2024-02-28 20:47:41.945061: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX2 AVX512F AVX512_VNNI FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2024-02-28 20:47:41.945063: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX2 AVX512F AVX512_VNNI FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2024-02-28 20:47:41.960872: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX2 AVX512F AVX512_VNNI FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2024-02-28 20:47:41.980750: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX2 AVX512F AVX512_VNNI FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2024-02-28 20:47:42.161791: I tensorflow/core/util/port.cc:104] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2024-02-28 20:47:42.161789: I tensorflow/core/util/port.cc:104] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2024-02-28 20:47:42.161790: I tensorflow/core/util/port.cc:104] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2024-02-28 20:47:42.188562: I tensorflow/core/util/port.cc:104] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2024-02-28 20:47:42.914412: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: :/usr/local/cuda-11.0/lib64:/usr/local/cuda-11.0/lib64
2024-02-28 20:47:42.914824: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: :/usr/local/cuda-11.0/lib64:/usr/local/cuda-11.0/lib64
2024-02-28 20:47:42.914834: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.
2024-02-28 20:47:42.959699: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: :/usr/local/cuda-11.0/lib64:/usr/local/cuda-11.0/lib64
2024-02-28 20:47:42.959798: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: :/usr/local/cuda-11.0/lib64:/usr/local/cuda-11.0/lib64
2024-02-28 20:47:42.959807: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.
2024-02-28 20:47:42.967992: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: :/usr/local/cuda-11.0/lib64:/usr/local/cuda-11.0/lib64
2024-02-28 20:47:42.968086: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: :/usr/local/cuda-11.0/lib64:/usr/local/cuda-11.0/lib64
2024-02-28 20:47:42.968095: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.
2024-02-28 20:47:43.042980: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: :/usr/local/cuda-11.0/lib64:/usr/local/cuda-11.0/lib64
2024-02-28 20:47:43.043082: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: :/usr/local/cuda-11.0/lib64:/usr/local/cuda-11.0/lib64
2024-02-28 20:47:43.043089: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.
xFormers not available
xFormers not available
xFormers not available
xFormers not available
xFormers not available
xFormers not available
xFormers not available
xFormers not available
You are using a model of type llama to instantiate a model of type locllm. This is not supported for all configurations of models and can yield errors.
You are using a model of type llama to instantiate a model of type locllm. This is not supported for all configurations of models and can yield errors.
You are using a model of type llama to instantiate a model of type locllm. This is not supported for all configurations of models and can yield errors.
You are using a model of type llama to instantiate a model of type locllm. This is not supported for all configurations of models and can yield errors.
dino init: _IncompatibleKeys(missing_keys=['blocks.0.attn.lora_A_v', 'blocks.0.attn.lora_B_v', 'blocks.0.attn.lora_A_q', 'blocks.0.attn.lora_B_q', 'blocks.1.attn.lora_A_v', 'blocks.1.attn.lora_B_v', 'blocks.1.attn.lora_A_q', 'blocks.1.attn.lora_B_q', 'blocks.2.attn.lora_A_v', 'blocks.2.attn.lora_B_v', 'blocks.2.attn.lora_A_q', 'blocks.2.attn.lora_B_q', 'blocks.3.attn.lora_A_v', 'blocks.3.attn.lora_B_v', 'blocks.3.attn.lora_A_q', 'blocks.3.attn.lora_B_q', 'blocks.4.attn.lora_A_v', 'blocks.4.attn.lora_B_v', 'blocks.4.attn.lora_A_q', 'blocks.4.attn.lora_B_q', 'blocks.5.attn.lora_A_v', 'blocks.5.attn.lora_B_v', 'blocks.5.attn.lora_A_q', 'blocks.5.attn.lora_B_q', 'blocks.6.attn.lora_A_v', 'blocks.6.attn.lora_B_v', 'blocks.6.attn.lora_A_q', 'blocks.6.attn.lora_B_q', 'blocks.7.attn.lora_A_v', 'blocks.7.attn.lora_B_v', 'blocks.7.attn.lora_A_q', 'blocks.7.attn.lora_B_q', 'blocks.8.attn.lora_A_v', 'blocks.8.attn.lora_B_v', 'blocks.8.attn.lora_A_q', 'blocks.8.attn.lora_B_q', 'blocks.9.attn.lora_A_v', 'blocks.9.attn.lora_B_v', 'blocks.9.attn.lora_A_q', 'blocks.9.attn.lora_B_q', 'blocks.10.attn.lora_A_v', 'blocks.10.attn.lora_B_v', 'blocks.10.attn.lora_A_q', 'blocks.10.attn.lora_B_q', 'blocks.11.attn.lora_A_v', 'blocks.11.attn.lora_B_v', 'blocks.11.attn.lora_A_q', 'blocks.11.attn.lora_B_q', 'blocks.12.attn.lora_A_v', 'blocks.12.attn.lora_B_v', 'blocks.12.attn.lora_A_q', 'blocks.12.attn.lora_B_q', 'blocks.13.attn.lora_A_v', 'blocks.13.attn.lora_B_v', 'blocks.13.attn.lora_A_q', 'blocks.13.attn.lora_B_q', 'blocks.14.attn.lora_A_v', 'blocks.14.attn.lora_B_v', 'blocks.14.attn.lora_A_q', 'blocks.14.attn.lora_B_q', 'blocks.15.attn.lora_A_v', 'blocks.15.attn.lora_B_v', 'blocks.15.attn.lora_A_q', 'blocks.15.attn.lora_B_q', 'blocks.16.attn.lora_A_v', 'blocks.16.attn.lora_B_v', 'blocks.16.attn.lora_A_q', 'blocks.16.attn.lora_B_q', 'blocks.17.attn.lora_A_v', 'blocks.17.attn.lora_B_v', 'blocks.17.attn.lora_A_q', 'blocks.17.attn.lora_B_q', 'blocks.18.attn.lora_A_v', 'blocks.18.attn.lora_B_v', 'blocks.18.attn.lora_A_q', 'blocks.18.attn.lora_B_q', 'blocks.19.attn.lora_A_v', 'blocks.19.attn.lora_B_v', 'blocks.19.attn.lora_A_q', 'blocks.19.attn.lora_B_q', 'blocks.20.attn.lora_A_v', 'blocks.20.attn.lora_B_v', 'blocks.20.attn.lora_A_q', 'blocks.20.attn.lora_B_q', 'blocks.21.attn.lora_A_v', 'blocks.21.attn.lora_B_v', 'blocks.21.attn.lora_A_q', 'blocks.21.attn.lora_B_q', 'blocks.22.attn.lora_A_v', 'blocks.22.attn.lora_B_v', 'blocks.22.attn.lora_A_q', 'blocks.22.attn.lora_B_q', 'blocks.23.attn.lora_A_v', 'blocks.23.attn.lora_B_v', 'blocks.23.attn.lora_A_q', 'blocks.23.attn.lora_B_q'], unexpected_keys=[])
dino init: _IncompatibleKeys(missing_keys=['blocks.0.attn.lora_A_v', 'blocks.0.attn.lora_B_v', 'blocks.0.attn.lora_A_q', 'blocks.0.attn.lora_B_q', 'blocks.1.attn.lora_A_v', 'blocks.1.attn.lora_B_v', 'blocks.1.attn.lora_A_q', 'blocks.1.attn.lora_B_q', 'blocks.2.attn.lora_A_v', 'blocks.2.attn.lora_B_v', 'blocks.2.attn.lora_A_q', 'blocks.2.attn.lora_B_q', 'blocks.3.attn.lora_A_v', 'blocks.3.attn.lora_B_v', 'blocks.3.attn.lora_A_q', 'blocks.3.attn.lora_B_q', 'blocks.4.attn.lora_A_v', 'blocks.4.attn.lora_B_v', 'blocks.4.attn.lora_A_q', 'blocks.4.attn.lora_B_q', 'blocks.5.attn.lora_A_v', 'blocks.5.attn.lora_B_v', 'blocks.5.attn.lora_A_q', 'blocks.5.attn.lora_B_q', 'blocks.6.attn.lora_A_v', 'blocks.6.attn.lora_B_v', 'blocks.6.attn.lora_A_q', 'blocks.6.attn.lora_B_q', 'blocks.7.attn.lora_A_v', 'blocks.7.attn.lora_B_v', 'blocks.7.attn.lora_A_q', 'blocks.7.attn.lora_B_q', 'blocks.8.attn.lora_A_v', 'blocks.8.attn.lora_B_v', 'blocks.8.attn.lora_A_q', 'blocks.8.attn.lora_B_q', 'blocks.9.attn.lora_A_v', 'blocks.9.attn.lora_B_v', 'blocks.9.attn.lora_A_q', 'blocks.9.attn.lora_B_q', 'blocks.10.attn.lora_A_v', 'blocks.10.attn.lora_B_v', 'blocks.10.attn.lora_A_q', 'blocks.10.attn.lora_B_q', 'blocks.11.attn.lora_A_v', 'blocks.11.attn.lora_B_v', 'blocks.11.attn.lora_A_q', 'blocks.11.attn.lora_B_q', 'blocks.12.attn.lora_A_v', 'blocks.12.attn.lora_B_v', 'blocks.12.attn.lora_A_q', 'blocks.12.attn.lora_B_q', 'blocks.13.attn.lora_A_v', 'blocks.13.attn.lora_B_v', 'blocks.13.attn.lora_A_q', 'blocks.13.attn.lora_B_q', 'blocks.14.attn.lora_A_v', 'blocks.14.attn.lora_B_v', 'blocks.14.attn.lora_A_q', 'blocks.14.attn.lora_B_q', 'blocks.15.attn.lora_A_v', 'blocks.15.attn.lora_B_v', 'blocks.15.attn.lora_A_q', 'blocks.15.attn.lora_B_q', 'blocks.16.attn.lora_A_v', 'blocks.16.attn.lora_B_v', 'blocks.16.attn.lora_A_q', 'blocks.16.attn.lora_B_q', 'blocks.17.attn.lora_A_v', 'blocks.17.attn.lora_B_v', 'blocks.17.attn.lora_A_q', 'blocks.17.attn.lora_B_q', 'blocks.18.attn.lora_A_v', 'blocks.18.attn.lora_B_v', 'blocks.18.attn.lora_A_q', 'blocks.18.attn.lora_B_q', 'blocks.19.attn.lora_A_v', 'blocks.19.attn.lora_B_v', 'blocks.19.attn.lora_A_q', 'blocks.19.attn.lora_B_q', 'blocks.20.attn.lora_A_v', 'blocks.20.attn.lora_B_v', 'blocks.20.attn.lora_A_q', 'blocks.20.attn.lora_B_q', 'blocks.21.attn.lora_A_v', 'blocks.21.attn.lora_B_v', 'blocks.21.attn.lora_A_q', 'blocks.21.attn.lora_B_q', 'blocks.22.attn.lora_A_v', 'blocks.22.attn.lora_B_v', 'blocks.22.attn.lora_A_q', 'blocks.22.attn.lora_B_q', 'blocks.23.attn.lora_A_v', 'blocks.23.attn.lora_B_v', 'blocks.23.attn.lora_A_q', 'blocks.23.attn.lora_B_q'], unexpected_keys=[])
dino init: _IncompatibleKeys(missing_keys=['blocks.0.attn.lora_A_v', 'blocks.0.attn.lora_B_v', 'blocks.0.attn.lora_A_q', 'blocks.0.attn.lora_B_q', 'blocks.1.attn.lora_A_v', 'blocks.1.attn.lora_B_v', 'blocks.1.attn.lora_A_q', 'blocks.1.attn.lora_B_q', 'blocks.2.attn.lora_A_v', 'blocks.2.attn.lora_B_v', 'blocks.2.attn.lora_A_q', 'blocks.2.attn.lora_B_q', 'blocks.3.attn.lora_A_v', 'blocks.3.attn.lora_B_v', 'blocks.3.attn.lora_A_q', 'blocks.3.attn.lora_B_q', 'blocks.4.attn.lora_A_v', 'blocks.4.attn.lora_B_v', 'blocks.4.attn.lora_A_q', 'blocks.4.attn.lora_B_q', 'blocks.5.attn.lora_A_v', 'blocks.5.attn.lora_B_v', 'blocks.5.attn.lora_A_q', 'blocks.5.attn.lora_B_q', 'blocks.6.attn.lora_A_v', 'blocks.6.attn.lora_B_v', 'blocks.6.attn.lora_A_q', 'blocks.6.attn.lora_B_q', 'blocks.7.attn.lora_A_v', 'blocks.7.attn.lora_B_v', 'blocks.7.attn.lora_A_q', 'blocks.7.attn.lora_B_q', 'blocks.8.attn.lora_A_v', 'blocks.8.attn.lora_B_v', 'blocks.8.attn.lora_A_q', 'blocks.8.attn.lora_B_q', 'blocks.9.attn.lora_A_v', 'blocks.9.attn.lora_B_v', 'blocks.9.attn.lora_A_q', 'blocks.9.attn.lora_B_q', 'blocks.10.attn.lora_A_v', 'blocks.10.attn.lora_B_v', 'blocks.10.attn.lora_A_q', 'blocks.10.attn.lora_B_q', 'blocks.11.attn.lora_A_v', 'blocks.11.attn.lora_B_v', 'blocks.11.attn.lora_A_q', 'blocks.11.attn.lora_B_q', 'blocks.12.attn.lora_A_v', 'blocks.12.attn.lora_B_v', 'blocks.12.attn.lora_A_q', 'blocks.12.attn.lora_B_q', 'blocks.13.attn.lora_A_v', 'blocks.13.attn.lora_B_v', 'blocks.13.attn.lora_A_q', 'blocks.13.attn.lora_B_q', 'blocks.14.attn.lora_A_v', 'blocks.14.attn.lora_B_v', 'blocks.14.attn.lora_A_q', 'blocks.14.attn.lora_B_q', 'blocks.15.attn.lora_A_v', 'blocks.15.attn.lora_B_v', 'blocks.15.attn.lora_A_q', 'blocks.15.attn.lora_B_q', 'blocks.16.attn.lora_A_v', 'blocks.16.attn.lora_B_v', 'blocks.16.attn.lora_A_q', 'blocks.16.attn.lora_B_q', 'blocks.17.attn.lora_A_v', 'blocks.17.attn.lora_B_v', 'blocks.17.attn.lora_A_q', 'blocks.17.attn.lora_B_q', 'blocks.18.attn.lora_A_v', 'blocks.18.attn.lora_B_v', 'blocks.18.attn.lora_A_q', 'blocks.18.attn.lora_B_q', 'blocks.19.attn.lora_A_v', 'blocks.19.attn.lora_B_v', 'blocks.19.attn.lora_A_q', 'blocks.19.attn.lora_B_q', 'blocks.20.attn.lora_A_v', 'blocks.20.attn.lora_B_v', 'blocks.20.attn.lora_A_q', 'blocks.20.attn.lora_B_q', 'blocks.21.attn.lora_A_v', 'blocks.21.attn.lora_B_v', 'blocks.21.attn.lora_A_q', 'blocks.21.attn.lora_B_q', 'blocks.22.attn.lora_A_v', 'blocks.22.attn.lora_B_v', 'blocks.22.attn.lora_A_q', 'blocks.22.attn.lora_B_q', 'blocks.23.attn.lora_A_v', 'blocks.23.attn.lora_B_v', 'blocks.23.attn.lora_A_q', 'blocks.23.attn.lora_B_q'], unexpected_keys=[])
dino init: _IncompatibleKeys(missing_keys=['blocks.0.attn.lora_A_v', 'blocks.0.attn.lora_B_v', 'blocks.0.attn.lora_A_q', 'blocks.0.attn.lora_B_q', 'blocks.1.attn.lora_A_v', 'blocks.1.attn.lora_B_v', 'blocks.1.attn.lora_A_q', 'blocks.1.attn.lora_B_q', 'blocks.2.attn.lora_A_v', 'blocks.2.attn.lora_B_v', 'blocks.2.attn.lora_A_q', 'blocks.2.attn.lora_B_q', 'blocks.3.attn.lora_A_v', 'blocks.3.attn.lora_B_v', 'blocks.3.attn.lora_A_q', 'blocks.3.attn.lora_B_q', 'blocks.4.attn.lora_A_v', 'blocks.4.attn.lora_B_v', 'blocks.4.attn.lora_A_q', 'blocks.4.attn.lora_B_q', 'blocks.5.attn.lora_A_v', 'blocks.5.attn.lora_B_v', 'blocks.5.attn.lora_A_q', 'blocks.5.attn.lora_B_q', 'blocks.6.attn.lora_A_v', 'blocks.6.attn.lora_B_v', 'blocks.6.attn.lora_A_q', 'blocks.6.attn.lora_B_q', 'blocks.7.attn.lora_A_v', 'blocks.7.attn.lora_B_v', 'blocks.7.attn.lora_A_q', 'blocks.7.attn.lora_B_q', 'blocks.8.attn.lora_A_v', 'blocks.8.attn.lora_B_v', 'blocks.8.attn.lora_A_q', 'blocks.8.attn.lora_B_q', 'blocks.9.attn.lora_A_v', 'blocks.9.attn.lora_B_v', 'blocks.9.attn.lora_A_q', 'blocks.9.attn.lora_B_q', 'blocks.10.attn.lora_A_v', 'blocks.10.attn.lora_B_v', 'blocks.10.attn.lora_A_q', 'blocks.10.attn.lora_B_q', 'blocks.11.attn.lora_A_v', 'blocks.11.attn.lora_B_v', 'blocks.11.attn.lora_A_q', 'blocks.11.attn.lora_B_q', 'blocks.12.attn.lora_A_v', 'blocks.12.attn.lora_B_v', 'blocks.12.attn.lora_A_q', 'blocks.12.attn.lora_B_q', 'blocks.13.attn.lora_A_v', 'blocks.13.attn.lora_B_v', 'blocks.13.attn.lora_A_q', 'blocks.13.attn.lora_B_q', 'blocks.14.attn.lora_A_v', 'blocks.14.attn.lora_B_v', 'blocks.14.attn.lora_A_q', 'blocks.14.attn.lora_B_q', 'blocks.15.attn.lora_A_v', 'blocks.15.attn.lora_B_v', 'blocks.15.attn.lora_A_q', 'blocks.15.attn.lora_B_q', 'blocks.16.attn.lora_A_v', 'blocks.16.attn.lora_B_v', 'blocks.16.attn.lora_A_q', 'blocks.16.attn.lora_B_q', 'blocks.17.attn.lora_A_v', 'blocks.17.attn.lora_B_v', 'blocks.17.attn.lora_A_q', 'blocks.17.attn.lora_B_q', 'blocks.18.attn.lora_A_v', 'blocks.18.attn.lora_B_v', 'blocks.18.attn.lora_A_q', 'blocks.18.attn.lora_B_q', 'blocks.19.attn.lora_A_v', 'blocks.19.attn.lora_B_v', 'blocks.19.attn.lora_A_q', 'blocks.19.attn.lora_B_q', 'blocks.20.attn.lora_A_v', 'blocks.20.attn.lora_B_v', 'blocks.20.attn.lora_A_q', 'blocks.20.attn.lora_B_q', 'blocks.21.attn.lora_A_v', 'blocks.21.attn.lora_B_v', 'blocks.21.attn.lora_A_q', 'blocks.21.attn.lora_B_q', 'blocks.22.attn.lora_A_v', 'blocks.22.attn.lora_B_v', 'blocks.22.attn.lora_A_q', 'blocks.22.attn.lora_B_q', 'blocks.23.attn.lora_A_v', 'blocks.23.attn.lora_B_v', 'blocks.23.attn.lora_A_q', 'blocks.23.attn.lora_B_q'], unexpected_keys=[])

Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:11<00:11, 11.03s/it]
Loading checkpoint shards:  50%|█████     | 1/2 [00:11<00:11, 11.44s/it]
Loading checkpoint shards:  50%|█████     | 1/2 [00:11<00:11, 11.69s/it]
Loading checkpoint shards:  50%|█████     | 1/2 [00:11<00:11, 11.78s/it]
Loading checkpoint shards: 100%|██████████| 2/2 [00:14<00:00,  6.77s/it]
Loading checkpoint shards: 100%|██████████| 2/2 [00:14<00:00,  7.41s/it]
Some weights of LocLLMModel were not initialized from the model checkpoint at ./checkpoints/model_weights/vicuna-7b-v1.5 and are newly initialized: ['vision_model.blocks.12.attn.qkv.weight', 'vision_model.blocks.13.norm1.bias', 'vision_model.blocks.10.ls1.gamma', 'vision_model.blocks.21.attn.lora_A_v', 'vision_model.blocks.12.attn.proj.weight', 'vision_model.blocks.23.attn.qkv.bias', 'vision_model.blocks.21.attn.qkv.weight', 'vision_model.pos_embed', 'model.layers.25.self_attn.v_proj.lora_A', 'vision_model.patch_embed.proj.weight', 'vision_model.blocks.18.norm1.bias', 'vision_model.blocks.3.norm2.bias', 'vision_model.blocks.8.mlp.fc1.bias', 'vision_model.blocks.20.norm2.weight', 'vision_model.blocks.6.mlp.fc1.weight', 'vision_model.blocks.17.attn.proj.bias', 'model.layers.21.self_attn.q_proj.lora_A', 'vision_model.blocks.13.attn.qkv.weight', 'model.layers.1.self_attn.q_proj.lora_A', 'vision_model.blocks.6.mlp.fc2.weight', 'vision_model.blocks.7.mlp.fc1.weight', 'vision_model.blocks.12.mlp.fc2.bias', 'vision_model.blocks.7.ls1.gamma', 'vision_model.blocks.21.mlp.fc1.weight', 'vision_model.blocks.19.ls1.gamma', 'vision_model.blocks.1.mlp.fc1.bias', 'vision_model.blocks.11.attn.qkv.weight', 'vision_model.blocks.21.mlp.fc2.bias', 'model.layers.18.self_attn.q_proj.lora_A', 'model.layers.22.self_attn.v_proj.lora_A', 'vision_model.blocks.1.ls1.gamma', 'vision_model.blocks.18.attn.qkv.bias', 'model.layers.20.self_attn.v_proj.lora_A', 'vision_model.blocks.9.attn.proj.weight', 'vision_model.blocks.5.attn.proj.weight', 'vision_model.blocks.11.ls1.gamma', 'model.layers.7.self_attn.q_proj.lora_B', 'vision_model.blocks.11.mlp.fc1.bias', 'vision_model.blocks.1.attn.lora_B_v', 'vision_model.blocks.7.attn.proj.weight', 'vision_model.blocks.20.mlp.fc2.weight', 'model.layers.24.self_attn.v_proj.lora_A', 'vision_model.blocks.11.mlp.fc2.weight', 'vision_model.blocks.1.attn.lora_B_q', 'vision_model.blocks.9.norm2.weight', 'vision_model.blocks.14.norm1.bias', 'model.layers.5.self_attn.v_proj.lora_B', 'vision_model.blocks.13.attn.lora_B_v', 'vision_model.blocks.3.attn.lora_B_q', 'model.layers.11.self_attn.v_proj.lora_B', 'vision_model.blocks.22.norm1.bias', 'vision_model.blocks.1.mlp.fc2.bias', 'vision_model.blocks.19.mlp.fc2.bias', 'vision_model.blocks.22.norm2.bias', 'model.layers.25.self_attn.q_proj.lora_B', 'vision_model.blocks.20.norm1.weight', 'model.layers.20.self_attn.v_proj.lora_B', 'vision_model.blocks.10.attn.lora_B_v', 'model.layers.23.self_attn.q_proj.lora_A', 'vision_model.blocks.0.attn.proj.weight', 'vision_model.blocks.1.attn.lora_A_v', 'vision_model.blocks.13.mlp.fc1.bias', 'vision_model.blocks.6.mlp.fc2.bias', 'model.layers.3.self_attn.q_proj.lora_A', 'vision_model.blocks.21.norm1.bias', 'vision_model.blocks.2.attn.proj.weight', 'vision_model.blocks.11.attn.lora_A_q', 'vision_model.blocks.14.mlp.fc2.weight', 'vision_model.blocks.6.attn.proj.bias', 'vision_model.blocks.16.ls2.gamma', 'model.layers.0.self_attn.q_proj.lora_B', 'vision_model.blocks.8.norm2.bias', 'vision_model.blocks.13.norm1.weight', 'vision_model.blocks.9.mlp.fc1.weight', 'model.layers.6.self_attn.v_proj.lora_A', 'vision_model.blocks.14.mlp.fc1.weight', 'vision_model.blocks.13.attn.proj.bias', 'model.layers.10.self_attn.v_proj.lora_A', 'vision_model.blocks.20.mlp.fc2.bias', 'model.layers.4.self_attn.q_proj.lora_B', 'vision_model.blocks.1.norm1.weight', 'vision_model.blocks.3.attn.lora_A_v', 'model.layers.19.self_attn.q_proj.lora_B', 'model.layers.12.self_attn.v_proj.lora_B', 'vision_model.blocks.19.attn.proj.bias', 'vision_model.blocks.21.ls1.gamma', 'model.layers.21.self_attn.q_proj.lora_B', 'vision_model.blocks.5.ls2.gamma', 'model.layers.18.self_attn.v_proj.lora_A', 'model.layers.17.self_attn.v_proj.lora_B', 'vision_model.blocks.9.ls1.gamma', 'vision_model.blocks.21.mlp.fc1.bias', 'model.layers.13.self_attn.v_proj.lora_B', 'vision_model.blocks.14.attn.lora_B_q', 'vision_model.blocks.14.ls1.gamma', 'vision_model.blocks.19.attn.lora_B_q', 'vision_model.blocks.12.attn.lora_B_q', 'vision_model.blocks.16.attn.lora_A_v', 'vision_model.blocks.13.ls1.gamma', 'vision_model.blocks.0.ls2.gamma', 'vision_model.blocks.13.attn.qkv.bias', 'vision_model.blocks.7.norm1.bias', 'vision_model.blocks.2.norm2.weight', 'vision_model.blocks.18.norm2.bias', 'vision_model.blocks.4.mlp.fc1.weight', 'model.layers.26.self_attn.v_proj.lora_A', 'vision_model.blocks.23.mlp.fc2.bias', 'vision_model.blocks.10.attn.lora_A_q', 'vision_model.blocks.2.norm1.bias', 'vision_model.blocks.3.attn.lora_B_v', 'vision_model.blocks.10.norm1.bias', 'vision_model.blocks.19.ls2.gamma', 'vision_model.blocks.17.mlp.fc2.weight', 'vision_model.blocks.21.norm2.bias', 'vision_model.blocks.15.mlp.fc2.weight', 'vision_model.blocks.3.attn.proj.weight', 'vision_model.blocks.14.attn.lora_B_v', 'vision_model.blocks.12.norm2.weight', 'vision_model.blocks.22.attn.proj.weight', 'vision_model.blocks.20.attn.lora_B_q', 'vision_model.blocks.0.mlp.fc1.bias', 'model.layers.11.self_attn.v_proj.lora_A', 'vision_model.blocks.23.ls2.gamma', 'model.layers.17.self_attn.q_proj.lora_A', 'model.layers.27.self_attn.q_proj.lora_A', 'vision_model.blocks.2.attn.lora_A_v', 'vision_model.blocks.5.norm2.bias', 'model.layers.23.self_attn.v_proj.lora_B', 'vision_model.blocks.5.attn.lora_B_q', 'model.layers.1.self_attn.q_proj.lora_B', 'model.layers.23.self_attn.v_proj.lora_A', 'vision_model.blocks.8.attn.proj.bias', 'model.layers.17.self_attn.q_proj.lora_B', 'vision_model.blocks.10.norm1.weight', 'vision_model.blocks.11.norm2.weight', 'model.layers.29.self_attn.v_proj.lora_A', 'vision_model.blocks.23.mlp.fc2.weight', 'vision_model.blocks.16.attn.lora_A_q', 'model.layers.28.self_attn.q_proj.lora_A', 'vision_model.blocks.11.mlp.fc1.weight', 'vision_model.blocks.1.norm2.bias', 'vision_model.blocks.21.mlp.fc2.weight', 'model.layers.30.self_attn.q_proj.lora_A', 'vision_model.blocks.16.norm1.bias', 'vision_model.blocks.5.norm1.bias', 'vision_model.blocks.18.attn.proj.weight', 'vision_model.blocks.14.norm2.weight', 'model.layers.6.self_attn.v_proj.lora_B', 'vision_model.blocks.1.norm1.bias', 'vision_model.blocks.23.mlp.fc1.weight', 'vision_model.blocks.2.ls2.gamma', 'vision_model.blocks.3.norm1.bias', 'vision_model.blocks.17.attn.lora_A_v', 'model.layers.8.self_attn.v_proj.lora_B', 'vision_model.blocks.17.norm1.weight', 'model.layers.5.self_attn.q_proj.lora_B', 'vision_model.blocks.15.ls1.gamma', 'vision_model.blocks.23.attn.lora_A_v', 'vision_model.blocks.19.mlp.fc1.bias', 'model.layers.8.self_attn.q_proj.lora_B', 'vision_model.blocks.17.norm1.bias', 'model.layers.24.self_attn.q_proj.lora_A', 'vision_model.blocks.20.mlp.fc1.weight', 'vision_model.blocks.6.norm1.weight', 'vision_model.blocks.15.attn.proj.weight', 'model.layers.27.self_attn.v_proj.lora_A', 'vision_model.blocks.6.ls2.gamma', 'vision_model.blocks.22.attn.lora_A_q', 'model.layers.7.self_attn.v_proj.lora_A', 'vision_model.blocks.11.norm1.weight', 'vision_model.blocks.9.norm1.weight', 'vision_model.blocks.9.attn.qkv.bias', 'vision_model.blocks.8.mlp.fc2.bias', 'vision_model.blocks.1.attn.proj.bias', 'vision_model.blocks.4.attn.lora_A_v', 'vision_model.blocks.18.mlp.fc2.weight', 'vision_model.blocks.12.attn.lora_A_v', 'vision_model.blocks.23.norm2.bias', 'vision_model.blocks.9.mlp.fc1.bias', 'vision_model.blocks.1.attn.qkv.weight', 'vision_model.blocks.9.mlp.fc2.bias', 'vision_model.blocks.18.attn.proj.bias', 'vision_model.blocks.11.norm2.bias', 'vision_model.blocks.0.attn.lora_B_q', 'vision_model.blocks.18.mlp.fc1.bias', 'vision_model.blocks.15.attn.qkv.weight', 'vision_model.blocks.18.norm1.weight', 'vision_model.blocks.23.norm1.weight', 'vision_model.blocks.13.mlp.fc1.weight', 'model.layers.31.self_attn.v_proj.lora_A', 'vision_model.blocks.8.norm2.weight', 'vision_model.blocks.7.attn.lora_A_v', 'model.layers.11.self_attn.q_proj.lora_B', 'vision_model.blocks.16.attn.lora_B_v', 'vision_model.blocks.14.attn.proj.bias', 'vision_model.blocks.13.norm2.weight', 'vision_model.blocks.0.norm2.weight', 'model.layers.11.self_attn.q_proj.lora_A', 'model.layers.14.self_attn.v_proj.lora_B', 'model.layers.26.self_attn.v_proj.lora_B', 'model.layers.13.self_attn.v_proj.lora_A', 'vision_model.blocks.13.norm2.bias', 'model.layers.4.self_attn.q_proj.lora_A', 'vision_model.blocks.21.attn.proj.weight', 'model.layers.29.self_attn.q_proj.lora_A', 'model.layers.1.self_attn.v_proj.lora_B', 'vision_model.blocks.23.norm2.weight', 'vision_model.blocks.2.norm1.weight', 'vision_model.blocks.1.attn.qkv.bias', 'model.layers.20.self_attn.q_proj.lora_B', 'vision_model.blocks.8.mlp.fc1.weight', 'model.layers.2.self_attn.q_proj.lora_B', 'vision_model.blocks.5.mlp.fc2.weight', 'vision_model.blocks.2.norm2.bias', 'vision_model.blocks.7.attn.lora_B_q', 'model.layers.9.self_attn.q_proj.lora_A', 'model.layers.28.self_attn.q_proj.lora_B', 'vision_model.blocks.6.norm1.bias', 'vision_model.blocks.20.ls2.gamma', 'vision_model.blocks.16.norm2.bias', 'vision_model.blocks.3.ls1.gamma', 'model.layers.4.self_attn.v_proj.lora_A', 'model.layers.23.self_attn.q_proj.lora_B', 'vision_model.blocks.23.attn.lora_B_v', 'vision_model.blocks.20.norm1.bias', 'vision_model.blocks.12.mlp.fc1.bias', 'vision_model.blocks.13.mlp.fc2.weight', 'vision_model.blocks.15.mlp.fc2.bias', 'vision_model.blocks.0.mlp.fc2.bias', 'vision_model.blocks.9.attn.lora_A_q', 'vision_model.blocks.11.attn.lora_B_v', 'model.layers.18.self_attn.v_proj.lora_B', 'model.layers.0.self_attn.q_proj.lora_A', 'vision_model.blocks.4.attn.proj.weight', 'vision_model.blocks.14.mlp.fc2.bias', 'vision_model.blocks.2.attn.lora_B_q', 'vision_model.blocks.8.ls1.gamma', 'model.layers.14.self_attn.v_proj.lora_A', 'model.layers.15.self_attn.q_proj.lora_B', 'vision_model.blocks.6.norm2.bias', 'vision_model.blocks.8.mlp.fc2.weight', 'vision_model.blocks.17.mlp.fc1.weight', 'vision_model.blocks.15.norm2.bias', 'vision_model.blocks.8.attn.lora_B_q', 'vision_model.blocks.2.mlp.fc2.bias', 'vision_model.blocks.8.norm1.bias', 'vision_model.blocks.21.attn.lora_B_q', 'vision_model.blocks.9.attn.lora_B_q', 'vision_model.blocks.3.mlp.fc2.weight', 'model.layers.16.self_attn.v_proj.lora_B', 'vision_model.blocks.20.attn.lora_A_q', 'vision_model.blocks.7.attn.proj.bias', 'vision_model.blocks.20.attn.lora_A_v', 'vision_model.blocks.15.norm1.bias', 'vision_model.blocks.20.mlp.fc1.bias', 'model.layers.26.self_attn.q_proj.lora_B', 'vision_model.blocks.19.norm1.weight', 'vision_model.blocks.6.mlp.fc1.bias', 'vision_model.blocks.22.mlp.fc1.bias', 'vision_model.blocks.1.attn.proj.weight', 'vision_model.blocks.18.attn.lora_B_v', 'vision_model.blocks.9.attn.proj.bias', 'vision_model.blocks.21.attn.lora_A_q', 'vision_model.blocks.16.mlp.fc2.weight', 'vision_model.blocks.12.attn.lora_A_q', 'model.layers.3.self_attn.v_proj.lora_A', 'vision_model.norm.weight', 'vision_model.blocks.5.attn.proj.bias', 'vision_model.blocks.10.attn.proj.bias', 'model.layers.27.self_attn.v_proj.lora_B', 'vision_model.blocks.23.attn.proj.bias', 'vision_model.blocks.4.attn.qkv.weight', 'vision_model.blocks.1.ls2.gamma', 'model.layers.12.self_attn.q_proj.lora_B', 'vision_model.blocks.20.attn.proj.bias', 'vision_model.blocks.11.attn.proj.bias', 'vision_model.blocks.0.mlp.fc2.weight', 'vision_model.blocks.5.attn.lora_A_q', 'vision_model.blocks.13.attn.proj.weight', 'model.layers.10.self_attn.q_proj.lora_B', 'vision_model.blocks.10.mlp.fc2.bias', 'vision_model.blocks.10.norm2.weight', 'vision_model.blocks.19.norm1.bias', 'vision_model.blocks.18.norm2.weight', 'model.layers.8.self_attn.q_proj.lora_A', 'vision_model.blocks.11.attn.lora_B_q', 'vision_model.blocks.21.attn.lora_B_v', 'vision_model.blocks.7.mlp.fc2.weight', 'vision_model.blocks.17.attn.qkv.bias', 'vision_model.blocks.9.attn.lora_B_v', 'vision_model.blocks.15.attn.lora_A_v', 'vision_model.blocks.21.norm2.weight', 'vision_model.blocks.3.mlp.fc2.bias', 'vision_model.blocks.16.attn.qkv.bias', 'vision_model.blocks.19.attn.qkv.bias', 'vision_model.blocks.7.ls2.gamma', 'vision_model.blocks.2.mlp.fc1.weight', 'vision_model.blocks.7.norm2.bias', 'model.layers.24.self_attn.q_proj.lora_B', 'vision_model.blocks.8.attn.qkv.bias', 'vision_model.blocks.16.mlp.fc1.weight', 'vision_model.blocks.9.attn.qkv.weight', 'vision_model.blocks.0.norm1.bias', 'model.layers.31.self_attn.q_proj.lora_A', 'vision_model.blocks.5.mlp.fc1.weight', 'model.layers.20.self_attn.q_proj.lora_A', 'vision_model.blocks.23.mlp.fc1.bias', 'vision_model.blocks.5.attn.qkv.bias', 'vision_model.blocks.3.mlp.fc1.bias', 'vision_model.blocks.13.attn.lora_A_q', 'vision_model.blocks.11.mlp.fc2.bias', 'vision_model.blocks.22.attn.qkv.weight', 'vision_model.blocks.13.attn.lora_B_q', 'vision_model.blocks.14.attn.qkv.weight', 'vision_model.blocks.22.attn.proj.bias', 'vision_model.blocks.3.attn.proj.bias', 'vision_model.blocks.15.mlp.fc1.bias', 'vision_model.blocks.16.norm1.weight', 'model.layers.21.self_attn.v_proj.lora_A', 'vision_model.blocks.1.attn.lora_A_q', 'model.layers.22.self_attn.v_proj.lora_B', 'vision_model.blocks.11.attn.proj.weight', 'vision_model.blocks.6.attn.proj.weight', 'vision_model.blocks.9.attn.lora_A_v', 'vision_model.blocks.19.norm2.weight', 'vision_model.blocks.20.ls1.gamma', 'vision_model.blocks.11.ls2.gamma', 'vision_model.blocks.20.norm2.bias', 'vision_model.blocks.16.mlp.fc2.bias', 'vision_model.blocks.6.attn.qkv.bias', 'vision_model.blocks.19.mlp.fc1.weight', 'vision_model.blocks.15.norm1.weight', 'model.layers.24.self_attn.v_proj.lora_B', 'model.layers.9.self_attn.q_proj.lora_B', 'vision_model.blocks.0.ls1.gamma', 'vision_model.blocks.14.mlp.fc1.bias', 'model.layers.12.self_attn.v_proj.lora_A', 'vision_model.blocks.3.norm1.weight', 'vision_model.blocks.16.ls1.gamma', 'vision_model.blocks.0.mlp.fc1.weight', 'vision_model.blocks.10.attn.lora_B_q', 'vision_model.blocks.2.attn.qkv.bias', 'vision_model.blocks.12.attn.qkv.bias', 'vision_model.blocks.16.attn.proj.weight', 'vision_model.blocks.6.attn.qkv.weight', 'vision_model.blocks.12.ls2.gamma', 'model.layers.2.self_attn.q_proj.lora_A', 'vision_model.blocks.2.ls1.gamma', 'vision_model.blocks.15.mlp.fc1.weight', 'vision_model.blocks.14.norm1.weight', 'vision_model.blocks.18.attn.lora_A_v', 'vision_model.blocks.19.attn.lora_B_v', 'vision_model.blocks.22.mlp.fc2.weight', 'vision_model.blocks.5.attn.lora_A_v', 'vision_model.blocks.15.norm2.weight', 'vision_model.blocks.18.mlp.fc2.bias', 'model.layers.16.self_attn.q_proj.lora_A', 'vision_model.blocks.18.ls2.gamma', 'vision_model.blocks.4.mlp.fc1.bias', 'model.layers.3.self_attn.v_proj.lora_B', 'vision_model.blocks.6.attn.lora_B_v', 'vision_model.blocks.23.attn.proj.weight', 'vision_model.blocks.13.mlp.fc2.bias', 'model.layers.22.self_attn.q_proj.lora_B', 'vision_model.blocks.20.attn.qkv.weight', 'vision_model.blocks.10.mlp.fc2.weight', 'model.layers.31.self_attn.q_proj.lora_B', 'vision_model.blocks.17.attn.lora_B_v', 'model.layers.21.self_attn.v_proj.lora_B', 'vision_model.blocks.22.ls2.gamma', 'vision_model.blocks.12.mlp.fc2.weight', 'model.layers.29.self_attn.q_proj.lora_B', 'vision_model.blocks.23.ls1.gamma', 'vision_model.blocks.4.attn.proj.bias', 'vision_model.blocks.10.attn.qkv.weight', 'model.layers.22.self_attn.q_proj.lora_A', 'vision_model.blocks.4.attn.lora_B_q', 'vision_model.blocks.4.norm2.bias', 'vision_model.blocks.3.attn.lora_A_q', 'vision_model.blocks.5.norm1.weight', 'vision_model.blocks.6.ls1.gamma', 'vision_model.blocks.4.attn.lora_B_v', 'vision_model.blocks.2.attn.lora_B_v', 'model.layers.16.self_attn.q_proj.lora_B', 'vision_model.blocks.17.mlp.fc1.bias', 'vision_model.blocks.14.ls2.gamma', 'vision_model.blocks.21.attn.qkv.bias', 'vision_model.blocks.4.attn.lora_A_q', 'vision_model.blocks.9.ls2.gamma', 'vision_model.blocks.6.norm2.weight', 'vision_model.blocks.19.attn.lora_A_v', 'vision_model.blocks.0.norm1.weight', 'vision_model.blocks.15.attn.lora_B_q', 'model.layers.29.self_attn.v_proj.lora_B', 'model.layers.13.self_attn.q_proj.lora_A', 'vision_model.blocks.3.ls2.gamma', 'vision_model.blocks.10.attn.lora_A_v', 'vision_model.blocks.13.ls2.gamma', 'vision_model.blocks.4.ls2.gamma', 'vision_model.blocks.19.mlp.fc2.weight', 'vision_model.blocks.17.attn.lora_B_q', 'model.layers.10.self_attn.q_proj.lora_A', 'vision_model.blocks.18.ls1.gamma', 'model.layers.15.self_attn.v_proj.lora_B', 'vision_model.blocks.21.attn.proj.bias', 'vision_model.blocks.7.mlp.fc2.bias', 'model.layers.17.self_attn.v_proj.lora_A', 'model.layers.5.self_attn.q_proj.lora_A', 'vision_model.blocks.6.attn.lora_A_q', 'model.layers.0.self_attn.v_proj.lora_B', 'vision_model.blocks.22.attn.qkv.bias', 'model.layers.6.self_attn.q_proj.lora_A', 'model.layers.13.self_attn.q_proj.lora_B', 'vision_model.mask_token', 'model.layers.9.self_attn.v_proj.lora_B', 'vision_model.blocks.8.ls2.gamma', 'vision_model.blocks.17.attn.lora_A_q', 'vision_model.blocks.8.attn.lora_A_q', 'vision_model.blocks.7.norm2.weight', 'vision_model.blocks.17.mlp.fc2.bias', 'model.layers.16.self_attn.v_proj.lora_A', 'vision_model.blocks.15.attn.lora_A_q', 'mm_projector.weight', 'vision_model.blocks.12.norm1.bias', 'vision_model.blocks.1.norm2.weight', 'vision_model.blocks.5.mlp.fc2.bias', 'vision_model.blocks.0.attn.qkv.weight', 'vision_model.blocks.7.norm1.weight', 'model.layers.19.self_attn.v_proj.lora_A', 'vision_model.blocks.19.attn.qkv.weight', 'vision_model.blocks.12.ls1.gamma', 'vision_model.blocks.3.norm2.weight', 'model.layers.1.self_attn.v_proj.lora_A', 'vision_model.blocks.4.ls1.gamma', 'vision_model.blocks.10.attn.proj.weight', 'model.layers.7.self_attn.q_proj.lora_A', 'vision_model.blocks.17.norm2.bias', 'model.layers.18.self_attn.q_proj.lora_B', 'vision_model.blocks.16.attn.lora_B_q', 'vision_model.blocks.14.attn.lora_A_q', 'model.layers.3.self_attn.q_proj.lora_B', 'vision_model.blocks.8.attn.lora_B_v', 'vision_model.blocks.14.attn.lora_A_v', 'vision_model.blocks.3.attn.qkv.weight', 'vision_model.blocks.23.attn.qkv.weight', 'vision_model.blocks.8.norm1.weight', 'vision_model.blocks.10.mlp.fc1.bias', 'vision_model.blocks.18.attn.lora_A_q', 'model.layers.25.self_attn.v_proj.lora_B', 'vision_model.blocks.0.attn.lora_B_v', 'vision_model.blocks.4.norm1.bias', 'model.layers.9.self_attn.v_proj.lora_A', 'vision_model.blocks.12.attn.proj.bias', 'vision_model.blocks.19.norm2.bias', 'vision_model.blocks.2.attn.lora_A_q', 'vision_model.blocks.6.attn.lora_B_q', 'vision_model.blocks.10.ls2.gamma', 'model.layers.7.self_attn.v_proj.lora_B', 'vision_model.blocks.17.attn.qkv.weight', 'vision_model.blocks.0.attn.lora_A_q', 'vision_model.blocks.0.attn.lora_A_v', 'vision_model.blocks.11.norm1.bias', 'vision_model.blocks.1.mlp.fc1.weight', 'vision_model.blocks.23.attn.lora_A_q', 'vision_model.cls_token', 'vision_model.blocks.20.attn.qkv.bias', 'vision_model.blocks.1.mlp.fc2.weight', 'vision_model.blocks.7.attn.qkv.bias', 'model.layers.30.self_attn.v_proj.lora_A', 'vision_model.blocks.21.ls2.gamma', 'vision_model.blocks.13.attn.lora_A_v', 'vision_model.blocks.4.mlp.fc2.weight', 'vision_model.blocks.17.norm2.weight', 'vision_model.blocks.7.attn.lora_B_v', 'vision_model.blocks.22.attn.lora_B_q', 'vision_model.blocks.20.attn.lora_B_v', 'model.layers.26.self_attn.q_proj.lora_A', 'vision_model.blocks.16.attn.proj.bias', 'vision_model.blocks.12.attn.lora_B_v', 'vision_model.blocks.7.attn.lora_A_q', 'vision_model.blocks.17.ls2.gamma', 'vision_model.patch_embed.proj.bias', 'model.layers.2.self_attn.v_proj.lora_B', 'vision_model.blocks.0.attn.qkv.bias', 'vision_model.blocks.2.mlp.fc2.weight', 'model.layers.12.self_attn.q_proj.lora_A', 'vision_model.blocks.2.mlp.fc1.bias', 'model.layers.28.self_attn.v_proj.lora_A', 'vision_model.blocks.22.mlp.fc2.bias', 'model.layers.27.self_attn.q_proj.lora_B', 'model.layers.19.self_attn.q_proj.lora_A', 'model.layers.19.self_attn.v_proj.lora_B', 'vision_model.blocks.17.ls1.gamma', 'model.layers.30.self_attn.v_proj.lora_B', 'vision_model.blocks.4.attn.qkv.bias', 'vision_model.norm.bias', 'vision_model.blocks.7.attn.qkv.weight', 'vision_model.blocks.6.attn.lora_A_v', 'vision_model.blocks.18.mlp.fc1.weight', 'vision_model.blocks.10.norm2.bias', 'model.layers.4.self_attn.v_proj.lora_B', 'vision_model.blocks.8.attn.lora_A_v', 'vision_model.blocks.5.ls1.gamma', 'vision_model.blocks.19.attn.proj.weight', 'vision_model.blocks.9.norm2.bias', 'vision_model.blocks.5.mlp.fc1.bias', 'mm_projector.bias', 'vision_model.blocks.15.attn.lora_B_v', 'vision_model.blocks.22.attn.lora_B_v', 'vision_model.blocks.22.attn.lora_A_v', 'model.layers.2.self_attn.v_proj.lora_A', 'vision_model.blocks.3.attn.qkv.bias', 'vision_model.blocks.17.attn.proj.weight', 'vision_model.blocks.12.norm2.bias', 'vision_model.blocks.3.mlp.fc1.weight', 'vision_model.blocks.4.mlp.fc2.bias', 'model.layers.8.self_attn.v_proj.lora_A', 'vision_model.blocks.18.attn.lora_B_q', 'vision_model.blocks.4.norm2.weight', 'vision_model.blocks.22.ls1.gamma', 'vision_model.blocks.15.attn.proj.bias', 'model.layers.30.self_attn.q_proj.lora_B', 'vision_model.blocks.22.norm2.weight', 'vision_model.blocks.14.attn.proj.weight', 'model.layers.5.self_attn.v_proj.lora_A', 'vision_model.blocks.9.norm1.bias', 'vision_model.blocks.16.mlp.fc1.bias', 'vision_model.blocks.0.norm2.bias', 'model.layers.31.self_attn.v_proj.lora_B', 'model.layers.25.self_attn.q_proj.lora_A', 'vision_model.blocks.5.attn.lora_B_v', 'vision_model.blocks.8.attn.proj.weight', 'vision_model.blocks.15.attn.qkv.bias', 'vision_model.blocks.8.attn.qkv.weight', 'vision_model.blocks.12.norm1.weight', 'model.layers.10.self_attn.v_proj.lora_B', 'vision_model.blocks.16.norm2.weight', 'vision_model.blocks.22.mlp.fc1.weight', 'model.layers.0.self_attn.v_proj.lora_A', 'vision_model.blocks.0.attn.proj.bias', 'vision_model.blocks.2.attn.qkv.weight', 'vision_model.blocks.21.norm1.weight', 'vision_model.blocks.18.attn.qkv.weight', 'vision_model.blocks.2.attn.proj.bias', 'vision_model.blocks.10.mlp.fc1.weight', 'model.layers.15.self_attn.q_proj.lora_A', 'vision_model.blocks.5.norm2.weight', 'vision_model.blocks.7.mlp.fc1.bias', 'vision_model.blocks.11.attn.qkv.bias', 'vision_model.blocks.10.attn.qkv.bias', 'vision_model.blocks.14.attn.qkv.bias', 'vision_model.blocks.15.ls2.gamma', 'vision_model.blocks.23.norm1.bias', 'model.layers.6.self_attn.q_proj.lora_B', 'vision_model.blocks.19.attn.lora_A_q', 'vision_model.blocks.20.attn.proj.weight', 'vision_model.blocks.22.norm1.weight', 'vision_model.blocks.9.mlp.fc2.weight', 'model.layers.28.self_attn.v_proj.lora_B', 'vision_model.blocks.23.attn.lora_B_q', 'model.layers.14.self_attn.q_proj.lora_A', 'vision_model.blocks.5.attn.qkv.weight', 'vision_model.blocks.16.attn.qkv.weight', 'vision_model.blocks.14.norm2.bias', 'vision_model.blocks.11.attn.lora_A_v', 'vision_model.blocks.12.mlp.fc1.weight', 'model.layers.15.self_attn.v_proj.lora_A', 'vision_model.blocks.4.norm1.weight', 'model.layers.14.self_attn.q_proj.lora_B']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.

Loading checkpoint shards: 100%|██████████| 2/2 [00:14<00:00,  6.80s/it]
Loading checkpoint shards: 100%|██████████| 2/2 [00:14<00:00,  7.49s/it]
Some weights of LocLLMModel were not initialized from the model checkpoint at ./checkpoints/model_weights/vicuna-7b-v1.5 and are newly initialized: ['vision_model.blocks.22.attn.lora_A_q', 'vision_model.blocks.23.attn.proj.weight', 'model.layers.11.self_attn.v_proj.lora_A', 'vision_model.blocks.3.norm2.bias', 'model.layers.21.self_attn.v_proj.lora_A', 'vision_model.blocks.20.mlp.fc1.weight', 'vision_model.pos_embed', 'vision_model.blocks.13.norm2.weight', 'model.layers.26.self_attn.v_proj.lora_A', 'model.layers.31.self_attn.q_proj.lora_A', 'vision_model.blocks.12.attn.qkv.bias', 'model.layers.10.self_attn.v_proj.lora_A', 'vision_model.blocks.4.attn.lora_B_q', 'vision_model.blocks.17.norm2.bias', 'vision_model.blocks.9.attn.proj.bias', 'vision_model.blocks.7.norm1.weight', 'vision_model.blocks.11.norm1.weight', 'model.layers.1.self_attn.v_proj.lora_A', 'vision_model.blocks.5.mlp.fc1.weight', 'vision_model.blocks.3.norm2.weight', 'vision_model.blocks.18.mlp.fc2.weight', 'vision_model.blocks.12.attn.lora_B_v', 'vision_model.blocks.11.attn.qkv.weight', 'vision_model.blocks.2.attn.qkv.bias', 'model.layers.1.self_attn.q_proj.lora_B', 'model.layers.20.self_attn.v_proj.lora_B', 'model.layers.30.self_attn.v_proj.lora_B', 'vision_model.blocks.15.norm1.bias', 'vision_model.blocks.11.attn.proj.bias', 'vision_model.blocks.23.norm1.bias', 'vision_model.blocks.17.attn.proj.bias', 'model.layers.24.self_attn.q_proj.lora_B', 'model.layers.3.self_attn.q_proj.lora_B', 'vision_model.blocks.7.norm2.bias', 'model.layers.22.self_attn.q_proj.lora_A', 'vision_model.blocks.17.attn.qkv.weight', 'vision_model.blocks.9.attn.qkv.weight', 'vision_model.blocks.12.norm2.weight', 'vision_model.blocks.15.attn.proj.bias', 'vision_model.blocks.18.attn.qkv.weight', 'vision_model.blocks.20.attn.lora_B_v', 'vision_model.blocks.23.mlp.fc1.bias', 'model.layers.6.self_attn.v_proj.lora_A', 'vision_model.blocks.7.attn.proj.bias', 'vision_model.blocks.9.attn.lora_A_q', 'vision_model.blocks.16.attn.lora_A_v', 'vision_model.blocks.15.norm2.bias', 'model.layers.27.self_attn.v_proj.lora_B', 'vision_model.blocks.18.mlp.fc1.bias', 'model.layers.17.self_attn.q_proj.lora_B', 'vision_model.blocks.0.norm1.bias', 'vision_model.blocks.2.norm1.weight', 'model.layers.0.self_attn.q_proj.lora_A', 'vision_model.blocks.3.attn.qkv.weight', 'vision_model.blocks.10.attn.qkv.weight', 'vision_model.blocks.13.norm1.bias', 'vision_model.blocks.7.attn.qkv.weight', 'model.layers.19.self_attn.q_proj.lora_B', 'vision_model.blocks.19.ls2.gamma', 'vision_model.blocks.4.mlp.fc1.weight', 'vision_model.blocks.15.ls2.gamma', 'vision_model.blocks.7.attn.lora_A_v', 'model.layers.11.self_attn.q_proj.lora_A', 'model.layers.4.self_attn.v_proj.lora_A', 'vision_model.blocks.11.attn.lora_A_q', 'vision_model.blocks.18.ls2.gamma', 'vision_model.blocks.6.norm1.bias', 'vision_model.blocks.3.attn.lora_B_v', 'model.layers.27.self_attn.v_proj.lora_A', 'model.layers.5.self_attn.q_proj.lora_B', 'vision_model.blocks.18.mlp.fc2.bias', 'model.layers.23.self_attn.v_proj.lora_A', 'vision_model.blocks.13.attn.lora_B_v', 'vision_model.blocks.6.attn.proj.bias', 'vision_model.blocks.19.attn.qkv.bias', 'vision_model.blocks.4.ls2.gamma', 'vision_model.norm.weight', 'vision_model.blocks.6.mlp.fc1.weight', 'model.layers.7.self_attn.q_proj.lora_B', 'model.layers.11.self_attn.q_proj.lora_B', 'model.layers.23.self_attn.q_proj.lora_B', 'model.layers.2.self_attn.q_proj.lora_A', 'vision_model.blocks.15.attn.lora_B_v', 'vision_model.blocks.16.attn.lora_B_q', 'vision_model.blocks.0.norm1.weight', 'vision_model.blocks.14.ls2.gamma', 'vision_model.blocks.8.norm1.bias', 'model.layers.12.self_attn.q_proj.lora_A', 'vision_model.blocks.19.ls1.gamma', 'vision_model.blocks.8.ls1.gamma', 'model.layers.12.self_attn.q_proj.lora_B', 'vision_model.blocks.15.mlp.fc1.bias', 'vision_model.blocks.22.ls1.gamma', 'vision_model.blocks.23.attn.lora_A_v', 'vision_model.blocks.1.mlp.fc2.weight', 'vision_model.blocks.1.attn.proj.bias', 'model.layers.0.self_attn.v_proj.lora_B', 'model.layers.28.self_attn.q_proj.lora_A', 'model.layers.17.self_attn.v_proj.lora_A', 'model.layers.24.self_attn.q_proj.lora_A', 'vision_model.blocks.18.attn.proj.bias', 'vision_model.blocks.1.mlp.fc1.bias', 'vision_model.blocks.5.mlp.fc2.weight', 'model.layers.31.self_attn.v_proj.lora_A', 'vision_model.blocks.22.attn.lora_A_v', 'vision_model.blocks.23.norm2.weight', 'vision_model.blocks.1.ls1.gamma', 'model.layers.9.self_attn.q_proj.lora_A', 'vision_model.blocks.12.mlp.fc1.weight', 'model.layers.15.self_attn.q_proj.lora_B', 'vision_model.blocks.3.ls2.gamma', 'vision_model.blocks.14.norm2.bias', 'vision_model.blocks.8.attn.lora_B_q', 'vision_model.blocks.14.mlp.fc1.weight', 'model.layers.31.self_attn.v_proj.lora_B', 'vision_model.blocks.19.norm2.weight', 'model.layers.0.self_attn.q_proj.lora_B', 'vision_model.blocks.2.mlp.fc2.weight', 'vision_model.blocks.17.attn.proj.weight', 'vision_model.blocks.7.norm2.weight', 'vision_model.blocks.20.norm1.bias', 'vision_model.blocks.22.norm2.bias', 'vision_model.blocks.22.attn.proj.bias', 'vision_model.blocks.9.attn.lora_A_v', 'model.layers.12.self_attn.v_proj.lora_A', 'vision_model.blocks.18.attn.lora_A_v', 'vision_model.blocks.10.norm1.weight', 'vision_model.blocks.2.norm1.bias', 'vision_model.blocks.21.mlp.fc1.weight', 'vision_model.blocks.7.norm1.bias', 'vision_model.blocks.8.attn.lora_A_q', 'vision_model.blocks.21.norm1.weight', 'model.layers.2.self_attn.v_proj.lora_A', 'vision_model.blocks.22.mlp.fc1.weight', 'vision_model.blocks.6.attn.lora_A_q', 'model.layers.6.self_attn.q_proj.lora_A', 'vision_model.blocks.22.mlp.fc2.weight', 'vision_model.blocks.2.attn.lora_A_q', 'model.layers.4.self_attn.q_proj.lora_B', 'vision_model.blocks.14.norm1.bias', 'vision_model.blocks.19.mlp.fc2.bias', 'vision_model.blocks.4.attn.proj.bias', 'vision_model.blocks.19.attn.proj.weight', 'vision_model.blocks.16.norm1.weight', 'vision_model.blocks.9.norm2.bias', 'vision_model.blocks.20.attn.proj.weight', 'vision_model.blocks.20.mlp.fc1.bias', 'vision_model.blocks.10.ls2.gamma', 'model.layers.13.self_attn.v_proj.lora_B', 'vision_model.blocks.20.attn.qkv.weight', 'vision_model.blocks.2.mlp.fc1.bias', 'vision_model.blocks.4.norm1.bias', 'model.layers.4.self_attn.q_proj.lora_A', 'vision_model.blocks.4.attn.lora_A_v', 'vision_model.blocks.5.ls2.gamma', 'model.layers.6.self_attn.q_proj.lora_B', 'vision_model.blocks.22.ls2.gamma', 'vision_model.blocks.16.attn.proj.weight', 'vision_model.blocks.2.norm2.weight', 'vision_model.blocks.13.norm1.weight', 'model.layers.2.self_attn.q_proj.lora_B', 'vision_model.blocks.21.mlp.fc1.bias', 'model.layers.18.self_attn.q_proj.lora_B', 'vision_model.blocks.16.attn.lora_B_v', 'vision_model.blocks.14.attn.lora_B_v', 'vision_model.blocks.14.norm1.weight', 'vision_model.blocks.1.attn.lora_B_v', 'vision_model.blocks.17.mlp.fc1.bias', 'vision_model.blocks.19.mlp.fc1.bias', 'vision_model.blocks.15.ls1.gamma', 'vision_model.blocks.14.attn.lora_B_q', 'vision_model.blocks.6.norm1.weight', 'model.layers.4.self_attn.v_proj.lora_B', 'vision_model.blocks.16.attn.proj.bias', 'vision_model.blocks.14.attn.proj.bias', 'vision_model.blocks.2.norm2.bias', 'vision_model.blocks.13.attn.qkv.weight', 'vision_model.blocks.5.attn.lora_A_v', 'model.layers.20.self_attn.q_proj.lora_A', 'model.layers.13.self_attn.q_proj.lora_B', 'model.layers.18.self_attn.q_proj.lora_A', 'vision_model.blocks.3.attn.proj.bias', 'vision_model.blocks.20.ls2.gamma', 'vision_model.blocks.8.mlp.fc1.bias', 'vision_model.blocks.4.attn.qkv.weight', 'vision_model.blocks.18.attn.lora_B_q', 'vision_model.blocks.20.ls1.gamma', 'vision_model.blocks.6.mlp.fc2.bias', 'vision_model.blocks.17.ls1.gamma', 'vision_model.blocks.19.attn.lora_A_v', 'vision_model.blocks.1.mlp.fc2.bias', 'model.layers.23.self_attn.q_proj.lora_A', 'vision_model.blocks.2.mlp.fc1.weight', 'vision_model.blocks.12.mlp.fc1.bias', 'model.layers.14.self_attn.q_proj.lora_B', 'vision_model.blocks.8.attn.lora_A_v', 'vision_model.blocks.14.mlp.fc1.bias', 'model.layers.16.self_attn.v_proj.lora_A', 'model.layers.29.self_attn.q_proj.lora_B', 'vision_model.blocks.14.attn.lora_A_q', 'vision_model.blocks.16.mlp.fc1.bias', 'model.layers.28.self_attn.v_proj.lora_A', 'vision_model.blocks.4.ls1.gamma', 'vision_model.norm.bias', 'model.layers.13.self_attn.q_proj.lora_A', 'vision_model.blocks.11.mlp.fc2.weight', 'model.layers.5.self_attn.v_proj.lora_B', 'vision_model.blocks.4.attn.lora_A_q', 'vision_model.blocks.15.norm1.weight', 'vision_model.blocks.10.attn.lora_B_q', 'vision_model.patch_embed.proj.weight', 'model.layers.14.self_attn.v_proj.lora_A', 'mm_projector.bias', 'vision_model.blocks.20.norm2.bias', 'vision_model.blocks.4.norm2.weight', 'vision_model.blocks.9.mlp.fc2.weight', 'model.layers.16.self_attn.q_proj.lora_A', 'model.layers.29.self_attn.v_proj.lora_B', 'model.layers.10.self_attn.q_proj.lora_A', 'vision_model.blocks.23.attn.qkv.bias', 'vision_model.blocks.9.norm1.weight', 'model.layers.29.self_attn.v_proj.lora_A', 'vision_model.blocks.3.norm1.bias', 'vision_model.blocks.19.attn.lora_B_v', 'vision_model.blocks.9.attn.proj.weight', 'vision_model.blocks.8.attn.qkv.bias', 'vision_model.blocks.9.attn.qkv.bias', 'vision_model.blocks.8.attn.proj.weight', 'vision_model.blocks.1.attn.qkv.bias', 'vision_model.blocks.1.ls2.gamma', 'vision_model.blocks.17.attn.qkv.bias', 'vision_model.blocks.12.attn.lora_B_q', 'vision_model.blocks.8.attn.proj.bias', 'vision_model.blocks.12.ls2.gamma', 'vision_model.blocks.23.mlp.fc2.bias', 'model.layers.26.self_attn.q_proj.lora_B', 'vision_model.blocks.16.mlp.fc2.weight', 'vision_model.blocks.22.norm2.weight', 'vision_model.blocks.9.attn.lora_B_q', 'vision_model.blocks.0.norm2.weight', 'vision_model.blocks.9.norm1.bias', 'vision_model.blocks.2.attn.lora_B_q', 'vision_model.blocks.6.attn.lora_B_v', 'vision_model.blocks.5.attn.proj.bias', 'vision_model.blocks.6.norm2.bias', 'vision_model.blocks.9.mlp.fc2.bias', 'vision_model.blocks.5.mlp.fc1.bias', 'model.layers.3.self_attn.q_proj.lora_A', 'vision_model.blocks.5.norm2.bias', 'vision_model.blocks.17.mlp.fc2.bias', 'vision_model.blocks.0.norm2.bias', 'model.layers.6.self_attn.v_proj.lora_B', 'model.layers.7.self_attn.v_proj.lora_B', 'vision_model.blocks.9.ls1.gamma', 'model.layers.26.self_attn.v_proj.lora_B', 'vision_model.blocks.13.attn.qkv.bias', 'model.layers.22.self_attn.q_proj.lora_B', 'vision_model.blocks.0.attn.lora_B_v', 'vision_model.blocks.16.mlp.fc1.weight', 'vision_model.blocks.19.attn.qkv.weight', 'vision_model.blocks.7.attn.lora_B_q', 'model.layers.26.self_attn.q_proj.lora_A', 'model.layers.10.self_attn.q_proj.lora_B', 'vision_model.blocks.13.mlp.fc1.weight', 'vision_model.blocks.17.norm1.weight', 'vision_model.blocks.10.attn.lora_B_v', 'vision_model.blocks.23.norm2.bias', 'vision_model.blocks.23.norm1.weight', 'model.layers.28.self_attn.v_proj.lora_B', 'vision_model.mask_token', 'vision_model.blocks.11.mlp.fc1.weight', 'vision_model.blocks.23.attn.qkv.weight', 'vision_model.blocks.0.ls1.gamma', 'vision_model.blocks.12.attn.lora_A_q', 'model.layers.21.self_attn.q_proj.lora_A', 'model.layers.5.self_attn.q_proj.lora_A', 'vision_model.blocks.23.ls1.gamma', 'vision_model.blocks.16.ls1.gamma', 'vision_model.blocks.18.attn.proj.weight', 'vision_model.blocks.22.norm1.weight', 'model.layers.17.self_attn.q_proj.lora_A', 'vision_model.blocks.20.attn.lora_A_v', 'vision_model.blocks.13.attn.proj.weight', 'vision_model.blocks.5.attn.proj.weight', 'vision_model.blocks.23.ls2.gamma', 'vision_model.blocks.11.attn.qkv.bias', 'vision_model.blocks.10.mlp.fc1.weight', 'vision_model.blocks.7.ls2.gamma', 'vision_model.blocks.4.mlp.fc2.weight', 'vision_model.blocks.20.norm2.weight', 'model.layers.24.self_attn.v_proj.lora_B', 'vision_model.blocks.7.attn.proj.weight', 'vision_model.blocks.10.norm1.bias', 'vision_model.blocks.3.mlp.fc1.weight', 'model.layers.16.self_attn.q_proj.lora_B', 'vision_model.blocks.15.norm2.weight', 'vision_model.blocks.11.mlp.fc1.bias', 'vision_model.blocks.22.attn.qkv.bias', 'model.layers.27.self_attn.q_proj.lora_B', 'vision_model.blocks.9.mlp.fc1.weight', 'vision_model.blocks.6.norm2.weight', 'vision_model.blocks.14.attn.qkv.bias', 'vision_model.blocks.5.norm1.weight', 'vision_model.blocks.21.attn.proj.weight', 'model.layers.14.self_attn.v_proj.lora_B', 'vision_model.blocks.21.attn.proj.bias', 'vision_model.blocks.21.attn.lora_A_v', 'vision_model.blocks.1.attn.qkv.weight', 'vision_model.blocks.4.attn.proj.weight', 'vision_model.blocks.10.mlp.fc2.weight', 'vision_model.blocks.2.attn.proj.weight', 'vision_model.blocks.18.ls1.gamma', 'model.layers.12.self_attn.v_proj.lora_B', 'model.layers.19.self_attn.q_proj.lora_A', 'vision_model.blocks.0.attn.proj.bias', 'vision_model.blocks.16.attn.qkv.bias', 'model.layers.23.self_attn.v_proj.lora_B', 'vision_model.blocks.21.attn.qkv.bias', 'vision_model.blocks.19.mlp.fc1.weight', 'model.layers.14.self_attn.q_proj.lora_A', 'vision_model.blocks.17.mlp.fc1.weight', 'vision_model.blocks.2.ls2.gamma', 'vision_model.blocks.7.mlp.fc2.bias', 'vision_model.blocks.20.attn.proj.bias', 'vision_model.blocks.23.attn.lora_A_q', 'vision_model.blocks.1.norm2.bias', 'vision_model.blocks.10.mlp.fc2.bias', 'vision_model.blocks.15.mlp.fc1.weight', 'vision_model.blocks.21.ls1.gamma', 'vision_model.blocks.3.mlp.fc2.weight', 'vision_model.blocks.12.norm1.bias', 'vision_model.blocks.4.norm1.weight', 'vision_model.blocks.14.ls1.gamma', 'vision_model.blocks.16.norm2.bias', 'vision_model.blocks.17.attn.lora_A_q', 'vision_model.blocks.18.norm1.weight', 'vision_model.blocks.18.norm1.bias', 'vision_model.blocks.12.attn.proj.bias', 'vision_model.blocks.0.mlp.fc1.weight', 'vision_model.blocks.17.attn.lora_B_v', 'vision_model.blocks.21.attn.lora_A_q', 'vision_model.blocks.15.attn.lora_B_q', 'vision_model.blocks.16.mlp.fc2.bias', 'vision_model.blocks.6.attn.qkv.weight', 'vision_model.blocks.3.norm1.weight', 'vision_model.blocks.15.attn.lora_A_v', 'vision_model.blocks.6.mlp.fc1.bias', 'vision_model.blocks.18.attn.lora_B_v', 'vision_model.blocks.6.mlp.fc2.weight', 'model.layers.8.self_attn.q_proj.lora_B', 'vision_model.blocks.13.attn.lora_B_q', 'vision_model.blocks.17.norm2.weight', 'vision_model.blocks.5.mlp.fc2.bias', 'vision_model.blocks.15.attn.qkv.weight', 'model.layers.15.self_attn.q_proj.lora_A', 'vision_model.blocks.5.ls1.gamma', 'vision_model.blocks.0.attn.proj.weight', 'model.layers.13.self_attn.v_proj.lora_A', 'vision_model.blocks.22.mlp.fc2.bias', 'vision_model.blocks.1.attn.proj.weight', 'vision_model.blocks.20.attn.qkv.bias', 'vision_model.blocks.11.norm2.weight', 'vision_model.blocks.11.attn.lora_B_q', 'vision_model.blocks.1.attn.lora_A_q', 'vision_model.blocks.14.attn.lora_A_v', 'vision_model.blocks.10.norm2.weight', 'vision_model.blocks.3.mlp.fc2.bias', 'vision_model.blocks.6.attn.qkv.bias', 'model.layers.11.self_attn.v_proj.lora_B', 'model.layers.25.self_attn.q_proj.lora_B', 'vision_model.blocks.3.attn.lora_A_v', 'vision_model.blocks.0.mlp.fc2.bias', 'vision_model.blocks.20.mlp.fc2.bias', 'vision_model.blocks.8.norm2.bias', 'vision_model.blocks.22.norm1.bias', 'model.layers.21.self_attn.q_proj.lora_B', 'vision_model.blocks.12.norm1.weight', 'vision_model.blocks.20.attn.lora_A_q', 'vision_model.blocks.18.norm2.weight', 'vision_model.blocks.13.ls1.gamma', 'model.layers.18.self_attn.v_proj.lora_B', 'vision_model.blocks.4.mlp.fc1.bias', 'vision_model.blocks.21.mlp.fc2.bias', 'model.layers.18.self_attn.v_proj.lora_A', 'vision_model.blocks.10.norm2.bias', 'vision_model.blocks.8.ls2.gamma', 'vision_model.blocks.22.attn.lora_B_q', 'vision_model.blocks.3.attn.proj.weight', 'model.layers.19.self_attn.v_proj.lora_B', 'vision_model.blocks.5.attn.lora_B_v', 'vision_model.blocks.11.ls1.gamma', 'vision_model.blocks.13.norm2.bias', 'vision_model.blocks.16.ls2.gamma', 'vision_model.blocks.19.mlp.fc2.weight', 'vision_model.blocks.1.norm1.weight', 'vision_model.blocks.21.attn.lora_B_q', 'vision_model.blocks.9.attn.lora_B_v', 'vision_model.blocks.1.attn.lora_A_v', 'model.layers.28.self_attn.q_proj.lora_B', 'vision_model.blocks.12.attn.proj.weight', 'vision_model.blocks.19.attn.lora_A_q', 'vision_model.blocks.8.mlp.fc2.bias', 'vision_model.blocks.11.attn.lora_B_v', 'vision_model.blocks.0.mlp.fc1.bias', 'vision_model.blocks.12.ls1.gamma', 'vision_model.blocks.5.attn.qkv.weight', 'vision_model.blocks.4.attn.qkv.bias', 'vision_model.blocks.8.norm2.weight', 'vision_model.blocks.22.attn.qkv.weight', 'vision_model.blocks.8.norm1.weight', 'vision_model.blocks.12.mlp.fc2.bias', 'vision_model.patch_embed.proj.bias', 'vision_model.blocks.5.norm2.weight', 'vision_model.blocks.15.mlp.fc2.bias', 'vision_model.blocks.10.ls1.gamma', 'vision_model.blocks.21.attn.lora_B_v', 'vision_model.blocks.7.mlp.fc1.bias', 'vision_model.blocks.11.attn.lora_A_v', 'vision_model.blocks.11.attn.proj.weight', 'vision_model.blocks.12.attn.qkv.weight', 'vision_model.blocks.18.norm2.bias', 'vision_model.blocks.22.attn.lora_B_v', 'vision_model.blocks.16.attn.qkv.weight', 'vision_model.blocks.7.mlp.fc1.weight', 'vision_model.blocks.2.attn.lora_B_v', 'vision_model.blocks.20.attn.lora_B_q', 'vision_model.blocks.1.norm1.bias', 'vision_model.blocks.4.norm2.bias', 'model.layers.30.self_attn.q_proj.lora_B', 'vision_model.blocks.16.attn.lora_A_q', 'vision_model.blocks.13.mlp.fc2.weight', 'vision_model.blocks.10.attn.proj.weight', 'vision_model.blocks.0.attn.qkv.bias', 'vision_model.blocks.0.attn.lora_B_q', 'vision_model.blocks.14.attn.proj.weight', 'vision_model.cls_token', 'vision_model.blocks.23.attn.lora_B_v', 'model.layers.22.self_attn.v_proj.lora_B', 'model.layers.17.self_attn.v_proj.lora_B', 'vision_model.blocks.7.ls1.gamma', 'vision_model.blocks.16.norm1.bias', 'vision_model.blocks.2.attn.qkv.weight', 'vision_model.blocks.6.ls2.gamma', 'vision_model.blocks.23.attn.proj.bias', 'vision_model.blocks.12.norm2.bias', 'model.layers.19.self_attn.v_proj.lora_A', 'model.layers.9.self_attn.v_proj.lora_B', 'vision_model.blocks.18.attn.qkv.bias', 'vision_model.blocks.14.norm2.weight', 'model.layers.25.self_attn.v_proj.lora_B', 'model.layers.21.self_attn.v_proj.lora_B', 'vision_model.blocks.11.norm2.bias', 'vision_model.blocks.16.norm2.weight', 'vision_model.blocks.10.attn.lora_A_q', 'model.layers.22.self_attn.v_proj.lora_A', 'vision_model.blocks.12.attn.lora_A_v', 'vision_model.blocks.22.mlp.fc1.bias', 'vision_model.blocks.7.attn.qkv.bias', 'vision_model.blocks.5.norm1.bias', 'model.layers.20.self_attn.v_proj.lora_A', 'vision_model.blocks.10.attn.lora_A_v', 'vision_model.blocks.11.ls2.gamma', 'model.layers.24.self_attn.v_proj.lora_A', 'vision_model.blocks.2.ls1.gamma', 'vision_model.blocks.6.attn.lora_B_q', 'model.layers.31.self_attn.q_proj.lora_B', 'vision_model.blocks.14.mlp.fc2.weight', 'vision_model.blocks.23.attn.lora_B_q', 'vision_model.blocks.2.mlp.fc2.bias', 'vision_model.blocks.15.mlp.fc2.weight', 'vision_model.blocks.17.mlp.fc2.weight', 'vision_model.blocks.22.attn.proj.weight', 'vision_model.blocks.2.attn.proj.bias', 'vision_model.blocks.19.attn.proj.bias', 'model.layers.30.self_attn.q_proj.lora_A', 'model.layers.8.self_attn.q_proj.lora_A', 'vision_model.blocks.23.mlp.fc2.weight', 'model.layers.7.self_attn.v_proj.lora_A', 'model.layers.2.self_attn.v_proj.lora_B', 'vision_model.blocks.15.attn.qkv.bias', 'vision_model.blocks.8.attn.lora_B_v', 'model.layers.7.self_attn.q_proj.lora_A', 'model.layers.20.self_attn.q_proj.lora_B', 'vision_model.blocks.18.attn.lora_A_q', 'model.layers.8.self_attn.v_proj.lora_B', 'vision_model.blocks.1.norm2.weight', 'vision_model.blocks.13.mlp.fc1.bias', 'model.layers.27.self_attn.q_proj.lora_A', 'model.layers.15.self_attn.v_proj.lora_B', 'model.layers.1.self_attn.v_proj.lora_B', 'vision_model.blocks.9.norm2.weight', 'vision_model.blocks.3.attn.qkv.bias', 'vision_model.blocks.17.ls2.gamma', 'vision_model.blocks.3.attn.lora_B_q', 'vision_model.blocks.4.mlp.fc2.bias', 'vision_model.blocks.13.attn.proj.bias', 'vision_model.blocks.21.norm2.bias', 'vision_model.blocks.11.mlp.fc2.bias', 'vision_model.blocks.10.attn.proj.bias', 'vision_model.blocks.17.norm1.bias', 'vision_model.blocks.5.attn.lora_B_q', 'vision_model.blocks.21.norm2.weight', 'vision_model.blocks.13.attn.lora_A_q', 'vision_model.blocks.8.mlp.fc2.weight', 'vision_model.blocks.11.norm1.bias', 'vision_model.blocks.19.norm2.bias', 'model.layers.0.self_attn.v_proj.lora_A', 'vision_model.blocks.5.attn.lora_A_q', 'model.layers.5.self_attn.v_proj.lora_A', 'model.layers.25.self_attn.v_proj.lora_A', 'vision_model.blocks.6.attn.lora_A_v', 'vision_model.blocks.1.mlp.fc1.weight', 'vision_model.blocks.3.mlp.fc1.bias', 'model.layers.3.self_attn.v_proj.lora_B', 'vision_model.blocks.1.attn.lora_B_q', 'vision_model.blocks.0.mlp.fc2.weight', 'vision_model.blocks.15.attn.proj.weight', 'vision_model.blocks.13.attn.lora_A_v', 'model.layers.9.self_attn.v_proj.lora_A', 'model.layers.25.self_attn.q_proj.lora_A', 'vision_model.blocks.13.ls2.gamma', 'vision_model.blocks.21.ls2.gamma', 'model.layers.8.self_attn.v_proj.lora_A', 'vision_model.blocks.7.attn.lora_A_q', 'model.layers.15.self_attn.v_proj.lora_A', 'vision_model.blocks.17.attn.lora_B_q', 'vision_model.blocks.5.attn.qkv.bias', 'vision_model.blocks.0.ls2.gamma', 'vision_model.blocks.9.ls2.gamma', 'vision_model.blocks.9.mlp.fc1.bias', 'vision_model.blocks.23.mlp.fc1.weight', 'vision_model.blocks.19.norm1.bias', 'model.layers.16.self_attn.v_proj.lora_B', 'model.layers.3.self_attn.v_proj.lora_A', 'vision_model.blocks.0.attn.qkv.weight', 'vision_model.blocks.19.norm1.weight', 'vision_model.blocks.8.attn.qkv.weight', 'vision_model.blocks.18.mlp.fc1.weight', 'vision_model.blocks.21.attn.qkv.weight', 'model.layers.10.self_attn.v_proj.lora_B', 'model.layers.9.self_attn.q_proj.lora_B', 'vision_model.blocks.6.attn.proj.weight', 'vision_model.blocks.21.mlp.fc2.weight', 'model.layers.29.self_attn.q_proj.lora_A', 'model.layers.30.self_attn.v_proj.lora_A', 'vision_model.blocks.20.mlp.fc2.weight', 'vision_model.blocks.20.norm1.weight', 'vision_model.blocks.7.mlp.fc2.weight', 'vision_model.blocks.3.attn.lora_A_q', 'vision_model.blocks.7.attn.lora_B_v', 'vision_model.blocks.14.attn.qkv.weight', 'vision_model.blocks.15.attn.lora_A_q', 'vision_model.blocks.0.attn.lora_A_q', 'vision_model.blocks.21.norm1.bias', 'vision_model.blocks.17.attn.lora_A_v', 'vision_model.blocks.10.mlp.fc1.bias', 'vision_model.blocks.14.mlp.fc2.bias', 'vision_model.blocks.0.attn.lora_A_v', 'vision_model.blocks.4.attn.lora_B_v', 'vision_model.blocks.6.ls1.gamma', 'mm_projector.weight', 'model.layers.1.self_attn.q_proj.lora_A', 'vision_model.blocks.8.mlp.fc1.weight', 'vision_model.blocks.13.mlp.fc2.bias', 'vision_model.blocks.19.attn.lora_B_q', 'vision_model.blocks.2.attn.lora_A_v', 'vision_model.blocks.12.mlp.fc2.weight', 'vision_model.blocks.10.attn.qkv.bias', 'vision_model.blocks.3.ls1.gamma']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.

Loading checkpoint shards: 100%|██████████| 2/2 [00:16<00:00,  7.74s/it]
Loading checkpoint shards: 100%|██████████| 2/2 [00:16<00:00,  8.33s/it]
Some weights of LocLLMModel were not initialized from the model checkpoint at ./checkpoints/model_weights/vicuna-7b-v1.5 and are newly initialized: ['vision_model.blocks.18.mlp.fc1.bias', 'mm_projector.bias', 'vision_model.blocks.18.norm1.weight', 'vision_model.blocks.13.attn.proj.bias', 'vision_model.blocks.21.norm2.bias', 'vision_model.blocks.12.ls2.gamma', 'vision_model.blocks.22.attn.proj.bias', 'vision_model.blocks.21.norm2.weight', 'model.layers.9.self_attn.q_proj.lora_A', 'vision_model.blocks.16.mlp.fc2.bias', 'vision_model.blocks.6.mlp.fc1.weight', 'vision_model.blocks.18.mlp.fc2.weight', 'vision_model.blocks.20.attn.lora_A_q', 'vision_model.blocks.5.attn.proj.bias', 'model.layers.12.self_attn.v_proj.lora_B', 'model.layers.7.self_attn.v_proj.lora_A', 'vision_model.blocks.0.norm1.bias', 'model.layers.26.self_attn.q_proj.lora_A', 'vision_model.blocks.14.ls2.gamma', 'vision_model.blocks.21.norm1.bias', 'vision_model.blocks.15.attn.qkv.bias', 'vision_model.blocks.21.mlp.fc2.bias', 'vision_model.blocks.9.attn.proj.weight', 'vision_model.blocks.17.ls1.gamma', 'vision_model.blocks.0.attn.lora_B_v', 'vision_model.blocks.17.mlp.fc2.weight', 'vision_model.blocks.2.norm2.bias', 'vision_model.blocks.8.attn.lora_B_v', 'model.layers.12.self_attn.q_proj.lora_A', 'vision_model.blocks.22.mlp.fc2.weight', 'vision_model.blocks.4.norm1.weight', 'vision_model.blocks.12.mlp.fc2.bias', 'vision_model.blocks.23.norm2.bias', 'vision_model.blocks.3.ls2.gamma', 'model.layers.9.self_attn.v_proj.lora_B', 'vision_model.blocks.15.ls1.gamma', 'model.layers.27.self_attn.q_proj.lora_B', 'vision_model.blocks.16.attn.proj.bias', 'vision_model.blocks.13.mlp.fc2.bias', 'vision_model.blocks.2.mlp.fc1.bias', 'vision_model.blocks.13.norm2.bias', 'vision_model.blocks.12.norm1.bias', 'vision_model.blocks.8.mlp.fc2.bias', 'vision_model.blocks.15.attn.proj.weight', 'model.layers.4.self_attn.q_proj.lora_B', 'model.layers.3.self_attn.q_proj.lora_B', 'model.layers.30.self_attn.v_proj.lora_A', 'vision_model.blocks.6.attn.qkv.weight', 'vision_model.blocks.23.attn.qkv.bias', 'vision_model.blocks.10.norm1.weight', 'vision_model.blocks.22.attn.lora_A_v', 'model.layers.13.self_attn.v_proj.lora_A', 'vision_model.blocks.19.attn.qkv.bias', 'model.layers.2.self_attn.q_proj.lora_B', 'vision_model.blocks.3.attn.lora_B_q', 'model.layers.5.self_attn.q_proj.lora_B', 'vision_model.blocks.19.norm1.weight', 'vision_model.blocks.22.norm1.weight', 'vision_model.blocks.5.mlp.fc1.bias', 'vision_model.blocks.6.attn.lora_A_v', 'vision_model.blocks.5.ls1.gamma', 'vision_model.blocks.3.attn.lora_A_v', 'model.layers.19.self_attn.q_proj.lora_B', 'vision_model.blocks.23.ls1.gamma', 'vision_model.blocks.5.norm2.bias', 'vision_model.blocks.18.attn.lora_A_q', 'vision_model.blocks.2.attn.qkv.bias', 'vision_model.blocks.7.attn.proj.bias', 'model.layers.1.self_attn.v_proj.lora_B', 'model.layers.16.self_attn.v_proj.lora_B', 'model.layers.11.self_attn.q_proj.lora_A', 'vision_model.blocks.20.norm2.weight', 'vision_model.blocks.1.attn.lora_B_q', 'model.layers.24.self_attn.v_proj.lora_A', 'vision_model.blocks.16.norm1.bias', 'vision_model.blocks.15.ls2.gamma', 'vision_model.blocks.15.mlp.fc1.weight', 'model.layers.14.self_attn.v_proj.lora_A', 'model.layers.27.self_attn.v_proj.lora_A', 'vision_model.blocks.13.attn.qkv.weight', 'vision_model.blocks.6.mlp.fc1.bias', 'vision_model.blocks.18.attn.proj.weight', 'vision_model.blocks.23.norm2.weight', 'model.layers.1.self_attn.q_proj.lora_B', 'vision_model.blocks.18.norm2.weight', 'model.layers.19.self_attn.v_proj.lora_A', 'vision_model.blocks.16.norm1.weight', 'model.layers.13.self_attn.q_proj.lora_B', 'vision_model.blocks.1.attn.lora_A_v', 'model.layers.7.self_attn.q_proj.lora_B', 'vision_model.blocks.8.ls1.gamma', 'vision_model.blocks.12.mlp.fc1.weight', 'vision_model.blocks.15.mlp.fc1.bias', 'vision_model.blocks.13.mlp.fc1.weight', 'vision_model.blocks.20.mlp.fc1.weight', 'vision_model.blocks.3.mlp.fc1.bias', 'model.layers.0.self_attn.v_proj.lora_B', 'vision_model.blocks.7.norm2.bias', 'vision_model.blocks.20.ls1.gamma', 'vision_model.patch_embed.proj.bias', 'model.layers.8.self_attn.v_proj.lora_B', 'vision_model.blocks.18.attn.proj.bias', 'vision_model.blocks.4.ls2.gamma', 'vision_model.blocks.19.attn.lora_B_q', 'vision_model.blocks.19.attn.qkv.weight', 'model.layers.28.self_attn.q_proj.lora_A', 'vision_model.blocks.20.attn.proj.bias', 'vision_model.blocks.21.attn.lora_A_v', 'model.layers.11.self_attn.v_proj.lora_A', 'vision_model.blocks.8.attn.lora_A_q', 'model.layers.16.self_attn.v_proj.lora_A', 'vision_model.blocks.0.attn.proj.weight', 'model.layers.4.self_attn.v_proj.lora_A', 'vision_model.blocks.13.mlp.fc1.bias', 'model.layers.23.self_attn.q_proj.lora_B', 'vision_model.cls_token', 'vision_model.blocks.9.attn.proj.bias', 'model.layers.17.self_attn.v_proj.lora_B', 'vision_model.blocks.15.mlp.fc2.weight', 'vision_model.blocks.4.norm2.weight', 'vision_model.blocks.11.norm2.weight', 'vision_model.blocks.17.attn.lora_B_q', 'vision_model.blocks.0.norm2.bias', 'vision_model.blocks.8.attn.qkv.weight', 'vision_model.blocks.10.norm2.weight', 'vision_model.blocks.18.ls1.gamma', 'vision_model.blocks.17.attn.proj.bias', 'vision_model.blocks.12.attn.qkv.weight', 'vision_model.blocks.10.ls1.gamma', 'vision_model.blocks.11.norm1.weight', 'vision_model.blocks.22.norm1.bias', 'model.layers.11.self_attn.v_proj.lora_B', 'vision_model.blocks.9.norm1.bias', 'vision_model.blocks.9.mlp.fc2.bias', 'vision_model.blocks.16.mlp.fc1.weight', 'vision_model.blocks.14.norm2.weight', 'model.layers.20.self_attn.q_proj.lora_B', 'vision_model.blocks.16.ls2.gamma', 'model.layers.27.self_attn.q_proj.lora_A', 'vision_model.blocks.1.norm1.bias', 'vision_model.blocks.9.ls1.gamma', 'vision_model.blocks.13.ls1.gamma', 'mm_projector.weight', 'vision_model.blocks.11.attn.lora_B_v', 'vision_model.blocks.6.norm2.weight', 'vision_model.blocks.1.attn.qkv.weight', 'vision_model.blocks.14.attn.qkv.bias', 'vision_model.blocks.4.attn.qkv.bias', 'vision_model.blocks.9.norm1.weight', 'model.layers.15.self_attn.q_proj.lora_A', 'vision_model.blocks.0.attn.lora_A_v', 'vision_model.blocks.6.norm1.weight', 'vision_model.blocks.16.attn.qkv.weight', 'vision_model.blocks.16.norm2.bias', 'model.layers.17.self_attn.q_proj.lora_B', 'model.layers.10.self_attn.q_proj.lora_A', 'vision_model.blocks.3.ls1.gamma', 'model.layers.15.self_attn.q_proj.lora_B', 'vision_model.blocks.7.attn.qkv.bias', 'vision_model.blocks.13.attn.proj.weight', 'vision_model.blocks.14.norm1.bias', 'model.layers.17.self_attn.q_proj.lora_A', 'model.layers.31.self_attn.v_proj.lora_B', 'vision_model.blocks.17.norm1.bias', 'vision_model.blocks.21.mlp.fc2.weight', 'vision_model.blocks.15.norm2.bias', 'model.layers.13.self_attn.v_proj.lora_B', 'vision_model.blocks.19.attn.lora_A_q', 'vision_model.blocks.5.attn.lora_A_q', 'vision_model.blocks.3.norm1.weight', 'vision_model.blocks.4.attn.lora_B_v', 'vision_model.blocks.19.ls1.gamma', 'vision_model.blocks.23.attn.lora_A_q', 'model.layers.16.self_attn.q_proj.lora_B', 'model.layers.10.self_attn.q_proj.lora_B', 'vision_model.blocks.5.attn.proj.weight', 'model.layers.25.self_attn.q_proj.lora_A', 'vision_model.blocks.17.attn.lora_A_q', 'vision_model.blocks.21.attn.lora_B_q', 'vision_model.blocks.20.norm1.bias', 'model.layers.11.self_attn.q_proj.lora_B', 'model.layers.24.self_attn.v_proj.lora_B', 'model.layers.18.self_attn.q_proj.lora_A', 'vision_model.blocks.2.attn.lora_B_v', 'vision_model.blocks.10.attn.qkv.weight', 'vision_model.blocks.17.ls2.gamma', 'vision_model.blocks.20.attn.proj.weight', 'vision_model.blocks.13.mlp.fc2.weight', 'vision_model.blocks.16.attn.lora_B_v', 'vision_model.blocks.23.ls2.gamma', 'vision_model.blocks.8.attn.lora_A_v', 'vision_model.blocks.10.attn.lora_B_v', 'vision_model.blocks.3.norm1.bias', 'vision_model.blocks.9.mlp.fc1.bias', 'vision_model.blocks.2.ls1.gamma', 'vision_model.blocks.0.attn.lora_A_q', 'vision_model.blocks.16.attn.lora_B_q', 'vision_model.blocks.17.attn.proj.weight', 'vision_model.blocks.11.mlp.fc1.bias', 'vision_model.blocks.18.mlp.fc1.weight', 'vision_model.blocks.2.attn.lora_A_q', 'vision_model.blocks.6.ls2.gamma', 'vision_model.blocks.13.attn.lora_B_q', 'vision_model.blocks.8.mlp.fc2.weight', 'vision_model.blocks.20.mlp.fc2.weight', 'vision_model.blocks.3.attn.proj.weight', 'model.layers.7.self_attn.v_proj.lora_B', 'vision_model.blocks.1.mlp.fc1.weight', 'vision_model.blocks.15.attn.proj.bias', 'vision_model.blocks.16.mlp.fc1.bias', 'model.layers.7.self_attn.q_proj.lora_A', 'vision_model.blocks.1.norm2.bias', 'vision_model.blocks.1.attn.qkv.bias', 'vision_model.blocks.19.norm2.weight', 'model.layers.14.self_attn.q_proj.lora_B', 'vision_model.blocks.23.attn.qkv.weight', 'model.layers.12.self_attn.q_proj.lora_B', 'model.layers.25.self_attn.v_proj.lora_B', 'vision_model.blocks.20.ls2.gamma', 'vision_model.blocks.14.norm2.bias', 'model.layers.21.self_attn.v_proj.lora_B', 'model.layers.4.self_attn.v_proj.lora_B', 'vision_model.blocks.2.mlp.fc2.bias', 'vision_model.blocks.4.attn.qkv.weight', 'vision_model.blocks.14.attn.proj.weight', 'vision_model.blocks.17.mlp.fc2.bias', 'vision_model.blocks.7.ls2.gamma', 'vision_model.blocks.19.attn.lora_B_v', 'vision_model.blocks.20.attn.lora_B_v', 'vision_model.blocks.10.norm2.bias', 'vision_model.blocks.17.mlp.fc1.weight', 'model.layers.30.self_attn.v_proj.lora_B', 'vision_model.blocks.0.mlp.fc1.weight', 'vision_model.blocks.14.mlp.fc2.bias', 'vision_model.blocks.8.norm2.bias', 'vision_model.blocks.4.ls1.gamma', 'vision_model.blocks.21.ls2.gamma', 'model.layers.8.self_attn.v_proj.lora_A', 'model.layers.26.self_attn.v_proj.lora_B', 'vision_model.blocks.21.attn.proj.weight', 'model.layers.6.self_attn.v_proj.lora_B', 'vision_model.blocks.21.attn.qkv.weight', 'vision_model.blocks.6.attn.proj.weight', 'vision_model.blocks.7.attn.proj.weight', 'vision_model.blocks.19.norm1.bias', 'vision_model.blocks.11.attn.lora_A_v', 'model.layers.10.self_attn.v_proj.lora_A', 'vision_model.blocks.17.norm2.weight', 'vision_model.blocks.17.norm1.weight', 'vision_model.blocks.15.attn.lora_A_q', 'vision_model.blocks.6.mlp.fc2.weight', 'vision_model.blocks.2.attn.lora_B_q', 'vision_model.blocks.19.ls2.gamma', 'vision_model.blocks.6.attn.lora_B_q', 'model.layers.22.self_attn.q_proj.lora_A', 'vision_model.blocks.2.norm2.weight', 'vision_model.blocks.5.mlp.fc2.weight', 'model.layers.0.self_attn.q_proj.lora_B', 'vision_model.blocks.5.attn.qkv.bias', 'model.layers.2.self_attn.v_proj.lora_A', 'vision_model.blocks.17.mlp.fc1.bias', 'vision_model.blocks.21.attn.proj.bias', 'vision_model.blocks.5.mlp.fc1.weight', 'vision_model.blocks.8.mlp.fc1.weight', 'model.layers.0.self_attn.v_proj.lora_A', 'vision_model.blocks.0.attn.proj.bias', 'vision_model.blocks.6.attn.lora_B_v', 'vision_model.blocks.8.attn.qkv.bias', 'vision_model.blocks.14.attn.lora_A_v', 'vision_model.blocks.20.norm1.weight', 'vision_model.blocks.7.attn.qkv.weight', 'vision_model.blocks.22.attn.lora_B_v', 'vision_model.blocks.10.mlp.fc2.bias', 'vision_model.blocks.2.norm1.bias', 'model.layers.22.self_attn.q_proj.lora_B', 'vision_model.blocks.5.mlp.fc2.bias', 'vision_model.blocks.18.attn.lora_B_q', 'vision_model.blocks.9.norm2.bias', 'vision_model.blocks.14.mlp.fc1.bias', 'vision_model.blocks.9.attn.lora_A_v', 'vision_model.blocks.20.norm2.bias', 'vision_model.blocks.3.mlp.fc2.weight', 'vision_model.blocks.15.attn.lora_B_q', 'vision_model.blocks.2.attn.qkv.weight', 'model.layers.29.self_attn.v_proj.lora_B', 'vision_model.blocks.9.attn.lora_B_v', 'vision_model.blocks.20.mlp.fc2.bias', 'vision_model.blocks.21.mlp.fc1.weight', 'model.layers.17.self_attn.v_proj.lora_A', 'model.layers.28.self_attn.v_proj.lora_B', 'model.layers.12.self_attn.v_proj.lora_A', 'vision_model.blocks.12.attn.qkv.bias', 'vision_model.blocks.13.norm2.weight', 'vision_model.blocks.16.ls1.gamma', 'vision_model.blocks.16.attn.qkv.bias', 'model.layers.14.self_attn.v_proj.lora_B', 'model.layers.15.self_attn.v_proj.lora_A', 'vision_model.blocks.3.attn.lora_A_q', 'vision_model.blocks.20.attn.qkv.weight', 'model.layers.8.self_attn.q_proj.lora_B', 'model.layers.29.self_attn.v_proj.lora_A', 'vision_model.blocks.11.attn.proj.weight', 'vision_model.blocks.0.ls1.gamma', 'vision_model.blocks.14.ls1.gamma', 'vision_model.blocks.0.norm1.weight', 'vision_model.blocks.22.attn.proj.weight', 'vision_model.blocks.11.ls1.gamma', 'model.layers.2.self_attn.v_proj.lora_B', 'vision_model.blocks.7.attn.lora_B_v', 'vision_model.blocks.11.attn.lora_B_q', 'vision_model.blocks.19.mlp.fc1.weight', 'vision_model.blocks.18.attn.qkv.bias', 'vision_model.blocks.12.attn.lora_A_v', 'vision_model.blocks.9.attn.qkv.bias', 'vision_model.blocks.15.attn.lora_B_v', 'vision_model.blocks.12.attn.lora_B_v', 'vision_model.blocks.8.attn.proj.bias', 'model.layers.22.self_attn.v_proj.lora_A', 'vision_model.blocks.19.mlp.fc1.bias', 'vision_model.blocks.12.attn.lora_B_q', 'vision_model.blocks.8.attn.proj.weight', 'vision_model.blocks.3.mlp.fc2.bias', 'vision_model.blocks.4.mlp.fc1.bias', 'vision_model.blocks.0.mlp.fc1.bias', 'vision_model.blocks.14.attn.lora_A_q', 'model.layers.24.self_attn.q_proj.lora_A', 'vision_model.blocks.6.norm2.bias', 'model.layers.25.self_attn.q_proj.lora_B', 'vision_model.blocks.5.attn.lora_B_v', 'vision_model.blocks.1.attn.lora_A_q', 'vision_model.blocks.18.attn.lora_B_v', 'vision_model.blocks.1.ls1.gamma', 'model.layers.31.self_attn.v_proj.lora_A', 'vision_model.blocks.15.attn.qkv.weight', 'vision_model.patch_embed.proj.weight', 'vision_model.blocks.6.ls1.gamma', 'vision_model.blocks.23.mlp.fc1.bias', 'vision_model.blocks.23.attn.lora_B_v', 'vision_model.blocks.1.attn.lora_B_v', 'vision_model.pos_embed', 'model.layers.9.self_attn.q_proj.lora_B', 'vision_model.blocks.1.attn.proj.bias', 'vision_model.blocks.3.attn.lora_B_v', 'vision_model.blocks.22.mlp.fc1.bias', 'model.layers.23.self_attn.v_proj.lora_A', 'vision_model.blocks.11.attn.proj.bias', 'vision_model.blocks.18.attn.qkv.weight', 'vision_model.blocks.22.mlp.fc2.bias', 'vision_model.blocks.16.norm2.weight', 'vision_model.blocks.9.attn.lora_B_q', 'vision_model.blocks.21.attn.lora_A_q', 'vision_model.blocks.13.ls2.gamma', 'vision_model.blocks.6.attn.lora_A_q', 'vision_model.blocks.10.mlp.fc1.bias', 'vision_model.blocks.3.mlp.fc1.weight', 'vision_model.blocks.13.attn.qkv.bias', 'vision_model.blocks.5.norm2.weight', 'vision_model.blocks.18.norm2.bias', 'vision_model.blocks.16.attn.proj.weight', 'vision_model.blocks.1.ls2.gamma', 'model.layers.29.self_attn.q_proj.lora_A', 'vision_model.blocks.18.mlp.fc2.bias', 'vision_model.blocks.23.mlp.fc1.weight', 'vision_model.blocks.22.attn.lora_A_q', 'model.layers.28.self_attn.v_proj.lora_A', 'model.layers.19.self_attn.q_proj.lora_A', 'model.layers.13.self_attn.q_proj.lora_A', 'vision_model.blocks.1.attn.proj.weight', 'vision_model.blocks.4.attn.lora_B_q', 'vision_model.blocks.21.norm1.weight', 'vision_model.blocks.8.norm1.bias', 'vision_model.blocks.11.ls2.gamma', 'vision_model.blocks.7.mlp.fc1.bias', 'model.layers.27.self_attn.v_proj.lora_B', 'vision_model.blocks.3.attn.qkv.weight', 'vision_model.blocks.2.mlp.fc2.weight', 'vision_model.blocks.10.attn.proj.weight', 'vision_model.blocks.2.norm1.weight', 'vision_model.blocks.4.norm1.bias', 'vision_model.blocks.11.mlp.fc2.bias', 'vision_model.blocks.12.norm2.weight', 'vision_model.blocks.7.attn.lora_A_v', 'model.layers.18.self_attn.v_proj.lora_B', 'vision_model.blocks.23.norm1.bias', 'vision_model.blocks.0.attn.lora_B_q', 'vision_model.blocks.18.attn.lora_A_v', 'vision_model.blocks.4.attn.lora_A_q', 'vision_model.blocks.10.norm1.bias', 'vision_model.blocks.20.mlp.fc1.bias', 'vision_model.blocks.4.mlp.fc2.bias', 'vision_model.blocks.17.attn.qkv.weight', 'vision_model.blocks.8.norm1.weight', 'vision_model.blocks.21.attn.qkv.bias', 'model.layers.1.self_attn.q_proj.lora_A', 'vision_model.blocks.13.attn.lora_A_v', 'vision_model.blocks.6.norm1.bias', 'vision_model.blocks.11.mlp.fc1.weight', 'vision_model.blocks.19.mlp.fc2.bias', 'vision_model.blocks.5.norm1.weight', 'vision_model.blocks.1.mlp.fc2.bias', 'vision_model.blocks.4.attn.lora_A_v', 'vision_model.blocks.17.attn.lora_A_v', 'model.layers.19.self_attn.v_proj.lora_B', 'vision_model.blocks.23.norm1.weight', 'vision_model.blocks.22.norm2.weight', 'vision_model.blocks.10.attn.proj.bias', 'model.layers.1.self_attn.v_proj.lora_A', 'vision_model.blocks.1.norm2.weight', 'model.layers.28.self_attn.q_proj.lora_B', 'vision_model.blocks.13.norm1.weight', 'vision_model.mask_token', 'vision_model.blocks.11.attn.lora_A_q', 'vision_model.blocks.8.norm2.weight', 'vision_model.blocks.15.norm1.weight', 'vision_model.blocks.14.attn.lora_B_v', 'model.layers.6.self_attn.q_proj.lora_B', 'vision_model.blocks.0.ls2.gamma', 'vision_model.blocks.1.mlp.fc1.bias', 'vision_model.blocks.22.ls1.gamma', 'vision_model.blocks.23.attn.lora_A_v', 'vision_model.blocks.12.mlp.fc2.weight', 'vision_model.blocks.11.norm2.bias', 'model.layers.29.self_attn.q_proj.lora_B', 'vision_model.blocks.0.norm2.weight', 'model.layers.0.self_attn.q_proj.lora_A', 'vision_model.blocks.5.attn.lora_B_q', 'model.layers.24.self_attn.q_proj.lora_B', 'vision_model.blocks.14.mlp.fc2.weight', 'vision_model.blocks.9.attn.qkv.weight', 'vision_model.blocks.12.attn.proj.weight', 'model.layers.9.self_attn.v_proj.lora_A', 'vision_model.blocks.22.ls2.gamma', 'vision_model.blocks.6.attn.qkv.bias', 'vision_model.blocks.2.attn.lora_A_v', 'vision_model.blocks.0.mlp.fc2.bias', 'model.layers.3.self_attn.v_proj.lora_A', 'vision_model.blocks.11.norm1.bias', 'vision_model.blocks.22.attn.lora_B_q', 'model.layers.6.self_attn.v_proj.lora_A', 'vision_model.blocks.21.attn.lora_B_v', 'vision_model.blocks.22.attn.qkv.weight', 'vision_model.blocks.10.attn.qkv.bias', 'vision_model.blocks.21.mlp.fc1.bias', 'vision_model.blocks.7.norm1.weight', 'vision_model.blocks.0.attn.qkv.weight', 'vision_model.blocks.12.norm1.weight', 'vision_model.blocks.5.ls2.gamma', 'vision_model.blocks.15.mlp.fc2.bias', 'vision_model.blocks.22.norm2.bias', 'vision_model.blocks.5.attn.lora_A_v', 'vision_model.blocks.1.norm1.weight', 'vision_model.blocks.11.attn.qkv.weight', 'vision_model.blocks.16.mlp.fc2.weight', 'vision_model.blocks.23.attn.lora_B_q', 'model.layers.23.self_attn.v_proj.lora_B', 'vision_model.blocks.9.norm2.weight', 'vision_model.blocks.10.mlp.fc1.weight', 'vision_model.blocks.3.norm2.weight', 'vision_model.blocks.17.attn.qkv.bias', 'model.layers.25.self_attn.v_proj.lora_A', 'vision_model.blocks.23.mlp.fc2.bias', 'model.layers.21.self_attn.q_proj.lora_B', 'model.layers.21.self_attn.q_proj.lora_A', 'vision_model.blocks.11.mlp.fc2.weight', 'vision_model.blocks.12.ls1.gamma', 'model.layers.26.self_attn.v_proj.lora_A', 'model.layers.2.self_attn.q_proj.lora_A', 'vision_model.blocks.13.attn.lora_B_v', 'model.layers.10.self_attn.v_proj.lora_B', 'vision_model.blocks.7.ls1.gamma', 'vision_model.blocks.12.attn.lora_A_q', 'vision_model.blocks.9.attn.lora_A_q', 'model.layers.20.self_attn.q_proj.lora_A', 'vision_model.blocks.4.mlp.fc1.weight', 'vision_model.blocks.7.attn.lora_A_q', 'model.layers.22.self_attn.v_proj.lora_B', 'vision_model.blocks.22.attn.qkv.bias', 'model.layers.4.self_attn.q_proj.lora_A', 'vision_model.blocks.14.attn.lora_B_q', 'model.layers.26.self_attn.q_proj.lora_B', 'vision_model.blocks.3.attn.proj.bias', 'vision_model.blocks.2.ls2.gamma', 'vision_model.blocks.12.norm2.bias', 'vision_model.blocks.9.mlp.fc2.weight', 'model.layers.20.self_attn.v_proj.lora_B', 'model.layers.30.self_attn.q_proj.lora_B', 'vision_model.blocks.7.mlp.fc2.weight', 'model.layers.18.self_attn.q_proj.lora_B', 'model.layers.6.self_attn.q_proj.lora_A', 'model.layers.16.self_attn.q_proj.lora_A', 'vision_model.blocks.3.norm2.bias', 'model.layers.3.self_attn.v_proj.lora_B', 'vision_model.blocks.3.attn.qkv.bias', 'vision_model.blocks.7.mlp.fc1.weight', 'model.layers.18.self_attn.v_proj.lora_A', 'vision_model.blocks.6.mlp.fc2.bias', 'vision_model.blocks.18.norm1.bias', 'vision_model.blocks.22.mlp.fc1.weight', 'vision_model.blocks.19.attn.proj.weight', 'vision_model.blocks.14.attn.proj.bias', 'model.layers.23.self_attn.q_proj.lora_A', 'vision_model.blocks.4.mlp.fc2.weight', 'vision_model.blocks.7.attn.lora_B_q', 'vision_model.blocks.0.mlp.fc2.weight', 'vision_model.blocks.13.norm1.bias', 'vision_model.blocks.14.attn.qkv.weight', 'vision_model.blocks.8.mlp.fc1.bias', 'vision_model.blocks.14.mlp.fc1.weight', 'vision_model.blocks.16.attn.lora_A_q', 'vision_model.blocks.17.attn.lora_B_v', 'vision_model.norm.bias', 'vision_model.blocks.17.norm2.bias', 'vision_model.blocks.5.attn.qkv.weight', 'vision_model.blocks.12.mlp.fc1.bias', 'model.layers.14.self_attn.q_proj.lora_A', 'vision_model.blocks.6.attn.proj.bias', 'vision_model.norm.weight', 'model.layers.8.self_attn.q_proj.lora_A', 'vision_model.blocks.10.ls2.gamma', 'vision_model.blocks.8.attn.lora_B_q', 'vision_model.blocks.11.attn.qkv.bias', 'vision_model.blocks.14.norm1.weight', 'model.layers.31.self_attn.q_proj.lora_B', 'vision_model.blocks.2.attn.proj.bias', 'vision_model.blocks.1.mlp.fc2.weight', 'vision_model.blocks.19.mlp.fc2.weight', 'model.layers.31.self_attn.q_proj.lora_A', 'model.layers.20.self_attn.v_proj.lora_A', 'vision_model.blocks.18.ls2.gamma', 'vision_model.blocks.2.attn.proj.weight', 'model.layers.5.self_attn.v_proj.lora_B', 'vision_model.blocks.5.norm1.bias', 'vision_model.blocks.15.attn.lora_A_v', 'vision_model.blocks.0.attn.qkv.bias', 'vision_model.blocks.7.mlp.fc2.bias', 'vision_model.blocks.10.attn.lora_B_q', 'model.layers.15.self_attn.v_proj.lora_B', 'vision_model.blocks.19.attn.lora_A_v', 'vision_model.blocks.20.attn.lora_B_q', 'vision_model.blocks.10.attn.lora_A_v', 'vision_model.blocks.19.attn.proj.bias', 'vision_model.blocks.10.attn.lora_A_q', 'vision_model.blocks.20.attn.lora_A_v', 'vision_model.blocks.15.norm2.weight', 'vision_model.blocks.2.mlp.fc1.weight', 'vision_model.blocks.16.attn.lora_A_v', 'vision_model.blocks.4.attn.proj.weight', 'vision_model.blocks.8.ls2.gamma', 'model.layers.21.self_attn.v_proj.lora_A', 'vision_model.blocks.20.attn.qkv.bias', 'vision_model.blocks.19.norm2.bias', 'vision_model.blocks.7.norm2.weight', 'model.layers.30.self_attn.q_proj.lora_A', 'model.layers.3.self_attn.q_proj.lora_A', 'vision_model.blocks.15.norm1.bias', 'vision_model.blocks.9.mlp.fc1.weight', 'model.layers.5.self_attn.v_proj.lora_A', 'vision_model.blocks.12.attn.proj.bias', 'vision_model.blocks.4.norm2.bias', 'vision_model.blocks.10.mlp.fc2.weight', 'vision_model.blocks.21.ls1.gamma', 'vision_model.blocks.13.attn.lora_A_q', 'model.layers.5.self_attn.q_proj.lora_A', 'vision_model.blocks.23.attn.proj.bias', 'vision_model.blocks.23.attn.proj.weight', 'vision_model.blocks.7.norm1.bias', 'vision_model.blocks.9.ls2.gamma', 'vision_model.blocks.4.attn.proj.bias', 'vision_model.blocks.23.mlp.fc2.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.

Loading checkpoint shards: 100%|██████████| 2/2 [00:14<00:00,  6.69s/it]
Loading checkpoint shards: 100%|██████████| 2/2 [00:14<00:00,  7.45s/it]
Some weights of LocLLMModel were not initialized from the model checkpoint at ./checkpoints/model_weights/vicuna-7b-v1.5 and are newly initialized: ['vision_model.blocks.5.attn.lora_B_q', 'model.layers.13.self_attn.v_proj.lora_A', 'vision_model.blocks.15.mlp.fc2.weight', 'vision_model.blocks.3.ls2.gamma', 'vision_model.blocks.21.attn.lora_B_v', 'vision_model.blocks.14.mlp.fc2.bias', 'vision_model.blocks.12.mlp.fc1.weight', 'model.layers.12.self_attn.q_proj.lora_B', 'vision_model.blocks.17.attn.proj.bias', 'vision_model.blocks.18.norm1.bias', 'vision_model.blocks.14.attn.qkv.weight', 'model.layers.17.self_attn.q_proj.lora_A', 'vision_model.blocks.15.attn.proj.bias', 'model.layers.0.self_attn.q_proj.lora_B', 'vision_model.blocks.21.attn.proj.weight', 'model.layers.29.self_attn.q_proj.lora_A', 'model.layers.23.self_attn.v_proj.lora_B', 'vision_model.blocks.19.mlp.fc2.bias', 'vision_model.blocks.14.norm2.weight', 'vision_model.blocks.18.attn.lora_B_v', 'vision_model.blocks.4.attn.lora_B_q', 'model.layers.20.self_attn.q_proj.lora_B', 'vision_model.blocks.7.ls1.gamma', 'vision_model.blocks.20.attn.lora_B_q', 'vision_model.blocks.19.attn.qkv.bias', 'model.layers.18.self_attn.q_proj.lora_B', 'vision_model.blocks.18.attn.lora_A_v', 'vision_model.blocks.4.ls2.gamma', 'vision_model.blocks.3.attn.proj.weight', 'vision_model.blocks.9.norm2.weight', 'vision_model.blocks.18.norm2.bias', 'vision_model.blocks.14.attn.qkv.bias', 'vision_model.blocks.13.attn.lora_A_v', 'vision_model.blocks.7.norm1.bias', 'vision_model.blocks.3.attn.proj.bias', 'model.layers.13.self_attn.q_proj.lora_A', 'vision_model.blocks.12.attn.lora_A_q', 'vision_model.blocks.10.attn.proj.bias', 'model.layers.17.self_attn.v_proj.lora_B', 'vision_model.blocks.11.norm2.weight', 'vision_model.blocks.14.attn.proj.weight', 'vision_model.cls_token', 'vision_model.blocks.13.mlp.fc2.bias', 'vision_model.blocks.9.attn.qkv.bias', 'model.layers.27.self_attn.q_proj.lora_B', 'vision_model.blocks.23.norm2.bias', 'model.layers.8.self_attn.v_proj.lora_B', 'vision_model.blocks.7.attn.lora_B_q', 'model.layers.10.self_attn.q_proj.lora_A', 'vision_model.blocks.3.norm1.bias', 'vision_model.blocks.2.mlp.fc1.bias', 'model.layers.17.self_attn.q_proj.lora_B', 'vision_model.blocks.16.norm1.bias', 'vision_model.blocks.17.norm1.bias', 'vision_model.blocks.22.attn.lora_B_q', 'vision_model.blocks.12.attn.qkv.weight', 'vision_model.blocks.3.attn.lora_B_q', 'vision_model.blocks.2.attn.lora_B_v', 'vision_model.blocks.17.mlp.fc1.bias', 'model.layers.12.self_attn.v_proj.lora_B', 'vision_model.blocks.9.attn.proj.bias', 'vision_model.blocks.3.mlp.fc2.bias', 'model.layers.3.self_attn.v_proj.lora_B', 'vision_model.blocks.3.attn.lora_A_q', 'vision_model.blocks.18.mlp.fc1.bias', 'vision_model.blocks.21.attn.proj.bias', 'vision_model.blocks.16.attn.lora_B_q', 'vision_model.blocks.2.norm1.weight', 'model.layers.29.self_attn.v_proj.lora_A', 'vision_model.blocks.15.attn.lora_B_v', 'model.layers.12.self_attn.v_proj.lora_A', 'vision_model.blocks.12.norm1.weight', 'vision_model.blocks.16.mlp.fc1.weight', 'model.layers.28.self_attn.q_proj.lora_B', 'vision_model.blocks.11.attn.lora_A_q', 'model.layers.5.self_attn.v_proj.lora_B', 'vision_model.blocks.16.attn.lora_A_v', 'vision_model.blocks.8.mlp.fc2.weight', 'vision_model.blocks.9.norm2.bias', 'vision_model.blocks.1.attn.lora_A_v', 'model.layers.5.self_attn.v_proj.lora_A', 'vision_model.blocks.21.attn.qkv.weight', 'vision_model.patch_embed.proj.bias', 'model.layers.11.self_attn.v_proj.lora_B', 'vision_model.blocks.9.mlp.fc1.weight', 'vision_model.blocks.11.attn.lora_B_q', 'vision_model.blocks.16.mlp.fc2.bias', 'vision_model.blocks.20.norm1.weight', 'vision_model.blocks.18.norm2.weight', 'vision_model.blocks.17.attn.proj.weight', 'vision_model.blocks.20.norm1.bias', 'vision_model.blocks.23.attn.lora_A_q', 'model.layers.31.self_attn.v_proj.lora_A', 'vision_model.blocks.18.norm1.weight', 'model.layers.30.self_attn.v_proj.lora_B', 'vision_model.blocks.15.attn.qkv.bias', 'model.layers.14.self_attn.v_proj.lora_A', 'vision_model.blocks.9.norm1.weight', 'vision_model.blocks.22.norm2.bias', 'vision_model.blocks.21.mlp.fc1.weight', 'vision_model.blocks.7.mlp.fc1.weight', 'model.layers.0.self_attn.v_proj.lora_A', 'vision_model.blocks.20.attn.lora_A_v', 'model.layers.20.self_attn.v_proj.lora_B', 'model.layers.30.self_attn.q_proj.lora_B', 'vision_model.blocks.23.attn.qkv.bias', 'vision_model.blocks.6.ls2.gamma', 'vision_model.blocks.5.attn.lora_A_q', 'vision_model.blocks.21.ls1.gamma', 'vision_model.blocks.13.attn.lora_B_v', 'vision_model.blocks.12.mlp.fc2.bias', 'model.layers.12.self_attn.q_proj.lora_A', 'model.layers.31.self_attn.q_proj.lora_A', 'model.layers.0.self_attn.q_proj.lora_A', 'model.layers.25.self_attn.v_proj.lora_B', 'vision_model.blocks.12.attn.proj.bias', 'model.layers.16.self_attn.v_proj.lora_A', 'vision_model.blocks.4.mlp.fc1.bias', 'vision_model.blocks.19.norm2.weight', 'vision_model.blocks.6.norm1.bias', 'vision_model.blocks.7.attn.lora_A_q', 'model.layers.30.self_attn.q_proj.lora_A', 'vision_model.blocks.17.ls2.gamma', 'vision_model.blocks.23.attn.lora_B_v', 'vision_model.blocks.19.mlp.fc2.weight', 'vision_model.blocks.0.mlp.fc1.bias', 'vision_model.blocks.5.norm1.bias', 'vision_model.blocks.5.norm2.bias', 'vision_model.blocks.16.ls1.gamma', 'model.layers.22.self_attn.v_proj.lora_B', 'vision_model.blocks.13.mlp.fc1.weight', 'vision_model.blocks.5.norm1.weight', 'vision_model.blocks.7.attn.qkv.weight', 'vision_model.blocks.14.ls2.gamma', 'vision_model.blocks.23.attn.qkv.weight', 'model.layers.16.self_attn.q_proj.lora_A', 'vision_model.blocks.20.attn.qkv.weight', 'vision_model.blocks.22.mlp.fc2.weight', 'vision_model.blocks.11.attn.qkv.bias', 'vision_model.blocks.18.ls2.gamma', 'model.layers.21.self_attn.v_proj.lora_B', 'model.layers.2.self_attn.q_proj.lora_A', 'model.layers.18.self_attn.v_proj.lora_B', 'vision_model.blocks.6.attn.qkv.bias', 'vision_model.blocks.3.attn.qkv.weight', 'vision_model.blocks.17.ls1.gamma', 'vision_model.blocks.9.attn.lora_A_v', 'model.layers.4.self_attn.v_proj.lora_B', 'vision_model.blocks.5.mlp.fc1.weight', 'vision_model.blocks.21.attn.lora_B_q', 'model.layers.6.self_attn.q_proj.lora_A', 'vision_model.blocks.1.attn.lora_B_q', 'vision_model.blocks.4.attn.lora_B_v', 'vision_model.blocks.15.ls2.gamma', 'vision_model.blocks.19.attn.lora_A_q', 'model.layers.3.self_attn.q_proj.lora_A', 'vision_model.blocks.3.norm1.weight', 'vision_model.blocks.2.ls1.gamma', 'model.layers.19.self_attn.q_proj.lora_A', 'vision_model.blocks.2.mlp.fc2.weight', 'vision_model.blocks.4.norm1.bias', 'vision_model.blocks.18.attn.qkv.weight', 'model.layers.13.self_attn.q_proj.lora_B', 'vision_model.blocks.3.attn.lora_B_v', 'vision_model.blocks.11.norm1.bias', 'vision_model.blocks.6.attn.qkv.weight', 'vision_model.blocks.8.attn.proj.bias', 'vision_model.blocks.23.attn.lora_B_q', 'vision_model.blocks.3.attn.qkv.bias', 'model.layers.19.self_attn.v_proj.lora_B', 'vision_model.blocks.1.attn.lora_B_v', 'vision_model.blocks.23.norm1.bias', 'vision_model.blocks.7.attn.proj.weight', 'vision_model.blocks.15.ls1.gamma', 'vision_model.blocks.2.norm2.bias', 'vision_model.blocks.6.mlp.fc1.weight', 'vision_model.blocks.12.mlp.fc2.weight', 'vision_model.blocks.13.attn.qkv.bias', 'vision_model.blocks.20.norm2.bias', 'vision_model.blocks.0.norm1.weight', 'vision_model.blocks.8.attn.lora_A_v', 'model.layers.30.self_attn.v_proj.lora_A', 'vision_model.patch_embed.proj.weight', 'vision_model.blocks.7.norm2.weight', 'vision_model.blocks.13.mlp.fc1.bias', 'model.layers.26.self_attn.v_proj.lora_B', 'vision_model.blocks.17.mlp.fc2.bias', 'vision_model.blocks.5.attn.lora_B_v', 'model.layers.28.self_attn.v_proj.lora_B', 'vision_model.blocks.21.attn.qkv.bias', 'vision_model.blocks.23.mlp.fc2.weight', 'model.layers.24.self_attn.q_proj.lora_A', 'vision_model.blocks.2.norm2.weight', 'vision_model.blocks.7.norm1.weight', 'model.layers.18.self_attn.q_proj.lora_A', 'model.layers.24.self_attn.v_proj.lora_B', 'model.layers.9.self_attn.v_proj.lora_A', 'vision_model.blocks.18.attn.lora_B_q', 'vision_model.blocks.6.mlp.fc2.bias', 'vision_model.blocks.2.attn.lora_B_q', 'model.layers.1.self_attn.v_proj.lora_B', 'vision_model.blocks.8.attn.lora_A_q', 'vision_model.blocks.2.attn.proj.bias', 'vision_model.blocks.15.mlp.fc2.bias', 'vision_model.blocks.6.attn.proj.bias', 'vision_model.blocks.0.ls2.gamma', 'vision_model.blocks.19.attn.lora_A_v', 'vision_model.blocks.21.mlp.fc2.bias', 'vision_model.blocks.15.attn.lora_B_q', 'vision_model.blocks.13.norm2.weight', 'vision_model.blocks.20.attn.proj.weight', 'vision_model.blocks.17.mlp.fc2.weight', 'model.layers.9.self_attn.q_proj.lora_B', 'vision_model.blocks.9.norm1.bias', 'vision_model.blocks.1.mlp.fc2.bias', 'vision_model.blocks.4.attn.proj.weight', 'vision_model.blocks.13.norm1.weight', 'vision_model.blocks.21.mlp.fc2.weight', 'model.layers.15.self_attn.v_proj.lora_B', 'vision_model.blocks.7.ls2.gamma', 'vision_model.blocks.3.norm2.weight', 'vision_model.blocks.18.mlp.fc1.weight', 'vision_model.blocks.11.mlp.fc2.weight', 'vision_model.blocks.12.attn.lora_A_v', 'vision_model.blocks.5.attn.proj.bias', 'vision_model.blocks.12.attn.qkv.bias', 'vision_model.blocks.0.mlp.fc2.weight', 'vision_model.blocks.8.attn.qkv.bias', 'model.layers.5.self_attn.q_proj.lora_A', 'vision_model.blocks.2.attn.qkv.bias', 'vision_model.blocks.7.attn.lora_A_v', 'vision_model.blocks.0.attn.qkv.bias', 'model.layers.1.self_attn.q_proj.lora_A', 'model.layers.7.self_attn.v_proj.lora_B', 'vision_model.blocks.8.attn.lora_B_q', 'model.layers.25.self_attn.q_proj.lora_A', 'vision_model.blocks.1.norm2.weight', 'vision_model.blocks.17.attn.qkv.bias', 'vision_model.blocks.19.attn.proj.bias', 'vision_model.blocks.20.norm2.weight', 'vision_model.blocks.22.norm1.bias', 'vision_model.blocks.0.attn.lora_A_v', 'vision_model.blocks.12.mlp.fc1.bias', 'vision_model.blocks.8.norm2.weight', 'model.layers.21.self_attn.q_proj.lora_A', 'vision_model.blocks.21.mlp.fc1.bias', 'vision_model.blocks.4.mlp.fc2.bias', 'model.layers.28.self_attn.q_proj.lora_A', 'vision_model.blocks.16.attn.proj.weight', 'vision_model.blocks.6.attn.lora_B_v', 'vision_model.blocks.0.ls1.gamma', 'vision_model.blocks.13.ls1.gamma', 'model.layers.19.self_attn.q_proj.lora_B', 'vision_model.blocks.17.norm2.weight', 'vision_model.blocks.7.attn.lora_B_v', 'vision_model.blocks.8.ls1.gamma', 'vision_model.blocks.10.mlp.fc2.weight', 'vision_model.blocks.13.attn.lora_B_q', 'vision_model.blocks.5.norm2.weight', 'vision_model.blocks.14.attn.lora_A_q', 'vision_model.blocks.16.mlp.fc1.bias', 'vision_model.blocks.4.attn.qkv.bias', 'vision_model.blocks.3.mlp.fc2.weight', 'vision_model.blocks.8.norm1.weight', 'vision_model.blocks.1.attn.lora_A_q', 'vision_model.blocks.10.mlp.fc1.bias', 'model.layers.6.self_attn.v_proj.lora_B', 'vision_model.blocks.13.attn.lora_A_q', 'model.layers.22.self_attn.q_proj.lora_A', 'vision_model.blocks.8.norm1.bias', 'vision_model.blocks.4.attn.lora_A_q', 'vision_model.blocks.5.attn.qkv.bias', 'vision_model.blocks.8.attn.qkv.weight', 'vision_model.blocks.22.mlp.fc1.weight', 'vision_model.blocks.15.norm2.weight', 'vision_model.blocks.12.attn.lora_B_q', 'vision_model.blocks.16.attn.lora_B_v', 'vision_model.blocks.12.ls1.gamma', 'model.layers.19.self_attn.v_proj.lora_A', 'vision_model.blocks.10.ls1.gamma', 'vision_model.blocks.7.attn.proj.bias', 'vision_model.blocks.21.attn.lora_A_v', 'model.layers.29.self_attn.q_proj.lora_B', 'vision_model.blocks.14.norm2.bias', 'vision_model.blocks.15.attn.lora_A_q', 'model.layers.14.self_attn.v_proj.lora_B', 'model.layers.27.self_attn.q_proj.lora_A', 'model.layers.7.self_attn.q_proj.lora_A', 'model.layers.1.self_attn.v_proj.lora_A', 'model.layers.11.self_attn.q_proj.lora_A', 'model.layers.8.self_attn.q_proj.lora_B', 'vision_model.blocks.11.mlp.fc1.weight', 'model.layers.31.self_attn.q_proj.lora_B', 'vision_model.blocks.0.attn.qkv.weight', 'vision_model.blocks.23.norm2.weight', 'vision_model.blocks.23.mlp.fc1.weight', 'model.layers.9.self_attn.v_proj.lora_B', 'vision_model.blocks.11.norm1.weight', 'model.layers.7.self_attn.q_proj.lora_B', 'vision_model.blocks.4.attn.proj.bias', 'model.layers.22.self_attn.q_proj.lora_B', 'vision_model.blocks.19.attn.lora_B_q', 'vision_model.blocks.0.mlp.fc2.bias', 'vision_model.blocks.21.norm1.weight', 'vision_model.blocks.8.ls2.gamma', 'vision_model.blocks.15.mlp.fc1.bias', 'vision_model.blocks.16.attn.qkv.bias', 'vision_model.blocks.21.ls2.gamma', 'vision_model.blocks.12.norm2.weight', 'vision_model.blocks.20.attn.lora_A_q', 'vision_model.blocks.22.attn.lora_A_q', 'vision_model.blocks.19.ls2.gamma', 'vision_model.blocks.20.attn.lora_B_v', 'vision_model.blocks.5.attn.lora_A_v', 'vision_model.blocks.18.attn.lora_A_q', 'vision_model.blocks.20.mlp.fc2.bias', 'vision_model.blocks.22.ls2.gamma', 'model.layers.20.self_attn.v_proj.lora_A', 'vision_model.blocks.6.mlp.fc2.weight', 'vision_model.blocks.6.attn.lora_A_v', 'model.layers.2.self_attn.q_proj.lora_B', 'vision_model.blocks.14.attn.lora_B_v', 'vision_model.blocks.16.ls2.gamma', 'vision_model.blocks.23.attn.proj.weight', 'vision_model.blocks.5.mlp.fc2.bias', 'vision_model.blocks.10.attn.lora_B_v', 'model.layers.26.self_attn.q_proj.lora_B', 'vision_model.blocks.10.mlp.fc1.weight', 'vision_model.blocks.13.norm2.bias', 'vision_model.blocks.2.norm1.bias', 'vision_model.blocks.23.ls1.gamma', 'vision_model.blocks.1.ls1.gamma', 'vision_model.blocks.19.norm2.bias', 'model.layers.10.self_attn.q_proj.lora_B', 'vision_model.blocks.9.mlp.fc1.bias', 'vision_model.blocks.22.norm1.weight', 'vision_model.blocks.22.attn.qkv.bias', 'vision_model.blocks.2.attn.proj.weight', 'vision_model.blocks.16.norm2.bias', 'vision_model.blocks.14.attn.proj.bias', 'vision_model.pos_embed', 'vision_model.blocks.9.attn.lora_B_v', 'vision_model.blocks.17.mlp.fc1.weight', 'vision_model.blocks.5.attn.proj.weight', 'model.layers.14.self_attn.q_proj.lora_A', 'vision_model.blocks.11.norm2.bias', 'vision_model.blocks.6.norm2.weight', 'vision_model.blocks.17.norm2.bias', 'model.layers.25.self_attn.q_proj.lora_B', 'vision_model.blocks.2.mlp.fc1.weight', 'vision_model.mask_token', 'vision_model.blocks.10.attn.qkv.weight', 'model.layers.3.self_attn.v_proj.lora_A', 'vision_model.blocks.13.ls2.gamma', 'vision_model.blocks.8.norm2.bias', 'model.layers.23.self_attn.q_proj.lora_B', 'vision_model.blocks.0.norm2.bias', 'vision_model.blocks.10.norm2.weight', 'vision_model.blocks.13.norm1.bias', 'vision_model.blocks.15.norm2.bias', 'vision_model.blocks.9.ls1.gamma', 'vision_model.blocks.2.ls2.gamma', 'model.layers.11.self_attn.v_proj.lora_A', 'vision_model.blocks.1.attn.proj.weight', 'vision_model.blocks.14.norm1.bias', 'vision_model.blocks.16.norm1.weight', 'vision_model.blocks.5.mlp.fc2.weight', 'vision_model.blocks.1.norm1.weight', 'vision_model.blocks.4.attn.lora_A_v', 'vision_model.blocks.12.norm1.bias', 'model.layers.9.self_attn.q_proj.lora_A', 'model.layers.21.self_attn.q_proj.lora_B', 'vision_model.blocks.19.attn.qkv.weight', 'vision_model.blocks.0.attn.proj.weight', 'vision_model.blocks.19.ls1.gamma', 'model.layers.4.self_attn.q_proj.lora_B', 'vision_model.blocks.11.ls1.gamma', 'vision_model.blocks.1.mlp.fc2.weight', 'vision_model.blocks.10.attn.lora_B_q', 'vision_model.blocks.17.attn.lora_B_q', 'vision_model.blocks.6.ls1.gamma', 'vision_model.blocks.16.attn.lora_A_q', 'model.layers.15.self_attn.v_proj.lora_A', 'vision_model.blocks.13.mlp.fc2.weight', 'model.layers.15.self_attn.q_proj.lora_A', 'vision_model.blocks.16.attn.proj.bias', 'vision_model.blocks.2.attn.lora_A_q', 'vision_model.blocks.1.mlp.fc1.bias', 'vision_model.blocks.3.attn.lora_A_v', 'vision_model.blocks.13.attn.proj.weight', 'vision_model.blocks.3.norm2.bias', 'vision_model.blocks.23.attn.lora_A_v', 'vision_model.blocks.14.norm1.weight', 'vision_model.blocks.2.attn.qkv.weight', 'vision_model.blocks.6.attn.proj.weight', 'vision_model.blocks.22.attn.lora_A_v', 'model.layers.2.self_attn.v_proj.lora_A', 'vision_model.blocks.19.mlp.fc1.bias', 'vision_model.blocks.22.attn.qkv.weight', 'vision_model.blocks.2.mlp.fc2.bias', 'vision_model.blocks.6.norm1.weight', 'vision_model.blocks.12.ls2.gamma', 'vision_model.blocks.4.mlp.fc1.weight', 'vision_model.blocks.20.ls1.gamma', 'vision_model.blocks.1.mlp.fc1.weight', 'vision_model.blocks.3.ls1.gamma', 'model.layers.22.self_attn.v_proj.lora_A', 'vision_model.blocks.9.mlp.fc2.weight', 'vision_model.blocks.14.attn.lora_A_v', 'model.layers.6.self_attn.v_proj.lora_A', 'vision_model.blocks.0.mlp.fc1.weight', 'vision_model.blocks.18.attn.qkv.bias', 'model.layers.8.self_attn.q_proj.lora_A', 'vision_model.blocks.5.attn.qkv.weight', 'vision_model.blocks.9.attn.lora_A_q', 'vision_model.blocks.19.norm1.bias', 'model.layers.17.self_attn.v_proj.lora_A', 'vision_model.blocks.21.norm2.weight', 'vision_model.blocks.4.ls1.gamma', 'vision_model.blocks.10.attn.lora_A_v', 'vision_model.blocks.22.attn.proj.weight', 'vision_model.blocks.19.attn.lora_B_v', 'vision_model.blocks.1.norm1.bias', 'vision_model.blocks.21.norm2.bias', 'vision_model.blocks.15.attn.qkv.weight', 'vision_model.blocks.11.mlp.fc1.bias', 'vision_model.blocks.11.attn.qkv.weight', 'vision_model.blocks.20.attn.proj.bias', 'model.layers.20.self_attn.q_proj.lora_A', 'vision_model.blocks.6.attn.lora_A_q', 'model.layers.6.self_attn.q_proj.lora_B', 'model.layers.11.self_attn.q_proj.lora_B', 'vision_model.blocks.4.mlp.fc2.weight', 'vision_model.blocks.23.mlp.fc2.bias', 'model.layers.4.self_attn.v_proj.lora_A', 'vision_model.blocks.23.ls2.gamma', 'vision_model.blocks.9.attn.qkv.weight', 'model.layers.0.self_attn.v_proj.lora_B', 'vision_model.blocks.22.norm2.weight', 'vision_model.blocks.10.attn.lora_A_q', 'vision_model.blocks.10.norm2.bias', 'vision_model.blocks.7.mlp.fc1.bias', 'vision_model.blocks.9.mlp.fc2.bias', 'vision_model.blocks.19.mlp.fc1.weight', 'vision_model.blocks.0.attn.lora_A_q', 'vision_model.blocks.19.attn.proj.weight', 'vision_model.blocks.23.mlp.fc1.bias', 'mm_projector.bias', 'vision_model.blocks.16.mlp.fc2.weight', 'vision_model.blocks.7.norm2.bias', 'model.layers.16.self_attn.q_proj.lora_B', 'vision_model.blocks.18.ls1.gamma', 'vision_model.blocks.0.attn.proj.bias', 'model.layers.29.self_attn.v_proj.lora_B', 'vision_model.blocks.4.norm2.bias', 'vision_model.blocks.8.attn.proj.weight', 'model.layers.26.self_attn.q_proj.lora_A', 'model.layers.8.self_attn.v_proj.lora_A', 'vision_model.blocks.8.mlp.fc2.bias', 'vision_model.blocks.12.norm2.bias', 'model.layers.31.self_attn.v_proj.lora_B', 'vision_model.blocks.8.attn.lora_B_v', 'vision_model.blocks.10.norm1.bias', 'vision_model.blocks.22.mlp.fc1.bias', 'vision_model.blocks.0.attn.lora_B_v', 'model.layers.23.self_attn.v_proj.lora_A', 'vision_model.blocks.11.attn.lora_A_v', 'vision_model.blocks.3.mlp.fc1.bias', 'model.layers.16.self_attn.v_proj.lora_B', 'vision_model.blocks.6.norm2.bias', 'vision_model.blocks.7.attn.qkv.bias', 'vision_model.blocks.14.mlp.fc2.weight', 'vision_model.blocks.14.attn.lora_B_q', 'vision_model.blocks.6.mlp.fc1.bias', 'vision_model.blocks.20.mlp.fc2.weight', 'vision_model.blocks.17.attn.lora_B_v', 'vision_model.blocks.11.attn.lora_B_v', 'model.layers.14.self_attn.q_proj.lora_B', 'vision_model.blocks.0.norm2.weight', 'vision_model.blocks.10.mlp.fc2.bias', 'vision_model.blocks.10.attn.proj.weight', 'vision_model.blocks.10.norm1.weight', 'vision_model.blocks.8.mlp.fc1.weight', 'model.layers.27.self_attn.v_proj.lora_B', 'model.layers.24.self_attn.q_proj.lora_B', 'model.layers.7.self_attn.v_proj.lora_A', 'model.layers.23.self_attn.q_proj.lora_A', 'vision_model.blocks.1.attn.qkv.weight', 'vision_model.blocks.18.attn.proj.weight', 'model.layers.5.self_attn.q_proj.lora_B', 'vision_model.blocks.4.norm2.weight', 'model.layers.18.self_attn.v_proj.lora_A', 'vision_model.blocks.22.attn.proj.bias', 'vision_model.blocks.10.attn.qkv.bias', 'model.layers.3.self_attn.q_proj.lora_B', 'model.layers.24.self_attn.v_proj.lora_A', 'vision_model.blocks.17.attn.lora_A_v', 'model.layers.26.self_attn.v_proj.lora_A', 'vision_model.blocks.15.norm1.weight', 'vision_model.blocks.5.ls2.gamma', 'vision_model.blocks.15.attn.proj.weight', 'vision_model.blocks.5.ls1.gamma', 'vision_model.blocks.22.ls1.gamma', 'vision_model.blocks.5.mlp.fc1.bias', 'vision_model.blocks.9.attn.proj.weight', 'vision_model.blocks.17.attn.lora_A_q', 'vision_model.blocks.17.norm1.weight', 'vision_model.norm.weight', 'vision_model.blocks.4.norm1.weight', 'vision_model.blocks.6.attn.lora_B_q', 'vision_model.blocks.3.mlp.fc1.weight', 'vision_model.blocks.11.attn.proj.bias', 'vision_model.blocks.15.norm1.bias', 'vision_model.blocks.11.mlp.fc2.bias', 'vision_model.blocks.1.norm2.bias', 'vision_model.blocks.10.ls2.gamma', 'vision_model.blocks.22.attn.lora_B_v', 'vision_model.blocks.13.attn.proj.bias', 'vision_model.blocks.7.mlp.fc2.weight', 'vision_model.blocks.17.attn.qkv.weight', 'vision_model.blocks.20.attn.qkv.bias', 'vision_model.blocks.8.mlp.fc1.bias', 'vision_model.blocks.14.mlp.fc1.weight', 'vision_model.blocks.14.mlp.fc1.bias', 'vision_model.blocks.12.attn.lora_B_v', 'vision_model.blocks.7.mlp.fc2.bias', 'vision_model.blocks.0.norm1.bias', 'vision_model.blocks.14.ls1.gamma', 'model.layers.2.self_attn.v_proj.lora_B', 'model.layers.27.self_attn.v_proj.lora_A', 'vision_model.blocks.16.norm2.weight', 'model.layers.10.self_attn.v_proj.lora_B', 'vision_model.blocks.18.mlp.fc2.bias', 'vision_model.blocks.9.attn.lora_B_q', 'vision_model.blocks.13.attn.qkv.weight', 'model.layers.10.self_attn.v_proj.lora_A', 'vision_model.blocks.22.mlp.fc2.bias', 'vision_model.blocks.15.mlp.fc1.weight', 'vision_model.blocks.20.mlp.fc1.weight', 'model.layers.21.self_attn.v_proj.lora_A', 'vision_model.blocks.20.ls2.gamma', 'model.layers.25.self_attn.v_proj.lora_A', 'vision_model.blocks.18.attn.proj.bias', 'vision_model.blocks.1.attn.qkv.bias', 'vision_model.blocks.20.mlp.fc1.bias', 'vision_model.blocks.2.attn.lora_A_v', 'vision_model.blocks.11.attn.proj.weight', 'vision_model.blocks.12.attn.proj.weight', 'model.layers.28.self_attn.v_proj.lora_A', 'vision_model.blocks.15.attn.lora_A_v', 'vision_model.blocks.1.ls2.gamma', 'model.layers.15.self_attn.q_proj.lora_B', 'vision_model.norm.bias', 'vision_model.blocks.11.ls2.gamma', 'vision_model.blocks.4.attn.qkv.weight', 'vision_model.blocks.9.ls2.gamma', 'vision_model.blocks.19.norm1.weight', 'mm_projector.weight', 'vision_model.blocks.18.mlp.fc2.weight', 'vision_model.blocks.23.norm1.weight', 'model.layers.4.self_attn.q_proj.lora_A', 'vision_model.blocks.0.attn.lora_B_q', 'vision_model.blocks.1.attn.proj.bias', 'vision_model.blocks.21.norm1.bias', 'vision_model.blocks.23.attn.proj.bias', 'vision_model.blocks.21.attn.lora_A_q', 'model.layers.13.self_attn.v_proj.lora_B', 'model.layers.1.self_attn.q_proj.lora_B', 'vision_model.blocks.16.attn.qkv.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
WARNING:root:Loading data...
loading annotations into memory...
WARNING:root:Loading data...
loading annotations into memory...
WARNING:root:Loading data...
loading annotations into memory...
WARNING:root:Loading data...
loading annotations into memory...
Done (t=6.02s)
creating index...
index created!
Done (t=5.94s)
creating index...
index created!
Done (t=7.05s)
creating index...
index created!
Done (t=7.78s)
creating index...
index created!
WARNING:root:The number of training samples is 149813
WARNING:root:Formatting inputs...Skip in lazy mode
Use Conv Format  keypoint
param_grad: ['model.layers.0.self_attn.q_proj.lora_A', 'model.layers.0.self_attn.q_proj.lora_B', 'model.layers.0.self_attn.v_proj.lora_A', 'model.layers.0.self_attn.v_proj.lora_B', 'model.layers.1.self_attn.q_proj.lora_A', 'model.layers.1.self_attn.q_proj.lora_B', 'model.layers.1.self_attn.v_proj.lora_A', 'model.layers.1.self_attn.v_proj.lora_B', 'model.layers.2.self_attn.q_proj.lora_A', 'model.layers.2.self_attn.q_proj.lora_B', 'model.layers.2.self_attn.v_proj.lora_A', 'model.layers.2.self_attn.v_proj.lora_B', 'model.layers.3.self_attn.q_proj.lora_A', 'model.layers.3.self_attn.q_proj.lora_B', 'model.layers.3.self_attn.v_proj.lora_A', 'model.layers.3.self_attn.v_proj.lora_B', 'model.layers.4.self_attn.q_proj.lora_A', 'model.layers.4.self_attn.q_proj.lora_B', 'model.layers.4.self_attn.v_proj.lora_A', 'model.layers.4.self_attn.v_proj.lora_B', 'model.layers.5.self_attn.q_proj.lora_A', 'model.layers.5.self_attn.q_proj.lora_B', 'model.layers.5.self_attn.v_proj.lora_A', 'model.layers.5.self_attn.v_proj.lora_B', 'model.layers.6.self_attn.q_proj.lora_A', 'model.layers.6.self_attn.q_proj.lora_B', 'model.layers.6.self_attn.v_proj.lora_A', 'model.layers.6.self_attn.v_proj.lora_B', 'model.layers.7.self_attn.q_proj.lora_A', 'model.layers.7.self_attn.q_proj.lora_B', 'model.layers.7.self_attn.v_proj.lora_A', 'model.layers.7.self_attn.v_proj.lora_B', 'model.layers.8.self_attn.q_proj.lora_A', 'model.layers.8.self_attn.q_proj.lora_B', 'model.layers.8.self_attn.v_proj.lora_A', 'model.layers.8.self_attn.v_proj.lora_B', 'model.layers.9.self_attn.q_proj.lora_A', 'model.layers.9.self_attn.q_proj.lora_B', 'model.layers.9.self_attn.v_proj.lora_A', 'model.layers.9.self_attn.v_proj.lora_B', 'model.layers.10.self_attn.q_proj.lora_A', 'model.layers.10.self_attn.q_proj.lora_B', 'model.layers.10.self_attn.v_proj.lora_A', 'model.layers.10.self_attn.v_proj.lora_B', 'model.layers.11.self_attn.q_proj.lora_A', 'model.layers.11.self_attn.q_proj.lora_B', 'model.layers.11.self_attn.v_proj.lora_A', 'model.layers.11.self_attn.v_proj.lora_B', 'model.layers.12.self_attn.q_proj.lora_A', 'model.layers.12.self_attn.q_proj.lora_B', 'model.layers.12.self_attn.v_proj.lora_A', 'model.layers.12.self_attn.v_proj.lora_B', 'model.layers.13.self_attn.q_proj.lora_A', 'model.layers.13.self_attn.q_proj.lora_B', 'model.layers.13.self_attn.v_proj.lora_A', 'model.layers.13.self_attn.v_proj.lora_B', 'model.layers.14.self_attn.q_proj.lora_A', 'model.layers.14.self_attn.q_proj.lora_B', 'model.layers.14.self_attn.v_proj.lora_A', 'model.layers.14.self_attn.v_proj.lora_B', 'model.layers.15.self_attn.q_proj.lora_A', 'model.layers.15.self_attn.q_proj.lora_B', 'model.layers.15.self_attn.v_proj.lora_A', 'model.layers.15.self_attn.v_proj.lora_B', 'model.layers.16.self_attn.q_proj.lora_A', 'model.layers.16.self_attn.q_proj.lora_B', 'model.layers.16.self_attn.v_proj.lora_A', 'model.layers.16.self_attn.v_proj.lora_B', 'model.layers.17.self_attn.q_proj.lora_A', 'model.layers.17.self_attn.q_proj.lora_B', 'model.layers.17.self_attn.v_proj.lora_A', 'model.layers.17.self_attn.v_proj.lora_B', 'model.layers.18.self_attn.q_proj.lora_A', 'model.layers.18.self_attn.q_proj.lora_B', 'model.layers.18.self_attn.v_proj.lora_A', 'model.layers.18.self_attn.v_proj.lora_B', 'model.layers.19.self_attn.q_proj.lora_A', 'model.layers.19.self_attn.q_proj.lora_B', 'model.layers.19.self_attn.v_proj.lora_A', 'model.layers.19.self_attn.v_proj.lora_B', 'model.layers.20.self_attn.q_proj.lora_A', 'model.layers.20.self_attn.q_proj.lora_B', 'model.layers.20.self_attn.v_proj.lora_A', 'model.layers.20.self_attn.v_proj.lora_B', 'model.layers.21.self_attn.q_proj.lora_A', 'model.layers.21.self_attn.q_proj.lora_B', 'model.layers.21.self_attn.v_proj.lora_A', 'model.layers.21.self_attn.v_proj.lora_B', 'model.layers.22.self_attn.q_proj.lora_A', 'model.layers.22.self_attn.q_proj.lora_B', 'model.layers.22.self_attn.v_proj.lora_A', 'model.layers.22.self_attn.v_proj.lora_B', 'model.layers.23.self_attn.q_proj.lora_A', 'model.layers.23.self_attn.q_proj.lora_B', 'model.layers.23.self_attn.v_proj.lora_A', 'model.layers.23.self_attn.v_proj.lora_B', 'model.layers.24.self_attn.q_proj.lora_A', 'model.layers.24.self_attn.q_proj.lora_B', 'model.layers.24.self_attn.v_proj.lora_A', 'model.layers.24.self_attn.v_proj.lora_B', 'model.layers.25.self_attn.q_proj.lora_A', 'model.layers.25.self_attn.q_proj.lora_B', 'model.layers.25.self_attn.v_proj.lora_A', 'model.layers.25.self_attn.v_proj.lora_B', 'model.layers.26.self_attn.q_proj.lora_A', 'model.layers.26.self_attn.q_proj.lora_B', 'model.layers.26.self_attn.v_proj.lora_A', 'model.layers.26.self_attn.v_proj.lora_B', 'model.layers.27.self_attn.q_proj.lora_A', 'model.layers.27.self_attn.q_proj.lora_B', 'model.layers.27.self_attn.v_proj.lora_A', 'model.layers.27.self_attn.v_proj.lora_B', 'model.layers.28.self_attn.q_proj.lora_A', 'model.layers.28.self_attn.q_proj.lora_B', 'model.layers.28.self_attn.v_proj.lora_A', 'model.layers.28.self_attn.v_proj.lora_B', 'model.layers.29.self_attn.q_proj.lora_A', 'model.layers.29.self_attn.q_proj.lora_B', 'model.layers.29.self_attn.v_proj.lora_A', 'model.layers.29.self_attn.v_proj.lora_B', 'model.layers.30.self_attn.q_proj.lora_A', 'model.layers.30.self_attn.q_proj.lora_B', 'model.layers.30.self_attn.v_proj.lora_A', 'model.layers.30.self_attn.v_proj.lora_B', 'model.layers.31.self_attn.q_proj.lora_A', 'model.layers.31.self_attn.q_proj.lora_B', 'model.layers.31.self_attn.v_proj.lora_A', 'model.layers.31.self_attn.v_proj.lora_B', 'vision_model.blocks.0.attn.lora_A_v', 'vision_model.blocks.0.attn.lora_B_v', 'vision_model.blocks.0.attn.lora_A_q', 'vision_model.blocks.0.attn.lora_B_q', 'vision_model.blocks.1.attn.lora_A_v', 'vision_model.blocks.1.attn.lora_B_v', 'vision_model.blocks.1.attn.lora_A_q', 'vision_model.blocks.1.attn.lora_B_q', 'vision_model.blocks.2.attn.lora_A_v', 'vision_model.blocks.2.attn.lora_B_v', 'vision_model.blocks.2.attn.lora_A_q', 'vision_model.blocks.2.attn.lora_B_q', 'vision_model.blocks.3.attn.lora_A_v', 'vision_model.blocks.3.attn.lora_B_v', 'vision_model.blocks.3.attn.lora_A_q', 'vision_model.blocks.3.attn.lora_B_q', 'vision_model.blocks.4.attn.lora_A_v', 'vision_model.blocks.4.attn.lora_B_v', 'vision_model.blocks.4.attn.lora_A_q', 'vision_model.blocks.4.attn.lora_B_q', 'vision_model.blocks.5.attn.lora_A_v', 'vision_model.blocks.5.attn.lora_B_v', 'vision_model.blocks.5.attn.lora_A_q', 'vision_model.blocks.5.attn.lora_B_q', 'vision_model.blocks.6.attn.lora_A_v', 'vision_model.blocks.6.attn.lora_B_v', 'vision_model.blocks.6.attn.lora_A_q', 'vision_model.blocks.6.attn.lora_B_q', 'vision_model.blocks.7.attn.lora_A_v', 'vision_model.blocks.7.attn.lora_B_v', 'vision_model.blocks.7.attn.lora_A_q', 'vision_model.blocks.7.attn.lora_B_q', 'vision_model.blocks.8.attn.lora_A_v', 'vision_model.blocks.8.attn.lora_B_v', 'vision_model.blocks.8.attn.lora_A_q', 'vision_model.blocks.8.attn.lora_B_q', 'vision_model.blocks.9.attn.lora_A_v', 'vision_model.blocks.9.attn.lora_B_v', 'vision_model.blocks.9.attn.lora_A_q', 'vision_model.blocks.9.attn.lora_B_q', 'vision_model.blocks.10.attn.lora_A_v', 'vision_model.blocks.10.attn.lora_B_v', 'vision_model.blocks.10.attn.lora_A_q', 'vision_model.blocks.10.attn.lora_B_q', 'vision_model.blocks.11.attn.lora_A_v', 'vision_model.blocks.11.attn.lora_B_v', 'vision_model.blocks.11.attn.lora_A_q', 'vision_model.blocks.11.attn.lora_B_q', 'vision_model.blocks.12.attn.lora_A_v', 'vision_model.blocks.12.attn.lora_B_v', 'vision_model.blocks.12.attn.lora_A_q', 'vision_model.blocks.12.attn.lora_B_q', 'vision_model.blocks.13.attn.lora_A_v', 'vision_model.blocks.13.attn.lora_B_v', 'vision_model.blocks.13.attn.lora_A_q', 'vision_model.blocks.13.attn.lora_B_q', 'vision_model.blocks.14.attn.lora_A_v', 'vision_model.blocks.14.attn.lora_B_v', 'vision_model.blocks.14.attn.lora_A_q', 'vision_model.blocks.14.attn.lora_B_q', 'vision_model.blocks.15.attn.lora_A_v', 'vision_model.blocks.15.attn.lora_B_v', 'vision_model.blocks.15.attn.lora_A_q', 'vision_model.blocks.15.attn.lora_B_q', 'vision_model.blocks.16.attn.lora_A_v', 'vision_model.blocks.16.attn.lora_B_v', 'vision_model.blocks.16.attn.lora_A_q', 'vision_model.blocks.16.attn.lora_B_q', 'vision_model.blocks.17.attn.lora_A_v', 'vision_model.blocks.17.attn.lora_B_v', 'vision_model.blocks.17.attn.lora_A_q', 'vision_model.blocks.17.attn.lora_B_q', 'vision_model.blocks.18.attn.lora_A_v', 'vision_model.blocks.18.attn.lora_B_v', 'vision_model.blocks.18.attn.lora_A_q', 'vision_model.blocks.18.attn.lora_B_q', 'vision_model.blocks.19.attn.lora_A_v', 'vision_model.blocks.19.attn.lora_B_v', 'vision_model.blocks.19.attn.lora_A_q', 'vision_model.blocks.19.attn.lora_B_q', 'vision_model.blocks.20.attn.lora_A_v', 'vision_model.blocks.20.attn.lora_B_v', 'vision_model.blocks.20.attn.lora_A_q', 'vision_model.blocks.20.attn.lora_B_q', 'vision_model.blocks.21.attn.lora_A_v', 'vision_model.blocks.21.attn.lora_B_v', 'vision_model.blocks.21.attn.lora_A_q', 'vision_model.blocks.21.attn.lora_B_q', 'vision_model.blocks.22.attn.lora_A_v', 'vision_model.blocks.22.attn.lora_B_v', 'vision_model.blocks.22.attn.lora_A_q', 'vision_model.blocks.22.attn.lora_B_q', 'vision_model.blocks.23.attn.lora_A_v', 'vision_model.blocks.23.attn.lora_B_v', 'vision_model.blocks.23.attn.lora_A_q', 'vision_model.blocks.23.attn.lora_B_q', 'mm_projector.weight', 'mm_projector.bias']
WARNING:root:The number of training samples is 149813
WARNING:root:Formatting inputs...Skip in lazy mode
Use Conv Format  keypoint
param_grad: ['model.layers.0.self_attn.q_proj.lora_A', 'model.layers.0.self_attn.q_proj.lora_B', 'model.layers.0.self_attn.v_proj.lora_A', 'model.layers.0.self_attn.v_proj.lora_B', 'model.layers.1.self_attn.q_proj.lora_A', 'model.layers.1.self_attn.q_proj.lora_B', 'model.layers.1.self_attn.v_proj.lora_A', 'model.layers.1.self_attn.v_proj.lora_B', 'model.layers.2.self_attn.q_proj.lora_A', 'model.layers.2.self_attn.q_proj.lora_B', 'model.layers.2.self_attn.v_proj.lora_A', 'model.layers.2.self_attn.v_proj.lora_B', 'model.layers.3.self_attn.q_proj.lora_A', 'model.layers.3.self_attn.q_proj.lora_B', 'model.layers.3.self_attn.v_proj.lora_A', 'model.layers.3.self_attn.v_proj.lora_B', 'model.layers.4.self_attn.q_proj.lora_A', 'model.layers.4.self_attn.q_proj.lora_B', 'model.layers.4.self_attn.v_proj.lora_A', 'model.layers.4.self_attn.v_proj.lora_B', 'model.layers.5.self_attn.q_proj.lora_A', 'model.layers.5.self_attn.q_proj.lora_B', 'model.layers.5.self_attn.v_proj.lora_A', 'model.layers.5.self_attn.v_proj.lora_B', 'model.layers.6.self_attn.q_proj.lora_A', 'model.layers.6.self_attn.q_proj.lora_B', 'model.layers.6.self_attn.v_proj.lora_A', 'model.layers.6.self_attn.v_proj.lora_B', 'model.layers.7.self_attn.q_proj.lora_A', 'model.layers.7.self_attn.q_proj.lora_B', 'model.layers.7.self_attn.v_proj.lora_A', 'model.layers.7.self_attn.v_proj.lora_B', 'model.layers.8.self_attn.q_proj.lora_A', 'model.layers.8.self_attn.q_proj.lora_B', 'model.layers.8.self_attn.v_proj.lora_A', 'model.layers.8.self_attn.v_proj.lora_B', 'model.layers.9.self_attn.q_proj.lora_A', 'model.layers.9.self_attn.q_proj.lora_B', 'model.layers.9.self_attn.v_proj.lora_A', 'model.layers.9.self_attn.v_proj.lora_B', 'model.layers.10.self_attn.q_proj.lora_A', 'model.layers.10.self_attn.q_proj.lora_B', 'model.layers.10.self_attn.v_proj.lora_A', 'model.layers.10.self_attn.v_proj.lora_B', 'model.layers.11.self_attn.q_proj.lora_A', 'model.layers.11.self_attn.q_proj.lora_B', 'model.layers.11.self_attn.v_proj.lora_A', 'model.layers.11.self_attn.v_proj.lora_B', 'model.layers.12.self_attn.q_proj.lora_A', 'model.layers.12.self_attn.q_proj.lora_B', 'model.layers.12.self_attn.v_proj.lora_A', 'model.layers.12.self_attn.v_proj.lora_B', 'model.layers.13.self_attn.q_proj.lora_A', 'model.layers.13.self_attn.q_proj.lora_B', 'model.layers.13.self_attn.v_proj.lora_A', 'model.layers.13.self_attn.v_proj.lora_B', 'model.layers.14.self_attn.q_proj.lora_A', 'model.layers.14.self_attn.q_proj.lora_B', 'model.layers.14.self_attn.v_proj.lora_A', 'model.layers.14.self_attn.v_proj.lora_B', 'model.layers.15.self_attn.q_proj.lora_A', 'model.layers.15.self_attn.q_proj.lora_B', 'model.layers.15.self_attn.v_proj.lora_A', 'model.layers.15.self_attn.v_proj.lora_B', 'model.layers.16.self_attn.q_proj.lora_A', 'model.layers.16.self_attn.q_proj.lora_B', 'model.layers.16.self_attn.v_proj.lora_A', 'model.layers.16.self_attn.v_proj.lora_B', 'model.layers.17.self_attn.q_proj.lora_A', 'model.layers.17.self_attn.q_proj.lora_B', 'model.layers.17.self_attn.v_proj.lora_A', 'model.layers.17.self_attn.v_proj.lora_B', 'model.layers.18.self_attn.q_proj.lora_A', 'model.layers.18.self_attn.q_proj.lora_B', 'model.layers.18.self_attn.v_proj.lora_A', 'model.layers.18.self_attn.v_proj.lora_B', 'model.layers.19.self_attn.q_proj.lora_A', 'model.layers.19.self_attn.q_proj.lora_B', 'model.layers.19.self_attn.v_proj.lora_A', 'model.layers.19.self_attn.v_proj.lora_B', 'model.layers.20.self_attn.q_proj.lora_A', 'model.layers.20.self_attn.q_proj.lora_B', 'model.layers.20.self_attn.v_proj.lora_A', 'model.layers.20.self_attn.v_proj.lora_B', 'model.layers.21.self_attn.q_proj.lora_A', 'model.layers.21.self_attn.q_proj.lora_B', 'model.layers.21.self_attn.v_proj.lora_A', 'model.layers.21.self_attn.v_proj.lora_B', 'model.layers.22.self_attn.q_proj.lora_A', 'model.layers.22.self_attn.q_proj.lora_B', 'model.layers.22.self_attn.v_proj.lora_A', 'model.layers.22.self_attn.v_proj.lora_B', 'model.layers.23.self_attn.q_proj.lora_A', 'model.layers.23.self_attn.q_proj.lora_B', 'model.layers.23.self_attn.v_proj.lora_A', 'model.layers.23.self_attn.v_proj.lora_B', 'model.layers.24.self_attn.q_proj.lora_A', 'model.layers.24.self_attn.q_proj.lora_B', 'model.layers.24.self_attn.v_proj.lora_A', 'model.layers.24.self_attn.v_proj.lora_B', 'model.layers.25.self_attn.q_proj.lora_A', 'model.layers.25.self_attn.q_proj.lora_B', 'model.layers.25.self_attn.v_proj.lora_A', 'model.layers.25.self_attn.v_proj.lora_B', 'model.layers.26.self_attn.q_proj.lora_A', 'model.layers.26.self_attn.q_proj.lora_B', 'model.layers.26.self_attn.v_proj.lora_A', 'model.layers.26.self_attn.v_proj.lora_B', 'model.layers.27.self_attn.q_proj.lora_A', 'model.layers.27.self_attn.q_proj.lora_B', 'model.layers.27.self_attn.v_proj.lora_A', 'model.layers.27.self_attn.v_proj.lora_B', 'model.layers.28.self_attn.q_proj.lora_A', 'model.layers.28.self_attn.q_proj.lora_B', 'model.layers.28.self_attn.v_proj.lora_A', 'model.layers.28.self_attn.v_proj.lora_B', 'model.layers.29.self_attn.q_proj.lora_A', 'model.layers.29.self_attn.q_proj.lora_B', 'model.layers.29.self_attn.v_proj.lora_A', 'model.layers.29.self_attn.v_proj.lora_B', 'model.layers.30.self_attn.q_proj.lora_A', 'model.layers.30.self_attn.q_proj.lora_B', 'model.layers.30.self_attn.v_proj.lora_A', 'model.layers.30.self_attn.v_proj.lora_B', 'model.layers.31.self_attn.q_proj.lora_A', 'model.layers.31.self_attn.q_proj.lora_B', 'model.layers.31.self_attn.v_proj.lora_A', 'model.layers.31.self_attn.v_proj.lora_B', 'vision_model.blocks.0.attn.lora_A_v', 'vision_model.blocks.0.attn.lora_B_v', 'vision_model.blocks.0.attn.lora_A_q', 'vision_model.blocks.0.attn.lora_B_q', 'vision_model.blocks.1.attn.lora_A_v', 'vision_model.blocks.1.attn.lora_B_v', 'vision_model.blocks.1.attn.lora_A_q', 'vision_model.blocks.1.attn.lora_B_q', 'vision_model.blocks.2.attn.lora_A_v', 'vision_model.blocks.2.attn.lora_B_v', 'vision_model.blocks.2.attn.lora_A_q', 'vision_model.blocks.2.attn.lora_B_q', 'vision_model.blocks.3.attn.lora_A_v', 'vision_model.blocks.3.attn.lora_B_v', 'vision_model.blocks.3.attn.lora_A_q', 'vision_model.blocks.3.attn.lora_B_q', 'vision_model.blocks.4.attn.lora_A_v', 'vision_model.blocks.4.attn.lora_B_v', 'vision_model.blocks.4.attn.lora_A_q', 'vision_model.blocks.4.attn.lora_B_q', 'vision_model.blocks.5.attn.lora_A_v', 'vision_model.blocks.5.attn.lora_B_v', 'vision_model.blocks.5.attn.lora_A_q', 'vision_model.blocks.5.attn.lora_B_q', 'vision_model.blocks.6.attn.lora_A_v', 'vision_model.blocks.6.attn.lora_B_v', 'vision_model.blocks.6.attn.lora_A_q', 'vision_model.blocks.6.attn.lora_B_q', 'vision_model.blocks.7.attn.lora_A_v', 'vision_model.blocks.7.attn.lora_B_v', 'vision_model.blocks.7.attn.lora_A_q', 'vision_model.blocks.7.attn.lora_B_q', 'vision_model.blocks.8.attn.lora_A_v', 'vision_model.blocks.8.attn.lora_B_v', 'vision_model.blocks.8.attn.lora_A_q', 'vision_model.blocks.8.attn.lora_B_q', 'vision_model.blocks.9.attn.lora_A_v', 'vision_model.blocks.9.attn.lora_B_v', 'vision_model.blocks.9.attn.lora_A_q', 'vision_model.blocks.9.attn.lora_B_q', 'vision_model.blocks.10.attn.lora_A_v', 'vision_model.blocks.10.attn.lora_B_v', 'vision_model.blocks.10.attn.lora_A_q', 'vision_model.blocks.10.attn.lora_B_q', 'vision_model.blocks.11.attn.lora_A_v', 'vision_model.blocks.11.attn.lora_B_v', 'vision_model.blocks.11.attn.lora_A_q', 'vision_model.blocks.11.attn.lora_B_q', 'vision_model.blocks.12.attn.lora_A_v', 'vision_model.blocks.12.attn.lora_B_v', 'vision_model.blocks.12.attn.lora_A_q', 'vision_model.blocks.12.attn.lora_B_q', 'vision_model.blocks.13.attn.lora_A_v', 'vision_model.blocks.13.attn.lora_B_v', 'vision_model.blocks.13.attn.lora_A_q', 'vision_model.blocks.13.attn.lora_B_q', 'vision_model.blocks.14.attn.lora_A_v', 'vision_model.blocks.14.attn.lora_B_v', 'vision_model.blocks.14.attn.lora_A_q', 'vision_model.blocks.14.attn.lora_B_q', 'vision_model.blocks.15.attn.lora_A_v', 'vision_model.blocks.15.attn.lora_B_v', 'vision_model.blocks.15.attn.lora_A_q', 'vision_model.blocks.15.attn.lora_B_q', 'vision_model.blocks.16.attn.lora_A_v', 'vision_model.blocks.16.attn.lora_B_v', 'vision_model.blocks.16.attn.lora_A_q', 'vision_model.blocks.16.attn.lora_B_q', 'vision_model.blocks.17.attn.lora_A_v', 'vision_model.blocks.17.attn.lora_B_v', 'vision_model.blocks.17.attn.lora_A_q', 'vision_model.blocks.17.attn.lora_B_q', 'vision_model.blocks.18.attn.lora_A_v', 'vision_model.blocks.18.attn.lora_B_v', 'vision_model.blocks.18.attn.lora_A_q', 'vision_model.blocks.18.attn.lora_B_q', 'vision_model.blocks.19.attn.lora_A_v', 'vision_model.blocks.19.attn.lora_B_v', 'vision_model.blocks.19.attn.lora_A_q', 'vision_model.blocks.19.attn.lora_B_q', 'vision_model.blocks.20.attn.lora_A_v', 'vision_model.blocks.20.attn.lora_B_v', 'vision_model.blocks.20.attn.lora_A_q', 'vision_model.blocks.20.attn.lora_B_q', 'vision_model.blocks.21.attn.lora_A_v', 'vision_model.blocks.21.attn.lora_B_v', 'vision_model.blocks.21.attn.lora_A_q', 'vision_model.blocks.21.attn.lora_B_q', 'vision_model.blocks.22.attn.lora_A_v', 'vision_model.blocks.22.attn.lora_B_v', 'vision_model.blocks.22.attn.lora_A_q', 'vision_model.blocks.22.attn.lora_B_q', 'vision_model.blocks.23.attn.lora_A_v', 'vision_model.blocks.23.attn.lora_B_v', 'vision_model.blocks.23.attn.lora_A_q', 'vision_model.blocks.23.attn.lora_B_q', 'mm_projector.weight', 'mm_projector.bias']
WARNING:root:The number of training samples is 149813
WARNING:root:Formatting inputs...Skip in lazy mode
Use Conv Format  keypoint
param_grad: ['model.layers.0.self_attn.q_proj.lora_A', 'model.layers.0.self_attn.q_proj.lora_B', 'model.layers.0.self_attn.v_proj.lora_A', 'model.layers.0.self_attn.v_proj.lora_B', 'model.layers.1.self_attn.q_proj.lora_A', 'model.layers.1.self_attn.q_proj.lora_B', 'model.layers.1.self_attn.v_proj.lora_A', 'model.layers.1.self_attn.v_proj.lora_B', 'model.layers.2.self_attn.q_proj.lora_A', 'model.layers.2.self_attn.q_proj.lora_B', 'model.layers.2.self_attn.v_proj.lora_A', 'model.layers.2.self_attn.v_proj.lora_B', 'model.layers.3.self_attn.q_proj.lora_A', 'model.layers.3.self_attn.q_proj.lora_B', 'model.layers.3.self_attn.v_proj.lora_A', 'model.layers.3.self_attn.v_proj.lora_B', 'model.layers.4.self_attn.q_proj.lora_A', 'model.layers.4.self_attn.q_proj.lora_B', 'model.layers.4.self_attn.v_proj.lora_A', 'model.layers.4.self_attn.v_proj.lora_B', 'model.layers.5.self_attn.q_proj.lora_A', 'model.layers.5.self_attn.q_proj.lora_B', 'model.layers.5.self_attn.v_proj.lora_A', 'model.layers.5.self_attn.v_proj.lora_B', 'model.layers.6.self_attn.q_proj.lora_A', 'model.layers.6.self_attn.q_proj.lora_B', 'model.layers.6.self_attn.v_proj.lora_A', 'model.layers.6.self_attn.v_proj.lora_B', 'model.layers.7.self_attn.q_proj.lora_A', 'model.layers.7.self_attn.q_proj.lora_B', 'model.layers.7.self_attn.v_proj.lora_A', 'model.layers.7.self_attn.v_proj.lora_B', 'model.layers.8.self_attn.q_proj.lora_A', 'model.layers.8.self_attn.q_proj.lora_B', 'model.layers.8.self_attn.v_proj.lora_A', 'model.layers.8.self_attn.v_proj.lora_B', 'model.layers.9.self_attn.q_proj.lora_A', 'model.layers.9.self_attn.q_proj.lora_B', 'model.layers.9.self_attn.v_proj.lora_A', 'model.layers.9.self_attn.v_proj.lora_B', 'model.layers.10.self_attn.q_proj.lora_A', 'model.layers.10.self_attn.q_proj.lora_B', 'model.layers.10.self_attn.v_proj.lora_A', 'model.layers.10.self_attn.v_proj.lora_B', 'model.layers.11.self_attn.q_proj.lora_A', 'model.layers.11.self_attn.q_proj.lora_B', 'model.layers.11.self_attn.v_proj.lora_A', 'model.layers.11.self_attn.v_proj.lora_B', 'model.layers.12.self_attn.q_proj.lora_A', 'model.layers.12.self_attn.q_proj.lora_B', 'model.layers.12.self_attn.v_proj.lora_A', 'model.layers.12.self_attn.v_proj.lora_B', 'model.layers.13.self_attn.q_proj.lora_A', 'model.layers.13.self_attn.q_proj.lora_B', 'model.layers.13.self_attn.v_proj.lora_A', 'model.layers.13.self_attn.v_proj.lora_B', 'model.layers.14.self_attn.q_proj.lora_A', 'model.layers.14.self_attn.q_proj.lora_B', 'model.layers.14.self_attn.v_proj.lora_A', 'model.layers.14.self_attn.v_proj.lora_B', 'model.layers.15.self_attn.q_proj.lora_A', 'model.layers.15.self_attn.q_proj.lora_B', 'model.layers.15.self_attn.v_proj.lora_A', 'model.layers.15.self_attn.v_proj.lora_B', 'model.layers.16.self_attn.q_proj.lora_A', 'model.layers.16.self_attn.q_proj.lora_B', 'model.layers.16.self_attn.v_proj.lora_A', 'model.layers.16.self_attn.v_proj.lora_B', 'model.layers.17.self_attn.q_proj.lora_A', 'model.layers.17.self_attn.q_proj.lora_B', 'model.layers.17.self_attn.v_proj.lora_A', 'model.layers.17.self_attn.v_proj.lora_B', 'model.layers.18.self_attn.q_proj.lora_A', 'model.layers.18.self_attn.q_proj.lora_B', 'model.layers.18.self_attn.v_proj.lora_A', 'model.layers.18.self_attn.v_proj.lora_B', 'model.layers.19.self_attn.q_proj.lora_A', 'model.layers.19.self_attn.q_proj.lora_B', 'model.layers.19.self_attn.v_proj.lora_A', 'model.layers.19.self_attn.v_proj.lora_B', 'model.layers.20.self_attn.q_proj.lora_A', 'model.layers.20.self_attn.q_proj.lora_B', 'model.layers.20.self_attn.v_proj.lora_A', 'model.layers.20.self_attn.v_proj.lora_B', 'model.layers.21.self_attn.q_proj.lora_A', 'model.layers.21.self_attn.q_proj.lora_B', 'model.layers.21.self_attn.v_proj.lora_A', 'model.layers.21.self_attn.v_proj.lora_B', 'model.layers.22.self_attn.q_proj.lora_A', 'model.layers.22.self_attn.q_proj.lora_B', 'model.layers.22.self_attn.v_proj.lora_A', 'model.layers.22.self_attn.v_proj.lora_B', 'model.layers.23.self_attn.q_proj.lora_A', 'model.layers.23.self_attn.q_proj.lora_B', 'model.layers.23.self_attn.v_proj.lora_A', 'model.layers.23.self_attn.v_proj.lora_B', 'model.layers.24.self_attn.q_proj.lora_A', 'model.layers.24.self_attn.q_proj.lora_B', 'model.layers.24.self_attn.v_proj.lora_A', 'model.layers.24.self_attn.v_proj.lora_B', 'model.layers.25.self_attn.q_proj.lora_A', 'model.layers.25.self_attn.q_proj.lora_B', 'model.layers.25.self_attn.v_proj.lora_A', 'model.layers.25.self_attn.v_proj.lora_B', 'model.layers.26.self_attn.q_proj.lora_A', 'model.layers.26.self_attn.q_proj.lora_B', 'model.layers.26.self_attn.v_proj.lora_A', 'model.layers.26.self_attn.v_proj.lora_B', 'model.layers.27.self_attn.q_proj.lora_A', 'model.layers.27.self_attn.q_proj.lora_B', 'model.layers.27.self_attn.v_proj.lora_A', 'model.layers.27.self_attn.v_proj.lora_B', 'model.layers.28.self_attn.q_proj.lora_A', 'model.layers.28.self_attn.q_proj.lora_B', 'model.layers.28.self_attn.v_proj.lora_A', 'model.layers.28.self_attn.v_proj.lora_B', 'model.layers.29.self_attn.q_proj.lora_A', 'model.layers.29.self_attn.q_proj.lora_B', 'model.layers.29.self_attn.v_proj.lora_A', 'model.layers.29.self_attn.v_proj.lora_B', 'model.layers.30.self_attn.q_proj.lora_A', 'model.layers.30.self_attn.q_proj.lora_B', 'model.layers.30.self_attn.v_proj.lora_A', 'model.layers.30.self_attn.v_proj.lora_B', 'model.layers.31.self_attn.q_proj.lora_A', 'model.layers.31.self_attn.q_proj.lora_B', 'model.layers.31.self_attn.v_proj.lora_A', 'model.layers.31.self_attn.v_proj.lora_B', 'vision_model.blocks.0.attn.lora_A_v', 'vision_model.blocks.0.attn.lora_B_v', 'vision_model.blocks.0.attn.lora_A_q', 'vision_model.blocks.0.attn.lora_B_q', 'vision_model.blocks.1.attn.lora_A_v', 'vision_model.blocks.1.attn.lora_B_v', 'vision_model.blocks.1.attn.lora_A_q', 'vision_model.blocks.1.attn.lora_B_q', 'vision_model.blocks.2.attn.lora_A_v', 'vision_model.blocks.2.attn.lora_B_v', 'vision_model.blocks.2.attn.lora_A_q', 'vision_model.blocks.2.attn.lora_B_q', 'vision_model.blocks.3.attn.lora_A_v', 'vision_model.blocks.3.attn.lora_B_v', 'vision_model.blocks.3.attn.lora_A_q', 'vision_model.blocks.3.attn.lora_B_q', 'vision_model.blocks.4.attn.lora_A_v', 'vision_model.blocks.4.attn.lora_B_v', 'vision_model.blocks.4.attn.lora_A_q', 'vision_model.blocks.4.attn.lora_B_q', 'vision_model.blocks.5.attn.lora_A_v', 'vision_model.blocks.5.attn.lora_B_v', 'vision_model.blocks.5.attn.lora_A_q', 'vision_model.blocks.5.attn.lora_B_q', 'vision_model.blocks.6.attn.lora_A_v', 'vision_model.blocks.6.attn.lora_B_v', 'vision_model.blocks.6.attn.lora_A_q', 'vision_model.blocks.6.attn.lora_B_q', 'vision_model.blocks.7.attn.lora_A_v', 'vision_model.blocks.7.attn.lora_B_v', 'vision_model.blocks.7.attn.lora_A_q', 'vision_model.blocks.7.attn.lora_B_q', 'vision_model.blocks.8.attn.lora_A_v', 'vision_model.blocks.8.attn.lora_B_v', 'vision_model.blocks.8.attn.lora_A_q', 'vision_model.blocks.8.attn.lora_B_q', 'vision_model.blocks.9.attn.lora_A_v', 'vision_model.blocks.9.attn.lora_B_v', 'vision_model.blocks.9.attn.lora_A_q', 'vision_model.blocks.9.attn.lora_B_q', 'vision_model.blocks.10.attn.lora_A_v', 'vision_model.blocks.10.attn.lora_B_v', 'vision_model.blocks.10.attn.lora_A_q', 'vision_model.blocks.10.attn.lora_B_q', 'vision_model.blocks.11.attn.lora_A_v', 'vision_model.blocks.11.attn.lora_B_v', 'vision_model.blocks.11.attn.lora_A_q', 'vision_model.blocks.11.attn.lora_B_q', 'vision_model.blocks.12.attn.lora_A_v', 'vision_model.blocks.12.attn.lora_B_v', 'vision_model.blocks.12.attn.lora_A_q', 'vision_model.blocks.12.attn.lora_B_q', 'vision_model.blocks.13.attn.lora_A_v', 'vision_model.blocks.13.attn.lora_B_v', 'vision_model.blocks.13.attn.lora_A_q', 'vision_model.blocks.13.attn.lora_B_q', 'vision_model.blocks.14.attn.lora_A_v', 'vision_model.blocks.14.attn.lora_B_v', 'vision_model.blocks.14.attn.lora_A_q', 'vision_model.blocks.14.attn.lora_B_q', 'vision_model.blocks.15.attn.lora_A_v', 'vision_model.blocks.15.attn.lora_B_v', 'vision_model.blocks.15.attn.lora_A_q', 'vision_model.blocks.15.attn.lora_B_q', 'vision_model.blocks.16.attn.lora_A_v', 'vision_model.blocks.16.attn.lora_B_v', 'vision_model.blocks.16.attn.lora_A_q', 'vision_model.blocks.16.attn.lora_B_q', 'vision_model.blocks.17.attn.lora_A_v', 'vision_model.blocks.17.attn.lora_B_v', 'vision_model.blocks.17.attn.lora_A_q', 'vision_model.blocks.17.attn.lora_B_q', 'vision_model.blocks.18.attn.lora_A_v', 'vision_model.blocks.18.attn.lora_B_v', 'vision_model.blocks.18.attn.lora_A_q', 'vision_model.blocks.18.attn.lora_B_q', 'vision_model.blocks.19.attn.lora_A_v', 'vision_model.blocks.19.attn.lora_B_v', 'vision_model.blocks.19.attn.lora_A_q', 'vision_model.blocks.19.attn.lora_B_q', 'vision_model.blocks.20.attn.lora_A_v', 'vision_model.blocks.20.attn.lora_B_v', 'vision_model.blocks.20.attn.lora_A_q', 'vision_model.blocks.20.attn.lora_B_q', 'vision_model.blocks.21.attn.lora_A_v', 'vision_model.blocks.21.attn.lora_B_v', 'vision_model.blocks.21.attn.lora_A_q', 'vision_model.blocks.21.attn.lora_B_q', 'vision_model.blocks.22.attn.lora_A_v', 'vision_model.blocks.22.attn.lora_B_v', 'vision_model.blocks.22.attn.lora_A_q', 'vision_model.blocks.22.attn.lora_B_q', 'vision_model.blocks.23.attn.lora_A_v', 'vision_model.blocks.23.attn.lora_B_v', 'vision_model.blocks.23.attn.lora_A_q', 'vision_model.blocks.23.attn.lora_B_q', 'mm_projector.weight', 'mm_projector.bias']
WARNING:root:The number of training samples is 149813
WARNING:root:Formatting inputs...Skip in lazy mode
Use Conv Format  keypoint
param_grad: ['model.layers.0.self_attn.q_proj.lora_A', 'model.layers.0.self_attn.q_proj.lora_B', 'model.layers.0.self_attn.v_proj.lora_A', 'model.layers.0.self_attn.v_proj.lora_B', 'model.layers.1.self_attn.q_proj.lora_A', 'model.layers.1.self_attn.q_proj.lora_B', 'model.layers.1.self_attn.v_proj.lora_A', 'model.layers.1.self_attn.v_proj.lora_B', 'model.layers.2.self_attn.q_proj.lora_A', 'model.layers.2.self_attn.q_proj.lora_B', 'model.layers.2.self_attn.v_proj.lora_A', 'model.layers.2.self_attn.v_proj.lora_B', 'model.layers.3.self_attn.q_proj.lora_A', 'model.layers.3.self_attn.q_proj.lora_B', 'model.layers.3.self_attn.v_proj.lora_A', 'model.layers.3.self_attn.v_proj.lora_B', 'model.layers.4.self_attn.q_proj.lora_A', 'model.layers.4.self_attn.q_proj.lora_B', 'model.layers.4.self_attn.v_proj.lora_A', 'model.layers.4.self_attn.v_proj.lora_B', 'model.layers.5.self_attn.q_proj.lora_A', 'model.layers.5.self_attn.q_proj.lora_B', 'model.layers.5.self_attn.v_proj.lora_A', 'model.layers.5.self_attn.v_proj.lora_B', 'model.layers.6.self_attn.q_proj.lora_A', 'model.layers.6.self_attn.q_proj.lora_B', 'model.layers.6.self_attn.v_proj.lora_A', 'model.layers.6.self_attn.v_proj.lora_B', 'model.layers.7.self_attn.q_proj.lora_A', 'model.layers.7.self_attn.q_proj.lora_B', 'model.layers.7.self_attn.v_proj.lora_A', 'model.layers.7.self_attn.v_proj.lora_B', 'model.layers.8.self_attn.q_proj.lora_A', 'model.layers.8.self_attn.q_proj.lora_B', 'model.layers.8.self_attn.v_proj.lora_A', 'model.layers.8.self_attn.v_proj.lora_B', 'model.layers.9.self_attn.q_proj.lora_A', 'model.layers.9.self_attn.q_proj.lora_B', 'model.layers.9.self_attn.v_proj.lora_A', 'model.layers.9.self_attn.v_proj.lora_B', 'model.layers.10.self_attn.q_proj.lora_A', 'model.layers.10.self_attn.q_proj.lora_B', 'model.layers.10.self_attn.v_proj.lora_A', 'model.layers.10.self_attn.v_proj.lora_B', 'model.layers.11.self_attn.q_proj.lora_A', 'model.layers.11.self_attn.q_proj.lora_B', 'model.layers.11.self_attn.v_proj.lora_A', 'model.layers.11.self_attn.v_proj.lora_B', 'model.layers.12.self_attn.q_proj.lora_A', 'model.layers.12.self_attn.q_proj.lora_B', 'model.layers.12.self_attn.v_proj.lora_A', 'model.layers.12.self_attn.v_proj.lora_B', 'model.layers.13.self_attn.q_proj.lora_A', 'model.layers.13.self_attn.q_proj.lora_B', 'model.layers.13.self_attn.v_proj.lora_A', 'model.layers.13.self_attn.v_proj.lora_B', 'model.layers.14.self_attn.q_proj.lora_A', 'model.layers.14.self_attn.q_proj.lora_B', 'model.layers.14.self_attn.v_proj.lora_A', 'model.layers.14.self_attn.v_proj.lora_B', 'model.layers.15.self_attn.q_proj.lora_A', 'model.layers.15.self_attn.q_proj.lora_B', 'model.layers.15.self_attn.v_proj.lora_A', 'model.layers.15.self_attn.v_proj.lora_B', 'model.layers.16.self_attn.q_proj.lora_A', 'model.layers.16.self_attn.q_proj.lora_B', 'model.layers.16.self_attn.v_proj.lora_A', 'model.layers.16.self_attn.v_proj.lora_B', 'model.layers.17.self_attn.q_proj.lora_A', 'model.layers.17.self_attn.q_proj.lora_B', 'model.layers.17.self_attn.v_proj.lora_A', 'model.layers.17.self_attn.v_proj.lora_B', 'model.layers.18.self_attn.q_proj.lora_A', 'model.layers.18.self_attn.q_proj.lora_B', 'model.layers.18.self_attn.v_proj.lora_A', 'model.layers.18.self_attn.v_proj.lora_B', 'model.layers.19.self_attn.q_proj.lora_A', 'model.layers.19.self_attn.q_proj.lora_B', 'model.layers.19.self_attn.v_proj.lora_A', 'model.layers.19.self_attn.v_proj.lora_B', 'model.layers.20.self_attn.q_proj.lora_A', 'model.layers.20.self_attn.q_proj.lora_B', 'model.layers.20.self_attn.v_proj.lora_A', 'model.layers.20.self_attn.v_proj.lora_B', 'model.layers.21.self_attn.q_proj.lora_A', 'model.layers.21.self_attn.q_proj.lora_B', 'model.layers.21.self_attn.v_proj.lora_A', 'model.layers.21.self_attn.v_proj.lora_B', 'model.layers.22.self_attn.q_proj.lora_A', 'model.layers.22.self_attn.q_proj.lora_B', 'model.layers.22.self_attn.v_proj.lora_A', 'model.layers.22.self_attn.v_proj.lora_B', 'model.layers.23.self_attn.q_proj.lora_A', 'model.layers.23.self_attn.q_proj.lora_B', 'model.layers.23.self_attn.v_proj.lora_A', 'model.layers.23.self_attn.v_proj.lora_B', 'model.layers.24.self_attn.q_proj.lora_A', 'model.layers.24.self_attn.q_proj.lora_B', 'model.layers.24.self_attn.v_proj.lora_A', 'model.layers.24.self_attn.v_proj.lora_B', 'model.layers.25.self_attn.q_proj.lora_A', 'model.layers.25.self_attn.q_proj.lora_B', 'model.layers.25.self_attn.v_proj.lora_A', 'model.layers.25.self_attn.v_proj.lora_B', 'model.layers.26.self_attn.q_proj.lora_A', 'model.layers.26.self_attn.q_proj.lora_B', 'model.layers.26.self_attn.v_proj.lora_A', 'model.layers.26.self_attn.v_proj.lora_B', 'model.layers.27.self_attn.q_proj.lora_A', 'model.layers.27.self_attn.q_proj.lora_B', 'model.layers.27.self_attn.v_proj.lora_A', 'model.layers.27.self_attn.v_proj.lora_B', 'model.layers.28.self_attn.q_proj.lora_A', 'model.layers.28.self_attn.q_proj.lora_B', 'model.layers.28.self_attn.v_proj.lora_A', 'model.layers.28.self_attn.v_proj.lora_B', 'model.layers.29.self_attn.q_proj.lora_A', 'model.layers.29.self_attn.q_proj.lora_B', 'model.layers.29.self_attn.v_proj.lora_A', 'model.layers.29.self_attn.v_proj.lora_B', 'model.layers.30.self_attn.q_proj.lora_A', 'model.layers.30.self_attn.q_proj.lora_B', 'model.layers.30.self_attn.v_proj.lora_A', 'model.layers.30.self_attn.v_proj.lora_B', 'model.layers.31.self_attn.q_proj.lora_A', 'model.layers.31.self_attn.q_proj.lora_B', 'model.layers.31.self_attn.v_proj.lora_A', 'model.layers.31.self_attn.v_proj.lora_B', 'vision_model.blocks.0.attn.lora_A_v', 'vision_model.blocks.0.attn.lora_B_v', 'vision_model.blocks.0.attn.lora_A_q', 'vision_model.blocks.0.attn.lora_B_q', 'vision_model.blocks.1.attn.lora_A_v', 'vision_model.blocks.1.attn.lora_B_v', 'vision_model.blocks.1.attn.lora_A_q', 'vision_model.blocks.1.attn.lora_B_q', 'vision_model.blocks.2.attn.lora_A_v', 'vision_model.blocks.2.attn.lora_B_v', 'vision_model.blocks.2.attn.lora_A_q', 'vision_model.blocks.2.attn.lora_B_q', 'vision_model.blocks.3.attn.lora_A_v', 'vision_model.blocks.3.attn.lora_B_v', 'vision_model.blocks.3.attn.lora_A_q', 'vision_model.blocks.3.attn.lora_B_q', 'vision_model.blocks.4.attn.lora_A_v', 'vision_model.blocks.4.attn.lora_B_v', 'vision_model.blocks.4.attn.lora_A_q', 'vision_model.blocks.4.attn.lora_B_q', 'vision_model.blocks.5.attn.lora_A_v', 'vision_model.blocks.5.attn.lora_B_v', 'vision_model.blocks.5.attn.lora_A_q', 'vision_model.blocks.5.attn.lora_B_q', 'vision_model.blocks.6.attn.lora_A_v', 'vision_model.blocks.6.attn.lora_B_v', 'vision_model.blocks.6.attn.lora_A_q', 'vision_model.blocks.6.attn.lora_B_q', 'vision_model.blocks.7.attn.lora_A_v', 'vision_model.blocks.7.attn.lora_B_v', 'vision_model.blocks.7.attn.lora_A_q', 'vision_model.blocks.7.attn.lora_B_q', 'vision_model.blocks.8.attn.lora_A_v', 'vision_model.blocks.8.attn.lora_B_v', 'vision_model.blocks.8.attn.lora_A_q', 'vision_model.blocks.8.attn.lora_B_q', 'vision_model.blocks.9.attn.lora_A_v', 'vision_model.blocks.9.attn.lora_B_v', 'vision_model.blocks.9.attn.lora_A_q', 'vision_model.blocks.9.attn.lora_B_q', 'vision_model.blocks.10.attn.lora_A_v', 'vision_model.blocks.10.attn.lora_B_v', 'vision_model.blocks.10.attn.lora_A_q', 'vision_model.blocks.10.attn.lora_B_q', 'vision_model.blocks.11.attn.lora_A_v', 'vision_model.blocks.11.attn.lora_B_v', 'vision_model.blocks.11.attn.lora_A_q', 'vision_model.blocks.11.attn.lora_B_q', 'vision_model.blocks.12.attn.lora_A_v', 'vision_model.blocks.12.attn.lora_B_v', 'vision_model.blocks.12.attn.lora_A_q', 'vision_model.blocks.12.attn.lora_B_q', 'vision_model.blocks.13.attn.lora_A_v', 'vision_model.blocks.13.attn.lora_B_v', 'vision_model.blocks.13.attn.lora_A_q', 'vision_model.blocks.13.attn.lora_B_q', 'vision_model.blocks.14.attn.lora_A_v', 'vision_model.blocks.14.attn.lora_B_v', 'vision_model.blocks.14.attn.lora_A_q', 'vision_model.blocks.14.attn.lora_B_q', 'vision_model.blocks.15.attn.lora_A_v', 'vision_model.blocks.15.attn.lora_B_v', 'vision_model.blocks.15.attn.lora_A_q', 'vision_model.blocks.15.attn.lora_B_q', 'vision_model.blocks.16.attn.lora_A_v', 'vision_model.blocks.16.attn.lora_B_v', 'vision_model.blocks.16.attn.lora_A_q', 'vision_model.blocks.16.attn.lora_B_q', 'vision_model.blocks.17.attn.lora_A_v', 'vision_model.blocks.17.attn.lora_B_v', 'vision_model.blocks.17.attn.lora_A_q', 'vision_model.blocks.17.attn.lora_B_q', 'vision_model.blocks.18.attn.lora_A_v', 'vision_model.blocks.18.attn.lora_B_v', 'vision_model.blocks.18.attn.lora_A_q', 'vision_model.blocks.18.attn.lora_B_q', 'vision_model.blocks.19.attn.lora_A_v', 'vision_model.blocks.19.attn.lora_B_v', 'vision_model.blocks.19.attn.lora_A_q', 'vision_model.blocks.19.attn.lora_B_q', 'vision_model.blocks.20.attn.lora_A_v', 'vision_model.blocks.20.attn.lora_B_v', 'vision_model.blocks.20.attn.lora_A_q', 'vision_model.blocks.20.attn.lora_B_q', 'vision_model.blocks.21.attn.lora_A_v', 'vision_model.blocks.21.attn.lora_B_v', 'vision_model.blocks.21.attn.lora_A_q', 'vision_model.blocks.21.attn.lora_B_q', 'vision_model.blocks.22.attn.lora_A_v', 'vision_model.blocks.22.attn.lora_B_v', 'vision_model.blocks.22.attn.lora_A_q', 'vision_model.blocks.22.attn.lora_B_q', 'vision_model.blocks.23.attn.lora_A_v', 'vision_model.blocks.23.attn.lora_B_v', 'vision_model.blocks.23.attn.lora_A_q', 'vision_model.blocks.23.attn.lora_B_q', 'mm_projector.weight', 'mm_projector.bias']

  0%|          | 0/28080 [00:00<?, ?it/s][W reducer.cpp:1300] Warning: find_unused_parameters=True was specified in DDP constructor, but did not find any unused parameters in the forward pass. This flag results in an extra traversal of the autograd graph every iteration,  which can adversely affect performance. If your model indeed never has any unused parameters in the forward pass, consider turning this flag off. Note that this warning may be a false positive if your model has flow control causing later iterations to have unused parameters. (function operator())
[W reducer.cpp:1300] Warning: find_unused_parameters=True was specified in DDP constructor, but did not find any unused parameters in the forward pass. This flag results in an extra traversal of the autograd graph every iteration,  which can adversely affect performance. If your model indeed never has any unused parameters in the forward pass, consider turning this flag off. Note that this warning may be a false positive if your model has flow control causing later iterations to have unused parameters. (function operator())
[W reducer.cpp:1300] Warning: find_unused_parameters=True was specified in DDP constructor, but did not find any unused parameters in the forward pass. This flag results in an extra traversal of the autograd graph every iteration,  which can adversely affect performance. If your model indeed never has any unused parameters in the forward pass, consider turning this flag off. Note that this warning may be a false positive if your model has flow control causing later iterations to have unused parameters. (function operator())
[W reducer.cpp:1300] Warning: find_unused_parameters=True was specified in DDP constructor, but did not find any unused parameters in the forward pass. This flag results in an extra traversal of the autograd graph every iteration,  which can adversely affect performance. If your model indeed never has any unused parameters in the forward pass, consider turning this flag off. Note that this warning may be a false positive if your model has flow control causing later iterations to have unused parameters. (function operator())

  0%|          | 1/28080 [00:09<74:23:33,  9.54s/it]
                                                    
{'loss': 3.9387, 'learning_rate': 5.931198102016608e-07, 'epoch': 0.0}

  0%|          | 1/28080 [00:09<74:23:33,  9.54s/it]
  0%|          | 2/28080 [00:16<62:42:23,  8.04s/it]
                                                    
{'loss': 4.0974, 'learning_rate': 1.1862396204033216e-06, 'epoch': 0.0}

  0%|          | 2/28080 [00:16<62:42:23,  8.04s/it]
  0%|          | 3/28080 [00:23<58:35:18,  7.51s/it]
                                                    
{'loss': 4.0712, 'learning_rate': 1.7793594306049821e-06, 'epoch': 0.0}

  0%|          | 3/28080 [00:23<58:35:18,  7.51s/it]
  0%|          | 4/28080 [00:30<56:53:57,  7.30s/it]
                                                    
{'loss': 4.006, 'learning_rate': 2.3724792408066433e-06, 'epoch': 0.0}

  0%|          | 4/28080 [00:30<56:53:57,  7.30s/it]
  0%|          | 5/28080 [00:37<56:06:56,  7.20s/it]
                                                    
{'loss': 3.99, 'learning_rate': 2.9655990510083035e-06, 'epoch': 0.0}

  0%|          | 5/28080 [00:37<56:06:56,  7.20s/it]
  0%|          | 6/28080 [00:44<55:35:51,  7.13s/it]
                                                    
{'loss': 4.0626, 'learning_rate': 3.5587188612099643e-06, 'epoch': 0.0}

  0%|          | 6/28080 [00:44<55:35:51,  7.13s/it]
  0%|          | 7/28080 [00:51<55:09:53,  7.07s/it]
                                                    
{'loss': 3.9735, 'learning_rate': 4.151838671411625e-06, 'epoch': 0.0}

  0%|          | 7/28080 [00:51<55:09:53,  7.07s/it]
  0%|          | 8/28080 [00:58<55:02:02,  7.06s/it]
                                                    
{'loss': 3.9009, 'learning_rate': 4.7449584816132865e-06, 'epoch': 0.0}

  0%|          | 8/28080 [00:58<55:02:02,  7.06s/it]
  0%|          | 9/28080 [01:05<54:56:49,  7.05s/it]
                                                    
{'loss': 3.8553, 'learning_rate': 5.338078291814947e-06, 'epoch': 0.0}

  0%|          | 9/28080 [01:05<54:56:49,  7.05s/it]
  0%|          | 10/28080 [01:12<54:47:59,  7.03s/it]
                                                     
{'loss': 3.8014, 'learning_rate': 5.931198102016607e-06, 'epoch': 0.0}

  0%|          | 10/28080 [01:12<54:47:59,  7.03s/it]
  0%|          | 11/28080 [01:19<54:56:25,  7.05s/it]
                                                     
{'loss': 3.8908, 'learning_rate': 6.524317912218268e-06, 'epoch': 0.0}

  0%|          | 11/28080 [01:19<54:56:25,  7.05s/it]
  0%|          | 12/28080 [01:26<55:07:45,  7.07s/it]
                                                     
{'loss': 3.6461, 'learning_rate': 7.1174377224199285e-06, 'epoch': 0.01}

  0%|          | 12/28080 [01:26<55:07:45,  7.07s/it]
  0%|          | 13/28080 [01:33<55:11:26,  7.08s/it]
                                                     
{'loss': 3.7034, 'learning_rate': 7.71055753262159e-06, 'epoch': 0.01}

  0%|          | 13/28080 [01:33<55:11:26,  7.08s/it]
  0%|          | 14/28080 [01:40<55:19:25,  7.10s/it]
                                                     
{'loss': 3.6551, 'learning_rate': 8.30367734282325e-06, 'epoch': 0.01}

  0%|          | 14/28080 [01:40<55:19:25,  7.10s/it]
  0%|          | 15/28080 [01:47<55:14:09,  7.09s/it]
                                                     
{'loss': 3.5677, 'learning_rate': 8.896797153024912e-06, 'epoch': 0.01}

  0%|          | 15/28080 [01:47<55:14:09,  7.09s/it]
  0%|          | 16/28080 [01:55<55:24:57,  7.11s/it]
                                                     
{'loss': 3.3956, 'learning_rate': 9.489916963226573e-06, 'epoch': 0.01}

  0%|          | 16/28080 [01:55<55:24:57,  7.11s/it]
  0%|          | 17/28080 [02:02<55:11:06,  7.08s/it]
                                                     
{'loss': 3.3778, 'learning_rate': 1.0083036773428234e-05, 'epoch': 0.01}

  0%|          | 17/28080 [02:02<55:11:06,  7.08s/it]
  0%|          | 18/28080 [02:09<55:19:28,  7.10s/it]
                                                     
{'loss': 3.3387, 'learning_rate': 1.0676156583629894e-05, 'epoch': 0.01}

  0%|          | 18/28080 [02:09<55:19:28,  7.10s/it]
  0%|          | 19/28080 [02:16<55:09:57,  7.08s/it]
                                                     
{'loss': 3.3706, 'learning_rate': 1.1269276393831555e-05, 'epoch': 0.01}

  0%|          | 19/28080 [02:16<55:09:57,  7.08s/it]
  0%|          | 20/28080 [02:23<55:23:26,  7.11s/it]
                                                     
{'loss': 3.1322, 'learning_rate': 1.1862396204033214e-05, 'epoch': 0.01}

  0%|          | 20/28080 [02:23<55:23:26,  7.11s/it]
  0%|          | 21/28080 [02:30<55:14:46,  7.09s/it]
                                                     
{'loss': 3.1163, 'learning_rate': 1.2455516014234875e-05, 'epoch': 0.01}

  0%|          | 21/28080 [02:30<55:14:46,  7.09s/it]
  0%|          | 22/28080 [02:37<55:13:32,  7.09s/it]
                                                     
{'loss': 3.0287, 'learning_rate': 1.3048635824436536e-05, 'epoch': 0.01}

  0%|          | 22/28080 [02:37<55:13:32,  7.09s/it]
  0%|          | 23/28080 [02:44<55:20:03,  7.10s/it]
                                                     
{'loss': 2.9513, 'learning_rate': 1.3641755634638196e-05, 'epoch': 0.01}

  0%|          | 23/28080 [02:44<55:20:03,  7.10s/it]
  0%|          | 24/28080 [02:51<55:17:36,  7.09s/it]
                                                     
{'loss': 2.9507, 'learning_rate': 1.4234875444839857e-05, 'epoch': 0.01}

  0%|          | 24/28080 [02:51<55:17:36,  7.09s/it]
  0%|          | 25/28080 [02:58<55:21:14,  7.10s/it]
                                                     
{'loss': 2.8617, 'learning_rate': 1.482799525504152e-05, 'epoch': 0.01}

  0%|          | 25/28080 [02:58<55:21:14,  7.10s/it]
  0%|          | 26/28080 [03:06<55:31:17,  7.12s/it]
                                                     
{'loss': 2.7941, 'learning_rate': 1.542111506524318e-05, 'epoch': 0.01}

  0%|          | 26/28080 [03:06<55:31:17,  7.12s/it]
  0%|          | 27/28080 [03:13<55:08:59,  7.08s/it]
                                                     
{'loss': 2.6679, 'learning_rate': 1.601423487544484e-05, 'epoch': 0.01}

  0%|          | 27/28080 [03:13<55:08:59,  7.08s/it]
  0%|          | 28/28080 [03:20<55:07:42,  7.07s/it]
                                                     
{'loss': 2.5834, 'learning_rate': 1.66073546856465e-05, 'epoch': 0.01}

  0%|          | 28/28080 [03:20<55:07:42,  7.07s/it]
  0%|          | 29/28080 [03:27<54:50:00,  7.04s/it]
                                                     
{'loss': 2.5815, 'learning_rate': 1.7200474495848162e-05, 'epoch': 0.01}

  0%|          | 29/28080 [03:27<54:50:00,  7.04s/it]
  0%|          | 30/28080 [03:34<55:03:32,  7.07s/it]
                                                     
{'loss': 2.4122, 'learning_rate': 1.7793594306049825e-05, 'epoch': 0.01}

  0%|          | 30/28080 [03:34<55:03:32,  7.07s/it]
  0%|          | 31/28080 [03:41<54:59:53,  7.06s/it]
                                                     
{'loss': 2.411, 'learning_rate': 1.8386714116251484e-05, 'epoch': 0.01}

  0%|          | 31/28080 [03:41<54:59:53,  7.06s/it]
  0%|          | 32/28080 [03:48<55:10:37,  7.08s/it]
                                                     
{'loss': 2.31, 'learning_rate': 1.8979833926453146e-05, 'epoch': 0.01}

  0%|          | 32/28080 [03:48<55:10:37,  7.08s/it]
  0%|          | 33/28080 [03:55<55:14:01,  7.09s/it]
                                                     
{'loss': 2.1883, 'learning_rate': 1.9572953736654805e-05, 'epoch': 0.01}

  0%|          | 33/28080 [03:55<55:14:01,  7.09s/it]
  0%|          | 34/28080 [04:02<55:20:40,  7.10s/it]
                                                     
{'loss': 2.1004, 'learning_rate': 2.0166073546856468e-05, 'epoch': 0.01}

  0%|          | 34/28080 [04:02<55:20:40,  7.10s/it]
  0%|          | 35/28080 [04:09<55:36:39,  7.14s/it]
                                                     
{'loss': 2.0833, 'learning_rate': 2.0759193357058127e-05, 'epoch': 0.01}

  0%|          | 35/28080 [04:09<55:36:39,  7.14s/it]
  0%|          | 36/28080 [04:16<55:31:20,  7.13s/it]
                                                     
{'loss': 2.0655, 'learning_rate': 2.135231316725979e-05, 'epoch': 0.02}

  0%|          | 36/28080 [04:16<55:31:20,  7.13s/it]
  0%|          | 37/28080 [04:24<55:42:10,  7.15s/it]
                                                     
{'loss': 1.9571, 'learning_rate': 2.1945432977461448e-05, 'epoch': 0.02}

  0%|          | 37/28080 [04:24<55:42:10,  7.15s/it]
  0%|          | 38/28080 [04:31<55:36:07,  7.14s/it]
                                                     
{'loss': 1.9363, 'learning_rate': 2.253855278766311e-05, 'epoch': 0.02}

  0%|          | 38/28080 [04:31<55:36:07,  7.14s/it]
  0%|          | 39/28080 [04:38<55:37:43,  7.14s/it]
                                                     
{'loss': 1.8875, 'learning_rate': 2.3131672597864766e-05, 'epoch': 0.02}

  0%|          | 39/28080 [04:38<55:37:43,  7.14s/it]
  0%|          | 40/28080 [04:45<55:31:51,  7.13s/it]
                                                     
{'loss': 1.8512, 'learning_rate': 2.372479240806643e-05, 'epoch': 0.02}

  0%|          | 40/28080 [04:45<55:31:51,  7.13s/it]
  0%|          | 41/28080 [04:52<55:19:53,  7.10s/it]
                                                     
{'loss': 1.8294, 'learning_rate': 2.431791221826809e-05, 'epoch': 0.02}

  0%|          | 41/28080 [04:52<55:19:53,  7.10s/it]
  0%|          | 42/28080 [04:59<55:23:35,  7.11s/it]
                                                     
{'loss': 1.7293, 'learning_rate': 2.491103202846975e-05, 'epoch': 0.02}

  0%|          | 42/28080 [04:59<55:23:35,  7.11s/it]
  0%|          | 43/28080 [05:06<55:11:37,  7.09s/it]
                                                     
{'loss': 1.7712, 'learning_rate': 2.5504151838671412e-05, 'epoch': 0.02}

  0%|          | 43/28080 [05:06<55:11:37,  7.09s/it]
  0%|          | 44/28080 [05:13<55:18:51,  7.10s/it]
                                                     
{'loss': 1.6615, 'learning_rate': 2.609727164887307e-05, 'epoch': 0.02}

  0%|          | 44/28080 [05:13<55:18:51,  7.10s/it]
  0%|          | 45/28080 [05:20<55:15:00,  7.09s/it]
                                                     
{'loss': 1.6371, 'learning_rate': 2.6690391459074734e-05, 'epoch': 0.02}

  0%|          | 45/28080 [05:20<55:15:00,  7.09s/it]
  0%|          | 46/28080 [05:27<55:15:06,  7.10s/it]
                                                     
{'loss': 1.5677, 'learning_rate': 2.7283511269276393e-05, 'epoch': 0.02}

  0%|          | 46/28080 [05:28<55:15:06,  7.10s/it]
  0%|          | 47/28080 [05:35<55:19:50,  7.11s/it]
                                                     
{'loss': 1.5461, 'learning_rate': 2.7876631079478055e-05, 'epoch': 0.02}

  0%|          | 47/28080 [05:35<55:19:50,  7.11s/it]
  0%|          | 48/28080 [05:42<55:20:35,  7.11s/it]
                                                     
{'loss': 1.4821, 'learning_rate': 2.8469750889679714e-05, 'epoch': 0.02}

  0%|          | 48/28080 [05:42<55:20:35,  7.11s/it]
  0%|          | 49/28080 [05:49<55:32:17,  7.13s/it]
                                                     
{'loss': 1.4262, 'learning_rate': 2.9062870699881376e-05, 'epoch': 0.02}

  0%|          | 49/28080 [05:49<55:32:17,  7.13s/it]
  0%|          | 50/28080 [05:56<55:46:14,  7.16s/it]
                                                     
{'loss': 1.4101, 'learning_rate': 2.965599051008304e-05, 'epoch': 0.02}

  0%|          | 50/28080 [05:56<55:46:14,  7.16s/it]
  0%|          | 51/28080 [06:03<55:36:42,  7.14s/it]
                                                     
{'loss': 1.3515, 'learning_rate': 3.0249110320284698e-05, 'epoch': 0.02}

  0%|          | 51/28080 [06:03<55:36:42,  7.14s/it]
  0%|          | 52/28080 [06:10<55:37:29,  7.14s/it]
                                                     
{'loss': 1.3379, 'learning_rate': 3.084223013048636e-05, 'epoch': 0.02}

  0%|          | 52/28080 [06:10<55:37:29,  7.14s/it]
  0%|          | 53/28080 [06:18<55:41:58,  7.15s/it]
                                                     
{'loss': 1.2768, 'learning_rate': 3.143534994068802e-05, 'epoch': 0.02}

  0%|          | 53/28080 [06:18<55:41:58,  7.15s/it]
  0%|          | 54/28080 [06:25<55:47:32,  7.17s/it]
                                                     
{'loss': 1.2395, 'learning_rate': 3.202846975088968e-05, 'epoch': 0.02}

  0%|          | 54/28080 [06:25<55:47:32,  7.17s/it]
  0%|          | 55/28080 [06:32<55:51:01,  7.17s/it]
                                                     
{'loss': 1.2164, 'learning_rate': 3.262158956109134e-05, 'epoch': 0.02}

  0%|          | 55/28080 [06:32<55:51:01,  7.17s/it]
  0%|          | 56/28080 [06:39<55:20:57,  7.11s/it]
                                                     
{'loss': 1.2007, 'learning_rate': 3.3214709371293e-05, 'epoch': 0.02}

  0%|          | 56/28080 [06:39<55:20:57,  7.11s/it]
  0%|          | 57/28080 [06:46<55:21:57,  7.11s/it]
                                                     
{'loss': 1.1637, 'learning_rate': 3.380782918149466e-05, 'epoch': 0.02}

  0%|          | 57/28080 [06:46<55:21:57,  7.11s/it]
  0%|          | 58/28080 [06:53<55:19:23,  7.11s/it]
                                                     
{'loss': 1.1375, 'learning_rate': 3.4400948991696325e-05, 'epoch': 0.02}

  0%|          | 58/28080 [06:53<55:19:23,  7.11s/it]
  0%|          | 59/28080 [07:00<55:07:38,  7.08s/it]
                                                     
{'loss': 1.1052, 'learning_rate': 3.499406880189798e-05, 'epoch': 0.03}

  0%|          | 59/28080 [07:00<55:07:38,  7.08s/it]
  0%|          | 60/28080 [07:07<55:07:37,  7.08s/it]
                                                     
{'loss': 1.0859, 'learning_rate': 3.558718861209965e-05, 'epoch': 0.03}

  0%|          | 60/28080 [07:07<55:07:37,  7.08s/it]
  0%|          | 61/28080 [07:14<55:17:53,  7.10s/it]
                                                     
{'loss': 1.0782, 'learning_rate': 3.6180308422301305e-05, 'epoch': 0.03}

  0%|          | 61/28080 [07:14<55:17:53,  7.10s/it]
  0%|          | 62/28080 [07:22<55:21:00,  7.11s/it]
                                                     
{'loss': 1.0808, 'learning_rate': 3.677342823250297e-05, 'epoch': 0.03}

  0%|          | 62/28080 [07:22<55:21:00,  7.11s/it]
  0%|          | 63/28080 [07:28<54:57:04,  7.06s/it]
                                                     
{'loss': 1.0655, 'learning_rate': 3.736654804270462e-05, 'epoch': 0.03}

  0%|          | 63/28080 [07:28<54:57:04,  7.06s/it]
  0%|          | 64/28080 [07:36<55:03:38,  7.08s/it]
                                                     
{'loss': 1.0325, 'learning_rate': 3.795966785290629e-05, 'epoch': 0.03}

  0%|          | 64/28080 [07:36<55:03:38,  7.08s/it]
  0%|          | 65/28080 [07:43<54:59:34,  7.07s/it]
                                                     
{'loss': 1.0159, 'learning_rate': 3.855278766310795e-05, 'epoch': 0.03}

  0%|          | 65/28080 [07:43<54:59:34,  7.07s/it]
  0%|          | 66/28080 [07:50<54:45:22,  7.04s/it]
                                                     
{'loss': 1.0335, 'learning_rate': 3.914590747330961e-05, 'epoch': 0.03}

  0%|          | 66/28080 [07:50<54:45:22,  7.04s/it]
  0%|          | 67/28080 [07:57<54:47:57,  7.04s/it]
                                                     
{'loss': 1.0058, 'learning_rate': 3.9739027283511266e-05, 'epoch': 0.03}

  0%|          | 67/28080 [07:57<54:47:57,  7.04s/it]
  0%|          | 68/28080 [08:04<54:45:40,  7.04s/it]
                                                     
{'loss': 1.0019, 'learning_rate': 4.0332147093712935e-05, 'epoch': 0.03}

  0%|          | 68/28080 [08:04<54:45:40,  7.04s/it]
  0%|          | 69/28080 [08:11<54:56:59,  7.06s/it]
                                                     
{'loss': 0.9947, 'learning_rate': 4.092526690391459e-05, 'epoch': 0.03}

  0%|          | 69/28080 [08:11<54:56:59,  7.06s/it]
  0%|          | 70/28080 [08:18<55:03:04,  7.08s/it]
                                                     
{'loss': 0.9853, 'learning_rate': 4.151838671411625e-05, 'epoch': 0.03}

  0%|          | 70/28080 [08:18<55:03:04,  7.08s/it]
  0%|          | 71/28080 [08:25<55:01:30,  7.07s/it]
                                                     
{'loss': 0.9826, 'learning_rate': 4.2111506524317915e-05, 'epoch': 0.03}

  0%|          | 71/28080 [08:25<55:01:30,  7.07s/it]
  0%|          | 72/28080 [08:32<55:00:47,  7.07s/it]
                                                     
{'loss': 0.9781, 'learning_rate': 4.270462633451958e-05, 'epoch': 0.03}

  0%|          | 72/28080 [08:32<55:00:47,  7.07s/it]
  0%|          | 73/28080 [08:39<55:06:55,  7.08s/it]
                                                     
{'loss': 0.9733, 'learning_rate': 4.3297746144721233e-05, 'epoch': 0.03}

  0%|          | 73/28080 [08:39<55:06:55,  7.08s/it]
  0%|          | 74/28080 [08:46<55:13:10,  7.10s/it]
                                                     
{'loss': 0.9699, 'learning_rate': 4.3890865954922896e-05, 'epoch': 0.03}

  0%|          | 74/28080 [08:46<55:13:10,  7.10s/it]
  0%|          | 75/28080 [08:53<55:17:12,  7.11s/it]
                                                     
{'loss': 0.9749, 'learning_rate': 4.448398576512456e-05, 'epoch': 0.03}

  0%|          | 75/28080 [08:53<55:17:12,  7.11s/it]
  0%|          | 76/28080 [09:01<55:24:55,  7.12s/it]
                                                     
{'loss': 0.9713, 'learning_rate': 4.507710557532622e-05, 'epoch': 0.03}

  0%|          | 76/28080 [09:01<55:24:55,  7.12s/it]
  0%|          | 77/28080 [09:08<55:22:21,  7.12s/it]
                                                     
{'loss': 0.9721, 'learning_rate': 4.5670225385527876e-05, 'epoch': 0.03}

  0%|          | 77/28080 [09:08<55:22:21,  7.12s/it]
  0%|          | 78/28080 [09:15<55:08:20,  7.09s/it]
                                                     
{'loss': 0.969, 'learning_rate': 4.626334519572953e-05, 'epoch': 0.03}

  0%|          | 78/28080 [09:15<55:08:20,  7.09s/it]
  0%|          | 79/28080 [09:22<55:21:26,  7.12s/it]
                                                     
{'loss': 0.9796, 'learning_rate': 4.68564650059312e-05, 'epoch': 0.03}

  0%|          | 79/28080 [09:22<55:21:26,  7.12s/it]
  0%|          | 80/28080 [09:29<55:31:53,  7.14s/it]
                                                     
{'loss': 0.9617, 'learning_rate': 4.744958481613286e-05, 'epoch': 0.03}

  0%|          | 80/28080 [09:29<55:31:53,  7.14s/it]
  0%|          | 81/28080 [09:36<55:22:01,  7.12s/it]
                                                     
{'loss': 0.9638, 'learning_rate': 4.804270462633452e-05, 'epoch': 0.03}

  0%|          | 81/28080 [09:36<55:22:01,  7.12s/it]
  0%|          | 82/28080 [09:43<55:19:10,  7.11s/it]
                                                     
{'loss': 0.9667, 'learning_rate': 4.863582443653618e-05, 'epoch': 0.04}

  0%|          | 82/28080 [09:43<55:19:10,  7.11s/it]
  0%|          | 83/28080 [09:50<55:14:35,  7.10s/it]
                                                     
{'loss': 0.9667, 'learning_rate': 4.9228944246737844e-05, 'epoch': 0.04}

  0%|          | 83/28080 [09:50<55:14:35,  7.10s/it]
  0%|          | 84/28080 [09:57<55:11:58,  7.10s/it]
                                                     
{'loss': 0.9664, 'learning_rate': 4.98220640569395e-05, 'epoch': 0.04}

  0%|          | 84/28080 [09:57<55:11:58,  7.10s/it]
  0%|          | 85/28080 [10:04<55:01:45,  7.08s/it]
                                                     
{'loss': 0.9643, 'learning_rate': 5.041518386714116e-05, 'epoch': 0.04}

  0%|          | 85/28080 [10:04<55:01:45,  7.08s/it]
  0%|          | 86/28080 [10:12<55:15:29,  7.11s/it]
                                                     
{'loss': 0.968, 'learning_rate': 5.1008303677342824e-05, 'epoch': 0.04}

  0%|          | 86/28080 [10:12<55:15:29,  7.11s/it]
  0%|          | 87/28080 [10:19<55:25:31,  7.13s/it]
                                                     
{'loss': 0.9621, 'learning_rate': 5.160142348754449e-05, 'epoch': 0.04}

  0%|          | 87/28080 [10:19<55:25:31,  7.13s/it]
  0%|          | 88/28080 [10:26<55:53:18,  7.19s/it]
                                                     
{'loss': 0.9676, 'learning_rate': 5.219454329774614e-05, 'epoch': 0.04}

  0%|          | 88/28080 [10:26<55:53:18,  7.19s/it]
  0%|          | 89/28080 [10:33<55:40:24,  7.16s/it]
                                                     
{'loss': 0.964, 'learning_rate': 5.2787663107947805e-05, 'epoch': 0.04}

  0%|          | 89/28080 [10:33<55:40:24,  7.16s/it]
  0%|          | 90/28080 [10:40<55:26:19,  7.13s/it]
                                                     
{'loss': 0.9698, 'learning_rate': 5.338078291814947e-05, 'epoch': 0.04}

  0%|          | 90/28080 [10:40<55:26:19,  7.13s/it]
  0%|          | 91/28080 [10:47<55:30:17,  7.14s/it]
                                                     
{'loss': 0.9638, 'learning_rate': 5.397390272835113e-05, 'epoch': 0.04}

  0%|          | 91/28080 [10:47<55:30:17,  7.14s/it]
  0%|          | 92/28080 [10:55<55:33:49,  7.15s/it]
                                                     
{'loss': 0.965, 'learning_rate': 5.4567022538552785e-05, 'epoch': 0.04}

  0%|          | 92/28080 [10:55<55:33:49,  7.15s/it]
  0%|          | 93/28080 [11:02<55:08:35,  7.09s/it]
                                                     
{'loss': 0.9627, 'learning_rate': 5.5160142348754454e-05, 'epoch': 0.04}

  0%|          | 93/28080 [11:02<55:08:35,  7.09s/it]
  0%|          | 94/28080 [11:09<55:20:35,  7.12s/it]
                                                     
{'loss': 0.9628, 'learning_rate': 5.575326215895611e-05, 'epoch': 0.04}

  0%|          | 94/28080 [11:09<55:20:35,  7.12s/it]
  0%|          | 95/28080 [11:16<55:17:31,  7.11s/it]
                                                     
{'loss': 0.9556, 'learning_rate': 5.634638196915777e-05, 'epoch': 0.04}

  0%|          | 95/28080 [11:16<55:17:31,  7.11s/it]
  0%|          | 96/28080 [11:23<55:31:03,  7.14s/it]
                                                     
{'loss': 0.9695, 'learning_rate': 5.693950177935943e-05, 'epoch': 0.04}

  0%|          | 96/28080 [11:23<55:31:03,  7.14s/it]
  0%|          | 97/28080 [11:30<55:35:30,  7.15s/it]
                                                     
{'loss': 0.963, 'learning_rate': 5.75326215895611e-05, 'epoch': 0.04}

  0%|          | 97/28080 [11:30<55:35:30,  7.15s/it]
  0%|          | 98/28080 [11:37<55:19:21,  7.12s/it]
                                                     
{'loss': 0.9646, 'learning_rate': 5.812574139976275e-05, 'epoch': 0.04}

  0%|          | 98/28080 [11:37<55:19:21,  7.12s/it]
  0%|          | 99/28080 [11:44<55:06:50,  7.09s/it]
                                                     
{'loss': 0.9659, 'learning_rate': 5.8718861209964415e-05, 'epoch': 0.04}

  0%|          | 99/28080 [11:44<55:06:50,  7.09s/it]
  0%|          | 100/28080 [11:51<55:10:27,  7.10s/it]
                                                      
{'loss': 0.9647, 'learning_rate': 5.931198102016608e-05, 'epoch': 0.04}

  0%|          | 100/28080 [11:51<55:10:27,  7.10s/it]
  0%|          | 101/28080 [11:59<55:08:32,  7.10s/it]
                                                      
{'loss': 0.9611, 'learning_rate': 5.990510083036774e-05, 'epoch': 0.04}

  0%|          | 101/28080 [11:59<55:08:32,  7.10s/it]
  0%|          | 102/28080 [12:06<55:13:42,  7.11s/it]
                                                      
{'loss': 0.9594, 'learning_rate': 6.0498220640569396e-05, 'epoch': 0.04}

  0%|          | 102/28080 [12:06<55:13:42,  7.11s/it]
  0%|          | 103/28080 [12:13<55:19:46,  7.12s/it]
                                                      
{'loss': 0.9663, 'learning_rate': 6.109134045077105e-05, 'epoch': 0.04}

  0%|          | 103/28080 [12:13<55:19:46,  7.12s/it]
  0%|          | 104/28080 [12:20<55:18:45,  7.12s/it]
                                                      
{'loss': 0.9636, 'learning_rate': 6.168446026097271e-05, 'epoch': 0.04}

  0%|          | 104/28080 [12:20<55:18:45,  7.12s/it]
  0%|          | 105/28080 [12:27<55:15:05,  7.11s/it]
                                                      
{'loss': 0.9528, 'learning_rate': 6.227758007117438e-05, 'epoch': 0.04}

  0%|          | 105/28080 [12:27<55:15:05,  7.11s/it]
  0%|          | 106/28080 [12:34<55:17:03,  7.11s/it]
                                                      
{'loss': 0.95, 'learning_rate': 6.287069988137604e-05, 'epoch': 0.05}

  0%|          | 106/28080 [12:34<55:17:03,  7.11s/it]
  0%|          | 107/28080 [12:41<55:19:04,  7.12s/it]
                                                      
{'loss': 0.9605, 'learning_rate': 6.34638196915777e-05, 'epoch': 0.05}

  0%|          | 107/28080 [12:41<55:19:04,  7.12s/it]
  0%|          | 108/28080 [12:48<55:33:05,  7.15s/it]
                                                      
{'loss': 0.9532, 'learning_rate': 6.405693950177936e-05, 'epoch': 0.05}

  0%|          | 108/28080 [12:48<55:33:05,  7.15s/it]
  0%|          | 109/28080 [12:56<55:28:58,  7.14s/it]
                                                      
{'loss': 0.9605, 'learning_rate': 6.465005931198103e-05, 'epoch': 0.05}

  0%|          | 109/28080 [12:56<55:28:58,  7.14s/it]
  0%|          | 110/28080 [13:03<55:35:05,  7.15s/it]
                                                      
{'loss': 0.9642, 'learning_rate': 6.524317912218267e-05, 'epoch': 0.05}

  0%|          | 110/28080 [13:03<55:35:05,  7.15s/it]
  0%|          | 111/28080 [13:10<55:29:38,  7.14s/it]
                                                      
{'loss': 0.959, 'learning_rate': 6.583629893238434e-05, 'epoch': 0.05}

  0%|          | 111/28080 [13:10<55:29:38,  7.14s/it]
  0%|          | 112/28080 [13:17<55:17:42,  7.12s/it]
                                                      
{'loss': 0.9608, 'learning_rate': 6.6429418742586e-05, 'epoch': 0.05}

  0%|          | 112/28080 [13:17<55:17:42,  7.12s/it]
  0%|          | 113/28080 [13:24<55:43:05,  7.17s/it]
                                                      
{'loss': 0.9579, 'learning_rate': 6.702253855278768e-05, 'epoch': 0.05}

  0%|          | 113/28080 [13:24<55:43:05,  7.17s/it]
  0%|          | 114/28080 [13:31<55:21:24,  7.13s/it]
                                                      
{'loss': 0.9612, 'learning_rate': 6.761565836298932e-05, 'epoch': 0.05}

  0%|          | 114/28080 [13:31<55:21:24,  7.13s/it]
  0%|          | 115/28080 [13:38<55:17:41,  7.12s/it]
                                                      
{'loss': 0.9634, 'learning_rate': 6.820877817319099e-05, 'epoch': 0.05}

  0%|          | 115/28080 [13:38<55:17:41,  7.12s/it]
  0%|          | 116/28080 [13:45<55:06:43,  7.09s/it]
                                                      
{'loss': 0.9589, 'learning_rate': 6.880189798339265e-05, 'epoch': 0.05}

  0%|          | 116/28080 [13:45<55:06:43,  7.09s/it]
  0%|          | 117/28080 [13:53<55:06:35,  7.09s/it]
                                                      
{'loss': 0.9611, 'learning_rate': 6.939501779359431e-05, 'epoch': 0.05}

  0%|          | 117/28080 [13:53<55:06:35,  7.09s/it]
  0%|          | 118/28080 [14:00<55:13:19,  7.11s/it]
                                                      
{'loss': 0.9666, 'learning_rate': 6.998813760379596e-05, 'epoch': 0.05}

  0%|          | 118/28080 [14:00<55:13:19,  7.11s/it]
  0%|          | 119/28080 [14:07<55:19:02,  7.12s/it]
                                                      
{'loss': 0.9588, 'learning_rate': 7.058125741399762e-05, 'epoch': 0.05}

  0%|          | 119/28080 [14:07<55:19:02,  7.12s/it]
  0%|          | 120/28080 [14:14<55:15:52,  7.12s/it]
                                                      
{'loss': 0.9626, 'learning_rate': 7.11743772241993e-05, 'epoch': 0.05}

  0%|          | 120/28080 [14:14<55:15:52,  7.12s/it]
  0%|          | 121/28080 [14:21<55:03:09,  7.09s/it]
                                                      
{'loss': 0.9546, 'learning_rate': 7.176749703440096e-05, 'epoch': 0.05}

  0%|          | 121/28080 [14:21<55:03:09,  7.09s/it]
  0%|          | 122/28080 [14:28<54:54:28,  7.07s/it]
                                                      
{'loss': 0.9584, 'learning_rate': 7.236061684460261e-05, 'epoch': 0.05}

  0%|          | 122/28080 [14:28<54:54:28,  7.07s/it]
  0%|          | 123/28080 [14:35<55:07:38,  7.10s/it]
                                                      
{'loss': 0.9645, 'learning_rate': 7.295373665480427e-05, 'epoch': 0.05}

  0%|          | 123/28080 [14:35<55:07:38,  7.10s/it]
  0%|          | 124/28080 [14:42<55:13:55,  7.11s/it]
                                                      
{'loss': 0.9526, 'learning_rate': 7.354685646500593e-05, 'epoch': 0.05}

  0%|          | 124/28080 [14:42<55:13:55,  7.11s/it]
  0%|          | 125/28080 [14:49<55:12:29,  7.11s/it]
                                                      
{'loss': 0.9507, 'learning_rate': 7.41399762752076e-05, 'epoch': 0.05}

  0%|          | 125/28080 [14:49<55:12:29,  7.11s/it]
  0%|          | 126/28080 [14:56<55:10:37,  7.11s/it]
                                                      
{'loss': 0.9567, 'learning_rate': 7.473309608540925e-05, 'epoch': 0.05}

  0%|          | 126/28080 [14:56<55:10:37,  7.11s/it]
  0%|          | 127/28080 [15:04<55:09:30,  7.10s/it]
                                                      
{'loss': 0.9567, 'learning_rate': 7.532621589561091e-05, 'epoch': 0.05}

  0%|          | 127/28080 [15:04<55:09:30,  7.10s/it]
  0%|          | 128/28080 [15:11<55:03:38,  7.09s/it]
                                                      
{'loss': 0.9595, 'learning_rate': 7.591933570581258e-05, 'epoch': 0.05}

  0%|          | 128/28080 [15:11<55:03:38,  7.09s/it]
  0%|          | 129/28080 [15:18<54:49:35,  7.06s/it]
                                                      
{'loss': 0.9625, 'learning_rate': 7.651245551601423e-05, 'epoch': 0.06}

  0%|          | 129/28080 [15:18<54:49:35,  7.06s/it]
  0%|          | 130/28080 [15:25<54:54:31,  7.07s/it]
                                                      
{'loss': 0.9632, 'learning_rate': 7.71055753262159e-05, 'epoch': 0.06}

  0%|          | 130/28080 [15:25<54:54:31,  7.07s/it]
  0%|          | 131/28080 [15:32<55:09:51,  7.11s/it]
                                                      
{'loss': 0.9569, 'learning_rate': 7.769869513641756e-05, 'epoch': 0.06}

  0%|          | 131/28080 [15:32<55:09:51,  7.11s/it]
  0%|          | 132/28080 [15:39<55:09:12,  7.10s/it]
                                                      
{'loss': 0.9666, 'learning_rate': 7.829181494661922e-05, 'epoch': 0.06}

  0%|          | 132/28080 [15:39<55:09:12,  7.10s/it]
  0%|          | 133/28080 [15:46<55:13:53,  7.11s/it]
                                                      
{'loss': 0.9598, 'learning_rate': 7.888493475682087e-05, 'epoch': 0.06}

  0%|          | 133/28080 [15:46<55:13:53,  7.11s/it]
  0%|          | 134/28080 [15:53<55:20:00,  7.13s/it]
                                                      
{'loss': 0.9527, 'learning_rate': 7.947805456702253e-05, 'epoch': 0.06}

  0%|          | 134/28080 [15:53<55:20:00,  7.13s/it]
  0%|          | 135/28080 [16:00<55:10:35,  7.11s/it]
                                                      
{'loss': 0.9553, 'learning_rate': 8.007117437722421e-05, 'epoch': 0.06}

  0%|          | 135/28080 [16:00<55:10:35,  7.11s/it]
  0%|          | 136/28080 [16:07<55:04:41,  7.10s/it]
                                                      
{'loss': 0.9609, 'learning_rate': 8.066429418742587e-05, 'epoch': 0.06}

  0%|          | 136/28080 [16:07<55:04:41,  7.10s/it]
  0%|          | 137/28080 [16:14<54:49:14,  7.06s/it]
                                                      
{'loss': 0.9564, 'learning_rate': 8.125741399762752e-05, 'epoch': 0.06}

  0%|          | 137/28080 [16:14<54:49:14,  7.06s/it]
  0%|          | 138/28080 [16:21<54:46:29,  7.06s/it]
                                                      
{'loss': 0.9546, 'learning_rate': 8.185053380782918e-05, 'epoch': 0.06}

  0%|          | 138/28080 [16:21<54:46:29,  7.06s/it]
  0%|          | 139/28080 [16:29<54:59:41,  7.09s/it]
                                                      
{'loss': 0.9532, 'learning_rate': 8.244365361803084e-05, 'epoch': 0.06}

  0%|          | 139/28080 [16:29<54:59:41,  7.09s/it]
  0%|          | 140/28080 [16:36<54:54:25,  7.07s/it]
                                                      
{'loss': 0.9533, 'learning_rate': 8.30367734282325e-05, 'epoch': 0.06}

  0%|          | 140/28080 [16:36<54:54:25,  7.07s/it]
  1%|          | 141/28080 [16:43<54:56:53,  7.08s/it]
                                                      
{'loss': 0.9472, 'learning_rate': 8.362989323843415e-05, 'epoch': 0.06}

  1%|          | 141/28080 [16:43<54:56:53,  7.08s/it]
  1%|          | 142/28080 [16:50<55:02:32,  7.09s/it]
                                                      
{'loss': 0.9494, 'learning_rate': 8.422301304863583e-05, 'epoch': 0.06}

  1%|          | 142/28080 [16:50<55:02:32,  7.09s/it]
  1%|          | 143/28080 [16:57<55:17:11,  7.12s/it]
                                                      
{'loss': 0.9536, 'learning_rate': 8.48161328588375e-05, 'epoch': 0.06}

  1%|          | 143/28080 [16:57<55:17:11,  7.12s/it]
  1%|          | 144/28080 [17:04<55:21:14,  7.13s/it]
                                                      
{'loss': 0.9561, 'learning_rate': 8.540925266903916e-05, 'epoch': 0.06}

  1%|          | 144/28080 [17:04<55:21:14,  7.13s/it]
  1%|          | 145/28080 [17:11<55:23:12,  7.14s/it]
                                                      
{'loss': 0.9452, 'learning_rate': 8.60023724792408e-05, 'epoch': 0.06}

  1%|          | 145/28080 [17:11<55:23:12,  7.14s/it]
  1%|          | 146/28080 [17:18<55:19:42,  7.13s/it]
                                                      
{'loss': 0.9574, 'learning_rate': 8.659549228944247e-05, 'epoch': 0.06}

  1%|          | 146/28080 [17:18<55:19:42,  7.13s/it]
  1%|          | 147/28080 [17:26<55:19:00,  7.13s/it]
                                                      
{'loss': 0.9615, 'learning_rate': 8.718861209964413e-05, 'epoch': 0.06}

  1%|          | 147/28080 [17:26<55:19:00,  7.13s/it]
  1%|          | 148/28080 [17:33<55:07:40,  7.11s/it]
                                                      
{'loss': 0.9521, 'learning_rate': 8.778173190984579e-05, 'epoch': 0.06}

  1%|          | 148/28080 [17:33<55:07:40,  7.11s/it]
  1%|          | 149/28080 [17:40<55:03:46,  7.10s/it]
                                                      
{'loss': 0.9564, 'learning_rate': 8.837485172004745e-05, 'epoch': 0.06}

  1%|          | 149/28080 [17:40<55:03:46,  7.10s/it]
  1%|          | 150/28080 [17:47<55:06:49,  7.10s/it]
                                                      
{'loss': 0.9562, 'learning_rate': 8.896797153024912e-05, 'epoch': 0.06}

  1%|          | 150/28080 [17:47<55:06:49,  7.10s/it]
  1%|          | 151/28080 [17:54<55:08:07,  7.11s/it]
                                                      
{'loss': 0.9671, 'learning_rate': 8.956109134045078e-05, 'epoch': 0.06}

  1%|          | 151/28080 [17:54<55:08:07,  7.11s/it]
  1%|          | 152/28080 [18:01<55:10:34,  7.11s/it]
                                                      
{'loss': 0.954, 'learning_rate': 9.015421115065244e-05, 'epoch': 0.06}

  1%|          | 152/28080 [18:01<55:10:34,  7.11s/it]
  1%|          | 153/28080 [18:08<55:15:49,  7.12s/it]
                                                      
{'loss': 0.9551, 'learning_rate': 9.074733096085409e-05, 'epoch': 0.07}

  1%|          | 153/28080 [18:08<55:15:49,  7.12s/it]
  1%|          | 154/28080 [18:15<55:11:53,  7.12s/it]
                                                      
{'loss': 0.9583, 'learning_rate': 9.134045077105575e-05, 'epoch': 0.07}

  1%|          | 154/28080 [18:15<55:11:53,  7.12s/it]
  1%|          | 155/28080 [18:22<55:15:06,  7.12s/it]
                                                      
{'loss': 0.9551, 'learning_rate': 9.193357058125742e-05, 'epoch': 0.07}

  1%|          | 155/28080 [18:23<55:15:06,  7.12s/it]
  1%|          | 156/28080 [18:30<55:23:37,  7.14s/it]
                                                      
{'loss': 0.9577, 'learning_rate': 9.252669039145906e-05, 'epoch': 0.07}

  1%|          | 156/28080 [18:30<55:23:37,  7.14s/it]
  1%|          | 157/28080 [18:37<55:23:29,  7.14s/it]
                                                      
{'loss': 0.9568, 'learning_rate': 9.311981020166074e-05, 'epoch': 0.07}

  1%|          | 157/28080 [18:37<55:23:29,  7.14s/it]
  1%|          | 158/28080 [18:44<55:29:05,  7.15s/it]
                                                      
{'loss': 0.954, 'learning_rate': 9.37129300118624e-05, 'epoch': 0.07}

  1%|          | 158/28080 [18:44<55:29:05,  7.15s/it]
  1%|          | 159/28080 [18:51<55:17:15,  7.13s/it]
                                                      
{'loss': 0.9535, 'learning_rate': 9.430604982206406e-05, 'epoch': 0.07}

  1%|          | 159/28080 [18:51<55:17:15,  7.13s/it]
  1%|          | 160/28080 [18:58<55:18:58,  7.13s/it]
                                                      
{'loss': 0.9512, 'learning_rate': 9.489916963226571e-05, 'epoch': 0.07}

  1%|          | 160/28080 [18:58<55:18:58,  7.13s/it]
  1%|          | 161/28080 [19:05<54:59:14,  7.09s/it]
                                                      
{'loss': 0.9574, 'learning_rate': 9.549228944246738e-05, 'epoch': 0.07}

  1%|          | 161/28080 [19:05<54:59:14,  7.09s/it]
  1%|          | 162/28080 [19:12<54:51:13,  7.07s/it]
                                                      
{'loss': 0.9629, 'learning_rate': 9.608540925266904e-05, 'epoch': 0.07}

  1%|          | 162/28080 [19:12<54:51:13,  7.07s/it]
  1%|          | 163/28080 [19:19<54:41:24,  7.05s/it]
                                                      
{'loss': 0.9508, 'learning_rate': 9.66785290628707e-05, 'epoch': 0.07}

  1%|          | 163/28080 [19:19<54:41:24,  7.05s/it]
  1%|          | 164/28080 [19:26<54:46:08,  7.06s/it]
                                                      
{'loss': 0.9514, 'learning_rate': 9.727164887307236e-05, 'epoch': 0.07}

  1%|          | 164/28080 [19:26<54:46:08,  7.06s/it]
  1%|          | 165/28080 [19:33<54:53:00,  7.08s/it]
                                                      
{'loss': 0.948, 'learning_rate': 9.786476868327403e-05, 'epoch': 0.07}

  1%|          | 165/28080 [19:33<54:53:00,  7.08s/it]
  1%|          | 166/28080 [19:41<54:51:27,  7.07s/it]
                                                      
{'loss': 0.9508, 'learning_rate': 9.845788849347569e-05, 'epoch': 0.07}

  1%|          | 166/28080 [19:41<54:51:27,  7.07s/it]
  1%|          | 167/28080 [19:48<55:05:27,  7.11s/it]
                                                      
{'loss': 0.9532, 'learning_rate': 9.905100830367735e-05, 'epoch': 0.07}

  1%|          | 167/28080 [19:48<55:05:27,  7.11s/it]
  1%|          | 168/28080 [19:55<55:07:19,  7.11s/it]
                                                      
{'loss': 0.9501, 'learning_rate': 9.9644128113879e-05, 'epoch': 0.07}

  1%|          | 168/28080 [19:55<55:07:19,  7.11s/it]
  1%|          | 169/28080 [20:02<55:02:50,  7.10s/it]
                                                      
{'loss': 0.9558, 'learning_rate': 0.00010023724792408066, 'epoch': 0.07}

  1%|          | 169/28080 [20:02<55:02:50,  7.10s/it]
  1%|          | 170/28080 [20:09<55:08:08,  7.11s/it]
                                                      
{'loss': 0.9523, 'learning_rate': 0.00010083036773428232, 'epoch': 0.07}

  1%|          | 170/28080 [20:09<55:08:08,  7.11s/it]
  1%|          | 171/28080 [20:16<55:04:16,  7.10s/it]
                                                      
{'loss': 0.9499, 'learning_rate': 0.000101423487544484, 'epoch': 0.07}

  1%|          | 171/28080 [20:16<55:04:16,  7.10s/it]
  1%|          | 172/28080 [20:23<54:56:32,  7.09s/it]
                                                      
{'loss': 0.9547, 'learning_rate': 0.00010201660735468565, 'epoch': 0.07}

  1%|          | 172/28080 [20:23<54:56:32,  7.09s/it]
  1%|          | 173/28080 [20:30<55:09:27,  7.12s/it]
                                                      
{'loss': 0.9445, 'learning_rate': 0.00010260972716488731, 'epoch': 0.07}

  1%|          | 173/28080 [20:30<55:09:27,  7.12s/it]
  1%|          | 174/28080 [20:37<55:09:00,  7.11s/it]
                                                      
{'loss': 0.9622, 'learning_rate': 0.00010320284697508897, 'epoch': 0.07}

  1%|          | 174/28080 [20:37<55:09:00,  7.11s/it]
  1%|          | 175/28080 [20:45<55:09:58,  7.12s/it]
                                                      
{'loss': 0.9582, 'learning_rate': 0.00010379596678529064, 'epoch': 0.07}

  1%|          | 175/28080 [20:45<55:09:58,  7.12s/it]
  1%|          | 176/28080 [20:52<54:48:17,  7.07s/it]
                                                      
{'loss': 0.9516, 'learning_rate': 0.00010438908659549228, 'epoch': 0.08}

  1%|          | 176/28080 [20:52<54:48:17,  7.07s/it]
  1%|          | 177/28080 [20:59<55:08:39,  7.11s/it]
                                                      
{'loss': 0.9514, 'learning_rate': 0.00010498220640569395, 'epoch': 0.08}

  1%|          | 177/28080 [20:59<55:08:39,  7.11s/it]
  1%|          | 178/28080 [21:06<55:14:09,  7.13s/it]
                                                      
{'loss': 0.9585, 'learning_rate': 0.00010557532621589561, 'epoch': 0.08}

  1%|          | 178/28080 [21:06<55:14:09,  7.13s/it]
  1%|          | 179/28080 [21:13<55:22:23,  7.14s/it]
                                                      
{'loss': 0.9572, 'learning_rate': 0.00010616844602609729, 'epoch': 0.08}

  1%|          | 179/28080 [21:13<55:22:23,  7.14s/it]
  1%|          | 180/28080 [21:20<55:13:06,  7.12s/it]
                                                      
{'loss': 0.9503, 'learning_rate': 0.00010676156583629893, 'epoch': 0.08}

  1%|          | 180/28080 [21:20<55:13:06,  7.12s/it]
  1%|          | 181/28080 [21:27<55:00:36,  7.10s/it]
                                                      
{'loss': 0.9519, 'learning_rate': 0.0001073546856465006, 'epoch': 0.08}

  1%|          | 181/28080 [21:27<55:00:36,  7.10s/it]
  1%|          | 182/28080 [21:34<55:05:57,  7.11s/it]
                                                      
{'loss': 0.9486, 'learning_rate': 0.00010794780545670226, 'epoch': 0.08}

  1%|          | 182/28080 [21:34<55:05:57,  7.11s/it]
  1%|          | 183/28080 [21:41<54:57:01,  7.09s/it]
                                                      
{'loss': 0.9598, 'learning_rate': 0.00010854092526690391, 'epoch': 0.08}

  1%|          | 183/28080 [21:41<54:57:01,  7.09s/it]
  1%|          | 184/28080 [21:48<54:53:08,  7.08s/it]
                                                      
{'loss': 0.953, 'learning_rate': 0.00010913404507710557, 'epoch': 0.08}

  1%|          | 184/28080 [21:48<54:53:08,  7.08s/it]
  1%|          | 185/28080 [21:56<55:01:54,  7.10s/it]
                                                      
{'loss': 0.9583, 'learning_rate': 0.00010972716488730723, 'epoch': 0.08}

  1%|          | 185/28080 [21:56<55:01:54,  7.10s/it]
  1%|          | 186/28080 [22:03<55:05:16,  7.11s/it]
                                                      
{'loss': 0.959, 'learning_rate': 0.00011032028469750891, 'epoch': 0.08}

  1%|          | 186/28080 [22:03<55:05:16,  7.11s/it]
  1%|          | 187/28080 [22:10<55:06:22,  7.11s/it]
                                                      
{'loss': 0.96, 'learning_rate': 0.00011091340450771056, 'epoch': 0.08}

  1%|          | 187/28080 [22:10<55:06:22,  7.11s/it]
  1%|          | 188/28080 [22:17<55:22:24,  7.15s/it]
                                                      
{'loss': 0.9515, 'learning_rate': 0.00011150652431791222, 'epoch': 0.08}

  1%|          | 188/28080 [22:17<55:22:24,  7.15s/it]
  1%|          | 189/28080 [22:24<55:27:58,  7.16s/it]
                                                      
{'loss': 0.9459, 'learning_rate': 0.00011209964412811388, 'epoch': 0.08}

  1%|          | 189/28080 [22:24<55:27:58,  7.16s/it]
  1%|          | 190/28080 [22:31<55:22:28,  7.15s/it]
                                                      
{'loss': 0.9546, 'learning_rate': 0.00011269276393831554, 'epoch': 0.08}

  1%|          | 190/28080 [22:31<55:22:28,  7.15s/it]
  1%|          | 191/28080 [22:38<55:17:02,  7.14s/it]
                                                      
{'loss': 0.9493, 'learning_rate': 0.0001132858837485172, 'epoch': 0.08}

  1%|          | 191/28080 [22:38<55:17:02,  7.14s/it]
  1%|          | 192/28080 [22:46<55:13:27,  7.13s/it]
                                                      
{'loss': 0.9418, 'learning_rate': 0.00011387900355871886, 'epoch': 0.08}

  1%|          | 192/28080 [22:46<55:13:27,  7.13s/it]
  1%|          | 193/28080 [22:53<55:09:55,  7.12s/it]
                                                      
{'loss': 0.9494, 'learning_rate': 0.00011447212336892053, 'epoch': 0.08}

  1%|          | 193/28080 [22:53<55:09:55,  7.12s/it]
  1%|          | 194/28080 [23:00<55:12:43,  7.13s/it]
                                                      
{'loss': 0.9531, 'learning_rate': 0.0001150652431791222, 'epoch': 0.08}

  1%|          | 194/28080 [23:00<55:12:43,  7.13s/it]
  1%|          | 195/28080 [23:07<55:15:34,  7.13s/it]
                                                      
{'loss': 0.9509, 'learning_rate': 0.00011565836298932384, 'epoch': 0.08}

  1%|          | 195/28080 [23:07<55:15:34,  7.13s/it]
  1%|          | 196/28080 [23:14<55:15:05,  7.13s/it]
                                                      
{'loss': 0.9529, 'learning_rate': 0.0001162514827995255, 'epoch': 0.08}

  1%|          | 196/28080 [23:14<55:15:05,  7.13s/it]
  1%|          | 197/28080 [23:21<55:10:42,  7.12s/it]
                                                      
{'loss': 0.9548, 'learning_rate': 0.00011684460260972717, 'epoch': 0.08}

  1%|          | 197/28080 [23:21<55:10:42,  7.12s/it]
  1%|          | 198/28080 [23:28<55:00:37,  7.10s/it]
                                                      
{'loss': 0.9593, 'learning_rate': 0.00011743772241992883, 'epoch': 0.08}

  1%|          | 198/28080 [23:28<55:00:37,  7.10s/it]
  1%|          | 199/28080 [23:35<55:02:31,  7.11s/it]
                                                      
{'loss': 0.9576, 'learning_rate': 0.00011803084223013048, 'epoch': 0.09}

  1%|          | 199/28080 [23:35<55:02:31,  7.11s/it]
  1%|          | 200/28080 [23:42<54:57:05,  7.10s/it]
                                                      
{'loss': 0.9534, 'learning_rate': 0.00011862396204033216, 'epoch': 0.09}

  1%|          | 200/28080 [23:42<54:57:05,  7.10s/it]
  1%|          | 201/28080 [23:50<55:06:50,  7.12s/it]
                                                      
{'loss': 0.9469, 'learning_rate': 0.00011921708185053382, 'epoch': 0.09}

  1%|          | 201/28080 [23:50<55:06:50,  7.12s/it]
  1%|          | 202/28080 [23:57<54:46:07,  7.07s/it]
                                                      
{'loss': 0.9512, 'learning_rate': 0.00011981020166073548, 'epoch': 0.09}

  1%|          | 202/28080 [23:57<54:46:07,  7.07s/it]
  1%|          | 203/28080 [24:04<54:50:41,  7.08s/it]
                                                      
{'loss': 0.9546, 'learning_rate': 0.00012040332147093713, 'epoch': 0.09}

  1%|          | 203/28080 [24:04<54:50:41,  7.08s/it]
  1%|          | 204/28080 [24:11<54:58:10,  7.10s/it]
                                                      
{'loss': 0.9521, 'learning_rate': 0.00012099644128113879, 'epoch': 0.09}

  1%|          | 204/28080 [24:11<54:58:10,  7.10s/it]
  1%|          | 205/28080 [24:18<55:04:41,  7.11s/it]
                                                      
{'loss': 0.9435, 'learning_rate': 0.00012158956109134045, 'epoch': 0.09}

  1%|          | 205/28080 [24:18<55:04:41,  7.11s/it]
  1%|          | 206/28080 [24:25<54:57:44,  7.10s/it]
                                                      
{'loss': 0.9471, 'learning_rate': 0.0001221826809015421, 'epoch': 0.09}

  1%|          | 206/28080 [24:25<54:57:44,  7.10s/it]
  1%|          | 207/28080 [24:32<55:05:09,  7.11s/it]
                                                      
{'loss': 0.9475, 'learning_rate': 0.00012277580071174378, 'epoch': 0.09}

  1%|          | 207/28080 [24:32<55:05:09,  7.11s/it]
  1%|          | 208/28080 [24:39<55:07:03,  7.12s/it]
                                                      
{'loss': 0.9584, 'learning_rate': 0.00012336892052194543, 'epoch': 0.09}

  1%|          | 208/28080 [24:39<55:07:03,  7.12s/it]
  1%|          | 209/28080 [24:46<54:56:43,  7.10s/it]
                                                      
{'loss': 0.9458, 'learning_rate': 0.0001239620403321471, 'epoch': 0.09}

  1%|          | 209/28080 [24:46<54:56:43,  7.10s/it]
  1%|          | 210/28080 [24:53<54:58:25,  7.10s/it]
                                                      
{'loss': 0.946, 'learning_rate': 0.00012455516014234875, 'epoch': 0.09}

  1%|          | 210/28080 [24:54<54:58:25,  7.10s/it]
  1%|          | 211/28080 [25:01<55:02:58,  7.11s/it]
                                                      
{'loss': 0.9313, 'learning_rate': 0.00012514827995255043, 'epoch': 0.09}

  1%|          | 211/28080 [25:01<55:02:58,  7.11s/it]
  1%|          | 212/28080 [25:08<55:07:52,  7.12s/it]
                                                      
{'loss': 0.937, 'learning_rate': 0.00012574139976275208, 'epoch': 0.09}

  1%|          | 212/28080 [25:08<55:07:52,  7.12s/it]
  1%|          | 213/28080 [25:15<55:01:01,  7.11s/it]
                                                      
{'loss': 0.9329, 'learning_rate': 0.00012633451957295375, 'epoch': 0.09}

  1%|          | 213/28080 [25:15<55:01:01,  7.11s/it]
  1%|          | 214/28080 [25:22<55:13:42,  7.13s/it]
                                                      
{'loss': 0.9348, 'learning_rate': 0.0001269276393831554, 'epoch': 0.09}

  1%|          | 214/28080 [25:22<55:13:42,  7.13s/it]
  1%|          | 215/28080 [25:29<54:58:31,  7.10s/it]
                                                      
{'loss': 0.9406, 'learning_rate': 0.00012752075919335708, 'epoch': 0.09}

  1%|          | 215/28080 [25:29<54:58:31,  7.10s/it]
  1%|          | 216/28080 [25:36<55:02:23,  7.11s/it]
                                                      
{'loss': 0.9247, 'learning_rate': 0.00012811387900355873, 'epoch': 0.09}

  1%|          | 216/28080 [25:36<55:02:23,  7.11s/it]
  1%|          | 217/28080 [25:43<55:02:03,  7.11s/it]
                                                      
{'loss': 0.9206, 'learning_rate': 0.00012870699881376038, 'epoch': 0.09}

  1%|          | 217/28080 [25:43<55:02:03,  7.11s/it]
  1%|          | 218/28080 [25:50<55:01:18,  7.11s/it]
                                                      
{'loss': 0.939, 'learning_rate': 0.00012930011862396205, 'epoch': 0.09}

  1%|          | 218/28080 [25:50<55:01:18,  7.11s/it]
  1%|          | 219/28080 [25:58<55:06:58,  7.12s/it]
                                                      
{'loss': 0.9324, 'learning_rate': 0.0001298932384341637, 'epoch': 0.09}

  1%|          | 219/28080 [25:58<55:06:58,  7.12s/it]
  1%|          | 220/28080 [26:05<54:53:41,  7.09s/it]
                                                      
{'loss': 0.9257, 'learning_rate': 0.00013048635824436535, 'epoch': 0.09}

  1%|          | 220/28080 [26:05<54:53:41,  7.09s/it]
  1%|          | 221/28080 [26:12<55:07:53,  7.12s/it]
                                                      
{'loss': 0.922, 'learning_rate': 0.00013107947805456703, 'epoch': 0.09}

  1%|          | 221/28080 [26:12<55:07:53,  7.12s/it]
  1%|          | 222/28080 [26:19<55:10:45,  7.13s/it]
                                                      
{'loss': 0.9266, 'learning_rate': 0.00013167259786476867, 'epoch': 0.09}

  1%|          | 222/28080 [26:19<55:10:45,  7.13s/it]
  1%|          | 223/28080 [26:26<54:50:44,  7.09s/it]
                                                      
{'loss': 0.9216, 'learning_rate': 0.00013226571767497035, 'epoch': 0.1}

  1%|          | 223/28080 [26:26<54:50:44,  7.09s/it]
  1%|          | 224/28080 [26:33<54:53:47,  7.09s/it]
                                                      
{'loss': 0.9267, 'learning_rate': 0.000132858837485172, 'epoch': 0.1}

  1%|          | 224/28080 [26:33<54:53:47,  7.09s/it]
  1%|          | 225/28080 [26:40<54:52:08,  7.09s/it]
                                                      
{'loss': 0.9359, 'learning_rate': 0.00013345195729537365, 'epoch': 0.1}

  1%|          | 225/28080 [26:40<54:52:08,  7.09s/it]
  1%|          | 226/28080 [26:47<54:45:43,  7.08s/it]
                                                      
{'loss': 0.9314, 'learning_rate': 0.00013404507710557535, 'epoch': 0.1}

  1%|          | 226/28080 [26:47<54:45:43,  7.08s/it]
  1%|          | 227/28080 [26:54<54:51:52,  7.09s/it]
                                                      
{'loss': 0.9174, 'learning_rate': 0.000134638196915777, 'epoch': 0.1}

  1%|          | 227/28080 [26:54<54:51:52,  7.09s/it]
  1%|          | 228/28080 [27:02<55:12:04,  7.14s/it]
                                                      
{'loss': 0.9129, 'learning_rate': 0.00013523131672597865, 'epoch': 0.1}

  1%|          | 228/28080 [27:02<55:12:04,  7.14s/it]
  1%|          | 229/28080 [27:09<55:17:04,  7.15s/it]
                                                      
{'loss': 0.9315, 'learning_rate': 0.00013582443653618032, 'epoch': 0.1}

  1%|          | 229/28080 [27:09<55:17:04,  7.15s/it]
  1%|          | 230/28080 [27:16<55:00:02,  7.11s/it]
                                                      
{'loss': 0.9184, 'learning_rate': 0.00013641755634638197, 'epoch': 0.1}

  1%|          | 230/28080 [27:16<55:00:02,  7.11s/it]
  1%|          | 231/28080 [27:23<55:08:49,  7.13s/it]
                                                      
{'loss': 0.9147, 'learning_rate': 0.00013701067615658362, 'epoch': 0.1}

  1%|          | 231/28080 [27:23<55:08:49,  7.13s/it]
  1%|          | 232/28080 [27:30<55:06:31,  7.12s/it]
                                                      
{'loss': 0.9246, 'learning_rate': 0.0001376037959667853, 'epoch': 0.1}

  1%|          | 232/28080 [27:30<55:06:31,  7.12s/it]
  1%|          | 233/28080 [27:37<54:58:07,  7.11s/it]
                                                      
{'loss': 0.9162, 'learning_rate': 0.00013819691577698695, 'epoch': 0.1}

  1%|          | 233/28080 [27:37<54:58:07,  7.11s/it]
  1%|          | 234/28080 [27:44<54:56:55,  7.10s/it]
                                                      
{'loss': 0.9219, 'learning_rate': 0.00013879003558718862, 'epoch': 0.1}

  1%|          | 234/28080 [27:44<54:56:55,  7.10s/it]
  1%|          | 235/28080 [27:51<55:04:36,  7.12s/it]
                                                      
{'loss': 0.9009, 'learning_rate': 0.00013938315539739027, 'epoch': 0.1}

  1%|          | 235/28080 [27:51<55:04:36,  7.12s/it]
  1%|          | 236/28080 [27:58<55:04:56,  7.12s/it]
                                                      
{'loss': 0.9028, 'learning_rate': 0.00013997627520759192, 'epoch': 0.1}

  1%|          | 236/28080 [27:58<55:04:56,  7.12s/it]
  1%|          | 237/28080 [28:06<55:06:28,  7.13s/it]
                                                      
{'loss': 0.9237, 'learning_rate': 0.0001405693950177936, 'epoch': 0.1}

  1%|          | 237/28080 [28:06<55:06:28,  7.13s/it]
  1%|          | 238/28080 [28:13<55:02:39,  7.12s/it]
                                                      
{'loss': 0.9057, 'learning_rate': 0.00014116251482799525, 'epoch': 0.1}

  1%|          | 238/28080 [28:13<55:02:39,  7.12s/it]
  1%|          | 239/28080 [28:20<55:08:28,  7.13s/it]
                                                      
{'loss': 0.9206, 'learning_rate': 0.0001417556346381969, 'epoch': 0.1}

  1%|          | 239/28080 [28:20<55:08:28,  7.13s/it]
  1%|          | 240/28080 [28:27<55:03:38,  7.12s/it]
                                                      
{'loss': 0.8951, 'learning_rate': 0.0001423487544483986, 'epoch': 0.1}

  1%|          | 240/28080 [28:27<55:03:38,  7.12s/it]
  1%|          | 241/28080 [28:34<55:07:45,  7.13s/it]
                                                      
{'loss': 0.9086, 'learning_rate': 0.00014294187425860025, 'epoch': 0.1}

  1%|          | 241/28080 [28:34<55:07:45,  7.13s/it]
  1%|          | 242/28080 [28:41<55:03:15,  7.12s/it]
                                                      
{'loss': 0.9004, 'learning_rate': 0.00014353499406880192, 'epoch': 0.1}

  1%|          | 242/28080 [28:41<55:03:15,  7.12s/it]
  1%|          | 243/28080 [28:48<55:09:51,  7.13s/it]
                                                      
{'loss': 0.895, 'learning_rate': 0.00014412811387900357, 'epoch': 0.1}

  1%|          | 243/28080 [28:48<55:09:51,  7.13s/it]
  1%|          | 244/28080 [28:55<54:57:13,  7.11s/it]
                                                      
{'loss': 0.9059, 'learning_rate': 0.00014472123368920522, 'epoch': 0.1}

  1%|          | 244/28080 [28:55<54:57:13,  7.11s/it]
  1%|          | 245/28080 [29:03<54:57:20,  7.11s/it]
                                                      
{'loss': 0.9212, 'learning_rate': 0.0001453143534994069, 'epoch': 0.1}

  1%|          | 245/28080 [29:03<54:57:20,  7.11s/it]
  1%|          | 246/28080 [29:10<54:57:09,  7.11s/it]
                                                      
{'loss': 0.9053, 'learning_rate': 0.00014590747330960854, 'epoch': 0.11}

  1%|          | 246/28080 [29:10<54:57:09,  7.11s/it]
  1%|          | 247/28080 [29:17<54:55:14,  7.10s/it]
                                                      
{'loss': 0.9029, 'learning_rate': 0.0001465005931198102, 'epoch': 0.11}

  1%|          | 247/28080 [29:17<54:55:14,  7.10s/it]
  1%|          | 248/28080 [29:24<54:58:13,  7.11s/it]
                                                      
{'loss': 0.9, 'learning_rate': 0.00014709371293001187, 'epoch': 0.11}

  1%|          | 248/28080 [29:24<54:58:13,  7.11s/it]
  1%|          | 249/28080 [29:31<54:50:50,  7.09s/it]
                                                      
{'loss': 0.918, 'learning_rate': 0.00014768683274021352, 'epoch': 0.11}

  1%|          | 249/28080 [29:31<54:50:50,  7.09s/it]
  1%|          | 250/28080 [29:38<54:56:49,  7.11s/it]
                                                      
{'loss': 0.9139, 'learning_rate': 0.0001482799525504152, 'epoch': 0.11}

  1%|          | 250/28080 [29:38<54:56:49,  7.11s/it]
  1%|          | 251/28080 [29:45<55:03:26,  7.12s/it]
                                                      
{'loss': 0.9074, 'learning_rate': 0.00014887307236061684, 'epoch': 0.11}

  1%|          | 251/28080 [29:45<55:03:26,  7.12s/it]
  1%|          | 252/28080 [29:52<54:46:53,  7.09s/it]
                                                      
{'loss': 0.9119, 'learning_rate': 0.0001494661921708185, 'epoch': 0.11}

  1%|          | 252/28080 [29:52<54:46:53,  7.09s/it]
  1%|          | 253/28080 [29:59<54:45:00,  7.08s/it]
                                                      
{'loss': 0.9123, 'learning_rate': 0.00015005931198102017, 'epoch': 0.11}

  1%|          | 253/28080 [29:59<54:45:00,  7.08s/it]
  1%|          | 254/28080 [30:06<54:45:05,  7.08s/it]
                                                      
{'loss': 0.9109, 'learning_rate': 0.00015065243179122182, 'epoch': 0.11}

  1%|          | 254/28080 [30:06<54:45:05,  7.08s/it]
  1%|          | 255/28080 [30:14<55:07:29,  7.13s/it]
                                                      
{'loss': 0.9055, 'learning_rate': 0.0001512455516014235, 'epoch': 0.11}

  1%|          | 255/28080 [30:14<55:07:29,  7.13s/it]
  1%|          | 256/28080 [30:21<55:01:14,  7.12s/it]
                                                      
{'loss': 0.9028, 'learning_rate': 0.00015183867141162517, 'epoch': 0.11}

  1%|          | 256/28080 [30:21<55:01:14,  7.12s/it]
  1%|          | 257/28080 [30:28<54:56:34,  7.11s/it]
                                                      
{'loss': 0.9014, 'learning_rate': 0.00015243179122182682, 'epoch': 0.11}

  1%|          | 257/28080 [30:28<54:56:34,  7.11s/it]
  1%|          | 258/28080 [30:35<54:53:56,  7.10s/it]
                                                      
{'loss': 0.9061, 'learning_rate': 0.00015302491103202847, 'epoch': 0.11}

  1%|          | 258/28080 [30:35<54:53:56,  7.10s/it]
  1%|          | 259/28080 [30:42<54:57:09,  7.11s/it]
                                                      
{'loss': 0.908, 'learning_rate': 0.00015361803084223014, 'epoch': 0.11}

  1%|          | 259/28080 [30:42<54:57:09,  7.11s/it]
  1%|          | 260/28080 [30:49<54:50:29,  7.10s/it]
                                                      
{'loss': 0.9027, 'learning_rate': 0.0001542111506524318, 'epoch': 0.11}

  1%|          | 260/28080 [30:49<54:50:29,  7.10s/it]
  1%|          | 261/28080 [30:56<54:55:02,  7.11s/it]
                                                      
{'loss': 0.9074, 'learning_rate': 0.00015480427046263347, 'epoch': 0.11}

  1%|          | 261/28080 [30:56<54:55:02,  7.11s/it]
  1%|          | 262/28080 [31:03<55:06:23,  7.13s/it]
                                                      
{'loss': 0.8977, 'learning_rate': 0.00015539739027283512, 'epoch': 0.11}

  1%|          | 262/28080 [31:03<55:06:23,  7.13s/it]
  1%|          | 263/28080 [31:10<54:46:12,  7.09s/it]
                                                      
{'loss': 0.9137, 'learning_rate': 0.00015599051008303676, 'epoch': 0.11}

  1%|          | 263/28080 [31:10<54:46:12,  7.09s/it]
  1%|          | 264/28080 [31:17<54:36:46,  7.07s/it]
                                                      
{'loss': 0.8969, 'learning_rate': 0.00015658362989323844, 'epoch': 0.11}

  1%|          | 264/28080 [31:17<54:36:46,  7.07s/it]
  1%|          | 265/28080 [31:25<54:48:11,  7.09s/it]
                                                      
{'loss': 0.8835, 'learning_rate': 0.0001571767497034401, 'epoch': 0.11}

  1%|          | 265/28080 [31:25<54:48:11,  7.09s/it]
  1%|          | 266/28080 [31:32<54:51:11,  7.10s/it]
                                                      
{'loss': 0.889, 'learning_rate': 0.00015776986951364174, 'epoch': 0.11}

  1%|          | 266/28080 [31:32<54:51:11,  7.10s/it]
  1%|          | 267/28080 [31:39<54:39:03,  7.07s/it]
                                                      
{'loss': 0.8874, 'learning_rate': 0.00015836298932384341, 'epoch': 0.11}

  1%|          | 267/28080 [31:39<54:39:03,  7.07s/it]
  1%|          | 268/28080 [31:46<54:50:47,  7.10s/it]
                                                      
{'loss': 0.9148, 'learning_rate': 0.00015895610913404506, 'epoch': 0.11}

  1%|          | 268/28080 [31:46<54:50:47,  7.10s/it]
  1%|          | 269/28080 [31:53<54:59:19,  7.12s/it]
                                                      
{'loss': 0.9208, 'learning_rate': 0.00015954922894424677, 'epoch': 0.11}

  1%|          | 269/28080 [31:53<54:59:19,  7.12s/it]
  1%|          | 270/28080 [32:00<54:58:41,  7.12s/it]
                                                      
{'loss': 0.9001, 'learning_rate': 0.00016014234875444842, 'epoch': 0.12}

  1%|          | 270/28080 [32:00<54:58:41,  7.12s/it]
  1%|          | 271/28080 [32:07<54:55:46,  7.11s/it]
                                                      
{'loss': 0.8869, 'learning_rate': 0.00016073546856465006, 'epoch': 0.12}

  1%|          | 271/28080 [32:07<54:55:46,  7.11s/it]
  1%|          | 272/28080 [32:14<54:50:11,  7.10s/it]
                                                      
{'loss': 0.8968, 'learning_rate': 0.00016132858837485174, 'epoch': 0.12}

  1%|          | 272/28080 [32:14<54:50:11,  7.10s/it]
  1%|          | 273/28080 [32:21<54:49:45,  7.10s/it]
                                                      
{'loss': 0.9023, 'learning_rate': 0.0001619217081850534, 'epoch': 0.12}

  1%|          | 273/28080 [32:21<54:49:45,  7.10s/it]
  1%|          | 274/28080 [32:28<54:51:56,  7.10s/it]
                                                      
{'loss': 0.8877, 'learning_rate': 0.00016251482799525504, 'epoch': 0.12}

  1%|          | 274/28080 [32:28<54:51:56,  7.10s/it]
  1%|          | 275/28080 [32:36<54:50:49,  7.10s/it]
                                                      
{'loss': 0.8859, 'learning_rate': 0.00016310794780545671, 'epoch': 0.12}

  1%|          | 275/28080 [32:36<54:50:49,  7.10s/it]
  1%|          | 276/28080 [32:43<54:42:25,  7.08s/it]
                                                      
{'loss': 0.8992, 'learning_rate': 0.00016370106761565836, 'epoch': 0.12}

  1%|          | 276/28080 [32:43<54:42:25,  7.08s/it]
  1%|          | 277/28080 [32:50<54:50:33,  7.10s/it]
                                                      
{'loss': 0.8883, 'learning_rate': 0.00016429418742586004, 'epoch': 0.12}

  1%|          | 277/28080 [32:50<54:50:33,  7.10s/it]
  1%|          | 278/28080 [32:57<54:47:49,  7.10s/it]
                                                      
{'loss': 0.8972, 'learning_rate': 0.0001648873072360617, 'epoch': 0.12}

  1%|          | 278/28080 [32:57<54:47:49,  7.10s/it]
  1%|          | 279/28080 [33:04<54:48:04,  7.10s/it]
                                                      
{'loss': 0.887, 'learning_rate': 0.00016548042704626334, 'epoch': 0.12}

  1%|          | 279/28080 [33:04<54:48:04,  7.10s/it]
  1%|          | 280/28080 [33:11<54:24:06,  7.04s/it]
                                                      
{'loss': 0.9129, 'learning_rate': 0.000166073546856465, 'epoch': 0.12}

  1%|          | 280/28080 [33:11<54:24:06,  7.04s/it]
  1%|          | 281/28080 [33:18<54:31:52,  7.06s/it]
                                                      
{'loss': 0.9035, 'learning_rate': 0.00016666666666666666, 'epoch': 0.12}

  1%|          | 281/28080 [33:18<54:31:52,  7.06s/it]
  1%|          | 282/28080 [33:25<54:28:41,  7.06s/it]
                                                      
{'loss': 0.8952, 'learning_rate': 0.0001672597864768683, 'epoch': 0.12}

  1%|          | 282/28080 [33:25<54:28:41,  7.06s/it]
  1%|          | 283/28080 [33:32<54:35:51,  7.07s/it]
                                                      
{'loss': 0.8943, 'learning_rate': 0.00016785290628706999, 'epoch': 0.12}

  1%|          | 283/28080 [33:32<54:35:51,  7.07s/it]
  1%|          | 284/28080 [33:39<54:34:52,  7.07s/it]
                                                      
{'loss': 0.8985, 'learning_rate': 0.00016844602609727166, 'epoch': 0.12}

  1%|          | 284/28080 [33:39<54:34:52,  7.07s/it]
  1%|          | 285/28080 [33:46<54:43:12,  7.09s/it]
                                                      
{'loss': 0.8868, 'learning_rate': 0.0001690391459074733, 'epoch': 0.12}

  1%|          | 285/28080 [33:46<54:43:12,  7.09s/it]
  1%|          | 286/28080 [33:53<54:51:09,  7.10s/it]
                                                      
{'loss': 0.8785, 'learning_rate': 0.000169632265717675, 'epoch': 0.12}

  1%|          | 286/28080 [33:53<54:51:09,  7.10s/it]
  1%|          | 287/28080 [34:01<54:53:06,  7.11s/it]
                                                      
{'loss': 0.8795, 'learning_rate': 0.00017022538552787664, 'epoch': 0.12}

  1%|          | 287/28080 [34:01<54:53:06,  7.11s/it]
  1%|          | 288/28080 [34:08<54:43:54,  7.09s/it]
                                                      
{'loss': 0.8908, 'learning_rate': 0.0001708185053380783, 'epoch': 0.12}

  1%|          | 288/28080 [34:08<54:43:54,  7.09s/it]
  1%|          | 289/28080 [34:15<54:43:42,  7.09s/it]
                                                      
{'loss': 0.8882, 'learning_rate': 0.00017141162514827996, 'epoch': 0.12}

  1%|          | 289/28080 [34:15<54:43:42,  7.09s/it]
  1%|          | 290/28080 [34:22<54:51:10,  7.11s/it]
                                                      
{'loss': 0.8835, 'learning_rate': 0.0001720047449584816, 'epoch': 0.12}

  1%|          | 290/28080 [34:22<54:51:10,  7.11s/it]
  1%|          | 291/28080 [34:29<54:59:56,  7.13s/it]
                                                      
{'loss': 0.8795, 'learning_rate': 0.00017259786476868329, 'epoch': 0.12}

  1%|          | 291/28080 [34:29<54:59:56,  7.13s/it]
  1%|          | 292/28080 [34:36<54:59:27,  7.12s/it]
                                                      
{'loss': 0.8977, 'learning_rate': 0.00017319098457888493, 'epoch': 0.12}

  1%|          | 292/28080 [34:36<54:59:27,  7.12s/it]
  1%|          | 293/28080 [34:43<54:52:51,  7.11s/it]
                                                      
{'loss': 0.8911, 'learning_rate': 0.00017378410438908658, 'epoch': 0.13}

  1%|          | 293/28080 [34:43<54:52:51,  7.11s/it]
  1%|          | 294/28080 [34:50<54:45:54,  7.10s/it]
                                                      
{'loss': 0.8909, 'learning_rate': 0.00017437722419928826, 'epoch': 0.13}

  1%|          | 294/28080 [34:50<54:45:54,  7.10s/it]
  1%|          | 295/28080 [34:57<54:58:36,  7.12s/it]
                                                      
{'loss': 0.8759, 'learning_rate': 0.0001749703440094899, 'epoch': 0.13}

  1%|          | 295/28080 [34:57<54:58:36,  7.12s/it]
  1%|          | 296/28080 [35:05<54:57:21,  7.12s/it]
                                                      
{'loss': 0.8739, 'learning_rate': 0.00017556346381969158, 'epoch': 0.13}

  1%|          | 296/28080 [35:05<54:57:21,  7.12s/it]
  1%|          | 297/28080 [35:12<54:40:15,  7.08s/it]
                                                      
{'loss': 0.8944, 'learning_rate': 0.00017615658362989323, 'epoch': 0.13}

  1%|          | 297/28080 [35:12<54:40:15,  7.08s/it]
  1%|          | 298/28080 [35:19<54:45:28,  7.10s/it]
                                                      
{'loss': 0.8909, 'learning_rate': 0.0001767497034400949, 'epoch': 0.13}

  1%|          | 298/28080 [35:19<54:45:28,  7.10s/it]
  1%|          | 299/28080 [35:26<54:49:23,  7.10s/it]
                                                      
{'loss': 0.8888, 'learning_rate': 0.00017734282325029658, 'epoch': 0.13}

  1%|          | 299/28080 [35:26<54:49:23,  7.10s/it]
  1%|          | 300/28080 [35:33<54:54:38,  7.12s/it]
                                                      
{'loss': 0.8748, 'learning_rate': 0.00017793594306049823, 'epoch': 0.13}

  1%|          | 300/28080 [35:33<54:54:38,  7.12s/it]
  1%|          | 301/28080 [35:40<54:59:52,  7.13s/it]
                                                      
{'loss': 0.8776, 'learning_rate': 0.00017852906287069988, 'epoch': 0.13}

  1%|          | 301/28080 [35:40<54:59:52,  7.13s/it]
  1%|          | 302/28080 [35:47<55:02:31,  7.13s/it]
                                                      
{'loss': 0.8849, 'learning_rate': 0.00017912218268090156, 'epoch': 0.13}

  1%|          | 302/28080 [35:47<55:02:31,  7.13s/it]
  1%|          | 303/28080 [35:54<54:44:14,  7.09s/it]
                                                      
{'loss': 0.8894, 'learning_rate': 0.0001797153024911032, 'epoch': 0.13}

  1%|          | 303/28080 [35:54<54:44:14,  7.09s/it]
  1%|          | 304/28080 [36:01<54:48:40,  7.10s/it]
                                                      
{'loss': 0.8901, 'learning_rate': 0.00018030842230130488, 'epoch': 0.13}

  1%|          | 304/28080 [36:01<54:48:40,  7.10s/it]
  1%|          | 305/28080 [36:09<54:48:17,  7.10s/it]
                                                      
{'loss': 0.8797, 'learning_rate': 0.00018090154211150653, 'epoch': 0.13}

  1%|          | 305/28080 [36:09<54:48:17,  7.10s/it]
  1%|          | 306/28080 [36:16<54:44:52,  7.10s/it]
                                                      
{'loss': 0.8912, 'learning_rate': 0.00018149466192170818, 'epoch': 0.13}

  1%|          | 306/28080 [36:16<54:44:52,  7.10s/it]
  1%|          | 307/28080 [36:23<54:51:34,  7.11s/it]
                                                      
{'loss': 0.8738, 'learning_rate': 0.00018208778173190986, 'epoch': 0.13}

  1%|          | 307/28080 [36:23<54:51:34,  7.11s/it]
  1%|          | 308/28080 [36:30<54:46:52,  7.10s/it]
                                                      
{'loss': 0.8688, 'learning_rate': 0.0001826809015421115, 'epoch': 0.13}

  1%|          | 308/28080 [36:30<54:46:52,  7.10s/it]
  1%|          | 309/28080 [36:37<55:01:07,  7.13s/it]
                                                      
{'loss': 0.8828, 'learning_rate': 0.00018327402135231315, 'epoch': 0.13}

  1%|          | 309/28080 [36:37<55:01:07,  7.13s/it]
  1%|          | 310/28080 [36:44<55:03:42,  7.14s/it]
                                                      
{'loss': 0.8777, 'learning_rate': 0.00018386714116251483, 'epoch': 0.13}

  1%|          | 310/28080 [36:44<55:03:42,  7.14s/it]
  1%|          | 311/28080 [36:51<54:45:31,  7.10s/it]
                                                      
{'loss': 0.8966, 'learning_rate': 0.00018446026097271648, 'epoch': 0.13}

  1%|          | 311/28080 [36:51<54:45:31,  7.10s/it]
  1%|          | 312/28080 [36:58<54:58:03,  7.13s/it]
                                                      
{'loss': 0.877, 'learning_rate': 0.00018505338078291813, 'epoch': 0.13}

  1%|          | 312/28080 [36:58<54:58:03,  7.13s/it]
  1%|          | 313/28080 [37:06<55:19:03,  7.17s/it]
                                                      
{'loss': 0.875, 'learning_rate': 0.00018564650059311983, 'epoch': 0.13}

  1%|          | 313/28080 [37:06<55:19:03,  7.17s/it]
  1%|          | 314/28080 [37:13<54:53:22,  7.12s/it]
                                                      
{'loss': 0.8768, 'learning_rate': 0.00018623962040332148, 'epoch': 0.13}

  1%|          | 314/28080 [37:13<54:53:22,  7.12s/it]
  1%|          | 315/28080 [37:20<54:54:15,  7.12s/it]
                                                      
{'loss': 0.8814, 'learning_rate': 0.00018683274021352316, 'epoch': 0.13}

  1%|          | 315/28080 [37:20<54:54:15,  7.12s/it]
  1%|          | 316/28080 [37:27<54:53:45,  7.12s/it]
                                                      
{'loss': 0.8821, 'learning_rate': 0.0001874258600237248, 'epoch': 0.13}

  1%|          | 316/28080 [37:27<54:53:45,  7.12s/it]
  1%|          | 317/28080 [37:34<54:59:55,  7.13s/it]
                                                      
{'loss': 0.8519, 'learning_rate': 0.00018801897983392645, 'epoch': 0.14}

  1%|          | 317/28080 [37:34<54:59:55,  7.13s/it]
  1%|          | 318/28080 [37:41<55:07:03,  7.15s/it]
                                                      
{'loss': 0.8682, 'learning_rate': 0.00018861209964412813, 'epoch': 0.14}

  1%|          | 318/28080 [37:41<55:07:03,  7.15s/it]
  1%|          | 319/28080 [37:48<54:51:50,  7.11s/it]
                                                      
{'loss': 0.8634, 'learning_rate': 0.00018920521945432978, 'epoch': 0.14}

  1%|          | 319/28080 [37:48<54:51:50,  7.11s/it]
  1%|          | 320/28080 [37:55<54:56:02,  7.12s/it]
                                                      
{'loss': 0.8649, 'learning_rate': 0.00018979833926453143, 'epoch': 0.14}

  1%|          | 320/28080 [37:55<54:56:02,  7.12s/it]
  1%|          | 321/28080 [38:02<54:45:40,  7.10s/it]
                                                      
{'loss': 0.8696, 'learning_rate': 0.0001903914590747331, 'epoch': 0.14}

  1%|          | 321/28080 [38:02<54:45:40,  7.10s/it]
  1%|          | 322/28080 [38:09<54:32:11,  7.07s/it]
                                                      
{'loss': 0.8745, 'learning_rate': 0.00019098457888493475, 'epoch': 0.14}

  1%|          | 322/28080 [38:09<54:32:11,  7.07s/it]
  1%|          | 323/28080 [38:16<54:18:32,  7.04s/it]
                                                      
{'loss': 0.888, 'learning_rate': 0.00019157769869513643, 'epoch': 0.14}

  1%|          | 323/28080 [38:16<54:18:32,  7.04s/it]
  1%|          | 324/28080 [38:24<54:28:53,  7.07s/it]
                                                      
{'loss': 0.8805, 'learning_rate': 0.00019217081850533808, 'epoch': 0.14}

  1%|          | 324/28080 [38:24<54:28:53,  7.07s/it]
  1%|          | 325/28080 [38:31<54:46:51,  7.11s/it]
                                                      
{'loss': 0.8854, 'learning_rate': 0.00019276393831553973, 'epoch': 0.14}

  1%|          | 325/28080 [38:31<54:46:51,  7.11s/it]
  1%|          | 326/28080 [38:38<54:47:44,  7.11s/it]
                                                      
{'loss': 0.8513, 'learning_rate': 0.0001933570581257414, 'epoch': 0.14}

  1%|          | 326/28080 [38:38<54:47:44,  7.11s/it]
  1%|          | 327/28080 [38:45<54:53:59,  7.12s/it]
                                                      
{'loss': 0.8677, 'learning_rate': 0.00019395017793594305, 'epoch': 0.14}

  1%|          | 327/28080 [38:45<54:53:59,  7.12s/it]
  1%|          | 328/28080 [38:52<54:55:56,  7.13s/it]
                                                      
{'loss': 0.8791, 'learning_rate': 0.00019454329774614473, 'epoch': 0.14}

  1%|          | 328/28080 [38:52<54:55:56,  7.13s/it]
  1%|          | 329/28080 [38:59<54:54:25,  7.12s/it]
                                                      
{'loss': 0.8795, 'learning_rate': 0.0001951364175563464, 'epoch': 0.14}

  1%|          | 329/28080 [38:59<54:54:25,  7.12s/it]
  1%|          | 330/28080 [39:06<54:45:10,  7.10s/it]
                                                      
{'loss': 0.8773, 'learning_rate': 0.00019572953736654805, 'epoch': 0.14}

  1%|          | 330/28080 [39:06<54:45:10,  7.10s/it]
  1%|          | 331/28080 [39:13<54:47:05,  7.11s/it]
                                                      
{'loss': 0.8654, 'learning_rate': 0.00019632265717674973, 'epoch': 0.14}

  1%|          | 331/28080 [39:13<54:47:05,  7.11s/it]
  1%|          | 332/28080 [39:21<54:40:16,  7.09s/it]
                                                      
{'loss': 0.8553, 'learning_rate': 0.00019691577698695138, 'epoch': 0.14}

  1%|          | 332/28080 [39:21<54:40:16,  7.09s/it]
  1%|          | 333/28080 [39:28<54:42:57,  7.10s/it]
                                                      
{'loss': 0.8615, 'learning_rate': 0.00019750889679715302, 'epoch': 0.14}

  1%|          | 333/28080 [39:28<54:42:57,  7.10s/it]
  1%|          | 334/28080 [39:35<54:40:37,  7.09s/it]
                                                      
{'loss': 0.8762, 'learning_rate': 0.0001981020166073547, 'epoch': 0.14}

  1%|          | 334/28080 [39:35<54:40:37,  7.09s/it]
  1%|          | 335/28080 [39:42<54:29:28,  7.07s/it]
                                                      
{'loss': 0.8698, 'learning_rate': 0.00019869513641755635, 'epoch': 0.14}

  1%|          | 335/28080 [39:42<54:29:28,  7.07s/it]
  1%|          | 336/28080 [39:49<54:11:46,  7.03s/it]
                                                      
{'loss': 0.8765, 'learning_rate': 0.000199288256227758, 'epoch': 0.14}

  1%|          | 336/28080 [39:49<54:11:46,  7.03s/it]
  1%|          | 337/28080 [39:56<54:20:14,  7.05s/it]
                                                      
{'loss': 0.8621, 'learning_rate': 0.00019988137603795967, 'epoch': 0.14}

  1%|          | 337/28080 [39:56<54:20:14,  7.05s/it]
  1%|          | 338/28080 [40:03<54:33:40,  7.08s/it]
                                                      
{'loss': 0.8811, 'learning_rate': 0.00020047449584816132, 'epoch': 0.14}

  1%|          | 338/28080 [40:03<54:33:40,  7.08s/it]
  1%|          | 339/28080 [40:10<54:38:38,  7.09s/it]
                                                      
{'loss': 0.8546, 'learning_rate': 0.00020106761565836297, 'epoch': 0.14}

  1%|          | 339/28080 [40:10<54:38:38,  7.09s/it]
  1%|          | 340/28080 [40:17<54:47:12,  7.11s/it]
                                                      
{'loss': 0.8521, 'learning_rate': 0.00020166073546856465, 'epoch': 0.15}

  1%|          | 340/28080 [40:17<54:47:12,  7.11s/it]
  1%|          | 341/28080 [40:24<54:27:07,  7.07s/it]
                                                      
{'loss': 0.8839, 'learning_rate': 0.0002022538552787663, 'epoch': 0.15}

  1%|          | 341/28080 [40:24<54:27:07,  7.07s/it]
  1%|          | 342/28080 [40:31<54:41:04,  7.10s/it]
                                                      
{'loss': 0.8896, 'learning_rate': 0.000202846975088968, 'epoch': 0.15}

  1%|          | 342/28080 [40:31<54:41:04,  7.10s/it]
  1%|          | 343/28080 [40:38<54:36:06,  7.09s/it]
                                                      
{'loss': 0.8521, 'learning_rate': 0.00020344009489916965, 'epoch': 0.15}

  1%|          | 343/28080 [40:38<54:36:06,  7.09s/it]
  1%|          | 344/28080 [40:45<54:34:10,  7.08s/it]
                                                      
{'loss': 0.8811, 'learning_rate': 0.0002040332147093713, 'epoch': 0.15}

  1%|          | 344/28080 [40:45<54:34:10,  7.08s/it]
  1%|          | 345/28080 [40:53<54:36:59,  7.09s/it]
                                                      
{'loss': 0.8563, 'learning_rate': 0.00020462633451957297, 'epoch': 0.15}

  1%|          | 345/28080 [40:53<54:36:59,  7.09s/it]
  1%|          | 346/28080 [41:00<54:42:59,  7.10s/it]
                                                      
{'loss': 0.8564, 'learning_rate': 0.00020521945432977462, 'epoch': 0.15}

  1%|          | 346/28080 [41:00<54:42:59,  7.10s/it]
  1%|          | 347/28080 [41:07<54:51:37,  7.12s/it]
                                                      
{'loss': 0.8699, 'learning_rate': 0.00020581257413997627, 'epoch': 0.15}

  1%|          | 347/28080 [41:07<54:51:37,  7.12s/it]
  1%|          | 348/28080 [41:14<55:02:44,  7.15s/it]
                                                      
{'loss': 0.8486, 'learning_rate': 0.00020640569395017795, 'epoch': 0.15}

  1%|          | 348/28080 [41:14<55:02:44,  7.15s/it]
  1%|          | 349/28080 [41:21<55:04:26,  7.15s/it]
                                                      
{'loss': 0.8471, 'learning_rate': 0.0002069988137603796, 'epoch': 0.15}

  1%|          | 349/28080 [41:21<55:04:26,  7.15s/it]
  1%|          | 350/28080 [41:28<54:49:18,  7.12s/it]
                                                      
{'loss': 0.8694, 'learning_rate': 0.00020759193357058127, 'epoch': 0.15}

  1%|          | 350/28080 [41:28<54:49:18,  7.12s/it]
  1%|▏         | 351/28080 [41:35<54:47:03,  7.11s/it]
                                                      
{'loss': 0.8635, 'learning_rate': 0.00020818505338078292, 'epoch': 0.15}

  1%|▏         | 351/28080 [41:35<54:47:03,  7.11s/it]
  1%|▏         | 352/28080 [41:42<54:45:32,  7.11s/it]
                                                      
{'loss': 0.859, 'learning_rate': 0.00020877817319098457, 'epoch': 0.15}

  1%|▏         | 352/28080 [41:42<54:45:32,  7.11s/it]
  1%|▏         | 353/28080 [41:50<54:44:05,  7.11s/it]
                                                      
{'loss': 0.8667, 'learning_rate': 0.00020937129300118625, 'epoch': 0.15}

  1%|▏         | 353/28080 [41:50<54:44:05,  7.11s/it]
  1%|▏         | 354/28080 [41:57<54:54:26,  7.13s/it]
                                                      
{'loss': 0.8588, 'learning_rate': 0.0002099644128113879, 'epoch': 0.15}

  1%|▏         | 354/28080 [41:57<54:54:26,  7.13s/it]
  1%|▏         | 355/28080 [42:04<54:44:35,  7.11s/it]
                                                      
{'loss': 0.8551, 'learning_rate': 0.00021055753262158954, 'epoch': 0.15}

  1%|▏         | 355/28080 [42:04<54:44:35,  7.11s/it]
  1%|▏         | 356/28080 [42:11<54:49:22,  7.12s/it]
                                                      
{'loss': 0.8654, 'learning_rate': 0.00021115065243179122, 'epoch': 0.15}

  1%|▏         | 356/28080 [42:11<54:49:22,  7.12s/it]
  1%|▏         | 357/28080 [42:18<54:33:48,  7.09s/it]
                                                      
{'loss': 0.8653, 'learning_rate': 0.0002117437722419929, 'epoch': 0.15}

  1%|▏         | 357/28080 [42:18<54:33:48,  7.09s/it]
  1%|▏         | 358/28080 [42:25<54:56:20,  7.13s/it]
                                                      
{'loss': 0.8514, 'learning_rate': 0.00021233689205219457, 'epoch': 0.15}

  1%|▏         | 358/28080 [42:25<54:56:20,  7.13s/it]
  1%|▏         | 359/28080 [42:32<54:46:33,  7.11s/it]
                                                      
{'loss': 0.8609, 'learning_rate': 0.00021293001186239622, 'epoch': 0.15}

  1%|▏         | 359/28080 [42:32<54:46:33,  7.11s/it]
  1%|▏         | 360/28080 [42:39<54:45:58,  7.11s/it]
                                                      
{'loss': 0.8578, 'learning_rate': 0.00021352313167259787, 'epoch': 0.15}

  1%|▏         | 360/28080 [42:39<54:45:58,  7.11s/it]
  1%|▏         | 361/28080 [42:47<54:58:29,  7.14s/it]
                                                      
{'loss': 0.856, 'learning_rate': 0.00021411625148279954, 'epoch': 0.15}

  1%|▏         | 361/28080 [42:47<54:58:29,  7.14s/it]
  1%|▏         | 362/28080 [42:54<54:50:31,  7.12s/it]
                                                      
{'loss': 0.8421, 'learning_rate': 0.0002147093712930012, 'epoch': 0.15}

  1%|▏         | 362/28080 [42:54<54:50:31,  7.12s/it]
  1%|▏         | 363/28080 [43:01<54:49:39,  7.12s/it]
                                                      
{'loss': 0.8416, 'learning_rate': 0.00021530249110320284, 'epoch': 0.16}

  1%|▏         | 363/28080 [43:01<54:49:39,  7.12s/it]
  1%|▏         | 364/28080 [43:08<54:47:26,  7.12s/it]
                                                      
{'loss': 0.8597, 'learning_rate': 0.00021589561091340452, 'epoch': 0.16}

  1%|▏         | 364/28080 [43:08<54:47:26,  7.12s/it]
  1%|▏         | 365/28080 [43:15<54:39:13,  7.10s/it]
                                                      
{'loss': 0.8688, 'learning_rate': 0.00021648873072360617, 'epoch': 0.16}

  1%|▏         | 365/28080 [43:15<54:39:13,  7.10s/it]
  1%|▏         | 366/28080 [43:22<54:42:46,  7.11s/it]
                                                      
{'loss': 0.8385, 'learning_rate': 0.00021708185053380782, 'epoch': 0.16}

  1%|▏         | 366/28080 [43:22<54:42:46,  7.11s/it]
  1%|▏         | 367/28080 [43:29<54:43:27,  7.11s/it]
                                                      
{'loss': 0.8586, 'learning_rate': 0.0002176749703440095, 'epoch': 0.16}

  1%|▏         | 367/28080 [43:29<54:43:27,  7.11s/it]
  1%|▏         | 368/28080 [43:36<54:36:22,  7.09s/it]
                                                      
{'loss': 0.833, 'learning_rate': 0.00021826809015421114, 'epoch': 0.16}

  1%|▏         | 368/28080 [43:36<54:36:22,  7.09s/it]
  1%|▏         | 369/28080 [43:43<54:36:19,  7.09s/it]
                                                      
{'loss': 0.8537, 'learning_rate': 0.00021886120996441282, 'epoch': 0.16}

  1%|▏         | 369/28080 [43:43<54:36:19,  7.09s/it]
  1%|▏         | 370/28080 [43:50<54:28:58,  7.08s/it]
                                                      
{'loss': 0.8532, 'learning_rate': 0.00021945432977461447, 'epoch': 0.16}

  1%|▏         | 370/28080 [43:50<54:28:58,  7.08s/it]
  1%|▏         | 371/28080 [43:58<54:37:38,  7.10s/it]
                                                      
{'loss': 0.8469, 'learning_rate': 0.00022004744958481614, 'epoch': 0.16}

  1%|▏         | 371/28080 [43:58<54:37:38,  7.10s/it]
  1%|▏         | 372/28080 [44:05<54:38:49,  7.10s/it]
                                                      
{'loss': 0.8623, 'learning_rate': 0.00022064056939501782, 'epoch': 0.16}

  1%|▏         | 372/28080 [44:05<54:38:49,  7.10s/it]
  1%|▏         | 373/28080 [44:12<54:31:09,  7.08s/it]
                                                      
{'loss': 0.8571, 'learning_rate': 0.00022123368920521947, 'epoch': 0.16}

  1%|▏         | 373/28080 [44:12<54:31:09,  7.08s/it]
  1%|▏         | 374/28080 [44:19<54:24:36,  7.07s/it]
                                                      
{'loss': 0.8482, 'learning_rate': 0.00022182680901542112, 'epoch': 0.16}

  1%|▏         | 374/28080 [44:19<54:24:36,  7.07s/it]
  1%|▏         | 375/28080 [44:26<54:29:44,  7.08s/it]
                                                      
{'loss': 0.8446, 'learning_rate': 0.0002224199288256228, 'epoch': 0.16}

  1%|▏         | 375/28080 [44:26<54:29:44,  7.08s/it]
  1%|▏         | 376/28080 [44:33<54:37:27,  7.10s/it]
                                                      
{'loss': 0.8549, 'learning_rate': 0.00022301304863582444, 'epoch': 0.16}

  1%|▏         | 376/28080 [44:33<54:37:27,  7.10s/it]
  1%|▏         | 377/28080 [44:40<54:26:21,  7.07s/it]
                                                      
{'loss': 0.8387, 'learning_rate': 0.00022360616844602612, 'epoch': 0.16}

  1%|▏         | 377/28080 [44:40<54:26:21,  7.07s/it]
  1%|▏         | 378/28080 [44:47<54:24:17,  7.07s/it]
                                                      
{'loss': 0.8527, 'learning_rate': 0.00022419928825622777, 'epoch': 0.16}

  1%|▏         | 378/28080 [44:47<54:24:17,  7.07s/it]
  1%|▏         | 379/28080 [44:54<54:19:13,  7.06s/it]
                                                      
{'loss': 0.837, 'learning_rate': 0.00022479240806642941, 'epoch': 0.16}

  1%|▏         | 379/28080 [44:54<54:19:13,  7.06s/it]
  1%|▏         | 380/28080 [45:01<54:23:05,  7.07s/it]
                                                      
{'loss': 0.8465, 'learning_rate': 0.0002253855278766311, 'epoch': 0.16}

  1%|▏         | 380/28080 [45:01<54:23:05,  7.07s/it]
  1%|▏         | 381/28080 [45:08<54:34:53,  7.09s/it]
                                                      
{'loss': 0.8474, 'learning_rate': 0.00022597864768683274, 'epoch': 0.16}

  1%|▏         | 381/28080 [45:08<54:34:53,  7.09s/it]
  1%|▏         | 382/28080 [45:15<54:38:44,  7.10s/it]
                                                      
{'loss': 0.8454, 'learning_rate': 0.0002265717674970344, 'epoch': 0.16}

  1%|▏         | 382/28080 [45:15<54:38:44,  7.10s/it]
  1%|▏         | 383/28080 [45:23<54:38:29,  7.10s/it]
                                                      
{'loss': 0.8499, 'learning_rate': 0.00022716488730723606, 'epoch': 0.16}

  1%|▏         | 383/28080 [45:23<54:38:29,  7.10s/it]
  1%|▏         | 384/28080 [45:30<54:56:21,  7.14s/it]
                                                      
{'loss': 0.83, 'learning_rate': 0.0002277580071174377, 'epoch': 0.16}

  1%|▏         | 384/28080 [45:30<54:56:21,  7.14s/it]
  1%|▏         | 385/28080 [45:37<54:49:18,  7.13s/it]
                                                      
{'loss': 0.8489, 'learning_rate': 0.00022835112692763936, 'epoch': 0.16}

  1%|▏         | 385/28080 [45:37<54:49:18,  7.13s/it]
  1%|▏         | 386/28080 [45:44<54:50:41,  7.13s/it]
                                                      
{'loss': 0.8549, 'learning_rate': 0.00022894424673784106, 'epoch': 0.16}

  1%|▏         | 386/28080 [45:44<54:50:41,  7.13s/it]
  1%|▏         | 387/28080 [45:51<54:41:47,  7.11s/it]
                                                      
{'loss': 0.8501, 'learning_rate': 0.0002295373665480427, 'epoch': 0.17}

  1%|▏         | 387/28080 [45:51<54:41:47,  7.11s/it]
  1%|▏         | 388/28080 [45:58<54:37:55,  7.10s/it]
                                                      
{'loss': 0.8431, 'learning_rate': 0.0002301304863582444, 'epoch': 0.17}

  1%|▏         | 388/28080 [45:58<54:37:55,  7.10s/it]
  1%|▏         | 389/28080 [46:05<54:41:39,  7.11s/it]
                                                      
{'loss': 0.8461, 'learning_rate': 0.00023072360616844604, 'epoch': 0.17}

  1%|▏         | 389/28080 [46:05<54:41:39,  7.11s/it]
  1%|▏         | 390/28080 [46:12<54:38:30,  7.10s/it]
                                                      
{'loss': 0.8372, 'learning_rate': 0.0002313167259786477, 'epoch': 0.17}

  1%|▏         | 390/28080 [46:12<54:38:30,  7.10s/it]
  1%|▏         | 391/28080 [46:19<54:37:54,  7.10s/it]
                                                      
{'loss': 0.8333, 'learning_rate': 0.00023190984578884936, 'epoch': 0.17}

  1%|▏         | 391/28080 [46:19<54:37:54,  7.10s/it]
  1%|▏         | 392/28080 [46:27<54:50:23,  7.13s/it]
                                                      
{'loss': 0.8421, 'learning_rate': 0.000232502965599051, 'epoch': 0.17}

  1%|▏         | 392/28080 [46:27<54:50:23,  7.13s/it]
  1%|▏         | 393/28080 [46:34<54:46:45,  7.12s/it]
                                                      
{'loss': 0.8508, 'learning_rate': 0.00023309608540925266, 'epoch': 0.17}

  1%|▏         | 393/28080 [46:34<54:46:45,  7.12s/it]
  1%|▏         | 394/28080 [46:41<54:37:59,  7.10s/it]
                                                      
{'loss': 0.8387, 'learning_rate': 0.00023368920521945434, 'epoch': 0.17}

  1%|▏         | 394/28080 [46:41<54:37:59,  7.10s/it]
  1%|▏         | 395/28080 [46:48<54:33:11,  7.09s/it]
                                                      
{'loss': 0.8515, 'learning_rate': 0.00023428232502965599, 'epoch': 0.17}

  1%|▏         | 395/28080 [46:48<54:33:11,  7.09s/it]
  1%|▏         | 396/28080 [46:55<54:32:24,  7.09s/it]
                                                      
{'loss': 0.8607, 'learning_rate': 0.00023487544483985766, 'epoch': 0.17}

  1%|▏         | 396/28080 [46:55<54:32:24,  7.09s/it]
  1%|▏         | 397/28080 [47:02<54:22:35,  7.07s/it]
                                                      
{'loss': 0.8596, 'learning_rate': 0.0002354685646500593, 'epoch': 0.17}

  1%|▏         | 397/28080 [47:02<54:22:35,  7.07s/it]
  1%|▏         | 398/28080 [47:09<54:30:47,  7.09s/it]
                                                      
{'loss': 0.8324, 'learning_rate': 0.00023606168446026096, 'epoch': 0.17}

  1%|▏         | 398/28080 [47:09<54:30:47,  7.09s/it]
  1%|▏         | 399/28080 [47:16<54:29:29,  7.09s/it]
                                                      
{'loss': 0.8249, 'learning_rate': 0.00023665480427046264, 'epoch': 0.17}

  1%|▏         | 399/28080 [47:16<54:29:29,  7.09s/it]
  1%|▏         | 400/28080 [47:23<54:33:42,  7.10s/it]
                                                      
{'loss': 0.8476, 'learning_rate': 0.0002372479240806643, 'epoch': 0.17}

  1%|▏         | 400/28080 [47:23<54:33:42,  7.10s/it]
  1%|▏         | 401/28080 [47:30<54:26:53,  7.08s/it]
                                                      
{'loss': 0.8492, 'learning_rate': 0.00023784104389086596, 'epoch': 0.17}

  1%|▏         | 401/28080 [47:30<54:26:53,  7.08s/it]
  1%|▏         | 402/28080 [47:38<54:39:44,  7.11s/it]
                                                      
{'loss': 0.8471, 'learning_rate': 0.00023843416370106764, 'epoch': 0.17}

  1%|▏         | 402/28080 [47:38<54:39:44,  7.11s/it]
  1%|▏         | 403/28080 [47:45<54:35:14,  7.10s/it]
                                                      
{'loss': 0.8211, 'learning_rate': 0.00023902728351126928, 'epoch': 0.17}

  1%|▏         | 403/28080 [47:45<54:35:14,  7.10s/it]
  1%|▏         | 404/28080 [47:52<54:35:09,  7.10s/it]
                                                      
{'loss': 0.8357, 'learning_rate': 0.00023962040332147096, 'epoch': 0.17}

  1%|▏         | 404/28080 [47:52<54:35:09,  7.10s/it]
  1%|▏         | 405/28080 [47:59<54:33:52,  7.10s/it]
                                                      
{'loss': 0.8338, 'learning_rate': 0.0002402135231316726, 'epoch': 0.17}

  1%|▏         | 405/28080 [47:59<54:33:52,  7.10s/it]
  1%|▏         | 406/28080 [48:06<54:38:42,  7.11s/it]
                                                      
{'loss': 0.8601, 'learning_rate': 0.00024080664294187426, 'epoch': 0.17}

  1%|▏         | 406/28080 [48:06<54:38:42,  7.11s/it]
  1%|▏         | 407/28080 [48:13<54:53:06,  7.14s/it]
                                                      
{'loss': 0.8484, 'learning_rate': 0.00024139976275207593, 'epoch': 0.17}

  1%|▏         | 407/28080 [48:13<54:53:06,  7.14s/it]
  1%|▏         | 408/28080 [48:20<54:54:25,  7.14s/it]
                                                      
{'loss': 0.8422, 'learning_rate': 0.00024199288256227758, 'epoch': 0.17}

  1%|▏         | 408/28080 [48:20<54:54:25,  7.14s/it]
  1%|▏         | 409/28080 [48:28<55:00:27,  7.16s/it]
                                                      
{'loss': 0.8371, 'learning_rate': 0.00024258600237247923, 'epoch': 0.17}

  1%|▏         | 409/28080 [48:28<55:00:27,  7.16s/it]
  1%|▏         | 410/28080 [48:35<54:52:48,  7.14s/it]
                                                      
{'loss': 0.833, 'learning_rate': 0.0002431791221826809, 'epoch': 0.18}

  1%|▏         | 410/28080 [48:35<54:52:48,  7.14s/it]
  1%|▏         | 411/28080 [48:42<54:37:50,  7.11s/it]
                                                      
{'loss': 0.8535, 'learning_rate': 0.00024377224199288256, 'epoch': 0.18}

  1%|▏         | 411/28080 [48:42<54:37:50,  7.11s/it]
  1%|▏         | 412/28080 [48:49<54:39:47,  7.11s/it]
                                                      
{'loss': 0.8579, 'learning_rate': 0.0002443653618030842, 'epoch': 0.18}

  1%|▏         | 412/28080 [48:49<54:39:47,  7.11s/it]
  1%|▏         | 413/28080 [48:56<54:56:29,  7.15s/it]
                                                      
{'loss': 0.8456, 'learning_rate': 0.00024495848161328585, 'epoch': 0.18}

  1%|▏         | 413/28080 [48:56<54:56:29,  7.15s/it]
  1%|▏         | 414/28080 [49:03<54:58:19,  7.15s/it]
                                                      
{'loss': 0.8385, 'learning_rate': 0.00024555160142348756, 'epoch': 0.18}

  1%|▏         | 414/28080 [49:03<54:58:19,  7.15s/it]
  1%|▏         | 415/28080 [49:10<54:54:38,  7.15s/it]
                                                      
{'loss': 0.8178, 'learning_rate': 0.0002461447212336892, 'epoch': 0.18}

  1%|▏         | 415/28080 [49:10<54:54:38,  7.15s/it]
  1%|▏         | 416/28080 [49:17<54:41:37,  7.12s/it]
                                                      
{'loss': 0.8504, 'learning_rate': 0.00024673784104389086, 'epoch': 0.18}

  1%|▏         | 416/28080 [49:17<54:41:37,  7.12s/it]
  1%|▏         | 417/28080 [49:24<54:43:01,  7.12s/it]
                                                      
{'loss': 0.8534, 'learning_rate': 0.00024733096085409256, 'epoch': 0.18}

  1%|▏         | 417/28080 [49:24<54:43:01,  7.12s/it]
  1%|▏         | 418/28080 [49:32<54:52:11,  7.14s/it]
                                                      
{'loss': 0.8393, 'learning_rate': 0.0002479240806642942, 'epoch': 0.18}

  1%|▏         | 418/28080 [49:32<54:52:11,  7.14s/it]
  1%|▏         | 419/28080 [49:39<54:41:30,  7.12s/it]
                                                      
{'loss': 0.847, 'learning_rate': 0.00024851720047449586, 'epoch': 0.18}

  1%|▏         | 419/28080 [49:39<54:41:30,  7.12s/it]
  1%|▏         | 420/28080 [49:46<54:41:40,  7.12s/it]
                                                      
{'loss': 0.8423, 'learning_rate': 0.0002491103202846975, 'epoch': 0.18}

  1%|▏         | 420/28080 [49:46<54:41:40,  7.12s/it]
  1%|▏         | 421/28080 [49:53<54:31:57,  7.10s/it]
                                                      
{'loss': 0.8366, 'learning_rate': 0.00024970344009489915, 'epoch': 0.18}

  1%|▏         | 421/28080 [49:53<54:31:57,  7.10s/it]
  2%|▏         | 422/28080 [50:00<54:26:32,  7.09s/it]
                                                      
{'loss': 0.8416, 'learning_rate': 0.00025029655990510086, 'epoch': 0.18}

  2%|▏         | 422/28080 [50:00<54:26:32,  7.09s/it]
  2%|▏         | 423/28080 [50:07<54:31:10,  7.10s/it]
                                                      
{'loss': 0.8324, 'learning_rate': 0.0002508896797153025, 'epoch': 0.18}

  2%|▏         | 423/28080 [50:07<54:31:10,  7.10s/it]
  2%|▏         | 424/28080 [50:14<54:22:00,  7.08s/it]
                                                      
{'loss': 0.8562, 'learning_rate': 0.00025148279952550415, 'epoch': 0.18}

  2%|▏         | 424/28080 [50:14<54:22:00,  7.08s/it]
  2%|▏         | 425/28080 [50:21<54:26:15,  7.09s/it]
                                                      
{'loss': 0.8398, 'learning_rate': 0.00025207591933570586, 'epoch': 0.18}

  2%|▏         | 425/28080 [50:21<54:26:15,  7.09s/it]
  2%|▏         | 426/28080 [50:28<54:35:29,  7.11s/it]
                                                      
{'loss': 0.8544, 'learning_rate': 0.0002526690391459075, 'epoch': 0.18}

  2%|▏         | 426/28080 [50:28<54:35:29,  7.11s/it]
  2%|▏         | 427/28080 [50:35<54:26:10,  7.09s/it]
                                                      
{'loss': 0.8257, 'learning_rate': 0.00025326215895610916, 'epoch': 0.18}

  2%|▏         | 427/28080 [50:35<54:26:10,  7.09s/it]
  2%|▏         | 428/28080 [50:43<54:38:36,  7.11s/it]
                                                      
{'loss': 0.8307, 'learning_rate': 0.0002538552787663108, 'epoch': 0.18}

  2%|▏         | 428/28080 [50:43<54:38:36,  7.11s/it]
  2%|▏         | 429/28080 [50:50<54:26:40,  7.09s/it]
                                                      
{'loss': 0.8474, 'learning_rate': 0.00025444839857651245, 'epoch': 0.18}

  2%|▏         | 429/28080 [50:50<54:26:40,  7.09s/it]
  2%|▏         | 430/28080 [50:57<54:29:31,  7.09s/it]
                                                      
{'loss': 0.8357, 'learning_rate': 0.00025504151838671416, 'epoch': 0.18}

  2%|▏         | 430/28080 [50:57<54:29:31,  7.09s/it]
  2%|▏         | 431/28080 [51:04<54:20:43,  7.08s/it]
                                                      
{'loss': 0.8383, 'learning_rate': 0.0002556346381969158, 'epoch': 0.18}

  2%|▏         | 431/28080 [51:04<54:20:43,  7.08s/it]
  2%|▏         | 432/28080 [51:11<54:26:58,  7.09s/it]
                                                      
{'loss': 0.857, 'learning_rate': 0.00025622775800711745, 'epoch': 0.18}

  2%|▏         | 432/28080 [51:11<54:26:58,  7.09s/it]
  2%|▏         | 433/28080 [51:18<54:37:59,  7.11s/it]
                                                      
{'loss': 0.8315, 'learning_rate': 0.0002568208778173191, 'epoch': 0.18}

  2%|▏         | 433/28080 [51:18<54:37:59,  7.11s/it]
  2%|▏         | 434/28080 [51:25<54:41:27,  7.12s/it]
                                                      
{'loss': 0.831, 'learning_rate': 0.00025741399762752075, 'epoch': 0.19}

  2%|▏         | 434/28080 [51:25<54:41:27,  7.12s/it]
  2%|▏         | 435/28080 [51:32<54:41:11,  7.12s/it]
                                                      
{'loss': 0.8436, 'learning_rate': 0.0002580071174377224, 'epoch': 0.19}

  2%|▏         | 435/28080 [51:32<54:41:11,  7.12s/it]
  2%|▏         | 436/28080 [51:39<54:47:02,  7.13s/it]
                                                      
{'loss': 0.8388, 'learning_rate': 0.0002586002372479241, 'epoch': 0.19}

  2%|▏         | 436/28080 [51:39<54:47:02,  7.13s/it]
  2%|▏         | 437/28080 [51:47<54:31:50,  7.10s/it]
                                                      
{'loss': 0.8332, 'learning_rate': 0.00025919335705812575, 'epoch': 0.19}

  2%|▏         | 437/28080 [51:47<54:31:50,  7.10s/it]
  2%|▏         | 438/28080 [51:54<54:22:28,  7.08s/it]
                                                      
{'loss': 0.8679, 'learning_rate': 0.0002597864768683274, 'epoch': 0.19}

  2%|▏         | 438/28080 [51:54<54:22:28,  7.08s/it]
  2%|▏         | 439/28080 [52:01<54:40:51,  7.12s/it]
                                                      
{'loss': 0.8365, 'learning_rate': 0.00026037959667852905, 'epoch': 0.19}

  2%|▏         | 439/28080 [52:01<54:40:51,  7.12s/it]
  2%|▏         | 440/28080 [52:08<54:31:28,  7.10s/it]
                                                      
{'loss': 0.8466, 'learning_rate': 0.0002609727164887307, 'epoch': 0.19}

  2%|▏         | 440/28080 [52:08<54:31:28,  7.10s/it]
  2%|▏         | 441/28080 [52:15<54:30:51,  7.10s/it]
                                                      
{'loss': 0.8323, 'learning_rate': 0.0002615658362989324, 'epoch': 0.19}

  2%|▏         | 441/28080 [52:15<54:30:51,  7.10s/it]
  2%|▏         | 442/28080 [52:22<54:28:54,  7.10s/it]
                                                      
{'loss': 0.8394, 'learning_rate': 0.00026215895610913405, 'epoch': 0.19}

  2%|▏         | 442/28080 [52:22<54:28:54,  7.10s/it]
  2%|▏         | 443/28080 [52:29<54:29:09,  7.10s/it]
                                                      
{'loss': 0.8662, 'learning_rate': 0.0002627520759193357, 'epoch': 0.19}

  2%|▏         | 443/28080 [52:29<54:29:09,  7.10s/it]
  2%|▏         | 444/28080 [52:36<54:45:09,  7.13s/it]
                                                      
{'loss': 0.8412, 'learning_rate': 0.00026334519572953735, 'epoch': 0.19}

  2%|▏         | 444/28080 [52:36<54:45:09,  7.13s/it]
  2%|▏         | 445/28080 [52:43<54:40:55,  7.12s/it]
                                                      
{'loss': 0.8223, 'learning_rate': 0.000263938315539739, 'epoch': 0.19}

  2%|▏         | 445/28080 [52:43<54:40:55,  7.12s/it]
  2%|▏         | 446/28080 [52:51<54:40:56,  7.12s/it]
                                                      
{'loss': 0.8243, 'learning_rate': 0.0002645314353499407, 'epoch': 0.19}

  2%|▏         | 446/28080 [52:51<54:40:56,  7.12s/it]
  2%|▏         | 447/28080 [52:58<54:53:47,  7.15s/it]
                                                      
{'loss': 0.8311, 'learning_rate': 0.00026512455516014235, 'epoch': 0.19}

  2%|▏         | 447/28080 [52:58<54:53:47,  7.15s/it]
  2%|▏         | 448/28080 [53:05<55:03:43,  7.17s/it]
                                                      
{'loss': 0.8166, 'learning_rate': 0.000265717674970344, 'epoch': 0.19}

  2%|▏         | 448/28080 [53:05<55:03:43,  7.17s/it]
  2%|▏         | 449/28080 [53:12<54:54:30,  7.15s/it]
                                                      
{'loss': 0.8321, 'learning_rate': 0.00026631079478054565, 'epoch': 0.19}

  2%|▏         | 449/28080 [53:12<54:54:30,  7.15s/it]
  2%|▏         | 450/28080 [53:19<54:44:30,  7.13s/it]
                                                      
{'loss': 0.8331, 'learning_rate': 0.0002669039145907473, 'epoch': 0.19}

  2%|▏         | 450/28080 [53:19<54:44:30,  7.13s/it]
  2%|▏         | 451/28080 [53:26<54:52:04,  7.15s/it]
                                                      
{'loss': 0.8247, 'learning_rate': 0.000267497034400949, 'epoch': 0.19}

  2%|▏         | 451/28080 [53:26<54:52:04,  7.15s/it]
  2%|▏         | 452/28080 [53:33<54:31:58,  7.11s/it]
                                                      
{'loss': 0.8376, 'learning_rate': 0.0002680901542111507, 'epoch': 0.19}

  2%|▏         | 452/28080 [53:33<54:31:58,  7.11s/it]
  2%|▏         | 453/28080 [53:40<54:29:54,  7.10s/it]
                                                      
{'loss': 0.8181, 'learning_rate': 0.00026868327402135235, 'epoch': 0.19}

  2%|▏         | 453/28080 [53:40<54:29:54,  7.10s/it]
  2%|▏         | 454/28080 [53:48<54:33:00,  7.11s/it]
                                                      
{'loss': 0.822, 'learning_rate': 0.000269276393831554, 'epoch': 0.19}

  2%|▏         | 454/28080 [53:48<54:33:00,  7.11s/it]
  2%|▏         | 455/28080 [53:55<54:38:41,  7.12s/it]
                                                      
{'loss': 0.8383, 'learning_rate': 0.00026986951364175565, 'epoch': 0.19}

  2%|▏         | 455/28080 [53:55<54:38:41,  7.12s/it]
  2%|▏         | 456/28080 [54:02<54:45:25,  7.14s/it]
                                                      
{'loss': 0.8103, 'learning_rate': 0.0002704626334519573, 'epoch': 0.19}

  2%|▏         | 456/28080 [54:02<54:45:25,  7.14s/it]
  2%|▏         | 457/28080 [54:09<54:37:00,  7.12s/it]
                                                      
{'loss': 0.8262, 'learning_rate': 0.000271055753262159, 'epoch': 0.2}

  2%|▏         | 457/28080 [54:09<54:37:00,  7.12s/it]
  2%|▏         | 458/28080 [54:16<54:37:19,  7.12s/it]
                                                      
{'loss': 0.8149, 'learning_rate': 0.00027164887307236065, 'epoch': 0.2}

  2%|▏         | 458/28080 [54:16<54:37:19,  7.12s/it]
  2%|▏         | 459/28080 [54:23<54:25:07,  7.09s/it]
                                                      
{'loss': 0.8185, 'learning_rate': 0.0002722419928825623, 'epoch': 0.2}

  2%|▏         | 459/28080 [54:23<54:25:07,  7.09s/it]
  2%|▏         | 460/28080 [54:30<54:26:36,  7.10s/it]
                                                      
{'loss': 0.8322, 'learning_rate': 0.00027283511269276395, 'epoch': 0.2}

  2%|▏         | 460/28080 [54:30<54:26:36,  7.10s/it]
  2%|▏         | 461/28080 [54:37<54:33:13,  7.11s/it]
                                                      
{'loss': 0.8436, 'learning_rate': 0.0002734282325029656, 'epoch': 0.2}

  2%|▏         | 461/28080 [54:37<54:33:13,  7.11s/it]
  2%|▏         | 462/28080 [54:44<54:34:28,  7.11s/it]
                                                      
{'loss': 0.8079, 'learning_rate': 0.00027402135231316724, 'epoch': 0.2}

  2%|▏         | 462/28080 [54:44<54:34:28,  7.11s/it]
  2%|▏         | 463/28080 [54:52<54:35:21,  7.12s/it]
                                                      
{'loss': 0.8265, 'learning_rate': 0.00027461447212336895, 'epoch': 0.2}

  2%|▏         | 463/28080 [54:52<54:35:21,  7.12s/it]
  2%|▏         | 464/28080 [54:59<54:42:14,  7.13s/it]
                                                      
{'loss': 0.8158, 'learning_rate': 0.0002752075919335706, 'epoch': 0.2}

  2%|▏         | 464/28080 [54:59<54:42:14,  7.13s/it]
  2%|▏         | 465/28080 [55:06<54:19:23,  7.08s/it]
                                                      
{'loss': 0.8219, 'learning_rate': 0.00027580071174377225, 'epoch': 0.2}

  2%|▏         | 465/28080 [55:06<54:19:23,  7.08s/it]
  2%|▏         | 466/28080 [55:13<54:36:50,  7.12s/it]
                                                      
{'loss': 0.8141, 'learning_rate': 0.0002763938315539739, 'epoch': 0.2}

  2%|▏         | 466/28080 [55:13<54:36:50,  7.12s/it]
  2%|▏         | 467/28080 [55:20<54:47:29,  7.14s/it]
                                                      
{'loss': 0.82, 'learning_rate': 0.00027698695136417554, 'epoch': 0.2}

  2%|▏         | 467/28080 [55:20<54:47:29,  7.14s/it]
  2%|▏         | 468/28080 [55:27<54:37:47,  7.12s/it]
                                                      
{'loss': 0.8214, 'learning_rate': 0.00027758007117437725, 'epoch': 0.2}

  2%|▏         | 468/28080 [55:27<54:37:47,  7.12s/it]
  2%|▏         | 469/28080 [55:34<54:26:42,  7.10s/it]
                                                      
{'loss': 0.8099, 'learning_rate': 0.0002781731909845789, 'epoch': 0.2}

  2%|▏         | 469/28080 [55:34<54:26:42,  7.10s/it]
  2%|▏         | 470/28080 [55:41<54:28:34,  7.10s/it]
                                                      
{'loss': 0.7984, 'learning_rate': 0.00027876631079478054, 'epoch': 0.2}

  2%|▏         | 470/28080 [55:41<54:28:34,  7.10s/it]
  2%|▏         | 471/28080 [55:48<54:16:48,  7.08s/it]
                                                      
{'loss': 0.8136, 'learning_rate': 0.0002793594306049822, 'epoch': 0.2}

  2%|▏         | 471/28080 [55:48<54:16:48,  7.08s/it]
  2%|▏         | 472/28080 [55:56<54:28:28,  7.10s/it]
                                                      
{'loss': 0.8022, 'learning_rate': 0.00027995255041518384, 'epoch': 0.2}

  2%|▏         | 472/28080 [55:56<54:28:28,  7.10s/it]
  2%|▏         | 473/28080 [56:03<54:23:33,  7.09s/it]
                                                      
{'loss': 0.8199, 'learning_rate': 0.00028054567022538554, 'epoch': 0.2}

  2%|▏         | 473/28080 [56:03<54:23:33,  7.09s/it]
  2%|▏         | 474/28080 [56:10<54:39:52,  7.13s/it]
                                                      
{'loss': 0.8325, 'learning_rate': 0.0002811387900355872, 'epoch': 0.2}

  2%|▏         | 474/28080 [56:10<54:39:52,  7.13s/it]
  2%|▏         | 475/28080 [56:17<54:28:30,  7.10s/it]
                                                      
{'loss': 0.8194, 'learning_rate': 0.00028173190984578884, 'epoch': 0.2}

  2%|▏         | 475/28080 [56:17<54:28:30,  7.10s/it]
  2%|▏         | 476/28080 [56:24<54:22:34,  7.09s/it]
                                                      
{'loss': 0.8152, 'learning_rate': 0.0002823250296559905, 'epoch': 0.2}

  2%|▏         | 476/28080 [56:24<54:22:34,  7.09s/it]
  2%|▏         | 477/28080 [56:31<54:21:47,  7.09s/it]
                                                      
{'loss': 0.8259, 'learning_rate': 0.00028291814946619214, 'epoch': 0.2}

  2%|▏         | 477/28080 [56:31<54:21:47,  7.09s/it]
  2%|▏         | 478/28080 [56:38<53:57:42,  7.04s/it]
                                                      
{'loss': 0.8214, 'learning_rate': 0.0002835112692763938, 'epoch': 0.2}

  2%|▏         | 478/28080 [56:38<53:57:42,  7.04s/it]
  2%|▏         | 479/28080 [56:45<54:06:53,  7.06s/it]
                                                      
{'loss': 0.8182, 'learning_rate': 0.0002841043890865955, 'epoch': 0.2}

  2%|▏         | 479/28080 [56:45<54:06:53,  7.06s/it]
  2%|▏         | 480/28080 [56:52<54:15:36,  7.08s/it]
                                                      
{'loss': 0.8242, 'learning_rate': 0.0002846975088967972, 'epoch': 0.21}

  2%|▏         | 480/28080 [56:52<54:15:36,  7.08s/it]
  2%|▏         | 481/28080 [56:59<54:31:40,  7.11s/it]
                                                      
{'loss': 0.8181, 'learning_rate': 0.00028529062870699884, 'epoch': 0.21}

  2%|▏         | 481/28080 [56:59<54:31:40,  7.11s/it]
  2%|▏         | 482/28080 [57:07<54:40:40,  7.13s/it]
                                                      
{'loss': 0.8017, 'learning_rate': 0.0002858837485172005, 'epoch': 0.21}

  2%|▏         | 482/28080 [57:07<54:40:40,  7.13s/it]
  2%|▏         | 483/28080 [57:14<54:26:19,  7.10s/it]
                                                      
{'loss': 0.818, 'learning_rate': 0.00028647686832740214, 'epoch': 0.21}

  2%|▏         | 483/28080 [57:14<54:26:19,  7.10s/it]
  2%|▏         | 484/28080 [57:21<54:32:48,  7.12s/it]
                                                      
{'loss': 0.8274, 'learning_rate': 0.00028706998813760384, 'epoch': 0.21}

  2%|▏         | 484/28080 [57:21<54:32:48,  7.12s/it]
  2%|▏         | 485/28080 [57:28<54:32:48,  7.12s/it]
                                                      
{'loss': 0.8277, 'learning_rate': 0.0002876631079478055, 'epoch': 0.21}

  2%|▏         | 485/28080 [57:28<54:32:48,  7.12s/it]
  2%|▏         | 486/28080 [57:35<54:29:40,  7.11s/it]
                                                      
{'loss': 0.802, 'learning_rate': 0.00028825622775800714, 'epoch': 0.21}

  2%|▏         | 486/28080 [57:35<54:29:40,  7.11s/it]
  2%|▏         | 487/28080 [57:42<54:41:36,  7.14s/it]
                                                      
{'loss': 0.8035, 'learning_rate': 0.0002888493475682088, 'epoch': 0.21}

  2%|▏         | 487/28080 [57:42<54:41:36,  7.14s/it]
  2%|▏         | 488/28080 [57:49<54:33:30,  7.12s/it]
                                                      
{'loss': 0.8197, 'learning_rate': 0.00028944246737841044, 'epoch': 0.21}

  2%|▏         | 488/28080 [57:49<54:33:30,  7.12s/it]
  2%|▏         | 489/28080 [57:56<54:38:02,  7.13s/it]
                                                      
{'loss': 0.8209, 'learning_rate': 0.0002900355871886121, 'epoch': 0.21}

  2%|▏         | 489/28080 [57:56<54:38:02,  7.13s/it]
  2%|▏         | 490/28080 [58:03<54:22:55,  7.10s/it]
                                                      
{'loss': 0.8123, 'learning_rate': 0.0002906287069988138, 'epoch': 0.21}

  2%|▏         | 490/28080 [58:03<54:22:55,  7.10s/it]
  2%|▏         | 491/28080 [58:10<54:20:13,  7.09s/it]
                                                      
{'loss': 0.8003, 'learning_rate': 0.00029122182680901544, 'epoch': 0.21}

  2%|▏         | 491/28080 [58:10<54:20:13,  7.09s/it]
  2%|▏         | 492/28080 [58:18<54:19:58,  7.09s/it]
                                                      
{'loss': 0.797, 'learning_rate': 0.0002918149466192171, 'epoch': 0.21}

  2%|▏         | 492/28080 [58:18<54:19:58,  7.09s/it]
  2%|▏         | 493/28080 [58:25<54:06:06,  7.06s/it]
                                                      
{'loss': 0.8071, 'learning_rate': 0.00029240806642941874, 'epoch': 0.21}

  2%|▏         | 493/28080 [58:25<54:06:06,  7.06s/it]
  2%|▏         | 494/28080 [58:32<54:15:27,  7.08s/it]
                                                      
{'loss': 0.8286, 'learning_rate': 0.0002930011862396204, 'epoch': 0.21}

  2%|▏         | 494/28080 [58:32<54:15:27,  7.08s/it]
  2%|▏         | 495/28080 [58:39<54:17:43,  7.09s/it]
                                                      
{'loss': 0.812, 'learning_rate': 0.0002935943060498221, 'epoch': 0.21}

  2%|▏         | 495/28080 [58:39<54:17:43,  7.09s/it]
  2%|▏         | 496/28080 [58:46<54:18:27,  7.09s/it]
                                                      
{'loss': 0.8041, 'learning_rate': 0.00029418742586002374, 'epoch': 0.21}

  2%|▏         | 496/28080 [58:46<54:18:27,  7.09s/it]
  2%|▏         | 497/28080 [58:53<54:09:46,  7.07s/it]
                                                      
{'loss': 0.8125, 'learning_rate': 0.0002947805456702254, 'epoch': 0.21}

  2%|▏         | 497/28080 [58:53<54:09:46,  7.07s/it]
  2%|▏         | 498/28080 [59:00<54:09:02,  7.07s/it]
                                                      
{'loss': 0.8193, 'learning_rate': 0.00029537366548042704, 'epoch': 0.21}

  2%|▏         | 498/28080 [59:00<54:09:02,  7.07s/it]
  2%|▏         | 499/28080 [59:07<54:12:43,  7.08s/it]
                                                      
{'loss': 0.8189, 'learning_rate': 0.0002959667852906287, 'epoch': 0.21}

  2%|▏         | 499/28080 [59:07<54:12:43,  7.08s/it]
  2%|▏         | 500/28080 [59:14<54:22:29,  7.10s/it]
                                                      
{'loss': 0.8192, 'learning_rate': 0.0002965599051008304, 'epoch': 0.21}

  2%|▏         | 500/28080 [59:14<54:22:29,  7.10s/it]
  2%|▏         | 501/28080 [59:21<54:21:44,  7.10s/it]
                                                      
{'loss': 0.8153, 'learning_rate': 0.00029715302491103204, 'epoch': 0.21}

  2%|▏         | 501/28080 [59:21<54:21:44,  7.10s/it]
  2%|▏         | 502/28080 [59:28<54:16:08,  7.08s/it]
                                                      
{'loss': 0.8009, 'learning_rate': 0.0002977461447212337, 'epoch': 0.21}

  2%|▏         | 502/28080 [59:28<54:16:08,  7.08s/it]
  2%|▏         | 503/28080 [59:35<54:04:43,  7.06s/it]
                                                      
{'loss': 0.8113, 'learning_rate': 0.00029833926453143534, 'epoch': 0.21}

  2%|▏         | 503/28080 [59:35<54:04:43,  7.06s/it]
  2%|▏         | 504/28080 [59:43<54:20:49,  7.09s/it]
                                                      
{'loss': 0.7869, 'learning_rate': 0.000298932384341637, 'epoch': 0.22}

  2%|▏         | 504/28080 [59:43<54:20:49,  7.09s/it]
  2%|▏         | 505/28080 [59:50<54:29:20,  7.11s/it]
                                                      
{'loss': 0.7852, 'learning_rate': 0.00029952550415183863, 'epoch': 0.22}

  2%|▏         | 505/28080 [59:50<54:29:20,  7.11s/it]
  2%|▏         | 506/28080 [59:57<54:41:41,  7.14s/it]
                                                      
{'loss': 0.8049, 'learning_rate': 0.00030011862396204034, 'epoch': 0.22}

  2%|▏         | 506/28080 [59:57<54:41:41,  7.14s/it]
  2%|▏         | 507/28080 [1:00:04<54:38:05,  7.13s/it]
                                                        
{'loss': 0.7995, 'learning_rate': 0.000300711743772242, 'epoch': 0.22}

  2%|▏         | 507/28080 [1:00:04<54:38:05,  7.13s/it]
  2%|▏         | 508/28080 [1:00:11<54:30:20,  7.12s/it]
                                                        
{'loss': 0.7925, 'learning_rate': 0.00030130486358244363, 'epoch': 0.22}

  2%|▏         | 508/28080 [1:00:11<54:30:20,  7.12s/it]
  2%|▏         | 509/28080 [1:00:18<54:38:09,  7.13s/it]
                                                        
{'loss': 0.7975, 'learning_rate': 0.00030189798339264534, 'epoch': 0.22}

  2%|▏         | 509/28080 [1:00:18<54:38:09,  7.13s/it]
  2%|▏         | 510/28080 [1:00:25<54:25:16,  7.11s/it]
                                                        
{'loss': 0.7961, 'learning_rate': 0.000302491103202847, 'epoch': 0.22}

  2%|▏         | 510/28080 [1:00:25<54:25:16,  7.11s/it]
  2%|▏         | 511/28080 [1:00:32<54:20:33,  7.10s/it]
                                                        
{'loss': 0.8004, 'learning_rate': 0.0003030842230130487, 'epoch': 0.22}

  2%|▏         | 511/28080 [1:00:32<54:20:33,  7.10s/it]
  2%|▏         | 512/28080 [1:00:39<54:06:21,  7.07s/it]
                                                        
{'loss': 0.8022, 'learning_rate': 0.00030367734282325034, 'epoch': 0.22}

  2%|▏         | 512/28080 [1:00:39<54:06:21,  7.07s/it]
  2%|▏         | 513/28080 [1:00:46<54:11:13,  7.08s/it]
                                                        
{'loss': 0.7981, 'learning_rate': 0.000304270462633452, 'epoch': 0.22}

  2%|▏         | 513/28080 [1:00:46<54:11:13,  7.08s/it]
  2%|▏         | 514/28080 [1:00:54<54:14:36,  7.08s/it]
                                                        
{'loss': 0.8042, 'learning_rate': 0.00030486358244365364, 'epoch': 0.22}

  2%|▏         | 514/28080 [1:00:54<54:14:36,  7.08s/it]
  2%|▏         | 515/28080 [1:01:01<54:12:37,  7.08s/it]
                                                        
{'loss': 0.8052, 'learning_rate': 0.0003054567022538553, 'epoch': 0.22}

  2%|▏         | 515/28080 [1:01:01<54:12:37,  7.08s/it]
  2%|▏         | 516/28080 [1:01:08<54:17:28,  7.09s/it]
                                                        
{'loss': 0.7977, 'learning_rate': 0.00030604982206405693, 'epoch': 0.22}

  2%|▏         | 516/28080 [1:01:08<54:17:28,  7.09s/it]
  2%|▏         | 517/28080 [1:01:15<54:23:25,  7.10s/it]
                                                        
{'loss': 0.8277, 'learning_rate': 0.00030664294187425864, 'epoch': 0.22}

  2%|▏         | 517/28080 [1:01:15<54:23:25,  7.10s/it]
  2%|▏         | 518/28080 [1:01:22<54:27:45,  7.11s/it]
                                                        
{'loss': 0.7891, 'learning_rate': 0.0003072360616844603, 'epoch': 0.22}

  2%|▏         | 518/28080 [1:01:22<54:27:45,  7.11s/it]
  2%|▏         | 519/28080 [1:01:29<54:26:16,  7.11s/it]
                                                        
{'loss': 0.7871, 'learning_rate': 0.00030782918149466193, 'epoch': 0.22}

  2%|▏         | 519/28080 [1:01:29<54:26:16,  7.11s/it]
  2%|▏         | 520/28080 [1:01:36<54:29:47,  7.12s/it]
                                                        
{'loss': 0.7991, 'learning_rate': 0.0003084223013048636, 'epoch': 0.22}

  2%|▏         | 520/28080 [1:01:36<54:29:47,  7.12s/it]
  2%|▏         | 521/28080 [1:01:43<54:34:10,  7.13s/it]
                                                        
{'loss': 0.7875, 'learning_rate': 0.00030901542111506523, 'epoch': 0.22}

  2%|▏         | 521/28080 [1:01:43<54:34:10,  7.13s/it]
  2%|▏         | 522/28080 [1:01:51<54:30:36,  7.12s/it]
                                                        
{'loss': 0.7892, 'learning_rate': 0.00030960854092526693, 'epoch': 0.22}

  2%|▏         | 522/28080 [1:01:51<54:30:36,  7.12s/it]
  2%|▏         | 523/28080 [1:01:58<54:18:10,  7.09s/it]
                                                        
{'loss': 0.7823, 'learning_rate': 0.0003102016607354686, 'epoch': 0.22}

  2%|▏         | 523/28080 [1:01:58<54:18:10,  7.09s/it]
  2%|▏         | 524/28080 [1:02:05<54:28:08,  7.12s/it]
                                                        
{'loss': 0.7939, 'learning_rate': 0.00031079478054567023, 'epoch': 0.22}

  2%|▏         | 524/28080 [1:02:05<54:28:08,  7.12s/it]
  2%|▏         | 525/28080 [1:02:12<54:13:40,  7.08s/it]
                                                        
{'loss': 0.7968, 'learning_rate': 0.0003113879003558719, 'epoch': 0.22}

  2%|▏         | 525/28080 [1:02:12<54:13:40,  7.08s/it]
  2%|▏         | 526/28080 [1:02:19<54:23:34,  7.11s/it]
                                                        
{'loss': 0.7925, 'learning_rate': 0.00031198102016607353, 'epoch': 0.22}

  2%|▏         | 526/28080 [1:02:19<54:23:34,  7.11s/it]
  2%|▏         | 527/28080 [1:02:26<54:32:30,  7.13s/it]
                                                        
{'loss': 0.7858, 'learning_rate': 0.00031257413997627523, 'epoch': 0.23}

  2%|▏         | 527/28080 [1:02:26<54:32:30,  7.13s/it]
  2%|▏         | 528/28080 [1:02:33<54:15:30,  7.09s/it]
                                                        
{'loss': 0.8102, 'learning_rate': 0.0003131672597864769, 'epoch': 0.23}

  2%|▏         | 528/28080 [1:02:33<54:15:30,  7.09s/it]
  2%|▏         | 529/28080 [1:02:40<54:13:00,  7.08s/it]
                                                        
{'loss': 0.7896, 'learning_rate': 0.00031376037959667853, 'epoch': 0.23}

  2%|▏         | 529/28080 [1:02:40<54:13:00,  7.08s/it]
  2%|▏         | 530/28080 [1:02:47<54:23:33,  7.11s/it]
                                                        
{'loss': 0.7865, 'learning_rate': 0.0003143534994068802, 'epoch': 0.23}

  2%|▏         | 530/28080 [1:02:47<54:23:33,  7.11s/it]
  2%|▏         | 531/28080 [1:02:54<54:22:54,  7.11s/it]
                                                        
{'loss': 0.796, 'learning_rate': 0.00031494661921708183, 'epoch': 0.23}

  2%|▏         | 531/28080 [1:02:54<54:22:54,  7.11s/it]
  2%|▏         | 532/28080 [1:03:01<54:15:38,  7.09s/it]
                                                        
{'loss': 0.823, 'learning_rate': 0.0003155397390272835, 'epoch': 0.23}

  2%|▏         | 532/28080 [1:03:01<54:15:38,  7.09s/it]
  2%|▏         | 533/28080 [1:03:08<54:05:00,  7.07s/it]
                                                        
{'loss': 0.7903, 'learning_rate': 0.0003161328588374852, 'epoch': 0.23}

  2%|▏         | 533/28080 [1:03:08<54:05:00,  7.07s/it]
  2%|▏         | 534/28080 [1:03:16<54:07:38,  7.07s/it]
                                                        
{'loss': 0.7856, 'learning_rate': 0.00031672597864768683, 'epoch': 0.23}

  2%|▏         | 534/28080 [1:03:16<54:07:38,  7.07s/it]
  2%|▏         | 535/28080 [1:03:23<54:05:35,  7.07s/it]
                                                        
{'loss': 0.8104, 'learning_rate': 0.0003173190984578885, 'epoch': 0.23}

  2%|▏         | 535/28080 [1:03:23<54:05:35,  7.07s/it]
  2%|▏         | 536/28080 [1:03:30<54:09:36,  7.08s/it]
                                                        
{'loss': 0.7875, 'learning_rate': 0.0003179122182680901, 'epoch': 0.23}

  2%|▏         | 536/28080 [1:03:30<54:09:36,  7.08s/it]
  2%|▏         | 537/28080 [1:03:37<54:30:55,  7.13s/it]
                                                        
{'loss': 0.7864, 'learning_rate': 0.0003185053380782918, 'epoch': 0.23}

  2%|▏         | 537/28080 [1:03:37<54:30:55,  7.13s/it]
  2%|▏         | 538/28080 [1:03:44<54:28:28,  7.12s/it]
                                                        
{'loss': 0.803, 'learning_rate': 0.00031909845788849353, 'epoch': 0.23}

  2%|▏         | 538/28080 [1:03:44<54:28:28,  7.12s/it]
  2%|▏         | 539/28080 [1:03:51<54:42:54,  7.15s/it]
                                                        
{'loss': 0.8029, 'learning_rate': 0.0003196915776986952, 'epoch': 0.23}

  2%|▏         | 539/28080 [1:03:51<54:42:54,  7.15s/it]
  2%|▏         | 540/28080 [1:03:58<54:36:44,  7.14s/it]
                                                        
{'loss': 0.787, 'learning_rate': 0.00032028469750889683, 'epoch': 0.23}

  2%|▏         | 540/28080 [1:03:58<54:36:44,  7.14s/it]
  2%|▏         | 541/28080 [1:04:06<54:30:47,  7.13s/it]
                                                        
{'loss': 0.7824, 'learning_rate': 0.0003208778173190985, 'epoch': 0.23}

  2%|▏         | 541/28080 [1:04:06<54:30:47,  7.13s/it]
  2%|▏         | 542/28080 [1:04:13<54:21:08,  7.11s/it]
                                                        
{'loss': 0.8018, 'learning_rate': 0.00032147093712930013, 'epoch': 0.23}

  2%|▏         | 542/28080 [1:04:13<54:21:08,  7.11s/it]
  2%|▏         | 543/28080 [1:04:20<54:21:15,  7.11s/it]
                                                        
{'loss': 0.7997, 'learning_rate': 0.0003220640569395018, 'epoch': 0.23}

  2%|▏         | 543/28080 [1:04:20<54:21:15,  7.11s/it]
  2%|▏         | 544/28080 [1:04:27<54:05:54,  7.07s/it]
                                                        
{'loss': 0.7985, 'learning_rate': 0.0003226571767497035, 'epoch': 0.23}

  2%|▏         | 544/28080 [1:04:27<54:05:54,  7.07s/it]
  2%|▏         | 545/28080 [1:04:34<54:01:50,  7.06s/it]
                                                        
{'loss': 0.7934, 'learning_rate': 0.00032325029655990513, 'epoch': 0.23}

  2%|▏         | 545/28080 [1:04:34<54:01:50,  7.06s/it]
  2%|▏         | 546/28080 [1:04:41<53:52:15,  7.04s/it]
                                                        
{'loss': 0.8176, 'learning_rate': 0.0003238434163701068, 'epoch': 0.23}

  2%|▏         | 546/28080 [1:04:41<53:52:15,  7.04s/it]
  2%|▏         | 547/28080 [1:04:48<54:03:55,  7.07s/it]
                                                        
{'loss': 0.8018, 'learning_rate': 0.0003244365361803084, 'epoch': 0.23}

  2%|▏         | 547/28080 [1:04:48<54:03:55,  7.07s/it]
  2%|▏         | 548/28080 [1:04:55<54:09:49,  7.08s/it]
                                                        
{'loss': 0.8078, 'learning_rate': 0.0003250296559905101, 'epoch': 0.23}

  2%|▏         | 548/28080 [1:04:55<54:09:49,  7.08s/it]
  2%|▏         | 549/28080 [1:05:02<54:20:33,  7.11s/it]
                                                        
{'loss': 0.7696, 'learning_rate': 0.0003256227758007118, 'epoch': 0.23}

  2%|▏         | 549/28080 [1:05:02<54:20:33,  7.11s/it]
  2%|▏         | 550/28080 [1:05:09<54:03:26,  7.07s/it]
                                                        
{'loss': 0.7749, 'learning_rate': 0.00032621589561091343, 'epoch': 0.23}

  2%|▏         | 550/28080 [1:05:09<54:03:26,  7.07s/it]
  2%|▏         | 551/28080 [1:05:16<54:00:42,  7.06s/it]
                                                        
{'loss': 0.8085, 'learning_rate': 0.0003268090154211151, 'epoch': 0.24}

  2%|▏         | 551/28080 [1:05:16<54:00:42,  7.06s/it]
  2%|▏         | 552/28080 [1:05:23<54:05:51,  7.07s/it]
                                                        
{'loss': 0.7907, 'learning_rate': 0.0003274021352313167, 'epoch': 0.24}

  2%|▏         | 552/28080 [1:05:23<54:05:51,  7.07s/it]
  2%|▏         | 553/28080 [1:05:30<53:39:45,  7.02s/it]
                                                        
{'loss': 0.8107, 'learning_rate': 0.0003279952550415184, 'epoch': 0.24}

  2%|▏         | 553/28080 [1:05:30<53:39:45,  7.02s/it]
  2%|▏         | 554/28080 [1:05:37<53:47:27,  7.04s/it]
                                                        
{'loss': 0.7916, 'learning_rate': 0.0003285883748517201, 'epoch': 0.24}

  2%|▏         | 554/28080 [1:05:37<53:47:27,  7.04s/it]
  2%|▏         | 555/28080 [1:05:44<53:56:11,  7.05s/it]
                                                        
{'loss': 0.8007, 'learning_rate': 0.0003291814946619217, 'epoch': 0.24}

  2%|▏         | 555/28080 [1:05:44<53:56:11,  7.05s/it]
  2%|▏         | 556/28080 [1:05:51<53:52:45,  7.05s/it]
                                                        
{'loss': 0.8169, 'learning_rate': 0.0003297746144721234, 'epoch': 0.24}

  2%|▏         | 556/28080 [1:05:51<53:52:45,  7.05s/it]
  2%|▏         | 557/28080 [1:05:58<53:58:27,  7.06s/it]
                                                        
{'loss': 0.7694, 'learning_rate': 0.000330367734282325, 'epoch': 0.24}

  2%|▏         | 557/28080 [1:05:58<53:58:27,  7.06s/it]
  2%|▏         | 558/28080 [1:06:06<54:14:47,  7.10s/it]
                                                        
{'loss': 0.8007, 'learning_rate': 0.00033096085409252667, 'epoch': 0.24}

  2%|▏         | 558/28080 [1:06:06<54:14:47,  7.10s/it]
  2%|▏         | 559/28080 [1:06:13<54:15:03,  7.10s/it]
                                                        
{'loss': 0.7738, 'learning_rate': 0.0003315539739027283, 'epoch': 0.24}

  2%|▏         | 559/28080 [1:06:13<54:15:03,  7.10s/it]
  2%|▏         | 560/28080 [1:06:20<54:16:19,  7.10s/it]
                                                        
{'loss': 0.8077, 'learning_rate': 0.00033214709371293, 'epoch': 0.24}

  2%|▏         | 560/28080 [1:06:20<54:16:19,  7.10s/it]
  2%|▏         | 561/28080 [1:06:27<54:09:48,  7.09s/it]
                                                        
{'loss': 0.8032, 'learning_rate': 0.0003327402135231317, 'epoch': 0.24}

  2%|▏         | 561/28080 [1:06:27<54:09:48,  7.09s/it]
  2%|▏         | 562/28080 [1:06:34<54:19:05,  7.11s/it]
                                                        
{'loss': 0.7907, 'learning_rate': 0.0003333333333333333, 'epoch': 0.24}

  2%|▏         | 562/28080 [1:06:34<54:19:05,  7.11s/it]
  2%|▏         | 563/28080 [1:06:41<54:25:16,  7.12s/it]
                                                        
{'loss': 0.7747, 'learning_rate': 0.00033392645314353497, 'epoch': 0.24}

  2%|▏         | 563/28080 [1:06:41<54:25:16,  7.12s/it]
  2%|▏         | 564/28080 [1:06:48<54:29:10,  7.13s/it]
                                                        
{'loss': 0.7774, 'learning_rate': 0.0003345195729537366, 'epoch': 0.24}

  2%|▏         | 564/28080 [1:06:48<54:29:10,  7.13s/it]
  2%|▏         | 565/28080 [1:06:55<54:29:13,  7.13s/it]
                                                        
{'loss': 0.793, 'learning_rate': 0.0003351126927639383, 'epoch': 0.24}

  2%|▏         | 565/28080 [1:06:55<54:29:13,  7.13s/it]
  2%|▏         | 566/28080 [1:07:03<54:30:56,  7.13s/it]
                                                        
{'loss': 0.7762, 'learning_rate': 0.00033570581257413997, 'epoch': 0.24}

  2%|▏         | 566/28080 [1:07:03<54:30:56,  7.13s/it]
  2%|▏         | 567/28080 [1:07:10<54:30:39,  7.13s/it]
                                                        
{'loss': 0.801, 'learning_rate': 0.0003362989323843417, 'epoch': 0.24}

  2%|▏         | 567/28080 [1:07:10<54:30:39,  7.13s/it]
  2%|▏         | 568/28080 [1:07:17<54:14:57,  7.10s/it]
                                                        
{'loss': 0.7935, 'learning_rate': 0.0003368920521945433, 'epoch': 0.24}

  2%|▏         | 568/28080 [1:07:17<54:14:57,  7.10s/it]
  2%|▏         | 569/28080 [1:07:24<54:18:16,  7.11s/it]
                                                        
{'loss': 0.7931, 'learning_rate': 0.00033748517200474497, 'epoch': 0.24}

  2%|▏         | 569/28080 [1:07:24<54:18:16,  7.11s/it]
  2%|▏         | 570/28080 [1:07:31<54:18:07,  7.11s/it]
                                                        
{'loss': 0.7815, 'learning_rate': 0.0003380782918149466, 'epoch': 0.24}

  2%|▏         | 570/28080 [1:07:31<54:18:07,  7.11s/it]
  2%|▏         | 571/28080 [1:07:38<54:23:09,  7.12s/it]
                                                        
{'loss': 0.7919, 'learning_rate': 0.0003386714116251483, 'epoch': 0.24}

  2%|▏         | 571/28080 [1:07:38<54:23:09,  7.12s/it]
  2%|▏         | 572/28080 [1:07:45<54:25:33,  7.12s/it]
                                                        
{'loss': 0.7933, 'learning_rate': 0.00033926453143535, 'epoch': 0.24}

  2%|▏         | 572/28080 [1:07:45<54:25:33,  7.12s/it]
  2%|▏         | 573/28080 [1:07:52<54:29:42,  7.13s/it]
                                                        
{'loss': 0.8028, 'learning_rate': 0.0003398576512455516, 'epoch': 0.24}

  2%|▏         | 573/28080 [1:07:52<54:29:42,  7.13s/it]
  2%|▏         | 574/28080 [1:07:59<54:24:47,  7.12s/it]
                                                        
{'loss': 0.7908, 'learning_rate': 0.00034045077105575327, 'epoch': 0.25}

  2%|▏         | 574/28080 [1:07:59<54:24:47,  7.12s/it]
  2%|▏         | 575/28080 [1:08:07<54:32:19,  7.14s/it]
                                                        
{'loss': 0.7887, 'learning_rate': 0.0003410438908659549, 'epoch': 0.25}

  2%|▏         | 575/28080 [1:08:07<54:32:19,  7.14s/it]
  2%|▏         | 576/28080 [1:08:14<54:29:49,  7.13s/it]
                                                        
{'loss': 0.7886, 'learning_rate': 0.0003416370106761566, 'epoch': 0.25}

  2%|▏         | 576/28080 [1:08:14<54:29:49,  7.13s/it]
  2%|▏         | 577/28080 [1:08:21<54:44:50,  7.17s/it]
                                                        
{'loss': 0.7569, 'learning_rate': 0.00034223013048635827, 'epoch': 0.25}

  2%|▏         | 577/28080 [1:08:21<54:44:50,  7.17s/it]
  2%|▏         | 578/28080 [1:08:28<54:38:49,  7.15s/it]
                                                        
{'loss': 0.7788, 'learning_rate': 0.0003428232502965599, 'epoch': 0.25}

  2%|▏         | 578/28080 [1:08:28<54:38:49,  7.15s/it]
  2%|▏         | 579/28080 [1:08:35<54:37:41,  7.15s/it]
                                                        
{'loss': 0.7914, 'learning_rate': 0.00034341637010676157, 'epoch': 0.25}

  2%|▏         | 579/28080 [1:08:35<54:37:41,  7.15s/it]
  2%|▏         | 580/28080 [1:08:42<54:21:00,  7.11s/it]
                                                        
{'loss': 0.7788, 'learning_rate': 0.0003440094899169632, 'epoch': 0.25}

  2%|▏         | 580/28080 [1:08:42<54:21:00,  7.11s/it]
  2%|▏         | 581/28080 [1:08:49<54:17:55,  7.11s/it]
                                                        
{'loss': 0.796, 'learning_rate': 0.0003446026097271649, 'epoch': 0.25}

  2%|▏         | 581/28080 [1:08:49<54:17:55,  7.11s/it]
  2%|▏         | 582/28080 [1:08:56<54:12:52,  7.10s/it]
                                                        
{'loss': 0.7912, 'learning_rate': 0.00034519572953736657, 'epoch': 0.25}

  2%|▏         | 582/28080 [1:08:57<54:12:52,  7.10s/it]
  2%|▏         | 583/28080 [1:09:04<54:07:05,  7.09s/it]
                                                        
{'loss': 0.7955, 'learning_rate': 0.0003457888493475682, 'epoch': 0.25}

  2%|▏         | 583/28080 [1:09:04<54:07:05,  7.09s/it]
  2%|▏         | 584/28080 [1:09:11<54:06:20,  7.08s/it]
                                                        
{'loss': 0.7871, 'learning_rate': 0.00034638196915776987, 'epoch': 0.25}

  2%|▏         | 584/28080 [1:09:11<54:06:20,  7.08s/it]
  2%|▏         | 585/28080 [1:09:18<54:21:36,  7.12s/it]
                                                        
{'loss': 0.7835, 'learning_rate': 0.0003469750889679715, 'epoch': 0.25}

  2%|▏         | 585/28080 [1:09:18<54:21:36,  7.12s/it]
  2%|▏         | 586/28080 [1:09:25<54:25:28,  7.13s/it]
                                                        
{'loss': 0.7764, 'learning_rate': 0.00034756820877817317, 'epoch': 0.25}

  2%|▏         | 586/28080 [1:09:25<54:25:28,  7.13s/it]
  2%|▏         | 587/28080 [1:09:32<54:08:18,  7.09s/it]
                                                        
{'loss': 0.7839, 'learning_rate': 0.00034816132858837487, 'epoch': 0.25}

  2%|▏         | 587/28080 [1:09:32<54:08:18,  7.09s/it]
  2%|▏         | 588/28080 [1:09:39<54:07:47,  7.09s/it]
                                                        
{'loss': 0.7766, 'learning_rate': 0.0003487544483985765, 'epoch': 0.25}

  2%|▏         | 588/28080 [1:09:39<54:07:47,  7.09s/it]
  2%|▏         | 589/28080 [1:09:46<53:48:17,  7.05s/it]
                                                        
{'loss': 0.8066, 'learning_rate': 0.00034934756820877817, 'epoch': 0.25}

  2%|▏         | 589/28080 [1:09:46<53:48:17,  7.05s/it]
  2%|▏         | 590/28080 [1:09:53<53:59:32,  7.07s/it]
                                                        
{'loss': 0.7878, 'learning_rate': 0.0003499406880189798, 'epoch': 0.25}

  2%|▏         | 590/28080 [1:09:53<53:59:32,  7.07s/it]
  2%|▏         | 591/28080 [1:10:00<54:04:30,  7.08s/it]
                                                        
{'loss': 0.8077, 'learning_rate': 0.00035053380782918146, 'epoch': 0.25}

  2%|▏         | 591/28080 [1:10:00<54:04:30,  7.08s/it]
  2%|▏         | 592/28080 [1:10:07<53:50:12,  7.05s/it]
                                                        
{'loss': 0.7924, 'learning_rate': 0.00035112692763938317, 'epoch': 0.25}

  2%|▏         | 592/28080 [1:10:07<53:50:12,  7.05s/it]
  2%|▏         | 593/28080 [1:10:14<54:03:05,  7.08s/it]
                                                        
{'loss': 0.7736, 'learning_rate': 0.0003517200474495848, 'epoch': 0.25}

  2%|▏         | 593/28080 [1:10:14<54:03:05,  7.08s/it]
  2%|▏         | 594/28080 [1:10:21<54:03:03,  7.08s/it]
                                                        
{'loss': 0.7756, 'learning_rate': 0.00035231316725978646, 'epoch': 0.25}

  2%|▏         | 594/28080 [1:10:21<54:03:03,  7.08s/it]
  2%|▏         | 595/28080 [1:10:29<54:07:14,  7.09s/it]
                                                        
{'loss': 0.782, 'learning_rate': 0.0003529062870699881, 'epoch': 0.25}

  2%|▏         | 595/28080 [1:10:29<54:07:14,  7.09s/it]
  2%|▏         | 596/28080 [1:10:36<54:12:13,  7.10s/it]
                                                        
{'loss': 0.7785, 'learning_rate': 0.0003534994068801898, 'epoch': 0.25}

  2%|▏         | 596/28080 [1:10:36<54:12:13,  7.10s/it]
  2%|▏         | 597/28080 [1:10:43<54:16:05,  7.11s/it]
                                                        
{'loss': 0.774, 'learning_rate': 0.00035409252669039147, 'epoch': 0.26}

  2%|▏         | 597/28080 [1:10:43<54:16:05,  7.11s/it]
  2%|▏         | 598/28080 [1:10:50<54:14:04,  7.10s/it]
                                                        
{'loss': 0.8051, 'learning_rate': 0.00035468564650059317, 'epoch': 0.26}

  2%|▏         | 598/28080 [1:10:50<54:14:04,  7.10s/it]
  2%|▏         | 599/28080 [1:10:57<54:23:34,  7.13s/it]
                                                        
{'loss': 0.7871, 'learning_rate': 0.0003552787663107948, 'epoch': 0.26}

  2%|▏         | 599/28080 [1:10:57<54:23:34,  7.13s/it]
  2%|▏         | 600/28080 [1:11:04<54:25:10,  7.13s/it]
                                                        
{'loss': 0.8055, 'learning_rate': 0.00035587188612099647, 'epoch': 0.26}

  2%|▏         | 600/28080 [1:11:04<54:25:10,  7.13s/it]
  2%|▏         | 601/28080 [1:11:11<54:18:10,  7.11s/it]
                                                        
{'loss': 0.7688, 'learning_rate': 0.0003564650059311981, 'epoch': 0.26}

  2%|▏         | 601/28080 [1:11:11<54:18:10,  7.11s/it]
  2%|▏         | 602/28080 [1:11:19<54:31:19,  7.14s/it]
                                                        
{'loss': 0.7665, 'learning_rate': 0.00035705812574139976, 'epoch': 0.26}

  2%|▏         | 602/28080 [1:11:19<54:31:19,  7.14s/it]
  2%|▏         | 603/28080 [1:11:26<54:28:38,  7.14s/it]
                                                        
{'loss': 0.772, 'learning_rate': 0.00035765124555160147, 'epoch': 0.26}

  2%|▏         | 603/28080 [1:11:26<54:28:38,  7.14s/it]
  2%|▏         | 604/28080 [1:11:33<54:05:03,  7.09s/it]
                                                        
{'loss': 0.8033, 'learning_rate': 0.0003582443653618031, 'epoch': 0.26}

  2%|▏         | 604/28080 [1:11:33<54:05:03,  7.09s/it]
  2%|▏         | 605/28080 [1:11:40<54:13:52,  7.11s/it]
                                                        
{'loss': 0.7641, 'learning_rate': 0.00035883748517200476, 'epoch': 0.26}

  2%|▏         | 605/28080 [1:11:40<54:13:52,  7.11s/it]
  2%|▏         | 606/28080 [1:11:47<54:04:31,  7.09s/it]
                                                        
{'loss': 0.7953, 'learning_rate': 0.0003594306049822064, 'epoch': 0.26}

  2%|▏         | 606/28080 [1:11:47<54:04:31,  7.09s/it]
  2%|▏         | 607/28080 [1:11:54<54:05:52,  7.09s/it]
                                                        
{'loss': 0.765, 'learning_rate': 0.00036002372479240806, 'epoch': 0.26}

  2%|▏         | 607/28080 [1:11:54<54:05:52,  7.09s/it]
  2%|▏         | 608/28080 [1:12:01<53:59:23,  7.07s/it]
                                                        
{'loss': 0.7961, 'learning_rate': 0.00036061684460260977, 'epoch': 0.26}

  2%|▏         | 608/28080 [1:12:01<53:59:23,  7.07s/it]
  2%|▏         | 609/28080 [1:12:08<53:57:36,  7.07s/it]
                                                        
{'loss': 0.7989, 'learning_rate': 0.0003612099644128114, 'epoch': 0.26}

  2%|▏         | 609/28080 [1:12:08<53:57:36,  7.07s/it]
  2%|▏         | 610/28080 [1:12:15<54:10:13,  7.10s/it]
                                                        
{'loss': 0.7794, 'learning_rate': 0.00036180308422301306, 'epoch': 0.26}

  2%|▏         | 610/28080 [1:12:15<54:10:13,  7.10s/it]
  2%|▏         | 611/28080 [1:12:22<54:04:27,  7.09s/it]
                                                        
{'loss': 0.793, 'learning_rate': 0.0003623962040332147, 'epoch': 0.26}

  2%|▏         | 611/28080 [1:12:22<54:04:27,  7.09s/it]
  2%|▏         | 612/28080 [1:12:29<54:12:13,  7.10s/it]
                                                        
{'loss': 0.7947, 'learning_rate': 0.00036298932384341636, 'epoch': 0.26}

  2%|▏         | 612/28080 [1:12:29<54:12:13,  7.10s/it]
  2%|▏         | 613/28080 [1:12:36<54:06:04,  7.09s/it]
                                                        
{'loss': 0.7837, 'learning_rate': 0.000363582443653618, 'epoch': 0.26}

  2%|▏         | 613/28080 [1:12:36<54:06:04,  7.09s/it]
  2%|▏         | 614/28080 [1:12:43<53:58:48,  7.08s/it]
                                                        
{'loss': 0.7751, 'learning_rate': 0.0003641755634638197, 'epoch': 0.26}

  2%|▏         | 614/28080 [1:12:43<53:58:48,  7.08s/it]
  2%|▏         | 615/28080 [1:12:51<54:03:35,  7.09s/it]
                                                        
{'loss': 0.7872, 'learning_rate': 0.00036476868327402136, 'epoch': 0.26}

  2%|▏         | 615/28080 [1:12:51<54:03:35,  7.09s/it]
  2%|▏         | 616/28080 [1:12:58<53:59:30,  7.08s/it]
                                                        
{'loss': 0.7805, 'learning_rate': 0.000365361803084223, 'epoch': 0.26}

  2%|▏         | 616/28080 [1:12:58<53:59:30,  7.08s/it]
  2%|▏         | 617/28080 [1:13:05<53:55:32,  7.07s/it]
                                                        
{'loss': 0.7692, 'learning_rate': 0.00036595492289442466, 'epoch': 0.26}

  2%|▏         | 617/28080 [1:13:05<53:55:32,  7.07s/it]
  2%|▏         | 618/28080 [1:13:12<54:19:59,  7.12s/it]
                                                        
{'loss': 0.7935, 'learning_rate': 0.0003665480427046263, 'epoch': 0.26}

  2%|▏         | 618/28080 [1:13:12<54:19:59,  7.12s/it]
  2%|▏         | 619/28080 [1:13:19<54:20:18,  7.12s/it]
                                                        
{'loss': 0.7744, 'learning_rate': 0.000367141162514828, 'epoch': 0.26}

  2%|▏         | 619/28080 [1:13:19<54:20:18,  7.12s/it]
  2%|▏         | 620/28080 [1:13:26<54:20:49,  7.12s/it]
                                                        
{'loss': 0.7876, 'learning_rate': 0.00036773428232502966, 'epoch': 0.26}

  2%|▏         | 620/28080 [1:13:26<54:20:49,  7.12s/it]
  2%|▏         | 621/28080 [1:13:33<54:26:15,  7.14s/it]
                                                        
{'loss': 0.7625, 'learning_rate': 0.0003683274021352313, 'epoch': 0.27}

  2%|▏         | 621/28080 [1:13:33<54:26:15,  7.14s/it]
  2%|▏         | 622/28080 [1:13:40<54:27:34,  7.14s/it]
                                                        
{'loss': 0.7817, 'learning_rate': 0.00036892052194543296, 'epoch': 0.27}

  2%|▏         | 622/28080 [1:13:41<54:27:34,  7.14s/it]
  2%|▏         | 623/28080 [1:13:48<54:31:19,  7.15s/it]
                                                        
{'loss': 0.7729, 'learning_rate': 0.0003695136417556346, 'epoch': 0.27}

  2%|▏         | 623/28080 [1:13:48<54:31:19,  7.15s/it]
  2%|▏         | 624/28080 [1:13:55<54:09:44,  7.10s/it]
                                                        
{'loss': 0.7873, 'learning_rate': 0.00037010676156583626, 'epoch': 0.27}

  2%|▏         | 624/28080 [1:13:55<54:09:44,  7.10s/it]
  2%|▏         | 625/28080 [1:14:02<54:02:28,  7.09s/it]
                                                        
{'loss': 0.7998, 'learning_rate': 0.000370699881376038, 'epoch': 0.27}

  2%|▏         | 625/28080 [1:14:02<54:02:28,  7.09s/it]
  2%|▏         | 626/28080 [1:14:09<54:03:39,  7.09s/it]
                                                        
{'loss': 0.7664, 'learning_rate': 0.00037129300118623966, 'epoch': 0.27}

  2%|▏         | 626/28080 [1:14:09<54:03:39,  7.09s/it]
  2%|▏         | 627/28080 [1:14:16<54:04:23,  7.09s/it]
                                                        
{'loss': 0.7616, 'learning_rate': 0.0003718861209964413, 'epoch': 0.27}

  2%|▏         | 627/28080 [1:14:16<54:04:23,  7.09s/it]
  2%|▏         | 628/28080 [1:14:23<54:08:39,  7.10s/it]
                                                        
{'loss': 0.7841, 'learning_rate': 0.00037247924080664296, 'epoch': 0.27}

  2%|▏         | 628/28080 [1:14:23<54:08:39,  7.10s/it]
  2%|▏         | 629/28080 [1:14:30<53:51:23,  7.06s/it]
                                                        
{'loss': 0.7905, 'learning_rate': 0.0003730723606168446, 'epoch': 0.27}

  2%|▏         | 629/28080 [1:14:30<53:51:23,  7.06s/it]
  2%|▏         | 630/28080 [1:14:37<53:59:46,  7.08s/it]
                                                        
{'loss': 0.774, 'learning_rate': 0.0003736654804270463, 'epoch': 0.27}

  2%|▏         | 630/28080 [1:14:37<53:59:46,  7.08s/it]
  2%|▏         | 631/28080 [1:14:44<54:09:50,  7.10s/it]
                                                        
{'loss': 0.7717, 'learning_rate': 0.00037425860023724796, 'epoch': 0.27}

  2%|▏         | 631/28080 [1:14:44<54:09:50,  7.10s/it]
  2%|▏         | 632/28080 [1:14:51<54:10:54,  7.11s/it]
                                                        
{'loss': 0.7851, 'learning_rate': 0.0003748517200474496, 'epoch': 0.27}

  2%|▏         | 632/28080 [1:14:51<54:10:54,  7.11s/it]
  2%|▏         | 633/28080 [1:14:59<54:16:05,  7.12s/it]
                                                        
{'loss': 0.7878, 'learning_rate': 0.00037544483985765126, 'epoch': 0.27}

  2%|▏         | 633/28080 [1:14:59<54:16:05,  7.12s/it]
  2%|▏         | 634/28080 [1:15:06<54:23:44,  7.13s/it]
                                                        
{'loss': 0.7889, 'learning_rate': 0.0003760379596678529, 'epoch': 0.27}

  2%|▏         | 634/28080 [1:15:06<54:23:44,  7.13s/it]
  2%|▏         | 635/28080 [1:15:13<54:24:03,  7.14s/it]
                                                        
{'loss': 0.7661, 'learning_rate': 0.0003766310794780546, 'epoch': 0.27}

  2%|▏         | 635/28080 [1:15:13<54:24:03,  7.14s/it]
  2%|▏         | 636/28080 [1:15:20<54:18:14,  7.12s/it]
                                                        
{'loss': 0.766, 'learning_rate': 0.00037722419928825626, 'epoch': 0.27}

  2%|▏         | 636/28080 [1:15:20<54:18:14,  7.12s/it]
  2%|▏         | 637/28080 [1:15:27<54:15:47,  7.12s/it]
                                                        
{'loss': 0.7678, 'learning_rate': 0.0003778173190984579, 'epoch': 0.27}

  2%|▏         | 637/28080 [1:15:27<54:15:47,  7.12s/it]
  2%|▏         | 638/28080 [1:15:34<54:16:45,  7.12s/it]
                                                        
{'loss': 0.7781, 'learning_rate': 0.00037841043890865956, 'epoch': 0.27}

  2%|▏         | 638/28080 [1:15:34<54:16:45,  7.12s/it]
  2%|▏         | 639/28080 [1:15:41<54:26:11,  7.14s/it]
                                                        
{'loss': 0.7848, 'learning_rate': 0.0003790035587188612, 'epoch': 0.27}

  2%|▏         | 639/28080 [1:15:41<54:26:11,  7.14s/it]
  2%|▏         | 640/28080 [1:15:48<54:20:59,  7.13s/it]
                                                        
{'loss': 0.7815, 'learning_rate': 0.00037959667852906285, 'epoch': 0.27}

  2%|▏         | 640/28080 [1:15:48<54:20:59,  7.13s/it]
  2%|▏         | 641/28080 [1:15:56<54:23:52,  7.14s/it]
                                                        
{'loss': 0.7647, 'learning_rate': 0.00038018979833926456, 'epoch': 0.27}

  2%|▏         | 641/28080 [1:15:56<54:23:52,  7.14s/it]
  2%|▏         | 642/28080 [1:16:03<54:09:58,  7.11s/it]
                                                        
{'loss': 0.7986, 'learning_rate': 0.0003807829181494662, 'epoch': 0.27}

  2%|▏         | 642/28080 [1:16:03<54:09:58,  7.11s/it]
  2%|▏         | 643/28080 [1:16:10<54:07:14,  7.10s/it]
                                                        
{'loss': 0.7766, 'learning_rate': 0.00038137603795966785, 'epoch': 0.27}

  2%|▏         | 643/28080 [1:16:10<54:07:14,  7.10s/it]
  2%|▏         | 644/28080 [1:16:17<54:05:28,  7.10s/it]
                                                        
{'loss': 0.7742, 'learning_rate': 0.0003819691577698695, 'epoch': 0.28}

  2%|▏         | 644/28080 [1:16:17<54:05:28,  7.10s/it]
  2%|▏         | 645/28080 [1:16:24<54:07:23,  7.10s/it]
                                                        
{'loss': 0.7726, 'learning_rate': 0.00038256227758007115, 'epoch': 0.28}

  2%|▏         | 645/28080 [1:16:24<54:07:23,  7.10s/it]
  2%|▏         | 646/28080 [1:16:31<54:09:58,  7.11s/it]
                                                        
{'loss': 0.779, 'learning_rate': 0.00038315539739027286, 'epoch': 0.28}

  2%|▏         | 646/28080 [1:16:31<54:09:58,  7.11s/it]
  2%|▏         | 647/28080 [1:16:38<54:12:33,  7.11s/it]
                                                        
{'loss': 0.7794, 'learning_rate': 0.0003837485172004745, 'epoch': 0.28}

  2%|▏         | 647/28080 [1:16:38<54:12:33,  7.11s/it]
  2%|▏         | 648/28080 [1:16:45<54:02:13,  7.09s/it]
                                                        
{'loss': 0.7788, 'learning_rate': 0.00038434163701067615, 'epoch': 0.28}

  2%|▏         | 648/28080 [1:16:45<54:02:13,  7.09s/it]
  2%|▏         | 649/28080 [1:16:52<54:01:50,  7.09s/it]
                                                        
{'loss': 0.7794, 'learning_rate': 0.0003849347568208778, 'epoch': 0.28}

  2%|▏         | 649/28080 [1:16:52<54:01:50,  7.09s/it]
  2%|▏         | 650/28080 [1:16:59<53:51:33,  7.07s/it]
                                                        
{'loss': 0.7868, 'learning_rate': 0.00038552787663107945, 'epoch': 0.28}

  2%|▏         | 650/28080 [1:16:59<53:51:33,  7.07s/it]
  2%|▏         | 651/28080 [1:17:06<53:59:17,  7.09s/it]
                                                        
{'loss': 0.7949, 'learning_rate': 0.0003861209964412811, 'epoch': 0.28}

  2%|▏         | 651/28080 [1:17:06<53:59:17,  7.09s/it]
  2%|▏         | 652/28080 [1:17:14<53:58:48,  7.09s/it]
                                                        
{'loss': 0.7891, 'learning_rate': 0.0003867141162514828, 'epoch': 0.28}

  2%|▏         | 652/28080 [1:17:14<53:58:48,  7.09s/it]
  2%|▏         | 653/28080 [1:17:21<54:05:15,  7.10s/it]
                                                        
{'loss': 0.7794, 'learning_rate': 0.00038730723606168445, 'epoch': 0.28}

  2%|▏         | 653/28080 [1:17:21<54:05:15,  7.10s/it]
  2%|▏         | 654/28080 [1:17:28<54:02:55,  7.09s/it]
                                                        
{'loss': 0.7757, 'learning_rate': 0.0003879003558718861, 'epoch': 0.28}

  2%|▏         | 654/28080 [1:17:28<54:02:55,  7.09s/it]
  2%|▏         | 655/28080 [1:17:35<53:59:13,  7.09s/it]
                                                        
{'loss': 0.7809, 'learning_rate': 0.0003884934756820878, 'epoch': 0.28}

  2%|▏         | 655/28080 [1:17:35<53:59:13,  7.09s/it]
  2%|▏         | 656/28080 [1:17:42<54:03:33,  7.10s/it]
                                                        
{'loss': 0.7725, 'learning_rate': 0.00038908659549228945, 'epoch': 0.28}

  2%|▏         | 656/28080 [1:17:42<54:03:33,  7.10s/it]
  2%|▏         | 657/28080 [1:17:49<53:46:12,  7.06s/it]
                                                        
{'loss': 0.7837, 'learning_rate': 0.00038967971530249116, 'epoch': 0.28}

  2%|▏         | 657/28080 [1:17:49<53:46:12,  7.06s/it]
  2%|▏         | 658/28080 [1:17:56<53:58:46,  7.09s/it]
                                                        
{'loss': 0.7783, 'learning_rate': 0.0003902728351126928, 'epoch': 0.28}

  2%|▏         | 658/28080 [1:17:56<53:58:46,  7.09s/it]
  2%|▏         | 659/28080 [1:18:03<54:07:43,  7.11s/it]
                                                        
{'loss': 0.7668, 'learning_rate': 0.00039086595492289445, 'epoch': 0.28}

  2%|▏         | 659/28080 [1:18:03<54:07:43,  7.11s/it]
  2%|▏         | 660/28080 [1:18:10<53:36:32,  7.04s/it]
                                                        
{'loss': 0.7793, 'learning_rate': 0.0003914590747330961, 'epoch': 0.28}

  2%|▏         | 660/28080 [1:18:10<53:36:32,  7.04s/it]
  2%|▏         | 661/28080 [1:18:17<53:36:28,  7.04s/it]
                                                        
{'loss': 0.7875, 'learning_rate': 0.00039205219454329775, 'epoch': 0.28}

  2%|▏         | 661/28080 [1:18:17<53:36:28,  7.04s/it]
  2%|▏         | 662/28080 [1:18:24<53:33:18,  7.03s/it]
                                                        
{'loss': 0.7757, 'learning_rate': 0.00039264531435349945, 'epoch': 0.28}

  2%|▏         | 662/28080 [1:18:24<53:33:18,  7.03s/it]
  2%|▏         | 663/28080 [1:18:31<53:56:14,  7.08s/it]
                                                        
{'loss': 0.7771, 'learning_rate': 0.0003932384341637011, 'epoch': 0.28}

  2%|▏         | 663/28080 [1:18:31<53:56:14,  7.08s/it]
  2%|▏         | 664/28080 [1:18:38<53:48:29,  7.07s/it]
                                                        
{'loss': 0.7782, 'learning_rate': 0.00039383155397390275, 'epoch': 0.28}

  2%|▏         | 664/28080 [1:18:38<53:48:29,  7.07s/it]
  2%|▏         | 665/28080 [1:18:45<53:44:42,  7.06s/it]
                                                        
{'loss': 0.7769, 'learning_rate': 0.0003944246737841044, 'epoch': 0.28}

  2%|▏         | 665/28080 [1:18:45<53:44:42,  7.06s/it]
  2%|▏         | 666/28080 [1:18:52<53:44:10,  7.06s/it]
                                                        
{'loss': 0.7714, 'learning_rate': 0.00039501779359430605, 'epoch': 0.28}

  2%|▏         | 666/28080 [1:18:52<53:44:10,  7.06s/it]
  2%|▏         | 667/28080 [1:19:00<53:44:00,  7.06s/it]
                                                        
{'loss': 0.7717, 'learning_rate': 0.0003956109134045077, 'epoch': 0.28}

  2%|▏         | 667/28080 [1:19:00<53:44:00,  7.06s/it]
  2%|▏         | 668/28080 [1:19:07<53:46:47,  7.06s/it]
                                                        
{'loss': 0.78, 'learning_rate': 0.0003962040332147094, 'epoch': 0.29}

  2%|▏         | 668/28080 [1:19:07<53:46:47,  7.06s/it]
  2%|▏         | 669/28080 [1:19:14<54:08:16,  7.11s/it]
                                                        
{'loss': 0.7649, 'learning_rate': 0.00039679715302491105, 'epoch': 0.29}

  2%|▏         | 669/28080 [1:19:14<54:08:16,  7.11s/it]
  2%|▏         | 670/28080 [1:19:21<54:20:42,  7.14s/it]
                                                        
{'loss': 0.7686, 'learning_rate': 0.0003973902728351127, 'epoch': 0.29}

  2%|▏         | 670/28080 [1:19:21<54:20:42,  7.14s/it]
  2%|▏         | 671/28080 [1:19:28<54:11:50,  7.12s/it]
                                                        
{'loss': 0.7824, 'learning_rate': 0.00039798339264531435, 'epoch': 0.29}

  2%|▏         | 671/28080 [1:19:28<54:11:50,  7.12s/it]
  2%|▏         | 672/28080 [1:19:35<54:14:32,  7.12s/it]
                                                        
{'loss': 0.757, 'learning_rate': 0.000398576512455516, 'epoch': 0.29}

  2%|▏         | 672/28080 [1:19:35<54:14:32,  7.12s/it]
  2%|▏         | 673/28080 [1:19:42<54:11:40,  7.12s/it]
                                                        
{'loss': 0.7703, 'learning_rate': 0.0003991696322657177, 'epoch': 0.29}

  2%|▏         | 673/28080 [1:19:42<54:11:40,  7.12s/it]
  2%|▏         | 674/28080 [1:19:49<53:59:11,  7.09s/it]
                                                        
{'loss': 0.7708, 'learning_rate': 0.00039976275207591935, 'epoch': 0.29}

  2%|▏         | 674/28080 [1:19:49<53:59:11,  7.09s/it]
  2%|▏         | 675/28080 [1:19:57<54:10:19,  7.12s/it]
                                                        
{'loss': 0.7621, 'learning_rate': 0.000400355871886121, 'epoch': 0.29}

  2%|▏         | 675/28080 [1:19:57<54:10:19,  7.12s/it]
  2%|▏         | 676/28080 [1:20:04<54:14:09,  7.12s/it]
                                                        
{'loss': 0.7506, 'learning_rate': 0.00040094899169632265, 'epoch': 0.29}

  2%|▏         | 676/28080 [1:20:04<54:14:09,  7.12s/it]
  2%|▏         | 677/28080 [1:20:11<54:00:31,  7.10s/it]
                                                        
{'loss': 0.7536, 'learning_rate': 0.0004015421115065243, 'epoch': 0.29}

  2%|▏         | 677/28080 [1:20:11<54:00:31,  7.10s/it]
  2%|▏         | 678/28080 [1:20:18<54:04:31,  7.10s/it]
                                                        
{'loss': 0.7538, 'learning_rate': 0.00040213523131672594, 'epoch': 0.29}

  2%|▏         | 678/28080 [1:20:18<54:04:31,  7.10s/it]
  2%|▏         | 679/28080 [1:20:25<54:06:26,  7.11s/it]
                                                        
{'loss': 0.7828, 'learning_rate': 0.00040272835112692765, 'epoch': 0.29}

  2%|▏         | 679/28080 [1:20:25<54:06:26,  7.11s/it]
  2%|▏         | 680/28080 [1:20:32<53:58:09,  7.09s/it]
                                                        
{'loss': 0.7555, 'learning_rate': 0.0004033214709371293, 'epoch': 0.29}

  2%|▏         | 680/28080 [1:20:32<53:58:09,  7.09s/it]
  2%|▏         | 681/28080 [1:20:39<54:05:42,  7.11s/it]
                                                        
{'loss': 0.7627, 'learning_rate': 0.00040391459074733094, 'epoch': 0.29}

  2%|▏         | 681/28080 [1:20:39<54:05:42,  7.11s/it]
  2%|▏         | 682/28080 [1:20:46<54:05:00,  7.11s/it]
                                                        
{'loss': 0.7676, 'learning_rate': 0.0004045077105575326, 'epoch': 0.29}

  2%|▏         | 682/28080 [1:20:46<54:05:00,  7.11s/it]
  2%|▏         | 683/28080 [1:20:53<54:04:39,  7.11s/it]
                                                        
{'loss': 0.7741, 'learning_rate': 0.00040510083036773424, 'epoch': 0.29}

  2%|▏         | 683/28080 [1:20:53<54:04:39,  7.11s/it]
  2%|▏         | 684/28080 [1:21:01<54:09:17,  7.12s/it]
                                                        
{'loss': 0.7597, 'learning_rate': 0.000405693950177936, 'epoch': 0.29}

  2%|▏         | 684/28080 [1:21:01<54:09:17,  7.12s/it]
  2%|▏         | 685/28080 [1:21:08<54:07:57,  7.11s/it]
                                                        
{'loss': 0.7793, 'learning_rate': 0.00040628706998813765, 'epoch': 0.29}

  2%|▏         | 685/28080 [1:21:08<54:07:57,  7.11s/it]
  2%|▏         | 686/28080 [1:21:15<53:58:50,  7.09s/it]
                                                        
{'loss': 0.7955, 'learning_rate': 0.0004068801897983393, 'epoch': 0.29}

  2%|▏         | 686/28080 [1:21:15<53:58:50,  7.09s/it]
  2%|▏         | 687/28080 [1:21:22<53:55:57,  7.09s/it]
                                                        
{'loss': 0.7889, 'learning_rate': 0.00040747330960854095, 'epoch': 0.29}

  2%|▏         | 687/28080 [1:21:22<53:55:57,  7.09s/it]
  2%|▏         | 688/28080 [1:21:29<54:00:17,  7.10s/it]
                                                        
{'loss': 0.7894, 'learning_rate': 0.0004080664294187426, 'epoch': 0.29}

  2%|▏         | 688/28080 [1:21:29<54:00:17,  7.10s/it]
  2%|▏         | 689/28080 [1:21:36<54:00:00,  7.10s/it]
                                                        
{'loss': 0.7669, 'learning_rate': 0.0004086595492289443, 'epoch': 0.29}

  2%|▏         | 689/28080 [1:21:36<54:00:00,  7.10s/it]
  2%|▏         | 690/28080 [1:21:43<54:12:41,  7.13s/it]
                                                        
{'loss': 0.7587, 'learning_rate': 0.00040925266903914595, 'epoch': 0.29}

  2%|▏         | 690/28080 [1:21:43<54:12:41,  7.13s/it]
  2%|▏         | 691/28080 [1:21:50<54:22:20,  7.15s/it]
                                                        
{'loss': 0.7821, 'learning_rate': 0.0004098457888493476, 'epoch': 0.3}

  2%|▏         | 691/28080 [1:21:50<54:22:20,  7.15s/it]
  2%|▏         | 692/28080 [1:21:58<54:23:06,  7.15s/it]
                                                        
{'loss': 0.7695, 'learning_rate': 0.00041043890865954924, 'epoch': 0.3}

  2%|▏         | 692/28080 [1:21:58<54:23:06,  7.15s/it]
  2%|▏         | 693/28080 [1:22:05<54:15:51,  7.13s/it]
                                                        
{'loss': 0.7719, 'learning_rate': 0.0004110320284697509, 'epoch': 0.3}

  2%|▏         | 693/28080 [1:22:05<54:15:51,  7.13s/it]
  2%|▏         | 694/28080 [1:22:12<53:52:07,  7.08s/it]
                                                        
{'loss': 0.7946, 'learning_rate': 0.00041162514827995254, 'epoch': 0.3}

  2%|▏         | 694/28080 [1:22:12<53:52:07,  7.08s/it]
  2%|▏         | 695/28080 [1:22:19<53:47:49,  7.07s/it]
                                                        
{'loss': 0.7603, 'learning_rate': 0.00041221826809015425, 'epoch': 0.3}

  2%|▏         | 695/28080 [1:22:19<53:47:49,  7.07s/it]
  2%|▏         | 696/28080 [1:22:26<53:42:37,  7.06s/it]
                                                        
{'loss': 0.7801, 'learning_rate': 0.0004128113879003559, 'epoch': 0.3}

  2%|▏         | 696/28080 [1:22:26<53:42:37,  7.06s/it]
  2%|▏         | 697/28080 [1:22:33<53:56:12,  7.09s/it]
                                                        
{'loss': 0.7632, 'learning_rate': 0.00041340450771055754, 'epoch': 0.3}

  2%|▏         | 697/28080 [1:22:33<53:56:12,  7.09s/it]
  2%|▏         | 698/28080 [1:22:40<54:03:33,  7.11s/it]
                                                        
{'loss': 0.7524, 'learning_rate': 0.0004139976275207592, 'epoch': 0.3}

  2%|▏         | 698/28080 [1:22:40<54:03:33,  7.11s/it]
  2%|▏         | 699/28080 [1:22:47<53:56:40,  7.09s/it]
                                                        
{'loss': 0.7918, 'learning_rate': 0.00041459074733096084, 'epoch': 0.3}

  2%|▏         | 699/28080 [1:22:47<53:56:40,  7.09s/it]
  2%|▏         | 700/28080 [1:22:54<53:53:42,  7.09s/it]
                                                        
{'loss': 0.7676, 'learning_rate': 0.00041518386714116254, 'epoch': 0.3}

  2%|▏         | 700/28080 [1:22:54<53:53:42,  7.09s/it]
  2%|▏         | 701/28080 [1:23:01<53:47:21,  7.07s/it]
                                                        
{'loss': 0.768, 'learning_rate': 0.0004157769869513642, 'epoch': 0.3}

  2%|▏         | 701/28080 [1:23:01<53:47:21,  7.07s/it]
  2%|▎         | 702/28080 [1:23:08<53:44:16,  7.07s/it]
                                                        
{'loss': 0.7689, 'learning_rate': 0.00041637010676156584, 'epoch': 0.3}

  2%|▎         | 702/28080 [1:23:08<53:44:16,  7.07s/it]
  3%|▎         | 703/28080 [1:23:15<53:42:55,  7.06s/it]
                                                        
{'loss': 0.762, 'learning_rate': 0.0004169632265717675, 'epoch': 0.3}

  3%|▎         | 703/28080 [1:23:15<53:42:55,  7.06s/it]
  3%|▎         | 704/28080 [1:23:22<53:54:21,  7.09s/it]
                                                        
{'loss': 0.7666, 'learning_rate': 0.00041755634638196914, 'epoch': 0.3}

  3%|▎         | 704/28080 [1:23:22<53:54:21,  7.09s/it]
  3%|▎         | 705/28080 [1:23:30<54:02:25,  7.11s/it]
                                                        
{'loss': 0.7738, 'learning_rate': 0.0004181494661921708, 'epoch': 0.3}

  3%|▎         | 705/28080 [1:23:30<54:02:25,  7.11s/it]
  3%|▎         | 706/28080 [1:23:37<54:00:53,  7.10s/it]
                                                        
{'loss': 0.7699, 'learning_rate': 0.0004187425860023725, 'epoch': 0.3}

  3%|▎         | 706/28080 [1:23:37<54:00:53,  7.10s/it]
  3%|▎         | 707/28080 [1:23:44<53:42:13,  7.06s/it]
                                                        
{'loss': 0.7821, 'learning_rate': 0.00041933570581257414, 'epoch': 0.3}

  3%|▎         | 707/28080 [1:23:44<53:42:13,  7.06s/it]
  3%|▎         | 708/28080 [1:23:51<53:53:43,  7.09s/it]
                                                        
{'loss': 0.7742, 'learning_rate': 0.0004199288256227758, 'epoch': 0.3}

  3%|▎         | 708/28080 [1:23:51<53:53:43,  7.09s/it]
  3%|▎         | 709/28080 [1:23:58<53:54:06,  7.09s/it]
                                                        
{'loss': 0.7727, 'learning_rate': 0.00042052194543297744, 'epoch': 0.3}

  3%|▎         | 709/28080 [1:23:58<53:54:06,  7.09s/it]
  3%|▎         | 710/28080 [1:24:05<54:02:43,  7.11s/it]
                                                        
{'loss': 0.7552, 'learning_rate': 0.0004211150652431791, 'epoch': 0.3}

  3%|▎         | 710/28080 [1:24:05<54:02:43,  7.11s/it]
  3%|▎         | 711/28080 [1:24:12<53:55:27,  7.09s/it]
                                                        
{'loss': 0.7546, 'learning_rate': 0.0004217081850533808, 'epoch': 0.3}

  3%|▎         | 711/28080 [1:24:12<53:55:27,  7.09s/it]
  3%|▎         | 712/28080 [1:24:19<53:58:16,  7.10s/it]
                                                        
{'loss': 0.7613, 'learning_rate': 0.00042230130486358244, 'epoch': 0.3}

  3%|▎         | 712/28080 [1:24:19<53:58:16,  7.10s/it]
  3%|▎         | 713/28080 [1:24:26<53:38:21,  7.06s/it]
                                                        
{'loss': 0.7784, 'learning_rate': 0.00042289442467378414, 'epoch': 0.3}

  3%|▎         | 713/28080 [1:24:26<53:38:21,  7.06s/it]
  3%|▎         | 714/28080 [1:24:33<53:34:34,  7.05s/it]
                                                        
{'loss': 0.7592, 'learning_rate': 0.0004234875444839858, 'epoch': 0.31}

  3%|▎         | 714/28080 [1:24:33<53:34:34,  7.05s/it]
  3%|▎         | 715/28080 [1:24:40<53:58:48,  7.10s/it]
                                                        
{'loss': 0.7709, 'learning_rate': 0.00042408066429418744, 'epoch': 0.31}

  3%|▎         | 715/28080 [1:24:40<53:58:48,  7.10s/it]
  3%|▎         | 716/28080 [1:24:47<53:57:36,  7.10s/it]
                                                        
{'loss': 0.764, 'learning_rate': 0.00042467378410438914, 'epoch': 0.31}

  3%|▎         | 716/28080 [1:24:47<53:57:36,  7.10s/it]
  3%|▎         | 717/28080 [1:24:55<54:08:30,  7.12s/it]
                                                        
{'loss': 0.7632, 'learning_rate': 0.0004252669039145908, 'epoch': 0.31}

  3%|▎         | 717/28080 [1:24:55<54:08:30,  7.12s/it]
  3%|▎         | 718/28080 [1:25:02<53:59:59,  7.10s/it]
                                                        
{'loss': 0.7546, 'learning_rate': 0.00042586002372479244, 'epoch': 0.31}

  3%|▎         | 718/28080 [1:25:02<53:59:59,  7.10s/it]
  3%|▎         | 719/28080 [1:25:09<54:13:27,  7.13s/it]
                                                        
{'loss': 0.7654, 'learning_rate': 0.0004264531435349941, 'epoch': 0.31}

  3%|▎         | 719/28080 [1:25:09<54:13:27,  7.13s/it]
  3%|▎         | 720/28080 [1:25:16<54:11:33,  7.13s/it]
                                                        
{'loss': 0.7503, 'learning_rate': 0.00042704626334519574, 'epoch': 0.31}

  3%|▎         | 720/28080 [1:25:16<54:11:33,  7.13s/it]
  3%|▎         | 721/28080 [1:25:23<54:04:47,  7.12s/it]
                                                        
{'loss': 0.7786, 'learning_rate': 0.0004276393831553974, 'epoch': 0.31}

  3%|▎         | 721/28080 [1:25:23<54:04:47,  7.12s/it]
  3%|▎         | 722/28080 [1:25:30<53:54:54,  7.09s/it]
                                                        
{'loss': 0.7798, 'learning_rate': 0.0004282325029655991, 'epoch': 0.31}

  3%|▎         | 722/28080 [1:25:30<53:54:54,  7.09s/it]
  3%|▎         | 723/28080 [1:25:37<53:55:17,  7.10s/it]
                                                        
{'loss': 0.769, 'learning_rate': 0.00042882562277580074, 'epoch': 0.31}

  3%|▎         | 723/28080 [1:25:37<53:55:17,  7.10s/it]
  3%|▎         | 724/28080 [1:25:44<53:54:47,  7.09s/it]
                                                        
{'loss': 0.7678, 'learning_rate': 0.0004294187425860024, 'epoch': 0.31}

  3%|▎         | 724/28080 [1:25:44<53:54:47,  7.09s/it]
  3%|▎         | 725/28080 [1:25:51<53:59:02,  7.10s/it]
                                                        
{'loss': 0.7735, 'learning_rate': 0.00043001186239620404, 'epoch': 0.31}

  3%|▎         | 725/28080 [1:25:51<53:59:02,  7.10s/it]
  3%|▎         | 726/28080 [1:25:59<53:52:23,  7.09s/it]
                                                        
{'loss': 0.7842, 'learning_rate': 0.0004306049822064057, 'epoch': 0.31}

  3%|▎         | 726/28080 [1:25:59<53:52:23,  7.09s/it]
  3%|▎         | 727/28080 [1:26:06<53:57:15,  7.10s/it]
                                                        
{'loss': 0.7514, 'learning_rate': 0.0004311981020166074, 'epoch': 0.31}

  3%|▎         | 727/28080 [1:26:06<53:57:15,  7.10s/it]
  3%|▎         | 728/28080 [1:26:13<53:58:47,  7.10s/it]
                                                        
{'loss': 0.7969, 'learning_rate': 0.00043179122182680904, 'epoch': 0.31}

  3%|▎         | 728/28080 [1:26:13<53:58:47,  7.10s/it]
  3%|▎         | 729/28080 [1:26:20<53:50:49,  7.09s/it]
                                                        
{'loss': 0.7914, 'learning_rate': 0.0004323843416370107, 'epoch': 0.31}

  3%|▎         | 729/28080 [1:26:20<53:50:49,  7.09s/it]
  3%|▎         | 730/28080 [1:26:27<53:36:54,  7.06s/it]
                                                        
{'loss': 0.7711, 'learning_rate': 0.00043297746144721233, 'epoch': 0.31}

  3%|▎         | 730/28080 [1:26:27<53:36:54,  7.06s/it]
  3%|▎         | 731/28080 [1:26:34<53:49:18,  7.08s/it]
                                                        
{'loss': 0.7603, 'learning_rate': 0.000433570581257414, 'epoch': 0.31}

  3%|▎         | 731/28080 [1:26:34<53:49:18,  7.08s/it]
  3%|▎         | 732/28080 [1:26:41<54:03:01,  7.12s/it]
                                                        
{'loss': 0.7611, 'learning_rate': 0.00043416370106761563, 'epoch': 0.31}

  3%|▎         | 732/28080 [1:26:41<54:03:01,  7.12s/it]
  3%|▎         | 733/28080 [1:26:48<53:53:02,  7.09s/it]
                                                        
{'loss': 0.7628, 'learning_rate': 0.00043475682087781734, 'epoch': 0.31}

  3%|▎         | 733/28080 [1:26:48<53:53:02,  7.09s/it]
  3%|▎         | 734/28080 [1:26:55<54:00:52,  7.11s/it]
                                                        
{'loss': 0.7521, 'learning_rate': 0.000435349940688019, 'epoch': 0.31}

  3%|▎         | 734/28080 [1:26:55<54:00:52,  7.11s/it]
  3%|▎         | 735/28080 [1:27:02<53:57:08,  7.10s/it]
                                                        
{'loss': 0.7638, 'learning_rate': 0.00043594306049822063, 'epoch': 0.31}

  3%|▎         | 735/28080 [1:27:02<53:57:08,  7.10s/it]
  3%|▎         | 736/28080 [1:27:10<53:56:33,  7.10s/it]
                                                        
{'loss': 0.7454, 'learning_rate': 0.0004365361803084223, 'epoch': 0.31}

  3%|▎         | 736/28080 [1:27:10<53:56:33,  7.10s/it]
  3%|▎         | 737/28080 [1:27:17<53:53:08,  7.09s/it]
                                                        
{'loss': 0.7694, 'learning_rate': 0.00043712930011862393, 'epoch': 0.31}

  3%|▎         | 737/28080 [1:27:17<53:53:08,  7.09s/it]
  3%|▎         | 738/28080 [1:27:24<54:02:37,  7.12s/it]
                                                        
{'loss': 0.7585, 'learning_rate': 0.00043772241992882563, 'epoch': 0.32}

  3%|▎         | 738/28080 [1:27:24<54:02:37,  7.12s/it]
  3%|▎         | 739/28080 [1:27:31<53:55:00,  7.10s/it]
                                                        
{'loss': 0.7428, 'learning_rate': 0.0004383155397390273, 'epoch': 0.32}

  3%|▎         | 739/28080 [1:27:31<53:55:00,  7.10s/it]
  3%|▎         | 740/28080 [1:27:38<53:52:31,  7.09s/it]
                                                        
{'loss': 0.7659, 'learning_rate': 0.00043890865954922893, 'epoch': 0.32}

  3%|▎         | 740/28080 [1:27:38<53:52:31,  7.09s/it]
  3%|▎         | 741/28080 [1:27:45<53:54:05,  7.10s/it]
                                                        
{'loss': 0.7567, 'learning_rate': 0.0004395017793594306, 'epoch': 0.32}

  3%|▎         | 741/28080 [1:27:45<53:54:05,  7.10s/it]
  3%|▎         | 742/28080 [1:27:52<54:04:12,  7.12s/it]
                                                        
{'loss': 0.771, 'learning_rate': 0.0004400948991696323, 'epoch': 0.32}

  3%|▎         | 742/28080 [1:27:52<54:04:12,  7.12s/it]
  3%|▎         | 743/28080 [1:27:59<54:05:42,  7.12s/it]
                                                        
{'loss': 0.7543, 'learning_rate': 0.000440688018979834, 'epoch': 0.32}

  3%|▎         | 743/28080 [1:27:59<54:05:42,  7.12s/it]
  3%|▎         | 744/28080 [1:28:06<54:00:39,  7.11s/it]
                                                        
{'loss': 0.7585, 'learning_rate': 0.00044128113879003564, 'epoch': 0.32}

  3%|▎         | 744/28080 [1:28:06<54:00:39,  7.11s/it]
  3%|▎         | 745/28080 [1:28:13<53:53:19,  7.10s/it]
                                                        
{'loss': 0.7689, 'learning_rate': 0.0004418742586002373, 'epoch': 0.32}

  3%|▎         | 745/28080 [1:28:13<53:53:19,  7.10s/it]
  3%|▎         | 746/28080 [1:28:21<53:56:38,  7.10s/it]
                                                        
{'loss': 0.7794, 'learning_rate': 0.00044246737841043893, 'epoch': 0.32}

  3%|▎         | 746/28080 [1:28:21<53:56:38,  7.10s/it]
  3%|▎         | 747/28080 [1:28:28<53:49:19,  7.09s/it]
                                                        
{'loss': 0.7724, 'learning_rate': 0.0004430604982206406, 'epoch': 0.32}

  3%|▎         | 747/28080 [1:28:28<53:49:19,  7.09s/it]
  3%|▎         | 748/28080 [1:28:35<53:42:32,  7.07s/it]
                                                        
{'loss': 0.78, 'learning_rate': 0.00044365361803084223, 'epoch': 0.32}

  3%|▎         | 748/28080 [1:28:35<53:42:32,  7.07s/it]
  3%|▎         | 749/28080 [1:28:42<53:46:48,  7.08s/it]
                                                        
{'loss': 0.7716, 'learning_rate': 0.00044424673784104393, 'epoch': 0.32}

  3%|▎         | 749/28080 [1:28:42<53:46:48,  7.08s/it]
  3%|▎         | 750/28080 [1:28:49<54:10:57,  7.14s/it]
                                                        
{'loss': 0.7704, 'learning_rate': 0.0004448398576512456, 'epoch': 0.32}

  3%|▎         | 750/28080 [1:28:49<54:10:57,  7.14s/it]
  3%|▎         | 751/28080 [1:28:56<54:07:26,  7.13s/it]
                                                        
{'loss': 0.7517, 'learning_rate': 0.00044543297746144723, 'epoch': 0.32}

  3%|▎         | 751/28080 [1:28:56<54:07:26,  7.13s/it]
  3%|▎         | 752/28080 [1:29:03<54:05:10,  7.12s/it]
                                                        
{'loss': 0.7791, 'learning_rate': 0.0004460260972716489, 'epoch': 0.32}

  3%|▎         | 752/28080 [1:29:03<54:05:10,  7.12s/it]
  3%|▎         | 753/28080 [1:29:10<54:10:54,  7.14s/it]
                                                        
{'loss': 0.7545, 'learning_rate': 0.00044661921708185053, 'epoch': 0.32}

  3%|▎         | 753/28080 [1:29:10<54:10:54,  7.14s/it]
  3%|▎         | 754/28080 [1:29:18<54:03:23,  7.12s/it]
                                                        
{'loss': 0.7767, 'learning_rate': 0.00044721233689205223, 'epoch': 0.32}

  3%|▎         | 754/28080 [1:29:18<54:03:23,  7.12s/it]
  3%|▎         | 755/28080 [1:29:25<53:52:58,  7.10s/it]
                                                        
{'loss': 0.7519, 'learning_rate': 0.0004478054567022539, 'epoch': 0.32}

  3%|▎         | 755/28080 [1:29:25<53:52:58,  7.10s/it]
  3%|▎         | 756/28080 [1:29:32<53:49:22,  7.09s/it]
                                                        
{'loss': 0.7684, 'learning_rate': 0.00044839857651245553, 'epoch': 0.32}

  3%|▎         | 756/28080 [1:29:32<53:49:22,  7.09s/it]
  3%|▎         | 757/28080 [1:29:39<53:57:25,  7.11s/it]
                                                        
{'loss': 0.7496, 'learning_rate': 0.0004489916963226572, 'epoch': 0.32}

  3%|▎         | 757/28080 [1:29:39<53:57:25,  7.11s/it]
  3%|▎         | 758/28080 [1:29:46<53:55:15,  7.10s/it]
                                                        
{'loss': 0.7478, 'learning_rate': 0.00044958481613285883, 'epoch': 0.32}

  3%|▎         | 758/28080 [1:29:46<53:55:15,  7.10s/it]
  3%|▎         | 759/28080 [1:29:53<53:49:56,  7.09s/it]
                                                        
{'loss': 0.7646, 'learning_rate': 0.0004501779359430605, 'epoch': 0.32}

  3%|▎         | 759/28080 [1:29:53<53:49:56,  7.09s/it]
  3%|▎         | 760/28080 [1:30:00<53:46:36,  7.09s/it]
                                                        
{'loss': 0.7919, 'learning_rate': 0.0004507710557532622, 'epoch': 0.32}

  3%|▎         | 760/28080 [1:30:00<53:46:36,  7.09s/it]
  3%|▎         | 761/28080 [1:30:07<53:45:42,  7.08s/it]
                                                        
{'loss': 0.7699, 'learning_rate': 0.00045136417556346383, 'epoch': 0.33}

  3%|▎         | 761/28080 [1:30:07<53:45:42,  7.08s/it]
  3%|▎         | 762/28080 [1:30:14<53:57:08,  7.11s/it]
                                                        
{'loss': 0.7594, 'learning_rate': 0.0004519572953736655, 'epoch': 0.33}

  3%|▎         | 762/28080 [1:30:14<53:57:08,  7.11s/it]
  3%|▎         | 763/28080 [1:30:21<53:47:20,  7.09s/it]
                                                        
{'loss': 0.7603, 'learning_rate': 0.0004525504151838671, 'epoch': 0.33}

  3%|▎         | 763/28080 [1:30:21<53:47:20,  7.09s/it]
  3%|▎         | 764/28080 [1:30:28<53:48:00,  7.09s/it]
                                                        
{'loss': 0.7541, 'learning_rate': 0.0004531435349940688, 'epoch': 0.33}

  3%|▎         | 764/28080 [1:30:28<53:48:00,  7.09s/it]
  3%|▎         | 765/28080 [1:30:35<53:47:32,  7.09s/it]
                                                        
{'loss': 0.7657, 'learning_rate': 0.0004537366548042705, 'epoch': 0.33}

  3%|▎         | 765/28080 [1:30:35<53:47:32,  7.09s/it]
  3%|▎         | 766/28080 [1:30:43<53:39:54,  7.07s/it]
                                                        
{'loss': 0.7528, 'learning_rate': 0.00045432977461447213, 'epoch': 0.33}

  3%|▎         | 766/28080 [1:30:43<53:39:54,  7.07s/it]
  3%|▎         | 767/28080 [1:30:50<53:31:30,  7.05s/it]
                                                        
{'loss': 0.7777, 'learning_rate': 0.0004549228944246738, 'epoch': 0.33}

  3%|▎         | 767/28080 [1:30:50<53:31:30,  7.05s/it]
  3%|▎         | 768/28080 [1:30:57<53:41:06,  7.08s/it]
                                                        
{'loss': 0.7505, 'learning_rate': 0.0004555160142348754, 'epoch': 0.33}

  3%|▎         | 768/28080 [1:30:57<53:41:06,  7.08s/it]
  3%|▎         | 769/28080 [1:31:04<53:38:45,  7.07s/it]
                                                        
{'loss': 0.7671, 'learning_rate': 0.0004561091340450771, 'epoch': 0.33}

  3%|▎         | 769/28080 [1:31:04<53:38:45,  7.07s/it]
  3%|▎         | 770/28080 [1:31:11<53:42:13,  7.08s/it]
                                                        
{'loss': 0.7685, 'learning_rate': 0.0004567022538552787, 'epoch': 0.33}

  3%|▎         | 770/28080 [1:31:11<53:42:13,  7.08s/it]
  3%|▎         | 771/28080 [1:31:18<53:48:34,  7.09s/it]
                                                        
{'loss': 0.7402, 'learning_rate': 0.0004572953736654805, 'epoch': 0.33}

  3%|▎         | 771/28080 [1:31:18<53:48:34,  7.09s/it]
  3%|▎         | 772/28080 [1:31:25<53:39:57,  7.07s/it]
                                                        
{'loss': 0.7924, 'learning_rate': 0.00045788849347568213, 'epoch': 0.33}

  3%|▎         | 772/28080 [1:31:25<53:39:57,  7.07s/it]
  3%|▎         | 773/28080 [1:31:32<53:35:54,  7.07s/it]
                                                        
{'loss': 0.7466, 'learning_rate': 0.0004584816132858838, 'epoch': 0.33}

  3%|▎         | 773/28080 [1:31:32<53:35:54,  7.07s/it]
  3%|▎         | 774/28080 [1:31:39<53:34:06,  7.06s/it]
                                                        
{'loss': 0.7695, 'learning_rate': 0.0004590747330960854, 'epoch': 0.33}

  3%|▎         | 774/28080 [1:31:39<53:34:06,  7.06s/it]
  3%|▎         | 775/28080 [1:31:46<53:33:33,  7.06s/it]
                                                        
{'loss': 0.7599, 'learning_rate': 0.0004596678529062871, 'epoch': 0.33}

  3%|▎         | 775/28080 [1:31:46<53:33:33,  7.06s/it]
  3%|▎         | 776/28080 [1:31:53<53:58:15,  7.12s/it]
                                                        
{'loss': 0.7798, 'learning_rate': 0.0004602609727164888, 'epoch': 0.33}

  3%|▎         | 776/28080 [1:31:53<53:58:15,  7.12s/it]
  3%|▎         | 777/28080 [1:32:01<54:06:27,  7.13s/it]
                                                        
{'loss': 0.7553, 'learning_rate': 0.00046085409252669043, 'epoch': 0.33}

  3%|▎         | 777/28080 [1:32:01<54:06:27,  7.13s/it]
  3%|▎         | 778/28080 [1:32:08<54:09:22,  7.14s/it]
                                                        
{'loss': 0.7634, 'learning_rate': 0.0004614472123368921, 'epoch': 0.33}

  3%|▎         | 778/28080 [1:32:08<54:09:22,  7.14s/it]
  3%|▎         | 779/28080 [1:32:15<54:01:25,  7.12s/it]
                                                        
{'loss': 0.7668, 'learning_rate': 0.0004620403321470937, 'epoch': 0.33}

  3%|▎         | 779/28080 [1:32:15<54:01:25,  7.12s/it]
  3%|▎         | 780/28080 [1:32:22<54:04:56,  7.13s/it]
                                                        
{'loss': 0.7771, 'learning_rate': 0.0004626334519572954, 'epoch': 0.33}

  3%|▎         | 780/28080 [1:32:22<54:04:56,  7.13s/it]
  3%|▎         | 781/28080 [1:32:29<53:54:31,  7.11s/it]
                                                        
{'loss': 0.7594, 'learning_rate': 0.0004632265717674971, 'epoch': 0.33}

  3%|▎         | 781/28080 [1:32:29<53:54:31,  7.11s/it]
  3%|▎         | 782/28080 [1:32:36<53:57:01,  7.11s/it]
                                                        
{'loss': 0.7467, 'learning_rate': 0.0004638196915776987, 'epoch': 0.33}

  3%|▎         | 782/28080 [1:32:36<53:57:01,  7.11s/it]
  3%|▎         | 783/28080 [1:32:43<53:47:02,  7.09s/it]
                                                        
{'loss': 0.7559, 'learning_rate': 0.0004644128113879004, 'epoch': 0.33}

  3%|▎         | 783/28080 [1:32:43<53:47:02,  7.09s/it]
  3%|▎         | 784/28080 [1:32:50<53:43:31,  7.09s/it]
                                                        
{'loss': 0.7516, 'learning_rate': 0.000465005931198102, 'epoch': 0.33}

  3%|▎         | 784/28080 [1:32:50<53:43:31,  7.09s/it]
  3%|▎         | 785/28080 [1:32:57<53:36:59,  7.07s/it]
                                                        
{'loss': 0.7818, 'learning_rate': 0.00046559905100830367, 'epoch': 0.34}

  3%|▎         | 785/28080 [1:32:57<53:36:59,  7.07s/it]
  3%|▎         | 786/28080 [1:33:04<53:47:53,  7.10s/it]
                                                        
{'loss': 0.7561, 'learning_rate': 0.0004661921708185053, 'epoch': 0.34}

  3%|▎         | 786/28080 [1:33:04<53:47:53,  7.10s/it]
  3%|▎         | 787/28080 [1:33:12<53:44:53,  7.09s/it]
                                                        
{'loss': 0.7584, 'learning_rate': 0.000466785290628707, 'epoch': 0.34}

  3%|▎         | 787/28080 [1:33:12<53:44:53,  7.09s/it]
  3%|▎         | 788/28080 [1:33:19<53:45:15,  7.09s/it]
                                                        
{'loss': 0.747, 'learning_rate': 0.0004673784104389087, 'epoch': 0.34}

  3%|▎         | 788/28080 [1:33:19<53:45:15,  7.09s/it]
  3%|▎         | 789/28080 [1:33:26<53:47:10,  7.10s/it]
                                                        
{'loss': 0.7404, 'learning_rate': 0.0004679715302491103, 'epoch': 0.34}

  3%|▎         | 789/28080 [1:33:26<53:47:10,  7.10s/it]
  3%|▎         | 790/28080 [1:33:33<53:36:05,  7.07s/it]
                                                        
{'loss': 0.7509, 'learning_rate': 0.00046856465005931197, 'epoch': 0.34}

  3%|▎         | 790/28080 [1:33:33<53:36:05,  7.07s/it]
  3%|▎         | 791/28080 [1:33:40<53:40:14,  7.08s/it]
                                                        
{'loss': 0.761, 'learning_rate': 0.0004691577698695136, 'epoch': 0.34}

  3%|▎         | 791/28080 [1:33:40<53:40:14,  7.08s/it]
  3%|▎         | 792/28080 [1:33:47<53:46:27,  7.09s/it]
                                                        
{'loss': 0.7719, 'learning_rate': 0.0004697508896797153, 'epoch': 0.34}

  3%|▎         | 792/28080 [1:33:47<53:46:27,  7.09s/it]
  3%|▎         | 793/28080 [1:33:54<53:40:31,  7.08s/it]
                                                        
{'loss': 0.777, 'learning_rate': 0.00047034400948991697, 'epoch': 0.34}

  3%|▎         | 793/28080 [1:33:54<53:40:31,  7.08s/it]
  3%|▎         | 794/28080 [1:34:01<53:51:19,  7.11s/it]
                                                        
{'loss': 0.7638, 'learning_rate': 0.0004709371293001186, 'epoch': 0.34}

  3%|▎         | 794/28080 [1:34:01<53:51:19,  7.11s/it]
  3%|▎         | 795/28080 [1:34:08<53:52:59,  7.11s/it]
                                                        
{'loss': 0.7649, 'learning_rate': 0.00047153024911032027, 'epoch': 0.34}

  3%|▎         | 795/28080 [1:34:08<53:52:59,  7.11s/it]
  3%|▎         | 796/28080 [1:34:15<53:58:18,  7.12s/it]
                                                        
{'loss': 0.7519, 'learning_rate': 0.0004721233689205219, 'epoch': 0.34}

  3%|▎         | 796/28080 [1:34:15<53:58:18,  7.12s/it]
  3%|▎         | 797/28080 [1:34:22<53:38:02,  7.08s/it]
                                                        
{'loss': 0.7588, 'learning_rate': 0.00047271648873072357, 'epoch': 0.34}

  3%|▎         | 797/28080 [1:34:22<53:38:02,  7.08s/it]
  3%|▎         | 798/28080 [1:34:29<53:38:23,  7.08s/it]
                                                        
{'loss': 0.775, 'learning_rate': 0.00047330960854092527, 'epoch': 0.34}

  3%|▎         | 798/28080 [1:34:29<53:38:23,  7.08s/it]
  3%|▎         | 799/28080 [1:34:37<53:30:09,  7.06s/it]
                                                        
{'loss': 0.744, 'learning_rate': 0.0004739027283511269, 'epoch': 0.34}

  3%|▎         | 799/28080 [1:34:37<53:30:09,  7.06s/it]
  3%|▎         | 800/28080 [1:34:44<53:25:37,  7.05s/it]
                                                        
{'loss': 0.7643, 'learning_rate': 0.0004744958481613286, 'epoch': 0.34}

  3%|▎         | 800/28080 [1:34:44<53:25:37,  7.05s/it]
  3%|▎         | 801/28080 [1:34:51<53:40:27,  7.08s/it]
                                                        
{'loss': 0.7585, 'learning_rate': 0.00047508896797153027, 'epoch': 0.34}

  3%|▎         | 801/28080 [1:34:51<53:40:27,  7.08s/it]
  3%|▎         | 802/28080 [1:34:58<53:51:50,  7.11s/it]
                                                        
{'loss': 0.7453, 'learning_rate': 0.0004756820877817319, 'epoch': 0.34}

  3%|▎         | 802/28080 [1:34:58<53:51:50,  7.11s/it]
  3%|▎         | 803/28080 [1:35:05<53:47:27,  7.10s/it]
                                                        
{'loss': 0.7586, 'learning_rate': 0.0004762752075919336, 'epoch': 0.34}

  3%|▎         | 803/28080 [1:35:05<53:47:27,  7.10s/it]
  3%|▎         | 804/28080 [1:35:12<53:52:37,  7.11s/it]
                                                        
{'loss': 0.7789, 'learning_rate': 0.00047686832740213527, 'epoch': 0.34}

  3%|▎         | 804/28080 [1:35:12<53:52:37,  7.11s/it]
  3%|▎         | 805/28080 [1:35:19<53:46:09,  7.10s/it]
                                                        
{'loss': 0.779, 'learning_rate': 0.0004774614472123369, 'epoch': 0.34}

  3%|▎         | 805/28080 [1:35:19<53:46:09,  7.10s/it]
  3%|▎         | 806/28080 [1:35:26<54:00:15,  7.13s/it]
                                                        
{'loss': 0.7554, 'learning_rate': 0.00047805456702253857, 'epoch': 0.34}

  3%|▎         | 806/28080 [1:35:26<54:00:15,  7.13s/it]
  3%|▎         | 807/28080 [1:35:33<54:03:20,  7.14s/it]
                                                        
{'loss': 0.7527, 'learning_rate': 0.0004786476868327402, 'epoch': 0.34}

  3%|▎         | 807/28080 [1:35:33<54:03:20,  7.14s/it]
  3%|▎         | 808/28080 [1:35:41<54:18:41,  7.17s/it]
                                                        
{'loss': 0.7659, 'learning_rate': 0.0004792408066429419, 'epoch': 0.35}

  3%|▎         | 808/28080 [1:35:41<54:18:41,  7.17s/it]
  3%|▎         | 809/28080 [1:35:48<54:09:55,  7.15s/it]
                                                        
{'loss': 0.7624, 'learning_rate': 0.00047983392645314357, 'epoch': 0.35}

  3%|▎         | 809/28080 [1:35:48<54:09:55,  7.15s/it]
  3%|▎         | 810/28080 [1:35:55<54:07:52,  7.15s/it]
                                                        
{'loss': 0.7639, 'learning_rate': 0.0004804270462633452, 'epoch': 0.35}

  3%|▎         | 810/28080 [1:35:55<54:07:52,  7.15s/it]
  3%|▎         | 811/28080 [1:36:02<54:09:31,  7.15s/it]
                                                        
{'loss': 0.7454, 'learning_rate': 0.00048102016607354687, 'epoch': 0.35}

  3%|▎         | 811/28080 [1:36:02<54:09:31,  7.15s/it]
  3%|▎         | 812/28080 [1:36:09<53:59:24,  7.13s/it]
                                                        
{'loss': 0.7508, 'learning_rate': 0.0004816132858837485, 'epoch': 0.35}

  3%|▎         | 812/28080 [1:36:09<53:59:24,  7.13s/it]
  3%|▎         | 813/28080 [1:36:16<54:05:03,  7.14s/it]
                                                        
{'loss': 0.752, 'learning_rate': 0.00048220640569395017, 'epoch': 0.35}

  3%|▎         | 813/28080 [1:36:16<54:05:03,  7.14s/it]
  3%|▎         | 814/28080 [1:36:24<54:12:08,  7.16s/it]
                                                        
{'loss': 0.75, 'learning_rate': 0.00048279952550415187, 'epoch': 0.35}

  3%|▎         | 814/28080 [1:36:24<54:12:08,  7.16s/it]
  3%|▎         | 815/28080 [1:36:31<54:09:28,  7.15s/it]
                                                        
{'loss': 0.7501, 'learning_rate': 0.0004833926453143535, 'epoch': 0.35}

  3%|▎         | 815/28080 [1:36:31<54:09:28,  7.15s/it]
  3%|▎         | 816/28080 [1:36:38<53:49:55,  7.11s/it]
                                                        
{'loss': 0.7651, 'learning_rate': 0.00048398576512455517, 'epoch': 0.35}

  3%|▎         | 816/28080 [1:36:38<53:49:55,  7.11s/it]
  3%|▎         | 817/28080 [1:36:45<53:42:08,  7.09s/it]
                                                        
{'loss': 0.7923, 'learning_rate': 0.0004845788849347568, 'epoch': 0.35}

  3%|▎         | 817/28080 [1:36:45<53:42:08,  7.09s/it]
  3%|▎         | 818/28080 [1:36:52<53:35:28,  7.08s/it]
                                                        
{'loss': 0.7811, 'learning_rate': 0.00048517200474495846, 'epoch': 0.35}

  3%|▎         | 818/28080 [1:36:52<53:35:28,  7.08s/it]
  3%|▎         | 819/28080 [1:36:59<53:34:07,  7.07s/it]
                                                        
{'loss': 0.7506, 'learning_rate': 0.00048576512455516017, 'epoch': 0.35}

  3%|▎         | 819/28080 [1:36:59<53:34:07,  7.07s/it]
  3%|▎         | 820/28080 [1:37:06<53:33:12,  7.07s/it]
                                                        
{'loss': 0.779, 'learning_rate': 0.0004863582443653618, 'epoch': 0.35}

  3%|▎         | 820/28080 [1:37:06<53:33:12,  7.07s/it]
  3%|▎         | 821/28080 [1:37:13<53:42:11,  7.09s/it]
                                                        
{'loss': 0.7334, 'learning_rate': 0.00048695136417556346, 'epoch': 0.35}

  3%|▎         | 821/28080 [1:37:13<53:42:11,  7.09s/it]
  3%|▎         | 822/28080 [1:37:20<53:44:37,  7.10s/it]
                                                        
{'loss': 0.7692, 'learning_rate': 0.0004875444839857651, 'epoch': 0.35}

  3%|▎         | 822/28080 [1:37:20<53:44:37,  7.10s/it]
  3%|▎         | 823/28080 [1:37:27<53:34:18,  7.08s/it]
                                                        
{'loss': 0.7558, 'learning_rate': 0.00048813760379596676, 'epoch': 0.35}

  3%|▎         | 823/28080 [1:37:27<53:34:18,  7.08s/it]
  3%|▎         | 824/28080 [1:37:34<53:27:28,  7.06s/it]
                                                        
{'loss': 0.7472, 'learning_rate': 0.0004887307236061684, 'epoch': 0.35}

  3%|▎         | 824/28080 [1:37:34<53:27:28,  7.06s/it]
  3%|▎         | 825/28080 [1:37:41<53:42:09,  7.09s/it]
                                                        
{'loss': 0.7409, 'learning_rate': 0.0004893238434163701, 'epoch': 0.35}

  3%|▎         | 825/28080 [1:37:41<53:42:09,  7.09s/it]
  3%|▎         | 826/28080 [1:37:49<53:39:02,  7.09s/it]
                                                        
{'loss': 0.7504, 'learning_rate': 0.0004899169632265717, 'epoch': 0.35}

  3%|▎         | 826/28080 [1:37:49<53:39:02,  7.09s/it]
  3%|▎         | 827/28080 [1:37:56<53:34:14,  7.08s/it]
                                                        
{'loss': 0.7641, 'learning_rate': 0.0004905100830367734, 'epoch': 0.35}

  3%|▎         | 827/28080 [1:37:56<53:34:14,  7.08s/it]
  3%|▎         | 828/28080 [1:38:03<53:37:57,  7.08s/it]
                                                        
{'loss': 0.7583, 'learning_rate': 0.0004911032028469751, 'epoch': 0.35}

  3%|▎         | 828/28080 [1:38:03<53:37:57,  7.08s/it]
  3%|▎         | 829/28080 [1:38:10<53:42:06,  7.09s/it]
                                                        
{'loss': 0.7431, 'learning_rate': 0.0004916963226571768, 'epoch': 0.35}

  3%|▎         | 829/28080 [1:38:10<53:42:06,  7.09s/it]
  3%|▎         | 830/28080 [1:38:17<53:47:48,  7.11s/it]
                                                        
{'loss': 0.7458, 'learning_rate': 0.0004922894424673784, 'epoch': 0.35}

  3%|▎         | 830/28080 [1:38:17<53:47:48,  7.11s/it]
  3%|▎         | 831/28080 [1:38:24<53:34:50,  7.08s/it]
                                                        
{'loss': 0.7601, 'learning_rate': 0.0004928825622775801, 'epoch': 0.35}

  3%|▎         | 831/28080 [1:38:24<53:34:50,  7.08s/it]
  3%|▎         | 832/28080 [1:38:31<53:41:39,  7.09s/it]
                                                        
{'loss': 0.7298, 'learning_rate': 0.0004934756820877817, 'epoch': 0.36}

  3%|▎         | 832/28080 [1:38:31<53:41:39,  7.09s/it]
  3%|▎         | 833/28080 [1:38:38<53:54:23,  7.12s/it]
                                                        
{'loss': 0.7407, 'learning_rate': 0.0004940688018979834, 'epoch': 0.36}

  3%|▎         | 833/28080 [1:38:38<53:54:23,  7.12s/it]
  3%|▎         | 834/28080 [1:38:45<53:41:37,  7.09s/it]
                                                        
{'loss': 0.7409, 'learning_rate': 0.0004946619217081851, 'epoch': 0.36}

  3%|▎         | 834/28080 [1:38:45<53:41:37,  7.09s/it]
  3%|▎         | 835/28080 [1:38:52<53:44:51,  7.10s/it]
                                                        
{'loss': 0.771, 'learning_rate': 0.0004952550415183867, 'epoch': 0.36}

  3%|▎         | 835/28080 [1:38:52<53:44:51,  7.10s/it]
  3%|▎         | 836/28080 [1:38:59<53:27:17,  7.06s/it]
                                                        
{'loss': 0.7518, 'learning_rate': 0.0004958481613285884, 'epoch': 0.36}

  3%|▎         | 836/28080 [1:38:59<53:27:17,  7.06s/it]
  3%|▎         | 837/28080 [1:39:06<53:33:44,  7.08s/it]
                                                        
{'loss': 0.7605, 'learning_rate': 0.00049644128113879, 'epoch': 0.36}

  3%|▎         | 837/28080 [1:39:06<53:33:44,  7.08s/it]
  3%|▎         | 838/28080 [1:39:14<53:46:20,  7.11s/it]
                                                        
{'loss': 0.7612, 'learning_rate': 0.0004970344009489917, 'epoch': 0.36}

  3%|▎         | 838/28080 [1:39:14<53:46:20,  7.11s/it]
  3%|▎         | 839/28080 [1:39:21<53:51:29,  7.12s/it]
                                                        
{'loss': 0.7659, 'learning_rate': 0.0004976275207591934, 'epoch': 0.36}

  3%|▎         | 839/28080 [1:39:21<53:51:29,  7.12s/it]
  3%|▎         | 840/28080 [1:39:28<53:49:57,  7.11s/it]
                                                        
{'loss': 0.7675, 'learning_rate': 0.000498220640569395, 'epoch': 0.36}

  3%|▎         | 840/28080 [1:39:28<53:49:57,  7.11s/it]
  3%|▎         | 841/28080 [1:39:35<53:54:16,  7.12s/it]
                                                        
{'loss': 0.7539, 'learning_rate': 0.0004988137603795967, 'epoch': 0.36}

  3%|▎         | 841/28080 [1:39:35<53:54:16,  7.12s/it]
  3%|▎         | 842/28080 [1:39:42<53:42:28,  7.10s/it]
                                                        
{'loss': 0.7687, 'learning_rate': 0.0004994068801897983, 'epoch': 0.36}

  3%|▎         | 842/28080 [1:39:42<53:42:28,  7.10s/it]
  3%|▎         | 843/28080 [1:39:49<53:52:33,  7.12s/it]
                                                        
{'loss': 0.7394, 'learning_rate': 0.0005, 'epoch': 0.36}

  3%|▎         | 843/28080 [1:39:49<53:52:33,  7.12s/it]
  3%|▎         | 844/28080 [1:39:56<53:35:35,  7.08s/it]
                                                        
{'loss': 0.7572, 'learning_rate': 0.000499999998337004, 'epoch': 0.36}

  3%|▎         | 844/28080 [1:39:56<53:35:35,  7.08s/it]
  3%|▎         | 845/28080 [1:40:03<53:43:06,  7.10s/it]
                                                        
{'loss': 0.7459, 'learning_rate': 0.0004999999933480158, 'epoch': 0.36}

  3%|▎         | 845/28080 [1:40:03<53:43:06,  7.10s/it]
  3%|▎         | 846/28080 [1:40:10<53:39:33,  7.09s/it]
                                                        
{'loss': 0.7571, 'learning_rate': 0.0004999999850330357, 'epoch': 0.36}

  3%|▎         | 846/28080 [1:40:10<53:39:33,  7.09s/it]
  3%|▎         | 847/28080 [1:40:18<53:30:56,  7.07s/it]
                                                        
{'loss': 0.7736, 'learning_rate': 0.0004999999733920637, 'epoch': 0.36}

  3%|▎         | 847/28080 [1:40:18<53:30:56,  7.07s/it]
  3%|▎         | 848/28080 [1:40:25<53:36:34,  7.09s/it]
                                                        
{'loss': 0.7355, 'learning_rate': 0.0004999999584251, 'epoch': 0.36}

  3%|▎         | 848/28080 [1:40:25<53:36:34,  7.09s/it]
  3%|▎         | 849/28080 [1:40:32<53:48:27,  7.11s/it]
                                                        
{'loss': 0.7442, 'learning_rate': 0.0004999999401321448, 'epoch': 0.36}

  3%|▎         | 849/28080 [1:40:32<53:48:27,  7.11s/it]
  3%|▎         | 850/28080 [1:40:39<53:40:23,  7.10s/it]
                                                        
{'loss': 0.7643, 'learning_rate': 0.0004999999185131981, 'epoch': 0.36}

  3%|▎         | 850/28080 [1:40:39<53:40:23,  7.10s/it]
  3%|▎         | 851/28080 [1:40:46<53:22:11,  7.06s/it]
                                                        
{'loss': 0.7386, 'learning_rate': 0.0004999998935682606, 'epoch': 0.36}

  3%|▎         | 851/28080 [1:40:46<53:22:11,  7.06s/it]
  3%|▎         | 852/28080 [1:40:53<53:31:44,  7.08s/it]
                                                        
{'loss': 0.7396, 'learning_rate': 0.0004999998652973324, 'epoch': 0.36}

  3%|▎         | 852/28080 [1:40:53<53:31:44,  7.08s/it]
  3%|▎         | 853/28080 [1:41:00<53:25:51,  7.06s/it]
                                                        
{'loss': 0.7726, 'learning_rate': 0.0004999998337004138, 'epoch': 0.36}

  3%|▎         | 853/28080 [1:41:00<53:25:51,  7.06s/it]
  3%|▎         | 854/28080 [1:41:07<53:41:29,  7.10s/it]
                                                        
{'loss': 0.7463, 'learning_rate': 0.0004999997987775054, 'epoch': 0.36}

  3%|▎         | 854/28080 [1:41:07<53:41:29,  7.10s/it]
  3%|▎         | 855/28080 [1:41:14<53:46:38,  7.11s/it]
                                                        
{'loss': 0.7497, 'learning_rate': 0.0004999997605286075, 'epoch': 0.37}

  3%|▎         | 855/28080 [1:41:14<53:46:38,  7.11s/it]
  3%|▎         | 856/28080 [1:41:21<53:46:13,  7.11s/it]
                                                        
{'loss': 0.7625, 'learning_rate': 0.0004999997189537208, 'epoch': 0.37}

  3%|▎         | 856/28080 [1:41:21<53:46:13,  7.11s/it]
  3%|▎         | 857/28080 [1:41:28<53:41:16,  7.10s/it]
                                                        
{'loss': 0.7681, 'learning_rate': 0.0004999996740528458, 'epoch': 0.37}

  3%|▎         | 857/28080 [1:41:28<53:41:16,  7.10s/it]
  3%|▎         | 858/28080 [1:41:36<53:36:45,  7.09s/it]
                                                        
{'loss': 0.7563, 'learning_rate': 0.0004999996258259829, 'epoch': 0.37}

  3%|▎         | 858/28080 [1:41:36<53:36:45,  7.09s/it]
  3%|▎         | 859/28080 [1:41:43<53:46:34,  7.11s/it]
                                                        
{'loss': 0.7506, 'learning_rate': 0.000499999574273133, 'epoch': 0.37}

  3%|▎         | 859/28080 [1:41:43<53:46:34,  7.11s/it]
  3%|▎         | 860/28080 [1:41:50<53:51:30,  7.12s/it]
                                                        
{'loss': 0.7648, 'learning_rate': 0.0004999995193942966, 'epoch': 0.37}

  3%|▎         | 860/28080 [1:41:50<53:51:30,  7.12s/it]
  3%|▎         | 861/28080 [1:41:57<53:53:26,  7.13s/it]
                                                        
{'loss': 0.7456, 'learning_rate': 0.0004999994611894745, 'epoch': 0.37}

  3%|▎         | 861/28080 [1:41:57<53:53:26,  7.13s/it]
  3%|▎         | 862/28080 [1:42:04<53:59:44,  7.14s/it]
                                                        
{'loss': 0.7509, 'learning_rate': 0.0004999993996586675, 'epoch': 0.37}

  3%|▎         | 862/28080 [1:42:04<53:59:44,  7.14s/it]
  3%|▎         | 863/28080 [1:42:11<53:55:43,  7.13s/it]
                                                        
{'loss': 0.7365, 'learning_rate': 0.0004999993348018764, 'epoch': 0.37}

  3%|▎         | 863/28080 [1:42:11<53:55:43,  7.13s/it]
  3%|▎         | 864/28080 [1:42:18<53:42:43,  7.10s/it]
                                                        
{'loss': 0.7572, 'learning_rate': 0.000499999266619102, 'epoch': 0.37}

  3%|▎         | 864/28080 [1:42:18<53:42:43,  7.10s/it]
  3%|▎         | 865/28080 [1:42:25<53:51:05,  7.12s/it]
                                                        
{'loss': 0.755, 'learning_rate': 0.0004999991951103454, 'epoch': 0.37}

  3%|▎         | 865/28080 [1:42:26<53:51:05,  7.12s/it]
  3%|▎         | 866/28080 [1:42:33<53:51:53,  7.13s/it]
                                                        
{'loss': 0.7787, 'learning_rate': 0.0004999991202756074, 'epoch': 0.37}

  3%|▎         | 866/28080 [1:42:33<53:51:53,  7.13s/it]
  3%|▎         | 867/28080 [1:42:40<53:44:23,  7.11s/it]
                                                        
{'loss': 0.7852, 'learning_rate': 0.0004999990421148889, 'epoch': 0.37}

  3%|▎         | 867/28080 [1:42:40<53:44:23,  7.11s/it]
  3%|▎         | 868/28080 [1:42:47<53:34:04,  7.09s/it]
                                                        
{'loss': 0.7785, 'learning_rate': 0.0004999989606281911, 'epoch': 0.37}

  3%|▎         | 868/28080 [1:42:47<53:34:04,  7.09s/it]
  3%|▎         | 869/28080 [1:42:54<53:40:44,  7.10s/it]
                                                        
{'loss': 0.768, 'learning_rate': 0.000499998875815515, 'epoch': 0.37}

  3%|▎         | 869/28080 [1:42:54<53:40:44,  7.10s/it]
  3%|▎         | 870/28080 [1:43:01<53:38:06,  7.10s/it]
                                                        
{'loss': 0.743, 'learning_rate': 0.0004999987876768619, 'epoch': 0.37}

  3%|▎         | 870/28080 [1:43:01<53:38:06,  7.10s/it]
  3%|▎         | 871/28080 [1:43:08<53:38:11,  7.10s/it]
                                                        
{'loss': 0.738, 'learning_rate': 0.0004999986962122328, 'epoch': 0.37}

  3%|▎         | 871/28080 [1:43:08<53:38:11,  7.10s/it]
  3%|▎         | 872/28080 [1:43:15<53:41:22,  7.10s/it]
                                                        
{'loss': 0.7369, 'learning_rate': 0.000499998601421629, 'epoch': 0.37}

  3%|▎         | 872/28080 [1:43:15<53:41:22,  7.10s/it]
  3%|▎         | 873/28080 [1:43:22<53:43:24,  7.11s/it]
                                                        
{'loss': 0.7243, 'learning_rate': 0.0004999985033050516, 'epoch': 0.37}

  3%|▎         | 873/28080 [1:43:22<53:43:24,  7.11s/it]
  3%|▎         | 874/28080 [1:43:29<53:41:09,  7.10s/it]
                                                        
{'loss': 0.7485, 'learning_rate': 0.000499998401862502, 'epoch': 0.37}

  3%|▎         | 874/28080 [1:43:29<53:41:09,  7.10s/it]
  3%|▎         | 875/28080 [1:43:36<53:41:21,  7.10s/it]
                                                        
{'loss': 0.7619, 'learning_rate': 0.0004999982970939817, 'epoch': 0.37}

  3%|▎         | 875/28080 [1:43:36<53:41:21,  7.10s/it]
  3%|▎         | 876/28080 [1:43:44<53:54:00,  7.13s/it]
                                                        
{'loss': 0.7628, 'learning_rate': 0.0004999981889994918, 'epoch': 0.37}

  3%|▎         | 876/28080 [1:43:44<53:54:00,  7.13s/it]
  3%|▎         | 877/28080 [1:43:51<54:02:26,  7.15s/it]
                                                        
{'loss': 0.7437, 'learning_rate': 0.000499998077579034, 'epoch': 0.37}

  3%|▎         | 877/28080 [1:43:51<54:02:26,  7.15s/it]
  3%|▎         | 878/28080 [1:43:58<53:51:03,  7.13s/it]
                                                        
{'loss': 0.738, 'learning_rate': 0.0004999979628326097, 'epoch': 0.38}

  3%|▎         | 878/28080 [1:43:58<53:51:03,  7.13s/it]
  3%|▎         | 879/28080 [1:44:05<53:56:23,  7.14s/it]
                                                        
{'loss': 0.7322, 'learning_rate': 0.0004999978447602205, 'epoch': 0.38}

  3%|▎         | 879/28080 [1:44:05<53:56:23,  7.14s/it]
  3%|▎         | 880/28080 [1:44:12<53:48:31,  7.12s/it]
                                                        
{'loss': 0.755, 'learning_rate': 0.0004999977233618678, 'epoch': 0.38}

  3%|▎         | 880/28080 [1:44:12<53:48:31,  7.12s/it]
  3%|▎         | 881/28080 [1:44:19<53:51:34,  7.13s/it]
                                                        
{'loss': 0.7638, 'learning_rate': 0.0004999975986375532, 'epoch': 0.38}

  3%|▎         | 881/28080 [1:44:19<53:51:34,  7.13s/it]
  3%|▎         | 882/28080 [1:44:27<53:56:59,  7.14s/it]
                                                        
{'loss': 0.7517, 'learning_rate': 0.0004999974705872785, 'epoch': 0.38}

  3%|▎         | 882/28080 [1:44:27<53:56:59,  7.14s/it]
  3%|▎         | 883/28080 [1:44:34<53:44:46,  7.11s/it]
                                                        
{'loss': 0.763, 'learning_rate': 0.0004999973392110455, 'epoch': 0.38}

  3%|▎         | 883/28080 [1:44:34<53:44:46,  7.11s/it]
  3%|▎         | 884/28080 [1:44:41<53:36:50,  7.10s/it]
                                                        
{'loss': 0.7576, 'learning_rate': 0.0004999972045088557, 'epoch': 0.38}

  3%|▎         | 884/28080 [1:44:41<53:36:50,  7.10s/it]
  3%|▎         | 885/28080 [1:44:48<53:36:24,  7.10s/it]
                                                        
{'loss': 0.7502, 'learning_rate': 0.000499997066480711, 'epoch': 0.38}

  3%|▎         | 885/28080 [1:44:48<53:36:24,  7.10s/it]
  3%|▎         | 886/28080 [1:44:55<53:32:27,  7.09s/it]
                                                        
{'loss': 0.754, 'learning_rate': 0.0004999969251266133, 'epoch': 0.38}

  3%|▎         | 886/28080 [1:44:55<53:32:27,  7.09s/it]
  3%|▎         | 887/28080 [1:45:02<53:29:21,  7.08s/it]
                                                        
{'loss': 0.7522, 'learning_rate': 0.0004999967804465643, 'epoch': 0.38}

  3%|▎         | 887/28080 [1:45:02<53:29:21,  7.08s/it]
  3%|▎         | 888/28080 [1:45:09<53:30:48,  7.08s/it]
                                                        
{'loss': 0.7654, 'learning_rate': 0.0004999966324405661, 'epoch': 0.38}

  3%|▎         | 888/28080 [1:45:09<53:30:48,  7.08s/it]
  3%|▎         | 889/28080 [1:45:16<53:37:46,  7.10s/it]
                                                        
{'loss': 0.7678, 'learning_rate': 0.0004999964811086207, 'epoch': 0.38}

  3%|▎         | 889/28080 [1:45:16<53:37:46,  7.10s/it]
  3%|▎         | 890/28080 [1:45:23<53:39:25,  7.10s/it]
                                                        
{'loss': 0.7574, 'learning_rate': 0.00049999632645073, 'epoch': 0.38}

  3%|▎         | 890/28080 [1:45:23<53:39:25,  7.10s/it]
  3%|▎         | 891/28080 [1:45:30<53:54:37,  7.14s/it]
                                                        
{'loss': 0.7637, 'learning_rate': 0.000499996168466896, 'epoch': 0.38}

  3%|▎         | 891/28080 [1:45:30<53:54:37,  7.14s/it]
  3%|▎         | 892/28080 [1:45:38<54:12:50,  7.18s/it]
                                                        
{'loss': 0.7426, 'learning_rate': 0.0004999960071571209, 'epoch': 0.38}

  3%|▎         | 892/28080 [1:45:38<54:12:50,  7.18s/it]
  3%|▎         | 893/28080 [1:45:45<54:08:37,  7.17s/it]
                                                        
{'loss': 0.7699, 'learning_rate': 0.0004999958425214068, 'epoch': 0.38}

  3%|▎         | 893/28080 [1:45:45<54:08:37,  7.17s/it]
  3%|▎         | 894/28080 [1:45:52<53:53:36,  7.14s/it]
                                                        
{'loss': 0.7477, 'learning_rate': 0.0004999956745597561, 'epoch': 0.38}

  3%|▎         | 894/28080 [1:45:52<53:53:36,  7.14s/it]
  3%|▎         | 895/28080 [1:45:59<53:44:24,  7.12s/it]
                                                        
{'loss': 0.7697, 'learning_rate': 0.0004999955032721707, 'epoch': 0.38}

  3%|▎         | 895/28080 [1:45:59<53:44:24,  7.12s/it]
  3%|▎         | 896/28080 [1:46:06<53:54:05,  7.14s/it]
                                                        
{'loss': 0.7599, 'learning_rate': 0.0004999953286586531, 'epoch': 0.38}

  3%|▎         | 896/28080 [1:46:06<53:54:05,  7.14s/it]
  3%|▎         | 897/28080 [1:46:13<53:45:40,  7.12s/it]
                                                        
{'loss': 0.7408, 'learning_rate': 0.0004999951507192055, 'epoch': 0.38}

  3%|▎         | 897/28080 [1:46:13<53:45:40,  7.12s/it]
  3%|▎         | 898/28080 [1:46:20<53:48:30,  7.13s/it]
                                                        
{'loss': 0.7759, 'learning_rate': 0.0004999949694538303, 'epoch': 0.38}

  3%|▎         | 898/28080 [1:46:20<53:48:30,  7.13s/it]
  3%|▎         | 899/28080 [1:46:27<53:32:47,  7.09s/it]
                                                        
{'loss': 0.7501, 'learning_rate': 0.00049999478486253, 'epoch': 0.38}

  3%|▎         | 899/28080 [1:46:27<53:32:47,  7.09s/it]
  3%|▎         | 900/28080 [1:46:34<53:36:03,  7.10s/it]
                                                        
{'loss': 0.741, 'learning_rate': 0.000499994596945307, 'epoch': 0.38}

  3%|▎         | 900/28080 [1:46:34<53:36:03,  7.10s/it]
  3%|▎         | 901/28080 [1:46:42<53:38:38,  7.11s/it]
                                                        
{'loss': 0.7419, 'learning_rate': 0.0004999944057021638, 'epoch': 0.38}

  3%|▎         | 901/28080 [1:46:42<53:38:38,  7.11s/it]
  3%|▎         | 902/28080 [1:46:49<53:33:43,  7.09s/it]
                                                        
{'loss': 0.7677, 'learning_rate': 0.0004999942111331029, 'epoch': 0.39}

  3%|▎         | 902/28080 [1:46:49<53:33:43,  7.09s/it]
  3%|▎         | 903/28080 [1:46:56<53:52:29,  7.14s/it]
                                                        
{'loss': 0.7511, 'learning_rate': 0.000499994013238127, 'epoch': 0.39}

  3%|▎         | 903/28080 [1:46:56<53:52:29,  7.14s/it]
  3%|▎         | 904/28080 [1:47:03<53:34:48,  7.10s/it]
                                                        
{'loss': 0.7543, 'learning_rate': 0.0004999938120172385, 'epoch': 0.39}

  3%|▎         | 904/28080 [1:47:03<53:34:48,  7.10s/it]
  3%|▎         | 905/28080 [1:47:10<53:42:33,  7.12s/it]
                                                        
{'loss': 0.7427, 'learning_rate': 0.0004999936074704403, 'epoch': 0.39}

  3%|▎         | 905/28080 [1:47:10<53:42:33,  7.12s/it]
  3%|▎         | 906/28080 [1:47:17<53:45:50,  7.12s/it]
                                                        
{'loss': 0.759, 'learning_rate': 0.0004999933995977351, 'epoch': 0.39}

  3%|▎         | 906/28080 [1:47:17<53:45:50,  7.12s/it]
  3%|▎         | 907/28080 [1:47:24<53:50:26,  7.13s/it]
                                                        
{'loss': 0.7415, 'learning_rate': 0.0004999931883991256, 'epoch': 0.39}

  3%|▎         | 907/28080 [1:47:24<53:50:26,  7.13s/it]
  3%|▎         | 908/28080 [1:47:32<53:52:53,  7.14s/it]
                                                        
{'loss': 0.7413, 'learning_rate': 0.0004999929738746147, 'epoch': 0.39}

  3%|▎         | 908/28080 [1:47:32<53:52:53,  7.14s/it]
  3%|▎         | 909/28080 [1:47:39<53:52:15,  7.14s/it]
                                                        
{'loss': 0.7528, 'learning_rate': 0.0004999927560242051, 'epoch': 0.39}

  3%|▎         | 909/28080 [1:47:39<53:52:15,  7.14s/it]
  3%|▎         | 910/28080 [1:47:46<53:47:53,  7.13s/it]
                                                        
{'loss': 0.7505, 'learning_rate': 0.0004999925348478999, 'epoch': 0.39}

  3%|▎         | 910/28080 [1:47:46<53:47:53,  7.13s/it]
  3%|▎         | 911/28080 [1:47:53<53:39:29,  7.11s/it]
                                                        
{'loss': 0.7537, 'learning_rate': 0.0004999923103457018, 'epoch': 0.39}

  3%|▎         | 911/28080 [1:47:53<53:39:29,  7.11s/it]
  3%|▎         | 912/28080 [1:48:00<53:40:51,  7.11s/it]
                                                        
{'loss': 0.7374, 'learning_rate': 0.0004999920825176139, 'epoch': 0.39}

  3%|▎         | 912/28080 [1:48:00<53:40:51,  7.11s/it]
  3%|▎         | 913/28080 [1:48:07<53:40:17,  7.11s/it]
                                                        
{'loss': 0.7546, 'learning_rate': 0.0004999918513636393, 'epoch': 0.39}

  3%|▎         | 913/28080 [1:48:07<53:40:17,  7.11s/it]
  3%|▎         | 914/28080 [1:48:14<53:48:40,  7.13s/it]
                                                        
{'loss': 0.7436, 'learning_rate': 0.000499991616883781, 'epoch': 0.39}

  3%|▎         | 914/28080 [1:48:14<53:48:40,  7.13s/it]
  3%|▎         | 915/28080 [1:48:21<53:43:55,  7.12s/it]
                                                        
{'loss': 0.7649, 'learning_rate': 0.0004999913790780422, 'epoch': 0.39}

  3%|▎         | 915/28080 [1:48:21<53:43:55,  7.12s/it]
  3%|▎         | 916/28080 [1:48:28<53:36:33,  7.10s/it]
                                                        
{'loss': 0.7695, 'learning_rate': 0.000499991137946426, 'epoch': 0.39}

  3%|▎         | 916/28080 [1:48:28<53:36:33,  7.10s/it]
  3%|▎         | 917/28080 [1:48:35<53:23:37,  7.08s/it]
                                                        
{'loss': 0.7633, 'learning_rate': 0.0004999908934889356, 'epoch': 0.39}

  3%|▎         | 917/28080 [1:48:35<53:23:37,  7.08s/it]
  3%|▎         | 918/28080 [1:48:42<53:22:12,  7.07s/it]
                                                        
{'loss': 0.762, 'learning_rate': 0.0004999906457055741, 'epoch': 0.39}

  3%|▎         | 918/28080 [1:48:42<53:22:12,  7.07s/it]
  3%|▎         | 919/28080 [1:48:50<53:22:49,  7.08s/it]
                                                        
{'loss': 0.7408, 'learning_rate': 0.0004999903945963451, 'epoch': 0.39}

  3%|▎         | 919/28080 [1:48:50<53:22:49,  7.08s/it]
  3%|▎         | 920/28080 [1:48:57<53:16:58,  7.06s/it]
                                                        
{'loss': 0.7599, 'learning_rate': 0.0004999901401612519, 'epoch': 0.39}

  3%|▎         | 920/28080 [1:48:57<53:16:58,  7.06s/it]
  3%|▎         | 921/28080 [1:49:04<53:33:32,  7.10s/it]
                                                        
{'loss': 0.7459, 'learning_rate': 0.0004999898824002976, 'epoch': 0.39}

  3%|▎         | 921/28080 [1:49:04<53:33:32,  7.10s/it]
  3%|▎         | 922/28080 [1:49:11<53:41:58,  7.12s/it]
                                                        
{'loss': 0.7421, 'learning_rate': 0.000499989621313486, 'epoch': 0.39}

  3%|▎         | 922/28080 [1:49:11<53:41:58,  7.12s/it]
  3%|▎         | 923/28080 [1:49:18<53:43:09,  7.12s/it]
                                                        
{'loss': 0.751, 'learning_rate': 0.0004999893569008203, 'epoch': 0.39}

  3%|▎         | 923/28080 [1:49:18<53:43:09,  7.12s/it]
  3%|▎         | 924/28080 [1:49:25<53:30:19,  7.09s/it]
                                                        
{'loss': 0.7472, 'learning_rate': 0.000499989089162304, 'epoch': 0.39}

  3%|▎         | 924/28080 [1:49:25<53:30:19,  7.09s/it]
  3%|▎         | 925/28080 [1:49:32<53:43:44,  7.12s/it]
                                                        
{'loss': 0.7443, 'learning_rate': 0.0004999888180979409, 'epoch': 0.4}

  3%|▎         | 925/28080 [1:49:32<53:43:44,  7.12s/it]
  3%|▎         | 926/28080 [1:49:39<53:42:27,  7.12s/it]
                                                        
{'loss': 0.75, 'learning_rate': 0.0004999885437077344, 'epoch': 0.4}

  3%|▎         | 926/28080 [1:49:39<53:42:27,  7.12s/it]
  3%|▎         | 927/28080 [1:49:47<53:45:10,  7.13s/it]
                                                        
{'loss': 0.7432, 'learning_rate': 0.0004999882659916882, 'epoch': 0.4}

  3%|▎         | 927/28080 [1:49:47<53:45:10,  7.13s/it]
  3%|▎         | 928/28080 [1:49:54<53:37:43,  7.11s/it]
                                                        
{'loss': 0.7476, 'learning_rate': 0.0004999879849498061, 'epoch': 0.4}

  3%|▎         | 928/28080 [1:49:54<53:37:43,  7.11s/it]
  3%|▎         | 929/28080 [1:50:01<53:35:20,  7.11s/it]
                                                        
{'loss': 0.7902, 'learning_rate': 0.0004999877005820917, 'epoch': 0.4}

  3%|▎         | 929/28080 [1:50:01<53:35:20,  7.11s/it]
  3%|▎         | 930/28080 [1:50:08<53:45:58,  7.13s/it]
                                                        
{'loss': 0.7713, 'learning_rate': 0.000499987412888549, 'epoch': 0.4}

  3%|▎         | 930/28080 [1:50:08<53:45:58,  7.13s/it]
  3%|▎         | 931/28080 [1:50:15<53:38:28,  7.11s/it]
                                                        
{'loss': 0.7627, 'learning_rate': 0.0004999871218691815, 'epoch': 0.4}

  3%|▎         | 931/28080 [1:50:15<53:38:28,  7.11s/it]
  3%|▎         | 932/28080 [1:50:22<53:20:34,  7.07s/it]
                                                        
{'loss': 0.7259, 'learning_rate': 0.0004999868275239932, 'epoch': 0.4}

  3%|▎         | 932/28080 [1:50:22<53:20:34,  7.07s/it]
  3%|▎         | 933/28080 [1:50:29<53:28:19,  7.09s/it]
                                                        
{'loss': 0.7689, 'learning_rate': 0.0004999865298529882, 'epoch': 0.4}

  3%|▎         | 933/28080 [1:50:29<53:28:19,  7.09s/it]
  3%|▎         | 934/28080 [1:50:36<53:27:20,  7.09s/it]
                                                        
{'loss': 0.7478, 'learning_rate': 0.0004999862288561702, 'epoch': 0.4}

  3%|▎         | 934/28080 [1:50:36<53:27:20,  7.09s/it]
  3%|▎         | 935/28080 [1:50:43<53:27:52,  7.09s/it]
                                                        
{'loss': 0.7458, 'learning_rate': 0.0004999859245335435, 'epoch': 0.4}

  3%|▎         | 935/28080 [1:50:43<53:27:52,  7.09s/it]
  3%|▎         | 936/28080 [1:50:50<53:22:29,  7.08s/it]
                                                        
{'loss': 0.7477, 'learning_rate': 0.0004999856168851118, 'epoch': 0.4}

  3%|▎         | 936/28080 [1:50:50<53:22:29,  7.08s/it]
  3%|▎         | 937/28080 [1:50:57<53:21:14,  7.08s/it]
                                                        
{'loss': 0.7384, 'learning_rate': 0.0004999853059108794, 'epoch': 0.4}

  3%|▎         | 937/28080 [1:50:57<53:21:14,  7.08s/it]
  3%|▎         | 938/28080 [1:51:04<53:25:15,  7.09s/it]
                                                        
{'loss': 0.7296, 'learning_rate': 0.0004999849916108504, 'epoch': 0.4}

  3%|▎         | 938/28080 [1:51:05<53:25:15,  7.09s/it]
  3%|▎         | 939/28080 [1:51:12<53:26:22,  7.09s/it]
                                                        
{'loss': 0.7574, 'learning_rate': 0.0004999846739850291, 'epoch': 0.4}

  3%|▎         | 939/28080 [1:51:12<53:26:22,  7.09s/it]
  3%|▎         | 940/28080 [1:51:19<53:36:32,  7.11s/it]
                                                        
{'loss': 0.7521, 'learning_rate': 0.0004999843530334195, 'epoch': 0.4}

  3%|▎         | 940/28080 [1:51:19<53:36:32,  7.11s/it]
  3%|▎         | 941/28080 [1:51:26<53:42:49,  7.13s/it]
                                                        
{'loss': 0.754, 'learning_rate': 0.000499984028756026, 'epoch': 0.4}

  3%|▎         | 941/28080 [1:51:26<53:42:49,  7.13s/it]
  3%|▎         | 942/28080 [1:51:33<53:45:04,  7.13s/it]
                                                        
{'loss': 0.7335, 'learning_rate': 0.0004999837011528529, 'epoch': 0.4}

  3%|▎         | 942/28080 [1:51:33<53:45:04,  7.13s/it]
  3%|▎         | 943/28080 [1:51:40<53:47:01,  7.13s/it]
                                                        
{'loss': 0.7463, 'learning_rate': 0.0004999833702239044, 'epoch': 0.4}

  3%|▎         | 943/28080 [1:51:40<53:47:01,  7.13s/it]
  3%|▎         | 944/28080 [1:51:47<53:44:31,  7.13s/it]
                                                        
{'loss': 0.7389, 'learning_rate': 0.0004999830359691853, 'epoch': 0.4}

  3%|▎         | 944/28080 [1:51:47<53:44:31,  7.13s/it]
  3%|▎         | 945/28080 [1:51:54<53:45:10,  7.13s/it]
                                                        
{'loss': 0.7302, 'learning_rate': 0.0004999826983886996, 'epoch': 0.4}

  3%|▎         | 945/28080 [1:51:54<53:45:10,  7.13s/it]
  3%|▎         | 946/28080 [1:52:02<53:47:51,  7.14s/it]
                                                        
{'loss': 0.7266, 'learning_rate': 0.0004999823574824521, 'epoch': 0.4}

  3%|▎         | 946/28080 [1:52:02<53:47:51,  7.14s/it]
  3%|▎         | 947/28080 [1:52:09<53:53:27,  7.15s/it]
                                                        
{'loss': 0.734, 'learning_rate': 0.0004999820132504471, 'epoch': 0.4}

  3%|▎         | 947/28080 [1:52:09<53:53:27,  7.15s/it]
  3%|▎         | 948/28080 [1:52:16<53:52:17,  7.15s/it]
                                                        
{'loss': 0.7233, 'learning_rate': 0.0004999816656926895, 'epoch': 0.4}

  3%|▎         | 948/28080 [1:52:16<53:52:17,  7.15s/it]
  3%|▎         | 949/28080 [1:52:23<53:40:49,  7.12s/it]
                                                        
{'loss': 0.7378, 'learning_rate': 0.0004999813148091836, 'epoch': 0.41}

  3%|▎         | 949/28080 [1:52:23<53:40:49,  7.12s/it]
  3%|▎         | 950/28080 [1:52:30<53:01:47,  7.04s/it]
                                                        
{'loss': 0.7802, 'learning_rate': 0.0004999809605999343, 'epoch': 0.41}

  3%|▎         | 950/28080 [1:52:30<53:01:47,  7.04s/it]
  3%|▎         | 951/28080 [1:52:37<53:11:12,  7.06s/it]
                                                        
{'loss': 0.7471, 'learning_rate': 0.0004999806030649461, 'epoch': 0.41}

  3%|▎         | 951/28080 [1:52:37<53:11:12,  7.06s/it]
  3%|▎         | 952/28080 [1:52:44<53:17:46,  7.07s/it]
                                                        
{'loss': 0.7507, 'learning_rate': 0.0004999802422042239, 'epoch': 0.41}

  3%|▎         | 952/28080 [1:52:44<53:17:46,  7.07s/it]
  3%|▎         | 953/28080 [1:52:51<53:12:47,  7.06s/it]
                                                        
{'loss': 0.7564, 'learning_rate': 0.0004999798780177724, 'epoch': 0.41}

  3%|▎         | 953/28080 [1:52:51<53:12:47,  7.06s/it]
  3%|▎         | 954/28080 [1:52:58<53:06:16,  7.05s/it]
                                                        
{'loss': 0.7472, 'learning_rate': 0.0004999795105055967, 'epoch': 0.41}

  3%|▎         | 954/28080 [1:52:58<53:06:16,  7.05s/it]
  3%|▎         | 955/28080 [1:53:05<53:14:47,  7.07s/it]
                                                        
{'loss': 0.7386, 'learning_rate': 0.0004999791396677013, 'epoch': 0.41}

  3%|▎         | 955/28080 [1:53:05<53:14:47,  7.07s/it]
  3%|▎         | 956/28080 [1:53:12<53:14:48,  7.07s/it]
                                                        
{'loss': 0.7391, 'learning_rate': 0.0004999787655040914, 'epoch': 0.41}

  3%|▎         | 956/28080 [1:53:12<53:14:48,  7.07s/it]
  3%|▎         | 957/28080 [1:53:19<53:13:53,  7.07s/it]
                                                        
{'loss': 0.7514, 'learning_rate': 0.000499978388014772, 'epoch': 0.41}

  3%|▎         | 957/28080 [1:53:19<53:13:53,  7.07s/it]
  3%|▎         | 958/28080 [1:53:26<53:20:57,  7.08s/it]
                                                        
{'loss': 0.7568, 'learning_rate': 0.000499978007199748, 'epoch': 0.41}

  3%|▎         | 958/28080 [1:53:26<53:20:57,  7.08s/it]
  3%|▎         | 959/28080 [1:53:33<53:15:53,  7.07s/it]
                                                        
{'loss': 0.7524, 'learning_rate': 0.0004999776230590244, 'epoch': 0.41}

  3%|▎         | 959/28080 [1:53:34<53:15:53,  7.07s/it]
  3%|▎         | 960/28080 [1:53:41<53:31:22,  7.10s/it]
                                                        
{'loss': 0.7446, 'learning_rate': 0.0004999772355926066, 'epoch': 0.41}

  3%|▎         | 960/28080 [1:53:41<53:31:22,  7.10s/it]
  3%|▎         | 961/28080 [1:53:48<53:33:55,  7.11s/it]
                                                        
{'loss': 0.7359, 'learning_rate': 0.0004999768448004994, 'epoch': 0.41}

  3%|▎         | 961/28080 [1:53:48<53:33:55,  7.11s/it]
  3%|▎         | 962/28080 [1:53:55<53:20:42,  7.08s/it]
                                                        
{'loss': 0.7335, 'learning_rate': 0.0004999764506827082, 'epoch': 0.41}

  3%|▎         | 962/28080 [1:53:55<53:20:42,  7.08s/it]
  3%|▎         | 963/28080 [1:54:02<53:38:57,  7.12s/it]
                                                        
{'loss': 0.7277, 'learning_rate': 0.0004999760532392383, 'epoch': 0.41}

  3%|▎         | 963/28080 [1:54:02<53:38:57,  7.12s/it]
  3%|▎         | 964/28080 [1:54:09<53:31:11,  7.11s/it]
                                                        
{'loss': 0.7444, 'learning_rate': 0.0004999756524700947, 'epoch': 0.41}

  3%|▎         | 964/28080 [1:54:09<53:31:11,  7.11s/it]
  3%|▎         | 965/28080 [1:54:16<53:15:07,  7.07s/it]
                                                        
{'loss': 0.7596, 'learning_rate': 0.0004999752483752831, 'epoch': 0.41}

  3%|▎         | 965/28080 [1:54:16<53:15:07,  7.07s/it]
  3%|▎         | 966/28080 [1:54:23<53:21:43,  7.09s/it]
                                                        
{'loss': 0.7332, 'learning_rate': 0.0004999748409548088, 'epoch': 0.41}

  3%|▎         | 966/28080 [1:54:23<53:21:43,  7.09s/it]
  3%|▎         | 967/28080 [1:54:30<53:11:59,  7.06s/it]
                                                        
{'loss': 0.7602, 'learning_rate': 0.0004999744302086769, 'epoch': 0.41}

  3%|▎         | 967/28080 [1:54:30<53:11:59,  7.06s/it]
  3%|▎         | 968/28080 [1:54:37<53:10:24,  7.06s/it]
                                                        
{'loss': 0.7265, 'learning_rate': 0.0004999740161368932, 'epoch': 0.41}

  3%|▎         | 968/28080 [1:54:37<53:10:24,  7.06s/it]
  3%|▎         | 969/28080 [1:54:44<53:19:31,  7.08s/it]
                                                        
{'loss': 0.7403, 'learning_rate': 0.000499973598739463, 'epoch': 0.41}

  3%|▎         | 969/28080 [1:54:44<53:19:31,  7.08s/it]
  3%|▎         | 970/28080 [1:54:51<53:20:11,  7.08s/it]
                                                        
{'loss': 0.7456, 'learning_rate': 0.0004999731780163921, 'epoch': 0.41}

  3%|▎         | 970/28080 [1:54:51<53:20:11,  7.08s/it]
  3%|▎         | 971/28080 [1:54:59<53:16:28,  7.07s/it]
                                                        
{'loss': 0.7508, 'learning_rate': 0.0004999727539676858, 'epoch': 0.41}

  3%|▎         | 971/28080 [1:54:59<53:16:28,  7.07s/it]
  3%|▎         | 972/28080 [1:55:06<53:25:50,  7.10s/it]
                                                        
{'loss': 0.7543, 'learning_rate': 0.00049997232659335, 'epoch': 0.42}

  3%|▎         | 972/28080 [1:55:06<53:25:50,  7.10s/it]
  3%|▎         | 973/28080 [1:55:13<53:02:13,  7.04s/it]
                                                        
{'loss': 0.7654, 'learning_rate': 0.0004999718958933903, 'epoch': 0.42}

  3%|▎         | 973/28080 [1:55:13<53:02:13,  7.04s/it]
  3%|▎         | 974/28080 [1:55:20<52:56:47,  7.03s/it]
                                                        
{'loss': 0.7608, 'learning_rate': 0.0004999714618678123, 'epoch': 0.42}

  3%|▎         | 974/28080 [1:55:20<52:56:47,  7.03s/it]
  3%|▎         | 975/28080 [1:55:27<52:47:10,  7.01s/it]
                                                        
{'loss': 0.7562, 'learning_rate': 0.000499971024516622, 'epoch': 0.42}

  3%|▎         | 975/28080 [1:55:27<52:47:10,  7.01s/it]
  3%|▎         | 976/28080 [1:55:34<52:49:37,  7.02s/it]
                                                        
{'loss': 0.7635, 'learning_rate': 0.000499970583839825, 'epoch': 0.42}

  3%|▎         | 976/28080 [1:55:34<52:49:37,  7.02s/it]
  3%|▎         | 977/28080 [1:55:41<52:58:08,  7.04s/it]
                                                        
{'loss': 0.7402, 'learning_rate': 0.0004999701398374273, 'epoch': 0.42}

  3%|▎         | 977/28080 [1:55:41<52:58:08,  7.04s/it]
  3%|▎         | 978/28080 [1:55:48<53:08:38,  7.06s/it]
                                                        
{'loss': 0.7609, 'learning_rate': 0.0004999696925094348, 'epoch': 0.42}

  3%|▎         | 978/28080 [1:55:48<53:08:38,  7.06s/it]
  3%|▎         | 979/28080 [1:55:55<53:11:41,  7.07s/it]
                                                        
{'loss': 0.7524, 'learning_rate': 0.0004999692418558533, 'epoch': 0.42}

  3%|▎         | 979/28080 [1:55:55<53:11:41,  7.07s/it]
  3%|▎         | 980/28080 [1:56:02<53:25:44,  7.10s/it]
                                                        
{'loss': 0.7331, 'learning_rate': 0.0004999687878766891, 'epoch': 0.42}

  3%|▎         | 980/28080 [1:56:02<53:25:44,  7.10s/it]
  3%|▎         | 981/28080 [1:56:09<53:17:25,  7.08s/it]
                                                        
{'loss': 0.7503, 'learning_rate': 0.0004999683305719479, 'epoch': 0.42}

  3%|▎         | 981/28080 [1:56:09<53:17:25,  7.08s/it]
  3%|▎         | 982/28080 [1:56:16<53:18:25,  7.08s/it]
                                                        
{'loss': 0.7341, 'learning_rate': 0.000499967869941636, 'epoch': 0.42}

  3%|▎         | 982/28080 [1:56:16<53:18:25,  7.08s/it]
  4%|▎         | 983/28080 [1:56:23<53:12:44,  7.07s/it]
                                                        
{'loss': 0.7346, 'learning_rate': 0.0004999674059857595, 'epoch': 0.42}

  4%|▎         | 983/28080 [1:56:23<53:12:44,  7.07s/it]
  4%|▎         | 984/28080 [1:56:30<53:01:01,  7.04s/it]
                                                        
{'loss': 0.7487, 'learning_rate': 0.0004999669387043246, 'epoch': 0.42}

  4%|▎         | 984/28080 [1:56:30<53:01:01,  7.04s/it]
  4%|▎         | 985/28080 [1:56:37<53:07:58,  7.06s/it]
                                                        
{'loss': 0.7443, 'learning_rate': 0.0004999664680973373, 'epoch': 0.42}

  4%|▎         | 985/28080 [1:56:37<53:07:58,  7.06s/it]
  4%|▎         | 986/28080 [1:56:44<53:17:21,  7.08s/it]
                                                        
{'loss': 0.7503, 'learning_rate': 0.0004999659941648041, 'epoch': 0.42}

  4%|▎         | 986/28080 [1:56:44<53:17:21,  7.08s/it]
  4%|▎         | 987/28080 [1:56:52<53:28:16,  7.11s/it]
                                                        
{'loss': 0.7247, 'learning_rate': 0.0004999655169067312, 'epoch': 0.42}

  4%|▎         | 987/28080 [1:56:52<53:28:16,  7.11s/it]
  4%|▎         | 988/28080 [1:56:59<53:23:52,  7.10s/it]
                                                        
{'loss': 0.7238, 'learning_rate': 0.000499965036323125, 'epoch': 0.42}

  4%|▎         | 988/28080 [1:56:59<53:23:52,  7.10s/it]
  4%|▎         | 989/28080 [1:57:06<53:36:16,  7.12s/it]
                                                        
{'loss': 0.7322, 'learning_rate': 0.0004999645524139917, 'epoch': 0.42}

  4%|▎         | 989/28080 [1:57:06<53:36:16,  7.12s/it]
  4%|▎         | 990/28080 [1:57:13<53:46:04,  7.15s/it]
                                                        
{'loss': 0.7534, 'learning_rate': 0.0004999640651793381, 'epoch': 0.42}

  4%|▎         | 990/28080 [1:57:13<53:46:04,  7.15s/it]
  4%|▎         | 991/28080 [1:57:20<53:28:07,  7.11s/it]
                                                        
{'loss': 0.7154, 'learning_rate': 0.0004999635746191705, 'epoch': 0.42}

  4%|▎         | 991/28080 [1:57:20<53:28:07,  7.11s/it]
  4%|▎         | 992/28080 [1:57:27<53:15:23,  7.08s/it]
                                                        
{'loss': 0.7415, 'learning_rate': 0.0004999630807334954, 'epoch': 0.42}

  4%|▎         | 992/28080 [1:57:27<53:15:23,  7.08s/it]
  4%|▎         | 993/28080 [1:57:34<53:28:07,  7.11s/it]
                                                        
{'loss': 0.726, 'learning_rate': 0.0004999625835223193, 'epoch': 0.42}

  4%|▎         | 993/28080 [1:57:34<53:28:07,  7.11s/it]
  4%|▎         | 994/28080 [1:57:41<53:28:03,  7.11s/it]
                                                        
{'loss': 0.7327, 'learning_rate': 0.0004999620829856489, 'epoch': 0.42}

  4%|▎         | 994/28080 [1:57:41<53:28:03,  7.11s/it]
  4%|▎         | 995/28080 [1:57:48<53:28:25,  7.11s/it]
                                                        
{'loss': 0.7381, 'learning_rate': 0.0004999615791234909, 'epoch': 0.43}

  4%|▎         | 995/28080 [1:57:48<53:28:25,  7.11s/it]
  4%|▎         | 996/28080 [1:57:56<53:18:26,  7.09s/it]
                                                        
{'loss': 0.7425, 'learning_rate': 0.000499961071935852, 'epoch': 0.43}

  4%|▎         | 996/28080 [1:57:56<53:18:26,  7.09s/it]
  4%|▎         | 997/28080 [1:58:03<53:22:32,  7.09s/it]
                                                        
{'loss': 0.7336, 'learning_rate': 0.0004999605614227388, 'epoch': 0.43}

  4%|▎         | 997/28080 [1:58:03<53:22:32,  7.09s/it]
  4%|▎         | 998/28080 [1:58:10<53:24:31,  7.10s/it]
                                                        
{'loss': 0.7584, 'learning_rate': 0.0004999600475841582, 'epoch': 0.43}

  4%|▎         | 998/28080 [1:58:10<53:24:31,  7.10s/it]
  4%|▎         | 999/28080 [1:58:17<53:26:05,  7.10s/it]
                                                        
{'loss': 0.7316, 'learning_rate': 0.0004999595304201171, 'epoch': 0.43}

  4%|▎         | 999/28080 [1:58:17<53:26:05,  7.10s/it]
  4%|▎         | 1000/28080 [1:58:24<53:25:17,  7.10s/it]
                                                         
{'loss': 0.7861, 'learning_rate': 0.0004999590099306224, 'epoch': 0.43}

  4%|▎         | 1000/28080 [1:58:24<53:25:17,  7.10s/it]
  4%|▎         | 1001/28080 [1:58:31<53:32:21,  7.12s/it]
                                                         
{'loss': 0.763, 'learning_rate': 0.0004999584861156808, 'epoch': 0.43}

  4%|▎         | 1001/28080 [1:58:31<53:32:21,  7.12s/it]
  4%|▎         | 1002/28080 [1:58:38<53:40:05,  7.14s/it]
                                                         
{'loss': 0.7407, 'learning_rate': 0.0004999579589752995, 'epoch': 0.43}

  4%|▎         | 1002/28080 [1:58:38<53:40:05,  7.14s/it]
  4%|▎         | 1003/28080 [1:58:45<53:36:13,  7.13s/it]
                                                         
{'loss': 0.7444, 'learning_rate': 0.0004999574285094854, 'epoch': 0.43}

  4%|▎         | 1003/28080 [1:58:45<53:36:13,  7.13s/it]
  4%|▎         | 1004/28080 [1:58:52<53:27:54,  7.11s/it]
                                                         
{'loss': 0.7502, 'learning_rate': 0.0004999568947182455, 'epoch': 0.43}

  4%|▎         | 1004/28080 [1:58:52<53:27:54,  7.11s/it]
  4%|▎         | 1005/28080 [1:59:00<53:40:19,  7.14s/it]
                                                         
{'loss': 0.7389, 'learning_rate': 0.0004999563576015871, 'epoch': 0.43}

  4%|▎         | 1005/28080 [1:59:00<53:40:19,  7.14s/it]
  4%|▎         | 1006/28080 [1:59:07<53:36:15,  7.13s/it]
                                                         
{'loss': 0.7568, 'learning_rate': 0.0004999558171595171, 'epoch': 0.43}

  4%|▎         | 1006/28080 [1:59:07<53:36:15,  7.13s/it]
  4%|▎         | 1007/28080 [1:59:14<53:30:58,  7.12s/it]
                                                         
{'loss': 0.736, 'learning_rate': 0.0004999552733920429, 'epoch': 0.43}

  4%|▎         | 1007/28080 [1:59:14<53:30:58,  7.12s/it]
  4%|▎         | 1008/28080 [1:59:21<53:25:04,  7.10s/it]
                                                         
{'loss': 0.7386, 'learning_rate': 0.0004999547262991717, 'epoch': 0.43}

  4%|▎         | 1008/28080 [1:59:21<53:25:04,  7.10s/it]
  4%|▎         | 1009/28080 [1:59:28<53:15:35,  7.08s/it]
                                                         
{'loss': 0.7417, 'learning_rate': 0.0004999541758809107, 'epoch': 0.43}

  4%|▎         | 1009/28080 [1:59:28<53:15:35,  7.08s/it]
  4%|▎         | 1010/28080 [1:59:35<53:17:48,  7.09s/it]
                                                         
{'loss': 0.7661, 'learning_rate': 0.0004999536221372672, 'epoch': 0.43}

  4%|▎         | 1010/28080 [1:59:35<53:17:48,  7.09s/it]
  4%|▎         | 1011/28080 [1:59:42<53:13:11,  7.08s/it]
                                                         
{'loss': 0.7488, 'learning_rate': 0.0004999530650682487, 'epoch': 0.43}

  4%|▎         | 1011/28080 [1:59:42<53:13:11,  7.08s/it]
  4%|▎         | 1012/28080 [1:59:49<53:22:01,  7.10s/it]
                                                         
{'loss': 0.7427, 'learning_rate': 0.0004999525046738624, 'epoch': 0.43}

  4%|▎         | 1012/28080 [1:59:49<53:22:01,  7.10s/it]
  4%|▎         | 1013/28080 [1:59:56<53:30:07,  7.12s/it]
                                                         
{'loss': 0.7403, 'learning_rate': 0.0004999519409541161, 'epoch': 0.43}

  4%|▎         | 1013/28080 [1:59:56<53:30:07,  7.12s/it]
  4%|▎         | 1014/28080 [2:00:04<53:34:01,  7.12s/it]
                                                         
{'loss': 0.7356, 'learning_rate': 0.0004999513739090168, 'epoch': 0.43}

  4%|▎         | 1014/28080 [2:00:04<53:34:01,  7.12s/it]
  4%|▎         | 1015/28080 [2:00:11<53:16:46,  7.09s/it]
                                                         
{'loss': 0.7096, 'learning_rate': 0.0004999508035385726, 'epoch': 0.43}

  4%|▎         | 1015/28080 [2:00:11<53:16:46,  7.09s/it]
  4%|▎         | 1016/28080 [2:00:18<53:13:45,  7.08s/it]
                                                         
{'loss': 0.7293, 'learning_rate': 0.0004999502298427906, 'epoch': 0.43}

  4%|▎         | 1016/28080 [2:00:18<53:13:45,  7.08s/it]
  4%|▎         | 1017/28080 [2:00:25<53:19:41,  7.09s/it]
                                                         
{'loss': 0.7367, 'learning_rate': 0.0004999496528216788, 'epoch': 0.43}

  4%|▎         | 1017/28080 [2:00:25<53:19:41,  7.09s/it]
  4%|▎         | 1018/28080 [2:00:32<53:14:15,  7.08s/it]
                                                         
{'loss': 0.7465, 'learning_rate': 0.0004999490724752446, 'epoch': 0.43}

  4%|▎         | 1018/28080 [2:00:32<53:14:15,  7.08s/it]
  4%|▎         | 1019/28080 [2:00:39<53:24:42,  7.11s/it]
                                                         
{'loss': 0.725, 'learning_rate': 0.000499948488803496, 'epoch': 0.44}

  4%|▎         | 1019/28080 [2:00:39<53:24:42,  7.11s/it]
  4%|▎         | 1020/28080 [2:00:46<53:28:02,  7.11s/it]
                                                         
{'loss': 0.7385, 'learning_rate': 0.0004999479018064405, 'epoch': 0.44}

  4%|▎         | 1020/28080 [2:00:46<53:28:02,  7.11s/it]
  4%|▎         | 1021/28080 [2:00:53<53:29:40,  7.12s/it]
                                                         
{'loss': 0.7253, 'learning_rate': 0.0004999473114840861, 'epoch': 0.44}

  4%|▎         | 1021/28080 [2:00:53<53:29:40,  7.12s/it]
  4%|▎         | 1022/28080 [2:01:00<53:32:36,  7.12s/it]
                                                         
{'loss': 0.7561, 'learning_rate': 0.0004999467178364406, 'epoch': 0.44}

  4%|▎         | 1022/28080 [2:01:00<53:32:36,  7.12s/it]
  4%|▎         | 1023/28080 [2:01:07<53:16:21,  7.09s/it]
                                                         
{'loss': 0.7677, 'learning_rate': 0.0004999461208635117, 'epoch': 0.44}

  4%|▎         | 1023/28080 [2:01:07<53:16:21,  7.09s/it]
  4%|▎         | 1024/28080 [2:01:15<53:30:36,  7.12s/it]
                                                         
{'loss': 0.739, 'learning_rate': 0.0004999455205653078, 'epoch': 0.44}

  4%|▎         | 1024/28080 [2:01:15<53:30:36,  7.12s/it]
  4%|▎         | 1025/28080 [2:01:22<53:34:43,  7.13s/it]
                                                         
{'loss': 0.7496, 'learning_rate': 0.0004999449169418364, 'epoch': 0.44}

  4%|▎         | 1025/28080 [2:01:22<53:34:43,  7.13s/it]
  4%|▎         | 1026/28080 [2:01:29<53:33:21,  7.13s/it]
                                                         
{'loss': 0.7398, 'learning_rate': 0.0004999443099931057, 'epoch': 0.44}

  4%|▎         | 1026/28080 [2:01:29<53:33:21,  7.13s/it]
  4%|▎         | 1027/28080 [2:01:36<53:40:32,  7.14s/it]
                                                         
{'loss': 0.7334, 'learning_rate': 0.0004999436997191239, 'epoch': 0.44}

  4%|▎         | 1027/28080 [2:01:36<53:40:32,  7.14s/it]
  4%|▎         | 1028/28080 [2:01:43<53:30:40,  7.12s/it]
                                                         
{'loss': 0.7326, 'learning_rate': 0.0004999430861198991, 'epoch': 0.44}

  4%|▎         | 1028/28080 [2:01:43<53:30:40,  7.12s/it]
  4%|▎         | 1029/28080 [2:01:50<53:16:43,  7.09s/it]
                                                         
{'loss': 0.7381, 'learning_rate': 0.0004999424691954393, 'epoch': 0.44}

  4%|▎         | 1029/28080 [2:01:50<53:16:43,  7.09s/it]
  4%|▎         | 1030/28080 [2:01:57<53:22:39,  7.10s/it]
                                                         
{'loss': 0.7289, 'learning_rate': 0.0004999418489457528, 'epoch': 0.44}

  4%|▎         | 1030/28080 [2:01:57<53:22:39,  7.10s/it]
  4%|▎         | 1031/28080 [2:02:04<53:17:18,  7.09s/it]
                                                         
{'loss': 0.7265, 'learning_rate': 0.0004999412253708478, 'epoch': 0.44}

  4%|▎         | 1031/28080 [2:02:04<53:17:18,  7.09s/it]
  4%|▎         | 1032/28080 [2:02:11<53:11:50,  7.08s/it]
                                                         
{'loss': 0.7245, 'learning_rate': 0.0004999405984707326, 'epoch': 0.44}

  4%|▎         | 1032/28080 [2:02:11<53:11:50,  7.08s/it]
  4%|▎         | 1033/28080 [2:02:18<53:19:09,  7.10s/it]
                                                         
{'loss': 0.7539, 'learning_rate': 0.0004999399682454157, 'epoch': 0.44}

  4%|▎         | 1033/28080 [2:02:18<53:19:09,  7.10s/it]
  4%|▎         | 1034/28080 [2:02:26<53:25:51,  7.11s/it]
                                                         
{'loss': 0.7529, 'learning_rate': 0.0004999393346949054, 'epoch': 0.44}

  4%|▎         | 1034/28080 [2:02:26<53:25:51,  7.11s/it]
  4%|▎         | 1035/28080 [2:02:33<53:27:39,  7.12s/it]
                                                         
{'loss': 0.7427, 'learning_rate': 0.0004999386978192101, 'epoch': 0.44}

  4%|▎         | 1035/28080 [2:02:33<53:27:39,  7.12s/it]
  4%|▎         | 1036/28080 [2:02:40<53:30:09,  7.12s/it]
                                                         
{'loss': 0.7581, 'learning_rate': 0.0004999380576183382, 'epoch': 0.44}

  4%|▎         | 1036/28080 [2:02:40<53:30:09,  7.12s/it]
  4%|▎         | 1037/28080 [2:02:47<53:29:13,  7.12s/it]
                                                         
{'loss': 0.7383, 'learning_rate': 0.0004999374140922983, 'epoch': 0.44}

  4%|▎         | 1037/28080 [2:02:47<53:29:13,  7.12s/it]
  4%|▎         | 1038/28080 [2:02:54<53:20:41,  7.10s/it]
                                                         
{'loss': 0.7443, 'learning_rate': 0.0004999367672410991, 'epoch': 0.44}

  4%|▎         | 1038/28080 [2:02:54<53:20:41,  7.10s/it]
  4%|▎         | 1039/28080 [2:03:01<53:17:56,  7.10s/it]
                                                         
{'loss': 0.7427, 'learning_rate': 0.0004999361170647488, 'epoch': 0.44}

  4%|▎         | 1039/28080 [2:03:01<53:17:56,  7.10s/it]
  4%|▎         | 1040/28080 [2:03:08<53:09:44,  7.08s/it]
                                                         
{'loss': 0.7313, 'learning_rate': 0.0004999354635632564, 'epoch': 0.44}

  4%|▎         | 1040/28080 [2:03:08<53:09:44,  7.08s/it]
  4%|▎         | 1041/28080 [2:03:15<53:12:49,  7.08s/it]
                                                         
{'loss': 0.7403, 'learning_rate': 0.0004999348067366306, 'epoch': 0.44}

  4%|▎         | 1041/28080 [2:03:15<53:12:49,  7.08s/it]
  4%|▎         | 1042/28080 [2:03:22<53:20:21,  7.10s/it]
                                                         
{'loss': 0.7613, 'learning_rate': 0.00049993414658488, 'epoch': 0.45}

  4%|▎         | 1042/28080 [2:03:22<53:20:21,  7.10s/it]
  4%|▎         | 1043/28080 [2:03:29<53:13:25,  7.09s/it]
                                                         
{'loss': 0.7489, 'learning_rate': 0.0004999334831080134, 'epoch': 0.45}

  4%|▎         | 1043/28080 [2:03:29<53:13:25,  7.09s/it]
  4%|▎         | 1044/28080 [2:03:37<53:08:48,  7.08s/it]
                                                         
{'loss': 0.7348, 'learning_rate': 0.0004999328163060396, 'epoch': 0.45}

  4%|▎         | 1044/28080 [2:03:37<53:08:48,  7.08s/it]
  4%|▎         | 1045/28080 [2:03:44<53:13:41,  7.09s/it]
                                                         
{'loss': 0.7323, 'learning_rate': 0.0004999321461789676, 'epoch': 0.45}

  4%|▎         | 1045/28080 [2:03:44<53:13:41,  7.09s/it]
  4%|▎         | 1046/28080 [2:03:51<53:12:31,  7.09s/it]
                                                         
{'loss': 0.7368, 'learning_rate': 0.0004999314727268063, 'epoch': 0.45}

  4%|▎         | 1046/28080 [2:03:51<53:12:31,  7.09s/it]
  4%|▎         | 1047/28080 [2:03:58<53:23:36,  7.11s/it]
                                                         
{'loss': 0.7412, 'learning_rate': 0.0004999307959495644, 'epoch': 0.45}

  4%|▎         | 1047/28080 [2:03:58<53:23:36,  7.11s/it]
  4%|▎         | 1048/28080 [2:04:05<53:20:47,  7.10s/it]
                                                         
{'loss': 0.731, 'learning_rate': 0.0004999301158472513, 'epoch': 0.45}

  4%|▎         | 1048/28080 [2:04:05<53:20:47,  7.10s/it]
  4%|▎         | 1049/28080 [2:04:12<53:16:06,  7.09s/it]
                                                         
{'loss': 0.7422, 'learning_rate': 0.0004999294324198756, 'epoch': 0.45}

  4%|▎         | 1049/28080 [2:04:12<53:16:06,  7.09s/it]
  4%|▎         | 1050/28080 [2:04:19<53:21:44,  7.11s/it]
                                                         
{'loss': 0.7232, 'learning_rate': 0.0004999287456674468, 'epoch': 0.45}

  4%|▎         | 1050/28080 [2:04:19<53:21:44,  7.11s/it]
  4%|▎         | 1051/28080 [2:04:26<53:15:00,  7.09s/it]
                                                         
{'loss': 0.7431, 'learning_rate': 0.0004999280555899739, 'epoch': 0.45}

  4%|▎         | 1051/28080 [2:04:26<53:15:00,  7.09s/it]
  4%|▎         | 1052/28080 [2:04:33<53:20:19,  7.10s/it]
                                                         
{'loss': 0.7148, 'learning_rate': 0.000499927362187466, 'epoch': 0.45}

  4%|▎         | 1052/28080 [2:04:33<53:20:19,  7.10s/it]
  4%|▍         | 1053/28080 [2:04:40<53:03:25,  7.07s/it]
                                                         
{'loss': 0.7564, 'learning_rate': 0.0004999266654599325, 'epoch': 0.45}

  4%|▍         | 1053/28080 [2:04:40<53:03:25,  7.07s/it]
  4%|▍         | 1054/28080 [2:04:47<53:03:17,  7.07s/it]
                                                         
{'loss': 0.7209, 'learning_rate': 0.0004999259654073824, 'epoch': 0.45}

  4%|▍         | 1054/28080 [2:04:47<53:03:17,  7.07s/it]
  4%|▍         | 1055/28080 [2:04:55<53:10:09,  7.08s/it]
                                                         
{'loss': 0.7557, 'learning_rate': 0.0004999252620298253, 'epoch': 0.45}

  4%|▍         | 1055/28080 [2:04:55<53:10:09,  7.08s/it]
  4%|▍         | 1056/28080 [2:05:02<53:17:25,  7.10s/it]
                                                         
{'loss': 0.7291, 'learning_rate': 0.0004999245553272703, 'epoch': 0.45}

  4%|▍         | 1056/28080 [2:05:02<53:17:25,  7.10s/it]
  4%|▍         | 1057/28080 [2:05:09<53:21:32,  7.11s/it]
                                                         
{'loss': 0.7468, 'learning_rate': 0.0004999238452997269, 'epoch': 0.45}

  4%|▍         | 1057/28080 [2:05:09<53:21:32,  7.11s/it]
  4%|▍         | 1058/28080 [2:05:16<53:26:31,  7.12s/it]
                                                         
{'loss': 0.7351, 'learning_rate': 0.0004999231319472047, 'epoch': 0.45}

  4%|▍         | 1058/28080 [2:05:16<53:26:31,  7.12s/it]
  4%|▍         | 1059/28080 [2:05:23<53:21:41,  7.11s/it]
                                                         
{'loss': 0.7331, 'learning_rate': 0.0004999224152697129, 'epoch': 0.45}

  4%|▍         | 1059/28080 [2:05:23<53:21:41,  7.11s/it]
  4%|▍         | 1060/28080 [2:05:30<53:22:06,  7.11s/it]
                                                         
{'loss': 0.7404, 'learning_rate': 0.0004999216952672614, 'epoch': 0.45}

  4%|▍         | 1060/28080 [2:05:30<53:22:06,  7.11s/it]
  4%|▍         | 1061/28080 [2:05:37<53:16:06,  7.10s/it]
                                                         
{'loss': 0.7393, 'learning_rate': 0.0004999209719398594, 'epoch': 0.45}

  4%|▍         | 1061/28080 [2:05:37<53:16:06,  7.10s/it]
  4%|▍         | 1062/28080 [2:05:44<53:18:36,  7.10s/it]
                                                         
{'loss': 0.7386, 'learning_rate': 0.0004999202452875168, 'epoch': 0.45}

  4%|▍         | 1062/28080 [2:05:44<53:18:36,  7.10s/it]
  4%|▍         | 1063/28080 [2:05:51<53:19:58,  7.11s/it]
                                                         
{'loss': 0.7199, 'learning_rate': 0.0004999195153102431, 'epoch': 0.45}

  4%|▍         | 1063/28080 [2:05:51<53:19:58,  7.11s/it]
  4%|▍         | 1064/28080 [2:05:58<53:07:21,  7.08s/it]
                                                         
{'loss': 0.7676, 'learning_rate': 0.0004999187820080481, 'epoch': 0.45}

  4%|▍         | 1064/28080 [2:05:58<53:07:21,  7.08s/it]
  4%|▍         | 1065/28080 [2:06:06<53:17:20,  7.10s/it]
                                                         
{'loss': 0.7247, 'learning_rate': 0.0004999180453809415, 'epoch': 0.45}

  4%|▍         | 1065/28080 [2:06:06<53:17:20,  7.10s/it]
  4%|▍         | 1066/28080 [2:06:13<53:14:40,  7.10s/it]
                                                         
{'loss': 0.7387, 'learning_rate': 0.0004999173054289332, 'epoch': 0.46}

  4%|▍         | 1066/28080 [2:06:13<53:14:40,  7.10s/it]
  4%|▍         | 1067/28080 [2:06:20<53:16:21,  7.10s/it]
                                                         
{'loss': 0.7484, 'learning_rate': 0.0004999165621520329, 'epoch': 0.46}

  4%|▍         | 1067/28080 [2:06:20<53:16:21,  7.10s/it]
  4%|▍         | 1068/28080 [2:06:27<53:24:57,  7.12s/it]
                                                         
{'loss': 0.7281, 'learning_rate': 0.0004999158155502507, 'epoch': 0.46}

  4%|▍         | 1068/28080 [2:06:27<53:24:57,  7.12s/it]
  4%|▍         | 1069/28080 [2:06:34<53:33:52,  7.14s/it]
                                                         
{'loss': 0.7223, 'learning_rate': 0.0004999150656235963, 'epoch': 0.46}

  4%|▍         | 1069/28080 [2:06:34<53:33:52,  7.14s/it]
  4%|▍         | 1070/28080 [2:06:41<53:23:58,  7.12s/it]
                                                         
{'loss': 0.7341, 'learning_rate': 0.0004999143123720798, 'epoch': 0.46}

  4%|▍         | 1070/28080 [2:06:41<53:23:58,  7.12s/it]
  4%|▍         | 1071/28080 [2:06:48<53:23:17,  7.12s/it]
                                                         
{'loss': 0.7274, 'learning_rate': 0.0004999135557957112, 'epoch': 0.46}

  4%|▍         | 1071/28080 [2:06:48<53:23:17,  7.12s/it]
  4%|▍         | 1072/28080 [2:06:56<53:27:25,  7.13s/it]
                                                         
{'loss': 0.7328, 'learning_rate': 0.0004999127958945004, 'epoch': 0.46}

  4%|▍         | 1072/28080 [2:06:56<53:27:25,  7.13s/it]
  4%|▍         | 1073/28080 [2:07:02<53:09:03,  7.08s/it]
                                                         
{'loss': 0.7503, 'learning_rate': 0.0004999120326684578, 'epoch': 0.46}

  4%|▍         | 1073/28080 [2:07:02<53:09:03,  7.08s/it]
  4%|▍         | 1074/28080 [2:07:10<53:11:25,  7.09s/it]
                                                         
{'loss': 0.7327, 'learning_rate': 0.0004999112661175935, 'epoch': 0.46}

  4%|▍         | 1074/28080 [2:07:10<53:11:25,  7.09s/it]
  4%|▍         | 1075/28080 [2:07:17<53:07:59,  7.08s/it]
                                                         
{'loss': 0.7506, 'learning_rate': 0.0004999104962419176, 'epoch': 0.46}

  4%|▍         | 1075/28080 [2:07:17<53:07:59,  7.08s/it]
  4%|▍         | 1076/28080 [2:07:24<53:20:04,  7.11s/it]
                                                         
{'loss': 0.7163, 'learning_rate': 0.0004999097230414403, 'epoch': 0.46}

  4%|▍         | 1076/28080 [2:07:24<53:20:04,  7.11s/it]
  4%|▍         | 1077/28080 [2:07:31<53:19:01,  7.11s/it]
                                                         
{'loss': 0.7379, 'learning_rate': 0.0004999089465161719, 'epoch': 0.46}

  4%|▍         | 1077/28080 [2:07:31<53:19:01,  7.11s/it]
  4%|▍         | 1078/28080 [2:07:38<53:37:56,  7.15s/it]
                                                         
{'loss': 0.7228, 'learning_rate': 0.0004999081666661229, 'epoch': 0.46}

  4%|▍         | 1078/28080 [2:07:38<53:37:56,  7.15s/it]
  4%|▍         | 1079/28080 [2:07:45<53:28:57,  7.13s/it]
                                                         
{'loss': 0.7438, 'learning_rate': 0.0004999073834913036, 'epoch': 0.46}

  4%|▍         | 1079/28080 [2:07:45<53:28:57,  7.13s/it]
  4%|▍         | 1080/28080 [2:07:52<53:12:50,  7.10s/it]
                                                         
{'loss': 0.7522, 'learning_rate': 0.0004999065969917242, 'epoch': 0.46}

  4%|▍         | 1080/28080 [2:07:52<53:12:50,  7.10s/it]
  4%|▍         | 1081/28080 [2:07:59<53:03:31,  7.07s/it]
                                                         
{'loss': 0.7121, 'learning_rate': 0.0004999058071673956, 'epoch': 0.46}

  4%|▍         | 1081/28080 [2:07:59<53:03:31,  7.07s/it]
  4%|▍         | 1082/28080 [2:08:06<53:07:48,  7.08s/it]
                                                         
{'loss': 0.7444, 'learning_rate': 0.0004999050140183278, 'epoch': 0.46}

  4%|▍         | 1082/28080 [2:08:06<53:07:48,  7.08s/it]
  4%|▍         | 1083/28080 [2:08:13<53:05:01,  7.08s/it]
                                                         
{'loss': 0.7324, 'learning_rate': 0.0004999042175445317, 'epoch': 0.46}

  4%|▍         | 1083/28080 [2:08:13<53:05:01,  7.08s/it]
  4%|▍         | 1084/28080 [2:08:21<53:18:21,  7.11s/it]
                                                         
{'loss': 0.741, 'learning_rate': 0.0004999034177460178, 'epoch': 0.46}

  4%|▍         | 1084/28080 [2:08:21<53:18:21,  7.11s/it]
  4%|▍         | 1085/28080 [2:08:28<53:17:36,  7.11s/it]
                                                         
{'loss': 0.7323, 'learning_rate': 0.0004999026146227967, 'epoch': 0.46}

  4%|▍         | 1085/28080 [2:08:28<53:17:36,  7.11s/it]
  4%|▍         | 1086/28080 [2:08:35<53:05:54,  7.08s/it]
                                                         
{'loss': 0.7443, 'learning_rate': 0.0004999018081748791, 'epoch': 0.46}

  4%|▍         | 1086/28080 [2:08:35<53:05:54,  7.08s/it]
  4%|▍         | 1087/28080 [2:08:42<53:06:01,  7.08s/it]
                                                         
{'loss': 0.7266, 'learning_rate': 0.0004999009984022758, 'epoch': 0.46}

  4%|▍         | 1087/28080 [2:08:42<53:06:01,  7.08s/it]
  4%|▍         | 1088/28080 [2:08:49<53:14:30,  7.10s/it]
                                                         
{'loss': 0.732, 'learning_rate': 0.0004999001853049975, 'epoch': 0.46}

  4%|▍         | 1088/28080 [2:08:49<53:14:30,  7.10s/it]
  4%|▍         | 1089/28080 [2:08:56<53:07:52,  7.09s/it]
                                                         
{'loss': 0.7642, 'learning_rate': 0.0004998993688830551, 'epoch': 0.47}

  4%|▍         | 1089/28080 [2:08:56<53:07:52,  7.09s/it]
  4%|▍         | 1090/28080 [2:09:03<53:10:38,  7.09s/it]
                                                         
{'loss': 0.7357, 'learning_rate': 0.0004998985491364594, 'epoch': 0.47}

  4%|▍         | 1090/28080 [2:09:03<53:10:38,  7.09s/it]
  4%|▍         | 1091/28080 [2:09:10<53:04:09,  7.08s/it]
                                                         
{'loss': 0.7498, 'learning_rate': 0.0004998977260652213, 'epoch': 0.47}

  4%|▍         | 1091/28080 [2:09:10<53:04:09,  7.08s/it]
  4%|▍         | 1092/28080 [2:09:17<52:56:58,  7.06s/it]
                                                         
{'loss': 0.7369, 'learning_rate': 0.0004998968996693517, 'epoch': 0.47}

  4%|▍         | 1092/28080 [2:09:17<52:56:58,  7.06s/it]
  4%|▍         | 1093/28080 [2:09:24<52:50:06,  7.05s/it]
                                                         
{'loss': 0.7509, 'learning_rate': 0.0004998960699488617, 'epoch': 0.47}

  4%|▍         | 1093/28080 [2:09:24<52:50:06,  7.05s/it]
  4%|▍         | 1094/28080 [2:09:31<52:46:11,  7.04s/it]
                                                         
{'loss': 0.7442, 'learning_rate': 0.0004998952369037622, 'epoch': 0.47}

  4%|▍         | 1094/28080 [2:09:31<52:46:11,  7.04s/it]
  4%|▍         | 1095/28080 [2:09:38<52:54:25,  7.06s/it]
                                                         
{'loss': 0.7336, 'learning_rate': 0.0004998944005340645, 'epoch': 0.47}

  4%|▍         | 1095/28080 [2:09:38<52:54:25,  7.06s/it]
  4%|▍         | 1096/28080 [2:09:46<53:05:46,  7.08s/it]
                                                         
{'loss': 0.723, 'learning_rate': 0.0004998935608397796, 'epoch': 0.47}

  4%|▍         | 1096/28080 [2:09:46<53:05:46,  7.08s/it]
  4%|▍         | 1097/28080 [2:09:53<52:55:54,  7.06s/it]
                                                         
{'loss': 0.734, 'learning_rate': 0.0004998927178209186, 'epoch': 0.47}

  4%|▍         | 1097/28080 [2:09:53<52:55:54,  7.06s/it]
  4%|▍         | 1098/28080 [2:10:00<53:07:06,  7.09s/it]
                                                         
{'loss': 0.7507, 'learning_rate': 0.0004998918714774928, 'epoch': 0.47}

  4%|▍         | 1098/28080 [2:10:00<53:07:06,  7.09s/it]
  4%|▍         | 1099/28080 [2:10:07<53:10:35,  7.10s/it]
                                                         
{'loss': 0.766, 'learning_rate': 0.0004998910218095135, 'epoch': 0.47}

  4%|▍         | 1099/28080 [2:10:07<53:10:35,  7.10s/it]
  4%|▍         | 1100/28080 [2:10:14<53:16:36,  7.11s/it]
                                                         
{'loss': 0.7236, 'learning_rate': 0.000499890168816992, 'epoch': 0.47}

  4%|▍         | 1100/28080 [2:10:14<53:16:36,  7.11s/it]
  4%|▍         | 1101/28080 [2:10:21<53:24:04,  7.13s/it]
                                                         
{'loss': 0.74, 'learning_rate': 0.0004998893124999396, 'epoch': 0.47}

  4%|▍         | 1101/28080 [2:10:21<53:24:04,  7.13s/it]
  4%|▍         | 1102/28080 [2:10:28<53:26:57,  7.13s/it]
                                                         
{'loss': 0.7344, 'learning_rate': 0.0004998884528583675, 'epoch': 0.47}

  4%|▍         | 1102/28080 [2:10:28<53:26:57,  7.13s/it]
  4%|▍         | 1103/28080 [2:10:35<53:34:11,  7.15s/it]
                                                         
{'loss': 0.7305, 'learning_rate': 0.0004998875898922875, 'epoch': 0.47}

  4%|▍         | 1103/28080 [2:10:35<53:34:11,  7.15s/it]
  4%|▍         | 1104/28080 [2:10:43<53:25:35,  7.13s/it]
                                                         
{'loss': 0.7439, 'learning_rate': 0.0004998867236017108, 'epoch': 0.47}

  4%|▍         | 1104/28080 [2:10:43<53:25:35,  7.13s/it]
  4%|▍         | 1105/28080 [2:10:50<53:24:24,  7.13s/it]
                                                         
{'loss': 0.7329, 'learning_rate': 0.0004998858539866492, 'epoch': 0.47}

  4%|▍         | 1105/28080 [2:10:50<53:24:24,  7.13s/it]
  4%|▍         | 1106/28080 [2:10:57<53:22:23,  7.12s/it]
                                                         
{'loss': 0.732, 'learning_rate': 0.000499884981047114, 'epoch': 0.47}

  4%|▍         | 1106/28080 [2:10:57<53:22:23,  7.12s/it]
  4%|▍         | 1107/28080 [2:11:04<53:22:14,  7.12s/it]
                                                         
{'loss': 0.7351, 'learning_rate': 0.0004998841047831169, 'epoch': 0.47}

  4%|▍         | 1107/28080 [2:11:04<53:22:14,  7.12s/it]
  4%|▍         | 1108/28080 [2:11:11<53:36:30,  7.16s/it]
                                                         
{'loss': 0.7438, 'learning_rate': 0.0004998832251946696, 'epoch': 0.47}

  4%|▍         | 1108/28080 [2:11:11<53:36:30,  7.16s/it]
  4%|▍         | 1109/28080 [2:11:18<53:22:06,  7.12s/it]
                                                         
{'loss': 0.7272, 'learning_rate': 0.0004998823422817837, 'epoch': 0.47}

  4%|▍         | 1109/28080 [2:11:18<53:22:06,  7.12s/it]
  4%|▍         | 1110/28080 [2:11:25<53:28:53,  7.14s/it]
                                                         
{'loss': 0.7493, 'learning_rate': 0.0004998814560444713, 'epoch': 0.47}

  4%|▍         | 1110/28080 [2:11:25<53:28:53,  7.14s/it]
  4%|▍         | 1111/28080 [2:11:32<53:13:17,  7.10s/it]
                                                         
{'loss': 0.7279, 'learning_rate': 0.0004998805664827436, 'epoch': 0.47}

  4%|▍         | 1111/28080 [2:11:32<53:13:17,  7.10s/it]
  4%|▍         | 1112/28080 [2:11:40<53:23:38,  7.13s/it]
                                                         
{'loss': 0.7322, 'learning_rate': 0.0004998796735966129, 'epoch': 0.48}

  4%|▍         | 1112/28080 [2:11:40<53:23:38,  7.13s/it]
  4%|▍         | 1113/28080 [2:11:47<53:14:10,  7.11s/it]
                                                         
{'loss': 0.744, 'learning_rate': 0.0004998787773860909, 'epoch': 0.48}

  4%|▍         | 1113/28080 [2:11:47<53:14:10,  7.11s/it]
  4%|▍         | 1114/28080 [2:11:54<53:29:54,  7.14s/it]
                                                         
{'loss': 0.7321, 'learning_rate': 0.0004998778778511896, 'epoch': 0.48}

  4%|▍         | 1114/28080 [2:11:54<53:29:54,  7.14s/it]
  4%|▍         | 1115/28080 [2:12:01<53:29:03,  7.14s/it]
                                                         
{'loss': 0.7351, 'learning_rate': 0.0004998769749919209, 'epoch': 0.48}

  4%|▍         | 1115/28080 [2:12:01<53:29:03,  7.14s/it]
  4%|▍         | 1116/28080 [2:12:08<53:17:08,  7.11s/it]
                                                         
{'loss': 0.7365, 'learning_rate': 0.0004998760688082967, 'epoch': 0.48}

  4%|▍         | 1116/28080 [2:12:08<53:17:08,  7.11s/it]
  4%|▍         | 1117/28080 [2:12:15<53:16:49,  7.11s/it]
                                                         
{'loss': 0.718, 'learning_rate': 0.0004998751593003293, 'epoch': 0.48}

  4%|▍         | 1117/28080 [2:12:15<53:16:49,  7.11s/it]
  4%|▍         | 1118/28080 [2:12:22<53:27:18,  7.14s/it]
                                                         
{'loss': 0.7262, 'learning_rate': 0.0004998742464680307, 'epoch': 0.48}

  4%|▍         | 1118/28080 [2:12:22<53:27:18,  7.14s/it]
  4%|▍         | 1119/28080 [2:12:29<53:12:32,  7.10s/it]
                                                         
{'loss': 0.7555, 'learning_rate': 0.0004998733303114131, 'epoch': 0.48}

  4%|▍         | 1119/28080 [2:12:29<53:12:32,  7.10s/it]
  4%|▍         | 1120/28080 [2:12:36<53:17:37,  7.12s/it]
                                                         
{'loss': 0.74, 'learning_rate': 0.0004998724108304885, 'epoch': 0.48}

  4%|▍         | 1120/28080 [2:12:36<53:17:37,  7.12s/it]
  4%|▍         | 1121/28080 [2:12:44<53:09:11,  7.10s/it]
                                                         
{'loss': 0.7587, 'learning_rate': 0.0004998714880252693, 'epoch': 0.48}

  4%|▍         | 1121/28080 [2:12:44<53:09:11,  7.10s/it]
  4%|▍         | 1122/28080 [2:12:51<53:02:29,  7.08s/it]
                                                         
{'loss': 0.7254, 'learning_rate': 0.0004998705618957677, 'epoch': 0.48}

  4%|▍         | 1122/28080 [2:12:51<53:02:29,  7.08s/it]
  4%|▍         | 1123/28080 [2:12:58<53:08:57,  7.10s/it]
                                                         
{'loss': 0.7306, 'learning_rate': 0.000499869632441996, 'epoch': 0.48}

  4%|▍         | 1123/28080 [2:12:58<53:08:57,  7.10s/it]
  4%|▍         | 1124/28080 [2:13:05<52:58:30,  7.07s/it]
                                                         
{'loss': 0.7326, 'learning_rate': 0.0004998686996639667, 'epoch': 0.48}

  4%|▍         | 1124/28080 [2:13:05<52:58:30,  7.07s/it]
  4%|▍         | 1125/28080 [2:13:12<52:59:52,  7.08s/it]
                                                         
{'loss': 0.7583, 'learning_rate': 0.0004998677635616921, 'epoch': 0.48}

  4%|▍         | 1125/28080 [2:13:12<52:59:52,  7.08s/it]
  4%|▍         | 1126/28080 [2:13:19<52:59:35,  7.08s/it]
                                                         
{'loss': 0.749, 'learning_rate': 0.0004998668241351846, 'epoch': 0.48}

  4%|▍         | 1126/28080 [2:13:19<52:59:35,  7.08s/it]
  4%|▍         | 1127/28080 [2:13:26<53:02:18,  7.08s/it]
                                                         
{'loss': 0.7284, 'learning_rate': 0.000499865881384457, 'epoch': 0.48}

  4%|▍         | 1127/28080 [2:13:26<53:02:18,  7.08s/it]
  4%|▍         | 1128/28080 [2:13:33<52:54:37,  7.07s/it]
                                                         
{'loss': 0.726, 'learning_rate': 0.0004998649353095215, 'epoch': 0.48}

  4%|▍         | 1128/28080 [2:13:33<52:54:37,  7.07s/it]
  4%|▍         | 1129/28080 [2:13:40<53:00:39,  7.08s/it]
                                                         
{'loss': 0.7371, 'learning_rate': 0.0004998639859103908, 'epoch': 0.48}

  4%|▍         | 1129/28080 [2:13:40<53:00:39,  7.08s/it]
  4%|▍         | 1130/28080 [2:13:47<52:55:40,  7.07s/it]
                                                         
{'loss': 0.7336, 'learning_rate': 0.0004998630331870775, 'epoch': 0.48}

  4%|▍         | 1130/28080 [2:13:47<52:55:40,  7.07s/it]
  4%|▍         | 1131/28080 [2:13:54<53:05:00,  7.09s/it]
                                                         
{'loss': 0.7464, 'learning_rate': 0.0004998620771395944, 'epoch': 0.48}

  4%|▍         | 1131/28080 [2:13:54<53:05:00,  7.09s/it]
  4%|▍         | 1132/28080 [2:14:01<53:10:16,  7.10s/it]
                                                         
{'loss': 0.7395, 'learning_rate': 0.000499861117767954, 'epoch': 0.48}

  4%|▍         | 1132/28080 [2:14:01<53:10:16,  7.10s/it]
  4%|▍         | 1133/28080 [2:14:09<53:09:49,  7.10s/it]
                                                         
{'loss': 0.7214, 'learning_rate': 0.0004998601550721693, 'epoch': 0.48}

  4%|▍         | 1133/28080 [2:14:09<53:09:49,  7.10s/it]
  4%|▍         | 1134/28080 [2:14:16<53:03:26,  7.09s/it]
                                                         
{'loss': 0.7296, 'learning_rate': 0.000499859189052253, 'epoch': 0.48}

  4%|▍         | 1134/28080 [2:14:16<53:03:26,  7.09s/it]
  4%|▍         | 1135/28080 [2:14:23<53:09:08,  7.10s/it]
                                                         
{'loss': 0.7259, 'learning_rate': 0.0004998582197082179, 'epoch': 0.48}

  4%|▍         | 1135/28080 [2:14:23<53:09:08,  7.10s/it]
  4%|▍         | 1136/28080 [2:14:30<53:09:16,  7.10s/it]
                                                         
{'loss': 0.7298, 'learning_rate': 0.000499857247040077, 'epoch': 0.49}

  4%|▍         | 1136/28080 [2:14:30<53:09:16,  7.10s/it]
  4%|▍         | 1137/28080 [2:14:37<53:18:15,  7.12s/it]
                                                         
{'loss': 0.738, 'learning_rate': 0.0004998562710478432, 'epoch': 0.49}

  4%|▍         | 1137/28080 [2:14:37<53:18:15,  7.12s/it]
  4%|▍         | 1138/28080 [2:14:44<53:19:08,  7.12s/it]
                                                         
{'loss': 0.758, 'learning_rate': 0.0004998552917315295, 'epoch': 0.49}

  4%|▍         | 1138/28080 [2:14:44<53:19:08,  7.12s/it]
  4%|▍         | 1139/28080 [2:14:51<53:02:55,  7.09s/it]
                                                         
{'loss': 0.748, 'learning_rate': 0.0004998543090911488, 'epoch': 0.49}

  4%|▍         | 1139/28080 [2:14:51<53:02:55,  7.09s/it]
  4%|▍         | 1140/28080 [2:14:58<53:05:58,  7.10s/it]
                                                         
{'loss': 0.7443, 'learning_rate': 0.0004998533231267144, 'epoch': 0.49}

  4%|▍         | 1140/28080 [2:14:58<53:05:58,  7.10s/it]
  4%|▍         | 1141/28080 [2:15:05<53:13:23,  7.11s/it]
                                                         
{'loss': 0.7568, 'learning_rate': 0.0004998523338382391, 'epoch': 0.49}

  4%|▍         | 1141/28080 [2:15:05<53:13:23,  7.11s/it]
  4%|▍         | 1142/28080 [2:15:13<53:13:12,  7.11s/it]
                                                         
{'loss': 0.742, 'learning_rate': 0.0004998513412257364, 'epoch': 0.49}

  4%|▍         | 1142/28080 [2:15:13<53:13:12,  7.11s/it]
  4%|▍         | 1143/28080 [2:15:20<53:12:54,  7.11s/it]
                                                         
{'loss': 0.7366, 'learning_rate': 0.0004998503452892195, 'epoch': 0.49}

  4%|▍         | 1143/28080 [2:15:20<53:12:54,  7.11s/it]
  4%|▍         | 1144/28080 [2:15:27<53:00:16,  7.08s/it]
                                                         
{'loss': 0.7417, 'learning_rate': 0.0004998493460287013, 'epoch': 0.49}

  4%|▍         | 1144/28080 [2:15:27<53:00:16,  7.08s/it]
  4%|▍         | 1145/28080 [2:15:34<53:08:01,  7.10s/it]
                                                         
{'loss': 0.7302, 'learning_rate': 0.0004998483434441953, 'epoch': 0.49}

  4%|▍         | 1145/28080 [2:15:34<53:08:01,  7.10s/it]
  4%|▍         | 1146/28080 [2:15:41<53:04:15,  7.09s/it]
                                                         
{'loss': 0.7356, 'learning_rate': 0.000499847337535715, 'epoch': 0.49}

  4%|▍         | 1146/28080 [2:15:41<53:04:15,  7.09s/it]
  4%|▍         | 1147/28080 [2:15:48<53:10:57,  7.11s/it]
                                                         
{'loss': 0.7019, 'learning_rate': 0.0004998463283032734, 'epoch': 0.49}

  4%|▍         | 1147/28080 [2:15:48<53:10:57,  7.11s/it]
  4%|▍         | 1148/28080 [2:15:55<53:07:59,  7.10s/it]
                                                         
{'loss': 0.737, 'learning_rate': 0.0004998453157468844, 'epoch': 0.49}

  4%|▍         | 1148/28080 [2:15:55<53:07:59,  7.10s/it]
  4%|▍         | 1149/28080 [2:16:02<53:13:59,  7.12s/it]
                                                         
{'loss': 0.7409, 'learning_rate': 0.0004998442998665611, 'epoch': 0.49}

  4%|▍         | 1149/28080 [2:16:02<53:13:59,  7.12s/it]
  4%|▍         | 1150/28080 [2:16:09<53:10:31,  7.11s/it]
                                                         
{'loss': 0.7283, 'learning_rate': 0.0004998432806623172, 'epoch': 0.49}

  4%|▍         | 1150/28080 [2:16:09<53:10:31,  7.11s/it]
  4%|▍         | 1151/28080 [2:16:16<53:13:48,  7.12s/it]
                                                         
{'loss': 0.7447, 'learning_rate': 0.0004998422581341661, 'epoch': 0.49}

  4%|▍         | 1151/28080 [2:16:16<53:13:48,  7.12s/it]
  4%|▍         | 1152/28080 [2:16:24<53:25:34,  7.14s/it]
                                                         
{'loss': 0.7039, 'learning_rate': 0.0004998412322821216, 'epoch': 0.49}

  4%|▍         | 1152/28080 [2:16:24<53:25:34,  7.14s/it]
  4%|▍         | 1153/28080 [2:16:31<53:29:34,  7.15s/it]
                                                         
{'loss': 0.7294, 'learning_rate': 0.0004998402031061971, 'epoch': 0.49}

  4%|▍         | 1153/28080 [2:16:31<53:29:34,  7.15s/it]
  4%|▍         | 1154/28080 [2:16:38<53:26:11,  7.14s/it]
                                                         
{'loss': 0.7267, 'learning_rate': 0.0004998391706064067, 'epoch': 0.49}

  4%|▍         | 1154/28080 [2:16:38<53:26:11,  7.14s/it]
  4%|▍         | 1155/28080 [2:16:45<53:11:51,  7.11s/it]
                                                         
{'loss': 0.7335, 'learning_rate': 0.0004998381347827637, 'epoch': 0.49}

  4%|▍         | 1155/28080 [2:16:45<53:11:51,  7.11s/it]
  4%|▍         | 1156/28080 [2:16:52<53:07:24,  7.10s/it]
                                                         
{'loss': 0.7343, 'learning_rate': 0.0004998370956352821, 'epoch': 0.49}

  4%|▍         | 1156/28080 [2:16:52<53:07:24,  7.10s/it]
  4%|▍         | 1157/28080 [2:16:59<53:07:17,  7.10s/it]
                                                         
{'loss': 0.7426, 'learning_rate': 0.0004998360531639756, 'epoch': 0.49}

  4%|▍         | 1157/28080 [2:16:59<53:07:17,  7.10s/it]
  4%|▍         | 1158/28080 [2:17:06<53:06:25,  7.10s/it]
                                                         
{'loss': 0.7236, 'learning_rate': 0.0004998350073688583, 'epoch': 0.49}

  4%|▍         | 1158/28080 [2:17:06<53:06:25,  7.10s/it]
  4%|▍         | 1159/28080 [2:17:13<53:06:48,  7.10s/it]
                                                         
{'loss': 0.7362, 'learning_rate': 0.0004998339582499439, 'epoch': 0.5}

  4%|▍         | 1159/28080 [2:17:13<53:06:48,  7.10s/it]
  4%|▍         | 1160/28080 [2:17:21<53:26:03,  7.15s/it]
                                                         
{'loss': 0.7229, 'learning_rate': 0.0004998329058072465, 'epoch': 0.5}

  4%|▍         | 1160/28080 [2:17:21<53:26:03,  7.15s/it]
  4%|▍         | 1161/28080 [2:17:28<53:16:17,  7.12s/it]
                                                         
{'loss': 0.7253, 'learning_rate': 0.0004998318500407799, 'epoch': 0.5}

  4%|▍         | 1161/28080 [2:17:28<53:16:17,  7.12s/it]
  4%|▍         | 1162/28080 [2:17:35<52:49:28,  7.06s/it]
                                                         
{'loss': 0.7981, 'learning_rate': 0.0004998307909505582, 'epoch': 0.5}

  4%|▍         | 1162/28080 [2:17:35<52:49:28,  7.06s/it]
  4%|▍         | 1163/28080 [2:17:42<52:33:40,  7.03s/it]
                                                         
{'loss': 0.7509, 'learning_rate': 0.0004998297285365958, 'epoch': 0.5}

  4%|▍         | 1163/28080 [2:17:42<52:33:40,  7.03s/it]
  4%|▍         | 1164/28080 [2:17:49<52:54:11,  7.08s/it]
                                                         
{'loss': 0.7177, 'learning_rate': 0.0004998286627989065, 'epoch': 0.5}

  4%|▍         | 1164/28080 [2:17:49<52:54:11,  7.08s/it]
  4%|▍         | 1165/28080 [2:17:56<53:12:25,  7.12s/it]
                                                         
{'loss': 0.7165, 'learning_rate': 0.0004998275937375046, 'epoch': 0.5}

  4%|▍         | 1165/28080 [2:17:56<53:12:25,  7.12s/it]
  4%|▍         | 1166/28080 [2:18:03<53:23:12,  7.14s/it]
                                                         
{'loss': 0.7221, 'learning_rate': 0.0004998265213524043, 'epoch': 0.5}

  4%|▍         | 1166/28080 [2:18:03<53:23:12,  7.14s/it]
  4%|▍         | 1167/28080 [2:18:10<53:13:35,  7.12s/it]
                                                         
{'loss': 0.7372, 'learning_rate': 0.0004998254456436197, 'epoch': 0.5}

  4%|▍         | 1167/28080 [2:18:10<53:13:35,  7.12s/it]
  4%|▍         | 1168/28080 [2:18:17<53:23:38,  7.14s/it]
                                                         
{'loss': 0.7262, 'learning_rate': 0.0004998243666111654, 'epoch': 0.5}

  4%|▍         | 1168/28080 [2:18:17<53:23:38,  7.14s/it]
  4%|▍         | 1169/28080 [2:18:25<53:37:35,  7.17s/it]
                                                         
{'loss': 0.7325, 'learning_rate': 0.0004998232842550556, 'epoch': 0.5}

  4%|▍         | 1169/28080 [2:18:25<53:37:35,  7.17s/it]
  4%|▍         | 1170/28080 [2:18:32<53:30:57,  7.16s/it]
                                                         
{'loss': 0.7459, 'learning_rate': 0.0004998221985753049, 'epoch': 0.5}

  4%|▍         | 1170/28080 [2:18:32<53:30:57,  7.16s/it]
  4%|▍         | 1171/28080 [2:18:39<53:30:01,  7.16s/it]
                                                         
{'loss': 0.7164, 'learning_rate': 0.0004998211095719274, 'epoch': 0.5}

  4%|▍         | 1171/28080 [2:18:39<53:30:01,  7.16s/it]
  4%|▍         | 1172/28080 [2:18:46<53:17:19,  7.13s/it]
                                                         
{'loss': 0.7496, 'learning_rate': 0.0004998200172449378, 'epoch': 0.5}

  4%|▍         | 1172/28080 [2:18:46<53:17:19,  7.13s/it]
  4%|▍         | 1173/28080 [2:18:53<53:00:15,  7.09s/it]
                                                         
{'loss': 0.7415, 'learning_rate': 0.0004998189215943506, 'epoch': 0.5}

  4%|▍         | 1173/28080 [2:18:53<53:00:15,  7.09s/it]
  4%|▍         | 1174/28080 [2:19:00<52:56:04,  7.08s/it]
                                                         
{'loss': 0.757, 'learning_rate': 0.0004998178226201804, 'epoch': 0.5}

  4%|▍         | 1174/28080 [2:19:00<52:56:04,  7.08s/it]
  4%|▍         | 1175/28080 [2:19:07<53:08:38,  7.11s/it]
                                                         
{'loss': 0.7389, 'learning_rate': 0.0004998167203224417, 'epoch': 0.5}

  4%|▍         | 1175/28080 [2:19:07<53:08:38,  7.11s/it]
  4%|▍         | 1176/28080 [2:19:14<53:07:00,  7.11s/it]
                                                         
{'loss': 0.7335, 'learning_rate': 0.0004998156147011494, 'epoch': 0.5}

  4%|▍         | 1176/28080 [2:19:14<53:07:00,  7.11s/it]
  4%|▍         | 1177/28080 [2:19:22<53:12:50,  7.12s/it]
                                                         
{'loss': 0.7516, 'learning_rate': 0.0004998145057563179, 'epoch': 0.5}

  4%|▍         | 1177/28080 [2:19:22<53:12:50,  7.12s/it]
  4%|▍         | 1178/28080 [2:19:29<53:08:57,  7.11s/it]
                                                         
{'loss': 0.7434, 'learning_rate': 0.0004998133934879623, 'epoch': 0.5}

  4%|▍         | 1178/28080 [2:19:29<53:08:57,  7.11s/it]
  4%|▍         | 1179/28080 [2:19:36<53:21:56,  7.14s/it]
                                                         
{'loss': 0.7289, 'learning_rate': 0.0004998122778960971, 'epoch': 0.5}

  4%|▍         | 1179/28080 [2:19:36<53:21:56,  7.14s/it]
  4%|▍         | 1180/28080 [2:19:43<53:07:23,  7.11s/it]
                                                         
{'loss': 0.7348, 'learning_rate': 0.0004998111589807373, 'epoch': 0.5}

  4%|▍         | 1180/28080 [2:19:43<53:07:23,  7.11s/it]
  4%|▍         | 1181/28080 [2:19:50<53:13:26,  7.12s/it]
                                                         
{'loss': 0.7247, 'learning_rate': 0.0004998100367418977, 'epoch': 0.5}

  4%|▍         | 1181/28080 [2:19:50<53:13:26,  7.12s/it]
  4%|▍         | 1182/28080 [2:19:57<53:17:51,  7.13s/it]
                                                         
{'loss': 0.7321, 'learning_rate': 0.0004998089111795933, 'epoch': 0.5}

  4%|▍         | 1182/28080 [2:19:57<53:17:51,  7.13s/it]
  4%|▍         | 1183/28080 [2:20:04<53:13:58,  7.12s/it]
                                                         
{'loss': 0.7165, 'learning_rate': 0.0004998077822938391, 'epoch': 0.51}

  4%|▍         | 1183/28080 [2:20:04<53:13:58,  7.12s/it]
  4%|▍         | 1184/28080 [2:20:11<53:04:18,  7.10s/it]
                                                         
{'loss': 0.7387, 'learning_rate': 0.00049980665008465, 'epoch': 0.51}

  4%|▍         | 1184/28080 [2:20:11<53:04:18,  7.10s/it]
  4%|▍         | 1185/28080 [2:20:19<53:11:00,  7.12s/it]
                                                         
{'loss': 0.7149, 'learning_rate': 0.0004998055145520411, 'epoch': 0.51}

  4%|▍         | 1185/28080 [2:20:19<53:11:00,  7.12s/it]
  4%|▍         | 1186/28080 [2:20:26<53:01:56,  7.10s/it]
                                                         
{'loss': 0.7134, 'learning_rate': 0.0004998043756960276, 'epoch': 0.51}

  4%|▍         | 1186/28080 [2:20:26<53:01:56,  7.10s/it]
  4%|▍         | 1187/28080 [2:20:33<53:11:41,  7.12s/it]
                                                         
{'loss': 0.721, 'learning_rate': 0.0004998032335166246, 'epoch': 0.51}

  4%|▍         | 1187/28080 [2:20:33<53:11:41,  7.12s/it]
  4%|▍         | 1188/28080 [2:20:40<52:56:45,  7.09s/it]
                                                         
{'loss': 0.7354, 'learning_rate': 0.0004998020880138473, 'epoch': 0.51}

  4%|▍         | 1188/28080 [2:20:40<52:56:45,  7.09s/it]
  4%|▍         | 1189/28080 [2:20:47<52:57:17,  7.09s/it]
                                                         
{'loss': 0.7251, 'learning_rate': 0.0004998009391877109, 'epoch': 0.51}

  4%|▍         | 1189/28080 [2:20:47<52:57:17,  7.09s/it]
  4%|▍         | 1190/28080 [2:20:54<53:07:09,  7.11s/it]
                                                         
{'loss': 0.7217, 'learning_rate': 0.0004997997870382307, 'epoch': 0.51}

  4%|▍         | 1190/28080 [2:20:54<53:07:09,  7.11s/it]
  4%|▍         | 1191/28080 [2:21:01<52:52:43,  7.08s/it]
                                                         
{'loss': 0.7354, 'learning_rate': 0.000499798631565422, 'epoch': 0.51}

  4%|▍         | 1191/28080 [2:21:01<52:52:43,  7.08s/it]
  4%|▍         | 1192/28080 [2:21:08<52:57:34,  7.09s/it]
                                                         
{'loss': 0.7439, 'learning_rate': 0.0004997974727693003, 'epoch': 0.51}

  4%|▍         | 1192/28080 [2:21:08<52:57:34,  7.09s/it]
  4%|▍         | 1193/28080 [2:21:15<52:52:26,  7.08s/it]
                                                         
{'loss': 0.7302, 'learning_rate': 0.0004997963106498809, 'epoch': 0.51}

  4%|▍         | 1193/28080 [2:21:15<52:52:26,  7.08s/it]
  4%|▍         | 1194/28080 [2:21:22<53:08:55,  7.12s/it]
                                                         
{'loss': 0.7223, 'learning_rate': 0.0004997951452071793, 'epoch': 0.51}

  4%|▍         | 1194/28080 [2:21:22<53:08:55,  7.12s/it]
  4%|▍         | 1195/28080 [2:21:29<53:05:59,  7.11s/it]
                                                         
{'loss': 0.7343, 'learning_rate': 0.000499793976441211, 'epoch': 0.51}

  4%|▍         | 1195/28080 [2:21:29<53:05:59,  7.11s/it]
  4%|▍         | 1196/28080 [2:21:37<53:03:00,  7.10s/it]
                                                         
{'loss': 0.7476, 'learning_rate': 0.0004997928043519914, 'epoch': 0.51}

  4%|▍         | 1196/28080 [2:21:37<53:03:00,  7.10s/it]
  4%|▍         | 1197/28080 [2:21:44<53:13:26,  7.13s/it]
                                                         
{'loss': 0.7301, 'learning_rate': 0.0004997916289395364, 'epoch': 0.51}

  4%|▍         | 1197/28080 [2:21:44<53:13:26,  7.13s/it]
  4%|▍         | 1198/28080 [2:21:51<53:17:34,  7.14s/it]
                                                         
{'loss': 0.7371, 'learning_rate': 0.0004997904502038613, 'epoch': 0.51}

  4%|▍         | 1198/28080 [2:21:51<53:17:34,  7.14s/it]
  4%|▍         | 1199/28080 [2:21:58<53:08:42,  7.12s/it]
                                                         
{'loss': 0.7276, 'learning_rate': 0.0004997892681449822, 'epoch': 0.51}

  4%|▍         | 1199/28080 [2:21:58<53:08:42,  7.12s/it]
  4%|▍         | 1200/28080 [2:22:05<53:06:47,  7.11s/it]
                                                         
{'loss': 0.7076, 'learning_rate': 0.0004997880827629144, 'epoch': 0.51}

  4%|▍         | 1200/28080 [2:22:05<53:06:47,  7.11s/it]
  4%|▍         | 1201/28080 [2:22:12<53:00:36,  7.10s/it]
                                                         
{'loss': 0.725, 'learning_rate': 0.0004997868940576738, 'epoch': 0.51}

  4%|▍         | 1201/28080 [2:22:12<53:00:36,  7.10s/it]
  4%|▍         | 1202/28080 [2:22:19<52:47:28,  7.07s/it]
                                                         
{'loss': 0.7178, 'learning_rate': 0.0004997857020292764, 'epoch': 0.51}

  4%|▍         | 1202/28080 [2:22:19<52:47:28,  7.07s/it]
  4%|▍         | 1203/28080 [2:22:26<52:41:41,  7.06s/it]
                                                         
{'loss': 0.7158, 'learning_rate': 0.0004997845066777379, 'epoch': 0.51}

  4%|▍         | 1203/28080 [2:22:26<52:41:41,  7.06s/it]
  4%|▍         | 1204/28080 [2:22:33<52:53:52,  7.09s/it]
                                                         
{'loss': 0.7264, 'learning_rate': 0.0004997833080030743, 'epoch': 0.51}

  4%|▍         | 1204/28080 [2:22:33<52:53:52,  7.09s/it]
  4%|▍         | 1205/28080 [2:22:40<52:51:00,  7.08s/it]
                                                         
{'loss': 0.7227, 'learning_rate': 0.0004997821060053013, 'epoch': 0.51}

  4%|▍         | 1205/28080 [2:22:40<52:51:00,  7.08s/it]
  4%|▍         | 1206/28080 [2:22:48<52:55:53,  7.09s/it]
                                                         
{'loss': 0.7338, 'learning_rate': 0.0004997809006844351, 'epoch': 0.52}

  4%|▍         | 1206/28080 [2:22:48<52:55:53,  7.09s/it]
  4%|▍         | 1207/28080 [2:22:55<52:58:40,  7.10s/it]
                                                         
{'loss': 0.7527, 'learning_rate': 0.0004997796920404918, 'epoch': 0.52}

  4%|▍         | 1207/28080 [2:22:55<52:58:40,  7.10s/it]
  4%|▍         | 1208/28080 [2:23:02<52:58:16,  7.10s/it]
                                                         
{'loss': 0.7158, 'learning_rate': 0.0004997784800734873, 'epoch': 0.52}

  4%|▍         | 1208/28080 [2:23:02<52:58:16,  7.10s/it]
  4%|▍         | 1209/28080 [2:23:09<53:00:26,  7.10s/it]
                                                         
{'loss': 0.7443, 'learning_rate': 0.0004997772647834379, 'epoch': 0.52}

  4%|▍         | 1209/28080 [2:23:09<53:00:26,  7.10s/it]
  4%|▍         | 1210/28080 [2:23:16<52:57:49,  7.10s/it]
                                                         
{'loss': 0.7504, 'learning_rate': 0.0004997760461703596, 'epoch': 0.52}

  4%|▍         | 1210/28080 [2:23:16<52:57:49,  7.10s/it]
  4%|▍         | 1211/28080 [2:23:23<53:02:11,  7.11s/it]
                                                         
{'loss': 0.748, 'learning_rate': 0.0004997748242342686, 'epoch': 0.52}

  4%|▍         | 1211/28080 [2:23:23<53:02:11,  7.11s/it]
  4%|▍         | 1212/28080 [2:23:30<53:01:04,  7.10s/it]
                                                         
{'loss': 0.7135, 'learning_rate': 0.0004997735989751814, 'epoch': 0.52}

  4%|▍         | 1212/28080 [2:23:30<53:01:04,  7.10s/it]
  4%|▍         | 1213/28080 [2:23:37<52:59:55,  7.10s/it]
                                                         
{'loss': 0.7511, 'learning_rate': 0.0004997723703931142, 'epoch': 0.52}

  4%|▍         | 1213/28080 [2:23:37<52:59:55,  7.10s/it]
  4%|▍         | 1214/28080 [2:23:44<52:37:13,  7.05s/it]
                                                         
{'loss': 0.7266, 'learning_rate': 0.0004997711384880831, 'epoch': 0.52}

  4%|▍         | 1214/28080 [2:23:44<52:37:13,  7.05s/it]
  4%|▍         | 1215/28080 [2:23:51<52:56:08,  7.09s/it]
                                                         
{'loss': 0.7122, 'learning_rate': 0.0004997699032601048, 'epoch': 0.52}

  4%|▍         | 1215/28080 [2:23:51<52:56:08,  7.09s/it]
  4%|▍         | 1216/28080 [2:23:58<52:58:14,  7.10s/it]
                                                         
{'loss': 0.7302, 'learning_rate': 0.0004997686647091955, 'epoch': 0.52}

  4%|▍         | 1216/28080 [2:23:58<52:58:14,  7.10s/it]
  4%|▍         | 1217/28080 [2:24:06<53:05:44,  7.12s/it]
                                                         
{'loss': 0.7311, 'learning_rate': 0.0004997674228353719, 'epoch': 0.52}

  4%|▍         | 1217/28080 [2:24:06<53:05:44,  7.12s/it]
  4%|▍         | 1218/28080 [2:24:13<52:57:02,  7.10s/it]
                                                         
{'loss': 0.7316, 'learning_rate': 0.0004997661776386503, 'epoch': 0.52}

  4%|▍         | 1218/28080 [2:24:13<52:57:02,  7.10s/it]
  4%|▍         | 1219/28080 [2:24:20<53:06:25,  7.12s/it]
                                                         
{'loss': 0.7253, 'learning_rate': 0.0004997649291190474, 'epoch': 0.52}

  4%|▍         | 1219/28080 [2:24:20<53:06:25,  7.12s/it]
  4%|▍         | 1220/28080 [2:24:27<52:59:36,  7.10s/it]
                                                         
{'loss': 0.7371, 'learning_rate': 0.0004997636772765798, 'epoch': 0.52}

  4%|▍         | 1220/28080 [2:24:27<52:59:36,  7.10s/it]
  4%|▍         | 1221/28080 [2:24:34<52:57:44,  7.10s/it]
                                                         
{'loss': 0.7215, 'learning_rate': 0.0004997624221112642, 'epoch': 0.52}

  4%|▍         | 1221/28080 [2:24:34<52:57:44,  7.10s/it]
  4%|▍         | 1222/28080 [2:24:41<52:51:18,  7.08s/it]
                                                         
{'loss': 0.7225, 'learning_rate': 0.0004997611636231172, 'epoch': 0.52}

  4%|▍         | 1222/28080 [2:24:41<52:51:18,  7.08s/it]
  4%|▍         | 1223/28080 [2:24:48<52:59:23,  7.10s/it]
                                                         
{'loss': 0.7283, 'learning_rate': 0.0004997599018121556, 'epoch': 0.52}

  4%|▍         | 1223/28080 [2:24:48<52:59:23,  7.10s/it]
  4%|▍         | 1224/28080 [2:24:55<52:58:13,  7.10s/it]
                                                         
{'loss': 0.7243, 'learning_rate': 0.0004997586366783962, 'epoch': 0.52}

  4%|▍         | 1224/28080 [2:24:55<52:58:13,  7.10s/it]
  4%|▍         | 1225/28080 [2:25:02<52:53:15,  7.09s/it]
                                                         
{'loss': 0.7173, 'learning_rate': 0.0004997573682218557, 'epoch': 0.52}

  4%|▍         | 1225/28080 [2:25:02<52:53:15,  7.09s/it]
  4%|▍         | 1226/28080 [2:25:10<52:58:25,  7.10s/it]
                                                         
{'loss': 0.7358, 'learning_rate': 0.0004997560964425511, 'epoch': 0.52}

  4%|▍         | 1226/28080 [2:25:10<52:58:25,  7.10s/it]
  4%|▍         | 1227/28080 [2:25:17<53:11:11,  7.13s/it]
                                                         
{'loss': 0.7184, 'learning_rate': 0.0004997548213404993, 'epoch': 0.52}

  4%|▍         | 1227/28080 [2:25:17<53:11:11,  7.13s/it]
  4%|▍         | 1228/28080 [2:25:24<53:18:25,  7.15s/it]
                                                         
{'loss': 0.7221, 'learning_rate': 0.0004997535429157173, 'epoch': 0.52}

  4%|▍         | 1228/28080 [2:25:24<53:18:25,  7.15s/it]
  4%|▍         | 1229/28080 [2:25:31<53:19:29,  7.15s/it]
                                                         
{'loss': 0.7294, 'learning_rate': 0.000499752261168222, 'epoch': 0.53}

  4%|▍         | 1229/28080 [2:25:31<53:19:29,  7.15s/it]
  4%|▍         | 1230/28080 [2:25:38<53:10:37,  7.13s/it]
                                                         
{'loss': 0.7446, 'learning_rate': 0.0004997509760980306, 'epoch': 0.53}

  4%|▍         | 1230/28080 [2:25:38<53:10:37,  7.13s/it]
  4%|▍         | 1231/28080 [2:25:45<52:58:01,  7.10s/it]
                                                         
{'loss': 0.7422, 'learning_rate': 0.0004997496877051601, 'epoch': 0.53}

  4%|▍         | 1231/28080 [2:25:45<52:58:01,  7.10s/it]
  4%|▍         | 1232/28080 [2:25:52<52:47:32,  7.08s/it]
                                                         
{'loss': 0.7473, 'learning_rate': 0.0004997483959896276, 'epoch': 0.53}

  4%|▍         | 1232/28080 [2:25:52<52:47:32,  7.08s/it]
  4%|▍         | 1233/28080 [2:25:59<52:47:49,  7.08s/it]
                                                         
{'loss': 0.733, 'learning_rate': 0.0004997471009514505, 'epoch': 0.53}

  4%|▍         | 1233/28080 [2:25:59<52:47:49,  7.08s/it]
  4%|▍         | 1234/28080 [2:26:06<53:02:36,  7.11s/it]
                                                         
{'loss': 0.733, 'learning_rate': 0.0004997458025906458, 'epoch': 0.53}

  4%|▍         | 1234/28080 [2:26:06<53:02:36,  7.11s/it]
  4%|▍         | 1235/28080 [2:26:14<53:15:47,  7.14s/it]
                                                         
{'loss': 0.7153, 'learning_rate': 0.0004997445009072307, 'epoch': 0.53}

  4%|▍         | 1235/28080 [2:26:14<53:15:47,  7.14s/it]
  4%|▍         | 1236/28080 [2:26:21<53:15:04,  7.14s/it]
                                                         
{'loss': 0.7033, 'learning_rate': 0.0004997431959012227, 'epoch': 0.53}

  4%|▍         | 1236/28080 [2:26:21<53:15:04,  7.14s/it]
  4%|▍         | 1237/28080 [2:26:28<53:14:39,  7.14s/it]
                                                         
{'loss': 0.72, 'learning_rate': 0.0004997418875726392, 'epoch': 0.53}

  4%|▍         | 1237/28080 [2:26:28<53:14:39,  7.14s/it]
  4%|▍         | 1238/28080 [2:26:35<53:10:42,  7.13s/it]
                                                         
{'loss': 0.7523, 'learning_rate': 0.0004997405759214976, 'epoch': 0.53}

  4%|▍         | 1238/28080 [2:26:35<53:10:42,  7.13s/it]
  4%|▍         | 1239/28080 [2:26:42<53:14:27,  7.14s/it]
                                                         
{'loss': 0.7253, 'learning_rate': 0.0004997392609478151, 'epoch': 0.53}

  4%|▍         | 1239/28080 [2:26:42<53:14:27,  7.14s/it]
  4%|▍         | 1240/28080 [2:26:49<53:08:27,  7.13s/it]
                                                         
{'loss': 0.7551, 'learning_rate': 0.0004997379426516095, 'epoch': 0.53}

  4%|▍         | 1240/28080 [2:26:49<53:08:27,  7.13s/it]
  4%|▍         | 1241/28080 [2:26:56<52:56:59,  7.10s/it]
                                                         
{'loss': 0.7076, 'learning_rate': 0.0004997366210328983, 'epoch': 0.53}

  4%|▍         | 1241/28080 [2:26:56<52:56:59,  7.10s/it]
  4%|▍         | 1242/28080 [2:27:03<52:59:00,  7.11s/it]
                                                         
{'loss': 0.7137, 'learning_rate': 0.0004997352960916989, 'epoch': 0.53}

  4%|▍         | 1242/28080 [2:27:03<52:59:00,  7.11s/it]
  4%|▍         | 1243/28080 [2:27:11<53:04:48,  7.12s/it]
                                                         
{'loss': 0.7473, 'learning_rate': 0.0004997339678280289, 'epoch': 0.53}

  4%|▍         | 1243/28080 [2:27:11<53:04:48,  7.12s/it]
  4%|▍         | 1244/28080 [2:27:18<52:52:02,  7.09s/it]
                                                         
{'loss': 0.7343, 'learning_rate': 0.0004997326362419062, 'epoch': 0.53}

  4%|▍         | 1244/28080 [2:27:18<52:52:02,  7.09s/it]
  4%|▍         | 1245/28080 [2:27:25<52:54:35,  7.10s/it]
                                                         
{'loss': 0.7155, 'learning_rate': 0.0004997313013333485, 'epoch': 0.53}

  4%|▍         | 1245/28080 [2:27:25<52:54:35,  7.10s/it]
  4%|▍         | 1246/28080 [2:27:32<53:01:30,  7.11s/it]
                                                         
{'loss': 0.7225, 'learning_rate': 0.0004997299631023733, 'epoch': 0.53}

  4%|▍         | 1246/28080 [2:27:32<53:01:30,  7.11s/it]
  4%|▍         | 1247/28080 [2:27:39<52:56:24,  7.10s/it]
                                                         
{'loss': 0.7304, 'learning_rate': 0.0004997286215489986, 'epoch': 0.53}

  4%|▍         | 1247/28080 [2:27:39<52:56:24,  7.10s/it]
  4%|▍         | 1248/28080 [2:27:46<53:10:56,  7.14s/it]
                                                         
{'loss': 0.7151, 'learning_rate': 0.0004997272766732423, 'epoch': 0.53}

  4%|▍         | 1248/28080 [2:27:46<53:10:56,  7.14s/it]
  4%|▍         | 1249/28080 [2:27:53<53:02:58,  7.12s/it]
                                                         
{'loss': 0.7131, 'learning_rate': 0.0004997259284751222, 'epoch': 0.53}

  4%|▍         | 1249/28080 [2:27:53<53:02:58,  7.12s/it]
  4%|▍         | 1250/28080 [2:28:00<53:05:57,  7.12s/it]
                                                         
{'loss': 0.7236, 'learning_rate': 0.0004997245769546563, 'epoch': 0.53}

  4%|▍         | 1250/28080 [2:28:00<53:05:57,  7.12s/it]
  4%|▍         | 1251/28080 [2:28:08<53:03:35,  7.12s/it]
                                                         
{'loss': 0.7205, 'learning_rate': 0.0004997232221118625, 'epoch': 0.53}

  4%|▍         | 1251/28080 [2:28:08<53:03:35,  7.12s/it]
  4%|▍         | 1252/28080 [2:28:15<53:03:35,  7.12s/it]
                                                         
{'loss': 0.7189, 'learning_rate': 0.0004997218639467588, 'epoch': 0.53}

  4%|▍         | 1252/28080 [2:28:15<53:03:35,  7.12s/it]
  4%|▍         | 1253/28080 [2:28:22<53:01:26,  7.12s/it]
                                                         
{'loss': 0.7106, 'learning_rate': 0.0004997205024593633, 'epoch': 0.54}

  4%|▍         | 1253/28080 [2:28:22<53:01:26,  7.12s/it]
  4%|▍         | 1254/28080 [2:28:29<52:45:41,  7.08s/it]
                                                         
{'loss': 0.7275, 'learning_rate': 0.0004997191376496942, 'epoch': 0.54}

  4%|▍         | 1254/28080 [2:28:29<52:45:41,  7.08s/it]
  4%|▍         | 1255/28080 [2:28:36<53:01:37,  7.12s/it]
                                                         
{'loss': 0.7395, 'learning_rate': 0.0004997177695177696, 'epoch': 0.54}

  4%|▍         | 1255/28080 [2:28:36<53:01:37,  7.12s/it]
  4%|▍         | 1256/28080 [2:28:43<52:54:24,  7.10s/it]
                                                         
{'loss': 0.7574, 'learning_rate': 0.0004997163980636077, 'epoch': 0.54}

  4%|▍         | 1256/28080 [2:28:43<52:54:24,  7.10s/it]
  4%|▍         | 1257/28080 [2:28:50<52:51:01,  7.09s/it]
                                                         
{'loss': 0.7255, 'learning_rate': 0.0004997150232872267, 'epoch': 0.54}

  4%|▍         | 1257/28080 [2:28:50<52:51:01,  7.09s/it]
  4%|▍         | 1258/28080 [2:28:57<53:14:35,  7.15s/it]
                                                         
{'loss': 0.7304, 'learning_rate': 0.000499713645188645, 'epoch': 0.54}

  4%|▍         | 1258/28080 [2:28:57<53:14:35,  7.15s/it]
  4%|▍         | 1259/28080 [2:29:04<52:56:31,  7.11s/it]
                                                         
{'loss': 0.7436, 'learning_rate': 0.0004997122637678807, 'epoch': 0.54}

  4%|▍         | 1259/28080 [2:29:04<52:56:31,  7.11s/it]
  4%|▍         | 1260/28080 [2:29:12<53:03:27,  7.12s/it]
                                                         
{'loss': 0.7275, 'learning_rate': 0.0004997108790249525, 'epoch': 0.54}

  4%|▍         | 1260/28080 [2:29:12<53:03:27,  7.12s/it]
  4%|▍         | 1261/28080 [2:29:19<52:53:43,  7.10s/it]
                                                         
{'loss': 0.7266, 'learning_rate': 0.0004997094909598786, 'epoch': 0.54}

  4%|▍         | 1261/28080 [2:29:19<52:53:43,  7.10s/it]
  4%|▍         | 1262/28080 [2:29:26<52:57:55,  7.11s/it]
                                                         
{'loss': 0.7272, 'learning_rate': 0.0004997080995726777, 'epoch': 0.54}

  4%|▍         | 1262/28080 [2:29:26<52:57:55,  7.11s/it]
  4%|▍         | 1263/28080 [2:29:33<52:54:58,  7.10s/it]
                                                         
{'loss': 0.7276, 'learning_rate': 0.0004997067048633679, 'epoch': 0.54}

  4%|▍         | 1263/28080 [2:29:33<52:54:58,  7.10s/it]
  5%|▍         | 1264/28080 [2:29:40<52:54:38,  7.10s/it]
                                                         
{'loss': 0.7214, 'learning_rate': 0.0004997053068319682, 'epoch': 0.54}

  5%|▍         | 1264/28080 [2:29:40<52:54:38,  7.10s/it]
  5%|▍         | 1265/28080 [2:29:47<53:05:57,  7.13s/it]
                                                         
{'loss': 0.7363, 'learning_rate': 0.0004997039054784969, 'epoch': 0.54}

  5%|▍         | 1265/28080 [2:29:47<53:05:57,  7.13s/it]
  5%|▍         | 1266/28080 [2:29:54<53:02:13,  7.12s/it]
                                                         
{'loss': 0.7224, 'learning_rate': 0.0004997025008029726, 'epoch': 0.54}

  5%|▍         | 1266/28080 [2:29:54<53:02:13,  7.12s/it]
  5%|▍         | 1267/28080 [2:30:01<53:10:42,  7.14s/it]
                                                         
{'loss': 0.732, 'learning_rate': 0.0004997010928054144, 'epoch': 0.54}

  5%|▍         | 1267/28080 [2:30:01<53:10:42,  7.14s/it]
  5%|▍         | 1268/28080 [2:30:09<53:18:22,  7.16s/it]
                                                         
{'loss': 0.7386, 'learning_rate': 0.0004996996814858406, 'epoch': 0.54}

  5%|▍         | 1268/28080 [2:30:09<53:18:22,  7.16s/it]
  5%|▍         | 1269/28080 [2:30:16<53:12:06,  7.14s/it]
                                                         
{'loss': 0.69, 'learning_rate': 0.0004996982668442701, 'epoch': 0.54}

  5%|▍         | 1269/28080 [2:30:16<53:12:06,  7.14s/it]
  5%|▍         | 1270/28080 [2:30:23<53:00:05,  7.12s/it]
                                                         
{'loss': 0.7107, 'learning_rate': 0.0004996968488807219, 'epoch': 0.54}

  5%|▍         | 1270/28080 [2:30:23<53:00:05,  7.12s/it]
  5%|▍         | 1271/28080 [2:30:30<52:58:14,  7.11s/it]
                                                         
{'loss': 0.7409, 'learning_rate': 0.0004996954275952146, 'epoch': 0.54}

  5%|▍         | 1271/28080 [2:30:30<52:58:14,  7.11s/it]
  5%|▍         | 1272/28080 [2:30:37<53:00:11,  7.12s/it]
                                                         
{'loss': 0.7146, 'learning_rate': 0.0004996940029877673, 'epoch': 0.54}

  5%|▍         | 1272/28080 [2:30:37<53:00:11,  7.12s/it]
  5%|▍         | 1273/28080 [2:30:44<53:01:40,  7.12s/it]
                                                         
{'loss': 0.7112, 'learning_rate': 0.0004996925750583989, 'epoch': 0.54}

  5%|▍         | 1273/28080 [2:30:44<53:01:40,  7.12s/it]
  5%|▍         | 1274/28080 [2:30:51<52:59:51,  7.12s/it]
                                                         
{'loss': 0.7284, 'learning_rate': 0.0004996911438071283, 'epoch': 0.54}

  5%|▍         | 1274/28080 [2:30:51<52:59:51,  7.12s/it]
  5%|▍         | 1275/28080 [2:30:58<52:47:27,  7.09s/it]
                                                         
{'loss': 0.7484, 'learning_rate': 0.0004996897092339747, 'epoch': 0.54}

  5%|▍         | 1275/28080 [2:30:58<52:47:27,  7.09s/it]
  5%|▍         | 1276/28080 [2:31:05<52:55:58,  7.11s/it]
                                                         
{'loss': 0.7251, 'learning_rate': 0.0004996882713389571, 'epoch': 0.55}

  5%|▍         | 1276/28080 [2:31:05<52:55:58,  7.11s/it]
  5%|▍         | 1277/28080 [2:31:12<52:53:05,  7.10s/it]
                                                         
{'loss': 0.7047, 'learning_rate': 0.0004996868301220947, 'epoch': 0.55}

  5%|▍         | 1277/28080 [2:31:12<52:53:05,  7.10s/it]
  5%|▍         | 1278/28080 [2:31:20<52:52:11,  7.10s/it]
                                                         
{'loss': 0.7387, 'learning_rate': 0.0004996853855834065, 'epoch': 0.55}

  5%|▍         | 1278/28080 [2:31:20<52:52:11,  7.10s/it]
  5%|▍         | 1279/28080 [2:31:27<52:43:06,  7.08s/it]
                                                         
{'loss': 0.7379, 'learning_rate': 0.0004996839377229119, 'epoch': 0.55}

  5%|▍         | 1279/28080 [2:31:27<52:43:06,  7.08s/it]
  5%|▍         | 1280/28080 [2:31:34<52:38:48,  7.07s/it]
                                                         
{'loss': 0.7113, 'learning_rate': 0.00049968248654063, 'epoch': 0.55}

  5%|▍         | 1280/28080 [2:31:34<52:38:48,  7.07s/it]
  5%|▍         | 1281/28080 [2:31:41<52:44:14,  7.08s/it]
                                                         
{'loss': 0.7283, 'learning_rate': 0.0004996810320365803, 'epoch': 0.55}

  5%|▍         | 1281/28080 [2:31:41<52:44:14,  7.08s/it]
  5%|▍         | 1282/28080 [2:31:48<52:25:28,  7.04s/it]
                                                         
{'loss': 0.7481, 'learning_rate': 0.0004996795742107821, 'epoch': 0.55}

  5%|▍         | 1282/28080 [2:31:48<52:25:28,  7.04s/it]
  5%|▍         | 1283/28080 [2:31:55<52:23:36,  7.04s/it]
                                                         
{'loss': 0.7555, 'learning_rate': 0.0004996781130632546, 'epoch': 0.55}

  5%|▍         | 1283/28080 [2:31:55<52:23:36,  7.04s/it]
  5%|▍         | 1284/28080 [2:32:02<52:42:28,  7.08s/it]
                                                         
{'loss': 0.72, 'learning_rate': 0.0004996766485940175, 'epoch': 0.55}

  5%|▍         | 1284/28080 [2:32:02<52:42:28,  7.08s/it]
  5%|▍         | 1285/28080 [2:32:09<52:52:41,  7.10s/it]
                                                         
{'loss': 0.7195, 'learning_rate': 0.00049967518080309, 'epoch': 0.55}

  5%|▍         | 1285/28080 [2:32:09<52:52:41,  7.10s/it]
  5%|▍         | 1286/28080 [2:32:16<52:53:58,  7.11s/it]
                                                         
{'loss': 0.7139, 'learning_rate': 0.000499673709690492, 'epoch': 0.55}

  5%|▍         | 1286/28080 [2:32:16<52:53:58,  7.11s/it]
  5%|▍         | 1287/28080 [2:32:23<53:01:13,  7.12s/it]
                                                         
{'loss': 0.7108, 'learning_rate': 0.0004996722352562428, 'epoch': 0.55}

  5%|▍         | 1287/28080 [2:32:23<53:01:13,  7.12s/it]
  5%|▍         | 1288/28080 [2:32:30<53:00:16,  7.12s/it]
                                                         
{'loss': 0.7471, 'learning_rate': 0.000499670757500362, 'epoch': 0.55}

  5%|▍         | 1288/28080 [2:32:31<53:00:16,  7.12s/it]
  5%|▍         | 1289/28080 [2:32:38<52:58:18,  7.12s/it]
                                                         
{'loss': 0.7251, 'learning_rate': 0.0004996692764228694, 'epoch': 0.55}

  5%|▍         | 1289/28080 [2:32:38<52:58:18,  7.12s/it]
  5%|▍         | 1290/28080 [2:32:45<53:00:48,  7.12s/it]
                                                         
{'loss': 0.7237, 'learning_rate': 0.0004996677920237846, 'epoch': 0.55}

  5%|▍         | 1290/28080 [2:32:45<53:00:48,  7.12s/it]
  5%|▍         | 1291/28080 [2:32:52<53:04:04,  7.13s/it]
                                                         
{'loss': 0.7307, 'learning_rate': 0.0004996663043031276, 'epoch': 0.55}

  5%|▍         | 1291/28080 [2:32:52<53:04:04,  7.13s/it]
  5%|▍         | 1292/28080 [2:32:59<52:59:58,  7.12s/it]
                                                         
{'loss': 0.7263, 'learning_rate': 0.0004996648132609177, 'epoch': 0.55}

  5%|▍         | 1292/28080 [2:32:59<52:59:58,  7.12s/it]
  5%|▍         | 1293/28080 [2:33:06<53:00:57,  7.13s/it]
                                                         
{'loss': 0.7407, 'learning_rate': 0.0004996633188971752, 'epoch': 0.55}

  5%|▍         | 1293/28080 [2:33:06<53:00:57,  7.13s/it]
  5%|▍         | 1294/28080 [2:33:13<53:05:55,  7.14s/it]
                                                         
{'loss': 0.6941, 'learning_rate': 0.0004996618212119197, 'epoch': 0.55}

  5%|▍         | 1294/28080 [2:33:13<53:05:55,  7.14s/it]
  5%|▍         | 1295/28080 [2:33:20<53:02:12,  7.13s/it]
                                                         
{'loss': 0.7415, 'learning_rate': 0.0004996603202051714, 'epoch': 0.55}

  5%|▍         | 1295/28080 [2:33:20<53:02:12,  7.13s/it]
  5%|▍         | 1296/28080 [2:33:28<53:03:50,  7.13s/it]
                                                         
{'loss': 0.7368, 'learning_rate': 0.0004996588158769499, 'epoch': 0.55}

  5%|▍         | 1296/28080 [2:33:28<53:03:50,  7.13s/it]
  5%|▍         | 1297/28080 [2:33:35<52:58:25,  7.12s/it]
                                                         
{'loss': 0.7253, 'learning_rate': 0.0004996573082272755, 'epoch': 0.55}

  5%|▍         | 1297/28080 [2:33:35<52:58:25,  7.12s/it]
  5%|▍         | 1298/28080 [2:33:42<52:46:59,  7.10s/it]
                                                         
{'loss': 0.7182, 'learning_rate': 0.0004996557972561683, 'epoch': 0.55}

  5%|▍         | 1298/28080 [2:33:42<52:46:59,  7.10s/it]
  5%|▍         | 1299/28080 [2:33:49<52:45:28,  7.09s/it]
                                                         
{'loss': 0.7336, 'learning_rate': 0.0004996542829636482, 'epoch': 0.55}

  5%|▍         | 1299/28080 [2:33:49<52:45:28,  7.09s/it]
  5%|▍         | 1300/28080 [2:33:56<52:48:24,  7.10s/it]
                                                         
{'loss': 0.7136, 'learning_rate': 0.0004996527653497353, 'epoch': 0.56}

  5%|▍         | 1300/28080 [2:33:56<52:48:24,  7.10s/it]
  5%|▍         | 1301/28080 [2:34:03<52:51:55,  7.11s/it]
                                                         
{'loss': 0.7229, 'learning_rate': 0.0004996512444144499, 'epoch': 0.56}

  5%|▍         | 1301/28080 [2:34:03<52:51:55,  7.11s/it]
  5%|▍         | 1302/28080 [2:34:10<52:43:32,  7.09s/it]
                                                         
{'loss': 0.7492, 'learning_rate': 0.0004996497201578123, 'epoch': 0.56}

  5%|▍         | 1302/28080 [2:34:10<52:43:32,  7.09s/it]
  5%|▍         | 1303/28080 [2:34:17<52:40:16,  7.08s/it]
                                                         
{'loss': 0.7455, 'learning_rate': 0.0004996481925798428, 'epoch': 0.56}

  5%|▍         | 1303/28080 [2:34:17<52:40:16,  7.08s/it]
  5%|▍         | 1304/28080 [2:34:24<52:48:19,  7.10s/it]
                                                         
{'loss': 0.7259, 'learning_rate': 0.0004996466616805617, 'epoch': 0.56}

  5%|▍         | 1304/28080 [2:34:24<52:48:19,  7.10s/it]
  5%|▍         | 1305/28080 [2:34:31<52:52:43,  7.11s/it]
                                                         
{'loss': 0.7509, 'learning_rate': 0.0004996451274599891, 'epoch': 0.56}

  5%|▍         | 1305/28080 [2:34:31<52:52:43,  7.11s/it]
  5%|▍         | 1306/28080 [2:34:38<52:45:05,  7.09s/it]
                                                         
{'loss': 0.7202, 'learning_rate': 0.0004996435899181457, 'epoch': 0.56}

  5%|▍         | 1306/28080 [2:34:38<52:45:05,  7.09s/it]
  5%|▍         | 1307/28080 [2:34:46<52:56:51,  7.12s/it]
                                                         
{'loss': 0.7174, 'learning_rate': 0.0004996420490550519, 'epoch': 0.56}

  5%|▍         | 1307/28080 [2:34:46<52:56:51,  7.12s/it]
  5%|▍         | 1308/28080 [2:34:53<53:00:11,  7.13s/it]
                                                         
{'loss': 0.7087, 'learning_rate': 0.0004996405048707282, 'epoch': 0.56}

  5%|▍         | 1308/28080 [2:34:53<53:00:11,  7.13s/it]
  5%|▍         | 1309/28080 [2:35:00<52:55:16,  7.12s/it]
                                                         
{'loss': 0.7347, 'learning_rate': 0.0004996389573651952, 'epoch': 0.56}

  5%|▍         | 1309/28080 [2:35:00<52:55:16,  7.12s/it]
  5%|▍         | 1310/28080 [2:35:07<52:46:54,  7.10s/it]
                                                         
{'loss': 0.738, 'learning_rate': 0.0004996374065384732, 'epoch': 0.56}

  5%|▍         | 1310/28080 [2:35:07<52:46:54,  7.10s/it]
  5%|▍         | 1311/28080 [2:35:14<52:49:58,  7.11s/it]
                                                         
{'loss': 0.7182, 'learning_rate': 0.0004996358523905831, 'epoch': 0.56}

  5%|▍         | 1311/28080 [2:35:14<52:49:58,  7.11s/it]
  5%|▍         | 1312/28080 [2:35:21<52:55:54,  7.12s/it]
                                                         
{'loss': 0.7242, 'learning_rate': 0.0004996342949215456, 'epoch': 0.56}

  5%|▍         | 1312/28080 [2:35:21<52:55:54,  7.12s/it]
  5%|▍         | 1313/28080 [2:35:28<52:52:22,  7.11s/it]
                                                         
{'loss': 0.7211, 'learning_rate': 0.0004996327341313814, 'epoch': 0.56}

  5%|▍         | 1313/28080 [2:35:28<52:52:22,  7.11s/it]
  5%|▍         | 1314/28080 [2:35:35<52:59:56,  7.13s/it]
                                                         
{'loss': 0.7401, 'learning_rate': 0.0004996311700201111, 'epoch': 0.56}

  5%|▍         | 1314/28080 [2:35:35<52:59:56,  7.13s/it]
  5%|▍         | 1315/28080 [2:35:42<52:46:54,  7.10s/it]
                                                         
{'loss': 0.7316, 'learning_rate': 0.0004996296025877557, 'epoch': 0.56}

  5%|▍         | 1315/28080 [2:35:42<52:46:54,  7.10s/it]
  5%|▍         | 1316/28080 [2:35:50<53:02:29,  7.13s/it]
                                                         
{'loss': 0.7318, 'learning_rate': 0.0004996280318343358, 'epoch': 0.56}

  5%|▍         | 1316/28080 [2:35:50<53:02:29,  7.13s/it]
  5%|▍         | 1317/28080 [2:35:57<53:07:31,  7.15s/it]
                                                         
{'loss': 0.7231, 'learning_rate': 0.0004996264577598726, 'epoch': 0.56}

  5%|▍         | 1317/28080 [2:35:57<53:07:31,  7.15s/it]
  5%|▍         | 1318/28080 [2:36:04<53:12:06,  7.16s/it]
                                                         
{'loss': 0.7051, 'learning_rate': 0.0004996248803643869, 'epoch': 0.56}

  5%|▍         | 1318/28080 [2:36:04<53:12:06,  7.16s/it]
  5%|▍         | 1319/28080 [2:36:11<53:07:43,  7.15s/it]
                                                         
{'loss': 0.7406, 'learning_rate': 0.0004996232996478996, 'epoch': 0.56}

  5%|▍         | 1319/28080 [2:36:11<53:07:43,  7.15s/it]
  5%|▍         | 1320/28080 [2:36:18<52:50:56,  7.11s/it]
                                                         
{'loss': 0.7272, 'learning_rate': 0.0004996217156104319, 'epoch': 0.56}

  5%|▍         | 1320/28080 [2:36:18<52:50:56,  7.11s/it]
  5%|▍         | 1321/28080 [2:36:25<52:57:28,  7.12s/it]
                                                         
{'loss': 0.7376, 'learning_rate': 0.0004996201282520047, 'epoch': 0.56}

  5%|▍         | 1321/28080 [2:36:25<52:57:28,  7.12s/it]
  5%|▍         | 1322/28080 [2:36:32<52:47:17,  7.10s/it]
                                                         
{'loss': 0.7191, 'learning_rate': 0.0004996185375726395, 'epoch': 0.56}

  5%|▍         | 1322/28080 [2:36:32<52:47:17,  7.10s/it]
  5%|▍         | 1323/28080 [2:36:40<52:54:47,  7.12s/it]
                                                         
{'loss': 0.7097, 'learning_rate': 0.0004996169435723569, 'epoch': 0.57}

  5%|▍         | 1323/28080 [2:36:40<52:54:47,  7.12s/it]
  5%|▍         | 1324/28080 [2:36:47<52:56:18,  7.12s/it]
                                                         
{'loss': 0.7207, 'learning_rate': 0.0004996153462511784, 'epoch': 0.57}

  5%|▍         | 1324/28080 [2:36:47<52:56:18,  7.12s/it]
  5%|▍         | 1325/28080 [2:36:54<52:44:00,  7.10s/it]
                                                         
{'loss': 0.7163, 'learning_rate': 0.0004996137456091252, 'epoch': 0.57}

  5%|▍         | 1325/28080 [2:36:54<52:44:00,  7.10s/it]
  5%|▍         | 1326/28080 [2:37:01<52:43:29,  7.09s/it]
                                                         
{'loss': 0.7242, 'learning_rate': 0.0004996121416462188, 'epoch': 0.57}

  5%|▍         | 1326/28080 [2:37:01<52:43:29,  7.09s/it]
  5%|▍         | 1327/28080 [2:37:08<52:51:21,  7.11s/it]
                                                         
{'loss': 0.734, 'learning_rate': 0.0004996105343624803, 'epoch': 0.57}

  5%|▍         | 1327/28080 [2:37:08<52:51:21,  7.11s/it]
  5%|▍         | 1328/28080 [2:37:15<52:58:31,  7.13s/it]
                                                         
{'loss': 0.7132, 'learning_rate': 0.0004996089237579311, 'epoch': 0.57}

  5%|▍         | 1328/28080 [2:37:15<52:58:31,  7.13s/it]
  5%|▍         | 1329/28080 [2:37:22<52:59:43,  7.13s/it]
                                                         
{'loss': 0.7346, 'learning_rate': 0.0004996073098325926, 'epoch': 0.57}

  5%|▍         | 1329/28080 [2:37:22<52:59:43,  7.13s/it]
  5%|▍         | 1330/28080 [2:37:29<52:52:09,  7.12s/it]
                                                         
{'loss': 0.7235, 'learning_rate': 0.0004996056925864865, 'epoch': 0.57}

  5%|▍         | 1330/28080 [2:37:29<52:52:09,  7.12s/it]
  5%|▍         | 1331/28080 [2:37:36<52:50:52,  7.11s/it]
                                                         
{'loss': 0.7234, 'learning_rate': 0.0004996040720196341, 'epoch': 0.57}

  5%|▍         | 1331/28080 [2:37:36<52:50:52,  7.11s/it]
  5%|▍         | 1332/28080 [2:37:44<52:58:08,  7.13s/it]
                                                         
{'loss': 0.7431, 'learning_rate': 0.000499602448132057, 'epoch': 0.57}

  5%|▍         | 1332/28080 [2:37:44<52:58:08,  7.13s/it]
  5%|▍         | 1333/28080 [2:37:51<53:08:43,  7.15s/it]
                                                         
{'loss': 0.731, 'learning_rate': 0.0004996008209237769, 'epoch': 0.57}

  5%|▍         | 1333/28080 [2:37:51<53:08:43,  7.15s/it]
  5%|▍         | 1334/28080 [2:37:58<53:00:45,  7.14s/it]
                                                         
{'loss': 0.7295, 'learning_rate': 0.0004995991903948152, 'epoch': 0.57}

  5%|▍         | 1334/28080 [2:37:58<53:00:45,  7.14s/it]
  5%|▍         | 1335/28080 [2:38:05<53:02:44,  7.14s/it]
                                                         
{'loss': 0.7468, 'learning_rate': 0.000499597556545194, 'epoch': 0.57}

  5%|▍         | 1335/28080 [2:38:05<53:02:44,  7.14s/it]
  5%|▍         | 1336/28080 [2:38:12<52:43:58,  7.10s/it]
                                                         
{'loss': 0.7246, 'learning_rate': 0.0004995959193749347, 'epoch': 0.57}

  5%|▍         | 1336/28080 [2:38:12<52:43:58,  7.10s/it]
  5%|▍         | 1337/28080 [2:38:19<52:40:56,  7.09s/it]
                                                         
{'loss': 0.7319, 'learning_rate': 0.0004995942788840592, 'epoch': 0.57}

  5%|▍         | 1337/28080 [2:38:19<52:40:56,  7.09s/it]
  5%|▍         | 1338/28080 [2:38:26<52:49:01,  7.11s/it]
                                                         
{'loss': 0.7278, 'learning_rate': 0.0004995926350725893, 'epoch': 0.57}

  5%|▍         | 1338/28080 [2:38:26<52:49:01,  7.11s/it]
  5%|▍         | 1339/28080 [2:38:33<52:51:48,  7.12s/it]
                                                         
{'loss': 0.6986, 'learning_rate': 0.0004995909879405469, 'epoch': 0.57}

  5%|▍         | 1339/28080 [2:38:33<52:51:48,  7.12s/it]
  5%|▍         | 1340/28080 [2:38:41<52:54:02,  7.12s/it]
                                                         
{'loss': 0.7249, 'learning_rate': 0.0004995893374879539, 'epoch': 0.57}

  5%|▍         | 1340/28080 [2:38:41<52:54:02,  7.12s/it]
  5%|▍         | 1341/28080 [2:38:48<52:52:19,  7.12s/it]
                                                         
{'loss': 0.7176, 'learning_rate': 0.0004995876837148322, 'epoch': 0.57}

  5%|▍         | 1341/28080 [2:38:48<52:52:19,  7.12s/it]
  5%|▍         | 1342/28080 [2:38:55<52:49:18,  7.11s/it]
                                                         
{'loss': 0.733, 'learning_rate': 0.0004995860266212039, 'epoch': 0.57}

  5%|▍         | 1342/28080 [2:38:55<52:49:18,  7.11s/it]
  5%|▍         | 1343/28080 [2:39:02<52:49:39,  7.11s/it]
                                                         
{'loss': 0.7038, 'learning_rate': 0.000499584366207091, 'epoch': 0.57}

  5%|▍         | 1343/28080 [2:39:02<52:49:39,  7.11s/it]
  5%|▍         | 1344/28080 [2:39:09<52:49:13,  7.11s/it]
                                                         
{'loss': 0.7151, 'learning_rate': 0.0004995827024725155, 'epoch': 0.57}

  5%|▍         | 1344/28080 [2:39:09<52:49:13,  7.11s/it]
  5%|▍         | 1345/28080 [2:39:16<53:00:18,  7.14s/it]
                                                         
{'loss': 0.7404, 'learning_rate': 0.0004995810354174998, 'epoch': 0.57}

  5%|▍         | 1345/28080 [2:39:16<53:00:18,  7.14s/it]
  5%|▍         | 1346/28080 [2:39:23<53:02:25,  7.14s/it]
                                                         
{'loss': 0.7242, 'learning_rate': 0.0004995793650420658, 'epoch': 0.57}

  5%|▍         | 1346/28080 [2:39:23<53:02:25,  7.14s/it]
  5%|▍         | 1347/28080 [2:39:30<52:55:06,  7.13s/it]
                                                         
{'loss': 0.7165, 'learning_rate': 0.0004995776913462359, 'epoch': 0.58}

  5%|▍         | 1347/28080 [2:39:30<52:55:06,  7.13s/it]
  5%|▍         | 1348/28080 [2:39:38<53:03:27,  7.15s/it]
                                                         
{'loss': 0.7199, 'learning_rate': 0.0004995760143300321, 'epoch': 0.58}

  5%|▍         | 1348/28080 [2:39:38<53:03:27,  7.15s/it]
  5%|▍         | 1349/28080 [2:39:45<53:24:12,  7.19s/it]
                                                         
{'loss': 0.7171, 'learning_rate': 0.0004995743339934771, 'epoch': 0.58}

  5%|▍         | 1349/28080 [2:39:45<53:24:12,  7.19s/it]
  5%|▍         | 1350/28080 [2:39:52<53:08:36,  7.16s/it]
                                                         
{'loss': 0.694, 'learning_rate': 0.000499572650336593, 'epoch': 0.58}

  5%|▍         | 1350/28080 [2:39:52<53:08:36,  7.16s/it]
  5%|▍         | 1351/28080 [2:39:59<52:57:54,  7.13s/it]
                                                         
{'loss': 0.7274, 'learning_rate': 0.0004995709633594022, 'epoch': 0.58}

  5%|▍         | 1351/28080 [2:39:59<52:57:54,  7.13s/it]
  5%|▍         | 1352/28080 [2:40:06<52:55:09,  7.13s/it]
                                                         
{'loss': 0.7207, 'learning_rate': 0.0004995692730619272, 'epoch': 0.58}

  5%|▍         | 1352/28080 [2:40:06<52:55:09,  7.13s/it]
  5%|▍         | 1353/28080 [2:40:13<52:58:48,  7.14s/it]
                                                         
{'loss': 0.7197, 'learning_rate': 0.0004995675794441905, 'epoch': 0.58}

  5%|▍         | 1353/28080 [2:40:13<52:58:48,  7.14s/it]
  5%|▍         | 1354/28080 [2:40:20<52:50:09,  7.12s/it]
                                                         
{'loss': 0.7281, 'learning_rate': 0.0004995658825062147, 'epoch': 0.58}

  5%|▍         | 1354/28080 [2:40:20<52:50:09,  7.12s/it]
  5%|▍         | 1355/28080 [2:40:28<52:44:18,  7.10s/it]
                                                         
{'loss': 0.728, 'learning_rate': 0.0004995641822480222, 'epoch': 0.58}

  5%|▍         | 1355/28080 [2:40:28<52:44:18,  7.10s/it]
  5%|▍         | 1356/28080 [2:40:34<52:28:45,  7.07s/it]
                                                         
{'loss': 0.7289, 'learning_rate': 0.0004995624786696358, 'epoch': 0.58}

  5%|▍         | 1356/28080 [2:40:35<52:28:45,  7.07s/it]
  5%|▍         | 1357/28080 [2:40:42<52:36:16,  7.09s/it]
                                                         
{'loss': 0.736, 'learning_rate': 0.0004995607717710781, 'epoch': 0.58}

  5%|▍         | 1357/28080 [2:40:42<52:36:16,  7.09s/it]
  5%|▍         | 1358/28080 [2:40:49<52:44:19,  7.10s/it]
                                                         
{'loss': 0.7289, 'learning_rate': 0.0004995590615523716, 'epoch': 0.58}

  5%|▍         | 1358/28080 [2:40:49<52:44:19,  7.10s/it]
  5%|▍         | 1359/28080 [2:40:56<52:39:01,  7.09s/it]
                                                         
{'loss': 0.7092, 'learning_rate': 0.0004995573480135394, 'epoch': 0.58}

  5%|▍         | 1359/28080 [2:40:56<52:39:01,  7.09s/it]
  5%|▍         | 1360/28080 [2:41:03<52:33:12,  7.08s/it]
                                                         
{'loss': 0.7155, 'learning_rate': 0.0004995556311546041, 'epoch': 0.58}

  5%|▍         | 1360/28080 [2:41:03<52:33:12,  7.08s/it]
  5%|▍         | 1361/28080 [2:41:10<52:40:12,  7.10s/it]
                                                         
{'loss': 0.7004, 'learning_rate': 0.0004995539109755886, 'epoch': 0.58}

  5%|▍         | 1361/28080 [2:41:10<52:40:12,  7.10s/it]
  5%|▍         | 1362/28080 [2:41:17<52:32:02,  7.08s/it]
                                                         
{'loss': 0.7097, 'learning_rate': 0.0004995521874765158, 'epoch': 0.58}

  5%|▍         | 1362/28080 [2:41:17<52:32:02,  7.08s/it]
  5%|▍         | 1363/28080 [2:41:24<52:37:42,  7.09s/it]
                                                         
{'loss': 0.713, 'learning_rate': 0.0004995504606574085, 'epoch': 0.58}

  5%|▍         | 1363/28080 [2:41:24<52:37:42,  7.09s/it]
  5%|▍         | 1364/28080 [2:41:31<52:37:39,  7.09s/it]
                                                         
{'loss': 0.7436, 'learning_rate': 0.0004995487305182898, 'epoch': 0.58}

  5%|▍         | 1364/28080 [2:41:31<52:37:39,  7.09s/it]
  5%|▍         | 1365/28080 [2:41:38<52:43:25,  7.10s/it]
                                                         
{'loss': 0.7254, 'learning_rate': 0.0004995469970591827, 'epoch': 0.58}

  5%|▍         | 1365/28080 [2:41:38<52:43:25,  7.10s/it]
  5%|▍         | 1366/28080 [2:41:45<52:38:46,  7.09s/it]
                                                         
{'loss': 0.7241, 'learning_rate': 0.0004995452602801103, 'epoch': 0.58}

  5%|▍         | 1366/28080 [2:41:45<52:38:46,  7.09s/it]
  5%|▍         | 1367/28080 [2:41:53<52:41:36,  7.10s/it]
                                                         
{'loss': 0.7137, 'learning_rate': 0.0004995435201810955, 'epoch': 0.58}

  5%|▍         | 1367/28080 [2:41:53<52:41:36,  7.10s/it]
  5%|▍         | 1368/28080 [2:42:00<52:35:30,  7.09s/it]
                                                         
{'loss': 0.7148, 'learning_rate': 0.0004995417767621617, 'epoch': 0.58}

  5%|▍         | 1368/28080 [2:42:00<52:35:30,  7.09s/it]
  5%|▍         | 1369/28080 [2:42:07<52:39:04,  7.10s/it]
                                                         
{'loss': 0.7106, 'learning_rate': 0.000499540030023332, 'epoch': 0.58}

  5%|▍         | 1369/28080 [2:42:07<52:39:04,  7.10s/it]
  5%|▍         | 1370/28080 [2:42:14<52:41:55,  7.10s/it]
                                                         
{'loss': 0.7331, 'learning_rate': 0.0004995382799646297, 'epoch': 0.59}

  5%|▍         | 1370/28080 [2:42:14<52:41:55,  7.10s/it]
  5%|▍         | 1371/28080 [2:42:21<52:33:38,  7.08s/it]
                                                         
{'loss': 0.7229, 'learning_rate': 0.000499536526586078, 'epoch': 0.59}

  5%|▍         | 1371/28080 [2:42:21<52:33:38,  7.08s/it]
  5%|▍         | 1372/28080 [2:42:28<52:27:21,  7.07s/it]
                                                         
{'loss': 0.7231, 'learning_rate': 0.0004995347698877002, 'epoch': 0.59}

  5%|▍         | 1372/28080 [2:42:28<52:27:21,  7.07s/it]
  5%|▍         | 1373/28080 [2:42:35<52:25:17,  7.07s/it]
                                                         
{'loss': 0.7128, 'learning_rate': 0.0004995330098695196, 'epoch': 0.59}

  5%|▍         | 1373/28080 [2:42:35<52:25:17,  7.07s/it]
  5%|▍         | 1374/28080 [2:42:42<52:29:57,  7.08s/it]
                                                         
{'loss': 0.733, 'learning_rate': 0.0004995312465315599, 'epoch': 0.59}

  5%|▍         | 1374/28080 [2:42:42<52:29:57,  7.08s/it]
  5%|▍         | 1375/28080 [2:42:49<52:45:50,  7.11s/it]
                                                         
{'loss': 0.7043, 'learning_rate': 0.0004995294798738443, 'epoch': 0.59}

  5%|▍         | 1375/28080 [2:42:49<52:45:50,  7.11s/it]
  5%|▍         | 1376/28080 [2:42:56<52:47:59,  7.12s/it]
                                                         
{'loss': 0.7152, 'learning_rate': 0.0004995277098963965, 'epoch': 0.59}

  5%|▍         | 1376/28080 [2:42:56<52:47:59,  7.12s/it]
  5%|▍         | 1377/28080 [2:43:03<52:38:12,  7.10s/it]
                                                         
{'loss': 0.7062, 'learning_rate': 0.0004995259365992399, 'epoch': 0.59}

  5%|▍         | 1377/28080 [2:43:04<52:38:12,  7.10s/it]
  5%|▍         | 1378/28080 [2:43:11<52:40:03,  7.10s/it]
                                                         
{'loss': 0.7149, 'learning_rate': 0.0004995241599823981, 'epoch': 0.59}

  5%|▍         | 1378/28080 [2:43:11<52:40:03,  7.10s/it]
  5%|▍         | 1379/28080 [2:43:18<52:42:51,  7.11s/it]
                                                         
{'loss': 0.7198, 'learning_rate': 0.0004995223800458948, 'epoch': 0.59}

  5%|▍         | 1379/28080 [2:43:18<52:42:51,  7.11s/it]
  5%|▍         | 1380/28080 [2:43:25<52:37:11,  7.09s/it]
                                                         
{'loss': 0.7344, 'learning_rate': 0.0004995205967897537, 'epoch': 0.59}

  5%|▍         | 1380/28080 [2:43:25<52:37:11,  7.09s/it]
  5%|▍         | 1381/28080 [2:43:32<52:40:04,  7.10s/it]
                                                         
{'loss': 0.7205, 'learning_rate': 0.0004995188102139983, 'epoch': 0.59}

  5%|▍         | 1381/28080 [2:43:32<52:40:04,  7.10s/it]
  5%|▍         | 1382/28080 [2:43:39<52:37:16,  7.10s/it]
                                                         
{'loss': 0.7143, 'learning_rate': 0.0004995170203186528, 'epoch': 0.59}

  5%|▍         | 1382/28080 [2:43:39<52:37:16,  7.10s/it]
  5%|▍         | 1383/28080 [2:43:46<52:37:36,  7.10s/it]
                                                         
{'loss': 0.724, 'learning_rate': 0.0004995152271037405, 'epoch': 0.59}

  5%|▍         | 1383/28080 [2:43:46<52:37:36,  7.10s/it]
  5%|▍         | 1384/28080 [2:43:53<52:39:20,  7.10s/it]
                                                         
{'loss': 0.7501, 'learning_rate': 0.0004995134305692857, 'epoch': 0.59}

  5%|▍         | 1384/28080 [2:43:53<52:39:20,  7.10s/it]
  5%|▍         | 1385/28080 [2:44:00<52:46:38,  7.12s/it]
                                                         
{'loss': 0.7159, 'learning_rate': 0.000499511630715312, 'epoch': 0.59}

  5%|▍         | 1385/28080 [2:44:00<52:46:38,  7.12s/it]
  5%|▍         | 1386/28080 [2:44:07<52:35:43,  7.09s/it]
                                                         
{'loss': 0.7369, 'learning_rate': 0.0004995098275418436, 'epoch': 0.59}

  5%|▍         | 1386/28080 [2:44:07<52:35:43,  7.09s/it]
  5%|▍         | 1387/28080 [2:44:15<52:38:14,  7.10s/it]
                                                         
{'loss': 0.7288, 'learning_rate': 0.0004995080210489042, 'epoch': 0.59}

  5%|▍         | 1387/28080 [2:44:15<52:38:14,  7.10s/it]
  5%|▍         | 1388/28080 [2:44:22<52:50:17,  7.13s/it]
                                                         
{'loss': 0.7256, 'learning_rate': 0.0004995062112365181, 'epoch': 0.59}

  5%|▍         | 1388/28080 [2:44:22<52:50:17,  7.13s/it]
  5%|▍         | 1389/28080 [2:44:29<52:50:58,  7.13s/it]
                                                         
{'loss': 0.7521, 'learning_rate': 0.0004995043981047091, 'epoch': 0.59}

  5%|▍         | 1389/28080 [2:44:29<52:50:58,  7.13s/it]
  5%|▍         | 1390/28080 [2:44:36<52:42:12,  7.11s/it]
                                                         
{'loss': 0.7238, 'learning_rate': 0.0004995025816535017, 'epoch': 0.59}

  5%|▍         | 1390/28080 [2:44:36<52:42:12,  7.11s/it]
  5%|▍         | 1391/28080 [2:44:43<52:35:56,  7.09s/it]
                                                         
{'loss': 0.7027, 'learning_rate': 0.0004995007618829198, 'epoch': 0.59}

  5%|▍         | 1391/28080 [2:44:43<52:35:56,  7.09s/it]
  5%|▍         | 1392/28080 [2:44:50<52:39:46,  7.10s/it]
                                                         
{'loss': 0.7052, 'learning_rate': 0.0004994989387929875, 'epoch': 0.59}

  5%|▍         | 1392/28080 [2:44:50<52:39:46,  7.10s/it]
  5%|▍         | 1393/28080 [2:44:57<52:42:39,  7.11s/it]
                                                         
{'loss': 0.7367, 'learning_rate': 0.0004994971123837293, 'epoch': 0.6}

  5%|▍         | 1393/28080 [2:44:57<52:42:39,  7.11s/it]
  5%|▍         | 1394/28080 [2:45:04<52:41:20,  7.11s/it]
                                                         
{'loss': 0.7129, 'learning_rate': 0.0004994952826551694, 'epoch': 0.6}

  5%|▍         | 1394/28080 [2:45:04<52:41:20,  7.11s/it]
  5%|▍         | 1395/28080 [2:45:11<52:49:58,  7.13s/it]
                                                         
{'loss': 0.703, 'learning_rate': 0.0004994934496073322, 'epoch': 0.6}

  5%|▍         | 1395/28080 [2:45:11<52:49:58,  7.13s/it]
  5%|▍         | 1396/28080 [2:45:19<52:52:13,  7.13s/it]
                                                         
{'loss': 0.7364, 'learning_rate': 0.0004994916132402419, 'epoch': 0.6}

  5%|▍         | 1396/28080 [2:45:19<52:52:13,  7.13s/it]
  5%|▍         | 1397/28080 [2:45:26<52:57:05,  7.14s/it]
                                                         
{'loss': 0.7081, 'learning_rate': 0.0004994897735539233, 'epoch': 0.6}

  5%|▍         | 1397/28080 [2:45:26<52:57:05,  7.14s/it]
  5%|▍         | 1398/28080 [2:45:33<52:45:24,  7.12s/it]
                                                         
{'loss': 0.7317, 'learning_rate': 0.0004994879305484004, 'epoch': 0.6}

  5%|▍         | 1398/28080 [2:45:33<52:45:24,  7.12s/it]
  5%|▍         | 1399/28080 [2:45:40<52:36:22,  7.10s/it]
                                                         
{'loss': 0.7026, 'learning_rate': 0.0004994860842236983, 'epoch': 0.6}

  5%|▍         | 1399/28080 [2:45:40<52:36:22,  7.10s/it]
  5%|▍         | 1400/28080 [2:45:47<52:41:07,  7.11s/it]
                                                         
{'loss': 0.7125, 'learning_rate': 0.0004994842345798409, 'epoch': 0.6}

  5%|▍         | 1400/28080 [2:45:47<52:41:07,  7.11s/it]
  5%|▍         | 1401/28080 [2:45:54<52:42:29,  7.11s/it]
                                                         
{'loss': 0.7122, 'learning_rate': 0.0004994823816168532, 'epoch': 0.6}

  5%|▍         | 1401/28080 [2:45:54<52:42:29,  7.11s/it]
  5%|▍         | 1402/28080 [2:46:01<52:46:46,  7.12s/it]
                                                         
{'loss': 0.7311, 'learning_rate': 0.0004994805253347599, 'epoch': 0.6}

  5%|▍         | 1402/28080 [2:46:01<52:46:46,  7.12s/it]
  5%|▍         | 1403/28080 [2:46:08<52:44:36,  7.12s/it]
                                                         
{'loss': 0.7117, 'learning_rate': 0.0004994786657335856, 'epoch': 0.6}

  5%|▍         | 1403/28080 [2:46:08<52:44:36,  7.12s/it]
  5%|▌         | 1404/28080 [2:46:16<52:50:50,  7.13s/it]
                                                         
{'loss': 0.7347, 'learning_rate': 0.000499476802813355, 'epoch': 0.6}

  5%|▌         | 1404/28080 [2:46:16<52:50:50,  7.13s/it]
  5%|▌         | 1405/28080 [2:46:23<52:56:20,  7.14s/it]
                                                         
{'loss': 0.7165, 'learning_rate': 0.0004994749365740928, 'epoch': 0.6}

  5%|▌         | 1405/28080 [2:46:23<52:56:20,  7.14s/it]
  5%|▌         | 1406/28080 [2:46:30<52:48:37,  7.13s/it]
                                                         
{'loss': 0.7146, 'learning_rate': 0.000499473067015824, 'epoch': 0.6}

  5%|▌         | 1406/28080 [2:46:30<52:48:37,  7.13s/it]
  5%|▌         | 1407/28080 [2:46:37<52:39:50,  7.11s/it]
                                                         
{'loss': 0.729, 'learning_rate': 0.0004994711941385734, 'epoch': 0.6}

  5%|▌         | 1407/28080 [2:46:37<52:39:50,  7.11s/it]
  5%|▌         | 1408/28080 [2:46:44<52:35:56,  7.10s/it]
                                                         
{'loss': 0.7351, 'learning_rate': 0.000499469317942366, 'epoch': 0.6}

  5%|▌         | 1408/28080 [2:46:44<52:35:56,  7.10s/it]
  5%|▌         | 1409/28080 [2:46:51<52:35:08,  7.10s/it]
                                                         
{'loss': 0.7281, 'learning_rate': 0.0004994674384272267, 'epoch': 0.6}

  5%|▌         | 1409/28080 [2:46:51<52:35:08,  7.10s/it]
  5%|▌         | 1410/28080 [2:46:58<52:38:22,  7.11s/it]
                                                         
{'loss': 0.7035, 'learning_rate': 0.0004994655555931804, 'epoch': 0.6}

  5%|▌         | 1410/28080 [2:46:58<52:38:22,  7.11s/it]
  5%|▌         | 1411/28080 [2:47:05<52:40:07,  7.11s/it]
                                                         
{'loss': 0.718, 'learning_rate': 0.0004994636694402523, 'epoch': 0.6}

  5%|▌         | 1411/28080 [2:47:05<52:40:07,  7.11s/it]
  5%|▌         | 1412/28080 [2:47:12<52:27:15,  7.08s/it]
                                                         
{'loss': 0.7316, 'learning_rate': 0.0004994617799684674, 'epoch': 0.6}

  5%|▌         | 1412/28080 [2:47:12<52:27:15,  7.08s/it]
  5%|▌         | 1413/28080 [2:47:19<52:14:39,  7.05s/it]
                                                         
{'loss': 0.7259, 'learning_rate': 0.0004994598871778509, 'epoch': 0.6}

  5%|▌         | 1413/28080 [2:47:19<52:14:39,  7.05s/it]
  5%|▌         | 1414/28080 [2:47:26<52:13:59,  7.05s/it]
                                                         
{'loss': 0.7057, 'learning_rate': 0.0004994579910684279, 'epoch': 0.6}

  5%|▌         | 1414/28080 [2:47:26<52:13:59,  7.05s/it]
  5%|▌         | 1415/28080 [2:47:33<52:21:21,  7.07s/it]
                                                         
{'loss': 0.7003, 'learning_rate': 0.0004994560916402237, 'epoch': 0.6}

  5%|▌         | 1415/28080 [2:47:33<52:21:21,  7.07s/it]
  5%|▌         | 1416/28080 [2:47:41<52:23:14,  7.07s/it]
                                                         
{'loss': 0.7285, 'learning_rate': 0.0004994541888932635, 'epoch': 0.6}

  5%|▌         | 1416/28080 [2:47:41<52:23:14,  7.07s/it]
  5%|▌         | 1417/28080 [2:47:48<52:32:57,  7.10s/it]
                                                         
{'loss': 0.7098, 'learning_rate': 0.0004994522828275728, 'epoch': 0.61}

  5%|▌         | 1417/28080 [2:47:48<52:32:57,  7.10s/it]
  5%|▌         | 1418/28080 [2:47:55<52:37:03,  7.10s/it]
                                                         
{'loss': 0.7196, 'learning_rate': 0.0004994503734431768, 'epoch': 0.61}

  5%|▌         | 1418/28080 [2:47:55<52:37:03,  7.10s/it]
  5%|▌         | 1419/28080 [2:48:02<52:40:34,  7.11s/it]
                                                         
{'loss': 0.7039, 'learning_rate': 0.0004994484607401009, 'epoch': 0.61}

  5%|▌         | 1419/28080 [2:48:02<52:40:34,  7.11s/it]
  5%|▌         | 1420/28080 [2:48:09<52:42:39,  7.12s/it]
                                                         
{'loss': 0.7092, 'learning_rate': 0.0004994465447183705, 'epoch': 0.61}

  5%|▌         | 1420/28080 [2:48:09<52:42:39,  7.12s/it]
  5%|▌         | 1421/28080 [2:48:16<52:41:16,  7.11s/it]
                                                         
{'loss': 0.7033, 'learning_rate': 0.0004994446253780111, 'epoch': 0.61}

  5%|▌         | 1421/28080 [2:48:16<52:41:16,  7.11s/it]
  5%|▌         | 1422/28080 [2:48:23<52:32:27,  7.10s/it]
                                                         
{'loss': 0.7224, 'learning_rate': 0.0004994427027190484, 'epoch': 0.61}

  5%|▌         | 1422/28080 [2:48:23<52:32:27,  7.10s/it]
  5%|▌         | 1423/28080 [2:48:30<52:39:43,  7.11s/it]
                                                         
{'loss': 0.7086, 'learning_rate': 0.000499440776741508, 'epoch': 0.61}

  5%|▌         | 1423/28080 [2:48:30<52:39:43,  7.11s/it]
  5%|▌         | 1424/28080 [2:48:37<52:28:27,  7.09s/it]
                                                         
{'loss': 0.7296, 'learning_rate': 0.0004994388474454152, 'epoch': 0.61}

  5%|▌         | 1424/28080 [2:48:37<52:28:27,  7.09s/it]
  5%|▌         | 1425/28080 [2:48:44<52:18:51,  7.07s/it]
                                                         
{'loss': 0.7374, 'learning_rate': 0.000499436914830796, 'epoch': 0.61}

  5%|▌         | 1425/28080 [2:48:44<52:18:51,  7.07s/it]
  5%|▌         | 1426/28080 [2:48:52<52:25:05,  7.08s/it]
                                                         
{'loss': 0.7344, 'learning_rate': 0.000499434978897676, 'epoch': 0.61}

  5%|▌         | 1426/28080 [2:48:52<52:25:05,  7.08s/it]
  5%|▌         | 1427/28080 [2:48:59<52:23:42,  7.08s/it]
                                                         
{'loss': 0.7308, 'learning_rate': 0.0004994330396460808, 'epoch': 0.61}

  5%|▌         | 1427/28080 [2:48:59<52:23:42,  7.08s/it]
  5%|▌         | 1428/28080 [2:49:06<52:14:08,  7.06s/it]
                                                         
{'loss': 0.7373, 'learning_rate': 0.0004994310970760364, 'epoch': 0.61}

  5%|▌         | 1428/28080 [2:49:06<52:14:08,  7.06s/it]
  5%|▌         | 1429/28080 [2:49:13<52:29:58,  7.09s/it]
                                                         
{'loss': 0.7247, 'learning_rate': 0.0004994291511875686, 'epoch': 0.61}

  5%|▌         | 1429/28080 [2:49:13<52:29:58,  7.09s/it]
  5%|▌         | 1430/28080 [2:49:20<52:40:56,  7.12s/it]
                                                         
{'loss': 0.704, 'learning_rate': 0.0004994272019807032, 'epoch': 0.61}

  5%|▌         | 1430/28080 [2:49:20<52:40:56,  7.12s/it]
  5%|▌         | 1431/28080 [2:49:27<52:32:46,  7.10s/it]
                                                         
{'loss': 0.7236, 'learning_rate': 0.0004994252494554662, 'epoch': 0.61}

  5%|▌         | 1431/28080 [2:49:27<52:32:46,  7.10s/it]
  5%|▌         | 1432/28080 [2:49:34<52:29:06,  7.09s/it]
                                                         
{'loss': 0.722, 'learning_rate': 0.0004994232936118836, 'epoch': 0.61}

  5%|▌         | 1432/28080 [2:49:34<52:29:06,  7.09s/it]
  5%|▌         | 1433/28080 [2:49:41<52:22:30,  7.08s/it]
                                                         
{'loss': 0.7166, 'learning_rate': 0.0004994213344499815, 'epoch': 0.61}

  5%|▌         | 1433/28080 [2:49:41<52:22:30,  7.08s/it]
  5%|▌         | 1434/28080 [2:49:48<52:24:53,  7.08s/it]
                                                         
{'loss': 0.7203, 'learning_rate': 0.0004994193719697857, 'epoch': 0.61}

  5%|▌         | 1434/28080 [2:49:48<52:24:53,  7.08s/it]
  5%|▌         | 1435/28080 [2:49:55<52:37:56,  7.11s/it]
                                                         
{'loss': 0.7107, 'learning_rate': 0.0004994174061713225, 'epoch': 0.61}

  5%|▌         | 1435/28080 [2:49:55<52:37:56,  7.11s/it]
  5%|▌         | 1436/28080 [2:50:03<52:42:08,  7.12s/it]
                                                         
{'loss': 0.7191, 'learning_rate': 0.0004994154370546181, 'epoch': 0.61}

  5%|▌         | 1436/28080 [2:50:03<52:42:08,  7.12s/it]
  5%|▌         | 1437/28080 [2:50:10<52:36:43,  7.11s/it]
                                                         
{'loss': 0.6948, 'learning_rate': 0.0004994134646196986, 'epoch': 0.61}

  5%|▌         | 1437/28080 [2:50:10<52:36:43,  7.11s/it]
  5%|▌         | 1438/28080 [2:50:17<52:36:14,  7.11s/it]
                                                         
{'loss': 0.7238, 'learning_rate': 0.0004994114888665902, 'epoch': 0.61}

  5%|▌         | 1438/28080 [2:50:17<52:36:14,  7.11s/it]
  5%|▌         | 1439/28080 [2:50:24<52:50:45,  7.14s/it]
                                                         
{'loss': 0.7249, 'learning_rate': 0.0004994095097953193, 'epoch': 0.61}

  5%|▌         | 1439/28080 [2:50:24<52:50:45,  7.14s/it]
  5%|▌         | 1440/28080 [2:50:31<52:44:24,  7.13s/it]
                                                         
{'loss': 0.724, 'learning_rate': 0.0004994075274059121, 'epoch': 0.62}

  5%|▌         | 1440/28080 [2:50:31<52:44:24,  7.13s/it]
  5%|▌         | 1441/28080 [2:50:38<52:35:55,  7.11s/it]
                                                         
{'loss': 0.7365, 'learning_rate': 0.0004994055416983951, 'epoch': 0.62}

  5%|▌         | 1441/28080 [2:50:38<52:35:55,  7.11s/it]
  5%|▌         | 1442/28080 [2:50:45<52:34:12,  7.10s/it]
                                                         
{'loss': 0.732, 'learning_rate': 0.0004994035526727947, 'epoch': 0.62}

  5%|▌         | 1442/28080 [2:50:45<52:34:12,  7.10s/it]
  5%|▌         | 1443/28080 [2:50:52<52:47:54,  7.14s/it]
                                                         
{'loss': 0.7132, 'learning_rate': 0.0004994015603291373, 'epoch': 0.62}

  5%|▌         | 1443/28080 [2:50:52<52:47:54,  7.14s/it]
  5%|▌         | 1444/28080 [2:51:00<52:38:11,  7.11s/it]
                                                         
{'loss': 0.738, 'learning_rate': 0.0004993995646674494, 'epoch': 0.62}

  5%|▌         | 1444/28080 [2:51:00<52:38:11,  7.11s/it]
  5%|▌         | 1445/28080 [2:51:07<52:39:43,  7.12s/it]
                                                         
{'loss': 0.7045, 'learning_rate': 0.0004993975656877575, 'epoch': 0.62}

  5%|▌         | 1445/28080 [2:51:07<52:39:43,  7.12s/it]
  5%|▌         | 1446/28080 [2:51:14<52:25:10,  7.09s/it]
                                                         
{'loss': 0.723, 'learning_rate': 0.0004993955633900884, 'epoch': 0.62}

  5%|▌         | 1446/28080 [2:51:14<52:25:10,  7.09s/it]
  5%|▌         | 1447/28080 [2:51:21<52:35:31,  7.11s/it]
                                                         
{'loss': 0.7084, 'learning_rate': 0.0004993935577744686, 'epoch': 0.62}

  5%|▌         | 1447/28080 [2:51:21<52:35:31,  7.11s/it]
  5%|▌         | 1448/28080 [2:51:28<52:41:24,  7.12s/it]
                                                         
{'loss': 0.7055, 'learning_rate': 0.0004993915488409248, 'epoch': 0.62}

  5%|▌         | 1448/28080 [2:51:28<52:41:24,  7.12s/it]
  5%|▌         | 1449/28080 [2:51:35<52:41:10,  7.12s/it]
                                                         
{'loss': 0.7078, 'learning_rate': 0.0004993895365894838, 'epoch': 0.62}

  5%|▌         | 1449/28080 [2:51:35<52:41:10,  7.12s/it]
  5%|▌         | 1450/28080 [2:51:42<52:37:21,  7.11s/it]
                                                         
{'loss': 0.7118, 'learning_rate': 0.0004993875210201721, 'epoch': 0.62}

  5%|▌         | 1450/28080 [2:51:42<52:37:21,  7.11s/it]
  5%|▌         | 1451/28080 [2:51:49<52:43:26,  7.13s/it]
                                                         
{'loss': 0.7209, 'learning_rate': 0.0004993855021330169, 'epoch': 0.62}

  5%|▌         | 1451/28080 [2:51:49<52:43:26,  7.13s/it]
  5%|▌         | 1452/28080 [2:51:56<52:41:02,  7.12s/it]
                                                         
{'loss': 0.7081, 'learning_rate': 0.0004993834799280447, 'epoch': 0.62}

  5%|▌         | 1452/28080 [2:51:56<52:41:02,  7.12s/it]
  5%|▌         | 1453/28080 [2:52:03<52:27:47,  7.09s/it]
                                                         
{'loss': 0.7167, 'learning_rate': 0.0004993814544052827, 'epoch': 0.62}

  5%|▌         | 1453/28080 [2:52:03<52:27:47,  7.09s/it]
  5%|▌         | 1454/28080 [2:52:11<52:23:09,  7.08s/it]
                                                         
{'loss': 0.7016, 'learning_rate': 0.0004993794255647578, 'epoch': 0.62}

  5%|▌         | 1454/28080 [2:52:11<52:23:09,  7.08s/it]
  5%|▌         | 1455/28080 [2:52:18<52:16:34,  7.07s/it]
                                                         
{'loss': 0.7297, 'learning_rate': 0.0004993773934064968, 'epoch': 0.62}

  5%|▌         | 1455/28080 [2:52:18<52:16:34,  7.07s/it]
  5%|▌         | 1456/28080 [2:52:25<52:11:14,  7.06s/it]
                                                         
{'loss': 0.711, 'learning_rate': 0.0004993753579305268, 'epoch': 0.62}

  5%|▌         | 1456/28080 [2:52:25<52:11:14,  7.06s/it]
  5%|▌         | 1457/28080 [2:52:32<52:08:42,  7.05s/it]
                                                         
{'loss': 0.721, 'learning_rate': 0.000499373319136875, 'epoch': 0.62}

  5%|▌         | 1457/28080 [2:52:32<52:08:42,  7.05s/it]
  5%|▌         | 1458/28080 [2:52:39<52:11:51,  7.06s/it]
                                                         
{'loss': 0.744, 'learning_rate': 0.0004993712770255685, 'epoch': 0.62}

  5%|▌         | 1458/28080 [2:52:39<52:11:51,  7.06s/it]
  5%|▌         | 1459/28080 [2:52:46<52:06:05,  7.05s/it]
                                                         
{'loss': 0.7203, 'learning_rate': 0.0004993692315966343, 'epoch': 0.62}

  5%|▌         | 1459/28080 [2:52:46<52:06:05,  7.05s/it]
  5%|▌         | 1460/28080 [2:52:53<52:18:01,  7.07s/it]
                                                         
{'loss': 0.7141, 'learning_rate': 0.0004993671828500998, 'epoch': 0.62}

  5%|▌         | 1460/28080 [2:52:53<52:18:01,  7.07s/it]
  5%|▌         | 1461/28080 [2:53:00<52:24:28,  7.09s/it]
                                                         
{'loss': 0.7119, 'learning_rate': 0.0004993651307859923, 'epoch': 0.62}

  5%|▌         | 1461/28080 [2:53:00<52:24:28,  7.09s/it]
  5%|▌         | 1462/28080 [2:53:07<52:16:59,  7.07s/it]
                                                         
{'loss': 0.7229, 'learning_rate': 0.0004993630754043388, 'epoch': 0.62}

  5%|▌         | 1462/28080 [2:53:07<52:16:59,  7.07s/it]
  5%|▌         | 1463/28080 [2:53:14<52:24:46,  7.09s/it]
                                                         
{'loss': 0.7327, 'learning_rate': 0.0004993610167051669, 'epoch': 0.62}

  5%|▌         | 1463/28080 [2:53:14<52:24:46,  7.09s/it]
  5%|▌         | 1464/28080 [2:53:21<52:30:13,  7.10s/it]
                                                         
{'loss': 0.7026, 'learning_rate': 0.0004993589546885039, 'epoch': 0.63}

  5%|▌         | 1464/28080 [2:53:21<52:30:13,  7.10s/it]
  5%|▌         | 1465/28080 [2:53:28<52:27:54,  7.10s/it]
                                                         
{'loss': 0.7187, 'learning_rate': 0.0004993568893543773, 'epoch': 0.63}

  5%|▌         | 1465/28080 [2:53:28<52:27:54,  7.10s/it]
  5%|▌         | 1466/28080 [2:53:35<52:31:24,  7.10s/it]
                                                         
{'loss': 0.7108, 'learning_rate': 0.0004993548207028145, 'epoch': 0.63}

  5%|▌         | 1466/28080 [2:53:35<52:31:24,  7.10s/it]
  5%|▌         | 1467/28080 [2:53:43<52:35:30,  7.11s/it]
                                                         
{'loss': 0.7192, 'learning_rate': 0.000499352748733843, 'epoch': 0.63}

  5%|▌         | 1467/28080 [2:53:43<52:35:30,  7.11s/it]
  5%|▌         | 1468/28080 [2:53:50<52:33:37,  7.11s/it]
                                                         
{'loss': 0.724, 'learning_rate': 0.0004993506734474907, 'epoch': 0.63}

  5%|▌         | 1468/28080 [2:53:50<52:33:37,  7.11s/it]
  5%|▌         | 1469/28080 [2:53:57<52:34:26,  7.11s/it]
                                                         
{'loss': 0.7136, 'learning_rate': 0.0004993485948437846, 'epoch': 0.63}

  5%|▌         | 1469/28080 [2:53:57<52:34:26,  7.11s/it]
  5%|▌         | 1470/28080 [2:54:04<52:46:00,  7.14s/it]
                                                         
{'loss': 0.7129, 'learning_rate': 0.0004993465129227529, 'epoch': 0.63}

  5%|▌         | 1470/28080 [2:54:04<52:46:00,  7.14s/it]
  5%|▌         | 1471/28080 [2:54:11<52:38:44,  7.12s/it]
                                                         
{'loss': 0.7238, 'learning_rate': 0.0004993444276844229, 'epoch': 0.63}

  5%|▌         | 1471/28080 [2:54:11<52:38:44,  7.12s/it]
  5%|▌         | 1472/28080 [2:54:18<52:27:03,  7.10s/it]
                                                         
{'loss': 0.7383, 'learning_rate': 0.0004993423391288226, 'epoch': 0.63}

  5%|▌         | 1472/28080 [2:54:18<52:27:03,  7.10s/it]
  5%|▌         | 1473/28080 [2:54:25<52:30:27,  7.10s/it]
                                                         
{'loss': 0.7011, 'learning_rate': 0.0004993402472559798, 'epoch': 0.63}

  5%|▌         | 1473/28080 [2:54:25<52:30:27,  7.10s/it]
  5%|▌         | 1474/28080 [2:54:32<52:27:51,  7.10s/it]
                                                         
{'loss': 0.7192, 'learning_rate': 0.0004993381520659221, 'epoch': 0.63}

  5%|▌         | 1474/28080 [2:54:32<52:27:51,  7.10s/it]
  5%|▌         | 1475/28080 [2:54:39<52:26:51,  7.10s/it]
                                                         
{'loss': 0.7155, 'learning_rate': 0.0004993360535586776, 'epoch': 0.63}

  5%|▌         | 1475/28080 [2:54:39<52:26:51,  7.10s/it]
  5%|▌         | 1476/28080 [2:54:47<52:21:31,  7.09s/it]
                                                         
{'loss': 0.7068, 'learning_rate': 0.0004993339517342742, 'epoch': 0.63}

  5%|▌         | 1476/28080 [2:54:47<52:21:31,  7.09s/it]
  5%|▌         | 1477/28080 [2:54:54<52:36:01,  7.12s/it]
                                                         
{'loss': 0.7094, 'learning_rate': 0.0004993318465927397, 'epoch': 0.63}

  5%|▌         | 1477/28080 [2:54:54<52:36:01,  7.12s/it]
  5%|▌         | 1478/28080 [2:55:01<52:36:56,  7.12s/it]
                                                         
{'loss': 0.691, 'learning_rate': 0.0004993297381341022, 'epoch': 0.63}

  5%|▌         | 1478/28080 [2:55:01<52:36:56,  7.12s/it]
  5%|▌         | 1479/28080 [2:55:08<52:33:35,  7.11s/it]
                                                         
{'loss': 0.7138, 'learning_rate': 0.0004993276263583898, 'epoch': 0.63}

  5%|▌         | 1479/28080 [2:55:08<52:33:35,  7.11s/it]
  5%|▌         | 1480/28080 [2:55:15<52:31:07,  7.11s/it]
                                                         
{'loss': 0.7265, 'learning_rate': 0.0004993255112656305, 'epoch': 0.63}

  5%|▌         | 1480/28080 [2:55:15<52:31:07,  7.11s/it]
  5%|▌         | 1481/28080 [2:55:22<52:37:39,  7.12s/it]
                                                         
{'loss': 0.7367, 'learning_rate': 0.0004993233928558525, 'epoch': 0.63}

  5%|▌         | 1481/28080 [2:55:22<52:37:39,  7.12s/it]
  5%|▌         | 1482/28080 [2:55:29<52:36:17,  7.12s/it]
                                                         
{'loss': 0.7373, 'learning_rate': 0.000499321271129084, 'epoch': 0.63}

  5%|▌         | 1482/28080 [2:55:29<52:36:17,  7.12s/it]
  5%|▌         | 1483/28080 [2:55:36<52:43:42,  7.14s/it]
                                                         
{'loss': 0.7169, 'learning_rate': 0.0004993191460853531, 'epoch': 0.63}

  5%|▌         | 1483/28080 [2:55:36<52:43:42,  7.14s/it]
  5%|▌         | 1484/28080 [2:55:44<52:35:28,  7.12s/it]
                                                         
{'loss': 0.7201, 'learning_rate': 0.0004993170177246882, 'epoch': 0.63}

  5%|▌         | 1484/28080 [2:55:44<52:35:28,  7.12s/it]
  5%|▌         | 1485/28080 [2:55:51<52:34:26,  7.12s/it]
                                                         
{'loss': 0.7399, 'learning_rate': 0.0004993148860471177, 'epoch': 0.63}

  5%|▌         | 1485/28080 [2:55:51<52:34:26,  7.12s/it]
  5%|▌         | 1486/28080 [2:55:58<52:24:49,  7.10s/it]
                                                         
{'loss': 0.7024, 'learning_rate': 0.0004993127510526698, 'epoch': 0.63}

  5%|▌         | 1486/28080 [2:55:58<52:24:49,  7.10s/it]
  5%|▌         | 1487/28080 [2:56:05<52:39:44,  7.13s/it]
                                                         
{'loss': 0.7149, 'learning_rate': 0.0004993106127413729, 'epoch': 0.64}

  5%|▌         | 1487/28080 [2:56:05<52:39:44,  7.13s/it]
  5%|▌         | 1488/28080 [2:56:12<52:33:38,  7.12s/it]
                                                         
{'loss': 0.6886, 'learning_rate': 0.0004993084711132556, 'epoch': 0.64}

  5%|▌         | 1488/28080 [2:56:12<52:33:38,  7.12s/it]
  5%|▌         | 1489/28080 [2:56:19<52:38:07,  7.13s/it]
                                                         
{'loss': 0.7145, 'learning_rate': 0.0004993063261683462, 'epoch': 0.64}

  5%|▌         | 1489/28080 [2:56:19<52:38:07,  7.13s/it]
  5%|▌         | 1490/28080 [2:56:26<52:31:26,  7.11s/it]
                                                         
{'loss': 0.7226, 'learning_rate': 0.0004993041779066733, 'epoch': 0.64}

  5%|▌         | 1490/28080 [2:56:26<52:31:26,  7.11s/it]
  5%|▌         | 1491/28080 [2:56:33<52:47:41,  7.15s/it]
                                                         
{'loss': 0.7036, 'learning_rate': 0.0004993020263282656, 'epoch': 0.64}

  5%|▌         | 1491/28080 [2:56:33<52:47:41,  7.15s/it]
  5%|▌         | 1492/28080 [2:56:41<52:42:19,  7.14s/it]
                                                         
{'loss': 0.7235, 'learning_rate': 0.0004992998714331516, 'epoch': 0.64}

  5%|▌         | 1492/28080 [2:56:41<52:42:19,  7.14s/it]
  5%|▌         | 1493/28080 [2:56:48<52:38:12,  7.13s/it]
                                                         
{'loss': 0.7341, 'learning_rate': 0.0004992977132213599, 'epoch': 0.64}

  5%|▌         | 1493/28080 [2:56:48<52:38:12,  7.13s/it]
  5%|▌         | 1494/28080 [2:56:55<52:46:24,  7.15s/it]
                                                         
{'loss': 0.7128, 'learning_rate': 0.0004992955516929194, 'epoch': 0.64}

  5%|▌         | 1494/28080 [2:56:55<52:46:24,  7.15s/it]
  5%|▌         | 1495/28080 [2:57:02<52:57:07,  7.17s/it]
                                                         
{'loss': 0.7133, 'learning_rate': 0.0004992933868478587, 'epoch': 0.64}

  5%|▌         | 1495/28080 [2:57:02<52:57:07,  7.17s/it]
  5%|▌         | 1496/28080 [2:57:09<52:52:06,  7.16s/it]
                                                         
{'loss': 0.7247, 'learning_rate': 0.0004992912186862067, 'epoch': 0.64}

  5%|▌         | 1496/28080 [2:57:09<52:52:06,  7.16s/it]
  5%|▌         | 1497/28080 [2:57:16<52:55:49,  7.17s/it]
                                                         
{'loss': 0.7088, 'learning_rate': 0.0004992890472079923, 'epoch': 0.64}

  5%|▌         | 1497/28080 [2:57:16<52:55:49,  7.17s/it]
  5%|▌         | 1498/28080 [2:57:24<52:52:51,  7.16s/it]
                                                         
{'loss': 0.7228, 'learning_rate': 0.0004992868724132442, 'epoch': 0.64}

  5%|▌         | 1498/28080 [2:57:24<52:52:51,  7.16s/it]
  5%|▌         | 1499/28080 [2:57:31<52:51:13,  7.16s/it]
                                                         
{'loss': 0.7176, 'learning_rate': 0.0004992846943019916, 'epoch': 0.64}

  5%|▌         | 1499/28080 [2:57:31<52:51:13,  7.16s/it]
  5%|▌         | 1500/28080 [2:57:38<52:35:22,  7.12s/it]
                                                         
{'loss': 0.7228, 'learning_rate': 0.0004992825128742631, 'epoch': 0.64}

  5%|▌         | 1500/28080 [2:57:38<52:35:22,  7.12s/it]
  5%|▌         | 1501/28080 [2:57:45<52:38:24,  7.13s/it]
                                                         
{'loss': 0.7181, 'learning_rate': 0.000499280328130088, 'epoch': 0.64}

  5%|▌         | 1501/28080 [2:57:45<52:38:24,  7.13s/it]
  5%|▌         | 1502/28080 [2:57:52<52:32:11,  7.12s/it]
                                                         
{'loss': 0.7332, 'learning_rate': 0.0004992781400694953, 'epoch': 0.64}

  5%|▌         | 1502/28080 [2:57:52<52:32:11,  7.12s/it]
  5%|▌         | 1503/28080 [2:57:59<52:32:33,  7.12s/it]
                                                         
{'loss': 0.6989, 'learning_rate': 0.0004992759486925143, 'epoch': 0.64}

  5%|▌         | 1503/28080 [2:57:59<52:32:33,  7.12s/it]
  5%|▌         | 1504/28080 [2:58:06<52:28:35,  7.11s/it]
                                                         
{'loss': 0.7047, 'learning_rate': 0.0004992737539991737, 'epoch': 0.64}

  5%|▌         | 1504/28080 [2:58:06<52:28:35,  7.11s/it]
  5%|▌         | 1505/28080 [2:58:13<52:29:48,  7.11s/it]
                                                         
{'loss': 0.7064, 'learning_rate': 0.0004992715559895032, 'epoch': 0.64}

  5%|▌         | 1505/28080 [2:58:13<52:29:48,  7.11s/it]
  5%|▌         | 1506/28080 [2:58:20<52:27:41,  7.11s/it]
                                                         
{'loss': 0.7097, 'learning_rate': 0.0004992693546635316, 'epoch': 0.64}

  5%|▌         | 1506/28080 [2:58:20<52:27:41,  7.11s/it]
  5%|▌         | 1507/28080 [2:58:28<52:35:12,  7.12s/it]
                                                         
{'loss': 0.7066, 'learning_rate': 0.0004992671500212884, 'epoch': 0.64}

  5%|▌         | 1507/28080 [2:58:28<52:35:12,  7.12s/it]
  5%|▌         | 1508/28080 [2:58:35<52:40:22,  7.14s/it]
                                                         
{'loss': 0.7024, 'learning_rate': 0.000499264942062803, 'epoch': 0.64}

  5%|▌         | 1508/28080 [2:58:35<52:40:22,  7.14s/it]
  5%|▌         | 1509/28080 [2:58:42<52:34:36,  7.12s/it]
                                                         
{'loss': 0.7075, 'learning_rate': 0.0004992627307881048, 'epoch': 0.64}

  5%|▌         | 1509/28080 [2:58:42<52:34:36,  7.12s/it]
  5%|▌         | 1510/28080 [2:58:49<52:44:54,  7.15s/it]
                                                         
{'loss': 0.7178, 'learning_rate': 0.0004992605161972231, 'epoch': 0.65}

  5%|▌         | 1510/28080 [2:58:49<52:44:54,  7.15s/it]
  5%|▌         | 1511/28080 [2:58:56<52:42:51,  7.14s/it]
                                                         
{'loss': 0.7142, 'learning_rate': 0.0004992582982901872, 'epoch': 0.65}

  5%|▌         | 1511/28080 [2:58:56<52:42:51,  7.14s/it]
  5%|▌         | 1512/28080 [2:59:03<52:42:13,  7.14s/it]
                                                         
{'loss': 0.7271, 'learning_rate': 0.0004992560770670268, 'epoch': 0.65}

  5%|▌         | 1512/28080 [2:59:03<52:42:13,  7.14s/it]
  5%|▌         | 1513/28080 [2:59:10<52:39:18,  7.14s/it]
                                                         
{'loss': 0.7373, 'learning_rate': 0.0004992538525277715, 'epoch': 0.65}

  5%|▌         | 1513/28080 [2:59:10<52:39:18,  7.14s/it]
  5%|▌         | 1514/28080 [2:59:18<52:33:20,  7.12s/it]
                                                         
{'loss': 0.7268, 'learning_rate': 0.0004992516246724508, 'epoch': 0.65}

  5%|▌         | 1514/28080 [2:59:18<52:33:20,  7.12s/it]
  5%|▌         | 1515/28080 [2:59:25<52:21:14,  7.09s/it]
                                                         
{'loss': 0.7093, 'learning_rate': 0.0004992493935010946, 'epoch': 0.65}

  5%|▌         | 1515/28080 [2:59:25<52:21:14,  7.09s/it]
  5%|▌         | 1516/28080 [2:59:32<52:16:04,  7.08s/it]
                                                         
{'loss': 0.7086, 'learning_rate': 0.0004992471590137322, 'epoch': 0.65}

  5%|▌         | 1516/28080 [2:59:32<52:16:04,  7.08s/it]
  5%|▌         | 1517/28080 [2:59:39<52:20:26,  7.09s/it]
                                                         
{'loss': 0.6975, 'learning_rate': 0.0004992449212103934, 'epoch': 0.65}

  5%|▌         | 1517/28080 [2:59:39<52:20:26,  7.09s/it]
  5%|▌         | 1518/28080 [2:59:46<52:06:34,  7.06s/it]
                                                         
{'loss': 0.7319, 'learning_rate': 0.0004992426800911081, 'epoch': 0.65}

  5%|▌         | 1518/28080 [2:59:46<52:06:34,  7.06s/it]
  5%|▌         | 1519/28080 [2:59:53<52:16:48,  7.09s/it]
                                                         
{'loss': 0.7225, 'learning_rate': 0.0004992404356559061, 'epoch': 0.65}

  5%|▌         | 1519/28080 [2:59:53<52:16:48,  7.09s/it]
  5%|▌         | 1520/28080 [3:00:00<52:26:19,  7.11s/it]
                                                         
{'loss': 0.7044, 'learning_rate': 0.0004992381879048172, 'epoch': 0.65}

  5%|▌         | 1520/28080 [3:00:00<52:26:19,  7.11s/it]
  5%|▌         | 1521/28080 [3:00:07<52:27:11,  7.11s/it]
                                                         
{'loss': 0.7222, 'learning_rate': 0.0004992359368378714, 'epoch': 0.65}

  5%|▌         | 1521/28080 [3:00:07<52:27:11,  7.11s/it]
  5%|▌         | 1522/28080 [3:00:14<52:31:45,  7.12s/it]
                                                         
{'loss': 0.7101, 'learning_rate': 0.0004992336824550985, 'epoch': 0.65}

  5%|▌         | 1522/28080 [3:00:14<52:31:45,  7.12s/it]
  5%|▌         | 1523/28080 [3:00:21<52:36:22,  7.13s/it]
                                                         
{'loss': 0.6995, 'learning_rate': 0.0004992314247565286, 'epoch': 0.65}

  5%|▌         | 1523/28080 [3:00:21<52:36:22,  7.13s/it]
  5%|▌         | 1524/28080 [3:00:29<52:29:04,  7.11s/it]
                                                         
{'loss': 0.7032, 'learning_rate': 0.0004992291637421917, 'epoch': 0.65}

  5%|▌         | 1524/28080 [3:00:29<52:29:04,  7.11s/it]
  5%|▌         | 1525/28080 [3:00:36<52:29:34,  7.12s/it]
                                                         
{'loss': 0.7017, 'learning_rate': 0.000499226899412118, 'epoch': 0.65}

  5%|▌         | 1525/28080 [3:00:36<52:29:34,  7.12s/it]
  5%|▌         | 1526/28080 [3:00:43<52:25:25,  7.11s/it]
                                                         
{'loss': 0.7113, 'learning_rate': 0.0004992246317663373, 'epoch': 0.65}

  5%|▌         | 1526/28080 [3:00:43<52:25:25,  7.11s/it]
  5%|▌         | 1527/28080 [3:00:50<52:35:08,  7.13s/it]
                                                         
{'loss': 0.7172, 'learning_rate': 0.0004992223608048802, 'epoch': 0.65}

  5%|▌         | 1527/28080 [3:00:50<52:35:08,  7.13s/it]
  5%|▌         | 1528/28080 [3:00:57<52:37:58,  7.14s/it]
                                                         
{'loss': 0.7287, 'learning_rate': 0.0004992200865277766, 'epoch': 0.65}

  5%|▌         | 1528/28080 [3:00:57<52:37:58,  7.14s/it]
  5%|▌         | 1529/28080 [3:01:04<52:25:06,  7.11s/it]
                                                         
{'loss': 0.7108, 'learning_rate': 0.0004992178089350569, 'epoch': 0.65}

  5%|▌         | 1529/28080 [3:01:04<52:25:06,  7.11s/it]
  5%|▌         | 1530/28080 [3:01:11<52:30:00,  7.12s/it]
                                                         
{'loss': 0.7133, 'learning_rate': 0.0004992155280267513, 'epoch': 0.65}

  5%|▌         | 1530/28080 [3:01:11<52:30:00,  7.12s/it]
  5%|▌         | 1531/28080 [3:01:18<52:45:29,  7.15s/it]
                                                         
{'loss': 0.7028, 'learning_rate': 0.0004992132438028903, 'epoch': 0.65}

  5%|▌         | 1531/28080 [3:01:18<52:45:29,  7.15s/it]
  5%|▌         | 1532/28080 [3:01:26<52:31:44,  7.12s/it]
                                                         
{'loss': 0.7115, 'learning_rate': 0.0004992109562635041, 'epoch': 0.65}

  5%|▌         | 1532/28080 [3:01:26<52:31:44,  7.12s/it]
  5%|▌         | 1533/28080 [3:01:33<52:22:57,  7.10s/it]
                                                         
{'loss': 0.7148, 'learning_rate': 0.0004992086654086232, 'epoch': 0.65}

  5%|▌         | 1533/28080 [3:01:33<52:22:57,  7.10s/it]
  5%|▌         | 1534/28080 [3:01:40<52:34:58,  7.13s/it]
                                                         
{'loss': 0.735, 'learning_rate': 0.0004992063712382782, 'epoch': 0.66}

  5%|▌         | 1534/28080 [3:01:40<52:34:58,  7.13s/it]
  5%|▌         | 1535/28080 [3:01:47<52:33:35,  7.13s/it]
                                                         
{'loss': 0.7317, 'learning_rate': 0.0004992040737524994, 'epoch': 0.66}

  5%|▌         | 1535/28080 [3:01:47<52:33:35,  7.13s/it]
  5%|▌         | 1536/28080 [3:01:54<52:27:33,  7.11s/it]
                                                         
{'loss': 0.7138, 'learning_rate': 0.0004992017729513175, 'epoch': 0.66}

  5%|▌         | 1536/28080 [3:01:54<52:27:33,  7.11s/it]
  5%|▌         | 1537/28080 [3:02:01<52:31:59,  7.13s/it]
                                                         
{'loss': 0.7029, 'learning_rate': 0.0004991994688347632, 'epoch': 0.66}

  5%|▌         | 1537/28080 [3:02:01<52:31:59,  7.13s/it]
  5%|▌         | 1538/28080 [3:02:08<52:24:13,  7.11s/it]
                                                         
{'loss': 0.7069, 'learning_rate': 0.0004991971614028669, 'epoch': 0.66}

  5%|▌         | 1538/28080 [3:02:08<52:24:13,  7.11s/it]
  5%|▌         | 1539/28080 [3:02:15<52:28:47,  7.12s/it]
                                                         
{'loss': 0.7108, 'learning_rate': 0.0004991948506556596, 'epoch': 0.66}

  5%|▌         | 1539/28080 [3:02:15<52:28:47,  7.12s/it]
  5%|▌         | 1540/28080 [3:02:22<52:27:30,  7.12s/it]
                                                         
{'loss': 0.7043, 'learning_rate': 0.0004991925365931719, 'epoch': 0.66}

  5%|▌         | 1540/28080 [3:02:22<52:27:30,  7.12s/it]
  5%|▌         | 1541/28080 [3:02:30<52:26:59,  7.11s/it]
                                                         
{'loss': 0.7079, 'learning_rate': 0.0004991902192154345, 'epoch': 0.66}

  5%|▌         | 1541/28080 [3:02:30<52:26:59,  7.11s/it]
  5%|▌         | 1542/28080 [3:02:37<52:15:45,  7.09s/it]
                                                         
{'loss': 0.7243, 'learning_rate': 0.0004991878985224783, 'epoch': 0.66}

  5%|▌         | 1542/28080 [3:02:37<52:15:45,  7.09s/it]
  5%|▌         | 1543/28080 [3:02:44<52:11:30,  7.08s/it]
                                                         
{'loss': 0.6961, 'learning_rate': 0.0004991855745143343, 'epoch': 0.66}

  5%|▌         | 1543/28080 [3:02:44<52:11:30,  7.08s/it]
  5%|▌         | 1544/28080 [3:02:51<52:01:49,  7.06s/it]
                                                         
{'loss': 0.7178, 'learning_rate': 0.0004991832471910331, 'epoch': 0.66}

  5%|▌         | 1544/28080 [3:02:51<52:01:49,  7.06s/it]
  6%|▌         | 1545/28080 [3:02:58<52:03:42,  7.06s/it]
                                                         
{'loss': 0.7062, 'learning_rate': 0.0004991809165526061, 'epoch': 0.66}

  6%|▌         | 1545/28080 [3:02:58<52:03:42,  7.06s/it]
  6%|▌         | 1546/28080 [3:03:05<51:45:03,  7.02s/it]
                                                         
{'loss': 0.7237, 'learning_rate': 0.0004991785825990839, 'epoch': 0.66}

  6%|▌         | 1546/28080 [3:03:05<51:45:03,  7.02s/it]
  6%|▌         | 1547/28080 [3:03:12<51:44:30,  7.02s/it]
                                                         
{'loss': 0.7214, 'learning_rate': 0.0004991762453304977, 'epoch': 0.66}

  6%|▌         | 1547/28080 [3:03:12<51:44:30,  7.02s/it]
  6%|▌         | 1548/28080 [3:03:19<51:53:05,  7.04s/it]
                                                         
{'loss': 0.7072, 'learning_rate': 0.0004991739047468788, 'epoch': 0.66}

  6%|▌         | 1548/28080 [3:03:19<51:53:05,  7.04s/it]
  6%|▌         | 1549/28080 [3:03:26<52:17:24,  7.10s/it]
                                                         
{'loss': 0.7075, 'learning_rate': 0.000499171560848258, 'epoch': 0.66}

  6%|▌         | 1549/28080 [3:03:26<52:17:24,  7.10s/it]
  6%|▌         | 1550/28080 [3:03:33<52:09:30,  7.08s/it]
                                                         
{'loss': 0.7054, 'learning_rate': 0.0004991692136346668, 'epoch': 0.66}

  6%|▌         | 1550/28080 [3:03:33<52:09:30,  7.08s/it]
  6%|▌         | 1551/28080 [3:03:40<52:11:39,  7.08s/it]
                                                         
{'loss': 0.6958, 'learning_rate': 0.000499166863106136, 'epoch': 0.66}

  6%|▌         | 1551/28080 [3:03:40<52:11:39,  7.08s/it]
  6%|▌         | 1552/28080 [3:03:47<52:15:45,  7.09s/it]
                                                         
{'loss': 0.6937, 'learning_rate': 0.0004991645092626973, 'epoch': 0.66}

  6%|▌         | 1552/28080 [3:03:47<52:15:45,  7.09s/it]
  6%|▌         | 1553/28080 [3:03:54<52:12:46,  7.09s/it]
                                                         
{'loss': 0.7217, 'learning_rate': 0.0004991621521043819, 'epoch': 0.66}

  6%|▌         | 1553/28080 [3:03:54<52:12:46,  7.09s/it]
  6%|▌         | 1554/28080 [3:04:01<52:21:57,  7.11s/it]
                                                         
{'loss': 0.7015, 'learning_rate': 0.0004991597916312211, 'epoch': 0.66}

  6%|▌         | 1554/28080 [3:04:01<52:21:57,  7.11s/it]
  6%|▌         | 1555/28080 [3:04:09<52:18:16,  7.10s/it]
                                                         
{'loss': 0.6987, 'learning_rate': 0.0004991574278432461, 'epoch': 0.66}

  6%|▌         | 1555/28080 [3:04:09<52:18:16,  7.10s/it]
  6%|▌         | 1556/28080 [3:04:16<52:15:17,  7.09s/it]
                                                         
{'loss': 0.6899, 'learning_rate': 0.0004991550607404889, 'epoch': 0.66}

  6%|▌         | 1556/28080 [3:04:16<52:15:17,  7.09s/it]
  6%|▌         | 1557/28080 [3:04:23<52:15:24,  7.09s/it]
                                                         
{'loss': 0.7067, 'learning_rate': 0.0004991526903229804, 'epoch': 0.67}

  6%|▌         | 1557/28080 [3:04:23<52:15:24,  7.09s/it]
  6%|▌         | 1558/28080 [3:04:30<52:17:52,  7.10s/it]
                                                         
{'loss': 0.7101, 'learning_rate': 0.0004991503165907525, 'epoch': 0.67}

  6%|▌         | 1558/28080 [3:04:30<52:17:52,  7.10s/it]
  6%|▌         | 1559/28080 [3:04:37<52:18:49,  7.10s/it]
                                                         
{'loss': 0.7221, 'learning_rate': 0.0004991479395438366, 'epoch': 0.67}

  6%|▌         | 1559/28080 [3:04:37<52:18:49,  7.10s/it]
  6%|▌         | 1560/28080 [3:04:44<52:22:16,  7.11s/it]
                                                         
{'loss': 0.7149, 'learning_rate': 0.0004991455591822645, 'epoch': 0.67}

  6%|▌         | 1560/28080 [3:04:44<52:22:16,  7.11s/it]
  6%|▌         | 1561/28080 [3:04:51<52:26:36,  7.12s/it]
                                                         
{'loss': 0.7059, 'learning_rate': 0.0004991431755060676, 'epoch': 0.67}

  6%|▌         | 1561/28080 [3:04:51<52:26:36,  7.12s/it]
  6%|▌         | 1562/28080 [3:04:58<52:34:38,  7.14s/it]
                                                         
{'loss': 0.7182, 'learning_rate': 0.000499140788515278, 'epoch': 0.67}

  6%|▌         | 1562/28080 [3:04:58<52:34:38,  7.14s/it]
  6%|▌         | 1563/28080 [3:05:06<52:32:21,  7.13s/it]
                                                         
{'loss': 0.7032, 'learning_rate': 0.0004991383982099272, 'epoch': 0.67}

  6%|▌         | 1563/28080 [3:05:06<52:32:21,  7.13s/it]
  6%|▌         | 1564/28080 [3:05:13<52:29:19,  7.13s/it]
                                                         
{'loss': 0.7179, 'learning_rate': 0.0004991360045900468, 'epoch': 0.67}

  6%|▌         | 1564/28080 [3:05:13<52:29:19,  7.13s/it]
  6%|▌         | 1565/28080 [3:05:20<52:22:12,  7.11s/it]
                                                         
{'loss': 0.7296, 'learning_rate': 0.0004991336076556691, 'epoch': 0.67}

  6%|▌         | 1565/28080 [3:05:20<52:22:12,  7.11s/it]
  6%|▌         | 1566/28080 [3:05:27<52:21:17,  7.11s/it]
                                                         
{'loss': 0.719, 'learning_rate': 0.0004991312074068258, 'epoch': 0.67}

  6%|▌         | 1566/28080 [3:05:27<52:21:17,  7.11s/it]
  6%|▌         | 1567/28080 [3:05:34<52:19:51,  7.11s/it]
                                                         
{'loss': 0.747, 'learning_rate': 0.0004991288038435486, 'epoch': 0.67}

  6%|▌         | 1567/28080 [3:05:34<52:19:51,  7.11s/it]
  6%|▌         | 1568/28080 [3:05:41<52:19:03,  7.10s/it]
                                                         
{'loss': 0.7333, 'learning_rate': 0.0004991263969658698, 'epoch': 0.67}

  6%|▌         | 1568/28080 [3:05:41<52:19:03,  7.10s/it]
  6%|▌         | 1569/28080 [3:05:48<52:22:24,  7.11s/it]
                                                         
{'loss': 0.7108, 'learning_rate': 0.0004991239867738213, 'epoch': 0.67}

  6%|▌         | 1569/28080 [3:05:48<52:22:24,  7.11s/it]
  6%|▌         | 1570/28080 [3:05:55<52:23:59,  7.12s/it]
                                                         
{'loss': 0.6994, 'learning_rate': 0.0004991215732674351, 'epoch': 0.67}

  6%|▌         | 1570/28080 [3:05:55<52:23:59,  7.12s/it]
  6%|▌         | 1571/28080 [3:06:02<52:15:56,  7.10s/it]
                                                         
{'loss': 0.7186, 'learning_rate': 0.0004991191564467435, 'epoch': 0.67}

  6%|▌         | 1571/28080 [3:06:02<52:15:56,  7.10s/it]
  6%|▌         | 1572/28080 [3:06:10<52:33:50,  7.14s/it]
                                                         
{'loss': 0.7487, 'learning_rate': 0.0004991167363117783, 'epoch': 0.67}

  6%|▌         | 1572/28080 [3:06:10<52:33:50,  7.14s/it]
  6%|▌         | 1573/28080 [3:06:17<52:20:28,  7.11s/it]
                                                         
{'loss': 0.7084, 'learning_rate': 0.0004991143128625722, 'epoch': 0.67}

  6%|▌         | 1573/28080 [3:06:17<52:20:28,  7.11s/it]
  6%|▌         | 1574/28080 [3:06:24<52:08:29,  7.08s/it]
                                                         
{'loss': 0.7162, 'learning_rate': 0.0004991118860991569, 'epoch': 0.67}

  6%|▌         | 1574/28080 [3:06:24<52:08:29,  7.08s/it]
  6%|▌         | 1575/28080 [3:06:31<52:09:13,  7.08s/it]
                                                         
{'loss': 0.729, 'learning_rate': 0.0004991094560215651, 'epoch': 0.67}

  6%|▌         | 1575/28080 [3:06:31<52:09:13,  7.08s/it]
  6%|▌         | 1576/28080 [3:06:38<52:19:15,  7.11s/it]
                                                         
{'loss': 0.724, 'learning_rate': 0.0004991070226298289, 'epoch': 0.67}

  6%|▌         | 1576/28080 [3:06:38<52:19:15,  7.11s/it]
  6%|▌         | 1577/28080 [3:06:45<52:05:56,  7.08s/it]
                                                         
{'loss': 0.7016, 'learning_rate': 0.0004991045859239809, 'epoch': 0.67}

  6%|▌         | 1577/28080 [3:06:45<52:05:56,  7.08s/it]
  6%|▌         | 1578/28080 [3:06:52<52:18:07,  7.10s/it]
                                                         
{'loss': 0.7127, 'learning_rate': 0.0004991021459040532, 'epoch': 0.67}

  6%|▌         | 1578/28080 [3:06:52<52:18:07,  7.10s/it]
  6%|▌         | 1579/28080 [3:06:59<52:21:41,  7.11s/it]
                                                         
{'loss': 0.7156, 'learning_rate': 0.0004990997025700785, 'epoch': 0.67}

  6%|▌         | 1579/28080 [3:06:59<52:21:41,  7.11s/it]
  6%|▌         | 1580/28080 [3:07:06<52:24:33,  7.12s/it]
                                                         
{'loss': 0.6896, 'learning_rate': 0.0004990972559220893, 'epoch': 0.67}

  6%|▌         | 1580/28080 [3:07:06<52:24:33,  7.12s/it]
  6%|▌         | 1581/28080 [3:07:13<52:25:36,  7.12s/it]
                                                         
{'loss': 0.7264, 'learning_rate': 0.000499094805960118, 'epoch': 0.68}

  6%|▌         | 1581/28080 [3:07:13<52:25:36,  7.12s/it]
  6%|▌         | 1582/28080 [3:07:21<52:34:36,  7.14s/it]
                                                         
{'loss': 0.7083, 'learning_rate': 0.0004990923526841974, 'epoch': 0.68}

  6%|▌         | 1582/28080 [3:07:21<52:34:36,  7.14s/it]
  6%|▌         | 1583/28080 [3:07:28<52:30:55,  7.13s/it]
                                                         
{'loss': 0.7048, 'learning_rate': 0.0004990898960943599, 'epoch': 0.68}

  6%|▌         | 1583/28080 [3:07:28<52:30:55,  7.13s/it]
  6%|▌         | 1584/28080 [3:07:35<52:23:44,  7.12s/it]
                                                         
{'loss': 0.7054, 'learning_rate': 0.0004990874361906384, 'epoch': 0.68}

  6%|▌         | 1584/28080 [3:07:35<52:23:44,  7.12s/it]
  6%|▌         | 1585/28080 [3:07:42<52:18:40,  7.11s/it]
                                                         
{'loss': 0.7044, 'learning_rate': 0.0004990849729730654, 'epoch': 0.68}

  6%|▌         | 1585/28080 [3:07:42<52:18:40,  7.11s/it]
  6%|▌         | 1586/28080 [3:07:49<52:02:35,  7.07s/it]
                                                         
{'loss': 0.7352, 'learning_rate': 0.000499082506441674, 'epoch': 0.68}

  6%|▌         | 1586/28080 [3:07:49<52:02:35,  7.07s/it]
  6%|▌         | 1587/28080 [3:07:56<51:58:22,  7.06s/it]
                                                         
{'loss': 0.7211, 'learning_rate': 0.0004990800365964966, 'epoch': 0.68}

  6%|▌         | 1587/28080 [3:07:56<51:58:22,  7.06s/it]
  6%|▌         | 1588/28080 [3:08:03<52:07:15,  7.08s/it]
                                                         
{'loss': 0.7252, 'learning_rate': 0.0004990775634375664, 'epoch': 0.68}

  6%|▌         | 1588/28080 [3:08:03<52:07:15,  7.08s/it]
  6%|▌         | 1589/28080 [3:08:10<52:11:23,  7.09s/it]
                                                         
{'loss': 0.7181, 'learning_rate': 0.0004990750869649161, 'epoch': 0.68}

  6%|▌         | 1589/28080 [3:08:10<52:11:23,  7.09s/it]
  6%|▌         | 1590/28080 [3:08:17<52:07:41,  7.08s/it]
                                                         
{'loss': 0.7172, 'learning_rate': 0.0004990726071785788, 'epoch': 0.68}

  6%|▌         | 1590/28080 [3:08:17<52:07:41,  7.08s/it]
  6%|▌         | 1591/28080 [3:08:24<52:18:01,  7.11s/it]
                                                         
{'loss': 0.714, 'learning_rate': 0.0004990701240785875, 'epoch': 0.68}

  6%|▌         | 1591/28080 [3:08:24<52:18:01,  7.11s/it]
  6%|▌         | 1592/28080 [3:08:31<52:09:28,  7.09s/it]
                                                         
{'loss': 0.7287, 'learning_rate': 0.0004990676376649749, 'epoch': 0.68}

  6%|▌         | 1592/28080 [3:08:31<52:09:28,  7.09s/it]
  6%|▌         | 1593/28080 [3:08:39<52:11:01,  7.09s/it]
                                                         
{'loss': 0.7069, 'learning_rate': 0.0004990651479377745, 'epoch': 0.68}

  6%|▌         | 1593/28080 [3:08:39<52:11:01,  7.09s/it]
  6%|▌         | 1594/28080 [3:08:46<52:24:42,  7.12s/it]
                                                         
{'loss': 0.688, 'learning_rate': 0.0004990626548970192, 'epoch': 0.68}

  6%|▌         | 1594/28080 [3:08:46<52:24:42,  7.12s/it]
  6%|▌         | 1595/28080 [3:08:53<52:32:59,  7.14s/it]
                                                         
{'loss': 0.7243, 'learning_rate': 0.0004990601585427423, 'epoch': 0.68}

  6%|▌         | 1595/28080 [3:08:53<52:32:59,  7.14s/it]
  6%|▌         | 1596/28080 [3:09:00<52:29:10,  7.13s/it]
                                                         
{'loss': 0.6876, 'learning_rate': 0.0004990576588749768, 'epoch': 0.68}

  6%|▌         | 1596/28080 [3:09:00<52:29:10,  7.13s/it]
  6%|▌         | 1597/28080 [3:09:07<52:29:44,  7.14s/it]
                                                         
{'loss': 0.712, 'learning_rate': 0.0004990551558937561, 'epoch': 0.68}

  6%|▌         | 1597/28080 [3:09:07<52:29:44,  7.14s/it]
  6%|▌         | 1598/28080 [3:09:14<52:25:21,  7.13s/it]
                                                         
{'loss': 0.716, 'learning_rate': 0.0004990526495991137, 'epoch': 0.68}

  6%|▌         | 1598/28080 [3:09:14<52:25:21,  7.13s/it]
  6%|▌         | 1599/28080 [3:09:21<52:17:09,  7.11s/it]
                                                         
{'loss': 0.7222, 'learning_rate': 0.0004990501399910825, 'epoch': 0.68}

  6%|▌         | 1599/28080 [3:09:21<52:17:09,  7.11s/it]
  6%|▌         | 1600/28080 [3:09:28<52:03:45,  7.08s/it]
                                                         
{'loss': 0.7215, 'learning_rate': 0.0004990476270696962, 'epoch': 0.68}

  6%|▌         | 1600/28080 [3:09:28<52:03:45,  7.08s/it]
  6%|▌         | 1601/28080 [3:09:35<51:56:09,  7.06s/it]
                                                         
{'loss': 0.717, 'learning_rate': 0.0004990451108349881, 'epoch': 0.68}

  6%|▌         | 1601/28080 [3:09:35<51:56:09,  7.06s/it]
  6%|▌         | 1602/28080 [3:09:43<52:09:16,  7.09s/it]
                                                         
{'loss': 0.7187, 'learning_rate': 0.0004990425912869918, 'epoch': 0.68}

  6%|▌         | 1602/28080 [3:09:43<52:09:16,  7.09s/it]
  6%|▌         | 1603/28080 [3:09:50<52:04:34,  7.08s/it]
                                                         
{'loss': 0.7348, 'learning_rate': 0.0004990400684257408, 'epoch': 0.68}

  6%|▌         | 1603/28080 [3:09:50<52:04:34,  7.08s/it]
  6%|▌         | 1604/28080 [3:09:56<51:34:02,  7.01s/it]
                                                         
{'loss': 0.7638, 'learning_rate': 0.0004990375422512685, 'epoch': 0.69}

  6%|▌         | 1604/28080 [3:09:56<51:34:02,  7.01s/it]
  6%|▌         | 1605/28080 [3:10:04<51:48:40,  7.05s/it]
                                                         
{'loss': 0.7228, 'learning_rate': 0.0004990350127636086, 'epoch': 0.69}

  6%|▌         | 1605/28080 [3:10:04<51:48:40,  7.05s/it]
  6%|▌         | 1606/28080 [3:10:11<51:58:08,  7.07s/it]
                                                         
{'loss': 0.7118, 'learning_rate': 0.0004990324799627949, 'epoch': 0.69}

  6%|▌         | 1606/28080 [3:10:11<51:58:08,  7.07s/it]
  6%|▌         | 1607/28080 [3:10:18<52:09:15,  7.09s/it]
                                                         
{'loss': 0.7024, 'learning_rate': 0.0004990299438488608, 'epoch': 0.69}

  6%|▌         | 1607/28080 [3:10:18<52:09:15,  7.09s/it]
  6%|▌         | 1608/28080 [3:10:25<52:06:55,  7.09s/it]
                                                         
{'loss': 0.7234, 'learning_rate': 0.0004990274044218403, 'epoch': 0.69}

  6%|▌         | 1608/28080 [3:10:25<52:06:55,  7.09s/it]
  6%|▌         | 1609/28080 [3:10:32<52:12:21,  7.10s/it]
                                                         
{'loss': 0.6941, 'learning_rate': 0.0004990248616817671, 'epoch': 0.69}

  6%|▌         | 1609/28080 [3:10:32<52:12:21,  7.10s/it]
  6%|▌         | 1610/28080 [3:10:39<52:16:50,  7.11s/it]
                                                         
{'loss': 0.7019, 'learning_rate': 0.000499022315628675, 'epoch': 0.69}

  6%|▌         | 1610/28080 [3:10:39<52:16:50,  7.11s/it]
  6%|▌         | 1611/28080 [3:10:46<52:13:58,  7.10s/it]
                                                         
{'loss': 0.7289, 'learning_rate': 0.0004990197662625979, 'epoch': 0.69}

  6%|▌         | 1611/28080 [3:10:46<52:13:58,  7.10s/it]
  6%|▌         | 1612/28080 [3:10:53<51:58:47,  7.07s/it]
                                                         
{'loss': 0.6999, 'learning_rate': 0.0004990172135835697, 'epoch': 0.69}

  6%|▌         | 1612/28080 [3:10:53<51:58:47,  7.07s/it]
  6%|▌         | 1613/28080 [3:11:00<52:07:35,  7.09s/it]
                                                         
{'loss': 0.7003, 'learning_rate': 0.0004990146575916244, 'epoch': 0.69}

  6%|▌         | 1613/28080 [3:11:00<52:07:35,  7.09s/it]
  6%|▌         | 1614/28080 [3:11:07<52:08:38,  7.09s/it]
                                                         
{'loss': 0.7016, 'learning_rate': 0.000499012098286796, 'epoch': 0.69}

  6%|▌         | 1614/28080 [3:11:07<52:08:38,  7.09s/it]
  6%|▌         | 1615/28080 [3:11:15<52:12:36,  7.10s/it]
                                                         
{'loss': 0.7068, 'learning_rate': 0.0004990095356691183, 'epoch': 0.69}

  6%|▌         | 1615/28080 [3:11:15<52:12:36,  7.10s/it]
  6%|▌         | 1616/28080 [3:11:22<52:20:31,  7.12s/it]
                                                         
{'loss': 0.6966, 'learning_rate': 0.0004990069697386259, 'epoch': 0.69}

  6%|▌         | 1616/28080 [3:11:22<52:20:31,  7.12s/it]
  6%|▌         | 1617/28080 [3:11:29<52:12:10,  7.10s/it]
                                                         
{'loss': 0.7032, 'learning_rate': 0.0004990044004953525, 'epoch': 0.69}

  6%|▌         | 1617/28080 [3:11:29<52:12:10,  7.10s/it]
  6%|▌         | 1618/28080 [3:11:36<52:18:09,  7.12s/it]
                                                         
{'loss': 0.6853, 'learning_rate': 0.0004990018279393324, 'epoch': 0.69}

  6%|▌         | 1618/28080 [3:11:36<52:18:09,  7.12s/it]
  6%|▌         | 1619/28080 [3:11:43<52:32:31,  7.15s/it]
                                                         
{'loss': 0.7136, 'learning_rate': 0.0004989992520706, 'epoch': 0.69}

  6%|▌         | 1619/28080 [3:11:43<52:32:31,  7.15s/it]
  6%|▌         | 1620/28080 [3:11:50<52:23:14,  7.13s/it]
                                                         
{'loss': 0.7089, 'learning_rate': 0.0004989966728891894, 'epoch': 0.69}

  6%|▌         | 1620/28080 [3:11:50<52:23:14,  7.13s/it]
  6%|▌         | 1621/28080 [3:11:57<52:21:55,  7.12s/it]
                                                         
{'loss': 0.704, 'learning_rate': 0.0004989940903951348, 'epoch': 0.69}

  6%|▌         | 1621/28080 [3:11:57<52:21:55,  7.12s/it]
  6%|▌         | 1622/28080 [3:12:04<52:11:25,  7.10s/it]
                                                         
{'loss': 0.705, 'learning_rate': 0.0004989915045884709, 'epoch': 0.69}

  6%|▌         | 1622/28080 [3:12:04<52:11:25,  7.10s/it]
  6%|▌         | 1623/28080 [3:12:12<52:08:15,  7.09s/it]
                                                         
{'loss': 0.7281, 'learning_rate': 0.0004989889154692319, 'epoch': 0.69}

  6%|▌         | 1623/28080 [3:12:12<52:08:15,  7.09s/it]
  6%|▌         | 1624/28080 [3:12:19<52:00:57,  7.08s/it]
                                                         
{'loss': 0.714, 'learning_rate': 0.000498986323037452, 'epoch': 0.69}

  6%|▌         | 1624/28080 [3:12:19<52:00:57,  7.08s/it]
  6%|▌         | 1625/28080 [3:12:26<52:17:34,  7.12s/it]
                                                         
{'loss': 0.7219, 'learning_rate': 0.0004989837272931662, 'epoch': 0.69}

  6%|▌         | 1625/28080 [3:12:26<52:17:34,  7.12s/it]
  6%|▌         | 1626/28080 [3:12:33<52:04:00,  7.09s/it]
                                                         
{'loss': 0.7265, 'learning_rate': 0.0004989811282364086, 'epoch': 0.69}

  6%|▌         | 1626/28080 [3:12:33<52:04:00,  7.09s/it]
  6%|▌         | 1627/28080 [3:12:40<52:05:22,  7.09s/it]
                                                         
{'loss': 0.7265, 'learning_rate': 0.000498978525867214, 'epoch': 0.7}

  6%|▌         | 1627/28080 [3:12:40<52:05:22,  7.09s/it]
  6%|▌         | 1628/28080 [3:12:47<52:14:33,  7.11s/it]
                                                         
{'loss': 0.7059, 'learning_rate': 0.0004989759201856171, 'epoch': 0.7}

  6%|▌         | 1628/28080 [3:12:47<52:14:33,  7.11s/it]
  6%|▌         | 1629/28080 [3:12:54<52:09:46,  7.10s/it]
                                                         
{'loss': 0.7228, 'learning_rate': 0.0004989733111916522, 'epoch': 0.7}

  6%|▌         | 1629/28080 [3:12:54<52:09:46,  7.10s/it]
  6%|▌         | 1630/28080 [3:13:01<51:58:30,  7.07s/it]
                                                         
{'loss': 0.6844, 'learning_rate': 0.0004989706988853544, 'epoch': 0.7}

  6%|▌         | 1630/28080 [3:13:01<51:58:30,  7.07s/it]
  6%|▌         | 1631/28080 [3:13:08<51:55:42,  7.07s/it]
                                                         
{'loss': 0.7103, 'learning_rate': 0.0004989680832667583, 'epoch': 0.7}

  6%|▌         | 1631/28080 [3:13:08<51:55:42,  7.07s/it]
  6%|▌         | 1632/28080 [3:13:15<52:07:57,  7.10s/it]
                                                         
{'loss': 0.7212, 'learning_rate': 0.0004989654643358987, 'epoch': 0.7}

  6%|▌         | 1632/28080 [3:13:15<52:07:57,  7.10s/it]
  6%|▌         | 1633/28080 [3:13:22<52:08:21,  7.10s/it]
                                                         
{'loss': 0.7217, 'learning_rate': 0.0004989628420928105, 'epoch': 0.7}

  6%|▌         | 1633/28080 [3:13:22<52:08:21,  7.10s/it]
  6%|▌         | 1634/28080 [3:13:30<52:14:20,  7.11s/it]
                                                         
{'loss': 0.71, 'learning_rate': 0.0004989602165375284, 'epoch': 0.7}

  6%|▌         | 1634/28080 [3:13:30<52:14:20,  7.11s/it]
  6%|▌         | 1635/28080 [3:13:37<52:09:59,  7.10s/it]
                                                         
{'loss': 0.7238, 'learning_rate': 0.0004989575876700874, 'epoch': 0.7}

  6%|▌         | 1635/28080 [3:13:37<52:09:59,  7.10s/it]
  6%|▌         | 1636/28080 [3:13:44<52:14:47,  7.11s/it]
                                                         
{'loss': 0.7059, 'learning_rate': 0.0004989549554905227, 'epoch': 0.7}

  6%|▌         | 1636/28080 [3:13:44<52:14:47,  7.11s/it]
  6%|▌         | 1637/28080 [3:13:51<52:16:15,  7.12s/it]
                                                         
{'loss': 0.6941, 'learning_rate': 0.000498952319998869, 'epoch': 0.7}

  6%|▌         | 1637/28080 [3:13:51<52:16:15,  7.12s/it]
  6%|▌         | 1638/28080 [3:13:58<52:22:50,  7.13s/it]
                                                         
{'loss': 0.6991, 'learning_rate': 0.0004989496811951616, 'epoch': 0.7}

  6%|▌         | 1638/28080 [3:13:58<52:22:50,  7.13s/it]
  6%|▌         | 1639/28080 [3:14:05<52:17:53,  7.12s/it]
                                                         
{'loss': 0.6946, 'learning_rate': 0.0004989470390794355, 'epoch': 0.7}

  6%|▌         | 1639/28080 [3:14:05<52:17:53,  7.12s/it]
  6%|▌         | 1640/28080 [3:14:12<52:20:26,  7.13s/it]
                                                         
{'loss': 0.7168, 'learning_rate': 0.0004989443936517259, 'epoch': 0.7}

  6%|▌         | 1640/28080 [3:14:12<52:20:26,  7.13s/it]
  6%|▌         | 1641/28080 [3:14:19<52:12:30,  7.11s/it]
                                                         
{'loss': 0.7091, 'learning_rate': 0.0004989417449120679, 'epoch': 0.7}

  6%|▌         | 1641/28080 [3:14:19<52:12:30,  7.11s/it]
  6%|▌         | 1642/28080 [3:14:27<52:13:40,  7.11s/it]
                                                         
{'loss': 0.696, 'learning_rate': 0.0004989390928604969, 'epoch': 0.7}

  6%|▌         | 1642/28080 [3:14:27<52:13:40,  7.11s/it]
  6%|▌         | 1643/28080 [3:14:34<52:27:29,  7.14s/it]
                                                         
{'loss': 0.7116, 'learning_rate': 0.000498936437497048, 'epoch': 0.7}

  6%|▌         | 1643/28080 [3:14:34<52:27:29,  7.14s/it]
  6%|▌         | 1644/28080 [3:14:41<52:23:15,  7.13s/it]
                                                         
{'loss': 0.7087, 'learning_rate': 0.0004989337788217566, 'epoch': 0.7}

  6%|▌         | 1644/28080 [3:14:41<52:23:15,  7.13s/it]
  6%|▌         | 1645/28080 [3:14:48<52:29:36,  7.15s/it]
                                                         
{'loss': 0.7204, 'learning_rate': 0.000498931116834658, 'epoch': 0.7}

  6%|▌         | 1645/28080 [3:14:48<52:29:36,  7.15s/it]
  6%|▌         | 1646/28080 [3:14:55<52:34:05,  7.16s/it]
                                                         
{'loss': 0.712, 'learning_rate': 0.000498928451535788, 'epoch': 0.7}

  6%|▌         | 1646/28080 [3:14:55<52:34:05,  7.16s/it]
  6%|▌         | 1647/28080 [3:15:02<52:27:13,  7.14s/it]
                                                         
{'loss': 0.7191, 'learning_rate': 0.0004989257829251815, 'epoch': 0.7}

  6%|▌         | 1647/28080 [3:15:02<52:27:13,  7.14s/it]
  6%|▌         | 1648/28080 [3:15:09<52:08:26,  7.10s/it]
                                                         
{'loss': 0.7095, 'learning_rate': 0.0004989231110028744, 'epoch': 0.7}

  6%|▌         | 1648/28080 [3:15:09<52:08:26,  7.10s/it]
  6%|▌         | 1649/28080 [3:15:16<52:12:50,  7.11s/it]
                                                         
{'loss': 0.6997, 'learning_rate': 0.000498920435768902, 'epoch': 0.7}

  6%|▌         | 1649/28080 [3:15:16<52:12:50,  7.11s/it]
  6%|▌         | 1650/28080 [3:15:24<52:15:19,  7.12s/it]
                                                         
{'loss': 0.7153, 'learning_rate': 0.0004989177572233, 'epoch': 0.7}

  6%|▌         | 1650/28080 [3:15:24<52:15:19,  7.12s/it]
  6%|▌         | 1651/28080 [3:15:31<52:19:45,  7.13s/it]
                                                         
{'loss': 0.7258, 'learning_rate': 0.000498915075366104, 'epoch': 0.71}

  6%|▌         | 1651/28080 [3:15:31<52:19:45,  7.13s/it]
  6%|▌         | 1652/28080 [3:15:38<52:20:11,  7.13s/it]
                                                         
{'loss': 0.7148, 'learning_rate': 0.0004989123901973499, 'epoch': 0.71}

  6%|▌         | 1652/28080 [3:15:38<52:20:11,  7.13s/it]
  6%|▌         | 1653/28080 [3:15:45<52:22:12,  7.13s/it]
                                                         
{'loss': 0.7048, 'learning_rate': 0.0004989097017170731, 'epoch': 0.71}

  6%|▌         | 1653/28080 [3:15:45<52:22:12,  7.13s/it]
  6%|▌         | 1654/28080 [3:15:52<52:26:38,  7.14s/it]
                                                         
{'loss': 0.6677, 'learning_rate': 0.0004989070099253095, 'epoch': 0.71}

  6%|▌         | 1654/28080 [3:15:52<52:26:38,  7.14s/it]
  6%|▌         | 1655/28080 [3:15:59<52:29:04,  7.15s/it]
                                                         
{'loss': 0.6929, 'learning_rate': 0.0004989043148220949, 'epoch': 0.71}

  6%|▌         | 1655/28080 [3:15:59<52:29:04,  7.15s/it]
  6%|▌         | 1656/28080 [3:16:06<52:10:20,  7.11s/it]
                                                         
{'loss': 0.7156, 'learning_rate': 0.0004989016164074654, 'epoch': 0.71}

  6%|▌         | 1656/28080 [3:16:06<52:10:20,  7.11s/it]
  6%|▌         | 1657/28080 [3:16:14<52:15:09,  7.12s/it]
                                                         
{'loss': 0.7136, 'learning_rate': 0.0004988989146814565, 'epoch': 0.71}

  6%|▌         | 1657/28080 [3:16:14<52:15:09,  7.12s/it]
  6%|▌         | 1658/28080 [3:16:21<52:18:12,  7.13s/it]
                                                         
{'loss': 0.7333, 'learning_rate': 0.0004988962096441042, 'epoch': 0.71}

  6%|▌         | 1658/28080 [3:16:21<52:18:12,  7.13s/it]
  6%|▌         | 1659/28080 [3:16:28<52:08:11,  7.10s/it]
                                                         
{'loss': 0.7194, 'learning_rate': 0.0004988935012954448, 'epoch': 0.71}

  6%|▌         | 1659/28080 [3:16:28<52:08:11,  7.10s/it]
  6%|▌         | 1660/28080 [3:16:35<52:11:39,  7.11s/it]
                                                         
{'loss': 0.6961, 'learning_rate': 0.000498890789635514, 'epoch': 0.71}

  6%|▌         | 1660/28080 [3:16:35<52:11:39,  7.11s/it]
  6%|▌         | 1661/28080 [3:16:42<52:00:11,  7.09s/it]
                                                         
{'loss': 0.7137, 'learning_rate': 0.000498888074664348, 'epoch': 0.71}

  6%|▌         | 1661/28080 [3:16:42<52:00:11,  7.09s/it]
  6%|▌         | 1662/28080 [3:16:49<52:01:08,  7.09s/it]
                                                         
{'loss': 0.7034, 'learning_rate': 0.000498885356381983, 'epoch': 0.71}

  6%|▌         | 1662/28080 [3:16:49<52:01:08,  7.09s/it]
  6%|▌         | 1663/28080 [3:16:56<52:02:32,  7.09s/it]
                                                         
{'loss': 0.7034, 'learning_rate': 0.0004988826347884551, 'epoch': 0.71}

  6%|▌         | 1663/28080 [3:16:56<52:02:32,  7.09s/it]
  6%|▌         | 1664/28080 [3:17:03<52:00:34,  7.09s/it]
                                                         
{'loss': 0.7152, 'learning_rate': 0.0004988799098838004, 'epoch': 0.71}

  6%|▌         | 1664/28080 [3:17:03<52:00:34,  7.09s/it]
  6%|▌         | 1665/28080 [3:17:10<51:58:07,  7.08s/it]
                                                         
{'loss': 0.7206, 'learning_rate': 0.0004988771816680554, 'epoch': 0.71}

  6%|▌         | 1665/28080 [3:17:10<51:58:07,  7.08s/it]
  6%|▌         | 1666/28080 [3:17:17<52:00:23,  7.09s/it]
                                                         
{'loss': 0.7043, 'learning_rate': 0.0004988744501412563, 'epoch': 0.71}

  6%|▌         | 1666/28080 [3:17:17<52:00:23,  7.09s/it]
  6%|▌         | 1667/28080 [3:17:24<52:05:20,  7.10s/it]
                                                         
{'loss': 0.7027, 'learning_rate': 0.0004988717153034391, 'epoch': 0.71}

  6%|▌         | 1667/28080 [3:17:24<52:05:20,  7.10s/it]
  6%|▌         | 1668/28080 [3:17:32<52:13:19,  7.12s/it]
                                                         
{'loss': 0.6936, 'learning_rate': 0.0004988689771546407, 'epoch': 0.71}

  6%|▌         | 1668/28080 [3:17:32<52:13:19,  7.12s/it]
  6%|▌         | 1669/28080 [3:17:39<52:24:10,  7.14s/it]
                                                         
{'loss': 0.7261, 'learning_rate': 0.0004988662356948972, 'epoch': 0.71}

  6%|▌         | 1669/28080 [3:17:39<52:24:10,  7.14s/it]
  6%|▌         | 1670/28080 [3:17:46<52:18:50,  7.13s/it]
                                                         
{'loss': 0.6987, 'learning_rate': 0.0004988634909242453, 'epoch': 0.71}

  6%|▌         | 1670/28080 [3:17:46<52:18:50,  7.13s/it]
  6%|▌         | 1671/28080 [3:17:53<52:12:01,  7.12s/it]
                                                         
{'loss': 0.7129, 'learning_rate': 0.0004988607428427213, 'epoch': 0.71}

  6%|▌         | 1671/28080 [3:17:53<52:12:01,  7.12s/it]
  6%|▌         | 1672/28080 [3:18:00<52:15:52,  7.12s/it]
                                                         
{'loss': 0.7189, 'learning_rate': 0.0004988579914503618, 'epoch': 0.71}

  6%|▌         | 1672/28080 [3:18:00<52:15:52,  7.12s/it]
  6%|▌         | 1673/28080 [3:18:07<52:16:38,  7.13s/it]
                                                         
{'loss': 0.7181, 'learning_rate': 0.0004988552367472035, 'epoch': 0.71}

  6%|▌         | 1673/28080 [3:18:07<52:16:38,  7.13s/it]
  6%|▌         | 1674/28080 [3:18:14<52:22:06,  7.14s/it]
                                                         
{'loss': 0.7001, 'learning_rate': 0.0004988524787332831, 'epoch': 0.72}

  6%|▌         | 1674/28080 [3:18:14<52:22:06,  7.14s/it]
  6%|▌         | 1675/28080 [3:18:22<52:26:33,  7.15s/it]
                                                         
{'loss': 0.6985, 'learning_rate': 0.0004988497174086372, 'epoch': 0.72}

  6%|▌         | 1675/28080 [3:18:22<52:26:33,  7.15s/it]
  6%|▌         | 1676/28080 [3:18:29<52:22:37,  7.14s/it]
                                                         
{'loss': 0.689, 'learning_rate': 0.0004988469527733024, 'epoch': 0.72}

  6%|▌         | 1676/28080 [3:18:29<52:22:37,  7.14s/it]
  6%|▌         | 1677/28080 [3:18:36<52:21:54,  7.14s/it]
                                                         
{'loss': 0.6947, 'learning_rate': 0.0004988441848273157, 'epoch': 0.72}

  6%|▌         | 1677/28080 [3:18:36<52:21:54,  7.14s/it]
  6%|▌         | 1678/28080 [3:18:43<52:16:11,  7.13s/it]
                                                         
{'loss': 0.7021, 'learning_rate': 0.0004988414135707138, 'epoch': 0.72}

  6%|▌         | 1678/28080 [3:18:43<52:16:11,  7.13s/it]
  6%|▌         | 1679/28080 [3:18:50<52:02:08,  7.10s/it]
                                                         
{'loss': 0.7116, 'learning_rate': 0.0004988386390035336, 'epoch': 0.72}

  6%|▌         | 1679/28080 [3:18:50<52:02:08,  7.10s/it]
  6%|▌         | 1680/28080 [3:18:57<52:10:24,  7.11s/it]
                                                         
{'loss': 0.669, 'learning_rate': 0.000498835861125812, 'epoch': 0.72}

  6%|▌         | 1680/28080 [3:18:57<52:10:24,  7.11s/it]
  6%|▌         | 1681/28080 [3:19:04<52:07:49,  7.11s/it]
                                                         
{'loss': 0.6843, 'learning_rate': 0.0004988330799375861, 'epoch': 0.72}

  6%|▌         | 1681/28080 [3:19:04<52:07:49,  7.11s/it]
  6%|▌         | 1682/28080 [3:19:11<52:09:29,  7.11s/it]
                                                         
{'loss': 0.6921, 'learning_rate': 0.0004988302954388927, 'epoch': 0.72}

  6%|▌         | 1682/28080 [3:19:11<52:09:29,  7.11s/it]
  6%|▌         | 1683/28080 [3:19:18<52:11:40,  7.12s/it]
                                                         
{'loss': 0.6872, 'learning_rate': 0.0004988275076297689, 'epoch': 0.72}

  6%|▌         | 1683/28080 [3:19:18<52:11:40,  7.12s/it]
  6%|▌         | 1684/28080 [3:19:26<52:16:14,  7.13s/it]
                                                         
{'loss': 0.68, 'learning_rate': 0.0004988247165102519, 'epoch': 0.72}

  6%|▌         | 1684/28080 [3:19:26<52:16:14,  7.13s/it]
  6%|▌         | 1685/28080 [3:19:33<51:56:05,  7.08s/it]
                                                         
{'loss': 0.7056, 'learning_rate': 0.0004988219220803786, 'epoch': 0.72}

  6%|▌         | 1685/28080 [3:19:33<51:56:05,  7.08s/it]
  6%|▌         | 1686/28080 [3:19:40<51:58:29,  7.09s/it]
                                                         
{'loss': 0.6968, 'learning_rate': 0.0004988191243401864, 'epoch': 0.72}

  6%|▌         | 1686/28080 [3:19:40<51:58:29,  7.09s/it]
  6%|▌         | 1687/28080 [3:19:47<51:51:04,  7.07s/it]
                                                         
{'loss': 0.722, 'learning_rate': 0.0004988163232897125, 'epoch': 0.72}

  6%|▌         | 1687/28080 [3:19:47<51:51:04,  7.07s/it]
  6%|▌         | 1688/28080 [3:19:54<51:49:41,  7.07s/it]
                                                         
{'loss': 0.6932, 'learning_rate': 0.000498813518928994, 'epoch': 0.72}

  6%|▌         | 1688/28080 [3:19:54<51:49:41,  7.07s/it]
  6%|▌         | 1689/28080 [3:20:01<51:52:09,  7.08s/it]
                                                         
{'loss': 0.7023, 'learning_rate': 0.0004988107112580684, 'epoch': 0.72}

  6%|▌         | 1689/28080 [3:20:01<51:52:09,  7.08s/it]
  6%|▌         | 1690/28080 [3:20:08<52:25:29,  7.15s/it]
                                                         
{'loss': 0.7136, 'learning_rate': 0.000498807900276973, 'epoch': 0.72}

  6%|▌         | 1690/28080 [3:20:08<52:25:29,  7.15s/it]
  6%|▌         | 1691/28080 [3:20:15<52:21:33,  7.14s/it]
                                                         
{'loss': 0.6959, 'learning_rate': 0.0004988050859857451, 'epoch': 0.72}

  6%|▌         | 1691/28080 [3:20:15<52:21:33,  7.14s/it]
  6%|▌         | 1692/28080 [3:20:22<52:17:40,  7.13s/it]
                                                         
{'loss': 0.7086, 'learning_rate': 0.0004988022683844222, 'epoch': 0.72}

  6%|▌         | 1692/28080 [3:20:22<52:17:40,  7.13s/it]
  6%|▌         | 1693/28080 [3:20:30<52:13:25,  7.12s/it]
                                                         
{'loss': 0.7063, 'learning_rate': 0.0004987994474730418, 'epoch': 0.72}

  6%|▌         | 1693/28080 [3:20:30<52:13:25,  7.12s/it]
  6%|▌         | 1694/28080 [3:20:37<52:10:44,  7.12s/it]
                                                         
{'loss': 0.7179, 'learning_rate': 0.0004987966232516414, 'epoch': 0.72}

  6%|▌         | 1694/28080 [3:20:37<52:10:44,  7.12s/it]
  6%|▌         | 1695/28080 [3:20:44<52:02:29,  7.10s/it]
                                                         
{'loss': 0.7206, 'learning_rate': 0.0004987937957202587, 'epoch': 0.72}

  6%|▌         | 1695/28080 [3:20:44<52:02:29,  7.10s/it]
  6%|▌         | 1696/28080 [3:20:51<52:04:05,  7.10s/it]
                                                         
{'loss': 0.7183, 'learning_rate': 0.0004987909648789311, 'epoch': 0.72}

  6%|▌         | 1696/28080 [3:20:51<52:04:05,  7.10s/it]
  6%|▌         | 1697/28080 [3:20:58<52:08:58,  7.12s/it]
                                                         
{'loss': 0.7467, 'learning_rate': 0.0004987881307276965, 'epoch': 0.72}

  6%|▌         | 1697/28080 [3:20:58<52:08:58,  7.12s/it]
  6%|▌         | 1698/28080 [3:21:05<52:14:02,  7.13s/it]
                                                         
{'loss': 0.7259, 'learning_rate': 0.0004987852932665923, 'epoch': 0.73}

  6%|▌         | 1698/28080 [3:21:05<52:14:02,  7.13s/it]
  6%|▌         | 1699/28080 [3:21:12<52:08:44,  7.12s/it]
                                                         
{'loss': 0.7147, 'learning_rate': 0.0004987824524956565, 'epoch': 0.73}

  6%|▌         | 1699/28080 [3:21:12<52:08:44,  7.12s/it]
  6%|▌         | 1700/28080 [3:21:19<52:13:56,  7.13s/it]
                                                         
{'loss': 0.679, 'learning_rate': 0.0004987796084149269, 'epoch': 0.73}

  6%|▌         | 1700/28080 [3:21:19<52:13:56,  7.13s/it]
  6%|▌         | 1701/28080 [3:21:27<52:14:06,  7.13s/it]
                                                         
{'loss': 0.71, 'learning_rate': 0.0004987767610244412, 'epoch': 0.73}

  6%|▌         | 1701/28080 [3:21:27<52:14:06,  7.13s/it]
  6%|▌         | 1702/28080 [3:21:34<52:20:27,  7.14s/it]
                                                         
{'loss': 0.7238, 'learning_rate': 0.0004987739103242374, 'epoch': 0.73}

  6%|▌         | 1702/28080 [3:21:34<52:20:27,  7.14s/it]
  6%|▌         | 1703/28080 [3:21:41<52:25:30,  7.16s/it]
                                                         
{'loss': 0.7264, 'learning_rate': 0.0004987710563143534, 'epoch': 0.73}

  6%|▌         | 1703/28080 [3:21:41<52:25:30,  7.16s/it]
  6%|▌         | 1704/28080 [3:21:48<52:18:14,  7.14s/it]
                                                         
{'loss': 0.704, 'learning_rate': 0.000498768198994827, 'epoch': 0.73}

  6%|▌         | 1704/28080 [3:21:48<52:18:14,  7.14s/it]
  6%|▌         | 1705/28080 [3:21:55<52:21:40,  7.15s/it]
                                                         
{'loss': 0.6986, 'learning_rate': 0.0004987653383656964, 'epoch': 0.73}

  6%|▌         | 1705/28080 [3:21:55<52:21:40,  7.15s/it]
  6%|▌         | 1706/28080 [3:22:02<52:14:24,  7.13s/it]
                                                         
{'loss': 0.7071, 'learning_rate': 0.0004987624744269997, 'epoch': 0.73}

  6%|▌         | 1706/28080 [3:22:02<52:14:24,  7.13s/it]
  6%|▌         | 1707/28080 [3:22:09<52:11:21,  7.12s/it]
                                                         
{'loss': 0.6976, 'learning_rate': 0.0004987596071787748, 'epoch': 0.73}

  6%|▌         | 1707/28080 [3:22:09<52:11:21,  7.12s/it]
  6%|▌         | 1708/28080 [3:22:17<52:16:39,  7.14s/it]
                                                         
{'loss': 0.6795, 'learning_rate': 0.00049875673662106, 'epoch': 0.73}

  6%|▌         | 1708/28080 [3:22:17<52:16:39,  7.14s/it]
  6%|▌         | 1709/28080 [3:22:24<52:08:19,  7.12s/it]
                                                         
{'loss': 0.7236, 'learning_rate': 0.0004987538627538935, 'epoch': 0.73}

  6%|▌         | 1709/28080 [3:22:24<52:08:19,  7.12s/it]
  6%|▌         | 1710/28080 [3:22:31<51:57:00,  7.09s/it]
                                                         
{'loss': 0.7274, 'learning_rate': 0.0004987509855773134, 'epoch': 0.73}

  6%|▌         | 1710/28080 [3:22:31<51:57:00,  7.09s/it]
  6%|▌         | 1711/28080 [3:22:38<51:43:40,  7.06s/it]
                                                         
{'loss': 0.6987, 'learning_rate': 0.0004987481050913581, 'epoch': 0.73}

  6%|▌         | 1711/28080 [3:22:38<51:43:40,  7.06s/it]
  6%|▌         | 1712/28080 [3:22:45<51:56:58,  7.09s/it]
                                                         
{'loss': 0.7207, 'learning_rate': 0.0004987452212960659, 'epoch': 0.73}

  6%|▌         | 1712/28080 [3:22:45<51:56:58,  7.09s/it]
  6%|▌         | 1713/28080 [3:22:52<51:50:22,  7.08s/it]
                                                         
{'loss': 0.6933, 'learning_rate': 0.0004987423341914751, 'epoch': 0.73}

  6%|▌         | 1713/28080 [3:22:52<51:50:22,  7.08s/it]
  6%|▌         | 1714/28080 [3:22:59<52:02:04,  7.10s/it]
                                                         
{'loss': 0.7039, 'learning_rate': 0.0004987394437776241, 'epoch': 0.73}

  6%|▌         | 1714/28080 [3:22:59<52:02:04,  7.10s/it]
  6%|▌         | 1715/28080 [3:23:06<52:15:36,  7.14s/it]
                                                         
{'loss': 0.7081, 'learning_rate': 0.0004987365500545516, 'epoch': 0.73}

  6%|▌         | 1715/28080 [3:23:06<52:15:36,  7.14s/it]
  6%|▌         | 1716/28080 [3:23:13<52:13:42,  7.13s/it]
                                                         
{'loss': 0.6953, 'learning_rate': 0.0004987336530222958, 'epoch': 0.73}

  6%|▌         | 1716/28080 [3:23:13<52:13:42,  7.13s/it]
  6%|▌         | 1717/28080 [3:23:20<52:14:35,  7.13s/it]
                                                         
{'loss': 0.7179, 'learning_rate': 0.0004987307526808953, 'epoch': 0.73}

  6%|▌         | 1717/28080 [3:23:20<52:14:35,  7.13s/it]
  6%|▌         | 1718/28080 [3:23:28<52:08:54,  7.12s/it]
                                                         
{'loss': 0.7187, 'learning_rate': 0.0004987278490303888, 'epoch': 0.73}

  6%|▌         | 1718/28080 [3:23:28<52:08:54,  7.12s/it]
  6%|▌         | 1719/28080 [3:23:35<52:29:41,  7.17s/it]
                                                         
{'loss': 0.6885, 'learning_rate': 0.0004987249420708148, 'epoch': 0.73}

  6%|▌         | 1719/28080 [3:23:35<52:29:41,  7.17s/it]
  6%|▌         | 1720/28080 [3:23:42<52:26:06,  7.16s/it]
                                                         
{'loss': 0.6892, 'learning_rate': 0.0004987220318022121, 'epoch': 0.73}

  6%|▌         | 1720/28080 [3:23:42<52:26:06,  7.16s/it]
  6%|▌         | 1721/28080 [3:23:49<52:24:11,  7.16s/it]
                                                         
{'loss': 0.6867, 'learning_rate': 0.0004987191182246193, 'epoch': 0.74}

  6%|▌         | 1721/28080 [3:23:49<52:24:11,  7.16s/it]
  6%|▌         | 1722/28080 [3:23:56<52:07:31,  7.12s/it]
                                                         
{'loss': 0.7096, 'learning_rate': 0.0004987162013380753, 'epoch': 0.74}

  6%|▌         | 1722/28080 [3:23:56<52:07:31,  7.12s/it]
  6%|▌         | 1723/28080 [3:24:03<51:54:54,  7.09s/it]
                                                         
{'loss': 0.7109, 'learning_rate': 0.0004987132811426189, 'epoch': 0.74}

  6%|▌         | 1723/28080 [3:24:03<51:54:54,  7.09s/it]
  6%|▌         | 1724/28080 [3:24:10<51:59:37,  7.10s/it]
                                                         
{'loss': 0.7012, 'learning_rate': 0.0004987103576382886, 'epoch': 0.74}

  6%|▌         | 1724/28080 [3:24:10<51:59:37,  7.10s/it]
  6%|▌         | 1725/28080 [3:24:17<52:08:05,  7.12s/it]
                                                         
{'loss': 0.7124, 'learning_rate': 0.0004987074308251238, 'epoch': 0.74}

  6%|▌         | 1725/28080 [3:24:17<52:08:05,  7.12s/it]
  6%|▌         | 1726/28080 [3:24:25<52:09:40,  7.13s/it]
                                                         
{'loss': 0.7171, 'learning_rate': 0.0004987045007031632, 'epoch': 0.74}

  6%|▌         | 1726/28080 [3:24:25<52:09:40,  7.13s/it]
  6%|▌         | 1727/28080 [3:24:32<52:20:46,  7.15s/it]
                                                         
{'loss': 0.7153, 'learning_rate': 0.0004987015672724458, 'epoch': 0.74}

  6%|▌         | 1727/28080 [3:24:32<52:20:46,  7.15s/it]
  6%|▌         | 1728/28080 [3:24:39<52:15:02,  7.14s/it]
                                                         
{'loss': 0.7146, 'learning_rate': 0.0004986986305330105, 'epoch': 0.74}

  6%|▌         | 1728/28080 [3:24:39<52:15:02,  7.14s/it]
  6%|▌         | 1729/28080 [3:24:46<52:25:43,  7.16s/it]
                                                         
{'loss': 0.7171, 'learning_rate': 0.0004986956904848965, 'epoch': 0.74}

  6%|▌         | 1729/28080 [3:24:46<52:25:43,  7.16s/it]
  6%|▌         | 1730/28080 [3:24:53<52:23:53,  7.16s/it]
                                                         
{'loss': 0.7186, 'learning_rate': 0.000498692747128143, 'epoch': 0.74}

  6%|▌         | 1730/28080 [3:24:53<52:23:53,  7.16s/it]
  6%|▌         | 1731/28080 [3:25:00<52:24:04,  7.16s/it]
                                                         
{'loss': 0.6843, 'learning_rate': 0.000498689800462789, 'epoch': 0.74}

  6%|▌         | 1731/28080 [3:25:00<52:24:04,  7.16s/it]
  6%|▌         | 1732/28080 [3:25:08<52:10:53,  7.13s/it]
                                                         
{'loss': 0.6984, 'learning_rate': 0.0004986868504888739, 'epoch': 0.74}

  6%|▌         | 1732/28080 [3:25:08<52:10:53,  7.13s/it]
  6%|▌         | 1733/28080 [3:25:15<52:00:52,  7.11s/it]
                                                         
{'loss': 0.7128, 'learning_rate': 0.0004986838972064366, 'epoch': 0.74}

  6%|▌         | 1733/28080 [3:25:15<52:00:52,  7.11s/it]
  6%|▌         | 1734/28080 [3:25:22<52:02:22,  7.11s/it]
                                                         
{'loss': 0.6999, 'learning_rate': 0.0004986809406155167, 'epoch': 0.74}

  6%|▌         | 1734/28080 [3:25:22<52:02:22,  7.11s/it]
  6%|▌         | 1735/28080 [3:25:29<51:54:58,  7.09s/it]
                                                         
{'loss': 0.7368, 'learning_rate': 0.0004986779807161535, 'epoch': 0.74}

  6%|▌         | 1735/28080 [3:25:29<51:54:58,  7.09s/it]
  6%|▌         | 1736/28080 [3:25:36<51:50:06,  7.08s/it]
                                                         
{'loss': 0.7086, 'learning_rate': 0.0004986750175083862, 'epoch': 0.74}

  6%|▌         | 1736/28080 [3:25:36<51:50:06,  7.08s/it]
  6%|▌         | 1737/28080 [3:25:43<51:55:15,  7.10s/it]
                                                         
{'loss': 0.695, 'learning_rate': 0.0004986720509922544, 'epoch': 0.74}

  6%|▌         | 1737/28080 [3:25:43<51:55:15,  7.10s/it]
  6%|▌         | 1738/28080 [3:25:50<51:56:47,  7.10s/it]
                                                         
{'loss': 0.7154, 'learning_rate': 0.0004986690811677974, 'epoch': 0.74}

  6%|▌         | 1738/28080 [3:25:50<51:56:47,  7.10s/it]
  6%|▌         | 1739/28080 [3:25:57<52:04:32,  7.12s/it]
                                                         
{'loss': 0.7044, 'learning_rate': 0.000498666108035055, 'epoch': 0.74}

  6%|▌         | 1739/28080 [3:25:57<52:04:32,  7.12s/it]
  6%|▌         | 1740/28080 [3:26:04<52:12:45,  7.14s/it]
                                                         
{'loss': 0.7182, 'learning_rate': 0.0004986631315940664, 'epoch': 0.74}

  6%|▌         | 1740/28080 [3:26:04<52:12:45,  7.14s/it]
  6%|▌         | 1741/28080 [3:26:12<52:12:39,  7.14s/it]
                                                         
{'loss': 0.7067, 'learning_rate': 0.0004986601518448715, 'epoch': 0.74}

  6%|▌         | 1741/28080 [3:26:12<52:12:39,  7.14s/it]
  6%|▌         | 1742/28080 [3:26:19<51:59:55,  7.11s/it]
                                                         
{'loss': 0.7274, 'learning_rate': 0.0004986571687875097, 'epoch': 0.74}

  6%|▌         | 1742/28080 [3:26:19<51:59:55,  7.11s/it]
  6%|▌         | 1743/28080 [3:26:26<51:54:11,  7.09s/it]
                                                         
{'loss': 0.7244, 'learning_rate': 0.0004986541824220208, 'epoch': 0.74}

  6%|▌         | 1743/28080 [3:26:26<51:54:11,  7.09s/it]
  6%|▌         | 1744/28080 [3:26:33<51:48:54,  7.08s/it]
                                                         
{'loss': 0.7097, 'learning_rate': 0.0004986511927484446, 'epoch': 0.75}

  6%|▌         | 1744/28080 [3:26:33<51:48:54,  7.08s/it]
  6%|▌         | 1745/28080 [3:26:40<51:49:03,  7.08s/it]
                                                         
{'loss': 0.7178, 'learning_rate': 0.0004986481997668208, 'epoch': 0.75}

  6%|▌         | 1745/28080 [3:26:40<51:49:03,  7.08s/it]
  6%|▌         | 1746/28080 [3:26:47<51:59:02,  7.11s/it]
                                                         
{'loss': 0.7042, 'learning_rate': 0.0004986452034771891, 'epoch': 0.75}

  6%|▌         | 1746/28080 [3:26:47<51:59:02,  7.11s/it]
  6%|▌         | 1747/28080 [3:26:54<51:51:48,  7.09s/it]
                                                         
{'loss': 0.697, 'learning_rate': 0.0004986422038795895, 'epoch': 0.75}

  6%|▌         | 1747/28080 [3:26:54<51:51:48,  7.09s/it]
  6%|▌         | 1748/28080 [3:27:01<51:55:34,  7.10s/it]
                                                         
{'loss': 0.7064, 'learning_rate': 0.000498639200974062, 'epoch': 0.75}

  6%|▌         | 1748/28080 [3:27:01<51:55:34,  7.10s/it]
  6%|▌         | 1749/28080 [3:27:08<52:05:51,  7.12s/it]
                                                         
{'loss': 0.6955, 'learning_rate': 0.0004986361947606464, 'epoch': 0.75}

  6%|▌         | 1749/28080 [3:27:08<52:05:51,  7.12s/it]
  6%|▌         | 1750/28080 [3:27:15<51:57:40,  7.10s/it]
                                                         
{'loss': 0.7053, 'learning_rate': 0.0004986331852393827, 'epoch': 0.75}

  6%|▌         | 1750/28080 [3:27:15<51:57:40,  7.10s/it]
  6%|▌         | 1751/28080 [3:27:23<52:10:56,  7.13s/it]
                                                         
{'loss': 0.7055, 'learning_rate': 0.000498630172410311, 'epoch': 0.75}

  6%|▌         | 1751/28080 [3:27:23<52:10:56,  7.13s/it]
  6%|▌         | 1752/28080 [3:27:30<51:58:29,  7.11s/it]
                                                         
{'loss': 0.7275, 'learning_rate': 0.0004986271562734713, 'epoch': 0.75}

  6%|▌         | 1752/28080 [3:27:30<51:58:29,  7.11s/it]
  6%|▌         | 1753/28080 [3:27:37<51:57:31,  7.10s/it]
                                                         
{'loss': 0.7042, 'learning_rate': 0.0004986241368289038, 'epoch': 0.75}

  6%|▌         | 1753/28080 [3:27:37<51:57:31,  7.10s/it]
  6%|▌         | 1754/28080 [3:27:44<51:50:03,  7.09s/it]
                                                         
{'loss': 0.7116, 'learning_rate': 0.0004986211140766487, 'epoch': 0.75}

  6%|▌         | 1754/28080 [3:27:44<51:50:03,  7.09s/it]
  6%|▋         | 1755/28080 [3:27:51<51:43:44,  7.07s/it]
                                                         
{'loss': 0.7343, 'learning_rate': 0.0004986180880167462, 'epoch': 0.75}

  6%|▋         | 1755/28080 [3:27:51<51:43:44,  7.07s/it]
  6%|▋         | 1756/28080 [3:27:58<51:57:23,  7.11s/it]
                                                         
{'loss': 0.6981, 'learning_rate': 0.0004986150586492364, 'epoch': 0.75}

  6%|▋         | 1756/28080 [3:27:58<51:57:23,  7.11s/it]
  6%|▋         | 1757/28080 [3:28:05<51:48:07,  7.08s/it]
                                                         
{'loss': 0.7197, 'learning_rate': 0.0004986120259741597, 'epoch': 0.75}

  6%|▋         | 1757/28080 [3:28:05<51:48:07,  7.08s/it]
  6%|▋         | 1758/28080 [3:28:12<51:53:49,  7.10s/it]
                                                         
{'loss': 0.7135, 'learning_rate': 0.0004986089899915566, 'epoch': 0.75}

  6%|▋         | 1758/28080 [3:28:12<51:53:49,  7.10s/it]
  6%|▋         | 1759/28080 [3:28:19<52:03:25,  7.12s/it]
                                                         
{'loss': 0.6962, 'learning_rate': 0.0004986059507014673, 'epoch': 0.75}

  6%|▋         | 1759/28080 [3:28:19<52:03:25,  7.12s/it]
  6%|▋         | 1760/28080 [3:28:26<51:52:13,  7.09s/it]
                                                         
{'loss': 0.7194, 'learning_rate': 0.0004986029081039323, 'epoch': 0.75}

  6%|▋         | 1760/28080 [3:28:26<51:52:13,  7.09s/it]
  6%|▋         | 1761/28080 [3:28:33<51:47:32,  7.08s/it]
                                                         
{'loss': 0.6913, 'learning_rate': 0.0004985998621989921, 'epoch': 0.75}

  6%|▋         | 1761/28080 [3:28:33<51:47:32,  7.08s/it]
  6%|▋         | 1762/28080 [3:28:41<51:57:51,  7.11s/it]
                                                         
{'loss': 0.705, 'learning_rate': 0.0004985968129866872, 'epoch': 0.75}

  6%|▋         | 1762/28080 [3:28:41<51:57:51,  7.11s/it]
  6%|▋         | 1763/28080 [3:28:48<51:58:30,  7.11s/it]
                                                         
{'loss': 0.6933, 'learning_rate': 0.0004985937604670582, 'epoch': 0.75}

  6%|▋         | 1763/28080 [3:28:48<51:58:30,  7.11s/it]
  6%|▋         | 1764/28080 [3:28:55<51:48:46,  7.09s/it]
                                                         
{'loss': 0.7156, 'learning_rate': 0.0004985907046401456, 'epoch': 0.75}

  6%|▋         | 1764/28080 [3:28:55<51:48:46,  7.09s/it]
  6%|▋         | 1765/28080 [3:29:02<51:57:32,  7.11s/it]
                                                         
{'loss': 0.7136, 'learning_rate': 0.0004985876455059902, 'epoch': 0.75}

  6%|▋         | 1765/28080 [3:29:02<51:57:32,  7.11s/it]
  6%|▋         | 1766/28080 [3:29:09<52:02:17,  7.12s/it]
                                                         
{'loss': 0.7235, 'learning_rate': 0.0004985845830646326, 'epoch': 0.75}

  6%|▋         | 1766/28080 [3:29:09<52:02:17,  7.12s/it]
  6%|▋         | 1767/28080 [3:29:16<52:02:38,  7.12s/it]
                                                         
{'loss': 0.6978, 'learning_rate': 0.0004985815173161136, 'epoch': 0.75}

  6%|▋         | 1767/28080 [3:29:16<52:02:38,  7.12s/it]
  6%|▋         | 1768/28080 [3:29:23<51:46:28,  7.08s/it]
                                                         
{'loss': 0.7067, 'learning_rate': 0.0004985784482604739, 'epoch': 0.76}

  6%|▋         | 1768/28080 [3:29:23<51:46:28,  7.08s/it]
  6%|▋         | 1769/28080 [3:29:30<51:49:04,  7.09s/it]
                                                         
{'loss': 0.7154, 'learning_rate': 0.0004985753758977545, 'epoch': 0.76}

  6%|▋         | 1769/28080 [3:29:30<51:49:04,  7.09s/it]
  6%|▋         | 1770/28080 [3:29:37<51:44:39,  7.08s/it]
                                                         
{'loss': 0.7017, 'learning_rate': 0.0004985723002279961, 'epoch': 0.76}

  6%|▋         | 1770/28080 [3:29:37<51:44:39,  7.08s/it]
  6%|▋         | 1771/28080 [3:29:44<51:24:05,  7.03s/it]
                                                         
{'loss': 0.7369, 'learning_rate': 0.0004985692212512396, 'epoch': 0.76}

  6%|▋         | 1771/28080 [3:29:44<51:24:05,  7.03s/it]
  6%|▋         | 1772/28080 [3:29:51<51:24:30,  7.03s/it]
                                                         
{'loss': 0.6981, 'learning_rate': 0.0004985661389675262, 'epoch': 0.76}

  6%|▋         | 1772/28080 [3:29:51<51:24:30,  7.03s/it]
  6%|▋         | 1773/28080 [3:29:58<51:36:45,  7.06s/it]
                                                         
{'loss': 0.7196, 'learning_rate': 0.0004985630533768966, 'epoch': 0.76}

  6%|▋         | 1773/28080 [3:29:58<51:36:45,  7.06s/it]
  6%|▋         | 1774/28080 [3:30:06<51:48:25,  7.09s/it]
                                                         
{'loss': 0.7112, 'learning_rate': 0.000498559964479392, 'epoch': 0.76}

  6%|▋         | 1774/28080 [3:30:06<51:48:25,  7.09s/it]
  6%|▋         | 1775/28080 [3:30:13<51:44:00,  7.08s/it]
                                                         
{'loss': 0.7186, 'learning_rate': 0.0004985568722750537, 'epoch': 0.76}

  6%|▋         | 1775/28080 [3:30:13<51:44:00,  7.08s/it]
  6%|▋         | 1776/28080 [3:30:20<51:29:05,  7.05s/it]
                                                         
{'loss': 0.7278, 'learning_rate': 0.0004985537767639225, 'epoch': 0.76}

  6%|▋         | 1776/28080 [3:30:20<51:29:05,  7.05s/it]
  6%|▋         | 1777/28080 [3:30:27<51:38:37,  7.07s/it]
                                                         
{'loss': 0.7002, 'learning_rate': 0.0004985506779460396, 'epoch': 0.76}

  6%|▋         | 1777/28080 [3:30:27<51:38:37,  7.07s/it]
  6%|▋         | 1778/28080 [3:30:34<51:57:25,  7.11s/it]
                                                         
{'loss': 0.692, 'learning_rate': 0.0004985475758214465, 'epoch': 0.76}

  6%|▋         | 1778/28080 [3:30:34<51:57:25,  7.11s/it]
  6%|▋         | 1779/28080 [3:30:41<51:58:55,  7.12s/it]
                                                         
{'loss': 0.6993, 'learning_rate': 0.0004985444703901843, 'epoch': 0.76}

  6%|▋         | 1779/28080 [3:30:41<51:58:55,  7.12s/it]
  6%|▋         | 1780/28080 [3:30:48<52:05:47,  7.13s/it]
                                                         
{'loss': 0.7176, 'learning_rate': 0.0004985413616522943, 'epoch': 0.76}

  6%|▋         | 1780/28080 [3:30:48<52:05:47,  7.13s/it]
  6%|▋         | 1781/28080 [3:30:55<52:05:13,  7.13s/it]
                                                         
{'loss': 0.7111, 'learning_rate': 0.0004985382496078179, 'epoch': 0.76}

  6%|▋         | 1781/28080 [3:30:55<52:05:13,  7.13s/it]
  6%|▋         | 1782/28080 [3:31:02<52:09:59,  7.14s/it]
                                                         
{'loss': 0.6942, 'learning_rate': 0.0004985351342567966, 'epoch': 0.76}

  6%|▋         | 1782/28080 [3:31:02<52:09:59,  7.14s/it]
  6%|▋         | 1783/28080 [3:31:10<52:14:55,  7.15s/it]
                                                         
{'loss': 0.6931, 'learning_rate': 0.0004985320155992715, 'epoch': 0.76}

  6%|▋         | 1783/28080 [3:31:10<52:14:55,  7.15s/it]
  6%|▋         | 1784/28080 [3:31:17<52:15:34,  7.15s/it]
                                                         
{'loss': 0.7002, 'learning_rate': 0.0004985288936352845, 'epoch': 0.76}

  6%|▋         | 1784/28080 [3:31:17<52:15:34,  7.15s/it]
  6%|▋         | 1785/28080 [3:31:24<52:02:13,  7.12s/it]
                                                         
{'loss': 0.7307, 'learning_rate': 0.0004985257683648769, 'epoch': 0.76}

  6%|▋         | 1785/28080 [3:31:24<52:02:13,  7.12s/it]
  6%|▋         | 1786/28080 [3:31:31<51:47:58,  7.09s/it]
                                                         
{'loss': 0.7239, 'learning_rate': 0.0004985226397880904, 'epoch': 0.76}

  6%|▋         | 1786/28080 [3:31:31<51:47:58,  7.09s/it]
  6%|▋         | 1787/28080 [3:31:38<51:46:17,  7.09s/it]
                                                         
{'loss': 0.7373, 'learning_rate': 0.0004985195079049666, 'epoch': 0.76}

  6%|▋         | 1787/28080 [3:31:38<51:46:17,  7.09s/it]
  6%|▋         | 1788/28080 [3:31:45<51:49:25,  7.10s/it]
                                                         
{'loss': 0.7216, 'learning_rate': 0.000498516372715547, 'epoch': 0.76}

  6%|▋         | 1788/28080 [3:31:45<51:49:25,  7.10s/it]
  6%|▋         | 1789/28080 [3:31:52<51:57:44,  7.12s/it]
                                                         
{'loss': 0.6963, 'learning_rate': 0.0004985132342198734, 'epoch': 0.76}

  6%|▋         | 1789/28080 [3:31:52<51:57:44,  7.12s/it]
  6%|▋         | 1790/28080 [3:31:59<51:47:39,  7.09s/it]
                                                         
{'loss': 0.7055, 'learning_rate': 0.0004985100924179878, 'epoch': 0.76}

  6%|▋         | 1790/28080 [3:31:59<51:47:39,  7.09s/it]
  6%|▋         | 1791/28080 [3:32:06<51:56:56,  7.11s/it]
                                                         
{'loss': 0.6886, 'learning_rate': 0.0004985069473099317, 'epoch': 0.77}

  6%|▋         | 1791/28080 [3:32:06<51:56:56,  7.11s/it]
  6%|▋         | 1792/28080 [3:32:14<51:59:06,  7.12s/it]
                                                         
{'loss': 0.6913, 'learning_rate': 0.000498503798895747, 'epoch': 0.77}

  6%|▋         | 1792/28080 [3:32:14<51:59:06,  7.12s/it]
  6%|▋         | 1793/28080 [3:32:21<51:51:15,  7.10s/it]
                                                         
{'loss': 0.6985, 'learning_rate': 0.0004985006471754757, 'epoch': 0.77}

  6%|▋         | 1793/28080 [3:32:21<51:51:15,  7.10s/it]
  6%|▋         | 1794/28080 [3:32:28<51:43:02,  7.08s/it]
                                                         
{'loss': 0.7014, 'learning_rate': 0.0004984974921491596, 'epoch': 0.77}

  6%|▋         | 1794/28080 [3:32:28<51:43:02,  7.08s/it]
  6%|▋         | 1795/28080 [3:32:35<51:48:50,  7.10s/it]
                                                         
{'loss': 0.6885, 'learning_rate': 0.0004984943338168407, 'epoch': 0.77}

  6%|▋         | 1795/28080 [3:32:35<51:48:50,  7.10s/it]
  6%|▋         | 1796/28080 [3:32:42<51:58:16,  7.12s/it]
                                                         
{'loss': 0.6865, 'learning_rate': 0.0004984911721785611, 'epoch': 0.77}

  6%|▋         | 1796/28080 [3:32:42<51:58:16,  7.12s/it]
  6%|▋         | 1797/28080 [3:32:49<51:54:16,  7.11s/it]
                                                         
{'loss': 0.7057, 'learning_rate': 0.0004984880072343628, 'epoch': 0.77}

  6%|▋         | 1797/28080 [3:32:49<51:54:16,  7.11s/it]
  6%|▋         | 1798/28080 [3:32:56<51:56:30,  7.11s/it]
                                                         
{'loss': 0.713, 'learning_rate': 0.0004984848389842879, 'epoch': 0.77}

  6%|▋         | 1798/28080 [3:32:56<51:56:30,  7.11s/it]
  6%|▋         | 1799/28080 [3:33:03<52:00:26,  7.12s/it]
                                                         
{'loss': 0.7161, 'learning_rate': 0.0004984816674283786, 'epoch': 0.77}

  6%|▋         | 1799/28080 [3:33:03<52:00:26,  7.12s/it]
  6%|▋         | 1800/28080 [3:33:10<51:47:43,  7.10s/it]
                                                         
{'loss': 0.7213, 'learning_rate': 0.000498478492566677, 'epoch': 0.77}

  6%|▋         | 1800/28080 [3:33:10<51:47:43,  7.10s/it]
  6%|▋         | 1801/28080 [3:33:17<51:54:52,  7.11s/it]
                                                         
{'loss': 0.7164, 'learning_rate': 0.0004984753143992255, 'epoch': 0.77}

  6%|▋         | 1801/28080 [3:33:17<51:54:52,  7.11s/it]
  6%|▋         | 1802/28080 [3:33:25<52:02:22,  7.13s/it]
                                                         
{'loss': 0.7179, 'learning_rate': 0.0004984721329260661, 'epoch': 0.77}

  6%|▋         | 1802/28080 [3:33:25<52:02:22,  7.13s/it]
  6%|▋         | 1803/28080 [3:33:32<51:57:50,  7.12s/it]
                                                         
{'loss': 0.697, 'learning_rate': 0.0004984689481472415, 'epoch': 0.77}

  6%|▋         | 1803/28080 [3:33:32<51:57:50,  7.12s/it]
  6%|▋         | 1804/28080 [3:33:39<51:54:38,  7.11s/it]
                                                         
{'loss': 0.6943, 'learning_rate': 0.0004984657600627938, 'epoch': 0.77}

  6%|▋         | 1804/28080 [3:33:39<51:54:38,  7.11s/it]
  6%|▋         | 1805/28080 [3:33:46<51:49:11,  7.10s/it]
                                                         
{'loss': 0.7052, 'learning_rate': 0.0004984625686727654, 'epoch': 0.77}

  6%|▋         | 1805/28080 [3:33:46<51:49:11,  7.10s/it]
  6%|▋         | 1806/28080 [3:33:53<51:54:18,  7.11s/it]
                                                         
{'loss': 0.6873, 'learning_rate': 0.000498459373977199, 'epoch': 0.77}

  6%|▋         | 1806/28080 [3:33:53<51:54:18,  7.11s/it]
  6%|▋         | 1807/28080 [3:34:00<51:59:33,  7.12s/it]
                                                         
{'loss': 0.6936, 'learning_rate': 0.0004984561759761368, 'epoch': 0.77}

  6%|▋         | 1807/28080 [3:34:00<51:59:33,  7.12s/it]
  6%|▋         | 1808/28080 [3:34:07<51:53:07,  7.11s/it]
                                                         
{'loss': 0.6903, 'learning_rate': 0.0004984529746696216, 'epoch': 0.77}

  6%|▋         | 1808/28080 [3:34:07<51:53:07,  7.11s/it]
  6%|▋         | 1809/28080 [3:34:14<51:46:28,  7.09s/it]
                                                         
{'loss': 0.6972, 'learning_rate': 0.0004984497700576959, 'epoch': 0.77}

  6%|▋         | 1809/28080 [3:34:14<51:46:28,  7.09s/it]
  6%|▋         | 1810/28080 [3:34:21<51:47:04,  7.10s/it]
                                                         
{'loss': 0.683, 'learning_rate': 0.0004984465621404022, 'epoch': 0.77}

  6%|▋         | 1810/28080 [3:34:21<51:47:04,  7.10s/it]
  6%|▋         | 1811/28080 [3:34:29<51:45:59,  7.09s/it]
                                                         
{'loss': 0.7152, 'learning_rate': 0.0004984433509177833, 'epoch': 0.77}

  6%|▋         | 1811/28080 [3:34:29<51:45:59,  7.09s/it]
  6%|▋         | 1812/28080 [3:34:36<51:44:31,  7.09s/it]
                                                         
{'loss': 0.6816, 'learning_rate': 0.0004984401363898821, 'epoch': 0.77}

  6%|▋         | 1812/28080 [3:34:36<51:44:31,  7.09s/it]
  6%|▋         | 1813/28080 [3:34:43<51:44:58,  7.09s/it]
                                                         
{'loss': 0.7055, 'learning_rate': 0.0004984369185567411, 'epoch': 0.77}

  6%|▋         | 1813/28080 [3:34:43<51:44:58,  7.09s/it]
  6%|▋         | 1814/28080 [3:34:50<51:47:18,  7.10s/it]
                                                         
{'loss': 0.69, 'learning_rate': 0.0004984336974184031, 'epoch': 0.77}

  6%|▋         | 1814/28080 [3:34:50<51:47:18,  7.10s/it]
  6%|▋         | 1815/28080 [3:34:57<51:58:03,  7.12s/it]
                                                         
{'loss': 0.7056, 'learning_rate': 0.0004984304729749112, 'epoch': 0.78}

  6%|▋         | 1815/28080 [3:34:57<51:58:03,  7.12s/it]
  6%|▋         | 1816/28080 [3:35:04<51:48:58,  7.10s/it]
                                                         
{'loss': 0.7013, 'learning_rate': 0.0004984272452263081, 'epoch': 0.78}

  6%|▋         | 1816/28080 [3:35:04<51:48:58,  7.10s/it]
  6%|▋         | 1817/28080 [3:35:11<51:45:26,  7.09s/it]
                                                         
{'loss': 0.7201, 'learning_rate': 0.0004984240141726367, 'epoch': 0.78}

  6%|▋         | 1817/28080 [3:35:11<51:45:26,  7.09s/it]
  6%|▋         | 1818/28080 [3:35:18<51:48:34,  7.10s/it]
                                                         
{'loss': 0.7071, 'learning_rate': 0.0004984207798139402, 'epoch': 0.78}

  6%|▋         | 1818/28080 [3:35:18<51:48:34,  7.10s/it]
  6%|▋         | 1819/28080 [3:35:25<51:45:21,  7.10s/it]
                                                         
{'loss': 0.7173, 'learning_rate': 0.0004984175421502614, 'epoch': 0.78}

  6%|▋         | 1819/28080 [3:35:25<51:45:21,  7.10s/it]
  6%|▋         | 1820/28080 [3:35:32<51:49:37,  7.11s/it]
                                                         
{'loss': 0.7274, 'learning_rate': 0.0004984143011816435, 'epoch': 0.78}

  6%|▋         | 1820/28080 [3:35:32<51:49:37,  7.11s/it]
  6%|▋         | 1821/28080 [3:35:40<51:52:15,  7.11s/it]
                                                         
{'loss': 0.7023, 'learning_rate': 0.0004984110569081297, 'epoch': 0.78}

  6%|▋         | 1821/28080 [3:35:40<51:52:15,  7.11s/it]
  6%|▋         | 1822/28080 [3:35:47<51:45:43,  7.10s/it]
                                                         
{'loss': 0.6974, 'learning_rate': 0.000498407809329763, 'epoch': 0.78}

  6%|▋         | 1822/28080 [3:35:47<51:45:43,  7.10s/it]
  6%|▋         | 1823/28080 [3:35:54<51:40:23,  7.08s/it]
                                                         
{'loss': 0.729, 'learning_rate': 0.0004984045584465866, 'epoch': 0.78}

  6%|▋         | 1823/28080 [3:35:54<51:40:23,  7.08s/it]
  6%|▋         | 1824/28080 [3:36:01<51:28:49,  7.06s/it]
                                                         
{'loss': 0.7044, 'learning_rate': 0.000498401304258644, 'epoch': 0.78}

  6%|▋         | 1824/28080 [3:36:01<51:28:49,  7.06s/it]
  6%|▋         | 1825/28080 [3:36:08<51:24:49,  7.05s/it]
                                                         
{'loss': 0.6903, 'learning_rate': 0.0004983980467659781, 'epoch': 0.78}

  6%|▋         | 1825/28080 [3:36:08<51:24:49,  7.05s/it]
  7%|▋         | 1826/28080 [3:36:15<51:27:02,  7.06s/it]
                                                         
{'loss': 0.7194, 'learning_rate': 0.0004983947859686325, 'epoch': 0.78}

  7%|▋         | 1826/28080 [3:36:15<51:27:02,  7.06s/it]
  7%|▋         | 1827/28080 [3:36:22<51:21:22,  7.04s/it]
                                                         
{'loss': 0.7063, 'learning_rate': 0.0004983915218666506, 'epoch': 0.78}

  7%|▋         | 1827/28080 [3:36:22<51:21:22,  7.04s/it]
  7%|▋         | 1828/28080 [3:36:29<51:27:05,  7.06s/it]
                                                         
{'loss': 0.7007, 'learning_rate': 0.0004983882544600756, 'epoch': 0.78}

  7%|▋         | 1828/28080 [3:36:29<51:27:05,  7.06s/it]
  7%|▋         | 1829/28080 [3:36:36<51:15:43,  7.03s/it]
                                                         
{'loss': 0.7037, 'learning_rate': 0.0004983849837489513, 'epoch': 0.78}

  7%|▋         | 1829/28080 [3:36:36<51:15:43,  7.03s/it]
  7%|▋         | 1830/28080 [3:36:43<51:31:36,  7.07s/it]
                                                         
{'loss': 0.6947, 'learning_rate': 0.0004983817097333209, 'epoch': 0.78}

  7%|▋         | 1830/28080 [3:36:43<51:31:36,  7.07s/it]
  7%|▋         | 1831/28080 [3:36:50<51:45:23,  7.10s/it]
                                                         
{'loss': 0.6863, 'learning_rate': 0.0004983784324132282, 'epoch': 0.78}

  7%|▋         | 1831/28080 [3:36:50<51:45:23,  7.10s/it]
  7%|▋         | 1832/28080 [3:36:57<51:46:25,  7.10s/it]
                                                         
{'loss': 0.7063, 'learning_rate': 0.0004983751517887167, 'epoch': 0.78}

  7%|▋         | 1832/28080 [3:36:57<51:46:25,  7.10s/it]
  7%|▋         | 1833/28080 [3:37:04<51:52:09,  7.11s/it]
                                                         
{'loss': 0.6815, 'learning_rate': 0.00049837186785983, 'epoch': 0.78}

  7%|▋         | 1833/28080 [3:37:04<51:52:09,  7.11s/it]
  7%|▋         | 1834/28080 [3:37:12<51:52:45,  7.12s/it]
                                                         
{'loss': 0.6983, 'learning_rate': 0.0004983685806266118, 'epoch': 0.78}

  7%|▋         | 1834/28080 [3:37:12<51:52:45,  7.12s/it]
  7%|▋         | 1835/28080 [3:37:19<51:50:39,  7.11s/it]
                                                         
{'loss': 0.6953, 'learning_rate': 0.0004983652900891059, 'epoch': 0.78}

  7%|▋         | 1835/28080 [3:37:19<51:50:39,  7.11s/it]
  7%|▋         | 1836/28080 [3:37:26<51:55:26,  7.12s/it]
                                                         
{'loss': 0.699, 'learning_rate': 0.000498361996247356, 'epoch': 0.78}

  7%|▋         | 1836/28080 [3:37:26<51:55:26,  7.12s/it]
  7%|▋         | 1837/28080 [3:37:33<51:40:50,  7.09s/it]
                                                         
{'loss': 0.7273, 'learning_rate': 0.000498358699101406, 'epoch': 0.78}

  7%|▋         | 1837/28080 [3:37:33<51:40:50,  7.09s/it]
  7%|▋         | 1838/28080 [3:37:40<51:24:16,  7.05s/it]
                                                         
{'loss': 0.6993, 'learning_rate': 0.0004983553986512996, 'epoch': 0.79}

  7%|▋         | 1838/28080 [3:37:40<51:24:16,  7.05s/it]
  7%|▋         | 1839/28080 [3:37:47<51:32:47,  7.07s/it]
                                                         
{'loss': 0.7012, 'learning_rate': 0.0004983520948970809, 'epoch': 0.79}

  7%|▋         | 1839/28080 [3:37:47<51:32:47,  7.07s/it]
  7%|▋         | 1840/28080 [3:37:54<51:43:19,  7.10s/it]
                                                         
{'loss': 0.6934, 'learning_rate': 0.0004983487878387939, 'epoch': 0.79}

  7%|▋         | 1840/28080 [3:37:54<51:43:19,  7.10s/it]
  7%|▋         | 1841/28080 [3:38:01<51:37:43,  7.08s/it]
                                                         
{'loss': 0.6942, 'learning_rate': 0.0004983454774764825, 'epoch': 0.79}

  7%|▋         | 1841/28080 [3:38:01<51:37:43,  7.08s/it]
  7%|▋         | 1842/28080 [3:38:08<51:39:03,  7.09s/it]
                                                         
{'loss': 0.6981, 'learning_rate': 0.0004983421638101906, 'epoch': 0.79}

  7%|▋         | 1842/28080 [3:38:08<51:39:03,  7.09s/it]
  7%|▋         | 1843/28080 [3:38:15<51:50:25,  7.11s/it]
                                                         
{'loss': 0.6868, 'learning_rate': 0.0004983388468399625, 'epoch': 0.79}

  7%|▋         | 1843/28080 [3:38:15<51:50:25,  7.11s/it]
  7%|▋         | 1844/28080 [3:38:22<51:31:26,  7.07s/it]
                                                         
{'loss': 0.6938, 'learning_rate': 0.0004983355265658422, 'epoch': 0.79}

  7%|▋         | 1844/28080 [3:38:22<51:31:26,  7.07s/it]
  7%|▋         | 1845/28080 [3:38:29<51:21:48,  7.05s/it]
                                                         
{'loss': 0.6967, 'learning_rate': 0.0004983322029878739, 'epoch': 0.79}

  7%|▋         | 1845/28080 [3:38:29<51:21:48,  7.05s/it]
  7%|▋         | 1846/28080 [3:38:36<51:24:03,  7.05s/it]
                                                         
{'loss': 0.7001, 'learning_rate': 0.0004983288761061018, 'epoch': 0.79}

  7%|▋         | 1846/28080 [3:38:36<51:24:03,  7.05s/it]
  7%|▋         | 1847/28080 [3:38:43<51:25:33,  7.06s/it]
                                                         
{'loss': 0.7059, 'learning_rate': 0.0004983255459205702, 'epoch': 0.79}

  7%|▋         | 1847/28080 [3:38:44<51:25:33,  7.06s/it]
  7%|▋         | 1848/28080 [3:38:51<51:34:35,  7.08s/it]
                                                         
{'loss': 0.7054, 'learning_rate': 0.0004983222124313234, 'epoch': 0.79}

  7%|▋         | 1848/28080 [3:38:51<51:34:35,  7.08s/it]
  7%|▋         | 1849/28080 [3:38:58<51:28:55,  7.07s/it]
                                                         
{'loss': 0.7034, 'learning_rate': 0.0004983188756384057, 'epoch': 0.79}

  7%|▋         | 1849/28080 [3:38:58<51:28:55,  7.07s/it]
  7%|▋         | 1850/28080 [3:39:05<51:33:00,  7.08s/it]
                                                         
{'loss': 0.7129, 'learning_rate': 0.0004983155355418617, 'epoch': 0.79}

  7%|▋         | 1850/28080 [3:39:05<51:33:00,  7.08s/it]
  7%|▋         | 1851/28080 [3:39:12<51:33:00,  7.08s/it]
                                                         
{'loss': 0.7133, 'learning_rate': 0.0004983121921417356, 'epoch': 0.79}

  7%|▋         | 1851/28080 [3:39:12<51:33:00,  7.08s/it]
  7%|▋         | 1852/28080 [3:39:19<51:31:09,  7.07s/it]
                                                         
{'loss': 0.7169, 'learning_rate': 0.0004983088454380719, 'epoch': 0.79}

  7%|▋         | 1852/28080 [3:39:19<51:31:09,  7.07s/it]
  7%|▋         | 1853/28080 [3:39:26<51:45:02,  7.10s/it]
                                                         
{'loss': 0.7014, 'learning_rate': 0.0004983054954309151, 'epoch': 0.79}

  7%|▋         | 1853/28080 [3:39:26<51:45:02,  7.10s/it]
  7%|▋         | 1854/28080 [3:39:33<51:47:34,  7.11s/it]
                                                         
{'loss': 0.7185, 'learning_rate': 0.00049830214212031, 'epoch': 0.79}

  7%|▋         | 1854/28080 [3:39:33<51:47:34,  7.11s/it]
  7%|▋         | 1855/28080 [3:39:40<51:42:27,  7.10s/it]
                                                         
{'loss': 0.6924, 'learning_rate': 0.0004982987855063011, 'epoch': 0.79}

  7%|▋         | 1855/28080 [3:39:40<51:42:27,  7.10s/it]
  7%|▋         | 1856/28080 [3:39:47<51:46:34,  7.11s/it]
                                                         
{'loss': 0.724, 'learning_rate': 0.0004982954255889329, 'epoch': 0.79}

  7%|▋         | 1856/28080 [3:39:47<51:46:34,  7.11s/it]
  7%|▋         | 1857/28080 [3:39:55<51:53:03,  7.12s/it]
                                                         
{'loss': 0.7146, 'learning_rate': 0.0004982920623682502, 'epoch': 0.79}

  7%|▋         | 1857/28080 [3:39:55<51:53:03,  7.12s/it]
  7%|▋         | 1858/28080 [3:40:02<51:53:52,  7.13s/it]
                                                         
{'loss': 0.7024, 'learning_rate': 0.0004982886958442978, 'epoch': 0.79}

  7%|▋         | 1858/28080 [3:40:02<51:53:52,  7.13s/it]
  7%|▋         | 1859/28080 [3:40:09<52:01:59,  7.14s/it]
                                                         
{'loss': 0.6888, 'learning_rate': 0.0004982853260171204, 'epoch': 0.79}

  7%|▋         | 1859/28080 [3:40:09<52:01:59,  7.14s/it]
  7%|▋         | 1860/28080 [3:40:16<52:04:07,  7.15s/it]
                                                         
{'loss': 0.7198, 'learning_rate': 0.0004982819528867629, 'epoch': 0.79}

  7%|▋         | 1860/28080 [3:40:16<52:04:07,  7.15s/it]
  7%|▋         | 1861/28080 [3:40:23<52:01:55,  7.14s/it]
                                                         
{'loss': 0.7232, 'learning_rate': 0.0004982785764532702, 'epoch': 0.8}

  7%|▋         | 1861/28080 [3:40:23<52:01:55,  7.14s/it]
  7%|▋         | 1862/28080 [3:40:30<51:56:47,  7.13s/it]
                                                         
{'loss': 0.7255, 'learning_rate': 0.0004982751967166872, 'epoch': 0.8}

  7%|▋         | 1862/28080 [3:40:30<51:56:47,  7.13s/it]
  7%|▋         | 1863/28080 [3:40:37<51:54:01,  7.13s/it]
                                                         
{'loss': 0.7025, 'learning_rate': 0.0004982718136770588, 'epoch': 0.8}

  7%|▋         | 1863/28080 [3:40:37<51:54:01,  7.13s/it]
  7%|▋         | 1864/28080 [3:40:44<51:41:46,  7.10s/it]
                                                         
{'loss': 0.6873, 'learning_rate': 0.0004982684273344301, 'epoch': 0.8}

  7%|▋         | 1864/28080 [3:40:44<51:41:46,  7.10s/it]
  7%|▋         | 1865/28080 [3:40:52<51:48:13,  7.11s/it]
                                                         
{'loss': 0.7003, 'learning_rate': 0.0004982650376888459, 'epoch': 0.8}

  7%|▋         | 1865/28080 [3:40:52<51:48:13,  7.11s/it]
  7%|▋         | 1866/28080 [3:40:59<52:00:40,  7.14s/it]
                                                         
{'loss': 0.7241, 'learning_rate': 0.0004982616447403517, 'epoch': 0.8}

  7%|▋         | 1866/28080 [3:40:59<52:00:40,  7.14s/it]
  7%|▋         | 1867/28080 [3:41:06<51:45:39,  7.11s/it]
                                                         
{'loss': 0.677, 'learning_rate': 0.0004982582484889923, 'epoch': 0.8}

  7%|▋         | 1867/28080 [3:41:06<51:45:39,  7.11s/it]
  7%|▋         | 1868/28080 [3:41:13<51:42:31,  7.10s/it]
                                                         
{'loss': 0.695, 'learning_rate': 0.0004982548489348131, 'epoch': 0.8}

  7%|▋         | 1868/28080 [3:41:13<51:42:31,  7.10s/it]
  7%|▋         | 1869/28080 [3:41:20<51:43:20,  7.10s/it]
                                                         
{'loss': 0.7074, 'learning_rate': 0.0004982514460778592, 'epoch': 0.8}

  7%|▋         | 1869/28080 [3:41:20<51:43:20,  7.10s/it]
  7%|▋         | 1870/28080 [3:41:27<51:33:57,  7.08s/it]
                                                         
{'loss': 0.7059, 'learning_rate': 0.0004982480399181759, 'epoch': 0.8}

  7%|▋         | 1870/28080 [3:41:27<51:33:57,  7.08s/it]
  7%|▋         | 1871/28080 [3:41:34<51:36:33,  7.09s/it]
                                                         
{'loss': 0.7114, 'learning_rate': 0.0004982446304558086, 'epoch': 0.8}

  7%|▋         | 1871/28080 [3:41:34<51:36:33,  7.09s/it]
  7%|▋         | 1872/28080 [3:41:41<51:43:53,  7.11s/it]
                                                         
{'loss': 0.6942, 'learning_rate': 0.0004982412176908026, 'epoch': 0.8}

  7%|▋         | 1872/28080 [3:41:41<51:43:53,  7.11s/it]
  7%|▋         | 1873/28080 [3:41:48<51:51:17,  7.12s/it]
                                                         
{'loss': 0.7007, 'learning_rate': 0.0004982378016232033, 'epoch': 0.8}

  7%|▋         | 1873/28080 [3:41:48<51:51:17,  7.12s/it]
  7%|▋         | 1874/28080 [3:41:56<51:54:35,  7.13s/it]
                                                         
{'loss': 0.697, 'learning_rate': 0.0004982343822530561, 'epoch': 0.8}

  7%|▋         | 1874/28080 [3:41:56<51:54:35,  7.13s/it]
  7%|▋         | 1875/28080 [3:42:03<51:32:56,  7.08s/it]
                                                         
{'loss': 0.6856, 'learning_rate': 0.0004982309595804065, 'epoch': 0.8}

  7%|▋         | 1875/28080 [3:42:03<51:32:56,  7.08s/it]
  7%|▋         | 1876/28080 [3:42:10<51:30:35,  7.08s/it]
                                                         
{'loss': 0.6932, 'learning_rate': 0.0004982275336053001, 'epoch': 0.8}

  7%|▋         | 1876/28080 [3:42:10<51:30:35,  7.08s/it]
  7%|▋         | 1877/28080 [3:42:17<51:24:17,  7.06s/it]
                                                         
{'loss': 0.6818, 'learning_rate': 0.0004982241043277824, 'epoch': 0.8}

  7%|▋         | 1877/28080 [3:42:17<51:24:17,  7.06s/it]
  7%|▋         | 1878/28080 [3:42:24<51:20:59,  7.06s/it]
                                                         
{'loss': 0.6887, 'learning_rate': 0.0004982206717478992, 'epoch': 0.8}

  7%|▋         | 1878/28080 [3:42:24<51:20:59,  7.06s/it]
  7%|▋         | 1879/28080 [3:42:31<51:19:36,  7.05s/it]
                                                         
{'loss': 0.6935, 'learning_rate': 0.0004982172358656959, 'epoch': 0.8}

  7%|▋         | 1879/28080 [3:42:31<51:19:36,  7.05s/it]
  7%|▋         | 1880/28080 [3:42:38<51:19:23,  7.05s/it]
                                                         
{'loss': 0.696, 'learning_rate': 0.0004982137966812185, 'epoch': 0.8}

  7%|▋         | 1880/28080 [3:42:38<51:19:23,  7.05s/it]
  7%|▋         | 1881/28080 [3:42:45<51:31:53,  7.08s/it]
                                                         
{'loss': 0.7053, 'learning_rate': 0.0004982103541945124, 'epoch': 0.8}

  7%|▋         | 1881/28080 [3:42:45<51:31:53,  7.08s/it]
  7%|▋         | 1882/28080 [3:42:52<51:35:45,  7.09s/it]
                                                         
{'loss': 0.6918, 'learning_rate': 0.0004982069084056238, 'epoch': 0.8}

  7%|▋         | 1882/28080 [3:42:52<51:35:45,  7.09s/it]
  7%|▋         | 1883/28080 [3:42:59<51:18:12,  7.05s/it]
                                                         
{'loss': 0.6975, 'learning_rate': 0.0004982034593145982, 'epoch': 0.8}

  7%|▋         | 1883/28080 [3:42:59<51:18:12,  7.05s/it]
  7%|▋         | 1884/28080 [3:43:06<51:14:20,  7.04s/it]
                                                         
{'loss': 0.7154, 'learning_rate': 0.0004982000069214817, 'epoch': 0.8}

  7%|▋         | 1884/28080 [3:43:06<51:14:20,  7.04s/it]
  7%|▋         | 1885/28080 [3:43:13<51:30:53,  7.08s/it]
                                                         
{'loss': 0.7013, 'learning_rate': 0.0004981965512263201, 'epoch': 0.81}

  7%|▋         | 1885/28080 [3:43:13<51:30:53,  7.08s/it]
  7%|▋         | 1886/28080 [3:43:20<51:21:13,  7.06s/it]
                                                         
{'loss': 0.7229, 'learning_rate': 0.0004981930922291595, 'epoch': 0.81}

  7%|▋         | 1886/28080 [3:43:20<51:21:13,  7.06s/it]
  7%|▋         | 1887/28080 [3:43:27<51:28:57,  7.08s/it]
                                                         
{'loss': 0.6945, 'learning_rate': 0.0004981896299300459, 'epoch': 0.81}

  7%|▋         | 1887/28080 [3:43:27<51:28:57,  7.08s/it]
  7%|▋         | 1888/28080 [3:43:34<51:30:16,  7.08s/it]
                                                         
{'loss': 0.6981, 'learning_rate': 0.0004981861643290253, 'epoch': 0.81}

  7%|▋         | 1888/28080 [3:43:34<51:30:16,  7.08s/it]
  7%|▋         | 1889/28080 [3:43:42<51:55:12,  7.14s/it]
                                                         
{'loss': 0.6939, 'learning_rate': 0.0004981826954261437, 'epoch': 0.81}

  7%|▋         | 1889/28080 [3:43:42<51:55:12,  7.14s/it]
  7%|▋         | 1890/28080 [3:43:49<51:47:16,  7.12s/it]
                                                         
{'loss': 0.7095, 'learning_rate': 0.0004981792232214475, 'epoch': 0.81}

  7%|▋         | 1890/28080 [3:43:49<51:47:16,  7.12s/it]
  7%|▋         | 1891/28080 [3:43:56<51:31:13,  7.08s/it]
                                                         
{'loss': 0.7108, 'learning_rate': 0.0004981757477149827, 'epoch': 0.81}

  7%|▋         | 1891/28080 [3:43:56<51:31:13,  7.08s/it]
  7%|▋         | 1892/28080 [3:44:03<51:35:36,  7.09s/it]
                                                         
{'loss': 0.7071, 'learning_rate': 0.0004981722689067957, 'epoch': 0.81}

  7%|▋         | 1892/28080 [3:44:03<51:35:36,  7.09s/it]
  7%|▋         | 1893/28080 [3:44:10<51:29:00,  7.08s/it]
                                                         
{'loss': 0.6942, 'learning_rate': 0.0004981687867969325, 'epoch': 0.81}

  7%|▋         | 1893/28080 [3:44:10<51:29:00,  7.08s/it]
  7%|▋         | 1894/28080 [3:44:17<51:23:58,  7.07s/it]
                                                         
{'loss': 0.6963, 'learning_rate': 0.0004981653013854398, 'epoch': 0.81}

  7%|▋         | 1894/28080 [3:44:17<51:23:58,  7.07s/it]
  7%|▋         | 1895/28080 [3:44:24<51:28:31,  7.08s/it]
                                                         
{'loss': 0.6914, 'learning_rate': 0.0004981618126723638, 'epoch': 0.81}

  7%|▋         | 1895/28080 [3:44:24<51:28:31,  7.08s/it]
  7%|▋         | 1896/28080 [3:44:31<51:31:12,  7.08s/it]
                                                         
{'loss': 0.6792, 'learning_rate': 0.0004981583206577506, 'epoch': 0.81}

  7%|▋         | 1896/28080 [3:44:31<51:31:12,  7.08s/it]
  7%|▋         | 1897/28080 [3:44:38<51:16:52,  7.05s/it]
                                                         
{'loss': 0.7025, 'learning_rate': 0.0004981548253416472, 'epoch': 0.81}

  7%|▋         | 1897/28080 [3:44:38<51:16:52,  7.05s/it]
  7%|▋         | 1898/28080 [3:44:45<51:31:06,  7.08s/it]
                                                         
{'loss': 0.7051, 'learning_rate': 0.0004981513267240999, 'epoch': 0.81}

  7%|▋         | 1898/28080 [3:44:45<51:31:06,  7.08s/it]
  7%|▋         | 1899/28080 [3:44:52<51:27:38,  7.08s/it]
                                                         
{'loss': 0.6872, 'learning_rate': 0.0004981478248051551, 'epoch': 0.81}

  7%|▋         | 1899/28080 [3:44:52<51:27:38,  7.08s/it]
  7%|▋         | 1900/28080 [3:44:59<51:34:23,  7.09s/it]
                                                         
{'loss': 0.7084, 'learning_rate': 0.0004981443195848595, 'epoch': 0.81}

  7%|▋         | 1900/28080 [3:44:59<51:34:23,  7.09s/it]
  7%|▋         | 1901/28080 [3:45:07<51:35:31,  7.09s/it]
                                                         
{'loss': 0.6873, 'learning_rate': 0.0004981408110632597, 'epoch': 0.81}

  7%|▋         | 1901/28080 [3:45:07<51:35:31,  7.09s/it]
  7%|▋         | 1902/28080 [3:45:14<51:29:00,  7.08s/it]
                                                         
{'loss': 0.696, 'learning_rate': 0.0004981372992404025, 'epoch': 0.81}

  7%|▋         | 1902/28080 [3:45:14<51:29:00,  7.08s/it]
  7%|▋         | 1903/28080 [3:45:21<51:40:29,  7.11s/it]
                                                         
{'loss': 0.6979, 'learning_rate': 0.0004981337841163345, 'epoch': 0.81}

  7%|▋         | 1903/28080 [3:45:21<51:40:29,  7.11s/it]
  7%|▋         | 1904/28080 [3:45:28<51:48:29,  7.13s/it]
                                                         
{'loss': 0.7002, 'learning_rate': 0.0004981302656911024, 'epoch': 0.81}

  7%|▋         | 1904/28080 [3:45:28<51:48:29,  7.13s/it]
  7%|▋         | 1905/28080 [3:45:35<51:41:12,  7.11s/it]
                                                         
{'loss': 0.6923, 'learning_rate': 0.0004981267439647531, 'epoch': 0.81}

  7%|▋         | 1905/28080 [3:45:35<51:41:12,  7.11s/it]
  7%|▋         | 1906/28080 [3:45:42<51:41:44,  7.11s/it]
                                                         
{'loss': 0.7073, 'learning_rate': 0.0004981232189373335, 'epoch': 0.81}

  7%|▋         | 1906/28080 [3:45:42<51:41:44,  7.11s/it]
  7%|▋         | 1907/28080 [3:45:49<51:48:54,  7.13s/it]
                                                         
{'loss': 0.7127, 'learning_rate': 0.0004981196906088904, 'epoch': 0.81}

  7%|▋         | 1907/28080 [3:45:49<51:48:54,  7.13s/it]
  7%|▋         | 1908/28080 [3:45:56<51:50:55,  7.13s/it]
                                                         
{'loss': 0.7028, 'learning_rate': 0.0004981161589794708, 'epoch': 0.82}

  7%|▋         | 1908/28080 [3:45:56<51:50:55,  7.13s/it]
  7%|▋         | 1909/28080 [3:46:03<51:28:35,  7.08s/it]
                                                         
{'loss': 0.6981, 'learning_rate': 0.0004981126240491217, 'epoch': 0.82}

  7%|▋         | 1909/28080 [3:46:03<51:28:35,  7.08s/it]
  7%|▋         | 1910/28080 [3:46:11<51:39:49,  7.11s/it]
                                                         
{'loss': 0.7011, 'learning_rate': 0.0004981090858178902, 'epoch': 0.82}

  7%|▋         | 1910/28080 [3:46:11<51:39:49,  7.11s/it]
  7%|▋         | 1911/28080 [3:46:18<51:40:42,  7.11s/it]
                                                         
{'loss': 0.6983, 'learning_rate': 0.0004981055442858231, 'epoch': 0.82}

  7%|▋         | 1911/28080 [3:46:18<51:40:42,  7.11s/it]
  7%|▋         | 1912/28080 [3:46:25<51:38:21,  7.10s/it]
                                                         
{'loss': 0.7132, 'learning_rate': 0.0004981019994529678, 'epoch': 0.82}

  7%|▋         | 1912/28080 [3:46:25<51:38:21,  7.10s/it]
  7%|▋         | 1913/28080 [3:46:32<51:36:41,  7.10s/it]
                                                         
{'loss': 0.7028, 'learning_rate': 0.0004980984513193713, 'epoch': 0.82}

  7%|▋         | 1913/28080 [3:46:32<51:36:41,  7.10s/it]
  7%|▋         | 1914/28080 [3:46:39<51:36:29,  7.10s/it]
                                                         
{'loss': 0.705, 'learning_rate': 0.0004980948998850809, 'epoch': 0.82}

  7%|▋         | 1914/28080 [3:46:39<51:36:29,  7.10s/it]
  7%|▋         | 1915/28080 [3:46:46<51:41:35,  7.11s/it]
                                                         
{'loss': 0.7032, 'learning_rate': 0.0004980913451501438, 'epoch': 0.82}

  7%|▋         | 1915/28080 [3:46:46<51:41:35,  7.11s/it]
  7%|▋         | 1916/28080 [3:46:53<51:48:40,  7.13s/it]
                                                         
{'loss': 0.7119, 'learning_rate': 0.0004980877871146071, 'epoch': 0.82}

  7%|▋         | 1916/28080 [3:46:53<51:48:40,  7.13s/it]
  7%|▋         | 1917/28080 [3:47:00<51:52:09,  7.14s/it]
                                                         
{'loss': 0.688, 'learning_rate': 0.0004980842257785186, 'epoch': 0.82}

  7%|▋         | 1917/28080 [3:47:00<51:52:09,  7.14s/it]
  7%|▋         | 1918/28080 [3:47:07<51:31:46,  7.09s/it]
                                                         
{'loss': 0.7078, 'learning_rate': 0.0004980806611419253, 'epoch': 0.82}

  7%|▋         | 1918/28080 [3:47:07<51:31:46,  7.09s/it]
  7%|▋         | 1919/28080 [3:47:15<51:49:34,  7.13s/it]
                                                         
{'loss': 0.6749, 'learning_rate': 0.0004980770932048747, 'epoch': 0.82}

  7%|▋         | 1919/28080 [3:47:15<51:49:34,  7.13s/it]
  7%|▋         | 1920/28080 [3:47:22<51:40:24,  7.11s/it]
                                                         
{'loss': 0.689, 'learning_rate': 0.0004980735219674143, 'epoch': 0.82}

  7%|▋         | 1920/28080 [3:47:22<51:40:24,  7.11s/it]
  7%|▋         | 1921/28080 [3:47:29<51:39:26,  7.11s/it]
                                                         
{'loss': 0.6924, 'learning_rate': 0.0004980699474295917, 'epoch': 0.82}

  7%|▋         | 1921/28080 [3:47:29<51:39:26,  7.11s/it]
  7%|▋         | 1922/28080 [3:47:36<51:33:38,  7.10s/it]
                                                         
{'loss': 0.6915, 'learning_rate': 0.0004980663695914544, 'epoch': 0.82}

  7%|▋         | 1922/28080 [3:47:36<51:33:38,  7.10s/it]
  7%|▋         | 1923/28080 [3:47:43<51:39:02,  7.11s/it]
                                                         
{'loss': 0.6908, 'learning_rate': 0.0004980627884530498, 'epoch': 0.82}

  7%|▋         | 1923/28080 [3:47:43<51:39:02,  7.11s/it]
  7%|▋         | 1924/28080 [3:47:50<51:30:26,  7.09s/it]
                                                         
{'loss': 0.6827, 'learning_rate': 0.0004980592040144258, 'epoch': 0.82}

  7%|▋         | 1924/28080 [3:47:50<51:30:26,  7.09s/it]
  7%|▋         | 1925/28080 [3:47:57<51:28:41,  7.09s/it]
                                                         
{'loss': 0.6701, 'learning_rate': 0.00049805561627563, 'epoch': 0.82}

  7%|▋         | 1925/28080 [3:47:57<51:28:41,  7.09s/it]
  7%|▋         | 1926/28080 [3:48:04<51:28:00,  7.08s/it]
                                                         
{'loss': 0.7117, 'learning_rate': 0.0004980520252367101, 'epoch': 0.82}

  7%|▋         | 1926/28080 [3:48:04<51:28:00,  7.08s/it]
  7%|▋         | 1927/28080 [3:48:11<51:31:36,  7.09s/it]
                                                         
{'loss': 0.6939, 'learning_rate': 0.0004980484308977141, 'epoch': 0.82}

  7%|▋         | 1927/28080 [3:48:11<51:31:36,  7.09s/it]
  7%|▋         | 1928/28080 [3:48:18<51:30:19,  7.09s/it]
                                                         
{'loss': 0.6941, 'learning_rate': 0.0004980448332586894, 'epoch': 0.82}

  7%|▋         | 1928/28080 [3:48:18<51:30:19,  7.09s/it]
  7%|▋         | 1929/28080 [3:48:26<51:27:29,  7.08s/it]
                                                         
{'loss': 0.7266, 'learning_rate': 0.0004980412323196841, 'epoch': 0.82}

  7%|▋         | 1929/28080 [3:48:26<51:27:29,  7.08s/it]
  7%|▋         | 1930/28080 [3:48:33<51:42:15,  7.12s/it]
                                                         
{'loss': 0.7077, 'learning_rate': 0.0004980376280807462, 'epoch': 0.82}

  7%|▋         | 1930/28080 [3:48:33<51:42:15,  7.12s/it]
  7%|▋         | 1931/28080 [3:48:40<51:41:14,  7.12s/it]
                                                         
{'loss': 0.6861, 'learning_rate': 0.0004980340205419234, 'epoch': 0.82}

  7%|▋         | 1931/28080 [3:48:40<51:41:14,  7.12s/it]
  7%|▋         | 1932/28080 [3:48:47<51:41:57,  7.12s/it]
                                                         
{'loss': 0.705, 'learning_rate': 0.0004980304097032639, 'epoch': 0.83}

  7%|▋         | 1932/28080 [3:48:47<51:41:57,  7.12s/it]
  7%|▋         | 1933/28080 [3:48:54<51:38:31,  7.11s/it]
                                                         
{'loss': 0.7029, 'learning_rate': 0.0004980267955648157, 'epoch': 0.83}

  7%|▋         | 1933/28080 [3:48:54<51:38:31,  7.11s/it]
  7%|▋         | 1934/28080 [3:49:01<51:36:43,  7.11s/it]
                                                         
{'loss': 0.6802, 'learning_rate': 0.0004980231781266269, 'epoch': 0.83}

  7%|▋         | 1934/28080 [3:49:01<51:36:43,  7.11s/it]
  7%|▋         | 1935/28080 [3:49:08<51:38:05,  7.11s/it]
                                                         
{'loss': 0.6969, 'learning_rate': 0.0004980195573887456, 'epoch': 0.83}

  7%|▋         | 1935/28080 [3:49:08<51:38:05,  7.11s/it]
  7%|▋         | 1936/28080 [3:49:15<51:40:30,  7.12s/it]
                                                         
{'loss': 0.7342, 'learning_rate': 0.0004980159333512199, 'epoch': 0.83}

  7%|▋         | 1936/28080 [3:49:15<51:40:30,  7.12s/it]
  7%|▋         | 1937/28080 [3:49:22<51:31:27,  7.10s/it]
                                                         
{'loss': 0.7128, 'learning_rate': 0.000498012306014098, 'epoch': 0.83}

  7%|▋         | 1937/28080 [3:49:22<51:31:27,  7.10s/it]
  7%|▋         | 1938/28080 [3:49:29<51:25:59,  7.08s/it]
                                                         
{'loss': 0.7239, 'learning_rate': 0.0004980086753774283, 'epoch': 0.83}

  7%|▋         | 1938/28080 [3:49:29<51:25:59,  7.08s/it]
  7%|▋         | 1939/28080 [3:49:37<51:33:50,  7.10s/it]
                                                         
{'loss': 0.7013, 'learning_rate': 0.000498005041441259, 'epoch': 0.83}

  7%|▋         | 1939/28080 [3:49:37<51:33:50,  7.10s/it]
  7%|▋         | 1940/28080 [3:49:44<51:29:11,  7.09s/it]
                                                         
{'loss': 0.6985, 'learning_rate': 0.0004980014042056386, 'epoch': 0.83}

  7%|▋         | 1940/28080 [3:49:44<51:29:11,  7.09s/it]
  7%|▋         | 1941/28080 [3:49:51<51:29:11,  7.09s/it]
                                                         
{'loss': 0.7108, 'learning_rate': 0.0004979977636706153, 'epoch': 0.83}

  7%|▋         | 1941/28080 [3:49:51<51:29:11,  7.09s/it]
  7%|▋         | 1942/28080 [3:49:58<51:38:58,  7.11s/it]
                                                         
{'loss': 0.6843, 'learning_rate': 0.0004979941198362376, 'epoch': 0.83}

  7%|▋         | 1942/28080 [3:49:58<51:38:58,  7.11s/it]
  7%|▋         | 1943/28080 [3:50:05<51:15:13,  7.06s/it]
                                                         
{'loss': 0.7203, 'learning_rate': 0.0004979904727025539, 'epoch': 0.83}

  7%|▋         | 1943/28080 [3:50:05<51:15:13,  7.06s/it]
  7%|▋         | 1944/28080 [3:50:12<51:32:00,  7.10s/it]
                                                         
{'loss': 0.6861, 'learning_rate': 0.0004979868222696128, 'epoch': 0.83}

  7%|▋         | 1944/28080 [3:50:12<51:32:00,  7.10s/it]
  7%|▋         | 1945/28080 [3:50:19<51:39:30,  7.12s/it]
                                                         
{'loss': 0.7115, 'learning_rate': 0.000497983168537463, 'epoch': 0.83}

  7%|▋         | 1945/28080 [3:50:19<51:39:30,  7.12s/it]
  7%|▋         | 1946/28080 [3:50:26<51:43:18,  7.12s/it]
                                                         
{'loss': 0.7043, 'learning_rate': 0.0004979795115061528, 'epoch': 0.83}

  7%|▋         | 1946/28080 [3:50:26<51:43:18,  7.12s/it]
  7%|▋         | 1947/28080 [3:50:33<51:41:18,  7.12s/it]
                                                         
{'loss': 0.6983, 'learning_rate': 0.0004979758511757311, 'epoch': 0.83}

  7%|▋         | 1947/28080 [3:50:33<51:41:18,  7.12s/it]
  7%|▋         | 1948/28080 [3:50:41<51:44:07,  7.13s/it]
                                                         
{'loss': 0.6891, 'learning_rate': 0.0004979721875462466, 'epoch': 0.83}

  7%|▋         | 1948/28080 [3:50:41<51:44:07,  7.13s/it]
  7%|▋         | 1949/28080 [3:50:48<51:36:44,  7.11s/it]
                                                         
{'loss': 0.7053, 'learning_rate': 0.0004979685206177479, 'epoch': 0.83}

  7%|▋         | 1949/28080 [3:50:48<51:36:44,  7.11s/it]
  7%|▋         | 1950/28080 [3:50:55<51:50:24,  7.14s/it]
                                                         
{'loss': 0.6938, 'learning_rate': 0.0004979648503902838, 'epoch': 0.83}

  7%|▋         | 1950/28080 [3:50:55<51:50:24,  7.14s/it]
  7%|▋         | 1951/28080 [3:51:02<51:40:02,  7.12s/it]
                                                         
{'loss': 0.6939, 'learning_rate': 0.0004979611768639033, 'epoch': 0.83}

  7%|▋         | 1951/28080 [3:51:02<51:40:02,  7.12s/it]
  7%|▋         | 1952/28080 [3:51:09<51:52:40,  7.15s/it]
                                                         
{'loss': 0.6814, 'learning_rate': 0.0004979575000386551, 'epoch': 0.83}

  7%|▋         | 1952/28080 [3:51:09<51:52:40,  7.15s/it]
  7%|▋         | 1953/28080 [3:51:16<51:45:31,  7.13s/it]
                                                         
{'loss': 0.6814, 'learning_rate': 0.000497953819914588, 'epoch': 0.83}

  7%|▋         | 1953/28080 [3:51:16<51:45:31,  7.13s/it]
  7%|▋         | 1954/28080 [3:51:23<51:50:35,  7.14s/it]
                                                         
{'loss': 0.7046, 'learning_rate': 0.0004979501364917513, 'epoch': 0.83}

  7%|▋         | 1954/28080 [3:51:23<51:50:35,  7.14s/it]
  7%|▋         | 1955/28080 [3:51:31<51:44:02,  7.13s/it]
                                                         
{'loss': 0.6976, 'learning_rate': 0.0004979464497701937, 'epoch': 0.84}

  7%|▋         | 1955/28080 [3:51:31<51:44:02,  7.13s/it]
  7%|▋         | 1956/28080 [3:51:38<51:52:30,  7.15s/it]
                                                         
{'loss': 0.6868, 'learning_rate': 0.0004979427597499646, 'epoch': 0.84}

  7%|▋         | 1956/28080 [3:51:38<51:52:30,  7.15s/it]
  7%|▋         | 1957/28080 [3:51:45<51:45:52,  7.13s/it]
                                                         
{'loss': 0.6959, 'learning_rate': 0.0004979390664311128, 'epoch': 0.84}

  7%|▋         | 1957/28080 [3:51:45<51:45:52,  7.13s/it]
  7%|▋         | 1958/28080 [3:51:52<51:48:24,  7.14s/it]
                                                         
{'loss': 0.7019, 'learning_rate': 0.0004979353698136874, 'epoch': 0.84}

  7%|▋         | 1958/28080 [3:51:52<51:48:24,  7.14s/it]
  7%|▋         | 1959/28080 [3:51:59<51:42:53,  7.13s/it]
                                                         
{'loss': 0.6851, 'learning_rate': 0.0004979316698977377, 'epoch': 0.84}

  7%|▋         | 1959/28080 [3:51:59<51:42:53,  7.13s/it]
  7%|▋         | 1960/28080 [3:52:06<51:30:52,  7.10s/it]
                                                         
{'loss': 0.6857, 'learning_rate': 0.0004979279666833129, 'epoch': 0.84}

  7%|▋         | 1960/28080 [3:52:06<51:30:52,  7.10s/it]
  7%|▋         | 1961/28080 [3:52:13<51:34:07,  7.11s/it]
                                                         
{'loss': 0.6781, 'learning_rate': 0.0004979242601704623, 'epoch': 0.84}

  7%|▋         | 1961/28080 [3:52:13<51:34:07,  7.11s/it]
  7%|▋         | 1962/28080 [3:52:20<51:17:31,  7.07s/it]
                                                         
{'loss': 0.7072, 'learning_rate': 0.0004979205503592352, 'epoch': 0.84}

  7%|▋         | 1962/28080 [3:52:20<51:17:31,  7.07s/it]
  7%|▋         | 1963/28080 [3:52:27<51:24:25,  7.09s/it]
                                                         
{'loss': 0.71, 'learning_rate': 0.000497916837249681, 'epoch': 0.84}

  7%|▋         | 1963/28080 [3:52:27<51:24:25,  7.09s/it]
  7%|▋         | 1964/28080 [3:52:34<51:21:14,  7.08s/it]
                                                         
{'loss': 0.7047, 'learning_rate': 0.000497913120841849, 'epoch': 0.84}

  7%|▋         | 1964/28080 [3:52:34<51:21:14,  7.08s/it]
  7%|▋         | 1965/28080 [3:52:42<51:27:42,  7.09s/it]
                                                         
{'loss': 0.7076, 'learning_rate': 0.0004979094011357887, 'epoch': 0.84}

  7%|▋         | 1965/28080 [3:52:42<51:27:42,  7.09s/it]
  7%|▋         | 1966/28080 [3:52:49<51:20:16,  7.08s/it]
                                                         
{'loss': 0.72, 'learning_rate': 0.0004979056781315495, 'epoch': 0.84}

  7%|▋         | 1966/28080 [3:52:49<51:20:16,  7.08s/it]
  7%|▋         | 1967/28080 [3:52:56<51:21:10,  7.08s/it]
                                                         
{'loss': 0.7058, 'learning_rate': 0.000497901951829181, 'epoch': 0.84}

  7%|▋         | 1967/28080 [3:52:56<51:21:10,  7.08s/it]
  7%|▋         | 1968/28080 [3:53:03<51:30:40,  7.10s/it]
                                                         
{'loss': 0.6946, 'learning_rate': 0.0004978982222287329, 'epoch': 0.84}

  7%|▋         | 1968/28080 [3:53:03<51:30:40,  7.10s/it]
  7%|▋         | 1969/28080 [3:53:10<51:34:47,  7.11s/it]
                                                         
{'loss': 0.6827, 'learning_rate': 0.0004978944893302546, 'epoch': 0.84}

  7%|▋         | 1969/28080 [3:53:10<51:34:47,  7.11s/it]
  7%|▋         | 1970/28080 [3:53:17<51:39:31,  7.12s/it]
                                                         
{'loss': 0.6771, 'learning_rate': 0.0004978907531337959, 'epoch': 0.84}

  7%|▋         | 1970/28080 [3:53:17<51:39:31,  7.12s/it]
  7%|▋         | 1971/28080 [3:53:24<51:46:31,  7.14s/it]
                                                         
{'loss': 0.6904, 'learning_rate': 0.0004978870136394065, 'epoch': 0.84}

  7%|▋         | 1971/28080 [3:53:24<51:46:31,  7.14s/it]
  7%|▋         | 1972/28080 [3:53:31<51:48:19,  7.14s/it]
                                                         
{'loss': 0.6872, 'learning_rate': 0.000497883270847136, 'epoch': 0.84}

  7%|▋         | 1972/28080 [3:53:31<51:48:19,  7.14s/it]
  7%|▋         | 1973/28080 [3:53:39<51:53:40,  7.16s/it]
                                                         
{'loss': 0.6961, 'learning_rate': 0.0004978795247570344, 'epoch': 0.84}

  7%|▋         | 1973/28080 [3:53:39<51:53:40,  7.16s/it]
  7%|▋         | 1974/28080 [3:53:46<51:56:25,  7.16s/it]
                                                         
{'loss': 0.7034, 'learning_rate': 0.0004978757753691514, 'epoch': 0.84}

  7%|▋         | 1974/28080 [3:53:46<51:56:25,  7.16s/it]
  7%|▋         | 1975/28080 [3:53:53<51:51:15,  7.15s/it]
                                                         
{'loss': 0.7032, 'learning_rate': 0.0004978720226835369, 'epoch': 0.84}

  7%|▋         | 1975/28080 [3:53:53<51:51:15,  7.15s/it]
  7%|▋         | 1976/28080 [3:54:00<51:54:36,  7.16s/it]
                                                         
{'loss': 0.6907, 'learning_rate': 0.0004978682667002408, 'epoch': 0.84}

  7%|▋         | 1976/28080 [3:54:00<51:54:36,  7.16s/it]
  7%|▋         | 1977/28080 [3:54:07<51:49:03,  7.15s/it]
                                                         
{'loss': 0.7067, 'learning_rate': 0.0004978645074193134, 'epoch': 0.84}

  7%|▋         | 1977/28080 [3:54:07<51:49:03,  7.15s/it]
  7%|▋         | 1978/28080 [3:54:14<51:44:30,  7.14s/it]
                                                         
{'loss': 0.6977, 'learning_rate': 0.0004978607448408042, 'epoch': 0.84}

  7%|▋         | 1978/28080 [3:54:14<51:44:30,  7.14s/it]
  7%|▋         | 1979/28080 [3:54:21<51:38:07,  7.12s/it]
                                                         
{'loss': 0.6883, 'learning_rate': 0.0004978569789647636, 'epoch': 0.85}

  7%|▋         | 1979/28080 [3:54:21<51:38:07,  7.12s/it]
  7%|▋         | 1980/28080 [3:54:29<51:55:55,  7.16s/it]
                                                         
{'loss': 0.6858, 'learning_rate': 0.0004978532097912415, 'epoch': 0.85}

  7%|▋         | 1980/28080 [3:54:29<51:55:55,  7.16s/it]
  7%|▋         | 1981/28080 [3:54:36<51:27:32,  7.10s/it]
                                                         
{'loss': 0.7172, 'learning_rate': 0.0004978494373202882, 'epoch': 0.85}

  7%|▋         | 1981/28080 [3:54:36<51:27:32,  7.10s/it]
  7%|▋         | 1982/28080 [3:54:43<51:20:43,  7.08s/it]
                                                         
{'loss': 0.7124, 'learning_rate': 0.0004978456615519537, 'epoch': 0.85}

  7%|▋         | 1982/28080 [3:54:43<51:20:43,  7.08s/it]
  7%|▋         | 1983/28080 [3:54:50<51:28:29,  7.10s/it]
                                                         
{'loss': 0.7033, 'learning_rate': 0.0004978418824862885, 'epoch': 0.85}

  7%|▋         | 1983/28080 [3:54:50<51:28:29,  7.10s/it]
  7%|▋         | 1984/28080 [3:54:57<51:21:45,  7.09s/it]
                                                         
{'loss': 0.7051, 'learning_rate': 0.0004978381001233428, 'epoch': 0.85}

  7%|▋         | 1984/28080 [3:54:57<51:21:45,  7.09s/it]
  7%|▋         | 1985/28080 [3:55:04<51:29:52,  7.10s/it]
                                                         
{'loss': 0.6971, 'learning_rate': 0.0004978343144631667, 'epoch': 0.85}

  7%|▋         | 1985/28080 [3:55:04<51:29:52,  7.10s/it]
  7%|▋         | 1986/28080 [3:55:11<51:35:53,  7.12s/it]
                                                         
{'loss': 0.6888, 'learning_rate': 0.0004978305255058108, 'epoch': 0.85}

  7%|▋         | 1986/28080 [3:55:11<51:35:53,  7.12s/it]
  7%|▋         | 1987/28080 [3:55:18<51:37:27,  7.12s/it]
                                                         
{'loss': 0.6959, 'learning_rate': 0.0004978267332513255, 'epoch': 0.85}

  7%|▋         | 1987/28080 [3:55:18<51:37:27,  7.12s/it]
  7%|▋         | 1988/28080 [3:55:25<51:38:44,  7.13s/it]
                                                         
{'loss': 0.6754, 'learning_rate': 0.000497822937699761, 'epoch': 0.85}

  7%|▋         | 1988/28080 [3:55:25<51:38:44,  7.13s/it]
  7%|▋         | 1989/28080 [3:55:33<51:39:03,  7.13s/it]
                                                         
{'loss': 0.6914, 'learning_rate': 0.0004978191388511681, 'epoch': 0.85}

  7%|▋         | 1989/28080 [3:55:33<51:39:03,  7.13s/it]
  7%|▋         | 1990/28080 [3:55:40<51:43:38,  7.14s/it]
                                                         
{'loss': 0.6876, 'learning_rate': 0.0004978153367055972, 'epoch': 0.85}

  7%|▋         | 1990/28080 [3:55:40<51:43:38,  7.14s/it]
  7%|▋         | 1991/28080 [3:55:47<51:29:31,  7.11s/it]
                                                         
{'loss': 0.7022, 'learning_rate': 0.000497811531263099, 'epoch': 0.85}

  7%|▋         | 1991/28080 [3:55:47<51:29:31,  7.11s/it]
  7%|▋         | 1992/28080 [3:55:54<51:28:57,  7.10s/it]
                                                         
{'loss': 0.7002, 'learning_rate': 0.0004978077225237239, 'epoch': 0.85}

  7%|▋         | 1992/28080 [3:55:54<51:28:57,  7.10s/it]
  7%|▋         | 1993/28080 [3:56:01<51:20:13,  7.08s/it]
                                                         
{'loss': 0.6941, 'learning_rate': 0.0004978039104875227, 'epoch': 0.85}

  7%|▋         | 1993/28080 [3:56:01<51:20:13,  7.08s/it]
  7%|▋         | 1994/28080 [3:56:08<51:17:56,  7.08s/it]
                                                         
{'loss': 0.7129, 'learning_rate': 0.0004978000951545462, 'epoch': 0.85}

  7%|▋         | 1994/28080 [3:56:08<51:17:56,  7.08s/it]
  7%|▋         | 1995/28080 [3:56:15<51:21:08,  7.09s/it]
                                                         
{'loss': 0.6902, 'learning_rate': 0.0004977962765248449, 'epoch': 0.85}

  7%|▋         | 1995/28080 [3:56:15<51:21:08,  7.09s/it]
  7%|▋         | 1996/28080 [3:56:22<51:24:55,  7.10s/it]
                                                         
{'loss': 0.7109, 'learning_rate': 0.00049779245459847, 'epoch': 0.85}

  7%|▋         | 1996/28080 [3:56:22<51:24:55,  7.10s/it]
  7%|▋         | 1997/28080 [3:56:29<51:29:53,  7.11s/it]
                                                         
{'loss': 0.6799, 'learning_rate': 0.000497788629375472, 'epoch': 0.85}

  7%|▋         | 1997/28080 [3:56:29<51:29:53,  7.11s/it]
  7%|▋         | 1998/28080 [3:56:36<51:30:30,  7.11s/it]
                                                         
{'loss': 0.6988, 'learning_rate': 0.0004977848008559019, 'epoch': 0.85}

  7%|▋         | 1998/28080 [3:56:36<51:30:30,  7.11s/it]
  7%|▋         | 1999/28080 [3:56:44<51:33:27,  7.12s/it]
                                                         
{'loss': 0.7134, 'learning_rate': 0.0004977809690398107, 'epoch': 0.85}

  7%|▋         | 1999/28080 [3:56:44<51:33:27,  7.12s/it]
  7%|▋         | 2000/28080 [3:56:51<51:27:37,  7.10s/it]
                                                         
{'loss': 0.6889, 'learning_rate': 0.0004977771339272493, 'epoch': 0.85}

  7%|▋         | 2000/28080 [3:56:51<51:27:37,  7.10s/it]
  7%|▋         | 2001/28080 [3:56:58<51:34:36,  7.12s/it]
                                                         
{'loss': 0.6907, 'learning_rate': 0.0004977732955182688, 'epoch': 0.85}

  7%|▋         | 2001/28080 [3:56:58<51:34:36,  7.12s/it]
  7%|▋         | 2002/28080 [3:57:05<51:37:24,  7.13s/it]
                                                         
{'loss': 0.7037, 'learning_rate': 0.0004977694538129202, 'epoch': 0.86}

  7%|▋         | 2002/28080 [3:57:05<51:37:24,  7.13s/it]
  7%|▋         | 2003/28080 [3:57:12<51:25:27,  7.10s/it]
                                                         
{'loss': 0.6907, 'learning_rate': 0.0004977656088112546, 'epoch': 0.86}

  7%|▋         | 2003/28080 [3:57:12<51:25:27,  7.10s/it]
  7%|▋         | 2004/28080 [3:57:19<51:14:58,  7.08s/it]
                                                         
{'loss': 0.7001, 'learning_rate': 0.0004977617605133232, 'epoch': 0.86}

  7%|▋         | 2004/28080 [3:57:19<51:14:58,  7.08s/it]
  7%|▋         | 2005/28080 [3:57:26<51:18:36,  7.08s/it]
                                                         
{'loss': 0.7041, 'learning_rate': 0.0004977579089191772, 'epoch': 0.86}

  7%|▋         | 2005/28080 [3:57:26<51:18:36,  7.08s/it]
  7%|▋         | 2006/28080 [3:57:33<51:22:56,  7.09s/it]
                                                         
{'loss': 0.6872, 'learning_rate': 0.0004977540540288677, 'epoch': 0.86}

  7%|▋         | 2006/28080 [3:57:33<51:22:56,  7.09s/it]
  7%|▋         | 2007/28080 [3:57:40<51:25:02,  7.10s/it]
                                                         
{'loss': 0.701, 'learning_rate': 0.0004977501958424462, 'epoch': 0.86}

  7%|▋         | 2007/28080 [3:57:40<51:25:02,  7.10s/it]
  7%|▋         | 2008/28080 [3:57:47<51:09:29,  7.06s/it]
                                                         
{'loss': 0.7024, 'learning_rate': 0.000497746334359964, 'epoch': 0.86}

  7%|▋         | 2008/28080 [3:57:47<51:09:29,  7.06s/it]
  7%|▋         | 2009/28080 [3:57:54<51:17:33,  7.08s/it]
                                                         
{'loss': 0.7061, 'learning_rate': 0.0004977424695814724, 'epoch': 0.86}

  7%|▋         | 2009/28080 [3:57:54<51:17:33,  7.08s/it]
  7%|▋         | 2010/28080 [3:58:02<51:21:43,  7.09s/it]
                                                         
{'loss': 0.6908, 'learning_rate': 0.0004977386015070227, 'epoch': 0.86}

  7%|▋         | 2010/28080 [3:58:02<51:21:43,  7.09s/it]
  7%|▋         | 2011/28080 [3:58:09<51:13:54,  7.07s/it]
                                                         
{'loss': 0.6998, 'learning_rate': 0.0004977347301366666, 'epoch': 0.86}

  7%|▋         | 2011/28080 [3:58:09<51:13:54,  7.07s/it]
  7%|▋         | 2012/28080 [3:58:16<51:34:16,  7.12s/it]
                                                         
{'loss': 0.6911, 'learning_rate': 0.0004977308554704554, 'epoch': 0.86}

  7%|▋         | 2012/28080 [3:58:16<51:34:16,  7.12s/it]
  7%|▋         | 2013/28080 [3:58:23<51:38:20,  7.13s/it]
                                                         
{'loss': 0.7039, 'learning_rate': 0.0004977269775084407, 'epoch': 0.86}

  7%|▋         | 2013/28080 [3:58:23<51:38:20,  7.13s/it]
  7%|▋         | 2014/28080 [3:58:30<51:42:32,  7.14s/it]
                                                         
{'loss': 0.6996, 'learning_rate': 0.0004977230962506743, 'epoch': 0.86}

  7%|▋         | 2014/28080 [3:58:30<51:42:32,  7.14s/it]
  7%|▋         | 2015/28080 [3:58:37<51:42:22,  7.14s/it]
                                                         
{'loss': 0.6931, 'learning_rate': 0.0004977192116972076, 'epoch': 0.86}

  7%|▋         | 2015/28080 [3:58:37<51:42:22,  7.14s/it]
  7%|▋         | 2016/28080 [3:58:44<51:49:08,  7.16s/it]
                                                         
{'loss': 0.7052, 'learning_rate': 0.0004977153238480923, 'epoch': 0.86}

  7%|▋         | 2016/28080 [3:58:44<51:49:08,  7.16s/it]
  7%|▋         | 2017/28080 [3:58:52<51:48:18,  7.16s/it]
                                                         
{'loss': 0.6981, 'learning_rate': 0.0004977114327033801, 'epoch': 0.86}

  7%|▋         | 2017/28080 [3:58:52<51:48:18,  7.16s/it]
  7%|▋         | 2018/28080 [3:58:59<51:53:31,  7.17s/it]
                                                         
{'loss': 0.7085, 'learning_rate': 0.000497707538263123, 'epoch': 0.86}

  7%|▋         | 2018/28080 [3:58:59<51:53:31,  7.17s/it]
  7%|▋         | 2019/28080 [3:59:06<51:51:03,  7.16s/it]
                                                         
{'loss': 0.6931, 'learning_rate': 0.0004977036405273725, 'epoch': 0.86}

  7%|▋         | 2019/28080 [3:59:06<51:51:03,  7.16s/it]
  7%|▋         | 2020/28080 [3:59:13<52:09:19,  7.20s/it]
                                                         
{'loss': 0.6899, 'learning_rate': 0.0004976997394961806, 'epoch': 0.86}

  7%|▋         | 2020/28080 [3:59:13<52:09:19,  7.20s/it]
  7%|▋         | 2021/28080 [3:59:20<51:56:52,  7.18s/it]
                                                         
{'loss': 0.6846, 'learning_rate': 0.0004976958351695994, 'epoch': 0.86}

  7%|▋         | 2021/28080 [3:59:20<51:56:52,  7.18s/it]
  7%|▋         | 2022/28080 [3:59:27<51:48:42,  7.16s/it]
                                                         
{'loss': 0.6774, 'learning_rate': 0.0004976919275476805, 'epoch': 0.86}

  7%|▋         | 2022/28080 [3:59:28<51:48:42,  7.16s/it]
  7%|▋         | 2023/28080 [3:59:35<51:42:45,  7.14s/it]
                                                         
{'loss': 0.6734, 'learning_rate': 0.0004976880166304761, 'epoch': 0.86}

  7%|▋         | 2023/28080 [3:59:35<51:42:45,  7.14s/it]
  7%|▋         | 2024/28080 [3:59:42<51:45:10,  7.15s/it]
                                                         
{'loss': 0.6876, 'learning_rate': 0.0004976841024180381, 'epoch': 0.86}

  7%|▋         | 2024/28080 [3:59:42<51:45:10,  7.15s/it]
  7%|▋         | 2025/28080 [3:59:49<51:44:11,  7.15s/it]
                                                         
{'loss': 0.6846, 'learning_rate': 0.0004976801849104187, 'epoch': 0.87}

  7%|▋         | 2025/28080 [3:59:49<51:44:11,  7.15s/it]
  7%|▋         | 2026/28080 [3:59:56<51:22:41,  7.10s/it]
                                                         
{'loss': 0.7131, 'learning_rate': 0.0004976762641076698, 'epoch': 0.87}

  7%|▋         | 2026/28080 [3:59:56<51:22:41,  7.10s/it]
  7%|▋         | 2027/28080 [4:00:03<51:30:57,  7.12s/it]
                                                         
{'loss': 0.6897, 'learning_rate': 0.000497672340009844, 'epoch': 0.87}

  7%|▋         | 2027/28080 [4:00:03<51:30:57,  7.12s/it]
  7%|▋         | 2028/28080 [4:00:10<51:37:02,  7.13s/it]
                                                         
{'loss': 0.7118, 'learning_rate': 0.000497668412616993, 'epoch': 0.87}

  7%|▋         | 2028/28080 [4:00:10<51:37:02,  7.13s/it]
  7%|▋         | 2029/28080 [4:00:17<51:45:29,  7.15s/it]
                                                         
{'loss': 0.685, 'learning_rate': 0.0004976644819291694, 'epoch': 0.87}

  7%|▋         | 2029/28080 [4:00:17<51:45:29,  7.15s/it]
  7%|▋         | 2030/28080 [4:00:25<51:46:36,  7.16s/it]
                                                         
{'loss': 0.6896, 'learning_rate': 0.0004976605479464252, 'epoch': 0.87}

  7%|▋         | 2030/28080 [4:00:25<51:46:36,  7.16s/it]
  7%|▋         | 2031/28080 [4:00:32<51:51:02,  7.17s/it]
                                                         
{'loss': 0.6922, 'learning_rate': 0.0004976566106688131, 'epoch': 0.87}

  7%|▋         | 2031/28080 [4:00:32<51:51:02,  7.17s/it]
  7%|▋         | 2032/28080 [4:00:39<51:38:45,  7.14s/it]
                                                         
{'loss': 0.6858, 'learning_rate': 0.0004976526700963852, 'epoch': 0.87}

  7%|▋         | 2032/28080 [4:00:39<51:38:45,  7.14s/it]
  7%|▋         | 2033/28080 [4:00:46<51:43:04,  7.15s/it]
                                                         
{'loss': 0.6705, 'learning_rate': 0.000497648726229194, 'epoch': 0.87}

  7%|▋         | 2033/28080 [4:00:46<51:43:04,  7.15s/it]
  7%|▋         | 2034/28080 [4:00:53<51:44:38,  7.15s/it]
                                                         
{'loss': 0.6897, 'learning_rate': 0.000497644779067292, 'epoch': 0.87}

  7%|▋         | 2034/28080 [4:00:53<51:44:38,  7.15s/it]
  7%|▋         | 2035/28080 [4:01:00<51:43:09,  7.15s/it]
                                                         
{'loss': 0.6965, 'learning_rate': 0.0004976408286107317, 'epoch': 0.87}

  7%|▋         | 2035/28080 [4:01:00<51:43:09,  7.15s/it]
  7%|▋         | 2036/28080 [4:01:08<51:47:13,  7.16s/it]
                                                         
{'loss': 0.6865, 'learning_rate': 0.0004976368748595656, 'epoch': 0.87}

  7%|▋         | 2036/28080 [4:01:08<51:47:13,  7.16s/it]
  7%|▋         | 2037/28080 [4:01:15<51:37:50,  7.14s/it]
                                                         
{'loss': 0.6961, 'learning_rate': 0.0004976329178138464, 'epoch': 0.87}

  7%|▋         | 2037/28080 [4:01:15<51:37:50,  7.14s/it]
  7%|▋         | 2038/28080 [4:01:22<51:23:43,  7.10s/it]
                                                         
{'loss': 0.6965, 'learning_rate': 0.0004976289574736267, 'epoch': 0.87}

  7%|▋         | 2038/28080 [4:01:22<51:23:43,  7.10s/it]
  7%|▋         | 2039/28080 [4:01:29<51:39:33,  7.14s/it]
                                                         
{'loss': 0.7044, 'learning_rate': 0.0004976249938389592, 'epoch': 0.87}

  7%|▋         | 2039/28080 [4:01:29<51:39:33,  7.14s/it]
  7%|▋         | 2040/28080 [4:01:36<51:29:36,  7.12s/it]
                                                         
{'loss': 0.701, 'learning_rate': 0.0004976210269098967, 'epoch': 0.87}

  7%|▋         | 2040/28080 [4:01:36<51:29:36,  7.12s/it]
  7%|▋         | 2041/28080 [4:01:43<51:20:40,  7.10s/it]
                                                         
{'loss': 0.7116, 'learning_rate': 0.0004976170566864917, 'epoch': 0.87}

  7%|▋         | 2041/28080 [4:01:43<51:20:40,  7.10s/it]
  7%|▋         | 2042/28080 [4:01:50<51:26:28,  7.11s/it]
                                                         
{'loss': 0.6799, 'learning_rate': 0.0004976130831687973, 'epoch': 0.87}

  7%|▋         | 2042/28080 [4:01:50<51:26:28,  7.11s/it]
  7%|▋         | 2043/28080 [4:01:57<51:28:27,  7.12s/it]
                                                         
{'loss': 0.6869, 'learning_rate': 0.0004976091063568663, 'epoch': 0.87}

  7%|▋         | 2043/28080 [4:01:57<51:28:27,  7.12s/it]
  7%|▋         | 2044/28080 [4:02:04<51:17:37,  7.09s/it]
                                                         
{'loss': 0.7085, 'learning_rate': 0.0004976051262507516, 'epoch': 0.87}

  7%|▋         | 2044/28080 [4:02:04<51:17:37,  7.09s/it]
  7%|▋         | 2045/28080 [4:02:11<51:20:57,  7.10s/it]
                                                         
{'loss': 0.6998, 'learning_rate': 0.000497601142850506, 'epoch': 0.87}

  7%|▋         | 2045/28080 [4:02:11<51:20:57,  7.10s/it]
  7%|▋         | 2046/28080 [4:02:19<51:35:00,  7.13s/it]
                                                         
{'loss': 0.6801, 'learning_rate': 0.0004975971561561828, 'epoch': 0.87}

  7%|▋         | 2046/28080 [4:02:19<51:35:00,  7.13s/it]
  7%|▋         | 2047/28080 [4:02:26<51:28:52,  7.12s/it]
                                                         
{'loss': 0.6717, 'learning_rate': 0.0004975931661678348, 'epoch': 0.87}

  7%|▋         | 2047/28080 [4:02:26<51:28:52,  7.12s/it]
  7%|▋         | 2048/28080 [4:02:33<51:28:46,  7.12s/it]
                                                         
{'loss': 0.68, 'learning_rate': 0.0004975891728855151, 'epoch': 0.87}

  7%|▋         | 2048/28080 [4:02:33<51:28:46,  7.12s/it]
  7%|▋         | 2049/28080 [4:02:40<51:41:30,  7.15s/it]
                                                         
{'loss': 0.6953, 'learning_rate': 0.000497585176309277, 'epoch': 0.88}

  7%|▋         | 2049/28080 [4:02:40<51:41:30,  7.15s/it]
  7%|▋         | 2050/28080 [4:02:47<51:49:23,  7.17s/it]
                                                         
{'loss': 0.6696, 'learning_rate': 0.0004975811764391735, 'epoch': 0.88}

  7%|▋         | 2050/28080 [4:02:47<51:49:23,  7.17s/it]
  7%|▋         | 2051/28080 [4:02:54<51:50:59,  7.17s/it]
                                                         
{'loss': 0.6786, 'learning_rate': 0.0004975771732752579, 'epoch': 0.88}

  7%|▋         | 2051/28080 [4:02:54<51:50:59,  7.17s/it]
  7%|▋         | 2052/28080 [4:03:02<52:01:13,  7.20s/it]
                                                         
{'loss': 0.6621, 'learning_rate': 0.0004975731668175833, 'epoch': 0.88}

  7%|▋         | 2052/28080 [4:03:02<52:01:13,  7.20s/it]
  7%|▋         | 2053/28080 [4:03:09<51:56:27,  7.18s/it]
                                                         
{'loss': 0.716, 'learning_rate': 0.0004975691570662033, 'epoch': 0.88}

  7%|▋         | 2053/28080 [4:03:09<51:56:27,  7.18s/it]
  7%|▋         | 2054/28080 [4:03:16<51:32:12,  7.13s/it]
                                                         
{'loss': 0.6903, 'learning_rate': 0.0004975651440211708, 'epoch': 0.88}

  7%|▋         | 2054/28080 [4:03:16<51:32:12,  7.13s/it]
  7%|▋         | 2055/28080 [4:03:23<51:37:28,  7.14s/it]
                                                         
{'loss': 0.7091, 'learning_rate': 0.0004975611276825397, 'epoch': 0.88}

  7%|▋         | 2055/28080 [4:03:23<51:37:28,  7.14s/it]
  7%|▋         | 2056/28080 [4:03:30<51:41:04,  7.15s/it]
                                                         
{'loss': 0.6829, 'learning_rate': 0.0004975571080503631, 'epoch': 0.88}

  7%|▋         | 2056/28080 [4:03:30<51:41:04,  7.15s/it]
  7%|▋         | 2057/28080 [4:03:37<51:35:54,  7.14s/it]
                                                         
{'loss': 0.6937, 'learning_rate': 0.0004975530851246946, 'epoch': 0.88}

  7%|▋         | 2057/28080 [4:03:37<51:35:54,  7.14s/it]
  7%|▋         | 2058/28080 [4:03:44<51:27:14,  7.12s/it]
                                                         
{'loss': 0.701, 'learning_rate': 0.0004975490589055876, 'epoch': 0.88}

  7%|▋         | 2058/28080 [4:03:44<51:27:14,  7.12s/it]
  7%|▋         | 2059/28080 [4:03:51<51:29:53,  7.12s/it]
                                                         
{'loss': 0.6707, 'learning_rate': 0.0004975450293930958, 'epoch': 0.88}

  7%|▋         | 2059/28080 [4:03:51<51:29:53,  7.12s/it]
  7%|▋         | 2060/28080 [4:03:59<51:21:58,  7.11s/it]
                                                         
{'loss': 0.6925, 'learning_rate': 0.0004975409965872728, 'epoch': 0.88}

  7%|▋         | 2060/28080 [4:03:59<51:21:58,  7.11s/it]
  7%|▋         | 2061/28080 [4:04:06<51:31:43,  7.13s/it]
                                                         
{'loss': 0.6804, 'learning_rate': 0.0004975369604881722, 'epoch': 0.88}

  7%|▋         | 2061/28080 [4:04:06<51:31:43,  7.13s/it]
  7%|▋         | 2062/28080 [4:04:13<51:33:12,  7.13s/it]
                                                         
{'loss': 0.6751, 'learning_rate': 0.0004975329210958477, 'epoch': 0.88}

  7%|▋         | 2062/28080 [4:04:13<51:33:12,  7.13s/it]
  7%|▋         | 2063/28080 [4:04:20<51:26:42,  7.12s/it]
                                                         
{'loss': 0.7213, 'learning_rate': 0.000497528878410353, 'epoch': 0.88}

  7%|▋         | 2063/28080 [4:04:20<51:26:42,  7.12s/it]
  7%|▋         | 2064/28080 [4:04:27<51:28:20,  7.12s/it]
                                                         
{'loss': 0.7063, 'learning_rate': 0.000497524832431742, 'epoch': 0.88}

  7%|▋         | 2064/28080 [4:04:27<51:28:20,  7.12s/it]
  7%|▋         | 2065/28080 [4:04:34<51:26:09,  7.12s/it]
                                                         
{'loss': 0.6925, 'learning_rate': 0.0004975207831600685, 'epoch': 0.88}

  7%|▋         | 2065/28080 [4:04:34<51:26:09,  7.12s/it]
  7%|▋         | 2066/28080 [4:04:41<51:19:18,  7.10s/it]
                                                         
{'loss': 0.7016, 'learning_rate': 0.0004975167305953863, 'epoch': 0.88}

  7%|▋         | 2066/28080 [4:04:41<51:19:18,  7.10s/it]
  7%|▋         | 2067/28080 [4:04:48<51:19:43,  7.10s/it]
                                                         
{'loss': 0.6763, 'learning_rate': 0.0004975126747377493, 'epoch': 0.88}

  7%|▋         | 2067/28080 [4:04:48<51:19:43,  7.10s/it]
  7%|▋         | 2068/28080 [4:04:56<51:42:07,  7.16s/it]
                                                         
{'loss': 0.7295, 'learning_rate': 0.0004975086155872115, 'epoch': 0.88}

  7%|▋         | 2068/28080 [4:04:56<51:42:07,  7.16s/it]
  7%|▋         | 2069/28080 [4:05:03<51:43:06,  7.16s/it]
                                                         
{'loss': 0.6926, 'learning_rate': 0.0004975045531438269, 'epoch': 0.88}

  7%|▋         | 2069/28080 [4:05:03<51:43:06,  7.16s/it]
  7%|▋         | 2070/28080 [4:05:10<51:42:10,  7.16s/it]
                                                         
{'loss': 0.6812, 'learning_rate': 0.0004975004874076496, 'epoch': 0.88}

  7%|▋         | 2070/28080 [4:05:10<51:42:10,  7.16s/it]
  7%|▋         | 2071/28080 [4:05:17<51:36:12,  7.14s/it]
                                                         
{'loss': 0.7073, 'learning_rate': 0.0004974964183787337, 'epoch': 0.88}

  7%|▋         | 2071/28080 [4:05:17<51:36:12,  7.14s/it]
  7%|▋         | 2072/28080 [4:05:24<51:41:41,  7.16s/it]
                                                         
{'loss': 0.6896, 'learning_rate': 0.0004974923460571332, 'epoch': 0.89}

  7%|▋         | 2072/28080 [4:05:24<51:41:41,  7.16s/it]
  7%|▋         | 2073/28080 [4:05:31<51:35:13,  7.14s/it]
                                                         
{'loss': 0.6932, 'learning_rate': 0.0004974882704429025, 'epoch': 0.89}

  7%|▋         | 2073/28080 [4:05:31<51:35:13,  7.14s/it]
  7%|▋         | 2074/28080 [4:05:38<51:30:00,  7.13s/it]
                                                         
{'loss': 0.6752, 'learning_rate': 0.0004974841915360954, 'epoch': 0.89}

  7%|▋         | 2074/28080 [4:05:38<51:30:00,  7.13s/it]
  7%|▋         | 2075/28080 [4:05:46<51:28:19,  7.13s/it]
                                                         
{'loss': 0.7052, 'learning_rate': 0.0004974801093367667, 'epoch': 0.89}

  7%|▋         | 2075/28080 [4:05:46<51:28:19,  7.13s/it]
  7%|▋         | 2076/28080 [4:05:53<51:22:35,  7.11s/it]
                                                         
{'loss': 0.6837, 'learning_rate': 0.0004974760238449703, 'epoch': 0.89}

  7%|▋         | 2076/28080 [4:05:53<51:22:35,  7.11s/it]
  7%|▋         | 2077/28080 [4:06:00<51:12:19,  7.09s/it]
                                                         
{'loss': 0.7006, 'learning_rate': 0.0004974719350607608, 'epoch': 0.89}

  7%|▋         | 2077/28080 [4:06:00<51:12:19,  7.09s/it]
  7%|▋         | 2078/28080 [4:06:07<51:18:28,  7.10s/it]
                                                         
{'loss': 0.6695, 'learning_rate': 0.0004974678429841926, 'epoch': 0.89}

  7%|▋         | 2078/28080 [4:06:07<51:18:28,  7.10s/it]
  7%|▋         | 2079/28080 [4:06:14<51:10:55,  7.09s/it]
                                                         
{'loss': 0.684, 'learning_rate': 0.0004974637476153199, 'epoch': 0.89}

  7%|▋         | 2079/28080 [4:06:14<51:10:55,  7.09s/it]
  7%|▋         | 2080/28080 [4:06:21<51:20:41,  7.11s/it]
                                                         
{'loss': 0.6842, 'learning_rate': 0.0004974596489541974, 'epoch': 0.89}

  7%|▋         | 2080/28080 [4:06:21<51:20:41,  7.11s/it]
  7%|▋         | 2081/28080 [4:06:28<51:27:03,  7.12s/it]
                                                         
{'loss': 0.6804, 'learning_rate': 0.0004974555470008794, 'epoch': 0.89}

  7%|▋         | 2081/28080 [4:06:28<51:27:03,  7.12s/it]
  7%|▋         | 2082/28080 [4:06:35<51:34:24,  7.14s/it]
                                                         
{'loss': 0.6619, 'learning_rate': 0.0004974514417554209, 'epoch': 0.89}

  7%|▋         | 2082/28080 [4:06:35<51:34:24,  7.14s/it]
  7%|▋         | 2083/28080 [4:06:43<51:32:58,  7.14s/it]
                                                         
{'loss': 0.6877, 'learning_rate': 0.0004974473332178761, 'epoch': 0.89}

  7%|▋         | 2083/28080 [4:06:43<51:32:58,  7.14s/it]
  7%|▋         | 2084/28080 [4:06:50<51:36:30,  7.15s/it]
                                                         
{'loss': 0.6988, 'learning_rate': 0.0004974432213882998, 'epoch': 0.89}

  7%|▋         | 2084/28080 [4:06:50<51:36:30,  7.15s/it]
  7%|▋         | 2085/28080 [4:06:57<51:40:46,  7.16s/it]
                                                         
{'loss': 0.7047, 'learning_rate': 0.0004974391062667467, 'epoch': 0.89}

  7%|▋         | 2085/28080 [4:06:57<51:40:46,  7.16s/it]
  7%|▋         | 2086/28080 [4:07:04<51:29:18,  7.13s/it]
                                                         
{'loss': 0.7136, 'learning_rate': 0.0004974349878532717, 'epoch': 0.89}

  7%|▋         | 2086/28080 [4:07:04<51:29:18,  7.13s/it]
  7%|▋         | 2087/28080 [4:07:11<51:46:29,  7.17s/it]
                                                         
{'loss': 0.6933, 'learning_rate': 0.0004974308661479293, 'epoch': 0.89}

  7%|▋         | 2087/28080 [4:07:11<51:46:29,  7.17s/it]
  7%|▋         | 2088/28080 [4:07:18<51:45:35,  7.17s/it]
                                                         
{'loss': 0.6814, 'learning_rate': 0.0004974267411507745, 'epoch': 0.89}

  7%|▋         | 2088/28080 [4:07:18<51:45:35,  7.17s/it]
  7%|▋         | 2089/28080 [4:07:26<51:40:53,  7.16s/it]
                                                         
{'loss': 0.672, 'learning_rate': 0.0004974226128618621, 'epoch': 0.89}

  7%|▋         | 2089/28080 [4:07:26<51:40:53,  7.16s/it]
  7%|▋         | 2090/28080 [4:07:33<51:23:00,  7.12s/it]
                                                         
{'loss': 0.6858, 'learning_rate': 0.0004974184812812473, 'epoch': 0.89}

  7%|▋         | 2090/28080 [4:07:33<51:23:00,  7.12s/it]
  7%|▋         | 2091/28080 [4:07:40<51:08:24,  7.08s/it]
                                                         
{'loss': 0.6771, 'learning_rate': 0.0004974143464089848, 'epoch': 0.89}

  7%|▋         | 2091/28080 [4:07:40<51:08:24,  7.08s/it]
  7%|▋         | 2092/28080 [4:07:47<51:15:15,  7.10s/it]
                                                         
{'loss': 0.6797, 'learning_rate': 0.0004974102082451295, 'epoch': 0.89}

  7%|▋         | 2092/28080 [4:07:47<51:15:15,  7.10s/it]
  7%|▋         | 2093/28080 [4:07:54<51:28:45,  7.13s/it]
                                                         
{'loss': 0.6958, 'learning_rate': 0.0004974060667897368, 'epoch': 0.89}

  7%|▋         | 2093/28080 [4:07:54<51:28:45,  7.13s/it]
  7%|▋         | 2094/28080 [4:08:01<51:37:17,  7.15s/it]
                                                         
{'loss': 0.6856, 'learning_rate': 0.0004974019220428615, 'epoch': 0.89}

  7%|▋         | 2094/28080 [4:08:01<51:37:17,  7.15s/it]
  7%|▋         | 2095/28080 [4:08:08<51:32:38,  7.14s/it]
                                                         
{'loss': 0.6688, 'learning_rate': 0.0004973977740045589, 'epoch': 0.89}

  7%|▋         | 2095/28080 [4:08:08<51:32:38,  7.14s/it]
  7%|▋         | 2096/28080 [4:08:15<51:34:01,  7.14s/it]
                                                         
{'loss': 0.7004, 'learning_rate': 0.000497393622674884, 'epoch': 0.9}

  7%|▋         | 2096/28080 [4:08:15<51:34:01,  7.14s/it]
  7%|▋         | 2097/28080 [4:08:22<51:21:43,  7.12s/it]
                                                         
{'loss': 0.6943, 'learning_rate': 0.0004973894680538924, 'epoch': 0.9}

  7%|▋         | 2097/28080 [4:08:22<51:21:43,  7.12s/it]
  7%|▋         | 2098/28080 [4:08:30<51:28:17,  7.13s/it]
                                                         
{'loss': 0.675, 'learning_rate': 0.0004973853101416391, 'epoch': 0.9}

  7%|▋         | 2098/28080 [4:08:30<51:28:17,  7.13s/it]
  7%|▋         | 2099/28080 [4:08:37<51:15:49,  7.10s/it]
                                                         
{'loss': 0.6958, 'learning_rate': 0.0004973811489381794, 'epoch': 0.9}

  7%|▋         | 2099/28080 [4:08:37<51:15:49,  7.10s/it]
  7%|▋         | 2100/28080 [4:08:44<51:15:14,  7.10s/it]
                                                         
{'loss': 0.6891, 'learning_rate': 0.0004973769844435688, 'epoch': 0.9}

  7%|▋         | 2100/28080 [4:08:44<51:15:14,  7.10s/it]
  7%|▋         | 2101/28080 [4:08:51<51:12:06,  7.10s/it]
                                                         
{'loss': 0.7051, 'learning_rate': 0.0004973728166578625, 'epoch': 0.9}

  7%|▋         | 2101/28080 [4:08:51<51:12:06,  7.10s/it]
  7%|▋         | 2102/28080 [4:08:58<51:15:20,  7.10s/it]
                                                         
{'loss': 0.6969, 'learning_rate': 0.0004973686455811161, 'epoch': 0.9}

  7%|▋         | 2102/28080 [4:08:58<51:15:20,  7.10s/it]
  7%|▋         | 2103/28080 [4:09:05<51:19:34,  7.11s/it]
                                                         
{'loss': 0.6918, 'learning_rate': 0.0004973644712133851, 'epoch': 0.9}

  7%|▋         | 2103/28080 [4:09:05<51:19:34,  7.11s/it]
  7%|▋         | 2104/28080 [4:09:12<51:19:16,  7.11s/it]
                                                         
{'loss': 0.7092, 'learning_rate': 0.000497360293554725, 'epoch': 0.9}

  7%|▋         | 2104/28080 [4:09:12<51:19:16,  7.11s/it]
  7%|▋         | 2105/28080 [4:09:19<51:07:38,  7.09s/it]
                                                         
{'loss': 0.7043, 'learning_rate': 0.0004973561126051915, 'epoch': 0.9}

  7%|▋         | 2105/28080 [4:09:19<51:07:38,  7.09s/it]
  8%|▊         | 2106/28080 [4:09:26<51:15:29,  7.10s/it]
                                                         
{'loss': 0.6915, 'learning_rate': 0.0004973519283648399, 'epoch': 0.9}

  8%|▊         | 2106/28080 [4:09:26<51:15:29,  7.10s/it]
  8%|▊         | 2107/28080 [4:09:33<51:14:31,  7.10s/it]
                                                         
{'loss': 0.6851, 'learning_rate': 0.0004973477408337262, 'epoch': 0.9}

  8%|▊         | 2107/28080 [4:09:33<51:14:31,  7.10s/it]
  8%|▊         | 2108/28080 [4:09:40<50:58:37,  7.07s/it]
                                                         
{'loss': 0.7202, 'learning_rate': 0.0004973435500119059, 'epoch': 0.9}

  8%|▊         | 2108/28080 [4:09:40<50:58:37,  7.07s/it]
  8%|▊         | 2109/28080 [4:09:48<51:05:01,  7.08s/it]
                                                         
{'loss': 0.6763, 'learning_rate': 0.0004973393558994349, 'epoch': 0.9}

  8%|▊         | 2109/28080 [4:09:48<51:05:01,  7.08s/it]
  8%|▊         | 2110/28080 [4:09:55<51:01:02,  7.07s/it]
                                                         
{'loss': 0.6772, 'learning_rate': 0.0004973351584963689, 'epoch': 0.9}

  8%|▊         | 2110/28080 [4:09:55<51:01:02,  7.07s/it]
  8%|▊         | 2111/28080 [4:10:02<51:08:38,  7.09s/it]
                                                         
{'loss': 0.6785, 'learning_rate': 0.0004973309578027638, 'epoch': 0.9}

  8%|▊         | 2111/28080 [4:10:02<51:08:38,  7.09s/it]
  8%|▊         | 2112/28080 [4:10:09<51:01:39,  7.07s/it]
                                                         
{'loss': 0.6828, 'learning_rate': 0.0004973267538186755, 'epoch': 0.9}

  8%|▊         | 2112/28080 [4:10:09<51:01:39,  7.07s/it]
  8%|▊         | 2113/28080 [4:10:16<51:00:49,  7.07s/it]
                                                         
{'loss': 0.672, 'learning_rate': 0.0004973225465441599, 'epoch': 0.9}

  8%|▊         | 2113/28080 [4:10:16<51:00:49,  7.07s/it]
  8%|▊         | 2114/28080 [4:10:23<51:06:17,  7.09s/it]
                                                         
{'loss': 0.7182, 'learning_rate': 0.0004973183359792729, 'epoch': 0.9}

  8%|▊         | 2114/28080 [4:10:23<51:06:17,  7.09s/it]
  8%|▊         | 2115/28080 [4:10:30<50:53:52,  7.06s/it]
                                                         
{'loss': 0.707, 'learning_rate': 0.0004973141221240705, 'epoch': 0.9}

  8%|▊         | 2115/28080 [4:10:30<50:53:52,  7.06s/it]
  8%|▊         | 2116/28080 [4:10:37<50:52:50,  7.05s/it]
                                                         
{'loss': 0.7002, 'learning_rate': 0.000497309904978609, 'epoch': 0.9}

  8%|▊         | 2116/28080 [4:10:37<50:52:50,  7.05s/it]
  8%|▊         | 2117/28080 [4:10:44<50:50:24,  7.05s/it]
                                                         
{'loss': 0.6853, 'learning_rate': 0.0004973056845429443, 'epoch': 0.9}

  8%|▊         | 2117/28080 [4:10:44<50:50:24,  7.05s/it]
  8%|▊         | 2118/28080 [4:10:51<50:55:44,  7.06s/it]
                                                         
{'loss': 0.6813, 'learning_rate': 0.0004973014608171327, 'epoch': 0.9}

  8%|▊         | 2118/28080 [4:10:51<50:55:44,  7.06s/it]
  8%|▊         | 2119/28080 [4:10:58<51:01:13,  7.07s/it]
                                                         
{'loss': 0.6865, 'learning_rate': 0.0004972972338012302, 'epoch': 0.91}

  8%|▊         | 2119/28080 [4:10:58<51:01:13,  7.07s/it]
  8%|▊         | 2120/28080 [4:11:05<50:59:41,  7.07s/it]
                                                         
{'loss': 0.6944, 'learning_rate': 0.000497293003495293, 'epoch': 0.91}

  8%|▊         | 2120/28080 [4:11:05<50:59:41,  7.07s/it]
  8%|▊         | 2121/28080 [4:11:12<51:00:25,  7.07s/it]
                                                         
{'loss': 0.6918, 'learning_rate': 0.0004972887698993777, 'epoch': 0.91}

  8%|▊         | 2121/28080 [4:11:12<51:00:25,  7.07s/it]
  8%|▊         | 2122/28080 [4:11:19<50:58:20,  7.07s/it]
                                                         
{'loss': 0.7156, 'learning_rate': 0.0004972845330135404, 'epoch': 0.91}

  8%|▊         | 2122/28080 [4:11:19<50:58:20,  7.07s/it]
  8%|▊         | 2123/28080 [4:11:26<51:02:32,  7.08s/it]
                                                         
{'loss': 0.6779, 'learning_rate': 0.0004972802928378374, 'epoch': 0.91}

  8%|▊         | 2123/28080 [4:11:27<51:02:32,  7.08s/it]
  8%|▊         | 2124/28080 [4:11:34<51:11:44,  7.10s/it]
                                                         
{'loss': 0.7017, 'learning_rate': 0.0004972760493723253, 'epoch': 0.91}

  8%|▊         | 2124/28080 [4:11:34<51:11:44,  7.10s/it]
  8%|▊         | 2125/28080 [4:11:41<51:12:12,  7.10s/it]
                                                         
{'loss': 0.6901, 'learning_rate': 0.0004972718026170604, 'epoch': 0.91}

  8%|▊         | 2125/28080 [4:11:41<51:12:12,  7.10s/it]
  8%|▊         | 2126/28080 [4:11:48<51:02:42,  7.08s/it]
                                                         
{'loss': 0.6998, 'learning_rate': 0.0004972675525720993, 'epoch': 0.91}

  8%|▊         | 2126/28080 [4:11:48<51:02:42,  7.08s/it]
  8%|▊         | 2127/28080 [4:11:55<51:12:44,  7.10s/it]
                                                         
{'loss': 0.7065, 'learning_rate': 0.0004972632992374985, 'epoch': 0.91}

  8%|▊         | 2127/28080 [4:11:55<51:12:44,  7.10s/it]
  8%|▊         | 2128/28080 [4:12:02<51:20:21,  7.12s/it]
                                                         
{'loss': 0.6743, 'learning_rate': 0.0004972590426133146, 'epoch': 0.91}

  8%|▊         | 2128/28080 [4:12:02<51:20:21,  7.12s/it]
  8%|▊         | 2129/28080 [4:12:09<51:03:31,  7.08s/it]
                                                         
{'loss': 0.6928, 'learning_rate': 0.0004972547826996042, 'epoch': 0.91}

  8%|▊         | 2129/28080 [4:12:09<51:03:31,  7.08s/it]
  8%|▊         | 2130/28080 [4:12:16<51:09:59,  7.10s/it]
                                                         
{'loss': 0.6898, 'learning_rate': 0.0004972505194964239, 'epoch': 0.91}

  8%|▊         | 2130/28080 [4:12:16<51:09:59,  7.10s/it]
  8%|▊         | 2131/28080 [4:12:23<51:17:34,  7.12s/it]
                                                         
{'loss': 0.6771, 'learning_rate': 0.0004972462530038307, 'epoch': 0.91}

  8%|▊         | 2131/28080 [4:12:23<51:17:34,  7.12s/it]
  8%|▊         | 2132/28080 [4:12:30<51:05:27,  7.09s/it]
                                                         
{'loss': 0.6995, 'learning_rate': 0.000497241983221881, 'epoch': 0.91}

  8%|▊         | 2132/28080 [4:12:30<51:05:27,  7.09s/it]
  8%|▊         | 2133/28080 [4:12:37<51:00:53,  7.08s/it]
                                                         
{'loss': 0.686, 'learning_rate': 0.0004972377101506319, 'epoch': 0.91}

  8%|▊         | 2133/28080 [4:12:37<51:00:53,  7.08s/it]
  8%|▊         | 2134/28080 [4:12:44<50:49:42,  7.05s/it]
                                                         
{'loss': 0.7043, 'learning_rate': 0.0004972334337901401, 'epoch': 0.91}

  8%|▊         | 2134/28080 [4:12:44<50:49:42,  7.05s/it]
  8%|▊         | 2135/28080 [4:12:52<51:02:04,  7.08s/it]
                                                         
{'loss': 0.686, 'learning_rate': 0.0004972291541404625, 'epoch': 0.91}

  8%|▊         | 2135/28080 [4:12:52<51:02:04,  7.08s/it]
  8%|▊         | 2136/28080 [4:12:59<51:03:39,  7.09s/it]
                                                         
{'loss': 0.6995, 'learning_rate': 0.0004972248712016561, 'epoch': 0.91}

  8%|▊         | 2136/28080 [4:12:59<51:03:39,  7.09s/it]
  8%|▊         | 2137/28080 [4:13:06<51:11:56,  7.10s/it]
                                                         
{'loss': 0.7004, 'learning_rate': 0.0004972205849737778, 'epoch': 0.91}

  8%|▊         | 2137/28080 [4:13:06<51:11:56,  7.10s/it]
  8%|▊         | 2138/28080 [4:13:13<51:03:33,  7.09s/it]
                                                         
{'loss': 0.7171, 'learning_rate': 0.0004972162954568846, 'epoch': 0.91}

  8%|▊         | 2138/28080 [4:13:13<51:03:33,  7.09s/it]
  8%|▊         | 2139/28080 [4:13:20<51:13:38,  7.11s/it]
                                                         
{'loss': 0.6915, 'learning_rate': 0.0004972120026510337, 'epoch': 0.91}

  8%|▊         | 2139/28080 [4:13:20<51:13:38,  7.11s/it]
  8%|▊         | 2140/28080 [4:13:27<51:19:23,  7.12s/it]
                                                         
{'loss': 0.6966, 'learning_rate': 0.0004972077065562821, 'epoch': 0.91}

  8%|▊         | 2140/28080 [4:13:27<51:19:23,  7.12s/it]
  8%|▊         | 2141/28080 [4:13:34<51:09:59,  7.10s/it]
                                                         
{'loss': 0.7268, 'learning_rate': 0.000497203407172687, 'epoch': 0.91}

  8%|▊         | 2141/28080 [4:13:34<51:09:59,  7.10s/it]
  8%|▊         | 2142/28080 [4:13:41<51:14:30,  7.11s/it]
                                                         
{'loss': 0.7023, 'learning_rate': 0.0004971991045003057, 'epoch': 0.92}

  8%|▊         | 2142/28080 [4:13:41<51:14:30,  7.11s/it]
  8%|▊         | 2143/28080 [4:13:49<51:25:13,  7.14s/it]
                                                         
{'loss': 0.6746, 'learning_rate': 0.0004971947985391952, 'epoch': 0.92}

  8%|▊         | 2143/28080 [4:13:49<51:25:13,  7.14s/it]
  8%|▊         | 2144/28080 [4:13:56<51:08:51,  7.10s/it]
                                                         
{'loss': 0.6891, 'learning_rate': 0.000497190489289413, 'epoch': 0.92}

  8%|▊         | 2144/28080 [4:13:56<51:08:51,  7.10s/it]
  8%|▊         | 2145/28080 [4:14:03<51:10:38,  7.10s/it]
                                                         
{'loss': 0.679, 'learning_rate': 0.0004971861767510163, 'epoch': 0.92}

  8%|▊         | 2145/28080 [4:14:03<51:10:38,  7.10s/it]
  8%|▊         | 2146/28080 [4:14:10<51:03:50,  7.09s/it]
                                                         
{'loss': 0.682, 'learning_rate': 0.0004971818609240626, 'epoch': 0.92}

  8%|▊         | 2146/28080 [4:14:10<51:03:50,  7.09s/it]
  8%|▊         | 2147/28080 [4:14:17<51:18:28,  7.12s/it]
                                                         
{'loss': 0.7085, 'learning_rate': 0.0004971775418086092, 'epoch': 0.92}

  8%|▊         | 2147/28080 [4:14:17<51:18:28,  7.12s/it]
  8%|▊         | 2148/28080 [4:14:24<51:25:09,  7.14s/it]
                                                         
{'loss': 0.6525, 'learning_rate': 0.0004971732194047136, 'epoch': 0.92}

  8%|▊         | 2148/28080 [4:14:24<51:25:09,  7.14s/it]
  8%|▊         | 2149/28080 [4:14:31<51:31:15,  7.15s/it]
                                                         
{'loss': 0.673, 'learning_rate': 0.0004971688937124334, 'epoch': 0.92}

  8%|▊         | 2149/28080 [4:14:31<51:31:15,  7.15s/it]
  8%|▊         | 2150/28080 [4:14:38<51:30:21,  7.15s/it]
                                                         
{'loss': 0.6956, 'learning_rate': 0.0004971645647318259, 'epoch': 0.92}

  8%|▊         | 2150/28080 [4:14:38<51:30:21,  7.15s/it]
  8%|▊         | 2151/28080 [4:14:46<51:36:47,  7.17s/it]
                                                         
{'loss': 0.6759, 'learning_rate': 0.0004971602324629489, 'epoch': 0.92}

  8%|▊         | 2151/28080 [4:14:46<51:36:47,  7.17s/it]
  8%|▊         | 2152/28080 [4:14:53<51:36:53,  7.17s/it]
                                                         
{'loss': 0.6946, 'learning_rate': 0.00049715589690586, 'epoch': 0.92}

  8%|▊         | 2152/28080 [4:14:53<51:36:53,  7.17s/it]
  8%|▊         | 2153/28080 [4:15:00<51:35:02,  7.16s/it]
                                                         
{'loss': 0.7001, 'learning_rate': 0.0004971515580606169, 'epoch': 0.92}

  8%|▊         | 2153/28080 [4:15:00<51:35:02,  7.16s/it]
  8%|▊         | 2154/28080 [4:15:07<52:00:35,  7.22s/it]
                                                         
{'loss': 0.672, 'learning_rate': 0.0004971472159272773, 'epoch': 0.92}

  8%|▊         | 2154/28080 [4:15:07<52:00:35,  7.22s/it]
  8%|▊         | 2155/28080 [4:15:15<51:58:22,  7.22s/it]
                                                         
{'loss': 0.6848, 'learning_rate': 0.0004971428705058989, 'epoch': 0.92}

  8%|▊         | 2155/28080 [4:15:15<51:58:22,  7.22s/it]
  8%|▊         | 2156/28080 [4:15:22<51:41:51,  7.18s/it]
                                                         
{'loss': 0.6725, 'learning_rate': 0.0004971385217965396, 'epoch': 0.92}

  8%|▊         | 2156/28080 [4:15:22<51:41:51,  7.18s/it]
  8%|▊         | 2157/28080 [4:15:29<51:38:24,  7.17s/it]
                                                         
{'loss': 0.685, 'learning_rate': 0.0004971341697992572, 'epoch': 0.92}

  8%|▊         | 2157/28080 [4:15:29<51:38:24,  7.17s/it]
  8%|▊         | 2158/28080 [4:15:36<51:17:33,  7.12s/it]
                                                         
{'loss': 0.7096, 'learning_rate': 0.0004971298145141096, 'epoch': 0.92}

  8%|▊         | 2158/28080 [4:15:36<51:17:33,  7.12s/it]
  8%|▊         | 2159/28080 [4:15:43<51:17:14,  7.12s/it]
                                                         
{'loss': 0.6978, 'learning_rate': 0.0004971254559411549, 'epoch': 0.92}

  8%|▊         | 2159/28080 [4:15:43<51:17:14,  7.12s/it]
  8%|▊         | 2160/28080 [4:15:50<51:36:54,  7.17s/it]
                                                         
{'loss': 0.6738, 'learning_rate': 0.0004971210940804509, 'epoch': 0.92}

  8%|▊         | 2160/28080 [4:15:50<51:36:54,  7.17s/it]
  8%|▊         | 2161/28080 [4:15:57<51:42:56,  7.18s/it]
                                                         
{'loss': 0.6891, 'learning_rate': 0.0004971167289320556, 'epoch': 0.92}

  8%|▊         | 2161/28080 [4:15:57<51:42:56,  7.18s/it]
  8%|▊         | 2162/28080 [4:16:05<51:49:18,  7.20s/it]
                                                         
{'loss': 0.6969, 'learning_rate': 0.0004971123604960273, 'epoch': 0.92}

  8%|▊         | 2162/28080 [4:16:05<51:49:18,  7.20s/it]
  8%|▊         | 2163/28080 [4:16:12<51:42:54,  7.18s/it]
                                                         
{'loss': 0.6845, 'learning_rate': 0.0004971079887724239, 'epoch': 0.92}

  8%|▊         | 2163/28080 [4:16:12<51:42:54,  7.18s/it]
  8%|▊         | 2164/28080 [4:16:19<51:41:58,  7.18s/it]
                                                         
{'loss': 0.7067, 'learning_rate': 0.0004971036137613035, 'epoch': 0.92}

  8%|▊         | 2164/28080 [4:16:19<51:41:58,  7.18s/it]
  8%|▊         | 2165/28080 [4:16:26<51:34:07,  7.16s/it]
                                                         
{'loss': 0.6778, 'learning_rate': 0.0004970992354627246, 'epoch': 0.92}

  8%|▊         | 2165/28080 [4:16:26<51:34:07,  7.16s/it]
  8%|▊         | 2166/28080 [4:16:33<51:34:18,  7.16s/it]
                                                         
{'loss': 0.6892, 'learning_rate': 0.0004970948538767453, 'epoch': 0.93}

  8%|▊         | 2166/28080 [4:16:33<51:34:18,  7.16s/it]
  8%|▊         | 2167/28080 [4:16:40<51:18:44,  7.13s/it]
                                                         
{'loss': 0.6622, 'learning_rate': 0.0004970904690034238, 'epoch': 0.93}

  8%|▊         | 2167/28080 [4:16:40<51:18:44,  7.13s/it]
  8%|▊         | 2168/28080 [4:16:47<51:13:47,  7.12s/it]
                                                         
{'loss': 0.6761, 'learning_rate': 0.0004970860808428185, 'epoch': 0.93}

  8%|▊         | 2168/28080 [4:16:47<51:13:47,  7.12s/it]
  8%|▊         | 2169/28080 [4:16:55<51:17:59,  7.13s/it]
                                                         
{'loss': 0.6845, 'learning_rate': 0.000497081689394988, 'epoch': 0.93}

  8%|▊         | 2169/28080 [4:16:55<51:17:59,  7.13s/it]
  8%|▊         | 2170/28080 [4:17:02<51:25:55,  7.15s/it]
                                                         
{'loss': 0.6771, 'learning_rate': 0.0004970772946599904, 'epoch': 0.93}

  8%|▊         | 2170/28080 [4:17:02<51:25:55,  7.15s/it]
  8%|▊         | 2171/28080 [4:17:09<51:13:28,  7.12s/it]
                                                         
{'loss': 0.695, 'learning_rate': 0.0004970728966378843, 'epoch': 0.93}

  8%|▊         | 2171/28080 [4:17:09<51:13:28,  7.12s/it]
  8%|▊         | 2172/28080 [4:17:16<51:30:32,  7.16s/it]
                                                         
{'loss': 0.694, 'learning_rate': 0.0004970684953287282, 'epoch': 0.93}

  8%|▊         | 2172/28080 [4:17:16<51:30:32,  7.16s/it]
  8%|▊         | 2173/28080 [4:17:23<51:27:05,  7.15s/it]
                                                         
{'loss': 0.6792, 'learning_rate': 0.0004970640907325805, 'epoch': 0.93}

  8%|▊         | 2173/28080 [4:17:23<51:27:05,  7.15s/it]
  8%|▊         | 2174/28080 [4:17:30<51:25:49,  7.15s/it]
                                                         
{'loss': 0.6811, 'learning_rate': 0.0004970596828495001, 'epoch': 0.93}

  8%|▊         | 2174/28080 [4:17:30<51:25:49,  7.15s/it]
  8%|▊         | 2175/28080 [4:17:37<51:12:26,  7.12s/it]
                                                         
{'loss': 0.7023, 'learning_rate': 0.0004970552716795455, 'epoch': 0.93}

  8%|▊         | 2175/28080 [4:17:37<51:12:26,  7.12s/it]
  8%|▊         | 2176/28080 [4:17:45<51:23:26,  7.14s/it]
                                                         
{'loss': 0.6958, 'learning_rate': 0.0004970508572227754, 'epoch': 0.93}

  8%|▊         | 2176/28080 [4:17:45<51:23:26,  7.14s/it]
  8%|▊         | 2177/28080 [4:17:52<51:14:53,  7.12s/it]
                                                         
{'loss': 0.7075, 'learning_rate': 0.0004970464394792485, 'epoch': 0.93}

  8%|▊         | 2177/28080 [4:17:52<51:14:53,  7.12s/it]
  8%|▊         | 2178/28080 [4:17:59<51:06:30,  7.10s/it]
                                                         
{'loss': 0.7028, 'learning_rate': 0.0004970420184490235, 'epoch': 0.93}

  8%|▊         | 2178/28080 [4:17:59<51:06:30,  7.10s/it]
  8%|▊         | 2179/28080 [4:18:06<51:17:11,  7.13s/it]
                                                         
{'loss': 0.6904, 'learning_rate': 0.0004970375941321594, 'epoch': 0.93}

  8%|▊         | 2179/28080 [4:18:06<51:17:11,  7.13s/it]
  8%|▊         | 2180/28080 [4:18:13<50:51:29,  7.07s/it]
                                                         
{'loss': 0.7177, 'learning_rate': 0.0004970331665287149, 'epoch': 0.93}

  8%|▊         | 2180/28080 [4:18:13<50:51:29,  7.07s/it]
  8%|▊         | 2181/28080 [4:18:20<51:05:09,  7.10s/it]
                                                         
{'loss': 0.6975, 'learning_rate': 0.000497028735638749, 'epoch': 0.93}

  8%|▊         | 2181/28080 [4:18:20<51:05:09,  7.10s/it]
  8%|▊         | 2182/28080 [4:18:27<51:01:52,  7.09s/it]
                                                         
{'loss': 0.6998, 'learning_rate': 0.0004970243014623206, 'epoch': 0.93}

  8%|▊         | 2182/28080 [4:18:27<51:01:52,  7.09s/it]
  8%|▊         | 2183/28080 [4:18:34<51:13:00,  7.12s/it]
                                                         
{'loss': 0.6734, 'learning_rate': 0.0004970198639994887, 'epoch': 0.93}

  8%|▊         | 2183/28080 [4:18:34<51:13:00,  7.12s/it]
  8%|▊         | 2184/28080 [4:18:41<51:20:42,  7.14s/it]
                                                         
{'loss': 0.6974, 'learning_rate': 0.0004970154232503125, 'epoch': 0.93}

  8%|▊         | 2184/28080 [4:18:41<51:20:42,  7.14s/it]
  8%|▊         | 2185/28080 [4:18:49<51:16:54,  7.13s/it]
                                                         
{'loss': 0.6647, 'learning_rate': 0.0004970109792148507, 'epoch': 0.93}

  8%|▊         | 2185/28080 [4:18:49<51:16:54,  7.13s/it]
  8%|▊         | 2186/28080 [4:18:56<51:18:49,  7.13s/it]
                                                         
{'loss': 0.7, 'learning_rate': 0.0004970065318931628, 'epoch': 0.93}

  8%|▊         | 2186/28080 [4:18:56<51:18:49,  7.13s/it]
  8%|▊         | 2187/28080 [4:19:03<51:20:09,  7.14s/it]
                                                         
{'loss': 0.7013, 'learning_rate': 0.0004970020812853078, 'epoch': 0.93}

  8%|▊         | 2187/28080 [4:19:03<51:20:09,  7.14s/it]
  8%|▊         | 2188/28080 [4:19:10<51:20:47,  7.14s/it]
                                                         
{'loss': 0.6959, 'learning_rate': 0.0004969976273913448, 'epoch': 0.93}

  8%|▊         | 2188/28080 [4:19:10<51:20:47,  7.14s/it]
  8%|▊         | 2189/28080 [4:19:17<51:21:05,  7.14s/it]
                                                         
{'loss': 0.6921, 'learning_rate': 0.0004969931702113332, 'epoch': 0.94}

  8%|▊         | 2189/28080 [4:19:17<51:21:05,  7.14s/it]
  8%|▊         | 2190/28080 [4:19:24<51:11:45,  7.12s/it]
                                                         
{'loss': 0.6854, 'learning_rate': 0.0004969887097453325, 'epoch': 0.94}

  8%|▊         | 2190/28080 [4:19:24<51:11:45,  7.12s/it]
  8%|▊         | 2191/28080 [4:19:31<51:21:19,  7.14s/it]
                                                         
{'loss': 0.7094, 'learning_rate': 0.0004969842459934017, 'epoch': 0.94}

  8%|▊         | 2191/28080 [4:19:31<51:21:19,  7.14s/it]
  8%|▊         | 2192/28080 [4:19:39<51:26:44,  7.15s/it]
                                                         
{'loss': 0.6963, 'learning_rate': 0.0004969797789556001, 'epoch': 0.94}

  8%|▊         | 2192/28080 [4:19:39<51:26:44,  7.15s/it]
  8%|▊         | 2193/28080 [4:19:46<51:36:34,  7.18s/it]
                                                         
{'loss': 0.6818, 'learning_rate': 0.0004969753086319877, 'epoch': 0.94}

  8%|▊         | 2193/28080 [4:19:46<51:36:34,  7.18s/it]
  8%|▊         | 2194/28080 [4:19:53<51:17:32,  7.13s/it]
                                                         
{'loss': 0.6935, 'learning_rate': 0.0004969708350226233, 'epoch': 0.94}

  8%|▊         | 2194/28080 [4:19:53<51:17:32,  7.13s/it]
  8%|▊         | 2195/28080 [4:20:00<51:12:11,  7.12s/it]
                                                         
{'loss': 0.7091, 'learning_rate': 0.0004969663581275669, 'epoch': 0.94}

  8%|▊         | 2195/28080 [4:20:00<51:12:11,  7.12s/it]
  8%|▊         | 2196/28080 [4:20:07<51:17:17,  7.13s/it]
                                                         
{'loss': 0.6595, 'learning_rate': 0.0004969618779468778, 'epoch': 0.94}

  8%|▊         | 2196/28080 [4:20:07<51:17:17,  7.13s/it]
  8%|▊         | 2197/28080 [4:20:14<51:11:42,  7.12s/it]
                                                         
{'loss': 0.7009, 'learning_rate': 0.0004969573944806157, 'epoch': 0.94}

  8%|▊         | 2197/28080 [4:20:14<51:11:42,  7.12s/it]
  8%|▊         | 2198/28080 [4:20:21<51:08:22,  7.11s/it]
                                                         
{'loss': 0.6901, 'learning_rate': 0.0004969529077288404, 'epoch': 0.94}

  8%|▊         | 2198/28080 [4:20:21<51:08:22,  7.11s/it]
  8%|▊         | 2199/28080 [4:20:28<51:12:18,  7.12s/it]
                                                         
{'loss': 0.6898, 'learning_rate': 0.0004969484176916112, 'epoch': 0.94}

  8%|▊         | 2199/28080 [4:20:28<51:12:18,  7.12s/it]
  8%|▊         | 2200/28080 [4:20:36<51:19:05,  7.14s/it]
                                                         
{'loss': 0.691, 'learning_rate': 0.0004969439243689882, 'epoch': 0.94}

  8%|▊         | 2200/28080 [4:20:36<51:19:05,  7.14s/it]
  8%|▊         | 2201/28080 [4:20:43<51:30:09,  7.16s/it]
                                                         
{'loss': 0.7029, 'learning_rate': 0.000496939427761031, 'epoch': 0.94}

  8%|▊         | 2201/28080 [4:20:43<51:30:09,  7.16s/it]
  8%|▊         | 2202/28080 [4:20:50<51:34:46,  7.18s/it]
                                                         
{'loss': 0.7063, 'learning_rate': 0.0004969349278677995, 'epoch': 0.94}

  8%|▊         | 2202/28080 [4:20:50<51:34:46,  7.18s/it]
  8%|▊         | 2203/28080 [4:20:57<51:37:26,  7.18s/it]
                                                         
{'loss': 0.6895, 'learning_rate': 0.0004969304246893535, 'epoch': 0.94}

  8%|▊         | 2203/28080 [4:20:57<51:37:26,  7.18s/it]
  8%|▊         | 2204/28080 [4:21:04<51:38:45,  7.19s/it]
                                                         
{'loss': 0.6606, 'learning_rate': 0.0004969259182257529, 'epoch': 0.94}

  8%|▊         | 2204/28080 [4:21:04<51:38:45,  7.19s/it]
  8%|▊         | 2205/28080 [4:21:12<51:35:37,  7.18s/it]
                                                         
{'loss': 0.6952, 'learning_rate': 0.0004969214084770577, 'epoch': 0.94}

  8%|▊         | 2205/28080 [4:21:12<51:35:37,  7.18s/it]
  8%|▊         | 2206/28080 [4:21:19<51:10:02,  7.12s/it]
                                                         
{'loss': 0.7097, 'learning_rate': 0.000496916895443328, 'epoch': 0.94}

  8%|▊         | 2206/28080 [4:21:19<51:10:02,  7.12s/it]
  8%|▊         | 2207/28080 [4:21:26<51:13:49,  7.13s/it]
                                                         
{'loss': 0.6916, 'learning_rate': 0.0004969123791246237, 'epoch': 0.94}

  8%|▊         | 2207/28080 [4:21:26<51:13:49,  7.13s/it]
  8%|▊         | 2208/28080 [4:21:33<51:23:13,  7.15s/it]
                                                         
{'loss': 0.6847, 'learning_rate': 0.0004969078595210048, 'epoch': 0.94}

  8%|▊         | 2208/28080 [4:21:33<51:23:13,  7.15s/it]
  8%|▊         | 2209/28080 [4:21:40<51:21:36,  7.15s/it]
                                                         
{'loss': 0.69, 'learning_rate': 0.0004969033366325318, 'epoch': 0.94}

  8%|▊         | 2209/28080 [4:21:40<51:21:36,  7.15s/it]
  8%|▊         | 2210/28080 [4:21:47<51:26:54,  7.16s/it]
                                                         
{'loss': 0.6896, 'learning_rate': 0.0004968988104592644, 'epoch': 0.94}

  8%|▊         | 2210/28080 [4:21:47<51:26:54,  7.16s/it]
  8%|▊         | 2211/28080 [4:21:54<51:25:36,  7.16s/it]
                                                         
{'loss': 0.6937, 'learning_rate': 0.0004968942810012631, 'epoch': 0.94}

  8%|▊         | 2211/28080 [4:21:54<51:25:36,  7.16s/it]
  8%|▊         | 2212/28080 [4:22:02<51:26:27,  7.16s/it]
                                                         
{'loss': 0.6904, 'learning_rate': 0.000496889748258588, 'epoch': 0.94}

  8%|▊         | 2212/28080 [4:22:02<51:26:27,  7.16s/it]
  8%|▊         | 2213/28080 [4:22:09<51:24:29,  7.15s/it]
                                                         
{'loss': 0.6951, 'learning_rate': 0.0004968852122312997, 'epoch': 0.95}

  8%|▊         | 2213/28080 [4:22:09<51:24:29,  7.15s/it]
  8%|▊         | 2214/28080 [4:22:16<51:35:31,  7.18s/it]
                                                         
{'loss': 0.6927, 'learning_rate': 0.0004968806729194582, 'epoch': 0.95}

  8%|▊         | 2214/28080 [4:22:16<51:35:31,  7.18s/it]
  8%|▊         | 2215/28080 [4:22:23<51:26:02,  7.16s/it]
                                                         
{'loss': 0.6977, 'learning_rate': 0.0004968761303231241, 'epoch': 0.95}

  8%|▊         | 2215/28080 [4:22:23<51:26:02,  7.16s/it]
  8%|▊         | 2216/28080 [4:22:30<51:18:29,  7.14s/it]
                                                         
{'loss': 0.6898, 'learning_rate': 0.0004968715844423578, 'epoch': 0.95}

  8%|▊         | 2216/28080 [4:22:30<51:18:29,  7.14s/it]
  8%|▊         | 2217/28080 [4:22:37<51:14:20,  7.13s/it]
                                                         
{'loss': 0.6745, 'learning_rate': 0.0004968670352772197, 'epoch': 0.95}

  8%|▊         | 2217/28080 [4:22:37<51:14:20,  7.13s/it]
  8%|▊         | 2218/28080 [4:22:44<51:18:07,  7.14s/it]
                                                         
{'loss': 0.6894, 'learning_rate': 0.0004968624828277704, 'epoch': 0.95}

  8%|▊         | 2218/28080 [4:22:44<51:18:07,  7.14s/it]
  8%|▊         | 2219/28080 [4:22:52<51:27:33,  7.16s/it]
                                                         
{'loss': 0.6827, 'learning_rate': 0.0004968579270940704, 'epoch': 0.95}

  8%|▊         | 2219/28080 [4:22:52<51:27:33,  7.16s/it]
  8%|▊         | 2220/28080 [4:22:59<51:24:28,  7.16s/it]
                                                         
{'loss': 0.6891, 'learning_rate': 0.0004968533680761804, 'epoch': 0.95}

  8%|▊         | 2220/28080 [4:22:59<51:24:28,  7.16s/it]
  8%|▊         | 2221/28080 [4:23:06<51:02:16,  7.11s/it]
                                                         
{'loss': 0.6947, 'learning_rate': 0.000496848805774161, 'epoch': 0.95}

  8%|▊         | 2221/28080 [4:23:06<51:02:16,  7.11s/it]
  8%|▊         | 2222/28080 [4:23:13<51:11:05,  7.13s/it]
                                                         
{'loss': 0.6825, 'learning_rate': 0.0004968442401880729, 'epoch': 0.95}

  8%|▊         | 2222/28080 [4:23:13<51:11:05,  7.13s/it]
  8%|▊         | 2223/28080 [4:23:20<51:20:30,  7.15s/it]
                                                         
{'loss': 0.676, 'learning_rate': 0.0004968396713179768, 'epoch': 0.95}

  8%|▊         | 2223/28080 [4:23:20<51:20:30,  7.15s/it]
  8%|▊         | 2224/28080 [4:23:27<51:08:58,  7.12s/it]
                                                         
{'loss': 0.6798, 'learning_rate': 0.0004968350991639335, 'epoch': 0.95}

  8%|▊         | 2224/28080 [4:23:27<51:08:58,  7.12s/it]
  8%|▊         | 2225/28080 [4:23:34<51:05:03,  7.11s/it]
                                                         
{'loss': 0.6806, 'learning_rate': 0.0004968305237260039, 'epoch': 0.95}

  8%|▊         | 2225/28080 [4:23:34<51:05:03,  7.11s/it]
  8%|▊         | 2226/28080 [4:23:41<51:00:05,  7.10s/it]
                                                         
{'loss': 0.6934, 'learning_rate': 0.0004968259450042489, 'epoch': 0.95}

  8%|▊         | 2226/28080 [4:23:41<51:00:05,  7.10s/it]
  8%|▊         | 2227/28080 [4:23:49<51:05:25,  7.11s/it]
                                                         
{'loss': 0.6991, 'learning_rate': 0.0004968213629987292, 'epoch': 0.95}

  8%|▊         | 2227/28080 [4:23:49<51:05:25,  7.11s/it]
  8%|▊         | 2228/28080 [4:23:56<51:10:39,  7.13s/it]
                                                         
{'loss': 0.7009, 'learning_rate': 0.000496816777709506, 'epoch': 0.95}

  8%|▊         | 2228/28080 [4:23:56<51:10:39,  7.13s/it]
  8%|▊         | 2229/28080 [4:24:03<51:14:44,  7.14s/it]
                                                         
{'loss': 0.6806, 'learning_rate': 0.0004968121891366402, 'epoch': 0.95}

  8%|▊         | 2229/28080 [4:24:03<51:14:44,  7.14s/it]
  8%|▊         | 2230/28080 [4:24:10<51:20:12,  7.15s/it]
                                                         
{'loss': 0.6946, 'learning_rate': 0.0004968075972801928, 'epoch': 0.95}

  8%|▊         | 2230/28080 [4:24:10<51:20:12,  7.15s/it]
  8%|▊         | 2231/28080 [4:24:17<51:20:20,  7.15s/it]
                                                         
{'loss': 0.6916, 'learning_rate': 0.0004968030021402249, 'epoch': 0.95}

  8%|▊         | 2231/28080 [4:24:17<51:20:20,  7.15s/it]
  8%|▊         | 2232/28080 [4:24:24<51:16:04,  7.14s/it]
                                                         
{'loss': 0.7065, 'learning_rate': 0.0004967984037167977, 'epoch': 0.95}

  8%|▊         | 2232/28080 [4:24:24<51:16:04,  7.14s/it]
  8%|▊         | 2233/28080 [4:24:31<51:10:47,  7.13s/it]
                                                         
{'loss': 0.7066, 'learning_rate': 0.0004967938020099724, 'epoch': 0.95}

  8%|▊         | 2233/28080 [4:24:31<51:10:47,  7.13s/it]
  8%|▊         | 2234/28080 [4:24:39<51:19:03,  7.15s/it]
                                                         
{'loss': 0.6903, 'learning_rate': 0.0004967891970198101, 'epoch': 0.95}

  8%|▊         | 2234/28080 [4:24:39<51:19:03,  7.15s/it]
  8%|▊         | 2235/28080 [4:24:46<51:33:12,  7.18s/it]
                                                         
{'loss': 0.6998, 'learning_rate': 0.0004967845887463721, 'epoch': 0.95}

  8%|▊         | 2235/28080 [4:24:46<51:33:12,  7.18s/it]
  8%|▊         | 2236/28080 [4:24:53<51:42:14,  7.20s/it]
                                                         
{'loss': 0.6817, 'learning_rate': 0.0004967799771897198, 'epoch': 0.96}

  8%|▊         | 2236/28080 [4:24:53<51:42:14,  7.20s/it]
  8%|▊         | 2237/28080 [4:25:00<51:44:30,  7.21s/it]
                                                         
{'loss': 0.6812, 'learning_rate': 0.0004967753623499145, 'epoch': 0.96}

  8%|▊         | 2237/28080 [4:25:00<51:44:30,  7.21s/it]
  8%|▊         | 2238/28080 [4:25:07<51:31:22,  7.18s/it]
                                                         
{'loss': 0.6978, 'learning_rate': 0.0004967707442270176, 'epoch': 0.96}

  8%|▊         | 2238/28080 [4:25:07<51:31:22,  7.18s/it]
  8%|▊         | 2239/28080 [4:25:15<51:33:23,  7.18s/it]
                                                         
{'loss': 0.6705, 'learning_rate': 0.0004967661228210905, 'epoch': 0.96}

  8%|▊         | 2239/28080 [4:25:15<51:33:23,  7.18s/it]
  8%|▊         | 2240/28080 [4:25:22<51:24:53,  7.16s/it]
                                                         
{'loss': 0.6872, 'learning_rate': 0.0004967614981321946, 'epoch': 0.96}

  8%|▊         | 2240/28080 [4:25:22<51:24:53,  7.16s/it]
  8%|▊         | 2241/28080 [4:25:29<51:19:13,  7.15s/it]
                                                         
{'loss': 0.697, 'learning_rate': 0.0004967568701603918, 'epoch': 0.96}

  8%|▊         | 2241/28080 [4:25:29<51:19:13,  7.15s/it]
  8%|▊         | 2242/28080 [4:25:36<51:22:31,  7.16s/it]
                                                         
{'loss': 0.7002, 'learning_rate': 0.0004967522389057432, 'epoch': 0.96}

  8%|▊         | 2242/28080 [4:25:36<51:22:31,  7.16s/it]
  8%|▊         | 2243/28080 [4:25:43<51:35:49,  7.19s/it]
                                                         
{'loss': 0.6987, 'learning_rate': 0.0004967476043683106, 'epoch': 0.96}

  8%|▊         | 2243/28080 [4:25:43<51:35:49,  7.19s/it]
  8%|▊         | 2244/28080 [4:25:50<51:31:26,  7.18s/it]
                                                         
{'loss': 0.7073, 'learning_rate': 0.0004967429665481557, 'epoch': 0.96}

  8%|▊         | 2244/28080 [4:25:50<51:31:26,  7.18s/it]
  8%|▊         | 2245/28080 [4:25:58<51:31:20,  7.18s/it]
                                                         
{'loss': 0.6868, 'learning_rate': 0.0004967383254453403, 'epoch': 0.96}

  8%|▊         | 2245/28080 [4:25:58<51:31:20,  7.18s/it]
  8%|▊         | 2246/28080 [4:26:05<51:18:40,  7.15s/it]
                                                         
{'loss': 0.7069, 'learning_rate': 0.000496733681059926, 'epoch': 0.96}

  8%|▊         | 2246/28080 [4:26:05<51:18:40,  7.15s/it]
  8%|▊         | 2247/28080 [4:26:12<51:35:01,  7.19s/it]
                                                         
{'loss': 0.6865, 'learning_rate': 0.0004967290333919745, 'epoch': 0.96}

  8%|▊         | 2247/28080 [4:26:12<51:35:01,  7.19s/it]
  8%|▊         | 2248/28080 [4:26:19<51:36:22,  7.19s/it]
                                                         
{'loss': 0.6824, 'learning_rate': 0.0004967243824415479, 'epoch': 0.96}

  8%|▊         | 2248/28080 [4:26:19<51:36:22,  7.19s/it]
  8%|▊         | 2249/28080 [4:26:26<51:26:04,  7.17s/it]
                                                         
{'loss': 0.6814, 'learning_rate': 0.0004967197282087078, 'epoch': 0.96}

  8%|▊         | 2249/28080 [4:26:26<51:26:04,  7.17s/it]
  8%|▊         | 2250/28080 [4:26:33<51:30:10,  7.18s/it]
                                                         
{'loss': 0.6721, 'learning_rate': 0.0004967150706935163, 'epoch': 0.96}

  8%|▊         | 2250/28080 [4:26:33<51:30:10,  7.18s/it]
  8%|▊         | 2251/28080 [4:26:41<51:28:12,  7.17s/it]
                                                         
{'loss': 0.6895, 'learning_rate': 0.0004967104098960353, 'epoch': 0.96}

  8%|▊         | 2251/28080 [4:26:41<51:28:12,  7.17s/it]
  8%|▊         | 2252/28080 [4:26:48<51:24:26,  7.17s/it]
                                                         
{'loss': 0.6821, 'learning_rate': 0.0004967057458163267, 'epoch': 0.96}

  8%|▊         | 2252/28080 [4:26:48<51:24:26,  7.17s/it]
  8%|▊         | 2253/28080 [4:26:55<51:09:50,  7.13s/it]
                                                         
{'loss': 0.6885, 'learning_rate': 0.0004967010784544529, 'epoch': 0.96}

  8%|▊         | 2253/28080 [4:26:55<51:09:50,  7.13s/it]
  8%|▊         | 2254/28080 [4:27:02<51:12:57,  7.14s/it]
                                                         
{'loss': 0.7048, 'learning_rate': 0.0004966964078104756, 'epoch': 0.96}

  8%|▊         | 2254/28080 [4:27:02<51:12:57,  7.14s/it]
  8%|▊         | 2255/28080 [4:27:09<51:00:20,  7.11s/it]
                                                         
{'loss': 0.6793, 'learning_rate': 0.0004966917338844571, 'epoch': 0.96}

  8%|▊         | 2255/28080 [4:27:09<51:00:20,  7.11s/it]
  8%|▊         | 2256/28080 [4:27:16<50:48:26,  7.08s/it]
                                                         
{'loss': 0.7099, 'learning_rate': 0.0004966870566764596, 'epoch': 0.96}

  8%|▊         | 2256/28080 [4:27:16<50:48:26,  7.08s/it]
  8%|▊         | 2257/28080 [4:27:23<50:46:44,  7.08s/it]
                                                         
{'loss': 0.6906, 'learning_rate': 0.0004966823761865454, 'epoch': 0.96}

  8%|▊         | 2257/28080 [4:27:23<50:46:44,  7.08s/it]
  8%|▊         | 2258/28080 [4:27:30<51:02:53,  7.12s/it]
                                                         
{'loss': 0.6866, 'learning_rate': 0.0004966776924147766, 'epoch': 0.96}

  8%|▊         | 2258/28080 [4:27:30<51:02:53,  7.12s/it]
  8%|▊         | 2259/28080 [4:27:37<51:02:17,  7.12s/it]
                                                         
{'loss': 0.7022, 'learning_rate': 0.0004966730053612155, 'epoch': 0.97}

  8%|▊         | 2259/28080 [4:27:37<51:02:17,  7.12s/it]
  8%|▊         | 2260/28080 [4:27:45<51:05:26,  7.12s/it]
                                                         
{'loss': 0.6816, 'learning_rate': 0.0004966683150259245, 'epoch': 0.97}

  8%|▊         | 2260/28080 [4:27:45<51:05:26,  7.12s/it]
  8%|▊         | 2261/28080 [4:27:52<51:12:06,  7.14s/it]
                                                         
{'loss': 0.681, 'learning_rate': 0.0004966636214089662, 'epoch': 0.97}

  8%|▊         | 2261/28080 [4:27:52<51:12:06,  7.14s/it]
  8%|▊         | 2262/28080 [4:27:59<51:12:13,  7.14s/it]
                                                         
{'loss': 0.6936, 'learning_rate': 0.0004966589245104029, 'epoch': 0.97}

  8%|▊         | 2262/28080 [4:27:59<51:12:13,  7.14s/it]
  8%|▊         | 2263/28080 [4:28:06<51:18:16,  7.15s/it]
                                                         
{'loss': 0.6871, 'learning_rate': 0.000496654224330297, 'epoch': 0.97}

  8%|▊         | 2263/28080 [4:28:06<51:18:16,  7.15s/it]
  8%|▊         | 2264/28080 [4:28:13<51:19:59,  7.16s/it]
                                                         
{'loss': 0.6843, 'learning_rate': 0.0004966495208687111, 'epoch': 0.97}

  8%|▊         | 2264/28080 [4:28:13<51:19:59,  7.16s/it]
  8%|▊         | 2265/28080 [4:28:20<51:15:51,  7.15s/it]
                                                         
{'loss': 0.6854, 'learning_rate': 0.0004966448141257078, 'epoch': 0.97}

  8%|▊         | 2265/28080 [4:28:20<51:15:51,  7.15s/it]
  8%|▊         | 2266/28080 [4:28:27<50:57:11,  7.11s/it]
                                                         
{'loss': 0.6974, 'learning_rate': 0.0004966401041013497, 'epoch': 0.97}

  8%|▊         | 2266/28080 [4:28:27<50:57:11,  7.11s/it]
  8%|▊         | 2267/28080 [4:28:35<51:00:15,  7.11s/it]
                                                         
{'loss': 0.687, 'learning_rate': 0.0004966353907956994, 'epoch': 0.97}

  8%|▊         | 2267/28080 [4:28:35<51:00:15,  7.11s/it]
  8%|▊         | 2268/28080 [4:28:42<51:07:10,  7.13s/it]
                                                         
{'loss': 0.6925, 'learning_rate': 0.0004966306742088198, 'epoch': 0.97}

  8%|▊         | 2268/28080 [4:28:42<51:07:10,  7.13s/it]
  8%|▊         | 2269/28080 [4:28:49<51:05:04,  7.13s/it]
                                                         
{'loss': 0.702, 'learning_rate': 0.0004966259543407734, 'epoch': 0.97}

  8%|▊         | 2269/28080 [4:28:49<51:05:04,  7.13s/it]
  8%|▊         | 2270/28080 [4:28:56<50:59:18,  7.11s/it]
                                                         
{'loss': 0.6953, 'learning_rate': 0.0004966212311916231, 'epoch': 0.97}

  8%|▊         | 2270/28080 [4:28:56<50:59:18,  7.11s/it]
  8%|▊         | 2271/28080 [4:29:03<50:52:16,  7.10s/it]
                                                         
{'loss': 0.6752, 'learning_rate': 0.0004966165047614318, 'epoch': 0.97}

  8%|▊         | 2271/28080 [4:29:03<50:52:16,  7.10s/it]
  8%|▊         | 2272/28080 [4:29:10<50:57:33,  7.11s/it]
                                                         
{'loss': 0.6833, 'learning_rate': 0.0004966117750502624, 'epoch': 0.97}

  8%|▊         | 2272/28080 [4:29:10<50:57:33,  7.11s/it]
  8%|▊         | 2273/28080 [4:29:17<51:15:22,  7.15s/it]
                                                         
{'loss': 0.7024, 'learning_rate': 0.0004966070420581775, 'epoch': 0.97}

  8%|▊         | 2273/28080 [4:29:17<51:15:22,  7.15s/it]
  8%|▊         | 2274/28080 [4:29:25<51:24:41,  7.17s/it]
                                                         
{'loss': 0.6839, 'learning_rate': 0.0004966023057852406, 'epoch': 0.97}

  8%|▊         | 2274/28080 [4:29:25<51:24:41,  7.17s/it]
  8%|▊         | 2275/28080 [4:29:32<51:25:24,  7.17s/it]
                                                         
{'loss': 0.6753, 'learning_rate': 0.0004965975662315142, 'epoch': 0.97}

  8%|▊         | 2275/28080 [4:29:32<51:25:24,  7.17s/it]
  8%|▊         | 2276/28080 [4:29:39<51:27:30,  7.18s/it]
                                                         
{'loss': 0.675, 'learning_rate': 0.0004965928233970617, 'epoch': 0.97}

  8%|▊         | 2276/28080 [4:29:39<51:27:30,  7.18s/it]
  8%|▊         | 2277/28080 [4:29:46<51:32:14,  7.19s/it]
                                                         
{'loss': 0.6779, 'learning_rate': 0.0004965880772819461, 'epoch': 0.97}

  8%|▊         | 2277/28080 [4:29:46<51:32:14,  7.19s/it]
  8%|▊         | 2278/28080 [4:29:53<51:05:01,  7.13s/it]
                                                         
{'loss': 0.6743, 'learning_rate': 0.0004965833278862304, 'epoch': 0.97}

  8%|▊         | 2278/28080 [4:29:53<51:05:01,  7.13s/it]
  8%|▊         | 2279/28080 [4:30:00<50:58:31,  7.11s/it]
                                                         
{'loss': 0.6972, 'learning_rate': 0.0004965785752099781, 'epoch': 0.97}

  8%|▊         | 2279/28080 [4:30:00<50:58:31,  7.11s/it]
  8%|▊         | 2280/28080 [4:30:07<50:53:39,  7.10s/it]
                                                         
{'loss': 0.6937, 'learning_rate': 0.0004965738192532521, 'epoch': 0.97}

  8%|▊         | 2280/28080 [4:30:07<50:53:39,  7.10s/it]
  8%|▊         | 2281/28080 [4:30:14<51:03:59,  7.13s/it]
                                                         
{'loss': 0.6937, 'learning_rate': 0.0004965690600161158, 'epoch': 0.97}

  8%|▊         | 2281/28080 [4:30:14<51:03:59,  7.13s/it]
  8%|▊         | 2282/28080 [4:30:22<51:01:43,  7.12s/it]
                                                         
{'loss': 0.7023, 'learning_rate': 0.0004965642974986325, 'epoch': 0.97}

  8%|▊         | 2282/28080 [4:30:22<51:01:43,  7.12s/it]
  8%|▊         | 2283/28080 [4:30:29<51:02:49,  7.12s/it]
                                                         
{'loss': 0.7074, 'learning_rate': 0.0004965595317008657, 'epoch': 0.98}

  8%|▊         | 2283/28080 [4:30:29<51:02:49,  7.12s/it]
  8%|▊         | 2284/28080 [4:30:36<51:01:04,  7.12s/it]
                                                         
{'loss': 0.6859, 'learning_rate': 0.0004965547626228787, 'epoch': 0.98}

  8%|▊         | 2284/28080 [4:30:36<51:01:04,  7.12s/it]
  8%|▊         | 2285/28080 [4:30:43<50:51:00,  7.10s/it]
                                                         
{'loss': 0.6973, 'learning_rate': 0.0004965499902647349, 'epoch': 0.98}

  8%|▊         | 2285/28080 [4:30:43<50:51:00,  7.10s/it]
  8%|▊         | 2286/28080 [4:30:50<50:57:21,  7.11s/it]
                                                         
{'loss': 0.6706, 'learning_rate': 0.0004965452146264978, 'epoch': 0.98}

  8%|▊         | 2286/28080 [4:30:50<50:57:21,  7.11s/it]
  8%|▊         | 2287/28080 [4:30:57<50:51:23,  7.10s/it]
                                                         
{'loss': 0.6962, 'learning_rate': 0.000496540435708231, 'epoch': 0.98}

  8%|▊         | 2287/28080 [4:30:57<50:51:23,  7.10s/it]
  8%|▊         | 2288/28080 [4:31:04<51:01:30,  7.12s/it]
                                                         
{'loss': 0.6715, 'learning_rate': 0.000496535653509998, 'epoch': 0.98}

  8%|▊         | 2288/28080 [4:31:04<51:01:30,  7.12s/it]
  8%|▊         | 2289/28080 [4:31:12<51:20:59,  7.17s/it]
                                                         
{'loss': 0.6698, 'learning_rate': 0.0004965308680318624, 'epoch': 0.98}

  8%|▊         | 2289/28080 [4:31:12<51:20:59,  7.17s/it]
  8%|▊         | 2290/28080 [4:31:19<51:26:52,  7.18s/it]
                                                         
{'loss': 0.666, 'learning_rate': 0.0004965260792738881, 'epoch': 0.98}

  8%|▊         | 2290/28080 [4:31:19<51:26:52,  7.18s/it]
  8%|▊         | 2291/28080 [4:31:26<51:25:24,  7.18s/it]
                                                         
{'loss': 0.6713, 'learning_rate': 0.0004965212872361385, 'epoch': 0.98}

  8%|▊         | 2291/28080 [4:31:26<51:25:24,  7.18s/it]
  8%|▊         | 2292/28080 [4:31:33<51:21:13,  7.17s/it]
                                                         
{'loss': 0.6734, 'learning_rate': 0.0004965164919186777, 'epoch': 0.98}

  8%|▊         | 2292/28080 [4:31:33<51:21:13,  7.17s/it]
  8%|▊         | 2293/28080 [4:31:40<51:15:27,  7.16s/it]
                                                         
{'loss': 0.6799, 'learning_rate': 0.000496511693321569, 'epoch': 0.98}

  8%|▊         | 2293/28080 [4:31:40<51:15:27,  7.16s/it]
  8%|▊         | 2294/28080 [4:31:47<51:06:06,  7.13s/it]
                                                         
{'loss': 0.6722, 'learning_rate': 0.0004965068914448768, 'epoch': 0.98}

  8%|▊         | 2294/28080 [4:31:47<51:06:06,  7.13s/it]
  8%|▊         | 2295/28080 [4:31:54<51:07:19,  7.14s/it]
                                                         
{'loss': 0.684, 'learning_rate': 0.0004965020862886646, 'epoch': 0.98}

  8%|▊         | 2295/28080 [4:31:54<51:07:19,  7.14s/it]
  8%|▊         | 2296/28080 [4:32:02<51:19:49,  7.17s/it]
                                                         
{'loss': 0.6664, 'learning_rate': 0.0004964972778529964, 'epoch': 0.98}

  8%|▊         | 2296/28080 [4:32:02<51:19:49,  7.17s/it]
  8%|▊         | 2297/28080 [4:32:09<51:20:00,  7.17s/it]
                                                         
{'loss': 0.6741, 'learning_rate': 0.0004964924661379363, 'epoch': 0.98}

  8%|▊         | 2297/28080 [4:32:09<51:20:00,  7.17s/it]
  8%|▊         | 2298/28080 [4:32:16<51:16:34,  7.16s/it]
                                                         
{'loss': 0.6829, 'learning_rate': 0.0004964876511435481, 'epoch': 0.98}

  8%|▊         | 2298/28080 [4:32:16<51:16:34,  7.16s/it]
  8%|▊         | 2299/28080 [4:32:23<51:13:59,  7.15s/it]
                                                         
{'loss': 0.6791, 'learning_rate': 0.0004964828328698961, 'epoch': 0.98}

  8%|▊         | 2299/28080 [4:32:23<51:13:59,  7.15s/it]
  8%|▊         | 2300/28080 [4:32:30<51:00:26,  7.12s/it]
                                                         
{'loss': 0.6817, 'learning_rate': 0.0004964780113170443, 'epoch': 0.98}

  8%|▊         | 2300/28080 [4:32:30<51:00:26,  7.12s/it]
  8%|▊         | 2301/28080 [4:32:37<51:11:37,  7.15s/it]
                                                         
{'loss': 0.688, 'learning_rate': 0.0004964731864850568, 'epoch': 0.98}

  8%|▊         | 2301/28080 [4:32:37<51:11:37,  7.15s/it]
  8%|▊         | 2302/28080 [4:32:44<50:59:28,  7.12s/it]
                                                         
{'loss': 0.6851, 'learning_rate': 0.0004964683583739978, 'epoch': 0.98}

  8%|▊         | 2302/28080 [4:32:44<50:59:28,  7.12s/it]
  8%|▊         | 2303/28080 [4:32:52<51:01:00,  7.12s/it]
                                                         
{'loss': 0.7021, 'learning_rate': 0.0004964635269839317, 'epoch': 0.98}

  8%|▊         | 2303/28080 [4:32:52<51:01:00,  7.12s/it]
  8%|▊         | 2304/28080 [4:32:59<51:03:08,  7.13s/it]
                                                         
{'loss': 0.6924, 'learning_rate': 0.0004964586923149225, 'epoch': 0.98}

  8%|▊         | 2304/28080 [4:32:59<51:03:08,  7.13s/it]
  8%|▊         | 2305/28080 [4:33:06<50:51:38,  7.10s/it]
                                                         
{'loss': 0.7045, 'learning_rate': 0.0004964538543670347, 'epoch': 0.98}

  8%|▊         | 2305/28080 [4:33:06<50:51:38,  7.10s/it]
  8%|▊         | 2306/28080 [4:33:13<50:52:44,  7.11s/it]
                                                         
{'loss': 0.69, 'learning_rate': 0.0004964490131403326, 'epoch': 0.99}

  8%|▊         | 2306/28080 [4:33:13<50:52:44,  7.11s/it]
  8%|▊         | 2307/28080 [4:33:20<51:01:57,  7.13s/it]
                                                         
{'loss': 0.6703, 'learning_rate': 0.0004964441686348807, 'epoch': 0.99}

  8%|▊         | 2307/28080 [4:33:20<51:01:57,  7.13s/it]
  8%|▊         | 2308/28080 [4:33:27<51:05:35,  7.14s/it]
                                                         
{'loss': 0.6934, 'learning_rate': 0.0004964393208507432, 'epoch': 0.99}

  8%|▊         | 2308/28080 [4:33:27<51:05:35,  7.14s/it]
  8%|▊         | 2309/28080 [4:33:34<51:07:56,  7.14s/it]
                                                         
{'loss': 0.6897, 'learning_rate': 0.0004964344697879849, 'epoch': 0.99}

  8%|▊         | 2309/28080 [4:33:34<51:07:56,  7.14s/it]
  8%|▊         | 2310/28080 [4:33:41<51:06:29,  7.14s/it]
                                                         
{'loss': 0.6837, 'learning_rate': 0.0004964296154466702, 'epoch': 0.99}

  8%|▊         | 2310/28080 [4:33:41<51:06:29,  7.14s/it]
  8%|▊         | 2311/28080 [4:33:49<51:07:25,  7.14s/it]
                                                         
{'loss': 0.6978, 'learning_rate': 0.0004964247578268637, 'epoch': 0.99}

  8%|▊         | 2311/28080 [4:33:49<51:07:25,  7.14s/it]
  8%|▊         | 2312/28080 [4:33:56<51:10:30,  7.15s/it]
                                                         
{'loss': 0.6808, 'learning_rate': 0.00049641989692863, 'epoch': 0.99}

  8%|▊         | 2312/28080 [4:33:56<51:10:30,  7.15s/it]
  8%|▊         | 2313/28080 [4:34:03<51:00:55,  7.13s/it]
                                                         
{'loss': 0.6948, 'learning_rate': 0.0004964150327520338, 'epoch': 0.99}

  8%|▊         | 2313/28080 [4:34:03<51:00:55,  7.13s/it]
  8%|▊         | 2314/28080 [4:34:10<51:01:47,  7.13s/it]
                                                         
{'loss': 0.6783, 'learning_rate': 0.0004964101652971398, 'epoch': 0.99}

  8%|▊         | 2314/28080 [4:34:10<51:01:47,  7.13s/it]
  8%|▊         | 2315/28080 [4:34:17<51:09:03,  7.15s/it]
                                                         
{'loss': 0.683, 'learning_rate': 0.0004964052945640127, 'epoch': 0.99}

  8%|▊         | 2315/28080 [4:34:17<51:09:03,  7.15s/it]
  8%|▊         | 2316/28080 [4:34:24<51:01:23,  7.13s/it]
                                                         
{'loss': 0.6648, 'learning_rate': 0.0004964004205527175, 'epoch': 0.99}

  8%|▊         | 2316/28080 [4:34:24<51:01:23,  7.13s/it]
  8%|▊         | 2317/28080 [4:34:31<51:04:23,  7.14s/it]
                                                         
{'loss': 0.6729, 'learning_rate': 0.0004963955432633188, 'epoch': 0.99}

  8%|▊         | 2317/28080 [4:34:31<51:04:23,  7.14s/it]
  8%|▊         | 2318/28080 [4:34:39<51:08:20,  7.15s/it]
                                                         
{'loss': 0.6855, 'learning_rate': 0.0004963906626958817, 'epoch': 0.99}

  8%|▊         | 2318/28080 [4:34:39<51:08:20,  7.15s/it]
  8%|▊         | 2319/28080 [4:34:46<50:57:35,  7.12s/it]
                                                         
{'loss': 0.7106, 'learning_rate': 0.0004963857788504709, 'epoch': 0.99}

  8%|▊         | 2319/28080 [4:34:46<50:57:35,  7.12s/it]
  8%|▊         | 2320/28080 [4:34:53<50:59:59,  7.13s/it]
                                                         
{'loss': 0.694, 'learning_rate': 0.0004963808917271515, 'epoch': 0.99}

  8%|▊         | 2320/28080 [4:34:53<50:59:59,  7.13s/it]
  8%|▊         | 2321/28080 [4:35:00<50:51:37,  7.11s/it]
                                                         
{'loss': 0.69, 'learning_rate': 0.0004963760013259885, 'epoch': 0.99}

  8%|▊         | 2321/28080 [4:35:00<50:51:37,  7.11s/it]
  8%|▊         | 2322/28080 [4:35:07<51:02:49,  7.13s/it]
                                                         
{'loss': 0.6873, 'learning_rate': 0.000496371107647047, 'epoch': 0.99}

  8%|▊         | 2322/28080 [4:35:07<51:02:49,  7.13s/it]
  8%|▊         | 2323/28080 [4:35:14<51:03:25,  7.14s/it]
                                                         
{'loss': 0.7161, 'learning_rate': 0.0004963662106903921, 'epoch': 0.99}

  8%|▊         | 2323/28080 [4:35:14<51:03:25,  7.14s/it]
  8%|▊         | 2324/28080 [4:35:21<51:06:20,  7.14s/it]
                                                         
{'loss': 0.6839, 'learning_rate': 0.0004963613104560889, 'epoch': 0.99}

  8%|▊         | 2324/28080 [4:35:21<51:06:20,  7.14s/it]
  8%|▊         | 2325/28080 [4:35:28<51:01:57,  7.13s/it]
                                                         
{'loss': 0.7029, 'learning_rate': 0.0004963564069442026, 'epoch': 0.99}

  8%|▊         | 2325/28080 [4:35:28<51:01:57,  7.13s/it]
  8%|▊         | 2326/28080 [4:35:36<51:04:35,  7.14s/it]
                                                         
{'loss': 0.6861, 'learning_rate': 0.0004963515001547986, 'epoch': 0.99}

  8%|▊         | 2326/28080 [4:35:36<51:04:35,  7.14s/it]
  8%|▊         | 2327/28080 [4:35:43<51:10:57,  7.15s/it]
                                                         
{'loss': 0.6811, 'learning_rate': 0.0004963465900879419, 'epoch': 0.99}

  8%|▊         | 2327/28080 [4:35:43<51:10:57,  7.15s/it]
  8%|▊         | 2328/28080 [4:35:50<51:04:18,  7.14s/it]
                                                         
{'loss': 0.6961, 'learning_rate': 0.000496341676743698, 'epoch': 0.99}

  8%|▊         | 2328/28080 [4:35:50<51:04:18,  7.14s/it]
  8%|▊         | 2329/28080 [4:35:57<51:15:10,  7.17s/it]
                                                         
{'loss': 0.6798, 'learning_rate': 0.0004963367601221322, 'epoch': 0.99}

  8%|▊         | 2329/28080 [4:35:57<51:15:10,  7.17s/it]
  8%|▊         | 2330/28080 [4:36:04<51:11:07,  7.16s/it]
                                                         
{'loss': 0.6857, 'learning_rate': 0.00049633184022331, 'epoch': 1.0}

  8%|▊         | 2330/28080 [4:36:04<51:11:07,  7.16s/it]
  8%|▊         | 2331/28080 [4:36:12<51:21:56,  7.18s/it]
                                                         
{'loss': 0.6879, 'learning_rate': 0.0004963269170472967, 'epoch': 1.0}

  8%|▊         | 2331/28080 [4:36:12<51:21:56,  7.18s/it]
  8%|▊         | 2332/28080 [4:36:19<51:08:03,  7.15s/it]
                                                         
{'loss': 0.7009, 'learning_rate': 0.0004963219905941579, 'epoch': 1.0}

  8%|▊         | 2332/28080 [4:36:19<51:08:03,  7.15s/it]
  8%|▊         | 2333/28080 [4:36:26<51:08:10,  7.15s/it]
                                                         
{'loss': 0.7067, 'learning_rate': 0.0004963170608639592, 'epoch': 1.0}

  8%|▊         | 2333/28080 [4:36:26<51:08:10,  7.15s/it]
  8%|▊         | 2334/28080 [4:36:33<51:04:57,  7.14s/it]
                                                         
{'loss': 0.7055, 'learning_rate': 0.0004963121278567661, 'epoch': 1.0}

  8%|▊         | 2334/28080 [4:36:33<51:04:57,  7.14s/it]
  8%|▊         | 2335/28080 [4:36:40<51:09:48,  7.15s/it]
                                                         
{'loss': 0.7056, 'learning_rate': 0.0004963071915726442, 'epoch': 1.0}

  8%|▊         | 2335/28080 [4:36:40<51:09:48,  7.15s/it]
  8%|▊         | 2336/28080 [4:36:47<51:07:21,  7.15s/it]
                                                         
{'loss': 0.6842, 'learning_rate': 0.0004963022520116593, 'epoch': 1.0}

  8%|▊         | 2336/28080 [4:36:47<51:07:21,  7.15s/it]
  8%|▊         | 2337/28080 [4:36:54<51:23:36,  7.19s/it]
                                                         
{'loss': 0.6631, 'learning_rate': 0.000496297309173877, 'epoch': 1.0}

  8%|▊         | 2337/28080 [4:36:54<51:23:36,  7.19s/it]
  8%|▊         | 2338/28080 [4:37:02<51:21:58,  7.18s/it]
                                                         
{'loss': 0.6799, 'learning_rate': 0.0004962923630593631, 'epoch': 1.0}

  8%|▊         | 2338/28080 [4:37:02<51:21:58,  7.18s/it]
  8%|▊         | 2339/28080 [4:37:09<51:16:50,  7.17s/it]
                                                         
{'loss': 0.6785, 'learning_rate': 0.0004962874136681834, 'epoch': 1.0}

  8%|▊         | 2339/28080 [4:37:09<51:16:50,  7.17s/it]
  8%|▊         | 2340/28080 [4:37:16<50:55:51,  7.12s/it]
                                                         
{'loss': 0.6937, 'learning_rate': 0.0004962824610004037, 'epoch': 1.0}

  8%|▊         | 2340/28080 [4:37:16<50:55:51,  7.12s/it]
  8%|▊         | 2341/28080 [4:37:23<51:40:07,  7.23s/it]
                                                         
{'loss': 0.6887, 'learning_rate': 0.0004962775050560899, 'epoch': 1.0}

  8%|▊         | 2341/28080 [4:37:23<51:40:07,  7.23s/it]
  8%|▊         | 2342/28080 [4:37:30<51:26:53,  7.20s/it]
                                                         
{'loss': 0.6777, 'learning_rate': 0.000496272545835308, 'epoch': 1.0}

  8%|▊         | 2342/28080 [4:37:30<51:26:53,  7.20s/it]
  8%|▊         | 2343/28080 [4:37:38<51:18:58,  7.18s/it]
                                                         
{'loss': 0.6843, 'learning_rate': 0.0004962675833381239, 'epoch': 1.0}

  8%|▊         | 2343/28080 [4:37:38<51:18:58,  7.18s/it]
  8%|▊         | 2344/28080 [4:37:45<51:12:57,  7.16s/it]
                                                         
{'loss': 0.6832, 'learning_rate': 0.0004962626175646038, 'epoch': 1.0}

  8%|▊         | 2344/28080 [4:37:45<51:12:57,  7.16s/it]
  8%|▊         | 2345/28080 [4:37:52<50:57:18,  7.13s/it]
                                                         
{'loss': 0.6833, 'learning_rate': 0.0004962576485148135, 'epoch': 1.0}

  8%|▊         | 2345/28080 [4:37:52<50:57:18,  7.13s/it]
  8%|▊         | 2346/28080 [4:37:59<50:58:53,  7.13s/it]
                                                         
{'loss': 0.6846, 'learning_rate': 0.0004962526761888193, 'epoch': 1.0}

  8%|▊         | 2346/28080 [4:37:59<50:58:53,  7.13s/it]
  8%|▊         | 2347/28080 [4:38:06<50:59:07,  7.13s/it]
                                                         
{'loss': 0.6817, 'learning_rate': 0.0004962477005866873, 'epoch': 1.0}

  8%|▊         | 2347/28080 [4:38:06<50:59:07,  7.13s/it]
  8%|▊         | 2348/28080 [4:38:13<51:06:12,  7.15s/it]
                                                         
{'loss': 0.6786, 'learning_rate': 0.0004962427217084836, 'epoch': 1.0}

  8%|▊         | 2348/28080 [4:38:13<51:06:12,  7.15s/it]
  8%|▊         | 2349/28080 [4:38:20<51:01:44,  7.14s/it]
                                                         
{'loss': 0.6774, 'learning_rate': 0.0004962377395542745, 'epoch': 1.0}

  8%|▊         | 2349/28080 [4:38:20<51:01:44,  7.14s/it]
  8%|▊         | 2350/28080 [4:38:27<50:57:41,  7.13s/it]
                                                         
{'loss': 0.6875, 'learning_rate': 0.0004962327541241265, 'epoch': 1.0}

  8%|▊         | 2350/28080 [4:38:27<50:57:41,  7.13s/it]
  8%|▊         | 2351/28080 [4:38:35<51:02:59,  7.14s/it]
                                                         
{'loss': 0.6968, 'learning_rate': 0.0004962277654181055, 'epoch': 1.0}

  8%|▊         | 2351/28080 [4:38:35<51:02:59,  7.14s/it]
  8%|▊         | 2352/28080 [4:38:42<51:08:09,  7.16s/it]
                                                         
{'loss': 0.6918, 'learning_rate': 0.0004962227734362783, 'epoch': 1.0}

  8%|▊         | 2352/28080 [4:38:42<51:08:09,  7.16s/it]
  8%|▊         | 2353/28080 [4:38:49<50:56:19,  7.13s/it]
                                                         
{'loss': 0.6924, 'learning_rate': 0.0004962177781787111, 'epoch': 1.01}

  8%|▊         | 2353/28080 [4:38:49<50:56:19,  7.13s/it]
  8%|▊         | 2354/28080 [4:38:56<51:04:28,  7.15s/it]
                                                         
{'loss': 0.7043, 'learning_rate': 0.0004962127796454701, 'epoch': 1.01}

  8%|▊         | 2354/28080 [4:38:56<51:04:28,  7.15s/it]
  8%|▊         | 2355/28080 [4:39:03<50:47:03,  7.11s/it]
                                                         
{'loss': 0.6951, 'learning_rate': 0.0004962077778366224, 'epoch': 1.01}

  8%|▊         | 2355/28080 [4:39:03<50:47:03,  7.11s/it]
  8%|▊         | 2356/28080 [4:39:10<50:51:26,  7.12s/it]
                                                         
{'loss': 0.6953, 'learning_rate': 0.000496202772752234, 'epoch': 1.01}

  8%|▊         | 2356/28080 [4:39:10<50:51:26,  7.12s/it]
  8%|▊         | 2357/28080 [4:39:17<51:03:11,  7.15s/it]
                                                         
{'loss': 0.6928, 'learning_rate': 0.0004961977643923719, 'epoch': 1.01}

  8%|▊         | 2357/28080 [4:39:17<51:03:11,  7.15s/it]
  8%|▊         | 2358/28080 [4:39:25<51:04:34,  7.15s/it]
                                                         
{'loss': 0.6939, 'learning_rate': 0.0004961927527571023, 'epoch': 1.01}

  8%|▊         | 2358/28080 [4:39:25<51:04:34,  7.15s/it]
  8%|▊         | 2359/28080 [4:39:32<50:52:00,  7.12s/it]
                                                         
{'loss': 0.6906, 'learning_rate': 0.0004961877378464923, 'epoch': 1.01}

  8%|▊         | 2359/28080 [4:39:32<50:52:00,  7.12s/it]
  8%|▊         | 2360/28080 [4:39:39<50:52:09,  7.12s/it]
                                                         
{'loss': 0.7058, 'learning_rate': 0.0004961827196606083, 'epoch': 1.01}

  8%|▊         | 2360/28080 [4:39:39<50:52:09,  7.12s/it]
  8%|▊         | 2361/28080 [4:39:46<50:46:18,  7.11s/it]
                                                         
{'loss': 0.7141, 'learning_rate': 0.0004961776981995173, 'epoch': 1.01}

  8%|▊         | 2361/28080 [4:39:46<50:46:18,  7.11s/it]
  8%|▊         | 2362/28080 [4:39:53<50:47:34,  7.11s/it]
                                                         
{'loss': 0.6881, 'learning_rate': 0.0004961726734632859, 'epoch': 1.01}

  8%|▊         | 2362/28080 [4:39:53<50:47:34,  7.11s/it]
  8%|▊         | 2363/28080 [4:40:00<50:54:49,  7.13s/it]
                                                         
{'loss': 0.7057, 'learning_rate': 0.0004961676454519811, 'epoch': 1.01}

  8%|▊         | 2363/28080 [4:40:00<50:54:49,  7.13s/it]
  8%|▊         | 2364/28080 [4:40:07<51:04:27,  7.15s/it]
                                                         
{'loss': 0.6536, 'learning_rate': 0.0004961626141656697, 'epoch': 1.01}

  8%|▊         | 2364/28080 [4:40:07<51:04:27,  7.15s/it]
  8%|▊         | 2365/28080 [4:40:14<51:08:06,  7.16s/it]
                                                         
{'loss': 0.6874, 'learning_rate': 0.0004961575796044186, 'epoch': 1.01}

  8%|▊         | 2365/28080 [4:40:14<51:08:06,  7.16s/it]
  8%|▊         | 2366/28080 [4:40:22<51:09:45,  7.16s/it]
                                                         
{'loss': 0.6956, 'learning_rate': 0.000496152541768295, 'epoch': 1.01}

  8%|▊         | 2366/28080 [4:40:22<51:09:45,  7.16s/it]
  8%|▊         | 2367/28080 [4:40:29<50:53:39,  7.13s/it]
                                                         
{'loss': 0.699, 'learning_rate': 0.0004961475006573657, 'epoch': 1.01}

  8%|▊         | 2367/28080 [4:40:29<50:53:39,  7.13s/it]
  8%|▊         | 2368/28080 [4:40:36<50:57:26,  7.13s/it]
                                                         
{'loss': 0.6938, 'learning_rate': 0.0004961424562716978, 'epoch': 1.01}

  8%|▊         | 2368/28080 [4:40:36<50:57:26,  7.13s/it]
  8%|▊         | 2369/28080 [4:40:43<51:03:32,  7.15s/it]
                                                         
{'loss': 0.6706, 'learning_rate': 0.0004961374086113585, 'epoch': 1.01}

  8%|▊         | 2369/28080 [4:40:43<51:03:32,  7.15s/it]
  8%|▊         | 2370/28080 [4:40:50<51:02:38,  7.15s/it]
                                                         
{'loss': 0.6792, 'learning_rate': 0.0004961323576764149, 'epoch': 1.01}

  8%|▊         | 2370/28080 [4:40:50<51:02:38,  7.15s/it]
  8%|▊         | 2371/28080 [4:40:57<51:08:22,  7.16s/it]
                                                         
{'loss': 0.6939, 'learning_rate': 0.0004961273034669342, 'epoch': 1.01}

  8%|▊         | 2371/28080 [4:40:57<51:08:22,  7.16s/it]
  8%|▊         | 2372/28080 [4:41:05<51:11:59,  7.17s/it]
                                                         
{'loss': 0.6833, 'learning_rate': 0.0004961222459829836, 'epoch': 1.01}

  8%|▊         | 2372/28080 [4:41:05<51:11:59,  7.17s/it]
  8%|▊         | 2373/28080 [4:41:12<51:11:49,  7.17s/it]
                                                         
{'loss': 0.683, 'learning_rate': 0.0004961171852246305, 'epoch': 1.01}

  8%|▊         | 2373/28080 [4:41:12<51:11:49,  7.17s/it]
  8%|▊         | 2374/28080 [4:41:19<51:10:06,  7.17s/it]
                                                         
{'loss': 0.6856, 'learning_rate': 0.0004961121211919421, 'epoch': 1.01}

  8%|▊         | 2374/28080 [4:41:19<51:10:06,  7.17s/it]
  8%|▊         | 2375/28080 [4:41:26<50:40:15,  7.10s/it]
                                                         
{'loss': 0.7241, 'learning_rate': 0.0004961070538849859, 'epoch': 1.01}

  8%|▊         | 2375/28080 [4:41:26<50:40:15,  7.10s/it]
  8%|▊         | 2376/28080 [4:41:33<50:30:46,  7.07s/it]
                                                         
{'loss': 0.6741, 'learning_rate': 0.0004961019833038292, 'epoch': 1.02}

  8%|▊         | 2376/28080 [4:41:33<50:30:46,  7.07s/it]
  8%|▊         | 2377/28080 [4:41:40<50:35:54,  7.09s/it]
                                                         
{'loss': 0.6787, 'learning_rate': 0.0004960969094485394, 'epoch': 1.02}

  8%|▊         | 2377/28080 [4:41:40<50:35:54,  7.09s/it]
  8%|▊         | 2378/28080 [4:41:47<50:33:02,  7.08s/it]
                                                         
{'loss': 0.6937, 'learning_rate': 0.0004960918323191842, 'epoch': 1.02}

  8%|▊         | 2378/28080 [4:41:47<50:33:02,  7.08s/it]
  8%|▊         | 2379/28080 [4:41:54<50:43:39,  7.11s/it]
                                                         
{'loss': 0.6745, 'learning_rate': 0.0004960867519158311, 'epoch': 1.02}

  8%|▊         | 2379/28080 [4:41:54<50:43:39,  7.11s/it]
  8%|▊         | 2380/28080 [4:42:01<50:29:20,  7.07s/it]
                                                         
{'loss': 0.6494, 'learning_rate': 0.0004960816682385475, 'epoch': 1.02}

  8%|▊         | 2380/28080 [4:42:01<50:29:20,  7.07s/it]
  8%|▊         | 2381/28080 [4:42:08<50:40:35,  7.10s/it]
                                                         
{'loss': 0.6744, 'learning_rate': 0.0004960765812874013, 'epoch': 1.02}

  8%|▊         | 2381/28080 [4:42:08<50:40:35,  7.10s/it]
  8%|▊         | 2382/28080 [4:42:15<50:43:23,  7.11s/it]
                                                         
{'loss': 0.7014, 'learning_rate': 0.00049607149106246, 'epoch': 1.02}

  8%|▊         | 2382/28080 [4:42:15<50:43:23,  7.11s/it]
  8%|▊         | 2383/28080 [4:42:23<50:51:32,  7.13s/it]
                                                         
{'loss': 0.6714, 'learning_rate': 0.0004960663975637913, 'epoch': 1.02}

  8%|▊         | 2383/28080 [4:42:23<50:51:32,  7.13s/it]
  8%|▊         | 2384/28080 [4:42:30<50:32:26,  7.08s/it]
                                                         
{'loss': 0.6847, 'learning_rate': 0.0004960613007914631, 'epoch': 1.02}

  8%|▊         | 2384/28080 [4:42:30<50:32:26,  7.08s/it]
  8%|▊         | 2385/28080 [4:42:37<50:40:54,  7.10s/it]
                                                         
{'loss': 0.665, 'learning_rate': 0.0004960562007455433, 'epoch': 1.02}

  8%|▊         | 2385/28080 [4:42:37<50:40:54,  7.10s/it]
  8%|▊         | 2386/28080 [4:42:44<50:30:25,  7.08s/it]
                                                         
{'loss': 0.6861, 'learning_rate': 0.0004960510974260994, 'epoch': 1.02}

  8%|▊         | 2386/28080 [4:42:44<50:30:25,  7.08s/it]
  9%|▊         | 2387/28080 [4:42:51<50:45:49,  7.11s/it]
                                                         
{'loss': 0.6719, 'learning_rate': 0.0004960459908331994, 'epoch': 1.02}

  9%|▊         | 2387/28080 [4:42:51<50:45:49,  7.11s/it]
  9%|▊         | 2388/28080 [4:42:58<50:42:43,  7.11s/it]
                                                         
{'loss': 0.6845, 'learning_rate': 0.0004960408809669116, 'epoch': 1.02}

  9%|▊         | 2388/28080 [4:42:58<50:42:43,  7.11s/it]
  9%|▊         | 2389/28080 [4:43:05<50:55:10,  7.14s/it]
                                                         
{'loss': 0.6575, 'learning_rate': 0.0004960357678273035, 'epoch': 1.02}

  9%|▊         | 2389/28080 [4:43:05<50:55:10,  7.14s/it]
  9%|▊         | 2390/28080 [4:43:12<51:00:16,  7.15s/it]
                                                         
{'loss': 0.6811, 'learning_rate': 0.0004960306514144434, 'epoch': 1.02}

  9%|▊         | 2390/28080 [4:43:12<51:00:16,  7.15s/it]
  9%|▊         | 2391/28080 [4:43:19<50:50:49,  7.13s/it]
                                                         
{'loss': 0.678, 'learning_rate': 0.0004960255317283992, 'epoch': 1.02}

  9%|▊         | 2391/28080 [4:43:19<50:50:49,  7.13s/it]
  9%|▊         | 2392/28080 [4:43:27<50:51:53,  7.13s/it]
                                                         
{'loss': 0.6861, 'learning_rate': 0.0004960204087692393, 'epoch': 1.02}

  9%|▊         | 2392/28080 [4:43:27<50:51:53,  7.13s/it]
  9%|▊         | 2393/28080 [4:43:34<50:44:24,  7.11s/it]
                                                         
{'loss': 0.6823, 'learning_rate': 0.0004960152825370316, 'epoch': 1.02}

  9%|▊         | 2393/28080 [4:43:34<50:44:24,  7.11s/it]
  9%|▊         | 2394/28080 [4:43:41<50:56:58,  7.14s/it]
                                                         
{'loss': 0.6918, 'learning_rate': 0.0004960101530318443, 'epoch': 1.02}

  9%|▊         | 2394/28080 [4:43:41<50:56:58,  7.14s/it]
  9%|▊         | 2395/28080 [4:43:48<50:50:45,  7.13s/it]
                                                         
{'loss': 0.688, 'learning_rate': 0.0004960050202537456, 'epoch': 1.02}

  9%|▊         | 2395/28080 [4:43:48<50:50:45,  7.13s/it]
  9%|▊         | 2396/28080 [4:43:55<51:00:16,  7.15s/it]
                                                         
{'loss': 0.6869, 'learning_rate': 0.0004959998842028041, 'epoch': 1.02}

  9%|▊         | 2396/28080 [4:43:55<51:00:16,  7.15s/it]
  9%|▊         | 2397/28080 [4:44:02<51:10:07,  7.17s/it]
                                                         
{'loss': 0.6834, 'learning_rate': 0.0004959947448790878, 'epoch': 1.02}

  9%|▊         | 2397/28080 [4:44:02<51:10:07,  7.17s/it]
  9%|▊         | 2398/28080 [4:44:10<51:07:37,  7.17s/it]
                                                         
{'loss': 0.6841, 'learning_rate': 0.0004959896022826653, 'epoch': 1.02}

  9%|▊         | 2398/28080 [4:44:10<51:07:37,  7.17s/it]
  9%|▊         | 2399/28080 [4:44:17<51:01:50,  7.15s/it]
                                                         
{'loss': 0.6641, 'learning_rate': 0.0004959844564136049, 'epoch': 1.02}

  9%|▊         | 2399/28080 [4:44:17<51:01:50,  7.15s/it]
  9%|▊         | 2400/28080 [4:44:24<51:06:14,  7.16s/it]
                                                         
{'loss': 0.655, 'learning_rate': 0.000495979307271975, 'epoch': 1.03}

  9%|▊         | 2400/28080 [4:44:24<51:06:14,  7.16s/it]
  9%|▊         | 2401/28080 [4:44:31<51:07:57,  7.17s/it]
                                                         
{'loss': 0.6737, 'learning_rate': 0.0004959741548578443, 'epoch': 1.03}

  9%|▊         | 2401/28080 [4:44:31<51:07:57,  7.17s/it]
  9%|▊         | 2402/28080 [4:44:38<51:06:28,  7.17s/it]
                                                         
{'loss': 0.6696, 'learning_rate': 0.000495968999171281, 'epoch': 1.03}

  9%|▊         | 2402/28080 [4:44:38<51:06:28,  7.17s/it]
  9%|▊         | 2403/28080 [4:44:45<51:15:12,  7.19s/it]
                                                         
{'loss': 0.6857, 'learning_rate': 0.0004959638402123542, 'epoch': 1.03}

  9%|▊         | 2403/28080 [4:44:45<51:15:12,  7.19s/it]
  9%|▊         | 2404/28080 [4:44:53<50:57:48,  7.15s/it]
                                                         
{'loss': 0.6735, 'learning_rate': 0.0004959586779811321, 'epoch': 1.03}

  9%|▊         | 2404/28080 [4:44:53<50:57:48,  7.15s/it]
  9%|▊         | 2405/28080 [4:45:00<50:52:02,  7.13s/it]
                                                         
{'loss': 0.6453, 'learning_rate': 0.0004959535124776835, 'epoch': 1.03}

  9%|▊         | 2405/28080 [4:45:00<50:52:02,  7.13s/it]
  9%|▊         | 2406/28080 [4:45:07<50:55:28,  7.14s/it]
                                                         
{'loss': 0.6795, 'learning_rate': 0.0004959483437020772, 'epoch': 1.03}

  9%|▊         | 2406/28080 [4:45:07<50:55:28,  7.14s/it]
  9%|▊         | 2407/28080 [4:45:14<50:52:01,  7.13s/it]
                                                         
{'loss': 0.6628, 'learning_rate': 0.000495943171654382, 'epoch': 1.03}

  9%|▊         | 2407/28080 [4:45:14<50:52:01,  7.13s/it]
  9%|▊         | 2408/28080 [4:45:21<50:51:07,  7.13s/it]
                                                         
{'loss': 0.7114, 'learning_rate': 0.0004959379963346665, 'epoch': 1.03}

  9%|▊         | 2408/28080 [4:45:21<50:51:07,  7.13s/it]
  9%|▊         | 2409/28080 [4:45:28<51:03:21,  7.16s/it]
                                                         
{'loss': 0.7041, 'learning_rate': 0.0004959328177429997, 'epoch': 1.03}

  9%|▊         | 2409/28080 [4:45:28<51:03:21,  7.16s/it]
  9%|▊         | 2410/28080 [4:45:35<50:57:48,  7.15s/it]
                                                         
{'loss': 0.6717, 'learning_rate': 0.0004959276358794505, 'epoch': 1.03}

  9%|▊         | 2410/28080 [4:45:35<50:57:48,  7.15s/it]
  9%|▊         | 2411/28080 [4:45:43<50:57:58,  7.15s/it]
                                                         
{'loss': 0.6718, 'learning_rate': 0.0004959224507440878, 'epoch': 1.03}

  9%|▊         | 2411/28080 [4:45:43<50:57:58,  7.15s/it]
  9%|▊         | 2412/28080 [4:45:50<50:48:17,  7.13s/it]
                                                         
{'loss': 0.6903, 'learning_rate': 0.0004959172623369806, 'epoch': 1.03}

  9%|▊         | 2412/28080 [4:45:50<50:48:17,  7.13s/it]
  9%|▊         | 2413/28080 [4:45:57<50:55:48,  7.14s/it]
                                                         
{'loss': 0.6848, 'learning_rate': 0.000495912070658198, 'epoch': 1.03}

  9%|▊         | 2413/28080 [4:45:57<50:55:48,  7.14s/it]
  9%|▊         | 2414/28080 [4:46:04<50:49:44,  7.13s/it]
                                                         
{'loss': 0.6831, 'learning_rate': 0.000495906875707809, 'epoch': 1.03}

  9%|▊         | 2414/28080 [4:46:04<50:49:44,  7.13s/it]
  9%|▊         | 2415/28080 [4:46:11<50:47:22,  7.12s/it]
                                                         
{'loss': 0.6893, 'learning_rate': 0.0004959016774858826, 'epoch': 1.03}

  9%|▊         | 2415/28080 [4:46:11<50:47:22,  7.12s/it]
  9%|▊         | 2416/28080 [4:46:18<50:58:37,  7.15s/it]
                                                         
{'loss': 0.678, 'learning_rate': 0.000495896475992488, 'epoch': 1.03}

  9%|▊         | 2416/28080 [4:46:18<50:58:37,  7.15s/it]
  9%|▊         | 2417/28080 [4:46:25<51:05:27,  7.17s/it]
                                                         
{'loss': 0.6758, 'learning_rate': 0.0004958912712276946, 'epoch': 1.03}

  9%|▊         | 2417/28080 [4:46:25<51:05:27,  7.17s/it]
  9%|▊         | 2418/28080 [4:46:33<51:06:15,  7.17s/it]
                                                         
{'loss': 0.6745, 'learning_rate': 0.0004958860631915715, 'epoch': 1.03}

  9%|▊         | 2418/28080 [4:46:33<51:06:15,  7.17s/it]
  9%|▊         | 2419/28080 [4:46:40<51:05:10,  7.17s/it]
                                                         
{'loss': 0.6846, 'learning_rate': 0.000495880851884188, 'epoch': 1.03}

  9%|▊         | 2419/28080 [4:46:40<51:05:10,  7.17s/it]
  9%|▊         | 2420/28080 [4:46:47<50:58:21,  7.15s/it]
                                                         
{'loss': 0.7058, 'learning_rate': 0.0004958756373056133, 'epoch': 1.03}

  9%|▊         | 2420/28080 [4:46:47<50:58:21,  7.15s/it]
  9%|▊         | 2421/28080 [4:46:54<50:59:19,  7.15s/it]
                                                         
{'loss': 0.6883, 'learning_rate': 0.0004958704194559171, 'epoch': 1.03}

  9%|▊         | 2421/28080 [4:46:54<50:59:19,  7.15s/it]
  9%|▊         | 2422/28080 [4:47:01<50:50:18,  7.13s/it]
                                                         
{'loss': 0.6859, 'learning_rate': 0.0004958651983351684, 'epoch': 1.03}

  9%|▊         | 2422/28080 [4:47:01<50:50:18,  7.13s/it]
  9%|▊         | 2423/28080 [4:47:08<50:57:48,  7.15s/it]
                                                         
{'loss': 0.6761, 'learning_rate': 0.000495859973943437, 'epoch': 1.04}

  9%|▊         | 2423/28080 [4:47:08<50:57:48,  7.15s/it]
  9%|▊         | 2424/28080 [4:47:16<51:22:47,  7.21s/it]
                                                         
{'loss': 0.6663, 'learning_rate': 0.0004958547462807923, 'epoch': 1.04}

  9%|▊         | 2424/28080 [4:47:16<51:22:47,  7.21s/it]
  9%|▊         | 2425/28080 [4:47:23<51:22:41,  7.21s/it]
                                                         
{'loss': 0.6502, 'learning_rate': 0.0004958495153473038, 'epoch': 1.04}

  9%|▊         | 2425/28080 [4:47:23<51:22:41,  7.21s/it]
  9%|▊         | 2426/28080 [4:47:30<51:25:45,  7.22s/it]
                                                         
{'loss': 0.6762, 'learning_rate': 0.0004958442811430411, 'epoch': 1.04}

  9%|▊         | 2426/28080 [4:47:30<51:25:45,  7.22s/it]
  9%|▊         | 2427/28080 [4:47:37<51:27:08,  7.22s/it]
                                                         
{'loss': 0.665, 'learning_rate': 0.000495839043668074, 'epoch': 1.04}

  9%|▊         | 2427/28080 [4:47:37<51:27:08,  7.22s/it]
  9%|▊         | 2428/28080 [4:47:44<51:14:07,  7.19s/it]
                                                         
{'loss': 0.6635, 'learning_rate': 0.0004958338029224719, 'epoch': 1.04}

  9%|▊         | 2428/28080 [4:47:44<51:14:07,  7.19s/it]
  9%|▊         | 2429/28080 [4:47:51<51:00:05,  7.16s/it]
                                                         
{'loss': 0.6648, 'learning_rate': 0.0004958285589063047, 'epoch': 1.04}

  9%|▊         | 2429/28080 [4:47:52<51:00:05,  7.16s/it]
  9%|▊         | 2430/28080 [4:47:59<50:40:20,  7.11s/it]
                                                         
{'loss': 0.717, 'learning_rate': 0.0004958233116196423, 'epoch': 1.04}

  9%|▊         | 2430/28080 [4:47:59<50:40:20,  7.11s/it]
  9%|▊         | 2431/28080 [4:48:06<50:47:15,  7.13s/it]
                                                         
{'loss': 0.6894, 'learning_rate': 0.0004958180610625541, 'epoch': 1.04}

  9%|▊         | 2431/28080 [4:48:06<50:47:15,  7.13s/it]
  9%|▊         | 2432/28080 [4:48:13<50:53:14,  7.14s/it]
                                                         
{'loss': 0.6854, 'learning_rate': 0.0004958128072351102, 'epoch': 1.04}

  9%|▊         | 2432/28080 [4:48:13<50:53:14,  7.14s/it]
  9%|▊         | 2433/28080 [4:48:20<50:55:10,  7.15s/it]
                                                         
{'loss': 0.6944, 'learning_rate': 0.0004958075501373807, 'epoch': 1.04}

  9%|▊         | 2433/28080 [4:48:20<50:55:10,  7.15s/it]
  9%|▊         | 2434/28080 [4:48:27<50:41:44,  7.12s/it]
                                                         
{'loss': 0.6874, 'learning_rate': 0.0004958022897694351, 'epoch': 1.04}

  9%|▊         | 2434/28080 [4:48:27<50:41:44,  7.12s/it]
  9%|▊         | 2435/28080 [4:48:34<50:33:16,  7.10s/it]
                                                         
{'loss': 0.6663, 'learning_rate': 0.0004957970261313438, 'epoch': 1.04}

  9%|▊         | 2435/28080 [4:48:34<50:33:16,  7.10s/it]
  9%|▊         | 2436/28080 [4:48:41<50:36:32,  7.10s/it]
                                                         
{'loss': 0.6984, 'learning_rate': 0.0004957917592231765, 'epoch': 1.04}

  9%|▊         | 2436/28080 [4:48:41<50:36:32,  7.10s/it]
  9%|▊         | 2437/28080 [4:48:48<50:47:14,  7.13s/it]
                                                         
{'loss': 0.6918, 'learning_rate': 0.0004957864890450034, 'epoch': 1.04}

  9%|▊         | 2437/28080 [4:48:48<50:47:14,  7.13s/it]
  9%|▊         | 2438/28080 [4:48:56<50:56:15,  7.15s/it]
                                                         
{'loss': 0.6688, 'learning_rate': 0.0004957812155968948, 'epoch': 1.04}

  9%|▊         | 2438/28080 [4:48:56<50:56:15,  7.15s/it]
  9%|▊         | 2439/28080 [4:49:03<50:49:33,  7.14s/it]
                                                         
{'loss': 0.7021, 'learning_rate': 0.0004957759388789206, 'epoch': 1.04}

  9%|▊         | 2439/28080 [4:49:03<50:49:33,  7.14s/it]
  9%|▊         | 2440/28080 [4:49:10<50:54:20,  7.15s/it]
                                                         
{'loss': 0.6821, 'learning_rate': 0.000495770658891151, 'epoch': 1.04}

  9%|▊         | 2440/28080 [4:49:10<50:54:20,  7.15s/it]
  9%|▊         | 2441/28080 [4:49:17<50:58:38,  7.16s/it]
                                                         
{'loss': 0.6859, 'learning_rate': 0.0004957653756336565, 'epoch': 1.04}

  9%|▊         | 2441/28080 [4:49:17<50:58:38,  7.16s/it]
  9%|▊         | 2442/28080 [4:49:24<51:06:00,  7.18s/it]
                                                         
{'loss': 0.7006, 'learning_rate': 0.000495760089106507, 'epoch': 1.04}

  9%|▊         | 2442/28080 [4:49:24<51:06:00,  7.18s/it]
  9%|▊         | 2443/28080 [4:49:31<51:01:39,  7.17s/it]
                                                         
{'loss': 0.6773, 'learning_rate': 0.0004957547993097732, 'epoch': 1.04}

  9%|▊         | 2443/28080 [4:49:31<51:01:39,  7.17s/it]
  9%|▊         | 2444/28080 [4:49:39<50:50:12,  7.14s/it]
                                                         
{'loss': 0.6894, 'learning_rate': 0.0004957495062435254, 'epoch': 1.04}

  9%|▊         | 2444/28080 [4:49:39<50:50:12,  7.14s/it]
  9%|▊         | 2445/28080 [4:49:46<50:42:01,  7.12s/it]
                                                         
{'loss': 0.6822, 'learning_rate': 0.0004957442099078337, 'epoch': 1.04}

  9%|▊         | 2445/28080 [4:49:46<50:42:01,  7.12s/it]
  9%|▊         | 2446/28080 [4:49:53<51:15:46,  7.20s/it]
                                                         
{'loss': 0.6851, 'learning_rate': 0.0004957389103027689, 'epoch': 1.04}

  9%|▊         | 2446/28080 [4:49:53<51:15:46,  7.20s/it]
  9%|▊         | 2447/28080 [4:50:00<51:24:25,  7.22s/it]
                                                         
{'loss': 0.6693, 'learning_rate': 0.0004957336074284016, 'epoch': 1.05}

  9%|▊         | 2447/28080 [4:50:00<51:24:25,  7.22s/it]
  9%|▊         | 2448/28080 [4:50:07<51:18:39,  7.21s/it]
                                                         
{'loss': 0.6602, 'learning_rate': 0.000495728301284802, 'epoch': 1.05}

  9%|▊         | 2448/28080 [4:50:07<51:18:39,  7.21s/it]
  9%|▊         | 2449/28080 [4:50:15<51:04:20,  7.17s/it]
                                                         
{'loss': 0.6742, 'learning_rate': 0.0004957229918720409, 'epoch': 1.05}

  9%|▊         | 2449/28080 [4:50:15<51:04:20,  7.17s/it]
  9%|▊         | 2450/28080 [4:50:22<50:56:15,  7.15s/it]
                                                         
{'loss': 0.6771, 'learning_rate': 0.0004957176791901888, 'epoch': 1.05}

  9%|▊         | 2450/28080 [4:50:22<50:56:15,  7.15s/it]
  9%|▊         | 2451/28080 [4:50:29<50:38:53,  7.11s/it]
                                                         
{'loss': 0.687, 'learning_rate': 0.0004957123632393166, 'epoch': 1.05}

  9%|▊         | 2451/28080 [4:50:29<50:38:53,  7.11s/it]
  9%|▊         | 2452/28080 [4:50:36<50:43:47,  7.13s/it]
                                                         
{'loss': 0.6708, 'learning_rate': 0.0004957070440194948, 'epoch': 1.05}

  9%|▊         | 2452/28080 [4:50:36<50:43:47,  7.13s/it]
  9%|▊         | 2453/28080 [4:50:43<50:56:21,  7.16s/it]
                                                         
{'loss': 0.6693, 'learning_rate': 0.0004957017215307943, 'epoch': 1.05}

  9%|▊         | 2453/28080 [4:50:43<50:56:21,  7.16s/it]
  9%|▊         | 2454/28080 [4:50:50<50:48:13,  7.14s/it]
                                                         
{'loss': 0.6745, 'learning_rate': 0.0004956963957732859, 'epoch': 1.05}

  9%|▊         | 2454/28080 [4:50:50<50:48:13,  7.14s/it]
  9%|▊         | 2455/28080 [4:50:57<51:00:58,  7.17s/it]
                                                         
{'loss': 0.6839, 'learning_rate': 0.0004956910667470403, 'epoch': 1.05}

  9%|▊         | 2455/28080 [4:50:57<51:00:58,  7.17s/it]
  9%|▊         | 2456/28080 [4:51:05<51:07:52,  7.18s/it]
                                                         
{'loss': 0.6946, 'learning_rate': 0.0004956857344521287, 'epoch': 1.05}

  9%|▊         | 2456/28080 [4:51:05<51:07:52,  7.18s/it]
  9%|▉         | 2457/28080 [4:51:12<51:03:43,  7.17s/it]
                                                         
{'loss': 0.6751, 'learning_rate': 0.0004956803988886218, 'epoch': 1.05}

  9%|▉         | 2457/28080 [4:51:12<51:03:43,  7.17s/it]
  9%|▉         | 2458/28080 [4:51:19<51:08:16,  7.19s/it]
                                                         
{'loss': 0.6918, 'learning_rate': 0.0004956750600565906, 'epoch': 1.05}

  9%|▉         | 2458/28080 [4:51:19<51:08:16,  7.19s/it]
  9%|▉         | 2459/28080 [4:51:26<50:49:21,  7.14s/it]
                                                         
{'loss': 0.6845, 'learning_rate': 0.0004956697179561061, 'epoch': 1.05}

  9%|▉         | 2459/28080 [4:51:26<50:49:21,  7.14s/it]
  9%|▉         | 2460/28080 [4:51:33<50:32:47,  7.10s/it]
                                                         
{'loss': 0.6835, 'learning_rate': 0.0004956643725872396, 'epoch': 1.05}

  9%|▉         | 2460/28080 [4:51:33<50:32:47,  7.10s/it]
  9%|▉         | 2461/28080 [4:51:40<50:28:32,  7.09s/it]
                                                         
{'loss': 0.6909, 'learning_rate': 0.0004956590239500621, 'epoch': 1.05}

  9%|▉         | 2461/28080 [4:51:40<50:28:32,  7.09s/it]
  9%|▉         | 2462/28080 [4:51:47<50:28:38,  7.09s/it]
                                                         
{'loss': 0.6847, 'learning_rate': 0.0004956536720446445, 'epoch': 1.05}

  9%|▉         | 2462/28080 [4:51:47<50:28:38,  7.09s/it]
  9%|▉         | 2463/28080 [4:51:54<50:45:13,  7.13s/it]
                                                         
{'loss': 0.6834, 'learning_rate': 0.0004956483168710585, 'epoch': 1.05}

  9%|▉         | 2463/28080 [4:51:54<50:45:13,  7.13s/it]
  9%|▉         | 2464/28080 [4:52:01<50:44:10,  7.13s/it]
                                                         
{'loss': 0.6671, 'learning_rate': 0.0004956429584293748, 'epoch': 1.05}

  9%|▉         | 2464/28080 [4:52:01<50:44:10,  7.13s/it]
  9%|▉         | 2465/28080 [4:52:09<50:43:44,  7.13s/it]
                                                         
{'loss': 0.6688, 'learning_rate': 0.0004956375967196652, 'epoch': 1.05}

  9%|▉         | 2465/28080 [4:52:09<50:43:44,  7.13s/it]
  9%|▉         | 2466/28080 [4:52:16<50:39:01,  7.12s/it]
                                                         
{'loss': 0.7052, 'learning_rate': 0.0004956322317420006, 'epoch': 1.05}

  9%|▉         | 2466/28080 [4:52:16<50:39:01,  7.12s/it]
  9%|▉         | 2467/28080 [4:52:23<50:43:41,  7.13s/it]
                                                         
{'loss': 0.6851, 'learning_rate': 0.0004956268634964526, 'epoch': 1.05}

  9%|▉         | 2467/28080 [4:52:23<50:43:41,  7.13s/it]
  9%|▉         | 2468/28080 [4:52:30<50:45:51,  7.14s/it]
                                                         
{'loss': 0.674, 'learning_rate': 0.0004956214919830926, 'epoch': 1.05}

  9%|▉         | 2468/28080 [4:52:30<50:45:51,  7.14s/it]
  9%|▉         | 2469/28080 [4:52:37<50:47:10,  7.14s/it]
                                                         
{'loss': 0.6994, 'learning_rate': 0.000495616117201992, 'epoch': 1.05}

  9%|▉         | 2469/28080 [4:52:37<50:47:10,  7.14s/it]
  9%|▉         | 2470/28080 [4:52:44<50:46:58,  7.14s/it]
                                                         
{'loss': 0.669, 'learning_rate': 0.0004956107391532224, 'epoch': 1.06}

  9%|▉         | 2470/28080 [4:52:44<50:46:58,  7.14s/it]
  9%|▉         | 2471/28080 [4:52:51<50:46:23,  7.14s/it]
                                                         
{'loss': 0.6743, 'learning_rate': 0.0004956053578368552, 'epoch': 1.06}

  9%|▉         | 2471/28080 [4:52:51<50:46:23,  7.14s/it]
  9%|▉         | 2472/28080 [4:52:59<51:01:49,  7.17s/it]
                                                         
{'loss': 0.6874, 'learning_rate': 0.0004955999732529623, 'epoch': 1.06}

  9%|▉         | 2472/28080 [4:52:59<51:01:49,  7.17s/it]
  9%|▉         | 2473/28080 [4:53:06<50:51:51,  7.15s/it]
                                                         
{'loss': 0.668, 'learning_rate': 0.0004955945854016149, 'epoch': 1.06}

  9%|▉         | 2473/28080 [4:53:06<50:51:51,  7.15s/it]
  9%|▉         | 2474/28080 [4:53:13<50:53:48,  7.16s/it]
                                                         
{'loss': 0.6724, 'learning_rate': 0.0004955891942828851, 'epoch': 1.06}

  9%|▉         | 2474/28080 [4:53:13<50:53:48,  7.16s/it]
  9%|▉         | 2475/28080 [4:53:20<50:52:47,  7.15s/it]
                                                         
{'loss': 0.6705, 'learning_rate': 0.0004955837998968444, 'epoch': 1.06}

  9%|▉         | 2475/28080 [4:53:20<50:52:47,  7.15s/it]
  9%|▉         | 2476/28080 [4:53:27<50:48:12,  7.14s/it]
                                                         
{'loss': 0.6755, 'learning_rate': 0.0004955784022435644, 'epoch': 1.06}

  9%|▉         | 2476/28080 [4:53:27<50:48:12,  7.14s/it]
  9%|▉         | 2477/28080 [4:53:34<50:49:16,  7.15s/it]
                                                         
{'loss': 0.6751, 'learning_rate': 0.0004955730013231173, 'epoch': 1.06}

  9%|▉         | 2477/28080 [4:53:34<50:49:16,  7.15s/it]
  9%|▉         | 2478/28080 [4:53:42<50:50:56,  7.15s/it]
                                                         
{'loss': 0.6823, 'learning_rate': 0.0004955675971355746, 'epoch': 1.06}

  9%|▉         | 2478/28080 [4:53:42<50:50:56,  7.15s/it]
  9%|▉         | 2479/28080 [4:53:49<50:50:40,  7.15s/it]
                                                         
{'loss': 0.7011, 'learning_rate': 0.0004955621896810085, 'epoch': 1.06}

  9%|▉         | 2479/28080 [4:53:49<50:50:40,  7.15s/it]
  9%|▉         | 2480/28080 [4:53:56<50:30:17,  7.10s/it]
                                                         
{'loss': 0.6852, 'learning_rate': 0.0004955567789594908, 'epoch': 1.06}

  9%|▉         | 2480/28080 [4:53:56<50:30:17,  7.10s/it]
  9%|▉         | 2481/28080 [4:54:03<50:24:54,  7.09s/it]
                                                         
{'loss': 0.6872, 'learning_rate': 0.0004955513649710934, 'epoch': 1.06}

  9%|▉         | 2481/28080 [4:54:03<50:24:54,  7.09s/it]
  9%|▉         | 2482/28080 [4:54:10<50:25:49,  7.09s/it]
                                                         
{'loss': 0.6714, 'learning_rate': 0.0004955459477158884, 'epoch': 1.06}

  9%|▉         | 2482/28080 [4:54:10<50:25:49,  7.09s/it]
  9%|▉         | 2483/28080 [4:54:17<50:29:52,  7.10s/it]
                                                         
{'loss': 0.6895, 'learning_rate': 0.000495540527193948, 'epoch': 1.06}

  9%|▉         | 2483/28080 [4:54:17<50:29:52,  7.10s/it]
  9%|▉         | 2484/28080 [4:54:24<50:30:09,  7.10s/it]
                                                         
{'loss': 0.68, 'learning_rate': 0.0004955351034053441, 'epoch': 1.06}

  9%|▉         | 2484/28080 [4:54:24<50:30:09,  7.10s/it]
  9%|▉         | 2485/28080 [4:54:31<50:32:10,  7.11s/it]
                                                         
{'loss': 0.6766, 'learning_rate': 0.000495529676350149, 'epoch': 1.06}

  9%|▉         | 2485/28080 [4:54:31<50:32:10,  7.11s/it]
  9%|▉         | 2486/28080 [4:54:38<50:34:10,  7.11s/it]
                                                         
{'loss': 0.686, 'learning_rate': 0.0004955242460284348, 'epoch': 1.06}

  9%|▉         | 2486/28080 [4:54:38<50:34:10,  7.11s/it]
  9%|▉         | 2487/28080 [4:54:45<50:33:58,  7.11s/it]
                                                         
{'loss': 0.6737, 'learning_rate': 0.0004955188124402739, 'epoch': 1.06}

  9%|▉         | 2487/28080 [4:54:45<50:33:58,  7.11s/it]
  9%|▉         | 2488/28080 [4:54:53<50:48:07,  7.15s/it]
                                                         
{'loss': 0.6711, 'learning_rate': 0.0004955133755857385, 'epoch': 1.06}

  9%|▉         | 2488/28080 [4:54:53<50:48:07,  7.15s/it]
  9%|▉         | 2489/28080 [4:55:00<50:46:27,  7.14s/it]
                                                         
{'loss': 0.6605, 'learning_rate': 0.0004955079354649008, 'epoch': 1.06}

  9%|▉         | 2489/28080 [4:55:00<50:46:27,  7.14s/it]
  9%|▉         | 2490/28080 [4:55:07<50:35:06,  7.12s/it]
                                                         
{'loss': 0.6901, 'learning_rate': 0.0004955024920778333, 'epoch': 1.06}

  9%|▉         | 2490/28080 [4:55:07<50:35:06,  7.12s/it]
  9%|▉         | 2491/28080 [4:55:14<50:36:32,  7.12s/it]
                                                         
{'loss': 0.6672, 'learning_rate': 0.0004954970454246085, 'epoch': 1.06}

  9%|▉         | 2491/28080 [4:55:14<50:36:32,  7.12s/it]
  9%|▉         | 2492/28080 [4:55:21<50:34:59,  7.12s/it]
                                                         
{'loss': 0.6754, 'learning_rate': 0.0004954915955052987, 'epoch': 1.06}

  9%|▉         | 2492/28080 [4:55:21<50:34:59,  7.12s/it]
  9%|▉         | 2493/28080 [4:55:28<50:36:03,  7.12s/it]
                                                         
{'loss': 0.6915, 'learning_rate': 0.0004954861423199766, 'epoch': 1.06}

  9%|▉         | 2493/28080 [4:55:28<50:36:03,  7.12s/it]
  9%|▉         | 2494/28080 [4:55:35<50:41:23,  7.13s/it]
                                                         
{'loss': 0.6742, 'learning_rate': 0.0004954806858687145, 'epoch': 1.07}

  9%|▉         | 2494/28080 [4:55:35<50:41:23,  7.13s/it]
  9%|▉         | 2495/28080 [4:55:43<50:43:11,  7.14s/it]
                                                         
{'loss': 0.674, 'learning_rate': 0.0004954752261515851, 'epoch': 1.07}

  9%|▉         | 2495/28080 [4:55:43<50:43:11,  7.14s/it]
  9%|▉         | 2496/28080 [4:55:50<50:40:29,  7.13s/it]
                                                         
{'loss': 0.6859, 'learning_rate': 0.0004954697631686612, 'epoch': 1.07}

  9%|▉         | 2496/28080 [4:55:50<50:40:29,  7.13s/it]
  9%|▉         | 2497/28080 [4:55:57<50:35:54,  7.12s/it]
                                                         
{'loss': 0.6717, 'learning_rate': 0.0004954642969200153, 'epoch': 1.07}

  9%|▉         | 2497/28080 [4:55:57<50:35:54,  7.12s/it]
  9%|▉         | 2498/28080 [4:56:04<50:36:04,  7.12s/it]
                                                         
{'loss': 0.6533, 'learning_rate': 0.0004954588274057201, 'epoch': 1.07}

  9%|▉         | 2498/28080 [4:56:04<50:36:04,  7.12s/it]
  9%|▉         | 2499/28080 [4:56:11<50:39:33,  7.13s/it]
                                                         
{'loss': 0.6982, 'learning_rate': 0.0004954533546258484, 'epoch': 1.07}

  9%|▉         | 2499/28080 [4:56:11<50:39:33,  7.13s/it]
  9%|▉         | 2500/28080 [4:56:18<50:46:38,  7.15s/it]
                                                         
{'loss': 0.685, 'learning_rate': 0.0004954478785804731, 'epoch': 1.07}

  9%|▉         | 2500/28080 [4:56:18<50:46:38,  7.15s/it]
  9%|▉         | 2501/28080 [4:56:25<50:45:22,  7.14s/it]
                                                         
{'loss': 0.6734, 'learning_rate': 0.000495442399269667, 'epoch': 1.07}

  9%|▉         | 2501/28080 [4:56:25<50:45:22,  7.14s/it]
  9%|▉         | 2502/28080 [4:56:33<50:52:31,  7.16s/it]
                                                         
{'loss': 0.6643, 'learning_rate': 0.000495436916693503, 'epoch': 1.07}

  9%|▉         | 2502/28080 [4:56:33<50:52:31,  7.16s/it]
  9%|▉         | 2503/28080 [4:56:40<50:47:53,  7.15s/it]
                                                         
{'loss': 0.6585, 'learning_rate': 0.000495431430852054, 'epoch': 1.07}

  9%|▉         | 2503/28080 [4:56:40<50:47:53,  7.15s/it]
  9%|▉         | 2504/28080 [4:56:47<50:40:58,  7.13s/it]
                                                         
{'loss': 0.6746, 'learning_rate': 0.000495425941745393, 'epoch': 1.07}

  9%|▉         | 2504/28080 [4:56:47<50:40:58,  7.13s/it]
  9%|▉         | 2505/28080 [4:56:54<51:11:41,  7.21s/it]
                                                         
{'loss': 0.6908, 'learning_rate': 0.000495420449373593, 'epoch': 1.07}

  9%|▉         | 2505/28080 [4:56:54<51:11:41,  7.21s/it]
  9%|▉         | 2506/28080 [4:57:01<50:56:44,  7.17s/it]
                                                         
{'loss': 0.6861, 'learning_rate': 0.0004954149537367272, 'epoch': 1.07}

  9%|▉         | 2506/28080 [4:57:01<50:56:44,  7.17s/it]
  9%|▉         | 2507/28080 [4:57:08<50:53:08,  7.16s/it]
                                                         
{'loss': 0.6903, 'learning_rate': 0.0004954094548348686, 'epoch': 1.07}

  9%|▉         | 2507/28080 [4:57:08<50:53:08,  7.16s/it]
  9%|▉         | 2508/28080 [4:57:15<50:49:40,  7.16s/it]
                                                         
{'loss': 0.6792, 'learning_rate': 0.0004954039526680902, 'epoch': 1.07}

  9%|▉         | 2508/28080 [4:57:15<50:49:40,  7.16s/it]
  9%|▉         | 2509/28080 [4:57:23<50:54:25,  7.17s/it]
                                                         
{'loss': 0.6809, 'learning_rate': 0.0004953984472364656, 'epoch': 1.07}

  9%|▉         | 2509/28080 [4:57:23<50:54:25,  7.17s/it]
  9%|▉         | 2510/28080 [4:57:30<50:57:54,  7.18s/it]
                                                         
{'loss': 0.6766, 'learning_rate': 0.0004953929385400677, 'epoch': 1.07}

  9%|▉         | 2510/28080 [4:57:30<50:57:54,  7.18s/it]
  9%|▉         | 2511/28080 [4:57:37<50:51:48,  7.16s/it]
                                                         
{'loss': 0.6751, 'learning_rate': 0.00049538742657897, 'epoch': 1.07}

  9%|▉         | 2511/28080 [4:57:37<50:51:48,  7.16s/it]
  9%|▉         | 2512/28080 [4:57:44<50:44:48,  7.15s/it]
                                                         
{'loss': 0.7056, 'learning_rate': 0.0004953819113532457, 'epoch': 1.07}

  9%|▉         | 2512/28080 [4:57:44<50:44:48,  7.15s/it]
  9%|▉         | 2513/28080 [4:57:51<51:04:12,  7.19s/it]
                                                         
{'loss': 0.6844, 'learning_rate': 0.0004953763928629682, 'epoch': 1.07}

  9%|▉         | 2513/28080 [4:57:51<51:04:12,  7.19s/it]
  9%|▉         | 2514/28080 [4:57:58<50:48:02,  7.15s/it]
                                                         
{'loss': 0.7042, 'learning_rate': 0.000495370871108211, 'epoch': 1.07}

  9%|▉         | 2514/28080 [4:57:58<50:48:02,  7.15s/it]
  9%|▉         | 2515/28080 [4:58:06<50:58:18,  7.18s/it]
                                                         
{'loss': 0.6909, 'learning_rate': 0.0004953653460890474, 'epoch': 1.07}

  9%|▉         | 2515/28080 [4:58:06<50:58:18,  7.18s/it]
  9%|▉         | 2516/28080 [4:58:13<51:08:22,  7.20s/it]
                                                         
{'loss': 0.673, 'learning_rate': 0.000495359817805551, 'epoch': 1.07}

  9%|▉         | 2516/28080 [4:58:13<51:08:22,  7.20s/it]
  9%|▉         | 2517/28080 [4:58:20<50:49:00,  7.16s/it]
                                                         
{'loss': 0.6728, 'learning_rate': 0.0004953542862577954, 'epoch': 1.08}

  9%|▉         | 2517/28080 [4:58:20<50:49:00,  7.16s/it]
  9%|▉         | 2518/28080 [4:58:27<50:59:51,  7.18s/it]
                                                         
{'loss': 0.6685, 'learning_rate': 0.0004953487514458542, 'epoch': 1.08}

  9%|▉         | 2518/28080 [4:58:27<50:59:51,  7.18s/it]
  9%|▉         | 2519/28080 [4:58:34<50:46:45,  7.15s/it]
                                                         
{'loss': 0.6936, 'learning_rate': 0.0004953432133698009, 'epoch': 1.08}

  9%|▉         | 2519/28080 [4:58:34<50:46:45,  7.15s/it]
  9%|▉         | 2520/28080 [4:58:41<50:36:04,  7.13s/it]
                                                         
{'loss': 0.6793, 'learning_rate': 0.0004953376720297092, 'epoch': 1.08}

  9%|▉         | 2520/28080 [4:58:41<50:36:04,  7.13s/it]
  9%|▉         | 2521/28080 [4:58:49<50:53:58,  7.17s/it]
                                                         
{'loss': 0.6645, 'learning_rate': 0.000495332127425653, 'epoch': 1.08}

  9%|▉         | 2521/28080 [4:58:49<50:53:58,  7.17s/it]
  9%|▉         | 2522/28080 [4:58:56<50:54:38,  7.17s/it]
                                                         
{'loss': 0.6591, 'learning_rate': 0.0004953265795577058, 'epoch': 1.08}

  9%|▉         | 2522/28080 [4:58:56<50:54:38,  7.17s/it]
  9%|▉         | 2523/28080 [4:59:03<50:50:51,  7.16s/it]
                                                         
{'loss': 0.6813, 'learning_rate': 0.0004953210284259416, 'epoch': 1.08}

  9%|▉         | 2523/28080 [4:59:03<50:50:51,  7.16s/it]
  9%|▉         | 2524/28080 [4:59:10<50:55:34,  7.17s/it]
                                                         
{'loss': 0.6694, 'learning_rate': 0.0004953154740304343, 'epoch': 1.08}

  9%|▉         | 2524/28080 [4:59:10<50:55:34,  7.17s/it]
  9%|▉         | 2525/28080 [4:59:17<50:56:00,  7.18s/it]
                                                         
{'loss': 0.6697, 'learning_rate': 0.0004953099163712576, 'epoch': 1.08}

  9%|▉         | 2525/28080 [4:59:17<50:56:00,  7.18s/it]
  9%|▉         | 2526/28080 [4:59:25<50:55:45,  7.17s/it]
                                                         
{'loss': 0.6542, 'learning_rate': 0.0004953043554484855, 'epoch': 1.08}

  9%|▉         | 2526/28080 [4:59:25<50:55:45,  7.17s/it]
  9%|▉         | 2527/28080 [4:59:32<50:53:02,  7.17s/it]
                                                         
{'loss': 0.668, 'learning_rate': 0.0004952987912621921, 'epoch': 1.08}

  9%|▉         | 2527/28080 [4:59:32<50:53:02,  7.17s/it]
  9%|▉         | 2528/28080 [4:59:39<50:39:56,  7.14s/it]
                                                         
{'loss': 0.6826, 'learning_rate': 0.0004952932238124514, 'epoch': 1.08}

  9%|▉         | 2528/28080 [4:59:39<50:39:56,  7.14s/it]
  9%|▉         | 2529/28080 [4:59:46<50:45:44,  7.15s/it]
                                                         
{'loss': 0.6836, 'learning_rate': 0.0004952876530993373, 'epoch': 1.08}

  9%|▉         | 2529/28080 [4:59:46<50:45:44,  7.15s/it]
  9%|▉         | 2530/28080 [4:59:53<50:52:49,  7.17s/it]
                                                         
{'loss': 0.6689, 'learning_rate': 0.000495282079122924, 'epoch': 1.08}

  9%|▉         | 2530/28080 [4:59:53<50:52:49,  7.17s/it]
  9%|▉         | 2531/28080 [5:00:00<50:44:29,  7.15s/it]
                                                         
{'loss': 0.6807, 'learning_rate': 0.0004952765018832858, 'epoch': 1.08}

  9%|▉         | 2531/28080 [5:00:00<50:44:29,  7.15s/it]
  9%|▉         | 2532/28080 [5:00:07<50:49:55,  7.16s/it]
                                                         
{'loss': 0.6744, 'learning_rate': 0.0004952709213804967, 'epoch': 1.08}

  9%|▉         | 2532/28080 [5:00:07<50:49:55,  7.16s/it]
  9%|▉         | 2533/28080 [5:00:15<50:47:21,  7.16s/it]
                                                         
{'loss': 0.6843, 'learning_rate': 0.000495265337614631, 'epoch': 1.08}

  9%|▉         | 2533/28080 [5:00:15<50:47:21,  7.16s/it]
  9%|▉         | 2534/28080 [5:00:22<50:35:50,  7.13s/it]
                                                         
{'loss': 0.6857, 'learning_rate': 0.000495259750585763, 'epoch': 1.08}

  9%|▉         | 2534/28080 [5:00:22<50:35:50,  7.13s/it]
  9%|▉         | 2535/28080 [5:00:29<50:39:10,  7.14s/it]
                                                         
{'loss': 0.6695, 'learning_rate': 0.0004952541602939671, 'epoch': 1.08}

  9%|▉         | 2535/28080 [5:00:29<50:39:10,  7.14s/it]
  9%|▉         | 2536/28080 [5:00:36<50:51:06,  7.17s/it]
                                                         
{'loss': 0.6848, 'learning_rate': 0.0004952485667393176, 'epoch': 1.08}

  9%|▉         | 2536/28080 [5:00:36<50:51:06,  7.17s/it]
  9%|▉         | 2537/28080 [5:00:43<50:44:31,  7.15s/it]
                                                         
{'loss': 0.6782, 'learning_rate': 0.0004952429699218889, 'epoch': 1.08}

  9%|▉         | 2537/28080 [5:00:43<50:44:31,  7.15s/it]
  9%|▉         | 2538/28080 [5:00:50<50:31:07,  7.12s/it]
                                                         
{'loss': 0.6784, 'learning_rate': 0.0004952373698417555, 'epoch': 1.08}

  9%|▉         | 2538/28080 [5:00:50<50:31:07,  7.12s/it]
  9%|▉         | 2539/28080 [5:00:57<50:26:29,  7.11s/it]
                                                         
{'loss': 0.6677, 'learning_rate': 0.0004952317664989919, 'epoch': 1.08}

  9%|▉         | 2539/28080 [5:00:57<50:26:29,  7.11s/it]
  9%|▉         | 2540/28080 [5:01:05<50:41:41,  7.15s/it]
                                                         
{'loss': 0.6768, 'learning_rate': 0.0004952261598936726, 'epoch': 1.09}

  9%|▉         | 2540/28080 [5:01:05<50:41:41,  7.15s/it]
  9%|▉         | 2541/28080 [5:01:12<50:40:27,  7.14s/it]
                                                         
{'loss': 0.674, 'learning_rate': 0.0004952205500258723, 'epoch': 1.09}

  9%|▉         | 2541/28080 [5:01:12<50:40:27,  7.14s/it]
  9%|▉         | 2542/28080 [5:01:19<50:48:56,  7.16s/it]
                                                         
{'loss': 0.6459, 'learning_rate': 0.0004952149368956655, 'epoch': 1.09}

  9%|▉         | 2542/28080 [5:01:19<50:48:56,  7.16s/it]
  9%|▉         | 2543/28080 [5:01:26<50:43:17,  7.15s/it]
                                                         
{'loss': 0.6951, 'learning_rate': 0.0004952093205031271, 'epoch': 1.09}

  9%|▉         | 2543/28080 [5:01:26<50:43:17,  7.15s/it]
  9%|▉         | 2544/28080 [5:01:33<50:40:36,  7.14s/it]
                                                         
{'loss': 0.6906, 'learning_rate': 0.0004952037008483315, 'epoch': 1.09}

  9%|▉         | 2544/28080 [5:01:33<50:40:36,  7.14s/it]
  9%|▉         | 2545/28080 [5:01:40<50:45:47,  7.16s/it]
                                                         
{'loss': 0.679, 'learning_rate': 0.0004951980779313536, 'epoch': 1.09}

  9%|▉         | 2545/28080 [5:01:40<50:45:47,  7.16s/it]
  9%|▉         | 2546/28080 [5:01:47<50:36:30,  7.14s/it]
                                                         
{'loss': 0.6603, 'learning_rate': 0.0004951924517522683, 'epoch': 1.09}

  9%|▉         | 2546/28080 [5:01:47<50:36:30,  7.14s/it]
  9%|▉         | 2547/28080 [5:01:55<50:37:46,  7.14s/it]
                                                         
{'loss': 0.6673, 'learning_rate': 0.0004951868223111503, 'epoch': 1.09}

  9%|▉         | 2547/28080 [5:01:55<50:37:46,  7.14s/it]
  9%|▉         | 2548/28080 [5:02:02<50:48:29,  7.16s/it]
                                                         
{'loss': 0.6838, 'learning_rate': 0.0004951811896080747, 'epoch': 1.09}

  9%|▉         | 2548/28080 [5:02:02<50:48:29,  7.16s/it]
  9%|▉         | 2549/28080 [5:02:09<50:43:44,  7.15s/it]
                                                         
{'loss': 0.7005, 'learning_rate': 0.0004951755536431162, 'epoch': 1.09}

  9%|▉         | 2549/28080 [5:02:09<50:43:44,  7.15s/it]
  9%|▉         | 2550/28080 [5:02:16<50:40:18,  7.15s/it]
                                                         
{'loss': 0.7169, 'learning_rate': 0.00049516991441635, 'epoch': 1.09}

  9%|▉         | 2550/28080 [5:02:16<50:40:18,  7.15s/it]
  9%|▉         | 2551/28080 [5:02:23<51:03:54,  7.20s/it]
                                                         
{'loss': 0.6768, 'learning_rate': 0.0004951642719278509, 'epoch': 1.09}

  9%|▉         | 2551/28080 [5:02:23<51:03:54,  7.20s/it]
  9%|▉         | 2552/28080 [5:02:31<50:57:26,  7.19s/it]
                                                         
{'loss': 0.6771, 'learning_rate': 0.0004951586261776941, 'epoch': 1.09}

  9%|▉         | 2552/28080 [5:02:31<50:57:26,  7.19s/it]
  9%|▉         | 2553/28080 [5:02:38<50:55:11,  7.18s/it]
                                                         
{'loss': 0.6877, 'learning_rate': 0.0004951529771659547, 'epoch': 1.09}

  9%|▉         | 2553/28080 [5:02:38<50:55:11,  7.18s/it]
  9%|▉         | 2554/28080 [5:02:45<50:46:52,  7.16s/it]
                                                         
{'loss': 0.7138, 'learning_rate': 0.0004951473248927079, 'epoch': 1.09}

  9%|▉         | 2554/28080 [5:02:45<50:46:52,  7.16s/it]
  9%|▉         | 2555/28080 [5:02:52<50:48:13,  7.17s/it]
                                                         
{'loss': 0.6832, 'learning_rate': 0.0004951416693580289, 'epoch': 1.09}

  9%|▉         | 2555/28080 [5:02:52<50:48:13,  7.17s/it]
  9%|▉         | 2556/28080 [5:02:59<50:41:48,  7.15s/it]
                                                         
{'loss': 0.7002, 'learning_rate': 0.0004951360105619928, 'epoch': 1.09}

  9%|▉         | 2556/28080 [5:02:59<50:41:48,  7.15s/it]
  9%|▉         | 2557/28080 [5:03:06<50:43:22,  7.15s/it]
                                                         
{'loss': 0.6686, 'learning_rate': 0.000495130348504675, 'epoch': 1.09}

  9%|▉         | 2557/28080 [5:03:06<50:43:22,  7.15s/it]
  9%|▉         | 2558/28080 [5:03:13<50:38:39,  7.14s/it]
                                                         
{'loss': 0.6858, 'learning_rate': 0.0004951246831861508, 'epoch': 1.09}

  9%|▉         | 2558/28080 [5:03:13<50:38:39,  7.14s/it]
  9%|▉         | 2559/28080 [5:03:20<50:32:40,  7.13s/it]
                                                         
{'loss': 0.6786, 'learning_rate': 0.0004951190146064955, 'epoch': 1.09}

  9%|▉         | 2559/28080 [5:03:20<50:32:40,  7.13s/it]
  9%|▉         | 2560/28080 [5:03:28<50:30:41,  7.13s/it]
                                                         
{'loss': 0.6584, 'learning_rate': 0.0004951133427657847, 'epoch': 1.09}

  9%|▉         | 2560/28080 [5:03:28<50:30:41,  7.13s/it]
  9%|▉         | 2561/28080 [5:03:35<50:24:52,  7.11s/it]
                                                         
{'loss': 0.6848, 'learning_rate': 0.0004951076676640937, 'epoch': 1.09}

  9%|▉         | 2561/28080 [5:03:35<50:24:52,  7.11s/it]
  9%|▉         | 2562/28080 [5:03:42<50:25:01,  7.11s/it]
                                                         
{'loss': 0.6839, 'learning_rate': 0.000495101989301498, 'epoch': 1.09}

  9%|▉         | 2562/28080 [5:03:42<50:25:01,  7.11s/it]
  9%|▉         | 2563/28080 [5:03:49<50:34:37,  7.14s/it]
                                                         
{'loss': 0.6558, 'learning_rate': 0.0004950963076780732, 'epoch': 1.09}

  9%|▉         | 2563/28080 [5:03:49<50:34:37,  7.14s/it]
  9%|▉         | 2564/28080 [5:03:56<50:34:28,  7.14s/it]
                                                         
{'loss': 0.689, 'learning_rate': 0.0004950906227938949, 'epoch': 1.1}

  9%|▉         | 2564/28080 [5:03:56<50:34:28,  7.14s/it]
  9%|▉         | 2565/28080 [5:04:03<50:21:48,  7.11s/it]
                                                         
{'loss': 0.6593, 'learning_rate': 0.0004950849346490388, 'epoch': 1.1}

  9%|▉         | 2565/28080 [5:04:03<50:21:48,  7.11s/it]
  9%|▉         | 2566/28080 [5:04:10<50:29:25,  7.12s/it]
                                                         
{'loss': 0.6774, 'learning_rate': 0.0004950792432435804, 'epoch': 1.1}

  9%|▉         | 2566/28080 [5:04:10<50:29:25,  7.12s/it]
  9%|▉         | 2567/28080 [5:04:18<50:44:16,  7.16s/it]
                                                         
{'loss': 0.6833, 'learning_rate': 0.0004950735485775954, 'epoch': 1.1}

  9%|▉         | 2567/28080 [5:04:18<50:44:16,  7.16s/it]
  9%|▉         | 2568/28080 [5:04:25<50:38:05,  7.15s/it]
                                                         
{'loss': 0.6819, 'learning_rate': 0.0004950678506511598, 'epoch': 1.1}

  9%|▉         | 2568/28080 [5:04:25<50:38:05,  7.15s/it]
  9%|▉         | 2569/28080 [5:04:32<50:47:43,  7.17s/it]
                                                         
{'loss': 0.6698, 'learning_rate': 0.0004950621494643492, 'epoch': 1.1}

  9%|▉         | 2569/28080 [5:04:32<50:47:43,  7.17s/it]
  9%|▉         | 2570/28080 [5:04:39<50:35:15,  7.14s/it]
                                                         
{'loss': 0.688, 'learning_rate': 0.0004950564450172397, 'epoch': 1.1}

  9%|▉         | 2570/28080 [5:04:39<50:35:15,  7.14s/it]
  9%|▉         | 2571/28080 [5:04:46<50:30:41,  7.13s/it]
                                                         
{'loss': 0.6749, 'learning_rate': 0.0004950507373099068, 'epoch': 1.1}

  9%|▉         | 2571/28080 [5:04:46<50:30:41,  7.13s/it]
  9%|▉         | 2572/28080 [5:04:53<50:24:25,  7.11s/it]
                                                         
{'loss': 0.6784, 'learning_rate': 0.0004950450263424267, 'epoch': 1.1}

  9%|▉         | 2572/28080 [5:04:53<50:24:25,  7.11s/it]
  9%|▉         | 2573/28080 [5:05:00<50:32:46,  7.13s/it]
                                                         
{'loss': 0.6571, 'learning_rate': 0.0004950393121148754, 'epoch': 1.1}

  9%|▉         | 2573/28080 [5:05:00<50:32:46,  7.13s/it]
  9%|▉         | 2574/28080 [5:05:07<50:24:20,  7.11s/it]
                                                         
{'loss': 0.6766, 'learning_rate': 0.0004950335946273287, 'epoch': 1.1}

  9%|▉         | 2574/28080 [5:05:07<50:24:20,  7.11s/it]
  9%|▉         | 2575/28080 [5:05:14<50:16:37,  7.10s/it]
                                                         
{'loss': 0.6653, 'learning_rate': 0.0004950278738798629, 'epoch': 1.1}

  9%|▉         | 2575/28080 [5:05:14<50:16:37,  7.10s/it]
  9%|▉         | 2576/28080 [5:05:22<50:15:50,  7.09s/it]
                                                         
{'loss': 0.667, 'learning_rate': 0.0004950221498725541, 'epoch': 1.1}

  9%|▉         | 2576/28080 [5:05:22<50:15:50,  7.09s/it]
  9%|▉         | 2577/28080 [5:05:29<50:26:08,  7.12s/it]
                                                         
{'loss': 0.671, 'learning_rate': 0.0004950164226054782, 'epoch': 1.1}

  9%|▉         | 2577/28080 [5:05:29<50:26:08,  7.12s/it]
  9%|▉         | 2578/28080 [5:05:36<50:20:49,  7.11s/it]
                                                         
{'loss': 0.6573, 'learning_rate': 0.0004950106920787117, 'epoch': 1.1}

  9%|▉         | 2578/28080 [5:05:36<50:20:49,  7.11s/it]
  9%|▉         | 2579/28080 [5:05:43<50:19:51,  7.11s/it]
                                                         
{'loss': 0.6857, 'learning_rate': 0.0004950049582923306, 'epoch': 1.1}

  9%|▉         | 2579/28080 [5:05:43<50:19:51,  7.11s/it]
  9%|▉         | 2580/28080 [5:05:50<50:32:01,  7.13s/it]
                                                         
{'loss': 0.6861, 'learning_rate': 0.0004949992212464113, 'epoch': 1.1}

  9%|▉         | 2580/28080 [5:05:50<50:32:01,  7.13s/it]
  9%|▉         | 2581/28080 [5:05:57<50:21:14,  7.11s/it]
                                                         
{'loss': 0.6904, 'learning_rate': 0.0004949934809410302, 'epoch': 1.1}

  9%|▉         | 2581/28080 [5:05:57<50:21:14,  7.11s/it]
  9%|▉         | 2582/28080 [5:06:04<50:37:20,  7.15s/it]
                                                         
{'loss': 0.7008, 'learning_rate': 0.0004949877373762635, 'epoch': 1.1}

  9%|▉         | 2582/28080 [5:06:04<50:37:20,  7.15s/it]
  9%|▉         | 2583/28080 [5:06:11<50:30:34,  7.13s/it]
                                                         
{'loss': 0.708, 'learning_rate': 0.0004949819905521877, 'epoch': 1.1}

  9%|▉         | 2583/28080 [5:06:11<50:30:34,  7.13s/it]
  9%|▉         | 2584/28080 [5:06:19<50:41:51,  7.16s/it]
                                                         
{'loss': 0.672, 'learning_rate': 0.0004949762404688792, 'epoch': 1.1}

  9%|▉         | 2584/28080 [5:06:19<50:41:51,  7.16s/it]
  9%|▉         | 2585/28080 [5:06:26<50:23:44,  7.12s/it]
                                                         
{'loss': 0.6924, 'learning_rate': 0.0004949704871264147, 'epoch': 1.1}

  9%|▉         | 2585/28080 [5:06:26<50:23:44,  7.12s/it]
  9%|▉         | 2586/28080 [5:06:33<50:17:09,  7.10s/it]
                                                         
{'loss': 0.696, 'learning_rate': 0.0004949647305248706, 'epoch': 1.1}

  9%|▉         | 2586/28080 [5:06:33<50:17:09,  7.10s/it]
  9%|▉         | 2587/28080 [5:06:40<50:26:18,  7.12s/it]
                                                         
{'loss': 0.677, 'learning_rate': 0.0004949589706643233, 'epoch': 1.11}

  9%|▉         | 2587/28080 [5:06:40<50:26:18,  7.12s/it]
  9%|▉         | 2588/28080 [5:06:47<50:26:24,  7.12s/it]
                                                         
{'loss': 0.6763, 'learning_rate': 0.0004949532075448497, 'epoch': 1.11}

  9%|▉         | 2588/28080 [5:06:47<50:26:24,  7.12s/it]
  9%|▉         | 2589/28080 [5:06:54<50:20:10,  7.11s/it]
                                                         
{'loss': 0.6799, 'learning_rate': 0.0004949474411665264, 'epoch': 1.11}

  9%|▉         | 2589/28080 [5:06:54<50:20:10,  7.11s/it]
  9%|▉         | 2590/28080 [5:07:01<50:24:56,  7.12s/it]
                                                         
{'loss': 0.679, 'learning_rate': 0.0004949416715294301, 'epoch': 1.11}

  9%|▉         | 2590/28080 [5:07:01<50:24:56,  7.12s/it]
  9%|▉         | 2591/28080 [5:07:08<50:31:27,  7.14s/it]
                                                         
{'loss': 0.6822, 'learning_rate': 0.0004949358986336375, 'epoch': 1.11}

  9%|▉         | 2591/28080 [5:07:08<50:31:27,  7.14s/it]
  9%|▉         | 2592/28080 [5:07:16<50:36:29,  7.15s/it]
                                                         
{'loss': 0.6759, 'learning_rate': 0.0004949301224792255, 'epoch': 1.11}

  9%|▉         | 2592/28080 [5:07:16<50:36:29,  7.15s/it]
  9%|▉         | 2593/28080 [5:07:23<50:37:30,  7.15s/it]
                                                         
{'loss': 0.6592, 'learning_rate': 0.0004949243430662709, 'epoch': 1.11}

  9%|▉         | 2593/28080 [5:07:23<50:37:30,  7.15s/it]
  9%|▉         | 2594/28080 [5:07:30<50:27:06,  7.13s/it]
                                                         
{'loss': 0.6901, 'learning_rate': 0.0004949185603948505, 'epoch': 1.11}

  9%|▉         | 2594/28080 [5:07:30<50:27:06,  7.13s/it]
  9%|▉         | 2595/28080 [5:07:37<50:43:51,  7.17s/it]
                                                         
{'loss': 0.682, 'learning_rate': 0.0004949127744650414, 'epoch': 1.11}

  9%|▉         | 2595/28080 [5:07:37<50:43:51,  7.17s/it]
  9%|▉         | 2596/28080 [5:07:44<50:44:05,  7.17s/it]
                                                         
{'loss': 0.6763, 'learning_rate': 0.0004949069852769204, 'epoch': 1.11}

  9%|▉         | 2596/28080 [5:07:44<50:44:05,  7.17s/it]
  9%|▉         | 2597/28080 [5:07:51<50:30:07,  7.13s/it]
                                                         
{'loss': 0.6743, 'learning_rate': 0.0004949011928305647, 'epoch': 1.11}

  9%|▉         | 2597/28080 [5:07:51<50:30:07,  7.13s/it]
  9%|▉         | 2598/28080 [5:07:58<50:20:51,  7.11s/it]
                                                         
{'loss': 0.6915, 'learning_rate': 0.0004948953971260514, 'epoch': 1.11}

  9%|▉         | 2598/28080 [5:07:58<50:20:51,  7.11s/it]
  9%|▉         | 2599/28080 [5:08:06<50:39:03,  7.16s/it]
                                                         
{'loss': 0.6824, 'learning_rate': 0.0004948895981634573, 'epoch': 1.11}

  9%|▉         | 2599/28080 [5:08:06<50:39:03,  7.16s/it]
  9%|▉         | 2600/28080 [5:08:13<50:30:35,  7.14s/it]
                                                         
{'loss': 0.6999, 'learning_rate': 0.0004948837959428598, 'epoch': 1.11}

  9%|▉         | 2600/28080 [5:08:13<50:30:35,  7.14s/it]
  9%|▉         | 2601/28080 [5:08:20<50:57:54,  7.20s/it]
                                                         
{'loss': 0.6857, 'learning_rate': 0.0004948779904643361, 'epoch': 1.11}

  9%|▉         | 2601/28080 [5:08:20<50:57:54,  7.20s/it]
  9%|▉         | 2602/28080 [5:08:27<50:49:41,  7.18s/it]
                                                         
{'loss': 0.6669, 'learning_rate': 0.0004948721817279632, 'epoch': 1.11}

  9%|▉         | 2602/28080 [5:08:27<50:49:41,  7.18s/it]
  9%|▉         | 2603/28080 [5:08:35<50:58:14,  7.20s/it]
                                                         
{'loss': 0.6599, 'learning_rate': 0.0004948663697338187, 'epoch': 1.11}

  9%|▉         | 2603/28080 [5:08:35<50:58:14,  7.20s/it]
  9%|▉         | 2604/28080 [5:08:42<50:48:16,  7.18s/it]
                                                         
{'loss': 0.6837, 'learning_rate': 0.0004948605544819797, 'epoch': 1.11}

  9%|▉         | 2604/28080 [5:08:42<50:48:16,  7.18s/it]
  9%|▉         | 2605/28080 [5:08:49<50:46:23,  7.18s/it]
                                                         
{'loss': 0.6711, 'learning_rate': 0.0004948547359725236, 'epoch': 1.11}

  9%|▉         | 2605/28080 [5:08:49<50:46:23,  7.18s/it]
  9%|▉         | 2606/28080 [5:08:56<50:35:12,  7.15s/it]
                                                         
{'loss': 0.6751, 'learning_rate': 0.0004948489142055279, 'epoch': 1.11}

  9%|▉         | 2606/28080 [5:08:56<50:35:12,  7.15s/it]
  9%|▉         | 2607/28080 [5:09:03<50:27:09,  7.13s/it]
                                                         
{'loss': 0.679, 'learning_rate': 0.00049484308918107, 'epoch': 1.11}

  9%|▉         | 2607/28080 [5:09:03<50:27:09,  7.13s/it]
  9%|▉         | 2608/28080 [5:09:10<50:21:22,  7.12s/it]
                                                         
{'loss': 0.6803, 'learning_rate': 0.0004948372608992273, 'epoch': 1.11}

  9%|▉         | 2608/28080 [5:09:10<50:21:22,  7.12s/it]
  9%|▉         | 2609/28080 [5:09:17<50:25:07,  7.13s/it]
                                                         
{'loss': 0.6646, 'learning_rate': 0.0004948314293600775, 'epoch': 1.11}

  9%|▉         | 2609/28080 [5:09:17<50:25:07,  7.13s/it]
  9%|▉         | 2610/28080 [5:09:24<50:22:13,  7.12s/it]
                                                         
{'loss': 0.6715, 'learning_rate': 0.0004948255945636981, 'epoch': 1.11}

  9%|▉         | 2610/28080 [5:09:24<50:22:13,  7.12s/it]
  9%|▉         | 2611/28080 [5:09:31<50:20:13,  7.12s/it]
                                                         
{'loss': 0.6988, 'learning_rate': 0.0004948197565101668, 'epoch': 1.12}

  9%|▉         | 2611/28080 [5:09:31<50:20:13,  7.12s/it]
  9%|▉         | 2612/28080 [5:09:39<50:35:32,  7.15s/it]
                                                         
{'loss': 0.677, 'learning_rate': 0.0004948139151995611, 'epoch': 1.12}

  9%|▉         | 2612/28080 [5:09:39<50:35:32,  7.15s/it]
  9%|▉         | 2613/28080 [5:09:46<50:40:48,  7.16s/it]
                                                         
{'loss': 0.6675, 'learning_rate': 0.0004948080706319588, 'epoch': 1.12}

  9%|▉         | 2613/28080 [5:09:46<50:40:48,  7.16s/it]
  9%|▉         | 2614/28080 [5:09:53<50:31:53,  7.14s/it]
                                                         
{'loss': 0.6685, 'learning_rate': 0.0004948022228074378, 'epoch': 1.12}

  9%|▉         | 2614/28080 [5:09:53<50:31:53,  7.14s/it]
  9%|▉         | 2615/28080 [5:10:00<50:51:28,  7.19s/it]
                                                         
{'loss': 0.6824, 'learning_rate': 0.0004947963717260757, 'epoch': 1.12}

  9%|▉         | 2615/28080 [5:10:00<50:51:28,  7.19s/it]
  9%|▉         | 2616/28080 [5:10:07<50:53:21,  7.19s/it]
                                                         
{'loss': 0.6761, 'learning_rate': 0.0004947905173879505, 'epoch': 1.12}

  9%|▉         | 2616/28080 [5:10:07<50:53:21,  7.19s/it]
  9%|▉         | 2617/28080 [5:10:15<50:52:59,  7.19s/it]
                                                         
{'loss': 0.6626, 'learning_rate': 0.0004947846597931399, 'epoch': 1.12}

  9%|▉         | 2617/28080 [5:10:15<50:52:59,  7.19s/it]
  9%|▉         | 2618/28080 [5:10:22<50:51:09,  7.19s/it]
                                                         
{'loss': 0.6772, 'learning_rate': 0.000494778798941722, 'epoch': 1.12}

  9%|▉         | 2618/28080 [5:10:22<50:51:09,  7.19s/it]
  9%|▉         | 2619/28080 [5:10:29<50:37:08,  7.16s/it]
                                                         
{'loss': 0.6676, 'learning_rate': 0.0004947729348337746, 'epoch': 1.12}

  9%|▉         | 2619/28080 [5:10:29<50:37:08,  7.16s/it]
  9%|▉         | 2620/28080 [5:10:36<50:22:30,  7.12s/it]
                                                         
{'loss': 0.6589, 'learning_rate': 0.0004947670674693758, 'epoch': 1.12}

  9%|▉         | 2620/28080 [5:10:36<50:22:30,  7.12s/it]
  9%|▉         | 2621/28080 [5:10:43<50:30:01,  7.14s/it]
                                                         
{'loss': 0.6833, 'learning_rate': 0.0004947611968486039, 'epoch': 1.12}

  9%|▉         | 2621/28080 [5:10:43<50:30:01,  7.14s/it]
  9%|▉         | 2622/28080 [5:10:50<50:20:52,  7.12s/it]
                                                         
{'loss': 0.7069, 'learning_rate': 0.0004947553229715366, 'epoch': 1.12}

  9%|▉         | 2622/28080 [5:10:50<50:20:52,  7.12s/it]
  9%|▉         | 2623/28080 [5:10:57<50:27:34,  7.14s/it]
                                                         
{'loss': 0.6697, 'learning_rate': 0.0004947494458382522, 'epoch': 1.12}

  9%|▉         | 2623/28080 [5:10:57<50:27:34,  7.14s/it]
  9%|▉         | 2624/28080 [5:11:05<50:31:53,  7.15s/it]
                                                         
{'loss': 0.6497, 'learning_rate': 0.000494743565448829, 'epoch': 1.12}

  9%|▉         | 2624/28080 [5:11:05<50:31:53,  7.15s/it]
  9%|▉         | 2625/28080 [5:11:12<50:19:42,  7.12s/it]
                                                         
{'loss': 0.6721, 'learning_rate': 0.0004947376818033452, 'epoch': 1.12}

  9%|▉         | 2625/28080 [5:11:12<50:19:42,  7.12s/it]
  9%|▉         | 2626/28080 [5:11:19<50:22:13,  7.12s/it]
                                                         
{'loss': 0.6871, 'learning_rate': 0.0004947317949018789, 'epoch': 1.12}

  9%|▉         | 2626/28080 [5:11:19<50:22:13,  7.12s/it]
  9%|▉         | 2627/28080 [5:11:26<50:14:24,  7.11s/it]
                                                         
{'loss': 0.6981, 'learning_rate': 0.0004947259047445086, 'epoch': 1.12}

  9%|▉         | 2627/28080 [5:11:26<50:14:24,  7.11s/it]
  9%|▉         | 2628/28080 [5:11:33<50:14:43,  7.11s/it]
                                                         
{'loss': 0.6764, 'learning_rate': 0.0004947200113313127, 'epoch': 1.12}

  9%|▉         | 2628/28080 [5:11:33<50:14:43,  7.11s/it]
  9%|▉         | 2629/28080 [5:11:40<50:22:08,  7.12s/it]
                                                         
{'loss': 0.654, 'learning_rate': 0.0004947141146623694, 'epoch': 1.12}

  9%|▉         | 2629/28080 [5:11:40<50:22:08,  7.12s/it]
  9%|▉         | 2630/28080 [5:11:47<50:26:01,  7.13s/it]
                                                         
{'loss': 0.6549, 'learning_rate': 0.0004947082147377573, 'epoch': 1.12}

  9%|▉         | 2630/28080 [5:11:47<50:26:01,  7.13s/it]
  9%|▉         | 2631/28080 [5:11:54<50:34:48,  7.16s/it]
                                                         
{'loss': 0.6549, 'learning_rate': 0.0004947023115575549, 'epoch': 1.12}

  9%|▉         | 2631/28080 [5:11:54<50:34:48,  7.16s/it]
  9%|▉         | 2632/28080 [5:12:02<50:36:07,  7.16s/it]
                                                         
{'loss': 0.6636, 'learning_rate': 0.0004946964051218406, 'epoch': 1.12}

  9%|▉         | 2632/28080 [5:12:02<50:36:07,  7.16s/it]
  9%|▉         | 2633/28080 [5:12:09<50:21:40,  7.12s/it]
                                                         
{'loss': 0.7126, 'learning_rate': 0.0004946904954306931, 'epoch': 1.12}

  9%|▉         | 2633/28080 [5:12:09<50:21:40,  7.12s/it]
  9%|▉         | 2634/28080 [5:12:16<50:25:10,  7.13s/it]
                                                         
{'loss': 0.6801, 'learning_rate': 0.000494684582484191, 'epoch': 1.13}

  9%|▉         | 2634/28080 [5:12:16<50:25:10,  7.13s/it]
  9%|▉         | 2635/28080 [5:12:23<50:43:03,  7.18s/it]
                                                         
{'loss': 0.6735, 'learning_rate': 0.0004946786662824128, 'epoch': 1.13}

  9%|▉         | 2635/28080 [5:12:23<50:43:03,  7.18s/it]
  9%|▉         | 2636/28080 [5:12:30<50:43:25,  7.18s/it]
                                                         
{'loss': 0.6751, 'learning_rate': 0.0004946727468254376, 'epoch': 1.13}

  9%|▉         | 2636/28080 [5:12:30<50:43:25,  7.18s/it]
  9%|▉         | 2637/28080 [5:12:37<50:38:48,  7.17s/it]
                                                         
{'loss': 0.6807, 'learning_rate': 0.0004946668241133438, 'epoch': 1.13}

  9%|▉         | 2637/28080 [5:12:37<50:38:48,  7.17s/it]
  9%|▉         | 2638/28080 [5:12:45<50:41:29,  7.17s/it]
                                                         
{'loss': 0.6785, 'learning_rate': 0.0004946608981462104, 'epoch': 1.13}

  9%|▉         | 2638/28080 [5:12:45<50:41:29,  7.17s/it]
  9%|▉         | 2639/28080 [5:12:52<50:46:15,  7.18s/it]
                                                         
{'loss': 0.6969, 'learning_rate': 0.0004946549689241161, 'epoch': 1.13}

  9%|▉         | 2639/28080 [5:12:52<50:46:15,  7.18s/it]
  9%|▉         | 2640/28080 [5:12:59<50:50:42,  7.20s/it]
                                                         
{'loss': 0.6941, 'learning_rate': 0.0004946490364471399, 'epoch': 1.13}

  9%|▉         | 2640/28080 [5:12:59<50:50:42,  7.20s/it]
  9%|▉         | 2641/28080 [5:13:06<50:42:11,  7.18s/it]
                                                         
{'loss': 0.697, 'learning_rate': 0.0004946431007153605, 'epoch': 1.13}

  9%|▉         | 2641/28080 [5:13:06<50:42:11,  7.18s/it]
  9%|▉         | 2642/28080 [5:13:13<50:41:09,  7.17s/it]
                                                         
{'loss': 0.6757, 'learning_rate': 0.0004946371617288572, 'epoch': 1.13}

  9%|▉         | 2642/28080 [5:13:13<50:41:09,  7.17s/it]
  9%|▉         | 2643/28080 [5:13:20<50:32:51,  7.15s/it]
                                                         
{'loss': 0.6954, 'learning_rate': 0.0004946312194877088, 'epoch': 1.13}

  9%|▉         | 2643/28080 [5:13:20<50:32:51,  7.15s/it]
  9%|▉         | 2644/28080 [5:13:28<50:38:10,  7.17s/it]
                                                         
{'loss': 0.6954, 'learning_rate': 0.0004946252739919943, 'epoch': 1.13}

  9%|▉         | 2644/28080 [5:13:28<50:38:10,  7.17s/it]
  9%|▉         | 2645/28080 [5:13:35<50:35:30,  7.16s/it]
                                                         
{'loss': 0.6883, 'learning_rate': 0.000494619325241793, 'epoch': 1.13}

  9%|▉         | 2645/28080 [5:13:35<50:35:30,  7.16s/it]
  9%|▉         | 2646/28080 [5:13:42<50:27:33,  7.14s/it]
                                                         
{'loss': 0.6629, 'learning_rate': 0.0004946133732371839, 'epoch': 1.13}

  9%|▉         | 2646/28080 [5:13:42<50:27:33,  7.14s/it]
  9%|▉         | 2647/28080 [5:13:49<50:40:59,  7.17s/it]
                                                         
{'loss': 0.6521, 'learning_rate': 0.0004946074179782462, 'epoch': 1.13}

  9%|▉         | 2647/28080 [5:13:49<50:40:59,  7.17s/it]
  9%|▉         | 2648/28080 [5:13:56<50:25:04,  7.14s/it]
                                                         
{'loss': 0.7105, 'learning_rate': 0.0004946014594650592, 'epoch': 1.13}

  9%|▉         | 2648/28080 [5:13:56<50:25:04,  7.14s/it]
  9%|▉         | 2649/28080 [5:14:03<50:22:31,  7.13s/it]
                                                         
{'loss': 0.6806, 'learning_rate': 0.0004945954976977021, 'epoch': 1.13}

  9%|▉         | 2649/28080 [5:14:03<50:22:31,  7.13s/it]
  9%|▉         | 2650/28080 [5:14:10<50:13:24,  7.11s/it]
                                                         
{'loss': 0.6826, 'learning_rate': 0.0004945895326762542, 'epoch': 1.13}

  9%|▉         | 2650/28080 [5:14:10<50:13:24,  7.11s/it]
  9%|▉         | 2651/28080 [5:14:18<50:26:07,  7.14s/it]
                                                         
{'loss': 0.6717, 'learning_rate': 0.0004945835644007949, 'epoch': 1.13}

  9%|▉         | 2651/28080 [5:14:18<50:26:07,  7.14s/it]
  9%|▉         | 2652/28080 [5:14:25<50:46:17,  7.19s/it]
                                                         
{'loss': 0.6639, 'learning_rate': 0.0004945775928714037, 'epoch': 1.13}

  9%|▉         | 2652/28080 [5:14:25<50:46:17,  7.19s/it]
  9%|▉         | 2653/28080 [5:14:32<50:47:37,  7.19s/it]
                                                         
{'loss': 0.6589, 'learning_rate': 0.0004945716180881598, 'epoch': 1.13}

  9%|▉         | 2653/28080 [5:14:32<50:47:37,  7.19s/it]
  9%|▉         | 2654/28080 [5:14:39<50:40:21,  7.17s/it]
                                                         
{'loss': 0.686, 'learning_rate': 0.0004945656400511429, 'epoch': 1.13}

  9%|▉         | 2654/28080 [5:14:39<50:40:21,  7.17s/it]
  9%|▉         | 2655/28080 [5:14:46<50:25:15,  7.14s/it]
                                                         
{'loss': 0.6813, 'learning_rate': 0.0004945596587604325, 'epoch': 1.13}

  9%|▉         | 2655/28080 [5:14:46<50:25:15,  7.14s/it]
  9%|▉         | 2656/28080 [5:14:53<50:21:23,  7.13s/it]
                                                         
{'loss': 0.6704, 'learning_rate': 0.0004945536742161081, 'epoch': 1.13}

  9%|▉         | 2656/28080 [5:14:53<50:21:23,  7.13s/it]
  9%|▉         | 2657/28080 [5:15:00<50:18:28,  7.12s/it]
                                                         
{'loss': 0.6812, 'learning_rate': 0.0004945476864182494, 'epoch': 1.14}

  9%|▉         | 2657/28080 [5:15:00<50:18:28,  7.12s/it]
  9%|▉         | 2658/28080 [5:15:08<50:22:09,  7.13s/it]
                                                         
{'loss': 0.6956, 'learning_rate': 0.0004945416953669359, 'epoch': 1.14}

  9%|▉         | 2658/28080 [5:15:08<50:22:09,  7.13s/it]
  9%|▉         | 2659/28080 [5:15:15<50:13:55,  7.11s/it]
                                                         
{'loss': 0.7, 'learning_rate': 0.0004945357010622476, 'epoch': 1.14}

  9%|▉         | 2659/28080 [5:15:15<50:13:55,  7.11s/it]
  9%|▉         | 2660/28080 [5:15:22<50:17:33,  7.12s/it]
                                                         
{'loss': 0.656, 'learning_rate': 0.0004945297035042639, 'epoch': 1.14}

  9%|▉         | 2660/28080 [5:15:22<50:17:33,  7.12s/it]
  9%|▉         | 2661/28080 [5:15:29<50:20:50,  7.13s/it]
                                                         
{'loss': 0.6559, 'learning_rate': 0.0004945237026930649, 'epoch': 1.14}

  9%|▉         | 2661/28080 [5:15:29<50:20:50,  7.13s/it]
  9%|▉         | 2662/28080 [5:15:36<50:23:30,  7.14s/it]
                                                         
{'loss': 0.6557, 'learning_rate': 0.0004945176986287302, 'epoch': 1.14}

  9%|▉         | 2662/28080 [5:15:36<50:23:30,  7.14s/it]
  9%|▉         | 2663/28080 [5:15:43<50:26:55,  7.15s/it]
                                                         
{'loss': 0.6634, 'learning_rate': 0.0004945116913113399, 'epoch': 1.14}

  9%|▉         | 2663/28080 [5:15:43<50:26:55,  7.15s/it]
  9%|▉         | 2664/28080 [5:15:50<50:23:42,  7.14s/it]
                                                         
{'loss': 0.6918, 'learning_rate': 0.0004945056807409736, 'epoch': 1.14}

  9%|▉         | 2664/28080 [5:15:50<50:23:42,  7.14s/it]
  9%|▉         | 2665/28080 [5:15:58<50:42:45,  7.18s/it]
                                                         
{'loss': 0.6809, 'learning_rate': 0.0004944996669177116, 'epoch': 1.14}

  9%|▉         | 2665/28080 [5:15:58<50:42:45,  7.18s/it]
  9%|▉         | 2666/28080 [5:16:05<50:55:48,  7.21s/it]
                                                         
{'loss': 0.6931, 'learning_rate': 0.0004944936498416337, 'epoch': 1.14}

  9%|▉         | 2666/28080 [5:16:05<50:55:48,  7.21s/it]
  9%|▉         | 2667/28080 [5:16:12<50:51:40,  7.20s/it]
                                                         
{'loss': 0.6659, 'learning_rate': 0.0004944876295128201, 'epoch': 1.14}

  9%|▉         | 2667/28080 [5:16:12<50:51:40,  7.20s/it]
 10%|▉         | 2668/28080 [5:16:19<50:45:50,  7.19s/it]
                                                         
{'loss': 0.6818, 'learning_rate': 0.0004944816059313507, 'epoch': 1.14}

 10%|▉         | 2668/28080 [5:16:19<50:45:50,  7.19s/it]
 10%|▉         | 2669/28080 [5:16:27<50:49:43,  7.20s/it]
                                                         
{'loss': 0.689, 'learning_rate': 0.0004944755790973059, 'epoch': 1.14}

 10%|▉         | 2669/28080 [5:16:27<50:49:43,  7.20s/it]
 10%|▉         | 2670/28080 [5:16:34<50:36:32,  7.17s/it]
                                                         
{'loss': 0.6721, 'learning_rate': 0.0004944695490107655, 'epoch': 1.14}

 10%|▉         | 2670/28080 [5:16:34<50:36:32,  7.17s/it]
 10%|▉         | 2671/28080 [5:16:41<50:36:38,  7.17s/it]
                                                         
{'loss': 0.6823, 'learning_rate': 0.0004944635156718103, 'epoch': 1.14}

 10%|▉         | 2671/28080 [5:16:41<50:36:38,  7.17s/it]
 10%|▉         | 2672/28080 [5:16:48<50:33:31,  7.16s/it]
                                                         
{'loss': 0.6646, 'learning_rate': 0.00049445747908052, 'epoch': 1.14}

 10%|▉         | 2672/28080 [5:16:48<50:33:31,  7.16s/it]
 10%|▉         | 2673/28080 [5:16:55<50:27:56,  7.15s/it]
                                                         
{'loss': 0.659, 'learning_rate': 0.0004944514392369752, 'epoch': 1.14}

 10%|▉         | 2673/28080 [5:16:55<50:27:56,  7.15s/it]
 10%|▉         | 2674/28080 [5:17:02<49:59:42,  7.08s/it]
                                                         
{'loss': 0.6809, 'learning_rate': 0.000494445396141256, 'epoch': 1.14}

 10%|▉         | 2674/28080 [5:17:02<49:59:42,  7.08s/it]
 10%|▉         | 2675/28080 [5:17:09<50:08:10,  7.10s/it]
                                                         
{'loss': 0.674, 'learning_rate': 0.0004944393497934432, 'epoch': 1.14}

 10%|▉         | 2675/28080 [5:17:09<50:08:10,  7.10s/it]
 10%|▉         | 2676/28080 [5:17:16<50:08:52,  7.11s/it]
                                                         
{'loss': 0.6856, 'learning_rate': 0.0004944333001936169, 'epoch': 1.14}

 10%|▉         | 2676/28080 [5:17:16<50:08:52,  7.11s/it]
 10%|▉         | 2677/28080 [5:17:23<50:16:56,  7.13s/it]
                                                         
{'loss': 0.6775, 'learning_rate': 0.0004944272473418578, 'epoch': 1.14}

 10%|▉         | 2677/28080 [5:17:23<50:16:56,  7.13s/it]
 10%|▉         | 2678/28080 [5:17:31<50:30:40,  7.16s/it]
                                                         
{'loss': 0.6728, 'learning_rate': 0.0004944211912382463, 'epoch': 1.14}

 10%|▉         | 2678/28080 [5:17:31<50:30:40,  7.16s/it]
 10%|▉         | 2679/28080 [5:17:38<50:45:36,  7.19s/it]
                                                         
{'loss': 0.6581, 'learning_rate': 0.000494415131882863, 'epoch': 1.14}

 10%|▉         | 2679/28080 [5:17:38<50:45:36,  7.19s/it]
 10%|▉         | 2680/28080 [5:17:45<50:28:23,  7.15s/it]
                                                         
{'loss': 0.6877, 'learning_rate': 0.0004944090692757886, 'epoch': 1.14}

 10%|▉         | 2680/28080 [5:17:45<50:28:23,  7.15s/it]
 10%|▉         | 2681/28080 [5:17:52<50:34:37,  7.17s/it]
                                                         
{'loss': 0.6679, 'learning_rate': 0.0004944030034171035, 'epoch': 1.15}

 10%|▉         | 2681/28080 [5:17:52<50:34:37,  7.17s/it]
 10%|▉         | 2682/28080 [5:17:59<50:41:23,  7.18s/it]
                                                         
{'loss': 0.677, 'learning_rate': 0.0004943969343068887, 'epoch': 1.15}

 10%|▉         | 2682/28080 [5:17:59<50:41:23,  7.18s/it]
 10%|▉         | 2683/28080 [5:18:07<50:31:33,  7.16s/it]
                                                         
{'loss': 0.6827, 'learning_rate': 0.0004943908619452248, 'epoch': 1.15}

 10%|▉         | 2683/28080 [5:18:07<50:31:33,  7.16s/it]
 10%|▉         | 2684/28080 [5:18:14<50:58:49,  7.23s/it]
                                                         
{'loss': 0.651, 'learning_rate': 0.0004943847863321927, 'epoch': 1.15}

 10%|▉         | 2684/28080 [5:18:14<50:58:49,  7.23s/it]
 10%|▉         | 2685/28080 [5:18:21<50:45:52,  7.20s/it]
                                                         
{'loss': 0.6913, 'learning_rate': 0.000494378707467873, 'epoch': 1.15}

 10%|▉         | 2685/28080 [5:18:21<50:45:52,  7.20s/it]
 10%|▉         | 2686/28080 [5:18:28<50:38:44,  7.18s/it]
                                                         
{'loss': 0.6823, 'learning_rate': 0.0004943726253523467, 'epoch': 1.15}

 10%|▉         | 2686/28080 [5:18:28<50:38:44,  7.18s/it]
 10%|▉         | 2687/28080 [5:18:35<50:37:10,  7.18s/it]
                                                         
{'loss': 0.6577, 'learning_rate': 0.0004943665399856947, 'epoch': 1.15}

 10%|▉         | 2687/28080 [5:18:35<50:37:10,  7.18s/it]
 10%|▉         | 2688/28080 [5:18:43<50:36:20,  7.17s/it]
                                                         
{'loss': 0.6826, 'learning_rate': 0.0004943604513679981, 'epoch': 1.15}

 10%|▉         | 2688/28080 [5:18:43<50:36:20,  7.17s/it]
 10%|▉         | 2689/28080 [5:18:50<50:24:29,  7.15s/it]
                                                         
{'loss': 0.6767, 'learning_rate': 0.0004943543594993378, 'epoch': 1.15}

 10%|▉         | 2689/28080 [5:18:50<50:24:29,  7.15s/it]
 10%|▉         | 2690/28080 [5:18:57<50:15:38,  7.13s/it]
                                                         
{'loss': 0.6891, 'learning_rate': 0.0004943482643797948, 'epoch': 1.15}

 10%|▉         | 2690/28080 [5:18:57<50:15:38,  7.13s/it]
 10%|▉         | 2691/28080 [5:19:04<50:14:03,  7.12s/it]
                                                         
{'loss': 0.6817, 'learning_rate': 0.0004943421660094502, 'epoch': 1.15}

 10%|▉         | 2691/28080 [5:19:04<50:14:03,  7.12s/it]
 10%|▉         | 2692/28080 [5:19:11<50:07:41,  7.11s/it]
                                                         
{'loss': 0.6771, 'learning_rate': 0.0004943360643883851, 'epoch': 1.15}

 10%|▉         | 2692/28080 [5:19:11<50:07:41,  7.11s/it]
 10%|▉         | 2693/28080 [5:19:18<50:22:32,  7.14s/it]
                                                         
{'loss': 0.6757, 'learning_rate': 0.0004943299595166808, 'epoch': 1.15}

 10%|▉         | 2693/28080 [5:19:18<50:22:32,  7.14s/it]
 10%|▉         | 2694/28080 [5:19:25<50:17:16,  7.13s/it]
                                                         
{'loss': 0.6697, 'learning_rate': 0.0004943238513944185, 'epoch': 1.15}

 10%|▉         | 2694/28080 [5:19:25<50:17:16,  7.13s/it]
 10%|▉         | 2695/28080 [5:19:32<50:09:28,  7.11s/it]
                                                         
{'loss': 0.6673, 'learning_rate': 0.0004943177400216793, 'epoch': 1.15}

 10%|▉         | 2695/28080 [5:19:32<50:09:28,  7.11s/it]
 10%|▉         | 2696/28080 [5:19:39<50:10:21,  7.12s/it]
                                                         
{'loss': 0.6848, 'learning_rate': 0.0004943116253985447, 'epoch': 1.15}

 10%|▉         | 2696/28080 [5:19:39<50:10:21,  7.12s/it]
 10%|▉         | 2697/28080 [5:19:47<50:33:25,  7.17s/it]
                                                         
{'loss': 0.6908, 'learning_rate': 0.0004943055075250958, 'epoch': 1.15}

 10%|▉         | 2697/28080 [5:19:47<50:33:25,  7.17s/it]
 10%|▉         | 2698/28080 [5:19:54<50:27:11,  7.16s/it]
                                                         
{'loss': 0.688, 'learning_rate': 0.0004942993864014144, 'epoch': 1.15}

 10%|▉         | 2698/28080 [5:19:54<50:27:11,  7.16s/it]
 10%|▉         | 2699/28080 [5:20:01<50:16:08,  7.13s/it]
                                                         
{'loss': 0.6765, 'learning_rate': 0.0004942932620275815, 'epoch': 1.15}

 10%|▉         | 2699/28080 [5:20:01<50:16:08,  7.13s/it]
 10%|▉         | 2700/28080 [5:20:08<50:29:40,  7.16s/it]
                                                         
{'loss': 0.6785, 'learning_rate': 0.0004942871344036789, 'epoch': 1.15}

 10%|▉         | 2700/28080 [5:20:08<50:29:40,  7.16s/it]
 10%|▉         | 2701/28080 [5:20:15<50:23:18,  7.15s/it]
                                                         
{'loss': 0.6721, 'learning_rate': 0.000494281003529788, 'epoch': 1.15}

 10%|▉         | 2701/28080 [5:20:15<50:23:18,  7.15s/it]
 10%|▉         | 2702/28080 [5:20:22<50:18:56,  7.14s/it]
                                                         
{'loss': 0.6848, 'learning_rate': 0.0004942748694059903, 'epoch': 1.15}

 10%|▉         | 2702/28080 [5:20:22<50:18:56,  7.14s/it]
 10%|▉         | 2703/28080 [5:20:29<50:15:35,  7.13s/it]
                                                         
{'loss': 0.6675, 'learning_rate': 0.0004942687320323674, 'epoch': 1.15}

 10%|▉         | 2703/28080 [5:20:29<50:15:35,  7.13s/it]
 10%|▉         | 2704/28080 [5:20:37<50:26:22,  7.16s/it]
                                                         
{'loss': 0.676, 'learning_rate': 0.0004942625914090011, 'epoch': 1.16}

 10%|▉         | 2704/28080 [5:20:37<50:26:22,  7.16s/it]
 10%|▉         | 2705/28080 [5:20:44<50:31:01,  7.17s/it]
                                                         
{'loss': 0.659, 'learning_rate': 0.000494256447535973, 'epoch': 1.16}

 10%|▉         | 2705/28080 [5:20:44<50:31:01,  7.17s/it]
 10%|▉         | 2706/28080 [5:20:51<50:24:55,  7.15s/it]
                                                         
{'loss': 0.6809, 'learning_rate': 0.0004942503004133649, 'epoch': 1.16}

 10%|▉         | 2706/28080 [5:20:51<50:24:55,  7.15s/it]
 10%|▉         | 2707/28080 [5:20:58<50:24:51,  7.15s/it]
                                                         
{'loss': 0.6803, 'learning_rate': 0.0004942441500412584, 'epoch': 1.16}

 10%|▉         | 2707/28080 [5:20:58<50:24:51,  7.15s/it]
 10%|▉         | 2708/28080 [5:21:05<50:31:53,  7.17s/it]
                                                         
{'loss': 0.6697, 'learning_rate': 0.0004942379964197357, 'epoch': 1.16}

 10%|▉         | 2708/28080 [5:21:05<50:31:53,  7.17s/it]
 10%|▉         | 2709/28080 [5:21:12<50:21:47,  7.15s/it]
                                                         
{'loss': 0.656, 'learning_rate': 0.0004942318395488781, 'epoch': 1.16}

 10%|▉         | 2709/28080 [5:21:12<50:21:47,  7.15s/it]
 10%|▉         | 2710/28080 [5:21:20<50:29:39,  7.17s/it]
                                                         
{'loss': 0.6706, 'learning_rate': 0.0004942256794287681, 'epoch': 1.16}

 10%|▉         | 2710/28080 [5:21:20<50:29:39,  7.17s/it]
 10%|▉         | 2711/28080 [5:21:27<50:30:37,  7.17s/it]
                                                         
{'loss': 0.662, 'learning_rate': 0.0004942195160594873, 'epoch': 1.16}

 10%|▉         | 2711/28080 [5:21:27<50:30:37,  7.17s/it]
 10%|▉         | 2712/28080 [5:21:34<50:16:36,  7.13s/it]
                                                         
{'loss': 0.683, 'learning_rate': 0.0004942133494411177, 'epoch': 1.16}

 10%|▉         | 2712/28080 [5:21:34<50:16:36,  7.13s/it]
 10%|▉         | 2713/28080 [5:21:41<50:16:04,  7.13s/it]
                                                         
{'loss': 0.6875, 'learning_rate': 0.0004942071795737416, 'epoch': 1.16}

 10%|▉         | 2713/28080 [5:21:41<50:16:04,  7.13s/it]
 10%|▉         | 2714/28080 [5:21:48<50:19:22,  7.14s/it]
                                                         
{'loss': 0.6903, 'learning_rate': 0.0004942010064574408, 'epoch': 1.16}

 10%|▉         | 2714/28080 [5:21:48<50:19:22,  7.14s/it]
 10%|▉         | 2715/28080 [5:21:55<50:17:28,  7.14s/it]
                                                         
{'loss': 0.6632, 'learning_rate': 0.0004941948300922975, 'epoch': 1.16}

 10%|▉         | 2715/28080 [5:21:55<50:17:28,  7.14s/it]
 10%|▉         | 2716/28080 [5:22:02<50:16:38,  7.14s/it]
                                                         
{'loss': 0.6645, 'learning_rate': 0.000494188650478394, 'epoch': 1.16}

 10%|▉         | 2716/28080 [5:22:02<50:16:38,  7.14s/it]
 10%|▉         | 2717/28080 [5:22:09<49:56:57,  7.09s/it]
                                                         
{'loss': 0.6785, 'learning_rate': 0.0004941824676158124, 'epoch': 1.16}

 10%|▉         | 2717/28080 [5:22:09<49:56:57,  7.09s/it]
 10%|▉         | 2718/28080 [5:22:17<50:02:54,  7.10s/it]
                                                         
{'loss': 0.6784, 'learning_rate': 0.000494176281504635, 'epoch': 1.16}

 10%|▉         | 2718/28080 [5:22:17<50:02:54,  7.10s/it]
 10%|▉         | 2719/28080 [5:22:24<50:05:07,  7.11s/it]
                                                         
{'loss': 0.6603, 'learning_rate': 0.0004941700921449441, 'epoch': 1.16}

 10%|▉         | 2719/28080 [5:22:24<50:05:07,  7.11s/it]
 10%|▉         | 2720/28080 [5:22:31<50:11:40,  7.13s/it]
                                                         
{'loss': 0.6572, 'learning_rate': 0.0004941638995368218, 'epoch': 1.16}

 10%|▉         | 2720/28080 [5:22:31<50:11:40,  7.13s/it]
 10%|▉         | 2721/28080 [5:22:38<50:12:40,  7.13s/it]
                                                         
{'loss': 0.6824, 'learning_rate': 0.0004941577036803509, 'epoch': 1.16}

 10%|▉         | 2721/28080 [5:22:38<50:12:40,  7.13s/it]
 10%|▉         | 2722/28080 [5:22:45<50:21:54,  7.15s/it]
                                                         
{'loss': 0.6606, 'learning_rate': 0.0004941515045756137, 'epoch': 1.16}

 10%|▉         | 2722/28080 [5:22:45<50:21:54,  7.15s/it]
 10%|▉         | 2723/28080 [5:22:52<50:26:40,  7.16s/it]
                                                         
{'loss': 0.6783, 'learning_rate': 0.0004941453022226924, 'epoch': 1.16}

 10%|▉         | 2723/28080 [5:22:52<50:26:40,  7.16s/it]
 10%|▉         | 2724/28080 [5:23:00<50:21:31,  7.15s/it]
                                                         
{'loss': 0.6537, 'learning_rate': 0.0004941390966216699, 'epoch': 1.16}

 10%|▉         | 2724/28080 [5:23:00<50:21:31,  7.15s/it]
 10%|▉         | 2725/28080 [5:23:07<50:23:42,  7.16s/it]
                                                         
{'loss': 0.6616, 'learning_rate': 0.0004941328877726284, 'epoch': 1.16}

 10%|▉         | 2725/28080 [5:23:07<50:23:42,  7.16s/it]
 10%|▉         | 2726/28080 [5:23:14<50:29:56,  7.17s/it]
                                                         
{'loss': 0.6764, 'learning_rate': 0.0004941266756756509, 'epoch': 1.16}

 10%|▉         | 2726/28080 [5:23:14<50:29:56,  7.17s/it]
 10%|▉         | 2727/28080 [5:23:21<50:24:11,  7.16s/it]
                                                         
{'loss': 0.6737, 'learning_rate': 0.0004941204603308197, 'epoch': 1.16}

 10%|▉         | 2727/28080 [5:23:21<50:24:11,  7.16s/it]
 10%|▉         | 2728/28080 [5:23:28<50:34:45,  7.18s/it]
                                                         
{'loss': 0.7034, 'learning_rate': 0.0004941142417382176, 'epoch': 1.17}

 10%|▉         | 2728/28080 [5:23:28<50:34:45,  7.18s/it]
 10%|▉         | 2729/28080 [5:23:35<50:25:16,  7.16s/it]
                                                         
{'loss': 0.662, 'learning_rate': 0.0004941080198979274, 'epoch': 1.17}

 10%|▉         | 2729/28080 [5:23:35<50:25:16,  7.16s/it]
 10%|▉         | 2730/28080 [5:23:42<50:10:24,  7.13s/it]
                                                         
{'loss': 0.6869, 'learning_rate': 0.000494101794810032, 'epoch': 1.17}

 10%|▉         | 2730/28080 [5:23:42<50:10:24,  7.13s/it]
 10%|▉         | 2731/28080 [5:23:50<50:11:36,  7.13s/it]
                                                         
{'loss': 0.6691, 'learning_rate': 0.0004940955664746137, 'epoch': 1.17}

 10%|▉         | 2731/28080 [5:23:50<50:11:36,  7.13s/it]
 10%|▉         | 2732/28080 [5:23:57<50:13:05,  7.13s/it]
                                                         
{'loss': 0.6759, 'learning_rate': 0.000494089334891756, 'epoch': 1.17}

 10%|▉         | 2732/28080 [5:23:57<50:13:05,  7.13s/it]
 10%|▉         | 2733/28080 [5:24:04<50:03:16,  7.11s/it]
                                                         
{'loss': 0.6971, 'learning_rate': 0.0004940831000615414, 'epoch': 1.17}

 10%|▉         | 2733/28080 [5:24:04<50:03:16,  7.11s/it]
 10%|▉         | 2734/28080 [5:24:11<50:28:33,  7.17s/it]
                                                         
{'loss': 0.6605, 'learning_rate': 0.0004940768619840529, 'epoch': 1.17}

 10%|▉         | 2734/28080 [5:24:11<50:28:33,  7.17s/it]
 10%|▉         | 2735/28080 [5:24:18<50:30:16,  7.17s/it]
                                                         
{'loss': 0.6629, 'learning_rate': 0.0004940706206593736, 'epoch': 1.17}

 10%|▉         | 2735/28080 [5:24:18<50:30:16,  7.17s/it]
 10%|▉         | 2736/28080 [5:24:25<50:35:08,  7.19s/it]
                                                         
{'loss': 0.6634, 'learning_rate': 0.0004940643760875865, 'epoch': 1.17}

 10%|▉         | 2736/28080 [5:24:25<50:35:08,  7.19s/it]
 10%|▉         | 2737/28080 [5:24:33<50:26:39,  7.17s/it]
                                                         
{'loss': 0.6576, 'learning_rate': 0.0004940581282687747, 'epoch': 1.17}

 10%|▉         | 2737/28080 [5:24:33<50:26:39,  7.17s/it]
 10%|▉         | 2738/28080 [5:24:40<50:22:23,  7.16s/it]
                                                         
{'loss': 0.6626, 'learning_rate': 0.0004940518772030213, 'epoch': 1.17}

 10%|▉         | 2738/28080 [5:24:40<50:22:23,  7.16s/it]
 10%|▉         | 2739/28080 [5:24:47<50:09:54,  7.13s/it]
                                                         
{'loss': 0.657, 'learning_rate': 0.0004940456228904093, 'epoch': 1.17}

 10%|▉         | 2739/28080 [5:24:47<50:09:54,  7.13s/it]
 10%|▉         | 2740/28080 [5:24:54<49:59:49,  7.10s/it]
                                                         
{'loss': 0.6759, 'learning_rate': 0.0004940393653310222, 'epoch': 1.17}

 10%|▉         | 2740/28080 [5:24:54<49:59:49,  7.10s/it]
 10%|▉         | 2741/28080 [5:25:01<50:14:25,  7.14s/it]
                                                         
{'loss': 0.6711, 'learning_rate': 0.000494033104524943, 'epoch': 1.17}

 10%|▉         | 2741/28080 [5:25:01<50:14:25,  7.14s/it]
 10%|▉         | 2742/28080 [5:25:08<50:03:47,  7.11s/it]
                                                         
{'loss': 0.6567, 'learning_rate': 0.0004940268404722552, 'epoch': 1.17}

 10%|▉         | 2742/28080 [5:25:08<50:03:47,  7.11s/it]
 10%|▉         | 2743/28080 [5:25:15<50:30:50,  7.18s/it]
                                                         
{'loss': 0.6746, 'learning_rate': 0.000494020573173042, 'epoch': 1.17}

 10%|▉         | 2743/28080 [5:25:15<50:30:50,  7.18s/it]
 10%|▉         | 2744/28080 [5:25:22<50:13:07,  7.14s/it]
                                                         
{'loss': 0.6935, 'learning_rate': 0.0004940143026273868, 'epoch': 1.17}

 10%|▉         | 2744/28080 [5:25:22<50:13:07,  7.14s/it]
 10%|▉         | 2745/28080 [5:25:30<50:17:30,  7.15s/it]
                                                         
{'loss': 0.6964, 'learning_rate': 0.000494008028835373, 'epoch': 1.17}

 10%|▉         | 2745/28080 [5:25:30<50:17:30,  7.15s/it]
 10%|▉         | 2746/28080 [5:25:37<50:17:40,  7.15s/it]
                                                         
{'loss': 0.6842, 'learning_rate': 0.0004940017517970842, 'epoch': 1.17}

 10%|▉         | 2746/28080 [5:25:37<50:17:40,  7.15s/it]
 10%|▉         | 2747/28080 [5:25:44<50:17:22,  7.15s/it]
                                                         
{'loss': 0.6799, 'learning_rate': 0.0004939954715126037, 'epoch': 1.17}

 10%|▉         | 2747/28080 [5:25:44<50:17:22,  7.15s/it]
 10%|▉         | 2748/28080 [5:25:51<50:20:57,  7.16s/it]
                                                         
{'loss': 0.673, 'learning_rate': 0.0004939891879820153, 'epoch': 1.17}

 10%|▉         | 2748/28080 [5:25:51<50:20:57,  7.16s/it]
 10%|▉         | 2749/28080 [5:25:58<50:23:35,  7.16s/it]
                                                         
{'loss': 0.6896, 'learning_rate': 0.0004939829012054023, 'epoch': 1.17}

 10%|▉         | 2749/28080 [5:25:58<50:23:35,  7.16s/it]
 10%|▉         | 2750/28080 [5:26:05<50:18:04,  7.15s/it]
                                                         
{'loss': 0.6638, 'learning_rate': 0.0004939766111828486, 'epoch': 1.17}

 10%|▉         | 2750/28080 [5:26:05<50:18:04,  7.15s/it]
 10%|▉         | 2751/28080 [5:26:13<50:17:46,  7.15s/it]
                                                         
{'loss': 0.6728, 'learning_rate': 0.0004939703179144379, 'epoch': 1.18}

 10%|▉         | 2751/28080 [5:26:13<50:17:46,  7.15s/it]
 10%|▉         | 2752/28080 [5:26:20<50:13:40,  7.14s/it]
                                                         
{'loss': 0.6609, 'learning_rate': 0.0004939640214002537, 'epoch': 1.18}

 10%|▉         | 2752/28080 [5:26:20<50:13:40,  7.14s/it]
 10%|▉         | 2753/28080 [5:26:27<50:01:11,  7.11s/it]
                                                         
{'loss': 0.682, 'learning_rate': 0.0004939577216403798, 'epoch': 1.18}

 10%|▉         | 2753/28080 [5:26:27<50:01:11,  7.11s/it]
 10%|▉         | 2754/28080 [5:26:34<50:10:55,  7.13s/it]
                                                         
{'loss': 0.6606, 'learning_rate': 0.0004939514186349001, 'epoch': 1.18}

 10%|▉         | 2754/28080 [5:26:34<50:10:55,  7.13s/it]
 10%|▉         | 2755/28080 [5:26:41<49:53:21,  7.09s/it]
                                                         
{'loss': 0.6859, 'learning_rate': 0.0004939451123838986, 'epoch': 1.18}

 10%|▉         | 2755/28080 [5:26:41<49:53:21,  7.09s/it]
 10%|▉         | 2756/28080 [5:26:48<49:44:40,  7.07s/it]
                                                         
{'loss': 0.6804, 'learning_rate': 0.000493938802887459, 'epoch': 1.18}

 10%|▉         | 2756/28080 [5:26:48<49:44:40,  7.07s/it]
 10%|▉         | 2757/28080 [5:26:55<49:53:47,  7.09s/it]
                                                         
{'loss': 0.6585, 'learning_rate': 0.0004939324901456653, 'epoch': 1.18}

 10%|▉         | 2757/28080 [5:26:55<49:53:47,  7.09s/it]
 10%|▉         | 2758/28080 [5:27:02<49:55:51,  7.10s/it]
                                                         
{'loss': 0.7027, 'learning_rate': 0.0004939261741586013, 'epoch': 1.18}

 10%|▉         | 2758/28080 [5:27:02<49:55:51,  7.10s/it]
 10%|▉         | 2759/28080 [5:27:09<49:57:11,  7.10s/it]
                                                         
{'loss': 0.6926, 'learning_rate': 0.0004939198549263513, 'epoch': 1.18}

 10%|▉         | 2759/28080 [5:27:09<49:57:11,  7.10s/it]
 10%|▉         | 2760/28080 [5:27:16<50:01:37,  7.11s/it]
                                                         
{'loss': 0.6851, 'learning_rate': 0.0004939135324489993, 'epoch': 1.18}

 10%|▉         | 2760/28080 [5:27:16<50:01:37,  7.11s/it]
 10%|▉         | 2761/28080 [5:27:24<50:08:36,  7.13s/it]
                                                         
{'loss': 0.6778, 'learning_rate': 0.0004939072067266293, 'epoch': 1.18}

 10%|▉         | 2761/28080 [5:27:24<50:08:36,  7.13s/it]
 10%|▉         | 2762/28080 [5:27:31<50:11:05,  7.14s/it]
                                                         
{'loss': 0.6954, 'learning_rate': 0.0004939008777593256, 'epoch': 1.18}

 10%|▉         | 2762/28080 [5:27:31<50:11:05,  7.14s/it]
 10%|▉         | 2763/28080 [5:27:38<50:29:38,  7.18s/it]
                                                         
{'loss': 0.6669, 'learning_rate': 0.0004938945455471724, 'epoch': 1.18}

 10%|▉         | 2763/28080 [5:27:38<50:29:38,  7.18s/it]
 10%|▉         | 2764/28080 [5:27:45<50:14:47,  7.15s/it]
                                                         
{'loss': 0.657, 'learning_rate': 0.0004938882100902537, 'epoch': 1.18}

 10%|▉         | 2764/28080 [5:27:45<50:14:47,  7.15s/it]
 10%|▉         | 2765/28080 [5:27:52<50:20:57,  7.16s/it]
                                                         
{'loss': 0.6573, 'learning_rate': 0.0004938818713886541, 'epoch': 1.18}

 10%|▉         | 2765/28080 [5:27:52<50:20:57,  7.16s/it]
 10%|▉         | 2766/28080 [5:27:59<50:12:56,  7.14s/it]
                                                         
{'loss': 0.6695, 'learning_rate': 0.0004938755294424578, 'epoch': 1.18}

 10%|▉         | 2766/28080 [5:27:59<50:12:56,  7.14s/it]
 10%|▉         | 2767/28080 [5:28:06<50:11:43,  7.14s/it]
                                                         
{'loss': 0.6766, 'learning_rate': 0.0004938691842517492, 'epoch': 1.18}

 10%|▉         | 2767/28080 [5:28:06<50:11:43,  7.14s/it]
 10%|▉         | 2768/28080 [5:28:14<50:04:36,  7.12s/it]
                                                         
{'loss': 0.6938, 'learning_rate': 0.0004938628358166127, 'epoch': 1.18}

 10%|▉         | 2768/28080 [5:28:14<50:04:36,  7.12s/it]
 10%|▉         | 2769/28080 [5:28:21<50:03:25,  7.12s/it]
                                                         
{'loss': 0.6869, 'learning_rate': 0.0004938564841371327, 'epoch': 1.18}

 10%|▉         | 2769/28080 [5:28:21<50:03:25,  7.12s/it]
 10%|▉         | 2770/28080 [5:28:28<50:08:32,  7.13s/it]
                                                         
{'loss': 0.6721, 'learning_rate': 0.0004938501292133938, 'epoch': 1.18}

 10%|▉         | 2770/28080 [5:28:28<50:08:32,  7.13s/it]
 10%|▉         | 2771/28080 [5:28:35<50:14:08,  7.15s/it]
                                                         
{'loss': 0.6816, 'learning_rate': 0.0004938437710454804, 'epoch': 1.18}

 10%|▉         | 2771/28080 [5:28:35<50:14:08,  7.15s/it]
 10%|▉         | 2772/28080 [5:28:42<50:41:10,  7.21s/it]
                                                         
{'loss': 0.6812, 'learning_rate': 0.0004938374096334772, 'epoch': 1.18}

 10%|▉         | 2772/28080 [5:28:42<50:41:10,  7.21s/it]
 10%|▉         | 2773/28080 [5:28:50<50:38:56,  7.21s/it]
                                                         
{'loss': 0.6576, 'learning_rate': 0.0004938310449774689, 'epoch': 1.18}

 10%|▉         | 2773/28080 [5:28:50<50:38:56,  7.21s/it]
 10%|▉         | 2774/28080 [5:28:57<50:32:43,  7.19s/it]
                                                         
{'loss': 0.6613, 'learning_rate': 0.00049382467707754, 'epoch': 1.19}

 10%|▉         | 2774/28080 [5:28:57<50:32:43,  7.19s/it]
 10%|▉         | 2775/28080 [5:29:04<50:25:35,  7.17s/it]
                                                         
{'loss': 0.6953, 'learning_rate': 0.0004938183059337753, 'epoch': 1.19}

 10%|▉         | 2775/28080 [5:29:04<50:25:35,  7.17s/it]
 10%|▉         | 2776/28080 [5:29:11<50:19:36,  7.16s/it]
                                                         
{'loss': 0.6706, 'learning_rate': 0.0004938119315462597, 'epoch': 1.19}

 10%|▉         | 2776/28080 [5:29:11<50:19:36,  7.16s/it]
 10%|▉         | 2777/28080 [5:29:18<50:27:03,  7.18s/it]
                                                         
{'loss': 0.6603, 'learning_rate': 0.0004938055539150778, 'epoch': 1.19}

 10%|▉         | 2777/28080 [5:29:18<50:27:03,  7.18s/it]
 10%|▉         | 2778/28080 [5:29:25<50:13:55,  7.15s/it]
                                                         
{'loss': 0.6732, 'learning_rate': 0.0004937991730403146, 'epoch': 1.19}

 10%|▉         | 2778/28080 [5:29:25<50:13:55,  7.15s/it]
 10%|▉         | 2779/28080 [5:29:33<50:24:35,  7.17s/it]
                                                         
{'loss': 0.6582, 'learning_rate': 0.0004937927889220548, 'epoch': 1.19}

 10%|▉         | 2779/28080 [5:29:33<50:24:35,  7.17s/it]
 10%|▉         | 2780/28080 [5:29:40<50:47:05,  7.23s/it]
                                                         
{'loss': 0.6592, 'learning_rate': 0.0004937864015603834, 'epoch': 1.19}

 10%|▉         | 2780/28080 [5:29:40<50:47:05,  7.23s/it]
 10%|▉         | 2781/28080 [5:29:47<50:41:51,  7.21s/it]
                                                         
{'loss': 0.671, 'learning_rate': 0.0004937800109553856, 'epoch': 1.19}

 10%|▉         | 2781/28080 [5:29:47<50:41:51,  7.21s/it]
 10%|▉         | 2782/28080 [5:29:54<50:25:54,  7.18s/it]
                                                         
{'loss': 0.6581, 'learning_rate': 0.0004937736171071462, 'epoch': 1.19}

 10%|▉         | 2782/28080 [5:29:54<50:25:54,  7.18s/it]
 10%|▉         | 2783/28080 [5:30:01<50:12:28,  7.15s/it]
                                                         
{'loss': 0.6755, 'learning_rate': 0.0004937672200157503, 'epoch': 1.19}

 10%|▉         | 2783/28080 [5:30:01<50:12:28,  7.15s/it]
 10%|▉         | 2784/28080 [5:30:08<50:04:06,  7.13s/it]
                                                         
{'loss': 0.6827, 'learning_rate': 0.000493760819681283, 'epoch': 1.19}

 10%|▉         | 2784/28080 [5:30:08<50:04:06,  7.13s/it]
 10%|▉         | 2785/28080 [5:30:16<50:18:35,  7.16s/it]
                                                         
{'loss': 0.6909, 'learning_rate': 0.0004937544161038295, 'epoch': 1.19}

 10%|▉         | 2785/28080 [5:30:16<50:18:35,  7.16s/it]
 10%|▉         | 2786/28080 [5:30:23<50:00:05,  7.12s/it]
                                                         
{'loss': 0.6855, 'learning_rate': 0.0004937480092834749, 'epoch': 1.19}

 10%|▉         | 2786/28080 [5:30:23<50:00:05,  7.12s/it]
 10%|▉         | 2787/28080 [5:30:30<50:03:34,  7.13s/it]
                                                         
{'loss': 0.6876, 'learning_rate': 0.0004937415992203046, 'epoch': 1.19}

 10%|▉         | 2787/28080 [5:30:30<50:03:34,  7.13s/it]
 10%|▉         | 2788/28080 [5:30:37<49:50:31,  7.09s/it]
                                                         
{'loss': 0.6834, 'learning_rate': 0.0004937351859144037, 'epoch': 1.19}

 10%|▉         | 2788/28080 [5:30:37<49:50:31,  7.09s/it]
 10%|▉         | 2789/28080 [5:30:44<49:56:17,  7.11s/it]
                                                         
{'loss': 0.6874, 'learning_rate': 0.0004937287693658575, 'epoch': 1.19}

 10%|▉         | 2789/28080 [5:30:44<49:56:17,  7.11s/it]
 10%|▉         | 2790/28080 [5:30:51<49:58:46,  7.11s/it]
                                                         
{'loss': 0.6751, 'learning_rate': 0.0004937223495747516, 'epoch': 1.19}

 10%|▉         | 2790/28080 [5:30:51<49:58:46,  7.11s/it]
 10%|▉         | 2791/28080 [5:30:58<50:06:59,  7.13s/it]
                                                         
{'loss': 0.6742, 'learning_rate': 0.0004937159265411713, 'epoch': 1.19}

 10%|▉         | 2791/28080 [5:30:58<50:06:59,  7.13s/it]
 10%|▉         | 2792/28080 [5:31:05<49:49:12,  7.09s/it]
                                                         
{'loss': 0.6775, 'learning_rate': 0.0004937095002652019, 'epoch': 1.19}

 10%|▉         | 2792/28080 [5:31:05<49:49:12,  7.09s/it]
 10%|▉         | 2793/28080 [5:31:12<50:00:55,  7.12s/it]
                                                         
{'loss': 0.6605, 'learning_rate': 0.0004937030707469291, 'epoch': 1.19}

 10%|▉         | 2793/28080 [5:31:12<50:00:55,  7.12s/it]
 10%|▉         | 2794/28080 [5:31:19<50:04:31,  7.13s/it]
                                                         
{'loss': 0.6665, 'learning_rate': 0.0004936966379864384, 'epoch': 1.19}

 10%|▉         | 2794/28080 [5:31:20<50:04:31,  7.13s/it]
 10%|▉         | 2795/28080 [5:31:27<50:08:20,  7.14s/it]
                                                         
{'loss': 0.6797, 'learning_rate': 0.0004936902019838153, 'epoch': 1.19}

 10%|▉         | 2795/28080 [5:31:27<50:08:20,  7.14s/it]
 10%|▉         | 2796/28080 [5:31:34<50:07:23,  7.14s/it]
                                                         
{'loss': 0.6857, 'learning_rate': 0.0004936837627391454, 'epoch': 1.19}

 10%|▉         | 2796/28080 [5:31:34<50:07:23,  7.14s/it]
 10%|▉         | 2797/28080 [5:31:41<50:13:12,  7.15s/it]
                                                         
{'loss': 0.6692, 'learning_rate': 0.0004936773202525146, 'epoch': 1.19}

 10%|▉         | 2797/28080 [5:31:41<50:13:12,  7.15s/it]
 10%|▉         | 2798/28080 [5:31:48<50:22:25,  7.17s/it]
                                                         
{'loss': 0.6747, 'learning_rate': 0.0004936708745240083, 'epoch': 1.2}

 10%|▉         | 2798/28080 [5:31:48<50:22:25,  7.17s/it]
 10%|▉         | 2799/28080 [5:31:55<50:12:56,  7.15s/it]
                                                         
{'loss': 0.6735, 'learning_rate': 0.0004936644255537124, 'epoch': 1.2}

 10%|▉         | 2799/28080 [5:31:55<50:12:56,  7.15s/it]
 10%|▉         | 2800/28080 [5:32:02<50:10:17,  7.14s/it]
                                                         
{'loss': 0.6835, 'learning_rate': 0.0004936579733417127, 'epoch': 1.2}

 10%|▉         | 2800/28080 [5:32:02<50:10:17,  7.14s/it]
 10%|▉         | 2801/28080 [5:32:10<50:11:00,  7.15s/it]
                                                         
{'loss': 0.6813, 'learning_rate': 0.000493651517888095, 'epoch': 1.2}

 10%|▉         | 2801/28080 [5:32:10<50:11:00,  7.15s/it]
 10%|▉         | 2802/28080 [5:32:17<50:18:43,  7.17s/it]
                                                         
{'loss': 0.6794, 'learning_rate': 0.0004936450591929453, 'epoch': 1.2}

 10%|▉         | 2802/28080 [5:32:17<50:18:43,  7.17s/it]
 10%|▉         | 2803/28080 [5:32:24<50:17:04,  7.16s/it]
                                                         
{'loss': 0.6815, 'learning_rate': 0.0004936385972563494, 'epoch': 1.2}

 10%|▉         | 2803/28080 [5:32:24<50:17:04,  7.16s/it]
 10%|▉         | 2804/28080 [5:32:31<50:28:09,  7.19s/it]
                                                         
{'loss': 0.6762, 'learning_rate': 0.0004936321320783933, 'epoch': 1.2}

 10%|▉         | 2804/28080 [5:32:31<50:28:09,  7.19s/it]
 10%|▉         | 2805/28080 [5:32:38<50:22:58,  7.18s/it]
                                                         
{'loss': 0.6691, 'learning_rate': 0.000493625663659163, 'epoch': 1.2}

 10%|▉         | 2805/28080 [5:32:38<50:22:58,  7.18s/it]
 10%|▉         | 2806/28080 [5:32:45<50:14:37,  7.16s/it]
                                                         
{'loss': 0.6565, 'learning_rate': 0.0004936191919987446, 'epoch': 1.2}

 10%|▉         | 2806/28080 [5:32:45<50:14:37,  7.16s/it]
 10%|▉         | 2807/28080 [5:32:53<50:04:37,  7.13s/it]
                                                         
{'loss': 0.6731, 'learning_rate': 0.0004936127170972243, 'epoch': 1.2}

 10%|▉         | 2807/28080 [5:32:53<50:04:37,  7.13s/it]
 10%|█         | 2808/28080 [5:33:00<50:05:18,  7.14s/it]
                                                         
{'loss': 0.6609, 'learning_rate': 0.000493606238954688, 'epoch': 1.2}

 10%|█         | 2808/28080 [5:33:00<50:05:18,  7.14s/it]
 10%|█         | 2809/28080 [5:33:07<50:07:44,  7.14s/it]
                                                         
{'loss': 0.6645, 'learning_rate': 0.000493599757571222, 'epoch': 1.2}

 10%|█         | 2809/28080 [5:33:07<50:07:44,  7.14s/it]
 10%|█         | 2810/28080 [5:33:14<50:14:11,  7.16s/it]
                                                         
{'loss': 0.6708, 'learning_rate': 0.0004935932729469125, 'epoch': 1.2}

 10%|█         | 2810/28080 [5:33:14<50:14:11,  7.16s/it]
 10%|█         | 2811/28080 [5:33:21<50:08:03,  7.14s/it]
                                                         
{'loss': 0.67, 'learning_rate': 0.000493586785081846, 'epoch': 1.2}

 10%|█         | 2811/28080 [5:33:21<50:08:03,  7.14s/it]
 10%|█         | 2812/28080 [5:33:28<50:11:38,  7.15s/it]
                                                         
{'loss': 0.6946, 'learning_rate': 0.0004935802939761084, 'epoch': 1.2}

 10%|█         | 2812/28080 [5:33:28<50:11:38,  7.15s/it]
 10%|█         | 2813/28080 [5:33:36<50:20:48,  7.17s/it]
                                                         
{'loss': 0.6763, 'learning_rate': 0.0004935737996297863, 'epoch': 1.2}

 10%|█         | 2813/28080 [5:33:36<50:20:48,  7.17s/it]
 10%|█         | 2814/28080 [5:33:43<50:15:53,  7.16s/it]
                                                         
{'loss': 0.6798, 'learning_rate': 0.0004935673020429661, 'epoch': 1.2}

 10%|█         | 2814/28080 [5:33:43<50:15:53,  7.16s/it]
 10%|█         | 2815/28080 [5:33:50<50:05:48,  7.14s/it]
                                                         
{'loss': 0.7058, 'learning_rate': 0.0004935608012157344, 'epoch': 1.2}

 10%|█         | 2815/28080 [5:33:50<50:05:48,  7.14s/it]
 10%|█         | 2816/28080 [5:33:57<49:58:11,  7.12s/it]
                                                         
{'loss': 0.6798, 'learning_rate': 0.0004935542971481774, 'epoch': 1.2}

 10%|█         | 2816/28080 [5:33:57<49:58:11,  7.12s/it]
 10%|█         | 2817/28080 [5:34:04<49:56:26,  7.12s/it]
                                                         
{'loss': 0.6881, 'learning_rate': 0.0004935477898403816, 'epoch': 1.2}

 10%|█         | 2817/28080 [5:34:04<49:56:26,  7.12s/it]
 10%|█         | 2818/28080 [5:34:11<50:12:57,  7.16s/it]
                                                         
{'loss': 0.6685, 'learning_rate': 0.0004935412792924339, 'epoch': 1.2}

 10%|█         | 2818/28080 [5:34:11<50:12:57,  7.16s/it]
 10%|█         | 2819/28080 [5:34:18<50:12:05,  7.15s/it]
                                                         
{'loss': 0.6607, 'learning_rate': 0.0004935347655044206, 'epoch': 1.2}

 10%|█         | 2819/28080 [5:34:18<50:12:05,  7.15s/it]
 10%|█         | 2820/28080 [5:34:26<50:23:41,  7.18s/it]
                                                         
{'loss': 0.6676, 'learning_rate': 0.0004935282484764285, 'epoch': 1.2}

 10%|█         | 2820/28080 [5:34:26<50:23:41,  7.18s/it]
 10%|█         | 2821/28080 [5:34:33<50:19:25,  7.17s/it]
                                                         
{'loss': 0.6741, 'learning_rate': 0.0004935217282085443, 'epoch': 1.21}

 10%|█         | 2821/28080 [5:34:33<50:19:25,  7.17s/it]
 10%|█         | 2822/28080 [5:34:40<50:18:31,  7.17s/it]
                                                         
{'loss': 0.6526, 'learning_rate': 0.0004935152047008547, 'epoch': 1.21}

 10%|█         | 2822/28080 [5:34:40<50:18:31,  7.17s/it]
 10%|█         | 2823/28080 [5:34:47<50:13:04,  7.16s/it]
                                                         
{'loss': 0.6815, 'learning_rate': 0.0004935086779534467, 'epoch': 1.21}

 10%|█         | 2823/28080 [5:34:47<50:13:04,  7.16s/it]
 10%|█         | 2824/28080 [5:34:54<50:06:41,  7.14s/it]
                                                         
{'loss': 0.6614, 'learning_rate': 0.0004935021479664068, 'epoch': 1.21}

 10%|█         | 2824/28080 [5:34:54<50:06:41,  7.14s/it]
 10%|█         | 2825/28080 [5:35:01<49:57:39,  7.12s/it]
                                                         
{'loss': 0.6645, 'learning_rate': 0.0004934956147398219, 'epoch': 1.21}

 10%|█         | 2825/28080 [5:35:01<49:57:39,  7.12s/it]
 10%|█         | 2826/28080 [5:35:08<50:07:05,  7.14s/it]
                                                         
{'loss': 0.6524, 'learning_rate': 0.0004934890782737793, 'epoch': 1.21}

 10%|█         | 2826/28080 [5:35:08<50:07:05,  7.14s/it]
 10%|█         | 2827/28080 [5:35:16<50:14:50,  7.16s/it]
                                                         
{'loss': 0.6778, 'learning_rate': 0.0004934825385683655, 'epoch': 1.21}

 10%|█         | 2827/28080 [5:35:16<50:14:50,  7.16s/it]
 10%|█         | 2828/28080 [5:35:23<50:08:35,  7.15s/it]
                                                         
{'loss': 0.6567, 'learning_rate': 0.0004934759956236679, 'epoch': 1.21}

 10%|█         | 2828/28080 [5:35:23<50:08:35,  7.15s/it]
 10%|█         | 2829/28080 [5:35:30<50:10:28,  7.15s/it]
                                                         
{'loss': 0.647, 'learning_rate': 0.0004934694494397732, 'epoch': 1.21}

 10%|█         | 2829/28080 [5:35:30<50:10:28,  7.15s/it]
 10%|█         | 2830/28080 [5:35:37<50:13:06,  7.16s/it]
                                                         
{'loss': 0.6603, 'learning_rate': 0.0004934629000167688, 'epoch': 1.21}

 10%|█         | 2830/28080 [5:35:37<50:13:06,  7.16s/it]
 10%|█         | 2831/28080 [5:35:44<50:21:18,  7.18s/it]
                                                         
{'loss': 0.6553, 'learning_rate': 0.0004934563473547416, 'epoch': 1.21}

 10%|█         | 2831/28080 [5:35:44<50:21:18,  7.18s/it]
 10%|█         | 2832/28080 [5:35:51<50:08:31,  7.15s/it]
                                                         
{'loss': 0.6902, 'learning_rate': 0.0004934497914537789, 'epoch': 1.21}

 10%|█         | 2832/28080 [5:35:51<50:08:31,  7.15s/it]
 10%|█         | 2833/28080 [5:35:59<50:11:51,  7.16s/it]
                                                         
{'loss': 0.6578, 'learning_rate': 0.0004934432323139679, 'epoch': 1.21}

 10%|█         | 2833/28080 [5:35:59<50:11:51,  7.16s/it]
 10%|█         | 2834/28080 [5:36:06<50:08:39,  7.15s/it]
                                                         
{'loss': 0.6736, 'learning_rate': 0.0004934366699353957, 'epoch': 1.21}

 10%|█         | 2834/28080 [5:36:06<50:08:39,  7.15s/it]
 10%|█         | 2835/28080 [5:36:13<50:05:56,  7.14s/it]
                                                         
{'loss': 0.7016, 'learning_rate': 0.0004934301043181498, 'epoch': 1.21}

 10%|█         | 2835/28080 [5:36:13<50:05:56,  7.14s/it]
 10%|█         | 2836/28080 [5:36:20<50:08:52,  7.15s/it]
                                                         
{'loss': 0.6665, 'learning_rate': 0.0004934235354623176, 'epoch': 1.21}

 10%|█         | 2836/28080 [5:36:20<50:08:52,  7.15s/it]
 10%|█         | 2837/28080 [5:36:27<50:10:44,  7.16s/it]
                                                         
{'loss': 0.6617, 'learning_rate': 0.0004934169633679863, 'epoch': 1.21}

 10%|█         | 2837/28080 [5:36:27<50:10:44,  7.16s/it]
 10%|█         | 2838/28080 [5:36:34<50:31:05,  7.20s/it]
                                                         
{'loss': 0.6626, 'learning_rate': 0.0004934103880352434, 'epoch': 1.21}

 10%|█         | 2838/28080 [5:36:34<50:31:05,  7.20s/it]
 10%|█         | 2839/28080 [5:36:42<50:29:57,  7.20s/it]
                                                         
{'loss': 0.6538, 'learning_rate': 0.0004934038094641764, 'epoch': 1.21}

 10%|█         | 2839/28080 [5:36:42<50:29:57,  7.20s/it]
 10%|█         | 2840/28080 [5:36:49<49:59:58,  7.13s/it]
                                                         
{'loss': 0.6786, 'learning_rate': 0.0004933972276548728, 'epoch': 1.21}

 10%|█         | 2840/28080 [5:36:49<49:59:58,  7.13s/it]
 10%|█         | 2841/28080 [5:36:56<50:03:39,  7.14s/it]
                                                         
{'loss': 0.6758, 'learning_rate': 0.0004933906426074203, 'epoch': 1.21}

 10%|█         | 2841/28080 [5:36:56<50:03:39,  7.14s/it]
 10%|█         | 2842/28080 [5:37:03<50:07:48,  7.15s/it]
                                                         
{'loss': 0.6515, 'learning_rate': 0.0004933840543219063, 'epoch': 1.21}

 10%|█         | 2842/28080 [5:37:03<50:07:48,  7.15s/it]
 10%|█         | 2843/28080 [5:37:10<49:57:57,  7.13s/it]
                                                         
{'loss': 0.6675, 'learning_rate': 0.0004933774627984185, 'epoch': 1.21}

 10%|█         | 2843/28080 [5:37:10<49:57:57,  7.13s/it]
 10%|█         | 2844/28080 [5:37:17<49:56:41,  7.12s/it]
                                                         
{'loss': 0.6773, 'learning_rate': 0.0004933708680370448, 'epoch': 1.21}

 10%|█         | 2844/28080 [5:37:17<49:56:41,  7.12s/it]
 10%|█         | 2845/28080 [5:37:24<49:51:12,  7.11s/it]
                                                         
{'loss': 0.6789, 'learning_rate': 0.0004933642700378726, 'epoch': 1.22}

 10%|█         | 2845/28080 [5:37:24<49:51:12,  7.11s/it]
 10%|█         | 2846/28080 [5:37:31<50:08:15,  7.15s/it]
                                                         
{'loss': 0.6722, 'learning_rate': 0.00049335766880099, 'epoch': 1.22}

 10%|█         | 2846/28080 [5:37:31<50:08:15,  7.15s/it]
 10%|█         | 2847/28080 [5:37:39<50:01:53,  7.14s/it]
                                                         
{'loss': 0.6741, 'learning_rate': 0.0004933510643264846, 'epoch': 1.22}

 10%|█         | 2847/28080 [5:37:39<50:01:53,  7.14s/it]
 10%|█         | 2848/28080 [5:37:46<49:57:18,  7.13s/it]
                                                         
{'loss': 0.6857, 'learning_rate': 0.0004933444566144443, 'epoch': 1.22}

 10%|█         | 2848/28080 [5:37:46<49:57:18,  7.13s/it]
 10%|█         | 2849/28080 [5:37:53<49:39:35,  7.09s/it]
                                                         
{'loss': 0.696, 'learning_rate': 0.0004933378456649572, 'epoch': 1.22}

 10%|█         | 2849/28080 [5:37:53<49:39:35,  7.09s/it]
 10%|█         | 2850/28080 [5:38:00<49:49:06,  7.11s/it]
                                                         
{'loss': 0.6789, 'learning_rate': 0.0004933312314781109, 'epoch': 1.22}

 10%|█         | 2850/28080 [5:38:00<49:49:06,  7.11s/it]
 10%|█         | 2851/28080 [5:38:07<50:00:00,  7.13s/it]
                                                         
{'loss': 0.6572, 'learning_rate': 0.0004933246140539938, 'epoch': 1.22}

 10%|█         | 2851/28080 [5:38:07<50:00:00,  7.13s/it]
 10%|█         | 2852/28080 [5:38:14<49:50:34,  7.11s/it]
                                                         
{'loss': 0.6791, 'learning_rate': 0.0004933179933926936, 'epoch': 1.22}

 10%|█         | 2852/28080 [5:38:14<49:50:34,  7.11s/it]
 10%|█         | 2853/28080 [5:38:21<49:46:44,  7.10s/it]
                                                         
{'loss': 0.7081, 'learning_rate': 0.0004933113694942985, 'epoch': 1.22}

 10%|█         | 2853/28080 [5:38:21<49:46:44,  7.10s/it]
 10%|█         | 2854/28080 [5:38:28<49:43:01,  7.10s/it]
                                                         
{'loss': 0.6572, 'learning_rate': 0.0004933047423588967, 'epoch': 1.22}

 10%|█         | 2854/28080 [5:38:28<49:43:01,  7.10s/it]
 10%|█         | 2855/28080 [5:38:35<49:46:37,  7.10s/it]
                                                         
{'loss': 0.684, 'learning_rate': 0.0004932981119865762, 'epoch': 1.22}

 10%|█         | 2855/28080 [5:38:35<49:46:37,  7.10s/it]
 10%|█         | 2856/28080 [5:38:43<49:53:50,  7.12s/it]
                                                         
{'loss': 0.6566, 'learning_rate': 0.0004932914783774255, 'epoch': 1.22}

 10%|█         | 2856/28080 [5:38:43<49:53:50,  7.12s/it]
 10%|█         | 2857/28080 [5:38:50<50:05:13,  7.15s/it]
                                                         
{'loss': 0.6981, 'learning_rate': 0.0004932848415315325, 'epoch': 1.22}

 10%|█         | 2857/28080 [5:38:50<50:05:13,  7.15s/it]
 10%|█         | 2858/28080 [5:38:57<49:51:08,  7.12s/it]
                                                         
{'loss': 0.6904, 'learning_rate': 0.0004932782014489857, 'epoch': 1.22}

 10%|█         | 2858/28080 [5:38:57<49:51:08,  7.12s/it]
 10%|█         | 2859/28080 [5:39:04<49:51:01,  7.12s/it]
                                                         
{'loss': 0.677, 'learning_rate': 0.0004932715581298736, 'epoch': 1.22}

 10%|█         | 2859/28080 [5:39:04<49:51:01,  7.12s/it]
 10%|█         | 2860/28080 [5:39:11<49:51:01,  7.12s/it]
                                                         
{'loss': 0.6873, 'learning_rate': 0.0004932649115742841, 'epoch': 1.22}

 10%|█         | 2860/28080 [5:39:11<49:51:01,  7.12s/it]
 10%|█         | 2861/28080 [5:39:18<49:47:49,  7.11s/it]
                                                         
{'loss': 0.662, 'learning_rate': 0.0004932582617823061, 'epoch': 1.22}

 10%|█         | 2861/28080 [5:39:18<49:47:49,  7.11s/it]
 10%|█         | 2862/28080 [5:39:25<49:52:09,  7.12s/it]
                                                         
{'loss': 0.6777, 'learning_rate': 0.0004932516087540279, 'epoch': 1.22}

 10%|█         | 2862/28080 [5:39:25<49:52:09,  7.12s/it]
 10%|█         | 2863/28080 [5:39:32<50:02:21,  7.14s/it]
                                                         
{'loss': 0.6822, 'learning_rate': 0.0004932449524895379, 'epoch': 1.22}

 10%|█         | 2863/28080 [5:39:32<50:02:21,  7.14s/it]
 10%|█         | 2864/28080 [5:39:40<50:06:39,  7.15s/it]
                                                         
{'loss': 0.6788, 'learning_rate': 0.0004932382929889248, 'epoch': 1.22}

 10%|█         | 2864/28080 [5:39:40<50:06:39,  7.15s/it]
 10%|█         | 2865/28080 [5:39:47<50:09:25,  7.16s/it]
                                                         
{'loss': 0.6833, 'learning_rate': 0.000493231630252277, 'epoch': 1.22}

 10%|█         | 2865/28080 [5:39:47<50:09:25,  7.16s/it]
 10%|█         | 2866/28080 [5:39:54<50:14:39,  7.17s/it]
                                                         
{'loss': 0.6812, 'learning_rate': 0.0004932249642796835, 'epoch': 1.22}

 10%|█         | 2866/28080 [5:39:54<50:14:39,  7.17s/it]
 10%|█         | 2867/28080 [5:40:01<50:23:32,  7.20s/it]
                                                         
{'loss': 0.6338, 'learning_rate': 0.0004932182950712327, 'epoch': 1.22}

 10%|█         | 2867/28080 [5:40:01<50:23:32,  7.20s/it]
 10%|█         | 2868/28080 [5:40:08<50:18:27,  7.18s/it]
                                                         
{'loss': 0.657, 'learning_rate': 0.0004932116226270133, 'epoch': 1.23}

 10%|█         | 2868/28080 [5:40:08<50:18:27,  7.18s/it]
 10%|█         | 2869/28080 [5:40:16<50:17:36,  7.18s/it]
                                                         
{'loss': 0.6469, 'learning_rate': 0.0004932049469471143, 'epoch': 1.23}

 10%|█         | 2869/28080 [5:40:16<50:17:36,  7.18s/it]
 10%|█         | 2870/28080 [5:40:23<50:07:02,  7.16s/it]
                                                         
{'loss': 0.6857, 'learning_rate': 0.0004931982680316243, 'epoch': 1.23}

 10%|█         | 2870/28080 [5:40:23<50:07:02,  7.16s/it]
 10%|█         | 2871/28080 [5:40:30<50:00:14,  7.14s/it]
                                                         
{'loss': 0.6344, 'learning_rate': 0.0004931915858806323, 'epoch': 1.23}

 10%|█         | 2871/28080 [5:40:30<50:00:14,  7.14s/it]
 10%|█         | 2872/28080 [5:40:37<49:56:41,  7.13s/it]
                                                         
{'loss': 0.6584, 'learning_rate': 0.0004931849004942271, 'epoch': 1.23}

 10%|█         | 2872/28080 [5:40:37<49:56:41,  7.13s/it]
 10%|█         | 2873/28080 [5:40:44<49:59:05,  7.14s/it]
                                                         
{'loss': 0.6617, 'learning_rate': 0.0004931782118724977, 'epoch': 1.23}

 10%|█         | 2873/28080 [5:40:44<49:59:05,  7.14s/it]
 10%|█         | 2874/28080 [5:40:51<49:59:47,  7.14s/it]
                                                         
{'loss': 0.667, 'learning_rate': 0.000493171520015533, 'epoch': 1.23}

 10%|█         | 2874/28080 [5:40:51<49:59:47,  7.14s/it]
 10%|█         | 2875/28080 [5:40:58<49:58:09,  7.14s/it]
                                                         
{'loss': 0.694, 'learning_rate': 0.0004931648249234221, 'epoch': 1.23}

 10%|█         | 2875/28080 [5:40:58<49:58:09,  7.14s/it]
 10%|█         | 2876/28080 [5:41:06<50:10:01,  7.17s/it]
                                                         
{'loss': 0.6799, 'learning_rate': 0.0004931581265962541, 'epoch': 1.23}

 10%|█         | 2876/28080 [5:41:06<50:10:01,  7.17s/it]
 10%|█         | 2877/28080 [5:41:13<49:56:38,  7.13s/it]
                                                         
{'loss': 0.6773, 'learning_rate': 0.0004931514250341182, 'epoch': 1.23}

 10%|█         | 2877/28080 [5:41:13<49:56:38,  7.13s/it]
 10%|█         | 2878/28080 [5:41:20<49:55:43,  7.13s/it]
                                                         
{'loss': 0.6816, 'learning_rate': 0.0004931447202371032, 'epoch': 1.23}

 10%|█         | 2878/28080 [5:41:20<49:55:43,  7.13s/it]
 10%|█         | 2879/28080 [5:41:27<49:52:42,  7.13s/it]
                                                         
{'loss': 0.6663, 'learning_rate': 0.0004931380122052987, 'epoch': 1.23}

 10%|█         | 2879/28080 [5:41:27<49:52:42,  7.13s/it]
 10%|█         | 2880/28080 [5:41:34<49:58:31,  7.14s/it]
                                                         
{'loss': 0.6716, 'learning_rate': 0.0004931313009387938, 'epoch': 1.23}

 10%|█         | 2880/28080 [5:41:34<49:58:31,  7.14s/it]
 10%|█         | 2881/28080 [5:41:41<50:02:23,  7.15s/it]
                                                         
{'loss': 0.6485, 'learning_rate': 0.0004931245864376777, 'epoch': 1.23}

 10%|█         | 2881/28080 [5:41:41<50:02:23,  7.15s/it]
 10%|█         | 2882/28080 [5:41:48<50:04:30,  7.15s/it]
                                                         
{'loss': 0.6771, 'learning_rate': 0.0004931178687020397, 'epoch': 1.23}

 10%|█         | 2882/28080 [5:41:48<50:04:30,  7.15s/it]
 10%|█         | 2883/28080 [5:41:55<49:57:04,  7.14s/it]
                                                         
{'loss': 0.686, 'learning_rate': 0.0004931111477319694, 'epoch': 1.23}

 10%|█         | 2883/28080 [5:41:55<49:57:04,  7.14s/it]
 10%|█         | 2884/28080 [5:42:03<49:48:11,  7.12s/it]
                                                         
{'loss': 0.6706, 'learning_rate': 0.000493104423527556, 'epoch': 1.23}

 10%|█         | 2884/28080 [5:42:03<49:48:11,  7.12s/it]
 10%|█         | 2885/28080 [5:42:10<49:59:29,  7.14s/it]
                                                         
{'loss': 0.655, 'learning_rate': 0.0004930976960888891, 'epoch': 1.23}

 10%|█         | 2885/28080 [5:42:10<49:59:29,  7.14s/it]
 10%|█         | 2886/28080 [5:42:17<49:58:48,  7.14s/it]
                                                         
{'loss': 0.6645, 'learning_rate': 0.0004930909654160581, 'epoch': 1.23}

 10%|█         | 2886/28080 [5:42:17<49:58:48,  7.14s/it]
 10%|█         | 2887/28080 [5:42:24<50:11:04,  7.17s/it]
                                                         
{'loss': 0.6756, 'learning_rate': 0.0004930842315091526, 'epoch': 1.23}

 10%|█         | 2887/28080 [5:42:24<50:11:04,  7.17s/it]
 10%|█         | 2888/28080 [5:42:31<50:18:02,  7.19s/it]
                                                         
{'loss': 0.6572, 'learning_rate': 0.0004930774943682622, 'epoch': 1.23}

 10%|█         | 2888/28080 [5:42:31<50:18:02,  7.19s/it]
 10%|█         | 2889/28080 [5:42:39<50:14:10,  7.18s/it]
                                                         
{'loss': 0.7025, 'learning_rate': 0.0004930707539934766, 'epoch': 1.23}

 10%|█         | 2889/28080 [5:42:39<50:14:10,  7.18s/it]
 10%|█         | 2890/28080 [5:42:46<50:15:32,  7.18s/it]
                                                         
{'loss': 0.6692, 'learning_rate': 0.0004930640103848852, 'epoch': 1.23}

 10%|█         | 2890/28080 [5:42:46<50:15:32,  7.18s/it]
 10%|█         | 2891/28080 [5:42:53<49:52:02,  7.13s/it]
                                                         
{'loss': 0.6616, 'learning_rate': 0.0004930572635425779, 'epoch': 1.24}

 10%|█         | 2891/28080 [5:42:53<49:52:02,  7.13s/it]
 10%|█         | 2892/28080 [5:43:00<49:45:00,  7.11s/it]
                                                         
{'loss': 0.6648, 'learning_rate': 0.0004930505134666446, 'epoch': 1.24}

 10%|█         | 2892/28080 [5:43:00<49:45:00,  7.11s/it]
 10%|█         | 2893/28080 [5:43:07<49:55:45,  7.14s/it]
                                                         
{'loss': 0.6677, 'learning_rate': 0.0004930437601571749, 'epoch': 1.24}

 10%|█         | 2893/28080 [5:43:07<49:55:45,  7.14s/it]
 10%|█         | 2894/28080 [5:43:14<49:58:51,  7.14s/it]
                                                         
{'loss': 0.6677, 'learning_rate': 0.0004930370036142587, 'epoch': 1.24}

 10%|█         | 2894/28080 [5:43:14<49:58:51,  7.14s/it]
 10%|█         | 2895/28080 [5:43:21<50:02:31,  7.15s/it]
                                                         
{'loss': 0.6611, 'learning_rate': 0.0004930302438379859, 'epoch': 1.24}

 10%|█         | 2895/28080 [5:43:21<50:02:31,  7.15s/it]
 10%|█         | 2896/28080 [5:43:29<50:13:01,  7.18s/it]
                                                         
{'loss': 0.6592, 'learning_rate': 0.0004930234808284464, 'epoch': 1.24}

 10%|█         | 2896/28080 [5:43:29<50:13:01,  7.18s/it]
 10%|█         | 2897/28080 [5:43:36<50:05:15,  7.16s/it]
                                                         
{'loss': 0.6694, 'learning_rate': 0.0004930167145857303, 'epoch': 1.24}

 10%|█         | 2897/28080 [5:43:36<50:05:15,  7.16s/it]
 10%|█         | 2898/28080 [5:43:43<49:59:18,  7.15s/it]
                                                         
{'loss': 0.6436, 'learning_rate': 0.0004930099451099274, 'epoch': 1.24}

 10%|█         | 2898/28080 [5:43:43<49:59:18,  7.15s/it]
 10%|█         | 2899/28080 [5:43:50<50:03:38,  7.16s/it]
                                                         
{'loss': 0.6443, 'learning_rate': 0.0004930031724011279, 'epoch': 1.24}

 10%|█         | 2899/28080 [5:43:50<50:03:38,  7.16s/it]
 10%|█         | 2900/28080 [5:43:57<49:57:58,  7.14s/it]
                                                         
{'loss': 0.6685, 'learning_rate': 0.0004929963964594219, 'epoch': 1.24}

 10%|█         | 2900/28080 [5:43:57<49:57:58,  7.14s/it]
 10%|█         | 2901/28080 [5:44:04<50:04:58,  7.16s/it]
                                                         
{'loss': 0.6571, 'learning_rate': 0.0004929896172848995, 'epoch': 1.24}

 10%|█         | 2901/28080 [5:44:04<50:04:58,  7.16s/it]
 10%|█         | 2902/28080 [5:44:11<50:01:51,  7.15s/it]
                                                         
{'loss': 0.6758, 'learning_rate': 0.0004929828348776509, 'epoch': 1.24}

 10%|█         | 2902/28080 [5:44:11<50:01:51,  7.15s/it]
 10%|█         | 2903/28080 [5:44:19<50:04:02,  7.16s/it]
                                                         
{'loss': 0.6681, 'learning_rate': 0.0004929760492377665, 'epoch': 1.24}

 10%|█         | 2903/28080 [5:44:19<50:04:02,  7.16s/it]
 10%|█         | 2904/28080 [5:44:26<49:56:17,  7.14s/it]
                                                         
{'loss': 0.6675, 'learning_rate': 0.0004929692603653363, 'epoch': 1.24}

 10%|█         | 2904/28080 [5:44:26<49:56:17,  7.14s/it]
 10%|█         | 2905/28080 [5:44:33<50:02:35,  7.16s/it]
                                                         
{'loss': 0.685, 'learning_rate': 0.0004929624682604508, 'epoch': 1.24}

 10%|█         | 2905/28080 [5:44:33<50:02:35,  7.16s/it]
 10%|█         | 2906/28080 [5:44:40<50:02:46,  7.16s/it]
                                                         
{'loss': 0.6619, 'learning_rate': 0.0004929556729232003, 'epoch': 1.24}

 10%|█         | 2906/28080 [5:44:40<50:02:46,  7.16s/it]
 10%|█         | 2907/28080 [5:44:47<49:55:53,  7.14s/it]
                                                         
{'loss': 0.6768, 'learning_rate': 0.0004929488743536752, 'epoch': 1.24}

 10%|█         | 2907/28080 [5:44:47<49:55:53,  7.14s/it]
 10%|█         | 2908/28080 [5:44:54<49:37:30,  7.10s/it]
                                                         
{'loss': 0.6938, 'learning_rate': 0.000492942072551966, 'epoch': 1.24}

 10%|█         | 2908/28080 [5:44:54<49:37:30,  7.10s/it]
 10%|█         | 2909/28080 [5:45:01<49:36:05,  7.09s/it]
                                                         
{'loss': 0.6686, 'learning_rate': 0.0004929352675181631, 'epoch': 1.24}

 10%|█         | 2909/28080 [5:45:01<49:36:05,  7.09s/it]
 10%|█         | 2910/28080 [5:45:08<49:56:41,  7.14s/it]
                                                         
{'loss': 0.6968, 'learning_rate': 0.0004929284592523571, 'epoch': 1.24}

 10%|█         | 2910/28080 [5:45:08<49:56:41,  7.14s/it]
 10%|█         | 2911/28080 [5:45:16<49:53:45,  7.14s/it]
                                                         
{'loss': 0.6718, 'learning_rate': 0.0004929216477546386, 'epoch': 1.24}

 10%|█         | 2911/28080 [5:45:16<49:53:45,  7.14s/it]
 10%|█         | 2912/28080 [5:45:23<49:56:05,  7.14s/it]
                                                         
{'loss': 0.6737, 'learning_rate': 0.0004929148330250981, 'epoch': 1.24}

 10%|█         | 2912/28080 [5:45:23<49:56:05,  7.14s/it]
 10%|█         | 2913/28080 [5:45:30<49:41:27,  7.11s/it]
                                                         
{'loss': 0.6817, 'learning_rate': 0.0004929080150638264, 'epoch': 1.24}

 10%|█         | 2913/28080 [5:45:30<49:41:27,  7.11s/it]
 10%|█         | 2914/28080 [5:45:37<49:39:33,  7.10s/it]
                                                         
{'loss': 0.6868, 'learning_rate': 0.0004929011938709142, 'epoch': 1.24}

 10%|█         | 2914/28080 [5:45:37<49:39:33,  7.10s/it]
 10%|█         | 2915/28080 [5:45:44<49:38:48,  7.10s/it]
                                                         
{'loss': 0.6759, 'learning_rate': 0.0004928943694464522, 'epoch': 1.25}

 10%|█         | 2915/28080 [5:45:44<49:38:48,  7.10s/it]
 10%|█         | 2916/28080 [5:45:51<49:41:35,  7.11s/it]
                                                         
{'loss': 0.6976, 'learning_rate': 0.0004928875417905312, 'epoch': 1.25}

 10%|█         | 2916/28080 [5:45:51<49:41:35,  7.11s/it]
 10%|█         | 2917/28080 [5:45:58<49:59:01,  7.15s/it]
                                                         
{'loss': 0.671, 'learning_rate': 0.0004928807109032419, 'epoch': 1.25}

 10%|█         | 2917/28080 [5:45:58<49:59:01,  7.15s/it]
 10%|█         | 2918/28080 [5:46:06<50:03:31,  7.16s/it]
                                                         
{'loss': 0.6815, 'learning_rate': 0.0004928738767846755, 'epoch': 1.25}

 10%|█         | 2918/28080 [5:46:06<50:03:31,  7.16s/it]
 10%|█         | 2919/28080 [5:46:13<49:58:18,  7.15s/it]
                                                         
{'loss': 0.6651, 'learning_rate': 0.0004928670394349226, 'epoch': 1.25}

 10%|█         | 2919/28080 [5:46:13<49:58:18,  7.15s/it]
 10%|█         | 2920/28080 [5:46:20<49:42:51,  7.11s/it]
                                                         
{'loss': 0.6799, 'learning_rate': 0.0004928601988540743, 'epoch': 1.25}

 10%|█         | 2920/28080 [5:46:20<49:42:51,  7.11s/it]
 10%|█         | 2921/28080 [5:46:27<49:41:27,  7.11s/it]
                                                         
{'loss': 0.7022, 'learning_rate': 0.0004928533550422217, 'epoch': 1.25}

 10%|█         | 2921/28080 [5:46:27<49:41:27,  7.11s/it]
 10%|█         | 2922/28080 [5:46:34<49:44:52,  7.12s/it]
                                                         
{'loss': 0.6758, 'learning_rate': 0.0004928465079994556, 'epoch': 1.25}

 10%|█         | 2922/28080 [5:46:34<49:44:52,  7.12s/it]
 10%|█         | 2923/28080 [5:46:41<49:46:10,  7.12s/it]
                                                         
{'loss': 0.6501, 'learning_rate': 0.0004928396577258673, 'epoch': 1.25}

 10%|█         | 2923/28080 [5:46:41<49:46:10,  7.12s/it]
 10%|█         | 2924/28080 [5:46:48<49:47:38,  7.13s/it]
                                                         
{'loss': 0.7025, 'learning_rate': 0.0004928328042215479, 'epoch': 1.25}

 10%|█         | 2924/28080 [5:46:48<49:47:38,  7.13s/it]
 10%|█         | 2925/28080 [5:46:55<49:41:04,  7.11s/it]
                                                         
{'loss': 0.6668, 'learning_rate': 0.0004928259474865884, 'epoch': 1.25}

 10%|█         | 2925/28080 [5:46:55<49:41:04,  7.11s/it]
 10%|█         | 2926/28080 [5:47:02<49:46:28,  7.12s/it]
                                                         
{'loss': 0.6752, 'learning_rate': 0.0004928190875210805, 'epoch': 1.25}

 10%|█         | 2926/28080 [5:47:02<49:46:28,  7.12s/it]
 10%|█         | 2927/28080 [5:47:10<49:44:29,  7.12s/it]
                                                         
{'loss': 0.6887, 'learning_rate': 0.0004928122243251149, 'epoch': 1.25}

 10%|█         | 2927/28080 [5:47:10<49:44:29,  7.12s/it]
 10%|█         | 2928/28080 [5:47:17<50:07:24,  7.17s/it]
                                                         
{'loss': 0.668, 'learning_rate': 0.0004928053578987832, 'epoch': 1.25}

 10%|█         | 2928/28080 [5:47:17<50:07:24,  7.17s/it]
 10%|█         | 2929/28080 [5:47:24<49:58:58,  7.15s/it]
                                                         
{'loss': 0.6924, 'learning_rate': 0.0004927984882421767, 'epoch': 1.25}

 10%|█         | 2929/28080 [5:47:24<49:58:58,  7.15s/it]
 10%|█         | 2930/28080 [5:47:31<49:59:29,  7.16s/it]
                                                         
{'loss': 0.6774, 'learning_rate': 0.0004927916153553869, 'epoch': 1.25}

 10%|█         | 2930/28080 [5:47:31<49:59:29,  7.16s/it]
 10%|█         | 2931/28080 [5:47:38<49:53:59,  7.14s/it]
                                                         
{'loss': 0.691, 'learning_rate': 0.000492784739238505, 'epoch': 1.25}

 10%|█         | 2931/28080 [5:47:38<49:53:59,  7.14s/it]
 10%|█         | 2932/28080 [5:47:45<49:46:36,  7.13s/it]
                                                         
{'loss': 0.6826, 'learning_rate': 0.0004927778598916227, 'epoch': 1.25}

 10%|█         | 2932/28080 [5:47:45<49:46:36,  7.13s/it]
 10%|█         | 2933/28080 [5:47:52<49:43:00,  7.12s/it]
                                                         
{'loss': 0.6634, 'learning_rate': 0.0004927709773148313, 'epoch': 1.25}

 10%|█         | 2933/28080 [5:47:52<49:43:00,  7.12s/it]
 10%|█         | 2934/28080 [5:48:00<49:58:35,  7.15s/it]
                                                         
{'loss': 0.6612, 'learning_rate': 0.0004927640915082227, 'epoch': 1.25}

 10%|█         | 2934/28080 [5:48:00<49:58:35,  7.15s/it]
 10%|█         | 2935/28080 [5:48:07<50:04:00,  7.17s/it]
                                                         
{'loss': 0.6626, 'learning_rate': 0.0004927572024718881, 'epoch': 1.25}

 10%|█         | 2935/28080 [5:48:07<50:04:00,  7.17s/it]
 10%|█         | 2936/28080 [5:48:14<49:58:00,  7.15s/it]
                                                         
{'loss': 0.6725, 'learning_rate': 0.0004927503102059196, 'epoch': 1.25}

 10%|█         | 2936/28080 [5:48:14<49:58:00,  7.15s/it]
 10%|█         | 2937/28080 [5:48:21<49:55:59,  7.15s/it]
                                                         
{'loss': 0.6732, 'learning_rate': 0.0004927434147104084, 'epoch': 1.25}

 10%|█         | 2937/28080 [5:48:21<49:55:59,  7.15s/it]
 10%|█         | 2938/28080 [5:48:28<49:51:45,  7.14s/it]
                                                         
{'loss': 0.6629, 'learning_rate': 0.0004927365159854466, 'epoch': 1.26}

 10%|█         | 2938/28080 [5:48:28<49:51:45,  7.14s/it]
 10%|█         | 2939/28080 [5:48:35<49:55:51,  7.15s/it]
                                                         
{'loss': 0.6727, 'learning_rate': 0.0004927296140311259, 'epoch': 1.26}

 10%|█         | 2939/28080 [5:48:35<49:55:51,  7.15s/it]
 10%|█         | 2940/28080 [5:48:42<49:43:15,  7.12s/it]
                                                         
{'loss': 0.683, 'learning_rate': 0.0004927227088475381, 'epoch': 1.26}

 10%|█         | 2940/28080 [5:48:42<49:43:15,  7.12s/it]
 10%|█         | 2941/28080 [5:48:50<50:02:48,  7.17s/it]
                                                         
{'loss': 0.6402, 'learning_rate': 0.000492715800434775, 'epoch': 1.26}

 10%|█         | 2941/28080 [5:48:50<50:02:48,  7.17s/it]
 10%|█         | 2942/28080 [5:48:57<50:02:37,  7.17s/it]
                                                         
{'loss': 0.6696, 'learning_rate': 0.0004927088887929286, 'epoch': 1.26}

 10%|█         | 2942/28080 [5:48:57<50:02:37,  7.17s/it]
 10%|█         | 2943/28080 [5:49:04<50:00:35,  7.16s/it]
                                                         
{'loss': 0.6898, 'learning_rate': 0.0004927019739220908, 'epoch': 1.26}

 10%|█         | 2943/28080 [5:49:04<50:00:35,  7.16s/it]
 10%|█         | 2944/28080 [5:49:11<50:02:11,  7.17s/it]
                                                         
{'loss': 0.6568, 'learning_rate': 0.0004926950558223537, 'epoch': 1.26}

 10%|█         | 2944/28080 [5:49:11<50:02:11,  7.17s/it]
 10%|█         | 2945/28080 [5:49:18<49:54:33,  7.15s/it]
                                                         
{'loss': 0.6737, 'learning_rate': 0.0004926881344938092, 'epoch': 1.26}

 10%|█         | 2945/28080 [5:49:18<49:54:33,  7.15s/it]
 10%|█         | 2946/28080 [5:49:25<49:53:28,  7.15s/it]
                                                         
{'loss': 0.6763, 'learning_rate': 0.0004926812099365494, 'epoch': 1.26}

 10%|█         | 2946/28080 [5:49:25<49:53:28,  7.15s/it]
 10%|█         | 2947/28080 [5:49:33<49:51:36,  7.14s/it]
                                                         
{'loss': 0.668, 'learning_rate': 0.0004926742821506666, 'epoch': 1.26}

 10%|█         | 2947/28080 [5:49:33<49:51:36,  7.14s/it]
 10%|█         | 2948/28080 [5:49:40<49:52:41,  7.14s/it]
                                                         
{'loss': 0.6734, 'learning_rate': 0.0004926673511362527, 'epoch': 1.26}

 10%|█         | 2948/28080 [5:49:40<49:52:41,  7.14s/it]
 11%|█         | 2949/28080 [5:49:47<49:57:25,  7.16s/it]
                                                         
{'loss': 0.6497, 'learning_rate': 0.0004926604168934, 'epoch': 1.26}

 11%|█         | 2949/28080 [5:49:47<49:57:25,  7.16s/it]
 11%|█         | 2950/28080 [5:49:54<49:43:48,  7.12s/it]
                                                         
{'loss': 0.6795, 'learning_rate': 0.000492653479422201, 'epoch': 1.26}

 11%|█         | 2950/28080 [5:49:54<49:43:48,  7.12s/it]
 11%|█         | 2951/28080 [5:50:01<49:46:37,  7.13s/it]
                                                         
{'loss': 0.6537, 'learning_rate': 0.0004926465387227475, 'epoch': 1.26}

 11%|█         | 2951/28080 [5:50:01<49:46:37,  7.13s/it]
 11%|█         | 2952/28080 [5:50:08<49:33:08,  7.10s/it]
                                                         
{'loss': 0.6728, 'learning_rate': 0.0004926395947951323, 'epoch': 1.26}

 11%|█         | 2952/28080 [5:50:08<49:33:08,  7.10s/it]
 11%|█         | 2953/28080 [5:50:15<49:43:23,  7.12s/it]
                                                         
{'loss': 0.6535, 'learning_rate': 0.0004926326476394476, 'epoch': 1.26}

 11%|█         | 2953/28080 [5:50:15<49:43:23,  7.12s/it]
 11%|█         | 2954/28080 [5:50:22<49:43:25,  7.12s/it]
                                                         
{'loss': 0.6656, 'learning_rate': 0.0004926256972557859, 'epoch': 1.26}

 11%|█         | 2954/28080 [5:50:22<49:43:25,  7.12s/it]
 11%|█         | 2955/28080 [5:50:30<49:51:39,  7.14s/it]
                                                         
{'loss': 0.6651, 'learning_rate': 0.0004926187436442395, 'epoch': 1.26}

 11%|█         | 2955/28080 [5:50:30<49:51:39,  7.14s/it]
 11%|█         | 2956/28080 [5:50:37<49:59:29,  7.16s/it]
                                                         
{'loss': 0.7068, 'learning_rate': 0.0004926117868049011, 'epoch': 1.26}

 11%|█         | 2956/28080 [5:50:37<49:59:29,  7.16s/it]
 11%|█         | 2957/28080 [5:50:44<49:50:54,  7.14s/it]
                                                         
{'loss': 0.6726, 'learning_rate': 0.000492604826737863, 'epoch': 1.26}

 11%|█         | 2957/28080 [5:50:44<49:50:54,  7.14s/it]
 11%|█         | 2958/28080 [5:50:51<49:56:41,  7.16s/it]
                                                         
{'loss': 0.6661, 'learning_rate': 0.0004925978634432181, 'epoch': 1.26}

 11%|█         | 2958/28080 [5:50:51<49:56:41,  7.16s/it]
 11%|█         | 2959/28080 [5:50:58<50:04:30,  7.18s/it]
                                                         
{'loss': 0.647, 'learning_rate': 0.0004925908969210588, 'epoch': 1.26}

 11%|█         | 2959/28080 [5:50:58<50:04:30,  7.18s/it]
 11%|█         | 2960/28080 [5:51:05<49:54:33,  7.15s/it]
                                                         
{'loss': 0.6774, 'learning_rate': 0.0004925839271714779, 'epoch': 1.26}

 11%|█         | 2960/28080 [5:51:05<49:54:33,  7.15s/it]
 11%|█         | 2961/28080 [5:51:13<49:46:45,  7.13s/it]
                                                         
{'loss': 0.6783, 'learning_rate': 0.0004925769541945683, 'epoch': 1.26}

 11%|█         | 2961/28080 [5:51:13<49:46:45,  7.13s/it]
 11%|█         | 2962/28080 [5:51:20<49:52:06,  7.15s/it]
                                                         
{'loss': 0.667, 'learning_rate': 0.0004925699779904224, 'epoch': 1.27}

 11%|█         | 2962/28080 [5:51:20<49:52:06,  7.15s/it]
 11%|█         | 2963/28080 [5:51:27<49:56:59,  7.16s/it]
                                                         
{'loss': 0.6814, 'learning_rate': 0.0004925629985591333, 'epoch': 1.27}

 11%|█         | 2963/28080 [5:51:27<49:56:59,  7.16s/it]
 11%|█         | 2964/28080 [5:51:34<49:47:49,  7.14s/it]
                                                         
{'loss': 0.6736, 'learning_rate': 0.0004925560159007936, 'epoch': 1.27}

 11%|█         | 2964/28080 [5:51:34<49:47:49,  7.14s/it]
 11%|█         | 2965/28080 [5:51:41<49:49:13,  7.14s/it]
                                                         
{'loss': 0.6546, 'learning_rate': 0.0004925490300154964, 'epoch': 1.27}

 11%|█         | 2965/28080 [5:51:41<49:49:13,  7.14s/it]
 11%|█         | 2966/28080 [5:51:48<49:46:40,  7.14s/it]
                                                         
{'loss': 0.6568, 'learning_rate': 0.0004925420409033345, 'epoch': 1.27}

 11%|█         | 2966/28080 [5:51:48<49:46:40,  7.14s/it]
 11%|█         | 2967/28080 [5:51:56<50:00:14,  7.17s/it]
                                                         
{'loss': 0.6558, 'learning_rate': 0.0004925350485644011, 'epoch': 1.27}

 11%|█         | 2967/28080 [5:51:56<50:00:14,  7.17s/it]
 11%|█         | 2968/28080 [5:52:03<49:52:55,  7.15s/it]
                                                         
{'loss': 0.6726, 'learning_rate': 0.000492528052998789, 'epoch': 1.27}

 11%|█         | 2968/28080 [5:52:03<49:52:55,  7.15s/it]
 11%|█         | 2969/28080 [5:52:10<49:54:45,  7.16s/it]
                                                         
{'loss': 0.6595, 'learning_rate': 0.0004925210542065915, 'epoch': 1.27}

 11%|█         | 2969/28080 [5:52:10<49:54:45,  7.16s/it]
 11%|█         | 2970/28080 [5:52:17<50:06:49,  7.18s/it]
                                                         
{'loss': 0.6517, 'learning_rate': 0.0004925140521879013, 'epoch': 1.27}

 11%|█         | 2970/28080 [5:52:17<50:06:49,  7.18s/it]
 11%|█         | 2971/28080 [5:52:24<49:50:09,  7.15s/it]
                                                         
{'loss': 0.6687, 'learning_rate': 0.000492507046942812, 'epoch': 1.27}

 11%|█         | 2971/28080 [5:52:24<49:50:09,  7.15s/it]
 11%|█         | 2972/28080 [5:52:31<49:46:04,  7.14s/it]
                                                         
{'loss': 0.6663, 'learning_rate': 0.0004925000384714167, 'epoch': 1.27}

 11%|█         | 2972/28080 [5:52:31<49:46:04,  7.14s/it]
 11%|█         | 2973/28080 [5:52:38<49:37:52,  7.12s/it]
                                                         
{'loss': 0.6689, 'learning_rate': 0.0004924930267738084, 'epoch': 1.27}

 11%|█         | 2973/28080 [5:52:38<49:37:52,  7.12s/it]
 11%|█         | 2974/28080 [5:52:45<49:44:03,  7.13s/it]
                                                         
{'loss': 0.6676, 'learning_rate': 0.0004924860118500806, 'epoch': 1.27}

 11%|█         | 2974/28080 [5:52:45<49:44:03,  7.13s/it]
 11%|█         | 2975/28080 [5:52:53<49:44:09,  7.13s/it]
                                                         
{'loss': 0.6829, 'learning_rate': 0.0004924789937003266, 'epoch': 1.27}

 11%|█         | 2975/28080 [5:52:53<49:44:09,  7.13s/it]
 11%|█         | 2976/28080 [5:53:00<49:43:04,  7.13s/it]
                                                         
{'loss': 0.6509, 'learning_rate': 0.0004924719723246397, 'epoch': 1.27}

 11%|█         | 2976/28080 [5:53:00<49:43:04,  7.13s/it]
 11%|█         | 2977/28080 [5:53:07<49:40:19,  7.12s/it]
                                                         
{'loss': 0.6627, 'learning_rate': 0.0004924649477231134, 'epoch': 1.27}

 11%|█         | 2977/28080 [5:53:07<49:40:19,  7.12s/it]
 11%|█         | 2978/28080 [5:53:14<49:27:33,  7.09s/it]
                                                         
{'loss': 0.6872, 'learning_rate': 0.0004924579198958411, 'epoch': 1.27}

 11%|█         | 2978/28080 [5:53:14<49:27:33,  7.09s/it]
 11%|█         | 2979/28080 [5:53:21<49:41:30,  7.13s/it]
                                                         
{'loss': 0.6801, 'learning_rate': 0.0004924508888429163, 'epoch': 1.27}

 11%|█         | 2979/28080 [5:53:21<49:41:30,  7.13s/it]
 11%|█         | 2980/28080 [5:53:28<50:02:51,  7.18s/it]
                                                         
{'loss': 0.6654, 'learning_rate': 0.0004924438545644325, 'epoch': 1.27}

 11%|█         | 2980/28080 [5:53:28<50:02:51,  7.18s/it]
 11%|█         | 2981/28080 [5:53:35<49:50:03,  7.15s/it]
                                                         
{'loss': 0.6844, 'learning_rate': 0.0004924368170604834, 'epoch': 1.27}

 11%|█         | 2981/28080 [5:53:35<49:50:03,  7.15s/it]
 11%|█         | 2982/28080 [5:53:43<49:47:49,  7.14s/it]
                                                         
{'loss': 0.6926, 'learning_rate': 0.0004924297763311625, 'epoch': 1.27}

 11%|█         | 2982/28080 [5:53:43<49:47:49,  7.14s/it]
 11%|█         | 2983/28080 [5:53:50<49:44:09,  7.13s/it]
                                                         
{'loss': 0.6525, 'learning_rate': 0.0004924227323765635, 'epoch': 1.27}

 11%|█         | 2983/28080 [5:53:50<49:44:09,  7.13s/it]
 11%|█         | 2984/28080 [5:53:57<49:51:26,  7.15s/it]
                                                         
{'loss': 0.6387, 'learning_rate': 0.0004924156851967802, 'epoch': 1.27}

 11%|█         | 2984/28080 [5:53:57<49:51:26,  7.15s/it]
 11%|█         | 2985/28080 [5:54:04<49:40:59,  7.13s/it]
                                                         
{'loss': 0.6695, 'learning_rate': 0.0004924086347919064, 'epoch': 1.28}

 11%|█         | 2985/28080 [5:54:04<49:40:59,  7.13s/it]
 11%|█         | 2986/28080 [5:54:11<49:46:58,  7.14s/it]
                                                         
{'loss': 0.6581, 'learning_rate': 0.0004924015811620355, 'epoch': 1.28}

 11%|█         | 2986/28080 [5:54:11<49:46:58,  7.14s/it]
 11%|█         | 2987/28080 [5:54:18<49:49:41,  7.15s/it]
                                                         
{'loss': 0.6781, 'learning_rate': 0.0004923945243072619, 'epoch': 1.28}

 11%|█         | 2987/28080 [5:54:18<49:49:41,  7.15s/it]
 11%|█         | 2988/28080 [5:54:25<49:46:35,  7.14s/it]
                                                         
{'loss': 0.6628, 'learning_rate': 0.0004923874642276791, 'epoch': 1.28}

 11%|█         | 2988/28080 [5:54:25<49:46:35,  7.14s/it]
 11%|█         | 2989/28080 [5:54:32<49:38:57,  7.12s/it]
                                                         
{'loss': 0.6854, 'learning_rate': 0.0004923804009233812, 'epoch': 1.28}

 11%|█         | 2989/28080 [5:54:32<49:38:57,  7.12s/it]
 11%|█         | 2990/28080 [5:54:40<49:37:51,  7.12s/it]
                                                         
{'loss': 0.6667, 'learning_rate': 0.000492373334394462, 'epoch': 1.28}

 11%|█         | 2990/28080 [5:54:40<49:37:51,  7.12s/it]
 11%|█         | 2991/28080 [5:54:47<49:52:25,  7.16s/it]
                                                         
{'loss': 0.6658, 'learning_rate': 0.0004923662646410159, 'epoch': 1.28}

 11%|█         | 2991/28080 [5:54:47<49:52:25,  7.16s/it]
 11%|█         | 2992/28080 [5:54:54<49:37:13,  7.12s/it]
                                                         
{'loss': 0.6673, 'learning_rate': 0.0004923591916631365, 'epoch': 1.28}

 11%|█         | 2992/28080 [5:54:54<49:37:13,  7.12s/it]
 11%|█         | 2993/28080 [5:55:01<49:30:04,  7.10s/it]
                                                         
{'loss': 0.6663, 'learning_rate': 0.000492352115460918, 'epoch': 1.28}

 11%|█         | 2993/28080 [5:55:01<49:30:04,  7.10s/it]
 11%|█         | 2994/28080 [5:55:08<49:31:09,  7.11s/it]
                                                         
{'loss': 0.6822, 'learning_rate': 0.0004923450360344547, 'epoch': 1.28}

 11%|█         | 2994/28080 [5:55:08<49:31:09,  7.11s/it]
 11%|█         | 2995/28080 [5:55:15<49:29:00,  7.10s/it]
                                                         
{'loss': 0.6505, 'learning_rate': 0.0004923379533838408, 'epoch': 1.28}

 11%|█         | 2995/28080 [5:55:15<49:29:00,  7.10s/it]
 11%|█         | 2996/28080 [5:55:22<49:21:27,  7.08s/it]
                                                         
{'loss': 0.6562, 'learning_rate': 0.0004923308675091703, 'epoch': 1.28}

 11%|█         | 2996/28080 [5:55:22<49:21:27,  7.08s/it]
 11%|█         | 2997/28080 [5:55:29<49:34:54,  7.12s/it]
                                                         
{'loss': 0.6471, 'learning_rate': 0.0004923237784105377, 'epoch': 1.28}

 11%|█         | 2997/28080 [5:55:29<49:34:54,  7.12s/it]
 11%|█         | 2998/28080 [5:55:37<49:44:16,  7.14s/it]
                                                         
{'loss': 0.6893, 'learning_rate': 0.0004923166860880371, 'epoch': 1.28}

 11%|█         | 2998/28080 [5:55:37<49:44:16,  7.14s/it]
 11%|█         | 2999/28080 [5:55:44<49:42:42,  7.14s/it]
                                                         
{'loss': 0.6623, 'learning_rate': 0.0004923095905417631, 'epoch': 1.28}

 11%|█         | 2999/28080 [5:55:44<49:42:42,  7.14s/it]
 11%|█         | 3000/28080 [5:55:51<49:41:14,  7.13s/it]
                                                         
{'loss': 0.6509, 'learning_rate': 0.0004923024917718099, 'epoch': 1.28}

 11%|█         | 3000/28080 [5:55:51<49:41:14,  7.13s/it]
 11%|█         | 3001/28080 [5:55:58<49:37:31,  7.12s/it]
                                                         
{'loss': 0.644, 'learning_rate': 0.0004922953897782721, 'epoch': 1.28}

 11%|█         | 3001/28080 [5:55:58<49:37:31,  7.12s/it]
 11%|█         | 3002/28080 [5:56:05<49:44:22,  7.14s/it]
                                                         
{'loss': 0.6663, 'learning_rate': 0.000492288284561244, 'epoch': 1.28}

 11%|█         | 3002/28080 [5:56:05<49:44:22,  7.14s/it]
 11%|█         | 3003/28080 [5:56:12<49:41:51,  7.13s/it]
                                                         
{'loss': 0.6632, 'learning_rate': 0.0004922811761208203, 'epoch': 1.28}

 11%|█         | 3003/28080 [5:56:12<49:41:51,  7.13s/it]
 11%|█         | 3004/28080 [5:56:19<49:40:05,  7.13s/it]
                                                         
{'loss': 0.6554, 'learning_rate': 0.0004922740644570955, 'epoch': 1.28}

 11%|█         | 3004/28080 [5:56:19<49:40:05,  7.13s/it]
 11%|█         | 3005/28080 [5:56:26<49:38:55,  7.13s/it]
                                                         
{'loss': 0.6749, 'learning_rate': 0.0004922669495701641, 'epoch': 1.28}

 11%|█         | 3005/28080 [5:56:26<49:38:55,  7.13s/it]
 11%|█         | 3006/28080 [5:56:33<49:29:00,  7.10s/it]
                                                         
{'loss': 0.673, 'learning_rate': 0.000492259831460121, 'epoch': 1.28}

 11%|█         | 3006/28080 [5:56:33<49:29:00,  7.10s/it]
 11%|█         | 3007/28080 [5:56:41<49:17:10,  7.08s/it]
                                                         
{'loss': 0.6798, 'learning_rate': 0.0004922527101270608, 'epoch': 1.28}

 11%|█         | 3007/28080 [5:56:41<49:17:10,  7.08s/it]
 11%|█         | 3008/28080 [5:56:48<49:19:40,  7.08s/it]
                                                         
{'loss': 0.6538, 'learning_rate': 0.0004922455855710782, 'epoch': 1.28}

 11%|█         | 3008/28080 [5:56:48<49:19:40,  7.08s/it]
 11%|█         | 3009/28080 [5:56:55<49:32:02,  7.11s/it]
                                                         
{'loss': 0.6866, 'learning_rate': 0.0004922384577922678, 'epoch': 1.29}

 11%|█         | 3009/28080 [5:56:55<49:32:02,  7.11s/it]
 11%|█         | 3010/28080 [5:57:02<49:38:29,  7.13s/it]
                                                         
{'loss': 0.6863, 'learning_rate': 0.0004922313267907248, 'epoch': 1.29}

 11%|█         | 3010/28080 [5:57:02<49:38:29,  7.13s/it]
 11%|█         | 3011/28080 [5:57:09<49:42:11,  7.14s/it]
                                                         
{'loss': 0.6699, 'learning_rate': 0.0004922241925665439, 'epoch': 1.29}

 11%|█         | 3011/28080 [5:57:09<49:42:11,  7.14s/it]
 11%|█         | 3012/28080 [5:57:16<49:51:09,  7.16s/it]
                                                         
{'loss': 0.668, 'learning_rate': 0.0004922170551198199, 'epoch': 1.29}

 11%|█         | 3012/28080 [5:57:16<49:51:09,  7.16s/it]
 11%|█         | 3013/28080 [5:57:23<49:45:55,  7.15s/it]
                                                         
{'loss': 0.6795, 'learning_rate': 0.0004922099144506479, 'epoch': 1.29}

 11%|█         | 3013/28080 [5:57:23<49:45:55,  7.15s/it]
 11%|█         | 3014/28080 [5:57:30<49:29:34,  7.11s/it]
                                                         
{'loss': 0.6767, 'learning_rate': 0.0004922027705591229, 'epoch': 1.29}

 11%|█         | 3014/28080 [5:57:30<49:29:34,  7.11s/it]
 11%|█         | 3015/28080 [5:57:38<49:44:01,  7.14s/it]
                                                         
{'loss': 0.6624, 'learning_rate': 0.0004921956234453399, 'epoch': 1.29}

 11%|█         | 3015/28080 [5:57:38<49:44:01,  7.14s/it]
 11%|█         | 3016/28080 [5:57:45<49:43:19,  7.14s/it]
                                                         
{'loss': 0.6517, 'learning_rate': 0.000492188473109394, 'epoch': 1.29}

 11%|█         | 3016/28080 [5:57:45<49:43:19,  7.14s/it]
 11%|█         | 3017/28080 [5:57:52<49:32:31,  7.12s/it]
                                                         
{'loss': 0.6887, 'learning_rate': 0.0004921813195513802, 'epoch': 1.29}

 11%|█         | 3017/28080 [5:57:52<49:32:31,  7.12s/it]
 11%|█         | 3018/28080 [5:57:59<49:31:36,  7.11s/it]
                                                         
{'loss': 0.6788, 'learning_rate': 0.000492174162771394, 'epoch': 1.29}

 11%|█         | 3018/28080 [5:57:59<49:31:36,  7.11s/it]
 11%|█         | 3019/28080 [5:58:06<49:35:26,  7.12s/it]
                                                         
{'loss': 0.6588, 'learning_rate': 0.0004921670027695302, 'epoch': 1.29}

 11%|█         | 3019/28080 [5:58:06<49:35:26,  7.12s/it]
 11%|█         | 3020/28080 [5:58:13<49:28:41,  7.11s/it]
                                                         
{'loss': 0.6651, 'learning_rate': 0.0004921598395458844, 'epoch': 1.29}

 11%|█         | 3020/28080 [5:58:13<49:28:41,  7.11s/it]
 11%|█         | 3021/28080 [5:58:20<49:30:47,  7.11s/it]
                                                         
{'loss': 0.6684, 'learning_rate': 0.0004921526731005517, 'epoch': 1.29}

 11%|█         | 3021/28080 [5:58:20<49:30:47,  7.11s/it]
 11%|█         | 3022/28080 [5:58:28<49:38:58,  7.13s/it]
                                                         
{'loss': 0.6647, 'learning_rate': 0.0004921455034336275, 'epoch': 1.29}

 11%|█         | 3022/28080 [5:58:28<49:38:58,  7.13s/it]
 11%|█         | 3023/28080 [5:58:35<49:44:18,  7.15s/it]
                                                         
{'loss': 0.6781, 'learning_rate': 0.0004921383305452071, 'epoch': 1.29}

 11%|█         | 3023/28080 [5:58:35<49:44:18,  7.15s/it]
 11%|█         | 3024/28080 [5:58:42<49:45:46,  7.15s/it]
                                                         
{'loss': 0.6776, 'learning_rate': 0.0004921311544353862, 'epoch': 1.29}

 11%|█         | 3024/28080 [5:58:42<49:45:46,  7.15s/it]
 11%|█         | 3025/28080 [5:58:49<49:41:37,  7.14s/it]
                                                         
{'loss': 0.6789, 'learning_rate': 0.0004921239751042598, 'epoch': 1.29}

 11%|█         | 3025/28080 [5:58:49<49:41:37,  7.14s/it]
 11%|█         | 3026/28080 [5:58:56<49:37:28,  7.13s/it]
                                                         
{'loss': 0.6775, 'learning_rate': 0.000492116792551924, 'epoch': 1.29}

 11%|█         | 3026/28080 [5:58:56<49:37:28,  7.13s/it]
 11%|█         | 3027/28080 [5:59:03<49:34:52,  7.12s/it]
                                                         
{'loss': 0.6599, 'learning_rate': 0.0004921096067784739, 'epoch': 1.29}

 11%|█         | 3027/28080 [5:59:03<49:34:52,  7.12s/it]
 11%|█         | 3028/28080 [5:59:10<49:36:53,  7.13s/it]
                                                         
{'loss': 0.6485, 'learning_rate': 0.0004921024177840053, 'epoch': 1.29}

 11%|█         | 3028/28080 [5:59:10<49:36:53,  7.13s/it]
 11%|█         | 3029/28080 [5:59:17<49:25:25,  7.10s/it]
                                                         
{'loss': 0.6709, 'learning_rate': 0.0004920952255686137, 'epoch': 1.29}

 11%|█         | 3029/28080 [5:59:17<49:25:25,  7.10s/it]
 11%|█         | 3030/28080 [5:59:25<49:30:29,  7.11s/it]
                                                         
{'loss': 0.6841, 'learning_rate': 0.000492088030132395, 'epoch': 1.29}

 11%|█         | 3030/28080 [5:59:25<49:30:29,  7.11s/it]
 11%|█         | 3031/28080 [5:59:32<49:28:06,  7.11s/it]
                                                         
{'loss': 0.6815, 'learning_rate': 0.0004920808314754448, 'epoch': 1.29}

 11%|█         | 3031/28080 [5:59:32<49:28:06,  7.11s/it]
 11%|█         | 3032/28080 [5:59:39<49:30:12,  7.11s/it]
                                                         
{'loss': 0.6767, 'learning_rate': 0.0004920736295978589, 'epoch': 1.3}

 11%|█         | 3032/28080 [5:59:39<49:30:12,  7.11s/it]
 11%|█         | 3033/28080 [5:59:46<49:41:17,  7.14s/it]
                                                         
{'loss': 0.6665, 'learning_rate': 0.000492066424499733, 'epoch': 1.3}

 11%|█         | 3033/28080 [5:59:46<49:41:17,  7.14s/it]
 11%|█         | 3034/28080 [5:59:53<49:54:36,  7.17s/it]
                                                         
{'loss': 0.6639, 'learning_rate': 0.000492059216181163, 'epoch': 1.3}

 11%|█         | 3034/28080 [5:59:53<49:54:36,  7.17s/it]
 11%|█         | 3035/28080 [6:00:00<49:58:31,  7.18s/it]
                                                         
{'loss': 0.6557, 'learning_rate': 0.000492052004642245, 'epoch': 1.3}

 11%|█         | 3035/28080 [6:00:00<49:58:31,  7.18s/it]
 11%|█         | 3036/28080 [6:00:08<49:52:08,  7.17s/it]
                                                         
{'loss': 0.6836, 'learning_rate': 0.0004920447898830747, 'epoch': 1.3}

 11%|█         | 3036/28080 [6:00:08<49:52:08,  7.17s/it]
 11%|█         | 3037/28080 [6:00:15<49:47:51,  7.16s/it]
                                                         
{'loss': 0.6819, 'learning_rate': 0.0004920375719037482, 'epoch': 1.3}

 11%|█         | 3037/28080 [6:00:15<49:47:51,  7.16s/it]
 11%|█         | 3038/28080 [6:00:22<49:33:28,  7.12s/it]
                                                         
{'loss': 0.6871, 'learning_rate': 0.0004920303507043615, 'epoch': 1.3}

 11%|█         | 3038/28080 [6:00:22<49:33:28,  7.12s/it]
 11%|█         | 3039/28080 [6:00:29<49:35:05,  7.13s/it]
                                                         
{'loss': 0.6534, 'learning_rate': 0.0004920231262850106, 'epoch': 1.3}

 11%|█         | 3039/28080 [6:00:29<49:35:05,  7.13s/it]
 11%|█         | 3040/28080 [6:00:36<49:22:44,  7.10s/it]
                                                         
{'loss': 0.6719, 'learning_rate': 0.0004920158986457917, 'epoch': 1.3}

 11%|█         | 3040/28080 [6:00:36<49:22:44,  7.10s/it]
 11%|█         | 3041/28080 [6:00:43<49:27:21,  7.11s/it]
                                                         
{'loss': 0.6703, 'learning_rate': 0.0004920086677868011, 'epoch': 1.3}

 11%|█         | 3041/28080 [6:00:43<49:27:21,  7.11s/it]
 11%|█         | 3042/28080 [6:00:50<49:31:07,  7.12s/it]
                                                         
{'loss': 0.6648, 'learning_rate': 0.0004920014337081347, 'epoch': 1.3}

 11%|█         | 3042/28080 [6:00:50<49:31:07,  7.12s/it]
 11%|█         | 3043/28080 [6:00:57<49:48:52,  7.16s/it]
                                                         
{'loss': 0.6423, 'learning_rate': 0.0004919941964098889, 'epoch': 1.3}

 11%|█         | 3043/28080 [6:00:57<49:48:52,  7.16s/it]
 11%|█         | 3044/28080 [6:01:05<49:54:54,  7.18s/it]
                                                         
{'loss': 0.6529, 'learning_rate': 0.00049198695589216, 'epoch': 1.3}

 11%|█         | 3044/28080 [6:01:05<49:54:54,  7.18s/it]
 11%|█         | 3045/28080 [6:01:12<49:46:52,  7.16s/it]
                                                         
{'loss': 0.6544, 'learning_rate': 0.0004919797121550443, 'epoch': 1.3}

 11%|█         | 3045/28080 [6:01:12<49:46:52,  7.16s/it]
 11%|█         | 3046/28080 [6:01:19<49:43:47,  7.15s/it]
                                                         
{'loss': 0.6694, 'learning_rate': 0.0004919724651986381, 'epoch': 1.3}

 11%|█         | 3046/28080 [6:01:19<49:43:47,  7.15s/it]
 11%|█         | 3047/28080 [6:01:26<49:27:29,  7.11s/it]
                                                         
{'loss': 0.6712, 'learning_rate': 0.0004919652150230379, 'epoch': 1.3}

 11%|█         | 3047/28080 [6:01:26<49:27:29,  7.11s/it]
 11%|█         | 3048/28080 [6:01:33<49:30:33,  7.12s/it]
                                                         
{'loss': 0.6401, 'learning_rate': 0.0004919579616283402, 'epoch': 1.3}

 11%|█         | 3048/28080 [6:01:33<49:30:33,  7.12s/it]
 11%|█         | 3049/28080 [6:01:40<49:24:28,  7.11s/it]
                                                         
{'loss': 0.6841, 'learning_rate': 0.0004919507050146415, 'epoch': 1.3}

 11%|█         | 3049/28080 [6:01:40<49:24:28,  7.11s/it]
 11%|█         | 3050/28080 [6:01:47<49:23:42,  7.10s/it]
                                                         
{'loss': 0.6776, 'learning_rate': 0.000491943445182038, 'epoch': 1.3}

 11%|█         | 3050/28080 [6:01:47<49:23:42,  7.10s/it]
 11%|█         | 3051/28080 [6:01:54<49:28:04,  7.12s/it]
                                                         
{'loss': 0.6813, 'learning_rate': 0.0004919361821306269, 'epoch': 1.3}

 11%|█         | 3051/28080 [6:01:54<49:28:04,  7.12s/it]
 11%|█         | 3052/28080 [6:02:02<49:33:27,  7.13s/it]
                                                         
{'loss': 0.6732, 'learning_rate': 0.0004919289158605043, 'epoch': 1.3}

 11%|█         | 3052/28080 [6:02:02<49:33:27,  7.13s/it]
 11%|█         | 3053/28080 [6:02:09<49:39:55,  7.14s/it]
                                                         
{'loss': 0.667, 'learning_rate': 0.0004919216463717671, 'epoch': 1.3}

 11%|█         | 3053/28080 [6:02:09<49:39:55,  7.14s/it]
 11%|█         | 3054/28080 [6:02:16<49:38:40,  7.14s/it]
                                                         
{'loss': 0.689, 'learning_rate': 0.0004919143736645119, 'epoch': 1.3}

 11%|█         | 3054/28080 [6:02:16<49:38:40,  7.14s/it]
 11%|█         | 3055/28080 [6:02:23<49:44:46,  7.16s/it]
                                                         
{'loss': 0.6651, 'learning_rate': 0.0004919070977388356, 'epoch': 1.31}

 11%|█         | 3055/28080 [6:02:23<49:44:46,  7.16s/it]
 11%|█         | 3056/28080 [6:02:30<49:40:06,  7.15s/it]
                                                         
{'loss': 0.6695, 'learning_rate': 0.0004918998185948349, 'epoch': 1.31}

 11%|█         | 3056/28080 [6:02:30<49:40:06,  7.15s/it]
 11%|█         | 3057/28080 [6:02:37<49:31:46,  7.13s/it]
                                                         
{'loss': 0.678, 'learning_rate': 0.0004918925362326067, 'epoch': 1.31}

 11%|█         | 3057/28080 [6:02:37<49:31:46,  7.13s/it]
 11%|█         | 3058/28080 [6:02:44<49:38:46,  7.14s/it]
                                                         
{'loss': 0.663, 'learning_rate': 0.0004918852506522477, 'epoch': 1.31}

 11%|█         | 3058/28080 [6:02:44<49:38:46,  7.14s/it]
 11%|█         | 3059/28080 [6:02:52<49:56:57,  7.19s/it]
                                                         
{'loss': 0.6686, 'learning_rate': 0.0004918779618538552, 'epoch': 1.31}

 11%|█         | 3059/28080 [6:02:52<49:56:57,  7.19s/it]
 11%|█         | 3060/28080 [6:02:59<49:52:25,  7.18s/it]
                                                         
{'loss': 0.6773, 'learning_rate': 0.0004918706698375258, 'epoch': 1.31}

 11%|█         | 3060/28080 [6:02:59<49:52:25,  7.18s/it]
 11%|█         | 3061/28080 [6:03:06<49:52:51,  7.18s/it]
                                                         
{'loss': 0.6517, 'learning_rate': 0.0004918633746033567, 'epoch': 1.31}

 11%|█         | 3061/28080 [6:03:06<49:52:51,  7.18s/it]
 11%|█         | 3062/28080 [6:03:13<49:55:58,  7.19s/it]
                                                         
{'loss': 0.6559, 'learning_rate': 0.000491856076151445, 'epoch': 1.31}

 11%|█         | 3062/28080 [6:03:13<49:55:58,  7.19s/it]
 11%|█         | 3063/28080 [6:03:20<50:02:54,  7.20s/it]
                                                         
{'loss': 0.6556, 'learning_rate': 0.0004918487744818877, 'epoch': 1.31}

 11%|█         | 3063/28080 [6:03:20<50:02:54,  7.20s/it]
 11%|█         | 3064/28080 [6:03:28<50:02:19,  7.20s/it]
                                                         
{'loss': 0.6625, 'learning_rate': 0.0004918414695947819, 'epoch': 1.31}

 11%|█         | 3064/28080 [6:03:28<50:02:19,  7.20s/it]
 11%|█         | 3065/28080 [6:03:35<49:56:00,  7.19s/it]
                                                         
{'loss': 0.655, 'learning_rate': 0.0004918341614902249, 'epoch': 1.31}

 11%|█         | 3065/28080 [6:03:35<49:56:00,  7.19s/it]
 11%|█         | 3066/28080 [6:03:42<49:56:37,  7.19s/it]
                                                         
{'loss': 0.6718, 'learning_rate': 0.0004918268501683138, 'epoch': 1.31}

 11%|█         | 3066/28080 [6:03:42<49:56:37,  7.19s/it]
 11%|█         | 3067/28080 [6:03:49<49:52:27,  7.18s/it]
                                                         
{'loss': 0.6537, 'learning_rate': 0.0004918195356291459, 'epoch': 1.31}

 11%|█         | 3067/28080 [6:03:49<49:52:27,  7.18s/it]
 11%|█         | 3068/28080 [6:03:56<49:45:13,  7.16s/it]
                                                         
{'loss': 0.6619, 'learning_rate': 0.0004918122178728186, 'epoch': 1.31}

 11%|█         | 3068/28080 [6:03:56<49:45:13,  7.16s/it]
 11%|█         | 3069/28080 [6:04:04<49:53:45,  7.18s/it]
                                                         
{'loss': 0.6548, 'learning_rate': 0.0004918048968994292, 'epoch': 1.31}

 11%|█         | 3069/28080 [6:04:04<49:53:45,  7.18s/it]
 11%|█         | 3070/28080 [6:04:11<49:52:10,  7.18s/it]
                                                         
{'loss': 0.6448, 'learning_rate': 0.0004917975727090751, 'epoch': 1.31}

 11%|█         | 3070/28080 [6:04:11<49:52:10,  7.18s/it]
 11%|█         | 3071/28080 [6:04:18<49:43:16,  7.16s/it]
                                                         
{'loss': 0.6641, 'learning_rate': 0.0004917902453018538, 'epoch': 1.31}

 11%|█         | 3071/28080 [6:04:18<49:43:16,  7.16s/it]
 11%|█         | 3072/28080 [6:04:25<49:44:36,  7.16s/it]
                                                         
{'loss': 0.6769, 'learning_rate': 0.0004917829146778626, 'epoch': 1.31}

 11%|█         | 3072/28080 [6:04:25<49:44:36,  7.16s/it]
 11%|█         | 3073/28080 [6:04:32<49:47:00,  7.17s/it]
                                                         
{'loss': 0.6739, 'learning_rate': 0.0004917755808371993, 'epoch': 1.31}

 11%|█         | 3073/28080 [6:04:32<49:47:00,  7.17s/it]
 11%|█         | 3074/28080 [6:04:39<49:31:09,  7.13s/it]
                                                         
{'loss': 0.6771, 'learning_rate': 0.0004917682437799612, 'epoch': 1.31}

 11%|█         | 3074/28080 [6:04:39<49:31:09,  7.13s/it]
 11%|█         | 3075/28080 [6:04:46<49:35:15,  7.14s/it]
                                                         
{'loss': 0.6657, 'learning_rate': 0.0004917609035062461, 'epoch': 1.31}

 11%|█         | 3075/28080 [6:04:46<49:35:15,  7.14s/it]
 11%|█         | 3076/28080 [6:04:53<49:36:42,  7.14s/it]
                                                         
{'loss': 0.6766, 'learning_rate': 0.0004917535600161517, 'epoch': 1.31}

 11%|█         | 3076/28080 [6:04:53<49:36:42,  7.14s/it]
 11%|█         | 3077/28080 [6:05:01<49:38:01,  7.15s/it]
                                                         
{'loss': 0.6585, 'learning_rate': 0.0004917462133097754, 'epoch': 1.31}

 11%|█         | 3077/28080 [6:05:01<49:38:01,  7.15s/it]
 11%|█         | 3078/28080 [6:05:08<49:40:56,  7.15s/it]
                                                         
{'loss': 0.6901, 'learning_rate': 0.0004917388633872152, 'epoch': 1.31}

 11%|█         | 3078/28080 [6:05:08<49:40:56,  7.15s/it]
 11%|█         | 3079/28080 [6:05:15<49:32:12,  7.13s/it]
                                                         
{'loss': 0.6514, 'learning_rate': 0.0004917315102485688, 'epoch': 1.32}

 11%|█         | 3079/28080 [6:05:15<49:32:12,  7.13s/it]
 11%|█         | 3080/28080 [6:05:22<49:42:41,  7.16s/it]
                                                         
{'loss': 0.6761, 'learning_rate': 0.0004917241538939341, 'epoch': 1.32}

 11%|█         | 3080/28080 [6:05:22<49:42:41,  7.16s/it]
 11%|█         | 3081/28080 [6:05:29<49:48:06,  7.17s/it]
                                                         
{'loss': 0.6537, 'learning_rate': 0.0004917167943234088, 'epoch': 1.32}

 11%|█         | 3081/28080 [6:05:29<49:48:06,  7.17s/it]
 11%|█         | 3082/28080 [6:05:36<49:43:24,  7.16s/it]
                                                         
{'loss': 0.6396, 'learning_rate': 0.000491709431537091, 'epoch': 1.32}

 11%|█         | 3082/28080 [6:05:36<49:43:24,  7.16s/it]
 11%|█         | 3083/28080 [6:05:44<49:48:31,  7.17s/it]
                                                         
{'loss': 0.6604, 'learning_rate': 0.0004917020655350786, 'epoch': 1.32}

 11%|█         | 3083/28080 [6:05:44<49:48:31,  7.17s/it]
 11%|█         | 3084/28080 [6:05:51<49:56:38,  7.19s/it]
                                                         
{'loss': 0.67, 'learning_rate': 0.0004916946963174695, 'epoch': 1.32}

 11%|█         | 3084/28080 [6:05:51<49:56:38,  7.19s/it]
 11%|█         | 3085/28080 [6:05:58<49:50:36,  7.18s/it]
                                                         
{'loss': 0.6639, 'learning_rate': 0.0004916873238843618, 'epoch': 1.32}

 11%|█         | 3085/28080 [6:05:58<49:50:36,  7.18s/it]
 11%|█         | 3086/28080 [6:06:05<49:44:35,  7.16s/it]
                                                         
{'loss': 0.6739, 'learning_rate': 0.0004916799482358536, 'epoch': 1.32}

 11%|█         | 3086/28080 [6:06:05<49:44:35,  7.16s/it]
 11%|█         | 3087/28080 [6:06:12<49:33:52,  7.14s/it]
                                                         
{'loss': 0.669, 'learning_rate': 0.000491672569372043, 'epoch': 1.32}

 11%|█         | 3087/28080 [6:06:12<49:33:52,  7.14s/it]
 11%|█         | 3088/28080 [6:06:19<49:41:00,  7.16s/it]
                                                         
{'loss': 0.65, 'learning_rate': 0.0004916651872930283, 'epoch': 1.32}

 11%|█         | 3088/28080 [6:06:19<49:41:00,  7.16s/it]
 11%|█         | 3089/28080 [6:06:27<49:27:52,  7.13s/it]
                                                         
{'loss': 0.6682, 'learning_rate': 0.0004916578019989074, 'epoch': 1.32}

 11%|█         | 3089/28080 [6:06:27<49:27:52,  7.13s/it]
 11%|█         | 3090/28080 [6:06:34<49:29:39,  7.13s/it]
                                                         
{'loss': 0.6497, 'learning_rate': 0.0004916504134897789, 'epoch': 1.32}

 11%|█         | 3090/28080 [6:06:34<49:29:39,  7.13s/it]
 11%|█         | 3091/28080 [6:06:41<49:45:04,  7.17s/it]
                                                         
{'loss': 0.6871, 'learning_rate': 0.0004916430217657408, 'epoch': 1.32}

 11%|█         | 3091/28080 [6:06:41<49:45:04,  7.17s/it]
 11%|█         | 3092/28080 [6:06:48<49:46:45,  7.17s/it]
                                                         
{'loss': 0.6655, 'learning_rate': 0.0004916356268268917, 'epoch': 1.32}

 11%|█         | 3092/28080 [6:06:48<49:46:45,  7.17s/it]
 11%|█         | 3093/28080 [6:06:55<49:51:23,  7.18s/it]
                                                         
{'loss': 0.6453, 'learning_rate': 0.0004916282286733299, 'epoch': 1.32}

 11%|█         | 3093/28080 [6:06:55<49:51:23,  7.18s/it]
 11%|█         | 3094/28080 [6:07:02<49:38:22,  7.15s/it]
                                                         
{'loss': 0.678, 'learning_rate': 0.0004916208273051538, 'epoch': 1.32}

 11%|█         | 3094/28080 [6:07:02<49:38:22,  7.15s/it]
 11%|█         | 3095/28080 [6:07:09<49:32:38,  7.14s/it]
                                                         
{'loss': 0.6816, 'learning_rate': 0.0004916134227224618, 'epoch': 1.32}

 11%|█         | 3095/28080 [6:07:09<49:32:38,  7.14s/it]
 11%|█         | 3096/28080 [6:07:17<49:37:27,  7.15s/it]
                                                         
{'loss': 0.663, 'learning_rate': 0.0004916060149253524, 'epoch': 1.32}

 11%|█         | 3096/28080 [6:07:17<49:37:27,  7.15s/it]
 11%|█         | 3097/28080 [6:07:24<49:41:29,  7.16s/it]
                                                         
{'loss': 0.6608, 'learning_rate': 0.0004915986039139243, 'epoch': 1.32}

 11%|█         | 3097/28080 [6:07:24<49:41:29,  7.16s/it]
 11%|█         | 3098/28080 [6:07:31<49:44:15,  7.17s/it]
                                                         
{'loss': 0.6706, 'learning_rate': 0.000491591189688276, 'epoch': 1.32}

 11%|█         | 3098/28080 [6:07:31<49:44:15,  7.17s/it]
 11%|█         | 3099/28080 [6:07:38<49:49:50,  7.18s/it]
                                                         
{'loss': 0.6876, 'learning_rate': 0.0004915837722485061, 'epoch': 1.32}

 11%|█         | 3099/28080 [6:07:38<49:49:50,  7.18s/it]
 11%|█         | 3100/28080 [6:07:45<49:41:27,  7.16s/it]
                                                         
{'loss': 0.6666, 'learning_rate': 0.0004915763515947135, 'epoch': 1.32}

 11%|█         | 3100/28080 [6:07:45<49:41:27,  7.16s/it]
 11%|█         | 3101/28080 [6:07:52<49:23:45,  7.12s/it]
                                                         
{'loss': 0.6682, 'learning_rate': 0.0004915689277269966, 'epoch': 1.32}

 11%|█         | 3101/28080 [6:07:52<49:23:45,  7.12s/it]
 11%|█         | 3102/28080 [6:08:00<49:27:57,  7.13s/it]
                                                         
{'loss': 0.6523, 'learning_rate': 0.0004915615006454545, 'epoch': 1.33}

 11%|█         | 3102/28080 [6:08:00<49:27:57,  7.13s/it]
 11%|█         | 3103/28080 [6:08:07<49:29:22,  7.13s/it]
                                                         
{'loss': 0.6763, 'learning_rate': 0.0004915540703501857, 'epoch': 1.33}

 11%|█         | 3103/28080 [6:08:07<49:29:22,  7.13s/it]
 11%|█         | 3104/28080 [6:08:14<49:28:10,  7.13s/it]
                                                         
{'loss': 0.6931, 'learning_rate': 0.0004915466368412892, 'epoch': 1.33}

 11%|█         | 3104/28080 [6:08:14<49:28:10,  7.13s/it]
 11%|█         | 3105/28080 [6:08:21<49:34:19,  7.15s/it]
                                                         
{'loss': 0.6571, 'learning_rate': 0.0004915392001188639, 'epoch': 1.33}

 11%|█         | 3105/28080 [6:08:21<49:34:19,  7.15s/it]
 11%|█         | 3106/28080 [6:08:28<49:30:34,  7.14s/it]
                                                         
{'loss': 0.6686, 'learning_rate': 0.0004915317601830088, 'epoch': 1.33}

 11%|█         | 3106/28080 [6:08:28<49:30:34,  7.14s/it]
 11%|█         | 3107/28080 [6:08:35<49:23:00,  7.12s/it]
                                                         
{'loss': 0.6656, 'learning_rate': 0.0004915243170338227, 'epoch': 1.33}

 11%|█         | 3107/28080 [6:08:35<49:23:00,  7.12s/it]
 11%|█         | 3108/28080 [6:08:42<49:28:59,  7.13s/it]
                                                         
{'loss': 0.67, 'learning_rate': 0.0004915168706714049, 'epoch': 1.33}

 11%|█         | 3108/28080 [6:08:42<49:28:59,  7.13s/it]
 11%|█         | 3109/28080 [6:08:50<49:41:18,  7.16s/it]
                                                         
{'loss': 0.6594, 'learning_rate': 0.000491509421095854, 'epoch': 1.33}

 11%|█         | 3109/28080 [6:08:50<49:41:18,  7.16s/it]
 11%|█         | 3110/28080 [6:08:57<49:41:37,  7.16s/it]
                                                         
{'loss': 0.666, 'learning_rate': 0.0004915019683072696, 'epoch': 1.33}

 11%|█         | 3110/28080 [6:08:57<49:41:37,  7.16s/it]
 11%|█         | 3111/28080 [6:09:04<49:35:18,  7.15s/it]
                                                         
{'loss': 0.676, 'learning_rate': 0.0004914945123057506, 'epoch': 1.33}

 11%|█         | 3111/28080 [6:09:04<49:35:18,  7.15s/it]
 11%|█         | 3112/28080 [6:09:11<49:39:57,  7.16s/it]
                                                         
{'loss': 0.6565, 'learning_rate': 0.0004914870530913963, 'epoch': 1.33}

 11%|█         | 3112/28080 [6:09:11<49:39:57,  7.16s/it]
 11%|█         | 3113/28080 [6:09:18<49:39:52,  7.16s/it]
                                                         
{'loss': 0.6749, 'learning_rate': 0.000491479590664306, 'epoch': 1.33}

 11%|█         | 3113/28080 [6:09:18<49:39:52,  7.16s/it]
 11%|█         | 3114/28080 [6:09:25<49:35:05,  7.15s/it]
                                                         
{'loss': 0.6717, 'learning_rate': 0.0004914721250245786, 'epoch': 1.33}

 11%|█         | 3114/28080 [6:09:25<49:35:05,  7.15s/it]
 11%|█         | 3115/28080 [6:09:32<49:26:01,  7.13s/it]
                                                         
{'loss': 0.679, 'learning_rate': 0.0004914646561723138, 'epoch': 1.33}

 11%|█         | 3115/28080 [6:09:32<49:26:01,  7.13s/it]
 11%|█         | 3116/28080 [6:09:40<49:32:01,  7.14s/it]
                                                         
{'loss': 0.6655, 'learning_rate': 0.0004914571841076109, 'epoch': 1.33}

 11%|█         | 3116/28080 [6:09:40<49:32:01,  7.14s/it]
 11%|█         | 3117/28080 [6:09:47<49:32:51,  7.15s/it]
                                                         
{'loss': 0.6687, 'learning_rate': 0.0004914497088305692, 'epoch': 1.33}

 11%|█         | 3117/28080 [6:09:47<49:32:51,  7.15s/it]
 11%|█         | 3118/28080 [6:09:54<49:44:44,  7.17s/it]
                                                         
{'loss': 0.6559, 'learning_rate': 0.0004914422303412883, 'epoch': 1.33}

 11%|█         | 3118/28080 [6:09:54<49:44:44,  7.17s/it]
 11%|█         | 3119/28080 [6:10:01<49:51:05,  7.19s/it]
                                                         
{'loss': 0.6746, 'learning_rate': 0.0004914347486398676, 'epoch': 1.33}

 11%|█         | 3119/28080 [6:10:01<49:51:05,  7.19s/it]
 11%|█         | 3120/28080 [6:10:08<49:47:10,  7.18s/it]
                                                         
{'loss': 0.6792, 'learning_rate': 0.0004914272637264066, 'epoch': 1.33}

 11%|█         | 3120/28080 [6:10:08<49:47:10,  7.18s/it]
 11%|█         | 3121/28080 [6:10:15<49:30:09,  7.14s/it]
                                                         
{'loss': 0.6675, 'learning_rate': 0.000491419775601005, 'epoch': 1.33}

 11%|█         | 3121/28080 [6:10:15<49:30:09,  7.14s/it]
 11%|█         | 3122/28080 [6:10:23<49:31:06,  7.14s/it]
                                                         
{'loss': 0.6668, 'learning_rate': 0.0004914122842637622, 'epoch': 1.33}

 11%|█         | 3122/28080 [6:10:23<49:31:06,  7.14s/it]
 11%|█         | 3123/28080 [6:10:30<49:28:40,  7.14s/it]
                                                         
{'loss': 0.6741, 'learning_rate': 0.000491404789714778, 'epoch': 1.33}

 11%|█         | 3123/28080 [6:10:30<49:28:40,  7.14s/it]
 11%|█         | 3124/28080 [6:10:37<49:22:24,  7.12s/it]
                                                         
{'loss': 0.6831, 'learning_rate': 0.0004913972919541522, 'epoch': 1.33}

 11%|█         | 3124/28080 [6:10:37<49:22:24,  7.12s/it]
 11%|█         | 3125/28080 [6:10:44<49:51:26,  7.19s/it]
                                                         
{'loss': 0.66, 'learning_rate': 0.0004913897909819845, 'epoch': 1.33}

 11%|█         | 3125/28080 [6:10:44<49:51:26,  7.19s/it]
 11%|█         | 3126/28080 [6:10:51<50:04:08,  7.22s/it]
                                                         
{'loss': 0.6648, 'learning_rate': 0.0004913822867983746, 'epoch': 1.34}

 11%|█         | 3126/28080 [6:10:51<50:04:08,  7.22s/it]
 11%|█         | 3127/28080 [6:10:59<50:03:32,  7.22s/it]
                                                         
{'loss': 0.6475, 'learning_rate': 0.0004913747794034225, 'epoch': 1.34}

 11%|█         | 3127/28080 [6:10:59<50:03:32,  7.22s/it]
 11%|█         | 3128/28080 [6:11:06<49:41:59,  7.17s/it]
                                                         
{'loss': 0.6996, 'learning_rate': 0.0004913672687972278, 'epoch': 1.34}

 11%|█         | 3128/28080 [6:11:06<49:41:59,  7.17s/it]
 11%|█         | 3129/28080 [6:11:13<49:41:50,  7.17s/it]
                                                         
{'loss': 0.6513, 'learning_rate': 0.0004913597549798907, 'epoch': 1.34}

 11%|█         | 3129/28080 [6:11:13<49:41:50,  7.17s/it]
 11%|█         | 3130/28080 [6:11:20<49:40:48,  7.17s/it]
                                                         
{'loss': 0.6586, 'learning_rate': 0.0004913522379515111, 'epoch': 1.34}

 11%|█         | 3130/28080 [6:11:20<49:40:48,  7.17s/it]
 11%|█         | 3131/28080 [6:11:27<49:28:37,  7.14s/it]
                                                         
{'loss': 0.6706, 'learning_rate': 0.0004913447177121888, 'epoch': 1.34}

 11%|█         | 3131/28080 [6:11:27<49:28:37,  7.14s/it]
 11%|█         | 3132/28080 [6:11:34<49:37:05,  7.16s/it]
                                                         
{'loss': 0.6595, 'learning_rate': 0.0004913371942620242, 'epoch': 1.34}

 11%|█         | 3132/28080 [6:11:34<49:37:05,  7.16s/it]
 11%|█         | 3133/28080 [6:11:42<49:42:58,  7.17s/it]
                                                         
{'loss': 0.6691, 'learning_rate': 0.0004913296676011171, 'epoch': 1.34}

 11%|█         | 3133/28080 [6:11:42<49:42:58,  7.17s/it]
 11%|█         | 3134/28080 [6:11:49<49:56:33,  7.21s/it]
                                                         
{'loss': 0.6509, 'learning_rate': 0.0004913221377295678, 'epoch': 1.34}

 11%|█         | 3134/28080 [6:11:49<49:56:33,  7.21s/it]
 11%|█         | 3135/28080 [6:11:56<49:49:35,  7.19s/it]
                                                         
{'loss': 0.6638, 'learning_rate': 0.0004913146046474764, 'epoch': 1.34}

 11%|█         | 3135/28080 [6:11:56<49:49:35,  7.19s/it]
 11%|█         | 3136/28080 [6:12:03<49:35:48,  7.16s/it]
                                                         
{'loss': 0.6649, 'learning_rate': 0.000491307068354943, 'epoch': 1.34}

 11%|█         | 3136/28080 [6:12:03<49:35:48,  7.16s/it]
 11%|█         | 3137/28080 [6:12:10<49:19:04,  7.12s/it]
                                                         
{'loss': 0.6706, 'learning_rate': 0.0004912995288520681, 'epoch': 1.34}

 11%|█         | 3137/28080 [6:12:10<49:19:04,  7.12s/it]
 11%|█         | 3138/28080 [6:12:17<49:21:20,  7.12s/it]
                                                         
{'loss': 0.6649, 'learning_rate': 0.0004912919861389519, 'epoch': 1.34}

 11%|█         | 3138/28080 [6:12:17<49:21:20,  7.12s/it]
 11%|█         | 3139/28080 [6:12:24<49:26:21,  7.14s/it]
                                                         
{'loss': 0.6779, 'learning_rate': 0.0004912844402156948, 'epoch': 1.34}

 11%|█         | 3139/28080 [6:12:24<49:26:21,  7.14s/it]
 11%|█         | 3140/28080 [6:12:31<49:26:32,  7.14s/it]
                                                         
{'loss': 0.6802, 'learning_rate': 0.0004912768910823971, 'epoch': 1.34}

 11%|█         | 3140/28080 [6:12:31<49:26:32,  7.14s/it]
 11%|█         | 3141/28080 [6:12:39<49:28:10,  7.14s/it]
                                                         
{'loss': 0.6802, 'learning_rate': 0.0004912693387391592, 'epoch': 1.34}

 11%|█         | 3141/28080 [6:12:39<49:28:10,  7.14s/it]
 11%|█         | 3142/28080 [6:12:46<49:23:09,  7.13s/it]
                                                         
{'loss': 0.6722, 'learning_rate': 0.0004912617831860818, 'epoch': 1.34}

 11%|█         | 3142/28080 [6:12:46<49:23:09,  7.13s/it]
 11%|█         | 3143/28080 [6:12:53<49:12:30,  7.10s/it]
                                                         
{'loss': 0.6603, 'learning_rate': 0.0004912542244232651, 'epoch': 1.34}

 11%|█         | 3143/28080 [6:12:53<49:12:30,  7.10s/it]
 11%|█         | 3144/28080 [6:13:00<49:09:14,  7.10s/it]
                                                         
{'loss': 0.6823, 'learning_rate': 0.0004912466624508101, 'epoch': 1.34}

 11%|█         | 3144/28080 [6:13:00<49:09:14,  7.10s/it]
 11%|█         | 3145/28080 [6:13:07<49:30:52,  7.15s/it]
                                                         
{'loss': 0.6575, 'learning_rate': 0.0004912390972688169, 'epoch': 1.34}

 11%|█         | 3145/28080 [6:13:07<49:30:52,  7.15s/it]
 11%|█         | 3146/28080 [6:13:14<49:26:56,  7.14s/it]
                                                         
{'loss': 0.6743, 'learning_rate': 0.0004912315288773865, 'epoch': 1.34}

 11%|█         | 3146/28080 [6:13:14<49:26:56,  7.14s/it]
 11%|█         | 3147/28080 [6:13:21<49:21:54,  7.13s/it]
                                                         
{'loss': 0.6652, 'learning_rate': 0.0004912239572766194, 'epoch': 1.34}

 11%|█         | 3147/28080 [6:13:21<49:21:54,  7.13s/it]
 11%|█         | 3148/28080 [6:13:29<49:34:17,  7.16s/it]
                                                         
{'loss': 0.682, 'learning_rate': 0.0004912163824666165, 'epoch': 1.34}

 11%|█         | 3148/28080 [6:13:29<49:34:17,  7.16s/it]
 11%|█         | 3149/28080 [6:13:36<49:08:39,  7.10s/it]
                                                         
{'loss': 0.6807, 'learning_rate': 0.0004912088044474784, 'epoch': 1.35}

 11%|█         | 3149/28080 [6:13:36<49:08:39,  7.10s/it]
 11%|█         | 3150/28080 [6:13:43<49:12:21,  7.11s/it]
                                                         
{'loss': 0.6633, 'learning_rate': 0.0004912012232193059, 'epoch': 1.35}

 11%|█         | 3150/28080 [6:13:43<49:12:21,  7.11s/it]
 11%|█         | 3151/28080 [6:13:50<49:13:31,  7.11s/it]
                                                         
{'loss': 0.6818, 'learning_rate': 0.0004911936387822001, 'epoch': 1.35}

 11%|█         | 3151/28080 [6:13:50<49:13:31,  7.11s/it]
 11%|█         | 3152/28080 [6:13:57<49:20:13,  7.13s/it]
                                                         
{'loss': 0.6586, 'learning_rate': 0.0004911860511362618, 'epoch': 1.35}

 11%|█         | 3152/28080 [6:13:57<49:20:13,  7.13s/it]
 11%|█         | 3153/28080 [6:14:04<49:28:33,  7.15s/it]
                                                         
{'loss': 0.6869, 'learning_rate': 0.0004911784602815918, 'epoch': 1.35}

 11%|█         | 3153/28080 [6:14:04<49:28:33,  7.15s/it]
 11%|█         | 3154/28080 [6:14:11<49:26:24,  7.14s/it]
                                                         
{'loss': 0.6669, 'learning_rate': 0.0004911708662182912, 'epoch': 1.35}

 11%|█         | 3154/28080 [6:14:11<49:26:24,  7.14s/it]
 11%|█         | 3155/28080 [6:14:18<49:15:42,  7.12s/it]
                                                         
{'loss': 0.6748, 'learning_rate': 0.0004911632689464611, 'epoch': 1.35}

 11%|█         | 3155/28080 [6:14:18<49:15:42,  7.12s/it]
 11%|█         | 3156/28080 [6:14:25<49:18:14,  7.12s/it]
                                                         
{'loss': 0.6849, 'learning_rate': 0.0004911556684662024, 'epoch': 1.35}

 11%|█         | 3156/28080 [6:14:25<49:18:14,  7.12s/it]
 11%|█         | 3157/28080 [6:14:33<49:25:38,  7.14s/it]
                                                         
{'loss': 0.666, 'learning_rate': 0.0004911480647776164, 'epoch': 1.35}

 11%|█         | 3157/28080 [6:14:33<49:25:38,  7.14s/it]
 11%|█         | 3158/28080 [6:14:40<49:08:24,  7.10s/it]
                                                         
{'loss': 0.6773, 'learning_rate': 0.0004911404578808042, 'epoch': 1.35}

 11%|█         | 3158/28080 [6:14:40<49:08:24,  7.10s/it]
 11%|█▏        | 3159/28080 [6:14:47<49:18:29,  7.12s/it]
                                                         
{'loss': 0.6819, 'learning_rate': 0.0004911328477758669, 'epoch': 1.35}

 11%|█▏        | 3159/28080 [6:14:47<49:18:29,  7.12s/it]
 11%|█▏        | 3160/28080 [6:14:54<49:16:11,  7.12s/it]
                                                         
{'loss': 0.6601, 'learning_rate': 0.0004911252344629059, 'epoch': 1.35}

 11%|█▏        | 3160/28080 [6:14:54<49:16:11,  7.12s/it]
 11%|█▏        | 3161/28080 [6:15:01<49:24:31,  7.14s/it]
                                                         
{'loss': 0.6746, 'learning_rate': 0.0004911176179420223, 'epoch': 1.35}

 11%|█▏        | 3161/28080 [6:15:01<49:24:31,  7.14s/it]
 11%|█▏        | 3162/28080 [6:15:08<49:27:17,  7.14s/it]
                                                         
{'loss': 0.6571, 'learning_rate': 0.0004911099982133177, 'epoch': 1.35}

 11%|█▏        | 3162/28080 [6:15:08<49:27:17,  7.14s/it]
 11%|█▏        | 3163/28080 [6:15:15<49:29:51,  7.15s/it]
                                                         
{'loss': 0.6463, 'learning_rate': 0.0004911023752768932, 'epoch': 1.35}

 11%|█▏        | 3163/28080 [6:15:15<49:29:51,  7.15s/it]
 11%|█▏        | 3164/28080 [6:15:23<49:19:58,  7.13s/it]
                                                         
{'loss': 0.6835, 'learning_rate': 0.0004910947491328503, 'epoch': 1.35}

 11%|█▏        | 3164/28080 [6:15:23<49:19:58,  7.13s/it]
 11%|█▏        | 3165/28080 [6:15:30<49:26:49,  7.14s/it]
                                                         
{'loss': 0.6625, 'learning_rate': 0.0004910871197812905, 'epoch': 1.35}

 11%|█▏        | 3165/28080 [6:15:30<49:26:49,  7.14s/it]
 11%|█▏        | 3166/28080 [6:15:37<49:29:44,  7.15s/it]
                                                         
{'loss': 0.662, 'learning_rate': 0.0004910794872223154, 'epoch': 1.35}

 11%|█▏        | 3166/28080 [6:15:37<49:29:44,  7.15s/it]
 11%|█▏        | 3167/28080 [6:15:44<49:35:40,  7.17s/it]
                                                         
{'loss': 0.6658, 'learning_rate': 0.0004910718514560264, 'epoch': 1.35}

 11%|█▏        | 3167/28080 [6:15:44<49:35:40,  7.17s/it]
 11%|█▏        | 3168/28080 [6:15:51<49:38:02,  7.17s/it]
                                                         
{'loss': 0.6503, 'learning_rate': 0.000491064212482525, 'epoch': 1.35}

 11%|█▏        | 3168/28080 [6:15:51<49:38:02,  7.17s/it]
 11%|█▏        | 3169/28080 [6:15:58<49:30:09,  7.15s/it]
                                                         
{'loss': 0.661, 'learning_rate': 0.000491056570301913, 'epoch': 1.35}

 11%|█▏        | 3169/28080 [6:15:58<49:30:09,  7.15s/it]
 11%|█▏        | 3170/28080 [6:16:05<49:13:54,  7.11s/it]
                                                         
{'loss': 0.6636, 'learning_rate': 0.0004910489249142921, 'epoch': 1.35}

 11%|█▏        | 3170/28080 [6:16:05<49:13:54,  7.11s/it]
 11%|█▏        | 3171/28080 [6:16:13<49:16:14,  7.12s/it]
                                                         
{'loss': 0.678, 'learning_rate': 0.0004910412763197638, 'epoch': 1.35}

 11%|█▏        | 3171/28080 [6:16:13<49:16:14,  7.12s/it]
 11%|█▏        | 3172/28080 [6:16:20<49:18:20,  7.13s/it]
                                                         
{'loss': 0.6722, 'learning_rate': 0.0004910336245184301, 'epoch': 1.36}

 11%|█▏        | 3172/28080 [6:16:20<49:18:20,  7.13s/it]
 11%|█▏        | 3173/28080 [6:16:27<49:11:14,  7.11s/it]
                                                         
{'loss': 0.657, 'learning_rate': 0.0004910259695103926, 'epoch': 1.36}

 11%|█▏        | 3173/28080 [6:16:27<49:11:14,  7.11s/it]
 11%|█▏        | 3174/28080 [6:16:34<49:14:38,  7.12s/it]
                                                         
{'loss': 0.6795, 'learning_rate': 0.0004910183112957532, 'epoch': 1.36}

 11%|█▏        | 3174/28080 [6:16:34<49:14:38,  7.12s/it]
 11%|█▏        | 3175/28080 [6:16:41<48:57:03,  7.08s/it]
                                                         
{'loss': 0.6891, 'learning_rate': 0.0004910106498746139, 'epoch': 1.36}

 11%|█▏        | 3175/28080 [6:16:41<48:57:03,  7.08s/it]
 11%|█▏        | 3176/28080 [6:16:48<49:06:53,  7.10s/it]
                                                         
{'loss': 0.6701, 'learning_rate': 0.0004910029852470766, 'epoch': 1.36}

 11%|█▏        | 3176/28080 [6:16:48<49:06:53,  7.10s/it]
 11%|█▏        | 3177/28080 [6:16:55<49:15:02,  7.12s/it]
                                                         
{'loss': 0.678, 'learning_rate': 0.0004909953174132431, 'epoch': 1.36}

 11%|█▏        | 3177/28080 [6:16:55<49:15:02,  7.12s/it]
 11%|█▏        | 3178/28080 [6:17:02<49:13:47,  7.12s/it]
                                                         
{'loss': 0.689, 'learning_rate': 0.0004909876463732156, 'epoch': 1.36}

 11%|█▏        | 3178/28080 [6:17:02<49:13:47,  7.12s/it]
 11%|█▏        | 3179/28080 [6:17:09<48:59:32,  7.08s/it]
                                                         
{'loss': 0.695, 'learning_rate': 0.000490979972127096, 'epoch': 1.36}

 11%|█▏        | 3179/28080 [6:17:09<48:59:32,  7.08s/it]
 11%|█▏        | 3180/28080 [6:17:16<48:57:44,  7.08s/it]
                                                         
{'loss': 0.6689, 'learning_rate': 0.0004909722946749865, 'epoch': 1.36}

 11%|█▏        | 3180/28080 [6:17:16<48:57:44,  7.08s/it]
 11%|█▏        | 3181/28080 [6:17:23<48:54:50,  7.07s/it]
                                                         
{'loss': 0.6668, 'learning_rate': 0.0004909646140169893, 'epoch': 1.36}

 11%|█▏        | 3181/28080 [6:17:23<48:54:50,  7.07s/it]
 11%|█▏        | 3182/28080 [6:17:31<48:59:34,  7.08s/it]
                                                         
{'loss': 0.6898, 'learning_rate': 0.0004909569301532063, 'epoch': 1.36}

 11%|█▏        | 3182/28080 [6:17:31<48:59:34,  7.08s/it]
 11%|█▏        | 3183/28080 [6:17:38<49:04:01,  7.09s/it]
                                                         
{'loss': 0.6713, 'learning_rate': 0.0004909492430837402, 'epoch': 1.36}

 11%|█▏        | 3183/28080 [6:17:38<49:04:01,  7.09s/it]
 11%|█▏        | 3184/28080 [6:17:45<49:14:59,  7.12s/it]
                                                         
{'loss': 0.6691, 'learning_rate': 0.0004909415528086926, 'epoch': 1.36}

 11%|█▏        | 3184/28080 [6:17:45<49:14:59,  7.12s/it]
 11%|█▏        | 3185/28080 [6:17:52<49:23:20,  7.14s/it]
                                                         
{'loss': 0.6637, 'learning_rate': 0.0004909338593281666, 'epoch': 1.36}

 11%|█▏        | 3185/28080 [6:17:52<49:23:20,  7.14s/it]
 11%|█▏        | 3186/28080 [6:17:59<49:27:02,  7.15s/it]
                                                         
{'loss': 0.6772, 'learning_rate': 0.000490926162642264, 'epoch': 1.36}

 11%|█▏        | 3186/28080 [6:17:59<49:27:02,  7.15s/it]
 11%|█▏        | 3187/28080 [6:18:06<49:43:41,  7.19s/it]
                                                         
{'loss': 0.6726, 'learning_rate': 0.0004909184627510874, 'epoch': 1.36}

 11%|█▏        | 3187/28080 [6:18:06<49:43:41,  7.19s/it]
 11%|█▏        | 3188/28080 [6:18:14<49:30:18,  7.16s/it]
                                                         
{'loss': 0.6639, 'learning_rate': 0.0004909107596547391, 'epoch': 1.36}

 11%|█▏        | 3188/28080 [6:18:14<49:30:18,  7.16s/it]
 11%|█▏        | 3189/28080 [6:18:21<49:31:11,  7.16s/it]
                                                         
{'loss': 0.678, 'learning_rate': 0.0004909030533533218, 'epoch': 1.36}

 11%|█▏        | 3189/28080 [6:18:21<49:31:11,  7.16s/it]
 11%|█▏        | 3190/28080 [6:18:28<49:34:19,  7.17s/it]
                                                         
{'loss': 0.6507, 'learning_rate': 0.0004908953438469378, 'epoch': 1.36}

 11%|█▏        | 3190/28080 [6:18:28<49:34:19,  7.17s/it]
 11%|█▏        | 3191/28080 [6:18:35<49:38:28,  7.18s/it]
                                                         
{'loss': 0.6842, 'learning_rate': 0.0004908876311356898, 'epoch': 1.36}

 11%|█▏        | 3191/28080 [6:18:35<49:38:28,  7.18s/it]
 11%|█▏        | 3192/28080 [6:18:42<49:18:03,  7.13s/it]
                                                         
{'loss': 0.6952, 'learning_rate': 0.0004908799152196804, 'epoch': 1.36}

 11%|█▏        | 3192/28080 [6:18:42<49:18:03,  7.13s/it]
 11%|█▏        | 3193/28080 [6:18:49<49:21:01,  7.14s/it]
                                                         
{'loss': 0.6726, 'learning_rate': 0.0004908721960990121, 'epoch': 1.36}

 11%|█▏        | 3193/28080 [6:18:49<49:21:01,  7.14s/it]
 11%|█▏        | 3194/28080 [6:18:56<49:18:25,  7.13s/it]
                                                         
{'loss': 0.6763, 'learning_rate': 0.0004908644737737879, 'epoch': 1.36}

 11%|█▏        | 3194/28080 [6:18:56<49:18:25,  7.13s/it]
 11%|█▏        | 3195/28080 [6:19:03<49:12:41,  7.12s/it]
                                                         
{'loss': 0.6825, 'learning_rate': 0.0004908567482441104, 'epoch': 1.36}

 11%|█▏        | 3195/28080 [6:19:03<49:12:41,  7.12s/it]
 11%|█▏        | 3196/28080 [6:19:11<49:03:54,  7.10s/it]
                                                         
{'loss': 0.6734, 'learning_rate': 0.000490849019510082, 'epoch': 1.37}

 11%|█▏        | 3196/28080 [6:19:11<49:03:54,  7.10s/it]
 11%|█▏        | 3197/28080 [6:19:18<49:05:50,  7.10s/it]
                                                         
{'loss': 0.6891, 'learning_rate': 0.0004908412875718062, 'epoch': 1.37}

 11%|█▏        | 3197/28080 [6:19:18<49:05:50,  7.10s/it]
 11%|█▏        | 3198/28080 [6:19:25<49:17:01,  7.13s/it]
                                                         
{'loss': 0.6601, 'learning_rate': 0.0004908335524293855, 'epoch': 1.37}

 11%|█▏        | 3198/28080 [6:19:25<49:17:01,  7.13s/it]
 11%|█▏        | 3199/28080 [6:19:32<49:33:02,  7.17s/it]
                                                         
{'loss': 0.6773, 'learning_rate': 0.0004908258140829228, 'epoch': 1.37}

 11%|█▏        | 3199/28080 [6:19:32<49:33:02,  7.17s/it]
 11%|█▏        | 3200/28080 [6:19:39<49:07:56,  7.11s/it]
                                                         
{'loss': 0.6698, 'learning_rate': 0.0004908180725325211, 'epoch': 1.37}

 11%|█▏        | 3200/28080 [6:19:39<49:07:56,  7.11s/it]
 11%|█▏        | 3201/28080 [6:19:46<49:10:58,  7.12s/it]
                                                         
{'loss': 0.6695, 'learning_rate': 0.0004908103277782833, 'epoch': 1.37}

 11%|█▏        | 3201/28080 [6:19:46<49:10:58,  7.12s/it]
 11%|█▏        | 3202/28080 [6:19:53<49:09:24,  7.11s/it]
                                                         
{'loss': 0.6732, 'learning_rate': 0.0004908025798203125, 'epoch': 1.37}

 11%|█▏        | 3202/28080 [6:19:53<49:09:24,  7.11s/it]
 11%|█▏        | 3203/28080 [6:20:01<49:17:35,  7.13s/it]
                                                         
{'loss': 0.6813, 'learning_rate': 0.000490794828658712, 'epoch': 1.37}

 11%|█▏        | 3203/28080 [6:20:01<49:17:35,  7.13s/it]
 11%|█▏        | 3204/28080 [6:20:08<49:18:41,  7.14s/it]
                                                         
{'loss': 0.6684, 'learning_rate': 0.0004907870742935845, 'epoch': 1.37}

 11%|█▏        | 3204/28080 [6:20:08<49:18:41,  7.14s/it]
 11%|█▏        | 3205/28080 [6:20:15<49:14:47,  7.13s/it]
                                                         
{'loss': 0.6853, 'learning_rate': 0.0004907793167250335, 'epoch': 1.37}

 11%|█▏        | 3205/28080 [6:20:15<49:14:47,  7.13s/it]
 11%|█▏        | 3206/28080 [6:20:22<49:00:06,  7.09s/it]
                                                         
{'loss': 0.6679, 'learning_rate': 0.0004907715559531621, 'epoch': 1.37}

 11%|█▏        | 3206/28080 [6:20:22<49:00:06,  7.09s/it]
 11%|█▏        | 3207/28080 [6:20:29<49:01:51,  7.10s/it]
                                                         
{'loss': 0.6607, 'learning_rate': 0.0004907637919780734, 'epoch': 1.37}

 11%|█▏        | 3207/28080 [6:20:29<49:01:51,  7.10s/it]
 11%|█▏        | 3208/28080 [6:20:36<49:12:54,  7.12s/it]
                                                         
{'loss': 0.6608, 'learning_rate': 0.0004907560247998709, 'epoch': 1.37}

 11%|█▏        | 3208/28080 [6:20:36<49:12:54,  7.12s/it]
 11%|█▏        | 3209/28080 [6:20:43<49:26:24,  7.16s/it]
                                                         
{'loss': 0.6598, 'learning_rate': 0.0004907482544186579, 'epoch': 1.37}

 11%|█▏        | 3209/28080 [6:20:43<49:26:24,  7.16s/it]
 11%|█▏        | 3210/28080 [6:20:51<49:34:07,  7.18s/it]
                                                         
{'loss': 0.6772, 'learning_rate': 0.0004907404808345378, 'epoch': 1.37}

 11%|█▏        | 3210/28080 [6:20:51<49:34:07,  7.18s/it]
 11%|█▏        | 3211/28080 [6:20:58<49:35:43,  7.18s/it]
                                                         
{'loss': 0.6602, 'learning_rate': 0.0004907327040476138, 'epoch': 1.37}

 11%|█▏        | 3211/28080 [6:20:58<49:35:43,  7.18s/it]
 11%|█▏        | 3212/28080 [6:21:05<49:34:25,  7.18s/it]
                                                         
{'loss': 0.651, 'learning_rate': 0.0004907249240579896, 'epoch': 1.37}

 11%|█▏        | 3212/28080 [6:21:05<49:34:25,  7.18s/it]
 11%|█▏        | 3213/28080 [6:21:12<49:37:50,  7.19s/it]
                                                         
{'loss': 0.6748, 'learning_rate': 0.0004907171408657687, 'epoch': 1.37}

 11%|█▏        | 3213/28080 [6:21:12<49:37:50,  7.19s/it]
 11%|█▏        | 3214/28080 [6:21:19<49:39:03,  7.19s/it]
                                                         
{'loss': 0.6712, 'learning_rate': 0.0004907093544710545, 'epoch': 1.37}

 11%|█▏        | 3214/28080 [6:21:19<49:39:03,  7.19s/it]
 11%|█▏        | 3215/28080 [6:21:26<49:31:23,  7.17s/it]
                                                         
{'loss': 0.6795, 'learning_rate': 0.0004907015648739506, 'epoch': 1.37}

 11%|█▏        | 3215/28080 [6:21:26<49:31:23,  7.17s/it]
 11%|█▏        | 3216/28080 [6:21:33<49:13:04,  7.13s/it]
                                                         
{'loss': 0.6582, 'learning_rate': 0.0004906937720745609, 'epoch': 1.37}

 11%|█▏        | 3216/28080 [6:21:33<49:13:04,  7.13s/it]
 11%|█▏        | 3217/28080 [6:21:41<49:12:18,  7.12s/it]
                                                         
{'loss': 0.6808, 'learning_rate': 0.0004906859760729887, 'epoch': 1.37}

 11%|█▏        | 3217/28080 [6:21:41<49:12:18,  7.12s/it]
 11%|█▏        | 3218/28080 [6:21:48<49:17:14,  7.14s/it]
                                                         
{'loss': 0.6788, 'learning_rate': 0.000490678176869338, 'epoch': 1.37}

 11%|█▏        | 3218/28080 [6:21:48<49:17:14,  7.14s/it]
 11%|█▏        | 3219/28080 [6:21:55<49:23:52,  7.15s/it]
                                                         
{'loss': 0.6592, 'learning_rate': 0.0004906703744637123, 'epoch': 1.38}

 11%|█▏        | 3219/28080 [6:21:55<49:23:52,  7.15s/it]
 11%|█▏        | 3220/28080 [6:22:02<49:19:54,  7.14s/it]
                                                         
{'loss': 0.672, 'learning_rate': 0.0004906625688562157, 'epoch': 1.38}

 11%|█▏        | 3220/28080 [6:22:02<49:19:54,  7.14s/it]
 11%|█▏        | 3221/28080 [6:22:09<49:23:39,  7.15s/it]
                                                         
{'loss': 0.6655, 'learning_rate': 0.0004906547600469519, 'epoch': 1.38}

 11%|█▏        | 3221/28080 [6:22:09<49:23:39,  7.15s/it]
 11%|█▏        | 3222/28080 [6:22:16<49:27:03,  7.16s/it]
                                                         
{'loss': 0.6595, 'learning_rate': 0.0004906469480360248, 'epoch': 1.38}

 11%|█▏        | 3222/28080 [6:22:16<49:27:03,  7.16s/it]
 11%|█▏        | 3223/28080 [6:22:24<49:31:01,  7.17s/it]
                                                         
{'loss': 0.6335, 'learning_rate': 0.0004906391328235382, 'epoch': 1.38}

 11%|█▏        | 3223/28080 [6:22:24<49:31:01,  7.17s/it]
 11%|█▏        | 3224/28080 [6:22:31<49:25:37,  7.16s/it]
                                                         
{'loss': 0.6765, 'learning_rate': 0.0004906313144095962, 'epoch': 1.38}

 11%|█▏        | 3224/28080 [6:22:31<49:25:37,  7.16s/it]
 11%|█▏        | 3225/28080 [6:22:38<49:21:15,  7.15s/it]
                                                         
{'loss': 0.6436, 'learning_rate': 0.0004906234927943029, 'epoch': 1.38}

 11%|█▏        | 3225/28080 [6:22:38<49:21:15,  7.15s/it]
 11%|█▏        | 3226/28080 [6:22:45<49:19:53,  7.15s/it]
                                                         
{'loss': 0.6709, 'learning_rate': 0.0004906156679777621, 'epoch': 1.38}

 11%|█▏        | 3226/28080 [6:22:45<49:19:53,  7.15s/it]
 11%|█▏        | 3227/28080 [6:22:52<49:24:57,  7.16s/it]
                                                         
{'loss': 0.6672, 'learning_rate': 0.0004906078399600782, 'epoch': 1.38}

 11%|█▏        | 3227/28080 [6:22:52<49:24:57,  7.16s/it]
 11%|█▏        | 3228/28080 [6:22:59<49:15:23,  7.14s/it]
                                                         
{'loss': 0.6778, 'learning_rate': 0.0004906000087413553, 'epoch': 1.38}

 11%|█▏        | 3228/28080 [6:22:59<49:15:23,  7.14s/it]
 11%|█▏        | 3229/28080 [6:23:06<49:30:20,  7.17s/it]
                                                         
{'loss': 0.678, 'learning_rate': 0.0004905921743216974, 'epoch': 1.38}

 11%|█▏        | 3229/28080 [6:23:06<49:30:20,  7.17s/it]
 12%|█▏        | 3230/28080 [6:23:14<49:26:28,  7.16s/it]
                                                         
{'loss': 0.6799, 'learning_rate': 0.0004905843367012088, 'epoch': 1.38}

 12%|█▏        | 3230/28080 [6:23:14<49:26:28,  7.16s/it]
 12%|█▏        | 3231/28080 [6:23:21<49:26:48,  7.16s/it]
                                                         
{'loss': 0.6621, 'learning_rate': 0.0004905764958799938, 'epoch': 1.38}

 12%|█▏        | 3231/28080 [6:23:21<49:26:48,  7.16s/it]
 12%|█▏        | 3232/28080 [6:23:28<49:21:47,  7.15s/it]
                                                         
{'loss': 0.6762, 'learning_rate': 0.0004905686518581567, 'epoch': 1.38}

 12%|█▏        | 3232/28080 [6:23:28<49:21:47,  7.15s/it]
 12%|█▏        | 3233/28080 [6:23:35<49:20:51,  7.15s/it]
                                                         
{'loss': 0.6779, 'learning_rate': 0.0004905608046358018, 'epoch': 1.38}

 12%|█▏        | 3233/28080 [6:23:35<49:20:51,  7.15s/it]
 12%|█▏        | 3234/28080 [6:23:42<49:22:50,  7.15s/it]
                                                         
{'loss': 0.6839, 'learning_rate': 0.0004905529542130337, 'epoch': 1.38}

 12%|█▏        | 3234/28080 [6:23:42<49:22:50,  7.15s/it]
 12%|█▏        | 3235/28080 [6:23:49<49:18:01,  7.14s/it]
                                                         
{'loss': 0.6736, 'learning_rate': 0.0004905451005899566, 'epoch': 1.38}

 12%|█▏        | 3235/28080 [6:23:49<49:18:01,  7.14s/it]
 12%|█▏        | 3236/28080 [6:23:57<49:26:24,  7.16s/it]
                                                         
{'loss': 0.6599, 'learning_rate': 0.0004905372437666752, 'epoch': 1.38}

 12%|█▏        | 3236/28080 [6:23:57<49:26:24,  7.16s/it]
 12%|█▏        | 3237/28080 [6:24:04<49:30:39,  7.17s/it]
                                                         
{'loss': 0.6535, 'learning_rate': 0.0004905293837432939, 'epoch': 1.38}

 12%|█▏        | 3237/28080 [6:24:04<49:30:39,  7.17s/it]
 12%|█▏        | 3238/28080 [6:24:11<49:17:55,  7.14s/it]
                                                         
{'loss': 0.6689, 'learning_rate': 0.0004905215205199173, 'epoch': 1.38}

 12%|█▏        | 3238/28080 [6:24:11<49:17:55,  7.14s/it]
 12%|█▏        | 3239/28080 [6:24:18<49:17:54,  7.14s/it]
                                                         
{'loss': 0.6499, 'learning_rate': 0.0004905136540966499, 'epoch': 1.38}

 12%|█▏        | 3239/28080 [6:24:18<49:17:54,  7.14s/it]
 12%|█▏        | 3240/28080 [6:24:25<49:22:28,  7.16s/it]
                                                         
{'loss': 0.6659, 'learning_rate': 0.0004905057844735966, 'epoch': 1.38}

 12%|█▏        | 3240/28080 [6:24:25<49:22:28,  7.16s/it]
 12%|█▏        | 3241/28080 [6:24:32<49:18:24,  7.15s/it]
                                                         
{'loss': 0.6647, 'learning_rate': 0.0004904979116508619, 'epoch': 1.38}

 12%|█▏        | 3241/28080 [6:24:32<49:18:24,  7.15s/it]
 12%|█▏        | 3242/28080 [6:24:39<49:09:07,  7.12s/it]
                                                         
{'loss': 0.6761, 'learning_rate': 0.0004904900356285506, 'epoch': 1.38}

 12%|█▏        | 3242/28080 [6:24:39<49:09:07,  7.12s/it]
 12%|█▏        | 3243/28080 [6:24:47<49:24:08,  7.16s/it]
                                                         
{'loss': 0.6553, 'learning_rate': 0.0004904821564067674, 'epoch': 1.39}

 12%|█▏        | 3243/28080 [6:24:47<49:24:08,  7.16s/it]
 12%|█▏        | 3244/28080 [6:24:54<49:24:43,  7.16s/it]
                                                         
{'loss': 0.6956, 'learning_rate': 0.0004904742739856173, 'epoch': 1.39}

 12%|█▏        | 3244/28080 [6:24:54<49:24:43,  7.16s/it]
 12%|█▏        | 3245/28080 [6:25:01<49:26:19,  7.17s/it]
                                                         
{'loss': 0.6961, 'learning_rate': 0.000490466388365205, 'epoch': 1.39}

 12%|█▏        | 3245/28080 [6:25:01<49:26:19,  7.17s/it]
 12%|█▏        | 3246/28080 [6:25:08<49:24:42,  7.16s/it]
                                                         
{'loss': 0.6662, 'learning_rate': 0.0004904584995456355, 'epoch': 1.39}

 12%|█▏        | 3246/28080 [6:25:08<49:24:42,  7.16s/it]
 12%|█▏        | 3247/28080 [6:25:15<49:20:44,  7.15s/it]
                                                         
{'loss': 0.6651, 'learning_rate': 0.0004904506075270136, 'epoch': 1.39}

 12%|█▏        | 3247/28080 [6:25:15<49:20:44,  7.15s/it]
 12%|█▏        | 3248/28080 [6:25:22<49:07:36,  7.12s/it]
                                                         
{'loss': 0.6803, 'learning_rate': 0.0004904427123094446, 'epoch': 1.39}

 12%|█▏        | 3248/28080 [6:25:22<49:07:36,  7.12s/it]
 12%|█▏        | 3249/28080 [6:25:29<49:03:46,  7.11s/it]
                                                         
{'loss': 0.6525, 'learning_rate': 0.0004904348138930334, 'epoch': 1.39}

 12%|█▏        | 3249/28080 [6:25:29<49:03:46,  7.11s/it]
 12%|█▏        | 3250/28080 [6:25:37<49:06:29,  7.12s/it]
                                                         
{'loss': 0.681, 'learning_rate': 0.0004904269122778849, 'epoch': 1.39}

 12%|█▏        | 3250/28080 [6:25:37<49:06:29,  7.12s/it]
 12%|█▏        | 3251/28080 [6:25:44<49:11:03,  7.13s/it]
                                                         
{'loss': 0.6687, 'learning_rate': 0.0004904190074641045, 'epoch': 1.39}

 12%|█▏        | 3251/28080 [6:25:44<49:11:03,  7.13s/it]
 12%|█▏        | 3252/28080 [6:25:51<49:03:40,  7.11s/it]
                                                         
{'loss': 0.6804, 'learning_rate': 0.0004904110994517971, 'epoch': 1.39}

 12%|█▏        | 3252/28080 [6:25:51<49:03:40,  7.11s/it]
 12%|█▏        | 3253/28080 [6:25:58<49:03:16,  7.11s/it]
                                                         
{'loss': 0.6511, 'learning_rate': 0.0004904031882410681, 'epoch': 1.39}

 12%|█▏        | 3253/28080 [6:25:58<49:03:16,  7.11s/it]
 12%|█▏        | 3254/28080 [6:26:05<49:09:21,  7.13s/it]
                                                         
{'loss': 0.6626, 'learning_rate': 0.0004903952738320227, 'epoch': 1.39}

 12%|█▏        | 3254/28080 [6:26:05<49:09:21,  7.13s/it]
 12%|█▏        | 3255/28080 [6:26:12<48:59:40,  7.10s/it]
                                                         
{'loss': 0.6769, 'learning_rate': 0.0004903873562247662, 'epoch': 1.39}

 12%|█▏        | 3255/28080 [6:26:12<48:59:40,  7.10s/it]
 12%|█▏        | 3256/28080 [6:26:19<49:09:32,  7.13s/it]
                                                         
{'loss': 0.6653, 'learning_rate': 0.0004903794354194039, 'epoch': 1.39}

 12%|█▏        | 3256/28080 [6:26:19<49:09:32,  7.13s/it]
 12%|█▏        | 3257/28080 [6:26:26<49:08:51,  7.13s/it]
                                                         
{'loss': 0.6776, 'learning_rate': 0.0004903715114160412, 'epoch': 1.39}

 12%|█▏        | 3257/28080 [6:26:26<49:08:51,  7.13s/it]
 12%|█▏        | 3258/28080 [6:26:33<49:05:59,  7.12s/it]
                                                         
{'loss': 0.6619, 'learning_rate': 0.0004903635842147835, 'epoch': 1.39}

 12%|█▏        | 3258/28080 [6:26:33<49:05:59,  7.12s/it]
 12%|█▏        | 3259/28080 [6:26:41<49:08:18,  7.13s/it]
                                                         
{'loss': 0.6552, 'learning_rate': 0.0004903556538157363, 'epoch': 1.39}

 12%|█▏        | 3259/28080 [6:26:41<49:08:18,  7.13s/it]
 12%|█▏        | 3260/28080 [6:26:48<48:59:06,  7.11s/it]
                                                         
{'loss': 0.6673, 'learning_rate': 0.000490347720219005, 'epoch': 1.39}

 12%|█▏        | 3260/28080 [6:26:48<48:59:06,  7.11s/it]
 12%|█▏        | 3261/28080 [6:26:55<49:10:50,  7.13s/it]
                                                         
{'loss': 0.6516, 'learning_rate': 0.0004903397834246954, 'epoch': 1.39}

 12%|█▏        | 3261/28080 [6:26:55<49:10:50,  7.13s/it]
 12%|█▏        | 3262/28080 [6:27:02<49:18:05,  7.15s/it]
                                                         
{'loss': 0.6609, 'learning_rate': 0.0004903318434329128, 'epoch': 1.39}

 12%|█▏        | 3262/28080 [6:27:02<49:18:05,  7.15s/it]
 12%|█▏        | 3263/28080 [6:27:09<49:23:45,  7.17s/it]
                                                         
{'loss': 0.6946, 'learning_rate': 0.000490323900243763, 'epoch': 1.39}

 12%|█▏        | 3263/28080 [6:27:09<49:23:45,  7.17s/it]
 12%|█▏        | 3264/28080 [6:27:16<49:16:50,  7.15s/it]
                                                         
{'loss': 0.6892, 'learning_rate': 0.0004903159538573516, 'epoch': 1.39}

 12%|█▏        | 3264/28080 [6:27:16<49:16:50,  7.15s/it]
 12%|█▏        | 3265/28080 [6:27:23<49:08:18,  7.13s/it]
                                                         
{'loss': 0.6672, 'learning_rate': 0.0004903080042737844, 'epoch': 1.39}

 12%|█▏        | 3265/28080 [6:27:23<49:08:18,  7.13s/it]
 12%|█▏        | 3266/28080 [6:27:31<49:13:28,  7.14s/it]
                                                         
{'loss': 0.6788, 'learning_rate': 0.0004903000514931671, 'epoch': 1.4}

 12%|█▏        | 3266/28080 [6:27:31<49:13:28,  7.14s/it]
 12%|█▏        | 3267/28080 [6:27:38<49:25:18,  7.17s/it]
                                                         
{'loss': 0.6858, 'learning_rate': 0.0004902920955156055, 'epoch': 1.4}

 12%|█▏        | 3267/28080 [6:27:38<49:25:18,  7.17s/it]
 12%|█▏        | 3268/28080 [6:27:45<49:18:43,  7.15s/it]
                                                         
{'loss': 0.6595, 'learning_rate': 0.0004902841363412056, 'epoch': 1.4}

 12%|█▏        | 3268/28080 [6:27:45<49:18:43,  7.15s/it]
 12%|█▏        | 3269/28080 [6:27:52<49:23:58,  7.17s/it]
                                                         
{'loss': 0.6663, 'learning_rate': 0.0004902761739700729, 'epoch': 1.4}

 12%|█▏        | 3269/28080 [6:27:52<49:23:58,  7.17s/it]
 12%|█▏        | 3270/28080 [6:27:59<49:06:38,  7.13s/it]
                                                         
{'loss': 0.636, 'learning_rate': 0.0004902682084023138, 'epoch': 1.4}

 12%|█▏        | 3270/28080 [6:27:59<49:06:38,  7.13s/it]
 12%|█▏        | 3271/28080 [6:28:06<49:17:47,  7.15s/it]
                                                         
{'loss': 0.657, 'learning_rate': 0.000490260239638034, 'epoch': 1.4}

 12%|█▏        | 3271/28080 [6:28:06<49:17:47,  7.15s/it]
 12%|█▏        | 3272/28080 [6:28:14<49:15:16,  7.15s/it]
                                                         
{'loss': 0.6409, 'learning_rate': 0.0004902522676773395, 'epoch': 1.4}

 12%|█▏        | 3272/28080 [6:28:14<49:15:16,  7.15s/it]
 12%|█▏        | 3273/28080 [6:28:21<49:23:27,  7.17s/it]
                                                         
{'loss': 0.6378, 'learning_rate': 0.0004902442925203365, 'epoch': 1.4}

 12%|█▏        | 3273/28080 [6:28:21<49:23:27,  7.17s/it]
 12%|█▏        | 3274/28080 [6:28:28<49:24:08,  7.17s/it]
                                                         
{'loss': 0.6717, 'learning_rate': 0.0004902363141671311, 'epoch': 1.4}

 12%|█▏        | 3274/28080 [6:28:28<49:24:08,  7.17s/it]
 12%|█▏        | 3275/28080 [6:28:35<49:27:53,  7.18s/it]
                                                         
{'loss': 0.6623, 'learning_rate': 0.0004902283326178293, 'epoch': 1.4}

 12%|█▏        | 3275/28080 [6:28:35<49:27:53,  7.18s/it]
 12%|█▏        | 3276/28080 [6:28:42<49:20:06,  7.16s/it]
                                                         
{'loss': 0.6666, 'learning_rate': 0.0004902203478725373, 'epoch': 1.4}

 12%|█▏        | 3276/28080 [6:28:42<49:20:06,  7.16s/it]
 12%|█▏        | 3277/28080 [6:28:49<49:12:42,  7.14s/it]
                                                         
{'loss': 0.6746, 'learning_rate': 0.0004902123599313615, 'epoch': 1.4}

 12%|█▏        | 3277/28080 [6:28:49<49:12:42,  7.14s/it]
 12%|█▏        | 3278/28080 [6:28:57<49:16:46,  7.15s/it]
                                                         
{'loss': 0.6656, 'learning_rate': 0.000490204368794408, 'epoch': 1.4}

 12%|█▏        | 3278/28080 [6:28:57<49:16:46,  7.15s/it]
 12%|█▏        | 3279/28080 [6:29:04<49:18:13,  7.16s/it]
                                                         
{'loss': 0.6594, 'learning_rate': 0.0004901963744617832, 'epoch': 1.4}

 12%|█▏        | 3279/28080 [6:29:04<49:18:13,  7.16s/it]
 12%|█▏        | 3280/28080 [6:29:11<49:16:05,  7.15s/it]
                                                         
{'loss': 0.6821, 'learning_rate': 0.0004901883769335935, 'epoch': 1.4}

 12%|█▏        | 3280/28080 [6:29:11<49:16:05,  7.15s/it]
 12%|█▏        | 3281/28080 [6:29:18<49:29:56,  7.19s/it]
                                                         
{'loss': 0.6687, 'learning_rate': 0.0004901803762099451, 'epoch': 1.4}

 12%|█▏        | 3281/28080 [6:29:18<49:29:56,  7.19s/it]
 12%|█▏        | 3282/28080 [6:29:25<49:09:30,  7.14s/it]
                                                         
{'loss': 0.6752, 'learning_rate': 0.0004901723722909447, 'epoch': 1.4}

 12%|█▏        | 3282/28080 [6:29:25<49:09:30,  7.14s/it]
 12%|█▏        | 3283/28080 [6:29:32<49:13:47,  7.15s/it]
                                                         
{'loss': 0.6656, 'learning_rate': 0.0004901643651766986, 'epoch': 1.4}

 12%|█▏        | 3283/28080 [6:29:32<49:13:47,  7.15s/it]
 12%|█▏        | 3284/28080 [6:29:39<49:10:10,  7.14s/it]
                                                         
{'loss': 0.6756, 'learning_rate': 0.0004901563548673134, 'epoch': 1.4}

 12%|█▏        | 3284/28080 [6:29:39<49:10:10,  7.14s/it]
 12%|█▏        | 3285/28080 [6:29:47<49:11:12,  7.14s/it]
                                                         
{'loss': 0.6629, 'learning_rate': 0.0004901483413628957, 'epoch': 1.4}

 12%|█▏        | 3285/28080 [6:29:47<49:11:12,  7.14s/it]
 12%|█▏        | 3286/28080 [6:29:54<49:10:10,  7.14s/it]
                                                         
{'loss': 0.6705, 'learning_rate': 0.0004901403246635519, 'epoch': 1.4}

 12%|█▏        | 3286/28080 [6:29:54<49:10:10,  7.14s/it]
 12%|█▏        | 3287/28080 [6:30:01<49:06:44,  7.13s/it]
                                                         
{'loss': 0.6434, 'learning_rate': 0.000490132304769389, 'epoch': 1.4}

 12%|█▏        | 3287/28080 [6:30:01<49:06:44,  7.13s/it]
 12%|█▏        | 3288/28080 [6:30:08<49:09:40,  7.14s/it]
                                                         
{'loss': 0.6751, 'learning_rate': 0.0004901242816805134, 'epoch': 1.4}

 12%|█▏        | 3288/28080 [6:30:08<49:09:40,  7.14s/it]
 12%|█▏        | 3289/28080 [6:30:15<49:01:40,  7.12s/it]
                                                         
{'loss': 0.6464, 'learning_rate': 0.000490116255397032, 'epoch': 1.41}

 12%|█▏        | 3289/28080 [6:30:15<49:01:40,  7.12s/it]
 12%|█▏        | 3290/28080 [6:30:22<49:15:51,  7.15s/it]
                                                         
{'loss': 0.6712, 'learning_rate': 0.0004901082259190515, 'epoch': 1.41}

 12%|█▏        | 3290/28080 [6:30:22<49:15:51,  7.15s/it]
 12%|█▏        | 3291/28080 [6:30:29<49:11:06,  7.14s/it]
                                                         
{'loss': 0.6362, 'learning_rate': 0.0004901001932466789, 'epoch': 1.41}

 12%|█▏        | 3291/28080 [6:30:29<49:11:06,  7.14s/it]
 12%|█▏        | 3292/28080 [6:30:37<49:20:34,  7.17s/it]
                                                         
{'loss': 0.6594, 'learning_rate': 0.0004900921573800208, 'epoch': 1.41}

 12%|█▏        | 3292/28080 [6:30:37<49:20:34,  7.17s/it]
 12%|█▏        | 3293/28080 [6:30:44<49:16:28,  7.16s/it]
                                                         
{'loss': 0.6842, 'learning_rate': 0.0004900841183191842, 'epoch': 1.41}

 12%|█▏        | 3293/28080 [6:30:44<49:16:28,  7.16s/it]
 12%|█▏        | 3294/28080 [6:30:51<49:11:04,  7.14s/it]
                                                         
{'loss': 0.6685, 'learning_rate': 0.0004900760760642762, 'epoch': 1.41}

 12%|█▏        | 3294/28080 [6:30:51<49:11:04,  7.14s/it]
 12%|█▏        | 3295/28080 [6:30:58<49:13:25,  7.15s/it]
                                                         
{'loss': 0.6722, 'learning_rate': 0.0004900680306154036, 'epoch': 1.41}

 12%|█▏        | 3295/28080 [6:30:58<49:13:25,  7.15s/it]
 12%|█▏        | 3296/28080 [6:31:05<49:23:51,  7.18s/it]
                                                         
{'loss': 0.682, 'learning_rate': 0.0004900599819726736, 'epoch': 1.41}

 12%|█▏        | 3296/28080 [6:31:05<49:23:51,  7.18s/it]
 12%|█▏        | 3297/28080 [6:31:12<49:20:46,  7.17s/it]
                                                         
{'loss': 0.6643, 'learning_rate': 0.0004900519301361931, 'epoch': 1.41}

 12%|█▏        | 3297/28080 [6:31:12<49:20:46,  7.17s/it]
 12%|█▏        | 3298/28080 [6:31:19<48:55:58,  7.11s/it]
                                                         
{'loss': 0.6497, 'learning_rate': 0.0004900438751060693, 'epoch': 1.41}

 12%|█▏        | 3298/28080 [6:31:19<48:55:58,  7.11s/it]
 12%|█▏        | 3299/28080 [6:31:27<48:56:27,  7.11s/it]
                                                         
{'loss': 0.6494, 'learning_rate': 0.0004900358168824095, 'epoch': 1.41}

 12%|█▏        | 3299/28080 [6:31:27<48:56:27,  7.11s/it]
 12%|█▏        | 3300/28080 [6:31:34<49:12:04,  7.15s/it]
                                                         
{'loss': 0.6751, 'learning_rate': 0.0004900277554653207, 'epoch': 1.41}

 12%|█▏        | 3300/28080 [6:31:34<49:12:04,  7.15s/it]
 12%|█▏        | 3301/28080 [6:31:41<49:17:33,  7.16s/it]
                                                         
{'loss': 0.6625, 'learning_rate': 0.0004900196908549102, 'epoch': 1.41}

 12%|█▏        | 3301/28080 [6:31:41<49:17:33,  7.16s/it]
 12%|█▏        | 3302/28080 [6:31:48<49:26:48,  7.18s/it]
                                                         
{'loss': 0.6784, 'learning_rate': 0.0004900116230512854, 'epoch': 1.41}

 12%|█▏        | 3302/28080 [6:31:48<49:26:48,  7.18s/it]
 12%|█▏        | 3303/28080 [6:31:55<49:17:23,  7.16s/it]
                                                         
{'loss': 0.6744, 'learning_rate': 0.0004900035520545536, 'epoch': 1.41}

 12%|█▏        | 3303/28080 [6:31:55<49:17:23,  7.16s/it]
 12%|█▏        | 3304/28080 [6:32:02<49:11:53,  7.15s/it]
                                                         
{'loss': 0.6657, 'learning_rate': 0.0004899954778648222, 'epoch': 1.41}

 12%|█▏        | 3304/28080 [6:32:02<49:11:53,  7.15s/it]
 12%|█▏        | 3305/28080 [6:32:10<49:15:18,  7.16s/it]
                                                         
{'loss': 0.6701, 'learning_rate': 0.0004899874004821984, 'epoch': 1.41}

 12%|█▏        | 3305/28080 [6:32:10<49:15:18,  7.16s/it]
 12%|█▏        | 3306/28080 [6:32:17<49:00:51,  7.12s/it]
                                                         
{'loss': 0.6551, 'learning_rate': 0.0004899793199067898, 'epoch': 1.41}

 12%|█▏        | 3306/28080 [6:32:17<49:00:51,  7.12s/it]
 12%|█▏        | 3307/28080 [6:32:24<49:09:43,  7.14s/it]
                                                         
{'loss': 0.6613, 'learning_rate': 0.0004899712361387039, 'epoch': 1.41}

 12%|█▏        | 3307/28080 [6:32:24<49:09:43,  7.14s/it]
 12%|█▏        | 3308/28080 [6:32:31<49:17:05,  7.16s/it]
                                                         
{'loss': 0.6687, 'learning_rate': 0.0004899631491780484, 'epoch': 1.41}

 12%|█▏        | 3308/28080 [6:32:31<49:17:05,  7.16s/it]
 12%|█▏        | 3309/28080 [6:32:38<49:20:33,  7.17s/it]
                                                         
{'loss': 0.6768, 'learning_rate': 0.0004899550590249308, 'epoch': 1.41}

 12%|█▏        | 3309/28080 [6:32:38<49:20:33,  7.17s/it]
 12%|█▏        | 3310/28080 [6:32:45<49:16:17,  7.16s/it]
                                                         
{'loss': 0.6613, 'learning_rate': 0.0004899469656794586, 'epoch': 1.41}

 12%|█▏        | 3310/28080 [6:32:45<49:16:17,  7.16s/it]
 12%|█▏        | 3311/28080 [6:32:52<48:54:13,  7.11s/it]
                                                         
{'loss': 0.6703, 'learning_rate': 0.0004899388691417395, 'epoch': 1.41}

 12%|█▏        | 3311/28080 [6:32:52<48:54:13,  7.11s/it]
 12%|█▏        | 3312/28080 [6:32:59<48:59:38,  7.12s/it]
                                                         
{'loss': 0.6698, 'learning_rate': 0.0004899307694118814, 'epoch': 1.41}

 12%|█▏        | 3312/28080 [6:32:59<48:59:38,  7.12s/it]
 12%|█▏        | 3313/28080 [6:33:07<48:56:18,  7.11s/it]
                                                         
{'loss': 0.6868, 'learning_rate': 0.0004899226664899918, 'epoch': 1.42}

 12%|█▏        | 3313/28080 [6:33:07<48:56:18,  7.11s/it]
 12%|█▏        | 3314/28080 [6:33:14<48:50:20,  7.10s/it]
                                                         
{'loss': 0.6956, 'learning_rate': 0.0004899145603761788, 'epoch': 1.42}

 12%|█▏        | 3314/28080 [6:33:14<48:50:20,  7.10s/it]
 12%|█▏        | 3315/28080 [6:33:21<48:49:20,  7.10s/it]
                                                         
{'loss': 0.6694, 'learning_rate': 0.00048990645107055, 'epoch': 1.42}

 12%|█▏        | 3315/28080 [6:33:21<48:49:20,  7.10s/it]
 12%|█▏        | 3316/28080 [6:33:28<48:48:34,  7.10s/it]
                                                         
{'loss': 0.6651, 'learning_rate': 0.0004898983385732133, 'epoch': 1.42}

 12%|█▏        | 3316/28080 [6:33:28<48:48:34,  7.10s/it]
 12%|█▏        | 3317/28080 [6:33:35<49:02:24,  7.13s/it]
                                                         
{'loss': 0.6935, 'learning_rate': 0.0004898902228842768, 'epoch': 1.42}

 12%|█▏        | 3317/28080 [6:33:35<49:02:24,  7.13s/it]
 12%|█▏        | 3318/28080 [6:33:42<49:09:13,  7.15s/it]
                                                         
{'loss': 0.6615, 'learning_rate': 0.0004898821040038483, 'epoch': 1.42}

 12%|█▏        | 3318/28080 [6:33:42<49:09:13,  7.15s/it]
 12%|█▏        | 3319/28080 [6:33:49<49:05:42,  7.14s/it]
                                                         
{'loss': 0.657, 'learning_rate': 0.0004898739819320358, 'epoch': 1.42}

 12%|█▏        | 3319/28080 [6:33:49<49:05:42,  7.14s/it]
 12%|█▏        | 3320/28080 [6:33:57<49:09:48,  7.15s/it]
                                                         
{'loss': 0.6625, 'learning_rate': 0.0004898658566689476, 'epoch': 1.42}

 12%|█▏        | 3320/28080 [6:33:57<49:09:48,  7.15s/it]
 12%|█▏        | 3321/28080 [6:34:03<48:45:55,  7.09s/it]
                                                         
{'loss': 0.6778, 'learning_rate': 0.0004898577282146916, 'epoch': 1.42}

 12%|█▏        | 3321/28080 [6:34:03<48:45:55,  7.09s/it]
 12%|█▏        | 3322/28080 [6:34:11<48:58:11,  7.12s/it]
                                                         
{'loss': 0.6686, 'learning_rate': 0.0004898495965693759, 'epoch': 1.42}

 12%|█▏        | 3322/28080 [6:34:11<48:58:11,  7.12s/it]
 12%|█▏        | 3323/28080 [6:34:18<48:46:07,  7.09s/it]
                                                         
{'loss': 0.6722, 'learning_rate': 0.0004898414617331088, 'epoch': 1.42}

 12%|█▏        | 3323/28080 [6:34:18<48:46:07,  7.09s/it]
 12%|█▏        | 3324/28080 [6:34:25<48:55:37,  7.11s/it]
                                                         
{'loss': 0.6593, 'learning_rate': 0.0004898333237059984, 'epoch': 1.42}

 12%|█▏        | 3324/28080 [6:34:25<48:55:37,  7.11s/it]
 12%|█▏        | 3325/28080 [6:34:32<49:03:36,  7.13s/it]
                                                         
{'loss': 0.6805, 'learning_rate': 0.0004898251824881531, 'epoch': 1.42}

 12%|█▏        | 3325/28080 [6:34:32<49:03:36,  7.13s/it]
 12%|█▏        | 3326/28080 [6:34:39<49:07:06,  7.14s/it]
                                                         
{'loss': 0.6792, 'learning_rate': 0.0004898170380796813, 'epoch': 1.42}

 12%|█▏        | 3326/28080 [6:34:39<49:07:06,  7.14s/it]
 12%|█▏        | 3327/28080 [6:34:46<49:02:52,  7.13s/it]
                                                         
{'loss': 0.6555, 'learning_rate': 0.000489808890480691, 'epoch': 1.42}

 12%|█▏        | 3327/28080 [6:34:46<49:02:52,  7.13s/it]
 12%|█▏        | 3328/28080 [6:34:53<49:01:48,  7.13s/it]
                                                         
{'loss': 0.6564, 'learning_rate': 0.0004898007396912909, 'epoch': 1.42}

 12%|█▏        | 3328/28080 [6:34:53<49:01:48,  7.13s/it]
 12%|█▏        | 3329/28080 [6:35:01<49:17:47,  7.17s/it]
                                                         
{'loss': 0.6765, 'learning_rate': 0.0004897925857115893, 'epoch': 1.42}

 12%|█▏        | 3329/28080 [6:35:01<49:17:47,  7.17s/it]
 12%|█▏        | 3330/28080 [6:35:08<49:01:49,  7.13s/it]
                                                         
{'loss': 0.6596, 'learning_rate': 0.0004897844285416949, 'epoch': 1.42}

 12%|█▏        | 3330/28080 [6:35:08<49:01:49,  7.13s/it]
 12%|█▏        | 3331/28080 [6:35:15<48:56:41,  7.12s/it]
                                                         
{'loss': 0.6756, 'learning_rate': 0.0004897762681817159, 'epoch': 1.42}

 12%|█▏        | 3331/28080 [6:35:15<48:56:41,  7.12s/it]
 12%|█▏        | 3332/28080 [6:35:22<49:04:45,  7.14s/it]
                                                         
{'loss': 0.6737, 'learning_rate': 0.0004897681046317611, 'epoch': 1.42}

 12%|█▏        | 3332/28080 [6:35:22<49:04:45,  7.14s/it]
 12%|█▏        | 3333/28080 [6:35:29<49:15:58,  7.17s/it]
                                                         
{'loss': 0.6704, 'learning_rate': 0.0004897599378919389, 'epoch': 1.42}

 12%|█▏        | 3333/28080 [6:35:29<49:15:58,  7.17s/it]
 12%|█▏        | 3334/28080 [6:35:36<49:23:19,  7.18s/it]
                                                         
{'loss': 0.6644, 'learning_rate': 0.0004897517679623582, 'epoch': 1.42}

 12%|█▏        | 3334/28080 [6:35:36<49:23:19,  7.18s/it]
 12%|█▏        | 3335/28080 [6:35:44<49:31:51,  7.21s/it]
                                                         
{'loss': 0.6684, 'learning_rate': 0.0004897435948431275, 'epoch': 1.42}

 12%|█▏        | 3335/28080 [6:35:44<49:31:51,  7.21s/it]
 12%|█▏        | 3336/28080 [6:35:51<49:30:22,  7.20s/it]
                                                         
{'loss': 0.656, 'learning_rate': 0.0004897354185343555, 'epoch': 1.43}

 12%|█▏        | 3336/28080 [6:35:51<49:30:22,  7.20s/it]
 12%|█▏        | 3337/28080 [6:35:58<49:11:57,  7.16s/it]
                                                         
{'loss': 0.6581, 'learning_rate': 0.0004897272390361512, 'epoch': 1.43}

 12%|█▏        | 3337/28080 [6:35:58<49:11:57,  7.16s/it]
 12%|█▏        | 3338/28080 [6:36:05<49:00:27,  7.13s/it]
                                                         
{'loss': 0.6626, 'learning_rate': 0.0004897190563486234, 'epoch': 1.43}

 12%|█▏        | 3338/28080 [6:36:05<49:00:27,  7.13s/it]
 12%|█▏        | 3339/28080 [6:36:12<49:03:21,  7.14s/it]
                                                         
{'loss': 0.6586, 'learning_rate': 0.0004897108704718806, 'epoch': 1.43}

 12%|█▏        | 3339/28080 [6:36:12<49:03:21,  7.14s/it]
 12%|█▏        | 3340/28080 [6:36:19<48:46:03,  7.10s/it]
                                                         
{'loss': 0.6746, 'learning_rate': 0.0004897026814060321, 'epoch': 1.43}

 12%|█▏        | 3340/28080 [6:36:19<48:46:03,  7.10s/it]
 12%|█▏        | 3341/28080 [6:36:26<49:01:51,  7.13s/it]
                                                         
{'loss': 0.6599, 'learning_rate': 0.0004896944891511868, 'epoch': 1.43}

 12%|█▏        | 3341/28080 [6:36:26<49:01:51,  7.13s/it]
 12%|█▏        | 3342/28080 [6:36:34<49:01:12,  7.13s/it]
                                                         
{'loss': 0.6786, 'learning_rate': 0.0004896862937074536, 'epoch': 1.43}

 12%|█▏        | 3342/28080 [6:36:34<49:01:12,  7.13s/it]
 12%|█▏        | 3343/28080 [6:36:41<48:55:06,  7.12s/it]
                                                         
{'loss': 0.6637, 'learning_rate': 0.0004896780950749414, 'epoch': 1.43}

 12%|█▏        | 3343/28080 [6:36:41<48:55:06,  7.12s/it]
 12%|█▏        | 3344/28080 [6:36:48<48:56:04,  7.12s/it]
                                                         
{'loss': 0.6748, 'learning_rate': 0.0004896698932537595, 'epoch': 1.43}

 12%|█▏        | 3344/28080 [6:36:48<48:56:04,  7.12s/it]
 12%|█▏        | 3345/28080 [6:36:55<49:00:58,  7.13s/it]
                                                         
{'loss': 0.669, 'learning_rate': 0.0004896616882440167, 'epoch': 1.43}

 12%|█▏        | 3345/28080 [6:36:55<49:00:58,  7.13s/it]
 12%|█▏        | 3346/28080 [6:37:02<48:45:51,  7.10s/it]
                                                         
{'loss': 0.6758, 'learning_rate': 0.0004896534800458227, 'epoch': 1.43}

 12%|█▏        | 3346/28080 [6:37:02<48:45:51,  7.10s/it]
 12%|█▏        | 3347/28080 [6:37:09<48:43:38,  7.09s/it]
                                                         
{'loss': 0.6927, 'learning_rate': 0.0004896452686592863, 'epoch': 1.43}

 12%|█▏        | 3347/28080 [6:37:09<48:43:38,  7.09s/it]
 12%|█▏        | 3348/28080 [6:37:16<48:48:11,  7.10s/it]
                                                         
{'loss': 0.6834, 'learning_rate': 0.0004896370540845167, 'epoch': 1.43}

 12%|█▏        | 3348/28080 [6:37:16<48:48:11,  7.10s/it]
 12%|█▏        | 3349/28080 [6:37:23<48:53:21,  7.12s/it]
                                                         
{'loss': 0.6473, 'learning_rate': 0.0004896288363216234, 'epoch': 1.43}

 12%|█▏        | 3349/28080 [6:37:23<48:53:21,  7.12s/it]
 12%|█▏        | 3350/28080 [6:37:30<48:54:50,  7.12s/it]
                                                         
{'loss': 0.6695, 'learning_rate': 0.0004896206153707157, 'epoch': 1.43}

 12%|█▏        | 3350/28080 [6:37:30<48:54:50,  7.12s/it]
 12%|█▏        | 3351/28080 [6:37:38<49:05:58,  7.15s/it]
                                                         
{'loss': 0.6771, 'learning_rate': 0.0004896123912319028, 'epoch': 1.43}

 12%|█▏        | 3351/28080 [6:37:38<49:05:58,  7.15s/it]
 12%|█▏        | 3352/28080 [6:37:45<48:55:09,  7.12s/it]
                                                         
{'loss': 0.6835, 'learning_rate': 0.0004896041639052943, 'epoch': 1.43}

 12%|█▏        | 3352/28080 [6:37:45<48:55:09,  7.12s/it]
 12%|█▏        | 3353/28080 [6:37:52<48:52:35,  7.12s/it]
                                                         
{'loss': 0.6517, 'learning_rate': 0.0004895959333909996, 'epoch': 1.43}

 12%|█▏        | 3353/28080 [6:37:52<48:52:35,  7.12s/it]
 12%|█▏        | 3354/28080 [6:37:59<49:10:24,  7.16s/it]
                                                         
{'loss': 0.6672, 'learning_rate': 0.0004895876996891281, 'epoch': 1.43}

 12%|█▏        | 3354/28080 [6:37:59<49:10:24,  7.16s/it]
 12%|█▏        | 3355/28080 [6:38:06<49:04:04,  7.14s/it]
                                                         
{'loss': 0.6634, 'learning_rate': 0.0004895794627997895, 'epoch': 1.43}

 12%|█▏        | 3355/28080 [6:38:06<49:04:04,  7.14s/it]
 12%|█▏        | 3356/28080 [6:38:13<48:55:57,  7.12s/it]
                                                         
{'loss': 0.6803, 'learning_rate': 0.0004895712227230933, 'epoch': 1.43}

 12%|█▏        | 3356/28080 [6:38:13<48:55:57,  7.12s/it]
 12%|█▏        | 3357/28080 [6:38:20<48:46:55,  7.10s/it]
                                                         
{'loss': 0.6874, 'learning_rate': 0.0004895629794591491, 'epoch': 1.43}

 12%|█▏        | 3357/28080 [6:38:20<48:46:55,  7.10s/it]
 12%|█▏        | 3358/28080 [6:38:27<48:47:59,  7.11s/it]
                                                         
{'loss': 0.688, 'learning_rate': 0.0004895547330080666, 'epoch': 1.43}

 12%|█▏        | 3358/28080 [6:38:27<48:47:59,  7.11s/it]
 12%|█▏        | 3359/28080 [6:38:35<48:45:51,  7.10s/it]
                                                         
{'loss': 0.6534, 'learning_rate': 0.0004895464833699556, 'epoch': 1.43}

 12%|█▏        | 3359/28080 [6:38:35<48:45:51,  7.10s/it]
 12%|█▏        | 3360/28080 [6:38:42<48:43:50,  7.10s/it]
                                                         
{'loss': 0.6667, 'learning_rate': 0.0004895382305449257, 'epoch': 1.44}

 12%|█▏        | 3360/28080 [6:38:42<48:43:50,  7.10s/it]
 12%|█▏        | 3361/28080 [6:38:49<48:50:54,  7.11s/it]
                                                         
{'loss': 0.6667, 'learning_rate': 0.0004895299745330868, 'epoch': 1.44}

 12%|█▏        | 3361/28080 [6:38:49<48:50:54,  7.11s/it]
 12%|█▏        | 3362/28080 [6:38:56<48:45:15,  7.10s/it]
                                                         
{'loss': 0.6843, 'learning_rate': 0.0004895217153345486, 'epoch': 1.44}

 12%|█▏        | 3362/28080 [6:38:56<48:45:15,  7.10s/it]
 12%|█▏        | 3363/28080 [6:39:03<48:47:53,  7.11s/it]
                                                         
{'loss': 0.6577, 'learning_rate': 0.0004895134529494211, 'epoch': 1.44}

 12%|█▏        | 3363/28080 [6:39:03<48:47:53,  7.11s/it]
 12%|█▏        | 3364/28080 [6:39:10<48:57:17,  7.13s/it]
                                                         
{'loss': 0.6718, 'learning_rate': 0.0004895051873778142, 'epoch': 1.44}

 12%|█▏        | 3364/28080 [6:39:10<48:57:17,  7.13s/it]
 12%|█▏        | 3365/28080 [6:39:17<48:50:27,  7.11s/it]
                                                         
{'loss': 0.6682, 'learning_rate': 0.0004894969186198379, 'epoch': 1.44}

 12%|█▏        | 3365/28080 [6:39:17<48:50:27,  7.11s/it]
 12%|█▏        | 3366/28080 [6:39:24<48:53:48,  7.12s/it]
                                                         
{'loss': 0.6843, 'learning_rate': 0.0004894886466756022, 'epoch': 1.44}

 12%|█▏        | 3366/28080 [6:39:24<48:53:48,  7.12s/it]
 12%|█▏        | 3367/28080 [6:39:31<48:53:45,  7.12s/it]
                                                         
{'loss': 0.6578, 'learning_rate': 0.0004894803715452172, 'epoch': 1.44}

 12%|█▏        | 3367/28080 [6:39:31<48:53:45,  7.12s/it]
 12%|█▏        | 3368/28080 [6:39:39<49:02:29,  7.14s/it]
                                                         
{'loss': 0.6846, 'learning_rate': 0.0004894720932287928, 'epoch': 1.44}

 12%|█▏        | 3368/28080 [6:39:39<49:02:29,  7.14s/it]
 12%|█▏        | 3369/28080 [6:39:46<49:12:56,  7.17s/it]
                                                         
{'loss': 0.6714, 'learning_rate': 0.0004894638117264392, 'epoch': 1.44}

 12%|█▏        | 3369/28080 [6:39:46<49:12:56,  7.17s/it]
 12%|█▏        | 3370/28080 [6:39:53<49:03:01,  7.15s/it]
                                                         
{'loss': 0.6763, 'learning_rate': 0.0004894555270382667, 'epoch': 1.44}

 12%|█▏        | 3370/28080 [6:39:53<49:03:01,  7.15s/it]
 12%|█▏        | 3371/28080 [6:40:00<49:07:50,  7.16s/it]
                                                         
{'loss': 0.6509, 'learning_rate': 0.0004894472391643854, 'epoch': 1.44}

 12%|█▏        | 3371/28080 [6:40:00<49:07:50,  7.16s/it]
 12%|█▏        | 3372/28080 [6:40:07<49:01:18,  7.14s/it]
                                                         
{'loss': 0.6409, 'learning_rate': 0.0004894389481049056, 'epoch': 1.44}

 12%|█▏        | 3372/28080 [6:40:07<49:01:18,  7.14s/it]
 12%|█▏        | 3373/28080 [6:40:14<48:52:50,  7.12s/it]
                                                         
{'loss': 0.6689, 'learning_rate': 0.0004894306538599377, 'epoch': 1.44}

 12%|█▏        | 3373/28080 [6:40:14<48:52:50,  7.12s/it]
 12%|█▏        | 3374/28080 [6:40:22<48:59:35,  7.14s/it]
                                                         
{'loss': 0.6698, 'learning_rate': 0.0004894223564295919, 'epoch': 1.44}

 12%|█▏        | 3374/28080 [6:40:22<48:59:35,  7.14s/it]
 12%|█▏        | 3375/28080 [6:40:29<49:00:23,  7.14s/it]
                                                         
{'loss': 0.681, 'learning_rate': 0.0004894140558139787, 'epoch': 1.44}

 12%|█▏        | 3375/28080 [6:40:29<49:00:23,  7.14s/it]
 12%|█▏        | 3376/28080 [6:40:36<49:00:02,  7.14s/it]
                                                         
{'loss': 0.688, 'learning_rate': 0.0004894057520132084, 'epoch': 1.44}

 12%|█▏        | 3376/28080 [6:40:36<49:00:02,  7.14s/it]
 12%|█▏        | 3377/28080 [6:40:43<49:06:14,  7.16s/it]
                                                         
{'loss': 0.69, 'learning_rate': 0.0004893974450273916, 'epoch': 1.44}

 12%|█▏        | 3377/28080 [6:40:43<49:06:14,  7.16s/it]
 12%|█▏        | 3378/28080 [6:40:50<49:05:55,  7.16s/it]
                                                         
{'loss': 0.6521, 'learning_rate': 0.0004893891348566387, 'epoch': 1.44}

 12%|█▏        | 3378/28080 [6:40:50<49:05:55,  7.16s/it]
 12%|█▏        | 3379/28080 [6:40:57<49:10:46,  7.17s/it]
                                                         
{'loss': 0.6695, 'learning_rate': 0.0004893808215010604, 'epoch': 1.44}

 12%|█▏        | 3379/28080 [6:40:57<49:10:46,  7.17s/it]
 12%|█▏        | 3380/28080 [6:41:04<49:05:27,  7.15s/it]
                                                         
{'loss': 0.6546, 'learning_rate': 0.0004893725049607672, 'epoch': 1.44}

 12%|█▏        | 3380/28080 [6:41:04<49:05:27,  7.15s/it]
 12%|█▏        | 3381/28080 [6:41:12<49:11:52,  7.17s/it]
                                                         
{'loss': 0.6668, 'learning_rate': 0.0004893641852358698, 'epoch': 1.44}

 12%|█▏        | 3381/28080 [6:41:12<49:11:52,  7.17s/it]
 12%|█▏        | 3382/28080 [6:41:19<49:18:00,  7.19s/it]
                                                         
{'loss': 0.6341, 'learning_rate': 0.0004893558623264788, 'epoch': 1.44}

 12%|█▏        | 3382/28080 [6:41:19<49:18:00,  7.19s/it]
 12%|█▏        | 3383/28080 [6:41:26<49:10:21,  7.17s/it]
                                                         
{'loss': 0.6648, 'learning_rate': 0.000489347536232705, 'epoch': 1.45}

 12%|█▏        | 3383/28080 [6:41:26<49:10:21,  7.17s/it]
 12%|█▏        | 3384/28080 [6:41:33<49:16:56,  7.18s/it]
                                                         
{'loss': 0.6569, 'learning_rate': 0.0004893392069546591, 'epoch': 1.45}

 12%|█▏        | 3384/28080 [6:41:33<49:16:56,  7.18s/it]
 12%|█▏        | 3385/28080 [6:41:40<49:08:01,  7.16s/it]
                                                         
{'loss': 0.683, 'learning_rate': 0.000489330874492452, 'epoch': 1.45}

 12%|█▏        | 3385/28080 [6:41:40<49:08:01,  7.16s/it]
 12%|█▏        | 3386/28080 [6:41:47<48:58:37,  7.14s/it]
                                                         
{'loss': 0.6537, 'learning_rate': 0.0004893225388461946, 'epoch': 1.45}

 12%|█▏        | 3386/28080 [6:41:47<48:58:37,  7.14s/it]
 12%|█▏        | 3387/28080 [6:41:55<49:00:56,  7.15s/it]
                                                         
{'loss': 0.6318, 'learning_rate': 0.0004893142000159976, 'epoch': 1.45}

 12%|█▏        | 3387/28080 [6:41:55<49:00:56,  7.15s/it]
 12%|█▏        | 3388/28080 [6:42:02<49:02:56,  7.15s/it]
                                                         
{'loss': 0.6547, 'learning_rate': 0.0004893058580019721, 'epoch': 1.45}

 12%|█▏        | 3388/28080 [6:42:02<49:02:56,  7.15s/it]
 12%|█▏        | 3389/28080 [6:42:09<49:08:56,  7.17s/it]
                                                         
{'loss': 0.6822, 'learning_rate': 0.0004892975128042291, 'epoch': 1.45}

 12%|█▏        | 3389/28080 [6:42:09<49:08:56,  7.17s/it]
 12%|█▏        | 3390/28080 [6:42:16<49:12:08,  7.17s/it]
                                                         
{'loss': 0.6394, 'learning_rate': 0.0004892891644228796, 'epoch': 1.45}

 12%|█▏        | 3390/28080 [6:42:16<49:12:08,  7.17s/it]
 12%|█▏        | 3391/28080 [6:42:23<49:13:52,  7.18s/it]
                                                         
{'loss': 0.6447, 'learning_rate': 0.0004892808128580345, 'epoch': 1.45}

 12%|█▏        | 3391/28080 [6:42:23<49:13:52,  7.18s/it]
 12%|█▏        | 3392/28080 [6:42:31<49:11:19,  7.17s/it]
                                                         
{'loss': 0.6678, 'learning_rate': 0.000489272458109805, 'epoch': 1.45}

 12%|█▏        | 3392/28080 [6:42:31<49:11:19,  7.17s/it]
 12%|█▏        | 3393/28080 [6:42:38<48:57:42,  7.14s/it]
                                                         
{'loss': 0.6763, 'learning_rate': 0.0004892641001783024, 'epoch': 1.45}

 12%|█▏        | 3393/28080 [6:42:38<48:57:42,  7.14s/it]
 12%|█▏        | 3394/28080 [6:42:45<49:08:52,  7.17s/it]
                                                         
{'loss': 0.6899, 'learning_rate': 0.0004892557390636377, 'epoch': 1.45}

 12%|█▏        | 3394/28080 [6:42:45<49:08:52,  7.17s/it]
 12%|█▏        | 3395/28080 [6:42:52<49:11:45,  7.17s/it]
                                                         
{'loss': 0.6846, 'learning_rate': 0.0004892473747659223, 'epoch': 1.45}

 12%|█▏        | 3395/28080 [6:42:52<49:11:45,  7.17s/it]
 12%|█▏        | 3396/28080 [6:42:59<49:00:59,  7.15s/it]
                                                         
{'loss': 0.6819, 'learning_rate': 0.0004892390072852674, 'epoch': 1.45}

 12%|█▏        | 3396/28080 [6:42:59<49:00:59,  7.15s/it]
 12%|█▏        | 3397/28080 [6:43:06<49:02:12,  7.15s/it]
                                                         
{'loss': 0.657, 'learning_rate': 0.0004892306366217842, 'epoch': 1.45}

 12%|█▏        | 3397/28080 [6:43:06<49:02:12,  7.15s/it]
 12%|█▏        | 3398/28080 [6:43:13<49:09:53,  7.17s/it]
                                                         
{'loss': 0.6633, 'learning_rate': 0.0004892222627755843, 'epoch': 1.45}

 12%|█▏        | 3398/28080 [6:43:13<49:09:53,  7.17s/it]
 12%|█▏        | 3399/28080 [6:43:21<49:04:21,  7.16s/it]
                                                         
{'loss': 0.6445, 'learning_rate': 0.0004892138857467789, 'epoch': 1.45}

 12%|█▏        | 3399/28080 [6:43:21<49:04:21,  7.16s/it]
 12%|█▏        | 3400/28080 [6:43:28<49:06:16,  7.16s/it]
                                                         
{'loss': 0.6601, 'learning_rate': 0.0004892055055354796, 'epoch': 1.45}

 12%|█▏        | 3400/28080 [6:43:28<49:06:16,  7.16s/it]
 12%|█▏        | 3401/28080 [6:43:35<49:16:36,  7.19s/it]
                                                         
{'loss': 0.677, 'learning_rate': 0.0004891971221417978, 'epoch': 1.45}

 12%|█▏        | 3401/28080 [6:43:35<49:16:36,  7.19s/it]
 12%|█▏        | 3402/28080 [6:43:42<49:05:59,  7.16s/it]
                                                         
{'loss': 0.6835, 'learning_rate': 0.000489188735565845, 'epoch': 1.45}

 12%|█▏        | 3402/28080 [6:43:42<49:05:59,  7.16s/it]
 12%|█▏        | 3403/28080 [6:43:49<49:12:51,  7.18s/it]
                                                         
{'loss': 0.6694, 'learning_rate': 0.0004891803458077329, 'epoch': 1.45}

 12%|█▏        | 3403/28080 [6:43:49<49:12:51,  7.18s/it]
 12%|█▏        | 3404/28080 [6:43:57<49:13:29,  7.18s/it]
                                                         
{'loss': 0.661, 'learning_rate': 0.0004891719528675731, 'epoch': 1.45}

 12%|█▏        | 3404/28080 [6:43:57<49:13:29,  7.18s/it]
 12%|█▏        | 3405/28080 [6:44:04<49:15:10,  7.19s/it]
                                                         
{'loss': 0.6627, 'learning_rate': 0.0004891635567454771, 'epoch': 1.45}

 12%|█▏        | 3405/28080 [6:44:04<49:15:10,  7.19s/it]
 12%|█▏        | 3406/28080 [6:44:11<49:16:28,  7.19s/it]
                                                         
{'loss': 0.6753, 'learning_rate': 0.0004891551574415567, 'epoch': 1.46}

 12%|█▏        | 3406/28080 [6:44:11<49:16:28,  7.19s/it]
 12%|█▏        | 3407/28080 [6:44:18<49:18:20,  7.19s/it]
                                                         
{'loss': 0.6347, 'learning_rate': 0.0004891467549559237, 'epoch': 1.46}

 12%|█▏        | 3407/28080 [6:44:18<49:18:20,  7.19s/it]
 12%|█▏        | 3408/28080 [6:44:25<48:56:49,  7.14s/it]
                                                         
{'loss': 0.6572, 'learning_rate': 0.0004891383492886898, 'epoch': 1.46}

 12%|█▏        | 3408/28080 [6:44:25<48:56:49,  7.14s/it]
 12%|█▏        | 3409/28080 [6:44:32<48:41:15,  7.10s/it]
                                                         
{'loss': 0.648, 'learning_rate': 0.0004891299404399669, 'epoch': 1.46}

 12%|█▏        | 3409/28080 [6:44:32<48:41:15,  7.10s/it]
 12%|█▏        | 3410/28080 [6:44:39<48:40:45,  7.10s/it]
                                                         
{'loss': 0.6712, 'learning_rate': 0.0004891215284098669, 'epoch': 1.46}

 12%|█▏        | 3410/28080 [6:44:39<48:40:45,  7.10s/it]
 12%|█▏        | 3411/28080 [6:44:46<48:46:06,  7.12s/it]
                                                         
{'loss': 0.6596, 'learning_rate': 0.0004891131131985016, 'epoch': 1.46}

 12%|█▏        | 3411/28080 [6:44:46<48:46:06,  7.12s/it]
 12%|█▏        | 3412/28080 [6:44:53<48:38:20,  7.10s/it]
                                                         
{'loss': 0.6664, 'learning_rate': 0.000489104694805983, 'epoch': 1.46}

 12%|█▏        | 3412/28080 [6:44:53<48:38:20,  7.10s/it]
 12%|█▏        | 3413/28080 [6:45:01<48:40:13,  7.10s/it]
                                                         
{'loss': 0.6655, 'learning_rate': 0.0004890962732324231, 'epoch': 1.46}

 12%|█▏        | 3413/28080 [6:45:01<48:40:13,  7.10s/it]
 12%|█▏        | 3414/28080 [6:45:08<48:41:05,  7.11s/it]
                                                         
{'loss': 0.661, 'learning_rate': 0.000489087848477934, 'epoch': 1.46}

 12%|█▏        | 3414/28080 [6:45:08<48:41:05,  7.11s/it]
 12%|█▏        | 3415/28080 [6:45:15<48:35:31,  7.09s/it]
                                                         
{'loss': 0.6668, 'learning_rate': 0.0004890794205426276, 'epoch': 1.46}

 12%|█▏        | 3415/28080 [6:45:15<48:35:31,  7.09s/it]
 12%|█▏        | 3416/28080 [6:45:22<48:37:51,  7.10s/it]
                                                         
{'loss': 0.6829, 'learning_rate': 0.0004890709894266164, 'epoch': 1.46}

 12%|█▏        | 3416/28080 [6:45:22<48:37:51,  7.10s/it]
 12%|█▏        | 3417/28080 [6:45:29<48:37:29,  7.10s/it]
                                                         
{'loss': 0.662, 'learning_rate': 0.0004890625551300121, 'epoch': 1.46}

 12%|█▏        | 3417/28080 [6:45:29<48:37:29,  7.10s/it]
 12%|█▏        | 3418/28080 [6:45:36<48:47:43,  7.12s/it]
                                                         
{'loss': 0.6807, 'learning_rate': 0.0004890541176529272, 'epoch': 1.46}

 12%|█▏        | 3418/28080 [6:45:36<48:47:43,  7.12s/it]
 12%|█▏        | 3419/28080 [6:45:43<48:57:14,  7.15s/it]
                                                         
{'loss': 0.7096, 'learning_rate': 0.0004890456769954739, 'epoch': 1.46}

 12%|█▏        | 3419/28080 [6:45:43<48:57:14,  7.15s/it]
 12%|█▏        | 3420/28080 [6:45:50<48:56:39,  7.15s/it]
                                                         
{'loss': 0.6627, 'learning_rate': 0.0004890372331577644, 'epoch': 1.46}

 12%|█▏        | 3420/28080 [6:45:50<48:56:39,  7.15s/it]
 12%|█▏        | 3421/28080 [6:45:58<48:51:17,  7.13s/it]
                                                         
{'loss': 0.6838, 'learning_rate': 0.0004890287861399112, 'epoch': 1.46}

 12%|█▏        | 3421/28080 [6:45:58<48:51:17,  7.13s/it]
 12%|█▏        | 3422/28080 [6:46:05<48:44:50,  7.12s/it]
                                                         
{'loss': 0.694, 'learning_rate': 0.0004890203359420265, 'epoch': 1.46}

 12%|█▏        | 3422/28080 [6:46:05<48:44:50,  7.12s/it]
 12%|█▏        | 3423/28080 [6:46:12<48:40:30,  7.11s/it]
                                                         
{'loss': 0.6614, 'learning_rate': 0.0004890118825642229, 'epoch': 1.46}

 12%|█▏        | 3423/28080 [6:46:12<48:40:30,  7.11s/it]
 12%|█▏        | 3424/28080 [6:46:19<48:46:11,  7.12s/it]
                                                         
{'loss': 0.6687, 'learning_rate': 0.0004890034260066128, 'epoch': 1.46}

 12%|█▏        | 3424/28080 [6:46:19<48:46:11,  7.12s/it]
 12%|█▏        | 3425/28080 [6:46:26<49:01:59,  7.16s/it]
                                                         
{'loss': 0.6777, 'learning_rate': 0.0004889949662693086, 'epoch': 1.46}

 12%|█▏        | 3425/28080 [6:46:26<49:01:59,  7.16s/it]
 12%|█▏        | 3426/28080 [6:46:33<49:14:44,  7.19s/it]
                                                         
{'loss': 0.6481, 'learning_rate': 0.000488986503352423, 'epoch': 1.46}

 12%|█▏        | 3426/28080 [6:46:33<49:14:44,  7.19s/it]
 12%|█▏        | 3427/28080 [6:46:40<48:56:41,  7.15s/it]
                                                         
{'loss': 0.662, 'learning_rate': 0.0004889780372560685, 'epoch': 1.46}

 12%|█▏        | 3427/28080 [6:46:40<48:56:41,  7.15s/it]
 12%|█▏        | 3428/28080 [6:46:48<48:56:57,  7.15s/it]
                                                         
{'loss': 0.6747, 'learning_rate': 0.0004889695679803577, 'epoch': 1.46}

 12%|█▏        | 3428/28080 [6:46:48<48:56:57,  7.15s/it]
 12%|█▏        | 3429/28080 [6:46:55<49:03:29,  7.16s/it]
                                                         
{'loss': 0.6532, 'learning_rate': 0.0004889610955254034, 'epoch': 1.46}

 12%|█▏        | 3429/28080 [6:46:55<49:03:29,  7.16s/it]
 12%|█▏        | 3430/28080 [6:47:02<48:58:33,  7.15s/it]
                                                         
{'loss': 0.6749, 'learning_rate': 0.0004889526198913183, 'epoch': 1.47}

 12%|█▏        | 3430/28080 [6:47:02<48:58:33,  7.15s/it]
 12%|█▏        | 3431/28080 [6:47:09<49:02:44,  7.16s/it]
                                                         
{'loss': 0.6601, 'learning_rate': 0.0004889441410782149, 'epoch': 1.47}

 12%|█▏        | 3431/28080 [6:47:09<49:02:44,  7.16s/it]
 12%|█▏        | 3432/28080 [6:47:16<49:00:14,  7.16s/it]
                                                         
{'loss': 0.6609, 'learning_rate': 0.0004889356590862064, 'epoch': 1.47}

 12%|█▏        | 3432/28080 [6:47:16<49:00:14,  7.16s/it]
 12%|█▏        | 3433/28080 [6:47:23<49:00:02,  7.16s/it]
                                                         
{'loss': 0.6746, 'learning_rate': 0.0004889271739154054, 'epoch': 1.47}

 12%|█▏        | 3433/28080 [6:47:23<49:00:02,  7.16s/it]
 12%|█▏        | 3434/28080 [6:47:31<48:53:41,  7.14s/it]
                                                         
{'loss': 0.6719, 'learning_rate': 0.0004889186855659247, 'epoch': 1.47}

 12%|█▏        | 3434/28080 [6:47:31<48:53:41,  7.14s/it]
 12%|█▏        | 3435/28080 [6:47:38<48:46:32,  7.12s/it]
                                                         
{'loss': 0.6444, 'learning_rate': 0.0004889101940378776, 'epoch': 1.47}

 12%|█▏        | 3435/28080 [6:47:38<48:46:32,  7.12s/it]
 12%|█▏        | 3436/28080 [6:47:45<48:43:50,  7.12s/it]
                                                         
{'loss': 0.6793, 'learning_rate': 0.0004889016993313767, 'epoch': 1.47}

 12%|█▏        | 3436/28080 [6:47:45<48:43:50,  7.12s/it]
 12%|█▏        | 3437/28080 [6:47:52<48:50:05,  7.13s/it]
                                                         
{'loss': 0.6626, 'learning_rate': 0.0004888932014465352, 'epoch': 1.47}

 12%|█▏        | 3437/28080 [6:47:52<48:50:05,  7.13s/it]
 12%|█▏        | 3438/28080 [6:47:59<48:46:42,  7.13s/it]
                                                         
{'loss': 0.6645, 'learning_rate': 0.0004888847003834662, 'epoch': 1.47}

 12%|█▏        | 3438/28080 [6:47:59<48:46:42,  7.13s/it]
 12%|█▏        | 3439/28080 [6:48:06<48:44:28,  7.12s/it]
                                                         
{'loss': 0.6618, 'learning_rate': 0.0004888761961422825, 'epoch': 1.47}

 12%|█▏        | 3439/28080 [6:48:06<48:44:28,  7.12s/it]
 12%|█▏        | 3440/28080 [6:48:13<48:54:50,  7.15s/it]
                                                         
{'loss': 0.6827, 'learning_rate': 0.0004888676887230975, 'epoch': 1.47}

 12%|█▏        | 3440/28080 [6:48:13<48:54:50,  7.15s/it]
 12%|█▏        | 3441/28080 [6:48:21<49:09:34,  7.18s/it]
                                                         
{'loss': 0.6712, 'learning_rate': 0.0004888591781260244, 'epoch': 1.47}

 12%|█▏        | 3441/28080 [6:48:21<49:09:34,  7.18s/it]
 12%|█▏        | 3442/28080 [6:48:28<49:11:27,  7.19s/it]
                                                         
{'loss': 0.6632, 'learning_rate': 0.0004888506643511763, 'epoch': 1.47}

 12%|█▏        | 3442/28080 [6:48:28<49:11:27,  7.19s/it]
 12%|█▏        | 3443/28080 [6:48:35<49:01:02,  7.16s/it]
                                                         
{'loss': 0.6759, 'learning_rate': 0.0004888421473986665, 'epoch': 1.47}

 12%|█▏        | 3443/28080 [6:48:35<49:01:02,  7.16s/it]
 12%|█▏        | 3444/28080 [6:48:42<48:48:38,  7.13s/it]
                                                         
{'loss': 0.6455, 'learning_rate': 0.0004888336272686084, 'epoch': 1.47}

 12%|█▏        | 3444/28080 [6:48:42<48:48:38,  7.13s/it]
 12%|█▏        | 3445/28080 [6:48:49<48:48:33,  7.13s/it]
                                                         
{'loss': 0.6458, 'learning_rate': 0.0004888251039611152, 'epoch': 1.47}

 12%|█▏        | 3445/28080 [6:48:49<48:48:33,  7.13s/it]
 12%|█▏        | 3446/28080 [6:48:56<48:55:15,  7.15s/it]
                                                         
{'loss': 0.6565, 'learning_rate': 0.0004888165774763005, 'epoch': 1.47}

 12%|█▏        | 3446/28080 [6:48:56<48:55:15,  7.15s/it]
 12%|█▏        | 3447/28080 [6:49:03<48:48:05,  7.13s/it]
                                                         
{'loss': 0.6718, 'learning_rate': 0.0004888080478142775, 'epoch': 1.47}

 12%|█▏        | 3447/28080 [6:49:03<48:48:05,  7.13s/it]
 12%|█▏        | 3448/28080 [6:49:10<48:37:48,  7.11s/it]
                                                         
{'loss': 0.6333, 'learning_rate': 0.0004887995149751599, 'epoch': 1.47}

 12%|█▏        | 3448/28080 [6:49:10<48:37:48,  7.11s/it]
 12%|█▏        | 3449/28080 [6:49:18<48:40:56,  7.12s/it]
                                                         
{'loss': 0.664, 'learning_rate': 0.000488790978959061, 'epoch': 1.47}

 12%|█▏        | 3449/28080 [6:49:18<48:40:56,  7.12s/it]
 12%|█▏        | 3450/28080 [6:49:25<48:56:14,  7.15s/it]
                                                         
{'loss': 0.6392, 'learning_rate': 0.0004887824397660945, 'epoch': 1.47}

 12%|█▏        | 3450/28080 [6:49:25<48:56:14,  7.15s/it]
 12%|█▏        | 3451/28080 [6:49:32<49:05:19,  7.18s/it]
                                                         
{'loss': 0.6604, 'learning_rate': 0.0004887738973963739, 'epoch': 1.47}

 12%|█▏        | 3451/28080 [6:49:32<49:05:19,  7.18s/it]
 12%|█▏        | 3452/28080 [6:49:39<48:53:50,  7.15s/it]
                                                         
{'loss': 0.6647, 'learning_rate': 0.000488765351850013, 'epoch': 1.47}

 12%|█▏        | 3452/28080 [6:49:39<48:53:50,  7.15s/it]
 12%|█▏        | 3453/28080 [6:49:46<48:42:45,  7.12s/it]
                                                         
{'loss': 0.6799, 'learning_rate': 0.0004887568031271255, 'epoch': 1.48}

 12%|█▏        | 3453/28080 [6:49:46<48:42:45,  7.12s/it]
 12%|█▏        | 3454/28080 [6:49:53<48:58:32,  7.16s/it]
                                                         
{'loss': 0.6653, 'learning_rate': 0.0004887482512278249, 'epoch': 1.48}

 12%|█▏        | 3454/28080 [6:49:53<48:58:32,  7.16s/it]
 12%|█▏        | 3455/28080 [6:50:01<49:08:02,  7.18s/it]
                                                         
{'loss': 0.6653, 'learning_rate': 0.0004887396961522251, 'epoch': 1.48}

 12%|█▏        | 3455/28080 [6:50:01<49:08:02,  7.18s/it]
 12%|█▏        | 3456/28080 [6:50:08<49:05:40,  7.18s/it]
                                                         
{'loss': 0.653, 'learning_rate': 0.0004887311379004402, 'epoch': 1.48}

 12%|█▏        | 3456/28080 [6:50:08<49:05:40,  7.18s/it]
 12%|█▏        | 3457/28080 [6:50:15<49:02:54,  7.17s/it]
                                                         
{'loss': 0.6839, 'learning_rate': 0.0004887225764725836, 'epoch': 1.48}

 12%|█▏        | 3457/28080 [6:50:15<49:02:54,  7.17s/it]
 12%|█▏        | 3458/28080 [6:50:22<49:07:06,  7.18s/it]
                                                         
{'loss': 0.6546, 'learning_rate': 0.0004887140118687693, 'epoch': 1.48}

 12%|█▏        | 3458/28080 [6:50:22<49:07:06,  7.18s/it]
 12%|█▏        | 3459/28080 [6:50:29<49:07:59,  7.18s/it]
                                                         
{'loss': 0.646, 'learning_rate': 0.0004887054440891115, 'epoch': 1.48}

 12%|█▏        | 3459/28080 [6:50:29<49:07:59,  7.18s/it]
 12%|█▏        | 3460/28080 [6:50:37<49:18:14,  7.21s/it]
                                                         
{'loss': 0.6579, 'learning_rate': 0.000488696873133724, 'epoch': 1.48}

 12%|█▏        | 3460/28080 [6:50:37<49:18:14,  7.21s/it]
 12%|█▏        | 3461/28080 [6:50:44<49:09:23,  7.19s/it]
                                                         
{'loss': 0.6584, 'learning_rate': 0.0004886882990027208, 'epoch': 1.48}

 12%|█▏        | 3461/28080 [6:50:44<49:09:23,  7.19s/it]
 12%|█▏        | 3462/28080 [6:50:51<48:57:51,  7.16s/it]
                                                         
{'loss': 0.6486, 'learning_rate': 0.000488679721696216, 'epoch': 1.48}

 12%|█▏        | 3462/28080 [6:50:51<48:57:51,  7.16s/it]
 12%|█▏        | 3463/28080 [6:50:58<48:45:33,  7.13s/it]
                                                         
{'loss': 0.6683, 'learning_rate': 0.0004886711412143239, 'epoch': 1.48}

 12%|█▏        | 3463/28080 [6:50:58<48:45:33,  7.13s/it]
 12%|█▏        | 3464/28080 [6:51:05<48:39:39,  7.12s/it]
                                                         
{'loss': 0.6397, 'learning_rate': 0.0004886625575571583, 'epoch': 1.48}

 12%|█▏        | 3464/28080 [6:51:05<48:39:39,  7.12s/it]
 12%|█▏        | 3465/28080 [6:51:12<48:50:12,  7.14s/it]
                                                         
{'loss': 0.6546, 'learning_rate': 0.0004886539707248337, 'epoch': 1.48}

 12%|█▏        | 3465/28080 [6:51:12<48:50:12,  7.14s/it]
 12%|█▏        | 3466/28080 [6:51:19<48:45:52,  7.13s/it]
                                                         
{'loss': 0.6495, 'learning_rate': 0.0004886453807174642, 'epoch': 1.48}

 12%|█▏        | 3466/28080 [6:51:19<48:45:52,  7.13s/it]
 12%|█▏        | 3467/28080 [6:51:27<48:52:53,  7.15s/it]
                                                         
{'loss': 0.6593, 'learning_rate': 0.000488636787535164, 'epoch': 1.48}

 12%|█▏        | 3467/28080 [6:51:27<48:52:53,  7.15s/it]
 12%|█▏        | 3468/28080 [6:51:34<49:01:22,  7.17s/it]
                                                         
{'loss': 0.631, 'learning_rate': 0.0004886281911780476, 'epoch': 1.48}

 12%|█▏        | 3468/28080 [6:51:34<49:01:22,  7.17s/it]
 12%|█▏        | 3469/28080 [6:51:41<49:06:23,  7.18s/it]
                                                         
{'loss': 0.6698, 'learning_rate': 0.0004886195916462293, 'epoch': 1.48}

 12%|█▏        | 3469/28080 [6:51:41<49:06:23,  7.18s/it]
 12%|█▏        | 3470/28080 [6:51:48<48:56:55,  7.16s/it]
                                                         
{'loss': 0.6698, 'learning_rate': 0.0004886109889398236, 'epoch': 1.48}

 12%|█▏        | 3470/28080 [6:51:48<48:56:55,  7.16s/it]
 12%|█▏        | 3471/28080 [6:51:55<48:53:33,  7.15s/it]
                                                         
{'loss': 0.6642, 'learning_rate': 0.0004886023830589448, 'epoch': 1.48}

 12%|█▏        | 3471/28080 [6:51:55<48:53:33,  7.15s/it]
 12%|█▏        | 3472/28080 [6:52:02<48:48:29,  7.14s/it]
                                                         
{'loss': 0.6771, 'learning_rate': 0.0004885937740037074, 'epoch': 1.48}

 12%|█▏        | 3472/28080 [6:52:02<48:48:29,  7.14s/it]
 12%|█▏        | 3473/28080 [6:52:09<48:44:06,  7.13s/it]
                                                         
{'loss': 0.7094, 'learning_rate': 0.000488585161774226, 'epoch': 1.48}

 12%|█▏        | 3473/28080 [6:52:09<48:44:06,  7.13s/it]
 12%|█▏        | 3474/28080 [6:52:17<48:56:31,  7.16s/it]
                                                         
{'loss': 0.6578, 'learning_rate': 0.0004885765463706152, 'epoch': 1.48}

 12%|█▏        | 3474/28080 [6:52:17<48:56:31,  7.16s/it]
 12%|█▏        | 3475/28080 [6:52:24<49:03:20,  7.18s/it]
                                                         
{'loss': 0.6608, 'learning_rate': 0.0004885679277929895, 'epoch': 1.48}

 12%|█▏        | 3475/28080 [6:52:24<49:03:20,  7.18s/it]
 12%|█▏        | 3476/28080 [6:52:31<48:57:20,  7.16s/it]
                                                         
{'loss': 0.6524, 'learning_rate': 0.0004885593060414637, 'epoch': 1.48}

 12%|█▏        | 3476/28080 [6:52:31<48:57:20,  7.16s/it]
 12%|█▏        | 3477/28080 [6:52:38<48:57:43,  7.16s/it]
                                                         
{'loss': 0.654, 'learning_rate': 0.0004885506811161524, 'epoch': 1.49}

 12%|█▏        | 3477/28080 [6:52:38<48:57:43,  7.16s/it]
 12%|█▏        | 3478/28080 [6:52:45<48:59:26,  7.17s/it]
                                                         
{'loss': 0.656, 'learning_rate': 0.0004885420530171703, 'epoch': 1.49}

 12%|█▏        | 3478/28080 [6:52:45<48:59:26,  7.17s/it]
 12%|█▏        | 3479/28080 [6:52:52<48:59:18,  7.17s/it]
                                                         
{'loss': 0.6344, 'learning_rate': 0.0004885334217446325, 'epoch': 1.49}

 12%|█▏        | 3479/28080 [6:52:53<48:59:18,  7.17s/it]
 12%|█▏        | 3480/28080 [6:53:00<48:56:31,  7.16s/it]
                                                         
{'loss': 0.6502, 'learning_rate': 0.0004885247872986534, 'epoch': 1.49}

 12%|█▏        | 3480/28080 [6:53:00<48:56:31,  7.16s/it]
 12%|█▏        | 3481/28080 [6:53:07<48:53:55,  7.16s/it]
                                                         
{'loss': 0.6493, 'learning_rate': 0.0004885161496793482, 'epoch': 1.49}

 12%|█▏        | 3481/28080 [6:53:07<48:53:55,  7.16s/it]
 12%|█▏        | 3482/28080 [6:53:14<48:44:32,  7.13s/it]
                                                         
{'loss': 0.6887, 'learning_rate': 0.0004885075088868317, 'epoch': 1.49}

 12%|█▏        | 3482/28080 [6:53:14<48:44:32,  7.13s/it]
 12%|█▏        | 3483/28080 [6:53:21<48:35:33,  7.11s/it]
                                                         
{'loss': 0.6521, 'learning_rate': 0.0004884988649212187, 'epoch': 1.49}

 12%|█▏        | 3483/28080 [6:53:21<48:35:33,  7.11s/it]
 12%|█▏        | 3484/28080 [6:53:28<48:42:50,  7.13s/it]
                                                         
{'loss': 0.6698, 'learning_rate': 0.0004884902177826245, 'epoch': 1.49}

 12%|█▏        | 3484/28080 [6:53:28<48:42:50,  7.13s/it]
 12%|█▏        | 3485/28080 [6:53:35<48:51:33,  7.15s/it]
                                                         
{'loss': 0.6369, 'learning_rate': 0.0004884815674711639, 'epoch': 1.49}

 12%|█▏        | 3485/28080 [6:53:35<48:51:33,  7.15s/it]
 12%|█▏        | 3486/28080 [6:53:43<49:05:36,  7.19s/it]
                                                         
{'loss': 0.653, 'learning_rate': 0.0004884729139869522, 'epoch': 1.49}

 12%|█▏        | 3486/28080 [6:53:43<49:05:36,  7.19s/it]
 12%|█▏        | 3487/28080 [6:53:50<49:03:43,  7.18s/it]
                                                         
{'loss': 0.6773, 'learning_rate': 0.0004884642573301043, 'epoch': 1.49}

 12%|█▏        | 3487/28080 [6:53:50<49:03:43,  7.18s/it]
 12%|█▏        | 3488/28080 [6:53:57<48:52:40,  7.16s/it]
                                                         
{'loss': 0.663, 'learning_rate': 0.0004884555975007355, 'epoch': 1.49}

 12%|█▏        | 3488/28080 [6:53:57<48:52:40,  7.16s/it]
 12%|█▏        | 3489/28080 [6:54:04<49:06:52,  7.19s/it]
                                                         
{'loss': 0.6904, 'learning_rate': 0.0004884469344989609, 'epoch': 1.49}

 12%|█▏        | 3489/28080 [6:54:04<49:06:52,  7.19s/it]
 12%|█▏        | 3490/28080 [6:54:11<49:00:51,  7.18s/it]
                                                         
{'loss': 0.6733, 'learning_rate': 0.0004884382683248958, 'epoch': 1.49}

 12%|█▏        | 3490/28080 [6:54:11<49:00:51,  7.18s/it]
 12%|█▏        | 3491/28080 [6:54:18<48:52:17,  7.16s/it]
                                                         
{'loss': 0.666, 'learning_rate': 0.0004884295989786557, 'epoch': 1.49}

 12%|█▏        | 3491/28080 [6:54:18<48:52:17,  7.16s/it]
 12%|█▏        | 3492/28080 [6:54:25<48:47:42,  7.14s/it]
                                                         
{'loss': 0.6702, 'learning_rate': 0.0004884209264603556, 'epoch': 1.49}

 12%|█▏        | 3492/28080 [6:54:25<48:47:42,  7.14s/it]
 12%|█▏        | 3493/28080 [6:54:33<48:55:25,  7.16s/it]
                                                         
{'loss': 0.6457, 'learning_rate': 0.0004884122507701111, 'epoch': 1.49}

 12%|█▏        | 3493/28080 [6:54:33<48:55:25,  7.16s/it]
 12%|█▏        | 3494/28080 [6:54:40<49:06:01,  7.19s/it]
                                                         
{'loss': 0.6719, 'learning_rate': 0.0004884035719080376, 'epoch': 1.49}

 12%|█▏        | 3494/28080 [6:54:40<49:06:01,  7.19s/it]
 12%|█▏        | 3495/28080 [6:54:47<48:51:26,  7.15s/it]
                                                         
{'loss': 0.6527, 'learning_rate': 0.0004883948898742504, 'epoch': 1.49}

 12%|█▏        | 3495/28080 [6:54:47<48:51:26,  7.15s/it]
 12%|█▏        | 3496/28080 [6:54:54<48:48:34,  7.15s/it]
                                                         
{'loss': 0.683, 'learning_rate': 0.0004883862046688653, 'epoch': 1.49}

 12%|█▏        | 3496/28080 [6:54:54<48:48:34,  7.15s/it]
 12%|█▏        | 3497/28080 [6:55:01<48:52:57,  7.16s/it]
                                                         
{'loss': 0.6459, 'learning_rate': 0.0004883775162919976, 'epoch': 1.49}

 12%|█▏        | 3497/28080 [6:55:01<48:52:57,  7.16s/it]
 12%|█▏        | 3498/28080 [6:55:08<48:48:56,  7.15s/it]
                                                         
{'loss': 0.6608, 'learning_rate': 0.0004883688247437629, 'epoch': 1.49}

 12%|█▏        | 3498/28080 [6:55:08<48:48:56,  7.15s/it]
 12%|█▏        | 3499/28080 [6:55:16<48:56:06,  7.17s/it]
                                                         
{'loss': 0.651, 'learning_rate': 0.0004883601300242769, 'epoch': 1.49}

 12%|█▏        | 3499/28080 [6:55:16<48:56:06,  7.17s/it]
 12%|█▏        | 3500/28080 [6:55:23<49:00:22,  7.18s/it]
                                                         
{'loss': 0.6537, 'learning_rate': 0.0004883514321336554, 'epoch': 1.5}

 12%|█▏        | 3500/28080 [6:55:23<49:00:22,  7.18s/it]
 12%|█▏        | 3501/28080 [6:55:30<48:53:31,  7.16s/it]
                                                         
{'loss': 0.6511, 'learning_rate': 0.0004883427310720139, 'epoch': 1.5}

 12%|█▏        | 3501/28080 [6:55:30<48:53:31,  7.16s/it]
 12%|█▏        | 3502/28080 [6:55:37<48:55:26,  7.17s/it]
                                                         
{'loss': 0.6284, 'learning_rate': 0.0004883340268394682, 'epoch': 1.5}

 12%|█▏        | 3502/28080 [6:55:37<48:55:26,  7.17s/it]
 12%|█▏        | 3503/28080 [6:55:44<49:05:36,  7.19s/it]
                                                         
{'loss': 0.6696, 'learning_rate': 0.0004883253194361342, 'epoch': 1.5}

 12%|█▏        | 3503/28080 [6:55:44<49:05:36,  7.19s/it]
 12%|█▏        | 3504/28080 [6:55:52<49:20:26,  7.23s/it]
                                                         
{'loss': 0.6491, 'learning_rate': 0.0004883166088621277, 'epoch': 1.5}

 12%|█▏        | 3504/28080 [6:55:52<49:20:26,  7.23s/it]
 12%|█▏        | 3505/28080 [6:55:59<49:08:32,  7.20s/it]
                                                         
{'loss': 0.6742, 'learning_rate': 0.0004883078951175646, 'epoch': 1.5}

 12%|█▏        | 3505/28080 [6:55:59<49:08:32,  7.20s/it]
 12%|█▏        | 3506/28080 [6:56:06<48:53:35,  7.16s/it]
                                                         
{'loss': 0.6717, 'learning_rate': 0.0004882991782025608, 'epoch': 1.5}

 12%|█▏        | 3506/28080 [6:56:06<48:53:35,  7.16s/it]
 12%|█▏        | 3507/28080 [6:56:13<48:50:41,  7.16s/it]
                                                         
{'loss': 0.6634, 'learning_rate': 0.0004882904581172322, 'epoch': 1.5}

 12%|█▏        | 3507/28080 [6:56:13<48:50:41,  7.16s/it]
 12%|█▏        | 3508/28080 [6:56:20<49:23:00,  7.24s/it]
                                                         
{'loss': 0.6504, 'learning_rate': 0.0004882817348616951, 'epoch': 1.5}

 12%|█▏        | 3508/28080 [6:56:20<49:23:00,  7.24s/it]
 12%|█▏        | 3509/28080 [6:56:28<49:19:46,  7.23s/it]
                                                         
{'loss': 0.6552, 'learning_rate': 0.00048827300843606506, 'epoch': 1.5}

 12%|█▏        | 3509/28080 [6:56:28<49:19:46,  7.23s/it]
 12%|█▎        | 3510/28080 [6:56:35<48:59:37,  7.18s/it]
                                                         
{'loss': 0.6723, 'learning_rate': 0.0004882642788404586, 'epoch': 1.5}

 12%|█▎        | 3510/28080 [6:56:35<48:59:37,  7.18s/it]
 13%|█▎        | 3511/28080 [6:56:42<49:07:01,  7.20s/it]
                                                         
{'loss': 0.6633, 'learning_rate': 0.0004882555460749917, 'epoch': 1.5}

 13%|█▎        | 3511/28080 [6:56:42<49:07:01,  7.20s/it]
 13%|█▎        | 3512/28080 [6:56:49<49:00:04,  7.18s/it]
                                                         
{'loss': 0.6706, 'learning_rate': 0.0004882468101397806, 'epoch': 1.5}

 13%|█▎        | 3512/28080 [6:56:49<49:00:04,  7.18s/it]
 13%|█▎        | 3513/28080 [6:56:56<49:02:07,  7.19s/it]
                                                         
{'loss': 0.6661, 'learning_rate': 0.0004882380710349413, 'epoch': 1.5}

 13%|█▎        | 3513/28080 [6:56:56<49:02:07,  7.19s/it]
 13%|█▎        | 3514/28080 [6:57:04<49:00:38,  7.18s/it]
                                                         
{'loss': 0.6525, 'learning_rate': 0.0004882293287605904, 'epoch': 1.5}

 13%|█▎        | 3514/28080 [6:57:04<49:00:38,  7.18s/it]
 13%|█▎        | 3515/28080 [6:57:11<48:54:52,  7.17s/it]
                                                         
{'loss': 0.6379, 'learning_rate': 0.000488220583316844, 'epoch': 1.5}

 13%|█▎        | 3515/28080 [6:57:11<48:54:52,  7.17s/it]
 13%|█▎        | 3516/28080 [6:57:18<49:00:02,  7.18s/it]
                                                         
{'loss': 0.6456, 'learning_rate': 0.0004882118347038185, 'epoch': 1.5}

 13%|█▎        | 3516/28080 [6:57:18<49:00:02,  7.18s/it]
 13%|█▎        | 3517/28080 [6:57:25<48:48:53,  7.15s/it]
                                                         
{'loss': 0.6942, 'learning_rate': 0.00048820308292163027, 'epoch': 1.5}

 13%|█▎        | 3517/28080 [6:57:25<48:48:53,  7.15s/it]
 13%|█▎        | 3518/28080 [6:57:32<48:53:57,  7.17s/it]
                                                         
{'loss': 0.6594, 'learning_rate': 0.0004881943279703958, 'epoch': 1.5}

 13%|█▎        | 3518/28080 [6:57:32<48:53:57,  7.17s/it]
 13%|█▎        | 3519/28080 [6:57:39<48:52:42,  7.16s/it]
                                                         
{'loss': 0.642, 'learning_rate': 0.00048818556985023154, 'epoch': 1.5}

 13%|█▎        | 3519/28080 [6:57:39<48:52:42,  7.16s/it]
 13%|█▎        | 3520/28080 [6:57:46<48:52:05,  7.16s/it]
                                                         
{'loss': 0.6643, 'learning_rate': 0.00048817680856125397, 'epoch': 1.5}

 13%|█▎        | 3520/28080 [6:57:46<48:52:05,  7.16s/it]
 13%|█▎        | 3521/28080 [6:57:54<48:45:40,  7.15s/it]
                                                         
{'loss': 0.6758, 'learning_rate': 0.00048816804410357965, 'epoch': 1.5}

 13%|█▎        | 3521/28080 [6:57:54<48:45:40,  7.15s/it]
 13%|█▎        | 3522/28080 [6:58:01<48:47:59,  7.15s/it]
                                                         
{'loss': 0.6573, 'learning_rate': 0.0004881592764773253, 'epoch': 1.5}

 13%|█▎        | 3522/28080 [6:58:01<48:47:59,  7.15s/it]
 13%|█▎        | 3523/28080 [6:58:08<48:50:48,  7.16s/it]
                                                         
{'loss': 0.6498, 'learning_rate': 0.0004881505056826073, 'epoch': 1.5}

 13%|█▎        | 3523/28080 [6:58:08<48:50:48,  7.16s/it]
 13%|█▎        | 3524/28080 [6:58:15<48:59:54,  7.18s/it]
                                                         
{'loss': 0.6821, 'learning_rate': 0.0004881417317195427, 'epoch': 1.51}

 13%|█▎        | 3524/28080 [6:58:15<48:59:54,  7.18s/it]
 13%|█▎        | 3525/28080 [6:58:22<48:48:21,  7.16s/it]
                                                         
{'loss': 0.6705, 'learning_rate': 0.0004881329545882479, 'epoch': 1.51}

 13%|█▎        | 3525/28080 [6:58:22<48:48:21,  7.16s/it]
 13%|█▎        | 3526/28080 [6:58:29<48:38:52,  7.13s/it]
                                                         
{'loss': 0.6668, 'learning_rate': 0.00048812417428883986, 'epoch': 1.51}

 13%|█▎        | 3526/28080 [6:58:29<48:38:52,  7.13s/it]
 13%|█▎        | 3527/28080 [6:58:37<48:52:58,  7.17s/it]
                                                         
{'loss': 0.6676, 'learning_rate': 0.00048811539082143534, 'epoch': 1.51}

 13%|█▎        | 3527/28080 [6:58:37<48:52:58,  7.17s/it]
 13%|█▎        | 3528/28080 [6:58:44<48:49:31,  7.16s/it]
                                                         
{'loss': 0.6563, 'learning_rate': 0.0004881066041861512, 'epoch': 1.51}

 13%|█▎        | 3528/28080 [6:58:44<48:49:31,  7.16s/it]
 13%|█▎        | 3529/28080 [6:58:51<49:01:40,  7.19s/it]
                                                         
{'loss': 0.6508, 'learning_rate': 0.0004880978143831043, 'epoch': 1.51}

 13%|█▎        | 3529/28080 [6:58:51<49:01:40,  7.19s/it]
 13%|█▎        | 3530/28080 [6:58:58<48:55:54,  7.18s/it]
                                                         
{'loss': 0.6631, 'learning_rate': 0.00048808902141241165, 'epoch': 1.51}

 13%|█▎        | 3530/28080 [6:58:58<48:55:54,  7.18s/it]
 13%|█▎        | 3531/28080 [6:59:05<48:44:01,  7.15s/it]
                                                         
{'loss': 0.6648, 'learning_rate': 0.00048808022527419015, 'epoch': 1.51}

 13%|█▎        | 3531/28080 [6:59:05<48:44:01,  7.15s/it]
 13%|█▎        | 3532/28080 [6:59:12<48:49:27,  7.16s/it]
                                                         
{'loss': 0.6609, 'learning_rate': 0.0004880714259685569, 'epoch': 1.51}

 13%|█▎        | 3532/28080 [6:59:12<48:49:27,  7.16s/it]
 13%|█▎        | 3533/28080 [6:59:19<48:40:26,  7.14s/it]
                                                         
{'loss': 0.6621, 'learning_rate': 0.000488062623495629, 'epoch': 1.51}

 13%|█▎        | 3533/28080 [6:59:19<48:40:26,  7.14s/it]
 13%|█▎        | 3534/28080 [6:59:27<48:44:24,  7.15s/it]
                                                         
{'loss': 0.658, 'learning_rate': 0.0004880538178555234, 'epoch': 1.51}

 13%|█▎        | 3534/28080 [6:59:27<48:44:24,  7.15s/it]
 13%|█▎        | 3535/28080 [6:59:34<48:36:10,  7.13s/it]
                                                         
{'loss': 0.6443, 'learning_rate': 0.0004880450090483574, 'epoch': 1.51}

 13%|█▎        | 3535/28080 [6:59:34<48:36:10,  7.13s/it]
 13%|█▎        | 3536/28080 [6:59:41<48:40:24,  7.14s/it]
                                                         
{'loss': 0.6471, 'learning_rate': 0.000488036197074248, 'epoch': 1.51}

 13%|█▎        | 3536/28080 [6:59:41<48:40:24,  7.14s/it]
 13%|█▎        | 3537/28080 [6:59:48<48:40:24,  7.14s/it]
                                                         
{'loss': 0.6568, 'learning_rate': 0.00048802738193331265, 'epoch': 1.51}

 13%|█▎        | 3537/28080 [6:59:48<48:40:24,  7.14s/it]
 13%|█▎        | 3538/28080 [6:59:55<48:40:27,  7.14s/it]
                                                         
{'loss': 0.6618, 'learning_rate': 0.00048801856362566855, 'epoch': 1.51}

 13%|█▎        | 3538/28080 [6:59:55<48:40:27,  7.14s/it]
 13%|█▎        | 3539/28080 [7:00:02<48:50:18,  7.16s/it]
                                                         
{'loss': 0.6613, 'learning_rate': 0.000488009742151433, 'epoch': 1.51}

 13%|█▎        | 3539/28080 [7:00:02<48:50:18,  7.16s/it]
 13%|█▎        | 3540/28080 [7:00:10<48:49:44,  7.16s/it]
                                                         
{'loss': 0.65, 'learning_rate': 0.0004880009175107234, 'epoch': 1.51}

 13%|█▎        | 3540/28080 [7:00:10<48:49:44,  7.16s/it]
 13%|█▎        | 3541/28080 [7:00:17<48:48:51,  7.16s/it]
                                                         
{'loss': 0.6541, 'learning_rate': 0.0004879920897036571, 'epoch': 1.51}

 13%|█▎        | 3541/28080 [7:00:17<48:48:51,  7.16s/it]
 13%|█▎        | 3542/28080 [7:00:24<48:44:27,  7.15s/it]
                                                         
{'loss': 0.6785, 'learning_rate': 0.0004879832587303516, 'epoch': 1.51}

 13%|█▎        | 3542/28080 [7:00:24<48:44:27,  7.15s/it]
 13%|█▎        | 3543/28080 [7:00:31<48:53:39,  7.17s/it]
                                                         
{'loss': 0.6515, 'learning_rate': 0.00048797442459092434, 'epoch': 1.51}

 13%|█▎        | 3543/28080 [7:00:31<48:53:39,  7.17s/it]
 13%|█▎        | 3544/28080 [7:00:38<48:58:48,  7.19s/it]
                                                         
{'loss': 0.6638, 'learning_rate': 0.00048796558728549284, 'epoch': 1.51}

 13%|█▎        | 3544/28080 [7:00:38<48:58:48,  7.19s/it]
 13%|█▎        | 3545/28080 [7:00:45<48:56:28,  7.18s/it]
                                                         
{'loss': 0.6571, 'learning_rate': 0.0004879567468141747, 'epoch': 1.51}

 13%|█▎        | 3545/28080 [7:00:45<48:56:28,  7.18s/it]
 13%|█▎        | 3546/28080 [7:00:53<48:49:32,  7.16s/it]
                                                         
{'loss': 0.6758, 'learning_rate': 0.00048794790317708756, 'epoch': 1.51}

 13%|█▎        | 3546/28080 [7:00:53<48:49:32,  7.16s/it]
 13%|█▎        | 3547/28080 [7:01:00<48:55:30,  7.18s/it]
                                                         
{'loss': 0.6546, 'learning_rate': 0.000487939056374349, 'epoch': 1.52}

 13%|█▎        | 3547/28080 [7:01:00<48:55:30,  7.18s/it]
 13%|█▎        | 3548/28080 [7:01:07<48:55:59,  7.18s/it]
                                                         
{'loss': 0.6576, 'learning_rate': 0.00048793020640607677, 'epoch': 1.52}

 13%|█▎        | 3548/28080 [7:01:07<48:55:59,  7.18s/it]
 13%|█▎        | 3549/28080 [7:01:14<48:55:21,  7.18s/it]
                                                         
{'loss': 0.6455, 'learning_rate': 0.0004879213532723886, 'epoch': 1.52}

 13%|█▎        | 3549/28080 [7:01:14<48:55:21,  7.18s/it]
 13%|█▎        | 3550/28080 [7:01:21<48:41:25,  7.15s/it]
                                                         
{'loss': 0.647, 'learning_rate': 0.00048791249697340233, 'epoch': 1.52}

 13%|█▎        | 3550/28080 [7:01:21<48:41:25,  7.15s/it]
 13%|█▎        | 3551/28080 [7:01:28<48:39:23,  7.14s/it]
                                                         
{'loss': 0.665, 'learning_rate': 0.0004879036375092357, 'epoch': 1.52}

 13%|█▎        | 3551/28080 [7:01:28<48:39:23,  7.14s/it]
 13%|█▎        | 3552/28080 [7:01:36<48:39:29,  7.14s/it]
                                                         
{'loss': 0.6484, 'learning_rate': 0.0004878947748800067, 'epoch': 1.52}

 13%|█▎        | 3552/28080 [7:01:36<48:39:29,  7.14s/it]
 13%|█▎        | 3553/28080 [7:01:43<48:44:26,  7.15s/it]
                                                         
{'loss': 0.6556, 'learning_rate': 0.00048788590908583295, 'epoch': 1.52}

 13%|█▎        | 3553/28080 [7:01:43<48:44:26,  7.15s/it]
 13%|█▎        | 3554/28080 [7:01:50<48:47:27,  7.16s/it]
                                                         
{'loss': 0.6475, 'learning_rate': 0.0004878770401268327, 'epoch': 1.52}

 13%|█▎        | 3554/28080 [7:01:50<48:47:27,  7.16s/it]
 13%|█▎        | 3555/28080 [7:01:57<48:46:27,  7.16s/it]
                                                         
{'loss': 0.6573, 'learning_rate': 0.00048786816800312386, 'epoch': 1.52}

 13%|█▎        | 3555/28080 [7:01:57<48:46:27,  7.16s/it]
 13%|█▎        | 3556/28080 [7:02:04<48:29:03,  7.12s/it]
                                                         
{'loss': 0.6599, 'learning_rate': 0.0004878592927148244, 'epoch': 1.52}

 13%|█▎        | 3556/28080 [7:02:04<48:29:03,  7.12s/it]
 13%|█▎        | 3557/28080 [7:02:11<48:41:18,  7.15s/it]
                                                         
{'loss': 0.661, 'learning_rate': 0.0004878504142620524, 'epoch': 1.52}

 13%|█▎        | 3557/28080 [7:02:11<48:41:18,  7.15s/it]
 13%|█▎        | 3558/28080 [7:02:18<48:39:37,  7.14s/it]
                                                         
{'loss': 0.6419, 'learning_rate': 0.00048784153264492603, 'epoch': 1.52}

 13%|█▎        | 3558/28080 [7:02:18<48:39:37,  7.14s/it]
 13%|█▎        | 3559/28080 [7:02:25<48:26:54,  7.11s/it]
                                                         
{'loss': 0.6757, 'learning_rate': 0.0004878326478635635, 'epoch': 1.52}

 13%|█▎        | 3559/28080 [7:02:25<48:26:54,  7.11s/it]
 13%|█▎        | 3560/28080 [7:02:33<48:31:30,  7.12s/it]
                                                         
{'loss': 0.6619, 'learning_rate': 0.0004878237599180829, 'epoch': 1.52}

 13%|█▎        | 3560/28080 [7:02:33<48:31:30,  7.12s/it]
 13%|█▎        | 3561/28080 [7:02:40<48:21:07,  7.10s/it]
                                                         
{'loss': 0.6716, 'learning_rate': 0.00048781486880860247, 'epoch': 1.52}

 13%|█▎        | 3561/28080 [7:02:40<48:21:07,  7.10s/it]
 13%|█▎        | 3562/28080 [7:02:47<48:31:37,  7.13s/it]
                                                         
{'loss': 0.6525, 'learning_rate': 0.00048780597453524066, 'epoch': 1.52}

 13%|█▎        | 3562/28080 [7:02:47<48:31:37,  7.13s/it]
 13%|█▎        | 3563/28080 [7:02:54<48:28:34,  7.12s/it]
                                                         
{'loss': 0.6601, 'learning_rate': 0.0004877970770981156, 'epoch': 1.52}

 13%|█▎        | 3563/28080 [7:02:54<48:28:34,  7.12s/it]
 13%|█▎        | 3564/28080 [7:03:01<48:34:31,  7.13s/it]
                                                         
{'loss': 0.6599, 'learning_rate': 0.0004877881764973459, 'epoch': 1.52}

 13%|█▎        | 3564/28080 [7:03:01<48:34:31,  7.13s/it]
 13%|█▎        | 3565/28080 [7:03:08<48:34:22,  7.13s/it]
                                                         
{'loss': 0.6483, 'learning_rate': 0.00048777927273304967, 'epoch': 1.52}

 13%|█▎        | 3565/28080 [7:03:08<48:34:22,  7.13s/it]
 13%|█▎        | 3566/28080 [7:03:15<48:19:46,  7.10s/it]
                                                         
{'loss': 0.6474, 'learning_rate': 0.0004877703658053455, 'epoch': 1.52}

 13%|█▎        | 3566/28080 [7:03:15<48:19:46,  7.10s/it]
 13%|█▎        | 3567/28080 [7:03:22<48:23:58,  7.11s/it]
                                                         
{'loss': 0.6677, 'learning_rate': 0.000487761455714352, 'epoch': 1.52}

 13%|█▎        | 3567/28080 [7:03:22<48:23:58,  7.11s/it]
 13%|█▎        | 3568/28080 [7:03:29<48:14:50,  7.09s/it]
                                                         
{'loss': 0.6817, 'learning_rate': 0.00048775254246018765, 'epoch': 1.52}

 13%|█▎        | 3568/28080 [7:03:29<48:14:50,  7.09s/it]
 13%|█▎        | 3569/28080 [7:03:36<48:10:59,  7.08s/it]
                                                         
{'loss': 0.6699, 'learning_rate': 0.00048774362604297084, 'epoch': 1.52}

 13%|█▎        | 3569/28080 [7:03:36<48:10:59,  7.08s/it]
 13%|█▎        | 3570/28080 [7:03:44<48:14:58,  7.09s/it]
                                                         
{'loss': 0.6749, 'learning_rate': 0.00048773470646282046, 'epoch': 1.53}

 13%|█▎        | 3570/28080 [7:03:44<48:14:58,  7.09s/it]
 13%|█▎        | 3571/28080 [7:03:51<48:23:58,  7.11s/it]
                                                         
{'loss': 0.6698, 'learning_rate': 0.0004877257837198551, 'epoch': 1.53}

 13%|█▎        | 3571/28080 [7:03:51<48:23:58,  7.11s/it]
 13%|█▎        | 3572/28080 [7:03:58<48:31:54,  7.13s/it]
                                                         
{'loss': 0.6723, 'learning_rate': 0.0004877168578141934, 'epoch': 1.53}

 13%|█▎        | 3572/28080 [7:03:58<48:31:54,  7.13s/it]
 13%|█▎        | 3573/28080 [7:04:05<48:40:10,  7.15s/it]
                                                         
{'loss': 0.6529, 'learning_rate': 0.0004877079287459541, 'epoch': 1.53}

 13%|█▎        | 3573/28080 [7:04:05<48:40:10,  7.15s/it]
 13%|█▎        | 3574/28080 [7:04:12<48:39:26,  7.15s/it]
                                                         
{'loss': 0.6697, 'learning_rate': 0.00048769899651525606, 'epoch': 1.53}

 13%|█▎        | 3574/28080 [7:04:12<48:39:26,  7.15s/it]
 13%|█▎        | 3575/28080 [7:04:20<48:57:30,  7.19s/it]
                                                         
{'loss': 0.6486, 'learning_rate': 0.00048769006112221817, 'epoch': 1.53}

 13%|█▎        | 3575/28080 [7:04:20<48:57:30,  7.19s/it]
 13%|█▎        | 3576/28080 [7:04:27<48:59:23,  7.20s/it]
                                                         
{'loss': 0.6536, 'learning_rate': 0.00048768112256695914, 'epoch': 1.53}

 13%|█▎        | 3576/28080 [7:04:27<48:59:23,  7.20s/it]
 13%|█▎        | 3577/28080 [7:04:34<48:57:59,  7.19s/it]
                                                         
{'loss': 0.6682, 'learning_rate': 0.00048767218084959797, 'epoch': 1.53}

 13%|█▎        | 3577/28080 [7:04:34<48:57:59,  7.19s/it]
 13%|█▎        | 3578/28080 [7:04:41<48:54:29,  7.19s/it]
                                                         
{'loss': 0.6735, 'learning_rate': 0.00048766323597025364, 'epoch': 1.53}

 13%|█▎        | 3578/28080 [7:04:41<48:54:29,  7.19s/it]
 13%|█▎        | 3579/28080 [7:04:48<49:08:48,  7.22s/it]
                                                         
{'loss': 0.6487, 'learning_rate': 0.0004876542879290452, 'epoch': 1.53}

 13%|█▎        | 3579/28080 [7:04:48<49:08:48,  7.22s/it]
 13%|█▎        | 3580/28080 [7:04:56<49:00:09,  7.20s/it]
                                                         
{'loss': 0.6787, 'learning_rate': 0.00048764533672609155, 'epoch': 1.53}

 13%|█▎        | 3580/28080 [7:04:56<49:00:09,  7.20s/it]
 13%|█▎        | 3581/28080 [7:05:03<48:40:09,  7.15s/it]
                                                         
{'loss': 0.6719, 'learning_rate': 0.0004876363823615119, 'epoch': 1.53}

 13%|█▎        | 3581/28080 [7:05:03<48:40:09,  7.15s/it]
 13%|█▎        | 3582/28080 [7:05:10<48:37:47,  7.15s/it]
                                                         
{'loss': 0.6622, 'learning_rate': 0.0004876274248354254, 'epoch': 1.53}

 13%|█▎        | 3582/28080 [7:05:10<48:37:47,  7.15s/it]
 13%|█▎        | 3583/28080 [7:05:17<48:30:21,  7.13s/it]
                                                         
{'loss': 0.6677, 'learning_rate': 0.0004876184641479511, 'epoch': 1.53}

 13%|█▎        | 3583/28080 [7:05:17<48:30:21,  7.13s/it]
 13%|█▎        | 3584/28080 [7:05:24<48:35:00,  7.14s/it]
                                                         
{'loss': 0.6578, 'learning_rate': 0.00048760950029920827, 'epoch': 1.53}

 13%|█▎        | 3584/28080 [7:05:24<48:35:00,  7.14s/it]
 13%|█▎        | 3585/28080 [7:05:31<49:03:37,  7.21s/it]
                                                         
{'loss': 0.6809, 'learning_rate': 0.0004876005332893161, 'epoch': 1.53}

 13%|█▎        | 3585/28080 [7:05:31<49:03:37,  7.21s/it]
 13%|█▎        | 3586/28080 [7:05:39<48:58:03,  7.20s/it]
                                                         
{'loss': 0.6839, 'learning_rate': 0.00048759156311839404, 'epoch': 1.53}

 13%|█▎        | 3586/28080 [7:05:39<48:58:03,  7.20s/it]
 13%|█▎        | 3587/28080 [7:05:46<48:57:23,  7.20s/it]
                                                         
{'loss': 0.6467, 'learning_rate': 0.00048758258978656135, 'epoch': 1.53}

 13%|█▎        | 3587/28080 [7:05:46<48:57:23,  7.20s/it]
 13%|█▎        | 3588/28080 [7:05:53<48:57:07,  7.20s/it]
                                                         
{'loss': 0.6562, 'learning_rate': 0.0004875736132939373, 'epoch': 1.53}

 13%|█▎        | 3588/28080 [7:05:53<48:57:07,  7.20s/it]
 13%|█▎        | 3589/28080 [7:06:00<49:01:03,  7.21s/it]
                                                         
{'loss': 0.6504, 'learning_rate': 0.00048756463364064154, 'epoch': 1.53}

 13%|█▎        | 3589/28080 [7:06:00<49:01:03,  7.21s/it]
 13%|█▎        | 3590/28080 [7:06:07<48:47:30,  7.17s/it]
                                                         
{'loss': 0.6274, 'learning_rate': 0.00048755565082679337, 'epoch': 1.53}

 13%|█▎        | 3590/28080 [7:06:07<48:47:30,  7.17s/it]
 13%|█▎        | 3591/28080 [7:06:14<48:24:31,  7.12s/it]
                                                         
{'loss': 0.6562, 'learning_rate': 0.0004875466648525123, 'epoch': 1.53}

 13%|█▎        | 3591/28080 [7:06:14<48:24:31,  7.12s/it]
 13%|█▎        | 3592/28080 [7:06:21<48:18:55,  7.10s/it]
                                                         
{'loss': 0.685, 'learning_rate': 0.00048753767571791794, 'epoch': 1.53}

 13%|█▎        | 3592/28080 [7:06:21<48:18:55,  7.10s/it]
 13%|█▎        | 3593/28080 [7:06:28<48:23:41,  7.11s/it]
                                                         
{'loss': 0.6591, 'learning_rate': 0.00048752868342312987, 'epoch': 1.53}

 13%|█▎        | 3593/28080 [7:06:28<48:23:41,  7.11s/it]
 13%|█▎        | 3594/28080 [7:06:36<48:27:44,  7.13s/it]
                                                         
{'loss': 0.665, 'learning_rate': 0.00048751968796826775, 'epoch': 1.54}

 13%|█▎        | 3594/28080 [7:06:36<48:27:44,  7.13s/it]
 13%|█▎        | 3595/28080 [7:06:43<48:36:31,  7.15s/it]
                                                         
{'loss': 0.661, 'learning_rate': 0.00048751068935345114, 'epoch': 1.54}

 13%|█▎        | 3595/28080 [7:06:43<48:36:31,  7.15s/it]
 13%|█▎        | 3596/28080 [7:06:50<48:24:29,  7.12s/it]
                                                         
{'loss': 0.6554, 'learning_rate': 0.0004875016875787999, 'epoch': 1.54}

 13%|█▎        | 3596/28080 [7:06:50<48:24:29,  7.12s/it]
 13%|█▎        | 3597/28080 [7:06:57<48:32:22,  7.14s/it]
                                                         
{'loss': 0.6526, 'learning_rate': 0.00048749268264443367, 'epoch': 1.54}

 13%|█▎        | 3597/28080 [7:06:57<48:32:22,  7.14s/it]
 13%|█▎        | 3598/28080 [7:07:04<48:18:28,  7.10s/it]
                                                         
{'loss': 0.6622, 'learning_rate': 0.00048748367455047237, 'epoch': 1.54}

 13%|█▎        | 3598/28080 [7:07:04<48:18:28,  7.10s/it]
 13%|█▎        | 3599/28080 [7:07:11<48:29:53,  7.13s/it]
                                                         
{'loss': 0.6378, 'learning_rate': 0.00048747466329703573, 'epoch': 1.54}

 13%|█▎        | 3599/28080 [7:07:11<48:29:53,  7.13s/it]
 13%|█▎        | 3600/28080 [7:07:18<48:35:07,  7.14s/it]
                                                         
{'loss': 0.6471, 'learning_rate': 0.00048746564888424367, 'epoch': 1.54}

 13%|█▎        | 3600/28080 [7:07:18<48:35:07,  7.14s/it]
 13%|█▎        | 3601/28080 [7:07:26<48:31:45,  7.14s/it]
                                                         
{'loss': 0.6521, 'learning_rate': 0.0004874566313122162, 'epoch': 1.54}

 13%|█▎        | 3601/28080 [7:07:26<48:31:45,  7.14s/it]
 13%|█▎        | 3602/28080 [7:07:33<48:37:10,  7.15s/it]
                                                         
{'loss': 0.6555, 'learning_rate': 0.0004874476105810731, 'epoch': 1.54}

 13%|█▎        | 3602/28080 [7:07:33<48:37:10,  7.15s/it]
 13%|█▎        | 3603/28080 [7:07:40<48:49:38,  7.18s/it]
                                                         
{'loss': 0.6697, 'learning_rate': 0.0004874385866909346, 'epoch': 1.54}

 13%|█▎        | 3603/28080 [7:07:40<48:49:38,  7.18s/it]
 13%|█▎        | 3604/28080 [7:07:47<48:41:55,  7.16s/it]
                                                         
{'loss': 0.6503, 'learning_rate': 0.0004874295596419206, 'epoch': 1.54}

 13%|█▎        | 3604/28080 [7:07:47<48:41:55,  7.16s/it]
 13%|█▎        | 3605/28080 [7:07:54<48:36:21,  7.15s/it]
                                                         
{'loss': 0.6438, 'learning_rate': 0.00048742052943415127, 'epoch': 1.54}

 13%|█▎        | 3605/28080 [7:07:54<48:36:21,  7.15s/it]
 13%|█▎        | 3606/28080 [7:08:01<48:39:47,  7.16s/it]
                                                         
{'loss': 0.6516, 'learning_rate': 0.0004874114960677468, 'epoch': 1.54}

 13%|█▎        | 3606/28080 [7:08:01<48:39:47,  7.16s/it]
 13%|█▎        | 3607/28080 [7:08:08<48:33:17,  7.14s/it]
                                                         
{'loss': 0.6629, 'learning_rate': 0.00048740245954282725, 'epoch': 1.54}

 13%|█▎        | 3607/28080 [7:08:08<48:33:17,  7.14s/it]
 13%|█▎        | 3608/28080 [7:08:16<48:33:46,  7.14s/it]
                                                         
{'loss': 0.6659, 'learning_rate': 0.00048739341985951285, 'epoch': 1.54}

 13%|█▎        | 3608/28080 [7:08:16<48:33:46,  7.14s/it]
 13%|█▎        | 3609/28080 [7:08:23<48:47:47,  7.18s/it]
                                                         
{'loss': 0.6767, 'learning_rate': 0.00048738437701792393, 'epoch': 1.54}

 13%|█▎        | 3609/28080 [7:08:23<48:47:47,  7.18s/it]
 13%|█▎        | 3610/28080 [7:08:30<48:26:12,  7.13s/it]
                                                         
{'loss': 0.6746, 'learning_rate': 0.00048737533101818076, 'epoch': 1.54}

 13%|█▎        | 3610/28080 [7:08:30<48:26:12,  7.13s/it]
 13%|█▎        | 3611/28080 [7:08:37<48:15:05,  7.10s/it]
                                                         
{'loss': 0.6635, 'learning_rate': 0.00048736628186040376, 'epoch': 1.54}

 13%|█▎        | 3611/28080 [7:08:37<48:15:05,  7.10s/it]
 13%|█▎        | 3612/28080 [7:08:44<48:11:47,  7.09s/it]
                                                         
{'loss': 0.6572, 'learning_rate': 0.00048735722954471316, 'epoch': 1.54}

 13%|█▎        | 3612/28080 [7:08:44<48:11:47,  7.09s/it]
 13%|█▎        | 3613/28080 [7:08:51<48:26:43,  7.13s/it]
                                                         
{'loss': 0.6824, 'learning_rate': 0.00048734817407122957, 'epoch': 1.54}

 13%|█▎        | 3613/28080 [7:08:51<48:26:43,  7.13s/it]
 13%|█▎        | 3614/28080 [7:08:58<48:44:53,  7.17s/it]
                                                         
{'loss': 0.6493, 'learning_rate': 0.00048733911544007334, 'epoch': 1.54}

 13%|█▎        | 3614/28080 [7:08:58<48:44:53,  7.17s/it]
 13%|█▎        | 3615/28080 [7:09:06<48:46:22,  7.18s/it]
                                                         
{'loss': 0.6771, 'learning_rate': 0.00048733005365136505, 'epoch': 1.54}

 13%|█▎        | 3615/28080 [7:09:06<48:46:22,  7.18s/it]
 13%|█▎        | 3616/28080 [7:09:13<48:42:25,  7.17s/it]
                                                         
{'loss': 0.648, 'learning_rate': 0.00048732098870522524, 'epoch': 1.54}

 13%|█▎        | 3616/28080 [7:09:13<48:42:25,  7.17s/it]
 13%|█▎        | 3617/28080 [7:09:20<48:31:53,  7.14s/it]
                                                         
{'loss': 0.6459, 'learning_rate': 0.00048731192060177443, 'epoch': 1.55}

 13%|█▎        | 3617/28080 [7:09:20<48:31:53,  7.14s/it]
 13%|█▎        | 3618/28080 [7:09:27<48:32:22,  7.14s/it]
                                                         
{'loss': 0.6609, 'learning_rate': 0.00048730284934113345, 'epoch': 1.55}

 13%|█▎        | 3618/28080 [7:09:27<48:32:22,  7.14s/it]
 13%|█▎        | 3619/28080 [7:09:34<48:32:27,  7.14s/it]
                                                         
{'loss': 0.6569, 'learning_rate': 0.00048729377492342276, 'epoch': 1.55}

 13%|█▎        | 3619/28080 [7:09:34<48:32:27,  7.14s/it]
 13%|█▎        | 3620/28080 [7:09:41<48:43:30,  7.17s/it]
                                                         
{'loss': 0.6432, 'learning_rate': 0.00048728469734876325, 'epoch': 1.55}

 13%|█▎        | 3620/28080 [7:09:41<48:43:30,  7.17s/it]
 13%|█▎        | 3621/28080 [7:09:49<48:41:17,  7.17s/it]
                                                         
{'loss': 0.6736, 'learning_rate': 0.0004872756166172757, 'epoch': 1.55}

 13%|█▎        | 3621/28080 [7:09:49<48:41:17,  7.17s/it]
 13%|█▎        | 3622/28080 [7:09:56<48:52:37,  7.19s/it]
                                                         
{'loss': 0.6511, 'learning_rate': 0.0004872665327290807, 'epoch': 1.55}

 13%|█▎        | 3622/28080 [7:09:56<48:52:37,  7.19s/it]
 13%|█▎        | 3623/28080 [7:10:03<48:49:07,  7.19s/it]
                                                         
{'loss': 0.6558, 'learning_rate': 0.0004872574456842994, 'epoch': 1.55}

 13%|█▎        | 3623/28080 [7:10:03<48:49:07,  7.19s/it]
 13%|█▎        | 3624/28080 [7:10:10<48:43:15,  7.17s/it]
                                                         
{'loss': 0.6769, 'learning_rate': 0.0004872483554830525, 'epoch': 1.55}

 13%|█▎        | 3624/28080 [7:10:10<48:43:15,  7.17s/it]
 13%|█▎        | 3625/28080 [7:10:17<48:34:43,  7.15s/it]
                                                         
{'loss': 0.6733, 'learning_rate': 0.000487239262125461, 'epoch': 1.55}

 13%|█▎        | 3625/28080 [7:10:17<48:34:43,  7.15s/it]
 13%|█▎        | 3626/28080 [7:10:24<48:43:44,  7.17s/it]
                                                         
{'loss': 0.6547, 'learning_rate': 0.0004872301656116458, 'epoch': 1.55}

 13%|█▎        | 3626/28080 [7:10:24<48:43:44,  7.17s/it]
 13%|█▎        | 3627/28080 [7:10:32<48:45:18,  7.18s/it]
                                                         
{'loss': 0.6392, 'learning_rate': 0.00048722106594172813, 'epoch': 1.55}

 13%|█▎        | 3627/28080 [7:10:32<48:45:18,  7.18s/it]
 13%|█▎        | 3628/28080 [7:10:39<48:44:38,  7.18s/it]
                                                         
{'loss': 0.6534, 'learning_rate': 0.00048721196311582877, 'epoch': 1.55}

 13%|█▎        | 3628/28080 [7:10:39<48:44:38,  7.18s/it]
 13%|█▎        | 3629/28080 [7:10:46<48:40:49,  7.17s/it]
                                                         
{'loss': 0.6517, 'learning_rate': 0.00048720285713406896, 'epoch': 1.55}

 13%|█▎        | 3629/28080 [7:10:46<48:40:49,  7.17s/it]
 13%|█▎        | 3630/28080 [7:10:53<48:28:31,  7.14s/it]
                                                         
{'loss': 0.6756, 'learning_rate': 0.0004871937479965699, 'epoch': 1.55}

 13%|█▎        | 3630/28080 [7:10:53<48:28:31,  7.14s/it]
 13%|█▎        | 3631/28080 [7:11:00<48:35:27,  7.15s/it]
                                                         
{'loss': 0.6406, 'learning_rate': 0.0004871846357034527, 'epoch': 1.55}

 13%|█▎        | 3631/28080 [7:11:00<48:35:27,  7.15s/it]
 13%|█▎        | 3632/28080 [7:11:07<48:25:37,  7.13s/it]
                                                         
{'loss': 0.6608, 'learning_rate': 0.0004871755202548386, 'epoch': 1.55}

 13%|█▎        | 3632/28080 [7:11:07<48:25:37,  7.13s/it]
 13%|█▎        | 3633/28080 [7:11:14<48:26:30,  7.13s/it]
                                                         
{'loss': 0.6461, 'learning_rate': 0.0004871664016508489, 'epoch': 1.55}

 13%|█▎        | 3633/28080 [7:11:14<48:26:30,  7.13s/it]
 13%|█▎        | 3634/28080 [7:11:22<48:22:21,  7.12s/it]
                                                         
{'loss': 0.6662, 'learning_rate': 0.0004871572798916049, 'epoch': 1.55}

 13%|█▎        | 3634/28080 [7:11:22<48:22:21,  7.12s/it]
 13%|█▎        | 3635/28080 [7:11:29<48:19:44,  7.12s/it]
                                                         
{'loss': 0.6943, 'learning_rate': 0.00048714815497722796, 'epoch': 1.55}

 13%|█▎        | 3635/28080 [7:11:29<48:19:44,  7.12s/it]
 13%|█▎        | 3636/28080 [7:11:36<48:13:35,  7.10s/it]
                                                         
{'loss': 0.6806, 'learning_rate': 0.00048713902690783944, 'epoch': 1.55}

 13%|█▎        | 3636/28080 [7:11:36<48:13:35,  7.10s/it]
 13%|█▎        | 3637/28080 [7:11:43<48:22:57,  7.13s/it]
                                                         
{'loss': 0.6524, 'learning_rate': 0.00048712989568356084, 'epoch': 1.55}

 13%|█▎        | 3637/28080 [7:11:43<48:22:57,  7.13s/it]
 13%|█▎        | 3638/28080 [7:11:50<48:14:57,  7.11s/it]
                                                         
{'loss': 0.6722, 'learning_rate': 0.0004871207613045136, 'epoch': 1.55}

 13%|█▎        | 3638/28080 [7:11:50<48:14:57,  7.11s/it]
 13%|█▎        | 3639/28080 [7:11:57<48:18:25,  7.12s/it]
                                                         
{'loss': 0.6629, 'learning_rate': 0.0004871116237708193, 'epoch': 1.55}

 13%|█▎        | 3639/28080 [7:11:57<48:18:25,  7.12s/it]
 13%|█▎        | 3640/28080 [7:12:04<48:31:47,  7.15s/it]
                                                         
{'loss': 0.6521, 'learning_rate': 0.0004871024830825994, 'epoch': 1.55}

 13%|█▎        | 3640/28080 [7:12:04<48:31:47,  7.15s/it]
 13%|█▎        | 3641/28080 [7:12:11<48:14:33,  7.11s/it]
                                                         
{'loss': 0.6461, 'learning_rate': 0.00048709333923997554, 'epoch': 1.56}

 13%|█▎        | 3641/28080 [7:12:11<48:14:33,  7.11s/it]
 13%|█▎        | 3642/28080 [7:12:18<48:17:50,  7.11s/it]
                                                         
{'loss': 0.6635, 'learning_rate': 0.00048708419224306943, 'epoch': 1.56}

 13%|█▎        | 3642/28080 [7:12:18<48:17:50,  7.11s/it]
 13%|█▎        | 3643/28080 [7:12:26<48:12:22,  7.10s/it]
                                                         
{'loss': 0.6712, 'learning_rate': 0.00048707504209200274, 'epoch': 1.56}

 13%|█▎        | 3643/28080 [7:12:26<48:12:22,  7.10s/it]
 13%|█▎        | 3644/28080 [7:12:33<48:19:14,  7.12s/it]
                                                         
{'loss': 0.6663, 'learning_rate': 0.00048706588878689723, 'epoch': 1.56}

 13%|█▎        | 3644/28080 [7:12:33<48:19:14,  7.12s/it]
 13%|█▎        | 3645/28080 [7:12:40<48:14:53,  7.11s/it]
                                                         
{'loss': 0.677, 'learning_rate': 0.00048705673232787465, 'epoch': 1.56}

 13%|█▎        | 3645/28080 [7:12:40<48:14:53,  7.11s/it]
 13%|█▎        | 3646/28080 [7:12:47<48:15:10,  7.11s/it]
                                                         
{'loss': 0.6462, 'learning_rate': 0.0004870475727150567, 'epoch': 1.56}

 13%|█▎        | 3646/28080 [7:12:47<48:15:10,  7.11s/it]
 13%|█▎        | 3647/28080 [7:12:54<48:18:15,  7.12s/it]
                                                         
{'loss': 0.6593, 'learning_rate': 0.0004870384099485654, 'epoch': 1.56}

 13%|█▎        | 3647/28080 [7:12:54<48:18:15,  7.12s/it]
 13%|█▎        | 3648/28080 [7:13:01<48:20:30,  7.12s/it]
                                                         
{'loss': 0.6766, 'learning_rate': 0.00048702924402852253, 'epoch': 1.56}

 13%|█▎        | 3648/28080 [7:13:01<48:20:30,  7.12s/it]
 13%|█▎        | 3649/28080 [7:13:08<48:22:35,  7.13s/it]
                                                         
{'loss': 0.6585, 'learning_rate': 0.0004870200749550502, 'epoch': 1.56}

 13%|█▎        | 3649/28080 [7:13:08<48:22:35,  7.13s/it]
 13%|█▎        | 3650/28080 [7:13:16<48:33:37,  7.16s/it]
                                                         
{'loss': 0.6337, 'learning_rate': 0.0004870109027282702, 'epoch': 1.56}

 13%|█▎        | 3650/28080 [7:13:16<48:33:37,  7.16s/it]
 13%|█▎        | 3651/28080 [7:13:23<48:37:09,  7.16s/it]
                                                         
{'loss': 0.6774, 'learning_rate': 0.0004870017273483047, 'epoch': 1.56}

 13%|█▎        | 3651/28080 [7:13:23<48:37:09,  7.16s/it]
 13%|█▎        | 3652/28080 [7:13:30<48:46:46,  7.19s/it]
                                                         
{'loss': 0.6555, 'learning_rate': 0.0004869925488152758, 'epoch': 1.56}

 13%|█▎        | 3652/28080 [7:13:30<48:46:46,  7.19s/it]
 13%|█▎        | 3653/28080 [7:13:37<48:43:24,  7.18s/it]
                                                         
{'loss': 0.6574, 'learning_rate': 0.0004869833671293054, 'epoch': 1.56}

 13%|█▎        | 3653/28080 [7:13:37<48:43:24,  7.18s/it]
 13%|█▎        | 3654/28080 [7:13:44<48:32:47,  7.15s/it]
                                                         
{'loss': 0.6799, 'learning_rate': 0.00048697418229051584, 'epoch': 1.56}

 13%|█▎        | 3654/28080 [7:13:44<48:32:47,  7.15s/it]
 13%|█▎        | 3655/28080 [7:13:51<48:27:42,  7.14s/it]
                                                         
{'loss': 0.6634, 'learning_rate': 0.00048696499429902923, 'epoch': 1.56}

 13%|█▎        | 3655/28080 [7:13:51<48:27:42,  7.14s/it]
 13%|█▎        | 3656/28080 [7:13:58<48:27:49,  7.14s/it]
                                                         
{'loss': 0.6679, 'learning_rate': 0.00048695580315496784, 'epoch': 1.56}

 13%|█▎        | 3656/28080 [7:13:58<48:27:49,  7.14s/it]
 13%|█▎        | 3657/28080 [7:14:06<48:28:04,  7.14s/it]
                                                         
{'loss': 0.6638, 'learning_rate': 0.000486946608858454, 'epoch': 1.56}

 13%|█▎        | 3657/28080 [7:14:06<48:28:04,  7.14s/it]
 13%|█▎        | 3658/28080 [7:14:13<48:39:07,  7.17s/it]
                                                         
{'loss': 0.664, 'learning_rate': 0.0004869374114096099, 'epoch': 1.56}

 13%|█▎        | 3658/28080 [7:14:13<48:39:07,  7.17s/it]
 13%|█▎        | 3659/28080 [7:14:20<48:30:33,  7.15s/it]
                                                         
{'loss': 0.6657, 'learning_rate': 0.00048692821080855797, 'epoch': 1.56}

 13%|█▎        | 3659/28080 [7:14:20<48:30:33,  7.15s/it]
 13%|█▎        | 3660/28080 [7:14:27<48:04:21,  7.09s/it]
                                                         
{'loss': 0.6802, 'learning_rate': 0.0004869190070554207, 'epoch': 1.56}

 13%|█▎        | 3660/28080 [7:14:27<48:04:21,  7.09s/it]
 13%|█▎        | 3661/28080 [7:14:34<48:19:25,  7.12s/it]
                                                         
{'loss': 0.6552, 'learning_rate': 0.0004869098001503204, 'epoch': 1.56}

 13%|█▎        | 3661/28080 [7:14:34<48:19:25,  7.12s/it]
 13%|█▎        | 3662/28080 [7:14:41<48:19:25,  7.12s/it]
                                                         
{'loss': 0.641, 'learning_rate': 0.0004869005900933796, 'epoch': 1.56}

 13%|█▎        | 3662/28080 [7:14:41<48:19:25,  7.12s/it]
 13%|█▎        | 3663/28080 [7:14:48<48:24:34,  7.14s/it]
                                                         
{'loss': 0.6634, 'learning_rate': 0.00048689137688472084, 'epoch': 1.56}

 13%|█▎        | 3663/28080 [7:14:48<48:24:34,  7.14s/it]
 13%|█▎        | 3664/28080 [7:14:55<48:14:48,  7.11s/it]
                                                         
{'loss': 0.6444, 'learning_rate': 0.00048688216052446677, 'epoch': 1.57}

 13%|█▎        | 3664/28080 [7:14:55<48:14:48,  7.11s/it]
 13%|█▎        | 3665/28080 [7:15:03<48:12:56,  7.11s/it]
                                                         
{'loss': 0.6683, 'learning_rate': 0.0004868729410127399, 'epoch': 1.57}

 13%|█▎        | 3665/28080 [7:15:03<48:12:56,  7.11s/it]
 13%|█▎        | 3666/28080 [7:15:10<48:11:45,  7.11s/it]
                                                         
{'loss': 0.6531, 'learning_rate': 0.00048686371834966293, 'epoch': 1.57}

 13%|█▎        | 3666/28080 [7:15:10<48:11:45,  7.11s/it]
 13%|█▎        | 3667/28080 [7:15:17<48:27:49,  7.15s/it]
                                                         
{'loss': 0.6799, 'learning_rate': 0.0004868544925353585, 'epoch': 1.57}

 13%|█▎        | 3667/28080 [7:15:17<48:27:49,  7.15s/it]
 13%|█▎        | 3668/28080 [7:15:24<48:27:44,  7.15s/it]
                                                         
{'loss': 0.6591, 'learning_rate': 0.0004868452635699494, 'epoch': 1.57}

 13%|█▎        | 3668/28080 [7:15:24<48:27:44,  7.15s/it]
 13%|█▎        | 3669/28080 [7:15:31<48:32:28,  7.16s/it]
                                                         
{'loss': 0.6727, 'learning_rate': 0.0004868360314535585, 'epoch': 1.57}

 13%|█▎        | 3669/28080 [7:15:31<48:32:28,  7.16s/it]
 13%|█▎        | 3670/28080 [7:15:38<48:23:33,  7.14s/it]
                                                         
{'loss': 0.6527, 'learning_rate': 0.00048682679618630844, 'epoch': 1.57}

 13%|█▎        | 3670/28080 [7:15:38<48:23:33,  7.14s/it]
 13%|█▎        | 3671/28080 [7:15:45<48:16:58,  7.12s/it]
                                                         
{'loss': 0.6626, 'learning_rate': 0.00048681755776832215, 'epoch': 1.57}

 13%|█▎        | 3671/28080 [7:15:45<48:16:58,  7.12s/it]
 13%|█▎        | 3672/28080 [7:15:53<48:26:51,  7.15s/it]
                                                         
{'loss': 0.6626, 'learning_rate': 0.00048680831619972263, 'epoch': 1.57}

 13%|█▎        | 3672/28080 [7:15:53<48:26:51,  7.15s/it]
 13%|█▎        | 3673/28080 [7:16:00<48:37:56,  7.17s/it]
                                                         
{'loss': 0.6307, 'learning_rate': 0.0004867990714806327, 'epoch': 1.57}

 13%|█▎        | 3673/28080 [7:16:00<48:37:56,  7.17s/it]
 13%|█▎        | 3674/28080 [7:16:07<48:46:14,  7.19s/it]
                                                         
{'loss': 0.6542, 'learning_rate': 0.0004867898236111755, 'epoch': 1.57}

 13%|█▎        | 3674/28080 [7:16:07<48:46:14,  7.19s/it]
 13%|█▎        | 3675/28080 [7:16:14<48:29:53,  7.15s/it]
                                                         
{'loss': 0.6497, 'learning_rate': 0.0004867805725914739, 'epoch': 1.57}

 13%|█▎        | 3675/28080 [7:16:14<48:29:53,  7.15s/it]
 13%|█▎        | 3676/28080 [7:16:21<48:28:14,  7.15s/it]
                                                         
{'loss': 0.6525, 'learning_rate': 0.0004867713184216511, 'epoch': 1.57}

 13%|█▎        | 3676/28080 [7:16:21<48:28:14,  7.15s/it]
 13%|█▎        | 3677/28080 [7:16:29<48:36:51,  7.17s/it]
                                                         
{'loss': 0.6599, 'learning_rate': 0.0004867620611018302, 'epoch': 1.57}

 13%|█▎        | 3677/28080 [7:16:29<48:36:51,  7.17s/it]
 13%|█▎        | 3678/28080 [7:16:36<48:38:25,  7.18s/it]
                                                         
{'loss': 0.6448, 'learning_rate': 0.00048675280063213434, 'epoch': 1.57}

 13%|█▎        | 3678/28080 [7:16:36<48:38:25,  7.18s/it]
 13%|█▎        | 3679/28080 [7:16:43<48:38:25,  7.18s/it]
                                                         
{'loss': 0.6535, 'learning_rate': 0.00048674353701268664, 'epoch': 1.57}

 13%|█▎        | 3679/28080 [7:16:43<48:38:25,  7.18s/it]
 13%|█▎        | 3680/28080 [7:16:50<48:40:14,  7.18s/it]
                                                         
{'loss': 0.6706, 'learning_rate': 0.0004867342702436104, 'epoch': 1.57}

 13%|█▎        | 3680/28080 [7:16:50<48:40:14,  7.18s/it]
 13%|█▎        | 3681/28080 [7:16:57<48:38:26,  7.18s/it]
                                                         
{'loss': 0.671, 'learning_rate': 0.000486725000325029, 'epoch': 1.57}

 13%|█▎        | 3681/28080 [7:16:57<48:38:26,  7.18s/it]
 13%|█▎        | 3682/28080 [7:17:04<48:16:52,  7.12s/it]
                                                         
{'loss': 0.6563, 'learning_rate': 0.0004867157272570657, 'epoch': 1.57}

 13%|█▎        | 3682/28080 [7:17:04<48:16:52,  7.12s/it]
 13%|█▎        | 3683/28080 [7:17:11<48:21:57,  7.14s/it]
                                                         
{'loss': 0.6732, 'learning_rate': 0.00048670645103984376, 'epoch': 1.57}

 13%|█▎        | 3683/28080 [7:17:11<48:21:57,  7.14s/it]
 13%|█▎        | 3684/28080 [7:17:19<48:19:43,  7.13s/it]
                                                         
{'loss': 0.6662, 'learning_rate': 0.0004866971716734867, 'epoch': 1.57}

 13%|█▎        | 3684/28080 [7:17:19<48:19:43,  7.13s/it]
 13%|█▎        | 3685/28080 [7:17:26<48:14:15,  7.12s/it]
                                                         
{'loss': 0.6559, 'learning_rate': 0.00048668788915811803, 'epoch': 1.57}

 13%|█▎        | 3685/28080 [7:17:26<48:14:15,  7.12s/it]
 13%|█▎        | 3686/28080 [7:17:33<48:13:27,  7.12s/it]
                                                         
{'loss': 0.6619, 'learning_rate': 0.00048667860349386116, 'epoch': 1.57}

 13%|█▎        | 3686/28080 [7:17:33<48:13:27,  7.12s/it]
 13%|█▎        | 3687/28080 [7:17:40<48:31:57,  7.16s/it]
                                                         
{'loss': 0.6712, 'learning_rate': 0.00048666931468083956, 'epoch': 1.58}

 13%|█▎        | 3687/28080 [7:17:40<48:31:57,  7.16s/it]
 13%|█▎        | 3688/28080 [7:17:47<48:29:33,  7.16s/it]
                                                         
{'loss': 0.6625, 'learning_rate': 0.000486660022719177, 'epoch': 1.58}

 13%|█▎        | 3688/28080 [7:17:47<48:29:33,  7.16s/it]
 13%|█▎        | 3689/28080 [7:17:54<48:26:09,  7.15s/it]
                                                         
{'loss': 0.6444, 'learning_rate': 0.00048665072760899685, 'epoch': 1.58}

 13%|█▎        | 3689/28080 [7:17:54<48:26:09,  7.15s/it]
 13%|█▎        | 3690/28080 [7:18:01<48:26:26,  7.15s/it]
                                                         
{'loss': 0.6502, 'learning_rate': 0.000486641429350423, 'epoch': 1.58}

 13%|█▎        | 3690/28080 [7:18:01<48:26:26,  7.15s/it]
 13%|█▎        | 3691/28080 [7:18:09<48:34:06,  7.17s/it]
                                                         
{'loss': 0.6392, 'learning_rate': 0.00048663212794357904, 'epoch': 1.58}

 13%|█▎        | 3691/28080 [7:18:09<48:34:06,  7.17s/it]
 13%|█▎        | 3692/28080 [7:18:16<48:45:16,  7.20s/it]
                                                         
{'loss': 0.6456, 'learning_rate': 0.0004866228233885888, 'epoch': 1.58}

 13%|█▎        | 3692/28080 [7:18:16<48:45:16,  7.20s/it]
 13%|█▎        | 3693/28080 [7:18:23<48:31:47,  7.16s/it]
                                                         
{'loss': 0.6466, 'learning_rate': 0.0004866135156855759, 'epoch': 1.58}

 13%|█▎        | 3693/28080 [7:18:23<48:31:47,  7.16s/it]
 13%|█▎        | 3694/28080 [7:18:30<48:21:05,  7.14s/it]
                                                         
{'loss': 0.6762, 'learning_rate': 0.00048660420483466433, 'epoch': 1.58}

 13%|█▎        | 3694/28080 [7:18:30<48:21:05,  7.14s/it]
 13%|█▎        | 3695/28080 [7:18:37<48:31:15,  7.16s/it]
                                                         
{'loss': 0.6489, 'learning_rate': 0.00048659489083597787, 'epoch': 1.58}

 13%|█▎        | 3695/28080 [7:18:37<48:31:15,  7.16s/it]
 13%|█▎        | 3696/28080 [7:18:44<48:25:15,  7.15s/it]
                                                         
{'loss': 0.6348, 'learning_rate': 0.0004865855736896405, 'epoch': 1.58}

 13%|█▎        | 3696/28080 [7:18:44<48:25:15,  7.15s/it]
 13%|█▎        | 3697/28080 [7:18:51<48:10:08,  7.11s/it]
                                                         
{'loss': 0.6647, 'learning_rate': 0.00048657625339577616, 'epoch': 1.58}

 13%|█▎        | 3697/28080 [7:18:51<48:10:08,  7.11s/it]
 13%|█▎        | 3698/28080 [7:18:59<48:07:36,  7.11s/it]
                                                         
{'loss': 0.6718, 'learning_rate': 0.0004865669299545088, 'epoch': 1.58}

 13%|█▎        | 3698/28080 [7:18:59<48:07:36,  7.11s/it]
 13%|█▎        | 3699/28080 [7:19:06<48:04:36,  7.10s/it]
                                                         
{'loss': 0.6506, 'learning_rate': 0.0004865576033659625, 'epoch': 1.58}

 13%|█▎        | 3699/28080 [7:19:06<48:04:36,  7.10s/it]
 13%|█▎        | 3700/28080 [7:19:13<47:51:53,  7.07s/it]
                                                         
{'loss': 0.6536, 'learning_rate': 0.0004865482736302613, 'epoch': 1.58}

 13%|█▎        | 3700/28080 [7:19:13<47:51:53,  7.07s/it]
 13%|█▎        | 3701/28080 [7:19:20<48:01:06,  7.09s/it]
                                                         
{'loss': 0.6776, 'learning_rate': 0.0004865389407475294, 'epoch': 1.58}

 13%|█▎        | 3701/28080 [7:19:20<48:01:06,  7.09s/it]
 13%|█▎        | 3702/28080 [7:19:27<48:21:04,  7.14s/it]
                                                         
{'loss': 0.652, 'learning_rate': 0.00048652960471789086, 'epoch': 1.58}

 13%|█▎        | 3702/28080 [7:19:27<48:21:04,  7.14s/it]
 13%|█▎        | 3703/28080 [7:19:34<48:12:31,  7.12s/it]
                                                         
{'loss': 0.6943, 'learning_rate': 0.00048652026554147, 'epoch': 1.58}

 13%|█▎        | 3703/28080 [7:19:34<48:12:31,  7.12s/it]
 13%|█▎        | 3704/28080 [7:19:41<48:10:14,  7.11s/it]
                                                         
{'loss': 0.6579, 'learning_rate': 0.000486510923218391, 'epoch': 1.58}

 13%|█▎        | 3704/28080 [7:19:41<48:10:14,  7.11s/it]
 13%|█▎        | 3705/28080 [7:19:48<47:55:33,  7.08s/it]
                                                         
{'loss': 0.6774, 'learning_rate': 0.0004865015777487782, 'epoch': 1.58}

 13%|█▎        | 3705/28080 [7:19:48<47:55:33,  7.08s/it]
 13%|█▎        | 3706/28080 [7:19:55<48:02:39,  7.10s/it]
                                                         
{'loss': 0.6618, 'learning_rate': 0.00048649222913275584, 'epoch': 1.58}

 13%|█▎        | 3706/28080 [7:19:55<48:02:39,  7.10s/it]
 13%|█▎        | 3707/28080 [7:20:03<48:23:03,  7.15s/it]
                                                         
{'loss': 0.6481, 'learning_rate': 0.0004864828773704483, 'epoch': 1.58}

 13%|█▎        | 3707/28080 [7:20:03<48:23:03,  7.15s/it]
 13%|█▎        | 3708/28080 [7:20:10<48:26:54,  7.16s/it]
                                                         
{'loss': 0.6752, 'learning_rate': 0.0004864735224619801, 'epoch': 1.58}

 13%|█▎        | 3708/28080 [7:20:10<48:26:54,  7.16s/it]
 13%|█▎        | 3709/28080 [7:20:17<48:12:35,  7.12s/it]
                                                         
{'loss': 0.676, 'learning_rate': 0.0004864641644074756, 'epoch': 1.58}

 13%|█▎        | 3709/28080 [7:20:17<48:12:35,  7.12s/it]
 13%|█▎        | 3710/28080 [7:20:24<48:06:10,  7.11s/it]
                                                         
{'loss': 0.6597, 'learning_rate': 0.00048645480320705944, 'epoch': 1.58}

 13%|█▎        | 3710/28080 [7:20:24<48:06:10,  7.11s/it]
 13%|█▎        | 3711/28080 [7:20:31<48:05:35,  7.10s/it]
                                                         
{'loss': 0.6552, 'learning_rate': 0.00048644543886085603, 'epoch': 1.59}

 13%|█▎        | 3711/28080 [7:20:31<48:05:35,  7.10s/it]
 13%|█▎        | 3712/28080 [7:20:38<48:14:58,  7.13s/it]
                                                         
{'loss': 0.65, 'learning_rate': 0.0004864360713689899, 'epoch': 1.59}

 13%|█▎        | 3712/28080 [7:20:38<48:14:58,  7.13s/it]
 13%|█▎        | 3713/28080 [7:20:45<48:26:35,  7.16s/it]
                                                         
{'loss': 0.6467, 'learning_rate': 0.0004864267007315858, 'epoch': 1.59}

 13%|█▎        | 3713/28080 [7:20:45<48:26:35,  7.16s/it]
 13%|█▎        | 3714/28080 [7:20:53<48:23:32,  7.15s/it]
                                                         
{'loss': 0.6492, 'learning_rate': 0.0004864173269487684, 'epoch': 1.59}

 13%|█▎        | 3714/28080 [7:20:53<48:23:32,  7.15s/it]
 13%|█▎        | 3715/28080 [7:21:00<48:22:39,  7.15s/it]
                                                         
{'loss': 0.6527, 'learning_rate': 0.0004864079500206623, 'epoch': 1.59}

 13%|█▎        | 3715/28080 [7:21:00<48:22:39,  7.15s/it]
 13%|█▎        | 3716/28080 [7:21:07<48:22:31,  7.15s/it]
                                                         
{'loss': 0.6905, 'learning_rate': 0.00048639856994739237, 'epoch': 1.59}

 13%|█▎        | 3716/28080 [7:21:07<48:22:31,  7.15s/it]
 13%|█▎        | 3717/28080 [7:21:14<48:27:35,  7.16s/it]
                                                         
{'loss': 0.6456, 'learning_rate': 0.00048638918672908325, 'epoch': 1.59}

 13%|█▎        | 3717/28080 [7:21:14<48:27:35,  7.16s/it]
 13%|█▎        | 3718/28080 [7:21:21<48:21:44,  7.15s/it]
                                                         
{'loss': 0.678, 'learning_rate': 0.00048637980036585996, 'epoch': 1.59}

 13%|█▎        | 3718/28080 [7:21:21<48:21:44,  7.15s/it]
 13%|█▎        | 3719/28080 [7:21:28<48:32:05,  7.17s/it]
                                                         
{'loss': 0.6552, 'learning_rate': 0.0004863704108578473, 'epoch': 1.59}

 13%|█▎        | 3719/28080 [7:21:28<48:32:05,  7.17s/it]
 13%|█▎        | 3720/28080 [7:21:36<48:35:35,  7.18s/it]
                                                         
{'loss': 0.662, 'learning_rate': 0.0004863610182051701, 'epoch': 1.59}

 13%|█▎        | 3720/28080 [7:21:36<48:35:35,  7.18s/it]
 13%|█▎        | 3721/28080 [7:21:43<48:33:49,  7.18s/it]
                                                         
{'loss': 0.6584, 'learning_rate': 0.0004863516224079534, 'epoch': 1.59}

 13%|█▎        | 3721/28080 [7:21:43<48:33:49,  7.18s/it]
 13%|█▎        | 3722/28080 [7:21:50<48:27:27,  7.16s/it]
                                                         
{'loss': 0.6714, 'learning_rate': 0.0004863422234663223, 'epoch': 1.59}

 13%|█▎        | 3722/28080 [7:21:50<48:27:27,  7.16s/it]
 13%|█▎        | 3723/28080 [7:21:57<48:22:26,  7.15s/it]
                                                         
{'loss': 0.6416, 'learning_rate': 0.0004863328213804016, 'epoch': 1.59}

 13%|█▎        | 3723/28080 [7:21:57<48:22:26,  7.15s/it]
 13%|█▎        | 3724/28080 [7:22:04<48:13:07,  7.13s/it]
                                                         
{'loss': 0.6682, 'learning_rate': 0.0004863234161503166, 'epoch': 1.59}

 13%|█▎        | 3724/28080 [7:22:04<48:13:07,  7.13s/it]
 13%|█▎        | 3725/28080 [7:22:11<48:25:08,  7.16s/it]
                                                         
{'loss': 0.6747, 'learning_rate': 0.0004863140077761923, 'epoch': 1.59}

 13%|█▎        | 3725/28080 [7:22:11<48:25:08,  7.16s/it]
 13%|█▎        | 3726/28080 [7:22:18<48:30:43,  7.17s/it]
                                                         
{'loss': 0.6259, 'learning_rate': 0.0004863045962581539, 'epoch': 1.59}

 13%|█▎        | 3726/28080 [7:22:18<48:30:43,  7.17s/it]
 13%|█▎        | 3727/28080 [7:22:26<48:21:14,  7.15s/it]
                                                         
{'loss': 0.6648, 'learning_rate': 0.00048629518159632677, 'epoch': 1.59}

 13%|█▎        | 3727/28080 [7:22:26<48:21:14,  7.15s/it]
 13%|█▎        | 3728/28080 [7:22:33<48:07:00,  7.11s/it]
                                                         
{'loss': 0.6476, 'learning_rate': 0.0004862857637908359, 'epoch': 1.59}

 13%|█▎        | 3728/28080 [7:22:33<48:07:00,  7.11s/it]
 13%|█▎        | 3729/28080 [7:22:40<48:01:19,  7.10s/it]
                                                         
{'loss': 0.6592, 'learning_rate': 0.0004862763428418067, 'epoch': 1.59}

 13%|█▎        | 3729/28080 [7:22:40<48:01:19,  7.10s/it]
 13%|█▎        | 3730/28080 [7:22:47<48:15:23,  7.13s/it]
                                                         
{'loss': 0.6277, 'learning_rate': 0.0004862669187493646, 'epoch': 1.59}

 13%|█▎        | 3730/28080 [7:22:47<48:15:23,  7.13s/it]
 13%|█▎        | 3731/28080 [7:22:54<47:51:55,  7.08s/it]
                                                         
{'loss': 0.6727, 'learning_rate': 0.0004862574915136348, 'epoch': 1.59}

 13%|█▎        | 3731/28080 [7:22:54<47:51:55,  7.08s/it]
 13%|█▎        | 3732/28080 [7:23:01<47:59:34,  7.10s/it]
                                                         
{'loss': 0.6527, 'learning_rate': 0.00048624806113474283, 'epoch': 1.59}

 13%|█▎        | 3732/28080 [7:23:01<47:59:34,  7.10s/it]
 13%|█▎        | 3733/28080 [7:23:08<48:09:22,  7.12s/it]
                                                         
{'loss': 0.6866, 'learning_rate': 0.0004862386276128141, 'epoch': 1.59}

 13%|█▎        | 3733/28080 [7:23:08<48:09:22,  7.12s/it]
 13%|█▎        | 3734/28080 [7:23:15<48:14:40,  7.13s/it]
                                                         
{'loss': 0.6756, 'learning_rate': 0.00048622919094797425, 'epoch': 1.6}

 13%|█▎        | 3734/28080 [7:23:15<48:14:40,  7.13s/it]
 13%|█▎        | 3735/28080 [7:23:22<48:16:32,  7.14s/it]
                                                         
{'loss': 0.6767, 'learning_rate': 0.0004862197511403487, 'epoch': 1.6}

 13%|█▎        | 3735/28080 [7:23:22<48:16:32,  7.14s/it]
 13%|█▎        | 3736/28080 [7:23:30<48:10:08,  7.12s/it]
                                                         
{'loss': 0.6889, 'learning_rate': 0.00048621030819006293, 'epoch': 1.6}

 13%|█▎        | 3736/28080 [7:23:30<48:10:08,  7.12s/it]
 13%|█▎        | 3737/28080 [7:23:37<48:10:00,  7.12s/it]
                                                         
{'loss': 0.6534, 'learning_rate': 0.00048620086209724277, 'epoch': 1.6}

 13%|█▎        | 3737/28080 [7:23:37<48:10:00,  7.12s/it]
 13%|█▎        | 3738/28080 [7:23:44<48:00:24,  7.10s/it]
                                                         
{'loss': 0.6703, 'learning_rate': 0.00048619141286201386, 'epoch': 1.6}

 13%|█▎        | 3738/28080 [7:23:44<48:00:24,  7.10s/it]
 13%|█▎        | 3739/28080 [7:23:51<47:51:08,  7.08s/it]
                                                         
{'loss': 0.6402, 'learning_rate': 0.0004861819604845018, 'epoch': 1.6}

 13%|█▎        | 3739/28080 [7:23:51<47:51:08,  7.08s/it]
 13%|█▎        | 3740/28080 [7:23:58<47:50:29,  7.08s/it]
                                                         
{'loss': 0.6462, 'learning_rate': 0.0004861725049648325, 'epoch': 1.6}

 13%|█▎        | 3740/28080 [7:23:58<47:50:29,  7.08s/it]
 13%|█▎        | 3741/28080 [7:24:05<47:50:42,  7.08s/it]
                                                         
{'loss': 0.645, 'learning_rate': 0.0004861630463031316, 'epoch': 1.6}

 13%|█▎        | 3741/28080 [7:24:05<47:50:42,  7.08s/it]
 13%|█▎        | 3742/28080 [7:24:12<47:54:16,  7.09s/it]
                                                         
{'loss': 0.6591, 'learning_rate': 0.00048615358449952497, 'epoch': 1.6}

 13%|█▎        | 3742/28080 [7:24:12<47:54:16,  7.09s/it]
 13%|█▎        | 3743/28080 [7:24:19<48:39:32,  7.20s/it]
                                                         
{'loss': 0.6607, 'learning_rate': 0.0004861441195541385, 'epoch': 1.6}

 13%|█▎        | 3743/28080 [7:24:19<48:39:32,  7.20s/it]
 13%|█▎        | 3744/28080 [7:24:27<48:31:09,  7.18s/it]
                                                         
{'loss': 0.6763, 'learning_rate': 0.00048613465146709825, 'epoch': 1.6}

 13%|█▎        | 3744/28080 [7:24:27<48:31:09,  7.18s/it]
 13%|█▎        | 3745/28080 [7:24:34<48:28:45,  7.17s/it]
                                                         
{'loss': 0.6685, 'learning_rate': 0.00048612518023853, 'epoch': 1.6}

 13%|█▎        | 3745/28080 [7:24:34<48:28:45,  7.17s/it]
 13%|█▎        | 3746/28080 [7:24:41<48:25:49,  7.16s/it]
                                                         
{'loss': 0.6445, 'learning_rate': 0.00048611570586855985, 'epoch': 1.6}

 13%|█▎        | 3746/28080 [7:24:41<48:25:49,  7.16s/it]
 13%|█▎        | 3747/28080 [7:24:48<48:13:30,  7.13s/it]
                                                         
{'loss': 0.6778, 'learning_rate': 0.0004861062283573138, 'epoch': 1.6}

 13%|█▎        | 3747/28080 [7:24:48<48:13:30,  7.13s/it]
 13%|█▎        | 3748/28080 [7:24:55<48:09:50,  7.13s/it]
                                                         
{'loss': 0.6627, 'learning_rate': 0.000486096747704918, 'epoch': 1.6}

 13%|█▎        | 3748/28080 [7:24:55<48:09:50,  7.13s/it]
 13%|█▎        | 3749/28080 [7:25:02<48:05:24,  7.12s/it]
                                                         
{'loss': 0.6717, 'learning_rate': 0.0004860872639114985, 'epoch': 1.6}

 13%|█▎        | 3749/28080 [7:25:02<48:05:24,  7.12s/it]
 13%|█▎        | 3750/28080 [7:25:09<48:05:55,  7.12s/it]
                                                         
{'loss': 0.661, 'learning_rate': 0.00048607777697718145, 'epoch': 1.6}

 13%|█▎        | 3750/28080 [7:25:09<48:05:55,  7.12s/it]
 13%|█▎        | 3751/28080 [7:25:16<48:13:14,  7.14s/it]
                                                         
{'loss': 0.6678, 'learning_rate': 0.00048606828690209326, 'epoch': 1.6}

 13%|█▎        | 3751/28080 [7:25:16<48:13:14,  7.14s/it]
 13%|█▎        | 3752/28080 [7:25:24<48:17:53,  7.15s/it]
                                                         
{'loss': 0.6851, 'learning_rate': 0.00048605879368635995, 'epoch': 1.6}

 13%|█▎        | 3752/28080 [7:25:24<48:17:53,  7.15s/it]
 13%|█▎        | 3753/28080 [7:25:31<48:05:22,  7.12s/it]
                                                         
{'loss': 0.676, 'learning_rate': 0.0004860492973301079, 'epoch': 1.6}

 13%|█▎        | 3753/28080 [7:25:31<48:05:22,  7.12s/it]
 13%|█▎        | 3754/28080 [7:25:38<48:15:01,  7.14s/it]
                                                         
{'loss': 0.6719, 'learning_rate': 0.00048603979783346364, 'epoch': 1.6}

 13%|█▎        | 3754/28080 [7:25:38<48:15:01,  7.14s/it]
 13%|█▎        | 3755/28080 [7:25:45<48:21:32,  7.16s/it]
                                                         
{'loss': 0.6453, 'learning_rate': 0.0004860302951965532, 'epoch': 1.6}

 13%|█▎        | 3755/28080 [7:25:45<48:21:32,  7.16s/it]
 13%|█▎        | 3756/28080 [7:25:52<48:32:51,  7.19s/it]
                                                         
{'loss': 0.6411, 'learning_rate': 0.0004860207894195032, 'epoch': 1.6}

 13%|█▎        | 3756/28080 [7:25:52<48:32:51,  7.19s/it]
 13%|█▎        | 3757/28080 [7:25:59<48:15:42,  7.14s/it]
                                                         
{'loss': 0.655, 'learning_rate': 0.0004860112805024402, 'epoch': 1.6}

 13%|█▎        | 3757/28080 [7:25:59<48:15:42,  7.14s/it]
 13%|█▎        | 3758/28080 [7:26:07<48:28:12,  7.17s/it]
                                                         
{'loss': 0.6677, 'learning_rate': 0.00048600176844549047, 'epoch': 1.61}

 13%|█▎        | 3758/28080 [7:26:07<48:28:12,  7.17s/it]
 13%|█▎        | 3759/28080 [7:26:14<48:16:23,  7.15s/it]
                                                         
{'loss': 0.6672, 'learning_rate': 0.00048599225324878076, 'epoch': 1.61}

 13%|█▎        | 3759/28080 [7:26:14<48:16:23,  7.15s/it]
 13%|█▎        | 3760/28080 [7:26:21<48:17:13,  7.15s/it]
                                                         
{'loss': 0.6744, 'learning_rate': 0.00048598273491243753, 'epoch': 1.61}

 13%|█▎        | 3760/28080 [7:26:21<48:17:13,  7.15s/it]
 13%|█▎        | 3761/28080 [7:26:28<48:15:44,  7.14s/it]
                                                         
{'loss': 0.6555, 'learning_rate': 0.0004859732134365875, 'epoch': 1.61}

 13%|█▎        | 3761/28080 [7:26:28<48:15:44,  7.14s/it]
 13%|█▎        | 3762/28080 [7:26:35<48:38:04,  7.20s/it]
                                                         
{'loss': 0.6661, 'learning_rate': 0.00048596368882135733, 'epoch': 1.61}

 13%|█▎        | 3762/28080 [7:26:35<48:38:04,  7.20s/it]
 13%|█▎        | 3763/28080 [7:26:43<48:42:31,  7.21s/it]
                                                         
{'loss': 0.6416, 'learning_rate': 0.00048595416106687363, 'epoch': 1.61}

 13%|█▎        | 3763/28080 [7:26:43<48:42:31,  7.21s/it]
 13%|█▎        | 3764/28080 [7:26:50<48:36:59,  7.20s/it]
                                                         
{'loss': 0.6423, 'learning_rate': 0.00048594463017326327, 'epoch': 1.61}

 13%|█▎        | 3764/28080 [7:26:50<48:36:59,  7.20s/it]
 13%|█▎        | 3765/28080 [7:26:57<48:30:28,  7.18s/it]
                                                         
{'loss': 0.6649, 'learning_rate': 0.000485935096140653, 'epoch': 1.61}

 13%|█▎        | 3765/28080 [7:26:57<48:30:28,  7.18s/it]
 13%|█▎        | 3766/28080 [7:27:04<48:20:22,  7.16s/it]
                                                         
{'loss': 0.6734, 'learning_rate': 0.00048592555896916973, 'epoch': 1.61}

 13%|█▎        | 3766/28080 [7:27:04<48:20:22,  7.16s/it]
 13%|█▎        | 3767/28080 [7:27:11<48:17:34,  7.15s/it]
                                                         
{'loss': 0.6489, 'learning_rate': 0.00048591601865894025, 'epoch': 1.61}

 13%|█▎        | 3767/28080 [7:27:11<48:17:34,  7.15s/it]
 13%|█▎        | 3768/28080 [7:27:18<48:26:40,  7.17s/it]
                                                         
{'loss': 0.6508, 'learning_rate': 0.0004859064752100916, 'epoch': 1.61}

 13%|█▎        | 3768/28080 [7:27:18<48:26:40,  7.17s/it]
 13%|█▎        | 3769/28080 [7:27:26<48:31:37,  7.19s/it]
                                                         
{'loss': 0.6399, 'learning_rate': 0.0004858969286227505, 'epoch': 1.61}

 13%|█▎        | 3769/28080 [7:27:26<48:31:37,  7.19s/it]
 13%|█▎        | 3770/28080 [7:27:33<48:22:27,  7.16s/it]
                                                         
{'loss': 0.6658, 'learning_rate': 0.0004858873788970443, 'epoch': 1.61}

 13%|█▎        | 3770/28080 [7:27:33<48:22:27,  7.16s/it]
 13%|█▎        | 3771/28080 [7:27:40<48:28:22,  7.18s/it]
                                                         
{'loss': 0.6442, 'learning_rate': 0.0004858778260330998, 'epoch': 1.61}

 13%|█▎        | 3771/28080 [7:27:40<48:28:22,  7.18s/it]
 13%|█▎        | 3772/28080 [7:27:47<48:29:49,  7.18s/it]
                                                         
{'loss': 0.6616, 'learning_rate': 0.0004858682700310441, 'epoch': 1.61}

 13%|█▎        | 3772/28080 [7:27:47<48:29:49,  7.18s/it]
 13%|█▎        | 3773/28080 [7:27:54<48:22:21,  7.16s/it]
                                                         
{'loss': 0.6812, 'learning_rate': 0.0004858587108910045, 'epoch': 1.61}

 13%|█▎        | 3773/28080 [7:27:54<48:22:21,  7.16s/it]
 13%|█▎        | 3774/28080 [7:28:01<48:22:52,  7.17s/it]
                                                         
{'loss': 0.6564, 'learning_rate': 0.00048584914861310804, 'epoch': 1.61}

 13%|█▎        | 3774/28080 [7:28:01<48:22:52,  7.17s/it]
 13%|█▎        | 3775/28080 [7:28:08<48:18:40,  7.16s/it]
                                                         
{'loss': 0.6633, 'learning_rate': 0.00048583958319748196, 'epoch': 1.61}

 13%|█▎        | 3775/28080 [7:28:08<48:18:40,  7.16s/it]
 13%|█▎        | 3776/28080 [7:28:16<48:05:55,  7.12s/it]
                                                         
{'loss': 0.6784, 'learning_rate': 0.0004858300146442535, 'epoch': 1.61}

 13%|█▎        | 3776/28080 [7:28:16<48:05:55,  7.12s/it]
 13%|█▎        | 3777/28080 [7:28:23<48:11:06,  7.14s/it]
                                                         
{'loss': 0.6388, 'learning_rate': 0.00048582044295355007, 'epoch': 1.61}

 13%|█▎        | 3777/28080 [7:28:23<48:11:06,  7.14s/it]
 13%|█▎        | 3778/28080 [7:28:30<48:13:05,  7.14s/it]
                                                         
{'loss': 0.6761, 'learning_rate': 0.0004858108681254989, 'epoch': 1.61}

 13%|█▎        | 3778/28080 [7:28:30<48:13:05,  7.14s/it]
 13%|█▎        | 3779/28080 [7:28:37<48:16:57,  7.15s/it]
                                                         
{'loss': 0.6833, 'learning_rate': 0.00048580129016022734, 'epoch': 1.61}

 13%|█▎        | 3779/28080 [7:28:37<48:16:57,  7.15s/it]
 13%|█▎        | 3780/28080 [7:28:44<48:05:20,  7.12s/it]
                                                         
{'loss': 0.677, 'learning_rate': 0.00048579170905786295, 'epoch': 1.61}

 13%|█▎        | 3780/28080 [7:28:44<48:05:20,  7.12s/it]
 13%|█▎        | 3781/28080 [7:28:51<48:13:48,  7.15s/it]
                                                         
{'loss': 0.6561, 'learning_rate': 0.0004857821248185331, 'epoch': 1.62}

 13%|█▎        | 3781/28080 [7:28:51<48:13:48,  7.15s/it]
 13%|█▎        | 3782/28080 [7:28:58<48:23:15,  7.17s/it]
                                                         
{'loss': 0.663, 'learning_rate': 0.0004857725374423653, 'epoch': 1.62}

 13%|█▎        | 3782/28080 [7:28:58<48:23:15,  7.17s/it]
 13%|█▎        | 3783/28080 [7:29:06<48:31:50,  7.19s/it]
                                                         
{'loss': 0.6642, 'learning_rate': 0.0004857629469294871, 'epoch': 1.62}

 13%|█▎        | 3783/28080 [7:29:06<48:31:50,  7.19s/it]
 13%|█▎        | 3784/28080 [7:29:13<48:19:03,  7.16s/it]
                                                         
{'loss': 0.6581, 'learning_rate': 0.0004857533532800262, 'epoch': 1.62}

 13%|█▎        | 3784/28080 [7:29:13<48:19:03,  7.16s/it]
 13%|█▎        | 3785/28080 [7:29:20<48:16:33,  7.15s/it]
                                                         
{'loss': 0.6739, 'learning_rate': 0.00048574375649411005, 'epoch': 1.62}

 13%|█▎        | 3785/28080 [7:29:20<48:16:33,  7.15s/it]
 13%|█▎        | 3786/28080 [7:29:27<48:16:18,  7.15s/it]
                                                         
{'loss': 0.6522, 'learning_rate': 0.00048573415657186646, 'epoch': 1.62}

 13%|█▎        | 3786/28080 [7:29:27<48:16:18,  7.15s/it]
 13%|█▎        | 3787/28080 [7:29:34<48:11:11,  7.14s/it]
                                                         
{'loss': 0.6609, 'learning_rate': 0.0004857245535134231, 'epoch': 1.62}

 13%|█▎        | 3787/28080 [7:29:34<48:11:11,  7.14s/it]
 13%|█▎        | 3788/28080 [7:29:41<48:11:56,  7.14s/it]
                                                         
{'loss': 0.6424, 'learning_rate': 0.0004857149473189079, 'epoch': 1.62}

 13%|█▎        | 3788/28080 [7:29:41<48:11:56,  7.14s/it]
 13%|█▎        | 3789/28080 [7:29:49<48:14:05,  7.15s/it]
                                                         
{'loss': 0.6586, 'learning_rate': 0.0004857053379884483, 'epoch': 1.62}

 13%|█▎        | 3789/28080 [7:29:49<48:14:05,  7.15s/it]
 13%|█▎        | 3790/28080 [7:29:56<48:03:12,  7.12s/it]
                                                         
{'loss': 0.6477, 'learning_rate': 0.00048569572552217247, 'epoch': 1.62}

 13%|█▎        | 3790/28080 [7:29:56<48:03:12,  7.12s/it]
 14%|█▎        | 3791/28080 [7:30:03<48:02:21,  7.12s/it]
                                                         
{'loss': 0.6559, 'learning_rate': 0.000485686109920208, 'epoch': 1.62}

 14%|█▎        | 3791/28080 [7:30:03<48:02:21,  7.12s/it]
 14%|█▎        | 3792/28080 [7:30:10<47:54:55,  7.10s/it]
                                                         
{'loss': 0.6645, 'learning_rate': 0.0004856764911826831, 'epoch': 1.62}

 14%|█▎        | 3792/28080 [7:30:10<47:54:55,  7.10s/it]
 14%|█▎        | 3793/28080 [7:30:17<47:54:58,  7.10s/it]
                                                         
{'loss': 0.6463, 'learning_rate': 0.0004856668693097256, 'epoch': 1.62}

 14%|█▎        | 3793/28080 [7:30:17<47:54:58,  7.10s/it]
 14%|█▎        | 3794/28080 [7:30:24<47:58:51,  7.11s/it]
                                                         
{'loss': 0.6635, 'learning_rate': 0.0004856572443014635, 'epoch': 1.62}

 14%|█▎        | 3794/28080 [7:30:24<47:58:51,  7.11s/it]
 14%|█▎        | 3795/28080 [7:30:31<48:03:27,  7.12s/it]
                                                         
{'loss': 0.6541, 'learning_rate': 0.000485647616158025, 'epoch': 1.62}

 14%|█▎        | 3795/28080 [7:30:31<48:03:27,  7.12s/it]
 14%|█▎        | 3796/28080 [7:30:38<47:47:42,  7.09s/it]
                                                         
{'loss': 0.6353, 'learning_rate': 0.0004856379848795379, 'epoch': 1.62}

 14%|█▎        | 3796/28080 [7:30:38<47:47:42,  7.09s/it]
 14%|█▎        | 3797/28080 [7:30:45<48:00:29,  7.12s/it]
                                                         
{'loss': 0.6472, 'learning_rate': 0.0004856283504661306, 'epoch': 1.62}

 14%|█▎        | 3797/28080 [7:30:45<48:00:29,  7.12s/it]
 14%|█▎        | 3798/28080 [7:30:53<48:07:22,  7.13s/it]
                                                         
{'loss': 0.6376, 'learning_rate': 0.0004856187129179312, 'epoch': 1.62}

 14%|█▎        | 3798/28080 [7:30:53<48:07:22,  7.13s/it]
 14%|█▎        | 3799/28080 [7:31:00<47:59:29,  7.12s/it]
                                                         
{'loss': 0.6415, 'learning_rate': 0.0004856090722350679, 'epoch': 1.62}

 14%|█▎        | 3799/28080 [7:31:00<47:59:29,  7.12s/it]
 14%|█▎        | 3800/28080 [7:31:07<48:01:56,  7.12s/it]
                                                         
{'loss': 0.6583, 'learning_rate': 0.00048559942841766893, 'epoch': 1.62}

 14%|█▎        | 3800/28080 [7:31:07<48:01:56,  7.12s/it]
 14%|█▎        | 3801/28080 [7:31:14<48:16:19,  7.16s/it]
                                                         
{'loss': 0.6601, 'learning_rate': 0.00048558978146586254, 'epoch': 1.62}

 14%|█▎        | 3801/28080 [7:31:14<48:16:19,  7.16s/it]
 14%|█▎        | 3802/28080 [7:31:21<48:20:24,  7.17s/it]
                                                         
{'loss': 0.6406, 'learning_rate': 0.0004855801313797772, 'epoch': 1.62}

 14%|█▎        | 3802/28080 [7:31:21<48:20:24,  7.17s/it]
 14%|█▎        | 3803/28080 [7:31:28<48:19:11,  7.17s/it]
                                                         
{'loss': 0.6547, 'learning_rate': 0.0004855704781595413, 'epoch': 1.62}

 14%|█▎        | 3803/28080 [7:31:28<48:19:11,  7.17s/it]
 14%|█▎        | 3804/28080 [7:31:35<48:17:17,  7.16s/it]
                                                         
{'loss': 0.6544, 'learning_rate': 0.0004855608218052832, 'epoch': 1.63}

 14%|█▎        | 3804/28080 [7:31:35<48:17:17,  7.16s/it]
 14%|█▎        | 3805/28080 [7:31:43<48:06:26,  7.13s/it]
                                                         
{'loss': 0.6557, 'learning_rate': 0.0004855511623171314, 'epoch': 1.63}

 14%|█▎        | 3805/28080 [7:31:43<48:06:26,  7.13s/it]
 14%|█▎        | 3806/28080 [7:31:50<48:09:03,  7.14s/it]
                                                         
{'loss': 0.6419, 'learning_rate': 0.00048554149969521433, 'epoch': 1.63}

 14%|█▎        | 3806/28080 [7:31:50<48:09:03,  7.14s/it]
 14%|█▎        | 3807/28080 [7:31:57<48:12:02,  7.15s/it]
                                                         
{'loss': 0.6428, 'learning_rate': 0.0004855318339396606, 'epoch': 1.63}

 14%|█▎        | 3807/28080 [7:31:57<48:12:02,  7.15s/it]
 14%|█▎        | 3808/28080 [7:32:04<48:21:10,  7.17s/it]
                                                         
{'loss': 0.6724, 'learning_rate': 0.0004855221650505989, 'epoch': 1.63}

 14%|█▎        | 3808/28080 [7:32:04<48:21:10,  7.17s/it]
 14%|█▎        | 3809/28080 [7:32:11<48:14:06,  7.15s/it]
                                                         
{'loss': 0.6441, 'learning_rate': 0.00048551249302815764, 'epoch': 1.63}

 14%|█▎        | 3809/28080 [7:32:11<48:14:06,  7.15s/it]
 14%|█▎        | 3810/28080 [7:32:18<48:11:28,  7.15s/it]
                                                         
{'loss': 0.6389, 'learning_rate': 0.0004855028178724656, 'epoch': 1.63}

 14%|█▎        | 3810/28080 [7:32:18<48:11:28,  7.15s/it]
 14%|█▎        | 3811/28080 [7:32:26<48:22:17,  7.18s/it]
                                                         
{'loss': 0.6598, 'learning_rate': 0.0004854931395836517, 'epoch': 1.63}

 14%|█▎        | 3811/28080 [7:32:26<48:22:17,  7.18s/it]
 14%|█▎        | 3812/28080 [7:32:33<48:14:24,  7.16s/it]
                                                         
{'loss': 0.6563, 'learning_rate': 0.00048548345816184444, 'epoch': 1.63}

 14%|█▎        | 3812/28080 [7:32:33<48:14:24,  7.16s/it]
 14%|█▎        | 3813/28080 [7:32:40<48:05:36,  7.13s/it]
                                                         
{'loss': 0.6373, 'learning_rate': 0.00048547377360717267, 'epoch': 1.63}

 14%|█▎        | 3813/28080 [7:32:40<48:05:36,  7.13s/it]
 14%|█▎        | 3814/28080 [7:32:47<48:24:04,  7.18s/it]
                                                         
{'loss': 0.6629, 'learning_rate': 0.0004854640859197653, 'epoch': 1.63}

 14%|█▎        | 3814/28080 [7:32:47<48:24:04,  7.18s/it]
 14%|█▎        | 3815/28080 [7:32:54<48:06:30,  7.14s/it]
                                                         
{'loss': 0.6673, 'learning_rate': 0.00048545439509975117, 'epoch': 1.63}

 14%|█▎        | 3815/28080 [7:32:54<48:06:30,  7.14s/it]
 14%|█▎        | 3816/28080 [7:33:01<48:11:35,  7.15s/it]
                                                         
{'loss': 0.6683, 'learning_rate': 0.0004854447011472592, 'epoch': 1.63}

 14%|█▎        | 3816/28080 [7:33:01<48:11:35,  7.15s/it]
 14%|█▎        | 3817/28080 [7:33:08<48:12:21,  7.15s/it]
                                                         
{'loss': 0.6829, 'learning_rate': 0.00048543500406241836, 'epoch': 1.63}

 14%|█▎        | 3817/28080 [7:33:08<48:12:21,  7.15s/it]
 14%|█▎        | 3818/28080 [7:33:15<47:59:27,  7.12s/it]
                                                         
{'loss': 0.6526, 'learning_rate': 0.0004854253038453578, 'epoch': 1.63}

 14%|█▎        | 3818/28080 [7:33:15<47:59:27,  7.12s/it]
 14%|█▎        | 3819/28080 [7:33:22<47:44:50,  7.09s/it]
                                                         
{'loss': 0.6599, 'learning_rate': 0.0004854156004962063, 'epoch': 1.63}

 14%|█▎        | 3819/28080 [7:33:22<47:44:50,  7.09s/it]
 14%|█▎        | 3820/28080 [7:33:30<47:47:32,  7.09s/it]
                                                         
{'loss': 0.6595, 'learning_rate': 0.0004854058940150932, 'epoch': 1.63}

 14%|█▎        | 3820/28080 [7:33:30<47:47:32,  7.09s/it]
 14%|█▎        | 3821/28080 [7:33:37<47:47:40,  7.09s/it]
                                                         
{'loss': 0.6548, 'learning_rate': 0.00048539618440214744, 'epoch': 1.63}

 14%|█▎        | 3821/28080 [7:33:37<47:47:40,  7.09s/it]
 14%|█▎        | 3822/28080 [7:33:44<47:44:29,  7.09s/it]
                                                         
{'loss': 0.6435, 'learning_rate': 0.0004853864716574984, 'epoch': 1.63}

 14%|█▎        | 3822/28080 [7:33:44<47:44:29,  7.09s/it]
 14%|█▎        | 3823/28080 [7:33:51<48:03:14,  7.13s/it]
                                                         
{'loss': 0.6384, 'learning_rate': 0.0004853767557812751, 'epoch': 1.63}

 14%|█▎        | 3823/28080 [7:33:51<48:03:14,  7.13s/it]
 14%|█▎        | 3824/28080 [7:33:58<47:59:39,  7.12s/it]
                                                         
{'loss': 0.6568, 'learning_rate': 0.00048536703677360695, 'epoch': 1.63}

 14%|█▎        | 3824/28080 [7:33:58<47:59:39,  7.12s/it]
 14%|█▎        | 3825/28080 [7:34:05<48:04:19,  7.14s/it]
                                                         
{'loss': 0.6587, 'learning_rate': 0.0004853573146346231, 'epoch': 1.63}

 14%|█▎        | 3825/28080 [7:34:05<48:04:19,  7.14s/it]
 14%|█▎        | 3826/28080 [7:34:12<48:07:04,  7.14s/it]
                                                         
{'loss': 0.6653, 'learning_rate': 0.0004853475893644531, 'epoch': 1.63}

 14%|█▎        | 3826/28080 [7:34:12<48:07:04,  7.14s/it]
 14%|█▎        | 3827/28080 [7:34:20<48:06:04,  7.14s/it]
                                                         
{'loss': 0.6492, 'learning_rate': 0.00048533786096322613, 'epoch': 1.63}

 14%|█▎        | 3827/28080 [7:34:20<48:06:04,  7.14s/it]
 14%|█▎        | 3828/28080 [7:34:27<48:00:56,  7.13s/it]
                                                         
{'loss': 0.6489, 'learning_rate': 0.00048532812943107175, 'epoch': 1.64}

 14%|█▎        | 3828/28080 [7:34:27<48:00:56,  7.13s/it]
 14%|█▎        | 3829/28080 [7:34:34<47:40:14,  7.08s/it]
                                                         
{'loss': 0.7013, 'learning_rate': 0.00048531839476811933, 'epoch': 1.64}

 14%|█▎        | 3829/28080 [7:34:34<47:40:14,  7.08s/it]
 14%|█▎        | 3830/28080 [7:34:41<47:57:50,  7.12s/it]
                                                         
{'loss': 0.6451, 'learning_rate': 0.0004853086569744985, 'epoch': 1.64}

 14%|█▎        | 3830/28080 [7:34:41<47:57:50,  7.12s/it]
 14%|█▎        | 3831/28080 [7:34:48<47:49:56,  7.10s/it]
                                                         
{'loss': 0.6616, 'learning_rate': 0.0004852989160503387, 'epoch': 1.64}

 14%|█▎        | 3831/28080 [7:34:48<47:49:56,  7.10s/it]
 14%|█▎        | 3832/28080 [7:34:55<47:56:10,  7.12s/it]
                                                         
{'loss': 0.652, 'learning_rate': 0.0004852891719957696, 'epoch': 1.64}

 14%|█▎        | 3832/28080 [7:34:55<47:56:10,  7.12s/it]
 14%|█▎        | 3833/28080 [7:35:02<48:01:56,  7.13s/it]
                                                         
{'loss': 0.6358, 'learning_rate': 0.0004852794248109208, 'epoch': 1.64}

 14%|█▎        | 3833/28080 [7:35:02<48:01:56,  7.13s/it]
 14%|█▎        | 3834/28080 [7:35:09<48:03:55,  7.14s/it]
                                                         
{'loss': 0.6502, 'learning_rate': 0.000485269674495922, 'epoch': 1.64}

 14%|█▎        | 3834/28080 [7:35:09<48:03:55,  7.14s/it]
 14%|█▎        | 3835/28080 [7:35:17<48:09:12,  7.15s/it]
                                                         
{'loss': 0.6483, 'learning_rate': 0.0004852599210509028, 'epoch': 1.64}

 14%|█▎        | 3835/28080 [7:35:17<48:09:12,  7.15s/it]
 14%|█▎        | 3836/28080 [7:35:24<48:22:28,  7.18s/it]
                                                         
{'loss': 0.6524, 'learning_rate': 0.0004852501644759931, 'epoch': 1.64}

 14%|█▎        | 3836/28080 [7:35:24<48:22:28,  7.18s/it]
 14%|█▎        | 3837/28080 [7:35:31<48:22:22,  7.18s/it]
                                                         
{'loss': 0.6551, 'learning_rate': 0.0004852404047713227, 'epoch': 1.64}

 14%|█▎        | 3837/28080 [7:35:31<48:22:22,  7.18s/it]
 14%|█▎        | 3838/28080 [7:35:38<48:15:38,  7.17s/it]
                                                         
{'loss': 0.6522, 'learning_rate': 0.0004852306419370214, 'epoch': 1.64}

 14%|█▎        | 3838/28080 [7:35:38<48:15:38,  7.17s/it]
 14%|█▎        | 3839/28080 [7:35:45<48:22:54,  7.19s/it]
                                                         
{'loss': 0.6577, 'learning_rate': 0.000485220875973219, 'epoch': 1.64}

 14%|█▎        | 3839/28080 [7:35:45<48:22:54,  7.19s/it]
 14%|█▎        | 3840/28080 [7:35:52<48:10:38,  7.16s/it]
                                                         
{'loss': 0.6617, 'learning_rate': 0.00048521110688004554, 'epoch': 1.64}

 14%|█▎        | 3840/28080 [7:35:52<48:10:38,  7.16s/it]
 14%|█▎        | 3841/28080 [7:36:00<48:03:21,  7.14s/it]
                                                         
{'loss': 0.6693, 'learning_rate': 0.000485201334657631, 'epoch': 1.64}

 14%|█▎        | 3841/28080 [7:36:00<48:03:21,  7.14s/it]
 14%|█▎        | 3842/28080 [7:36:07<47:59:16,  7.13s/it]
                                                         
{'loss': 0.6495, 'learning_rate': 0.00048519155930610533, 'epoch': 1.64}

 14%|█▎        | 3842/28080 [7:36:07<47:59:16,  7.13s/it]
 14%|█▎        | 3843/28080 [7:36:14<47:59:02,  7.13s/it]
                                                         
{'loss': 0.6382, 'learning_rate': 0.0004851817808255986, 'epoch': 1.64}

 14%|█▎        | 3843/28080 [7:36:14<47:59:02,  7.13s/it]
 14%|█▎        | 3844/28080 [7:36:21<48:13:59,  7.16s/it]
                                                         
{'loss': 0.6537, 'learning_rate': 0.0004851719992162409, 'epoch': 1.64}

 14%|█▎        | 3844/28080 [7:36:21<48:13:59,  7.16s/it]
 14%|█▎        | 3845/28080 [7:36:28<48:00:39,  7.13s/it]
                                                         
{'loss': 0.6562, 'learning_rate': 0.0004851622144781623, 'epoch': 1.64}

 14%|█▎        | 3845/28080 [7:36:28<48:00:39,  7.13s/it]
 14%|█▎        | 3846/28080 [7:36:35<48:02:15,  7.14s/it]
                                                         
{'loss': 0.6551, 'learning_rate': 0.00048515242661149307, 'epoch': 1.64}

 14%|█▎        | 3846/28080 [7:36:35<48:02:15,  7.14s/it]
 14%|█▎        | 3847/28080 [7:36:42<48:05:46,  7.15s/it]
                                                         
{'loss': 0.6659, 'learning_rate': 0.0004851426356163634, 'epoch': 1.64}

 14%|█▎        | 3847/28080 [7:36:42<48:05:46,  7.15s/it]
 14%|█▎        | 3848/28080 [7:36:50<48:20:02,  7.18s/it]
                                                         
{'loss': 0.6373, 'learning_rate': 0.0004851328414929036, 'epoch': 1.64}

 14%|█▎        | 3848/28080 [7:36:50<48:20:02,  7.18s/it]
 14%|█▎        | 3849/28080 [7:36:57<48:19:07,  7.18s/it]
                                                         
{'loss': 0.6391, 'learning_rate': 0.00048512304424124387, 'epoch': 1.64}

 14%|█▎        | 3849/28080 [7:36:57<48:19:07,  7.18s/it]
 14%|█▎        | 3850/28080 [7:37:04<48:17:02,  7.17s/it]
                                                         
{'loss': 0.6826, 'learning_rate': 0.0004851132438615146, 'epoch': 1.64}

 14%|█▎        | 3850/28080 [7:37:04<48:17:02,  7.17s/it]
 14%|█▎        | 3851/28080 [7:37:11<48:03:42,  7.14s/it]
                                                         
{'loss': 0.6523, 'learning_rate': 0.00048510344035384624, 'epoch': 1.65}

 14%|█▎        | 3851/28080 [7:37:11<48:03:42,  7.14s/it]
 14%|█▎        | 3852/28080 [7:37:18<47:54:47,  7.12s/it]
                                                         
{'loss': 0.6528, 'learning_rate': 0.00048509363371836904, 'epoch': 1.65}

 14%|█▎        | 3852/28080 [7:37:18<47:54:47,  7.12s/it]
 14%|█▎        | 3853/28080 [7:37:25<48:05:06,  7.15s/it]
                                                         
{'loss': 0.6631, 'learning_rate': 0.00048508382395521366, 'epoch': 1.65}

 14%|█▎        | 3853/28080 [7:37:25<48:05:06,  7.15s/it]
 14%|█▎        | 3854/28080 [7:37:32<48:03:40,  7.14s/it]
                                                         
{'loss': 0.6319, 'learning_rate': 0.00048507401106451047, 'epoch': 1.65}

 14%|█▎        | 3854/28080 [7:37:32<48:03:40,  7.14s/it]
 14%|█▎        | 3855/28080 [7:37:39<47:53:42,  7.12s/it]
                                                         
{'loss': 0.658, 'learning_rate': 0.0004850641950463901, 'epoch': 1.65}

 14%|█▎        | 3855/28080 [7:37:39<47:53:42,  7.12s/it]
 14%|█▎        | 3856/28080 [7:37:47<47:45:40,  7.10s/it]
                                                         
{'loss': 0.6578, 'learning_rate': 0.0004850543759009831, 'epoch': 1.65}

 14%|█▎        | 3856/28080 [7:37:47<47:45:40,  7.10s/it]
 14%|█▎        | 3857/28080 [7:37:54<47:53:08,  7.12s/it]
                                                         
{'loss': 0.6692, 'learning_rate': 0.00048504455362842014, 'epoch': 1.65}

 14%|█▎        | 3857/28080 [7:37:54<47:53:08,  7.12s/it]
 14%|█▎        | 3858/28080 [7:38:01<47:47:44,  7.10s/it]
                                                         
{'loss': 0.6609, 'learning_rate': 0.00048503472822883186, 'epoch': 1.65}

 14%|█▎        | 3858/28080 [7:38:01<47:47:44,  7.10s/it]
 14%|█▎        | 3859/28080 [7:38:08<47:53:02,  7.12s/it]
                                                         
{'loss': 0.6559, 'learning_rate': 0.00048502489970234905, 'epoch': 1.65}

 14%|█▎        | 3859/28080 [7:38:08<47:53:02,  7.12s/it]
 14%|█▎        | 3860/28080 [7:38:15<48:05:54,  7.15s/it]
                                                         
{'loss': 0.6486, 'learning_rate': 0.0004850150680491023, 'epoch': 1.65}

 14%|█▎        | 3860/28080 [7:38:15<48:05:54,  7.15s/it]
 14%|█▍        | 3861/28080 [7:38:22<48:06:15,  7.15s/it]
                                                         
{'loss': 0.6738, 'learning_rate': 0.0004850052332692226, 'epoch': 1.65}

 14%|█▍        | 3861/28080 [7:38:22<48:06:15,  7.15s/it]
 14%|█▍        | 3862/28080 [7:38:29<48:10:47,  7.16s/it]
                                                         
{'loss': 0.6623, 'learning_rate': 0.0004849953953628408, 'epoch': 1.65}

 14%|█▍        | 3862/28080 [7:38:29<48:10:47,  7.16s/it]
 14%|█▍        | 3863/28080 [7:38:37<48:07:38,  7.15s/it]
                                                         
{'loss': 0.688, 'learning_rate': 0.00048498555433008753, 'epoch': 1.65}

 14%|█▍        | 3863/28080 [7:38:37<48:07:38,  7.15s/it]
 14%|█▍        | 3864/28080 [7:38:44<48:09:49,  7.16s/it]
                                                         
{'loss': 0.6603, 'learning_rate': 0.000484975710171094, 'epoch': 1.65}

 14%|█▍        | 3864/28080 [7:38:44<48:09:49,  7.16s/it]
 14%|█▍        | 3865/28080 [7:38:51<48:05:16,  7.15s/it]
                                                         
{'loss': 0.6649, 'learning_rate': 0.000484965862885991, 'epoch': 1.65}

 14%|█▍        | 3865/28080 [7:38:51<48:05:16,  7.15s/it]
 14%|█▍        | 3866/28080 [7:38:58<48:03:31,  7.15s/it]
                                                         
{'loss': 0.702, 'learning_rate': 0.00048495601247490954, 'epoch': 1.65}

 14%|█▍        | 3866/28080 [7:38:58<48:03:31,  7.15s/it]
 14%|█▍        | 3867/28080 [7:39:05<48:04:44,  7.15s/it]
                                                         
{'loss': 0.6512, 'learning_rate': 0.00048494615893798077, 'epoch': 1.65}

 14%|█▍        | 3867/28080 [7:39:05<48:04:44,  7.15s/it]
 14%|█▍        | 3868/28080 [7:39:12<47:44:46,  7.10s/it]
                                                         
{'loss': 0.6819, 'learning_rate': 0.00048493630227533583, 'epoch': 1.65}

 14%|█▍        | 3868/28080 [7:39:12<47:44:46,  7.10s/it]
 14%|█▍        | 3869/28080 [7:39:19<47:57:21,  7.13s/it]
                                                         
{'loss': 0.6591, 'learning_rate': 0.0004849264424871056, 'epoch': 1.65}

 14%|█▍        | 3869/28080 [7:39:19<47:57:21,  7.13s/it]
 14%|█▍        | 3870/28080 [7:39:26<47:52:21,  7.12s/it]
                                                         
{'loss': 0.6521, 'learning_rate': 0.0004849165795734215, 'epoch': 1.65}

 14%|█▍        | 3870/28080 [7:39:26<47:52:21,  7.12s/it]
 14%|█▍        | 3871/28080 [7:39:33<47:36:13,  7.08s/it]
                                                         
{'loss': 0.6987, 'learning_rate': 0.00048490671353441467, 'epoch': 1.65}

 14%|█▍        | 3871/28080 [7:39:33<47:36:13,  7.08s/it]
 14%|█▍        | 3872/28080 [7:39:41<47:52:08,  7.12s/it]
                                                         
{'loss': 0.6502, 'learning_rate': 0.0004848968443702163, 'epoch': 1.65}

 14%|█▍        | 3872/28080 [7:39:41<47:52:08,  7.12s/it]
 14%|█▍        | 3873/28080 [7:39:48<47:52:37,  7.12s/it]
                                                         
{'loss': 0.637, 'learning_rate': 0.0004848869720809578, 'epoch': 1.65}

 14%|█▍        | 3873/28080 [7:39:48<47:52:37,  7.12s/it]
 14%|█▍        | 3874/28080 [7:39:55<47:57:12,  7.13s/it]
                                                         
{'loss': 0.6665, 'learning_rate': 0.0004848770966667705, 'epoch': 1.65}

 14%|█▍        | 3874/28080 [7:39:55<47:57:12,  7.13s/it]
 14%|█▍        | 3875/28080 [7:40:02<47:56:37,  7.13s/it]
                                                         
{'loss': 0.648, 'learning_rate': 0.00048486721812778563, 'epoch': 1.66}

 14%|█▍        | 3875/28080 [7:40:02<47:56:37,  7.13s/it]
 14%|█▍        | 3876/28080 [7:40:09<47:56:37,  7.13s/it]
                                                         
{'loss': 0.6514, 'learning_rate': 0.00048485733646413476, 'epoch': 1.66}

 14%|█▍        | 3876/28080 [7:40:09<47:56:37,  7.13s/it]
 14%|█▍        | 3877/28080 [7:40:16<47:59:52,  7.14s/it]
                                                         
{'loss': 0.6476, 'learning_rate': 0.00048484745167594936, 'epoch': 1.66}

 14%|█▍        | 3877/28080 [7:40:16<47:59:52,  7.14s/it]
 14%|█▍        | 3878/28080 [7:40:24<48:07:36,  7.16s/it]
                                                         
{'loss': 0.6604, 'learning_rate': 0.00048483756376336087, 'epoch': 1.66}

 14%|█▍        | 3878/28080 [7:40:24<48:07:36,  7.16s/it]
 14%|█▍        | 3879/28080 [7:40:31<48:12:01,  7.17s/it]
                                                         
{'loss': 0.6446, 'learning_rate': 0.0004848276727265008, 'epoch': 1.66}

 14%|█▍        | 3879/28080 [7:40:31<48:12:01,  7.17s/it]
 14%|█▍        | 3880/28080 [7:40:38<48:11:29,  7.17s/it]
                                                         
{'loss': 0.6513, 'learning_rate': 0.0004848177785655009, 'epoch': 1.66}

 14%|█▍        | 3880/28080 [7:40:38<48:11:29,  7.17s/it]
 14%|█▍        | 3881/28080 [7:40:45<48:08:25,  7.16s/it]
                                                         
{'loss': 0.6579, 'learning_rate': 0.00048480788128049256, 'epoch': 1.66}

 14%|█▍        | 3881/28080 [7:40:45<48:08:25,  7.16s/it]
 14%|█▍        | 3882/28080 [7:40:52<48:19:31,  7.19s/it]
                                                         
{'loss': 0.6795, 'learning_rate': 0.00048479798087160776, 'epoch': 1.66}

 14%|█▍        | 3882/28080 [7:40:52<48:19:31,  7.19s/it]
 14%|█▍        | 3883/28080 [7:41:00<48:18:50,  7.19s/it]
                                                         
{'loss': 0.6676, 'learning_rate': 0.000484788077338978, 'epoch': 1.66}

 14%|█▍        | 3883/28080 [7:41:00<48:18:50,  7.19s/it]
 14%|█▍        | 3884/28080 [7:41:07<48:12:33,  7.17s/it]
                                                         
{'loss': 0.6558, 'learning_rate': 0.00048477817068273503, 'epoch': 1.66}

 14%|█▍        | 3884/28080 [7:41:07<48:12:33,  7.17s/it]
 14%|█▍        | 3885/28080 [7:41:14<48:10:29,  7.17s/it]
                                                         
{'loss': 0.6706, 'learning_rate': 0.00048476826090301073, 'epoch': 1.66}

 14%|█▍        | 3885/28080 [7:41:14<48:10:29,  7.17s/it]
 14%|█▍        | 3886/28080 [7:41:21<48:14:33,  7.18s/it]
                                                         
{'loss': 0.6659, 'learning_rate': 0.00048475834799993704, 'epoch': 1.66}

 14%|█▍        | 3886/28080 [7:41:21<48:14:33,  7.18s/it]
 14%|█▍        | 3887/28080 [7:41:28<48:10:25,  7.17s/it]
                                                         
{'loss': 0.6478, 'learning_rate': 0.00048474843197364556, 'epoch': 1.66}

 14%|█▍        | 3887/28080 [7:41:28<48:10:25,  7.17s/it]
 14%|█▍        | 3888/28080 [7:41:35<48:15:11,  7.18s/it]
                                                         
{'loss': 0.6379, 'learning_rate': 0.0004847385128242684, 'epoch': 1.66}

 14%|█▍        | 3888/28080 [7:41:35<48:15:11,  7.18s/it]
 14%|█▍        | 3889/28080 [7:41:43<48:06:35,  7.16s/it]
                                                         
{'loss': 0.6472, 'learning_rate': 0.0004847285905519375, 'epoch': 1.66}

 14%|█▍        | 3889/28080 [7:41:43<48:06:35,  7.16s/it]
 14%|█▍        | 3890/28080 [7:41:50<48:05:28,  7.16s/it]
                                                         
{'loss': 0.6617, 'learning_rate': 0.00048471866515678493, 'epoch': 1.66}

 14%|█▍        | 3890/28080 [7:41:50<48:05:28,  7.16s/it]
 14%|█▍        | 3891/28080 [7:41:57<48:07:52,  7.16s/it]
                                                         
{'loss': 0.6604, 'learning_rate': 0.00048470873663894253, 'epoch': 1.66}

 14%|█▍        | 3891/28080 [7:41:57<48:07:52,  7.16s/it]
 14%|█▍        | 3892/28080 [7:42:04<48:14:30,  7.18s/it]
                                                         
{'loss': 0.6405, 'learning_rate': 0.0004846988049985427, 'epoch': 1.66}

 14%|█▍        | 3892/28080 [7:42:04<48:14:30,  7.18s/it]
 14%|█▍        | 3893/28080 [7:42:11<48:12:21,  7.17s/it]
                                                         
{'loss': 0.6789, 'learning_rate': 0.0004846888702357173, 'epoch': 1.66}

 14%|█▍        | 3893/28080 [7:42:11<48:12:21,  7.17s/it]
 14%|█▍        | 3894/28080 [7:42:19<48:30:00,  7.22s/it]
                                                         
{'loss': 0.6296, 'learning_rate': 0.0004846789323505986, 'epoch': 1.66}

 14%|█▍        | 3894/28080 [7:42:19<48:30:00,  7.22s/it]
 14%|█▍        | 3895/28080 [7:42:26<48:22:32,  7.20s/it]
                                                         
{'loss': 0.664, 'learning_rate': 0.00048466899134331874, 'epoch': 1.66}

 14%|█▍        | 3895/28080 [7:42:26<48:22:32,  7.20s/it]
 14%|█▍        | 3896/28080 [7:42:33<48:18:24,  7.19s/it]
                                                         
{'loss': 0.6801, 'learning_rate': 0.0004846590472140101, 'epoch': 1.66}

 14%|█▍        | 3896/28080 [7:42:33<48:18:24,  7.19s/it]
 14%|█▍        | 3897/28080 [7:42:40<48:18:11,  7.19s/it]
                                                         
{'loss': 0.6119, 'learning_rate': 0.00048464909996280493, 'epoch': 1.66}

 14%|█▍        | 3897/28080 [7:42:40<48:18:11,  7.19s/it]
 14%|█▍        | 3898/28080 [7:42:47<48:14:00,  7.18s/it]
                                                         
{'loss': 0.6493, 'learning_rate': 0.00048463914958983556, 'epoch': 1.67}

 14%|█▍        | 3898/28080 [7:42:47<48:14:00,  7.18s/it]
 14%|█▍        | 3899/28080 [7:42:54<48:15:17,  7.18s/it]
                                                         
{'loss': 0.6355, 'learning_rate': 0.0004846291960952344, 'epoch': 1.67}

 14%|█▍        | 3899/28080 [7:42:54<48:15:17,  7.18s/it]
 14%|█▍        | 3900/28080 [7:43:02<48:11:30,  7.17s/it]
                                                         
{'loss': 0.6651, 'learning_rate': 0.0004846192394791338, 'epoch': 1.67}

 14%|█▍        | 3900/28080 [7:43:02<48:11:30,  7.17s/it]
 14%|█▍        | 3901/28080 [7:43:09<47:56:42,  7.14s/it]
                                                         
{'loss': 0.6609, 'learning_rate': 0.0004846092797416663, 'epoch': 1.67}

 14%|█▍        | 3901/28080 [7:43:09<47:56:42,  7.14s/it]
 14%|█▍        | 3902/28080 [7:43:16<47:59:24,  7.15s/it]
                                                         
{'loss': 0.6556, 'learning_rate': 0.0004845993168829643, 'epoch': 1.67}

 14%|█▍        | 3902/28080 [7:43:16<47:59:24,  7.15s/it]
 14%|█▍        | 3903/28080 [7:43:23<48:00:30,  7.15s/it]
                                                         
{'loss': 0.6601, 'learning_rate': 0.0004845893509031605, 'epoch': 1.67}

 14%|█▍        | 3903/28080 [7:43:23<48:00:30,  7.15s/it]
 14%|█▍        | 3904/28080 [7:43:30<47:51:51,  7.13s/it]
                                                         
{'loss': 0.6938, 'learning_rate': 0.0004845793818023873, 'epoch': 1.67}

 14%|█▍        | 3904/28080 [7:43:30<47:51:51,  7.13s/it]
 14%|█▍        | 3905/28080 [7:43:37<47:49:08,  7.12s/it]
                                                         
{'loss': 0.6706, 'learning_rate': 0.0004845694095807775, 'epoch': 1.67}

 14%|█▍        | 3905/28080 [7:43:37<47:49:08,  7.12s/it]
 14%|█▍        | 3906/28080 [7:43:44<47:46:24,  7.11s/it]
                                                         
{'loss': 0.6561, 'learning_rate': 0.0004845594342384637, 'epoch': 1.67}

 14%|█▍        | 3906/28080 [7:43:44<47:46:24,  7.11s/it]
 14%|█▍        | 3907/28080 [7:43:51<47:40:46,  7.10s/it]
                                                         
{'loss': 0.6511, 'learning_rate': 0.0004845494557755785, 'epoch': 1.67}

 14%|█▍        | 3907/28080 [7:43:51<47:40:46,  7.10s/it]
 14%|█▍        | 3908/28080 [7:43:58<47:49:15,  7.12s/it]
                                                         
{'loss': 0.6504, 'learning_rate': 0.0004845394741922549, 'epoch': 1.67}

 14%|█▍        | 3908/28080 [7:43:58<47:49:15,  7.12s/it]
 14%|█▍        | 3909/28080 [7:44:06<47:50:14,  7.12s/it]
                                                         
{'loss': 0.6363, 'learning_rate': 0.0004845294894886255, 'epoch': 1.67}

 14%|█▍        | 3909/28080 [7:44:06<47:50:14,  7.12s/it]
 14%|█▍        | 3910/28080 [7:44:13<47:57:29,  7.14s/it]
                                                         
{'loss': 0.6669, 'learning_rate': 0.00048451950166482317, 'epoch': 1.67}

 14%|█▍        | 3910/28080 [7:44:13<47:57:29,  7.14s/it]
 14%|█▍        | 3911/28080 [7:44:20<47:58:07,  7.15s/it]
                                                         
{'loss': 0.6726, 'learning_rate': 0.0004845095107209808, 'epoch': 1.67}

 14%|█▍        | 3911/28080 [7:44:20<47:58:07,  7.15s/it]
 14%|█▍        | 3912/28080 [7:44:27<47:49:08,  7.12s/it]
                                                         
{'loss': 0.6493, 'learning_rate': 0.0004844995166572314, 'epoch': 1.67}

 14%|█▍        | 3912/28080 [7:44:27<47:49:08,  7.12s/it]
 14%|█▍        | 3913/28080 [7:44:34<47:40:49,  7.10s/it]
                                                         
{'loss': 0.6755, 'learning_rate': 0.00048448951947370776, 'epoch': 1.67}

 14%|█▍        | 3913/28080 [7:44:34<47:40:49,  7.10s/it]
 14%|█▍        | 3914/28080 [7:44:41<47:45:04,  7.11s/it]
                                                         
{'loss': 0.6564, 'learning_rate': 0.00048447951917054304, 'epoch': 1.67}

 14%|█▍        | 3914/28080 [7:44:41<47:45:04,  7.11s/it]
 14%|█▍        | 3915/28080 [7:44:48<47:44:09,  7.11s/it]
                                                         
{'loss': 0.6498, 'learning_rate': 0.00048446951574787026, 'epoch': 1.67}

 14%|█▍        | 3915/28080 [7:44:48<47:44:09,  7.11s/it]
 14%|█▍        | 3916/28080 [7:44:55<47:51:54,  7.13s/it]
                                                         
{'loss': 0.6463, 'learning_rate': 0.0004844595092058224, 'epoch': 1.67}

 14%|█▍        | 3916/28080 [7:44:55<47:51:54,  7.13s/it]
 14%|█▍        | 3917/28080 [7:45:03<47:39:52,  7.10s/it]
                                                         
{'loss': 0.6584, 'learning_rate': 0.0004844494995445326, 'epoch': 1.67}

 14%|█▍        | 3917/28080 [7:45:03<47:39:52,  7.10s/it]
 14%|█▍        | 3918/28080 [7:45:10<47:38:25,  7.10s/it]
                                                         
{'loss': 0.6394, 'learning_rate': 0.0004844394867641341, 'epoch': 1.67}

 14%|█▍        | 3918/28080 [7:45:10<47:38:25,  7.10s/it]
 14%|█▍        | 3919/28080 [7:45:17<47:47:36,  7.12s/it]
                                                         
{'loss': 0.6438, 'learning_rate': 0.0004844294708647601, 'epoch': 1.67}

 14%|█▍        | 3919/28080 [7:45:17<47:47:36,  7.12s/it]
 14%|█▍        | 3920/28080 [7:45:24<47:45:45,  7.12s/it]
                                                         
{'loss': 0.6619, 'learning_rate': 0.0004844194518465439, 'epoch': 1.67}

 14%|█▍        | 3920/28080 [7:45:24<47:45:45,  7.12s/it]
 14%|█▍        | 3921/28080 [7:45:31<47:46:52,  7.12s/it]
                                                         
{'loss': 0.6411, 'learning_rate': 0.0004844094297096187, 'epoch': 1.68}

 14%|█▍        | 3921/28080 [7:45:31<47:46:52,  7.12s/it]
 14%|█▍        | 3922/28080 [7:45:38<47:53:53,  7.14s/it]
                                                         
{'loss': 0.6627, 'learning_rate': 0.00048439940445411776, 'epoch': 1.68}

 14%|█▍        | 3922/28080 [7:45:38<47:53:53,  7.14s/it]
 14%|█▍        | 3923/28080 [7:45:45<47:52:18,  7.13s/it]
                                                         
{'loss': 0.6627, 'learning_rate': 0.00048438937608017465, 'epoch': 1.68}

 14%|█▍        | 3923/28080 [7:45:45<47:52:18,  7.13s/it]
 14%|█▍        | 3924/28080 [7:45:52<47:56:19,  7.14s/it]
                                                         
{'loss': 0.6517, 'learning_rate': 0.00048437934458792265, 'epoch': 1.68}

 14%|█▍        | 3924/28080 [7:45:52<47:56:19,  7.14s/it]
 14%|█▍        | 3925/28080 [7:46:00<47:51:38,  7.13s/it]
                                                         
{'loss': 0.6462, 'learning_rate': 0.00048436930997749534, 'epoch': 1.68}

 14%|█▍        | 3925/28080 [7:46:00<47:51:38,  7.13s/it]
 14%|█▍        | 3926/28080 [7:46:07<47:57:25,  7.15s/it]
                                                         
{'loss': 0.6612, 'learning_rate': 0.0004843592722490261, 'epoch': 1.68}

 14%|█▍        | 3926/28080 [7:46:07<47:57:25,  7.15s/it]
 14%|█▍        | 3927/28080 [7:46:14<47:58:00,  7.15s/it]
                                                         
{'loss': 0.6567, 'learning_rate': 0.00048434923140264853, 'epoch': 1.68}

 14%|█▍        | 3927/28080 [7:46:14<47:58:00,  7.15s/it]
 14%|█▍        | 3928/28080 [7:46:21<47:58:36,  7.15s/it]
                                                         
{'loss': 0.678, 'learning_rate': 0.0004843391874384962, 'epoch': 1.68}

 14%|█▍        | 3928/28080 [7:46:21<47:58:36,  7.15s/it]
 14%|█▍        | 3929/28080 [7:46:28<47:57:38,  7.15s/it]
                                                         
{'loss': 0.6696, 'learning_rate': 0.00048432914035670275, 'epoch': 1.68}

 14%|█▍        | 3929/28080 [7:46:28<47:57:38,  7.15s/it]
 14%|█▍        | 3930/28080 [7:46:35<47:58:08,  7.15s/it]
                                                         
{'loss': 0.6381, 'learning_rate': 0.0004843190901574018, 'epoch': 1.68}

 14%|█▍        | 3930/28080 [7:46:35<47:58:08,  7.15s/it]
 14%|█▍        | 3931/28080 [7:46:43<47:57:43,  7.15s/it]
                                                         
{'loss': 0.6562, 'learning_rate': 0.0004843090368407271, 'epoch': 1.68}

 14%|█▍        | 3931/28080 [7:46:43<47:57:43,  7.15s/it]
 14%|█▍        | 3932/28080 [7:46:50<47:51:10,  7.13s/it]
                                                         
{'loss': 0.6606, 'learning_rate': 0.0004842989804068124, 'epoch': 1.68}

 14%|█▍        | 3932/28080 [7:46:50<47:51:10,  7.13s/it]
 14%|█▍        | 3933/28080 [7:46:57<48:00:00,  7.16s/it]
                                                         
{'loss': 0.6638, 'learning_rate': 0.00048428892085579145, 'epoch': 1.68}

 14%|█▍        | 3933/28080 [7:46:57<48:00:00,  7.16s/it]
 14%|█▍        | 3934/28080 [7:47:04<47:56:04,  7.15s/it]
                                                         
{'loss': 0.6452, 'learning_rate': 0.00048427885818779816, 'epoch': 1.68}

 14%|█▍        | 3934/28080 [7:47:04<47:56:04,  7.15s/it]
 14%|█▍        | 3935/28080 [7:47:11<47:36:00,  7.10s/it]
                                                         
{'loss': 0.6815, 'learning_rate': 0.00048426879240296626, 'epoch': 1.68}

 14%|█▍        | 3935/28080 [7:47:11<47:36:00,  7.10s/it]
 14%|█▍        | 3936/28080 [7:47:18<47:32:27,  7.09s/it]
                                                         
{'loss': 0.6605, 'learning_rate': 0.0004842587235014299, 'epoch': 1.68}

 14%|█▍        | 3936/28080 [7:47:18<47:32:27,  7.09s/it]
 14%|█▍        | 3937/28080 [7:47:25<47:48:17,  7.13s/it]
                                                         
{'loss': 0.6509, 'learning_rate': 0.00048424865148332275, 'epoch': 1.68}

 14%|█▍        | 3937/28080 [7:47:25<47:48:17,  7.13s/it]
 14%|█▍        | 3938/28080 [7:47:32<47:50:15,  7.13s/it]
                                                         
{'loss': 0.6741, 'learning_rate': 0.00048423857634877904, 'epoch': 1.68}

 14%|█▍        | 3938/28080 [7:47:32<47:50:15,  7.13s/it]
 14%|█▍        | 3939/28080 [7:47:40<47:51:49,  7.14s/it]
                                                         
{'loss': 0.6602, 'learning_rate': 0.0004842284980979327, 'epoch': 1.68}

 14%|█▍        | 3939/28080 [7:47:40<47:51:49,  7.14s/it]
 14%|█▍        | 3940/28080 [7:47:47<48:02:25,  7.16s/it]
                                                         
{'loss': 0.6606, 'learning_rate': 0.0004842184167309178, 'epoch': 1.68}

 14%|█▍        | 3940/28080 [7:47:47<48:02:25,  7.16s/it]
 14%|█▍        | 3941/28080 [7:47:54<47:46:51,  7.13s/it]
                                                         
{'loss': 0.6752, 'learning_rate': 0.00048420833224786856, 'epoch': 1.68}

 14%|█▍        | 3941/28080 [7:47:54<47:46:51,  7.13s/it]
 14%|█▍        | 3942/28080 [7:48:01<47:47:56,  7.13s/it]
                                                         
{'loss': 0.6542, 'learning_rate': 0.00048419824464891904, 'epoch': 1.68}

 14%|█▍        | 3942/28080 [7:48:01<47:47:56,  7.13s/it]
 14%|█▍        | 3943/28080 [7:48:08<47:48:58,  7.13s/it]
                                                         
{'loss': 0.6748, 'learning_rate': 0.0004841881539342035, 'epoch': 1.68}

 14%|█▍        | 3943/28080 [7:48:08<47:48:58,  7.13s/it]
 14%|█▍        | 3944/28080 [7:48:15<47:42:57,  7.12s/it]
                                                         
{'loss': 0.6736, 'learning_rate': 0.0004841780601038562, 'epoch': 1.68}

 14%|█▍        | 3944/28080 [7:48:15<47:42:57,  7.12s/it]
 14%|█▍        | 3945/28080 [7:48:22<47:49:29,  7.13s/it]
                                                         
{'loss': 0.6408, 'learning_rate': 0.0004841679631580114, 'epoch': 1.69}

 14%|█▍        | 3945/28080 [7:48:22<47:49:29,  7.13s/it]
 14%|█▍        | 3946/28080 [7:48:30<48:01:21,  7.16s/it]
                                                         
{'loss': 0.6744, 'learning_rate': 0.0004841578630968033, 'epoch': 1.69}

 14%|█▍        | 3946/28080 [7:48:30<48:01:21,  7.16s/it]
 14%|█▍        | 3947/28080 [7:48:37<47:54:14,  7.15s/it]
                                                         
{'loss': 0.6583, 'learning_rate': 0.0004841477599203665, 'epoch': 1.69}

 14%|█▍        | 3947/28080 [7:48:37<47:54:14,  7.15s/it]
 14%|█▍        | 3948/28080 [7:48:44<47:54:00,  7.15s/it]
                                                         
{'loss': 0.6549, 'learning_rate': 0.00048413765362883535, 'epoch': 1.69}

 14%|█▍        | 3948/28080 [7:48:44<47:54:00,  7.15s/it]
 14%|█▍        | 3949/28080 [7:48:51<47:50:19,  7.14s/it]
                                                         
{'loss': 0.6626, 'learning_rate': 0.00048412754422234416, 'epoch': 1.69}

 14%|█▍        | 3949/28080 [7:48:51<47:50:19,  7.14s/it]
 14%|█▍        | 3950/28080 [7:48:58<47:54:50,  7.15s/it]
                                                         
{'loss': 0.6639, 'learning_rate': 0.00048411743170102763, 'epoch': 1.69}

 14%|█▍        | 3950/28080 [7:48:58<47:54:50,  7.15s/it]
 14%|█▍        | 3951/28080 [7:49:05<47:57:48,  7.16s/it]
                                                         
{'loss': 0.6525, 'learning_rate': 0.00048410731606502014, 'epoch': 1.69}

 14%|█▍        | 3951/28080 [7:49:05<47:57:48,  7.16s/it]
 14%|█▍        | 3952/28080 [7:49:12<47:57:06,  7.15s/it]
                                                         
{'loss': 0.6534, 'learning_rate': 0.00048409719731445634, 'epoch': 1.69}

 14%|█▍        | 3952/28080 [7:49:12<47:57:06,  7.15s/it]
 14%|█▍        | 3953/28080 [7:49:19<47:49:08,  7.14s/it]
                                                         
{'loss': 0.6521, 'learning_rate': 0.00048408707544947085, 'epoch': 1.69}

 14%|█▍        | 3953/28080 [7:49:20<47:49:08,  7.14s/it]
 14%|█▍        | 3954/28080 [7:49:27<47:53:18,  7.15s/it]
                                                         
{'loss': 0.6485, 'learning_rate': 0.00048407695047019827, 'epoch': 1.69}

 14%|█▍        | 3954/28080 [7:49:27<47:53:18,  7.15s/it]
 14%|█▍        | 3955/28080 [7:49:34<47:44:45,  7.12s/it]
                                                         
{'loss': 0.6611, 'learning_rate': 0.00048406682237677335, 'epoch': 1.69}

 14%|█▍        | 3955/28080 [7:49:34<47:44:45,  7.12s/it]
 14%|█▍        | 3956/28080 [7:49:41<47:51:26,  7.14s/it]
                                                         
{'loss': 0.66, 'learning_rate': 0.0004840566911693309, 'epoch': 1.69}

 14%|█▍        | 3956/28080 [7:49:41<47:51:26,  7.14s/it]
 14%|█▍        | 3957/28080 [7:49:48<47:46:51,  7.13s/it]
                                                         
{'loss': 0.6638, 'learning_rate': 0.0004840465568480056, 'epoch': 1.69}

 14%|█▍        | 3957/28080 [7:49:48<47:46:51,  7.13s/it]
 14%|█▍        | 3958/28080 [7:49:55<47:37:40,  7.11s/it]
                                                         
{'loss': 0.673, 'learning_rate': 0.0004840364194129323, 'epoch': 1.69}

 14%|█▍        | 3958/28080 [7:49:55<47:37:40,  7.11s/it]
 14%|█▍        | 3959/28080 [7:50:02<47:50:01,  7.14s/it]
                                                         
{'loss': 0.655, 'learning_rate': 0.0004840262788642459, 'epoch': 1.69}

 14%|█▍        | 3959/28080 [7:50:02<47:50:01,  7.14s/it]
 14%|█▍        | 3960/28080 [7:50:09<47:53:16,  7.15s/it]
                                                         
{'loss': 0.6472, 'learning_rate': 0.00048401613520208123, 'epoch': 1.69}

 14%|█▍        | 3960/28080 [7:50:09<47:53:16,  7.15s/it]
 14%|█▍        | 3961/28080 [7:50:17<47:57:01,  7.16s/it]
                                                         
{'loss': 0.6617, 'learning_rate': 0.0004840059884265734, 'epoch': 1.69}

 14%|█▍        | 3961/28080 [7:50:17<47:57:01,  7.16s/it]
 14%|█▍        | 3962/28080 [7:50:24<47:51:59,  7.14s/it]
                                                         
{'loss': 0.655, 'learning_rate': 0.00048399583853785724, 'epoch': 1.69}

 14%|█▍        | 3962/28080 [7:50:24<47:51:59,  7.14s/it]
 14%|█▍        | 3963/28080 [7:50:31<47:44:58,  7.13s/it]
                                                         
{'loss': 0.648, 'learning_rate': 0.00048398568553606784, 'epoch': 1.69}

 14%|█▍        | 3963/28080 [7:50:31<47:44:58,  7.13s/it]
 14%|█▍        | 3964/28080 [7:50:38<47:45:26,  7.13s/it]
                                                         
{'loss': 0.6661, 'learning_rate': 0.00048397552942134025, 'epoch': 1.69}

 14%|█▍        | 3964/28080 [7:50:38<47:45:26,  7.13s/it]
 14%|█▍        | 3965/28080 [7:50:45<48:04:32,  7.18s/it]
                                                         
{'loss': 0.6626, 'learning_rate': 0.0004839653701938097, 'epoch': 1.69}

 14%|█▍        | 3965/28080 [7:50:45<48:04:32,  7.18s/it]
 14%|█▍        | 3966/28080 [7:50:52<48:02:00,  7.17s/it]
                                                         
{'loss': 0.639, 'learning_rate': 0.0004839552078536112, 'epoch': 1.69}

 14%|█▍        | 3966/28080 [7:50:52<48:02:00,  7.17s/it]
 14%|█▍        | 3967/28080 [7:51:00<47:58:32,  7.16s/it]
                                                         
{'loss': 0.6634, 'learning_rate': 0.0004839450424008801, 'epoch': 1.69}

 14%|█▍        | 3967/28080 [7:51:00<47:58:32,  7.16s/it]
 14%|█▍        | 3968/28080 [7:51:07<48:05:51,  7.18s/it]
                                                         
{'loss': 0.6358, 'learning_rate': 0.0004839348738357516, 'epoch': 1.7}

 14%|█▍        | 3968/28080 [7:51:07<48:05:51,  7.18s/it]
 14%|█▍        | 3969/28080 [7:51:14<47:59:47,  7.17s/it]
                                                         
{'loss': 0.6382, 'learning_rate': 0.0004839247021583608, 'epoch': 1.7}

 14%|█▍        | 3969/28080 [7:51:14<47:59:47,  7.17s/it]
 14%|█▍        | 3970/28080 [7:51:21<47:43:30,  7.13s/it]
                                                         
{'loss': 0.6636, 'learning_rate': 0.0004839145273688432, 'epoch': 1.7}

 14%|█▍        | 3970/28080 [7:51:21<47:43:30,  7.13s/it]
 14%|█▍        | 3971/28080 [7:51:28<47:39:35,  7.12s/it]
                                                         
{'loss': 0.6737, 'learning_rate': 0.0004839043494673342, 'epoch': 1.7}

 14%|█▍        | 3971/28080 [7:51:28<47:39:35,  7.12s/it]
 14%|█▍        | 3972/28080 [7:51:35<47:46:43,  7.13s/it]
                                                         
{'loss': 0.6395, 'learning_rate': 0.0004838941684539691, 'epoch': 1.7}

 14%|█▍        | 3972/28080 [7:51:35<47:46:43,  7.13s/it]
 14%|█▍        | 3973/28080 [7:51:42<47:44:46,  7.13s/it]
                                                         
{'loss': 0.6497, 'learning_rate': 0.0004838839843288834, 'epoch': 1.7}

 14%|█▍        | 3973/28080 [7:51:42<47:44:46,  7.13s/it]
 14%|█▍        | 3974/28080 [7:51:49<47:46:11,  7.13s/it]
                                                         
{'loss': 0.6521, 'learning_rate': 0.0004838737970922125, 'epoch': 1.7}

 14%|█▍        | 3974/28080 [7:51:49<47:46:11,  7.13s/it]
 14%|█▍        | 3975/28080 [7:51:57<47:38:22,  7.11s/it]
                                                         
{'loss': 0.6485, 'learning_rate': 0.0004838636067440921, 'epoch': 1.7}

 14%|█▍        | 3975/28080 [7:51:57<47:38:22,  7.11s/it]
 14%|█▍        | 3976/28080 [7:52:03<47:16:27,  7.06s/it]
                                                         
{'loss': 0.66, 'learning_rate': 0.0004838534132846576, 'epoch': 1.7}

 14%|█▍        | 3976/28080 [7:52:03<47:16:27,  7.06s/it]
 14%|█▍        | 3977/28080 [7:52:11<47:22:32,  7.08s/it]
                                                         
{'loss': 0.6854, 'learning_rate': 0.00048384321671404474, 'epoch': 1.7}

 14%|█▍        | 3977/28080 [7:52:11<47:22:32,  7.08s/it]
 14%|█▍        | 3978/28080 [7:52:18<47:14:17,  7.06s/it]
                                                         
{'loss': 0.6359, 'learning_rate': 0.00048383301703238914, 'epoch': 1.7}

 14%|█▍        | 3978/28080 [7:52:18<47:14:17,  7.06s/it]
 14%|█▍        | 3979/28080 [7:52:25<47:15:55,  7.06s/it]
                                                         
{'loss': 0.6521, 'learning_rate': 0.0004838228142398264, 'epoch': 1.7}

 14%|█▍        | 3979/28080 [7:52:25<47:15:55,  7.06s/it]
 14%|█▍        | 3980/28080 [7:52:32<47:10:38,  7.05s/it]
                                                         
{'loss': 0.668, 'learning_rate': 0.00048381260833649237, 'epoch': 1.7}

 14%|█▍        | 3980/28080 [7:52:32<47:10:38,  7.05s/it]
 14%|█▍        | 3981/28080 [7:52:39<47:21:28,  7.07s/it]
                                                         
{'loss': 0.6701, 'learning_rate': 0.0004838023993225228, 'epoch': 1.7}

 14%|█▍        | 3981/28080 [7:52:39<47:21:28,  7.07s/it]
 14%|█▍        | 3982/28080 [7:52:46<47:42:27,  7.13s/it]
                                                         
{'loss': 0.6607, 'learning_rate': 0.00048379218719805353, 'epoch': 1.7}

 14%|█▍        | 3982/28080 [7:52:46<47:42:27,  7.13s/it]
 14%|█▍        | 3983/28080 [7:52:53<47:40:44,  7.12s/it]
                                                         
{'loss': 0.6579, 'learning_rate': 0.0004837819719632204, 'epoch': 1.7}

 14%|█▍        | 3983/28080 [7:52:53<47:40:44,  7.12s/it]
 14%|█▍        | 3984/28080 [7:53:01<48:03:11,  7.18s/it]
                                                         
{'loss': 0.6497, 'learning_rate': 0.0004837717536181593, 'epoch': 1.7}

 14%|█▍        | 3984/28080 [7:53:01<48:03:11,  7.18s/it]
 14%|█▍        | 3985/28080 [7:53:08<48:00:52,  7.17s/it]
                                                         
{'loss': 0.6623, 'learning_rate': 0.0004837615321630062, 'epoch': 1.7}

 14%|█▍        | 3985/28080 [7:53:08<48:00:52,  7.17s/it]
 14%|█▍        | 3986/28080 [7:53:15<47:56:56,  7.16s/it]
                                                         
{'loss': 0.6425, 'learning_rate': 0.00048375130759789706, 'epoch': 1.7}

 14%|█▍        | 3986/28080 [7:53:15<47:56:56,  7.16s/it]
 14%|█▍        | 3987/28080 [7:53:22<47:59:17,  7.17s/it]
                                                         
{'loss': 0.6501, 'learning_rate': 0.0004837410799229679, 'epoch': 1.7}

 14%|█▍        | 3987/28080 [7:53:22<47:59:17,  7.17s/it]
 14%|█▍        | 3988/28080 [7:53:29<47:58:40,  7.17s/it]
                                                         
{'loss': 0.664, 'learning_rate': 0.0004837308491383548, 'epoch': 1.7}

 14%|█▍        | 3988/28080 [7:53:29<47:58:40,  7.17s/it]
 14%|█▍        | 3989/28080 [7:53:36<48:11:01,  7.20s/it]
                                                         
{'loss': 0.6659, 'learning_rate': 0.0004837206152441939, 'epoch': 1.7}

 14%|█▍        | 3989/28080 [7:53:36<48:11:01,  7.20s/it]
 14%|█▍        | 3990/28080 [7:53:44<48:08:01,  7.19s/it]
                                                         
{'loss': 0.6696, 'learning_rate': 0.0004837103782406214, 'epoch': 1.7}

 14%|█▍        | 3990/28080 [7:53:44<48:08:01,  7.19s/it]
 14%|█▍        | 3991/28080 [7:53:51<48:12:22,  7.20s/it]
                                                         
{'loss': 0.6484, 'learning_rate': 0.0004837001381277733, 'epoch': 1.7}

 14%|█▍        | 3991/28080 [7:53:51<48:12:22,  7.20s/it]
 14%|█▍        | 3992/28080 [7:53:58<48:11:07,  7.20s/it]
                                                         
{'loss': 0.6452, 'learning_rate': 0.00048368989490578607, 'epoch': 1.71}

 14%|█▍        | 3992/28080 [7:53:58<48:11:07,  7.20s/it]
 14%|█▍        | 3993/28080 [7:54:05<47:57:25,  7.17s/it]
                                                         
{'loss': 0.6533, 'learning_rate': 0.0004836796485747958, 'epoch': 1.71}

 14%|█▍        | 3993/28080 [7:54:05<47:57:25,  7.17s/it]
 14%|█▍        | 3994/28080 [7:54:12<47:55:19,  7.16s/it]
                                                         
{'loss': 0.6493, 'learning_rate': 0.0004836693991349389, 'epoch': 1.71}

 14%|█▍        | 3994/28080 [7:54:12<47:55:19,  7.16s/it]
 14%|█▍        | 3995/28080 [7:54:20<48:16:05,  7.21s/it]
                                                         
{'loss': 0.6478, 'learning_rate': 0.00048365914658635167, 'epoch': 1.71}

 14%|█▍        | 3995/28080 [7:54:20<48:16:05,  7.21s/it]
 14%|█▍        | 3996/28080 [7:54:27<48:09:29,  7.20s/it]
                                                         
{'loss': 0.6765, 'learning_rate': 0.00048364889092917065, 'epoch': 1.71}

 14%|█▍        | 3996/28080 [7:54:27<48:09:29,  7.20s/it]
 14%|█▍        | 3997/28080 [7:54:34<47:53:09,  7.16s/it]
                                                         
{'loss': 0.6656, 'learning_rate': 0.00048363863216353207, 'epoch': 1.71}

 14%|█▍        | 3997/28080 [7:54:34<47:53:09,  7.16s/it]
 14%|█▍        | 3998/28080 [7:54:41<47:53:15,  7.16s/it]
                                                         
{'loss': 0.6872, 'learning_rate': 0.00048362837028957255, 'epoch': 1.71}

 14%|█▍        | 3998/28080 [7:54:41<47:53:15,  7.16s/it]
 14%|█▍        | 3999/28080 [7:54:48<47:50:02,  7.15s/it]
                                                         
{'loss': 0.6598, 'learning_rate': 0.00048361810530742863, 'epoch': 1.71}

 14%|█▍        | 3999/28080 [7:54:48<47:50:02,  7.15s/it]
 14%|█▍        | 4000/28080 [7:54:55<47:52:37,  7.16s/it]
                                                         
{'loss': 0.6547, 'learning_rate': 0.0004836078372172368, 'epoch': 1.71}

 14%|█▍        | 4000/28080 [7:54:55<47:52:37,  7.16s/it]
 14%|█▍        | 4001/28080 [7:55:02<47:39:34,  7.13s/it]
                                                         
{'loss': 0.6679, 'learning_rate': 0.00048359756601913363, 'epoch': 1.71}

 14%|█▍        | 4001/28080 [7:55:02<47:39:34,  7.13s/it]
 14%|█▍        | 4002/28080 [7:55:10<47:54:29,  7.16s/it]
                                                         
{'loss': 0.6445, 'learning_rate': 0.00048358729171325593, 'epoch': 1.71}

 14%|█▍        | 4002/28080 [7:55:10<47:54:29,  7.16s/it]
 14%|█▍        | 4003/28080 [7:55:17<47:59:23,  7.18s/it]
                                                         
{'loss': 0.6511, 'learning_rate': 0.0004835770142997403, 'epoch': 1.71}

 14%|█▍        | 4003/28080 [7:55:17<47:59:23,  7.18s/it]
 14%|█▍        | 4004/28080 [7:55:24<48:00:53,  7.18s/it]
                                                         
{'loss': 0.6686, 'learning_rate': 0.0004835667337787234, 'epoch': 1.71}

 14%|█▍        | 4004/28080 [7:55:24<48:00:53,  7.18s/it]
 14%|█▍        | 4005/28080 [7:55:31<47:58:45,  7.17s/it]
                                                         
{'loss': 0.6555, 'learning_rate': 0.00048355645015034214, 'epoch': 1.71}

 14%|█▍        | 4005/28080 [7:55:31<47:58:45,  7.17s/it]
 14%|█▍        | 4006/28080 [7:55:38<48:03:27,  7.19s/it]
                                                         
{'loss': 0.6683, 'learning_rate': 0.00048354616341473314, 'epoch': 1.71}

 14%|█▍        | 4006/28080 [7:55:38<48:03:27,  7.19s/it]
 14%|█▍        | 4007/28080 [7:55:45<47:50:18,  7.15s/it]
                                                         
{'loss': 0.6635, 'learning_rate': 0.00048353587357203345, 'epoch': 1.71}

 14%|█▍        | 4007/28080 [7:55:45<47:50:18,  7.15s/it]
 14%|█▍        | 4008/28080 [7:55:53<47:57:18,  7.17s/it]
                                                         
{'loss': 0.6528, 'learning_rate': 0.0004835255806223798, 'epoch': 1.71}

 14%|█▍        | 4008/28080 [7:55:53<47:57:18,  7.17s/it]
 14%|█▍        | 4009/28080 [7:56:00<47:51:21,  7.16s/it]
                                                         
{'loss': 0.661, 'learning_rate': 0.0004835152845659093, 'epoch': 1.71}

 14%|█▍        | 4009/28080 [7:56:00<47:51:21,  7.16s/it]
 14%|█▍        | 4010/28080 [7:56:07<47:58:53,  7.18s/it]
                                                         
{'loss': 0.6571, 'learning_rate': 0.0004835049854027589, 'epoch': 1.71}

 14%|█▍        | 4010/28080 [7:56:07<47:58:53,  7.18s/it]
 14%|█▍        | 4011/28080 [7:56:14<47:50:31,  7.16s/it]
                                                         
{'loss': 0.6654, 'learning_rate': 0.0004834946831330654, 'epoch': 1.71}

 14%|█▍        | 4011/28080 [7:56:14<47:50:31,  7.16s/it]
 14%|█▍        | 4012/28080 [7:56:21<47:57:53,  7.17s/it]
                                                         
{'loss': 0.6722, 'learning_rate': 0.0004834843777569662, 'epoch': 1.71}

 14%|█▍        | 4012/28080 [7:56:21<47:57:53,  7.17s/it]
 14%|█▍        | 4013/28080 [7:56:28<47:43:44,  7.14s/it]
                                                         
{'loss': 0.6473, 'learning_rate': 0.0004834740692745981, 'epoch': 1.71}

 14%|█▍        | 4013/28080 [7:56:28<47:43:44,  7.14s/it]
 14%|█▍        | 4014/28080 [7:56:36<47:43:42,  7.14s/it]
                                                         
{'loss': 0.6473, 'learning_rate': 0.0004834637576860984, 'epoch': 1.71}

 14%|█▍        | 4014/28080 [7:56:36<47:43:42,  7.14s/it]
 14%|█▍        | 4015/28080 [7:56:43<47:45:09,  7.14s/it]
                                                         
{'loss': 0.6544, 'learning_rate': 0.00048345344299160434, 'epoch': 1.72}

 14%|█▍        | 4015/28080 [7:56:43<47:45:09,  7.14s/it]
 14%|█▍        | 4016/28080 [7:56:50<48:00:53,  7.18s/it]
                                                         
{'loss': 0.6606, 'learning_rate': 0.00048344312519125294, 'epoch': 1.72}

 14%|█▍        | 4016/28080 [7:56:50<48:00:53,  7.18s/it]
 14%|█▍        | 4017/28080 [7:56:57<47:55:54,  7.17s/it]
                                                         
{'loss': 0.6563, 'learning_rate': 0.00048343280428518164, 'epoch': 1.72}

 14%|█▍        | 4017/28080 [7:56:57<47:55:54,  7.17s/it]
 14%|█▍        | 4018/28080 [7:57:04<47:56:50,  7.17s/it]
                                                         
{'loss': 0.6507, 'learning_rate': 0.00048342248027352777, 'epoch': 1.72}

 14%|█▍        | 4018/28080 [7:57:04<47:56:50,  7.17s/it]
 14%|█▍        | 4019/28080 [7:57:11<47:56:30,  7.17s/it]
                                                         
{'loss': 0.6558, 'learning_rate': 0.0004834121531564285, 'epoch': 1.72}

 14%|█▍        | 4019/28080 [7:57:11<47:56:30,  7.17s/it]
 14%|█▍        | 4020/28080 [7:57:19<47:52:00,  7.16s/it]
                                                         
{'loss': 0.6749, 'learning_rate': 0.00048340182293402133, 'epoch': 1.72}

 14%|█▍        | 4020/28080 [7:57:19<47:52:00,  7.16s/it]
 14%|█▍        | 4021/28080 [7:57:26<47:51:40,  7.16s/it]
                                                         
{'loss': 0.6532, 'learning_rate': 0.0004833914896064437, 'epoch': 1.72}

 14%|█▍        | 4021/28080 [7:57:26<47:51:40,  7.16s/it]
 14%|█▍        | 4022/28080 [7:57:33<47:59:23,  7.18s/it]
                                                         
{'loss': 0.6255, 'learning_rate': 0.0004833811531738331, 'epoch': 1.72}

 14%|█▍        | 4022/28080 [7:57:33<47:59:23,  7.18s/it]
 14%|█▍        | 4023/28080 [7:57:40<47:28:03,  7.10s/it]
                                                         
{'loss': 0.6552, 'learning_rate': 0.00048337081363632704, 'epoch': 1.72}

 14%|█▍        | 4023/28080 [7:57:40<47:28:03,  7.10s/it]
 14%|█▍        | 4024/28080 [7:57:47<47:23:54,  7.09s/it]
                                                         
{'loss': 0.6703, 'learning_rate': 0.0004833604709940631, 'epoch': 1.72}

 14%|█▍        | 4024/28080 [7:57:47<47:23:54,  7.09s/it]
 14%|█▍        | 4025/28080 [7:57:54<47:30:14,  7.11s/it]
                                                         
{'loss': 0.6534, 'learning_rate': 0.0004833501252471788, 'epoch': 1.72}

 14%|█▍        | 4025/28080 [7:57:54<47:30:14,  7.11s/it]
 14%|█▍        | 4026/28080 [7:58:01<47:40:32,  7.14s/it]
                                                         
{'loss': 0.6552, 'learning_rate': 0.0004833397763958118, 'epoch': 1.72}

 14%|█▍        | 4026/28080 [7:58:01<47:40:32,  7.14s/it]
 14%|█▍        | 4027/28080 [7:58:08<47:44:29,  7.15s/it]
                                                         
{'loss': 0.6432, 'learning_rate': 0.00048332942444009977, 'epoch': 1.72}

 14%|█▍        | 4027/28080 [7:58:08<47:44:29,  7.15s/it]
 14%|█▍        | 4028/28080 [7:58:16<47:43:58,  7.14s/it]
                                                         
{'loss': 0.666, 'learning_rate': 0.00048331906938018054, 'epoch': 1.72}

 14%|█▍        | 4028/28080 [7:58:16<47:43:58,  7.14s/it]
 14%|█▍        | 4029/28080 [7:58:23<47:28:52,  7.11s/it]
                                                         
{'loss': 0.6457, 'learning_rate': 0.0004833087112161917, 'epoch': 1.72}

 14%|█▍        | 4029/28080 [7:58:23<47:28:52,  7.11s/it]
 14%|█▍        | 4030/28080 [7:58:30<47:28:17,  7.11s/it]
                                                         
{'loss': 0.6296, 'learning_rate': 0.00048329834994827127, 'epoch': 1.72}

 14%|█▍        | 4030/28080 [7:58:30<47:28:17,  7.11s/it]
 14%|█▍        | 4031/28080 [7:58:37<47:39:29,  7.13s/it]
                                                         
{'loss': 0.6495, 'learning_rate': 0.00048328798557655683, 'epoch': 1.72}

 14%|█▍        | 4031/28080 [7:58:37<47:39:29,  7.13s/it]
 14%|█▍        | 4032/28080 [7:58:44<47:39:27,  7.13s/it]
                                                         
{'loss': 0.6495, 'learning_rate': 0.00048327761810118655, 'epoch': 1.72}

 14%|█▍        | 4032/28080 [7:58:44<47:39:27,  7.13s/it]
 14%|█▍        | 4033/28080 [7:58:51<47:46:30,  7.15s/it]
                                                         
{'loss': 0.6481, 'learning_rate': 0.00048326724752229813, 'epoch': 1.72}

 14%|█▍        | 4033/28080 [7:58:51<47:46:30,  7.15s/it]
 14%|█▍        | 4034/28080 [7:58:58<47:49:00,  7.16s/it]
                                                         
{'loss': 0.6593, 'learning_rate': 0.00048325687384002963, 'epoch': 1.72}

 14%|█▍        | 4034/28080 [7:58:58<47:49:00,  7.16s/it]
 14%|█▍        | 4035/28080 [7:59:06<47:45:45,  7.15s/it]
                                                         
{'loss': 0.6592, 'learning_rate': 0.0004832464970545191, 'epoch': 1.72}

 14%|█▍        | 4035/28080 [7:59:06<47:45:45,  7.15s/it]
 14%|█▍        | 4036/28080 [7:59:13<47:54:00,  7.17s/it]
                                                         
{'loss': 0.6681, 'learning_rate': 0.00048323611716590453, 'epoch': 1.72}

 14%|█▍        | 4036/28080 [7:59:13<47:54:00,  7.17s/it]
 14%|█▍        | 4037/28080 [7:59:20<47:46:23,  7.15s/it]
                                                         
{'loss': 0.6737, 'learning_rate': 0.00048322573417432403, 'epoch': 1.72}

 14%|█▍        | 4037/28080 [7:59:20<47:46:23,  7.15s/it]
 14%|█▍        | 4038/28080 [7:59:27<47:53:58,  7.17s/it]
                                                         
{'loss': 0.6439, 'learning_rate': 0.00048321534807991575, 'epoch': 1.72}

 14%|█▍        | 4038/28080 [7:59:27<47:53:58,  7.17s/it]
 14%|█▍        | 4039/28080 [7:59:34<47:56:12,  7.18s/it]
                                                         
{'loss': 0.637, 'learning_rate': 0.0004832049588828179, 'epoch': 1.73}

 14%|█▍        | 4039/28080 [7:59:34<47:56:12,  7.18s/it]
 14%|█▍        | 4040/28080 [7:59:41<47:52:56,  7.17s/it]
                                                         
{'loss': 0.6532, 'learning_rate': 0.0004831945665831686, 'epoch': 1.73}

 14%|█▍        | 4040/28080 [7:59:41<47:52:56,  7.17s/it]
 14%|█▍        | 4041/28080 [7:59:49<47:51:02,  7.17s/it]
                                                         
{'loss': 0.6704, 'learning_rate': 0.0004831841711811062, 'epoch': 1.73}

 14%|█▍        | 4041/28080 [7:59:49<47:51:02,  7.17s/it]
 14%|█▍        | 4042/28080 [7:59:56<47:37:25,  7.13s/it]
                                                         
{'loss': 0.651, 'learning_rate': 0.00048317377267676897, 'epoch': 1.73}

 14%|█▍        | 4042/28080 [7:59:56<47:37:25,  7.13s/it]
 14%|█▍        | 4043/28080 [8:00:03<47:49:35,  7.16s/it]
                                                         
{'loss': 0.6347, 'learning_rate': 0.0004831633710702952, 'epoch': 1.73}

 14%|█▍        | 4043/28080 [8:00:03<47:49:35,  7.16s/it]
 14%|█▍        | 4044/28080 [8:00:10<47:52:59,  7.17s/it]
                                                         
{'loss': 0.6566, 'learning_rate': 0.0004831529663618234, 'epoch': 1.73}

 14%|█▍        | 4044/28080 [8:00:10<47:52:59,  7.17s/it]
 14%|█▍        | 4045/28080 [8:00:17<48:02:29,  7.20s/it]
                                                         
{'loss': 0.6415, 'learning_rate': 0.00048314255855149183, 'epoch': 1.73}

 14%|█▍        | 4045/28080 [8:00:17<48:02:29,  7.20s/it]
 14%|█▍        | 4046/28080 [8:00:25<47:58:02,  7.18s/it]
                                                         
{'loss': 0.6446, 'learning_rate': 0.0004831321476394391, 'epoch': 1.73}

 14%|█▍        | 4046/28080 [8:00:25<47:58:02,  7.18s/it]
 14%|█▍        | 4047/28080 [8:00:32<47:47:04,  7.16s/it]
                                                         
{'loss': 0.6723, 'learning_rate': 0.0004831217336258036, 'epoch': 1.73}

 14%|█▍        | 4047/28080 [8:00:32<47:47:04,  7.16s/it]
 14%|█▍        | 4048/28080 [8:00:39<47:46:47,  7.16s/it]
                                                         
{'loss': 0.6396, 'learning_rate': 0.0004831113165107239, 'epoch': 1.73}

 14%|█▍        | 4048/28080 [8:00:39<47:46:47,  7.16s/it]
 14%|█▍        | 4049/28080 [8:00:46<47:45:22,  7.15s/it]
                                                         
{'loss': 0.655, 'learning_rate': 0.00048310089629433875, 'epoch': 1.73}

 14%|█▍        | 4049/28080 [8:00:46<47:45:22,  7.15s/it]
 14%|█▍        | 4050/28080 [8:00:53<47:45:25,  7.15s/it]
                                                         
{'loss': 0.662, 'learning_rate': 0.0004830904729767865, 'epoch': 1.73}

 14%|█▍        | 4050/28080 [8:00:53<47:45:25,  7.15s/it]
 14%|█▍        | 4051/28080 [8:01:00<47:39:48,  7.14s/it]
                                                         
{'loss': 0.6732, 'learning_rate': 0.0004830800465582061, 'epoch': 1.73}

 14%|█▍        | 4051/28080 [8:01:00<47:39:48,  7.14s/it]
 14%|█▍        | 4052/28080 [8:01:07<47:34:48,  7.13s/it]
                                                         
{'loss': 0.6527, 'learning_rate': 0.0004830696170387361, 'epoch': 1.73}

 14%|█▍        | 4052/28080 [8:01:07<47:34:48,  7.13s/it]
 14%|█▍        | 4053/28080 [8:01:15<47:49:14,  7.17s/it]
                                                         
{'loss': 0.6488, 'learning_rate': 0.0004830591844185153, 'epoch': 1.73}

 14%|█▍        | 4053/28080 [8:01:15<47:49:14,  7.17s/it]
 14%|█▍        | 4054/28080 [8:01:22<47:46:48,  7.16s/it]
                                                         
{'loss': 0.6554, 'learning_rate': 0.00048304874869768244, 'epoch': 1.73}

 14%|█▍        | 4054/28080 [8:01:22<47:46:48,  7.16s/it]
 14%|█▍        | 4055/28080 [8:01:29<47:56:50,  7.18s/it]
                                                         
{'loss': 0.6471, 'learning_rate': 0.00048303830987637644, 'epoch': 1.73}

 14%|█▍        | 4055/28080 [8:01:29<47:56:50,  7.18s/it]
 14%|█▍        | 4056/28080 [8:01:36<47:35:30,  7.13s/it]
                                                         
{'loss': 0.6606, 'learning_rate': 0.00048302786795473615, 'epoch': 1.73}

 14%|█▍        | 4056/28080 [8:01:36<47:35:30,  7.13s/it]
 14%|█▍        | 4057/28080 [8:01:43<47:40:58,  7.15s/it]
                                                         
{'loss': 0.6518, 'learning_rate': 0.0004830174229329004, 'epoch': 1.73}

 14%|█▍        | 4057/28080 [8:01:43<47:40:58,  7.15s/it]
 14%|█▍        | 4058/28080 [8:01:50<47:47:31,  7.16s/it]
                                                         
{'loss': 0.6494, 'learning_rate': 0.0004830069748110083, 'epoch': 1.73}

 14%|█▍        | 4058/28080 [8:01:50<47:47:31,  7.16s/it]
 14%|█▍        | 4059/28080 [8:01:57<47:47:31,  7.16s/it]
                                                         
{'loss': 0.6566, 'learning_rate': 0.00048299652358919877, 'epoch': 1.73}

 14%|█▍        | 4059/28080 [8:01:57<47:47:31,  7.16s/it]
 14%|█▍        | 4060/28080 [8:02:05<47:37:37,  7.14s/it]
                                                         
{'loss': 0.6539, 'learning_rate': 0.0004829860692676108, 'epoch': 1.73}

 14%|█▍        | 4060/28080 [8:02:05<47:37:37,  7.14s/it]
 14%|█▍        | 4061/28080 [8:02:12<47:24:44,  7.11s/it]
                                                         
{'loss': 0.6594, 'learning_rate': 0.00048297561184638363, 'epoch': 1.73}

 14%|█▍        | 4061/28080 [8:02:12<47:24:44,  7.11s/it]
 14%|█▍        | 4062/28080 [8:02:19<47:39:16,  7.14s/it]
                                                         
{'loss': 0.6623, 'learning_rate': 0.0004829651513256563, 'epoch': 1.74}

 14%|█▍        | 4062/28080 [8:02:19<47:39:16,  7.14s/it]
 14%|█▍        | 4063/28080 [8:02:26<47:35:48,  7.13s/it]
                                                         
{'loss': 0.6624, 'learning_rate': 0.0004829546877055679, 'epoch': 1.74}

 14%|█▍        | 4063/28080 [8:02:26<47:35:48,  7.13s/it]
 14%|█▍        | 4064/28080 [8:02:33<47:39:13,  7.14s/it]
                                                         
{'loss': 0.6552, 'learning_rate': 0.00048294422098625774, 'epoch': 1.74}

 14%|█▍        | 4064/28080 [8:02:33<47:39:13,  7.14s/it]
 14%|█▍        | 4065/28080 [8:02:40<47:33:19,  7.13s/it]
                                                         
{'loss': 0.663, 'learning_rate': 0.000482933751167865, 'epoch': 1.74}

 14%|█▍        | 4065/28080 [8:02:40<47:33:19,  7.13s/it]
 14%|█▍        | 4066/28080 [8:02:47<47:35:32,  7.13s/it]
                                                         
{'loss': 0.6706, 'learning_rate': 0.0004829232782505291, 'epoch': 1.74}

 14%|█▍        | 4066/28080 [8:02:47<47:35:32,  7.13s/it]
 14%|█▍        | 4067/28080 [8:02:55<47:46:03,  7.16s/it]
                                                         
{'loss': 0.6623, 'learning_rate': 0.00048291280223438916, 'epoch': 1.74}

 14%|█▍        | 4067/28080 [8:02:55<47:46:03,  7.16s/it]
 14%|█▍        | 4068/28080 [8:03:02<47:45:07,  7.16s/it]
                                                         
{'loss': 0.6599, 'learning_rate': 0.0004829023231195847, 'epoch': 1.74}

 14%|█▍        | 4068/28080 [8:03:02<47:45:07,  7.16s/it]
 14%|█▍        | 4069/28080 [8:03:09<47:44:29,  7.16s/it]
                                                         
{'loss': 0.6727, 'learning_rate': 0.00048289184090625516, 'epoch': 1.74}

 14%|█▍        | 4069/28080 [8:03:09<47:44:29,  7.16s/it]
 14%|█▍        | 4070/28080 [8:03:16<47:44:45,  7.16s/it]
                                                         
{'loss': 0.6445, 'learning_rate': 0.0004828813555945398, 'epoch': 1.74}

 14%|█▍        | 4070/28080 [8:03:16<47:44:45,  7.16s/it]
 14%|█▍        | 4071/28080 [8:03:23<47:45:46,  7.16s/it]
                                                         
{'loss': 0.6583, 'learning_rate': 0.0004828708671845784, 'epoch': 1.74}

 14%|█▍        | 4071/28080 [8:03:23<47:45:46,  7.16s/it]
 15%|█▍        | 4072/28080 [8:03:30<47:46:03,  7.16s/it]
                                                         
{'loss': 0.6605, 'learning_rate': 0.0004828603756765103, 'epoch': 1.74}

 15%|█▍        | 4072/28080 [8:03:30<47:46:03,  7.16s/it]
 15%|█▍        | 4073/28080 [8:03:37<47:41:37,  7.15s/it]
                                                         
{'loss': 0.6573, 'learning_rate': 0.00048284988107047513, 'epoch': 1.74}

 15%|█▍        | 4073/28080 [8:03:37<47:41:37,  7.15s/it]
 15%|█▍        | 4074/28080 [8:03:45<47:31:46,  7.13s/it]
                                                         
{'loss': 0.652, 'learning_rate': 0.0004828393833666125, 'epoch': 1.74}

 15%|█▍        | 4074/28080 [8:03:45<47:31:46,  7.13s/it]
 15%|█▍        | 4075/28080 [8:03:52<47:17:15,  7.09s/it]
                                                         
{'loss': 0.6744, 'learning_rate': 0.0004828288825650621, 'epoch': 1.74}

 15%|█▍        | 4075/28080 [8:03:52<47:17:15,  7.09s/it]
 15%|█▍        | 4076/28080 [8:03:59<47:34:31,  7.14s/it]
                                                         
{'loss': 0.6528, 'learning_rate': 0.00048281837866596364, 'epoch': 1.74}

 15%|█▍        | 4076/28080 [8:03:59<47:34:31,  7.14s/it]
 15%|█▍        | 4077/28080 [8:04:06<47:25:10,  7.11s/it]
                                                         
{'loss': 0.6338, 'learning_rate': 0.0004828078716694568, 'epoch': 1.74}

 15%|█▍        | 4077/28080 [8:04:06<47:25:10,  7.11s/it]
 15%|█▍        | 4078/28080 [8:04:13<47:23:57,  7.11s/it]
                                                         
{'loss': 0.6546, 'learning_rate': 0.0004827973615756814, 'epoch': 1.74}

 15%|█▍        | 4078/28080 [8:04:13<47:23:57,  7.11s/it]
 15%|█▍        | 4079/28080 [8:04:20<47:28:57,  7.12s/it]
                                                         
{'loss': 0.6872, 'learning_rate': 0.0004827868483847773, 'epoch': 1.74}

 15%|█▍        | 4079/28080 [8:04:20<47:28:57,  7.12s/it]
 15%|█▍        | 4080/28080 [8:04:27<47:29:58,  7.12s/it]
                                                         
{'loss': 0.652, 'learning_rate': 0.00048277633209688425, 'epoch': 1.74}

 15%|█▍        | 4080/28080 [8:04:27<47:29:58,  7.12s/it]
 15%|█▍        | 4081/28080 [8:04:34<47:33:46,  7.13s/it]
                                                         
{'loss': 0.6472, 'learning_rate': 0.00048276581271214234, 'epoch': 1.74}

 15%|█▍        | 4081/28080 [8:04:34<47:33:46,  7.13s/it]
 15%|█▍        | 4082/28080 [8:04:42<47:33:01,  7.13s/it]
                                                         
{'loss': 0.648, 'learning_rate': 0.0004827552902306914, 'epoch': 1.74}

 15%|█▍        | 4082/28080 [8:04:42<47:33:01,  7.13s/it]
 15%|█▍        | 4083/28080 [8:04:49<47:27:26,  7.12s/it]
                                                         
{'loss': 0.6566, 'learning_rate': 0.0004827447646526714, 'epoch': 1.74}

 15%|█▍        | 4083/28080 [8:04:49<47:27:26,  7.12s/it]
 15%|█▍        | 4084/28080 [8:04:56<47:28:45,  7.12s/it]
                                                         
{'loss': 0.6542, 'learning_rate': 0.00048273423597822244, 'epoch': 1.74}

 15%|█▍        | 4084/28080 [8:04:56<47:28:45,  7.12s/it]
 15%|█▍        | 4085/28080 [8:05:03<47:37:23,  7.14s/it]
                                                         
{'loss': 0.6417, 'learning_rate': 0.0004827237042074846, 'epoch': 1.75}

 15%|█▍        | 4085/28080 [8:05:03<47:37:23,  7.14s/it]
 15%|█▍        | 4086/28080 [8:05:10<47:36:56,  7.14s/it]
                                                         
{'loss': 0.649, 'learning_rate': 0.0004827131693405979, 'epoch': 1.75}

 15%|█▍        | 4086/28080 [8:05:10<47:36:56,  7.14s/it]
 15%|█▍        | 4087/28080 [8:05:17<47:35:10,  7.14s/it]
                                                         
{'loss': 0.6529, 'learning_rate': 0.0004827026313777026, 'epoch': 1.75}

 15%|█▍        | 4087/28080 [8:05:17<47:35:10,  7.14s/it]
 15%|█▍        | 4088/28080 [8:05:24<47:44:45,  7.16s/it]
                                                         
{'loss': 0.6528, 'learning_rate': 0.00048269209031893886, 'epoch': 1.75}

 15%|█▍        | 4088/28080 [8:05:24<47:44:45,  7.16s/it]
 15%|█▍        | 4089/28080 [8:05:32<47:45:01,  7.17s/it]
                                                         
{'loss': 0.6702, 'learning_rate': 0.00048268154616444694, 'epoch': 1.75}

 15%|█▍        | 4089/28080 [8:05:32<47:45:01,  7.17s/it]
 15%|█▍        | 4090/28080 [8:05:39<47:43:31,  7.16s/it]
                                                         
{'loss': 0.6497, 'learning_rate': 0.000482670998914367, 'epoch': 1.75}

 15%|█▍        | 4090/28080 [8:05:39<47:43:31,  7.16s/it]
 15%|█▍        | 4091/28080 [8:05:46<47:33:28,  7.14s/it]
                                                         
{'loss': 0.6702, 'learning_rate': 0.0004826604485688395, 'epoch': 1.75}

 15%|█▍        | 4091/28080 [8:05:46<47:33:28,  7.14s/it]
 15%|█▍        | 4092/28080 [8:05:53<47:27:35,  7.12s/it]
                                                         
{'loss': 0.6602, 'learning_rate': 0.0004826498951280048, 'epoch': 1.75}

 15%|█▍        | 4092/28080 [8:05:53<47:27:35,  7.12s/it]
 15%|█▍        | 4093/28080 [8:06:00<47:27:21,  7.12s/it]
                                                         
{'loss': 0.6616, 'learning_rate': 0.0004826393385920032, 'epoch': 1.75}

 15%|█▍        | 4093/28080 [8:06:00<47:27:21,  7.12s/it]
 15%|█▍        | 4094/28080 [8:06:07<47:33:44,  7.14s/it]
                                                         
{'loss': 0.6558, 'learning_rate': 0.00048262877896097523, 'epoch': 1.75}

 15%|█▍        | 4094/28080 [8:06:07<47:33:44,  7.14s/it]
 15%|█▍        | 4095/28080 [8:06:14<47:30:27,  7.13s/it]
                                                         
{'loss': 0.6679, 'learning_rate': 0.0004826182162350613, 'epoch': 1.75}

 15%|█▍        | 4095/28080 [8:06:14<47:30:27,  7.13s/it]
 15%|█▍        | 4096/28080 [8:06:22<47:38:33,  7.15s/it]
                                                         
{'loss': 0.6561, 'learning_rate': 0.00048260765041440205, 'epoch': 1.75}

 15%|█▍        | 4096/28080 [8:06:22<47:38:33,  7.15s/it]
 15%|█▍        | 4097/28080 [8:06:29<47:41:48,  7.16s/it]
                                                         
{'loss': 0.6387, 'learning_rate': 0.0004825970814991379, 'epoch': 1.75}

 15%|█▍        | 4097/28080 [8:06:29<47:41:48,  7.16s/it]
 15%|█▍        | 4098/28080 [8:06:36<47:41:39,  7.16s/it]
                                                         
{'loss': 0.6543, 'learning_rate': 0.0004825865094894096, 'epoch': 1.75}

 15%|█▍        | 4098/28080 [8:06:36<47:41:39,  7.16s/it]
 15%|█▍        | 4099/28080 [8:06:43<47:34:07,  7.14s/it]
                                                         
{'loss': 0.6637, 'learning_rate': 0.0004825759343853577, 'epoch': 1.75}

 15%|█▍        | 4099/28080 [8:06:43<47:34:07,  7.14s/it]
 15%|█▍        | 4100/28080 [8:06:50<47:27:41,  7.13s/it]
                                                         
{'loss': 0.6809, 'learning_rate': 0.00048256535618712305, 'epoch': 1.75}

 15%|█▍        | 4100/28080 [8:06:50<47:27:41,  7.13s/it]
 15%|█▍        | 4101/28080 [8:06:57<47:29:34,  7.13s/it]
                                                         
{'loss': 0.6542, 'learning_rate': 0.0004825547748948461, 'epoch': 1.75}

 15%|█▍        | 4101/28080 [8:06:57<47:29:34,  7.13s/it]
 15%|█▍        | 4102/28080 [8:07:04<47:24:54,  7.12s/it]
                                                         
{'loss': 0.6461, 'learning_rate': 0.0004825441905086679, 'epoch': 1.75}

 15%|█▍        | 4102/28080 [8:07:04<47:24:54,  7.12s/it]
 15%|█▍        | 4103/28080 [8:07:11<47:18:45,  7.10s/it]
                                                         
{'loss': 0.6776, 'learning_rate': 0.00048253360302872905, 'epoch': 1.75}

 15%|█▍        | 4103/28080 [8:07:11<47:18:45,  7.10s/it]
 15%|█▍        | 4104/28080 [8:07:19<47:25:47,  7.12s/it]
                                                         
{'loss': 0.6625, 'learning_rate': 0.0004825230124551706, 'epoch': 1.75}

 15%|█▍        | 4104/28080 [8:07:19<47:25:47,  7.12s/it]
 15%|█▍        | 4105/28080 [8:07:26<47:40:52,  7.16s/it]
                                                         
{'loss': 0.6473, 'learning_rate': 0.00048251241878813323, 'epoch': 1.75}

 15%|█▍        | 4105/28080 [8:07:26<47:40:52,  7.16s/it]
 15%|█▍        | 4106/28080 [8:07:33<47:38:19,  7.15s/it]
                                                         
{'loss': 0.6677, 'learning_rate': 0.00048250182202775807, 'epoch': 1.75}

 15%|█▍        | 4106/28080 [8:07:33<47:38:19,  7.15s/it]
 15%|█▍        | 4107/28080 [8:07:40<47:36:17,  7.15s/it]
                                                         
{'loss': 0.6434, 'learning_rate': 0.00048249122217418604, 'epoch': 1.75}

 15%|█▍        | 4107/28080 [8:07:40<47:36:17,  7.15s/it]
 15%|█▍        | 4108/28080 [8:07:47<47:45:47,  7.17s/it]
                                                         
{'loss': 0.6449, 'learning_rate': 0.00048248061922755815, 'epoch': 1.75}

 15%|█▍        | 4108/28080 [8:07:47<47:45:47,  7.17s/it]
 15%|█▍        | 4109/28080 [8:07:54<47:42:36,  7.17s/it]
                                                         
{'loss': 0.6496, 'learning_rate': 0.00048247001318801544, 'epoch': 1.76}

 15%|█▍        | 4109/28080 [8:07:54<47:42:36,  7.17s/it]
 15%|█▍        | 4110/28080 [8:08:02<47:37:32,  7.15s/it]
                                                         
{'loss': 0.6508, 'learning_rate': 0.00048245940405569897, 'epoch': 1.76}

 15%|█▍        | 4110/28080 [8:08:02<47:37:32,  7.15s/it]
 15%|█▍        | 4111/28080 [8:08:09<48:06:59,  7.23s/it]
                                                         
{'loss': 0.6834, 'learning_rate': 0.00048244879183075, 'epoch': 1.76}

 15%|█▍        | 4111/28080 [8:08:09<48:06:59,  7.23s/it]
 15%|█▍        | 4112/28080 [8:08:16<47:56:12,  7.20s/it]
                                                         
{'loss': 0.6636, 'learning_rate': 0.0004824381765133097, 'epoch': 1.76}

 15%|█▍        | 4112/28080 [8:08:16<47:56:12,  7.20s/it]
 15%|█▍        | 4113/28080 [8:08:23<47:51:47,  7.19s/it]
                                                         
{'loss': 0.6664, 'learning_rate': 0.00048242755810351924, 'epoch': 1.76}

 15%|█▍        | 4113/28080 [8:08:23<47:51:47,  7.19s/it]
 15%|█▍        | 4114/28080 [8:08:30<47:51:01,  7.19s/it]
                                                         
{'loss': 0.663, 'learning_rate': 0.00048241693660151986, 'epoch': 1.76}

 15%|█▍        | 4114/28080 [8:08:30<47:51:01,  7.19s/it]
 15%|█▍        | 4115/28080 [8:08:38<47:48:35,  7.18s/it]
                                                         
{'loss': 0.6397, 'learning_rate': 0.00048240631200745286, 'epoch': 1.76}

 15%|█▍        | 4115/28080 [8:08:38<47:48:35,  7.18s/it]
 15%|█▍        | 4116/28080 [8:08:45<47:48:28,  7.18s/it]
                                                         
{'loss': 0.6509, 'learning_rate': 0.00048239568432145973, 'epoch': 1.76}

 15%|█▍        | 4116/28080 [8:08:45<47:48:28,  7.18s/it]
 15%|█▍        | 4117/28080 [8:08:52<47:37:08,  7.15s/it]
                                                         
{'loss': 0.6619, 'learning_rate': 0.0004823850535436818, 'epoch': 1.76}

 15%|█▍        | 4117/28080 [8:08:52<47:37:08,  7.15s/it]
 15%|█▍        | 4118/28080 [8:08:59<47:34:53,  7.15s/it]
                                                         
{'loss': 0.6705, 'learning_rate': 0.0004823744196742604, 'epoch': 1.76}

 15%|█▍        | 4118/28080 [8:08:59<47:34:53,  7.15s/it]
 15%|█▍        | 4119/28080 [8:09:06<47:40:41,  7.16s/it]
                                                         
{'loss': 0.665, 'learning_rate': 0.00048236378271333705, 'epoch': 1.76}

 15%|█▍        | 4119/28080 [8:09:06<47:40:41,  7.16s/it]
 15%|█▍        | 4120/28080 [8:09:13<47:25:40,  7.13s/it]
                                                         
{'loss': 0.6628, 'learning_rate': 0.00048235314266105336, 'epoch': 1.76}

 15%|█▍        | 4120/28080 [8:09:13<47:25:40,  7.13s/it]
 15%|█▍        | 4121/28080 [8:09:20<47:20:09,  7.11s/it]
                                                         
{'loss': 0.6785, 'learning_rate': 0.0004823424995175507, 'epoch': 1.76}

 15%|█▍        | 4121/28080 [8:09:20<47:20:09,  7.11s/it]
 15%|█▍        | 4122/28080 [8:09:28<47:36:49,  7.15s/it]
                                                         
{'loss': 0.648, 'learning_rate': 0.00048233185328297093, 'epoch': 1.76}

 15%|█▍        | 4122/28080 [8:09:28<47:36:49,  7.15s/it]
 15%|█▍        | 4123/28080 [8:09:35<47:21:48,  7.12s/it]
                                                         
{'loss': 0.6602, 'learning_rate': 0.00048232120395745544, 'epoch': 1.76}

 15%|█▍        | 4123/28080 [8:09:35<47:21:48,  7.12s/it]
 15%|█▍        | 4124/28080 [8:09:42<47:30:21,  7.14s/it]
                                                         
{'loss': 0.6514, 'learning_rate': 0.000482310551541146, 'epoch': 1.76}

 15%|█▍        | 4124/28080 [8:09:42<47:30:21,  7.14s/it]
 15%|█▍        | 4125/28080 [8:09:49<47:48:42,  7.19s/it]
                                                         
{'loss': 0.6643, 'learning_rate': 0.0004822998960341844, 'epoch': 1.76}

 15%|█▍        | 4125/28080 [8:09:49<47:48:42,  7.19s/it]
 15%|█▍        | 4126/28080 [8:09:56<47:38:00,  7.16s/it]
                                                         
{'loss': 0.6465, 'learning_rate': 0.0004822892374367123, 'epoch': 1.76}

 15%|█▍        | 4126/28080 [8:09:56<47:38:00,  7.16s/it]
 15%|█▍        | 4127/28080 [8:10:03<47:34:42,  7.15s/it]
                                                         
{'loss': 0.6662, 'learning_rate': 0.0004822785757488715, 'epoch': 1.76}

 15%|█▍        | 4127/28080 [8:10:03<47:34:42,  7.15s/it]
 15%|█▍        | 4128/28080 [8:10:10<47:24:14,  7.12s/it]
                                                         
{'loss': 0.663, 'learning_rate': 0.00048226791097080393, 'epoch': 1.76}

 15%|█▍        | 4128/28080 [8:10:10<47:24:14,  7.12s/it]
 15%|█▍        | 4129/28080 [8:10:18<47:27:58,  7.13s/it]
                                                         
{'loss': 0.6451, 'learning_rate': 0.0004822572431026514, 'epoch': 1.76}

 15%|█▍        | 4129/28080 [8:10:18<47:27:58,  7.13s/it]
 15%|█▍        | 4130/28080 [8:10:25<47:27:24,  7.13s/it]
                                                         
{'loss': 0.6655, 'learning_rate': 0.00048224657214455583, 'epoch': 1.76}

 15%|█▍        | 4130/28080 [8:10:25<47:27:24,  7.13s/it]
 15%|█▍        | 4131/28080 [8:10:32<47:27:00,  7.13s/it]
                                                         
{'loss': 0.6226, 'learning_rate': 0.00048223589809665924, 'epoch': 1.76}

 15%|█▍        | 4131/28080 [8:10:32<47:27:00,  7.13s/it]
 15%|█▍        | 4132/28080 [8:10:39<47:30:34,  7.14s/it]
                                                         
{'loss': 0.6585, 'learning_rate': 0.0004822252209591036, 'epoch': 1.77}

 15%|█▍        | 4132/28080 [8:10:39<47:30:34,  7.14s/it]
 15%|█▍        | 4133/28080 [8:10:46<47:30:33,  7.14s/it]
                                                         
{'loss': 0.6416, 'learning_rate': 0.00048221454073203094, 'epoch': 1.77}

 15%|█▍        | 4133/28080 [8:10:46<47:30:33,  7.14s/it]
 15%|█▍        | 4134/28080 [8:10:53<47:34:53,  7.15s/it]
                                                         
{'loss': 0.6388, 'learning_rate': 0.00048220385741558347, 'epoch': 1.77}

 15%|█▍        | 4134/28080 [8:10:53<47:34:53,  7.15s/it]
 15%|█▍        | 4135/28080 [8:11:00<47:32:34,  7.15s/it]
                                                         
{'loss': 0.6523, 'learning_rate': 0.00048219317100990313, 'epoch': 1.77}

 15%|█▍        | 4135/28080 [8:11:00<47:32:34,  7.15s/it]
 15%|█▍        | 4136/28080 [8:11:08<47:34:18,  7.15s/it]
                                                         
{'loss': 0.6699, 'learning_rate': 0.0004821824815151323, 'epoch': 1.77}

 15%|█▍        | 4136/28080 [8:11:08<47:34:18,  7.15s/it]
 15%|█▍        | 4137/28080 [8:11:15<47:37:49,  7.16s/it]
                                                         
{'loss': 0.6548, 'learning_rate': 0.000482171788931413, 'epoch': 1.77}

 15%|█▍        | 4137/28080 [8:11:15<47:37:49,  7.16s/it]
 15%|█▍        | 4138/28080 [8:11:22<47:37:22,  7.16s/it]
                                                         
{'loss': 0.677, 'learning_rate': 0.0004821610932588876, 'epoch': 1.77}

 15%|█▍        | 4138/28080 [8:11:22<47:37:22,  7.16s/it]
 15%|█▍        | 4139/28080 [8:11:29<47:31:47,  7.15s/it]
                                                         
{'loss': 0.6551, 'learning_rate': 0.0004821503944976983, 'epoch': 1.77}

 15%|█▍        | 4139/28080 [8:11:29<47:31:47,  7.15s/it]
 15%|█▍        | 4140/28080 [8:11:36<47:28:12,  7.14s/it]
                                                         
{'loss': 0.6407, 'learning_rate': 0.0004821396926479875, 'epoch': 1.77}

 15%|█▍        | 4140/28080 [8:11:36<47:28:12,  7.14s/it]
 15%|█▍        | 4141/28080 [8:11:43<47:37:19,  7.16s/it]
                                                         
{'loss': 0.6624, 'learning_rate': 0.00048212898770989767, 'epoch': 1.77}

 15%|█▍        | 4141/28080 [8:11:43<47:37:19,  7.16s/it]
 15%|█▍        | 4142/28080 [8:11:51<47:34:41,  7.16s/it]
                                                         
{'loss': 0.6435, 'learning_rate': 0.0004821182796835711, 'epoch': 1.77}

 15%|█▍        | 4142/28080 [8:11:51<47:34:41,  7.16s/it]
 15%|█▍        | 4143/28080 [8:11:58<47:43:27,  7.18s/it]
                                                         
{'loss': 0.6542, 'learning_rate': 0.0004821075685691502, 'epoch': 1.77}

 15%|█▍        | 4143/28080 [8:11:58<47:43:27,  7.18s/it]
 15%|█▍        | 4144/28080 [8:12:05<47:44:45,  7.18s/it]
                                                         
{'loss': 0.6407, 'learning_rate': 0.00048209685436677763, 'epoch': 1.77}

 15%|█▍        | 4144/28080 [8:12:05<47:44:45,  7.18s/it]
 15%|█▍        | 4145/28080 [8:12:12<47:36:49,  7.16s/it]
                                                         
{'loss': 0.6528, 'learning_rate': 0.0004820861370765959, 'epoch': 1.77}

 15%|█▍        | 4145/28080 [8:12:12<47:36:49,  7.16s/it]
 15%|█▍        | 4146/28080 [8:12:19<47:37:55,  7.16s/it]
                                                         
{'loss': 0.6629, 'learning_rate': 0.00048207541669874744, 'epoch': 1.77}

 15%|█▍        | 4146/28080 [8:12:19<47:37:55,  7.16s/it]
 15%|█▍        | 4147/28080 [8:12:26<47:39:01,  7.17s/it]
                                                         
{'loss': 0.6611, 'learning_rate': 0.000482064693233375, 'epoch': 1.77}

 15%|█▍        | 4147/28080 [8:12:26<47:39:01,  7.17s/it]
 15%|█▍        | 4148/28080 [8:12:34<47:43:55,  7.18s/it]
                                                         
{'loss': 0.6628, 'learning_rate': 0.00048205396668062127, 'epoch': 1.77}

 15%|█▍        | 4148/28080 [8:12:34<47:43:55,  7.18s/it]
 15%|█▍        | 4149/28080 [8:12:41<47:21:59,  7.13s/it]
                                                         
{'loss': 0.6526, 'learning_rate': 0.0004820432370406289, 'epoch': 1.77}

 15%|█▍        | 4149/28080 [8:12:41<47:21:59,  7.13s/it]
 15%|█▍        | 4150/28080 [8:12:48<47:32:13,  7.15s/it]
                                                         
{'loss': 0.6667, 'learning_rate': 0.0004820325043135406, 'epoch': 1.77}

 15%|█▍        | 4150/28080 [8:12:48<47:32:13,  7.15s/it]
 15%|█▍        | 4151/28080 [8:12:55<47:23:12,  7.13s/it]
                                                         
{'loss': 0.6461, 'learning_rate': 0.00048202176849949924, 'epoch': 1.77}

 15%|█▍        | 4151/28080 [8:12:55<47:23:12,  7.13s/it]
 15%|█▍        | 4152/28080 [8:13:02<47:23:17,  7.13s/it]
                                                         
{'loss': 0.6654, 'learning_rate': 0.0004820110295986476, 'epoch': 1.77}

 15%|█▍        | 4152/28080 [8:13:02<47:23:17,  7.13s/it]
 15%|█▍        | 4153/28080 [8:13:09<47:14:12,  7.11s/it]
                                                         
{'loss': 0.6597, 'learning_rate': 0.00048200028761112855, 'epoch': 1.77}

 15%|█▍        | 4153/28080 [8:13:09<47:14:12,  7.11s/it]
 15%|█▍        | 4154/28080 [8:13:16<47:28:16,  7.14s/it]
                                                         
{'loss': 0.6561, 'learning_rate': 0.0004819895425370851, 'epoch': 1.77}

 15%|█▍        | 4154/28080 [8:13:16<47:28:16,  7.14s/it]
 15%|█▍        | 4155/28080 [8:13:24<47:34:28,  7.16s/it]
                                                         
{'loss': 0.6491, 'learning_rate': 0.00048197879437666003, 'epoch': 1.77}

 15%|█▍        | 4155/28080 [8:13:24<47:34:28,  7.16s/it]
 15%|█▍        | 4156/28080 [8:13:31<47:28:16,  7.14s/it]
                                                         
{'loss': 0.6478, 'learning_rate': 0.00048196804312999647, 'epoch': 1.78}

 15%|█▍        | 4156/28080 [8:13:31<47:28:16,  7.14s/it]
 15%|█▍        | 4157/28080 [8:13:38<47:27:37,  7.14s/it]
                                                         
{'loss': 0.6601, 'learning_rate': 0.0004819572887972374, 'epoch': 1.78}

 15%|█▍        | 4157/28080 [8:13:38<47:27:37,  7.14s/it]
 15%|█▍        | 4158/28080 [8:13:45<47:10:41,  7.10s/it]
                                                         
{'loss': 0.6664, 'learning_rate': 0.00048194653137852584, 'epoch': 1.78}

 15%|█▍        | 4158/28080 [8:13:45<47:10:41,  7.10s/it]
 15%|█▍        | 4159/28080 [8:13:52<47:20:11,  7.12s/it]
                                                         
{'loss': 0.6569, 'learning_rate': 0.00048193577087400505, 'epoch': 1.78}

 15%|█▍        | 4159/28080 [8:13:52<47:20:11,  7.12s/it]
 15%|█▍        | 4160/28080 [8:13:59<47:22:26,  7.13s/it]
                                                         
{'loss': 0.6667, 'learning_rate': 0.00048192500728381804, 'epoch': 1.78}

 15%|█▍        | 4160/28080 [8:13:59<47:22:26,  7.13s/it]
 15%|█▍        | 4161/28080 [8:14:06<47:32:08,  7.15s/it]
                                                         
{'loss': 0.633, 'learning_rate': 0.00048191424060810804, 'epoch': 1.78}

 15%|█▍        | 4161/28080 [8:14:06<47:32:08,  7.15s/it]
 15%|█▍        | 4162/28080 [8:14:14<47:40:39,  7.18s/it]
                                                         
{'loss': 0.6475, 'learning_rate': 0.0004819034708470185, 'epoch': 1.78}

 15%|█▍        | 4162/28080 [8:14:14<47:40:39,  7.18s/it]
 15%|█▍        | 4163/28080 [8:14:21<47:46:33,  7.19s/it]
                                                         
{'loss': 0.6533, 'learning_rate': 0.00048189269800069233, 'epoch': 1.78}

 15%|█▍        | 4163/28080 [8:14:21<47:46:33,  7.19s/it]
 15%|█▍        | 4164/28080 [8:14:28<47:29:22,  7.15s/it]
                                                         
{'loss': 0.6492, 'learning_rate': 0.00048188192206927307, 'epoch': 1.78}

 15%|█▍        | 4164/28080 [8:14:28<47:29:22,  7.15s/it]
 15%|█▍        | 4165/28080 [8:14:35<47:35:07,  7.16s/it]
                                                         
{'loss': 0.6502, 'learning_rate': 0.00048187114305290414, 'epoch': 1.78}

 15%|█▍        | 4165/28080 [8:14:35<47:35:07,  7.16s/it]
 15%|█▍        | 4166/28080 [8:14:42<47:35:48,  7.17s/it]
                                                         
{'loss': 0.6736, 'learning_rate': 0.0004818603609517288, 'epoch': 1.78}

 15%|█▍        | 4166/28080 [8:14:42<47:35:48,  7.17s/it]
 15%|█▍        | 4167/28080 [8:14:49<47:25:18,  7.14s/it]
                                                         
{'loss': 0.6591, 'learning_rate': 0.00048184957576589055, 'epoch': 1.78}

 15%|█▍        | 4167/28080 [8:14:49<47:25:18,  7.14s/it]
 15%|█▍        | 4168/28080 [8:14:56<47:28:11,  7.15s/it]
                                                         
{'loss': 0.6621, 'learning_rate': 0.00048183878749553287, 'epoch': 1.78}

 15%|█▍        | 4168/28080 [8:14:56<47:28:11,  7.15s/it]
 15%|█▍        | 4169/28080 [8:15:04<47:39:09,  7.17s/it]
                                                         
{'loss': 0.6643, 'learning_rate': 0.0004818279961407994, 'epoch': 1.78}

 15%|█▍        | 4169/28080 [8:15:04<47:39:09,  7.17s/it]
 15%|█▍        | 4170/28080 [8:15:11<47:33:50,  7.16s/it]
                                                         
{'loss': 0.6432, 'learning_rate': 0.0004818172017018335, 'epoch': 1.78}

 15%|█▍        | 4170/28080 [8:15:11<47:33:50,  7.16s/it]
 15%|█▍        | 4171/28080 [8:15:18<47:24:19,  7.14s/it]
                                                         
{'loss': 0.6466, 'learning_rate': 0.0004818064041787789, 'epoch': 1.78}

 15%|█▍        | 4171/28080 [8:15:18<47:24:19,  7.14s/it]
 15%|█▍        | 4172/28080 [8:15:25<47:25:03,  7.14s/it]
                                                         
{'loss': 0.6592, 'learning_rate': 0.0004817956035717793, 'epoch': 1.78}

 15%|█▍        | 4172/28080 [8:15:25<47:25:03,  7.14s/it]
 15%|█▍        | 4173/28080 [8:15:32<47:30:52,  7.15s/it]
                                                         
{'loss': 0.636, 'learning_rate': 0.0004817847998809782, 'epoch': 1.78}

 15%|█▍        | 4173/28080 [8:15:32<47:30:52,  7.15s/it]
 15%|█▍        | 4174/28080 [8:15:39<47:30:25,  7.15s/it]
                                                         
{'loss': 0.6536, 'learning_rate': 0.0004817739931065196, 'epoch': 1.78}

 15%|█▍        | 4174/28080 [8:15:39<47:30:25,  7.15s/it]
 15%|█▍        | 4175/28080 [8:15:47<47:30:51,  7.16s/it]
                                                         
{'loss': 0.6429, 'learning_rate': 0.00048176318324854705, 'epoch': 1.78}

 15%|█▍        | 4175/28080 [8:15:47<47:30:51,  7.16s/it]
 15%|█▍        | 4176/28080 [8:15:54<47:22:28,  7.13s/it]
                                                         
{'loss': 0.6674, 'learning_rate': 0.00048175237030720445, 'epoch': 1.78}

 15%|█▍        | 4176/28080 [8:15:54<47:22:28,  7.13s/it]
 15%|█▍        | 4177/28080 [8:16:01<47:10:27,  7.10s/it]
                                                         
{'loss': 0.664, 'learning_rate': 0.0004817415542826357, 'epoch': 1.78}

 15%|█▍        | 4177/28080 [8:16:01<47:10:27,  7.10s/it]
 15%|█▍        | 4178/28080 [8:16:08<47:15:06,  7.12s/it]
                                                         
{'loss': 0.6366, 'learning_rate': 0.00048173073517498457, 'epoch': 1.78}

 15%|█▍        | 4178/28080 [8:16:08<47:15:06,  7.12s/it]
 15%|█▍        | 4179/28080 [8:16:15<46:58:03,  7.07s/it]
                                                         
{'loss': 0.6555, 'learning_rate': 0.0004817199129843951, 'epoch': 1.79}

 15%|█▍        | 4179/28080 [8:16:15<46:58:03,  7.07s/it]
 15%|█▍        | 4180/28080 [8:16:22<47:03:06,  7.09s/it]
                                                         
{'loss': 0.6531, 'learning_rate': 0.0004817090877110112, 'epoch': 1.79}

 15%|█▍        | 4180/28080 [8:16:22<47:03:06,  7.09s/it]
 15%|█▍        | 4181/28080 [8:16:29<46:54:13,  7.07s/it]
                                                         
{'loss': 0.6518, 'learning_rate': 0.000481698259354977, 'epoch': 1.79}

 15%|█▍        | 4181/28080 [8:16:29<46:54:13,  7.07s/it]
 15%|█▍        | 4182/28080 [8:16:36<46:58:15,  7.08s/it]
                                                         
{'loss': 0.6767, 'learning_rate': 0.00048168742791643645, 'epoch': 1.79}

 15%|█▍        | 4182/28080 [8:16:36<46:58:15,  7.08s/it]
 15%|█▍        | 4183/28080 [8:16:43<47:13:30,  7.11s/it]
                                                         
{'loss': 0.6457, 'learning_rate': 0.0004816765933955337, 'epoch': 1.79}

 15%|█▍        | 4183/28080 [8:16:43<47:13:30,  7.11s/it]
 15%|█▍        | 4184/28080 [8:16:50<47:20:55,  7.13s/it]
                                                         
{'loss': 0.6629, 'learning_rate': 0.0004816657557924129, 'epoch': 1.79}

 15%|█▍        | 4184/28080 [8:16:50<47:20:55,  7.13s/it]
 15%|█▍        | 4185/28080 [8:16:58<47:36:29,  7.17s/it]
                                                         
{'loss': 0.635, 'learning_rate': 0.00048165491510721817, 'epoch': 1.79}

 15%|█▍        | 4185/28080 [8:16:58<47:36:29,  7.17s/it]
 15%|█▍        | 4186/28080 [8:17:05<47:50:37,  7.21s/it]
                                                         
{'loss': 0.6406, 'learning_rate': 0.0004816440713400938, 'epoch': 1.79}

 15%|█▍        | 4186/28080 [8:17:05<47:50:37,  7.21s/it]
 15%|█▍        | 4187/28080 [8:17:12<47:33:00,  7.16s/it]
                                                         
{'loss': 0.6512, 'learning_rate': 0.0004816332244911841, 'epoch': 1.79}

 15%|█▍        | 4187/28080 [8:17:12<47:33:00,  7.16s/it]
 15%|█▍        | 4188/28080 [8:17:19<47:35:46,  7.17s/it]
                                                         
{'loss': 0.6497, 'learning_rate': 0.0004816223745606332, 'epoch': 1.79}

 15%|█▍        | 4188/28080 [8:17:19<47:35:46,  7.17s/it]
 15%|█▍        | 4189/28080 [8:17:26<47:20:20,  7.13s/it]
                                                         
{'loss': 0.6541, 'learning_rate': 0.0004816115215485856, 'epoch': 1.79}

 15%|█▍        | 4189/28080 [8:17:26<47:20:20,  7.13s/it]
 15%|█▍        | 4190/28080 [8:17:33<47:18:36,  7.13s/it]
                                                         
{'loss': 0.6562, 'learning_rate': 0.00048160066545518564, 'epoch': 1.79}

 15%|█▍        | 4190/28080 [8:17:33<47:18:36,  7.13s/it]
 15%|█▍        | 4191/28080 [8:17:40<47:20:34,  7.13s/it]
                                                         
{'loss': 0.6381, 'learning_rate': 0.0004815898062805778, 'epoch': 1.79}

 15%|█▍        | 4191/28080 [8:17:40<47:20:34,  7.13s/it]
 15%|█▍        | 4192/28080 [8:17:48<47:27:54,  7.15s/it]
                                                         
{'loss': 0.6379, 'learning_rate': 0.00048157894402490645, 'epoch': 1.79}

 15%|█▍        | 4192/28080 [8:17:48<47:27:54,  7.15s/it]
 15%|█▍        | 4193/28080 [8:17:55<47:33:27,  7.17s/it]
                                                         
{'loss': 0.6455, 'learning_rate': 0.0004815680786883162, 'epoch': 1.79}

 15%|█▍        | 4193/28080 [8:17:55<47:33:27,  7.17s/it]
 15%|█▍        | 4194/28080 [8:18:02<47:36:09,  7.17s/it]
                                                         
{'loss': 0.6533, 'learning_rate': 0.00048155721027095155, 'epoch': 1.79}

 15%|█▍        | 4194/28080 [8:18:02<47:36:09,  7.17s/it]
 15%|█▍        | 4195/28080 [8:18:09<47:38:27,  7.18s/it]
                                                         
{'loss': 0.6486, 'learning_rate': 0.0004815463387729571, 'epoch': 1.79}

 15%|█▍        | 4195/28080 [8:18:09<47:38:27,  7.18s/it]
 15%|█▍        | 4196/28080 [8:18:17<47:59:29,  7.23s/it]
                                                         
{'loss': 0.6745, 'learning_rate': 0.00048153546419447746, 'epoch': 1.79}

 15%|█▍        | 4196/28080 [8:18:17<47:59:29,  7.23s/it]
 15%|█▍        | 4197/28080 [8:18:24<47:42:18,  7.19s/it]
                                                         
{'loss': 0.6376, 'learning_rate': 0.00048152458653565733, 'epoch': 1.79}

 15%|█▍        | 4197/28080 [8:18:24<47:42:18,  7.19s/it]
 15%|█▍        | 4198/28080 [8:18:31<47:34:00,  7.17s/it]
                                                         
{'loss': 0.6378, 'learning_rate': 0.00048151370579664144, 'epoch': 1.79}

 15%|█▍        | 4198/28080 [8:18:31<47:34:00,  7.17s/it]
 15%|█▍        | 4199/28080 [8:18:38<47:30:45,  7.16s/it]
                                                         
{'loss': 0.6367, 'learning_rate': 0.0004815028219775746, 'epoch': 1.79}

 15%|█▍        | 4199/28080 [8:18:38<47:30:45,  7.16s/it]
 15%|█▍        | 4200/28080 [8:18:45<47:35:06,  7.17s/it]
                                                         
{'loss': 0.658, 'learning_rate': 0.0004814919350786014, 'epoch': 1.79}

 15%|█▍        | 4200/28080 [8:18:45<47:35:06,  7.17s/it]
 15%|█▍        | 4201/28080 [8:18:52<47:32:52,  7.17s/it]
                                                         
{'loss': 0.66, 'learning_rate': 0.00048148104509986695, 'epoch': 1.79}

 15%|█▍        | 4201/28080 [8:18:52<47:32:52,  7.17s/it]
 15%|█▍        | 4202/28080 [8:19:00<47:45:00,  7.20s/it]
                                                         
{'loss': 0.6651, 'learning_rate': 0.00048147015204151594, 'epoch': 1.8}

 15%|█▍        | 4202/28080 [8:19:00<47:45:00,  7.20s/it]
 15%|█▍        | 4203/28080 [8:19:07<47:46:57,  7.20s/it]
                                                         
{'loss': 0.6521, 'learning_rate': 0.00048145925590369336, 'epoch': 1.8}

 15%|█▍        | 4203/28080 [8:19:07<47:46:57,  7.20s/it]
 15%|█▍        | 4204/28080 [8:19:14<48:09:23,  7.26s/it]
                                                         
{'loss': 0.6574, 'learning_rate': 0.00048144835668654417, 'epoch': 1.8}

 15%|█▍        | 4204/28080 [8:19:14<48:09:23,  7.26s/it]
 15%|█▍        | 4205/28080 [8:19:21<48:02:47,  7.24s/it]
                                                         
{'loss': 0.6378, 'learning_rate': 0.00048143745439021337, 'epoch': 1.8}

 15%|█▍        | 4205/28080 [8:19:21<48:02:47,  7.24s/it]
 15%|█▍        | 4206/28080 [8:19:28<47:36:50,  7.18s/it]
                                                         
{'loss': 0.6553, 'learning_rate': 0.00048142654901484603, 'epoch': 1.8}

 15%|█▍        | 4206/28080 [8:19:28<47:36:50,  7.18s/it]
 15%|█▍        | 4207/28080 [8:19:36<47:29:02,  7.16s/it]
                                                         
{'loss': 0.676, 'learning_rate': 0.0004814156405605871, 'epoch': 1.8}

 15%|█▍        | 4207/28080 [8:19:36<47:29:02,  7.16s/it]
 15%|█▍        | 4208/28080 [8:19:43<47:24:04,  7.15s/it]
                                                         
{'loss': 0.6453, 'learning_rate': 0.0004814047290275819, 'epoch': 1.8}

 15%|█▍        | 4208/28080 [8:19:43<47:24:04,  7.15s/it]
 15%|█▍        | 4209/28080 [8:19:50<47:27:05,  7.16s/it]
                                                         
{'loss': 0.6729, 'learning_rate': 0.0004813938144159755, 'epoch': 1.8}

 15%|█▍        | 4209/28080 [8:19:50<47:27:05,  7.16s/it]
 15%|█▍        | 4210/28080 [8:19:57<47:40:21,  7.19s/it]
                                                         
{'loss': 0.6515, 'learning_rate': 0.00048138289672591307, 'epoch': 1.8}

 15%|█▍        | 4210/28080 [8:19:57<47:40:21,  7.19s/it]
 15%|█▍        | 4211/28080 [8:20:04<47:25:31,  7.15s/it]
                                                         
{'loss': 0.6745, 'learning_rate': 0.00048137197595754, 'epoch': 1.8}

 15%|█▍        | 4211/28080 [8:20:04<47:25:31,  7.15s/it]
 15%|█▌        | 4212/28080 [8:20:11<47:20:41,  7.14s/it]
                                                         
{'loss': 0.6606, 'learning_rate': 0.0004813610521110014, 'epoch': 1.8}

 15%|█▌        | 4212/28080 [8:20:11<47:20:41,  7.14s/it]
 15%|█▌        | 4213/28080 [8:20:19<47:30:55,  7.17s/it]
                                                         
{'loss': 0.6687, 'learning_rate': 0.0004813501251864427, 'epoch': 1.8}

 15%|█▌        | 4213/28080 [8:20:19<47:30:55,  7.17s/it]
 15%|█▌        | 4214/28080 [8:20:26<47:14:54,  7.13s/it]
                                                         
{'loss': 0.6725, 'learning_rate': 0.00048133919518400926, 'epoch': 1.8}

 15%|█▌        | 4214/28080 [8:20:26<47:14:54,  7.13s/it]
 15%|█▌        | 4215/28080 [8:20:33<47:15:06,  7.13s/it]
                                                         
{'loss': 0.6663, 'learning_rate': 0.0004813282621038465, 'epoch': 1.8}

 15%|█▌        | 4215/28080 [8:20:33<47:15:06,  7.13s/it]
 15%|█▌        | 4216/28080 [8:20:40<47:22:15,  7.15s/it]
                                                         
{'loss': 0.6573, 'learning_rate': 0.0004813173259460998, 'epoch': 1.8}

 15%|█▌        | 4216/28080 [8:20:40<47:22:15,  7.15s/it]
 15%|█▌        | 4217/28080 [8:20:47<47:18:12,  7.14s/it]
                                                         
{'loss': 0.6529, 'learning_rate': 0.00048130638671091473, 'epoch': 1.8}

 15%|█▌        | 4217/28080 [8:20:47<47:18:12,  7.14s/it]
 15%|█▌        | 4218/28080 [8:20:54<47:19:35,  7.14s/it]
                                                         
{'loss': 0.6583, 'learning_rate': 0.00048129544439843685, 'epoch': 1.8}

 15%|█▌        | 4218/28080 [8:20:54<47:19:35,  7.14s/it]
 15%|█▌        | 4219/28080 [8:21:01<47:25:23,  7.15s/it]
                                                         
{'loss': 0.6544, 'learning_rate': 0.0004812844990088117, 'epoch': 1.8}

 15%|█▌        | 4219/28080 [8:21:01<47:25:23,  7.15s/it]
 15%|█▌        | 4220/28080 [8:21:09<47:30:11,  7.17s/it]
                                                         
{'loss': 0.6672, 'learning_rate': 0.0004812735505421849, 'epoch': 1.8}

 15%|█▌        | 4220/28080 [8:21:09<47:30:11,  7.17s/it]
 15%|█▌        | 4221/28080 [8:21:16<47:23:26,  7.15s/it]
                                                         
{'loss': 0.6534, 'learning_rate': 0.0004812625989987021, 'epoch': 1.8}

 15%|█▌        | 4221/28080 [8:21:16<47:23:26,  7.15s/it]
 15%|█▌        | 4222/28080 [8:21:23<47:26:54,  7.16s/it]
                                                         
{'loss': 0.6647, 'learning_rate': 0.00048125164437850897, 'epoch': 1.8}

 15%|█▌        | 4222/28080 [8:21:23<47:26:54,  7.16s/it]
 15%|█▌        | 4223/28080 [8:21:30<48:06:07,  7.26s/it]
                                                         
{'loss': 0.6527, 'learning_rate': 0.0004812406866817513, 'epoch': 1.8}

 15%|█▌        | 4223/28080 [8:21:30<48:06:07,  7.26s/it]
 15%|█▌        | 4224/28080 [8:21:38<48:18:26,  7.29s/it]
                                                         
{'loss': 0.6491, 'learning_rate': 0.00048122972590857485, 'epoch': 1.8}

 15%|█▌        | 4224/28080 [8:21:38<48:18:26,  7.29s/it]
 15%|█▌        | 4225/28080 [8:21:45<47:48:25,  7.21s/it]
                                                         
{'loss': 0.6539, 'learning_rate': 0.0004812187620591254, 'epoch': 1.8}

 15%|█▌        | 4225/28080 [8:21:45<47:48:25,  7.21s/it]
 15%|█▌        | 4226/28080 [8:21:52<47:36:12,  7.18s/it]
                                                         
{'loss': 0.66, 'learning_rate': 0.00048120779513354894, 'epoch': 1.81}

 15%|█▌        | 4226/28080 [8:21:52<47:36:12,  7.18s/it]
 15%|█▌        | 4227/28080 [8:21:59<47:19:59,  7.14s/it]
                                                         
{'loss': 0.6778, 'learning_rate': 0.00048119682513199125, 'epoch': 1.81}

 15%|█▌        | 4227/28080 [8:21:59<47:19:59,  7.14s/it]
 15%|█▌        | 4228/28080 [8:22:06<47:26:17,  7.16s/it]
                                                         
{'loss': 0.6357, 'learning_rate': 0.0004811858520545983, 'epoch': 1.81}

 15%|█▌        | 4228/28080 [8:22:06<47:26:17,  7.16s/it]
 15%|█▌        | 4229/28080 [8:22:13<47:51:25,  7.22s/it]
                                                         
{'loss': 0.6331, 'learning_rate': 0.0004811748759015161, 'epoch': 1.81}

 15%|█▌        | 4229/28080 [8:22:13<47:51:25,  7.22s/it]
 15%|█▌        | 4230/28080 [8:22:21<47:49:52,  7.22s/it]
                                                         
{'loss': 0.6667, 'learning_rate': 0.0004811638966728906, 'epoch': 1.81}

 15%|█▌        | 4230/28080 [8:22:21<47:49:52,  7.22s/it]
 15%|█▌        | 4231/28080 [8:22:28<47:36:54,  7.19s/it]
                                                         
{'loss': 0.6552, 'learning_rate': 0.00048115291436886805, 'epoch': 1.81}

 15%|█▌        | 4231/28080 [8:22:28<47:36:54,  7.19s/it]
 15%|█▌        | 4232/28080 [8:22:35<47:49:17,  7.22s/it]
                                                         
{'loss': 0.6482, 'learning_rate': 0.00048114192898959443, 'epoch': 1.81}

 15%|█▌        | 4232/28080 [8:22:35<47:49:17,  7.22s/it]
 15%|█▌        | 4233/28080 [8:22:42<47:52:05,  7.23s/it]
                                                         
{'loss': 0.6607, 'learning_rate': 0.00048113094053521576, 'epoch': 1.81}

 15%|█▌        | 4233/28080 [8:22:42<47:52:05,  7.23s/it]
 15%|█▌        | 4234/28080 [8:22:50<48:00:38,  7.25s/it]
                                                         
{'loss': 0.6484, 'learning_rate': 0.0004811199490058785, 'epoch': 1.81}

 15%|█▌        | 4234/28080 [8:22:50<48:00:38,  7.25s/it]
 15%|█▌        | 4235/28080 [8:22:57<47:51:27,  7.23s/it]
                                                         
{'loss': 0.6815, 'learning_rate': 0.00048110895440172877, 'epoch': 1.81}

 15%|█▌        | 4235/28080 [8:22:57<47:51:27,  7.23s/it]
 15%|█▌        | 4236/28080 [8:23:04<47:26:40,  7.16s/it]
                                                         
{'loss': 0.6471, 'learning_rate': 0.00048109795672291274, 'epoch': 1.81}

 15%|█▌        | 4236/28080 [8:23:04<47:26:40,  7.16s/it]
 15%|█▌        | 4237/28080 [8:23:11<47:26:07,  7.16s/it]
                                                         
{'loss': 0.6651, 'learning_rate': 0.00048108695596957686, 'epoch': 1.81}

 15%|█▌        | 4237/28080 [8:23:11<47:26:07,  7.16s/it]
 15%|█▌        | 4238/28080 [8:23:18<47:27:59,  7.17s/it]
                                                         
{'loss': 0.6538, 'learning_rate': 0.0004810759521418674, 'epoch': 1.81}

 15%|█▌        | 4238/28080 [8:23:18<47:27:59,  7.17s/it]
 15%|█▌        | 4239/28080 [8:23:25<47:31:01,  7.18s/it]
                                                         
{'loss': 0.6531, 'learning_rate': 0.00048106494523993083, 'epoch': 1.81}

 15%|█▌        | 4239/28080 [8:23:25<47:31:01,  7.18s/it]
 15%|█▌        | 4240/28080 [8:23:33<47:39:47,  7.20s/it]
                                                         
{'loss': 0.6658, 'learning_rate': 0.0004810539352639135, 'epoch': 1.81}

 15%|█▌        | 4240/28080 [8:23:33<47:39:47,  7.20s/it]
 15%|█▌        | 4241/28080 [8:23:40<47:39:56,  7.20s/it]
                                                         
{'loss': 0.6412, 'learning_rate': 0.0004810429222139619, 'epoch': 1.81}

 15%|█▌        | 4241/28080 [8:23:40<47:39:56,  7.20s/it]
 15%|█▌        | 4242/28080 [8:23:47<47:45:22,  7.21s/it]
                                                         
{'loss': 0.6363, 'learning_rate': 0.00048103190609022264, 'epoch': 1.81}

 15%|█▌        | 4242/28080 [8:23:47<47:45:22,  7.21s/it]
 15%|█▌        | 4243/28080 [8:23:54<48:01:40,  7.25s/it]
                                                         
{'loss': 0.6527, 'learning_rate': 0.0004810208868928421, 'epoch': 1.81}

 15%|█▌        | 4243/28080 [8:23:54<48:01:40,  7.25s/it]
 15%|█▌        | 4244/28080 [8:24:02<47:48:37,  7.22s/it]
                                                         
{'loss': 0.6594, 'learning_rate': 0.0004810098646219671, 'epoch': 1.81}

 15%|█▌        | 4244/28080 [8:24:02<47:48:37,  7.22s/it]
 15%|█▌        | 4245/28080 [8:24:09<47:44:30,  7.21s/it]
                                                         
{'loss': 0.6754, 'learning_rate': 0.00048099883927774415, 'epoch': 1.81}

 15%|█▌        | 4245/28080 [8:24:09<47:44:30,  7.21s/it]
 15%|█▌        | 4246/28080 [8:24:16<47:31:06,  7.18s/it]
                                                         
{'loss': 0.6388, 'learning_rate': 0.00048098781086031996, 'epoch': 1.81}

 15%|█▌        | 4246/28080 [8:24:16<47:31:06,  7.18s/it]
 15%|█▌        | 4247/28080 [8:24:23<47:56:25,  7.24s/it]
                                                         
{'loss': 0.6674, 'learning_rate': 0.00048097677936984116, 'epoch': 1.81}

 15%|█▌        | 4247/28080 [8:24:23<47:56:25,  7.24s/it]
 15%|█▌        | 4248/28080 [8:24:30<47:43:15,  7.21s/it]
                                                         
{'loss': 0.6595, 'learning_rate': 0.0004809657448064547, 'epoch': 1.81}

 15%|█▌        | 4248/28080 [8:24:30<47:43:15,  7.21s/it]
 15%|█▌        | 4249/28080 [8:24:37<47:35:39,  7.19s/it]
                                                         
{'loss': 0.6708, 'learning_rate': 0.0004809547071703072, 'epoch': 1.82}

 15%|█▌        | 4249/28080 [8:24:37<47:35:39,  7.19s/it]
 15%|█▌        | 4250/28080 [8:24:45<47:37:29,  7.19s/it]
                                                         
{'loss': 0.6736, 'learning_rate': 0.0004809436664615456, 'epoch': 1.82}

 15%|█▌        | 4250/28080 [8:24:45<47:37:29,  7.19s/it]
 15%|█▌        | 4251/28080 [8:24:52<47:50:28,  7.23s/it]
                                                         
{'loss': 0.6722, 'learning_rate': 0.0004809326226803169, 'epoch': 1.82}

 15%|█▌        | 4251/28080 [8:24:52<47:50:28,  7.23s/it]
 15%|█▌        | 4252/28080 [8:24:59<47:42:35,  7.21s/it]
                                                         
{'loss': 0.6415, 'learning_rate': 0.00048092157582676776, 'epoch': 1.82}

 15%|█▌        | 4252/28080 [8:24:59<47:42:35,  7.21s/it]
 15%|█▌        | 4253/28080 [8:25:06<47:53:27,  7.24s/it]
                                                         
{'loss': 0.6485, 'learning_rate': 0.0004809105259010453, 'epoch': 1.82}

 15%|█▌        | 4253/28080 [8:25:06<47:53:27,  7.24s/it]
 15%|█▌        | 4254/28080 [8:25:14<47:45:37,  7.22s/it]
                                                         
{'loss': 0.6767, 'learning_rate': 0.0004808994729032965, 'epoch': 1.82}

 15%|█▌        | 4254/28080 [8:25:14<47:45:37,  7.22s/it]
 15%|█▌        | 4255/28080 [8:25:21<47:36:50,  7.19s/it]
                                                         
{'loss': 0.6654, 'learning_rate': 0.00048088841683366845, 'epoch': 1.82}

 15%|█▌        | 4255/28080 [8:25:21<47:36:50,  7.19s/it]
 15%|█▌        | 4256/28080 [8:25:28<47:38:23,  7.20s/it]
                                                         
{'loss': 0.6427, 'learning_rate': 0.0004808773576923082, 'epoch': 1.82}

 15%|█▌        | 4256/28080 [8:25:28<47:38:23,  7.20s/it]
 15%|█▌        | 4257/28080 [8:25:35<47:15:55,  7.14s/it]
                                                         
{'loss': 0.6514, 'learning_rate': 0.0004808662954793629, 'epoch': 1.82}

 15%|█▌        | 4257/28080 [8:25:35<47:15:55,  7.14s/it]
 15%|█▌        | 4258/28080 [8:25:42<47:30:21,  7.18s/it]
                                                         
{'loss': 0.6588, 'learning_rate': 0.0004808552301949797, 'epoch': 1.82}

 15%|█▌        | 4258/28080 [8:25:42<47:30:21,  7.18s/it]
 15%|█▌        | 4259/28080 [8:25:49<47:30:56,  7.18s/it]
                                                         
{'loss': 0.6384, 'learning_rate': 0.0004808441618393058, 'epoch': 1.82}

 15%|█▌        | 4259/28080 [8:25:49<47:30:56,  7.18s/it]
 15%|█▌        | 4260/28080 [8:25:57<47:35:00,  7.19s/it]
                                                         
{'loss': 0.6684, 'learning_rate': 0.00048083309041248854, 'epoch': 1.82}

 15%|█▌        | 4260/28080 [8:25:57<47:35:00,  7.19s/it]
 15%|█▌        | 4261/28080 [8:26:04<47:36:53,  7.20s/it]
                                                         
{'loss': 0.6478, 'learning_rate': 0.00048082201591467507, 'epoch': 1.82}

 15%|█▌        | 4261/28080 [8:26:04<47:36:53,  7.20s/it]
 15%|█▌        | 4262/28080 [8:26:11<47:29:31,  7.18s/it]
                                                         
{'loss': 0.6584, 'learning_rate': 0.00048081093834601284, 'epoch': 1.82}

 15%|█▌        | 4262/28080 [8:26:11<47:29:31,  7.18s/it]
 15%|█▌        | 4263/28080 [8:26:18<47:24:44,  7.17s/it]
                                                         
{'loss': 0.6411, 'learning_rate': 0.0004807998577066492, 'epoch': 1.82}

 15%|█▌        | 4263/28080 [8:26:18<47:24:44,  7.17s/it]
 15%|█▌        | 4264/28080 [8:26:25<47:27:41,  7.17s/it]
                                                         
{'loss': 0.6519, 'learning_rate': 0.0004807887739967315, 'epoch': 1.82}

 15%|█▌        | 4264/28080 [8:26:25<47:27:41,  7.17s/it]
 15%|█▌        | 4265/28080 [8:26:33<47:33:06,  7.19s/it]
                                                         
{'loss': 0.6647, 'learning_rate': 0.00048077768721640736, 'epoch': 1.82}

 15%|█▌        | 4265/28080 [8:26:33<47:33:06,  7.19s/it]
 15%|█▌        | 4266/28080 [8:26:40<47:50:53,  7.23s/it]
                                                         
{'loss': 0.6601, 'learning_rate': 0.00048076659736582405, 'epoch': 1.82}

 15%|█▌        | 4266/28080 [8:26:40<47:50:53,  7.23s/it]
 15%|█▌        | 4267/28080 [8:26:47<47:43:58,  7.22s/it]
                                                         
{'loss': 0.6634, 'learning_rate': 0.00048075550444512925, 'epoch': 1.82}

 15%|█▌        | 4267/28080 [8:26:47<47:43:58,  7.22s/it]
 15%|█▌        | 4268/28080 [8:26:54<47:43:18,  7.21s/it]
                                                         
{'loss': 0.6629, 'learning_rate': 0.0004807444084544707, 'epoch': 1.82}

 15%|█▌        | 4268/28080 [8:26:54<47:43:18,  7.21s/it]
 15%|█▌        | 4269/28080 [8:27:01<47:36:54,  7.20s/it]
                                                         
{'loss': 0.6536, 'learning_rate': 0.0004807333093939956, 'epoch': 1.82}

 15%|█▌        | 4269/28080 [8:27:01<47:36:54,  7.20s/it]
 15%|█▌        | 4270/28080 [8:27:09<47:39:35,  7.21s/it]
                                                         
{'loss': 0.6542, 'learning_rate': 0.00048072220726385196, 'epoch': 1.82}

 15%|█▌        | 4270/28080 [8:27:09<47:39:35,  7.21s/it]
 15%|█▌        | 4271/28080 [8:27:16<47:44:58,  7.22s/it]
                                                         
{'loss': 0.6355, 'learning_rate': 0.0004807111020641874, 'epoch': 1.82}

 15%|█▌        | 4271/28080 [8:27:16<47:44:58,  7.22s/it]
 15%|█▌        | 4272/28080 [8:27:23<47:25:50,  7.17s/it]
                                                         
{'loss': 0.6493, 'learning_rate': 0.0004806999937951496, 'epoch': 1.82}

 15%|█▌        | 4272/28080 [8:27:23<47:25:50,  7.17s/it]
 15%|█▌        | 4273/28080 [8:27:30<47:10:17,  7.13s/it]
                                                         
{'loss': 0.6639, 'learning_rate': 0.0004806888824568864, 'epoch': 1.83}

 15%|█▌        | 4273/28080 [8:27:30<47:10:17,  7.13s/it]
 15%|█▌        | 4274/28080 [8:27:37<47:17:16,  7.15s/it]
                                                         
{'loss': 0.6712, 'learning_rate': 0.00048067776804954556, 'epoch': 1.83}

 15%|█▌        | 4274/28080 [8:27:37<47:17:16,  7.15s/it]
 15%|█▌        | 4275/28080 [8:27:44<47:27:23,  7.18s/it]
                                                         
{'loss': 0.6549, 'learning_rate': 0.0004806666505732751, 'epoch': 1.83}

 15%|█▌        | 4275/28080 [8:27:44<47:27:23,  7.18s/it]
 15%|█▌        | 4276/28080 [8:27:52<47:18:15,  7.15s/it]
                                                         
{'loss': 0.6574, 'learning_rate': 0.0004806555300282227, 'epoch': 1.83}

 15%|█▌        | 4276/28080 [8:27:52<47:18:15,  7.15s/it]
 15%|█▌        | 4277/28080 [8:27:59<47:20:59,  7.16s/it]
                                                         
{'loss': 0.6559, 'learning_rate': 0.0004806444064145364, 'epoch': 1.83}

 15%|█▌        | 4277/28080 [8:27:59<47:20:59,  7.16s/it]
 15%|█▌        | 4278/28080 [8:28:06<47:06:32,  7.13s/it]
                                                         
{'loss': 0.6522, 'learning_rate': 0.0004806332797323644, 'epoch': 1.83}

 15%|█▌        | 4278/28080 [8:28:06<47:06:32,  7.13s/it]
 15%|█▌        | 4279/28080 [8:28:13<47:07:28,  7.13s/it]
                                                         
{'loss': 0.6432, 'learning_rate': 0.0004806221499818544, 'epoch': 1.83}

 15%|█▌        | 4279/28080 [8:28:13<47:07:28,  7.13s/it]
 15%|█▌        | 4280/28080 [8:28:20<47:00:28,  7.11s/it]
                                                         
{'loss': 0.65, 'learning_rate': 0.0004806110171631546, 'epoch': 1.83}

 15%|█▌        | 4280/28080 [8:28:20<47:00:28,  7.11s/it]
 15%|█▌        | 4281/28080 [8:28:27<47:07:07,  7.13s/it]
                                                         
{'loss': 0.6524, 'learning_rate': 0.0004805998812764132, 'epoch': 1.83}

 15%|█▌        | 4281/28080 [8:28:27<47:07:07,  7.13s/it]
 15%|█▌        | 4282/28080 [8:28:34<46:53:39,  7.09s/it]
                                                         
{'loss': 0.6526, 'learning_rate': 0.0004805887423217783, 'epoch': 1.83}

 15%|█▌        | 4282/28080 [8:28:34<46:53:39,  7.09s/it]
 15%|█▌        | 4283/28080 [8:28:41<46:35:22,  7.05s/it]
                                                         
{'loss': 0.6649, 'learning_rate': 0.000480577600299398, 'epoch': 1.83}

 15%|█▌        | 4283/28080 [8:28:41<46:35:22,  7.05s/it]
 15%|█▌        | 4284/28080 [8:28:48<46:39:23,  7.06s/it]
                                                         
{'loss': 0.6392, 'learning_rate': 0.00048056645520942065, 'epoch': 1.83}

 15%|█▌        | 4284/28080 [8:28:48<46:39:23,  7.06s/it]
 15%|█▌        | 4285/28080 [8:28:55<46:50:00,  7.09s/it]
                                                         
{'loss': 0.6585, 'learning_rate': 0.0004805553070519945, 'epoch': 1.83}

 15%|█▌        | 4285/28080 [8:28:55<46:50:00,  7.09s/it]
 15%|█▌        | 4286/28080 [8:29:02<46:53:28,  7.09s/it]
                                                         
{'loss': 0.6154, 'learning_rate': 0.0004805441558272677, 'epoch': 1.83}

 15%|█▌        | 4286/28080 [8:29:02<46:53:28,  7.09s/it]
 15%|█▌        | 4287/28080 [8:29:10<46:57:40,  7.11s/it]
                                                         
{'loss': 0.656, 'learning_rate': 0.0004805330015353888, 'epoch': 1.83}

 15%|█▌        | 4287/28080 [8:29:10<46:57:40,  7.11s/it]
 15%|█▌        | 4288/28080 [8:29:17<46:55:38,  7.10s/it]
                                                         
{'loss': 0.6764, 'learning_rate': 0.00048052184417650623, 'epoch': 1.83}

 15%|█▌        | 4288/28080 [8:29:17<46:55:38,  7.10s/it]
 15%|█▌        | 4289/28080 [8:29:24<47:01:01,  7.11s/it]
                                                         
{'loss': 0.6501, 'learning_rate': 0.00048051068375076826, 'epoch': 1.83}

 15%|█▌        | 4289/28080 [8:29:24<47:01:01,  7.11s/it]
 15%|█▌        | 4290/28080 [8:29:31<47:17:54,  7.16s/it]
                                                         
{'loss': 0.638, 'learning_rate': 0.0004804995202583235, 'epoch': 1.83}

 15%|█▌        | 4290/28080 [8:29:31<47:17:54,  7.16s/it]
 15%|█▌        | 4291/28080 [8:29:38<47:00:05,  7.11s/it]
                                                         
{'loss': 0.6879, 'learning_rate': 0.00048048835369932037, 'epoch': 1.83}

 15%|█▌        | 4291/28080 [8:29:38<47:00:05,  7.11s/it]
 15%|█▌        | 4292/28080 [8:29:45<47:00:47,  7.11s/it]
                                                         
{'loss': 0.6438, 'learning_rate': 0.0004804771840739075, 'epoch': 1.83}

 15%|█▌        | 4292/28080 [8:29:45<47:00:47,  7.11s/it]
 15%|█▌        | 4293/28080 [8:29:52<46:54:22,  7.10s/it]
                                                         
{'loss': 0.6574, 'learning_rate': 0.00048046601138223346, 'epoch': 1.83}

 15%|█▌        | 4293/28080 [8:29:52<46:54:22,  7.10s/it]
 15%|█▌        | 4294/28080 [8:29:59<46:49:10,  7.09s/it]
                                                         
{'loss': 0.6389, 'learning_rate': 0.0004804548356244469, 'epoch': 1.83}

 15%|█▌        | 4294/28080 [8:29:59<46:49:10,  7.09s/it]
 15%|█▌        | 4295/28080 [8:30:06<46:55:21,  7.10s/it]
                                                         
{'loss': 0.6566, 'learning_rate': 0.0004804436568006965, 'epoch': 1.83}

 15%|█▌        | 4295/28080 [8:30:06<46:55:21,  7.10s/it]
 15%|█▌        | 4296/28080 [8:30:14<47:08:29,  7.14s/it]
                                                         
{'loss': 0.6545, 'learning_rate': 0.00048043247491113097, 'epoch': 1.84}

 15%|█▌        | 4296/28080 [8:30:14<47:08:29,  7.14s/it]
 15%|█▌        | 4297/28080 [8:30:21<47:13:14,  7.15s/it]
                                                         
{'loss': 0.6753, 'learning_rate': 0.00048042128995589905, 'epoch': 1.84}

 15%|█▌        | 4297/28080 [8:30:21<47:13:14,  7.15s/it]
 15%|█▌        | 4298/28080 [8:30:28<46:58:20,  7.11s/it]
                                                         
{'loss': 0.6653, 'learning_rate': 0.0004804101019351497, 'epoch': 1.84}

 15%|█▌        | 4298/28080 [8:30:28<46:58:20,  7.11s/it]
 15%|█▌        | 4299/28080 [8:30:35<46:52:45,  7.10s/it]
                                                         
{'loss': 0.6415, 'learning_rate': 0.00048039891084903155, 'epoch': 1.84}

 15%|█▌        | 4299/28080 [8:30:35<46:52:45,  7.10s/it]
 15%|█▌        | 4300/28080 [8:30:42<47:12:41,  7.15s/it]
                                                         
{'loss': 0.6568, 'learning_rate': 0.0004803877166976936, 'epoch': 1.84}

 15%|█▌        | 4300/28080 [8:30:42<47:12:41,  7.15s/it]
 15%|█▌        | 4301/28080 [8:30:49<46:48:08,  7.09s/it]
                                                         
{'loss': 0.6516, 'learning_rate': 0.0004803765194812847, 'epoch': 1.84}

 15%|█▌        | 4301/28080 [8:30:49<46:48:08,  7.09s/it]
 15%|█▌        | 4302/28080 [8:30:56<46:57:45,  7.11s/it]
                                                         
{'loss': 0.643, 'learning_rate': 0.00048036531919995397, 'epoch': 1.84}

 15%|█▌        | 4302/28080 [8:30:56<46:57:45,  7.11s/it]
 15%|█▌        | 4303/28080 [8:31:03<46:57:05,  7.11s/it]
                                                         
{'loss': 0.6614, 'learning_rate': 0.0004803541158538503, 'epoch': 1.84}

 15%|█▌        | 4303/28080 [8:31:03<46:57:05,  7.11s/it]
 15%|█▌        | 4304/28080 [8:31:11<46:56:17,  7.11s/it]
                                                         
{'loss': 0.653, 'learning_rate': 0.0004803429094431228, 'epoch': 1.84}

 15%|█▌        | 4304/28080 [8:31:11<46:56:17,  7.11s/it]
 15%|█▌        | 4305/28080 [8:31:18<47:02:22,  7.12s/it]
                                                         
{'loss': 0.6798, 'learning_rate': 0.00048033169996792034, 'epoch': 1.84}

 15%|█▌        | 4305/28080 [8:31:18<47:02:22,  7.12s/it]
 15%|█▌        | 4306/28080 [8:31:25<46:59:40,  7.12s/it]
                                                         
{'loss': 0.6328, 'learning_rate': 0.0004803204874283924, 'epoch': 1.84}

 15%|█▌        | 4306/28080 [8:31:25<46:59:40,  7.12s/it]
 15%|█▌        | 4307/28080 [8:31:32<46:56:16,  7.11s/it]
                                                         
{'loss': 0.6654, 'learning_rate': 0.000480309271824688, 'epoch': 1.84}

 15%|█▌        | 4307/28080 [8:31:32<46:56:16,  7.11s/it]
 15%|█▌        | 4308/28080 [8:31:39<46:53:49,  7.10s/it]
                                                         
{'loss': 0.6625, 'learning_rate': 0.0004802980531569563, 'epoch': 1.84}

 15%|█▌        | 4308/28080 [8:31:39<46:53:49,  7.10s/it]
 15%|█▌        | 4309/28080 [8:31:46<46:51:34,  7.10s/it]
                                                         
{'loss': 0.6514, 'learning_rate': 0.0004802868314253465, 'epoch': 1.84}

 15%|█▌        | 4309/28080 [8:31:46<46:51:34,  7.10s/it]
 15%|█▌        | 4310/28080 [8:31:53<46:53:15,  7.10s/it]
                                                         
{'loss': 0.641, 'learning_rate': 0.000480275606630008, 'epoch': 1.84}

 15%|█▌        | 4310/28080 [8:31:53<46:53:15,  7.10s/it]
 15%|█▌        | 4311/28080 [8:32:00<46:54:34,  7.10s/it]
                                                         
{'loss': 0.6587, 'learning_rate': 0.00048026437877109017, 'epoch': 1.84}

 15%|█▌        | 4311/28080 [8:32:00<46:54:34,  7.10s/it]
 15%|█▌        | 4312/28080 [8:32:07<46:59:43,  7.12s/it]
                                                         
{'loss': 0.6451, 'learning_rate': 0.0004802531478487424, 'epoch': 1.84}

 15%|█▌        | 4312/28080 [8:32:07<46:59:43,  7.12s/it]
 15%|█▌        | 4313/28080 [8:32:15<47:05:59,  7.13s/it]
                                                         
{'loss': 0.6512, 'learning_rate': 0.00048024191386311394, 'epoch': 1.84}

 15%|█▌        | 4313/28080 [8:32:15<47:05:59,  7.13s/it]
 15%|█▌        | 4314/28080 [8:32:22<47:04:33,  7.13s/it]
                                                         
{'loss': 0.6225, 'learning_rate': 0.0004802306768143544, 'epoch': 1.84}

 15%|█▌        | 4314/28080 [8:32:22<47:04:33,  7.13s/it]
 15%|█▌        | 4315/28080 [8:32:29<46:59:26,  7.12s/it]
                                                         
{'loss': 0.6761, 'learning_rate': 0.00048021943670261314, 'epoch': 1.84}

 15%|█▌        | 4315/28080 [8:32:29<46:59:26,  7.12s/it]
 15%|█▌        | 4316/28080 [8:32:36<47:07:54,  7.14s/it]
                                                         
{'loss': 0.6577, 'learning_rate': 0.0004802081935280398, 'epoch': 1.84}

 15%|█▌        | 4316/28080 [8:32:36<47:07:54,  7.14s/it]
 15%|█▌        | 4317/28080 [8:32:43<46:57:01,  7.11s/it]
                                                         
{'loss': 0.6375, 'learning_rate': 0.000480196947290784, 'epoch': 1.84}

 15%|█▌        | 4317/28080 [8:32:43<46:57:01,  7.11s/it]
 15%|█▌        | 4318/28080 [8:32:50<46:56:04,  7.11s/it]
                                                         
{'loss': 0.65, 'learning_rate': 0.0004801856979909952, 'epoch': 1.84}

 15%|█▌        | 4318/28080 [8:32:50<46:56:04,  7.11s/it]
 15%|█▌        | 4319/28080 [8:32:57<47:06:11,  7.14s/it]
                                                         
{'loss': 0.6645, 'learning_rate': 0.00048017444562882327, 'epoch': 1.85}

 15%|█▌        | 4319/28080 [8:32:57<47:06:11,  7.14s/it]
 15%|█▌        | 4320/28080 [8:33:04<47:04:43,  7.13s/it]
                                                         
{'loss': 0.6491, 'learning_rate': 0.00048016319020441773, 'epoch': 1.85}

 15%|█▌        | 4320/28080 [8:33:04<47:04:43,  7.13s/it]
 15%|█▌        | 4321/28080 [8:33:12<47:08:25,  7.14s/it]
                                                         
{'loss': 0.6464, 'learning_rate': 0.0004801519317179284, 'epoch': 1.85}

 15%|█▌        | 4321/28080 [8:33:12<47:08:25,  7.14s/it]
 15%|█▌        | 4322/28080 [8:33:19<46:59:19,  7.12s/it]
                                                         
{'loss': 0.6735, 'learning_rate': 0.00048014067016950506, 'epoch': 1.85}

 15%|█▌        | 4322/28080 [8:33:19<46:59:19,  7.12s/it]
 15%|█▌        | 4323/28080 [8:33:26<46:59:20,  7.12s/it]
                                                         
{'loss': 0.6532, 'learning_rate': 0.0004801294055592975, 'epoch': 1.85}

 15%|█▌        | 4323/28080 [8:33:26<46:59:20,  7.12s/it]
 15%|█▌        | 4324/28080 [8:33:33<47:07:45,  7.14s/it]
                                                         
{'loss': 0.6461, 'learning_rate': 0.00048011813788745566, 'epoch': 1.85}

 15%|█▌        | 4324/28080 [8:33:33<47:07:45,  7.14s/it]
 15%|█▌        | 4325/28080 [8:33:40<46:47:06,  7.09s/it]
                                                         
{'loss': 0.674, 'learning_rate': 0.0004801068671541294, 'epoch': 1.85}

 15%|█▌        | 4325/28080 [8:33:40<46:47:06,  7.09s/it]
 15%|█▌        | 4326/28080 [8:33:47<46:58:11,  7.12s/it]
                                                         
{'loss': 0.6731, 'learning_rate': 0.00048009559335946865, 'epoch': 1.85}

 15%|█▌        | 4326/28080 [8:33:47<46:58:11,  7.12s/it]
 15%|█▌        | 4327/28080 [8:33:54<46:55:01,  7.11s/it]
                                                         
{'loss': 0.6583, 'learning_rate': 0.00048008431650362337, 'epoch': 1.85}

 15%|█▌        | 4327/28080 [8:33:54<46:55:01,  7.11s/it]
 15%|█▌        | 4328/28080 [8:34:01<46:53:35,  7.11s/it]
                                                         
{'loss': 0.6375, 'learning_rate': 0.00048007303658674364, 'epoch': 1.85}

 15%|█▌        | 4328/28080 [8:34:01<46:53:35,  7.11s/it]
 15%|█▌        | 4329/28080 [8:34:08<46:51:21,  7.10s/it]
                                                         
{'loss': 0.6498, 'learning_rate': 0.0004800617536089795, 'epoch': 1.85}

 15%|█▌        | 4329/28080 [8:34:08<46:51:21,  7.10s/it]
 15%|█▌        | 4330/28080 [8:34:16<46:51:56,  7.10s/it]
                                                         
{'loss': 0.6483, 'learning_rate': 0.00048005046757048107, 'epoch': 1.85}

 15%|█▌        | 4330/28080 [8:34:16<46:51:56,  7.10s/it]
 15%|█▌        | 4331/28080 [8:34:23<47:00:56,  7.13s/it]
                                                         
{'loss': 0.6498, 'learning_rate': 0.0004800391784713985, 'epoch': 1.85}

 15%|█▌        | 4331/28080 [8:34:23<47:00:56,  7.13s/it]
 15%|█▌        | 4332/28080 [8:34:30<46:51:15,  7.10s/it]
                                                         
{'loss': 0.6622, 'learning_rate': 0.00048002788631188196, 'epoch': 1.85}

 15%|█▌        | 4332/28080 [8:34:30<46:51:15,  7.10s/it]
 15%|█▌        | 4333/28080 [8:34:37<47:03:28,  7.13s/it]
                                                         
{'loss': 0.6502, 'learning_rate': 0.00048001659109208174, 'epoch': 1.85}

 15%|█▌        | 4333/28080 [8:34:37<47:03:28,  7.13s/it]
 15%|█▌        | 4334/28080 [8:34:44<47:07:03,  7.14s/it]
                                                         
{'loss': 0.6557, 'learning_rate': 0.0004800052928121481, 'epoch': 1.85}

 15%|█▌        | 4334/28080 [8:34:44<47:07:03,  7.14s/it]
 15%|█▌        | 4335/28080 [8:34:51<47:03:59,  7.14s/it]
                                                         
{'loss': 0.6574, 'learning_rate': 0.00047999399147223126, 'epoch': 1.85}

 15%|█▌        | 4335/28080 [8:34:51<47:03:59,  7.14s/it]
 15%|█▌        | 4336/28080 [8:34:58<47:00:01,  7.13s/it]
                                                         
{'loss': 0.6428, 'learning_rate': 0.00047998268707248165, 'epoch': 1.85}

 15%|█▌        | 4336/28080 [8:34:58<47:00:01,  7.13s/it]
 15%|█▌        | 4337/28080 [8:35:05<46:54:28,  7.11s/it]
                                                         
{'loss': 0.6616, 'learning_rate': 0.0004799713796130497, 'epoch': 1.85}

 15%|█▌        | 4337/28080 [8:35:05<46:54:28,  7.11s/it]
 15%|█▌        | 4338/28080 [8:35:13<46:51:57,  7.11s/it]
                                                         
{'loss': 0.6565, 'learning_rate': 0.00047996006909408574, 'epoch': 1.85}

 15%|█▌        | 4338/28080 [8:35:13<46:51:57,  7.11s/it]
 15%|█▌        | 4339/28080 [8:35:20<46:54:29,  7.11s/it]
                                                         
{'loss': 0.6492, 'learning_rate': 0.0004799487555157403, 'epoch': 1.85}

 15%|█▌        | 4339/28080 [8:35:20<46:54:29,  7.11s/it]
 15%|█▌        | 4340/28080 [8:35:27<47:02:52,  7.13s/it]
                                                         
{'loss': 0.6414, 'learning_rate': 0.0004799374388781639, 'epoch': 1.85}

 15%|█▌        | 4340/28080 [8:35:27<47:02:52,  7.13s/it]
 15%|█▌        | 4341/28080 [8:35:34<46:53:27,  7.11s/it]
                                                         
{'loss': 0.6657, 'learning_rate': 0.0004799261191815071, 'epoch': 1.85}

 15%|█▌        | 4341/28080 [8:35:34<46:53:27,  7.11s/it]
 15%|█▌        | 4342/28080 [8:35:41<46:49:19,  7.10s/it]
                                                         
{'loss': 0.6323, 'learning_rate': 0.00047991479642592045, 'epoch': 1.85}

 15%|█▌        | 4342/28080 [8:35:41<46:49:19,  7.10s/it]
 15%|█▌        | 4343/28080 [8:35:48<47:03:24,  7.14s/it]
                                                         
{'loss': 0.6546, 'learning_rate': 0.00047990347061155467, 'epoch': 1.86}

 15%|█▌        | 4343/28080 [8:35:48<47:03:24,  7.14s/it]
 15%|█▌        | 4344/28080 [8:35:55<47:00:19,  7.13s/it]
                                                         
{'loss': 0.6544, 'learning_rate': 0.00047989214173856033, 'epoch': 1.86}

 15%|█▌        | 4344/28080 [8:35:55<47:00:19,  7.13s/it]
 15%|█▌        | 4345/28080 [8:36:02<47:00:29,  7.13s/it]
                                                         
{'loss': 0.6275, 'learning_rate': 0.00047988080980708827, 'epoch': 1.86}

 15%|█▌        | 4345/28080 [8:36:02<47:00:29,  7.13s/it]
 15%|█▌        | 4346/28080 [8:36:10<47:09:57,  7.15s/it]
                                                         
{'loss': 0.6522, 'learning_rate': 0.0004798694748172892, 'epoch': 1.86}

 15%|█▌        | 4346/28080 [8:36:10<47:09:57,  7.15s/it]
 15%|█▌        | 4347/28080 [8:36:17<46:57:55,  7.12s/it]
                                                         
{'loss': 0.6509, 'learning_rate': 0.0004798581367693138, 'epoch': 1.86}

 15%|█▌        | 4347/28080 [8:36:17<46:57:55,  7.12s/it]
 15%|█▌        | 4348/28080 [8:36:24<46:48:59,  7.10s/it]
                                                         
{'loss': 0.6624, 'learning_rate': 0.00047984679566331315, 'epoch': 1.86}

 15%|█▌        | 4348/28080 [8:36:24<46:48:59,  7.10s/it]
 15%|█▌        | 4349/28080 [8:36:31<46:46:33,  7.10s/it]
                                                         
{'loss': 0.6486, 'learning_rate': 0.00047983545149943795, 'epoch': 1.86}

 15%|█▌        | 4349/28080 [8:36:31<46:46:33,  7.10s/it]
 15%|█▌        | 4350/28080 [8:36:38<46:50:44,  7.11s/it]
                                                         
{'loss': 0.6466, 'learning_rate': 0.0004798241042778392, 'epoch': 1.86}

 15%|█▌        | 4350/28080 [8:36:38<46:50:44,  7.11s/it]
 15%|█▌        | 4351/28080 [8:36:45<46:48:21,  7.10s/it]
                                                         
{'loss': 0.6435, 'learning_rate': 0.0004798127539986678, 'epoch': 1.86}

 15%|█▌        | 4351/28080 [8:36:45<46:48:21,  7.10s/it]
 15%|█▌        | 4352/28080 [8:36:52<47:00:10,  7.13s/it]
                                                         
{'loss': 0.6293, 'learning_rate': 0.0004798014006620748, 'epoch': 1.86}

 15%|█▌        | 4352/28080 [8:36:52<47:00:10,  7.13s/it]
 16%|█▌        | 4353/28080 [8:36:59<46:46:52,  7.10s/it]
                                                         
{'loss': 0.6629, 'learning_rate': 0.0004797900442682113, 'epoch': 1.86}

 16%|█▌        | 4353/28080 [8:36:59<46:46:52,  7.10s/it]
 16%|█▌        | 4354/28080 [8:37:06<46:51:23,  7.11s/it]
                                                         
{'loss': 0.6496, 'learning_rate': 0.0004797786848172282, 'epoch': 1.86}

 16%|█▌        | 4354/28080 [8:37:06<46:51:23,  7.11s/it]
 16%|█▌        | 4355/28080 [8:37:14<47:01:31,  7.14s/it]
                                                         
{'loss': 0.6551, 'learning_rate': 0.0004797673223092769, 'epoch': 1.86}

 16%|█▌        | 4355/28080 [8:37:14<47:01:31,  7.14s/it]
 16%|█▌        | 4356/28080 [8:37:21<46:53:07,  7.11s/it]
                                                         
{'loss': 0.6603, 'learning_rate': 0.0004797559567445083, 'epoch': 1.86}

 16%|█▌        | 4356/28080 [8:37:21<46:53:07,  7.11s/it]
 16%|█▌        | 4357/28080 [8:37:28<46:50:51,  7.11s/it]
                                                         
{'loss': 0.6591, 'learning_rate': 0.0004797445881230738, 'epoch': 1.86}

 16%|█▌        | 4357/28080 [8:37:28<46:50:51,  7.11s/it]
 16%|█▌        | 4358/28080 [8:37:35<46:56:52,  7.12s/it]
                                                         
{'loss': 0.6581, 'learning_rate': 0.00047973321644512445, 'epoch': 1.86}

 16%|█▌        | 4358/28080 [8:37:35<46:56:52,  7.12s/it]
 16%|█▌        | 4359/28080 [8:37:42<46:59:41,  7.13s/it]
                                                         
{'loss': 0.6424, 'learning_rate': 0.0004797218417108118, 'epoch': 1.86}

 16%|█▌        | 4359/28080 [8:37:42<46:59:41,  7.13s/it]
 16%|█▌        | 4360/28080 [8:37:49<46:46:55,  7.10s/it]
                                                         
{'loss': 0.6668, 'learning_rate': 0.00047971046392028695, 'epoch': 1.86}

 16%|█▌        | 4360/28080 [8:37:49<46:46:55,  7.10s/it]
 16%|█▌        | 4361/28080 [8:37:56<46:44:25,  7.09s/it]
                                                         
{'loss': 0.6589, 'learning_rate': 0.00047969908307370134, 'epoch': 1.86}

 16%|█▌        | 4361/28080 [8:37:56<46:44:25,  7.09s/it]
 16%|█▌        | 4362/28080 [8:38:03<46:45:05,  7.10s/it]
                                                         
{'loss': 0.6496, 'learning_rate': 0.00047968769917120646, 'epoch': 1.86}

 16%|█▌        | 4362/28080 [8:38:03<46:45:05,  7.10s/it]
 16%|█▌        | 4363/28080 [8:38:10<46:35:33,  7.07s/it]
                                                         
{'loss': 0.6708, 'learning_rate': 0.0004796763122129537, 'epoch': 1.86}

 16%|█▌        | 4363/28080 [8:38:10<46:35:33,  7.07s/it]
 16%|█▌        | 4364/28080 [8:38:17<46:43:14,  7.09s/it]
                                                         
{'loss': 0.6431, 'learning_rate': 0.00047966492219909447, 'epoch': 1.86}

 16%|█▌        | 4364/28080 [8:38:17<46:43:14,  7.09s/it]
 16%|█▌        | 4365/28080 [8:38:25<46:42:22,  7.09s/it]
                                                         
{'loss': 0.6416, 'learning_rate': 0.00047965352912978043, 'epoch': 1.86}

 16%|█▌        | 4365/28080 [8:38:25<46:42:22,  7.09s/it]
 16%|█▌        | 4366/28080 [8:38:32<46:42:41,  7.09s/it]
                                                         
{'loss': 0.6621, 'learning_rate': 0.0004796421330051631, 'epoch': 1.87}

 16%|█▌        | 4366/28080 [8:38:32<46:42:41,  7.09s/it]
 16%|█▌        | 4367/28080 [8:38:39<46:46:01,  7.10s/it]
                                                         
{'loss': 0.6549, 'learning_rate': 0.00047963073382539415, 'epoch': 1.87}

 16%|█▌        | 4367/28080 [8:38:39<46:46:01,  7.10s/it]
 16%|█▌        | 4368/28080 [8:38:46<46:55:01,  7.12s/it]
                                                         
{'loss': 0.6551, 'learning_rate': 0.0004796193315906251, 'epoch': 1.87}

 16%|█▌        | 4368/28080 [8:38:46<46:55:01,  7.12s/it]
 16%|█▌        | 4369/28080 [8:38:53<46:56:36,  7.13s/it]
                                                         
{'loss': 0.6467, 'learning_rate': 0.0004796079263010078, 'epoch': 1.87}

 16%|█▌        | 4369/28080 [8:38:53<46:56:36,  7.13s/it]
 16%|█▌        | 4370/28080 [8:39:00<47:00:11,  7.14s/it]
                                                         
{'loss': 0.645, 'learning_rate': 0.0004795965179566939, 'epoch': 1.87}

 16%|█▌        | 4370/28080 [8:39:00<47:00:11,  7.14s/it]
 16%|█▌        | 4371/28080 [8:39:07<47:00:14,  7.14s/it]
                                                         
{'loss': 0.6437, 'learning_rate': 0.0004795851065578352, 'epoch': 1.87}

 16%|█▌        | 4371/28080 [8:39:07<47:00:14,  7.14s/it]
 16%|█▌        | 4372/28080 [8:39:14<46:49:15,  7.11s/it]
                                                         
{'loss': 0.6394, 'learning_rate': 0.00047957369210458345, 'epoch': 1.87}

 16%|█▌        | 4372/28080 [8:39:14<46:49:15,  7.11s/it]
 16%|█▌        | 4373/28080 [8:39:21<46:44:12,  7.10s/it]
                                                         
{'loss': 0.6462, 'learning_rate': 0.00047956227459709056, 'epoch': 1.87}

 16%|█▌        | 4373/28080 [8:39:21<46:44:12,  7.10s/it]
 16%|█▌        | 4374/28080 [8:39:29<46:39:04,  7.08s/it]
                                                         
{'loss': 0.6489, 'learning_rate': 0.00047955085403550847, 'epoch': 1.87}

 16%|█▌        | 4374/28080 [8:39:29<46:39:04,  7.08s/it]
 16%|█▌        | 4375/28080 [8:39:36<46:46:14,  7.10s/it]
                                                         
{'loss': 0.6398, 'learning_rate': 0.00047953943041998906, 'epoch': 1.87}

 16%|█▌        | 4375/28080 [8:39:36<46:46:14,  7.10s/it]
 16%|█▌        | 4376/28080 [8:39:43<46:46:52,  7.10s/it]
                                                         
{'loss': 0.675, 'learning_rate': 0.0004795280037506844, 'epoch': 1.87}

 16%|█▌        | 4376/28080 [8:39:43<46:46:52,  7.10s/it]
 16%|█▌        | 4377/28080 [8:39:50<46:50:26,  7.11s/it]
                                                         
{'loss': 0.6551, 'learning_rate': 0.0004795165740277464, 'epoch': 1.87}

 16%|█▌        | 4377/28080 [8:39:50<46:50:26,  7.11s/it]
 16%|█▌        | 4378/28080 [8:39:57<46:41:49,  7.09s/it]
                                                         
{'loss': 0.6494, 'learning_rate': 0.0004795051412513271, 'epoch': 1.87}

 16%|█▌        | 4378/28080 [8:39:57<46:41:49,  7.09s/it]
 16%|█▌        | 4379/28080 [8:40:04<46:38:28,  7.08s/it]
                                                         
{'loss': 0.6573, 'learning_rate': 0.00047949370542157873, 'epoch': 1.87}

 16%|█▌        | 4379/28080 [8:40:04<46:38:28,  7.08s/it]
 16%|█▌        | 4380/28080 [8:40:11<46:43:25,  7.10s/it]
                                                         
{'loss': 0.6413, 'learning_rate': 0.00047948226653865333, 'epoch': 1.87}

 16%|█▌        | 4380/28080 [8:40:11<46:43:25,  7.10s/it]
 16%|█▌        | 4381/28080 [8:40:18<47:09:02,  7.16s/it]
                                                         
{'loss': 0.6635, 'learning_rate': 0.0004794708246027032, 'epoch': 1.87}

 16%|█▌        | 4381/28080 [8:40:18<47:09:02,  7.16s/it]
 16%|█▌        | 4382/28080 [8:40:26<47:06:15,  7.16s/it]
                                                         
{'loss': 0.6724, 'learning_rate': 0.00047945937961388043, 'epoch': 1.87}

 16%|█▌        | 4382/28080 [8:40:26<47:06:15,  7.16s/it]
 16%|█▌        | 4383/28080 [8:40:33<46:57:26,  7.13s/it]
                                                         
{'loss': 0.6617, 'learning_rate': 0.00047944793157233726, 'epoch': 1.87}

 16%|█▌        | 4383/28080 [8:40:33<46:57:26,  7.13s/it]
 16%|█▌        | 4384/28080 [8:40:40<46:49:09,  7.11s/it]
                                                         
{'loss': 0.6646, 'learning_rate': 0.0004794364804782262, 'epoch': 1.87}

 16%|█▌        | 4384/28080 [8:40:40<46:49:09,  7.11s/it]
 16%|█▌        | 4385/28080 [8:40:47<46:40:57,  7.09s/it]
                                                         
{'loss': 0.6498, 'learning_rate': 0.00047942502633169937, 'epoch': 1.87}

 16%|█▌        | 4385/28080 [8:40:47<46:40:57,  7.09s/it]
 16%|█▌        | 4386/28080 [8:40:54<46:44:30,  7.10s/it]
                                                         
{'loss': 0.6602, 'learning_rate': 0.00047941356913290924, 'epoch': 1.87}

 16%|█▌        | 4386/28080 [8:40:54<46:44:30,  7.10s/it]
 16%|█▌        | 4387/28080 [8:41:01<46:35:26,  7.08s/it]
                                                         
{'loss': 0.6474, 'learning_rate': 0.0004794021088820083, 'epoch': 1.87}

 16%|█▌        | 4387/28080 [8:41:01<46:35:26,  7.08s/it]
 16%|█▌        | 4388/28080 [8:41:08<46:43:24,  7.10s/it]
                                                         
{'loss': 0.6464, 'learning_rate': 0.0004793906455791489, 'epoch': 1.87}

 16%|█▌        | 4388/28080 [8:41:08<46:43:24,  7.10s/it]
 16%|█▌        | 4389/28080 [8:41:15<46:42:10,  7.10s/it]
                                                         
{'loss': 0.6409, 'learning_rate': 0.0004793791792244837, 'epoch': 1.87}

 16%|█▌        | 4389/28080 [8:41:15<46:42:10,  7.10s/it]
 16%|█▌        | 4390/28080 [8:41:22<46:41:16,  7.09s/it]
                                                         
{'loss': 0.6693, 'learning_rate': 0.00047936770981816515, 'epoch': 1.88}

 16%|█▌        | 4390/28080 [8:41:22<46:41:16,  7.09s/it]
 16%|█▌        | 4391/28080 [8:41:29<46:34:11,  7.08s/it]
                                                         
{'loss': 0.6605, 'learning_rate': 0.00047935623736034574, 'epoch': 1.88}

 16%|█▌        | 4391/28080 [8:41:29<46:34:11,  7.08s/it]
 16%|█▌        | 4392/28080 [8:41:36<46:41:22,  7.10s/it]
                                                         
{'loss': 0.6473, 'learning_rate': 0.00047934476185117826, 'epoch': 1.88}

 16%|█▌        | 4392/28080 [8:41:36<46:41:22,  7.10s/it]
 16%|█▌        | 4393/28080 [8:41:44<46:51:52,  7.12s/it]
                                                         
{'loss': 0.654, 'learning_rate': 0.00047933328329081537, 'epoch': 1.88}

 16%|█▌        | 4393/28080 [8:41:44<46:51:52,  7.12s/it]
 16%|█▌        | 4394/28080 [8:41:51<46:39:16,  7.09s/it]
                                                         
{'loss': 0.673, 'learning_rate': 0.0004793218016794097, 'epoch': 1.88}

 16%|█▌        | 4394/28080 [8:41:51<46:39:16,  7.09s/it]
 16%|█▌        | 4395/28080 [8:41:58<46:30:53,  7.07s/it]
                                                         
{'loss': 0.6729, 'learning_rate': 0.00047931031701711405, 'epoch': 1.88}

 16%|█▌        | 4395/28080 [8:41:58<46:30:53,  7.07s/it]
 16%|█▌        | 4396/28080 [8:42:05<46:37:15,  7.09s/it]
                                                         
{'loss': 0.6588, 'learning_rate': 0.0004792988293040812, 'epoch': 1.88}

 16%|█▌        | 4396/28080 [8:42:05<46:37:15,  7.09s/it]
 16%|█▌        | 4397/28080 [8:42:12<46:31:47,  7.07s/it]
                                                         
{'loss': 0.6754, 'learning_rate': 0.0004792873385404639, 'epoch': 1.88}

 16%|█▌        | 4397/28080 [8:42:12<46:31:47,  7.07s/it]
 16%|█▌        | 4398/28080 [8:42:19<46:31:52,  7.07s/it]
                                                         
{'loss': 0.6711, 'learning_rate': 0.0004792758447264152, 'epoch': 1.88}

 16%|█▌        | 4398/28080 [8:42:19<46:31:52,  7.07s/it]
 16%|█▌        | 4399/28080 [8:42:26<46:35:37,  7.08s/it]
                                                         
{'loss': 0.6427, 'learning_rate': 0.0004792643478620879, 'epoch': 1.88}

 16%|█▌        | 4399/28080 [8:42:26<46:35:37,  7.08s/it]
 16%|█▌        | 4400/28080 [8:42:33<46:42:02,  7.10s/it]
                                                         
{'loss': 0.6485, 'learning_rate': 0.00047925284794763496, 'epoch': 1.88}

 16%|█▌        | 4400/28080 [8:42:33<46:42:02,  7.10s/it]
 16%|█▌        | 4401/28080 [8:42:40<46:38:23,  7.09s/it]
                                                         
{'loss': 0.6654, 'learning_rate': 0.00047924134498320936, 'epoch': 1.88}

 16%|█▌        | 4401/28080 [8:42:40<46:38:23,  7.09s/it]
 16%|█▌        | 4402/28080 [8:42:47<46:35:45,  7.08s/it]
                                                         
{'loss': 0.6574, 'learning_rate': 0.0004792298389689642, 'epoch': 1.88}

 16%|█▌        | 4402/28080 [8:42:47<46:35:45,  7.08s/it]
 16%|█▌        | 4403/28080 [8:42:55<46:49:54,  7.12s/it]
                                                         
{'loss': 0.6418, 'learning_rate': 0.00047921832990505255, 'epoch': 1.88}

 16%|█▌        | 4403/28080 [8:42:55<46:49:54,  7.12s/it]
 16%|█▌        | 4404/28080 [8:43:02<46:41:19,  7.10s/it]
                                                         
{'loss': 0.6515, 'learning_rate': 0.0004792068177916274, 'epoch': 1.88}

 16%|█▌        | 4404/28080 [8:43:02<46:41:19,  7.10s/it]
 16%|█▌        | 4405/28080 [8:43:09<46:51:52,  7.13s/it]
                                                         
{'loss': 0.6364, 'learning_rate': 0.00047919530262884204, 'epoch': 1.88}

 16%|█▌        | 4405/28080 [8:43:09<46:51:52,  7.13s/it]
 16%|█▌        | 4406/28080 [8:43:16<46:43:10,  7.10s/it]
                                                         
{'loss': 0.6415, 'learning_rate': 0.0004791837844168496, 'epoch': 1.88}

 16%|█▌        | 4406/28080 [8:43:16<46:43:10,  7.10s/it]
 16%|█▌        | 4407/28080 [8:43:23<46:35:07,  7.08s/it]
                                                         
{'loss': 0.67, 'learning_rate': 0.00047917226315580345, 'epoch': 1.88}

 16%|█▌        | 4407/28080 [8:43:23<46:35:07,  7.08s/it]
 16%|█▌        | 4408/28080 [8:43:30<46:39:40,  7.10s/it]
                                                         
{'loss': 0.6444, 'learning_rate': 0.00047916073884585663, 'epoch': 1.88}

 16%|█▌        | 4408/28080 [8:43:30<46:39:40,  7.10s/it]
 16%|█▌        | 4409/28080 [8:43:37<46:26:35,  7.06s/it]
                                                         
{'loss': 0.6444, 'learning_rate': 0.00047914921148716264, 'epoch': 1.88}

 16%|█▌        | 4409/28080 [8:43:37<46:26:35,  7.06s/it]
 16%|█▌        | 4410/28080 [8:43:44<46:27:22,  7.07s/it]
                                                         
{'loss': 0.661, 'learning_rate': 0.0004791376810798748, 'epoch': 1.88}

 16%|█▌        | 4410/28080 [8:43:44<46:27:22,  7.07s/it]
 16%|█▌        | 4411/28080 [8:43:51<46:44:33,  7.11s/it]
                                                         
{'loss': 0.6382, 'learning_rate': 0.00047912614762414654, 'epoch': 1.88}

 16%|█▌        | 4411/28080 [8:43:51<46:44:33,  7.11s/it]
 16%|█▌        | 4412/28080 [8:43:58<46:36:54,  7.09s/it]
                                                         
{'loss': 0.6696, 'learning_rate': 0.0004791146111201312, 'epoch': 1.88}

 16%|█▌        | 4412/28080 [8:43:58<46:36:54,  7.09s/it]
 16%|█▌        | 4413/28080 [8:44:05<46:39:52,  7.10s/it]
                                                         
{'loss': 0.6153, 'learning_rate': 0.0004791030715679823, 'epoch': 1.89}

 16%|█▌        | 4413/28080 [8:44:05<46:39:52,  7.10s/it]
 16%|█▌        | 4414/28080 [8:44:12<46:39:07,  7.10s/it]
                                                         
{'loss': 0.6809, 'learning_rate': 0.00047909152896785347, 'epoch': 1.89}

 16%|█▌        | 4414/28080 [8:44:13<46:39:07,  7.10s/it]
 16%|█▌        | 4415/28080 [8:44:19<46:20:29,  7.05s/it]
                                                         
{'loss': 0.644, 'learning_rate': 0.0004790799833198981, 'epoch': 1.89}

 16%|█▌        | 4415/28080 [8:44:19<46:20:29,  7.05s/it]
 16%|█▌        | 4416/28080 [8:44:27<46:27:48,  7.07s/it]
                                                         
{'loss': 0.6481, 'learning_rate': 0.00047906843462427, 'epoch': 1.89}

 16%|█▌        | 4416/28080 [8:44:27<46:27:48,  7.07s/it]
 16%|█▌        | 4417/28080 [8:44:34<46:23:48,  7.06s/it]
                                                         
{'loss': 0.6576, 'learning_rate': 0.0004790568828811226, 'epoch': 1.89}

 16%|█▌        | 4417/28080 [8:44:34<46:23:48,  7.06s/it]
 16%|█▌        | 4418/28080 [8:44:41<46:31:21,  7.08s/it]
                                                         
{'loss': 0.6459, 'learning_rate': 0.0004790453280906097, 'epoch': 1.89}

 16%|█▌        | 4418/28080 [8:44:41<46:31:21,  7.08s/it]
 16%|█▌        | 4419/28080 [8:44:48<46:36:00,  7.09s/it]
                                                         
{'loss': 0.65, 'learning_rate': 0.000479033770252885, 'epoch': 1.89}

 16%|█▌        | 4419/28080 [8:44:48<46:36:00,  7.09s/it]
 16%|█▌        | 4420/28080 [8:44:55<46:39:48,  7.10s/it]
                                                         
{'loss': 0.6507, 'learning_rate': 0.00047902220936810224, 'epoch': 1.89}

 16%|█▌        | 4420/28080 [8:44:55<46:39:48,  7.10s/it]
 16%|█▌        | 4421/28080 [8:45:02<46:48:14,  7.12s/it]
                                                         
{'loss': 0.6429, 'learning_rate': 0.0004790106454364153, 'epoch': 1.89}

 16%|█▌        | 4421/28080 [8:45:02<46:48:14,  7.12s/it]
 16%|█▌        | 4422/28080 [8:45:09<46:40:27,  7.10s/it]
                                                         
{'loss': 0.6678, 'learning_rate': 0.000478999078457978, 'epoch': 1.89}

 16%|█▌        | 4422/28080 [8:45:09<46:40:27,  7.10s/it]
 16%|█▌        | 4423/28080 [8:45:16<46:43:36,  7.11s/it]
                                                         
{'loss': 0.6432, 'learning_rate': 0.00047898750843294413, 'epoch': 1.89}

 16%|█▌        | 4423/28080 [8:45:16<46:43:36,  7.11s/it]
 16%|█▌        | 4424/28080 [8:45:23<46:52:47,  7.13s/it]
                                                         
{'loss': 0.6382, 'learning_rate': 0.0004789759353614678, 'epoch': 1.89}

 16%|█▌        | 4424/28080 [8:45:23<46:52:47,  7.13s/it]
 16%|█▌        | 4425/28080 [8:45:31<46:53:17,  7.14s/it]
                                                         
{'loss': 0.6521, 'learning_rate': 0.00047896435924370273, 'epoch': 1.89}

 16%|█▌        | 4425/28080 [8:45:31<46:53:17,  7.14s/it]
 16%|█▌        | 4426/28080 [8:45:38<46:37:29,  7.10s/it]
                                                         
{'loss': 0.6671, 'learning_rate': 0.00047895278007980315, 'epoch': 1.89}

 16%|█▌        | 4426/28080 [8:45:38<46:37:29,  7.10s/it]
 16%|█▌        | 4427/28080 [8:45:45<46:40:04,  7.10s/it]
                                                         
{'loss': 0.6402, 'learning_rate': 0.00047894119786992306, 'epoch': 1.89}

 16%|█▌        | 4427/28080 [8:45:45<46:40:04,  7.10s/it]
 16%|█▌        | 4428/28080 [8:45:52<46:45:36,  7.12s/it]
                                                         
{'loss': 0.6575, 'learning_rate': 0.0004789296126142164, 'epoch': 1.89}

 16%|█▌        | 4428/28080 [8:45:52<46:45:36,  7.12s/it]
 16%|█▌        | 4429/28080 [8:45:59<46:45:40,  7.12s/it]
                                                         
{'loss': 0.6486, 'learning_rate': 0.0004789180243128376, 'epoch': 1.89}

 16%|█▌        | 4429/28080 [8:45:59<46:45:40,  7.12s/it]
 16%|█▌        | 4430/28080 [8:46:06<46:43:55,  7.11s/it]
                                                         
{'loss': 0.6591, 'learning_rate': 0.0004789064329659405, 'epoch': 1.89}

 16%|█▌        | 4430/28080 [8:46:06<46:43:55,  7.11s/it]
 16%|█▌        | 4431/28080 [8:46:13<46:38:54,  7.10s/it]
                                                         
{'loss': 0.6553, 'learning_rate': 0.00047889483857367957, 'epoch': 1.89}

 16%|█▌        | 4431/28080 [8:46:13<46:38:54,  7.10s/it]
 16%|█▌        | 4432/28080 [8:46:20<46:35:10,  7.09s/it]
                                                         
{'loss': 0.6461, 'learning_rate': 0.00047888324113620886, 'epoch': 1.89}

 16%|█▌        | 4432/28080 [8:46:20<46:35:10,  7.09s/it]
 16%|█▌        | 4433/28080 [8:46:27<46:35:16,  7.09s/it]
                                                         
{'loss': 0.6361, 'learning_rate': 0.00047887164065368274, 'epoch': 1.89}

 16%|█▌        | 4433/28080 [8:46:27<46:35:16,  7.09s/it]
 16%|█▌        | 4434/28080 [8:46:34<46:28:35,  7.08s/it]
                                                         
{'loss': 0.639, 'learning_rate': 0.0004788600371262556, 'epoch': 1.89}

 16%|█▌        | 4434/28080 [8:46:34<46:28:35,  7.08s/it]
 16%|█▌        | 4435/28080 [8:46:42<46:31:23,  7.08s/it]
                                                         
{'loss': 0.6695, 'learning_rate': 0.0004788484305540818, 'epoch': 1.89}

 16%|█▌        | 4435/28080 [8:46:42<46:31:23,  7.08s/it]
 16%|█▌        | 4436/28080 [8:46:49<46:40:46,  7.11s/it]
                                                         
{'loss': 0.643, 'learning_rate': 0.00047883682093731564, 'epoch': 1.9}

 16%|█▌        | 4436/28080 [8:46:49<46:40:46,  7.11s/it]
 16%|█▌        | 4437/28080 [8:46:56<46:46:52,  7.12s/it]
                                                         
{'loss': 0.6538, 'learning_rate': 0.0004788252082761117, 'epoch': 1.9}

 16%|█▌        | 4437/28080 [8:46:56<46:46:52,  7.12s/it]
 16%|█▌        | 4438/28080 [8:47:03<46:33:43,  7.09s/it]
                                                         
{'loss': 0.6554, 'learning_rate': 0.0004788135925706244, 'epoch': 1.9}

 16%|█▌        | 4438/28080 [8:47:03<46:33:43,  7.09s/it]
 16%|█▌        | 4439/28080 [8:47:10<46:36:17,  7.10s/it]
                                                         
{'loss': 0.6542, 'learning_rate': 0.00047880197382100837, 'epoch': 1.9}

 16%|█▌        | 4439/28080 [8:47:10<46:36:17,  7.10s/it]
 16%|█▌        | 4440/28080 [8:47:17<46:26:36,  7.07s/it]
                                                         
{'loss': 0.6664, 'learning_rate': 0.00047879035202741805, 'epoch': 1.9}

 16%|█▌        | 4440/28080 [8:47:17<46:26:36,  7.07s/it]
 16%|█▌        | 4441/28080 [8:47:24<46:40:54,  7.11s/it]
                                                         
{'loss': 0.6522, 'learning_rate': 0.00047877872719000815, 'epoch': 1.9}

 16%|█▌        | 4441/28080 [8:47:24<46:40:54,  7.11s/it]
 16%|█▌        | 4442/28080 [8:47:31<46:46:59,  7.12s/it]
                                                         
{'loss': 0.6603, 'learning_rate': 0.00047876709930893337, 'epoch': 1.9}

 16%|█▌        | 4442/28080 [8:47:31<46:46:59,  7.12s/it]
 16%|█▌        | 4443/28080 [8:47:39<46:54:46,  7.15s/it]
                                                         
{'loss': 0.6665, 'learning_rate': 0.00047875546838434827, 'epoch': 1.9}

 16%|█▌        | 4443/28080 [8:47:39<46:54:46,  7.15s/it]
 16%|█▌        | 4444/28080 [8:47:46<46:38:42,  7.10s/it]
                                                         
{'loss': 0.6311, 'learning_rate': 0.00047874383441640767, 'epoch': 1.9}

 16%|█▌        | 4444/28080 [8:47:46<46:38:42,  7.10s/it]
 16%|█▌        | 4445/28080 [8:47:53<46:43:20,  7.12s/it]
                                                         
{'loss': 0.6311, 'learning_rate': 0.0004787321974052663, 'epoch': 1.9}

 16%|█▌        | 4445/28080 [8:47:53<46:43:20,  7.12s/it]
 16%|█▌        | 4446/28080 [8:48:00<46:40:51,  7.11s/it]
                                                         
{'loss': 0.6455, 'learning_rate': 0.00047872055735107905, 'epoch': 1.9}

 16%|█▌        | 4446/28080 [8:48:00<46:40:51,  7.11s/it]
 16%|█▌        | 4447/28080 [8:48:07<46:32:14,  7.09s/it]
                                                         
{'loss': 0.653, 'learning_rate': 0.00047870891425400074, 'epoch': 1.9}

 16%|█▌        | 4447/28080 [8:48:07<46:32:14,  7.09s/it]
 16%|█▌        | 4448/28080 [8:48:14<46:37:36,  7.10s/it]
                                                         
{'loss': 0.6664, 'learning_rate': 0.0004786972681141863, 'epoch': 1.9}

 16%|█▌        | 4448/28080 [8:48:14<46:37:36,  7.10s/it]
 16%|█▌        | 4449/28080 [8:48:21<46:32:04,  7.09s/it]
                                                         
{'loss': 0.6512, 'learning_rate': 0.0004786856189317906, 'epoch': 1.9}

 16%|█▌        | 4449/28080 [8:48:21<46:32:04,  7.09s/it]
 16%|█▌        | 4450/28080 [8:48:28<46:28:13,  7.08s/it]
                                                         
{'loss': 0.6362, 'learning_rate': 0.00047867396670696864, 'epoch': 1.9}

 16%|█▌        | 4450/28080 [8:48:28<46:28:13,  7.08s/it]
 16%|█▌        | 4451/28080 [8:48:35<46:11:38,  7.04s/it]
                                                         
{'loss': 0.6547, 'learning_rate': 0.0004786623114398755, 'epoch': 1.9}

 16%|█▌        | 4451/28080 [8:48:35<46:11:38,  7.04s/it]
 16%|█▌        | 4452/28080 [8:48:42<46:07:52,  7.03s/it]
                                                         
{'loss': 0.6711, 'learning_rate': 0.00047865065313066626, 'epoch': 1.9}

 16%|█▌        | 4452/28080 [8:48:42<46:07:52,  7.03s/it]
 16%|█▌        | 4453/28080 [8:48:49<46:24:16,  7.07s/it]
                                                         
{'loss': 0.6727, 'learning_rate': 0.00047863899177949586, 'epoch': 1.9}

 16%|█▌        | 4453/28080 [8:48:49<46:24:16,  7.07s/it]
 16%|█▌        | 4454/28080 [8:48:56<46:39:11,  7.11s/it]
                                                         
{'loss': 0.6456, 'learning_rate': 0.0004786273273865196, 'epoch': 1.9}

 16%|█▌        | 4454/28080 [8:48:56<46:39:11,  7.11s/it]
 16%|█▌        | 4455/28080 [8:49:04<46:41:10,  7.11s/it]
                                                         
{'loss': 0.6603, 'learning_rate': 0.0004786156599518926, 'epoch': 1.9}

 16%|█▌        | 4455/28080 [8:49:04<46:41:10,  7.11s/it]
 16%|█▌        | 4456/28080 [8:49:11<46:48:53,  7.13s/it]
                                                         
{'loss': 0.6534, 'learning_rate': 0.0004786039894757701, 'epoch': 1.9}

 16%|█▌        | 4456/28080 [8:49:11<46:48:53,  7.13s/it]
 16%|█▌        | 4457/28080 [8:49:18<46:40:37,  7.11s/it]
                                                         
{'loss': 0.6801, 'learning_rate': 0.0004785923159583074, 'epoch': 1.9}

 16%|█▌        | 4457/28080 [8:49:18<46:40:37,  7.11s/it]
 16%|█▌        | 4458/28080 [8:49:25<46:39:18,  7.11s/it]
                                                         
{'loss': 0.634, 'learning_rate': 0.00047858063939965967, 'epoch': 1.9}

 16%|█▌        | 4458/28080 [8:49:25<46:39:18,  7.11s/it]
 16%|█▌        | 4459/28080 [8:49:32<46:37:28,  7.11s/it]
                                                         
{'loss': 0.6645, 'learning_rate': 0.0004785689597999824, 'epoch': 1.9}

 16%|█▌        | 4459/28080 [8:49:32<46:37:28,  7.11s/it]
 16%|█▌        | 4460/28080 [8:49:39<46:31:21,  7.09s/it]
                                                         
{'loss': 0.6658, 'learning_rate': 0.00047855727715943094, 'epoch': 1.91}

 16%|█▌        | 4460/28080 [8:49:39<46:31:21,  7.09s/it]
 16%|█▌        | 4461/28080 [8:49:46<46:37:06,  7.11s/it]
                                                         
{'loss': 0.6435, 'learning_rate': 0.0004785455914781607, 'epoch': 1.91}

 16%|█▌        | 4461/28080 [8:49:46<46:37:06,  7.11s/it]
 16%|█▌        | 4462/28080 [8:49:53<46:21:33,  7.07s/it]
                                                         
{'loss': 0.671, 'learning_rate': 0.00047853390275632706, 'epoch': 1.91}

 16%|█▌        | 4462/28080 [8:49:53<46:21:33,  7.07s/it]
 16%|█▌        | 4463/28080 [8:50:00<46:30:43,  7.09s/it]
                                                         
{'loss': 0.634, 'learning_rate': 0.00047852221099408564, 'epoch': 1.91}

 16%|█▌        | 4463/28080 [8:50:00<46:30:43,  7.09s/it]
 16%|█▌        | 4464/28080 [8:50:07<46:33:23,  7.10s/it]
                                                         
{'loss': 0.6412, 'learning_rate': 0.00047851051619159205, 'epoch': 1.91}

 16%|█▌        | 4464/28080 [8:50:07<46:33:23,  7.10s/it]
 16%|█▌        | 4465/28080 [8:50:14<46:35:15,  7.10s/it]
                                                         
{'loss': 0.6652, 'learning_rate': 0.0004784988183490017, 'epoch': 1.91}

 16%|█▌        | 4465/28080 [8:50:14<46:35:15,  7.10s/it]
 16%|█▌        | 4466/28080 [8:50:22<46:41:16,  7.12s/it]
                                                         
{'loss': 0.6618, 'learning_rate': 0.00047848711746647035, 'epoch': 1.91}

 16%|█▌        | 4466/28080 [8:50:22<46:41:16,  7.12s/it]
 16%|█▌        | 4467/28080 [8:50:29<46:42:11,  7.12s/it]
                                                         
{'loss': 0.6516, 'learning_rate': 0.0004784754135441535, 'epoch': 1.91}

 16%|█▌        | 4467/28080 [8:50:29<46:42:11,  7.12s/it]
 16%|█▌        | 4468/28080 [8:50:36<46:41:27,  7.12s/it]
                                                         
{'loss': 0.6729, 'learning_rate': 0.00047846370658220707, 'epoch': 1.91}

 16%|█▌        | 4468/28080 [8:50:36<46:41:27,  7.12s/it]
 16%|█▌        | 4469/28080 [8:50:43<46:43:35,  7.12s/it]
                                                         
{'loss': 0.6452, 'learning_rate': 0.00047845199658078677, 'epoch': 1.91}

 16%|█▌        | 4469/28080 [8:50:43<46:43:35,  7.12s/it]
 16%|█▌        | 4470/28080 [8:50:50<46:38:05,  7.11s/it]
                                                         
{'loss': 0.6593, 'learning_rate': 0.0004784402835400482, 'epoch': 1.91}

 16%|█▌        | 4470/28080 [8:50:50<46:38:05,  7.11s/it]
 16%|█▌        | 4471/28080 [8:50:57<46:18:33,  7.06s/it]
                                                         
{'loss': 0.68, 'learning_rate': 0.0004784285674601475, 'epoch': 1.91}

 16%|█▌        | 4471/28080 [8:50:57<46:18:33,  7.06s/it]
 16%|█▌        | 4472/28080 [8:51:04<46:29:44,  7.09s/it]
                                                         
{'loss': 0.6494, 'learning_rate': 0.0004784168483412402, 'epoch': 1.91}

 16%|█▌        | 4472/28080 [8:51:04<46:29:44,  7.09s/it]
 16%|█▌        | 4473/28080 [8:51:11<46:35:19,  7.10s/it]
                                                         
{'loss': 0.6544, 'learning_rate': 0.00047840512618348244, 'epoch': 1.91}

 16%|█▌        | 4473/28080 [8:51:11<46:35:19,  7.10s/it]
 16%|█▌        | 4474/28080 [8:51:18<46:40:00,  7.12s/it]
                                                         
{'loss': 0.6731, 'learning_rate': 0.0004783934009870301, 'epoch': 1.91}

 16%|█▌        | 4474/28080 [8:51:18<46:40:00,  7.12s/it]
 16%|█▌        | 4475/28080 [8:51:26<46:33:45,  7.10s/it]
                                                         
{'loss': 0.6625, 'learning_rate': 0.00047838167275203924, 'epoch': 1.91}

 16%|█▌        | 4475/28080 [8:51:26<46:33:45,  7.10s/it]
 16%|█▌        | 4476/28080 [8:51:33<46:25:40,  7.08s/it]
                                                         
{'loss': 0.658, 'learning_rate': 0.0004783699414786657, 'epoch': 1.91}

 16%|█▌        | 4476/28080 [8:51:33<46:25:40,  7.08s/it]
 16%|█▌        | 4477/28080 [8:51:40<46:30:58,  7.09s/it]
                                                         
{'loss': 0.66, 'learning_rate': 0.00047835820716706585, 'epoch': 1.91}

 16%|█▌        | 4477/28080 [8:51:40<46:30:58,  7.09s/it]
 16%|█▌        | 4478/28080 [8:51:47<46:24:08,  7.08s/it]
                                                         
{'loss': 0.6558, 'learning_rate': 0.00047834646981739554, 'epoch': 1.91}

 16%|█▌        | 4478/28080 [8:51:47<46:24:08,  7.08s/it]
 16%|█▌        | 4479/28080 [8:51:54<46:23:35,  7.08s/it]
                                                         
{'loss': 0.6472, 'learning_rate': 0.00047833472942981106, 'epoch': 1.91}

 16%|█▌        | 4479/28080 [8:51:54<46:23:35,  7.08s/it]
 16%|█▌        | 4480/28080 [8:52:01<46:12:25,  7.05s/it]
                                                         
{'loss': 0.6457, 'learning_rate': 0.00047832298600446855, 'epoch': 1.91}

 16%|█▌        | 4480/28080 [8:52:01<46:12:25,  7.05s/it]
 16%|█▌        | 4481/28080 [8:52:08<46:30:30,  7.09s/it]
                                                         
{'loss': 0.6649, 'learning_rate': 0.00047831123954152424, 'epoch': 1.91}

 16%|█▌        | 4481/28080 [8:52:08<46:30:30,  7.09s/it]
 16%|█▌        | 4482/28080 [8:52:15<46:30:36,  7.10s/it]
                                                         
{'loss': 0.6627, 'learning_rate': 0.00047829949004113447, 'epoch': 1.91}

 16%|█▌        | 4482/28080 [8:52:15<46:30:36,  7.10s/it]
 16%|█▌        | 4483/28080 [8:52:22<46:29:09,  7.09s/it]
                                                         
{'loss': 0.6498, 'learning_rate': 0.0004782877375034554, 'epoch': 1.92}

 16%|█▌        | 4483/28080 [8:52:22<46:29:09,  7.09s/it]
 16%|█▌        | 4484/28080 [8:52:29<46:33:00,  7.10s/it]
                                                         
{'loss': 0.6342, 'learning_rate': 0.00047827598192864366, 'epoch': 1.92}

 16%|█▌        | 4484/28080 [8:52:29<46:33:00,  7.10s/it]
 16%|█▌        | 4485/28080 [8:52:36<46:32:48,  7.10s/it]
                                                         
{'loss': 0.6446, 'learning_rate': 0.00047826422331685535, 'epoch': 1.92}

 16%|█▌        | 4485/28080 [8:52:36<46:32:48,  7.10s/it]
 16%|█▌        | 4486/28080 [8:52:43<46:19:44,  7.07s/it]
                                                         
{'loss': 0.6645, 'learning_rate': 0.0004782524616682471, 'epoch': 1.92}

 16%|█▌        | 4486/28080 [8:52:43<46:19:44,  7.07s/it]
 16%|█▌        | 4487/28080 [8:52:50<46:16:30,  7.06s/it]
                                                         
{'loss': 0.6397, 'learning_rate': 0.0004782406969829753, 'epoch': 1.92}

 16%|█▌        | 4487/28080 [8:52:50<46:16:30,  7.06s/it]
 16%|█▌        | 4488/28080 [8:52:58<46:24:07,  7.08s/it]
                                                         
{'loss': 0.6643, 'learning_rate': 0.00047822892926119645, 'epoch': 1.92}

 16%|█▌        | 4488/28080 [8:52:58<46:24:07,  7.08s/it]
 16%|█▌        | 4489/28080 [8:53:05<46:06:59,  7.04s/it]
                                                         
{'loss': 0.6356, 'learning_rate': 0.0004782171585030672, 'epoch': 1.92}

 16%|█▌        | 4489/28080 [8:53:05<46:06:59,  7.04s/it]
 16%|█▌        | 4490/28080 [8:53:12<46:20:48,  7.07s/it]
                                                         
{'loss': 0.6765, 'learning_rate': 0.0004782053847087441, 'epoch': 1.92}

 16%|█▌        | 4490/28080 [8:53:12<46:20:48,  7.07s/it]
 16%|█▌        | 4491/28080 [8:53:19<46:20:40,  7.07s/it]
                                                         
{'loss': 0.6611, 'learning_rate': 0.0004781936078783837, 'epoch': 1.92}

 16%|█▌        | 4491/28080 [8:53:19<46:20:40,  7.07s/it]
 16%|█▌        | 4492/28080 [8:53:26<46:24:58,  7.08s/it]
                                                         
{'loss': 0.6621, 'learning_rate': 0.00047818182801214284, 'epoch': 1.92}

 16%|█▌        | 4492/28080 [8:53:26<46:24:58,  7.08s/it]
 16%|█▌        | 4493/28080 [8:53:33<46:29:23,  7.10s/it]
                                                         
{'loss': 0.6639, 'learning_rate': 0.00047817004511017816, 'epoch': 1.92}

 16%|█▌        | 4493/28080 [8:53:33<46:29:23,  7.10s/it]
 16%|█▌        | 4494/28080 [8:53:40<46:31:00,  7.10s/it]
                                                         
{'loss': 0.6378, 'learning_rate': 0.00047815825917264646, 'epoch': 1.92}

 16%|█▌        | 4494/28080 [8:53:40<46:31:00,  7.10s/it]
 16%|█▌        | 4495/28080 [8:53:47<46:27:37,  7.09s/it]
                                                         
{'loss': 0.6583, 'learning_rate': 0.00047814647019970435, 'epoch': 1.92}

 16%|█▌        | 4495/28080 [8:53:47<46:27:37,  7.09s/it]
 16%|█▌        | 4496/28080 [8:53:54<46:27:19,  7.09s/it]
                                                         
{'loss': 0.6547, 'learning_rate': 0.000478134678191509, 'epoch': 1.92}

 16%|█▌        | 4496/28080 [8:53:54<46:27:19,  7.09s/it]
 16%|█▌        | 4497/28080 [8:54:01<46:26:25,  7.09s/it]
                                                         
{'loss': 0.6438, 'learning_rate': 0.0004781228831482169, 'epoch': 1.92}

 16%|█▌        | 4497/28080 [8:54:01<46:26:25,  7.09s/it]
 16%|█▌        | 4498/28080 [8:54:08<46:21:36,  7.08s/it]
                                                         
{'loss': 0.6812, 'learning_rate': 0.0004781110850699854, 'epoch': 1.92}

 16%|█▌        | 4498/28080 [8:54:08<46:21:36,  7.08s/it]
 16%|█▌        | 4499/28080 [8:54:15<46:20:02,  7.07s/it]
                                                         
{'loss': 0.6304, 'learning_rate': 0.0004780992839569711, 'epoch': 1.92}

 16%|█▌        | 4499/28080 [8:54:15<46:20:02,  7.07s/it]
 16%|█▌        | 4500/28080 [8:54:23<46:29:37,  7.10s/it]
                                                         
{'loss': 0.6483, 'learning_rate': 0.0004780874798093312, 'epoch': 1.92}

 16%|█▌        | 4500/28080 [8:54:23<46:29:37,  7.10s/it]
 16%|█▌        | 4501/28080 [8:54:30<46:32:11,  7.11s/it]
                                                         
{'loss': 0.6508, 'learning_rate': 0.0004780756726272227, 'epoch': 1.92}

 16%|█▌        | 4501/28080 [8:54:30<46:32:11,  7.11s/it]
 16%|█▌        | 4502/28080 [8:54:37<46:41:37,  7.13s/it]
                                                         
{'loss': 0.6547, 'learning_rate': 0.00047806386241080264, 'epoch': 1.92}

 16%|█▌        | 4502/28080 [8:54:37<46:41:37,  7.13s/it]
 16%|█▌        | 4503/28080 [8:54:44<46:40:48,  7.13s/it]
                                                         
{'loss': 0.6596, 'learning_rate': 0.00047805204916022816, 'epoch': 1.92}

 16%|█▌        | 4503/28080 [8:54:44<46:40:48,  7.13s/it]
 16%|█▌        | 4504/28080 [8:54:51<46:12:16,  7.06s/it]
                                                         
{'loss': 0.668, 'learning_rate': 0.00047804023287565647, 'epoch': 1.92}

 16%|█▌        | 4504/28080 [8:54:51<46:12:16,  7.06s/it]
 16%|█▌        | 4505/28080 [8:54:58<46:21:04,  7.08s/it]
                                                         
{'loss': 0.6722, 'learning_rate': 0.0004780284135572447, 'epoch': 1.92}

 16%|█▌        | 4505/28080 [8:54:58<46:21:04,  7.08s/it]
 16%|█▌        | 4506/28080 [8:55:05<46:15:59,  7.07s/it]
                                                         
{'loss': 0.6458, 'learning_rate': 0.00047801659120515016, 'epoch': 1.92}

 16%|█▌        | 4506/28080 [8:55:05<46:15:59,  7.07s/it]
 16%|█▌        | 4507/28080 [8:55:12<46:18:14,  7.07s/it]
                                                         
{'loss': 0.6515, 'learning_rate': 0.0004780047658195301, 'epoch': 1.93}

 16%|█▌        | 4507/28080 [8:55:12<46:18:14,  7.07s/it]
 16%|█▌        | 4508/28080 [8:55:19<46:26:59,  7.09s/it]
                                                         
{'loss': 0.6474, 'learning_rate': 0.00047799293740054185, 'epoch': 1.93}

 16%|█▌        | 4508/28080 [8:55:19<46:26:59,  7.09s/it]
 16%|█▌        | 4509/28080 [8:55:26<46:23:05,  7.08s/it]
                                                         
{'loss': 0.658, 'learning_rate': 0.00047798110594834275, 'epoch': 1.93}

 16%|█▌        | 4509/28080 [8:55:26<46:23:05,  7.08s/it]
 16%|█▌        | 4510/28080 [8:55:33<46:19:39,  7.08s/it]
                                                         
{'loss': 0.6623, 'learning_rate': 0.0004779692714630902, 'epoch': 1.93}

 16%|█▌        | 4510/28080 [8:55:33<46:19:39,  7.08s/it]
 16%|█▌        | 4511/28080 [8:55:41<46:18:04,  7.07s/it]
                                                         
{'loss': 0.6433, 'learning_rate': 0.00047795743394494177, 'epoch': 1.93}

 16%|█▌        | 4511/28080 [8:55:41<46:18:04,  7.07s/it]
 16%|█▌        | 4512/28080 [8:55:48<46:25:23,  7.09s/it]
                                                         
{'loss': 0.6456, 'learning_rate': 0.00047794559339405483, 'epoch': 1.93}

 16%|█▌        | 4512/28080 [8:55:48<46:25:23,  7.09s/it]
 16%|█▌        | 4513/28080 [8:55:55<46:38:04,  7.12s/it]
                                                         
{'loss': 0.654, 'learning_rate': 0.00047793374981058693, 'epoch': 1.93}

 16%|█▌        | 4513/28080 [8:55:55<46:38:04,  7.12s/it]
 16%|█▌        | 4514/28080 [8:56:02<46:31:05,  7.11s/it]
                                                         
{'loss': 0.6852, 'learning_rate': 0.0004779219031946956, 'epoch': 1.93}

 16%|█▌        | 4514/28080 [8:56:02<46:31:05,  7.11s/it]
 16%|█▌        | 4515/28080 [8:56:09<46:14:58,  7.07s/it]
                                                         
{'loss': 0.6422, 'learning_rate': 0.00047791005354653847, 'epoch': 1.93}

 16%|█▌        | 4515/28080 [8:56:09<46:14:58,  7.07s/it]
 16%|█▌        | 4516/28080 [8:56:16<46:15:55,  7.07s/it]
                                                         
{'loss': 0.6714, 'learning_rate': 0.00047789820086627325, 'epoch': 1.93}

 16%|█▌        | 4516/28080 [8:56:16<46:15:55,  7.07s/it]
 16%|█▌        | 4517/28080 [8:56:23<46:21:06,  7.08s/it]
                                                         
{'loss': 0.6356, 'learning_rate': 0.0004778863451540575, 'epoch': 1.93}

 16%|█▌        | 4517/28080 [8:56:23<46:21:06,  7.08s/it]
 16%|█▌        | 4518/28080 [8:56:30<46:12:43,  7.06s/it]
                                                         
{'loss': 0.6495, 'learning_rate': 0.0004778744864100491, 'epoch': 1.93}

 16%|█▌        | 4518/28080 [8:56:30<46:12:43,  7.06s/it]
 16%|█▌        | 4519/28080 [8:56:37<46:19:09,  7.08s/it]
                                                         
{'loss': 0.6473, 'learning_rate': 0.00047786262463440574, 'epoch': 1.93}

 16%|█▌        | 4519/28080 [8:56:37<46:19:09,  7.08s/it]
 16%|█▌        | 4520/28080 [8:56:44<46:27:21,  7.10s/it]
                                                         
{'loss': 0.6479, 'learning_rate': 0.0004778507598272852, 'epoch': 1.93}

 16%|█▌        | 4520/28080 [8:56:44<46:27:21,  7.10s/it]
 16%|█▌        | 4521/28080 [8:56:51<46:18:43,  7.08s/it]
                                                         
{'loss': 0.6533, 'learning_rate': 0.0004778388919888453, 'epoch': 1.93}

 16%|█▌        | 4521/28080 [8:56:51<46:18:43,  7.08s/it]
 16%|█▌        | 4522/28080 [8:56:59<46:26:04,  7.10s/it]
                                                         
{'loss': 0.6573, 'learning_rate': 0.00047782702111924416, 'epoch': 1.93}

 16%|█▌        | 4522/28080 [8:56:59<46:26:04,  7.10s/it]
 16%|█▌        | 4523/28080 [8:57:06<46:30:21,  7.11s/it]
                                                         
{'loss': 0.6592, 'learning_rate': 0.0004778151472186394, 'epoch': 1.93}

 16%|█▌        | 4523/28080 [8:57:06<46:30:21,  7.11s/it]
 16%|█▌        | 4524/28080 [8:57:13<46:20:12,  7.08s/it]
                                                         
{'loss': 0.6796, 'learning_rate': 0.0004778032702871892, 'epoch': 1.93}

 16%|█▌        | 4524/28080 [8:57:13<46:20:12,  7.08s/it]
 16%|█▌        | 4525/28080 [8:57:20<46:24:57,  7.09s/it]
                                                         
{'loss': 0.6522, 'learning_rate': 0.0004777913903250515, 'epoch': 1.93}

 16%|█▌        | 4525/28080 [8:57:20<46:24:57,  7.09s/it]
 16%|█▌        | 4526/28080 [8:57:27<46:10:24,  7.06s/it]
                                                         
{'loss': 0.643, 'learning_rate': 0.0004777795073323843, 'epoch': 1.93}

 16%|█▌        | 4526/28080 [8:57:27<46:10:24,  7.06s/it]
 16%|█▌        | 4527/28080 [8:57:34<46:17:40,  7.08s/it]
                                                         
{'loss': 0.6353, 'learning_rate': 0.0004777676213093457, 'epoch': 1.93}

 16%|█▌        | 4527/28080 [8:57:34<46:17:40,  7.08s/it]
 16%|█▌        | 4528/28080 [8:57:41<46:31:07,  7.11s/it]
                                                         
{'loss': 0.6545, 'learning_rate': 0.000477755732256094, 'epoch': 1.93}

 16%|█▌        | 4528/28080 [8:57:41<46:31:07,  7.11s/it]
 16%|█▌        | 4529/28080 [8:57:48<46:28:49,  7.10s/it]
                                                         
{'loss': 0.6505, 'learning_rate': 0.0004777438401727872, 'epoch': 1.93}

 16%|█▌        | 4529/28080 [8:57:48<46:28:49,  7.10s/it]
 16%|█▌        | 4530/28080 [8:57:55<46:27:17,  7.10s/it]
                                                         
{'loss': 0.6411, 'learning_rate': 0.0004777319450595835, 'epoch': 1.94}

 16%|█▌        | 4530/28080 [8:57:55<46:27:17,  7.10s/it]
 16%|█▌        | 4531/28080 [8:58:02<46:13:43,  7.07s/it]
                                                         
{'loss': 0.6636, 'learning_rate': 0.00047772004691664125, 'epoch': 1.94}

 16%|█▌        | 4531/28080 [8:58:02<46:13:43,  7.07s/it]
 16%|█▌        | 4532/28080 [8:58:09<46:19:46,  7.08s/it]
                                                         
{'loss': 0.6566, 'learning_rate': 0.0004777081457441187, 'epoch': 1.94}

 16%|█▌        | 4532/28080 [8:58:09<46:19:46,  7.08s/it]
 16%|█▌        | 4533/28080 [8:58:16<46:15:45,  7.07s/it]
                                                         
{'loss': 0.6663, 'learning_rate': 0.0004776962415421742, 'epoch': 1.94}

 16%|█▌        | 4533/28080 [8:58:16<46:15:45,  7.07s/it]
 16%|█▌        | 4534/28080 [8:58:24<46:23:43,  7.09s/it]
                                                         
{'loss': 0.6449, 'learning_rate': 0.00047768433431096604, 'epoch': 1.94}

 16%|█▌        | 4534/28080 [8:58:24<46:23:43,  7.09s/it]
 16%|█▌        | 4535/28080 [8:58:31<46:16:02,  7.07s/it]
                                                         
{'loss': 0.6605, 'learning_rate': 0.00047767242405065283, 'epoch': 1.94}

 16%|█▌        | 4535/28080 [8:58:31<46:16:02,  7.07s/it]
 16%|█▌        | 4536/28080 [8:58:38<46:23:34,  7.09s/it]
                                                         
{'loss': 0.634, 'learning_rate': 0.0004776605107613928, 'epoch': 1.94}

 16%|█▌        | 4536/28080 [8:58:38<46:23:34,  7.09s/it]
 16%|█▌        | 4537/28080 [8:58:45<46:23:05,  7.09s/it]
                                                         
{'loss': 0.6432, 'learning_rate': 0.00047764859444334454, 'epoch': 1.94}

 16%|█▌        | 4537/28080 [8:58:45<46:23:05,  7.09s/it]
 16%|█▌        | 4538/28080 [8:58:52<46:28:50,  7.11s/it]
                                                         
{'loss': 0.644, 'learning_rate': 0.0004776366750966666, 'epoch': 1.94}

 16%|█▌        | 4538/28080 [8:58:52<46:28:50,  7.11s/it]
 16%|█▌        | 4539/28080 [8:58:59<46:13:28,  7.07s/it]
                                                         
{'loss': 0.6438, 'learning_rate': 0.0004776247527215175, 'epoch': 1.94}

 16%|█▌        | 4539/28080 [8:58:59<46:13:28,  7.07s/it]
 16%|█▌        | 4540/28080 [8:59:06<46:18:53,  7.08s/it]
                                                         
{'loss': 0.6427, 'learning_rate': 0.00047761282731805595, 'epoch': 1.94}

 16%|█▌        | 4540/28080 [8:59:06<46:18:53,  7.08s/it]
 16%|█▌        | 4541/28080 [8:59:13<46:24:00,  7.10s/it]
                                                         
{'loss': 0.6219, 'learning_rate': 0.00047760089888644055, 'epoch': 1.94}

 16%|█▌        | 4541/28080 [8:59:13<46:24:00,  7.10s/it]
 16%|█▌        | 4542/28080 [8:59:20<46:24:06,  7.10s/it]
                                                         
{'loss': 0.6467, 'learning_rate': 0.0004775889674268299, 'epoch': 1.94}

 16%|█▌        | 4542/28080 [8:59:20<46:24:06,  7.10s/it]
 16%|█▌        | 4543/28080 [8:59:27<46:12:04,  7.07s/it]
                                                         
{'loss': 0.6513, 'learning_rate': 0.0004775770329393829, 'epoch': 1.94}

 16%|█▌        | 4543/28080 [8:59:27<46:12:04,  7.07s/it]
 16%|█▌        | 4544/28080 [8:59:34<46:15:09,  7.07s/it]
                                                         
{'loss': 0.662, 'learning_rate': 0.0004775650954242583, 'epoch': 1.94}

 16%|█▌        | 4544/28080 [8:59:34<46:15:09,  7.07s/it]
 16%|█▌        | 4545/28080 [8:59:42<46:25:02,  7.10s/it]
                                                         
{'loss': 0.641, 'learning_rate': 0.00047755315488161483, 'epoch': 1.94}

 16%|█▌        | 4545/28080 [8:59:42<46:25:02,  7.10s/it]
 16%|█▌        | 4546/28080 [8:59:49<46:32:31,  7.12s/it]
                                                         
{'loss': 0.6416, 'learning_rate': 0.0004775412113116114, 'epoch': 1.94}

 16%|█▌        | 4546/28080 [8:59:49<46:32:31,  7.12s/it]
 16%|█▌        | 4547/28080 [8:59:56<46:21:52,  7.09s/it]
                                                         
{'loss': 0.6624, 'learning_rate': 0.00047752926471440684, 'epoch': 1.94}

 16%|█▌        | 4547/28080 [8:59:56<46:21:52,  7.09s/it]
 16%|█▌        | 4548/28080 [9:00:03<46:27:12,  7.11s/it]
                                                         
{'loss': 0.6689, 'learning_rate': 0.0004775173150901602, 'epoch': 1.94}

 16%|█▌        | 4548/28080 [9:00:03<46:27:12,  7.11s/it]
 16%|█▌        | 4549/28080 [9:00:10<46:24:09,  7.10s/it]
                                                         
{'loss': 0.6636, 'learning_rate': 0.00047750536243903037, 'epoch': 1.94}

 16%|█▌        | 4549/28080 [9:00:10<46:24:09,  7.10s/it]
 16%|█▌        | 4550/28080 [9:00:17<46:26:31,  7.11s/it]
                                                         
{'loss': 0.646, 'learning_rate': 0.00047749340676117634, 'epoch': 1.94}

 16%|█▌        | 4550/28080 [9:00:17<46:26:31,  7.11s/it]
 16%|█▌        | 4551/28080 [9:00:24<46:30:25,  7.12s/it]
                                                         
{'loss': 0.6466, 'learning_rate': 0.0004774814480567573, 'epoch': 1.94}

 16%|█▌        | 4551/28080 [9:00:24<46:30:25,  7.12s/it]
 16%|█▌        | 4552/28080 [9:00:31<46:15:44,  7.08s/it]
                                                         
{'loss': 0.6679, 'learning_rate': 0.00047746948632593233, 'epoch': 1.94}

 16%|█▌        | 4552/28080 [9:00:31<46:15:44,  7.08s/it]
 16%|█▌        | 4553/28080 [9:00:38<46:13:30,  7.07s/it]
                                                         
{'loss': 0.6435, 'learning_rate': 0.0004774575215688604, 'epoch': 1.94}

 16%|█▌        | 4553/28080 [9:00:38<46:13:30,  7.07s/it]
 16%|█▌        | 4554/28080 [9:00:45<46:13:21,  7.07s/it]
                                                         
{'loss': 0.6333, 'learning_rate': 0.0004774455537857009, 'epoch': 1.95}

 16%|█▌        | 4554/28080 [9:00:45<46:13:21,  7.07s/it]
 16%|█▌        | 4555/28080 [9:00:53<46:29:29,  7.11s/it]
                                                         
{'loss': 0.6487, 'learning_rate': 0.0004774335829766129, 'epoch': 1.95}

 16%|█▌        | 4555/28080 [9:00:53<46:29:29,  7.11s/it]
 16%|█▌        | 4556/28080 [9:01:00<46:26:08,  7.11s/it]
                                                         
{'loss': 0.6497, 'learning_rate': 0.0004774216091417557, 'epoch': 1.95}

 16%|█▌        | 4556/28080 [9:01:00<46:26:08,  7.11s/it]
 16%|█▌        | 4557/28080 [9:01:07<46:28:49,  7.11s/it]
                                                         
{'loss': 0.6634, 'learning_rate': 0.00047740963228128856, 'epoch': 1.95}

 16%|█▌        | 4557/28080 [9:01:07<46:28:49,  7.11s/it]
 16%|█▌        | 4558/28080 [9:01:14<46:30:56,  7.12s/it]
                                                         
{'loss': 0.6683, 'learning_rate': 0.0004773976523953709, 'epoch': 1.95}

 16%|█▌        | 4558/28080 [9:01:14<46:30:56,  7.12s/it]
 16%|█▌        | 4559/28080 [9:01:21<46:12:46,  7.07s/it]
                                                         
{'loss': 0.6532, 'learning_rate': 0.0004773856694841621, 'epoch': 1.95}

 16%|█▌        | 4559/28080 [9:01:21<46:12:46,  7.07s/it]
 16%|█▌        | 4560/28080 [9:01:28<46:07:29,  7.06s/it]
                                                         
{'loss': 0.6671, 'learning_rate': 0.00047737368354782155, 'epoch': 1.95}

 16%|█▌        | 4560/28080 [9:01:28<46:07:29,  7.06s/it]
 16%|█▌        | 4561/28080 [9:01:35<46:15:32,  7.08s/it]
                                                         
{'loss': 0.6419, 'learning_rate': 0.0004773616945865087, 'epoch': 1.95}

 16%|█▌        | 4561/28080 [9:01:35<46:15:32,  7.08s/it]
 16%|█▌        | 4562/28080 [9:01:42<46:44:44,  7.16s/it]
                                                         
{'loss': 0.6557, 'learning_rate': 0.00047734970260038305, 'epoch': 1.95}

 16%|█▌        | 4562/28080 [9:01:42<46:44:44,  7.16s/it]
 16%|█▋        | 4563/28080 [9:01:49<46:37:11,  7.14s/it]
                                                         
{'loss': 0.6545, 'learning_rate': 0.00047733770758960414, 'epoch': 1.95}

 16%|█▋        | 4563/28080 [9:01:49<46:37:11,  7.14s/it]
 16%|█▋        | 4564/28080 [9:01:56<46:28:39,  7.12s/it]
                                                         
{'loss': 0.6441, 'learning_rate': 0.00047732570955433165, 'epoch': 1.95}

 16%|█▋        | 4564/28080 [9:01:56<46:28:39,  7.12s/it]
 16%|█▋        | 4565/28080 [9:02:03<46:10:03,  7.07s/it]
                                                         
{'loss': 0.6533, 'learning_rate': 0.000477313708494725, 'epoch': 1.95}

 16%|█▋        | 4565/28080 [9:02:03<46:10:03,  7.07s/it]
 16%|█▋        | 4566/28080 [9:02:11<46:08:54,  7.07s/it]
                                                         
{'loss': 0.6477, 'learning_rate': 0.000477301704410944, 'epoch': 1.95}

 16%|█▋        | 4566/28080 [9:02:11<46:08:54,  7.07s/it]
 16%|█▋        | 4567/28080 [9:02:18<46:06:33,  7.06s/it]
                                                         
{'loss': 0.6516, 'learning_rate': 0.0004772896973031483, 'epoch': 1.95}

 16%|█▋        | 4567/28080 [9:02:18<46:06:33,  7.06s/it]
 16%|█▋        | 4568/28080 [9:02:25<46:03:51,  7.05s/it]
                                                         
{'loss': 0.6526, 'learning_rate': 0.0004772776871714977, 'epoch': 1.95}

 16%|█▋        | 4568/28080 [9:02:25<46:03:51,  7.05s/it]
 16%|█▋        | 4569/28080 [9:02:32<46:14:35,  7.08s/it]
                                                         
{'loss': 0.6641, 'learning_rate': 0.00047726567401615197, 'epoch': 1.95}

 16%|█▋        | 4569/28080 [9:02:32<46:14:35,  7.08s/it]
 16%|█▋        | 4570/28080 [9:02:39<46:19:36,  7.09s/it]
                                                         
{'loss': 0.6638, 'learning_rate': 0.00047725365783727084, 'epoch': 1.95}

 16%|█▋        | 4570/28080 [9:02:39<46:19:36,  7.09s/it]
 16%|█▋        | 4571/28080 [9:02:46<46:03:37,  7.05s/it]
                                                         
{'loss': 0.6718, 'learning_rate': 0.0004772416386350142, 'epoch': 1.95}

 16%|█▋        | 4571/28080 [9:02:46<46:03:37,  7.05s/it]
 16%|█▋        | 4572/28080 [9:02:53<46:02:17,  7.05s/it]
                                                         
{'loss': 0.648, 'learning_rate': 0.0004772296164095421, 'epoch': 1.95}

 16%|█▋        | 4572/28080 [9:02:53<46:02:17,  7.05s/it]
 16%|█▋        | 4573/28080 [9:03:00<46:09:49,  7.07s/it]
                                                         
{'loss': 0.6412, 'learning_rate': 0.0004772175911610143, 'epoch': 1.95}

 16%|█▋        | 4573/28080 [9:03:00<46:09:49,  7.07s/it]
 16%|█▋        | 4574/28080 [9:03:07<46:18:15,  7.09s/it]
                                                         
{'loss': 0.6621, 'learning_rate': 0.0004772055628895908, 'epoch': 1.95}

 16%|█▋        | 4574/28080 [9:03:07<46:18:15,  7.09s/it]
 16%|█▋        | 4575/28080 [9:03:14<46:26:51,  7.11s/it]
                                                         
{'loss': 0.6502, 'learning_rate': 0.0004771935315954318, 'epoch': 1.95}

 16%|█▋        | 4575/28080 [9:03:14<46:26:51,  7.11s/it]
 16%|█▋        | 4576/28080 [9:03:21<46:31:19,  7.13s/it]
                                                         
{'loss': 0.6697, 'learning_rate': 0.0004771814972786972, 'epoch': 1.95}

 16%|█▋        | 4576/28080 [9:03:21<46:31:19,  7.13s/it]
 16%|█▋        | 4577/28080 [9:03:29<46:30:46,  7.12s/it]
                                                         
{'loss': 0.6296, 'learning_rate': 0.00047716945993954717, 'epoch': 1.96}

 16%|█▋        | 4577/28080 [9:03:29<46:30:46,  7.12s/it]
 16%|█▋        | 4578/28080 [9:03:36<46:27:06,  7.12s/it]
                                                         
{'loss': 0.654, 'learning_rate': 0.0004771574195781418, 'epoch': 1.96}

 16%|█▋        | 4578/28080 [9:03:36<46:27:06,  7.12s/it]
 16%|█▋        | 4579/28080 [9:03:43<46:24:14,  7.11s/it]
                                                         
{'loss': 0.6483, 'learning_rate': 0.0004771453761946413, 'epoch': 1.96}

 16%|█▋        | 4579/28080 [9:03:43<46:24:14,  7.11s/it]
 16%|█▋        | 4580/28080 [9:03:50<46:25:46,  7.11s/it]
                                                         
{'loss': 0.6627, 'learning_rate': 0.00047713332978920595, 'epoch': 1.96}

 16%|█▋        | 4580/28080 [9:03:50<46:25:46,  7.11s/it]
 16%|█▋        | 4581/28080 [9:03:57<46:20:54,  7.10s/it]
                                                         
{'loss': 0.6593, 'learning_rate': 0.00047712128036199594, 'epoch': 1.96}

 16%|█▋        | 4581/28080 [9:03:57<46:20:54,  7.10s/it]
 16%|█▋        | 4582/28080 [9:04:04<46:18:34,  7.09s/it]
                                                         
{'loss': 0.6377, 'learning_rate': 0.00047710922791317155, 'epoch': 1.96}

 16%|█▋        | 4582/28080 [9:04:04<46:18:34,  7.09s/it]
 16%|█▋        | 4583/28080 [9:04:11<46:28:28,  7.12s/it]
                                                         
{'loss': 0.6526, 'learning_rate': 0.0004770971724428933, 'epoch': 1.96}

 16%|█▋        | 4583/28080 [9:04:11<46:28:28,  7.12s/it]
 16%|█▋        | 4584/28080 [9:04:18<46:23:11,  7.11s/it]
                                                         
{'loss': 0.6513, 'learning_rate': 0.0004770851139513214, 'epoch': 1.96}

 16%|█▋        | 4584/28080 [9:04:18<46:23:11,  7.11s/it]
 16%|█▋        | 4585/28080 [9:04:25<46:21:36,  7.10s/it]
                                                         
{'loss': 0.652, 'learning_rate': 0.00047707305243861633, 'epoch': 1.96}

 16%|█▋        | 4585/28080 [9:04:25<46:21:36,  7.10s/it]
 16%|█▋        | 4586/28080 [9:04:32<46:18:42,  7.10s/it]
                                                         
{'loss': 0.6706, 'learning_rate': 0.0004770609879049385, 'epoch': 1.96}

 16%|█▋        | 4586/28080 [9:04:32<46:18:42,  7.10s/it]
 16%|█▋        | 4587/28080 [9:04:40<46:29:18,  7.12s/it]
                                                         
{'loss': 0.6549, 'learning_rate': 0.0004770489203504485, 'epoch': 1.96}

 16%|█▋        | 4587/28080 [9:04:40<46:29:18,  7.12s/it]
 16%|█▋        | 4588/28080 [9:04:47<46:31:33,  7.13s/it]
                                                         
{'loss': 0.6374, 'learning_rate': 0.0004770368497753069, 'epoch': 1.96}

 16%|█▋        | 4588/28080 [9:04:47<46:31:33,  7.13s/it]
 16%|█▋        | 4589/28080 [9:04:54<46:25:57,  7.12s/it]
                                                         
{'loss': 0.6428, 'learning_rate': 0.0004770247761796742, 'epoch': 1.96}

 16%|█▋        | 4589/28080 [9:04:54<46:25:57,  7.12s/it]
 16%|█▋        | 4590/28080 [9:05:01<46:14:00,  7.09s/it]
                                                         
{'loss': 0.6564, 'learning_rate': 0.000477012699563711, 'epoch': 1.96}

 16%|█▋        | 4590/28080 [9:05:01<46:14:00,  7.09s/it]
 16%|█▋        | 4591/28080 [9:05:08<46:22:21,  7.11s/it]
                                                         
{'loss': 0.6443, 'learning_rate': 0.00047700061992757807, 'epoch': 1.96}

 16%|█▋        | 4591/28080 [9:05:08<46:22:21,  7.11s/it]
 16%|█▋        | 4592/28080 [9:05:15<46:25:39,  7.12s/it]
                                                         
{'loss': 0.6481, 'learning_rate': 0.0004769885372714361, 'epoch': 1.96}

 16%|█▋        | 4592/28080 [9:05:15<46:25:39,  7.12s/it]
 16%|█▋        | 4593/28080 [9:05:22<46:27:02,  7.12s/it]
                                                         
{'loss': 0.6471, 'learning_rate': 0.00047697645159544577, 'epoch': 1.96}

 16%|█▋        | 4593/28080 [9:05:22<46:27:02,  7.12s/it]
 16%|█▋        | 4594/28080 [9:05:29<46:27:04,  7.12s/it]
                                                         
{'loss': 0.6533, 'learning_rate': 0.000476964362899768, 'epoch': 1.96}

 16%|█▋        | 4594/28080 [9:05:29<46:27:04,  7.12s/it]
 16%|█▋        | 4595/28080 [9:05:37<46:31:03,  7.13s/it]
                                                         
{'loss': 0.6591, 'learning_rate': 0.0004769522711845634, 'epoch': 1.96}

 16%|█▋        | 4595/28080 [9:05:37<46:31:03,  7.13s/it]
 16%|█▋        | 4596/28080 [9:05:44<46:30:03,  7.13s/it]
                                                         
{'loss': 0.6415, 'learning_rate': 0.0004769401764499931, 'epoch': 1.96}

 16%|█▋        | 4596/28080 [9:05:44<46:30:03,  7.13s/it]
 16%|█▋        | 4597/28080 [9:05:51<46:27:59,  7.12s/it]
                                                         
{'loss': 0.6487, 'learning_rate': 0.0004769280786962178, 'epoch': 1.96}

 16%|█▋        | 4597/28080 [9:05:51<46:27:59,  7.12s/it]
 16%|█▋        | 4598/28080 [9:05:58<46:13:21,  7.09s/it]
                                                         
{'loss': 0.6587, 'learning_rate': 0.0004769159779233985, 'epoch': 1.96}

 16%|█▋        | 4598/28080 [9:05:58<46:13:21,  7.09s/it]
 16%|█▋        | 4599/28080 [9:06:05<46:20:26,  7.10s/it]
                                                         
{'loss': 0.6533, 'learning_rate': 0.0004769038741316962, 'epoch': 1.96}

 16%|█▋        | 4599/28080 [9:06:05<46:20:26,  7.10s/it]
 16%|█▋        | 4600/28080 [9:06:12<46:07:07,  7.07s/it]
                                                         
{'loss': 0.6529, 'learning_rate': 0.000476891767321272, 'epoch': 1.97}

 16%|█▋        | 4600/28080 [9:06:12<46:07:07,  7.07s/it]
 16%|█▋        | 4601/28080 [9:06:19<46:04:30,  7.06s/it]
                                                         
{'loss': 0.6683, 'learning_rate': 0.0004768796574922869, 'epoch': 1.97}

 16%|█▋        | 4601/28080 [9:06:19<46:04:30,  7.06s/it]
 16%|█▋        | 4602/28080 [9:06:26<46:09:25,  7.08s/it]
                                                         
{'loss': 0.6515, 'learning_rate': 0.000476867544644902, 'epoch': 1.97}

 16%|█▋        | 4602/28080 [9:06:26<46:09:25,  7.08s/it]
 16%|█▋        | 4603/28080 [9:06:33<46:15:52,  7.09s/it]
                                                         
{'loss': 0.6429, 'learning_rate': 0.00047685542877927845, 'epoch': 1.97}

 16%|█▋        | 4603/28080 [9:06:33<46:15:52,  7.09s/it]
 16%|█▋        | 4604/28080 [9:06:40<46:16:22,  7.10s/it]
                                                         
{'loss': 0.6266, 'learning_rate': 0.00047684330989557753, 'epoch': 1.97}

 16%|█▋        | 4604/28080 [9:06:40<46:16:22,  7.10s/it]
 16%|█▋        | 4605/28080 [9:06:47<46:13:58,  7.09s/it]
                                                         
{'loss': 0.6684, 'learning_rate': 0.0004768311879939603, 'epoch': 1.97}

 16%|█▋        | 4605/28080 [9:06:47<46:13:58,  7.09s/it]
 16%|█▋        | 4606/28080 [9:06:54<46:07:54,  7.07s/it]
                                                         
{'loss': 0.6561, 'learning_rate': 0.00047681906307458816, 'epoch': 1.97}

 16%|█▋        | 4606/28080 [9:06:54<46:07:54,  7.07s/it]
 16%|█▋        | 4607/28080 [9:07:02<46:13:19,  7.09s/it]
                                                         
{'loss': 0.674, 'learning_rate': 0.0004768069351376224, 'epoch': 1.97}

 16%|█▋        | 4607/28080 [9:07:02<46:13:19,  7.09s/it]
 16%|█▋        | 4608/28080 [9:07:09<46:18:53,  7.10s/it]
                                                         
{'loss': 0.6466, 'learning_rate': 0.0004767948041832243, 'epoch': 1.97}

 16%|█▋        | 4608/28080 [9:07:09<46:18:53,  7.10s/it]
 16%|█▋        | 4609/28080 [9:07:16<46:20:02,  7.11s/it]
                                                         
{'loss': 0.648, 'learning_rate': 0.00047678267021155534, 'epoch': 1.97}

 16%|█▋        | 4609/28080 [9:07:16<46:20:02,  7.11s/it]
 16%|█▋        | 4610/28080 [9:07:23<46:28:48,  7.13s/it]
                                                         
{'loss': 0.6654, 'learning_rate': 0.0004767705332227769, 'epoch': 1.97}

 16%|█▋        | 4610/28080 [9:07:23<46:28:48,  7.13s/it]
 16%|█▋        | 4611/28080 [9:07:30<46:25:16,  7.12s/it]
                                                         
{'loss': 0.6765, 'learning_rate': 0.0004767583932170505, 'epoch': 1.97}

 16%|█▋        | 4611/28080 [9:07:30<46:25:16,  7.12s/it]
 16%|█▋        | 4612/28080 [9:07:37<46:22:47,  7.11s/it]
                                                         
{'loss': 0.6657, 'learning_rate': 0.00047674625019453757, 'epoch': 1.97}

 16%|█▋        | 4612/28080 [9:07:37<46:22:47,  7.11s/it]
 16%|█▋        | 4613/28080 [9:07:44<46:21:27,  7.11s/it]
                                                         
{'loss': 0.6437, 'learning_rate': 0.00047673410415539967, 'epoch': 1.97}

 16%|█▋        | 4613/28080 [9:07:44<46:21:27,  7.11s/it]
 16%|█▋        | 4614/28080 [9:07:51<46:13:47,  7.09s/it]
                                                         
{'loss': 0.6375, 'learning_rate': 0.0004767219550997985, 'epoch': 1.97}

 16%|█▋        | 4614/28080 [9:07:51<46:13:47,  7.09s/it]
 16%|█▋        | 4615/28080 [9:07:58<46:14:42,  7.09s/it]
                                                         
{'loss': 0.6521, 'learning_rate': 0.00047670980302789556, 'epoch': 1.97}

 16%|█▋        | 4615/28080 [9:07:58<46:14:42,  7.09s/it]
 16%|█▋        | 4616/28080 [9:08:06<46:18:41,  7.11s/it]
                                                         
{'loss': 0.6542, 'learning_rate': 0.0004766976479398526, 'epoch': 1.97}

 16%|█▋        | 4616/28080 [9:08:06<46:18:41,  7.11s/it]
 16%|█▋        | 4617/28080 [9:08:13<46:11:46,  7.09s/it]
                                                         
{'loss': 0.6575, 'learning_rate': 0.00047668548983583126, 'epoch': 1.97}

 16%|█▋        | 4617/28080 [9:08:13<46:11:46,  7.09s/it]
 16%|█▋        | 4618/28080 [9:08:20<46:14:39,  7.10s/it]
                                                         
{'loss': 0.6534, 'learning_rate': 0.0004766733287159934, 'epoch': 1.97}

 16%|█▋        | 4618/28080 [9:08:20<46:14:39,  7.10s/it]
 16%|█▋        | 4619/28080 [9:08:27<46:16:22,  7.10s/it]
                                                         
{'loss': 0.6516, 'learning_rate': 0.00047666116458050067, 'epoch': 1.97}

 16%|█▋        | 4619/28080 [9:08:27<46:16:22,  7.10s/it]
 16%|█▋        | 4620/28080 [9:08:34<46:22:22,  7.12s/it]
                                                         
{'loss': 0.6668, 'learning_rate': 0.00047664899742951505, 'epoch': 1.97}

 16%|█▋        | 4620/28080 [9:08:34<46:22:22,  7.12s/it]
 16%|█▋        | 4621/28080 [9:08:41<46:09:16,  7.08s/it]
                                                         
{'loss': 0.6909, 'learning_rate': 0.00047663682726319833, 'epoch': 1.97}

 16%|█▋        | 4621/28080 [9:08:41<46:09:16,  7.08s/it]
 16%|█▋        | 4622/28080 [9:08:48<46:07:55,  7.08s/it]
                                                         
{'loss': 0.6702, 'learning_rate': 0.0004766246540817124, 'epoch': 1.97}

 16%|█▋        | 4622/28080 [9:08:48<46:07:55,  7.08s/it]
 16%|█▋        | 4623/28080 [9:08:55<46:06:35,  7.08s/it]
                                                         
{'loss': 0.6476, 'learning_rate': 0.00047661247788521925, 'epoch': 1.97}

 16%|█▋        | 4623/28080 [9:08:55<46:06:35,  7.08s/it]
 16%|█▋        | 4624/28080 [9:09:02<46:14:17,  7.10s/it]
                                                         
{'loss': 0.6489, 'learning_rate': 0.00047660029867388086, 'epoch': 1.98}

 16%|█▋        | 4624/28080 [9:09:02<46:14:17,  7.10s/it]
 16%|█▋        | 4625/28080 [9:09:09<46:08:25,  7.08s/it]
                                                         
{'loss': 0.6748, 'learning_rate': 0.00047658811644785934, 'epoch': 1.98}

 16%|█▋        | 4625/28080 [9:09:09<46:08:25,  7.08s/it]
 16%|█▋        | 4626/28080 [9:09:17<46:16:15,  7.10s/it]
                                                         
{'loss': 0.6431, 'learning_rate': 0.0004765759312073166, 'epoch': 1.98}

 16%|█▋        | 4626/28080 [9:09:17<46:16:15,  7.10s/it]
 16%|█▋        | 4627/28080 [9:09:24<46:16:46,  7.10s/it]
                                                         
{'loss': 0.6531, 'learning_rate': 0.00047656374295241486, 'epoch': 1.98}

 16%|█▋        | 4627/28080 [9:09:24<46:16:46,  7.10s/it]
 16%|█▋        | 4628/28080 [9:09:31<46:12:51,  7.09s/it]
                                                         
{'loss': 0.6597, 'learning_rate': 0.0004765515516833163, 'epoch': 1.98}

 16%|█▋        | 4628/28080 [9:09:31<46:12:51,  7.09s/it]
 16%|█▋        | 4629/28080 [9:09:38<46:05:55,  7.08s/it]
                                                         
{'loss': 0.6646, 'learning_rate': 0.000476539357400183, 'epoch': 1.98}

 16%|█▋        | 4629/28080 [9:09:38<46:05:55,  7.08s/it]
 16%|█▋        | 4630/28080 [9:09:45<46:10:06,  7.09s/it]
                                                         
{'loss': 0.6368, 'learning_rate': 0.0004765271601031773, 'epoch': 1.98}

 16%|█▋        | 4630/28080 [9:09:45<46:10:06,  7.09s/it]
 16%|█▋        | 4631/28080 [9:09:52<46:22:34,  7.12s/it]
                                                         
{'loss': 0.6604, 'learning_rate': 0.0004765149597924614, 'epoch': 1.98}

 16%|█▋        | 4631/28080 [9:09:52<46:22:34,  7.12s/it]
 16%|█▋        | 4632/28080 [9:09:59<46:32:34,  7.15s/it]
                                                         
{'loss': 0.6565, 'learning_rate': 0.00047650275646819767, 'epoch': 1.98}

 16%|█▋        | 4632/28080 [9:09:59<46:32:34,  7.15s/it]
 16%|█▋        | 4633/28080 [9:10:06<46:24:42,  7.13s/it]
                                                         
{'loss': 0.6373, 'learning_rate': 0.0004764905501305484, 'epoch': 1.98}

 16%|█▋        | 4633/28080 [9:10:06<46:24:42,  7.13s/it]
 17%|█▋        | 4634/28080 [9:10:13<46:17:30,  7.11s/it]
                                                         
{'loss': 0.6465, 'learning_rate': 0.00047647834077967603, 'epoch': 1.98}

 17%|█▋        | 4634/28080 [9:10:13<46:17:30,  7.11s/it]
 17%|█▋        | 4635/28080 [9:10:21<46:21:13,  7.12s/it]
                                                         
{'loss': 0.6531, 'learning_rate': 0.000476466128415743, 'epoch': 1.98}

 17%|█▋        | 4635/28080 [9:10:21<46:21:13,  7.12s/it]
 17%|█▋        | 4636/28080 [9:10:28<46:18:46,  7.11s/it]
                                                         
{'loss': 0.6288, 'learning_rate': 0.0004764539130389118, 'epoch': 1.98}

 17%|█▋        | 4636/28080 [9:10:28<46:18:46,  7.11s/it]
 17%|█▋        | 4637/28080 [9:10:35<46:32:42,  7.15s/it]
                                                         
{'loss': 0.6552, 'learning_rate': 0.00047644169464934486, 'epoch': 1.98}

 17%|█▋        | 4637/28080 [9:10:35<46:32:42,  7.15s/it]
 17%|█▋        | 4638/28080 [9:10:42<46:22:32,  7.12s/it]
                                                         
{'loss': 0.6386, 'learning_rate': 0.00047642947324720477, 'epoch': 1.98}

 17%|█▋        | 4638/28080 [9:10:42<46:22:32,  7.12s/it]
 17%|█▋        | 4639/28080 [9:10:49<46:08:00,  7.09s/it]
                                                         
{'loss': 0.6571, 'learning_rate': 0.00047641724883265416, 'epoch': 1.98}

 17%|█▋        | 4639/28080 [9:10:49<46:08:00,  7.09s/it]
 17%|█▋        | 4640/28080 [9:10:56<46:11:25,  7.09s/it]
                                                         
{'loss': 0.6445, 'learning_rate': 0.0004764050214058556, 'epoch': 1.98}

 17%|█▋        | 4640/28080 [9:10:56<46:11:25,  7.09s/it]
 17%|█▋        | 4641/28080 [9:11:03<46:05:29,  7.08s/it]
                                                         
{'loss': 0.6584, 'learning_rate': 0.00047639279096697184, 'epoch': 1.98}

 17%|█▋        | 4641/28080 [9:11:03<46:05:29,  7.08s/it]
 17%|█▋        | 4642/28080 [9:11:10<46:10:24,  7.09s/it]
                                                         
{'loss': 0.6541, 'learning_rate': 0.0004763805575161655, 'epoch': 1.98}

 17%|█▋        | 4642/28080 [9:11:10<46:10:24,  7.09s/it]
 17%|█▋        | 4643/28080 [9:11:17<46:09:15,  7.09s/it]
                                                         
{'loss': 0.638, 'learning_rate': 0.0004763683210535994, 'epoch': 1.98}

 17%|█▋        | 4643/28080 [9:11:17<46:09:15,  7.09s/it]
 17%|█▋        | 4644/28080 [9:11:24<46:19:09,  7.12s/it]
                                                         
{'loss': 0.6394, 'learning_rate': 0.0004763560815794364, 'epoch': 1.98}

 17%|█▋        | 4644/28080 [9:11:24<46:19:09,  7.12s/it]
 17%|█▋        | 4645/28080 [9:11:32<46:15:12,  7.11s/it]
                                                         
{'loss': 0.6384, 'learning_rate': 0.0004763438390938392, 'epoch': 1.98}

 17%|█▋        | 4645/28080 [9:11:32<46:15:12,  7.11s/it]
 17%|█▋        | 4646/28080 [9:11:39<46:09:58,  7.09s/it]
                                                         
{'loss': 0.6547, 'learning_rate': 0.00047633159359697065, 'epoch': 1.98}

 17%|█▋        | 4646/28080 [9:11:39<46:09:58,  7.09s/it]
 17%|█▋        | 4647/28080 [9:11:46<46:13:46,  7.10s/it]
                                                         
{'loss': 0.6335, 'learning_rate': 0.00047631934508899384, 'epoch': 1.99}

 17%|█▋        | 4647/28080 [9:11:46<46:13:46,  7.10s/it]
 17%|█▋        | 4648/28080 [9:11:53<46:13:56,  7.10s/it]
                                                         
{'loss': 0.648, 'learning_rate': 0.00047630709357007165, 'epoch': 1.99}

 17%|█▋        | 4648/28080 [9:11:53<46:13:56,  7.10s/it]
 17%|█▋        | 4649/28080 [9:12:00<46:16:29,  7.11s/it]
                                                         
{'loss': 0.6629, 'learning_rate': 0.00047629483904036696, 'epoch': 1.99}

 17%|█▋        | 4649/28080 [9:12:00<46:16:29,  7.11s/it]
 17%|█▋        | 4650/28080 [9:12:07<46:22:42,  7.13s/it]
                                                         
{'loss': 0.6688, 'learning_rate': 0.0004762825815000429, 'epoch': 1.99}

 17%|█▋        | 4650/28080 [9:12:07<46:22:42,  7.13s/it]
 17%|█▋        | 4651/28080 [9:12:14<46:29:58,  7.14s/it]
                                                         
{'loss': 0.6649, 'learning_rate': 0.0004762703209492626, 'epoch': 1.99}

 17%|█▋        | 4651/28080 [9:12:14<46:29:58,  7.14s/it]
 17%|█▋        | 4652/28080 [9:12:21<46:32:31,  7.15s/it]
                                                         
{'loss': 0.632, 'learning_rate': 0.00047625805738818906, 'epoch': 1.99}

 17%|█▋        | 4652/28080 [9:12:21<46:32:31,  7.15s/it]
 17%|█▋        | 4653/28080 [9:12:29<46:30:16,  7.15s/it]
                                                         
{'loss': 0.6444, 'learning_rate': 0.0004762457908169855, 'epoch': 1.99}

 17%|█▋        | 4653/28080 [9:12:29<46:30:16,  7.15s/it]
 17%|█▋        | 4654/28080 [9:12:36<46:31:55,  7.15s/it]
                                                         
{'loss': 0.6265, 'learning_rate': 0.00047623352123581504, 'epoch': 1.99}

 17%|█▋        | 4654/28080 [9:12:36<46:31:55,  7.15s/it]
 17%|█▋        | 4655/28080 [9:12:43<46:22:18,  7.13s/it]
                                                         
{'loss': 0.6573, 'learning_rate': 0.0004762212486448411, 'epoch': 1.99}

 17%|█▋        | 4655/28080 [9:12:43<46:22:18,  7.13s/it]
 17%|█▋        | 4656/28080 [9:12:50<46:26:01,  7.14s/it]
                                                         
{'loss': 0.6522, 'learning_rate': 0.0004762089730442267, 'epoch': 1.99}

 17%|█▋        | 4656/28080 [9:12:50<46:26:01,  7.14s/it]
 17%|█▋        | 4657/28080 [9:12:57<46:26:53,  7.14s/it]
                                                         
{'loss': 0.6468, 'learning_rate': 0.0004761966944341353, 'epoch': 1.99}

 17%|█▋        | 4657/28080 [9:12:57<46:26:53,  7.14s/it]
 17%|█▋        | 4658/28080 [9:13:04<46:19:51,  7.12s/it]
                                                         
{'loss': 0.6565, 'learning_rate': 0.00047618441281473026, 'epoch': 1.99}

 17%|█▋        | 4658/28080 [9:13:04<46:19:51,  7.12s/it]
 17%|█▋        | 4659/28080 [9:13:11<46:10:49,  7.10s/it]
                                                         
{'loss': 0.6653, 'learning_rate': 0.00047617212818617497, 'epoch': 1.99}

 17%|█▋        | 4659/28080 [9:13:11<46:10:49,  7.10s/it]
 17%|█▋        | 4660/28080 [9:13:18<46:13:15,  7.10s/it]
                                                         
{'loss': 0.6578, 'learning_rate': 0.0004761598405486328, 'epoch': 1.99}

 17%|█▋        | 4660/28080 [9:13:18<46:13:15,  7.10s/it]
 17%|█▋        | 4661/28080 [9:13:26<46:18:27,  7.12s/it]
                                                         
{'loss': 0.6715, 'learning_rate': 0.00047614754990226734, 'epoch': 1.99}

 17%|█▋        | 4661/28080 [9:13:26<46:18:27,  7.12s/it]
 17%|█▋        | 4662/28080 [9:13:33<46:13:30,  7.11s/it]
                                                         
{'loss': 0.6466, 'learning_rate': 0.00047613525624724194, 'epoch': 1.99}

 17%|█▋        | 4662/28080 [9:13:33<46:13:30,  7.11s/it]
 17%|█▋        | 4663/28080 [9:13:40<46:00:28,  7.07s/it]
                                                         
{'loss': 0.6393, 'learning_rate': 0.0004761229595837203, 'epoch': 1.99}

 17%|█▋        | 4663/28080 [9:13:40<46:00:28,  7.07s/it]
 17%|█▋        | 4664/28080 [9:13:47<46:04:48,  7.08s/it]
                                                         
{'loss': 0.6381, 'learning_rate': 0.00047611065991186595, 'epoch': 1.99}

 17%|█▋        | 4664/28080 [9:13:47<46:04:48,  7.08s/it]
 17%|█▋        | 4665/28080 [9:13:54<46:08:05,  7.09s/it]
                                                         
{'loss': 0.6519, 'learning_rate': 0.00047609835723184257, 'epoch': 1.99}

 17%|█▋        | 4665/28080 [9:13:54<46:08:05,  7.09s/it]
 17%|█▋        | 4666/28080 [9:14:01<46:15:04,  7.11s/it]
                                                         
{'loss': 0.6428, 'learning_rate': 0.0004760860515438138, 'epoch': 1.99}

 17%|█▋        | 4666/28080 [9:14:01<46:15:04,  7.11s/it]
 17%|█▋        | 4667/28080 [9:14:08<46:15:46,  7.11s/it]
                                                         
{'loss': 0.6353, 'learning_rate': 0.00047607374284794324, 'epoch': 1.99}

 17%|█▋        | 4667/28080 [9:14:08<46:15:46,  7.11s/it]
 17%|█▋        | 4668/28080 [9:14:15<46:10:49,  7.10s/it]
                                                         
{'loss': 0.6472, 'learning_rate': 0.0004760614311443949, 'epoch': 1.99}

 17%|█▋        | 4668/28080 [9:14:15<46:10:49,  7.10s/it]
 17%|█▋        | 4669/28080 [9:14:22<46:11:24,  7.10s/it]
                                                         
{'loss': 0.644, 'learning_rate': 0.00047604911643333236, 'epoch': 1.99}

 17%|█▋        | 4669/28080 [9:14:22<46:11:24,  7.10s/it]
 17%|█▋        | 4670/28080 [9:14:29<46:15:40,  7.11s/it]
                                                         
{'loss': 0.6543, 'learning_rate': 0.00047603679871491956, 'epoch': 1.99}

 17%|█▋        | 4670/28080 [9:14:29<46:15:40,  7.11s/it]
 17%|█▋        | 4671/28080 [9:14:37<46:11:30,  7.10s/it]
                                                         
{'loss': 0.6253, 'learning_rate': 0.0004760244779893203, 'epoch': 2.0}

 17%|█▋        | 4671/28080 [9:14:37<46:11:30,  7.10s/it]
 17%|█▋        | 4672/28080 [9:14:44<46:23:23,  7.13s/it]
                                                         
{'loss': 0.6502, 'learning_rate': 0.0004760121542566985, 'epoch': 2.0}

 17%|█▋        | 4672/28080 [9:14:44<46:23:23,  7.13s/it]
 17%|█▋        | 4673/28080 [9:14:51<46:19:10,  7.12s/it]
                                                         
{'loss': 0.6605, 'learning_rate': 0.0004759998275172183, 'epoch': 2.0}

 17%|█▋        | 4673/28080 [9:14:51<46:19:10,  7.12s/it]
 17%|█▋        | 4674/28080 [9:14:58<46:16:41,  7.12s/it]
                                                         
{'loss': 0.6366, 'learning_rate': 0.00047598749777104344, 'epoch': 2.0}

 17%|█▋        | 4674/28080 [9:14:58<46:16:41,  7.12s/it]
 17%|█▋        | 4675/28080 [9:15:05<46:06:28,  7.09s/it]
                                                         
{'loss': 0.6603, 'learning_rate': 0.00047597516501833803, 'epoch': 2.0}

 17%|█▋        | 4675/28080 [9:15:05<46:06:28,  7.09s/it]
 17%|█▋        | 4676/28080 [9:15:12<46:02:42,  7.08s/it]
                                                         
{'loss': 0.6375, 'learning_rate': 0.00047596282925926626, 'epoch': 2.0}

 17%|█▋        | 4676/28080 [9:15:12<46:02:42,  7.08s/it]
 17%|█▋        | 4677/28080 [9:15:19<46:01:43,  7.08s/it]
                                                         
{'loss': 0.6541, 'learning_rate': 0.00047595049049399215, 'epoch': 2.0}

 17%|█▋        | 4677/28080 [9:15:19<46:01:43,  7.08s/it]
 17%|█▋        | 4678/28080 [9:15:26<45:51:10,  7.05s/it]
                                                         
{'loss': 0.6485, 'learning_rate': 0.0004759381487226798, 'epoch': 2.0}

 17%|█▋        | 4678/28080 [9:15:26<45:51:10,  7.05s/it]
 17%|█▋        | 4679/28080 [9:15:33<45:53:12,  7.06s/it]
                                                         
{'loss': 0.6593, 'learning_rate': 0.00047592580394549355, 'epoch': 2.0}

 17%|█▋        | 4679/28080 [9:15:33<45:53:12,  7.06s/it]
 17%|█▋        | 4680/28080 [9:15:40<46:04:21,  7.09s/it]
                                                         
{'loss': 0.6492, 'learning_rate': 0.0004759134561625975, 'epoch': 2.0}

 17%|█▋        | 4680/28080 [9:15:40<46:04:21,  7.09s/it]
 17%|█▋        | 4681/28080 [9:15:47<46:01:53,  7.08s/it]
                                                         
{'loss': 0.6667, 'learning_rate': 0.000475901105374156, 'epoch': 2.0}

 17%|█▋        | 4681/28080 [9:15:47<46:01:53,  7.08s/it]
 17%|█▋        | 4682/28080 [9:15:55<46:57:04,  7.22s/it]
                                                         
{'loss': 0.6655, 'learning_rate': 0.0004758887515803333, 'epoch': 2.0}

 17%|█▋        | 4682/28080 [9:15:55<46:57:04,  7.22s/it]
 17%|█▋        | 4683/28080 [9:16:02<46:49:09,  7.20s/it]
                                                         
{'loss': 0.6428, 'learning_rate': 0.00047587639478129383, 'epoch': 2.0}

 17%|█▋        | 4683/28080 [9:16:02<46:49:09,  7.20s/it]
 17%|█▋        | 4684/28080 [9:16:09<46:37:33,  7.17s/it]
                                                         
{'loss': 0.6326, 'learning_rate': 0.000475864034977202, 'epoch': 2.0}

 17%|█▋        | 4684/28080 [9:16:09<46:37:33,  7.17s/it]
 17%|█▋        | 4685/28080 [9:16:16<46:35:21,  7.17s/it]
                                                         
{'loss': 0.6333, 'learning_rate': 0.00047585167216822213, 'epoch': 2.0}

 17%|█▋        | 4685/28080 [9:16:16<46:35:21,  7.17s/it]
 17%|█▋        | 4686/28080 [9:16:23<46:30:03,  7.16s/it]
                                                         
{'loss': 0.6378, 'learning_rate': 0.0004758393063545187, 'epoch': 2.0}

 17%|█▋        | 4686/28080 [9:16:23<46:30:03,  7.16s/it]
 17%|█▋        | 4687/28080 [9:16:31<46:18:30,  7.13s/it]
                                                         
{'loss': 0.6505, 'learning_rate': 0.0004758269375362564, 'epoch': 2.0}

 17%|█▋        | 4687/28080 [9:16:31<46:18:30,  7.13s/it]
 17%|█▋        | 4688/28080 [9:16:38<46:10:40,  7.11s/it]
                                                         
{'loss': 0.6534, 'learning_rate': 0.0004758145657135996, 'epoch': 2.0}

 17%|█▋        | 4688/28080 [9:16:38<46:10:40,  7.11s/it]
 17%|█▋        | 4689/28080 [9:16:45<46:03:15,  7.09s/it]
                                                         
{'loss': 0.6297, 'learning_rate': 0.000475802190886713, 'epoch': 2.0}

 17%|█▋        | 4689/28080 [9:16:45<46:03:15,  7.09s/it]
 17%|█▋        | 4690/28080 [9:16:52<46:07:54,  7.10s/it]
                                                         
{'loss': 0.6485, 'learning_rate': 0.0004757898130557612, 'epoch': 2.0}

 17%|█▋        | 4690/28080 [9:16:52<46:07:54,  7.10s/it]
 17%|█▋        | 4691/28080 [9:16:59<46:12:12,  7.11s/it]
                                                         
{'loss': 0.6402, 'learning_rate': 0.00047577743222090884, 'epoch': 2.0}

 17%|█▋        | 4691/28080 [9:16:59<46:12:12,  7.11s/it]
 17%|█▋        | 4692/28080 [9:17:06<46:04:38,  7.09s/it]
                                                         
{'loss': 0.6446, 'learning_rate': 0.00047576504838232073, 'epoch': 2.0}

 17%|█▋        | 4692/28080 [9:17:06<46:04:38,  7.09s/it]
 17%|█▋        | 4693/28080 [9:17:13<46:05:07,  7.09s/it]
                                                         
{'loss': 0.6456, 'learning_rate': 0.0004757526615401615, 'epoch': 2.0}

 17%|█▋        | 4693/28080 [9:17:13<46:05:07,  7.09s/it]
 17%|█▋        | 4694/28080 [9:17:20<46:13:26,  7.12s/it]
                                                         
{'loss': 0.6491, 'learning_rate': 0.000475740271694596, 'epoch': 2.01}

 17%|█▋        | 4694/28080 [9:17:20<46:13:26,  7.12s/it]
 17%|█▋        | 4695/28080 [9:17:27<46:17:44,  7.13s/it]
                                                         
{'loss': 0.6632, 'learning_rate': 0.00047572787884578906, 'epoch': 2.01}

 17%|█▋        | 4695/28080 [9:17:27<46:17:44,  7.13s/it]
 17%|█▋        | 4696/28080 [9:17:34<46:14:24,  7.12s/it]
                                                         
{'loss': 0.6621, 'learning_rate': 0.00047571548299390565, 'epoch': 2.01}

 17%|█▋        | 4696/28080 [9:17:34<46:14:24,  7.12s/it]
 17%|█▋        | 4697/28080 [9:17:42<46:11:45,  7.11s/it]
                                                         
{'loss': 0.6616, 'learning_rate': 0.0004757030841391105, 'epoch': 2.01}

 17%|█▋        | 4697/28080 [9:17:42<46:11:45,  7.11s/it]
 17%|█▋        | 4698/28080 [9:17:49<46:03:35,  7.09s/it]
                                                         
{'loss': 0.6687, 'learning_rate': 0.0004756906822815687, 'epoch': 2.01}

 17%|█▋        | 4698/28080 [9:17:49<46:03:35,  7.09s/it]
 17%|█▋        | 4699/28080 [9:17:56<46:12:05,  7.11s/it]
                                                         
{'loss': 0.6501, 'learning_rate': 0.0004756782774214452, 'epoch': 2.01}

 17%|█▋        | 4699/28080 [9:17:56<46:12:05,  7.11s/it]
 17%|█▋        | 4700/28080 [9:18:03<46:03:11,  7.09s/it]
                                                         
{'loss': 0.643, 'learning_rate': 0.00047566586955890503, 'epoch': 2.01}

 17%|█▋        | 4700/28080 [9:18:03<46:03:11,  7.09s/it]
 17%|█▋        | 4701/28080 [9:18:10<46:15:36,  7.12s/it]
                                                         
{'loss': 0.6451, 'learning_rate': 0.00047565345869411327, 'epoch': 2.01}

 17%|█▋        | 4701/28080 [9:18:10<46:15:36,  7.12s/it]
 17%|█▋        | 4702/28080 [9:18:17<46:00:51,  7.09s/it]
                                                         
{'loss': 0.6399, 'learning_rate': 0.0004756410448272351, 'epoch': 2.01}

 17%|█▋        | 4702/28080 [9:18:17<46:00:51,  7.09s/it]
 17%|█▋        | 4703/28080 [9:18:24<46:13:44,  7.12s/it]
                                                         
{'loss': 0.6454, 'learning_rate': 0.00047562862795843554, 'epoch': 2.01}

 17%|█▋        | 4703/28080 [9:18:24<46:13:44,  7.12s/it]
 17%|█▋        | 4704/28080 [9:18:31<46:03:53,  7.09s/it]
                                                         
{'loss': 0.6602, 'learning_rate': 0.0004756162080878799, 'epoch': 2.01}

 17%|█▋        | 4704/28080 [9:18:31<46:03:53,  7.09s/it]
 17%|█▋        | 4705/28080 [9:18:38<45:56:45,  7.08s/it]
                                                         
{'loss': 0.6656, 'learning_rate': 0.00047560378521573326, 'epoch': 2.01}

 17%|█▋        | 4705/28080 [9:18:38<45:56:45,  7.08s/it]
 17%|█▋        | 4706/28080 [9:18:45<45:57:11,  7.08s/it]
                                                         
{'loss': 0.6486, 'learning_rate': 0.00047559135934216115, 'epoch': 2.01}

 17%|█▋        | 4706/28080 [9:18:45<45:57:11,  7.08s/it]
 17%|█▋        | 4707/28080 [9:18:52<46:02:48,  7.09s/it]
                                                         
{'loss': 0.6301, 'learning_rate': 0.0004755789304673286, 'epoch': 2.01}

 17%|█▋        | 4707/28080 [9:18:52<46:02:48,  7.09s/it]
 17%|█▋        | 4708/28080 [9:19:00<46:11:04,  7.11s/it]
                                                         
{'loss': 0.6138, 'learning_rate': 0.0004755664985914012, 'epoch': 2.01}

 17%|█▋        | 4708/28080 [9:19:00<46:11:04,  7.11s/it]
 17%|█▋        | 4709/28080 [9:19:07<46:08:29,  7.11s/it]
                                                         
{'loss': 0.6449, 'learning_rate': 0.00047555406371454416, 'epoch': 2.01}

 17%|█▋        | 4709/28080 [9:19:07<46:08:29,  7.11s/it]
 17%|█▋        | 4710/28080 [9:19:14<46:06:26,  7.10s/it]
                                                         
{'loss': 0.6531, 'learning_rate': 0.0004755416258369231, 'epoch': 2.01}

 17%|█▋        | 4710/28080 [9:19:14<46:06:26,  7.10s/it]
 17%|█▋        | 4711/28080 [9:19:21<46:05:29,  7.10s/it]
                                                         
{'loss': 0.6599, 'learning_rate': 0.0004755291849587032, 'epoch': 2.01}

 17%|█▋        | 4711/28080 [9:19:21<46:05:29,  7.10s/it]
 17%|█▋        | 4712/28080 [9:19:28<46:16:05,  7.13s/it]
                                                         
{'loss': 0.6488, 'learning_rate': 0.0004755167410800504, 'epoch': 2.01}

 17%|█▋        | 4712/28080 [9:19:28<46:16:05,  7.13s/it]
 17%|█▋        | 4713/28080 [9:19:35<46:23:31,  7.15s/it]
                                                         
{'loss': 0.674, 'learning_rate': 0.00047550429420112984, 'epoch': 2.01}

 17%|█▋        | 4713/28080 [9:19:35<46:23:31,  7.15s/it]
 17%|█▋        | 4714/28080 [9:19:42<46:16:36,  7.13s/it]
                                                         
{'loss': 0.6603, 'learning_rate': 0.0004754918443221073, 'epoch': 2.01}

 17%|█▋        | 4714/28080 [9:19:42<46:16:36,  7.13s/it]
 17%|█▋        | 4715/28080 [9:19:49<46:10:33,  7.11s/it]
                                                         
{'loss': 0.6506, 'learning_rate': 0.00047547939144314846, 'epoch': 2.01}

 17%|█▋        | 4715/28080 [9:19:49<46:10:33,  7.11s/it]
 17%|█▋        | 4716/28080 [9:19:57<46:10:40,  7.12s/it]
                                                         
{'loss': 0.6499, 'learning_rate': 0.00047546693556441887, 'epoch': 2.01}

 17%|█▋        | 4716/28080 [9:19:57<46:10:40,  7.12s/it]
 17%|█▋        | 4717/28080 [9:20:04<45:59:49,  7.09s/it]
                                                         
{'loss': 0.6585, 'learning_rate': 0.00047545447668608437, 'epoch': 2.02}

 17%|█▋        | 4717/28080 [9:20:04<45:59:49,  7.09s/it]
 17%|█▋        | 4718/28080 [9:20:11<46:01:53,  7.09s/it]
                                                         
{'loss': 0.6545, 'learning_rate': 0.00047544201480831063, 'epoch': 2.02}

 17%|█▋        | 4718/28080 [9:20:11<46:01:53,  7.09s/it]
 17%|█▋        | 4719/28080 [9:20:18<46:06:24,  7.11s/it]
                                                         
{'loss': 0.6356, 'learning_rate': 0.00047542954993126343, 'epoch': 2.02}

 17%|█▋        | 4719/28080 [9:20:18<46:06:24,  7.11s/it]
 17%|█▋        | 4720/28080 [9:20:25<46:05:54,  7.10s/it]
                                                         
{'loss': 0.6789, 'learning_rate': 0.00047541708205510864, 'epoch': 2.02}

 17%|█▋        | 4720/28080 [9:20:25<46:05:54,  7.10s/it]
 17%|█▋        | 4721/28080 [9:20:32<46:06:19,  7.11s/it]
                                                         
{'loss': 0.6512, 'learning_rate': 0.0004754046111800121, 'epoch': 2.02}

 17%|█▋        | 4721/28080 [9:20:32<46:06:19,  7.11s/it]
 17%|█▋        | 4722/28080 [9:20:39<45:57:31,  7.08s/it]
                                                         
{'loss': 0.6667, 'learning_rate': 0.00047539213730613986, 'epoch': 2.02}

 17%|█▋        | 4722/28080 [9:20:39<45:57:31,  7.08s/it]
 17%|█▋        | 4723/28080 [9:20:46<46:02:07,  7.10s/it]
                                                         
{'loss': 0.6608, 'learning_rate': 0.00047537966043365764, 'epoch': 2.02}

 17%|█▋        | 4723/28080 [9:20:46<46:02:07,  7.10s/it]
 17%|█▋        | 4724/28080 [9:20:53<46:09:09,  7.11s/it]
                                                         
{'loss': 0.6187, 'learning_rate': 0.0004753671805627315, 'epoch': 2.02}

 17%|█▋        | 4724/28080 [9:20:53<46:09:09,  7.11s/it]
 17%|█▋        | 4725/28080 [9:21:00<46:04:43,  7.10s/it]
                                                         
{'loss': 0.642, 'learning_rate': 0.00047535469769352767, 'epoch': 2.02}

 17%|█▋        | 4725/28080 [9:21:00<46:04:43,  7.10s/it]
 17%|█▋        | 4726/28080 [9:21:08<46:03:03,  7.10s/it]
                                                         
{'loss': 0.6612, 'learning_rate': 0.00047534221182621197, 'epoch': 2.02}

 17%|█▋        | 4726/28080 [9:21:08<46:03:03,  7.10s/it]
 17%|█▋        | 4727/28080 [9:21:15<45:59:48,  7.09s/it]
                                                         
{'loss': 0.6695, 'learning_rate': 0.0004753297229609507, 'epoch': 2.02}

 17%|█▋        | 4727/28080 [9:21:15<45:59:48,  7.09s/it]
 17%|█▋        | 4728/28080 [9:21:22<46:02:20,  7.10s/it]
                                                         
{'loss': 0.6662, 'learning_rate': 0.0004753172310979098, 'epoch': 2.02}

 17%|█▋        | 4728/28080 [9:21:22<46:02:20,  7.10s/it]
 17%|█▋        | 4729/28080 [9:21:29<45:59:09,  7.09s/it]
                                                         
{'loss': 0.6627, 'learning_rate': 0.0004753047362372557, 'epoch': 2.02}

 17%|█▋        | 4729/28080 [9:21:29<45:59:09,  7.09s/it]
 17%|█▋        | 4730/28080 [9:21:36<45:59:33,  7.09s/it]
                                                         
{'loss': 0.6483, 'learning_rate': 0.00047529223837915446, 'epoch': 2.02}

 17%|█▋        | 4730/28080 [9:21:36<45:59:33,  7.09s/it]
 17%|█▋        | 4731/28080 [9:21:43<45:58:51,  7.09s/it]
                                                         
{'loss': 0.6522, 'learning_rate': 0.0004752797375237724, 'epoch': 2.02}

 17%|█▋        | 4731/28080 [9:21:43<45:58:51,  7.09s/it]
 17%|█▋        | 4732/28080 [9:21:50<46:00:38,  7.09s/it]
                                                         
{'loss': 0.6465, 'learning_rate': 0.0004752672336712759, 'epoch': 2.02}

 17%|█▋        | 4732/28080 [9:21:50<46:00:38,  7.09s/it]
 17%|█▋        | 4733/28080 [9:21:57<46:00:57,  7.10s/it]
                                                         
{'loss': 0.6406, 'learning_rate': 0.0004752547268218312, 'epoch': 2.02}

 17%|█▋        | 4733/28080 [9:21:57<46:00:57,  7.10s/it]
 17%|█▋        | 4734/28080 [9:22:04<45:59:48,  7.09s/it]
                                                         
{'loss': 0.6534, 'learning_rate': 0.00047524221697560476, 'epoch': 2.02}

 17%|█▋        | 4734/28080 [9:22:04<45:59:48,  7.09s/it]
 17%|█▋        | 4735/28080 [9:22:11<45:57:36,  7.09s/it]
                                                         
{'loss': 0.6491, 'learning_rate': 0.00047522970413276303, 'epoch': 2.02}

 17%|█▋        | 4735/28080 [9:22:11<45:57:36,  7.09s/it]
 17%|█▋        | 4736/28080 [9:22:19<46:16:51,  7.14s/it]
                                                         
{'loss': 0.6372, 'learning_rate': 0.0004752171882934724, 'epoch': 2.02}

 17%|█▋        | 4736/28080 [9:22:19<46:16:51,  7.14s/it]
 17%|█▋        | 4737/28080 [9:22:26<46:08:52,  7.12s/it]
                                                         
{'loss': 0.6287, 'learning_rate': 0.0004752046694578994, 'epoch': 2.02}

 17%|█▋        | 4737/28080 [9:22:26<46:08:52,  7.12s/it]
 17%|█▋        | 4738/28080 [9:22:33<46:16:55,  7.14s/it]
                                                         
{'loss': 0.6419, 'learning_rate': 0.00047519214762621067, 'epoch': 2.02}

 17%|█▋        | 4738/28080 [9:22:33<46:16:55,  7.14s/it]
 17%|█▋        | 4739/28080 [9:22:40<46:26:27,  7.16s/it]
                                                         
{'loss': 0.6542, 'learning_rate': 0.0004751796227985727, 'epoch': 2.02}

 17%|█▋        | 4739/28080 [9:22:40<46:26:27,  7.16s/it]
 17%|█▋        | 4740/28080 [9:22:47<46:27:43,  7.17s/it]
                                                         
{'loss': 0.6367, 'learning_rate': 0.00047516709497515217, 'epoch': 2.02}

 17%|█▋        | 4740/28080 [9:22:47<46:27:43,  7.17s/it]
 17%|█▋        | 4741/28080 [9:22:54<46:19:09,  7.14s/it]
                                                         
{'loss': 0.654, 'learning_rate': 0.0004751545641561157, 'epoch': 2.03}

 17%|█▋        | 4741/28080 [9:22:54<46:19:09,  7.14s/it]
 17%|█▋        | 4742/28080 [9:23:01<45:53:50,  7.08s/it]
                                                         
{'loss': 0.6559, 'learning_rate': 0.00047514203034163005, 'epoch': 2.03}

 17%|█▋        | 4742/28080 [9:23:01<45:53:50,  7.08s/it]
 17%|█▋        | 4743/28080 [9:23:08<45:49:28,  7.07s/it]
                                                         
{'loss': 0.6675, 'learning_rate': 0.00047512949353186194, 'epoch': 2.03}

 17%|█▋        | 4743/28080 [9:23:08<45:49:28,  7.07s/it]
 17%|█▋        | 4744/28080 [9:23:16<46:10:10,  7.12s/it]
                                                         
{'loss': 0.6587, 'learning_rate': 0.0004751169537269782, 'epoch': 2.03}

 17%|█▋        | 4744/28080 [9:23:16<46:10:10,  7.12s/it]
 17%|█▋        | 4745/28080 [9:23:23<46:16:54,  7.14s/it]
                                                         
{'loss': 0.6248, 'learning_rate': 0.0004751044109271456, 'epoch': 2.03}

 17%|█▋        | 4745/28080 [9:23:23<46:16:54,  7.14s/it]
 17%|█▋        | 4746/28080 [9:23:30<46:17:13,  7.14s/it]
                                                         
{'loss': 0.6512, 'learning_rate': 0.00047509186513253107, 'epoch': 2.03}

 17%|█▋        | 4746/28080 [9:23:30<46:17:13,  7.14s/it]
 17%|█▋        | 4747/28080 [9:23:37<46:08:58,  7.12s/it]
                                                         
{'loss': 0.6338, 'learning_rate': 0.0004750793163433015, 'epoch': 2.03}

 17%|█▋        | 4747/28080 [9:23:37<46:08:58,  7.12s/it]
 17%|█▋        | 4748/28080 [9:23:44<46:09:15,  7.12s/it]
                                                         
{'loss': 0.6292, 'learning_rate': 0.00047506676455962374, 'epoch': 2.03}

 17%|█▋        | 4748/28080 [9:23:44<46:09:15,  7.12s/it]
 17%|█▋        | 4749/28080 [9:23:51<46:15:51,  7.14s/it]
                                                         
{'loss': 0.6597, 'learning_rate': 0.0004750542097816649, 'epoch': 2.03}

 17%|█▋        | 4749/28080 [9:23:51<46:15:51,  7.14s/it]
 17%|█▋        | 4750/28080 [9:23:58<46:09:56,  7.12s/it]
                                                         
{'loss': 0.6403, 'learning_rate': 0.00047504165200959204, 'epoch': 2.03}

 17%|█▋        | 4750/28080 [9:23:58<46:09:56,  7.12s/it]
 17%|█▋        | 4751/28080 [9:24:05<46:05:08,  7.11s/it]
                                                         
{'loss': 0.6597, 'learning_rate': 0.0004750290912435721, 'epoch': 2.03}

 17%|█▋        | 4751/28080 [9:24:05<46:05:08,  7.11s/it]
 17%|█▋        | 4752/28080 [9:24:13<46:06:28,  7.12s/it]
                                                         
{'loss': 0.6503, 'learning_rate': 0.0004750165274837723, 'epoch': 2.03}

 17%|█▋        | 4752/28080 [9:24:13<46:06:28,  7.12s/it]
 17%|█▋        | 4753/28080 [9:24:20<46:05:16,  7.11s/it]
                                                         
{'loss': 0.6583, 'learning_rate': 0.0004750039607303597, 'epoch': 2.03}

 17%|█▋        | 4753/28080 [9:24:20<46:05:16,  7.11s/it]
 17%|█▋        | 4754/28080 [9:24:27<46:07:20,  7.12s/it]
                                                         
{'loss': 0.6343, 'learning_rate': 0.0004749913909835015, 'epoch': 2.03}

 17%|█▋        | 4754/28080 [9:24:27<46:07:20,  7.12s/it]
 17%|█▋        | 4755/28080 [9:24:34<46:02:18,  7.11s/it]
                                                         
{'loss': 0.6296, 'learning_rate': 0.000474978818243365, 'epoch': 2.03}

 17%|█▋        | 4755/28080 [9:24:34<46:02:18,  7.11s/it]
 17%|█▋        | 4756/28080 [9:24:41<46:03:27,  7.11s/it]
                                                         
{'loss': 0.6613, 'learning_rate': 0.00047496624251011746, 'epoch': 2.03}

 17%|█▋        | 4756/28080 [9:24:41<46:03:27,  7.11s/it]
 17%|█▋        | 4757/28080 [9:24:48<46:04:46,  7.11s/it]
                                                         
{'loss': 0.659, 'learning_rate': 0.00047495366378392606, 'epoch': 2.03}

 17%|█▋        | 4757/28080 [9:24:48<46:04:46,  7.11s/it]
 17%|█▋        | 4758/28080 [9:24:55<46:12:44,  7.13s/it]
                                                         
{'loss': 0.6466, 'learning_rate': 0.0004749410820649583, 'epoch': 2.03}

 17%|█▋        | 4758/28080 [9:24:55<46:12:44,  7.13s/it]
 17%|█▋        | 4759/28080 [9:25:02<46:13:42,  7.14s/it]
                                                         
{'loss': 0.6625, 'learning_rate': 0.0004749284973533815, 'epoch': 2.03}

 17%|█▋        | 4759/28080 [9:25:02<46:13:42,  7.14s/it]
 17%|█▋        | 4760/28080 [9:25:10<46:17:55,  7.15s/it]
                                                         
{'loss': 0.6354, 'learning_rate': 0.00047491590964936307, 'epoch': 2.03}

 17%|█▋        | 4760/28080 [9:25:10<46:17:55,  7.15s/it]
 17%|█▋        | 4761/28080 [9:25:17<46:22:51,  7.16s/it]
                                                         
{'loss': 0.6537, 'learning_rate': 0.0004749033189530705, 'epoch': 2.03}

 17%|█▋        | 4761/28080 [9:25:17<46:22:51,  7.16s/it]
 17%|█▋        | 4762/28080 [9:25:24<46:16:27,  7.14s/it]
                                                         
{'loss': 0.659, 'learning_rate': 0.00047489072526467124, 'epoch': 2.03}

 17%|█▋        | 4762/28080 [9:25:24<46:16:27,  7.14s/it]
 17%|█▋        | 4763/28080 [9:25:31<46:20:34,  7.16s/it]
                                                         
{'loss': 0.6402, 'learning_rate': 0.00047487812858433294, 'epoch': 2.03}

 17%|█▋        | 4763/28080 [9:25:31<46:20:34,  7.16s/it]
 17%|█▋        | 4764/28080 [9:25:38<46:17:58,  7.15s/it]
                                                         
{'loss': 0.6902, 'learning_rate': 0.00047486552891222314, 'epoch': 2.04}

 17%|█▋        | 4764/28080 [9:25:38<46:17:58,  7.15s/it]
 17%|█▋        | 4765/28080 [9:25:45<46:18:49,  7.15s/it]
                                                         
{'loss': 0.6441, 'learning_rate': 0.0004748529262485094, 'epoch': 2.04}

 17%|█▋        | 4765/28080 [9:25:45<46:18:49,  7.15s/it]
 17%|█▋        | 4766/28080 [9:25:53<46:21:45,  7.16s/it]
                                                         
{'loss': 0.6598, 'learning_rate': 0.00047484032059335945, 'epoch': 2.04}

 17%|█▋        | 4766/28080 [9:25:53<46:21:45,  7.16s/it]
 17%|█▋        | 4767/28080 [9:26:00<46:13:32,  7.14s/it]
                                                         
{'loss': 0.6777, 'learning_rate': 0.00047482771194694106, 'epoch': 2.04}

 17%|█▋        | 4767/28080 [9:26:00<46:13:32,  7.14s/it]
 17%|█▋        | 4768/28080 [9:26:07<46:21:05,  7.16s/it]
                                                         
{'loss': 0.6515, 'learning_rate': 0.00047481510030942186, 'epoch': 2.04}

 17%|█▋        | 4768/28080 [9:26:07<46:21:05,  7.16s/it]
 17%|█▋        | 4769/28080 [9:26:14<46:15:18,  7.14s/it]
                                                         
{'loss': 0.6376, 'learning_rate': 0.00047480248568096975, 'epoch': 2.04}

 17%|█▋        | 4769/28080 [9:26:14<46:15:18,  7.14s/it]
 17%|█▋        | 4770/28080 [9:26:21<46:11:34,  7.13s/it]
                                                         
{'loss': 0.6713, 'learning_rate': 0.0004747898680617524, 'epoch': 2.04}

 17%|█▋        | 4770/28080 [9:26:21<46:11:34,  7.13s/it]
 17%|█▋        | 4771/28080 [9:26:28<46:16:36,  7.15s/it]
                                                         
{'loss': 0.672, 'learning_rate': 0.00047477724745193775, 'epoch': 2.04}

 17%|█▋        | 4771/28080 [9:26:28<46:16:36,  7.15s/it]
 17%|█▋        | 4772/28080 [9:26:35<46:09:32,  7.13s/it]
                                                         
{'loss': 0.658, 'learning_rate': 0.00047476462385169374, 'epoch': 2.04}

 17%|█▋        | 4772/28080 [9:26:35<46:09:32,  7.13s/it]
 17%|█▋        | 4773/28080 [9:26:42<45:58:49,  7.10s/it]
                                                         
{'loss': 0.6454, 'learning_rate': 0.0004747519972611883, 'epoch': 2.04}

 17%|█▋        | 4773/28080 [9:26:42<45:58:49,  7.10s/it]
 17%|█▋        | 4774/28080 [9:26:50<46:06:55,  7.12s/it]
                                                         
{'loss': 0.6634, 'learning_rate': 0.0004747393676805894, 'epoch': 2.04}

 17%|█▋        | 4774/28080 [9:26:50<46:06:55,  7.12s/it]
 17%|█▋        | 4775/28080 [9:26:57<46:02:04,  7.11s/it]
                                                         
{'loss': 0.6384, 'learning_rate': 0.000474726735110065, 'epoch': 2.04}

 17%|█▋        | 4775/28080 [9:26:57<46:02:04,  7.11s/it]
 17%|█▋        | 4776/28080 [9:27:04<45:53:59,  7.09s/it]
                                                         
{'loss': 0.6833, 'learning_rate': 0.0004747140995497833, 'epoch': 2.04}

 17%|█▋        | 4776/28080 [9:27:04<45:53:59,  7.09s/it]
 17%|█▋        | 4777/28080 [9:27:11<45:56:17,  7.10s/it]
                                                         
{'loss': 0.6791, 'learning_rate': 0.0004747014609999123, 'epoch': 2.04}

 17%|█▋        | 4777/28080 [9:27:11<45:56:17,  7.10s/it]
 17%|█▋        | 4778/28080 [9:27:18<45:45:54,  7.07s/it]
                                                         
{'loss': 0.6651, 'learning_rate': 0.0004746888194606202, 'epoch': 2.04}

 17%|█▋        | 4778/28080 [9:27:18<45:45:54,  7.07s/it]
 17%|█▋        | 4779/28080 [9:27:25<45:42:29,  7.06s/it]
                                                         
{'loss': 0.6407, 'learning_rate': 0.00047467617493207517, 'epoch': 2.04}

 17%|█▋        | 4779/28080 [9:27:25<45:42:29,  7.06s/it]
 17%|█▋        | 4780/28080 [9:27:32<45:47:25,  7.07s/it]
                                                         
{'loss': 0.6502, 'learning_rate': 0.00047466352741444535, 'epoch': 2.04}

 17%|█▋        | 4780/28080 [9:27:32<45:47:25,  7.07s/it]
 17%|█▋        | 4781/28080 [9:27:39<45:49:22,  7.08s/it]
                                                         
{'loss': 0.6516, 'learning_rate': 0.0004746508769078991, 'epoch': 2.04}

 17%|█▋        | 4781/28080 [9:27:39<45:49:22,  7.08s/it]
 17%|█▋        | 4782/28080 [9:27:46<45:50:37,  7.08s/it]
                                                         
{'loss': 0.6485, 'learning_rate': 0.00047463822341260476, 'epoch': 2.04}

 17%|█▋        | 4782/28080 [9:27:46<45:50:37,  7.08s/it]
 17%|█▋        | 4783/28080 [9:27:53<45:46:11,  7.07s/it]
                                                         
{'loss': 0.6742, 'learning_rate': 0.00047462556692873047, 'epoch': 2.04}

 17%|█▋        | 4783/28080 [9:27:53<45:46:11,  7.07s/it]
 17%|█▋        | 4784/28080 [9:28:00<45:36:10,  7.05s/it]
                                                         
{'loss': 0.6486, 'learning_rate': 0.00047461290745644486, 'epoch': 2.04}

 17%|█▋        | 4784/28080 [9:28:00<45:36:10,  7.05s/it]
 17%|█▋        | 4785/28080 [9:28:07<45:47:31,  7.08s/it]
                                                         
{'loss': 0.6537, 'learning_rate': 0.0004746002449959162, 'epoch': 2.04}

 17%|█▋        | 4785/28080 [9:28:07<45:47:31,  7.08s/it]
 17%|█▋        | 4786/28080 [9:28:14<45:57:38,  7.10s/it]
                                                         
{'loss': 0.6604, 'learning_rate': 0.000474587579547313, 'epoch': 2.04}

 17%|█▋        | 4786/28080 [9:28:14<45:57:38,  7.10s/it]
 17%|█▋        | 4787/28080 [9:28:22<46:09:36,  7.13s/it]
                                                         
{'loss': 0.6708, 'learning_rate': 0.0004745749111108037, 'epoch': 2.04}

 17%|█▋        | 4787/28080 [9:28:22<46:09:36,  7.13s/it]
 17%|█▋        | 4788/28080 [9:28:29<46:01:22,  7.11s/it]
                                                         
{'loss': 0.6481, 'learning_rate': 0.00047456223968655694, 'epoch': 2.05}

 17%|█▋        | 4788/28080 [9:28:29<46:01:22,  7.11s/it]
 17%|█▋        | 4789/28080 [9:28:36<45:55:31,  7.10s/it]
                                                         
{'loss': 0.6529, 'learning_rate': 0.00047454956527474124, 'epoch': 2.05}

 17%|█▋        | 4789/28080 [9:28:36<45:55:31,  7.10s/it]
 17%|█▋        | 4790/28080 [9:28:43<45:54:44,  7.10s/it]
                                                         
{'loss': 0.6568, 'learning_rate': 0.0004745368878755252, 'epoch': 2.05}

 17%|█▋        | 4790/28080 [9:28:43<45:54:44,  7.10s/it]
 17%|█▋        | 4791/28080 [9:28:50<45:47:11,  7.08s/it]
                                                         
{'loss': 0.6583, 'learning_rate': 0.00047452420748907755, 'epoch': 2.05}

 17%|█▋        | 4791/28080 [9:28:50<45:47:11,  7.08s/it]
 17%|█▋        | 4792/28080 [9:28:57<45:55:37,  7.10s/it]
                                                         
{'loss': 0.6639, 'learning_rate': 0.00047451152411556686, 'epoch': 2.05}

 17%|█▋        | 4792/28080 [9:28:57<45:55:37,  7.10s/it]
 17%|█▋        | 4793/28080 [9:29:04<45:55:46,  7.10s/it]
                                                         
{'loss': 0.6469, 'learning_rate': 0.000474498837755162, 'epoch': 2.05}

 17%|█▋        | 4793/28080 [9:29:04<45:55:46,  7.10s/it]
 17%|█▋        | 4794/28080 [9:29:11<45:56:13,  7.10s/it]
                                                         
{'loss': 0.636, 'learning_rate': 0.0004744861484080318, 'epoch': 2.05}

 17%|█▋        | 4794/28080 [9:29:11<45:56:13,  7.10s/it]
 17%|█▋        | 4795/28080 [9:29:18<45:58:08,  7.11s/it]
                                                         
{'loss': 0.6411, 'learning_rate': 0.0004744734560743449, 'epoch': 2.05}

 17%|█▋        | 4795/28080 [9:29:18<45:58:08,  7.11s/it]
 17%|█▋        | 4796/28080 [9:29:25<45:49:33,  7.09s/it]
                                                         
{'loss': 0.6631, 'learning_rate': 0.00047446076075427024, 'epoch': 2.05}

 17%|█▋        | 4796/28080 [9:29:25<45:49:33,  7.09s/it]
 17%|█▋        | 4797/28080 [9:29:33<45:53:33,  7.10s/it]
                                                         
{'loss': 0.6562, 'learning_rate': 0.00047444806244797673, 'epoch': 2.05}

 17%|█▋        | 4797/28080 [9:29:33<45:53:33,  7.10s/it]
 17%|█▋        | 4798/28080 [9:29:40<46:02:06,  7.12s/it]
                                                         
{'loss': 0.6512, 'learning_rate': 0.00047443536115563333, 'epoch': 2.05}

 17%|█▋        | 4798/28080 [9:29:40<46:02:06,  7.12s/it]
 17%|█▋        | 4799/28080 [9:29:47<45:59:01,  7.11s/it]
                                                         
{'loss': 0.6446, 'learning_rate': 0.0004744226568774089, 'epoch': 2.05}

 17%|█▋        | 4799/28080 [9:29:47<45:59:01,  7.11s/it]
 17%|█▋        | 4800/28080 [9:29:54<45:56:56,  7.11s/it]
                                                         
{'loss': 0.6355, 'learning_rate': 0.0004744099496134726, 'epoch': 2.05}

 17%|█▋        | 4800/28080 [9:29:54<45:56:56,  7.11s/it]
 17%|█▋        | 4801/28080 [9:30:01<45:59:15,  7.11s/it]
                                                         
{'loss': 0.6471, 'learning_rate': 0.00047439723936399346, 'epoch': 2.05}

 17%|█▋        | 4801/28080 [9:30:01<45:59:15,  7.11s/it]
 17%|█▋        | 4802/28080 [9:30:08<46:07:49,  7.13s/it]
                                                         
{'loss': 0.6811, 'learning_rate': 0.00047438452612914053, 'epoch': 2.05}

 17%|█▋        | 4802/28080 [9:30:08<46:07:49,  7.13s/it]
 17%|█▋        | 4803/28080 [9:30:15<45:59:20,  7.11s/it]
                                                         
{'loss': 0.657, 'learning_rate': 0.000474371809909083, 'epoch': 2.05}

 17%|█▋        | 4803/28080 [9:30:15<45:59:20,  7.11s/it]
 17%|█▋        | 4804/28080 [9:30:22<46:02:23,  7.12s/it]
                                                         
{'loss': 0.6383, 'learning_rate': 0.00047435909070399, 'epoch': 2.05}

 17%|█▋        | 4804/28080 [9:30:22<46:02:23,  7.12s/it]
 17%|█▋        | 4805/28080 [9:30:30<46:07:47,  7.14s/it]
                                                         
{'loss': 0.6314, 'learning_rate': 0.00047434636851403065, 'epoch': 2.05}

 17%|█▋        | 4805/28080 [9:30:30<46:07:47,  7.14s/it]
 17%|█▋        | 4806/28080 [9:30:37<46:07:32,  7.13s/it]
                                                         
{'loss': 0.6493, 'learning_rate': 0.00047433364333937446, 'epoch': 2.05}

 17%|█▋        | 4806/28080 [9:30:37<46:07:32,  7.13s/it]
 17%|█▋        | 4807/28080 [9:30:44<46:03:56,  7.13s/it]
                                                         
{'loss': 0.6511, 'learning_rate': 0.0004743209151801905, 'epoch': 2.05}

 17%|█▋        | 4807/28080 [9:30:44<46:03:56,  7.13s/it]
 17%|█▋        | 4808/28080 [9:30:51<45:57:18,  7.11s/it]
                                                         
{'loss': 0.6395, 'learning_rate': 0.00047430818403664817, 'epoch': 2.05}

 17%|█▋        | 4808/28080 [9:30:51<45:57:18,  7.11s/it]
 17%|█▋        | 4809/28080 [9:30:58<45:53:10,  7.10s/it]
                                                         
{'loss': 0.6612, 'learning_rate': 0.0004742954499089169, 'epoch': 2.05}

 17%|█▋        | 4809/28080 [9:30:58<45:53:10,  7.10s/it]
 17%|█▋        | 4810/28080 [9:31:05<45:39:21,  7.06s/it]
                                                         
{'loss': 0.6534, 'learning_rate': 0.000474282712797166, 'epoch': 2.05}

 17%|█▋        | 4810/28080 [9:31:05<45:39:21,  7.06s/it]
 17%|█▋        | 4811/28080 [9:31:12<45:43:45,  7.07s/it]
                                                         
{'loss': 0.6577, 'learning_rate': 0.000474269972701565, 'epoch': 2.06}

 17%|█▋        | 4811/28080 [9:31:12<45:43:45,  7.07s/it]
 17%|█▋        | 4812/28080 [9:31:19<45:37:16,  7.06s/it]
                                                         
{'loss': 0.6501, 'learning_rate': 0.00047425722962228344, 'epoch': 2.06}

 17%|█▋        | 4812/28080 [9:31:19<45:37:16,  7.06s/it]
 17%|█▋        | 4813/28080 [9:31:26<45:38:13,  7.06s/it]
                                                         
{'loss': 0.6613, 'learning_rate': 0.0004742444835594908, 'epoch': 2.06}

 17%|█▋        | 4813/28080 [9:31:26<45:38:13,  7.06s/it]
 17%|█▋        | 4814/28080 [9:31:33<45:41:50,  7.07s/it]
                                                         
{'loss': 0.6692, 'learning_rate': 0.00047423173451335653, 'epoch': 2.06}

 17%|█▋        | 4814/28080 [9:31:33<45:41:50,  7.07s/it]
 17%|█▋        | 4815/28080 [9:31:40<45:39:02,  7.06s/it]
                                                         
{'loss': 0.6627, 'learning_rate': 0.0004742189824840505, 'epoch': 2.06}

 17%|█▋        | 4815/28080 [9:31:40<45:39:02,  7.06s/it]
 17%|█▋        | 4816/28080 [9:31:47<45:52:55,  7.10s/it]
                                                         
{'loss': 0.6383, 'learning_rate': 0.00047420622747174215, 'epoch': 2.06}

 17%|█▋        | 4816/28080 [9:31:47<45:52:55,  7.10s/it]
 17%|█▋        | 4817/28080 [9:31:55<45:46:47,  7.08s/it]
                                                         
{'loss': 0.6621, 'learning_rate': 0.00047419346947660124, 'epoch': 2.06}

 17%|█▋        | 4817/28080 [9:31:55<45:46:47,  7.08s/it]
 17%|█▋        | 4818/28080 [9:32:02<45:51:46,  7.10s/it]
                                                         
{'loss': 0.6427, 'learning_rate': 0.0004741807084987975, 'epoch': 2.06}

 17%|█▋        | 4818/28080 [9:32:02<45:51:46,  7.10s/it]
 17%|█▋        | 4819/28080 [9:32:09<45:51:34,  7.10s/it]
                                                         
{'loss': 0.6613, 'learning_rate': 0.00047416794453850075, 'epoch': 2.06}

 17%|█▋        | 4819/28080 [9:32:09<45:51:34,  7.10s/it]
 17%|█▋        | 4820/28080 [9:32:16<45:42:51,  7.08s/it]
                                                         
{'loss': 0.6449, 'learning_rate': 0.00047415517759588074, 'epoch': 2.06}

 17%|█▋        | 4820/28080 [9:32:16<45:42:51,  7.08s/it]
 17%|█▋        | 4821/28080 [9:32:23<45:51:02,  7.10s/it]
                                                         
{'loss': 0.6625, 'learning_rate': 0.00047414240767110725, 'epoch': 2.06}

 17%|█▋        | 4821/28080 [9:32:23<45:51:02,  7.10s/it]
 17%|█▋        | 4822/28080 [9:32:30<45:43:18,  7.08s/it]
                                                         
{'loss': 0.6539, 'learning_rate': 0.0004741296347643504, 'epoch': 2.06}

 17%|█▋        | 4822/28080 [9:32:30<45:43:18,  7.08s/it]
 17%|█▋        | 4823/28080 [9:32:37<45:47:34,  7.09s/it]
                                                         
{'loss': 0.6187, 'learning_rate': 0.0004741168588757799, 'epoch': 2.06}

 17%|█▋        | 4823/28080 [9:32:37<45:47:34,  7.09s/it]
 17%|█▋        | 4824/28080 [9:32:44<45:53:49,  7.10s/it]
                                                         
{'loss': 0.6325, 'learning_rate': 0.0004741040800055658, 'epoch': 2.06}

 17%|█▋        | 4824/28080 [9:32:44<45:53:49,  7.10s/it]
 17%|█▋        | 4825/28080 [9:32:51<45:47:15,  7.09s/it]
                                                         
{'loss': 0.6517, 'learning_rate': 0.0004740912981538782, 'epoch': 2.06}

 17%|█▋        | 4825/28080 [9:32:51<45:47:15,  7.09s/it]
 17%|█▋        | 4826/28080 [9:32:58<45:47:25,  7.09s/it]
                                                         
{'loss': 0.6499, 'learning_rate': 0.00047407851332088705, 'epoch': 2.06}

 17%|█▋        | 4826/28080 [9:32:58<45:47:25,  7.09s/it]
 17%|█▋        | 4827/28080 [9:33:06<46:01:30,  7.13s/it]
                                                         
{'loss': 0.6466, 'learning_rate': 0.00047406572550676233, 'epoch': 2.06}

 17%|█▋        | 4827/28080 [9:33:06<46:01:30,  7.13s/it]
 17%|█▋        | 4828/28080 [9:33:13<46:06:00,  7.14s/it]
                                                         
{'loss': 0.6434, 'learning_rate': 0.00047405293471167436, 'epoch': 2.06}

 17%|█▋        | 4828/28080 [9:33:13<46:06:00,  7.14s/it]
 17%|█▋        | 4829/28080 [9:33:20<45:59:02,  7.12s/it]
                                                         
{'loss': 0.6473, 'learning_rate': 0.0004740401409357932, 'epoch': 2.06}

 17%|█▋        | 4829/28080 [9:33:20<45:59:02,  7.12s/it]
 17%|█▋        | 4830/28080 [9:33:27<46:07:11,  7.14s/it]
                                                         
{'loss': 0.6337, 'learning_rate': 0.00047402734417928915, 'epoch': 2.06}

 17%|█▋        | 4830/28080 [9:33:27<46:07:11,  7.14s/it]
 17%|█▋        | 4831/28080 [9:33:34<45:53:53,  7.11s/it]
                                                         
{'loss': 0.6536, 'learning_rate': 0.0004740145444423324, 'epoch': 2.06}

 17%|█▋        | 4831/28080 [9:33:34<45:53:53,  7.11s/it]
 17%|█▋        | 4832/28080 [9:33:41<46:03:29,  7.13s/it]
                                                         
{'loss': 0.6447, 'learning_rate': 0.0004740017417250932, 'epoch': 2.06}

 17%|█▋        | 4832/28080 [9:33:41<46:03:29,  7.13s/it]
 17%|█▋        | 4833/28080 [9:33:48<45:47:37,  7.09s/it]
                                                         
{'loss': 0.6219, 'learning_rate': 0.00047398893602774197, 'epoch': 2.06}

 17%|█▋        | 4833/28080 [9:33:48<45:47:37,  7.09s/it]
 17%|█▋        | 4834/28080 [9:33:55<45:56:34,  7.11s/it]
                                                         
{'loss': 0.66, 'learning_rate': 0.0004739761273504489, 'epoch': 2.07}

 17%|█▋        | 4834/28080 [9:33:55<45:56:34,  7.11s/it]
 17%|█▋        | 4835/28080 [9:34:03<45:56:41,  7.12s/it]
                                                         
{'loss': 0.6423, 'learning_rate': 0.00047396331569338467, 'epoch': 2.07}

 17%|█▋        | 4835/28080 [9:34:03<45:56:41,  7.12s/it]
 17%|█▋        | 4836/28080 [9:34:10<45:47:14,  7.09s/it]
                                                         
{'loss': 0.6353, 'learning_rate': 0.0004739505010567195, 'epoch': 2.07}

 17%|█▋        | 4836/28080 [9:34:10<45:47:14,  7.09s/it]
 17%|█▋        | 4837/28080 [9:34:17<45:52:47,  7.11s/it]
                                                         
{'loss': 0.6527, 'learning_rate': 0.00047393768344062393, 'epoch': 2.07}

 17%|█▋        | 4837/28080 [9:34:17<45:52:47,  7.11s/it]
 17%|█▋        | 4838/28080 [9:34:24<45:44:40,  7.09s/it]
                                                         
{'loss': 0.6676, 'learning_rate': 0.00047392486284526857, 'epoch': 2.07}

 17%|█▋        | 4838/28080 [9:34:24<45:44:40,  7.09s/it]
 17%|█▋        | 4839/28080 [9:34:31<45:48:17,  7.10s/it]
                                                         
{'loss': 0.6478, 'learning_rate': 0.0004739120392708239, 'epoch': 2.07}

 17%|█▋        | 4839/28080 [9:34:31<45:48:17,  7.10s/it]
 17%|█▋        | 4840/28080 [9:34:38<45:43:46,  7.08s/it]
                                                         
{'loss': 0.6436, 'learning_rate': 0.0004738992127174605, 'epoch': 2.07}

 17%|█▋        | 4840/28080 [9:34:38<45:43:46,  7.08s/it]
 17%|█▋        | 4841/28080 [9:34:45<45:45:09,  7.09s/it]
                                                         
{'loss': 0.6489, 'learning_rate': 0.00047388638318534903, 'epoch': 2.07}

 17%|█▋        | 4841/28080 [9:34:45<45:45:09,  7.09s/it]
 17%|█▋        | 4842/28080 [9:34:52<45:40:56,  7.08s/it]
                                                         
{'loss': 0.6243, 'learning_rate': 0.0004738735506746603, 'epoch': 2.07}

 17%|█▋        | 4842/28080 [9:34:52<45:40:56,  7.08s/it]
 17%|█▋        | 4843/28080 [9:34:59<45:45:09,  7.09s/it]
                                                         
{'loss': 0.6511, 'learning_rate': 0.00047386071518556495, 'epoch': 2.07}

 17%|█▋        | 4843/28080 [9:34:59<45:45:09,  7.09s/it]
 17%|█▋        | 4844/28080 [9:35:06<45:56:15,  7.12s/it]
                                                         
{'loss': 0.6564, 'learning_rate': 0.00047384787671823366, 'epoch': 2.07}

 17%|█▋        | 4844/28080 [9:35:06<45:56:15,  7.12s/it]
 17%|█▋        | 4845/28080 [9:35:13<45:54:56,  7.11s/it]
                                                         
{'loss': 0.6281, 'learning_rate': 0.0004738350352728373, 'epoch': 2.07}

 17%|█▋        | 4845/28080 [9:35:13<45:54:56,  7.11s/it]
 17%|█▋        | 4846/28080 [9:35:21<45:54:07,  7.11s/it]
                                                         
{'loss': 0.6528, 'learning_rate': 0.0004738221908495467, 'epoch': 2.07}

 17%|█▋        | 4846/28080 [9:35:21<45:54:07,  7.11s/it]
 17%|█▋        | 4847/28080 [9:35:28<45:34:34,  7.06s/it]
                                                         
{'loss': 0.6474, 'learning_rate': 0.0004738093434485328, 'epoch': 2.07}

 17%|█▋        | 4847/28080 [9:35:28<45:34:34,  7.06s/it]
 17%|█▋        | 4848/28080 [9:35:35<45:33:44,  7.06s/it]
                                                         
{'loss': 0.6577, 'learning_rate': 0.0004737964930699665, 'epoch': 2.07}

 17%|█▋        | 4848/28080 [9:35:35<45:33:44,  7.06s/it]
 17%|█▋        | 4849/28080 [9:35:42<45:44:46,  7.09s/it]
                                                         
{'loss': 0.6388, 'learning_rate': 0.0004737836397140187, 'epoch': 2.07}

 17%|█▋        | 4849/28080 [9:35:42<45:44:46,  7.09s/it]
 17%|█▋        | 4850/28080 [9:35:49<45:52:47,  7.11s/it]
                                                         
{'loss': 0.6428, 'learning_rate': 0.00047377078338086044, 'epoch': 2.07}

 17%|█▋        | 4850/28080 [9:35:49<45:52:47,  7.11s/it]
 17%|█▋        | 4851/28080 [9:35:56<45:55:16,  7.12s/it]
                                                         
{'loss': 0.6502, 'learning_rate': 0.00047375792407066276, 'epoch': 2.07}

 17%|█▋        | 4851/28080 [9:35:56<45:55:16,  7.12s/it]
 17%|█▋        | 4852/28080 [9:36:03<45:55:25,  7.12s/it]
                                                         
{'loss': 0.6598, 'learning_rate': 0.0004737450617835967, 'epoch': 2.07}

 17%|█▋        | 4852/28080 [9:36:03<45:55:25,  7.12s/it]
 17%|█▋        | 4853/28080 [9:36:10<45:46:24,  7.09s/it]
                                                         
{'loss': 0.6388, 'learning_rate': 0.0004737321965198335, 'epoch': 2.07}

 17%|█▋        | 4853/28080 [9:36:10<45:46:24,  7.09s/it]
 17%|█▋        | 4854/28080 [9:36:17<45:45:48,  7.09s/it]
                                                         
{'loss': 0.6558, 'learning_rate': 0.0004737193282795441, 'epoch': 2.07}

 17%|█▋        | 4854/28080 [9:36:17<45:45:48,  7.09s/it]
 17%|█▋        | 4855/28080 [9:36:24<45:43:34,  7.09s/it]
                                                         
{'loss': 0.6386, 'learning_rate': 0.00047370645706289996, 'epoch': 2.07}

 17%|█▋        | 4855/28080 [9:36:24<45:43:34,  7.09s/it]
 17%|█▋        | 4856/28080 [9:36:31<45:42:33,  7.09s/it]
                                                         
{'loss': 0.6642, 'learning_rate': 0.00047369358287007216, 'epoch': 2.07}

 17%|█▋        | 4856/28080 [9:36:31<45:42:33,  7.09s/it]
 17%|█▋        | 4857/28080 [9:36:38<45:41:12,  7.08s/it]
                                                         
{'loss': 0.667, 'learning_rate': 0.000473680705701232, 'epoch': 2.07}

 17%|█▋        | 4857/28080 [9:36:38<45:41:12,  7.08s/it]
 17%|█▋        | 4858/28080 [9:36:46<46:02:24,  7.14s/it]
                                                         
{'loss': 0.6477, 'learning_rate': 0.00047366782555655085, 'epoch': 2.08}

 17%|█▋        | 4858/28080 [9:36:46<46:02:24,  7.14s/it]
 17%|█▋        | 4859/28080 [9:36:53<46:08:06,  7.15s/it]
                                                         
{'loss': 0.6475, 'learning_rate': 0.0004736549424362, 'epoch': 2.08}

 17%|█▋        | 4859/28080 [9:36:53<46:08:06,  7.15s/it]
 17%|█▋        | 4860/28080 [9:37:00<45:59:58,  7.13s/it]
                                                         
{'loss': 0.6444, 'learning_rate': 0.00047364205634035087, 'epoch': 2.08}

 17%|█▋        | 4860/28080 [9:37:00<45:59:58,  7.13s/it]
 17%|█▋        | 4861/28080 [9:37:07<45:44:48,  7.09s/it]
                                                         
{'loss': 0.6451, 'learning_rate': 0.00047362916726917495, 'epoch': 2.08}

 17%|█▋        | 4861/28080 [9:37:07<45:44:48,  7.09s/it]
 17%|█▋        | 4862/28080 [9:37:14<45:35:15,  7.07s/it]
                                                         
{'loss': 0.6803, 'learning_rate': 0.00047361627522284354, 'epoch': 2.08}

 17%|█▋        | 4862/28080 [9:37:14<45:35:15,  7.07s/it]
 17%|█▋        | 4863/28080 [9:37:21<45:37:51,  7.08s/it]
                                                         
{'loss': 0.661, 'learning_rate': 0.00047360338020152837, 'epoch': 2.08}

 17%|█▋        | 4863/28080 [9:37:21<45:37:51,  7.08s/it]
 17%|█▋        | 4864/28080 [9:37:28<45:49:57,  7.11s/it]
                                                         
{'loss': 0.6591, 'learning_rate': 0.0004735904822054009, 'epoch': 2.08}

 17%|█▋        | 4864/28080 [9:37:28<45:49:57,  7.11s/it]
 17%|█▋        | 4865/28080 [9:37:35<45:47:15,  7.10s/it]
                                                         
{'loss': 0.6563, 'learning_rate': 0.00047357758123463267, 'epoch': 2.08}

 17%|█▋        | 4865/28080 [9:37:35<45:47:15,  7.10s/it]
 17%|█▋        | 4866/28080 [9:37:43<45:49:40,  7.11s/it]
                                                         
{'loss': 0.6608, 'learning_rate': 0.00047356467728939546, 'epoch': 2.08}

 17%|█▋        | 4866/28080 [9:37:43<45:49:40,  7.11s/it]
 17%|█▋        | 4867/28080 [9:37:50<45:35:49,  7.07s/it]
                                                         
{'loss': 0.6565, 'learning_rate': 0.00047355177036986085, 'epoch': 2.08}

 17%|█▋        | 4867/28080 [9:37:50<45:35:49,  7.07s/it]
 17%|█▋        | 4868/28080 [9:37:57<45:43:01,  7.09s/it]
                                                         
{'loss': 0.6682, 'learning_rate': 0.00047353886047620057, 'epoch': 2.08}

 17%|█▋        | 4868/28080 [9:37:57<45:43:01,  7.09s/it]
 17%|█▋        | 4869/28080 [9:38:04<45:37:06,  7.08s/it]
                                                         
{'loss': 0.6542, 'learning_rate': 0.00047352594760858625, 'epoch': 2.08}

 17%|█▋        | 4869/28080 [9:38:04<45:37:06,  7.08s/it]
 17%|█▋        | 4870/28080 [9:38:11<45:37:34,  7.08s/it]
                                                         
{'loss': 0.6401, 'learning_rate': 0.00047351303176718985, 'epoch': 2.08}

 17%|█▋        | 4870/28080 [9:38:11<45:37:34,  7.08s/it]
 17%|█▋        | 4871/28080 [9:38:18<45:34:19,  7.07s/it]
                                                         
{'loss': 0.6784, 'learning_rate': 0.0004735001129521832, 'epoch': 2.08}

 17%|█▋        | 4871/28080 [9:38:18<45:34:19,  7.07s/it]
 17%|█▋        | 4872/28080 [9:38:25<45:30:32,  7.06s/it]
                                                         
{'loss': 0.6571, 'learning_rate': 0.0004734871911637381, 'epoch': 2.08}

 17%|█▋        | 4872/28080 [9:38:25<45:30:32,  7.06s/it]
 17%|█▋        | 4873/28080 [9:38:32<45:33:54,  7.07s/it]
                                                         
{'loss': 0.6547, 'learning_rate': 0.00047347426640202646, 'epoch': 2.08}

 17%|█▋        | 4873/28080 [9:38:32<45:33:54,  7.07s/it]
 17%|█▋        | 4874/28080 [9:38:39<45:38:37,  7.08s/it]
                                                         
{'loss': 0.659, 'learning_rate': 0.00047346133866722024, 'epoch': 2.08}

 17%|█▋        | 4874/28080 [9:38:39<45:38:37,  7.08s/it]
 17%|█▋        | 4875/28080 [9:38:46<45:34:57,  7.07s/it]
                                                         
{'loss': 0.6368, 'learning_rate': 0.0004734484079594915, 'epoch': 2.08}

 17%|█▋        | 4875/28080 [9:38:46<45:34:57,  7.07s/it]
 17%|█▋        | 4876/28080 [9:38:53<45:29:29,  7.06s/it]
                                                         
{'loss': 0.6703, 'learning_rate': 0.00047343547427901214, 'epoch': 2.08}

 17%|█▋        | 4876/28080 [9:38:53<45:29:29,  7.06s/it]
 17%|█▋        | 4877/28080 [9:39:00<45:30:56,  7.06s/it]
                                                         
{'loss': 0.6604, 'learning_rate': 0.0004734225376259543, 'epoch': 2.08}

 17%|█▋        | 4877/28080 [9:39:00<45:30:56,  7.06s/it]
 17%|█▋        | 4878/28080 [9:39:07<45:30:58,  7.06s/it]
                                                         
{'loss': 0.6675, 'learning_rate': 0.00047340959800049016, 'epoch': 2.08}

 17%|█▋        | 4878/28080 [9:39:07<45:30:58,  7.06s/it]
 17%|█▋        | 4879/28080 [9:39:14<45:30:12,  7.06s/it]
                                                         
{'loss': 0.6466, 'learning_rate': 0.0004733966554027918, 'epoch': 2.08}

 17%|█▋        | 4879/28080 [9:39:14<45:30:12,  7.06s/it]
 17%|█▋        | 4880/28080 [9:39:21<45:17:09,  7.03s/it]
                                                         
{'loss': 0.6572, 'learning_rate': 0.0004733837098330313, 'epoch': 2.08}

 17%|█▋        | 4880/28080 [9:39:21<45:17:09,  7.03s/it]
 17%|█▋        | 4881/28080 [9:39:28<45:32:06,  7.07s/it]
                                                         
{'loss': 0.6573, 'learning_rate': 0.0004733707612913811, 'epoch': 2.09}

 17%|█▋        | 4881/28080 [9:39:28<45:32:06,  7.07s/it]
 17%|█▋        | 4882/28080 [9:39:35<45:31:11,  7.06s/it]
                                                         
{'loss': 0.6237, 'learning_rate': 0.0004733578097780133, 'epoch': 2.09}

 17%|█▋        | 4882/28080 [9:39:35<45:31:11,  7.06s/it]
 17%|█▋        | 4883/28080 [9:39:43<45:34:33,  7.07s/it]
                                                         
{'loss': 0.6823, 'learning_rate': 0.0004733448552931003, 'epoch': 2.09}

 17%|█▋        | 4883/28080 [9:39:43<45:34:33,  7.07s/it]
 17%|█▋        | 4884/28080 [9:39:50<45:41:20,  7.09s/it]
                                                         
{'loss': 0.6382, 'learning_rate': 0.0004733318978368144, 'epoch': 2.09}

 17%|█▋        | 4884/28080 [9:39:50<45:41:20,  7.09s/it]
 17%|█▋        | 4885/28080 [9:39:57<45:28:16,  7.06s/it]
                                                         
{'loss': 0.6496, 'learning_rate': 0.000473318937409328, 'epoch': 2.09}

 17%|█▋        | 4885/28080 [9:39:57<45:28:16,  7.06s/it]
 17%|█▋        | 4886/28080 [9:40:04<45:42:30,  7.09s/it]
                                                         
{'loss': 0.656, 'learning_rate': 0.0004733059740108135, 'epoch': 2.09}

 17%|█▋        | 4886/28080 [9:40:04<45:42:30,  7.09s/it]
 17%|█▋        | 4887/28080 [9:40:11<45:33:50,  7.07s/it]
                                                         
{'loss': 0.6561, 'learning_rate': 0.00047329300764144337, 'epoch': 2.09}

 17%|█▋        | 4887/28080 [9:40:11<45:33:50,  7.07s/it]
 17%|█▋        | 4888/28080 [9:40:18<45:42:53,  7.10s/it]
                                                         
{'loss': 0.6344, 'learning_rate': 0.00047328003830139024, 'epoch': 2.09}

 17%|█▋        | 4888/28080 [9:40:18<45:42:53,  7.10s/it]
 17%|█▋        | 4889/28080 [9:40:25<45:32:47,  7.07s/it]
                                                         
{'loss': 0.6489, 'learning_rate': 0.00047326706599082644, 'epoch': 2.09}

 17%|█▋        | 4889/28080 [9:40:25<45:32:47,  7.07s/it]
 17%|█▋        | 4890/28080 [9:40:32<45:27:52,  7.06s/it]
                                                         
{'loss': 0.6467, 'learning_rate': 0.00047325409070992464, 'epoch': 2.09}

 17%|█▋        | 4890/28080 [9:40:32<45:27:52,  7.06s/it]
 17%|█▋        | 4891/28080 [9:40:39<45:42:02,  7.09s/it]
                                                         
{'loss': 0.6401, 'learning_rate': 0.0004732411124588576, 'epoch': 2.09}

 17%|█▋        | 4891/28080 [9:40:39<45:42:02,  7.09s/it]
 17%|█▋        | 4892/28080 [9:40:46<45:30:28,  7.07s/it]
                                                         
{'loss': 0.6699, 'learning_rate': 0.0004732281312377977, 'epoch': 2.09}

 17%|█▋        | 4892/28080 [9:40:46<45:30:28,  7.07s/it]
 17%|█▋        | 4893/28080 [9:40:53<45:37:13,  7.08s/it]
                                                         
{'loss': 0.6451, 'learning_rate': 0.0004732151470469179, 'epoch': 2.09}

 17%|█▋        | 4893/28080 [9:40:53<45:37:13,  7.08s/it]
 17%|█▋        | 4894/28080 [9:41:01<45:44:26,  7.10s/it]
                                                         
{'loss': 0.6359, 'learning_rate': 0.00047320215988639095, 'epoch': 2.09}

 17%|█▋        | 4894/28080 [9:41:01<45:44:26,  7.10s/it]
 17%|█▋        | 4895/28080 [9:41:08<45:38:14,  7.09s/it]
                                                         
{'loss': 0.6511, 'learning_rate': 0.0004731891697563894, 'epoch': 2.09}

 17%|█▋        | 4895/28080 [9:41:08<45:38:14,  7.09s/it]
 17%|█▋        | 4896/28080 [9:41:15<45:40:09,  7.09s/it]
                                                         
{'loss': 0.6341, 'learning_rate': 0.0004731761766570862, 'epoch': 2.09}

 17%|█▋        | 4896/28080 [9:41:15<45:40:09,  7.09s/it]
 17%|█▋        | 4897/28080 [9:41:22<45:49:34,  7.12s/it]
                                                         
{'loss': 0.649, 'learning_rate': 0.00047316318058865424, 'epoch': 2.09}

 17%|█▋        | 4897/28080 [9:41:22<45:49:34,  7.12s/it]
 17%|█▋        | 4898/28080 [9:41:29<45:37:04,  7.08s/it]
                                                         
{'loss': 0.6562, 'learning_rate': 0.00047315018155126635, 'epoch': 2.09}

 17%|█▋        | 4898/28080 [9:41:29<45:37:04,  7.08s/it]
 17%|█▋        | 4899/28080 [9:41:36<45:26:27,  7.06s/it]
                                                         
{'loss': 0.6597, 'learning_rate': 0.0004731371795450955, 'epoch': 2.09}

 17%|█▋        | 4899/28080 [9:41:36<45:26:27,  7.06s/it]
 17%|█▋        | 4900/28080 [9:41:43<45:28:16,  7.06s/it]
                                                         
{'loss': 0.6475, 'learning_rate': 0.00047312417457031475, 'epoch': 2.09}

 17%|█▋        | 4900/28080 [9:41:43<45:28:16,  7.06s/it]
 17%|█▋        | 4901/28080 [9:41:50<45:40:46,  7.09s/it]
                                                         
{'loss': 0.6426, 'learning_rate': 0.000473111166627097, 'epoch': 2.09}

 17%|█▋        | 4901/28080 [9:41:50<45:40:46,  7.09s/it]
 17%|█▋        | 4902/28080 [9:41:57<45:42:39,  7.10s/it]
                                                         
{'loss': 0.6429, 'learning_rate': 0.00047309815571561535, 'epoch': 2.09}

 17%|█▋        | 4902/28080 [9:41:57<45:42:39,  7.10s/it]
 17%|█▋        | 4903/28080 [9:42:04<45:32:29,  7.07s/it]
                                                         
{'loss': 0.6444, 'learning_rate': 0.0004730851418360429, 'epoch': 2.09}

 17%|█▋        | 4903/28080 [9:42:04<45:32:29,  7.07s/it]
 17%|█▋        | 4904/28080 [9:42:11<45:34:44,  7.08s/it]
                                                         
{'loss': 0.6272, 'learning_rate': 0.00047307212498855276, 'epoch': 2.09}

 17%|█▋        | 4904/28080 [9:42:11<45:34:44,  7.08s/it]
 17%|█▋        | 4905/28080 [9:42:18<45:43:20,  7.10s/it]
                                                         
{'loss': 0.656, 'learning_rate': 0.0004730591051733182, 'epoch': 2.1}

 17%|█▋        | 4905/28080 [9:42:18<45:43:20,  7.10s/it]
 17%|█▋        | 4906/28080 [9:42:26<45:48:00,  7.11s/it]
                                                         
{'loss': 0.6265, 'learning_rate': 0.0004730460823905123, 'epoch': 2.1}

 17%|█▋        | 4906/28080 [9:42:26<45:48:00,  7.11s/it]
 17%|█▋        | 4907/28080 [9:42:33<45:54:35,  7.13s/it]
                                                         
{'loss': 0.6412, 'learning_rate': 0.00047303305664030837, 'epoch': 2.1}

 17%|█▋        | 4907/28080 [9:42:33<45:54:35,  7.13s/it]
 17%|█▋        | 4908/28080 [9:42:40<45:49:31,  7.12s/it]
                                                         
{'loss': 0.6431, 'learning_rate': 0.00047302002792287966, 'epoch': 2.1}

 17%|█▋        | 4908/28080 [9:42:40<45:49:31,  7.12s/it]
 17%|█▋        | 4909/28080 [9:42:47<45:58:52,  7.14s/it]
                                                         
{'loss': 0.634, 'learning_rate': 0.0004730069962383997, 'epoch': 2.1}

 17%|█▋        | 4909/28080 [9:42:47<45:58:52,  7.14s/it]
 17%|█▋        | 4910/28080 [9:42:54<45:49:07,  7.12s/it]
                                                         
{'loss': 0.6624, 'learning_rate': 0.0004729939615870416, 'epoch': 2.1}

 17%|█▋        | 4910/28080 [9:42:54<45:49:07,  7.12s/it]
 17%|█▋        | 4911/28080 [9:43:01<45:41:58,  7.10s/it]
                                                         
{'loss': 0.6662, 'learning_rate': 0.000472980923968979, 'epoch': 2.1}

 17%|█▋        | 4911/28080 [9:43:01<45:41:58,  7.10s/it]
 17%|█▋        | 4912/28080 [9:43:08<45:41:40,  7.10s/it]
                                                         
{'loss': 0.6849, 'learning_rate': 0.00047296788338438515, 'epoch': 2.1}

 17%|█▋        | 4912/28080 [9:43:08<45:41:40,  7.10s/it]
 17%|█▋        | 4913/28080 [9:43:15<45:50:42,  7.12s/it]
                                                         
{'loss': 0.6441, 'learning_rate': 0.00047295483983343363, 'epoch': 2.1}

 17%|█▋        | 4913/28080 [9:43:15<45:50:42,  7.12s/it]
 18%|█▊        | 4914/28080 [9:43:23<45:37:47,  7.09s/it]
                                                         
{'loss': 0.6346, 'learning_rate': 0.000472941793316298, 'epoch': 2.1}

 18%|█▊        | 4914/28080 [9:43:23<45:37:47,  7.09s/it]
 18%|█▊        | 4915/28080 [9:43:30<45:36:20,  7.09s/it]
                                                         
{'loss': 0.6649, 'learning_rate': 0.0004729287438331518, 'epoch': 2.1}

 18%|█▊        | 4915/28080 [9:43:30<45:36:20,  7.09s/it]
 18%|█▊        | 4916/28080 [9:43:37<45:43:13,  7.11s/it]
                                                         
{'loss': 0.6423, 'learning_rate': 0.0004729156913841687, 'epoch': 2.1}

 18%|█▊        | 4916/28080 [9:43:37<45:43:13,  7.11s/it]
 18%|█▊        | 4917/28080 [9:43:44<45:51:00,  7.13s/it]
                                                         
{'loss': 0.6322, 'learning_rate': 0.0004729026359695222, 'epoch': 2.1}

 18%|█▊        | 4917/28080 [9:43:44<45:51:00,  7.13s/it]
 18%|█▊        | 4918/28080 [9:43:51<45:45:48,  7.11s/it]
                                                         
{'loss': 0.6381, 'learning_rate': 0.00047288957758938614, 'epoch': 2.1}

 18%|█▊        | 4918/28080 [9:43:51<45:45:48,  7.11s/it]
 18%|█▊        | 4919/28080 [9:43:58<45:46:57,  7.12s/it]
                                                         
{'loss': 0.648, 'learning_rate': 0.0004728765162439342, 'epoch': 2.1}

 18%|█▊        | 4919/28080 [9:43:58<45:46:57,  7.12s/it]
 18%|█▊        | 4920/28080 [9:44:05<45:46:49,  7.12s/it]
                                                         
{'loss': 0.6506, 'learning_rate': 0.0004728634519333401, 'epoch': 2.1}

 18%|█▊        | 4920/28080 [9:44:05<45:46:49,  7.12s/it]
 18%|█▊        | 4921/28080 [9:44:12<45:49:19,  7.12s/it]
                                                         
{'loss': 0.6517, 'learning_rate': 0.0004728503846577777, 'epoch': 2.1}

 18%|█▊        | 4921/28080 [9:44:12<45:49:19,  7.12s/it]
 18%|█▊        | 4922/28080 [9:44:19<45:43:17,  7.11s/it]
                                                         
{'loss': 0.6625, 'learning_rate': 0.00047283731441742096, 'epoch': 2.1}

 18%|█▊        | 4922/28080 [9:44:19<45:43:17,  7.11s/it]
 18%|█▊        | 4923/28080 [9:44:27<45:47:15,  7.12s/it]
                                                         
{'loss': 0.6308, 'learning_rate': 0.0004728242412124435, 'epoch': 2.1}

 18%|█▊        | 4923/28080 [9:44:27<45:47:15,  7.12s/it]
 18%|█▊        | 4924/28080 [9:44:34<45:50:04,  7.13s/it]
                                                         
{'loss': 0.6505, 'learning_rate': 0.0004728111650430194, 'epoch': 2.1}

 18%|█▊        | 4924/28080 [9:44:34<45:50:04,  7.13s/it]
 18%|█▊        | 4925/28080 [9:44:41<46:12:29,  7.18s/it]
                                                         
{'loss': 0.6235, 'learning_rate': 0.0004727980859093226, 'epoch': 2.1}

 18%|█▊        | 4925/28080 [9:44:41<46:12:29,  7.18s/it]
 18%|█▊        | 4926/28080 [9:44:48<46:09:57,  7.18s/it]
                                                         
{'loss': 0.6322, 'learning_rate': 0.0004727850038115272, 'epoch': 2.1}

 18%|█▊        | 4926/28080 [9:44:48<46:09:57,  7.18s/it]
 18%|█▊        | 4927/28080 [9:44:55<46:04:18,  7.16s/it]
                                                         
{'loss': 0.6344, 'learning_rate': 0.00047277191874980706, 'epoch': 2.1}

 18%|█▊        | 4927/28080 [9:44:55<46:04:18,  7.16s/it]
 18%|█▊        | 4928/28080 [9:45:02<45:47:29,  7.12s/it]
                                                         
{'loss': 0.6592, 'learning_rate': 0.0004727588307243365, 'epoch': 2.11}

 18%|█▊        | 4928/28080 [9:45:02<45:47:29,  7.12s/it]
 18%|█▊        | 4929/28080 [9:45:09<45:47:07,  7.12s/it]
                                                         
{'loss': 0.6344, 'learning_rate': 0.00047274573973528935, 'epoch': 2.11}

 18%|█▊        | 4929/28080 [9:45:09<45:47:07,  7.12s/it]
 18%|█▊        | 4930/28080 [9:45:16<45:32:59,  7.08s/it]
                                                         
{'loss': 0.662, 'learning_rate': 0.00047273264578284, 'epoch': 2.11}

 18%|█▊        | 4930/28080 [9:45:16<45:32:59,  7.08s/it]
 18%|█▊        | 4931/28080 [9:45:24<45:32:03,  7.08s/it]
                                                         
{'loss': 0.6504, 'learning_rate': 0.0004727195488671625, 'epoch': 2.11}

 18%|█▊        | 4931/28080 [9:45:24<45:32:03,  7.08s/it]
 18%|█▊        | 4932/28080 [9:45:31<45:38:13,  7.10s/it]
                                                         
{'loss': 0.6244, 'learning_rate': 0.00047270644898843127, 'epoch': 2.11}

 18%|█▊        | 4932/28080 [9:45:31<45:38:13,  7.10s/it]
 18%|█▊        | 4933/28080 [9:45:38<45:39:40,  7.10s/it]
                                                         
{'loss': 0.6523, 'learning_rate': 0.00047269334614682046, 'epoch': 2.11}

 18%|█▊        | 4933/28080 [9:45:38<45:39:40,  7.10s/it]
 18%|█▊        | 4934/28080 [9:45:45<45:34:25,  7.09s/it]
                                                         
{'loss': 0.6428, 'learning_rate': 0.0004726802403425045, 'epoch': 2.11}

 18%|█▊        | 4934/28080 [9:45:45<45:34:25,  7.09s/it]
 18%|█▊        | 4935/28080 [9:45:52<45:22:24,  7.06s/it]
                                                         
{'loss': 0.6461, 'learning_rate': 0.0004726671315756575, 'epoch': 2.11}

 18%|█▊        | 4935/28080 [9:45:52<45:22:24,  7.06s/it]
 18%|█▊        | 4936/28080 [9:45:59<45:19:20,  7.05s/it]
                                                         
{'loss': 0.6426, 'learning_rate': 0.00047265401984645405, 'epoch': 2.11}

 18%|█▊        | 4936/28080 [9:45:59<45:19:20,  7.05s/it]
 18%|█▊        | 4937/28080 [9:46:06<45:31:08,  7.08s/it]
                                                         
{'loss': 0.6282, 'learning_rate': 0.00047264090515506866, 'epoch': 2.11}

 18%|█▊        | 4937/28080 [9:46:06<45:31:08,  7.08s/it]
 18%|█▊        | 4938/28080 [9:46:13<45:29:11,  7.08s/it]
                                                         
{'loss': 0.6482, 'learning_rate': 0.00047262778750167567, 'epoch': 2.11}

 18%|█▊        | 4938/28080 [9:46:13<45:29:11,  7.08s/it]
 18%|█▊        | 4939/28080 [9:46:20<45:39:39,  7.10s/it]
                                                         
{'loss': 0.6317, 'learning_rate': 0.00047261466688644965, 'epoch': 2.11}

 18%|█▊        | 4939/28080 [9:46:20<45:39:39,  7.10s/it]
 18%|█▊        | 4940/28080 [9:46:27<45:32:27,  7.09s/it]
                                                         
{'loss': 0.6456, 'learning_rate': 0.00047260154330956515, 'epoch': 2.11}

 18%|█▊        | 4940/28080 [9:46:27<45:32:27,  7.09s/it]
 18%|█▊        | 4941/28080 [9:46:34<45:31:02,  7.08s/it]
                                                         
{'loss': 0.6426, 'learning_rate': 0.0004725884167711968, 'epoch': 2.11}

 18%|█▊        | 4941/28080 [9:46:34<45:31:02,  7.08s/it]
 18%|█▊        | 4942/28080 [9:46:41<45:20:56,  7.06s/it]
                                                         
{'loss': 0.6548, 'learning_rate': 0.0004725752872715191, 'epoch': 2.11}

 18%|█▊        | 4942/28080 [9:46:41<45:20:56,  7.06s/it]
 18%|█▊        | 4943/28080 [9:46:48<45:25:08,  7.07s/it]
                                                         
{'loss': 0.6544, 'learning_rate': 0.00047256215481070684, 'epoch': 2.11}

 18%|█▊        | 4943/28080 [9:46:48<45:25:08,  7.07s/it]
 18%|█▊        | 4944/28080 [9:46:56<45:26:15,  7.07s/it]
                                                         
{'loss': 0.6468, 'learning_rate': 0.0004725490193889348, 'epoch': 2.11}

 18%|█▊        | 4944/28080 [9:46:56<45:26:15,  7.07s/it]
 18%|█▊        | 4945/28080 [9:47:03<45:36:22,  7.10s/it]
                                                         
{'loss': 0.6517, 'learning_rate': 0.00047253588100637755, 'epoch': 2.11}

 18%|█▊        | 4945/28080 [9:47:03<45:36:22,  7.10s/it]
 18%|█▊        | 4946/28080 [9:47:10<45:36:19,  7.10s/it]
                                                         
{'loss': 0.6497, 'learning_rate': 0.00047252273966321003, 'epoch': 2.11}

 18%|█▊        | 4946/28080 [9:47:10<45:36:19,  7.10s/it]
 18%|█▊        | 4947/28080 [9:47:17<45:36:48,  7.10s/it]
                                                         
{'loss': 0.6503, 'learning_rate': 0.000472509595359607, 'epoch': 2.11}

 18%|█▊        | 4947/28080 [9:47:17<45:36:48,  7.10s/it]
 18%|█▊        | 4948/28080 [9:47:24<45:39:34,  7.11s/it]
                                                         
{'loss': 0.6454, 'learning_rate': 0.00047249644809574344, 'epoch': 2.11}

 18%|█▊        | 4948/28080 [9:47:24<45:39:34,  7.11s/it]
 18%|█▊        | 4949/28080 [9:47:31<45:39:48,  7.11s/it]
                                                         
{'loss': 0.6268, 'learning_rate': 0.0004724832978717941, 'epoch': 2.11}

 18%|█▊        | 4949/28080 [9:47:31<45:39:48,  7.11s/it]
 18%|█▊        | 4950/28080 [9:47:38<45:28:20,  7.08s/it]
                                                         
{'loss': 0.6478, 'learning_rate': 0.000472470144687934, 'epoch': 2.11}

 18%|█▊        | 4950/28080 [9:47:38<45:28:20,  7.08s/it]
 18%|█▊        | 4951/28080 [9:47:45<45:36:56,  7.10s/it]
                                                         
{'loss': 0.6547, 'learning_rate': 0.0004724569885443382, 'epoch': 2.12}

 18%|█▊        | 4951/28080 [9:47:45<45:36:56,  7.10s/it]
 18%|█▊        | 4952/28080 [9:47:52<45:39:17,  7.11s/it]
                                                         
{'loss': 0.6446, 'learning_rate': 0.0004724438294411816, 'epoch': 2.12}

 18%|█▊        | 4952/28080 [9:47:52<45:39:17,  7.11s/it]
 18%|█▊        | 4953/28080 [9:48:00<45:46:20,  7.13s/it]
                                                         
{'loss': 0.6452, 'learning_rate': 0.00047243066737863925, 'epoch': 2.12}

 18%|█▊        | 4953/28080 [9:48:00<45:46:20,  7.13s/it]
 18%|█▊        | 4954/28080 [9:48:07<45:37:19,  7.10s/it]
                                                         
{'loss': 0.65, 'learning_rate': 0.0004724175023568865, 'epoch': 2.12}

 18%|█▊        | 4954/28080 [9:48:07<45:37:19,  7.10s/it]
 18%|█▊        | 4955/28080 [9:48:14<45:36:58,  7.10s/it]
                                                         
{'loss': 0.6438, 'learning_rate': 0.0004724043343760982, 'epoch': 2.12}

 18%|█▊        | 4955/28080 [9:48:14<45:36:58,  7.10s/it]
 18%|█▊        | 4956/28080 [9:48:21<45:37:48,  7.10s/it]
                                                         
{'loss': 0.6577, 'learning_rate': 0.00047239116343644977, 'epoch': 2.12}

 18%|█▊        | 4956/28080 [9:48:21<45:37:48,  7.10s/it]
 18%|█▊        | 4957/28080 [9:48:28<45:25:42,  7.07s/it]
                                                         
{'loss': 0.6505, 'learning_rate': 0.00047237798953811633, 'epoch': 2.12}

 18%|█▊        | 4957/28080 [9:48:28<45:25:42,  7.07s/it]
 18%|█▊        | 4958/28080 [9:48:35<45:28:40,  7.08s/it]
                                                         
{'loss': 0.6474, 'learning_rate': 0.0004723648126812731, 'epoch': 2.12}

 18%|█▊        | 4958/28080 [9:48:35<45:28:40,  7.08s/it]
 18%|█▊        | 4959/28080 [9:48:42<45:32:44,  7.09s/it]
                                                         
{'loss': 0.6709, 'learning_rate': 0.0004723516328660955, 'epoch': 2.12}

 18%|█▊        | 4959/28080 [9:48:42<45:32:44,  7.09s/it]
 18%|█▊        | 4960/28080 [9:48:49<45:37:23,  7.10s/it]
                                                         
{'loss': 0.6572, 'learning_rate': 0.0004723384500927588, 'epoch': 2.12}

 18%|█▊        | 4960/28080 [9:48:49<45:37:23,  7.10s/it]
 18%|█▊        | 4961/28080 [9:48:56<45:40:45,  7.11s/it]
                                                         
{'loss': 0.6303, 'learning_rate': 0.00047232526436143834, 'epoch': 2.12}

 18%|█▊        | 4961/28080 [9:48:56<45:40:45,  7.11s/it]
 18%|█▊        | 4962/28080 [9:49:03<45:35:09,  7.10s/it]
                                                         
{'loss': 0.6248, 'learning_rate': 0.0004723120756723097, 'epoch': 2.12}

 18%|█▊        | 4962/28080 [9:49:03<45:35:09,  7.10s/it]
 18%|█▊        | 4963/28080 [9:49:10<45:24:52,  7.07s/it]
                                                         
{'loss': 0.6341, 'learning_rate': 0.0004722988840255481, 'epoch': 2.12}

 18%|█▊        | 4963/28080 [9:49:10<45:24:52,  7.07s/it]
 18%|█▊        | 4964/28080 [9:49:18<45:31:52,  7.09s/it]
                                                         
{'loss': 0.6302, 'learning_rate': 0.00047228568942132935, 'epoch': 2.12}

 18%|█▊        | 4964/28080 [9:49:18<45:31:52,  7.09s/it]
 18%|█▊        | 4965/28080 [9:49:25<45:34:06,  7.10s/it]
                                                         
{'loss': 0.67, 'learning_rate': 0.00047227249185982867, 'epoch': 2.12}

 18%|█▊        | 4965/28080 [9:49:25<45:34:06,  7.10s/it]
 18%|█▊        | 4966/28080 [9:49:32<45:38:45,  7.11s/it]
                                                         
{'loss': 0.6511, 'learning_rate': 0.0004722592913412218, 'epoch': 2.12}

 18%|█▊        | 4966/28080 [9:49:32<45:38:45,  7.11s/it]
 18%|█▊        | 4967/28080 [9:49:39<45:30:00,  7.09s/it]
                                                         
{'loss': 0.6354, 'learning_rate': 0.00047224608786568446, 'epoch': 2.12}

 18%|█▊        | 4967/28080 [9:49:39<45:30:00,  7.09s/it]
 18%|█▊        | 4968/28080 [9:49:46<45:26:44,  7.08s/it]
                                                         
{'loss': 0.6646, 'learning_rate': 0.00047223288143339215, 'epoch': 2.12}

 18%|█▊        | 4968/28080 [9:49:46<45:26:44,  7.08s/it]
 18%|█▊        | 4969/28080 [9:49:53<45:13:41,  7.05s/it]
                                                         
{'loss': 0.6428, 'learning_rate': 0.0004722196720445206, 'epoch': 2.12}

 18%|█▊        | 4969/28080 [9:49:53<45:13:41,  7.05s/it]
 18%|█▊        | 4970/28080 [9:50:00<45:18:37,  7.06s/it]
                                                         
{'loss': 0.6452, 'learning_rate': 0.0004722064596992456, 'epoch': 2.12}

 18%|█▊        | 4970/28080 [9:50:00<45:18:37,  7.06s/it]
 18%|█▊        | 4971/28080 [9:50:07<45:22:53,  7.07s/it]
                                                         
{'loss': 0.6566, 'learning_rate': 0.0004721932443977428, 'epoch': 2.12}

 18%|█▊        | 4971/28080 [9:50:07<45:22:53,  7.07s/it]
 18%|█▊        | 4972/28080 [9:50:14<45:22:03,  7.07s/it]
                                                         
{'loss': 0.6493, 'learning_rate': 0.00047218002614018815, 'epoch': 2.12}

 18%|█▊        | 4972/28080 [9:50:14<45:22:03,  7.07s/it]
 18%|█▊        | 4973/28080 [9:50:21<45:31:01,  7.09s/it]
                                                         
{'loss': 0.6572, 'learning_rate': 0.00047216680492675756, 'epoch': 2.12}

 18%|█▊        | 4973/28080 [9:50:21<45:31:01,  7.09s/it]
 18%|█▊        | 4974/28080 [9:50:28<45:37:26,  7.11s/it]
                                                         
{'loss': 0.6463, 'learning_rate': 0.0004721535807576267, 'epoch': 2.12}

 18%|█▊        | 4974/28080 [9:50:28<45:37:26,  7.11s/it]
 18%|█▊        | 4975/28080 [9:50:36<45:40:20,  7.12s/it]
                                                         
{'loss': 0.6126, 'learning_rate': 0.0004721403536329717, 'epoch': 2.13}

 18%|█▊        | 4975/28080 [9:50:36<45:40:20,  7.12s/it]
 18%|█▊        | 4976/28080 [9:50:43<45:49:55,  7.14s/it]
                                                         
{'loss': 0.6472, 'learning_rate': 0.0004721271235529685, 'epoch': 2.13}

 18%|█▊        | 4976/28080 [9:50:43<45:49:55,  7.14s/it]
 18%|█▊        | 4977/28080 [9:50:50<45:46:17,  7.13s/it]
                                                         
{'loss': 0.6581, 'learning_rate': 0.00047211389051779294, 'epoch': 2.13}

 18%|█▊        | 4977/28080 [9:50:50<45:46:17,  7.13s/it]
 18%|█▊        | 4978/28080 [9:50:57<45:47:48,  7.14s/it]
                                                         
{'loss': 0.6422, 'learning_rate': 0.0004721006545276213, 'epoch': 2.13}

 18%|█▊        | 4978/28080 [9:50:57<45:47:48,  7.14s/it]
 18%|█▊        | 4979/28080 [9:51:04<45:36:35,  7.11s/it]
                                                         
{'loss': 0.64, 'learning_rate': 0.00047208741558262956, 'epoch': 2.13}

 18%|█▊        | 4979/28080 [9:51:04<45:36:35,  7.11s/it]
 18%|█▊        | 4980/28080 [9:51:11<45:33:57,  7.10s/it]
                                                         
{'loss': 0.6496, 'learning_rate': 0.00047207417368299394, 'epoch': 2.13}

 18%|█▊        | 4980/28080 [9:51:11<45:33:57,  7.10s/it]
 18%|█▊        | 4981/28080 [9:51:18<45:07:59,  7.03s/it]
                                                         
{'loss': 0.6466, 'learning_rate': 0.0004720609288288905, 'epoch': 2.13}

 18%|█▊        | 4981/28080 [9:51:18<45:07:59,  7.03s/it]
 18%|█▊        | 4982/28080 [9:51:25<45:09:03,  7.04s/it]
                                                         
{'loss': 0.6693, 'learning_rate': 0.00047204768102049544, 'epoch': 2.13}

 18%|█▊        | 4982/28080 [9:51:25<45:09:03,  7.04s/it]
 18%|█▊        | 4983/28080 [9:51:32<45:18:31,  7.06s/it]
                                                         
{'loss': 0.6458, 'learning_rate': 0.0004720344302579851, 'epoch': 2.13}

 18%|█▊        | 4983/28080 [9:51:32<45:18:31,  7.06s/it]
 18%|█▊        | 4984/28080 [9:51:39<45:20:49,  7.07s/it]
                                                         
{'loss': 0.6434, 'learning_rate': 0.00047202117654153577, 'epoch': 2.13}

 18%|█▊        | 4984/28080 [9:51:39<45:20:49,  7.07s/it]
 18%|█▊        | 4985/28080 [9:51:46<45:14:22,  7.05s/it]
                                                         
{'loss': 0.6483, 'learning_rate': 0.0004720079198713236, 'epoch': 2.13}

 18%|█▊        | 4985/28080 [9:51:46<45:14:22,  7.05s/it]
 18%|█▊        | 4986/28080 [9:51:53<45:20:29,  7.07s/it]
                                                         
{'loss': 0.6409, 'learning_rate': 0.0004719946602475252, 'epoch': 2.13}

 18%|█▊        | 4986/28080 [9:51:53<45:20:29,  7.07s/it]
 18%|█▊        | 4987/28080 [9:52:00<45:23:25,  7.08s/it]
                                                         
{'loss': 0.6449, 'learning_rate': 0.0004719813976703168, 'epoch': 2.13}

 18%|█▊        | 4987/28080 [9:52:00<45:23:25,  7.08s/it]
 18%|█▊        | 4988/28080 [9:52:08<45:24:36,  7.08s/it]
                                                         
{'loss': 0.6448, 'learning_rate': 0.000471968132139875, 'epoch': 2.13}

 18%|█▊        | 4988/28080 [9:52:08<45:24:36,  7.08s/it]
 18%|█▊        | 4989/28080 [9:52:15<45:30:30,  7.09s/it]
                                                         
{'loss': 0.6366, 'learning_rate': 0.0004719548636563761, 'epoch': 2.13}

 18%|█▊        | 4989/28080 [9:52:15<45:30:30,  7.09s/it]
 18%|█▊        | 4990/28080 [9:52:22<45:23:25,  7.08s/it]
                                                         
{'loss': 0.6531, 'learning_rate': 0.00047194159221999676, 'epoch': 2.13}

 18%|█▊        | 4990/28080 [9:52:22<45:23:25,  7.08s/it]
 18%|█▊        | 4991/28080 [9:52:29<45:26:10,  7.08s/it]
                                                         
{'loss': 0.64, 'learning_rate': 0.0004719283178309135, 'epoch': 2.13}

 18%|█▊        | 4991/28080 [9:52:29<45:26:10,  7.08s/it]
 18%|█▊        | 4992/28080 [9:52:36<45:33:21,  7.10s/it]
                                                         
{'loss': 0.6234, 'learning_rate': 0.0004719150404893029, 'epoch': 2.13}

 18%|█▊        | 4992/28080 [9:52:36<45:33:21,  7.10s/it]
 18%|█▊        | 4993/28080 [9:52:43<45:32:06,  7.10s/it]
                                                         
{'loss': 0.6643, 'learning_rate': 0.0004719017601953416, 'epoch': 2.13}

 18%|█▊        | 4993/28080 [9:52:43<45:32:06,  7.10s/it]
 18%|█▊        | 4994/28080 [9:52:50<45:31:32,  7.10s/it]
                                                         
{'loss': 0.6511, 'learning_rate': 0.00047188847694920637, 'epoch': 2.13}

 18%|█▊        | 4994/28080 [9:52:50<45:31:32,  7.10s/it]
 18%|█▊        | 4995/28080 [9:52:57<45:29:49,  7.10s/it]
                                                         
{'loss': 0.6462, 'learning_rate': 0.00047187519075107386, 'epoch': 2.13}

 18%|█▊        | 4995/28080 [9:52:57<45:29:49,  7.10s/it]
 18%|█▊        | 4996/28080 [9:53:04<45:25:11,  7.08s/it]
                                                         
{'loss': 0.6484, 'learning_rate': 0.0004718619016011208, 'epoch': 2.13}

 18%|█▊        | 4996/28080 [9:53:04<45:25:11,  7.08s/it]
 18%|█▊        | 4997/28080 [9:53:11<45:33:03,  7.10s/it]
                                                         
{'loss': 0.647, 'learning_rate': 0.000471848609499524, 'epoch': 2.13}

 18%|█▊        | 4997/28080 [9:53:11<45:33:03,  7.10s/it]
 18%|█▊        | 4998/28080 [9:53:19<45:32:05,  7.10s/it]
                                                         
{'loss': 0.6114, 'learning_rate': 0.0004718353144464604, 'epoch': 2.14}

 18%|█▊        | 4998/28080 [9:53:19<45:32:05,  7.10s/it]
 18%|█▊        | 4999/28080 [9:53:26<45:26:11,  7.09s/it]
                                                         
{'loss': 0.6427, 'learning_rate': 0.0004718220164421068, 'epoch': 2.14}

 18%|█▊        | 4999/28080 [9:53:26<45:26:11,  7.09s/it]
 18%|█▊        | 5000/28080 [9:53:33<45:41:50,  7.13s/it]
                                                         
{'loss': 0.6624, 'learning_rate': 0.0004718087154866399, 'epoch': 2.14}

 18%|█▊        | 5000/28080 [9:53:33<45:41:50,  7.13s/it]
 18%|█▊        | 5001/28080 [9:53:40<45:39:48,  7.12s/it]
                                                         
{'loss': 0.6646, 'learning_rate': 0.0004717954115802371, 'epoch': 2.14}

 18%|█▊        | 5001/28080 [9:53:40<45:39:48,  7.12s/it]
 18%|█▊        | 5002/28080 [9:53:47<45:35:31,  7.11s/it]
                                                         
{'loss': 0.6574, 'learning_rate': 0.00047178210472307506, 'epoch': 2.14}

 18%|█▊        | 5002/28080 [9:53:47<45:35:31,  7.11s/it]
 18%|█▊        | 5003/28080 [9:53:54<45:35:03,  7.11s/it]
                                                         
{'loss': 0.6396, 'learning_rate': 0.000471768794915331, 'epoch': 2.14}

 18%|█▊        | 5003/28080 [9:53:54<45:35:03,  7.11s/it]
 18%|█▊        | 5004/28080 [9:54:01<45:37:07,  7.12s/it]
                                                         
{'loss': 0.6297, 'learning_rate': 0.00047175548215718183, 'epoch': 2.14}

 18%|█▊        | 5004/28080 [9:54:01<45:37:07,  7.12s/it]
 18%|█▊        | 5005/28080 [9:54:08<45:35:19,  7.11s/it]
                                                         
{'loss': 0.6715, 'learning_rate': 0.00047174216644880476, 'epoch': 2.14}

 18%|█▊        | 5005/28080 [9:54:08<45:35:19,  7.11s/it]
 18%|█▊        | 5006/28080 [9:54:15<45:39:23,  7.12s/it]
                                                         
{'loss': 0.6425, 'learning_rate': 0.00047172884779037694, 'epoch': 2.14}

 18%|█▊        | 5006/28080 [9:54:15<45:39:23,  7.12s/it]
 18%|█▊        | 5007/28080 [9:54:23<45:41:25,  7.13s/it]
                                                         
{'loss': 0.6361, 'learning_rate': 0.0004717155261820756, 'epoch': 2.14}

 18%|█▊        | 5007/28080 [9:54:23<45:41:25,  7.13s/it]
 18%|█▊        | 5008/28080 [9:54:30<45:34:25,  7.11s/it]
                                                         
{'loss': 0.6491, 'learning_rate': 0.00047170220162407784, 'epoch': 2.14}

 18%|█▊        | 5008/28080 [9:54:30<45:34:25,  7.11s/it]
 18%|█▊        | 5009/28080 [9:54:37<45:27:10,  7.09s/it]
                                                         
{'loss': 0.6745, 'learning_rate': 0.000471688874116561, 'epoch': 2.14}

 18%|█▊        | 5009/28080 [9:54:37<45:27:10,  7.09s/it]
 18%|█▊        | 5010/28080 [9:54:44<45:25:49,  7.09s/it]
                                                         
{'loss': 0.6567, 'learning_rate': 0.0004716755436597024, 'epoch': 2.14}

 18%|█▊        | 5010/28080 [9:54:44<45:25:49,  7.09s/it]
 18%|█▊        | 5011/28080 [9:54:51<45:29:36,  7.10s/it]
                                                         
{'loss': 0.6538, 'learning_rate': 0.0004716622102536794, 'epoch': 2.14}

 18%|█▊        | 5011/28080 [9:54:51<45:29:36,  7.10s/it]
 18%|█▊        | 5012/28080 [9:54:58<45:39:42,  7.13s/it]
                                                         
{'loss': 0.6482, 'learning_rate': 0.0004716488738986693, 'epoch': 2.14}

 18%|█▊        | 5012/28080 [9:54:58<45:39:42,  7.13s/it]
 18%|█▊        | 5013/28080 [9:55:05<45:40:27,  7.13s/it]
                                                         
{'loss': 0.6148, 'learning_rate': 0.0004716355345948497, 'epoch': 2.14}

 18%|█▊        | 5013/28080 [9:55:05<45:40:27,  7.13s/it]
 18%|█▊        | 5014/28080 [9:55:12<45:33:41,  7.11s/it]
                                                         
{'loss': 0.6545, 'learning_rate': 0.0004716221923423979, 'epoch': 2.14}

 18%|█▊        | 5014/28080 [9:55:12<45:33:41,  7.11s/it]
 18%|█▊        | 5015/28080 [9:55:19<45:37:35,  7.12s/it]
                                                         
{'loss': 0.6412, 'learning_rate': 0.0004716088471414915, 'epoch': 2.14}

 18%|█▊        | 5015/28080 [9:55:19<45:37:35,  7.12s/it]
 18%|█▊        | 5016/28080 [9:55:27<45:41:02,  7.13s/it]
                                                         
{'loss': 0.6399, 'learning_rate': 0.000471595498992308, 'epoch': 2.14}

 18%|█▊        | 5016/28080 [9:55:27<45:41:02,  7.13s/it]
 18%|█▊        | 5017/28080 [9:55:34<45:37:58,  7.12s/it]
                                                         
{'loss': 0.6355, 'learning_rate': 0.00047158214789502496, 'epoch': 2.14}

 18%|█▊        | 5017/28080 [9:55:34<45:37:58,  7.12s/it]
 18%|█▊        | 5018/28080 [9:55:41<45:28:59,  7.10s/it]
                                                         
{'loss': 0.6527, 'learning_rate': 0.0004715687938498201, 'epoch': 2.14}

 18%|█▊        | 5018/28080 [9:55:41<45:28:59,  7.10s/it]
 18%|█▊        | 5019/28080 [9:55:48<45:20:44,  7.08s/it]
                                                         
{'loss': 0.6298, 'learning_rate': 0.00047155543685687096, 'epoch': 2.14}

 18%|█▊        | 5019/28080 [9:55:48<45:20:44,  7.08s/it]
 18%|█▊        | 5020/28080 [9:55:55<45:28:42,  7.10s/it]
                                                         
{'loss': 0.6466, 'learning_rate': 0.0004715420769163553, 'epoch': 2.14}

 18%|█▊        | 5020/28080 [9:55:55<45:28:42,  7.10s/it]
 18%|█▊        | 5021/28080 [9:56:02<45:14:07,  7.06s/it]
                                                         
{'loss': 0.6707, 'learning_rate': 0.00047152871402845087, 'epoch': 2.14}

 18%|█▊        | 5021/28080 [9:56:02<45:14:07,  7.06s/it]
 18%|█▊        | 5022/28080 [9:56:09<45:20:07,  7.08s/it]
                                                         
{'loss': 0.6587, 'learning_rate': 0.0004715153481933355, 'epoch': 2.15}

 18%|█▊        | 5022/28080 [9:56:09<45:20:07,  7.08s/it]
 18%|█▊        | 5023/28080 [9:56:16<45:21:17,  7.08s/it]
                                                         
{'loss': 0.6408, 'learning_rate': 0.0004715019794111869, 'epoch': 2.15}

 18%|█▊        | 5023/28080 [9:56:16<45:21:17,  7.08s/it]
 18%|█▊        | 5024/28080 [9:56:23<45:32:10,  7.11s/it]
                                                         
{'loss': 0.6097, 'learning_rate': 0.00047148860768218294, 'epoch': 2.15}

 18%|█▊        | 5024/28080 [9:56:23<45:32:10,  7.11s/it]
 18%|█▊        | 5025/28080 [9:56:30<45:23:55,  7.09s/it]
                                                         
{'loss': 0.6568, 'learning_rate': 0.0004714752330065015, 'epoch': 2.15}

 18%|█▊        | 5025/28080 [9:56:30<45:23:55,  7.09s/it]
 18%|█▊        | 5026/28080 [9:56:38<45:29:48,  7.10s/it]
                                                         
{'loss': 0.6408, 'learning_rate': 0.0004714618553843207, 'epoch': 2.15}

 18%|█▊        | 5026/28080 [9:56:38<45:29:48,  7.10s/it]
 18%|█▊        | 5027/28080 [9:56:45<45:32:25,  7.11s/it]
                                                         
{'loss': 0.6595, 'learning_rate': 0.0004714484748158183, 'epoch': 2.15}

 18%|█▊        | 5027/28080 [9:56:45<45:32:25,  7.11s/it]
 18%|█▊        | 5028/28080 [9:56:52<45:27:14,  7.10s/it]
                                                         
{'loss': 0.6554, 'learning_rate': 0.00047143509130117243, 'epoch': 2.15}

 18%|█▊        | 5028/28080 [9:56:52<45:27:14,  7.10s/it]
 18%|█▊        | 5029/28080 [9:56:59<45:23:30,  7.09s/it]
                                                         
{'loss': 0.6591, 'learning_rate': 0.0004714217048405611, 'epoch': 2.15}

 18%|█▊        | 5029/28080 [9:56:59<45:23:30,  7.09s/it]
 18%|█▊        | 5030/28080 [9:57:06<45:27:04,  7.10s/it]
                                                         
{'loss': 0.6673, 'learning_rate': 0.00047140831543416244, 'epoch': 2.15}

 18%|█▊        | 5030/28080 [9:57:06<45:27:04,  7.10s/it]
 18%|█▊        | 5031/28080 [9:57:13<45:37:30,  7.13s/it]
                                                         
{'loss': 0.6559, 'learning_rate': 0.0004713949230821546, 'epoch': 2.15}

 18%|█▊        | 5031/28080 [9:57:13<45:37:30,  7.13s/it]
 18%|█▊        | 5032/28080 [9:57:20<45:31:35,  7.11s/it]
                                                         
{'loss': 0.6644, 'learning_rate': 0.00047138152778471566, 'epoch': 2.15}

 18%|█▊        | 5032/28080 [9:57:20<45:31:35,  7.11s/it]
 18%|█▊        | 5033/28080 [9:57:27<45:31:35,  7.11s/it]
                                                         
{'loss': 0.6295, 'learning_rate': 0.00047136812954202387, 'epoch': 2.15}

 18%|█▊        | 5033/28080 [9:57:27<45:31:35,  7.11s/it]
 18%|█▊        | 5034/28080 [9:57:34<45:29:12,  7.11s/it]
                                                         
{'loss': 0.6506, 'learning_rate': 0.00047135472835425744, 'epoch': 2.15}

 18%|█▊        | 5034/28080 [9:57:34<45:29:12,  7.11s/it]
 18%|█▊        | 5035/28080 [9:57:41<45:28:01,  7.10s/it]
                                                         
{'loss': 0.6371, 'learning_rate': 0.0004713413242215948, 'epoch': 2.15}

 18%|█▊        | 5035/28080 [9:57:41<45:28:01,  7.10s/it]
 18%|█▊        | 5036/28080 [9:57:49<45:28:55,  7.11s/it]
                                                         
{'loss': 0.6657, 'learning_rate': 0.0004713279171442141, 'epoch': 2.15}

 18%|█▊        | 5036/28080 [9:57:49<45:28:55,  7.11s/it]
 18%|█▊        | 5037/28080 [9:57:56<45:30:52,  7.11s/it]
                                                         
{'loss': 0.6245, 'learning_rate': 0.00047131450712229383, 'epoch': 2.15}

 18%|█▊        | 5037/28080 [9:57:56<45:30:52,  7.11s/it]
 18%|█▊        | 5038/28080 [9:58:03<45:28:41,  7.11s/it]
                                                         
{'loss': 0.6409, 'learning_rate': 0.0004713010941560124, 'epoch': 2.15}

 18%|█▊        | 5038/28080 [9:58:03<45:28:41,  7.11s/it]
 18%|█▊        | 5039/28080 [9:58:10<45:20:21,  7.08s/it]
                                                         
{'loss': 0.6505, 'learning_rate': 0.0004712876782455482, 'epoch': 2.15}

 18%|█▊        | 5039/28080 [9:58:10<45:20:21,  7.08s/it]
 18%|█▊        | 5040/28080 [9:58:17<45:16:43,  7.07s/it]
                                                         
{'loss': 0.6544, 'learning_rate': 0.00047127425939107973, 'epoch': 2.15}

 18%|█▊        | 5040/28080 [9:58:17<45:16:43,  7.07s/it]
 18%|█▊        | 5041/28080 [9:58:24<45:10:16,  7.06s/it]
                                                         
{'loss': 0.6571, 'learning_rate': 0.0004712608375927855, 'epoch': 2.15}

 18%|█▊        | 5041/28080 [9:58:24<45:10:16,  7.06s/it]
 18%|█▊        | 5042/28080 [9:58:31<45:29:15,  7.11s/it]
                                                         
{'loss': 0.6674, 'learning_rate': 0.00047124741285084406, 'epoch': 2.15}

 18%|█▊        | 5042/28080 [9:58:31<45:29:15,  7.11s/it]
 18%|█▊        | 5043/28080 [9:58:38<45:29:46,  7.11s/it]
                                                         
{'loss': 0.6657, 'learning_rate': 0.00047123398516543403, 'epoch': 2.15}

 18%|█▊        | 5043/28080 [9:58:38<45:29:46,  7.11s/it]
 18%|█▊        | 5044/28080 [9:58:45<45:33:01,  7.12s/it]
                                                         
{'loss': 0.6492, 'learning_rate': 0.0004712205545367342, 'epoch': 2.15}

 18%|█▊        | 5044/28080 [9:58:45<45:33:01,  7.12s/it]
 18%|█▊        | 5045/28080 [9:58:53<45:42:48,  7.14s/it]
                                                         
{'loss': 0.6421, 'learning_rate': 0.000471207120964923, 'epoch': 2.16}

 18%|█▊        | 5045/28080 [9:58:53<45:42:48,  7.14s/it]
 18%|█▊        | 5046/28080 [9:59:00<45:44:27,  7.15s/it]
                                                         
{'loss': 0.6545, 'learning_rate': 0.0004711936844501792, 'epoch': 2.16}

 18%|█▊        | 5046/28080 [9:59:00<45:44:27,  7.15s/it]
 18%|█▊        | 5047/28080 [9:59:07<45:40:21,  7.14s/it]
                                                         
{'loss': 0.6335, 'learning_rate': 0.00047118024499268177, 'epoch': 2.16}

 18%|█▊        | 5047/28080 [9:59:07<45:40:21,  7.14s/it]
 18%|█▊        | 5048/28080 [9:59:14<45:24:01,  7.10s/it]
                                                         
{'loss': 0.653, 'learning_rate': 0.00047116680259260926, 'epoch': 2.16}

 18%|█▊        | 5048/28080 [9:59:14<45:24:01,  7.10s/it]
 18%|█▊        | 5049/28080 [9:59:21<45:21:48,  7.09s/it]
                                                         
{'loss': 0.6472, 'learning_rate': 0.00047115335725014064, 'epoch': 2.16}

 18%|█▊        | 5049/28080 [9:59:21<45:21:48,  7.09s/it]
 18%|█▊        | 5050/28080 [9:59:28<45:17:41,  7.08s/it]
                                                         
{'loss': 0.6589, 'learning_rate': 0.00047113990896545475, 'epoch': 2.16}

 18%|█▊        | 5050/28080 [9:59:28<45:17:41,  7.08s/it]
 18%|█▊        | 5051/28080 [9:59:35<45:18:38,  7.08s/it]
                                                         
{'loss': 0.6415, 'learning_rate': 0.0004711264577387305, 'epoch': 2.16}

 18%|█▊        | 5051/28080 [9:59:35<45:18:38,  7.08s/it]
 18%|█▊        | 5052/28080 [9:59:42<45:23:01,  7.09s/it]
                                                         
{'loss': 0.6479, 'learning_rate': 0.00047111300357014684, 'epoch': 2.16}

 18%|█▊        | 5052/28080 [9:59:42<45:23:01,  7.09s/it]
 18%|█▊        | 5053/28080 [9:59:49<45:14:44,  7.07s/it]
                                                         
{'loss': 0.6734, 'learning_rate': 0.00047109954645988277, 'epoch': 2.16}

 18%|█▊        | 5053/28080 [9:59:49<45:14:44,  7.07s/it]
 18%|█▊        | 5054/28080 [9:59:56<45:13:55,  7.07s/it]
                                                         
{'loss': 0.6178, 'learning_rate': 0.0004710860864081173, 'epoch': 2.16}

 18%|█▊        | 5054/28080 [9:59:56<45:13:55,  7.07s/it]
 18%|█▊        | 5055/28080 [10:00:03<45:18:30,  7.08s/it]
                                                          
{'loss': 0.6491, 'learning_rate': 0.0004710726234150297, 'epoch': 2.16}

 18%|█▊        | 5055/28080 [10:00:03<45:18:30,  7.08s/it]
 18%|█▊        | 5056/28080 [10:00:10<45:11:31,  7.07s/it]
                                                          
{'loss': 0.6628, 'learning_rate': 0.00047105915748079876, 'epoch': 2.16}

 18%|█▊        | 5056/28080 [10:00:10<45:11:31,  7.07s/it]
 18%|█▊        | 5057/28080 [10:00:17<45:11:20,  7.07s/it]
                                                          
{'loss': 0.6496, 'learning_rate': 0.0004710456886056038, 'epoch': 2.16}

 18%|█▊        | 5057/28080 [10:00:17<45:11:20,  7.07s/it]
 18%|█▊        | 5058/28080 [10:00:25<45:14:07,  7.07s/it]
                                                          
{'loss': 0.6533, 'learning_rate': 0.00047103221678962404, 'epoch': 2.16}

 18%|█▊        | 5058/28080 [10:00:25<45:14:07,  7.07s/it]
 18%|█▊        | 5059/28080 [10:00:32<45:04:00,  7.05s/it]
                                                          
{'loss': 0.6642, 'learning_rate': 0.0004710187420330386, 'epoch': 2.16}

 18%|█▊        | 5059/28080 [10:00:32<45:04:00,  7.05s/it]
 18%|█▊        | 5060/28080 [10:00:39<45:03:35,  7.05s/it]
                                                          
{'loss': 0.6456, 'learning_rate': 0.00047100526433602684, 'epoch': 2.16}

 18%|█▊        | 5060/28080 [10:00:39<45:03:35,  7.05s/it]
 18%|█▊        | 5061/28080 [10:00:46<45:13:13,  7.07s/it]
                                                          
{'loss': 0.6355, 'learning_rate': 0.0004709917836987681, 'epoch': 2.16}

 18%|█▊        | 5061/28080 [10:00:46<45:13:13,  7.07s/it]
 18%|█▊        | 5062/28080 [10:00:53<45:24:38,  7.10s/it]
                                                          
{'loss': 0.6252, 'learning_rate': 0.00047097830012144163, 'epoch': 2.16}

 18%|█▊        | 5062/28080 [10:00:53<45:24:38,  7.10s/it]
 18%|█▊        | 5063/28080 [10:01:00<45:12:07,  7.07s/it]
                                                          
{'loss': 0.6533, 'learning_rate': 0.00047096481360422684, 'epoch': 2.16}

 18%|█▊        | 5063/28080 [10:01:00<45:12:07,  7.07s/it]
 18%|█▊        | 5064/28080 [10:01:07<45:17:21,  7.08s/it]
                                                          
{'loss': 0.6325, 'learning_rate': 0.0004709513241473031, 'epoch': 2.16}

 18%|█▊        | 5064/28080 [10:01:07<45:17:21,  7.08s/it]
 18%|█▊        | 5065/28080 [10:01:14<45:14:52,  7.08s/it]
                                                          
{'loss': 0.6605, 'learning_rate': 0.00047093783175085, 'epoch': 2.16}

 18%|█▊        | 5065/28080 [10:01:14<45:14:52,  7.08s/it]
 18%|█▊        | 5066/28080 [10:01:21<45:06:41,  7.06s/it]
                                                          
{'loss': 0.6708, 'learning_rate': 0.000470924336415047, 'epoch': 2.16}

 18%|█▊        | 5066/28080 [10:01:21<45:06:41,  7.06s/it]
 18%|█▊        | 5067/28080 [10:01:28<45:18:43,  7.09s/it]
                                                          
{'loss': 0.6615, 'learning_rate': 0.0004709108381400735, 'epoch': 2.16}

 18%|█▊        | 5067/28080 [10:01:28<45:18:43,  7.09s/it]
 18%|█▊        | 5068/28080 [10:01:35<45:02:28,  7.05s/it]
                                                          
{'loss': 0.6855, 'learning_rate': 0.00047089733692610926, 'epoch': 2.17}

 18%|█▊        | 5068/28080 [10:01:35<45:02:28,  7.05s/it]
 18%|█▊        | 5069/28080 [10:01:42<45:08:51,  7.06s/it]
                                                          
{'loss': 0.6635, 'learning_rate': 0.0004708838327733339, 'epoch': 2.17}

 18%|█▊        | 5069/28080 [10:01:42<45:08:51,  7.06s/it]
 18%|█▊        | 5070/28080 [10:01:49<45:19:22,  7.09s/it]
                                                          
{'loss': 0.6216, 'learning_rate': 0.000470870325681927, 'epoch': 2.17}

 18%|█▊        | 5070/28080 [10:01:49<45:19:22,  7.09s/it]
 18%|█▊        | 5071/28080 [10:01:57<45:28:41,  7.12s/it]
                                                          
{'loss': 0.6408, 'learning_rate': 0.0004708568156520682, 'epoch': 2.17}

 18%|█▊        | 5071/28080 [10:01:57<45:28:41,  7.12s/it]
 18%|█▊        | 5072/28080 [10:02:04<45:28:17,  7.11s/it]
                                                          
{'loss': 0.6503, 'learning_rate': 0.00047084330268393735, 'epoch': 2.17}

 18%|█▊        | 5072/28080 [10:02:04<45:28:17,  7.11s/it]
 18%|█▊        | 5073/28080 [10:02:11<45:36:13,  7.14s/it]
                                                          
{'loss': 0.6364, 'learning_rate': 0.00047082978677771424, 'epoch': 2.17}

 18%|█▊        | 5073/28080 [10:02:11<45:36:13,  7.14s/it]
 18%|█▊        | 5074/28080 [10:02:18<45:28:23,  7.12s/it]
                                                          
{'loss': 0.6393, 'learning_rate': 0.0004708162679335786, 'epoch': 2.17}

 18%|█▊        | 5074/28080 [10:02:18<45:28:23,  7.12s/it]
 18%|█▊        | 5075/28080 [10:02:25<45:27:08,  7.11s/it]
                                                          
{'loss': 0.6503, 'learning_rate': 0.00047080274615171033, 'epoch': 2.17}

 18%|█▊        | 5075/28080 [10:02:25<45:27:08,  7.11s/it]
 18%|█▊        | 5076/28080 [10:02:32<45:25:38,  7.11s/it]
                                                          
{'loss': 0.6617, 'learning_rate': 0.00047078922143228933, 'epoch': 2.17}

 18%|█▊        | 5076/28080 [10:02:32<45:25:38,  7.11s/it]
 18%|█▊        | 5077/28080 [10:02:39<45:23:16,  7.10s/it]
                                                          
{'loss': 0.6424, 'learning_rate': 0.00047077569377549543, 'epoch': 2.17}

 18%|█▊        | 5077/28080 [10:02:39<45:23:16,  7.10s/it]
 18%|█▊        | 5078/28080 [10:02:46<45:11:38,  7.07s/it]
                                                          
{'loss': 0.657, 'learning_rate': 0.0004707621631815088, 'epoch': 2.17}

 18%|█▊        | 5078/28080 [10:02:46<45:11:38,  7.07s/it]
 18%|█▊        | 5079/28080 [10:02:53<45:21:47,  7.10s/it]
                                                          
{'loss': 0.6669, 'learning_rate': 0.00047074862965050925, 'epoch': 2.17}

 18%|█▊        | 5079/28080 [10:02:53<45:21:47,  7.10s/it]
 18%|█▊        | 5080/28080 [10:03:01<45:22:35,  7.10s/it]
                                                          
{'loss': 0.6461, 'learning_rate': 0.0004707350931826769, 'epoch': 2.17}

 18%|█▊        | 5080/28080 [10:03:01<45:22:35,  7.10s/it]
 18%|█▊        | 5081/28080 [10:03:08<45:21:15,  7.10s/it]
                                                          
{'loss': 0.6318, 'learning_rate': 0.00047072155377819193, 'epoch': 2.17}

 18%|█▊        | 5081/28080 [10:03:08<45:21:15,  7.10s/it]
 18%|█▊        | 5082/28080 [10:03:15<45:29:42,  7.12s/it]
                                                          
{'loss': 0.639, 'learning_rate': 0.00047070801143723437, 'epoch': 2.17}

 18%|█▊        | 5082/28080 [10:03:15<45:29:42,  7.12s/it]
 18%|█▊        | 5083/28080 [10:03:22<45:35:25,  7.14s/it]
                                                          
{'loss': 0.6395, 'learning_rate': 0.00047069446615998433, 'epoch': 2.17}

 18%|█▊        | 5083/28080 [10:03:22<45:35:25,  7.14s/it]
 18%|█▊        | 5084/28080 [10:03:29<45:30:47,  7.13s/it]
                                                          
{'loss': 0.6341, 'learning_rate': 0.0004706809179466222, 'epoch': 2.17}

 18%|█▊        | 5084/28080 [10:03:29<45:30:47,  7.13s/it]
 18%|█▊        | 5085/28080 [10:03:36<45:23:49,  7.11s/it]
                                                          
{'loss': 0.6417, 'learning_rate': 0.0004706673667973281, 'epoch': 2.17}

 18%|█▊        | 5085/28080 [10:03:36<45:23:49,  7.11s/it]
 18%|█▊        | 5086/28080 [10:03:43<45:29:37,  7.12s/it]
                                                          
{'loss': 0.6626, 'learning_rate': 0.0004706538127122823, 'epoch': 2.17}

 18%|█▊        | 5086/28080 [10:03:43<45:29:37,  7.12s/it]
 18%|█▊        | 5087/28080 [10:03:50<45:21:00,  7.10s/it]
                                                          
{'loss': 0.6263, 'learning_rate': 0.0004706402556916652, 'epoch': 2.17}

 18%|█▊        | 5087/28080 [10:03:50<45:21:00,  7.10s/it]
 18%|█▊        | 5088/28080 [10:03:58<45:25:16,  7.11s/it]
                                                          
{'loss': 0.6652, 'learning_rate': 0.0004706266957356571, 'epoch': 2.17}

 18%|█▊        | 5088/28080 [10:03:58<45:25:16,  7.11s/it]
 18%|█▊        | 5089/28080 [10:04:05<45:30:15,  7.13s/it]
                                                          
{'loss': 0.6571, 'learning_rate': 0.0004706131328444384, 'epoch': 2.17}

 18%|█▊        | 5089/28080 [10:04:05<45:30:15,  7.13s/it]
 18%|█▊        | 5090/28080 [10:04:12<45:22:06,  7.10s/it]
                                                          
{'loss': 0.652, 'learning_rate': 0.00047059956701818955, 'epoch': 2.17}

 18%|█▊        | 5090/28080 [10:04:12<45:22:06,  7.10s/it]
 18%|█▊        | 5091/28080 [10:04:19<45:27:27,  7.12s/it]
                                                          
{'loss': 0.6455, 'learning_rate': 0.00047058599825709107, 'epoch': 2.17}

 18%|█▊        | 5091/28080 [10:04:19<45:27:27,  7.12s/it]
 18%|█▊        | 5092/28080 [10:04:26<45:20:36,  7.10s/it]
                                                          
{'loss': 0.6349, 'learning_rate': 0.0004705724265613235, 'epoch': 2.18}

 18%|█▊        | 5092/28080 [10:04:26<45:20:36,  7.10s/it]
 18%|█▊        | 5093/28080 [10:04:33<45:14:15,  7.08s/it]
                                                          
{'loss': 0.636, 'learning_rate': 0.0004705588519310673, 'epoch': 2.18}

 18%|█▊        | 5093/28080 [10:04:33<45:14:15,  7.08s/it]
 18%|█▊        | 5094/28080 [10:04:40<45:10:36,  7.08s/it]
                                                          
{'loss': 0.662, 'learning_rate': 0.0004705452743665031, 'epoch': 2.18}

 18%|█▊        | 5094/28080 [10:04:40<45:10:36,  7.08s/it]
 18%|█▊        | 5095/28080 [10:04:47<45:11:28,  7.08s/it]
                                                          
{'loss': 0.6342, 'learning_rate': 0.00047053169386781157, 'epoch': 2.18}

 18%|█▊        | 5095/28080 [10:04:47<45:11:28,  7.08s/it]
 18%|█▊        | 5096/28080 [10:04:54<45:08:54,  7.07s/it]
                                                          
{'loss': 0.6347, 'learning_rate': 0.00047051811043517333, 'epoch': 2.18}

 18%|█▊        | 5096/28080 [10:04:54<45:08:54,  7.07s/it]
 18%|█▊        | 5097/28080 [10:05:01<45:10:49,  7.08s/it]
                                                          
{'loss': 0.639, 'learning_rate': 0.00047050452406876913, 'epoch': 2.18}

 18%|█▊        | 5097/28080 [10:05:01<45:10:49,  7.08s/it]
 18%|█▊        | 5098/28080 [10:05:08<45:01:52,  7.05s/it]
                                                          
{'loss': 0.6739, 'learning_rate': 0.00047049093476877975, 'epoch': 2.18}

 18%|█▊        | 5098/28080 [10:05:08<45:01:52,  7.05s/it]
 18%|█▊        | 5099/28080 [10:05:15<45:09:37,  7.07s/it]
                                                          
{'loss': 0.663, 'learning_rate': 0.0004704773425353859, 'epoch': 2.18}

 18%|█▊        | 5099/28080 [10:05:15<45:09:37,  7.07s/it]
 18%|█▊        | 5100/28080 [10:05:22<45:08:47,  7.07s/it]
                                                          
{'loss': 0.6298, 'learning_rate': 0.0004704637473687685, 'epoch': 2.18}

 18%|█▊        | 5100/28080 [10:05:22<45:08:47,  7.07s/it]
 18%|█▊        | 5101/28080 [10:05:29<44:59:16,  7.05s/it]
                                                          
{'loss': 0.659, 'learning_rate': 0.0004704501492691084, 'epoch': 2.18}

 18%|█▊        | 5101/28080 [10:05:29<44:59:16,  7.05s/it]
 18%|█▊        | 5102/28080 [10:05:37<45:03:14,  7.06s/it]
                                                          
{'loss': 0.634, 'learning_rate': 0.0004704365482365864, 'epoch': 2.18}

 18%|█▊        | 5102/28080 [10:05:37<45:03:14,  7.06s/it]
 18%|█▊        | 5103/28080 [10:05:44<44:56:58,  7.04s/it]
                                                          
{'loss': 0.6438, 'learning_rate': 0.00047042294427138365, 'epoch': 2.18}

 18%|█▊        | 5103/28080 [10:05:44<44:56:58,  7.04s/it]
 18%|█▊        | 5104/28080 [10:05:51<45:09:44,  7.08s/it]
                                                          
{'loss': 0.6543, 'learning_rate': 0.00047040933737368105, 'epoch': 2.18}

 18%|█▊        | 5104/28080 [10:05:51<45:09:44,  7.08s/it]
 18%|█▊        | 5105/28080 [10:05:58<45:18:26,  7.10s/it]
                                                          
{'loss': 0.6587, 'learning_rate': 0.0004703957275436595, 'epoch': 2.18}

 18%|█▊        | 5105/28080 [10:05:58<45:18:26,  7.10s/it]
 18%|█▊        | 5106/28080 [10:06:05<45:18:24,  7.10s/it]
                                                          
{'loss': 0.6434, 'learning_rate': 0.00047038211478150015, 'epoch': 2.18}

 18%|█▊        | 5106/28080 [10:06:05<45:18:24,  7.10s/it]
 18%|█▊        | 5107/28080 [10:06:12<45:13:59,  7.09s/it]
                                                          
{'loss': 0.652, 'learning_rate': 0.0004703684990873842, 'epoch': 2.18}

 18%|█▊        | 5107/28080 [10:06:12<45:13:59,  7.09s/it]
 18%|█▊        | 5108/28080 [10:06:19<45:20:57,  7.11s/it]
                                                          
{'loss': 0.637, 'learning_rate': 0.00047035488046149264, 'epoch': 2.18}

 18%|█▊        | 5108/28080 [10:06:19<45:20:57,  7.11s/it]
 18%|█▊        | 5109/28080 [10:06:26<45:03:19,  7.06s/it]
                                                          
{'loss': 0.6582, 'learning_rate': 0.0004703412589040068, 'epoch': 2.18}

 18%|█▊        | 5109/28080 [10:06:26<45:03:19,  7.06s/it]
 18%|█▊        | 5110/28080 [10:06:33<45:09:33,  7.08s/it]
                                                          
{'loss': 0.6327, 'learning_rate': 0.0004703276344151078, 'epoch': 2.18}

 18%|█▊        | 5110/28080 [10:06:33<45:09:33,  7.08s/it]
 18%|█▊        | 5111/28080 [10:06:40<45:16:51,  7.10s/it]
                                                          
{'loss': 0.655, 'learning_rate': 0.0004703140069949769, 'epoch': 2.18}

 18%|█▊        | 5111/28080 [10:06:40<45:16:51,  7.10s/it]
 18%|█▊        | 5112/28080 [10:06:47<45:16:22,  7.10s/it]
                                                          
{'loss': 0.6471, 'learning_rate': 0.0004703003766437954, 'epoch': 2.18}

 18%|█▊        | 5112/28080 [10:06:47<45:16:22,  7.10s/it]
 18%|█▊        | 5113/28080 [10:06:55<45:10:26,  7.08s/it]
                                                          
{'loss': 0.6402, 'learning_rate': 0.0004702867433617447, 'epoch': 2.18}

 18%|█▊        | 5113/28080 [10:06:55<45:10:26,  7.08s/it]
 18%|█▊        | 5114/28080 [10:07:02<45:12:34,  7.09s/it]
                                                          
{'loss': 0.6454, 'learning_rate': 0.00047027310714900614, 'epoch': 2.18}

 18%|█▊        | 5114/28080 [10:07:02<45:12:34,  7.09s/it]
 18%|█▊        | 5115/28080 [10:07:09<45:16:31,  7.10s/it]
                                                          
{'loss': 0.6471, 'learning_rate': 0.00047025946800576115, 'epoch': 2.19}

 18%|█▊        | 5115/28080 [10:07:09<45:16:31,  7.10s/it]
 18%|█▊        | 5116/28080 [10:07:16<45:20:48,  7.11s/it]
                                                          
{'loss': 0.6443, 'learning_rate': 0.0004702458259321911, 'epoch': 2.19}

 18%|█▊        | 5116/28080 [10:07:16<45:20:48,  7.11s/it]
 18%|█▊        | 5117/28080 [10:07:23<45:15:19,  7.09s/it]
                                                          
{'loss': 0.6461, 'learning_rate': 0.00047023218092847756, 'epoch': 2.19}

 18%|█▊        | 5117/28080 [10:07:23<45:15:19,  7.09s/it]
 18%|█▊        | 5118/28080 [10:07:30<45:06:45,  7.07s/it]
                                                          
{'loss': 0.6546, 'learning_rate': 0.0004702185329948021, 'epoch': 2.19}

 18%|█▊        | 5118/28080 [10:07:30<45:06:45,  7.07s/it]
 18%|█▊        | 5119/28080 [10:07:37<45:10:40,  7.08s/it]
                                                          
{'loss': 0.653, 'learning_rate': 0.0004702048821313462, 'epoch': 2.19}

 18%|█▊        | 5119/28080 [10:07:37<45:10:40,  7.08s/it]
 18%|█▊        | 5120/28080 [10:07:44<45:11:41,  7.09s/it]
                                                          
{'loss': 0.6446, 'learning_rate': 0.00047019122833829154, 'epoch': 2.19}

 18%|█▊        | 5120/28080 [10:07:44<45:11:41,  7.09s/it]
 18%|█▊        | 5121/28080 [10:07:51<45:08:11,  7.08s/it]
                                                          
{'loss': 0.6369, 'learning_rate': 0.00047017757161581974, 'epoch': 2.19}

 18%|█▊        | 5121/28080 [10:07:51<45:08:11,  7.08s/it]
 18%|█▊        | 5122/28080 [10:07:58<45:01:02,  7.06s/it]
                                                          
{'loss': 0.6536, 'learning_rate': 0.0004701639119641126, 'epoch': 2.19}

 18%|█▊        | 5122/28080 [10:07:58<45:01:02,  7.06s/it]
 18%|█▊        | 5123/28080 [10:08:05<45:10:21,  7.08s/it]
                                                          
{'loss': 0.6492, 'learning_rate': 0.0004701502493833516, 'epoch': 2.19}

 18%|█▊        | 5123/28080 [10:08:05<45:10:21,  7.08s/it]
 18%|█▊        | 5124/28080 [10:08:12<44:58:06,  7.05s/it]
                                                          
{'loss': 0.6448, 'learning_rate': 0.00047013658387371865, 'epoch': 2.19}

 18%|█▊        | 5124/28080 [10:08:12<44:58:06,  7.05s/it]
 18%|█▊        | 5125/28080 [10:08:19<45:06:57,  7.08s/it]
                                                          
{'loss': 0.6422, 'learning_rate': 0.0004701229154353956, 'epoch': 2.19}

 18%|█▊        | 5125/28080 [10:08:19<45:06:57,  7.08s/it]
 18%|█▊        | 5126/28080 [10:08:27<45:09:23,  7.08s/it]
                                                          
{'loss': 0.6575, 'learning_rate': 0.00047010924406856426, 'epoch': 2.19}

 18%|█▊        | 5126/28080 [10:08:27<45:09:23,  7.08s/it]
 18%|█▊        | 5127/28080 [10:08:34<45:14:03,  7.09s/it]
                                                          
{'loss': 0.6292, 'learning_rate': 0.0004700955697734064, 'epoch': 2.19}

 18%|█▊        | 5127/28080 [10:08:34<45:14:03,  7.09s/it]
 18%|█▊        | 5128/28080 [10:08:41<45:03:20,  7.07s/it]
                                                          
{'loss': 0.6541, 'learning_rate': 0.0004700818925501042, 'epoch': 2.19}

 18%|█▊        | 5128/28080 [10:08:41<45:03:20,  7.07s/it]
 18%|█▊        | 5129/28080 [10:08:48<45:07:58,  7.08s/it]
                                                          
{'loss': 0.6723, 'learning_rate': 0.0004700682123988393, 'epoch': 2.19}

 18%|█▊        | 5129/28080 [10:08:48<45:07:58,  7.08s/it]
 18%|█▊        | 5130/28080 [10:08:55<45:04:21,  7.07s/it]
                                                          
{'loss': 0.644, 'learning_rate': 0.000470054529319794, 'epoch': 2.19}

 18%|█▊        | 5130/28080 [10:08:55<45:04:21,  7.07s/it]
 18%|█▊        | 5131/28080 [10:09:02<44:55:07,  7.05s/it]
                                                          
{'loss': 0.6507, 'learning_rate': 0.00047004084331315023, 'epoch': 2.19}

 18%|█▊        | 5131/28080 [10:09:02<44:55:07,  7.05s/it]
 18%|█▊        | 5132/28080 [10:09:09<44:58:33,  7.06s/it]
                                                          
{'loss': 0.6395, 'learning_rate': 0.00047002715437908995, 'epoch': 2.19}

 18%|█▊        | 5132/28080 [10:09:09<44:58:33,  7.06s/it]
 18%|█▊        | 5133/28080 [10:09:16<44:54:11,  7.04s/it]
                                                          
{'loss': 0.649, 'learning_rate': 0.0004700134625177954, 'epoch': 2.19}

 18%|█▊        | 5133/28080 [10:09:16<44:54:11,  7.04s/it]
 18%|█▊        | 5134/28080 [10:09:23<44:50:42,  7.04s/it]
                                                          
{'loss': 0.643, 'learning_rate': 0.0004699997677294487, 'epoch': 2.19}

 18%|█▊        | 5134/28080 [10:09:23<44:50:42,  7.04s/it]
 18%|█▊        | 5135/28080 [10:09:30<45:05:21,  7.07s/it]
                                                          
{'loss': 0.6317, 'learning_rate': 0.0004699860700142321, 'epoch': 2.19}

 18%|█▊        | 5135/28080 [10:09:30<45:05:21,  7.07s/it]
 18%|█▊        | 5136/28080 [10:09:37<45:07:21,  7.08s/it]
                                                          
{'loss': 0.6711, 'learning_rate': 0.0004699723693723277, 'epoch': 2.19}

 18%|█▊        | 5136/28080 [10:09:37<45:07:21,  7.08s/it]
 18%|█▊        | 5137/28080 [10:09:44<45:09:07,  7.08s/it]
                                                          
{'loss': 0.6537, 'learning_rate': 0.0004699586658039179, 'epoch': 2.19}

 18%|█▊        | 5137/28080 [10:09:44<45:09:07,  7.08s/it]
 18%|█▊        | 5138/28080 [10:09:51<45:13:00,  7.10s/it]
                                                          
{'loss': 0.6577, 'learning_rate': 0.000469944959309185, 'epoch': 2.19}

 18%|█▊        | 5138/28080 [10:09:51<45:13:00,  7.10s/it]
 18%|█▊        | 5139/28080 [10:09:59<45:08:53,  7.08s/it]
                                                          
{'loss': 0.636, 'learning_rate': 0.00046993124988831125, 'epoch': 2.2}

 18%|█▊        | 5139/28080 [10:09:59<45:08:53,  7.08s/it]
 18%|█▊        | 5140/28080 [10:10:05<44:55:36,  7.05s/it]
                                                          
{'loss': 0.6518, 'learning_rate': 0.00046991753754147914, 'epoch': 2.2}

 18%|█▊        | 5140/28080 [10:10:05<44:55:36,  7.05s/it]
 18%|█▊        | 5141/28080 [10:10:13<45:10:37,  7.09s/it]
                                                          
{'loss': 0.6432, 'learning_rate': 0.0004699038222688711, 'epoch': 2.2}

 18%|█▊        | 5141/28080 [10:10:13<45:10:37,  7.09s/it]
 18%|█▊        | 5142/28080 [10:10:20<45:01:58,  7.07s/it]
                                                          
{'loss': 0.6473, 'learning_rate': 0.00046989010407066955, 'epoch': 2.2}

 18%|█▊        | 5142/28080 [10:10:20<45:01:58,  7.07s/it]
 18%|█▊        | 5143/28080 [10:10:27<45:09:26,  7.09s/it]
                                                          
{'loss': 0.6329, 'learning_rate': 0.000469876382947057, 'epoch': 2.2}

 18%|█▊        | 5143/28080 [10:10:27<45:09:26,  7.09s/it]
 18%|█▊        | 5144/28080 [10:10:34<45:13:49,  7.10s/it]
                                                          
{'loss': 0.659, 'learning_rate': 0.0004698626588982161, 'epoch': 2.2}

 18%|█▊        | 5144/28080 [10:10:34<45:13:49,  7.10s/it]
 18%|█▊        | 5145/28080 [10:10:41<45:25:49,  7.13s/it]
                                                          
{'loss': 0.647, 'learning_rate': 0.0004698489319243292, 'epoch': 2.2}

 18%|█▊        | 5145/28080 [10:10:41<45:25:49,  7.13s/it]
 18%|█▊        | 5146/28080 [10:10:48<45:21:35,  7.12s/it]
                                                          
{'loss': 0.635, 'learning_rate': 0.00046983520202557914, 'epoch': 2.2}

 18%|█▊        | 5146/28080 [10:10:48<45:21:35,  7.12s/it]
 18%|█▊        | 5147/28080 [10:10:55<45:23:34,  7.13s/it]
                                                          
{'loss': 0.6238, 'learning_rate': 0.00046982146920214853, 'epoch': 2.2}

 18%|█▊        | 5147/28080 [10:10:55<45:23:34,  7.13s/it]
 18%|█▊        | 5148/28080 [10:11:02<45:11:16,  7.09s/it]
                                                          
{'loss': 0.626, 'learning_rate': 0.00046980773345422003, 'epoch': 2.2}

 18%|█▊        | 5148/28080 [10:11:02<45:11:16,  7.09s/it]
 18%|█▊        | 5149/28080 [10:11:09<45:12:00,  7.10s/it]
                                                          
{'loss': 0.6572, 'learning_rate': 0.0004697939947819764, 'epoch': 2.2}

 18%|█▊        | 5149/28080 [10:11:09<45:12:00,  7.10s/it]
 18%|█▊        | 5150/28080 [10:11:16<44:59:28,  7.06s/it]
                                                          
{'loss': 0.6548, 'learning_rate': 0.00046978025318560035, 'epoch': 2.2}

 18%|█▊        | 5150/28080 [10:11:16<44:59:28,  7.06s/it]
 18%|█▊        | 5151/28080 [10:11:23<44:54:46,  7.05s/it]
                                                          
{'loss': 0.6397, 'learning_rate': 0.0004697665086652748, 'epoch': 2.2}

 18%|█▊        | 5151/28080 [10:11:24<44:54:46,  7.05s/it]
 18%|█▊        | 5152/28080 [10:11:31<44:55:01,  7.05s/it]
                                                          
{'loss': 0.6462, 'learning_rate': 0.0004697527612211826, 'epoch': 2.2}

 18%|█▊        | 5152/28080 [10:11:31<44:55:01,  7.05s/it]
 18%|█▊        | 5153/28080 [10:11:38<45:08:16,  7.09s/it]
                                                          
{'loss': 0.6199, 'learning_rate': 0.0004697390108535066, 'epoch': 2.2}

 18%|█▊        | 5153/28080 [10:11:38<45:08:16,  7.09s/it]
 18%|█▊        | 5154/28080 [10:11:45<45:02:43,  7.07s/it]
                                                          
{'loss': 0.6314, 'learning_rate': 0.00046972525756242976, 'epoch': 2.2}

 18%|█▊        | 5154/28080 [10:11:45<45:02:43,  7.07s/it]
 18%|█▊        | 5155/28080 [10:11:52<45:07:51,  7.09s/it]
                                                          
{'loss': 0.6254, 'learning_rate': 0.0004697115013481351, 'epoch': 2.2}

 18%|█▊        | 5155/28080 [10:11:52<45:07:51,  7.09s/it]
 18%|█▊        | 5156/28080 [10:11:59<45:08:43,  7.09s/it]
                                                          
{'loss': 0.6308, 'learning_rate': 0.0004696977422108055, 'epoch': 2.2}

 18%|█▊        | 5156/28080 [10:11:59<45:08:43,  7.09s/it]
 18%|█▊        | 5157/28080 [10:12:06<45:04:08,  7.08s/it]
                                                          
{'loss': 0.6482, 'learning_rate': 0.0004696839801506241, 'epoch': 2.2}

 18%|█▊        | 5157/28080 [10:12:06<45:04:08,  7.08s/it]
 18%|█▊        | 5158/28080 [10:12:13<45:09:05,  7.09s/it]
                                                          
{'loss': 0.6208, 'learning_rate': 0.00046967021516777405, 'epoch': 2.2}

 18%|█▊        | 5158/28080 [10:12:13<45:09:05,  7.09s/it]
 18%|█▊        | 5159/28080 [10:12:20<45:11:47,  7.10s/it]
                                                          
{'loss': 0.6241, 'learning_rate': 0.00046965644726243834, 'epoch': 2.2}

 18%|█▊        | 5159/28080 [10:12:20<45:11:47,  7.10s/it]
 18%|█▊        | 5160/28080 [10:12:27<45:13:46,  7.10s/it]
                                                          
{'loss': 0.645, 'learning_rate': 0.0004696426764348002, 'epoch': 2.2}

 18%|█▊        | 5160/28080 [10:12:27<45:13:46,  7.10s/it]
 18%|█▊        | 5161/28080 [10:12:34<44:59:24,  7.07s/it]
                                                          
{'loss': 0.6285, 'learning_rate': 0.00046962890268504285, 'epoch': 2.2}

 18%|█▊        | 5161/28080 [10:12:34<44:59:24,  7.07s/it]
 18%|█▊        | 5162/28080 [10:12:42<45:08:36,  7.09s/it]
                                                          
{'loss': 0.6285, 'learning_rate': 0.00046961512601334954, 'epoch': 2.21}

 18%|█▊        | 5162/28080 [10:12:42<45:08:36,  7.09s/it]
 18%|█▊        | 5163/28080 [10:12:49<45:04:11,  7.08s/it]
                                                          
{'loss': 0.6409, 'learning_rate': 0.0004696013464199036, 'epoch': 2.21}

 18%|█▊        | 5163/28080 [10:12:49<45:04:11,  7.08s/it]
 18%|█▊        | 5164/28080 [10:12:56<45:06:30,  7.09s/it]
                                                          
{'loss': 0.6601, 'learning_rate': 0.0004695875639048882, 'epoch': 2.21}

 18%|█▊        | 5164/28080 [10:12:56<45:06:30,  7.09s/it]
 18%|█▊        | 5165/28080 [10:13:03<45:19:34,  7.12s/it]
                                                          
{'loss': 0.6531, 'learning_rate': 0.00046957377846848687, 'epoch': 2.21}

 18%|█▊        | 5165/28080 [10:13:03<45:19:34,  7.12s/it]
 18%|█▊        | 5166/28080 [10:13:10<45:15:45,  7.11s/it]
                                                          
{'loss': 0.6582, 'learning_rate': 0.0004695599901108829, 'epoch': 2.21}

 18%|█▊        | 5166/28080 [10:13:10<45:15:45,  7.11s/it]
 18%|█▊        | 5167/28080 [10:13:17<45:15:51,  7.11s/it]
                                                          
{'loss': 0.6428, 'learning_rate': 0.0004695461988322598, 'epoch': 2.21}

 18%|█▊        | 5167/28080 [10:13:17<45:15:51,  7.11s/it]
 18%|█▊        | 5168/28080 [10:13:24<45:16:53,  7.11s/it]
                                                          
{'loss': 0.6526, 'learning_rate': 0.000469532404632801, 'epoch': 2.21}

 18%|█▊        | 5168/28080 [10:13:24<45:16:53,  7.11s/it]
 18%|█▊        | 5169/28080 [10:13:31<45:16:52,  7.12s/it]
                                                          
{'loss': 0.6617, 'learning_rate': 0.00046951860751269004, 'epoch': 2.21}

 18%|█▊        | 5169/28080 [10:13:31<45:16:52,  7.12s/it]
 18%|█▊        | 5170/28080 [10:13:38<45:15:48,  7.11s/it]
                                                          
{'loss': 0.6429, 'learning_rate': 0.0004695048074721104, 'epoch': 2.21}

 18%|█▊        | 5170/28080 [10:13:38<45:15:48,  7.11s/it]
 18%|█▊        | 5171/28080 [10:13:46<45:18:06,  7.12s/it]
                                                          
{'loss': 0.6453, 'learning_rate': 0.0004694910045112458, 'epoch': 2.21}

 18%|█▊        | 5171/28080 [10:13:46<45:18:06,  7.12s/it]
 18%|█▊        | 5172/28080 [10:13:53<45:03:38,  7.08s/it]
                                                          
{'loss': 0.6573, 'learning_rate': 0.00046947719863027986, 'epoch': 2.21}

 18%|█▊        | 5172/28080 [10:13:53<45:03:38,  7.08s/it]
 18%|█▊        | 5173/28080 [10:14:00<45:00:06,  7.07s/it]
                                                          
{'loss': 0.6833, 'learning_rate': 0.0004694633898293962, 'epoch': 2.21}

 18%|█▊        | 5173/28080 [10:14:00<45:00:06,  7.07s/it]
 18%|█▊        | 5174/28080 [10:14:07<44:51:53,  7.05s/it]
                                                          
{'loss': 0.6435, 'learning_rate': 0.00046944957810877855, 'epoch': 2.21}

 18%|█▊        | 5174/28080 [10:14:07<44:51:53,  7.05s/it]
 18%|█▊        | 5175/28080 [10:14:14<44:57:20,  7.07s/it]
                                                          
{'loss': 0.64, 'learning_rate': 0.00046943576346861063, 'epoch': 2.21}

 18%|█▊        | 5175/28080 [10:14:14<44:57:20,  7.07s/it]
 18%|█▊        | 5176/28080 [10:14:21<45:05:30,  7.09s/it]
                                                          
{'loss': 0.6185, 'learning_rate': 0.00046942194590907625, 'epoch': 2.21}

 18%|█▊        | 5176/28080 [10:14:21<45:05:30,  7.09s/it]
 18%|█▊        | 5177/28080 [10:14:28<45:16:43,  7.12s/it]
                                                          
{'loss': 0.6599, 'learning_rate': 0.0004694081254303593, 'epoch': 2.21}

 18%|█▊        | 5177/28080 [10:14:28<45:16:43,  7.12s/it]
 18%|█▊        | 5178/28080 [10:14:35<45:19:55,  7.13s/it]
                                                          
{'loss': 0.63, 'learning_rate': 0.0004693943020326435, 'epoch': 2.21}

 18%|█▊        | 5178/28080 [10:14:35<45:19:55,  7.13s/it]
 18%|█▊        | 5179/28080 [10:14:42<45:22:33,  7.13s/it]
                                                          
{'loss': 0.632, 'learning_rate': 0.0004693804757161129, 'epoch': 2.21}

 18%|█▊        | 5179/28080 [10:14:42<45:22:33,  7.13s/it]
 18%|█▊        | 5180/28080 [10:14:49<45:12:49,  7.11s/it]
                                                          
{'loss': 0.6557, 'learning_rate': 0.0004693666464809514, 'epoch': 2.21}

 18%|█▊        | 5180/28080 [10:14:49<45:12:49,  7.11s/it]
 18%|█▊        | 5181/28080 [10:14:56<45:12:36,  7.11s/it]
                                                          
{'loss': 0.6529, 'learning_rate': 0.000469352814327343, 'epoch': 2.21}

 18%|█▊        | 5181/28080 [10:14:56<45:12:36,  7.11s/it]
 18%|█▊        | 5182/28080 [10:15:04<45:08:08,  7.10s/it]
                                                          
{'loss': 0.6458, 'learning_rate': 0.00046933897925547166, 'epoch': 2.21}

 18%|█▊        | 5182/28080 [10:15:04<45:08:08,  7.10s/it]
 18%|█▊        | 5183/28080 [10:15:11<44:53:22,  7.06s/it]
                                                          
{'loss': 0.6608, 'learning_rate': 0.0004693251412655215, 'epoch': 2.21}

 18%|█▊        | 5183/28080 [10:15:11<44:53:22,  7.06s/it]
 18%|█▊        | 5184/28080 [10:15:18<44:53:40,  7.06s/it]
                                                          
{'loss': 0.6371, 'learning_rate': 0.00046931130035767654, 'epoch': 2.21}

 18%|█▊        | 5184/28080 [10:15:18<44:53:40,  7.06s/it]
 18%|█▊        | 5185/28080 [10:15:25<44:50:59,  7.05s/it]
                                                          
{'loss': 0.6388, 'learning_rate': 0.00046929745653212106, 'epoch': 2.21}

 18%|█▊        | 5185/28080 [10:15:25<44:50:59,  7.05s/it]
 18%|█▊        | 5186/28080 [10:15:32<44:59:48,  7.08s/it]
                                                          
{'loss': 0.6432, 'learning_rate': 0.0004692836097890391, 'epoch': 2.22}

 18%|█▊        | 5186/28080 [10:15:32<44:59:48,  7.08s/it]
 18%|█▊        | 5187/28080 [10:15:39<45:07:16,  7.10s/it]
                                                          
{'loss': 0.6445, 'learning_rate': 0.000469269760128615, 'epoch': 2.22}

 18%|█▊        | 5187/28080 [10:15:39<45:07:16,  7.10s/it]
 18%|█▊        | 5188/28080 [10:15:46<45:12:34,  7.11s/it]
                                                          
{'loss': 0.6533, 'learning_rate': 0.0004692559075510329, 'epoch': 2.22}

 18%|█▊        | 5188/28080 [10:15:46<45:12:34,  7.11s/it]
 18%|█▊        | 5189/28080 [10:15:53<45:09:53,  7.10s/it]
                                                          
{'loss': 0.6437, 'learning_rate': 0.0004692420520564771, 'epoch': 2.22}

 18%|█▊        | 5189/28080 [10:15:53<45:09:53,  7.10s/it]
 18%|█▊        | 5190/28080 [10:16:00<45:14:13,  7.11s/it]
                                                          
{'loss': 0.6526, 'learning_rate': 0.000469228193645132, 'epoch': 2.22}

 18%|█▊        | 5190/28080 [10:16:00<45:14:13,  7.11s/it]
 18%|█▊        | 5191/28080 [10:16:07<45:18:40,  7.13s/it]
                                                          
{'loss': 0.6769, 'learning_rate': 0.00046921433231718204, 'epoch': 2.22}

 18%|█▊        | 5191/28080 [10:16:07<45:18:40,  7.13s/it]
 18%|█▊        | 5192/28080 [10:16:14<45:13:35,  7.11s/it]
                                                          
{'loss': 0.6609, 'learning_rate': 0.0004692004680728115, 'epoch': 2.22}

 18%|█▊        | 5192/28080 [10:16:14<45:13:35,  7.11s/it]
 18%|█▊        | 5193/28080 [10:16:22<45:09:49,  7.10s/it]
                                                          
{'loss': 0.6402, 'learning_rate': 0.00046918660091220483, 'epoch': 2.22}

 18%|█▊        | 5193/28080 [10:16:22<45:09:49,  7.10s/it]
 18%|█▊        | 5194/28080 [10:16:29<45:01:55,  7.08s/it]
                                                          
{'loss': 0.6623, 'learning_rate': 0.00046917273083554655, 'epoch': 2.22}

 18%|█▊        | 5194/28080 [10:16:29<45:01:55,  7.08s/it]
 19%|█▊        | 5195/28080 [10:16:36<44:59:52,  7.08s/it]
                                                          
{'loss': 0.6481, 'learning_rate': 0.00046915885784302124, 'epoch': 2.22}

 19%|█▊        | 5195/28080 [10:16:36<44:59:52,  7.08s/it]
 19%|█▊        | 5196/28080 [10:16:43<44:52:16,  7.06s/it]
                                                          
{'loss': 0.6706, 'learning_rate': 0.0004691449819348134, 'epoch': 2.22}

 19%|█▊        | 5196/28080 [10:16:43<44:52:16,  7.06s/it]
 19%|█▊        | 5197/28080 [10:16:50<45:08:01,  7.10s/it]
                                                          
{'loss': 0.6391, 'learning_rate': 0.00046913110311110767, 'epoch': 2.22}

 19%|█▊        | 5197/28080 [10:16:50<45:08:01,  7.10s/it]
 19%|█▊        | 5198/28080 [10:16:57<45:03:39,  7.09s/it]
                                                          
{'loss': 0.6512, 'learning_rate': 0.0004691172213720887, 'epoch': 2.22}

 19%|█▊        | 5198/28080 [10:16:57<45:03:39,  7.09s/it]
 19%|█▊        | 5199/28080 [10:17:04<44:59:47,  7.08s/it]
                                                          
{'loss': 0.6579, 'learning_rate': 0.0004691033367179411, 'epoch': 2.22}

 19%|█▊        | 5199/28080 [10:17:04<44:59:47,  7.08s/it]
 19%|█▊        | 5200/28080 [10:17:11<45:14:42,  7.12s/it]
                                                          
{'loss': 0.633, 'learning_rate': 0.00046908944914884963, 'epoch': 2.22}

 19%|█▊        | 5200/28080 [10:17:11<45:14:42,  7.12s/it]
 19%|█▊        | 5201/28080 [10:17:18<45:09:21,  7.11s/it]
                                                          
{'loss': 0.6483, 'learning_rate': 0.0004690755586649991, 'epoch': 2.22}

 19%|█▊        | 5201/28080 [10:17:18<45:09:21,  7.11s/it]
 19%|█▊        | 5202/28080 [10:17:25<45:09:38,  7.11s/it]
                                                          
{'loss': 0.6497, 'learning_rate': 0.00046906166526657425, 'epoch': 2.22}

 19%|█▊        | 5202/28080 [10:17:25<45:09:38,  7.11s/it]
 19%|█▊        | 5203/28080 [10:17:32<45:07:40,  7.10s/it]
                                                          
{'loss': 0.6526, 'learning_rate': 0.0004690477689537599, 'epoch': 2.22}

 19%|█▊        | 5203/28080 [10:17:32<45:07:40,  7.10s/it]
 19%|█▊        | 5204/28080 [10:17:40<45:10:45,  7.11s/it]
                                                          
{'loss': 0.6516, 'learning_rate': 0.000469033869726741, 'epoch': 2.22}

 19%|█▊        | 5204/28080 [10:17:40<45:10:45,  7.11s/it]
 19%|█▊        | 5205/28080 [10:17:47<45:04:26,  7.09s/it]
                                                          
{'loss': 0.6528, 'learning_rate': 0.0004690199675857024, 'epoch': 2.22}

 19%|█▊        | 5205/28080 [10:17:47<45:04:26,  7.09s/it]
 19%|█▊        | 5206/28080 [10:17:54<45:13:29,  7.12s/it]
                                                          
{'loss': 0.6362, 'learning_rate': 0.00046900606253082915, 'epoch': 2.22}

 19%|█▊        | 5206/28080 [10:17:54<45:13:29,  7.12s/it]
 19%|█▊        | 5207/28080 [10:18:01<45:21:12,  7.14s/it]
                                                          
{'loss': 0.6379, 'learning_rate': 0.00046899215456230615, 'epoch': 2.22}

 19%|█▊        | 5207/28080 [10:18:01<45:21:12,  7.14s/it]
 19%|█▊        | 5208/28080 [10:18:08<45:07:22,  7.10s/it]
                                                          
{'loss': 0.6349, 'learning_rate': 0.0004689782436803185, 'epoch': 2.22}

 19%|█▊        | 5208/28080 [10:18:08<45:07:22,  7.10s/it]
 19%|█▊        | 5209/28080 [10:18:15<45:03:48,  7.09s/it]
                                                          
{'loss': 0.6483, 'learning_rate': 0.0004689643298850511, 'epoch': 2.23}

 19%|█▊        | 5209/28080 [10:18:15<45:03:48,  7.09s/it]
 19%|█▊        | 5210/28080 [10:18:22<45:14:29,  7.12s/it]
                                                          
{'loss': 0.6363, 'learning_rate': 0.0004689504131766893, 'epoch': 2.23}

 19%|█▊        | 5210/28080 [10:18:22<45:14:29,  7.12s/it]
 19%|█▊        | 5211/28080 [10:18:29<45:07:58,  7.10s/it]
                                                          
{'loss': 0.6546, 'learning_rate': 0.0004689364935554181, 'epoch': 2.23}

 19%|█▊        | 5211/28080 [10:18:29<45:07:58,  7.10s/it]
 19%|█▊        | 5212/28080 [10:18:36<45:07:36,  7.10s/it]
                                                          
{'loss': 0.6463, 'learning_rate': 0.00046892257102142267, 'epoch': 2.23}

 19%|█▊        | 5212/28080 [10:18:36<45:07:36,  7.10s/it]
 19%|█▊        | 5213/28080 [10:18:44<45:11:35,  7.11s/it]
                                                          
{'loss': 0.6556, 'learning_rate': 0.00046890864557488834, 'epoch': 2.23}

 19%|█▊        | 5213/28080 [10:18:44<45:11:35,  7.11s/it]
 19%|█▊        | 5214/28080 [10:18:51<44:54:01,  7.07s/it]
                                                          
{'loss': 0.6441, 'learning_rate': 0.00046889471721600027, 'epoch': 2.23}

 19%|█▊        | 5214/28080 [10:18:51<44:54:01,  7.07s/it]
 19%|█▊        | 5215/28080 [10:18:58<45:10:40,  7.11s/it]
                                                          
{'loss': 0.6377, 'learning_rate': 0.0004688807859449438, 'epoch': 2.23}

 19%|█▊        | 5215/28080 [10:18:58<45:10:40,  7.11s/it]
 19%|█▊        | 5216/28080 [10:19:05<45:13:09,  7.12s/it]
                                                          
{'loss': 0.6541, 'learning_rate': 0.00046886685176190435, 'epoch': 2.23}

 19%|█▊        | 5216/28080 [10:19:05<45:13:09,  7.12s/it]
 19%|█▊        | 5217/28080 [10:19:12<45:09:47,  7.11s/it]
                                                          
{'loss': 0.6525, 'learning_rate': 0.00046885291466706715, 'epoch': 2.23}

 19%|█▊        | 5217/28080 [10:19:12<45:09:47,  7.11s/it]
 19%|█▊        | 5218/28080 [10:19:19<45:04:47,  7.10s/it]
                                                          
{'loss': 0.6582, 'learning_rate': 0.00046883897466061774, 'epoch': 2.23}

 19%|█▊        | 5218/28080 [10:19:19<45:04:47,  7.10s/it]
 19%|█▊        | 5219/28080 [10:19:26<45:00:28,  7.09s/it]
                                                          
{'loss': 0.6593, 'learning_rate': 0.00046882503174274154, 'epoch': 2.23}

 19%|█▊        | 5219/28080 [10:19:26<45:00:28,  7.09s/it]
 19%|█▊        | 5220/28080 [10:19:33<45:00:30,  7.09s/it]
                                                          
{'loss': 0.6545, 'learning_rate': 0.00046881108591362406, 'epoch': 2.23}

 19%|█▊        | 5220/28080 [10:19:33<45:00:30,  7.09s/it]
 19%|█▊        | 5221/28080 [10:19:40<45:01:50,  7.09s/it]
                                                          
{'loss': 0.6446, 'learning_rate': 0.00046879713717345073, 'epoch': 2.23}

 19%|█▊        | 5221/28080 [10:19:40<45:01:50,  7.09s/it]
 19%|█▊        | 5222/28080 [10:19:48<45:11:15,  7.12s/it]
                                                          
{'loss': 0.6246, 'learning_rate': 0.0004687831855224073, 'epoch': 2.23}

 19%|█▊        | 5222/28080 [10:19:48<45:11:15,  7.12s/it]
 19%|█▊        | 5223/28080 [10:19:55<45:10:52,  7.12s/it]
                                                          
{'loss': 0.6499, 'learning_rate': 0.00046876923096067925, 'epoch': 2.23}

 19%|█▊        | 5223/28080 [10:19:55<45:10:52,  7.12s/it]
 19%|█▊        | 5224/28080 [10:20:02<45:09:01,  7.11s/it]
                                                          
{'loss': 0.6663, 'learning_rate': 0.0004687552734884523, 'epoch': 2.23}

 19%|█▊        | 5224/28080 [10:20:02<45:09:01,  7.11s/it]
 19%|█▊        | 5225/28080 [10:20:09<45:11:43,  7.12s/it]
                                                          
{'loss': 0.6446, 'learning_rate': 0.0004687413131059121, 'epoch': 2.23}

 19%|█▊        | 5225/28080 [10:20:09<45:11:43,  7.12s/it]
 19%|█▊        | 5226/28080 [10:20:16<45:04:04,  7.10s/it]
                                                          
{'loss': 0.6585, 'learning_rate': 0.0004687273498132444, 'epoch': 2.23}

 19%|█▊        | 5226/28080 [10:20:16<45:04:04,  7.10s/it]
 19%|█▊        | 5227/28080 [10:20:23<45:01:52,  7.09s/it]
                                                          
{'loss': 0.6684, 'learning_rate': 0.00046871338361063495, 'epoch': 2.23}

 19%|█▊        | 5227/28080 [10:20:23<45:01:52,  7.09s/it]
 19%|█▊        | 5228/28080 [10:20:30<45:08:12,  7.11s/it]
                                                          
{'loss': 0.6421, 'learning_rate': 0.0004686994144982696, 'epoch': 2.23}

 19%|█▊        | 5228/28080 [10:20:30<45:08:12,  7.11s/it]
 19%|█▊        | 5229/28080 [10:20:37<45:03:56,  7.10s/it]
                                                          
{'loss': 0.6641, 'learning_rate': 0.0004686854424763341, 'epoch': 2.23}

 19%|█▊        | 5229/28080 [10:20:37<45:03:56,  7.10s/it]
 19%|█▊        | 5230/28080 [10:20:44<45:01:12,  7.09s/it]
                                                          
{'loss': 0.6401, 'learning_rate': 0.00046867146754501446, 'epoch': 2.23}

 19%|█▊        | 5230/28080 [10:20:44<45:01:12,  7.09s/it]
 19%|█▊        | 5231/28080 [10:20:52<45:19:43,  7.14s/it]
                                                          
{'loss': 0.6263, 'learning_rate': 0.00046865748970449645, 'epoch': 2.23}

 19%|█▊        | 5231/28080 [10:20:52<45:19:43,  7.14s/it]
 19%|█▊        | 5232/28080 [10:20:59<45:16:24,  7.13s/it]
                                                          
{'loss': 0.6637, 'learning_rate': 0.00046864350895496615, 'epoch': 2.24}

 19%|█▊        | 5232/28080 [10:20:59<45:16:24,  7.13s/it]
 19%|█▊        | 5233/28080 [10:21:06<45:03:50,  7.10s/it]
                                                          
{'loss': 0.6769, 'learning_rate': 0.0004686295252966095, 'epoch': 2.24}

 19%|█▊        | 5233/28080 [10:21:06<45:03:50,  7.10s/it]
 19%|█▊        | 5234/28080 [10:21:13<45:08:36,  7.11s/it]
                                                          
{'loss': 0.649, 'learning_rate': 0.00046861553872961265, 'epoch': 2.24}

 19%|█▊        | 5234/28080 [10:21:13<45:08:36,  7.11s/it]
 19%|█▊        | 5235/28080 [10:21:20<45:13:30,  7.13s/it]
                                                          
{'loss': 0.6344, 'learning_rate': 0.00046860154925416154, 'epoch': 2.24}

 19%|█▊        | 5235/28080 [10:21:20<45:13:30,  7.13s/it]
 19%|█▊        | 5236/28080 [10:21:27<45:01:45,  7.10s/it]
                                                          
{'loss': 0.6243, 'learning_rate': 0.0004685875568704423, 'epoch': 2.24}

 19%|█▊        | 5236/28080 [10:21:27<45:01:45,  7.10s/it]
 19%|█▊        | 5237/28080 [10:21:34<44:44:42,  7.05s/it]
                                                          
{'loss': 0.675, 'learning_rate': 0.0004685735615786412, 'epoch': 2.24}

 19%|█▊        | 5237/28080 [10:21:34<44:44:42,  7.05s/it]
 19%|█▊        | 5238/28080 [10:21:41<44:55:08,  7.08s/it]
                                                          
{'loss': 0.6493, 'learning_rate': 0.0004685595633789443, 'epoch': 2.24}

 19%|█▊        | 5238/28080 [10:21:41<44:55:08,  7.08s/it]
 19%|█▊        | 5239/28080 [10:21:48<44:54:36,  7.08s/it]
                                                          
{'loss': 0.6338, 'learning_rate': 0.0004685455622715379, 'epoch': 2.24}

 19%|█▊        | 5239/28080 [10:21:48<44:54:36,  7.08s/it]
 19%|█▊        | 5240/28080 [10:21:55<45:01:15,  7.10s/it]
                                                          
{'loss': 0.6468, 'learning_rate': 0.0004685315582566082, 'epoch': 2.24}

 19%|█▊        | 5240/28080 [10:21:55<45:01:15,  7.10s/it]
 19%|█▊        | 5241/28080 [10:22:02<45:00:55,  7.10s/it]
                                                          
{'loss': 0.6451, 'learning_rate': 0.0004685175513343416, 'epoch': 2.24}

 19%|█▊        | 5241/28080 [10:22:02<45:00:55,  7.10s/it]
 19%|█▊        | 5242/28080 [10:22:09<44:41:50,  7.05s/it]
                                                          
{'loss': 0.6489, 'learning_rate': 0.00046850354150492445, 'epoch': 2.24}

 19%|█▊        | 5242/28080 [10:22:09<44:41:50,  7.05s/it]
 19%|█▊        | 5243/28080 [10:22:16<44:50:28,  7.07s/it]
                                                          
{'loss': 0.6523, 'learning_rate': 0.0004684895287685431, 'epoch': 2.24}

 19%|█▊        | 5243/28080 [10:22:16<44:50:28,  7.07s/it]
 19%|█▊        | 5244/28080 [10:22:24<44:55:25,  7.08s/it]
                                                          
{'loss': 0.6571, 'learning_rate': 0.00046847551312538397, 'epoch': 2.24}

 19%|█▊        | 5244/28080 [10:22:24<44:55:25,  7.08s/it]
 19%|█▊        | 5245/28080 [10:22:31<44:59:15,  7.09s/it]
                                                          
{'loss': 0.633, 'learning_rate': 0.00046846149457563347, 'epoch': 2.24}

 19%|█▊        | 5245/28080 [10:22:31<44:59:15,  7.09s/it]
 19%|█▊        | 5246/28080 [10:22:38<45:04:04,  7.11s/it]
                                                          
{'loss': 0.6304, 'learning_rate': 0.0004684474731194782, 'epoch': 2.24}

 19%|█▊        | 5246/28080 [10:22:38<45:04:04,  7.11s/it]
 19%|█▊        | 5247/28080 [10:22:45<45:10:24,  7.12s/it]
                                                          
{'loss': 0.6417, 'learning_rate': 0.00046843344875710464, 'epoch': 2.24}

 19%|█▊        | 5247/28080 [10:22:45<45:10:24,  7.12s/it]
 19%|█▊        | 5248/28080 [10:22:52<45:04:14,  7.11s/it]
                                                          
{'loss': 0.6395, 'learning_rate': 0.00046841942148869944, 'epoch': 2.24}

 19%|█▊        | 5248/28080 [10:22:52<45:04:14,  7.11s/it]
 19%|█▊        | 5249/28080 [10:22:59<45:10:20,  7.12s/it]
                                                          
{'loss': 0.6325, 'learning_rate': 0.000468405391314449, 'epoch': 2.24}

 19%|█▊        | 5249/28080 [10:22:59<45:10:20,  7.12s/it]
 19%|█▊        | 5250/28080 [10:23:06<44:58:03,  7.09s/it]
                                                          
{'loss': 0.6691, 'learning_rate': 0.00046839135823454036, 'epoch': 2.24}

 19%|█▊        | 5250/28080 [10:23:06<44:58:03,  7.09s/it]
 19%|█▊        | 5251/28080 [10:23:13<44:52:28,  7.08s/it]
                                                          
{'loss': 0.6647, 'learning_rate': 0.0004683773222491599, 'epoch': 2.24}

 19%|█▊        | 5251/28080 [10:23:13<44:52:28,  7.08s/it]
 19%|█▊        | 5252/28080 [10:23:20<44:52:04,  7.08s/it]
                                                          
{'loss': 0.6405, 'learning_rate': 0.00046836328335849445, 'epoch': 2.24}

 19%|█▊        | 5252/28080 [10:23:20<44:52:04,  7.08s/it]
 19%|█▊        | 5253/28080 [10:23:27<44:54:00,  7.08s/it]
                                                          
{'loss': 0.6255, 'learning_rate': 0.0004683492415627308, 'epoch': 2.24}

 19%|█▊        | 5253/28080 [10:23:27<44:54:00,  7.08s/it]
 19%|█▊        | 5254/28080 [10:23:35<44:51:09,  7.07s/it]
                                                          
{'loss': 0.6523, 'learning_rate': 0.0004683351968620558, 'epoch': 2.24}

 19%|█▊        | 5254/28080 [10:23:35<44:51:09,  7.07s/it]
 19%|█▊        | 5255/28080 [10:23:42<44:56:51,  7.09s/it]
                                                          
{'loss': 0.6471, 'learning_rate': 0.0004683211492566562, 'epoch': 2.24}

 19%|█▊        | 5255/28080 [10:23:42<44:56:51,  7.09s/it]
 19%|█▊        | 5256/28080 [10:23:49<44:50:27,  7.07s/it]
                                                          
{'loss': 0.6634, 'learning_rate': 0.00046830709874671897, 'epoch': 2.25}

 19%|█▊        | 5256/28080 [10:23:49<44:50:27,  7.07s/it]
 19%|█▊        | 5257/28080 [10:23:56<44:51:12,  7.07s/it]
                                                          
{'loss': 0.6412, 'learning_rate': 0.00046829304533243095, 'epoch': 2.25}

 19%|█▊        | 5257/28080 [10:23:56<44:51:12,  7.07s/it]
 19%|█▊        | 5258/28080 [10:24:03<44:52:34,  7.08s/it]
                                                          
{'loss': 0.6578, 'learning_rate': 0.0004682789890139792, 'epoch': 2.25}

 19%|█▊        | 5258/28080 [10:24:03<44:52:34,  7.08s/it]
 19%|█▊        | 5259/28080 [10:24:10<44:46:18,  7.06s/it]
                                                          
{'loss': 0.6895, 'learning_rate': 0.00046826492979155064, 'epoch': 2.25}

 19%|█▊        | 5259/28080 [10:24:10<44:46:18,  7.06s/it]
 19%|█▊        | 5260/28080 [10:24:17<44:46:39,  7.06s/it]
                                                          
{'loss': 0.6624, 'learning_rate': 0.0004682508676653324, 'epoch': 2.25}

 19%|█▊        | 5260/28080 [10:24:17<44:46:39,  7.06s/it]
 19%|█▊        | 5261/28080 [10:24:24<44:59:28,  7.10s/it]
                                                          
{'loss': 0.6395, 'learning_rate': 0.0004682368026355115, 'epoch': 2.25}

 19%|█▊        | 5261/28080 [10:24:24<44:59:28,  7.10s/it]
 19%|█▊        | 5262/28080 [10:24:31<45:03:09,  7.11s/it]
                                                          
{'loss': 0.643, 'learning_rate': 0.00046822273470227516, 'epoch': 2.25}

 19%|█▊        | 5262/28080 [10:24:31<45:03:09,  7.11s/it]
 19%|█▊        | 5263/28080 [10:24:38<44:49:53,  7.07s/it]
                                                          
{'loss': 0.6398, 'learning_rate': 0.00046820866386581043, 'epoch': 2.25}

 19%|█▊        | 5263/28080 [10:24:38<44:49:53,  7.07s/it]
 19%|█▊        | 5264/28080 [10:24:45<44:52:28,  7.08s/it]
                                                          
{'loss': 0.6378, 'learning_rate': 0.0004681945901263045, 'epoch': 2.25}

 19%|█▊        | 5264/28080 [10:24:45<44:52:28,  7.08s/it]
 19%|█▉        | 5265/28080 [10:24:52<44:56:46,  7.09s/it]
                                                          
{'loss': 0.6295, 'learning_rate': 0.00046818051348394466, 'epoch': 2.25}

 19%|█▉        | 5265/28080 [10:24:52<44:56:46,  7.09s/it]
 19%|█▉        | 5266/28080 [10:25:00<44:55:01,  7.09s/it]
                                                          
{'loss': 0.6484, 'learning_rate': 0.00046816643393891817, 'epoch': 2.25}

 19%|█▉        | 5266/28080 [10:25:00<44:55:01,  7.09s/it]
 19%|█▉        | 5267/28080 [10:25:07<45:00:09,  7.10s/it]
                                                          
{'loss': 0.6342, 'learning_rate': 0.0004681523514914123, 'epoch': 2.25}

 19%|█▉        | 5267/28080 [10:25:07<45:00:09,  7.10s/it]
 19%|█▉        | 5268/28080 [10:25:14<44:52:17,  7.08s/it]
                                                          
{'loss': 0.6536, 'learning_rate': 0.00046813826614161455, 'epoch': 2.25}

 19%|█▉        | 5268/28080 [10:25:14<44:52:17,  7.08s/it]
 19%|█▉        | 5269/28080 [10:25:21<44:56:34,  7.09s/it]
                                                          
{'loss': 0.6463, 'learning_rate': 0.0004681241778897122, 'epoch': 2.25}

 19%|█▉        | 5269/28080 [10:25:21<44:56:34,  7.09s/it]
 19%|█▉        | 5270/28080 [10:25:28<44:48:26,  7.07s/it]
                                                          
{'loss': 0.6568, 'learning_rate': 0.0004681100867358926, 'epoch': 2.25}

 19%|█▉        | 5270/28080 [10:25:28<44:48:26,  7.07s/it]
 19%|█▉        | 5271/28080 [10:25:35<45:02:06,  7.11s/it]
                                                          
{'loss': 0.6284, 'learning_rate': 0.0004680959926803434, 'epoch': 2.25}

 19%|█▉        | 5271/28080 [10:25:35<45:02:06,  7.11s/it]
 19%|█▉        | 5272/28080 [10:25:42<44:56:59,  7.09s/it]
                                                          
{'loss': 0.646, 'learning_rate': 0.00046808189572325194, 'epoch': 2.25}

 19%|█▉        | 5272/28080 [10:25:42<44:56:59,  7.09s/it]
 19%|█▉        | 5273/28080 [10:25:49<44:54:56,  7.09s/it]
                                                          
{'loss': 0.6586, 'learning_rate': 0.0004680677958648059, 'epoch': 2.25}

 19%|█▉        | 5273/28080 [10:25:49<44:54:56,  7.09s/it]
 19%|█▉        | 5274/28080 [10:25:56<44:52:26,  7.08s/it]
                                                          
{'loss': 0.6227, 'learning_rate': 0.00046805369310519277, 'epoch': 2.25}

 19%|█▉        | 5274/28080 [10:25:56<44:52:26,  7.08s/it]
 19%|█▉        | 5275/28080 [10:26:03<44:53:16,  7.09s/it]
                                                          
{'loss': 0.6496, 'learning_rate': 0.0004680395874446002, 'epoch': 2.25}

 19%|█▉        | 5275/28080 [10:26:03<44:53:16,  7.09s/it]
 19%|█▉        | 5276/28080 [10:26:10<44:50:28,  7.08s/it]
                                                          
{'loss': 0.6483, 'learning_rate': 0.0004680254788832159, 'epoch': 2.25}

 19%|█▉        | 5276/28080 [10:26:10<44:50:28,  7.08s/it]
 19%|█▉        | 5277/28080 [10:26:18<44:55:37,  7.09s/it]
                                                          
{'loss': 0.6323, 'learning_rate': 0.00046801136742122745, 'epoch': 2.25}

 19%|█▉        | 5277/28080 [10:26:18<44:55:37,  7.09s/it]
 19%|█▉        | 5278/28080 [10:26:24<44:39:31,  7.05s/it]
                                                          
{'loss': 0.6485, 'learning_rate': 0.00046799725305882276, 'epoch': 2.25}

 19%|█▉        | 5278/28080 [10:26:24<44:39:31,  7.05s/it]
 19%|█▉        | 5279/28080 [10:26:32<44:37:39,  7.05s/it]
                                                          
{'loss': 0.6466, 'learning_rate': 0.00046798313579618945, 'epoch': 2.26}

 19%|█▉        | 5279/28080 [10:26:32<44:37:39,  7.05s/it]
 19%|█▉        | 5280/28080 [10:26:39<44:39:35,  7.05s/it]
                                                          
{'loss': 0.6403, 'learning_rate': 0.0004679690156335154, 'epoch': 2.26}

 19%|█▉        | 5280/28080 [10:26:39<44:39:35,  7.05s/it]
 19%|█▉        | 5281/28080 [10:26:46<44:42:43,  7.06s/it]
                                                          
{'loss': 0.6317, 'learning_rate': 0.0004679548925709885, 'epoch': 2.26}

 19%|█▉        | 5281/28080 [10:26:46<44:42:43,  7.06s/it]
 19%|█▉        | 5282/28080 [10:26:53<44:54:16,  7.09s/it]
                                                          
{'loss': 0.6821, 'learning_rate': 0.0004679407666087966, 'epoch': 2.26}

 19%|█▉        | 5282/28080 [10:26:53<44:54:16,  7.09s/it]
 19%|█▉        | 5283/28080 [10:27:00<44:46:01,  7.07s/it]
                                                          
{'loss': 0.6466, 'learning_rate': 0.00046792663774712764, 'epoch': 2.26}

 19%|█▉        | 5283/28080 [10:27:00<44:46:01,  7.07s/it]
 19%|█▉        | 5284/28080 [10:27:07<44:53:11,  7.09s/it]
                                                          
{'loss': 0.6727, 'learning_rate': 0.00046791250598616954, 'epoch': 2.26}

 19%|█▉        | 5284/28080 [10:27:07<44:53:11,  7.09s/it]
 19%|█▉        | 5285/28080 [10:27:14<45:02:37,  7.11s/it]
                                                          
{'loss': 0.6639, 'learning_rate': 0.0004678983713261104, 'epoch': 2.26}

 19%|█▉        | 5285/28080 [10:27:14<45:02:37,  7.11s/it]
 19%|█▉        | 5286/28080 [10:27:21<45:05:43,  7.12s/it]
                                                          
{'loss': 0.6202, 'learning_rate': 0.0004678842337671382, 'epoch': 2.26}

 19%|█▉        | 5286/28080 [10:27:21<45:05:43,  7.12s/it]
 19%|█▉        | 5287/28080 [10:27:28<45:04:30,  7.12s/it]
                                                          
{'loss': 0.6371, 'learning_rate': 0.00046787009330944107, 'epoch': 2.26}

 19%|█▉        | 5287/28080 [10:27:28<45:04:30,  7.12s/it]
 19%|█▉        | 5288/28080 [10:27:36<45:15:48,  7.15s/it]
                                                          
{'loss': 0.6374, 'learning_rate': 0.0004678559499532071, 'epoch': 2.26}

 19%|█▉        | 5288/28080 [10:27:36<45:15:48,  7.15s/it]
 19%|█▉        | 5289/28080 [10:27:43<45:08:42,  7.13s/it]
                                                          
{'loss': 0.6404, 'learning_rate': 0.00046784180369862445, 'epoch': 2.26}

 19%|█▉        | 5289/28080 [10:27:43<45:08:42,  7.13s/it]
 19%|█▉        | 5290/28080 [10:27:50<45:00:53,  7.11s/it]
                                                          
{'loss': 0.6324, 'learning_rate': 0.0004678276545458814, 'epoch': 2.26}

 19%|█▉        | 5290/28080 [10:27:50<45:00:53,  7.11s/it]
 19%|█▉        | 5291/28080 [10:27:57<45:03:23,  7.12s/it]
                                                          
{'loss': 0.6431, 'learning_rate': 0.00046781350249516606, 'epoch': 2.26}

 19%|█▉        | 5291/28080 [10:27:57<45:03:23,  7.12s/it]
 19%|█▉        | 5292/28080 [10:28:04<45:04:17,  7.12s/it]
                                                          
{'loss': 0.6492, 'learning_rate': 0.00046779934754666676, 'epoch': 2.26}

 19%|█▉        | 5292/28080 [10:28:04<45:04:17,  7.12s/it]
 19%|█▉        | 5293/28080 [10:28:11<45:03:16,  7.12s/it]
                                                          
{'loss': 0.6472, 'learning_rate': 0.0004677851897005719, 'epoch': 2.26}

 19%|█▉        | 5293/28080 [10:28:11<45:03:16,  7.12s/it]
 19%|█▉        | 5294/28080 [10:28:18<44:56:46,  7.10s/it]
                                                          
{'loss': 0.6406, 'learning_rate': 0.00046777102895706967, 'epoch': 2.26}

 19%|█▉        | 5294/28080 [10:28:18<44:56:46,  7.10s/it]
 19%|█▉        | 5295/28080 [10:28:25<44:51:40,  7.09s/it]
                                                          
{'loss': 0.6561, 'learning_rate': 0.00046775686531634863, 'epoch': 2.26}

 19%|█▉        | 5295/28080 [10:28:25<44:51:40,  7.09s/it]
 19%|█▉        | 5296/28080 [10:28:32<44:43:00,  7.07s/it]
                                                          
{'loss': 0.623, 'learning_rate': 0.0004677426987785972, 'epoch': 2.26}

 19%|█▉        | 5296/28080 [10:28:32<44:43:00,  7.07s/it]
 19%|█▉        | 5297/28080 [10:28:39<44:48:46,  7.08s/it]
                                                          
{'loss': 0.6181, 'learning_rate': 0.00046772852934400373, 'epoch': 2.26}

 19%|█▉        | 5297/28080 [10:28:39<44:48:46,  7.08s/it]
 19%|█▉        | 5298/28080 [10:28:47<45:00:19,  7.11s/it]
                                                          
{'loss': 0.6344, 'learning_rate': 0.00046771435701275675, 'epoch': 2.26}

 19%|█▉        | 5298/28080 [10:28:47<45:00:19,  7.11s/it]
 19%|█▉        | 5299/28080 [10:28:54<45:02:47,  7.12s/it]
                                                          
{'loss': 0.6368, 'learning_rate': 0.0004677001817850449, 'epoch': 2.26}

 19%|█▉        | 5299/28080 [10:28:54<45:02:47,  7.12s/it]
 19%|█▉        | 5300/28080 [10:29:01<45:02:45,  7.12s/it]
                                                          
{'loss': 0.6503, 'learning_rate': 0.00046768600366105674, 'epoch': 2.26}

 19%|█▉        | 5300/28080 [10:29:01<45:02:45,  7.12s/it]
 19%|█▉        | 5301/28080 [10:29:08<45:04:13,  7.12s/it]
                                                          
{'loss': 0.6587, 'learning_rate': 0.0004676718226409809, 'epoch': 2.26}

 19%|█▉        | 5301/28080 [10:29:08<45:04:13,  7.12s/it]
 19%|█▉        | 5302/28080 [10:29:15<45:06:01,  7.13s/it]
                                                          
{'loss': 0.6406, 'learning_rate': 0.000467657638725006, 'epoch': 2.26}

 19%|█▉        | 5302/28080 [10:29:15<45:06:01,  7.13s/it]
 19%|█▉        | 5303/28080 [10:29:22<44:52:45,  7.09s/it]
                                                          
{'loss': 0.6417, 'learning_rate': 0.0004676434519133207, 'epoch': 2.27}

 19%|█▉        | 5303/28080 [10:29:22<44:52:45,  7.09s/it]
 19%|█▉        | 5304/28080 [10:29:29<44:52:13,  7.09s/it]
                                                          
{'loss': 0.6317, 'learning_rate': 0.00046762926220611387, 'epoch': 2.27}

 19%|█▉        | 5304/28080 [10:29:29<44:52:13,  7.09s/it]
 19%|█▉        | 5305/28080 [10:29:36<44:53:05,  7.09s/it]
                                                          
{'loss': 0.6548, 'learning_rate': 0.00046761506960357415, 'epoch': 2.27}

 19%|█▉        | 5305/28080 [10:29:36<44:53:05,  7.09s/it]
 19%|█▉        | 5306/28080 [10:29:43<44:58:15,  7.11s/it]
                                                          
{'loss': 0.6347, 'learning_rate': 0.00046760087410589046, 'epoch': 2.27}

 19%|█▉        | 5306/28080 [10:29:43<44:58:15,  7.11s/it]
 19%|█▉        | 5307/28080 [10:29:51<44:56:26,  7.10s/it]
                                                          
{'loss': 0.6502, 'learning_rate': 0.0004675866757132517, 'epoch': 2.27}

 19%|█▉        | 5307/28080 [10:29:51<44:56:26,  7.10s/it]
 19%|█▉        | 5308/28080 [10:29:58<44:43:58,  7.07s/it]
                                                          
{'loss': 0.6395, 'learning_rate': 0.0004675724744258466, 'epoch': 2.27}

 19%|█▉        | 5308/28080 [10:29:58<44:43:58,  7.07s/it]
 19%|█▉        | 5309/28080 [10:30:05<44:55:28,  7.10s/it]
                                                          
{'loss': 0.6308, 'learning_rate': 0.0004675582702438642, 'epoch': 2.27}

 19%|█▉        | 5309/28080 [10:30:05<44:55:28,  7.10s/it]
 19%|█▉        | 5310/28080 [10:30:12<44:55:13,  7.10s/it]
                                                          
{'loss': 0.6539, 'learning_rate': 0.00046754406316749356, 'epoch': 2.27}

 19%|█▉        | 5310/28080 [10:30:12<44:55:13,  7.10s/it]
 19%|█▉        | 5311/28080 [10:30:19<44:46:41,  7.08s/it]
                                                          
{'loss': 0.6524, 'learning_rate': 0.00046752985319692343, 'epoch': 2.27}

 19%|█▉        | 5311/28080 [10:30:19<44:46:41,  7.08s/it]
 19%|█▉        | 5312/28080 [10:30:26<44:43:06,  7.07s/it]
                                                          
{'loss': 0.6476, 'learning_rate': 0.00046751564033234314, 'epoch': 2.27}

 19%|█▉        | 5312/28080 [10:30:26<44:43:06,  7.07s/it]
 19%|█▉        | 5313/28080 [10:30:33<44:42:54,  7.07s/it]
                                                          
{'loss': 0.6639, 'learning_rate': 0.0004675014245739416, 'epoch': 2.27}

 19%|█▉        | 5313/28080 [10:30:33<44:42:54,  7.07s/it]
 19%|█▉        | 5314/28080 [10:30:40<44:50:42,  7.09s/it]
                                                          
{'loss': 0.6547, 'learning_rate': 0.000467487205921908, 'epoch': 2.27}

 19%|█▉        | 5314/28080 [10:30:40<44:50:42,  7.09s/it]
 19%|█▉        | 5315/28080 [10:30:47<44:49:09,  7.09s/it]
                                                          
{'loss': 0.6517, 'learning_rate': 0.00046747298437643147, 'epoch': 2.27}

 19%|█▉        | 5315/28080 [10:30:47<44:49:09,  7.09s/it]
 19%|█▉        | 5316/28080 [10:30:54<44:48:38,  7.09s/it]
                                                          
{'loss': 0.638, 'learning_rate': 0.0004674587599377013, 'epoch': 2.27}

 19%|█▉        | 5316/28080 [10:30:54<44:48:38,  7.09s/it]
 19%|█▉        | 5317/28080 [10:31:01<44:58:33,  7.11s/it]
                                                          
{'loss': 0.662, 'learning_rate': 0.00046744453260590655, 'epoch': 2.27}

 19%|█▉        | 5317/28080 [10:31:01<44:58:33,  7.11s/it]
 19%|█▉        | 5318/28080 [10:31:09<44:58:32,  7.11s/it]
                                                          
{'loss': 0.6484, 'learning_rate': 0.00046743030238123666, 'epoch': 2.27}

 19%|█▉        | 5318/28080 [10:31:09<44:58:32,  7.11s/it]
 19%|█▉        | 5319/28080 [10:31:16<45:04:24,  7.13s/it]
                                                          
{'loss': 0.6382, 'learning_rate': 0.00046741606926388105, 'epoch': 2.27}

 19%|█▉        | 5319/28080 [10:31:16<45:04:24,  7.13s/it]
 19%|█▉        | 5320/28080 [10:31:23<44:47:35,  7.09s/it]
                                                          
{'loss': 0.6432, 'learning_rate': 0.00046740183325402876, 'epoch': 2.27}

 19%|█▉        | 5320/28080 [10:31:23<44:47:35,  7.09s/it]
 19%|█▉        | 5321/28080 [10:31:30<44:57:30,  7.11s/it]
                                                          
{'loss': 0.6462, 'learning_rate': 0.0004673875943518694, 'epoch': 2.27}

 19%|█▉        | 5321/28080 [10:31:30<44:57:30,  7.11s/it]
 19%|█▉        | 5322/28080 [10:31:37<44:54:04,  7.10s/it]
                                                          
{'loss': 0.6405, 'learning_rate': 0.00046737335255759237, 'epoch': 2.27}

 19%|█▉        | 5322/28080 [10:31:37<44:54:04,  7.10s/it]
 19%|█▉        | 5323/28080 [10:31:44<44:50:10,  7.09s/it]
                                                          
{'loss': 0.67, 'learning_rate': 0.0004673591078713872, 'epoch': 2.27}

 19%|█▉        | 5323/28080 [10:31:44<44:50:10,  7.09s/it]
 19%|█▉        | 5324/28080 [10:31:51<44:42:05,  7.07s/it]
                                                          
{'loss': 0.6594, 'learning_rate': 0.00046734486029344327, 'epoch': 2.27}

 19%|█▉        | 5324/28080 [10:31:51<44:42:05,  7.07s/it]
 19%|█▉        | 5325/28080 [10:31:58<44:36:55,  7.06s/it]
                                                          
{'loss': 0.64, 'learning_rate': 0.0004673306098239502, 'epoch': 2.27}

 19%|█▉        | 5325/28080 [10:31:58<44:36:55,  7.06s/it]
 19%|█▉        | 5326/28080 [10:32:05<44:28:57,  7.04s/it]
                                                          
{'loss': 0.6477, 'learning_rate': 0.0004673163564630976, 'epoch': 2.28}

 19%|█▉        | 5326/28080 [10:32:05<44:28:57,  7.04s/it]
 19%|█▉        | 5327/28080 [10:32:12<44:26:35,  7.03s/it]
                                                          
{'loss': 0.6642, 'learning_rate': 0.00046730210021107507, 'epoch': 2.28}

 19%|█▉        | 5327/28080 [10:32:12<44:26:35,  7.03s/it]
 19%|█▉        | 5328/28080 [10:32:19<44:23:50,  7.02s/it]
                                                          
{'loss': 0.6554, 'learning_rate': 0.00046728784106807227, 'epoch': 2.28}

 19%|█▉        | 5328/28080 [10:32:19<44:23:50,  7.02s/it]
 19%|█▉        | 5329/28080 [10:32:26<44:35:17,  7.06s/it]
                                                          
{'loss': 0.6147, 'learning_rate': 0.00046727357903427884, 'epoch': 2.28}

 19%|█▉        | 5329/28080 [10:32:26<44:35:17,  7.06s/it]
 19%|█▉        | 5330/28080 [10:32:33<44:36:28,  7.06s/it]
                                                          
{'loss': 0.6373, 'learning_rate': 0.0004672593141098846, 'epoch': 2.28}

 19%|█▉        | 5330/28080 [10:32:33<44:36:28,  7.06s/it]
 19%|█▉        | 5331/28080 [10:32:40<44:37:37,  7.06s/it]
                                                          
{'loss': 0.6442, 'learning_rate': 0.00046724504629507945, 'epoch': 2.28}

 19%|█▉        | 5331/28080 [10:32:40<44:37:37,  7.06s/it]
 19%|█▉        | 5332/28080 [10:32:48<44:56:20,  7.11s/it]
                                                          
{'loss': 0.6522, 'learning_rate': 0.000467230775590053, 'epoch': 2.28}

 19%|█▉        | 5332/28080 [10:32:48<44:56:20,  7.11s/it]
 19%|█▉        | 5333/28080 [10:32:55<44:50:42,  7.10s/it]
                                                          
{'loss': 0.654, 'learning_rate': 0.0004672165019949952, 'epoch': 2.28}

 19%|█▉        | 5333/28080 [10:32:55<44:50:42,  7.10s/it]
 19%|█▉        | 5334/28080 [10:33:02<44:55:50,  7.11s/it]
                                                          
{'loss': 0.6384, 'learning_rate': 0.00046720222551009595, 'epoch': 2.28}

 19%|█▉        | 5334/28080 [10:33:02<44:55:50,  7.11s/it]
 19%|█▉        | 5335/28080 [10:33:09<44:45:00,  7.08s/it]
                                                          
{'loss': 0.6296, 'learning_rate': 0.00046718794613554506, 'epoch': 2.28}

 19%|█▉        | 5335/28080 [10:33:09<44:45:00,  7.08s/it]
 19%|█▉        | 5336/28080 [10:33:16<44:44:43,  7.08s/it]
                                                          
{'loss': 0.6496, 'learning_rate': 0.0004671736638715327, 'epoch': 2.28}

 19%|█▉        | 5336/28080 [10:33:16<44:44:43,  7.08s/it]
 19%|█▉        | 5337/28080 [10:33:23<44:32:56,  7.05s/it]
                                                          
{'loss': 0.6705, 'learning_rate': 0.00046715937871824874, 'epoch': 2.28}

 19%|█▉        | 5337/28080 [10:33:23<44:32:56,  7.05s/it]
 19%|█▉        | 5338/28080 [10:33:30<44:38:17,  7.07s/it]
                                                          
{'loss': 0.6608, 'learning_rate': 0.0004671450906758833, 'epoch': 2.28}

 19%|█▉        | 5338/28080 [10:33:30<44:38:17,  7.07s/it]
 19%|█▉        | 5339/28080 [10:33:37<44:35:58,  7.06s/it]
                                                          
{'loss': 0.6708, 'learning_rate': 0.0004671307997446265, 'epoch': 2.28}

 19%|█▉        | 5339/28080 [10:33:37<44:35:58,  7.06s/it]
 19%|█▉        | 5340/28080 [10:33:44<44:45:27,  7.09s/it]
                                                          
{'loss': 0.617, 'learning_rate': 0.0004671165059246684, 'epoch': 2.28}

 19%|█▉        | 5340/28080 [10:33:44<44:45:27,  7.09s/it]
 19%|█▉        | 5341/28080 [10:33:51<44:43:38,  7.08s/it]
                                                          
{'loss': 0.6398, 'learning_rate': 0.00046710220921619905, 'epoch': 2.28}

 19%|█▉        | 5341/28080 [10:33:51<44:43:38,  7.08s/it]
 19%|█▉        | 5342/28080 [10:33:58<44:28:34,  7.04s/it]
                                                          
{'loss': 0.6511, 'learning_rate': 0.00046708790961940886, 'epoch': 2.28}

 19%|█▉        | 5342/28080 [10:33:58<44:28:34,  7.04s/it]
 19%|█▉        | 5343/28080 [10:34:05<44:44:49,  7.08s/it]
                                                          
{'loss': 0.6258, 'learning_rate': 0.000467073607134488, 'epoch': 2.28}

 19%|█▉        | 5343/28080 [10:34:05<44:44:49,  7.08s/it]
 19%|█▉        | 5344/28080 [10:34:13<44:51:32,  7.10s/it]
                                                          
{'loss': 0.6913, 'learning_rate': 0.0004670593017616267, 'epoch': 2.28}

 19%|█▉        | 5344/28080 [10:34:13<44:51:32,  7.10s/it]
 19%|█▉        | 5345/28080 [10:34:20<44:51:29,  7.10s/it]
                                                          
{'loss': 0.6297, 'learning_rate': 0.00046704499350101535, 'epoch': 2.28}

 19%|█▉        | 5345/28080 [10:34:20<44:51:29,  7.10s/it]
 19%|█▉        | 5346/28080 [10:34:27<44:55:02,  7.11s/it]
                                                          
{'loss': 0.6177, 'learning_rate': 0.0004670306823528443, 'epoch': 2.28}

 19%|█▉        | 5346/28080 [10:34:27<44:55:02,  7.11s/it]
 19%|█▉        | 5347/28080 [10:34:34<45:01:34,  7.13s/it]
                                                          
{'loss': 0.6386, 'learning_rate': 0.00046701636831730385, 'epoch': 2.28}

 19%|█▉        | 5347/28080 [10:34:34<45:01:34,  7.13s/it]
 19%|█▉        | 5348/28080 [10:34:41<45:06:36,  7.14s/it]
                                                          
{'loss': 0.6428, 'learning_rate': 0.00046700205139458455, 'epoch': 2.28}

 19%|█▉        | 5348/28080 [10:34:41<45:06:36,  7.14s/it]
 19%|█▉        | 5349/28080 [10:34:48<45:01:07,  7.13s/it]
                                                          
{'loss': 0.6267, 'learning_rate': 0.00046698773158487686, 'epoch': 2.29}

 19%|█▉        | 5349/28080 [10:34:48<45:01:07,  7.13s/it]
 19%|█▉        | 5350/28080 [10:34:55<45:04:29,  7.14s/it]
                                                          
{'loss': 0.6538, 'learning_rate': 0.0004669734088883712, 'epoch': 2.29}

 19%|█▉        | 5350/28080 [10:34:55<45:04:29,  7.14s/it]
 19%|█▉        | 5351/28080 [10:35:02<44:49:01,  7.10s/it]
                                                          
{'loss': 0.6301, 'learning_rate': 0.00046695908330525817, 'epoch': 2.29}

 19%|█▉        | 5351/28080 [10:35:02<44:49:01,  7.10s/it]
 19%|█▉        | 5352/28080 [10:35:09<44:47:49,  7.10s/it]
                                                          
{'loss': 0.6433, 'learning_rate': 0.0004669447548357284, 'epoch': 2.29}

 19%|█▉        | 5352/28080 [10:35:09<44:47:49,  7.10s/it]
 19%|█▉        | 5353/28080 [10:35:16<44:39:14,  7.07s/it]
                                                          
{'loss': 0.6526, 'learning_rate': 0.00046693042347997245, 'epoch': 2.29}

 19%|█▉        | 5353/28080 [10:35:16<44:39:14,  7.07s/it]
 19%|█▉        | 5354/28080 [10:35:24<44:47:11,  7.09s/it]
                                                          
{'loss': 0.6424, 'learning_rate': 0.000466916089238181, 'epoch': 2.29}

 19%|█▉        | 5354/28080 [10:35:24<44:47:11,  7.09s/it]
 19%|█▉        | 5355/28080 [10:35:31<44:49:10,  7.10s/it]
                                                          
{'loss': 0.6298, 'learning_rate': 0.0004669017521105448, 'epoch': 2.29}

 19%|█▉        | 5355/28080 [10:35:31<44:49:10,  7.10s/it]
 19%|█▉        | 5356/28080 [10:35:38<44:46:57,  7.09s/it]
                                                          
{'loss': 0.6433, 'learning_rate': 0.0004668874120972545, 'epoch': 2.29}

 19%|█▉        | 5356/28080 [10:35:38<44:46:57,  7.09s/it]
 19%|█▉        | 5357/28080 [10:35:45<44:55:55,  7.12s/it]
                                                          
{'loss': 0.6349, 'learning_rate': 0.000466873069198501, 'epoch': 2.29}

 19%|█▉        | 5357/28080 [10:35:45<44:55:55,  7.12s/it]
 19%|█▉        | 5358/28080 [10:35:52<45:01:36,  7.13s/it]
                                                          
{'loss': 0.6522, 'learning_rate': 0.000466858723414475, 'epoch': 2.29}

 19%|█▉        | 5358/28080 [10:35:52<45:01:36,  7.13s/it]
 19%|█▉        | 5359/28080 [10:35:59<44:47:55,  7.10s/it]
                                                          
{'loss': 0.643, 'learning_rate': 0.00046684437474536745, 'epoch': 2.29}

 19%|█▉        | 5359/28080 [10:35:59<44:47:55,  7.10s/it]
 19%|█▉        | 5360/28080 [10:36:06<44:43:44,  7.09s/it]
                                                          
{'loss': 0.6551, 'learning_rate': 0.00046683002319136913, 'epoch': 2.29}

 19%|█▉        | 5360/28080 [10:36:06<44:43:44,  7.09s/it]
 19%|█▉        | 5361/28080 [10:36:13<44:53:57,  7.11s/it]
                                                          
{'loss': 0.6219, 'learning_rate': 0.0004668156687526711, 'epoch': 2.29}

 19%|█▉        | 5361/28080 [10:36:13<44:53:57,  7.11s/it]
 19%|█▉        | 5362/28080 [10:36:21<45:02:00,  7.14s/it]
                                                          
{'loss': 0.6343, 'learning_rate': 0.0004668013114294642, 'epoch': 2.29}

 19%|█▉        | 5362/28080 [10:36:21<45:02:00,  7.14s/it]
 19%|█▉        | 5363/28080 [10:36:28<45:08:14,  7.15s/it]
                                                          
{'loss': 0.639, 'learning_rate': 0.0004667869512219396, 'epoch': 2.29}

 19%|█▉        | 5363/28080 [10:36:28<45:08:14,  7.15s/it]
 19%|█▉        | 5364/28080 [10:36:35<45:05:50,  7.15s/it]
                                                          
{'loss': 0.6474, 'learning_rate': 0.00046677258813028824, 'epoch': 2.29}

 19%|█▉        | 5364/28080 [10:36:35<45:05:50,  7.15s/it]
 19%|█▉        | 5365/28080 [10:36:42<44:56:28,  7.12s/it]
                                                          
{'loss': 0.633, 'learning_rate': 0.0004667582221547012, 'epoch': 2.29}

 19%|█▉        | 5365/28080 [10:36:42<44:56:28,  7.12s/it]
 19%|█▉        | 5366/28080 [10:36:49<44:45:07,  7.09s/it]
                                                          
{'loss': 0.6511, 'learning_rate': 0.0004667438532953696, 'epoch': 2.29}

 19%|█▉        | 5366/28080 [10:36:49<44:45:07,  7.09s/it]
 19%|█▉        | 5367/28080 [10:36:56<44:40:49,  7.08s/it]
                                                          
{'loss': 0.6597, 'learning_rate': 0.0004667294815524847, 'epoch': 2.29}

 19%|█▉        | 5367/28080 [10:36:56<44:40:49,  7.08s/it]
 19%|█▉        | 5368/28080 [10:37:03<44:42:00,  7.09s/it]
                                                          
{'loss': 0.6533, 'learning_rate': 0.00046671510692623765, 'epoch': 2.29}

 19%|█▉        | 5368/28080 [10:37:03<44:42:00,  7.09s/it]
 19%|█▉        | 5369/28080 [10:37:10<44:44:43,  7.09s/it]
                                                          
{'loss': 0.6448, 'learning_rate': 0.0004667007294168196, 'epoch': 2.29}

 19%|█▉        | 5369/28080 [10:37:10<44:44:43,  7.09s/it]
 19%|█▉        | 5370/28080 [10:37:17<44:45:28,  7.10s/it]
                                                          
{'loss': 0.6662, 'learning_rate': 0.00046668634902442195, 'epoch': 2.29}

 19%|█▉        | 5370/28080 [10:37:17<44:45:28,  7.10s/it]
 19%|█▉        | 5371/28080 [10:37:25<44:50:21,  7.11s/it]
                                                          
{'loss': 0.6463, 'learning_rate': 0.000466671965749236, 'epoch': 2.29}

 19%|█▉        | 5371/28080 [10:37:25<44:50:21,  7.11s/it]
 19%|█▉        | 5372/28080 [10:37:32<44:52:12,  7.11s/it]
                                                          
{'loss': 0.6463, 'learning_rate': 0.00046665757959145305, 'epoch': 2.29}

 19%|█▉        | 5372/28080 [10:37:32<44:52:12,  7.11s/it]
 19%|█▉        | 5373/28080 [10:37:39<44:53:00,  7.12s/it]
                                                          
{'loss': 0.6644, 'learning_rate': 0.0004666431905512645, 'epoch': 2.3}

 19%|█▉        | 5373/28080 [10:37:39<44:53:00,  7.12s/it]
 19%|█▉        | 5374/28080 [10:37:46<44:49:46,  7.11s/it]
                                                          
{'loss': 0.6431, 'learning_rate': 0.00046662879862886174, 'epoch': 2.3}

 19%|█▉        | 5374/28080 [10:37:46<44:49:46,  7.11s/it]
 19%|█▉        | 5375/28080 [10:37:53<44:52:32,  7.12s/it]
                                                          
{'loss': 0.6398, 'learning_rate': 0.0004666144038244364, 'epoch': 2.3}

 19%|█▉        | 5375/28080 [10:37:53<44:52:32,  7.12s/it]
 19%|█▉        | 5376/28080 [10:38:00<44:50:04,  7.11s/it]
                                                          
{'loss': 0.6768, 'learning_rate': 0.0004666000061381799, 'epoch': 2.3}

 19%|█▉        | 5376/28080 [10:38:00<44:50:04,  7.11s/it]
 19%|█▉        | 5377/28080 [10:38:07<44:48:40,  7.11s/it]
                                                          
{'loss': 0.6557, 'learning_rate': 0.00046658560557028364, 'epoch': 2.3}

 19%|█▉        | 5377/28080 [10:38:07<44:48:40,  7.11s/it]
 19%|█▉        | 5378/28080 [10:38:14<44:57:51,  7.13s/it]
                                                          
{'loss': 0.66, 'learning_rate': 0.0004665712021209394, 'epoch': 2.3}

 19%|█▉        | 5378/28080 [10:38:14<44:57:51,  7.13s/it]
 19%|█▉        | 5379/28080 [10:38:21<44:52:30,  7.12s/it]
                                                          
{'loss': 0.6528, 'learning_rate': 0.00046655679579033876, 'epoch': 2.3}

 19%|█▉        | 5379/28080 [10:38:21<44:52:30,  7.12s/it]
 19%|█▉        | 5380/28080 [10:38:28<44:44:56,  7.10s/it]
                                                          
{'loss': 0.6502, 'learning_rate': 0.0004665423865786734, 'epoch': 2.3}

 19%|█▉        | 5380/28080 [10:38:28<44:44:56,  7.10s/it]
 19%|█▉        | 5381/28080 [10:38:36<44:44:17,  7.10s/it]
                                                          
{'loss': 0.6278, 'learning_rate': 0.0004665279744861349, 'epoch': 2.3}

 19%|█▉        | 5381/28080 [10:38:36<44:44:17,  7.10s/it]
 19%|█▉        | 5382/28080 [10:38:43<44:48:14,  7.11s/it]
                                                          
{'loss': 0.6558, 'learning_rate': 0.0004665135595129151, 'epoch': 2.3}

 19%|█▉        | 5382/28080 [10:38:43<44:48:14,  7.11s/it]
 19%|█▉        | 5383/28080 [10:38:50<44:45:25,  7.10s/it]
                                                          
{'loss': 0.6323, 'learning_rate': 0.00046649914165920584, 'epoch': 2.3}

 19%|█▉        | 5383/28080 [10:38:50<44:45:25,  7.10s/it]
 19%|█▉        | 5384/28080 [10:38:57<44:47:23,  7.10s/it]
                                                          
{'loss': 0.6613, 'learning_rate': 0.0004664847209251988, 'epoch': 2.3}

 19%|█▉        | 5384/28080 [10:38:57<44:47:23,  7.10s/it]
 19%|█▉        | 5385/28080 [10:39:04<44:55:17,  7.13s/it]
                                                          
{'loss': 0.6447, 'learning_rate': 0.0004664702973110858, 'epoch': 2.3}

 19%|█▉        | 5385/28080 [10:39:04<44:55:17,  7.13s/it]
 19%|█▉        | 5386/28080 [10:39:11<44:48:05,  7.11s/it]
                                                          
{'loss': 0.6423, 'learning_rate': 0.0004664558708170589, 'epoch': 2.3}

 19%|█▉        | 5386/28080 [10:39:11<44:48:05,  7.11s/it]
 19%|█▉        | 5387/28080 [10:39:18<44:48:00,  7.11s/it]
                                                          
{'loss': 0.6295, 'learning_rate': 0.0004664414414433099, 'epoch': 2.3}

 19%|█▉        | 5387/28080 [10:39:18<44:48:00,  7.11s/it]
 19%|█▉        | 5388/28080 [10:39:25<44:46:37,  7.10s/it]
                                                          
{'loss': 0.6526, 'learning_rate': 0.00046642700919003084, 'epoch': 2.3}

 19%|█▉        | 5388/28080 [10:39:25<44:46:37,  7.10s/it]
 19%|█▉        | 5389/28080 [10:39:33<44:53:45,  7.12s/it]
                                                          
{'loss': 0.6458, 'learning_rate': 0.00046641257405741367, 'epoch': 2.3}

 19%|█▉        | 5389/28080 [10:39:33<44:53:45,  7.12s/it]
 19%|█▉        | 5390/28080 [10:39:40<44:39:07,  7.08s/it]
                                                          
{'loss': 0.6328, 'learning_rate': 0.0004663981360456505, 'epoch': 2.3}

 19%|█▉        | 5390/28080 [10:39:40<44:39:07,  7.08s/it]
 19%|█▉        | 5391/28080 [10:39:47<44:45:19,  7.10s/it]
                                                          
{'loss': 0.6542, 'learning_rate': 0.00046638369515493336, 'epoch': 2.3}

 19%|█▉        | 5391/28080 [10:39:47<44:45:19,  7.10s/it]
 19%|█▉        | 5392/28080 [10:39:54<44:49:02,  7.11s/it]
                                                          
{'loss': 0.6574, 'learning_rate': 0.0004663692513854544, 'epoch': 2.3}

 19%|█▉        | 5392/28080 [10:39:54<44:49:02,  7.11s/it]
 19%|█▉        | 5393/28080 [10:40:01<44:45:49,  7.10s/it]
                                                          
{'loss': 0.6607, 'learning_rate': 0.00046635480473740577, 'epoch': 2.3}

 19%|█▉        | 5393/28080 [10:40:01<44:45:49,  7.10s/it]
 19%|█▉        | 5394/28080 [10:40:08<44:50:22,  7.12s/it]
                                                          
{'loss': 0.647, 'learning_rate': 0.0004663403552109796, 'epoch': 2.3}

 19%|█▉        | 5394/28080 [10:40:08<44:50:22,  7.12s/it]
 19%|█▉        | 5395/28080 [10:40:15<44:45:10,  7.10s/it]
                                                          
{'loss': 0.651, 'learning_rate': 0.0004663259028063682, 'epoch': 2.3}

 19%|█▉        | 5395/28080 [10:40:15<44:45:10,  7.10s/it]
 19%|█▉        | 5396/28080 [10:40:22<44:52:05,  7.12s/it]
                                                          
{'loss': 0.6444, 'learning_rate': 0.00046631144752376394, 'epoch': 2.31}

 19%|█▉        | 5396/28080 [10:40:22<44:52:05,  7.12s/it]
 19%|█▉        | 5397/28080 [10:40:29<44:44:25,  7.10s/it]
                                                          
{'loss': 0.624, 'learning_rate': 0.000466296989363359, 'epoch': 2.31}

 19%|█▉        | 5397/28080 [10:40:29<44:44:25,  7.10s/it]
 19%|█▉        | 5398/28080 [10:40:36<44:38:06,  7.08s/it]
                                                          
{'loss': 0.6503, 'learning_rate': 0.0004662825283253457, 'epoch': 2.31}

 19%|█▉        | 5398/28080 [10:40:36<44:38:06,  7.08s/it]
 19%|█▉        | 5399/28080 [10:40:43<44:31:15,  7.07s/it]
                                                          
{'loss': 0.6698, 'learning_rate': 0.0004662680644099164, 'epoch': 2.31}

 19%|█▉        | 5399/28080 [10:40:43<44:31:15,  7.07s/it]
 19%|█▉        | 5400/28080 [10:40:51<44:40:58,  7.09s/it]
                                                          
{'loss': 0.6395, 'learning_rate': 0.00046625359761726375, 'epoch': 2.31}

 19%|█▉        | 5400/28080 [10:40:51<44:40:58,  7.09s/it]
 19%|█▉        | 5401/28080 [10:40:58<44:33:39,  7.07s/it]
                                                          
{'loss': 0.6216, 'learning_rate': 0.00046623912794758007, 'epoch': 2.31}

 19%|█▉        | 5401/28080 [10:40:58<44:33:39,  7.07s/it]
 19%|█▉        | 5402/28080 [10:41:05<44:35:43,  7.08s/it]
                                                          
{'loss': 0.6405, 'learning_rate': 0.00046622465540105786, 'epoch': 2.31}

 19%|█▉        | 5402/28080 [10:41:05<44:35:43,  7.08s/it]
 19%|█▉        | 5403/28080 [10:41:12<44:37:25,  7.08s/it]
                                                          
{'loss': 0.6494, 'learning_rate': 0.00046621017997788963, 'epoch': 2.31}

 19%|█▉        | 5403/28080 [10:41:12<44:37:25,  7.08s/it]
 19%|█▉        | 5404/28080 [10:41:19<44:24:06,  7.05s/it]
                                                          
{'loss': 0.626, 'learning_rate': 0.0004661957016782681, 'epoch': 2.31}

 19%|█▉        | 5404/28080 [10:41:19<44:24:06,  7.05s/it]
 19%|█▉        | 5405/28080 [10:41:26<44:26:42,  7.06s/it]
                                                          
{'loss': 0.6165, 'learning_rate': 0.00046618122050238564, 'epoch': 2.31}

 19%|█▉        | 5405/28080 [10:41:26<44:26:42,  7.06s/it]
 19%|█▉        | 5406/28080 [10:41:33<44:24:18,  7.05s/it]
                                                          
{'loss': 0.649, 'learning_rate': 0.0004661667364504352, 'epoch': 2.31}

 19%|█▉        | 5406/28080 [10:41:33<44:24:18,  7.05s/it]
 19%|█▉        | 5407/28080 [10:41:40<44:27:08,  7.06s/it]
                                                          
{'loss': 0.6563, 'learning_rate': 0.00046615224952260934, 'epoch': 2.31}

 19%|█▉        | 5407/28080 [10:41:40<44:27:08,  7.06s/it]
 19%|█▉        | 5408/28080 [10:41:47<44:20:08,  7.04s/it]
                                                          
{'loss': 0.633, 'learning_rate': 0.0004661377597191007, 'epoch': 2.31}

 19%|█▉        | 5408/28080 [10:41:47<44:20:08,  7.04s/it]
 19%|█▉        | 5409/28080 [10:41:54<44:21:55,  7.04s/it]
                                                          
{'loss': 0.6405, 'learning_rate': 0.0004661232670401022, 'epoch': 2.31}

 19%|█▉        | 5409/28080 [10:41:54<44:21:55,  7.04s/it]
 19%|█▉        | 5410/28080 [10:42:01<44:21:02,  7.04s/it]
                                                          
{'loss': 0.6741, 'learning_rate': 0.0004661087714858066, 'epoch': 2.31}

 19%|█▉        | 5410/28080 [10:42:01<44:21:02,  7.04s/it]
 19%|█▉        | 5411/28080 [10:42:08<44:35:05,  7.08s/it]
                                                          
{'loss': 0.6476, 'learning_rate': 0.0004660942730564067, 'epoch': 2.31}

 19%|█▉        | 5411/28080 [10:42:08<44:35:05,  7.08s/it]
 19%|█▉        | 5412/28080 [10:42:15<44:39:21,  7.09s/it]
                                                          
{'loss': 0.6473, 'learning_rate': 0.0004660797717520955, 'epoch': 2.31}

 19%|█▉        | 5412/28080 [10:42:15<44:39:21,  7.09s/it]
 19%|█▉        | 5413/28080 [10:42:22<44:50:49,  7.12s/it]
                                                          
{'loss': 0.664, 'learning_rate': 0.0004660652675730658, 'epoch': 2.31}

 19%|█▉        | 5413/28080 [10:42:22<44:50:49,  7.12s/it]
 19%|█▉        | 5414/28080 [10:42:30<44:49:03,  7.12s/it]
                                                          
{'loss': 0.6443, 'learning_rate': 0.0004660507605195107, 'epoch': 2.31}

 19%|█▉        | 5414/28080 [10:42:30<44:49:03,  7.12s/it]
 19%|█▉        | 5415/28080 [10:42:37<44:49:28,  7.12s/it]
                                                          
{'loss': 0.6374, 'learning_rate': 0.00046603625059162305, 'epoch': 2.31}

 19%|█▉        | 5415/28080 [10:42:37<44:49:28,  7.12s/it]
 19%|█▉        | 5416/28080 [10:42:44<44:54:05,  7.13s/it]
                                                          
{'loss': 0.6217, 'learning_rate': 0.0004660217377895959, 'epoch': 2.31}

 19%|█▉        | 5416/28080 [10:42:44<44:54:05,  7.13s/it]
 19%|█▉        | 5417/28080 [10:42:51<44:45:11,  7.11s/it]
                                                          
{'loss': 0.6518, 'learning_rate': 0.00046600722211362247, 'epoch': 2.31}

 19%|█▉        | 5417/28080 [10:42:51<44:45:11,  7.11s/it]
 19%|█▉        | 5418/28080 [10:42:58<44:46:07,  7.11s/it]
                                                          
{'loss': 0.6318, 'learning_rate': 0.00046599270356389576, 'epoch': 2.31}

 19%|█▉        | 5418/28080 [10:42:58<44:46:07,  7.11s/it]
 19%|█▉        | 5419/28080 [10:43:05<44:55:48,  7.14s/it]
                                                          
{'loss': 0.6272, 'learning_rate': 0.00046597818214060894, 'epoch': 2.31}

 19%|█▉        | 5419/28080 [10:43:05<44:55:48,  7.14s/it]
 19%|█▉        | 5420/28080 [10:43:12<44:35:49,  7.09s/it]
                                                          
{'loss': 0.6562, 'learning_rate': 0.0004659636578439552, 'epoch': 2.32}

 19%|█▉        | 5420/28080 [10:43:12<44:35:49,  7.09s/it]
 19%|█▉        | 5421/28080 [10:43:19<44:34:20,  7.08s/it]
                                                          
{'loss': 0.6447, 'learning_rate': 0.00046594913067412794, 'epoch': 2.32}

 19%|█▉        | 5421/28080 [10:43:19<44:34:20,  7.08s/it]
 19%|█▉        | 5422/28080 [10:43:26<44:43:09,  7.11s/it]
                                                          
{'loss': 0.6224, 'learning_rate': 0.0004659346006313201, 'epoch': 2.32}

 19%|█▉        | 5422/28080 [10:43:26<44:43:09,  7.11s/it]
 19%|█▉        | 5423/28080 [10:43:33<44:23:17,  7.05s/it]
                                                          
{'loss': 0.654, 'learning_rate': 0.00046592006771572526, 'epoch': 2.32}

 19%|█▉        | 5423/28080 [10:43:33<44:23:17,  7.05s/it]
 19%|█▉        | 5424/28080 [10:43:41<44:37:28,  7.09s/it]
                                                          
{'loss': 0.653, 'learning_rate': 0.00046590553192753665, 'epoch': 2.32}

 19%|█▉        | 5424/28080 [10:43:41<44:37:28,  7.09s/it]
 19%|█▉        | 5425/28080 [10:43:48<44:40:11,  7.10s/it]
                                                          
{'loss': 0.6421, 'learning_rate': 0.0004658909932669477, 'epoch': 2.32}

 19%|█▉        | 5425/28080 [10:43:48<44:40:11,  7.10s/it]
 19%|█▉        | 5426/28080 [10:43:55<44:46:46,  7.12s/it]
                                                          
{'loss': 0.6313, 'learning_rate': 0.0004658764517341517, 'epoch': 2.32}

 19%|█▉        | 5426/28080 [10:43:55<44:46:46,  7.12s/it]
 19%|█▉        | 5427/28080 [10:44:02<44:47:51,  7.12s/it]
                                                          
{'loss': 0.6644, 'learning_rate': 0.0004658619073293423, 'epoch': 2.32}

 19%|█▉        | 5427/28080 [10:44:02<44:47:51,  7.12s/it]
 19%|█▉        | 5428/28080 [10:44:09<44:38:56,  7.10s/it]
                                                          
{'loss': 0.6453, 'learning_rate': 0.00046584736005271293, 'epoch': 2.32}

 19%|█▉        | 5428/28080 [10:44:09<44:38:56,  7.10s/it]
 19%|█▉        | 5429/28080 [10:44:16<44:50:31,  7.13s/it]
                                                          
{'loss': 0.6447, 'learning_rate': 0.0004658328099044571, 'epoch': 2.32}

 19%|█▉        | 5429/28080 [10:44:16<44:50:31,  7.13s/it]
 19%|█▉        | 5430/28080 [10:44:23<44:59:32,  7.15s/it]
                                                          
{'loss': 0.6458, 'learning_rate': 0.0004658182568847684, 'epoch': 2.32}

 19%|█▉        | 5430/28080 [10:44:23<44:59:32,  7.15s/it]
 19%|█▉        | 5431/28080 [10:44:30<44:52:44,  7.13s/it]
                                                          
{'loss': 0.6379, 'learning_rate': 0.0004658037009938404, 'epoch': 2.32}

 19%|█▉        | 5431/28080 [10:44:30<44:52:44,  7.13s/it]
 19%|█▉        | 5432/28080 [10:44:38<44:48:22,  7.12s/it]
                                                          
{'loss': 0.6363, 'learning_rate': 0.00046578914223186684, 'epoch': 2.32}

 19%|█▉        | 5432/28080 [10:44:38<44:48:22,  7.12s/it]
 19%|█▉        | 5433/28080 [10:44:45<44:47:56,  7.12s/it]
                                                          
{'loss': 0.6343, 'learning_rate': 0.0004657745805990413, 'epoch': 2.32}

 19%|█▉        | 5433/28080 [10:44:45<44:47:56,  7.12s/it]
 19%|█▉        | 5434/28080 [10:44:52<44:39:16,  7.10s/it]
                                                          
{'loss': 0.6474, 'learning_rate': 0.0004657600160955576, 'epoch': 2.32}

 19%|█▉        | 5434/28080 [10:44:52<44:39:16,  7.10s/it]
 19%|█▉        | 5435/28080 [10:44:59<44:38:53,  7.10s/it]
                                                          
{'loss': 0.6329, 'learning_rate': 0.0004657454487216095, 'epoch': 2.32}

 19%|█▉        | 5435/28080 [10:44:59<44:38:53,  7.10s/it]
 19%|█▉        | 5436/28080 [10:45:06<44:33:52,  7.08s/it]
                                                          
{'loss': 0.6392, 'learning_rate': 0.0004657308784773908, 'epoch': 2.32}

 19%|█▉        | 5436/28080 [10:45:06<44:33:52,  7.08s/it]
 19%|█▉        | 5437/28080 [10:45:13<44:41:14,  7.10s/it]
                                                          
{'loss': 0.6345, 'learning_rate': 0.0004657163053630953, 'epoch': 2.32}

 19%|█▉        | 5437/28080 [10:45:13<44:41:14,  7.10s/it]
 19%|█▉        | 5438/28080 [10:45:20<44:30:31,  7.08s/it]
                                                          
{'loss': 0.656, 'learning_rate': 0.00046570172937891686, 'epoch': 2.32}

 19%|█▉        | 5438/28080 [10:45:20<44:30:31,  7.08s/it]
 19%|█▉        | 5439/28080 [10:45:27<44:25:24,  7.06s/it]
                                                          
{'loss': 0.6317, 'learning_rate': 0.00046568715052504946, 'epoch': 2.32}

 19%|█▉        | 5439/28080 [10:45:27<44:25:24,  7.06s/it]
 19%|█▉        | 5440/28080 [10:45:34<44:08:46,  7.02s/it]
                                                          
{'loss': 0.6406, 'learning_rate': 0.000465672568801687, 'epoch': 2.32}

 19%|█▉        | 5440/28080 [10:45:34<44:08:46,  7.02s/it]
 19%|█▉        | 5441/28080 [10:45:41<44:15:03,  7.04s/it]
                                                          
{'loss': 0.6181, 'learning_rate': 0.00046565798420902354, 'epoch': 2.32}

 19%|█▉        | 5441/28080 [10:45:41<44:15:03,  7.04s/it]
 19%|█▉        | 5442/28080 [10:45:48<44:22:08,  7.06s/it]
                                                          
{'loss': 0.6611, 'learning_rate': 0.00046564339674725307, 'epoch': 2.32}

 19%|█▉        | 5442/28080 [10:45:48<44:22:08,  7.06s/it]
 19%|█▉        | 5443/28080 [10:45:55<44:30:20,  7.08s/it]
                                                          
{'loss': 0.6406, 'learning_rate': 0.0004656288064165697, 'epoch': 2.33}

 19%|█▉        | 5443/28080 [10:45:55<44:30:20,  7.08s/it]
 19%|█▉        | 5444/28080 [10:46:02<44:27:50,  7.07s/it]
                                                          
{'loss': 0.6608, 'learning_rate': 0.00046561421321716744, 'epoch': 2.33}

 19%|█▉        | 5444/28080 [10:46:02<44:27:50,  7.07s/it]
 19%|█▉        | 5445/28080 [10:46:09<44:28:11,  7.07s/it]
                                                          
{'loss': 0.6793, 'learning_rate': 0.0004655996171492406, 'epoch': 2.33}

 19%|█▉        | 5445/28080 [10:46:09<44:28:11,  7.07s/it]
 19%|█▉        | 5446/28080 [10:46:17<44:28:34,  7.07s/it]
                                                          
{'loss': 0.634, 'learning_rate': 0.0004655850182129833, 'epoch': 2.33}

 19%|█▉        | 5446/28080 [10:46:17<44:28:34,  7.07s/it]
 19%|█▉        | 5447/28080 [10:46:24<44:33:45,  7.09s/it]
                                                          
{'loss': 0.6364, 'learning_rate': 0.00046557041640858963, 'epoch': 2.33}

 19%|█▉        | 5447/28080 [10:46:24<44:33:45,  7.09s/it]
 19%|█▉        | 5448/28080 [10:46:31<44:24:42,  7.06s/it]
                                                          
{'loss': 0.6632, 'learning_rate': 0.00046555581173625404, 'epoch': 2.33}

 19%|█▉        | 5448/28080 [10:46:31<44:24:42,  7.06s/it]
 19%|█▉        | 5449/28080 [10:46:38<44:35:54,  7.09s/it]
                                                          
{'loss': 0.6544, 'learning_rate': 0.00046554120419617075, 'epoch': 2.33}

 19%|█▉        | 5449/28080 [10:46:38<44:35:54,  7.09s/it]
 19%|█▉        | 5450/28080 [10:46:45<44:24:39,  7.06s/it]
                                                          
{'loss': 0.6461, 'learning_rate': 0.00046552659378853404, 'epoch': 2.33}

 19%|█▉        | 5450/28080 [10:46:45<44:24:39,  7.06s/it]
 19%|█▉        | 5451/28080 [10:46:52<44:29:14,  7.08s/it]
                                                          
{'loss': 0.6528, 'learning_rate': 0.00046551198051353836, 'epoch': 2.33}

 19%|█▉        | 5451/28080 [10:46:52<44:29:14,  7.08s/it]
 19%|█▉        | 5452/28080 [10:46:59<44:37:25,  7.10s/it]
                                                          
{'loss': 0.6413, 'learning_rate': 0.0004654973643713781, 'epoch': 2.33}

 19%|█▉        | 5452/28080 [10:46:59<44:37:25,  7.10s/it]
 19%|█▉        | 5453/28080 [10:47:06<44:44:48,  7.12s/it]
                                                          
{'loss': 0.6434, 'learning_rate': 0.00046548274536224775, 'epoch': 2.33}

 19%|█▉        | 5453/28080 [10:47:06<44:44:48,  7.12s/it]
 19%|█▉        | 5454/28080 [10:47:13<44:47:03,  7.13s/it]
                                                          
{'loss': 0.6362, 'learning_rate': 0.00046546812348634183, 'epoch': 2.33}

 19%|█▉        | 5454/28080 [10:47:13<44:47:03,  7.13s/it]
 19%|█▉        | 5455/28080 [10:47:21<44:47:23,  7.13s/it]
                                                          
{'loss': 0.6595, 'learning_rate': 0.0004654534987438547, 'epoch': 2.33}

 19%|█▉        | 5455/28080 [10:47:21<44:47:23,  7.13s/it]
 19%|█▉        | 5456/28080 [10:47:28<44:52:05,  7.14s/it]
                                                          
{'loss': 0.6248, 'learning_rate': 0.0004654388711349812, 'epoch': 2.33}

 19%|█▉        | 5456/28080 [10:47:28<44:52:05,  7.14s/it]
 19%|█▉        | 5457/28080 [10:47:35<44:34:53,  7.09s/it]
                                                          
{'loss': 0.6556, 'learning_rate': 0.00046542424065991564, 'epoch': 2.33}

 19%|█▉        | 5457/28080 [10:47:35<44:34:53,  7.09s/it]
 19%|█▉        | 5458/28080 [10:47:42<44:29:15,  7.08s/it]
                                                          
{'loss': 0.6423, 'learning_rate': 0.00046540960731885283, 'epoch': 2.33}

 19%|█▉        | 5458/28080 [10:47:42<44:29:15,  7.08s/it]
 19%|█▉        | 5459/28080 [10:47:49<44:49:40,  7.13s/it]
                                                          
{'loss': 0.6237, 'learning_rate': 0.0004653949711119874, 'epoch': 2.33}

 19%|█▉        | 5459/28080 [10:47:49<44:49:40,  7.13s/it]
 19%|█▉        | 5460/28080 [10:47:56<44:43:37,  7.12s/it]
                                                          
{'loss': 0.6467, 'learning_rate': 0.00046538033203951415, 'epoch': 2.33}

 19%|█▉        | 5460/28080 [10:47:56<44:43:37,  7.12s/it]
 19%|█▉        | 5461/28080 [10:48:03<44:39:08,  7.11s/it]
                                                          
{'loss': 0.6405, 'learning_rate': 0.0004653656901016277, 'epoch': 2.33}

 19%|█▉        | 5461/28080 [10:48:03<44:39:08,  7.11s/it]
 19%|█▉        | 5462/28080 [10:48:10<44:55:43,  7.15s/it]
                                                          
{'loss': 0.6466, 'learning_rate': 0.000465351045298523, 'epoch': 2.33}

 19%|█▉        | 5462/28080 [10:48:10<44:55:43,  7.15s/it]
 19%|█▉        | 5463/28080 [10:48:18<44:54:32,  7.15s/it]
                                                          
{'loss': 0.6223, 'learning_rate': 0.00046533639763039476, 'epoch': 2.33}

 19%|█▉        | 5463/28080 [10:48:18<44:54:32,  7.15s/it]
 19%|█▉        | 5464/28080 [10:48:25<44:46:01,  7.13s/it]
                                                          
{'loss': 0.6326, 'learning_rate': 0.0004653217470974379, 'epoch': 2.33}

 19%|█▉        | 5464/28080 [10:48:25<44:46:01,  7.13s/it]
 19%|█▉        | 5465/28080 [10:48:32<44:29:07,  7.08s/it]
                                                          
{'loss': 0.6665, 'learning_rate': 0.00046530709369984734, 'epoch': 2.33}

 19%|█▉        | 5465/28080 [10:48:32<44:29:07,  7.08s/it]
 19%|█▉        | 5466/28080 [10:48:39<44:42:27,  7.12s/it]
                                                          
{'loss': 0.6446, 'learning_rate': 0.00046529243743781803, 'epoch': 2.34}

 19%|█▉        | 5466/28080 [10:48:39<44:42:27,  7.12s/it]
 19%|█▉        | 5467/28080 [10:48:46<44:40:28,  7.11s/it]
                                                          
{'loss': 0.6489, 'learning_rate': 0.00046527777831154493, 'epoch': 2.34}

 19%|█▉        | 5467/28080 [10:48:46<44:40:28,  7.11s/it]
 19%|█▉        | 5468/28080 [10:48:53<44:23:31,  7.07s/it]
                                                          
{'loss': 0.6587, 'learning_rate': 0.0004652631163212231, 'epoch': 2.34}

 19%|█▉        | 5468/28080 [10:48:53<44:23:31,  7.07s/it]
 19%|█▉        | 5469/28080 [10:49:00<44:19:03,  7.06s/it]
                                                          
{'loss': 0.6337, 'learning_rate': 0.00046524845146704753, 'epoch': 2.34}

 19%|█▉        | 5469/28080 [10:49:00<44:19:03,  7.06s/it]
 19%|█▉        | 5470/28080 [10:49:07<44:29:54,  7.09s/it]
                                                          
{'loss': 0.6463, 'learning_rate': 0.00046523378374921343, 'epoch': 2.34}

 19%|█▉        | 5470/28080 [10:49:07<44:29:54,  7.09s/it]
 19%|█▉        | 5471/28080 [10:49:14<44:34:14,  7.10s/it]
                                                          
{'loss': 0.6508, 'learning_rate': 0.00046521911316791585, 'epoch': 2.34}

 19%|█▉        | 5471/28080 [10:49:14<44:34:14,  7.10s/it]
 19%|█▉        | 5472/28080 [10:49:21<44:37:52,  7.11s/it]
                                                          
{'loss': 0.6532, 'learning_rate': 0.00046520443972335, 'epoch': 2.34}

 19%|█▉        | 5472/28080 [10:49:21<44:37:52,  7.11s/it]
 19%|█▉        | 5473/28080 [10:49:28<44:34:15,  7.10s/it]
                                                          
{'loss': 0.6237, 'learning_rate': 0.0004651897634157112, 'epoch': 2.34}

 19%|█▉        | 5473/28080 [10:49:28<44:34:15,  7.10s/it]
 19%|█▉        | 5474/28080 [10:49:35<44:19:31,  7.06s/it]
                                                          
{'loss': 0.6365, 'learning_rate': 0.00046517508424519444, 'epoch': 2.34}

 19%|█▉        | 5474/28080 [10:49:35<44:19:31,  7.06s/it]
 19%|█▉        | 5475/28080 [10:49:42<44:23:36,  7.07s/it]
                                                          
{'loss': 0.6536, 'learning_rate': 0.00046516040221199526, 'epoch': 2.34}

 19%|█▉        | 5475/28080 [10:49:42<44:23:36,  7.07s/it]
 20%|█▉        | 5476/28080 [10:49:50<44:30:07,  7.09s/it]
                                                          
{'loss': 0.6388, 'learning_rate': 0.0004651457173163088, 'epoch': 2.34}

 20%|█▉        | 5476/28080 [10:49:50<44:30:07,  7.09s/it]
 20%|█▉        | 5477/28080 [10:49:57<44:42:11,  7.12s/it]
                                                          
{'loss': 0.6336, 'learning_rate': 0.00046513102955833064, 'epoch': 2.34}

 20%|█▉        | 5477/28080 [10:49:57<44:42:11,  7.12s/it]
 20%|█▉        | 5478/28080 [10:50:04<44:29:01,  7.09s/it]
                                                          
{'loss': 0.6654, 'learning_rate': 0.000465116338938256, 'epoch': 2.34}

 20%|█▉        | 5478/28080 [10:50:04<44:29:01,  7.09s/it]
 20%|█▉        | 5479/28080 [10:50:11<44:36:46,  7.11s/it]
                                                          
{'loss': 0.6397, 'learning_rate': 0.00046510164545628043, 'epoch': 2.34}

 20%|█▉        | 5479/28080 [10:50:11<44:36:46,  7.11s/it]
 20%|█▉        | 5480/28080 [10:50:18<44:30:17,  7.09s/it]
                                                          
{'loss': 0.6531, 'learning_rate': 0.00046508694911259936, 'epoch': 2.34}

 20%|█▉        | 5480/28080 [10:50:18<44:30:17,  7.09s/it]
 20%|█▉        | 5481/28080 [10:50:25<44:29:22,  7.09s/it]
                                                          
{'loss': 0.629, 'learning_rate': 0.0004650722499074083, 'epoch': 2.34}

 20%|█▉        | 5481/28080 [10:50:25<44:29:22,  7.09s/it]
 20%|█▉        | 5482/28080 [10:50:32<44:32:17,  7.10s/it]
                                                          
{'loss': 0.6519, 'learning_rate': 0.00046505754784090285, 'epoch': 2.34}

 20%|█▉        | 5482/28080 [10:50:32<44:32:17,  7.10s/it]
 20%|█▉        | 5483/28080 [10:50:39<44:27:06,  7.08s/it]
                                                          
{'loss': 0.6673, 'learning_rate': 0.0004650428429132786, 'epoch': 2.34}

 20%|█▉        | 5483/28080 [10:50:39<44:27:06,  7.08s/it]
 20%|█▉        | 5484/28080 [10:50:46<44:27:18,  7.08s/it]
                                                          
{'loss': 0.6528, 'learning_rate': 0.0004650281351247312, 'epoch': 2.34}

 20%|█▉        | 5484/28080 [10:50:46<44:27:18,  7.08s/it]
 20%|█▉        | 5485/28080 [10:50:53<44:27:47,  7.08s/it]
                                                          
{'loss': 0.6468, 'learning_rate': 0.00046501342447545626, 'epoch': 2.34}

 20%|█▉        | 5485/28080 [10:50:53<44:27:47,  7.08s/it]
 20%|█▉        | 5486/28080 [10:51:00<44:24:30,  7.08s/it]
                                                          
{'loss': 0.6513, 'learning_rate': 0.0004649987109656495, 'epoch': 2.34}

 20%|█▉        | 5486/28080 [10:51:00<44:24:30,  7.08s/it]
 20%|█▉        | 5487/28080 [10:51:08<44:25:34,  7.08s/it]
                                                          
{'loss': 0.6362, 'learning_rate': 0.00046498399459550673, 'epoch': 2.34}

 20%|█▉        | 5487/28080 [10:51:08<44:25:34,  7.08s/it]
 20%|█▉        | 5488/28080 [10:51:15<44:18:54,  7.06s/it]
                                                          
{'loss': 0.6373, 'learning_rate': 0.0004649692753652237, 'epoch': 2.34}

 20%|█▉        | 5488/28080 [10:51:15<44:18:54,  7.06s/it]
 20%|█▉        | 5489/28080 [10:51:22<44:23:51,  7.08s/it]
                                                          
{'loss': 0.645, 'learning_rate': 0.0004649545532749962, 'epoch': 2.34}

 20%|█▉        | 5489/28080 [10:51:22<44:23:51,  7.08s/it]
 20%|█▉        | 5490/28080 [10:51:29<44:27:21,  7.08s/it]
                                                          
{'loss': 0.6437, 'learning_rate': 0.0004649398283250201, 'epoch': 2.35}

 20%|█▉        | 5490/28080 [10:51:29<44:27:21,  7.08s/it]
 20%|█▉        | 5491/28080 [10:51:36<44:19:48,  7.06s/it]
                                                          
{'loss': 0.6501, 'learning_rate': 0.0004649251005154914, 'epoch': 2.35}

 20%|█▉        | 5491/28080 [10:51:36<44:19:48,  7.06s/it]
 20%|█▉        | 5492/28080 [10:51:43<44:13:59,  7.05s/it]
                                                          
{'loss': 0.6513, 'learning_rate': 0.00046491036984660594, 'epoch': 2.35}

 20%|█▉        | 5492/28080 [10:51:43<44:13:59,  7.05s/it]
 20%|█▉        | 5493/28080 [10:51:50<44:13:47,  7.05s/it]
                                                          
{'loss': 0.6609, 'learning_rate': 0.00046489563631855975, 'epoch': 2.35}

 20%|█▉        | 5493/28080 [10:51:50<44:13:47,  7.05s/it]
 20%|█▉        | 5494/28080 [10:51:57<44:20:42,  7.07s/it]
                                                          
{'loss': 0.6457, 'learning_rate': 0.00046488089993154875, 'epoch': 2.35}

 20%|█▉        | 5494/28080 [10:51:57<44:20:42,  7.07s/it]
 20%|█▉        | 5495/28080 [10:52:04<44:24:09,  7.08s/it]
                                                          
{'loss': 0.6333, 'learning_rate': 0.0004648661606857691, 'epoch': 2.35}

 20%|█▉        | 5495/28080 [10:52:04<44:24:09,  7.08s/it]
 20%|█▉        | 5496/28080 [10:52:11<44:17:36,  7.06s/it]
                                                          
{'loss': 0.6526, 'learning_rate': 0.00046485141858141683, 'epoch': 2.35}

 20%|█▉        | 5496/28080 [10:52:11<44:17:36,  7.06s/it]
 20%|█▉        | 5497/28080 [10:52:18<44:27:51,  7.09s/it]
                                                          
{'loss': 0.6337, 'learning_rate': 0.0004648366736186881, 'epoch': 2.35}

 20%|█▉        | 5497/28080 [10:52:18<44:27:51,  7.09s/it]
 20%|█▉        | 5498/28080 [10:52:25<44:34:08,  7.11s/it]
                                                          
{'loss': 0.6385, 'learning_rate': 0.00046482192579777907, 'epoch': 2.35}

 20%|█▉        | 5498/28080 [10:52:25<44:34:08,  7.11s/it]
 20%|█▉        | 5499/28080 [10:52:32<44:34:37,  7.11s/it]
                                                          
{'loss': 0.6303, 'learning_rate': 0.0004648071751188859, 'epoch': 2.35}

 20%|█▉        | 5499/28080 [10:52:32<44:34:37,  7.11s/it]
 20%|█▉        | 5500/28080 [10:52:39<44:23:29,  7.08s/it]
                                                          
{'loss': 0.6375, 'learning_rate': 0.00046479242158220486, 'epoch': 2.35}

 20%|█▉        | 5500/28080 [10:52:39<44:23:29,  7.08s/it]
 20%|█▉        | 5501/28080 [10:52:47<44:25:06,  7.08s/it]
                                                          
{'loss': 0.6552, 'learning_rate': 0.0004647776651879323, 'epoch': 2.35}

 20%|█▉        | 5501/28080 [10:52:47<44:25:06,  7.08s/it]
 20%|█▉        | 5502/28080 [10:52:54<44:24:13,  7.08s/it]
                                                          
{'loss': 0.6494, 'learning_rate': 0.0004647629059362644, 'epoch': 2.35}

 20%|█▉        | 5502/28080 [10:52:54<44:24:13,  7.08s/it]
 20%|█▉        | 5503/28080 [10:53:01<44:29:03,  7.09s/it]
                                                          
{'loss': 0.637, 'learning_rate': 0.00046474814382739765, 'epoch': 2.35}

 20%|█▉        | 5503/28080 [10:53:01<44:29:03,  7.09s/it]
 20%|█▉        | 5504/28080 [10:53:08<44:38:32,  7.12s/it]
                                                          
{'loss': 0.6612, 'learning_rate': 0.0004647333788615284, 'epoch': 2.35}

 20%|█▉        | 5504/28080 [10:53:08<44:38:32,  7.12s/it]
 20%|█▉        | 5505/28080 [10:53:15<44:38:44,  7.12s/it]
                                                          
{'loss': 0.6557, 'learning_rate': 0.00046471861103885307, 'epoch': 2.35}

 20%|█▉        | 5505/28080 [10:53:15<44:38:44,  7.12s/it]
 20%|█▉        | 5506/28080 [10:53:22<44:32:47,  7.10s/it]
                                                          
{'loss': 0.6597, 'learning_rate': 0.0004647038403595681, 'epoch': 2.35}

 20%|█▉        | 5506/28080 [10:53:22<44:32:47,  7.10s/it]
 20%|█▉        | 5507/28080 [10:53:29<44:41:02,  7.13s/it]
                                                          
{'loss': 0.6395, 'learning_rate': 0.00046468906682387, 'epoch': 2.35}

 20%|█▉        | 5507/28080 [10:53:29<44:41:02,  7.13s/it]
 20%|█▉        | 5508/28080 [10:53:36<44:38:57,  7.12s/it]
                                                          
{'loss': 0.6448, 'learning_rate': 0.00046467429043195544, 'epoch': 2.35}

 20%|█▉        | 5508/28080 [10:53:36<44:38:57,  7.12s/it]
 20%|█▉        | 5509/28080 [10:53:44<44:39:33,  7.12s/it]
                                                          
{'loss': 0.6496, 'learning_rate': 0.0004646595111840208, 'epoch': 2.35}

 20%|█▉        | 5509/28080 [10:53:44<44:39:33,  7.12s/it]
 20%|█▉        | 5510/28080 [10:53:51<44:28:34,  7.09s/it]
                                                          
{'loss': 0.6432, 'learning_rate': 0.0004646447290802629, 'epoch': 2.35}

 20%|█▉        | 5510/28080 [10:53:51<44:28:34,  7.09s/it]
 20%|█▉        | 5511/28080 [10:53:58<44:39:08,  7.12s/it]
                                                          
{'loss': 0.6518, 'learning_rate': 0.00046462994412087836, 'epoch': 2.35}

 20%|█▉        | 5511/28080 [10:53:58<44:39:08,  7.12s/it]
 20%|█▉        | 5512/28080 [10:54:05<44:49:09,  7.15s/it]
                                                          
{'loss': 0.6331, 'learning_rate': 0.0004646151563060638, 'epoch': 2.35}

 20%|█▉        | 5512/28080 [10:54:05<44:49:09,  7.15s/it]
 20%|█▉        | 5513/28080 [10:54:12<44:43:55,  7.14s/it]
                                                          
{'loss': 0.64, 'learning_rate': 0.00046460036563601595, 'epoch': 2.36}

 20%|█▉        | 5513/28080 [10:54:12<44:43:55,  7.14s/it]
 20%|█▉        | 5514/28080 [10:54:19<44:38:01,  7.12s/it]
                                                          
{'loss': 0.6502, 'learning_rate': 0.0004645855721109316, 'epoch': 2.36}

 20%|█▉        | 5514/28080 [10:54:19<44:38:01,  7.12s/it]
 20%|█▉        | 5515/28080 [10:54:26<44:27:23,  7.09s/it]
                                                          
{'loss': 0.6661, 'learning_rate': 0.0004645707757310076, 'epoch': 2.36}

 20%|█▉        | 5515/28080 [10:54:26<44:27:23,  7.09s/it]
 20%|█▉        | 5516/28080 [10:54:33<44:27:13,  7.09s/it]
                                                          
{'loss': 0.6309, 'learning_rate': 0.0004645559764964409, 'epoch': 2.36}

 20%|█▉        | 5516/28080 [10:54:33<44:27:13,  7.09s/it]
 20%|█▉        | 5517/28080 [10:54:40<44:25:13,  7.09s/it]
                                                          
{'loss': 0.6448, 'learning_rate': 0.0004645411744074282, 'epoch': 2.36}

 20%|█▉        | 5517/28080 [10:54:40<44:25:13,  7.09s/it]
 20%|█▉        | 5518/28080 [10:54:47<44:20:25,  7.07s/it]
                                                          
{'loss': 0.6462, 'learning_rate': 0.0004645263694641665, 'epoch': 2.36}

 20%|█▉        | 5518/28080 [10:54:47<44:20:25,  7.07s/it]
 20%|█▉        | 5519/28080 [10:54:54<44:17:42,  7.07s/it]
                                                          
{'loss': 0.644, 'learning_rate': 0.0004645115616668527, 'epoch': 2.36}

 20%|█▉        | 5519/28080 [10:54:54<44:17:42,  7.07s/it]
 20%|█▉        | 5520/28080 [10:55:02<44:18:25,  7.07s/it]
                                                          
{'loss': 0.6348, 'learning_rate': 0.000464496751015684, 'epoch': 2.36}

 20%|█▉        | 5520/28080 [10:55:02<44:18:25,  7.07s/it]
 20%|█▉        | 5521/28080 [10:55:09<44:25:03,  7.09s/it]
                                                          
{'loss': 0.6347, 'learning_rate': 0.00046448193751085724, 'epoch': 2.36}

 20%|█▉        | 5521/28080 [10:55:09<44:25:03,  7.09s/it]
 20%|█▉        | 5522/28080 [10:55:16<44:32:40,  7.11s/it]
                                                          
{'loss': 0.6431, 'learning_rate': 0.00046446712115256957, 'epoch': 2.36}

 20%|█▉        | 5522/28080 [10:55:16<44:32:40,  7.11s/it]
 20%|█▉        | 5523/28080 [10:55:23<44:20:09,  7.08s/it]
                                                          
{'loss': 0.6699, 'learning_rate': 0.0004644523019410181, 'epoch': 2.36}

 20%|█▉        | 5523/28080 [10:55:23<44:20:09,  7.08s/it]
 20%|█▉        | 5524/28080 [10:55:30<44:14:10,  7.06s/it]
                                                          
{'loss': 0.6465, 'learning_rate': 0.00046443747987640006, 'epoch': 2.36}

 20%|█▉        | 5524/28080 [10:55:30<44:14:10,  7.06s/it]
 20%|█▉        | 5525/28080 [10:55:37<44:16:22,  7.07s/it]
                                                          
{'loss': 0.6706, 'learning_rate': 0.00046442265495891244, 'epoch': 2.36}

 20%|█▉        | 5525/28080 [10:55:37<44:16:22,  7.07s/it]
 20%|█▉        | 5526/28080 [10:55:44<44:31:01,  7.11s/it]
                                                          
{'loss': 0.6571, 'learning_rate': 0.00046440782718875273, 'epoch': 2.36}

 20%|█▉        | 5526/28080 [10:55:44<44:31:01,  7.11s/it]
 20%|█▉        | 5527/28080 [10:55:51<44:37:04,  7.12s/it]
                                                          
{'loss': 0.6289, 'learning_rate': 0.000464392996566118, 'epoch': 2.36}

 20%|█▉        | 5527/28080 [10:55:51<44:37:04,  7.12s/it]
 20%|█▉        | 5528/28080 [10:55:58<44:26:32,  7.09s/it]
                                                          
{'loss': 0.6597, 'learning_rate': 0.00046437816309120573, 'epoch': 2.36}

 20%|█▉        | 5528/28080 [10:55:58<44:26:32,  7.09s/it]
 20%|█▉        | 5529/28080 [10:56:05<44:25:20,  7.09s/it]
                                                          
{'loss': 0.6305, 'learning_rate': 0.000464363326764213, 'epoch': 2.36}

 20%|█▉        | 5529/28080 [10:56:05<44:25:20,  7.09s/it]
 20%|█▉        | 5530/28080 [10:56:13<44:27:36,  7.10s/it]
                                                          
{'loss': 0.6308, 'learning_rate': 0.0004643484875853375, 'epoch': 2.36}

 20%|█▉        | 5530/28080 [10:56:13<44:27:36,  7.10s/it]
 20%|█▉        | 5531/28080 [10:56:20<44:36:54,  7.12s/it]
                                                          
{'loss': 0.6297, 'learning_rate': 0.0004643336455547764, 'epoch': 2.36}

 20%|█▉        | 5531/28080 [10:56:20<44:36:54,  7.12s/it]
 20%|█▉        | 5532/28080 [10:56:27<44:37:40,  7.13s/it]
                                                          
{'loss': 0.6295, 'learning_rate': 0.00046431880067272736, 'epoch': 2.36}

 20%|█▉        | 5532/28080 [10:56:27<44:37:40,  7.13s/it]
 20%|█▉        | 5533/28080 [10:56:34<44:34:44,  7.12s/it]
                                                          
{'loss': 0.6232, 'learning_rate': 0.0004643039529393877, 'epoch': 2.36}

 20%|█▉        | 5533/28080 [10:56:34<44:34:44,  7.12s/it]
 20%|█▉        | 5534/28080 [10:56:41<44:19:08,  7.08s/it]
                                                          
{'loss': 0.6429, 'learning_rate': 0.0004642891023549551, 'epoch': 2.36}

 20%|█▉        | 5534/28080 [10:56:41<44:19:08,  7.08s/it]
 20%|█▉        | 5535/28080 [10:56:48<44:15:46,  7.07s/it]
                                                          
{'loss': 0.6486, 'learning_rate': 0.00046427424891962697, 'epoch': 2.36}

 20%|█▉        | 5535/28080 [10:56:48<44:15:46,  7.07s/it]
 20%|█▉        | 5536/28080 [10:56:55<44:28:24,  7.10s/it]
                                                          
{'loss': 0.6472, 'learning_rate': 0.00046425939263360105, 'epoch': 2.36}

 20%|█▉        | 5536/28080 [10:56:55<44:28:24,  7.10s/it]
 20%|█▉        | 5537/28080 [10:57:02<44:14:23,  7.06s/it]
                                                          
{'loss': 0.6367, 'learning_rate': 0.00046424453349707496, 'epoch': 2.37}

 20%|█▉        | 5537/28080 [10:57:02<44:14:23,  7.06s/it]
 20%|█▉        | 5538/28080 [10:57:09<44:29:05,  7.10s/it]
                                                          
{'loss': 0.6312, 'learning_rate': 0.0004642296715102464, 'epoch': 2.37}

 20%|█▉        | 5538/28080 [10:57:09<44:29:05,  7.10s/it]
 20%|█▉        | 5539/28080 [10:57:16<44:24:53,  7.09s/it]
                                                          
{'loss': 0.6449, 'learning_rate': 0.00046421480667331307, 'epoch': 2.37}

 20%|█▉        | 5539/28080 [10:57:16<44:24:53,  7.09s/it]
 20%|█▉        | 5540/28080 [10:57:23<44:15:29,  7.07s/it]
                                                          
{'loss': 0.6546, 'learning_rate': 0.0004641999389864727, 'epoch': 2.37}

 20%|█▉        | 5540/28080 [10:57:23<44:15:29,  7.07s/it]
 20%|█▉        | 5541/28080 [10:57:30<44:13:20,  7.06s/it]
                                                          
{'loss': 0.6241, 'learning_rate': 0.0004641850684499231, 'epoch': 2.37}

 20%|█▉        | 5541/28080 [10:57:30<44:13:20,  7.06s/it]
 20%|█▉        | 5542/28080 [10:57:38<44:19:54,  7.08s/it]
                                                          
{'loss': 0.64, 'learning_rate': 0.00046417019506386217, 'epoch': 2.37}

 20%|█▉        | 5542/28080 [10:57:38<44:19:54,  7.08s/it]
 20%|█▉        | 5543/28080 [10:57:45<44:23:31,  7.09s/it]
                                                          
{'loss': 0.6404, 'learning_rate': 0.0004641553188284877, 'epoch': 2.37}

 20%|█▉        | 5543/28080 [10:57:45<44:23:31,  7.09s/it]
 20%|█▉        | 5544/28080 [10:57:52<44:22:10,  7.09s/it]
                                                          
{'loss': 0.6412, 'learning_rate': 0.00046414043974399766, 'epoch': 2.37}

 20%|█▉        | 5544/28080 [10:57:52<44:22:10,  7.09s/it]
 20%|█▉        | 5545/28080 [10:57:59<44:18:19,  7.08s/it]
                                                          
{'loss': 0.6663, 'learning_rate': 0.00046412555781059006, 'epoch': 2.37}

 20%|█▉        | 5545/28080 [10:57:59<44:18:19,  7.08s/it]
 20%|█▉        | 5546/28080 [10:58:06<44:23:06,  7.09s/it]
                                                          
{'loss': 0.6601, 'learning_rate': 0.0004641106730284627, 'epoch': 2.37}

 20%|█▉        | 5546/28080 [10:58:06<44:23:06,  7.09s/it]
 20%|█▉        | 5547/28080 [10:58:13<44:17:45,  7.08s/it]
                                                          
{'loss': 0.6295, 'learning_rate': 0.00046409578539781377, 'epoch': 2.37}

 20%|█▉        | 5547/28080 [10:58:13<44:17:45,  7.08s/it]
 20%|█▉        | 5548/28080 [10:58:20<44:24:36,  7.10s/it]
                                                          
{'loss': 0.6458, 'learning_rate': 0.0004640808949188413, 'epoch': 2.37}

 20%|█▉        | 5548/28080 [10:58:20<44:24:36,  7.10s/it]
 20%|█▉        | 5549/28080 [10:58:27<44:22:36,  7.09s/it]
                                                          
{'loss': 0.6647, 'learning_rate': 0.0004640660015917434, 'epoch': 2.37}

 20%|█▉        | 5549/28080 [10:58:27<44:22:36,  7.09s/it]
 20%|█▉        | 5550/28080 [10:58:34<44:32:39,  7.12s/it]
                                                          
{'loss': 0.6386, 'learning_rate': 0.00046405110541671815, 'epoch': 2.37}

 20%|█▉        | 5550/28080 [10:58:34<44:32:39,  7.12s/it]
 20%|█▉        | 5551/28080 [10:58:41<44:30:04,  7.11s/it]
                                                          
{'loss': 0.6344, 'learning_rate': 0.0004640362063939637, 'epoch': 2.37}

 20%|█▉        | 5551/28080 [10:58:41<44:30:04,  7.11s/it]
 20%|█▉        | 5552/28080 [10:58:48<44:18:42,  7.08s/it]
                                                          
{'loss': 0.6318, 'learning_rate': 0.0004640213045236784, 'epoch': 2.37}

 20%|█▉        | 5552/28080 [10:58:48<44:18:42,  7.08s/it]
 20%|█▉        | 5553/28080 [10:58:56<44:18:08,  7.08s/it]
                                                          
{'loss': 0.6385, 'learning_rate': 0.0004640063998060605, 'epoch': 2.37}

 20%|█▉        | 5553/28080 [10:58:56<44:18:08,  7.08s/it]
 20%|█▉        | 5554/28080 [10:59:03<44:25:13,  7.10s/it]
                                                          
{'loss': 0.6352, 'learning_rate': 0.0004639914922413081, 'epoch': 2.37}

 20%|█▉        | 5554/28080 [10:59:03<44:25:13,  7.10s/it]
 20%|█▉        | 5555/28080 [10:59:10<44:18:35,  7.08s/it]
                                                          
{'loss': 0.6585, 'learning_rate': 0.00046397658182961975, 'epoch': 2.37}

 20%|█▉        | 5555/28080 [10:59:10<44:18:35,  7.08s/it]
 20%|█▉        | 5556/28080 [10:59:17<44:21:19,  7.09s/it]
                                                          
{'loss': 0.6549, 'learning_rate': 0.0004639616685711937, 'epoch': 2.37}

 20%|█▉        | 5556/28080 [10:59:17<44:21:19,  7.09s/it]
 20%|█▉        | 5557/28080 [10:59:24<44:30:38,  7.11s/it]
                                                          
{'loss': 0.6299, 'learning_rate': 0.0004639467524662284, 'epoch': 2.37}

 20%|█▉        | 5557/28080 [10:59:24<44:30:38,  7.11s/it]
 20%|█▉        | 5558/28080 [10:59:31<44:37:53,  7.13s/it]
                                                          
{'loss': 0.6185, 'learning_rate': 0.0004639318335149223, 'epoch': 2.37}

 20%|█▉        | 5558/28080 [10:59:31<44:37:53,  7.13s/it]
 20%|█▉        | 5559/28080 [10:59:38<44:51:56,  7.17s/it]
                                                          
{'loss': 0.6609, 'learning_rate': 0.00046391691171747374, 'epoch': 2.37}

 20%|█▉        | 5559/28080 [10:59:38<44:51:56,  7.17s/it]
 20%|█▉        | 5560/28080 [10:59:46<44:44:47,  7.15s/it]
                                                          
{'loss': 0.6391, 'learning_rate': 0.0004639019870740815, 'epoch': 2.38}

 20%|█▉        | 5560/28080 [10:59:46<44:44:47,  7.15s/it]
 20%|█▉        | 5561/28080 [10:59:53<44:35:59,  7.13s/it]
                                                          
{'loss': 0.6484, 'learning_rate': 0.0004638870595849439, 'epoch': 2.38}

 20%|█▉        | 5561/28080 [10:59:53<44:35:59,  7.13s/it]
 20%|█▉        | 5562/28080 [11:00:00<44:36:11,  7.13s/it]
                                                          
{'loss': 0.6274, 'learning_rate': 0.0004638721292502597, 'epoch': 2.38}

 20%|█▉        | 5562/28080 [11:00:00<44:36:11,  7.13s/it]
 20%|█▉        | 5563/28080 [11:00:07<44:20:22,  7.09s/it]
                                                          
{'loss': 0.6432, 'learning_rate': 0.00046385719607022736, 'epoch': 2.38}

 20%|█▉        | 5563/28080 [11:00:07<44:20:22,  7.09s/it]
 20%|█▉        | 5564/28080 [11:00:14<44:16:00,  7.08s/it]
                                                          
{'loss': 0.6536, 'learning_rate': 0.0004638422600450457, 'epoch': 2.38}

 20%|█▉        | 5564/28080 [11:00:14<44:16:00,  7.08s/it]
 20%|█▉        | 5565/28080 [11:00:21<44:14:28,  7.07s/it]
                                                          
{'loss': 0.6287, 'learning_rate': 0.00046382732117491337, 'epoch': 2.38}

 20%|█▉        | 5565/28080 [11:00:21<44:14:28,  7.07s/it]
 20%|█▉        | 5566/28080 [11:00:28<44:09:56,  7.06s/it]
                                                          
{'loss': 0.6486, 'learning_rate': 0.0004638123794600291, 'epoch': 2.38}

 20%|█▉        | 5566/28080 [11:00:28<44:09:56,  7.06s/it]
 20%|█▉        | 5567/28080 [11:00:35<44:01:48,  7.04s/it]
                                                          
{'loss': 0.6459, 'learning_rate': 0.0004637974349005918, 'epoch': 2.38}

 20%|█▉        | 5567/28080 [11:00:35<44:01:48,  7.04s/it]
 20%|█▉        | 5568/28080 [11:00:42<44:17:56,  7.08s/it]
                                                          
{'loss': 0.6437, 'learning_rate': 0.0004637824874968001, 'epoch': 2.38}

 20%|█▉        | 5568/28080 [11:00:42<44:17:56,  7.08s/it]
 20%|█▉        | 5569/28080 [11:00:49<44:22:34,  7.10s/it]
                                                          
{'loss': 0.6692, 'learning_rate': 0.000463767537248853, 'epoch': 2.38}

 20%|█▉        | 5569/28080 [11:00:49<44:22:34,  7.10s/it]
 20%|█▉        | 5570/28080 [11:00:56<44:18:08,  7.09s/it]
                                                          
{'loss': 0.6465, 'learning_rate': 0.0004637525841569493, 'epoch': 2.38}

 20%|█▉        | 5570/28080 [11:00:56<44:18:08,  7.09s/it]
 20%|█▉        | 5571/28080 [11:01:03<44:14:57,  7.08s/it]
                                                          
{'loss': 0.6301, 'learning_rate': 0.000463737628221288, 'epoch': 2.38}

 20%|█▉        | 5571/28080 [11:01:03<44:14:57,  7.08s/it]
 20%|█▉        | 5572/28080 [11:01:10<44:22:04,  7.10s/it]
                                                          
{'loss': 0.6305, 'learning_rate': 0.0004637226694420681, 'epoch': 2.38}

 20%|█▉        | 5572/28080 [11:01:10<44:22:04,  7.10s/it]
 20%|█▉        | 5573/28080 [11:01:18<44:18:03,  7.09s/it]
                                                          
{'loss': 0.6393, 'learning_rate': 0.0004637077078194885, 'epoch': 2.38}

 20%|█▉        | 5573/28080 [11:01:18<44:18:03,  7.09s/it]
 20%|█▉        | 5574/28080 [11:01:25<44:25:28,  7.11s/it]
                                                          
{'loss': 0.6298, 'learning_rate': 0.0004636927433537483, 'epoch': 2.38}

 20%|█▉        | 5574/28080 [11:01:25<44:25:28,  7.11s/it]
 20%|█▉        | 5575/28080 [11:01:32<44:20:14,  7.09s/it]
                                                          
{'loss': 0.6541, 'learning_rate': 0.00046367777604504676, 'epoch': 2.38}

 20%|█▉        | 5575/28080 [11:01:32<44:20:14,  7.09s/it]
 20%|█▉        | 5576/28080 [11:01:39<44:15:30,  7.08s/it]
                                                          
{'loss': 0.6464, 'learning_rate': 0.0004636628058935827, 'epoch': 2.38}

 20%|█▉        | 5576/28080 [11:01:39<44:15:30,  7.08s/it]
 20%|█▉        | 5577/28080 [11:01:46<44:25:08,  7.11s/it]
                                                          
{'loss': 0.6405, 'learning_rate': 0.00046364783289955545, 'epoch': 2.38}

 20%|█▉        | 5577/28080 [11:01:46<44:25:08,  7.11s/it]
 20%|█▉        | 5578/28080 [11:01:53<44:34:26,  7.13s/it]
                                                          
{'loss': 0.6516, 'learning_rate': 0.00046363285706316426, 'epoch': 2.38}

 20%|█▉        | 5578/28080 [11:01:53<44:34:26,  7.13s/it]
 20%|█▉        | 5579/28080 [11:02:00<44:23:50,  7.10s/it]
                                                          
{'loss': 0.6286, 'learning_rate': 0.0004636178783846082, 'epoch': 2.38}

 20%|█▉        | 5579/28080 [11:02:00<44:23:50,  7.10s/it]
 20%|█▉        | 5580/28080 [11:02:07<44:34:26,  7.13s/it]
                                                          
{'loss': 0.6456, 'learning_rate': 0.00046360289686408676, 'epoch': 2.38}

 20%|█▉        | 5580/28080 [11:02:07<44:34:26,  7.13s/it]
 20%|█▉        | 5581/28080 [11:02:15<44:30:57,  7.12s/it]
                                                          
{'loss': 0.6196, 'learning_rate': 0.0004635879125017991, 'epoch': 2.38}

 20%|█▉        | 5581/28080 [11:02:15<44:30:57,  7.12s/it]
 20%|█▉        | 5582/28080 [11:02:22<44:23:09,  7.10s/it]
                                                          
{'loss': 0.634, 'learning_rate': 0.0004635729252979446, 'epoch': 2.38}

 20%|█▉        | 5582/28080 [11:02:22<44:23:09,  7.10s/it]
 20%|█▉        | 5583/28080 [11:02:29<44:23:29,  7.10s/it]
                                                          
{'loss': 0.6513, 'learning_rate': 0.0004635579352527226, 'epoch': 2.39}

 20%|█▉        | 5583/28080 [11:02:29<44:23:29,  7.10s/it]
 20%|█▉        | 5584/28080 [11:02:36<44:28:29,  7.12s/it]
                                                          
{'loss': 0.6616, 'learning_rate': 0.00046354294236633265, 'epoch': 2.39}

 20%|█▉        | 5584/28080 [11:02:36<44:28:29,  7.12s/it]
 20%|█▉        | 5585/28080 [11:02:43<44:22:56,  7.10s/it]
                                                          
{'loss': 0.6406, 'learning_rate': 0.0004635279466389741, 'epoch': 2.39}

 20%|█▉        | 5585/28080 [11:02:43<44:22:56,  7.10s/it]
 20%|█▉        | 5586/28080 [11:02:50<44:11:14,  7.07s/it]
                                                          
{'loss': 0.6714, 'learning_rate': 0.0004635129480708466, 'epoch': 2.39}

 20%|█▉        | 5586/28080 [11:02:50<44:11:14,  7.07s/it]
 20%|█▉        | 5587/28080 [11:02:57<44:06:38,  7.06s/it]
                                                          
{'loss': 0.6508, 'learning_rate': 0.0004634979466621495, 'epoch': 2.39}

 20%|█▉        | 5587/28080 [11:02:57<44:06:38,  7.06s/it]
 20%|█▉        | 5588/28080 [11:03:04<44:14:19,  7.08s/it]
                                                          
{'loss': 0.6164, 'learning_rate': 0.00046348294241308255, 'epoch': 2.39}

 20%|█▉        | 5588/28080 [11:03:04<44:14:19,  7.08s/it]
 20%|█▉        | 5589/28080 [11:03:11<44:01:00,  7.05s/it]
                                                          
{'loss': 0.6385, 'learning_rate': 0.00046346793532384524, 'epoch': 2.39}

 20%|█▉        | 5589/28080 [11:03:11<44:01:00,  7.05s/it]
 20%|█▉        | 5590/28080 [11:03:18<44:14:24,  7.08s/it]
                                                          
{'loss': 0.6385, 'learning_rate': 0.00046345292539463727, 'epoch': 2.39}

 20%|█▉        | 5590/28080 [11:03:18<44:14:24,  7.08s/it]
 20%|█▉        | 5591/28080 [11:03:25<44:09:55,  7.07s/it]
                                                          
{'loss': 0.6573, 'learning_rate': 0.0004634379126256584, 'epoch': 2.39}

 20%|█▉        | 5591/28080 [11:03:25<44:09:55,  7.07s/it]
 20%|█▉        | 5592/28080 [11:03:32<44:07:23,  7.06s/it]
                                                          
{'loss': 0.6403, 'learning_rate': 0.0004634228970171083, 'epoch': 2.39}

 20%|█▉        | 5592/28080 [11:03:32<44:07:23,  7.06s/it]
 20%|█▉        | 5593/28080 [11:03:39<44:05:41,  7.06s/it]
                                                          
{'loss': 0.6664, 'learning_rate': 0.00046340787856918663, 'epoch': 2.39}

 20%|█▉        | 5593/28080 [11:03:39<44:05:41,  7.06s/it]
 20%|█▉        | 5594/28080 [11:03:46<44:06:09,  7.06s/it]
                                                          
{'loss': 0.6367, 'learning_rate': 0.0004633928572820934, 'epoch': 2.39}

 20%|█▉        | 5594/28080 [11:03:46<44:06:09,  7.06s/it]
 20%|█▉        | 5595/28080 [11:03:54<44:17:17,  7.09s/it]
                                                          
{'loss': 0.6198, 'learning_rate': 0.0004633778331560282, 'epoch': 2.39}

 20%|█▉        | 5595/28080 [11:03:54<44:17:17,  7.09s/it]
 20%|█▉        | 5596/28080 [11:04:01<44:15:28,  7.09s/it]
                                                          
{'loss': 0.6515, 'learning_rate': 0.0004633628061911912, 'epoch': 2.39}

 20%|█▉        | 5596/28080 [11:04:01<44:15:28,  7.09s/it]
 20%|█▉        | 5597/28080 [11:04:08<44:10:38,  7.07s/it]
                                                          
{'loss': 0.6793, 'learning_rate': 0.00046334777638778216, 'epoch': 2.39}

 20%|█▉        | 5597/28080 [11:04:08<44:10:38,  7.07s/it]
 20%|█▉        | 5598/28080 [11:04:15<44:14:44,  7.08s/it]
                                                          
{'loss': 0.6427, 'learning_rate': 0.000463332743746001, 'epoch': 2.39}

 20%|█▉        | 5598/28080 [11:04:15<44:14:44,  7.08s/it]
 20%|█▉        | 5599/28080 [11:04:22<44:13:43,  7.08s/it]
                                                          
{'loss': 0.6488, 'learning_rate': 0.00046331770826604774, 'epoch': 2.39}

 20%|█▉        | 5599/28080 [11:04:22<44:13:43,  7.08s/it]
 20%|█▉        | 5600/28080 [11:04:29<44:11:32,  7.08s/it]
                                                          
{'loss': 0.6587, 'learning_rate': 0.00046330266994812255, 'epoch': 2.39}

 20%|█▉        | 5600/28080 [11:04:29<44:11:32,  7.08s/it]
 20%|█▉        | 5601/28080 [11:04:36<44:04:56,  7.06s/it]
                                                          
{'loss': 0.6531, 'learning_rate': 0.00046328762879242524, 'epoch': 2.39}

 20%|█▉        | 5601/28080 [11:04:36<44:04:56,  7.06s/it]
 20%|█▉        | 5602/28080 [11:04:43<44:02:13,  7.05s/it]
                                                          
{'loss': 0.6599, 'learning_rate': 0.0004632725847991562, 'epoch': 2.39}

 20%|█▉        | 5602/28080 [11:04:43<44:02:13,  7.05s/it]
 20%|█▉        | 5603/28080 [11:04:50<44:02:21,  7.05s/it]
                                                          
{'loss': 0.6631, 'learning_rate': 0.0004632575379685154, 'epoch': 2.39}

 20%|█▉        | 5603/28080 [11:04:50<44:02:21,  7.05s/it]
 20%|█▉        | 5604/28080 [11:04:57<44:06:49,  7.07s/it]
                                                          
{'loss': 0.6417, 'learning_rate': 0.00046324248830070303, 'epoch': 2.39}

 20%|█▉        | 5604/28080 [11:04:57<44:06:49,  7.07s/it]
 20%|█▉        | 5605/28080 [11:05:04<44:15:03,  7.09s/it]
                                                          
{'loss': 0.6298, 'learning_rate': 0.0004632274357959194, 'epoch': 2.39}

 20%|█▉        | 5605/28080 [11:05:04<44:15:03,  7.09s/it]
 20%|█▉        | 5606/28080 [11:05:11<44:07:03,  7.07s/it]
                                                          
{'loss': 0.654, 'learning_rate': 0.00046321238045436464, 'epoch': 2.39}

 20%|█▉        | 5606/28080 [11:05:11<44:07:03,  7.07s/it]
 20%|█▉        | 5607/28080 [11:05:18<44:11:32,  7.08s/it]
                                                          
{'loss': 0.6323, 'learning_rate': 0.00046319732227623916, 'epoch': 2.4}

 20%|█▉        | 5607/28080 [11:05:18<44:11:32,  7.08s/it]
 20%|█▉        | 5608/28080 [11:05:25<44:06:44,  7.07s/it]
                                                          
{'loss': 0.6247, 'learning_rate': 0.0004631822612617433, 'epoch': 2.4}

 20%|█▉        | 5608/28080 [11:05:25<44:06:44,  7.07s/it]
 20%|█▉        | 5609/28080 [11:05:32<43:51:14,  7.03s/it]
                                                          
{'loss': 0.6637, 'learning_rate': 0.0004631671974110773, 'epoch': 2.4}

 20%|█▉        | 5609/28080 [11:05:32<43:51:14,  7.03s/it]
 20%|█▉        | 5610/28080 [11:05:40<44:11:15,  7.08s/it]
                                                          
{'loss': 0.6285, 'learning_rate': 0.0004631521307244417, 'epoch': 2.4}

 20%|█▉        | 5610/28080 [11:05:40<44:11:15,  7.08s/it]
 20%|█▉        | 5611/28080 [11:05:47<44:13:27,  7.09s/it]
                                                          
{'loss': 0.6359, 'learning_rate': 0.0004631370612020369, 'epoch': 2.4}

 20%|█▉        | 5611/28080 [11:05:47<44:13:27,  7.09s/it]
 20%|█▉        | 5612/28080 [11:05:54<44:21:47,  7.11s/it]
                                                          
{'loss': 0.6433, 'learning_rate': 0.0004631219888440633, 'epoch': 2.4}

 20%|█▉        | 5612/28080 [11:05:54<44:21:47,  7.11s/it]
 20%|█▉        | 5613/28080 [11:06:01<44:25:02,  7.12s/it]
                                                          
{'loss': 0.6516, 'learning_rate': 0.0004631069136507216, 'epoch': 2.4}

 20%|█▉        | 5613/28080 [11:06:01<44:25:02,  7.12s/it]
 20%|█▉        | 5614/28080 [11:06:08<44:28:22,  7.13s/it]
                                                          
{'loss': 0.6432, 'learning_rate': 0.00046309183562221227, 'epoch': 2.4}

 20%|█▉        | 5614/28080 [11:06:08<44:28:22,  7.13s/it]
 20%|█▉        | 5615/28080 [11:06:15<44:29:24,  7.13s/it]
                                                          
{'loss': 0.6385, 'learning_rate': 0.0004630767547587358, 'epoch': 2.4}

 20%|█▉        | 5615/28080 [11:06:15<44:29:24,  7.13s/it]
 20%|██        | 5616/28080 [11:06:22<44:25:01,  7.12s/it]
                                                          
{'loss': 0.6347, 'learning_rate': 0.000463061671060493, 'epoch': 2.4}

 20%|██        | 5616/28080 [11:06:22<44:25:01,  7.12s/it]
 20%|██        | 5617/28080 [11:06:29<44:13:01,  7.09s/it]
                                                          
{'loss': 0.6514, 'learning_rate': 0.00046304658452768445, 'epoch': 2.4}

 20%|██        | 5617/28080 [11:06:29<44:13:01,  7.09s/it]
 20%|██        | 5618/28080 [11:06:36<44:02:58,  7.06s/it]
                                                          
{'loss': 0.6373, 'learning_rate': 0.00046303149516051093, 'epoch': 2.4}

 20%|██        | 5618/28080 [11:06:36<44:02:58,  7.06s/it]
 20%|██        | 5619/28080 [11:06:43<44:07:03,  7.07s/it]
                                                          
{'loss': 0.6366, 'learning_rate': 0.0004630164029591731, 'epoch': 2.4}

 20%|██        | 5619/28080 [11:06:43<44:07:03,  7.07s/it]
 20%|██        | 5620/28080 [11:06:50<44:04:08,  7.06s/it]
                                                          
{'loss': 0.6506, 'learning_rate': 0.0004630013079238717, 'epoch': 2.4}

 20%|██        | 5620/28080 [11:06:51<44:04:08,  7.06s/it]
 20%|██        | 5621/28080 [11:06:58<43:59:47,  7.05s/it]
                                                          
{'loss': 0.6422, 'learning_rate': 0.0004629862100548078, 'epoch': 2.4}

 20%|██        | 5621/28080 [11:06:58<43:59:47,  7.05s/it]
 20%|██        | 5622/28080 [11:07:05<44:14:30,  7.09s/it]
                                                          
{'loss': 0.6473, 'learning_rate': 0.000462971109352182, 'epoch': 2.4}

 20%|██        | 5622/28080 [11:07:05<44:14:30,  7.09s/it]
 20%|██        | 5623/28080 [11:07:12<44:04:05,  7.06s/it]
                                                          
{'loss': 0.6283, 'learning_rate': 0.00046295600581619533, 'epoch': 2.4}

 20%|██        | 5623/28080 [11:07:12<44:04:05,  7.06s/it]
 20%|██        | 5624/28080 [11:07:19<43:59:49,  7.05s/it]
                                                          
{'loss': 0.6393, 'learning_rate': 0.0004629408994470487, 'epoch': 2.4}

 20%|██        | 5624/28080 [11:07:19<43:59:49,  7.05s/it]
 20%|██        | 5625/28080 [11:07:26<44:01:45,  7.06s/it]
                                                          
{'loss': 0.6259, 'learning_rate': 0.0004629257902449431, 'epoch': 2.4}

 20%|██        | 5625/28080 [11:07:26<44:01:45,  7.06s/it]
 20%|██        | 5626/28080 [11:07:33<44:08:30,  7.08s/it]
                                                          
{'loss': 0.6654, 'learning_rate': 0.0004629106782100795, 'epoch': 2.4}

 20%|██        | 5626/28080 [11:07:33<44:08:30,  7.08s/it]
 20%|██        | 5627/28080 [11:07:40<44:15:28,  7.10s/it]
                                                          
{'loss': 0.6552, 'learning_rate': 0.00046289556334265893, 'epoch': 2.4}

 20%|██        | 5627/28080 [11:07:40<44:15:28,  7.10s/it]
 20%|██        | 5628/28080 [11:07:47<44:14:39,  7.09s/it]
                                                          
{'loss': 0.6454, 'learning_rate': 0.00046288044564288255, 'epoch': 2.4}

 20%|██        | 5628/28080 [11:07:47<44:14:39,  7.09s/it]
 20%|██        | 5629/28080 [11:07:54<44:04:36,  7.07s/it]
                                                          
{'loss': 0.6639, 'learning_rate': 0.0004628653251109515, 'epoch': 2.4}

 20%|██        | 5629/28080 [11:07:54<44:04:36,  7.07s/it]
 20%|██        | 5630/28080 [11:08:01<44:16:10,  7.10s/it]
                                                          
{'loss': 0.6329, 'learning_rate': 0.0004628502017470668, 'epoch': 2.41}

 20%|██        | 5630/28080 [11:08:01<44:16:10,  7.10s/it]
 20%|██        | 5631/28080 [11:08:08<44:06:31,  7.07s/it]
                                                          
{'loss': 0.65, 'learning_rate': 0.0004628350755514299, 'epoch': 2.41}

 20%|██        | 5631/28080 [11:08:08<44:06:31,  7.07s/it]
 20%|██        | 5632/28080 [11:08:15<44:07:10,  7.08s/it]
                                                          
{'loss': 0.6548, 'learning_rate': 0.00046281994652424174, 'epoch': 2.41}

 20%|██        | 5632/28080 [11:08:15<44:07:10,  7.08s/it]
 20%|██        | 5633/28080 [11:08:23<44:13:04,  7.09s/it]
                                                          
{'loss': 0.6279, 'learning_rate': 0.0004628048146657039, 'epoch': 2.41}

 20%|██        | 5633/28080 [11:08:23<44:13:04,  7.09s/it]
 20%|██        | 5634/28080 [11:08:30<44:15:16,  7.10s/it]
                                                          
{'loss': 0.6566, 'learning_rate': 0.0004627896799760174, 'epoch': 2.41}

 20%|██        | 5634/28080 [11:08:30<44:15:16,  7.10s/it]
 20%|██        | 5635/28080 [11:08:37<44:17:38,  7.10s/it]
                                                          
{'loss': 0.649, 'learning_rate': 0.00046277454245538383, 'epoch': 2.41}

 20%|██        | 5635/28080 [11:08:37<44:17:38,  7.10s/it]
 20%|██        | 5636/28080 [11:08:44<43:59:43,  7.06s/it]
                                                          
{'loss': 0.6447, 'learning_rate': 0.0004627594021040044, 'epoch': 2.41}

 20%|██        | 5636/28080 [11:08:44<43:59:43,  7.06s/it]
 20%|██        | 5637/28080 [11:08:51<44:06:39,  7.08s/it]
                                                          
{'loss': 0.6471, 'learning_rate': 0.00046274425892208073, 'epoch': 2.41}

 20%|██        | 5637/28080 [11:08:51<44:06:39,  7.08s/it]
 20%|██        | 5638/28080 [11:08:58<44:10:41,  7.09s/it]
                                                          
{'loss': 0.6413, 'learning_rate': 0.00046272911290981403, 'epoch': 2.41}

 20%|██        | 5638/28080 [11:08:58<44:10:41,  7.09s/it]
 20%|██        | 5639/28080 [11:09:05<44:12:27,  7.09s/it]
                                                          
{'loss': 0.6533, 'learning_rate': 0.000462713964067406, 'epoch': 2.41}

 20%|██        | 5639/28080 [11:09:05<44:12:27,  7.09s/it]
 20%|██        | 5640/28080 [11:09:12<44:16:39,  7.10s/it]
                                                          
{'loss': 0.6317, 'learning_rate': 0.0004626988123950582, 'epoch': 2.41}

 20%|██        | 5640/28080 [11:09:12<44:16:39,  7.10s/it]
 20%|██        | 5641/28080 [11:09:19<44:20:28,  7.11s/it]
                                                          
{'loss': 0.6522, 'learning_rate': 0.000462683657892972, 'epoch': 2.41}

 20%|██        | 5641/28080 [11:09:19<44:20:28,  7.11s/it]
 20%|██        | 5642/28080 [11:09:26<44:14:01,  7.10s/it]
                                                          
{'loss': 0.6559, 'learning_rate': 0.0004626685005613492, 'epoch': 2.41}

 20%|██        | 5642/28080 [11:09:26<44:14:01,  7.10s/it]
 20%|██        | 5643/28080 [11:09:34<44:33:00,  7.15s/it]
                                                          
{'loss': 0.6246, 'learning_rate': 0.0004626533404003914, 'epoch': 2.41}

 20%|██        | 5643/28080 [11:09:34<44:33:00,  7.15s/it]
 20%|██        | 5644/28080 [11:09:41<44:26:13,  7.13s/it]
                                                          
{'loss': 0.6402, 'learning_rate': 0.00046263817741030034, 'epoch': 2.41}

 20%|██        | 5644/28080 [11:09:41<44:26:13,  7.13s/it]
 20%|██        | 5645/28080 [11:09:48<44:16:59,  7.11s/it]
                                                          
{'loss': 0.6546, 'learning_rate': 0.00046262301159127764, 'epoch': 2.41}

 20%|██        | 5645/28080 [11:09:48<44:16:59,  7.11s/it]
 20%|██        | 5646/28080 [11:09:55<44:13:29,  7.10s/it]
                                                          
{'loss': 0.6557, 'learning_rate': 0.0004626078429435251, 'epoch': 2.41}

 20%|██        | 5646/28080 [11:09:55<44:13:29,  7.10s/it]
 20%|██        | 5647/28080 [11:10:02<44:20:50,  7.12s/it]
                                                          
{'loss': 0.6278, 'learning_rate': 0.0004625926714672446, 'epoch': 2.41}

 20%|██        | 5647/28080 [11:10:02<44:20:50,  7.12s/it]
 20%|██        | 5648/28080 [11:10:09<44:18:17,  7.11s/it]
                                                          
{'loss': 0.6597, 'learning_rate': 0.00046257749716263787, 'epoch': 2.41}

 20%|██        | 5648/28080 [11:10:09<44:18:17,  7.11s/it]
 20%|██        | 5649/28080 [11:10:16<44:12:40,  7.10s/it]
                                                          
{'loss': 0.6352, 'learning_rate': 0.0004625623200299069, 'epoch': 2.41}

 20%|██        | 5649/28080 [11:10:16<44:12:40,  7.10s/it]
 20%|██        | 5650/28080 [11:10:23<44:15:22,  7.10s/it]
                                                          
{'loss': 0.639, 'learning_rate': 0.0004625471400692535, 'epoch': 2.41}

 20%|██        | 5650/28080 [11:10:23<44:15:22,  7.10s/it]
 20%|██        | 5651/28080 [11:10:30<44:17:27,  7.11s/it]
                                                          
{'loss': 0.6427, 'learning_rate': 0.0004625319572808797, 'epoch': 2.41}

 20%|██        | 5651/28080 [11:10:30<44:17:27,  7.11s/it]
 20%|██        | 5652/28080 [11:10:38<44:16:54,  7.11s/it]
                                                          
{'loss': 0.6272, 'learning_rate': 0.0004625167716649875, 'epoch': 2.41}

 20%|██        | 5652/28080 [11:10:38<44:16:54,  7.11s/it]
 20%|██        | 5653/28080 [11:10:45<44:11:32,  7.09s/it]
                                                          
{'loss': 0.6313, 'learning_rate': 0.0004625015832217788, 'epoch': 2.41}

 20%|██        | 5653/28080 [11:10:45<44:11:32,  7.09s/it]
 20%|██        | 5654/28080 [11:10:52<44:04:20,  7.07s/it]
                                                          
{'loss': 0.635, 'learning_rate': 0.00046248639195145585, 'epoch': 2.42}

 20%|██        | 5654/28080 [11:10:52<44:04:20,  7.07s/it]
 20%|██        | 5655/28080 [11:10:59<44:18:30,  7.11s/it]
                                                          
{'loss': 0.6477, 'learning_rate': 0.00046247119785422063, 'epoch': 2.42}

 20%|██        | 5655/28080 [11:10:59<44:18:30,  7.11s/it]
 20%|██        | 5656/28080 [11:11:06<44:13:20,  7.10s/it]
                                                          
{'loss': 0.6591, 'learning_rate': 0.00046245600093027537, 'epoch': 2.42}

 20%|██        | 5656/28080 [11:11:06<44:13:20,  7.10s/it]
 20%|██        | 5657/28080 [11:11:13<44:15:49,  7.11s/it]
                                                          
{'loss': 0.6699, 'learning_rate': 0.00046244080117982214, 'epoch': 2.42}

 20%|██        | 5657/28080 [11:11:13<44:15:49,  7.11s/it]
 20%|██        | 5658/28080 [11:11:20<44:23:49,  7.13s/it]
                                                          
{'loss': 0.6467, 'learning_rate': 0.0004624255986030632, 'epoch': 2.42}

 20%|██        | 5658/28080 [11:11:20<44:23:49,  7.13s/it]
 20%|██        | 5659/28080 [11:11:27<44:21:08,  7.12s/it]
                                                          
{'loss': 0.6387, 'learning_rate': 0.0004624103932002008, 'epoch': 2.42}

 20%|██        | 5659/28080 [11:11:27<44:21:08,  7.12s/it]
 20%|██        | 5660/28080 [11:11:34<44:11:56,  7.10s/it]
                                                          
{'loss': 0.6392, 'learning_rate': 0.00046239518497143736, 'epoch': 2.42}

 20%|██        | 5660/28080 [11:11:34<44:11:56,  7.10s/it]
 20%|██        | 5661/28080 [11:11:41<44:06:33,  7.08s/it]
                                                          
{'loss': 0.6578, 'learning_rate': 0.000462379973916975, 'epoch': 2.42}

 20%|██        | 5661/28080 [11:11:41<44:06:33,  7.08s/it]
 20%|██        | 5662/28080 [11:11:48<44:01:02,  7.07s/it]
                                                          
{'loss': 0.6449, 'learning_rate': 0.0004623647600370162, 'epoch': 2.42}

 20%|██        | 5662/28080 [11:11:48<44:01:02,  7.07s/it]
 20%|██        | 5663/28080 [11:11:56<43:59:54,  7.07s/it]
                                                          
{'loss': 0.6491, 'learning_rate': 0.0004623495433317634, 'epoch': 2.42}

 20%|██        | 5663/28080 [11:11:56<43:59:54,  7.07s/it]
 20%|██        | 5664/28080 [11:12:03<43:56:21,  7.06s/it]
                                                          
{'loss': 0.6533, 'learning_rate': 0.00046233432380141895, 'epoch': 2.42}

 20%|██        | 5664/28080 [11:12:03<43:56:21,  7.06s/it]
 20%|██        | 5665/28080 [11:12:10<44:03:45,  7.08s/it]
                                                          
{'loss': 0.6501, 'learning_rate': 0.00046231910144618537, 'epoch': 2.42}

 20%|██        | 5665/28080 [11:12:10<44:03:45,  7.08s/it]
 20%|██        | 5666/28080 [11:12:17<44:07:41,  7.09s/it]
                                                          
{'loss': 0.6765, 'learning_rate': 0.00046230387626626523, 'epoch': 2.42}

 20%|██        | 5666/28080 [11:12:17<44:07:41,  7.09s/it]
 20%|██        | 5667/28080 [11:12:24<44:17:03,  7.11s/it]
                                                          
{'loss': 0.6375, 'learning_rate': 0.000462288648261861, 'epoch': 2.42}

 20%|██        | 5667/28080 [11:12:24<44:17:03,  7.11s/it]
 20%|██        | 5668/28080 [11:12:31<44:19:01,  7.12s/it]
                                                          
{'loss': 0.6457, 'learning_rate': 0.0004622734174331753, 'epoch': 2.42}

 20%|██        | 5668/28080 [11:12:31<44:19:01,  7.12s/it]
 20%|██        | 5669/28080 [11:12:38<44:26:27,  7.14s/it]
                                                          
{'loss': 0.6505, 'learning_rate': 0.00046225818378041087, 'epoch': 2.42}

 20%|██        | 5669/28080 [11:12:38<44:26:27,  7.14s/it]
 20%|██        | 5670/28080 [11:12:45<44:08:39,  7.09s/it]
                                                          
{'loss': 0.6366, 'learning_rate': 0.0004622429473037701, 'epoch': 2.42}

 20%|██        | 5670/28080 [11:12:45<44:08:39,  7.09s/it]
 20%|██        | 5671/28080 [11:12:52<44:03:42,  7.08s/it]
                                                          
{'loss': 0.6328, 'learning_rate': 0.00046222770800345605, 'epoch': 2.42}

 20%|██        | 5671/28080 [11:12:52<44:03:42,  7.08s/it]
 20%|██        | 5672/28080 [11:12:59<44:08:41,  7.09s/it]
                                                          
{'loss': 0.6361, 'learning_rate': 0.0004622124658796712, 'epoch': 2.42}

 20%|██        | 5672/28080 [11:12:59<44:08:41,  7.09s/it]
 20%|██        | 5673/28080 [11:13:07<44:14:56,  7.11s/it]
                                                          
{'loss': 0.6496, 'learning_rate': 0.0004621972209326184, 'epoch': 2.42}

 20%|██        | 5673/28080 [11:13:07<44:14:56,  7.11s/it]
 20%|██        | 5674/28080 [11:13:14<44:11:56,  7.10s/it]
                                                          
{'loss': 0.6258, 'learning_rate': 0.00046218197316250055, 'epoch': 2.42}

 20%|██        | 5674/28080 [11:13:14<44:11:56,  7.10s/it]
 20%|██        | 5675/28080 [11:13:21<44:01:13,  7.07s/it]
                                                          
{'loss': 0.6588, 'learning_rate': 0.0004621667225695204, 'epoch': 2.42}

 20%|██        | 5675/28080 [11:13:21<44:01:13,  7.07s/it]
 20%|██        | 5676/28080 [11:13:28<44:03:49,  7.08s/it]
                                                          
{'loss': 0.6362, 'learning_rate': 0.00046215146915388095, 'epoch': 2.42}

 20%|██        | 5676/28080 [11:13:28<44:03:49,  7.08s/it]
 20%|██        | 5677/28080 [11:13:35<44:07:07,  7.09s/it]
                                                          
{'loss': 0.6466, 'learning_rate': 0.00046213621291578503, 'epoch': 2.43}

 20%|██        | 5677/28080 [11:13:35<44:07:07,  7.09s/it]
 20%|██        | 5678/28080 [11:13:42<44:03:56,  7.08s/it]
                                                          
{'loss': 0.6452, 'learning_rate': 0.0004621209538554356, 'epoch': 2.43}

 20%|██        | 5678/28080 [11:13:42<44:03:56,  7.08s/it]
 20%|██        | 5679/28080 [11:13:49<43:49:16,  7.04s/it]
                                                          
{'loss': 0.6463, 'learning_rate': 0.00046210569197303576, 'epoch': 2.43}

 20%|██        | 5679/28080 [11:13:49<43:49:16,  7.04s/it]
 20%|██        | 5680/28080 [11:13:56<44:00:58,  7.07s/it]
                                                          
{'loss': 0.6443, 'learning_rate': 0.00046209042726878845, 'epoch': 2.43}

 20%|██        | 5680/28080 [11:13:56<44:00:58,  7.07s/it]
 20%|██        | 5681/28080 [11:14:03<44:03:57,  7.08s/it]
                                                          
{'loss': 0.6718, 'learning_rate': 0.00046207515974289686, 'epoch': 2.43}

 20%|██        | 5681/28080 [11:14:03<44:03:57,  7.08s/it]
 20%|██        | 5682/28080 [11:14:10<43:58:47,  7.07s/it]
                                                          
{'loss': 0.6666, 'learning_rate': 0.0004620598893955641, 'epoch': 2.43}

 20%|██        | 5682/28080 [11:14:10<43:58:47,  7.07s/it]
 20%|██        | 5683/28080 [11:14:17<44:00:48,  7.07s/it]
                                                          
{'loss': 0.6082, 'learning_rate': 0.00046204461622699315, 'epoch': 2.43}

 20%|██        | 5683/28080 [11:14:17<44:00:48,  7.07s/it]
 20%|██        | 5684/28080 [11:14:24<43:59:33,  7.07s/it]
                                                          
{'loss': 0.6509, 'learning_rate': 0.0004620293402373874, 'epoch': 2.43}

 20%|██        | 5684/28080 [11:14:24<43:59:33,  7.07s/it]
 20%|██        | 5685/28080 [11:14:31<44:03:02,  7.08s/it]
                                                          
{'loss': 0.6366, 'learning_rate': 0.00046201406142695007, 'epoch': 2.43}

 20%|██        | 5685/28080 [11:14:31<44:03:02,  7.08s/it]
 20%|██        | 5686/28080 [11:14:38<43:57:14,  7.07s/it]
                                                          
{'loss': 0.6205, 'learning_rate': 0.00046199877979588436, 'epoch': 2.43}

 20%|██        | 5686/28080 [11:14:38<43:57:14,  7.07s/it]
 20%|██        | 5687/28080 [11:14:46<43:55:53,  7.06s/it]
                                                          
{'loss': 0.6682, 'learning_rate': 0.00046198349534439355, 'epoch': 2.43}

 20%|██        | 5687/28080 [11:14:46<43:55:53,  7.06s/it]
 20%|██        | 5688/28080 [11:14:53<44:02:42,  7.08s/it]
                                                          
{'loss': 0.643, 'learning_rate': 0.00046196820807268104, 'epoch': 2.43}

 20%|██        | 5688/28080 [11:14:53<44:02:42,  7.08s/it]
 20%|██        | 5689/28080 [11:15:00<43:55:29,  7.06s/it]
                                                          
{'loss': 0.6435, 'learning_rate': 0.00046195291798095016, 'epoch': 2.43}

 20%|██        | 5689/28080 [11:15:00<43:55:29,  7.06s/it]
 20%|██        | 5690/28080 [11:15:07<43:54:40,  7.06s/it]
                                                          
{'loss': 0.6267, 'learning_rate': 0.0004619376250694044, 'epoch': 2.43}

 20%|██        | 5690/28080 [11:15:07<43:54:40,  7.06s/it]
 20%|██        | 5691/28080 [11:15:14<44:07:14,  7.09s/it]
                                                          
{'loss': 0.6386, 'learning_rate': 0.0004619223293382472, 'epoch': 2.43}

 20%|██        | 5691/28080 [11:15:14<44:07:14,  7.09s/it]
 20%|██        | 5692/28080 [11:15:21<44:27:26,  7.15s/it]
                                                          
{'loss': 0.647, 'learning_rate': 0.00046190703078768204, 'epoch': 2.43}

 20%|██        | 5692/28080 [11:15:21<44:27:26,  7.15s/it]
 20%|██        | 5693/28080 [11:15:28<44:29:54,  7.16s/it]
                                                          
{'loss': 0.6241, 'learning_rate': 0.0004618917294179125, 'epoch': 2.43}

 20%|██        | 5693/28080 [11:15:28<44:29:54,  7.16s/it]
 20%|██        | 5694/28080 [11:15:35<44:23:12,  7.14s/it]
                                                          
{'loss': 0.6376, 'learning_rate': 0.000461876425229142, 'epoch': 2.43}

 20%|██        | 5694/28080 [11:15:35<44:23:12,  7.14s/it]
 20%|██        | 5695/28080 [11:15:43<44:23:48,  7.14s/it]
                                                          
{'loss': 0.6333, 'learning_rate': 0.00046186111822157423, 'epoch': 2.43}

 20%|██        | 5695/28080 [11:15:43<44:23:48,  7.14s/it]
 20%|██        | 5696/28080 [11:15:50<44:23:32,  7.14s/it]
                                                          
{'loss': 0.6574, 'learning_rate': 0.0004618458083954129, 'epoch': 2.43}

 20%|██        | 5696/28080 [11:15:50<44:23:32,  7.14s/it]
 20%|██        | 5697/28080 [11:15:57<44:17:30,  7.12s/it]
                                                          
{'loss': 0.6542, 'learning_rate': 0.00046183049575086163, 'epoch': 2.43}

 20%|██        | 5697/28080 [11:15:57<44:17:30,  7.12s/it]
 20%|██        | 5698/28080 [11:16:04<44:16:22,  7.12s/it]
                                                          
{'loss': 0.669, 'learning_rate': 0.0004618151802881241, 'epoch': 2.43}

 20%|██        | 5698/28080 [11:16:04<44:16:22,  7.12s/it]
 20%|██        | 5699/28080 [11:16:11<44:15:14,  7.12s/it]
                                                          
{'loss': 0.6342, 'learning_rate': 0.0004617998620074042, 'epoch': 2.43}

 20%|██        | 5699/28080 [11:16:11<44:15:14,  7.12s/it]
 20%|██        | 5700/28080 [11:16:18<44:17:45,  7.13s/it]
                                                          
{'loss': 0.6393, 'learning_rate': 0.0004617845409089055, 'epoch': 2.43}

 20%|██        | 5700/28080 [11:16:18<44:17:45,  7.13s/it]
 20%|██        | 5701/28080 [11:16:25<44:08:31,  7.10s/it]
                                                          
{'loss': 0.6515, 'learning_rate': 0.0004617692169928321, 'epoch': 2.44}

 20%|██        | 5701/28080 [11:16:25<44:08:31,  7.10s/it]
 20%|██        | 5702/28080 [11:16:32<44:07:59,  7.10s/it]
                                                          
{'loss': 0.62, 'learning_rate': 0.00046175389025938777, 'epoch': 2.44}

 20%|██        | 5702/28080 [11:16:32<44:07:59,  7.10s/it]
 20%|██        | 5703/28080 [11:16:39<44:02:35,  7.09s/it]
                                                          
{'loss': 0.6544, 'learning_rate': 0.0004617385607087763, 'epoch': 2.44}

 20%|██        | 5703/28080 [11:16:39<44:02:35,  7.09s/it]
 20%|██        | 5704/28080 [11:16:46<44:00:25,  7.08s/it]
                                                          
{'loss': 0.6433, 'learning_rate': 0.0004617232283412017, 'epoch': 2.44}

 20%|██        | 5704/28080 [11:16:46<44:00:25,  7.08s/it]
 20%|██        | 5705/28080 [11:16:54<44:02:53,  7.09s/it]
                                                          
{'loss': 0.6245, 'learning_rate': 0.000461707893156868, 'epoch': 2.44}

 20%|██        | 5705/28080 [11:16:54<44:02:53,  7.09s/it]
 20%|██        | 5706/28080 [11:17:01<44:08:37,  7.10s/it]
                                                          
{'loss': 0.6397, 'learning_rate': 0.00046169255515597917, 'epoch': 2.44}

 20%|██        | 5706/28080 [11:17:01<44:08:37,  7.10s/it]
 20%|██        | 5707/28080 [11:17:08<44:00:59,  7.08s/it]
                                                          
{'loss': 0.6459, 'learning_rate': 0.0004616772143387393, 'epoch': 2.44}

 20%|██        | 5707/28080 [11:17:08<44:00:59,  7.08s/it]
 20%|██        | 5708/28080 [11:17:15<43:52:10,  7.06s/it]
                                                          
{'loss': 0.6511, 'learning_rate': 0.0004616618707053525, 'epoch': 2.44}

 20%|██        | 5708/28080 [11:17:15<43:52:10,  7.06s/it]
 20%|██        | 5709/28080 [11:17:22<43:57:15,  7.07s/it]
                                                          
{'loss': 0.6374, 'learning_rate': 0.00046164652425602283, 'epoch': 2.44}

 20%|██        | 5709/28080 [11:17:22<43:57:15,  7.07s/it]
 20%|██        | 5710/28080 [11:17:29<44:00:24,  7.08s/it]
                                                          
{'loss': 0.6383, 'learning_rate': 0.0004616311749909545, 'epoch': 2.44}

 20%|██        | 5710/28080 [11:17:29<44:00:24,  7.08s/it]
 20%|██        | 5711/28080 [11:17:36<44:05:04,  7.09s/it]
                                                          
{'loss': 0.6491, 'learning_rate': 0.00046161582291035175, 'epoch': 2.44}

 20%|██        | 5711/28080 [11:17:36<44:05:04,  7.09s/it]
 20%|██        | 5712/28080 [11:17:43<43:59:36,  7.08s/it]
                                                          
{'loss': 0.6402, 'learning_rate': 0.0004616004680144188, 'epoch': 2.44}

 20%|██        | 5712/28080 [11:17:43<43:59:36,  7.08s/it]
 20%|██        | 5713/28080 [11:17:50<44:04:34,  7.09s/it]
                                                          
{'loss': 0.6473, 'learning_rate': 0.00046158511030335985, 'epoch': 2.44}

 20%|██        | 5713/28080 [11:17:50<44:04:34,  7.09s/it]
 20%|██        | 5714/28080 [11:17:57<44:11:18,  7.11s/it]
                                                          
{'loss': 0.6576, 'learning_rate': 0.0004615697497773793, 'epoch': 2.44}

 20%|██        | 5714/28080 [11:17:57<44:11:18,  7.11s/it]
 20%|██        | 5715/28080 [11:18:04<44:07:23,  7.10s/it]
                                                          
{'loss': 0.6673, 'learning_rate': 0.00046155438643668157, 'epoch': 2.44}

 20%|██        | 5715/28080 [11:18:04<44:07:23,  7.10s/it]
 20%|██        | 5716/28080 [11:18:12<44:12:50,  7.12s/it]
                                                          
{'loss': 0.6773, 'learning_rate': 0.00046153902028147085, 'epoch': 2.44}

 20%|██        | 5716/28080 [11:18:12<44:12:50,  7.12s/it]
 20%|██        | 5717/28080 [11:18:19<44:03:19,  7.09s/it]
                                                          
{'loss': 0.6395, 'learning_rate': 0.00046152365131195183, 'epoch': 2.44}

 20%|██        | 5717/28080 [11:18:19<44:03:19,  7.09s/it]
 20%|██        | 5718/28080 [11:18:26<44:00:23,  7.08s/it]
                                                          
{'loss': 0.6486, 'learning_rate': 0.0004615082795283288, 'epoch': 2.44}

 20%|██        | 5718/28080 [11:18:26<44:00:23,  7.08s/it]
 20%|██        | 5719/28080 [11:18:33<44:03:52,  7.09s/it]
                                                          
{'loss': 0.613, 'learning_rate': 0.0004614929049308063, 'epoch': 2.44}

 20%|██        | 5719/28080 [11:18:33<44:03:52,  7.09s/it]
 20%|██        | 5720/28080 [11:18:40<44:01:46,  7.09s/it]
                                                          
{'loss': 0.653, 'learning_rate': 0.0004614775275195889, 'epoch': 2.44}

 20%|██        | 5720/28080 [11:18:40<44:01:46,  7.09s/it]
 20%|██        | 5721/28080 [11:18:47<44:04:18,  7.10s/it]
                                                          
{'loss': 0.6477, 'learning_rate': 0.0004614621472948811, 'epoch': 2.44}

 20%|██        | 5721/28080 [11:18:47<44:04:18,  7.10s/it]
 20%|██        | 5722/28080 [11:18:54<44:03:04,  7.09s/it]
                                                          
{'loss': 0.6443, 'learning_rate': 0.0004614467642568877, 'epoch': 2.44}

 20%|██        | 5722/28080 [11:18:54<44:03:04,  7.09s/it]
 20%|██        | 5723/28080 [11:19:01<43:53:48,  7.07s/it]
                                                          
{'loss': 0.6507, 'learning_rate': 0.00046143137840581313, 'epoch': 2.44}

 20%|██        | 5723/28080 [11:19:01<43:53:48,  7.07s/it]
 20%|██        | 5724/28080 [11:19:08<43:44:40,  7.04s/it]
                                                          
{'loss': 0.6415, 'learning_rate': 0.0004614159897418622, 'epoch': 2.45}

 20%|██        | 5724/28080 [11:19:08<43:44:40,  7.04s/it]
 20%|██        | 5725/28080 [11:19:15<44:02:20,  7.09s/it]
                                                          
{'loss': 0.6593, 'learning_rate': 0.0004614005982652397, 'epoch': 2.45}

 20%|██        | 5725/28080 [11:19:15<44:02:20,  7.09s/it]
 20%|██        | 5726/28080 [11:19:22<44:03:48,  7.10s/it]
                                                          
{'loss': 0.6456, 'learning_rate': 0.0004613852039761503, 'epoch': 2.45}

 20%|██        | 5726/28080 [11:19:22<44:03:48,  7.10s/it]
 20%|██        | 5727/28080 [11:19:30<44:10:07,  7.11s/it]
                                                          
{'loss': 0.6441, 'learning_rate': 0.0004613698068747988, 'epoch': 2.45}

 20%|██        | 5727/28080 [11:19:30<44:10:07,  7.11s/it]
 20%|██        | 5728/28080 [11:19:37<44:02:47,  7.09s/it]
                                                          
{'loss': 0.6308, 'learning_rate': 0.0004613544069613901, 'epoch': 2.45}

 20%|██        | 5728/28080 [11:19:37<44:02:47,  7.09s/it]
 20%|██        | 5729/28080 [11:19:44<44:08:10,  7.11s/it]
                                                          
{'loss': 0.6253, 'learning_rate': 0.0004613390042361291, 'epoch': 2.45}

 20%|██        | 5729/28080 [11:19:44<44:08:10,  7.11s/it]
 20%|██        | 5730/28080 [11:19:51<44:02:33,  7.09s/it]
                                                          
{'loss': 0.6689, 'learning_rate': 0.00046132359869922065, 'epoch': 2.45}

 20%|██        | 5730/28080 [11:19:51<44:02:33,  7.09s/it]
 20%|██        | 5731/28080 [11:19:58<43:53:47,  7.07s/it]
                                                          
{'loss': 0.6568, 'learning_rate': 0.0004613081903508697, 'epoch': 2.45}

 20%|██        | 5731/28080 [11:19:58<43:53:47,  7.07s/it]
 20%|██        | 5732/28080 [11:20:05<44:03:59,  7.10s/it]
                                                          
{'loss': 0.6528, 'learning_rate': 0.0004612927791912813, 'epoch': 2.45}

 20%|██        | 5732/28080 [11:20:05<44:03:59,  7.10s/it]
 20%|██        | 5733/28080 [11:20:12<43:58:41,  7.08s/it]
                                                          
{'loss': 0.6633, 'learning_rate': 0.0004612773652206604, 'epoch': 2.45}

 20%|██        | 5733/28080 [11:20:12<43:58:41,  7.08s/it]
 20%|██        | 5734/28080 [11:20:19<44:10:43,  7.12s/it]
                                                          
{'loss': 0.6314, 'learning_rate': 0.00046126194843921223, 'epoch': 2.45}

 20%|██        | 5734/28080 [11:20:19<44:10:43,  7.12s/it]
 20%|██        | 5735/28080 [11:20:26<44:05:34,  7.10s/it]
                                                          
{'loss': 0.6248, 'learning_rate': 0.0004612465288471417, 'epoch': 2.45}

 20%|██        | 5735/28080 [11:20:26<44:05:34,  7.10s/it]
 20%|██        | 5736/28080 [11:20:33<44:00:25,  7.09s/it]
                                                          
{'loss': 0.6392, 'learning_rate': 0.000461231106444654, 'epoch': 2.45}

 20%|██        | 5736/28080 [11:20:33<44:00:25,  7.09s/it]
 20%|██        | 5737/28080 [11:20:41<44:06:06,  7.11s/it]
                                                          
{'loss': 0.6342, 'learning_rate': 0.00046121568123195443, 'epoch': 2.45}

 20%|██        | 5737/28080 [11:20:41<44:06:06,  7.11s/it]
 20%|██        | 5738/28080 [11:20:48<44:07:08,  7.11s/it]
                                                          
{'loss': 0.6339, 'learning_rate': 0.0004612002532092481, 'epoch': 2.45}

 20%|██        | 5738/28080 [11:20:48<44:07:08,  7.11s/it]
 20%|██        | 5739/28080 [11:20:55<43:58:19,  7.09s/it]
                                                          
{'loss': 0.6641, 'learning_rate': 0.00046118482237674023, 'epoch': 2.45}

 20%|██        | 5739/28080 [11:20:55<43:58:19,  7.09s/it]
 20%|██        | 5740/28080 [11:21:02<43:59:50,  7.09s/it]
                                                          
{'loss': 0.6519, 'learning_rate': 0.0004611693887346362, 'epoch': 2.45}

 20%|██        | 5740/28080 [11:21:02<43:59:50,  7.09s/it]
 20%|██        | 5741/28080 [11:21:09<44:00:45,  7.09s/it]
                                                          
{'loss': 0.637, 'learning_rate': 0.0004611539522831414, 'epoch': 2.45}

 20%|██        | 5741/28080 [11:21:09<44:00:45,  7.09s/it]
 20%|██        | 5742/28080 [11:21:16<44:07:13,  7.11s/it]
                                                          
{'loss': 0.6383, 'learning_rate': 0.000461138513022461, 'epoch': 2.45}

 20%|██        | 5742/28080 [11:21:16<44:07:13,  7.11s/it]
 20%|██        | 5743/28080 [11:21:23<44:03:25,  7.10s/it]
                                                          
{'loss': 0.6403, 'learning_rate': 0.00046112307095280046, 'epoch': 2.45}

 20%|██        | 5743/28080 [11:21:23<44:03:25,  7.10s/it]
 20%|██        | 5744/28080 [11:21:30<43:48:06,  7.06s/it]
                                                          
{'loss': 0.6316, 'learning_rate': 0.0004611076260743653, 'epoch': 2.45}

 20%|██        | 5744/28080 [11:21:30<43:48:06,  7.06s/it]
 20%|██        | 5745/28080 [11:21:37<43:45:56,  7.05s/it]
                                                          
{'loss': 0.6659, 'learning_rate': 0.000461092178387361, 'epoch': 2.45}

 20%|██        | 5745/28080 [11:21:37<43:45:56,  7.05s/it]
 20%|██        | 5746/28080 [11:21:44<43:46:29,  7.06s/it]
                                                          
{'loss': 0.648, 'learning_rate': 0.0004610767278919931, 'epoch': 2.45}

 20%|██        | 5746/28080 [11:21:44<43:46:29,  7.06s/it]
 20%|██        | 5747/28080 [11:21:51<43:45:27,  7.05s/it]
                                                          
{'loss': 0.6506, 'learning_rate': 0.0004610612745884669, 'epoch': 2.46}

 20%|██        | 5747/28080 [11:21:51<43:45:27,  7.05s/it]
 20%|██        | 5748/28080 [11:21:58<43:48:48,  7.06s/it]
                                                          
{'loss': 0.6368, 'learning_rate': 0.0004610458184769883, 'epoch': 2.46}

 20%|██        | 5748/28080 [11:21:58<43:48:48,  7.06s/it]
 20%|██        | 5749/28080 [11:22:05<43:56:45,  7.08s/it]
                                                          
{'loss': 0.6362, 'learning_rate': 0.00046103035955776287, 'epoch': 2.46}

 20%|██        | 5749/28080 [11:22:05<43:56:45,  7.08s/it]
 20%|██        | 5750/28080 [11:22:13<44:06:57,  7.11s/it]
                                                          
{'loss': 0.6438, 'learning_rate': 0.0004610148978309961, 'epoch': 2.46}

 20%|██        | 5750/28080 [11:22:13<44:06:57,  7.11s/it]
 20%|██        | 5751/28080 [11:22:20<43:57:29,  7.09s/it]
                                                          
{'loss': 0.6444, 'learning_rate': 0.0004609994332968939, 'epoch': 2.46}

 20%|██        | 5751/28080 [11:22:20<43:57:29,  7.09s/it]
 20%|██        | 5752/28080 [11:22:27<43:59:51,  7.09s/it]
                                                          
{'loss': 0.6695, 'learning_rate': 0.00046098396595566185, 'epoch': 2.46}

 20%|██        | 5752/28080 [11:22:27<43:59:51,  7.09s/it]
 20%|██        | 5753/28080 [11:22:34<44:00:00,  7.09s/it]
                                                          
{'loss': 0.6427, 'learning_rate': 0.00046096849580750575, 'epoch': 2.46}

 20%|██        | 5753/28080 [11:22:34<44:00:00,  7.09s/it]
 20%|██        | 5754/28080 [11:22:41<44:03:53,  7.11s/it]
                                                          
{'loss': 0.6517, 'learning_rate': 0.0004609530228526315, 'epoch': 2.46}

 20%|██        | 5754/28080 [11:22:41<44:03:53,  7.11s/it]
 20%|██        | 5755/28080 [11:22:48<43:59:55,  7.09s/it]
                                                          
{'loss': 0.6328, 'learning_rate': 0.00046093754709124494, 'epoch': 2.46}

 20%|██        | 5755/28080 [11:22:48<43:59:55,  7.09s/it]
 20%|██        | 5756/28080 [11:22:55<44:06:51,  7.11s/it]
                                                          
{'loss': 0.6417, 'learning_rate': 0.00046092206852355196, 'epoch': 2.46}

 20%|██        | 5756/28080 [11:22:55<44:06:51,  7.11s/it]
 21%|██        | 5757/28080 [11:23:02<44:02:07,  7.10s/it]
                                                          
{'loss': 0.6562, 'learning_rate': 0.0004609065871497584, 'epoch': 2.46}

 21%|██        | 5757/28080 [11:23:02<44:02:07,  7.10s/it]
 21%|██        | 5758/28080 [11:23:09<43:58:57,  7.09s/it]
                                                          
{'loss': 0.6575, 'learning_rate': 0.0004608911029700703, 'epoch': 2.46}

 21%|██        | 5758/28080 [11:23:09<43:58:57,  7.09s/it]
 21%|██        | 5759/28080 [11:23:16<44:04:22,  7.11s/it]
                                                          
{'loss': 0.6627, 'learning_rate': 0.0004608756159846936, 'epoch': 2.46}

 21%|██        | 5759/28080 [11:23:16<44:04:22,  7.11s/it]
 21%|██        | 5760/28080 [11:23:24<43:58:31,  7.09s/it]
                                                          
{'loss': 0.6535, 'learning_rate': 0.00046086012619383446, 'epoch': 2.46}

 21%|██        | 5760/28080 [11:23:24<43:58:31,  7.09s/it]
 21%|██        | 5761/28080 [11:23:31<44:07:33,  7.12s/it]
                                                          
{'loss': 0.6552, 'learning_rate': 0.0004608446335976988, 'epoch': 2.46}

 21%|██        | 5761/28080 [11:23:31<44:07:33,  7.12s/it]
 21%|██        | 5762/28080 [11:23:38<44:03:47,  7.11s/it]
                                                          
{'loss': 0.635, 'learning_rate': 0.00046082913819649277, 'epoch': 2.46}

 21%|██        | 5762/28080 [11:23:38<44:03:47,  7.11s/it]
 21%|██        | 5763/28080 [11:23:45<43:53:46,  7.08s/it]
                                                          
{'loss': 0.6555, 'learning_rate': 0.0004608136399904226, 'epoch': 2.46}

 21%|██        | 5763/28080 [11:23:45<43:53:46,  7.08s/it]
 21%|██        | 5764/28080 [11:23:52<43:52:17,  7.08s/it]
                                                          
{'loss': 0.6504, 'learning_rate': 0.00046079813897969445, 'epoch': 2.46}

 21%|██        | 5764/28080 [11:23:52<43:52:17,  7.08s/it]
 21%|██        | 5765/28080 [11:23:59<43:50:00,  7.07s/it]
                                                          
{'loss': 0.6447, 'learning_rate': 0.0004607826351645146, 'epoch': 2.46}

 21%|██        | 5765/28080 [11:23:59<43:50:00,  7.07s/it]
 21%|██        | 5766/28080 [11:24:06<43:53:38,  7.08s/it]
                                                          
{'loss': 0.6422, 'learning_rate': 0.00046076712854508907, 'epoch': 2.46}

 21%|██        | 5766/28080 [11:24:06<43:53:38,  7.08s/it]
 21%|██        | 5767/28080 [11:24:13<43:49:40,  7.07s/it]
                                                          
{'loss': 0.6414, 'learning_rate': 0.00046075161912162443, 'epoch': 2.46}

 21%|██        | 5767/28080 [11:24:13<43:49:40,  7.07s/it]
 21%|██        | 5768/28080 [11:24:20<43:48:57,  7.07s/it]
                                                          
{'loss': 0.6341, 'learning_rate': 0.000460736106894327, 'epoch': 2.46}

 21%|██        | 5768/28080 [11:24:20<43:48:57,  7.07s/it]
 21%|██        | 5769/28080 [11:24:27<43:51:18,  7.08s/it]
                                                          
{'loss': 0.6565, 'learning_rate': 0.0004607205918634029, 'epoch': 2.46}

 21%|██        | 5769/28080 [11:24:27<43:51:18,  7.08s/it]
 21%|██        | 5770/28080 [11:24:34<43:49:40,  7.07s/it]
                                                          
{'loss': 0.6527, 'learning_rate': 0.0004607050740290588, 'epoch': 2.46}

 21%|██        | 5770/28080 [11:24:34<43:49:40,  7.07s/it]
 21%|██        | 5771/28080 [11:24:41<43:50:48,  7.08s/it]
                                                          
{'loss': 0.634, 'learning_rate': 0.0004606895533915011, 'epoch': 2.47}

 21%|██        | 5771/28080 [11:24:41<43:50:48,  7.08s/it]
 21%|██        | 5772/28080 [11:24:48<43:50:43,  7.08s/it]
                                                          
{'loss': 0.6379, 'learning_rate': 0.0004606740299509362, 'epoch': 2.47}

 21%|██        | 5772/28080 [11:24:48<43:50:43,  7.08s/it]
 21%|██        | 5773/28080 [11:24:56<43:49:13,  7.07s/it]
                                                          
{'loss': 0.643, 'learning_rate': 0.0004606585037075707, 'epoch': 2.47}

 21%|██        | 5773/28080 [11:24:56<43:49:13,  7.07s/it]
 21%|██        | 5774/28080 [11:25:03<43:53:15,  7.08s/it]
                                                          
{'loss': 0.638, 'learning_rate': 0.0004606429746616111, 'epoch': 2.47}

 21%|██        | 5774/28080 [11:25:03<43:53:15,  7.08s/it]
 21%|██        | 5775/28080 [11:25:10<43:42:35,  7.05s/it]
                                                          
{'loss': 0.6438, 'learning_rate': 0.00046062744281326405, 'epoch': 2.47}

 21%|██        | 5775/28080 [11:25:10<43:42:35,  7.05s/it]
 21%|██        | 5776/28080 [11:25:17<43:54:08,  7.09s/it]
                                                          
{'loss': 0.6363, 'learning_rate': 0.00046061190816273613, 'epoch': 2.47}

 21%|██        | 5776/28080 [11:25:17<43:54:08,  7.09s/it]
 21%|██        | 5777/28080 [11:25:24<43:51:11,  7.08s/it]
                                                          
{'loss': 0.625, 'learning_rate': 0.00046059637071023407, 'epoch': 2.47}

 21%|██        | 5777/28080 [11:25:24<43:51:11,  7.08s/it]
 21%|██        | 5778/28080 [11:25:31<43:57:38,  7.10s/it]
                                                          
{'loss': 0.6387, 'learning_rate': 0.00046058083045596456, 'epoch': 2.47}

 21%|██        | 5778/28080 [11:25:31<43:57:38,  7.10s/it]
 21%|██        | 5779/28080 [11:25:38<43:57:25,  7.10s/it]
                                                          
{'loss': 0.6457, 'learning_rate': 0.00046056528740013436, 'epoch': 2.47}

 21%|██        | 5779/28080 [11:25:38<43:57:25,  7.10s/it]
 21%|██        | 5780/28080 [11:25:45<43:54:18,  7.09s/it]
                                                          
{'loss': 0.6297, 'learning_rate': 0.00046054974154295024, 'epoch': 2.47}

 21%|██        | 5780/28080 [11:25:45<43:54:18,  7.09s/it]
 21%|██        | 5781/28080 [11:25:52<44:01:28,  7.11s/it]
                                                          
{'loss': 0.651, 'learning_rate': 0.00046053419288461905, 'epoch': 2.47}

 21%|██        | 5781/28080 [11:25:52<44:01:28,  7.11s/it]
 21%|██        | 5782/28080 [11:25:59<44:08:29,  7.13s/it]
                                                          
{'loss': 0.6543, 'learning_rate': 0.0004605186414253476, 'epoch': 2.47}

 21%|██        | 5782/28080 [11:25:59<44:08:29,  7.13s/it]
 21%|██        | 5783/28080 [11:26:07<44:14:58,  7.14s/it]
                                                          
{'loss': 0.6375, 'learning_rate': 0.0004605030871653427, 'epoch': 2.47}

 21%|██        | 5783/28080 [11:26:07<44:14:58,  7.14s/it]
 21%|██        | 5784/28080 [11:26:14<44:13:54,  7.14s/it]
                                                          
{'loss': 0.6628, 'learning_rate': 0.0004604875301048115, 'epoch': 2.47}

 21%|██        | 5784/28080 [11:26:14<44:13:54,  7.14s/it]
 21%|██        | 5785/28080 [11:26:21<44:08:37,  7.13s/it]
                                                          
{'loss': 0.6548, 'learning_rate': 0.00046047197024396086, 'epoch': 2.47}

 21%|██        | 5785/28080 [11:26:21<44:08:37,  7.13s/it]
 21%|██        | 5786/28080 [11:26:28<43:53:23,  7.09s/it]
                                                          
{'loss': 0.6573, 'learning_rate': 0.00046045640758299777, 'epoch': 2.47}

 21%|██        | 5786/28080 [11:26:28<43:53:23,  7.09s/it]
 21%|██        | 5787/28080 [11:26:35<43:53:13,  7.09s/it]
                                                          
{'loss': 0.6294, 'learning_rate': 0.0004604408421221293, 'epoch': 2.47}

 21%|██        | 5787/28080 [11:26:35<43:53:13,  7.09s/it]
 21%|██        | 5788/28080 [11:26:42<44:01:27,  7.11s/it]
                                                          
{'loss': 0.6284, 'learning_rate': 0.00046042527386156253, 'epoch': 2.47}

 21%|██        | 5788/28080 [11:26:42<44:01:27,  7.11s/it]
 21%|██        | 5789/28080 [11:26:49<43:54:30,  7.09s/it]
                                                          
{'loss': 0.6425, 'learning_rate': 0.0004604097028015045, 'epoch': 2.47}

 21%|██        | 5789/28080 [11:26:49<43:54:30,  7.09s/it]
 21%|██        | 5790/28080 [11:26:56<44:00:09,  7.11s/it]
                                                          
{'loss': 0.6237, 'learning_rate': 0.0004603941289421625, 'epoch': 2.47}

 21%|██        | 5790/28080 [11:26:56<44:00:09,  7.11s/it]
 21%|██        | 5791/28080 [11:27:03<44:00:11,  7.11s/it]
                                                          
{'loss': 0.6232, 'learning_rate': 0.0004603785522837437, 'epoch': 2.47}

 21%|██        | 5791/28080 [11:27:03<44:00:11,  7.11s/it]
 21%|██        | 5792/28080 [11:27:11<43:58:48,  7.10s/it]
                                                          
{'loss': 0.6565, 'learning_rate': 0.0004603629728264552, 'epoch': 2.47}

 21%|██        | 5792/28080 [11:27:11<43:58:48,  7.10s/it]
 21%|██        | 5793/28080 [11:27:18<44:02:03,  7.11s/it]
                                                          
{'loss': 0.6464, 'learning_rate': 0.00046034739057050443, 'epoch': 2.47}

 21%|██        | 5793/28080 [11:27:18<44:02:03,  7.11s/it]
 21%|██        | 5794/28080 [11:27:25<43:47:13,  7.07s/it]
                                                          
{'loss': 0.6362, 'learning_rate': 0.00046033180551609867, 'epoch': 2.48}

 21%|██        | 5794/28080 [11:27:25<43:47:13,  7.07s/it]
 21%|██        | 5795/28080 [11:27:32<43:45:44,  7.07s/it]
                                                          
{'loss': 0.6422, 'learning_rate': 0.0004603162176634452, 'epoch': 2.48}

 21%|██        | 5795/28080 [11:27:32<43:45:44,  7.07s/it]
 21%|██        | 5796/28080 [11:27:39<43:54:04,  7.09s/it]
                                                          
{'loss': 0.6378, 'learning_rate': 0.00046030062701275137, 'epoch': 2.48}

 21%|██        | 5796/28080 [11:27:39<43:54:04,  7.09s/it]
 21%|██        | 5797/28080 [11:27:46<43:47:04,  7.07s/it]
                                                          
{'loss': 0.6495, 'learning_rate': 0.0004602850335642247, 'epoch': 2.48}

 21%|██        | 5797/28080 [11:27:46<43:47:04,  7.07s/it]
 21%|██        | 5798/28080 [11:27:53<43:46:17,  7.07s/it]
                                                          
{'loss': 0.6466, 'learning_rate': 0.00046026943731807256, 'epoch': 2.48}

 21%|██        | 5798/28080 [11:27:53<43:46:17,  7.07s/it]
 21%|██        | 5799/28080 [11:28:00<43:48:05,  7.08s/it]
                                                          
{'loss': 0.6449, 'learning_rate': 0.0004602538382745026, 'epoch': 2.48}

 21%|██        | 5799/28080 [11:28:00<43:48:05,  7.08s/it]
 21%|██        | 5800/28080 [11:28:07<43:53:02,  7.09s/it]
                                                          
{'loss': 0.66, 'learning_rate': 0.00046023823643372207, 'epoch': 2.48}

 21%|██        | 5800/28080 [11:28:07<43:53:02,  7.09s/it]
 21%|██        | 5801/28080 [11:28:14<43:58:49,  7.11s/it]
                                                          
{'loss': 0.6297, 'learning_rate': 0.0004602226317959388, 'epoch': 2.48}

 21%|██        | 5801/28080 [11:28:14<43:58:49,  7.11s/it]
 21%|██        | 5802/28080 [11:28:22<44:10:42,  7.14s/it]
                                                          
{'loss': 0.6458, 'learning_rate': 0.00046020702436136017, 'epoch': 2.48}

 21%|██        | 5802/28080 [11:28:22<44:10:42,  7.14s/it]
 21%|██        | 5803/28080 [11:28:29<44:11:47,  7.14s/it]
                                                          
{'loss': 0.6393, 'learning_rate': 0.00046019141413019404, 'epoch': 2.48}

 21%|██        | 5803/28080 [11:28:29<44:11:47,  7.14s/it]
 21%|██        | 5804/28080 [11:28:36<44:02:17,  7.12s/it]
                                                          
{'loss': 0.65, 'learning_rate': 0.000460175801102648, 'epoch': 2.48}

 21%|██        | 5804/28080 [11:28:36<44:02:17,  7.12s/it]
 21%|██        | 5805/28080 [11:28:43<44:08:52,  7.14s/it]
                                                          
{'loss': 0.6425, 'learning_rate': 0.00046016018527892977, 'epoch': 2.48}

 21%|██        | 5805/28080 [11:28:43<44:08:52,  7.14s/it]
 21%|██        | 5806/28080 [11:28:50<44:07:29,  7.13s/it]
                                                          
{'loss': 0.6429, 'learning_rate': 0.00046014456665924704, 'epoch': 2.48}

 21%|██        | 5806/28080 [11:28:50<44:07:29,  7.13s/it]
 21%|██        | 5807/28080 [11:28:57<44:04:40,  7.12s/it]
                                                          
{'loss': 0.6279, 'learning_rate': 0.0004601289452438077, 'epoch': 2.48}

 21%|██        | 5807/28080 [11:28:57<44:04:40,  7.12s/it]
 21%|██        | 5808/28080 [11:29:04<43:53:58,  7.10s/it]
                                                          
{'loss': 0.6222, 'learning_rate': 0.0004601133210328193, 'epoch': 2.48}

 21%|██        | 5808/28080 [11:29:04<43:53:58,  7.10s/it]
 21%|██        | 5809/28080 [11:29:11<43:52:35,  7.09s/it]
                                                          
{'loss': 0.637, 'learning_rate': 0.00046009769402649016, 'epoch': 2.48}

 21%|██        | 5809/28080 [11:29:11<43:52:35,  7.09s/it]
 21%|██        | 5810/28080 [11:29:18<43:45:56,  7.07s/it]
                                                          
{'loss': 0.6453, 'learning_rate': 0.00046008206422502786, 'epoch': 2.48}

 21%|██        | 5810/28080 [11:29:18<43:45:56,  7.07s/it]
 21%|██        | 5811/28080 [11:29:25<43:39:33,  7.06s/it]
                                                          
{'loss': 0.6528, 'learning_rate': 0.00046006643162864046, 'epoch': 2.48}

 21%|██        | 5811/28080 [11:29:25<43:39:33,  7.06s/it]
 21%|██        | 5812/28080 [11:29:32<43:40:09,  7.06s/it]
                                                          
{'loss': 0.6556, 'learning_rate': 0.00046005079623753585, 'epoch': 2.48}

 21%|██        | 5812/28080 [11:29:32<43:40:09,  7.06s/it]
 21%|██        | 5813/28080 [11:29:39<43:45:46,  7.08s/it]
                                                          
{'loss': 0.6229, 'learning_rate': 0.00046003515805192216, 'epoch': 2.48}

 21%|██        | 5813/28080 [11:29:39<43:45:46,  7.08s/it]
 21%|██        | 5814/28080 [11:29:47<43:48:08,  7.08s/it]
                                                          
{'loss': 0.6264, 'learning_rate': 0.00046001951707200727, 'epoch': 2.48}

 21%|██        | 5814/28080 [11:29:47<43:48:08,  7.08s/it]
 21%|██        | 5815/28080 [11:29:54<44:00:02,  7.11s/it]
                                                          
{'loss': 0.6299, 'learning_rate': 0.00046000387329799946, 'epoch': 2.48}

 21%|██        | 5815/28080 [11:29:54<44:00:02,  7.11s/it]
 21%|██        | 5816/28080 [11:30:01<43:46:16,  7.08s/it]
                                                          
{'loss': 0.6212, 'learning_rate': 0.00045998822673010674, 'epoch': 2.48}

 21%|██        | 5816/28080 [11:30:01<43:46:16,  7.08s/it]
 21%|██        | 5817/28080 [11:30:08<44:02:00,  7.12s/it]
                                                          
{'loss': 0.6211, 'learning_rate': 0.00045997257736853737, 'epoch': 2.48}

 21%|██        | 5817/28080 [11:30:08<44:02:00,  7.12s/it]
 21%|██        | 5818/28080 [11:30:15<43:47:31,  7.08s/it]
                                                          
{'loss': 0.6485, 'learning_rate': 0.00045995692521349943, 'epoch': 2.49}

 21%|██        | 5818/28080 [11:30:15<43:47:31,  7.08s/it]
 21%|██        | 5819/28080 [11:30:22<43:52:22,  7.10s/it]
                                                          
{'loss': 0.6517, 'learning_rate': 0.0004599412702652012, 'epoch': 2.49}

 21%|██        | 5819/28080 [11:30:22<43:52:22,  7.10s/it]
 21%|██        | 5820/28080 [11:30:29<43:45:16,  7.08s/it]
                                                          
{'loss': 0.6575, 'learning_rate': 0.00045992561252385084, 'epoch': 2.49}

 21%|██        | 5820/28080 [11:30:29<43:45:16,  7.08s/it]
 21%|██        | 5821/28080 [11:30:36<43:50:34,  7.09s/it]
                                                          
{'loss': 0.6505, 'learning_rate': 0.00045990995198965686, 'epoch': 2.49}

 21%|██        | 5821/28080 [11:30:36<43:50:34,  7.09s/it]
 21%|██        | 5822/28080 [11:30:43<44:01:36,  7.12s/it]
                                                          
{'loss': 0.6557, 'learning_rate': 0.00045989428866282755, 'epoch': 2.49}

 21%|██        | 5822/28080 [11:30:43<44:01:36,  7.12s/it]
 21%|██        | 5823/28080 [11:30:50<43:44:08,  7.07s/it]
                                                          
{'loss': 0.6501, 'learning_rate': 0.0004598786225435712, 'epoch': 2.49}

 21%|██        | 5823/28080 [11:30:50<43:44:08,  7.07s/it]
 21%|██        | 5824/28080 [11:30:57<43:44:58,  7.08s/it]
                                                          
{'loss': 0.6298, 'learning_rate': 0.00045986295363209637, 'epoch': 2.49}

 21%|██        | 5824/28080 [11:30:57<43:44:58,  7.08s/it]
 21%|██        | 5825/28080 [11:31:05<43:43:29,  7.07s/it]
                                                          
{'loss': 0.6405, 'learning_rate': 0.00045984728192861136, 'epoch': 2.49}

 21%|██        | 5825/28080 [11:31:05<43:43:29,  7.07s/it]
 21%|██        | 5826/28080 [11:31:12<43:54:05,  7.10s/it]
                                                          
{'loss': 0.6563, 'learning_rate': 0.00045983160743332484, 'epoch': 2.49}

 21%|██        | 5826/28080 [11:31:12<43:54:05,  7.10s/it]
 21%|██        | 5827/28080 [11:31:19<43:59:29,  7.12s/it]
                                                          
{'loss': 0.6391, 'learning_rate': 0.0004598159301464452, 'epoch': 2.49}

 21%|██        | 5827/28080 [11:31:19<43:59:29,  7.12s/it]
 21%|██        | 5828/28080 [11:31:26<44:07:52,  7.14s/it]
                                                          
{'loss': 0.6337, 'learning_rate': 0.00045980025006818107, 'epoch': 2.49}

 21%|██        | 5828/28080 [11:31:26<44:07:52,  7.14s/it]
 21%|██        | 5829/28080 [11:31:33<44:08:02,  7.14s/it]
                                                          
{'loss': 0.6192, 'learning_rate': 0.0004597845671987411, 'epoch': 2.49}

 21%|██        | 5829/28080 [11:31:33<44:08:02,  7.14s/it]
 21%|██        | 5830/28080 [11:31:40<44:05:09,  7.13s/it]
                                                          
{'loss': 0.6509, 'learning_rate': 0.00045976888153833386, 'epoch': 2.49}

 21%|██        | 5830/28080 [11:31:40<44:05:09,  7.13s/it]
 21%|██        | 5831/28080 [11:31:48<44:24:59,  7.19s/it]
                                                          
{'loss': 0.6335, 'learning_rate': 0.00045975319308716803, 'epoch': 2.49}

 21%|██        | 5831/28080 [11:31:48<44:24:59,  7.19s/it]
 21%|██        | 5832/28080 [11:31:55<44:17:55,  7.17s/it]
                                                          
{'loss': 0.6557, 'learning_rate': 0.0004597375018454524, 'epoch': 2.49}

 21%|██        | 5832/28080 [11:31:55<44:17:55,  7.17s/it]
 21%|██        | 5833/28080 [11:32:02<43:54:19,  7.10s/it]
                                                          
{'loss': 0.6558, 'learning_rate': 0.00045972180781339556, 'epoch': 2.49}

 21%|██        | 5833/28080 [11:32:02<43:54:19,  7.10s/it]
 21%|██        | 5834/28080 [11:32:09<44:00:03,  7.12s/it]
                                                          
{'loss': 0.6428, 'learning_rate': 0.0004597061109912065, 'epoch': 2.49}

 21%|██        | 5834/28080 [11:32:09<44:00:03,  7.12s/it]
 21%|██        | 5835/28080 [11:32:16<44:00:17,  7.12s/it]
                                                          
{'loss': 0.6459, 'learning_rate': 0.00045969041137909405, 'epoch': 2.49}

 21%|██        | 5835/28080 [11:32:16<44:00:17,  7.12s/it]
 21%|██        | 5836/28080 [11:32:23<44:00:54,  7.12s/it]
                                                          
{'loss': 0.6209, 'learning_rate': 0.00045967470897726695, 'epoch': 2.49}

 21%|██        | 5836/28080 [11:32:23<44:00:54,  7.12s/it]
 21%|██        | 5837/28080 [11:32:30<43:57:24,  7.11s/it]
                                                          
{'loss': 0.6278, 'learning_rate': 0.0004596590037859342, 'epoch': 2.49}

 21%|██        | 5837/28080 [11:32:30<43:57:24,  7.11s/it]
 21%|██        | 5838/28080 [11:32:37<43:43:35,  7.08s/it]
                                                          
{'loss': 0.6597, 'learning_rate': 0.0004596432958053046, 'epoch': 2.49}

 21%|██        | 5838/28080 [11:32:37<43:43:35,  7.08s/it]
 21%|██        | 5839/28080 [11:32:44<43:36:16,  7.06s/it]
                                                          
{'loss': 0.659, 'learning_rate': 0.00045962758503558724, 'epoch': 2.49}

 21%|██        | 5839/28080 [11:32:44<43:36:16,  7.06s/it]
 21%|██        | 5840/28080 [11:32:51<43:36:31,  7.06s/it]
                                                          
{'loss': 0.6553, 'learning_rate': 0.00045961187147699117, 'epoch': 2.49}

 21%|██        | 5840/28080 [11:32:51<43:36:31,  7.06s/it]
 21%|██        | 5841/28080 [11:32:58<43:39:33,  7.07s/it]
                                                          
{'loss': 0.6539, 'learning_rate': 0.0004595961551297254, 'epoch': 2.5}

 21%|██        | 5841/28080 [11:32:58<43:39:33,  7.07s/it]
 21%|██        | 5842/28080 [11:33:05<43:43:49,  7.08s/it]
                                                          
{'loss': 0.641, 'learning_rate': 0.000459580435993999, 'epoch': 2.5}

 21%|██        | 5842/28080 [11:33:05<43:43:49,  7.08s/it]
 21%|██        | 5843/28080 [11:33:13<43:48:54,  7.09s/it]
                                                          
{'loss': 0.6481, 'learning_rate': 0.0004595647140700211, 'epoch': 2.5}

 21%|██        | 5843/28080 [11:33:13<43:48:54,  7.09s/it]
 21%|██        | 5844/28080 [11:33:20<43:39:45,  7.07s/it]
                                                          
{'loss': 0.6494, 'learning_rate': 0.0004595489893580009, 'epoch': 2.5}

 21%|██        | 5844/28080 [11:33:20<43:39:45,  7.07s/it]
 21%|██        | 5845/28080 [11:33:27<43:35:43,  7.06s/it]
                                                          
{'loss': 0.6468, 'learning_rate': 0.0004595332618581476, 'epoch': 2.5}

 21%|██        | 5845/28080 [11:33:27<43:35:43,  7.06s/it]
 21%|██        | 5846/28080 [11:33:34<43:48:00,  7.09s/it]
                                                          
{'loss': 0.6368, 'learning_rate': 0.00045951753157067035, 'epoch': 2.5}

 21%|██        | 5846/28080 [11:33:34<43:48:00,  7.09s/it]
 21%|██        | 5847/28080 [11:33:41<43:38:35,  7.07s/it]
                                                          
{'loss': 0.6393, 'learning_rate': 0.0004595017984957785, 'epoch': 2.5}

 21%|██        | 5847/28080 [11:33:41<43:38:35,  7.07s/it]
 21%|██        | 5848/28080 [11:33:48<43:42:58,  7.08s/it]
                                                          
{'loss': 0.6528, 'learning_rate': 0.0004594860626336814, 'epoch': 2.5}

 21%|██        | 5848/28080 [11:33:48<43:42:58,  7.08s/it]
 21%|██        | 5849/28080 [11:33:55<43:41:38,  7.08s/it]
                                                          
{'loss': 0.6438, 'learning_rate': 0.00045947032398458825, 'epoch': 2.5}

 21%|██        | 5849/28080 [11:33:55<43:41:38,  7.08s/it]
 21%|██        | 5850/28080 [11:34:02<43:47:38,  7.09s/it]
                                                          
{'loss': 0.6352, 'learning_rate': 0.00045945458254870864, 'epoch': 2.5}

 21%|██        | 5850/28080 [11:34:02<43:47:38,  7.09s/it]
 21%|██        | 5851/28080 [11:34:09<43:55:10,  7.11s/it]
                                                          
{'loss': 0.6349, 'learning_rate': 0.00045943883832625184, 'epoch': 2.5}

 21%|██        | 5851/28080 [11:34:09<43:55:10,  7.11s/it]
 21%|██        | 5852/28080 [11:34:16<43:55:50,  7.11s/it]
                                                          
{'loss': 0.6362, 'learning_rate': 0.0004594230913174274, 'epoch': 2.5}

 21%|██        | 5852/28080 [11:34:16<43:55:50,  7.11s/it]
 21%|██        | 5853/28080 [11:34:24<44:02:09,  7.13s/it]
                                                          
{'loss': 0.6363, 'learning_rate': 0.0004594073415224447, 'epoch': 2.5}

 21%|██        | 5853/28080 [11:34:24<44:02:09,  7.13s/it]
 21%|██        | 5854/28080 [11:34:31<44:03:32,  7.14s/it]
                                                          
{'loss': 0.633, 'learning_rate': 0.00045939158894151347, 'epoch': 2.5}

 21%|██        | 5854/28080 [11:34:31<44:03:32,  7.14s/it]
 21%|██        | 5855/28080 [11:34:38<44:01:33,  7.13s/it]
                                                          
{'loss': 0.6313, 'learning_rate': 0.00045937583357484314, 'epoch': 2.5}

 21%|██        | 5855/28080 [11:34:38<44:01:33,  7.13s/it]
 21%|██        | 5856/28080 [11:34:45<43:59:09,  7.13s/it]
                                                          
{'loss': 0.6471, 'learning_rate': 0.00045936007542264325, 'epoch': 2.5}

 21%|██        | 5856/28080 [11:34:45<43:59:09,  7.13s/it]
 21%|██        | 5857/28080 [11:34:52<44:00:07,  7.13s/it]
                                                          
{'loss': 0.6487, 'learning_rate': 0.0004593443144851236, 'epoch': 2.5}

 21%|██        | 5857/28080 [11:34:52<44:00:07,  7.13s/it]
 21%|██        | 5858/28080 [11:34:59<44:05:32,  7.14s/it]
                                                          
{'loss': 0.6647, 'learning_rate': 0.0004593285507624939, 'epoch': 2.5}

 21%|██        | 5858/28080 [11:34:59<44:05:32,  7.14s/it]
 21%|██        | 5859/28080 [11:35:06<44:07:11,  7.15s/it]
                                                          
{'loss': 0.6378, 'learning_rate': 0.0004593127842549636, 'epoch': 2.5}

 21%|██        | 5859/28080 [11:35:06<44:07:11,  7.15s/it]
 21%|██        | 5860/28080 [11:35:13<43:55:16,  7.12s/it]
                                                          
{'loss': 0.6453, 'learning_rate': 0.0004592970149627428, 'epoch': 2.5}

 21%|██        | 5860/28080 [11:35:13<43:55:16,  7.12s/it]
 21%|██        | 5861/28080 [11:35:20<43:42:54,  7.08s/it]
                                                          
{'loss': 0.6697, 'learning_rate': 0.0004592812428860411, 'epoch': 2.5}

 21%|██        | 5861/28080 [11:35:20<43:42:54,  7.08s/it]
 21%|██        | 5862/28080 [11:35:28<43:49:56,  7.10s/it]
                                                          
{'loss': 0.6313, 'learning_rate': 0.0004592654680250683, 'epoch': 2.5}

 21%|██        | 5862/28080 [11:35:28<43:49:56,  7.10s/it]
 21%|██        | 5863/28080 [11:35:35<43:52:31,  7.11s/it]
                                                          
{'loss': 0.644, 'learning_rate': 0.0004592496903800344, 'epoch': 2.5}

 21%|██        | 5863/28080 [11:35:35<43:52:31,  7.11s/it]
 21%|██        | 5864/28080 [11:35:42<43:55:23,  7.12s/it]
                                                          
{'loss': 0.6513, 'learning_rate': 0.00045923390995114923, 'epoch': 2.51}

 21%|██        | 5864/28080 [11:35:42<43:55:23,  7.12s/it]
 21%|██        | 5865/28080 [11:35:49<43:48:15,  7.10s/it]
                                                          
{'loss': 0.6567, 'learning_rate': 0.00045921812673862275, 'epoch': 2.51}

 21%|██        | 5865/28080 [11:35:49<43:48:15,  7.10s/it]
 21%|██        | 5866/28080 [11:35:56<43:52:56,  7.11s/it]
                                                          
{'loss': 0.6414, 'learning_rate': 0.00045920234074266485, 'epoch': 2.51}

 21%|██        | 5866/28080 [11:35:56<43:52:56,  7.11s/it]
 21%|██        | 5867/28080 [11:36:03<43:43:07,  7.09s/it]
                                                          
{'loss': 0.6491, 'learning_rate': 0.00045918655196348576, 'epoch': 2.51}

 21%|██        | 5867/28080 [11:36:03<43:43:07,  7.09s/it]
 21%|██        | 5868/28080 [11:36:10<43:42:26,  7.08s/it]
                                                          
{'loss': 0.6638, 'learning_rate': 0.0004591707604012953, 'epoch': 2.51}

 21%|██        | 5868/28080 [11:36:10<43:42:26,  7.08s/it]
 21%|██        | 5869/28080 [11:36:17<43:41:48,  7.08s/it]
                                                          
{'loss': 0.6457, 'learning_rate': 0.0004591549660563037, 'epoch': 2.51}

 21%|██        | 5869/28080 [11:36:17<43:41:48,  7.08s/it]
 21%|██        | 5870/28080 [11:36:24<43:23:14,  7.03s/it]
                                                          
{'loss': 0.6579, 'learning_rate': 0.0004591391689287211, 'epoch': 2.51}

 21%|██        | 5870/28080 [11:36:24<43:23:14,  7.03s/it]
 21%|██        | 5871/28080 [11:36:31<43:27:07,  7.04s/it]
                                                          
{'loss': 0.6525, 'learning_rate': 0.0004591233690187576, 'epoch': 2.51}

 21%|██        | 5871/28080 [11:36:31<43:27:07,  7.04s/it]
 21%|██        | 5872/28080 [11:36:38<43:22:10,  7.03s/it]
                                                          
{'loss': 0.6324, 'learning_rate': 0.00045910756632662334, 'epoch': 2.51}

 21%|██        | 5872/28080 [11:36:38<43:22:10,  7.03s/it]
 21%|██        | 5873/28080 [11:36:45<43:33:07,  7.06s/it]
                                                          
{'loss': 0.6503, 'learning_rate': 0.00045909176085252867, 'epoch': 2.51}

 21%|██        | 5873/28080 [11:36:45<43:33:07,  7.06s/it]
 21%|██        | 5874/28080 [11:36:52<43:35:52,  7.07s/it]
                                                          
{'loss': 0.6615, 'learning_rate': 0.00045907595259668386, 'epoch': 2.51}

 21%|██        | 5874/28080 [11:36:52<43:35:52,  7.07s/it]
 21%|██        | 5875/28080 [11:37:00<43:52:02,  7.11s/it]
                                                          
{'loss': 0.6156, 'learning_rate': 0.0004590601415592991, 'epoch': 2.51}

 21%|██        | 5875/28080 [11:37:00<43:52:02,  7.11s/it]
 21%|██        | 5876/28080 [11:37:07<43:51:06,  7.11s/it]
                                                          
{'loss': 0.6457, 'learning_rate': 0.0004590443277405849, 'epoch': 2.51}

 21%|██        | 5876/28080 [11:37:07<43:51:06,  7.11s/it]
 21%|██        | 5877/28080 [11:37:14<43:43:50,  7.09s/it]
                                                          
{'loss': 0.6397, 'learning_rate': 0.00045902851114075163, 'epoch': 2.51}

 21%|██        | 5877/28080 [11:37:14<43:43:50,  7.09s/it]
 21%|██        | 5878/28080 [11:37:21<43:55:07,  7.12s/it]
                                                          
{'loss': 0.6416, 'learning_rate': 0.0004590126917600096, 'epoch': 2.51}

 21%|██        | 5878/28080 [11:37:21<43:55:07,  7.12s/it]
 21%|██        | 5879/28080 [11:37:28<44:05:27,  7.15s/it]
                                                          
{'loss': 0.6537, 'learning_rate': 0.00045899686959856935, 'epoch': 2.51}

 21%|██        | 5879/28080 [11:37:28<44:05:27,  7.15s/it]
 21%|██        | 5880/28080 [11:37:35<44:03:14,  7.14s/it]
                                                          
{'loss': 0.646, 'learning_rate': 0.00045898104465664136, 'epoch': 2.51}

 21%|██        | 5880/28080 [11:37:35<44:03:14,  7.14s/it]
 21%|██        | 5881/28080 [11:37:43<44:03:07,  7.14s/it]
                                                          
{'loss': 0.648, 'learning_rate': 0.00045896521693443616, 'epoch': 2.51}

 21%|██        | 5881/28080 [11:37:43<44:03:07,  7.14s/it]
 21%|██        | 5882/28080 [11:37:50<44:04:16,  7.15s/it]
                                                          
{'loss': 0.6372, 'learning_rate': 0.0004589493864321643, 'epoch': 2.51}

 21%|██        | 5882/28080 [11:37:50<44:04:16,  7.15s/it]
 21%|██        | 5883/28080 [11:37:57<44:15:28,  7.18s/it]
                                                          
{'loss': 0.6428, 'learning_rate': 0.0004589335531500365, 'epoch': 2.51}

 21%|██        | 5883/28080 [11:37:57<44:15:28,  7.18s/it]
 21%|██        | 5884/28080 [11:38:04<44:11:07,  7.17s/it]
                                                          
{'loss': 0.6394, 'learning_rate': 0.00045891771708826326, 'epoch': 2.51}

 21%|██        | 5884/28080 [11:38:04<44:11:07,  7.17s/it]
 21%|██        | 5885/28080 [11:38:11<44:09:52,  7.16s/it]
                                                          
{'loss': 0.6379, 'learning_rate': 0.00045890187824705527, 'epoch': 2.51}

 21%|██        | 5885/28080 [11:38:11<44:09:52,  7.16s/it]
 21%|██        | 5886/28080 [11:38:18<44:06:06,  7.15s/it]
                                                          
{'loss': 0.6253, 'learning_rate': 0.0004588860366266234, 'epoch': 2.51}

 21%|██        | 5886/28080 [11:38:18<44:06:06,  7.15s/it]
 21%|██        | 5887/28080 [11:38:25<43:55:52,  7.13s/it]
                                                          
{'loss': 0.6472, 'learning_rate': 0.0004588701922271782, 'epoch': 2.51}

 21%|██        | 5887/28080 [11:38:25<43:55:52,  7.13s/it]
 21%|██        | 5888/28080 [11:38:33<43:58:44,  7.13s/it]
                                                          
{'loss': 0.6344, 'learning_rate': 0.00045885434504893064, 'epoch': 2.52}

 21%|██        | 5888/28080 [11:38:33<43:58:44,  7.13s/it]
 21%|██        | 5889/28080 [11:38:40<43:41:53,  7.09s/it]
                                                          
{'loss': 0.6599, 'learning_rate': 0.00045883849509209144, 'epoch': 2.52}

 21%|██        | 5889/28080 [11:38:40<43:41:53,  7.09s/it]
 21%|██        | 5890/28080 [11:38:47<43:38:37,  7.08s/it]
                                                          
{'loss': 0.6344, 'learning_rate': 0.00045882264235687153, 'epoch': 2.52}

 21%|██        | 5890/28080 [11:38:47<43:38:37,  7.08s/it]
 21%|██        | 5891/28080 [11:38:54<43:44:19,  7.10s/it]
                                                          
{'loss': 0.6419, 'learning_rate': 0.0004588067868434819, 'epoch': 2.52}

 21%|██        | 5891/28080 [11:38:54<43:44:19,  7.10s/it]
 21%|██        | 5892/28080 [11:39:01<43:42:27,  7.09s/it]
                                                          
{'loss': 0.6659, 'learning_rate': 0.00045879092855213323, 'epoch': 2.52}

 21%|██        | 5892/28080 [11:39:01<43:42:27,  7.09s/it]
 21%|██        | 5893/28080 [11:39:08<43:50:09,  7.11s/it]
                                                          
{'loss': 0.6219, 'learning_rate': 0.00045877506748303676, 'epoch': 2.52}

 21%|██        | 5893/28080 [11:39:08<43:50:09,  7.11s/it]
 21%|██        | 5894/28080 [11:39:15<43:38:10,  7.08s/it]
                                                          
{'loss': 0.6334, 'learning_rate': 0.00045875920363640336, 'epoch': 2.52}

 21%|██        | 5894/28080 [11:39:15<43:38:10,  7.08s/it]
 21%|██        | 5895/28080 [11:39:22<43:44:42,  7.10s/it]
                                                          
{'loss': 0.6577, 'learning_rate': 0.0004587433370124441, 'epoch': 2.52}

 21%|██        | 5895/28080 [11:39:22<43:44:42,  7.10s/it]
 21%|██        | 5896/28080 [11:39:29<43:38:37,  7.08s/it]
                                                          
{'loss': 0.6477, 'learning_rate': 0.00045872746761137006, 'epoch': 2.52}

 21%|██        | 5896/28080 [11:39:29<43:38:37,  7.08s/it]
 21%|██        | 5897/28080 [11:39:36<43:40:18,  7.09s/it]
                                                          
{'loss': 0.6399, 'learning_rate': 0.00045871159543339247, 'epoch': 2.52}

 21%|██        | 5897/28080 [11:39:36<43:40:18,  7.09s/it]
 21%|██        | 5898/28080 [11:39:43<43:40:42,  7.09s/it]
                                                          
{'loss': 0.6286, 'learning_rate': 0.00045869572047872243, 'epoch': 2.52}

 21%|██        | 5898/28080 [11:39:43<43:40:42,  7.09s/it]
 21%|██        | 5899/28080 [11:39:50<43:42:18,  7.09s/it]
                                                          
{'loss': 0.6371, 'learning_rate': 0.00045867984274757103, 'epoch': 2.52}

 21%|██        | 5899/28080 [11:39:50<43:42:18,  7.09s/it]
 21%|██        | 5900/28080 [11:39:58<43:39:22,  7.09s/it]
                                                          
{'loss': 0.6421, 'learning_rate': 0.0004586639622401497, 'epoch': 2.52}

 21%|██        | 5900/28080 [11:39:58<43:39:22,  7.09s/it]
 21%|██        | 5901/28080 [11:40:05<43:36:20,  7.08s/it]
                                                          
{'loss': 0.6515, 'learning_rate': 0.0004586480789566696, 'epoch': 2.52}

 21%|██        | 5901/28080 [11:40:05<43:36:20,  7.08s/it]
 21%|██        | 5902/28080 [11:40:12<43:39:46,  7.09s/it]
                                                          
{'loss': 0.6476, 'learning_rate': 0.00045863219289734203, 'epoch': 2.52}

 21%|██        | 5902/28080 [11:40:12<43:39:46,  7.09s/it]
 21%|██        | 5903/28080 [11:40:19<43:52:41,  7.12s/it]
                                                          
{'loss': 0.6542, 'learning_rate': 0.00045861630406237837, 'epoch': 2.52}

 21%|██        | 5903/28080 [11:40:19<43:52:41,  7.12s/it]
 21%|██        | 5904/28080 [11:40:26<43:57:20,  7.14s/it]
                                                          
{'loss': 0.6367, 'learning_rate': 0.00045860041245199, 'epoch': 2.52}

 21%|██        | 5904/28080 [11:40:26<43:57:20,  7.14s/it]
 21%|██        | 5905/28080 [11:40:33<43:52:55,  7.12s/it]
                                                          
{'loss': 0.6335, 'learning_rate': 0.00045858451806638834, 'epoch': 2.52}

 21%|██        | 5905/28080 [11:40:33<43:52:55,  7.12s/it]
 21%|██        | 5906/28080 [11:40:40<43:51:18,  7.12s/it]
                                                          
{'loss': 0.6313, 'learning_rate': 0.00045856862090578487, 'epoch': 2.52}

 21%|██        | 5906/28080 [11:40:40<43:51:18,  7.12s/it]
 21%|██        | 5907/28080 [11:40:47<43:59:50,  7.14s/it]
                                                          
{'loss': 0.6288, 'learning_rate': 0.00045855272097039106, 'epoch': 2.52}

 21%|██        | 5907/28080 [11:40:47<43:59:50,  7.14s/it]
 21%|██        | 5908/28080 [11:40:55<43:56:25,  7.13s/it]
                                                          
{'loss': 0.653, 'learning_rate': 0.00045853681826041846, 'epoch': 2.52}

 21%|██        | 5908/28080 [11:40:55<43:56:25,  7.13s/it]
 21%|██        | 5909/28080 [11:41:02<43:55:19,  7.13s/it]
                                                          
{'loss': 0.6665, 'learning_rate': 0.00045852091277607865, 'epoch': 2.52}

 21%|██        | 5909/28080 [11:41:02<43:55:19,  7.13s/it]
 21%|██        | 5910/28080 [11:41:09<43:54:57,  7.13s/it]
                                                          
{'loss': 0.6297, 'learning_rate': 0.00045850500451758314, 'epoch': 2.52}

 21%|██        | 5910/28080 [11:41:09<43:54:57,  7.13s/it]
 21%|██        | 5911/28080 [11:41:16<43:51:39,  7.12s/it]
                                                          
{'loss': 0.6223, 'learning_rate': 0.00045848909348514375, 'epoch': 2.53}

 21%|██        | 5911/28080 [11:41:16<43:51:39,  7.12s/it]
 21%|██        | 5912/28080 [11:41:23<43:56:58,  7.14s/it]
                                                          
{'loss': 0.6459, 'learning_rate': 0.00045847317967897194, 'epoch': 2.53}

 21%|██        | 5912/28080 [11:41:23<43:56:58,  7.14s/it]
 21%|██        | 5913/28080 [11:41:30<44:00:46,  7.15s/it]
                                                          
{'loss': 0.6276, 'learning_rate': 0.00045845726309927967, 'epoch': 2.53}

 21%|██        | 5913/28080 [11:41:30<44:00:46,  7.15s/it]
 21%|██        | 5914/28080 [11:41:37<43:55:10,  7.13s/it]
                                                          
{'loss': 0.6502, 'learning_rate': 0.00045844134374627843, 'epoch': 2.53}

 21%|██        | 5914/28080 [11:41:37<43:55:10,  7.13s/it]
 21%|██        | 5915/28080 [11:41:44<43:46:29,  7.11s/it]
                                                          
{'loss': 0.6395, 'learning_rate': 0.0004584254216201803, 'epoch': 2.53}

 21%|██        | 5915/28080 [11:41:44<43:46:29,  7.11s/it]
 21%|██        | 5916/28080 [11:41:52<43:42:35,  7.10s/it]
                                                          
{'loss': 0.6455, 'learning_rate': 0.00045840949672119684, 'epoch': 2.53}

 21%|██        | 5916/28080 [11:41:52<43:42:35,  7.10s/it]
 21%|██        | 5917/28080 [11:41:59<43:39:17,  7.09s/it]
                                                          
{'loss': 0.6514, 'learning_rate': 0.0004583935690495401, 'epoch': 2.53}

 21%|██        | 5917/28080 [11:41:59<43:39:17,  7.09s/it]
 21%|██        | 5918/28080 [11:42:06<43:40:38,  7.09s/it]
                                                          
{'loss': 0.6227, 'learning_rate': 0.00045837763860542185, 'epoch': 2.53}

 21%|██        | 5918/28080 [11:42:06<43:40:38,  7.09s/it]
 21%|██        | 5919/28080 [11:42:13<43:35:03,  7.08s/it]
                                                          
{'loss': 0.6529, 'learning_rate': 0.00045836170538905415, 'epoch': 2.53}

 21%|██        | 5919/28080 [11:42:13<43:35:03,  7.08s/it]
 21%|██        | 5920/28080 [11:42:20<43:26:21,  7.06s/it]
                                                          
{'loss': 0.6558, 'learning_rate': 0.00045834576940064885, 'epoch': 2.53}

 21%|██        | 5920/28080 [11:42:20<43:26:21,  7.06s/it]
 21%|██        | 5921/28080 [11:42:27<43:49:10,  7.12s/it]
                                                          
{'loss': 0.639, 'learning_rate': 0.0004583298306404181, 'epoch': 2.53}

 21%|██        | 5921/28080 [11:42:27<43:49:10,  7.12s/it]
 21%|██        | 5922/28080 [11:42:34<43:42:59,  7.10s/it]
                                                          
{'loss': 0.6476, 'learning_rate': 0.0004583138891085738, 'epoch': 2.53}

 21%|██        | 5922/28080 [11:42:34<43:42:59,  7.10s/it]
 21%|██        | 5923/28080 [11:42:41<43:37:27,  7.09s/it]
                                                          
{'loss': 0.6519, 'learning_rate': 0.00045829794480532814, 'epoch': 2.53}

 21%|██        | 5923/28080 [11:42:41<43:37:27,  7.09s/it]
 21%|██        | 5924/28080 [11:42:48<43:51:00,  7.12s/it]
                                                          
{'loss': 0.6297, 'learning_rate': 0.0004582819977308932, 'epoch': 2.53}

 21%|██        | 5924/28080 [11:42:48<43:51:00,  7.12s/it]
 21%|██        | 5925/28080 [11:42:56<43:58:21,  7.15s/it]
                                                          
{'loss': 0.6287, 'learning_rate': 0.0004582660478854812, 'epoch': 2.53}

 21%|██        | 5925/28080 [11:42:56<43:58:21,  7.15s/it]
 21%|██        | 5926/28080 [11:43:03<43:47:28,  7.12s/it]
                                                          
{'loss': 0.6335, 'learning_rate': 0.00045825009526930427, 'epoch': 2.53}

 21%|██        | 5926/28080 [11:43:03<43:47:28,  7.12s/it]
 21%|██        | 5927/28080 [11:43:10<43:34:32,  7.08s/it]
                                                          
{'loss': 0.6488, 'learning_rate': 0.00045823413988257467, 'epoch': 2.53}

 21%|██        | 5927/28080 [11:43:10<43:34:32,  7.08s/it]
 21%|██        | 5928/28080 [11:43:17<43:31:37,  7.07s/it]
                                                          
{'loss': 0.6604, 'learning_rate': 0.00045821818172550464, 'epoch': 2.53}

 21%|██        | 5928/28080 [11:43:17<43:31:37,  7.07s/it]
 21%|██        | 5929/28080 [11:43:24<43:28:37,  7.07s/it]
                                                          
{'loss': 0.6409, 'learning_rate': 0.00045820222079830656, 'epoch': 2.53}

 21%|██        | 5929/28080 [11:43:24<43:28:37,  7.07s/it]
 21%|██        | 5930/28080 [11:43:31<43:37:26,  7.09s/it]
                                                          
{'loss': 0.6224, 'learning_rate': 0.0004581862571011926, 'epoch': 2.53}

 21%|██        | 5930/28080 [11:43:31<43:37:26,  7.09s/it]
 21%|██        | 5931/28080 [11:43:38<43:31:47,  7.08s/it]
                                                          
{'loss': 0.6214, 'learning_rate': 0.00045817029063437533, 'epoch': 2.53}

 21%|██        | 5931/28080 [11:43:38<43:31:47,  7.08s/it]
 21%|██        | 5932/28080 [11:43:45<43:41:23,  7.10s/it]
                                                          
{'loss': 0.6405, 'learning_rate': 0.00045815432139806713, 'epoch': 2.53}

 21%|██        | 5932/28080 [11:43:45<43:41:23,  7.10s/it]
 21%|██        | 5933/28080 [11:43:52<43:43:11,  7.11s/it]
                                                          
{'loss': 0.6556, 'learning_rate': 0.00045813834939248047, 'epoch': 2.53}

 21%|██        | 5933/28080 [11:43:52<43:43:11,  7.11s/it]
 21%|██        | 5934/28080 [11:43:59<43:47:23,  7.12s/it]
                                                          
{'loss': 0.6427, 'learning_rate': 0.0004581223746178277, 'epoch': 2.53}

 21%|██        | 5934/28080 [11:43:59<43:47:23,  7.12s/it]
 21%|██        | 5935/28080 [11:44:06<43:41:30,  7.10s/it]
                                                          
{'loss': 0.6344, 'learning_rate': 0.00045810639707432146, 'epoch': 2.54}

 21%|██        | 5935/28080 [11:44:06<43:41:30,  7.10s/it]
 21%|██        | 5936/28080 [11:44:13<43:34:48,  7.08s/it]
                                                          
{'loss': 0.6399, 'learning_rate': 0.00045809041676217433, 'epoch': 2.54}

 21%|██        | 5936/28080 [11:44:13<43:34:48,  7.08s/it]
 21%|██        | 5937/28080 [11:44:21<43:35:40,  7.09s/it]
                                                          
{'loss': 0.6448, 'learning_rate': 0.00045807443368159887, 'epoch': 2.54}

 21%|██        | 5937/28080 [11:44:21<43:35:40,  7.09s/it]
 21%|██        | 5938/28080 [11:44:27<43:22:32,  7.05s/it]
                                                          
{'loss': 0.6749, 'learning_rate': 0.0004580584478328077, 'epoch': 2.54}

 21%|██        | 5938/28080 [11:44:27<43:22:32,  7.05s/it]
 21%|██        | 5939/28080 [11:44:35<43:31:51,  7.08s/it]
                                                          
{'loss': 0.6399, 'learning_rate': 0.0004580424592160135, 'epoch': 2.54}

 21%|██        | 5939/28080 [11:44:35<43:31:51,  7.08s/it]
 21%|██        | 5940/28080 [11:44:42<43:21:08,  7.05s/it]
                                                          
{'loss': 0.6261, 'learning_rate': 0.0004580264678314291, 'epoch': 2.54}

 21%|██        | 5940/28080 [11:44:42<43:21:08,  7.05s/it]
 21%|██        | 5941/28080 [11:44:49<43:16:10,  7.04s/it]
                                                          
{'loss': 0.6425, 'learning_rate': 0.00045801047367926705, 'epoch': 2.54}

 21%|██        | 5941/28080 [11:44:49<43:16:10,  7.04s/it]
 21%|██        | 5942/28080 [11:44:56<43:26:23,  7.06s/it]
                                                          
{'loss': 0.6321, 'learning_rate': 0.00045799447675974034, 'epoch': 2.54}

 21%|██        | 5942/28080 [11:44:56<43:26:23,  7.06s/it]
 21%|██        | 5943/28080 [11:45:03<43:26:40,  7.07s/it]
                                                          
{'loss': 0.6449, 'learning_rate': 0.0004579784770730616, 'epoch': 2.54}

 21%|██        | 5943/28080 [11:45:03<43:26:40,  7.07s/it]
 21%|██        | 5944/28080 [11:45:10<43:29:55,  7.07s/it]
                                                          
{'loss': 0.6369, 'learning_rate': 0.00045796247461944386, 'epoch': 2.54}

 21%|██        | 5944/28080 [11:45:10<43:29:55,  7.07s/it]
 21%|██        | 5945/28080 [11:45:17<43:39:18,  7.10s/it]
                                                          
{'loss': 0.6472, 'learning_rate': 0.0004579464693990999, 'epoch': 2.54}

 21%|██        | 5945/28080 [11:45:17<43:39:18,  7.10s/it]
 21%|██        | 5946/28080 [11:45:24<43:37:16,  7.09s/it]
                                                          
{'loss': 0.6478, 'learning_rate': 0.0004579304614122427, 'epoch': 2.54}

 21%|██        | 5946/28080 [11:45:24<43:37:16,  7.09s/it]
 21%|██        | 5947/28080 [11:45:31<43:29:42,  7.07s/it]
                                                          
{'loss': 0.6506, 'learning_rate': 0.0004579144506590852, 'epoch': 2.54}

 21%|██        | 5947/28080 [11:45:31<43:29:42,  7.07s/it]
 21%|██        | 5948/28080 [11:45:38<43:21:45,  7.05s/it]
                                                          
{'loss': 0.6455, 'learning_rate': 0.0004578984371398405, 'epoch': 2.54}

 21%|██        | 5948/28080 [11:45:38<43:21:45,  7.05s/it]
 21%|██        | 5949/28080 [11:45:45<43:20:30,  7.05s/it]
                                                          
{'loss': 0.6788, 'learning_rate': 0.00045788242085472147, 'epoch': 2.54}

 21%|██        | 5949/28080 [11:45:45<43:20:30,  7.05s/it]
 21%|██        | 5950/28080 [11:45:52<43:23:02,  7.06s/it]
                                                          
{'loss': 0.6778, 'learning_rate': 0.0004578664018039413, 'epoch': 2.54}

 21%|██        | 5950/28080 [11:45:52<43:23:02,  7.06s/it]
 21%|██        | 5951/28080 [11:45:59<43:26:14,  7.07s/it]
                                                          
{'loss': 0.6372, 'learning_rate': 0.00045785037998771316, 'epoch': 2.54}

 21%|██        | 5951/28080 [11:45:59<43:26:14,  7.07s/it]
 21%|██        | 5952/28080 [11:46:07<43:32:50,  7.08s/it]
                                                          
{'loss': 0.6442, 'learning_rate': 0.0004578343554062502, 'epoch': 2.54}

 21%|██        | 5952/28080 [11:46:07<43:32:50,  7.08s/it]
 21%|██        | 5953/28080 [11:46:14<43:30:36,  7.08s/it]
                                                          
{'loss': 0.6325, 'learning_rate': 0.0004578183280597654, 'epoch': 2.54}

 21%|██        | 5953/28080 [11:46:14<43:30:36,  7.08s/it]
 21%|██        | 5954/28080 [11:46:21<43:31:56,  7.08s/it]
                                                          
{'loss': 0.643, 'learning_rate': 0.0004578022979484722, 'epoch': 2.54}

 21%|██        | 5954/28080 [11:46:21<43:31:56,  7.08s/it]
 21%|██        | 5955/28080 [11:46:28<43:32:04,  7.08s/it]
                                                          
{'loss': 0.6453, 'learning_rate': 0.00045778626507258385, 'epoch': 2.54}

 21%|██        | 5955/28080 [11:46:28<43:32:04,  7.08s/it]
 21%|██        | 5956/28080 [11:46:35<43:49:17,  7.13s/it]
                                                          
{'loss': 0.6278, 'learning_rate': 0.0004577702294323136, 'epoch': 2.54}

 21%|██        | 5956/28080 [11:46:35<43:49:17,  7.13s/it]
 21%|██        | 5957/28080 [11:46:42<43:48:22,  7.13s/it]
                                                          
{'loss': 0.6558, 'learning_rate': 0.0004577541910278747, 'epoch': 2.54}

 21%|██        | 5957/28080 [11:46:42<43:48:22,  7.13s/it]
 21%|██        | 5958/28080 [11:46:49<43:42:54,  7.11s/it]
                                                          
{'loss': 0.645, 'learning_rate': 0.0004577381498594807, 'epoch': 2.55}

 21%|██        | 5958/28080 [11:46:49<43:42:54,  7.11s/it]
 21%|██        | 5959/28080 [11:46:56<43:44:40,  7.12s/it]
                                                          
{'loss': 0.6477, 'learning_rate': 0.00045772210592734495, 'epoch': 2.55}

 21%|██        | 5959/28080 [11:46:56<43:44:40,  7.12s/it]
 21%|██        | 5960/28080 [11:47:03<43:42:24,  7.11s/it]
                                                          
{'loss': 0.6475, 'learning_rate': 0.0004577060592316808, 'epoch': 2.55}

 21%|██        | 5960/28080 [11:47:03<43:42:24,  7.11s/it]
 21%|██        | 5961/28080 [11:47:11<43:57:25,  7.15s/it]
                                                          
{'loss': 0.6403, 'learning_rate': 0.0004576900097727018, 'epoch': 2.55}

 21%|██        | 5961/28080 [11:47:11<43:57:25,  7.15s/it]
 21%|██        | 5962/28080 [11:47:18<43:55:37,  7.15s/it]
                                                          
{'loss': 0.6358, 'learning_rate': 0.00045767395755062155, 'epoch': 2.55}

 21%|██        | 5962/28080 [11:47:18<43:55:37,  7.15s/it]
 21%|██        | 5963/28080 [11:47:25<43:40:46,  7.11s/it]
                                                          
{'loss': 0.6541, 'learning_rate': 0.00045765790256565355, 'epoch': 2.55}

 21%|██        | 5963/28080 [11:47:25<43:40:46,  7.11s/it]
 21%|██        | 5964/28080 [11:47:32<43:42:13,  7.11s/it]
                                                          
{'loss': 0.6596, 'learning_rate': 0.0004576418448180113, 'epoch': 2.55}

 21%|██        | 5964/28080 [11:47:32<43:42:13,  7.11s/it]
 21%|██        | 5965/28080 [11:47:39<43:43:32,  7.12s/it]
                                                          
{'loss': 0.6527, 'learning_rate': 0.0004576257843079086, 'epoch': 2.55}

 21%|██        | 5965/28080 [11:47:39<43:43:32,  7.12s/it]
 21%|██        | 5966/28080 [11:47:46<43:32:41,  7.09s/it]
                                                          
{'loss': 0.6209, 'learning_rate': 0.000457609721035559, 'epoch': 2.55}

 21%|██        | 5966/28080 [11:47:46<43:32:41,  7.09s/it]
 21%|██▏       | 5967/28080 [11:47:53<43:28:39,  7.08s/it]
                                                          
{'loss': 0.6551, 'learning_rate': 0.00045759365500117624, 'epoch': 2.55}

 21%|██▏       | 5967/28080 [11:47:53<43:28:39,  7.08s/it]
 21%|██▏       | 5968/28080 [11:48:00<43:34:58,  7.10s/it]
                                                          
{'loss': 0.6503, 'learning_rate': 0.000457577586204974, 'epoch': 2.55}

 21%|██▏       | 5968/28080 [11:48:00<43:34:58,  7.10s/it]
 21%|██▏       | 5969/28080 [11:48:07<43:43:42,  7.12s/it]
                                                          
{'loss': 0.6357, 'learning_rate': 0.00045756151464716624, 'epoch': 2.55}

 21%|██▏       | 5969/28080 [11:48:07<43:43:42,  7.12s/it]
 21%|██▏       | 5970/28080 [11:48:15<43:35:18,  7.10s/it]
                                                          
{'loss': 0.6392, 'learning_rate': 0.0004575454403279666, 'epoch': 2.55}

 21%|██▏       | 5970/28080 [11:48:15<43:35:18,  7.10s/it]
 21%|██▏       | 5971/28080 [11:48:22<43:43:51,  7.12s/it]
                                                          
{'loss': 0.6398, 'learning_rate': 0.000457529363247589, 'epoch': 2.55}

 21%|██▏       | 5971/28080 [11:48:22<43:43:51,  7.12s/it]
 21%|██▏       | 5972/28080 [11:48:29<43:55:00,  7.15s/it]
                                                          
{'loss': 0.6165, 'learning_rate': 0.0004575132834062473, 'epoch': 2.55}

 21%|██▏       | 5972/28080 [11:48:29<43:55:00,  7.15s/it]
 21%|██▏       | 5973/28080 [11:48:36<43:44:59,  7.12s/it]
                                                          
{'loss': 0.6374, 'learning_rate': 0.0004574972008041555, 'epoch': 2.55}

 21%|██▏       | 5973/28080 [11:48:36<43:44:59,  7.12s/it]
 21%|██▏       | 5974/28080 [11:48:43<43:48:04,  7.13s/it]
                                                          
{'loss': 0.6253, 'learning_rate': 0.00045748111544152736, 'epoch': 2.55}

 21%|██▏       | 5974/28080 [11:48:43<43:48:04,  7.13s/it]
 21%|██▏       | 5975/28080 [11:48:50<43:43:01,  7.12s/it]
                                                          
{'loss': 0.6315, 'learning_rate': 0.00045746502731857714, 'epoch': 2.55}

 21%|██▏       | 5975/28080 [11:48:50<43:43:01,  7.12s/it]
 21%|██▏       | 5976/28080 [11:48:57<43:39:58,  7.11s/it]
                                                          
{'loss': 0.6361, 'learning_rate': 0.00045744893643551876, 'epoch': 2.55}

 21%|██▏       | 5976/28080 [11:48:57<43:39:58,  7.11s/it]
 21%|██▏       | 5977/28080 [11:49:04<43:38:23,  7.11s/it]
                                                          
{'loss': 0.6511, 'learning_rate': 0.0004574328427925662, 'epoch': 2.55}

 21%|██▏       | 5977/28080 [11:49:04<43:38:23,  7.11s/it]
 21%|██▏       | 5978/28080 [11:49:12<43:40:32,  7.11s/it]
                                                          
{'loss': 0.6195, 'learning_rate': 0.0004574167463899338, 'epoch': 2.55}

 21%|██▏       | 5978/28080 [11:49:12<43:40:32,  7.11s/it]
 21%|██▏       | 5979/28080 [11:49:19<43:41:16,  7.12s/it]
                                                          
{'loss': 0.6197, 'learning_rate': 0.0004574006472278355, 'epoch': 2.55}

 21%|██▏       | 5979/28080 [11:49:19<43:41:16,  7.12s/it]
 21%|██▏       | 5980/28080 [11:49:26<43:37:18,  7.11s/it]
                                                          
{'loss': 0.6191, 'learning_rate': 0.0004573845453064856, 'epoch': 2.55}

 21%|██▏       | 5980/28080 [11:49:26<43:37:18,  7.11s/it]
 21%|██▏       | 5981/28080 [11:49:33<43:35:04,  7.10s/it]
                                                          
{'loss': 0.6536, 'learning_rate': 0.0004573684406260982, 'epoch': 2.56}

 21%|██▏       | 5981/28080 [11:49:33<43:35:04,  7.10s/it]
 21%|██▏       | 5982/28080 [11:49:40<43:40:34,  7.12s/it]
                                                          
{'loss': 0.6359, 'learning_rate': 0.00045735233318688776, 'epoch': 2.56}

 21%|██▏       | 5982/28080 [11:49:40<43:40:34,  7.12s/it]
 21%|██▏       | 5983/28080 [11:49:47<43:40:41,  7.12s/it]
                                                          
{'loss': 0.6375, 'learning_rate': 0.0004573362229890683, 'epoch': 2.56}

 21%|██▏       | 5983/28080 [11:49:47<43:40:41,  7.12s/it]
 21%|██▏       | 5984/28080 [11:49:54<43:36:08,  7.10s/it]
                                                          
{'loss': 0.6471, 'learning_rate': 0.00045732011003285435, 'epoch': 2.56}

 21%|██▏       | 5984/28080 [11:49:54<43:36:08,  7.10s/it]
 21%|██▏       | 5985/28080 [11:50:01<43:26:50,  7.08s/it]
                                                          
{'loss': 0.6487, 'learning_rate': 0.00045730399431846014, 'epoch': 2.56}

 21%|██▏       | 5985/28080 [11:50:01<43:26:50,  7.08s/it]
 21%|██▏       | 5986/28080 [11:50:08<43:29:38,  7.09s/it]
                                                          
{'loss': 0.6329, 'learning_rate': 0.0004572878758461002, 'epoch': 2.56}

 21%|██▏       | 5986/28080 [11:50:08<43:29:38,  7.09s/it]
 21%|██▏       | 5987/28080 [11:50:15<43:28:19,  7.08s/it]
                                                          
{'loss': 0.6286, 'learning_rate': 0.000457271754615989, 'epoch': 2.56}

 21%|██▏       | 5987/28080 [11:50:15<43:28:19,  7.08s/it]
 21%|██▏       | 5988/28080 [11:50:22<43:33:12,  7.10s/it]
                                                          
{'loss': 0.6282, 'learning_rate': 0.00045725563062834083, 'epoch': 2.56}

 21%|██▏       | 5988/28080 [11:50:23<43:33:12,  7.10s/it]
 21%|██▏       | 5989/28080 [11:50:30<43:24:40,  7.07s/it]
                                                          
{'loss': 0.6541, 'learning_rate': 0.0004572395038833703, 'epoch': 2.56}

 21%|██▏       | 5989/28080 [11:50:30<43:24:40,  7.07s/it]
 21%|██▏       | 5990/28080 [11:50:37<43:22:57,  7.07s/it]
                                                          
{'loss': 0.651, 'learning_rate': 0.000457223374381292, 'epoch': 2.56}

 21%|██▏       | 5990/28080 [11:50:37<43:22:57,  7.07s/it]
 21%|██▏       | 5991/28080 [11:50:44<43:20:52,  7.06s/it]
                                                          
{'loss': 0.6301, 'learning_rate': 0.0004572072421223205, 'epoch': 2.56}

 21%|██▏       | 5991/28080 [11:50:44<43:20:52,  7.06s/it]
 21%|██▏       | 5992/28080 [11:50:51<43:27:13,  7.08s/it]
                                                          
{'loss': 0.655, 'learning_rate': 0.00045719110710667045, 'epoch': 2.56}

 21%|██▏       | 5992/28080 [11:50:51<43:27:13,  7.08s/it]
 21%|██▏       | 5993/28080 [11:50:58<43:29:17,  7.09s/it]
                                                          
{'loss': 0.639, 'learning_rate': 0.0004571749693345564, 'epoch': 2.56}

 21%|██▏       | 5993/28080 [11:50:58<43:29:17,  7.09s/it]
 21%|██▏       | 5994/28080 [11:51:05<43:29:47,  7.09s/it]
                                                          
{'loss': 0.6466, 'learning_rate': 0.00045715882880619315, 'epoch': 2.56}

 21%|██▏       | 5994/28080 [11:51:05<43:29:47,  7.09s/it]
 21%|██▏       | 5995/28080 [11:51:12<43:27:10,  7.08s/it]
                                                          
{'loss': 0.6493, 'learning_rate': 0.00045714268552179537, 'epoch': 2.56}

 21%|██▏       | 5995/28080 [11:51:12<43:27:10,  7.08s/it]
 21%|██▏       | 5996/28080 [11:51:19<43:34:08,  7.10s/it]
                                                          
{'loss': 0.6602, 'learning_rate': 0.0004571265394815778, 'epoch': 2.56}

 21%|██▏       | 5996/28080 [11:51:19<43:34:08,  7.10s/it]
 21%|██▏       | 5997/28080 [11:51:26<43:38:00,  7.11s/it]
                                                          
{'loss': 0.6678, 'learning_rate': 0.00045711039068575544, 'epoch': 2.56}

 21%|██▏       | 5997/28080 [11:51:26<43:38:00,  7.11s/it]
 21%|██▏       | 5998/28080 [11:51:33<43:24:24,  7.08s/it]
                                                          
{'loss': 0.6602, 'learning_rate': 0.0004570942391345429, 'epoch': 2.56}

 21%|██▏       | 5998/28080 [11:51:33<43:24:24,  7.08s/it]
 21%|██▏       | 5999/28080 [11:51:40<43:25:12,  7.08s/it]
                                                          
{'loss': 0.6363, 'learning_rate': 0.00045707808482815516, 'epoch': 2.56}

 21%|██▏       | 5999/28080 [11:51:40<43:25:12,  7.08s/it]
 21%|██▏       | 6000/28080 [11:51:47<43:14:48,  7.05s/it]
                                                          
{'loss': 0.6489, 'learning_rate': 0.00045706192776680715, 'epoch': 2.56}

 21%|██▏       | 6000/28080 [11:51:47<43:14:48,  7.05s/it]
 21%|██▏       | 6001/28080 [11:51:55<43:24:58,  7.08s/it]
                                                          
{'loss': 0.6423, 'learning_rate': 0.0004570457679507138, 'epoch': 2.56}

 21%|██▏       | 6001/28080 [11:51:55<43:24:58,  7.08s/it]
 21%|██▏       | 6002/28080 [11:52:01<43:13:20,  7.05s/it]
                                                          
{'loss': 0.6611, 'learning_rate': 0.00045702960538009015, 'epoch': 2.56}

 21%|██▏       | 6002/28080 [11:52:01<43:13:20,  7.05s/it]
 21%|██▏       | 6003/28080 [11:52:09<43:13:59,  7.05s/it]
                                                          
{'loss': 0.6414, 'learning_rate': 0.0004570134400551511, 'epoch': 2.56}

 21%|██▏       | 6003/28080 [11:52:09<43:13:59,  7.05s/it]
 21%|██▏       | 6004/28080 [11:52:16<43:19:02,  7.06s/it]
                                                          
{'loss': 0.6422, 'learning_rate': 0.00045699727197611183, 'epoch': 2.56}

 21%|██▏       | 6004/28080 [11:52:16<43:19:02,  7.06s/it]
 21%|██▏       | 6005/28080 [11:52:23<43:26:05,  7.08s/it]
                                                          
{'loss': 0.6425, 'learning_rate': 0.0004569811011431875, 'epoch': 2.57}

 21%|██▏       | 6005/28080 [11:52:23<43:26:05,  7.08s/it]
 21%|██▏       | 6006/28080 [11:52:30<43:19:16,  7.07s/it]
                                                          
{'loss': 0.6423, 'learning_rate': 0.00045696492755659303, 'epoch': 2.57}

 21%|██▏       | 6006/28080 [11:52:30<43:19:16,  7.07s/it]
 21%|██▏       | 6007/28080 [11:52:37<43:20:46,  7.07s/it]
                                                          
{'loss': 0.6227, 'learning_rate': 0.0004569487512165437, 'epoch': 2.57}

 21%|██▏       | 6007/28080 [11:52:37<43:20:46,  7.07s/it]
 21%|██▏       | 6008/28080 [11:52:44<43:15:30,  7.06s/it]
                                                          
{'loss': 0.6413, 'learning_rate': 0.00045693257212325476, 'epoch': 2.57}

 21%|██▏       | 6008/28080 [11:52:44<43:15:30,  7.06s/it]
 21%|██▏       | 6009/28080 [11:52:51<43:19:59,  7.07s/it]
                                                          
{'loss': 0.6396, 'learning_rate': 0.00045691639027694143, 'epoch': 2.57}

 21%|██▏       | 6009/28080 [11:52:51<43:19:59,  7.07s/it]
 21%|██▏       | 6010/28080 [11:52:58<43:32:39,  7.10s/it]
                                                          
{'loss': 0.6329, 'learning_rate': 0.00045690020567781906, 'epoch': 2.57}

 21%|██▏       | 6010/28080 [11:52:58<43:32:39,  7.10s/it]
 21%|██▏       | 6011/28080 [11:53:05<43:35:06,  7.11s/it]
                                                          
{'loss': 0.6421, 'learning_rate': 0.0004568840183261028, 'epoch': 2.57}

 21%|██▏       | 6011/28080 [11:53:05<43:35:06,  7.11s/it]
 21%|██▏       | 6012/28080 [11:53:12<43:38:25,  7.12s/it]
                                                          
{'loss': 0.6517, 'learning_rate': 0.0004568678282220082, 'epoch': 2.57}

 21%|██▏       | 6012/28080 [11:53:12<43:38:25,  7.12s/it]
 21%|██▏       | 6013/28080 [11:53:20<43:37:01,  7.12s/it]
                                                          
{'loss': 0.6461, 'learning_rate': 0.0004568516353657505, 'epoch': 2.57}

 21%|██▏       | 6013/28080 [11:53:20<43:37:01,  7.12s/it]
 21%|██▏       | 6014/28080 [11:53:27<43:35:20,  7.11s/it]
                                                          
{'loss': 0.628, 'learning_rate': 0.00045683543975754516, 'epoch': 2.57}

 21%|██▏       | 6014/28080 [11:53:27<43:35:20,  7.11s/it]
 21%|██▏       | 6015/28080 [11:53:34<43:27:22,  7.09s/it]
                                                          
{'loss': 0.6351, 'learning_rate': 0.0004568192413976077, 'epoch': 2.57}

 21%|██▏       | 6015/28080 [11:53:34<43:27:22,  7.09s/it]
 21%|██▏       | 6016/28080 [11:53:41<43:13:57,  7.05s/it]
                                                          
{'loss': 0.6518, 'learning_rate': 0.00045680304028615363, 'epoch': 2.57}

 21%|██▏       | 6016/28080 [11:53:41<43:13:57,  7.05s/it]
 21%|██▏       | 6017/28080 [11:53:48<43:24:17,  7.08s/it]
                                                          
{'loss': 0.6328, 'learning_rate': 0.0004567868364233984, 'epoch': 2.57}

 21%|██▏       | 6017/28080 [11:53:48<43:24:17,  7.08s/it]
 21%|██▏       | 6018/28080 [11:53:55<43:32:48,  7.11s/it]
                                                          
{'loss': 0.6329, 'learning_rate': 0.00045677062980955776, 'epoch': 2.57}

 21%|██▏       | 6018/28080 [11:53:55<43:32:48,  7.11s/it]
 21%|██▏       | 6019/28080 [11:54:02<43:28:20,  7.09s/it]
                                                          
{'loss': 0.6405, 'learning_rate': 0.00045675442044484704, 'epoch': 2.57}

 21%|██▏       | 6019/28080 [11:54:02<43:28:20,  7.09s/it]
 21%|██▏       | 6020/28080 [11:54:09<43:38:13,  7.12s/it]
                                                          
{'loss': 0.6449, 'learning_rate': 0.00045673820832948213, 'epoch': 2.57}

 21%|██▏       | 6020/28080 [11:54:09<43:38:13,  7.12s/it]
 21%|██▏       | 6021/28080 [11:54:16<43:25:42,  7.09s/it]
                                                          
{'loss': 0.6507, 'learning_rate': 0.00045672199346367867, 'epoch': 2.57}

 21%|██▏       | 6021/28080 [11:54:16<43:25:42,  7.09s/it]
 21%|██▏       | 6022/28080 [11:54:23<43:28:02,  7.09s/it]
                                                          
{'loss': 0.6266, 'learning_rate': 0.0004567057758476523, 'epoch': 2.57}

 21%|██▏       | 6022/28080 [11:54:23<43:28:02,  7.09s/it]
 21%|██▏       | 6023/28080 [11:54:30<43:30:13,  7.10s/it]
                                                          
{'loss': 0.6401, 'learning_rate': 0.00045668955548161885, 'epoch': 2.57}

 21%|██▏       | 6023/28080 [11:54:30<43:30:13,  7.10s/it]
 21%|██▏       | 6024/28080 [11:54:37<43:13:37,  7.06s/it]
                                                          
{'loss': 0.6704, 'learning_rate': 0.0004566733323657941, 'epoch': 2.57}

 21%|██▏       | 6024/28080 [11:54:37<43:13:37,  7.06s/it]
 21%|██▏       | 6025/28080 [11:54:44<43:11:34,  7.05s/it]
                                                          
{'loss': 0.6262, 'learning_rate': 0.00045665710650039386, 'epoch': 2.57}

 21%|██▏       | 6025/28080 [11:54:44<43:11:34,  7.05s/it]
 21%|██▏       | 6026/28080 [11:54:51<43:07:12,  7.04s/it]
                                                          
{'loss': 0.6408, 'learning_rate': 0.000456640877885634, 'epoch': 2.57}

 21%|██▏       | 6026/28080 [11:54:51<43:07:12,  7.04s/it]
 21%|██▏       | 6027/28080 [11:54:59<43:18:58,  7.07s/it]
                                                          
{'loss': 0.6408, 'learning_rate': 0.0004566246465217305, 'epoch': 2.57}

 21%|██▏       | 6027/28080 [11:54:59<43:18:58,  7.07s/it]
 21%|██▏       | 6028/28080 [11:55:06<43:16:39,  7.07s/it]
                                                          
{'loss': 0.6648, 'learning_rate': 0.0004566084124088992, 'epoch': 2.58}

 21%|██▏       | 6028/28080 [11:55:06<43:16:39,  7.07s/it]
 21%|██▏       | 6029/28080 [11:55:13<43:22:50,  7.08s/it]
                                                          
{'loss': 0.6588, 'learning_rate': 0.0004565921755473561, 'epoch': 2.58}

 21%|██▏       | 6029/28080 [11:55:13<43:22:50,  7.08s/it]
 21%|██▏       | 6030/28080 [11:55:20<43:24:50,  7.09s/it]
                                                          
{'loss': 0.6482, 'learning_rate': 0.00045657593593731726, 'epoch': 2.58}

 21%|██▏       | 6030/28080 [11:55:20<43:24:50,  7.09s/it]
 21%|██▏       | 6031/28080 [11:55:27<43:27:48,  7.10s/it]
                                                          
{'loss': 0.6586, 'learning_rate': 0.00045655969357899875, 'epoch': 2.58}

 21%|██▏       | 6031/28080 [11:55:27<43:27:48,  7.10s/it]
 21%|██▏       | 6032/28080 [11:55:34<43:31:43,  7.11s/it]
                                                          
{'loss': 0.6447, 'learning_rate': 0.00045654344847261653, 'epoch': 2.58}

 21%|██▏       | 6032/28080 [11:55:34<43:31:43,  7.11s/it]
 21%|██▏       | 6033/28080 [11:55:41<43:31:46,  7.11s/it]
                                                          
{'loss': 0.6525, 'learning_rate': 0.00045652720061838684, 'epoch': 2.58}

 21%|██▏       | 6033/28080 [11:55:41<43:31:46,  7.11s/it]
 21%|██▏       | 6034/28080 [11:55:48<43:33:26,  7.11s/it]
                                                          
{'loss': 0.6472, 'learning_rate': 0.0004565109500165258, 'epoch': 2.58}

 21%|██▏       | 6034/28080 [11:55:48<43:33:26,  7.11s/it]
 21%|██▏       | 6035/28080 [11:55:55<43:34:06,  7.11s/it]
                                                          
{'loss': 0.6423, 'learning_rate': 0.00045649469666724966, 'epoch': 2.58}

 21%|██▏       | 6035/28080 [11:55:55<43:34:06,  7.11s/it]
 21%|██▏       | 6036/28080 [11:56:02<43:19:20,  7.07s/it]
                                                          
{'loss': 0.6519, 'learning_rate': 0.0004564784405707746, 'epoch': 2.58}

 21%|██▏       | 6036/28080 [11:56:02<43:19:20,  7.07s/it]
 21%|██▏       | 6037/28080 [11:56:10<43:39:41,  7.13s/it]
                                                          
{'loss': 0.645, 'learning_rate': 0.0004564621817273168, 'epoch': 2.58}

 21%|██▏       | 6037/28080 [11:56:10<43:39:41,  7.13s/it]
 22%|██▏       | 6038/28080 [11:56:17<43:33:59,  7.12s/it]
                                                          
{'loss': 0.6467, 'learning_rate': 0.0004564459201370928, 'epoch': 2.58}

 22%|██▏       | 6038/28080 [11:56:17<43:33:59,  7.12s/it]
 22%|██▏       | 6039/28080 [11:56:24<43:35:18,  7.12s/it]
                                                          
{'loss': 0.625, 'learning_rate': 0.0004564296558003187, 'epoch': 2.58}

 22%|██▏       | 6039/28080 [11:56:24<43:35:18,  7.12s/it]
 22%|██▏       | 6040/28080 [11:56:31<43:41:24,  7.14s/it]
                                                          
{'loss': 0.6224, 'learning_rate': 0.00045641338871721106, 'epoch': 2.58}

 22%|██▏       | 6040/28080 [11:56:31<43:41:24,  7.14s/it]
 22%|██▏       | 6041/28080 [11:56:38<43:45:18,  7.15s/it]
                                                          
{'loss': 0.6477, 'learning_rate': 0.0004563971188879862, 'epoch': 2.58}

 22%|██▏       | 6041/28080 [11:56:38<43:45:18,  7.15s/it]
 22%|██▏       | 6042/28080 [11:56:45<43:45:50,  7.15s/it]
                                                          
{'loss': 0.6405, 'learning_rate': 0.00045638084631286066, 'epoch': 2.58}

 22%|██▏       | 6042/28080 [11:56:45<43:45:50,  7.15s/it]
 22%|██▏       | 6043/28080 [11:56:53<43:44:37,  7.15s/it]
                                                          
{'loss': 0.634, 'learning_rate': 0.0004563645709920508, 'epoch': 2.58}

 22%|██▏       | 6043/28080 [11:56:53<43:44:37,  7.15s/it]
 22%|██▏       | 6044/28080 [11:57:00<43:28:31,  7.10s/it]
                                                          
{'loss': 0.6351, 'learning_rate': 0.0004563482929257733, 'epoch': 2.58}

 22%|██▏       | 6044/28080 [11:57:00<43:28:31,  7.10s/it]
 22%|██▏       | 6045/28080 [11:57:07<43:23:11,  7.09s/it]
                                                          
{'loss': 0.6583, 'learning_rate': 0.0004563320121142445, 'epoch': 2.58}

 22%|██▏       | 6045/28080 [11:57:07<43:23:11,  7.09s/it]
 22%|██▏       | 6046/28080 [11:57:14<43:11:27,  7.06s/it]
                                                          
{'loss': 0.6429, 'learning_rate': 0.0004563157285576812, 'epoch': 2.58}

 22%|██▏       | 6046/28080 [11:57:14<43:11:27,  7.06s/it]
 22%|██▏       | 6047/28080 [11:57:21<43:14:53,  7.07s/it]
                                                          
{'loss': 0.6504, 'learning_rate': 0.00045629944225630007, 'epoch': 2.58}

 22%|██▏       | 6047/28080 [11:57:21<43:14:53,  7.07s/it]
 22%|██▏       | 6048/28080 [11:57:28<43:18:26,  7.08s/it]
                                                          
{'loss': 0.6308, 'learning_rate': 0.0004562831532103176, 'epoch': 2.58}

 22%|██▏       | 6048/28080 [11:57:28<43:18:26,  7.08s/it]
 22%|██▏       | 6049/28080 [11:57:35<43:14:51,  7.07s/it]
                                                          
{'loss': 0.6133, 'learning_rate': 0.0004562668614199506, 'epoch': 2.58}

 22%|██▏       | 6049/28080 [11:57:35<43:14:51,  7.07s/it]
 22%|██▏       | 6050/28080 [11:57:42<43:21:50,  7.09s/it]
                                                          
{'loss': 0.6263, 'learning_rate': 0.0004562505668854158, 'epoch': 2.58}

 22%|██▏       | 6050/28080 [11:57:42<43:21:50,  7.09s/it]
 22%|██▏       | 6051/28080 [11:57:49<43:16:13,  7.07s/it]
                                                          
{'loss': 0.646, 'learning_rate': 0.00045623426960693, 'epoch': 2.58}

 22%|██▏       | 6051/28080 [11:57:49<43:16:13,  7.07s/it]
 22%|██▏       | 6052/28080 [11:57:56<43:18:27,  7.08s/it]
                                                          
{'loss': 0.6442, 'learning_rate': 0.00045621796958470996, 'epoch': 2.59}

 22%|██▏       | 6052/28080 [11:57:56<43:18:27,  7.08s/it]
 22%|██▏       | 6053/28080 [11:58:03<43:15:11,  7.07s/it]
                                                          
{'loss': 0.647, 'learning_rate': 0.00045620166681897264, 'epoch': 2.59}

 22%|██▏       | 6053/28080 [11:58:03<43:15:11,  7.07s/it]
 22%|██▏       | 6054/28080 [11:58:10<43:09:38,  7.05s/it]
                                                          
{'loss': 0.6557, 'learning_rate': 0.00045618536130993484, 'epoch': 2.59}

 22%|██▏       | 6054/28080 [11:58:10<43:09:38,  7.05s/it]
 22%|██▏       | 6055/28080 [11:58:17<43:14:04,  7.07s/it]
                                                          
{'loss': 0.6321, 'learning_rate': 0.00045616905305781354, 'epoch': 2.59}

 22%|██▏       | 6055/28080 [11:58:17<43:14:04,  7.07s/it]
 22%|██▏       | 6056/28080 [11:58:24<43:06:31,  7.05s/it]
                                                          
{'loss': 0.6436, 'learning_rate': 0.00045615274206282566, 'epoch': 2.59}

 22%|██▏       | 6056/28080 [11:58:24<43:06:31,  7.05s/it]
 22%|██▏       | 6057/28080 [11:58:31<43:18:38,  7.08s/it]
                                                          
{'loss': 0.6492, 'learning_rate': 0.0004561364283251882, 'epoch': 2.59}

 22%|██▏       | 6057/28080 [11:58:31<43:18:38,  7.08s/it]
 22%|██▏       | 6058/28080 [11:58:38<43:16:41,  7.07s/it]
                                                          
{'loss': 0.6677, 'learning_rate': 0.00045612011184511825, 'epoch': 2.59}

 22%|██▏       | 6058/28080 [11:58:38<43:16:41,  7.07s/it]
 22%|██▏       | 6059/28080 [11:58:46<43:16:38,  7.07s/it]
                                                          
{'loss': 0.6327, 'learning_rate': 0.00045610379262283284, 'epoch': 2.59}

 22%|██▏       | 6059/28080 [11:58:46<43:16:38,  7.07s/it]
 22%|██▏       | 6060/28080 [11:58:53<43:03:53,  7.04s/it]
                                                          
{'loss': 0.6648, 'learning_rate': 0.00045608747065854907, 'epoch': 2.59}

 22%|██▏       | 6060/28080 [11:58:53<43:03:53,  7.04s/it]
 22%|██▏       | 6061/28080 [11:59:00<43:12:25,  7.06s/it]
                                                          
{'loss': 0.6695, 'learning_rate': 0.00045607114595248415, 'epoch': 2.59}

 22%|██▏       | 6061/28080 [11:59:00<43:12:25,  7.06s/it]
 22%|██▏       | 6062/28080 [11:59:07<43:08:48,  7.05s/it]
                                                          
{'loss': 0.623, 'learning_rate': 0.0004560548185048552, 'epoch': 2.59}

 22%|██▏       | 6062/28080 [11:59:07<43:08:48,  7.05s/it]
 22%|██▏       | 6063/28080 [11:59:14<43:16:08,  7.07s/it]
                                                          
{'loss': 0.6402, 'learning_rate': 0.00045603848831587946, 'epoch': 2.59}

 22%|██▏       | 6063/28080 [11:59:14<43:16:08,  7.07s/it]
 22%|██▏       | 6064/28080 [11:59:21<43:13:29,  7.07s/it]
                                                          
{'loss': 0.6588, 'learning_rate': 0.0004560221553857742, 'epoch': 2.59}

 22%|██▏       | 6064/28080 [11:59:21<43:13:29,  7.07s/it]
 22%|██▏       | 6065/28080 [11:59:28<43:12:45,  7.07s/it]
                                                          
{'loss': 0.644, 'learning_rate': 0.00045600581971475673, 'epoch': 2.59}

 22%|██▏       | 6065/28080 [11:59:28<43:12:45,  7.07s/it]
 22%|██▏       | 6066/28080 [11:59:35<43:16:26,  7.08s/it]
                                                          
{'loss': 0.6446, 'learning_rate': 0.0004559894813030444, 'epoch': 2.59}

 22%|██▏       | 6066/28080 [11:59:35<43:16:26,  7.08s/it]
 22%|██▏       | 6067/28080 [11:59:42<43:25:34,  7.10s/it]
                                                          
{'loss': 0.6134, 'learning_rate': 0.00045597314015085444, 'epoch': 2.59}

 22%|██▏       | 6067/28080 [11:59:42<43:25:34,  7.10s/it]
 22%|██▏       | 6068/28080 [11:59:49<43:25:16,  7.10s/it]
                                                          
{'loss': 0.6582, 'learning_rate': 0.00045595679625840436, 'epoch': 2.59}

 22%|██▏       | 6068/28080 [11:59:49<43:25:16,  7.10s/it]
 22%|██▏       | 6069/28080 [11:59:56<43:31:31,  7.12s/it]
                                                          
{'loss': 0.6252, 'learning_rate': 0.00045594044962591165, 'epoch': 2.59}

 22%|██▏       | 6069/28080 [11:59:56<43:31:31,  7.12s/it]
 22%|██▏       | 6070/28080 [12:00:03<43:15:50,  7.08s/it]
                                                          
{'loss': 0.665, 'learning_rate': 0.00045592410025359364, 'epoch': 2.59}

 22%|██▏       | 6070/28080 [12:00:03<43:15:50,  7.08s/it]
 22%|██▏       | 6071/28080 [12:00:11<43:19:23,  7.09s/it]
                                                          
{'loss': 0.641, 'learning_rate': 0.0004559077481416679, 'epoch': 2.59}

 22%|██▏       | 6071/28080 [12:00:11<43:19:23,  7.09s/it]
 22%|██▏       | 6072/28080 [12:00:18<43:12:14,  7.07s/it]
                                                          
{'loss': 0.6377, 'learning_rate': 0.000455891393290352, 'epoch': 2.59}

 22%|██▏       | 6072/28080 [12:00:18<43:12:14,  7.07s/it]
 22%|██▏       | 6073/28080 [12:00:25<43:09:44,  7.06s/it]
                                                          
{'loss': 0.643, 'learning_rate': 0.00045587503569986354, 'epoch': 2.59}

 22%|██▏       | 6073/28080 [12:00:25<43:09:44,  7.06s/it]
 22%|██▏       | 6074/28080 [12:00:32<43:18:12,  7.08s/it]
                                                          
{'loss': 0.6305, 'learning_rate': 0.00045585867537042014, 'epoch': 2.59}

 22%|██▏       | 6074/28080 [12:00:32<43:18:12,  7.08s/it]
 22%|██▏       | 6075/28080 [12:00:39<43:17:04,  7.08s/it]
                                                          
{'loss': 0.6282, 'learning_rate': 0.00045584231230223944, 'epoch': 2.6}

 22%|██▏       | 6075/28080 [12:00:39<43:17:04,  7.08s/it]
 22%|██▏       | 6076/28080 [12:00:46<43:17:36,  7.08s/it]
                                                          
{'loss': 0.6358, 'learning_rate': 0.0004558259464955391, 'epoch': 2.6}

 22%|██▏       | 6076/28080 [12:00:46<43:17:36,  7.08s/it]
 22%|██▏       | 6077/28080 [12:00:53<43:08:37,  7.06s/it]
                                                          
{'loss': 0.6627, 'learning_rate': 0.00045580957795053693, 'epoch': 2.6}

 22%|██▏       | 6077/28080 [12:00:53<43:08:37,  7.06s/it]
 22%|██▏       | 6078/28080 [12:01:00<43:06:47,  7.05s/it]
                                                          
{'loss': 0.647, 'learning_rate': 0.00045579320666745053, 'epoch': 2.6}

 22%|██▏       | 6078/28080 [12:01:00<43:06:47,  7.05s/it]
 22%|██▏       | 6079/28080 [12:01:07<43:05:47,  7.05s/it]
                                                          
{'loss': 0.645, 'learning_rate': 0.00045577683264649794, 'epoch': 2.6}

 22%|██▏       | 6079/28080 [12:01:07<43:05:47,  7.05s/it]
 22%|██▏       | 6080/28080 [12:01:14<43:11:20,  7.07s/it]
                                                          
{'loss': 0.6685, 'learning_rate': 0.0004557604558878968, 'epoch': 2.6}

 22%|██▏       | 6080/28080 [12:01:14<43:11:20,  7.07s/it]
 22%|██▏       | 6081/28080 [12:01:21<43:20:59,  7.09s/it]
                                                          
{'loss': 0.6468, 'learning_rate': 0.0004557440763918651, 'epoch': 2.6}

 22%|██▏       | 6081/28080 [12:01:21<43:20:59,  7.09s/it]
 22%|██▏       | 6082/28080 [12:01:28<43:19:31,  7.09s/it]
                                                          
{'loss': 0.6536, 'learning_rate': 0.00045572769415862073, 'epoch': 2.6}

 22%|██▏       | 6082/28080 [12:01:28<43:19:31,  7.09s/it]
 22%|██▏       | 6083/28080 [12:01:35<43:26:30,  7.11s/it]
                                                          
{'loss': 0.6313, 'learning_rate': 0.0004557113091883817, 'epoch': 2.6}

 22%|██▏       | 6083/28080 [12:01:35<43:26:30,  7.11s/it]
 22%|██▏       | 6084/28080 [12:01:43<43:35:44,  7.14s/it]
                                                          
{'loss': 0.6146, 'learning_rate': 0.0004556949214813658, 'epoch': 2.6}

 22%|██▏       | 6084/28080 [12:01:43<43:35:44,  7.14s/it]
 22%|██▏       | 6085/28080 [12:01:50<43:30:39,  7.12s/it]
                                                          
{'loss': 0.6409, 'learning_rate': 0.0004556785310377912, 'epoch': 2.6}

 22%|██▏       | 6085/28080 [12:01:50<43:30:39,  7.12s/it]
 22%|██▏       | 6086/28080 [12:01:57<43:53:30,  7.18s/it]
                                                          
{'loss': 0.6521, 'learning_rate': 0.0004556621378578759, 'epoch': 2.6}

 22%|██▏       | 6086/28080 [12:01:57<43:53:30,  7.18s/it]
 22%|██▏       | 6087/28080 [12:02:04<43:53:41,  7.19s/it]
                                                          
{'loss': 0.6319, 'learning_rate': 0.0004556457419418381, 'epoch': 2.6}

 22%|██▏       | 6087/28080 [12:02:04<43:53:41,  7.19s/it]
 22%|██▏       | 6088/28080 [12:02:11<43:49:52,  7.17s/it]
                                                          
{'loss': 0.6351, 'learning_rate': 0.0004556293432898958, 'epoch': 2.6}

 22%|██▏       | 6088/28080 [12:02:11<43:49:52,  7.17s/it]
 22%|██▏       | 6089/28080 [12:02:19<43:48:00,  7.17s/it]
                                                          
{'loss': 0.64, 'learning_rate': 0.0004556129419022673, 'epoch': 2.6}

 22%|██▏       | 6089/28080 [12:02:19<43:48:00,  7.17s/it]
 22%|██▏       | 6090/28080 [12:02:26<43:49:48,  7.18s/it]
                                                          
{'loss': 0.6261, 'learning_rate': 0.00045559653777917065, 'epoch': 2.6}

 22%|██▏       | 6090/28080 [12:02:26<43:49:48,  7.18s/it]
 22%|██▏       | 6091/28080 [12:02:33<43:39:58,  7.15s/it]
                                                          
{'loss': 0.6477, 'learning_rate': 0.0004555801309208242, 'epoch': 2.6}

 22%|██▏       | 6091/28080 [12:02:33<43:39:58,  7.15s/it]
 22%|██▏       | 6092/28080 [12:02:40<43:30:13,  7.12s/it]
                                                          
{'loss': 0.6569, 'learning_rate': 0.0004555637213274462, 'epoch': 2.6}

 22%|██▏       | 6092/28080 [12:02:40<43:30:13,  7.12s/it]
 22%|██▏       | 6093/28080 [12:02:47<43:30:43,  7.12s/it]
                                                          
{'loss': 0.6523, 'learning_rate': 0.00045554730899925494, 'epoch': 2.6}

 22%|██▏       | 6093/28080 [12:02:47<43:30:43,  7.12s/it]
 22%|██▏       | 6094/28080 [12:02:54<43:29:17,  7.12s/it]
                                                          
{'loss': 0.6234, 'learning_rate': 0.0004555308939364688, 'epoch': 2.6}

 22%|██▏       | 6094/28080 [12:02:54<43:29:17,  7.12s/it]
 22%|██▏       | 6095/28080 [12:03:01<43:25:40,  7.11s/it]
                                                          
{'loss': 0.6488, 'learning_rate': 0.0004555144761393061, 'epoch': 2.6}

 22%|██▏       | 6095/28080 [12:03:01<43:25:40,  7.11s/it]
 22%|██▏       | 6096/28080 [12:03:08<43:35:35,  7.14s/it]
                                                          
{'loss': 0.6547, 'learning_rate': 0.00045549805560798543, 'epoch': 2.6}

 22%|██▏       | 6096/28080 [12:03:08<43:35:35,  7.14s/it]
 22%|██▏       | 6097/28080 [12:03:16<43:29:14,  7.12s/it]
                                                          
{'loss': 0.6655, 'learning_rate': 0.000455481632342725, 'epoch': 2.6}

 22%|██▏       | 6097/28080 [12:03:16<43:29:14,  7.12s/it]
 22%|██▏       | 6098/28080 [12:03:23<43:25:16,  7.11s/it]
                                                          
{'loss': 0.653, 'learning_rate': 0.0004554652063437435, 'epoch': 2.61}

 22%|██▏       | 6098/28080 [12:03:23<43:25:16,  7.11s/it]
 22%|██▏       | 6099/28080 [12:03:30<43:27:11,  7.12s/it]
                                                          
{'loss': 0.6329, 'learning_rate': 0.00045544877761125935, 'epoch': 2.61}

 22%|██▏       | 6099/28080 [12:03:30<43:27:11,  7.12s/it]
 22%|██▏       | 6100/28080 [12:03:37<43:26:26,  7.11s/it]
                                                          
{'loss': 0.645, 'learning_rate': 0.0004554323461454912, 'epoch': 2.61}

 22%|██▏       | 6100/28080 [12:03:37<43:26:26,  7.11s/it]
 22%|██▏       | 6101/28080 [12:03:44<43:23:47,  7.11s/it]
                                                          
{'loss': 0.6368, 'learning_rate': 0.00045541591194665765, 'epoch': 2.61}

 22%|██▏       | 6101/28080 [12:03:44<43:23:47,  7.11s/it]
 22%|██▏       | 6102/28080 [12:03:51<43:36:30,  7.14s/it]
                                                          
{'loss': 0.621, 'learning_rate': 0.00045539947501497727, 'epoch': 2.61}

 22%|██▏       | 6102/28080 [12:03:51<43:36:30,  7.14s/it]
 22%|██▏       | 6103/28080 [12:03:58<43:27:25,  7.12s/it]
                                                          
{'loss': 0.6187, 'learning_rate': 0.00045538303535066875, 'epoch': 2.61}

 22%|██▏       | 6103/28080 [12:03:58<43:27:25,  7.12s/it]
 22%|██▏       | 6104/28080 [12:04:05<43:32:18,  7.13s/it]
                                                          
{'loss': 0.6291, 'learning_rate': 0.0004553665929539509, 'epoch': 2.61}

 22%|██▏       | 6104/28080 [12:04:05<43:32:18,  7.13s/it]
 22%|██▏       | 6105/28080 [12:04:13<43:36:59,  7.15s/it]
                                                          
{'loss': 0.6361, 'learning_rate': 0.0004553501478250423, 'epoch': 2.61}

 22%|██▏       | 6105/28080 [12:04:13<43:36:59,  7.15s/it]
 22%|██▏       | 6106/28080 [12:04:20<43:35:34,  7.14s/it]
                                                          
{'loss': 0.6292, 'learning_rate': 0.0004553336999641619, 'epoch': 2.61}

 22%|██▏       | 6106/28080 [12:04:20<43:35:34,  7.14s/it]
 22%|██▏       | 6107/28080 [12:04:27<43:28:34,  7.12s/it]
                                                          
{'loss': 0.6449, 'learning_rate': 0.0004553172493715284, 'epoch': 2.61}

 22%|██▏       | 6107/28080 [12:04:27<43:28:34,  7.12s/it]
 22%|██▏       | 6108/28080 [12:04:34<43:23:04,  7.11s/it]
                                                          
{'loss': 0.649, 'learning_rate': 0.00045530079604736074, 'epoch': 2.61}

 22%|██▏       | 6108/28080 [12:04:34<43:23:04,  7.11s/it]
 22%|██▏       | 6109/28080 [12:04:41<43:17:45,  7.09s/it]
                                                          
{'loss': 0.6405, 'learning_rate': 0.0004552843399918778, 'epoch': 2.61}

 22%|██▏       | 6109/28080 [12:04:41<43:17:45,  7.09s/it]
 22%|██▏       | 6110/28080 [12:04:48<43:30:39,  7.13s/it]
                                                          
{'loss': 0.6394, 'learning_rate': 0.0004552678812052985, 'epoch': 2.61}

 22%|██▏       | 6110/28080 [12:04:48<43:30:39,  7.13s/it]
 22%|██▏       | 6111/28080 [12:04:55<43:23:30,  7.11s/it]
                                                          
{'loss': 0.6619, 'learning_rate': 0.00045525141968784177, 'epoch': 2.61}

 22%|██▏       | 6111/28080 [12:04:55<43:23:30,  7.11s/it]
 22%|██▏       | 6112/28080 [12:05:02<43:31:44,  7.13s/it]
                                                          
{'loss': 0.639, 'learning_rate': 0.0004552349554397267, 'epoch': 2.61}

 22%|██▏       | 6112/28080 [12:05:02<43:31:44,  7.13s/it]
 22%|██▏       | 6113/28080 [12:05:09<43:27:05,  7.12s/it]
                                                          
{'loss': 0.6471, 'learning_rate': 0.0004552184884611722, 'epoch': 2.61}

 22%|██▏       | 6113/28080 [12:05:09<43:27:05,  7.12s/it]
 22%|██▏       | 6114/28080 [12:05:16<43:10:12,  7.08s/it]
                                                          
{'loss': 0.6474, 'learning_rate': 0.0004552020187523975, 'epoch': 2.61}

 22%|██▏       | 6114/28080 [12:05:16<43:10:12,  7.08s/it]
 22%|██▏       | 6115/28080 [12:05:24<43:10:02,  7.08s/it]
                                                          
{'loss': 0.661, 'learning_rate': 0.00045518554631362166, 'epoch': 2.61}

 22%|██▏       | 6115/28080 [12:05:24<43:10:02,  7.08s/it]
 22%|██▏       | 6116/28080 [12:05:31<43:07:47,  7.07s/it]
                                                          
{'loss': 0.6728, 'learning_rate': 0.0004551690711450637, 'epoch': 2.61}

 22%|██▏       | 6116/28080 [12:05:31<43:07:47,  7.07s/it]
 22%|██▏       | 6117/28080 [12:05:38<43:18:22,  7.10s/it]
                                                          
{'loss': 0.6307, 'learning_rate': 0.0004551525932469429, 'epoch': 2.61}

 22%|██▏       | 6117/28080 [12:05:38<43:18:22,  7.10s/it]
 22%|██▏       | 6118/28080 [12:05:45<43:20:58,  7.11s/it]
                                                          
{'loss': 0.6378, 'learning_rate': 0.0004551361126194786, 'epoch': 2.61}

 22%|██▏       | 6118/28080 [12:05:45<43:20:58,  7.11s/it]
 22%|██▏       | 6119/28080 [12:05:52<43:19:19,  7.10s/it]
                                                          
{'loss': 0.6511, 'learning_rate': 0.0004551196292628899, 'epoch': 2.61}

 22%|██▏       | 6119/28080 [12:05:52<43:19:19,  7.10s/it]
 22%|██▏       | 6120/28080 [12:05:59<43:20:34,  7.11s/it]
                                                          
{'loss': 0.6701, 'learning_rate': 0.0004551031431773961, 'epoch': 2.61}

 22%|██▏       | 6120/28080 [12:05:59<43:20:34,  7.11s/it]
 22%|██▏       | 6121/28080 [12:06:06<43:27:02,  7.12s/it]
                                                          
{'loss': 0.6387, 'learning_rate': 0.0004550866543632166, 'epoch': 2.61}

 22%|██▏       | 6121/28080 [12:06:06<43:27:02,  7.12s/it]
 22%|██▏       | 6122/28080 [12:06:13<43:18:31,  7.10s/it]
                                                          
{'loss': 0.6359, 'learning_rate': 0.0004550701628205708, 'epoch': 2.62}

 22%|██▏       | 6122/28080 [12:06:13<43:18:31,  7.10s/it]
 22%|██▏       | 6123/28080 [12:06:20<43:24:42,  7.12s/it]
                                                          
{'loss': 0.6266, 'learning_rate': 0.000455053668549678, 'epoch': 2.62}

 22%|██▏       | 6123/28080 [12:06:20<43:24:42,  7.12s/it]
 22%|██▏       | 6124/28080 [12:06:28<43:23:13,  7.11s/it]
                                                          
{'loss': 0.651, 'learning_rate': 0.00045503717155075764, 'epoch': 2.62}

 22%|██▏       | 6124/28080 [12:06:28<43:23:13,  7.11s/it]
 22%|██▏       | 6125/28080 [12:06:35<43:20:46,  7.11s/it]
                                                          
{'loss': 0.6626, 'learning_rate': 0.0004550206718240293, 'epoch': 2.62}

 22%|██▏       | 6125/28080 [12:06:35<43:20:46,  7.11s/it]
 22%|██▏       | 6126/28080 [12:06:42<43:18:07,  7.10s/it]
                                                          
{'loss': 0.6482, 'learning_rate': 0.0004550041693697124, 'epoch': 2.62}

 22%|██▏       | 6126/28080 [12:06:42<43:18:07,  7.10s/it]
 22%|██▏       | 6127/28080 [12:06:49<43:10:58,  7.08s/it]
                                                          
{'loss': 0.6478, 'learning_rate': 0.00045498766418802653, 'epoch': 2.62}

 22%|██▏       | 6127/28080 [12:06:49<43:10:58,  7.08s/it]
 22%|██▏       | 6128/28080 [12:06:56<43:14:15,  7.09s/it]
                                                          
{'loss': 0.6569, 'learning_rate': 0.0004549711562791913, 'epoch': 2.62}

 22%|██▏       | 6128/28080 [12:06:56<43:14:15,  7.09s/it]
 22%|██▏       | 6129/28080 [12:07:03<43:15:09,  7.09s/it]
                                                          
{'loss': 0.6771, 'learning_rate': 0.0004549546456434262, 'epoch': 2.62}

 22%|██▏       | 6129/28080 [12:07:03<43:15:09,  7.09s/it]
 22%|██▏       | 6130/28080 [12:07:10<43:15:18,  7.09s/it]
                                                          
{'loss': 0.6324, 'learning_rate': 0.00045493813228095106, 'epoch': 2.62}

 22%|██▏       | 6130/28080 [12:07:10<43:15:18,  7.09s/it]
 22%|██▏       | 6131/28080 [12:07:17<43:13:14,  7.09s/it]
                                                          
{'loss': 0.6502, 'learning_rate': 0.0004549216161919854, 'epoch': 2.62}

 22%|██▏       | 6131/28080 [12:07:17<43:13:14,  7.09s/it]
 22%|██▏       | 6132/28080 [12:07:24<43:20:19,  7.11s/it]
                                                          
{'loss': 0.6355, 'learning_rate': 0.0004549050973767491, 'epoch': 2.62}

 22%|██▏       | 6132/28080 [12:07:24<43:20:19,  7.11s/it]
 22%|██▏       | 6133/28080 [12:07:31<43:11:28,  7.08s/it]
                                                          
{'loss': 0.6411, 'learning_rate': 0.0004548885758354619, 'epoch': 2.62}

 22%|██▏       | 6133/28080 [12:07:31<43:11:28,  7.08s/it]
 22%|██▏       | 6134/28080 [12:07:38<43:18:30,  7.10s/it]
                                                          
{'loss': 0.6404, 'learning_rate': 0.00045487205156834355, 'epoch': 2.62}

 22%|██▏       | 6134/28080 [12:07:39<43:18:30,  7.10s/it]
 22%|██▏       | 6135/28080 [12:07:46<43:18:06,  7.10s/it]
                                                          
{'loss': 0.6527, 'learning_rate': 0.00045485552457561384, 'epoch': 2.62}

 22%|██▏       | 6135/28080 [12:07:46<43:18:06,  7.10s/it]
 22%|██▏       | 6136/28080 [12:07:53<43:13:10,  7.09s/it]
                                                          
{'loss': 0.6427, 'learning_rate': 0.0004548389948574928, 'epoch': 2.62}

 22%|██▏       | 6136/28080 [12:07:53<43:13:10,  7.09s/it]
 22%|██▏       | 6137/28080 [12:08:00<43:11:10,  7.09s/it]
                                                          
{'loss': 0.6488, 'learning_rate': 0.0004548224624142002, 'epoch': 2.62}

 22%|██▏       | 6137/28080 [12:08:00<43:11:10,  7.09s/it]
 22%|██▏       | 6138/28080 [12:08:07<43:03:34,  7.06s/it]
                                                          
{'loss': 0.623, 'learning_rate': 0.0004548059272459561, 'epoch': 2.62}

 22%|██▏       | 6138/28080 [12:08:07<43:03:34,  7.06s/it]
 22%|██▏       | 6139/28080 [12:08:14<43:13:25,  7.09s/it]
                                                          
{'loss': 0.6088, 'learning_rate': 0.0004547893893529804, 'epoch': 2.62}

 22%|██▏       | 6139/28080 [12:08:14<43:13:25,  7.09s/it]
 22%|██▏       | 6140/28080 [12:08:21<43:16:58,  7.10s/it]
                                                          
{'loss': 0.6061, 'learning_rate': 0.0004547728487354931, 'epoch': 2.62}

 22%|██▏       | 6140/28080 [12:08:21<43:16:58,  7.10s/it]
 22%|██▏       | 6141/28080 [12:08:28<43:14:31,  7.10s/it]
                                                          
{'loss': 0.6211, 'learning_rate': 0.0004547563053937144, 'epoch': 2.62}

 22%|██▏       | 6141/28080 [12:08:28<43:14:31,  7.10s/it]
 22%|██▏       | 6142/28080 [12:08:35<43:19:15,  7.11s/it]
                                                          
{'loss': 0.668, 'learning_rate': 0.00045473975932786416, 'epoch': 2.62}

 22%|██▏       | 6142/28080 [12:08:35<43:19:15,  7.11s/it]
 22%|██▏       | 6143/28080 [12:08:42<43:04:38,  7.07s/it]
                                                          
{'loss': 0.6642, 'learning_rate': 0.0004547232105381627, 'epoch': 2.62}

 22%|██▏       | 6143/28080 [12:08:42<43:04:38,  7.07s/it]
 22%|██▏       | 6144/28080 [12:08:49<43:01:29,  7.06s/it]
                                                          
{'loss': 0.6352, 'learning_rate': 0.00045470665902483024, 'epoch': 2.62}

 22%|██▏       | 6144/28080 [12:08:49<43:01:29,  7.06s/it]
 22%|██▏       | 6145/28080 [12:08:56<43:06:35,  7.08s/it]
                                                          
{'loss': 0.6472, 'learning_rate': 0.0004546901047880867, 'epoch': 2.63}

 22%|██▏       | 6145/28080 [12:08:56<43:06:35,  7.08s/it]
 22%|██▏       | 6146/28080 [12:09:03<43:08:50,  7.08s/it]
                                                          
{'loss': 0.6426, 'learning_rate': 0.0004546735478281525, 'epoch': 2.63}

 22%|██▏       | 6146/28080 [12:09:03<43:08:50,  7.08s/it]
 22%|██▏       | 6147/28080 [12:09:11<43:16:48,  7.10s/it]
                                                          
{'loss': 0.6264, 'learning_rate': 0.000454656988145248, 'epoch': 2.63}

 22%|██▏       | 6147/28080 [12:09:11<43:16:48,  7.10s/it]
 22%|██▏       | 6148/28080 [12:09:18<43:20:18,  7.11s/it]
                                                          
{'loss': 0.6582, 'learning_rate': 0.0004546404257395933, 'epoch': 2.63}

 22%|██▏       | 6148/28080 [12:09:18<43:20:18,  7.11s/it]
 22%|██▏       | 6149/28080 [12:09:25<43:19:06,  7.11s/it]
                                                          
{'loss': 0.6413, 'learning_rate': 0.00045462386061140893, 'epoch': 2.63}

 22%|██▏       | 6149/28080 [12:09:25<43:19:06,  7.11s/it]
 22%|██▏       | 6150/28080 [12:09:32<43:14:21,  7.10s/it]
                                                          
{'loss': 0.6496, 'learning_rate': 0.00045460729276091517, 'epoch': 2.63}

 22%|██▏       | 6150/28080 [12:09:32<43:14:21,  7.10s/it]
 22%|██▏       | 6151/28080 [12:09:39<43:17:21,  7.11s/it]
                                                          
{'loss': 0.6159, 'learning_rate': 0.0004545907221883324, 'epoch': 2.63}

 22%|██▏       | 6151/28080 [12:09:39<43:17:21,  7.11s/it]
 22%|██▏       | 6152/28080 [12:09:46<43:08:55,  7.08s/it]
                                                          
{'loss': 0.633, 'learning_rate': 0.00045457414889388124, 'epoch': 2.63}

 22%|██▏       | 6152/28080 [12:09:46<43:08:55,  7.08s/it]
 22%|██▏       | 6153/28080 [12:09:53<43:13:42,  7.10s/it]
                                                          
{'loss': 0.636, 'learning_rate': 0.000454557572877782, 'epoch': 2.63}

 22%|██▏       | 6153/28080 [12:09:53<43:13:42,  7.10s/it]
 22%|██▏       | 6154/28080 [12:10:00<43:16:27,  7.11s/it]
                                                          
{'loss': 0.628, 'learning_rate': 0.0004545409941402553, 'epoch': 2.63}

 22%|██▏       | 6154/28080 [12:10:00<43:16:27,  7.11s/it]
 22%|██▏       | 6155/28080 [12:10:07<43:04:21,  7.07s/it]
                                                          
{'loss': 0.6417, 'learning_rate': 0.00045452441268152165, 'epoch': 2.63}

 22%|██▏       | 6155/28080 [12:10:07<43:04:21,  7.07s/it]
 22%|██▏       | 6156/28080 [12:10:14<43:10:57,  7.09s/it]
                                                          
{'loss': 0.6362, 'learning_rate': 0.0004545078285018017, 'epoch': 2.63}

 22%|██▏       | 6156/28080 [12:10:14<43:10:57,  7.09s/it]
 22%|██▏       | 6157/28080 [12:10:22<43:18:10,  7.11s/it]
                                                          
{'loss': 0.6288, 'learning_rate': 0.00045449124160131617, 'epoch': 2.63}

 22%|██▏       | 6157/28080 [12:10:22<43:18:10,  7.11s/it]
 22%|██▏       | 6158/28080 [12:10:29<43:12:28,  7.10s/it]
                                                          
{'loss': 0.6305, 'learning_rate': 0.00045447465198028553, 'epoch': 2.63}

 22%|██▏       | 6158/28080 [12:10:29<43:12:28,  7.10s/it]
 22%|██▏       | 6159/28080 [12:10:36<43:19:22,  7.11s/it]
                                                          
{'loss': 0.6636, 'learning_rate': 0.0004544580596389306, 'epoch': 2.63}

 22%|██▏       | 6159/28080 [12:10:36<43:19:22,  7.11s/it]
 22%|██▏       | 6160/28080 [12:10:43<43:22:25,  7.12s/it]
                                                          
{'loss': 0.6324, 'learning_rate': 0.0004544414645774722, 'epoch': 2.63}

 22%|██▏       | 6160/28080 [12:10:43<43:22:25,  7.12s/it]
 22%|██▏       | 6161/28080 [12:10:50<43:23:26,  7.13s/it]
                                                          
{'loss': 0.6103, 'learning_rate': 0.00045442486679613095, 'epoch': 2.63}

 22%|██▏       | 6161/28080 [12:10:50<43:23:26,  7.13s/it]
 22%|██▏       | 6162/28080 [12:10:57<43:28:28,  7.14s/it]
                                                          
{'loss': 0.6593, 'learning_rate': 0.0004544082662951277, 'epoch': 2.63}

 22%|██▏       | 6162/28080 [12:10:57<43:28:28,  7.14s/it]
 22%|██▏       | 6163/28080 [12:11:04<43:30:49,  7.15s/it]
                                                          
{'loss': 0.6392, 'learning_rate': 0.0004543916630746834, 'epoch': 2.63}

 22%|██▏       | 6163/28080 [12:11:04<43:30:49,  7.15s/it]
 22%|██▏       | 6164/28080 [12:11:12<43:21:43,  7.12s/it]
                                                          
{'loss': 0.6492, 'learning_rate': 0.0004543750571350189, 'epoch': 2.63}

 22%|██▏       | 6164/28080 [12:11:12<43:21:43,  7.12s/it]
 22%|██▏       | 6165/28080 [12:11:19<43:23:44,  7.13s/it]
                                                          
{'loss': 0.6319, 'learning_rate': 0.0004543584484763551, 'epoch': 2.63}

 22%|██▏       | 6165/28080 [12:11:19<43:23:44,  7.13s/it]
 22%|██▏       | 6166/28080 [12:11:26<43:28:21,  7.14s/it]
                                                          
{'loss': 0.6708, 'learning_rate': 0.0004543418370989129, 'epoch': 2.63}

 22%|██▏       | 6166/28080 [12:11:26<43:28:21,  7.14s/it]
 22%|██▏       | 6167/28080 [12:11:33<43:34:53,  7.16s/it]
                                                          
{'loss': 0.6348, 'learning_rate': 0.00045432522300291344, 'epoch': 2.63}

 22%|██▏       | 6167/28080 [12:11:33<43:34:53,  7.16s/it]
 22%|██▏       | 6168/28080 [12:11:40<43:15:30,  7.11s/it]
                                                          
{'loss': 0.6349, 'learning_rate': 0.00045430860618857763, 'epoch': 2.63}

 22%|██▏       | 6168/28080 [12:11:40<43:15:30,  7.11s/it]
 22%|██▏       | 6169/28080 [12:11:47<43:11:43,  7.10s/it]
                                                          
{'loss': 0.6299, 'learning_rate': 0.0004542919866561266, 'epoch': 2.64}

 22%|██▏       | 6169/28080 [12:11:47<43:11:43,  7.10s/it]
 22%|██▏       | 6170/28080 [12:11:54<43:18:27,  7.12s/it]
                                                          
{'loss': 0.6381, 'learning_rate': 0.0004542753644057815, 'epoch': 2.64}

 22%|██▏       | 6170/28080 [12:11:54<43:18:27,  7.12s/it]
 22%|██▏       | 6171/28080 [12:12:01<43:23:02,  7.13s/it]
                                                          
{'loss': 0.6351, 'learning_rate': 0.0004542587394377634, 'epoch': 2.64}

 22%|██▏       | 6171/28080 [12:12:01<43:23:02,  7.13s/it]
 22%|██▏       | 6172/28080 [12:12:08<43:09:18,  7.09s/it]
                                                          
{'loss': 0.6403, 'learning_rate': 0.0004542421117522934, 'epoch': 2.64}

 22%|██▏       | 6172/28080 [12:12:08<43:09:18,  7.09s/it]
 22%|██▏       | 6173/28080 [12:12:15<42:51:47,  7.04s/it]
                                                          
{'loss': 0.6498, 'learning_rate': 0.00045422548134959283, 'epoch': 2.64}

 22%|██▏       | 6173/28080 [12:12:15<42:51:47,  7.04s/it]
 22%|██▏       | 6174/28080 [12:12:22<43:01:37,  7.07s/it]
                                                          
{'loss': 0.6511, 'learning_rate': 0.00045420884822988303, 'epoch': 2.64}

 22%|██▏       | 6174/28080 [12:12:23<43:01:37,  7.07s/it]
 22%|██▏       | 6175/28080 [12:12:30<43:00:28,  7.07s/it]
                                                          
{'loss': 0.6739, 'learning_rate': 0.00045419221239338507, 'epoch': 2.64}

 22%|██▏       | 6175/28080 [12:12:30<43:00:28,  7.07s/it]
 22%|██▏       | 6176/28080 [12:12:37<43:12:38,  7.10s/it]
                                                          
{'loss': 0.6535, 'learning_rate': 0.00045417557384032044, 'epoch': 2.64}

 22%|██▏       | 6176/28080 [12:12:37<43:12:38,  7.10s/it]
 22%|██▏       | 6177/28080 [12:12:44<43:17:26,  7.12s/it]
                                                          
{'loss': 0.6163, 'learning_rate': 0.0004541589325709104, 'epoch': 2.64}

 22%|██▏       | 6177/28080 [12:12:44<43:17:26,  7.12s/it]
 22%|██▏       | 6178/28080 [12:12:51<43:14:22,  7.11s/it]
                                                          
{'loss': 0.6649, 'learning_rate': 0.00045414228858537645, 'epoch': 2.64}

 22%|██▏       | 6178/28080 [12:12:51<43:14:22,  7.11s/it]
 22%|██▏       | 6179/28080 [12:12:58<43:16:27,  7.11s/it]
                                                          
{'loss': 0.6373, 'learning_rate': 0.00045412564188393977, 'epoch': 2.64}

 22%|██▏       | 6179/28080 [12:12:58<43:16:27,  7.11s/it]
 22%|██▏       | 6180/28080 [12:13:05<43:14:03,  7.11s/it]
                                                          
{'loss': 0.6409, 'learning_rate': 0.0004541089924668222, 'epoch': 2.64}

 22%|██▏       | 6180/28080 [12:13:05<43:14:03,  7.11s/it]
 22%|██▏       | 6181/28080 [12:13:12<43:14:35,  7.11s/it]
                                                          
{'loss': 0.6505, 'learning_rate': 0.00045409234033424496, 'epoch': 2.64}

 22%|██▏       | 6181/28080 [12:13:12<43:14:35,  7.11s/it]
 22%|██▏       | 6182/28080 [12:13:19<43:09:47,  7.10s/it]
                                                          
{'loss': 0.6485, 'learning_rate': 0.00045407568548642974, 'epoch': 2.64}

 22%|██▏       | 6182/28080 [12:13:19<43:09:47,  7.10s/it]
 22%|██▏       | 6183/28080 [12:13:26<43:11:27,  7.10s/it]
                                                          
{'loss': 0.6256, 'learning_rate': 0.000454059027923598, 'epoch': 2.64}

 22%|██▏       | 6183/28080 [12:13:26<43:11:27,  7.10s/it]
 22%|██▏       | 6184/28080 [12:13:34<43:09:39,  7.10s/it]
                                                          
{'loss': 0.6376, 'learning_rate': 0.0004540423676459714, 'epoch': 2.64}

 22%|██▏       | 6184/28080 [12:13:34<43:09:39,  7.10s/it]
 22%|██▏       | 6185/28080 [12:13:41<43:04:36,  7.08s/it]
                                                          
{'loss': 0.6441, 'learning_rate': 0.0004540257046537717, 'epoch': 2.64}

 22%|██▏       | 6185/28080 [12:13:41<43:04:36,  7.08s/it]
 22%|██▏       | 6186/28080 [12:13:48<43:01:21,  7.07s/it]
                                                          
{'loss': 0.6447, 'learning_rate': 0.00045400903894722035, 'epoch': 2.64}

 22%|██▏       | 6186/28080 [12:13:48<43:01:21,  7.07s/it]
 22%|██▏       | 6187/28080 [12:13:55<43:05:02,  7.08s/it]
                                                          
{'loss': 0.6334, 'learning_rate': 0.0004539923705265393, 'epoch': 2.64}

 22%|██▏       | 6187/28080 [12:13:55<43:05:02,  7.08s/it]
 22%|██▏       | 6188/28080 [12:14:02<43:12:12,  7.10s/it]
                                                          
{'loss': 0.651, 'learning_rate': 0.00045397569939195013, 'epoch': 2.64}

 22%|██▏       | 6188/28080 [12:14:02<43:12:12,  7.10s/it]
 22%|██▏       | 6189/28080 [12:14:09<43:12:40,  7.11s/it]
                                                          
{'loss': 0.6518, 'learning_rate': 0.0004539590255436748, 'epoch': 2.64}

 22%|██▏       | 6189/28080 [12:14:09<43:12:40,  7.11s/it]
 22%|██▏       | 6190/28080 [12:14:16<43:16:50,  7.12s/it]
                                                          
{'loss': 0.6385, 'learning_rate': 0.00045394234898193497, 'epoch': 2.64}

 22%|██▏       | 6190/28080 [12:14:16<43:16:50,  7.12s/it]
 22%|██▏       | 6191/28080 [12:14:23<43:20:54,  7.13s/it]
                                                          
{'loss': 0.6405, 'learning_rate': 0.0004539256697069526, 'epoch': 2.64}

 22%|██▏       | 6191/28080 [12:14:23<43:20:54,  7.13s/it]
 22%|██▏       | 6192/28080 [12:14:30<43:15:45,  7.12s/it]
                                                          
{'loss': 0.6479, 'learning_rate': 0.00045390898771894964, 'epoch': 2.65}

 22%|██▏       | 6192/28080 [12:14:30<43:15:45,  7.12s/it]
 22%|██▏       | 6193/28080 [12:14:38<43:38:04,  7.18s/it]
                                                          
{'loss': 0.6417, 'learning_rate': 0.00045389230301814786, 'epoch': 2.65}

 22%|██▏       | 6193/28080 [12:14:38<43:38:04,  7.18s/it]
 22%|██▏       | 6194/28080 [12:14:45<43:36:48,  7.17s/it]
                                                          
{'loss': 0.6203, 'learning_rate': 0.00045387561560476943, 'epoch': 2.65}

 22%|██▏       | 6194/28080 [12:14:45<43:36:48,  7.17s/it]
 22%|██▏       | 6195/28080 [12:14:52<43:22:53,  7.14s/it]
                                                          
{'loss': 0.6417, 'learning_rate': 0.0004538589254790362, 'epoch': 2.65}

 22%|██▏       | 6195/28080 [12:14:52<43:22:53,  7.14s/it]
 22%|██▏       | 6196/28080 [12:14:59<43:18:42,  7.12s/it]
                                                          
{'loss': 0.648, 'learning_rate': 0.0004538422326411703, 'epoch': 2.65}

 22%|██▏       | 6196/28080 [12:14:59<43:18:42,  7.12s/it]
 22%|██▏       | 6197/28080 [12:15:06<43:04:00,  7.08s/it]
                                                          
{'loss': 0.6432, 'learning_rate': 0.00045382553709139375, 'epoch': 2.65}

 22%|██▏       | 6197/28080 [12:15:06<43:04:00,  7.08s/it]
 22%|██▏       | 6198/28080 [12:15:13<43:11:30,  7.11s/it]
                                                          
{'loss': 0.6403, 'learning_rate': 0.0004538088388299287, 'epoch': 2.65}

 22%|██▏       | 6198/28080 [12:15:13<43:11:30,  7.11s/it]
 22%|██▏       | 6199/28080 [12:15:20<43:21:14,  7.13s/it]
                                                          
{'loss': 0.6543, 'learning_rate': 0.00045379213785699736, 'epoch': 2.65}

 22%|██▏       | 6199/28080 [12:15:20<43:21:14,  7.13s/it]
 22%|██▏       | 6200/28080 [12:15:27<43:16:28,  7.12s/it]
                                                          
{'loss': 0.6553, 'learning_rate': 0.0004537754341728218, 'epoch': 2.65}

 22%|██▏       | 6200/28080 [12:15:27<43:16:28,  7.12s/it]
 22%|██▏       | 6201/28080 [12:15:35<43:18:58,  7.13s/it]
                                                          
{'loss': 0.6363, 'learning_rate': 0.00045375872777762437, 'epoch': 2.65}

 22%|██▏       | 6201/28080 [12:15:35<43:18:58,  7.13s/it]
 22%|██▏       | 6202/28080 [12:15:42<43:33:45,  7.17s/it]
                                                          
{'loss': 0.6403, 'learning_rate': 0.0004537420186716272, 'epoch': 2.65}

 22%|██▏       | 6202/28080 [12:15:42<43:33:45,  7.17s/it]
 22%|██▏       | 6203/28080 [12:15:49<43:34:16,  7.17s/it]
                                                          
{'loss': 0.6378, 'learning_rate': 0.00045372530685505274, 'epoch': 2.65}

 22%|██▏       | 6203/28080 [12:15:49<43:34:16,  7.17s/it]
 22%|██▏       | 6204/28080 [12:15:56<43:18:27,  7.13s/it]
                                                          
{'loss': 0.6551, 'learning_rate': 0.0004537085923281232, 'epoch': 2.65}

 22%|██▏       | 6204/28080 [12:15:56<43:18:27,  7.13s/it]
 22%|██▏       | 6205/28080 [12:16:03<43:19:35,  7.13s/it]
                                                          
{'loss': 0.635, 'learning_rate': 0.000453691875091061, 'epoch': 2.65}

 22%|██▏       | 6205/28080 [12:16:03<43:19:35,  7.13s/it]
 22%|██▏       | 6206/28080 [12:16:10<43:14:24,  7.12s/it]
                                                          
{'loss': 0.665, 'learning_rate': 0.0004536751551440886, 'epoch': 2.65}

 22%|██▏       | 6206/28080 [12:16:10<43:14:24,  7.12s/it]
 22%|██▏       | 6207/28080 [12:16:17<43:09:39,  7.10s/it]
                                                          
{'loss': 0.6274, 'learning_rate': 0.0004536584324874283, 'epoch': 2.65}

 22%|██▏       | 6207/28080 [12:16:17<43:09:39,  7.10s/it]
 22%|██▏       | 6208/28080 [12:16:24<42:59:09,  7.08s/it]
                                                          
{'loss': 0.6472, 'learning_rate': 0.0004536417071213027, 'epoch': 2.65}

 22%|██▏       | 6208/28080 [12:16:24<42:59:09,  7.08s/it]
 22%|██▏       | 6209/28080 [12:16:31<42:56:37,  7.07s/it]
                                                          
{'loss': 0.6619, 'learning_rate': 0.00045362497904593424, 'epoch': 2.65}

 22%|██▏       | 6209/28080 [12:16:31<42:56:37,  7.07s/it]
 22%|██▏       | 6210/28080 [12:16:39<43:03:43,  7.09s/it]
                                                          
{'loss': 0.6673, 'learning_rate': 0.0004536082482615456, 'epoch': 2.65}

 22%|██▏       | 6210/28080 [12:16:39<43:03:43,  7.09s/it]
 22%|██▏       | 6211/28080 [12:16:46<43:03:27,  7.09s/it]
                                                          
{'loss': 0.6287, 'learning_rate': 0.0004535915147683591, 'epoch': 2.65}

 22%|██▏       | 6211/28080 [12:16:46<43:03:27,  7.09s/it]
 22%|██▏       | 6212/28080 [12:16:53<43:09:50,  7.11s/it]
                                                          
{'loss': 0.6497, 'learning_rate': 0.0004535747785665977, 'epoch': 2.65}

 22%|██▏       | 6212/28080 [12:16:53<43:09:50,  7.11s/it]
 22%|██▏       | 6213/28080 [12:17:00<43:08:06,  7.10s/it]
                                                          
{'loss': 0.633, 'learning_rate': 0.0004535580396564838, 'epoch': 2.65}

 22%|██▏       | 6213/28080 [12:17:00<43:08:06,  7.10s/it]
 22%|██▏       | 6214/28080 [12:17:07<43:09:22,  7.11s/it]
                                                          
{'loss': 0.6516, 'learning_rate': 0.0004535412980382402, 'epoch': 2.65}

 22%|██▏       | 6214/28080 [12:17:07<43:09:22,  7.11s/it]
 22%|██▏       | 6215/28080 [12:17:14<43:02:45,  7.09s/it]
                                                          
{'loss': 0.6579, 'learning_rate': 0.00045352455371208954, 'epoch': 2.65}

 22%|██▏       | 6215/28080 [12:17:14<43:02:45,  7.09s/it]
 22%|██▏       | 6216/28080 [12:17:21<43:04:50,  7.09s/it]
                                                          
{'loss': 0.6437, 'learning_rate': 0.00045350780667825476, 'epoch': 2.66}

 22%|██▏       | 6216/28080 [12:17:21<43:04:50,  7.09s/it]
 22%|██▏       | 6217/28080 [12:17:28<42:53:47,  7.06s/it]
                                                          
{'loss': 0.6475, 'learning_rate': 0.0004534910569369585, 'epoch': 2.66}

 22%|██▏       | 6217/28080 [12:17:28<42:53:47,  7.06s/it]
 22%|██▏       | 6218/28080 [12:17:35<42:58:25,  7.08s/it]
                                                          
{'loss': 0.6498, 'learning_rate': 0.0004534743044884237, 'epoch': 2.66}

 22%|██▏       | 6218/28080 [12:17:35<42:58:25,  7.08s/it]
 22%|██▏       | 6219/28080 [12:17:42<42:56:20,  7.07s/it]
                                                          
{'loss': 0.6613, 'learning_rate': 0.0004534575493328732, 'epoch': 2.66}

 22%|██▏       | 6219/28080 [12:17:42<42:56:20,  7.07s/it]
 22%|██▏       | 6220/28080 [12:17:49<43:05:10,  7.10s/it]
                                                          
{'loss': 0.6371, 'learning_rate': 0.00045344079147052984, 'epoch': 2.66}

 22%|██▏       | 6220/28080 [12:17:50<43:05:10,  7.10s/it]
 22%|██▏       | 6221/28080 [12:17:57<42:59:39,  7.08s/it]
                                                          
{'loss': 0.6346, 'learning_rate': 0.0004534240309016167, 'epoch': 2.66}

 22%|██▏       | 6221/28080 [12:17:57<42:59:39,  7.08s/it]
 22%|██▏       | 6222/28080 [12:18:04<42:54:35,  7.07s/it]
                                                          
{'loss': 0.6471, 'learning_rate': 0.0004534072676263566, 'epoch': 2.66}

 22%|██▏       | 6222/28080 [12:18:04<42:54:35,  7.07s/it]
 22%|██▏       | 6223/28080 [12:18:11<43:01:33,  7.09s/it]
                                                          
{'loss': 0.6461, 'learning_rate': 0.00045339050164497265, 'epoch': 2.66}

 22%|██▏       | 6223/28080 [12:18:11<43:01:33,  7.09s/it]
 22%|██▏       | 6224/28080 [12:18:18<42:58:05,  7.08s/it]
                                                          
{'loss': 0.6623, 'learning_rate': 0.00045337373295768795, 'epoch': 2.66}

 22%|██▏       | 6224/28080 [12:18:18<42:58:05,  7.08s/it]
 22%|██▏       | 6225/28080 [12:18:25<43:10:18,  7.11s/it]
                                                          
{'loss': 0.6373, 'learning_rate': 0.00045335696156472555, 'epoch': 2.66}

 22%|██▏       | 6225/28080 [12:18:25<43:10:18,  7.11s/it]
 22%|██▏       | 6226/28080 [12:18:32<43:09:07,  7.11s/it]
                                                          
{'loss': 0.6711, 'learning_rate': 0.0004533401874663086, 'epoch': 2.66}

 22%|██▏       | 6226/28080 [12:18:32<43:09:07,  7.11s/it]
 22%|██▏       | 6227/28080 [12:18:39<43:17:01,  7.13s/it]
                                                          
{'loss': 0.6346, 'learning_rate': 0.0004533234106626601, 'epoch': 2.66}

 22%|██▏       | 6227/28080 [12:18:39<43:17:01,  7.13s/it]
 22%|██▏       | 6228/28080 [12:18:46<43:06:27,  7.10s/it]
                                                          
{'loss': 0.6301, 'learning_rate': 0.0004533066311540035, 'epoch': 2.66}

 22%|██▏       | 6228/28080 [12:18:46<43:06:27,  7.10s/it]
 22%|██▏       | 6229/28080 [12:18:53<43:01:00,  7.09s/it]
                                                          
{'loss': 0.6355, 'learning_rate': 0.0004532898489405619, 'epoch': 2.66}

 22%|██▏       | 6229/28080 [12:18:53<43:01:00,  7.09s/it]
 22%|██▏       | 6230/28080 [12:19:00<42:57:52,  7.08s/it]
                                                          
{'loss': 0.6631, 'learning_rate': 0.0004532730640225586, 'epoch': 2.66}

 22%|██▏       | 6230/28080 [12:19:00<42:57:52,  7.08s/it]
 22%|██▏       | 6231/28080 [12:19:07<42:53:47,  7.07s/it]
                                                          
{'loss': 0.6691, 'learning_rate': 0.0004532562764002168, 'epoch': 2.66}

 22%|██▏       | 6231/28080 [12:19:07<42:53:47,  7.07s/it]
 22%|██▏       | 6232/28080 [12:19:15<42:55:01,  7.07s/it]
                                                          
{'loss': 0.6419, 'learning_rate': 0.00045323948607376, 'epoch': 2.66}

 22%|██▏       | 6232/28080 [12:19:15<42:55:01,  7.07s/it]
 22%|██▏       | 6233/28080 [12:19:22<42:55:06,  7.07s/it]
                                                          
{'loss': 0.6419, 'learning_rate': 0.0004532226930434115, 'epoch': 2.66}

 22%|██▏       | 6233/28080 [12:19:22<42:55:06,  7.07s/it]
 22%|██▏       | 6234/28080 [12:19:29<43:04:05,  7.10s/it]
                                                          
{'loss': 0.6247, 'learning_rate': 0.00045320589730939463, 'epoch': 2.66}

 22%|██▏       | 6234/28080 [12:19:29<43:04:05,  7.10s/it]
 22%|██▏       | 6235/28080 [12:19:36<42:53:37,  7.07s/it]
                                                          
{'loss': 0.6531, 'learning_rate': 0.00045318909887193305, 'epoch': 2.66}

 22%|██▏       | 6235/28080 [12:19:36<42:53:37,  7.07s/it]
 22%|██▏       | 6236/28080 [12:19:43<42:55:04,  7.07s/it]
                                                          
{'loss': 0.6342, 'learning_rate': 0.00045317229773125014, 'epoch': 2.66}

 22%|██▏       | 6236/28080 [12:19:43<42:55:04,  7.07s/it]
 22%|██▏       | 6237/28080 [12:19:50<42:56:25,  7.08s/it]
                                                          
{'loss': 0.6276, 'learning_rate': 0.0004531554938875693, 'epoch': 2.66}

 22%|██▏       | 6237/28080 [12:19:50<42:56:25,  7.08s/it]
 22%|██▏       | 6238/28080 [12:19:57<43:03:52,  7.10s/it]
                                                          
{'loss': 0.6472, 'learning_rate': 0.0004531386873411143, 'epoch': 2.66}

 22%|██▏       | 6238/28080 [12:19:57<43:03:52,  7.10s/it]
 22%|██▏       | 6239/28080 [12:20:04<43:11:07,  7.12s/it]
                                                          
{'loss': 0.6418, 'learning_rate': 0.0004531218780921086, 'epoch': 2.67}

 22%|██▏       | 6239/28080 [12:20:04<43:11:07,  7.12s/it]
 22%|██▏       | 6240/28080 [12:20:11<43:11:07,  7.12s/it]
                                                          
{'loss': 0.6475, 'learning_rate': 0.00045310506614077583, 'epoch': 2.67}

 22%|██▏       | 6240/28080 [12:20:11<43:11:07,  7.12s/it]
 22%|██▏       | 6241/28080 [12:20:18<43:09:43,  7.11s/it]
                                                          
{'loss': 0.6555, 'learning_rate': 0.00045308825148733967, 'epoch': 2.67}

 22%|██▏       | 6241/28080 [12:20:18<43:09:43,  7.11s/it]
 22%|██▏       | 6242/28080 [12:20:26<43:19:58,  7.14s/it]
                                                          
{'loss': 0.642, 'learning_rate': 0.0004530714341320239, 'epoch': 2.67}

 22%|██▏       | 6242/28080 [12:20:26<43:19:58,  7.14s/it]
 22%|██▏       | 6243/28080 [12:20:33<43:16:17,  7.13s/it]
                                                          
{'loss': 0.6385, 'learning_rate': 0.00045305461407505224, 'epoch': 2.67}

 22%|██▏       | 6243/28080 [12:20:33<43:16:17,  7.13s/it]
 22%|██▏       | 6244/28080 [12:20:40<43:09:27,  7.12s/it]
                                                          
{'loss': 0.6312, 'learning_rate': 0.0004530377913166483, 'epoch': 2.67}

 22%|██▏       | 6244/28080 [12:20:40<43:09:27,  7.12s/it]
 22%|██▏       | 6245/28080 [12:20:47<42:57:33,  7.08s/it]
                                                          
{'loss': 0.6527, 'learning_rate': 0.000453020965857036, 'epoch': 2.67}

 22%|██▏       | 6245/28080 [12:20:47<42:57:33,  7.08s/it]
 22%|██▏       | 6246/28080 [12:20:54<43:00:29,  7.09s/it]
                                                          
{'loss': 0.6497, 'learning_rate': 0.00045300413769643934, 'epoch': 2.67}

 22%|██▏       | 6246/28080 [12:20:54<43:00:29,  7.09s/it]
 22%|██▏       | 6247/28080 [12:21:01<43:08:01,  7.11s/it]
                                                          
{'loss': 0.6119, 'learning_rate': 0.00045298730683508194, 'epoch': 2.67}

 22%|██▏       | 6247/28080 [12:21:01<43:08:01,  7.11s/it]
 22%|██▏       | 6248/28080 [12:21:08<43:08:33,  7.11s/it]
                                                          
{'loss': 0.6499, 'learning_rate': 0.00045297047327318786, 'epoch': 2.67}

 22%|██▏       | 6248/28080 [12:21:08<43:08:33,  7.11s/it]
 22%|██▏       | 6249/28080 [12:21:15<43:12:25,  7.12s/it]
                                                          
{'loss': 0.6227, 'learning_rate': 0.00045295363701098104, 'epoch': 2.67}

 22%|██▏       | 6249/28080 [12:21:15<43:12:25,  7.12s/it]
 22%|██▏       | 6250/28080 [12:21:23<43:13:20,  7.13s/it]
                                                          
{'loss': 0.6156, 'learning_rate': 0.00045293679804868543, 'epoch': 2.67}

 22%|██▏       | 6250/28080 [12:21:23<43:13:20,  7.13s/it]
 22%|██▏       | 6251/28080 [12:21:30<43:13:20,  7.13s/it]
                                                          
{'loss': 0.6349, 'learning_rate': 0.0004529199563865251, 'epoch': 2.67}

 22%|██▏       | 6251/28080 [12:21:30<43:13:20,  7.13s/it]
 22%|██▏       | 6252/28080 [12:21:37<43:07:20,  7.11s/it]
                                                          
{'loss': 0.6429, 'learning_rate': 0.0004529031120247241, 'epoch': 2.67}

 22%|██▏       | 6252/28080 [12:21:37<43:07:20,  7.11s/it]
 22%|██▏       | 6253/28080 [12:21:44<43:11:29,  7.12s/it]
                                                          
{'loss': 0.6371, 'learning_rate': 0.0004528862649635065, 'epoch': 2.67}

 22%|██▏       | 6253/28080 [12:21:44<43:11:29,  7.12s/it]
 22%|██▏       | 6254/28080 [12:21:51<42:56:28,  7.08s/it]
                                                          
{'loss': 0.663, 'learning_rate': 0.0004528694152030964, 'epoch': 2.67}

 22%|██▏       | 6254/28080 [12:21:51<42:56:28,  7.08s/it]
 22%|██▏       | 6255/28080 [12:21:58<42:55:45,  7.08s/it]
                                                          
{'loss': 0.6432, 'learning_rate': 0.0004528525627437181, 'epoch': 2.67}

 22%|██▏       | 6255/28080 [12:21:58<42:55:45,  7.08s/it]
 22%|██▏       | 6256/28080 [12:22:05<43:01:29,  7.10s/it]
                                                          
{'loss': 0.6409, 'learning_rate': 0.00045283570758559565, 'epoch': 2.67}

 22%|██▏       | 6256/28080 [12:22:05<43:01:29,  7.10s/it]
 22%|██▏       | 6257/28080 [12:22:12<42:43:04,  7.05s/it]
                                                          
{'loss': 0.6569, 'learning_rate': 0.0004528188497289535, 'epoch': 2.67}

 22%|██▏       | 6257/28080 [12:22:12<42:43:04,  7.05s/it]
 22%|██▏       | 6258/28080 [12:22:19<42:56:01,  7.08s/it]
                                                          
{'loss': 0.6331, 'learning_rate': 0.00045280198917401566, 'epoch': 2.67}

 22%|██▏       | 6258/28080 [12:22:19<42:56:01,  7.08s/it]
 22%|██▏       | 6259/28080 [12:22:26<42:57:23,  7.09s/it]
                                                          
{'loss': 0.6457, 'learning_rate': 0.0004527851259210066, 'epoch': 2.67}

 22%|██▏       | 6259/28080 [12:22:26<42:57:23,  7.09s/it]
 22%|██▏       | 6260/28080 [12:22:33<42:57:18,  7.09s/it]
                                                          
{'loss': 0.6271, 'learning_rate': 0.0004527682599701507, 'epoch': 2.67}

 22%|██▏       | 6260/28080 [12:22:33<42:57:18,  7.09s/it]
 22%|██▏       | 6261/28080 [12:22:40<42:46:43,  7.06s/it]
                                                          
{'loss': 0.6211, 'learning_rate': 0.0004527513913216722, 'epoch': 2.67}

 22%|██▏       | 6261/28080 [12:22:40<42:46:43,  7.06s/it]
 22%|██▏       | 6262/28080 [12:22:47<42:50:15,  7.07s/it]
                                                          
{'loss': 0.6338, 'learning_rate': 0.0004527345199757957, 'epoch': 2.68}

 22%|██▏       | 6262/28080 [12:22:47<42:50:15,  7.07s/it]
 22%|██▏       | 6263/28080 [12:22:55<42:57:02,  7.09s/it]
                                                          
{'loss': 0.6152, 'learning_rate': 0.00045271764593274544, 'epoch': 2.68}

 22%|██▏       | 6263/28080 [12:22:55<42:57:02,  7.09s/it]
 22%|██▏       | 6264/28080 [12:23:02<42:57:41,  7.09s/it]
                                                          
{'loss': 0.6298, 'learning_rate': 0.00045270076919274617, 'epoch': 2.68}

 22%|██▏       | 6264/28080 [12:23:02<42:57:41,  7.09s/it]
 22%|██▏       | 6265/28080 [12:23:09<43:03:21,  7.11s/it]
                                                          
{'loss': 0.6263, 'learning_rate': 0.00045268388975602217, 'epoch': 2.68}

 22%|██▏       | 6265/28080 [12:23:09<43:03:21,  7.11s/it]
 22%|██▏       | 6266/28080 [12:23:16<42:48:18,  7.06s/it]
                                                          
{'loss': 0.649, 'learning_rate': 0.00045266700762279814, 'epoch': 2.68}

 22%|██▏       | 6266/28080 [12:23:16<42:48:18,  7.06s/it]
 22%|██▏       | 6267/28080 [12:23:23<42:58:30,  7.09s/it]
                                                          
{'loss': 0.639, 'learning_rate': 0.0004526501227932987, 'epoch': 2.68}

 22%|██▏       | 6267/28080 [12:23:23<42:58:30,  7.09s/it]
 22%|██▏       | 6268/28080 [12:23:30<42:58:35,  7.09s/it]
                                                          
{'loss': 0.668, 'learning_rate': 0.0004526332352677484, 'epoch': 2.68}

 22%|██▏       | 6268/28080 [12:23:30<42:58:35,  7.09s/it]
 22%|██▏       | 6269/28080 [12:23:37<43:06:16,  7.11s/it]
                                                          
{'loss': 0.6757, 'learning_rate': 0.00045261634504637193, 'epoch': 2.68}

 22%|██▏       | 6269/28080 [12:23:37<43:06:16,  7.11s/it]
 22%|██▏       | 6270/28080 [12:23:44<42:58:28,  7.09s/it]
                                                          
{'loss': 0.6448, 'learning_rate': 0.00045259945212939407, 'epoch': 2.68}

 22%|██▏       | 6270/28080 [12:23:44<42:58:28,  7.09s/it]
 22%|██▏       | 6271/28080 [12:23:51<42:58:39,  7.09s/it]
                                                          
{'loss': 0.647, 'learning_rate': 0.0004525825565170395, 'epoch': 2.68}

 22%|██▏       | 6271/28080 [12:23:51<42:58:39,  7.09s/it]
 22%|██▏       | 6272/28080 [12:23:59<43:06:53,  7.12s/it]
                                                          
{'loss': 0.6594, 'learning_rate': 0.000452565658209533, 'epoch': 2.68}

 22%|██▏       | 6272/28080 [12:23:59<43:06:53,  7.12s/it]
 22%|██▏       | 6273/28080 [12:24:06<43:04:15,  7.11s/it]
                                                          
{'loss': 0.6255, 'learning_rate': 0.00045254875720709937, 'epoch': 2.68}

 22%|██▏       | 6273/28080 [12:24:06<43:04:15,  7.11s/it]
 22%|██▏       | 6274/28080 [12:24:13<43:06:13,  7.12s/it]
                                                          
{'loss': 0.6402, 'learning_rate': 0.0004525318535099635, 'epoch': 2.68}

 22%|██▏       | 6274/28080 [12:24:13<43:06:13,  7.12s/it]
 22%|██▏       | 6275/28080 [12:24:20<43:09:44,  7.13s/it]
                                                          
{'loss': 0.6335, 'learning_rate': 0.00045251494711835027, 'epoch': 2.68}

 22%|██▏       | 6275/28080 [12:24:20<43:09:44,  7.13s/it]
 22%|██▏       | 6276/28080 [12:24:27<42:57:29,  7.09s/it]
                                                          
{'loss': 0.6357, 'learning_rate': 0.00045249803803248457, 'epoch': 2.68}

 22%|██▏       | 6276/28080 [12:24:27<42:57:29,  7.09s/it]
 22%|██▏       | 6277/28080 [12:24:34<42:52:24,  7.08s/it]
                                                          
{'loss': 0.6305, 'learning_rate': 0.0004524811262525914, 'epoch': 2.68}

 22%|██▏       | 6277/28080 [12:24:34<42:52:24,  7.08s/it]
 22%|██▏       | 6278/28080 [12:24:41<42:58:03,  7.09s/it]
                                                          
{'loss': 0.627, 'learning_rate': 0.0004524642117788957, 'epoch': 2.68}

 22%|██▏       | 6278/28080 [12:24:41<42:58:03,  7.09s/it]
 22%|██▏       | 6279/28080 [12:24:48<43:05:55,  7.12s/it]
                                                          
{'loss': 0.642, 'learning_rate': 0.0004524472946116226, 'epoch': 2.68}

 22%|██▏       | 6279/28080 [12:24:48<43:05:55,  7.12s/it]
 22%|██▏       | 6280/28080 [12:24:55<43:04:20,  7.11s/it]
                                                          
{'loss': 0.6814, 'learning_rate': 0.00045243037475099703, 'epoch': 2.68}

 22%|██▏       | 6280/28080 [12:24:55<43:04:20,  7.11s/it]
 22%|██▏       | 6281/28080 [12:25:02<43:02:16,  7.11s/it]
                                                          
{'loss': 0.6354, 'learning_rate': 0.00045241345219724415, 'epoch': 2.68}

 22%|██▏       | 6281/28080 [12:25:02<43:02:16,  7.11s/it]
 22%|██▏       | 6282/28080 [12:25:10<43:03:52,  7.11s/it]
                                                          
{'loss': 0.6447, 'learning_rate': 0.0004523965269505892, 'epoch': 2.68}

 22%|██▏       | 6282/28080 [12:25:10<43:03:52,  7.11s/it]
 22%|██▏       | 6283/28080 [12:25:17<43:02:19,  7.11s/it]
                                                          
{'loss': 0.6491, 'learning_rate': 0.0004523795990112572, 'epoch': 2.68}

 22%|██▏       | 6283/28080 [12:25:17<43:02:19,  7.11s/it]
 22%|██▏       | 6284/28080 [12:25:24<43:20:14,  7.16s/it]
                                                          
{'loss': 0.6429, 'learning_rate': 0.0004523626683794734, 'epoch': 2.68}

 22%|██▏       | 6284/28080 [12:25:24<43:20:14,  7.16s/it]
 22%|██▏       | 6285/28080 [12:25:31<43:05:46,  7.12s/it]
                                                          
{'loss': 0.6313, 'learning_rate': 0.0004523457350554631, 'epoch': 2.68}

 22%|██▏       | 6285/28080 [12:25:31<43:05:46,  7.12s/it]
 22%|██▏       | 6286/28080 [12:25:38<42:57:47,  7.10s/it]
                                                          
{'loss': 0.6283, 'learning_rate': 0.00045232879903945157, 'epoch': 2.69}

 22%|██▏       | 6286/28080 [12:25:38<42:57:47,  7.10s/it]
 22%|██▏       | 6287/28080 [12:25:45<43:06:32,  7.12s/it]
                                                          
{'loss': 0.6547, 'learning_rate': 0.00045231186033166404, 'epoch': 2.69}

 22%|██▏       | 6287/28080 [12:25:45<43:06:32,  7.12s/it]
 22%|██▏       | 6288/28080 [12:25:52<43:06:19,  7.12s/it]
                                                          
{'loss': 0.6542, 'learning_rate': 0.0004522949189323259, 'epoch': 2.69}

 22%|██▏       | 6288/28080 [12:25:52<43:06:19,  7.12s/it]
 22%|██▏       | 6289/28080 [12:25:59<42:56:34,  7.09s/it]
                                                          
{'loss': 0.6423, 'learning_rate': 0.0004522779748416626, 'epoch': 2.69}

 22%|██▏       | 6289/28080 [12:25:59<42:56:34,  7.09s/it]
 22%|██▏       | 6290/28080 [12:26:06<42:54:40,  7.09s/it]
                                                          
{'loss': 0.6416, 'learning_rate': 0.00045226102805989954, 'epoch': 2.69}

 22%|██▏       | 6290/28080 [12:26:06<42:54:40,  7.09s/it]
 22%|██▏       | 6291/28080 [12:26:14<43:00:06,  7.10s/it]
                                                          
{'loss': 0.6456, 'learning_rate': 0.0004522440785872621, 'epoch': 2.69}

 22%|██▏       | 6291/28080 [12:26:14<43:00:06,  7.10s/it]
 22%|██▏       | 6292/28080 [12:26:21<42:54:51,  7.09s/it]
                                                          
{'loss': 0.6464, 'learning_rate': 0.0004522271264239759, 'epoch': 2.69}

 22%|██▏       | 6292/28080 [12:26:21<42:54:51,  7.09s/it]
 22%|██▏       | 6293/28080 [12:26:28<42:50:04,  7.08s/it]
                                                          
{'loss': 0.6254, 'learning_rate': 0.00045221017157026644, 'epoch': 2.69}

 22%|██▏       | 6293/28080 [12:26:28<42:50:04,  7.08s/it]
 22%|██▏       | 6294/28080 [12:26:35<42:57:09,  7.10s/it]
                                                          
{'loss': 0.6392, 'learning_rate': 0.0004521932140263592, 'epoch': 2.69}

 22%|██▏       | 6294/28080 [12:26:35<42:57:09,  7.10s/it]
 22%|██▏       | 6295/28080 [12:26:42<42:42:45,  7.06s/it]
                                                          
{'loss': 0.646, 'learning_rate': 0.00045217625379247986, 'epoch': 2.69}

 22%|██▏       | 6295/28080 [12:26:42<42:42:45,  7.06s/it]
 22%|██▏       | 6296/28080 [12:26:49<42:32:20,  7.03s/it]
                                                          
{'loss': 0.6511, 'learning_rate': 0.000452159290868854, 'epoch': 2.69}

 22%|██▏       | 6296/28080 [12:26:49<42:32:20,  7.03s/it]
 22%|██▏       | 6297/28080 [12:26:56<42:37:24,  7.04s/it]
                                                          
{'loss': 0.6591, 'learning_rate': 0.00045214232525570735, 'epoch': 2.69}

 22%|██▏       | 6297/28080 [12:26:56<42:37:24,  7.04s/it]
 22%|██▏       | 6298/28080 [12:27:03<42:48:18,  7.07s/it]
                                                          
{'loss': 0.6295, 'learning_rate': 0.0004521253569532656, 'epoch': 2.69}

 22%|██▏       | 6298/28080 [12:27:03<42:48:18,  7.07s/it]
 22%|██▏       | 6299/28080 [12:27:10<42:59:16,  7.11s/it]
                                                          
{'loss': 0.6406, 'learning_rate': 0.00045210838596175453, 'epoch': 2.69}

 22%|██▏       | 6299/28080 [12:27:10<42:59:16,  7.11s/it]
 22%|██▏       | 6300/28080 [12:27:17<43:05:00,  7.12s/it]
                                                          
{'loss': 0.6267, 'learning_rate': 0.00045209141228139983, 'epoch': 2.69}

 22%|██▏       | 6300/28080 [12:27:17<43:05:00,  7.12s/it]
 22%|██▏       | 6301/28080 [12:27:24<42:58:33,  7.10s/it]
                                                          
{'loss': 0.6552, 'learning_rate': 0.0004520744359124274, 'epoch': 2.69}

 22%|██▏       | 6301/28080 [12:27:24<42:58:33,  7.10s/it]
 22%|██▏       | 6302/28080 [12:27:31<42:53:59,  7.09s/it]
                                                          
{'loss': 0.6608, 'learning_rate': 0.00045205745685506307, 'epoch': 2.69}

 22%|██▏       | 6302/28080 [12:27:31<42:53:59,  7.09s/it]
 22%|██▏       | 6303/28080 [12:27:38<42:49:13,  7.08s/it]
                                                          
{'loss': 0.6479, 'learning_rate': 0.00045204047510953273, 'epoch': 2.69}

 22%|██▏       | 6303/28080 [12:27:38<42:49:13,  7.08s/it]
 22%|██▏       | 6304/28080 [12:27:45<42:31:21,  7.03s/it]
                                                          
{'loss': 0.6553, 'learning_rate': 0.0004520234906760623, 'epoch': 2.69}

 22%|██▏       | 6304/28080 [12:27:45<42:31:21,  7.03s/it]
 22%|██▏       | 6305/28080 [12:27:52<42:39:19,  7.05s/it]
                                                          
{'loss': 0.6342, 'learning_rate': 0.00045200650355487783, 'epoch': 2.69}

 22%|██▏       | 6305/28080 [12:27:52<42:39:19,  7.05s/it]
 22%|██▏       | 6306/28080 [12:28:00<42:35:20,  7.04s/it]
                                                          
{'loss': 0.6678, 'learning_rate': 0.0004519895137462051, 'epoch': 2.69}

 22%|██▏       | 6306/28080 [12:28:00<42:35:20,  7.04s/it]
 22%|██▏       | 6307/28080 [12:28:07<42:42:07,  7.06s/it]
                                                          
{'loss': 0.6442, 'learning_rate': 0.00045197252125027035, 'epoch': 2.69}

 22%|██▏       | 6307/28080 [12:28:07<42:42:07,  7.06s/it]
 22%|██▏       | 6308/28080 [12:28:14<42:38:50,  7.05s/it]
                                                          
{'loss': 0.652, 'learning_rate': 0.0004519555260672995, 'epoch': 2.69}

 22%|██▏       | 6308/28080 [12:28:14<42:38:50,  7.05s/it]
 22%|██▏       | 6309/28080 [12:28:21<42:52:11,  7.09s/it]
                                                          
{'loss': 0.6523, 'learning_rate': 0.0004519385281975188, 'epoch': 2.7}

 22%|██▏       | 6309/28080 [12:28:21<42:52:11,  7.09s/it]
 22%|██▏       | 6310/28080 [12:28:28<42:49:52,  7.08s/it]
                                                          
{'loss': 0.6271, 'learning_rate': 0.0004519215276411542, 'epoch': 2.7}

 22%|██▏       | 6310/28080 [12:28:28<42:49:52,  7.08s/it]
 22%|██▏       | 6311/28080 [12:28:35<42:54:11,  7.10s/it]
                                                          
{'loss': 0.6187, 'learning_rate': 0.0004519045243984321, 'epoch': 2.7}

 22%|██▏       | 6311/28080 [12:28:35<42:54:11,  7.10s/it]
 22%|██▏       | 6312/28080 [12:28:42<42:59:54,  7.11s/it]
                                                          
{'loss': 0.6348, 'learning_rate': 0.0004518875184695785, 'epoch': 2.7}

 22%|██▏       | 6312/28080 [12:28:42<42:59:54,  7.11s/it]
 22%|██▏       | 6313/28080 [12:28:49<42:49:28,  7.08s/it]
                                                          
{'loss': 0.668, 'learning_rate': 0.0004518705098548198, 'epoch': 2.7}

 22%|██▏       | 6313/28080 [12:28:49<42:49:28,  7.08s/it]
 22%|██▏       | 6314/28080 [12:28:56<42:39:50,  7.06s/it]
                                                          
{'loss': 0.6386, 'learning_rate': 0.00045185349855438224, 'epoch': 2.7}

 22%|██▏       | 6314/28080 [12:28:56<42:39:50,  7.06s/it]
 22%|██▏       | 6315/28080 [12:29:03<42:42:06,  7.06s/it]
                                                          
{'loss': 0.6463, 'learning_rate': 0.0004518364845684921, 'epoch': 2.7}

 22%|██▏       | 6315/28080 [12:29:03<42:42:06,  7.06s/it]
 22%|██▏       | 6316/28080 [12:29:10<42:50:37,  7.09s/it]
                                                          
{'loss': 0.6318, 'learning_rate': 0.0004518194678973757, 'epoch': 2.7}

 22%|██▏       | 6316/28080 [12:29:10<42:50:37,  7.09s/it]
 22%|██▏       | 6317/28080 [12:29:18<43:01:23,  7.12s/it]
                                                          
{'loss': 0.6376, 'learning_rate': 0.00045180244854125964, 'epoch': 2.7}

 22%|██▏       | 6317/28080 [12:29:18<43:01:23,  7.12s/it]
 22%|██▎       | 6318/28080 [12:29:25<43:08:04,  7.14s/it]
                                                          
{'loss': 0.627, 'learning_rate': 0.00045178542650037, 'epoch': 2.7}

 22%|██▎       | 6318/28080 [12:29:25<43:08:04,  7.14s/it]
 23%|██▎       | 6319/28080 [12:29:32<43:05:39,  7.13s/it]
                                                          
{'loss': 0.6186, 'learning_rate': 0.00045176840177493354, 'epoch': 2.7}

 23%|██▎       | 6319/28080 [12:29:32<43:05:39,  7.13s/it]
 23%|██▎       | 6320/28080 [12:29:39<43:03:15,  7.12s/it]
                                                          
{'loss': 0.6566, 'learning_rate': 0.0004517513743651767, 'epoch': 2.7}

 23%|██▎       | 6320/28080 [12:29:39<43:03:15,  7.12s/it]
 23%|██▎       | 6321/28080 [12:29:46<42:47:51,  7.08s/it]
                                                          
{'loss': 0.6671, 'learning_rate': 0.0004517343442713259, 'epoch': 2.7}

 23%|██▎       | 6321/28080 [12:29:46<42:47:51,  7.08s/it]
 23%|██▎       | 6322/28080 [12:29:53<42:47:36,  7.08s/it]
                                                          
{'loss': 0.6384, 'learning_rate': 0.00045171731149360773, 'epoch': 2.7}

 23%|██▎       | 6322/28080 [12:29:53<42:47:36,  7.08s/it]
 23%|██▎       | 6323/28080 [12:30:00<42:52:24,  7.09s/it]
                                                          
{'loss': 0.6431, 'learning_rate': 0.00045170027603224885, 'epoch': 2.7}

 23%|██▎       | 6323/28080 [12:30:00<42:52:24,  7.09s/it]
 23%|██▎       | 6324/28080 [12:30:07<42:58:18,  7.11s/it]
                                                          
{'loss': 0.6178, 'learning_rate': 0.00045168323788747586, 'epoch': 2.7}

 23%|██▎       | 6324/28080 [12:30:07<42:58:18,  7.11s/it]
 23%|██▎       | 6325/28080 [12:30:14<42:59:17,  7.11s/it]
                                                          
{'loss': 0.6427, 'learning_rate': 0.0004516661970595155, 'epoch': 2.7}

 23%|██▎       | 6325/28080 [12:30:14<42:59:17,  7.11s/it]
 23%|██▎       | 6326/28080 [12:30:21<42:50:47,  7.09s/it]
                                                          
{'loss': 0.654, 'learning_rate': 0.0004516491535485944, 'epoch': 2.7}

 23%|██▎       | 6326/28080 [12:30:21<42:50:47,  7.09s/it]
 23%|██▎       | 6327/28080 [12:30:29<42:54:13,  7.10s/it]
                                                          
{'loss': 0.6476, 'learning_rate': 0.0004516321073549393, 'epoch': 2.7}

 23%|██▎       | 6327/28080 [12:30:29<42:54:13,  7.10s/it]
 23%|██▎       | 6328/28080 [12:30:36<42:50:15,  7.09s/it]
                                                          
{'loss': 0.6462, 'learning_rate': 0.00045161505847877715, 'epoch': 2.7}

 23%|██▎       | 6328/28080 [12:30:36<42:50:15,  7.09s/it]
 23%|██▎       | 6329/28080 [12:30:43<42:50:21,  7.09s/it]
                                                          
{'loss': 0.6576, 'learning_rate': 0.0004515980069203346, 'epoch': 2.7}

 23%|██▎       | 6329/28080 [12:30:43<42:50:21,  7.09s/it]
 23%|██▎       | 6330/28080 [12:30:50<42:47:51,  7.08s/it]
                                                          
{'loss': 0.6495, 'learning_rate': 0.00045158095267983843, 'epoch': 2.7}

 23%|██▎       | 6330/28080 [12:30:50<42:47:51,  7.08s/it]
 23%|██▎       | 6331/28080 [12:30:57<42:40:30,  7.06s/it]
                                                          
{'loss': 0.6313, 'learning_rate': 0.0004515638957575158, 'epoch': 2.7}

 23%|██▎       | 6331/28080 [12:30:57<42:40:30,  7.06s/it]
 23%|██▎       | 6332/28080 [12:31:04<42:41:53,  7.07s/it]
                                                          
{'loss': 0.651, 'learning_rate': 0.0004515468361535934, 'epoch': 2.7}

 23%|██▎       | 6332/28080 [12:31:04<42:41:53,  7.07s/it]
 23%|██▎       | 6333/28080 [12:31:11<42:48:11,  7.09s/it]
                                                          
{'loss': 0.6377, 'learning_rate': 0.0004515297738682983, 'epoch': 2.71}

 23%|██▎       | 6333/28080 [12:31:11<42:48:11,  7.09s/it]
 23%|██▎       | 6334/28080 [12:31:18<42:49:56,  7.09s/it]
                                                          
{'loss': 0.6477, 'learning_rate': 0.00045151270890185746, 'epoch': 2.71}

 23%|██▎       | 6334/28080 [12:31:18<42:49:56,  7.09s/it]
 23%|██▎       | 6335/28080 [12:31:25<42:45:34,  7.08s/it]
                                                          
{'loss': 0.635, 'learning_rate': 0.0004514956412544979, 'epoch': 2.71}

 23%|██▎       | 6335/28080 [12:31:25<42:45:34,  7.08s/it]
 23%|██▎       | 6336/28080 [12:31:32<42:44:54,  7.08s/it]
                                                          
{'loss': 0.65, 'learning_rate': 0.0004514785709264467, 'epoch': 2.71}

 23%|██▎       | 6336/28080 [12:31:32<42:44:54,  7.08s/it]
 23%|██▎       | 6337/28080 [12:31:39<42:51:11,  7.10s/it]
                                                          
{'loss': 0.6551, 'learning_rate': 0.00045146149791793096, 'epoch': 2.71}

 23%|██▎       | 6337/28080 [12:31:39<42:51:11,  7.10s/it]
 23%|██▎       | 6338/28080 [12:31:47<42:58:31,  7.12s/it]
                                                          
{'loss': 0.6365, 'learning_rate': 0.0004514444222291778, 'epoch': 2.71}

 23%|██▎       | 6338/28080 [12:31:47<42:58:31,  7.12s/it]
 23%|██▎       | 6339/28080 [12:31:54<43:01:51,  7.13s/it]
                                                          
{'loss': 0.6323, 'learning_rate': 0.0004514273438604145, 'epoch': 2.71}

 23%|██▎       | 6339/28080 [12:31:54<43:01:51,  7.13s/it]
 23%|██▎       | 6340/28080 [12:32:01<42:52:14,  7.10s/it]
                                                          
{'loss': 0.6611, 'learning_rate': 0.00045141026281186815, 'epoch': 2.71}

 23%|██▎       | 6340/28080 [12:32:01<42:52:14,  7.10s/it]
 23%|██▎       | 6341/28080 [12:32:08<42:52:25,  7.10s/it]
                                                          
{'loss': 0.646, 'learning_rate': 0.000451393179083766, 'epoch': 2.71}

 23%|██▎       | 6341/28080 [12:32:08<42:52:25,  7.10s/it]
 23%|██▎       | 6342/28080 [12:32:15<43:01:03,  7.12s/it]
                                                          
{'loss': 0.6349, 'learning_rate': 0.00045137609267633543, 'epoch': 2.71}

 23%|██▎       | 6342/28080 [12:32:15<43:01:03,  7.12s/it]
 23%|██▎       | 6343/28080 [12:32:22<42:57:15,  7.11s/it]
                                                          
{'loss': 0.6396, 'learning_rate': 0.0004513590035898037, 'epoch': 2.71}

 23%|██▎       | 6343/28080 [12:32:22<42:57:15,  7.11s/it]
 23%|██▎       | 6344/28080 [12:32:29<42:49:47,  7.09s/it]
                                                          
{'loss': 0.6431, 'learning_rate': 0.0004513419118243981, 'epoch': 2.71}

 23%|██▎       | 6344/28080 [12:32:29<42:49:47,  7.09s/it]
 23%|██▎       | 6345/28080 [12:32:36<42:52:07,  7.10s/it]
                                                          
{'loss': 0.628, 'learning_rate': 0.00045132481738034615, 'epoch': 2.71}

 23%|██▎       | 6345/28080 [12:32:36<42:52:07,  7.10s/it]
 23%|██▎       | 6346/28080 [12:32:43<42:39:44,  7.07s/it]
                                                          
{'loss': 0.6433, 'learning_rate': 0.0004513077202578751, 'epoch': 2.71}

 23%|██▎       | 6346/28080 [12:32:43<42:39:44,  7.07s/it]
 23%|██▎       | 6347/28080 [12:32:50<42:34:38,  7.05s/it]
                                                          
{'loss': 0.6592, 'learning_rate': 0.0004512906204572126, 'epoch': 2.71}

 23%|██▎       | 6347/28080 [12:32:50<42:34:38,  7.05s/it]
 23%|██▎       | 6348/28080 [12:32:57<42:43:50,  7.08s/it]
                                                          
{'loss': 0.6424, 'learning_rate': 0.00045127351797858605, 'epoch': 2.71}

 23%|██▎       | 6348/28080 [12:32:57<42:43:50,  7.08s/it]
 23%|██▎       | 6349/28080 [12:33:05<42:49:11,  7.09s/it]
                                                          
{'loss': 0.6386, 'learning_rate': 0.00045125641282222294, 'epoch': 2.71}

 23%|██▎       | 6349/28080 [12:33:05<42:49:11,  7.09s/it]
 23%|██▎       | 6350/28080 [12:33:12<42:53:58,  7.11s/it]
                                                          
{'loss': 0.669, 'learning_rate': 0.0004512393049883509, 'epoch': 2.71}

 23%|██▎       | 6350/28080 [12:33:12<42:53:58,  7.11s/it]
 23%|██▎       | 6351/28080 [12:33:19<42:36:57,  7.06s/it]
                                                          
{'loss': 0.6566, 'learning_rate': 0.0004512221944771975, 'epoch': 2.71}

 23%|██▎       | 6351/28080 [12:33:19<42:36:57,  7.06s/it]
 23%|██▎       | 6352/28080 [12:33:26<42:44:41,  7.08s/it]
                                                          
{'loss': 0.6417, 'learning_rate': 0.0004512050812889904, 'epoch': 2.71}

 23%|██▎       | 6352/28080 [12:33:26<42:44:41,  7.08s/it]
 23%|██▎       | 6353/28080 [12:33:33<42:28:30,  7.04s/it]
                                                          
{'loss': 0.6608, 'learning_rate': 0.0004511879654239573, 'epoch': 2.71}

 23%|██▎       | 6353/28080 [12:33:33<42:28:30,  7.04s/it]
 23%|██▎       | 6354/28080 [12:33:40<42:36:53,  7.06s/it]
                                                          
{'loss': 0.6462, 'learning_rate': 0.00045117084688232586, 'epoch': 2.71}

 23%|██▎       | 6354/28080 [12:33:40<42:36:53,  7.06s/it]
 23%|██▎       | 6355/28080 [12:33:47<42:43:38,  7.08s/it]
                                                          
{'loss': 0.6352, 'learning_rate': 0.00045115372566432375, 'epoch': 2.71}

 23%|██▎       | 6355/28080 [12:33:47<42:43:38,  7.08s/it]
 23%|██▎       | 6356/28080 [12:33:54<42:33:28,  7.05s/it]
                                                          
{'loss': 0.6394, 'learning_rate': 0.00045113660177017903, 'epoch': 2.72}

 23%|██▎       | 6356/28080 [12:33:54<42:33:28,  7.05s/it]
 23%|██▎       | 6357/28080 [12:34:01<42:46:04,  7.09s/it]
                                                          
{'loss': 0.632, 'learning_rate': 0.0004511194752001192, 'epoch': 2.72}

 23%|██▎       | 6357/28080 [12:34:01<42:46:04,  7.09s/it]
 23%|██▎       | 6358/28080 [12:34:08<42:44:43,  7.08s/it]
                                                          
{'loss': 0.6149, 'learning_rate': 0.00045110234595437224, 'epoch': 2.72}

 23%|██▎       | 6358/28080 [12:34:08<42:44:43,  7.08s/it]
 23%|██▎       | 6359/28080 [12:34:15<42:56:47,  7.12s/it]
                                                          
{'loss': 0.6364, 'learning_rate': 0.00045108521403316597, 'epoch': 2.72}

 23%|██▎       | 6359/28080 [12:34:15<42:56:47,  7.12s/it]
 23%|██▎       | 6360/28080 [12:34:23<42:55:22,  7.11s/it]
                                                          
{'loss': 0.6339, 'learning_rate': 0.00045106807943672846, 'epoch': 2.72}

 23%|██▎       | 6360/28080 [12:34:23<42:55:22,  7.11s/it]
 23%|██▎       | 6361/28080 [12:34:30<42:53:05,  7.11s/it]
                                                          
{'loss': 0.6321, 'learning_rate': 0.00045105094216528756, 'epoch': 2.72}

 23%|██▎       | 6361/28080 [12:34:30<42:53:05,  7.11s/it]
 23%|██▎       | 6362/28080 [12:34:37<42:56:28,  7.12s/it]
                                                          
{'loss': 0.6307, 'learning_rate': 0.0004510338022190713, 'epoch': 2.72}

 23%|██▎       | 6362/28080 [12:34:37<42:56:28,  7.12s/it]
 23%|██▎       | 6363/28080 [12:34:44<42:54:17,  7.11s/it]
                                                          
{'loss': 0.6246, 'learning_rate': 0.0004510166595983077, 'epoch': 2.72}

 23%|██▎       | 6363/28080 [12:34:44<42:54:17,  7.11s/it]
 23%|██▎       | 6364/28080 [12:34:51<42:58:11,  7.12s/it]
                                                          
{'loss': 0.6242, 'learning_rate': 0.00045099951430322484, 'epoch': 2.72}

 23%|██▎       | 6364/28080 [12:34:51<42:58:11,  7.12s/it]
 23%|██▎       | 6365/28080 [12:34:58<43:00:09,  7.13s/it]
                                                          
{'loss': 0.6457, 'learning_rate': 0.00045098236633405077, 'epoch': 2.72}

 23%|██▎       | 6365/28080 [12:34:58<43:00:09,  7.13s/it]
 23%|██▎       | 6366/28080 [12:35:05<42:50:14,  7.10s/it]
                                                          
{'loss': 0.6361, 'learning_rate': 0.0004509652156910136, 'epoch': 2.72}

 23%|██▎       | 6366/28080 [12:35:05<42:50:14,  7.10s/it]
 23%|██▎       | 6367/28080 [12:35:12<42:53:45,  7.11s/it]
                                                          
{'loss': 0.6348, 'learning_rate': 0.00045094806237434165, 'epoch': 2.72}

 23%|██▎       | 6367/28080 [12:35:12<42:53:45,  7.11s/it]
 23%|██▎       | 6368/28080 [12:35:19<42:51:43,  7.11s/it]
                                                          
{'loss': 0.6398, 'learning_rate': 0.00045093090638426305, 'epoch': 2.72}

 23%|██▎       | 6368/28080 [12:35:19<42:51:43,  7.11s/it]
 23%|██▎       | 6369/28080 [12:35:27<42:57:23,  7.12s/it]
                                                          
{'loss': 0.6467, 'learning_rate': 0.00045091374772100593, 'epoch': 2.72}

 23%|██▎       | 6369/28080 [12:35:27<42:57:23,  7.12s/it]
 23%|██▎       | 6370/28080 [12:35:34<42:52:33,  7.11s/it]
                                                          
{'loss': 0.6608, 'learning_rate': 0.00045089658638479874, 'epoch': 2.72}

 23%|██▎       | 6370/28080 [12:35:34<42:52:33,  7.11s/it]
 23%|██▎       | 6371/28080 [12:35:41<42:55:13,  7.12s/it]
                                                          
{'loss': 0.6326, 'learning_rate': 0.0004508794223758697, 'epoch': 2.72}

 23%|██▎       | 6371/28080 [12:35:41<42:55:13,  7.12s/it]
 23%|██▎       | 6372/28080 [12:35:48<43:02:08,  7.14s/it]
                                                          
{'loss': 0.6383, 'learning_rate': 0.0004508622556944472, 'epoch': 2.72}

 23%|██▎       | 6372/28080 [12:35:48<43:02:08,  7.14s/it]
 23%|██▎       | 6373/28080 [12:35:55<43:06:12,  7.15s/it]
                                                          
{'loss': 0.6322, 'learning_rate': 0.0004508450863407596, 'epoch': 2.72}

 23%|██▎       | 6373/28080 [12:35:55<43:06:12,  7.15s/it]
 23%|██▎       | 6374/28080 [12:36:02<43:02:15,  7.14s/it]
                                                          
{'loss': 0.6297, 'learning_rate': 0.00045082791431503536, 'epoch': 2.72}

 23%|██▎       | 6374/28080 [12:36:02<43:02:15,  7.14s/it]
 23%|██▎       | 6375/28080 [12:36:09<43:01:13,  7.14s/it]
                                                          
{'loss': 0.6537, 'learning_rate': 0.00045081073961750277, 'epoch': 2.72}

 23%|██▎       | 6375/28080 [12:36:09<43:01:13,  7.14s/it]
 23%|██▎       | 6376/28080 [12:36:16<42:51:25,  7.11s/it]
                                                          
{'loss': 0.6652, 'learning_rate': 0.0004507935622483906, 'epoch': 2.72}

 23%|██▎       | 6376/28080 [12:36:16<42:51:25,  7.11s/it]
 23%|██▎       | 6377/28080 [12:36:23<42:43:48,  7.09s/it]
                                                          
{'loss': 0.6328, 'learning_rate': 0.00045077638220792715, 'epoch': 2.72}

 23%|██▎       | 6377/28080 [12:36:23<42:43:48,  7.09s/it]
 23%|██▎       | 6378/28080 [12:36:31<42:46:13,  7.09s/it]
                                                          
{'loss': 0.6126, 'learning_rate': 0.00045075919949634106, 'epoch': 2.72}

 23%|██▎       | 6378/28080 [12:36:31<42:46:13,  7.09s/it]
 23%|██▎       | 6379/28080 [12:36:38<42:47:38,  7.10s/it]
                                                          
{'loss': 0.6331, 'learning_rate': 0.00045074201411386103, 'epoch': 2.73}

 23%|██▎       | 6379/28080 [12:36:38<42:47:38,  7.10s/it]
 23%|██▎       | 6380/28080 [12:36:45<42:48:27,  7.10s/it]
                                                          
{'loss': 0.6549, 'learning_rate': 0.0004507248260607155, 'epoch': 2.73}

 23%|██▎       | 6380/28080 [12:36:45<42:48:27,  7.10s/it]
 23%|██▎       | 6381/28080 [12:36:52<42:42:40,  7.09s/it]
                                                          
{'loss': 0.6168, 'learning_rate': 0.0004507076353371333, 'epoch': 2.73}

 23%|██▎       | 6381/28080 [12:36:52<42:42:40,  7.09s/it]
 23%|██▎       | 6382/28080 [12:36:59<42:48:49,  7.10s/it]
                                                          
{'loss': 0.6603, 'learning_rate': 0.00045069044194334304, 'epoch': 2.73}

 23%|██▎       | 6382/28080 [12:36:59<42:48:49,  7.10s/it]
 23%|██▎       | 6383/28080 [12:37:06<42:42:47,  7.09s/it]
                                                          
{'loss': 0.6422, 'learning_rate': 0.0004506732458795735, 'epoch': 2.73}

 23%|██▎       | 6383/28080 [12:37:06<42:42:47,  7.09s/it]
 23%|██▎       | 6384/28080 [12:37:13<42:43:11,  7.09s/it]
                                                          
{'loss': 0.6269, 'learning_rate': 0.0004506560471460534, 'epoch': 2.73}

 23%|██▎       | 6384/28080 [12:37:13<42:43:11,  7.09s/it]
 23%|██▎       | 6385/28080 [12:37:20<42:39:20,  7.08s/it]
                                                          
{'loss': 0.6249, 'learning_rate': 0.0004506388457430116, 'epoch': 2.73}

 23%|██▎       | 6385/28080 [12:37:20<42:39:20,  7.08s/it]
 23%|██▎       | 6386/28080 [12:37:27<42:52:19,  7.11s/it]
                                                          
{'loss': 0.617, 'learning_rate': 0.000450621641670677, 'epoch': 2.73}

 23%|██▎       | 6386/28080 [12:37:27<42:52:19,  7.11s/it]
 23%|██▎       | 6387/28080 [12:37:35<42:54:05,  7.12s/it]
                                                          
{'loss': 0.6619, 'learning_rate': 0.00045060443492927837, 'epoch': 2.73}

 23%|██▎       | 6387/28080 [12:37:35<42:54:05,  7.12s/it]
 23%|██▎       | 6388/28080 [12:37:42<42:40:51,  7.08s/it]
                                                          
{'loss': 0.6566, 'learning_rate': 0.00045058722551904475, 'epoch': 2.73}

 23%|██▎       | 6388/28080 [12:37:42<42:40:51,  7.08s/it]
 23%|██▎       | 6389/28080 [12:37:49<42:55:50,  7.13s/it]
                                                          
{'loss': 0.6261, 'learning_rate': 0.00045057001344020497, 'epoch': 2.73}

 23%|██▎       | 6389/28080 [12:37:49<42:55:50,  7.13s/it]
 23%|██▎       | 6390/28080 [12:37:56<42:48:22,  7.10s/it]
                                                          
{'loss': 0.6533, 'learning_rate': 0.00045055279869298816, 'epoch': 2.73}

 23%|██▎       | 6390/28080 [12:37:56<42:48:22,  7.10s/it]
 23%|██▎       | 6391/28080 [12:38:03<42:48:30,  7.11s/it]
                                                          
{'loss': 0.6566, 'learning_rate': 0.00045053558127762316, 'epoch': 2.73}

 23%|██▎       | 6391/28080 [12:38:03<42:48:30,  7.11s/it]
 23%|██▎       | 6392/28080 [12:38:10<42:44:42,  7.10s/it]
                                                          
{'loss': 0.6463, 'learning_rate': 0.0004505183611943392, 'epoch': 2.73}

 23%|██▎       | 6392/28080 [12:38:10<42:44:42,  7.10s/it]
 23%|██▎       | 6393/28080 [12:38:17<42:47:52,  7.10s/it]
                                                          
{'loss': 0.6186, 'learning_rate': 0.00045050113844336524, 'epoch': 2.73}

 23%|██▎       | 6393/28080 [12:38:17<42:47:52,  7.10s/it]
 23%|██▎       | 6394/28080 [12:38:24<42:43:31,  7.09s/it]
                                                          
{'loss': 0.6454, 'learning_rate': 0.00045048391302493057, 'epoch': 2.73}

 23%|██▎       | 6394/28080 [12:38:24<42:43:31,  7.09s/it]
 23%|██▎       | 6395/28080 [12:38:31<42:44:51,  7.10s/it]
                                                          
{'loss': 0.6587, 'learning_rate': 0.0004504666849392642, 'epoch': 2.73}

 23%|██▎       | 6395/28080 [12:38:31<42:44:51,  7.10s/it]
 23%|██▎       | 6396/28080 [12:38:38<42:47:55,  7.11s/it]
                                                          
{'loss': 0.6303, 'learning_rate': 0.00045044945418659546, 'epoch': 2.73}

 23%|██▎       | 6396/28080 [12:38:38<42:47:55,  7.11s/it]
 23%|██▎       | 6397/28080 [12:38:45<42:38:57,  7.08s/it]
                                                          
{'loss': 0.6574, 'learning_rate': 0.00045043222076715343, 'epoch': 2.73}

 23%|██▎       | 6397/28080 [12:38:45<42:38:57,  7.08s/it]
 23%|██▎       | 6398/28080 [12:38:53<42:43:05,  7.09s/it]
                                                          
{'loss': 0.63, 'learning_rate': 0.0004504149846811676, 'epoch': 2.73}

 23%|██▎       | 6398/28080 [12:38:53<42:43:05,  7.09s/it]
 23%|██▎       | 6399/28080 [12:39:00<42:44:00,  7.10s/it]
                                                          
{'loss': 0.6386, 'learning_rate': 0.00045039774592886707, 'epoch': 2.73}

 23%|██▎       | 6399/28080 [12:39:00<42:44:00,  7.10s/it]
 23%|██▎       | 6400/28080 [12:39:07<42:50:46,  7.11s/it]
                                                          
{'loss': 0.6415, 'learning_rate': 0.0004503805045104813, 'epoch': 2.73}

 23%|██▎       | 6400/28080 [12:39:07<42:50:46,  7.11s/it]
 23%|██▎       | 6401/28080 [12:39:14<42:50:21,  7.11s/it]
                                                          
{'loss': 0.6481, 'learning_rate': 0.0004503632604262396, 'epoch': 2.73}

 23%|██▎       | 6401/28080 [12:39:14<42:50:21,  7.11s/it]
 23%|██▎       | 6402/28080 [12:39:21<42:54:29,  7.13s/it]
                                                          
{'loss': 0.6371, 'learning_rate': 0.00045034601367637146, 'epoch': 2.73}

 23%|██▎       | 6402/28080 [12:39:21<42:54:29,  7.13s/it]
 23%|██▎       | 6403/28080 [12:39:28<42:48:14,  7.11s/it]
                                                          
{'loss': 0.6569, 'learning_rate': 0.0004503287642611062, 'epoch': 2.74}

 23%|██▎       | 6403/28080 [12:39:28<42:48:14,  7.11s/it]
 23%|██▎       | 6404/28080 [12:39:35<42:41:05,  7.09s/it]
                                                          
{'loss': 0.6285, 'learning_rate': 0.0004503115121806736, 'epoch': 2.74}

 23%|██▎       | 6404/28080 [12:39:35<42:41:05,  7.09s/it]
 23%|██▎       | 6405/28080 [12:39:42<42:44:57,  7.10s/it]
                                                          
{'loss': 0.6526, 'learning_rate': 0.00045029425743530285, 'epoch': 2.74}

 23%|██▎       | 6405/28080 [12:39:42<42:44:57,  7.10s/it]
 23%|██▎       | 6406/28080 [12:39:49<42:39:19,  7.08s/it]
                                                          
{'loss': 0.6442, 'learning_rate': 0.0004502770000252236, 'epoch': 2.74}

 23%|██▎       | 6406/28080 [12:39:49<42:39:19,  7.08s/it]
 23%|██▎       | 6407/28080 [12:39:57<42:47:00,  7.11s/it]
                                                          
{'loss': 0.6323, 'learning_rate': 0.0004502597399506655, 'epoch': 2.74}

 23%|██▎       | 6407/28080 [12:39:57<42:47:00,  7.11s/it]
 23%|██▎       | 6408/28080 [12:40:04<42:41:42,  7.09s/it]
                                                          
{'loss': 0.6647, 'learning_rate': 0.0004502424772118582, 'epoch': 2.74}

 23%|██▎       | 6408/28080 [12:40:04<42:41:42,  7.09s/it]
 23%|██▎       | 6409/28080 [12:40:11<42:46:29,  7.11s/it]
                                                          
{'loss': 0.6309, 'learning_rate': 0.0004502252118090313, 'epoch': 2.74}

 23%|██▎       | 6409/28080 [12:40:11<42:46:29,  7.11s/it]
 23%|██▎       | 6410/28080 [12:40:18<43:06:14,  7.16s/it]
                                                          
{'loss': 0.6209, 'learning_rate': 0.0004502079437424145, 'epoch': 2.74}

 23%|██▎       | 6410/28080 [12:40:18<43:06:14,  7.16s/it]
 23%|██▎       | 6411/28080 [12:40:25<43:05:39,  7.16s/it]
                                                          
{'loss': 0.6372, 'learning_rate': 0.00045019067301223757, 'epoch': 2.74}

 23%|██▎       | 6411/28080 [12:40:25<43:05:39,  7.16s/it]
 23%|██▎       | 6412/28080 [12:40:32<42:55:53,  7.13s/it]
                                                          
{'loss': 0.6448, 'learning_rate': 0.00045017339961873025, 'epoch': 2.74}

 23%|██▎       | 6412/28080 [12:40:32<42:55:53,  7.13s/it]
 23%|██▎       | 6413/28080 [12:40:39<42:35:40,  7.08s/it]
                                                          
{'loss': 0.6406, 'learning_rate': 0.00045015612356212245, 'epoch': 2.74}

 23%|██▎       | 6413/28080 [12:40:39<42:35:40,  7.08s/it]
 23%|██▎       | 6414/28080 [12:40:46<42:37:53,  7.08s/it]
                                                          
{'loss': 0.6536, 'learning_rate': 0.0004501388448426438, 'epoch': 2.74}

 23%|██▎       | 6414/28080 [12:40:46<42:37:53,  7.08s/it]
 23%|██▎       | 6415/28080 [12:40:53<42:44:10,  7.10s/it]
                                                          
{'loss': 0.644, 'learning_rate': 0.00045012156346052433, 'epoch': 2.74}

 23%|██▎       | 6415/28080 [12:40:53<42:44:10,  7.10s/it]
 23%|██▎       | 6416/28080 [12:41:01<42:49:30,  7.12s/it]
                                                          
{'loss': 0.6304, 'learning_rate': 0.00045010427941599387, 'epoch': 2.74}

 23%|██▎       | 6416/28080 [12:41:01<42:49:30,  7.12s/it]
 23%|██▎       | 6417/28080 [12:41:08<42:54:36,  7.13s/it]
                                                          
{'loss': 0.645, 'learning_rate': 0.00045008699270928244, 'epoch': 2.74}

 23%|██▎       | 6417/28080 [12:41:08<42:54:36,  7.13s/it]
 23%|██▎       | 6418/28080 [12:41:15<42:54:07,  7.13s/it]
                                                          
{'loss': 0.6429, 'learning_rate': 0.00045006970334062006, 'epoch': 2.74}

 23%|██▎       | 6418/28080 [12:41:15<42:54:07,  7.13s/it]
 23%|██▎       | 6419/28080 [12:41:22<42:54:33,  7.13s/it]
                                                          
{'loss': 0.6468, 'learning_rate': 0.00045005241131023657, 'epoch': 2.74}

 23%|██▎       | 6419/28080 [12:41:22<42:54:33,  7.13s/it]
 23%|██▎       | 6420/28080 [12:41:29<42:55:21,  7.13s/it]
                                                          
{'loss': 0.6159, 'learning_rate': 0.00045003511661836215, 'epoch': 2.74}

 23%|██▎       | 6420/28080 [12:41:29<42:55:21,  7.13s/it]
 23%|██▎       | 6421/28080 [12:41:36<42:49:55,  7.12s/it]
                                                          
{'loss': 0.6278, 'learning_rate': 0.0004500178192652269, 'epoch': 2.74}

 23%|██▎       | 6421/28080 [12:41:36<42:49:55,  7.12s/it]
 23%|██▎       | 6422/28080 [12:41:43<42:48:42,  7.12s/it]
                                                          
{'loss': 0.6197, 'learning_rate': 0.00045000051925106086, 'epoch': 2.74}

 23%|██▎       | 6422/28080 [12:41:43<42:48:42,  7.12s/it]
 23%|██▎       | 6423/28080 [12:41:50<42:42:14,  7.10s/it]
                                                          
{'loss': 0.6473, 'learning_rate': 0.0004499832165760943, 'epoch': 2.74}

 23%|██▎       | 6423/28080 [12:41:50<42:42:14,  7.10s/it]
 23%|██▎       | 6424/28080 [12:41:57<42:35:19,  7.08s/it]
                                                          
{'loss': 0.6405, 'learning_rate': 0.00044996591124055744, 'epoch': 2.74}

 23%|██▎       | 6424/28080 [12:41:57<42:35:19,  7.08s/it]
 23%|██▎       | 6425/28080 [12:42:05<42:43:02,  7.10s/it]
                                                          
{'loss': 0.6239, 'learning_rate': 0.0004499486032446802, 'epoch': 2.74}

 23%|██▎       | 6425/28080 [12:42:05<42:43:02,  7.10s/it]
 23%|██▎       | 6426/28080 [12:42:12<42:31:43,  7.07s/it]
                                                          
{'loss': 0.6422, 'learning_rate': 0.0004499312925886933, 'epoch': 2.75}

 23%|██▎       | 6426/28080 [12:42:12<42:31:43,  7.07s/it]
 23%|██▎       | 6427/28080 [12:42:19<42:24:25,  7.05s/it]
                                                          
{'loss': 0.6358, 'learning_rate': 0.00044991397927282665, 'epoch': 2.75}

 23%|██▎       | 6427/28080 [12:42:19<42:24:25,  7.05s/it]
 23%|██▎       | 6428/28080 [12:42:26<42:36:11,  7.08s/it]
                                                          
{'loss': 0.6311, 'learning_rate': 0.00044989666329731077, 'epoch': 2.75}

 23%|██▎       | 6428/28080 [12:42:26<42:36:11,  7.08s/it]
 23%|██▎       | 6429/28080 [12:42:33<42:34:09,  7.08s/it]
                                                          
{'loss': 0.6526, 'learning_rate': 0.0004498793446623761, 'epoch': 2.75}

 23%|██▎       | 6429/28080 [12:42:33<42:34:09,  7.08s/it]
 23%|██▎       | 6430/28080 [12:42:40<42:53:27,  7.13s/it]
                                                          
{'loss': 0.6467, 'learning_rate': 0.0004498620233682529, 'epoch': 2.75}

 23%|██▎       | 6430/28080 [12:42:40<42:53:27,  7.13s/it]
 23%|██▎       | 6431/28080 [12:42:47<42:51:02,  7.13s/it]
                                                          
{'loss': 0.6393, 'learning_rate': 0.0004498446994151716, 'epoch': 2.75}

 23%|██▎       | 6431/28080 [12:42:47<42:51:02,  7.13s/it]
 23%|██▎       | 6432/28080 [12:42:54<42:43:07,  7.10s/it]
                                                          
{'loss': 0.6441, 'learning_rate': 0.0004498273728033628, 'epoch': 2.75}

 23%|██▎       | 6432/28080 [12:42:54<42:43:07,  7.10s/it]
 23%|██▎       | 6433/28080 [12:43:01<42:38:51,  7.09s/it]
                                                          
{'loss': 0.6522, 'learning_rate': 0.0004498100435330569, 'epoch': 2.75}

 23%|██▎       | 6433/28080 [12:43:01<42:38:51,  7.09s/it]
 23%|██▎       | 6434/28080 [12:43:08<42:44:32,  7.11s/it]
                                                          
{'loss': 0.6223, 'learning_rate': 0.0004497927116044846, 'epoch': 2.75}

 23%|██▎       | 6434/28080 [12:43:08<42:44:32,  7.11s/it]
 23%|██▎       | 6435/28080 [12:43:16<42:49:40,  7.12s/it]
                                                          
{'loss': 0.6311, 'learning_rate': 0.0004497753770178763, 'epoch': 2.75}

 23%|██▎       | 6435/28080 [12:43:16<42:49:40,  7.12s/it]
 23%|██▎       | 6436/28080 [12:43:23<42:44:35,  7.11s/it]
                                                          
{'loss': 0.6468, 'learning_rate': 0.00044975803977346276, 'epoch': 2.75}

 23%|██▎       | 6436/28080 [12:43:23<42:44:35,  7.11s/it]
 23%|██▎       | 6437/28080 [12:43:30<42:47:34,  7.12s/it]
                                                          
{'loss': 0.6478, 'learning_rate': 0.0004497406998714746, 'epoch': 2.75}

 23%|██▎       | 6437/28080 [12:43:30<42:47:34,  7.12s/it]
 23%|██▎       | 6438/28080 [12:43:37<42:38:28,  7.09s/it]
                                                          
{'loss': 0.6409, 'learning_rate': 0.0004497233573121424, 'epoch': 2.75}

 23%|██▎       | 6438/28080 [12:43:37<42:38:28,  7.09s/it]
 23%|██▎       | 6439/28080 [12:43:44<42:25:17,  7.06s/it]
                                                          
{'loss': 0.6402, 'learning_rate': 0.0004497060120956971, 'epoch': 2.75}

 23%|██▎       | 6439/28080 [12:43:44<42:25:17,  7.06s/it]
 23%|██▎       | 6440/28080 [12:43:51<42:37:03,  7.09s/it]
                                                          
{'loss': 0.6432, 'learning_rate': 0.0004496886642223692, 'epoch': 2.75}

 23%|██▎       | 6440/28080 [12:43:51<42:37:03,  7.09s/it]
 23%|██▎       | 6441/28080 [12:43:58<42:19:37,  7.04s/it]
                                                          
{'loss': 0.6597, 'learning_rate': 0.0004496713136923897, 'epoch': 2.75}

 23%|██▎       | 6441/28080 [12:43:58<42:19:37,  7.04s/it]
 23%|██▎       | 6442/28080 [12:44:05<42:17:16,  7.04s/it]
                                                          
{'loss': 0.6318, 'learning_rate': 0.0004496539605059894, 'epoch': 2.75}

 23%|██▎       | 6442/28080 [12:44:05<42:17:16,  7.04s/it]
 23%|██▎       | 6443/28080 [12:44:12<42:24:35,  7.06s/it]
                                                          
{'loss': 0.6328, 'learning_rate': 0.00044963660466339905, 'epoch': 2.75}

 23%|██▎       | 6443/28080 [12:44:12<42:24:35,  7.06s/it]
 23%|██▎       | 6444/28080 [12:44:19<42:35:21,  7.09s/it]
                                                          
{'loss': 0.6074, 'learning_rate': 0.0004496192461648497, 'epoch': 2.75}

 23%|██▎       | 6444/28080 [12:44:19<42:35:21,  7.09s/it]
 23%|██▎       | 6445/28080 [12:44:26<42:35:14,  7.09s/it]
                                                          
{'loss': 0.6244, 'learning_rate': 0.0004496018850105721, 'epoch': 2.75}

 23%|██▎       | 6445/28080 [12:44:26<42:35:14,  7.09s/it]
 23%|██▎       | 6446/28080 [12:44:33<42:38:57,  7.10s/it]
                                                          
{'loss': 0.6416, 'learning_rate': 0.0004495845212007974, 'epoch': 2.75}

 23%|██▎       | 6446/28080 [12:44:33<42:38:57,  7.10s/it]
 23%|██▎       | 6447/28080 [12:44:41<42:40:42,  7.10s/it]
                                                          
{'loss': 0.6352, 'learning_rate': 0.0004495671547357566, 'epoch': 2.75}

 23%|██▎       | 6447/28080 [12:44:41<42:40:42,  7.10s/it]
 23%|██▎       | 6448/28080 [12:44:48<42:48:50,  7.13s/it]
                                                          
{'loss': 0.6225, 'learning_rate': 0.0004495497856156806, 'epoch': 2.75}

 23%|██▎       | 6448/28080 [12:44:48<42:48:50,  7.13s/it]
 23%|██▎       | 6449/28080 [12:44:55<42:35:44,  7.09s/it]
                                                          
{'loss': 0.6258, 'learning_rate': 0.0004495324138408007, 'epoch': 2.75}

 23%|██▎       | 6449/28080 [12:44:55<42:35:44,  7.09s/it]
 23%|██▎       | 6450/28080 [12:45:02<42:40:53,  7.10s/it]
                                                          
{'loss': 0.6291, 'learning_rate': 0.00044951503941134777, 'epoch': 2.76}

 23%|██▎       | 6450/28080 [12:45:02<42:40:53,  7.10s/it]
 23%|██▎       | 6451/28080 [12:45:09<42:45:02,  7.12s/it]
                                                          
{'loss': 0.6345, 'learning_rate': 0.0004494976623275531, 'epoch': 2.76}

 23%|██▎       | 6451/28080 [12:45:09<42:45:02,  7.12s/it]
 23%|██▎       | 6452/28080 [12:45:16<42:47:58,  7.12s/it]
                                                          
{'loss': 0.6381, 'learning_rate': 0.0004494802825896478, 'epoch': 2.76}

 23%|██▎       | 6452/28080 [12:45:16<42:47:58,  7.12s/it]
 23%|██▎       | 6453/28080 [12:45:23<42:46:19,  7.12s/it]
                                                          
{'loss': 0.6213, 'learning_rate': 0.00044946290019786317, 'epoch': 2.76}

 23%|██▎       | 6453/28080 [12:45:23<42:46:19,  7.12s/it]
 23%|██▎       | 6454/28080 [12:45:30<42:50:33,  7.13s/it]
                                                          
{'loss': 0.6231, 'learning_rate': 0.0004494455151524304, 'epoch': 2.76}

 23%|██▎       | 6454/28080 [12:45:30<42:50:33,  7.13s/it]
 23%|██▎       | 6455/28080 [12:45:37<42:42:40,  7.11s/it]
                                                          
{'loss': 0.609, 'learning_rate': 0.00044942812745358087, 'epoch': 2.76}

 23%|██▎       | 6455/28080 [12:45:37<42:42:40,  7.11s/it]
 23%|██▎       | 6456/28080 [12:45:45<42:43:46,  7.11s/it]
                                                          
{'loss': 0.6506, 'learning_rate': 0.0004494107371015458, 'epoch': 2.76}

 23%|██▎       | 6456/28080 [12:45:45<42:43:46,  7.11s/it]
 23%|██▎       | 6457/28080 [12:45:52<42:49:54,  7.13s/it]
                                                          
{'loss': 0.6396, 'learning_rate': 0.0004493933440965566, 'epoch': 2.76}

 23%|██▎       | 6457/28080 [12:45:52<42:49:54,  7.13s/it]
 23%|██▎       | 6458/28080 [12:45:59<42:37:51,  7.10s/it]
                                                          
{'loss': 0.6593, 'learning_rate': 0.00044937594843884467, 'epoch': 2.76}

 23%|██▎       | 6458/28080 [12:45:59<42:37:51,  7.10s/it]
 23%|██▎       | 6459/28080 [12:46:06<42:45:52,  7.12s/it]
                                                          
{'loss': 0.6201, 'learning_rate': 0.00044935855012864133, 'epoch': 2.76}

 23%|██▎       | 6459/28080 [12:46:06<42:45:52,  7.12s/it]
 23%|██▎       | 6460/28080 [12:46:13<42:47:32,  7.13s/it]
                                                          
{'loss': 0.6381, 'learning_rate': 0.0004493411491661783, 'epoch': 2.76}

 23%|██▎       | 6460/28080 [12:46:13<42:47:32,  7.13s/it]
 23%|██▎       | 6461/28080 [12:46:20<42:46:56,  7.12s/it]
                                                          
{'loss': 0.6424, 'learning_rate': 0.00044932374555168686, 'epoch': 2.76}

 23%|██▎       | 6461/28080 [12:46:20<42:46:56,  7.12s/it]
 23%|██▎       | 6462/28080 [12:46:27<42:48:48,  7.13s/it]
                                                          
{'loss': 0.643, 'learning_rate': 0.00044930633928539867, 'epoch': 2.76}

 23%|██▎       | 6462/28080 [12:46:27<42:48:48,  7.13s/it]
 23%|██▎       | 6463/28080 [12:46:34<42:50:21,  7.13s/it]
                                                          
{'loss': 0.6342, 'learning_rate': 0.00044928893036754516, 'epoch': 2.76}

 23%|██▎       | 6463/28080 [12:46:34<42:50:21,  7.13s/it]
 23%|██▎       | 6464/28080 [12:46:41<42:34:34,  7.09s/it]
                                                          
{'loss': 0.6558, 'learning_rate': 0.00044927151879835806, 'epoch': 2.76}

 23%|██▎       | 6464/28080 [12:46:41<42:34:34,  7.09s/it]
 23%|██▎       | 6465/28080 [12:46:49<42:39:37,  7.11s/it]
                                                          
{'loss': 0.6242, 'learning_rate': 0.0004492541045780689, 'epoch': 2.76}

 23%|██▎       | 6465/28080 [12:46:49<42:39:37,  7.11s/it]
 23%|██▎       | 6466/28080 [12:46:56<42:52:38,  7.14s/it]
                                                          
{'loss': 0.6229, 'learning_rate': 0.00044923668770690964, 'epoch': 2.76}

 23%|██▎       | 6466/28080 [12:46:56<42:52:38,  7.14s/it]
 23%|██▎       | 6467/28080 [12:47:03<42:48:05,  7.13s/it]
                                                          
{'loss': 0.6369, 'learning_rate': 0.0004492192681851116, 'epoch': 2.76}

 23%|██▎       | 6467/28080 [12:47:03<42:48:05,  7.13s/it]
 23%|██▎       | 6468/28080 [12:47:10<42:46:06,  7.12s/it]
                                                          
{'loss': 0.6386, 'learning_rate': 0.0004492018460129068, 'epoch': 2.76}

 23%|██▎       | 6468/28080 [12:47:10<42:46:06,  7.12s/it]
 23%|██▎       | 6469/28080 [12:47:17<42:44:26,  7.12s/it]
                                                          
{'loss': 0.6433, 'learning_rate': 0.00044918442119052694, 'epoch': 2.76}

 23%|██▎       | 6469/28080 [12:47:17<42:44:26,  7.12s/it]
 23%|██▎       | 6470/28080 [12:47:24<42:35:17,  7.09s/it]
                                                          
{'loss': 0.6658, 'learning_rate': 0.00044916699371820384, 'epoch': 2.76}

 23%|██▎       | 6470/28080 [12:47:24<42:35:17,  7.09s/it]
 23%|██▎       | 6471/28080 [12:47:31<42:35:30,  7.10s/it]
                                                          
{'loss': 0.6337, 'learning_rate': 0.0004491495635961694, 'epoch': 2.76}

 23%|██▎       | 6471/28080 [12:47:31<42:35:30,  7.10s/it]
 23%|██▎       | 6472/28080 [12:47:38<42:31:34,  7.09s/it]
                                                          
{'loss': 0.66, 'learning_rate': 0.00044913213082465545, 'epoch': 2.76}

 23%|██▎       | 6472/28080 [12:47:38<42:31:34,  7.09s/it]
 23%|██▎       | 6473/28080 [12:47:45<42:26:22,  7.07s/it]
                                                          
{'loss': 0.6592, 'learning_rate': 0.00044911469540389384, 'epoch': 2.77}

 23%|██▎       | 6473/28080 [12:47:45<42:26:22,  7.07s/it]
 23%|██▎       | 6474/28080 [12:47:52<42:27:15,  7.07s/it]
                                                          
{'loss': 0.6336, 'learning_rate': 0.0004490972573341167, 'epoch': 2.77}

 23%|██▎       | 6474/28080 [12:47:52<42:27:15,  7.07s/it]
 23%|██▎       | 6475/28080 [12:48:00<42:34:30,  7.09s/it]
                                                          
{'loss': 0.6231, 'learning_rate': 0.00044907981661555595, 'epoch': 2.77}

 23%|██▎       | 6475/28080 [12:48:00<42:34:30,  7.09s/it]
 23%|██▎       | 6476/28080 [12:48:07<42:37:10,  7.10s/it]
                                                          
{'loss': 0.6157, 'learning_rate': 0.00044906237324844356, 'epoch': 2.77}

 23%|██▎       | 6476/28080 [12:48:07<42:37:10,  7.10s/it]
 23%|██▎       | 6477/28080 [12:48:14<42:43:42,  7.12s/it]
                                                          
{'loss': 0.6447, 'learning_rate': 0.00044904492723301173, 'epoch': 2.77}

 23%|██▎       | 6477/28080 [12:48:14<42:43:42,  7.12s/it]
 23%|██▎       | 6478/28080 [12:48:21<42:44:41,  7.12s/it]
                                                          
{'loss': 0.6344, 'learning_rate': 0.0004490274785694924, 'epoch': 2.77}

 23%|██▎       | 6478/28080 [12:48:21<42:44:41,  7.12s/it]
 23%|██▎       | 6479/28080 [12:48:28<42:42:13,  7.12s/it]
                                                          
{'loss': 0.6614, 'learning_rate': 0.000449010027258118, 'epoch': 2.77}

 23%|██▎       | 6479/28080 [12:48:28<42:42:13,  7.12s/it]
 23%|██▎       | 6480/28080 [12:48:35<42:40:20,  7.11s/it]
                                                          
{'loss': 0.6474, 'learning_rate': 0.0004489925732991203, 'epoch': 2.77}

 23%|██▎       | 6480/28080 [12:48:35<42:40:20,  7.11s/it]
 23%|██▎       | 6481/28080 [12:48:42<42:36:56,  7.10s/it]
                                                          
{'loss': 0.6483, 'learning_rate': 0.0004489751166927317, 'epoch': 2.77}

 23%|██▎       | 6481/28080 [12:48:42<42:36:56,  7.10s/it]
 23%|██▎       | 6482/28080 [12:48:49<42:19:57,  7.06s/it]
                                                          
{'loss': 0.6579, 'learning_rate': 0.0004489576574391845, 'epoch': 2.77}

 23%|██▎       | 6482/28080 [12:48:49<42:19:57,  7.06s/it]
 23%|██▎       | 6483/28080 [12:48:56<42:30:08,  7.08s/it]
                                                          
{'loss': 0.6659, 'learning_rate': 0.0004489401955387109, 'epoch': 2.77}

 23%|██▎       | 6483/28080 [12:48:56<42:30:08,  7.08s/it]
 23%|██▎       | 6484/28080 [12:49:03<42:29:39,  7.08s/it]
                                                          
{'loss': 0.6544, 'learning_rate': 0.0004489227309915433, 'epoch': 2.77}

 23%|██▎       | 6484/28080 [12:49:03<42:29:39,  7.08s/it]
 23%|██▎       | 6485/28080 [12:49:11<42:37:11,  7.10s/it]
                                                          
{'loss': 0.6415, 'learning_rate': 0.0004489052637979139, 'epoch': 2.77}

 23%|██▎       | 6485/28080 [12:49:11<42:37:11,  7.10s/it]
 23%|██▎       | 6486/28080 [12:49:18<42:38:03,  7.11s/it]
                                                          
{'loss': 0.6337, 'learning_rate': 0.00044888779395805525, 'epoch': 2.77}

 23%|██▎       | 6486/28080 [12:49:18<42:38:03,  7.11s/it]
 23%|██▎       | 6487/28080 [12:49:25<42:32:46,  7.09s/it]
                                                          
{'loss': 0.6357, 'learning_rate': 0.0004488703214721996, 'epoch': 2.77}

 23%|██▎       | 6487/28080 [12:49:25<42:32:46,  7.09s/it]
 23%|██▎       | 6488/28080 [12:49:32<42:35:53,  7.10s/it]
                                                          
{'loss': 0.6415, 'learning_rate': 0.00044885284634057956, 'epoch': 2.77}

 23%|██▎       | 6488/28080 [12:49:32<42:35:53,  7.10s/it]
 23%|██▎       | 6489/28080 [12:49:39<42:13:45,  7.04s/it]
                                                          
{'loss': 0.6405, 'learning_rate': 0.0004488353685634274, 'epoch': 2.77}

 23%|██▎       | 6489/28080 [12:49:39<42:13:45,  7.04s/it]
 23%|██▎       | 6490/28080 [12:49:46<42:06:53,  7.02s/it]
                                                          
{'loss': 0.6532, 'learning_rate': 0.0004488178881409759, 'epoch': 2.77}

 23%|██▎       | 6490/28080 [12:49:46<42:06:53,  7.02s/it]
 23%|██▎       | 6491/28080 [12:49:53<42:10:19,  7.03s/it]
                                                          
{'loss': 0.649, 'learning_rate': 0.00044880040507345754, 'epoch': 2.77}

 23%|██▎       | 6491/28080 [12:49:53<42:10:19,  7.03s/it]
 23%|██▎       | 6492/28080 [12:50:00<42:07:49,  7.03s/it]
                                                          
{'loss': 0.6531, 'learning_rate': 0.0004487829193611048, 'epoch': 2.77}

 23%|██▎       | 6492/28080 [12:50:00<42:07:49,  7.03s/it]
 23%|██▎       | 6493/28080 [12:50:07<42:22:07,  7.07s/it]
                                                          
{'loss': 0.6356, 'learning_rate': 0.00044876543100415045, 'epoch': 2.77}

 23%|██▎       | 6493/28080 [12:50:07<42:22:07,  7.07s/it]
 23%|██▎       | 6494/28080 [12:50:14<42:31:05,  7.09s/it]
                                                          
{'loss': 0.637, 'learning_rate': 0.00044874794000282703, 'epoch': 2.77}

 23%|██▎       | 6494/28080 [12:50:14<42:31:05,  7.09s/it]
 23%|██▎       | 6495/28080 [12:50:21<42:31:30,  7.09s/it]
                                                          
{'loss': 0.6427, 'learning_rate': 0.00044873044635736735, 'epoch': 2.77}

 23%|██▎       | 6495/28080 [12:50:21<42:31:30,  7.09s/it]
 23%|██▎       | 6496/28080 [12:50:28<42:31:26,  7.09s/it]
                                                          
{'loss': 0.6544, 'learning_rate': 0.0004487129500680041, 'epoch': 2.78}

 23%|██▎       | 6496/28080 [12:50:28<42:31:26,  7.09s/it]
 23%|██▎       | 6497/28080 [12:50:35<42:27:28,  7.08s/it]
                                                          
{'loss': 0.659, 'learning_rate': 0.00044869545113497, 'epoch': 2.78}

 23%|██▎       | 6497/28080 [12:50:35<42:27:28,  7.08s/it]
 23%|██▎       | 6498/28080 [12:50:43<42:30:29,  7.09s/it]
                                                          
{'loss': 0.6347, 'learning_rate': 0.000448677949558498, 'epoch': 2.78}

 23%|██▎       | 6498/28080 [12:50:43<42:30:29,  7.09s/it]
 23%|██▎       | 6499/28080 [12:50:50<42:25:36,  7.08s/it]
                                                          
{'loss': 0.6503, 'learning_rate': 0.00044866044533882076, 'epoch': 2.78}

 23%|██▎       | 6499/28080 [12:50:50<42:25:36,  7.08s/it]
 23%|██▎       | 6500/28080 [12:50:57<42:18:34,  7.06s/it]
                                                          
{'loss': 0.6558, 'learning_rate': 0.0004486429384761713, 'epoch': 2.78}

 23%|██▎       | 6500/28080 [12:50:57<42:18:34,  7.06s/it]
 23%|██▎       | 6501/28080 [12:51:04<42:28:45,  7.09s/it]
                                                          
{'loss': 0.6455, 'learning_rate': 0.0004486254289707825, 'epoch': 2.78}

 23%|██▎       | 6501/28080 [12:51:04<42:28:45,  7.09s/it]
 23%|██▎       | 6502/28080 [12:51:11<42:22:40,  7.07s/it]
                                                          
{'loss': 0.6361, 'learning_rate': 0.00044860791682288715, 'epoch': 2.78}

 23%|██▎       | 6502/28080 [12:51:11<42:22:40,  7.07s/it]
 23%|██▎       | 6503/28080 [12:51:18<42:19:11,  7.06s/it]
                                                          
{'loss': 0.6505, 'learning_rate': 0.0004485904020327185, 'epoch': 2.78}

 23%|██▎       | 6503/28080 [12:51:18<42:19:11,  7.06s/it]
 23%|██▎       | 6504/28080 [12:51:25<42:29:55,  7.09s/it]
                                                          
{'loss': 0.6451, 'learning_rate': 0.0004485728846005094, 'epoch': 2.78}

 23%|██▎       | 6504/28080 [12:51:25<42:29:55,  7.09s/it]
 23%|██▎       | 6505/28080 [12:51:32<42:29:40,  7.09s/it]
                                                          
{'loss': 0.6428, 'learning_rate': 0.0004485553645264928, 'epoch': 2.78}

 23%|██▎       | 6505/28080 [12:51:32<42:29:40,  7.09s/it]
 23%|██▎       | 6506/28080 [12:51:39<42:27:10,  7.08s/it]
                                                          
{'loss': 0.6329, 'learning_rate': 0.000448537841810902, 'epoch': 2.78}

 23%|██▎       | 6506/28080 [12:51:39<42:27:10,  7.08s/it]
 23%|██▎       | 6507/28080 [12:51:46<42:39:37,  7.12s/it]
                                                          
{'loss': 0.6408, 'learning_rate': 0.00044852031645397007, 'epoch': 2.78}

 23%|██▎       | 6507/28080 [12:51:46<42:39:37,  7.12s/it]
 23%|██▎       | 6508/28080 [12:51:53<42:38:52,  7.12s/it]
                                                          
{'loss': 0.6587, 'learning_rate': 0.0004485027884559301, 'epoch': 2.78}

 23%|██▎       | 6508/28080 [12:51:53<42:38:52,  7.12s/it]
 23%|██▎       | 6509/28080 [12:52:01<42:41:16,  7.12s/it]
                                                          
{'loss': 0.6306, 'learning_rate': 0.00044848525781701534, 'epoch': 2.78}

 23%|██▎       | 6509/28080 [12:52:01<42:41:16,  7.12s/it]
 23%|██▎       | 6510/28080 [12:52:08<42:51:13,  7.15s/it]
                                                          
{'loss': 0.6497, 'learning_rate': 0.0004484677245374589, 'epoch': 2.78}

 23%|██▎       | 6510/28080 [12:52:08<42:51:13,  7.15s/it]
 23%|██▎       | 6511/28080 [12:52:15<42:46:20,  7.14s/it]
                                                          
{'loss': 0.627, 'learning_rate': 0.0004484501886174942, 'epoch': 2.78}

 23%|██▎       | 6511/28080 [12:52:15<42:46:20,  7.14s/it]
 23%|██▎       | 6512/28080 [12:52:22<42:34:42,  7.11s/it]
                                                          
{'loss': 0.6376, 'learning_rate': 0.00044843265005735443, 'epoch': 2.78}

 23%|██▎       | 6512/28080 [12:52:22<42:34:42,  7.11s/it]
 23%|██▎       | 6513/28080 [12:52:29<42:31:48,  7.10s/it]
                                                          
{'loss': 0.6309, 'learning_rate': 0.00044841510885727304, 'epoch': 2.78}

 23%|██▎       | 6513/28080 [12:52:29<42:31:48,  7.10s/it]
 23%|██▎       | 6514/28080 [12:52:36<42:38:12,  7.12s/it]
                                                          
{'loss': 0.6642, 'learning_rate': 0.0004483975650174833, 'epoch': 2.78}

 23%|██▎       | 6514/28080 [12:52:36<42:38:12,  7.12s/it]
 23%|██▎       | 6515/28080 [12:52:43<42:47:02,  7.14s/it]
                                                          
{'loss': 0.6477, 'learning_rate': 0.0004483800185382186, 'epoch': 2.78}

 23%|██▎       | 6515/28080 [12:52:43<42:47:02,  7.14s/it]
 23%|██▎       | 6516/28080 [12:52:51<42:45:21,  7.14s/it]
                                                          
{'loss': 0.6343, 'learning_rate': 0.0004483624694197124, 'epoch': 2.78}

 23%|██▎       | 6516/28080 [12:52:51<42:45:21,  7.14s/it]
 23%|██▎       | 6517/28080 [12:52:58<42:32:59,  7.10s/it]
                                                          
{'loss': 0.624, 'learning_rate': 0.0004483449176621982, 'epoch': 2.78}

 23%|██▎       | 6517/28080 [12:52:58<42:32:59,  7.10s/it]
 23%|██▎       | 6518/28080 [12:53:05<42:36:52,  7.11s/it]
                                                          
{'loss': 0.6126, 'learning_rate': 0.0004483273632659095, 'epoch': 2.78}

 23%|██▎       | 6518/28080 [12:53:05<42:36:52,  7.11s/it]
 23%|██▎       | 6519/28080 [12:53:12<42:41:18,  7.13s/it]
                                                          
{'loss': 0.6364, 'learning_rate': 0.00044830980623107987, 'epoch': 2.78}

 23%|██▎       | 6519/28080 [12:53:12<42:41:18,  7.13s/it]
 23%|██▎       | 6520/28080 [12:53:19<42:44:18,  7.14s/it]
                                                          
{'loss': 0.6312, 'learning_rate': 0.0004482922465579428, 'epoch': 2.79}

 23%|██▎       | 6520/28080 [12:53:19<42:44:18,  7.14s/it]
 23%|██▎       | 6521/28080 [12:53:26<42:40:59,  7.13s/it]
                                                          
{'loss': 0.6447, 'learning_rate': 0.00044827468424673194, 'epoch': 2.79}

 23%|██▎       | 6521/28080 [12:53:26<42:40:59,  7.13s/it]
 23%|██▎       | 6522/28080 [12:53:33<42:45:55,  7.14s/it]
                                                          
{'loss': 0.614, 'learning_rate': 0.000448257119297681, 'epoch': 2.79}

 23%|██▎       | 6522/28080 [12:53:33<42:45:55,  7.14s/it]
 23%|██▎       | 6523/28080 [12:53:40<42:42:44,  7.13s/it]
                                                          
{'loss': 0.6304, 'learning_rate': 0.0004482395517110236, 'epoch': 2.79}

 23%|██▎       | 6523/28080 [12:53:40<42:42:44,  7.13s/it]
 23%|██▎       | 6524/28080 [12:53:48<42:59:00,  7.18s/it]
                                                          
{'loss': 0.629, 'learning_rate': 0.0004482219814869935, 'epoch': 2.79}

 23%|██▎       | 6524/28080 [12:53:48<42:59:00,  7.18s/it]
 23%|██▎       | 6525/28080 [12:53:55<42:50:36,  7.16s/it]
                                                          
{'loss': 0.6341, 'learning_rate': 0.0004482044086258244, 'epoch': 2.79}

 23%|██▎       | 6525/28080 [12:53:55<42:50:36,  7.16s/it]
 23%|██▎       | 6526/28080 [12:54:02<42:48:55,  7.15s/it]
                                                          
{'loss': 0.651, 'learning_rate': 0.0004481868331277501, 'epoch': 2.79}

 23%|██▎       | 6526/28080 [12:54:02<42:48:55,  7.15s/it]
 23%|██▎       | 6527/28080 [12:54:09<42:43:58,  7.14s/it]
                                                          
{'loss': 0.6561, 'learning_rate': 0.0004481692549930045, 'epoch': 2.79}

 23%|██▎       | 6527/28080 [12:54:09<42:43:58,  7.14s/it]
 23%|██▎       | 6528/28080 [12:54:16<42:34:55,  7.11s/it]
                                                          
{'loss': 0.6391, 'learning_rate': 0.00044815167422182137, 'epoch': 2.79}

 23%|██▎       | 6528/28080 [12:54:16<42:34:55,  7.11s/it]
 23%|██▎       | 6529/28080 [12:54:23<42:33:37,  7.11s/it]
                                                          
{'loss': 0.6612, 'learning_rate': 0.0004481340908144347, 'epoch': 2.79}

 23%|██▎       | 6529/28080 [12:54:23<42:33:37,  7.11s/it]
 23%|██▎       | 6530/28080 [12:54:30<42:35:04,  7.11s/it]
                                                          
{'loss': 0.6262, 'learning_rate': 0.0004481165047710782, 'epoch': 2.79}

 23%|██▎       | 6530/28080 [12:54:30<42:35:04,  7.11s/it]
 23%|██▎       | 6531/28080 [12:54:37<42:38:43,  7.12s/it]
                                                          
{'loss': 0.6456, 'learning_rate': 0.00044809891609198614, 'epoch': 2.79}

 23%|██▎       | 6531/28080 [12:54:37<42:38:43,  7.12s/it]
 23%|██▎       | 6532/28080 [12:54:45<42:33:28,  7.11s/it]
                                                          
{'loss': 0.6547, 'learning_rate': 0.0004480813247773923, 'epoch': 2.79}

 23%|██▎       | 6532/28080 [12:54:45<42:33:28,  7.11s/it]
 23%|██▎       | 6533/28080 [12:54:52<42:37:54,  7.12s/it]
                                                          
{'loss': 0.6281, 'learning_rate': 0.0004480637308275308, 'epoch': 2.79}

 23%|██▎       | 6533/28080 [12:54:52<42:37:54,  7.12s/it]
 23%|██▎       | 6534/28080 [12:54:59<42:36:49,  7.12s/it]
                                                          
{'loss': 0.6212, 'learning_rate': 0.00044804613424263574, 'epoch': 2.79}

 23%|██▎       | 6534/28080 [12:54:59<42:36:49,  7.12s/it]
 23%|██▎       | 6535/28080 [12:55:06<42:19:22,  7.07s/it]
                                                          
{'loss': 0.6614, 'learning_rate': 0.00044802853502294104, 'epoch': 2.79}

 23%|██▎       | 6535/28080 [12:55:06<42:19:22,  7.07s/it]
 23%|██▎       | 6536/28080 [12:55:13<42:26:24,  7.09s/it]
                                                          
{'loss': 0.6364, 'learning_rate': 0.00044801093316868115, 'epoch': 2.79}

 23%|██▎       | 6536/28080 [12:55:13<42:26:24,  7.09s/it]
 23%|██▎       | 6537/28080 [12:55:20<42:28:25,  7.10s/it]
                                                          
{'loss': 0.648, 'learning_rate': 0.0004479933286800899, 'epoch': 2.79}

 23%|██▎       | 6537/28080 [12:55:20<42:28:25,  7.10s/it]
 23%|██▎       | 6538/28080 [12:55:27<42:37:07,  7.12s/it]
                                                          
{'loss': 0.6069, 'learning_rate': 0.0004479757215574018, 'epoch': 2.79}

 23%|██▎       | 6538/28080 [12:55:27<42:37:07,  7.12s/it]
 23%|██▎       | 6539/28080 [12:55:34<42:31:17,  7.11s/it]
                                                          
{'loss': 0.6221, 'learning_rate': 0.0004479581118008509, 'epoch': 2.79}

 23%|██▎       | 6539/28080 [12:55:34<42:31:17,  7.11s/it]
 23%|██▎       | 6540/28080 [12:55:41<42:36:19,  7.12s/it]
                                                          
{'loss': 0.6101, 'learning_rate': 0.0004479404994106716, 'epoch': 2.79}

 23%|██▎       | 6540/28080 [12:55:41<42:36:19,  7.12s/it]
 23%|██▎       | 6541/28080 [12:55:48<42:30:05,  7.10s/it]
                                                          
{'loss': 0.6325, 'learning_rate': 0.0004479228843870981, 'epoch': 2.79}

 23%|██▎       | 6541/28080 [12:55:48<42:30:05,  7.10s/it]
 23%|██▎       | 6542/28080 [12:55:56<42:30:49,  7.11s/it]
                                                          
{'loss': 0.6502, 'learning_rate': 0.0004479052667303648, 'epoch': 2.79}

 23%|██▎       | 6542/28080 [12:55:56<42:30:49,  7.11s/it]
 23%|██▎       | 6543/28080 [12:56:03<42:19:09,  7.07s/it]
                                                          
{'loss': 0.6584, 'learning_rate': 0.00044788764644070614, 'epoch': 2.8}

 23%|██▎       | 6543/28080 [12:56:03<42:19:09,  7.07s/it]
 23%|██▎       | 6544/28080 [12:56:10<42:21:22,  7.08s/it]
                                                          
{'loss': 0.64, 'learning_rate': 0.0004478700235183565, 'epoch': 2.8}

 23%|██▎       | 6544/28080 [12:56:10<42:21:22,  7.08s/it]
 23%|██▎       | 6545/28080 [12:56:17<42:17:10,  7.07s/it]
                                                          
{'loss': 0.6646, 'learning_rate': 0.00044785239796355024, 'epoch': 2.8}

 23%|██▎       | 6545/28080 [12:56:17<42:17:10,  7.07s/it]
 23%|██▎       | 6546/28080 [12:56:24<42:18:09,  7.07s/it]
                                                          
{'loss': 0.6244, 'learning_rate': 0.000447834769776522, 'epoch': 2.8}

 23%|██▎       | 6546/28080 [12:56:24<42:18:09,  7.07s/it]
 23%|██▎       | 6547/28080 [12:56:31<42:16:01,  7.07s/it]
                                                          
{'loss': 0.6398, 'learning_rate': 0.0004478171389575063, 'epoch': 2.8}

 23%|██▎       | 6547/28080 [12:56:31<42:16:01,  7.07s/it]
 23%|██▎       | 6548/28080 [12:56:38<42:21:25,  7.08s/it]
                                                          
{'loss': 0.6427, 'learning_rate': 0.0004477995055067376, 'epoch': 2.8}

 23%|██▎       | 6548/28080 [12:56:38<42:21:25,  7.08s/it]
 23%|██▎       | 6549/28080 [12:56:45<42:12:26,  7.06s/it]
                                                          
{'loss': 0.6093, 'learning_rate': 0.0004477818694244505, 'epoch': 2.8}

 23%|██▎       | 6549/28080 [12:56:45<42:12:26,  7.06s/it]
 23%|██▎       | 6550/28080 [12:56:52<42:29:18,  7.10s/it]
                                                          
{'loss': 0.6547, 'learning_rate': 0.00044776423071087967, 'epoch': 2.8}

 23%|██▎       | 6550/28080 [12:56:52<42:29:18,  7.10s/it]
 23%|██▎       | 6551/28080 [12:56:59<42:22:05,  7.08s/it]
                                                          
{'loss': 0.6492, 'learning_rate': 0.00044774658936625985, 'epoch': 2.8}

 23%|██▎       | 6551/28080 [12:56:59<42:22:05,  7.08s/it]
 23%|██▎       | 6552/28080 [12:57:06<42:24:36,  7.09s/it]
                                                          
{'loss': 0.626, 'learning_rate': 0.0004477289453908256, 'epoch': 2.8}

 23%|██▎       | 6552/28080 [12:57:06<42:24:36,  7.09s/it]
 23%|██▎       | 6553/28080 [12:57:13<42:19:31,  7.08s/it]
                                                          
{'loss': 0.6561, 'learning_rate': 0.0004477112987848118, 'epoch': 2.8}

 23%|██▎       | 6553/28080 [12:57:13<42:19:31,  7.08s/it]
 23%|██▎       | 6554/28080 [12:57:20<42:04:41,  7.04s/it]
                                                          
{'loss': 0.6539, 'learning_rate': 0.00044769364954845304, 'epoch': 2.8}

 23%|██▎       | 6554/28080 [12:57:20<42:04:41,  7.04s/it]
 23%|██▎       | 6555/28080 [12:57:27<42:07:47,  7.05s/it]
                                                          
{'loss': 0.655, 'learning_rate': 0.0004476759976819842, 'epoch': 2.8}

 23%|██▎       | 6555/28080 [12:57:27<42:07:47,  7.05s/it]
 23%|██▎       | 6556/28080 [12:57:35<42:23:23,  7.09s/it]
                                                          
{'loss': 0.6363, 'learning_rate': 0.0004476583431856402, 'epoch': 2.8}

 23%|██▎       | 6556/28080 [12:57:35<42:23:23,  7.09s/it]
 23%|██▎       | 6557/28080 [12:57:42<42:39:23,  7.13s/it]
                                                          
{'loss': 0.6379, 'learning_rate': 0.0004476406860596559, 'epoch': 2.8}

 23%|██▎       | 6557/28080 [12:57:42<42:39:23,  7.13s/it]
 23%|██▎       | 6558/28080 [12:57:49<42:32:48,  7.12s/it]
                                                          
{'loss': 0.6477, 'learning_rate': 0.0004476230263042661, 'epoch': 2.8}

 23%|██▎       | 6558/28080 [12:57:49<42:32:48,  7.12s/it]
 23%|██▎       | 6559/28080 [12:57:56<42:30:42,  7.11s/it]
                                                          
{'loss': 0.6167, 'learning_rate': 0.0004476053639197058, 'epoch': 2.8}

 23%|██▎       | 6559/28080 [12:57:56<42:30:42,  7.11s/it]
 23%|██▎       | 6560/28080 [12:58:03<42:26:20,  7.10s/it]
                                                          
{'loss': 0.6397, 'learning_rate': 0.00044758769890621, 'epoch': 2.8}

 23%|██▎       | 6560/28080 [12:58:03<42:26:20,  7.10s/it]
 23%|██▎       | 6561/28080 [12:58:10<42:17:53,  7.08s/it]
                                                          
{'loss': 0.6297, 'learning_rate': 0.00044757003126401373, 'epoch': 2.8}

 23%|██▎       | 6561/28080 [12:58:10<42:17:53,  7.08s/it]
 23%|██▎       | 6562/28080 [12:58:17<42:17:43,  7.08s/it]
                                                          
{'loss': 0.6278, 'learning_rate': 0.00044755236099335195, 'epoch': 2.8}

 23%|██▎       | 6562/28080 [12:58:17<42:17:43,  7.08s/it]
 23%|██▎       | 6563/28080 [12:58:24<42:15:37,  7.07s/it]
                                                          
{'loss': 0.6454, 'learning_rate': 0.0004475346880944599, 'epoch': 2.8}

 23%|██▎       | 6563/28080 [12:58:24<42:15:37,  7.07s/it]
 23%|██▎       | 6564/28080 [12:58:31<42:21:48,  7.09s/it]
                                                          
{'loss': 0.6458, 'learning_rate': 0.0004475170125675726, 'epoch': 2.8}

 23%|██▎       | 6564/28080 [12:58:31<42:21:48,  7.09s/it]
 23%|██▎       | 6565/28080 [12:58:38<42:26:41,  7.10s/it]
                                                          
{'loss': 0.6409, 'learning_rate': 0.00044749933441292516, 'epoch': 2.8}

 23%|██▎       | 6565/28080 [12:58:39<42:26:41,  7.10s/it]
 23%|██▎       | 6566/28080 [12:58:46<42:17:53,  7.08s/it]
                                                          
{'loss': 0.6357, 'learning_rate': 0.0004474816536307529, 'epoch': 2.8}

 23%|██▎       | 6566/28080 [12:58:46<42:17:53,  7.08s/it]
 23%|██▎       | 6567/28080 [12:58:53<42:23:53,  7.09s/it]
                                                          
{'loss': 0.6168, 'learning_rate': 0.00044746397022129094, 'epoch': 2.81}

 23%|██▎       | 6567/28080 [12:58:53<42:23:53,  7.09s/it]
 23%|██▎       | 6568/28080 [12:59:00<42:27:47,  7.11s/it]
                                                          
{'loss': 0.6318, 'learning_rate': 0.0004474462841847745, 'epoch': 2.81}

 23%|██▎       | 6568/28080 [12:59:00<42:27:47,  7.11s/it]
 23%|██▎       | 6569/28080 [12:59:07<42:19:36,  7.08s/it]
                                                          
{'loss': 0.6306, 'learning_rate': 0.000447428595521439, 'epoch': 2.81}

 23%|██▎       | 6569/28080 [12:59:07<42:19:36,  7.08s/it]
 23%|██▎       | 6570/28080 [12:59:14<42:27:56,  7.11s/it]
                                                          
{'loss': 0.6503, 'learning_rate': 0.00044741090423151977, 'epoch': 2.81}

 23%|██▎       | 6570/28080 [12:59:14<42:27:56,  7.11s/it]
 23%|██▎       | 6571/28080 [12:59:21<42:24:54,  7.10s/it]
                                                          
{'loss': 0.6263, 'learning_rate': 0.00044739321031525206, 'epoch': 2.81}

 23%|██▎       | 6571/28080 [12:59:21<42:24:54,  7.10s/it]
 23%|██▎       | 6572/28080 [12:59:28<42:15:29,  7.07s/it]
                                                          
{'loss': 0.6341, 'learning_rate': 0.00044737551377287127, 'epoch': 2.81}

 23%|██▎       | 6572/28080 [12:59:28<42:15:29,  7.07s/it]
 23%|██▎       | 6573/28080 [12:59:35<42:15:41,  7.07s/it]
                                                          
{'loss': 0.6514, 'learning_rate': 0.0004473578146046129, 'epoch': 2.81}

 23%|██▎       | 6573/28080 [12:59:35<42:15:41,  7.07s/it]
 23%|██▎       | 6574/28080 [12:59:42<42:15:18,  7.07s/it]
                                                          
{'loss': 0.6503, 'learning_rate': 0.00044734011281071244, 'epoch': 2.81}

 23%|██▎       | 6574/28080 [12:59:42<42:15:18,  7.07s/it]
 23%|██▎       | 6575/28080 [12:59:49<42:12:38,  7.07s/it]
                                                          
{'loss': 0.635, 'learning_rate': 0.00044732240839140543, 'epoch': 2.81}

 23%|██▎       | 6575/28080 [12:59:49<42:12:38,  7.07s/it]
 23%|██▎       | 6576/28080 [12:59:56<42:24:46,  7.10s/it]
                                                          
{'loss': 0.6055, 'learning_rate': 0.00044730470134692724, 'epoch': 2.81}

 23%|██▎       | 6576/28080 [12:59:56<42:24:46,  7.10s/it]
 23%|██▎       | 6577/28080 [13:00:04<42:30:52,  7.12s/it]
                                                          
{'loss': 0.6496, 'learning_rate': 0.0004472869916775136, 'epoch': 2.81}

 23%|██▎       | 6577/28080 [13:00:04<42:30:52,  7.12s/it]
 23%|██▎       | 6578/28080 [13:00:11<42:23:41,  7.10s/it]
                                                          
{'loss': 0.6397, 'learning_rate': 0.0004472692793834001, 'epoch': 2.81}

 23%|██▎       | 6578/28080 [13:00:11<42:23:41,  7.10s/it]
 23%|██▎       | 6579/28080 [13:00:18<42:24:05,  7.10s/it]
                                                          
{'loss': 0.6444, 'learning_rate': 0.0004472515644648223, 'epoch': 2.81}

 23%|██▎       | 6579/28080 [13:00:18<42:24:05,  7.10s/it]
 23%|██▎       | 6580/28080 [13:00:25<42:30:54,  7.12s/it]
                                                          
{'loss': 0.6286, 'learning_rate': 0.000447233846922016, 'epoch': 2.81}

 23%|██▎       | 6580/28080 [13:00:25<42:30:54,  7.12s/it]
 23%|██▎       | 6581/28080 [13:00:32<42:23:45,  7.10s/it]
                                                          
{'loss': 0.6232, 'learning_rate': 0.00044721612675521674, 'epoch': 2.81}

 23%|██▎       | 6581/28080 [13:00:32<42:23:45,  7.10s/it]
 23%|██▎       | 6582/28080 [13:00:39<42:27:21,  7.11s/it]
                                                          
{'loss': 0.6338, 'learning_rate': 0.0004471984039646604, 'epoch': 2.81}

 23%|██▎       | 6582/28080 [13:00:39<42:27:21,  7.11s/it]
 23%|██▎       | 6583/28080 [13:00:46<42:18:40,  7.09s/it]
                                                          
{'loss': 0.6315, 'learning_rate': 0.00044718067855058273, 'epoch': 2.81}

 23%|██▎       | 6583/28080 [13:00:46<42:18:40,  7.09s/it]
 23%|██▎       | 6584/28080 [13:00:53<42:27:50,  7.11s/it]
                                                          
{'loss': 0.6202, 'learning_rate': 0.00044716295051321954, 'epoch': 2.81}

 23%|██▎       | 6584/28080 [13:00:53<42:27:50,  7.11s/it]
 23%|██▎       | 6585/28080 [13:01:00<42:21:59,  7.10s/it]
                                                          
{'loss': 0.624, 'learning_rate': 0.0004471452198528067, 'epoch': 2.81}

 23%|██▎       | 6585/28080 [13:01:00<42:21:59,  7.10s/it]
 23%|██▎       | 6586/28080 [13:01:08<42:31:24,  7.12s/it]
                                                          
{'loss': 0.6339, 'learning_rate': 0.0004471274865695801, 'epoch': 2.81}

 23%|██▎       | 6586/28080 [13:01:08<42:31:24,  7.12s/it]
 23%|██▎       | 6587/28080 [13:01:15<42:21:02,  7.09s/it]
                                                          
{'loss': 0.6434, 'learning_rate': 0.00044710975066377566, 'epoch': 2.81}

 23%|██▎       | 6587/28080 [13:01:15<42:21:02,  7.09s/it]
 23%|██▎       | 6588/28080 [13:01:22<42:20:39,  7.09s/it]
                                                          
{'loss': 0.6389, 'learning_rate': 0.00044709201213562937, 'epoch': 2.81}

 23%|██▎       | 6588/28080 [13:01:22<42:20:39,  7.09s/it]
 23%|██▎       | 6589/28080 [13:01:29<42:24:00,  7.10s/it]
                                                          
{'loss': 0.6337, 'learning_rate': 0.0004470742709853772, 'epoch': 2.81}

 23%|██▎       | 6589/28080 [13:01:29<42:24:00,  7.10s/it]
 23%|██▎       | 6590/28080 [13:01:36<42:25:45,  7.11s/it]
                                                          
{'loss': 0.6254, 'learning_rate': 0.0004470565272132551, 'epoch': 2.82}

 23%|██▎       | 6590/28080 [13:01:36<42:25:45,  7.11s/it]
 23%|██▎       | 6591/28080 [13:01:43<42:31:01,  7.12s/it]
                                                          
{'loss': 0.6395, 'learning_rate': 0.0004470387808194992, 'epoch': 2.82}

 23%|██▎       | 6591/28080 [13:01:43<42:31:01,  7.12s/it]
 23%|██▎       | 6592/28080 [13:01:50<42:26:28,  7.11s/it]
                                                          
{'loss': 0.6393, 'learning_rate': 0.0004470210318043456, 'epoch': 2.82}

 23%|██▎       | 6592/28080 [13:01:50<42:26:28,  7.11s/it]
 23%|██▎       | 6593/28080 [13:01:57<42:33:49,  7.13s/it]
                                                          
{'loss': 0.6326, 'learning_rate': 0.0004470032801680305, 'epoch': 2.82}

 23%|██▎       | 6593/28080 [13:01:57<42:33:49,  7.13s/it]
 23%|██▎       | 6594/28080 [13:02:04<42:30:58,  7.12s/it]
                                                          
{'loss': 0.6225, 'learning_rate': 0.0004469855259107899, 'epoch': 2.82}

 23%|██▎       | 6594/28080 [13:02:04<42:30:58,  7.12s/it]
 23%|██▎       | 6595/28080 [13:02:12<42:36:12,  7.14s/it]
                                                          
{'loss': 0.6334, 'learning_rate': 0.00044696776903286017, 'epoch': 2.82}

 23%|██▎       | 6595/28080 [13:02:12<42:36:12,  7.14s/it]
 23%|██▎       | 6596/28080 [13:02:19<42:38:39,  7.15s/it]
                                                          
{'loss': 0.6364, 'learning_rate': 0.0004469500095344774, 'epoch': 2.82}

 23%|██▎       | 6596/28080 [13:02:19<42:38:39,  7.15s/it]
 23%|██▎       | 6597/28080 [13:02:26<42:37:02,  7.14s/it]
                                                          
{'loss': 0.6256, 'learning_rate': 0.000446932247415878, 'epoch': 2.82}

 23%|██▎       | 6597/28080 [13:02:26<42:37:02,  7.14s/it]
 23%|██▎       | 6598/28080 [13:02:33<42:34:53,  7.14s/it]
                                                          
{'loss': 0.6369, 'learning_rate': 0.00044691448267729817, 'epoch': 2.82}

 23%|██▎       | 6598/28080 [13:02:33<42:34:53,  7.14s/it]
 24%|██▎       | 6599/28080 [13:02:40<42:32:52,  7.13s/it]
                                                          
{'loss': 0.637, 'learning_rate': 0.0004468967153189743, 'epoch': 2.82}

 24%|██▎       | 6599/28080 [13:02:40<42:32:52,  7.13s/it]
 24%|██▎       | 6600/28080 [13:02:47<42:29:14,  7.12s/it]
                                                          
{'loss': 0.6542, 'learning_rate': 0.00044687894534114277, 'epoch': 2.82}

 24%|██▎       | 6600/28080 [13:02:47<42:29:14,  7.12s/it]
 24%|██▎       | 6601/28080 [13:02:54<42:35:37,  7.14s/it]
                                                          
{'loss': 0.6456, 'learning_rate': 0.00044686117274404, 'epoch': 2.82}

 24%|██▎       | 6601/28080 [13:02:54<42:35:37,  7.14s/it]
 24%|██▎       | 6602/28080 [13:03:02<42:32:22,  7.13s/it]
                                                          
{'loss': 0.6146, 'learning_rate': 0.00044684339752790235, 'epoch': 2.82}

 24%|██▎       | 6602/28080 [13:03:02<42:32:22,  7.13s/it]
 24%|██▎       | 6603/28080 [13:03:09<42:33:21,  7.13s/it]
                                                          
{'loss': 0.6473, 'learning_rate': 0.0004468256196929664, 'epoch': 2.82}

 24%|██▎       | 6603/28080 [13:03:09<42:33:21,  7.13s/it]
 24%|██▎       | 6604/28080 [13:03:16<42:17:47,  7.09s/it]
                                                          
{'loss': 0.6238, 'learning_rate': 0.0004468078392394687, 'epoch': 2.82}

 24%|██▎       | 6604/28080 [13:03:16<42:17:47,  7.09s/it]
 24%|██▎       | 6605/28080 [13:03:23<42:27:22,  7.12s/it]
                                                          
{'loss': 0.6191, 'learning_rate': 0.0004467900561676457, 'epoch': 2.82}

 24%|██▎       | 6605/28080 [13:03:23<42:27:22,  7.12s/it]
 24%|██▎       | 6606/28080 [13:03:30<42:27:54,  7.12s/it]
                                                          
{'loss': 0.6413, 'learning_rate': 0.0004467722704777339, 'epoch': 2.82}

 24%|██▎       | 6606/28080 [13:03:30<42:27:54,  7.12s/it]
 24%|██▎       | 6607/28080 [13:03:37<42:28:56,  7.12s/it]
                                                          
{'loss': 0.6324, 'learning_rate': 0.00044675448216997024, 'epoch': 2.82}

 24%|██▎       | 6607/28080 [13:03:37<42:28:56,  7.12s/it]
 24%|██▎       | 6608/28080 [13:03:44<42:17:31,  7.09s/it]
                                                          
{'loss': 0.6533, 'learning_rate': 0.00044673669124459107, 'epoch': 2.82}

 24%|██▎       | 6608/28080 [13:03:44<42:17:31,  7.09s/it]
 24%|██▎       | 6609/28080 [13:03:51<42:13:47,  7.08s/it]
                                                          
{'loss': 0.6607, 'learning_rate': 0.00044671889770183314, 'epoch': 2.82}

 24%|██▎       | 6609/28080 [13:03:51<42:13:47,  7.08s/it]
 24%|██▎       | 6610/28080 [13:03:58<42:18:53,  7.10s/it]
                                                          
{'loss': 0.6348, 'learning_rate': 0.0004467011015419333, 'epoch': 2.82}

 24%|██▎       | 6610/28080 [13:03:58<42:18:53,  7.10s/it]
 24%|██▎       | 6611/28080 [13:04:05<42:13:48,  7.08s/it]
                                                          
{'loss': 0.6328, 'learning_rate': 0.0004466833027651282, 'epoch': 2.82}

 24%|██▎       | 6611/28080 [13:04:05<42:13:48,  7.08s/it]
 24%|██▎       | 6612/28080 [13:04:13<42:29:19,  7.12s/it]
                                                          
{'loss': 0.6197, 'learning_rate': 0.00044666550137165465, 'epoch': 2.82}

 24%|██▎       | 6612/28080 [13:04:13<42:29:19,  7.12s/it]
 24%|██▎       | 6613/28080 [13:04:20<42:27:25,  7.12s/it]
                                                          
{'loss': 0.6292, 'learning_rate': 0.0004466476973617495, 'epoch': 2.83}

 24%|██▎       | 6613/28080 [13:04:20<42:27:25,  7.12s/it]
 24%|██▎       | 6614/28080 [13:04:27<42:23:51,  7.11s/it]
                                                          
{'loss': 0.6288, 'learning_rate': 0.0004466298907356496, 'epoch': 2.83}

 24%|██▎       | 6614/28080 [13:04:27<42:23:51,  7.11s/it]
 24%|██▎       | 6615/28080 [13:04:34<42:32:47,  7.14s/it]
                                                          
{'loss': 0.6499, 'learning_rate': 0.0004466120814935919, 'epoch': 2.83}

 24%|██▎       | 6615/28080 [13:04:34<42:32:47,  7.14s/it]
 24%|██▎       | 6616/28080 [13:04:41<42:31:18,  7.13s/it]
                                                          
{'loss': 0.6484, 'learning_rate': 0.0004465942696358132, 'epoch': 2.83}

 24%|██▎       | 6616/28080 [13:04:41<42:31:18,  7.13s/it]
 24%|██▎       | 6617/28080 [13:04:48<42:36:31,  7.15s/it]
                                                          
{'loss': 0.6153, 'learning_rate': 0.0004465764551625507, 'epoch': 2.83}

 24%|██▎       | 6617/28080 [13:04:48<42:36:31,  7.15s/it]
 24%|██▎       | 6618/28080 [13:04:55<42:30:51,  7.13s/it]
                                                          
{'loss': 0.6303, 'learning_rate': 0.0004465586380740412, 'epoch': 2.83}

 24%|██▎       | 6618/28080 [13:04:55<42:30:51,  7.13s/it]
 24%|██▎       | 6619/28080 [13:05:02<42:29:20,  7.13s/it]
                                                          
{'loss': 0.652, 'learning_rate': 0.00044654081837052173, 'epoch': 2.83}

 24%|██▎       | 6619/28080 [13:05:03<42:29:20,  7.13s/it]
 24%|██▎       | 6620/28080 [13:05:10<42:28:15,  7.12s/it]
                                                          
{'loss': 0.6384, 'learning_rate': 0.00044652299605222944, 'epoch': 2.83}

 24%|██▎       | 6620/28080 [13:05:10<42:28:15,  7.12s/it]
 24%|██▎       | 6621/28080 [13:05:17<42:30:23,  7.13s/it]
                                                          
{'loss': 0.6351, 'learning_rate': 0.00044650517111940145, 'epoch': 2.83}

 24%|██▎       | 6621/28080 [13:05:17<42:30:23,  7.13s/it]
 24%|██▎       | 6622/28080 [13:05:24<42:34:51,  7.14s/it]
                                                          
{'loss': 0.6466, 'learning_rate': 0.00044648734357227493, 'epoch': 2.83}

 24%|██▎       | 6622/28080 [13:05:24<42:34:51,  7.14s/it]
 24%|██▎       | 6623/28080 [13:05:31<42:25:35,  7.12s/it]
                                                          
{'loss': 0.6595, 'learning_rate': 0.000446469513411087, 'epoch': 2.83}

 24%|██▎       | 6623/28080 [13:05:31<42:25:35,  7.12s/it]
 24%|██▎       | 6624/28080 [13:05:38<42:15:40,  7.09s/it]
                                                          
{'loss': 0.6411, 'learning_rate': 0.00044645168063607484, 'epoch': 2.83}

 24%|██▎       | 6624/28080 [13:05:38<42:15:40,  7.09s/it]
 24%|██▎       | 6625/28080 [13:05:45<42:07:17,  7.07s/it]
                                                          
{'loss': 0.6478, 'learning_rate': 0.0004464338452474758, 'epoch': 2.83}

 24%|██▎       | 6625/28080 [13:05:45<42:07:17,  7.07s/it]
 24%|██▎       | 6626/28080 [13:05:52<42:13:43,  7.09s/it]
                                                          
{'loss': 0.6167, 'learning_rate': 0.000446416007245527, 'epoch': 2.83}

 24%|██▎       | 6626/28080 [13:05:52<42:13:43,  7.09s/it]
 24%|██▎       | 6627/28080 [13:05:59<42:17:25,  7.10s/it]
                                                          
{'loss': 0.6174, 'learning_rate': 0.0004463981666304659, 'epoch': 2.83}

 24%|██▎       | 6627/28080 [13:05:59<42:17:25,  7.10s/it]
 24%|██▎       | 6628/28080 [13:06:06<42:14:57,  7.09s/it]
                                                          
{'loss': 0.6391, 'learning_rate': 0.0004463803234025298, 'epoch': 2.83}

 24%|██▎       | 6628/28080 [13:06:06<42:14:57,  7.09s/it]
 24%|██▎       | 6629/28080 [13:06:13<42:11:40,  7.08s/it]
                                                          
{'loss': 0.6177, 'learning_rate': 0.00044636247756195613, 'epoch': 2.83}

 24%|██▎       | 6629/28080 [13:06:13<42:11:40,  7.08s/it]
 24%|██▎       | 6630/28080 [13:06:21<42:16:30,  7.10s/it]
                                                          
{'loss': 0.6611, 'learning_rate': 0.0004463446291089822, 'epoch': 2.83}

 24%|██▎       | 6630/28080 [13:06:21<42:16:30,  7.10s/it]
 24%|██▎       | 6631/28080 [13:06:28<42:09:55,  7.08s/it]
                                                          
{'loss': 0.6289, 'learning_rate': 0.0004463267780438456, 'epoch': 2.83}

 24%|██▎       | 6631/28080 [13:06:28<42:09:55,  7.08s/it]
 24%|██▎       | 6632/28080 [13:06:35<42:12:17,  7.08s/it]
                                                          
{'loss': 0.6476, 'learning_rate': 0.00044630892436678377, 'epoch': 2.83}

 24%|██▎       | 6632/28080 [13:06:35<42:12:17,  7.08s/it]
 24%|██▎       | 6633/28080 [13:06:42<42:17:05,  7.10s/it]
                                                          
{'loss': 0.6496, 'learning_rate': 0.00044629106807803423, 'epoch': 2.83}

 24%|██▎       | 6633/28080 [13:06:42<42:17:05,  7.10s/it]
 24%|██▎       | 6634/28080 [13:06:49<42:15:22,  7.09s/it]
                                                          
{'loss': 0.6147, 'learning_rate': 0.0004462732091778344, 'epoch': 2.83}

 24%|██▎       | 6634/28080 [13:06:49<42:15:22,  7.09s/it]
 24%|██▎       | 6635/28080 [13:06:56<42:12:42,  7.09s/it]
                                                          
{'loss': 0.6345, 'learning_rate': 0.00044625534766642213, 'epoch': 2.83}

 24%|██▎       | 6635/28080 [13:06:56<42:12:42,  7.09s/it]
 24%|██▎       | 6636/28080 [13:07:03<42:13:44,  7.09s/it]
                                                          
{'loss': 0.6391, 'learning_rate': 0.00044623748354403494, 'epoch': 2.83}

 24%|██▎       | 6636/28080 [13:07:03<42:13:44,  7.09s/it]
 24%|██▎       | 6637/28080 [13:07:10<42:07:21,  7.07s/it]
                                                          
{'loss': 0.623, 'learning_rate': 0.0004462196168109104, 'epoch': 2.84}

 24%|██▎       | 6637/28080 [13:07:10<42:07:21,  7.07s/it]
 24%|██▎       | 6638/28080 [13:07:17<42:03:27,  7.06s/it]
                                                          
{'loss': 0.6414, 'learning_rate': 0.00044620174746728633, 'epoch': 2.84}

 24%|██▎       | 6638/28080 [13:07:17<42:03:27,  7.06s/it]
 24%|██▎       | 6639/28080 [13:07:24<42:10:00,  7.08s/it]
                                                          
{'loss': 0.6421, 'learning_rate': 0.0004461838755134004, 'epoch': 2.84}

 24%|██▎       | 6639/28080 [13:07:24<42:10:00,  7.08s/it]
 24%|██▎       | 6640/28080 [13:07:31<42:11:55,  7.09s/it]
                                                          
{'loss': 0.6256, 'learning_rate': 0.0004461660009494904, 'epoch': 2.84}

 24%|██▎       | 6640/28080 [13:07:31<42:11:55,  7.09s/it]
 24%|██▎       | 6641/28080 [13:07:38<41:51:32,  7.03s/it]
                                                          
{'loss': 0.6468, 'learning_rate': 0.00044614812377579414, 'epoch': 2.84}

 24%|██▎       | 6641/28080 [13:07:38<41:51:32,  7.03s/it]
 24%|██▎       | 6642/28080 [13:07:45<41:54:54,  7.04s/it]
                                                          
{'loss': 0.6215, 'learning_rate': 0.0004461302439925494, 'epoch': 2.84}

 24%|██▎       | 6642/28080 [13:07:45<41:54:54,  7.04s/it]
 24%|██▎       | 6643/28080 [13:07:52<41:54:26,  7.04s/it]
                                                          
{'loss': 0.6441, 'learning_rate': 0.00044611236159999417, 'epoch': 2.84}

 24%|██▎       | 6643/28080 [13:07:52<41:54:26,  7.04s/it]
 24%|██▎       | 6644/28080 [13:07:59<42:03:32,  7.06s/it]
                                                          
{'loss': 0.6453, 'learning_rate': 0.00044609447659836626, 'epoch': 2.84}

 24%|██▎       | 6644/28080 [13:07:59<42:03:32,  7.06s/it]
 24%|██▎       | 6645/28080 [13:08:07<42:11:44,  7.09s/it]
                                                          
{'loss': 0.6416, 'learning_rate': 0.00044607658898790365, 'epoch': 2.84}

 24%|██▎       | 6645/28080 [13:08:07<42:11:44,  7.09s/it]
 24%|██▎       | 6646/28080 [13:08:14<41:52:05,  7.03s/it]
                                                          
{'loss': 0.6693, 'learning_rate': 0.0004460586987688443, 'epoch': 2.84}

 24%|██▎       | 6646/28080 [13:08:14<41:52:05,  7.03s/it]
 24%|██▎       | 6647/28080 [13:08:21<42:05:00,  7.07s/it]
                                                          
{'loss': 0.6278, 'learning_rate': 0.0004460408059414262, 'epoch': 2.84}

 24%|██▎       | 6647/28080 [13:08:21<42:05:00,  7.07s/it]
 24%|██▎       | 6648/28080 [13:08:28<42:15:56,  7.10s/it]
                                                          
{'loss': 0.6225, 'learning_rate': 0.00044602291050588745, 'epoch': 2.84}

 24%|██▎       | 6648/28080 [13:08:28<42:15:56,  7.10s/it]
 24%|██▎       | 6649/28080 [13:08:35<42:24:09,  7.12s/it]
                                                          
{'loss': 0.6504, 'learning_rate': 0.00044600501246246603, 'epoch': 2.84}

 24%|██▎       | 6649/28080 [13:08:35<42:24:09,  7.12s/it]
 24%|██▎       | 6650/28080 [13:08:42<42:22:30,  7.12s/it]
                                                          
{'loss': 0.6346, 'learning_rate': 0.00044598711181140026, 'epoch': 2.84}

 24%|██▎       | 6650/28080 [13:08:42<42:22:30,  7.12s/it]
 24%|██▎       | 6651/28080 [13:08:49<42:23:23,  7.12s/it]
                                                          
{'loss': 0.6178, 'learning_rate': 0.0004459692085529281, 'epoch': 2.84}

 24%|██▎       | 6651/28080 [13:08:49<42:23:23,  7.12s/it]
 24%|██▎       | 6652/28080 [13:08:56<42:29:27,  7.14s/it]
                                                          
{'loss': 0.63, 'learning_rate': 0.00044595130268728776, 'epoch': 2.84}

 24%|██▎       | 6652/28080 [13:08:56<42:29:27,  7.14s/it]
 24%|██▎       | 6653/28080 [13:09:03<42:20:11,  7.11s/it]
                                                          
{'loss': 0.6317, 'learning_rate': 0.0004459333942147175, 'epoch': 2.84}

 24%|██▎       | 6653/28080 [13:09:03<42:20:11,  7.11s/it]
 24%|██▎       | 6654/28080 [13:09:11<42:15:37,  7.10s/it]
                                                          
{'loss': 0.6693, 'learning_rate': 0.0004459154831354556, 'epoch': 2.84}

 24%|██▎       | 6654/28080 [13:09:11<42:15:37,  7.10s/it]
 24%|██▎       | 6655/28080 [13:09:18<42:13:33,  7.10s/it]
                                                          
{'loss': 0.6546, 'learning_rate': 0.00044589756944974024, 'epoch': 2.84}

 24%|██▎       | 6655/28080 [13:09:18<42:13:33,  7.10s/it]
 24%|██▎       | 6656/28080 [13:09:25<42:18:06,  7.11s/it]
                                                          
{'loss': 0.6454, 'learning_rate': 0.0004458796531578099, 'epoch': 2.84}

 24%|██▎       | 6656/28080 [13:09:25<42:18:06,  7.11s/it]
 24%|██▎       | 6657/28080 [13:09:32<42:21:40,  7.12s/it]
                                                          
{'loss': 0.6498, 'learning_rate': 0.00044586173425990275, 'epoch': 2.84}

 24%|██▎       | 6657/28080 [13:09:32<42:21:40,  7.12s/it]
 24%|██▎       | 6658/28080 [13:09:39<42:22:56,  7.12s/it]
                                                          
{'loss': 0.6284, 'learning_rate': 0.00044584381275625734, 'epoch': 2.84}

 24%|██▎       | 6658/28080 [13:09:39<42:22:56,  7.12s/it]
 24%|██▎       | 6659/28080 [13:09:46<42:10:38,  7.09s/it]
                                                          
{'loss': 0.6484, 'learning_rate': 0.00044582588864711207, 'epoch': 2.84}

 24%|██▎       | 6659/28080 [13:09:46<42:10:38,  7.09s/it]
 24%|██▎       | 6660/28080 [13:09:53<42:11:38,  7.09s/it]
                                                          
{'loss': 0.6311, 'learning_rate': 0.00044580796193270536, 'epoch': 2.85}

 24%|██▎       | 6660/28080 [13:09:53<42:11:38,  7.09s/it]
 24%|██▎       | 6661/28080 [13:10:00<42:20:28,  7.12s/it]
                                                          
{'loss': 0.6349, 'learning_rate': 0.0004457900326132757, 'epoch': 2.85}

 24%|██▎       | 6661/28080 [13:10:00<42:20:28,  7.12s/it]
 24%|██▎       | 6662/28080 [13:10:08<42:26:14,  7.13s/it]
                                                          
{'loss': 0.6473, 'learning_rate': 0.0004457721006890616, 'epoch': 2.85}

 24%|██▎       | 6662/28080 [13:10:08<42:26:14,  7.13s/it]
 24%|██▎       | 6663/28080 [13:10:15<42:23:18,  7.13s/it]
                                                          
{'loss': 0.6506, 'learning_rate': 0.00044575416616030175, 'epoch': 2.85}

 24%|██▎       | 6663/28080 [13:10:15<42:23:18,  7.13s/it]
 24%|██▎       | 6664/28080 [13:10:22<42:05:45,  7.08s/it]
                                                          
{'loss': 0.6324, 'learning_rate': 0.00044573622902723464, 'epoch': 2.85}

 24%|██▎       | 6664/28080 [13:10:22<42:05:45,  7.08s/it]
 24%|██▎       | 6665/28080 [13:10:29<42:12:53,  7.10s/it]
                                                          
{'loss': 0.629, 'learning_rate': 0.0004457182892900989, 'epoch': 2.85}

 24%|██▎       | 6665/28080 [13:10:29<42:12:53,  7.10s/it]
 24%|██▎       | 6666/28080 [13:10:36<42:14:21,  7.10s/it]
                                                          
{'loss': 0.6284, 'learning_rate': 0.00044570034694913326, 'epoch': 2.85}

 24%|██▎       | 6666/28080 [13:10:36<42:14:21,  7.10s/it]
 24%|██▎       | 6667/28080 [13:10:43<42:16:52,  7.11s/it]
                                                          
{'loss': 0.6222, 'learning_rate': 0.0004456824020045764, 'epoch': 2.85}

 24%|██▎       | 6667/28080 [13:10:43<42:16:52,  7.11s/it]
 24%|██▎       | 6668/28080 [13:10:50<42:14:05,  7.10s/it]
                                                          
{'loss': 0.6418, 'learning_rate': 0.00044566445445666704, 'epoch': 2.85}

 24%|██▎       | 6668/28080 [13:10:50<42:14:05,  7.10s/it]
 24%|██▍       | 6669/28080 [13:10:57<42:17:06,  7.11s/it]
                                                          
{'loss': 0.6139, 'learning_rate': 0.000445646504305644, 'epoch': 2.85}

 24%|██▍       | 6669/28080 [13:10:57<42:17:06,  7.11s/it]
 24%|██▍       | 6670/28080 [13:11:04<42:18:50,  7.11s/it]
                                                          
{'loss': 0.6422, 'learning_rate': 0.00044562855155174606, 'epoch': 2.85}

 24%|██▍       | 6670/28080 [13:11:04<42:18:50,  7.11s/it]
 24%|██▍       | 6671/28080 [13:11:11<42:07:38,  7.08s/it]
                                                          
{'loss': 0.6529, 'learning_rate': 0.00044561059619521205, 'epoch': 2.85}

 24%|██▍       | 6671/28080 [13:11:11<42:07:38,  7.08s/it]
 24%|██▍       | 6672/28080 [13:11:18<42:15:38,  7.11s/it]
                                                          
{'loss': 0.6219, 'learning_rate': 0.0004455926382362808, 'epoch': 2.85}

 24%|██▍       | 6672/28080 [13:11:18<42:15:38,  7.11s/it]
 24%|██▍       | 6673/28080 [13:11:26<42:15:47,  7.11s/it]
                                                          
{'loss': 0.6396, 'learning_rate': 0.0004455746776751913, 'epoch': 2.85}

 24%|██▍       | 6673/28080 [13:11:26<42:15:47,  7.11s/it]
 24%|██▍       | 6674/28080 [13:11:33<42:14:13,  7.10s/it]
                                                          
{'loss': 0.624, 'learning_rate': 0.00044555671451218255, 'epoch': 2.85}

 24%|██▍       | 6674/28080 [13:11:33<42:14:13,  7.10s/it]
 24%|██▍       | 6675/28080 [13:11:40<42:16:51,  7.11s/it]
                                                          
{'loss': 0.6343, 'learning_rate': 0.0004455387487474934, 'epoch': 2.85}

 24%|██▍       | 6675/28080 [13:11:40<42:16:51,  7.11s/it]
 24%|██▍       | 6676/28080 [13:11:47<42:10:00,  7.09s/it]
                                                          
{'loss': 0.6491, 'learning_rate': 0.0004455207803813629, 'epoch': 2.85}

 24%|██▍       | 6676/28080 [13:11:47<42:10:00,  7.09s/it]
 24%|██▍       | 6677/28080 [13:11:54<42:16:44,  7.11s/it]
                                                          
{'loss': 0.6315, 'learning_rate': 0.00044550280941403023, 'epoch': 2.85}

 24%|██▍       | 6677/28080 [13:11:54<42:16:44,  7.11s/it]
 24%|██▍       | 6678/28080 [13:12:01<42:18:43,  7.12s/it]
                                                          
{'loss': 0.6683, 'learning_rate': 0.0004454848358457342, 'epoch': 2.85}

 24%|██▍       | 6678/28080 [13:12:01<42:18:43,  7.12s/it]
 24%|██▍       | 6679/28080 [13:12:08<41:59:54,  7.06s/it]
                                                          
{'loss': 0.6405, 'learning_rate': 0.0004454668596767143, 'epoch': 2.85}

 24%|██▍       | 6679/28080 [13:12:08<41:59:54,  7.06s/it]
 24%|██▍       | 6680/28080 [13:12:15<42:11:26,  7.10s/it]
                                                          
{'loss': 0.6368, 'learning_rate': 0.00044544888090720935, 'epoch': 2.85}

 24%|██▍       | 6680/28080 [13:12:15<42:11:26,  7.10s/it]
 24%|██▍       | 6681/28080 [13:12:22<42:12:02,  7.10s/it]
                                                          
{'loss': 0.635, 'learning_rate': 0.00044543089953745876, 'epoch': 2.85}

 24%|██▍       | 6681/28080 [13:12:22<42:12:02,  7.10s/it]
 24%|██▍       | 6682/28080 [13:12:29<42:13:31,  7.10s/it]
                                                          
{'loss': 0.6262, 'learning_rate': 0.0004454129155677016, 'epoch': 2.85}

 24%|██▍       | 6682/28080 [13:12:29<42:13:31,  7.10s/it]
 24%|██▍       | 6683/28080 [13:12:37<42:23:17,  7.13s/it]
                                                          
{'loss': 0.6248, 'learning_rate': 0.0004453949289981771, 'epoch': 2.85}

 24%|██▍       | 6683/28080 [13:12:37<42:23:17,  7.13s/it]
 24%|██▍       | 6684/28080 [13:12:44<42:14:42,  7.11s/it]
                                                          
{'loss': 0.6238, 'learning_rate': 0.00044537693982912483, 'epoch': 2.86}

 24%|██▍       | 6684/28080 [13:12:44<42:14:42,  7.11s/it]
 24%|██▍       | 6685/28080 [13:12:51<42:08:44,  7.09s/it]
                                                          
{'loss': 0.6365, 'learning_rate': 0.0004453589480607838, 'epoch': 2.86}

 24%|██▍       | 6685/28080 [13:12:51<42:08:44,  7.09s/it]
 24%|██▍       | 6686/28080 [13:12:58<42:05:13,  7.08s/it]
                                                          
{'loss': 0.6413, 'learning_rate': 0.0004453409536933936, 'epoch': 2.86}

 24%|██▍       | 6686/28080 [13:12:58<42:05:13,  7.08s/it]
 24%|██▍       | 6687/28080 [13:13:05<42:16:32,  7.11s/it]
                                                          
{'loss': 0.6638, 'learning_rate': 0.00044532295672719346, 'epoch': 2.86}

 24%|██▍       | 6687/28080 [13:13:05<42:16:32,  7.11s/it]
 24%|██▍       | 6688/28080 [13:13:12<42:17:28,  7.12s/it]
                                                          
{'loss': 0.6144, 'learning_rate': 0.000445304957162423, 'epoch': 2.86}

 24%|██▍       | 6688/28080 [13:13:12<42:17:28,  7.12s/it]
 24%|██▍       | 6689/28080 [13:13:19<42:19:06,  7.12s/it]
                                                          
{'loss': 0.6327, 'learning_rate': 0.00044528695499932146, 'epoch': 2.86}

 24%|██▍       | 6689/28080 [13:13:19<42:19:06,  7.12s/it]
 24%|██▍       | 6690/28080 [13:13:26<42:16:25,  7.11s/it]
                                                          
{'loss': 0.6573, 'learning_rate': 0.0004452689502381285, 'epoch': 2.86}

 24%|██▍       | 6690/28080 [13:13:26<42:16:25,  7.11s/it]
 24%|██▍       | 6691/28080 [13:13:33<42:13:53,  7.11s/it]
                                                          
{'loss': 0.6242, 'learning_rate': 0.0004452509428790835, 'epoch': 2.86}

 24%|██▍       | 6691/28080 [13:13:33<42:13:53,  7.11s/it]
 24%|██▍       | 6692/28080 [13:13:41<42:16:02,  7.11s/it]
                                                          
{'loss': 0.6422, 'learning_rate': 0.00044523293292242626, 'epoch': 2.86}

 24%|██▍       | 6692/28080 [13:13:41<42:16:02,  7.11s/it]
 24%|██▍       | 6693/28080 [13:13:48<42:10:43,  7.10s/it]
                                                          
{'loss': 0.641, 'learning_rate': 0.0004452149203683963, 'epoch': 2.86}

 24%|██▍       | 6693/28080 [13:13:48<42:10:43,  7.10s/it]
 24%|██▍       | 6694/28080 [13:13:55<42:15:23,  7.11s/it]
                                                          
{'loss': 0.6495, 'learning_rate': 0.0004451969052172331, 'epoch': 2.86}

 24%|██▍       | 6694/28080 [13:13:55<42:15:23,  7.11s/it]
 24%|██▍       | 6695/28080 [13:14:02<42:29:26,  7.15s/it]
                                                          
{'loss': 0.6642, 'learning_rate': 0.00044517888746917645, 'epoch': 2.86}

 24%|██▍       | 6695/28080 [13:14:02<42:29:26,  7.15s/it]
 24%|██▍       | 6696/28080 [13:14:09<42:30:20,  7.16s/it]
                                                          
{'loss': 0.6181, 'learning_rate': 0.00044516086712446614, 'epoch': 2.86}

 24%|██▍       | 6696/28080 [13:14:09<42:30:20,  7.16s/it]
 24%|██▍       | 6697/28080 [13:14:16<42:15:08,  7.11s/it]
                                                          
{'loss': 0.6534, 'learning_rate': 0.0004451428441833417, 'epoch': 2.86}

 24%|██▍       | 6697/28080 [13:14:16<42:15:08,  7.11s/it]
 24%|██▍       | 6698/28080 [13:14:23<42:10:43,  7.10s/it]
                                                          
{'loss': 0.6339, 'learning_rate': 0.00044512481864604313, 'epoch': 2.86}

 24%|██▍       | 6698/28080 [13:14:23<42:10:43,  7.10s/it]
 24%|██▍       | 6699/28080 [13:14:30<42:07:26,  7.09s/it]
                                                          
{'loss': 0.6471, 'learning_rate': 0.00044510679051281023, 'epoch': 2.86}

 24%|██▍       | 6699/28080 [13:14:30<42:07:26,  7.09s/it]
 24%|██▍       | 6700/28080 [13:14:37<42:08:34,  7.10s/it]
                                                          
{'loss': 0.6196, 'learning_rate': 0.0004450887597838826, 'epoch': 2.86}

 24%|██▍       | 6700/28080 [13:14:37<42:08:34,  7.10s/it]
 24%|██▍       | 6701/28080 [13:14:45<42:22:31,  7.14s/it]
                                                          
{'loss': 0.6586, 'learning_rate': 0.00044507072645950035, 'epoch': 2.86}

 24%|██▍       | 6701/28080 [13:14:45<42:22:31,  7.14s/it]
 24%|██▍       | 6702/28080 [13:14:52<42:21:11,  7.13s/it]
                                                          
{'loss': 0.6487, 'learning_rate': 0.00044505269053990334, 'epoch': 2.86}

 24%|██▍       | 6702/28080 [13:14:52<42:21:11,  7.13s/it]
 24%|██▍       | 6703/28080 [13:14:59<42:16:28,  7.12s/it]
                                                          
{'loss': 0.6214, 'learning_rate': 0.0004450346520253315, 'epoch': 2.86}

 24%|██▍       | 6703/28080 [13:14:59<42:16:28,  7.12s/it]
 24%|██▍       | 6704/28080 [13:15:06<42:17:34,  7.12s/it]
                                                          
{'loss': 0.642, 'learning_rate': 0.00044501661091602486, 'epoch': 2.86}

 24%|██▍       | 6704/28080 [13:15:06<42:17:34,  7.12s/it]
 24%|██▍       | 6705/28080 [13:15:13<42:18:29,  7.13s/it]
                                                          
{'loss': 0.6351, 'learning_rate': 0.0004449985672122233, 'epoch': 2.86}

 24%|██▍       | 6705/28080 [13:15:13<42:18:29,  7.13s/it]
 24%|██▍       | 6706/28080 [13:15:20<42:10:29,  7.10s/it]
                                                          
{'loss': 0.6401, 'learning_rate': 0.0004449805209141671, 'epoch': 2.86}

 24%|██▍       | 6706/28080 [13:15:20<42:10:29,  7.10s/it]
 24%|██▍       | 6707/28080 [13:15:27<42:12:09,  7.11s/it]
                                                          
{'loss': 0.6184, 'learning_rate': 0.0004449624720220961, 'epoch': 2.87}

 24%|██▍       | 6707/28080 [13:15:27<42:12:09,  7.11s/it]
 24%|██▍       | 6708/28080 [13:15:35<42:18:03,  7.13s/it]
                                                          
{'loss': 0.6314, 'learning_rate': 0.00044494442053625064, 'epoch': 2.87}

 24%|██▍       | 6708/28080 [13:15:35<42:18:03,  7.13s/it]
 24%|██▍       | 6709/28080 [13:15:42<42:19:27,  7.13s/it]
                                                          
{'loss': 0.6522, 'learning_rate': 0.00044492636645687066, 'epoch': 2.87}

 24%|██▍       | 6709/28080 [13:15:42<42:19:27,  7.13s/it]
 24%|██▍       | 6710/28080 [13:15:49<42:15:17,  7.12s/it]
                                                          
{'loss': 0.6303, 'learning_rate': 0.00044490830978419655, 'epoch': 2.87}

 24%|██▍       | 6710/28080 [13:15:49<42:15:17,  7.12s/it]
 24%|██▍       | 6711/28080 [13:15:56<42:14:21,  7.12s/it]
                                                          
{'loss': 0.6213, 'learning_rate': 0.0004448902505184684, 'epoch': 2.87}

 24%|██▍       | 6711/28080 [13:15:56<42:14:21,  7.12s/it]
 24%|██▍       | 6712/28080 [13:16:03<42:03:28,  7.09s/it]
                                                          
{'loss': 0.6368, 'learning_rate': 0.0004448721886599266, 'epoch': 2.87}

 24%|██▍       | 6712/28080 [13:16:03<42:03:28,  7.09s/it]
 24%|██▍       | 6713/28080 [13:16:10<42:03:42,  7.09s/it]
                                                          
{'loss': 0.6641, 'learning_rate': 0.0004448541242088113, 'epoch': 2.87}

 24%|██▍       | 6713/28080 [13:16:10<42:03:42,  7.09s/it]
 24%|██▍       | 6714/28080 [13:16:17<42:01:31,  7.08s/it]
                                                          
{'loss': 0.635, 'learning_rate': 0.00044483605716536293, 'epoch': 2.87}

 24%|██▍       | 6714/28080 [13:16:17<42:01:31,  7.08s/it]
 24%|██▍       | 6715/28080 [13:16:24<41:57:07,  7.07s/it]
                                                          
{'loss': 0.6242, 'learning_rate': 0.0004448179875298218, 'epoch': 2.87}

 24%|██▍       | 6715/28080 [13:16:24<41:57:07,  7.07s/it]
 24%|██▍       | 6716/28080 [13:16:31<42:09:10,  7.10s/it]
                                                          
{'loss': 0.633, 'learning_rate': 0.00044479991530242837, 'epoch': 2.87}

 24%|██▍       | 6716/28080 [13:16:31<42:09:10,  7.10s/it]
 24%|██▍       | 6717/28080 [13:16:38<42:14:28,  7.12s/it]
                                                          
{'loss': 0.6262, 'learning_rate': 0.0004447818404834231, 'epoch': 2.87}

 24%|██▍       | 6717/28080 [13:16:38<42:14:28,  7.12s/it]
 24%|██▍       | 6718/28080 [13:16:46<42:14:19,  7.12s/it]
                                                          
{'loss': 0.6524, 'learning_rate': 0.00044476376307304625, 'epoch': 2.87}

 24%|██▍       | 6718/28080 [13:16:46<42:14:19,  7.12s/it]
 24%|██▍       | 6719/28080 [13:16:53<42:10:46,  7.11s/it]
                                                          
{'loss': 0.6457, 'learning_rate': 0.0004447456830715385, 'epoch': 2.87}

 24%|██▍       | 6719/28080 [13:16:53<42:10:46,  7.11s/it]
 24%|██▍       | 6720/28080 [13:17:00<42:22:24,  7.14s/it]
                                                          
{'loss': 0.6384, 'learning_rate': 0.0004447276004791403, 'epoch': 2.87}

 24%|██▍       | 6720/28080 [13:17:00<42:22:24,  7.14s/it]
 24%|██▍       | 6721/28080 [13:17:07<42:18:10,  7.13s/it]
                                                          
{'loss': 0.6444, 'learning_rate': 0.00044470951529609236, 'epoch': 2.87}

 24%|██▍       | 6721/28080 [13:17:07<42:18:10,  7.13s/it]
 24%|██▍       | 6722/28080 [13:17:14<42:12:07,  7.11s/it]
                                                          
{'loss': 0.6493, 'learning_rate': 0.0004446914275226351, 'epoch': 2.87}

 24%|██▍       | 6722/28080 [13:17:14<42:12:07,  7.11s/it]
 24%|██▍       | 6723/28080 [13:17:21<42:02:18,  7.09s/it]
                                                          
{'loss': 0.6437, 'learning_rate': 0.0004446733371590093, 'epoch': 2.87}

 24%|██▍       | 6723/28080 [13:17:21<42:02:18,  7.09s/it]
 24%|██▍       | 6724/28080 [13:17:28<42:07:17,  7.10s/it]
                                                          
{'loss': 0.6292, 'learning_rate': 0.00044465524420545557, 'epoch': 2.87}

 24%|██▍       | 6724/28080 [13:17:28<42:07:17,  7.10s/it]
 24%|██▍       | 6725/28080 [13:17:35<42:06:21,  7.10s/it]
                                                          
{'loss': 0.6392, 'learning_rate': 0.0004446371486622146, 'epoch': 2.87}

 24%|██▍       | 6725/28080 [13:17:35<42:06:21,  7.10s/it]
 24%|██▍       | 6726/28080 [13:17:42<42:04:00,  7.09s/it]
                                                          
{'loss': 0.6655, 'learning_rate': 0.0004446190505295272, 'epoch': 2.87}

 24%|██▍       | 6726/28080 [13:17:42<42:04:00,  7.09s/it]
 24%|██▍       | 6727/28080 [13:17:49<41:58:28,  7.08s/it]
                                                          
{'loss': 0.6442, 'learning_rate': 0.00044460094980763415, 'epoch': 2.87}

 24%|██▍       | 6727/28080 [13:17:49<41:58:28,  7.08s/it]
 24%|██▍       | 6728/28080 [13:17:57<42:02:54,  7.09s/it]
                                                          
{'loss': 0.6521, 'learning_rate': 0.00044458284649677616, 'epoch': 2.87}

 24%|██▍       | 6728/28080 [13:17:57<42:02:54,  7.09s/it]
 24%|██▍       | 6729/28080 [13:18:04<42:01:41,  7.09s/it]
                                                          
{'loss': 0.6457, 'learning_rate': 0.0004445647405971942, 'epoch': 2.87}

 24%|██▍       | 6729/28080 [13:18:04<42:01:41,  7.09s/it]
 24%|██▍       | 6730/28080 [13:18:11<42:08:16,  7.11s/it]
                                                          
{'loss': 0.6295, 'learning_rate': 0.000444546632109129, 'epoch': 2.87}

 24%|██▍       | 6730/28080 [13:18:11<42:08:16,  7.11s/it]
 24%|██▍       | 6731/28080 [13:18:18<42:23:17,  7.15s/it]
                                                          
{'loss': 0.6353, 'learning_rate': 0.0004445285210328217, 'epoch': 2.88}

 24%|██▍       | 6731/28080 [13:18:18<42:23:17,  7.15s/it]
 24%|██▍       | 6732/28080 [13:18:25<42:09:23,  7.11s/it]
                                                          
{'loss': 0.642, 'learning_rate': 0.000444510407368513, 'epoch': 2.88}

 24%|██▍       | 6732/28080 [13:18:25<42:09:23,  7.11s/it]
 24%|██▍       | 6733/28080 [13:18:32<42:09:34,  7.11s/it]
                                                          
{'loss': 0.6416, 'learning_rate': 0.00044449229111644394, 'epoch': 2.88}

 24%|██▍       | 6733/28080 [13:18:32<42:09:34,  7.11s/it]
 24%|██▍       | 6734/28080 [13:18:39<42:11:29,  7.12s/it]
                                                          
{'loss': 0.6075, 'learning_rate': 0.0004444741722768557, 'epoch': 2.88}

 24%|██▍       | 6734/28080 [13:18:39<42:11:29,  7.12s/it]
 24%|██▍       | 6735/28080 [13:18:46<42:04:06,  7.10s/it]
                                                          
{'loss': 0.6542, 'learning_rate': 0.0004444560508499892, 'epoch': 2.88}

 24%|██▍       | 6735/28080 [13:18:46<42:04:06,  7.10s/it]
 24%|██▍       | 6736/28080 [13:18:53<42:00:39,  7.09s/it]
                                                          
{'loss': 0.6429, 'learning_rate': 0.00044443792683608553, 'epoch': 2.88}

 24%|██▍       | 6736/28080 [13:18:53<42:00:39,  7.09s/it]
 24%|██▍       | 6737/28080 [13:19:00<42:06:25,  7.10s/it]
                                                          
{'loss': 0.6305, 'learning_rate': 0.00044441980023538587, 'epoch': 2.88}

 24%|██▍       | 6737/28080 [13:19:00<42:06:25,  7.10s/it]
 24%|██▍       | 6738/28080 [13:19:08<42:06:57,  7.10s/it]
                                                          
{'loss': 0.6374, 'learning_rate': 0.0004444016710481313, 'epoch': 2.88}

 24%|██▍       | 6738/28080 [13:19:08<42:06:57,  7.10s/it]
 24%|██▍       | 6739/28080 [13:19:15<42:00:52,  7.09s/it]
                                                          
{'loss': 0.6306, 'learning_rate': 0.0004443835392745631, 'epoch': 2.88}

 24%|██▍       | 6739/28080 [13:19:15<42:00:52,  7.09s/it]
 24%|██▍       | 6740/28080 [13:19:22<42:04:43,  7.10s/it]
                                                          
{'loss': 0.6431, 'learning_rate': 0.0004443654049149224, 'epoch': 2.88}

 24%|██▍       | 6740/28080 [13:19:22<42:04:43,  7.10s/it]
 24%|██▍       | 6741/28080 [13:19:29<42:06:10,  7.10s/it]
                                                          
{'loss': 0.6198, 'learning_rate': 0.0004443472679694505, 'epoch': 2.88}

 24%|██▍       | 6741/28080 [13:19:29<42:06:10,  7.10s/it]
 24%|██▍       | 6742/28080 [13:19:36<41:59:07,  7.08s/it]
                                                          
{'loss': 0.6394, 'learning_rate': 0.00044432912843838876, 'epoch': 2.88}

 24%|██▍       | 6742/28080 [13:19:36<41:59:07,  7.08s/it]
 24%|██▍       | 6743/28080 [13:19:43<41:49:58,  7.06s/it]
                                                          
{'loss': 0.6588, 'learning_rate': 0.00044431098632197836, 'epoch': 2.88}

 24%|██▍       | 6743/28080 [13:19:43<41:49:58,  7.06s/it]
 24%|██▍       | 6744/28080 [13:19:50<41:56:06,  7.08s/it]
                                                          
{'loss': 0.6558, 'learning_rate': 0.0004442928416204608, 'epoch': 2.88}

 24%|██▍       | 6744/28080 [13:19:50<41:56:06,  7.08s/it]
 24%|██▍       | 6745/28080 [13:19:57<41:52:43,  7.07s/it]
                                                          
{'loss': 0.6346, 'learning_rate': 0.0004442746943340774, 'epoch': 2.88}

 24%|██▍       | 6745/28080 [13:19:57<41:52:43,  7.07s/it]
 24%|██▍       | 6746/28080 [13:20:04<41:58:20,  7.08s/it]
                                                          
{'loss': 0.6663, 'learning_rate': 0.0004442565444630696, 'epoch': 2.88}

 24%|██▍       | 6746/28080 [13:20:04<41:58:20,  7.08s/it]
 24%|██▍       | 6747/28080 [13:20:11<42:02:27,  7.09s/it]
                                                          
{'loss': 0.6287, 'learning_rate': 0.0004442383920076789, 'epoch': 2.88}

 24%|██▍       | 6747/28080 [13:20:11<42:02:27,  7.09s/it]
 24%|██▍       | 6748/28080 [13:20:18<41:57:15,  7.08s/it]
                                                          
{'loss': 0.6512, 'learning_rate': 0.0004442202369681468, 'epoch': 2.88}

 24%|██▍       | 6748/28080 [13:20:18<41:57:15,  7.08s/it]
 24%|██▍       | 6749/28080 [13:20:25<41:52:05,  7.07s/it]
                                                          
{'loss': 0.647, 'learning_rate': 0.0004442020793447148, 'epoch': 2.88}

 24%|██▍       | 6749/28080 [13:20:25<41:52:05,  7.07s/it]
 24%|██▍       | 6750/28080 [13:20:32<41:52:36,  7.07s/it]
                                                          
{'loss': 0.6382, 'learning_rate': 0.0004441839191376245, 'epoch': 2.88}

 24%|██▍       | 6750/28080 [13:20:32<41:52:36,  7.07s/it]
 24%|██▍       | 6751/28080 [13:20:40<41:55:55,  7.08s/it]
                                                          
{'loss': 0.6327, 'learning_rate': 0.0004441657563471174, 'epoch': 2.88}

 24%|██▍       | 6751/28080 [13:20:40<41:55:55,  7.08s/it]
 24%|██▍       | 6752/28080 [13:20:47<42:01:54,  7.09s/it]
                                                          
{'loss': 0.625, 'learning_rate': 0.00044414759097343527, 'epoch': 2.88}

 24%|██▍       | 6752/28080 [13:20:47<42:01:54,  7.09s/it]
 24%|██▍       | 6753/28080 [13:20:54<41:57:30,  7.08s/it]
                                                          
{'loss': 0.6457, 'learning_rate': 0.0004441294230168198, 'epoch': 2.88}

 24%|██▍       | 6753/28080 [13:20:54<41:57:30,  7.08s/it]
 24%|██▍       | 6754/28080 [13:21:01<41:53:56,  7.07s/it]
                                                          
{'loss': 0.6501, 'learning_rate': 0.00044411125247751255, 'epoch': 2.89}

 24%|██▍       | 6754/28080 [13:21:01<41:53:56,  7.07s/it]
 24%|██▍       | 6755/28080 [13:21:08<41:57:10,  7.08s/it]
                                                          
{'loss': 0.6469, 'learning_rate': 0.00044409307935575537, 'epoch': 2.89}

 24%|██▍       | 6755/28080 [13:21:08<41:57:10,  7.08s/it]
 24%|██▍       | 6756/28080 [13:21:15<42:04:21,  7.10s/it]
                                                          
{'loss': 0.6126, 'learning_rate': 0.00044407490365179, 'epoch': 2.89}

 24%|██▍       | 6756/28080 [13:21:15<42:04:21,  7.10s/it]
 24%|██▍       | 6757/28080 [13:21:22<42:01:12,  7.09s/it]
                                                          
{'loss': 0.6142, 'learning_rate': 0.0004440567253658582, 'epoch': 2.89}

 24%|██▍       | 6757/28080 [13:21:22<42:01:12,  7.09s/it]
 24%|██▍       | 6758/28080 [13:21:29<42:06:36,  7.11s/it]
                                                          
{'loss': 0.6308, 'learning_rate': 0.0004440385444982019, 'epoch': 2.89}

 24%|██▍       | 6758/28080 [13:21:29<42:06:36,  7.11s/it]
 24%|██▍       | 6759/28080 [13:21:36<42:02:10,  7.10s/it]
                                                          
{'loss': 0.6558, 'learning_rate': 0.00044402036104906304, 'epoch': 2.89}

 24%|██▍       | 6759/28080 [13:21:36<42:02:10,  7.10s/it]
 24%|██▍       | 6760/28080 [13:21:43<42:05:05,  7.11s/it]
                                                          
{'loss': 0.636, 'learning_rate': 0.00044400217501868334, 'epoch': 2.89}

 24%|██▍       | 6760/28080 [13:21:43<42:05:05,  7.11s/it]
 24%|██▍       | 6761/28080 [13:21:51<42:01:03,  7.10s/it]
                                                          
{'loss': 0.6346, 'learning_rate': 0.00044398398640730486, 'epoch': 2.89}

 24%|██▍       | 6761/28080 [13:21:51<42:01:03,  7.10s/it]
 24%|██▍       | 6762/28080 [13:21:58<41:53:32,  7.07s/it]
                                                          
{'loss': 0.6599, 'learning_rate': 0.00044396579521516953, 'epoch': 2.89}

 24%|██▍       | 6762/28080 [13:21:58<41:53:32,  7.07s/it]
 24%|██▍       | 6763/28080 [13:22:05<42:04:57,  7.11s/it]
                                                          
{'loss': 0.653, 'learning_rate': 0.00044394760144251947, 'epoch': 2.89}

 24%|██▍       | 6763/28080 [13:22:05<42:04:57,  7.11s/it]
 24%|██▍       | 6764/28080 [13:22:12<42:01:24,  7.10s/it]
                                                          
{'loss': 0.6433, 'learning_rate': 0.00044392940508959655, 'epoch': 2.89}

 24%|██▍       | 6764/28080 [13:22:12<42:01:24,  7.10s/it]
 24%|██▍       | 6765/28080 [13:22:19<42:03:33,  7.10s/it]
                                                          
{'loss': 0.6296, 'learning_rate': 0.00044391120615664304, 'epoch': 2.89}

 24%|██▍       | 6765/28080 [13:22:19<42:03:33,  7.10s/it]
 24%|██▍       | 6766/28080 [13:22:26<41:58:06,  7.09s/it]
                                                          
{'loss': 0.6319, 'learning_rate': 0.000443893004643901, 'epoch': 2.89}

 24%|██▍       | 6766/28080 [13:22:26<41:58:06,  7.09s/it]
 24%|██▍       | 6767/28080 [13:22:33<41:58:12,  7.09s/it]
                                                          
{'loss': 0.6457, 'learning_rate': 0.0004438748005516125, 'epoch': 2.89}

 24%|██▍       | 6767/28080 [13:22:33<41:58:12,  7.09s/it]
 24%|██▍       | 6768/28080 [13:22:40<41:45:57,  7.06s/it]
                                                          
{'loss': 0.6611, 'learning_rate': 0.00044385659388001983, 'epoch': 2.89}

 24%|██▍       | 6768/28080 [13:22:40<41:45:57,  7.06s/it]
 24%|██▍       | 6769/28080 [13:22:47<41:44:42,  7.05s/it]
                                                          
{'loss': 0.651, 'learning_rate': 0.0004438383846293651, 'epoch': 2.89}

 24%|██▍       | 6769/28080 [13:22:47<41:44:42,  7.05s/it]
 24%|██▍       | 6770/28080 [13:22:54<41:50:21,  7.07s/it]
                                                          
{'loss': 0.6521, 'learning_rate': 0.0004438201727998907, 'epoch': 2.89}

 24%|██▍       | 6770/28080 [13:22:54<41:50:21,  7.07s/it]
 24%|██▍       | 6771/28080 [13:23:01<41:59:59,  7.10s/it]
                                                          
{'loss': 0.6255, 'learning_rate': 0.0004438019583918389, 'epoch': 2.89}

 24%|██▍       | 6771/28080 [13:23:01<41:59:59,  7.10s/it]
 24%|██▍       | 6772/28080 [13:23:09<42:03:17,  7.11s/it]
                                                          
{'loss': 0.6447, 'learning_rate': 0.00044378374140545185, 'epoch': 2.89}

 24%|██▍       | 6772/28080 [13:23:09<42:03:17,  7.11s/it]
 24%|██▍       | 6773/28080 [13:23:16<42:12:45,  7.13s/it]
                                                          
{'loss': 0.6342, 'learning_rate': 0.00044376552184097217, 'epoch': 2.89}

 24%|██▍       | 6773/28080 [13:23:16<42:12:45,  7.13s/it]
 24%|██▍       | 6774/28080 [13:23:23<42:15:32,  7.14s/it]
                                                          
{'loss': 0.6711, 'learning_rate': 0.000443747299698642, 'epoch': 2.89}

 24%|██▍       | 6774/28080 [13:23:23<42:15:32,  7.14s/it]
 24%|██▍       | 6775/28080 [13:23:30<42:21:35,  7.16s/it]
                                                          
{'loss': 0.629, 'learning_rate': 0.000443729074978704, 'epoch': 2.89}

 24%|██▍       | 6775/28080 [13:23:30<42:21:35,  7.16s/it]
 24%|██▍       | 6776/28080 [13:23:37<42:20:03,  7.15s/it]
                                                          
{'loss': 0.6289, 'learning_rate': 0.00044371084768140043, 'epoch': 2.89}

 24%|██▍       | 6776/28080 [13:23:37<42:20:03,  7.15s/it]
 24%|██▍       | 6777/28080 [13:23:44<42:18:24,  7.15s/it]
                                                          
{'loss': 0.6247, 'learning_rate': 0.0004436926178069739, 'epoch': 2.9}

 24%|██▍       | 6777/28080 [13:23:44<42:18:24,  7.15s/it]
 24%|██▍       | 6778/28080 [13:23:51<42:06:00,  7.11s/it]
                                                          
{'loss': 0.6445, 'learning_rate': 0.0004436743853556669, 'epoch': 2.9}

 24%|██▍       | 6778/28080 [13:23:51<42:06:00,  7.11s/it]
 24%|██▍       | 6779/28080 [13:23:58<42:04:21,  7.11s/it]
                                                          
{'loss': 0.6433, 'learning_rate': 0.000443656150327722, 'epoch': 2.9}

 24%|██▍       | 6779/28080 [13:23:58<42:04:21,  7.11s/it]
 24%|██▍       | 6780/28080 [13:24:06<42:08:22,  7.12s/it]
                                                          
{'loss': 0.6362, 'learning_rate': 0.0004436379127233818, 'epoch': 2.9}

 24%|██▍       | 6780/28080 [13:24:06<42:08:22,  7.12s/it]
 24%|██▍       | 6781/28080 [13:24:13<42:04:49,  7.11s/it]
                                                          
{'loss': 0.6461, 'learning_rate': 0.00044361967254288897, 'epoch': 2.9}

 24%|██▍       | 6781/28080 [13:24:13<42:04:49,  7.11s/it]
 24%|██▍       | 6782/28080 [13:24:20<41:58:44,  7.10s/it]
                                                          
{'loss': 0.6608, 'learning_rate': 0.00044360142978648614, 'epoch': 2.9}

 24%|██▍       | 6782/28080 [13:24:20<41:58:44,  7.10s/it]
 24%|██▍       | 6783/28080 [13:24:27<41:57:28,  7.09s/it]
                                                          
{'loss': 0.6669, 'learning_rate': 0.00044358318445441604, 'epoch': 2.9}

 24%|██▍       | 6783/28080 [13:24:27<41:57:28,  7.09s/it]
 24%|██▍       | 6784/28080 [13:24:34<42:01:34,  7.10s/it]
                                                          
{'loss': 0.633, 'learning_rate': 0.0004435649365469213, 'epoch': 2.9}

 24%|██▍       | 6784/28080 [13:24:34<42:01:34,  7.10s/it]
 24%|██▍       | 6785/28080 [13:24:41<41:46:52,  7.06s/it]
                                                          
{'loss': 0.6493, 'learning_rate': 0.00044354668606424487, 'epoch': 2.9}

 24%|██▍       | 6785/28080 [13:24:41<41:46:52,  7.06s/it]
 24%|██▍       | 6786/28080 [13:24:48<41:46:47,  7.06s/it]
                                                          
{'loss': 0.6548, 'learning_rate': 0.00044352843300662936, 'epoch': 2.9}

 24%|██▍       | 6786/28080 [13:24:48<41:46:47,  7.06s/it]
 24%|██▍       | 6787/28080 [13:24:55<41:55:50,  7.09s/it]
                                                          
{'loss': 0.6575, 'learning_rate': 0.00044351017737431775, 'epoch': 2.9}

 24%|██▍       | 6787/28080 [13:24:55<41:55:50,  7.09s/it]
 24%|██▍       | 6788/28080 [13:25:02<42:00:15,  7.10s/it]
                                                          
{'loss': 0.6176, 'learning_rate': 0.00044349191916755285, 'epoch': 2.9}

 24%|██▍       | 6788/28080 [13:25:02<42:00:15,  7.10s/it]
 24%|██▍       | 6789/28080 [13:25:09<42:05:47,  7.12s/it]
                                                          
{'loss': 0.6561, 'learning_rate': 0.00044347365838657757, 'epoch': 2.9}

 24%|██▍       | 6789/28080 [13:25:09<42:05:47,  7.12s/it]
 24%|██▍       | 6790/28080 [13:25:17<41:56:44,  7.09s/it]
                                                          
{'loss': 0.6324, 'learning_rate': 0.0004434553950316349, 'epoch': 2.9}

 24%|██▍       | 6790/28080 [13:25:17<41:56:44,  7.09s/it]
 24%|██▍       | 6791/28080 [13:25:24<42:06:54,  7.12s/it]
                                                          
{'loss': 0.6298, 'learning_rate': 0.0004434371291029677, 'epoch': 2.9}

 24%|██▍       | 6791/28080 [13:25:24<42:06:54,  7.12s/it]
 24%|██▍       | 6792/28080 [13:25:31<42:03:06,  7.11s/it]
                                                          
{'loss': 0.6288, 'learning_rate': 0.0004434188606008191, 'epoch': 2.9}

 24%|██▍       | 6792/28080 [13:25:31<42:03:06,  7.11s/it]
 24%|██▍       | 6793/28080 [13:25:38<41:58:15,  7.10s/it]
                                                          
{'loss': 0.6196, 'learning_rate': 0.0004434005895254321, 'epoch': 2.9}

 24%|██▍       | 6793/28080 [13:25:38<41:58:15,  7.10s/it]
 24%|██▍       | 6794/28080 [13:25:45<41:52:58,  7.08s/it]
                                                          
{'loss': 0.6617, 'learning_rate': 0.0004433823158770498, 'epoch': 2.9}

 24%|██▍       | 6794/28080 [13:25:45<41:52:58,  7.08s/it]
 24%|██▍       | 6795/28080 [13:25:52<41:56:30,  7.09s/it]
                                                          
{'loss': 0.6212, 'learning_rate': 0.0004433640396559153, 'epoch': 2.9}

 24%|██▍       | 6795/28080 [13:25:52<41:56:30,  7.09s/it]
 24%|██▍       | 6796/28080 [13:25:59<41:59:52,  7.10s/it]
                                                          
{'loss': 0.6218, 'learning_rate': 0.0004433457608622716, 'epoch': 2.9}

 24%|██▍       | 6796/28080 [13:25:59<41:59:52,  7.10s/it]
 24%|██▍       | 6797/28080 [13:26:06<42:00:33,  7.11s/it]
                                                          
{'loss': 0.6391, 'learning_rate': 0.0004433274794963622, 'epoch': 2.9}

 24%|██▍       | 6797/28080 [13:26:06<42:00:33,  7.11s/it]
 24%|██▍       | 6798/28080 [13:26:13<42:08:09,  7.13s/it]
                                                          
{'loss': 0.6202, 'learning_rate': 0.00044330919555843004, 'epoch': 2.9}

 24%|██▍       | 6798/28080 [13:26:13<42:08:09,  7.13s/it]
 24%|██▍       | 6799/28080 [13:26:21<42:03:08,  7.11s/it]
                                                          
{'loss': 0.6287, 'learning_rate': 0.00044329090904871845, 'epoch': 2.9}

 24%|██▍       | 6799/28080 [13:26:21<42:03:08,  7.11s/it]
 24%|██▍       | 6800/28080 [13:26:28<41:59:55,  7.11s/it]
                                                          
{'loss': 0.6428, 'learning_rate': 0.0004432726199674707, 'epoch': 2.9}

 24%|██▍       | 6800/28080 [13:26:28<41:59:55,  7.11s/it]
 24%|██▍       | 6801/28080 [13:26:35<42:01:33,  7.11s/it]
                                                          
{'loss': 0.634, 'learning_rate': 0.00044325432831493017, 'epoch': 2.91}

 24%|██▍       | 6801/28080 [13:26:35<42:01:33,  7.11s/it]
 24%|██▍       | 6802/28080 [13:26:42<42:04:48,  7.12s/it]
                                                          
{'loss': 0.6475, 'learning_rate': 0.00044323603409134017, 'epoch': 2.91}

 24%|██▍       | 6802/28080 [13:26:42<42:04:48,  7.12s/it]
 24%|██▍       | 6803/28080 [13:26:49<42:01:29,  7.11s/it]
                                                          
{'loss': 0.6434, 'learning_rate': 0.00044321773729694413, 'epoch': 2.91}

 24%|██▍       | 6803/28080 [13:26:49<42:01:29,  7.11s/it]
 24%|██▍       | 6804/28080 [13:26:56<41:55:31,  7.09s/it]
                                                          
{'loss': 0.6442, 'learning_rate': 0.00044319943793198535, 'epoch': 2.91}

 24%|██▍       | 6804/28080 [13:26:56<41:55:31,  7.09s/it]
 24%|██▍       | 6805/28080 [13:27:03<41:49:38,  7.08s/it]
                                                          
{'loss': 0.6228, 'learning_rate': 0.0004431811359967074, 'epoch': 2.91}

 24%|██▍       | 6805/28080 [13:27:03<41:49:38,  7.08s/it]
 24%|██▍       | 6806/28080 [13:27:10<41:57:34,  7.10s/it]
                                                          
{'loss': 0.6084, 'learning_rate': 0.0004431628314913537, 'epoch': 2.91}

 24%|██▍       | 6806/28080 [13:27:10<41:57:34,  7.10s/it]
 24%|██▍       | 6807/28080 [13:27:17<41:46:29,  7.07s/it]
                                                          
{'loss': 0.6462, 'learning_rate': 0.00044314452441616785, 'epoch': 2.91}

 24%|██▍       | 6807/28080 [13:27:17<41:46:29,  7.07s/it]
 24%|██▍       | 6808/28080 [13:27:24<41:50:31,  7.08s/it]
                                                          
{'loss': 0.6449, 'learning_rate': 0.0004431262147713934, 'epoch': 2.91}

 24%|██▍       | 6808/28080 [13:27:24<41:50:31,  7.08s/it]
 24%|██▍       | 6809/28080 [13:27:31<41:38:31,  7.05s/it]
                                                          
{'loss': 0.66, 'learning_rate': 0.0004431079025572738, 'epoch': 2.91}

 24%|██▍       | 6809/28080 [13:27:31<41:38:31,  7.05s/it]
 24%|██▍       | 6810/28080 [13:27:38<41:42:57,  7.06s/it]
                                                          
{'loss': 0.6393, 'learning_rate': 0.00044308958777405276, 'epoch': 2.91}

 24%|██▍       | 6810/28080 [13:27:38<41:42:57,  7.06s/it]
 24%|██▍       | 6811/28080 [13:27:45<41:45:17,  7.07s/it]
                                                          
{'loss': 0.6469, 'learning_rate': 0.00044307127042197405, 'epoch': 2.91}

 24%|██▍       | 6811/28080 [13:27:45<41:45:17,  7.07s/it]
 24%|██▍       | 6812/28080 [13:27:53<41:53:22,  7.09s/it]
                                                          
{'loss': 0.647, 'learning_rate': 0.0004430529505012812, 'epoch': 2.91}

 24%|██▍       | 6812/28080 [13:27:53<41:53:22,  7.09s/it]
 24%|██▍       | 6813/28080 [13:28:00<41:49:23,  7.08s/it]
                                                          
{'loss': 0.6399, 'learning_rate': 0.00044303462801221805, 'epoch': 2.91}

 24%|██▍       | 6813/28080 [13:28:00<41:49:23,  7.08s/it]
 24%|██▍       | 6814/28080 [13:28:07<41:52:42,  7.09s/it]
                                                          
{'loss': 0.6604, 'learning_rate': 0.00044301630295502827, 'epoch': 2.91}

 24%|██▍       | 6814/28080 [13:28:07<41:52:42,  7.09s/it]
 24%|██▍       | 6815/28080 [13:28:14<41:59:28,  7.11s/it]
                                                          
{'loss': 0.6313, 'learning_rate': 0.00044299797532995573, 'epoch': 2.91}

 24%|██▍       | 6815/28080 [13:28:14<41:59:28,  7.11s/it]
 24%|██▍       | 6816/28080 [13:28:21<42:00:43,  7.11s/it]
                                                          
{'loss': 0.6353, 'learning_rate': 0.0004429796451372442, 'epoch': 2.91}

 24%|██▍       | 6816/28080 [13:28:21<42:00:43,  7.11s/it]
 24%|██▍       | 6817/28080 [13:28:28<41:59:07,  7.11s/it]
                                                          
{'loss': 0.6512, 'learning_rate': 0.0004429613123771377, 'epoch': 2.91}

 24%|██▍       | 6817/28080 [13:28:28<41:59:07,  7.11s/it]
 24%|██▍       | 6818/28080 [13:28:35<42:00:15,  7.11s/it]
                                                          
{'loss': 0.6524, 'learning_rate': 0.00044294297704987985, 'epoch': 2.91}

 24%|██▍       | 6818/28080 [13:28:35<42:00:15,  7.11s/it]
 24%|██▍       | 6819/28080 [13:28:42<42:02:28,  7.12s/it]
                                                          
{'loss': 0.6519, 'learning_rate': 0.00044292463915571477, 'epoch': 2.91}

 24%|██▍       | 6819/28080 [13:28:42<42:02:28,  7.12s/it]
 24%|██▍       | 6820/28080 [13:28:50<42:06:43,  7.13s/it]
                                                          
{'loss': 0.6378, 'learning_rate': 0.0004429062986948864, 'epoch': 2.91}

 24%|██▍       | 6820/28080 [13:28:50<42:06:43,  7.13s/it]
 24%|██▍       | 6821/28080 [13:28:57<42:03:06,  7.12s/it]
                                                          
{'loss': 0.6245, 'learning_rate': 0.0004428879556676388, 'epoch': 2.91}

 24%|██▍       | 6821/28080 [13:28:57<42:03:06,  7.12s/it]
 24%|██▍       | 6822/28080 [13:29:04<41:50:25,  7.09s/it]
                                                          
{'loss': 0.6355, 'learning_rate': 0.0004428696100742159, 'epoch': 2.91}

 24%|██▍       | 6822/28080 [13:29:04<41:50:25,  7.09s/it]
 24%|██▍       | 6823/28080 [13:29:11<41:59:36,  7.11s/it]
                                                          
{'loss': 0.5972, 'learning_rate': 0.0004428512619148618, 'epoch': 2.91}

 24%|██▍       | 6823/28080 [13:29:11<41:59:36,  7.11s/it]
 24%|██▍       | 6824/28080 [13:29:18<42:00:08,  7.11s/it]
                                                          
{'loss': 0.632, 'learning_rate': 0.0004428329111898206, 'epoch': 2.92}

 24%|██▍       | 6824/28080 [13:29:18<42:00:08,  7.11s/it]
 24%|██▍       | 6825/28080 [13:29:25<42:06:20,  7.13s/it]
                                                          
{'loss': 0.6309, 'learning_rate': 0.00044281455789933657, 'epoch': 2.92}

 24%|██▍       | 6825/28080 [13:29:25<42:06:20,  7.13s/it]
 24%|██▍       | 6826/28080 [13:29:32<42:06:28,  7.13s/it]
                                                          
{'loss': 0.6522, 'learning_rate': 0.00044279620204365364, 'epoch': 2.92}

 24%|██▍       | 6826/28080 [13:29:32<42:06:28,  7.13s/it]
 24%|██▍       | 6827/28080 [13:29:39<42:01:30,  7.12s/it]
                                                          
{'loss': 0.6267, 'learning_rate': 0.00044277784362301616, 'epoch': 2.92}

 24%|██▍       | 6827/28080 [13:29:39<42:01:30,  7.12s/it]
 24%|██▍       | 6828/28080 [13:29:46<41:49:08,  7.08s/it]
                                                          
{'loss': 0.6374, 'learning_rate': 0.00044275948263766836, 'epoch': 2.92}

 24%|██▍       | 6828/28080 [13:29:46<41:49:08,  7.08s/it]
 24%|██▍       | 6829/28080 [13:29:54<42:31:10,  7.20s/it]
                                                          
{'loss': 0.6479, 'learning_rate': 0.0004427411190878545, 'epoch': 2.92}

 24%|██▍       | 6829/28080 [13:29:54<42:31:10,  7.20s/it]
 24%|██▍       | 6830/28080 [13:30:01<42:29:36,  7.20s/it]
                                                          
{'loss': 0.6158, 'learning_rate': 0.0004427227529738189, 'epoch': 2.92}

 24%|██▍       | 6830/28080 [13:30:01<42:29:36,  7.20s/it]
 24%|██▍       | 6831/28080 [13:30:08<42:25:18,  7.19s/it]
                                                          
{'loss': 0.6263, 'learning_rate': 0.0004427043842958058, 'epoch': 2.92}

 24%|██▍       | 6831/28080 [13:30:08<42:25:18,  7.19s/it]
 24%|██▍       | 6832/28080 [13:30:15<42:15:42,  7.16s/it]
                                                          
{'loss': 0.6287, 'learning_rate': 0.00044268601305405986, 'epoch': 2.92}

 24%|██▍       | 6832/28080 [13:30:15<42:15:42,  7.16s/it]
 24%|██▍       | 6833/28080 [13:30:22<42:10:25,  7.15s/it]
                                                          
{'loss': 0.6423, 'learning_rate': 0.00044266763924882515, 'epoch': 2.92}

 24%|██▍       | 6833/28080 [13:30:22<42:10:25,  7.15s/it]
 24%|██▍       | 6834/28080 [13:30:29<42:03:45,  7.13s/it]
                                                          
{'loss': 0.6387, 'learning_rate': 0.0004426492628803463, 'epoch': 2.92}

 24%|██▍       | 6834/28080 [13:30:29<42:03:45,  7.13s/it]
 24%|██▍       | 6835/28080 [13:30:36<41:54:17,  7.10s/it]
                                                          
{'loss': 0.6403, 'learning_rate': 0.0004426308839488677, 'epoch': 2.92}

 24%|██▍       | 6835/28080 [13:30:36<41:54:17,  7.10s/it]
 24%|██▍       | 6836/28080 [13:30:44<41:54:39,  7.10s/it]
                                                          
{'loss': 0.6543, 'learning_rate': 0.00044261250245463405, 'epoch': 2.92}

 24%|██▍       | 6836/28080 [13:30:44<41:54:39,  7.10s/it]
 24%|██▍       | 6837/28080 [13:30:51<41:50:49,  7.09s/it]
                                                          
{'loss': 0.6302, 'learning_rate': 0.0004425941183978897, 'epoch': 2.92}

 24%|██▍       | 6837/28080 [13:30:51<41:50:49,  7.09s/it]
 24%|██▍       | 6838/28080 [13:30:58<41:52:36,  7.10s/it]
                                                          
{'loss': 0.6282, 'learning_rate': 0.00044257573177887926, 'epoch': 2.92}

 24%|██▍       | 6838/28080 [13:30:58<41:52:36,  7.10s/it]
 24%|██▍       | 6839/28080 [13:31:05<41:54:04,  7.10s/it]
                                                          
{'loss': 0.6224, 'learning_rate': 0.0004425573425978474, 'epoch': 2.92}

 24%|██▍       | 6839/28080 [13:31:05<41:54:04,  7.10s/it]
 24%|██▍       | 6840/28080 [13:31:12<41:56:08,  7.11s/it]
                                                          
{'loss': 0.636, 'learning_rate': 0.0004425389508550388, 'epoch': 2.92}

 24%|██▍       | 6840/28080 [13:31:12<41:56:08,  7.11s/it]
 24%|██▍       | 6841/28080 [13:31:19<42:03:03,  7.13s/it]
                                                          
{'loss': 0.6307, 'learning_rate': 0.000442520556550698, 'epoch': 2.92}

 24%|██▍       | 6841/28080 [13:31:19<42:03:03,  7.13s/it]
 24%|██▍       | 6842/28080 [13:31:26<41:51:48,  7.10s/it]
                                                          
{'loss': 0.6554, 'learning_rate': 0.0004425021596850698, 'epoch': 2.92}

 24%|██▍       | 6842/28080 [13:31:26<41:51:48,  7.10s/it]
 24%|██▍       | 6843/28080 [13:31:33<41:49:20,  7.09s/it]
                                                          
{'loss': 0.6451, 'learning_rate': 0.000442483760258399, 'epoch': 2.92}

 24%|██▍       | 6843/28080 [13:31:33<41:49:20,  7.09s/it]
 24%|██▍       | 6844/28080 [13:31:40<41:44:48,  7.08s/it]
                                                          
{'loss': 0.6472, 'learning_rate': 0.00044246535827093035, 'epoch': 2.92}

 24%|██▍       | 6844/28080 [13:31:40<41:44:48,  7.08s/it]
 24%|██▍       | 6845/28080 [13:31:47<41:47:32,  7.09s/it]
                                                          
{'loss': 0.6603, 'learning_rate': 0.0004424469537229087, 'epoch': 2.92}

 24%|██▍       | 6845/28080 [13:31:47<41:47:32,  7.09s/it]
 24%|██▍       | 6846/28080 [13:31:54<41:35:38,  7.05s/it]
                                                          
{'loss': 0.6413, 'learning_rate': 0.00044242854661457877, 'epoch': 2.92}

 24%|██▍       | 6846/28080 [13:31:54<41:35:38,  7.05s/it]
 24%|██▍       | 6847/28080 [13:32:02<41:49:09,  7.09s/it]
                                                          
{'loss': 0.6298, 'learning_rate': 0.0004424101369461856, 'epoch': 2.92}

 24%|██▍       | 6847/28080 [13:32:02<41:49:09,  7.09s/it]
 24%|██▍       | 6848/28080 [13:32:09<41:52:14,  7.10s/it]
                                                          
{'loss': 0.6413, 'learning_rate': 0.00044239172471797404, 'epoch': 2.93}

 24%|██▍       | 6848/28080 [13:32:09<41:52:14,  7.10s/it]
 24%|██▍       | 6849/28080 [13:32:16<41:50:26,  7.09s/it]
                                                          
{'loss': 0.6476, 'learning_rate': 0.00044237330993018907, 'epoch': 2.93}

 24%|██▍       | 6849/28080 [13:32:16<41:50:26,  7.09s/it]
 24%|██▍       | 6850/28080 [13:32:23<41:53:09,  7.10s/it]
                                                          
{'loss': 0.664, 'learning_rate': 0.0004423548925830757, 'epoch': 2.93}

 24%|██▍       | 6850/28080 [13:32:23<41:53:09,  7.10s/it]
 24%|██▍       | 6851/28080 [13:32:30<41:53:32,  7.10s/it]
                                                          
{'loss': 0.64, 'learning_rate': 0.0004423364726768789, 'epoch': 2.93}

 24%|██▍       | 6851/28080 [13:32:30<41:53:32,  7.10s/it]
 24%|██▍       | 6852/28080 [13:32:37<41:58:49,  7.12s/it]
                                                          
{'loss': 0.6314, 'learning_rate': 0.0004423180502118438, 'epoch': 2.93}

 24%|██▍       | 6852/28080 [13:32:37<41:58:49,  7.12s/it]
 24%|██▍       | 6853/28080 [13:32:44<42:09:31,  7.15s/it]
                                                          
{'loss': 0.6494, 'learning_rate': 0.00044229962518821544, 'epoch': 2.93}

 24%|██▍       | 6853/28080 [13:32:44<42:09:31,  7.15s/it]
 24%|██▍       | 6854/28080 [13:32:51<41:59:41,  7.12s/it]
                                                          
{'loss': 0.6416, 'learning_rate': 0.0004422811976062389, 'epoch': 2.93}

 24%|██▍       | 6854/28080 [13:32:51<41:59:41,  7.12s/it]
 24%|██▍       | 6855/28080 [13:32:59<41:53:37,  7.11s/it]
                                                          
{'loss': 0.6559, 'learning_rate': 0.00044226276746615943, 'epoch': 2.93}

 24%|██▍       | 6855/28080 [13:32:59<41:53:37,  7.11s/it]
 24%|██▍       | 6856/28080 [13:33:06<41:46:49,  7.09s/it]
                                                          
{'loss': 0.6323, 'learning_rate': 0.0004422443347682221, 'epoch': 2.93}

 24%|██▍       | 6856/28080 [13:33:06<41:46:49,  7.09s/it]
 24%|██▍       | 6857/28080 [13:33:13<41:51:30,  7.10s/it]
                                                          
{'loss': 0.6433, 'learning_rate': 0.00044222589951267233, 'epoch': 2.93}

 24%|██▍       | 6857/28080 [13:33:13<41:51:30,  7.10s/it]
 24%|██▍       | 6858/28080 [13:33:20<41:56:02,  7.11s/it]
                                                          
{'loss': 0.6589, 'learning_rate': 0.0004422074616997552, 'epoch': 2.93}

 24%|██▍       | 6858/28080 [13:33:20<41:56:02,  7.11s/it]
 24%|██▍       | 6859/28080 [13:33:27<41:55:00,  7.11s/it]
                                                          
{'loss': 0.6465, 'learning_rate': 0.00044218902132971616, 'epoch': 2.93}

 24%|██▍       | 6859/28080 [13:33:27<41:55:00,  7.11s/it]
 24%|██▍       | 6860/28080 [13:33:34<42:00:44,  7.13s/it]
                                                          
{'loss': 0.643, 'learning_rate': 0.0004421705784028004, 'epoch': 2.93}

 24%|██▍       | 6860/28080 [13:33:34<42:00:44,  7.13s/it]
 24%|██▍       | 6861/28080 [13:33:41<41:56:31,  7.12s/it]
                                                          
{'loss': 0.6673, 'learning_rate': 0.00044215213291925337, 'epoch': 2.93}

 24%|██▍       | 6861/28080 [13:33:41<41:56:31,  7.12s/it]
 24%|██▍       | 6862/28080 [13:33:48<41:51:19,  7.10s/it]
                                                          
{'loss': 0.6336, 'learning_rate': 0.00044213368487932046, 'epoch': 2.93}

 24%|██▍       | 6862/28080 [13:33:48<41:51:19,  7.10s/it]
 24%|██▍       | 6863/28080 [13:33:55<41:57:12,  7.12s/it]
                                                          
{'loss': 0.6498, 'learning_rate': 0.0004421152342832471, 'epoch': 2.93}

 24%|██▍       | 6863/28080 [13:33:55<41:57:12,  7.12s/it]
 24%|██▍       | 6864/28080 [13:34:03<41:55:50,  7.11s/it]
                                                          
{'loss': 0.6289, 'learning_rate': 0.0004420967811312786, 'epoch': 2.93}

 24%|██▍       | 6864/28080 [13:34:03<41:55:50,  7.11s/it]
 24%|██▍       | 6865/28080 [13:34:10<41:53:43,  7.11s/it]
                                                          
{'loss': 0.6487, 'learning_rate': 0.0004420783254236607, 'epoch': 2.93}

 24%|██▍       | 6865/28080 [13:34:10<41:53:43,  7.11s/it]
 24%|██▍       | 6866/28080 [13:34:17<41:42:36,  7.08s/it]
                                                          
{'loss': 0.6568, 'learning_rate': 0.0004420598671606389, 'epoch': 2.93}

 24%|██▍       | 6866/28080 [13:34:17<41:42:36,  7.08s/it]
 24%|██▍       | 6867/28080 [13:34:24<41:31:11,  7.05s/it]
                                                          
{'loss': 0.644, 'learning_rate': 0.00044204140634245866, 'epoch': 2.93}

 24%|██▍       | 6867/28080 [13:34:24<41:31:11,  7.05s/it]
 24%|██▍       | 6868/28080 [13:34:31<41:32:12,  7.05s/it]
                                                          
{'loss': 0.6459, 'learning_rate': 0.0004420229429693656, 'epoch': 2.93}

 24%|██▍       | 6868/28080 [13:34:31<41:32:12,  7.05s/it]
 24%|██▍       | 6869/28080 [13:34:38<41:23:32,  7.03s/it]
                                                          
{'loss': 0.6457, 'learning_rate': 0.0004420044770416054, 'epoch': 2.93}

 24%|██▍       | 6869/28080 [13:34:38<41:23:32,  7.03s/it]
 24%|██▍       | 6870/28080 [13:34:45<41:29:30,  7.04s/it]
                                                          
{'loss': 0.6464, 'learning_rate': 0.00044198600855942374, 'epoch': 2.93}

 24%|██▍       | 6870/28080 [13:34:45<41:29:30,  7.04s/it]
 24%|██▍       | 6871/28080 [13:34:52<41:33:04,  7.05s/it]
                                                          
{'loss': 0.6556, 'learning_rate': 0.00044196753752306624, 'epoch': 2.94}

 24%|██▍       | 6871/28080 [13:34:52<41:33:04,  7.05s/it]
 24%|██▍       | 6872/28080 [13:34:59<41:44:18,  7.09s/it]
                                                          
{'loss': 0.6548, 'learning_rate': 0.0004419490639327787, 'epoch': 2.94}

 24%|██▍       | 6872/28080 [13:34:59<41:44:18,  7.09s/it]
 24%|██▍       | 6873/28080 [13:35:06<41:32:36,  7.05s/it]
                                                          
{'loss': 0.6564, 'learning_rate': 0.0004419305877888069, 'epoch': 2.94}

 24%|██▍       | 6873/28080 [13:35:06<41:32:36,  7.05s/it]
 24%|██▍       | 6874/28080 [13:35:13<41:42:20,  7.08s/it]
                                                          
{'loss': 0.6291, 'learning_rate': 0.00044191210909139665, 'epoch': 2.94}

 24%|██▍       | 6874/28080 [13:35:13<41:42:20,  7.08s/it]
 24%|██▍       | 6875/28080 [13:35:20<41:41:27,  7.08s/it]
                                                          
{'loss': 0.6278, 'learning_rate': 0.0004418936278407938, 'epoch': 2.94}

 24%|██▍       | 6875/28080 [13:35:20<41:41:27,  7.08s/it]
 24%|██▍       | 6876/28080 [13:35:27<41:34:41,  7.06s/it]
                                                          
{'loss': 0.63, 'learning_rate': 0.00044187514403724415, 'epoch': 2.94}

 24%|██▍       | 6876/28080 [13:35:27<41:34:41,  7.06s/it]
 24%|██▍       | 6877/28080 [13:35:34<41:45:42,  7.09s/it]
                                                          
{'loss': 0.6272, 'learning_rate': 0.00044185665768099367, 'epoch': 2.94}

 24%|██▍       | 6877/28080 [13:35:34<41:45:42,  7.09s/it]
 24%|██▍       | 6878/28080 [13:35:41<41:43:47,  7.09s/it]
                                                          
{'loss': 0.6241, 'learning_rate': 0.0004418381687722882, 'epoch': 2.94}

 24%|██▍       | 6878/28080 [13:35:41<41:43:47,  7.09s/it]
 24%|██▍       | 6879/28080 [13:35:49<41:57:34,  7.12s/it]
                                                          
{'loss': 0.6418, 'learning_rate': 0.00044181967731137396, 'epoch': 2.94}

 24%|██▍       | 6879/28080 [13:35:49<41:57:34,  7.12s/it]
 25%|██▍       | 6880/28080 [13:35:56<41:58:31,  7.13s/it]
                                                          
{'loss': 0.6628, 'learning_rate': 0.00044180118329849674, 'epoch': 2.94}

 25%|██▍       | 6880/28080 [13:35:56<41:58:31,  7.13s/it]
 25%|██▍       | 6881/28080 [13:36:03<41:51:45,  7.11s/it]
                                                          
{'loss': 0.6344, 'learning_rate': 0.00044178268673390265, 'epoch': 2.94}

 25%|██▍       | 6881/28080 [13:36:03<41:51:45,  7.11s/it]
 25%|██▍       | 6882/28080 [13:36:10<41:53:52,  7.12s/it]
                                                          
{'loss': 0.6471, 'learning_rate': 0.00044176418761783775, 'epoch': 2.94}

 25%|██▍       | 6882/28080 [13:36:10<41:53:52,  7.12s/it]
 25%|██▍       | 6883/28080 [13:36:17<41:59:59,  7.13s/it]
                                                          
{'loss': 0.6472, 'learning_rate': 0.00044174568595054816, 'epoch': 2.94}

 25%|██▍       | 6883/28080 [13:36:17<41:59:59,  7.13s/it]
 25%|██▍       | 6884/28080 [13:36:24<41:51:49,  7.11s/it]
                                                          
{'loss': 0.6452, 'learning_rate': 0.00044172718173228, 'epoch': 2.94}

 25%|██▍       | 6884/28080 [13:36:24<41:51:49,  7.11s/it]
 25%|██▍       | 6885/28080 [13:36:31<41:54:58,  7.12s/it]
                                                          
{'loss': 0.6297, 'learning_rate': 0.00044170867496327957, 'epoch': 2.94}

 25%|██▍       | 6885/28080 [13:36:31<41:54:58,  7.12s/it]
 25%|██▍       | 6886/28080 [13:36:39<42:05:28,  7.15s/it]
                                                          
{'loss': 0.626, 'learning_rate': 0.00044169016564379296, 'epoch': 2.94}

 25%|██▍       | 6886/28080 [13:36:39<42:05:28,  7.15s/it]
 25%|██▍       | 6887/28080 [13:36:46<42:08:25,  7.16s/it]
                                                          
{'loss': 0.6211, 'learning_rate': 0.0004416716537740664, 'epoch': 2.94}

 25%|██▍       | 6887/28080 [13:36:46<42:08:25,  7.16s/it]
 25%|██▍       | 6888/28080 [13:36:53<42:01:50,  7.14s/it]
                                                          
{'loss': 0.6426, 'learning_rate': 0.0004416531393543463, 'epoch': 2.94}

 25%|██▍       | 6888/28080 [13:36:53<42:01:50,  7.14s/it]
 25%|██▍       | 6889/28080 [13:37:00<41:58:04,  7.13s/it]
                                                          
{'loss': 0.6613, 'learning_rate': 0.0004416346223848788, 'epoch': 2.94}

 25%|██▍       | 6889/28080 [13:37:00<41:58:04,  7.13s/it]
 25%|██▍       | 6890/28080 [13:37:07<41:40:01,  7.08s/it]
                                                          
{'loss': 0.6573, 'learning_rate': 0.00044161610286591043, 'epoch': 2.94}

 25%|██▍       | 6890/28080 [13:37:07<41:40:01,  7.08s/it]
 25%|██▍       | 6891/28080 [13:37:14<41:48:46,  7.10s/it]
                                                          
{'loss': 0.6618, 'learning_rate': 0.00044159758079768746, 'epoch': 2.94}

 25%|██▍       | 6891/28080 [13:37:14<41:48:46,  7.10s/it]
 25%|██▍       | 6892/28080 [13:37:21<41:45:33,  7.10s/it]
                                                          
{'loss': 0.6349, 'learning_rate': 0.00044157905618045633, 'epoch': 2.94}

 25%|██▍       | 6892/28080 [13:37:21<41:45:33,  7.10s/it]
 25%|██▍       | 6893/28080 [13:37:28<41:51:37,  7.11s/it]
                                                          
{'loss': 0.631, 'learning_rate': 0.00044156052901446355, 'epoch': 2.94}

 25%|██▍       | 6893/28080 [13:37:28<41:51:37,  7.11s/it]
 25%|██▍       | 6894/28080 [13:37:35<41:46:43,  7.10s/it]
                                                          
{'loss': 0.6316, 'learning_rate': 0.00044154199929995555, 'epoch': 2.95}

 25%|██▍       | 6894/28080 [13:37:35<41:46:43,  7.10s/it]
 25%|██▍       | 6895/28080 [13:37:42<41:42:08,  7.09s/it]
                                                          
{'loss': 0.6686, 'learning_rate': 0.0004415234670371787, 'epoch': 2.95}

 25%|██▍       | 6895/28080 [13:37:42<41:42:08,  7.09s/it]
 25%|██▍       | 6896/28080 [13:37:50<41:51:06,  7.11s/it]
                                                          
{'loss': 0.6192, 'learning_rate': 0.00044150493222637986, 'epoch': 2.95}

 25%|██▍       | 6896/28080 [13:37:50<41:51:06,  7.11s/it]
 25%|██▍       | 6897/28080 [13:37:57<41:48:07,  7.10s/it]
                                                          
{'loss': 0.6083, 'learning_rate': 0.00044148639486780544, 'epoch': 2.95}

 25%|██▍       | 6897/28080 [13:37:57<41:48:07,  7.10s/it]
 25%|██▍       | 6898/28080 [13:38:04<41:38:44,  7.08s/it]
                                                          
{'loss': 0.6271, 'learning_rate': 0.00044146785496170204, 'epoch': 2.95}

 25%|██▍       | 6898/28080 [13:38:04<41:38:44,  7.08s/it]
 25%|██▍       | 6899/28080 [13:38:11<41:44:01,  7.09s/it]
                                                          
{'loss': 0.6507, 'learning_rate': 0.00044144931250831643, 'epoch': 2.95}

 25%|██▍       | 6899/28080 [13:38:11<41:44:01,  7.09s/it]
 25%|██▍       | 6900/28080 [13:38:18<41:44:22,  7.09s/it]
                                                          
{'loss': 0.6265, 'learning_rate': 0.0004414307675078951, 'epoch': 2.95}

 25%|██▍       | 6900/28080 [13:38:18<41:44:22,  7.09s/it]
 25%|██▍       | 6901/28080 [13:38:25<41:57:11,  7.13s/it]
                                                          
{'loss': 0.641, 'learning_rate': 0.00044141221996068505, 'epoch': 2.95}

 25%|██▍       | 6901/28080 [13:38:25<41:57:11,  7.13s/it]
 25%|██▍       | 6902/28080 [13:38:32<41:56:43,  7.13s/it]
                                                          
{'loss': 0.62, 'learning_rate': 0.00044139366986693275, 'epoch': 2.95}

 25%|██▍       | 6902/28080 [13:38:32<41:56:43,  7.13s/it]
 25%|██▍       | 6903/28080 [13:38:39<41:54:40,  7.12s/it]
                                                          
{'loss': 0.6332, 'learning_rate': 0.0004413751172268852, 'epoch': 2.95}

 25%|██▍       | 6903/28080 [13:38:39<41:54:40,  7.12s/it]
 25%|██▍       | 6904/28080 [13:38:46<41:54:08,  7.12s/it]
                                                          
{'loss': 0.6629, 'learning_rate': 0.00044135656204078913, 'epoch': 2.95}

 25%|██▍       | 6904/28080 [13:38:46<41:54:08,  7.12s/it]
 25%|██▍       | 6905/28080 [13:38:54<41:51:37,  7.12s/it]
                                                          
{'loss': 0.6352, 'learning_rate': 0.0004413380043088914, 'epoch': 2.95}

 25%|██▍       | 6905/28080 [13:38:54<41:51:37,  7.12s/it]
 25%|██▍       | 6906/28080 [13:39:01<41:54:41,  7.13s/it]
                                                          
{'loss': 0.6497, 'learning_rate': 0.00044131944403143897, 'epoch': 2.95}

 25%|██▍       | 6906/28080 [13:39:01<41:54:41,  7.13s/it]
 25%|██▍       | 6907/28080 [13:39:08<41:55:43,  7.13s/it]
                                                          
{'loss': 0.6422, 'learning_rate': 0.0004413008812086786, 'epoch': 2.95}

 25%|██▍       | 6907/28080 [13:39:08<41:55:43,  7.13s/it]
 25%|██▍       | 6908/28080 [13:39:15<41:55:30,  7.13s/it]
                                                          
{'loss': 0.6381, 'learning_rate': 0.0004412823158408574, 'epoch': 2.95}

 25%|██▍       | 6908/28080 [13:39:15<41:55:30,  7.13s/it]
 25%|██▍       | 6909/28080 [13:39:22<41:59:28,  7.14s/it]
                                                          
{'loss': 0.6452, 'learning_rate': 0.00044126374792822245, 'epoch': 2.95}

 25%|██▍       | 6909/28080 [13:39:22<41:59:28,  7.14s/it]
 25%|██▍       | 6910/28080 [13:39:29<41:54:40,  7.13s/it]
                                                          
{'loss': 0.6275, 'learning_rate': 0.0004412451774710205, 'epoch': 2.95}

 25%|██▍       | 6910/28080 [13:39:29<41:54:40,  7.13s/it]
 25%|██▍       | 6911/28080 [13:39:36<41:57:57,  7.14s/it]
                                                          
{'loss': 0.6336, 'learning_rate': 0.0004412266044694988, 'epoch': 2.95}

 25%|██▍       | 6911/28080 [13:39:36<41:57:57,  7.14s/it]
 25%|██▍       | 6912/28080 [13:39:43<41:50:56,  7.12s/it]
                                                          
{'loss': 0.6555, 'learning_rate': 0.00044120802892390446, 'epoch': 2.95}

 25%|██▍       | 6912/28080 [13:39:43<41:50:56,  7.12s/it]
 25%|██▍       | 6913/28080 [13:39:51<41:57:58,  7.14s/it]
                                                          
{'loss': 0.6545, 'learning_rate': 0.00044118945083448447, 'epoch': 2.95}

 25%|██▍       | 6913/28080 [13:39:51<41:57:58,  7.14s/it]
 25%|██▍       | 6914/28080 [13:39:58<41:57:07,  7.14s/it]
                                                          
{'loss': 0.6575, 'learning_rate': 0.00044117087020148607, 'epoch': 2.95}

 25%|██▍       | 6914/28080 [13:39:58<41:57:07,  7.14s/it]
 25%|██▍       | 6915/28080 [13:40:05<41:46:13,  7.10s/it]
                                                          
{'loss': 0.6445, 'learning_rate': 0.0004411522870251565, 'epoch': 2.95}

 25%|██▍       | 6915/28080 [13:40:05<41:46:13,  7.10s/it]
 25%|██▍       | 6916/28080 [13:40:12<41:40:59,  7.09s/it]
                                                          
{'loss': 0.6192, 'learning_rate': 0.000441133701305743, 'epoch': 2.95}

 25%|██▍       | 6916/28080 [13:40:12<41:40:59,  7.09s/it]
 25%|██▍       | 6917/28080 [13:40:19<41:45:51,  7.10s/it]
                                                          
{'loss': 0.6324, 'learning_rate': 0.0004411151130434927, 'epoch': 2.95}

 25%|██▍       | 6917/28080 [13:40:19<41:45:51,  7.10s/it]
 25%|██▍       | 6918/28080 [13:40:26<41:46:57,  7.11s/it]
                                                          
{'loss': 0.6274, 'learning_rate': 0.000441096522238653, 'epoch': 2.96}

 25%|██▍       | 6918/28080 [13:40:26<41:46:57,  7.11s/it]
 25%|██▍       | 6919/28080 [13:40:33<41:37:07,  7.08s/it]
                                                          
{'loss': 0.6465, 'learning_rate': 0.00044107792889147123, 'epoch': 2.96}

 25%|██▍       | 6919/28080 [13:40:33<41:37:07,  7.08s/it]
 25%|██▍       | 6920/28080 [13:40:40<41:56:31,  7.14s/it]
                                                          
{'loss': 0.6426, 'learning_rate': 0.0004410593330021948, 'epoch': 2.96}

 25%|██▍       | 6920/28080 [13:40:40<41:56:31,  7.14s/it]
 25%|██▍       | 6921/28080 [13:40:48<41:52:30,  7.12s/it]
                                                          
{'loss': 0.639, 'learning_rate': 0.000441040734571071, 'epoch': 2.96}

 25%|██▍       | 6921/28080 [13:40:48<41:52:30,  7.12s/it]
 25%|██▍       | 6922/28080 [13:40:55<41:51:59,  7.12s/it]
                                                          
{'loss': 0.6569, 'learning_rate': 0.0004410221335983473, 'epoch': 2.96}

 25%|██▍       | 6922/28080 [13:40:55<41:51:59,  7.12s/it]
 25%|██▍       | 6923/28080 [13:41:02<41:38:07,  7.08s/it]
                                                          
{'loss': 0.6486, 'learning_rate': 0.00044100353008427116, 'epoch': 2.96}

 25%|██▍       | 6923/28080 [13:41:02<41:38:07,  7.08s/it]
 25%|██▍       | 6924/28080 [13:41:09<41:39:57,  7.09s/it]
                                                          
{'loss': 0.6347, 'learning_rate': 0.0004409849240290902, 'epoch': 2.96}

 25%|██▍       | 6924/28080 [13:41:09<41:39:57,  7.09s/it]
 25%|██▍       | 6925/28080 [13:41:16<41:36:31,  7.08s/it]
                                                          
{'loss': 0.6324, 'learning_rate': 0.00044096631543305174, 'epoch': 2.96}

 25%|██▍       | 6925/28080 [13:41:16<41:36:31,  7.08s/it]
 25%|██▍       | 6926/28080 [13:41:23<41:45:18,  7.11s/it]
                                                          
{'loss': 0.6432, 'learning_rate': 0.0004409477042964035, 'epoch': 2.96}

 25%|██▍       | 6926/28080 [13:41:23<41:45:18,  7.11s/it]
 25%|██▍       | 6927/28080 [13:41:30<41:45:55,  7.11s/it]
                                                          
{'loss': 0.6291, 'learning_rate': 0.00044092909061939307, 'epoch': 2.96}

 25%|██▍       | 6927/28080 [13:41:30<41:45:55,  7.11s/it]
 25%|██▍       | 6928/28080 [13:41:37<41:44:36,  7.10s/it]
                                                          
{'loss': 0.662, 'learning_rate': 0.00044091047440226804, 'epoch': 2.96}

 25%|██▍       | 6928/28080 [13:41:37<41:44:36,  7.10s/it]
 25%|██▍       | 6929/28080 [13:41:44<41:36:36,  7.08s/it]
                                                          
{'loss': 0.6526, 'learning_rate': 0.0004408918556452761, 'epoch': 2.96}

 25%|██▍       | 6929/28080 [13:41:44<41:36:36,  7.08s/it]
 25%|██▍       | 6930/28080 [13:41:51<41:42:46,  7.10s/it]
                                                          
{'loss': 0.6316, 'learning_rate': 0.000440873234348665, 'epoch': 2.96}

 25%|██▍       | 6930/28080 [13:41:51<41:42:46,  7.10s/it]
 25%|██▍       | 6931/28080 [13:41:58<41:36:18,  7.08s/it]
                                                          
{'loss': 0.6544, 'learning_rate': 0.0004408546105126823, 'epoch': 2.96}

 25%|██▍       | 6931/28080 [13:41:58<41:36:18,  7.08s/it]
 25%|██▍       | 6932/28080 [13:42:05<41:39:36,  7.09s/it]
                                                          
{'loss': 0.6271, 'learning_rate': 0.00044083598413757595, 'epoch': 2.96}

 25%|██▍       | 6932/28080 [13:42:05<41:39:36,  7.09s/it]
 25%|██▍       | 6933/28080 [13:42:13<41:34:18,  7.08s/it]
                                                          
{'loss': 0.6556, 'learning_rate': 0.0004408173552235938, 'epoch': 2.96}

 25%|██▍       | 6933/28080 [13:42:13<41:34:18,  7.08s/it]
 25%|██▍       | 6934/28080 [13:42:20<41:38:09,  7.09s/it]
                                                          
{'loss': 0.6537, 'learning_rate': 0.0004407987237709835, 'epoch': 2.96}

 25%|██▍       | 6934/28080 [13:42:20<41:38:09,  7.09s/it]
 25%|██▍       | 6935/28080 [13:42:27<41:39:10,  7.09s/it]
                                                          
{'loss': 0.6311, 'learning_rate': 0.00044078008977999306, 'epoch': 2.96}

 25%|██▍       | 6935/28080 [13:42:27<41:39:10,  7.09s/it]
 25%|██▍       | 6936/28080 [13:42:34<41:34:33,  7.08s/it]
                                                          
{'loss': 0.645, 'learning_rate': 0.00044076145325087034, 'epoch': 2.96}

 25%|██▍       | 6936/28080 [13:42:34<41:34:33,  7.08s/it]
 25%|██▍       | 6937/28080 [13:42:41<41:38:09,  7.09s/it]
                                                          
{'loss': 0.6229, 'learning_rate': 0.00044074281418386333, 'epoch': 2.96}

 25%|██▍       | 6937/28080 [13:42:41<41:38:09,  7.09s/it]
 25%|██▍       | 6938/28080 [13:42:48<41:30:36,  7.07s/it]
                                                          
{'loss': 0.6316, 'learning_rate': 0.0004407241725792198, 'epoch': 2.96}

 25%|██▍       | 6938/28080 [13:42:48<41:30:36,  7.07s/it]
 25%|██▍       | 6939/28080 [13:42:55<41:26:38,  7.06s/it]
                                                          
{'loss': 0.6283, 'learning_rate': 0.00044070552843718805, 'epoch': 2.96}

 25%|██▍       | 6939/28080 [13:42:55<41:26:38,  7.06s/it]
 25%|██▍       | 6940/28080 [13:43:02<41:30:46,  7.07s/it]
                                                          
{'loss': 0.6284, 'learning_rate': 0.00044068688175801597, 'epoch': 2.96}

 25%|██▍       | 6940/28080 [13:43:02<41:30:46,  7.07s/it]
 25%|██▍       | 6941/28080 [13:43:09<41:25:40,  7.06s/it]
                                                          
{'loss': 0.6372, 'learning_rate': 0.00044066823254195164, 'epoch': 2.97}

 25%|██▍       | 6941/28080 [13:43:09<41:25:40,  7.06s/it]
 25%|██▍       | 6942/28080 [13:43:16<41:48:18,  7.12s/it]
                                                          
{'loss': 0.6317, 'learning_rate': 0.00044064958078924313, 'epoch': 2.97}

 25%|██▍       | 6942/28080 [13:43:16<41:48:18,  7.12s/it]
 25%|██▍       | 6943/28080 [13:43:23<41:49:20,  7.12s/it]
                                                          
{'loss': 0.6197, 'learning_rate': 0.0004406309265001387, 'epoch': 2.97}

 25%|██▍       | 6943/28080 [13:43:23<41:49:20,  7.12s/it]
 25%|██▍       | 6944/28080 [13:43:31<41:45:15,  7.11s/it]
                                                          
{'loss': 0.6251, 'learning_rate': 0.0004406122696748864, 'epoch': 2.97}

 25%|██▍       | 6944/28080 [13:43:31<41:45:15,  7.11s/it]
 25%|██▍       | 6945/28080 [13:43:38<41:50:32,  7.13s/it]
                                                          
{'loss': 0.6364, 'learning_rate': 0.0004405936103137345, 'epoch': 2.97}

 25%|██▍       | 6945/28080 [13:43:38<41:50:32,  7.13s/it]
 25%|██▍       | 6946/28080 [13:43:45<41:48:57,  7.12s/it]
                                                          
{'loss': 0.6392, 'learning_rate': 0.00044057494841693125, 'epoch': 2.97}

 25%|██▍       | 6946/28080 [13:43:45<41:48:57,  7.12s/it]
 25%|██▍       | 6947/28080 [13:43:52<41:45:30,  7.11s/it]
                                                          
{'loss': 0.627, 'learning_rate': 0.00044055628398472494, 'epoch': 2.97}

 25%|██▍       | 6947/28080 [13:43:52<41:45:30,  7.11s/it]
 25%|██▍       | 6948/28080 [13:43:59<41:21:31,  7.05s/it]
                                                          
{'loss': 0.6782, 'learning_rate': 0.0004405376170173638, 'epoch': 2.97}

 25%|██▍       | 6948/28080 [13:43:59<41:21:31,  7.05s/it]
 25%|██▍       | 6949/28080 [13:44:06<41:26:49,  7.06s/it]
                                                          
{'loss': 0.6418, 'learning_rate': 0.00044051894751509626, 'epoch': 2.97}

 25%|██▍       | 6949/28080 [13:44:06<41:26:49,  7.06s/it]
 25%|██▍       | 6950/28080 [13:44:13<41:18:44,  7.04s/it]
                                                          
{'loss': 0.6399, 'learning_rate': 0.0004405002754781707, 'epoch': 2.97}

 25%|██▍       | 6950/28080 [13:44:13<41:18:44,  7.04s/it]
 25%|██▍       | 6951/28080 [13:44:20<41:26:51,  7.06s/it]
                                                          
{'loss': 0.6357, 'learning_rate': 0.00044048160090683547, 'epoch': 2.97}

 25%|██▍       | 6951/28080 [13:44:20<41:26:51,  7.06s/it]
 25%|██▍       | 6952/28080 [13:44:27<41:30:42,  7.07s/it]
                                                          
{'loss': 0.6629, 'learning_rate': 0.00044046292380133905, 'epoch': 2.97}

 25%|██▍       | 6952/28080 [13:44:27<41:30:42,  7.07s/it]
 25%|██▍       | 6953/28080 [13:44:34<41:22:46,  7.05s/it]
                                                          
{'loss': 0.6273, 'learning_rate': 0.00044044424416192995, 'epoch': 2.97}

 25%|██▍       | 6953/28080 [13:44:34<41:22:46,  7.05s/it]
 25%|██▍       | 6954/28080 [13:44:41<41:20:39,  7.05s/it]
                                                          
{'loss': 0.6447, 'learning_rate': 0.00044042556198885664, 'epoch': 2.97}

 25%|██▍       | 6954/28080 [13:44:41<41:20:39,  7.05s/it]
 25%|██▍       | 6955/28080 [13:44:48<41:31:37,  7.08s/it]
                                                          
{'loss': 0.626, 'learning_rate': 0.0004404068772823677, 'epoch': 2.97}

 25%|██▍       | 6955/28080 [13:44:48<41:31:37,  7.08s/it]
 25%|██▍       | 6956/28080 [13:44:55<41:34:26,  7.09s/it]
                                                          
{'loss': 0.6405, 'learning_rate': 0.00044038819004271166, 'epoch': 2.97}

 25%|██▍       | 6956/28080 [13:44:55<41:34:26,  7.09s/it]
 25%|██▍       | 6957/28080 [13:45:03<41:34:36,  7.09s/it]
                                                          
{'loss': 0.6166, 'learning_rate': 0.00044036950027013714, 'epoch': 2.97}

 25%|██▍       | 6957/28080 [13:45:03<41:34:36,  7.09s/it]
 25%|██▍       | 6958/28080 [13:45:10<41:37:43,  7.10s/it]
                                                          
{'loss': 0.656, 'learning_rate': 0.0004403508079648928, 'epoch': 2.97}

 25%|██▍       | 6958/28080 [13:45:10<41:37:43,  7.10s/it]
 25%|██▍       | 6959/28080 [13:45:17<41:32:56,  7.08s/it]
                                                          
{'loss': 0.6331, 'learning_rate': 0.0004403321131272274, 'epoch': 2.97}

 25%|██▍       | 6959/28080 [13:45:17<41:32:56,  7.08s/it]
 25%|██▍       | 6960/28080 [13:45:24<41:42:29,  7.11s/it]
                                                          
{'loss': 0.6417, 'learning_rate': 0.00044031341575738957, 'epoch': 2.97}

 25%|██▍       | 6960/28080 [13:45:24<41:42:29,  7.11s/it]
 25%|██▍       | 6961/28080 [13:45:31<41:41:20,  7.11s/it]
                                                          
{'loss': 0.6264, 'learning_rate': 0.00044029471585562807, 'epoch': 2.97}

 25%|██▍       | 6961/28080 [13:45:31<41:41:20,  7.11s/it]
 25%|██▍       | 6962/28080 [13:45:38<41:41:29,  7.11s/it]
                                                          
{'loss': 0.6459, 'learning_rate': 0.0004402760134221917, 'epoch': 2.97}

 25%|██▍       | 6962/28080 [13:45:38<41:41:29,  7.11s/it]
 25%|██▍       | 6963/28080 [13:45:45<41:31:14,  7.08s/it]
                                                          
{'loss': 0.6587, 'learning_rate': 0.00044025730845732923, 'epoch': 2.97}

 25%|██▍       | 6963/28080 [13:45:45<41:31:14,  7.08s/it]
 25%|██▍       | 6964/28080 [13:45:52<41:24:27,  7.06s/it]
                                                          
{'loss': 0.6628, 'learning_rate': 0.0004402386009612896, 'epoch': 2.97}

 25%|██▍       | 6964/28080 [13:45:52<41:24:27,  7.06s/it]
 25%|██▍       | 6965/28080 [13:45:59<41:21:46,  7.05s/it]
                                                          
{'loss': 0.6415, 'learning_rate': 0.0004402198909343216, 'epoch': 2.98}

 25%|██▍       | 6965/28080 [13:45:59<41:21:46,  7.05s/it]
 25%|██▍       | 6966/28080 [13:46:06<41:24:37,  7.06s/it]
                                                          
{'loss': 0.6359, 'learning_rate': 0.00044020117837667425, 'epoch': 2.98}

 25%|██▍       | 6966/28080 [13:46:06<41:24:37,  7.06s/it]
 25%|██▍       | 6967/28080 [13:46:13<41:27:58,  7.07s/it]
                                                          
{'loss': 0.6468, 'learning_rate': 0.00044018246328859635, 'epoch': 2.98}

 25%|██▍       | 6967/28080 [13:46:13<41:27:58,  7.07s/it]
 25%|██▍       | 6968/28080 [13:46:20<41:32:33,  7.08s/it]
                                                          
{'loss': 0.6308, 'learning_rate': 0.00044016374567033703, 'epoch': 2.98}

 25%|██▍       | 6968/28080 [13:46:20<41:32:33,  7.08s/it]
 25%|██▍       | 6969/28080 [13:46:28<41:38:20,  7.10s/it]
                                                          
{'loss': 0.6309, 'learning_rate': 0.0004401450255221453, 'epoch': 2.98}

 25%|██▍       | 6969/28080 [13:46:28<41:38:20,  7.10s/it]
 25%|██▍       | 6970/28080 [13:46:35<41:39:27,  7.10s/it]
                                                          
{'loss': 0.6335, 'learning_rate': 0.00044012630284427005, 'epoch': 2.98}

 25%|██▍       | 6970/28080 [13:46:35<41:39:27,  7.10s/it]
 25%|██▍       | 6971/28080 [13:46:42<41:38:51,  7.10s/it]
                                                          
{'loss': 0.6551, 'learning_rate': 0.00044010757763696064, 'epoch': 2.98}

 25%|██▍       | 6971/28080 [13:46:42<41:38:51,  7.10s/it]
 25%|██▍       | 6972/28080 [13:46:49<41:43:32,  7.12s/it]
                                                          
{'loss': 0.6265, 'learning_rate': 0.0004400888499004659, 'epoch': 2.98}

 25%|██▍       | 6972/28080 [13:46:49<41:43:32,  7.12s/it]
 25%|██▍       | 6973/28080 [13:46:56<41:46:28,  7.13s/it]
                                                          
{'loss': 0.6429, 'learning_rate': 0.0004400701196350352, 'epoch': 2.98}

 25%|██▍       | 6973/28080 [13:46:56<41:46:28,  7.13s/it]
 25%|██▍       | 6974/28080 [13:47:03<41:45:55,  7.12s/it]
                                                          
{'loss': 0.6274, 'learning_rate': 0.00044005138684091754, 'epoch': 2.98}

 25%|██▍       | 6974/28080 [13:47:03<41:45:55,  7.12s/it]
 25%|██▍       | 6975/28080 [13:47:10<41:40:01,  7.11s/it]
                                                          
{'loss': 0.6146, 'learning_rate': 0.00044003265151836235, 'epoch': 2.98}

 25%|██▍       | 6975/28080 [13:47:10<41:40:01,  7.11s/it]
 25%|██▍       | 6976/28080 [13:47:17<41:33:33,  7.09s/it]
                                                          
{'loss': 0.6272, 'learning_rate': 0.00044001391366761867, 'epoch': 2.98}

 25%|██▍       | 6976/28080 [13:47:17<41:33:33,  7.09s/it]
 25%|██▍       | 6977/28080 [13:47:24<41:45:41,  7.12s/it]
                                                          
{'loss': 0.638, 'learning_rate': 0.00043999517328893603, 'epoch': 2.98}

 25%|██▍       | 6977/28080 [13:47:24<41:45:41,  7.12s/it]
 25%|██▍       | 6978/28080 [13:47:32<41:42:19,  7.11s/it]
                                                          
{'loss': 0.6264, 'learning_rate': 0.00043997643038256354, 'epoch': 2.98}

 25%|██▍       | 6978/28080 [13:47:32<41:42:19,  7.11s/it]
 25%|██▍       | 6979/28080 [13:47:39<41:32:47,  7.09s/it]
                                                          
{'loss': 0.6278, 'learning_rate': 0.00043995768494875065, 'epoch': 2.98}

 25%|██▍       | 6979/28080 [13:47:39<41:32:47,  7.09s/it]
 25%|██▍       | 6980/28080 [13:47:46<41:28:46,  7.08s/it]
                                                          
{'loss': 0.6334, 'learning_rate': 0.0004399389369877467, 'epoch': 2.98}

 25%|██▍       | 6980/28080 [13:47:46<41:28:46,  7.08s/it]
 25%|██▍       | 6981/28080 [13:47:53<41:25:53,  7.07s/it]
                                                          
{'loss': 0.656, 'learning_rate': 0.0004399201864998011, 'epoch': 2.98}

 25%|██▍       | 6981/28080 [13:47:53<41:25:53,  7.07s/it]
 25%|██▍       | 6982/28080 [13:48:00<41:30:24,  7.08s/it]
                                                          
{'loss': 0.643, 'learning_rate': 0.00043990143348516343, 'epoch': 2.98}

 25%|██▍       | 6982/28080 [13:48:00<41:30:24,  7.08s/it]
 25%|██▍       | 6983/28080 [13:48:07<41:35:49,  7.10s/it]
                                                          
{'loss': 0.6301, 'learning_rate': 0.0004398826779440831, 'epoch': 2.98}

 25%|██▍       | 6983/28080 [13:48:07<41:35:49,  7.10s/it]
 25%|██▍       | 6984/28080 [13:48:14<41:27:39,  7.08s/it]
                                                          
{'loss': 0.6476, 'learning_rate': 0.0004398639198768096, 'epoch': 2.98}

 25%|██▍       | 6984/28080 [13:48:14<41:27:39,  7.08s/it]
 25%|██▍       | 6985/28080 [13:48:21<41:31:12,  7.09s/it]
                                                          
{'loss': 0.6145, 'learning_rate': 0.0004398451592835925, 'epoch': 2.98}

 25%|██▍       | 6985/28080 [13:48:21<41:31:12,  7.09s/it]
 25%|██▍       | 6986/28080 [13:48:28<41:37:38,  7.10s/it]
                                                          
{'loss': 0.6297, 'learning_rate': 0.00043982639616468145, 'epoch': 2.98}

 25%|██▍       | 6986/28080 [13:48:28<41:37:38,  7.10s/it]
 25%|██▍       | 6987/28080 [13:48:35<41:50:11,  7.14s/it]
                                                          
{'loss': 0.6412, 'learning_rate': 0.000439807630520326, 'epoch': 2.98}

 25%|██▍       | 6987/28080 [13:48:35<41:50:11,  7.14s/it]
 25%|██▍       | 6988/28080 [13:48:42<41:29:12,  7.08s/it]
                                                          
{'loss': 0.6483, 'learning_rate': 0.00043978886235077584, 'epoch': 2.99}

 25%|██▍       | 6988/28080 [13:48:42<41:29:12,  7.08s/it]
 25%|██▍       | 6989/28080 [13:48:49<41:25:04,  7.07s/it]
                                                          
{'loss': 0.6287, 'learning_rate': 0.0004397700916562807, 'epoch': 2.99}

 25%|██▍       | 6989/28080 [13:48:49<41:25:04,  7.07s/it]
 25%|██▍       | 6990/28080 [13:48:56<41:14:50,  7.04s/it]
                                                          
{'loss': 0.6491, 'learning_rate': 0.0004397513184370903, 'epoch': 2.99}

 25%|██▍       | 6990/28080 [13:48:56<41:14:50,  7.04s/it]
 25%|██▍       | 6991/28080 [13:49:04<41:19:19,  7.05s/it]
                                                          
{'loss': 0.622, 'learning_rate': 0.0004397325426934543, 'epoch': 2.99}

 25%|██▍       | 6991/28080 [13:49:04<41:19:19,  7.05s/it]
 25%|██▍       | 6992/28080 [13:49:11<41:32:51,  7.09s/it]
                                                          
{'loss': 0.6394, 'learning_rate': 0.0004397137644256225, 'epoch': 2.99}

 25%|██▍       | 6992/28080 [13:49:11<41:32:51,  7.09s/it]
 25%|██▍       | 6993/28080 [13:49:18<41:29:50,  7.08s/it]
                                                          
{'loss': 0.653, 'learning_rate': 0.00043969498363384486, 'epoch': 2.99}

 25%|██▍       | 6993/28080 [13:49:18<41:29:50,  7.08s/it]
 25%|██▍       | 6994/28080 [13:49:25<41:33:37,  7.10s/it]
                                                          
{'loss': 0.6484, 'learning_rate': 0.00043967620031837117, 'epoch': 2.99}

 25%|██▍       | 6994/28080 [13:49:25<41:33:37,  7.10s/it]
 25%|██▍       | 6995/28080 [13:49:32<41:36:42,  7.10s/it]
                                                          
{'loss': 0.6139, 'learning_rate': 0.0004396574144794513, 'epoch': 2.99}

 25%|██▍       | 6995/28080 [13:49:32<41:36:42,  7.10s/it]
 25%|██▍       | 6996/28080 [13:49:39<41:37:13,  7.11s/it]
                                                          
{'loss': 0.6225, 'learning_rate': 0.0004396386261173352, 'epoch': 2.99}

 25%|██▍       | 6996/28080 [13:49:39<41:37:13,  7.11s/it]
 25%|██▍       | 6997/28080 [13:49:46<41:32:54,  7.09s/it]
                                                          
{'loss': 0.6311, 'learning_rate': 0.00043961983523227276, 'epoch': 2.99}

 25%|██▍       | 6997/28080 [13:49:46<41:32:54,  7.09s/it]
 25%|██▍       | 6998/28080 [13:49:53<41:18:24,  7.05s/it]
                                                          
{'loss': 0.6418, 'learning_rate': 0.00043960104182451403, 'epoch': 2.99}

 25%|██▍       | 6998/28080 [13:49:53<41:18:24,  7.05s/it]
 25%|██▍       | 6999/28080 [13:50:00<41:18:54,  7.06s/it]
                                                          
{'loss': 0.6255, 'learning_rate': 0.0004395822458943091, 'epoch': 2.99}

 25%|██▍       | 6999/28080 [13:50:00<41:18:54,  7.06s/it]
 25%|██▍       | 7000/28080 [13:50:07<41:12:09,  7.04s/it]
                                                          
{'loss': 0.6463, 'learning_rate': 0.0004395634474419079, 'epoch': 2.99}

 25%|██▍       | 7000/28080 [13:50:07<41:12:09,  7.04s/it]
 25%|██▍       | 7001/28080 [13:50:14<41:20:31,  7.06s/it]
                                                          
{'loss': 0.6306, 'learning_rate': 0.00043954464646756063, 'epoch': 2.99}

 25%|██▍       | 7001/28080 [13:50:14<41:20:31,  7.06s/it]
 25%|██▍       | 7002/28080 [13:50:21<41:14:04,  7.04s/it]
                                                          
{'loss': 0.6371, 'learning_rate': 0.0004395258429715174, 'epoch': 2.99}

 25%|██▍       | 7002/28080 [13:50:21<41:14:04,  7.04s/it]
 25%|██▍       | 7003/28080 [13:50:28<41:18:48,  7.06s/it]
                                                          
{'loss': 0.6369, 'learning_rate': 0.0004395070369540284, 'epoch': 2.99}

 25%|██▍       | 7003/28080 [13:50:28<41:18:48,  7.06s/it]
 25%|██▍       | 7004/28080 [13:50:35<41:21:15,  7.06s/it]
                                                          
{'loss': 0.6251, 'learning_rate': 0.0004394882284153437, 'epoch': 2.99}

 25%|██▍       | 7004/28080 [13:50:35<41:21:15,  7.06s/it]
 25%|██▍       | 7005/28080 [13:50:43<41:18:21,  7.06s/it]
                                                          
{'loss': 0.6205, 'learning_rate': 0.00043946941735571363, 'epoch': 2.99}

 25%|██▍       | 7005/28080 [13:50:43<41:18:21,  7.06s/it]
 25%|██▍       | 7006/28080 [13:50:50<41:30:10,  7.09s/it]
                                                          
{'loss': 0.6388, 'learning_rate': 0.0004394506037753884, 'epoch': 2.99}

 25%|██▍       | 7006/28080 [13:50:50<41:30:10,  7.09s/it]
 25%|██▍       | 7007/28080 [13:50:57<41:30:46,  7.09s/it]
                                                          
{'loss': 0.6375, 'learning_rate': 0.00043943178767461835, 'epoch': 2.99}

 25%|██▍       | 7007/28080 [13:50:57<41:30:46,  7.09s/it]
 25%|██▍       | 7008/28080 [13:51:04<41:24:00,  7.07s/it]
                                                          
{'loss': 0.6346, 'learning_rate': 0.0004394129690536538, 'epoch': 2.99}

 25%|██▍       | 7008/28080 [13:51:04<41:24:00,  7.07s/it]
 25%|██▍       | 7009/28080 [13:51:11<41:35:00,  7.10s/it]
                                                          
{'loss': 0.6491, 'learning_rate': 0.0004393941479127451, 'epoch': 2.99}

 25%|██▍       | 7009/28080 [13:51:11<41:35:00,  7.10s/it]
 25%|██▍       | 7010/28080 [13:51:18<41:38:01,  7.11s/it]
                                                          
{'loss': 0.6261, 'learning_rate': 0.00043937532425214265, 'epoch': 2.99}

 25%|██▍       | 7010/28080 [13:51:18<41:38:01,  7.11s/it]
 25%|██▍       | 7011/28080 [13:51:25<41:32:39,  7.10s/it]
                                                          
{'loss': 0.6347, 'learning_rate': 0.00043935649807209687, 'epoch': 3.0}

 25%|██▍       | 7011/28080 [13:51:25<41:32:39,  7.10s/it]
 25%|██▍       | 7012/28080 [13:51:32<41:33:10,  7.10s/it]
                                                          
{'loss': 0.654, 'learning_rate': 0.00043933766937285823, 'epoch': 3.0}

 25%|██▍       | 7012/28080 [13:51:32<41:33:10,  7.10s/it]
 25%|██▍       | 7013/28080 [13:51:39<41:28:00,  7.09s/it]
                                                          
{'loss': 0.6397, 'learning_rate': 0.00043931883815467724, 'epoch': 3.0}

 25%|██▍       | 7013/28080 [13:51:39<41:28:00,  7.09s/it]
 25%|██▍       | 7014/28080 [13:51:46<41:25:18,  7.08s/it]
                                                          
{'loss': 0.6389, 'learning_rate': 0.0004393000044178044, 'epoch': 3.0}

 25%|██▍       | 7014/28080 [13:51:46<41:25:18,  7.08s/it]
 25%|██▍       | 7015/28080 [13:51:53<41:23:18,  7.07s/it]
                                                          
{'loss': 0.6526, 'learning_rate': 0.0004392811681624903, 'epoch': 3.0}

 25%|██▍       | 7015/28080 [13:51:53<41:23:18,  7.07s/it]
 25%|██▍       | 7016/28080 [13:52:01<41:25:02,  7.08s/it]
                                                          
{'loss': 0.6484, 'learning_rate': 0.00043926232938898554, 'epoch': 3.0}

 25%|██▍       | 7016/28080 [13:52:01<41:25:02,  7.08s/it]
 25%|██▍       | 7017/28080 [13:52:08<41:28:19,  7.09s/it]
                                                          
{'loss': 0.6224, 'learning_rate': 0.00043924348809754065, 'epoch': 3.0}

 25%|██▍       | 7017/28080 [13:52:08<41:28:19,  7.09s/it]
 25%|██▍       | 7018/28080 [13:52:15<41:25:42,  7.08s/it]
                                                          
{'loss': 0.6497, 'learning_rate': 0.00043922464428840653, 'epoch': 3.0}

 25%|██▍       | 7018/28080 [13:52:15<41:25:42,  7.08s/it]
 25%|██▍       | 7019/28080 [13:52:22<41:27:10,  7.09s/it]
                                                          
{'loss': 0.6527, 'learning_rate': 0.0004392057979618337, 'epoch': 3.0}

 25%|██▍       | 7019/28080 [13:52:22<41:27:10,  7.09s/it]
 25%|██▌       | 7020/28080 [13:52:29<41:29:52,  7.09s/it]
                                                          
{'loss': 0.6417, 'learning_rate': 0.0004391869491180728, 'epoch': 3.0}

 25%|██▌       | 7020/28080 [13:52:29<41:29:52,  7.09s/it]
 25%|██▌       | 7021/28080 [13:52:36<41:19:51,  7.07s/it]
                                                          
{'loss': 0.6378, 'learning_rate': 0.0004391680977573748, 'epoch': 3.0}

 25%|██▌       | 7021/28080 [13:52:36<41:19:51,  7.07s/it]
 25%|██▌       | 7022/28080 [13:52:43<41:16:18,  7.06s/it]
                                                          
{'loss': 0.6492, 'learning_rate': 0.00043914924387999043, 'epoch': 3.0}

 25%|██▌       | 7022/28080 [13:52:43<41:16:18,  7.06s/it]
 25%|██▌       | 7023/28080 [13:52:51<42:14:28,  7.22s/it]
                                                          
{'loss': 0.6258, 'learning_rate': 0.0004391303874861705, 'epoch': 3.0}

 25%|██▌       | 7023/28080 [13:52:51<42:14:28,  7.22s/it]
 25%|██▌       | 7024/28080 [13:52:58<42:05:07,  7.20s/it]
                                                          
{'loss': 0.6408, 'learning_rate': 0.00043911152857616586, 'epoch': 3.0}

 25%|██▌       | 7024/28080 [13:52:58<42:05:07,  7.20s/it]
 25%|██▌       | 7025/28080 [13:53:05<41:53:11,  7.16s/it]
                                                          
{'loss': 0.6452, 'learning_rate': 0.00043909266715022745, 'epoch': 3.0}

 25%|██▌       | 7025/28080 [13:53:05<41:53:11,  7.16s/it]
 25%|██▌       | 7026/28080 [13:53:12<41:39:57,  7.12s/it]
                                                          
{'loss': 0.6691, 'learning_rate': 0.00043907380320860613, 'epoch': 3.0}

 25%|██▌       | 7026/28080 [13:53:12<41:39:57,  7.12s/it]
 25%|██▌       | 7027/28080 [13:53:19<41:30:06,  7.10s/it]
                                                          
{'loss': 0.6399, 'learning_rate': 0.00043905493675155293, 'epoch': 3.0}

 25%|██▌       | 7027/28080 [13:53:19<41:30:06,  7.10s/it]
 25%|██▌       | 7028/28080 [13:53:26<41:33:18,  7.11s/it]
                                                          
{'loss': 0.6514, 'learning_rate': 0.00043903606777931885, 'epoch': 3.0}

 25%|██▌       | 7028/28080 [13:53:26<41:33:18,  7.11s/it]
 25%|██▌       | 7029/28080 [13:53:33<41:25:04,  7.08s/it]
                                                          
{'loss': 0.6325, 'learning_rate': 0.00043901719629215494, 'epoch': 3.0}

 25%|██▌       | 7029/28080 [13:53:33<41:25:04,  7.08s/it]
 25%|██▌       | 7030/28080 [13:53:40<41:35:38,  7.11s/it]
                                                          
{'loss': 0.6141, 'learning_rate': 0.0004389983222903122, 'epoch': 3.0}

 25%|██▌       | 7030/28080 [13:53:40<41:35:38,  7.11s/it]
 25%|██▌       | 7031/28080 [13:53:47<41:35:32,  7.11s/it]
                                                          
{'loss': 0.6239, 'learning_rate': 0.0004389794457740417, 'epoch': 3.0}

 25%|██▌       | 7031/28080 [13:53:47<41:35:32,  7.11s/it]
 25%|██▌       | 7032/28080 [13:53:54<41:18:45,  7.07s/it]
                                                          
{'loss': 0.652, 'learning_rate': 0.0004389605667435947, 'epoch': 3.0}

 25%|██▌       | 7032/28080 [13:53:54<41:18:45,  7.07s/it]
 25%|██▌       | 7033/28080 [13:54:01<41:21:21,  7.07s/it]
                                                          
{'loss': 0.6361, 'learning_rate': 0.00043894168519922227, 'epoch': 3.0}

 25%|██▌       | 7033/28080 [13:54:01<41:21:21,  7.07s/it]
 25%|██▌       | 7034/28080 [13:54:08<41:25:19,  7.09s/it]
                                                          
{'loss': 0.6408, 'learning_rate': 0.0004389228011411757, 'epoch': 3.0}

 25%|██▌       | 7034/28080 [13:54:08<41:25:19,  7.09s/it]
 25%|██▌       | 7035/28080 [13:54:16<41:28:46,  7.10s/it]
                                                          
{'loss': 0.6161, 'learning_rate': 0.00043890391456970614, 'epoch': 3.01}

 25%|██▌       | 7035/28080 [13:54:16<41:28:46,  7.10s/it]
 25%|██▌       | 7036/28080 [13:54:23<41:29:37,  7.10s/it]
                                                          
{'loss': 0.6314, 'learning_rate': 0.0004388850254850648, 'epoch': 3.01}

 25%|██▌       | 7036/28080 [13:54:23<41:29:37,  7.10s/it]
 25%|██▌       | 7037/28080 [13:54:30<41:32:02,  7.11s/it]
                                                          
{'loss': 0.6362, 'learning_rate': 0.0004388661338875032, 'epoch': 3.01}

 25%|██▌       | 7037/28080 [13:54:30<41:32:02,  7.11s/it]
 25%|██▌       | 7038/28080 [13:54:37<41:26:09,  7.09s/it]
                                                          
{'loss': 0.6458, 'learning_rate': 0.0004388472397772724, 'epoch': 3.01}

 25%|██▌       | 7038/28080 [13:54:37<41:26:09,  7.09s/it]
 25%|██▌       | 7039/28080 [13:54:44<41:21:22,  7.08s/it]
                                                          
{'loss': 0.6359, 'learning_rate': 0.00043882834315462396, 'epoch': 3.01}

 25%|██▌       | 7039/28080 [13:54:44<41:21:22,  7.08s/it]
 25%|██▌       | 7040/28080 [13:54:51<41:05:58,  7.03s/it]
                                                          
{'loss': 0.6479, 'learning_rate': 0.00043880944401980917, 'epoch': 3.01}

 25%|██▌       | 7040/28080 [13:54:51<41:05:58,  7.03s/it]
 25%|██▌       | 7041/28080 [13:54:58<41:01:02,  7.02s/it]
                                                          
{'loss': 0.6528, 'learning_rate': 0.0004387905423730796, 'epoch': 3.01}

 25%|██▌       | 7041/28080 [13:54:58<41:01:02,  7.02s/it]
 25%|██▌       | 7042/28080 [13:55:05<41:06:13,  7.03s/it]
                                                          
{'loss': 0.6527, 'learning_rate': 0.0004387716382146866, 'epoch': 3.01}

 25%|██▌       | 7042/28080 [13:55:05<41:06:13,  7.03s/it]
 25%|██▌       | 7043/28080 [13:55:12<41:06:33,  7.03s/it]
                                                          
{'loss': 0.6275, 'learning_rate': 0.00043875273154488163, 'epoch': 3.01}

 25%|██▌       | 7043/28080 [13:55:12<41:06:33,  7.03s/it]
 25%|██▌       | 7044/28080 [13:55:19<41:13:29,  7.06s/it]
                                                          
{'loss': 0.6114, 'learning_rate': 0.00043873382236391635, 'epoch': 3.01}

 25%|██▌       | 7044/28080 [13:55:19<41:13:29,  7.06s/it]
 25%|██▌       | 7045/28080 [13:55:26<41:20:21,  7.07s/it]
                                                          
{'loss': 0.6497, 'learning_rate': 0.0004387149106720422, 'epoch': 3.01}

 25%|██▌       | 7045/28080 [13:55:26<41:20:21,  7.07s/it]
 25%|██▌       | 7046/28080 [13:55:33<41:13:29,  7.06s/it]
                                                          
{'loss': 0.6433, 'learning_rate': 0.0004386959964695109, 'epoch': 3.01}

 25%|██▌       | 7046/28080 [13:55:33<41:13:29,  7.06s/it]
 25%|██▌       | 7047/28080 [13:55:40<41:07:30,  7.04s/it]
                                                          
{'loss': 0.6447, 'learning_rate': 0.000438677079756574, 'epoch': 3.01}

 25%|██▌       | 7047/28080 [13:55:40<41:07:30,  7.04s/it]
 25%|██▌       | 7048/28080 [13:55:47<41:16:24,  7.06s/it]
                                                          
{'loss': 0.6248, 'learning_rate': 0.0004386581605334833, 'epoch': 3.01}

 25%|██▌       | 7048/28080 [13:55:47<41:16:24,  7.06s/it]
 25%|██▌       | 7049/28080 [13:55:54<41:23:54,  7.09s/it]
                                                          
{'loss': 0.6332, 'learning_rate': 0.0004386392388004903, 'epoch': 3.01}

 25%|██▌       | 7049/28080 [13:55:54<41:23:54,  7.09s/it]
 25%|██▌       | 7050/28080 [13:56:02<41:24:34,  7.09s/it]
                                                          
{'loss': 0.6479, 'learning_rate': 0.0004386203145578469, 'epoch': 3.01}

 25%|██▌       | 7050/28080 [13:56:02<41:24:34,  7.09s/it]
 25%|██▌       | 7051/28080 [13:56:09<41:25:03,  7.09s/it]
                                                          
{'loss': 0.6426, 'learning_rate': 0.0004386013878058048, 'epoch': 3.01}

 25%|██▌       | 7051/28080 [13:56:09<41:25:03,  7.09s/it]
 25%|██▌       | 7052/28080 [13:56:16<41:16:03,  7.07s/it]
                                                          
{'loss': 0.6455, 'learning_rate': 0.00043858245854461577, 'epoch': 3.01}

 25%|██▌       | 7052/28080 [13:56:16<41:16:03,  7.07s/it]
 25%|██▌       | 7053/28080 [13:56:23<41:19:35,  7.08s/it]
                                                          
{'loss': 0.6194, 'learning_rate': 0.0004385635267745317, 'epoch': 3.01}

 25%|██▌       | 7053/28080 [13:56:23<41:19:35,  7.08s/it]
 25%|██▌       | 7054/28080 [13:56:30<41:14:34,  7.06s/it]
                                                          
{'loss': 0.6411, 'learning_rate': 0.0004385445924958044, 'epoch': 3.01}

 25%|██▌       | 7054/28080 [13:56:30<41:14:34,  7.06s/it]
 25%|██▌       | 7055/28080 [13:56:37<41:15:25,  7.06s/it]
                                                          
{'loss': 0.6516, 'learning_rate': 0.00043852565570868586, 'epoch': 3.01}

 25%|██▌       | 7055/28080 [13:56:37<41:15:25,  7.06s/it]
 25%|██▌       | 7056/28080 [13:56:44<41:16:10,  7.07s/it]
                                                          
{'loss': 0.626, 'learning_rate': 0.00043850671641342795, 'epoch': 3.01}

 25%|██▌       | 7056/28080 [13:56:44<41:16:10,  7.07s/it]
 25%|██▌       | 7057/28080 [13:56:51<41:19:24,  7.08s/it]
                                                          
{'loss': 0.624, 'learning_rate': 0.0004384877746102826, 'epoch': 3.01}

 25%|██▌       | 7057/28080 [13:56:51<41:19:24,  7.08s/it]
 25%|██▌       | 7058/28080 [13:56:58<41:15:09,  7.06s/it]
                                                          
{'loss': 0.6612, 'learning_rate': 0.0004384688302995019, 'epoch': 3.02}

 25%|██▌       | 7058/28080 [13:56:58<41:15:09,  7.06s/it]
 25%|██▌       | 7059/28080 [13:57:05<41:17:57,  7.07s/it]
                                                          
{'loss': 0.6227, 'learning_rate': 0.00043844988348133783, 'epoch': 3.02}

 25%|██▌       | 7059/28080 [13:57:05<41:17:57,  7.07s/it]
 25%|██▌       | 7060/28080 [13:57:12<41:28:41,  7.10s/it]
                                                          
{'loss': 0.6263, 'learning_rate': 0.0004384309341560425, 'epoch': 3.02}

 25%|██▌       | 7060/28080 [13:57:12<41:28:41,  7.10s/it]
 25%|██▌       | 7061/28080 [13:57:19<41:34:46,  7.12s/it]
                                                          
{'loss': 0.6264, 'learning_rate': 0.00043841198232386796, 'epoch': 3.02}

 25%|██▌       | 7061/28080 [13:57:19<41:34:46,  7.12s/it]
 25%|██▌       | 7062/28080 [13:57:27<41:34:31,  7.12s/it]
                                                          
{'loss': 0.6384, 'learning_rate': 0.00043839302798506644, 'epoch': 3.02}

 25%|██▌       | 7062/28080 [13:57:27<41:34:31,  7.12s/it]
 25%|██▌       | 7063/28080 [13:57:34<41:26:28,  7.10s/it]
                                                          
{'loss': 0.6265, 'learning_rate': 0.00043837407113988993, 'epoch': 3.02}

 25%|██▌       | 7063/28080 [13:57:34<41:26:28,  7.10s/it]
 25%|██▌       | 7064/28080 [13:57:41<41:22:30,  7.09s/it]
                                                          
{'loss': 0.6295, 'learning_rate': 0.0004383551117885908, 'epoch': 3.02}

 25%|██▌       | 7064/28080 [13:57:41<41:22:30,  7.09s/it]
 25%|██▌       | 7065/28080 [13:57:48<41:25:00,  7.09s/it]
                                                          
{'loss': 0.6391, 'learning_rate': 0.0004383361499314212, 'epoch': 3.02}

 25%|██▌       | 7065/28080 [13:57:48<41:25:00,  7.09s/it]
 25%|██▌       | 7066/28080 [13:57:55<41:32:02,  7.12s/it]
                                                          
{'loss': 0.637, 'learning_rate': 0.0004383171855686334, 'epoch': 3.02}

 25%|██▌       | 7066/28080 [13:57:55<41:32:02,  7.12s/it]
 25%|██▌       | 7067/28080 [13:58:02<41:20:26,  7.08s/it]
                                                          
{'loss': 0.6483, 'learning_rate': 0.0004382982187004798, 'epoch': 3.02}

 25%|██▌       | 7067/28080 [13:58:02<41:20:26,  7.08s/it]
 25%|██▌       | 7068/28080 [13:58:09<41:22:09,  7.09s/it]
                                                          
{'loss': 0.6394, 'learning_rate': 0.0004382792493272126, 'epoch': 3.02}

 25%|██▌       | 7068/28080 [13:58:09<41:22:09,  7.09s/it]
 25%|██▌       | 7069/28080 [13:58:16<41:23:15,  7.09s/it]
                                                          
{'loss': 0.6658, 'learning_rate': 0.00043826027744908426, 'epoch': 3.02}

 25%|██▌       | 7069/28080 [13:58:16<41:23:15,  7.09s/it]
 25%|██▌       | 7070/28080 [13:58:23<41:24:00,  7.09s/it]
                                                          
{'loss': 0.6247, 'learning_rate': 0.00043824130306634705, 'epoch': 3.02}

 25%|██▌       | 7070/28080 [13:58:23<41:24:00,  7.09s/it]
 25%|██▌       | 7071/28080 [13:58:30<41:24:32,  7.10s/it]
                                                          
{'loss': 0.6397, 'learning_rate': 0.00043822232617925363, 'epoch': 3.02}

 25%|██▌       | 7071/28080 [13:58:30<41:24:32,  7.10s/it]
 25%|██▌       | 7072/28080 [13:58:38<41:30:16,  7.11s/it]
                                                          
{'loss': 0.6198, 'learning_rate': 0.00043820334678805624, 'epoch': 3.02}

 25%|██▌       | 7072/28080 [13:58:38<41:30:16,  7.11s/it]
 25%|██▌       | 7073/28080 [13:58:45<41:22:25,  7.09s/it]
                                                          
{'loss': 0.6215, 'learning_rate': 0.0004381843648930075, 'epoch': 3.02}

 25%|██▌       | 7073/28080 [13:58:45<41:22:25,  7.09s/it]
 25%|██▌       | 7074/28080 [13:58:52<41:27:48,  7.11s/it]
                                                          
{'loss': 0.6511, 'learning_rate': 0.00043816538049435994, 'epoch': 3.02}

 25%|██▌       | 7074/28080 [13:58:52<41:27:48,  7.11s/it]
 25%|██▌       | 7075/28080 [13:58:59<41:20:11,  7.08s/it]
                                                          
{'loss': 0.6505, 'learning_rate': 0.00043814639359236615, 'epoch': 3.02}

 25%|██▌       | 7075/28080 [13:58:59<41:20:11,  7.08s/it]
 25%|██▌       | 7076/28080 [13:59:06<41:18:38,  7.08s/it]
                                                          
{'loss': 0.629, 'learning_rate': 0.0004381274041872786, 'epoch': 3.02}

 25%|██▌       | 7076/28080 [13:59:06<41:18:38,  7.08s/it]
 25%|██▌       | 7077/28080 [13:59:13<41:09:52,  7.06s/it]
                                                          
{'loss': 0.637, 'learning_rate': 0.00043810841227935013, 'epoch': 3.02}

 25%|██▌       | 7077/28080 [13:59:13<41:09:52,  7.06s/it]
 25%|██▌       | 7078/28080 [13:59:20<41:09:36,  7.06s/it]
                                                          
{'loss': 0.6325, 'learning_rate': 0.00043808941786883314, 'epoch': 3.02}

 25%|██▌       | 7078/28080 [13:59:20<41:09:36,  7.06s/it]
 25%|██▌       | 7079/28080 [13:59:27<41:12:59,  7.07s/it]
                                                          
{'loss': 0.6511, 'learning_rate': 0.00043807042095598067, 'epoch': 3.02}

 25%|██▌       | 7079/28080 [13:59:27<41:12:59,  7.07s/it]
 25%|██▌       | 7080/28080 [13:59:34<41:14:08,  7.07s/it]
                                                          
{'loss': 0.6452, 'learning_rate': 0.00043805142154104514, 'epoch': 3.02}

 25%|██▌       | 7080/28080 [13:59:34<41:14:08,  7.07s/it]
 25%|██▌       | 7081/28080 [13:59:41<41:15:43,  7.07s/it]
                                                          
{'loss': 0.631, 'learning_rate': 0.00043803241962427953, 'epoch': 3.02}

 25%|██▌       | 7081/28080 [13:59:41<41:15:43,  7.07s/it]
 25%|██▌       | 7082/28080 [13:59:48<41:14:02,  7.07s/it]
                                                          
{'loss': 0.6453, 'learning_rate': 0.00043801341520593654, 'epoch': 3.03}

 25%|██▌       | 7082/28080 [13:59:48<41:14:02,  7.07s/it]
 25%|██▌       | 7083/28080 [13:59:55<41:12:59,  7.07s/it]
                                                          
{'loss': 0.6125, 'learning_rate': 0.000437994408286269, 'epoch': 3.03}

 25%|██▌       | 7083/28080 [13:59:55<41:12:59,  7.07s/it]
 25%|██▌       | 7084/28080 [14:00:02<41:07:26,  7.05s/it]
                                                          
{'loss': 0.6345, 'learning_rate': 0.0004379753988655298, 'epoch': 3.03}

 25%|██▌       | 7084/28080 [14:00:02<41:07:26,  7.05s/it]
 25%|██▌       | 7085/28080 [14:00:09<41:13:48,  7.07s/it]
                                                          
{'loss': 0.6455, 'learning_rate': 0.00043795638694397185, 'epoch': 3.03}

 25%|██▌       | 7085/28080 [14:00:09<41:13:48,  7.07s/it]
 25%|██▌       | 7086/28080 [14:00:16<41:13:25,  7.07s/it]
                                                          
{'loss': 0.6184, 'learning_rate': 0.00043793737252184806, 'epoch': 3.03}

 25%|██▌       | 7086/28080 [14:00:16<41:13:25,  7.07s/it]
 25%|██▌       | 7087/28080 [14:00:24<41:17:04,  7.08s/it]
                                                          
{'loss': 0.6226, 'learning_rate': 0.0004379183555994114, 'epoch': 3.03}

 25%|██▌       | 7087/28080 [14:00:24<41:17:04,  7.08s/it]
 25%|██▌       | 7088/28080 [14:00:31<41:05:57,  7.05s/it]
                                                          
{'loss': 0.6558, 'learning_rate': 0.0004378993361769149, 'epoch': 3.03}

 25%|██▌       | 7088/28080 [14:00:31<41:05:57,  7.05s/it]
 25%|██▌       | 7089/28080 [14:00:37<40:51:57,  7.01s/it]
                                                          
{'loss': 0.6481, 'learning_rate': 0.0004378803142546116, 'epoch': 3.03}

 25%|██▌       | 7089/28080 [14:00:37<40:51:57,  7.01s/it]
 25%|██▌       | 7090/28080 [14:00:45<41:06:03,  7.05s/it]
                                                          
{'loss': 0.6577, 'learning_rate': 0.00043786128983275453, 'epoch': 3.03}

 25%|██▌       | 7090/28080 [14:00:45<41:06:03,  7.05s/it]
 25%|██▌       | 7091/28080 [14:00:52<41:13:18,  7.07s/it]
                                                          
{'loss': 0.6316, 'learning_rate': 0.00043784226291159687, 'epoch': 3.03}

 25%|██▌       | 7091/28080 [14:00:52<41:13:18,  7.07s/it]
 25%|██▌       | 7092/28080 [14:00:59<41:15:45,  7.08s/it]
                                                          
{'loss': 0.621, 'learning_rate': 0.0004378232334913916, 'epoch': 3.03}

 25%|██▌       | 7092/28080 [14:00:59<41:15:45,  7.08s/it]
 25%|██▌       | 7093/28080 [14:01:06<41:11:31,  7.07s/it]
                                                          
{'loss': 0.6437, 'learning_rate': 0.000437804201572392, 'epoch': 3.03}

 25%|██▌       | 7093/28080 [14:01:06<41:11:31,  7.07s/it]
 25%|██▌       | 7094/28080 [14:01:13<41:26:33,  7.11s/it]
                                                          
{'loss': 0.6423, 'learning_rate': 0.0004377851671548512, 'epoch': 3.03}

 25%|██▌       | 7094/28080 [14:01:13<41:26:33,  7.11s/it]
 25%|██▌       | 7095/28080 [14:01:20<41:29:33,  7.12s/it]
                                                          
{'loss': 0.6303, 'learning_rate': 0.00043776613023902255, 'epoch': 3.03}

 25%|██▌       | 7095/28080 [14:01:20<41:29:33,  7.12s/it]
 25%|██▌       | 7096/28080 [14:01:27<41:23:33,  7.10s/it]
                                                          
{'loss': 0.6425, 'learning_rate': 0.0004377470908251592, 'epoch': 3.03}

 25%|██▌       | 7096/28080 [14:01:27<41:23:33,  7.10s/it]
 25%|██▌       | 7097/28080 [14:01:34<41:18:42,  7.09s/it]
                                                          
{'loss': 0.6419, 'learning_rate': 0.0004377280489135145, 'epoch': 3.03}

 25%|██▌       | 7097/28080 [14:01:34<41:18:42,  7.09s/it]
 25%|██▌       | 7098/28080 [14:01:41<41:22:41,  7.10s/it]
                                                          
{'loss': 0.6287, 'learning_rate': 0.0004377090045043418, 'epoch': 3.03}

 25%|██▌       | 7098/28080 [14:01:41<41:22:41,  7.10s/it]
 25%|██▌       | 7099/28080 [14:01:49<41:26:44,  7.11s/it]
                                                          
{'loss': 0.6596, 'learning_rate': 0.00043768995759789443, 'epoch': 3.03}

 25%|██▌       | 7099/28080 [14:01:49<41:26:44,  7.11s/it]
 25%|██▌       | 7100/28080 [14:01:56<41:23:04,  7.10s/it]
                                                          
{'loss': 0.6097, 'learning_rate': 0.0004376709081944258, 'epoch': 3.03}

 25%|██▌       | 7100/28080 [14:01:56<41:23:04,  7.10s/it]
 25%|██▌       | 7101/28080 [14:02:03<41:48:26,  7.17s/it]
                                                          
{'loss': 0.6259, 'learning_rate': 0.00043765185629418937, 'epoch': 3.03}

 25%|██▌       | 7101/28080 [14:02:03<41:48:26,  7.17s/it]
 25%|██▌       | 7102/28080 [14:02:10<41:41:08,  7.15s/it]
                                                          
{'loss': 0.6173, 'learning_rate': 0.00043763280189743856, 'epoch': 3.03}

 25%|██▌       | 7102/28080 [14:02:10<41:41:08,  7.15s/it]
 25%|██▌       | 7103/28080 [14:02:17<41:39:12,  7.15s/it]
                                                          
{'loss': 0.6204, 'learning_rate': 0.00043761374500442686, 'epoch': 3.03}

 25%|██▌       | 7103/28080 [14:02:17<41:39:12,  7.15s/it]
 25%|██▌       | 7104/28080 [14:02:24<41:40:18,  7.15s/it]
                                                          
{'loss': 0.6494, 'learning_rate': 0.00043759468561540795, 'epoch': 3.03}

 25%|██▌       | 7104/28080 [14:02:24<41:40:18,  7.15s/it]
 25%|██▌       | 7105/28080 [14:02:32<41:42:21,  7.16s/it]
                                                          
{'loss': 0.6237, 'learning_rate': 0.0004375756237306351, 'epoch': 3.04}

 25%|██▌       | 7105/28080 [14:02:32<41:42:21,  7.16s/it]
 25%|██▌       | 7106/28080 [14:02:39<41:34:12,  7.14s/it]
                                                          
{'loss': 0.6526, 'learning_rate': 0.0004375565593503622, 'epoch': 3.04}

 25%|██▌       | 7106/28080 [14:02:39<41:34:12,  7.14s/it]
 25%|██▌       | 7107/28080 [14:02:46<41:36:57,  7.14s/it]
                                                          
{'loss': 0.6646, 'learning_rate': 0.00043753749247484275, 'epoch': 3.04}

 25%|██▌       | 7107/28080 [14:02:46<41:36:57,  7.14s/it]
 25%|██▌       | 7108/28080 [14:02:53<41:32:52,  7.13s/it]
                                                          
{'loss': 0.6656, 'learning_rate': 0.00043751842310433046, 'epoch': 3.04}

 25%|██▌       | 7108/28080 [14:02:53<41:32:52,  7.13s/it]
 25%|██▌       | 7109/28080 [14:03:00<41:24:06,  7.11s/it]
                                                          
{'loss': 0.6562, 'learning_rate': 0.000437499351239079, 'epoch': 3.04}

 25%|██▌       | 7109/28080 [14:03:00<41:24:06,  7.11s/it]
 25%|██▌       | 7110/28080 [14:03:07<41:27:25,  7.12s/it]
                                                          
{'loss': 0.6379, 'learning_rate': 0.00043748027687934206, 'epoch': 3.04}

 25%|██▌       | 7110/28080 [14:03:07<41:27:25,  7.12s/it]
 25%|██▌       | 7111/28080 [14:03:14<41:28:51,  7.12s/it]
                                                          
{'loss': 0.6449, 'learning_rate': 0.0004374612000253735, 'epoch': 3.04}

 25%|██▌       | 7111/28080 [14:03:14<41:28:51,  7.12s/it]
 25%|██▌       | 7112/28080 [14:03:21<41:14:17,  7.08s/it]
                                                          
{'loss': 0.6413, 'learning_rate': 0.000437442120677427, 'epoch': 3.04}

 25%|██▌       | 7112/28080 [14:03:21<41:14:17,  7.08s/it]
 25%|██▌       | 7113/28080 [14:03:28<41:22:04,  7.10s/it]
                                                          
{'loss': 0.6449, 'learning_rate': 0.00043742303883575654, 'epoch': 3.04}

 25%|██▌       | 7113/28080 [14:03:28<41:22:04,  7.10s/it]
 25%|██▌       | 7114/28080 [14:03:35<41:17:22,  7.09s/it]
                                                          
{'loss': 0.6289, 'learning_rate': 0.0004374039545006158, 'epoch': 3.04}

 25%|██▌       | 7114/28080 [14:03:35<41:17:22,  7.09s/it]
 25%|██▌       | 7115/28080 [14:03:43<41:22:31,  7.10s/it]
                                                          
{'loss': 0.6352, 'learning_rate': 0.00043738486767225883, 'epoch': 3.04}

 25%|██▌       | 7115/28080 [14:03:43<41:22:31,  7.10s/it]
 25%|██▌       | 7116/28080 [14:03:50<41:17:24,  7.09s/it]
                                                          
{'loss': 0.6284, 'learning_rate': 0.0004373657783509395, 'epoch': 3.04}

 25%|██▌       | 7116/28080 [14:03:50<41:17:24,  7.09s/it]
 25%|██▌       | 7117/28080 [14:03:57<41:16:39,  7.09s/it]
                                                          
{'loss': 0.641, 'learning_rate': 0.0004373466865369118, 'epoch': 3.04}

 25%|██▌       | 7117/28080 [14:03:57<41:16:39,  7.09s/it]
 25%|██▌       | 7118/28080 [14:04:04<41:13:12,  7.08s/it]
                                                          
{'loss': 0.6598, 'learning_rate': 0.00043732759223042973, 'epoch': 3.04}

 25%|██▌       | 7118/28080 [14:04:04<41:13:12,  7.08s/it]
 25%|██▌       | 7119/28080 [14:04:11<41:15:57,  7.09s/it]
                                                          
{'loss': 0.634, 'learning_rate': 0.00043730849543174735, 'epoch': 3.04}

 25%|██▌       | 7119/28080 [14:04:11<41:15:57,  7.09s/it]
 25%|██▌       | 7120/28080 [14:04:18<41:19:14,  7.10s/it]
                                                          
{'loss': 0.6409, 'learning_rate': 0.00043728939614111855, 'epoch': 3.04}

 25%|██▌       | 7120/28080 [14:04:18<41:19:14,  7.10s/it]
 25%|██▌       | 7121/28080 [14:04:25<41:19:55,  7.10s/it]
                                                          
{'loss': 0.6312, 'learning_rate': 0.0004372702943587976, 'epoch': 3.04}

 25%|██▌       | 7121/28080 [14:04:25<41:19:55,  7.10s/it]
 25%|██▌       | 7122/28080 [14:04:32<41:22:42,  7.11s/it]
                                                          
{'loss': 0.6371, 'learning_rate': 0.00043725119008503863, 'epoch': 3.04}

 25%|██▌       | 7122/28080 [14:04:32<41:22:42,  7.11s/it]
 25%|██▌       | 7123/28080 [14:04:39<41:27:52,  7.12s/it]
                                                          
{'loss': 0.6292, 'learning_rate': 0.0004372320833200957, 'epoch': 3.04}

 25%|██▌       | 7123/28080 [14:04:39<41:27:52,  7.12s/it]
 25%|██▌       | 7124/28080 [14:04:46<41:24:14,  7.11s/it]
                                                          
{'loss': 0.6333, 'learning_rate': 0.0004372129740642231, 'epoch': 3.04}

 25%|██▌       | 7124/28080 [14:04:46<41:24:14,  7.11s/it]
 25%|██▌       | 7125/28080 [14:04:54<41:25:31,  7.12s/it]
                                                          
{'loss': 0.6427, 'learning_rate': 0.00043719386231767495, 'epoch': 3.04}

 25%|██▌       | 7125/28080 [14:04:54<41:25:31,  7.12s/it]
 25%|██▌       | 7126/28080 [14:05:01<41:18:22,  7.10s/it]
                                                          
{'loss': 0.6416, 'learning_rate': 0.0004371747480807056, 'epoch': 3.04}

 25%|██▌       | 7126/28080 [14:05:01<41:18:22,  7.10s/it]
 25%|██▌       | 7127/28080 [14:05:08<41:11:37,  7.08s/it]
                                                          
{'loss': 0.6243, 'learning_rate': 0.0004371556313535693, 'epoch': 3.04}

 25%|██▌       | 7127/28080 [14:05:08<41:11:37,  7.08s/it]
 25%|██▌       | 7128/28080 [14:05:15<41:15:57,  7.09s/it]
                                                          
{'loss': 0.6493, 'learning_rate': 0.0004371365121365205, 'epoch': 3.05}

 25%|██▌       | 7128/28080 [14:05:15<41:15:57,  7.09s/it]
 25%|██▌       | 7129/28080 [14:05:22<41:16:06,  7.09s/it]
                                                          
{'loss': 0.6559, 'learning_rate': 0.00043711739042981337, 'epoch': 3.05}

 25%|██▌       | 7129/28080 [14:05:22<41:16:06,  7.09s/it]
 25%|██▌       | 7130/28080 [14:05:29<41:13:37,  7.08s/it]
                                                          
{'loss': 0.6583, 'learning_rate': 0.0004370982662337024, 'epoch': 3.05}

 25%|██▌       | 7130/28080 [14:05:29<41:13:37,  7.08s/it]
 25%|██▌       | 7131/28080 [14:05:36<41:22:17,  7.11s/it]
                                                          
{'loss': 0.6495, 'learning_rate': 0.0004370791395484421, 'epoch': 3.05}

 25%|██▌       | 7131/28080 [14:05:36<41:22:17,  7.11s/it]
 25%|██▌       | 7132/28080 [14:05:43<41:18:57,  7.10s/it]
                                                          
{'loss': 0.6317, 'learning_rate': 0.0004370600103742868, 'epoch': 3.05}

 25%|██▌       | 7132/28080 [14:05:43<41:18:57,  7.10s/it]
 25%|██▌       | 7133/28080 [14:05:50<41:12:09,  7.08s/it]
                                                          
{'loss': 0.6204, 'learning_rate': 0.000437040878711491, 'epoch': 3.05}

 25%|██▌       | 7133/28080 [14:05:50<41:12:09,  7.08s/it]
 25%|██▌       | 7134/28080 [14:05:57<41:20:12,  7.10s/it]
                                                          
{'loss': 0.6214, 'learning_rate': 0.0004370217445603093, 'epoch': 3.05}

 25%|██▌       | 7134/28080 [14:05:57<41:20:12,  7.10s/it]
 25%|██▌       | 7135/28080 [14:06:05<41:24:41,  7.12s/it]
                                                          
{'loss': 0.6194, 'learning_rate': 0.00043700260792099623, 'epoch': 3.05}

 25%|██▌       | 7135/28080 [14:06:05<41:24:41,  7.12s/it]
 25%|██▌       | 7136/28080 [14:06:12<41:22:34,  7.11s/it]
                                                          
{'loss': 0.6395, 'learning_rate': 0.00043698346879380635, 'epoch': 3.05}

 25%|██▌       | 7136/28080 [14:06:12<41:22:34,  7.11s/it]
 25%|██▌       | 7137/28080 [14:06:19<41:21:41,  7.11s/it]
                                                          
{'loss': 0.6146, 'learning_rate': 0.00043696432717899437, 'epoch': 3.05}

 25%|██▌       | 7137/28080 [14:06:19<41:21:41,  7.11s/it]
 25%|██▌       | 7138/28080 [14:06:26<41:20:31,  7.11s/it]
                                                          
{'loss': 0.6512, 'learning_rate': 0.0004369451830768149, 'epoch': 3.05}

 25%|██▌       | 7138/28080 [14:06:26<41:20:31,  7.11s/it]
 25%|██▌       | 7139/28080 [14:06:33<41:21:59,  7.11s/it]
                                                          
{'loss': 0.6236, 'learning_rate': 0.0004369260364875226, 'epoch': 3.05}

 25%|██▌       | 7139/28080 [14:06:33<41:21:59,  7.11s/it]
 25%|██▌       | 7140/28080 [14:06:40<41:20:05,  7.11s/it]
                                                          
{'loss': 0.6312, 'learning_rate': 0.0004369068874113722, 'epoch': 3.05}

 25%|██▌       | 7140/28080 [14:06:40<41:20:05,  7.11s/it]
 25%|██▌       | 7141/28080 [14:06:47<41:12:49,  7.09s/it]
                                                          
{'loss': 0.639, 'learning_rate': 0.00043688773584861854, 'epoch': 3.05}

 25%|██▌       | 7141/28080 [14:06:47<41:12:49,  7.09s/it]
 25%|██▌       | 7142/28080 [14:06:54<41:09:14,  7.08s/it]
                                                          
{'loss': 0.6488, 'learning_rate': 0.00043686858179951637, 'epoch': 3.05}

 25%|██▌       | 7142/28080 [14:06:54<41:09:14,  7.08s/it]
 25%|██▌       | 7143/28080 [14:07:01<41:17:03,  7.10s/it]
                                                          
{'loss': 0.6412, 'learning_rate': 0.00043684942526432045, 'epoch': 3.05}

 25%|██▌       | 7143/28080 [14:07:01<41:17:03,  7.10s/it]
 25%|██▌       | 7144/28080 [14:07:08<41:25:17,  7.12s/it]
                                                          
{'loss': 0.6519, 'learning_rate': 0.0004368302662432857, 'epoch': 3.05}

 25%|██▌       | 7144/28080 [14:07:09<41:25:17,  7.12s/it]
 25%|██▌       | 7145/28080 [14:07:16<41:24:17,  7.12s/it]
                                                          
{'loss': 0.6433, 'learning_rate': 0.000436811104736667, 'epoch': 3.05}

 25%|██▌       | 7145/28080 [14:07:16<41:24:17,  7.12s/it]
 25%|██▌       | 7146/28080 [14:07:23<41:19:04,  7.11s/it]
                                                          
{'loss': 0.6429, 'learning_rate': 0.0004367919407447193, 'epoch': 3.05}

 25%|██▌       | 7146/28080 [14:07:23<41:19:04,  7.11s/it]
 25%|██▌       | 7147/28080 [14:07:30<41:20:40,  7.11s/it]
                                                          
{'loss': 0.6253, 'learning_rate': 0.00043677277426769747, 'epoch': 3.05}

 25%|██▌       | 7147/28080 [14:07:30<41:20:40,  7.11s/it]
 25%|██▌       | 7148/28080 [14:07:37<41:08:29,  7.08s/it]
                                                          
{'loss': 0.635, 'learning_rate': 0.0004367536053058566, 'epoch': 3.05}

 25%|██▌       | 7148/28080 [14:07:37<41:08:29,  7.08s/it]
 25%|██▌       | 7149/28080 [14:07:44<41:08:17,  7.08s/it]
                                                          
{'loss': 0.6178, 'learning_rate': 0.00043673443385945166, 'epoch': 3.05}

 25%|██▌       | 7149/28080 [14:07:44<41:08:17,  7.08s/it]
 25%|██▌       | 7150/28080 [14:07:51<41:08:47,  7.08s/it]
                                                          
{'loss': 0.6227, 'learning_rate': 0.0004367152599287377, 'epoch': 3.05}

 25%|██▌       | 7150/28080 [14:07:51<41:08:47,  7.08s/it]
 25%|██▌       | 7151/28080 [14:07:58<41:05:33,  7.07s/it]
                                                          
{'loss': 0.6488, 'learning_rate': 0.00043669608351396986, 'epoch': 3.05}

 25%|██▌       | 7151/28080 [14:07:58<41:05:33,  7.07s/it]
 25%|██▌       | 7152/28080 [14:08:05<41:00:45,  7.05s/it]
                                                          
{'loss': 0.6404, 'learning_rate': 0.00043667690461540325, 'epoch': 3.06}

 25%|██▌       | 7152/28080 [14:08:05<41:00:45,  7.05s/it]
 25%|██▌       | 7153/28080 [14:08:12<41:00:31,  7.05s/it]
                                                          
{'loss': 0.6302, 'learning_rate': 0.000436657723233293, 'epoch': 3.06}

 25%|██▌       | 7153/28080 [14:08:12<41:00:31,  7.05s/it]
 25%|██▌       | 7154/28080 [14:08:19<41:07:44,  7.08s/it]
                                                          
{'loss': 0.6126, 'learning_rate': 0.0004366385393678943, 'epoch': 3.06}

 25%|██▌       | 7154/28080 [14:08:19<41:07:44,  7.08s/it]
 25%|██▌       | 7155/28080 [14:08:26<41:11:22,  7.09s/it]
                                                          
{'loss': 0.6625, 'learning_rate': 0.0004366193530194624, 'epoch': 3.06}

 25%|██▌       | 7155/28080 [14:08:26<41:11:22,  7.09s/it]
 25%|██▌       | 7156/28080 [14:08:33<41:07:56,  7.08s/it]
                                                          
{'loss': 0.6544, 'learning_rate': 0.0004366001641882525, 'epoch': 3.06}

 25%|██▌       | 7156/28080 [14:08:33<41:07:56,  7.08s/it]
 25%|██▌       | 7157/28080 [14:08:41<41:16:26,  7.10s/it]
                                                          
{'loss': 0.6313, 'learning_rate': 0.00043658097287451993, 'epoch': 3.06}

 25%|██▌       | 7157/28080 [14:08:41<41:16:26,  7.10s/it]
 25%|██▌       | 7158/28080 [14:08:48<41:12:18,  7.09s/it]
                                                          
{'loss': 0.6511, 'learning_rate': 0.00043656177907852004, 'epoch': 3.06}

 25%|██▌       | 7158/28080 [14:08:48<41:12:18,  7.09s/it]
 25%|██▌       | 7159/28080 [14:08:55<41:16:58,  7.10s/it]
                                                          
{'loss': 0.6399, 'learning_rate': 0.00043654258280050804, 'epoch': 3.06}

 25%|██▌       | 7159/28080 [14:08:55<41:16:58,  7.10s/it]
 25%|██▌       | 7160/28080 [14:09:02<41:27:02,  7.13s/it]
                                                          
{'loss': 0.6231, 'learning_rate': 0.00043652338404073955, 'epoch': 3.06}

 25%|██▌       | 7160/28080 [14:09:02<41:27:02,  7.13s/it]
 26%|██▌       | 7161/28080 [14:09:09<41:21:04,  7.12s/it]
                                                          
{'loss': 0.6573, 'learning_rate': 0.0004365041827994698, 'epoch': 3.06}

 26%|██▌       | 7161/28080 [14:09:09<41:21:04,  7.12s/it]
 26%|██▌       | 7162/28080 [14:09:16<41:14:21,  7.10s/it]
                                                          
{'loss': 0.641, 'learning_rate': 0.0004364849790769543, 'epoch': 3.06}

 26%|██▌       | 7162/28080 [14:09:16<41:14:21,  7.10s/it]
 26%|██▌       | 7163/28080 [14:09:23<41:21:33,  7.12s/it]
                                                          
{'loss': 0.6592, 'learning_rate': 0.0004364657728734485, 'epoch': 3.06}

 26%|██▌       | 7163/28080 [14:09:23<41:21:33,  7.12s/it]
 26%|██▌       | 7164/28080 [14:09:30<41:16:21,  7.10s/it]
                                                          
{'loss': 0.6134, 'learning_rate': 0.00043644656418920805, 'epoch': 3.06}

 26%|██▌       | 7164/28080 [14:09:30<41:16:21,  7.10s/it]
 26%|██▌       | 7165/28080 [14:09:37<41:21:00,  7.12s/it]
                                                          
{'loss': 0.6604, 'learning_rate': 0.0004364273530244883, 'epoch': 3.06}

 26%|██▌       | 7165/28080 [14:09:37<41:21:00,  7.12s/it]
 26%|██▌       | 7166/28080 [14:09:45<41:16:34,  7.11s/it]
                                                          
{'loss': 0.6334, 'learning_rate': 0.00043640813937954507, 'epoch': 3.06}

 26%|██▌       | 7166/28080 [14:09:45<41:16:34,  7.11s/it]
 26%|██▌       | 7167/28080 [14:09:52<41:13:23,  7.10s/it]
                                                          
{'loss': 0.6427, 'learning_rate': 0.0004363889232546337, 'epoch': 3.06}

 26%|██▌       | 7167/28080 [14:09:52<41:13:23,  7.10s/it]
 26%|██▌       | 7168/28080 [14:09:59<41:18:58,  7.11s/it]
                                                          
{'loss': 0.6215, 'learning_rate': 0.00043636970465001014, 'epoch': 3.06}

 26%|██▌       | 7168/28080 [14:09:59<41:18:58,  7.11s/it]
 26%|██▌       | 7169/28080 [14:10:06<41:17:15,  7.11s/it]
                                                          
{'loss': 0.6283, 'learning_rate': 0.0004363504835659298, 'epoch': 3.06}

 26%|██▌       | 7169/28080 [14:10:06<41:17:15,  7.11s/it]
 26%|██▌       | 7170/28080 [14:10:13<41:16:52,  7.11s/it]
                                                          
{'loss': 0.6506, 'learning_rate': 0.0004363312600026486, 'epoch': 3.06}

 26%|██▌       | 7170/28080 [14:10:13<41:16:52,  7.11s/it]
 26%|██▌       | 7171/28080 [14:10:20<41:07:05,  7.08s/it]
                                                          
{'loss': 0.626, 'learning_rate': 0.0004363120339604222, 'epoch': 3.06}

 26%|██▌       | 7171/28080 [14:10:20<41:07:05,  7.08s/it]
 26%|██▌       | 7172/28080 [14:10:27<41:03:35,  7.07s/it]
                                                          
{'loss': 0.6269, 'learning_rate': 0.00043629280543950645, 'epoch': 3.06}

 26%|██▌       | 7172/28080 [14:10:27<41:03:35,  7.07s/it]
 26%|██▌       | 7173/28080 [14:10:34<41:14:29,  7.10s/it]
                                                          
{'loss': 0.6492, 'learning_rate': 0.00043627357444015705, 'epoch': 3.06}

 26%|██▌       | 7173/28080 [14:10:34<41:14:29,  7.10s/it]
 26%|██▌       | 7174/28080 [14:10:41<41:21:26,  7.12s/it]
                                                          
{'loss': 0.6289, 'learning_rate': 0.0004362543409626299, 'epoch': 3.06}

 26%|██▌       | 7174/28080 [14:10:41<41:21:26,  7.12s/it]
 26%|██▌       | 7175/28080 [14:10:48<41:16:33,  7.11s/it]
                                                          
{'loss': 0.6331, 'learning_rate': 0.0004362351050071809, 'epoch': 3.07}

 26%|██▌       | 7175/28080 [14:10:48<41:16:33,  7.11s/it]
 26%|██▌       | 7176/28080 [14:10:56<41:18:12,  7.11s/it]
                                                          
{'loss': 0.6376, 'learning_rate': 0.000436215866574066, 'epoch': 3.07}

 26%|██▌       | 7176/28080 [14:10:56<41:18:12,  7.11s/it]
 26%|██▌       | 7177/28080 [14:11:03<41:04:42,  7.07s/it]
                                                          
{'loss': 0.6491, 'learning_rate': 0.000436196625663541, 'epoch': 3.07}

 26%|██▌       | 7177/28080 [14:11:03<41:04:42,  7.07s/it]
 26%|██▌       | 7178/28080 [14:11:10<41:08:52,  7.09s/it]
                                                          
{'loss': 0.6639, 'learning_rate': 0.0004361773822758621, 'epoch': 3.07}

 26%|██▌       | 7178/28080 [14:11:10<41:08:52,  7.09s/it]
 26%|██▌       | 7179/28080 [14:11:17<41:10:38,  7.09s/it]
                                                          
{'loss': 0.6251, 'learning_rate': 0.0004361581364112851, 'epoch': 3.07}

 26%|██▌       | 7179/28080 [14:11:17<41:10:38,  7.09s/it]
 26%|██▌       | 7180/28080 [14:11:24<41:08:13,  7.09s/it]
                                                          
{'loss': 0.6283, 'learning_rate': 0.0004361388880700662, 'epoch': 3.07}

 26%|██▌       | 7180/28080 [14:11:24<41:08:13,  7.09s/it]
 26%|██▌       | 7181/28080 [14:11:31<41:15:26,  7.11s/it]
                                                          
{'loss': 0.6461, 'learning_rate': 0.0004361196372524614, 'epoch': 3.07}

 26%|██▌       | 7181/28080 [14:11:31<41:15:26,  7.11s/it]
 26%|██▌       | 7182/28080 [14:11:38<41:24:01,  7.13s/it]
                                                          
{'loss': 0.6539, 'learning_rate': 0.0004361003839587269, 'epoch': 3.07}

 26%|██▌       | 7182/28080 [14:11:38<41:24:01,  7.13s/it]
 26%|██▌       | 7183/28080 [14:11:45<41:09:53,  7.09s/it]
                                                          
{'loss': 0.6331, 'learning_rate': 0.0004360811281891187, 'epoch': 3.07}

 26%|██▌       | 7183/28080 [14:11:45<41:09:53,  7.09s/it]
 26%|██▌       | 7184/28080 [14:11:52<41:10:54,  7.09s/it]
                                                          
{'loss': 0.6399, 'learning_rate': 0.0004360618699438931, 'epoch': 3.07}

 26%|██▌       | 7184/28080 [14:11:52<41:10:54,  7.09s/it]
 26%|██▌       | 7185/28080 [14:11:59<41:15:40,  7.11s/it]
                                                          
{'loss': 0.6137, 'learning_rate': 0.0004360426092233063, 'epoch': 3.07}

 26%|██▌       | 7185/28080 [14:11:59<41:15:40,  7.11s/it]
 26%|██▌       | 7186/28080 [14:12:07<41:19:09,  7.12s/it]
                                                          
{'loss': 0.6382, 'learning_rate': 0.00043602334602761445, 'epoch': 3.07}

 26%|██▌       | 7186/28080 [14:12:07<41:19:09,  7.12s/it]
 26%|██▌       | 7187/28080 [14:12:14<41:08:19,  7.09s/it]
                                                          
{'loss': 0.651, 'learning_rate': 0.0004360040803570739, 'epoch': 3.07}

 26%|██▌       | 7187/28080 [14:12:14<41:08:19,  7.09s/it]
 26%|██▌       | 7188/28080 [14:12:21<41:03:21,  7.07s/it]
                                                          
{'loss': 0.6587, 'learning_rate': 0.000435984812211941, 'epoch': 3.07}

 26%|██▌       | 7188/28080 [14:12:21<41:03:21,  7.07s/it]
 26%|██▌       | 7189/28080 [14:12:28<41:00:49,  7.07s/it]
                                                          
{'loss': 0.6354, 'learning_rate': 0.000435965541592472, 'epoch': 3.07}

 26%|██▌       | 7189/28080 [14:12:28<41:00:49,  7.07s/it]
 26%|██▌       | 7190/28080 [14:12:35<41:00:12,  7.07s/it]
                                                          
{'loss': 0.6368, 'learning_rate': 0.0004359462684989233, 'epoch': 3.07}

 26%|██▌       | 7190/28080 [14:12:35<41:00:12,  7.07s/it]
 26%|██▌       | 7191/28080 [14:12:42<40:57:15,  7.06s/it]
                                                          
{'loss': 0.6462, 'learning_rate': 0.0004359269929315514, 'epoch': 3.07}

 26%|██▌       | 7191/28080 [14:12:42<40:57:15,  7.06s/it]
 26%|██▌       | 7192/28080 [14:12:49<40:58:36,  7.06s/it]
                                                          
{'loss': 0.6283, 'learning_rate': 0.00043590771489061255, 'epoch': 3.07}

 26%|██▌       | 7192/28080 [14:12:49<40:58:36,  7.06s/it]
 26%|██▌       | 7193/28080 [14:12:56<41:12:45,  7.10s/it]
                                                          
{'loss': 0.6465, 'learning_rate': 0.00043588843437636344, 'epoch': 3.07}

 26%|██▌       | 7193/28080 [14:12:56<41:12:45,  7.10s/it]
 26%|██▌       | 7194/28080 [14:13:03<41:14:06,  7.11s/it]
                                                          
{'loss': 0.6304, 'learning_rate': 0.0004358691513890605, 'epoch': 3.07}

 26%|██▌       | 7194/28080 [14:13:03<41:14:06,  7.11s/it]
 26%|██▌       | 7195/28080 [14:13:10<41:08:22,  7.09s/it]
                                                          
{'loss': 0.6319, 'learning_rate': 0.00043584986592896014, 'epoch': 3.07}

 26%|██▌       | 7195/28080 [14:13:10<41:08:22,  7.09s/it]
 26%|██▌       | 7196/28080 [14:13:17<41:14:00,  7.11s/it]
                                                          
{'loss': 0.653, 'learning_rate': 0.0004358305779963192, 'epoch': 3.07}

 26%|██▌       | 7196/28080 [14:13:17<41:14:00,  7.11s/it]
 26%|██▌       | 7197/28080 [14:13:24<41:08:55,  7.09s/it]
                                                          
{'loss': 0.6535, 'learning_rate': 0.000435811287591394, 'epoch': 3.07}

 26%|██▌       | 7197/28080 [14:13:24<41:08:55,  7.09s/it]
 26%|██▌       | 7198/28080 [14:13:31<41:00:22,  7.07s/it]
                                                          
{'loss': 0.6645, 'learning_rate': 0.00043579199471444134, 'epoch': 3.07}

 26%|██▌       | 7198/28080 [14:13:31<41:00:22,  7.07s/it]
 26%|██▌       | 7199/28080 [14:13:38<40:51:56,  7.05s/it]
                                                          
{'loss': 0.615, 'learning_rate': 0.00043577269936571786, 'epoch': 3.08}

 26%|██▌       | 7199/28080 [14:13:38<40:51:56,  7.05s/it]
 26%|██▌       | 7200/28080 [14:13:46<41:02:25,  7.08s/it]
                                                          
{'loss': 0.6261, 'learning_rate': 0.0004357534015454803, 'epoch': 3.08}

 26%|██▌       | 7200/28080 [14:13:46<41:02:25,  7.08s/it]
 26%|██▌       | 7201/28080 [14:13:53<41:10:56,  7.10s/it]
                                                          
{'loss': 0.643, 'learning_rate': 0.0004357341012539854, 'epoch': 3.08}

 26%|██▌       | 7201/28080 [14:13:53<41:10:56,  7.10s/it]
 26%|██▌       | 7202/28080 [14:14:00<41:13:29,  7.11s/it]
                                                          
{'loss': 0.6665, 'learning_rate': 0.00043571479849148975, 'epoch': 3.08}

 26%|██▌       | 7202/28080 [14:14:00<41:13:29,  7.11s/it]
 26%|██▌       | 7203/28080 [14:14:07<41:08:50,  7.10s/it]
                                                          
{'loss': 0.6295, 'learning_rate': 0.00043569549325825043, 'epoch': 3.08}

 26%|██▌       | 7203/28080 [14:14:07<41:08:50,  7.10s/it]
 26%|██▌       | 7204/28080 [14:14:14<41:09:26,  7.10s/it]
                                                          
{'loss': 0.6486, 'learning_rate': 0.0004356761855545241, 'epoch': 3.08}

 26%|██▌       | 7204/28080 [14:14:14<41:09:26,  7.10s/it]
 26%|██▌       | 7205/28080 [14:14:21<40:57:17,  7.06s/it]
                                                          
{'loss': 0.6418, 'learning_rate': 0.00043565687538056765, 'epoch': 3.08}

 26%|██▌       | 7205/28080 [14:14:21<40:57:17,  7.06s/it]
 26%|██▌       | 7206/28080 [14:14:28<40:58:59,  7.07s/it]
                                                          
{'loss': 0.6287, 'learning_rate': 0.00043563756273663805, 'epoch': 3.08}

 26%|██▌       | 7206/28080 [14:14:28<40:58:59,  7.07s/it]
 26%|██▌       | 7207/28080 [14:14:35<41:16:06,  7.12s/it]
                                                          
{'loss': 0.6398, 'learning_rate': 0.0004356182476229922, 'epoch': 3.08}

 26%|██▌       | 7207/28080 [14:14:35<41:16:06,  7.12s/it]
 26%|██▌       | 7208/28080 [14:14:42<41:07:09,  7.09s/it]
                                                          
{'loss': 0.6214, 'learning_rate': 0.00043559893003988705, 'epoch': 3.08}

 26%|██▌       | 7208/28080 [14:14:42<41:07:09,  7.09s/it]
 26%|██▌       | 7209/28080 [14:14:50<41:12:45,  7.11s/it]
                                                          
{'loss': 0.6323, 'learning_rate': 0.0004355796099875795, 'epoch': 3.08}

 26%|██▌       | 7209/28080 [14:14:50<41:12:45,  7.11s/it]
 26%|██▌       | 7210/28080 [14:14:57<41:08:57,  7.10s/it]
                                                          
{'loss': 0.6132, 'learning_rate': 0.0004355602874663268, 'epoch': 3.08}

 26%|██▌       | 7210/28080 [14:14:57<41:08:57,  7.10s/it]
 26%|██▌       | 7211/28080 [14:15:04<41:14:45,  7.12s/it]
                                                          
{'loss': 0.6292, 'learning_rate': 0.00043554096247638586, 'epoch': 3.08}

 26%|██▌       | 7211/28080 [14:15:04<41:14:45,  7.12s/it]
 26%|██▌       | 7212/28080 [14:15:11<41:14:34,  7.11s/it]
                                                          
{'loss': 0.6591, 'learning_rate': 0.0004355216350180139, 'epoch': 3.08}

 26%|██▌       | 7212/28080 [14:15:11<41:14:34,  7.11s/it]
 26%|██▌       | 7213/28080 [14:15:18<41:12:44,  7.11s/it]
                                                          
{'loss': 0.6223, 'learning_rate': 0.00043550230509146787, 'epoch': 3.08}

 26%|██▌       | 7213/28080 [14:15:18<41:12:44,  7.11s/it]
 26%|██▌       | 7214/28080 [14:15:25<41:03:23,  7.08s/it]
                                                          
{'loss': 0.6489, 'learning_rate': 0.0004354829726970051, 'epoch': 3.08}

 26%|██▌       | 7214/28080 [14:15:25<41:03:23,  7.08s/it]
 26%|██▌       | 7215/28080 [14:15:32<41:01:42,  7.08s/it]
                                                          
{'loss': 0.631, 'learning_rate': 0.00043546363783488276, 'epoch': 3.08}

 26%|██▌       | 7215/28080 [14:15:32<41:01:42,  7.08s/it]
 26%|██▌       | 7216/28080 [14:15:39<41:03:05,  7.08s/it]
                                                          
{'loss': 0.6358, 'learning_rate': 0.000435444300505358, 'epoch': 3.08}

 26%|██▌       | 7216/28080 [14:15:39<41:03:05,  7.08s/it]
 26%|██▌       | 7217/28080 [14:15:46<41:03:28,  7.08s/it]
                                                          
{'loss': 0.6176, 'learning_rate': 0.0004354249607086882, 'epoch': 3.08}

 26%|██▌       | 7217/28080 [14:15:46<41:03:28,  7.08s/it]
 26%|██▌       | 7218/28080 [14:15:53<41:07:36,  7.10s/it]
                                                          
{'loss': 0.6431, 'learning_rate': 0.0004354056184451305, 'epoch': 3.08}

 26%|██▌       | 7218/28080 [14:15:53<41:07:36,  7.10s/it]
 26%|██▌       | 7219/28080 [14:16:00<41:10:35,  7.11s/it]
                                                          
{'loss': 0.6258, 'learning_rate': 0.0004353862737149424, 'epoch': 3.08}

 26%|██▌       | 7219/28080 [14:16:00<41:10:35,  7.11s/it]
 26%|██▌       | 7220/28080 [14:16:07<41:01:02,  7.08s/it]
                                                          
{'loss': 0.6593, 'learning_rate': 0.00043536692651838113, 'epoch': 3.08}

 26%|██▌       | 7220/28080 [14:16:07<41:01:02,  7.08s/it]
 26%|██▌       | 7221/28080 [14:16:15<41:05:02,  7.09s/it]
                                                          
{'loss': 0.6373, 'learning_rate': 0.00043534757685570415, 'epoch': 3.08}

 26%|██▌       | 7221/28080 [14:16:15<41:05:02,  7.09s/it]
 26%|██▌       | 7222/28080 [14:16:22<41:13:30,  7.12s/it]
                                                          
{'loss': 0.6277, 'learning_rate': 0.0004353282247271688, 'epoch': 3.09}

 26%|██▌       | 7222/28080 [14:16:22<41:13:30,  7.12s/it]
 26%|██▌       | 7223/28080 [14:16:29<41:13:30,  7.12s/it]
                                                          
{'loss': 0.6296, 'learning_rate': 0.0004353088701330327, 'epoch': 3.09}

 26%|██▌       | 7223/28080 [14:16:29<41:13:30,  7.12s/it]
 26%|██▌       | 7224/28080 [14:16:36<41:14:52,  7.12s/it]
                                                          
{'loss': 0.63, 'learning_rate': 0.00043528951307355326, 'epoch': 3.09}

 26%|██▌       | 7224/28080 [14:16:36<41:14:52,  7.12s/it]
 26%|██▌       | 7225/28080 [14:16:43<41:01:17,  7.08s/it]
                                                          
{'loss': 0.6401, 'learning_rate': 0.00043527015354898795, 'epoch': 3.09}

 26%|██▌       | 7225/28080 [14:16:43<41:01:17,  7.08s/it]
 26%|██▌       | 7226/28080 [14:16:50<41:00:55,  7.08s/it]
                                                          
{'loss': 0.6418, 'learning_rate': 0.00043525079155959444, 'epoch': 3.09}

 26%|██▌       | 7226/28080 [14:16:50<41:00:55,  7.08s/it]
 26%|██▌       | 7227/28080 [14:16:57<41:00:45,  7.08s/it]
                                                          
{'loss': 0.6335, 'learning_rate': 0.0004352314271056302, 'epoch': 3.09}

 26%|██▌       | 7227/28080 [14:16:57<41:00:45,  7.08s/it]
 26%|██▌       | 7228/28080 [14:17:04<40:57:32,  7.07s/it]
                                                          
{'loss': 0.6434, 'learning_rate': 0.00043521206018735297, 'epoch': 3.09}

 26%|██▌       | 7228/28080 [14:17:04<40:57:32,  7.07s/it]
 26%|██▌       | 7229/28080 [14:17:11<41:02:17,  7.09s/it]
                                                          
{'loss': 0.6283, 'learning_rate': 0.00043519269080502033, 'epoch': 3.09}

 26%|██▌       | 7229/28080 [14:17:11<41:02:17,  7.09s/it]
 26%|██▌       | 7230/28080 [14:17:18<40:56:29,  7.07s/it]
                                                          
{'loss': 0.6494, 'learning_rate': 0.00043517331895889, 'epoch': 3.09}

 26%|██▌       | 7230/28080 [14:17:18<40:56:29,  7.07s/it]
 26%|██▌       | 7231/28080 [14:17:25<40:57:40,  7.07s/it]
                                                          
{'loss': 0.6365, 'learning_rate': 0.00043515394464921966, 'epoch': 3.09}

 26%|██▌       | 7231/28080 [14:17:25<40:57:40,  7.07s/it]
 26%|██▌       | 7232/28080 [14:17:33<40:59:40,  7.08s/it]
                                                          
{'loss': 0.6579, 'learning_rate': 0.00043513456787626717, 'epoch': 3.09}

 26%|██▌       | 7232/28080 [14:17:33<40:59:40,  7.08s/it]
 26%|██▌       | 7233/28080 [14:17:40<41:04:12,  7.09s/it]
                                                          
{'loss': 0.6279, 'learning_rate': 0.0004351151886402902, 'epoch': 3.09}

 26%|██▌       | 7233/28080 [14:17:40<41:04:12,  7.09s/it]
 26%|██▌       | 7234/28080 [14:17:47<41:09:54,  7.11s/it]
                                                          
{'loss': 0.6555, 'learning_rate': 0.0004350958069415466, 'epoch': 3.09}

 26%|██▌       | 7234/28080 [14:17:47<41:09:54,  7.11s/it]
 26%|██▌       | 7235/28080 [14:17:54<41:00:54,  7.08s/it]
                                                          
{'loss': 0.6299, 'learning_rate': 0.00043507642278029423, 'epoch': 3.09}

 26%|██▌       | 7235/28080 [14:17:54<41:00:54,  7.08s/it]
 26%|██▌       | 7236/28080 [14:18:01<41:04:12,  7.09s/it]
                                                          
{'loss': 0.6459, 'learning_rate': 0.000435057036156791, 'epoch': 3.09}

 26%|██▌       | 7236/28080 [14:18:01<41:04:12,  7.09s/it]
 26%|██▌       | 7237/28080 [14:18:08<40:59:46,  7.08s/it]
                                                          
{'loss': 0.6469, 'learning_rate': 0.00043503764707129486, 'epoch': 3.09}

 26%|██▌       | 7237/28080 [14:18:08<40:59:46,  7.08s/it]
 26%|██▌       | 7238/28080 [14:18:15<40:59:04,  7.08s/it]
                                                          
{'loss': 0.6324, 'learning_rate': 0.00043501825552406373, 'epoch': 3.09}

 26%|██▌       | 7238/28080 [14:18:15<40:59:04,  7.08s/it]
 26%|██▌       | 7239/28080 [14:18:22<40:58:25,  7.08s/it]
                                                          
{'loss': 0.6279, 'learning_rate': 0.0004349988615153555, 'epoch': 3.09}

 26%|██▌       | 7239/28080 [14:18:22<40:58:25,  7.08s/it]
 26%|██▌       | 7240/28080 [14:18:29<41:07:52,  7.11s/it]
                                                          
{'loss': 0.6249, 'learning_rate': 0.00043497946504542827, 'epoch': 3.09}

 26%|██▌       | 7240/28080 [14:18:29<41:07:52,  7.11s/it]
 26%|██▌       | 7241/28080 [14:18:36<41:03:14,  7.09s/it]
                                                          
{'loss': 0.6537, 'learning_rate': 0.0004349600661145402, 'epoch': 3.09}

 26%|██▌       | 7241/28080 [14:18:36<41:03:14,  7.09s/it]
 26%|██▌       | 7242/28080 [14:18:44<41:09:54,  7.11s/it]
                                                          
{'loss': 0.6302, 'learning_rate': 0.00043494066472294914, 'epoch': 3.09}

 26%|██▌       | 7242/28080 [14:18:44<41:09:54,  7.11s/it]
 26%|██▌       | 7243/28080 [14:18:51<41:12:41,  7.12s/it]
                                                          
{'loss': 0.6582, 'learning_rate': 0.0004349212608709134, 'epoch': 3.09}

 26%|██▌       | 7243/28080 [14:18:51<41:12:41,  7.12s/it]
 26%|██▌       | 7244/28080 [14:18:58<41:02:50,  7.09s/it]
                                                          
{'loss': 0.6352, 'learning_rate': 0.000434901854558691, 'epoch': 3.09}

 26%|██▌       | 7244/28080 [14:18:58<41:02:50,  7.09s/it]
 26%|██▌       | 7245/28080 [14:19:05<41:05:42,  7.10s/it]
                                                          
{'loss': 0.6345, 'learning_rate': 0.0004348824457865402, 'epoch': 3.09}

 26%|██▌       | 7245/28080 [14:19:05<41:05:42,  7.10s/it]
 26%|██▌       | 7246/28080 [14:19:12<41:07:56,  7.11s/it]
                                                          
{'loss': 0.6389, 'learning_rate': 0.00043486303455471934, 'epoch': 3.1}

 26%|██▌       | 7246/28080 [14:19:12<41:07:56,  7.11s/it]
 26%|██▌       | 7247/28080 [14:19:19<41:14:32,  7.13s/it]
                                                          
{'loss': 0.613, 'learning_rate': 0.00043484362086348635, 'epoch': 3.1}

 26%|██▌       | 7247/28080 [14:19:19<41:14:32,  7.13s/it]
 26%|██▌       | 7248/28080 [14:19:26<41:29:33,  7.17s/it]
                                                          
{'loss': 0.6493, 'learning_rate': 0.0004348242047130997, 'epoch': 3.1}

 26%|██▌       | 7248/28080 [14:19:26<41:29:33,  7.17s/it]
 26%|██▌       | 7249/28080 [14:19:34<41:27:19,  7.16s/it]
                                                          
{'loss': 0.6312, 'learning_rate': 0.0004348047861038177, 'epoch': 3.1}

 26%|██▌       | 7249/28080 [14:19:34<41:27:19,  7.16s/it]
 26%|██▌       | 7250/28080 [14:19:41<41:15:36,  7.13s/it]
                                                          
{'loss': 0.6331, 'learning_rate': 0.0004347853650358987, 'epoch': 3.1}

 26%|██▌       | 7250/28080 [14:19:41<41:15:36,  7.13s/it]
 26%|██▌       | 7251/28080 [14:19:48<41:17:34,  7.14s/it]
                                                          
{'loss': 0.6312, 'learning_rate': 0.00043476594150960096, 'epoch': 3.1}

 26%|██▌       | 7251/28080 [14:19:48<41:17:34,  7.14s/it]
 26%|██▌       | 7252/28080 [14:19:55<41:21:23,  7.15s/it]
                                                          
{'loss': 0.6284, 'learning_rate': 0.00043474651552518305, 'epoch': 3.1}

 26%|██▌       | 7252/28080 [14:19:55<41:21:23,  7.15s/it]
 26%|██▌       | 7253/28080 [14:20:02<41:17:57,  7.14s/it]
                                                          
{'loss': 0.6423, 'learning_rate': 0.0004347270870829033, 'epoch': 3.1}

 26%|██▌       | 7253/28080 [14:20:02<41:17:57,  7.14s/it]
 26%|██▌       | 7254/28080 [14:20:09<41:13:22,  7.13s/it]
                                                          
{'loss': 0.6419, 'learning_rate': 0.00043470765618302035, 'epoch': 3.1}

 26%|██▌       | 7254/28080 [14:20:09<41:13:22,  7.13s/it]
 26%|██▌       | 7255/28080 [14:20:16<41:03:21,  7.10s/it]
                                                          
{'loss': 0.6429, 'learning_rate': 0.00043468822282579245, 'epoch': 3.1}

 26%|██▌       | 7255/28080 [14:20:16<41:03:21,  7.10s/it]
 26%|██▌       | 7256/28080 [14:20:23<40:58:14,  7.08s/it]
                                                          
{'loss': 0.62, 'learning_rate': 0.0004346687870114783, 'epoch': 3.1}

 26%|██▌       | 7256/28080 [14:20:23<40:58:14,  7.08s/it]
 26%|██▌       | 7257/28080 [14:20:30<41:07:27,  7.11s/it]
                                                          
{'loss': 0.6249, 'learning_rate': 0.00043464934874033653, 'epoch': 3.1}

 26%|██▌       | 7257/28080 [14:20:30<41:07:27,  7.11s/it]
 26%|██▌       | 7258/28080 [14:20:37<41:05:03,  7.10s/it]
                                                          
{'loss': 0.6387, 'learning_rate': 0.0004346299080126256, 'epoch': 3.1}

 26%|██▌       | 7258/28080 [14:20:37<41:05:03,  7.10s/it]
 26%|██▌       | 7259/28080 [14:20:45<41:01:11,  7.09s/it]
                                                          
{'loss': 0.63, 'learning_rate': 0.0004346104648286042, 'epoch': 3.1}

 26%|██▌       | 7259/28080 [14:20:45<41:01:11,  7.09s/it]
 26%|██▌       | 7260/28080 [14:20:52<41:00:58,  7.09s/it]
                                                          
{'loss': 0.6463, 'learning_rate': 0.00043459101918853104, 'epoch': 3.1}

 26%|██▌       | 7260/28080 [14:20:52<41:00:58,  7.09s/it]
 26%|██▌       | 7261/28080 [14:20:59<41:05:21,  7.11s/it]
                                                          
{'loss': 0.6487, 'learning_rate': 0.00043457157109266483, 'epoch': 3.1}

 26%|██▌       | 7261/28080 [14:20:59<41:05:21,  7.11s/it]
 26%|██▌       | 7262/28080 [14:21:06<40:55:26,  7.08s/it]
                                                          
{'loss': 0.6465, 'learning_rate': 0.00043455212054126425, 'epoch': 3.1}

 26%|██▌       | 7262/28080 [14:21:06<40:55:26,  7.08s/it]
 26%|██▌       | 7263/28080 [14:21:13<40:56:07,  7.08s/it]
                                                          
{'loss': 0.6351, 'learning_rate': 0.0004345326675345881, 'epoch': 3.1}

 26%|██▌       | 7263/28080 [14:21:13<40:56:07,  7.08s/it]
 26%|██▌       | 7264/28080 [14:21:20<40:55:36,  7.08s/it]
                                                          
{'loss': 0.6287, 'learning_rate': 0.0004345132120728952, 'epoch': 3.1}

 26%|██▌       | 7264/28080 [14:21:20<40:55:36,  7.08s/it]
 26%|██▌       | 7265/28080 [14:21:27<40:58:44,  7.09s/it]
                                                          
{'loss': 0.6125, 'learning_rate': 0.0004344937541564443, 'epoch': 3.1}

 26%|██▌       | 7265/28080 [14:21:27<40:58:44,  7.09s/it]
 26%|██▌       | 7266/28080 [14:21:34<41:08:48,  7.12s/it]
                                                          
{'loss': 0.6275, 'learning_rate': 0.00043447429378549443, 'epoch': 3.1}

 26%|██▌       | 7266/28080 [14:21:34<41:08:48,  7.12s/it]
 26%|██▌       | 7267/28080 [14:21:41<41:06:50,  7.11s/it]
                                                          
{'loss': 0.6639, 'learning_rate': 0.00043445483096030433, 'epoch': 3.1}

 26%|██▌       | 7267/28080 [14:21:41<41:06:50,  7.11s/it]
 26%|██▌       | 7268/28080 [14:21:48<41:08:41,  7.12s/it]
                                                          
{'loss': 0.6362, 'learning_rate': 0.00043443536568113305, 'epoch': 3.1}

 26%|██▌       | 7268/28080 [14:21:48<41:08:41,  7.12s/it]
 26%|██▌       | 7269/28080 [14:21:56<41:01:28,  7.10s/it]
                                                          
{'loss': 0.6214, 'learning_rate': 0.0004344158979482394, 'epoch': 3.11}

 26%|██▌       | 7269/28080 [14:21:56<41:01:28,  7.10s/it]
 26%|██▌       | 7270/28080 [14:22:03<41:05:11,  7.11s/it]
                                                          
{'loss': 0.6591, 'learning_rate': 0.0004343964277618826, 'epoch': 3.11}

 26%|██▌       | 7270/28080 [14:22:03<41:05:11,  7.11s/it]
 26%|██▌       | 7271/28080 [14:22:10<41:02:35,  7.10s/it]
                                                          
{'loss': 0.6446, 'learning_rate': 0.0004343769551223215, 'epoch': 3.11}

 26%|██▌       | 7271/28080 [14:22:10<41:02:35,  7.10s/it]
 26%|██▌       | 7272/28080 [14:22:17<41:00:56,  7.10s/it]
                                                          
{'loss': 0.6379, 'learning_rate': 0.00043435748002981523, 'epoch': 3.11}

 26%|██▌       | 7272/28080 [14:22:17<41:00:56,  7.10s/it]
 26%|██▌       | 7273/28080 [14:22:24<40:47:44,  7.06s/it]
                                                          
{'loss': 0.6294, 'learning_rate': 0.00043433800248462285, 'epoch': 3.11}

 26%|██▌       | 7273/28080 [14:22:24<40:47:44,  7.06s/it]
 26%|██▌       | 7274/28080 [14:22:31<40:42:31,  7.04s/it]
                                                          
{'loss': 0.6342, 'learning_rate': 0.00043431852248700353, 'epoch': 3.11}

 26%|██▌       | 7274/28080 [14:22:31<40:42:31,  7.04s/it]
 26%|██▌       | 7275/28080 [14:22:38<40:55:02,  7.08s/it]
                                                          
{'loss': 0.5941, 'learning_rate': 0.0004342990400372164, 'epoch': 3.11}

 26%|██▌       | 7275/28080 [14:22:38<40:55:02,  7.08s/it]
 26%|██▌       | 7276/28080 [14:22:45<40:55:19,  7.08s/it]
                                                          
{'loss': 0.6213, 'learning_rate': 0.00043427955513552076, 'epoch': 3.11}

 26%|██▌       | 7276/28080 [14:22:45<40:55:19,  7.08s/it]
 26%|██▌       | 7277/28080 [14:22:52<40:55:26,  7.08s/it]
                                                          
{'loss': 0.6404, 'learning_rate': 0.0004342600677821757, 'epoch': 3.11}

 26%|██▌       | 7277/28080 [14:22:52<40:55:26,  7.08s/it]
 26%|██▌       | 7278/28080 [14:22:59<40:54:51,  7.08s/it]
                                                          
{'loss': 0.6406, 'learning_rate': 0.00043424057797744056, 'epoch': 3.11}

 26%|██▌       | 7278/28080 [14:22:59<40:54:51,  7.08s/it]
 26%|██▌       | 7279/28080 [14:23:06<41:01:44,  7.10s/it]
                                                          
{'loss': 0.6499, 'learning_rate': 0.00043422108572157447, 'epoch': 3.11}

 26%|██▌       | 7279/28080 [14:23:06<41:01:44,  7.10s/it]
 26%|██▌       | 7280/28080 [14:23:13<40:51:23,  7.07s/it]
                                                          
{'loss': 0.6285, 'learning_rate': 0.000434201591014837, 'epoch': 3.11}

 26%|██▌       | 7280/28080 [14:23:13<40:51:23,  7.07s/it]
 26%|██▌       | 7281/28080 [14:23:20<40:53:02,  7.08s/it]
                                                          
{'loss': 0.6373, 'learning_rate': 0.0004341820938574874, 'epoch': 3.11}

 26%|██▌       | 7281/28080 [14:23:20<40:53:02,  7.08s/it]
 26%|██▌       | 7282/28080 [14:23:27<40:32:48,  7.02s/it]
                                                          
{'loss': 0.6524, 'learning_rate': 0.000434162594249785, 'epoch': 3.11}

 26%|██▌       | 7282/28080 [14:23:27<40:32:48,  7.02s/it]
 26%|██▌       | 7283/28080 [14:23:34<40:47:00,  7.06s/it]
                                                          
{'loss': 0.629, 'learning_rate': 0.00043414309219198935, 'epoch': 3.11}

 26%|██▌       | 7283/28080 [14:23:34<40:47:00,  7.06s/it]
 26%|██▌       | 7284/28080 [14:23:42<40:57:24,  7.09s/it]
                                                          
{'loss': 0.62, 'learning_rate': 0.00043412358768435974, 'epoch': 3.11}

 26%|██▌       | 7284/28080 [14:23:42<40:57:24,  7.09s/it]
 26%|██▌       | 7285/28080 [14:23:49<41:04:21,  7.11s/it]
                                                          
{'loss': 0.6158, 'learning_rate': 0.0004341040807271558, 'epoch': 3.11}

 26%|██▌       | 7285/28080 [14:23:49<41:04:21,  7.11s/it]
 26%|██▌       | 7286/28080 [14:23:56<41:08:15,  7.12s/it]
                                                          
{'loss': 0.6336, 'learning_rate': 0.00043408457132063696, 'epoch': 3.11}

 26%|██▌       | 7286/28080 [14:23:56<41:08:15,  7.12s/it]
 26%|██▌       | 7287/28080 [14:24:03<41:15:15,  7.14s/it]
                                                          
{'loss': 0.6617, 'learning_rate': 0.0004340650594650628, 'epoch': 3.11}

 26%|██▌       | 7287/28080 [14:24:03<41:15:15,  7.14s/it]
 26%|██▌       | 7288/28080 [14:24:10<41:16:16,  7.15s/it]
                                                          
{'loss': 0.6341, 'learning_rate': 0.00043404554516069294, 'epoch': 3.11}

 26%|██▌       | 7288/28080 [14:24:10<41:16:16,  7.15s/it]
 26%|██▌       | 7289/28080 [14:24:17<41:07:42,  7.12s/it]
                                                          
{'loss': 0.6252, 'learning_rate': 0.00043402602840778693, 'epoch': 3.11}

 26%|██▌       | 7289/28080 [14:24:17<41:07:42,  7.12s/it]
 26%|██▌       | 7290/28080 [14:24:24<41:04:02,  7.11s/it]
                                                          
{'loss': 0.6462, 'learning_rate': 0.0004340065092066046, 'epoch': 3.11}

 26%|██▌       | 7290/28080 [14:24:24<41:04:02,  7.11s/it]
 26%|██▌       | 7291/28080 [14:24:32<41:04:33,  7.11s/it]
                                                          
{'loss': 0.6105, 'learning_rate': 0.0004339869875574053, 'epoch': 3.11}

 26%|██▌       | 7291/28080 [14:24:32<41:04:33,  7.11s/it]
 26%|██▌       | 7292/28080 [14:24:39<40:50:53,  7.07s/it]
                                                          
{'loss': 0.6462, 'learning_rate': 0.000433967463460449, 'epoch': 3.12}

 26%|██▌       | 7292/28080 [14:24:39<40:50:53,  7.07s/it]
 26%|██▌       | 7293/28080 [14:24:46<40:55:35,  7.09s/it]
                                                          
{'loss': 0.6034, 'learning_rate': 0.0004339479369159954, 'epoch': 3.12}

 26%|██▌       | 7293/28080 [14:24:46<40:55:35,  7.09s/it]
 26%|██▌       | 7294/28080 [14:24:53<40:52:33,  7.08s/it]
                                                          
{'loss': 0.6361, 'learning_rate': 0.00043392840792430434, 'epoch': 3.12}

 26%|██▌       | 7294/28080 [14:24:53<40:52:33,  7.08s/it]
 26%|██▌       | 7295/28080 [14:25:00<40:55:04,  7.09s/it]
                                                          
{'loss': 0.6192, 'learning_rate': 0.0004339088764856355, 'epoch': 3.12}

 26%|██▌       | 7295/28080 [14:25:00<40:55:04,  7.09s/it]
 26%|██▌       | 7296/28080 [14:25:07<40:57:45,  7.10s/it]
                                                          
{'loss': 0.6269, 'learning_rate': 0.0004338893426002488, 'epoch': 3.12}

 26%|██▌       | 7296/28080 [14:25:07<40:57:45,  7.10s/it]
 26%|██▌       | 7297/28080 [14:25:14<40:59:53,  7.10s/it]
                                                          
{'loss': 0.6259, 'learning_rate': 0.0004338698062684041, 'epoch': 3.12}

 26%|██▌       | 7297/28080 [14:25:14<40:59:53,  7.10s/it]
 26%|██▌       | 7298/28080 [14:25:21<41:00:33,  7.10s/it]
                                                          
{'loss': 0.6213, 'learning_rate': 0.0004338502674903613, 'epoch': 3.12}

 26%|██▌       | 7298/28080 [14:25:21<41:00:33,  7.10s/it]
 26%|██▌       | 7299/28080 [14:25:28<40:39:59,  7.04s/it]
                                                          
{'loss': 0.6497, 'learning_rate': 0.00043383072626638043, 'epoch': 3.12}

 26%|██▌       | 7299/28080 [14:25:28<40:39:59,  7.04s/it]
 26%|██▌       | 7300/28080 [14:25:35<40:38:36,  7.04s/it]
                                                          
{'loss': 0.6462, 'learning_rate': 0.00043381118259672126, 'epoch': 3.12}

 26%|██▌       | 7300/28080 [14:25:35<40:38:36,  7.04s/it]
 26%|██▌       | 7301/28080 [14:25:42<40:44:59,  7.06s/it]
                                                          
{'loss': 0.6165, 'learning_rate': 0.000433791636481644, 'epoch': 3.12}

 26%|██▌       | 7301/28080 [14:25:42<40:44:59,  7.06s/it]
 26%|██▌       | 7302/28080 [14:25:49<40:43:25,  7.06s/it]
                                                          
{'loss': 0.6388, 'learning_rate': 0.00043377208792140867, 'epoch': 3.12}

 26%|██▌       | 7302/28080 [14:25:49<40:43:25,  7.06s/it]
 26%|██▌       | 7303/28080 [14:25:56<40:39:01,  7.04s/it]
                                                          
{'loss': 0.6606, 'learning_rate': 0.00043375253691627525, 'epoch': 3.12}

 26%|██▌       | 7303/28080 [14:25:56<40:39:01,  7.04s/it]
 26%|██▌       | 7304/28080 [14:26:03<40:48:50,  7.07s/it]
                                                          
{'loss': 0.656, 'learning_rate': 0.0004337329834665039, 'epoch': 3.12}

 26%|██▌       | 7304/28080 [14:26:03<40:48:50,  7.07s/it]
 26%|██▌       | 7305/28080 [14:26:11<40:57:53,  7.10s/it]
                                                          
{'loss': 0.6256, 'learning_rate': 0.00043371342757235476, 'epoch': 3.12}

 26%|██▌       | 7305/28080 [14:26:11<40:57:53,  7.10s/it]
 26%|██▌       | 7306/28080 [14:26:18<40:48:52,  7.07s/it]
                                                          
{'loss': 0.637, 'learning_rate': 0.00043369386923408805, 'epoch': 3.12}

 26%|██▌       | 7306/28080 [14:26:18<40:48:52,  7.07s/it]
 26%|██▌       | 7307/28080 [14:26:25<40:57:37,  7.10s/it]
                                                          
{'loss': 0.6483, 'learning_rate': 0.00043367430845196384, 'epoch': 3.12}

 26%|██▌       | 7307/28080 [14:26:25<40:57:37,  7.10s/it]
 26%|██▌       | 7308/28080 [14:26:32<40:48:25,  7.07s/it]
                                                          
{'loss': 0.6379, 'learning_rate': 0.00043365474522624243, 'epoch': 3.12}

 26%|██▌       | 7308/28080 [14:26:32<40:48:25,  7.07s/it]
 26%|██▌       | 7309/28080 [14:26:39<40:45:28,  7.06s/it]
                                                          
{'loss': 0.6493, 'learning_rate': 0.00043363517955718415, 'epoch': 3.12}

 26%|██▌       | 7309/28080 [14:26:39<40:45:28,  7.06s/it]
 26%|██▌       | 7310/28080 [14:26:46<40:38:23,  7.04s/it]
                                                          
{'loss': 0.6541, 'learning_rate': 0.00043361561144504926, 'epoch': 3.12}

 26%|██▌       | 7310/28080 [14:26:46<40:38:23,  7.04s/it]
 26%|██▌       | 7311/28080 [14:26:53<40:46:01,  7.07s/it]
                                                          
{'loss': 0.6305, 'learning_rate': 0.00043359604089009796, 'epoch': 3.12}

 26%|██▌       | 7311/28080 [14:26:53<40:46:01,  7.07s/it]
 26%|██▌       | 7312/28080 [14:27:00<40:36:01,  7.04s/it]
                                                          
{'loss': 0.621, 'learning_rate': 0.00043357646789259085, 'epoch': 3.12}

 26%|██▌       | 7312/28080 [14:27:00<40:36:01,  7.04s/it]
 26%|██▌       | 7313/28080 [14:27:07<40:35:50,  7.04s/it]
                                                          
{'loss': 0.6322, 'learning_rate': 0.00043355689245278825, 'epoch': 3.12}

 26%|██▌       | 7313/28080 [14:27:07<40:35:50,  7.04s/it]
 26%|██▌       | 7314/28080 [14:27:14<40:41:39,  7.05s/it]
                                                          
{'loss': 0.6428, 'learning_rate': 0.00043353731457095046, 'epoch': 3.12}

 26%|██▌       | 7314/28080 [14:27:14<40:41:39,  7.05s/it]
 26%|██▌       | 7315/28080 [14:27:21<40:43:31,  7.06s/it]
                                                          
{'loss': 0.6113, 'learning_rate': 0.00043351773424733813, 'epoch': 3.12}

 26%|██▌       | 7315/28080 [14:27:21<40:43:31,  7.06s/it]
 26%|██▌       | 7316/28080 [14:27:28<40:53:22,  7.09s/it]
                                                          
{'loss': 0.6484, 'learning_rate': 0.0004334981514822117, 'epoch': 3.13}

 26%|██▌       | 7316/28080 [14:27:28<40:53:22,  7.09s/it]
 26%|██▌       | 7317/28080 [14:27:35<40:47:28,  7.07s/it]
                                                          
{'loss': 0.643, 'learning_rate': 0.0004334785662758316, 'epoch': 3.13}

 26%|██▌       | 7317/28080 [14:27:35<40:47:28,  7.07s/it]
 26%|██▌       | 7318/28080 [14:27:42<40:48:31,  7.08s/it]
                                                          
{'loss': 0.6319, 'learning_rate': 0.00043345897862845844, 'epoch': 3.13}

 26%|██▌       | 7318/28080 [14:27:42<40:48:31,  7.08s/it]
 26%|██▌       | 7319/28080 [14:27:49<40:48:50,  7.08s/it]
                                                          
{'loss': 0.6455, 'learning_rate': 0.0004334393885403529, 'epoch': 3.13}

 26%|██▌       | 7319/28080 [14:27:49<40:48:50,  7.08s/it]
 26%|██▌       | 7320/28080 [14:27:57<40:57:01,  7.10s/it]
                                                          
{'loss': 0.6453, 'learning_rate': 0.00043341979601177553, 'epoch': 3.13}

 26%|██▌       | 7320/28080 [14:27:57<40:57:01,  7.10s/it]
 26%|██▌       | 7321/28080 [14:28:04<40:59:33,  7.11s/it]
                                                          
{'loss': 0.6311, 'learning_rate': 0.00043340020104298696, 'epoch': 3.13}

 26%|██▌       | 7321/28080 [14:28:04<40:59:33,  7.11s/it]
 26%|██▌       | 7322/28080 [14:28:11<40:52:46,  7.09s/it]
                                                          
{'loss': 0.6377, 'learning_rate': 0.0004333806036342479, 'epoch': 3.13}

 26%|██▌       | 7322/28080 [14:28:11<40:52:46,  7.09s/it]
 26%|██▌       | 7323/28080 [14:28:18<41:04:32,  7.12s/it]
                                                          
{'loss': 0.6204, 'learning_rate': 0.0004333610037858191, 'epoch': 3.13}

 26%|██▌       | 7323/28080 [14:28:18<41:04:32,  7.12s/it]
 26%|██▌       | 7324/28080 [14:28:25<41:00:34,  7.11s/it]
                                                          
{'loss': 0.635, 'learning_rate': 0.0004333414014979613, 'epoch': 3.13}

 26%|██▌       | 7324/28080 [14:28:25<41:00:34,  7.11s/it]
 26%|██▌       | 7325/28080 [14:28:32<40:54:03,  7.09s/it]
                                                          
{'loss': 0.621, 'learning_rate': 0.0004333217967709354, 'epoch': 3.13}

 26%|██▌       | 7325/28080 [14:28:32<40:54:03,  7.09s/it]
 26%|██▌       | 7326/28080 [14:28:39<40:54:55,  7.10s/it]
                                                          
{'loss': 0.6492, 'learning_rate': 0.000433302189605002, 'epoch': 3.13}

 26%|██▌       | 7326/28080 [14:28:39<40:54:55,  7.10s/it]
 26%|██▌       | 7327/28080 [14:28:46<40:57:29,  7.10s/it]
                                                          
{'loss': 0.6103, 'learning_rate': 0.0004332825800004221, 'epoch': 3.13}

 26%|██▌       | 7327/28080 [14:28:46<40:57:29,  7.10s/it]
 26%|██▌       | 7328/28080 [14:28:53<40:57:53,  7.11s/it]
                                                          
{'loss': 0.6491, 'learning_rate': 0.00043326296795745655, 'epoch': 3.13}

 26%|██▌       | 7328/28080 [14:28:53<40:57:53,  7.11s/it]
 26%|██▌       | 7329/28080 [14:29:01<40:57:36,  7.11s/it]
                                                          
{'loss': 0.6556, 'learning_rate': 0.0004332433534763663, 'epoch': 3.13}

 26%|██▌       | 7329/28080 [14:29:01<40:57:36,  7.11s/it]
 26%|██▌       | 7330/28080 [14:29:08<40:48:51,  7.08s/it]
                                                          
{'loss': 0.6224, 'learning_rate': 0.00043322373655741233, 'epoch': 3.13}

 26%|██▌       | 7330/28080 [14:29:08<40:48:51,  7.08s/it]
 26%|██▌       | 7331/28080 [14:29:15<40:50:58,  7.09s/it]
                                                          
{'loss': 0.6498, 'learning_rate': 0.0004332041172008555, 'epoch': 3.13}

 26%|██▌       | 7331/28080 [14:29:15<40:50:58,  7.09s/it]
 26%|██▌       | 7332/28080 [14:29:22<40:48:50,  7.08s/it]
                                                          
{'loss': 0.647, 'learning_rate': 0.00043318449540695686, 'epoch': 3.13}

 26%|██▌       | 7332/28080 [14:29:22<40:48:50,  7.08s/it]
 26%|██▌       | 7333/28080 [14:29:29<40:42:35,  7.06s/it]
                                                          
{'loss': 0.6445, 'learning_rate': 0.00043316487117597754, 'epoch': 3.13}

 26%|██▌       | 7333/28080 [14:29:29<40:42:35,  7.06s/it]
 26%|██▌       | 7334/28080 [14:29:36<40:44:36,  7.07s/it]
                                                          
{'loss': 0.6284, 'learning_rate': 0.00043314524450817853, 'epoch': 3.13}

 26%|██▌       | 7334/28080 [14:29:36<40:44:36,  7.07s/it]
 26%|██▌       | 7335/28080 [14:29:43<40:41:09,  7.06s/it]
                                                          
{'loss': 0.6428, 'learning_rate': 0.000433125615403821, 'epoch': 3.13}

 26%|██▌       | 7335/28080 [14:29:43<40:41:09,  7.06s/it]
 26%|██▌       | 7336/28080 [14:29:50<40:51:34,  7.09s/it]
                                                          
{'loss': 0.64, 'learning_rate': 0.00043310598386316616, 'epoch': 3.13}

 26%|██▌       | 7336/28080 [14:29:50<40:51:34,  7.09s/it]
 26%|██▌       | 7337/28080 [14:29:57<40:47:18,  7.08s/it]
                                                          
{'loss': 0.6527, 'learning_rate': 0.000433086349886475, 'epoch': 3.13}

 26%|██▌       | 7337/28080 [14:29:57<40:47:18,  7.08s/it]
 26%|██▌       | 7338/28080 [14:30:04<40:46:10,  7.08s/it]
                                                          
{'loss': 0.6337, 'learning_rate': 0.00043306671347400884, 'epoch': 3.13}

 26%|██▌       | 7338/28080 [14:30:04<40:46:10,  7.08s/it]
 26%|██▌       | 7339/28080 [14:30:11<40:42:41,  7.07s/it]
                                                          
{'loss': 0.6372, 'learning_rate': 0.00043304707462602887, 'epoch': 3.14}

 26%|██▌       | 7339/28080 [14:30:11<40:42:41,  7.07s/it]
 26%|██▌       | 7340/28080 [14:30:18<40:35:40,  7.05s/it]
                                                          
{'loss': 0.6363, 'learning_rate': 0.0004330274333427965, 'epoch': 3.14}

 26%|██▌       | 7340/28080 [14:30:18<40:35:40,  7.05s/it]
 26%|██▌       | 7341/28080 [14:30:25<40:37:13,  7.05s/it]
                                                          
{'loss': 0.6454, 'learning_rate': 0.000433007789624573, 'epoch': 3.14}

 26%|██▌       | 7341/28080 [14:30:25<40:37:13,  7.05s/it]
 26%|██▌       | 7342/28080 [14:30:32<40:41:43,  7.06s/it]
                                                          
{'loss': 0.6354, 'learning_rate': 0.00043298814347161955, 'epoch': 3.14}

 26%|██▌       | 7342/28080 [14:30:32<40:41:43,  7.06s/it]
 26%|██▌       | 7343/28080 [14:30:39<40:45:27,  7.08s/it]
                                                          
{'loss': 0.6235, 'learning_rate': 0.00043296849488419763, 'epoch': 3.14}

 26%|██▌       | 7343/28080 [14:30:40<40:45:27,  7.08s/it]
 26%|██▌       | 7344/28080 [14:30:47<40:42:38,  7.07s/it]
                                                          
{'loss': 0.6507, 'learning_rate': 0.00043294884386256875, 'epoch': 3.14}

 26%|██▌       | 7344/28080 [14:30:47<40:42:38,  7.07s/it]
 26%|██▌       | 7345/28080 [14:30:54<40:40:03,  7.06s/it]
                                                          
{'loss': 0.65, 'learning_rate': 0.00043292919040699413, 'epoch': 3.14}

 26%|██▌       | 7345/28080 [14:30:54<40:40:03,  7.06s/it]
 26%|██▌       | 7346/28080 [14:31:01<40:52:06,  7.10s/it]
                                                          
{'loss': 0.6411, 'learning_rate': 0.0004329095345177354, 'epoch': 3.14}

 26%|██▌       | 7346/28080 [14:31:01<40:52:06,  7.10s/it]
 26%|██▌       | 7347/28080 [14:31:08<40:54:13,  7.10s/it]
                                                          
{'loss': 0.6458, 'learning_rate': 0.000432889876195054, 'epoch': 3.14}

 26%|██▌       | 7347/28080 [14:31:08<40:54:13,  7.10s/it]
 26%|██▌       | 7348/28080 [14:31:15<40:48:41,  7.09s/it]
                                                          
{'loss': 0.6462, 'learning_rate': 0.00043287021543921147, 'epoch': 3.14}

 26%|██▌       | 7348/28080 [14:31:15<40:48:41,  7.09s/it]
 26%|██▌       | 7349/28080 [14:31:22<41:04:22,  7.13s/it]
                                                          
{'loss': 0.6464, 'learning_rate': 0.0004328505522504694, 'epoch': 3.14}

 26%|██▌       | 7349/28080 [14:31:22<41:04:22,  7.13s/it]
 26%|██▌       | 7350/28080 [14:31:29<40:54:17,  7.10s/it]
                                                          
{'loss': 0.6587, 'learning_rate': 0.0004328308866290893, 'epoch': 3.14}

 26%|██▌       | 7350/28080 [14:31:29<40:54:17,  7.10s/it]
 26%|██▌       | 7351/28080 [14:31:36<40:52:13,  7.10s/it]
                                                          
{'loss': 0.6368, 'learning_rate': 0.0004328112185753329, 'epoch': 3.14}

 26%|██▌       | 7351/28080 [14:31:36<40:52:13,  7.10s/it]
 26%|██▌       | 7352/28080 [14:31:43<40:41:58,  7.07s/it]
                                                          
{'loss': 0.6283, 'learning_rate': 0.00043279154808946186, 'epoch': 3.14}

 26%|██▌       | 7352/28080 [14:31:43<40:41:58,  7.07s/it]
 26%|██▌       | 7353/28080 [14:31:50<40:40:47,  7.07s/it]
                                                          
{'loss': 0.6549, 'learning_rate': 0.0004327718751717379, 'epoch': 3.14}

 26%|██▌       | 7353/28080 [14:31:50<40:40:47,  7.07s/it]
 26%|██▌       | 7354/28080 [14:31:57<40:37:22,  7.06s/it]
                                                          
{'loss': 0.6084, 'learning_rate': 0.00043275219982242267, 'epoch': 3.14}

 26%|██▌       | 7354/28080 [14:31:57<40:37:22,  7.06s/it]
 26%|██▌       | 7355/28080 [14:32:04<40:32:24,  7.04s/it]
                                                          
{'loss': 0.6251, 'learning_rate': 0.0004327325220417779, 'epoch': 3.14}

 26%|██▌       | 7355/28080 [14:32:04<40:32:24,  7.04s/it]
 26%|██▌       | 7356/28080 [14:32:11<40:36:55,  7.06s/it]
                                                          
{'loss': 0.6272, 'learning_rate': 0.00043271284183006543, 'epoch': 3.14}

 26%|██▌       | 7356/28080 [14:32:11<40:36:55,  7.06s/it]
 26%|██▌       | 7357/28080 [14:32:19<40:40:59,  7.07s/it]
                                                          
{'loss': 0.6446, 'learning_rate': 0.00043269315918754715, 'epoch': 3.14}

 26%|██▌       | 7357/28080 [14:32:19<40:40:59,  7.07s/it]
 26%|██▌       | 7358/28080 [14:32:26<40:46:40,  7.08s/it]
                                                          
{'loss': 0.6169, 'learning_rate': 0.0004326734741144848, 'epoch': 3.14}

 26%|██▌       | 7358/28080 [14:32:26<40:46:40,  7.08s/it]
 26%|██▌       | 7359/28080 [14:32:33<40:49:54,  7.09s/it]
                                                          
{'loss': 0.6763, 'learning_rate': 0.0004326537866111404, 'epoch': 3.14}

 26%|██▌       | 7359/28080 [14:32:33<40:49:54,  7.09s/it]
 26%|██▌       | 7360/28080 [14:32:40<40:57:02,  7.11s/it]
                                                          
{'loss': 0.6434, 'learning_rate': 0.00043263409667777575, 'epoch': 3.14}

 26%|██▌       | 7360/28080 [14:32:40<40:57:02,  7.11s/it]
 26%|██▌       | 7361/28080 [14:32:47<40:58:28,  7.12s/it]
                                                          
{'loss': 0.6145, 'learning_rate': 0.0004326144043146529, 'epoch': 3.14}

 26%|██▌       | 7361/28080 [14:32:47<40:58:28,  7.12s/it]
 26%|██▌       | 7362/28080 [14:32:54<40:44:02,  7.08s/it]
                                                          
{'loss': 0.6566, 'learning_rate': 0.00043259470952203375, 'epoch': 3.14}

 26%|██▌       | 7362/28080 [14:32:54<40:44:02,  7.08s/it]
 26%|██▌       | 7363/28080 [14:33:01<40:37:52,  7.06s/it]
                                                          
{'loss': 0.6323, 'learning_rate': 0.0004325750123001804, 'epoch': 3.15}

 26%|██▌       | 7363/28080 [14:33:01<40:37:52,  7.06s/it]
 26%|██▌       | 7364/28080 [14:33:08<40:36:17,  7.06s/it]
                                                          
{'loss': 0.6368, 'learning_rate': 0.0004325553126493548, 'epoch': 3.15}

 26%|██▌       | 7364/28080 [14:33:08<40:36:17,  7.06s/it]
 26%|██▌       | 7365/28080 [14:33:15<40:49:13,  7.09s/it]
                                                          
{'loss': 0.6421, 'learning_rate': 0.00043253561056981916, 'epoch': 3.15}

 26%|██▌       | 7365/28080 [14:33:15<40:49:13,  7.09s/it]
 26%|██▌       | 7366/28080 [14:33:22<40:48:50,  7.09s/it]
                                                          
{'loss': 0.6343, 'learning_rate': 0.00043251590606183555, 'epoch': 3.15}

 26%|██▌       | 7366/28080 [14:33:22<40:48:50,  7.09s/it]
 26%|██▌       | 7367/28080 [14:33:30<40:50:08,  7.10s/it]
                                                          
{'loss': 0.6637, 'learning_rate': 0.0004324961991256661, 'epoch': 3.15}

 26%|██▌       | 7367/28080 [14:33:30<40:50:08,  7.10s/it]
 26%|██▌       | 7368/28080 [14:33:37<41:01:02,  7.13s/it]
                                                          
{'loss': 0.6356, 'learning_rate': 0.00043247648976157293, 'epoch': 3.15}

 26%|██▌       | 7368/28080 [14:33:37<41:01:02,  7.13s/it]
 26%|██▌       | 7369/28080 [14:33:44<41:05:21,  7.14s/it]
                                                          
{'loss': 0.6203, 'learning_rate': 0.0004324567779698183, 'epoch': 3.15}

 26%|██▌       | 7369/28080 [14:33:44<41:05:21,  7.14s/it]
 26%|██▌       | 7370/28080 [14:33:51<40:57:09,  7.12s/it]
                                                          
{'loss': 0.6167, 'learning_rate': 0.00043243706375066456, 'epoch': 3.15}

 26%|██▌       | 7370/28080 [14:33:51<40:57:09,  7.12s/it]
 26%|██▋       | 7371/28080 [14:33:58<40:53:46,  7.11s/it]
                                                          
{'loss': 0.6281, 'learning_rate': 0.0004324173471043739, 'epoch': 3.15}

 26%|██▋       | 7371/28080 [14:33:58<40:53:46,  7.11s/it]
 26%|██▋       | 7372/28080 [14:34:05<41:00:13,  7.13s/it]
                                                          
{'loss': 0.6179, 'learning_rate': 0.00043239762803120853, 'epoch': 3.15}

 26%|██▋       | 7372/28080 [14:34:05<41:00:13,  7.13s/it]
 26%|██▋       | 7373/28080 [14:34:12<40:54:35,  7.11s/it]
                                                          
{'loss': 0.6267, 'learning_rate': 0.00043237790653143093, 'epoch': 3.15}

 26%|██▋       | 7373/28080 [14:34:12<40:54:35,  7.11s/it]
 26%|██▋       | 7374/28080 [14:34:19<40:52:55,  7.11s/it]
                                                          
{'loss': 0.637, 'learning_rate': 0.0004323581826053035, 'epoch': 3.15}

 26%|██▋       | 7374/28080 [14:34:19<40:52:55,  7.11s/it]
 26%|██▋       | 7375/28080 [14:34:26<40:49:12,  7.10s/it]
                                                          
{'loss': 0.6082, 'learning_rate': 0.0004323384562530884, 'epoch': 3.15}

 26%|██▋       | 7375/28080 [14:34:26<40:49:12,  7.10s/it]
 26%|██▋       | 7376/28080 [14:34:34<40:45:30,  7.09s/it]
                                                          
{'loss': 0.6355, 'learning_rate': 0.0004323187274750484, 'epoch': 3.15}

 26%|██▋       | 7376/28080 [14:34:34<40:45:30,  7.09s/it]
 26%|██▋       | 7377/28080 [14:34:41<40:44:13,  7.08s/it]
                                                          
{'loss': 0.6241, 'learning_rate': 0.0004322989962714458, 'epoch': 3.15}

 26%|██▋       | 7377/28080 [14:34:41<40:44:13,  7.08s/it]
 26%|██▋       | 7378/28080 [14:34:48<40:49:52,  7.10s/it]
                                                          
{'loss': 0.6201, 'learning_rate': 0.0004322792626425431, 'epoch': 3.15}

 26%|██▋       | 7378/28080 [14:34:48<40:49:52,  7.10s/it]
 26%|██▋       | 7379/28080 [14:34:55<40:42:55,  7.08s/it]
                                                          
{'loss': 0.6452, 'learning_rate': 0.0004322595265886029, 'epoch': 3.15}

 26%|██▋       | 7379/28080 [14:34:55<40:42:55,  7.08s/it]
 26%|██▋       | 7380/28080 [14:35:02<40:53:40,  7.11s/it]
                                                          
{'loss': 0.6083, 'learning_rate': 0.00043223978810988763, 'epoch': 3.15}

 26%|██▋       | 7380/28080 [14:35:02<40:53:40,  7.11s/it]
 26%|██▋       | 7381/28080 [14:35:09<40:48:14,  7.10s/it]
                                                          
{'loss': 0.6662, 'learning_rate': 0.0004322200472066601, 'epoch': 3.15}

 26%|██▋       | 7381/28080 [14:35:09<40:48:14,  7.10s/it]
 26%|██▋       | 7382/28080 [14:35:16<40:45:39,  7.09s/it]
                                                          
{'loss': 0.6233, 'learning_rate': 0.00043220030387918276, 'epoch': 3.15}

 26%|██▋       | 7382/28080 [14:35:16<40:45:39,  7.09s/it]
 26%|██▋       | 7383/28080 [14:35:23<40:47:56,  7.10s/it]
                                                          
{'loss': 0.6382, 'learning_rate': 0.0004321805581277183, 'epoch': 3.15}

 26%|██▋       | 7383/28080 [14:35:23<40:47:56,  7.10s/it]
 26%|██▋       | 7384/28080 [14:35:30<40:43:10,  7.08s/it]
                                                          
{'loss': 0.6395, 'learning_rate': 0.00043216080995252953, 'epoch': 3.15}

 26%|██▋       | 7384/28080 [14:35:30<40:43:10,  7.08s/it]
 26%|██▋       | 7385/28080 [14:35:37<40:44:30,  7.09s/it]
                                                          
{'loss': 0.6626, 'learning_rate': 0.0004321410593538791, 'epoch': 3.15}

 26%|██▋       | 7385/28080 [14:35:37<40:44:30,  7.09s/it]
 26%|██▋       | 7386/28080 [14:35:44<40:44:52,  7.09s/it]
                                                          
{'loss': 0.6213, 'learning_rate': 0.0004321213063320297, 'epoch': 3.16}

 26%|██▋       | 7386/28080 [14:35:44<40:44:52,  7.09s/it]
 26%|██▋       | 7387/28080 [14:35:52<40:49:19,  7.10s/it]
                                                          
{'loss': 0.6281, 'learning_rate': 0.00043210155088724435, 'epoch': 3.16}

 26%|██▋       | 7387/28080 [14:35:52<40:49:19,  7.10s/it]
 26%|██▋       | 7388/28080 [14:35:59<40:47:17,  7.10s/it]
                                                          
{'loss': 0.6338, 'learning_rate': 0.0004320817930197856, 'epoch': 3.16}

 26%|██▋       | 7388/28080 [14:35:59<40:47:17,  7.10s/it]
 26%|██▋       | 7389/28080 [14:36:06<40:46:06,  7.09s/it]
                                                          
{'loss': 0.6254, 'learning_rate': 0.0004320620327299165, 'epoch': 3.16}

 26%|██▋       | 7389/28080 [14:36:06<40:46:06,  7.09s/it]
 26%|██▋       | 7390/28080 [14:36:13<40:36:37,  7.07s/it]
                                                          
{'loss': 0.6485, 'learning_rate': 0.00043204227001789985, 'epoch': 3.16}

 26%|██▋       | 7390/28080 [14:36:13<40:36:37,  7.07s/it]
 26%|██▋       | 7391/28080 [14:36:20<40:35:25,  7.06s/it]
                                                          
{'loss': 0.6604, 'learning_rate': 0.0004320225048839987, 'epoch': 3.16}

 26%|██▋       | 7391/28080 [14:36:20<40:35:25,  7.06s/it]
 26%|██▋       | 7392/28080 [14:36:27<40:38:27,  7.07s/it]
                                                          
{'loss': 0.6411, 'learning_rate': 0.00043200273732847585, 'epoch': 3.16}

 26%|██▋       | 7392/28080 [14:36:27<40:38:27,  7.07s/it]
 26%|██▋       | 7393/28080 [14:36:34<40:56:32,  7.12s/it]
                                                          
{'loss': 0.6375, 'learning_rate': 0.00043198296735159425, 'epoch': 3.16}

 26%|██▋       | 7393/28080 [14:36:34<40:56:32,  7.12s/it]
 26%|██▋       | 7394/28080 [14:36:41<40:59:02,  7.13s/it]
                                                          
{'loss': 0.6277, 'learning_rate': 0.0004319631949536171, 'epoch': 3.16}

 26%|██▋       | 7394/28080 [14:36:41<40:59:02,  7.13s/it]
 26%|██▋       | 7395/28080 [14:36:48<40:50:46,  7.11s/it]
                                                          
{'loss': 0.6277, 'learning_rate': 0.0004319434201348073, 'epoch': 3.16}

 26%|██▋       | 7395/28080 [14:36:48<40:50:46,  7.11s/it]
 26%|██▋       | 7396/28080 [14:36:56<40:53:44,  7.12s/it]
                                                          
{'loss': 0.6218, 'learning_rate': 0.00043192364289542805, 'epoch': 3.16}

 26%|██▋       | 7396/28080 [14:36:56<40:53:44,  7.12s/it]
 26%|██▋       | 7397/28080 [14:37:03<40:59:18,  7.13s/it]
                                                          
{'loss': 0.644, 'learning_rate': 0.00043190386323574236, 'epoch': 3.16}

 26%|██▋       | 7397/28080 [14:37:03<40:59:18,  7.13s/it]
 26%|██▋       | 7398/28080 [14:37:10<40:58:11,  7.13s/it]
                                                          
{'loss': 0.6231, 'learning_rate': 0.0004318840811560135, 'epoch': 3.16}

 26%|██▋       | 7398/28080 [14:37:10<40:58:11,  7.13s/it]
 26%|██▋       | 7399/28080 [14:37:17<40:52:16,  7.11s/it]
                                                          
{'loss': 0.6441, 'learning_rate': 0.0004318642966565045, 'epoch': 3.16}

 26%|██▋       | 7399/28080 [14:37:17<40:52:16,  7.11s/it]
 26%|██▋       | 7400/28080 [14:37:24<40:50:44,  7.11s/it]
                                                          
{'loss': 0.6513, 'learning_rate': 0.0004318445097374787, 'epoch': 3.16}

 26%|██▋       | 7400/28080 [14:37:24<40:50:44,  7.11s/it]
 26%|██▋       | 7401/28080 [14:37:31<40:51:09,  7.11s/it]
                                                          
{'loss': 0.6411, 'learning_rate': 0.0004318247203991993, 'epoch': 3.16}

 26%|██▋       | 7401/28080 [14:37:31<40:51:09,  7.11s/it]
 26%|██▋       | 7402/28080 [14:37:38<40:57:49,  7.13s/it]
                                                          
{'loss': 0.6326, 'learning_rate': 0.00043180492864192956, 'epoch': 3.16}

 26%|██▋       | 7402/28080 [14:37:38<40:57:49,  7.13s/it]
 26%|██▋       | 7403/28080 [14:37:45<40:57:25,  7.13s/it]
                                                          
{'loss': 0.6231, 'learning_rate': 0.0004317851344659328, 'epoch': 3.16}

 26%|██▋       | 7403/28080 [14:37:45<40:57:25,  7.13s/it]
 26%|██▋       | 7404/28080 [14:37:53<40:57:33,  7.13s/it]
                                                          
{'loss': 0.6399, 'learning_rate': 0.0004317653378714724, 'epoch': 3.16}

 26%|██▋       | 7404/28080 [14:37:53<40:57:33,  7.13s/it]
 26%|██▋       | 7405/28080 [14:38:00<40:59:42,  7.14s/it]
                                                          
{'loss': 0.6401, 'learning_rate': 0.00043174553885881166, 'epoch': 3.16}

 26%|██▋       | 7405/28080 [14:38:00<40:59:42,  7.14s/it]
 26%|██▋       | 7406/28080 [14:38:07<41:00:57,  7.14s/it]
                                                          
{'loss': 0.618, 'learning_rate': 0.0004317257374282141, 'epoch': 3.16}

 26%|██▋       | 7406/28080 [14:38:07<41:00:57,  7.14s/it]
 26%|██▋       | 7407/28080 [14:38:14<40:55:40,  7.13s/it]
                                                          
{'loss': 0.648, 'learning_rate': 0.0004317059335799429, 'epoch': 3.16}

 26%|██▋       | 7407/28080 [14:38:14<40:55:40,  7.13s/it]
 26%|██▋       | 7408/28080 [14:38:21<40:48:50,  7.11s/it]
                                                          
{'loss': 0.639, 'learning_rate': 0.00043168612731426186, 'epoch': 3.16}

 26%|██▋       | 7408/28080 [14:38:21<40:48:50,  7.11s/it]
 26%|██▋       | 7409/28080 [14:38:28<40:51:32,  7.12s/it]
                                                          
{'loss': 0.6295, 'learning_rate': 0.0004316663186314343, 'epoch': 3.17}

 26%|██▋       | 7409/28080 [14:38:28<40:51:32,  7.12s/it]
 26%|██▋       | 7410/28080 [14:38:35<40:50:14,  7.11s/it]
                                                          
{'loss': 0.6072, 'learning_rate': 0.00043164650753172373, 'epoch': 3.17}

 26%|██▋       | 7410/28080 [14:38:35<40:50:14,  7.11s/it]
 26%|██▋       | 7411/28080 [14:38:42<40:54:35,  7.13s/it]
                                                          
{'loss': 0.6418, 'learning_rate': 0.0004316266940153939, 'epoch': 3.17}

 26%|██▋       | 7411/28080 [14:38:42<40:54:35,  7.13s/it]
 26%|██▋       | 7412/28080 [14:38:50<40:57:33,  7.13s/it]
                                                          
{'loss': 0.6567, 'learning_rate': 0.0004316068780827082, 'epoch': 3.17}

 26%|██▋       | 7412/28080 [14:38:50<40:57:33,  7.13s/it]
 26%|██▋       | 7413/28080 [14:38:57<40:52:49,  7.12s/it]
                                                          
{'loss': 0.6388, 'learning_rate': 0.0004315870597339303, 'epoch': 3.17}

 26%|██▋       | 7413/28080 [14:38:57<40:52:49,  7.12s/it]
 26%|██▋       | 7414/28080 [14:39:04<41:02:16,  7.15s/it]
                                                          
{'loss': 0.6421, 'learning_rate': 0.0004315672389693239, 'epoch': 3.17}

 26%|██▋       | 7414/28080 [14:39:04<41:02:16,  7.15s/it]
 26%|██▋       | 7415/28080 [14:39:11<40:48:14,  7.11s/it]
                                                          
{'loss': 0.6284, 'learning_rate': 0.0004315474157891528, 'epoch': 3.17}

 26%|██▋       | 7415/28080 [14:39:11<40:48:14,  7.11s/it]
 26%|██▋       | 7416/28080 [14:39:18<40:33:06,  7.06s/it]
                                                          
{'loss': 0.6565, 'learning_rate': 0.00043152759019368057, 'epoch': 3.17}

 26%|██▋       | 7416/28080 [14:39:18<40:33:06,  7.06s/it]
 26%|██▋       | 7417/28080 [14:39:25<40:38:30,  7.08s/it]
                                                          
{'loss': 0.6436, 'learning_rate': 0.000431507762183171, 'epoch': 3.17}

 26%|██▋       | 7417/28080 [14:39:25<40:38:30,  7.08s/it]
 26%|██▋       | 7418/28080 [14:39:32<40:36:59,  7.08s/it]
                                                          
{'loss': 0.6407, 'learning_rate': 0.0004314879317578879, 'epoch': 3.17}

 26%|██▋       | 7418/28080 [14:39:32<40:36:59,  7.08s/it]
 26%|██▋       | 7419/28080 [14:39:39<40:37:11,  7.08s/it]
                                                          
{'loss': 0.6337, 'learning_rate': 0.00043146809891809513, 'epoch': 3.17}

 26%|██▋       | 7419/28080 [14:39:39<40:37:11,  7.08s/it]
 26%|██▋       | 7420/28080 [14:39:46<40:53:32,  7.13s/it]
                                                          
{'loss': 0.6311, 'learning_rate': 0.00043144826366405654, 'epoch': 3.17}

 26%|██▋       | 7420/28080 [14:39:46<40:53:32,  7.13s/it]
 26%|██▋       | 7421/28080 [14:39:53<40:55:02,  7.13s/it]
                                                          
{'loss': 0.6358, 'learning_rate': 0.00043142842599603595, 'epoch': 3.17}

 26%|██▋       | 7421/28080 [14:39:53<40:55:02,  7.13s/it]
 26%|██▋       | 7422/28080 [14:40:01<40:54:32,  7.13s/it]
                                                          
{'loss': 0.6312, 'learning_rate': 0.0004314085859142973, 'epoch': 3.17}

 26%|██▋       | 7422/28080 [14:40:01<40:54:32,  7.13s/it]
 26%|██▋       | 7423/28080 [14:40:08<40:48:51,  7.11s/it]
                                                          
{'loss': 0.626, 'learning_rate': 0.0004313887434191046, 'epoch': 3.17}

 26%|██▋       | 7423/28080 [14:40:08<40:48:51,  7.11s/it]
 26%|██▋       | 7424/28080 [14:40:15<40:45:05,  7.10s/it]
                                                          
{'loss': 0.6317, 'learning_rate': 0.0004313688985107218, 'epoch': 3.17}

 26%|██▋       | 7424/28080 [14:40:15<40:45:05,  7.10s/it]
 26%|██▋       | 7425/28080 [14:40:22<40:46:02,  7.11s/it]
                                                          
{'loss': 0.6288, 'learning_rate': 0.0004313490511894129, 'epoch': 3.17}

 26%|██▋       | 7425/28080 [14:40:22<40:46:02,  7.11s/it]
 26%|██▋       | 7426/28080 [14:40:29<40:46:00,  7.11s/it]
                                                          
{'loss': 0.6318, 'learning_rate': 0.00043132920145544194, 'epoch': 3.17}

 26%|██▋       | 7426/28080 [14:40:29<40:46:00,  7.11s/it]
 26%|██▋       | 7427/28080 [14:40:36<40:39:55,  7.09s/it]
                                                          
{'loss': 0.6389, 'learning_rate': 0.00043130934930907304, 'epoch': 3.17}

 26%|██▋       | 7427/28080 [14:40:36<40:39:55,  7.09s/it]
 26%|██▋       | 7428/28080 [14:40:43<40:46:59,  7.11s/it]
                                                          
{'loss': 0.6589, 'learning_rate': 0.00043128949475057033, 'epoch': 3.17}

 26%|██▋       | 7428/28080 [14:40:43<40:46:59,  7.11s/it]
 26%|██▋       | 7429/28080 [14:40:50<40:54:39,  7.13s/it]
                                                          
{'loss': 0.6344, 'learning_rate': 0.00043126963778019787, 'epoch': 3.17}

 26%|██▋       | 7429/28080 [14:40:50<40:54:39,  7.13s/it]
 26%|██▋       | 7430/28080 [14:40:57<40:50:58,  7.12s/it]
                                                          
{'loss': 0.6421, 'learning_rate': 0.0004312497783982199, 'epoch': 3.17}

 26%|██▋       | 7430/28080 [14:40:57<40:50:58,  7.12s/it]
 26%|██▋       | 7431/28080 [14:41:05<40:55:12,  7.13s/it]
                                                          
{'loss': 0.6265, 'learning_rate': 0.00043122991660490064, 'epoch': 3.17}

 26%|██▋       | 7431/28080 [14:41:05<40:55:12,  7.13s/it]
 26%|██▋       | 7432/28080 [14:41:12<40:55:44,  7.14s/it]
                                                          
{'loss': 0.6196, 'learning_rate': 0.00043121005240050425, 'epoch': 3.17}

 26%|██▋       | 7432/28080 [14:41:12<40:55:44,  7.14s/it]
 26%|██▋       | 7433/28080 [14:41:19<41:03:05,  7.16s/it]
                                                          
{'loss': 0.6646, 'learning_rate': 0.0004311901857852951, 'epoch': 3.18}

 26%|██▋       | 7433/28080 [14:41:19<41:03:05,  7.16s/it]
 26%|██▋       | 7434/28080 [14:41:26<41:15:06,  7.19s/it]
                                                          
{'loss': 0.6377, 'learning_rate': 0.0004311703167595374, 'epoch': 3.18}

 26%|██▋       | 7434/28080 [14:41:26<41:15:06,  7.19s/it]
 26%|██▋       | 7435/28080 [14:41:33<41:12:32,  7.19s/it]
                                                          
{'loss': 0.6217, 'learning_rate': 0.00043115044532349557, 'epoch': 3.18}

 26%|██▋       | 7435/28080 [14:41:33<41:12:32,  7.19s/it]
 26%|██▋       | 7436/28080 [14:41:41<41:02:28,  7.16s/it]
                                                          
{'loss': 0.6422, 'learning_rate': 0.00043113057147743395, 'epoch': 3.18}

 26%|██▋       | 7436/28080 [14:41:41<41:02:28,  7.16s/it]
 26%|██▋       | 7437/28080 [14:41:48<40:51:03,  7.12s/it]
                                                          
{'loss': 0.6389, 'learning_rate': 0.00043111069522161694, 'epoch': 3.18}

 26%|██▋       | 7437/28080 [14:41:48<40:51:03,  7.12s/it]
 26%|██▋       | 7438/28080 [14:41:55<40:47:39,  7.11s/it]
                                                          
{'loss': 0.624, 'learning_rate': 0.00043109081655630897, 'epoch': 3.18}

 26%|██▋       | 7438/28080 [14:41:55<40:47:39,  7.11s/it]
 26%|██▋       | 7439/28080 [14:42:02<40:46:31,  7.11s/it]
                                                          
{'loss': 0.6707, 'learning_rate': 0.00043107093548177454, 'epoch': 3.18}

 26%|██▋       | 7439/28080 [14:42:02<40:46:31,  7.11s/it]
 26%|██▋       | 7440/28080 [14:42:09<40:36:33,  7.08s/it]
                                                          
{'loss': 0.6326, 'learning_rate': 0.0004310510519982781, 'epoch': 3.18}

 26%|██▋       | 7440/28080 [14:42:09<40:36:33,  7.08s/it]
 26%|██▋       | 7441/28080 [14:42:16<40:44:42,  7.11s/it]
                                                          
{'loss': 0.6341, 'learning_rate': 0.0004310311661060842, 'epoch': 3.18}

 26%|██▋       | 7441/28080 [14:42:16<40:44:42,  7.11s/it]
 27%|██▋       | 7442/28080 [14:42:23<40:54:57,  7.14s/it]
                                                          
{'loss': 0.6315, 'learning_rate': 0.0004310112778054574, 'epoch': 3.18}

 27%|██▋       | 7442/28080 [14:42:23<40:54:57,  7.14s/it]
 27%|██▋       | 7443/28080 [14:42:30<41:06:55,  7.17s/it]
                                                          
{'loss': 0.6516, 'learning_rate': 0.0004309913870966622, 'epoch': 3.18}

 27%|██▋       | 7443/28080 [14:42:30<41:06:55,  7.17s/it]
 27%|██▋       | 7444/28080 [14:42:38<41:12:23,  7.19s/it]
                                                          
{'loss': 0.6341, 'learning_rate': 0.00043097149397996337, 'epoch': 3.18}

 27%|██▋       | 7444/28080 [14:42:38<41:12:23,  7.19s/it]
 27%|██▋       | 7445/28080 [14:42:45<41:01:15,  7.16s/it]
                                                          
{'loss': 0.6324, 'learning_rate': 0.0004309515984556255, 'epoch': 3.18}

 27%|██▋       | 7445/28080 [14:42:45<41:01:15,  7.16s/it]
 27%|██▋       | 7446/28080 [14:42:52<40:55:25,  7.14s/it]
                                                          
{'loss': 0.6201, 'learning_rate': 0.0004309317005239133, 'epoch': 3.18}

 27%|██▋       | 7446/28080 [14:42:52<40:55:25,  7.14s/it]
 27%|██▋       | 7447/28080 [14:42:59<40:56:48,  7.14s/it]
                                                          
{'loss': 0.6367, 'learning_rate': 0.00043091180018509144, 'epoch': 3.18}

 27%|██▋       | 7447/28080 [14:42:59<40:56:48,  7.14s/it]
 27%|██▋       | 7448/28080 [14:43:06<40:49:08,  7.12s/it]
                                                          
{'loss': 0.6213, 'learning_rate': 0.0004308918974394248, 'epoch': 3.18}

 27%|██▋       | 7448/28080 [14:43:06<40:49:08,  7.12s/it]
 27%|██▋       | 7449/28080 [14:43:13<40:50:25,  7.13s/it]
                                                          
{'loss': 0.661, 'learning_rate': 0.00043087199228717803, 'epoch': 3.18}

 27%|██▋       | 7449/28080 [14:43:13<40:50:25,  7.13s/it]
 27%|██▋       | 7450/28080 [14:43:20<40:48:53,  7.12s/it]
                                                          
{'loss': 0.6456, 'learning_rate': 0.000430852084728616, 'epoch': 3.18}

 27%|██▋       | 7450/28080 [14:43:20<40:48:53,  7.12s/it]
 27%|██▋       | 7451/28080 [14:43:27<40:44:36,  7.11s/it]
                                                          
{'loss': 0.6427, 'learning_rate': 0.0004308321747640036, 'epoch': 3.18}

 27%|██▋       | 7451/28080 [14:43:27<40:44:36,  7.11s/it]
 27%|██▋       | 7452/28080 [14:43:35<40:54:13,  7.14s/it]
                                                          
{'loss': 0.6454, 'learning_rate': 0.0004308122623936056, 'epoch': 3.18}

 27%|██▋       | 7452/28080 [14:43:35<40:54:13,  7.14s/it]
 27%|██▋       | 7453/28080 [14:43:42<41:21:35,  7.22s/it]
                                                          
{'loss': 0.6214, 'learning_rate': 0.00043079234761768707, 'epoch': 3.18}

 27%|██▋       | 7453/28080 [14:43:42<41:21:35,  7.22s/it]
 27%|██▋       | 7454/28080 [14:43:49<41:08:06,  7.18s/it]
                                                          
{'loss': 0.6358, 'learning_rate': 0.0004307724304365128, 'epoch': 3.18}

 27%|██▋       | 7454/28080 [14:43:49<41:08:06,  7.18s/it]
 27%|██▋       | 7455/28080 [14:43:56<41:02:17,  7.16s/it]
                                                          
{'loss': 0.6436, 'learning_rate': 0.0004307525108503478, 'epoch': 3.18}

 27%|██▋       | 7455/28080 [14:43:56<41:02:17,  7.16s/it]
 27%|██▋       | 7456/28080 [14:44:03<40:53:32,  7.14s/it]
                                                          
{'loss': 0.6402, 'learning_rate': 0.0004307325888594572, 'epoch': 3.19}

 27%|██▋       | 7456/28080 [14:44:03<40:53:32,  7.14s/it]
 27%|██▋       | 7457/28080 [14:44:10<40:48:13,  7.12s/it]
                                                          
{'loss': 0.6205, 'learning_rate': 0.00043071266446410595, 'epoch': 3.19}

 27%|██▋       | 7457/28080 [14:44:10<40:48:13,  7.12s/it]
 27%|██▋       | 7458/28080 [14:44:17<40:34:08,  7.08s/it]
                                                          
{'loss': 0.6342, 'learning_rate': 0.0004306927376645591, 'epoch': 3.19}

 27%|██▋       | 7458/28080 [14:44:17<40:34:08,  7.08s/it]
 27%|██▋       | 7459/28080 [14:44:24<40:33:06,  7.08s/it]
                                                          
{'loss': 0.6266, 'learning_rate': 0.0004306728084610818, 'epoch': 3.19}

 27%|██▋       | 7459/28080 [14:44:24<40:33:06,  7.08s/it]
 27%|██▋       | 7460/28080 [14:44:32<40:35:58,  7.09s/it]
                                                          
{'loss': 0.638, 'learning_rate': 0.00043065287685393913, 'epoch': 3.19}

 27%|██▋       | 7460/28080 [14:44:32<40:35:58,  7.09s/it]
 27%|██▋       | 7461/28080 [14:44:39<40:37:11,  7.09s/it]
                                                          
{'loss': 0.6365, 'learning_rate': 0.0004306329428433963, 'epoch': 3.19}

 27%|██▋       | 7461/28080 [14:44:39<40:37:11,  7.09s/it]
 27%|██▋       | 7462/28080 [14:44:46<40:31:29,  7.08s/it]
                                                          
{'loss': 0.6351, 'learning_rate': 0.00043061300642971857, 'epoch': 3.19}

 27%|██▋       | 7462/28080 [14:44:46<40:31:29,  7.08s/it]
 27%|██▋       | 7463/28080 [14:44:53<40:34:46,  7.09s/it]
                                                          
{'loss': 0.6382, 'learning_rate': 0.0004305930676131711, 'epoch': 3.19}

 27%|██▋       | 7463/28080 [14:44:53<40:34:46,  7.09s/it]
 27%|██▋       | 7464/28080 [14:45:00<40:45:11,  7.12s/it]
                                                          
{'loss': 0.6244, 'learning_rate': 0.0004305731263940191, 'epoch': 3.19}

 27%|██▋       | 7464/28080 [14:45:00<40:45:11,  7.12s/it]
 27%|██▋       | 7465/28080 [14:45:07<40:44:04,  7.11s/it]
                                                          
{'loss': 0.6562, 'learning_rate': 0.0004305531827725281, 'epoch': 3.19}

 27%|██▋       | 7465/28080 [14:45:07<40:44:04,  7.11s/it]
 27%|██▋       | 7466/28080 [14:45:14<40:44:20,  7.11s/it]
                                                          
{'loss': 0.645, 'learning_rate': 0.0004305332367489632, 'epoch': 3.19}

 27%|██▋       | 7466/28080 [14:45:14<40:44:20,  7.11s/it]
 27%|██▋       | 7467/28080 [14:45:21<40:44:27,  7.12s/it]
                                                          
{'loss': 0.6462, 'learning_rate': 0.00043051328832358976, 'epoch': 3.19}

 27%|██▋       | 7467/28080 [14:45:21<40:44:27,  7.12s/it]
 27%|██▋       | 7468/28080 [14:45:28<40:47:31,  7.12s/it]
                                                          
{'loss': 0.6555, 'learning_rate': 0.0004304933374966733, 'epoch': 3.19}

 27%|██▋       | 7468/28080 [14:45:28<40:47:31,  7.12s/it]
 27%|██▋       | 7469/28080 [14:45:35<40:36:48,  7.09s/it]
                                                          
{'loss': 0.6582, 'learning_rate': 0.00043047338426847913, 'epoch': 3.19}

 27%|██▋       | 7469/28080 [14:45:35<40:36:48,  7.09s/it]
 27%|██▋       | 7470/28080 [14:45:43<40:37:42,  7.10s/it]
                                                          
{'loss': 0.634, 'learning_rate': 0.0004304534286392729, 'epoch': 3.19}

 27%|██▋       | 7470/28080 [14:45:43<40:37:42,  7.10s/it]
 27%|██▋       | 7471/28080 [14:45:50<40:40:30,  7.11s/it]
                                                          
{'loss': 0.6294, 'learning_rate': 0.0004304334706093199, 'epoch': 3.19}

 27%|██▋       | 7471/28080 [14:45:50<40:40:30,  7.11s/it]
 27%|██▋       | 7472/28080 [14:45:57<40:35:01,  7.09s/it]
                                                          
{'loss': 0.6593, 'learning_rate': 0.0004304135101788856, 'epoch': 3.19}

 27%|██▋       | 7472/28080 [14:45:57<40:35:01,  7.09s/it]
 27%|██▋       | 7473/28080 [14:46:04<40:46:58,  7.12s/it]
                                                          
{'loss': 0.6313, 'learning_rate': 0.00043039354734823585, 'epoch': 3.19}

 27%|██▋       | 7473/28080 [14:46:04<40:46:58,  7.12s/it]
 27%|██▋       | 7474/28080 [14:46:11<40:49:44,  7.13s/it]
                                                          
{'loss': 0.628, 'learning_rate': 0.00043037358211763595, 'epoch': 3.19}

 27%|██▋       | 7474/28080 [14:46:11<40:49:44,  7.13s/it]
 27%|██▋       | 7475/28080 [14:46:18<40:46:09,  7.12s/it]
                                                          
{'loss': 0.6521, 'learning_rate': 0.00043035361448735165, 'epoch': 3.19}

 27%|██▋       | 7475/28080 [14:46:18<40:46:09,  7.12s/it]
 27%|██▋       | 7476/28080 [14:46:25<40:51:14,  7.14s/it]
                                                          
{'loss': 0.6239, 'learning_rate': 0.00043033364445764857, 'epoch': 3.19}

 27%|██▋       | 7476/28080 [14:46:25<40:51:14,  7.14s/it]
 27%|██▋       | 7477/28080 [14:46:32<40:21:05,  7.05s/it]
                                                          
{'loss': 0.659, 'learning_rate': 0.00043031367202879235, 'epoch': 3.19}

 27%|██▋       | 7477/28080 [14:46:32<40:21:05,  7.05s/it]
 27%|██▋       | 7478/28080 [14:46:39<40:26:38,  7.07s/it]
                                                          
{'loss': 0.6259, 'learning_rate': 0.00043029369720104884, 'epoch': 3.19}

 27%|██▋       | 7478/28080 [14:46:39<40:26:38,  7.07s/it]
 27%|██▋       | 7479/28080 [14:46:46<40:26:02,  7.07s/it]
                                                          
{'loss': 0.619, 'learning_rate': 0.00043027371997468356, 'epoch': 3.19}

 27%|██▋       | 7479/28080 [14:46:46<40:26:02,  7.07s/it]
 27%|██▋       | 7480/28080 [14:46:54<40:30:24,  7.08s/it]
                                                          
{'loss': 0.6373, 'learning_rate': 0.0004302537403499625, 'epoch': 3.2}

 27%|██▋       | 7480/28080 [14:46:54<40:30:24,  7.08s/it]
 27%|██▋       | 7481/28080 [14:47:01<40:31:53,  7.08s/it]
                                                          
{'loss': 0.629, 'learning_rate': 0.00043023375832715137, 'epoch': 3.2}

 27%|██▋       | 7481/28080 [14:47:01<40:31:53,  7.08s/it]
 27%|██▋       | 7482/28080 [14:47:08<40:35:25,  7.09s/it]
                                                          
{'loss': 0.6543, 'learning_rate': 0.00043021377390651606, 'epoch': 3.2}

 27%|██▋       | 7482/28080 [14:47:08<40:35:25,  7.09s/it]
 27%|██▋       | 7483/28080 [14:47:15<40:39:30,  7.11s/it]
                                                          
{'loss': 0.6489, 'learning_rate': 0.00043019378708832235, 'epoch': 3.2}

 27%|██▋       | 7483/28080 [14:47:15<40:39:30,  7.11s/it]
 27%|██▋       | 7484/28080 [14:47:22<40:38:47,  7.10s/it]
                                                          
{'loss': 0.6151, 'learning_rate': 0.00043017379787283616, 'epoch': 3.2}

 27%|██▋       | 7484/28080 [14:47:22<40:38:47,  7.10s/it]
 27%|██▋       | 7485/28080 [14:47:29<40:29:34,  7.08s/it]
                                                          
{'loss': 0.6437, 'learning_rate': 0.00043015380626032355, 'epoch': 3.2}

 27%|██▋       | 7485/28080 [14:47:29<40:29:34,  7.08s/it]
 27%|██▋       | 7486/28080 [14:47:36<40:32:53,  7.09s/it]
                                                          
{'loss': 0.6356, 'learning_rate': 0.0004301338122510503, 'epoch': 3.2}

 27%|██▋       | 7486/28080 [14:47:36<40:32:53,  7.09s/it]
 27%|██▋       | 7487/28080 [14:47:43<40:37:24,  7.10s/it]
                                                          
{'loss': 0.5971, 'learning_rate': 0.00043011381584528264, 'epoch': 3.2}

 27%|██▋       | 7487/28080 [14:47:43<40:37:24,  7.10s/it]
 27%|██▋       | 7488/28080 [14:47:50<40:43:57,  7.12s/it]
                                                          
{'loss': 0.6486, 'learning_rate': 0.00043009381704328637, 'epoch': 3.2}

 27%|██▋       | 7488/28080 [14:47:50<40:43:57,  7.12s/it]
 27%|██▋       | 7489/28080 [14:47:57<40:39:56,  7.11s/it]
                                                          
{'loss': 0.6265, 'learning_rate': 0.00043007381584532766, 'epoch': 3.2}

 27%|██▋       | 7489/28080 [14:47:57<40:39:56,  7.11s/it]
 27%|██▋       | 7490/28080 [14:48:05<40:39:24,  7.11s/it]
                                                          
{'loss': 0.637, 'learning_rate': 0.00043005381225167267, 'epoch': 3.2}

 27%|██▋       | 7490/28080 [14:48:05<40:39:24,  7.11s/it]
 27%|██▋       | 7491/28080 [14:48:12<40:37:23,  7.10s/it]
                                                          
{'loss': 0.6402, 'learning_rate': 0.0004300338062625874, 'epoch': 3.2}

 27%|██▋       | 7491/28080 [14:48:12<40:37:23,  7.10s/it]
 27%|██▋       | 7492/28080 [14:48:19<40:13:23,  7.03s/it]
                                                          
{'loss': 0.6684, 'learning_rate': 0.00043001379787833814, 'epoch': 3.2}

 27%|██▋       | 7492/28080 [14:48:19<40:13:23,  7.03s/it]
 27%|██▋       | 7493/28080 [14:48:26<40:12:07,  7.03s/it]
                                                          
{'loss': 0.6423, 'learning_rate': 0.00042999378709919093, 'epoch': 3.2}

 27%|██▋       | 7493/28080 [14:48:26<40:12:07,  7.03s/it]
 27%|██▋       | 7494/28080 [14:48:33<40:09:33,  7.02s/it]
                                                          
{'loss': 0.6205, 'learning_rate': 0.00042997377392541214, 'epoch': 3.2}

 27%|██▋       | 7494/28080 [14:48:33<40:09:33,  7.02s/it]
 27%|██▋       | 7495/28080 [14:48:40<40:34:27,  7.10s/it]
                                                          
{'loss': 0.6173, 'learning_rate': 0.0004299537583572679, 'epoch': 3.2}

 27%|██▋       | 7495/28080 [14:48:40<40:34:27,  7.10s/it]
 27%|██▋       | 7496/28080 [14:48:47<40:21:45,  7.06s/it]
                                                          
{'loss': 0.637, 'learning_rate': 0.00042993374039502455, 'epoch': 3.2}

 27%|██▋       | 7496/28080 [14:48:47<40:21:45,  7.06s/it]
 27%|██▋       | 7497/28080 [14:48:54<40:28:54,  7.08s/it]
                                                          
{'loss': 0.6241, 'learning_rate': 0.00042991372003894847, 'epoch': 3.2}

 27%|██▋       | 7497/28080 [14:48:54<40:28:54,  7.08s/it]
 27%|██▋       | 7498/28080 [14:49:01<40:29:53,  7.08s/it]
                                                          
{'loss': 0.6571, 'learning_rate': 0.0004298936972893059, 'epoch': 3.2}

 27%|██▋       | 7498/28080 [14:49:01<40:29:53,  7.08s/it]
 27%|██▋       | 7499/28080 [14:49:08<40:26:00,  7.07s/it]
                                                          
{'loss': 0.6362, 'learning_rate': 0.0004298736721463633, 'epoch': 3.2}

 27%|██▋       | 7499/28080 [14:49:08<40:26:00,  7.07s/it]
 27%|██▋       | 7500/28080 [14:49:15<40:37:37,  7.11s/it]
                                                          
{'loss': 0.6611, 'learning_rate': 0.000429853644610387, 'epoch': 3.2}

 27%|██▋       | 7500/28080 [14:49:15<40:37:37,  7.11s/it]
 27%|██▋       | 7501/28080 [14:49:22<40:22:30,  7.06s/it]
                                                          
{'loss': 0.6326, 'learning_rate': 0.0004298336146816436, 'epoch': 3.2}

 27%|██▋       | 7501/28080 [14:49:22<40:22:30,  7.06s/it]
 27%|██▋       | 7502/28080 [14:49:29<40:23:10,  7.07s/it]
                                                          
{'loss': 0.6278, 'learning_rate': 0.00042981358236039946, 'epoch': 3.2}

 27%|██▋       | 7502/28080 [14:49:29<40:23:10,  7.07s/it]
 27%|██▋       | 7503/28080 [14:49:36<40:21:55,  7.06s/it]
                                                          
{'loss': 0.6426, 'learning_rate': 0.000429793547646921, 'epoch': 3.21}

 27%|██▋       | 7503/28080 [14:49:36<40:21:55,  7.06s/it]
 27%|██▋       | 7504/28080 [14:49:43<40:28:59,  7.08s/it]
                                                          
{'loss': 0.6371, 'learning_rate': 0.00042977351054147503, 'epoch': 3.21}

 27%|██▋       | 7504/28080 [14:49:43<40:28:59,  7.08s/it]
 27%|██▋       | 7505/28080 [14:49:51<40:33:26,  7.10s/it]
                                                          
{'loss': 0.6295, 'learning_rate': 0.0004297534710443279, 'epoch': 3.21}

 27%|██▋       | 7505/28080 [14:49:51<40:33:26,  7.10s/it]
 27%|██▋       | 7506/28080 [14:49:58<40:35:16,  7.10s/it]
                                                          
{'loss': 0.6459, 'learning_rate': 0.0004297334291557462, 'epoch': 3.21}

 27%|██▋       | 7506/28080 [14:49:58<40:35:16,  7.10s/it]
 27%|██▋       | 7507/28080 [14:50:05<40:39:45,  7.12s/it]
                                                          
{'loss': 0.6188, 'learning_rate': 0.00042971338487599677, 'epoch': 3.21}

 27%|██▋       | 7507/28080 [14:50:05<40:39:45,  7.12s/it]
 27%|██▋       | 7508/28080 [14:50:12<40:33:34,  7.10s/it]
                                                          
{'loss': 0.6524, 'learning_rate': 0.0004296933382053461, 'epoch': 3.21}

 27%|██▋       | 7508/28080 [14:50:12<40:33:34,  7.10s/it]
 27%|██▋       | 7509/28080 [14:50:19<40:31:17,  7.09s/it]
                                                          
{'loss': 0.6453, 'learning_rate': 0.0004296732891440609, 'epoch': 3.21}

 27%|██▋       | 7509/28080 [14:50:19<40:31:17,  7.09s/it]
 27%|██▋       | 7510/28080 [14:50:26<40:29:40,  7.09s/it]
                                                          
{'loss': 0.6124, 'learning_rate': 0.000429653237692408, 'epoch': 3.21}

 27%|██▋       | 7510/28080 [14:50:26<40:29:40,  7.09s/it]
 27%|██▋       | 7511/28080 [14:50:33<40:38:45,  7.11s/it]
                                                          
{'loss': 0.6456, 'learning_rate': 0.00042963318385065406, 'epoch': 3.21}

 27%|██▋       | 7511/28080 [14:50:33<40:38:45,  7.11s/it]
 27%|██▋       | 7512/28080 [14:50:40<40:38:17,  7.11s/it]
                                                          
{'loss': 0.6565, 'learning_rate': 0.000429613127619066, 'epoch': 3.21}

 27%|██▋       | 7512/28080 [14:50:40<40:38:17,  7.11s/it]
 27%|██▋       | 7513/28080 [14:50:47<40:33:30,  7.10s/it]
                                                          
{'loss': 0.6278, 'learning_rate': 0.0004295930689979105, 'epoch': 3.21}

 27%|██▋       | 7513/28080 [14:50:47<40:33:30,  7.10s/it]
 27%|██▋       | 7514/28080 [14:50:55<40:33:50,  7.10s/it]
                                                          
{'loss': 0.642, 'learning_rate': 0.0004295730079874546, 'epoch': 3.21}

 27%|██▋       | 7514/28080 [14:50:55<40:33:50,  7.10s/it]
 27%|██▋       | 7515/28080 [14:51:02<40:36:18,  7.11s/it]
                                                          
{'loss': 0.6261, 'learning_rate': 0.000429552944587965, 'epoch': 3.21}

 27%|██▋       | 7515/28080 [14:51:02<40:36:18,  7.11s/it]
 27%|██▋       | 7516/28080 [14:51:09<40:39:42,  7.12s/it]
                                                          
{'loss': 0.6395, 'learning_rate': 0.0004295328787997087, 'epoch': 3.21}

 27%|██▋       | 7516/28080 [14:51:09<40:39:42,  7.12s/it]
 27%|██▋       | 7517/28080 [14:51:16<40:36:49,  7.11s/it]
                                                          
{'loss': 0.6367, 'learning_rate': 0.00042951281062295266, 'epoch': 3.21}

 27%|██▋       | 7517/28080 [14:51:16<40:36:49,  7.11s/it]
 27%|██▋       | 7518/28080 [14:51:23<40:35:53,  7.11s/it]
                                                          
{'loss': 0.6387, 'learning_rate': 0.0004294927400579639, 'epoch': 3.21}

 27%|██▋       | 7518/28080 [14:51:23<40:35:53,  7.11s/it]
 27%|██▋       | 7519/28080 [14:51:30<40:29:02,  7.09s/it]
                                                          
{'loss': 0.6196, 'learning_rate': 0.00042947266710500944, 'epoch': 3.21}

 27%|██▋       | 7519/28080 [14:51:30<40:29:02,  7.09s/it]
 27%|██▋       | 7520/28080 [14:51:37<40:19:32,  7.06s/it]
                                                          
{'loss': 0.6259, 'learning_rate': 0.00042945259176435625, 'epoch': 3.21}

 27%|██▋       | 7520/28080 [14:51:37<40:19:32,  7.06s/it]
 27%|██▋       | 7521/28080 [14:51:44<40:22:59,  7.07s/it]
                                                          
{'loss': 0.623, 'learning_rate': 0.00042943251403627144, 'epoch': 3.21}

 27%|██▋       | 7521/28080 [14:51:44<40:22:59,  7.07s/it]
 27%|██▋       | 7522/28080 [14:51:51<40:22:11,  7.07s/it]
                                                          
{'loss': 0.6368, 'learning_rate': 0.00042941243392102216, 'epoch': 3.21}

 27%|██▋       | 7522/28080 [14:51:51<40:22:11,  7.07s/it]
 27%|██▋       | 7523/28080 [14:51:58<40:32:58,  7.10s/it]
                                                          
{'loss': 0.6311, 'learning_rate': 0.00042939235141887556, 'epoch': 3.21}

 27%|██▋       | 7523/28080 [14:51:58<40:32:58,  7.10s/it]
 27%|██▋       | 7524/28080 [14:52:06<40:40:39,  7.12s/it]
                                                          
{'loss': 0.6314, 'learning_rate': 0.00042937226653009874, 'epoch': 3.21}

 27%|██▋       | 7524/28080 [14:52:06<40:40:39,  7.12s/it]
 27%|██▋       | 7525/28080 [14:52:13<40:37:08,  7.11s/it]
                                                          
{'loss': 0.6255, 'learning_rate': 0.000429352179254959, 'epoch': 3.21}

 27%|██▋       | 7525/28080 [14:52:13<40:37:08,  7.11s/it]
 27%|██▋       | 7526/28080 [14:52:20<40:28:05,  7.09s/it]
                                                          
{'loss': 0.6419, 'learning_rate': 0.0004293320895937235, 'epoch': 3.22}

 27%|██▋       | 7526/28080 [14:52:20<40:28:05,  7.09s/it]
 27%|██▋       | 7527/28080 [14:52:27<40:28:54,  7.09s/it]
                                                          
{'loss': 0.6188, 'learning_rate': 0.0004293119975466596, 'epoch': 3.22}

 27%|██▋       | 7527/28080 [14:52:27<40:28:54,  7.09s/it]
 27%|██▋       | 7528/28080 [14:52:34<40:27:49,  7.09s/it]
                                                          
{'loss': 0.6457, 'learning_rate': 0.00042929190311403456, 'epoch': 3.22}

 27%|██▋       | 7528/28080 [14:52:34<40:27:49,  7.09s/it]
 27%|██▋       | 7529/28080 [14:52:41<40:29:24,  7.09s/it]
                                                          
{'loss': 0.6529, 'learning_rate': 0.0004292718062961157, 'epoch': 3.22}

 27%|██▋       | 7529/28080 [14:52:41<40:29:24,  7.09s/it]
 27%|██▋       | 7530/28080 [14:52:48<40:35:13,  7.11s/it]
                                                          
{'loss': 0.644, 'learning_rate': 0.00042925170709317043, 'epoch': 3.22}

 27%|██▋       | 7530/28080 [14:52:48<40:35:13,  7.11s/it]
 27%|██▋       | 7531/28080 [14:52:55<40:37:46,  7.12s/it]
                                                          
{'loss': 0.6406, 'learning_rate': 0.0004292316055054661, 'epoch': 3.22}

 27%|██▋       | 7531/28080 [14:52:55<40:37:46,  7.12s/it]
 27%|██▋       | 7532/28080 [14:53:02<40:30:21,  7.10s/it]
                                                          
{'loss': 0.6539, 'learning_rate': 0.00042921150153327014, 'epoch': 3.22}

 27%|██▋       | 7532/28080 [14:53:02<40:30:21,  7.10s/it]
 27%|██▋       | 7533/28080 [14:53:09<40:09:20,  7.04s/it]
                                                          
{'loss': 0.6685, 'learning_rate': 0.00042919139517685, 'epoch': 3.22}

 27%|██▋       | 7533/28080 [14:53:09<40:09:20,  7.04s/it]
 27%|██▋       | 7534/28080 [14:53:16<40:10:43,  7.04s/it]
                                                          
{'loss': 0.6476, 'learning_rate': 0.0004291712864364733, 'epoch': 3.22}

 27%|██▋       | 7534/28080 [14:53:16<40:10:43,  7.04s/it]
 27%|██▋       | 7535/28080 [14:53:23<40:27:47,  7.09s/it]
                                                          
{'loss': 0.6236, 'learning_rate': 0.00042915117531240745, 'epoch': 3.22}

 27%|██▋       | 7535/28080 [14:53:23<40:27:47,  7.09s/it]
 27%|██▋       | 7536/28080 [14:53:30<40:23:40,  7.08s/it]
                                                          
{'loss': 0.6577, 'learning_rate': 0.00042913106180492, 'epoch': 3.22}

 27%|██▋       | 7536/28080 [14:53:30<40:23:40,  7.08s/it]
 27%|██▋       | 7537/28080 [14:53:38<40:23:38,  7.08s/it]
                                                          
{'loss': 0.6169, 'learning_rate': 0.00042911094591427856, 'epoch': 3.22}

 27%|██▋       | 7537/28080 [14:53:38<40:23:38,  7.08s/it]
 27%|██▋       | 7538/28080 [14:53:45<40:29:01,  7.09s/it]
                                                          
{'loss': 0.6651, 'learning_rate': 0.00042909082764075083, 'epoch': 3.22}

 27%|██▋       | 7538/28080 [14:53:45<40:29:01,  7.09s/it]
 27%|██▋       | 7539/28080 [14:53:52<40:25:01,  7.08s/it]
                                                          
{'loss': 0.6369, 'learning_rate': 0.00042907070698460436, 'epoch': 3.22}

 27%|██▋       | 7539/28080 [14:53:52<40:25:01,  7.08s/it]
 27%|██▋       | 7540/28080 [14:53:59<40:29:54,  7.10s/it]
                                                          
{'loss': 0.6474, 'learning_rate': 0.00042905058394610685, 'epoch': 3.22}

 27%|██▋       | 7540/28080 [14:53:59<40:29:54,  7.10s/it]
 27%|██▋       | 7541/28080 [14:54:06<40:31:56,  7.10s/it]
                                                          
{'loss': 0.6435, 'learning_rate': 0.0004290304585255261, 'epoch': 3.22}

 27%|██▋       | 7541/28080 [14:54:06<40:31:56,  7.10s/it]
 27%|██▋       | 7542/28080 [14:54:13<40:37:58,  7.12s/it]
                                                          
{'loss': 0.6162, 'learning_rate': 0.0004290103307231297, 'epoch': 3.22}

 27%|██▋       | 7542/28080 [14:54:13<40:37:58,  7.12s/it]
 27%|██▋       | 7543/28080 [14:54:20<40:24:48,  7.08s/it]
                                                          
{'loss': 0.6333, 'learning_rate': 0.0004289902005391856, 'epoch': 3.22}

 27%|██▋       | 7543/28080 [14:54:20<40:24:48,  7.08s/it]
 27%|██▋       | 7544/28080 [14:54:27<40:21:42,  7.08s/it]
                                                          
{'loss': 0.629, 'learning_rate': 0.00042897006797396156, 'epoch': 3.22}

 27%|██▋       | 7544/28080 [14:54:27<40:21:42,  7.08s/it]
 27%|██▋       | 7545/28080 [14:54:34<40:09:11,  7.04s/it]
                                                          
{'loss': 0.6504, 'learning_rate': 0.00042894993302772526, 'epoch': 3.22}

 27%|██▋       | 7545/28080 [14:54:34<40:09:11,  7.04s/it]
 27%|██▋       | 7546/28080 [14:54:41<40:18:44,  7.07s/it]
                                                          
{'loss': 0.628, 'learning_rate': 0.0004289297957007448, 'epoch': 3.22}

 27%|██▋       | 7546/28080 [14:54:41<40:18:44,  7.07s/it]
 27%|██▋       | 7547/28080 [14:54:48<40:13:45,  7.05s/it]
                                                          
{'loss': 0.6205, 'learning_rate': 0.000428909655993288, 'epoch': 3.22}

 27%|██▋       | 7547/28080 [14:54:48<40:13:45,  7.05s/it]
 27%|██▋       | 7548/28080 [14:54:55<40:22:36,  7.08s/it]
                                                          
{'loss': 0.6217, 'learning_rate': 0.0004288895139056228, 'epoch': 3.22}

 27%|██▋       | 7548/28080 [14:54:55<40:22:36,  7.08s/it]
 27%|██▋       | 7549/28080 [14:55:03<40:40:50,  7.13s/it]
                                                          
{'loss': 0.6235, 'learning_rate': 0.0004288693694380172, 'epoch': 3.22}

 27%|██▋       | 7549/28080 [14:55:03<40:40:50,  7.13s/it]
 27%|██▋       | 7550/28080 [14:55:10<40:43:51,  7.14s/it]
                                                          
{'loss': 0.6511, 'learning_rate': 0.0004288492225907391, 'epoch': 3.23}

 27%|██▋       | 7550/28080 [14:55:10<40:43:51,  7.14s/it]
 27%|██▋       | 7551/28080 [14:55:17<40:38:38,  7.13s/it]
                                                          
{'loss': 0.6284, 'learning_rate': 0.0004288290733640566, 'epoch': 3.23}

 27%|██▋       | 7551/28080 [14:55:17<40:38:38,  7.13s/it]
 27%|██▋       | 7552/28080 [14:55:24<40:37:19,  7.12s/it]
                                                          
{'loss': 0.6335, 'learning_rate': 0.0004288089217582378, 'epoch': 3.23}

 27%|██▋       | 7552/28080 [14:55:24<40:37:19,  7.12s/it]
 27%|██▋       | 7553/28080 [14:55:31<40:30:55,  7.11s/it]
                                                          
{'loss': 0.6291, 'learning_rate': 0.0004287887677735508, 'epoch': 3.23}

 27%|██▋       | 7553/28080 [14:55:31<40:30:55,  7.11s/it]
 27%|██▋       | 7554/28080 [14:55:38<40:33:32,  7.11s/it]
                                                          
{'loss': 0.6387, 'learning_rate': 0.00042876861141026367, 'epoch': 3.23}

 27%|██▋       | 7554/28080 [14:55:38<40:33:32,  7.11s/it]
 27%|██▋       | 7555/28080 [14:55:45<40:35:49,  7.12s/it]
                                                          
{'loss': 0.6177, 'learning_rate': 0.0004287484526686446, 'epoch': 3.23}

 27%|██▋       | 7555/28080 [14:55:45<40:35:49,  7.12s/it]
 27%|██▋       | 7556/28080 [14:55:53<40:33:16,  7.11s/it]
                                                          
{'loss': 0.6392, 'learning_rate': 0.00042872829154896175, 'epoch': 3.23}

 27%|██▋       | 7556/28080 [14:55:53<40:33:16,  7.11s/it]
 27%|██▋       | 7557/28080 [14:56:00<40:27:44,  7.10s/it]
                                                          
{'loss': 0.6439, 'learning_rate': 0.0004287081280514834, 'epoch': 3.23}

 27%|██▋       | 7557/28080 [14:56:00<40:27:44,  7.10s/it]
 27%|██▋       | 7558/28080 [14:56:07<40:26:35,  7.09s/it]
                                                          
{'loss': 0.6308, 'learning_rate': 0.00042868796217647773, 'epoch': 3.23}

 27%|██▋       | 7558/28080 [14:56:07<40:26:35,  7.09s/it]
 27%|██▋       | 7559/28080 [14:56:14<40:16:28,  7.07s/it]
                                                          
{'loss': 0.6332, 'learning_rate': 0.0004286677939242131, 'epoch': 3.23}

 27%|██▋       | 7559/28080 [14:56:14<40:16:28,  7.07s/it]
 27%|██▋       | 7560/28080 [14:56:21<40:28:49,  7.10s/it]
                                                          
{'loss': 0.6309, 'learning_rate': 0.00042864762329495774, 'epoch': 3.23}

 27%|██▋       | 7560/28080 [14:56:21<40:28:49,  7.10s/it]
 27%|██▋       | 7561/28080 [14:56:28<40:21:01,  7.08s/it]
                                                          
{'loss': 0.6292, 'learning_rate': 0.00042862745028898004, 'epoch': 3.23}

 27%|██▋       | 7561/28080 [14:56:28<40:21:01,  7.08s/it]
 27%|██▋       | 7562/28080 [14:56:35<40:18:40,  7.07s/it]
                                                          
{'loss': 0.6427, 'learning_rate': 0.00042860727490654844, 'epoch': 3.23}

 27%|██▋       | 7562/28080 [14:56:35<40:18:40,  7.07s/it]
 27%|██▋       | 7563/28080 [14:56:42<40:11:34,  7.05s/it]
                                                          
{'loss': 0.662, 'learning_rate': 0.0004285870971479313, 'epoch': 3.23}

 27%|██▋       | 7563/28080 [14:56:42<40:11:34,  7.05s/it]
 27%|██▋       | 7564/28080 [14:56:49<40:10:09,  7.05s/it]
                                                          
{'loss': 0.6416, 'learning_rate': 0.000428566917013397, 'epoch': 3.23}

 27%|██▋       | 7564/28080 [14:56:49<40:10:09,  7.05s/it]
 27%|██▋       | 7565/28080 [14:56:56<40:16:52,  7.07s/it]
                                                          
{'loss': 0.6511, 'learning_rate': 0.00042854673450321424, 'epoch': 3.23}

 27%|██▋       | 7565/28080 [14:56:56<40:16:52,  7.07s/it]
 27%|██▋       | 7566/28080 [14:57:03<40:20:16,  7.08s/it]
                                                          
{'loss': 0.6275, 'learning_rate': 0.00042852654961765123, 'epoch': 3.23}

 27%|██▋       | 7566/28080 [14:57:03<40:20:16,  7.08s/it]
 27%|██▋       | 7567/28080 [14:57:10<40:20:17,  7.08s/it]
                                                          
{'loss': 0.6433, 'learning_rate': 0.0004285063623569767, 'epoch': 3.23}

 27%|██▋       | 7567/28080 [14:57:10<40:20:17,  7.08s/it]
 27%|██▋       | 7568/28080 [14:57:17<40:13:01,  7.06s/it]
                                                          
{'loss': 0.6325, 'learning_rate': 0.0004284861727214592, 'epoch': 3.23}

 27%|██▋       | 7568/28080 [14:57:17<40:13:01,  7.06s/it]
 27%|██▋       | 7569/28080 [14:57:24<40:14:55,  7.06s/it]
                                                          
{'loss': 0.6235, 'learning_rate': 0.0004284659807113673, 'epoch': 3.23}

 27%|██▋       | 7569/28080 [14:57:24<40:14:55,  7.06s/it]
 27%|██▋       | 7570/28080 [14:57:31<40:16:27,  7.07s/it]
                                                          
{'loss': 0.6369, 'learning_rate': 0.00042844578632696964, 'epoch': 3.23}

 27%|██▋       | 7570/28080 [14:57:31<40:16:27,  7.07s/it]
 27%|██▋       | 7571/28080 [14:57:38<40:11:49,  7.06s/it]
                                                          
{'loss': 0.6369, 'learning_rate': 0.00042842558956853485, 'epoch': 3.23}

 27%|██▋       | 7571/28080 [14:57:38<40:11:49,  7.06s/it]
 27%|██▋       | 7572/28080 [14:57:46<40:08:24,  7.05s/it]
                                                          
{'loss': 0.6413, 'learning_rate': 0.0004284053904363317, 'epoch': 3.23}

 27%|██▋       | 7572/28080 [14:57:46<40:08:24,  7.05s/it]
 27%|██▋       | 7573/28080 [14:57:53<40:05:15,  7.04s/it]
                                                          
{'loss': 0.6197, 'learning_rate': 0.00042838518893062883, 'epoch': 3.24}

 27%|██▋       | 7573/28080 [14:57:53<40:05:15,  7.04s/it]
 27%|██▋       | 7574/28080 [14:58:00<40:17:13,  7.07s/it]
                                                          
{'loss': 0.6203, 'learning_rate': 0.00042836498505169514, 'epoch': 3.24}

 27%|██▋       | 7574/28080 [14:58:00<40:17:13,  7.07s/it]
 27%|██▋       | 7575/28080 [14:58:07<40:18:38,  7.08s/it]
                                                          
{'loss': 0.6338, 'learning_rate': 0.00042834477879979927, 'epoch': 3.24}

 27%|██▋       | 7575/28080 [14:58:07<40:18:38,  7.08s/it]
 27%|██▋       | 7576/28080 [14:58:14<40:20:05,  7.08s/it]
                                                          
{'loss': 0.6315, 'learning_rate': 0.0004283245701752101, 'epoch': 3.24}

 27%|██▋       | 7576/28080 [14:58:14<40:20:05,  7.08s/it]
 27%|██▋       | 7577/28080 [14:58:21<40:23:47,  7.09s/it]
                                                          
{'loss': 0.6278, 'learning_rate': 0.0004283043591781965, 'epoch': 3.24}

 27%|██▋       | 7577/28080 [14:58:21<40:23:47,  7.09s/it]
 27%|██▋       | 7578/28080 [14:58:28<40:24:50,  7.10s/it]
                                                          
{'loss': 0.6327, 'learning_rate': 0.0004282841458090274, 'epoch': 3.24}

 27%|██▋       | 7578/28080 [14:58:28<40:24:50,  7.10s/it]
 27%|██▋       | 7579/28080 [14:58:35<40:20:27,  7.08s/it]
                                                          
{'loss': 0.6053, 'learning_rate': 0.0004282639300679716, 'epoch': 3.24}

 27%|██▋       | 7579/28080 [14:58:35<40:20:27,  7.08s/it]
 27%|██▋       | 7580/28080 [14:58:42<40:23:27,  7.09s/it]
                                                          
{'loss': 0.6229, 'learning_rate': 0.0004282437119552981, 'epoch': 3.24}

 27%|██▋       | 7580/28080 [14:58:42<40:23:27,  7.09s/it]
 27%|██▋       | 7581/28080 [14:58:49<40:27:59,  7.11s/it]
                                                          
{'loss': 0.6497, 'learning_rate': 0.00042822349147127593, 'epoch': 3.24}

 27%|██▋       | 7581/28080 [14:58:49<40:27:59,  7.11s/it]
 27%|██▋       | 7582/28080 [14:58:56<40:28:19,  7.11s/it]
                                                          
{'loss': 0.6289, 'learning_rate': 0.0004282032686161741, 'epoch': 3.24}

 27%|██▋       | 7582/28080 [14:58:57<40:28:19,  7.11s/it]
 27%|██▋       | 7583/28080 [14:59:04<40:30:12,  7.11s/it]
                                                          
{'loss': 0.6304, 'learning_rate': 0.0004281830433902616, 'epoch': 3.24}

 27%|██▋       | 7583/28080 [14:59:04<40:30:12,  7.11s/it]
 27%|██▋       | 7584/28080 [14:59:11<40:38:03,  7.14s/it]
                                                          
{'loss': 0.6224, 'learning_rate': 0.0004281628157938075, 'epoch': 3.24}

 27%|██▋       | 7584/28080 [14:59:11<40:38:03,  7.14s/it]
 27%|██▋       | 7585/28080 [14:59:18<40:50:39,  7.17s/it]
                                                          
{'loss': 0.623, 'learning_rate': 0.00042814258582708097, 'epoch': 3.24}

 27%|██▋       | 7585/28080 [14:59:18<40:50:39,  7.17s/it]
 27%|██▋       | 7586/28080 [14:59:25<40:41:04,  7.15s/it]
                                                          
{'loss': 0.6419, 'learning_rate': 0.0004281223534903511, 'epoch': 3.24}

 27%|██▋       | 7586/28080 [14:59:25<40:41:04,  7.15s/it]
 27%|██▋       | 7587/28080 [14:59:32<40:36:37,  7.13s/it]
                                                          
{'loss': 0.6303, 'learning_rate': 0.00042810211878388705, 'epoch': 3.24}

 27%|██▋       | 7587/28080 [14:59:32<40:36:37,  7.13s/it]
 27%|██▋       | 7588/28080 [14:59:39<40:43:02,  7.15s/it]
                                                          
{'loss': 0.6248, 'learning_rate': 0.0004280818817079581, 'epoch': 3.24}

 27%|██▋       | 7588/28080 [14:59:39<40:43:02,  7.15s/it]
 27%|██▋       | 7589/28080 [14:59:47<40:38:49,  7.14s/it]
                                                          
{'loss': 0.6268, 'learning_rate': 0.0004280616422628334, 'epoch': 3.24}

 27%|██▋       | 7589/28080 [14:59:47<40:38:49,  7.14s/it]
 27%|██▋       | 7590/28080 [14:59:54<40:24:50,  7.10s/it]
                                                          
{'loss': 0.6461, 'learning_rate': 0.00042804140044878225, 'epoch': 3.24}

 27%|██▋       | 7590/28080 [14:59:54<40:24:50,  7.10s/it]
 27%|██▋       | 7591/28080 [15:00:01<40:25:55,  7.10s/it]
                                                          
{'loss': 0.6521, 'learning_rate': 0.000428021156266074, 'epoch': 3.24}

 27%|██▋       | 7591/28080 [15:00:01<40:25:55,  7.10s/it]
 27%|██▋       | 7592/28080 [15:00:08<40:21:54,  7.09s/it]
                                                          
{'loss': 0.6299, 'learning_rate': 0.0004280009097149778, 'epoch': 3.24}

 27%|██▋       | 7592/28080 [15:00:08<40:21:54,  7.09s/it]
 27%|██▋       | 7593/28080 [15:00:15<40:21:56,  7.09s/it]
                                                          
{'loss': 0.6234, 'learning_rate': 0.0004279806607957633, 'epoch': 3.24}

 27%|██▋       | 7593/28080 [15:00:15<40:21:56,  7.09s/it]
 27%|██▋       | 7594/28080 [15:00:22<40:30:30,  7.12s/it]
                                                          
{'loss': 0.6259, 'learning_rate': 0.00042796040950869954, 'epoch': 3.24}

 27%|██▋       | 7594/28080 [15:00:22<40:30:30,  7.12s/it]
 27%|██▋       | 7595/28080 [15:00:29<40:15:13,  7.07s/it]
                                                          
{'loss': 0.6443, 'learning_rate': 0.0004279401558540562, 'epoch': 3.24}

 27%|██▋       | 7595/28080 [15:00:29<40:15:13,  7.07s/it]
 27%|██▋       | 7596/28080 [15:00:36<40:12:18,  7.07s/it]
                                                          
{'loss': 0.6406, 'learning_rate': 0.0004279198998321027, 'epoch': 3.24}

 27%|██▋       | 7596/28080 [15:00:36<40:12:18,  7.07s/it]
 27%|██▋       | 7597/28080 [15:00:43<40:14:19,  7.07s/it]
                                                          
{'loss': 0.6469, 'learning_rate': 0.0004278996414431084, 'epoch': 3.25}

 27%|██▋       | 7597/28080 [15:00:43<40:14:19,  7.07s/it]
 27%|██▋       | 7598/28080 [15:00:50<40:07:04,  7.05s/it]
                                                          
{'loss': 0.6318, 'learning_rate': 0.00042787938068734296, 'epoch': 3.25}

 27%|██▋       | 7598/28080 [15:00:50<40:07:04,  7.05s/it]
 27%|██▋       | 7599/28080 [15:00:57<40:08:41,  7.06s/it]
                                                          
{'loss': 0.6146, 'learning_rate': 0.00042785911756507584, 'epoch': 3.25}

 27%|██▋       | 7599/28080 [15:00:57<40:08:41,  7.06s/it]
 27%|██▋       | 7600/28080 [15:01:04<40:10:32,  7.06s/it]
                                                          
{'loss': 0.6472, 'learning_rate': 0.00042783885207657666, 'epoch': 3.25}

 27%|██▋       | 7600/28080 [15:01:04<40:10:32,  7.06s/it]
 27%|██▋       | 7601/28080 [15:01:11<40:12:31,  7.07s/it]
                                                          
{'loss': 0.6489, 'learning_rate': 0.00042781858422211497, 'epoch': 3.25}

 27%|██▋       | 7601/28080 [15:01:11<40:12:31,  7.07s/it]
 27%|██▋       | 7602/28080 [15:01:18<40:13:45,  7.07s/it]
                                                          
{'loss': 0.6304, 'learning_rate': 0.0004277983140019605, 'epoch': 3.25}

 27%|██▋       | 7602/28080 [15:01:18<40:13:45,  7.07s/it]
 27%|██▋       | 7603/28080 [15:01:26<40:22:15,  7.10s/it]
                                                          
{'loss': 0.6352, 'learning_rate': 0.00042777804141638293, 'epoch': 3.25}

 27%|██▋       | 7603/28080 [15:01:26<40:22:15,  7.10s/it]
 27%|██▋       | 7604/28080 [15:01:33<40:26:45,  7.11s/it]
                                                          
{'loss': 0.6236, 'learning_rate': 0.0004277577664656519, 'epoch': 3.25}

 27%|██▋       | 7604/28080 [15:01:33<40:26:45,  7.11s/it]
 27%|██▋       | 7605/28080 [15:01:40<40:31:59,  7.13s/it]
                                                          
{'loss': 0.6142, 'learning_rate': 0.0004277374891500371, 'epoch': 3.25}

 27%|██▋       | 7605/28080 [15:01:40<40:31:59,  7.13s/it]
 27%|██▋       | 7606/28080 [15:01:47<40:28:33,  7.12s/it]
                                                          
{'loss': 0.6287, 'learning_rate': 0.0004277172094698084, 'epoch': 3.25}

 27%|██▋       | 7606/28080 [15:01:47<40:28:33,  7.12s/it]
 27%|██▋       | 7607/28080 [15:01:54<40:18:48,  7.09s/it]
                                                          
{'loss': 0.6575, 'learning_rate': 0.00042769692742523565, 'epoch': 3.25}

 27%|██▋       | 7607/28080 [15:01:54<40:18:48,  7.09s/it]
 27%|██▋       | 7608/28080 [15:02:01<40:11:36,  7.07s/it]
                                                          
{'loss': 0.6382, 'learning_rate': 0.0004276766430165885, 'epoch': 3.25}

 27%|██▋       | 7608/28080 [15:02:01<40:11:36,  7.07s/it]
 27%|██▋       | 7609/28080 [15:02:08<40:13:09,  7.07s/it]
                                                          
{'loss': 0.6336, 'learning_rate': 0.000427656356244137, 'epoch': 3.25}

 27%|██▋       | 7609/28080 [15:02:08<40:13:09,  7.07s/it]
 27%|██▋       | 7610/28080 [15:02:15<40:11:00,  7.07s/it]
                                                          
{'loss': 0.6445, 'learning_rate': 0.0004276360671081509, 'epoch': 3.25}

 27%|██▋       | 7610/28080 [15:02:15<40:11:00,  7.07s/it]
 27%|██▋       | 7611/28080 [15:02:22<40:13:22,  7.07s/it]
                                                          
{'loss': 0.6447, 'learning_rate': 0.0004276157756089002, 'epoch': 3.25}

 27%|██▋       | 7611/28080 [15:02:22<40:13:22,  7.07s/it]
 27%|██▋       | 7612/28080 [15:02:29<40:14:21,  7.08s/it]
                                                          
{'loss': 0.6564, 'learning_rate': 0.0004275954817466548, 'epoch': 3.25}

 27%|██▋       | 7612/28080 [15:02:29<40:14:21,  7.08s/it]
 27%|██▋       | 7613/28080 [15:02:36<40:08:07,  7.06s/it]
                                                          
{'loss': 0.6507, 'learning_rate': 0.0004275751855216848, 'epoch': 3.25}

 27%|██▋       | 7613/28080 [15:02:36<40:08:07,  7.06s/it]
 27%|██▋       | 7614/28080 [15:02:43<40:13:27,  7.08s/it]
                                                          
{'loss': 0.637, 'learning_rate': 0.0004275548869342601, 'epoch': 3.25}

 27%|██▋       | 7614/28080 [15:02:43<40:13:27,  7.08s/it]
 27%|██▋       | 7615/28080 [15:02:51<40:20:16,  7.10s/it]
                                                          
{'loss': 0.624, 'learning_rate': 0.00042753458598465086, 'epoch': 3.25}

 27%|██▋       | 7615/28080 [15:02:51<40:20:16,  7.10s/it]
 27%|██▋       | 7616/28080 [15:02:58<40:11:51,  7.07s/it]
                                                          
{'loss': 0.6184, 'learning_rate': 0.0004275142826731271, 'epoch': 3.25}

 27%|██▋       | 7616/28080 [15:02:58<40:11:51,  7.07s/it]
 27%|██▋       | 7617/28080 [15:03:05<40:12:49,  7.07s/it]
                                                          
{'loss': 0.6292, 'learning_rate': 0.00042749397699995883, 'epoch': 3.25}

 27%|██▋       | 7617/28080 [15:03:05<40:12:49,  7.07s/it]
 27%|██▋       | 7618/28080 [15:03:12<40:21:14,  7.10s/it]
                                                          
{'loss': 0.6532, 'learning_rate': 0.0004274736689654164, 'epoch': 3.25}

 27%|██▋       | 7618/28080 [15:03:12<40:21:14,  7.10s/it]
 27%|██▋       | 7619/28080 [15:03:19<40:20:56,  7.10s/it]
                                                          
{'loss': 0.6508, 'learning_rate': 0.00042745335856976985, 'epoch': 3.25}

 27%|██▋       | 7619/28080 [15:03:19<40:20:56,  7.10s/it]
 27%|██▋       | 7620/28080 [15:03:26<40:24:27,  7.11s/it]
                                                          
{'loss': 0.6336, 'learning_rate': 0.0004274330458132895, 'epoch': 3.26}

 27%|██▋       | 7620/28080 [15:03:26<40:24:27,  7.11s/it]
 27%|██▋       | 7621/28080 [15:03:33<40:30:55,  7.13s/it]
                                                          
{'loss': 0.6297, 'learning_rate': 0.0004274127306962455, 'epoch': 3.26}

 27%|██▋       | 7621/28080 [15:03:33<40:30:55,  7.13s/it]
 27%|██▋       | 7622/28080 [15:03:40<40:18:04,  7.09s/it]
                                                          
{'loss': 0.64, 'learning_rate': 0.0004273924132189081, 'epoch': 3.26}

 27%|██▋       | 7622/28080 [15:03:40<40:18:04,  7.09s/it]
 27%|██▋       | 7623/28080 [15:03:47<40:25:07,  7.11s/it]
                                                          
{'loss': 0.6455, 'learning_rate': 0.0004273720933815477, 'epoch': 3.26}

 27%|██▋       | 7623/28080 [15:03:47<40:25:07,  7.11s/it]
 27%|██▋       | 7624/28080 [15:03:55<40:21:04,  7.10s/it]
                                                          
{'loss': 0.6469, 'learning_rate': 0.00042735177118443453, 'epoch': 3.26}

 27%|██▋       | 7624/28080 [15:03:55<40:21:04,  7.10s/it]
 27%|██▋       | 7625/28080 [15:04:02<40:19:26,  7.10s/it]
                                                          
{'loss': 0.6129, 'learning_rate': 0.0004273314466278391, 'epoch': 3.26}

 27%|██▋       | 7625/28080 [15:04:02<40:19:26,  7.10s/it]
 27%|██▋       | 7626/28080 [15:04:09<40:29:26,  7.13s/it]
                                                          
{'loss': 0.6293, 'learning_rate': 0.0004273111197120316, 'epoch': 3.26}

 27%|██▋       | 7626/28080 [15:04:09<40:29:26,  7.13s/it]
 27%|██▋       | 7627/28080 [15:04:16<40:23:14,  7.11s/it]
                                                          
{'loss': 0.6299, 'learning_rate': 0.00042729079043728256, 'epoch': 3.26}

 27%|██▋       | 7627/28080 [15:04:16<40:23:14,  7.11s/it]
 27%|██▋       | 7628/28080 [15:04:23<40:21:22,  7.10s/it]
                                                          
{'loss': 0.6272, 'learning_rate': 0.0004272704588038626, 'epoch': 3.26}

 27%|██▋       | 7628/28080 [15:04:23<40:21:22,  7.10s/it]
 27%|██▋       | 7629/28080 [15:04:30<40:16:50,  7.09s/it]
                                                          
{'loss': 0.6225, 'learning_rate': 0.00042725012481204194, 'epoch': 3.26}

 27%|██▋       | 7629/28080 [15:04:30<40:16:50,  7.09s/it]
 27%|██▋       | 7630/28080 [15:04:37<40:09:50,  7.07s/it]
                                                          
{'loss': 0.6671, 'learning_rate': 0.00042722978846209124, 'epoch': 3.26}

 27%|██▋       | 7630/28080 [15:04:37<40:09:50,  7.07s/it]
 27%|██▋       | 7631/28080 [15:04:44<40:00:03,  7.04s/it]
                                                          
{'loss': 0.6353, 'learning_rate': 0.00042720944975428114, 'epoch': 3.26}

 27%|██▋       | 7631/28080 [15:04:44<40:00:03,  7.04s/it]
 27%|██▋       | 7632/28080 [15:04:51<40:07:01,  7.06s/it]
                                                          
{'loss': 0.6371, 'learning_rate': 0.0004271891086888821, 'epoch': 3.26}

 27%|██▋       | 7632/28080 [15:04:51<40:07:01,  7.06s/it]
 27%|██▋       | 7633/28080 [15:04:58<40:15:11,  7.09s/it]
                                                          
{'loss': 0.6381, 'learning_rate': 0.0004271687652661647, 'epoch': 3.26}

 27%|██▋       | 7633/28080 [15:04:58<40:15:11,  7.09s/it]
 27%|██▋       | 7634/28080 [15:05:05<40:11:59,  7.08s/it]
                                                          
{'loss': 0.6361, 'learning_rate': 0.0004271484194863997, 'epoch': 3.26}

 27%|██▋       | 7634/28080 [15:05:05<40:11:59,  7.08s/it]
 27%|██▋       | 7635/28080 [15:05:12<40:09:41,  7.07s/it]
                                                          
{'loss': 0.6763, 'learning_rate': 0.00042712807134985764, 'epoch': 3.26}

 27%|██▋       | 7635/28080 [15:05:12<40:09:41,  7.07s/it]
 27%|██▋       | 7636/28080 [15:05:19<40:09:03,  7.07s/it]
                                                          
{'loss': 0.6501, 'learning_rate': 0.00042710772085680944, 'epoch': 3.26}

 27%|██▋       | 7636/28080 [15:05:19<40:09:03,  7.07s/it]
 27%|██▋       | 7637/28080 [15:05:26<40:04:32,  7.06s/it]
                                                          
{'loss': 0.6525, 'learning_rate': 0.0004270873680075257, 'epoch': 3.26}

 27%|██▋       | 7637/28080 [15:05:27<40:04:32,  7.06s/it]
 27%|██▋       | 7638/28080 [15:05:34<40:05:13,  7.06s/it]
                                                          
{'loss': 0.6348, 'learning_rate': 0.0004270670128022772, 'epoch': 3.26}

 27%|██▋       | 7638/28080 [15:05:34<40:05:13,  7.06s/it]
 27%|██▋       | 7639/28080 [15:05:41<40:05:55,  7.06s/it]
                                                          
{'loss': 0.6447, 'learning_rate': 0.00042704665524133476, 'epoch': 3.26}

 27%|██▋       | 7639/28080 [15:05:41<40:05:55,  7.06s/it]
 27%|██▋       | 7640/28080 [15:05:48<40:04:11,  7.06s/it]
                                                          
{'loss': 0.6397, 'learning_rate': 0.00042702629532496923, 'epoch': 3.26}

 27%|██▋       | 7640/28080 [15:05:48<40:04:11,  7.06s/it]
 27%|██▋       | 7641/28080 [15:05:55<40:07:51,  7.07s/it]
                                                          
{'loss': 0.6321, 'learning_rate': 0.0004270059330534515, 'epoch': 3.26}

 27%|██▋       | 7641/28080 [15:05:55<40:07:51,  7.07s/it]
 27%|██▋       | 7642/28080 [15:06:02<40:00:00,  7.05s/it]
                                                          
{'loss': 0.6507, 'learning_rate': 0.0004269855684270524, 'epoch': 3.26}

 27%|██▋       | 7642/28080 [15:06:02<40:00:00,  7.05s/it]
 27%|██▋       | 7643/28080 [15:06:09<39:56:42,  7.04s/it]
                                                          
{'loss': 0.6386, 'learning_rate': 0.0004269652014460429, 'epoch': 3.27}

 27%|██▋       | 7643/28080 [15:06:09<39:56:42,  7.04s/it]
 27%|██▋       | 7644/28080 [15:06:16<40:10:33,  7.08s/it]
                                                          
{'loss': 0.6197, 'learning_rate': 0.0004269448321106939, 'epoch': 3.27}

 27%|██▋       | 7644/28080 [15:06:16<40:10:33,  7.08s/it]
 27%|██▋       | 7645/28080 [15:06:23<40:13:16,  7.09s/it]
                                                          
{'loss': 0.648, 'learning_rate': 0.00042692446042127654, 'epoch': 3.27}

 27%|██▋       | 7645/28080 [15:06:23<40:13:16,  7.09s/it]
 27%|██▋       | 7646/28080 [15:06:30<40:14:02,  7.09s/it]
                                                          
{'loss': 0.6216, 'learning_rate': 0.00042690408637806174, 'epoch': 3.27}

 27%|██▋       | 7646/28080 [15:06:30<40:14:02,  7.09s/it]
 27%|██▋       | 7647/28080 [15:06:37<40:13:11,  7.09s/it]
                                                          
{'loss': 0.6407, 'learning_rate': 0.00042688370998132056, 'epoch': 3.27}

 27%|██▋       | 7647/28080 [15:06:37<40:13:11,  7.09s/it]
 27%|██▋       | 7648/28080 [15:06:44<40:08:37,  7.07s/it]
                                                          
{'loss': 0.6608, 'learning_rate': 0.00042686333123132403, 'epoch': 3.27}

 27%|██▋       | 7648/28080 [15:06:44<40:08:37,  7.07s/it]
 27%|██▋       | 7649/28080 [15:06:51<40:05:05,  7.06s/it]
                                                          
{'loss': 0.6406, 'learning_rate': 0.00042684295012834344, 'epoch': 3.27}

 27%|██▋       | 7649/28080 [15:06:51<40:05:05,  7.06s/it]
 27%|██▋       | 7650/28080 [15:06:58<40:10:52,  7.08s/it]
                                                          
{'loss': 0.642, 'learning_rate': 0.00042682256667264987, 'epoch': 3.27}

 27%|██▋       | 7650/28080 [15:06:58<40:10:52,  7.08s/it]
 27%|██▋       | 7651/28080 [15:07:05<40:08:25,  7.07s/it]
                                                          
{'loss': 0.625, 'learning_rate': 0.0004268021808645144, 'epoch': 3.27}

 27%|██▋       | 7651/28080 [15:07:05<40:08:25,  7.07s/it]
 27%|██▋       | 7652/28080 [15:07:13<40:07:28,  7.07s/it]
                                                          
{'loss': 0.6233, 'learning_rate': 0.00042678179270420826, 'epoch': 3.27}

 27%|██▋       | 7652/28080 [15:07:13<40:07:28,  7.07s/it]
 27%|██▋       | 7653/28080 [15:07:20<40:06:37,  7.07s/it]
                                                          
{'loss': 0.6577, 'learning_rate': 0.0004267614021920029, 'epoch': 3.27}

 27%|██▋       | 7653/28080 [15:07:20<40:06:37,  7.07s/it]
 27%|██▋       | 7654/28080 [15:07:27<40:10:30,  7.08s/it]
                                                          
{'loss': 0.6349, 'learning_rate': 0.00042674100932816927, 'epoch': 3.27}

 27%|██▋       | 7654/28080 [15:07:27<40:10:30,  7.08s/it]
 27%|██▋       | 7655/28080 [15:07:34<40:16:12,  7.10s/it]
                                                          
{'loss': 0.633, 'learning_rate': 0.0004267206141129789, 'epoch': 3.27}

 27%|██▋       | 7655/28080 [15:07:34<40:16:12,  7.10s/it]
 27%|██▋       | 7656/28080 [15:07:41<40:19:16,  7.11s/it]
                                                          
{'loss': 0.6315, 'learning_rate': 0.0004267002165467031, 'epoch': 3.27}

 27%|██▋       | 7656/28080 [15:07:41<40:19:16,  7.11s/it]
 27%|██▋       | 7657/28080 [15:07:48<40:17:26,  7.10s/it]
                                                          
{'loss': 0.6195, 'learning_rate': 0.0004266798166296132, 'epoch': 3.27}

 27%|██▋       | 7657/28080 [15:07:48<40:17:26,  7.10s/it]
 27%|██▋       | 7658/28080 [15:07:55<40:17:42,  7.10s/it]
                                                          
{'loss': 0.6441, 'learning_rate': 0.0004266594143619806, 'epoch': 3.27}

 27%|██▋       | 7658/28080 [15:07:55<40:17:42,  7.10s/it]
 27%|██▋       | 7659/28080 [15:08:02<40:16:59,  7.10s/it]
                                                          
{'loss': 0.6516, 'learning_rate': 0.0004266390097440768, 'epoch': 3.27}

 27%|██▋       | 7659/28080 [15:08:02<40:16:59,  7.10s/it]
 27%|██▋       | 7660/28080 [15:08:09<40:23:14,  7.12s/it]
                                                          
{'loss': 0.6422, 'learning_rate': 0.0004266186027761731, 'epoch': 3.27}

 27%|██▋       | 7660/28080 [15:08:09<40:23:14,  7.12s/it]
 27%|██▋       | 7661/28080 [15:08:16<40:14:47,  7.10s/it]
                                                          
{'loss': 0.6347, 'learning_rate': 0.0004265981934585411, 'epoch': 3.27}

 27%|██▋       | 7661/28080 [15:08:16<40:14:47,  7.10s/it]
 27%|██▋       | 7662/28080 [15:08:24<40:12:14,  7.09s/it]
                                                          
{'loss': 0.6549, 'learning_rate': 0.0004265777817914524, 'epoch': 3.27}

 27%|██▋       | 7662/28080 [15:08:24<40:12:14,  7.09s/it]
 27%|██▋       | 7663/28080 [15:08:31<40:12:10,  7.09s/it]
                                                          
{'loss': 0.639, 'learning_rate': 0.00042655736777517846, 'epoch': 3.27}

 27%|██▋       | 7663/28080 [15:08:31<40:12:10,  7.09s/it]
 27%|██▋       | 7664/28080 [15:08:38<40:12:47,  7.09s/it]
                                                          
{'loss': 0.65, 'learning_rate': 0.00042653695140999087, 'epoch': 3.27}

 27%|██▋       | 7664/28080 [15:08:38<40:12:47,  7.09s/it]
 27%|██▋       | 7665/28080 [15:08:45<40:12:26,  7.09s/it]
                                                          
{'loss': 0.6452, 'learning_rate': 0.0004265165326961613, 'epoch': 3.27}

 27%|██▋       | 7665/28080 [15:08:45<40:12:26,  7.09s/it]
 27%|██▋       | 7666/28080 [15:08:52<40:18:56,  7.11s/it]
                                                          
{'loss': 0.6379, 'learning_rate': 0.0004264961116339613, 'epoch': 3.27}

 27%|██▋       | 7666/28080 [15:08:52<40:18:56,  7.11s/it]
 27%|██▋       | 7667/28080 [15:08:59<40:24:34,  7.13s/it]
                                                          
{'loss': 0.6288, 'learning_rate': 0.0004264756882236627, 'epoch': 3.28}

 27%|██▋       | 7667/28080 [15:08:59<40:24:34,  7.13s/it]
 27%|██▋       | 7668/28080 [15:09:06<40:11:37,  7.09s/it]
                                                          
{'loss': 0.6358, 'learning_rate': 0.000426455262465537, 'epoch': 3.28}

 27%|██▋       | 7668/28080 [15:09:06<40:11:37,  7.09s/it]
 27%|██▋       | 7669/28080 [15:09:13<40:12:08,  7.09s/it]
                                                          
{'loss': 0.6646, 'learning_rate': 0.0004264348343598562, 'epoch': 3.28}

 27%|██▋       | 7669/28080 [15:09:13<40:12:08,  7.09s/it]
 27%|██▋       | 7670/28080 [15:09:20<40:05:36,  7.07s/it]
                                                          
{'loss': 0.6239, 'learning_rate': 0.00042641440390689183, 'epoch': 3.28}

 27%|██▋       | 7670/28080 [15:09:20<40:05:36,  7.07s/it]
 27%|██▋       | 7671/28080 [15:09:27<40:07:59,  7.08s/it]
                                                          
{'loss': 0.6303, 'learning_rate': 0.0004263939711069159, 'epoch': 3.28}

 27%|██▋       | 7671/28080 [15:09:27<40:07:59,  7.08s/it]
 27%|██▋       | 7672/28080 [15:09:34<40:05:34,  7.07s/it]
                                                          
{'loss': 0.6153, 'learning_rate': 0.0004263735359602002, 'epoch': 3.28}

 27%|██▋       | 7672/28080 [15:09:34<40:05:34,  7.07s/it]
 27%|██▋       | 7673/28080 [15:09:41<39:59:44,  7.06s/it]
                                                          
{'loss': 0.6284, 'learning_rate': 0.00042635309846701647, 'epoch': 3.28}

 27%|██▋       | 7673/28080 [15:09:41<39:59:44,  7.06s/it]
 27%|██▋       | 7674/28080 [15:09:48<39:58:32,  7.05s/it]
                                                          
{'loss': 0.6776, 'learning_rate': 0.0004263326586276367, 'epoch': 3.28}

 27%|██▋       | 7674/28080 [15:09:49<39:58:32,  7.05s/it]
 27%|██▋       | 7675/28080 [15:09:56<40:05:38,  7.07s/it]
                                                          
{'loss': 0.6339, 'learning_rate': 0.00042631221644233284, 'epoch': 3.28}

 27%|██▋       | 7675/28080 [15:09:56<40:05:38,  7.07s/it]
 27%|██▋       | 7676/28080 [15:10:03<40:05:27,  7.07s/it]
                                                          
{'loss': 0.6428, 'learning_rate': 0.00042629177191137686, 'epoch': 3.28}

 27%|██▋       | 7676/28080 [15:10:03<40:05:27,  7.07s/it]
 27%|██▋       | 7677/28080 [15:10:10<40:14:23,  7.10s/it]
                                                          
{'loss': 0.6725, 'learning_rate': 0.00042627132503504075, 'epoch': 3.28}

 27%|██▋       | 7677/28080 [15:10:10<40:14:23,  7.10s/it]
 27%|██▋       | 7678/28080 [15:10:17<40:13:56,  7.10s/it]
                                                          
{'loss': 0.6364, 'learning_rate': 0.0004262508758135964, 'epoch': 3.28}

 27%|██▋       | 7678/28080 [15:10:17<40:13:56,  7.10s/it]
 27%|██▋       | 7679/28080 [15:10:24<40:06:06,  7.08s/it]
                                                          
{'loss': 0.6432, 'learning_rate': 0.0004262304242473161, 'epoch': 3.28}

 27%|██▋       | 7679/28080 [15:10:24<40:06:06,  7.08s/it]
 27%|██▋       | 7680/28080 [15:10:31<40:13:53,  7.10s/it]
                                                          
{'loss': 0.62, 'learning_rate': 0.0004262099703364717, 'epoch': 3.28}

 27%|██▋       | 7680/28080 [15:10:31<40:13:53,  7.10s/it]
 27%|██▋       | 7681/28080 [15:10:38<40:13:28,  7.10s/it]
                                                          
{'loss': 0.6507, 'learning_rate': 0.00042618951408133544, 'epoch': 3.28}

 27%|██▋       | 7681/28080 [15:10:38<40:13:28,  7.10s/it]
 27%|██▋       | 7682/28080 [15:10:45<40:16:45,  7.11s/it]
                                                          
{'loss': 0.6222, 'learning_rate': 0.00042616905548217957, 'epoch': 3.28}

 27%|██▋       | 7682/28080 [15:10:45<40:16:45,  7.11s/it]
 27%|██▋       | 7683/28080 [15:10:52<40:01:54,  7.07s/it]
                                                          
{'loss': 0.6308, 'learning_rate': 0.000426148594539276, 'epoch': 3.28}

 27%|██▋       | 7683/28080 [15:10:52<40:01:54,  7.07s/it]
 27%|██▋       | 7684/28080 [15:11:00<40:14:25,  7.10s/it]
                                                          
{'loss': 0.6517, 'learning_rate': 0.00042612813125289723, 'epoch': 3.28}

 27%|██▋       | 7684/28080 [15:11:00<40:14:25,  7.10s/it]
 27%|██▋       | 7685/28080 [15:11:07<40:12:20,  7.10s/it]
                                                          
{'loss': 0.6267, 'learning_rate': 0.0004261076656233153, 'epoch': 3.28}

 27%|██▋       | 7685/28080 [15:11:07<40:12:20,  7.10s/it]
 27%|██▋       | 7686/28080 [15:11:14<40:05:12,  7.08s/it]
                                                          
{'loss': 0.6363, 'learning_rate': 0.00042608719765080264, 'epoch': 3.28}

 27%|██▋       | 7686/28080 [15:11:14<40:05:12,  7.08s/it]
 27%|██▋       | 7687/28080 [15:11:21<40:05:30,  7.08s/it]
                                                          
{'loss': 0.6545, 'learning_rate': 0.0004260667273356314, 'epoch': 3.28}

 27%|██▋       | 7687/28080 [15:11:21<40:05:30,  7.08s/it]
 27%|██▋       | 7688/28080 [15:11:28<39:59:09,  7.06s/it]
                                                          
{'loss': 0.6449, 'learning_rate': 0.000426046254678074, 'epoch': 3.28}

 27%|██▋       | 7688/28080 [15:11:28<39:59:09,  7.06s/it]
 27%|██▋       | 7689/28080 [15:11:35<40:01:11,  7.07s/it]
                                                          
{'loss': 0.6445, 'learning_rate': 0.00042602577967840286, 'epoch': 3.28}

 27%|██▋       | 7689/28080 [15:11:35<40:01:11,  7.07s/it]
 27%|██▋       | 7690/28080 [15:11:42<40:03:50,  7.07s/it]
                                                          
{'loss': 0.6471, 'learning_rate': 0.0004260053023368903, 'epoch': 3.29}

 27%|██▋       | 7690/28080 [15:11:42<40:03:50,  7.07s/it]
 27%|██▋       | 7691/28080 [15:11:49<40:10:20,  7.09s/it]
                                                          
{'loss': 0.6372, 'learning_rate': 0.00042598482265380865, 'epoch': 3.29}

 27%|██▋       | 7691/28080 [15:11:49<40:10:20,  7.09s/it]
 27%|██▋       | 7692/28080 [15:11:56<40:10:38,  7.09s/it]
                                                          
{'loss': 0.6312, 'learning_rate': 0.00042596434062943056, 'epoch': 3.29}

 27%|██▋       | 7692/28080 [15:11:56<40:10:38,  7.09s/it]
 27%|██▋       | 7693/28080 [15:12:03<40:18:15,  7.12s/it]
                                                          
{'loss': 0.6294, 'learning_rate': 0.00042594385626402856, 'epoch': 3.29}

 27%|██▋       | 7693/28080 [15:12:03<40:18:15,  7.12s/it]
 27%|██▋       | 7694/28080 [15:12:10<40:04:43,  7.08s/it]
                                                          
{'loss': 0.628, 'learning_rate': 0.0004259233695578749, 'epoch': 3.29}

 27%|██▋       | 7694/28080 [15:12:10<40:04:43,  7.08s/it]
 27%|██▋       | 7695/28080 [15:12:17<39:57:32,  7.06s/it]
                                                          
{'loss': 0.6207, 'learning_rate': 0.0004259028805112424, 'epoch': 3.29}

 27%|██▋       | 7695/28080 [15:12:17<39:57:32,  7.06s/it]
 27%|██▋       | 7696/28080 [15:12:24<40:00:09,  7.06s/it]
                                                          
{'loss': 0.6447, 'learning_rate': 0.0004258823891244036, 'epoch': 3.29}

 27%|██▋       | 7696/28080 [15:12:24<40:00:09,  7.06s/it]
 27%|██▋       | 7697/28080 [15:12:31<40:05:33,  7.08s/it]
                                                          
{'loss': 0.626, 'learning_rate': 0.0004258618953976309, 'epoch': 3.29}

 27%|██▋       | 7697/28080 [15:12:32<40:05:33,  7.08s/it]
 27%|██▋       | 7698/28080 [15:12:39<40:03:32,  7.08s/it]
                                                          
{'loss': 0.6384, 'learning_rate': 0.0004258413993311972, 'epoch': 3.29}

 27%|██▋       | 7698/28080 [15:12:39<40:03:32,  7.08s/it]
 27%|██▋       | 7699/28080 [15:12:46<40:06:10,  7.08s/it]
                                                          
{'loss': 0.6455, 'learning_rate': 0.0004258209009253751, 'epoch': 3.29}

 27%|██▋       | 7699/28080 [15:12:46<40:06:10,  7.08s/it]
 27%|██▋       | 7700/28080 [15:12:53<40:14:29,  7.11s/it]
                                                          
{'loss': 0.6241, 'learning_rate': 0.00042580040018043723, 'epoch': 3.29}

 27%|██▋       | 7700/28080 [15:12:53<40:14:29,  7.11s/it]
 27%|██▋       | 7701/28080 [15:13:00<40:17:52,  7.12s/it]
                                                          
{'loss': 0.6115, 'learning_rate': 0.00042577989709665645, 'epoch': 3.29}

 27%|██▋       | 7701/28080 [15:13:00<40:17:52,  7.12s/it]
 27%|██▋       | 7702/28080 [15:13:07<40:19:39,  7.12s/it]
                                                          
{'loss': 0.6347, 'learning_rate': 0.00042575939167430546, 'epoch': 3.29}

 27%|██▋       | 7702/28080 [15:13:07<40:19:39,  7.12s/it]
 27%|██▋       | 7703/28080 [15:13:14<40:19:27,  7.12s/it]
                                                          
{'loss': 0.6463, 'learning_rate': 0.0004257388839136571, 'epoch': 3.29}

 27%|██▋       | 7703/28080 [15:13:14<40:19:27,  7.12s/it]
 27%|██▋       | 7704/28080 [15:13:21<40:24:29,  7.14s/it]
                                                          
{'loss': 0.6548, 'learning_rate': 0.0004257183738149841, 'epoch': 3.29}

 27%|██▋       | 7704/28080 [15:13:21<40:24:29,  7.14s/it]
 27%|██▋       | 7705/28080 [15:13:29<40:21:57,  7.13s/it]
                                                          
{'loss': 0.6213, 'learning_rate': 0.00042569786137855957, 'epoch': 3.29}

 27%|██▋       | 7705/28080 [15:13:29<40:21:57,  7.13s/it]
 27%|██▋       | 7706/28080 [15:13:36<40:23:58,  7.14s/it]
                                                          
{'loss': 0.6258, 'learning_rate': 0.0004256773466046562, 'epoch': 3.29}

 27%|██▋       | 7706/28080 [15:13:36<40:23:58,  7.14s/it]
 27%|██▋       | 7707/28080 [15:13:43<40:22:42,  7.14s/it]
                                                          
{'loss': 0.6443, 'learning_rate': 0.0004256568294935469, 'epoch': 3.29}

 27%|██▋       | 7707/28080 [15:13:43<40:22:42,  7.14s/it]
 27%|██▋       | 7708/28080 [15:13:50<40:12:25,  7.11s/it]
                                                          
{'loss': 0.6537, 'learning_rate': 0.00042563631004550475, 'epoch': 3.29}

 27%|██▋       | 7708/28080 [15:13:50<40:12:25,  7.11s/it]
 27%|██▋       | 7709/28080 [15:13:57<40:08:16,  7.09s/it]
                                                          
{'loss': 0.6363, 'learning_rate': 0.0004256157882608027, 'epoch': 3.29}

 27%|██▋       | 7709/28080 [15:13:57<40:08:16,  7.09s/it]
 27%|██▋       | 7710/28080 [15:14:04<40:02:22,  7.08s/it]
                                                          
{'loss': 0.646, 'learning_rate': 0.0004255952641397137, 'epoch': 3.29}

 27%|██▋       | 7710/28080 [15:14:04<40:02:22,  7.08s/it]
 27%|██▋       | 7711/28080 [15:14:11<40:05:19,  7.09s/it]
                                                          
{'loss': 0.6538, 'learning_rate': 0.00042557473768251096, 'epoch': 3.29}

 27%|██▋       | 7711/28080 [15:14:11<40:05:19,  7.09s/it]
 27%|██▋       | 7712/28080 [15:14:18<40:11:44,  7.10s/it]
                                                          
{'loss': 0.6274, 'learning_rate': 0.0004255542088894674, 'epoch': 3.29}

 27%|██▋       | 7712/28080 [15:14:18<40:11:44,  7.10s/it]
 27%|██▋       | 7713/28080 [15:14:25<40:11:04,  7.10s/it]
                                                          
{'loss': 0.6614, 'learning_rate': 0.0004255336777608562, 'epoch': 3.29}

 27%|██▋       | 7713/28080 [15:14:25<40:11:04,  7.10s/it]
 27%|██▋       | 7714/28080 [15:14:32<40:12:31,  7.11s/it]
                                                          
{'loss': 0.6111, 'learning_rate': 0.00042551314429695056, 'epoch': 3.3}

 27%|██▋       | 7714/28080 [15:14:32<40:12:31,  7.11s/it]
 27%|██▋       | 7715/28080 [15:14:40<40:15:27,  7.12s/it]
                                                          
{'loss': 0.6374, 'learning_rate': 0.00042549260849802353, 'epoch': 3.3}

 27%|██▋       | 7715/28080 [15:14:40<40:15:27,  7.12s/it]
 27%|██▋       | 7716/28080 [15:14:47<40:18:35,  7.13s/it]
                                                          
{'loss': 0.6517, 'learning_rate': 0.00042547207036434844, 'epoch': 3.3}

 27%|██▋       | 7716/28080 [15:14:47<40:18:35,  7.13s/it]
 27%|██▋       | 7717/28080 [15:14:54<40:19:17,  7.13s/it]
                                                          
{'loss': 0.6189, 'learning_rate': 0.0004254515298961984, 'epoch': 3.3}

 27%|██▋       | 7717/28080 [15:14:54<40:19:17,  7.13s/it]
 27%|██▋       | 7718/28080 [15:15:01<40:22:42,  7.14s/it]
                                                          
{'loss': 0.6302, 'learning_rate': 0.00042543098709384684, 'epoch': 3.3}

 27%|██▋       | 7718/28080 [15:15:01<40:22:42,  7.14s/it]
 27%|██▋       | 7719/28080 [15:15:08<40:12:57,  7.11s/it]
                                                          
{'loss': 0.6207, 'learning_rate': 0.00042541044195756693, 'epoch': 3.3}

 27%|██▋       | 7719/28080 [15:15:08<40:12:57,  7.11s/it]
 27%|██▋       | 7720/28080 [15:15:15<40:04:07,  7.08s/it]
                                                          
{'loss': 0.6523, 'learning_rate': 0.0004253898944876321, 'epoch': 3.3}

 27%|██▋       | 7720/28080 [15:15:15<40:04:07,  7.08s/it]
 27%|██▋       | 7721/28080 [15:15:22<40:04:40,  7.09s/it]
                                                          
{'loss': 0.6421, 'learning_rate': 0.00042536934468431563, 'epoch': 3.3}

 27%|██▋       | 7721/28080 [15:15:22<40:04:40,  7.09s/it]
 28%|██▊       | 7722/28080 [15:15:29<40:10:55,  7.11s/it]
                                                          
{'loss': 0.655, 'learning_rate': 0.00042534879254789107, 'epoch': 3.3}

 28%|██▊       | 7722/28080 [15:15:29<40:10:55,  7.11s/it]
 28%|██▊       | 7723/28080 [15:15:36<40:12:42,  7.11s/it]
                                                          
{'loss': 0.6503, 'learning_rate': 0.0004253282380786315, 'epoch': 3.3}

 28%|██▊       | 7723/28080 [15:15:36<40:12:42,  7.11s/it]
 28%|██▊       | 7724/28080 [15:15:44<40:08:28,  7.10s/it]
                                                          
{'loss': 0.6359, 'learning_rate': 0.0004253076812768107, 'epoch': 3.3}

 28%|██▊       | 7724/28080 [15:15:44<40:08:28,  7.10s/it]
 28%|██▊       | 7725/28080 [15:15:51<40:08:51,  7.10s/it]
                                                          
{'loss': 0.6242, 'learning_rate': 0.00042528712214270214, 'epoch': 3.3}

 28%|██▊       | 7725/28080 [15:15:51<40:08:51,  7.10s/it]
 28%|██▊       | 7726/28080 [15:15:58<40:01:38,  7.08s/it]
                                                          
{'loss': 0.6432, 'learning_rate': 0.00042526656067657916, 'epoch': 3.3}

 28%|██▊       | 7726/28080 [15:15:58<40:01:38,  7.08s/it]
 28%|██▊       | 7727/28080 [15:16:05<40:03:45,  7.09s/it]
                                                          
{'loss': 0.6307, 'learning_rate': 0.0004252459968787154, 'epoch': 3.3}

 28%|██▊       | 7727/28080 [15:16:05<40:03:45,  7.09s/it]
 28%|██▊       | 7728/28080 [15:16:12<40:08:56,  7.10s/it]
                                                          
{'loss': 0.6402, 'learning_rate': 0.00042522543074938445, 'epoch': 3.3}

 28%|██▊       | 7728/28080 [15:16:12<40:08:56,  7.10s/it]
 28%|██▊       | 7729/28080 [15:16:19<40:03:26,  7.09s/it]
                                                          
{'loss': 0.6309, 'learning_rate': 0.00042520486228886, 'epoch': 3.3}

 28%|██▊       | 7729/28080 [15:16:19<40:03:26,  7.09s/it]
 28%|██▊       | 7730/28080 [15:16:26<40:03:04,  7.09s/it]
                                                          
{'loss': 0.6263, 'learning_rate': 0.0004251842914974155, 'epoch': 3.3}

 28%|██▊       | 7730/28080 [15:16:26<40:03:04,  7.09s/it]
 28%|██▊       | 7731/28080 [15:16:33<40:05:00,  7.09s/it]
                                                          
{'loss': 0.6324, 'learning_rate': 0.00042516371837532477, 'epoch': 3.3}

 28%|██▊       | 7731/28080 [15:16:33<40:05:00,  7.09s/it]
 28%|██▊       | 7732/28080 [15:16:40<40:04:48,  7.09s/it]
                                                          
{'loss': 0.6386, 'learning_rate': 0.00042514314292286143, 'epoch': 3.3}

 28%|██▊       | 7732/28080 [15:16:40<40:04:48,  7.09s/it]
 28%|██▊       | 7733/28080 [15:16:47<40:00:31,  7.08s/it]
                                                          
{'loss': 0.6468, 'learning_rate': 0.0004251225651402993, 'epoch': 3.3}

 28%|██▊       | 7733/28080 [15:16:47<40:00:31,  7.08s/it]
 28%|██▊       | 7734/28080 [15:16:54<39:59:31,  7.08s/it]
                                                          
{'loss': 0.6412, 'learning_rate': 0.0004251019850279121, 'epoch': 3.3}

 28%|██▊       | 7734/28080 [15:16:54<39:59:31,  7.08s/it]
 28%|██▊       | 7735/28080 [15:17:02<40:10:36,  7.11s/it]
                                                          
{'loss': 0.6266, 'learning_rate': 0.0004250814025859736, 'epoch': 3.3}

 28%|██▊       | 7735/28080 [15:17:02<40:10:36,  7.11s/it]
 28%|██▊       | 7736/28080 [15:17:09<40:06:31,  7.10s/it]
                                                          
{'loss': 0.6255, 'learning_rate': 0.0004250608178147577, 'epoch': 3.3}

 28%|██▊       | 7736/28080 [15:17:09<40:06:31,  7.10s/it]
 28%|██▊       | 7737/28080 [15:17:16<39:57:12,  7.07s/it]
                                                          
{'loss': 0.6352, 'learning_rate': 0.00042504023071453825, 'epoch': 3.31}

 28%|██▊       | 7737/28080 [15:17:16<39:57:12,  7.07s/it]
 28%|██▊       | 7738/28080 [15:17:23<40:03:25,  7.09s/it]
                                                          
{'loss': 0.613, 'learning_rate': 0.00042501964128558903, 'epoch': 3.31}

 28%|██▊       | 7738/28080 [15:17:23<40:03:25,  7.09s/it]
 28%|██▊       | 7739/28080 [15:17:30<39:59:13,  7.08s/it]
                                                          
{'loss': 0.6147, 'learning_rate': 0.00042499904952818414, 'epoch': 3.31}

 28%|██▊       | 7739/28080 [15:17:30<39:59:13,  7.08s/it]
 28%|██▊       | 7740/28080 [15:17:37<40:00:20,  7.08s/it]
                                                          
{'loss': 0.6514, 'learning_rate': 0.0004249784554425973, 'epoch': 3.31}

 28%|██▊       | 7740/28080 [15:17:37<40:00:20,  7.08s/it]
 28%|██▊       | 7741/28080 [15:17:44<39:52:27,  7.06s/it]
                                                          
{'loss': 0.6336, 'learning_rate': 0.00042495785902910274, 'epoch': 3.31}

 28%|██▊       | 7741/28080 [15:17:44<39:52:27,  7.06s/it]
 28%|██▊       | 7742/28080 [15:17:51<39:57:55,  7.07s/it]
                                                          
{'loss': 0.6602, 'learning_rate': 0.0004249372602879743, 'epoch': 3.31}

 28%|██▊       | 7742/28080 [15:17:51<39:57:55,  7.07s/it]
 28%|██▊       | 7743/28080 [15:17:58<39:53:29,  7.06s/it]
                                                          
{'loss': 0.641, 'learning_rate': 0.0004249166592194861, 'epoch': 3.31}

 28%|██▊       | 7743/28080 [15:17:58<39:53:29,  7.06s/it]
 28%|██▊       | 7744/28080 [15:18:05<39:47:59,  7.05s/it]
                                                          
{'loss': 0.6345, 'learning_rate': 0.00042489605582391224, 'epoch': 3.31}

 28%|██▊       | 7744/28080 [15:18:05<39:47:59,  7.05s/it]
 28%|██▊       | 7745/28080 [15:18:12<39:51:21,  7.06s/it]
                                                          
{'loss': 0.6452, 'learning_rate': 0.0004248754501015267, 'epoch': 3.31}

 28%|██▊       | 7745/28080 [15:18:12<39:51:21,  7.06s/it]
 28%|██▊       | 7746/28080 [15:18:19<39:41:58,  7.03s/it]
                                                          
{'loss': 0.6321, 'learning_rate': 0.00042485484205260376, 'epoch': 3.31}

 28%|██▊       | 7746/28080 [15:18:19<39:41:58,  7.03s/it]
 28%|██▊       | 7747/28080 [15:18:26<39:50:29,  7.05s/it]
                                                          
{'loss': 0.6561, 'learning_rate': 0.0004248342316774175, 'epoch': 3.31}

 28%|██▊       | 7747/28080 [15:18:26<39:50:29,  7.05s/it]
 28%|██▊       | 7748/28080 [15:18:33<40:04:19,  7.10s/it]
                                                          
{'loss': 0.6325, 'learning_rate': 0.0004248136189762423, 'epoch': 3.31}

 28%|██▊       | 7748/28080 [15:18:33<40:04:19,  7.10s/it]
 28%|██▊       | 7749/28080 [15:18:41<40:08:28,  7.11s/it]
                                                          
{'loss': 0.6137, 'learning_rate': 0.00042479300394935205, 'epoch': 3.31}

 28%|██▊       | 7749/28080 [15:18:41<40:08:28,  7.11s/it]
 28%|██▊       | 7750/28080 [15:18:48<40:10:30,  7.11s/it]
                                                          
{'loss': 0.6193, 'learning_rate': 0.00042477238659702134, 'epoch': 3.31}

 28%|██▊       | 7750/28080 [15:18:48<40:10:30,  7.11s/it]
 28%|██▊       | 7751/28080 [15:18:55<40:10:51,  7.12s/it]
                                                          
{'loss': 0.6172, 'learning_rate': 0.0004247517669195242, 'epoch': 3.31}

 28%|██▊       | 7751/28080 [15:18:55<40:10:51,  7.12s/it]
 28%|██▊       | 7752/28080 [15:19:02<39:59:37,  7.08s/it]
                                                          
{'loss': 0.6539, 'learning_rate': 0.0004247311449171352, 'epoch': 3.31}

 28%|██▊       | 7752/28080 [15:19:02<39:59:37,  7.08s/it]
 28%|██▊       | 7753/28080 [15:19:09<39:59:18,  7.08s/it]
                                                          
{'loss': 0.6255, 'learning_rate': 0.0004247105205901285, 'epoch': 3.31}

 28%|██▊       | 7753/28080 [15:19:09<39:59:18,  7.08s/it]
 28%|██▊       | 7754/28080 [15:19:16<39:58:02,  7.08s/it]
                                                          
{'loss': 0.636, 'learning_rate': 0.0004246898939387786, 'epoch': 3.31}

 28%|██▊       | 7754/28080 [15:19:16<39:58:02,  7.08s/it]
 28%|██▊       | 7755/28080 [15:19:23<40:02:42,  7.09s/it]
                                                          
{'loss': 0.6378, 'learning_rate': 0.00042466926496335987, 'epoch': 3.31}

 28%|██▊       | 7755/28080 [15:19:23<40:02:42,  7.09s/it]
 28%|██▊       | 7756/28080 [15:19:30<39:56:34,  7.08s/it]
                                                          
{'loss': 0.6471, 'learning_rate': 0.0004246486336641467, 'epoch': 3.31}

 28%|██▊       | 7756/28080 [15:19:30<39:56:34,  7.08s/it]
 28%|██▊       | 7757/28080 [15:19:37<39:59:55,  7.09s/it]
                                                          
{'loss': 0.6025, 'learning_rate': 0.0004246280000414138, 'epoch': 3.31}

 28%|██▊       | 7757/28080 [15:19:37<39:59:55,  7.09s/it]
 28%|██▊       | 7758/28080 [15:19:44<40:01:57,  7.09s/it]
                                                          
{'loss': 0.6281, 'learning_rate': 0.00042460736409543536, 'epoch': 3.31}

 28%|██▊       | 7758/28080 [15:19:44<40:01:57,  7.09s/it]
 28%|██▊       | 7759/28080 [15:19:51<40:10:12,  7.12s/it]
                                                          
{'loss': 0.6436, 'learning_rate': 0.00042458672582648617, 'epoch': 3.31}

 28%|██▊       | 7759/28080 [15:19:51<40:10:12,  7.12s/it]
 28%|██▊       | 7760/28080 [15:19:59<40:04:23,  7.10s/it]
                                                          
{'loss': 0.6442, 'learning_rate': 0.00042456608523484064, 'epoch': 3.31}

 28%|██▊       | 7760/28080 [15:19:59<40:04:23,  7.10s/it]
 28%|██▊       | 7761/28080 [15:20:06<40:02:45,  7.10s/it]
                                                          
{'loss': 0.626, 'learning_rate': 0.00042454544232077345, 'epoch': 3.32}

 28%|██▊       | 7761/28080 [15:20:06<40:02:45,  7.10s/it]
 28%|██▊       | 7762/28080 [15:20:13<39:58:35,  7.08s/it]
                                                          
{'loss': 0.6327, 'learning_rate': 0.0004245247970845593, 'epoch': 3.32}

 28%|██▊       | 7762/28080 [15:20:13<39:58:35,  7.08s/it]
 28%|██▊       | 7763/28080 [15:20:20<39:59:28,  7.09s/it]
                                                          
{'loss': 0.6459, 'learning_rate': 0.00042450414952647267, 'epoch': 3.32}

 28%|██▊       | 7763/28080 [15:20:20<39:59:28,  7.09s/it]
 28%|██▊       | 7764/28080 [15:20:27<39:59:43,  7.09s/it]
                                                          
{'loss': 0.6417, 'learning_rate': 0.0004244834996467883, 'epoch': 3.32}

 28%|██▊       | 7764/28080 [15:20:27<39:59:43,  7.09s/it]
 28%|██▊       | 7765/28080 [15:20:34<40:07:06,  7.11s/it]
                                                          
{'loss': 0.6242, 'learning_rate': 0.0004244628474457811, 'epoch': 3.32}

 28%|██▊       | 7765/28080 [15:20:34<40:07:06,  7.11s/it]
 28%|██▊       | 7766/28080 [15:20:41<40:08:05,  7.11s/it]
                                                          
{'loss': 0.6163, 'learning_rate': 0.00042444219292372563, 'epoch': 3.32}

 28%|██▊       | 7766/28080 [15:20:41<40:08:05,  7.11s/it]
 28%|██▊       | 7767/28080 [15:20:48<40:08:59,  7.12s/it]
                                                          
{'loss': 0.6241, 'learning_rate': 0.0004244215360808968, 'epoch': 3.32}

 28%|██▊       | 7767/28080 [15:20:48<40:08:59,  7.12s/it]
 28%|██▊       | 7768/28080 [15:20:55<40:05:27,  7.11s/it]
                                                          
{'loss': 0.6211, 'learning_rate': 0.00042440087691756934, 'epoch': 3.32}

 28%|██▊       | 7768/28080 [15:20:55<40:05:27,  7.11s/it]
 28%|██▊       | 7769/28080 [15:21:02<40:00:49,  7.09s/it]
                                                          
{'loss': 0.6268, 'learning_rate': 0.00042438021543401814, 'epoch': 3.32}

 28%|██▊       | 7769/28080 [15:21:02<40:00:49,  7.09s/it]
 28%|██▊       | 7770/28080 [15:21:10<40:04:13,  7.10s/it]
                                                          
{'loss': 0.6328, 'learning_rate': 0.0004243595516305181, 'epoch': 3.32}

 28%|██▊       | 7770/28080 [15:21:10<40:04:13,  7.10s/it]
 28%|██▊       | 7771/28080 [15:21:17<40:04:44,  7.10s/it]
                                                          
{'loss': 0.6188, 'learning_rate': 0.0004243388855073441, 'epoch': 3.32}

 28%|██▊       | 7771/28080 [15:21:17<40:04:44,  7.10s/it]
 28%|██▊       | 7772/28080 [15:21:24<40:08:32,  7.12s/it]
                                                          
{'loss': 0.6156, 'learning_rate': 0.000424318217064771, 'epoch': 3.32}

 28%|██▊       | 7772/28080 [15:21:24<40:08:32,  7.12s/it]
 28%|██▊       | 7773/28080 [15:21:31<40:06:28,  7.11s/it]
                                                          
{'loss': 0.6234, 'learning_rate': 0.0004242975463030739, 'epoch': 3.32}

 28%|██▊       | 7773/28080 [15:21:31<40:06:28,  7.11s/it]
 28%|██▊       | 7774/28080 [15:21:38<40:00:26,  7.09s/it]
                                                          
{'loss': 0.6258, 'learning_rate': 0.00042427687322252783, 'epoch': 3.32}

 28%|██▊       | 7774/28080 [15:21:38<40:00:26,  7.09s/it]
 28%|██▊       | 7775/28080 [15:21:45<39:52:43,  7.07s/it]
                                                          
{'loss': 0.6501, 'learning_rate': 0.00042425619782340764, 'epoch': 3.32}

 28%|██▊       | 7775/28080 [15:21:45<39:52:43,  7.07s/it]
 28%|██▊       | 7776/28080 [15:21:52<39:58:32,  7.09s/it]
                                                          
{'loss': 0.6327, 'learning_rate': 0.00042423552010598857, 'epoch': 3.32}

 28%|██▊       | 7776/28080 [15:21:52<39:58:32,  7.09s/it]
 28%|██▊       | 7777/28080 [15:21:59<40:02:35,  7.10s/it]
                                                          
{'loss': 0.6472, 'learning_rate': 0.0004242148400705457, 'epoch': 3.32}

 28%|██▊       | 7777/28080 [15:21:59<40:02:35,  7.10s/it]
 28%|██▊       | 7778/28080 [15:22:06<39:59:22,  7.09s/it]
                                                          
{'loss': 0.6307, 'learning_rate': 0.000424194157717354, 'epoch': 3.32}

 28%|██▊       | 7778/28080 [15:22:06<39:59:22,  7.09s/it]
 28%|██▊       | 7779/28080 [15:22:13<39:51:21,  7.07s/it]
                                                          
{'loss': 0.6428, 'learning_rate': 0.00042417347304668886, 'epoch': 3.32}

 28%|██▊       | 7779/28080 [15:22:13<39:51:21,  7.07s/it]
 28%|██▊       | 7780/28080 [15:22:20<39:50:28,  7.07s/it]
                                                          
{'loss': 0.632, 'learning_rate': 0.00042415278605882525, 'epoch': 3.32}

 28%|██▊       | 7780/28080 [15:22:20<39:50:28,  7.07s/it]
 28%|██▊       | 7781/28080 [15:22:27<39:57:35,  7.09s/it]
                                                          
{'loss': 0.6321, 'learning_rate': 0.0004241320967540385, 'epoch': 3.32}

 28%|██▊       | 7781/28080 [15:22:27<39:57:35,  7.09s/it]
 28%|██▊       | 7782/28080 [15:22:35<39:53:44,  7.08s/it]
                                                          
{'loss': 0.6525, 'learning_rate': 0.0004241114051326038, 'epoch': 3.32}

 28%|██▊       | 7782/28080 [15:22:35<39:53:44,  7.08s/it]
 28%|██▊       | 7783/28080 [15:22:42<39:59:43,  7.09s/it]
                                                          
{'loss': 0.6599, 'learning_rate': 0.0004240907111947966, 'epoch': 3.32}

 28%|██▊       | 7783/28080 [15:22:42<39:59:43,  7.09s/it]
 28%|██▊       | 7784/28080 [15:22:49<40:01:51,  7.10s/it]
                                                          
{'loss': 0.6338, 'learning_rate': 0.000424070014940892, 'epoch': 3.33}

 28%|██▊       | 7784/28080 [15:22:49<40:01:51,  7.10s/it]
 28%|██▊       | 7785/28080 [15:22:56<39:54:10,  7.08s/it]
                                                          
{'loss': 0.6403, 'learning_rate': 0.00042404931637116545, 'epoch': 3.33}

 28%|██▊       | 7785/28080 [15:22:56<39:54:10,  7.08s/it]
 28%|██▊       | 7786/28080 [15:23:03<39:54:03,  7.08s/it]
                                                          
{'loss': 0.6512, 'learning_rate': 0.00042402861548589235, 'epoch': 3.33}

 28%|██▊       | 7786/28080 [15:23:03<39:54:03,  7.08s/it]
 28%|██▊       | 7787/28080 [15:23:10<40:01:13,  7.10s/it]
                                                          
{'loss': 0.6401, 'learning_rate': 0.00042400791228534797, 'epoch': 3.33}

 28%|██▊       | 7787/28080 [15:23:10<40:01:13,  7.10s/it]
 28%|██▊       | 7788/28080 [15:23:17<40:10:26,  7.13s/it]
                                                          
{'loss': 0.6354, 'learning_rate': 0.00042398720676980784, 'epoch': 3.33}

 28%|██▊       | 7788/28080 [15:23:17<40:10:26,  7.13s/it]
 28%|██▊       | 7789/28080 [15:23:24<40:13:01,  7.14s/it]
                                                          
{'loss': 0.6205, 'learning_rate': 0.00042396649893954746, 'epoch': 3.33}

 28%|██▊       | 7789/28080 [15:23:24<40:13:01,  7.14s/it]
 28%|██▊       | 7790/28080 [15:23:31<40:05:46,  7.11s/it]
                                                          
{'loss': 0.6382, 'learning_rate': 0.0004239457887948422, 'epoch': 3.33}

 28%|██▊       | 7790/28080 [15:23:31<40:05:46,  7.11s/it]
 28%|██▊       | 7791/28080 [15:23:39<40:04:39,  7.11s/it]
                                                          
{'loss': 0.6319, 'learning_rate': 0.0004239250763359678, 'epoch': 3.33}

 28%|██▊       | 7791/28080 [15:23:39<40:04:39,  7.11s/it]
 28%|██▊       | 7792/28080 [15:23:46<40:06:55,  7.12s/it]
                                                          
{'loss': 0.6312, 'learning_rate': 0.0004239043615631997, 'epoch': 3.33}

 28%|██▊       | 7792/28080 [15:23:46<40:06:55,  7.12s/it]
 28%|██▊       | 7793/28080 [15:23:53<40:00:14,  7.10s/it]
                                                          
{'loss': 0.6287, 'learning_rate': 0.0004238836444768134, 'epoch': 3.33}

 28%|██▊       | 7793/28080 [15:23:53<40:00:14,  7.10s/it]
 28%|██▊       | 7794/28080 [15:24:00<40:01:23,  7.10s/it]
                                                          
{'loss': 0.6387, 'learning_rate': 0.0004238629250770846, 'epoch': 3.33}

 28%|██▊       | 7794/28080 [15:24:00<40:01:23,  7.10s/it]
 28%|██▊       | 7795/28080 [15:24:07<40:13:13,  7.14s/it]
                                                          
{'loss': 0.6278, 'learning_rate': 0.0004238422033642889, 'epoch': 3.33}

 28%|██▊       | 7795/28080 [15:24:07<40:13:13,  7.14s/it]
 28%|██▊       | 7796/28080 [15:24:14<40:07:32,  7.12s/it]
                                                          
{'loss': 0.6382, 'learning_rate': 0.0004238214793387021, 'epoch': 3.33}

 28%|██▊       | 7796/28080 [15:24:14<40:07:32,  7.12s/it]
 28%|██▊       | 7797/28080 [15:24:21<40:05:46,  7.12s/it]
                                                          
{'loss': 0.6425, 'learning_rate': 0.00042380075300059986, 'epoch': 3.33}

 28%|██▊       | 7797/28080 [15:24:21<40:05:46,  7.12s/it]
 28%|██▊       | 7798/28080 [15:24:28<40:11:41,  7.13s/it]
                                                          
{'loss': 0.6258, 'learning_rate': 0.0004237800243502578, 'epoch': 3.33}

 28%|██▊       | 7798/28080 [15:24:28<40:11:41,  7.13s/it]
 28%|██▊       | 7799/28080 [15:24:36<40:07:37,  7.12s/it]
                                                          
{'loss': 0.6395, 'learning_rate': 0.00042375929338795185, 'epoch': 3.33}

 28%|██▊       | 7799/28080 [15:24:36<40:07:37,  7.12s/it]
 28%|██▊       | 7800/28080 [15:24:43<40:08:10,  7.12s/it]
                                                          
{'loss': 0.6289, 'learning_rate': 0.0004237385601139577, 'epoch': 3.33}

 28%|██▊       | 7800/28080 [15:24:43<40:08:10,  7.12s/it]
 28%|██▊       | 7801/28080 [15:24:50<40:12:30,  7.14s/it]
                                                          
{'loss': 0.6333, 'learning_rate': 0.00042371782452855133, 'epoch': 3.33}

 28%|██▊       | 7801/28080 [15:24:50<40:12:30,  7.14s/it]
 28%|██▊       | 7802/28080 [15:24:57<40:07:00,  7.12s/it]
                                                          
{'loss': 0.6481, 'learning_rate': 0.0004236970866320085, 'epoch': 3.33}

 28%|██▊       | 7802/28080 [15:24:57<40:07:00,  7.12s/it]
 28%|██▊       | 7803/28080 [15:25:04<40:13:50,  7.14s/it]
                                                          
{'loss': 0.6348, 'learning_rate': 0.0004236763464246051, 'epoch': 3.33}

 28%|██▊       | 7803/28080 [15:25:04<40:13:50,  7.14s/it]
 28%|██▊       | 7804/28080 [15:25:11<40:17:35,  7.15s/it]
                                                          
{'loss': 0.6235, 'learning_rate': 0.0004236556039066171, 'epoch': 3.33}

 28%|██▊       | 7804/28080 [15:25:11<40:17:35,  7.15s/it]
 28%|██▊       | 7805/28080 [15:25:18<40:09:54,  7.13s/it]
                                                          
{'loss': 0.6315, 'learning_rate': 0.00042363485907832046, 'epoch': 3.33}

 28%|██▊       | 7805/28080 [15:25:18<40:09:54,  7.13s/it]
 28%|██▊       | 7806/28080 [15:25:25<40:03:36,  7.11s/it]
                                                          
{'loss': 0.6447, 'learning_rate': 0.00042361411193999113, 'epoch': 3.33}

 28%|██▊       | 7806/28080 [15:25:25<40:03:36,  7.11s/it]
 28%|██▊       | 7807/28080 [15:25:33<40:10:36,  7.13s/it]
                                                          
{'loss': 0.6385, 'learning_rate': 0.00042359336249190514, 'epoch': 3.34}

 28%|██▊       | 7807/28080 [15:25:33<40:10:36,  7.13s/it]
 28%|██▊       | 7808/28080 [15:25:40<40:01:23,  7.11s/it]
                                                          
{'loss': 0.6258, 'learning_rate': 0.0004235726107343386, 'epoch': 3.34}

 28%|██▊       | 7808/28080 [15:25:40<40:01:23,  7.11s/it]
 28%|██▊       | 7809/28080 [15:25:47<39:58:56,  7.10s/it]
                                                          
{'loss': 0.6302, 'learning_rate': 0.00042355185666756743, 'epoch': 3.34}

 28%|██▊       | 7809/28080 [15:25:47<39:58:56,  7.10s/it]
 28%|██▊       | 7810/28080 [15:25:54<39:59:56,  7.10s/it]
                                                          
{'loss': 0.6467, 'learning_rate': 0.0004235311002918679, 'epoch': 3.34}

 28%|██▊       | 7810/28080 [15:25:54<39:59:56,  7.10s/it]
 28%|██▊       | 7811/28080 [15:26:01<40:01:12,  7.11s/it]
                                                          
{'loss': 0.6341, 'learning_rate': 0.0004235103416075162, 'epoch': 3.34}

 28%|██▊       | 7811/28080 [15:26:01<40:01:12,  7.11s/it]
 28%|██▊       | 7812/28080 [15:26:08<40:14:26,  7.15s/it]
                                                          
{'loss': 0.6478, 'learning_rate': 0.0004234895806147883, 'epoch': 3.34}

 28%|██▊       | 7812/28080 [15:26:08<40:14:26,  7.15s/it]
 28%|██▊       | 7813/28080 [15:26:15<40:06:35,  7.12s/it]
                                                          
{'loss': 0.6331, 'learning_rate': 0.00042346881731396047, 'epoch': 3.34}

 28%|██▊       | 7813/28080 [15:26:15<40:06:35,  7.12s/it]
 28%|██▊       | 7814/28080 [15:26:22<39:58:22,  7.10s/it]
                                                          
{'loss': 0.6457, 'learning_rate': 0.0004234480517053091, 'epoch': 3.34}

 28%|██▊       | 7814/28080 [15:26:22<39:58:22,  7.10s/it]
 28%|██▊       | 7815/28080 [15:26:29<39:55:17,  7.09s/it]
                                                          
{'loss': 0.6336, 'learning_rate': 0.00042342728378911025, 'epoch': 3.34}

 28%|██▊       | 7815/28080 [15:26:29<39:55:17,  7.09s/it]
 28%|██▊       | 7816/28080 [15:26:36<39:49:42,  7.08s/it]
                                                          
{'loss': 0.6371, 'learning_rate': 0.00042340651356564035, 'epoch': 3.34}

 28%|██▊       | 7816/28080 [15:26:36<39:49:42,  7.08s/it]
 28%|██▊       | 7817/28080 [15:26:44<39:51:41,  7.08s/it]
                                                          
{'loss': 0.6299, 'learning_rate': 0.0004233857410351757, 'epoch': 3.34}

 28%|██▊       | 7817/28080 [15:26:44<39:51:41,  7.08s/it]
 28%|██▊       | 7818/28080 [15:26:51<40:00:40,  7.11s/it]
                                                          
{'loss': 0.6157, 'learning_rate': 0.00042336496619799257, 'epoch': 3.34}

 28%|██▊       | 7818/28080 [15:26:51<40:00:40,  7.11s/it]
 28%|██▊       | 7819/28080 [15:26:58<39:52:06,  7.08s/it]
                                                          
{'loss': 0.6586, 'learning_rate': 0.00042334418905436746, 'epoch': 3.34}

 28%|██▊       | 7819/28080 [15:26:58<39:52:06,  7.08s/it]
 28%|██▊       | 7820/28080 [15:27:05<39:50:59,  7.08s/it]
                                                          
{'loss': 0.6233, 'learning_rate': 0.00042332340960457674, 'epoch': 3.34}

 28%|██▊       | 7820/28080 [15:27:05<39:50:59,  7.08s/it]
 28%|██▊       | 7821/28080 [15:27:12<39:56:27,  7.10s/it]
                                                          
{'loss': 0.6455, 'learning_rate': 0.0004233026278488969, 'epoch': 3.34}

 28%|██▊       | 7821/28080 [15:27:12<39:56:27,  7.10s/it]
 28%|██▊       | 7822/28080 [15:27:19<40:01:09,  7.11s/it]
                                                          
{'loss': 0.6274, 'learning_rate': 0.00042328184378760436, 'epoch': 3.34}

 28%|██▊       | 7822/28080 [15:27:19<40:01:09,  7.11s/it]
 28%|██▊       | 7823/28080 [15:27:26<39:49:33,  7.08s/it]
                                                          
{'loss': 0.633, 'learning_rate': 0.0004232610574209756, 'epoch': 3.34}

 28%|██▊       | 7823/28080 [15:27:26<39:49:33,  7.08s/it]
 28%|██▊       | 7824/28080 [15:27:33<39:57:14,  7.10s/it]
                                                          
{'loss': 0.628, 'learning_rate': 0.0004232402687492872, 'epoch': 3.34}

 28%|██▊       | 7824/28080 [15:27:33<39:57:14,  7.10s/it]
 28%|██▊       | 7825/28080 [15:27:40<40:08:55,  7.14s/it]
                                                          
{'loss': 0.6341, 'learning_rate': 0.00042321947777281585, 'epoch': 3.34}

 28%|██▊       | 7825/28080 [15:27:40<40:08:55,  7.14s/it]
 28%|██▊       | 7826/28080 [15:27:48<40:16:09,  7.16s/it]
                                                          
{'loss': 0.6359, 'learning_rate': 0.00042319868449183795, 'epoch': 3.34}

 28%|██▊       | 7826/28080 [15:27:48<40:16:09,  7.16s/it]
 28%|██▊       | 7827/28080 [15:27:55<40:22:23,  7.18s/it]
                                                          
{'loss': 0.6531, 'learning_rate': 0.00042317788890663033, 'epoch': 3.34}

 28%|██▊       | 7827/28080 [15:27:55<40:22:23,  7.18s/it]
 28%|██▊       | 7828/28080 [15:28:02<40:11:50,  7.15s/it]
                                                          
{'loss': 0.6318, 'learning_rate': 0.00042315709101746945, 'epoch': 3.34}

 28%|██▊       | 7828/28080 [15:28:02<40:11:50,  7.15s/it]
 28%|██▊       | 7829/28080 [15:28:09<40:10:56,  7.14s/it]
                                                          
{'loss': 0.6527, 'learning_rate': 0.00042313629082463223, 'epoch': 3.34}

 28%|██▊       | 7829/28080 [15:28:09<40:10:56,  7.14s/it]
 28%|██▊       | 7830/28080 [15:28:16<39:59:10,  7.11s/it]
                                                          
{'loss': 0.6572, 'learning_rate': 0.0004231154883283952, 'epoch': 3.34}

 28%|██▊       | 7830/28080 [15:28:16<39:59:10,  7.11s/it]
 28%|██▊       | 7831/28080 [15:28:23<40:03:56,  7.12s/it]
                                                          
{'loss': 0.6385, 'learning_rate': 0.00042309468352903513, 'epoch': 3.35}

 28%|██▊       | 7831/28080 [15:28:23<40:03:56,  7.12s/it]
 28%|██▊       | 7832/28080 [15:28:30<40:09:03,  7.14s/it]
                                                          
{'loss': 0.6212, 'learning_rate': 0.000423073876426829, 'epoch': 3.35}

 28%|██▊       | 7832/28080 [15:28:30<40:09:03,  7.14s/it]
 28%|██▊       | 7833/28080 [15:28:37<39:56:44,  7.10s/it]
                                                          
{'loss': 0.6417, 'learning_rate': 0.0004230530670220534, 'epoch': 3.35}

 28%|██▊       | 7833/28080 [15:28:37<39:56:44,  7.10s/it]
 28%|██▊       | 7834/28080 [15:28:45<40:02:30,  7.12s/it]
                                                          
{'loss': 0.6505, 'learning_rate': 0.00042303225531498535, 'epoch': 3.35}

 28%|██▊       | 7834/28080 [15:28:45<40:02:30,  7.12s/it]
 28%|██▊       | 7835/28080 [15:28:52<40:02:00,  7.12s/it]
                                                          
{'loss': 0.6412, 'learning_rate': 0.0004230114413059016, 'epoch': 3.35}

 28%|██▊       | 7835/28080 [15:28:52<40:02:00,  7.12s/it]
 28%|██▊       | 7836/28080 [15:28:59<40:04:46,  7.13s/it]
                                                          
{'loss': 0.6548, 'learning_rate': 0.0004229906249950791, 'epoch': 3.35}

 28%|██▊       | 7836/28080 [15:28:59<40:04:46,  7.13s/it]
 28%|██▊       | 7837/28080 [15:29:06<39:59:27,  7.11s/it]
                                                          
{'loss': 0.6286, 'learning_rate': 0.00042296980638279483, 'epoch': 3.35}

 28%|██▊       | 7837/28080 [15:29:06<39:59:27,  7.11s/it]
 28%|██▊       | 7838/28080 [15:29:13<39:56:23,  7.10s/it]
                                                          
{'loss': 0.6238, 'learning_rate': 0.0004229489854693257, 'epoch': 3.35}

 28%|██▊       | 7838/28080 [15:29:13<39:56:23,  7.10s/it]
 28%|██▊       | 7839/28080 [15:29:20<40:00:43,  7.12s/it]
                                                          
{'loss': 0.6338, 'learning_rate': 0.0004229281622549487, 'epoch': 3.35}

 28%|██▊       | 7839/28080 [15:29:20<40:00:43,  7.12s/it]
 28%|██▊       | 7840/28080 [15:29:27<39:52:40,  7.09s/it]
                                                          
{'loss': 0.6345, 'learning_rate': 0.000422907336739941, 'epoch': 3.35}

 28%|██▊       | 7840/28080 [15:29:27<39:52:40,  7.09s/it]
 28%|██▊       | 7841/28080 [15:29:34<39:48:21,  7.08s/it]
                                                          
{'loss': 0.6328, 'learning_rate': 0.0004228865089245795, 'epoch': 3.35}

 28%|██▊       | 7841/28080 [15:29:34<39:48:21,  7.08s/it]
 28%|██▊       | 7842/28080 [15:29:42<40:01:57,  7.12s/it]
                                                          
{'loss': 0.6488, 'learning_rate': 0.0004228656788091414, 'epoch': 3.35}

 28%|██▊       | 7842/28080 [15:29:42<40:01:57,  7.12s/it]
 28%|██▊       | 7843/28080 [15:29:49<40:05:40,  7.13s/it]
                                                          
{'loss': 0.6393, 'learning_rate': 0.00042284484639390377, 'epoch': 3.35}

 28%|██▊       | 7843/28080 [15:29:49<40:05:40,  7.13s/it]
 28%|██▊       | 7844/28080 [15:29:56<40:01:50,  7.12s/it]
                                                          
{'loss': 0.6338, 'learning_rate': 0.0004228240116791437, 'epoch': 3.35}

 28%|██▊       | 7844/28080 [15:29:56<40:01:50,  7.12s/it]
 28%|██▊       | 7845/28080 [15:30:03<39:58:38,  7.11s/it]
                                                          
{'loss': 0.626, 'learning_rate': 0.0004228031746651385, 'epoch': 3.35}

 28%|██▊       | 7845/28080 [15:30:03<39:58:38,  7.11s/it]
 28%|██▊       | 7846/28080 [15:30:10<39:57:49,  7.11s/it]
                                                          
{'loss': 0.6226, 'learning_rate': 0.0004227823353521654, 'epoch': 3.35}

 28%|██▊       | 7846/28080 [15:30:10<39:57:49,  7.11s/it]
 28%|██▊       | 7847/28080 [15:30:17<39:49:04,  7.08s/it]
                                                          
{'loss': 0.6329, 'learning_rate': 0.00042276149374050146, 'epoch': 3.35}

 28%|██▊       | 7847/28080 [15:30:17<39:49:04,  7.08s/it]
 28%|██▊       | 7848/28080 [15:30:24<39:48:41,  7.08s/it]
                                                          
{'loss': 0.6393, 'learning_rate': 0.0004227406498304241, 'epoch': 3.35}

 28%|██▊       | 7848/28080 [15:30:24<39:48:41,  7.08s/it]
 28%|██▊       | 7849/28080 [15:30:31<39:50:51,  7.09s/it]
                                                          
{'loss': 0.6182, 'learning_rate': 0.0004227198036222106, 'epoch': 3.35}

 28%|██▊       | 7849/28080 [15:30:31<39:50:51,  7.09s/it]
 28%|██▊       | 7850/28080 [15:30:38<39:50:07,  7.09s/it]
                                                          
{'loss': 0.6489, 'learning_rate': 0.00042269895511613836, 'epoch': 3.35}

 28%|██▊       | 7850/28080 [15:30:38<39:50:07,  7.09s/it]
 28%|██▊       | 7851/28080 [15:30:45<39:52:15,  7.10s/it]
                                                          
{'loss': 0.6212, 'learning_rate': 0.00042267810431248466, 'epoch': 3.35}

 28%|██▊       | 7851/28080 [15:30:45<39:52:15,  7.10s/it]
 28%|██▊       | 7852/28080 [15:30:52<39:51:55,  7.09s/it]
                                                          
{'loss': 0.6188, 'learning_rate': 0.00042265725121152695, 'epoch': 3.35}

 28%|██▊       | 7852/28080 [15:30:52<39:51:55,  7.09s/it]
 28%|██▊       | 7853/28080 [15:31:00<39:55:06,  7.10s/it]
                                                          
{'loss': 0.6405, 'learning_rate': 0.0004226363958135426, 'epoch': 3.35}

 28%|██▊       | 7853/28080 [15:31:00<39:55:06,  7.10s/it]
 28%|██▊       | 7854/28080 [15:31:07<40:02:43,  7.13s/it]
                                                          
{'loss': 0.6223, 'learning_rate': 0.00042261553811880905, 'epoch': 3.36}

 28%|██▊       | 7854/28080 [15:31:07<40:02:43,  7.13s/it]
 28%|██▊       | 7855/28080 [15:31:14<40:06:50,  7.14s/it]
                                                          
{'loss': 0.6645, 'learning_rate': 0.00042259467812760386, 'epoch': 3.36}

 28%|██▊       | 7855/28080 [15:31:14<40:06:50,  7.14s/it]
 28%|██▊       | 7856/28080 [15:31:21<40:06:20,  7.14s/it]
                                                          
{'loss': 0.6418, 'learning_rate': 0.0004225738158402046, 'epoch': 3.36}

 28%|██▊       | 7856/28080 [15:31:21<40:06:20,  7.14s/it]
 28%|██▊       | 7857/28080 [15:31:28<40:05:37,  7.14s/it]
                                                          
{'loss': 0.6232, 'learning_rate': 0.00042255295125688877, 'epoch': 3.36}

 28%|██▊       | 7857/28080 [15:31:28<40:05:37,  7.14s/it]
 28%|██▊       | 7858/28080 [15:31:35<39:55:59,  7.11s/it]
                                                          
{'loss': 0.6159, 'learning_rate': 0.0004225320843779339, 'epoch': 3.36}

 28%|██▊       | 7858/28080 [15:31:35<39:55:59,  7.11s/it]
 28%|██▊       | 7859/28080 [15:31:42<39:55:23,  7.11s/it]
                                                          
{'loss': 0.6243, 'learning_rate': 0.00042251121520361755, 'epoch': 3.36}

 28%|██▊       | 7859/28080 [15:31:42<39:55:23,  7.11s/it]
 28%|██▊       | 7860/28080 [15:31:50<40:02:28,  7.13s/it]
                                                          
{'loss': 0.6084, 'learning_rate': 0.00042249034373421755, 'epoch': 3.36}

 28%|██▊       | 7860/28080 [15:31:50<40:02:28,  7.13s/it]
 28%|██▊       | 7861/28080 [15:31:57<40:00:32,  7.12s/it]
                                                          
{'loss': 0.6265, 'learning_rate': 0.00042246946997001144, 'epoch': 3.36}

 28%|██▊       | 7861/28080 [15:31:57<40:00:32,  7.12s/it]
 28%|██▊       | 7862/28080 [15:32:04<39:51:03,  7.10s/it]
                                                          
{'loss': 0.6179, 'learning_rate': 0.000422448593911277, 'epoch': 3.36}

 28%|██▊       | 7862/28080 [15:32:04<39:51:03,  7.10s/it]
 28%|██▊       | 7863/28080 [15:32:11<39:46:17,  7.08s/it]
                                                          
{'loss': 0.633, 'learning_rate': 0.00042242771555829183, 'epoch': 3.36}

 28%|██▊       | 7863/28080 [15:32:11<39:46:17,  7.08s/it]
 28%|██▊       | 7864/28080 [15:32:18<39:50:45,  7.10s/it]
                                                          
{'loss': 0.6509, 'learning_rate': 0.0004224068349113339, 'epoch': 3.36}

 28%|██▊       | 7864/28080 [15:32:18<39:50:45,  7.10s/it]
 28%|██▊       | 7865/28080 [15:32:25<39:47:09,  7.09s/it]
                                                          
{'loss': 0.6656, 'learning_rate': 0.00042238595197068084, 'epoch': 3.36}

 28%|██▊       | 7865/28080 [15:32:25<39:47:09,  7.09s/it]
 28%|██▊       | 7866/28080 [15:32:32<39:49:09,  7.09s/it]
                                                          
{'loss': 0.6467, 'learning_rate': 0.00042236506673661055, 'epoch': 3.36}

 28%|██▊       | 7866/28080 [15:32:32<39:49:09,  7.09s/it]
 28%|██▊       | 7867/28080 [15:32:39<39:52:05,  7.10s/it]
                                                          
{'loss': 0.6586, 'learning_rate': 0.0004223441792094008, 'epoch': 3.36}

 28%|██▊       | 7867/28080 [15:32:39<39:52:05,  7.10s/it]
 28%|██▊       | 7868/28080 [15:32:46<39:47:27,  7.09s/it]
                                                          
{'loss': 0.6337, 'learning_rate': 0.0004223232893893296, 'epoch': 3.36}

 28%|██▊       | 7868/28080 [15:32:46<39:47:27,  7.09s/it]
 28%|██▊       | 7869/28080 [15:32:53<39:46:32,  7.08s/it]
                                                          
{'loss': 0.6191, 'learning_rate': 0.0004223023972766749, 'epoch': 3.36}

 28%|██▊       | 7869/28080 [15:32:53<39:46:32,  7.08s/it]
 28%|██▊       | 7870/28080 [15:33:00<39:48:46,  7.09s/it]
                                                          
{'loss': 0.6407, 'learning_rate': 0.0004222815028717144, 'epoch': 3.36}

 28%|██▊       | 7870/28080 [15:33:00<39:48:46,  7.09s/it]
 28%|██▊       | 7871/28080 [15:33:08<39:52:14,  7.10s/it]
                                                          
{'loss': 0.6389, 'learning_rate': 0.0004222606061747264, 'epoch': 3.36}

 28%|██▊       | 7871/28080 [15:33:08<39:52:14,  7.10s/it]
 28%|██▊       | 7872/28080 [15:33:15<39:46:31,  7.09s/it]
                                                          
{'loss': 0.6352, 'learning_rate': 0.00042223970718598857, 'epoch': 3.36}

 28%|██▊       | 7872/28080 [15:33:15<39:46:31,  7.09s/it]
 28%|██▊       | 7873/28080 [15:33:22<39:48:12,  7.09s/it]
                                                          
{'loss': 0.6437, 'learning_rate': 0.0004222188059057792, 'epoch': 3.36}

 28%|██▊       | 7873/28080 [15:33:22<39:48:12,  7.09s/it]
 28%|██▊       | 7874/28080 [15:33:29<39:41:39,  7.07s/it]
                                                          
{'loss': 0.6275, 'learning_rate': 0.00042219790233437635, 'epoch': 3.36}

 28%|██▊       | 7874/28080 [15:33:29<39:41:39,  7.07s/it]
 28%|██▊       | 7875/28080 [15:33:36<39:44:53,  7.08s/it]
                                                          
{'loss': 0.637, 'learning_rate': 0.000422176996472058, 'epoch': 3.36}

 28%|██▊       | 7875/28080 [15:33:36<39:44:53,  7.08s/it]
 28%|██▊       | 7876/28080 [15:33:43<39:28:47,  7.03s/it]
                                                          
{'loss': 0.6387, 'learning_rate': 0.0004221560883191023, 'epoch': 3.36}

 28%|██▊       | 7876/28080 [15:33:43<39:28:47,  7.03s/it]
 28%|██▊       | 7877/28080 [15:33:50<39:29:27,  7.04s/it]
                                                          
{'loss': 0.6304, 'learning_rate': 0.0004221351778757875, 'epoch': 3.36}

 28%|██▊       | 7877/28080 [15:33:50<39:29:27,  7.04s/it]
 28%|██▊       | 7878/28080 [15:33:57<39:32:54,  7.05s/it]
                                                          
{'loss': 0.6237, 'learning_rate': 0.00042211426514239173, 'epoch': 3.37}

 28%|██▊       | 7878/28080 [15:33:57<39:32:54,  7.05s/it]
 28%|██▊       | 7879/28080 [15:34:04<39:38:15,  7.06s/it]
                                                          
{'loss': 0.6197, 'learning_rate': 0.00042209335011919314, 'epoch': 3.37}

 28%|██▊       | 7879/28080 [15:34:04<39:38:15,  7.06s/it]
 28%|██▊       | 7880/28080 [15:34:11<39:37:13,  7.06s/it]
                                                          
{'loss': 0.6234, 'learning_rate': 0.0004220724328064702, 'epoch': 3.37}

 28%|██▊       | 7880/28080 [15:34:11<39:37:13,  7.06s/it]
 28%|██▊       | 7881/28080 [15:34:18<39:28:36,  7.04s/it]
                                                          
{'loss': 0.6366, 'learning_rate': 0.000422051513204501, 'epoch': 3.37}

 28%|██▊       | 7881/28080 [15:34:18<39:28:36,  7.04s/it]
 28%|██▊       | 7882/28080 [15:34:25<39:33:46,  7.05s/it]
                                                          
{'loss': 0.6315, 'learning_rate': 0.0004220305913135639, 'epoch': 3.37}

 28%|██▊       | 7882/28080 [15:34:25<39:33:46,  7.05s/it]
 28%|██▊       | 7883/28080 [15:34:32<39:32:26,  7.05s/it]
                                                          
{'loss': 0.6366, 'learning_rate': 0.0004220096671339373, 'epoch': 3.37}

 28%|██▊       | 7883/28080 [15:34:32<39:32:26,  7.05s/it]
 28%|██▊       | 7884/28080 [15:34:39<39:31:36,  7.05s/it]
                                                          
{'loss': 0.63, 'learning_rate': 0.0004219887406658994, 'epoch': 3.37}

 28%|██▊       | 7884/28080 [15:34:39<39:31:36,  7.05s/it]
 28%|██▊       | 7885/28080 [15:34:46<39:47:32,  7.09s/it]
                                                          
{'loss': 0.6385, 'learning_rate': 0.0004219678119097289, 'epoch': 3.37}

 28%|██▊       | 7885/28080 [15:34:46<39:47:32,  7.09s/it]
 28%|██▊       | 7886/28080 [15:34:53<39:46:59,  7.09s/it]
                                                          
{'loss': 0.6656, 'learning_rate': 0.000421946880865704, 'epoch': 3.37}

 28%|██▊       | 7886/28080 [15:34:53<39:46:59,  7.09s/it]
 28%|██▊       | 7887/28080 [15:35:01<39:50:38,  7.10s/it]
                                                          
{'loss': 0.654, 'learning_rate': 0.00042192594753410323, 'epoch': 3.37}

 28%|██▊       | 7887/28080 [15:35:01<39:50:38,  7.10s/it]
 28%|██▊       | 7888/28080 [15:35:08<39:45:11,  7.09s/it]
                                                          
{'loss': 0.6294, 'learning_rate': 0.00042190501191520513, 'epoch': 3.37}

 28%|██▊       | 7888/28080 [15:35:08<39:45:11,  7.09s/it]
 28%|██▊       | 7889/28080 [15:35:15<39:51:15,  7.11s/it]
                                                          
{'loss': 0.6277, 'learning_rate': 0.0004218840740092882, 'epoch': 3.37}

 28%|██▊       | 7889/28080 [15:35:15<39:51:15,  7.11s/it]
 28%|██▊       | 7890/28080 [15:35:22<39:55:02,  7.12s/it]
                                                          
{'loss': 0.6243, 'learning_rate': 0.0004218631338166309, 'epoch': 3.37}

 28%|██▊       | 7890/28080 [15:35:22<39:55:02,  7.12s/it]
 28%|██▊       | 7891/28080 [15:35:29<39:51:04,  7.11s/it]
                                                          
{'loss': 0.6395, 'learning_rate': 0.000421842191337512, 'epoch': 3.37}

 28%|██▊       | 7891/28080 [15:35:29<39:51:04,  7.11s/it]
 28%|██▊       | 7892/28080 [15:35:36<39:46:08,  7.09s/it]
                                                          
{'loss': 0.6296, 'learning_rate': 0.00042182124657221, 'epoch': 3.37}

 28%|██▊       | 7892/28080 [15:35:36<39:46:08,  7.09s/it]
 28%|██▊       | 7893/28080 [15:35:43<39:49:38,  7.10s/it]
                                                          
{'loss': 0.6349, 'learning_rate': 0.0004218002995210035, 'epoch': 3.37}

 28%|██▊       | 7893/28080 [15:35:43<39:49:38,  7.10s/it]
 28%|██▊       | 7894/28080 [15:35:50<39:42:09,  7.08s/it]
                                                          
{'loss': 0.6314, 'learning_rate': 0.0004217793501841714, 'epoch': 3.37}

 28%|██▊       | 7894/28080 [15:35:50<39:42:09,  7.08s/it]
 28%|██▊       | 7895/28080 [15:35:57<39:30:19,  7.05s/it]
                                                          
{'loss': 0.645, 'learning_rate': 0.00042175839856199216, 'epoch': 3.37}

 28%|██▊       | 7895/28080 [15:35:57<39:30:19,  7.05s/it]
 28%|██▊       | 7896/28080 [15:36:04<39:38:23,  7.07s/it]
                                                          
{'loss': 0.6435, 'learning_rate': 0.0004217374446547446, 'epoch': 3.37}

 28%|██▊       | 7896/28080 [15:36:04<39:38:23,  7.07s/it]
 28%|██▊       | 7897/28080 [15:36:11<39:43:10,  7.08s/it]
                                                          
{'loss': 0.6505, 'learning_rate': 0.0004217164884627076, 'epoch': 3.37}

 28%|██▊       | 7897/28080 [15:36:11<39:43:10,  7.08s/it]
 28%|██▊       | 7898/28080 [15:36:19<39:58:32,  7.13s/it]
                                                          
{'loss': 0.6177, 'learning_rate': 0.0004216955299861598, 'epoch': 3.37}

 28%|██▊       | 7898/28080 [15:36:19<39:58:32,  7.13s/it]
 28%|██▊       | 7899/28080 [15:36:26<40:01:05,  7.14s/it]
                                                          
{'loss': 0.6465, 'learning_rate': 0.00042167456922538013, 'epoch': 3.37}

 28%|██▊       | 7899/28080 [15:36:26<40:01:05,  7.14s/it]
 28%|██▊       | 7900/28080 [15:36:33<39:50:03,  7.11s/it]
                                                          
{'loss': 0.6544, 'learning_rate': 0.0004216536061806474, 'epoch': 3.37}

 28%|██▊       | 7900/28080 [15:36:33<39:50:03,  7.11s/it]
 28%|██▊       | 7901/28080 [15:36:40<39:47:37,  7.10s/it]
                                                          
{'loss': 0.6594, 'learning_rate': 0.0004216326408522405, 'epoch': 3.38}

 28%|██▊       | 7901/28080 [15:36:40<39:47:37,  7.10s/it]
 28%|██▊       | 7902/28080 [15:36:47<39:45:19,  7.09s/it]
                                                          
{'loss': 0.6245, 'learning_rate': 0.00042161167324043845, 'epoch': 3.38}

 28%|██▊       | 7902/28080 [15:36:47<39:45:19,  7.09s/it]
 28%|██▊       | 7903/28080 [15:36:54<39:34:35,  7.06s/it]
                                                          
{'loss': 0.645, 'learning_rate': 0.00042159070334552007, 'epoch': 3.38}

 28%|██▊       | 7903/28080 [15:36:54<39:34:35,  7.06s/it]
 28%|██▊       | 7904/28080 [15:37:01<39:39:26,  7.08s/it]
                                                          
{'loss': 0.6468, 'learning_rate': 0.0004215697311677644, 'epoch': 3.38}

 28%|██▊       | 7904/28080 [15:37:01<39:39:26,  7.08s/it]
 28%|██▊       | 7905/28080 [15:37:08<39:47:18,  7.10s/it]
                                                          
{'loss': 0.6099, 'learning_rate': 0.0004215487567074505, 'epoch': 3.38}

 28%|██▊       | 7905/28080 [15:37:08<39:47:18,  7.10s/it]
 28%|██▊       | 7906/28080 [15:37:15<39:47:02,  7.10s/it]
                                                          
{'loss': 0.6336, 'learning_rate': 0.00042152777996485734, 'epoch': 3.38}

 28%|██▊       | 7906/28080 [15:37:15<39:47:02,  7.10s/it]
 28%|██▊       | 7907/28080 [15:37:22<39:36:26,  7.07s/it]
                                                          
{'loss': 0.6415, 'learning_rate': 0.0004215068009402641, 'epoch': 3.38}

 28%|██▊       | 7907/28080 [15:37:22<39:36:26,  7.07s/it]
 28%|██▊       | 7908/28080 [15:37:29<39:38:13,  7.07s/it]
                                                          
{'loss': 0.6129, 'learning_rate': 0.0004214858196339497, 'epoch': 3.38}

 28%|██▊       | 7908/28080 [15:37:29<39:38:13,  7.07s/it]
 28%|██▊       | 7909/28080 [15:37:37<39:39:18,  7.08s/it]
                                                          
{'loss': 0.6335, 'learning_rate': 0.0004214648360461934, 'epoch': 3.38}

 28%|██▊       | 7909/28080 [15:37:37<39:39:18,  7.08s/it]
 28%|██▊       | 7910/28080 [15:37:44<39:41:47,  7.09s/it]
                                                          
{'loss': 0.629, 'learning_rate': 0.00042144385017727436, 'epoch': 3.38}

 28%|██▊       | 7910/28080 [15:37:44<39:41:47,  7.09s/it]
 28%|██▊       | 7911/28080 [15:37:51<39:48:00,  7.10s/it]
                                                          
{'loss': 0.6236, 'learning_rate': 0.0004214228620274718, 'epoch': 3.38}

 28%|██▊       | 7911/28080 [15:37:51<39:48:00,  7.10s/it]
 28%|██▊       | 7912/28080 [15:37:58<39:49:57,  7.11s/it]
                                                          
{'loss': 0.6312, 'learning_rate': 0.0004214018715970649, 'epoch': 3.38}

 28%|██▊       | 7912/28080 [15:37:58<39:49:57,  7.11s/it]
 28%|██▊       | 7913/28080 [15:38:05<39:56:12,  7.13s/it]
                                                          
{'loss': 0.6214, 'learning_rate': 0.00042138087888633286, 'epoch': 3.38}

 28%|██▊       | 7913/28080 [15:38:05<39:56:12,  7.13s/it]
 28%|██▊       | 7914/28080 [15:38:12<39:51:17,  7.11s/it]
                                                          
{'loss': 0.6438, 'learning_rate': 0.00042135988389555506, 'epoch': 3.38}

 28%|██▊       | 7914/28080 [15:38:12<39:51:17,  7.11s/it]
 28%|██▊       | 7915/28080 [15:38:19<39:54:30,  7.12s/it]
                                                          
{'loss': 0.6423, 'learning_rate': 0.0004213388866250109, 'epoch': 3.38}

 28%|██▊       | 7915/28080 [15:38:19<39:54:30,  7.12s/it]
 28%|██▊       | 7916/28080 [15:38:26<39:51:03,  7.11s/it]
                                                          
{'loss': 0.6192, 'learning_rate': 0.00042131788707497944, 'epoch': 3.38}

 28%|██▊       | 7916/28080 [15:38:26<39:51:03,  7.11s/it]
 28%|██▊       | 7917/28080 [15:38:33<39:45:20,  7.10s/it]
                                                          
{'loss': 0.6431, 'learning_rate': 0.0004212968852457403, 'epoch': 3.38}

 28%|██▊       | 7917/28080 [15:38:33<39:45:20,  7.10s/it]
 28%|██▊       | 7918/28080 [15:38:41<39:47:40,  7.11s/it]
                                                          
{'loss': 0.6569, 'learning_rate': 0.0004212758811375728, 'epoch': 3.38}

 28%|██▊       | 7918/28080 [15:38:41<39:47:40,  7.11s/it]
 28%|██▊       | 7919/28080 [15:38:48<40:02:27,  7.15s/it]
                                                          
{'loss': 0.6349, 'learning_rate': 0.0004212548747507564, 'epoch': 3.38}

 28%|██▊       | 7919/28080 [15:38:48<40:02:27,  7.15s/it]
 28%|██▊       | 7920/28080 [15:38:55<40:00:18,  7.14s/it]
                                                          
{'loss': 0.6183, 'learning_rate': 0.00042123386608557064, 'epoch': 3.38}

 28%|██▊       | 7920/28080 [15:38:55<40:00:18,  7.14s/it]
 28%|██▊       | 7921/28080 [15:39:02<39:59:24,  7.14s/it]
                                                          
{'loss': 0.6506, 'learning_rate': 0.0004212128551422949, 'epoch': 3.38}

 28%|██▊       | 7921/28080 [15:39:02<39:59:24,  7.14s/it]
 28%|██▊       | 7922/28080 [15:39:09<39:44:33,  7.10s/it]
                                                          
{'loss': 0.6391, 'learning_rate': 0.00042119184192120876, 'epoch': 3.38}

 28%|██▊       | 7922/28080 [15:39:09<39:44:33,  7.10s/it]
 28%|██▊       | 7923/28080 [15:39:16<39:40:13,  7.09s/it]
                                                          
{'loss': 0.6399, 'learning_rate': 0.00042117082642259177, 'epoch': 3.38}

 28%|██▊       | 7923/28080 [15:39:16<39:40:13,  7.09s/it]
 28%|██▊       | 7924/28080 [15:39:23<39:35:47,  7.07s/it]
                                                          
{'loss': 0.6347, 'learning_rate': 0.0004211498086467235, 'epoch': 3.39}

 28%|██▊       | 7924/28080 [15:39:23<39:35:47,  7.07s/it]
 28%|██▊       | 7925/28080 [15:39:30<39:41:41,  7.09s/it]
                                                          
{'loss': 0.6209, 'learning_rate': 0.0004211287885938836, 'epoch': 3.39}

 28%|██▊       | 7925/28080 [15:39:30<39:41:41,  7.09s/it]
 28%|██▊       | 7926/28080 [15:39:37<39:44:27,  7.10s/it]
                                                          
{'loss': 0.6296, 'learning_rate': 0.00042110776626435166, 'epoch': 3.39}

 28%|██▊       | 7926/28080 [15:39:37<39:44:27,  7.10s/it]
 28%|██▊       | 7927/28080 [15:39:44<39:39:17,  7.08s/it]
                                                          
{'loss': 0.6606, 'learning_rate': 0.0004210867416584074, 'epoch': 3.39}

 28%|██▊       | 7927/28080 [15:39:44<39:39:17,  7.08s/it]
 28%|██▊       | 7928/28080 [15:39:51<39:32:00,  7.06s/it]
                                                          
{'loss': 0.6304, 'learning_rate': 0.00042106571477633066, 'epoch': 3.39}

 28%|██▊       | 7928/28080 [15:39:51<39:32:00,  7.06s/it]
 28%|██▊       | 7929/28080 [15:39:59<39:36:45,  7.08s/it]
                                                          
{'loss': 0.634, 'learning_rate': 0.00042104468561840106, 'epoch': 3.39}

 28%|██▊       | 7929/28080 [15:39:59<39:36:45,  7.08s/it]
 28%|██▊       | 7930/28080 [15:40:06<39:31:03,  7.06s/it]
                                                          
{'loss': 0.6291, 'learning_rate': 0.0004210236541848983, 'epoch': 3.39}

 28%|██▊       | 7930/28080 [15:40:06<39:31:03,  7.06s/it]
 28%|██▊       | 7931/28080 [15:40:13<39:36:13,  7.08s/it]
                                                          
{'loss': 0.6387, 'learning_rate': 0.00042100262047610227, 'epoch': 3.39}

 28%|██▊       | 7931/28080 [15:40:13<39:36:13,  7.08s/it]
 28%|██▊       | 7932/28080 [15:40:20<39:43:39,  7.10s/it]
                                                          
{'loss': 0.6332, 'learning_rate': 0.0004209815844922928, 'epoch': 3.39}

 28%|██▊       | 7932/28080 [15:40:20<39:43:39,  7.10s/it]
 28%|██▊       | 7933/28080 [15:40:27<39:41:38,  7.09s/it]
                                                          
{'loss': 0.6309, 'learning_rate': 0.0004209605462337497, 'epoch': 3.39}

 28%|██▊       | 7933/28080 [15:40:27<39:41:38,  7.09s/it]
 28%|██▊       | 7934/28080 [15:40:34<39:33:33,  7.07s/it]
                                                          
{'loss': 0.6444, 'learning_rate': 0.000420939505700753, 'epoch': 3.39}

 28%|██▊       | 7934/28080 [15:40:34<39:33:33,  7.07s/it]
 28%|██▊       | 7935/28080 [15:40:41<39:41:50,  7.09s/it]
                                                          
{'loss': 0.6198, 'learning_rate': 0.0004209184628935824, 'epoch': 3.39}

 28%|██▊       | 7935/28080 [15:40:41<39:41:50,  7.09s/it]
 28%|██▊       | 7936/28080 [15:40:48<39:46:20,  7.11s/it]
                                                          
{'loss': 0.6196, 'learning_rate': 0.0004208974178125181, 'epoch': 3.39}

 28%|██▊       | 7936/28080 [15:40:48<39:46:20,  7.11s/it]
 28%|██▊       | 7937/28080 [15:40:55<39:43:49,  7.10s/it]
                                                          
{'loss': 0.6364, 'learning_rate': 0.0004208763704578399, 'epoch': 3.39}

 28%|██▊       | 7937/28080 [15:40:55<39:43:49,  7.10s/it]
 28%|██▊       | 7938/28080 [15:41:02<39:43:22,  7.10s/it]
                                                          
{'loss': 0.631, 'learning_rate': 0.0004208553208298278, 'epoch': 3.39}

 28%|██▊       | 7938/28080 [15:41:02<39:43:22,  7.10s/it]
 28%|██▊       | 7939/28080 [15:41:10<39:41:42,  7.10s/it]
                                                          
{'loss': 0.6366, 'learning_rate': 0.00042083426892876205, 'epoch': 3.39}

 28%|██▊       | 7939/28080 [15:41:10<39:41:42,  7.10s/it]
 28%|██▊       | 7940/28080 [15:41:17<39:42:01,  7.10s/it]
                                                          
{'loss': 0.6363, 'learning_rate': 0.00042081321475492253, 'epoch': 3.39}

 28%|██▊       | 7940/28080 [15:41:17<39:42:01,  7.10s/it]
 28%|██▊       | 7941/28080 [15:41:24<39:34:54,  7.08s/it]
                                                          
{'loss': 0.6406, 'learning_rate': 0.0004207921583085894, 'epoch': 3.39}

 28%|██▊       | 7941/28080 [15:41:24<39:34:54,  7.08s/it]
 28%|██▊       | 7942/28080 [15:41:31<39:40:24,  7.09s/it]
                                                          
{'loss': 0.6349, 'learning_rate': 0.00042077109959004277, 'epoch': 3.39}

 28%|██▊       | 7942/28080 [15:41:31<39:40:24,  7.09s/it]
 28%|██▊       | 7943/28080 [15:41:38<39:39:23,  7.09s/it]
                                                          
{'loss': 0.63, 'learning_rate': 0.00042075003859956295, 'epoch': 3.39}

 28%|██▊       | 7943/28080 [15:41:38<39:39:23,  7.09s/it]
 28%|██▊       | 7944/28080 [15:41:45<39:45:48,  7.11s/it]
                                                          
{'loss': 0.6311, 'learning_rate': 0.00042072897533742995, 'epoch': 3.39}

 28%|██▊       | 7944/28080 [15:41:45<39:45:48,  7.11s/it]
 28%|██▊       | 7945/28080 [15:41:52<39:47:10,  7.11s/it]
                                                          
{'loss': 0.6168, 'learning_rate': 0.000420707909803924, 'epoch': 3.39}

 28%|██▊       | 7945/28080 [15:41:52<39:47:10,  7.11s/it]
 28%|██▊       | 7946/28080 [15:41:59<39:45:49,  7.11s/it]
                                                          
{'loss': 0.6222, 'learning_rate': 0.00042068684199932555, 'epoch': 3.39}

 28%|██▊       | 7946/28080 [15:41:59<39:45:49,  7.11s/it]
 28%|██▊       | 7947/28080 [15:42:06<39:46:15,  7.11s/it]
                                                          
{'loss': 0.6397, 'learning_rate': 0.0004206657719239146, 'epoch': 3.39}

 28%|██▊       | 7947/28080 [15:42:06<39:46:15,  7.11s/it]
 28%|██▊       | 7948/28080 [15:42:14<40:00:41,  7.15s/it]
                                                          
{'loss': 0.654, 'learning_rate': 0.0004206446995779718, 'epoch': 3.4}

 28%|██▊       | 7948/28080 [15:42:14<40:00:41,  7.15s/it]
 28%|██▊       | 7949/28080 [15:42:21<39:52:14,  7.13s/it]
                                                          
{'loss': 0.6139, 'learning_rate': 0.0004206236249617772, 'epoch': 3.4}

 28%|██▊       | 7949/28080 [15:42:21<39:52:14,  7.13s/it]
 28%|██▊       | 7950/28080 [15:42:28<39:44:59,  7.11s/it]
                                                          
{'loss': 0.6289, 'learning_rate': 0.0004206025480756113, 'epoch': 3.4}

 28%|██▊       | 7950/28080 [15:42:28<39:44:59,  7.11s/it]
 28%|██▊       | 7951/28080 [15:42:35<39:35:57,  7.08s/it]
                                                          
{'loss': 0.6397, 'learning_rate': 0.0004205814689197546, 'epoch': 3.4}

 28%|██▊       | 7951/28080 [15:42:35<39:35:57,  7.08s/it]
 28%|██▊       | 7952/28080 [15:42:42<39:40:44,  7.10s/it]
                                                          
{'loss': 0.6409, 'learning_rate': 0.0004205603874944873, 'epoch': 3.4}

 28%|██▊       | 7952/28080 [15:42:42<39:40:44,  7.10s/it]
 28%|██▊       | 7953/28080 [15:42:49<39:38:03,  7.09s/it]
                                                          
{'loss': 0.6356, 'learning_rate': 0.00042053930380009006, 'epoch': 3.4}

 28%|██▊       | 7953/28080 [15:42:49<39:38:03,  7.09s/it]
 28%|██▊       | 7954/28080 [15:42:56<39:36:33,  7.09s/it]
                                                          
{'loss': 0.6644, 'learning_rate': 0.0004205182178368433, 'epoch': 3.4}

 28%|██▊       | 7954/28080 [15:42:56<39:36:33,  7.09s/it]
 28%|██▊       | 7955/28080 [15:43:03<39:41:05,  7.10s/it]
                                                          
{'loss': 0.6341, 'learning_rate': 0.00042049712960502754, 'epoch': 3.4}

 28%|██▊       | 7955/28080 [15:43:03<39:41:05,  7.10s/it]
 28%|██▊       | 7956/28080 [15:43:10<39:37:29,  7.09s/it]
                                                          
{'loss': 0.6284, 'learning_rate': 0.00042047603910492343, 'epoch': 3.4}

 28%|██▊       | 7956/28080 [15:43:10<39:37:29,  7.09s/it]
 28%|██▊       | 7957/28080 [15:43:17<39:33:37,  7.08s/it]
                                                          
{'loss': 0.6302, 'learning_rate': 0.0004204549463368115, 'epoch': 3.4}

 28%|██▊       | 7957/28080 [15:43:17<39:33:37,  7.08s/it]
 28%|██▊       | 7958/28080 [15:43:24<39:35:22,  7.08s/it]
                                                          
{'loss': 0.631, 'learning_rate': 0.0004204338513009722, 'epoch': 3.4}

 28%|██▊       | 7958/28080 [15:43:24<39:35:22,  7.08s/it]
 28%|██▊       | 7959/28080 [15:43:31<39:30:11,  7.07s/it]
                                                          
{'loss': 0.6451, 'learning_rate': 0.00042041275399768655, 'epoch': 3.4}

 28%|██▊       | 7959/28080 [15:43:31<39:30:11,  7.07s/it]
 28%|██▊       | 7960/28080 [15:43:39<39:36:47,  7.09s/it]
                                                          
{'loss': 0.6473, 'learning_rate': 0.0004203916544272349, 'epoch': 3.4}

 28%|██▊       | 7960/28080 [15:43:39<39:36:47,  7.09s/it]
 28%|██▊       | 7961/28080 [15:43:46<39:37:02,  7.09s/it]
                                                          
{'loss': 0.626, 'learning_rate': 0.0004203705525898981, 'epoch': 3.4}

 28%|██▊       | 7961/28080 [15:43:46<39:37:02,  7.09s/it]
 28%|██▊       | 7962/28080 [15:43:53<39:27:18,  7.06s/it]
                                                          
{'loss': 0.6112, 'learning_rate': 0.0004203494484859568, 'epoch': 3.4}

 28%|██▊       | 7962/28080 [15:43:53<39:27:18,  7.06s/it]
 28%|██▊       | 7963/28080 [15:44:00<39:47:11,  7.12s/it]
                                                          
{'loss': 0.6542, 'learning_rate': 0.00042032834211569193, 'epoch': 3.4}

 28%|██▊       | 7963/28080 [15:44:00<39:47:11,  7.12s/it]
 28%|██▊       | 7964/28080 [15:44:07<39:49:59,  7.13s/it]
                                                          
{'loss': 0.6316, 'learning_rate': 0.0004203072334793841, 'epoch': 3.4}

 28%|██▊       | 7964/28080 [15:44:07<39:49:59,  7.13s/it]
 28%|██▊       | 7965/28080 [15:44:14<39:46:59,  7.12s/it]
                                                          
{'loss': 0.6339, 'learning_rate': 0.00042028612257731426, 'epoch': 3.4}

 28%|██▊       | 7965/28080 [15:44:14<39:46:59,  7.12s/it]
 28%|██▊       | 7966/28080 [15:44:21<39:43:21,  7.11s/it]
                                                          
{'loss': 0.616, 'learning_rate': 0.0004202650094097632, 'epoch': 3.4}

 28%|██▊       | 7966/28080 [15:44:21<39:43:21,  7.11s/it]
 28%|██▊       | 7967/28080 [15:44:28<39:34:07,  7.08s/it]
                                                          
{'loss': 0.6108, 'learning_rate': 0.0004202438939770119, 'epoch': 3.4}

 28%|██▊       | 7967/28080 [15:44:28<39:34:07,  7.08s/it]
 28%|██▊       | 7968/28080 [15:44:35<39:32:25,  7.08s/it]
                                                          
{'loss': 0.6317, 'learning_rate': 0.00042022277627934114, 'epoch': 3.4}

 28%|██▊       | 7968/28080 [15:44:35<39:32:25,  7.08s/it]
 28%|██▊       | 7969/28080 [15:44:42<39:35:48,  7.09s/it]
                                                          
{'loss': 0.6284, 'learning_rate': 0.000420201656317032, 'epoch': 3.4}

 28%|██▊       | 7969/28080 [15:44:42<39:35:48,  7.09s/it]
 28%|██▊       | 7970/28080 [15:44:49<39:28:17,  7.07s/it]
                                                          
{'loss': 0.639, 'learning_rate': 0.00042018053409036545, 'epoch': 3.4}

 28%|██▊       | 7970/28080 [15:44:49<39:28:17,  7.07s/it]
 28%|██▊       | 7971/28080 [15:44:57<39:38:35,  7.10s/it]
                                                          
{'loss': 0.6401, 'learning_rate': 0.0004201594095996224, 'epoch': 3.41}

 28%|██▊       | 7971/28080 [15:44:57<39:38:35,  7.10s/it]
 28%|██▊       | 7972/28080 [15:45:04<39:43:32,  7.11s/it]
                                                          
{'loss': 0.638, 'learning_rate': 0.000420138282845084, 'epoch': 3.41}

 28%|██▊       | 7972/28080 [15:45:04<39:43:32,  7.11s/it]
 28%|██▊       | 7973/28080 [15:45:11<39:36:37,  7.09s/it]
                                                          
{'loss': 0.6474, 'learning_rate': 0.00042011715382703126, 'epoch': 3.41}

 28%|██▊       | 7973/28080 [15:45:11<39:36:37,  7.09s/it]
 28%|██▊       | 7974/28080 [15:45:18<39:41:06,  7.11s/it]
                                                          
{'loss': 0.6336, 'learning_rate': 0.00042009602254574523, 'epoch': 3.41}

 28%|██▊       | 7974/28080 [15:45:18<39:41:06,  7.11s/it]
 28%|██▊       | 7975/28080 [15:45:25<39:37:17,  7.09s/it]
                                                          
{'loss': 0.6322, 'learning_rate': 0.00042007488900150716, 'epoch': 3.41}

 28%|██▊       | 7975/28080 [15:45:25<39:37:17,  7.09s/it]
 28%|██▊       | 7976/28080 [15:45:32<39:26:08,  7.06s/it]
                                                          
{'loss': 0.6442, 'learning_rate': 0.00042005375319459815, 'epoch': 3.41}

 28%|██▊       | 7976/28080 [15:45:32<39:26:08,  7.06s/it]
 28%|██▊       | 7977/28080 [15:45:39<39:30:35,  7.08s/it]
                                                          
{'loss': 0.6263, 'learning_rate': 0.0004200326151252993, 'epoch': 3.41}

 28%|██▊       | 7977/28080 [15:45:39<39:30:35,  7.08s/it]
 28%|██▊       | 7978/28080 [15:45:46<39:37:20,  7.10s/it]
                                                          
{'loss': 0.6065, 'learning_rate': 0.000420011474793892, 'epoch': 3.41}

 28%|██▊       | 7978/28080 [15:45:46<39:37:20,  7.10s/it]
 28%|██▊       | 7979/28080 [15:45:53<39:38:57,  7.10s/it]
                                                          
{'loss': 0.6511, 'learning_rate': 0.0004199903322006574, 'epoch': 3.41}

 28%|██▊       | 7979/28080 [15:45:53<39:38:57,  7.10s/it]
 28%|██▊       | 7980/28080 [15:46:01<39:42:52,  7.11s/it]
                                                          
{'loss': 0.6417, 'learning_rate': 0.00041996918734587684, 'epoch': 3.41}

 28%|██▊       | 7980/28080 [15:46:01<39:42:52,  7.11s/it]
 28%|██▊       | 7981/28080 [15:46:08<39:43:35,  7.12s/it]
                                                          
{'loss': 0.6373, 'learning_rate': 0.0004199480402298315, 'epoch': 3.41}

 28%|██▊       | 7981/28080 [15:46:08<39:43:35,  7.12s/it]
 28%|██▊       | 7982/28080 [15:46:15<39:46:47,  7.13s/it]
                                                          
{'loss': 0.6488, 'learning_rate': 0.00041992689085280287, 'epoch': 3.41}

 28%|██▊       | 7982/28080 [15:46:15<39:46:47,  7.13s/it]
 28%|██▊       | 7983/28080 [15:46:22<39:47:35,  7.13s/it]
                                                          
{'loss': 0.6072, 'learning_rate': 0.0004199057392150722, 'epoch': 3.41}

 28%|██▊       | 7983/28080 [15:46:22<39:47:35,  7.13s/it]
 28%|██▊       | 7984/28080 [15:46:29<39:37:57,  7.10s/it]
                                                          
{'loss': 0.6189, 'learning_rate': 0.0004198845853169211, 'epoch': 3.41}

 28%|██▊       | 7984/28080 [15:46:29<39:37:57,  7.10s/it]
 28%|██▊       | 7985/28080 [15:46:36<39:44:45,  7.12s/it]
                                                          
{'loss': 0.6289, 'learning_rate': 0.00041986342915863075, 'epoch': 3.41}

 28%|██▊       | 7985/28080 [15:46:36<39:44:45,  7.12s/it]
 28%|██▊       | 7986/28080 [15:46:43<39:43:28,  7.12s/it]
                                                          
{'loss': 0.6101, 'learning_rate': 0.00041984227074048263, 'epoch': 3.41}

 28%|██▊       | 7986/28080 [15:46:43<39:43:28,  7.12s/it]
 28%|██▊       | 7987/28080 [15:46:50<39:29:33,  7.08s/it]
                                                          
{'loss': 0.6572, 'learning_rate': 0.00041982111006275846, 'epoch': 3.41}

 28%|██▊       | 7987/28080 [15:46:50<39:29:33,  7.08s/it]
 28%|██▊       | 7988/28080 [15:46:57<39:26:42,  7.07s/it]
                                                          
{'loss': 0.6505, 'learning_rate': 0.00041979994712573954, 'epoch': 3.41}

 28%|██▊       | 7988/28080 [15:46:57<39:26:42,  7.07s/it]
 28%|██▊       | 7989/28080 [15:47:04<39:40:20,  7.11s/it]
                                                          
{'loss': 0.6238, 'learning_rate': 0.00041977878192970755, 'epoch': 3.41}

 28%|██▊       | 7989/28080 [15:47:04<39:40:20,  7.11s/it]
 28%|██▊       | 7990/28080 [15:47:12<39:48:50,  7.13s/it]
                                                          
{'loss': 0.6246, 'learning_rate': 0.000419757614474944, 'epoch': 3.41}

 28%|██▊       | 7990/28080 [15:47:12<39:48:50,  7.13s/it]
 28%|██▊       | 7991/28080 [15:47:19<39:36:35,  7.10s/it]
                                                          
{'loss': 0.6229, 'learning_rate': 0.00041973644476173046, 'epoch': 3.41}

 28%|██▊       | 7991/28080 [15:47:19<39:36:35,  7.10s/it]
 28%|██▊       | 7992/28080 [15:47:26<39:37:50,  7.10s/it]
                                                          
{'loss': 0.6367, 'learning_rate': 0.00041971527279034866, 'epoch': 3.41}

 28%|██▊       | 7992/28080 [15:47:26<39:37:50,  7.10s/it]
 28%|██▊       | 7993/28080 [15:47:33<39:38:07,  7.10s/it]
                                                          
{'loss': 0.6073, 'learning_rate': 0.0004196940985610803, 'epoch': 3.41}

 28%|██▊       | 7993/28080 [15:47:33<39:38:07,  7.10s/it]
 28%|██▊       | 7994/28080 [15:47:40<39:45:09,  7.12s/it]
                                                          
{'loss': 0.6151, 'learning_rate': 0.0004196729220742069, 'epoch': 3.41}

 28%|██▊       | 7994/28080 [15:47:40<39:45:09,  7.12s/it]
 28%|██▊       | 7995/28080 [15:47:47<39:40:37,  7.11s/it]
                                                          
{'loss': 0.6159, 'learning_rate': 0.00041965174333001044, 'epoch': 3.42}

 28%|██▊       | 7995/28080 [15:47:47<39:40:37,  7.11s/it]
 28%|██▊       | 7996/28080 [15:47:54<39:26:37,  7.07s/it]
                                                          
{'loss': 0.6407, 'learning_rate': 0.0004196305623287725, 'epoch': 3.42}

 28%|██▊       | 7996/28080 [15:47:54<39:26:37,  7.07s/it]
 28%|██▊       | 7997/28080 [15:48:01<39:31:23,  7.08s/it]
                                                          
{'loss': 0.6557, 'learning_rate': 0.000419609379070775, 'epoch': 3.42}

 28%|██▊       | 7997/28080 [15:48:01<39:31:23,  7.08s/it]
 28%|██▊       | 7998/28080 [15:48:08<39:25:25,  7.07s/it]
                                                          
{'loss': 0.6422, 'learning_rate': 0.00041958819355629955, 'epoch': 3.42}

 28%|██▊       | 7998/28080 [15:48:08<39:25:25,  7.07s/it]
 28%|██▊       | 7999/28080 [15:48:15<39:26:53,  7.07s/it]
                                                          
{'loss': 0.6385, 'learning_rate': 0.00041956700578562825, 'epoch': 3.42}

 28%|██▊       | 7999/28080 [15:48:15<39:26:53,  7.07s/it]
 28%|██▊       | 8000/28080 [15:48:22<39:31:32,  7.09s/it]
                                                          
{'loss': 0.6505, 'learning_rate': 0.0004195458157590428, 'epoch': 3.42}

 28%|██▊       | 8000/28080 [15:48:22<39:31:32,  7.09s/it]
 28%|██▊       | 8001/28080 [15:48:29<39:20:33,  7.05s/it]
                                                          
{'loss': 0.6396, 'learning_rate': 0.0004195246234768252, 'epoch': 3.42}

 28%|██▊       | 8001/28080 [15:48:29<39:20:33,  7.05s/it]
 28%|██▊       | 8002/28080 [15:48:37<39:26:23,  7.07s/it]
                                                          
{'loss': 0.6149, 'learning_rate': 0.0004195034289392574, 'epoch': 3.42}

 28%|██▊       | 8002/28080 [15:48:37<39:26:23,  7.07s/it]
 29%|██▊       | 8003/28080 [15:48:44<39:29:13,  7.08s/it]
                                                          
{'loss': 0.6403, 'learning_rate': 0.0004194822321466213, 'epoch': 3.42}

 29%|██▊       | 8003/28080 [15:48:44<39:29:13,  7.08s/it]
 29%|██▊       | 8004/28080 [15:48:51<39:47:01,  7.13s/it]
                                                          
{'loss': 0.6198, 'learning_rate': 0.000419461033099199, 'epoch': 3.42}

 29%|██▊       | 8004/28080 [15:48:51<39:47:01,  7.13s/it]
 29%|██▊       | 8005/28080 [15:48:58<39:40:57,  7.12s/it]
                                                          
{'loss': 0.6173, 'learning_rate': 0.0004194398317972724, 'epoch': 3.42}

 29%|██▊       | 8005/28080 [15:48:58<39:40:57,  7.12s/it]
 29%|██▊       | 8006/28080 [15:49:05<39:40:48,  7.12s/it]
                                                          
{'loss': 0.635, 'learning_rate': 0.0004194186282411237, 'epoch': 3.42}

 29%|██▊       | 8006/28080 [15:49:05<39:40:48,  7.12s/it]
 29%|██▊       | 8007/28080 [15:49:12<39:41:03,  7.12s/it]
                                                          
{'loss': 0.6392, 'learning_rate': 0.00041939742243103493, 'epoch': 3.42}

 29%|██▊       | 8007/28080 [15:49:12<39:41:03,  7.12s/it]
 29%|██▊       | 8008/28080 [15:49:19<39:37:18,  7.11s/it]
                                                          
{'loss': 0.6626, 'learning_rate': 0.00041937621436728825, 'epoch': 3.42}

 29%|██▊       | 8008/28080 [15:49:19<39:37:18,  7.11s/it]
 29%|██▊       | 8009/28080 [15:49:26<39:27:08,  7.08s/it]
                                                          
{'loss': 0.6605, 'learning_rate': 0.0004193550040501657, 'epoch': 3.42}

 29%|██▊       | 8009/28080 [15:49:26<39:27:08,  7.08s/it]
 29%|██▊       | 8010/28080 [15:49:34<39:37:43,  7.11s/it]
                                                          
{'loss': 0.6268, 'learning_rate': 0.00041933379147994954, 'epoch': 3.42}

 29%|██▊       | 8010/28080 [15:49:34<39:37:43,  7.11s/it]
 29%|██▊       | 8011/28080 [15:49:41<39:37:01,  7.11s/it]
                                                          
{'loss': 0.6295, 'learning_rate': 0.000419312576656922, 'epoch': 3.42}

 29%|██▊       | 8011/28080 [15:49:41<39:37:01,  7.11s/it]
 29%|██▊       | 8012/28080 [15:49:48<39:35:41,  7.10s/it]
                                                          
{'loss': 0.6163, 'learning_rate': 0.0004192913595813653, 'epoch': 3.42}

 29%|██▊       | 8012/28080 [15:49:48<39:35:41,  7.10s/it]
 29%|██▊       | 8013/28080 [15:49:55<39:33:15,  7.10s/it]
                                                          
{'loss': 0.6426, 'learning_rate': 0.0004192701402535617, 'epoch': 3.42}

 29%|██▊       | 8013/28080 [15:49:55<39:33:15,  7.10s/it]
 29%|██▊       | 8014/28080 [15:50:02<39:33:33,  7.10s/it]
                                                          
{'loss': 0.653, 'learning_rate': 0.0004192489186737935, 'epoch': 3.42}

 29%|██▊       | 8014/28080 [15:50:02<39:33:33,  7.10s/it]
 29%|██▊       | 8015/28080 [15:50:09<39:37:01,  7.11s/it]
                                                          
{'loss': 0.63, 'learning_rate': 0.000419227694842343, 'epoch': 3.42}

 29%|██▊       | 8015/28080 [15:50:09<39:37:01,  7.11s/it]
 29%|██▊       | 8016/28080 [15:50:16<39:42:01,  7.12s/it]
                                                          
{'loss': 0.6322, 'learning_rate': 0.00041920646875949274, 'epoch': 3.42}

 29%|██▊       | 8016/28080 [15:50:16<39:42:01,  7.12s/it]
 29%|██▊       | 8017/28080 [15:50:23<39:39:40,  7.12s/it]
                                                          
{'loss': 0.6309, 'learning_rate': 0.00041918524042552485, 'epoch': 3.42}

 29%|██▊       | 8017/28080 [15:50:23<39:39:40,  7.12s/it]
 29%|██▊       | 8018/28080 [15:50:30<39:26:24,  7.08s/it]
                                                          
{'loss': 0.6562, 'learning_rate': 0.00041916400984072196, 'epoch': 3.43}

 29%|██▊       | 8018/28080 [15:50:30<39:26:24,  7.08s/it]
 29%|██▊       | 8019/28080 [15:50:37<39:20:02,  7.06s/it]
                                                          
{'loss': 0.6429, 'learning_rate': 0.0004191427770053664, 'epoch': 3.43}

 29%|██▊       | 8019/28080 [15:50:37<39:20:02,  7.06s/it]
 29%|██▊       | 8020/28080 [15:50:44<39:12:02,  7.04s/it]
                                                          
{'loss': 0.6309, 'learning_rate': 0.00041912154191974064, 'epoch': 3.43}

 29%|██▊       | 8020/28080 [15:50:44<39:12:02,  7.04s/it]
 29%|██▊       | 8021/28080 [15:50:51<39:17:30,  7.05s/it]
                                                          
{'loss': 0.6364, 'learning_rate': 0.0004191003045841273, 'epoch': 3.43}

 29%|██▊       | 8021/28080 [15:50:51<39:17:30,  7.05s/it]
 29%|██▊       | 8022/28080 [15:50:58<39:11:18,  7.03s/it]
                                                          
{'loss': 0.6538, 'learning_rate': 0.0004190790649988089, 'epoch': 3.43}

 29%|██▊       | 8022/28080 [15:50:58<39:11:18,  7.03s/it]
 29%|██▊       | 8023/28080 [15:51:05<39:11:53,  7.04s/it]
                                                          
{'loss': 0.6444, 'learning_rate': 0.00041905782316406786, 'epoch': 3.43}

 29%|██▊       | 8023/28080 [15:51:05<39:11:53,  7.04s/it]
 29%|██▊       | 8024/28080 [15:51:13<39:24:27,  7.07s/it]
                                                          
{'loss': 0.6306, 'learning_rate': 0.0004190365790801869, 'epoch': 3.43}

 29%|██▊       | 8024/28080 [15:51:13<39:24:27,  7.07s/it]
 29%|██▊       | 8025/28080 [15:51:20<39:29:20,  7.09s/it]
                                                          
{'loss': 0.6299, 'learning_rate': 0.00041901533274744875, 'epoch': 3.43}

 29%|██▊       | 8025/28080 [15:51:20<39:29:20,  7.09s/it]
 29%|██▊       | 8026/28080 [15:51:27<39:38:03,  7.11s/it]
                                                          
{'loss': 0.6138, 'learning_rate': 0.0004189940841661358, 'epoch': 3.43}

 29%|██▊       | 8026/28080 [15:51:27<39:38:03,  7.11s/it]
 29%|██▊       | 8027/28080 [15:51:34<39:37:49,  7.11s/it]
                                                          
{'loss': 0.6222, 'learning_rate': 0.000418972833336531, 'epoch': 3.43}

 29%|██▊       | 8027/28080 [15:51:34<39:37:49,  7.11s/it]
 29%|██▊       | 8028/28080 [15:51:41<39:27:02,  7.08s/it]
                                                          
{'loss': 0.6331, 'learning_rate': 0.000418951580258917, 'epoch': 3.43}

 29%|██▊       | 8028/28080 [15:51:41<39:27:02,  7.08s/it]
 29%|██▊       | 8029/28080 [15:51:48<39:24:55,  7.08s/it]
                                                          
{'loss': 0.6204, 'learning_rate': 0.00041893032493357655, 'epoch': 3.43}

 29%|██▊       | 8029/28080 [15:51:48<39:24:55,  7.08s/it]
 29%|██▊       | 8030/28080 [15:51:55<39:17:04,  7.05s/it]
                                                          
{'loss': 0.6383, 'learning_rate': 0.00041890906736079226, 'epoch': 3.43}

 29%|██▊       | 8030/28080 [15:51:55<39:17:04,  7.05s/it]
 29%|██▊       | 8031/28080 [15:52:02<39:12:42,  7.04s/it]
                                                          
{'loss': 0.6295, 'learning_rate': 0.00041888780754084713, 'epoch': 3.43}

 29%|██▊       | 8031/28080 [15:52:02<39:12:42,  7.04s/it]
 29%|██▊       | 8032/28080 [15:52:09<39:10:36,  7.03s/it]
                                                          
{'loss': 0.6667, 'learning_rate': 0.000418866545474024, 'epoch': 3.43}

 29%|██▊       | 8032/28080 [15:52:09<39:10:36,  7.03s/it]
 29%|██▊       | 8033/28080 [15:52:16<39:12:19,  7.04s/it]
                                                          
{'loss': 0.6286, 'learning_rate': 0.0004188452811606057, 'epoch': 3.43}

 29%|██▊       | 8033/28080 [15:52:16<39:12:19,  7.04s/it]
 29%|██▊       | 8034/28080 [15:52:23<39:18:12,  7.06s/it]
                                                          
{'loss': 0.6377, 'learning_rate': 0.000418824014600875, 'epoch': 3.43}

 29%|██▊       | 8034/28080 [15:52:23<39:18:12,  7.06s/it]
 29%|██▊       | 8035/28080 [15:52:30<39:25:43,  7.08s/it]
                                                          
{'loss': 0.6136, 'learning_rate': 0.00041880274579511514, 'epoch': 3.43}

 29%|██▊       | 8035/28080 [15:52:30<39:25:43,  7.08s/it]
 29%|██▊       | 8036/28080 [15:52:38<39:39:14,  7.12s/it]
                                                          
{'loss': 0.6315, 'learning_rate': 0.00041878147474360886, 'epoch': 3.43}

 29%|██▊       | 8036/28080 [15:52:38<39:39:14,  7.12s/it]
 29%|██▊       | 8037/28080 [15:52:45<39:25:35,  7.08s/it]
                                                          
{'loss': 0.6464, 'learning_rate': 0.00041876020144663906, 'epoch': 3.43}

 29%|██▊       | 8037/28080 [15:52:45<39:25:35,  7.08s/it]
 29%|██▊       | 8038/28080 [15:52:52<39:26:50,  7.09s/it]
                                                          
{'loss': 0.652, 'learning_rate': 0.0004187389259044889, 'epoch': 3.43}

 29%|██▊       | 8038/28080 [15:52:52<39:26:50,  7.09s/it]
 29%|██▊       | 8039/28080 [15:52:59<39:21:24,  7.07s/it]
                                                          
{'loss': 0.6142, 'learning_rate': 0.00041871764811744153, 'epoch': 3.43}

 29%|██▊       | 8039/28080 [15:52:59<39:21:24,  7.07s/it]
 29%|██▊       | 8040/28080 [15:53:06<39:20:15,  7.07s/it]
                                                          
{'loss': 0.6368, 'learning_rate': 0.00041869636808577977, 'epoch': 3.43}

 29%|██▊       | 8040/28080 [15:53:06<39:20:15,  7.07s/it]
 29%|██▊       | 8041/28080 [15:53:13<39:22:20,  7.07s/it]
                                                          
{'loss': 0.6165, 'learning_rate': 0.00041867508580978693, 'epoch': 3.44}

 29%|██▊       | 8041/28080 [15:53:13<39:22:20,  7.07s/it]
 29%|██▊       | 8042/28080 [15:53:20<39:23:55,  7.08s/it]
                                                          
{'loss': 0.6167, 'learning_rate': 0.00041865380128974604, 'epoch': 3.44}

 29%|██▊       | 8042/28080 [15:53:20<39:23:55,  7.08s/it]
 29%|██▊       | 8043/28080 [15:53:27<39:21:24,  7.07s/it]
                                                          
{'loss': 0.6411, 'learning_rate': 0.0004186325145259404, 'epoch': 3.44}

 29%|██▊       | 8043/28080 [15:53:27<39:21:24,  7.07s/it]
 29%|██▊       | 8044/28080 [15:53:34<39:22:59,  7.08s/it]
                                                          
{'loss': 0.625, 'learning_rate': 0.00041861122551865306, 'epoch': 3.44}

 29%|██▊       | 8044/28080 [15:53:34<39:22:59,  7.08s/it]
 29%|██▊       | 8045/28080 [15:53:41<39:14:12,  7.05s/it]
                                                          
{'loss': 0.6308, 'learning_rate': 0.0004185899342681673, 'epoch': 3.44}

 29%|██▊       | 8045/28080 [15:53:41<39:14:12,  7.05s/it]
 29%|██▊       | 8046/28080 [15:53:48<39:19:11,  7.07s/it]
                                                          
{'loss': 0.642, 'learning_rate': 0.0004185686407747665, 'epoch': 3.44}

 29%|██▊       | 8046/28080 [15:53:48<39:19:11,  7.07s/it]
 29%|██▊       | 8047/28080 [15:53:55<39:25:21,  7.08s/it]
                                                          
{'loss': 0.6284, 'learning_rate': 0.0004185473450387337, 'epoch': 3.44}

 29%|██▊       | 8047/28080 [15:53:55<39:25:21,  7.08s/it]
 29%|██▊       | 8048/28080 [15:54:02<39:28:32,  7.09s/it]
                                                          
{'loss': 0.6197, 'learning_rate': 0.0004185260470603525, 'epoch': 3.44}

 29%|██▊       | 8048/28080 [15:54:02<39:28:32,  7.09s/it]
 29%|██▊       | 8049/28080 [15:54:09<39:22:15,  7.08s/it]
                                                          
{'loss': 0.6365, 'learning_rate': 0.00041850474683990593, 'epoch': 3.44}

 29%|██▊       | 8049/28080 [15:54:09<39:22:15,  7.08s/it]
 29%|██▊       | 8050/28080 [15:54:16<39:21:09,  7.07s/it]
                                                          
{'loss': 0.6663, 'learning_rate': 0.0004184834443776776, 'epoch': 3.44}

 29%|██▊       | 8050/28080 [15:54:16<39:21:09,  7.07s/it]
 29%|██▊       | 8051/28080 [15:54:24<39:22:32,  7.08s/it]
                                                          
{'loss': 0.6197, 'learning_rate': 0.00041846213967395093, 'epoch': 3.44}

 29%|██▊       | 8051/28080 [15:54:24<39:22:32,  7.08s/it]
 29%|██▊       | 8052/28080 [15:54:31<39:24:17,  7.08s/it]
                                                          
{'loss': 0.6311, 'learning_rate': 0.00041844083272900924, 'epoch': 3.44}

 29%|██▊       | 8052/28080 [15:54:31<39:24:17,  7.08s/it]
 29%|██▊       | 8053/28080 [15:54:38<39:27:06,  7.09s/it]
                                                          
{'loss': 0.6301, 'learning_rate': 0.000418419523543136, 'epoch': 3.44}

 29%|██▊       | 8053/28080 [15:54:38<39:27:06,  7.09s/it]
 29%|██▊       | 8054/28080 [15:54:45<39:36:09,  7.12s/it]
                                                          
{'loss': 0.6362, 'learning_rate': 0.00041839821211661475, 'epoch': 3.44}

 29%|██▊       | 8054/28080 [15:54:45<39:36:09,  7.12s/it]
 29%|██▊       | 8055/28080 [15:54:52<39:26:29,  7.09s/it]
                                                          
{'loss': 0.6426, 'learning_rate': 0.0004183768984497291, 'epoch': 3.44}

 29%|██▊       | 8055/28080 [15:54:52<39:26:29,  7.09s/it]
 29%|██▊       | 8056/28080 [15:54:59<39:15:25,  7.06s/it]
                                                          
{'loss': 0.633, 'learning_rate': 0.0004183555825427625, 'epoch': 3.44}

 29%|██▊       | 8056/28080 [15:54:59<39:15:25,  7.06s/it]
 29%|██▊       | 8057/28080 [15:55:06<39:27:21,  7.09s/it]
                                                          
{'loss': 0.6238, 'learning_rate': 0.0004183342643959985, 'epoch': 3.44}

 29%|██▊       | 8057/28080 [15:55:06<39:27:21,  7.09s/it]
 29%|██▊       | 8058/28080 [15:55:13<39:27:00,  7.09s/it]
                                                          
{'loss': 0.6272, 'learning_rate': 0.00041831294400972076, 'epoch': 3.44}

 29%|██▊       | 8058/28080 [15:55:13<39:27:00,  7.09s/it]
 29%|██▊       | 8059/28080 [15:55:20<39:29:50,  7.10s/it]
                                                          
{'loss': 0.6311, 'learning_rate': 0.000418291621384213, 'epoch': 3.44}

 29%|██▊       | 8059/28080 [15:55:20<39:29:50,  7.10s/it]
 29%|██▊       | 8060/28080 [15:55:27<39:27:06,  7.09s/it]
                                                          
{'loss': 0.6533, 'learning_rate': 0.00041827029651975877, 'epoch': 3.44}

 29%|██▊       | 8060/28080 [15:55:27<39:27:06,  7.09s/it]
 29%|██▊       | 8061/28080 [15:55:35<39:25:49,  7.09s/it]
                                                          
{'loss': 0.6442, 'learning_rate': 0.00041824896941664193, 'epoch': 3.44}

 29%|██▊       | 8061/28080 [15:55:35<39:25:49,  7.09s/it]
 29%|██▊       | 8062/28080 [15:55:42<39:30:23,  7.10s/it]
                                                          
{'loss': 0.6304, 'learning_rate': 0.000418227640075146, 'epoch': 3.44}

 29%|██▊       | 8062/28080 [15:55:42<39:30:23,  7.10s/it]
 29%|██▊       | 8063/28080 [15:55:49<39:33:18,  7.11s/it]
                                                          
{'loss': 0.6212, 'learning_rate': 0.00041820630849555496, 'epoch': 3.44}

 29%|██▊       | 8063/28080 [15:55:49<39:33:18,  7.11s/it]
 29%|██▊       | 8064/28080 [15:55:56<39:31:45,  7.11s/it]
                                                          
{'loss': 0.6362, 'learning_rate': 0.0004181849746781525, 'epoch': 3.44}

 29%|██▊       | 8064/28080 [15:55:56<39:31:45,  7.11s/it]
 29%|██▊       | 8065/28080 [15:56:03<39:30:39,  7.11s/it]
                                                          
{'loss': 0.6271, 'learning_rate': 0.0004181636386232225, 'epoch': 3.45}

 29%|██▊       | 8065/28080 [15:56:03<39:30:39,  7.11s/it]
 29%|██▊       | 8066/28080 [15:56:10<39:34:26,  7.12s/it]
                                                          
{'loss': 0.6515, 'learning_rate': 0.0004181423003310487, 'epoch': 3.45}

 29%|██▊       | 8066/28080 [15:56:10<39:34:26,  7.12s/it]
 29%|██▊       | 8067/28080 [15:56:17<39:33:06,  7.11s/it]
                                                          
{'loss': 0.6237, 'learning_rate': 0.0004181209598019151, 'epoch': 3.45}

 29%|██▊       | 8067/28080 [15:56:17<39:33:06,  7.11s/it]
 29%|██▊       | 8068/28080 [15:56:24<39:30:32,  7.11s/it]
                                                          
{'loss': 0.6275, 'learning_rate': 0.00041809961703610554, 'epoch': 3.45}

 29%|██▊       | 8068/28080 [15:56:24<39:30:32,  7.11s/it]
 29%|██▊       | 8069/28080 [15:56:31<39:34:19,  7.12s/it]
                                                          
{'loss': 0.6109, 'learning_rate': 0.00041807827203390403, 'epoch': 3.45}

 29%|██▊       | 8069/28080 [15:56:31<39:34:19,  7.12s/it]
 29%|██▊       | 8070/28080 [15:56:39<39:30:29,  7.11s/it]
                                                          
{'loss': 0.6567, 'learning_rate': 0.00041805692479559447, 'epoch': 3.45}

 29%|██▊       | 8070/28080 [15:56:39<39:30:29,  7.11s/it]
 29%|██▊       | 8071/28080 [15:56:46<39:26:41,  7.10s/it]
                                                          
{'loss': 0.6166, 'learning_rate': 0.00041803557532146097, 'epoch': 3.45}

 29%|██▊       | 8071/28080 [15:56:46<39:26:41,  7.10s/it]
 29%|██▊       | 8072/28080 [15:56:53<39:24:18,  7.09s/it]
                                                          
{'loss': 0.6219, 'learning_rate': 0.0004180142236117874, 'epoch': 3.45}

 29%|██▊       | 8072/28080 [15:56:53<39:24:18,  7.09s/it]
 29%|██▉       | 8073/28080 [15:57:00<39:20:24,  7.08s/it]
                                                          
{'loss': 0.63, 'learning_rate': 0.000417992869666858, 'epoch': 3.45}

 29%|██▉       | 8073/28080 [15:57:00<39:20:24,  7.08s/it]
 29%|██▉       | 8074/28080 [15:57:07<39:25:00,  7.09s/it]
                                                          
{'loss': 0.634, 'learning_rate': 0.00041797151348695673, 'epoch': 3.45}

 29%|██▉       | 8074/28080 [15:57:07<39:25:00,  7.09s/it]
 29%|██▉       | 8075/28080 [15:57:14<39:32:52,  7.12s/it]
                                                          
{'loss': 0.63, 'learning_rate': 0.00041795015507236776, 'epoch': 3.45}

 29%|██▉       | 8075/28080 [15:57:14<39:32:52,  7.12s/it]
 29%|██▉       | 8076/28080 [15:57:21<39:22:11,  7.09s/it]
                                                          
{'loss': 0.625, 'learning_rate': 0.00041792879442337526, 'epoch': 3.45}

 29%|██▉       | 8076/28080 [15:57:21<39:22:11,  7.09s/it]
 29%|██▉       | 8077/28080 [15:57:28<39:19:42,  7.08s/it]
                                                          
{'loss': 0.6516, 'learning_rate': 0.0004179074315402634, 'epoch': 3.45}

 29%|██▉       | 8077/28080 [15:57:28<39:19:42,  7.08s/it]
 29%|██▉       | 8078/28080 [15:57:35<39:17:20,  7.07s/it]
                                                          
{'loss': 0.6217, 'learning_rate': 0.0004178860664233164, 'epoch': 3.45}

 29%|██▉       | 8078/28080 [15:57:35<39:17:20,  7.07s/it]
 29%|██▉       | 8079/28080 [15:57:42<39:14:34,  7.06s/it]
                                                          
{'loss': 0.6568, 'learning_rate': 0.0004178646990728184, 'epoch': 3.45}

 29%|██▉       | 8079/28080 [15:57:42<39:14:34,  7.06s/it]
 29%|██▉       | 8080/28080 [15:57:49<39:22:49,  7.09s/it]
                                                          
{'loss': 0.6209, 'learning_rate': 0.0004178433294890538, 'epoch': 3.45}

 29%|██▉       | 8080/28080 [15:57:49<39:22:49,  7.09s/it]
 29%|██▉       | 8081/28080 [15:57:56<39:16:37,  7.07s/it]
                                                          
{'loss': 0.6229, 'learning_rate': 0.0004178219576723069, 'epoch': 3.45}

 29%|██▉       | 8081/28080 [15:57:56<39:16:37,  7.07s/it]
 29%|██▉       | 8082/28080 [15:58:04<39:23:57,  7.09s/it]
                                                          
{'loss': 0.6415, 'learning_rate': 0.00041780058362286186, 'epoch': 3.45}

 29%|██▉       | 8082/28080 [15:58:04<39:23:57,  7.09s/it]
 29%|██▉       | 8083/28080 [15:58:11<39:11:00,  7.05s/it]
                                                          
{'loss': 0.6709, 'learning_rate': 0.00041777920734100327, 'epoch': 3.45}

 29%|██▉       | 8083/28080 [15:58:11<39:11:00,  7.05s/it]
 29%|██▉       | 8084/28080 [15:58:18<39:09:22,  7.05s/it]
                                                          
{'loss': 0.6295, 'learning_rate': 0.0004177578288270154, 'epoch': 3.45}

 29%|██▉       | 8084/28080 [15:58:18<39:09:22,  7.05s/it]
 29%|██▉       | 8085/28080 [15:58:25<39:09:22,  7.05s/it]
                                                          
{'loss': 0.6331, 'learning_rate': 0.0004177364480811827, 'epoch': 3.45}

 29%|██▉       | 8085/28080 [15:58:25<39:09:22,  7.05s/it]
 29%|██▉       | 8086/28080 [15:58:32<39:09:22,  7.05s/it]
                                                          
{'loss': 0.6382, 'learning_rate': 0.00041771506510378953, 'epoch': 3.45}

 29%|██▉       | 8086/28080 [15:58:32<39:09:22,  7.05s/it]
 29%|██▉       | 8087/28080 [15:58:39<38:59:17,  7.02s/it]
                                                          
{'loss': 0.6338, 'learning_rate': 0.0004176936798951205, 'epoch': 3.45}

 29%|██▉       | 8087/28080 [15:58:39<38:59:17,  7.02s/it]
 29%|██▉       | 8088/28080 [15:58:46<38:53:41,  7.00s/it]
                                                          
{'loss': 0.641, 'learning_rate': 0.0004176722924554601, 'epoch': 3.46}

 29%|██▉       | 8088/28080 [15:58:46<38:53:41,  7.00s/it]
 29%|██▉       | 8089/28080 [15:58:53<39:05:13,  7.04s/it]
                                                          
{'loss': 0.6317, 'learning_rate': 0.00041765090278509276, 'epoch': 3.46}

 29%|██▉       | 8089/28080 [15:58:53<39:05:13,  7.04s/it]
 29%|██▉       | 8090/28080 [15:59:00<39:06:37,  7.04s/it]
                                                          
{'loss': 0.6238, 'learning_rate': 0.0004176295108843031, 'epoch': 3.46}

 29%|██▉       | 8090/28080 [15:59:00<39:06:37,  7.04s/it]
 29%|██▉       | 8091/28080 [15:59:07<39:13:15,  7.06s/it]
                                                          
{'loss': 0.6369, 'learning_rate': 0.00041760811675337577, 'epoch': 3.46}

 29%|██▉       | 8091/28080 [15:59:07<39:13:15,  7.06s/it]
 29%|██▉       | 8092/28080 [15:59:14<39:25:07,  7.10s/it]
                                                          
{'loss': 0.6273, 'learning_rate': 0.00041758672039259536, 'epoch': 3.46}

 29%|██▉       | 8092/28080 [15:59:14<39:25:07,  7.10s/it]
 29%|██▉       | 8093/28080 [15:59:21<39:23:39,  7.10s/it]
                                                          
{'loss': 0.6345, 'learning_rate': 0.0004175653218022465, 'epoch': 3.46}

 29%|██▉       | 8093/28080 [15:59:21<39:23:39,  7.10s/it]
 29%|██▉       | 8094/28080 [15:59:28<39:38:07,  7.14s/it]
                                                          
{'loss': 0.6291, 'learning_rate': 0.00041754392098261394, 'epoch': 3.46}

 29%|██▉       | 8094/28080 [15:59:28<39:38:07,  7.14s/it]
 29%|██▉       | 8095/28080 [15:59:35<39:26:51,  7.11s/it]
                                                          
{'loss': 0.6487, 'learning_rate': 0.0004175225179339823, 'epoch': 3.46}

 29%|██▉       | 8095/28080 [15:59:35<39:26:51,  7.11s/it]
 29%|██▉       | 8096/28080 [15:59:42<39:23:42,  7.10s/it]
                                                          
{'loss': 0.6472, 'learning_rate': 0.0004175011126566365, 'epoch': 3.46}

 29%|██▉       | 8096/28080 [15:59:42<39:23:42,  7.10s/it]
 29%|██▉       | 8097/28080 [15:59:49<39:12:40,  7.06s/it]
                                                          
{'loss': 0.6603, 'learning_rate': 0.0004174797051508611, 'epoch': 3.46}

 29%|██▉       | 8097/28080 [15:59:49<39:12:40,  7.06s/it]
 29%|██▉       | 8098/28080 [15:59:57<39:12:51,  7.06s/it]
                                                          
{'loss': 0.6251, 'learning_rate': 0.000417458295416941, 'epoch': 3.46}

 29%|██▉       | 8098/28080 [15:59:57<39:12:51,  7.06s/it]
 29%|██▉       | 8099/28080 [16:00:03<38:59:56,  7.03s/it]
                                                          
{'loss': 0.632, 'learning_rate': 0.00041743688345516106, 'epoch': 3.46}

 29%|██▉       | 8099/28080 [16:00:03<38:59:56,  7.03s/it]
 29%|██▉       | 8100/28080 [16:00:11<39:15:52,  7.07s/it]
                                                          
{'loss': 0.6405, 'learning_rate': 0.0004174154692658061, 'epoch': 3.46}

 29%|██▉       | 8100/28080 [16:00:11<39:15:52,  7.07s/it]
 29%|██▉       | 8101/28080 [16:00:18<39:25:49,  7.10s/it]
                                                          
{'loss': 0.6525, 'learning_rate': 0.00041739405284916105, 'epoch': 3.46}

 29%|██▉       | 8101/28080 [16:00:18<39:25:49,  7.10s/it]
 29%|██▉       | 8102/28080 [16:00:25<39:40:49,  7.15s/it]
                                                          
{'loss': 0.6205, 'learning_rate': 0.0004173726342055108, 'epoch': 3.46}

 29%|██▉       | 8102/28080 [16:00:25<39:40:49,  7.15s/it]
 29%|██▉       | 8103/28080 [16:00:32<39:39:10,  7.15s/it]
                                                          
{'loss': 0.6401, 'learning_rate': 0.00041735121333514035, 'epoch': 3.46}

 29%|██▉       | 8103/28080 [16:00:32<39:39:10,  7.15s/it]
 29%|██▉       | 8104/28080 [16:00:39<39:39:33,  7.15s/it]
                                                          
{'loss': 0.6593, 'learning_rate': 0.0004173297902383346, 'epoch': 3.46}

 29%|██▉       | 8104/28080 [16:00:39<39:39:33,  7.15s/it]
 29%|██▉       | 8105/28080 [16:00:47<39:39:34,  7.15s/it]
                                                          
{'loss': 0.6428, 'learning_rate': 0.0004173083649153787, 'epoch': 3.46}

 29%|██▉       | 8105/28080 [16:00:47<39:39:34,  7.15s/it]
 29%|██▉       | 8106/28080 [16:00:54<39:35:02,  7.13s/it]
                                                          
{'loss': 0.6192, 'learning_rate': 0.00041728693736655753, 'epoch': 3.46}

 29%|██▉       | 8106/28080 [16:00:54<39:35:02,  7.13s/it]
 29%|██▉       | 8107/28080 [16:01:01<39:35:16,  7.14s/it]
                                                          
{'loss': 0.6244, 'learning_rate': 0.0004172655075921563, 'epoch': 3.46}

 29%|██▉       | 8107/28080 [16:01:01<39:35:16,  7.14s/it]
 29%|██▉       | 8108/28080 [16:01:08<39:30:26,  7.12s/it]
                                                          
{'loss': 0.6392, 'learning_rate': 0.00041724407559246, 'epoch': 3.46}

 29%|██▉       | 8108/28080 [16:01:08<39:30:26,  7.12s/it]
 29%|██▉       | 8109/28080 [16:01:15<39:33:09,  7.13s/it]
                                                          
{'loss': 0.6456, 'learning_rate': 0.00041722264136775385, 'epoch': 3.46}

 29%|██▉       | 8109/28080 [16:01:15<39:33:09,  7.13s/it]
 29%|██▉       | 8110/28080 [16:01:22<39:31:15,  7.12s/it]
                                                          
{'loss': 0.6354, 'learning_rate': 0.00041720120491832294, 'epoch': 3.46}

 29%|██▉       | 8110/28080 [16:01:22<39:31:15,  7.12s/it]
 29%|██▉       | 8111/28080 [16:01:29<39:16:43,  7.08s/it]
                                                          
{'loss': 0.6541, 'learning_rate': 0.0004171797662444525, 'epoch': 3.46}

 29%|██▉       | 8111/28080 [16:01:29<39:16:43,  7.08s/it]
 29%|██▉       | 8112/28080 [16:01:36<39:11:43,  7.07s/it]
                                                          
{'loss': 0.6511, 'learning_rate': 0.00041715832534642774, 'epoch': 3.47}

 29%|██▉       | 8112/28080 [16:01:36<39:11:43,  7.07s/it]
 29%|██▉       | 8113/28080 [16:01:43<39:16:19,  7.08s/it]
                                                          
{'loss': 0.6371, 'learning_rate': 0.0004171368822245339, 'epoch': 3.47}

 29%|██▉       | 8113/28080 [16:01:43<39:16:19,  7.08s/it]
 29%|██▉       | 8114/28080 [16:01:50<39:15:05,  7.08s/it]
                                                          
{'loss': 0.6213, 'learning_rate': 0.0004171154368790563, 'epoch': 3.47}

 29%|██▉       | 8114/28080 [16:01:50<39:15:05,  7.08s/it]
 29%|██▉       | 8115/28080 [16:01:57<39:16:01,  7.08s/it]
                                                          
{'loss': 0.641, 'learning_rate': 0.0004170939893102802, 'epoch': 3.47}

 29%|██▉       | 8115/28080 [16:01:57<39:16:01,  7.08s/it]
 29%|██▉       | 8116/28080 [16:02:04<39:15:18,  7.08s/it]
                                                          
{'loss': 0.6316, 'learning_rate': 0.0004170725395184909, 'epoch': 3.47}

 29%|██▉       | 8116/28080 [16:02:04<39:15:18,  7.08s/it]
 29%|██▉       | 8117/28080 [16:02:12<39:17:15,  7.08s/it]
                                                          
{'loss': 0.6457, 'learning_rate': 0.00041705108750397384, 'epoch': 3.47}

 29%|██▉       | 8117/28080 [16:02:12<39:17:15,  7.08s/it]
 29%|██▉       | 8118/28080 [16:02:19<39:20:42,  7.10s/it]
                                                          
{'loss': 0.6276, 'learning_rate': 0.0004170296332670145, 'epoch': 3.47}

 29%|██▉       | 8118/28080 [16:02:19<39:20:42,  7.10s/it]
 29%|██▉       | 8119/28080 [16:02:26<39:26:13,  7.11s/it]
                                                          
{'loss': 0.6589, 'learning_rate': 0.00041700817680789804, 'epoch': 3.47}

 29%|██▉       | 8119/28080 [16:02:26<39:26:13,  7.11s/it]
 29%|██▉       | 8120/28080 [16:02:33<39:21:18,  7.10s/it]
                                                          
{'loss': 0.6287, 'learning_rate': 0.00041698671812691025, 'epoch': 3.47}

 29%|██▉       | 8120/28080 [16:02:33<39:21:18,  7.10s/it]
 29%|██▉       | 8121/28080 [16:02:40<39:25:59,  7.11s/it]
                                                          
{'loss': 0.6286, 'learning_rate': 0.00041696525722433633, 'epoch': 3.47}

 29%|██▉       | 8121/28080 [16:02:40<39:25:59,  7.11s/it]
 29%|██▉       | 8122/28080 [16:02:47<39:22:34,  7.10s/it]
                                                          
{'loss': 0.6357, 'learning_rate': 0.00041694379410046195, 'epoch': 3.47}

 29%|██▉       | 8122/28080 [16:02:47<39:22:34,  7.10s/it]
 29%|██▉       | 8123/28080 [16:02:54<39:13:19,  7.08s/it]
                                                          
{'loss': 0.6349, 'learning_rate': 0.00041692232875557264, 'epoch': 3.47}

 29%|██▉       | 8123/28080 [16:02:54<39:13:19,  7.08s/it]
 29%|██▉       | 8124/28080 [16:03:01<39:23:02,  7.10s/it]
                                                          
{'loss': 0.6056, 'learning_rate': 0.0004169008611899539, 'epoch': 3.47}

 29%|██▉       | 8124/28080 [16:03:01<39:23:02,  7.10s/it]
 29%|██▉       | 8125/28080 [16:03:08<39:25:53,  7.11s/it]
                                                          
{'loss': 0.6311, 'learning_rate': 0.00041687939140389144, 'epoch': 3.47}

 29%|██▉       | 8125/28080 [16:03:08<39:25:53,  7.11s/it]
 29%|██▉       | 8126/28080 [16:03:15<39:10:12,  7.07s/it]
                                                          
{'loss': 0.655, 'learning_rate': 0.0004168579193976708, 'epoch': 3.47}

 29%|██▉       | 8126/28080 [16:03:15<39:10:12,  7.07s/it]
 29%|██▉       | 8127/28080 [16:03:22<39:11:19,  7.07s/it]
                                                          
{'loss': 0.6289, 'learning_rate': 0.0004168364451715776, 'epoch': 3.47}

 29%|██▉       | 8127/28080 [16:03:22<39:11:19,  7.07s/it]
 29%|██▉       | 8128/28080 [16:03:30<39:07:06,  7.06s/it]
                                                          
{'loss': 0.6439, 'learning_rate': 0.00041681496872589773, 'epoch': 3.47}

 29%|██▉       | 8128/28080 [16:03:30<39:07:06,  7.06s/it]
 29%|██▉       | 8129/28080 [16:03:37<39:14:37,  7.08s/it]
                                                          
{'loss': 0.6588, 'learning_rate': 0.00041679349006091675, 'epoch': 3.47}

 29%|██▉       | 8129/28080 [16:03:37<39:14:37,  7.08s/it]
 29%|██▉       | 8130/28080 [16:03:44<39:09:32,  7.07s/it]
                                                          
{'loss': 0.6269, 'learning_rate': 0.0004167720091769205, 'epoch': 3.47}

 29%|██▉       | 8130/28080 [16:03:44<39:09:32,  7.07s/it]
 29%|██▉       | 8131/28080 [16:03:51<39:15:51,  7.09s/it]
                                                          
{'loss': 0.6507, 'learning_rate': 0.00041675052607419475, 'epoch': 3.47}

 29%|██▉       | 8131/28080 [16:03:51<39:15:51,  7.09s/it]
 29%|██▉       | 8132/28080 [16:03:58<39:19:15,  7.10s/it]
                                                          
{'loss': 0.648, 'learning_rate': 0.00041672904075302516, 'epoch': 3.47}

 29%|██▉       | 8132/28080 [16:03:58<39:19:15,  7.10s/it]
 29%|██▉       | 8133/28080 [16:04:05<39:18:54,  7.10s/it]
                                                          
{'loss': 0.6563, 'learning_rate': 0.0004167075532136977, 'epoch': 3.47}

 29%|██▉       | 8133/28080 [16:04:05<39:18:54,  7.10s/it]
 29%|██▉       | 8134/28080 [16:04:12<39:13:52,  7.08s/it]
                                                          
{'loss': 0.6549, 'learning_rate': 0.0004166860634564983, 'epoch': 3.47}

 29%|██▉       | 8134/28080 [16:04:12<39:13:52,  7.08s/it]
 29%|██▉       | 8135/28080 [16:04:19<39:17:47,  7.09s/it]
                                                          
{'loss': 0.6156, 'learning_rate': 0.0004166645714817128, 'epoch': 3.48}

 29%|██▉       | 8135/28080 [16:04:19<39:17:47,  7.09s/it]
 29%|██▉       | 8136/28080 [16:04:26<39:15:51,  7.09s/it]
                                                          
{'loss': 0.6428, 'learning_rate': 0.000416643077289627, 'epoch': 3.48}

 29%|██▉       | 8136/28080 [16:04:26<39:15:51,  7.09s/it]
 29%|██▉       | 8137/28080 [16:04:33<39:08:42,  7.07s/it]
                                                          
{'loss': 0.6512, 'learning_rate': 0.00041662158088052705, 'epoch': 3.48}

 29%|██▉       | 8137/28080 [16:04:33<39:08:42,  7.07s/it]
 29%|██▉       | 8138/28080 [16:04:40<38:57:57,  7.03s/it]
                                                          
{'loss': 0.6293, 'learning_rate': 0.0004166000822546988, 'epoch': 3.48}

 29%|██▉       | 8138/28080 [16:04:40<38:57:57,  7.03s/it]
 29%|██▉       | 8139/28080 [16:04:47<39:10:23,  7.07s/it]
                                                          
{'loss': 0.6493, 'learning_rate': 0.0004165785814124284, 'epoch': 3.48}

 29%|██▉       | 8139/28080 [16:04:47<39:10:23,  7.07s/it]
 29%|██▉       | 8140/28080 [16:04:55<39:12:18,  7.08s/it]
                                                          
{'loss': 0.6463, 'learning_rate': 0.0004165570783540018, 'epoch': 3.48}

 29%|██▉       | 8140/28080 [16:04:55<39:12:18,  7.08s/it]
 29%|██▉       | 8141/28080 [16:05:02<39:13:02,  7.08s/it]
                                                          
{'loss': 0.6231, 'learning_rate': 0.0004165355730797051, 'epoch': 3.48}

 29%|██▉       | 8141/28080 [16:05:02<39:13:02,  7.08s/it]
 29%|██▉       | 8142/28080 [16:05:09<39:15:56,  7.09s/it]
                                                          
{'loss': 0.6386, 'learning_rate': 0.0004165140655898244, 'epoch': 3.48}

 29%|██▉       | 8142/28080 [16:05:09<39:15:56,  7.09s/it]
 29%|██▉       | 8143/28080 [16:05:16<39:21:19,  7.11s/it]
                                                          
{'loss': 0.6364, 'learning_rate': 0.00041649255588464585, 'epoch': 3.48}

 29%|██▉       | 8143/28080 [16:05:16<39:21:19,  7.11s/it]
 29%|██▉       | 8144/28080 [16:05:23<39:24:02,  7.11s/it]
                                                          
{'loss': 0.6336, 'learning_rate': 0.00041647104396445563, 'epoch': 3.48}

 29%|██▉       | 8144/28080 [16:05:23<39:24:02,  7.11s/it]
 29%|██▉       | 8145/28080 [16:05:30<39:31:57,  7.14s/it]
                                                          
{'loss': 0.6456, 'learning_rate': 0.0004164495298295399, 'epoch': 3.48}

 29%|██▉       | 8145/28080 [16:05:30<39:31:57,  7.14s/it]
 29%|██▉       | 8146/28080 [16:05:37<39:31:24,  7.14s/it]
                                                          
{'loss': 0.6372, 'learning_rate': 0.0004164280134801849, 'epoch': 3.48}

 29%|██▉       | 8146/28080 [16:05:37<39:31:24,  7.14s/it]
 29%|██▉       | 8147/28080 [16:05:44<39:23:12,  7.11s/it]
                                                          
{'loss': 0.646, 'learning_rate': 0.00041640649491667684, 'epoch': 3.48}

 29%|██▉       | 8147/28080 [16:05:44<39:23:12,  7.11s/it]
 29%|██▉       | 8148/28080 [16:05:51<39:19:29,  7.10s/it]
                                                          
{'loss': 0.635, 'learning_rate': 0.000416384974139302, 'epoch': 3.48}

 29%|██▉       | 8148/28080 [16:05:51<39:19:29,  7.10s/it]
 29%|██▉       | 8149/28080 [16:05:59<39:29:36,  7.13s/it]
                                                          
{'loss': 0.6348, 'learning_rate': 0.0004163634511483468, 'epoch': 3.48}

 29%|██▉       | 8149/28080 [16:05:59<39:29:36,  7.13s/it]
 29%|██▉       | 8150/28080 [16:06:06<39:29:03,  7.13s/it]
                                                          
{'loss': 0.6581, 'learning_rate': 0.00041634192594409747, 'epoch': 3.48}

 29%|██▉       | 8150/28080 [16:06:06<39:29:03,  7.13s/it]
 29%|██▉       | 8151/28080 [16:06:13<39:27:43,  7.13s/it]
                                                          
{'loss': 0.6483, 'learning_rate': 0.00041632039852684046, 'epoch': 3.48}

 29%|██▉       | 8151/28080 [16:06:13<39:27:43,  7.13s/it]
 29%|██▉       | 8152/28080 [16:06:20<39:25:13,  7.12s/it]
                                                          
{'loss': 0.6514, 'learning_rate': 0.00041629886889686207, 'epoch': 3.48}

 29%|██▉       | 8152/28080 [16:06:20<39:25:13,  7.12s/it]
 29%|██▉       | 8153/28080 [16:06:27<39:14:53,  7.09s/it]
                                                          
{'loss': 0.6424, 'learning_rate': 0.0004162773370544488, 'epoch': 3.48}

 29%|██▉       | 8153/28080 [16:06:27<39:14:53,  7.09s/it]
 29%|██▉       | 8154/28080 [16:06:34<39:21:33,  7.11s/it]
                                                          
{'loss': 0.6218, 'learning_rate': 0.0004162558029998872, 'epoch': 3.48}

 29%|██▉       | 8154/28080 [16:06:34<39:21:33,  7.11s/it]
 29%|██▉       | 8155/28080 [16:06:41<39:19:47,  7.11s/it]
                                                          
{'loss': 0.6459, 'learning_rate': 0.0004162342667334635, 'epoch': 3.48}

 29%|██▉       | 8155/28080 [16:06:41<39:19:47,  7.11s/it]
 29%|██▉       | 8156/28080 [16:06:48<39:21:31,  7.11s/it]
                                                          
{'loss': 0.6313, 'learning_rate': 0.0004162127282554645, 'epoch': 3.48}

 29%|██▉       | 8156/28080 [16:06:48<39:21:31,  7.11s/it]
 29%|██▉       | 8157/28080 [16:06:55<39:18:39,  7.10s/it]
                                                          
{'loss': 0.6352, 'learning_rate': 0.00041619118756617657, 'epoch': 3.48}

 29%|██▉       | 8157/28080 [16:06:55<39:18:39,  7.10s/it]
 29%|██▉       | 8158/28080 [16:07:03<39:14:16,  7.09s/it]
                                                          
{'loss': 0.6316, 'learning_rate': 0.00041616964466588635, 'epoch': 3.49}

 29%|██▉       | 8158/28080 [16:07:03<39:14:16,  7.09s/it]
 29%|██▉       | 8159/28080 [16:07:10<39:16:30,  7.10s/it]
                                                          
{'loss': 0.6523, 'learning_rate': 0.0004161480995548804, 'epoch': 3.49}

 29%|██▉       | 8159/28080 [16:07:10<39:16:30,  7.10s/it]
 29%|██▉       | 8160/28080 [16:07:17<39:19:11,  7.11s/it]
                                                          
{'loss': 0.6382, 'learning_rate': 0.0004161265522334455, 'epoch': 3.49}

 29%|██▉       | 8160/28080 [16:07:17<39:19:11,  7.11s/it]
 29%|██▉       | 8161/28080 [16:07:24<39:17:45,  7.10s/it]
                                                          
{'loss': 0.6283, 'learning_rate': 0.00041610500270186814, 'epoch': 3.49}

 29%|██▉       | 8161/28080 [16:07:24<39:17:45,  7.10s/it]
 29%|██▉       | 8162/28080 [16:07:31<39:05:41,  7.07s/it]
                                                          
{'loss': 0.6471, 'learning_rate': 0.00041608345096043504, 'epoch': 3.49}

 29%|██▉       | 8162/28080 [16:07:31<39:05:41,  7.07s/it]
 29%|██▉       | 8163/28080 [16:07:38<39:16:12,  7.10s/it]
                                                          
{'loss': 0.6387, 'learning_rate': 0.000416061897009433, 'epoch': 3.49}

 29%|██▉       | 8163/28080 [16:07:38<39:16:12,  7.10s/it]
 29%|██▉       | 8164/28080 [16:07:45<39:13:51,  7.09s/it]
                                                          
{'loss': 0.6403, 'learning_rate': 0.0004160403408491487, 'epoch': 3.49}

 29%|██▉       | 8164/28080 [16:07:45<39:13:51,  7.09s/it]
 29%|██▉       | 8165/28080 [16:07:52<39:13:36,  7.09s/it]
                                                          
{'loss': 0.6318, 'learning_rate': 0.000416018782479869, 'epoch': 3.49}

 29%|██▉       | 8165/28080 [16:07:52<39:13:36,  7.09s/it]
 29%|██▉       | 8166/28080 [16:07:59<39:05:20,  7.07s/it]
                                                          
{'loss': 0.6347, 'learning_rate': 0.00041599722190188064, 'epoch': 3.49}

 29%|██▉       | 8166/28080 [16:07:59<39:05:20,  7.07s/it]
 29%|██▉       | 8167/28080 [16:08:06<39:09:11,  7.08s/it]
                                                          
{'loss': 0.6221, 'learning_rate': 0.00041597565911547055, 'epoch': 3.49}

 29%|██▉       | 8167/28080 [16:08:06<39:09:11,  7.08s/it]
 29%|██▉       | 8168/28080 [16:08:13<39:16:47,  7.10s/it]
                                                          
{'loss': 0.626, 'learning_rate': 0.00041595409412092547, 'epoch': 3.49}

 29%|██▉       | 8168/28080 [16:08:13<39:16:47,  7.10s/it]
 29%|██▉       | 8169/28080 [16:08:21<39:16:56,  7.10s/it]
                                                          
{'loss': 0.6263, 'learning_rate': 0.00041593252691853245, 'epoch': 3.49}

 29%|██▉       | 8169/28080 [16:08:21<39:16:56,  7.10s/it]
 29%|██▉       | 8170/28080 [16:08:28<39:18:17,  7.11s/it]
                                                          
{'loss': 0.603, 'learning_rate': 0.0004159109575085783, 'epoch': 3.49}

 29%|██▉       | 8170/28080 [16:08:28<39:18:17,  7.11s/it]
 29%|██▉       | 8171/28080 [16:08:35<39:20:26,  7.11s/it]
                                                          
{'loss': 0.6512, 'learning_rate': 0.00041588938589135003, 'epoch': 3.49}

 29%|██▉       | 8171/28080 [16:08:35<39:20:26,  7.11s/it]
 29%|██▉       | 8172/28080 [16:08:42<39:26:26,  7.13s/it]
                                                          
{'loss': 0.6283, 'learning_rate': 0.00041586781206713467, 'epoch': 3.49}

 29%|██▉       | 8172/28080 [16:08:42<39:26:26,  7.13s/it]
 29%|██▉       | 8173/28080 [16:08:49<39:18:58,  7.11s/it]
                                                          
{'loss': 0.6111, 'learning_rate': 0.0004158462360362191, 'epoch': 3.49}

 29%|██▉       | 8173/28080 [16:08:49<39:18:58,  7.11s/it]
 29%|██▉       | 8174/28080 [16:08:56<39:18:22,  7.11s/it]
                                                          
{'loss': 0.6454, 'learning_rate': 0.00041582465779889047, 'epoch': 3.49}

 29%|██▉       | 8174/28080 [16:08:56<39:18:22,  7.11s/it]
 29%|██▉       | 8175/28080 [16:09:03<39:14:16,  7.10s/it]
                                                          
{'loss': 0.6214, 'learning_rate': 0.0004158030773554359, 'epoch': 3.49}

 29%|██▉       | 8175/28080 [16:09:03<39:14:16,  7.10s/it]
 29%|██▉       | 8176/28080 [16:09:10<39:21:55,  7.12s/it]
                                                          
{'loss': 0.6542, 'learning_rate': 0.00041578149470614237, 'epoch': 3.49}

 29%|██▉       | 8176/28080 [16:09:10<39:21:55,  7.12s/it]
 29%|██▉       | 8177/28080 [16:09:18<39:24:20,  7.13s/it]
                                                          
{'loss': 0.6425, 'learning_rate': 0.0004157599098512971, 'epoch': 3.49}

 29%|██▉       | 8177/28080 [16:09:18<39:24:20,  7.13s/it]
 29%|██▉       | 8178/28080 [16:09:25<39:23:11,  7.12s/it]
                                                          
{'loss': 0.6476, 'learning_rate': 0.0004157383227911872, 'epoch': 3.49}

 29%|██▉       | 8178/28080 [16:09:25<39:23:11,  7.12s/it]
 29%|██▉       | 8179/28080 [16:09:32<39:25:17,  7.13s/it]
                                                          
{'loss': 0.6174, 'learning_rate': 0.00041571673352609994, 'epoch': 3.49}

 29%|██▉       | 8179/28080 [16:09:32<39:25:17,  7.13s/it]
 29%|██▉       | 8180/28080 [16:09:39<39:20:32,  7.12s/it]
                                                          
{'loss': 0.6481, 'learning_rate': 0.00041569514205632254, 'epoch': 3.49}

 29%|██▉       | 8180/28080 [16:09:39<39:20:32,  7.12s/it]
 29%|██▉       | 8181/28080 [16:09:46<39:23:24,  7.13s/it]
                                                          
{'loss': 0.6393, 'learning_rate': 0.00041567354838214213, 'epoch': 3.49}

 29%|██▉       | 8181/28080 [16:09:46<39:23:24,  7.13s/it]
 29%|██▉       | 8182/28080 [16:09:53<39:27:15,  7.14s/it]
                                                          
{'loss': 0.6161, 'learning_rate': 0.00041565195250384615, 'epoch': 3.5}

 29%|██▉       | 8182/28080 [16:09:53<39:27:15,  7.14s/it]
 29%|██▉       | 8183/28080 [16:10:00<39:25:28,  7.13s/it]
                                                          
{'loss': 0.6325, 'learning_rate': 0.0004156303544217217, 'epoch': 3.5}

 29%|██▉       | 8183/28080 [16:10:00<39:25:28,  7.13s/it]
 29%|██▉       | 8184/28080 [16:10:07<39:13:17,  7.10s/it]
                                                          
{'loss': 0.6236, 'learning_rate': 0.0004156087541360564, 'epoch': 3.5}

 29%|██▉       | 8184/28080 [16:10:07<39:13:17,  7.10s/it]
 29%|██▉       | 8185/28080 [16:10:14<39:14:44,  7.10s/it]
                                                          
{'loss': 0.6398, 'learning_rate': 0.0004155871516471375, 'epoch': 3.5}

 29%|██▉       | 8185/28080 [16:10:14<39:14:44,  7.10s/it]
 29%|██▉       | 8186/28080 [16:10:22<39:19:37,  7.12s/it]
                                                          
{'loss': 0.6169, 'learning_rate': 0.0004155655469552522, 'epoch': 3.5}

 29%|██▉       | 8186/28080 [16:10:22<39:19:37,  7.12s/it]
 29%|██▉       | 8187/28080 [16:10:29<39:13:06,  7.10s/it]
                                                          
{'loss': 0.619, 'learning_rate': 0.00041554394006068824, 'epoch': 3.5}

 29%|██▉       | 8187/28080 [16:10:29<39:13:06,  7.10s/it]
 29%|██▉       | 8188/28080 [16:10:36<39:13:54,  7.10s/it]
                                                          
{'loss': 0.6225, 'learning_rate': 0.0004155223309637329, 'epoch': 3.5}

 29%|██▉       | 8188/28080 [16:10:36<39:13:54,  7.10s/it]
 29%|██▉       | 8189/28080 [16:10:43<39:15:19,  7.10s/it]
                                                          
{'loss': 0.6119, 'learning_rate': 0.0004155007196646737, 'epoch': 3.5}

 29%|██▉       | 8189/28080 [16:10:43<39:15:19,  7.10s/it]
 29%|██▉       | 8190/28080 [16:10:50<39:22:06,  7.13s/it]
                                                          
{'loss': 0.6127, 'learning_rate': 0.00041547910616379814, 'epoch': 3.5}

 29%|██▉       | 8190/28080 [16:10:50<39:22:06,  7.13s/it]
 29%|██▉       | 8191/28080 [16:10:57<39:17:12,  7.11s/it]
                                                          
{'loss': 0.6508, 'learning_rate': 0.0004154574904613938, 'epoch': 3.5}

 29%|██▉       | 8191/28080 [16:10:57<39:17:12,  7.11s/it]
 29%|██▉       | 8192/28080 [16:11:04<39:21:26,  7.12s/it]
                                                          
{'loss': 0.638, 'learning_rate': 0.0004154358725577483, 'epoch': 3.5}

 29%|██▉       | 8192/28080 [16:11:04<39:21:26,  7.12s/it]
 29%|██▉       | 8193/28080 [16:11:11<39:23:20,  7.13s/it]
                                                          
{'loss': 0.6301, 'learning_rate': 0.0004154142524531491, 'epoch': 3.5}

 29%|██▉       | 8193/28080 [16:11:11<39:23:20,  7.13s/it]
 29%|██▉       | 8194/28080 [16:11:19<39:17:22,  7.11s/it]
                                                          
{'loss': 0.6208, 'learning_rate': 0.000415392630147884, 'epoch': 3.5}

 29%|██▉       | 8194/28080 [16:11:19<39:17:22,  7.11s/it]
 29%|██▉       | 8195/28080 [16:11:26<39:19:34,  7.12s/it]
                                                          
{'loss': 0.6346, 'learning_rate': 0.0004153710056422406, 'epoch': 3.5}

 29%|██▉       | 8195/28080 [16:11:26<39:19:34,  7.12s/it]
 29%|██▉       | 8196/28080 [16:11:33<39:18:25,  7.12s/it]
                                                          
{'loss': 0.6353, 'learning_rate': 0.00041534937893650655, 'epoch': 3.5}

 29%|██▉       | 8196/28080 [16:11:33<39:18:25,  7.12s/it]
 29%|██▉       | 8197/28080 [16:11:40<39:24:59,  7.14s/it]
                                                          
{'loss': 0.6118, 'learning_rate': 0.00041532775003096957, 'epoch': 3.5}

 29%|██▉       | 8197/28080 [16:11:40<39:24:59,  7.14s/it]
 29%|██▉       | 8198/28080 [16:11:47<39:21:26,  7.13s/it]
                                                          
{'loss': 0.6333, 'learning_rate': 0.0004153061189259174, 'epoch': 3.5}

 29%|██▉       | 8198/28080 [16:11:47<39:21:26,  7.13s/it]
 29%|██▉       | 8199/28080 [16:11:54<39:09:56,  7.09s/it]
                                                          
{'loss': 0.6462, 'learning_rate': 0.0004152844856216379, 'epoch': 3.5}

 29%|██▉       | 8199/28080 [16:11:54<39:09:56,  7.09s/it]
 29%|██▉       | 8200/28080 [16:12:01<39:14:35,  7.11s/it]
                                                          
{'loss': 0.6363, 'learning_rate': 0.0004152628501184188, 'epoch': 3.5}

 29%|██▉       | 8200/28080 [16:12:01<39:14:35,  7.11s/it]
 29%|██▉       | 8201/28080 [16:12:08<39:11:56,  7.10s/it]
                                                          
{'loss': 0.6564, 'learning_rate': 0.000415241212416548, 'epoch': 3.5}

 29%|██▉       | 8201/28080 [16:12:08<39:11:56,  7.10s/it]
 29%|██▉       | 8202/28080 [16:12:15<39:09:54,  7.09s/it]
                                                          
{'loss': 0.6383, 'learning_rate': 0.00041521957251631337, 'epoch': 3.5}

 29%|██▉       | 8202/28080 [16:12:15<39:09:54,  7.09s/it]
 29%|██▉       | 8203/28080 [16:12:22<39:13:26,  7.10s/it]
                                                          
{'loss': 0.6466, 'learning_rate': 0.0004151979304180027, 'epoch': 3.5}

 29%|██▉       | 8203/28080 [16:12:22<39:13:26,  7.10s/it]
 29%|██▉       | 8204/28080 [16:12:30<39:15:22,  7.11s/it]
                                                          
{'loss': 0.6236, 'learning_rate': 0.00041517628612190407, 'epoch': 3.5}

 29%|██▉       | 8204/28080 [16:12:30<39:15:22,  7.11s/it]
 29%|██▉       | 8205/28080 [16:12:37<39:21:43,  7.13s/it]
                                                          
{'loss': 0.6354, 'learning_rate': 0.0004151546396283053, 'epoch': 3.51}

 29%|██▉       | 8205/28080 [16:12:37<39:21:43,  7.13s/it]
 29%|██▉       | 8206/28080 [16:12:44<39:22:11,  7.13s/it]
                                                          
{'loss': 0.643, 'learning_rate': 0.00041513299093749446, 'epoch': 3.51}

 29%|██▉       | 8206/28080 [16:12:44<39:22:11,  7.13s/it]
 29%|██▉       | 8207/28080 [16:12:51<39:11:46,  7.10s/it]
                                                          
{'loss': 0.637, 'learning_rate': 0.00041511134004975947, 'epoch': 3.51}

 29%|██▉       | 8207/28080 [16:12:51<39:11:46,  7.10s/it]
 29%|██▉       | 8208/28080 [16:12:58<39:06:28,  7.08s/it]
                                                          
{'loss': 0.6234, 'learning_rate': 0.0004150896869653885, 'epoch': 3.51}

 29%|██▉       | 8208/28080 [16:12:58<39:06:28,  7.08s/it]
 29%|██▉       | 8209/28080 [16:13:05<38:58:16,  7.06s/it]
                                                          
{'loss': 0.6218, 'learning_rate': 0.0004150680316846696, 'epoch': 3.51}

 29%|██▉       | 8209/28080 [16:13:05<38:58:16,  7.06s/it]
 29%|██▉       | 8210/28080 [16:13:12<39:09:35,  7.09s/it]
                                                          
{'loss': 0.6477, 'learning_rate': 0.0004150463742078907, 'epoch': 3.51}

 29%|██▉       | 8210/28080 [16:13:12<39:09:35,  7.09s/it]
 29%|██▉       | 8211/28080 [16:13:19<39:08:56,  7.09s/it]
                                                          
{'loss': 0.6138, 'learning_rate': 0.00041502471453534013, 'epoch': 3.51}

 29%|██▉       | 8211/28080 [16:13:19<39:08:56,  7.09s/it]
 29%|██▉       | 8212/28080 [16:13:26<39:04:15,  7.08s/it]
                                                          
{'loss': 0.6189, 'learning_rate': 0.000415003052667306, 'epoch': 3.51}

 29%|██▉       | 8212/28080 [16:13:26<39:04:15,  7.08s/it]
 29%|██▉       | 8213/28080 [16:13:33<39:09:35,  7.10s/it]
                                                          
{'loss': 0.6077, 'learning_rate': 0.00041498138860407647, 'epoch': 3.51}

 29%|██▉       | 8213/28080 [16:13:33<39:09:35,  7.10s/it]
 29%|██▉       | 8214/28080 [16:13:41<39:11:18,  7.10s/it]
                                                          
{'loss': 0.6228, 'learning_rate': 0.0004149597223459397, 'epoch': 3.51}

 29%|██▉       | 8214/28080 [16:13:41<39:11:18,  7.10s/it]
 29%|██▉       | 8215/28080 [16:13:48<39:14:24,  7.11s/it]
                                                          
{'loss': 0.6351, 'learning_rate': 0.0004149380538931841, 'epoch': 3.51}

 29%|██▉       | 8215/28080 [16:13:48<39:14:24,  7.11s/it]
 29%|██▉       | 8216/28080 [16:13:55<39:12:43,  7.11s/it]
                                                          
{'loss': 0.6441, 'learning_rate': 0.0004149163832460978, 'epoch': 3.51}

 29%|██▉       | 8216/28080 [16:13:55<39:12:43,  7.11s/it]
 29%|██▉       | 8217/28080 [16:14:02<39:04:05,  7.08s/it]
                                                          
{'loss': 0.6441, 'learning_rate': 0.0004148947104049692, 'epoch': 3.51}

 29%|██▉       | 8217/28080 [16:14:02<39:04:05,  7.08s/it]
 29%|██▉       | 8218/28080 [16:14:09<39:08:04,  7.09s/it]
                                                          
{'loss': 0.6373, 'learning_rate': 0.00041487303537008654, 'epoch': 3.51}

 29%|██▉       | 8218/28080 [16:14:09<39:08:04,  7.09s/it]
 29%|██▉       | 8219/28080 [16:14:16<39:00:10,  7.07s/it]
                                                          
{'loss': 0.6468, 'learning_rate': 0.00041485135814173826, 'epoch': 3.51}

 29%|██▉       | 8219/28080 [16:14:16<39:00:10,  7.07s/it]
 29%|██▉       | 8220/28080 [16:14:23<39:03:44,  7.08s/it]
                                                          
{'loss': 0.6157, 'learning_rate': 0.0004148296787202127, 'epoch': 3.51}

 29%|██▉       | 8220/28080 [16:14:23<39:03:44,  7.08s/it]
 29%|██▉       | 8221/28080 [16:14:30<39:08:13,  7.09s/it]
                                                          
{'loss': 0.6195, 'learning_rate': 0.0004148079971057984, 'epoch': 3.51}

 29%|██▉       | 8221/28080 [16:14:30<39:08:13,  7.09s/it]
 29%|██▉       | 8222/28080 [16:14:37<39:05:37,  7.09s/it]
                                                          
{'loss': 0.6711, 'learning_rate': 0.00041478631329878356, 'epoch': 3.51}

 29%|██▉       | 8222/28080 [16:14:37<39:05:37,  7.09s/it]
 29%|██▉       | 8223/28080 [16:14:44<39:09:09,  7.10s/it]
                                                          
{'loss': 0.6624, 'learning_rate': 0.000414764627299457, 'epoch': 3.51}

 29%|██▉       | 8223/28080 [16:14:44<39:09:09,  7.10s/it]
 29%|██▉       | 8224/28080 [16:14:52<39:13:16,  7.11s/it]
                                                          
{'loss': 0.6264, 'learning_rate': 0.0004147429391081069, 'epoch': 3.51}

 29%|██▉       | 8224/28080 [16:14:52<39:13:16,  7.11s/it]
 29%|██▉       | 8225/28080 [16:14:58<38:59:27,  7.07s/it]
                                                          
{'loss': 0.6637, 'learning_rate': 0.000414721248725022, 'epoch': 3.51}

 29%|██▉       | 8225/28080 [16:14:58<38:59:27,  7.07s/it]
 29%|██▉       | 8226/28080 [16:15:06<39:03:46,  7.08s/it]
                                                          
{'loss': 0.6192, 'learning_rate': 0.0004146995561504909, 'epoch': 3.51}

 29%|██▉       | 8226/28080 [16:15:06<39:03:46,  7.08s/it]
 29%|██▉       | 8227/28080 [16:15:13<39:09:54,  7.10s/it]
                                                          
{'loss': 0.6067, 'learning_rate': 0.000414677861384802, 'epoch': 3.51}

 29%|██▉       | 8227/28080 [16:15:13<39:09:54,  7.10s/it]
 29%|██▉       | 8228/28080 [16:15:20<39:15:04,  7.12s/it]
                                                          
{'loss': 0.635, 'learning_rate': 0.0004146561644282441, 'epoch': 3.51}

 29%|██▉       | 8228/28080 [16:15:20<39:15:04,  7.12s/it]
 29%|██▉       | 8229/28080 [16:15:27<39:13:16,  7.11s/it]
                                                          
{'loss': 0.6307, 'learning_rate': 0.00041463446528110584, 'epoch': 3.52}

 29%|██▉       | 8229/28080 [16:15:27<39:13:16,  7.11s/it]
 29%|██▉       | 8230/28080 [16:15:34<39:11:08,  7.11s/it]
                                                          
{'loss': 0.6328, 'learning_rate': 0.0004146127639436758, 'epoch': 3.52}

 29%|██▉       | 8230/28080 [16:15:34<39:11:08,  7.11s/it]
 29%|██▉       | 8231/28080 [16:15:41<39:08:38,  7.10s/it]
                                                          
{'loss': 0.6219, 'learning_rate': 0.0004145910604162427, 'epoch': 3.52}

 29%|██▉       | 8231/28080 [16:15:41<39:08:38,  7.10s/it]
 29%|██▉       | 8232/28080 [16:15:48<38:58:07,  7.07s/it]
                                                          
{'loss': 0.6463, 'learning_rate': 0.00041456935469909545, 'epoch': 3.52}

 29%|██▉       | 8232/28080 [16:15:48<38:58:07,  7.07s/it]
 29%|██▉       | 8233/28080 [16:15:55<39:09:50,  7.10s/it]
                                                          
{'loss': 0.6171, 'learning_rate': 0.00041454764679252267, 'epoch': 3.52}

 29%|██▉       | 8233/28080 [16:15:55<39:09:50,  7.10s/it]
 29%|██▉       | 8234/28080 [16:16:02<39:09:36,  7.10s/it]
                                                          
{'loss': 0.6331, 'learning_rate': 0.0004145259366968133, 'epoch': 3.52}

 29%|██▉       | 8234/28080 [16:16:02<39:09:36,  7.10s/it]
 29%|██▉       | 8235/28080 [16:16:09<38:56:24,  7.06s/it]
                                                          
{'loss': 0.6455, 'learning_rate': 0.0004145042244122559, 'epoch': 3.52}

 29%|██▉       | 8235/28080 [16:16:09<38:56:24,  7.06s/it]
 29%|██▉       | 8236/28080 [16:16:17<39:07:41,  7.10s/it]
                                                          
{'loss': 0.6147, 'learning_rate': 0.0004144825099391396, 'epoch': 3.52}

 29%|██▉       | 8236/28080 [16:16:17<39:07:41,  7.10s/it]
 29%|██▉       | 8237/28080 [16:16:24<39:04:53,  7.09s/it]
                                                          
{'loss': 0.6371, 'learning_rate': 0.00041446079327775323, 'epoch': 3.52}

 29%|██▉       | 8237/28080 [16:16:24<39:04:53,  7.09s/it]
 29%|██▉       | 8238/28080 [16:16:31<39:12:38,  7.11s/it]
                                                          
{'loss': 0.6228, 'learning_rate': 0.00041443907442838555, 'epoch': 3.52}

 29%|██▉       | 8238/28080 [16:16:31<39:12:38,  7.11s/it]
 29%|██▉       | 8239/28080 [16:16:38<39:19:13,  7.13s/it]
                                                          
{'loss': 0.6164, 'learning_rate': 0.0004144173533913257, 'epoch': 3.52}

 29%|██▉       | 8239/28080 [16:16:38<39:19:13,  7.13s/it]
 29%|██▉       | 8240/28080 [16:16:45<39:28:30,  7.16s/it]
                                                          
{'loss': 0.6262, 'learning_rate': 0.0004143956301668626, 'epoch': 3.52}

 29%|██▉       | 8240/28080 [16:16:45<39:28:30,  7.16s/it]
 29%|██▉       | 8241/28080 [16:16:52<39:26:14,  7.16s/it]
                                                          
{'loss': 0.6266, 'learning_rate': 0.00041437390475528523, 'epoch': 3.52}

 29%|██▉       | 8241/28080 [16:16:52<39:26:14,  7.16s/it]
 29%|██▉       | 8242/28080 [16:16:59<39:16:03,  7.13s/it]
                                                          
{'loss': 0.6409, 'learning_rate': 0.00041435217715688264, 'epoch': 3.52}

 29%|██▉       | 8242/28080 [16:16:59<39:16:03,  7.13s/it]
 29%|██▉       | 8243/28080 [16:17:06<39:04:13,  7.09s/it]
                                                          
{'loss': 0.634, 'learning_rate': 0.0004143304473719439, 'epoch': 3.52}

 29%|██▉       | 8243/28080 [16:17:06<39:04:13,  7.09s/it]
 29%|██▉       | 8244/28080 [16:17:14<39:12:13,  7.12s/it]
                                                          
{'loss': 0.6328, 'learning_rate': 0.000414308715400758, 'epoch': 3.52}

 29%|██▉       | 8244/28080 [16:17:14<39:12:13,  7.12s/it]
 29%|██▉       | 8245/28080 [16:17:21<39:09:40,  7.11s/it]
                                                          
{'loss': 0.6179, 'learning_rate': 0.0004142869812436142, 'epoch': 3.52}

 29%|██▉       | 8245/28080 [16:17:21<39:09:40,  7.11s/it]
 29%|██▉       | 8246/28080 [16:17:28<39:00:43,  7.08s/it]
                                                          
{'loss': 0.625, 'learning_rate': 0.00041426524490080166, 'epoch': 3.52}

 29%|██▉       | 8246/28080 [16:17:28<39:00:43,  7.08s/it]
 29%|██▉       | 8247/28080 [16:17:35<39:12:26,  7.12s/it]
                                                          
{'loss': 0.6192, 'learning_rate': 0.00041424350637260944, 'epoch': 3.52}

 29%|██▉       | 8247/28080 [16:17:35<39:12:26,  7.12s/it]
 29%|██▉       | 8248/28080 [16:17:42<39:01:41,  7.08s/it]
                                                          
{'loss': 0.6372, 'learning_rate': 0.0004142217656593268, 'epoch': 3.52}

 29%|██▉       | 8248/28080 [16:17:42<39:01:41,  7.08s/it]
 29%|██▉       | 8249/28080 [16:17:49<38:54:14,  7.06s/it]
                                                          
{'loss': 0.6404, 'learning_rate': 0.000414200022761243, 'epoch': 3.52}

 29%|██▉       | 8249/28080 [16:17:49<38:54:14,  7.06s/it]
 29%|██▉       | 8250/28080 [16:17:56<38:56:47,  7.07s/it]
                                                          
{'loss': 0.6415, 'learning_rate': 0.00041417827767864724, 'epoch': 3.52}

 29%|██▉       | 8250/28080 [16:17:56<38:56:47,  7.07s/it]
 29%|██▉       | 8251/28080 [16:18:03<38:50:14,  7.05s/it]
                                                          
{'loss': 0.6257, 'learning_rate': 0.000414156530411829, 'epoch': 3.52}

 29%|██▉       | 8251/28080 [16:18:03<38:50:14,  7.05s/it]
 29%|██▉       | 8252/28080 [16:18:10<38:57:23,  7.07s/it]
                                                          
{'loss': 0.622, 'learning_rate': 0.00041413478096107736, 'epoch': 3.53}

 29%|██▉       | 8252/28080 [16:18:10<38:57:23,  7.07s/it]
 29%|██▉       | 8253/28080 [16:18:17<38:54:25,  7.06s/it]
                                                          
{'loss': 0.6274, 'learning_rate': 0.00041411302932668184, 'epoch': 3.53}

 29%|██▉       | 8253/28080 [16:18:17<38:54:25,  7.06s/it]
 29%|██▉       | 8254/28080 [16:18:24<38:59:08,  7.08s/it]
                                                          
{'loss': 0.6201, 'learning_rate': 0.00041409127550893175, 'epoch': 3.53}

 29%|██▉       | 8254/28080 [16:18:24<38:59:08,  7.08s/it]
 29%|██▉       | 8255/28080 [16:18:31<39:06:12,  7.10s/it]
                                                          
{'loss': 0.6241, 'learning_rate': 0.0004140695195081165, 'epoch': 3.53}

 29%|██▉       | 8255/28080 [16:18:32<39:06:12,  7.10s/it]
 29%|██▉       | 8256/28080 [16:18:39<39:05:35,  7.10s/it]
                                                          
{'loss': 0.6436, 'learning_rate': 0.0004140477613245256, 'epoch': 3.53}

 29%|██▉       | 8256/28080 [16:18:39<39:05:35,  7.10s/it]
 29%|██▉       | 8257/28080 [16:18:46<39:05:35,  7.10s/it]
                                                          
{'loss': 0.6302, 'learning_rate': 0.00041402600095844845, 'epoch': 3.53}

 29%|██▉       | 8257/28080 [16:18:46<39:05:35,  7.10s/it]
 29%|██▉       | 8258/28080 [16:18:53<39:03:26,  7.09s/it]
                                                          
{'loss': 0.6453, 'learning_rate': 0.0004140042384101745, 'epoch': 3.53}

 29%|██▉       | 8258/28080 [16:18:53<39:03:26,  7.09s/it]
 29%|██▉       | 8259/28080 [16:19:00<39:06:40,  7.10s/it]
                                                          
{'loss': 0.6194, 'learning_rate': 0.0004139824736799935, 'epoch': 3.53}

 29%|██▉       | 8259/28080 [16:19:00<39:06:40,  7.10s/it]
 29%|██▉       | 8260/28080 [16:19:07<39:08:11,  7.11s/it]
                                                          
{'loss': 0.6141, 'learning_rate': 0.00041396070676819475, 'epoch': 3.53}

 29%|██▉       | 8260/28080 [16:19:07<39:08:11,  7.11s/it]
 29%|██▉       | 8261/28080 [16:19:14<39:20:14,  7.15s/it]
                                                          
{'loss': 0.6408, 'learning_rate': 0.000413938937675068, 'epoch': 3.53}

 29%|██▉       | 8261/28080 [16:19:14<39:20:14,  7.15s/it]
 29%|██▉       | 8262/28080 [16:19:21<39:06:11,  7.10s/it]
                                                          
{'loss': 0.6509, 'learning_rate': 0.0004139171664009028, 'epoch': 3.53}

 29%|██▉       | 8262/28080 [16:19:21<39:06:11,  7.10s/it]
 29%|██▉       | 8263/28080 [16:19:28<39:07:14,  7.11s/it]
                                                          
{'loss': 0.6384, 'learning_rate': 0.00041389539294598874, 'epoch': 3.53}

 29%|██▉       | 8263/28080 [16:19:28<39:07:14,  7.11s/it]
 29%|██▉       | 8264/28080 [16:19:35<39:03:03,  7.09s/it]
                                                          
{'loss': 0.6402, 'learning_rate': 0.0004138736173106157, 'epoch': 3.53}

 29%|██▉       | 8264/28080 [16:19:35<39:03:03,  7.09s/it]
 29%|██▉       | 8265/28080 [16:19:42<38:57:51,  7.08s/it]
                                                          
{'loss': 0.6271, 'learning_rate': 0.0004138518394950731, 'epoch': 3.53}

 29%|██▉       | 8265/28080 [16:19:42<38:57:51,  7.08s/it]
 29%|██▉       | 8266/28080 [16:19:50<38:53:13,  7.07s/it]
                                                          
{'loss': 0.6437, 'learning_rate': 0.00041383005949965093, 'epoch': 3.53}

 29%|██▉       | 8266/28080 [16:19:50<38:53:13,  7.07s/it]
 29%|██▉       | 8267/28080 [16:19:57<38:52:52,  7.06s/it]
                                                          
{'loss': 0.65, 'learning_rate': 0.0004138082773246388, 'epoch': 3.53}

 29%|██▉       | 8267/28080 [16:19:57<38:52:52,  7.06s/it]
 29%|██▉       | 8268/28080 [16:20:04<38:59:57,  7.09s/it]
                                                          
{'loss': 0.6433, 'learning_rate': 0.0004137864929703264, 'epoch': 3.53}

 29%|██▉       | 8268/28080 [16:20:04<38:59:57,  7.09s/it]
 29%|██▉       | 8269/28080 [16:20:11<39:10:55,  7.12s/it]
                                                          
{'loss': 0.6471, 'learning_rate': 0.0004137647064370038, 'epoch': 3.53}

 29%|██▉       | 8269/28080 [16:20:11<39:10:55,  7.12s/it]
 29%|██▉       | 8270/28080 [16:20:18<39:14:25,  7.13s/it]
                                                          
{'loss': 0.6589, 'learning_rate': 0.00041374291772496073, 'epoch': 3.53}

 29%|██▉       | 8270/28080 [16:20:18<39:14:25,  7.13s/it]
 29%|██▉       | 8271/28080 [16:20:25<39:04:26,  7.10s/it]
                                                          
{'loss': 0.6424, 'learning_rate': 0.0004137211268344871, 'epoch': 3.53}

 29%|██▉       | 8271/28080 [16:20:25<39:04:26,  7.10s/it]
 29%|██▉       | 8272/28080 [16:20:32<38:55:16,  7.07s/it]
                                                          
{'loss': 0.6288, 'learning_rate': 0.00041369933376587275, 'epoch': 3.53}

 29%|██▉       | 8272/28080 [16:20:32<38:55:16,  7.07s/it]
 29%|██▉       | 8273/28080 [16:20:39<38:54:13,  7.07s/it]
                                                          
{'loss': 0.6319, 'learning_rate': 0.0004136775385194076, 'epoch': 3.53}

 29%|██▉       | 8273/28080 [16:20:39<38:54:13,  7.07s/it]
 29%|██▉       | 8274/28080 [16:20:46<38:51:16,  7.06s/it]
                                                          
{'loss': 0.6384, 'learning_rate': 0.00041365574109538165, 'epoch': 3.53}

 29%|██▉       | 8274/28080 [16:20:46<38:51:16,  7.06s/it]
 29%|██▉       | 8275/28080 [16:20:53<38:50:43,  7.06s/it]
                                                          
{'loss': 0.6327, 'learning_rate': 0.00041363394149408495, 'epoch': 3.54}

 29%|██▉       | 8275/28080 [16:20:53<38:50:43,  7.06s/it]
 29%|██▉       | 8276/28080 [16:21:00<38:54:40,  7.07s/it]
                                                          
{'loss': 0.6331, 'learning_rate': 0.00041361213971580744, 'epoch': 3.54}

 29%|██▉       | 8276/28080 [16:21:00<38:54:40,  7.07s/it]
 29%|██▉       | 8277/28080 [16:21:07<38:54:05,  7.07s/it]
                                                          
{'loss': 0.632, 'learning_rate': 0.0004135903357608392, 'epoch': 3.54}

 29%|██▉       | 8277/28080 [16:21:07<38:54:05,  7.07s/it]
 29%|██▉       | 8278/28080 [16:21:15<38:56:27,  7.08s/it]
                                                          
{'loss': 0.6186, 'learning_rate': 0.00041356852962947033, 'epoch': 3.54}

 29%|██▉       | 8278/28080 [16:21:15<38:56:27,  7.08s/it]
 29%|██▉       | 8279/28080 [16:21:22<38:56:50,  7.08s/it]
                                                          
{'loss': 0.6313, 'learning_rate': 0.0004135467213219909, 'epoch': 3.54}

 29%|██▉       | 8279/28080 [16:21:22<38:56:50,  7.08s/it]
 29%|██▉       | 8280/28080 [16:21:29<38:48:54,  7.06s/it]
                                                          
{'loss': 0.64, 'learning_rate': 0.00041352491083869106, 'epoch': 3.54}

 29%|██▉       | 8280/28080 [16:21:29<38:48:54,  7.06s/it]
 29%|██▉       | 8281/28080 [16:21:36<38:49:47,  7.06s/it]
                                                          
{'loss': 0.6097, 'learning_rate': 0.00041350309817986096, 'epoch': 3.54}

 29%|██▉       | 8281/28080 [16:21:36<38:49:47,  7.06s/it]
 29%|██▉       | 8282/28080 [16:21:43<38:57:48,  7.08s/it]
                                                          
{'loss': 0.6273, 'learning_rate': 0.00041348128334579083, 'epoch': 3.54}

 29%|██▉       | 8282/28080 [16:21:43<38:57:48,  7.08s/it]
 29%|██▉       | 8283/28080 [16:21:50<38:54:01,  7.07s/it]
                                                          
{'loss': 0.6316, 'learning_rate': 0.0004134594663367709, 'epoch': 3.54}

 29%|██▉       | 8283/28080 [16:21:50<38:54:01,  7.07s/it]
 30%|██▉       | 8284/28080 [16:21:57<38:59:22,  7.09s/it]
                                                          
{'loss': 0.6507, 'learning_rate': 0.0004134376471530914, 'epoch': 3.54}

 30%|██▉       | 8284/28080 [16:21:57<38:59:22,  7.09s/it]
 30%|██▉       | 8285/28080 [16:22:04<39:04:57,  7.11s/it]
                                                          
{'loss': 0.6454, 'learning_rate': 0.00041341582579504263, 'epoch': 3.54}

 30%|██▉       | 8285/28080 [16:22:04<39:04:57,  7.11s/it]
 30%|██▉       | 8286/28080 [16:22:11<39:02:34,  7.10s/it]
                                                          
{'loss': 0.629, 'learning_rate': 0.0004133940022629148, 'epoch': 3.54}

 30%|██▉       | 8286/28080 [16:22:11<39:02:34,  7.10s/it]
 30%|██▉       | 8287/28080 [16:22:18<38:56:44,  7.08s/it]
                                                          
{'loss': 0.6317, 'learning_rate': 0.0004133721765569984, 'epoch': 3.54}

 30%|██▉       | 8287/28080 [16:22:18<38:56:44,  7.08s/it]
 30%|██▉       | 8288/28080 [16:22:25<38:52:52,  7.07s/it]
                                                          
{'loss': 0.6359, 'learning_rate': 0.0004133503486775838, 'epoch': 3.54}

 30%|██▉       | 8288/28080 [16:22:25<38:52:52,  7.07s/it]
 30%|██▉       | 8289/28080 [16:22:32<38:54:50,  7.08s/it]
                                                          
{'loss': 0.6307, 'learning_rate': 0.00041332851862496125, 'epoch': 3.54}

 30%|██▉       | 8289/28080 [16:22:32<38:54:50,  7.08s/it]
 30%|██▉       | 8290/28080 [16:22:40<38:57:08,  7.09s/it]
                                                          
{'loss': 0.637, 'learning_rate': 0.00041330668639942125, 'epoch': 3.54}

 30%|██▉       | 8290/28080 [16:22:40<38:57:08,  7.09s/it]
 30%|██▉       | 8291/28080 [16:22:47<39:00:12,  7.10s/it]
                                                          
{'loss': 0.6311, 'learning_rate': 0.00041328485200125425, 'epoch': 3.54}

 30%|██▉       | 8291/28080 [16:22:47<39:00:12,  7.10s/it]
 30%|██▉       | 8292/28080 [16:22:54<38:54:12,  7.08s/it]
                                                          
{'loss': 0.6173, 'learning_rate': 0.0004132630154307508, 'epoch': 3.54}

 30%|██▉       | 8292/28080 [16:22:54<38:54:12,  7.08s/it]
 30%|██▉       | 8293/28080 [16:23:01<38:56:25,  7.08s/it]
                                                          
{'loss': 0.6304, 'learning_rate': 0.00041324117668820135, 'epoch': 3.54}

 30%|██▉       | 8293/28080 [16:23:01<38:56:25,  7.08s/it]
 30%|██▉       | 8294/28080 [16:23:08<39:02:10,  7.10s/it]
                                                          
{'loss': 0.6035, 'learning_rate': 0.00041321933577389636, 'epoch': 3.54}

 30%|██▉       | 8294/28080 [16:23:08<39:02:10,  7.10s/it]
 30%|██▉       | 8295/28080 [16:23:15<39:04:27,  7.11s/it]
                                                          
{'loss': 0.6336, 'learning_rate': 0.00041319749268812665, 'epoch': 3.54}

 30%|██▉       | 8295/28080 [16:23:15<39:04:27,  7.11s/it]
 30%|██▉       | 8296/28080 [16:23:22<39:03:54,  7.11s/it]
                                                          
{'loss': 0.6278, 'learning_rate': 0.00041317564743118256, 'epoch': 3.54}

 30%|██▉       | 8296/28080 [16:23:22<39:03:54,  7.11s/it]
 30%|██▉       | 8297/28080 [16:23:29<38:57:50,  7.09s/it]
                                                          
{'loss': 0.6663, 'learning_rate': 0.00041315380000335483, 'epoch': 3.54}

 30%|██▉       | 8297/28080 [16:23:29<38:57:50,  7.09s/it]
 30%|██▉       | 8298/28080 [16:23:36<39:01:09,  7.10s/it]
                                                          
{'loss': 0.6448, 'learning_rate': 0.0004131319504049341, 'epoch': 3.54}

 30%|██▉       | 8298/28080 [16:23:36<39:01:09,  7.10s/it]
 30%|██▉       | 8299/28080 [16:23:43<39:02:32,  7.11s/it]
                                                          
{'loss': 0.6467, 'learning_rate': 0.0004131100986362111, 'epoch': 3.55}

 30%|██▉       | 8299/28080 [16:23:43<39:02:32,  7.11s/it]
 30%|██▉       | 8300/28080 [16:23:50<38:55:56,  7.09s/it]
                                                          
{'loss': 0.6482, 'learning_rate': 0.0004130882446974765, 'epoch': 3.55}

 30%|██▉       | 8300/28080 [16:23:50<38:55:56,  7.09s/it]
 30%|██▉       | 8301/28080 [16:23:58<38:59:33,  7.10s/it]
                                                          
{'loss': 0.6339, 'learning_rate': 0.000413066388589021, 'epoch': 3.55}

 30%|██▉       | 8301/28080 [16:23:58<38:59:33,  7.10s/it]
 30%|██▉       | 8302/28080 [16:24:05<38:57:09,  7.09s/it]
                                                          
{'loss': 0.6309, 'learning_rate': 0.0004130445303111355, 'epoch': 3.55}

 30%|██▉       | 8302/28080 [16:24:05<38:57:09,  7.09s/it]
 30%|██▉       | 8303/28080 [16:24:12<39:03:59,  7.11s/it]
                                                          
{'loss': 0.6326, 'learning_rate': 0.00041302266986411066, 'epoch': 3.55}

 30%|██▉       | 8303/28080 [16:24:12<39:03:59,  7.11s/it]
 30%|██▉       | 8304/28080 [16:24:19<39:11:19,  7.13s/it]
                                                          
{'loss': 0.6268, 'learning_rate': 0.0004130008072482374, 'epoch': 3.55}

 30%|██▉       | 8304/28080 [16:24:19<39:11:19,  7.13s/it]
 30%|██▉       | 8305/28080 [16:24:26<39:07:50,  7.12s/it]
                                                          
{'loss': 0.6038, 'learning_rate': 0.00041297894246380664, 'epoch': 3.55}

 30%|██▉       | 8305/28080 [16:24:26<39:07:50,  7.12s/it]
 30%|██▉       | 8306/28080 [16:24:33<39:06:21,  7.12s/it]
                                                          
{'loss': 0.614, 'learning_rate': 0.00041295707551110907, 'epoch': 3.55}

 30%|██▉       | 8306/28080 [16:24:33<39:06:21,  7.12s/it]
 30%|██▉       | 8307/28080 [16:24:40<38:51:22,  7.07s/it]
                                                          
{'loss': 0.6186, 'learning_rate': 0.0004129352063904358, 'epoch': 3.55}

 30%|██▉       | 8307/28080 [16:24:40<38:51:22,  7.07s/it]
 30%|██▉       | 8308/28080 [16:24:47<38:59:14,  7.10s/it]
                                                          
{'loss': 0.6152, 'learning_rate': 0.00041291333510207765, 'epoch': 3.55}

 30%|██▉       | 8308/28080 [16:24:47<38:59:14,  7.10s/it]
 30%|██▉       | 8309/28080 [16:24:55<39:04:12,  7.11s/it]
                                                          
{'loss': 0.6445, 'learning_rate': 0.00041289146164632563, 'epoch': 3.55}

 30%|██▉       | 8309/28080 [16:24:55<39:04:12,  7.11s/it]
 30%|██▉       | 8310/28080 [16:25:02<39:10:39,  7.13s/it]
                                                          
{'loss': 0.6629, 'learning_rate': 0.0004128695860234708, 'epoch': 3.55}

 30%|██▉       | 8310/28080 [16:25:02<39:10:39,  7.13s/it]
 30%|██▉       | 8311/28080 [16:25:09<38:59:44,  7.10s/it]
                                                          
{'loss': 0.6377, 'learning_rate': 0.0004128477082338041, 'epoch': 3.55}

 30%|██▉       | 8311/28080 [16:25:09<38:59:44,  7.10s/it]
 30%|██▉       | 8312/28080 [16:25:16<38:49:27,  7.07s/it]
                                                          
{'loss': 0.645, 'learning_rate': 0.0004128258282776167, 'epoch': 3.55}

 30%|██▉       | 8312/28080 [16:25:16<38:49:27,  7.07s/it]
 30%|██▉       | 8313/28080 [16:25:23<38:51:13,  7.08s/it]
                                                          
{'loss': 0.6304, 'learning_rate': 0.00041280394615519965, 'epoch': 3.55}

 30%|██▉       | 8313/28080 [16:25:23<38:51:13,  7.08s/it]
 30%|██▉       | 8314/28080 [16:25:30<38:46:04,  7.06s/it]
                                                          
{'loss': 0.6323, 'learning_rate': 0.00041278206186684405, 'epoch': 3.55}

 30%|██▉       | 8314/28080 [16:25:30<38:46:04,  7.06s/it]
 30%|██▉       | 8315/28080 [16:25:37<38:44:12,  7.06s/it]
                                                          
{'loss': 0.6303, 'learning_rate': 0.000412760175412841, 'epoch': 3.55}

 30%|██▉       | 8315/28080 [16:25:37<38:44:12,  7.06s/it]
 30%|██▉       | 8316/28080 [16:25:44<38:51:31,  7.08s/it]
                                                          
{'loss': 0.6305, 'learning_rate': 0.00041273828679348176, 'epoch': 3.55}

 30%|██▉       | 8316/28080 [16:25:44<38:51:31,  7.08s/it]
 30%|██▉       | 8317/28080 [16:25:51<38:58:12,  7.10s/it]
                                                          
{'loss': 0.628, 'learning_rate': 0.00041271639600905745, 'epoch': 3.55}

 30%|██▉       | 8317/28080 [16:25:51<38:58:12,  7.10s/it]
 30%|██▉       | 8318/28080 [16:25:58<38:58:26,  7.10s/it]
                                                          
{'loss': 0.6562, 'learning_rate': 0.00041269450305985946, 'epoch': 3.55}

 30%|██▉       | 8318/28080 [16:25:58<38:58:26,  7.10s/it]
 30%|██▉       | 8319/28080 [16:26:05<38:52:01,  7.08s/it]
                                                          
{'loss': 0.6475, 'learning_rate': 0.00041267260794617885, 'epoch': 3.55}

 30%|██▉       | 8319/28080 [16:26:05<38:52:01,  7.08s/it]
 30%|██▉       | 8320/28080 [16:26:12<38:49:14,  7.07s/it]
                                                          
{'loss': 0.6305, 'learning_rate': 0.00041265071066830705, 'epoch': 3.55}

 30%|██▉       | 8320/28080 [16:26:12<38:49:14,  7.07s/it]
 30%|██▉       | 8321/28080 [16:26:19<38:45:17,  7.06s/it]
                                                          
{'loss': 0.6327, 'learning_rate': 0.00041262881122653534, 'epoch': 3.55}

 30%|██▉       | 8321/28080 [16:26:19<38:45:17,  7.06s/it]
 30%|██▉       | 8322/28080 [16:26:26<38:50:05,  7.08s/it]
                                                          
{'loss': 0.6234, 'learning_rate': 0.0004126069096211551, 'epoch': 3.56}

 30%|██▉       | 8322/28080 [16:26:27<38:50:05,  7.08s/it]
 30%|██▉       | 8323/28080 [16:26:33<38:41:55,  7.05s/it]
                                                          
{'loss': 0.6076, 'learning_rate': 0.0004125850058524576, 'epoch': 3.56}

 30%|██▉       | 8323/28080 [16:26:33<38:41:55,  7.05s/it]
 30%|██▉       | 8324/28080 [16:26:41<38:39:08,  7.04s/it]
                                                          
{'loss': 0.6114, 'learning_rate': 0.00041256309992073435, 'epoch': 3.56}

 30%|██▉       | 8324/28080 [16:26:41<38:39:08,  7.04s/it]
 30%|██▉       | 8325/28080 [16:26:48<38:48:11,  7.07s/it]
                                                          
{'loss': 0.625, 'learning_rate': 0.00041254119182627686, 'epoch': 3.56}

 30%|██▉       | 8325/28080 [16:26:48<38:48:11,  7.07s/it]
 30%|██▉       | 8326/28080 [16:26:55<38:50:24,  7.08s/it]
                                                          
{'loss': 0.6309, 'learning_rate': 0.0004125192815693764, 'epoch': 3.56}

 30%|██▉       | 8326/28080 [16:26:55<38:50:24,  7.08s/it]
 30%|██▉       | 8327/28080 [16:27:02<38:38:12,  7.04s/it]
                                                          
{'loss': 0.6463, 'learning_rate': 0.00041249736915032457, 'epoch': 3.56}

 30%|██▉       | 8327/28080 [16:27:02<38:38:12,  7.04s/it]
 30%|██▉       | 8328/28080 [16:27:09<38:42:11,  7.05s/it]
                                                          
{'loss': 0.6336, 'learning_rate': 0.0004124754545694129, 'epoch': 3.56}

 30%|██▉       | 8328/28080 [16:27:09<38:42:11,  7.05s/it]
 30%|██▉       | 8329/28080 [16:27:16<38:42:49,  7.06s/it]
                                                          
{'loss': 0.6336, 'learning_rate': 0.00041245353782693296, 'epoch': 3.56}

 30%|██▉       | 8329/28080 [16:27:16<38:42:49,  7.06s/it]
 30%|██▉       | 8330/28080 [16:27:23<38:52:30,  7.09s/it]
                                                          
{'loss': 0.6474, 'learning_rate': 0.00041243161892317627, 'epoch': 3.56}

 30%|██▉       | 8330/28080 [16:27:23<38:52:30,  7.09s/it]
 30%|██▉       | 8331/28080 [16:27:30<38:48:39,  7.07s/it]
                                                          
{'loss': 0.6218, 'learning_rate': 0.0004124096978584344, 'epoch': 3.56}

 30%|██▉       | 8331/28080 [16:27:30<38:48:39,  7.07s/it]
 30%|██▉       | 8332/28080 [16:27:37<38:47:42,  7.07s/it]
                                                          
{'loss': 0.6332, 'learning_rate': 0.00041238777463299914, 'epoch': 3.56}

 30%|██▉       | 8332/28080 [16:27:37<38:47:42,  7.07s/it]
 30%|██▉       | 8333/28080 [16:27:44<38:54:08,  7.09s/it]
                                                          
{'loss': 0.6328, 'learning_rate': 0.00041236584924716205, 'epoch': 3.56}

 30%|██▉       | 8333/28080 [16:27:44<38:54:08,  7.09s/it]
 30%|██▉       | 8334/28080 [16:27:51<38:52:32,  7.09s/it]
                                                          
{'loss': 0.6456, 'learning_rate': 0.0004123439217012148, 'epoch': 3.56}

 30%|██▉       | 8334/28080 [16:27:51<38:52:32,  7.09s/it]
 30%|██▉       | 8335/28080 [16:27:58<38:55:42,  7.10s/it]
                                                          
{'loss': 0.6228, 'learning_rate': 0.0004123219919954491, 'epoch': 3.56}

 30%|██▉       | 8335/28080 [16:27:58<38:55:42,  7.10s/it]
 30%|██▉       | 8336/28080 [16:28:06<38:54:27,  7.09s/it]
                                                          
{'loss': 0.6296, 'learning_rate': 0.00041230006013015687, 'epoch': 3.56}

 30%|██▉       | 8336/28080 [16:28:06<38:54:27,  7.09s/it]
 30%|██▉       | 8337/28080 [16:28:13<38:55:16,  7.10s/it]
                                                          
{'loss': 0.644, 'learning_rate': 0.00041227812610562965, 'epoch': 3.56}

 30%|██▉       | 8337/28080 [16:28:13<38:55:16,  7.10s/it]
 30%|██▉       | 8338/28080 [16:28:20<38:56:11,  7.10s/it]
                                                          
{'loss': 0.6166, 'learning_rate': 0.0004122561899221595, 'epoch': 3.56}

 30%|██▉       | 8338/28080 [16:28:20<38:56:11,  7.10s/it]
 30%|██▉       | 8339/28080 [16:28:27<39:00:08,  7.11s/it]
                                                          
{'loss': 0.6434, 'learning_rate': 0.0004122342515800381, 'epoch': 3.56}

 30%|██▉       | 8339/28080 [16:28:27<39:00:08,  7.11s/it]
 30%|██▉       | 8340/28080 [16:28:34<39:05:55,  7.13s/it]
                                                          
{'loss': 0.6106, 'learning_rate': 0.0004122123110795573, 'epoch': 3.56}

 30%|██▉       | 8340/28080 [16:28:34<39:05:55,  7.13s/it]
 30%|██▉       | 8341/28080 [16:28:41<38:59:06,  7.11s/it]
                                                          
{'loss': 0.6551, 'learning_rate': 0.0004121903684210091, 'epoch': 3.56}

 30%|██▉       | 8341/28080 [16:28:41<38:59:06,  7.11s/it]
 30%|██▉       | 8342/28080 [16:28:48<39:07:02,  7.13s/it]
                                                          
{'loss': 0.6479, 'learning_rate': 0.0004121684236046853, 'epoch': 3.56}

 30%|██▉       | 8342/28080 [16:28:48<39:07:02,  7.13s/it]
 30%|██▉       | 8343/28080 [16:28:55<39:04:21,  7.13s/it]
                                                          
{'loss': 0.6142, 'learning_rate': 0.000412146476630878, 'epoch': 3.56}

 30%|██▉       | 8343/28080 [16:28:55<39:04:21,  7.13s/it]
 30%|██▉       | 8344/28080 [16:29:03<39:07:30,  7.14s/it]
                                                          
{'loss': 0.6062, 'learning_rate': 0.00041212452749987905, 'epoch': 3.56}

 30%|██▉       | 8344/28080 [16:29:03<39:07:30,  7.14s/it]
 30%|██▉       | 8345/28080 [16:29:10<39:09:37,  7.14s/it]
                                                          
{'loss': 0.6341, 'learning_rate': 0.00041210257621198055, 'epoch': 3.56}

 30%|██▉       | 8345/28080 [16:29:10<39:09:37,  7.14s/it]
 30%|██▉       | 8346/28080 [16:29:17<39:13:33,  7.16s/it]
                                                          
{'loss': 0.6297, 'learning_rate': 0.0004120806227674745, 'epoch': 3.57}

 30%|██▉       | 8346/28080 [16:29:17<39:13:33,  7.16s/it]
 30%|██▉       | 8347/28080 [16:29:24<39:01:31,  7.12s/it]
                                                          
{'loss': 0.6715, 'learning_rate': 0.000412058667166653, 'epoch': 3.57}

 30%|██▉       | 8347/28080 [16:29:24<39:01:31,  7.12s/it]
 30%|██▉       | 8348/28080 [16:29:31<39:04:42,  7.13s/it]
                                                          
{'loss': 0.6276, 'learning_rate': 0.0004120367094098081, 'epoch': 3.57}

 30%|██▉       | 8348/28080 [16:29:31<39:04:42,  7.13s/it]
 30%|██▉       | 8349/28080 [16:29:38<39:03:39,  7.13s/it]
                                                          
{'loss': 0.618, 'learning_rate': 0.00041201474949723195, 'epoch': 3.57}

 30%|██▉       | 8349/28080 [16:29:38<39:03:39,  7.13s/it]
 30%|██▉       | 8350/28080 [16:29:45<39:14:03,  7.16s/it]
                                                          
{'loss': 0.6061, 'learning_rate': 0.0004119927874292167, 'epoch': 3.57}

 30%|██▉       | 8350/28080 [16:29:45<39:14:03,  7.16s/it]
 30%|██▉       | 8351/28080 [16:29:53<39:35:28,  7.22s/it]
                                                          
{'loss': 0.643, 'learning_rate': 0.0004119708232060545, 'epoch': 3.57}

 30%|██▉       | 8351/28080 [16:29:53<39:35:28,  7.22s/it]
 30%|██▉       | 8352/28080 [16:30:00<39:25:01,  7.19s/it]
                                                          
{'loss': 0.6344, 'learning_rate': 0.00041194885682803765, 'epoch': 3.57}

 30%|██▉       | 8352/28080 [16:30:00<39:25:01,  7.19s/it]
 30%|██▉       | 8353/28080 [16:30:07<39:06:08,  7.14s/it]
                                                          
{'loss': 0.6403, 'learning_rate': 0.00041192688829545825, 'epoch': 3.57}

 30%|██▉       | 8353/28080 [16:30:07<39:06:08,  7.14s/it]
 30%|██▉       | 8354/28080 [16:30:14<39:08:56,  7.14s/it]
                                                          
{'loss': 0.6319, 'learning_rate': 0.0004119049176086087, 'epoch': 3.57}

 30%|██▉       | 8354/28080 [16:30:14<39:08:56,  7.14s/it]
 30%|██▉       | 8355/28080 [16:30:21<39:07:08,  7.14s/it]
                                                          
{'loss': 0.6279, 'learning_rate': 0.0004118829447677813, 'epoch': 3.57}

 30%|██▉       | 8355/28080 [16:30:21<39:07:08,  7.14s/it]
 30%|██▉       | 8356/28080 [16:30:28<39:08:10,  7.14s/it]
                                                          
{'loss': 0.6442, 'learning_rate': 0.00041186096977326826, 'epoch': 3.57}

 30%|██▉       | 8356/28080 [16:30:28<39:08:10,  7.14s/it]
 30%|██▉       | 8357/28080 [16:30:36<39:08:27,  7.14s/it]
                                                          
{'loss': 0.5984, 'learning_rate': 0.00041183899262536193, 'epoch': 3.57}

 30%|██▉       | 8357/28080 [16:30:36<39:08:27,  7.14s/it]
 30%|██▉       | 8358/28080 [16:30:43<39:04:43,  7.13s/it]
                                                          
{'loss': 0.622, 'learning_rate': 0.00041181701332435494, 'epoch': 3.57}

 30%|██▉       | 8358/28080 [16:30:43<39:04:43,  7.13s/it]
 30%|██▉       | 8359/28080 [16:30:50<38:50:02,  7.09s/it]
                                                          
{'loss': 0.6426, 'learning_rate': 0.00041179503187053937, 'epoch': 3.57}

 30%|██▉       | 8359/28080 [16:30:50<38:50:02,  7.09s/it]
 30%|██▉       | 8360/28080 [16:30:57<38:51:46,  7.09s/it]
                                                          
{'loss': 0.6315, 'learning_rate': 0.00041177304826420794, 'epoch': 3.57}

 30%|██▉       | 8360/28080 [16:30:57<38:51:46,  7.09s/it]
 30%|██▉       | 8361/28080 [16:31:04<38:49:16,  7.09s/it]
                                                          
{'loss': 0.6332, 'learning_rate': 0.00041175106250565286, 'epoch': 3.57}

 30%|██▉       | 8361/28080 [16:31:04<38:49:16,  7.09s/it]
 30%|██▉       | 8362/28080 [16:31:11<38:53:42,  7.10s/it]
                                                          
{'loss': 0.6279, 'learning_rate': 0.00041172907459516685, 'epoch': 3.57}

 30%|██▉       | 8362/28080 [16:31:11<38:53:42,  7.10s/it]
 30%|██▉       | 8363/28080 [16:31:18<38:51:48,  7.10s/it]
                                                          
{'loss': 0.6326, 'learning_rate': 0.00041170708453304233, 'epoch': 3.57}

 30%|██▉       | 8363/28080 [16:31:18<38:51:48,  7.10s/it]
 30%|██▉       | 8364/28080 [16:31:25<38:52:10,  7.10s/it]
                                                          
{'loss': 0.6456, 'learning_rate': 0.0004116850923195719, 'epoch': 3.57}

 30%|██▉       | 8364/28080 [16:31:25<38:52:10,  7.10s/it]
 30%|██▉       | 8365/28080 [16:31:32<38:52:34,  7.10s/it]
                                                          
{'loss': 0.6443, 'learning_rate': 0.0004116630979550481, 'epoch': 3.57}

 30%|██▉       | 8365/28080 [16:31:32<38:52:34,  7.10s/it]
 30%|██▉       | 8366/28080 [16:31:39<39:00:14,  7.12s/it]
                                                          
{'loss': 0.6517, 'learning_rate': 0.0004116411014397635, 'epoch': 3.57}

 30%|██▉       | 8366/28080 [16:31:39<39:00:14,  7.12s/it]
 30%|██▉       | 8367/28080 [16:31:47<38:58:40,  7.12s/it]
                                                          
{'loss': 0.6181, 'learning_rate': 0.00041161910277401093, 'epoch': 3.57}

 30%|██▉       | 8367/28080 [16:31:47<38:58:40,  7.12s/it]
 30%|██▉       | 8368/28080 [16:31:54<38:56:06,  7.11s/it]
                                                          
{'loss': 0.6299, 'learning_rate': 0.00041159710195808286, 'epoch': 3.57}

 30%|██▉       | 8368/28080 [16:31:54<38:56:06,  7.11s/it]
 30%|██▉       | 8369/28080 [16:32:01<39:10:46,  7.16s/it]
                                                          
{'loss': 0.6215, 'learning_rate': 0.000411575098992272, 'epoch': 3.58}

 30%|██▉       | 8369/28080 [16:32:01<39:10:46,  7.16s/it]
 30%|██▉       | 8370/28080 [16:32:08<39:10:50,  7.16s/it]
                                                          
{'loss': 0.6289, 'learning_rate': 0.0004115530938768712, 'epoch': 3.58}

 30%|██▉       | 8370/28080 [16:32:08<39:10:50,  7.16s/it]
 30%|██▉       | 8371/28080 [16:32:15<39:10:38,  7.16s/it]
                                                          
{'loss': 0.6205, 'learning_rate': 0.0004115310866121732, 'epoch': 3.58}

 30%|██▉       | 8371/28080 [16:32:15<39:10:38,  7.16s/it]
 30%|██▉       | 8372/28080 [16:32:22<39:20:28,  7.19s/it]
                                                          
{'loss': 0.6415, 'learning_rate': 0.00041150907719847066, 'epoch': 3.58}

 30%|██▉       | 8372/28080 [16:32:22<39:20:28,  7.19s/it]
 30%|██▉       | 8373/28080 [16:32:30<39:17:23,  7.18s/it]
                                                          
{'loss': 0.628, 'learning_rate': 0.00041148706563605647, 'epoch': 3.58}

 30%|██▉       | 8373/28080 [16:32:30<39:17:23,  7.18s/it]
 30%|██▉       | 8374/28080 [16:32:37<39:15:55,  7.17s/it]
                                                          
{'loss': 0.6191, 'learning_rate': 0.0004114650519252235, 'epoch': 3.58}

 30%|██▉       | 8374/28080 [16:32:37<39:15:55,  7.17s/it]
 30%|██▉       | 8375/28080 [16:32:44<39:08:07,  7.15s/it]
                                                          
{'loss': 0.6389, 'learning_rate': 0.0004114430360662646, 'epoch': 3.58}

 30%|██▉       | 8375/28080 [16:32:44<39:08:07,  7.15s/it]
 30%|██▉       | 8376/28080 [16:32:51<39:10:32,  7.16s/it]
                                                          
{'loss': 0.6319, 'learning_rate': 0.0004114210180594726, 'epoch': 3.58}

 30%|██▉       | 8376/28080 [16:32:51<39:10:32,  7.16s/it]
 30%|██▉       | 8377/28080 [16:32:58<38:59:46,  7.13s/it]
                                                          
{'loss': 0.6378, 'learning_rate': 0.0004113989979051405, 'epoch': 3.58}

 30%|██▉       | 8377/28080 [16:32:58<38:59:46,  7.13s/it]
 30%|██▉       | 8378/28080 [16:33:05<39:00:31,  7.13s/it]
                                                          
{'loss': 0.618, 'learning_rate': 0.00041137697560356123, 'epoch': 3.58}

 30%|██▉       | 8378/28080 [16:33:05<39:00:31,  7.13s/it]
 30%|██▉       | 8379/28080 [16:33:12<39:02:09,  7.13s/it]
                                                          
{'loss': 0.6375, 'learning_rate': 0.00041135495115502785, 'epoch': 3.58}

 30%|██▉       | 8379/28080 [16:33:12<39:02:09,  7.13s/it]
 30%|██▉       | 8380/28080 [16:33:20<39:00:52,  7.13s/it]
                                                          
{'loss': 0.6249, 'learning_rate': 0.0004113329245598333, 'epoch': 3.58}

 30%|██▉       | 8380/28080 [16:33:20<39:00:52,  7.13s/it]
 30%|██▉       | 8381/28080 [16:33:27<39:06:31,  7.15s/it]
                                                          
{'loss': 0.6404, 'learning_rate': 0.00041131089581827055, 'epoch': 3.58}

 30%|██▉       | 8381/28080 [16:33:27<39:06:31,  7.15s/it]
 30%|██▉       | 8382/28080 [16:33:34<38:52:45,  7.11s/it]
                                                          
{'loss': 0.6459, 'learning_rate': 0.00041128886493063275, 'epoch': 3.58}

 30%|██▉       | 8382/28080 [16:33:34<38:52:45,  7.11s/it]
 30%|██▉       | 8383/28080 [16:33:41<38:54:16,  7.11s/it]
                                                          
{'loss': 0.6367, 'learning_rate': 0.00041126683189721304, 'epoch': 3.58}

 30%|██▉       | 8383/28080 [16:33:41<38:54:16,  7.11s/it]
 30%|██▉       | 8384/28080 [16:33:48<39:00:26,  7.13s/it]
                                                          
{'loss': 0.6306, 'learning_rate': 0.0004112447967183045, 'epoch': 3.58}

 30%|██▉       | 8384/28080 [16:33:48<39:00:26,  7.13s/it]
 30%|██▉       | 8385/28080 [16:33:55<38:55:10,  7.11s/it]
                                                          
{'loss': 0.635, 'learning_rate': 0.0004112227593942003, 'epoch': 3.58}

 30%|██▉       | 8385/28080 [16:33:55<38:55:10,  7.11s/it]
 30%|██▉       | 8386/28080 [16:34:02<39:00:29,  7.13s/it]
                                                          
{'loss': 0.6318, 'learning_rate': 0.0004112007199251936, 'epoch': 3.58}

 30%|██▉       | 8386/28080 [16:34:02<39:00:29,  7.13s/it]
 30%|██▉       | 8387/28080 [16:34:09<38:55:22,  7.12s/it]
                                                          
{'loss': 0.6158, 'learning_rate': 0.0004111786783115776, 'epoch': 3.58}

 30%|██▉       | 8387/28080 [16:34:09<38:55:22,  7.12s/it]
 30%|██▉       | 8388/28080 [16:34:16<38:53:28,  7.11s/it]
                                                          
{'loss': 0.6511, 'learning_rate': 0.00041115663455364556, 'epoch': 3.58}

 30%|██▉       | 8388/28080 [16:34:16<38:53:28,  7.11s/it]
 30%|██▉       | 8389/28080 [16:34:24<38:58:39,  7.13s/it]
                                                          
{'loss': 0.6401, 'learning_rate': 0.0004111345886516907, 'epoch': 3.58}

 30%|██▉       | 8389/28080 [16:34:24<38:58:39,  7.13s/it]
 30%|██▉       | 8390/28080 [16:34:31<39:01:45,  7.14s/it]
                                                          
{'loss': 0.6424, 'learning_rate': 0.00041111254060600646, 'epoch': 3.58}

 30%|██▉       | 8390/28080 [16:34:31<39:01:45,  7.14s/it]
 30%|██▉       | 8391/28080 [16:34:38<39:07:50,  7.15s/it]
                                                          
{'loss': 0.6193, 'learning_rate': 0.00041109049041688605, 'epoch': 3.58}

 30%|██▉       | 8391/28080 [16:34:38<39:07:50,  7.15s/it]
 30%|██▉       | 8392/28080 [16:34:45<39:02:05,  7.14s/it]
                                                          
{'loss': 0.6344, 'learning_rate': 0.0004110684380846229, 'epoch': 3.58}

 30%|██▉       | 8392/28080 [16:34:45<39:02:05,  7.14s/it]
 30%|██▉       | 8393/28080 [16:34:52<39:11:42,  7.17s/it]
                                                          
{'loss': 0.633, 'learning_rate': 0.0004110463836095103, 'epoch': 3.59}

 30%|██▉       | 8393/28080 [16:34:52<39:11:42,  7.17s/it]
 30%|██▉       | 8394/28080 [16:34:59<39:01:49,  7.14s/it]
                                                          
{'loss': 0.6295, 'learning_rate': 0.00041102432699184166, 'epoch': 3.59}

 30%|██▉       | 8394/28080 [16:34:59<39:01:49,  7.14s/it]
 30%|██▉       | 8395/28080 [16:35:07<39:04:49,  7.15s/it]
                                                          
{'loss': 0.6388, 'learning_rate': 0.0004110022682319106, 'epoch': 3.59}

 30%|██▉       | 8395/28080 [16:35:07<39:04:49,  7.15s/it]
 30%|██▉       | 8396/28080 [16:35:14<39:06:16,  7.15s/it]
                                                          
{'loss': 0.636, 'learning_rate': 0.0004109802073300104, 'epoch': 3.59}

 30%|██▉       | 8396/28080 [16:35:14<39:06:16,  7.15s/it]
 30%|██▉       | 8397/28080 [16:35:21<39:08:30,  7.16s/it]
                                                          
{'loss': 0.6335, 'learning_rate': 0.0004109581442864346, 'epoch': 3.59}

 30%|██▉       | 8397/28080 [16:35:21<39:08:30,  7.16s/it]
 30%|██▉       | 8398/28080 [16:35:28<38:56:10,  7.12s/it]
                                                          
{'loss': 0.6516, 'learning_rate': 0.00041093607910147665, 'epoch': 3.59}

 30%|██▉       | 8398/28080 [16:35:28<38:56:10,  7.12s/it]
 30%|██▉       | 8399/28080 [16:35:35<38:51:06,  7.11s/it]
                                                          
{'loss': 0.6384, 'learning_rate': 0.0004109140117754303, 'epoch': 3.59}

 30%|██▉       | 8399/28080 [16:35:35<38:51:06,  7.11s/it]
 30%|██▉       | 8400/28080 [16:35:42<38:59:51,  7.13s/it]
                                                          
{'loss': 0.6262, 'learning_rate': 0.00041089194230858905, 'epoch': 3.59}

 30%|██▉       | 8400/28080 [16:35:42<38:59:51,  7.13s/it]
 30%|██▉       | 8401/28080 [16:35:49<38:59:30,  7.13s/it]
                                                          
{'loss': 0.6089, 'learning_rate': 0.00041086987070124647, 'epoch': 3.59}

 30%|██▉       | 8401/28080 [16:35:49<38:59:30,  7.13s/it]
 30%|██▉       | 8402/28080 [16:35:57<39:14:04,  7.18s/it]
                                                          
{'loss': 0.6346, 'learning_rate': 0.00041084779695369617, 'epoch': 3.59}

 30%|██▉       | 8402/28080 [16:35:57<39:14:04,  7.18s/it]
 30%|██▉       | 8403/28080 [16:36:04<39:19:29,  7.19s/it]
                                                          
{'loss': 0.617, 'learning_rate': 0.000410825721066232, 'epoch': 3.59}

 30%|██▉       | 8403/28080 [16:36:04<39:19:29,  7.19s/it]
 30%|██▉       | 8404/28080 [16:36:11<39:06:30,  7.16s/it]
                                                          
{'loss': 0.6381, 'learning_rate': 0.0004108036430391474, 'epoch': 3.59}

 30%|██▉       | 8404/28080 [16:36:11<39:06:30,  7.16s/it]
 30%|██▉       | 8405/28080 [16:36:18<39:01:39,  7.14s/it]
                                                          
{'loss': 0.6594, 'learning_rate': 0.00041078156287273614, 'epoch': 3.59}

 30%|██▉       | 8405/28080 [16:36:18<39:01:39,  7.14s/it]
 30%|██▉       | 8406/28080 [16:36:25<38:56:01,  7.12s/it]
                                                          
{'loss': 0.6401, 'learning_rate': 0.00041075948056729225, 'epoch': 3.59}

 30%|██▉       | 8406/28080 [16:36:25<38:56:01,  7.12s/it]
 30%|██▉       | 8407/28080 [16:36:32<38:55:52,  7.12s/it]
                                                          
{'loss': 0.6189, 'learning_rate': 0.00041073739612310924, 'epoch': 3.59}

 30%|██▉       | 8407/28080 [16:36:32<38:55:52,  7.12s/it]
 30%|██▉       | 8408/28080 [16:36:39<38:54:51,  7.12s/it]
                                                          
{'loss': 0.6159, 'learning_rate': 0.00041071530954048095, 'epoch': 3.59}

 30%|██▉       | 8408/28080 [16:36:39<38:54:51,  7.12s/it]
 30%|██▉       | 8409/28080 [16:36:46<38:59:07,  7.13s/it]
                                                          
{'loss': 0.6312, 'learning_rate': 0.0004106932208197013, 'epoch': 3.59}

 30%|██▉       | 8409/28080 [16:36:46<38:59:07,  7.13s/it]
 30%|██▉       | 8410/28080 [16:36:54<39:01:25,  7.14s/it]
                                                          
{'loss': 0.6408, 'learning_rate': 0.00041067112996106414, 'epoch': 3.59}

 30%|██▉       | 8410/28080 [16:36:54<39:01:25,  7.14s/it]
 30%|██▉       | 8411/28080 [16:37:01<38:58:58,  7.13s/it]
                                                          
{'loss': 0.6405, 'learning_rate': 0.0004106490369648633, 'epoch': 3.59}

 30%|██▉       | 8411/28080 [16:37:01<38:58:58,  7.13s/it]
 30%|██▉       | 8412/28080 [16:37:08<38:53:19,  7.12s/it]
                                                          
{'loss': 0.6258, 'learning_rate': 0.0004106269418313928, 'epoch': 3.59}

 30%|██▉       | 8412/28080 [16:37:08<38:53:19,  7.12s/it]
 30%|██▉       | 8413/28080 [16:37:15<38:58:05,  7.13s/it]
                                                          
{'loss': 0.6086, 'learning_rate': 0.0004106048445609466, 'epoch': 3.59}

 30%|██▉       | 8413/28080 [16:37:15<38:58:05,  7.13s/it]
 30%|██▉       | 8414/28080 [16:37:22<38:49:28,  7.11s/it]
                                                          
{'loss': 0.6352, 'learning_rate': 0.0004105827451538185, 'epoch': 3.59}

 30%|██▉       | 8414/28080 [16:37:22<38:49:28,  7.11s/it]
 30%|██▉       | 8415/28080 [16:37:29<38:53:55,  7.12s/it]
                                                          
{'loss': 0.6508, 'learning_rate': 0.0004105606436103028, 'epoch': 3.59}

 30%|██▉       | 8415/28080 [16:37:29<38:53:55,  7.12s/it]
 30%|██▉       | 8416/28080 [16:37:36<38:48:52,  7.11s/it]
                                                          
{'loss': 0.6242, 'learning_rate': 0.00041053853993069326, 'epoch': 3.6}

 30%|██▉       | 8416/28080 [16:37:36<38:48:52,  7.11s/it]
 30%|██▉       | 8417/28080 [16:37:43<38:49:15,  7.11s/it]
                                                          
{'loss': 0.6222, 'learning_rate': 0.0004105164341152841, 'epoch': 3.6}

 30%|██▉       | 8417/28080 [16:37:43<38:49:15,  7.11s/it]
 30%|██▉       | 8418/28080 [16:37:51<38:58:37,  7.14s/it]
                                                          
{'loss': 0.6302, 'learning_rate': 0.00041049432616436946, 'epoch': 3.6}

 30%|██▉       | 8418/28080 [16:37:51<38:58:37,  7.14s/it]
 30%|██▉       | 8419/28080 [16:37:58<38:56:59,  7.13s/it]
                                                          
{'loss': 0.6431, 'learning_rate': 0.00041047221607824324, 'epoch': 3.6}

 30%|██▉       | 8419/28080 [16:37:58<38:56:59,  7.13s/it]
 30%|██▉       | 8420/28080 [16:38:05<38:49:50,  7.11s/it]
                                                          
{'loss': 0.6127, 'learning_rate': 0.00041045010385719983, 'epoch': 3.6}

 30%|██▉       | 8420/28080 [16:38:05<38:49:50,  7.11s/it]
 30%|██▉       | 8421/28080 [16:38:12<38:45:07,  7.10s/it]
                                                          
{'loss': 0.6252, 'learning_rate': 0.0004104279895015333, 'epoch': 3.6}

 30%|██▉       | 8421/28080 [16:38:12<38:45:07,  7.10s/it]
 30%|██▉       | 8422/28080 [16:38:19<38:49:04,  7.11s/it]
                                                          
{'loss': 0.6181, 'learning_rate': 0.00041040587301153787, 'epoch': 3.6}

 30%|██▉       | 8422/28080 [16:38:19<38:49:04,  7.11s/it]
 30%|██▉       | 8423/28080 [16:38:26<38:48:42,  7.11s/it]
                                                          
{'loss': 0.6135, 'learning_rate': 0.00041038375438750776, 'epoch': 3.6}

 30%|██▉       | 8423/28080 [16:38:26<38:48:42,  7.11s/it]
 30%|███       | 8424/28080 [16:38:33<38:53:51,  7.12s/it]
                                                          
{'loss': 0.6152, 'learning_rate': 0.0004103616336297372, 'epoch': 3.6}

 30%|███       | 8424/28080 [16:38:33<38:53:51,  7.12s/it]
 30%|███       | 8425/28080 [16:38:40<39:05:20,  7.16s/it]
                                                          
{'loss': 0.6317, 'learning_rate': 0.0004103395107385206, 'epoch': 3.6}

 30%|███       | 8425/28080 [16:38:40<39:05:20,  7.16s/it]
 30%|███       | 8426/28080 [16:38:48<39:13:01,  7.18s/it]
                                                          
{'loss': 0.6197, 'learning_rate': 0.00041031738571415224, 'epoch': 3.6}

 30%|███       | 8426/28080 [16:38:48<39:13:01,  7.18s/it]
 30%|███       | 8427/28080 [16:38:55<38:57:27,  7.14s/it]
                                                          
{'loss': 0.6395, 'learning_rate': 0.0004102952585569265, 'epoch': 3.6}

 30%|███       | 8427/28080 [16:38:55<38:57:27,  7.14s/it]
 30%|███       | 8428/28080 [16:39:02<39:00:12,  7.14s/it]
                                                          
{'loss': 0.609, 'learning_rate': 0.00041027312926713764, 'epoch': 3.6}

 30%|███       | 8428/28080 [16:39:02<39:00:12,  7.14s/it]
 30%|███       | 8429/28080 [16:39:09<39:06:35,  7.16s/it]
                                                          
{'loss': 0.623, 'learning_rate': 0.00041025099784508013, 'epoch': 3.6}

 30%|███       | 8429/28080 [16:39:09<39:06:35,  7.16s/it]
 30%|███       | 8430/28080 [16:39:16<39:06:49,  7.17s/it]
                                                          
{'loss': 0.6368, 'learning_rate': 0.00041022886429104846, 'epoch': 3.6}

 30%|███       | 8430/28080 [16:39:16<39:06:49,  7.17s/it]
 30%|███       | 8431/28080 [16:39:24<39:13:59,  7.19s/it]
                                                          
{'loss': 0.6459, 'learning_rate': 0.000410206728605337, 'epoch': 3.6}

 30%|███       | 8431/28080 [16:39:24<39:13:59,  7.19s/it]
 30%|███       | 8432/28080 [16:39:31<39:06:38,  7.17s/it]
                                                          
{'loss': 0.6269, 'learning_rate': 0.00041018459078824034, 'epoch': 3.6}

 30%|███       | 8432/28080 [16:39:31<39:06:38,  7.17s/it]
 30%|███       | 8433/28080 [16:39:38<38:59:35,  7.14s/it]
                                                          
{'loss': 0.6541, 'learning_rate': 0.0004101624508400529, 'epoch': 3.6}

 30%|███       | 8433/28080 [16:39:38<38:59:35,  7.14s/it]
 30%|███       | 8434/28080 [16:39:45<38:58:52,  7.14s/it]
                                                          
{'loss': 0.6285, 'learning_rate': 0.0004101403087610693, 'epoch': 3.6}

 30%|███       | 8434/28080 [16:39:45<38:58:52,  7.14s/it]
 30%|███       | 8435/28080 [16:39:52<38:59:13,  7.14s/it]
                                                          
{'loss': 0.6301, 'learning_rate': 0.0004101181645515841, 'epoch': 3.6}

 30%|███       | 8435/28080 [16:39:52<38:59:13,  7.14s/it]
 30%|███       | 8436/28080 [16:39:59<38:53:04,  7.13s/it]
                                                          
{'loss': 0.6569, 'learning_rate': 0.000410096018211892, 'epoch': 3.6}

 30%|███       | 8436/28080 [16:39:59<38:53:04,  7.13s/it]
 30%|███       | 8437/28080 [16:40:06<38:48:25,  7.11s/it]
                                                          
{'loss': 0.6177, 'learning_rate': 0.0004100738697422874, 'epoch': 3.6}

 30%|███       | 8437/28080 [16:40:06<38:48:25,  7.11s/it]
 30%|███       | 8438/28080 [16:40:13<38:45:15,  7.10s/it]
                                                          
{'loss': 0.6542, 'learning_rate': 0.0004100517191430652, 'epoch': 3.6}

 30%|███       | 8438/28080 [16:40:13<38:45:15,  7.10s/it]
 30%|███       | 8439/28080 [16:40:20<38:50:35,  7.12s/it]
                                                          
{'loss': 0.6235, 'learning_rate': 0.00041002956641451996, 'epoch': 3.61}

 30%|███       | 8439/28080 [16:40:20<38:50:35,  7.12s/it]
 30%|███       | 8440/28080 [16:40:28<39:07:13,  7.17s/it]
                                                          
{'loss': 0.6419, 'learning_rate': 0.00041000741155694645, 'epoch': 3.61}

 30%|███       | 8440/28080 [16:40:28<39:07:13,  7.17s/it]
 30%|███       | 8441/28080 [16:40:35<38:55:40,  7.14s/it]
                                                          
{'loss': 0.637, 'learning_rate': 0.00040998525457063933, 'epoch': 3.61}

 30%|███       | 8441/28080 [16:40:35<38:55:40,  7.14s/it]
 30%|███       | 8442/28080 [16:40:42<38:56:58,  7.14s/it]
                                                          
{'loss': 0.6188, 'learning_rate': 0.0004099630954558935, 'epoch': 3.61}

 30%|███       | 8442/28080 [16:40:42<38:56:58,  7.14s/it]
 30%|███       | 8443/28080 [16:40:49<38:48:34,  7.11s/it]
                                                          
{'loss': 0.6178, 'learning_rate': 0.0004099409342130037, 'epoch': 3.61}

 30%|███       | 8443/28080 [16:40:49<38:48:34,  7.11s/it]
 30%|███       | 8444/28080 [16:40:56<38:46:39,  7.11s/it]
                                                          
{'loss': 0.6306, 'learning_rate': 0.0004099187708422648, 'epoch': 3.61}

 30%|███       | 8444/28080 [16:40:56<38:46:39,  7.11s/it]
 30%|███       | 8445/28080 [16:41:03<38:55:31,  7.14s/it]
                                                          
{'loss': 0.6356, 'learning_rate': 0.0004098966053439716, 'epoch': 3.61}

 30%|███       | 8445/28080 [16:41:03<38:55:31,  7.14s/it]
 30%|███       | 8446/28080 [16:41:10<38:51:11,  7.12s/it]
                                                          
{'loss': 0.6234, 'learning_rate': 0.00040987443771841903, 'epoch': 3.61}

 30%|███       | 8446/28080 [16:41:10<38:51:11,  7.12s/it]
 30%|███       | 8447/28080 [16:41:18<38:58:15,  7.15s/it]
                                                          
{'loss': 0.6342, 'learning_rate': 0.000409852267965902, 'epoch': 3.61}

 30%|███       | 8447/28080 [16:41:18<38:58:15,  7.15s/it]
 30%|███       | 8448/28080 [16:41:25<38:48:59,  7.12s/it]
                                                          
{'loss': 0.6311, 'learning_rate': 0.0004098300960867155, 'epoch': 3.61}

 30%|███       | 8448/28080 [16:41:25<38:48:59,  7.12s/it]
 30%|███       | 8449/28080 [16:41:32<38:46:26,  7.11s/it]
                                                          
{'loss': 0.6311, 'learning_rate': 0.00040980792208115437, 'epoch': 3.61}

 30%|███       | 8449/28080 [16:41:32<38:46:26,  7.11s/it]
 30%|███       | 8450/28080 [16:41:39<38:32:32,  7.07s/it]
                                                          
{'loss': 0.6472, 'learning_rate': 0.0004097857459495137, 'epoch': 3.61}

 30%|███       | 8450/28080 [16:41:39<38:32:32,  7.07s/it]
 30%|███       | 8451/28080 [16:41:46<38:47:35,  7.11s/it]
                                                          
{'loss': 0.6273, 'learning_rate': 0.0004097635676920886, 'epoch': 3.61}

 30%|███       | 8451/28080 [16:41:46<38:47:35,  7.11s/it]
 30%|███       | 8452/28080 [16:41:53<38:56:50,  7.14s/it]
                                                          
{'loss': 0.6221, 'learning_rate': 0.000409741387309174, 'epoch': 3.61}

 30%|███       | 8452/28080 [16:41:53<38:56:50,  7.14s/it]
 30%|███       | 8453/28080 [16:42:00<39:03:55,  7.17s/it]
                                                          
{'loss': 0.6363, 'learning_rate': 0.00040971920480106506, 'epoch': 3.61}

 30%|███       | 8453/28080 [16:42:00<39:03:55,  7.17s/it]
 30%|███       | 8454/28080 [16:42:07<38:53:48,  7.13s/it]
                                                          
{'loss': 0.614, 'learning_rate': 0.0004096970201680569, 'epoch': 3.61}

 30%|███       | 8454/28080 [16:42:07<38:53:48,  7.13s/it]
 30%|███       | 8455/28080 [16:42:15<38:58:48,  7.15s/it]
                                                          
{'loss': 0.628, 'learning_rate': 0.00040967483341044467, 'epoch': 3.61}

 30%|███       | 8455/28080 [16:42:15<38:58:48,  7.15s/it]
 30%|███       | 8456/28080 [16:42:22<38:50:29,  7.13s/it]
                                                          
{'loss': 0.6263, 'learning_rate': 0.00040965264452852337, 'epoch': 3.61}

 30%|███       | 8456/28080 [16:42:22<38:50:29,  7.13s/it]
 30%|███       | 8457/28080 [16:42:29<38:52:08,  7.13s/it]
                                                          
{'loss': 0.6303, 'learning_rate': 0.00040963045352258843, 'epoch': 3.61}

 30%|███       | 8457/28080 [16:42:29<38:52:08,  7.13s/it]
 30%|███       | 8458/28080 [16:42:36<38:57:57,  7.15s/it]
                                                          
{'loss': 0.6317, 'learning_rate': 0.00040960826039293497, 'epoch': 3.61}

 30%|███       | 8458/28080 [16:42:36<38:57:57,  7.15s/it]
 30%|███       | 8459/28080 [16:42:43<38:53:02,  7.13s/it]
                                                          
{'loss': 0.6356, 'learning_rate': 0.0004095860651398582, 'epoch': 3.61}

 30%|███       | 8459/28080 [16:42:43<38:53:02,  7.13s/it]
 30%|███       | 8460/28080 [16:42:50<38:47:40,  7.12s/it]
                                                          
{'loss': 0.6177, 'learning_rate': 0.0004095638677636536, 'epoch': 3.61}

 30%|███       | 8460/28080 [16:42:50<38:47:40,  7.12s/it]
 30%|███       | 8461/28080 [16:42:58<39:10:02,  7.19s/it]
                                                          
{'loss': 0.6273, 'learning_rate': 0.00040954166826461625, 'epoch': 3.61}

 30%|███       | 8461/28080 [16:42:58<39:10:02,  7.19s/it]
 30%|███       | 8462/28080 [16:43:05<39:06:32,  7.18s/it]
                                                          
{'loss': 0.6425, 'learning_rate': 0.00040951946664304165, 'epoch': 3.61}

 30%|███       | 8462/28080 [16:43:05<39:06:32,  7.18s/it]
 30%|███       | 8463/28080 [16:43:12<38:56:10,  7.15s/it]
                                                          
{'loss': 0.6363, 'learning_rate': 0.00040949726289922505, 'epoch': 3.62}

 30%|███       | 8463/28080 [16:43:12<38:56:10,  7.15s/it]
 30%|███       | 8464/28080 [16:43:19<38:57:36,  7.15s/it]
                                                          
{'loss': 0.614, 'learning_rate': 0.000409475057033462, 'epoch': 3.62}

 30%|███       | 8464/28080 [16:43:19<38:57:36,  7.15s/it]
 30%|███       | 8465/28080 [16:43:26<38:51:22,  7.13s/it]
                                                          
{'loss': 0.6409, 'learning_rate': 0.0004094528490460478, 'epoch': 3.62}

 30%|███       | 8465/28080 [16:43:26<38:51:22,  7.13s/it]
 30%|███       | 8466/28080 [16:43:33<38:47:55,  7.12s/it]
                                                          
{'loss': 0.6273, 'learning_rate': 0.00040943063893727794, 'epoch': 3.62}

 30%|███       | 8466/28080 [16:43:33<38:47:55,  7.12s/it]
 30%|███       | 8467/28080 [16:43:40<38:44:14,  7.11s/it]
                                                          
{'loss': 0.6333, 'learning_rate': 0.00040940842670744785, 'epoch': 3.62}

 30%|███       | 8467/28080 [16:43:40<38:44:14,  7.11s/it]
 30%|███       | 8468/28080 [16:43:47<38:46:13,  7.12s/it]
                                                          
{'loss': 0.6573, 'learning_rate': 0.00040938621235685316, 'epoch': 3.62}

 30%|███       | 8468/28080 [16:43:47<38:46:13,  7.12s/it]
 30%|███       | 8469/28080 [16:43:55<39:00:38,  7.16s/it]
                                                          
{'loss': 0.6156, 'learning_rate': 0.0004093639958857893, 'epoch': 3.62}

 30%|███       | 8469/28080 [16:43:55<39:00:38,  7.16s/it]
 30%|███       | 8470/28080 [16:44:02<39:02:18,  7.17s/it]
                                                          
{'loss': 0.6348, 'learning_rate': 0.000409341777294552, 'epoch': 3.62}

 30%|███       | 8470/28080 [16:44:02<39:02:18,  7.17s/it]
 30%|███       | 8471/28080 [16:44:09<39:07:33,  7.18s/it]
                                                          
{'loss': 0.6394, 'learning_rate': 0.0004093195565834366, 'epoch': 3.62}

 30%|███       | 8471/28080 [16:44:09<39:07:33,  7.18s/it]
 30%|███       | 8472/28080 [16:44:16<38:59:59,  7.16s/it]
                                                          
{'loss': 0.6442, 'learning_rate': 0.0004092973337527389, 'epoch': 3.62}

 30%|███       | 8472/28080 [16:44:16<38:59:59,  7.16s/it]
 30%|███       | 8473/28080 [16:44:23<38:55:52,  7.15s/it]
                                                          
{'loss': 0.6501, 'learning_rate': 0.0004092751088027545, 'epoch': 3.62}

 30%|███       | 8473/28080 [16:44:23<38:55:52,  7.15s/it]
 30%|███       | 8474/28080 [16:44:30<38:48:59,  7.13s/it]
                                                          
{'loss': 0.651, 'learning_rate': 0.0004092528817337792, 'epoch': 3.62}

 30%|███       | 8474/28080 [16:44:30<38:48:59,  7.13s/it]
 30%|███       | 8475/28080 [16:44:37<38:56:32,  7.15s/it]
                                                          
{'loss': 0.6196, 'learning_rate': 0.00040923065254610847, 'epoch': 3.62}

 30%|███       | 8475/28080 [16:44:37<38:56:32,  7.15s/it]
 30%|███       | 8476/28080 [16:44:45<38:54:24,  7.14s/it]
                                                          
{'loss': 0.6178, 'learning_rate': 0.00040920842124003823, 'epoch': 3.62}

 30%|███       | 8476/28080 [16:44:45<38:54:24,  7.14s/it]
 30%|███       | 8477/28080 [16:44:52<38:57:54,  7.16s/it]
                                                          
{'loss': 0.6132, 'learning_rate': 0.0004091861878158641, 'epoch': 3.62}

 30%|███       | 8477/28080 [16:44:52<38:57:54,  7.16s/it]
 30%|███       | 8478/28080 [16:44:59<38:54:32,  7.15s/it]
                                                          
{'loss': 0.6173, 'learning_rate': 0.00040916395227388213, 'epoch': 3.62}

 30%|███       | 8478/28080 [16:44:59<38:54:32,  7.15s/it]
 30%|███       | 8479/28080 [16:45:06<38:53:24,  7.14s/it]
                                                          
{'loss': 0.6263, 'learning_rate': 0.00040914171461438787, 'epoch': 3.62}

 30%|███       | 8479/28080 [16:45:06<38:53:24,  7.14s/it]
 30%|███       | 8480/28080 [16:45:13<38:55:16,  7.15s/it]
                                                          
{'loss': 0.6379, 'learning_rate': 0.0004091194748376773, 'epoch': 3.62}

 30%|███       | 8480/28080 [16:45:13<38:55:16,  7.15s/it]
 30%|███       | 8481/28080 [16:45:20<38:55:57,  7.15s/it]
                                                          
{'loss': 0.6205, 'learning_rate': 0.0004090972329440462, 'epoch': 3.62}

 30%|███       | 8481/28080 [16:45:20<38:55:57,  7.15s/it]
 30%|███       | 8482/28080 [16:45:28<39:01:44,  7.17s/it]
                                                          
{'loss': 0.6257, 'learning_rate': 0.0004090749889337907, 'epoch': 3.62}

 30%|███       | 8482/28080 [16:45:28<39:01:44,  7.17s/it]
 30%|███       | 8483/28080 [16:45:35<38:49:37,  7.13s/it]
                                                          
{'loss': 0.6354, 'learning_rate': 0.00040905274280720645, 'epoch': 3.62}

 30%|███       | 8483/28080 [16:45:35<38:49:37,  7.13s/it]
 30%|███       | 8484/28080 [16:45:42<38:44:58,  7.12s/it]
                                                          
{'loss': 0.6468, 'learning_rate': 0.00040903049456458965, 'epoch': 3.62}

 30%|███       | 8484/28080 [16:45:42<38:44:58,  7.12s/it]
 30%|███       | 8485/28080 [16:45:49<38:51:29,  7.14s/it]
                                                          
{'loss': 0.6146, 'learning_rate': 0.00040900824420623606, 'epoch': 3.62}

 30%|███       | 8485/28080 [16:45:49<38:51:29,  7.14s/it]
 30%|███       | 8486/28080 [16:45:56<38:31:14,  7.08s/it]
                                                          
{'loss': 0.6441, 'learning_rate': 0.0004089859917324419, 'epoch': 3.63}

 30%|███       | 8486/28080 [16:45:56<38:31:14,  7.08s/it]
 30%|███       | 8487/28080 [16:46:03<38:38:37,  7.10s/it]
                                                          
{'loss': 0.6282, 'learning_rate': 0.0004089637371435031, 'epoch': 3.63}

 30%|███       | 8487/28080 [16:46:03<38:38:37,  7.10s/it]
 30%|███       | 8488/28080 [16:46:10<38:47:10,  7.13s/it]
                                                          
{'loss': 0.5954, 'learning_rate': 0.0004089414804397158, 'epoch': 3.63}

 30%|███       | 8488/28080 [16:46:10<38:47:10,  7.13s/it]
 30%|███       | 8489/28080 [16:46:17<38:48:24,  7.13s/it]
                                                          
{'loss': 0.6269, 'learning_rate': 0.0004089192216213761, 'epoch': 3.63}

 30%|███       | 8489/28080 [16:46:17<38:48:24,  7.13s/it]
 30%|███       | 8490/28080 [16:46:24<38:48:55,  7.13s/it]
                                                          
{'loss': 0.6279, 'learning_rate': 0.00040889696068878, 'epoch': 3.63}

 30%|███       | 8490/28080 [16:46:24<38:48:55,  7.13s/it]
 30%|███       | 8491/28080 [16:46:31<38:35:05,  7.09s/it]
                                                          
{'loss': 0.6269, 'learning_rate': 0.00040887469764222387, 'epoch': 3.63}

 30%|███       | 8491/28080 [16:46:31<38:35:05,  7.09s/it]
 30%|███       | 8492/28080 [16:46:38<38:26:40,  7.07s/it]
                                                          
{'loss': 0.6156, 'learning_rate': 0.00040885243248200374, 'epoch': 3.63}

 30%|███       | 8492/28080 [16:46:38<38:26:40,  7.07s/it]
 30%|███       | 8493/28080 [16:46:46<38:37:06,  7.10s/it]
                                                          
{'loss': 0.628, 'learning_rate': 0.00040883016520841585, 'epoch': 3.63}

 30%|███       | 8493/28080 [16:46:46<38:37:06,  7.10s/it]
 30%|███       | 8494/28080 [16:46:53<38:44:29,  7.12s/it]
                                                          
{'loss': 0.6577, 'learning_rate': 0.0004088078958217565, 'epoch': 3.63}

 30%|███       | 8494/28080 [16:46:53<38:44:29,  7.12s/it]
 30%|███       | 8495/28080 [16:47:00<38:41:57,  7.11s/it]
                                                          
{'loss': 0.6397, 'learning_rate': 0.000408785624322322, 'epoch': 3.63}

 30%|███       | 8495/28080 [16:47:00<38:41:57,  7.11s/it]
 30%|███       | 8496/28080 [16:47:07<38:50:30,  7.14s/it]
                                                          
{'loss': 0.6402, 'learning_rate': 0.0004087633507104085, 'epoch': 3.63}

 30%|███       | 8496/28080 [16:47:07<38:50:30,  7.14s/it]
 30%|███       | 8497/28080 [16:47:14<38:45:27,  7.12s/it]
                                                          
{'loss': 0.6334, 'learning_rate': 0.0004087410749863124, 'epoch': 3.63}

 30%|███       | 8497/28080 [16:47:14<38:45:27,  7.12s/it]
 30%|███       | 8498/28080 [16:47:21<38:43:58,  7.12s/it]
                                                          
{'loss': 0.6503, 'learning_rate': 0.00040871879715033004, 'epoch': 3.63}

 30%|███       | 8498/28080 [16:47:21<38:43:58,  7.12s/it]
 30%|███       | 8499/28080 [16:47:28<38:44:49,  7.12s/it]
                                                          
{'loss': 0.6409, 'learning_rate': 0.0004086965172027579, 'epoch': 3.63}

 30%|███       | 8499/28080 [16:47:28<38:44:49,  7.12s/it]
 30%|███       | 8500/28080 [16:47:35<38:38:52,  7.11s/it]
                                                          
{'loss': 0.6409, 'learning_rate': 0.00040867423514389224, 'epoch': 3.63}

 30%|███       | 8500/28080 [16:47:35<38:38:52,  7.11s/it]
 30%|███       | 8501/28080 [16:47:43<38:46:36,  7.13s/it]
                                                          
{'loss': 0.6127, 'learning_rate': 0.0004086519509740296, 'epoch': 3.63}

 30%|███       | 8501/28080 [16:47:43<38:46:36,  7.13s/it]
 30%|███       | 8502/28080 [16:47:50<38:54:34,  7.15s/it]
                                                          
{'loss': 0.6142, 'learning_rate': 0.0004086296646934665, 'epoch': 3.63}

 30%|███       | 8502/28080 [16:47:50<38:54:34,  7.15s/it]
 30%|███       | 8503/28080 [16:47:57<38:54:57,  7.16s/it]
                                                          
{'loss': 0.6299, 'learning_rate': 0.00040860737630249927, 'epoch': 3.63}

 30%|███       | 8503/28080 [16:47:57<38:54:57,  7.16s/it]
 30%|███       | 8504/28080 [16:48:04<38:57:23,  7.16s/it]
                                                          
{'loss': 0.6317, 'learning_rate': 0.0004085850858014245, 'epoch': 3.63}

 30%|███       | 8504/28080 [16:48:04<38:57:23,  7.16s/it]
 30%|███       | 8505/28080 [16:48:11<38:45:17,  7.13s/it]
                                                          
{'loss': 0.6396, 'learning_rate': 0.00040856279319053887, 'epoch': 3.63}

 30%|███       | 8505/28080 [16:48:11<38:45:17,  7.13s/it]
 30%|███       | 8506/28080 [16:48:18<38:48:10,  7.14s/it]
                                                          
{'loss': 0.6211, 'learning_rate': 0.0004085404984701388, 'epoch': 3.63}

 30%|███       | 8506/28080 [16:48:18<38:48:10,  7.14s/it]
 30%|███       | 8507/28080 [16:48:26<38:46:40,  7.13s/it]
                                                          
{'loss': 0.6205, 'learning_rate': 0.0004085182016405209, 'epoch': 3.63}

 30%|███       | 8507/28080 [16:48:26<38:46:40,  7.13s/it]
 30%|███       | 8508/28080 [16:48:33<38:43:28,  7.12s/it]
                                                          
{'loss': 0.6184, 'learning_rate': 0.000408495902701982, 'epoch': 3.63}

 30%|███       | 8508/28080 [16:48:33<38:43:28,  7.12s/it]
 30%|███       | 8509/28080 [16:48:40<38:54:04,  7.16s/it]
                                                          
{'loss': 0.6383, 'learning_rate': 0.0004084736016548185, 'epoch': 3.63}

 30%|███       | 8509/28080 [16:48:40<38:54:04,  7.16s/it]
 30%|███       | 8510/28080 [16:48:47<38:59:21,  7.17s/it]
                                                          
{'loss': 0.6455, 'learning_rate': 0.00040845129849932725, 'epoch': 3.64}

 30%|███       | 8510/28080 [16:48:47<38:59:21,  7.17s/it]
 30%|███       | 8511/28080 [16:48:54<39:01:52,  7.18s/it]
                                                          
{'loss': 0.6347, 'learning_rate': 0.000408428993235805, 'epoch': 3.64}

 30%|███       | 8511/28080 [16:48:54<39:01:52,  7.18s/it]
 30%|███       | 8512/28080 [16:49:01<38:56:44,  7.16s/it]
                                                          
{'loss': 0.6271, 'learning_rate': 0.00040840668586454836, 'epoch': 3.64}

 30%|███       | 8512/28080 [16:49:01<38:56:44,  7.16s/it]
 30%|███       | 8513/28080 [16:49:09<38:54:13,  7.16s/it]
                                                          
{'loss': 0.6396, 'learning_rate': 0.00040838437638585426, 'epoch': 3.64}

 30%|███       | 8513/28080 [16:49:09<38:54:13,  7.16s/it]
 30%|███       | 8514/28080 [16:49:16<39:03:23,  7.19s/it]
                                                          
{'loss': 0.6451, 'learning_rate': 0.00040836206480001936, 'epoch': 3.64}

 30%|███       | 8514/28080 [16:49:16<39:03:23,  7.19s/it]
 30%|███       | 8515/28080 [16:49:23<38:52:08,  7.15s/it]
                                                          
{'loss': 0.6346, 'learning_rate': 0.00040833975110734057, 'epoch': 3.64}

 30%|███       | 8515/28080 [16:49:23<38:52:08,  7.15s/it]
 30%|███       | 8516/28080 [16:49:30<38:56:36,  7.17s/it]
                                                          
{'loss': 0.6437, 'learning_rate': 0.00040831743530811475, 'epoch': 3.64}

 30%|███       | 8516/28080 [16:49:30<38:56:36,  7.17s/it]
 30%|███       | 8517/28080 [16:49:37<38:56:03,  7.16s/it]
                                                          
{'loss': 0.6356, 'learning_rate': 0.0004082951174026388, 'epoch': 3.64}

 30%|███       | 8517/28080 [16:49:37<38:56:03,  7.16s/it]
 30%|███       | 8518/28080 [16:49:44<38:51:55,  7.15s/it]
                                                          
{'loss': 0.6486, 'learning_rate': 0.0004082727973912096, 'epoch': 3.64}

 30%|███       | 8518/28080 [16:49:44<38:51:55,  7.15s/it]
 30%|███       | 8519/28080 [16:49:52<38:50:33,  7.15s/it]
                                                          
{'loss': 0.6406, 'learning_rate': 0.0004082504752741241, 'epoch': 3.64}

 30%|███       | 8519/28080 [16:49:52<38:50:33,  7.15s/it]
 30%|███       | 8520/28080 [16:49:59<38:54:17,  7.16s/it]
                                                          
{'loss': 0.6278, 'learning_rate': 0.0004082281510516793, 'epoch': 3.64}

 30%|███       | 8520/28080 [16:49:59<38:54:17,  7.16s/it]
 30%|███       | 8521/28080 [16:50:06<38:42:38,  7.13s/it]
                                                          
{'loss': 0.6374, 'learning_rate': 0.00040820582472417223, 'epoch': 3.64}

 30%|███       | 8521/28080 [16:50:06<38:42:38,  7.13s/it]
 30%|███       | 8522/28080 [16:50:13<38:42:21,  7.12s/it]
                                                          
{'loss': 0.6187, 'learning_rate': 0.00040818349629189983, 'epoch': 3.64}

 30%|███       | 8522/28080 [16:50:13<38:42:21,  7.12s/it]
 30%|███       | 8523/28080 [16:50:20<38:44:13,  7.13s/it]
                                                          
{'loss': 0.6531, 'learning_rate': 0.00040816116575515915, 'epoch': 3.64}

 30%|███       | 8523/28080 [16:50:20<38:44:13,  7.13s/it]
 30%|███       | 8524/28080 [16:50:27<38:41:25,  7.12s/it]
                                                          
{'loss': 0.6341, 'learning_rate': 0.00040813883311424746, 'epoch': 3.64}

 30%|███       | 8524/28080 [16:50:27<38:41:25,  7.12s/it]
 30%|███       | 8525/28080 [16:50:34<38:31:34,  7.09s/it]
                                                          
{'loss': 0.6288, 'learning_rate': 0.0004081164983694616, 'epoch': 3.64}

 30%|███       | 8525/28080 [16:50:34<38:31:34,  7.09s/it]
 30%|███       | 8526/28080 [16:50:41<38:34:38,  7.10s/it]
                                                          
{'loss': 0.6155, 'learning_rate': 0.0004080941615210989, 'epoch': 3.64}

 30%|███       | 8526/28080 [16:50:41<38:34:38,  7.10s/it]
 30%|███       | 8527/28080 [16:50:48<38:29:20,  7.09s/it]
                                                          
{'loss': 0.6271, 'learning_rate': 0.00040807182256945654, 'epoch': 3.64}

 30%|███       | 8527/28080 [16:50:48<38:29:20,  7.09s/it]
 30%|███       | 8528/28080 [16:50:56<38:40:11,  7.12s/it]
                                                          
{'loss': 0.6241, 'learning_rate': 0.00040804948151483154, 'epoch': 3.64}

 30%|███       | 8528/28080 [16:50:56<38:40:11,  7.12s/it]
 30%|███       | 8529/28080 [16:51:03<38:51:26,  7.15s/it]
                                                          
{'loss': 0.6342, 'learning_rate': 0.00040802713835752123, 'epoch': 3.64}

 30%|███       | 8529/28080 [16:51:03<38:51:26,  7.15s/it]
 30%|███       | 8530/28080 [16:51:10<38:48:41,  7.15s/it]
                                                          
{'loss': 0.6284, 'learning_rate': 0.000408004793097823, 'epoch': 3.64}

 30%|███       | 8530/28080 [16:51:10<38:48:41,  7.15s/it]
 30%|███       | 8531/28080 [16:51:17<38:35:40,  7.11s/it]
                                                          
{'loss': 0.6483, 'learning_rate': 0.00040798244573603395, 'epoch': 3.64}

 30%|███       | 8531/28080 [16:51:17<38:35:40,  7.11s/it]
 30%|███       | 8532/28080 [16:51:24<38:44:52,  7.14s/it]
                                                          
{'loss': 0.6236, 'learning_rate': 0.00040796009627245145, 'epoch': 3.64}

 30%|███       | 8532/28080 [16:51:24<38:44:52,  7.14s/it]
 30%|███       | 8533/28080 [16:51:31<38:47:13,  7.14s/it]
                                                          
{'loss': 0.6412, 'learning_rate': 0.0004079377447073728, 'epoch': 3.65}

 30%|███       | 8533/28080 [16:51:31<38:47:13,  7.14s/it]
 30%|███       | 8534/28080 [16:51:38<38:44:42,  7.14s/it]
                                                          
{'loss': 0.6309, 'learning_rate': 0.00040791539104109535, 'epoch': 3.65}

 30%|███       | 8534/28080 [16:51:38<38:44:42,  7.14s/it]
 30%|███       | 8535/28080 [16:51:45<38:39:06,  7.12s/it]
                                                          
{'loss': 0.6472, 'learning_rate': 0.0004078930352739166, 'epoch': 3.65}

 30%|███       | 8535/28080 [16:51:45<38:39:06,  7.12s/it]
 30%|███       | 8536/28080 [16:51:53<38:39:35,  7.12s/it]
                                                          
{'loss': 0.6251, 'learning_rate': 0.00040787067740613385, 'epoch': 3.65}

 30%|███       | 8536/28080 [16:51:53<38:39:35,  7.12s/it]
 30%|███       | 8537/28080 [16:52:00<38:45:12,  7.14s/it]
                                                          
{'loss': 0.6342, 'learning_rate': 0.0004078483174380447, 'epoch': 3.65}

 30%|███       | 8537/28080 [16:52:00<38:45:12,  7.14s/it]
 30%|███       | 8538/28080 [16:52:07<38:42:14,  7.13s/it]
                                                          
{'loss': 0.6286, 'learning_rate': 0.0004078259553699464, 'epoch': 3.65}

 30%|███       | 8538/28080 [16:52:07<38:42:14,  7.13s/it]
 30%|███       | 8539/28080 [16:52:14<38:34:16,  7.11s/it]
                                                          
{'loss': 0.6398, 'learning_rate': 0.0004078035912021367, 'epoch': 3.65}

 30%|███       | 8539/28080 [16:52:14<38:34:16,  7.11s/it]
 30%|███       | 8540/28080 [16:52:21<38:36:47,  7.11s/it]
                                                          
{'loss': 0.6382, 'learning_rate': 0.000407781224934913, 'epoch': 3.65}

 30%|███       | 8540/28080 [16:52:21<38:36:47,  7.11s/it]
 30%|███       | 8541/28080 [16:52:28<38:30:26,  7.09s/it]
                                                          
{'loss': 0.6379, 'learning_rate': 0.00040775885656857283, 'epoch': 3.65}

 30%|███       | 8541/28080 [16:52:28<38:30:26,  7.09s/it]
 30%|███       | 8542/28080 [16:52:35<38:28:37,  7.09s/it]
                                                          
{'loss': 0.6267, 'learning_rate': 0.0004077364861034138, 'epoch': 3.65}

 30%|███       | 8542/28080 [16:52:35<38:28:37,  7.09s/it]
 30%|███       | 8543/28080 [16:52:42<38:33:05,  7.10s/it]
                                                          
{'loss': 0.6433, 'learning_rate': 0.0004077141135397336, 'epoch': 3.65}

 30%|███       | 8543/28080 [16:52:42<38:33:05,  7.10s/it]
 30%|███       | 8544/28080 [16:52:50<38:43:51,  7.14s/it]
                                                          
{'loss': 0.626, 'learning_rate': 0.00040769173887782986, 'epoch': 3.65}

 30%|███       | 8544/28080 [16:52:50<38:43:51,  7.14s/it]
 30%|███       | 8545/28080 [16:52:57<38:52:37,  7.16s/it]
                                                          
{'loss': 0.6197, 'learning_rate': 0.0004076693621180002, 'epoch': 3.65}

 30%|███       | 8545/28080 [16:52:57<38:52:37,  7.16s/it]
 30%|███       | 8546/28080 [16:53:04<38:49:50,  7.16s/it]
                                                          
{'loss': 0.6312, 'learning_rate': 0.0004076469832605423, 'epoch': 3.65}

 30%|███       | 8546/28080 [16:53:04<38:49:50,  7.16s/it]
 30%|███       | 8547/28080 [16:53:11<38:49:28,  7.16s/it]
                                                          
{'loss': 0.622, 'learning_rate': 0.00040762460230575387, 'epoch': 3.65}

 30%|███       | 8547/28080 [16:53:11<38:49:28,  7.16s/it]
 30%|███       | 8548/28080 [16:53:18<38:48:01,  7.15s/it]
                                                          
{'loss': 0.6239, 'learning_rate': 0.0004076022192539328, 'epoch': 3.65}

 30%|███       | 8548/28080 [16:53:18<38:48:01,  7.15s/it]
 30%|███       | 8549/28080 [16:53:25<38:36:37,  7.12s/it]
                                                          
{'loss': 0.63, 'learning_rate': 0.00040757983410537676, 'epoch': 3.65}

 30%|███       | 8549/28080 [16:53:25<38:36:37,  7.12s/it]
 30%|███       | 8550/28080 [16:53:32<38:39:57,  7.13s/it]
                                                          
{'loss': 0.6325, 'learning_rate': 0.0004075574468603836, 'epoch': 3.65}

 30%|███       | 8550/28080 [16:53:32<38:39:57,  7.13s/it]
 30%|███       | 8551/28080 [16:53:40<38:39:46,  7.13s/it]
                                                          
{'loss': 0.6379, 'learning_rate': 0.00040753505751925113, 'epoch': 3.65}

 30%|███       | 8551/28080 [16:53:40<38:39:46,  7.13s/it]
 30%|███       | 8552/28080 [16:53:47<38:49:11,  7.16s/it]
                                                          
{'loss': 0.6519, 'learning_rate': 0.00040751266608227734, 'epoch': 3.65}

 30%|███       | 8552/28080 [16:53:47<38:49:11,  7.16s/it]
 30%|███       | 8553/28080 [16:53:54<38:43:35,  7.14s/it]
                                                          
{'loss': 0.6453, 'learning_rate': 0.0004074902725497599, 'epoch': 3.65}

 30%|███       | 8553/28080 [16:53:54<38:43:35,  7.14s/it]
 30%|███       | 8554/28080 [16:54:01<38:51:02,  7.16s/it]
                                                          
{'loss': 0.6445, 'learning_rate': 0.0004074678769219969, 'epoch': 3.65}

 30%|███       | 8554/28080 [16:54:01<38:51:02,  7.16s/it]
 30%|███       | 8555/28080 [16:54:08<38:37:24,  7.12s/it]
                                                          
{'loss': 0.6507, 'learning_rate': 0.0004074454791992862, 'epoch': 3.65}

 30%|███       | 8555/28080 [16:54:08<38:37:24,  7.12s/it]
 30%|███       | 8556/28080 [16:54:15<38:33:33,  7.11s/it]
                                                          
{'loss': 0.64, 'learning_rate': 0.0004074230793819259, 'epoch': 3.66}

 30%|███       | 8556/28080 [16:54:15<38:33:33,  7.11s/it]
 30%|███       | 8557/28080 [16:54:22<38:32:14,  7.11s/it]
                                                          
{'loss': 0.6336, 'learning_rate': 0.0004074006774702139, 'epoch': 3.66}

 30%|███       | 8557/28080 [16:54:22<38:32:14,  7.11s/it]
 30%|███       | 8558/28080 [16:54:29<38:30:50,  7.10s/it]
                                                          
{'loss': 0.6226, 'learning_rate': 0.0004073782734644483, 'epoch': 3.66}

 30%|███       | 8558/28080 [16:54:29<38:30:50,  7.10s/it]
 30%|███       | 8559/28080 [16:54:36<38:32:55,  7.11s/it]
                                                          
{'loss': 0.6342, 'learning_rate': 0.00040735586736492715, 'epoch': 3.66}

 30%|███       | 8559/28080 [16:54:36<38:32:55,  7.11s/it]
 30%|███       | 8560/28080 [16:54:44<38:30:39,  7.10s/it]
                                                          
{'loss': 0.6091, 'learning_rate': 0.0004073334591719484, 'epoch': 3.66}

 30%|███       | 8560/28080 [16:54:44<38:30:39,  7.10s/it]
 30%|███       | 8561/28080 [16:54:51<38:35:20,  7.12s/it]
                                                          
{'loss': 0.6175, 'learning_rate': 0.0004073110488858104, 'epoch': 3.66}

 30%|███       | 8561/28080 [16:54:51<38:35:20,  7.12s/it]
 30%|███       | 8562/28080 [16:54:58<38:47:02,  7.15s/it]
                                                          
{'loss': 0.6233, 'learning_rate': 0.00040728863650681113, 'epoch': 3.66}

 30%|███       | 8562/28080 [16:54:58<38:47:02,  7.15s/it]
 30%|███       | 8563/28080 [16:55:05<38:44:11,  7.15s/it]
                                                          
{'loss': 0.6271, 'learning_rate': 0.0004072662220352489, 'epoch': 3.66}

 30%|███       | 8563/28080 [16:55:05<38:44:11,  7.15s/it]
 30%|███       | 8564/28080 [16:55:12<38:50:43,  7.17s/it]
                                                          
{'loss': 0.6213, 'learning_rate': 0.00040724380547142177, 'epoch': 3.66}

 30%|███       | 8564/28080 [16:55:12<38:50:43,  7.17s/it]
 31%|███       | 8565/28080 [16:55:19<38:42:34,  7.14s/it]
                                                          
{'loss': 0.6298, 'learning_rate': 0.000407221386815628, 'epoch': 3.66}

 31%|███       | 8565/28080 [16:55:19<38:42:34,  7.14s/it]
 31%|███       | 8566/28080 [16:55:27<38:47:07,  7.16s/it]
                                                          
{'loss': 0.6263, 'learning_rate': 0.00040719896606816584, 'epoch': 3.66}

 31%|███       | 8566/28080 [16:55:27<38:47:07,  7.16s/it]
 31%|███       | 8567/28080 [16:55:34<38:45:09,  7.15s/it]
                                                          
{'loss': 0.6317, 'learning_rate': 0.00040717654322933373, 'epoch': 3.66}

 31%|███       | 8567/28080 [16:55:34<38:45:09,  7.15s/it]
 31%|███       | 8568/28080 [16:55:41<38:40:49,  7.14s/it]
                                                          
{'loss': 0.6313, 'learning_rate': 0.00040715411829942983, 'epoch': 3.66}

 31%|███       | 8568/28080 [16:55:41<38:40:49,  7.14s/it]
 31%|███       | 8569/28080 [16:55:48<38:39:21,  7.13s/it]
                                                          
{'loss': 0.6296, 'learning_rate': 0.0004071316912787524, 'epoch': 3.66}

 31%|███       | 8569/28080 [16:55:48<38:39:21,  7.13s/it]
 31%|███       | 8570/28080 [16:55:55<38:45:42,  7.15s/it]
                                                          
{'loss': 0.6342, 'learning_rate': 0.0004071092621676001, 'epoch': 3.66}

 31%|███       | 8570/28080 [16:55:55<38:45:42,  7.15s/it]
 31%|███       | 8571/28080 [16:56:02<38:43:18,  7.15s/it]
                                                          
{'loss': 0.6284, 'learning_rate': 0.000407086830966271, 'epoch': 3.66}

 31%|███       | 8571/28080 [16:56:02<38:43:18,  7.15s/it]
 31%|███       | 8572/28080 [16:56:09<38:37:14,  7.13s/it]
                                                          
{'loss': 0.6386, 'learning_rate': 0.0004070643976750638, 'epoch': 3.66}

 31%|███       | 8572/28080 [16:56:09<38:37:14,  7.13s/it]
 31%|███       | 8573/28080 [16:56:16<38:36:57,  7.13s/it]
                                                          
{'loss': 0.6193, 'learning_rate': 0.00040704196229427673, 'epoch': 3.66}

 31%|███       | 8573/28080 [16:56:16<38:36:57,  7.13s/it]
 31%|███       | 8574/28080 [16:56:24<38:41:12,  7.14s/it]
                                                          
{'loss': 0.6187, 'learning_rate': 0.00040701952482420834, 'epoch': 3.66}

 31%|███       | 8574/28080 [16:56:24<38:41:12,  7.14s/it]
 31%|███       | 8575/28080 [16:56:31<38:39:19,  7.13s/it]
                                                          
{'loss': 0.6196, 'learning_rate': 0.0004069970852651572, 'epoch': 3.66}

 31%|███       | 8575/28080 [16:56:31<38:39:19,  7.13s/it]
 31%|███       | 8576/28080 [16:56:38<38:41:24,  7.14s/it]
                                                          
{'loss': 0.6291, 'learning_rate': 0.0004069746436174219, 'epoch': 3.66}

 31%|███       | 8576/28080 [16:56:38<38:41:24,  7.14s/it]
 31%|███       | 8577/28080 [16:56:45<38:43:58,  7.15s/it]
                                                          
{'loss': 0.6232, 'learning_rate': 0.0004069521998813007, 'epoch': 3.66}

 31%|███       | 8577/28080 [16:56:45<38:43:58,  7.15s/it]
 31%|███       | 8578/28080 [16:56:52<38:47:19,  7.16s/it]
                                                          
{'loss': 0.6267, 'learning_rate': 0.00040692975405709253, 'epoch': 3.66}

 31%|███       | 8578/28080 [16:56:52<38:47:19,  7.16s/it]
 31%|███       | 8579/28080 [16:57:00<38:55:41,  7.19s/it]
                                                          
{'loss': 0.6042, 'learning_rate': 0.00040690730614509585, 'epoch': 3.66}

 31%|███       | 8579/28080 [16:57:00<38:55:41,  7.19s/it]
 31%|███       | 8580/28080 [16:57:07<38:51:21,  7.17s/it]
                                                          
{'loss': 0.6129, 'learning_rate': 0.00040688485614560937, 'epoch': 3.67}

 31%|███       | 8580/28080 [16:57:07<38:51:21,  7.17s/it]
 31%|███       | 8581/28080 [16:57:14<38:44:57,  7.15s/it]
                                                          
{'loss': 0.6342, 'learning_rate': 0.00040686240405893173, 'epoch': 3.67}

 31%|███       | 8581/28080 [16:57:14<38:44:57,  7.15s/it]
 31%|███       | 8582/28080 [16:57:21<38:42:07,  7.15s/it]
                                                          
{'loss': 0.6249, 'learning_rate': 0.00040683994988536154, 'epoch': 3.67}

 31%|███       | 8582/28080 [16:57:21<38:42:07,  7.15s/it]
 31%|███       | 8583/28080 [16:57:28<38:49:07,  7.17s/it]
                                                          
{'loss': 0.6193, 'learning_rate': 0.0004068174936251977, 'epoch': 3.67}

 31%|███       | 8583/28080 [16:57:28<38:49:07,  7.17s/it]
 31%|███       | 8584/28080 [16:57:35<38:40:00,  7.14s/it]
                                                          
{'loss': 0.6461, 'learning_rate': 0.00040679503527873886, 'epoch': 3.67}

 31%|███       | 8584/28080 [16:57:35<38:40:00,  7.14s/it]
 31%|███       | 8585/28080 [16:57:42<38:36:00,  7.13s/it]
                                                          
{'loss': 0.6379, 'learning_rate': 0.0004067725748462838, 'epoch': 3.67}

 31%|███       | 8585/28080 [16:57:42<38:36:00,  7.13s/it]
 31%|███       | 8586/28080 [16:57:49<38:40:25,  7.14s/it]
                                                          
{'loss': 0.6244, 'learning_rate': 0.0004067501123281315, 'epoch': 3.67}

 31%|███       | 8586/28080 [16:57:49<38:40:25,  7.14s/it]
 31%|███       | 8587/28080 [16:57:57<38:47:09,  7.16s/it]
                                                          
{'loss': 0.6482, 'learning_rate': 0.0004067276477245805, 'epoch': 3.67}

 31%|███       | 8587/28080 [16:57:57<38:47:09,  7.16s/it]
 31%|███       | 8588/28080 [16:58:04<38:46:04,  7.16s/it]
                                                          
{'loss': 0.65, 'learning_rate': 0.00040670518103592994, 'epoch': 3.67}

 31%|███       | 8588/28080 [16:58:04<38:46:04,  7.16s/it]
 31%|███       | 8589/28080 [16:58:11<38:32:09,  7.12s/it]
                                                          
{'loss': 0.635, 'learning_rate': 0.0004066827122624786, 'epoch': 3.67}

 31%|███       | 8589/28080 [16:58:11<38:32:09,  7.12s/it]
 31%|███       | 8590/28080 [16:58:18<38:32:07,  7.12s/it]
                                                          
{'loss': 0.6079, 'learning_rate': 0.0004066602414045254, 'epoch': 3.67}

 31%|███       | 8590/28080 [16:58:18<38:32:07,  7.12s/it]
 31%|███       | 8591/28080 [16:58:25<38:33:39,  7.12s/it]
                                                          
{'loss': 0.6428, 'learning_rate': 0.00040663776846236926, 'epoch': 3.67}

 31%|███       | 8591/28080 [16:58:25<38:33:39,  7.12s/it]
 31%|███       | 8592/28080 [16:58:32<38:26:47,  7.10s/it]
                                                          
{'loss': 0.6395, 'learning_rate': 0.0004066152934363092, 'epoch': 3.67}

 31%|███       | 8592/28080 [16:58:32<38:26:47,  7.10s/it]
 31%|███       | 8593/28080 [16:58:39<38:26:29,  7.10s/it]
                                                          
{'loss': 0.6375, 'learning_rate': 0.00040659281632664436, 'epoch': 3.67}

 31%|███       | 8593/28080 [16:58:39<38:26:29,  7.10s/it]
 31%|███       | 8594/28080 [16:58:46<38:37:17,  7.14s/it]
                                                          
{'loss': 0.6212, 'learning_rate': 0.00040657033713367355, 'epoch': 3.67}

 31%|███       | 8594/28080 [16:58:46<38:37:17,  7.14s/it]
 31%|███       | 8595/28080 [16:58:54<38:31:30,  7.12s/it]
                                                          
{'loss': 0.6294, 'learning_rate': 0.00040654785585769596, 'epoch': 3.67}

 31%|███       | 8595/28080 [16:58:54<38:31:30,  7.12s/it]
 31%|███       | 8596/28080 [16:59:01<38:33:12,  7.12s/it]
                                                          
{'loss': 0.6416, 'learning_rate': 0.0004065253724990106, 'epoch': 3.67}

 31%|███       | 8596/28080 [16:59:01<38:33:12,  7.12s/it]
 31%|███       | 8597/28080 [16:59:08<38:28:18,  7.11s/it]
                                                          
{'loss': 0.6385, 'learning_rate': 0.00040650288705791664, 'epoch': 3.67}

 31%|███       | 8597/28080 [16:59:08<38:28:18,  7.11s/it]
 31%|███       | 8598/28080 [16:59:15<38:23:13,  7.09s/it]
                                                          
{'loss': 0.6492, 'learning_rate': 0.0004064803995347133, 'epoch': 3.67}

 31%|███       | 8598/28080 [16:59:15<38:23:13,  7.09s/it]
 31%|███       | 8599/28080 [16:59:22<38:23:28,  7.09s/it]
                                                          
{'loss': 0.6258, 'learning_rate': 0.0004064579099296996, 'epoch': 3.67}

 31%|███       | 8599/28080 [16:59:22<38:23:28,  7.09s/it]
 31%|███       | 8600/28080 [16:59:29<38:27:43,  7.11s/it]
                                                          
{'loss': 0.6428, 'learning_rate': 0.00040643541824317487, 'epoch': 3.67}

 31%|███       | 8600/28080 [16:59:29<38:27:43,  7.11s/it]
 31%|███       | 8601/28080 [16:59:36<38:27:46,  7.11s/it]
                                                          
{'loss': 0.6287, 'learning_rate': 0.0004064129244754382, 'epoch': 3.67}

 31%|███       | 8601/28080 [16:59:36<38:27:46,  7.11s/it]
 31%|███       | 8602/28080 [16:59:43<38:34:31,  7.13s/it]
                                                          
{'loss': 0.6338, 'learning_rate': 0.00040639042862678897, 'epoch': 3.67}

 31%|███       | 8602/28080 [16:59:43<38:34:31,  7.13s/it]
 31%|███       | 8603/28080 [16:59:51<38:38:44,  7.14s/it]
                                                          
{'loss': 0.629, 'learning_rate': 0.00040636793069752646, 'epoch': 3.68}

 31%|███       | 8603/28080 [16:59:51<38:38:44,  7.14s/it]
 31%|███       | 8604/28080 [16:59:58<38:31:07,  7.12s/it]
                                                          
{'loss': 0.6447, 'learning_rate': 0.00040634543068794994, 'epoch': 3.68}

 31%|███       | 8604/28080 [16:59:58<38:31:07,  7.12s/it]
 31%|███       | 8605/28080 [17:00:05<38:34:46,  7.13s/it]
                                                          
{'loss': 0.64, 'learning_rate': 0.0004063229285983587, 'epoch': 3.68}

 31%|███       | 8605/28080 [17:00:05<38:34:46,  7.13s/it]
 31%|███       | 8606/28080 [17:00:12<38:36:49,  7.14s/it]
                                                          
{'loss': 0.659, 'learning_rate': 0.0004063004244290523, 'epoch': 3.68}

 31%|███       | 8606/28080 [17:00:12<38:36:49,  7.14s/it]
 31%|███       | 8607/28080 [17:00:19<38:40:31,  7.15s/it]
                                                          
{'loss': 0.6227, 'learning_rate': 0.00040627791818032986, 'epoch': 3.68}

 31%|███       | 8607/28080 [17:00:19<38:40:31,  7.15s/it]
 31%|███       | 8608/28080 [17:00:26<38:37:14,  7.14s/it]
                                                          
{'loss': 0.6102, 'learning_rate': 0.000406255409852491, 'epoch': 3.68}

 31%|███       | 8608/28080 [17:00:26<38:37:14,  7.14s/it]
 31%|███       | 8609/28080 [17:00:33<38:27:27,  7.11s/it]
                                                          
{'loss': 0.6329, 'learning_rate': 0.00040623289944583506, 'epoch': 3.68}

 31%|███       | 8609/28080 [17:00:33<38:27:27,  7.11s/it]
 31%|███       | 8610/28080 [17:00:40<38:35:10,  7.13s/it]
                                                          
{'loss': 0.6214, 'learning_rate': 0.0004062103869606617, 'epoch': 3.68}

 31%|███       | 8610/28080 [17:00:40<38:35:10,  7.13s/it]
 31%|███       | 8611/28080 [17:00:48<38:33:27,  7.13s/it]
                                                          
{'loss': 0.6341, 'learning_rate': 0.00040618787239727017, 'epoch': 3.68}

 31%|███       | 8611/28080 [17:00:48<38:33:27,  7.13s/it]
 31%|███       | 8612/28080 [17:00:55<38:32:27,  7.13s/it]
                                                          
{'loss': 0.6314, 'learning_rate': 0.00040616535575596017, 'epoch': 3.68}

 31%|███       | 8612/28080 [17:00:55<38:32:27,  7.13s/it]
 31%|███       | 8613/28080 [17:01:02<38:33:07,  7.13s/it]
                                                          
{'loss': 0.627, 'learning_rate': 0.00040614283703703123, 'epoch': 3.68}

 31%|███       | 8613/28080 [17:01:02<38:33:07,  7.13s/it]
 31%|███       | 8614/28080 [17:01:09<38:32:23,  7.13s/it]
                                                          
{'loss': 0.6353, 'learning_rate': 0.00040612031624078296, 'epoch': 3.68}

 31%|███       | 8614/28080 [17:01:09<38:32:23,  7.13s/it]
 31%|███       | 8615/28080 [17:01:16<38:32:28,  7.13s/it]
                                                          
{'loss': 0.6328, 'learning_rate': 0.00040609779336751487, 'epoch': 3.68}

 31%|███       | 8615/28080 [17:01:16<38:32:28,  7.13s/it]
 31%|███       | 8616/28080 [17:01:23<38:36:11,  7.14s/it]
                                                          
{'loss': 0.6596, 'learning_rate': 0.0004060752684175267, 'epoch': 3.68}

 31%|███       | 8616/28080 [17:01:23<38:36:11,  7.14s/it]
 31%|███       | 8617/28080 [17:01:30<38:36:42,  7.14s/it]
                                                          
{'loss': 0.6362, 'learning_rate': 0.0004060527413911181, 'epoch': 3.68}

 31%|███       | 8617/28080 [17:01:30<38:36:42,  7.14s/it]
 31%|███       | 8618/28080 [17:01:38<38:36:48,  7.14s/it]
                                                          
{'loss': 0.6306, 'learning_rate': 0.0004060302122885887, 'epoch': 3.68}

 31%|███       | 8618/28080 [17:01:38<38:36:48,  7.14s/it]
 31%|███       | 8619/28080 [17:01:45<38:40:43,  7.15s/it]
                                                          
{'loss': 0.6189, 'learning_rate': 0.00040600768111023847, 'epoch': 3.68}

 31%|███       | 8619/28080 [17:01:45<38:40:43,  7.15s/it]
 31%|███       | 8620/28080 [17:01:52<38:42:51,  7.16s/it]
                                                          
{'loss': 0.64, 'learning_rate': 0.0004059851478563669, 'epoch': 3.68}

 31%|███       | 8620/28080 [17:01:52<38:42:51,  7.16s/it]
 31%|███       | 8621/28080 [17:01:59<38:53:34,  7.20s/it]
                                                          
{'loss': 0.6312, 'learning_rate': 0.0004059626125272738, 'epoch': 3.68}

 31%|███       | 8621/28080 [17:01:59<38:53:34,  7.20s/it]
 31%|███       | 8622/28080 [17:02:06<38:56:47,  7.21s/it]
                                                          
{'loss': 0.6276, 'learning_rate': 0.00040594007512325905, 'epoch': 3.68}

 31%|███       | 8622/28080 [17:02:06<38:56:47,  7.21s/it]
 31%|███       | 8623/28080 [17:02:14<39:00:14,  7.22s/it]
                                                          
{'loss': 0.6117, 'learning_rate': 0.0004059175356446225, 'epoch': 3.68}

 31%|███       | 8623/28080 [17:02:14<39:00:14,  7.22s/it]
 31%|███       | 8624/28080 [17:02:21<38:57:43,  7.21s/it]
                                                          
{'loss': 0.6232, 'learning_rate': 0.000405894994091664, 'epoch': 3.68}

 31%|███       | 8624/28080 [17:02:21<38:57:43,  7.21s/it]
 31%|███       | 8625/28080 [17:02:28<38:43:23,  7.17s/it]
                                                          
{'loss': 0.6331, 'learning_rate': 0.0004058724504646834, 'epoch': 3.68}

 31%|███       | 8625/28080 [17:02:28<38:43:23,  7.17s/it]
 31%|███       | 8626/28080 [17:02:35<38:38:24,  7.15s/it]
                                                          
{'loss': 0.6539, 'learning_rate': 0.00040584990476398065, 'epoch': 3.68}

 31%|███       | 8626/28080 [17:02:35<38:38:24,  7.15s/it]
 31%|███       | 8627/28080 [17:02:42<38:36:34,  7.15s/it]
                                                          
{'loss': 0.6331, 'learning_rate': 0.00040582735698985574, 'epoch': 3.69}

 31%|███       | 8627/28080 [17:02:42<38:36:34,  7.15s/it]
 31%|███       | 8628/28080 [17:02:49<38:30:25,  7.13s/it]
                                                          
{'loss': 0.6471, 'learning_rate': 0.0004058048071426086, 'epoch': 3.69}

 31%|███       | 8628/28080 [17:02:49<38:30:25,  7.13s/it]
 31%|███       | 8629/28080 [17:02:56<38:15:48,  7.08s/it]
                                                          
{'loss': 0.6524, 'learning_rate': 0.0004057822552225392, 'epoch': 3.69}

 31%|███       | 8629/28080 [17:02:56<38:15:48,  7.08s/it]
 31%|███       | 8630/28080 [17:03:03<38:31:50,  7.13s/it]
                                                          
{'loss': 0.6246, 'learning_rate': 0.00040575970122994765, 'epoch': 3.69}

 31%|███       | 8630/28080 [17:03:03<38:31:50,  7.13s/it]
 31%|███       | 8631/28080 [17:03:11<38:35:08,  7.14s/it]
                                                          
{'loss': 0.6458, 'learning_rate': 0.0004057371451651339, 'epoch': 3.69}

 31%|███       | 8631/28080 [17:03:11<38:35:08,  7.14s/it]
 31%|███       | 8632/28080 [17:03:18<38:39:19,  7.16s/it]
                                                          
{'loss': 0.6273, 'learning_rate': 0.00040571458702839817, 'epoch': 3.69}

 31%|███       | 8632/28080 [17:03:18<38:39:19,  7.16s/it]
 31%|███       | 8633/28080 [17:03:25<38:38:16,  7.15s/it]
                                                          
{'loss': 0.658, 'learning_rate': 0.00040569202682004047, 'epoch': 3.69}

 31%|███       | 8633/28080 [17:03:25<38:38:16,  7.15s/it]
 31%|███       | 8634/28080 [17:03:32<38:49:50,  7.19s/it]
                                                          
{'loss': 0.6247, 'learning_rate': 0.0004056694645403609, 'epoch': 3.69}

 31%|███       | 8634/28080 [17:03:32<38:49:50,  7.19s/it]
 31%|███       | 8635/28080 [17:03:39<38:34:10,  7.14s/it]
                                                          
{'loss': 0.6489, 'learning_rate': 0.00040564690018965975, 'epoch': 3.69}

 31%|███       | 8635/28080 [17:03:39<38:34:10,  7.14s/it]
 31%|███       | 8636/28080 [17:03:46<38:30:57,  7.13s/it]
                                                          
{'loss': 0.6209, 'learning_rate': 0.00040562433376823727, 'epoch': 3.69}

 31%|███       | 8636/28080 [17:03:46<38:30:57,  7.13s/it]
 31%|███       | 8637/28080 [17:03:53<38:33:49,  7.14s/it]
                                                          
{'loss': 0.6454, 'learning_rate': 0.0004056017652763935, 'epoch': 3.69}

 31%|███       | 8637/28080 [17:03:53<38:33:49,  7.14s/it]
 31%|███       | 8638/28080 [17:04:01<38:21:25,  7.10s/it]
                                                          
{'loss': 0.6287, 'learning_rate': 0.0004055791947144287, 'epoch': 3.69}

 31%|███       | 8638/28080 [17:04:01<38:21:25,  7.10s/it]
 31%|███       | 8639/28080 [17:04:08<38:26:07,  7.12s/it]
                                                          
{'loss': 0.6391, 'learning_rate': 0.0004055566220826433, 'epoch': 3.69}

 31%|███       | 8639/28080 [17:04:08<38:26:07,  7.12s/it]
 31%|███       | 8640/28080 [17:04:15<38:30:15,  7.13s/it]
                                                          
{'loss': 0.6203, 'learning_rate': 0.0004055340473813375, 'epoch': 3.69}

 31%|███       | 8640/28080 [17:04:15<38:30:15,  7.13s/it]
 31%|███       | 8641/28080 [17:04:22<38:33:51,  7.14s/it]
                                                          
{'loss': 0.6248, 'learning_rate': 0.0004055114706108116, 'epoch': 3.69}

 31%|███       | 8641/28080 [17:04:22<38:33:51,  7.14s/it]
 31%|███       | 8642/28080 [17:04:29<38:27:46,  7.12s/it]
                                                          
{'loss': 0.6066, 'learning_rate': 0.0004054888917713662, 'epoch': 3.69}

 31%|███       | 8642/28080 [17:04:29<38:27:46,  7.12s/it]
 31%|███       | 8643/28080 [17:04:36<38:30:36,  7.13s/it]
                                                          
{'loss': 0.6345, 'learning_rate': 0.0004054663108633013, 'epoch': 3.69}

 31%|███       | 8643/28080 [17:04:36<38:30:36,  7.13s/it]
 31%|███       | 8644/28080 [17:04:43<38:21:32,  7.10s/it]
                                                          
{'loss': 0.6066, 'learning_rate': 0.00040544372788691764, 'epoch': 3.69}

 31%|███       | 8644/28080 [17:04:43<38:21:32,  7.10s/it]
 31%|███       | 8645/28080 [17:04:50<38:26:06,  7.12s/it]
                                                          
{'loss': 0.6305, 'learning_rate': 0.0004054211428425155, 'epoch': 3.69}

 31%|███       | 8645/28080 [17:04:50<38:26:06,  7.12s/it]
 31%|███       | 8646/28080 [17:04:58<38:29:34,  7.13s/it]
                                                          
{'loss': 0.6286, 'learning_rate': 0.00040539855573039536, 'epoch': 3.69}

 31%|███       | 8646/28080 [17:04:58<38:29:34,  7.13s/it]
 31%|███       | 8647/28080 [17:05:05<38:33:36,  7.14s/it]
                                                          
{'loss': 0.638, 'learning_rate': 0.00040537596655085777, 'epoch': 3.69}

 31%|███       | 8647/28080 [17:05:05<38:33:36,  7.14s/it]
 31%|███       | 8648/28080 [17:05:12<38:30:47,  7.14s/it]
                                                          
{'loss': 0.628, 'learning_rate': 0.00040535337530420325, 'epoch': 3.69}

 31%|███       | 8648/28080 [17:05:12<38:30:47,  7.14s/it]
 31%|███       | 8649/28080 [17:05:19<38:36:15,  7.15s/it]
                                                          
{'loss': 0.6582, 'learning_rate': 0.0004053307819907324, 'epoch': 3.69}

 31%|███       | 8649/28080 [17:05:19<38:36:15,  7.15s/it]
 31%|███       | 8650/28080 [17:05:26<38:35:27,  7.15s/it]
                                                          
{'loss': 0.6242, 'learning_rate': 0.00040530818661074563, 'epoch': 3.7}

 31%|███       | 8650/28080 [17:05:26<38:35:27,  7.15s/it]
 31%|███       | 8651/28080 [17:05:33<38:33:04,  7.14s/it]
                                                          
{'loss': 0.6528, 'learning_rate': 0.0004052855891645437, 'epoch': 3.7}

 31%|███       | 8651/28080 [17:05:33<38:33:04,  7.14s/it]
 31%|███       | 8652/28080 [17:05:40<38:22:55,  7.11s/it]
                                                          
{'loss': 0.6465, 'learning_rate': 0.00040526298965242727, 'epoch': 3.7}

 31%|███       | 8652/28080 [17:05:40<38:22:55,  7.11s/it]
 31%|███       | 8653/28080 [17:05:48<38:33:10,  7.14s/it]
                                                          
{'loss': 0.6428, 'learning_rate': 0.00040524038807469685, 'epoch': 3.7}

 31%|███       | 8653/28080 [17:05:48<38:33:10,  7.14s/it]
 31%|███       | 8654/28080 [17:05:55<38:23:36,  7.12s/it]
                                                          
{'loss': 0.6384, 'learning_rate': 0.00040521778443165324, 'epoch': 3.7}

 31%|███       | 8654/28080 [17:05:55<38:23:36,  7.12s/it]
 31%|███       | 8655/28080 [17:06:02<38:14:06,  7.09s/it]
                                                          
{'loss': 0.6474, 'learning_rate': 0.00040519517872359713, 'epoch': 3.7}

 31%|███       | 8655/28080 [17:06:02<38:14:06,  7.09s/it]
 31%|███       | 8656/28080 [17:06:09<38:26:09,  7.12s/it]
                                                          
{'loss': 0.6499, 'learning_rate': 0.00040517257095082934, 'epoch': 3.7}

 31%|███       | 8656/28080 [17:06:09<38:26:09,  7.12s/it]
 31%|███       | 8657/28080 [17:06:16<38:39:11,  7.16s/it]
                                                          
{'loss': 0.6138, 'learning_rate': 0.0004051499611136505, 'epoch': 3.7}

 31%|███       | 8657/28080 [17:06:16<38:39:11,  7.16s/it]
 31%|███       | 8658/28080 [17:06:23<38:38:28,  7.16s/it]
                                                          
{'loss': 0.6225, 'learning_rate': 0.0004051273492123615, 'epoch': 3.7}

 31%|███       | 8658/28080 [17:06:23<38:38:28,  7.16s/it]
 31%|███       | 8659/28080 [17:06:30<38:35:34,  7.15s/it]
                                                          
{'loss': 0.6273, 'learning_rate': 0.00040510473524726324, 'epoch': 3.7}

 31%|███       | 8659/28080 [17:06:30<38:35:34,  7.15s/it]
 31%|███       | 8660/28080 [17:06:38<38:39:28,  7.17s/it]
                                                          
{'loss': 0.6098, 'learning_rate': 0.00040508211921865635, 'epoch': 3.7}

 31%|███       | 8660/28080 [17:06:38<38:39:28,  7.17s/it]
 31%|███       | 8661/28080 [17:06:45<38:23:21,  7.12s/it]
                                                          
{'loss': 0.6417, 'learning_rate': 0.000405059501126842, 'epoch': 3.7}

 31%|███       | 8661/28080 [17:06:45<38:23:21,  7.12s/it]
 31%|███       | 8662/28080 [17:06:52<38:20:44,  7.11s/it]
                                                          
{'loss': 0.6355, 'learning_rate': 0.0004050368809721209, 'epoch': 3.7}

 31%|███       | 8662/28080 [17:06:52<38:20:44,  7.11s/it]
 31%|███       | 8663/28080 [17:06:59<38:21:50,  7.11s/it]
                                                          
{'loss': 0.6301, 'learning_rate': 0.00040501425875479394, 'epoch': 3.7}

 31%|███       | 8663/28080 [17:06:59<38:21:50,  7.11s/it]
 31%|███       | 8664/28080 [17:07:06<38:18:25,  7.10s/it]
                                                          
{'loss': 0.6351, 'learning_rate': 0.0004049916344751623, 'epoch': 3.7}

 31%|███       | 8664/28080 [17:07:06<38:18:25,  7.10s/it]
 31%|███       | 8665/28080 [17:07:13<38:11:22,  7.08s/it]
                                                          
{'loss': 0.6501, 'learning_rate': 0.00040496900813352676, 'epoch': 3.7}

 31%|███       | 8665/28080 [17:07:13<38:11:22,  7.08s/it]
 31%|███       | 8666/28080 [17:07:20<38:08:39,  7.07s/it]
                                                          
{'loss': 0.6382, 'learning_rate': 0.00040494637973018853, 'epoch': 3.7}

 31%|███       | 8666/28080 [17:07:20<38:08:39,  7.07s/it]
 31%|███       | 8667/28080 [17:07:27<38:09:48,  7.08s/it]
                                                          
{'loss': 0.6257, 'learning_rate': 0.0004049237492654486, 'epoch': 3.7}

 31%|███       | 8667/28080 [17:07:27<38:09:48,  7.08s/it]
 31%|███       | 8668/28080 [17:07:34<38:18:01,  7.10s/it]
                                                          
{'loss': 0.6345, 'learning_rate': 0.00040490111673960793, 'epoch': 3.7}

 31%|███       | 8668/28080 [17:07:34<38:18:01,  7.10s/it]
 31%|███       | 8669/28080 [17:07:41<38:17:22,  7.10s/it]
                                                          
{'loss': 0.6385, 'learning_rate': 0.00040487848215296773, 'epoch': 3.7}

 31%|███       | 8669/28080 [17:07:41<38:17:22,  7.10s/it]
 31%|███       | 8670/28080 [17:07:49<38:24:55,  7.12s/it]
                                                          
{'loss': 0.6374, 'learning_rate': 0.0004048558455058291, 'epoch': 3.7}

 31%|███       | 8670/28080 [17:07:49<38:24:55,  7.12s/it]
 31%|███       | 8671/28080 [17:07:56<38:25:14,  7.13s/it]
                                                          
{'loss': 0.6211, 'learning_rate': 0.0004048332067984932, 'epoch': 3.7}

 31%|███       | 8671/28080 [17:07:56<38:25:14,  7.13s/it]
 31%|███       | 8672/28080 [17:08:03<38:28:20,  7.14s/it]
                                                          
{'loss': 0.6267, 'learning_rate': 0.0004048105660312612, 'epoch': 3.7}

 31%|███       | 8672/28080 [17:08:03<38:28:20,  7.14s/it]
 31%|███       | 8673/28080 [17:08:10<38:26:16,  7.13s/it]
                                                          
{'loss': 0.6439, 'learning_rate': 0.0004047879232044344, 'epoch': 3.71}

 31%|███       | 8673/28080 [17:08:10<38:26:16,  7.13s/it]
 31%|███       | 8674/28080 [17:08:17<38:28:57,  7.14s/it]
                                                          
{'loss': 0.6352, 'learning_rate': 0.0004047652783183139, 'epoch': 3.71}

 31%|███       | 8674/28080 [17:08:17<38:28:57,  7.14s/it]
 31%|███       | 8675/28080 [17:08:24<38:27:17,  7.13s/it]
                                                          
{'loss': 0.6416, 'learning_rate': 0.00040474263137320104, 'epoch': 3.71}

 31%|███       | 8675/28080 [17:08:24<38:27:17,  7.13s/it]
 31%|███       | 8676/28080 [17:08:31<38:27:21,  7.13s/it]
                                                          
{'loss': 0.633, 'learning_rate': 0.0004047199823693971, 'epoch': 3.71}

 31%|███       | 8676/28080 [17:08:31<38:27:21,  7.13s/it]
 31%|███       | 8677/28080 [17:08:38<38:20:07,  7.11s/it]
                                                          
{'loss': 0.659, 'learning_rate': 0.00040469733130720344, 'epoch': 3.71}

 31%|███       | 8677/28080 [17:08:38<38:20:07,  7.11s/it]
 31%|███       | 8678/28080 [17:08:45<38:14:00,  7.09s/it]
                                                          
{'loss': 0.6599, 'learning_rate': 0.0004046746781869214, 'epoch': 3.71}

 31%|███       | 8678/28080 [17:08:45<38:14:00,  7.09s/it]
 31%|███       | 8679/28080 [17:08:53<38:17:23,  7.10s/it]
                                                          
{'loss': 0.6208, 'learning_rate': 0.0004046520230088523, 'epoch': 3.71}

 31%|███       | 8679/28080 [17:08:53<38:17:23,  7.10s/it]
 31%|███       | 8680/28080 [17:09:00<38:19:55,  7.11s/it]
                                                          
{'loss': 0.6351, 'learning_rate': 0.00040462936577329755, 'epoch': 3.71}

 31%|███       | 8680/28080 [17:09:00<38:19:55,  7.11s/it]
 31%|███       | 8681/28080 [17:09:07<38:18:14,  7.11s/it]
                                                          
{'loss': 0.6202, 'learning_rate': 0.00040460670648055863, 'epoch': 3.71}

 31%|███       | 8681/28080 [17:09:07<38:18:14,  7.11s/it]
 31%|███       | 8682/28080 [17:09:14<38:16:44,  7.10s/it]
                                                          
{'loss': 0.6305, 'learning_rate': 0.00040458404513093706, 'epoch': 3.71}

 31%|███       | 8682/28080 [17:09:14<38:16:44,  7.10s/it]
 31%|███       | 8683/28080 [17:09:21<38:25:05,  7.13s/it]
                                                          
{'loss': 0.6235, 'learning_rate': 0.00040456138172473413, 'epoch': 3.71}

 31%|███       | 8683/28080 [17:09:21<38:25:05,  7.13s/it]
 31%|███       | 8684/28080 [17:09:28<38:19:39,  7.11s/it]
                                                          
{'loss': 0.629, 'learning_rate': 0.00040453871626225157, 'epoch': 3.71}

 31%|███       | 8684/28080 [17:09:28<38:19:39,  7.11s/it]
 31%|███       | 8685/28080 [17:09:35<38:21:35,  7.12s/it]
                                                          
{'loss': 0.6331, 'learning_rate': 0.0004045160487437908, 'epoch': 3.71}

 31%|███       | 8685/28080 [17:09:35<38:21:35,  7.12s/it]
 31%|███       | 8686/28080 [17:09:42<38:23:46,  7.13s/it]
                                                          
{'loss': 0.6215, 'learning_rate': 0.0004044933791696533, 'epoch': 3.71}

 31%|███       | 8686/28080 [17:09:42<38:23:46,  7.13s/it]
 31%|███       | 8687/28080 [17:09:50<38:33:08,  7.16s/it]
                                                          
{'loss': 0.6353, 'learning_rate': 0.0004044707075401408, 'epoch': 3.71}

 31%|███       | 8687/28080 [17:09:50<38:33:08,  7.16s/it]
 31%|███       | 8688/28080 [17:09:57<38:31:28,  7.15s/it]
                                                          
{'loss': 0.631, 'learning_rate': 0.00040444803385555493, 'epoch': 3.71}

 31%|███       | 8688/28080 [17:09:57<38:31:28,  7.15s/it]
 31%|███       | 8689/28080 [17:10:04<38:35:19,  7.16s/it]
                                                          
{'loss': 0.6246, 'learning_rate': 0.0004044253581161974, 'epoch': 3.71}

 31%|███       | 8689/28080 [17:10:04<38:35:19,  7.16s/it]
 31%|███       | 8690/28080 [17:10:11<38:36:19,  7.17s/it]
                                                          
{'loss': 0.6283, 'learning_rate': 0.0004044026803223697, 'epoch': 3.71}

 31%|███       | 8690/28080 [17:10:11<38:36:19,  7.17s/it]
 31%|███       | 8691/28080 [17:10:18<38:31:48,  7.15s/it]
                                                          
{'loss': 0.6273, 'learning_rate': 0.0004043800004743736, 'epoch': 3.71}

 31%|███       | 8691/28080 [17:10:18<38:31:48,  7.15s/it]
 31%|███       | 8692/28080 [17:10:26<38:36:23,  7.17s/it]
                                                          
{'loss': 0.6249, 'learning_rate': 0.0004043573185725109, 'epoch': 3.71}

 31%|███       | 8692/28080 [17:10:26<38:36:23,  7.17s/it]
 31%|███       | 8693/28080 [17:10:33<38:41:47,  7.19s/it]
                                                          
{'loss': 0.6238, 'learning_rate': 0.0004043346346170833, 'epoch': 3.71}

 31%|███       | 8693/28080 [17:10:33<38:41:47,  7.19s/it]
 31%|███       | 8694/28080 [17:10:40<38:41:14,  7.18s/it]
                                                          
{'loss': 0.6298, 'learning_rate': 0.0004043119486083926, 'epoch': 3.71}

 31%|███       | 8694/28080 [17:10:40<38:41:14,  7.18s/it]
 31%|███       | 8695/28080 [17:10:47<38:20:00,  7.12s/it]
                                                          
{'loss': 0.6246, 'learning_rate': 0.0004042892605467407, 'epoch': 3.71}

 31%|███       | 8695/28080 [17:10:47<38:20:00,  7.12s/it]
 31%|███       | 8696/28080 [17:10:54<38:27:55,  7.14s/it]
                                                          
{'loss': 0.6286, 'learning_rate': 0.00040426657043242934, 'epoch': 3.71}

 31%|███       | 8696/28080 [17:10:54<38:27:55,  7.14s/it]
 31%|███       | 8697/28080 [17:11:01<38:19:43,  7.12s/it]
                                                          
{'loss': 0.6359, 'learning_rate': 0.0004042438782657603, 'epoch': 3.72}

 31%|███       | 8697/28080 [17:11:01<38:19:43,  7.12s/it]
 31%|███       | 8698/28080 [17:11:08<38:20:41,  7.12s/it]
                                                          
{'loss': 0.6283, 'learning_rate': 0.00040422118404703566, 'epoch': 3.72}

 31%|███       | 8698/28080 [17:11:08<38:20:41,  7.12s/it]
 31%|███       | 8699/28080 [17:11:15<38:22:10,  7.13s/it]
                                                          
{'loss': 0.6128, 'learning_rate': 0.0004041984877765572, 'epoch': 3.72}

 31%|███       | 8699/28080 [17:11:15<38:22:10,  7.13s/it]
 31%|███       | 8700/28080 [17:11:23<38:27:01,  7.14s/it]
                                                          
{'loss': 0.6376, 'learning_rate': 0.000404175789454627, 'epoch': 3.72}

 31%|███       | 8700/28080 [17:11:23<38:27:01,  7.14s/it]
 31%|███       | 8701/28080 [17:11:30<38:25:37,  7.14s/it]
                                                          
{'loss': 0.6458, 'learning_rate': 0.000404153089081547, 'epoch': 3.72}

 31%|███       | 8701/28080 [17:11:30<38:25:37,  7.14s/it]
 31%|███       | 8702/28080 [17:11:37<38:29:38,  7.15s/it]
                                                          
{'loss': 0.6324, 'learning_rate': 0.00040413038665761917, 'epoch': 3.72}

 31%|███       | 8702/28080 [17:11:37<38:29:38,  7.15s/it]
 31%|███       | 8703/28080 [17:11:44<38:28:09,  7.15s/it]
                                                          
{'loss': 0.6405, 'learning_rate': 0.00040410768218314554, 'epoch': 3.72}

 31%|███       | 8703/28080 [17:11:44<38:28:09,  7.15s/it]
 31%|███       | 8704/28080 [17:11:51<38:20:28,  7.12s/it]
                                                          
{'loss': 0.6656, 'learning_rate': 0.00040408497565842816, 'epoch': 3.72}

 31%|███       | 8704/28080 [17:11:51<38:20:28,  7.12s/it]
 31%|███       | 8705/28080 [17:11:58<38:22:00,  7.13s/it]
                                                          
{'loss': 0.6237, 'learning_rate': 0.0004040622670837691, 'epoch': 3.72}

 31%|███       | 8705/28080 [17:11:58<38:22:00,  7.13s/it]
 31%|███       | 8706/28080 [17:12:05<38:22:23,  7.13s/it]
                                                          
{'loss': 0.6312, 'learning_rate': 0.00040403955645947054, 'epoch': 3.72}

 31%|███       | 8706/28080 [17:12:05<38:22:23,  7.13s/it]
 31%|███       | 8707/28080 [17:12:13<38:21:54,  7.13s/it]
                                                          
{'loss': 0.6646, 'learning_rate': 0.0004040168437858347, 'epoch': 3.72}

 31%|███       | 8707/28080 [17:12:13<38:21:54,  7.13s/it]
 31%|███       | 8708/28080 [17:12:20<38:28:21,  7.15s/it]
                                                          
{'loss': 0.6391, 'learning_rate': 0.00040399412906316355, 'epoch': 3.72}

 31%|███       | 8708/28080 [17:12:20<38:28:21,  7.15s/it]
 31%|███       | 8709/28080 [17:12:27<38:32:41,  7.16s/it]
                                                          
{'loss': 0.625, 'learning_rate': 0.00040397141229175937, 'epoch': 3.72}

 31%|███       | 8709/28080 [17:12:27<38:32:41,  7.16s/it]
 31%|███       | 8710/28080 [17:12:34<38:39:46,  7.19s/it]
                                                          
{'loss': 0.6219, 'learning_rate': 0.0004039486934719244, 'epoch': 3.72}

 31%|███       | 8710/28080 [17:12:34<38:39:46,  7.19s/it]
 31%|███       | 8711/28080 [17:12:41<38:37:07,  7.18s/it]
                                                          
{'loss': 0.6131, 'learning_rate': 0.00040392597260396093, 'epoch': 3.72}

 31%|███       | 8711/28080 [17:12:41<38:37:07,  7.18s/it]
 31%|███       | 8712/28080 [17:12:49<38:39:37,  7.19s/it]
                                                          
{'loss': 0.6343, 'learning_rate': 0.0004039032496881712, 'epoch': 3.72}

 31%|███       | 8712/28080 [17:12:49<38:39:37,  7.19s/it]
 31%|███       | 8713/28080 [17:12:56<38:45:10,  7.20s/it]
                                                          
{'loss': 0.6498, 'learning_rate': 0.00040388052472485744, 'epoch': 3.72}

 31%|███       | 8713/28080 [17:12:56<38:45:10,  7.20s/it]
 31%|███       | 8714/28080 [17:13:03<38:56:25,  7.24s/it]
                                                          
{'loss': 0.6153, 'learning_rate': 0.0004038577977143221, 'epoch': 3.72}

 31%|███       | 8714/28080 [17:13:03<38:56:25,  7.24s/it]
 31%|███       | 8715/28080 [17:13:10<38:46:58,  7.21s/it]
                                                          
{'loss': 0.6499, 'learning_rate': 0.0004038350686568674, 'epoch': 3.72}

 31%|███       | 8715/28080 [17:13:10<38:46:58,  7.21s/it]
 31%|███       | 8716/28080 [17:13:17<38:37:04,  7.18s/it]
                                                          
{'loss': 0.6352, 'learning_rate': 0.0004038123375527959, 'epoch': 3.72}

 31%|███       | 8716/28080 [17:13:17<38:37:04,  7.18s/it]
 31%|███       | 8717/28080 [17:13:24<38:30:15,  7.16s/it]
                                                          
{'loss': 0.6281, 'learning_rate': 0.0004037896044024099, 'epoch': 3.72}

 31%|███       | 8717/28080 [17:13:24<38:30:15,  7.16s/it]
 31%|███       | 8718/28080 [17:13:32<38:25:10,  7.14s/it]
                                                          
{'loss': 0.6185, 'learning_rate': 0.0004037668692060119, 'epoch': 3.72}

 31%|███       | 8718/28080 [17:13:32<38:25:10,  7.14s/it]
 31%|███       | 8719/28080 [17:13:39<38:35:51,  7.18s/it]
                                                          
{'loss': 0.6335, 'learning_rate': 0.00040374413196390426, 'epoch': 3.72}

 31%|███       | 8719/28080 [17:13:39<38:35:51,  7.18s/it]
 31%|███       | 8720/28080 [17:13:46<38:38:37,  7.19s/it]
                                                          
{'loss': 0.6163, 'learning_rate': 0.0004037213926763897, 'epoch': 3.73}

 31%|███       | 8720/28080 [17:13:46<38:38:37,  7.19s/it]
 31%|███       | 8721/28080 [17:13:53<38:30:45,  7.16s/it]
                                                          
{'loss': 0.6182, 'learning_rate': 0.0004036986513437705, 'epoch': 3.73}

 31%|███       | 8721/28080 [17:13:53<38:30:45,  7.16s/it]
 31%|███       | 8722/28080 [17:14:00<38:32:27,  7.17s/it]
                                                          
{'loss': 0.6145, 'learning_rate': 0.0004036759079663493, 'epoch': 3.73}

 31%|███       | 8722/28080 [17:14:00<38:32:27,  7.17s/it]
 31%|███       | 8723/28080 [17:14:07<38:34:57,  7.18s/it]
                                                          
{'loss': 0.633, 'learning_rate': 0.0004036531625444286, 'epoch': 3.73}

 31%|███       | 8723/28080 [17:14:07<38:34:57,  7.18s/it]
 31%|███       | 8724/28080 [17:14:14<38:18:34,  7.13s/it]
                                                          
{'loss': 0.6299, 'learning_rate': 0.0004036304150783112, 'epoch': 3.73}

 31%|███       | 8724/28080 [17:14:14<38:18:34,  7.13s/it]
 31%|███       | 8725/28080 [17:14:22<38:14:39,  7.11s/it]
                                                          
{'loss': 0.6242, 'learning_rate': 0.00040360766556829964, 'epoch': 3.73}

 31%|███       | 8725/28080 [17:14:22<38:14:39,  7.11s/it]
 31%|███       | 8726/28080 [17:14:29<38:15:02,  7.11s/it]
                                                          
{'loss': 0.6345, 'learning_rate': 0.0004035849140146965, 'epoch': 3.73}

 31%|███       | 8726/28080 [17:14:29<38:15:02,  7.11s/it]
 31%|███       | 8727/28080 [17:14:36<38:12:45,  7.11s/it]
                                                          
{'loss': 0.618, 'learning_rate': 0.0004035621604178046, 'epoch': 3.73}

 31%|███       | 8727/28080 [17:14:36<38:12:45,  7.11s/it]
 31%|███       | 8728/28080 [17:14:43<38:22:14,  7.14s/it]
                                                          
{'loss': 0.6158, 'learning_rate': 0.0004035394047779265, 'epoch': 3.73}

 31%|███       | 8728/28080 [17:14:43<38:22:14,  7.14s/it]
 31%|███       | 8729/28080 [17:14:50<38:34:16,  7.18s/it]
                                                          
{'loss': 0.6338, 'learning_rate': 0.000403516647095365, 'epoch': 3.73}

 31%|███       | 8729/28080 [17:14:50<38:34:16,  7.18s/it]
 31%|███       | 8730/28080 [17:14:57<38:30:31,  7.16s/it]
                                                          
{'loss': 0.6189, 'learning_rate': 0.0004034938873704229, 'epoch': 3.73}

 31%|███       | 8730/28080 [17:14:57<38:30:31,  7.16s/it]
 31%|███       | 8731/28080 [17:15:05<38:27:31,  7.16s/it]
                                                          
{'loss': 0.6259, 'learning_rate': 0.00040347112560340303, 'epoch': 3.73}

 31%|███       | 8731/28080 [17:15:05<38:27:31,  7.16s/it]
 31%|███       | 8732/28080 [17:15:12<38:34:52,  7.18s/it]
                                                          
{'loss': 0.6386, 'learning_rate': 0.00040344836179460815, 'epoch': 3.73}

 31%|███       | 8732/28080 [17:15:12<38:34:52,  7.18s/it]
 31%|███       | 8733/28080 [17:15:19<38:33:41,  7.18s/it]
                                                          
{'loss': 0.6465, 'learning_rate': 0.0004034255959443411, 'epoch': 3.73}

 31%|███       | 8733/28080 [17:15:19<38:33:41,  7.18s/it]
 31%|███       | 8734/28080 [17:15:26<38:32:14,  7.17s/it]
                                                          
{'loss': 0.6342, 'learning_rate': 0.00040340282805290475, 'epoch': 3.73}

 31%|███       | 8734/28080 [17:15:26<38:32:14,  7.17s/it]
 31%|███       | 8735/28080 [17:15:33<38:25:01,  7.15s/it]
                                                          
{'loss': 0.6382, 'learning_rate': 0.0004033800581206021, 'epoch': 3.73}

 31%|███       | 8735/28080 [17:15:33<38:25:01,  7.15s/it]
 31%|███       | 8736/28080 [17:15:40<38:32:51,  7.17s/it]
                                                          
{'loss': 0.6225, 'learning_rate': 0.0004033572861477359, 'epoch': 3.73}

 31%|███       | 8736/28080 [17:15:40<38:32:51,  7.17s/it]
 31%|███       | 8737/28080 [17:15:47<38:20:30,  7.14s/it]
                                                          
{'loss': 0.6405, 'learning_rate': 0.00040333451213460934, 'epoch': 3.73}

 31%|███       | 8737/28080 [17:15:47<38:20:30,  7.14s/it]
 31%|███       | 8738/28080 [17:15:55<38:22:19,  7.14s/it]
                                                          
{'loss': 0.6418, 'learning_rate': 0.00040331173608152516, 'epoch': 3.73}

 31%|███       | 8738/28080 [17:15:55<38:22:19,  7.14s/it]
 31%|███       | 8739/28080 [17:16:02<38:26:04,  7.15s/it]
                                                          
{'loss': 0.6363, 'learning_rate': 0.0004032889579887866, 'epoch': 3.73}

 31%|███       | 8739/28080 [17:16:02<38:26:04,  7.15s/it]
 31%|███       | 8740/28080 [17:16:09<38:26:44,  7.16s/it]
                                                          
{'loss': 0.6147, 'learning_rate': 0.00040326617785669654, 'epoch': 3.73}

 31%|███       | 8740/28080 [17:16:09<38:26:44,  7.16s/it]
 31%|███       | 8741/28080 [17:16:16<38:19:16,  7.13s/it]
                                                          
{'loss': 0.6383, 'learning_rate': 0.0004032433956855581, 'epoch': 3.73}

 31%|███       | 8741/28080 [17:16:16<38:19:16,  7.13s/it]
 31%|███       | 8742/28080 [17:16:23<38:16:25,  7.13s/it]
                                                          
{'loss': 0.6105, 'learning_rate': 0.0004032206114756743, 'epoch': 3.73}

 31%|███       | 8742/28080 [17:16:23<38:16:25,  7.13s/it]
 31%|███       | 8743/28080 [17:16:30<38:12:55,  7.11s/it]
                                                          
{'loss': 0.6175, 'learning_rate': 0.0004031978252273485, 'epoch': 3.73}

 31%|███       | 8743/28080 [17:16:30<38:12:55,  7.11s/it]
 31%|███       | 8744/28080 [17:16:37<38:17:43,  7.13s/it]
                                                          
{'loss': 0.6355, 'learning_rate': 0.00040317503694088365, 'epoch': 3.74}

 31%|███       | 8744/28080 [17:16:37<38:17:43,  7.13s/it]
 31%|███       | 8745/28080 [17:16:44<38:12:45,  7.11s/it]
                                                          
{'loss': 0.6193, 'learning_rate': 0.0004031522466165829, 'epoch': 3.74}

 31%|███       | 8745/28080 [17:16:45<38:12:45,  7.11s/it]
 31%|███       | 8746/28080 [17:16:52<38:12:03,  7.11s/it]
                                                          
{'loss': 0.6458, 'learning_rate': 0.0004031294542547495, 'epoch': 3.74}

 31%|███       | 8746/28080 [17:16:52<38:12:03,  7.11s/it]
 31%|███       | 8747/28080 [17:16:59<38:16:33,  7.13s/it]
                                                          
{'loss': 0.6455, 'learning_rate': 0.0004031066598556867, 'epoch': 3.74}

 31%|███       | 8747/28080 [17:16:59<38:16:33,  7.13s/it]
 31%|███       | 8748/28080 [17:17:06<38:23:55,  7.15s/it]
                                                          
{'loss': 0.6381, 'learning_rate': 0.0004030838634196977, 'epoch': 3.74}

 31%|███       | 8748/28080 [17:17:06<38:23:55,  7.15s/it]
 31%|███       | 8749/28080 [17:17:13<38:19:16,  7.14s/it]
                                                          
{'loss': 0.639, 'learning_rate': 0.0004030610649470859, 'epoch': 3.74}

 31%|███       | 8749/28080 [17:17:13<38:19:16,  7.14s/it]
 31%|███       | 8750/28080 [17:17:20<38:22:30,  7.15s/it]
                                                          
{'loss': 0.6181, 'learning_rate': 0.0004030382644381545, 'epoch': 3.74}

 31%|███       | 8750/28080 [17:17:20<38:22:30,  7.15s/it]
 31%|███       | 8751/28080 [17:17:27<38:21:34,  7.14s/it]
                                                          
{'loss': 0.627, 'learning_rate': 0.0004030154618932069, 'epoch': 3.74}

 31%|███       | 8751/28080 [17:17:27<38:21:34,  7.14s/it]
 31%|███       | 8752/28080 [17:17:34<38:15:58,  7.13s/it]
                                                          
{'loss': 0.632, 'learning_rate': 0.0004029926573125464, 'epoch': 3.74}

 31%|███       | 8752/28080 [17:17:34<38:15:58,  7.13s/it]
 31%|███       | 8753/28080 [17:17:42<38:07:44,  7.10s/it]
                                                          
{'loss': 0.6278, 'learning_rate': 0.0004029698506964764, 'epoch': 3.74}

 31%|███       | 8753/28080 [17:17:42<38:07:44,  7.10s/it]
 31%|███       | 8754/28080 [17:17:49<38:16:39,  7.13s/it]
                                                          
{'loss': 0.6107, 'learning_rate': 0.0004029470420453004, 'epoch': 3.74}

 31%|███       | 8754/28080 [17:17:49<38:16:39,  7.13s/it]
 31%|███       | 8755/28080 [17:17:56<38:23:22,  7.15s/it]
                                                          
{'loss': 0.622, 'learning_rate': 0.00040292423135932176, 'epoch': 3.74}

 31%|███       | 8755/28080 [17:17:56<38:23:22,  7.15s/it]
 31%|███       | 8756/28080 [17:18:03<38:24:04,  7.15s/it]
                                                          
{'loss': 0.6303, 'learning_rate': 0.0004029014186388441, 'epoch': 3.74}

 31%|███       | 8756/28080 [17:18:03<38:24:04,  7.15s/it]
 31%|███       | 8757/28080 [17:18:10<38:26:01,  7.16s/it]
                                                          
{'loss': 0.6319, 'learning_rate': 0.00040287860388417066, 'epoch': 3.74}

 31%|███       | 8757/28080 [17:18:10<38:26:01,  7.16s/it]
 31%|███       | 8758/28080 [17:18:17<38:27:01,  7.16s/it]
                                                          
{'loss': 0.6353, 'learning_rate': 0.00040285578709560514, 'epoch': 3.74}

 31%|███       | 8758/28080 [17:18:17<38:27:01,  7.16s/it]
 31%|███       | 8759/28080 [17:18:25<38:20:01,  7.14s/it]
                                                          
{'loss': 0.6509, 'learning_rate': 0.00040283296827345105, 'epoch': 3.74}

 31%|███       | 8759/28080 [17:18:25<38:20:01,  7.14s/it]
 31%|███       | 8760/28080 [17:18:32<38:23:30,  7.15s/it]
                                                          
{'loss': 0.6238, 'learning_rate': 0.000402810147418012, 'epoch': 3.74}

 31%|███       | 8760/28080 [17:18:32<38:23:30,  7.15s/it]
 31%|███       | 8761/28080 [17:18:39<38:23:28,  7.15s/it]
                                                          
{'loss': 0.6413, 'learning_rate': 0.00040278732452959167, 'epoch': 3.74}

 31%|███       | 8761/28080 [17:18:39<38:23:28,  7.15s/it]
 31%|███       | 8762/28080 [17:18:46<38:13:13,  7.12s/it]
                                                          
{'loss': 0.6328, 'learning_rate': 0.00040276449960849353, 'epoch': 3.74}

 31%|███       | 8762/28080 [17:18:46<38:13:13,  7.12s/it]
 31%|███       | 8763/28080 [17:18:53<38:08:01,  7.11s/it]
                                                          
{'loss': 0.6347, 'learning_rate': 0.0004027416726550214, 'epoch': 3.74}

 31%|███       | 8763/28080 [17:18:53<38:08:01,  7.11s/it]
 31%|███       | 8764/28080 [17:19:00<38:13:57,  7.13s/it]
                                                          
{'loss': 0.6365, 'learning_rate': 0.0004027188436694788, 'epoch': 3.74}

 31%|███       | 8764/28080 [17:19:00<38:13:57,  7.13s/it]
 31%|███       | 8765/28080 [17:19:07<38:21:12,  7.15s/it]
                                                          
{'loss': 0.617, 'learning_rate': 0.0004026960126521695, 'epoch': 3.74}

 31%|███       | 8765/28080 [17:19:07<38:21:12,  7.15s/it]
 31%|███       | 8766/28080 [17:19:14<38:09:56,  7.11s/it]
                                                          
{'loss': 0.6175, 'learning_rate': 0.00040267317960339735, 'epoch': 3.74}

 31%|███       | 8766/28080 [17:19:14<38:09:56,  7.11s/it]
 31%|███       | 8767/28080 [17:19:21<37:58:21,  7.08s/it]
                                                          
{'loss': 0.644, 'learning_rate': 0.0004026503445234661, 'epoch': 3.75}

 31%|███       | 8767/28080 [17:19:21<37:58:21,  7.08s/it]
 31%|███       | 8768/28080 [17:19:29<38:07:12,  7.11s/it]
                                                          
{'loss': 0.6276, 'learning_rate': 0.0004026275074126794, 'epoch': 3.75}

 31%|███       | 8768/28080 [17:19:29<38:07:12,  7.11s/it]
 31%|███       | 8769/28080 [17:19:36<38:03:08,  7.09s/it]
                                                          
{'loss': 0.6165, 'learning_rate': 0.0004026046682713412, 'epoch': 3.75}

 31%|███       | 8769/28080 [17:19:36<38:03:08,  7.09s/it]
 31%|███       | 8770/28080 [17:19:43<38:06:45,  7.11s/it]
                                                          
{'loss': 0.6488, 'learning_rate': 0.00040258182709975533, 'epoch': 3.75}

 31%|███       | 8770/28080 [17:19:43<38:06:45,  7.11s/it]
 31%|███       | 8771/28080 [17:19:50<38:10:42,  7.12s/it]
                                                          
{'loss': 0.6175, 'learning_rate': 0.00040255898389822566, 'epoch': 3.75}

 31%|███       | 8771/28080 [17:19:50<38:10:42,  7.12s/it]
 31%|███       | 8772/28080 [17:19:57<38:01:35,  7.09s/it]
                                                          
{'loss': 0.6151, 'learning_rate': 0.0004025361386670561, 'epoch': 3.75}

 31%|███       | 8772/28080 [17:19:57<38:01:35,  7.09s/it]
 31%|███       | 8773/28080 [17:20:04<38:07:25,  7.11s/it]
                                                          
{'loss': 0.627, 'learning_rate': 0.0004025132914065506, 'epoch': 3.75}

 31%|███       | 8773/28080 [17:20:04<38:07:25,  7.11s/it]
 31%|███       | 8774/28080 [17:20:11<38:07:08,  7.11s/it]
                                                          
{'loss': 0.6498, 'learning_rate': 0.000402490442117013, 'epoch': 3.75}

 31%|███       | 8774/28080 [17:20:11<38:07:08,  7.11s/it]
 31%|███▏      | 8775/28080 [17:20:18<38:03:00,  7.10s/it]
                                                          
{'loss': 0.6404, 'learning_rate': 0.0004024675907987475, 'epoch': 3.75}

 31%|███▏      | 8775/28080 [17:20:18<38:03:00,  7.10s/it]
 31%|███▏      | 8776/28080 [17:20:25<38:16:25,  7.14s/it]
                                                          
{'loss': 0.6344, 'learning_rate': 0.0004024447374520579, 'epoch': 3.75}

 31%|███▏      | 8776/28080 [17:20:25<38:16:25,  7.14s/it]
 31%|███▏      | 8777/28080 [17:20:33<38:29:09,  7.18s/it]
                                                          
{'loss': 0.6372, 'learning_rate': 0.0004024218820772484, 'epoch': 3.75}

 31%|███▏      | 8777/28080 [17:20:33<38:29:09,  7.18s/it]
 31%|███▏      | 8778/28080 [17:20:40<38:20:31,  7.15s/it]
                                                          
{'loss': 0.64, 'learning_rate': 0.00040239902467462303, 'epoch': 3.75}

 31%|███▏      | 8778/28080 [17:20:40<38:20:31,  7.15s/it]
 31%|███▏      | 8779/28080 [17:20:47<38:18:32,  7.15s/it]
                                                          
{'loss': 0.6406, 'learning_rate': 0.0004023761652444858, 'epoch': 3.75}

 31%|███▏      | 8779/28080 [17:20:47<38:18:32,  7.15s/it]
 31%|███▏      | 8780/28080 [17:20:54<38:21:44,  7.16s/it]
                                                          
{'loss': 0.6151, 'learning_rate': 0.00040235330378714094, 'epoch': 3.75}

 31%|███▏      | 8780/28080 [17:20:54<38:21:44,  7.16s/it]
 31%|███▏      | 8781/28080 [17:21:01<38:13:23,  7.13s/it]
                                                          
{'loss': 0.6296, 'learning_rate': 0.0004023304403028925, 'epoch': 3.75}

 31%|███▏      | 8781/28080 [17:21:01<38:13:23,  7.13s/it]
 31%|███▏      | 8782/28080 [17:21:08<38:15:47,  7.14s/it]
                                                          
{'loss': 0.6379, 'learning_rate': 0.0004023075747920447, 'epoch': 3.75}

 31%|███▏      | 8782/28080 [17:21:08<38:15:47,  7.14s/it]
 31%|███▏      | 8783/28080 [17:21:15<38:06:53,  7.11s/it]
                                                          
{'loss': 0.6407, 'learning_rate': 0.00040228470725490177, 'epoch': 3.75}

 31%|███▏      | 8783/28080 [17:21:15<38:06:53,  7.11s/it]
 31%|███▏      | 8784/28080 [17:21:23<38:10:37,  7.12s/it]
                                                          
{'loss': 0.6353, 'learning_rate': 0.0004022618376917679, 'epoch': 3.75}

 31%|███▏      | 8784/28080 [17:21:23<38:10:37,  7.12s/it]
 31%|███▏      | 8785/28080 [17:21:30<38:10:09,  7.12s/it]
                                                          
{'loss': 0.6262, 'learning_rate': 0.00040223896610294734, 'epoch': 3.75}

 31%|███▏      | 8785/28080 [17:21:30<38:10:09,  7.12s/it]
 31%|███▏      | 8786/28080 [17:21:37<38:09:08,  7.12s/it]
                                                          
{'loss': 0.6283, 'learning_rate': 0.00040221609248874447, 'epoch': 3.75}

 31%|███▏      | 8786/28080 [17:21:37<38:09:08,  7.12s/it]
 31%|███▏      | 8787/28080 [17:21:44<38:09:25,  7.12s/it]
                                                          
{'loss': 0.637, 'learning_rate': 0.0004021932168494634, 'epoch': 3.75}

 31%|███▏      | 8787/28080 [17:21:44<38:09:25,  7.12s/it]
 31%|███▏      | 8788/28080 [17:21:51<38:07:47,  7.12s/it]
                                                          
{'loss': 0.622, 'learning_rate': 0.0004021703391854087, 'epoch': 3.75}

 31%|███▏      | 8788/28080 [17:21:51<38:07:47,  7.12s/it]
 31%|███▏      | 8789/28080 [17:21:58<38:12:16,  7.13s/it]
                                                          
{'loss': 0.6124, 'learning_rate': 0.0004021474594968846, 'epoch': 3.75}

 31%|███▏      | 8789/28080 [17:21:58<38:12:16,  7.13s/it]
 31%|███▏      | 8790/28080 [17:22:05<38:12:00,  7.13s/it]
                                                          
{'loss': 0.6417, 'learning_rate': 0.0004021245777841955, 'epoch': 3.76}

 31%|███▏      | 8790/28080 [17:22:05<38:12:00,  7.13s/it]
 31%|███▏      | 8791/28080 [17:22:12<38:12:26,  7.13s/it]
                                                          
{'loss': 0.6287, 'learning_rate': 0.0004021016940476457, 'epoch': 3.76}

 31%|███▏      | 8791/28080 [17:22:12<38:12:26,  7.13s/it]
 31%|███▏      | 8792/28080 [17:22:20<38:11:32,  7.13s/it]
                                                          
{'loss': 0.6428, 'learning_rate': 0.00040207880828754, 'epoch': 3.76}

 31%|███▏      | 8792/28080 [17:22:20<38:11:32,  7.13s/it]
 31%|███▏      | 8793/28080 [17:22:27<38:19:11,  7.15s/it]
                                                          
{'loss': 0.6296, 'learning_rate': 0.0004020559205041825, 'epoch': 3.76}

 31%|███▏      | 8793/28080 [17:22:27<38:19:11,  7.15s/it]
 31%|███▏      | 8794/28080 [17:22:34<38:18:46,  7.15s/it]
                                                          
{'loss': 0.6222, 'learning_rate': 0.0004020330306978779, 'epoch': 3.76}

 31%|███▏      | 8794/28080 [17:22:34<38:18:46,  7.15s/it]
 31%|███▏      | 8795/28080 [17:22:41<38:23:33,  7.17s/it]
                                                          
{'loss': 0.64, 'learning_rate': 0.0004020101388689307, 'epoch': 3.76}

 31%|███▏      | 8795/28080 [17:22:41<38:23:33,  7.17s/it]
 31%|███▏      | 8796/28080 [17:22:48<38:21:26,  7.16s/it]
                                                          
{'loss': 0.6221, 'learning_rate': 0.0004019872450176454, 'epoch': 3.76}

 31%|███▏      | 8796/28080 [17:22:48<38:21:26,  7.16s/it]
 31%|███▏      | 8797/28080 [17:22:55<38:21:48,  7.16s/it]
                                                          
{'loss': 0.6233, 'learning_rate': 0.00040196434914432656, 'epoch': 3.76}

 31%|███▏      | 8797/28080 [17:22:55<38:21:48,  7.16s/it]
 31%|███▏      | 8798/28080 [17:23:03<38:24:16,  7.17s/it]
                                                          
{'loss': 0.645, 'learning_rate': 0.0004019414512492789, 'epoch': 3.76}

 31%|███▏      | 8798/28080 [17:23:03<38:24:16,  7.17s/it]
 31%|███▏      | 8799/28080 [17:23:10<38:34:34,  7.20s/it]
                                                          
{'loss': 0.6346, 'learning_rate': 0.0004019185513328069, 'epoch': 3.76}

 31%|███▏      | 8799/28080 [17:23:10<38:34:34,  7.20s/it]
 31%|███▏      | 8800/28080 [17:23:17<38:28:00,  7.18s/it]
                                                          
{'loss': 0.6355, 'learning_rate': 0.0004018956493952153, 'epoch': 3.76}

 31%|███▏      | 8800/28080 [17:23:17<38:28:00,  7.18s/it]
 31%|███▏      | 8801/28080 [17:23:24<38:18:20,  7.15s/it]
                                                          
{'loss': 0.6418, 'learning_rate': 0.00040187274543680886, 'epoch': 3.76}

 31%|███▏      | 8801/28080 [17:23:24<38:18:20,  7.15s/it]
 31%|███▏      | 8802/28080 [17:23:31<38:14:46,  7.14s/it]
                                                          
{'loss': 0.6267, 'learning_rate': 0.00040184983945789216, 'epoch': 3.76}

 31%|███▏      | 8802/28080 [17:23:31<38:14:46,  7.14s/it]
 31%|███▏      | 8803/28080 [17:23:38<38:12:39,  7.14s/it]
                                                          
{'loss': 0.6601, 'learning_rate': 0.00040182693145877, 'epoch': 3.76}

 31%|███▏      | 8803/28080 [17:23:38<38:12:39,  7.14s/it]
 31%|███▏      | 8804/28080 [17:23:45<38:09:50,  7.13s/it]
                                                          
{'loss': 0.641, 'learning_rate': 0.0004018040214397472, 'epoch': 3.76}

 31%|███▏      | 8804/28080 [17:23:45<38:09:50,  7.13s/it]
 31%|███▏      | 8805/28080 [17:23:53<38:09:25,  7.13s/it]
                                                          
{'loss': 0.6176, 'learning_rate': 0.00040178110940112844, 'epoch': 3.76}

 31%|███▏      | 8805/28080 [17:23:53<38:09:25,  7.13s/it]
 31%|███▏      | 8806/28080 [17:24:00<38:06:49,  7.12s/it]
                                                          
{'loss': 0.6258, 'learning_rate': 0.00040175819534321865, 'epoch': 3.76}

 31%|███▏      | 8806/28080 [17:24:00<38:06:49,  7.12s/it]
 31%|███▏      | 8807/28080 [17:24:07<38:13:10,  7.14s/it]
                                                          
{'loss': 0.6198, 'learning_rate': 0.00040173527926632265, 'epoch': 3.76}

 31%|███▏      | 8807/28080 [17:24:07<38:13:10,  7.14s/it]
 31%|███▏      | 8808/28080 [17:24:14<38:15:16,  7.15s/it]
                                                          
{'loss': 0.6292, 'learning_rate': 0.00040171236117074525, 'epoch': 3.76}

 31%|███▏      | 8808/28080 [17:24:14<38:15:16,  7.15s/it]
 31%|███▏      | 8809/28080 [17:24:21<38:05:20,  7.12s/it]
                                                          
{'loss': 0.6593, 'learning_rate': 0.0004016894410567914, 'epoch': 3.76}

 31%|███▏      | 8809/28080 [17:24:21<38:05:20,  7.12s/it]
 31%|███▏      | 8810/28080 [17:24:28<38:11:24,  7.13s/it]
                                                          
{'loss': 0.6319, 'learning_rate': 0.000401666518924766, 'epoch': 3.76}

 31%|███▏      | 8810/28080 [17:24:28<38:11:24,  7.13s/it]
 31%|███▏      | 8811/28080 [17:24:35<38:16:25,  7.15s/it]
                                                          
{'loss': 0.6176, 'learning_rate': 0.00040164359477497415, 'epoch': 3.76}

 31%|███▏      | 8811/28080 [17:24:35<38:16:25,  7.15s/it]
 31%|███▏      | 8812/28080 [17:24:43<38:21:01,  7.17s/it]
                                                          
{'loss': 0.6433, 'learning_rate': 0.0004016206686077206, 'epoch': 3.76}

 31%|███▏      | 8812/28080 [17:24:43<38:21:01,  7.17s/it]
 31%|███▏      | 8813/28080 [17:24:50<38:23:07,  7.17s/it]
                                                          
{'loss': 0.6431, 'learning_rate': 0.0004015977404233105, 'epoch': 3.76}

 31%|███▏      | 8813/28080 [17:24:50<38:23:07,  7.17s/it]
 31%|███▏      | 8814/28080 [17:24:57<38:21:54,  7.17s/it]
                                                          
{'loss': 0.6501, 'learning_rate': 0.0004015748102220489, 'epoch': 3.77}

 31%|███▏      | 8814/28080 [17:24:57<38:21:54,  7.17s/it]
 31%|███▏      | 8815/28080 [17:25:04<38:23:50,  7.18s/it]
                                                          
{'loss': 0.6254, 'learning_rate': 0.00040155187800424075, 'epoch': 3.77}

 31%|███▏      | 8815/28080 [17:25:04<38:23:50,  7.18s/it]
 31%|███▏      | 8816/28080 [17:25:11<38:32:48,  7.20s/it]
                                                          
{'loss': 0.6335, 'learning_rate': 0.00040152894377019124, 'epoch': 3.77}

 31%|███▏      | 8816/28080 [17:25:11<38:32:48,  7.20s/it]
 31%|███▏      | 8817/28080 [17:25:19<38:39:10,  7.22s/it]
                                                          
{'loss': 0.6141, 'learning_rate': 0.0004015060075202054, 'epoch': 3.77}

 31%|███▏      | 8817/28080 [17:25:19<38:39:10,  7.22s/it]
 31%|███▏      | 8818/28080 [17:25:26<38:29:28,  7.19s/it]
                                                          
{'loss': 0.6617, 'learning_rate': 0.00040148306925458856, 'epoch': 3.77}

 31%|███▏      | 8818/28080 [17:25:26<38:29:28,  7.19s/it]
 31%|███▏      | 8819/28080 [17:25:33<38:34:44,  7.21s/it]
                                                          
{'loss': 0.6355, 'learning_rate': 0.0004014601289736457, 'epoch': 3.77}

 31%|███▏      | 8819/28080 [17:25:33<38:34:44,  7.21s/it]
 31%|███▏      | 8820/28080 [17:25:40<38:30:27,  7.20s/it]
                                                          
{'loss': 0.6281, 'learning_rate': 0.00040143718667768203, 'epoch': 3.77}

 31%|███▏      | 8820/28080 [17:25:40<38:30:27,  7.20s/it]
 31%|███▏      | 8821/28080 [17:25:47<38:32:12,  7.20s/it]
                                                          
{'loss': 0.6278, 'learning_rate': 0.0004014142423670029, 'epoch': 3.77}

 31%|███▏      | 8821/28080 [17:25:47<38:32:12,  7.20s/it]
 31%|███▏      | 8822/28080 [17:25:55<38:24:56,  7.18s/it]
                                                          
{'loss': 0.6345, 'learning_rate': 0.0004013912960419134, 'epoch': 3.77}

 31%|███▏      | 8822/28080 [17:25:55<38:24:56,  7.18s/it]
 31%|███▏      | 8823/28080 [17:26:02<38:18:23,  7.16s/it]
                                                          
{'loss': 0.617, 'learning_rate': 0.000401368347702719, 'epoch': 3.77}

 31%|███▏      | 8823/28080 [17:26:02<38:18:23,  7.16s/it]
 31%|███▏      | 8824/28080 [17:26:09<38:19:46,  7.17s/it]
                                                          
{'loss': 0.6443, 'learning_rate': 0.00040134539734972474, 'epoch': 3.77}

 31%|███▏      | 8824/28080 [17:26:09<38:19:46,  7.17s/it]
 31%|███▏      | 8825/28080 [17:26:16<38:26:12,  7.19s/it]
                                                          
{'loss': 0.6092, 'learning_rate': 0.0004013224449832362, 'epoch': 3.77}

 31%|███▏      | 8825/28080 [17:26:16<38:26:12,  7.19s/it]
 31%|███▏      | 8826/28080 [17:26:23<38:32:59,  7.21s/it]
                                                          
{'loss': 0.6256, 'learning_rate': 0.00040129949060355863, 'epoch': 3.77}

 31%|███▏      | 8826/28080 [17:26:23<38:32:59,  7.21s/it]
 31%|███▏      | 8827/28080 [17:26:31<38:28:06,  7.19s/it]
                                                          
{'loss': 0.6167, 'learning_rate': 0.00040127653421099743, 'epoch': 3.77}

 31%|███▏      | 8827/28080 [17:26:31<38:28:06,  7.19s/it]
 31%|███▏      | 8828/28080 [17:26:38<38:22:43,  7.18s/it]
                                                          
{'loss': 0.6248, 'learning_rate': 0.000401253575805858, 'epoch': 3.77}

 31%|███▏      | 8828/28080 [17:26:38<38:22:43,  7.18s/it]
 31%|███▏      | 8829/28080 [17:26:45<38:23:05,  7.18s/it]
                                                          
{'loss': 0.6175, 'learning_rate': 0.00040123061538844575, 'epoch': 3.77}

 31%|███▏      | 8829/28080 [17:26:45<38:23:05,  7.18s/it]
 31%|███▏      | 8830/28080 [17:26:52<38:13:45,  7.15s/it]
                                                          
{'loss': 0.6288, 'learning_rate': 0.0004012076529590662, 'epoch': 3.77}

 31%|███▏      | 8830/28080 [17:26:52<38:13:45,  7.15s/it]
 31%|███▏      | 8831/28080 [17:26:59<38:13:44,  7.15s/it]
                                                          
{'loss': 0.6278, 'learning_rate': 0.00040118468851802483, 'epoch': 3.77}

 31%|███▏      | 8831/28080 [17:26:59<38:13:44,  7.15s/it]
 31%|███▏      | 8832/28080 [17:27:06<38:11:34,  7.14s/it]
                                                          
{'loss': 0.6146, 'learning_rate': 0.00040116172206562705, 'epoch': 3.77}

 31%|███▏      | 8832/28080 [17:27:06<38:11:34,  7.14s/it]
 31%|███▏      | 8833/28080 [17:27:13<38:06:53,  7.13s/it]
                                                          
{'loss': 0.6267, 'learning_rate': 0.00040113875360217865, 'epoch': 3.77}

 31%|███▏      | 8833/28080 [17:27:13<38:06:53,  7.13s/it]
 31%|███▏      | 8834/28080 [17:27:20<37:56:33,  7.10s/it]
                                                          
{'loss': 0.6153, 'learning_rate': 0.000401115783127985, 'epoch': 3.77}

 31%|███▏      | 8834/28080 [17:27:20<37:56:33,  7.10s/it]
 31%|███▏      | 8835/28080 [17:27:28<38:03:31,  7.12s/it]
                                                          
{'loss': 0.6253, 'learning_rate': 0.00040109281064335174, 'epoch': 3.77}

 31%|███▏      | 8835/28080 [17:27:28<38:03:31,  7.12s/it]
 31%|███▏      | 8836/28080 [17:27:35<38:06:33,  7.13s/it]
                                                          
{'loss': 0.6322, 'learning_rate': 0.0004010698361485845, 'epoch': 3.77}

 31%|███▏      | 8836/28080 [17:27:35<38:06:33,  7.13s/it]
 31%|███▏      | 8837/28080 [17:27:42<38:09:50,  7.14s/it]
                                                          
{'loss': 0.6269, 'learning_rate': 0.00040104685964398903, 'epoch': 3.78}

 31%|███▏      | 8837/28080 [17:27:42<38:09:50,  7.14s/it]
 31%|███▏      | 8838/28080 [17:27:49<38:15:14,  7.16s/it]
                                                          
{'loss': 0.6152, 'learning_rate': 0.0004010238811298708, 'epoch': 3.78}

 31%|███▏      | 8838/28080 [17:27:49<38:15:14,  7.16s/it]
 31%|███▏      | 8839/28080 [17:27:56<38:17:11,  7.16s/it]
                                                          
{'loss': 0.6126, 'learning_rate': 0.0004010009006065357, 'epoch': 3.78}

 31%|███▏      | 8839/28080 [17:27:56<38:17:11,  7.16s/it]
 31%|███▏      | 8840/28080 [17:28:03<38:22:03,  7.18s/it]
                                                          
{'loss': 0.6227, 'learning_rate': 0.00040097791807428934, 'epoch': 3.78}

 31%|███▏      | 8840/28080 [17:28:03<38:22:03,  7.18s/it]
 31%|███▏      | 8841/28080 [17:28:11<38:18:34,  7.17s/it]
                                                          
{'loss': 0.6188, 'learning_rate': 0.0004009549335334376, 'epoch': 3.78}

 31%|███▏      | 8841/28080 [17:28:11<38:18:34,  7.17s/it]
 31%|███▏      | 8842/28080 [17:28:18<38:05:48,  7.13s/it]
                                                          
{'loss': 0.615, 'learning_rate': 0.00040093194698428617, 'epoch': 3.78}

 31%|███▏      | 8842/28080 [17:28:18<38:05:48,  7.13s/it]
 31%|███▏      | 8843/28080 [17:28:25<37:59:05,  7.11s/it]
                                                          
{'loss': 0.6302, 'learning_rate': 0.00040090895842714093, 'epoch': 3.78}

 31%|███▏      | 8843/28080 [17:28:25<37:59:05,  7.11s/it]
 31%|███▏      | 8844/28080 [17:28:32<37:56:45,  7.10s/it]
                                                          
{'loss': 0.636, 'learning_rate': 0.0004008859678623076, 'epoch': 3.78}

 31%|███▏      | 8844/28080 [17:28:32<37:56:45,  7.10s/it]
 31%|███▏      | 8845/28080 [17:28:39<37:58:55,  7.11s/it]
                                                          
{'loss': 0.6013, 'learning_rate': 0.0004008629752900922, 'epoch': 3.78}

 31%|███▏      | 8845/28080 [17:28:39<37:58:55,  7.11s/it]
 32%|███▏      | 8846/28080 [17:28:46<38:06:54,  7.13s/it]
                                                          
{'loss': 0.6288, 'learning_rate': 0.00040083998071080055, 'epoch': 3.78}

 32%|███▏      | 8846/28080 [17:28:46<38:06:54,  7.13s/it]
 32%|███▏      | 8847/28080 [17:28:53<38:01:28,  7.12s/it]
                                                          
{'loss': 0.6293, 'learning_rate': 0.00040081698412473853, 'epoch': 3.78}

 32%|███▏      | 8847/28080 [17:28:53<38:01:28,  7.12s/it]
 32%|███▏      | 8848/28080 [17:29:00<38:02:56,  7.12s/it]
                                                          
{'loss': 0.6182, 'learning_rate': 0.00040079398553221214, 'epoch': 3.78}

 32%|███▏      | 8848/28080 [17:29:00<38:02:56,  7.12s/it]
 32%|███▏      | 8849/28080 [17:29:07<38:01:31,  7.12s/it]
                                                          
{'loss': 0.6112, 'learning_rate': 0.00040077098493352737, 'epoch': 3.78}

 32%|███▏      | 8849/28080 [17:29:07<38:01:31,  7.12s/it]
 32%|███▏      | 8850/28080 [17:29:14<37:56:20,  7.10s/it]
                                                          
{'loss': 0.634, 'learning_rate': 0.00040074798232899014, 'epoch': 3.78}

 32%|███▏      | 8850/28080 [17:29:14<37:56:20,  7.10s/it]
 32%|███▏      | 8851/28080 [17:29:22<37:59:32,  7.11s/it]
                                                          
{'loss': 0.62, 'learning_rate': 0.0004007249777189065, 'epoch': 3.78}

 32%|███▏      | 8851/28080 [17:29:22<37:59:32,  7.11s/it]
 32%|███▏      | 8852/28080 [17:29:29<38:08:11,  7.14s/it]
                                                          
{'loss': 0.6356, 'learning_rate': 0.0004007019711035826, 'epoch': 3.78}

 32%|███▏      | 8852/28080 [17:29:29<38:08:11,  7.14s/it]
 32%|███▏      | 8853/28080 [17:29:36<38:01:18,  7.12s/it]
                                                          
{'loss': 0.6238, 'learning_rate': 0.0004006789624833244, 'epoch': 3.78}

 32%|███▏      | 8853/28080 [17:29:36<38:01:18,  7.12s/it]
 32%|███▏      | 8854/28080 [17:29:43<38:11:55,  7.15s/it]
                                                          
{'loss': 0.6019, 'learning_rate': 0.0004006559518584381, 'epoch': 3.78}

 32%|███▏      | 8854/28080 [17:29:43<38:11:55,  7.15s/it]
 32%|███▏      | 8855/28080 [17:29:50<38:16:31,  7.17s/it]
                                                          
{'loss': 0.6492, 'learning_rate': 0.0004006329392292297, 'epoch': 3.78}

 32%|███▏      | 8855/28080 [17:29:50<38:16:31,  7.17s/it]
 32%|███▏      | 8856/28080 [17:29:57<38:16:39,  7.17s/it]
                                                          
{'loss': 0.6111, 'learning_rate': 0.0004006099245960055, 'epoch': 3.78}

 32%|███▏      | 8856/28080 [17:29:57<38:16:39,  7.17s/it]
 32%|███▏      | 8857/28080 [17:30:05<38:09:04,  7.14s/it]
                                                          
{'loss': 0.6423, 'learning_rate': 0.0004005869079590716, 'epoch': 3.78}

 32%|███▏      | 8857/28080 [17:30:05<38:09:04,  7.14s/it]
 32%|███▏      | 8858/28080 [17:30:12<38:05:25,  7.13s/it]
                                                          
{'loss': 0.6167, 'learning_rate': 0.00040056388931873426, 'epoch': 3.78}

 32%|███▏      | 8858/28080 [17:30:12<38:05:25,  7.13s/it]
 32%|███▏      | 8859/28080 [17:30:19<38:04:13,  7.13s/it]
                                                          
{'loss': 0.6271, 'learning_rate': 0.0004005408686752997, 'epoch': 3.78}

 32%|███▏      | 8859/28080 [17:30:19<38:04:13,  7.13s/it]
 32%|███▏      | 8860/28080 [17:30:26<37:59:47,  7.12s/it]
                                                          
{'loss': 0.6263, 'learning_rate': 0.0004005178460290742, 'epoch': 3.78}

 32%|███▏      | 8860/28080 [17:30:26<37:59:47,  7.12s/it]
 32%|███▏      | 8861/28080 [17:30:33<38:05:40,  7.14s/it]
                                                          
{'loss': 0.6482, 'learning_rate': 0.00040049482138036405, 'epoch': 3.79}

 32%|███▏      | 8861/28080 [17:30:33<38:05:40,  7.14s/it]
 32%|███▏      | 8862/28080 [17:30:40<38:07:32,  7.14s/it]
                                                          
{'loss': 0.6293, 'learning_rate': 0.00040047179472947554, 'epoch': 3.79}

 32%|███▏      | 8862/28080 [17:30:40<38:07:32,  7.14s/it]
 32%|███▏      | 8863/28080 [17:30:47<38:08:47,  7.15s/it]
                                                          
{'loss': 0.632, 'learning_rate': 0.000400448766076715, 'epoch': 3.79}

 32%|███▏      | 8863/28080 [17:30:47<38:08:47,  7.15s/it]
 32%|███▏      | 8864/28080 [17:30:55<38:09:57,  7.15s/it]
                                                          
{'loss': 0.632, 'learning_rate': 0.0004004257354223889, 'epoch': 3.79}

 32%|███▏      | 8864/28080 [17:30:55<38:09:57,  7.15s/it]
 32%|███▏      | 8865/28080 [17:31:02<38:16:19,  7.17s/it]
                                                          
{'loss': 0.6184, 'learning_rate': 0.0004004027027668035, 'epoch': 3.79}

 32%|███▏      | 8865/28080 [17:31:02<38:16:19,  7.17s/it]
 32%|███▏      | 8866/28080 [17:31:09<38:13:56,  7.16s/it]
                                                          
{'loss': 0.6308, 'learning_rate': 0.0004003796681102654, 'epoch': 3.79}

 32%|███▏      | 8866/28080 [17:31:09<38:13:56,  7.16s/it]
 32%|███▏      | 8867/28080 [17:31:16<38:05:20,  7.14s/it]
                                                          
{'loss': 0.6156, 'learning_rate': 0.0004003566314530809, 'epoch': 3.79}

 32%|███▏      | 8867/28080 [17:31:16<38:05:20,  7.14s/it]
 32%|███▏      | 8868/28080 [17:31:23<38:03:25,  7.13s/it]
                                                          
{'loss': 0.6373, 'learning_rate': 0.00040033359279555646, 'epoch': 3.79}

 32%|███▏      | 8868/28080 [17:31:23<38:03:25,  7.13s/it]
 32%|███▏      | 8869/28080 [17:31:30<38:04:45,  7.14s/it]
                                                          
{'loss': 0.6248, 'learning_rate': 0.0004003105521379987, 'epoch': 3.79}

 32%|███▏      | 8869/28080 [17:31:30<38:04:45,  7.14s/it]
 32%|███▏      | 8870/28080 [17:31:37<38:09:49,  7.15s/it]
                                                          
{'loss': 0.6333, 'learning_rate': 0.0004002875094807142, 'epoch': 3.79}

 32%|███▏      | 8870/28080 [17:31:37<38:09:49,  7.15s/it]
 32%|███▏      | 8871/28080 [17:31:45<38:14:03,  7.17s/it]
                                                          
{'loss': 0.6347, 'learning_rate': 0.00040026446482400936, 'epoch': 3.79}

 32%|███▏      | 8871/28080 [17:31:45<38:14:03,  7.17s/it]
 32%|███▏      | 8872/28080 [17:31:52<38:13:54,  7.17s/it]
                                                          
{'loss': 0.5918, 'learning_rate': 0.00040024141816819085, 'epoch': 3.79}

 32%|███▏      | 8872/28080 [17:31:52<38:13:54,  7.17s/it]
 32%|███▏      | 8873/28080 [17:31:59<38:17:49,  7.18s/it]
                                                          
{'loss': 0.6318, 'learning_rate': 0.0004002183695135653, 'epoch': 3.79}

 32%|███▏      | 8873/28080 [17:31:59<38:17:49,  7.18s/it]
 32%|███▏      | 8874/28080 [17:32:06<38:13:21,  7.16s/it]
                                                          
{'loss': 0.6534, 'learning_rate': 0.00040019531886043925, 'epoch': 3.79}

 32%|███▏      | 8874/28080 [17:32:06<38:13:21,  7.16s/it]
 32%|███▏      | 8875/28080 [17:32:13<38:08:33,  7.15s/it]
                                                          
{'loss': 0.6042, 'learning_rate': 0.00040017226620911944, 'epoch': 3.79}

 32%|███▏      | 8875/28080 [17:32:13<38:08:33,  7.15s/it]
 32%|███▏      | 8876/28080 [17:32:20<38:08:17,  7.15s/it]
                                                          
{'loss': 0.643, 'learning_rate': 0.0004001492115599126, 'epoch': 3.79}

 32%|███▏      | 8876/28080 [17:32:20<38:08:17,  7.15s/it]
 32%|███▏      | 8877/28080 [17:32:27<37:58:46,  7.12s/it]
                                                          
{'loss': 0.6419, 'learning_rate': 0.0004001261549131253, 'epoch': 3.79}

 32%|███▏      | 8877/28080 [17:32:27<37:58:46,  7.12s/it]
 32%|███▏      | 8878/28080 [17:32:35<38:02:23,  7.13s/it]
                                                          
{'loss': 0.6304, 'learning_rate': 0.0004001030962690645, 'epoch': 3.79}

 32%|███▏      | 8878/28080 [17:32:35<38:02:23,  7.13s/it]
 32%|███▏      | 8879/28080 [17:32:42<37:53:04,  7.10s/it]
                                                          
{'loss': 0.6523, 'learning_rate': 0.00040008003562803685, 'epoch': 3.79}

 32%|███▏      | 8879/28080 [17:32:42<37:53:04,  7.10s/it]
 32%|███▏      | 8880/28080 [17:32:49<37:49:23,  7.09s/it]
                                                          
{'loss': 0.6543, 'learning_rate': 0.000400056972990349, 'epoch': 3.79}

 32%|███▏      | 8880/28080 [17:32:49<37:49:23,  7.09s/it]
 32%|███▏      | 8881/28080 [17:32:56<37:51:43,  7.10s/it]
                                                          
{'loss': 0.6399, 'learning_rate': 0.0004000339083563081, 'epoch': 3.79}

 32%|███▏      | 8881/28080 [17:32:56<37:51:43,  7.10s/it]
 32%|███▏      | 8882/28080 [17:33:03<37:55:50,  7.11s/it]
                                                          
{'loss': 0.6464, 'learning_rate': 0.0004000108417262208, 'epoch': 3.79}

 32%|███▏      | 8882/28080 [17:33:03<37:55:50,  7.11s/it]
 32%|███▏      | 8883/28080 [17:33:10<37:56:33,  7.12s/it]
                                                          
{'loss': 0.6309, 'learning_rate': 0.00039998777310039396, 'epoch': 3.79}

 32%|███▏      | 8883/28080 [17:33:10<37:56:33,  7.12s/it]
 32%|███▏      | 8884/28080 [17:33:17<38:02:50,  7.14s/it]
                                                          
{'loss': 0.6323, 'learning_rate': 0.0003999647024791346, 'epoch': 3.8}

 32%|███▏      | 8884/28080 [17:33:17<38:02:50,  7.14s/it]
 32%|███▏      | 8885/28080 [17:33:24<37:55:44,  7.11s/it]
                                                          
{'loss': 0.6432, 'learning_rate': 0.00039994162986274953, 'epoch': 3.8}

 32%|███▏      | 8885/28080 [17:33:24<37:55:44,  7.11s/it]
 32%|███▏      | 8886/28080 [17:33:31<37:57:26,  7.12s/it]
                                                          
{'loss': 0.6166, 'learning_rate': 0.0003999185552515457, 'epoch': 3.8}

 32%|███▏      | 8886/28080 [17:33:31<37:57:26,  7.12s/it]
 32%|███▏      | 8887/28080 [17:33:39<37:50:26,  7.10s/it]
                                                          
{'loss': 0.632, 'learning_rate': 0.0003998954786458303, 'epoch': 3.8}

 32%|███▏      | 8887/28080 [17:33:39<37:50:26,  7.10s/it]
 32%|███▏      | 8888/28080 [17:33:46<37:54:53,  7.11s/it]
                                                          
{'loss': 0.6449, 'learning_rate': 0.0003998724000459101, 'epoch': 3.8}

 32%|███▏      | 8888/28080 [17:33:46<37:54:53,  7.11s/it]
 32%|███▏      | 8889/28080 [17:33:53<38:05:01,  7.14s/it]
                                                          
{'loss': 0.6458, 'learning_rate': 0.00039984931945209225, 'epoch': 3.8}

 32%|███▏      | 8889/28080 [17:33:53<38:05:01,  7.14s/it]
 32%|███▏      | 8890/28080 [17:34:00<38:08:59,  7.16s/it]
                                                          
{'loss': 0.6071, 'learning_rate': 0.0003998262368646838, 'epoch': 3.8}

 32%|███▏      | 8890/28080 [17:34:00<38:08:59,  7.16s/it]
 32%|███▏      | 8891/28080 [17:34:07<38:10:40,  7.16s/it]
                                                          
{'loss': 0.6438, 'learning_rate': 0.00039980315228399185, 'epoch': 3.8}

 32%|███▏      | 8891/28080 [17:34:07<38:10:40,  7.16s/it]
 32%|███▏      | 8892/28080 [17:34:14<38:11:29,  7.17s/it]
                                                          
{'loss': 0.6448, 'learning_rate': 0.00039978006571032344, 'epoch': 3.8}

 32%|███▏      | 8892/28080 [17:34:14<38:11:29,  7.17s/it]
 32%|███▏      | 8893/28080 [17:34:22<38:09:55,  7.16s/it]
                                                          
{'loss': 0.6375, 'learning_rate': 0.00039975697714398587, 'epoch': 3.8}

 32%|███▏      | 8893/28080 [17:34:22<38:09:55,  7.16s/it]
 32%|███▏      | 8894/28080 [17:34:29<38:08:50,  7.16s/it]
                                                          
{'loss': 0.6495, 'learning_rate': 0.0003997338865852861, 'epoch': 3.8}

 32%|███▏      | 8894/28080 [17:34:29<38:08:50,  7.16s/it]
 32%|███▏      | 8895/28080 [17:34:36<38:07:39,  7.15s/it]
                                                          
{'loss': 0.6089, 'learning_rate': 0.0003997107940345316, 'epoch': 3.8}

 32%|███▏      | 8895/28080 [17:34:36<38:07:39,  7.15s/it]
 32%|███▏      | 8896/28080 [17:34:43<38:12:33,  7.17s/it]
                                                          
{'loss': 0.6278, 'learning_rate': 0.0003996876994920293, 'epoch': 3.8}

 32%|███▏      | 8896/28080 [17:34:43<38:12:33,  7.17s/it]
 32%|███▏      | 8897/28080 [17:34:50<38:08:38,  7.16s/it]
                                                          
{'loss': 0.6395, 'learning_rate': 0.00039966460295808666, 'epoch': 3.8}

 32%|███▏      | 8897/28080 [17:34:50<38:08:38,  7.16s/it]
 32%|███▏      | 8898/28080 [17:34:57<37:54:01,  7.11s/it]
                                                          
{'loss': 0.6289, 'learning_rate': 0.00039964150443301083, 'epoch': 3.8}

 32%|███▏      | 8898/28080 [17:34:57<37:54:01,  7.11s/it]
 32%|███▏      | 8899/28080 [17:35:04<38:00:14,  7.13s/it]
                                                          
{'loss': 0.6276, 'learning_rate': 0.00039961840391710915, 'epoch': 3.8}

 32%|███▏      | 8899/28080 [17:35:04<38:00:14,  7.13s/it]
 32%|███▏      | 8900/28080 [17:35:12<38:00:05,  7.13s/it]
                                                          
{'loss': 0.6276, 'learning_rate': 0.000399595301410689, 'epoch': 3.8}

 32%|███▏      | 8900/28080 [17:35:12<38:00:05,  7.13s/it]
 32%|███▏      | 8901/28080 [17:35:19<38:09:39,  7.16s/it]
                                                          
{'loss': 0.6278, 'learning_rate': 0.00039957219691405765, 'epoch': 3.8}

 32%|███▏      | 8901/28080 [17:35:19<38:09:39,  7.16s/it]
 32%|███▏      | 8902/28080 [17:35:26<38:02:50,  7.14s/it]
                                                          
{'loss': 0.6229, 'learning_rate': 0.0003995490904275226, 'epoch': 3.8}

 32%|███▏      | 8902/28080 [17:35:26<38:02:50,  7.14s/it]
 32%|███▏      | 8903/28080 [17:35:33<38:02:55,  7.14s/it]
                                                          
{'loss': 0.6052, 'learning_rate': 0.0003995259819513911, 'epoch': 3.8}

 32%|███▏      | 8903/28080 [17:35:33<38:02:55,  7.14s/it]
 32%|███▏      | 8904/28080 [17:35:40<38:06:41,  7.15s/it]
                                                          
{'loss': 0.6349, 'learning_rate': 0.0003995028714859707, 'epoch': 3.8}

 32%|███▏      | 8904/28080 [17:35:40<38:06:41,  7.15s/it]
 32%|███▏      | 8905/28080 [17:35:47<38:01:41,  7.14s/it]
                                                          
{'loss': 0.6115, 'learning_rate': 0.00039947975903156883, 'epoch': 3.8}

 32%|███▏      | 8905/28080 [17:35:47<38:01:41,  7.14s/it]
 32%|███▏      | 8906/28080 [17:35:54<38:00:40,  7.14s/it]
                                                          
{'loss': 0.644, 'learning_rate': 0.00039945664458849295, 'epoch': 3.8}

 32%|███▏      | 8906/28080 [17:35:54<38:00:40,  7.14s/it]
 32%|███▏      | 8907/28080 [17:36:02<38:03:21,  7.15s/it]
                                                          
{'loss': 0.6209, 'learning_rate': 0.00039943352815705063, 'epoch': 3.8}

 32%|███▏      | 8907/28080 [17:36:02<38:03:21,  7.15s/it]
 32%|███▏      | 8908/28080 [17:36:09<38:06:30,  7.16s/it]
                                                          
{'loss': 0.6358, 'learning_rate': 0.0003994104097375494, 'epoch': 3.81}

 32%|███▏      | 8908/28080 [17:36:09<38:06:30,  7.16s/it]
 32%|███▏      | 8909/28080 [17:36:16<38:05:18,  7.15s/it]
                                                          
{'loss': 0.6482, 'learning_rate': 0.00039938728933029677, 'epoch': 3.81}

 32%|███▏      | 8909/28080 [17:36:16<38:05:18,  7.15s/it]
 32%|███▏      | 8910/28080 [17:36:23<37:57:06,  7.13s/it]
                                                          
{'loss': 0.6614, 'learning_rate': 0.0003993641669356004, 'epoch': 3.81}

 32%|███▏      | 8910/28080 [17:36:23<37:57:06,  7.13s/it]
 32%|███▏      | 8911/28080 [17:36:30<37:48:51,  7.10s/it]
                                                          
{'loss': 0.6254, 'learning_rate': 0.0003993410425537678, 'epoch': 3.81}

 32%|███▏      | 8911/28080 [17:36:30<37:48:51,  7.10s/it]
 32%|███▏      | 8912/28080 [17:36:37<37:48:33,  7.10s/it]
                                                          
{'loss': 0.6346, 'learning_rate': 0.0003993179161851068, 'epoch': 3.81}

 32%|███▏      | 8912/28080 [17:36:37<37:48:33,  7.10s/it]
 32%|███▏      | 8913/28080 [17:36:44<37:53:38,  7.12s/it]
                                                          
{'loss': 0.6292, 'learning_rate': 0.0003992947878299249, 'epoch': 3.81}

 32%|███▏      | 8913/28080 [17:36:44<37:53:38,  7.12s/it]
 32%|███▏      | 8914/28080 [17:36:51<37:50:40,  7.11s/it]
                                                          
{'loss': 0.6547, 'learning_rate': 0.0003992716574885299, 'epoch': 3.81}

 32%|███▏      | 8914/28080 [17:36:51<37:50:40,  7.11s/it]
 32%|███▏      | 8915/28080 [17:36:58<37:53:00,  7.12s/it]
                                                          
{'loss': 0.6154, 'learning_rate': 0.00039924852516122944, 'epoch': 3.81}

 32%|███▏      | 8915/28080 [17:36:58<37:53:00,  7.12s/it]
 32%|███▏      | 8916/28080 [17:37:06<37:44:25,  7.09s/it]
                                                          
{'loss': 0.675, 'learning_rate': 0.0003992253908483314, 'epoch': 3.81}

 32%|███▏      | 8916/28080 [17:37:06<37:44:25,  7.09s/it]
 32%|███▏      | 8917/28080 [17:37:13<37:52:04,  7.11s/it]
                                                          
{'loss': 0.6287, 'learning_rate': 0.0003992022545501435, 'epoch': 3.81}

 32%|███▏      | 8917/28080 [17:37:13<37:52:04,  7.11s/it]
 32%|███▏      | 8918/28080 [17:37:20<38:02:28,  7.15s/it]
                                                          
{'loss': 0.6312, 'learning_rate': 0.0003991791162669735, 'epoch': 3.81}

 32%|███▏      | 8918/28080 [17:37:20<38:02:28,  7.15s/it]
 32%|███▏      | 8919/28080 [17:37:27<38:01:00,  7.14s/it]
                                                          
{'loss': 0.6359, 'learning_rate': 0.0003991559759991291, 'epoch': 3.81}

 32%|███▏      | 8919/28080 [17:37:27<38:01:00,  7.14s/it]
 32%|███▏      | 8920/28080 [17:37:34<37:56:59,  7.13s/it]
                                                          
{'loss': 0.6078, 'learning_rate': 0.0003991328337469186, 'epoch': 3.81}

 32%|███▏      | 8920/28080 [17:37:34<37:56:59,  7.13s/it]
 32%|███▏      | 8921/28080 [17:37:41<38:01:44,  7.15s/it]
                                                          
{'loss': 0.6251, 'learning_rate': 0.00039910968951064934, 'epoch': 3.81}

 32%|███▏      | 8921/28080 [17:37:41<38:01:44,  7.15s/it]
 32%|███▏      | 8922/28080 [17:37:49<38:04:22,  7.15s/it]
                                                          
{'loss': 0.6583, 'learning_rate': 0.0003990865432906296, 'epoch': 3.81}

 32%|███▏      | 8922/28080 [17:37:49<38:04:22,  7.15s/it]
 32%|███▏      | 8923/28080 [17:37:56<37:57:39,  7.13s/it]
                                                          
{'loss': 0.6365, 'learning_rate': 0.00039906339508716715, 'epoch': 3.81}

 32%|███▏      | 8923/28080 [17:37:56<37:57:39,  7.13s/it]
 32%|███▏      | 8924/28080 [17:38:03<37:39:59,  7.08s/it]
                                                          
{'loss': 0.6559, 'learning_rate': 0.0003990402449005701, 'epoch': 3.81}

 32%|███▏      | 8924/28080 [17:38:03<37:39:59,  7.08s/it]
 32%|███▏      | 8925/28080 [17:38:10<37:47:54,  7.10s/it]
                                                          
{'loss': 0.6215, 'learning_rate': 0.00039901709273114627, 'epoch': 3.81}

 32%|███▏      | 8925/28080 [17:38:10<37:47:54,  7.10s/it]
 32%|███▏      | 8926/28080 [17:38:17<37:58:21,  7.14s/it]
                                                          
{'loss': 0.6587, 'learning_rate': 0.0003989939385792038, 'epoch': 3.81}

 32%|███▏      | 8926/28080 [17:38:17<37:58:21,  7.14s/it]
 32%|███▏      | 8927/28080 [17:38:24<38:01:03,  7.15s/it]
                                                          
{'loss': 0.6207, 'learning_rate': 0.0003989707824450507, 'epoch': 3.81}

 32%|███▏      | 8927/28080 [17:38:24<38:01:03,  7.15s/it]
 32%|███▏      | 8928/28080 [17:38:31<38:02:51,  7.15s/it]
                                                          
{'loss': 0.6245, 'learning_rate': 0.000398947624328995, 'epoch': 3.81}

 32%|███▏      | 8928/28080 [17:38:31<38:02:51,  7.15s/it]
 32%|███▏      | 8929/28080 [17:38:38<37:58:14,  7.14s/it]
                                                          
{'loss': 0.6486, 'learning_rate': 0.0003989244642313448, 'epoch': 3.81}

 32%|███▏      | 8929/28080 [17:38:38<37:58:14,  7.14s/it]
 32%|███▏      | 8930/28080 [17:38:46<38:01:20,  7.15s/it]
                                                          
{'loss': 0.6222, 'learning_rate': 0.0003989013021524083, 'epoch': 3.81}

 32%|███▏      | 8930/28080 [17:38:46<38:01:20,  7.15s/it]
 32%|███▏      | 8931/28080 [17:38:53<37:55:32,  7.13s/it]
                                                          
{'loss': 0.6339, 'learning_rate': 0.0003988781380924935, 'epoch': 3.82}

 32%|███▏      | 8931/28080 [17:38:53<37:55:32,  7.13s/it]
 32%|███▏      | 8932/28080 [17:39:00<37:52:23,  7.12s/it]
                                                          
{'loss': 0.6265, 'learning_rate': 0.0003988549720519087, 'epoch': 3.82}

 32%|███▏      | 8932/28080 [17:39:00<37:52:23,  7.12s/it]
 32%|███▏      | 8933/28080 [17:39:07<38:06:11,  7.16s/it]
                                                          
{'loss': 0.6157, 'learning_rate': 0.0003988318040309621, 'epoch': 3.82}

 32%|███▏      | 8933/28080 [17:39:07<38:06:11,  7.16s/it]
 32%|███▏      | 8934/28080 [17:39:14<38:10:05,  7.18s/it]
                                                          
{'loss': 0.6342, 'learning_rate': 0.0003988086340299619, 'epoch': 3.82}

 32%|███▏      | 8934/28080 [17:39:14<38:10:05,  7.18s/it]
 32%|███▏      | 8935/28080 [17:39:21<38:03:10,  7.16s/it]
                                                          
{'loss': 0.6427, 'learning_rate': 0.0003987854620492163, 'epoch': 3.82}

 32%|███▏      | 8935/28080 [17:39:21<38:03:10,  7.16s/it]
 32%|███▏      | 8936/28080 [17:39:28<38:06:51,  7.17s/it]
                                                          
{'loss': 0.6422, 'learning_rate': 0.0003987622880890336, 'epoch': 3.82}

 32%|███▏      | 8936/28080 [17:39:28<38:06:51,  7.17s/it]
 32%|███▏      | 8937/28080 [17:39:36<37:54:49,  7.13s/it]
                                                          
{'loss': 0.6374, 'learning_rate': 0.00039873911214972213, 'epoch': 3.82}

 32%|███▏      | 8937/28080 [17:39:36<37:54:49,  7.13s/it]
 32%|███▏      | 8938/28080 [17:39:43<37:49:51,  7.11s/it]
                                                          
{'loss': 0.6261, 'learning_rate': 0.00039871593423159026, 'epoch': 3.82}

 32%|███▏      | 8938/28080 [17:39:43<37:49:51,  7.11s/it]
 32%|███▏      | 8939/28080 [17:39:50<37:56:31,  7.14s/it]
                                                          
{'loss': 0.6279, 'learning_rate': 0.0003986927543349462, 'epoch': 3.82}

 32%|███▏      | 8939/28080 [17:39:50<37:56:31,  7.14s/it]
 32%|███▏      | 8940/28080 [17:39:57<38:01:47,  7.15s/it]
                                                          
{'loss': 0.6201, 'learning_rate': 0.0003986695724600986, 'epoch': 3.82}

 32%|███▏      | 8940/28080 [17:39:57<38:01:47,  7.15s/it]
 32%|███▏      | 8941/28080 [17:40:04<37:57:53,  7.14s/it]
                                                          
{'loss': 0.6234, 'learning_rate': 0.00039864638860735556, 'epoch': 3.82}

 32%|███▏      | 8941/28080 [17:40:04<37:57:53,  7.14s/it]
 32%|███▏      | 8942/28080 [17:40:11<37:42:14,  7.09s/it]
                                                          
{'loss': 0.6513, 'learning_rate': 0.00039862320277702577, 'epoch': 3.82}

 32%|███▏      | 8942/28080 [17:40:11<37:42:14,  7.09s/it]
 32%|███▏      | 8943/28080 [17:40:18<37:42:08,  7.09s/it]
                                                          
{'loss': 0.6117, 'learning_rate': 0.00039860001496941756, 'epoch': 3.82}

 32%|███▏      | 8943/28080 [17:40:18<37:42:08,  7.09s/it]
 32%|███▏      | 8944/28080 [17:40:25<37:42:05,  7.09s/it]
                                                          
{'loss': 0.6501, 'learning_rate': 0.0003985768251848395, 'epoch': 3.82}

 32%|███▏      | 8944/28080 [17:40:25<37:42:05,  7.09s/it]
 32%|███▏      | 8945/28080 [17:40:32<37:41:47,  7.09s/it]
                                                          
{'loss': 0.6418, 'learning_rate': 0.0003985536334236001, 'epoch': 3.82}

 32%|███▏      | 8945/28080 [17:40:32<37:41:47,  7.09s/it]
 32%|███▏      | 8946/28080 [17:40:39<37:46:14,  7.11s/it]
                                                          
{'loss': 0.6385, 'learning_rate': 0.0003985304396860078, 'epoch': 3.82}

 32%|███▏      | 8946/28080 [17:40:40<37:46:14,  7.11s/it]
 32%|███▏      | 8947/28080 [17:40:47<37:39:51,  7.09s/it]
                                                          
{'loss': 0.6591, 'learning_rate': 0.00039850724397237115, 'epoch': 3.82}

 32%|███▏      | 8947/28080 [17:40:47<37:39:51,  7.09s/it]
 32%|███▏      | 8948/28080 [17:40:54<37:48:45,  7.12s/it]
                                                          
{'loss': 0.6395, 'learning_rate': 0.0003984840462829988, 'epoch': 3.82}

 32%|███▏      | 8948/28080 [17:40:54<37:48:45,  7.12s/it]
 32%|███▏      | 8949/28080 [17:41:01<37:49:18,  7.12s/it]
                                                          
{'loss': 0.6192, 'learning_rate': 0.0003984608466181996, 'epoch': 3.82}

 32%|███▏      | 8949/28080 [17:41:01<37:49:18,  7.12s/it]
 32%|███▏      | 8950/28080 [17:41:08<37:54:18,  7.13s/it]
                                                          
{'loss': 0.6408, 'learning_rate': 0.00039843764497828185, 'epoch': 3.82}

 32%|███▏      | 8950/28080 [17:41:08<37:54:18,  7.13s/it]
 32%|███▏      | 8951/28080 [17:41:15<37:49:00,  7.12s/it]
                                                          
{'loss': 0.6333, 'learning_rate': 0.0003984144413635544, 'epoch': 3.82}

 32%|███▏      | 8951/28080 [17:41:15<37:49:00,  7.12s/it]
 32%|███▏      | 8952/28080 [17:41:22<37:47:47,  7.11s/it]
                                                          
{'loss': 0.6407, 'learning_rate': 0.0003983912357743259, 'epoch': 3.82}

 32%|███▏      | 8952/28080 [17:41:22<37:47:47,  7.11s/it]
 32%|███▏      | 8953/28080 [17:41:29<37:40:59,  7.09s/it]
                                                          
{'loss': 0.6532, 'learning_rate': 0.0003983680282109051, 'epoch': 3.82}

 32%|███▏      | 8953/28080 [17:41:29<37:40:59,  7.09s/it]
 32%|███▏      | 8954/28080 [17:41:36<37:53:36,  7.13s/it]
                                                          
{'loss': 0.618, 'learning_rate': 0.0003983448186736007, 'epoch': 3.83}

 32%|███▏      | 8954/28080 [17:41:36<37:53:36,  7.13s/it]
 32%|███▏      | 8955/28080 [17:41:44<37:49:24,  7.12s/it]
                                                          
{'loss': 0.6375, 'learning_rate': 0.00039832160716272167, 'epoch': 3.83}

 32%|███▏      | 8955/28080 [17:41:44<37:49:24,  7.12s/it]
 32%|███▏      | 8956/28080 [17:41:51<37:39:13,  7.09s/it]
                                                          
{'loss': 0.6428, 'learning_rate': 0.00039829839367857655, 'epoch': 3.83}

 32%|███▏      | 8956/28080 [17:41:51<37:39:13,  7.09s/it]
 32%|███▏      | 8957/28080 [17:41:58<37:37:41,  7.08s/it]
                                                          
{'loss': 0.641, 'learning_rate': 0.0003982751782214744, 'epoch': 3.83}

 32%|███▏      | 8957/28080 [17:41:58<37:37:41,  7.08s/it]
 32%|███▏      | 8958/28080 [17:42:05<37:40:32,  7.09s/it]
                                                          
{'loss': 0.6283, 'learning_rate': 0.00039825196079172387, 'epoch': 3.83}

 32%|███▏      | 8958/28080 [17:42:05<37:40:32,  7.09s/it]
 32%|███▏      | 8959/28080 [17:42:12<37:41:11,  7.10s/it]
                                                          
{'loss': 0.6423, 'learning_rate': 0.00039822874138963397, 'epoch': 3.83}

 32%|███▏      | 8959/28080 [17:42:12<37:41:11,  7.10s/it]
 32%|███▏      | 8960/28080 [17:42:19<37:39:52,  7.09s/it]
                                                          
{'loss': 0.6564, 'learning_rate': 0.00039820552001551356, 'epoch': 3.83}

 32%|███▏      | 8960/28080 [17:42:19<37:39:52,  7.09s/it]
 32%|███▏      | 8961/28080 [17:42:26<37:41:01,  7.10s/it]
                                                          
{'loss': 0.6418, 'learning_rate': 0.00039818229666967165, 'epoch': 3.83}

 32%|███▏      | 8961/28080 [17:42:26<37:41:01,  7.10s/it]
 32%|███▏      | 8962/28080 [17:42:33<37:55:04,  7.14s/it]
                                                          
{'loss': 0.6181, 'learning_rate': 0.0003981590713524171, 'epoch': 3.83}

 32%|███▏      | 8962/28080 [17:42:33<37:55:04,  7.14s/it]
 32%|███▏      | 8963/28080 [17:42:40<37:55:57,  7.14s/it]
                                                          
{'loss': 0.6219, 'learning_rate': 0.000398135844064059, 'epoch': 3.83}

 32%|███▏      | 8963/28080 [17:42:40<37:55:57,  7.14s/it]
 32%|███▏      | 8964/28080 [17:42:47<37:47:14,  7.12s/it]
                                                          
{'loss': 0.6505, 'learning_rate': 0.00039811261480490637, 'epoch': 3.83}

 32%|███▏      | 8964/28080 [17:42:47<37:47:14,  7.12s/it]
 32%|███▏      | 8965/28080 [17:42:55<37:45:32,  7.11s/it]
                                                          
{'loss': 0.6415, 'learning_rate': 0.0003980893835752681, 'epoch': 3.83}

 32%|███▏      | 8965/28080 [17:42:55<37:45:32,  7.11s/it]
 32%|███▏      | 8966/28080 [17:43:02<37:52:46,  7.13s/it]
                                                          
{'loss': 0.6239, 'learning_rate': 0.00039806615037545333, 'epoch': 3.83}

 32%|███▏      | 8966/28080 [17:43:02<37:52:46,  7.13s/it]
 32%|███▏      | 8967/28080 [17:43:09<37:46:19,  7.11s/it]
                                                          
{'loss': 0.613, 'learning_rate': 0.0003980429152057713, 'epoch': 3.83}

 32%|███▏      | 8967/28080 [17:43:09<37:46:19,  7.11s/it]
 32%|███▏      | 8968/28080 [17:43:16<37:42:57,  7.10s/it]
                                                          
{'loss': 0.6431, 'learning_rate': 0.00039801967806653093, 'epoch': 3.83}

 32%|███▏      | 8968/28080 [17:43:16<37:42:57,  7.10s/it]
 32%|███▏      | 8969/28080 [17:43:23<37:46:13,  7.11s/it]
                                                          
{'loss': 0.6421, 'learning_rate': 0.0003979964389580415, 'epoch': 3.83}

 32%|███▏      | 8969/28080 [17:43:23<37:46:13,  7.11s/it]
 32%|███▏      | 8970/28080 [17:43:30<37:55:10,  7.14s/it]
                                                          
{'loss': 0.6515, 'learning_rate': 0.00039797319788061216, 'epoch': 3.83}

 32%|███▏      | 8970/28080 [17:43:30<37:55:10,  7.14s/it]
 32%|███▏      | 8971/28080 [17:43:37<37:53:20,  7.14s/it]
                                                          
{'loss': 0.6302, 'learning_rate': 0.000397949954834552, 'epoch': 3.83}

 32%|███▏      | 8971/28080 [17:43:37<37:53:20,  7.14s/it]
 32%|███▏      | 8972/28080 [17:43:45<37:57:02,  7.15s/it]
                                                          
{'loss': 0.6214, 'learning_rate': 0.0003979267098201703, 'epoch': 3.83}

 32%|███▏      | 8972/28080 [17:43:45<37:57:02,  7.15s/it]
 32%|███▏      | 8973/28080 [17:43:52<37:57:14,  7.15s/it]
                                                          
{'loss': 0.6279, 'learning_rate': 0.00039790346283777637, 'epoch': 3.83}

 32%|███▏      | 8973/28080 [17:43:52<37:57:14,  7.15s/it]
 32%|███▏      | 8974/28080 [17:43:59<37:55:29,  7.15s/it]
                                                          
{'loss': 0.6432, 'learning_rate': 0.00039788021388767946, 'epoch': 3.83}

 32%|███▏      | 8974/28080 [17:43:59<37:55:29,  7.15s/it]
 32%|███▏      | 8975/28080 [17:44:06<37:55:08,  7.15s/it]
                                                          
{'loss': 0.6353, 'learning_rate': 0.0003978569629701888, 'epoch': 3.83}

 32%|███▏      | 8975/28080 [17:44:06<37:55:08,  7.15s/it]
 32%|███▏      | 8976/28080 [17:44:13<37:54:24,  7.14s/it]
                                                          
{'loss': 0.63, 'learning_rate': 0.00039783371008561384, 'epoch': 3.83}

 32%|███▏      | 8976/28080 [17:44:13<37:54:24,  7.14s/it]
 32%|███▏      | 8977/28080 [17:44:20<37:48:52,  7.13s/it]
                                                          
{'loss': 0.6441, 'learning_rate': 0.000397810455234264, 'epoch': 3.83}

 32%|███▏      | 8977/28080 [17:44:20<37:48:52,  7.13s/it]
 32%|███▏      | 8978/28080 [17:44:27<37:55:33,  7.15s/it]
                                                          
{'loss': 0.6437, 'learning_rate': 0.00039778719841644834, 'epoch': 3.84}

 32%|███▏      | 8978/28080 [17:44:27<37:55:33,  7.15s/it]
 32%|███▏      | 8979/28080 [17:44:35<37:57:37,  7.15s/it]
                                                          
{'loss': 0.6201, 'learning_rate': 0.0003977639396324765, 'epoch': 3.84}

 32%|███▏      | 8979/28080 [17:44:35<37:57:37,  7.15s/it]
 32%|███▏      | 8980/28080 [17:44:42<37:59:09,  7.16s/it]
                                                          
{'loss': 0.6292, 'learning_rate': 0.000397740678882658, 'epoch': 3.84}

 32%|███▏      | 8980/28080 [17:44:42<37:59:09,  7.16s/it]
 32%|███▏      | 8981/28080 [17:44:49<37:59:37,  7.16s/it]
                                                          
{'loss': 0.632, 'learning_rate': 0.0003977174161673021, 'epoch': 3.84}

 32%|███▏      | 8981/28080 [17:44:49<37:59:37,  7.16s/it]
 32%|███▏      | 8982/28080 [17:44:56<37:55:54,  7.15s/it]
                                                          
{'loss': 0.6363, 'learning_rate': 0.0003976941514867184, 'epoch': 3.84}

 32%|███▏      | 8982/28080 [17:44:56<37:55:54,  7.15s/it]
 32%|███▏      | 8983/28080 [17:45:03<37:57:24,  7.16s/it]
                                                          
{'loss': 0.6314, 'learning_rate': 0.00039767088484121634, 'epoch': 3.84}

 32%|███▏      | 8983/28080 [17:45:03<37:57:24,  7.16s/it]
 32%|███▏      | 8984/28080 [17:45:10<37:42:12,  7.11s/it]
                                                          
{'loss': 0.622, 'learning_rate': 0.00039764761623110553, 'epoch': 3.84}

 32%|███▏      | 8984/28080 [17:45:10<37:42:12,  7.11s/it]
 32%|███▏      | 8985/28080 [17:45:17<37:44:15,  7.11s/it]
                                                          
{'loss': 0.6207, 'learning_rate': 0.0003976243456566955, 'epoch': 3.84}

 32%|███▏      | 8985/28080 [17:45:17<37:44:15,  7.11s/it]
 32%|███▏      | 8986/28080 [17:45:25<37:50:37,  7.14s/it]
                                                          
{'loss': 0.6252, 'learning_rate': 0.00039760107311829585, 'epoch': 3.84}

 32%|███▏      | 8986/28080 [17:45:25<37:50:37,  7.14s/it]
 32%|███▏      | 8987/28080 [17:45:32<38:00:31,  7.17s/it]
                                                          
{'loss': 0.6324, 'learning_rate': 0.00039757779861621616, 'epoch': 3.84}

 32%|███▏      | 8987/28080 [17:45:32<38:00:31,  7.17s/it]
 32%|███▏      | 8988/28080 [17:45:39<38:02:03,  7.17s/it]
                                                          
{'loss': 0.6369, 'learning_rate': 0.00039755452215076614, 'epoch': 3.84}

 32%|███▏      | 8988/28080 [17:45:39<38:02:03,  7.17s/it]
 32%|███▏      | 8989/28080 [17:45:46<37:39:13,  7.10s/it]
                                                          
{'loss': 0.6439, 'learning_rate': 0.00039753124372225544, 'epoch': 3.84}

 32%|███▏      | 8989/28080 [17:45:46<37:39:13,  7.10s/it]
 32%|███▏      | 8990/28080 [17:45:53<37:53:34,  7.15s/it]
                                                          
{'loss': 0.6212, 'learning_rate': 0.0003975079633309937, 'epoch': 3.84}

 32%|███▏      | 8990/28080 [17:45:53<37:53:34,  7.15s/it]
 32%|███▏      | 8991/28080 [17:46:00<37:48:47,  7.13s/it]
                                                          
{'loss': 0.6224, 'learning_rate': 0.00039748468097729076, 'epoch': 3.84}

 32%|███▏      | 8991/28080 [17:46:00<37:48:47,  7.13s/it]
 32%|███▏      | 8992/28080 [17:46:07<37:55:24,  7.15s/it]
                                                          
{'loss': 0.633, 'learning_rate': 0.00039746139666145617, 'epoch': 3.84}

 32%|███▏      | 8992/28080 [17:46:07<37:55:24,  7.15s/it]
 32%|███▏      | 8993/28080 [17:46:15<37:54:46,  7.15s/it]
                                                          
{'loss': 0.6292, 'learning_rate': 0.00039743811038379993, 'epoch': 3.84}

 32%|███▏      | 8993/28080 [17:46:15<37:54:46,  7.15s/it]
 32%|███▏      | 8994/28080 [17:46:22<37:58:42,  7.16s/it]
                                                          
{'loss': 0.6284, 'learning_rate': 0.0003974148221446317, 'epoch': 3.84}

 32%|███▏      | 8994/28080 [17:46:22<37:58:42,  7.16s/it]
 32%|███▏      | 8995/28080 [17:46:29<37:51:41,  7.14s/it]
                                                          
{'loss': 0.6223, 'learning_rate': 0.00039739153194426135, 'epoch': 3.84}

 32%|███▏      | 8995/28080 [17:46:29<37:51:41,  7.14s/it]
 32%|███▏      | 8996/28080 [17:46:36<37:53:50,  7.15s/it]
                                                          
{'loss': 0.64, 'learning_rate': 0.00039736823978299874, 'epoch': 3.84}

 32%|███▏      | 8996/28080 [17:46:36<37:53:50,  7.15s/it]
 32%|███▏      | 8997/28080 [17:46:43<37:52:41,  7.15s/it]
                                                          
{'loss': 0.6325, 'learning_rate': 0.0003973449456611537, 'epoch': 3.84}

 32%|███▏      | 8997/28080 [17:46:43<37:52:41,  7.15s/it]
 32%|███▏      | 8998/28080 [17:46:50<37:54:45,  7.15s/it]
                                                          
{'loss': 0.6228, 'learning_rate': 0.00039732164957903614, 'epoch': 3.84}

 32%|███▏      | 8998/28080 [17:46:50<37:54:45,  7.15s/it]
 32%|███▏      | 8999/28080 [17:46:57<37:51:08,  7.14s/it]
                                                          
{'loss': 0.6351, 'learning_rate': 0.0003972983515369561, 'epoch': 3.84}

 32%|███▏      | 8999/28080 [17:46:57<37:51:08,  7.14s/it]
 32%|███▏      | 9000/28080 [17:47:05<37:44:39,  7.12s/it]
                                                          
{'loss': 0.6423, 'learning_rate': 0.00039727505153522335, 'epoch': 3.84}

 32%|███▏      | 9000/28080 [17:47:05<37:44:39,  7.12s/it]
 32%|███▏      | 9001/28080 [17:47:12<37:51:34,  7.14s/it]
                                                          
{'loss': 0.6355, 'learning_rate': 0.0003972517495741481, 'epoch': 3.85}

 32%|███▏      | 9001/28080 [17:47:12<37:51:34,  7.14s/it]
 32%|███▏      | 9002/28080 [17:47:19<37:52:30,  7.15s/it]
                                                          
{'loss': 0.6217, 'learning_rate': 0.0003972284456540401, 'epoch': 3.85}

 32%|███▏      | 9002/28080 [17:47:19<37:52:30,  7.15s/it]
 32%|███▏      | 9003/28080 [17:47:26<37:41:03,  7.11s/it]
                                                          
{'loss': 0.6399, 'learning_rate': 0.00039720513977520956, 'epoch': 3.85}

 32%|███▏      | 9003/28080 [17:47:26<37:41:03,  7.11s/it]
 32%|███▏      | 9004/28080 [17:47:33<37:50:13,  7.14s/it]
                                                          
{'loss': 0.63, 'learning_rate': 0.0003971818319379665, 'epoch': 3.85}

 32%|███▏      | 9004/28080 [17:47:33<37:50:13,  7.14s/it]
 32%|███▏      | 9005/28080 [17:47:40<37:51:20,  7.14s/it]
                                                          
{'loss': 0.6437, 'learning_rate': 0.00039715852214262107, 'epoch': 3.85}

 32%|███▏      | 9005/28080 [17:47:40<37:51:20,  7.14s/it]
 32%|███▏      | 9006/28080 [17:47:47<37:57:07,  7.16s/it]
                                                          
{'loss': 0.6372, 'learning_rate': 0.00039713521038948324, 'epoch': 3.85}

 32%|███▏      | 9006/28080 [17:47:47<37:57:07,  7.16s/it]
 32%|███▏      | 9007/28080 [17:47:55<37:52:43,  7.15s/it]
                                                          
{'loss': 0.6353, 'learning_rate': 0.0003971118966788633, 'epoch': 3.85}

 32%|███▏      | 9007/28080 [17:47:55<37:52:43,  7.15s/it]
 32%|███▏      | 9008/28080 [17:48:02<37:51:20,  7.15s/it]
                                                          
{'loss': 0.6215, 'learning_rate': 0.00039708858101107126, 'epoch': 3.85}

 32%|███▏      | 9008/28080 [17:48:02<37:51:20,  7.15s/it]
 32%|███▏      | 9009/28080 [17:48:09<37:55:14,  7.16s/it]
                                                          
{'loss': 0.6262, 'learning_rate': 0.00039706526338641743, 'epoch': 3.85}

 32%|███▏      | 9009/28080 [17:48:09<37:55:14,  7.16s/it]
 32%|███▏      | 9010/28080 [17:48:16<38:05:27,  7.19s/it]
                                                          
{'loss': 0.6306, 'learning_rate': 0.000397041943805212, 'epoch': 3.85}

 32%|███▏      | 9010/28080 [17:48:16<38:05:27,  7.19s/it]
 32%|███▏      | 9011/28080 [17:48:23<37:41:32,  7.12s/it]
                                                          
{'loss': 0.6432, 'learning_rate': 0.0003970186222677652, 'epoch': 3.85}

 32%|███▏      | 9011/28080 [17:48:23<37:41:32,  7.12s/it]
 32%|███▏      | 9012/28080 [17:48:30<37:38:18,  7.11s/it]
                                                          
{'loss': 0.6443, 'learning_rate': 0.0003969952987743872, 'epoch': 3.85}

 32%|███▏      | 9012/28080 [17:48:30<37:38:18,  7.11s/it]
 32%|███▏      | 9013/28080 [17:48:37<37:38:03,  7.11s/it]
                                                          
{'loss': 0.6241, 'learning_rate': 0.0003969719733253885, 'epoch': 3.85}

 32%|███▏      | 9013/28080 [17:48:37<37:38:03,  7.11s/it]
 32%|███▏      | 9014/28080 [17:48:44<37:40:44,  7.11s/it]
                                                          
{'loss': 0.6125, 'learning_rate': 0.00039694864592107937, 'epoch': 3.85}

 32%|███▏      | 9014/28080 [17:48:44<37:40:44,  7.11s/it]
 32%|███▏      | 9015/28080 [17:48:52<37:41:03,  7.12s/it]
                                                          
{'loss': 0.6224, 'learning_rate': 0.00039692531656177, 'epoch': 3.85}

 32%|███▏      | 9015/28080 [17:48:52<37:41:03,  7.12s/it]
 32%|███▏      | 9016/28080 [17:48:59<37:44:44,  7.13s/it]
                                                          
{'loss': 0.6276, 'learning_rate': 0.00039690198524777086, 'epoch': 3.85}

 32%|███▏      | 9016/28080 [17:48:59<37:44:44,  7.13s/it]
 32%|███▏      | 9017/28080 [17:49:06<37:38:12,  7.11s/it]
                                                          
{'loss': 0.6654, 'learning_rate': 0.00039687865197939243, 'epoch': 3.85}

 32%|███▏      | 9017/28080 [17:49:06<37:38:12,  7.11s/it]
 32%|███▏      | 9018/28080 [17:49:13<37:43:34,  7.12s/it]
                                                          
{'loss': 0.6217, 'learning_rate': 0.0003968553167569451, 'epoch': 3.85}

 32%|███▏      | 9018/28080 [17:49:13<37:43:34,  7.12s/it]
 32%|███▏      | 9019/28080 [17:49:20<37:45:14,  7.13s/it]
                                                          
{'loss': 0.6168, 'learning_rate': 0.0003968319795807391, 'epoch': 3.85}

 32%|███▏      | 9019/28080 [17:49:20<37:45:14,  7.13s/it]
 32%|███▏      | 9020/28080 [17:49:27<37:35:10,  7.10s/it]
                                                          
{'loss': 0.6231, 'learning_rate': 0.00039680864045108535, 'epoch': 3.85}

 32%|███▏      | 9020/28080 [17:49:27<37:35:10,  7.10s/it]
 32%|███▏      | 9021/28080 [17:49:34<37:43:16,  7.13s/it]
                                                          
{'loss': 0.643, 'learning_rate': 0.00039678529936829386, 'epoch': 3.85}

 32%|███▏      | 9021/28080 [17:49:34<37:43:16,  7.13s/it]
 32%|███▏      | 9022/28080 [17:49:41<37:47:09,  7.14s/it]
                                                          
{'loss': 0.6279, 'learning_rate': 0.0003967619563326755, 'epoch': 3.85}

 32%|███▏      | 9022/28080 [17:49:41<37:47:09,  7.14s/it]
 32%|███▏      | 9023/28080 [17:49:49<37:49:19,  7.14s/it]
                                                          
{'loss': 0.6388, 'learning_rate': 0.0003967386113445407, 'epoch': 3.85}

 32%|███▏      | 9023/28080 [17:49:49<37:49:19,  7.14s/it]
 32%|███▏      | 9024/28080 [17:49:56<37:48:04,  7.14s/it]
                                                          
{'loss': 0.6523, 'learning_rate': 0.0003967152644042001, 'epoch': 3.85}

 32%|███▏      | 9024/28080 [17:49:56<37:48:04,  7.14s/it]
 32%|███▏      | 9025/28080 [17:50:03<37:37:31,  7.11s/it]
                                                          
{'loss': 0.6619, 'learning_rate': 0.0003966919155119642, 'epoch': 3.86}

 32%|███▏      | 9025/28080 [17:50:03<37:37:31,  7.11s/it]
 32%|███▏      | 9026/28080 [17:50:10<37:43:29,  7.13s/it]
                                                          
{'loss': 0.6343, 'learning_rate': 0.0003966685646681437, 'epoch': 3.86}

 32%|███▏      | 9026/28080 [17:50:10<37:43:29,  7.13s/it]
 32%|███▏      | 9027/28080 [17:50:17<37:43:52,  7.13s/it]
                                                          
{'loss': 0.6314, 'learning_rate': 0.00039664521187304926, 'epoch': 3.86}

 32%|███▏      | 9027/28080 [17:50:17<37:43:52,  7.13s/it]
 32%|███▏      | 9028/28080 [17:50:24<37:41:49,  7.12s/it]
                                                          
{'loss': 0.6154, 'learning_rate': 0.0003966218571269916, 'epoch': 3.86}

 32%|███▏      | 9028/28080 [17:50:24<37:41:49,  7.12s/it]
 32%|███▏      | 9029/28080 [17:50:31<37:53:09,  7.16s/it]
                                                          
{'loss': 0.6387, 'learning_rate': 0.0003965985004302813, 'epoch': 3.86}

 32%|███▏      | 9029/28080 [17:50:31<37:53:09,  7.16s/it]
 32%|███▏      | 9030/28080 [17:50:39<37:51:03,  7.15s/it]
                                                          
{'loss': 0.6289, 'learning_rate': 0.00039657514178322934, 'epoch': 3.86}

 32%|███▏      | 9030/28080 [17:50:39<37:51:03,  7.15s/it]
 32%|███▏      | 9031/28080 [17:50:46<37:53:36,  7.16s/it]
                                                          
{'loss': 0.6362, 'learning_rate': 0.0003965517811861462, 'epoch': 3.86}

 32%|███▏      | 9031/28080 [17:50:46<37:53:36,  7.16s/it]
 32%|███▏      | 9032/28080 [17:50:53<37:56:15,  7.17s/it]
                                                          
{'loss': 0.6445, 'learning_rate': 0.00039652841863934286, 'epoch': 3.86}

 32%|███▏      | 9032/28080 [17:50:53<37:56:15,  7.17s/it]
 32%|███▏      | 9033/28080 [17:51:00<37:46:42,  7.14s/it]
                                                          
{'loss': 0.6256, 'learning_rate': 0.0003965050541431301, 'epoch': 3.86}

 32%|███▏      | 9033/28080 [17:51:00<37:46:42,  7.14s/it]
 32%|███▏      | 9034/28080 [17:51:07<37:51:03,  7.15s/it]
                                                          
{'loss': 0.6428, 'learning_rate': 0.0003964816876978187, 'epoch': 3.86}

 32%|███▏      | 9034/28080 [17:51:07<37:51:03,  7.15s/it]
 32%|███▏      | 9035/28080 [17:51:14<37:48:09,  7.15s/it]
                                                          
{'loss': 0.6422, 'learning_rate': 0.00039645831930371956, 'epoch': 3.86}

 32%|███▏      | 9035/28080 [17:51:14<37:48:09,  7.15s/it]
 32%|███▏      | 9036/28080 [17:51:21<37:39:56,  7.12s/it]
                                                          
{'loss': 0.626, 'learning_rate': 0.0003964349489611436, 'epoch': 3.86}

 32%|███▏      | 9036/28080 [17:51:21<37:39:56,  7.12s/it]
 32%|███▏      | 9037/28080 [17:51:29<37:36:10,  7.11s/it]
                                                          
{'loss': 0.6406, 'learning_rate': 0.0003964115766704017, 'epoch': 3.86}

 32%|███▏      | 9037/28080 [17:51:29<37:36:10,  7.11s/it]
 32%|███▏      | 9038/28080 [17:51:36<37:42:02,  7.13s/it]
                                                          
{'loss': 0.6271, 'learning_rate': 0.00039638820243180473, 'epoch': 3.86}

 32%|███▏      | 9038/28080 [17:51:36<37:42:02,  7.13s/it]
 32%|███▏      | 9039/28080 [17:51:43<37:44:04,  7.13s/it]
                                                          
{'loss': 0.6214, 'learning_rate': 0.0003963648262456638, 'epoch': 3.86}

 32%|███▏      | 9039/28080 [17:51:43<37:44:04,  7.13s/it]
 32%|███▏      | 9040/28080 [17:51:50<37:42:47,  7.13s/it]
                                                          
{'loss': 0.6189, 'learning_rate': 0.0003963414481122899, 'epoch': 3.86}

 32%|███▏      | 9040/28080 [17:51:50<37:42:47,  7.13s/it]
 32%|███▏      | 9041/28080 [17:51:57<37:44:59,  7.14s/it]
                                                          
{'loss': 0.6099, 'learning_rate': 0.000396318068031994, 'epoch': 3.86}

 32%|███▏      | 9041/28080 [17:51:57<37:44:59,  7.14s/it]
 32%|███▏      | 9042/28080 [17:52:04<37:51:50,  7.16s/it]
                                                          
{'loss': 0.642, 'learning_rate': 0.0003962946860050871, 'epoch': 3.86}

 32%|███▏      | 9042/28080 [17:52:04<37:51:50,  7.16s/it]
 32%|███▏      | 9043/28080 [17:52:11<37:49:34,  7.15s/it]
                                                          
{'loss': 0.6215, 'learning_rate': 0.0003962713020318804, 'epoch': 3.86}

 32%|███▏      | 9043/28080 [17:52:11<37:49:34,  7.15s/it]
 32%|███▏      | 9044/28080 [17:52:19<37:44:55,  7.14s/it]
                                                          
{'loss': 0.6264, 'learning_rate': 0.0003962479161126849, 'epoch': 3.86}

 32%|███▏      | 9044/28080 [17:52:19<37:44:55,  7.14s/it]
 32%|███▏      | 9045/28080 [17:52:26<37:36:22,  7.11s/it]
                                                          
{'loss': 0.6281, 'learning_rate': 0.00039622452824781174, 'epoch': 3.86}

 32%|███▏      | 9045/28080 [17:52:26<37:36:22,  7.11s/it]
 32%|███▏      | 9046/28080 [17:52:33<37:30:30,  7.09s/it]
                                                          
{'loss': 0.6444, 'learning_rate': 0.0003962011384375721, 'epoch': 3.86}

 32%|███▏      | 9046/28080 [17:52:33<37:30:30,  7.09s/it]
 32%|███▏      | 9047/28080 [17:52:40<37:28:31,  7.09s/it]
                                                          
{'loss': 0.6427, 'learning_rate': 0.00039617774668227715, 'epoch': 3.86}

 32%|███▏      | 9047/28080 [17:52:40<37:28:31,  7.09s/it]
 32%|███▏      | 9048/28080 [17:52:47<37:27:38,  7.09s/it]
                                                          
{'loss': 0.6343, 'learning_rate': 0.000396154352982238, 'epoch': 3.87}

 32%|███▏      | 9048/28080 [17:52:47<37:27:38,  7.09s/it]
 32%|███▏      | 9049/28080 [17:52:54<37:25:33,  7.08s/it]
                                                          
{'loss': 0.6308, 'learning_rate': 0.00039613095733776604, 'epoch': 3.87}

 32%|███▏      | 9049/28080 [17:52:54<37:25:33,  7.08s/it]
 32%|███▏      | 9050/28080 [17:53:01<37:32:49,  7.10s/it]
                                                          
{'loss': 0.6306, 'learning_rate': 0.00039610755974917245, 'epoch': 3.87}

 32%|███▏      | 9050/28080 [17:53:01<37:32:49,  7.10s/it]
 32%|███▏      | 9051/28080 [17:53:08<37:31:37,  7.10s/it]
                                                          
{'loss': 0.6321, 'learning_rate': 0.00039608416021676845, 'epoch': 3.87}

 32%|███▏      | 9051/28080 [17:53:08<37:31:37,  7.10s/it]
 32%|███▏      | 9052/28080 [17:53:15<37:41:25,  7.13s/it]
                                                          
{'loss': 0.6327, 'learning_rate': 0.00039606075874086544, 'epoch': 3.87}

 32%|███▏      | 9052/28080 [17:53:15<37:41:25,  7.13s/it]
 32%|███▏      | 9053/28080 [17:53:22<37:43:02,  7.14s/it]
                                                          
{'loss': 0.6556, 'learning_rate': 0.0003960373553217748, 'epoch': 3.87}

 32%|███▏      | 9053/28080 [17:53:23<37:43:02,  7.14s/it]
 32%|███▏      | 9054/28080 [17:53:29<37:30:17,  7.10s/it]
                                                          
{'loss': 0.6467, 'learning_rate': 0.00039601394995980767, 'epoch': 3.87}

 32%|███▏      | 9054/28080 [17:53:29<37:30:17,  7.10s/it]
 32%|███▏      | 9055/28080 [17:53:37<37:42:33,  7.14s/it]
                                                          
{'loss': 0.625, 'learning_rate': 0.00039599054265527557, 'epoch': 3.87}

 32%|███▏      | 9055/28080 [17:53:37<37:42:33,  7.14s/it]
 32%|███▏      | 9056/28080 [17:53:44<37:53:27,  7.17s/it]
                                                          
{'loss': 0.6604, 'learning_rate': 0.00039596713340849, 'epoch': 3.87}

 32%|███▏      | 9056/28080 [17:53:44<37:53:27,  7.17s/it]
 32%|███▏      | 9057/28080 [17:53:51<37:52:48,  7.17s/it]
                                                          
{'loss': 0.6229, 'learning_rate': 0.0003959437222197623, 'epoch': 3.87}

 32%|███▏      | 9057/28080 [17:53:51<37:52:48,  7.17s/it]
 32%|███▏      | 9058/28080 [17:53:58<37:48:41,  7.16s/it]
                                                          
{'loss': 0.6358, 'learning_rate': 0.00039592030908940383, 'epoch': 3.87}

 32%|███▏      | 9058/28080 [17:53:58<37:48:41,  7.16s/it]
 32%|███▏      | 9059/28080 [17:54:05<37:36:36,  7.12s/it]
                                                          
{'loss': 0.6256, 'learning_rate': 0.00039589689401772635, 'epoch': 3.87}

 32%|███▏      | 9059/28080 [17:54:05<37:36:36,  7.12s/it]
 32%|███▏      | 9060/28080 [17:54:12<37:44:27,  7.14s/it]
                                                          
{'loss': 0.6124, 'learning_rate': 0.0003958734770050411, 'epoch': 3.87}

 32%|███▏      | 9060/28080 [17:54:12<37:44:27,  7.14s/it]
 32%|███▏      | 9061/28080 [17:54:20<37:39:34,  7.13s/it]
                                                          
{'loss': 0.6161, 'learning_rate': 0.0003958500580516597, 'epoch': 3.87}

 32%|███▏      | 9061/28080 [17:54:20<37:39:34,  7.13s/it]
 32%|███▏      | 9062/28080 [17:54:27<37:42:01,  7.14s/it]
                                                          
{'loss': 0.6221, 'learning_rate': 0.0003958266371578938, 'epoch': 3.87}

 32%|███▏      | 9062/28080 [17:54:27<37:42:01,  7.14s/it]
 32%|███▏      | 9063/28080 [17:54:34<37:42:51,  7.14s/it]
                                                          
{'loss': 0.6216, 'learning_rate': 0.00039580321432405494, 'epoch': 3.87}

 32%|███▏      | 9063/28080 [17:54:34<37:42:51,  7.14s/it]
 32%|███▏      | 9064/28080 [17:54:41<37:48:21,  7.16s/it]
                                                          
{'loss': 0.6383, 'learning_rate': 0.00039577978955045466, 'epoch': 3.87}

 32%|███▏      | 9064/28080 [17:54:41<37:48:21,  7.16s/it]
 32%|███▏      | 9065/28080 [17:54:48<37:44:54,  7.15s/it]
                                                          
{'loss': 0.6463, 'learning_rate': 0.00039575636283740474, 'epoch': 3.87}

 32%|███▏      | 9065/28080 [17:54:48<37:44:54,  7.15s/it]
 32%|███▏      | 9066/28080 [17:54:55<37:42:56,  7.14s/it]
                                                          
{'loss': 0.6207, 'learning_rate': 0.0003957329341852168, 'epoch': 3.87}

 32%|███▏      | 9066/28080 [17:54:55<37:42:56,  7.14s/it]
 32%|███▏      | 9067/28080 [17:55:02<37:41:31,  7.14s/it]
                                                          
{'loss': 0.6387, 'learning_rate': 0.0003957095035942024, 'epoch': 3.87}

 32%|███▏      | 9067/28080 [17:55:02<37:41:31,  7.14s/it]
 32%|███▏      | 9068/28080 [17:55:10<37:38:35,  7.13s/it]
                                                          
{'loss': 0.6312, 'learning_rate': 0.00039568607106467353, 'epoch': 3.87}

 32%|███▏      | 9068/28080 [17:55:10<37:38:35,  7.13s/it]
 32%|███▏      | 9069/28080 [17:55:17<37:28:39,  7.10s/it]
                                                          
{'loss': 0.6368, 'learning_rate': 0.0003956626365969417, 'epoch': 3.87}

 32%|███▏      | 9069/28080 [17:55:17<37:28:39,  7.10s/it]
 32%|███▏      | 9070/28080 [17:55:24<37:33:04,  7.11s/it]
                                                          
{'loss': 0.6149, 'learning_rate': 0.0003956392001913188, 'epoch': 3.87}

 32%|███▏      | 9070/28080 [17:55:24<37:33:04,  7.11s/it]
 32%|███▏      | 9071/28080 [17:55:31<37:27:33,  7.09s/it]
                                                          
{'loss': 0.6145, 'learning_rate': 0.00039561576184811653, 'epoch': 3.88}

 32%|███▏      | 9071/28080 [17:55:31<37:27:33,  7.09s/it]
 32%|███▏      | 9072/28080 [17:55:38<37:36:53,  7.12s/it]
                                                          
{'loss': 0.6104, 'learning_rate': 0.0003955923215676468, 'epoch': 3.88}

 32%|███▏      | 9072/28080 [17:55:38<37:36:53,  7.12s/it]
 32%|███▏      | 9073/28080 [17:55:45<37:44:58,  7.15s/it]
                                                          
{'loss': 0.6398, 'learning_rate': 0.00039556887935022144, 'epoch': 3.88}

 32%|███▏      | 9073/28080 [17:55:45<37:44:58,  7.15s/it]
 32%|███▏      | 9074/28080 [17:55:52<37:41:24,  7.14s/it]
                                                          
{'loss': 0.6437, 'learning_rate': 0.0003955454351961523, 'epoch': 3.88}

 32%|███▏      | 9074/28080 [17:55:52<37:41:24,  7.14s/it]
 32%|███▏      | 9075/28080 [17:55:59<37:31:40,  7.11s/it]
                                                          
{'loss': 0.6311, 'learning_rate': 0.0003955219891057513, 'epoch': 3.88}

 32%|███▏      | 9075/28080 [17:55:59<37:31:40,  7.11s/it]
 32%|███▏      | 9076/28080 [17:56:07<37:41:09,  7.14s/it]
                                                          
{'loss': 0.6305, 'learning_rate': 0.00039549854107933036, 'epoch': 3.88}

 32%|███▏      | 9076/28080 [17:56:07<37:41:09,  7.14s/it]
 32%|███▏      | 9077/28080 [17:56:14<37:35:41,  7.12s/it]
                                                          
{'loss': 0.6033, 'learning_rate': 0.00039547509111720146, 'epoch': 3.88}

 32%|███▏      | 9077/28080 [17:56:14<37:35:41,  7.12s/it]
 32%|███▏      | 9078/28080 [17:56:21<37:31:55,  7.11s/it]
                                                          
{'loss': 0.6337, 'learning_rate': 0.00039545163921967654, 'epoch': 3.88}

 32%|███▏      | 9078/28080 [17:56:21<37:31:55,  7.11s/it]
 32%|███▏      | 9079/28080 [17:56:28<37:33:45,  7.12s/it]
                                                          
{'loss': 0.6338, 'learning_rate': 0.0003954281853870676, 'epoch': 3.88}

 32%|███▏      | 9079/28080 [17:56:28<37:33:45,  7.12s/it]
 32%|███▏      | 9080/28080 [17:56:35<37:42:52,  7.15s/it]
                                                          
{'loss': 0.6247, 'learning_rate': 0.00039540472961968663, 'epoch': 3.88}

 32%|███▏      | 9080/28080 [17:56:35<37:42:52,  7.15s/it]
 32%|███▏      | 9081/28080 [17:56:42<37:23:42,  7.09s/it]
                                                          
{'loss': 0.6544, 'learning_rate': 0.00039538127191784587, 'epoch': 3.88}

 32%|███▏      | 9081/28080 [17:56:42<37:23:42,  7.09s/it]
 32%|███▏      | 9082/28080 [17:56:49<37:27:21,  7.10s/it]
                                                          
{'loss': 0.6492, 'learning_rate': 0.00039535781228185716, 'epoch': 3.88}

 32%|███▏      | 9082/28080 [17:56:49<37:27:21,  7.10s/it]
 32%|███▏      | 9083/28080 [17:56:56<37:42:43,  7.15s/it]
                                                          
{'loss': 0.6056, 'learning_rate': 0.0003953343507120327, 'epoch': 3.88}

 32%|███▏      | 9083/28080 [17:56:56<37:42:43,  7.15s/it]
 32%|███▏      | 9084/28080 [17:57:04<37:44:43,  7.15s/it]
                                                          
{'loss': 0.6336, 'learning_rate': 0.00039531088720868473, 'epoch': 3.88}

 32%|███▏      | 9084/28080 [17:57:04<37:44:43,  7.15s/it]
 32%|███▏      | 9085/28080 [17:57:11<37:47:19,  7.16s/it]
                                                          
{'loss': 0.6356, 'learning_rate': 0.0003952874217721253, 'epoch': 3.88}

 32%|███▏      | 9085/28080 [17:57:11<37:47:19,  7.16s/it]
 32%|███▏      | 9086/28080 [17:57:18<37:49:30,  7.17s/it]
                                                          
{'loss': 0.6377, 'learning_rate': 0.00039526395440266657, 'epoch': 3.88}

 32%|███▏      | 9086/28080 [17:57:18<37:49:30,  7.17s/it]
 32%|███▏      | 9087/28080 [17:57:25<37:53:22,  7.18s/it]
                                                          
{'loss': 0.6247, 'learning_rate': 0.0003952404851006208, 'epoch': 3.88}

 32%|███▏      | 9087/28080 [17:57:25<37:53:22,  7.18s/it]
 32%|███▏      | 9088/28080 [17:57:32<37:52:20,  7.18s/it]
                                                          
{'loss': 0.6453, 'learning_rate': 0.00039521701386630015, 'epoch': 3.88}

 32%|███▏      | 9088/28080 [17:57:32<37:52:20,  7.18s/it]
 32%|███▏      | 9089/28080 [17:57:39<37:46:31,  7.16s/it]
                                                          
{'loss': 0.6377, 'learning_rate': 0.000395193540700017, 'epoch': 3.88}

 32%|███▏      | 9089/28080 [17:57:39<37:46:31,  7.16s/it]
 32%|███▏      | 9090/28080 [17:57:47<37:57:14,  7.20s/it]
                                                          
{'loss': 0.6266, 'learning_rate': 0.0003951700656020836, 'epoch': 3.88}

 32%|███▏      | 9090/28080 [17:57:47<37:57:14,  7.20s/it]
 32%|███▏      | 9091/28080 [17:57:54<37:56:44,  7.19s/it]
                                                          
{'loss': 0.6138, 'learning_rate': 0.0003951465885728122, 'epoch': 3.88}

 32%|███▏      | 9091/28080 [17:57:54<37:56:44,  7.19s/it]
 32%|███▏      | 9092/28080 [17:58:01<37:44:44,  7.16s/it]
                                                          
{'loss': 0.6327, 'learning_rate': 0.0003951231096125152, 'epoch': 3.88}

 32%|███▏      | 9092/28080 [17:58:01<37:44:44,  7.16s/it]
 32%|███▏      | 9093/28080 [17:58:08<37:43:27,  7.15s/it]
                                                          
{'loss': 0.6484, 'learning_rate': 0.00039509962872150497, 'epoch': 3.88}

 32%|███▏      | 9093/28080 [17:58:08<37:43:27,  7.15s/it]
 32%|███▏      | 9094/28080 [17:58:15<37:37:27,  7.13s/it]
                                                          
{'loss': 0.6297, 'learning_rate': 0.0003950761459000939, 'epoch': 3.88}

 32%|███▏      | 9094/28080 [17:58:15<37:37:27,  7.13s/it]
 32%|███▏      | 9095/28080 [17:58:22<37:38:26,  7.14s/it]
                                                          
{'loss': 0.641, 'learning_rate': 0.00039505266114859427, 'epoch': 3.89}

 32%|███▏      | 9095/28080 [17:58:22<37:38:26,  7.14s/it]
 32%|███▏      | 9096/28080 [17:58:29<37:38:26,  7.14s/it]
                                                          
{'loss': 0.6318, 'learning_rate': 0.00039502917446731866, 'epoch': 3.89}

 32%|███▏      | 9096/28080 [17:58:30<37:38:26,  7.14s/it]
 32%|███▏      | 9097/28080 [17:58:37<37:38:57,  7.14s/it]
                                                          
{'loss': 0.649, 'learning_rate': 0.0003950056858565795, 'epoch': 3.89}

 32%|███▏      | 9097/28080 [17:58:37<37:38:57,  7.14s/it]
 32%|███▏      | 9098/28080 [17:58:44<37:20:23,  7.08s/it]
                                                          
{'loss': 0.6328, 'learning_rate': 0.00039498219531668936, 'epoch': 3.89}

 32%|███▏      | 9098/28080 [17:58:44<37:20:23,  7.08s/it]
 32%|███▏      | 9099/28080 [17:58:51<37:22:19,  7.09s/it]
                                                          
{'loss': 0.6444, 'learning_rate': 0.00039495870284796055, 'epoch': 3.89}

 32%|███▏      | 9099/28080 [17:58:51<37:22:19,  7.09s/it]
 32%|███▏      | 9100/28080 [17:58:58<37:26:26,  7.10s/it]
                                                          
{'loss': 0.6358, 'learning_rate': 0.0003949352084507059, 'epoch': 3.89}

 32%|███▏      | 9100/28080 [17:58:58<37:26:26,  7.10s/it]
 32%|███▏      | 9101/28080 [17:59:05<37:31:44,  7.12s/it]
                                                          
{'loss': 0.6501, 'learning_rate': 0.0003949117121252377, 'epoch': 3.89}

 32%|███▏      | 9101/28080 [17:59:05<37:31:44,  7.12s/it]
 32%|███▏      | 9102/28080 [17:59:12<37:38:40,  7.14s/it]
                                                          
{'loss': 0.65, 'learning_rate': 0.0003948882138718687, 'epoch': 3.89}

 32%|███▏      | 9102/28080 [17:59:12<37:38:40,  7.14s/it]
 32%|███▏      | 9103/28080 [17:59:19<37:30:34,  7.12s/it]
                                                          
{'loss': 0.6456, 'learning_rate': 0.00039486471369091147, 'epoch': 3.89}

 32%|███▏      | 9103/28080 [17:59:19<37:30:34,  7.12s/it]
 32%|███▏      | 9104/28080 [17:59:26<37:42:03,  7.15s/it]
                                                          
{'loss': 0.6188, 'learning_rate': 0.00039484121158267873, 'epoch': 3.89}

 32%|███▏      | 9104/28080 [17:59:26<37:42:03,  7.15s/it]
 32%|███▏      | 9105/28080 [17:59:34<37:37:37,  7.14s/it]
                                                          
{'loss': 0.639, 'learning_rate': 0.000394817707547483, 'epoch': 3.89}

 32%|███▏      | 9105/28080 [17:59:34<37:37:37,  7.14s/it]
 32%|███▏      | 9106/28080 [17:59:41<37:44:26,  7.16s/it]
                                                          
{'loss': 0.6419, 'learning_rate': 0.0003947942015856372, 'epoch': 3.89}

 32%|███▏      | 9106/28080 [17:59:41<37:44:26,  7.16s/it]
 32%|███▏      | 9107/28080 [17:59:48<37:39:22,  7.15s/it]
                                                          
{'loss': 0.6095, 'learning_rate': 0.00039477069369745377, 'epoch': 3.89}

 32%|███▏      | 9107/28080 [17:59:48<37:39:22,  7.15s/it]
 32%|███▏      | 9108/28080 [17:59:55<37:46:37,  7.17s/it]
                                                          
{'loss': 0.6298, 'learning_rate': 0.0003947471838832457, 'epoch': 3.89}

 32%|███▏      | 9108/28080 [17:59:55<37:46:37,  7.17s/it]
 32%|███▏      | 9109/28080 [18:00:02<37:37:05,  7.14s/it]
                                                          
{'loss': 0.6226, 'learning_rate': 0.00039472367214332573, 'epoch': 3.89}

 32%|███▏      | 9109/28080 [18:00:02<37:37:05,  7.14s/it]
 32%|███▏      | 9110/28080 [18:00:09<37:40:36,  7.15s/it]
                                                          
{'loss': 0.628, 'learning_rate': 0.0003947001584780065, 'epoch': 3.89}

 32%|███▏      | 9110/28080 [18:00:09<37:40:36,  7.15s/it]
 32%|███▏      | 9111/28080 [18:00:17<37:43:27,  7.16s/it]
                                                          
{'loss': 0.6357, 'learning_rate': 0.00039467664288760096, 'epoch': 3.89}

 32%|███▏      | 9111/28080 [18:00:17<37:43:27,  7.16s/it]
 32%|███▏      | 9112/28080 [18:00:24<37:47:25,  7.17s/it]
                                                          
{'loss': 0.6296, 'learning_rate': 0.000394653125372422, 'epoch': 3.89}

 32%|███▏      | 9112/28080 [18:00:24<37:47:25,  7.17s/it]
 32%|███▏      | 9113/28080 [18:00:31<37:43:59,  7.16s/it]
                                                          
{'loss': 0.6341, 'learning_rate': 0.00039462960593278243, 'epoch': 3.89}

 32%|███▏      | 9113/28080 [18:00:31<37:43:59,  7.16s/it]
 32%|███▏      | 9114/28080 [18:00:38<37:34:26,  7.13s/it]
                                                          
{'loss': 0.6365, 'learning_rate': 0.00039460608456899507, 'epoch': 3.89}

 32%|███▏      | 9114/28080 [18:00:38<37:34:26,  7.13s/it]
 32%|███▏      | 9115/28080 [18:00:45<37:40:33,  7.15s/it]
                                                          
{'loss': 0.6454, 'learning_rate': 0.00039458256128137303, 'epoch': 3.89}

 32%|███▏      | 9115/28080 [18:00:45<37:40:33,  7.15s/it]
 32%|███▏      | 9116/28080 [18:00:52<37:43:34,  7.16s/it]
                                                          
{'loss': 0.6339, 'learning_rate': 0.00039455903607022916, 'epoch': 3.89}

 32%|███▏      | 9116/28080 [18:00:52<37:43:34,  7.16s/it]
 32%|███▏      | 9117/28080 [18:00:59<37:37:03,  7.14s/it]
                                                          
{'loss': 0.6354, 'learning_rate': 0.0003945355089358764, 'epoch': 3.89}

 32%|███▏      | 9117/28080 [18:00:59<37:37:03,  7.14s/it]
 32%|███▏      | 9118/28080 [18:01:07<37:34:29,  7.13s/it]
                                                          
{'loss': 0.6582, 'learning_rate': 0.00039451197987862784, 'epoch': 3.9}

 32%|███▏      | 9118/28080 [18:01:07<37:34:29,  7.13s/it]
 32%|███▏      | 9119/28080 [18:01:14<37:27:22,  7.11s/it]
                                                          
{'loss': 0.6414, 'learning_rate': 0.00039448844889879647, 'epoch': 3.9}

 32%|███▏      | 9119/28080 [18:01:14<37:27:22,  7.11s/it]
 32%|███▏      | 9120/28080 [18:01:21<37:38:04,  7.15s/it]
                                                          
{'loss': 0.6357, 'learning_rate': 0.0003944649159966953, 'epoch': 3.9}

 32%|███▏      | 9120/28080 [18:01:21<37:38:04,  7.15s/it]
 32%|███▏      | 9121/28080 [18:01:28<37:37:19,  7.14s/it]
                                                          
{'loss': 0.6219, 'learning_rate': 0.00039444138117263755, 'epoch': 3.9}

 32%|███▏      | 9121/28080 [18:01:28<37:37:19,  7.14s/it]
 32%|███▏      | 9122/28080 [18:01:35<37:34:11,  7.13s/it]
                                                          
{'loss': 0.6306, 'learning_rate': 0.0003944178444269362, 'epoch': 3.9}

 32%|███▏      | 9122/28080 [18:01:35<37:34:11,  7.13s/it]
 32%|███▏      | 9123/28080 [18:01:42<37:29:41,  7.12s/it]
                                                          
{'loss': 0.6313, 'learning_rate': 0.0003943943057599044, 'epoch': 3.9}

 32%|███▏      | 9123/28080 [18:01:42<37:29:41,  7.12s/it]
 32%|███▏      | 9124/28080 [18:01:49<37:25:08,  7.11s/it]
                                                          
{'loss': 0.6239, 'learning_rate': 0.00039437076517185535, 'epoch': 3.9}

 32%|███▏      | 9124/28080 [18:01:49<37:25:08,  7.11s/it]
 32%|███▏      | 9125/28080 [18:01:56<37:34:44,  7.14s/it]
                                                          
{'loss': 0.6215, 'learning_rate': 0.0003943472226631021, 'epoch': 3.9}

 32%|███▏      | 9125/28080 [18:01:56<37:34:44,  7.14s/it]
 32%|███▎      | 9126/28080 [18:02:03<37:22:49,  7.10s/it]
                                                          
{'loss': 0.6304, 'learning_rate': 0.0003943236782339581, 'epoch': 3.9}

 32%|███▎      | 9126/28080 [18:02:03<37:22:49,  7.10s/it]
 33%|███▎      | 9127/28080 [18:02:11<37:23:18,  7.10s/it]
                                                          
{'loss': 0.6255, 'learning_rate': 0.0003943001318847364, 'epoch': 3.9}

 33%|███▎      | 9127/28080 [18:02:11<37:23:18,  7.10s/it]
 33%|███▎      | 9128/28080 [18:02:18<37:15:06,  7.08s/it]
                                                          
{'loss': 0.6496, 'learning_rate': 0.0003942765836157503, 'epoch': 3.9}

 33%|███▎      | 9128/28080 [18:02:18<37:15:06,  7.08s/it]
 33%|███▎      | 9129/28080 [18:02:25<37:23:10,  7.10s/it]
                                                          
{'loss': 0.6156, 'learning_rate': 0.0003942530334273131, 'epoch': 3.9}

 33%|███▎      | 9129/28080 [18:02:25<37:23:10,  7.10s/it]
 33%|███▎      | 9130/28080 [18:02:32<37:24:30,  7.11s/it]
                                                          
{'loss': 0.6224, 'learning_rate': 0.00039422948131973814, 'epoch': 3.9}

 33%|███▎      | 9130/28080 [18:02:32<37:24:30,  7.11s/it]
 33%|███▎      | 9131/28080 [18:02:39<37:25:45,  7.11s/it]
                                                          
{'loss': 0.6218, 'learning_rate': 0.0003942059272933387, 'epoch': 3.9}

 33%|███▎      | 9131/28080 [18:02:39<37:25:45,  7.11s/it]
 33%|███▎      | 9132/28080 [18:02:46<37:28:08,  7.12s/it]
                                                          
{'loss': 0.6351, 'learning_rate': 0.00039418237134842816, 'epoch': 3.9}

 33%|███▎      | 9132/28080 [18:02:46<37:28:08,  7.12s/it]
 33%|███▎      | 9133/28080 [18:02:53<37:25:56,  7.11s/it]
                                                          
{'loss': 0.6099, 'learning_rate': 0.0003941588134853199, 'epoch': 3.9}

 33%|███▎      | 9133/28080 [18:02:53<37:25:56,  7.11s/it]
 33%|███▎      | 9134/28080 [18:03:00<37:33:00,  7.14s/it]
                                                          
{'loss': 0.6513, 'learning_rate': 0.0003941352537043274, 'epoch': 3.9}

 33%|███▎      | 9134/28080 [18:03:00<37:33:00,  7.14s/it]
 33%|███▎      | 9135/28080 [18:03:08<37:29:03,  7.12s/it]
                                                          
{'loss': 0.6352, 'learning_rate': 0.00039411169200576405, 'epoch': 3.9}

 33%|███▎      | 9135/28080 [18:03:08<37:29:03,  7.12s/it]
 33%|███▎      | 9136/28080 [18:03:15<37:28:13,  7.12s/it]
                                                          
{'loss': 0.6304, 'learning_rate': 0.0003940881283899432, 'epoch': 3.9}

 33%|███▎      | 9136/28080 [18:03:15<37:28:13,  7.12s/it]
 33%|███▎      | 9137/28080 [18:03:22<37:26:54,  7.12s/it]
                                                          
{'loss': 0.626, 'learning_rate': 0.0003940645628571786, 'epoch': 3.9}

 33%|███▎      | 9137/28080 [18:03:22<37:26:54,  7.12s/it]
 33%|███▎      | 9138/28080 [18:03:29<37:33:05,  7.14s/it]
                                                          
{'loss': 0.6208, 'learning_rate': 0.0003940409954077835, 'epoch': 3.9}

 33%|███▎      | 9138/28080 [18:03:29<37:33:05,  7.14s/it]
 33%|███▎      | 9139/28080 [18:03:36<37:49:24,  7.19s/it]
                                                          
{'loss': 0.6083, 'learning_rate': 0.00039401742604207155, 'epoch': 3.9}

 33%|███▎      | 9139/28080 [18:03:36<37:49:24,  7.19s/it]
 33%|███▎      | 9140/28080 [18:03:43<37:49:33,  7.19s/it]
                                                          
{'loss': 0.6211, 'learning_rate': 0.00039399385476035644, 'epoch': 3.9}

 33%|███▎      | 9140/28080 [18:03:43<37:49:33,  7.19s/it]
 33%|███▎      | 9141/28080 [18:03:51<37:51:10,  7.20s/it]
                                                          
{'loss': 0.6226, 'learning_rate': 0.00039397028156295155, 'epoch': 3.9}

 33%|███▎      | 9141/28080 [18:03:51<37:51:10,  7.20s/it]
 33%|███▎      | 9142/28080 [18:03:58<37:50:06,  7.19s/it]
                                                          
{'loss': 0.6261, 'learning_rate': 0.0003939467064501706, 'epoch': 3.91}

 33%|███▎      | 9142/28080 [18:03:58<37:50:06,  7.19s/it]
 33%|███▎      | 9143/28080 [18:04:05<37:42:04,  7.17s/it]
                                                          
{'loss': 0.6383, 'learning_rate': 0.0003939231294223272, 'epoch': 3.91}

 33%|███▎      | 9143/28080 [18:04:05<37:42:04,  7.17s/it]
 33%|███▎      | 9144/28080 [18:04:12<37:39:10,  7.16s/it]
                                                          
{'loss': 0.6359, 'learning_rate': 0.0003938995504797351, 'epoch': 3.91}

 33%|███▎      | 9144/28080 [18:04:12<37:39:10,  7.16s/it]
 33%|███▎      | 9145/28080 [18:04:19<37:27:31,  7.12s/it]
                                                          
{'loss': 0.6274, 'learning_rate': 0.000393875969622708, 'epoch': 3.91}

 33%|███▎      | 9145/28080 [18:04:19<37:27:31,  7.12s/it]
 33%|███▎      | 9146/28080 [18:04:26<37:30:52,  7.13s/it]
                                                          
{'loss': 0.6359, 'learning_rate': 0.00039385238685155945, 'epoch': 3.91}

 33%|███▎      | 9146/28080 [18:04:26<37:30:52,  7.13s/it]
 33%|███▎      | 9147/28080 [18:04:33<37:16:59,  7.09s/it]
                                                          
{'loss': 0.642, 'learning_rate': 0.0003938288021666032, 'epoch': 3.91}

 33%|███▎      | 9147/28080 [18:04:33<37:16:59,  7.09s/it]
 33%|███▎      | 9148/28080 [18:04:40<37:25:23,  7.12s/it]
                                                          
{'loss': 0.6233, 'learning_rate': 0.0003938052155681533, 'epoch': 3.91}

 33%|███▎      | 9148/28080 [18:04:40<37:25:23,  7.12s/it]
 33%|███▎      | 9149/28080 [18:04:48<37:28:59,  7.13s/it]
                                                          
{'loss': 0.6387, 'learning_rate': 0.00039378162705652325, 'epoch': 3.91}

 33%|███▎      | 9149/28080 [18:04:48<37:28:59,  7.13s/it]
 33%|███▎      | 9150/28080 [18:04:55<37:33:57,  7.14s/it]
                                                          
{'loss': 0.622, 'learning_rate': 0.000393758036632027, 'epoch': 3.91}

 33%|███▎      | 9150/28080 [18:04:55<37:33:57,  7.14s/it]
 33%|███▎      | 9151/28080 [18:05:02<37:38:48,  7.16s/it]
                                                          
{'loss': 0.6201, 'learning_rate': 0.0003937344442949784, 'epoch': 3.91}

 33%|███▎      | 9151/28080 [18:05:02<37:38:48,  7.16s/it]
 33%|███▎      | 9152/28080 [18:05:09<37:43:19,  7.17s/it]
                                                          
{'loss': 0.6398, 'learning_rate': 0.00039371085004569136, 'epoch': 3.91}

 33%|███▎      | 9152/28080 [18:05:09<37:43:19,  7.17s/it]
 33%|███▎      | 9153/28080 [18:05:16<37:28:38,  7.13s/it]
                                                          
{'loss': 0.6385, 'learning_rate': 0.0003936872538844796, 'epoch': 3.91}

 33%|███▎      | 9153/28080 [18:05:16<37:28:38,  7.13s/it]
 33%|███▎      | 9154/28080 [18:05:23<37:24:44,  7.12s/it]
                                                          
{'loss': 0.6413, 'learning_rate': 0.0003936636558116572, 'epoch': 3.91}

 33%|███▎      | 9154/28080 [18:05:23<37:24:44,  7.12s/it]
 33%|███▎      | 9155/28080 [18:05:30<37:26:19,  7.12s/it]
                                                          
{'loss': 0.6294, 'learning_rate': 0.00039364005582753813, 'epoch': 3.91}

 33%|███▎      | 9155/28080 [18:05:30<37:26:19,  7.12s/it]
 33%|███▎      | 9156/28080 [18:05:38<37:28:11,  7.13s/it]
                                                          
{'loss': 0.6353, 'learning_rate': 0.0003936164539324363, 'epoch': 3.91}

 33%|███▎      | 9156/28080 [18:05:38<37:28:11,  7.13s/it]
 33%|███▎      | 9157/28080 [18:05:45<37:43:15,  7.18s/it]
                                                          
{'loss': 0.613, 'learning_rate': 0.00039359285012666563, 'epoch': 3.91}

 33%|███▎      | 9157/28080 [18:05:45<37:43:15,  7.18s/it]
 33%|███▎      | 9158/28080 [18:05:52<37:43:56,  7.18s/it]
                                                          
{'loss': 0.64, 'learning_rate': 0.0003935692444105403, 'epoch': 3.91}

 33%|███▎      | 9158/28080 [18:05:52<37:43:56,  7.18s/it]
 33%|███▎      | 9159/28080 [18:05:59<37:35:02,  7.15s/it]
                                                          
{'loss': 0.6551, 'learning_rate': 0.00039354563678437423, 'epoch': 3.91}

 33%|███▎      | 9159/28080 [18:05:59<37:35:02,  7.15s/it]
 33%|███▎      | 9160/28080 [18:06:06<37:32:51,  7.14s/it]
                                                          
{'loss': 0.6324, 'learning_rate': 0.00039352202724848157, 'epoch': 3.91}

 33%|███▎      | 9160/28080 [18:06:06<37:32:51,  7.14s/it]
 33%|███▎      | 9161/28080 [18:06:13<37:35:24,  7.15s/it]
                                                          
{'loss': 0.63, 'learning_rate': 0.00039349841580317633, 'epoch': 3.91}

 33%|███▎      | 9161/28080 [18:06:13<37:35:24,  7.15s/it]
 33%|███▎      | 9162/28080 [18:06:21<37:33:09,  7.15s/it]
                                                          
{'loss': 0.6464, 'learning_rate': 0.00039347480244877284, 'epoch': 3.91}

 33%|███▎      | 9162/28080 [18:06:21<37:33:09,  7.15s/it]
 33%|███▎      | 9163/28080 [18:06:28<37:41:03,  7.17s/it]
                                                          
{'loss': 0.6346, 'learning_rate': 0.000393451187185585, 'epoch': 3.91}

 33%|███▎      | 9163/28080 [18:06:28<37:41:03,  7.17s/it]
 33%|███▎      | 9164/28080 [18:06:35<37:38:54,  7.17s/it]
                                                          
{'loss': 0.6179, 'learning_rate': 0.0003934275700139272, 'epoch': 3.91}

 33%|███▎      | 9164/28080 [18:06:35<37:38:54,  7.17s/it]
 33%|███▎      | 9165/28080 [18:06:42<37:41:05,  7.17s/it]
                                                          
{'loss': 0.6382, 'learning_rate': 0.00039340395093411353, 'epoch': 3.92}

 33%|███▎      | 9165/28080 [18:06:42<37:41:05,  7.17s/it]
 33%|███▎      | 9166/28080 [18:06:49<37:37:05,  7.16s/it]
                                                          
{'loss': 0.6264, 'learning_rate': 0.0003933803299464582, 'epoch': 3.92}

 33%|███▎      | 9166/28080 [18:06:49<37:37:05,  7.16s/it]
 33%|███▎      | 9167/28080 [18:06:57<37:47:03,  7.19s/it]
                                                          
{'loss': 0.6132, 'learning_rate': 0.0003933567070512755, 'epoch': 3.92}

 33%|███▎      | 9167/28080 [18:06:57<37:47:03,  7.19s/it]
 33%|███▎      | 9168/28080 [18:07:04<37:46:25,  7.19s/it]
                                                          
{'loss': 0.6276, 'learning_rate': 0.00039333308224887974, 'epoch': 3.92}

 33%|███▎      | 9168/28080 [18:07:04<37:46:25,  7.19s/it]
 33%|███▎      | 9169/28080 [18:07:11<37:44:13,  7.18s/it]
                                                          
{'loss': 0.6405, 'learning_rate': 0.0003933094555395852, 'epoch': 3.92}

 33%|███▎      | 9169/28080 [18:07:11<37:44:13,  7.18s/it]
 33%|███▎      | 9170/28080 [18:07:18<37:42:16,  7.18s/it]
                                                          
{'loss': 0.6254, 'learning_rate': 0.00039328582692370616, 'epoch': 3.92}

 33%|███▎      | 9170/28080 [18:07:18<37:42:16,  7.18s/it]
 33%|███▎      | 9171/28080 [18:07:25<37:36:47,  7.16s/it]
                                                          
{'loss': 0.6193, 'learning_rate': 0.00039326219640155704, 'epoch': 3.92}

 33%|███▎      | 9171/28080 [18:07:25<37:36:47,  7.16s/it]
 33%|███▎      | 9172/28080 [18:07:32<37:27:10,  7.13s/it]
                                                          
{'loss': 0.6266, 'learning_rate': 0.00039323856397345216, 'epoch': 3.92}

 33%|███▎      | 9172/28080 [18:07:32<37:27:10,  7.13s/it]
 33%|███▎      | 9173/28080 [18:07:39<37:34:41,  7.16s/it]
                                                          
{'loss': 0.6193, 'learning_rate': 0.00039321492963970595, 'epoch': 3.92}

 33%|███▎      | 9173/28080 [18:07:39<37:34:41,  7.16s/it]
 33%|███▎      | 9174/28080 [18:07:47<37:34:11,  7.15s/it]
                                                          
{'loss': 0.6379, 'learning_rate': 0.0003931912934006329, 'epoch': 3.92}

 33%|███▎      | 9174/28080 [18:07:47<37:34:11,  7.15s/it]
 33%|███▎      | 9175/28080 [18:07:54<37:23:03,  7.12s/it]
                                                          
{'loss': 0.6414, 'learning_rate': 0.00039316765525654736, 'epoch': 3.92}

 33%|███▎      | 9175/28080 [18:07:54<37:23:03,  7.12s/it]
 33%|███▎      | 9176/28080 [18:08:01<37:20:18,  7.11s/it]
                                                          
{'loss': 0.6211, 'learning_rate': 0.00039314401520776387, 'epoch': 3.92}

 33%|███▎      | 9176/28080 [18:08:01<37:20:18,  7.11s/it]
 33%|███▎      | 9177/28080 [18:08:08<37:22:32,  7.12s/it]
                                                          
{'loss': 0.6568, 'learning_rate': 0.00039312037325459694, 'epoch': 3.92}

 33%|███▎      | 9177/28080 [18:08:08<37:22:32,  7.12s/it]
 33%|███▎      | 9178/28080 [18:08:15<37:33:36,  7.15s/it]
                                                          
{'loss': 0.6293, 'learning_rate': 0.0003930967293973611, 'epoch': 3.92}

 33%|███▎      | 9178/28080 [18:08:15<37:33:36,  7.15s/it]
 33%|███▎      | 9179/28080 [18:08:22<37:34:24,  7.16s/it]
                                                          
{'loss': 0.6289, 'learning_rate': 0.00039307308363637086, 'epoch': 3.92}

 33%|███▎      | 9179/28080 [18:08:22<37:34:24,  7.16s/it]
 33%|███▎      | 9180/28080 [18:08:29<37:28:55,  7.14s/it]
                                                          
{'loss': 0.6382, 'learning_rate': 0.00039304943597194086, 'epoch': 3.92}

 33%|███▎      | 9180/28080 [18:08:29<37:28:55,  7.14s/it]
 33%|███▎      | 9181/28080 [18:08:36<37:25:28,  7.13s/it]
                                                          
{'loss': 0.6497, 'learning_rate': 0.00039302578640438576, 'epoch': 3.92}

 33%|███▎      | 9181/28080 [18:08:36<37:25:28,  7.13s/it]
 33%|███▎      | 9182/28080 [18:08:44<37:28:05,  7.14s/it]
                                                          
{'loss': 0.6032, 'learning_rate': 0.00039300213493402006, 'epoch': 3.92}

 33%|███▎      | 9182/28080 [18:08:44<37:28:05,  7.14s/it]
 33%|███▎      | 9183/28080 [18:08:51<37:30:45,  7.15s/it]
                                                          
{'loss': 0.6438, 'learning_rate': 0.0003929784815611585, 'epoch': 3.92}

 33%|███▎      | 9183/28080 [18:08:51<37:30:45,  7.15s/it]
 33%|███▎      | 9184/28080 [18:08:58<37:24:15,  7.13s/it]
                                                          
{'loss': 0.6346, 'learning_rate': 0.0003929548262861158, 'epoch': 3.92}

 33%|███▎      | 9184/28080 [18:08:58<37:24:15,  7.13s/it]
 33%|███▎      | 9185/28080 [18:09:05<37:25:29,  7.13s/it]
                                                          
{'loss': 0.6461, 'learning_rate': 0.00039293116910920647, 'epoch': 3.92}

 33%|███▎      | 9185/28080 [18:09:05<37:25:29,  7.13s/it]
 33%|███▎      | 9186/28080 [18:09:12<37:35:13,  7.16s/it]
                                                          
{'loss': 0.6063, 'learning_rate': 0.00039290751003074546, 'epoch': 3.92}

 33%|███▎      | 9186/28080 [18:09:12<37:35:13,  7.16s/it]
 33%|███▎      | 9187/28080 [18:09:19<37:44:14,  7.19s/it]
                                                          
{'loss': 0.6437, 'learning_rate': 0.00039288384905104747, 'epoch': 3.92}

 33%|███▎      | 9187/28080 [18:09:19<37:44:14,  7.19s/it]
 33%|███▎      | 9188/28080 [18:09:27<37:43:03,  7.19s/it]
                                                          
{'loss': 0.6222, 'learning_rate': 0.0003928601861704273, 'epoch': 3.93}

 33%|███▎      | 9188/28080 [18:09:27<37:43:03,  7.19s/it]
 33%|███▎      | 9189/28080 [18:09:34<37:31:41,  7.15s/it]
                                                          
{'loss': 0.6264, 'learning_rate': 0.00039283652138919975, 'epoch': 3.93}

 33%|███▎      | 9189/28080 [18:09:34<37:31:41,  7.15s/it]
 33%|███▎      | 9190/28080 [18:09:41<37:37:30,  7.17s/it]
                                                          
{'loss': 0.6258, 'learning_rate': 0.00039281285470767956, 'epoch': 3.93}

 33%|███▎      | 9190/28080 [18:09:41<37:37:30,  7.17s/it]
 33%|███▎      | 9191/28080 [18:09:48<37:37:58,  7.17s/it]
                                                          
{'loss': 0.6237, 'learning_rate': 0.00039278918612618174, 'epoch': 3.93}

 33%|███▎      | 9191/28080 [18:09:48<37:37:58,  7.17s/it]
 33%|███▎      | 9192/28080 [18:09:55<37:34:38,  7.16s/it]
                                                          
{'loss': 0.634, 'learning_rate': 0.00039276551564502104, 'epoch': 3.93}

 33%|███▎      | 9192/28080 [18:09:55<37:34:38,  7.16s/it]
 33%|███▎      | 9193/28080 [18:10:02<37:26:54,  7.14s/it]
                                                          
{'loss': 0.6403, 'learning_rate': 0.00039274184326451247, 'epoch': 3.93}

 33%|███▎      | 9193/28080 [18:10:02<37:26:54,  7.14s/it]
 33%|███▎      | 9194/28080 [18:10:10<37:31:32,  7.15s/it]
                                                          
{'loss': 0.6503, 'learning_rate': 0.000392718168984971, 'epoch': 3.93}

 33%|███▎      | 9194/28080 [18:10:10<37:31:32,  7.15s/it]
 33%|███▎      | 9195/28080 [18:10:17<37:31:30,  7.15s/it]
                                                          
{'loss': 0.6121, 'learning_rate': 0.0003926944928067114, 'epoch': 3.93}

 33%|███▎      | 9195/28080 [18:10:17<37:31:30,  7.15s/it]
 33%|███▎      | 9196/28080 [18:10:24<37:44:06,  7.19s/it]
                                                          
{'loss': 0.6351, 'learning_rate': 0.00039267081473004885, 'epoch': 3.93}

 33%|███▎      | 9196/28080 [18:10:24<37:44:06,  7.19s/it]
 33%|███▎      | 9197/28080 [18:10:31<37:39:00,  7.18s/it]
                                                          
{'loss': 0.6164, 'learning_rate': 0.0003926471347552983, 'epoch': 3.93}

 33%|███▎      | 9197/28080 [18:10:31<37:39:00,  7.18s/it]
 33%|███▎      | 9198/28080 [18:10:38<37:27:33,  7.14s/it]
                                                          
{'loss': 0.6256, 'learning_rate': 0.0003926234528827748, 'epoch': 3.93}

 33%|███▎      | 9198/28080 [18:10:38<37:27:33,  7.14s/it]
 33%|███▎      | 9199/28080 [18:10:45<37:29:00,  7.15s/it]
                                                          
{'loss': 0.626, 'learning_rate': 0.0003925997691127934, 'epoch': 3.93}

 33%|███▎      | 9199/28080 [18:10:45<37:29:00,  7.15s/it]
 33%|███▎      | 9200/28080 [18:10:52<37:29:55,  7.15s/it]
                                                          
{'loss': 0.6317, 'learning_rate': 0.0003925760834456691, 'epoch': 3.93}

 33%|███▎      | 9200/28080 [18:10:52<37:29:55,  7.15s/it]
 33%|███▎      | 9201/28080 [18:11:00<37:21:50,  7.12s/it]
                                                          
{'loss': 0.6306, 'learning_rate': 0.0003925523958817172, 'epoch': 3.93}

 33%|███▎      | 9201/28080 [18:11:00<37:21:50,  7.12s/it]
 33%|███▎      | 9202/28080 [18:11:07<37:23:09,  7.13s/it]
                                                          
{'loss': 0.6313, 'learning_rate': 0.0003925287064212526, 'epoch': 3.93}

 33%|███▎      | 9202/28080 [18:11:07<37:23:09,  7.13s/it]
 33%|███▎      | 9203/28080 [18:11:14<37:26:21,  7.14s/it]
                                                          
{'loss': 0.6218, 'learning_rate': 0.0003925050150645907, 'epoch': 3.93}

 33%|███▎      | 9203/28080 [18:11:14<37:26:21,  7.14s/it]
 33%|███▎      | 9204/28080 [18:11:21<37:19:19,  7.12s/it]
                                                          
{'loss': 0.6187, 'learning_rate': 0.0003924813218120466, 'epoch': 3.93}

 33%|███▎      | 9204/28080 [18:11:21<37:19:19,  7.12s/it]
 33%|███▎      | 9205/28080 [18:11:28<37:33:00,  7.16s/it]
                                                          
{'loss': 0.6361, 'learning_rate': 0.00039245762666393545, 'epoch': 3.93}

 33%|███▎      | 9205/28080 [18:11:28<37:33:00,  7.16s/it]
 33%|███▎      | 9206/28080 [18:11:35<37:32:25,  7.16s/it]
                                                          
{'loss': 0.6205, 'learning_rate': 0.00039243392962057255, 'epoch': 3.93}

 33%|███▎      | 9206/28080 [18:11:35<37:32:25,  7.16s/it]
 33%|███▎      | 9207/28080 [18:11:42<37:27:28,  7.15s/it]
                                                          
{'loss': 0.6085, 'learning_rate': 0.00039241023068227324, 'epoch': 3.93}

 33%|███▎      | 9207/28080 [18:11:42<37:27:28,  7.15s/it]
 33%|███▎      | 9208/28080 [18:11:50<37:27:39,  7.15s/it]
                                                          
{'loss': 0.6476, 'learning_rate': 0.00039238652984935265, 'epoch': 3.93}

 33%|███▎      | 9208/28080 [18:11:50<37:27:39,  7.15s/it]
 33%|███▎      | 9209/28080 [18:11:57<37:30:59,  7.16s/it]
                                                          
{'loss': 0.6232, 'learning_rate': 0.00039236282712212616, 'epoch': 3.93}

 33%|███▎      | 9209/28080 [18:11:57<37:30:59,  7.16s/it]
 33%|███▎      | 9210/28080 [18:12:04<37:24:14,  7.14s/it]
                                                          
{'loss': 0.6235, 'learning_rate': 0.0003923391225009092, 'epoch': 3.93}

 33%|███▎      | 9210/28080 [18:12:04<37:24:14,  7.14s/it]
 33%|███▎      | 9211/28080 [18:12:11<37:29:30,  7.15s/it]
                                                          
{'loss': 0.6308, 'learning_rate': 0.00039231541598601697, 'epoch': 3.93}

 33%|███▎      | 9211/28080 [18:12:11<37:29:30,  7.15s/it]
 33%|███▎      | 9212/28080 [18:12:18<37:26:27,  7.14s/it]
                                                          
{'loss': 0.6411, 'learning_rate': 0.000392291707577765, 'epoch': 3.94}

 33%|███▎      | 9212/28080 [18:12:18<37:26:27,  7.14s/it]
 33%|███▎      | 9213/28080 [18:12:25<37:28:29,  7.15s/it]
                                                          
{'loss': 0.6073, 'learning_rate': 0.00039226799727646867, 'epoch': 3.94}

 33%|███▎      | 9213/28080 [18:12:25<37:28:29,  7.15s/it]
 33%|███▎      | 9214/28080 [18:12:32<37:26:03,  7.14s/it]
                                                          
{'loss': 0.6497, 'learning_rate': 0.00039224428508244336, 'epoch': 3.94}

 33%|███▎      | 9214/28080 [18:12:32<37:26:03,  7.14s/it]
 33%|███▎      | 9215/28080 [18:12:40<37:23:42,  7.14s/it]
                                                          
{'loss': 0.6392, 'learning_rate': 0.00039222057099600464, 'epoch': 3.94}

 33%|███▎      | 9215/28080 [18:12:40<37:23:42,  7.14s/it]
 33%|███▎      | 9216/28080 [18:12:47<37:25:01,  7.14s/it]
                                                          
{'loss': 0.6496, 'learning_rate': 0.00039219685501746783, 'epoch': 3.94}

 33%|███▎      | 9216/28080 [18:12:47<37:25:01,  7.14s/it]
 33%|███▎      | 9217/28080 [18:12:54<37:32:29,  7.16s/it]
                                                          
{'loss': 0.6374, 'learning_rate': 0.0003921731371471486, 'epoch': 3.94}

 33%|███▎      | 9217/28080 [18:12:54<37:32:29,  7.16s/it]
 33%|███▎      | 9218/28080 [18:13:01<37:24:09,  7.14s/it]
                                                          
{'loss': 0.6557, 'learning_rate': 0.00039214941738536255, 'epoch': 3.94}

 33%|███▎      | 9218/28080 [18:13:01<37:24:09,  7.14s/it]
 33%|███▎      | 9219/28080 [18:13:08<37:30:31,  7.16s/it]
                                                          
{'loss': 0.628, 'learning_rate': 0.0003921256957324251, 'epoch': 3.94}

 33%|███▎      | 9219/28080 [18:13:08<37:30:31,  7.16s/it]
 33%|███▎      | 9220/28080 [18:13:15<37:28:16,  7.15s/it]
                                                          
{'loss': 0.6255, 'learning_rate': 0.00039210197218865185, 'epoch': 3.94}

 33%|███▎      | 9220/28080 [18:13:15<37:28:16,  7.15s/it]
 33%|███▎      | 9221/28080 [18:13:22<37:16:12,  7.11s/it]
                                                          
{'loss': 0.6134, 'learning_rate': 0.0003920782467543585, 'epoch': 3.94}

 33%|███▎      | 9221/28080 [18:13:22<37:16:12,  7.11s/it]
 33%|███▎      | 9222/28080 [18:13:29<37:12:57,  7.10s/it]
                                                          
{'loss': 0.6168, 'learning_rate': 0.00039205451942986064, 'epoch': 3.94}

 33%|███▎      | 9222/28080 [18:13:29<37:12:57,  7.10s/it]
 33%|███▎      | 9223/28080 [18:13:37<37:24:47,  7.14s/it]
                                                          
{'loss': 0.6234, 'learning_rate': 0.0003920307902154739, 'epoch': 3.94}

 33%|███▎      | 9223/28080 [18:13:37<37:24:47,  7.14s/it]
 33%|███▎      | 9224/28080 [18:13:44<37:20:00,  7.13s/it]
                                                          
{'loss': 0.6124, 'learning_rate': 0.0003920070591115141, 'epoch': 3.94}

 33%|███▎      | 9224/28080 [18:13:44<37:20:00,  7.13s/it]
 33%|███▎      | 9225/28080 [18:13:51<37:13:00,  7.11s/it]
                                                          
{'loss': 0.6247, 'learning_rate': 0.0003919833261182969, 'epoch': 3.94}

 33%|███▎      | 9225/28080 [18:13:51<37:13:00,  7.11s/it]
 33%|███▎      | 9226/28080 [18:13:58<37:24:37,  7.14s/it]
                                                          
{'loss': 0.6268, 'learning_rate': 0.00039195959123613795, 'epoch': 3.94}

 33%|███▎      | 9226/28080 [18:13:58<37:24:37,  7.14s/it]
 33%|███▎      | 9227/28080 [18:14:05<37:22:10,  7.14s/it]
                                                          
{'loss': 0.6265, 'learning_rate': 0.00039193585446535307, 'epoch': 3.94}

 33%|███▎      | 9227/28080 [18:14:05<37:22:10,  7.14s/it]
 33%|███▎      | 9228/28080 [18:14:12<37:23:37,  7.14s/it]
                                                          
{'loss': 0.6444, 'learning_rate': 0.0003919121158062581, 'epoch': 3.94}

 33%|███▎      | 9228/28080 [18:14:12<37:23:37,  7.14s/it]
 33%|███▎      | 9229/28080 [18:14:19<37:22:06,  7.14s/it]
                                                          
{'loss': 0.6508, 'learning_rate': 0.00039188837525916886, 'epoch': 3.94}

 33%|███▎      | 9229/28080 [18:14:19<37:22:06,  7.14s/it]
 33%|███▎      | 9230/28080 [18:14:27<37:22:46,  7.14s/it]
                                                          
{'loss': 0.6197, 'learning_rate': 0.00039186463282440113, 'epoch': 3.94}

 33%|███▎      | 9230/28080 [18:14:27<37:22:46,  7.14s/it]
 33%|███▎      | 9231/28080 [18:14:34<37:17:36,  7.12s/it]
                                                          
{'loss': 0.6307, 'learning_rate': 0.00039184088850227085, 'epoch': 3.94}

 33%|███▎      | 9231/28080 [18:14:34<37:17:36,  7.12s/it]
 33%|███▎      | 9232/28080 [18:14:41<37:18:36,  7.13s/it]
                                                          
{'loss': 0.6203, 'learning_rate': 0.00039181714229309384, 'epoch': 3.94}

 33%|███▎      | 9232/28080 [18:14:41<37:18:36,  7.13s/it]
 33%|███▎      | 9233/28080 [18:14:48<37:22:08,  7.14s/it]
                                                          
{'loss': 0.6211, 'learning_rate': 0.00039179339419718605, 'epoch': 3.94}

 33%|███▎      | 9233/28080 [18:14:48<37:22:08,  7.14s/it]
 33%|███▎      | 9234/28080 [18:14:55<37:24:43,  7.15s/it]
                                                          
{'loss': 0.6306, 'learning_rate': 0.0003917696442148635, 'epoch': 3.94}

 33%|███▎      | 9234/28080 [18:14:55<37:24:43,  7.15s/it]
 33%|███▎      | 9235/28080 [18:15:02<37:19:36,  7.13s/it]
                                                          
{'loss': 0.6335, 'learning_rate': 0.00039174589234644206, 'epoch': 3.95}

 33%|███▎      | 9235/28080 [18:15:02<37:19:36,  7.13s/it]
 33%|███▎      | 9236/28080 [18:15:09<37:27:26,  7.16s/it]
                                                          
{'loss': 0.6251, 'learning_rate': 0.00039172213859223773, 'epoch': 3.95}

 33%|███▎      | 9236/28080 [18:15:10<37:27:26,  7.16s/it]
 33%|███▎      | 9237/28080 [18:15:17<37:28:06,  7.16s/it]
                                                          
{'loss': 0.6466, 'learning_rate': 0.0003916983829525665, 'epoch': 3.95}

 33%|███▎      | 9237/28080 [18:15:17<37:28:06,  7.16s/it]
 33%|███▎      | 9238/28080 [18:15:24<37:33:04,  7.17s/it]
                                                          
{'loss': 0.6121, 'learning_rate': 0.0003916746254277446, 'epoch': 3.95}

 33%|███▎      | 9238/28080 [18:15:24<37:33:04,  7.17s/it]
 33%|███▎      | 9239/28080 [18:15:31<37:24:23,  7.15s/it]
                                                          
{'loss': 0.6344, 'learning_rate': 0.00039165086601808787, 'epoch': 3.95}

 33%|███▎      | 9239/28080 [18:15:31<37:24:23,  7.15s/it]
 33%|███▎      | 9240/28080 [18:15:38<37:32:03,  7.17s/it]
                                                          
{'loss': 0.6323, 'learning_rate': 0.0003916271047239125, 'epoch': 3.95}

 33%|███▎      | 9240/28080 [18:15:38<37:32:03,  7.17s/it]
 33%|███▎      | 9241/28080 [18:15:45<37:23:03,  7.14s/it]
                                                          
{'loss': 0.6268, 'learning_rate': 0.00039160334154553466, 'epoch': 3.95}

 33%|███▎      | 9241/28080 [18:15:45<37:23:03,  7.14s/it]
 33%|███▎      | 9242/28080 [18:15:52<37:23:56,  7.15s/it]
                                                          
{'loss': 0.642, 'learning_rate': 0.00039157957648327043, 'epoch': 3.95}

 33%|███▎      | 9242/28080 [18:15:52<37:23:56,  7.15s/it]
 33%|███▎      | 9243/28080 [18:15:59<37:11:35,  7.11s/it]
                                                          
{'loss': 0.6264, 'learning_rate': 0.000391555809537436, 'epoch': 3.95}

 33%|███▎      | 9243/28080 [18:15:59<37:11:35,  7.11s/it]
 33%|███▎      | 9244/28080 [18:16:06<37:02:21,  7.08s/it]
                                                          
{'loss': 0.6349, 'learning_rate': 0.00039153204070834755, 'epoch': 3.95}

 33%|███▎      | 9244/28080 [18:16:06<37:02:21,  7.08s/it]
 33%|███▎      | 9245/28080 [18:16:14<37:08:13,  7.10s/it]
                                                          
{'loss': 0.6069, 'learning_rate': 0.0003915082699963213, 'epoch': 3.95}

 33%|███▎      | 9245/28080 [18:16:14<37:08:13,  7.10s/it]
 33%|███▎      | 9246/28080 [18:16:21<37:21:23,  7.14s/it]
                                                          
{'loss': 0.6217, 'learning_rate': 0.00039148449740167345, 'epoch': 3.95}

 33%|███▎      | 9246/28080 [18:16:21<37:21:23,  7.14s/it]
 33%|███▎      | 9247/28080 [18:16:28<37:16:44,  7.13s/it]
                                                          
{'loss': 0.6263, 'learning_rate': 0.00039146072292472046, 'epoch': 3.95}

 33%|███▎      | 9247/28080 [18:16:28<37:16:44,  7.13s/it]
 33%|███▎      | 9248/28080 [18:16:35<37:11:54,  7.11s/it]
                                                          
{'loss': 0.6147, 'learning_rate': 0.0003914369465657784, 'epoch': 3.95}

 33%|███▎      | 9248/28080 [18:16:35<37:11:54,  7.11s/it]
 33%|███▎      | 9249/28080 [18:16:42<37:05:39,  7.09s/it]
                                                          
{'loss': 0.6227, 'learning_rate': 0.00039141316832516366, 'epoch': 3.95}

 33%|███▎      | 9249/28080 [18:16:42<37:05:39,  7.09s/it]
 33%|███▎      | 9250/28080 [18:16:49<37:15:42,  7.12s/it]
                                                          
{'loss': 0.6374, 'learning_rate': 0.00039138938820319264, 'epoch': 3.95}

 33%|███▎      | 9250/28080 [18:16:49<37:15:42,  7.12s/it]
 33%|███▎      | 9251/28080 [18:16:56<37:03:11,  7.08s/it]
                                                          
{'loss': 0.6465, 'learning_rate': 0.00039136560620018165, 'epoch': 3.95}

 33%|███▎      | 9251/28080 [18:16:56<37:03:11,  7.08s/it]
 33%|███▎      | 9252/28080 [18:17:03<37:02:56,  7.08s/it]
                                                          
{'loss': 0.6165, 'learning_rate': 0.0003913418223164471, 'epoch': 3.95}

 33%|███▎      | 9252/28080 [18:17:03<37:02:56,  7.08s/it]
 33%|███▎      | 9253/28080 [18:17:10<37:02:37,  7.08s/it]
                                                          
{'loss': 0.6448, 'learning_rate': 0.0003913180365523055, 'epoch': 3.95}

 33%|███▎      | 9253/28080 [18:17:10<37:02:37,  7.08s/it]
 33%|███▎      | 9254/28080 [18:17:18<37:08:16,  7.10s/it]
                                                          
{'loss': 0.6497, 'learning_rate': 0.00039129424890807306, 'epoch': 3.95}

 33%|███▎      | 9254/28080 [18:17:18<37:08:16,  7.10s/it]
 33%|███▎      | 9255/28080 [18:17:25<37:13:14,  7.12s/it]
                                                          
{'loss': 0.6323, 'learning_rate': 0.0003912704593840666, 'epoch': 3.95}

 33%|███▎      | 9255/28080 [18:17:25<37:13:14,  7.12s/it]
 33%|███▎      | 9256/28080 [18:17:32<37:13:50,  7.12s/it]
                                                          
{'loss': 0.6354, 'learning_rate': 0.00039124666798060224, 'epoch': 3.95}

 33%|███▎      | 9256/28080 [18:17:32<37:13:50,  7.12s/it]
 33%|███▎      | 9257/28080 [18:17:39<37:15:12,  7.12s/it]
                                                          
{'loss': 0.643, 'learning_rate': 0.0003912228746979968, 'epoch': 3.95}

 33%|███▎      | 9257/28080 [18:17:39<37:15:12,  7.12s/it]
 33%|███▎      | 9258/28080 [18:17:46<37:15:59,  7.13s/it]
                                                          
{'loss': 0.6249, 'learning_rate': 0.00039119907953656663, 'epoch': 3.95}

 33%|███▎      | 9258/28080 [18:17:46<37:15:59,  7.13s/it]
 33%|███▎      | 9259/28080 [18:17:53<37:15:18,  7.13s/it]
                                                          
{'loss': 0.6313, 'learning_rate': 0.00039117528249662837, 'epoch': 3.96}

 33%|███▎      | 9259/28080 [18:17:53<37:15:18,  7.13s/it]
 33%|███▎      | 9260/28080 [18:18:00<36:58:43,  7.07s/it]
                                                          
{'loss': 0.6682, 'learning_rate': 0.00039115148357849865, 'epoch': 3.96}

 33%|███▎      | 9260/28080 [18:18:00<36:58:43,  7.07s/it]
 33%|███▎      | 9261/28080 [18:18:07<37:00:21,  7.08s/it]
                                                          
{'loss': 0.6111, 'learning_rate': 0.00039112768278249413, 'epoch': 3.96}

 33%|███▎      | 9261/28080 [18:18:07<37:00:21,  7.08s/it]
 33%|███▎      | 9262/28080 [18:18:15<37:21:34,  7.15s/it]
                                                          
{'loss': 0.6183, 'learning_rate': 0.0003911038801089313, 'epoch': 3.96}

 33%|███▎      | 9262/28080 [18:18:15<37:21:34,  7.15s/it]
 33%|███▎      | 9263/28080 [18:18:22<37:19:30,  7.14s/it]
                                                          
{'loss': 0.618, 'learning_rate': 0.00039108007555812684, 'epoch': 3.96}

 33%|███▎      | 9263/28080 [18:18:22<37:19:30,  7.14s/it]
 33%|███▎      | 9264/28080 [18:18:29<37:22:16,  7.15s/it]
                                                          
{'loss': 0.6144, 'learning_rate': 0.0003910562691303976, 'epoch': 3.96}

 33%|███▎      | 9264/28080 [18:18:29<37:22:16,  7.15s/it]
 33%|███▎      | 9265/28080 [18:18:36<37:20:01,  7.14s/it]
                                                          
{'loss': 0.6634, 'learning_rate': 0.00039103246082606023, 'epoch': 3.96}

 33%|███▎      | 9265/28080 [18:18:36<37:20:01,  7.14s/it]
 33%|███▎      | 9266/28080 [18:18:43<37:14:58,  7.13s/it]
                                                          
{'loss': 0.6319, 'learning_rate': 0.00039100865064543145, 'epoch': 3.96}

 33%|███▎      | 9266/28080 [18:18:43<37:14:58,  7.13s/it]
 33%|███▎      | 9267/28080 [18:18:50<37:09:15,  7.11s/it]
                                                          
{'loss': 0.6278, 'learning_rate': 0.0003909848385888281, 'epoch': 3.96}

 33%|███▎      | 9267/28080 [18:18:50<37:09:15,  7.11s/it]
 33%|███▎      | 9268/28080 [18:18:57<37:01:38,  7.09s/it]
                                                          
{'loss': 0.6136, 'learning_rate': 0.00039096102465656694, 'epoch': 3.96}

 33%|███▎      | 9268/28080 [18:18:57<37:01:38,  7.09s/it]
 33%|███▎      | 9269/28080 [18:19:04<37:14:36,  7.13s/it]
                                                          
{'loss': 0.6337, 'learning_rate': 0.00039093720884896465, 'epoch': 3.96}

 33%|███▎      | 9269/28080 [18:19:04<37:14:36,  7.13s/it]
 33%|███▎      | 9270/28080 [18:19:12<37:18:39,  7.14s/it]
                                                          
{'loss': 0.6386, 'learning_rate': 0.0003909133911663383, 'epoch': 3.96}

 33%|███▎      | 9270/28080 [18:19:12<37:18:39,  7.14s/it]
 33%|███▎      | 9271/28080 [18:19:19<37:16:29,  7.13s/it]
                                                          
{'loss': 0.6373, 'learning_rate': 0.0003908895716090045, 'epoch': 3.96}

 33%|███▎      | 9271/28080 [18:19:19<37:16:29,  7.13s/it]
 33%|███▎      | 9272/28080 [18:19:26<37:21:53,  7.15s/it]
                                                          
{'loss': 0.6355, 'learning_rate': 0.00039086575017728044, 'epoch': 3.96}

 33%|███▎      | 9272/28080 [18:19:26<37:21:53,  7.15s/it]
 33%|███▎      | 9273/28080 [18:19:33<37:17:30,  7.14s/it]
                                                          
{'loss': 0.6401, 'learning_rate': 0.00039084192687148284, 'epoch': 3.96}

 33%|███▎      | 9273/28080 [18:19:33<37:17:30,  7.14s/it]
 33%|███▎      | 9274/28080 [18:19:40<37:15:43,  7.13s/it]
                                                          
{'loss': 0.6189, 'learning_rate': 0.0003908181016919287, 'epoch': 3.96}

 33%|███▎      | 9274/28080 [18:19:40<37:15:43,  7.13s/it]
 33%|███▎      | 9275/28080 [18:19:47<37:14:20,  7.13s/it]
                                                          
{'loss': 0.6217, 'learning_rate': 0.00039079427463893505, 'epoch': 3.96}

 33%|███▎      | 9275/28080 [18:19:47<37:14:20,  7.13s/it]
 33%|███▎      | 9276/28080 [18:19:54<37:09:48,  7.11s/it]
                                                          
{'loss': 0.6286, 'learning_rate': 0.00039077044571281873, 'epoch': 3.96}

 33%|███▎      | 9276/28080 [18:19:54<37:09:48,  7.11s/it]
 33%|███▎      | 9277/28080 [18:20:01<37:08:40,  7.11s/it]
                                                          
{'loss': 0.6339, 'learning_rate': 0.0003907466149138969, 'epoch': 3.96}

 33%|███▎      | 9277/28080 [18:20:01<37:08:40,  7.11s/it]
 33%|███▎      | 9278/28080 [18:20:09<37:16:37,  7.14s/it]
                                                          
{'loss': 0.6475, 'learning_rate': 0.0003907227822424866, 'epoch': 3.96}

 33%|███▎      | 9278/28080 [18:20:09<37:16:37,  7.14s/it]
 33%|███▎      | 9279/28080 [18:20:16<37:19:26,  7.15s/it]
                                                          
{'loss': 0.6064, 'learning_rate': 0.0003906989476989048, 'epoch': 3.96}

 33%|███▎      | 9279/28080 [18:20:16<37:19:26,  7.15s/it]
 33%|███▎      | 9280/28080 [18:20:23<37:24:24,  7.16s/it]
                                                          
{'loss': 0.6127, 'learning_rate': 0.00039067511128346866, 'epoch': 3.96}

 33%|███▎      | 9280/28080 [18:20:23<37:24:24,  7.16s/it]
 33%|███▎      | 9281/28080 [18:20:30<37:24:01,  7.16s/it]
                                                          
{'loss': 0.626, 'learning_rate': 0.00039065127299649525, 'epoch': 3.96}

 33%|███▎      | 9281/28080 [18:20:30<37:24:01,  7.16s/it]
 33%|███▎      | 9282/28080 [18:20:37<37:25:44,  7.17s/it]
                                                          
{'loss': 0.6467, 'learning_rate': 0.0003906274328383018, 'epoch': 3.97}

 33%|███▎      | 9282/28080 [18:20:37<37:25:44,  7.17s/it]
 33%|███▎      | 9283/28080 [18:20:44<37:24:48,  7.17s/it]
                                                          
{'loss': 0.632, 'learning_rate': 0.0003906035908092055, 'epoch': 3.97}

 33%|███▎      | 9283/28080 [18:20:45<37:24:48,  7.17s/it]
 33%|███▎      | 9284/28080 [18:20:52<37:30:09,  7.18s/it]
                                                          
{'loss': 0.6207, 'learning_rate': 0.0003905797469095234, 'epoch': 3.97}

 33%|███▎      | 9284/28080 [18:20:52<37:30:09,  7.18s/it]
 33%|███▎      | 9285/28080 [18:20:59<37:22:12,  7.16s/it]
                                                          
{'loss': 0.5995, 'learning_rate': 0.00039055590113957285, 'epoch': 3.97}

 33%|███▎      | 9285/28080 [18:20:59<37:22:12,  7.16s/it]
 33%|███▎      | 9286/28080 [18:21:06<37:19:14,  7.15s/it]
                                                          
{'loss': 0.6196, 'learning_rate': 0.00039053205349967097, 'epoch': 3.97}

 33%|███▎      | 9286/28080 [18:21:06<37:19:14,  7.15s/it]
 33%|███▎      | 9287/28080 [18:21:13<37:10:01,  7.12s/it]
                                                          
{'loss': 0.6276, 'learning_rate': 0.0003905082039901351, 'epoch': 3.97}

 33%|███▎      | 9287/28080 [18:21:13<37:10:01,  7.12s/it]
 33%|███▎      | 9288/28080 [18:21:20<37:15:00,  7.14s/it]
                                                          
{'loss': 0.6434, 'learning_rate': 0.0003904843526112826, 'epoch': 3.97}

 33%|███▎      | 9288/28080 [18:21:20<37:15:00,  7.14s/it]
 33%|███▎      | 9289/28080 [18:21:27<37:18:06,  7.15s/it]
                                                          
{'loss': 0.6212, 'learning_rate': 0.0003904604993634306, 'epoch': 3.97}

 33%|███▎      | 9289/28080 [18:21:27<37:18:06,  7.15s/it]
 33%|███▎      | 9290/28080 [18:21:34<37:08:54,  7.12s/it]
                                                          
{'loss': 0.6273, 'learning_rate': 0.0003904366442468967, 'epoch': 3.97}

 33%|███▎      | 9290/28080 [18:21:34<37:08:54,  7.12s/it]
 33%|███▎      | 9291/28080 [18:21:42<37:16:37,  7.14s/it]
                                                          
{'loss': 0.6148, 'learning_rate': 0.000390412787261998, 'epoch': 3.97}

 33%|███▎      | 9291/28080 [18:21:42<37:16:37,  7.14s/it]
 33%|███▎      | 9292/28080 [18:21:49<37:19:51,  7.15s/it]
                                                          
{'loss': 0.6226, 'learning_rate': 0.00039038892840905214, 'epoch': 3.97}

 33%|███▎      | 9292/28080 [18:21:49<37:19:51,  7.15s/it]
 33%|███▎      | 9293/28080 [18:21:56<37:29:43,  7.18s/it]
                                                          
{'loss': 0.6223, 'learning_rate': 0.00039036506768837633, 'epoch': 3.97}

 33%|███▎      | 9293/28080 [18:21:56<37:29:43,  7.18s/it]
 33%|███▎      | 9294/28080 [18:22:03<37:25:51,  7.17s/it]
                                                          
{'loss': 0.6378, 'learning_rate': 0.00039034120510028815, 'epoch': 3.97}

 33%|███▎      | 9294/28080 [18:22:03<37:25:51,  7.17s/it]
 33%|███▎      | 9295/28080 [18:22:10<37:24:53,  7.17s/it]
                                                          
{'loss': 0.6395, 'learning_rate': 0.00039031734064510506, 'epoch': 3.97}

 33%|███▎      | 9295/28080 [18:22:10<37:24:53,  7.17s/it]
 33%|███▎      | 9296/28080 [18:22:17<37:22:52,  7.16s/it]
                                                          
{'loss': 0.6233, 'learning_rate': 0.00039029347432314445, 'epoch': 3.97}

 33%|███▎      | 9296/28080 [18:22:17<37:22:52,  7.16s/it]
 33%|███▎      | 9297/28080 [18:22:25<37:21:24,  7.16s/it]
                                                          
{'loss': 0.6084, 'learning_rate': 0.0003902696061347239, 'epoch': 3.97}

 33%|███▎      | 9297/28080 [18:22:25<37:21:24,  7.16s/it]
 33%|███▎      | 9298/28080 [18:22:32<37:26:09,  7.18s/it]
                                                          
{'loss': 0.6304, 'learning_rate': 0.00039024573608016096, 'epoch': 3.97}

 33%|███▎      | 9298/28080 [18:22:32<37:26:09,  7.18s/it]
 33%|███▎      | 9299/28080 [18:22:39<37:13:24,  7.14s/it]
                                                          
{'loss': 0.6305, 'learning_rate': 0.00039022186415977315, 'epoch': 3.97}

 33%|███▎      | 9299/28080 [18:22:39<37:13:24,  7.14s/it]
 33%|███▎      | 9300/28080 [18:22:46<37:09:14,  7.12s/it]
                                                          
{'loss': 0.6149, 'learning_rate': 0.00039019799037387807, 'epoch': 3.97}

 33%|███▎      | 9300/28080 [18:22:46<37:09:14,  7.12s/it]
 33%|███▎      | 9301/28080 [18:22:53<37:04:03,  7.11s/it]
                                                          
{'loss': 0.6384, 'learning_rate': 0.00039017411472279346, 'epoch': 3.97}

 33%|███▎      | 9301/28080 [18:22:53<37:04:03,  7.11s/it]
 33%|███▎      | 9302/28080 [18:23:00<37:02:31,  7.10s/it]
                                                          
{'loss': 0.6365, 'learning_rate': 0.0003901502372068368, 'epoch': 3.97}

 33%|███▎      | 9302/28080 [18:23:00<37:02:31,  7.10s/it]
 33%|███▎      | 9303/28080 [18:23:07<37:03:44,  7.11s/it]
                                                          
{'loss': 0.6323, 'learning_rate': 0.0003901263578263259, 'epoch': 3.97}

 33%|███▎      | 9303/28080 [18:23:07<37:03:44,  7.11s/it]
 33%|███▎      | 9304/28080 [18:23:14<37:03:22,  7.10s/it]
                                                          
{'loss': 0.6404, 'learning_rate': 0.00039010247658157826, 'epoch': 3.97}

 33%|███▎      | 9304/28080 [18:23:14<37:03:22,  7.10s/it]
 33%|███▎      | 9305/28080 [18:23:21<37:02:12,  7.10s/it]
                                                          
{'loss': 0.6232, 'learning_rate': 0.00039007859347291174, 'epoch': 3.98}

 33%|███▎      | 9305/28080 [18:23:21<37:02:12,  7.10s/it]
 33%|███▎      | 9306/28080 [18:23:29<37:01:23,  7.10s/it]
                                                          
{'loss': 0.617, 'learning_rate': 0.0003900547085006441, 'epoch': 3.98}

 33%|███▎      | 9306/28080 [18:23:29<37:01:23,  7.10s/it]
 33%|███▎      | 9307/28080 [18:23:36<37:11:21,  7.13s/it]
                                                          
{'loss': 0.635, 'learning_rate': 0.000390030821665093, 'epoch': 3.98}

 33%|███▎      | 9307/28080 [18:23:36<37:11:21,  7.13s/it]
 33%|███▎      | 9308/28080 [18:23:43<36:52:33,  7.07s/it]
                                                          
{'loss': 0.6518, 'learning_rate': 0.00039000693296657626, 'epoch': 3.98}

 33%|███▎      | 9308/28080 [18:23:43<36:52:33,  7.07s/it]
 33%|███▎      | 9309/28080 [18:23:50<37:05:00,  7.11s/it]
                                                          
{'loss': 0.621, 'learning_rate': 0.0003899830424054117, 'epoch': 3.98}

 33%|███▎      | 9309/28080 [18:23:50<37:05:00,  7.11s/it]
 33%|███▎      | 9310/28080 [18:23:57<37:10:23,  7.13s/it]
                                                          
{'loss': 0.646, 'learning_rate': 0.00038995914998191724, 'epoch': 3.98}

 33%|███▎      | 9310/28080 [18:23:57<37:10:23,  7.13s/it]
 33%|███▎      | 9311/28080 [18:24:04<37:02:29,  7.10s/it]
                                                          
{'loss': 0.6469, 'learning_rate': 0.00038993525569641066, 'epoch': 3.98}

 33%|███▎      | 9311/28080 [18:24:04<37:02:29,  7.10s/it]
 33%|███▎      | 9312/28080 [18:24:11<37:00:19,  7.10s/it]
                                                          
{'loss': 0.6376, 'learning_rate': 0.00038991135954920985, 'epoch': 3.98}

 33%|███▎      | 9312/28080 [18:24:11<37:00:19,  7.10s/it]
 33%|███▎      | 9313/28080 [18:24:18<36:55:05,  7.08s/it]
                                                          
{'loss': 0.6295, 'learning_rate': 0.0003898874615406327, 'epoch': 3.98}

 33%|███▎      | 9313/28080 [18:24:18<36:55:05,  7.08s/it]
 33%|███▎      | 9314/28080 [18:24:25<36:59:42,  7.10s/it]
                                                          
{'loss': 0.6006, 'learning_rate': 0.00038986356167099726, 'epoch': 3.98}

 33%|███▎      | 9314/28080 [18:24:25<36:59:42,  7.10s/it]
 33%|███▎      | 9315/28080 [18:24:32<37:01:50,  7.10s/it]
                                                          
{'loss': 0.6295, 'learning_rate': 0.00038983965994062136, 'epoch': 3.98}

 33%|███▎      | 9315/28080 [18:24:33<37:01:50,  7.10s/it]
 33%|███▎      | 9316/28080 [18:24:40<37:10:51,  7.13s/it]
                                                          
{'loss': 0.6352, 'learning_rate': 0.0003898157563498231, 'epoch': 3.98}

 33%|███▎      | 9316/28080 [18:24:40<37:10:51,  7.13s/it]
 33%|███▎      | 9317/28080 [18:24:47<37:10:45,  7.13s/it]
                                                          
{'loss': 0.6316, 'learning_rate': 0.00038979185089892045, 'epoch': 3.98}

 33%|███▎      | 9317/28080 [18:24:47<37:10:45,  7.13s/it]
 33%|███▎      | 9318/28080 [18:24:54<37:12:19,  7.14s/it]
                                                          
{'loss': 0.641, 'learning_rate': 0.00038976794358823143, 'epoch': 3.98}

 33%|███▎      | 9318/28080 [18:24:54<37:12:19,  7.14s/it]
 33%|███▎      | 9319/28080 [18:25:01<37:08:01,  7.13s/it]
                                                          
{'loss': 0.6609, 'learning_rate': 0.00038974403441807405, 'epoch': 3.98}

 33%|███▎      | 9319/28080 [18:25:01<37:08:01,  7.13s/it]
 33%|███▎      | 9320/28080 [18:25:08<36:59:44,  7.10s/it]
                                                          
{'loss': 0.6249, 'learning_rate': 0.0003897201233887665, 'epoch': 3.98}

 33%|███▎      | 9320/28080 [18:25:08<36:59:44,  7.10s/it]
 33%|███▎      | 9321/28080 [18:25:15<37:04:26,  7.11s/it]
                                                          
{'loss': 0.6447, 'learning_rate': 0.0003896962105006269, 'epoch': 3.98}

 33%|███▎      | 9321/28080 [18:25:15<37:04:26,  7.11s/it]
 33%|███▎      | 9322/28080 [18:25:22<37:06:32,  7.12s/it]
                                                          
{'loss': 0.6286, 'learning_rate': 0.00038967229575397327, 'epoch': 3.98}

 33%|███▎      | 9322/28080 [18:25:22<37:06:32,  7.12s/it]
 33%|███▎      | 9323/28080 [18:25:29<36:58:54,  7.10s/it]
                                                          
{'loss': 0.6089, 'learning_rate': 0.00038964837914912386, 'epoch': 3.98}

 33%|███▎      | 9323/28080 [18:25:29<36:58:54,  7.10s/it]
 33%|███▎      | 9324/28080 [18:25:37<37:02:09,  7.11s/it]
                                                          
{'loss': 0.6418, 'learning_rate': 0.0003896244606863968, 'epoch': 3.98}

 33%|███▎      | 9324/28080 [18:25:37<37:02:09,  7.11s/it]
 33%|███▎      | 9325/28080 [18:25:44<37:06:06,  7.12s/it]
                                                          
{'loss': 0.6349, 'learning_rate': 0.00038960054036611035, 'epoch': 3.98}

 33%|███▎      | 9325/28080 [18:25:44<37:06:06,  7.12s/it]
 33%|███▎      | 9326/28080 [18:25:51<37:11:11,  7.14s/it]
                                                          
{'loss': 0.6056, 'learning_rate': 0.0003895766181885828, 'epoch': 3.98}

 33%|███▎      | 9326/28080 [18:25:51<37:11:11,  7.14s/it]
 33%|███▎      | 9327/28080 [18:25:58<37:07:55,  7.13s/it]
                                                          
{'loss': 0.6443, 'learning_rate': 0.0003895526941541323, 'epoch': 3.98}

 33%|███▎      | 9327/28080 [18:25:58<37:07:55,  7.13s/it]
 33%|███▎      | 9328/28080 [18:26:05<37:13:47,  7.15s/it]
                                                          
{'loss': 0.6104, 'learning_rate': 0.0003895287682630771, 'epoch': 3.98}

 33%|███▎      | 9328/28080 [18:26:05<37:13:47,  7.15s/it]
 33%|███▎      | 9329/28080 [18:26:12<37:20:23,  7.17s/it]
                                                          
{'loss': 0.6088, 'learning_rate': 0.00038950484051573567, 'epoch': 3.99}

 33%|███▎      | 9329/28080 [18:26:12<37:20:23,  7.17s/it]
 33%|███▎      | 9330/28080 [18:26:20<37:13:47,  7.15s/it]
                                                          
{'loss': 0.629, 'learning_rate': 0.00038948091091242615, 'epoch': 3.99}

 33%|███▎      | 9330/28080 [18:26:20<37:13:47,  7.15s/it]
 33%|███▎      | 9331/28080 [18:26:27<37:02:38,  7.11s/it]
                                                          
{'loss': 0.6389, 'learning_rate': 0.0003894569794534671, 'epoch': 3.99}

 33%|███▎      | 9331/28080 [18:26:27<37:02:38,  7.11s/it]
 33%|███▎      | 9332/28080 [18:26:34<36:58:08,  7.10s/it]
                                                          
{'loss': 0.6358, 'learning_rate': 0.00038943304613917674, 'epoch': 3.99}

 33%|███▎      | 9332/28080 [18:26:34<36:58:08,  7.10s/it]
 33%|███▎      | 9333/28080 [18:26:41<37:00:35,  7.11s/it]
                                                          
{'loss': 0.6483, 'learning_rate': 0.00038940911096987366, 'epoch': 3.99}

 33%|███▎      | 9333/28080 [18:26:41<37:00:35,  7.11s/it]
 33%|███▎      | 9334/28080 [18:26:48<36:58:26,  7.10s/it]
                                                          
{'loss': 0.6601, 'learning_rate': 0.000389385173945876, 'epoch': 3.99}

 33%|███▎      | 9334/28080 [18:26:48<36:58:26,  7.10s/it]
 33%|███▎      | 9335/28080 [18:26:55<36:52:56,  7.08s/it]
                                                          
{'loss': 0.6467, 'learning_rate': 0.00038936123506750253, 'epoch': 3.99}

 33%|███▎      | 9335/28080 [18:26:55<36:52:56,  7.08s/it]
 33%|███▎      | 9336/28080 [18:27:02<36:54:39,  7.09s/it]
                                                          
{'loss': 0.6658, 'learning_rate': 0.0003893372943350716, 'epoch': 3.99}

 33%|███▎      | 9336/28080 [18:27:02<36:54:39,  7.09s/it]
 33%|███▎      | 9337/28080 [18:27:09<37:06:14,  7.13s/it]
                                                          
{'loss': 0.6164, 'learning_rate': 0.0003893133517489017, 'epoch': 3.99}

 33%|███▎      | 9337/28080 [18:27:09<37:06:14,  7.13s/it]
 33%|███▎      | 9338/28080 [18:27:16<37:12:22,  7.15s/it]
                                                          
{'loss': 0.6032, 'learning_rate': 0.00038928940730931135, 'epoch': 3.99}

 33%|███▎      | 9338/28080 [18:27:16<37:12:22,  7.15s/it]
 33%|███▎      | 9339/28080 [18:27:24<37:11:08,  7.14s/it]
                                                          
{'loss': 0.638, 'learning_rate': 0.00038926546101661916, 'epoch': 3.99}

 33%|███▎      | 9339/28080 [18:27:24<37:11:08,  7.14s/it]
 33%|███▎      | 9340/28080 [18:27:31<36:58:59,  7.10s/it]
                                                          
{'loss': 0.6363, 'learning_rate': 0.00038924151287114363, 'epoch': 3.99}

 33%|███▎      | 9340/28080 [18:27:31<36:58:59,  7.10s/it]
 33%|███▎      | 9341/28080 [18:27:38<36:51:58,  7.08s/it]
                                                          
{'loss': 0.6372, 'learning_rate': 0.0003892175628732035, 'epoch': 3.99}

 33%|███▎      | 9341/28080 [18:27:38<36:51:58,  7.08s/it]
 33%|███▎      | 9342/28080 [18:27:45<37:00:09,  7.11s/it]
                                                          
{'loss': 0.6292, 'learning_rate': 0.0003891936110231172, 'epoch': 3.99}

 33%|███▎      | 9342/28080 [18:27:45<37:00:09,  7.11s/it]
 33%|███▎      | 9343/28080 [18:27:52<36:52:08,  7.08s/it]
                                                          
{'loss': 0.6399, 'learning_rate': 0.0003891696573212036, 'epoch': 3.99}

 33%|███▎      | 9343/28080 [18:27:52<36:52:08,  7.08s/it]
 33%|███▎      | 9344/28080 [18:27:59<36:52:40,  7.09s/it]
                                                          
{'loss': 0.6236, 'learning_rate': 0.0003891457017677813, 'epoch': 3.99}

 33%|███▎      | 9344/28080 [18:27:59<36:52:40,  7.09s/it]
 33%|███▎      | 9345/28080 [18:28:06<36:52:37,  7.09s/it]
                                                          
{'loss': 0.6423, 'learning_rate': 0.00038912174436316895, 'epoch': 3.99}

 33%|███▎      | 9345/28080 [18:28:06<36:52:37,  7.09s/it]
 33%|███▎      | 9346/28080 [18:28:13<37:18:16,  7.17s/it]
                                                          
{'loss': 0.6208, 'learning_rate': 0.00038909778510768533, 'epoch': 3.99}

 33%|███▎      | 9346/28080 [18:28:13<37:18:16,  7.17s/it]
 33%|███▎      | 9347/28080 [18:28:20<37:11:40,  7.15s/it]
                                                          
{'loss': 0.639, 'learning_rate': 0.0003890738240016491, 'epoch': 3.99}

 33%|███▎      | 9347/28080 [18:28:20<37:11:40,  7.15s/it]
 33%|███▎      | 9348/28080 [18:28:27<37:04:24,  7.12s/it]
                                                          
{'loss': 0.6281, 'learning_rate': 0.0003890498610453792, 'epoch': 3.99}

 33%|███▎      | 9348/28080 [18:28:27<37:04:24,  7.12s/it]
 33%|███▎      | 9349/28080 [18:28:35<37:10:44,  7.15s/it]
                                                          
{'loss': 0.6141, 'learning_rate': 0.0003890258962391944, 'epoch': 3.99}

 33%|███▎      | 9349/28080 [18:28:35<37:10:44,  7.15s/it]
 33%|███▎      | 9350/28080 [18:28:42<37:05:23,  7.13s/it]
                                                          
{'loss': 0.6301, 'learning_rate': 0.0003890019295834134, 'epoch': 3.99}

 33%|███▎      | 9350/28080 [18:28:42<37:05:23,  7.13s/it]
 33%|███▎      | 9351/28080 [18:28:49<37:06:55,  7.13s/it]
                                                          
{'loss': 0.6173, 'learning_rate': 0.00038897796107835507, 'epoch': 3.99}

 33%|███▎      | 9351/28080 [18:28:49<37:06:55,  7.13s/it]
 33%|███▎      | 9352/28080 [18:28:56<37:06:48,  7.13s/it]
                                                          
{'loss': 0.6304, 'learning_rate': 0.00038895399072433844, 'epoch': 4.0}

 33%|███▎      | 9352/28080 [18:28:56<37:06:48,  7.13s/it]
 33%|███▎      | 9353/28080 [18:29:03<36:54:38,  7.10s/it]
                                                          
{'loss': 0.64, 'learning_rate': 0.00038893001852168224, 'epoch': 4.0}

 33%|███▎      | 9353/28080 [18:29:03<36:54:38,  7.10s/it]
 33%|███▎      | 9354/28080 [18:29:10<37:02:06,  7.12s/it]
                                                          
{'loss': 0.6242, 'learning_rate': 0.00038890604447070555, 'epoch': 4.0}

 33%|███▎      | 9354/28080 [18:29:10<37:02:06,  7.12s/it]
 33%|███▎      | 9355/28080 [18:29:17<37:04:40,  7.13s/it]
                                                          
{'loss': 0.6325, 'learning_rate': 0.00038888206857172713, 'epoch': 4.0}

 33%|███▎      | 9355/28080 [18:29:17<37:04:40,  7.13s/it]
 33%|███▎      | 9356/28080 [18:29:24<37:02:11,  7.12s/it]
                                                          
{'loss': 0.6092, 'learning_rate': 0.0003888580908250662, 'epoch': 4.0}

 33%|███▎      | 9356/28080 [18:29:24<37:02:11,  7.12s/it]
 33%|███▎      | 9357/28080 [18:29:32<37:03:18,  7.12s/it]
                                                          
{'loss': 0.6269, 'learning_rate': 0.00038883411123104153, 'epoch': 4.0}

 33%|███▎      | 9357/28080 [18:29:32<37:03:18,  7.12s/it]
 33%|███▎      | 9358/28080 [18:29:39<37:01:54,  7.12s/it]
                                                          
{'loss': 0.6548, 'learning_rate': 0.0003888101297899722, 'epoch': 4.0}

 33%|███▎      | 9358/28080 [18:29:39<37:01:54,  7.12s/it]
 33%|███▎      | 9359/28080 [18:29:46<36:58:39,  7.11s/it]
                                                          
{'loss': 0.6266, 'learning_rate': 0.00038878614650217743, 'epoch': 4.0}

 33%|███▎      | 9359/28080 [18:29:46<36:58:39,  7.11s/it]
 33%|███▎      | 9360/28080 [18:29:53<36:59:56,  7.12s/it]
                                                          
{'loss': 0.611, 'learning_rate': 0.000388762161367976, 'epoch': 4.0}

 33%|███▎      | 9360/28080 [18:29:53<36:59:56,  7.12s/it]
 33%|███▎      | 9361/28080 [18:30:00<36:52:32,  7.09s/it]
                                                          
{'loss': 0.6264, 'learning_rate': 0.0003887381743876873, 'epoch': 4.0}

 33%|███▎      | 9361/28080 [18:30:00<36:52:32,  7.09s/it]
 33%|███▎      | 9362/28080 [18:30:07<36:51:44,  7.09s/it]
                                                          
{'loss': 0.6324, 'learning_rate': 0.0003887141855616303, 'epoch': 4.0}

 33%|███▎      | 9362/28080 [18:30:07<36:51:44,  7.09s/it]
 33%|███▎      | 9363/28080 [18:30:14<36:58:31,  7.11s/it]
                                                          
{'loss': 0.6443, 'learning_rate': 0.00038869019489012413, 'epoch': 4.0}

 33%|███▎      | 9363/28080 [18:30:14<36:58:31,  7.11s/it]
 33%|███▎      | 9364/28080 [18:30:22<37:53:22,  7.29s/it]
                                                          
{'loss': 0.6156, 'learning_rate': 0.000388666202373488, 'epoch': 4.0}

 33%|███▎      | 9364/28080 [18:30:22<37:53:22,  7.29s/it]
 33%|███▎      | 9365/28080 [18:30:29<37:40:53,  7.25s/it]
                                                          
{'loss': 0.6425, 'learning_rate': 0.0003886422080120411, 'epoch': 4.0}

 33%|███▎      | 9365/28080 [18:30:29<37:40:53,  7.25s/it]
 33%|███▎      | 9366/28080 [18:30:36<37:35:50,  7.23s/it]
                                                          
{'loss': 0.6411, 'learning_rate': 0.00038861821180610263, 'epoch': 4.0}

 33%|███▎      | 9366/28080 [18:30:36<37:35:50,  7.23s/it]
 33%|███▎      | 9367/28080 [18:30:43<37:30:59,  7.22s/it]
                                                          
{'loss': 0.6376, 'learning_rate': 0.0003885942137559919, 'epoch': 4.0}

 33%|███▎      | 9367/28080 [18:30:43<37:30:59,  7.22s/it]
 33%|███▎      | 9368/28080 [18:30:51<37:16:06,  7.17s/it]
                                                          
{'loss': 0.6453, 'learning_rate': 0.00038857021386202805, 'epoch': 4.0}

 33%|███▎      | 9368/28080 [18:30:51<37:16:06,  7.17s/it]
 33%|███▎      | 9369/28080 [18:30:58<37:09:23,  7.15s/it]
                                                          
{'loss': 0.6313, 'learning_rate': 0.00038854621212453054, 'epoch': 4.0}

 33%|███▎      | 9369/28080 [18:30:58<37:09:23,  7.15s/it]
 33%|███▎      | 9370/28080 [18:31:05<37:05:09,  7.14s/it]
                                                          
{'loss': 0.6191, 'learning_rate': 0.00038852220854381864, 'epoch': 4.0}

 33%|███▎      | 9370/28080 [18:31:05<37:05:09,  7.14s/it]
 33%|███▎      | 9371/28080 [18:31:12<37:00:35,  7.12s/it]
                                                          
{'loss': 0.6429, 'learning_rate': 0.00038849820312021166, 'epoch': 4.0}

 33%|███▎      | 9371/28080 [18:31:12<37:00:35,  7.12s/it]
 33%|███▎      | 9372/28080 [18:31:19<37:04:33,  7.13s/it]
                                                          
{'loss': 0.6361, 'learning_rate': 0.0003884741958540289, 'epoch': 4.0}

 33%|███▎      | 9372/28080 [18:31:19<37:04:33,  7.13s/it]
 33%|███▎      | 9373/28080 [18:31:26<37:04:14,  7.13s/it]
                                                          
{'loss': 0.6281, 'learning_rate': 0.00038845018674558984, 'epoch': 4.0}

 33%|███▎      | 9373/28080 [18:31:26<37:04:14,  7.13s/it]
 33%|███▎      | 9374/28080 [18:31:33<37:08:46,  7.15s/it]
                                                          
{'loss': 0.6306, 'learning_rate': 0.0003884261757952139, 'epoch': 4.0}

 33%|███▎      | 9374/28080 [18:31:33<37:08:46,  7.15s/it]
 33%|███▎      | 9375/28080 [18:31:40<37:12:40,  7.16s/it]
                                                          
{'loss': 0.6102, 'learning_rate': 0.0003884021630032204, 'epoch': 4.0}

 33%|███▎      | 9375/28080 [18:31:40<37:12:40,  7.16s/it]
 33%|███▎      | 9376/28080 [18:31:48<37:10:13,  7.15s/it]
                                                          
{'loss': 0.6371, 'learning_rate': 0.000388378148369929, 'epoch': 4.01}

 33%|███▎      | 9376/28080 [18:31:48<37:10:13,  7.15s/it]
 33%|███▎      | 9377/28080 [18:31:55<37:04:51,  7.14s/it]
                                                          
{'loss': 0.6291, 'learning_rate': 0.00038835413189565904, 'epoch': 4.01}

 33%|███▎      | 9377/28080 [18:31:55<37:04:51,  7.14s/it]
 33%|███▎      | 9378/28080 [18:32:02<37:10:42,  7.16s/it]
                                                          
{'loss': 0.6132, 'learning_rate': 0.00038833011358073015, 'epoch': 4.01}

 33%|███▎      | 9378/28080 [18:32:02<37:10:42,  7.16s/it]
 33%|███▎      | 9379/28080 [18:32:09<37:02:40,  7.13s/it]
                                                          
{'loss': 0.6459, 'learning_rate': 0.00038830609342546175, 'epoch': 4.01}

 33%|███▎      | 9379/28080 [18:32:09<37:02:40,  7.13s/it]
 33%|███▎      | 9380/28080 [18:32:16<37:04:35,  7.14s/it]
                                                          
{'loss': 0.64, 'learning_rate': 0.00038828207143017346, 'epoch': 4.01}

 33%|███▎      | 9380/28080 [18:32:16<37:04:35,  7.14s/it]
 33%|███▎      | 9381/28080 [18:32:23<37:00:31,  7.13s/it]
                                                          
{'loss': 0.6574, 'learning_rate': 0.0003882580475951849, 'epoch': 4.01}

 33%|███▎      | 9381/28080 [18:32:23<37:00:31,  7.13s/it]
 33%|███▎      | 9382/28080 [18:32:30<37:04:51,  7.14s/it]
                                                          
{'loss': 0.6221, 'learning_rate': 0.0003882340219208157, 'epoch': 4.01}

 33%|███▎      | 9382/28080 [18:32:30<37:04:51,  7.14s/it]
 33%|███▎      | 9383/28080 [18:32:37<36:57:10,  7.12s/it]
                                                          
{'loss': 0.6424, 'learning_rate': 0.00038820999440738536, 'epoch': 4.01}

 33%|███▎      | 9383/28080 [18:32:37<36:57:10,  7.12s/it]
 33%|███▎      | 9384/28080 [18:32:45<36:54:54,  7.11s/it]
                                                          
{'loss': 0.6353, 'learning_rate': 0.0003881859650552136, 'epoch': 4.01}

 33%|███▎      | 9384/28080 [18:32:45<36:54:54,  7.11s/it]
 33%|███▎      | 9385/28080 [18:32:52<37:09:52,  7.16s/it]
                                                          
{'loss': 0.6163, 'learning_rate': 0.0003881619338646202, 'epoch': 4.01}

 33%|███▎      | 9385/28080 [18:32:52<37:09:52,  7.16s/it]
 33%|███▎      | 9386/28080 [18:32:59<37:09:52,  7.16s/it]
                                                          
{'loss': 0.6279, 'learning_rate': 0.00038813790083592483, 'epoch': 4.01}

 33%|███▎      | 9386/28080 [18:32:59<37:09:52,  7.16s/it]
 33%|███▎      | 9387/28080 [18:33:06<37:00:33,  7.13s/it]
                                                          
{'loss': 0.6235, 'learning_rate': 0.0003881138659694471, 'epoch': 4.01}

 33%|███▎      | 9387/28080 [18:33:06<37:00:33,  7.13s/it]
 33%|███▎      | 9388/28080 [18:33:13<37:05:06,  7.14s/it]
                                                          
{'loss': 0.6353, 'learning_rate': 0.00038808982926550695, 'epoch': 4.01}

 33%|███▎      | 9388/28080 [18:33:13<37:05:06,  7.14s/it]
 33%|███▎      | 9389/28080 [18:33:20<37:16:25,  7.18s/it]
                                                          
{'loss': 0.6323, 'learning_rate': 0.0003880657907244241, 'epoch': 4.01}

 33%|███▎      | 9389/28080 [18:33:20<37:16:25,  7.18s/it]
 33%|███▎      | 9390/28080 [18:33:28<37:06:22,  7.15s/it]
                                                          
{'loss': 0.6465, 'learning_rate': 0.0003880417503465183, 'epoch': 4.01}

 33%|███▎      | 9390/28080 [18:33:28<37:06:22,  7.15s/it]
 33%|███▎      | 9391/28080 [18:33:35<37:07:53,  7.15s/it]
                                                          
{'loss': 0.6192, 'learning_rate': 0.0003880177081321094, 'epoch': 4.01}

 33%|███▎      | 9391/28080 [18:33:35<37:07:53,  7.15s/it]
 33%|███▎      | 9392/28080 [18:33:42<37:08:49,  7.16s/it]
                                                          
{'loss': 0.6199, 'learning_rate': 0.00038799366408151726, 'epoch': 4.01}

 33%|███▎      | 9392/28080 [18:33:42<37:08:49,  7.16s/it]
 33%|███▎      | 9393/28080 [18:33:49<37:06:53,  7.15s/it]
                                                          
{'loss': 0.6335, 'learning_rate': 0.0003879696181950618, 'epoch': 4.01}

 33%|███▎      | 9393/28080 [18:33:49<37:06:53,  7.15s/it]
 33%|███▎      | 9394/28080 [18:33:56<37:14:03,  7.17s/it]
                                                          
{'loss': 0.6085, 'learning_rate': 0.000387945570473063, 'epoch': 4.01}

 33%|███▎      | 9394/28080 [18:33:56<37:14:03,  7.17s/it]
 33%|███▎      | 9395/28080 [18:34:03<37:05:07,  7.15s/it]
                                                          
{'loss': 0.6226, 'learning_rate': 0.00038792152091584063, 'epoch': 4.01}

 33%|███▎      | 9395/28080 [18:34:03<37:05:07,  7.15s/it]
 33%|███▎      | 9396/28080 [18:34:10<37:04:48,  7.14s/it]
                                                          
{'loss': 0.6344, 'learning_rate': 0.00038789746952371467, 'epoch': 4.01}

 33%|███▎      | 9396/28080 [18:34:10<37:04:48,  7.14s/it]
 33%|███▎      | 9397/28080 [18:34:18<37:02:42,  7.14s/it]
                                                          
{'loss': 0.6414, 'learning_rate': 0.0003878734162970052, 'epoch': 4.01}

 33%|███▎      | 9397/28080 [18:34:18<37:02:42,  7.14s/it]
 33%|███▎      | 9398/28080 [18:34:25<37:00:17,  7.13s/it]
                                                          
{'loss': 0.605, 'learning_rate': 0.0003878493612360321, 'epoch': 4.01}

 33%|███▎      | 9398/28080 [18:34:25<37:00:17,  7.13s/it]
 33%|███▎      | 9399/28080 [18:34:32<37:00:20,  7.13s/it]
                                                          
{'loss': 0.6106, 'learning_rate': 0.0003878253043411155, 'epoch': 4.02}

 33%|███▎      | 9399/28080 [18:34:32<37:00:20,  7.13s/it]
 33%|███▎      | 9400/28080 [18:34:39<37:02:30,  7.14s/it]
                                                          
{'loss': 0.6475, 'learning_rate': 0.0003878012456125754, 'epoch': 4.02}

 33%|███▎      | 9400/28080 [18:34:39<37:02:30,  7.14s/it]
 33%|███▎      | 9401/28080 [18:34:46<36:59:12,  7.13s/it]
                                                          
{'loss': 0.6406, 'learning_rate': 0.0003877771850507319, 'epoch': 4.02}

 33%|███▎      | 9401/28080 [18:34:46<36:59:12,  7.13s/it]
 33%|███▎      | 9402/28080 [18:34:53<36:57:44,  7.12s/it]
                                                          
{'loss': 0.6281, 'learning_rate': 0.0003877531226559051, 'epoch': 4.02}

 33%|███▎      | 9402/28080 [18:34:53<36:57:44,  7.12s/it]
 33%|███▎      | 9403/28080 [18:35:00<37:05:14,  7.15s/it]
                                                          
{'loss': 0.6149, 'learning_rate': 0.00038772905842841506, 'epoch': 4.02}

 33%|███▎      | 9403/28080 [18:35:00<37:05:14,  7.15s/it]
 33%|███▎      | 9404/28080 [18:35:08<37:05:42,  7.15s/it]
                                                          
{'loss': 0.5821, 'learning_rate': 0.00038770499236858206, 'epoch': 4.02}

 33%|███▎      | 9404/28080 [18:35:08<37:05:42,  7.15s/it]
 33%|███▎      | 9405/28080 [18:35:15<37:08:33,  7.16s/it]
                                                          
{'loss': 0.6223, 'learning_rate': 0.0003876809244767261, 'epoch': 4.02}

 33%|███▎      | 9405/28080 [18:35:15<37:08:33,  7.16s/it]
 33%|███▎      | 9406/28080 [18:35:22<36:58:02,  7.13s/it]
                                                          
{'loss': 0.6281, 'learning_rate': 0.0003876568547531676, 'epoch': 4.02}

 33%|███▎      | 9406/28080 [18:35:22<36:58:02,  7.13s/it]
 34%|███▎      | 9407/28080 [18:35:29<36:54:44,  7.12s/it]
                                                          
{'loss': 0.6341, 'learning_rate': 0.00038763278319822655, 'epoch': 4.02}

 34%|███▎      | 9407/28080 [18:35:29<36:54:44,  7.12s/it]
 34%|███▎      | 9408/28080 [18:35:36<37:01:01,  7.14s/it]
                                                          
{'loss': 0.6647, 'learning_rate': 0.00038760870981222333, 'epoch': 4.02}

 34%|███▎      | 9408/28080 [18:35:36<37:01:01,  7.14s/it]
 34%|███▎      | 9409/28080 [18:35:43<36:58:14,  7.13s/it]
                                                          
{'loss': 0.6336, 'learning_rate': 0.0003875846345954782, 'epoch': 4.02}

 34%|███▎      | 9409/28080 [18:35:43<36:58:14,  7.13s/it]
 34%|███▎      | 9410/28080 [18:35:50<36:54:16,  7.12s/it]
                                                          
{'loss': 0.6403, 'learning_rate': 0.00038756055754831146, 'epoch': 4.02}

 34%|███▎      | 9410/28080 [18:35:50<36:54:16,  7.12s/it]
 34%|███▎      | 9411/28080 [18:35:57<36:58:08,  7.13s/it]
                                                          
{'loss': 0.6116, 'learning_rate': 0.0003875364786710434, 'epoch': 4.02}

 34%|███▎      | 9411/28080 [18:35:57<36:58:08,  7.13s/it]
 34%|███▎      | 9412/28080 [18:36:05<36:54:28,  7.12s/it]
                                                          
{'loss': 0.6316, 'learning_rate': 0.0003875123979639944, 'epoch': 4.02}

 34%|███▎      | 9412/28080 [18:36:05<36:54:28,  7.12s/it]
 34%|███▎      | 9413/28080 [18:36:12<37:02:34,  7.14s/it]
                                                          
{'loss': 0.6529, 'learning_rate': 0.00038748831542748487, 'epoch': 4.02}

 34%|███▎      | 9413/28080 [18:36:12<37:02:34,  7.14s/it]
 34%|███▎      | 9414/28080 [18:36:19<37:06:41,  7.16s/it]
                                                          
{'loss': 0.6266, 'learning_rate': 0.00038746423106183505, 'epoch': 4.02}

 34%|███▎      | 9414/28080 [18:36:19<37:06:41,  7.16s/it]
 34%|███▎      | 9415/28080 [18:36:26<37:00:17,  7.14s/it]
                                                          
{'loss': 0.6246, 'learning_rate': 0.00038744014486736546, 'epoch': 4.02}

 34%|███▎      | 9415/28080 [18:36:26<37:00:17,  7.14s/it]
 34%|███▎      | 9416/28080 [18:36:33<36:55:40,  7.12s/it]
                                                          
{'loss': 0.6286, 'learning_rate': 0.0003874160568443965, 'epoch': 4.02}

 34%|███▎      | 9416/28080 [18:36:33<36:55:40,  7.12s/it]
 34%|███▎      | 9417/28080 [18:36:40<36:49:00,  7.10s/it]
                                                          
{'loss': 0.6394, 'learning_rate': 0.00038739196699324877, 'epoch': 4.02}

 34%|███▎      | 9417/28080 [18:36:40<36:49:00,  7.10s/it]
 34%|███▎      | 9418/28080 [18:36:47<36:55:40,  7.12s/it]
                                                          
{'loss': 0.6408, 'learning_rate': 0.00038736787531424254, 'epoch': 4.02}

 34%|███▎      | 9418/28080 [18:36:47<36:55:40,  7.12s/it]
 34%|███▎      | 9419/28080 [18:36:54<36:58:45,  7.13s/it]
                                                          
{'loss': 0.6281, 'learning_rate': 0.00038734378180769856, 'epoch': 4.02}

 34%|███▎      | 9419/28080 [18:36:54<36:58:45,  7.13s/it]
 34%|███▎      | 9420/28080 [18:37:02<37:02:59,  7.15s/it]
                                                          
{'loss': 0.6399, 'learning_rate': 0.00038731968647393717, 'epoch': 4.02}

 34%|███▎      | 9420/28080 [18:37:02<37:02:59,  7.15s/it]
 34%|███▎      | 9421/28080 [18:37:09<37:04:44,  7.15s/it]
                                                          
{'loss': 0.6417, 'learning_rate': 0.00038729558931327907, 'epoch': 4.02}

 34%|███▎      | 9421/28080 [18:37:09<37:04:44,  7.15s/it]
 34%|███▎      | 9422/28080 [18:37:16<37:19:06,  7.20s/it]
                                                          
{'loss': 0.6355, 'learning_rate': 0.00038727149032604475, 'epoch': 4.02}

 34%|███▎      | 9422/28080 [18:37:16<37:19:06,  7.20s/it]
 34%|███▎      | 9423/28080 [18:37:23<37:17:39,  7.20s/it]
                                                          
{'loss': 0.6175, 'learning_rate': 0.0003872473895125549, 'epoch': 4.03}

 34%|███▎      | 9423/28080 [18:37:23<37:17:39,  7.20s/it]
 34%|███▎      | 9424/28080 [18:37:31<37:17:33,  7.20s/it]
                                                          
{'loss': 0.6242, 'learning_rate': 0.00038722328687313014, 'epoch': 4.03}

 34%|███▎      | 9424/28080 [18:37:31<37:17:33,  7.20s/it]
 34%|███▎      | 9425/28080 [18:37:38<37:18:03,  7.20s/it]
                                                          
{'loss': 0.6345, 'learning_rate': 0.00038719918240809104, 'epoch': 4.03}

 34%|███▎      | 9425/28080 [18:37:38<37:18:03,  7.20s/it]
 34%|███▎      | 9426/28080 [18:37:45<37:11:28,  7.18s/it]
                                                          
{'loss': 0.604, 'learning_rate': 0.0003871750761177584, 'epoch': 4.03}

 34%|███▎      | 9426/28080 [18:37:45<37:11:28,  7.18s/it]
 34%|███▎      | 9427/28080 [18:37:52<37:07:53,  7.17s/it]
                                                          
{'loss': 0.6363, 'learning_rate': 0.0003871509680024529, 'epoch': 4.03}

 34%|███▎      | 9427/28080 [18:37:52<37:07:53,  7.17s/it]
 34%|███▎      | 9428/28080 [18:37:59<37:12:55,  7.18s/it]
                                                          
{'loss': 0.6235, 'learning_rate': 0.00038712685806249525, 'epoch': 4.03}

 34%|███▎      | 9428/28080 [18:37:59<37:12:55,  7.18s/it]
 34%|███▎      | 9429/28080 [18:38:06<37:13:19,  7.18s/it]
                                                          
{'loss': 0.6051, 'learning_rate': 0.0003871027462982062, 'epoch': 4.03}

 34%|███▎      | 9429/28080 [18:38:06<37:13:19,  7.18s/it]
 34%|███▎      | 9430/28080 [18:38:14<37:17:30,  7.20s/it]
                                                          
{'loss': 0.6312, 'learning_rate': 0.00038707863270990656, 'epoch': 4.03}

 34%|███▎      | 9430/28080 [18:38:14<37:17:30,  7.20s/it]
 34%|███▎      | 9431/28080 [18:38:21<37:03:56,  7.16s/it]
                                                          
{'loss': 0.6138, 'learning_rate': 0.00038705451729791713, 'epoch': 4.03}

 34%|███▎      | 9431/28080 [18:38:21<37:03:56,  7.16s/it]
 34%|███▎      | 9432/28080 [18:38:28<36:59:16,  7.14s/it]
                                                          
{'loss': 0.6395, 'learning_rate': 0.0003870304000625587, 'epoch': 4.03}

 34%|███▎      | 9432/28080 [18:38:28<36:59:16,  7.14s/it]
 34%|███▎      | 9433/28080 [18:38:35<36:54:35,  7.13s/it]
                                                          
{'loss': 0.6323, 'learning_rate': 0.00038700628100415225, 'epoch': 4.03}

 34%|███▎      | 9433/28080 [18:38:35<36:54:35,  7.13s/it]
 34%|███▎      | 9434/28080 [18:38:42<37:09:11,  7.17s/it]
                                                          
{'loss': 0.6373, 'learning_rate': 0.00038698216012301854, 'epoch': 4.03}

 34%|███▎      | 9434/28080 [18:38:42<37:09:11,  7.17s/it]
 34%|███▎      | 9435/28080 [18:38:49<37:00:59,  7.15s/it]
                                                          
{'loss': 0.6527, 'learning_rate': 0.0003869580374194785, 'epoch': 4.03}

 34%|███▎      | 9435/28080 [18:38:49<37:00:59,  7.15s/it]
 34%|███▎      | 9436/28080 [18:38:56<36:52:16,  7.12s/it]
                                                          
{'loss': 0.6472, 'learning_rate': 0.00038693391289385307, 'epoch': 4.03}

 34%|███▎      | 9436/28080 [18:38:56<36:52:16,  7.12s/it]
 34%|███▎      | 9437/28080 [18:39:03<36:45:20,  7.10s/it]
                                                          
{'loss': 0.6239, 'learning_rate': 0.00038690978654646317, 'epoch': 4.03}

 34%|███▎      | 9437/28080 [18:39:03<36:45:20,  7.10s/it]
 34%|███▎      | 9438/28080 [18:39:10<36:48:38,  7.11s/it]
                                                          
{'loss': 0.6169, 'learning_rate': 0.00038688565837762976, 'epoch': 4.03}

 34%|███▎      | 9438/28080 [18:39:10<36:48:38,  7.11s/it]
 34%|███▎      | 9439/28080 [18:39:18<36:46:03,  7.10s/it]
                                                          
{'loss': 0.6166, 'learning_rate': 0.00038686152838767396, 'epoch': 4.03}

 34%|███▎      | 9439/28080 [18:39:18<36:46:03,  7.10s/it]
 34%|███▎      | 9440/28080 [18:39:25<37:09:34,  7.18s/it]
                                                          
{'loss': 0.6248, 'learning_rate': 0.00038683739657691677, 'epoch': 4.03}

 34%|███▎      | 9440/28080 [18:39:25<37:09:34,  7.18s/it]
 34%|███▎      | 9441/28080 [18:39:32<37:06:42,  7.17s/it]
                                                          
{'loss': 0.6181, 'learning_rate': 0.0003868132629456791, 'epoch': 4.03}

 34%|███▎      | 9441/28080 [18:39:32<37:06:42,  7.17s/it]
 34%|███▎      | 9442/28080 [18:39:39<36:55:56,  7.13s/it]
                                                          
{'loss': 0.6547, 'learning_rate': 0.00038678912749428207, 'epoch': 4.03}

 34%|███▎      | 9442/28080 [18:39:39<36:55:56,  7.13s/it]
 34%|███▎      | 9443/28080 [18:39:46<37:06:05,  7.17s/it]
                                                          
{'loss': 0.6244, 'learning_rate': 0.0003867649902230469, 'epoch': 4.03}

 34%|███▎      | 9443/28080 [18:39:46<37:06:05,  7.17s/it]
 34%|███▎      | 9444/28080 [18:39:54<37:05:50,  7.17s/it]
                                                          
{'loss': 0.6115, 'learning_rate': 0.00038674085113229464, 'epoch': 4.03}

 34%|███▎      | 9444/28080 [18:39:54<37:05:50,  7.17s/it]
 34%|███▎      | 9445/28080 [18:40:01<37:01:10,  7.15s/it]
                                                          
{'loss': 0.6118, 'learning_rate': 0.0003867167102223463, 'epoch': 4.03}

 34%|███▎      | 9445/28080 [18:40:01<37:01:10,  7.15s/it]
 34%|███▎      | 9446/28080 [18:40:08<37:06:13,  7.17s/it]
                                                          
{'loss': 0.617, 'learning_rate': 0.0003866925674935233, 'epoch': 4.04}

 34%|███▎      | 9446/28080 [18:40:08<37:06:13,  7.17s/it]
 34%|███▎      | 9447/28080 [18:40:15<37:04:32,  7.16s/it]
                                                          
{'loss': 0.6288, 'learning_rate': 0.0003866684229461467, 'epoch': 4.04}

 34%|███▎      | 9447/28080 [18:40:15<37:04:32,  7.16s/it]
 34%|███▎      | 9448/28080 [18:40:22<36:58:58,  7.15s/it]
                                                          
{'loss': 0.6291, 'learning_rate': 0.00038664427658053767, 'epoch': 4.04}

 34%|███▎      | 9448/28080 [18:40:22<36:58:58,  7.15s/it]
 34%|███▎      | 9449/28080 [18:40:29<37:04:34,  7.16s/it]
                                                          
{'loss': 0.627, 'learning_rate': 0.00038662012839701753, 'epoch': 4.04}

 34%|███▎      | 9449/28080 [18:40:29<37:04:34,  7.16s/it]
 34%|███▎      | 9450/28080 [18:40:37<37:10:29,  7.18s/it]
                                                          
{'loss': 0.6369, 'learning_rate': 0.0003865959783959075, 'epoch': 4.04}

 34%|███▎      | 9450/28080 [18:40:37<37:10:29,  7.18s/it]
 34%|███▎      | 9451/28080 [18:40:44<37:07:10,  7.17s/it]
                                                          
{'loss': 0.6318, 'learning_rate': 0.00038657182657752886, 'epoch': 4.04}

 34%|███▎      | 9451/28080 [18:40:44<37:07:10,  7.17s/it]
 34%|███▎      | 9452/28080 [18:40:51<37:03:54,  7.16s/it]
                                                          
{'loss': 0.6291, 'learning_rate': 0.00038654767294220304, 'epoch': 4.04}

 34%|███▎      | 9452/28080 [18:40:51<37:03:54,  7.16s/it]
 34%|███▎      | 9453/28080 [18:40:58<37:01:45,  7.16s/it]
                                                          
{'loss': 0.6369, 'learning_rate': 0.0003865235174902513, 'epoch': 4.04}

 34%|███▎      | 9453/28080 [18:40:58<37:01:45,  7.16s/it]
 34%|███▎      | 9454/28080 [18:41:05<36:48:51,  7.12s/it]
                                                          
{'loss': 0.6265, 'learning_rate': 0.000386499360221995, 'epoch': 4.04}

 34%|███▎      | 9454/28080 [18:41:05<36:48:51,  7.12s/it]
 34%|███▎      | 9455/28080 [18:41:12<36:49:50,  7.12s/it]
                                                          
{'loss': 0.6206, 'learning_rate': 0.0003864752011377555, 'epoch': 4.04}

 34%|███▎      | 9455/28080 [18:41:12<36:49:50,  7.12s/it]
 34%|███▎      | 9456/28080 [18:41:19<36:50:08,  7.12s/it]
                                                          
{'loss': 0.6243, 'learning_rate': 0.0003864510402378543, 'epoch': 4.04}

 34%|███▎      | 9456/28080 [18:41:19<36:50:08,  7.12s/it]
 34%|███▎      | 9457/28080 [18:41:26<36:55:49,  7.14s/it]
                                                          
{'loss': 0.6557, 'learning_rate': 0.00038642687752261267, 'epoch': 4.04}

 34%|███▎      | 9457/28080 [18:41:26<36:55:49,  7.14s/it]
 34%|███▎      | 9458/28080 [18:41:34<37:04:24,  7.17s/it]
                                                          
{'loss': 0.6242, 'learning_rate': 0.00038640271299235227, 'epoch': 4.04}

 34%|███▎      | 9458/28080 [18:41:34<37:04:24,  7.17s/it]
 34%|███▎      | 9459/28080 [18:41:41<37:05:29,  7.17s/it]
                                                          
{'loss': 0.6273, 'learning_rate': 0.00038637854664739444, 'epoch': 4.04}

 34%|███▎      | 9459/28080 [18:41:41<37:05:29,  7.17s/it]
 34%|███▎      | 9460/28080 [18:41:48<37:02:33,  7.16s/it]
                                                          
{'loss': 0.6519, 'learning_rate': 0.00038635437848806077, 'epoch': 4.04}

 34%|███▎      | 9460/28080 [18:41:48<37:02:33,  7.16s/it]
 34%|███▎      | 9461/28080 [18:41:55<36:57:42,  7.15s/it]
                                                          
{'loss': 0.6212, 'learning_rate': 0.0003863302085146727, 'epoch': 4.04}

 34%|███▎      | 9461/28080 [18:41:55<36:57:42,  7.15s/it]
 34%|███▎      | 9462/28080 [18:42:02<37:00:56,  7.16s/it]
                                                          
{'loss': 0.6337, 'learning_rate': 0.00038630603672755193, 'epoch': 4.04}

 34%|███▎      | 9462/28080 [18:42:02<37:00:56,  7.16s/it]
 34%|███▎      | 9463/28080 [18:42:09<36:57:59,  7.15s/it]
                                                          
{'loss': 0.6178, 'learning_rate': 0.00038628186312702, 'epoch': 4.04}

 34%|███▎      | 9463/28080 [18:42:09<36:57:59,  7.15s/it]
 34%|███▎      | 9464/28080 [18:42:16<36:51:50,  7.13s/it]
                                                          
{'loss': 0.6373, 'learning_rate': 0.00038625768771339837, 'epoch': 4.04}

 34%|███▎      | 9464/28080 [18:42:16<36:51:50,  7.13s/it]
 34%|███▎      | 9465/28080 [18:42:24<36:48:38,  7.12s/it]
                                                          
{'loss': 0.6304, 'learning_rate': 0.0003862335104870088, 'epoch': 4.04}

 34%|███▎      | 9465/28080 [18:42:24<36:48:38,  7.12s/it]
 34%|███▎      | 9466/28080 [18:42:31<36:48:12,  7.12s/it]
                                                          
{'loss': 0.6094, 'learning_rate': 0.00038620933144817293, 'epoch': 4.04}

 34%|███▎      | 9466/28080 [18:42:31<36:48:12,  7.12s/it]
 34%|███▎      | 9467/28080 [18:42:38<36:48:10,  7.12s/it]
                                                          
{'loss': 0.6068, 'learning_rate': 0.0003861851505972124, 'epoch': 4.04}

 34%|███▎      | 9467/28080 [18:42:38<36:48:10,  7.12s/it]
 34%|███▎      | 9468/28080 [18:42:45<36:44:13,  7.11s/it]
                                                          
{'loss': 0.6385, 'learning_rate': 0.000386160967934449, 'epoch': 4.04}

 34%|███▎      | 9468/28080 [18:42:45<36:44:13,  7.11s/it]
 34%|███▎      | 9469/28080 [18:42:52<36:43:02,  7.10s/it]
                                                          
{'loss': 0.6553, 'learning_rate': 0.00038613678346020435, 'epoch': 4.05}

 34%|███▎      | 9469/28080 [18:42:52<36:43:02,  7.10s/it]
 34%|███▎      | 9470/28080 [18:42:59<36:46:44,  7.11s/it]
                                                          
{'loss': 0.6306, 'learning_rate': 0.0003861125971748003, 'epoch': 4.05}

 34%|███▎      | 9470/28080 [18:42:59<36:46:44,  7.11s/it]
 34%|███▎      | 9471/28080 [18:43:06<37:01:49,  7.16s/it]
                                                          
{'loss': 0.6224, 'learning_rate': 0.00038608840907855844, 'epoch': 4.05}

 34%|███▎      | 9471/28080 [18:43:06<37:01:49,  7.16s/it]
 34%|███▎      | 9472/28080 [18:43:14<36:54:36,  7.14s/it]
                                                          
{'loss': 0.6281, 'learning_rate': 0.0003860642191718008, 'epoch': 4.05}

 34%|███▎      | 9472/28080 [18:43:14<36:54:36,  7.14s/it]
 34%|███▎      | 9473/28080 [18:43:21<36:55:48,  7.15s/it]
                                                          
{'loss': 0.6031, 'learning_rate': 0.0003860400274548491, 'epoch': 4.05}

 34%|███▎      | 9473/28080 [18:43:21<36:55:48,  7.15s/it]
 34%|███▎      | 9474/28080 [18:43:28<36:52:37,  7.14s/it]
                                                          
{'loss': 0.6252, 'learning_rate': 0.0003860158339280251, 'epoch': 4.05}

 34%|███▎      | 9474/28080 [18:43:28<36:52:37,  7.14s/it]
 34%|███▎      | 9475/28080 [18:43:35<37:00:14,  7.16s/it]
                                                          
{'loss': 0.6331, 'learning_rate': 0.0003859916385916508, 'epoch': 4.05}

 34%|███▎      | 9475/28080 [18:43:35<37:00:14,  7.16s/it]
 34%|███▎      | 9476/28080 [18:43:42<36:49:47,  7.13s/it]
                                                          
{'loss': 0.6333, 'learning_rate': 0.000385967441446048, 'epoch': 4.05}

 34%|███▎      | 9476/28080 [18:43:42<36:49:47,  7.13s/it]
 34%|███▍      | 9477/28080 [18:43:49<36:46:02,  7.12s/it]
                                                          
{'loss': 0.62, 'learning_rate': 0.00038594324249153865, 'epoch': 4.05}

 34%|███▍      | 9477/28080 [18:43:49<36:46:02,  7.12s/it]
 34%|███▍      | 9478/28080 [18:43:56<36:51:59,  7.13s/it]
                                                          
{'loss': 0.6253, 'learning_rate': 0.0003859190417284448, 'epoch': 4.05}

 34%|███▍      | 9478/28080 [18:43:56<36:51:59,  7.13s/it]
 34%|███▍      | 9479/28080 [18:44:03<36:47:16,  7.12s/it]
                                                          
{'loss': 0.6043, 'learning_rate': 0.00038589483915708823, 'epoch': 4.05}

 34%|███▍      | 9479/28080 [18:44:03<36:47:16,  7.12s/it]
 34%|███▍      | 9480/28080 [18:44:11<36:48:04,  7.12s/it]
                                                          
{'loss': 0.6378, 'learning_rate': 0.00038587063477779106, 'epoch': 4.05}

 34%|███▍      | 9480/28080 [18:44:11<36:48:04,  7.12s/it]
 34%|███▍      | 9481/28080 [18:44:18<36:47:54,  7.12s/it]
                                                          
{'loss': 0.6442, 'learning_rate': 0.00038584642859087527, 'epoch': 4.05}

 34%|███▍      | 9481/28080 [18:44:18<36:47:54,  7.12s/it]
 34%|███▍      | 9482/28080 [18:44:25<36:38:55,  7.09s/it]
                                                          
{'loss': 0.62, 'learning_rate': 0.0003858222205966628, 'epoch': 4.05}

 34%|███▍      | 9482/28080 [18:44:25<36:38:55,  7.09s/it]
 34%|███▍      | 9483/28080 [18:44:32<36:47:26,  7.12s/it]
                                                          
{'loss': 0.616, 'learning_rate': 0.0003857980107954759, 'epoch': 4.05}

 34%|███▍      | 9483/28080 [18:44:32<36:47:26,  7.12s/it]
 34%|███▍      | 9484/28080 [18:44:39<36:49:04,  7.13s/it]
                                                          
{'loss': 0.6389, 'learning_rate': 0.00038577379918763654, 'epoch': 4.05}

 34%|███▍      | 9484/28080 [18:44:39<36:49:04,  7.13s/it]
 34%|███▍      | 9485/28080 [18:44:46<36:51:19,  7.14s/it]
                                                          
{'loss': 0.6248, 'learning_rate': 0.00038574958577346685, 'epoch': 4.05}

 34%|███▍      | 9485/28080 [18:44:46<36:51:19,  7.14s/it]
 34%|███▍      | 9486/28080 [18:44:53<36:51:11,  7.14s/it]
                                                          
{'loss': 0.6249, 'learning_rate': 0.000385725370553289, 'epoch': 4.05}

 34%|███▍      | 9486/28080 [18:44:53<36:51:11,  7.14s/it]
 34%|███▍      | 9487/28080 [18:45:00<36:51:58,  7.14s/it]
                                                          
{'loss': 0.6265, 'learning_rate': 0.00038570115352742505, 'epoch': 4.05}

 34%|███▍      | 9487/28080 [18:45:00<36:51:58,  7.14s/it]
 34%|███▍      | 9488/28080 [18:45:08<36:45:56,  7.12s/it]
                                                          
{'loss': 0.6328, 'learning_rate': 0.00038567693469619734, 'epoch': 4.05}

 34%|███▍      | 9488/28080 [18:45:08<36:45:56,  7.12s/it]
 34%|███▍      | 9489/28080 [18:45:15<36:45:41,  7.12s/it]
                                                          
{'loss': 0.6267, 'learning_rate': 0.0003856527140599279, 'epoch': 4.05}

 34%|███▍      | 9489/28080 [18:45:15<36:45:41,  7.12s/it]
 34%|███▍      | 9490/28080 [18:45:22<36:50:54,  7.14s/it]
                                                          
{'loss': 0.6379, 'learning_rate': 0.0003856284916189391, 'epoch': 4.05}

 34%|███▍      | 9490/28080 [18:45:22<36:50:54,  7.14s/it]
 34%|███▍      | 9491/28080 [18:45:29<36:38:12,  7.10s/it]
                                                          
{'loss': 0.6652, 'learning_rate': 0.0003856042673735531, 'epoch': 4.05}

 34%|███▍      | 9491/28080 [18:45:29<36:38:12,  7.10s/it]
 34%|███▍      | 9492/28080 [18:45:36<36:35:16,  7.09s/it]
                                                          
{'loss': 0.6217, 'learning_rate': 0.0003855800413240922, 'epoch': 4.05}

 34%|███▍      | 9492/28080 [18:45:36<36:35:16,  7.09s/it]
 34%|███▍      | 9493/28080 [18:45:43<36:41:27,  7.11s/it]
                                                          
{'loss': 0.6152, 'learning_rate': 0.00038555581347087876, 'epoch': 4.06}

 34%|███▍      | 9493/28080 [18:45:43<36:41:27,  7.11s/it]
 34%|███▍      | 9494/28080 [18:45:50<36:35:46,  7.09s/it]
                                                          
{'loss': 0.6288, 'learning_rate': 0.0003855315838142351, 'epoch': 4.06}

 34%|███▍      | 9494/28080 [18:45:50<36:35:46,  7.09s/it]
 34%|███▍      | 9495/28080 [18:45:57<36:38:01,  7.10s/it]
                                                          
{'loss': 0.6332, 'learning_rate': 0.00038550735235448353, 'epoch': 4.06}

 34%|███▍      | 9495/28080 [18:45:57<36:38:01,  7.10s/it]
 34%|███▍      | 9496/28080 [18:46:04<36:44:38,  7.12s/it]
                                                          
{'loss': 0.6193, 'learning_rate': 0.0003854831190919463, 'epoch': 4.06}

 34%|███▍      | 9496/28080 [18:46:04<36:44:38,  7.12s/it]
 34%|███▍      | 9497/28080 [18:46:11<36:46:01,  7.12s/it]
                                                          
{'loss': 0.5942, 'learning_rate': 0.00038545888402694614, 'epoch': 4.06}

 34%|███▍      | 9497/28080 [18:46:12<36:46:01,  7.12s/it]
 34%|███▍      | 9498/28080 [18:46:19<36:51:37,  7.14s/it]
                                                          
{'loss': 0.6062, 'learning_rate': 0.00038543464715980517, 'epoch': 4.06}

 34%|███▍      | 9498/28080 [18:46:19<36:51:37,  7.14s/it]
 34%|███▍      | 9499/28080 [18:46:26<36:41:09,  7.11s/it]
                                                          
{'loss': 0.6471, 'learning_rate': 0.0003854104084908459, 'epoch': 4.06}

 34%|███▍      | 9499/28080 [18:46:26<36:41:09,  7.11s/it]
 34%|███▍      | 9500/28080 [18:46:33<36:50:03,  7.14s/it]
                                                          
{'loss': 0.6043, 'learning_rate': 0.0003853861680203908, 'epoch': 4.06}

 34%|███▍      | 9500/28080 [18:46:33<36:50:03,  7.14s/it]
 34%|███▍      | 9501/28080 [18:46:40<36:53:34,  7.15s/it]
                                                          
{'loss': 0.61, 'learning_rate': 0.00038536192574876256, 'epoch': 4.06}

 34%|███▍      | 9501/28080 [18:46:40<36:53:34,  7.15s/it]
 34%|███▍      | 9502/28080 [18:46:47<36:45:03,  7.12s/it]
                                                          
{'loss': 0.6231, 'learning_rate': 0.0003853376816762835, 'epoch': 4.06}

 34%|███▍      | 9502/28080 [18:46:47<36:45:03,  7.12s/it]
 34%|███▍      | 9503/28080 [18:46:54<36:44:51,  7.12s/it]
                                                          
{'loss': 0.6157, 'learning_rate': 0.00038531343580327615, 'epoch': 4.06}

 34%|███▍      | 9503/28080 [18:46:54<36:44:51,  7.12s/it]
 34%|███▍      | 9504/28080 [18:47:01<36:46:28,  7.13s/it]
                                                          
{'loss': 0.6522, 'learning_rate': 0.0003852891881300632, 'epoch': 4.06}

 34%|███▍      | 9504/28080 [18:47:01<36:46:28,  7.13s/it]
 34%|███▍      | 9505/28080 [18:47:09<36:50:47,  7.14s/it]
                                                          
{'loss': 0.6278, 'learning_rate': 0.0003852649386569671, 'epoch': 4.06}

 34%|███▍      | 9505/28080 [18:47:09<36:50:47,  7.14s/it]
 34%|███▍      | 9506/28080 [18:47:16<36:56:03,  7.16s/it]
                                                          
{'loss': 0.6211, 'learning_rate': 0.00038524068738431057, 'epoch': 4.06}

 34%|███▍      | 9506/28080 [18:47:16<36:56:03,  7.16s/it]
 34%|███▍      | 9507/28080 [18:47:23<36:51:56,  7.15s/it]
                                                          
{'loss': 0.6358, 'learning_rate': 0.00038521643431241613, 'epoch': 4.06}

 34%|███▍      | 9507/28080 [18:47:23<36:51:56,  7.15s/it]
 34%|███▍      | 9508/28080 [18:47:30<36:47:38,  7.13s/it]
                                                          
{'loss': 0.6486, 'learning_rate': 0.00038519217944160667, 'epoch': 4.06}

 34%|███▍      | 9508/28080 [18:47:30<36:47:38,  7.13s/it]
 34%|███▍      | 9509/28080 [18:47:37<36:46:24,  7.13s/it]
                                                          
{'loss': 0.6304, 'learning_rate': 0.00038516792277220463, 'epoch': 4.06}

 34%|███▍      | 9509/28080 [18:47:37<36:46:24,  7.13s/it]
 34%|███▍      | 9510/28080 [18:47:44<36:51:35,  7.15s/it]
                                                          
{'loss': 0.6261, 'learning_rate': 0.00038514366430453283, 'epoch': 4.06}

 34%|███▍      | 9510/28080 [18:47:44<36:51:35,  7.15s/it]
 34%|███▍      | 9511/28080 [18:47:51<36:55:03,  7.16s/it]
                                                          
{'loss': 0.6136, 'learning_rate': 0.0003851194040389141, 'epoch': 4.06}

 34%|███▍      | 9511/28080 [18:47:51<36:55:03,  7.16s/it]
 34%|███▍      | 9512/28080 [18:47:59<36:58:24,  7.17s/it]
                                                          
{'loss': 0.6284, 'learning_rate': 0.000385095141975671, 'epoch': 4.06}

 34%|███▍      | 9512/28080 [18:47:59<36:58:24,  7.17s/it]
 34%|███▍      | 9513/28080 [18:48:06<37:01:15,  7.18s/it]
                                                          
{'loss': 0.6177, 'learning_rate': 0.0003850708781151264, 'epoch': 4.06}

 34%|███▍      | 9513/28080 [18:48:06<37:01:15,  7.18s/it]
 34%|███▍      | 9514/28080 [18:48:13<37:06:11,  7.19s/it]
                                                          
{'loss': 0.6005, 'learning_rate': 0.0003850466124576032, 'epoch': 4.06}

 34%|███▍      | 9514/28080 [18:48:13<37:06:11,  7.19s/it]
 34%|███▍      | 9515/28080 [18:48:20<37:03:27,  7.19s/it]
                                                          
{'loss': 0.5977, 'learning_rate': 0.00038502234500342405, 'epoch': 4.06}

 34%|███▍      | 9515/28080 [18:48:20<37:03:27,  7.19s/it]
 34%|███▍      | 9516/28080 [18:48:27<36:52:16,  7.15s/it]
                                                          
{'loss': 0.6222, 'learning_rate': 0.0003849980757529119, 'epoch': 4.07}

 34%|███▍      | 9516/28080 [18:48:27<36:52:16,  7.15s/it]
 34%|███▍      | 9517/28080 [18:48:34<36:52:05,  7.15s/it]
                                                          
{'loss': 0.637, 'learning_rate': 0.0003849738047063897, 'epoch': 4.07}

 34%|███▍      | 9517/28080 [18:48:34<36:52:05,  7.15s/it]
 34%|███▍      | 9518/28080 [18:48:42<36:51:46,  7.15s/it]
                                                          
{'loss': 0.6642, 'learning_rate': 0.00038494953186418013, 'epoch': 4.07}

 34%|███▍      | 9518/28080 [18:48:42<36:51:46,  7.15s/it]
 34%|███▍      | 9519/28080 [18:48:49<36:51:43,  7.15s/it]
                                                          
{'loss': 0.6343, 'learning_rate': 0.00038492525722660643, 'epoch': 4.07}

 34%|███▍      | 9519/28080 [18:48:49<36:51:43,  7.15s/it]
 34%|███▍      | 9520/28080 [18:48:56<36:48:33,  7.14s/it]
                                                          
{'loss': 0.6075, 'learning_rate': 0.00038490098079399125, 'epoch': 4.07}

 34%|███▍      | 9520/28080 [18:48:56<36:48:33,  7.14s/it]
 34%|███▍      | 9521/28080 [18:49:03<36:50:44,  7.15s/it]
                                                          
{'loss': 0.6388, 'learning_rate': 0.00038487670256665777, 'epoch': 4.07}

 34%|███▍      | 9521/28080 [18:49:03<36:50:44,  7.15s/it]
 34%|███▍      | 9522/28080 [18:49:10<36:53:53,  7.16s/it]
                                                          
{'loss': 0.6142, 'learning_rate': 0.0003848524225449289, 'epoch': 4.07}

 34%|███▍      | 9522/28080 [18:49:10<36:53:53,  7.16s/it]
 34%|███▍      | 9523/28080 [18:49:17<36:49:56,  7.15s/it]
                                                          
{'loss': 0.6338, 'learning_rate': 0.0003848281407291276, 'epoch': 4.07}

 34%|███▍      | 9523/28080 [18:49:17<36:49:56,  7.15s/it]
 34%|███▍      | 9524/28080 [18:49:24<36:38:19,  7.11s/it]
                                                          
{'loss': 0.6233, 'learning_rate': 0.000384803857119577, 'epoch': 4.07}

 34%|███▍      | 9524/28080 [18:49:24<36:38:19,  7.11s/it]
 34%|███▍      | 9525/28080 [18:49:32<36:50:01,  7.15s/it]
                                                          
{'loss': 0.6167, 'learning_rate': 0.00038477957171660014, 'epoch': 4.07}

 34%|███▍      | 9525/28080 [18:49:32<36:50:01,  7.15s/it]
 34%|███▍      | 9526/28080 [18:49:39<36:52:27,  7.15s/it]
                                                          
{'loss': 0.6274, 'learning_rate': 0.00038475528452052023, 'epoch': 4.07}

 34%|███▍      | 9526/28080 [18:49:39<36:52:27,  7.15s/it]
 34%|███▍      | 9527/28080 [18:49:46<36:55:24,  7.16s/it]
                                                          
{'loss': 0.6066, 'learning_rate': 0.00038473099553166016, 'epoch': 4.07}

 34%|███▍      | 9527/28080 [18:49:46<36:55:24,  7.16s/it]
 34%|███▍      | 9528/28080 [18:49:53<36:49:23,  7.15s/it]
                                                          
{'loss': 0.6342, 'learning_rate': 0.0003847067047503432, 'epoch': 4.07}

 34%|███▍      | 9528/28080 [18:49:53<36:49:23,  7.15s/it]
 34%|███▍      | 9529/28080 [18:50:00<36:57:08,  7.17s/it]
                                                          
{'loss': 0.6232, 'learning_rate': 0.00038468241217689257, 'epoch': 4.07}

 34%|███▍      | 9529/28080 [18:50:00<36:57:08,  7.17s/it]
 34%|███▍      | 9530/28080 [18:50:07<36:57:33,  7.17s/it]
                                                          
{'loss': 0.6195, 'learning_rate': 0.0003846581178116313, 'epoch': 4.07}

 34%|███▍      | 9530/28080 [18:50:07<36:57:33,  7.17s/it]
 34%|███▍      | 9531/28080 [18:50:15<36:52:39,  7.16s/it]
                                                          
{'loss': 0.6397, 'learning_rate': 0.0003846338216548828, 'epoch': 4.07}

 34%|███▍      | 9531/28080 [18:50:15<36:52:39,  7.16s/it]
 34%|███▍      | 9532/28080 [18:50:22<36:46:04,  7.14s/it]
                                                          
{'loss': 0.6475, 'learning_rate': 0.0003846095237069701, 'epoch': 4.07}

 34%|███▍      | 9532/28080 [18:50:22<36:46:04,  7.14s/it]
 34%|███▍      | 9533/28080 [18:50:29<36:51:17,  7.15s/it]
                                                          
{'loss': 0.6107, 'learning_rate': 0.00038458522396821664, 'epoch': 4.07}

 34%|███▍      | 9533/28080 [18:50:29<36:51:17,  7.15s/it]
 34%|███▍      | 9534/28080 [18:50:36<36:42:45,  7.13s/it]
                                                          
{'loss': 0.6409, 'learning_rate': 0.0003845609224389456, 'epoch': 4.07}

 34%|███▍      | 9534/28080 [18:50:36<36:42:45,  7.13s/it]
 34%|███▍      | 9535/28080 [18:50:43<36:52:03,  7.16s/it]
                                                          
{'loss': 0.6218, 'learning_rate': 0.00038453661911948023, 'epoch': 4.07}

 34%|███▍      | 9535/28080 [18:50:43<36:52:03,  7.16s/it]
 34%|███▍      | 9536/28080 [18:50:50<36:54:01,  7.16s/it]
                                                          
{'loss': 0.6147, 'learning_rate': 0.00038451231401014394, 'epoch': 4.07}

 34%|███▍      | 9536/28080 [18:50:50<36:54:01,  7.16s/it]
 34%|███▍      | 9537/28080 [18:50:58<36:52:38,  7.16s/it]
                                                          
{'loss': 0.6178, 'learning_rate': 0.0003844880071112602, 'epoch': 4.07}

 34%|███▍      | 9537/28080 [18:50:58<36:52:38,  7.16s/it]
 34%|███▍      | 9538/28080 [18:51:05<36:49:13,  7.15s/it]
                                                          
{'loss': 0.6159, 'learning_rate': 0.0003844636984231522, 'epoch': 4.07}

 34%|███▍      | 9538/28080 [18:51:05<36:49:13,  7.15s/it]
 34%|███▍      | 9539/28080 [18:51:12<36:46:16,  7.14s/it]
                                                          
{'loss': 0.6392, 'learning_rate': 0.0003844393879461434, 'epoch': 4.07}

 34%|███▍      | 9539/28080 [18:51:12<36:46:16,  7.14s/it]
 34%|███▍      | 9540/28080 [18:51:19<36:44:08,  7.13s/it]
                                                          
{'loss': 0.6075, 'learning_rate': 0.00038441507568055724, 'epoch': 4.08}

 34%|███▍      | 9540/28080 [18:51:19<36:44:08,  7.13s/it]
 34%|███▍      | 9541/28080 [18:51:26<36:39:51,  7.12s/it]
                                                          
{'loss': 0.662, 'learning_rate': 0.0003843907616267172, 'epoch': 4.08}

 34%|███▍      | 9541/28080 [18:51:26<36:39:51,  7.12s/it]
 34%|███▍      | 9542/28080 [18:51:33<36:46:04,  7.14s/it]
                                                          
{'loss': 0.6217, 'learning_rate': 0.00038436644578494663, 'epoch': 4.08}

 34%|███▍      | 9542/28080 [18:51:33<36:46:04,  7.14s/it]
 34%|███▍      | 9543/28080 [18:51:40<36:47:58,  7.15s/it]
                                                          
{'loss': 0.6212, 'learning_rate': 0.00038434212815556925, 'epoch': 4.08}

 34%|███▍      | 9543/28080 [18:51:40<36:47:58,  7.15s/it]
 34%|███▍      | 9544/28080 [18:51:47<36:49:46,  7.15s/it]
                                                          
{'loss': 0.6346, 'learning_rate': 0.0003843178087389084, 'epoch': 4.08}

 34%|███▍      | 9544/28080 [18:51:47<36:49:46,  7.15s/it]
 34%|███▍      | 9545/28080 [18:51:55<36:40:15,  7.12s/it]
                                                          
{'loss': 0.6554, 'learning_rate': 0.0003842934875352876, 'epoch': 4.08}

 34%|███▍      | 9545/28080 [18:51:55<36:40:15,  7.12s/it]
 34%|███▍      | 9546/28080 [18:52:02<36:45:54,  7.14s/it]
                                                          
{'loss': 0.6433, 'learning_rate': 0.00038426916454503056, 'epoch': 4.08}

 34%|███▍      | 9546/28080 [18:52:02<36:45:54,  7.14s/it]
 34%|███▍      | 9547/28080 [18:52:09<36:48:59,  7.15s/it]
                                                          
{'loss': 0.6114, 'learning_rate': 0.0003842448397684608, 'epoch': 4.08}

 34%|███▍      | 9547/28080 [18:52:09<36:48:59,  7.15s/it]
 34%|███▍      | 9548/28080 [18:52:16<36:43:54,  7.14s/it]
                                                          
{'loss': 0.6336, 'learning_rate': 0.0003842205132059019, 'epoch': 4.08}

 34%|███▍      | 9548/28080 [18:52:16<36:43:54,  7.14s/it]
 34%|███▍      | 9549/28080 [18:52:23<36:37:13,  7.11s/it]
                                                          
{'loss': 0.6308, 'learning_rate': 0.0003841961848576776, 'epoch': 4.08}

 34%|███▍      | 9549/28080 [18:52:23<36:37:13,  7.11s/it]
 34%|███▍      | 9550/28080 [18:52:30<36:33:56,  7.10s/it]
                                                          
{'loss': 0.6163, 'learning_rate': 0.0003841718547241114, 'epoch': 4.08}

 34%|███▍      | 9550/28080 [18:52:30<36:33:56,  7.10s/it]
 34%|███▍      | 9551/28080 [18:52:37<36:29:08,  7.09s/it]
                                                          
{'loss': 0.6025, 'learning_rate': 0.0003841475228055272, 'epoch': 4.08}

 34%|███▍      | 9551/28080 [18:52:37<36:29:08,  7.09s/it]
 34%|███▍      | 9552/28080 [18:52:44<36:37:30,  7.12s/it]
                                                          
{'loss': 0.6321, 'learning_rate': 0.0003841231891022485, 'epoch': 4.08}

 34%|███▍      | 9552/28080 [18:52:44<36:37:30,  7.12s/it]
 34%|███▍      | 9553/28080 [18:52:52<36:40:53,  7.13s/it]
                                                          
{'loss': 0.6413, 'learning_rate': 0.0003840988536145993, 'epoch': 4.08}

 34%|███▍      | 9553/28080 [18:52:52<36:40:53,  7.13s/it]
 34%|███▍      | 9554/28080 [18:52:59<36:41:16,  7.13s/it]
                                                          
{'loss': 0.6353, 'learning_rate': 0.00038407451634290304, 'epoch': 4.08}

 34%|███▍      | 9554/28080 [18:52:59<36:41:16,  7.13s/it]
 34%|███▍      | 9555/28080 [18:53:06<36:54:30,  7.17s/it]
                                                          
{'loss': 0.6149, 'learning_rate': 0.0003840501772874837, 'epoch': 4.08}

 34%|███▍      | 9555/28080 [18:53:06<36:54:30,  7.17s/it]
 34%|███▍      | 9556/28080 [18:53:13<36:40:25,  7.13s/it]
                                                          
{'loss': 0.6256, 'learning_rate': 0.0003840258364486651, 'epoch': 4.08}

 34%|███▍      | 9556/28080 [18:53:13<36:40:25,  7.13s/it]
 34%|███▍      | 9557/28080 [18:53:20<36:33:42,  7.11s/it]
                                                          
{'loss': 0.6415, 'learning_rate': 0.00038400149382677095, 'epoch': 4.08}

 34%|███▍      | 9557/28080 [18:53:20<36:33:42,  7.11s/it]
 34%|███▍      | 9558/28080 [18:53:27<36:33:58,  7.11s/it]
                                                          
{'loss': 0.643, 'learning_rate': 0.00038397714942212514, 'epoch': 4.08}

 34%|███▍      | 9558/28080 [18:53:27<36:33:58,  7.11s/it]
 34%|███▍      | 9559/28080 [18:53:34<36:38:44,  7.12s/it]
                                                          
{'loss': 0.6329, 'learning_rate': 0.00038395280323505156, 'epoch': 4.08}

 34%|███▍      | 9559/28080 [18:53:34<36:38:44,  7.12s/it]
 34%|███▍      | 9560/28080 [18:53:41<36:42:06,  7.13s/it]
                                                          
{'loss': 0.6149, 'learning_rate': 0.0003839284552658742, 'epoch': 4.08}

 34%|███▍      | 9560/28080 [18:53:41<36:42:06,  7.13s/it]
 34%|███▍      | 9561/28080 [18:53:49<36:45:37,  7.15s/it]
                                                          
{'loss': 0.6014, 'learning_rate': 0.0003839041055149169, 'epoch': 4.08}

 34%|███▍      | 9561/28080 [18:53:49<36:45:37,  7.15s/it]
 34%|███▍      | 9562/28080 [18:53:56<36:48:09,  7.15s/it]
                                                          
{'loss': 0.6307, 'learning_rate': 0.00038387975398250366, 'epoch': 4.08}

 34%|███▍      | 9562/28080 [18:53:56<36:48:09,  7.15s/it]
 34%|███▍      | 9563/28080 [18:54:03<36:46:59,  7.15s/it]
                                                          
{'loss': 0.654, 'learning_rate': 0.0003838554006689583, 'epoch': 4.09}

 34%|███▍      | 9563/28080 [18:54:03<36:46:59,  7.15s/it]
 34%|███▍      | 9564/28080 [18:54:10<36:44:27,  7.14s/it]
                                                          
{'loss': 0.6244, 'learning_rate': 0.000383831045574605, 'epoch': 4.09}

 34%|███▍      | 9564/28080 [18:54:10<36:44:27,  7.14s/it]
 34%|███▍      | 9565/28080 [18:54:17<36:44:19,  7.14s/it]
                                                          
{'loss': 0.6334, 'learning_rate': 0.00038380668869976767, 'epoch': 4.09}

 34%|███▍      | 9565/28080 [18:54:17<36:44:19,  7.14s/it]
 34%|███▍      | 9566/28080 [18:54:24<36:48:41,  7.16s/it]
                                                          
{'loss': 0.6322, 'learning_rate': 0.00038378233004477037, 'epoch': 4.09}

 34%|███▍      | 9566/28080 [18:54:24<36:48:41,  7.16s/it]
 34%|███▍      | 9567/28080 [18:54:31<36:42:57,  7.14s/it]
                                                          
{'loss': 0.6419, 'learning_rate': 0.00038375796960993724, 'epoch': 4.09}

 34%|███▍      | 9567/28080 [18:54:31<36:42:57,  7.14s/it]
 34%|███▍      | 9568/28080 [18:54:39<36:33:52,  7.11s/it]
                                                          
{'loss': 0.6282, 'learning_rate': 0.00038373360739559224, 'epoch': 4.09}

 34%|███▍      | 9568/28080 [18:54:39<36:33:52,  7.11s/it]
 34%|███▍      | 9569/28080 [18:54:46<36:37:11,  7.12s/it]
                                                          
{'loss': 0.624, 'learning_rate': 0.00038370924340205967, 'epoch': 4.09}

 34%|███▍      | 9569/28080 [18:54:46<36:37:11,  7.12s/it]
 34%|███▍      | 9570/28080 [18:54:53<36:38:35,  7.13s/it]
                                                          
{'loss': 0.6277, 'learning_rate': 0.0003836848776296635, 'epoch': 4.09}

 34%|███▍      | 9570/28080 [18:54:53<36:38:35,  7.13s/it]
 34%|███▍      | 9571/28080 [18:55:00<36:39:42,  7.13s/it]
                                                          
{'loss': 0.6318, 'learning_rate': 0.0003836605100787279, 'epoch': 4.09}

 34%|███▍      | 9571/28080 [18:55:00<36:39:42,  7.13s/it]
 34%|███▍      | 9572/28080 [18:55:07<36:44:58,  7.15s/it]
                                                          
{'loss': 0.6304, 'learning_rate': 0.0003836361407495772, 'epoch': 4.09}

 34%|███▍      | 9572/28080 [18:55:07<36:44:58,  7.15s/it]
 34%|███▍      | 9573/28080 [18:55:14<36:55:31,  7.18s/it]
                                                          
{'loss': 0.6205, 'learning_rate': 0.0003836117696425354, 'epoch': 4.09}

 34%|███▍      | 9573/28080 [18:55:14<36:55:31,  7.18s/it]
 34%|███▍      | 9574/28080 [18:55:22<36:47:56,  7.16s/it]
                                                          
{'loss': 0.613, 'learning_rate': 0.000383587396757927, 'epoch': 4.09}

 34%|███▍      | 9574/28080 [18:55:22<36:47:56,  7.16s/it]
 34%|███▍      | 9575/28080 [18:55:29<36:53:13,  7.18s/it]
                                                          
{'loss': 0.6175, 'learning_rate': 0.00038356302209607596, 'epoch': 4.09}

 34%|███▍      | 9575/28080 [18:55:29<36:53:13,  7.18s/it]
 34%|███▍      | 9576/28080 [18:55:36<37:00:23,  7.20s/it]
                                                          
{'loss': 0.6256, 'learning_rate': 0.0003835386456573067, 'epoch': 4.09}

 34%|███▍      | 9576/28080 [18:55:36<37:00:23,  7.20s/it]
 34%|███▍      | 9577/28080 [18:55:43<36:49:50,  7.17s/it]
                                                          
{'loss': 0.6252, 'learning_rate': 0.00038351426744194365, 'epoch': 4.09}

 34%|███▍      | 9577/28080 [18:55:43<36:49:50,  7.17s/it]
 34%|███▍      | 9578/28080 [18:55:50<36:41:15,  7.14s/it]
                                                          
{'loss': 0.647, 'learning_rate': 0.00038348988745031087, 'epoch': 4.09}

 34%|███▍      | 9578/28080 [18:55:50<36:41:15,  7.14s/it]
 34%|███▍      | 9579/28080 [18:55:57<36:36:33,  7.12s/it]
                                                          
{'loss': 0.6392, 'learning_rate': 0.0003834655056827329, 'epoch': 4.09}

 34%|███▍      | 9579/28080 [18:55:57<36:36:33,  7.12s/it]
 34%|███▍      | 9580/28080 [18:56:04<36:34:14,  7.12s/it]
                                                          
{'loss': 0.6493, 'learning_rate': 0.0003834411221395341, 'epoch': 4.09}

 34%|███▍      | 9580/28080 [18:56:04<36:34:14,  7.12s/it]
 34%|███▍      | 9581/28080 [18:56:11<36:32:17,  7.11s/it]
                                                          
{'loss': 0.6442, 'learning_rate': 0.00038341673682103884, 'epoch': 4.09}

 34%|███▍      | 9581/28080 [18:56:11<36:32:17,  7.11s/it]
 34%|███▍      | 9582/28080 [18:56:18<36:24:42,  7.09s/it]
                                                          
{'loss': 0.6151, 'learning_rate': 0.0003833923497275714, 'epoch': 4.09}

 34%|███▍      | 9582/28080 [18:56:18<36:24:42,  7.09s/it]
 34%|███▍      | 9583/28080 [18:56:26<36:26:49,  7.09s/it]
                                                          
{'loss': 0.6241, 'learning_rate': 0.00038336796085945647, 'epoch': 4.09}

 34%|███▍      | 9583/28080 [18:56:26<36:26:49,  7.09s/it]
 34%|███▍      | 9584/28080 [18:56:33<36:29:18,  7.10s/it]
                                                          
{'loss': 0.6346, 'learning_rate': 0.0003833435702170184, 'epoch': 4.09}

 34%|███▍      | 9584/28080 [18:56:33<36:29:18,  7.10s/it]
 34%|███▍      | 9585/28080 [18:56:40<36:25:02,  7.09s/it]
                                                          
{'loss': 0.6425, 'learning_rate': 0.0003833191778005817, 'epoch': 4.09}

 34%|███▍      | 9585/28080 [18:56:40<36:25:02,  7.09s/it]
 34%|███▍      | 9586/28080 [18:56:47<36:30:38,  7.11s/it]
                                                          
{'loss': 0.6312, 'learning_rate': 0.0003832947836104709, 'epoch': 4.1}

 34%|███▍      | 9586/28080 [18:56:47<36:30:38,  7.11s/it]
 34%|███▍      | 9587/28080 [18:56:54<36:37:02,  7.13s/it]
                                                          
{'loss': 0.6289, 'learning_rate': 0.0003832703876470105, 'epoch': 4.1}

 34%|███▍      | 9587/28080 [18:56:54<36:37:02,  7.13s/it]
 34%|███▍      | 9588/28080 [18:57:01<36:39:21,  7.14s/it]
                                                          
{'loss': 0.6184, 'learning_rate': 0.00038324598991052507, 'epoch': 4.1}

 34%|███▍      | 9588/28080 [18:57:01<36:39:21,  7.14s/it]
 34%|███▍      | 9589/28080 [18:57:08<36:39:56,  7.14s/it]
                                                          
{'loss': 0.6248, 'learning_rate': 0.0003832215904013392, 'epoch': 4.1}

 34%|███▍      | 9589/28080 [18:57:08<36:39:56,  7.14s/it]
 34%|███▍      | 9590/28080 [18:57:15<36:32:41,  7.12s/it]
                                                          
{'loss': 0.6404, 'learning_rate': 0.00038319718911977745, 'epoch': 4.1}

 34%|███▍      | 9590/28080 [18:57:15<36:32:41,  7.12s/it]
 34%|███▍      | 9591/28080 [18:57:23<36:44:35,  7.15s/it]
                                                          
{'loss': 0.622, 'learning_rate': 0.00038317278606616456, 'epoch': 4.1}

 34%|███▍      | 9591/28080 [18:57:23<36:44:35,  7.15s/it]
 34%|███▍      | 9592/28080 [18:57:30<36:39:19,  7.14s/it]
                                                          
{'loss': 0.6148, 'learning_rate': 0.0003831483812408252, 'epoch': 4.1}

 34%|███▍      | 9592/28080 [18:57:30<36:39:19,  7.14s/it]
 34%|███▍      | 9593/28080 [18:57:37<36:44:31,  7.15s/it]
                                                          
{'loss': 0.6437, 'learning_rate': 0.00038312397464408394, 'epoch': 4.1}

 34%|███▍      | 9593/28080 [18:57:37<36:44:31,  7.15s/it]
 34%|███▍      | 9594/28080 [18:57:44<36:41:45,  7.15s/it]
                                                          
{'loss': 0.6414, 'learning_rate': 0.00038309956627626554, 'epoch': 4.1}

 34%|███▍      | 9594/28080 [18:57:44<36:41:45,  7.15s/it]
 34%|███▍      | 9595/28080 [18:57:51<36:44:23,  7.16s/it]
                                                          
{'loss': 0.6256, 'learning_rate': 0.0003830751561376947, 'epoch': 4.1}

 34%|███▍      | 9595/28080 [18:57:51<36:44:23,  7.16s/it]
 34%|███▍      | 9596/28080 [18:57:58<36:43:16,  7.15s/it]
                                                          
{'loss': 0.6389, 'learning_rate': 0.00038305074422869626, 'epoch': 4.1}

 34%|███▍      | 9596/28080 [18:57:58<36:43:16,  7.15s/it]
 34%|███▍      | 9597/28080 [18:58:06<36:46:15,  7.16s/it]
                                                          
{'loss': 0.619, 'learning_rate': 0.00038302633054959487, 'epoch': 4.1}

 34%|███▍      | 9597/28080 [18:58:06<36:46:15,  7.16s/it]
 34%|███▍      | 9598/28080 [18:58:13<36:47:46,  7.17s/it]
                                                          
{'loss': 0.6389, 'learning_rate': 0.00038300191510071537, 'epoch': 4.1}

 34%|███▍      | 9598/28080 [18:58:13<36:47:46,  7.17s/it]
 34%|███▍      | 9599/28080 [18:58:20<36:48:52,  7.17s/it]
                                                          
{'loss': 0.633, 'learning_rate': 0.0003829774978823826, 'epoch': 4.1}

 34%|███▍      | 9599/28080 [18:58:20<36:48:52,  7.17s/it]
 34%|███▍      | 9600/28080 [18:58:27<36:46:44,  7.16s/it]
                                                          
{'loss': 0.6335, 'learning_rate': 0.0003829530788949214, 'epoch': 4.1}

 34%|███▍      | 9600/28080 [18:58:27<36:46:44,  7.16s/it]
 34%|███▍      | 9601/28080 [18:58:34<36:38:26,  7.14s/it]
                                                          
{'loss': 0.6378, 'learning_rate': 0.00038292865813865674, 'epoch': 4.1}

 34%|███▍      | 9601/28080 [18:58:34<36:38:26,  7.14s/it]
 34%|███▍      | 9602/28080 [18:58:41<36:36:27,  7.13s/it]
                                                          
{'loss': 0.6208, 'learning_rate': 0.0003829042356139133, 'epoch': 4.1}

 34%|███▍      | 9602/28080 [18:58:41<36:36:27,  7.13s/it]
 34%|███▍      | 9603/28080 [18:58:48<36:37:14,  7.14s/it]
                                                          
{'loss': 0.6303, 'learning_rate': 0.00038287981132101626, 'epoch': 4.1}

 34%|███▍      | 9603/28080 [18:58:48<36:37:14,  7.14s/it]
 34%|███▍      | 9604/28080 [18:58:56<36:34:28,  7.13s/it]
                                                          
{'loss': 0.6223, 'learning_rate': 0.0003828553852602903, 'epoch': 4.1}

 34%|███▍      | 9604/28080 [18:58:56<36:34:28,  7.13s/it]
 34%|███▍      | 9605/28080 [18:59:03<36:45:55,  7.16s/it]
                                                          
{'loss': 0.6246, 'learning_rate': 0.0003828309574320605, 'epoch': 4.1}

 34%|███▍      | 9605/28080 [18:59:03<36:45:55,  7.16s/it]
 34%|███▍      | 9606/28080 [18:59:10<36:45:39,  7.16s/it]
                                                          
{'loss': 0.6254, 'learning_rate': 0.0003828065278366518, 'epoch': 4.1}

 34%|███▍      | 9606/28080 [18:59:10<36:45:39,  7.16s/it]
 34%|███▍      | 9607/28080 [18:59:17<36:38:33,  7.14s/it]
                                                          
{'loss': 0.6281, 'learning_rate': 0.0003827820964743893, 'epoch': 4.1}

 34%|███▍      | 9607/28080 [18:59:17<36:38:33,  7.14s/it]
 34%|███▍      | 9608/28080 [18:59:24<36:31:18,  7.12s/it]
                                                          
{'loss': 0.6267, 'learning_rate': 0.0003827576633455981, 'epoch': 4.1}

 34%|███▍      | 9608/28080 [18:59:24<36:31:18,  7.12s/it]
 34%|███▍      | 9609/28080 [18:59:31<36:30:49,  7.12s/it]
                                                          
{'loss': 0.6353, 'learning_rate': 0.000382733228450603, 'epoch': 4.1}

 34%|███▍      | 9609/28080 [18:59:31<36:30:49,  7.12s/it]
 34%|███▍      | 9610/28080 [18:59:38<36:36:23,  7.13s/it]
                                                          
{'loss': 0.637, 'learning_rate': 0.0003827087917897293, 'epoch': 4.11}

 34%|███▍      | 9610/28080 [18:59:38<36:36:23,  7.13s/it]
 34%|███▍      | 9611/28080 [18:59:45<36:29:02,  7.11s/it]
                                                          
{'loss': 0.6286, 'learning_rate': 0.00038268435336330205, 'epoch': 4.11}

 34%|███▍      | 9611/28080 [18:59:45<36:29:02,  7.11s/it]
 34%|███▍      | 9612/28080 [18:59:53<36:25:39,  7.10s/it]
                                                          
{'loss': 0.6346, 'learning_rate': 0.00038265991317164636, 'epoch': 4.11}

 34%|███▍      | 9612/28080 [18:59:53<36:25:39,  7.10s/it]
 34%|███▍      | 9613/28080 [19:00:00<36:36:22,  7.14s/it]
                                                          
{'loss': 0.6222, 'learning_rate': 0.00038263547121508733, 'epoch': 4.11}

 34%|███▍      | 9613/28080 [19:00:00<36:36:22,  7.14s/it]
 34%|███▍      | 9614/28080 [19:00:07<36:34:06,  7.13s/it]
                                                          
{'loss': 0.6279, 'learning_rate': 0.00038261102749395014, 'epoch': 4.11}

 34%|███▍      | 9614/28080 [19:00:07<36:34:06,  7.13s/it]
 34%|███▍      | 9615/28080 [19:00:14<36:30:52,  7.12s/it]
                                                          
{'loss': 0.6287, 'learning_rate': 0.0003825865820085602, 'epoch': 4.11}

 34%|███▍      | 9615/28080 [19:00:14<36:30:52,  7.12s/it]
 34%|███▍      | 9616/28080 [19:00:21<36:26:53,  7.11s/it]
                                                          
{'loss': 0.6162, 'learning_rate': 0.0003825621347592424, 'epoch': 4.11}

 34%|███▍      | 9616/28080 [19:00:21<36:26:53,  7.11s/it]
 34%|███▍      | 9617/28080 [19:00:28<36:31:42,  7.12s/it]
                                                          
{'loss': 0.6276, 'learning_rate': 0.0003825376857463223, 'epoch': 4.11}

 34%|███▍      | 9617/28080 [19:00:28<36:31:42,  7.12s/it]
 34%|███▍      | 9618/28080 [19:00:35<36:28:57,  7.11s/it]
                                                          
{'loss': 0.6143, 'learning_rate': 0.0003825132349701249, 'epoch': 4.11}

 34%|███▍      | 9618/28080 [19:00:35<36:28:57,  7.11s/it]
 34%|███▍      | 9619/28080 [19:00:43<36:39:57,  7.15s/it]
                                                          
{'loss': 0.6043, 'learning_rate': 0.00038248878243097575, 'epoch': 4.11}

 34%|███▍      | 9619/28080 [19:00:43<36:39:57,  7.15s/it]
 34%|███▍      | 9620/28080 [19:00:50<36:40:20,  7.15s/it]
                                                          
{'loss': 0.6114, 'learning_rate': 0.0003824643281292, 'epoch': 4.11}

 34%|███▍      | 9620/28080 [19:00:50<36:40:20,  7.15s/it]
 34%|███▍      | 9621/28080 [19:00:57<36:45:07,  7.17s/it]
                                                          
{'loss': 0.6294, 'learning_rate': 0.00038243987206512285, 'epoch': 4.11}

 34%|███▍      | 9621/28080 [19:00:57<36:45:07,  7.17s/it]
 34%|███▍      | 9622/28080 [19:01:04<36:35:52,  7.14s/it]
                                                          
{'loss': 0.6471, 'learning_rate': 0.00038241541423907, 'epoch': 4.11}

 34%|███▍      | 9622/28080 [19:01:04<36:35:52,  7.14s/it]
 34%|███▍      | 9623/28080 [19:01:11<36:38:32,  7.15s/it]
                                                          
{'loss': 0.6328, 'learning_rate': 0.0003823909546513666, 'epoch': 4.11}

 34%|███▍      | 9623/28080 [19:01:11<36:38:32,  7.15s/it]
 34%|███▍      | 9624/28080 [19:01:18<36:29:04,  7.12s/it]
                                                          
{'loss': 0.6134, 'learning_rate': 0.0003823664933023382, 'epoch': 4.11}

 34%|███▍      | 9624/28080 [19:01:18<36:29:04,  7.12s/it]
 34%|███▍      | 9625/28080 [19:01:25<36:30:47,  7.12s/it]
                                                          
{'loss': 0.6202, 'learning_rate': 0.0003823420301923101, 'epoch': 4.11}

 34%|███▍      | 9625/28080 [19:01:25<36:30:47,  7.12s/it]
 34%|███▍      | 9626/28080 [19:01:32<36:30:55,  7.12s/it]
                                                          
{'loss': 0.6539, 'learning_rate': 0.0003823175653216078, 'epoch': 4.11}

 34%|███▍      | 9626/28080 [19:01:32<36:30:55,  7.12s/it]
 34%|███▍      | 9627/28080 [19:01:40<36:38:09,  7.15s/it]
                                                          
{'loss': 0.6045, 'learning_rate': 0.00038229309869055683, 'epoch': 4.11}

 34%|███▍      | 9627/28080 [19:01:40<36:38:09,  7.15s/it]
 34%|███▍      | 9628/28080 [19:01:47<36:41:55,  7.16s/it]
                                                          
{'loss': 0.6035, 'learning_rate': 0.00038226863029948264, 'epoch': 4.11}

 34%|███▍      | 9628/28080 [19:01:47<36:41:55,  7.16s/it]
 34%|███▍      | 9629/28080 [19:01:54<36:48:24,  7.18s/it]
                                                          
{'loss': 0.6046, 'learning_rate': 0.00038224416014871087, 'epoch': 4.11}

 34%|███▍      | 9629/28080 [19:01:54<36:48:24,  7.18s/it]
 34%|███▍      | 9630/28080 [19:02:01<36:37:51,  7.15s/it]
                                                          
{'loss': 0.6389, 'learning_rate': 0.0003822196882385669, 'epoch': 4.11}

 34%|███▍      | 9630/28080 [19:02:01<36:37:51,  7.15s/it]
 34%|███▍      | 9631/28080 [19:02:08<36:43:42,  7.17s/it]
                                                          
{'loss': 0.6215, 'learning_rate': 0.0003821952145693763, 'epoch': 4.11}

 34%|███▍      | 9631/28080 [19:02:08<36:43:42,  7.17s/it]
 34%|███▍      | 9632/28080 [19:02:15<36:39:21,  7.15s/it]
                                                          
{'loss': 0.6292, 'learning_rate': 0.0003821707391414649, 'epoch': 4.11}

 34%|███▍      | 9632/28080 [19:02:15<36:39:21,  7.15s/it]
 34%|███▍      | 9633/28080 [19:02:23<36:41:59,  7.16s/it]
                                                          
{'loss': 0.6223, 'learning_rate': 0.0003821462619551581, 'epoch': 4.12}

 34%|███▍      | 9633/28080 [19:02:23<36:41:59,  7.16s/it]
 34%|███▍      | 9634/28080 [19:02:30<36:44:19,  7.17s/it]
                                                          
{'loss': 0.6305, 'learning_rate': 0.0003821217830107816, 'epoch': 4.12}

 34%|███▍      | 9634/28080 [19:02:30<36:44:19,  7.17s/it]
 34%|███▍      | 9635/28080 [19:02:37<36:51:27,  7.19s/it]
                                                          
{'loss': 0.6169, 'learning_rate': 0.00038209730230866115, 'epoch': 4.12}

 34%|███▍      | 9635/28080 [19:02:37<36:51:27,  7.19s/it]
 34%|███▍      | 9636/28080 [19:02:44<36:35:52,  7.14s/it]
                                                          
{'loss': 0.6446, 'learning_rate': 0.0003820728198491223, 'epoch': 4.12}

 34%|███▍      | 9636/28080 [19:02:44<36:35:52,  7.14s/it]
 34%|███▍      | 9637/28080 [19:02:51<36:36:12,  7.14s/it]
                                                          
{'loss': 0.6238, 'learning_rate': 0.0003820483356324909, 'epoch': 4.12}

 34%|███▍      | 9637/28080 [19:02:51<36:36:12,  7.14s/it]
 34%|███▍      | 9638/28080 [19:02:58<36:38:05,  7.15s/it]
                                                          
{'loss': 0.6151, 'learning_rate': 0.0003820238496590925, 'epoch': 4.12}

 34%|███▍      | 9638/28080 [19:02:58<36:38:05,  7.15s/it]
 34%|███▍      | 9639/28080 [19:03:06<36:34:39,  7.14s/it]
                                                          
{'loss': 0.6459, 'learning_rate': 0.00038199936192925306, 'epoch': 4.12}

 34%|███▍      | 9639/28080 [19:03:06<36:34:39,  7.14s/it]
 34%|███▍      | 9640/28080 [19:03:13<36:37:46,  7.15s/it]
                                                          
{'loss': 0.6181, 'learning_rate': 0.00038197487244329825, 'epoch': 4.12}

 34%|███▍      | 9640/28080 [19:03:13<36:37:46,  7.15s/it]
 34%|███▍      | 9641/28080 [19:03:20<36:23:05,  7.10s/it]
                                                          
{'loss': 0.6406, 'learning_rate': 0.00038195038120155403, 'epoch': 4.12}

 34%|███▍      | 9641/28080 [19:03:20<36:23:05,  7.10s/it]
 34%|███▍      | 9642/28080 [19:03:27<36:28:04,  7.12s/it]
                                                          
{'loss': 0.636, 'learning_rate': 0.00038192588820434593, 'epoch': 4.12}

 34%|███▍      | 9642/28080 [19:03:27<36:28:04,  7.12s/it]
 34%|███▍      | 9643/28080 [19:03:34<36:28:25,  7.12s/it]
                                                          
{'loss': 0.6182, 'learning_rate': 0.0003819013934520001, 'epoch': 4.12}

 34%|███▍      | 9643/28080 [19:03:34<36:28:25,  7.12s/it]
 34%|███▍      | 9644/28080 [19:03:41<36:21:19,  7.10s/it]
                                                          
{'loss': 0.6173, 'learning_rate': 0.00038187689694484236, 'epoch': 4.12}

 34%|███▍      | 9644/28080 [19:03:41<36:21:19,  7.10s/it]
 34%|███▍      | 9645/28080 [19:03:48<36:33:44,  7.14s/it]
                                                          
{'loss': 0.6087, 'learning_rate': 0.00038185239868319845, 'epoch': 4.12}

 34%|███▍      | 9645/28080 [19:03:48<36:33:44,  7.14s/it]
 34%|███▍      | 9646/28080 [19:03:56<36:42:41,  7.17s/it]
                                                          
{'loss': 0.5992, 'learning_rate': 0.0003818278986673944, 'epoch': 4.12}

 34%|███▍      | 9646/28080 [19:03:56<36:42:41,  7.17s/it]
 34%|███▍      | 9647/28080 [19:04:03<36:36:18,  7.15s/it]
                                                          
{'loss': 0.6249, 'learning_rate': 0.0003818033968977562, 'epoch': 4.12}

 34%|███▍      | 9647/28080 [19:04:03<36:36:18,  7.15s/it]
 34%|███▍      | 9648/28080 [19:04:10<36:35:29,  7.15s/it]
                                                          
{'loss': 0.6321, 'learning_rate': 0.0003817788933746098, 'epoch': 4.12}

 34%|███▍      | 9648/28080 [19:04:10<36:35:29,  7.15s/it]
 34%|███▍      | 9649/28080 [19:04:17<36:31:52,  7.14s/it]
                                                          
{'loss': 0.6387, 'learning_rate': 0.0003817543880982811, 'epoch': 4.12}

 34%|███▍      | 9649/28080 [19:04:17<36:31:52,  7.14s/it]
 34%|███▍      | 9650/28080 [19:04:24<36:29:33,  7.13s/it]
                                                          
{'loss': 0.6346, 'learning_rate': 0.00038172988106909624, 'epoch': 4.12}

 34%|███▍      | 9650/28080 [19:04:24<36:29:33,  7.13s/it]
 34%|███▍      | 9651/28080 [19:04:31<36:31:44,  7.14s/it]
                                                          
{'loss': 0.6323, 'learning_rate': 0.00038170537228738124, 'epoch': 4.12}

 34%|███▍      | 9651/28080 [19:04:31<36:31:44,  7.14s/it]
 34%|███▍      | 9652/28080 [19:04:38<36:31:45,  7.14s/it]
                                                          
{'loss': 0.655, 'learning_rate': 0.00038168086175346206, 'epoch': 4.12}

 34%|███▍      | 9652/28080 [19:04:38<36:31:45,  7.14s/it]
 34%|███▍      | 9653/28080 [19:04:45<36:35:38,  7.15s/it]
                                                          
{'loss': 0.6323, 'learning_rate': 0.0003816563494676649, 'epoch': 4.12}

 34%|███▍      | 9653/28080 [19:04:45<36:35:38,  7.15s/it]
 34%|███▍      | 9654/28080 [19:04:53<36:39:41,  7.16s/it]
                                                          
{'loss': 0.6442, 'learning_rate': 0.00038163183543031586, 'epoch': 4.12}

 34%|███▍      | 9654/28080 [19:04:53<36:39:41,  7.16s/it]
 34%|███▍      | 9655/28080 [19:05:00<36:41:50,  7.17s/it]
                                                          
{'loss': 0.6061, 'learning_rate': 0.000381607319641741, 'epoch': 4.12}

 34%|███▍      | 9655/28080 [19:05:00<36:41:50,  7.17s/it]
 34%|███▍      | 9656/28080 [19:05:07<36:29:10,  7.13s/it]
                                                          
{'loss': 0.6232, 'learning_rate': 0.0003815828021022666, 'epoch': 4.12}

 34%|███▍      | 9656/28080 [19:05:07<36:29:10,  7.13s/it]
 34%|███▍      | 9657/28080 [19:05:14<36:23:44,  7.11s/it]
                                                          
{'loss': 0.6441, 'learning_rate': 0.0003815582828122186, 'epoch': 4.13}

 34%|███▍      | 9657/28080 [19:05:14<36:23:44,  7.11s/it]
 34%|███▍      | 9658/28080 [19:05:21<36:28:55,  7.13s/it]
                                                          
{'loss': 0.6437, 'learning_rate': 0.00038153376177192357, 'epoch': 4.13}

 34%|███▍      | 9658/28080 [19:05:21<36:28:55,  7.13s/it]
 34%|███▍      | 9659/28080 [19:05:28<36:37:34,  7.16s/it]
                                                          
{'loss': 0.6287, 'learning_rate': 0.0003815092389817074, 'epoch': 4.13}

 34%|███▍      | 9659/28080 [19:05:28<36:37:34,  7.16s/it]
 34%|███▍      | 9660/28080 [19:05:36<36:40:25,  7.17s/it]
                                                          
{'loss': 0.6172, 'learning_rate': 0.0003814847144418965, 'epoch': 4.13}

 34%|███▍      | 9660/28080 [19:05:36<36:40:25,  7.17s/it]
 34%|███▍      | 9661/28080 [19:05:43<36:37:41,  7.16s/it]
                                                          
{'loss': 0.6282, 'learning_rate': 0.00038146018815281714, 'epoch': 4.13}

 34%|███▍      | 9661/28080 [19:05:43<36:37:41,  7.16s/it]
 34%|███▍      | 9662/28080 [19:05:50<36:24:48,  7.12s/it]
                                                          
{'loss': 0.6241, 'learning_rate': 0.00038143566011479557, 'epoch': 4.13}

 34%|███▍      | 9662/28080 [19:05:50<36:24:48,  7.12s/it]
 34%|███▍      | 9663/28080 [19:05:57<36:30:02,  7.13s/it]
                                                          
{'loss': 0.6556, 'learning_rate': 0.0003814111303281582, 'epoch': 4.13}

 34%|███▍      | 9663/28080 [19:05:57<36:30:02,  7.13s/it]
 34%|███▍      | 9664/28080 [19:06:04<36:33:24,  7.15s/it]
                                                          
{'loss': 0.637, 'learning_rate': 0.00038138659879323125, 'epoch': 4.13}

 34%|███▍      | 9664/28080 [19:06:04<36:33:24,  7.15s/it]
 34%|███▍      | 9665/28080 [19:06:11<36:45:07,  7.18s/it]
                                                          
{'loss': 0.6249, 'learning_rate': 0.0003813620655103412, 'epoch': 4.13}

 34%|███▍      | 9665/28080 [19:06:11<36:45:07,  7.18s/it]
 34%|███▍      | 9666/28080 [19:06:18<36:38:51,  7.16s/it]
                                                          
{'loss': 0.6124, 'learning_rate': 0.00038133753047981436, 'epoch': 4.13}

 34%|███▍      | 9666/28080 [19:06:18<36:38:51,  7.16s/it]
 34%|███▍      | 9667/28080 [19:06:26<36:44:25,  7.18s/it]
                                                          
{'loss': 0.6155, 'learning_rate': 0.0003813129937019771, 'epoch': 4.13}

 34%|███▍      | 9667/28080 [19:06:26<36:44:25,  7.18s/it]
 34%|███▍      | 9668/28080 [19:06:33<36:48:13,  7.20s/it]
                                                          
{'loss': 0.6144, 'learning_rate': 0.00038128845517715603, 'epoch': 4.13}

 34%|███▍      | 9668/28080 [19:06:33<36:48:13,  7.20s/it]
 34%|███▍      | 9669/28080 [19:06:40<36:51:42,  7.21s/it]
                                                          
{'loss': 0.6104, 'learning_rate': 0.0003812639149056775, 'epoch': 4.13}

 34%|███▍      | 9669/28080 [19:06:40<36:51:42,  7.21s/it]
 34%|███▍      | 9670/28080 [19:06:47<36:36:07,  7.16s/it]
                                                          
{'loss': 0.6293, 'learning_rate': 0.00038123937288786795, 'epoch': 4.13}

 34%|███▍      | 9670/28080 [19:06:47<36:36:07,  7.16s/it]
 34%|███▍      | 9671/28080 [19:06:54<36:21:55,  7.11s/it]
                                                          
{'loss': 0.6301, 'learning_rate': 0.00038121482912405397, 'epoch': 4.13}

 34%|███▍      | 9671/28080 [19:06:54<36:21:55,  7.11s/it]
 34%|███▍      | 9672/28080 [19:07:01<36:25:39,  7.12s/it]
                                                          
{'loss': 0.6234, 'learning_rate': 0.0003811902836145621, 'epoch': 4.13}

 34%|███▍      | 9672/28080 [19:07:01<36:25:39,  7.12s/it]
 34%|███▍      | 9673/28080 [19:07:08<36:30:22,  7.14s/it]
                                                          
{'loss': 0.6554, 'learning_rate': 0.00038116573635971874, 'epoch': 4.13}

 34%|███▍      | 9673/28080 [19:07:09<36:30:22,  7.14s/it]
 34%|███▍      | 9674/28080 [19:07:16<36:30:01,  7.14s/it]
                                                          
{'loss': 0.6305, 'learning_rate': 0.0003811411873598506, 'epoch': 4.13}

 34%|███▍      | 9674/28080 [19:07:16<36:30:01,  7.14s/it]
 34%|███▍      | 9675/28080 [19:07:23<36:16:21,  7.09s/it]
                                                          
{'loss': 0.6436, 'learning_rate': 0.0003811166366152843, 'epoch': 4.13}

 34%|███▍      | 9675/28080 [19:07:23<36:16:21,  7.09s/it]
 34%|███▍      | 9676/28080 [19:07:30<36:22:01,  7.11s/it]
                                                          
{'loss': 0.6271, 'learning_rate': 0.00038109208412634633, 'epoch': 4.13}

 34%|███▍      | 9676/28080 [19:07:30<36:22:01,  7.11s/it]
 34%|███▍      | 9677/28080 [19:07:37<36:21:41,  7.11s/it]
                                                          
{'loss': 0.6396, 'learning_rate': 0.0003810675298933636, 'epoch': 4.13}

 34%|███▍      | 9677/28080 [19:07:37<36:21:41,  7.11s/it]
 34%|███▍      | 9678/28080 [19:07:44<36:24:32,  7.12s/it]
                                                          
{'loss': 0.6171, 'learning_rate': 0.00038104297391666243, 'epoch': 4.13}

 34%|███▍      | 9678/28080 [19:07:44<36:24:32,  7.12s/it]
 34%|███▍      | 9679/28080 [19:07:51<36:21:24,  7.11s/it]
                                                          
{'loss': 0.6368, 'learning_rate': 0.00038101841619656967, 'epoch': 4.13}

 34%|███▍      | 9679/28080 [19:07:51<36:21:24,  7.11s/it]
 34%|███▍      | 9680/28080 [19:07:58<36:26:05,  7.13s/it]
                                                          
{'loss': 0.6323, 'learning_rate': 0.0003809938567334121, 'epoch': 4.14}

 34%|███▍      | 9680/28080 [19:07:58<36:26:05,  7.13s/it]
 34%|███▍      | 9681/28080 [19:08:05<36:21:23,  7.11s/it]
                                                          
{'loss': 0.6288, 'learning_rate': 0.0003809692955275164, 'epoch': 4.14}

 34%|███▍      | 9681/28080 [19:08:05<36:21:23,  7.11s/it]
 34%|███▍      | 9682/28080 [19:08:13<36:27:15,  7.13s/it]
                                                          
{'loss': 0.6315, 'learning_rate': 0.00038094473257920935, 'epoch': 4.14}

 34%|███▍      | 9682/28080 [19:08:13<36:27:15,  7.13s/it]
 34%|███▍      | 9683/28080 [19:08:20<36:36:00,  7.16s/it]
                                                          
{'loss': 0.6194, 'learning_rate': 0.0003809201678888178, 'epoch': 4.14}

 34%|███▍      | 9683/28080 [19:08:20<36:36:00,  7.16s/it]
 34%|███▍      | 9684/28080 [19:08:27<36:33:07,  7.15s/it]
                                                          
{'loss': 0.6369, 'learning_rate': 0.00038089560145666834, 'epoch': 4.14}

 34%|███▍      | 9684/28080 [19:08:27<36:33:07,  7.15s/it]
 34%|███▍      | 9685/28080 [19:08:34<36:33:47,  7.16s/it]
                                                          
{'loss': 0.632, 'learning_rate': 0.00038087103328308806, 'epoch': 4.14}

 34%|███▍      | 9685/28080 [19:08:34<36:33:47,  7.16s/it]
 34%|███▍      | 9686/28080 [19:08:41<36:34:56,  7.16s/it]
                                                          
{'loss': 0.657, 'learning_rate': 0.00038084646336840355, 'epoch': 4.14}

 34%|███▍      | 9686/28080 [19:08:41<36:34:56,  7.16s/it]
 34%|███▍      | 9687/28080 [19:08:48<36:43:18,  7.19s/it]
                                                          
{'loss': 0.6365, 'learning_rate': 0.000380821891712942, 'epoch': 4.14}

 34%|███▍      | 9687/28080 [19:08:48<36:43:18,  7.19s/it]
 35%|███▍      | 9688/28080 [19:08:56<36:27:47,  7.14s/it]
                                                          
{'loss': 0.6007, 'learning_rate': 0.00038079731831703, 'epoch': 4.14}

 35%|███▍      | 9688/28080 [19:08:56<36:27:47,  7.14s/it]
 35%|███▍      | 9689/28080 [19:09:03<36:26:07,  7.13s/it]
                                                          
{'loss': 0.6196, 'learning_rate': 0.0003807727431809947, 'epoch': 4.14}

 35%|███▍      | 9689/28080 [19:09:03<36:26:07,  7.13s/it]
 35%|███▍      | 9690/28080 [19:09:10<36:21:08,  7.12s/it]
                                                          
{'loss': 0.6341, 'learning_rate': 0.0003807481663051629, 'epoch': 4.14}

 35%|███▍      | 9690/28080 [19:09:10<36:21:08,  7.12s/it]
 35%|███▍      | 9691/28080 [19:09:17<36:18:21,  7.11s/it]
                                                          
{'loss': 0.6396, 'learning_rate': 0.0003807235876898617, 'epoch': 4.14}

 35%|███▍      | 9691/28080 [19:09:17<36:18:21,  7.11s/it]
 35%|███▍      | 9692/28080 [19:09:24<36:26:30,  7.13s/it]
                                                          
{'loss': 0.6306, 'learning_rate': 0.00038069900733541794, 'epoch': 4.14}

 35%|███▍      | 9692/28080 [19:09:24<36:26:30,  7.13s/it]
 35%|███▍      | 9693/28080 [19:09:31<36:25:51,  7.13s/it]
                                                          
{'loss': 0.6346, 'learning_rate': 0.00038067442524215877, 'epoch': 4.14}

 35%|███▍      | 9693/28080 [19:09:31<36:25:51,  7.13s/it]
 35%|███▍      | 9694/28080 [19:09:38<36:14:58,  7.10s/it]
                                                          
{'loss': 0.6546, 'learning_rate': 0.0003806498414104113, 'epoch': 4.14}

 35%|███▍      | 9694/28080 [19:09:38<36:14:58,  7.10s/it]
 35%|███▍      | 9695/28080 [19:09:45<36:15:37,  7.10s/it]
                                                          
{'loss': 0.6224, 'learning_rate': 0.0003806252558405023, 'epoch': 4.14}

 35%|███▍      | 9695/28080 [19:09:45<36:15:37,  7.10s/it]
 35%|███▍      | 9696/28080 [19:09:52<36:19:43,  7.11s/it]
                                                          
{'loss': 0.6377, 'learning_rate': 0.00038060066853275914, 'epoch': 4.14}

 35%|███▍      | 9696/28080 [19:09:52<36:19:43,  7.11s/it]
 35%|███▍      | 9697/28080 [19:09:59<36:19:07,  7.11s/it]
                                                          
{'loss': 0.6458, 'learning_rate': 0.00038057607948750873, 'epoch': 4.14}

 35%|███▍      | 9697/28080 [19:10:00<36:19:07,  7.11s/it]
 35%|███▍      | 9698/28080 [19:10:07<36:20:23,  7.12s/it]
                                                          
{'loss': 0.6377, 'learning_rate': 0.00038055148870507833, 'epoch': 4.14}

 35%|███▍      | 9698/28080 [19:10:07<36:20:23,  7.12s/it]
 35%|███▍      | 9699/28080 [19:10:14<36:25:20,  7.13s/it]
                                                          
{'loss': 0.6471, 'learning_rate': 0.00038052689618579507, 'epoch': 4.14}

 35%|███▍      | 9699/28080 [19:10:14<36:25:20,  7.13s/it]
 35%|███▍      | 9700/28080 [19:10:21<36:23:08,  7.13s/it]
                                                          
{'loss': 0.6487, 'learning_rate': 0.0003805023019299861, 'epoch': 4.14}

 35%|███▍      | 9700/28080 [19:10:21<36:23:08,  7.13s/it]
 35%|███▍      | 9701/28080 [19:10:28<36:17:20,  7.11s/it]
                                                          
{'loss': 0.6194, 'learning_rate': 0.00038047770593797864, 'epoch': 4.14}

 35%|███▍      | 9701/28080 [19:10:28<36:17:20,  7.11s/it]
 35%|███▍      | 9702/28080 [19:10:35<36:23:36,  7.13s/it]
                                                          
{'loss': 0.6522, 'learning_rate': 0.00038045310821009995, 'epoch': 4.14}

 35%|███▍      | 9702/28080 [19:10:35<36:23:36,  7.13s/it]
 35%|███▍      | 9703/28080 [19:10:42<36:18:30,  7.11s/it]
                                                          
{'loss': 0.6337, 'learning_rate': 0.00038042850874667715, 'epoch': 4.15}

 35%|███▍      | 9703/28080 [19:10:42<36:18:30,  7.11s/it]
 35%|███▍      | 9704/28080 [19:10:49<36:20:50,  7.12s/it]
                                                          
{'loss': 0.6302, 'learning_rate': 0.00038040390754803767, 'epoch': 4.15}

 35%|███▍      | 9704/28080 [19:10:49<36:20:50,  7.12s/it]
 35%|███▍      | 9705/28080 [19:10:57<36:22:56,  7.13s/it]
                                                          
{'loss': 0.6285, 'learning_rate': 0.00038037930461450866, 'epoch': 4.15}

 35%|███▍      | 9705/28080 [19:10:57<36:22:56,  7.13s/it]
 35%|███▍      | 9706/28080 [19:11:04<36:15:11,  7.10s/it]
                                                          
{'loss': 0.6153, 'learning_rate': 0.00038035469994641757, 'epoch': 4.15}

 35%|███▍      | 9706/28080 [19:11:04<36:15:11,  7.10s/it]
 35%|███▍      | 9707/28080 [19:11:11<36:32:08,  7.16s/it]
                                                          
{'loss': 0.6383, 'learning_rate': 0.0003803300935440916, 'epoch': 4.15}

 35%|███▍      | 9707/28080 [19:11:11<36:32:08,  7.16s/it]
 35%|███▍      | 9708/28080 [19:11:18<36:25:32,  7.14s/it]
                                                          
{'loss': 0.6174, 'learning_rate': 0.0003803054854078583, 'epoch': 4.15}

 35%|███▍      | 9708/28080 [19:11:18<36:25:32,  7.14s/it]
 35%|███▍      | 9709/28080 [19:11:25<36:23:56,  7.13s/it]
                                                          
{'loss': 0.6191, 'learning_rate': 0.0003802808755380448, 'epoch': 4.15}

 35%|███▍      | 9709/28080 [19:11:25<36:23:56,  7.13s/it]
 35%|███▍      | 9710/28080 [19:11:32<36:24:05,  7.13s/it]
                                                          
{'loss': 0.6216, 'learning_rate': 0.00038025626393497873, 'epoch': 4.15}

 35%|███▍      | 9710/28080 [19:11:32<36:24:05,  7.13s/it]
 35%|███▍      | 9711/28080 [19:11:39<36:16:27,  7.11s/it]
                                                          
{'loss': 0.6249, 'learning_rate': 0.0003802316505989875, 'epoch': 4.15}

 35%|███▍      | 9711/28080 [19:11:39<36:16:27,  7.11s/it]
 35%|███▍      | 9712/28080 [19:11:46<36:19:24,  7.12s/it]
                                                          
{'loss': 0.6574, 'learning_rate': 0.0003802070355303985, 'epoch': 4.15}

 35%|███▍      | 9712/28080 [19:11:46<36:19:24,  7.12s/it]
 35%|███▍      | 9713/28080 [19:11:54<36:21:35,  7.13s/it]
                                                          
{'loss': 0.6262, 'learning_rate': 0.0003801824187295392, 'epoch': 4.15}

 35%|███▍      | 9713/28080 [19:11:54<36:21:35,  7.13s/it]
 35%|███▍      | 9714/28080 [19:12:01<36:23:38,  7.13s/it]
                                                          
{'loss': 0.6399, 'learning_rate': 0.00038015780019673705, 'epoch': 4.15}

 35%|███▍      | 9714/28080 [19:12:01<36:23:38,  7.13s/it]
 35%|███▍      | 9715/28080 [19:12:08<36:18:06,  7.12s/it]
                                                          
{'loss': 0.603, 'learning_rate': 0.0003801331799323197, 'epoch': 4.15}

 35%|███▍      | 9715/28080 [19:12:08<36:18:06,  7.12s/it]
 35%|███▍      | 9716/28080 [19:12:15<36:21:42,  7.13s/it]
                                                          
{'loss': 0.6291, 'learning_rate': 0.00038010855793661465, 'epoch': 4.15}

 35%|███▍      | 9716/28080 [19:12:15<36:21:42,  7.13s/it]
 35%|███▍      | 9717/28080 [19:12:22<36:20:24,  7.12s/it]
                                                          
{'loss': 0.6436, 'learning_rate': 0.00038008393420994944, 'epoch': 4.15}

 35%|███▍      | 9717/28080 [19:12:22<36:20:24,  7.12s/it]
 35%|███▍      | 9718/28080 [19:12:29<36:20:49,  7.13s/it]
                                                          
{'loss': 0.6352, 'learning_rate': 0.00038005930875265173, 'epoch': 4.15}

 35%|███▍      | 9718/28080 [19:12:29<36:20:49,  7.13s/it]
 35%|███▍      | 9719/28080 [19:12:36<36:26:04,  7.14s/it]
                                                          
{'loss': 0.6327, 'learning_rate': 0.00038003468156504904, 'epoch': 4.15}

 35%|███▍      | 9719/28080 [19:12:36<36:26:04,  7.14s/it]
 35%|███▍      | 9720/28080 [19:12:44<36:37:29,  7.18s/it]
                                                          
{'loss': 0.6349, 'learning_rate': 0.00038001005264746914, 'epoch': 4.15}

 35%|███▍      | 9720/28080 [19:12:44<36:37:29,  7.18s/it]
 35%|███▍      | 9721/28080 [19:12:51<36:45:52,  7.21s/it]
                                                          
{'loss': 0.626, 'learning_rate': 0.00037998542200023955, 'epoch': 4.15}

 35%|███▍      | 9721/28080 [19:12:51<36:45:52,  7.21s/it]
 35%|███▍      | 9722/28080 [19:12:58<36:40:52,  7.19s/it]
                                                          
{'loss': 0.626, 'learning_rate': 0.000379960789623688, 'epoch': 4.15}

 35%|███▍      | 9722/28080 [19:12:58<36:40:52,  7.19s/it]
 35%|███▍      | 9723/28080 [19:13:05<36:33:33,  7.17s/it]
                                                          
{'loss': 0.6581, 'learning_rate': 0.00037993615551814224, 'epoch': 4.15}

 35%|███▍      | 9723/28080 [19:13:05<36:33:33,  7.17s/it]
 35%|███▍      | 9724/28080 [19:13:12<36:28:43,  7.15s/it]
                                                          
{'loss': 0.6447, 'learning_rate': 0.00037991151968393003, 'epoch': 4.15}

 35%|███▍      | 9724/28080 [19:13:12<36:28:43,  7.15s/it]
 35%|███▍      | 9725/28080 [19:13:20<36:36:08,  7.18s/it]
                                                          
{'loss': 0.6265, 'learning_rate': 0.000379886882121379, 'epoch': 4.15}

 35%|███▍      | 9725/28080 [19:13:20<36:36:08,  7.18s/it]
 35%|███▍      | 9726/28080 [19:13:27<36:30:13,  7.16s/it]
                                                          
{'loss': 0.6209, 'learning_rate': 0.000379862242830817, 'epoch': 4.15}

 35%|███▍      | 9726/28080 [19:13:27<36:30:13,  7.16s/it]
 35%|███▍      | 9727/28080 [19:13:34<36:24:42,  7.14s/it]
                                                          
{'loss': 0.6216, 'learning_rate': 0.0003798376018125719, 'epoch': 4.16}

 35%|███▍      | 9727/28080 [19:13:34<36:24:42,  7.14s/it]
 35%|███▍      | 9728/28080 [19:13:41<36:30:34,  7.16s/it]
                                                          
{'loss': 0.6119, 'learning_rate': 0.0003798129590669714, 'epoch': 4.16}

 35%|███▍      | 9728/28080 [19:13:41<36:30:34,  7.16s/it]
 35%|███▍      | 9729/28080 [19:13:48<36:29:02,  7.16s/it]
                                                          
{'loss': 0.6166, 'learning_rate': 0.00037978831459434335, 'epoch': 4.16}

 35%|███▍      | 9729/28080 [19:13:48<36:29:02,  7.16s/it]
 35%|███▍      | 9730/28080 [19:13:55<36:41:39,  7.20s/it]
                                                          
{'loss': 0.6319, 'learning_rate': 0.00037976366839501574, 'epoch': 4.16}

 35%|███▍      | 9730/28080 [19:13:55<36:41:39,  7.20s/it]
 35%|███▍      | 9731/28080 [19:14:03<36:44:43,  7.21s/it]
                                                          
{'loss': 0.6316, 'learning_rate': 0.00037973902046931643, 'epoch': 4.16}

 35%|███▍      | 9731/28080 [19:14:03<36:44:43,  7.21s/it]
 35%|███▍      | 9732/28080 [19:14:10<36:39:51,  7.19s/it]
                                                          
{'loss': 0.6525, 'learning_rate': 0.0003797143708175732, 'epoch': 4.16}

 35%|███▍      | 9732/28080 [19:14:10<36:39:51,  7.19s/it]
 35%|███▍      | 9733/28080 [19:14:17<36:31:49,  7.17s/it]
                                                          
{'loss': 0.6269, 'learning_rate': 0.00037968971944011415, 'epoch': 4.16}

 35%|███▍      | 9733/28080 [19:14:17<36:31:49,  7.17s/it]
 35%|███▍      | 9734/28080 [19:14:24<36:31:42,  7.17s/it]
                                                          
{'loss': 0.6211, 'learning_rate': 0.00037966506633726717, 'epoch': 4.16}

 35%|███▍      | 9734/28080 [19:14:24<36:31:42,  7.17s/it]
 35%|███▍      | 9735/28080 [19:14:31<36:12:48,  7.11s/it]
                                                          
{'loss': 0.6468, 'learning_rate': 0.0003796404115093602, 'epoch': 4.16}

 35%|███▍      | 9735/28080 [19:14:31<36:12:48,  7.11s/it]
 35%|███▍      | 9736/28080 [19:14:38<36:09:10,  7.09s/it]
                                                          
{'loss': 0.6223, 'learning_rate': 0.00037961575495672136, 'epoch': 4.16}

 35%|███▍      | 9736/28080 [19:14:38<36:09:10,  7.09s/it]
 35%|███▍      | 9737/28080 [19:14:45<36:16:32,  7.12s/it]
                                                          
{'loss': 0.6184, 'learning_rate': 0.0003795910966796786, 'epoch': 4.16}

 35%|███▍      | 9737/28080 [19:14:45<36:16:32,  7.12s/it]
 35%|███▍      | 9738/28080 [19:14:52<36:18:06,  7.12s/it]
                                                          
{'loss': 0.6288, 'learning_rate': 0.0003795664366785599, 'epoch': 4.16}

 35%|███▍      | 9738/28080 [19:14:52<36:18:06,  7.12s/it]
 35%|███▍      | 9739/28080 [19:14:59<36:13:09,  7.11s/it]
                                                          
{'loss': 0.6326, 'learning_rate': 0.00037954177495369356, 'epoch': 4.16}

 35%|███▍      | 9739/28080 [19:14:59<36:13:09,  7.11s/it]
 35%|███▍      | 9740/28080 [19:15:07<36:16:53,  7.12s/it]
                                                          
{'loss': 0.6098, 'learning_rate': 0.0003795171115054075, 'epoch': 4.16}

 35%|███▍      | 9740/28080 [19:15:07<36:16:53,  7.12s/it]
 35%|███▍      | 9741/28080 [19:15:14<36:18:02,  7.13s/it]
                                                          
{'loss': 0.6156, 'learning_rate': 0.0003794924463340299, 'epoch': 4.16}

 35%|███▍      | 9741/28080 [19:15:14<36:18:02,  7.13s/it]
 35%|███▍      | 9742/28080 [19:15:21<36:26:19,  7.15s/it]
                                                          
{'loss': 0.6108, 'learning_rate': 0.00037946777943988886, 'epoch': 4.16}

 35%|███▍      | 9742/28080 [19:15:21<36:26:19,  7.15s/it]
 35%|███▍      | 9743/28080 [19:15:28<36:15:40,  7.12s/it]
                                                          
{'loss': 0.6131, 'learning_rate': 0.00037944311082331264, 'epoch': 4.16}

 35%|███▍      | 9743/28080 [19:15:28<36:15:40,  7.12s/it]
 35%|███▍      | 9744/28080 [19:15:35<36:22:27,  7.14s/it]
                                                          
{'loss': 0.6202, 'learning_rate': 0.00037941844048462937, 'epoch': 4.16}

 35%|███▍      | 9744/28080 [19:15:35<36:22:27,  7.14s/it]
 35%|███▍      | 9745/28080 [19:15:42<36:22:41,  7.14s/it]
                                                          
{'loss': 0.6247, 'learning_rate': 0.0003793937684241672, 'epoch': 4.16}

 35%|███▍      | 9745/28080 [19:15:42<36:22:41,  7.14s/it]
 35%|███▍      | 9746/28080 [19:15:49<36:21:17,  7.14s/it]
                                                          
{'loss': 0.6542, 'learning_rate': 0.0003793690946422544, 'epoch': 4.16}

 35%|███▍      | 9746/28080 [19:15:49<36:21:17,  7.14s/it]
 35%|███▍      | 9747/28080 [19:15:57<36:19:22,  7.13s/it]
                                                          
{'loss': 0.6293, 'learning_rate': 0.00037934441913921936, 'epoch': 4.16}

 35%|███▍      | 9747/28080 [19:15:57<36:19:22,  7.13s/it]
 35%|███▍      | 9748/28080 [19:16:04<36:17:51,  7.13s/it]
                                                          
{'loss': 0.6385, 'learning_rate': 0.00037931974191539016, 'epoch': 4.16}

 35%|███▍      | 9748/28080 [19:16:04<36:17:51,  7.13s/it]
 35%|███▍      | 9749/28080 [19:16:11<36:21:19,  7.14s/it]
                                                          
{'loss': 0.6359, 'learning_rate': 0.0003792950629710953, 'epoch': 4.16}

 35%|███▍      | 9749/28080 [19:16:11<36:21:19,  7.14s/it]
 35%|███▍      | 9750/28080 [19:16:18<36:18:58,  7.13s/it]
                                                          
{'loss': 0.6435, 'learning_rate': 0.0003792703823066629, 'epoch': 4.17}

 35%|███▍      | 9750/28080 [19:16:18<36:18:58,  7.13s/it]
 35%|███▍      | 9751/28080 [19:16:25<36:16:45,  7.13s/it]
                                                          
{'loss': 0.6431, 'learning_rate': 0.0003792456999224215, 'epoch': 4.17}

 35%|███▍      | 9751/28080 [19:16:25<36:16:45,  7.13s/it]
 35%|███▍      | 9752/28080 [19:16:32<36:10:21,  7.11s/it]
                                                          
{'loss': 0.6745, 'learning_rate': 0.0003792210158186994, 'epoch': 4.17}

 35%|███▍      | 9752/28080 [19:16:32<36:10:21,  7.11s/it]
 35%|███▍      | 9753/28080 [19:16:39<36:02:55,  7.08s/it]
                                                          
{'loss': 0.6248, 'learning_rate': 0.00037919632999582493, 'epoch': 4.17}

 35%|███▍      | 9753/28080 [19:16:39<36:02:55,  7.08s/it]
 35%|███▍      | 9754/28080 [19:16:46<36:05:37,  7.09s/it]
                                                          
{'loss': 0.637, 'learning_rate': 0.00037917164245412666, 'epoch': 4.17}

 35%|███▍      | 9754/28080 [19:16:46<36:05:37,  7.09s/it]
 35%|███▍      | 9755/28080 [19:16:53<36:01:35,  7.08s/it]
                                                          
{'loss': 0.6336, 'learning_rate': 0.0003791469531939329, 'epoch': 4.17}

 35%|███▍      | 9755/28080 [19:16:53<36:01:35,  7.08s/it]
 35%|███▍      | 9756/28080 [19:17:00<36:06:47,  7.09s/it]
                                                          
{'loss': 0.6364, 'learning_rate': 0.00037912226221557225, 'epoch': 4.17}

 35%|███▍      | 9756/28080 [19:17:00<36:06:47,  7.09s/it]
 35%|███▍      | 9757/28080 [19:17:08<36:07:27,  7.10s/it]
                                                          
{'loss': 0.6454, 'learning_rate': 0.0003790975695193729, 'epoch': 4.17}

 35%|███▍      | 9757/28080 [19:17:08<36:07:27,  7.10s/it]
 35%|███▍      | 9758/28080 [19:17:15<36:03:05,  7.08s/it]
                                                          
{'loss': 0.6488, 'learning_rate': 0.0003790728751056638, 'epoch': 4.17}

 35%|███▍      | 9758/28080 [19:17:15<36:03:05,  7.08s/it]
 35%|███▍      | 9759/28080 [19:17:22<36:06:53,  7.10s/it]
                                                          
{'loss': 0.6462, 'learning_rate': 0.0003790481789747731, 'epoch': 4.17}

 35%|███▍      | 9759/28080 [19:17:22<36:06:53,  7.10s/it]
 35%|███▍      | 9760/28080 [19:17:29<36:08:13,  7.10s/it]
                                                          
{'loss': 0.6331, 'learning_rate': 0.0003790234811270296, 'epoch': 4.17}

 35%|███▍      | 9760/28080 [19:17:29<36:08:13,  7.10s/it]
 35%|███▍      | 9761/28080 [19:17:36<36:20:54,  7.14s/it]
                                                          
{'loss': 0.6341, 'learning_rate': 0.0003789987815627617, 'epoch': 4.17}

 35%|███▍      | 9761/28080 [19:17:36<36:20:54,  7.14s/it]
 35%|███▍      | 9762/28080 [19:17:43<36:25:20,  7.16s/it]
                                                          
{'loss': 0.6453, 'learning_rate': 0.0003789740802822982, 'epoch': 4.17}

 35%|███▍      | 9762/28080 [19:17:43<36:25:20,  7.16s/it]
 35%|███▍      | 9763/28080 [19:17:50<36:24:34,  7.16s/it]
                                                          
{'loss': 0.6419, 'learning_rate': 0.00037894937728596756, 'epoch': 4.17}

 35%|███▍      | 9763/28080 [19:17:50<36:24:34,  7.16s/it]
 35%|███▍      | 9764/28080 [19:17:58<36:27:00,  7.16s/it]
                                                          
{'loss': 0.6279, 'learning_rate': 0.00037892467257409846, 'epoch': 4.17}

 35%|███▍      | 9764/28080 [19:17:58<36:27:00,  7.16s/it]
 35%|███▍      | 9765/28080 [19:18:05<36:25:10,  7.16s/it]
                                                          
{'loss': 0.6333, 'learning_rate': 0.0003788999661470196, 'epoch': 4.17}

 35%|███▍      | 9765/28080 [19:18:05<36:25:10,  7.16s/it]
 35%|███▍      | 9766/28080 [19:18:12<36:22:13,  7.15s/it]
                                                          
{'loss': 0.6255, 'learning_rate': 0.00037887525800505973, 'epoch': 4.17}

 35%|███▍      | 9766/28080 [19:18:12<36:22:13,  7.15s/it]
 35%|███▍      | 9767/28080 [19:18:19<36:15:24,  7.13s/it]
                                                          
{'loss': 0.6325, 'learning_rate': 0.0003788505481485474, 'epoch': 4.17}

 35%|███▍      | 9767/28080 [19:18:19<36:15:24,  7.13s/it]
 35%|███▍      | 9768/28080 [19:18:26<36:12:06,  7.12s/it]
                                                          
{'loss': 0.6538, 'learning_rate': 0.00037882583657781153, 'epoch': 4.17}

 35%|███▍      | 9768/28080 [19:18:26<36:12:06,  7.12s/it]
 35%|███▍      | 9769/28080 [19:18:33<36:03:46,  7.09s/it]
                                                          
{'loss': 0.6349, 'learning_rate': 0.00037880112329318085, 'epoch': 4.17}

 35%|███▍      | 9769/28080 [19:18:33<36:03:46,  7.09s/it]
 35%|███▍      | 9770/28080 [19:18:40<36:00:17,  7.08s/it]
                                                          
{'loss': 0.6389, 'learning_rate': 0.0003787764082949841, 'epoch': 4.17}

 35%|███▍      | 9770/28080 [19:18:40<36:00:17,  7.08s/it]
 35%|███▍      | 9771/28080 [19:18:47<36:07:44,  7.10s/it]
                                                          
{'loss': 0.6302, 'learning_rate': 0.00037875169158355006, 'epoch': 4.17}

 35%|███▍      | 9771/28080 [19:18:47<36:07:44,  7.10s/it]
 35%|███▍      | 9772/28080 [19:18:54<36:12:27,  7.12s/it]
                                                          
{'loss': 0.6431, 'learning_rate': 0.00037872697315920753, 'epoch': 4.17}

 35%|███▍      | 9772/28080 [19:18:54<36:12:27,  7.12s/it]
 35%|███▍      | 9773/28080 [19:19:02<36:12:24,  7.12s/it]
                                                          
{'loss': 0.6212, 'learning_rate': 0.00037870225302228544, 'epoch': 4.17}

 35%|███▍      | 9773/28080 [19:19:02<36:12:24,  7.12s/it]
 35%|███▍      | 9774/28080 [19:19:09<36:14:54,  7.13s/it]
                                                          
{'loss': 0.6203, 'learning_rate': 0.00037867753117311266, 'epoch': 4.18}

 35%|███▍      | 9774/28080 [19:19:09<36:14:54,  7.13s/it]
 35%|███▍      | 9775/28080 [19:19:16<36:18:36,  7.14s/it]
                                                          
{'loss': 0.6225, 'learning_rate': 0.00037865280761201816, 'epoch': 4.18}

 35%|███▍      | 9775/28080 [19:19:16<36:18:36,  7.14s/it]
 35%|███▍      | 9776/28080 [19:19:23<36:21:45,  7.15s/it]
                                                          
{'loss': 0.644, 'learning_rate': 0.00037862808233933066, 'epoch': 4.18}

 35%|███▍      | 9776/28080 [19:19:23<36:21:45,  7.15s/it]
 35%|███▍      | 9777/28080 [19:19:30<36:22:31,  7.15s/it]
                                                          
{'loss': 0.6243, 'learning_rate': 0.00037860335535537927, 'epoch': 4.18}

 35%|███▍      | 9777/28080 [19:19:30<36:22:31,  7.15s/it]
 35%|███▍      | 9778/28080 [19:19:37<36:21:02,  7.15s/it]
                                                          
{'loss': 0.6144, 'learning_rate': 0.00037857862666049294, 'epoch': 4.18}

 35%|███▍      | 9778/28080 [19:19:37<36:21:02,  7.15s/it]
 35%|███▍      | 9779/28080 [19:19:45<36:23:54,  7.16s/it]
                                                          
{'loss': 0.6385, 'learning_rate': 0.0003785538962550005, 'epoch': 4.18}

 35%|███▍      | 9779/28080 [19:19:45<36:23:54,  7.16s/it]
 35%|███▍      | 9780/28080 [19:19:52<36:21:18,  7.15s/it]
                                                          
{'loss': 0.645, 'learning_rate': 0.00037852916413923124, 'epoch': 4.18}

 35%|███▍      | 9780/28080 [19:19:52<36:21:18,  7.15s/it]
 35%|███▍      | 9781/28080 [19:19:59<36:25:53,  7.17s/it]
                                                          
{'loss': 0.6249, 'learning_rate': 0.000378504430313514, 'epoch': 4.18}

 35%|███▍      | 9781/28080 [19:19:59<36:25:53,  7.17s/it]
 35%|███▍      | 9782/28080 [19:20:06<36:36:40,  7.20s/it]
                                                          
{'loss': 0.6083, 'learning_rate': 0.0003784796947781779, 'epoch': 4.18}

 35%|███▍      | 9782/28080 [19:20:06<36:36:40,  7.20s/it]
 35%|███▍      | 9783/28080 [19:20:13<36:29:54,  7.18s/it]
                                                          
{'loss': 0.616, 'learning_rate': 0.000378454957533552, 'epoch': 4.18}

 35%|███▍      | 9783/28080 [19:20:13<36:29:54,  7.18s/it]
 35%|███▍      | 9784/28080 [19:20:20<36:28:18,  7.18s/it]
                                                          
{'loss': 0.6121, 'learning_rate': 0.0003784302185799653, 'epoch': 4.18}

 35%|███▍      | 9784/28080 [19:20:21<36:28:18,  7.18s/it]
 35%|███▍      | 9785/28080 [19:20:28<36:21:03,  7.15s/it]
                                                          
{'loss': 0.6105, 'learning_rate': 0.00037840547791774716, 'epoch': 4.18}

 35%|███▍      | 9785/28080 [19:20:28<36:21:03,  7.15s/it]
 35%|███▍      | 9786/28080 [19:20:35<36:16:44,  7.14s/it]
                                                          
{'loss': 0.6523, 'learning_rate': 0.0003783807355472266, 'epoch': 4.18}

 35%|███▍      | 9786/28080 [19:20:35<36:16:44,  7.14s/it]
 35%|███▍      | 9787/28080 [19:20:42<36:21:33,  7.16s/it]
                                                          
{'loss': 0.6281, 'learning_rate': 0.0003783559914687328, 'epoch': 4.18}

 35%|███▍      | 9787/28080 [19:20:42<36:21:33,  7.16s/it]
 35%|███▍      | 9788/28080 [19:20:49<36:23:17,  7.16s/it]
                                                          
{'loss': 0.618, 'learning_rate': 0.0003783312456825949, 'epoch': 4.18}

 35%|███▍      | 9788/28080 [19:20:49<36:23:17,  7.16s/it]
 35%|███▍      | 9789/28080 [19:20:56<36:22:04,  7.16s/it]
                                                          
{'loss': 0.6134, 'learning_rate': 0.0003783064981891422, 'epoch': 4.18}

 35%|███▍      | 9789/28080 [19:20:56<36:22:04,  7.16s/it]
 35%|███▍      | 9790/28080 [19:21:03<36:19:41,  7.15s/it]
                                                          
{'loss': 0.6177, 'learning_rate': 0.00037828174898870385, 'epoch': 4.18}

 35%|███▍      | 9790/28080 [19:21:03<36:19:41,  7.15s/it]
 35%|███▍      | 9791/28080 [19:21:11<36:20:16,  7.15s/it]
                                                          
{'loss': 0.6054, 'learning_rate': 0.0003782569980816092, 'epoch': 4.18}

 35%|███▍      | 9791/28080 [19:21:11<36:20:16,  7.15s/it]
 35%|███▍      | 9792/28080 [19:21:18<36:08:06,  7.11s/it]
                                                          
{'loss': 0.6207, 'learning_rate': 0.0003782322454681876, 'epoch': 4.18}

 35%|███▍      | 9792/28080 [19:21:18<36:08:06,  7.11s/it]
 35%|███▍      | 9793/28080 [19:21:25<36:02:36,  7.10s/it]
                                                          
{'loss': 0.6205, 'learning_rate': 0.0003782074911487682, 'epoch': 4.18}

 35%|███▍      | 9793/28080 [19:21:25<36:02:36,  7.10s/it]
 35%|███▍      | 9794/28080 [19:21:32<36:07:40,  7.11s/it]
                                                          
{'loss': 0.6453, 'learning_rate': 0.00037818273512368037, 'epoch': 4.18}

 35%|███▍      | 9794/28080 [19:21:32<36:07:40,  7.11s/it]
 35%|███▍      | 9795/28080 [19:21:39<36:02:24,  7.10s/it]
                                                          
{'loss': 0.6401, 'learning_rate': 0.0003781579773932535, 'epoch': 4.18}

 35%|███▍      | 9795/28080 [19:21:39<36:02:24,  7.10s/it]
 35%|███▍      | 9796/28080 [19:21:46<36:06:31,  7.11s/it]
                                                          
{'loss': 0.625, 'learning_rate': 0.00037813321795781695, 'epoch': 4.18}

 35%|███▍      | 9796/28080 [19:21:46<36:06:31,  7.11s/it]
 35%|███▍      | 9797/28080 [19:21:53<36:20:07,  7.15s/it]
                                                          
{'loss': 0.6233, 'learning_rate': 0.0003781084568177002, 'epoch': 4.19}

 35%|███▍      | 9797/28080 [19:21:53<36:20:07,  7.15s/it]
 35%|███▍      | 9798/28080 [19:22:00<36:15:14,  7.14s/it]
                                                          
{'loss': 0.6297, 'learning_rate': 0.0003780836939732325, 'epoch': 4.19}

 35%|███▍      | 9798/28080 [19:22:00<36:15:14,  7.14s/it]
 35%|███▍      | 9799/28080 [19:22:07<36:10:49,  7.12s/it]
                                                          
{'loss': 0.6304, 'learning_rate': 0.0003780589294247434, 'epoch': 4.19}

 35%|███▍      | 9799/28080 [19:22:07<36:10:49,  7.12s/it]
 35%|███▍      | 9800/28080 [19:22:15<36:10:22,  7.12s/it]
                                                          
{'loss': 0.6311, 'learning_rate': 0.00037803416317256234, 'epoch': 4.19}

 35%|███▍      | 9800/28080 [19:22:15<36:10:22,  7.12s/it]
 35%|███▍      | 9801/28080 [19:22:22<36:12:42,  7.13s/it]
                                                          
{'loss': 0.6229, 'learning_rate': 0.00037800939521701884, 'epoch': 4.19}

 35%|███▍      | 9801/28080 [19:22:22<36:12:42,  7.13s/it]
 35%|███▍      | 9802/28080 [19:22:29<36:16:46,  7.15s/it]
                                                          
{'loss': 0.6091, 'learning_rate': 0.0003779846255584425, 'epoch': 4.19}

 35%|███▍      | 9802/28080 [19:22:29<36:16:46,  7.15s/it]
 35%|███▍      | 9803/28080 [19:22:36<36:15:28,  7.14s/it]
                                                          
{'loss': 0.6325, 'learning_rate': 0.00037795985419716263, 'epoch': 4.19}

 35%|███▍      | 9803/28080 [19:22:36<36:15:28,  7.14s/it]
 35%|███▍      | 9804/28080 [19:22:43<36:10:11,  7.12s/it]
                                                          
{'loss': 0.6306, 'learning_rate': 0.00037793508113350896, 'epoch': 4.19}

 35%|███▍      | 9804/28080 [19:22:43<36:10:11,  7.12s/it]
 35%|███▍      | 9805/28080 [19:22:50<36:04:31,  7.11s/it]
                                                          
{'loss': 0.6269, 'learning_rate': 0.00037791030636781097, 'epoch': 4.19}

 35%|███▍      | 9805/28080 [19:22:50<36:04:31,  7.11s/it]
 35%|███▍      | 9806/28080 [19:22:57<36:10:19,  7.13s/it]
                                                          
{'loss': 0.617, 'learning_rate': 0.00037788552990039836, 'epoch': 4.19}

 35%|███▍      | 9806/28080 [19:22:57<36:10:19,  7.13s/it]
 35%|███▍      | 9807/28080 [19:23:04<36:09:04,  7.12s/it]
                                                          
{'loss': 0.6269, 'learning_rate': 0.0003778607517316006, 'epoch': 4.19}

 35%|███▍      | 9807/28080 [19:23:04<36:09:04,  7.12s/it]
 35%|███▍      | 9808/28080 [19:23:12<36:13:56,  7.14s/it]
                                                          
{'loss': 0.6394, 'learning_rate': 0.0003778359718617476, 'epoch': 4.19}

 35%|███▍      | 9808/28080 [19:23:12<36:13:56,  7.14s/it]
 35%|███▍      | 9809/28080 [19:23:19<36:08:16,  7.12s/it]
                                                          
{'loss': 0.6214, 'learning_rate': 0.0003778111902911688, 'epoch': 4.19}

 35%|███▍      | 9809/28080 [19:23:19<36:08:16,  7.12s/it]
 35%|███▍      | 9810/28080 [19:23:26<36:08:55,  7.12s/it]
                                                          
{'loss': 0.6195, 'learning_rate': 0.00037778640702019393, 'epoch': 4.19}

 35%|███▍      | 9810/28080 [19:23:26<36:08:55,  7.12s/it]
 35%|███▍      | 9811/28080 [19:23:33<36:11:25,  7.13s/it]
                                                          
{'loss': 0.6409, 'learning_rate': 0.00037776162204915286, 'epoch': 4.19}

 35%|███▍      | 9811/28080 [19:23:33<36:11:25,  7.13s/it]
 35%|███▍      | 9812/28080 [19:23:40<36:16:36,  7.15s/it]
                                                          
{'loss': 0.604, 'learning_rate': 0.00037773683537837513, 'epoch': 4.19}

 35%|███▍      | 9812/28080 [19:23:40<36:16:36,  7.15s/it]
 35%|███▍      | 9813/28080 [19:23:47<36:24:15,  7.17s/it]
                                                          
{'loss': 0.6319, 'learning_rate': 0.0003777120470081906, 'epoch': 4.19}

 35%|███▍      | 9813/28080 [19:23:47<36:24:15,  7.17s/it]
 35%|███▍      | 9814/28080 [19:23:55<36:22:52,  7.17s/it]
                                                          
{'loss': 0.621, 'learning_rate': 0.00037768725693892904, 'epoch': 4.19}

 35%|███▍      | 9814/28080 [19:23:55<36:22:52,  7.17s/it]
 35%|███▍      | 9815/28080 [19:24:02<36:19:14,  7.16s/it]
                                                          
{'loss': 0.6162, 'learning_rate': 0.0003776624651709202, 'epoch': 4.19}

 35%|███▍      | 9815/28080 [19:24:02<36:19:14,  7.16s/it]
 35%|███▍      | 9816/28080 [19:24:09<36:20:38,  7.16s/it]
                                                          
{'loss': 0.6404, 'learning_rate': 0.00037763767170449406, 'epoch': 4.19}

 35%|███▍      | 9816/28080 [19:24:09<36:20:38,  7.16s/it]
 35%|███▍      | 9817/28080 [19:24:16<36:15:07,  7.15s/it]
                                                          
{'loss': 0.6338, 'learning_rate': 0.0003776128765399803, 'epoch': 4.19}

 35%|███▍      | 9817/28080 [19:24:16<36:15:07,  7.15s/it]
 35%|███▍      | 9818/28080 [19:24:23<36:09:15,  7.13s/it]
                                                          
{'loss': 0.6243, 'learning_rate': 0.0003775880796777089, 'epoch': 4.19}

 35%|███▍      | 9818/28080 [19:24:23<36:09:15,  7.13s/it]
 35%|███▍      | 9819/28080 [19:24:30<36:07:27,  7.12s/it]
                                                          
{'loss': 0.6132, 'learning_rate': 0.00037756328111800976, 'epoch': 4.19}

 35%|███▍      | 9819/28080 [19:24:30<36:07:27,  7.12s/it]
 35%|███▍      | 9820/28080 [19:24:37<35:55:01,  7.08s/it]
                                                          
{'loss': 0.654, 'learning_rate': 0.0003775384808612127, 'epoch': 4.2}

 35%|███▍      | 9820/28080 [19:24:37<35:55:01,  7.08s/it]
 35%|███▍      | 9821/28080 [19:24:44<36:01:01,  7.10s/it]
                                                          
{'loss': 0.6208, 'learning_rate': 0.00037751367890764777, 'epoch': 4.2}

 35%|███▍      | 9821/28080 [19:24:44<36:01:01,  7.10s/it]
 35%|███▍      | 9822/28080 [19:24:51<36:03:18,  7.11s/it]
                                                          
{'loss': 0.6264, 'learning_rate': 0.00037748887525764483, 'epoch': 4.2}

 35%|███▍      | 9822/28080 [19:24:51<36:03:18,  7.11s/it]
 35%|███▍      | 9823/28080 [19:24:58<35:58:13,  7.09s/it]
                                                          
{'loss': 0.629, 'learning_rate': 0.000377464069911534, 'epoch': 4.2}

 35%|███▍      | 9823/28080 [19:24:58<35:58:13,  7.09s/it]
 35%|███▍      | 9824/28080 [19:25:06<35:57:53,  7.09s/it]
                                                          
{'loss': 0.615, 'learning_rate': 0.00037743926286964513, 'epoch': 4.2}

 35%|███▍      | 9824/28080 [19:25:06<35:57:53,  7.09s/it]
 35%|███▍      | 9825/28080 [19:25:13<35:59:17,  7.10s/it]
                                                          
{'loss': 0.6289, 'learning_rate': 0.00037741445413230843, 'epoch': 4.2}

 35%|███▍      | 9825/28080 [19:25:13<35:59:17,  7.10s/it]
 35%|███▍      | 9826/28080 [19:25:20<35:56:05,  7.09s/it]
                                                          
{'loss': 0.6307, 'learning_rate': 0.00037738964369985384, 'epoch': 4.2}

 35%|███▍      | 9826/28080 [19:25:20<35:56:05,  7.09s/it]
 35%|███▍      | 9827/28080 [19:25:27<35:56:37,  7.09s/it]
                                                          
{'loss': 0.6284, 'learning_rate': 0.0003773648315726115, 'epoch': 4.2}

 35%|███▍      | 9827/28080 [19:25:27<35:56:37,  7.09s/it]
 35%|███▌      | 9828/28080 [19:25:34<36:06:05,  7.12s/it]
                                                          
{'loss': 0.6294, 'learning_rate': 0.0003773400177509114, 'epoch': 4.2}

 35%|███▌      | 9828/28080 [19:25:34<36:06:05,  7.12s/it]
 35%|███▌      | 9829/28080 [19:25:41<36:02:04,  7.11s/it]
                                                          
{'loss': 0.6136, 'learning_rate': 0.00037731520223508374, 'epoch': 4.2}

 35%|███▌      | 9829/28080 [19:25:41<36:02:04,  7.11s/it]
 35%|███▌      | 9830/28080 [19:25:48<36:07:04,  7.12s/it]
                                                          
{'loss': 0.6018, 'learning_rate': 0.00037729038502545863, 'epoch': 4.2}

 35%|███▌      | 9830/28080 [19:25:48<36:07:04,  7.12s/it]
 35%|███▌      | 9831/28080 [19:25:55<36:11:46,  7.14s/it]
                                                          
{'loss': 0.625, 'learning_rate': 0.0003772655661223663, 'epoch': 4.2}

 35%|███▌      | 9831/28080 [19:25:55<36:11:46,  7.14s/it]
 35%|███▌      | 9832/28080 [19:26:03<36:13:13,  7.15s/it]
                                                          
{'loss': 0.6037, 'learning_rate': 0.00037724074552613696, 'epoch': 4.2}

 35%|███▌      | 9832/28080 [19:26:03<36:13:13,  7.15s/it]
 35%|███▌      | 9833/28080 [19:26:10<36:12:14,  7.14s/it]
                                                          
{'loss': 0.642, 'learning_rate': 0.00037721592323710073, 'epoch': 4.2}

 35%|███▌      | 9833/28080 [19:26:10<36:12:14,  7.14s/it]
 35%|███▌      | 9834/28080 [19:26:17<36:09:24,  7.13s/it]
                                                          
{'loss': 0.634, 'learning_rate': 0.0003771910992555878, 'epoch': 4.2}

 35%|███▌      | 9834/28080 [19:26:17<36:09:24,  7.13s/it]
 35%|███▌      | 9835/28080 [19:26:24<36:11:40,  7.14s/it]
                                                          
{'loss': 0.6315, 'learning_rate': 0.00037716627358192866, 'epoch': 4.2}

 35%|███▌      | 9835/28080 [19:26:24<36:11:40,  7.14s/it]
 35%|███▌      | 9836/28080 [19:26:31<36:13:39,  7.15s/it]
                                                          
{'loss': 0.6185, 'learning_rate': 0.00037714144621645327, 'epoch': 4.2}

 35%|███▌      | 9836/28080 [19:26:31<36:13:39,  7.15s/it]
 35%|███▌      | 9837/28080 [19:26:38<36:17:45,  7.16s/it]
                                                          
{'loss': 0.6413, 'learning_rate': 0.0003771166171594923, 'epoch': 4.2}

 35%|███▌      | 9837/28080 [19:26:38<36:17:45,  7.16s/it]
 35%|███▌      | 9838/28080 [19:26:46<36:22:30,  7.18s/it]
                                                          
{'loss': 0.6393, 'learning_rate': 0.00037709178641137577, 'epoch': 4.2}

 35%|███▌      | 9838/28080 [19:26:46<36:22:30,  7.18s/it]
 35%|███▌      | 9839/28080 [19:26:53<36:12:18,  7.15s/it]
                                                          
{'loss': 0.6189, 'learning_rate': 0.00037706695397243405, 'epoch': 4.2}

 35%|███▌      | 9839/28080 [19:26:53<36:12:18,  7.15s/it]
 35%|███▌      | 9840/28080 [19:27:00<36:10:04,  7.14s/it]
                                                          
{'loss': 0.6201, 'learning_rate': 0.00037704211984299773, 'epoch': 4.2}

 35%|███▌      | 9840/28080 [19:27:00<36:10:04,  7.14s/it]
 35%|███▌      | 9841/28080 [19:27:07<36:20:07,  7.17s/it]
                                                          
{'loss': 0.6221, 'learning_rate': 0.00037701728402339703, 'epoch': 4.2}

 35%|███▌      | 9841/28080 [19:27:07<36:20:07,  7.17s/it]
 35%|███▌      | 9842/28080 [19:27:14<36:17:59,  7.17s/it]
                                                          
{'loss': 0.6062, 'learning_rate': 0.0003769924465139624, 'epoch': 4.2}

 35%|███▌      | 9842/28080 [19:27:14<36:17:59,  7.17s/it]
 35%|███▌      | 9843/28080 [19:27:21<36:12:12,  7.15s/it]
                                                          
{'loss': 0.6294, 'learning_rate': 0.0003769676073150243, 'epoch': 4.2}

 35%|███▌      | 9843/28080 [19:27:21<36:12:12,  7.15s/it]
 35%|███▌      | 9844/28080 [19:27:28<36:09:16,  7.14s/it]
                                                          
{'loss': 0.6161, 'learning_rate': 0.00037694276642691316, 'epoch': 4.21}

 35%|███▌      | 9844/28080 [19:27:28<36:09:16,  7.14s/it]
 35%|███▌      | 9845/28080 [19:27:35<35:54:48,  7.09s/it]
                                                          
{'loss': 0.6319, 'learning_rate': 0.0003769179238499595, 'epoch': 4.21}

 35%|███▌      | 9845/28080 [19:27:35<35:54:48,  7.09s/it]
 35%|███▌      | 9846/28080 [19:27:42<35:56:24,  7.10s/it]
                                                          
{'loss': 0.6457, 'learning_rate': 0.0003768930795844937, 'epoch': 4.21}

 35%|███▌      | 9846/28080 [19:27:42<35:56:24,  7.10s/it]
 35%|███▌      | 9847/28080 [19:27:50<36:05:19,  7.13s/it]
                                                          
{'loss': 0.6195, 'learning_rate': 0.0003768682336308464, 'epoch': 4.21}

 35%|███▌      | 9847/28080 [19:27:50<36:05:19,  7.13s/it]
 35%|███▌      | 9848/28080 [19:27:57<36:12:54,  7.15s/it]
                                                          
{'loss': 0.619, 'learning_rate': 0.0003768433859893482, 'epoch': 4.21}

 35%|███▌      | 9848/28080 [19:27:57<36:12:54,  7.15s/it]
 35%|███▌      | 9849/28080 [19:28:04<36:10:20,  7.14s/it]
                                                          
{'loss': 0.6347, 'learning_rate': 0.00037681853666032963, 'epoch': 4.21}

 35%|███▌      | 9849/28080 [19:28:04<36:10:20,  7.14s/it]
 35%|███▌      | 9850/28080 [19:28:11<36:02:55,  7.12s/it]
                                                          
{'loss': 0.6281, 'learning_rate': 0.00037679368564412117, 'epoch': 4.21}

 35%|███▌      | 9850/28080 [19:28:11<36:02:55,  7.12s/it]
 35%|███▌      | 9851/28080 [19:28:18<36:11:00,  7.15s/it]
                                                          
{'loss': 0.6062, 'learning_rate': 0.00037676883294105357, 'epoch': 4.21}

 35%|███▌      | 9851/28080 [19:28:18<36:11:00,  7.15s/it]
 35%|███▌      | 9852/28080 [19:28:25<36:12:54,  7.15s/it]
                                                          
{'loss': 0.6499, 'learning_rate': 0.0003767439785514575, 'epoch': 4.21}

 35%|███▌      | 9852/28080 [19:28:25<36:12:54,  7.15s/it]
 35%|███▌      | 9853/28080 [19:28:33<36:19:19,  7.17s/it]
                                                          
{'loss': 0.6334, 'learning_rate': 0.0003767191224756634, 'epoch': 4.21}

 35%|███▌      | 9853/28080 [19:28:33<36:19:19,  7.17s/it]
 35%|███▌      | 9854/28080 [19:28:40<36:16:31,  7.17s/it]
                                                          
{'loss': 0.6227, 'learning_rate': 0.0003766942647140022, 'epoch': 4.21}

 35%|███▌      | 9854/28080 [19:28:40<36:16:31,  7.17s/it]
 35%|███▌      | 9855/28080 [19:28:47<36:12:27,  7.15s/it]
                                                          
{'loss': 0.6237, 'learning_rate': 0.0003766694052668045, 'epoch': 4.21}

 35%|███▌      | 9855/28080 [19:28:47<36:12:27,  7.15s/it]
 35%|███▌      | 9856/28080 [19:28:54<36:03:20,  7.12s/it]
                                                          
{'loss': 0.6171, 'learning_rate': 0.000376644544134401, 'epoch': 4.21}

 35%|███▌      | 9856/28080 [19:28:54<36:03:20,  7.12s/it]
 35%|███▌      | 9857/28080 [19:29:01<36:00:08,  7.11s/it]
                                                          
{'loss': 0.6209, 'learning_rate': 0.00037661968131712253, 'epoch': 4.21}

 35%|███▌      | 9857/28080 [19:29:01<36:00:08,  7.11s/it]
 35%|███▌      | 9858/28080 [19:29:08<36:07:25,  7.14s/it]
                                                          
{'loss': 0.6189, 'learning_rate': 0.0003765948168152998, 'epoch': 4.21}

 35%|███▌      | 9858/28080 [19:29:08<36:07:25,  7.14s/it]
 35%|███▌      | 9859/28080 [19:29:15<35:53:50,  7.09s/it]
                                                          
{'loss': 0.6432, 'learning_rate': 0.00037656995062926367, 'epoch': 4.21}

 35%|███▌      | 9859/28080 [19:29:15<35:53:50,  7.09s/it]
 35%|███▌      | 9860/28080 [19:29:22<35:53:20,  7.09s/it]
                                                          
{'loss': 0.626, 'learning_rate': 0.0003765450827593449, 'epoch': 4.21}

 35%|███▌      | 9860/28080 [19:29:22<35:53:20,  7.09s/it]
 35%|███▌      | 9861/28080 [19:29:30<36:02:09,  7.12s/it]
                                                          
{'loss': 0.6043, 'learning_rate': 0.0003765202132058744, 'epoch': 4.21}

 35%|███▌      | 9861/28080 [19:29:30<36:02:09,  7.12s/it]
 35%|███▌      | 9862/28080 [19:29:37<36:04:07,  7.13s/it]
                                                          
{'loss': 0.6261, 'learning_rate': 0.0003764953419691829, 'epoch': 4.21}

 35%|███▌      | 9862/28080 [19:29:37<36:04:07,  7.13s/it]
 35%|███▌      | 9863/28080 [19:29:44<36:08:20,  7.14s/it]
                                                          
{'loss': 0.6236, 'learning_rate': 0.0003764704690496014, 'epoch': 4.21}

 35%|███▌      | 9863/28080 [19:29:44<36:08:20,  7.14s/it]
 35%|███▌      | 9864/28080 [19:29:51<36:18:35,  7.18s/it]
                                                          
{'loss': 0.6366, 'learning_rate': 0.00037644559444746086, 'epoch': 4.21}

 35%|███▌      | 9864/28080 [19:29:51<36:18:35,  7.18s/it]
 35%|███▌      | 9865/28080 [19:29:58<36:11:04,  7.15s/it]
                                                          
{'loss': 0.6357, 'learning_rate': 0.000376420718163092, 'epoch': 4.21}

 35%|███▌      | 9865/28080 [19:29:58<36:11:04,  7.15s/it]
 35%|███▌      | 9866/28080 [19:30:05<36:07:15,  7.14s/it]
                                                          
{'loss': 0.6126, 'learning_rate': 0.00037639584019682603, 'epoch': 4.21}

 35%|███▌      | 9866/28080 [19:30:05<36:07:15,  7.14s/it]
 35%|███▌      | 9867/28080 [19:30:12<36:00:32,  7.12s/it]
                                                          
{'loss': 0.6527, 'learning_rate': 0.0003763709605489937, 'epoch': 4.22}

 35%|███▌      | 9867/28080 [19:30:12<36:00:32,  7.12s/it]
 35%|███▌      | 9868/28080 [19:30:20<36:08:39,  7.14s/it]
                                                          
{'loss': 0.6208, 'learning_rate': 0.00037634607921992625, 'epoch': 4.22}

 35%|███▌      | 9868/28080 [19:30:20<36:08:39,  7.14s/it]
 35%|███▌      | 9869/28080 [19:30:27<36:11:44,  7.16s/it]
                                                          
{'loss': 0.6097, 'learning_rate': 0.00037632119620995447, 'epoch': 4.22}

 35%|███▌      | 9869/28080 [19:30:27<36:11:44,  7.16s/it]
 35%|███▌      | 9870/28080 [19:30:34<36:10:41,  7.15s/it]
                                                          
{'loss': 0.6245, 'learning_rate': 0.0003762963115194095, 'epoch': 4.22}

 35%|███▌      | 9870/28080 [19:30:34<36:10:41,  7.15s/it]
 35%|███▌      | 9871/28080 [19:30:41<36:12:34,  7.16s/it]
                                                          
{'loss': 0.6343, 'learning_rate': 0.0003762714251486224, 'epoch': 4.22}

 35%|███▌      | 9871/28080 [19:30:41<36:12:34,  7.16s/it]
 35%|███▌      | 9872/28080 [19:30:48<36:12:04,  7.16s/it]
                                                          
{'loss': 0.6165, 'learning_rate': 0.00037624653709792424, 'epoch': 4.22}

 35%|███▌      | 9872/28080 [19:30:48<36:12:04,  7.16s/it]
 35%|███▌      | 9873/28080 [19:30:55<36:14:25,  7.17s/it]
                                                          
{'loss': 0.6322, 'learning_rate': 0.0003762216473676461, 'epoch': 4.22}

 35%|███▌      | 9873/28080 [19:30:55<36:14:25,  7.17s/it]
 35%|███▌      | 9874/28080 [19:31:03<36:11:09,  7.16s/it]
                                                          
{'loss': 0.62, 'learning_rate': 0.00037619675595811926, 'epoch': 4.22}

 35%|███▌      | 9874/28080 [19:31:03<36:11:09,  7.16s/it]
 35%|███▌      | 9875/28080 [19:31:10<36:04:20,  7.13s/it]
                                                          
{'loss': 0.6207, 'learning_rate': 0.00037617186286967465, 'epoch': 4.22}

 35%|███▌      | 9875/28080 [19:31:10<36:04:20,  7.13s/it]
 35%|███▌      | 9876/28080 [19:31:17<36:07:23,  7.14s/it]
                                                          
{'loss': 0.6141, 'learning_rate': 0.00037614696810264373, 'epoch': 4.22}

 35%|███▌      | 9876/28080 [19:31:17<36:07:23,  7.14s/it]
 35%|███▌      | 9877/28080 [19:31:24<36:14:04,  7.17s/it]
                                                          
{'loss': 0.6052, 'learning_rate': 0.0003761220716573574, 'epoch': 4.22}

 35%|███▌      | 9877/28080 [19:31:24<36:14:04,  7.17s/it]
 35%|███▌      | 9878/28080 [19:31:31<36:05:37,  7.14s/it]
                                                          
{'loss': 0.6382, 'learning_rate': 0.00037609717353414705, 'epoch': 4.22}

 35%|███▌      | 9878/28080 [19:31:31<36:05:37,  7.14s/it]
 35%|███▌      | 9879/28080 [19:31:38<35:58:22,  7.12s/it]
                                                          
{'loss': 0.6233, 'learning_rate': 0.00037607227373334396, 'epoch': 4.22}

 35%|███▌      | 9879/28080 [19:31:38<35:58:22,  7.12s/it]
 35%|███▌      | 9880/28080 [19:31:45<36:03:01,  7.13s/it]
                                                          
{'loss': 0.6296, 'learning_rate': 0.0003760473722552792, 'epoch': 4.22}

 35%|███▌      | 9880/28080 [19:31:45<36:03:01,  7.13s/it]
 35%|███▌      | 9881/28080 [19:31:53<36:14:05,  7.17s/it]
                                                          
{'loss': 0.6448, 'learning_rate': 0.00037602246910028433, 'epoch': 4.22}

 35%|███▌      | 9881/28080 [19:31:53<36:14:05,  7.17s/it]
 35%|███▌      | 9882/28080 [19:32:00<36:11:28,  7.16s/it]
                                                          
{'loss': 0.6322, 'learning_rate': 0.0003759975642686904, 'epoch': 4.22}

 35%|███▌      | 9882/28080 [19:32:00<36:11:28,  7.16s/it]
 35%|███▌      | 9883/28080 [19:32:07<36:13:32,  7.17s/it]
                                                          
{'loss': 0.6317, 'learning_rate': 0.000375972657760829, 'epoch': 4.22}

 35%|███▌      | 9883/28080 [19:32:07<36:13:32,  7.17s/it]
 35%|███▌      | 9884/28080 [19:32:14<36:12:18,  7.16s/it]
                                                          
{'loss': 0.6447, 'learning_rate': 0.0003759477495770312, 'epoch': 4.22}

 35%|███▌      | 9884/28080 [19:32:14<36:12:18,  7.16s/it]
 35%|███▌      | 9885/28080 [19:32:21<36:06:02,  7.14s/it]
                                                          
{'loss': 0.6172, 'learning_rate': 0.00037592283971762865, 'epoch': 4.22}

 35%|███▌      | 9885/28080 [19:32:21<36:06:02,  7.14s/it]
 35%|███▌      | 9886/28080 [19:32:28<36:11:41,  7.16s/it]
                                                          
{'loss': 0.6148, 'learning_rate': 0.0003758979281829525, 'epoch': 4.22}

 35%|███▌      | 9886/28080 [19:32:28<36:11:41,  7.16s/it]
 35%|███▌      | 9887/28080 [19:32:35<36:01:33,  7.13s/it]
                                                          
{'loss': 0.6116, 'learning_rate': 0.00037587301497333435, 'epoch': 4.22}

 35%|███▌      | 9887/28080 [19:32:35<36:01:33,  7.13s/it]
 35%|███▌      | 9888/28080 [19:32:42<35:55:15,  7.11s/it]
                                                          
{'loss': 0.6395, 'learning_rate': 0.00037584810008910565, 'epoch': 4.22}

 35%|███▌      | 9888/28080 [19:32:42<35:55:15,  7.11s/it]
 35%|███▌      | 9889/28080 [19:32:50<35:52:15,  7.10s/it]
                                                          
{'loss': 0.6305, 'learning_rate': 0.00037582318353059774, 'epoch': 4.22}

 35%|███▌      | 9889/28080 [19:32:50<35:52:15,  7.10s/it]
 35%|███▌      | 9890/28080 [19:32:57<35:56:18,  7.11s/it]
                                                          
{'loss': 0.6464, 'learning_rate': 0.00037579826529814223, 'epoch': 4.22}

 35%|███▌      | 9890/28080 [19:32:57<35:56:18,  7.11s/it]
 35%|███▌      | 9891/28080 [19:33:04<36:04:18,  7.14s/it]
                                                          
{'loss': 0.6076, 'learning_rate': 0.00037577334539207056, 'epoch': 4.23}

 35%|███▌      | 9891/28080 [19:33:04<36:04:18,  7.14s/it]
 35%|███▌      | 9892/28080 [19:33:11<36:00:34,  7.13s/it]
                                                          
{'loss': 0.6203, 'learning_rate': 0.0003757484238127142, 'epoch': 4.23}

 35%|███▌      | 9892/28080 [19:33:11<36:00:34,  7.13s/it]
 35%|███▌      | 9893/28080 [19:33:18<35:59:42,  7.13s/it]
                                                          
{'loss': 0.6295, 'learning_rate': 0.00037572350056040493, 'epoch': 4.23}

 35%|███▌      | 9893/28080 [19:33:18<35:59:42,  7.13s/it]
 35%|███▌      | 9894/28080 [19:33:25<35:54:41,  7.11s/it]
                                                          
{'loss': 0.652, 'learning_rate': 0.0003756985756354742, 'epoch': 4.23}

 35%|███▌      | 9894/28080 [19:33:25<35:54:41,  7.11s/it]
 35%|███▌      | 9895/28080 [19:33:32<35:58:55,  7.12s/it]
                                                          
{'loss': 0.608, 'learning_rate': 0.00037567364903825346, 'epoch': 4.23}

 35%|███▌      | 9895/28080 [19:33:32<35:58:55,  7.12s/it]
 35%|███▌      | 9896/28080 [19:33:40<36:05:33,  7.15s/it]
                                                          
{'loss': 0.6453, 'learning_rate': 0.00037564872076907454, 'epoch': 4.23}

 35%|███▌      | 9896/28080 [19:33:40<36:05:33,  7.15s/it]
 35%|███▌      | 9897/28080 [19:33:47<36:08:35,  7.16s/it]
                                                          
{'loss': 0.5978, 'learning_rate': 0.0003756237908282689, 'epoch': 4.23}

 35%|███▌      | 9897/28080 [19:33:47<36:08:35,  7.16s/it]
 35%|███▌      | 9898/28080 [19:33:54<36:05:50,  7.15s/it]
                                                          
{'loss': 0.6453, 'learning_rate': 0.0003755988592161685, 'epoch': 4.23}

 35%|███▌      | 9898/28080 [19:33:54<36:05:50,  7.15s/it]
 35%|███▌      | 9899/28080 [19:34:01<36:07:37,  7.15s/it]
                                                          
{'loss': 0.627, 'learning_rate': 0.00037557392593310474, 'epoch': 4.23}

 35%|███▌      | 9899/28080 [19:34:01<36:07:37,  7.15s/it]
 35%|███▌      | 9900/28080 [19:34:08<36:14:28,  7.18s/it]
                                                          
{'loss': 0.6226, 'learning_rate': 0.00037554899097940955, 'epoch': 4.23}

 35%|███▌      | 9900/28080 [19:34:08<36:14:28,  7.18s/it]
 35%|███▌      | 9901/28080 [19:34:16<36:25:30,  7.21s/it]
                                                          
{'loss': 0.6255, 'learning_rate': 0.00037552405435541445, 'epoch': 4.23}

 35%|███▌      | 9901/28080 [19:34:16<36:25:30,  7.21s/it]
 35%|███▌      | 9902/28080 [19:34:23<36:20:19,  7.20s/it]
                                                          
{'loss': 0.6254, 'learning_rate': 0.0003754991160614513, 'epoch': 4.23}

 35%|███▌      | 9902/28080 [19:34:23<36:20:19,  7.20s/it]
 35%|███▌      | 9903/28080 [19:34:30<36:15:20,  7.18s/it]
                                                          
{'loss': 0.6245, 'learning_rate': 0.00037547417609785195, 'epoch': 4.23}

 35%|███▌      | 9903/28080 [19:34:30<36:15:20,  7.18s/it]
 35%|███▌      | 9904/28080 [19:34:37<36:06:17,  7.15s/it]
                                                          
{'loss': 0.6362, 'learning_rate': 0.00037544923446494803, 'epoch': 4.23}

 35%|███▌      | 9904/28080 [19:34:37<36:06:17,  7.15s/it]
 35%|███▌      | 9905/28080 [19:34:44<36:10:05,  7.16s/it]
                                                          
{'loss': 0.6022, 'learning_rate': 0.0003754242911630716, 'epoch': 4.23}

 35%|███▌      | 9905/28080 [19:34:44<36:10:05,  7.16s/it]
 35%|███▌      | 9906/28080 [19:34:51<36:03:54,  7.14s/it]
                                                          
{'loss': 0.6, 'learning_rate': 0.0003753993461925542, 'epoch': 4.23}

 35%|███▌      | 9906/28080 [19:34:51<36:03:54,  7.14s/it]
 35%|███▌      | 9907/28080 [19:34:58<36:06:27,  7.15s/it]
                                                          
{'loss': 0.6103, 'learning_rate': 0.00037537439955372804, 'epoch': 4.23}

 35%|███▌      | 9907/28080 [19:34:58<36:06:27,  7.15s/it]
 35%|███▌      | 9908/28080 [19:35:05<35:58:30,  7.13s/it]
                                                          
{'loss': 0.615, 'learning_rate': 0.0003753494512469248, 'epoch': 4.23}

 35%|███▌      | 9908/28080 [19:35:05<35:58:30,  7.13s/it]
 35%|███▌      | 9909/28080 [19:35:13<35:53:40,  7.11s/it]
                                                          
{'loss': 0.6225, 'learning_rate': 0.00037532450127247634, 'epoch': 4.23}

 35%|███▌      | 9909/28080 [19:35:13<35:53:40,  7.11s/it]
 35%|███▌      | 9910/28080 [19:35:20<35:57:05,  7.12s/it]
                                                          
{'loss': 0.6378, 'learning_rate': 0.0003752995496307148, 'epoch': 4.23}

 35%|███▌      | 9910/28080 [19:35:20<35:57:05,  7.12s/it]
 35%|███▌      | 9911/28080 [19:35:27<35:58:38,  7.13s/it]
                                                          
{'loss': 0.6434, 'learning_rate': 0.0003752745963219719, 'epoch': 4.23}

 35%|███▌      | 9911/28080 [19:35:27<35:58:38,  7.13s/it]
 35%|███▌      | 9912/28080 [19:35:34<35:54:13,  7.11s/it]
                                                          
{'loss': 0.6451, 'learning_rate': 0.0003752496413465798, 'epoch': 4.23}

 35%|███▌      | 9912/28080 [19:35:34<35:54:13,  7.11s/it]
 35%|███▌      | 9913/28080 [19:35:41<35:57:08,  7.12s/it]
                                                          
{'loss': 0.6186, 'learning_rate': 0.00037522468470487034, 'epoch': 4.23}

 35%|███▌      | 9913/28080 [19:35:41<35:57:08,  7.12s/it]
 35%|███▌      | 9914/28080 [19:35:48<35:57:21,  7.13s/it]
                                                          
{'loss': 0.6421, 'learning_rate': 0.00037519972639717575, 'epoch': 4.24}

 35%|███▌      | 9914/28080 [19:35:48<35:57:21,  7.13s/it]
 35%|███▌      | 9915/28080 [19:35:55<35:51:24,  7.11s/it]
                                                          
{'loss': 0.6471, 'learning_rate': 0.0003751747664238279, 'epoch': 4.24}

 35%|███▌      | 9915/28080 [19:35:55<35:51:24,  7.11s/it]
 35%|███▌      | 9916/28080 [19:36:02<35:56:13,  7.12s/it]
                                                          
{'loss': 0.6314, 'learning_rate': 0.00037514980478515906, 'epoch': 4.24}

 35%|███▌      | 9916/28080 [19:36:02<35:56:13,  7.12s/it]
 35%|███▌      | 9917/28080 [19:36:10<36:11:39,  7.17s/it]
                                                          
{'loss': 0.6202, 'learning_rate': 0.00037512484148150097, 'epoch': 4.24}

 35%|███▌      | 9917/28080 [19:36:10<36:11:39,  7.17s/it]
 35%|███▌      | 9918/28080 [19:36:17<36:03:18,  7.15s/it]
                                                          
{'loss': 0.6232, 'learning_rate': 0.0003750998765131861, 'epoch': 4.24}

 35%|███▌      | 9918/28080 [19:36:17<36:03:18,  7.15s/it]
 35%|███▌      | 9919/28080 [19:36:24<36:02:23,  7.14s/it]
                                                          
{'loss': 0.6426, 'learning_rate': 0.0003750749098805464, 'epoch': 4.24}

 35%|███▌      | 9919/28080 [19:36:24<36:02:23,  7.14s/it]
 35%|███▌      | 9920/28080 [19:36:31<36:18:11,  7.20s/it]
                                                          
{'loss': 0.6238, 'learning_rate': 0.000375049941583914, 'epoch': 4.24}

 35%|███▌      | 9920/28080 [19:36:31<36:18:11,  7.20s/it]
 35%|███▌      | 9921/28080 [19:36:38<36:13:19,  7.18s/it]
                                                          
{'loss': 0.6407, 'learning_rate': 0.00037502497162362114, 'epoch': 4.24}

 35%|███▌      | 9921/28080 [19:36:38<36:13:19,  7.18s/it]
 35%|███▌      | 9922/28080 [19:36:46<36:10:11,  7.17s/it]
                                                          
{'loss': 0.6388, 'learning_rate': 0.000375, 'epoch': 4.24}

 35%|███▌      | 9922/28080 [19:36:46<36:10:11,  7.17s/it]
 35%|███▌      | 9923/28080 [19:36:53<36:19:18,  7.20s/it]
                                                          
{'loss': 0.6203, 'learning_rate': 0.00037497502671338286, 'epoch': 4.24}

 35%|███▌      | 9923/28080 [19:36:53<36:19:18,  7.20s/it]
 35%|███▌      | 9924/28080 [19:37:00<36:11:18,  7.18s/it]
                                                          
{'loss': 0.6286, 'learning_rate': 0.0003749500517641019, 'epoch': 4.24}

 35%|███▌      | 9924/28080 [19:37:00<36:11:18,  7.18s/it]
 35%|███▌      | 9925/28080 [19:37:07<36:14:31,  7.19s/it]
                                                          
{'loss': 0.6257, 'learning_rate': 0.0003749250751524894, 'epoch': 4.24}

 35%|███▌      | 9925/28080 [19:37:07<36:14:31,  7.19s/it]
 35%|███▌      | 9926/28080 [19:37:14<36:04:27,  7.15s/it]
                                                          
{'loss': 0.6372, 'learning_rate': 0.0003749000968788777, 'epoch': 4.24}

 35%|███▌      | 9926/28080 [19:37:14<36:04:27,  7.15s/it]
 35%|███▌      | 9927/28080 [19:37:21<35:58:46,  7.14s/it]
                                                          
{'loss': 0.6247, 'learning_rate': 0.00037487511694359906, 'epoch': 4.24}

 35%|███▌      | 9927/28080 [19:37:21<35:58:46,  7.14s/it]
 35%|███▌      | 9928/28080 [19:37:28<36:02:01,  7.15s/it]
                                                          
{'loss': 0.6281, 'learning_rate': 0.00037485013534698577, 'epoch': 4.24}

 35%|███▌      | 9928/28080 [19:37:28<36:02:01,  7.15s/it]
 35%|███▌      | 9929/28080 [19:37:35<35:48:28,  7.10s/it]
                                                          
{'loss': 0.6198, 'learning_rate': 0.00037482515208937025, 'epoch': 4.24}

 35%|███▌      | 9929/28080 [19:37:35<35:48:28,  7.10s/it]
 35%|███▌      | 9930/28080 [19:37:43<35:56:39,  7.13s/it]
                                                          
{'loss': 0.6157, 'learning_rate': 0.0003748001671710848, 'epoch': 4.24}

 35%|███▌      | 9930/28080 [19:37:43<35:56:39,  7.13s/it]
 35%|███▌      | 9931/28080 [19:37:50<35:59:49,  7.14s/it]
                                                          
{'loss': 0.6138, 'learning_rate': 0.000374775180592462, 'epoch': 4.24}

 35%|███▌      | 9931/28080 [19:37:50<35:59:49,  7.14s/it]
 35%|███▌      | 9932/28080 [19:37:57<35:56:47,  7.13s/it]
                                                          
{'loss': 0.6243, 'learning_rate': 0.000374750192353834, 'epoch': 4.24}

 35%|███▌      | 9932/28080 [19:37:57<35:56:47,  7.13s/it]
 35%|███▌      | 9933/28080 [19:38:04<35:59:45,  7.14s/it]
                                                          
{'loss': 0.6255, 'learning_rate': 0.0003747252024555335, 'epoch': 4.24}

 35%|███▌      | 9933/28080 [19:38:04<35:59:45,  7.14s/it]
 35%|███▌      | 9934/28080 [19:38:11<35:54:52,  7.13s/it]
                                                          
{'loss': 0.6278, 'learning_rate': 0.0003747002108978928, 'epoch': 4.24}

 35%|███▌      | 9934/28080 [19:38:11<35:54:52,  7.13s/it]
 35%|███▌      | 9935/28080 [19:38:18<36:01:11,  7.15s/it]
                                                          
{'loss': 0.6084, 'learning_rate': 0.00037467521768124444, 'epoch': 4.24}

 35%|███▌      | 9935/28080 [19:38:18<36:01:11,  7.15s/it]
 35%|███▌      | 9936/28080 [19:38:26<36:02:59,  7.15s/it]
                                                          
{'loss': 0.6146, 'learning_rate': 0.000374650222805921, 'epoch': 4.24}

 35%|███▌      | 9936/28080 [19:38:26<36:02:59,  7.15s/it]
 35%|███▌      | 9937/28080 [19:38:33<35:54:35,  7.13s/it]
                                                          
{'loss': 0.6306, 'learning_rate': 0.0003746252262722548, 'epoch': 4.24}

 35%|███▌      | 9937/28080 [19:38:33<35:54:35,  7.13s/it]
 35%|███▌      | 9938/28080 [19:38:40<36:00:03,  7.14s/it]
                                                          
{'loss': 0.6269, 'learning_rate': 0.0003746002280805787, 'epoch': 4.25}

 35%|███▌      | 9938/28080 [19:38:40<36:00:03,  7.14s/it]
 35%|███▌      | 9939/28080 [19:38:47<35:55:59,  7.13s/it]
                                                          
{'loss': 0.6322, 'learning_rate': 0.00037457522823122497, 'epoch': 4.25}

 35%|███▌      | 9939/28080 [19:38:47<35:55:59,  7.13s/it]
 35%|███▌      | 9940/28080 [19:38:54<36:00:36,  7.15s/it]
                                                          
{'loss': 0.6255, 'learning_rate': 0.00037455022672452644, 'epoch': 4.25}

 35%|███▌      | 9940/28080 [19:38:54<36:00:36,  7.15s/it]
 35%|███▌      | 9941/28080 [19:39:01<36:05:11,  7.16s/it]
                                                          
{'loss': 0.6318, 'learning_rate': 0.0003745252235608156, 'epoch': 4.25}

 35%|███▌      | 9941/28080 [19:39:01<36:05:11,  7.16s/it]
 35%|███▌      | 9942/28080 [19:39:08<36:00:00,  7.15s/it]
                                                          
{'loss': 0.6219, 'learning_rate': 0.0003745002187404251, 'epoch': 4.25}

 35%|███▌      | 9942/28080 [19:39:08<36:00:00,  7.15s/it]
 35%|███▌      | 9943/28080 [19:39:16<35:57:35,  7.14s/it]
                                                          
{'loss': 0.6264, 'learning_rate': 0.0003744752122636877, 'epoch': 4.25}

 35%|███▌      | 9943/28080 [19:39:16<35:57:35,  7.14s/it]
 35%|███▌      | 9944/28080 [19:39:23<35:59:27,  7.14s/it]
                                                          
{'loss': 0.6244, 'learning_rate': 0.00037445020413093597, 'epoch': 4.25}

 35%|███▌      | 9944/28080 [19:39:23<35:59:27,  7.14s/it]
 35%|███▌      | 9945/28080 [19:39:30<35:58:01,  7.14s/it]
                                                          
{'loss': 0.6405, 'learning_rate': 0.00037442519434250266, 'epoch': 4.25}

 35%|███▌      | 9945/28080 [19:39:30<35:58:01,  7.14s/it]
 35%|███▌      | 9946/28080 [19:39:37<35:59:14,  7.14s/it]
                                                          
{'loss': 0.6469, 'learning_rate': 0.00037440018289872047, 'epoch': 4.25}

 35%|███▌      | 9946/28080 [19:39:37<35:59:14,  7.14s/it]
 35%|███▌      | 9947/28080 [19:39:44<35:59:12,  7.14s/it]
                                                          
{'loss': 0.626, 'learning_rate': 0.0003743751697999222, 'epoch': 4.25}

 35%|███▌      | 9947/28080 [19:39:44<35:59:12,  7.14s/it]
 35%|███▌      | 9948/28080 [19:39:51<36:01:58,  7.15s/it]
                                                          
{'loss': 0.6233, 'learning_rate': 0.00037435015504644066, 'epoch': 4.25}

 35%|███▌      | 9948/28080 [19:39:51<36:01:58,  7.15s/it]
 35%|███▌      | 9949/28080 [19:39:58<35:58:41,  7.14s/it]
                                                          
{'loss': 0.6232, 'learning_rate': 0.0003743251386386085, 'epoch': 4.25}

 35%|███▌      | 9949/28080 [19:39:58<35:58:41,  7.14s/it]
 35%|███▌      | 9950/28080 [19:40:06<36:02:05,  7.16s/it]
                                                          
{'loss': 0.6316, 'learning_rate': 0.0003743001205767587, 'epoch': 4.25}

 35%|███▌      | 9950/28080 [19:40:06<36:02:05,  7.16s/it]
 35%|███▌      | 9951/28080 [19:40:13<35:54:36,  7.13s/it]
                                                          
{'loss': 0.6199, 'learning_rate': 0.000374275100861224, 'epoch': 4.25}

 35%|███▌      | 9951/28080 [19:40:13<35:54:36,  7.13s/it]
 35%|███▌      | 9952/28080 [19:40:20<35:58:00,  7.14s/it]
                                                          
{'loss': 0.6108, 'learning_rate': 0.00037425007949233737, 'epoch': 4.25}

 35%|███▌      | 9952/28080 [19:40:20<35:58:00,  7.14s/it]
 35%|███▌      | 9953/28080 [19:40:27<36:03:19,  7.16s/it]
                                                          
{'loss': 0.6118, 'learning_rate': 0.00037422505647043147, 'epoch': 4.25}

 35%|███▌      | 9953/28080 [19:40:27<36:03:19,  7.16s/it]
 35%|███▌      | 9954/28080 [19:40:34<36:03:36,  7.16s/it]
                                                          
{'loss': 0.6348, 'learning_rate': 0.0003742000317958394, 'epoch': 4.25}

 35%|███▌      | 9954/28080 [19:40:34<36:03:36,  7.16s/it]
 35%|███▌      | 9955/28080 [19:40:41<35:55:13,  7.13s/it]
                                                          
{'loss': 0.6288, 'learning_rate': 0.0003741750054688941, 'epoch': 4.25}

 35%|███▌      | 9955/28080 [19:40:41<35:55:13,  7.13s/it]
 35%|███▌      | 9956/28080 [19:40:48<36:02:56,  7.16s/it]
                                                          
{'loss': 0.609, 'learning_rate': 0.0003741499774899284, 'epoch': 4.25}

 35%|███▌      | 9956/28080 [19:40:48<36:02:56,  7.16s/it]
 35%|███▌      | 9957/28080 [19:40:56<36:01:09,  7.15s/it]
                                                          
{'loss': 0.6077, 'learning_rate': 0.0003741249478592754, 'epoch': 4.25}

 35%|███▌      | 9957/28080 [19:40:56<36:01:09,  7.15s/it]
 35%|███▌      | 9958/28080 [19:41:03<35:58:32,  7.15s/it]
                                                          
{'loss': 0.6486, 'learning_rate': 0.00037409991657726794, 'epoch': 4.25}

 35%|███▌      | 9958/28080 [19:41:03<35:58:32,  7.15s/it]
 35%|███▌      | 9959/28080 [19:41:10<36:02:55,  7.16s/it]
                                                          
{'loss': 0.6435, 'learning_rate': 0.0003740748836442391, 'epoch': 4.25}

 35%|███▌      | 9959/28080 [19:41:10<36:02:55,  7.16s/it]
 35%|███▌      | 9960/28080 [19:41:17<35:57:19,  7.14s/it]
                                                          
{'loss': 0.6172, 'learning_rate': 0.00037404984906052203, 'epoch': 4.25}

 35%|███▌      | 9960/28080 [19:41:17<35:57:19,  7.14s/it]
 35%|███▌      | 9961/28080 [19:41:24<35:57:58,  7.15s/it]
                                                          
{'loss': 0.6338, 'learning_rate': 0.00037402481282644963, 'epoch': 4.26}

 35%|███▌      | 9961/28080 [19:41:24<35:57:58,  7.15s/it]
 35%|███▌      | 9962/28080 [19:41:31<36:00:17,  7.15s/it]
                                                          
{'loss': 0.6324, 'learning_rate': 0.00037399977494235505, 'epoch': 4.26}

 35%|███▌      | 9962/28080 [19:41:31<36:00:17,  7.15s/it]
 35%|███▌      | 9963/28080 [19:41:38<35:50:48,  7.12s/it]
                                                          
{'loss': 0.6208, 'learning_rate': 0.00037397473540857134, 'epoch': 4.26}

 35%|███▌      | 9963/28080 [19:41:38<35:50:48,  7.12s/it]
 35%|███▌      | 9964/28080 [19:41:45<35:47:09,  7.11s/it]
                                                          
{'loss': 0.6381, 'learning_rate': 0.0003739496942254318, 'epoch': 4.26}

 35%|███▌      | 9964/28080 [19:41:46<35:47:09,  7.11s/it]
 35%|███▌      | 9965/28080 [19:41:53<35:49:00,  7.12s/it]
                                                          
{'loss': 0.6306, 'learning_rate': 0.0003739246513932694, 'epoch': 4.26}

 35%|███▌      | 9965/28080 [19:41:53<35:49:00,  7.12s/it]
 35%|███▌      | 9966/28080 [19:42:00<35:57:49,  7.15s/it]
                                                          
{'loss': 0.6101, 'learning_rate': 0.00037389960691241726, 'epoch': 4.26}

 35%|███▌      | 9966/28080 [19:42:00<35:57:49,  7.15s/it]
 35%|███▌      | 9967/28080 [19:42:07<36:02:13,  7.16s/it]
                                                          
{'loss': 0.6539, 'learning_rate': 0.0003738745607832088, 'epoch': 4.26}

 35%|███▌      | 9967/28080 [19:42:07<36:02:13,  7.16s/it]
 35%|███▌      | 9968/28080 [19:42:14<36:08:43,  7.18s/it]
                                                          
{'loss': 0.6311, 'learning_rate': 0.00037384951300597705, 'epoch': 4.26}

 35%|███▌      | 9968/28080 [19:42:14<36:08:43,  7.18s/it]
 36%|███▌      | 9969/28080 [19:42:21<36:07:33,  7.18s/it]
                                                          
{'loss': 0.6425, 'learning_rate': 0.0003738244635810553, 'epoch': 4.26}

 36%|███▌      | 9969/28080 [19:42:21<36:07:33,  7.18s/it]
 36%|███▌      | 9970/28080 [19:42:29<36:11:25,  7.19s/it]
                                                          
{'loss': 0.6144, 'learning_rate': 0.00037379941250877683, 'epoch': 4.26}

 36%|███▌      | 9970/28080 [19:42:29<36:11:25,  7.19s/it]
 36%|███▌      | 9971/28080 [19:42:36<36:04:00,  7.17s/it]
                                                          
{'loss': 0.6289, 'learning_rate': 0.0003737743597894748, 'epoch': 4.26}

 36%|███▌      | 9971/28080 [19:42:36<36:04:00,  7.17s/it]
 36%|███▌      | 9972/28080 [19:42:43<35:59:03,  7.15s/it]
                                                          
{'loss': 0.6418, 'learning_rate': 0.0003737493054234827, 'epoch': 4.26}

 36%|███▌      | 9972/28080 [19:42:43<35:59:03,  7.15s/it]
 36%|███▌      | 9973/28080 [19:42:50<35:48:22,  7.12s/it]
                                                          
{'loss': 0.6242, 'learning_rate': 0.0003737242494111337, 'epoch': 4.26}

 36%|███▌      | 9973/28080 [19:42:50<35:48:22,  7.12s/it]
 36%|███▌      | 9974/28080 [19:42:57<35:52:10,  7.13s/it]
                                                          
{'loss': 0.6267, 'learning_rate': 0.00037369919175276125, 'epoch': 4.26}

 36%|███▌      | 9974/28080 [19:42:57<35:52:10,  7.13s/it]
 36%|███▌      | 9975/28080 [19:43:04<35:50:37,  7.13s/it]
                                                          
{'loss': 0.623, 'learning_rate': 0.00037367413244869866, 'epoch': 4.26}

 36%|███▌      | 9975/28080 [19:43:04<35:50:37,  7.13s/it]
 36%|███▌      | 9976/28080 [19:43:11<35:44:56,  7.11s/it]
                                                          
{'loss': 0.6293, 'learning_rate': 0.0003736490714992793, 'epoch': 4.26}

 36%|███▌      | 9976/28080 [19:43:11<35:44:56,  7.11s/it]
 36%|███▌      | 9977/28080 [19:43:18<35:51:43,  7.13s/it]
                                                          
{'loss': 0.6398, 'learning_rate': 0.0003736240089048366, 'epoch': 4.26}

 36%|███▌      | 9977/28080 [19:43:18<35:51:43,  7.13s/it]
 36%|███▌      | 9978/28080 [19:43:26<35:49:33,  7.12s/it]
                                                          
{'loss': 0.6283, 'learning_rate': 0.000373598944665704, 'epoch': 4.26}

 36%|███▌      | 9978/28080 [19:43:26<35:49:33,  7.12s/it]
 36%|███▌      | 9979/28080 [19:43:33<36:05:32,  7.18s/it]
                                                          
{'loss': 0.6324, 'learning_rate': 0.000373573878782215, 'epoch': 4.26}

 36%|███▌      | 9979/28080 [19:43:33<36:05:32,  7.18s/it]
 36%|███▌      | 9980/28080 [19:43:40<36:08:48,  7.19s/it]
                                                          
{'loss': 0.6119, 'learning_rate': 0.000373548811254703, 'epoch': 4.26}

 36%|███▌      | 9980/28080 [19:43:40<36:08:48,  7.19s/it]
 36%|███▌      | 9981/28080 [19:43:47<35:56:03,  7.15s/it]
                                                          
{'loss': 0.6345, 'learning_rate': 0.0003735237420835015, 'epoch': 4.26}

 36%|███▌      | 9981/28080 [19:43:47<35:56:03,  7.15s/it]
 36%|███▌      | 9982/28080 [19:43:54<35:57:49,  7.15s/it]
                                                          
{'loss': 0.6085, 'learning_rate': 0.000373498671268944, 'epoch': 4.26}

 36%|███▌      | 9982/28080 [19:43:54<35:57:49,  7.15s/it]
 36%|███▌      | 9983/28080 [19:44:02<36:02:46,  7.17s/it]
                                                          
{'loss': 0.6249, 'learning_rate': 0.0003734735988113642, 'epoch': 4.26}

 36%|███▌      | 9983/28080 [19:44:02<36:02:46,  7.17s/it]
 36%|███▌      | 9984/28080 [19:44:09<36:00:26,  7.16s/it]
                                                          
{'loss': 0.6503, 'learning_rate': 0.00037344852471109545, 'epoch': 4.27}

 36%|███▌      | 9984/28080 [19:44:09<36:00:26,  7.16s/it]
 36%|███▌      | 9985/28080 [19:44:16<35:58:37,  7.16s/it]
                                                          
{'loss': 0.6411, 'learning_rate': 0.00037342344896847146, 'epoch': 4.27}

 36%|███▌      | 9985/28080 [19:44:16<35:58:37,  7.16s/it]
 36%|███▌      | 9986/28080 [19:44:23<35:58:55,  7.16s/it]
                                                          
{'loss': 0.6224, 'learning_rate': 0.0003733983715838258, 'epoch': 4.27}

 36%|███▌      | 9986/28080 [19:44:23<35:58:55,  7.16s/it]
 36%|███▌      | 9987/28080 [19:44:30<35:50:18,  7.13s/it]
                                                          
{'loss': 0.6214, 'learning_rate': 0.0003733732925574922, 'epoch': 4.27}

 36%|███▌      | 9987/28080 [19:44:30<35:50:18,  7.13s/it]
 36%|███▌      | 9988/28080 [19:44:37<35:39:58,  7.10s/it]
                                                          
{'loss': 0.6348, 'learning_rate': 0.00037334821188980417, 'epoch': 4.27}

 36%|███▌      | 9988/28080 [19:44:37<35:39:58,  7.10s/it]
 36%|███▌      | 9989/28080 [19:44:44<35:45:56,  7.12s/it]
                                                          
{'loss': 0.644, 'learning_rate': 0.00037332312958109537, 'epoch': 4.27}

 36%|███▌      | 9989/28080 [19:44:44<35:45:56,  7.12s/it]
 36%|███▌      | 9990/28080 [19:44:51<35:41:26,  7.10s/it]
                                                          
{'loss': 0.6233, 'learning_rate': 0.0003732980456316996, 'epoch': 4.27}

 36%|███▌      | 9990/28080 [19:44:51<35:41:26,  7.10s/it]
 36%|███▌      | 9991/28080 [19:44:58<35:39:32,  7.10s/it]
                                                          
{'loss': 0.6189, 'learning_rate': 0.0003732729600419506, 'epoch': 4.27}

 36%|███▌      | 9991/28080 [19:44:58<35:39:32,  7.10s/it]
 36%|███▌      | 9992/28080 [19:45:06<35:42:25,  7.11s/it]
                                                          
{'loss': 0.6277, 'learning_rate': 0.00037324787281218185, 'epoch': 4.27}

 36%|███▌      | 9992/28080 [19:45:06<35:42:25,  7.11s/it]
 36%|███▌      | 9993/28080 [19:45:13<35:46:47,  7.12s/it]
                                                          
{'loss': 0.634, 'learning_rate': 0.00037322278394272756, 'epoch': 4.27}

 36%|███▌      | 9993/28080 [19:45:13<35:46:47,  7.12s/it]
 36%|███▌      | 9994/28080 [19:45:20<35:50:49,  7.14s/it]
                                                          
{'loss': 0.6256, 'learning_rate': 0.0003731976934339211, 'epoch': 4.27}

 36%|███▌      | 9994/28080 [19:45:20<35:50:49,  7.14s/it]
 36%|███▌      | 9995/28080 [19:45:27<35:53:29,  7.14s/it]
                                                          
{'loss': 0.6232, 'learning_rate': 0.00037317260128609645, 'epoch': 4.27}

 36%|███▌      | 9995/28080 [19:45:27<35:53:29,  7.14s/it]
 36%|███▌      | 9996/28080 [19:45:34<35:42:23,  7.11s/it]
                                                          
{'loss': 0.635, 'learning_rate': 0.0003731475074995874, 'epoch': 4.27}

 36%|███▌      | 9996/28080 [19:45:34<35:42:23,  7.11s/it]
 36%|███▌      | 9997/28080 [19:45:41<35:37:49,  7.09s/it]
                                                          
{'loss': 0.642, 'learning_rate': 0.00037312241207472773, 'epoch': 4.27}

 36%|███▌      | 9997/28080 [19:45:41<35:37:49,  7.09s/it]
 36%|███▌      | 9998/28080 [19:45:48<35:37:46,  7.09s/it]
                                                          
{'loss': 0.6354, 'learning_rate': 0.00037309731501185153, 'epoch': 4.27}

 36%|███▌      | 9998/28080 [19:45:48<35:37:46,  7.09s/it]
 36%|███▌      | 9999/28080 [19:45:55<35:40:49,  7.10s/it]
                                                          
{'loss': 0.6157, 'learning_rate': 0.00037307221631129245, 'epoch': 4.27}

 36%|███▌      | 9999/28080 [19:45:55<35:40:49,  7.10s/it]
 36%|███▌      | 10000/28080 [19:46:02<35:38:21,  7.10s/it]
                                                           
{'loss': 0.62, 'learning_rate': 0.0003730471159733846, 'epoch': 4.27}

 36%|███▌      | 10000/28080 [19:46:02<35:38:21,  7.10s/it]
 36%|███▌      | 10001/28080 [19:46:09<35:18:18,  7.03s/it]
                                                           
{'loss': 0.6479, 'learning_rate': 0.0003730220139984617, 'epoch': 4.27}

 36%|███▌      | 10001/28080 [19:46:09<35:18:18,  7.03s/it]
 36%|███▌      | 10002/28080 [19:46:16<35:26:40,  7.06s/it]
                                                           
{'loss': 0.6288, 'learning_rate': 0.0003729969103868578, 'epoch': 4.27}

 36%|███▌      | 10002/28080 [19:46:16<35:26:40,  7.06s/it]
 36%|███▌      | 10003/28080 [19:46:23<35:31:04,  7.07s/it]
                                                           
{'loss': 0.6219, 'learning_rate': 0.000372971805138907, 'epoch': 4.27}

 36%|███▌      | 10003/28080 [19:46:23<35:31:04,  7.07s/it]
 36%|███▌      | 10004/28080 [19:46:31<35:34:56,  7.09s/it]
                                                           
{'loss': 0.6169, 'learning_rate': 0.0003729466982549431, 'epoch': 4.27}

 36%|███▌      | 10004/28080 [19:46:31<35:34:56,  7.09s/it]
 36%|███▌      | 10005/28080 [19:46:38<35:33:43,  7.08s/it]
                                                           
{'loss': 0.6231, 'learning_rate': 0.0003729215897353003, 'epoch': 4.27}

 36%|███▌      | 10005/28080 [19:46:38<35:33:43,  7.08s/it]
 36%|███▌      | 10006/28080 [19:46:45<35:26:46,  7.06s/it]
                                                           
{'loss': 0.6406, 'learning_rate': 0.00037289647958031253, 'epoch': 4.27}

 36%|███▌      | 10006/28080 [19:46:45<35:26:46,  7.06s/it]
 36%|███▌      | 10007/28080 [19:46:52<35:33:55,  7.08s/it]
                                                           
{'loss': 0.6168, 'learning_rate': 0.00037287136779031387, 'epoch': 4.27}

 36%|███▌      | 10007/28080 [19:46:52<35:33:55,  7.08s/it]
 36%|███▌      | 10008/28080 [19:46:59<35:42:59,  7.11s/it]
                                                           
{'loss': 0.5942, 'learning_rate': 0.00037284625436563844, 'epoch': 4.28}

 36%|███▌      | 10008/28080 [19:46:59<35:42:59,  7.11s/it]
 36%|███▌      | 10009/28080 [19:47:06<35:40:27,  7.11s/it]
                                                           
{'loss': 0.6302, 'learning_rate': 0.0003728211393066203, 'epoch': 4.28}

 36%|███▌      | 10009/28080 [19:47:06<35:40:27,  7.11s/it]
 36%|███▌      | 10010/28080 [19:47:13<35:44:34,  7.12s/it]
                                                           
{'loss': 0.6162, 'learning_rate': 0.00037279602261359367, 'epoch': 4.28}

 36%|███▌      | 10010/28080 [19:47:13<35:44:34,  7.12s/it]
 36%|███▌      | 10011/28080 [19:47:20<35:43:43,  7.12s/it]
                                                           
{'loss': 0.6394, 'learning_rate': 0.00037277090428689257, 'epoch': 4.28}

 36%|███▌      | 10011/28080 [19:47:20<35:43:43,  7.12s/it]
 36%|███▌      | 10012/28080 [19:47:27<35:39:48,  7.11s/it]
                                                           
{'loss': 0.66, 'learning_rate': 0.0003727457843268513, 'epoch': 4.28}

 36%|███▌      | 10012/28080 [19:47:27<35:39:48,  7.11s/it]
 36%|███▌      | 10013/28080 [19:47:35<35:37:22,  7.10s/it]
                                                           
{'loss': 0.6341, 'learning_rate': 0.000372720662733804, 'epoch': 4.28}

 36%|███▌      | 10013/28080 [19:47:35<35:37:22,  7.10s/it]
 36%|███▌      | 10014/28080 [19:47:42<35:36:59,  7.10s/it]
                                                           
{'loss': 0.6341, 'learning_rate': 0.0003726955395080849, 'epoch': 4.28}

 36%|███▌      | 10014/28080 [19:47:42<35:36:59,  7.10s/it]
 36%|███▌      | 10015/28080 [19:47:49<35:37:21,  7.10s/it]
                                                           
{'loss': 0.6258, 'learning_rate': 0.0003726704146500281, 'epoch': 4.28}

 36%|███▌      | 10015/28080 [19:47:49<35:37:21,  7.10s/it]
 36%|███▌      | 10016/28080 [19:47:56<35:42:29,  7.12s/it]
                                                           
{'loss': 0.6317, 'learning_rate': 0.00037264528815996806, 'epoch': 4.28}

 36%|███▌      | 10016/28080 [19:47:56<35:42:29,  7.12s/it]
 36%|███▌      | 10017/28080 [19:48:03<35:46:35,  7.13s/it]
                                                           
{'loss': 0.6259, 'learning_rate': 0.00037262016003823906, 'epoch': 4.28}

 36%|███▌      | 10017/28080 [19:48:03<35:46:35,  7.13s/it]
 36%|███▌      | 10018/28080 [19:48:10<35:42:15,  7.12s/it]
                                                           
{'loss': 0.6401, 'learning_rate': 0.0003725950302851753, 'epoch': 4.28}

 36%|███▌      | 10018/28080 [19:48:10<35:42:15,  7.12s/it]
 36%|███▌      | 10019/28080 [19:48:17<35:37:28,  7.10s/it]
                                                           
{'loss': 0.6371, 'learning_rate': 0.00037256989890111105, 'epoch': 4.28}

 36%|███▌      | 10019/28080 [19:48:17<35:37:28,  7.10s/it]
 36%|███▌      | 10020/28080 [19:48:24<35:26:24,  7.06s/it]
                                                           
{'loss': 0.6513, 'learning_rate': 0.00037254476588638083, 'epoch': 4.28}

 36%|███▌      | 10020/28080 [19:48:24<35:26:24,  7.06s/it]
 36%|███▌      | 10021/28080 [19:48:31<35:23:30,  7.06s/it]
                                                           
{'loss': 0.6307, 'learning_rate': 0.0003725196312413189, 'epoch': 4.28}

 36%|███▌      | 10021/28080 [19:48:31<35:23:30,  7.06s/it]
 36%|███▌      | 10022/28080 [19:48:38<35:28:15,  7.07s/it]
                                                           
{'loss': 0.6172, 'learning_rate': 0.00037249449496625967, 'epoch': 4.28}

 36%|███▌      | 10022/28080 [19:48:38<35:28:15,  7.07s/it]
 36%|███▌      | 10023/28080 [19:48:45<35:22:14,  7.05s/it]
                                                           
{'loss': 0.6308, 'learning_rate': 0.0003724693570615375, 'epoch': 4.28}

 36%|███▌      | 10023/28080 [19:48:45<35:22:14,  7.05s/it]
 36%|███▌      | 10024/28080 [19:48:52<35:32:24,  7.09s/it]
                                                           
{'loss': 0.6534, 'learning_rate': 0.00037244421752748695, 'epoch': 4.28}

 36%|███▌      | 10024/28080 [19:48:52<35:32:24,  7.09s/it]
 36%|███▌      | 10025/28080 [19:48:59<35:25:17,  7.06s/it]
                                                           
{'loss': 0.6247, 'learning_rate': 0.0003724190763644424, 'epoch': 4.28}

 36%|███▌      | 10025/28080 [19:49:00<35:25:17,  7.06s/it]
 36%|███▌      | 10026/28080 [19:49:07<35:24:10,  7.06s/it]
                                                           
{'loss': 0.6359, 'learning_rate': 0.00037239393357273826, 'epoch': 4.28}

 36%|███▌      | 10026/28080 [19:49:07<35:24:10,  7.06s/it]
 36%|███▌      | 10027/28080 [19:49:14<35:33:45,  7.09s/it]
                                                           
{'loss': 0.6408, 'learning_rate': 0.0003723687891527092, 'epoch': 4.28}

 36%|███▌      | 10027/28080 [19:49:14<35:33:45,  7.09s/it]
 36%|███▌      | 10028/28080 [19:49:21<35:39:12,  7.11s/it]
                                                           
{'loss': 0.6232, 'learning_rate': 0.0003723436431046896, 'epoch': 4.28}

 36%|███▌      | 10028/28080 [19:49:21<35:39:12,  7.11s/it]
 36%|███▌      | 10029/28080 [19:49:28<35:39:20,  7.11s/it]
                                                           
{'loss': 0.6234, 'learning_rate': 0.000372318495429014, 'epoch': 4.28}

 36%|███▌      | 10029/28080 [19:49:28<35:39:20,  7.11s/it]
 36%|███▌      | 10030/28080 [19:49:35<35:44:04,  7.13s/it]
                                                           
{'loss': 0.6401, 'learning_rate': 0.00037229334612601706, 'epoch': 4.28}

 36%|███▌      | 10030/28080 [19:49:35<35:44:04,  7.13s/it]
 36%|███▌      | 10031/28080 [19:49:42<35:43:55,  7.13s/it]
                                                           
{'loss': 0.6218, 'learning_rate': 0.0003722681951960333, 'epoch': 4.29}

 36%|███▌      | 10031/28080 [19:49:42<35:43:55,  7.13s/it]
 36%|███▌      | 10032/28080 [19:49:49<35:41:28,  7.12s/it]
                                                           
{'loss': 0.6219, 'learning_rate': 0.00037224304263939735, 'epoch': 4.29}

 36%|███▌      | 10032/28080 [19:49:49<35:41:28,  7.12s/it]
 36%|███▌      | 10033/28080 [19:49:56<35:37:48,  7.11s/it]
                                                           
{'loss': 0.6589, 'learning_rate': 0.00037221788845644377, 'epoch': 4.29}

 36%|███▌      | 10033/28080 [19:49:56<35:37:48,  7.11s/it]
 36%|███▌      | 10034/28080 [19:50:03<35:30:10,  7.08s/it]
                                                           
{'loss': 0.6402, 'learning_rate': 0.00037219273264750736, 'epoch': 4.29}

 36%|███▌      | 10034/28080 [19:50:03<35:30:10,  7.08s/it]
 36%|███▌      | 10035/28080 [19:50:11<35:38:03,  7.11s/it]
                                                           
{'loss': 0.6204, 'learning_rate': 0.00037216757521292267, 'epoch': 4.29}

 36%|███▌      | 10035/28080 [19:50:11<35:38:03,  7.11s/it]
 36%|███▌      | 10036/28080 [19:50:18<35:33:13,  7.09s/it]
                                                           
{'loss': 0.6003, 'learning_rate': 0.0003721424161530244, 'epoch': 4.29}

 36%|███▌      | 10036/28080 [19:50:18<35:33:13,  7.09s/it]
 36%|███▌      | 10037/28080 [19:50:25<35:36:30,  7.10s/it]
                                                           
{'loss': 0.613, 'learning_rate': 0.0003721172554681473, 'epoch': 4.29}

 36%|███▌      | 10037/28080 [19:50:25<35:36:30,  7.10s/it]
 36%|███▌      | 10038/28080 [19:50:32<35:27:10,  7.07s/it]
                                                           
{'loss': 0.635, 'learning_rate': 0.00037209209315862613, 'epoch': 4.29}

 36%|███▌      | 10038/28080 [19:50:32<35:27:10,  7.07s/it]
 36%|███▌      | 10039/28080 [19:50:39<35:24:04,  7.06s/it]
                                                           
{'loss': 0.6407, 'learning_rate': 0.0003720669292247956, 'epoch': 4.29}

 36%|███▌      | 10039/28080 [19:50:39<35:24:04,  7.06s/it]
 36%|███▌      | 10040/28080 [19:50:46<35:25:37,  7.07s/it]
                                                           
{'loss': 0.6301, 'learning_rate': 0.0003720417636669904, 'epoch': 4.29}

 36%|███▌      | 10040/28080 [19:50:46<35:25:37,  7.07s/it]
 36%|███▌      | 10041/28080 [19:50:53<35:27:40,  7.08s/it]
                                                           
{'loss': 0.6226, 'learning_rate': 0.0003720165964855456, 'epoch': 4.29}

 36%|███▌      | 10041/28080 [19:50:53<35:27:40,  7.08s/it]
 36%|███▌      | 10042/28080 [19:51:00<35:34:37,  7.10s/it]
                                                           
{'loss': 0.637, 'learning_rate': 0.00037199142768079574, 'epoch': 4.29}

 36%|███▌      | 10042/28080 [19:51:00<35:34:37,  7.10s/it]
 36%|███▌      | 10043/28080 [19:51:07<35:30:58,  7.09s/it]
                                                           
{'loss': 0.6052, 'learning_rate': 0.0003719662572530759, 'epoch': 4.29}

 36%|███▌      | 10043/28080 [19:51:07<35:30:58,  7.09s/it]
 36%|███▌      | 10044/28080 [19:51:14<35:30:35,  7.09s/it]
                                                           
{'loss': 0.6166, 'learning_rate': 0.0003719410852027208, 'epoch': 4.29}

 36%|███▌      | 10044/28080 [19:51:14<35:30:35,  7.09s/it]
 36%|███▌      | 10045/28080 [19:51:21<35:26:29,  7.07s/it]
                                                           
{'loss': 0.6177, 'learning_rate': 0.0003719159115300653, 'epoch': 4.29}

 36%|███▌      | 10045/28080 [19:51:21<35:26:29,  7.07s/it]
 36%|███▌      | 10046/28080 [19:51:29<35:28:36,  7.08s/it]
                                                           
{'loss': 0.5978, 'learning_rate': 0.00037189073623544445, 'epoch': 4.29}

 36%|███▌      | 10046/28080 [19:51:29<35:28:36,  7.08s/it]
 36%|███▌      | 10047/28080 [19:51:35<35:18:55,  7.05s/it]
                                                           
{'loss': 0.6283, 'learning_rate': 0.00037186555931919304, 'epoch': 4.29}

 36%|███▌      | 10047/28080 [19:51:35<35:18:55,  7.05s/it]
 36%|███▌      | 10048/28080 [19:51:43<35:22:36,  7.06s/it]
                                                           
{'loss': 0.65, 'learning_rate': 0.00037184038078164614, 'epoch': 4.29}

 36%|███▌      | 10048/28080 [19:51:43<35:22:36,  7.06s/it]
 36%|███▌      | 10049/28080 [19:51:50<35:21:49,  7.06s/it]
                                                           
{'loss': 0.6303, 'learning_rate': 0.00037181520062313855, 'epoch': 4.29}

 36%|███▌      | 10049/28080 [19:51:50<35:21:49,  7.06s/it]
 36%|███▌      | 10050/28080 [19:51:57<35:29:18,  7.09s/it]
                                                           
{'loss': 0.6245, 'learning_rate': 0.0003717900188440055, 'epoch': 4.29}

 36%|███▌      | 10050/28080 [19:51:57<35:29:18,  7.09s/it]
 36%|███▌      | 10051/28080 [19:52:04<35:33:07,  7.10s/it]
                                                           
{'loss': 0.6481, 'learning_rate': 0.00037176483544458186, 'epoch': 4.29}

 36%|███▌      | 10051/28080 [19:52:04<35:33:07,  7.10s/it]
 36%|███▌      | 10052/28080 [19:52:11<35:35:55,  7.11s/it]
                                                           
{'loss': 0.6272, 'learning_rate': 0.0003717396504252027, 'epoch': 4.29}

 36%|███▌      | 10052/28080 [19:52:11<35:35:55,  7.11s/it]
 36%|███▌      | 10053/28080 [19:52:18<35:38:56,  7.12s/it]
                                                           
{'loss': 0.6331, 'learning_rate': 0.0003717144637862031, 'epoch': 4.29}

 36%|███▌      | 10053/28080 [19:52:18<35:38:56,  7.12s/it]
 36%|███▌      | 10054/28080 [19:52:25<35:34:35,  7.11s/it]
                                                           
{'loss': 0.6303, 'learning_rate': 0.0003716892755279181, 'epoch': 4.29}

 36%|███▌      | 10054/28080 [19:52:25<35:34:35,  7.11s/it]
 36%|███▌      | 10055/28080 [19:52:32<35:37:24,  7.11s/it]
                                                           
{'loss': 0.6171, 'learning_rate': 0.0003716640856506829, 'epoch': 4.3}

 36%|███▌      | 10055/28080 [19:52:32<35:37:24,  7.11s/it]
 36%|███▌      | 10056/28080 [19:52:40<35:38:04,  7.12s/it]
                                                           
{'loss': 0.6181, 'learning_rate': 0.0003716388941548324, 'epoch': 4.3}

 36%|███▌      | 10056/28080 [19:52:40<35:38:04,  7.12s/it]
 36%|███▌      | 10057/28080 [19:52:47<35:36:46,  7.11s/it]
                                                           
{'loss': 0.6226, 'learning_rate': 0.000371613701040702, 'epoch': 4.3}

 36%|███▌      | 10057/28080 [19:52:47<35:36:46,  7.11s/it]
 36%|███▌      | 10058/28080 [19:52:54<35:28:25,  7.09s/it]
                                                           
{'loss': 0.6572, 'learning_rate': 0.00037158850630862676, 'epoch': 4.3}

 36%|███▌      | 10058/28080 [19:52:54<35:28:25,  7.09s/it]
 36%|███▌      | 10059/28080 [19:53:01<35:27:26,  7.08s/it]
                                                           
{'loss': 0.6325, 'learning_rate': 0.00037156330995894186, 'epoch': 4.3}

 36%|███▌      | 10059/28080 [19:53:01<35:27:26,  7.08s/it]
 36%|███▌      | 10060/28080 [19:53:08<35:36:42,  7.11s/it]
                                                           
{'loss': 0.6212, 'learning_rate': 0.0003715381119919826, 'epoch': 4.3}

 36%|███▌      | 10060/28080 [19:53:08<35:36:42,  7.11s/it]
 36%|███▌      | 10061/28080 [19:53:15<35:35:02,  7.11s/it]
                                                           
{'loss': 0.612, 'learning_rate': 0.00037151291240808404, 'epoch': 4.3}

 36%|███▌      | 10061/28080 [19:53:15<35:35:02,  7.11s/it]
 36%|███▌      | 10062/28080 [19:53:22<35:38:49,  7.12s/it]
                                                           
{'loss': 0.6191, 'learning_rate': 0.0003714877112075817, 'epoch': 4.3}

 36%|███▌      | 10062/28080 [19:53:22<35:38:49,  7.12s/it]
 36%|███▌      | 10063/28080 [19:53:29<35:28:20,  7.09s/it]
                                                           
{'loss': 0.6405, 'learning_rate': 0.00037146250839081054, 'epoch': 4.3}

 36%|███▌      | 10063/28080 [19:53:29<35:28:20,  7.09s/it]
 36%|███▌      | 10064/28080 [19:53:36<35:27:33,  7.09s/it]
                                                           
{'loss': 0.6196, 'learning_rate': 0.00037143730395810604, 'epoch': 4.3}

 36%|███▌      | 10064/28080 [19:53:36<35:27:33,  7.09s/it]
 36%|███▌      | 10065/28080 [19:53:43<35:36:46,  7.12s/it]
                                                           
{'loss': 0.6123, 'learning_rate': 0.00037141209790980353, 'epoch': 4.3}

 36%|███▌      | 10065/28080 [19:53:43<35:36:46,  7.12s/it]
 36%|███▌      | 10066/28080 [19:53:51<35:36:11,  7.12s/it]
                                                           
{'loss': 0.6084, 'learning_rate': 0.0003713868902462383, 'epoch': 4.3}

 36%|███▌      | 10066/28080 [19:53:51<35:36:11,  7.12s/it]
 36%|███▌      | 10067/28080 [19:53:58<35:37:22,  7.12s/it]
                                                           
{'loss': 0.6281, 'learning_rate': 0.0003713616809677457, 'epoch': 4.3}

 36%|███▌      | 10067/28080 [19:53:58<35:37:22,  7.12s/it]
 36%|███▌      | 10068/28080 [19:54:05<35:40:23,  7.13s/it]
                                                           
{'loss': 0.6254, 'learning_rate': 0.0003713364700746612, 'epoch': 4.3}

 36%|███▌      | 10068/28080 [19:54:05<35:40:23,  7.13s/it]
 36%|███▌      | 10069/28080 [19:54:12<35:34:49,  7.11s/it]
                                                           
{'loss': 0.6321, 'learning_rate': 0.0003713112575673201, 'epoch': 4.3}

 36%|███▌      | 10069/28080 [19:54:12<35:34:49,  7.11s/it]
 36%|███▌      | 10070/28080 [19:54:19<35:36:05,  7.12s/it]
                                                           
{'loss': 0.6314, 'learning_rate': 0.00037128604344605786, 'epoch': 4.3}

 36%|███▌      | 10070/28080 [19:54:19<35:36:05,  7.12s/it]
 36%|███▌      | 10071/28080 [19:54:26<35:31:58,  7.10s/it]
                                                           
{'loss': 0.618, 'learning_rate': 0.00037126082771120995, 'epoch': 4.3}

 36%|███▌      | 10071/28080 [19:54:26<35:31:58,  7.10s/it]
 36%|███▌      | 10072/28080 [19:54:33<35:38:23,  7.12s/it]
                                                           
{'loss': 0.6179, 'learning_rate': 0.0003712356103631118, 'epoch': 4.3}

 36%|███▌      | 10072/28080 [19:54:33<35:38:23,  7.12s/it]
 36%|███▌      | 10073/28080 [19:54:40<35:38:10,  7.12s/it]
                                                           
{'loss': 0.626, 'learning_rate': 0.00037121039140209896, 'epoch': 4.3}

 36%|███▌      | 10073/28080 [19:54:40<35:38:10,  7.12s/it]
 36%|███▌      | 10074/28080 [19:54:48<35:41:57,  7.14s/it]
                                                           
{'loss': 0.622, 'learning_rate': 0.00037118517082850684, 'epoch': 4.3}

 36%|███▌      | 10074/28080 [19:54:48<35:41:57,  7.14s/it]
 36%|███▌      | 10075/28080 [19:54:55<35:39:39,  7.13s/it]
                                                           
{'loss': 0.6173, 'learning_rate': 0.0003711599486426711, 'epoch': 4.3}

 36%|███▌      | 10075/28080 [19:54:55<35:39:39,  7.13s/it]
 36%|███▌      | 10076/28080 [19:55:02<35:35:25,  7.12s/it]
                                                           
{'loss': 0.6288, 'learning_rate': 0.0003711347248449272, 'epoch': 4.3}

 36%|███▌      | 10076/28080 [19:55:02<35:35:25,  7.12s/it]
 36%|███▌      | 10077/28080 [19:55:09<35:18:44,  7.06s/it]
                                                           
{'loss': 0.6587, 'learning_rate': 0.0003711094994356108, 'epoch': 4.3}

 36%|███▌      | 10077/28080 [19:55:09<35:18:44,  7.06s/it]
 36%|███▌      | 10078/28080 [19:55:16<35:19:39,  7.06s/it]
                                                           
{'loss': 0.6114, 'learning_rate': 0.00037108427241505746, 'epoch': 4.31}

 36%|███▌      | 10078/28080 [19:55:16<35:19:39,  7.06s/it]
 36%|███▌      | 10079/28080 [19:55:23<35:13:33,  7.04s/it]
                                                           
{'loss': 0.6424, 'learning_rate': 0.0003710590437836028, 'epoch': 4.31}

 36%|███▌      | 10079/28080 [19:55:23<35:13:33,  7.04s/it]
 36%|███▌      | 10080/28080 [19:55:30<35:13:58,  7.05s/it]
                                                           
{'loss': 0.6443, 'learning_rate': 0.0003710338135415824, 'epoch': 4.31}

 36%|███▌      | 10080/28080 [19:55:30<35:13:58,  7.05s/it]
 36%|███▌      | 10081/28080 [19:55:37<35:21:30,  7.07s/it]
                                                           
{'loss': 0.6368, 'learning_rate': 0.00037100858168933194, 'epoch': 4.31}

 36%|███▌      | 10081/28080 [19:55:37<35:21:30,  7.07s/it]
 36%|███▌      | 10082/28080 [19:55:44<35:28:22,  7.10s/it]
                                                           
{'loss': 0.6276, 'learning_rate': 0.00037098334822718723, 'epoch': 4.31}

 36%|███▌      | 10082/28080 [19:55:44<35:28:22,  7.10s/it]
 36%|███▌      | 10083/28080 [19:55:51<35:29:29,  7.10s/it]
                                                           
{'loss': 0.6161, 'learning_rate': 0.0003709581131554838, 'epoch': 4.31}

 36%|███▌      | 10083/28080 [19:55:51<35:29:29,  7.10s/it]
 36%|███▌      | 10084/28080 [19:55:58<35:27:27,  7.09s/it]
                                                           
{'loss': 0.6236, 'learning_rate': 0.0003709328764745575, 'epoch': 4.31}

 36%|███▌      | 10084/28080 [19:55:58<35:27:27,  7.09s/it]
 36%|███▌      | 10085/28080 [19:56:05<35:26:27,  7.09s/it]
                                                           
{'loss': 0.6432, 'learning_rate': 0.00037090763818474406, 'epoch': 4.31}

 36%|███▌      | 10085/28080 [19:56:05<35:26:27,  7.09s/it]
 36%|███▌      | 10086/28080 [19:56:12<35:22:40,  7.08s/it]
                                                           
{'loss': 0.6209, 'learning_rate': 0.0003708823982863792, 'epoch': 4.31}

 36%|███▌      | 10086/28080 [19:56:12<35:22:40,  7.08s/it]
 36%|███▌      | 10087/28080 [19:56:20<35:25:31,  7.09s/it]
                                                           
{'loss': 0.6345, 'learning_rate': 0.00037085715677979877, 'epoch': 4.31}

 36%|███▌      | 10087/28080 [19:56:20<35:25:31,  7.09s/it]
 36%|███▌      | 10088/28080 [19:56:27<35:24:22,  7.08s/it]
                                                           
{'loss': 0.6078, 'learning_rate': 0.0003708319136653385, 'epoch': 4.31}

 36%|███▌      | 10088/28080 [19:56:27<35:24:22,  7.08s/it]
 36%|███▌      | 10089/28080 [19:56:34<35:24:56,  7.09s/it]
                                                           
{'loss': 0.6044, 'learning_rate': 0.0003708066689433343, 'epoch': 4.31}

 36%|███▌      | 10089/28080 [19:56:34<35:24:56,  7.09s/it]
 36%|███▌      | 10090/28080 [19:56:41<35:23:34,  7.08s/it]
                                                           
{'loss': 0.6336, 'learning_rate': 0.00037078142261412196, 'epoch': 4.31}

 36%|███▌      | 10090/28080 [19:56:41<35:23:34,  7.08s/it]
 36%|███▌      | 10091/28080 [19:56:48<35:23:48,  7.08s/it]
                                                           
{'loss': 0.6165, 'learning_rate': 0.00037075617467803747, 'epoch': 4.31}

 36%|███▌      | 10091/28080 [19:56:48<35:23:48,  7.08s/it]
 36%|███▌      | 10092/28080 [19:56:55<35:27:17,  7.10s/it]
                                                           
{'loss': 0.6357, 'learning_rate': 0.0003707309251354166, 'epoch': 4.31}

 36%|███▌      | 10092/28080 [19:56:55<35:27:17,  7.10s/it]
 36%|███▌      | 10093/28080 [19:57:02<35:30:12,  7.11s/it]
                                                           
{'loss': 0.6386, 'learning_rate': 0.00037070567398659536, 'epoch': 4.31}

 36%|███▌      | 10093/28080 [19:57:02<35:30:12,  7.11s/it]
 36%|███▌      | 10094/28080 [19:57:09<35:32:45,  7.11s/it]
                                                           
{'loss': 0.6083, 'learning_rate': 0.0003706804212319097, 'epoch': 4.31}

 36%|███▌      | 10094/28080 [19:57:09<35:32:45,  7.11s/it]
 36%|███▌      | 10095/28080 [19:57:16<35:32:03,  7.11s/it]
                                                           
{'loss': 0.6157, 'learning_rate': 0.00037065516687169545, 'epoch': 4.31}

 36%|███▌      | 10095/28080 [19:57:16<35:32:03,  7.11s/it]
 36%|███▌      | 10096/28080 [19:57:24<35:35:24,  7.12s/it]
                                                           
{'loss': 0.6155, 'learning_rate': 0.00037062991090628874, 'epoch': 4.31}

 36%|███▌      | 10096/28080 [19:57:24<35:35:24,  7.12s/it]
 36%|███▌      | 10097/28080 [19:57:31<35:39:46,  7.14s/it]
                                                           
{'loss': 0.6314, 'learning_rate': 0.0003706046533360254, 'epoch': 4.31}

 36%|███▌      | 10097/28080 [19:57:31<35:39:46,  7.14s/it]
 36%|███▌      | 10098/28080 [19:57:38<35:35:58,  7.13s/it]
                                                           
{'loss': 0.6152, 'learning_rate': 0.00037057939416124163, 'epoch': 4.31}

 36%|███▌      | 10098/28080 [19:57:38<35:35:58,  7.13s/it]
 36%|███▌      | 10099/28080 [19:57:45<35:33:25,  7.12s/it]
                                                           
{'loss': 0.6181, 'learning_rate': 0.0003705541333822735, 'epoch': 4.31}

 36%|███▌      | 10099/28080 [19:57:45<35:33:25,  7.12s/it]
 36%|███▌      | 10100/28080 [19:57:52<35:27:17,  7.10s/it]
                                                           
{'loss': 0.62, 'learning_rate': 0.0003705288709994568, 'epoch': 4.31}

 36%|███▌      | 10100/28080 [19:57:52<35:27:17,  7.10s/it]
 36%|███▌      | 10101/28080 [19:57:59<35:28:57,  7.10s/it]
                                                           
{'loss': 0.632, 'learning_rate': 0.00037050360701312797, 'epoch': 4.32}

 36%|███▌      | 10101/28080 [19:57:59<35:28:57,  7.10s/it]
 36%|███▌      | 10102/28080 [19:58:06<35:31:50,  7.11s/it]
                                                           
{'loss': 0.6236, 'learning_rate': 0.0003704783414236229, 'epoch': 4.32}

 36%|███▌      | 10102/28080 [19:58:06<35:31:50,  7.11s/it]
 36%|███▌      | 10103/28080 [19:58:13<35:24:58,  7.09s/it]
                                                           
{'loss': 0.611, 'learning_rate': 0.00037045307423127783, 'epoch': 4.32}

 36%|███▌      | 10103/28080 [19:58:13<35:24:58,  7.09s/it]
 36%|███▌      | 10104/28080 [19:58:20<35:29:29,  7.11s/it]
                                                           
{'loss': 0.6342, 'learning_rate': 0.00037042780543642887, 'epoch': 4.32}

 36%|███▌      | 10104/28080 [19:58:20<35:29:29,  7.11s/it]
 36%|███▌      | 10105/28080 [19:58:27<35:29:06,  7.11s/it]
                                                           
{'loss': 0.6451, 'learning_rate': 0.0003704025350394121, 'epoch': 4.32}

 36%|███▌      | 10105/28080 [19:58:27<35:29:06,  7.11s/it]
 36%|███▌      | 10106/28080 [19:58:35<35:28:00,  7.10s/it]
                                                           
{'loss': 0.6453, 'learning_rate': 0.00037037726304056396, 'epoch': 4.32}

 36%|███▌      | 10106/28080 [19:58:35<35:28:00,  7.10s/it]
 36%|███▌      | 10107/28080 [19:58:42<35:32:41,  7.12s/it]
                                                           
{'loss': 0.6276, 'learning_rate': 0.0003703519894402204, 'epoch': 4.32}

 36%|███▌      | 10107/28080 [19:58:42<35:32:41,  7.12s/it]
 36%|███▌      | 10108/28080 [19:58:49<35:30:50,  7.11s/it]
                                                           
{'loss': 0.6071, 'learning_rate': 0.0003703267142387179, 'epoch': 4.32}

 36%|███▌      | 10108/28080 [19:58:49<35:30:50,  7.11s/it]
 36%|███▌      | 10109/28080 [19:58:56<35:35:06,  7.13s/it]
                                                           
{'loss': 0.641, 'learning_rate': 0.0003703014374363926, 'epoch': 4.32}

 36%|███▌      | 10109/28080 [19:58:56<35:35:06,  7.13s/it]
 36%|███▌      | 10110/28080 [19:59:03<35:24:14,  7.09s/it]
                                                           
{'loss': 0.6336, 'learning_rate': 0.0003702761590335807, 'epoch': 4.32}

 36%|███▌      | 10110/28080 [19:59:03<35:24:14,  7.09s/it]
 36%|███▌      | 10111/28080 [19:59:10<35:27:16,  7.10s/it]
                                                           
{'loss': 0.6277, 'learning_rate': 0.00037025087903061856, 'epoch': 4.32}

 36%|███▌      | 10111/28080 [19:59:10<35:27:16,  7.10s/it]
 36%|███▌      | 10112/28080 [19:59:17<35:26:03,  7.10s/it]
                                                           
{'loss': 0.6471, 'learning_rate': 0.00037022559742784256, 'epoch': 4.32}

 36%|███▌      | 10112/28080 [19:59:17<35:26:03,  7.10s/it]
 36%|███▌      | 10113/28080 [19:59:24<35:18:34,  7.07s/it]
                                                           
{'loss': 0.6399, 'learning_rate': 0.00037020031422558907, 'epoch': 4.32}

 36%|███▌      | 10113/28080 [19:59:24<35:18:34,  7.07s/it]
 36%|███▌      | 10114/28080 [19:59:31<35:17:07,  7.07s/it]
                                                           
{'loss': 0.6278, 'learning_rate': 0.00037017502942419435, 'epoch': 4.32}

 36%|███▌      | 10114/28080 [19:59:31<35:17:07,  7.07s/it]
 36%|███▌      | 10115/28080 [19:59:38<35:20:02,  7.08s/it]
                                                           
{'loss': 0.6308, 'learning_rate': 0.0003701497430239948, 'epoch': 4.32}

 36%|███▌      | 10115/28080 [19:59:38<35:20:02,  7.08s/it]
 36%|███▌      | 10116/28080 [19:59:46<35:23:52,  7.09s/it]
                                                           
{'loss': 0.632, 'learning_rate': 0.000370124455025327, 'epoch': 4.32}

 36%|███▌      | 10116/28080 [19:59:46<35:23:52,  7.09s/it]
 36%|███▌      | 10117/28080 [19:59:53<35:28:51,  7.11s/it]
                                                           
{'loss': 0.6393, 'learning_rate': 0.0003700991654285272, 'epoch': 4.32}

 36%|███▌      | 10117/28080 [19:59:53<35:28:51,  7.11s/it]
 36%|███▌      | 10118/28080 [20:00:00<35:26:48,  7.10s/it]
                                                           
{'loss': 0.6282, 'learning_rate': 0.0003700738742339319, 'epoch': 4.32}

 36%|███▌      | 10118/28080 [20:00:00<35:26:48,  7.10s/it]
 36%|███▌      | 10119/28080 [20:00:07<35:18:04,  7.08s/it]
                                                           
{'loss': 0.6452, 'learning_rate': 0.00037004858144187755, 'epoch': 4.32}

 36%|███▌      | 10119/28080 [20:00:07<35:18:04,  7.08s/it]
 36%|███▌      | 10120/28080 [20:00:14<35:21:30,  7.09s/it]
                                                           
{'loss': 0.6194, 'learning_rate': 0.0003700232870527007, 'epoch': 4.32}

 36%|███▌      | 10120/28080 [20:00:14<35:21:30,  7.09s/it]
 36%|███▌      | 10121/28080 [20:00:21<35:18:28,  7.08s/it]
                                                           
{'loss': 0.6058, 'learning_rate': 0.0003699979910667378, 'epoch': 4.32}

 36%|███▌      | 10121/28080 [20:00:21<35:18:28,  7.08s/it]
 36%|███▌      | 10122/28080 [20:00:28<35:18:25,  7.08s/it]
                                                           
{'loss': 0.6322, 'learning_rate': 0.0003699726934843254, 'epoch': 4.32}

 36%|███▌      | 10122/28080 [20:00:28<35:18:25,  7.08s/it]
 36%|███▌      | 10123/28080 [20:00:35<35:17:38,  7.08s/it]
                                                           
{'loss': 0.6299, 'learning_rate': 0.00036994739430580017, 'epoch': 4.32}

 36%|███▌      | 10123/28080 [20:00:35<35:17:38,  7.08s/it]
 36%|███▌      | 10124/28080 [20:00:42<35:25:35,  7.10s/it]
                                                           
{'loss': 0.6236, 'learning_rate': 0.00036992209353149853, 'epoch': 4.32}

 36%|███▌      | 10124/28080 [20:00:42<35:25:35,  7.10s/it]
 36%|███▌      | 10125/28080 [20:00:49<35:20:08,  7.08s/it]
                                                           
{'loss': 0.6421, 'learning_rate': 0.00036989679116175724, 'epoch': 4.33}

 36%|███▌      | 10125/28080 [20:00:49<35:20:08,  7.08s/it]
 36%|███▌      | 10126/28080 [20:00:56<35:15:29,  7.07s/it]
                                                           
{'loss': 0.6238, 'learning_rate': 0.0003698714871969127, 'epoch': 4.33}

 36%|███▌      | 10126/28080 [20:00:56<35:15:29,  7.07s/it]
 36%|███▌      | 10127/28080 [20:01:04<35:24:38,  7.10s/it]
                                                           
{'loss': 0.6355, 'learning_rate': 0.00036984618163730183, 'epoch': 4.33}

 36%|███▌      | 10127/28080 [20:01:04<35:24:38,  7.10s/it]
 36%|███▌      | 10128/28080 [20:01:11<35:32:27,  7.13s/it]
                                                           
{'loss': 0.6431, 'learning_rate': 0.00036982087448326107, 'epoch': 4.33}

 36%|███▌      | 10128/28080 [20:01:11<35:32:27,  7.13s/it]
 36%|███▌      | 10129/28080 [20:01:18<35:30:02,  7.12s/it]
                                                           
{'loss': 0.6435, 'learning_rate': 0.00036979556573512717, 'epoch': 4.33}

 36%|███▌      | 10129/28080 [20:01:18<35:30:02,  7.12s/it]
 36%|███▌      | 10130/28080 [20:01:25<35:22:40,  7.10s/it]
                                                           
{'loss': 0.6245, 'learning_rate': 0.0003697702553932369, 'epoch': 4.33}

 36%|███▌      | 10130/28080 [20:01:25<35:22:40,  7.10s/it]
 36%|███▌      | 10131/28080 [20:01:32<35:25:27,  7.10s/it]
                                                           
{'loss': 0.6401, 'learning_rate': 0.0003697449434579269, 'epoch': 4.33}

 36%|███▌      | 10131/28080 [20:01:32<35:25:27,  7.10s/it]
 36%|███▌      | 10132/28080 [20:01:39<35:20:14,  7.09s/it]
                                                           
{'loss': 0.6242, 'learning_rate': 0.000369719629929534, 'epoch': 4.33}

 36%|███▌      | 10132/28080 [20:01:39<35:20:14,  7.09s/it]
 36%|███▌      | 10133/28080 [20:01:46<35:19:22,  7.09s/it]
                                                           
{'loss': 0.6367, 'learning_rate': 0.0003696943148083949, 'epoch': 4.33}

 36%|███▌      | 10133/28080 [20:01:46<35:19:22,  7.09s/it]
 36%|███▌      | 10134/28080 [20:01:53<35:22:14,  7.10s/it]
                                                           
{'loss': 0.6422, 'learning_rate': 0.00036966899809484643, 'epoch': 4.33}

 36%|███▌      | 10134/28080 [20:01:53<35:22:14,  7.10s/it]
 36%|███▌      | 10135/28080 [20:02:00<35:24:10,  7.10s/it]
                                                           
{'loss': 0.613, 'learning_rate': 0.0003696436797892254, 'epoch': 4.33}

 36%|███▌      | 10135/28080 [20:02:00<35:24:10,  7.10s/it]
 36%|███▌      | 10136/28080 [20:02:07<35:19:42,  7.09s/it]
                                                           
{'loss': 0.6342, 'learning_rate': 0.00036961835989186864, 'epoch': 4.33}

 36%|███▌      | 10136/28080 [20:02:07<35:19:42,  7.09s/it]
 36%|███▌      | 10137/28080 [20:02:14<35:21:34,  7.09s/it]
                                                           
{'loss': 0.6431, 'learning_rate': 0.0003695930384031131, 'epoch': 4.33}

 36%|███▌      | 10137/28080 [20:02:14<35:21:34,  7.09s/it]
 36%|███▌      | 10138/28080 [20:02:21<35:13:11,  7.07s/it]
                                                           
{'loss': 0.6295, 'learning_rate': 0.0003695677153232954, 'epoch': 4.33}

 36%|███▌      | 10138/28080 [20:02:21<35:13:11,  7.07s/it]
 36%|███▌      | 10139/28080 [20:02:29<35:18:42,  7.09s/it]
                                                           
{'loss': 0.662, 'learning_rate': 0.0003695423906527527, 'epoch': 4.33}

 36%|███▌      | 10139/28080 [20:02:29<35:18:42,  7.09s/it]
 36%|███▌      | 10140/28080 [20:02:36<35:17:11,  7.08s/it]
                                                           
{'loss': 0.6193, 'learning_rate': 0.00036951706439182177, 'epoch': 4.33}

 36%|███▌      | 10140/28080 [20:02:36<35:17:11,  7.08s/it]
 36%|███▌      | 10141/28080 [20:02:43<35:14:35,  7.07s/it]
                                                           
{'loss': 0.6295, 'learning_rate': 0.00036949173654083966, 'epoch': 4.33}

 36%|███▌      | 10141/28080 [20:02:43<35:14:35,  7.07s/it]
 36%|███▌      | 10142/28080 [20:02:50<35:15:15,  7.08s/it]
                                                           
{'loss': 0.6323, 'learning_rate': 0.0003694664071001432, 'epoch': 4.33}

 36%|███▌      | 10142/28080 [20:02:50<35:15:15,  7.08s/it]
 36%|███▌      | 10143/28080 [20:02:57<35:22:42,  7.10s/it]
                                                           
{'loss': 0.6379, 'learning_rate': 0.0003694410760700695, 'epoch': 4.33}

 36%|███▌      | 10143/28080 [20:02:57<35:22:42,  7.10s/it]
 36%|███▌      | 10144/28080 [20:03:04<35:23:34,  7.10s/it]
                                                           
{'loss': 0.6176, 'learning_rate': 0.0003694157434509555, 'epoch': 4.33}

 36%|███▌      | 10144/28080 [20:03:04<35:23:34,  7.10s/it]
 36%|███▌      | 10145/28080 [20:03:11<35:21:16,  7.10s/it]
                                                           
{'loss': 0.6495, 'learning_rate': 0.00036939040924313817, 'epoch': 4.33}

 36%|███▌      | 10145/28080 [20:03:11<35:21:16,  7.10s/it]
 36%|███▌      | 10146/28080 [20:03:18<35:13:53,  7.07s/it]
                                                           
{'loss': 0.6433, 'learning_rate': 0.0003693650734469546, 'epoch': 4.33}

 36%|███▌      | 10146/28080 [20:03:18<35:13:53,  7.07s/it]
 36%|███▌      | 10147/28080 [20:03:25<35:17:40,  7.09s/it]
                                                           
{'loss': 0.622, 'learning_rate': 0.00036933973606274195, 'epoch': 4.33}

 36%|███▌      | 10147/28080 [20:03:25<35:17:40,  7.09s/it]
 36%|███▌      | 10148/28080 [20:03:32<35:19:15,  7.09s/it]
                                                           
{'loss': 0.6412, 'learning_rate': 0.00036931439709083714, 'epoch': 4.34}

 36%|███▌      | 10148/28080 [20:03:32<35:19:15,  7.09s/it]
 36%|███▌      | 10149/28080 [20:03:40<35:20:36,  7.10s/it]
                                                           
{'loss': 0.6439, 'learning_rate': 0.00036928905653157745, 'epoch': 4.34}

 36%|███▌      | 10149/28080 [20:03:40<35:20:36,  7.10s/it]
 36%|███▌      | 10150/28080 [20:03:47<35:26:15,  7.12s/it]
                                                           
{'loss': 0.6062, 'learning_rate': 0.0003692637143852999, 'epoch': 4.34}

 36%|███▌      | 10150/28080 [20:03:47<35:26:15,  7.12s/it]
 36%|███▌      | 10151/28080 [20:03:54<35:20:15,  7.10s/it]
                                                           
{'loss': 0.6261, 'learning_rate': 0.0003692383706523417, 'epoch': 4.34}

 36%|███▌      | 10151/28080 [20:03:54<35:20:15,  7.10s/it]
 36%|███▌      | 10152/28080 [20:04:01<35:23:38,  7.11s/it]
                                                           
{'loss': 0.6276, 'learning_rate': 0.0003692130253330399, 'epoch': 4.34}

 36%|███▌      | 10152/28080 [20:04:01<35:23:38,  7.11s/it]
 36%|███▌      | 10153/28080 [20:04:08<35:27:14,  7.12s/it]
                                                           
{'loss': 0.6072, 'learning_rate': 0.00036918767842773184, 'epoch': 4.34}

 36%|███▌      | 10153/28080 [20:04:08<35:27:14,  7.12s/it]
 36%|███▌      | 10154/28080 [20:04:15<35:28:35,  7.12s/it]
                                                           
{'loss': 0.6343, 'learning_rate': 0.0003691623299367547, 'epoch': 4.34}

 36%|███▌      | 10154/28080 [20:04:15<35:28:35,  7.12s/it]
 36%|███▌      | 10155/28080 [20:04:22<35:25:16,  7.11s/it]
                                                           
{'loss': 0.639, 'learning_rate': 0.0003691369798604456, 'epoch': 4.34}

 36%|███▌      | 10155/28080 [20:04:22<35:25:16,  7.11s/it]
 36%|███▌      | 10156/28080 [20:04:29<35:25:17,  7.11s/it]
                                                           
{'loss': 0.62, 'learning_rate': 0.000369111628199142, 'epoch': 4.34}

 36%|███▌      | 10156/28080 [20:04:29<35:25:17,  7.11s/it]
 36%|███▌      | 10157/28080 [20:04:36<35:21:07,  7.10s/it]
                                                           
{'loss': 0.6427, 'learning_rate': 0.00036908627495318096, 'epoch': 4.34}

 36%|███▌      | 10157/28080 [20:04:36<35:21:07,  7.10s/it]
 36%|███▌      | 10158/28080 [20:04:44<35:22:20,  7.11s/it]
                                                           
{'loss': 0.6249, 'learning_rate': 0.0003690609201229, 'epoch': 4.34}

 36%|███▌      | 10158/28080 [20:04:44<35:22:20,  7.11s/it]
 36%|███▌      | 10159/28080 [20:04:51<35:27:56,  7.12s/it]
                                                           
{'loss': 0.6162, 'learning_rate': 0.0003690355637086362, 'epoch': 4.34}

 36%|███▌      | 10159/28080 [20:04:51<35:27:56,  7.12s/it]
 36%|███▌      | 10160/28080 [20:04:58<35:29:00,  7.13s/it]
                                                           
{'loss': 0.6489, 'learning_rate': 0.0003690102057107271, 'epoch': 4.34}

 36%|███▌      | 10160/28080 [20:04:58<35:29:00,  7.13s/it]
 36%|███▌      | 10161/28080 [20:05:05<35:17:29,  7.09s/it]
                                                           
{'loss': 0.6305, 'learning_rate': 0.00036898484612951003, 'epoch': 4.34}

 36%|███▌      | 10161/28080 [20:05:05<35:17:29,  7.09s/it]
 36%|███▌      | 10162/28080 [20:05:12<35:19:09,  7.10s/it]
                                                           
{'loss': 0.6435, 'learning_rate': 0.00036895948496532227, 'epoch': 4.34}

 36%|███▌      | 10162/28080 [20:05:12<35:19:09,  7.10s/it]
 36%|███▌      | 10163/28080 [20:05:19<35:21:33,  7.10s/it]
                                                           
{'loss': 0.6405, 'learning_rate': 0.0003689341222185013, 'epoch': 4.34}

 36%|███▌      | 10163/28080 [20:05:19<35:21:33,  7.10s/it]
 36%|███▌      | 10164/28080 [20:05:26<35:08:14,  7.06s/it]
                                                           
{'loss': 0.6275, 'learning_rate': 0.00036890875788938454, 'epoch': 4.34}

 36%|███▌      | 10164/28080 [20:05:26<35:08:14,  7.06s/it]
 36%|███▌      | 10165/28080 [20:05:33<35:08:24,  7.06s/it]
                                                           
{'loss': 0.6672, 'learning_rate': 0.00036888339197830943, 'epoch': 4.34}

 36%|███▌      | 10165/28080 [20:05:33<35:08:24,  7.06s/it]
 36%|███▌      | 10166/28080 [20:05:40<35:13:44,  7.08s/it]
                                                           
{'loss': 0.6156, 'learning_rate': 0.00036885802448561347, 'epoch': 4.34}

 36%|███▌      | 10166/28080 [20:05:40<35:13:44,  7.08s/it]
 36%|███▌      | 10167/28080 [20:05:47<35:17:01,  7.09s/it]
                                                           
{'loss': 0.6303, 'learning_rate': 0.000368832655411634, 'epoch': 4.34}

 36%|███▌      | 10167/28080 [20:05:47<35:17:01,  7.09s/it]
 36%|███▌      | 10168/28080 [20:05:54<35:20:51,  7.10s/it]
                                                           
{'loss': 0.6281, 'learning_rate': 0.00036880728475670885, 'epoch': 4.34}

 36%|███▌      | 10168/28080 [20:05:54<35:20:51,  7.10s/it]
 36%|███▌      | 10169/28080 [20:06:02<35:14:06,  7.08s/it]
                                                           
{'loss': 0.6223, 'learning_rate': 0.00036878191252117515, 'epoch': 4.34}

 36%|███▌      | 10169/28080 [20:06:02<35:14:06,  7.08s/it]
 36%|███▌      | 10170/28080 [20:06:09<35:15:41,  7.09s/it]
                                                           
{'loss': 0.6197, 'learning_rate': 0.0003687565387053707, 'epoch': 4.34}

 36%|███▌      | 10170/28080 [20:06:09<35:15:41,  7.09s/it]
 36%|███▌      | 10171/28080 [20:06:16<35:18:45,  7.10s/it]
                                                           
{'loss': 0.6348, 'learning_rate': 0.00036873116330963303, 'epoch': 4.34}

 36%|███▌      | 10171/28080 [20:06:16<35:18:45,  7.10s/it]
 36%|███▌      | 10172/28080 [20:06:23<35:17:49,  7.10s/it]
                                                           
{'loss': 0.6245, 'learning_rate': 0.0003687057863342997, 'epoch': 4.35}

 36%|███▌      | 10172/28080 [20:06:23<35:17:49,  7.10s/it]
 36%|███▌      | 10173/28080 [20:06:30<35:16:06,  7.09s/it]
                                                           
{'loss': 0.6096, 'learning_rate': 0.00036868040777970836, 'epoch': 4.35}

 36%|███▌      | 10173/28080 [20:06:30<35:16:06,  7.09s/it]
 36%|███▌      | 10174/28080 [20:06:37<35:15:44,  7.09s/it]
                                                           
{'loss': 0.6162, 'learning_rate': 0.00036865502764619665, 'epoch': 4.35}

 36%|███▌      | 10174/28080 [20:06:37<35:15:44,  7.09s/it]
 36%|███▌      | 10175/28080 [20:06:44<35:18:36,  7.10s/it]
                                                           
{'loss': 0.6227, 'learning_rate': 0.0003686296459341022, 'epoch': 4.35}

 36%|███▌      | 10175/28080 [20:06:44<35:18:36,  7.10s/it]
 36%|███▌      | 10176/28080 [20:06:51<35:21:57,  7.11s/it]
                                                           
{'loss': 0.6165, 'learning_rate': 0.0003686042626437626, 'epoch': 4.35}

 36%|███▌      | 10176/28080 [20:06:51<35:21:57,  7.11s/it]
 36%|███▌      | 10177/28080 [20:06:58<35:09:48,  7.07s/it]
                                                           
{'loss': 0.6432, 'learning_rate': 0.00036857887777551573, 'epoch': 4.35}

 36%|███▌      | 10177/28080 [20:06:58<35:09:48,  7.07s/it]
 36%|███▌      | 10178/28080 [20:07:05<35:17:59,  7.10s/it]
                                                           
{'loss': 0.621, 'learning_rate': 0.00036855349132969924, 'epoch': 4.35}

 36%|███▌      | 10178/28080 [20:07:05<35:17:59,  7.10s/it]
 36%|███▋      | 10179/28080 [20:07:12<35:12:51,  7.08s/it]
                                                           
{'loss': 0.6349, 'learning_rate': 0.0003685281033066508, 'epoch': 4.35}

 36%|███▋      | 10179/28080 [20:07:12<35:12:51,  7.08s/it]
 36%|███▋      | 10180/28080 [20:07:20<35:21:08,  7.11s/it]
                                                           
{'loss': 0.6419, 'learning_rate': 0.0003685027137067083, 'epoch': 4.35}

 36%|███▋      | 10180/28080 [20:07:20<35:21:08,  7.11s/it]
 36%|███▋      | 10181/28080 [20:07:27<35:20:06,  7.11s/it]
                                                           
{'loss': 0.6279, 'learning_rate': 0.0003684773225302094, 'epoch': 4.35}

 36%|███▋      | 10181/28080 [20:07:27<35:20:06,  7.11s/it]
 36%|███▋      | 10182/28080 [20:07:34<35:23:59,  7.12s/it]
                                                           
{'loss': 0.619, 'learning_rate': 0.0003684519297774919, 'epoch': 4.35}

 36%|███▋      | 10182/28080 [20:07:34<35:23:59,  7.12s/it]
 36%|███▋      | 10183/28080 [20:07:41<35:26:35,  7.13s/it]
                                                           
{'loss': 0.6208, 'learning_rate': 0.0003684265354488937, 'epoch': 4.35}

 36%|███▋      | 10183/28080 [20:07:41<35:26:35,  7.13s/it]
 36%|███▋      | 10184/28080 [20:07:48<35:22:11,  7.12s/it]
                                                           
{'loss': 0.6193, 'learning_rate': 0.0003684011395447526, 'epoch': 4.35}

 36%|███▋      | 10184/28080 [20:07:48<35:22:11,  7.12s/it]
 36%|███▋      | 10185/28080 [20:07:55<35:03:17,  7.05s/it]
                                                           
{'loss': 0.6413, 'learning_rate': 0.00036837574206540657, 'epoch': 4.35}

 36%|███▋      | 10185/28080 [20:07:55<35:03:17,  7.05s/it]
 36%|███▋      | 10186/28080 [20:08:02<35:05:25,  7.06s/it]
                                                           
{'loss': 0.6143, 'learning_rate': 0.0003683503430111934, 'epoch': 4.35}

 36%|███▋      | 10186/28080 [20:08:02<35:05:25,  7.06s/it]
 36%|███▋      | 10187/28080 [20:08:09<35:06:31,  7.06s/it]
                                                           
{'loss': 0.6359, 'learning_rate': 0.00036832494238245094, 'epoch': 4.35}

 36%|███▋      | 10187/28080 [20:08:09<35:06:31,  7.06s/it]
 36%|███▋      | 10188/28080 [20:08:16<35:05:35,  7.06s/it]
                                                           
{'loss': 0.6189, 'learning_rate': 0.0003682995401795172, 'epoch': 4.35}

 36%|███▋      | 10188/28080 [20:08:16<35:05:35,  7.06s/it]
 36%|███▋      | 10189/28080 [20:08:23<35:03:18,  7.05s/it]
                                                           
{'loss': 0.6359, 'learning_rate': 0.00036827413640273023, 'epoch': 4.35}

 36%|███▋      | 10189/28080 [20:08:23<35:03:18,  7.05s/it]
 36%|███▋      | 10190/28080 [20:08:30<35:08:54,  7.07s/it]
                                                           
{'loss': 0.6256, 'learning_rate': 0.0003682487310524278, 'epoch': 4.35}

 36%|███▋      | 10190/28080 [20:08:30<35:08:54,  7.07s/it]
 36%|███▋      | 10191/28080 [20:08:37<35:10:21,  7.08s/it]
                                                           
{'loss': 0.6273, 'learning_rate': 0.000368223324128948, 'epoch': 4.35}

 36%|███▋      | 10191/28080 [20:08:37<35:10:21,  7.08s/it]
 36%|███▋      | 10192/28080 [20:08:45<35:12:30,  7.09s/it]
                                                           
{'loss': 0.6233, 'learning_rate': 0.0003681979156326288, 'epoch': 4.35}

 36%|███▋      | 10192/28080 [20:08:45<35:12:30,  7.09s/it]
 36%|███▋      | 10193/28080 [20:08:52<35:02:48,  7.05s/it]
                                                           
{'loss': 0.6108, 'learning_rate': 0.00036817250556380837, 'epoch': 4.35}

 36%|███▋      | 10193/28080 [20:08:52<35:02:48,  7.05s/it]
 36%|███▋      | 10194/28080 [20:08:59<35:12:28,  7.09s/it]
                                                           
{'loss': 0.5979, 'learning_rate': 0.00036814709392282463, 'epoch': 4.35}

 36%|███▋      | 10194/28080 [20:08:59<35:12:28,  7.09s/it]
 36%|███▋      | 10195/28080 [20:09:06<35:03:10,  7.06s/it]
                                                           
{'loss': 0.6084, 'learning_rate': 0.00036812168071001565, 'epoch': 4.36}

 36%|███▋      | 10195/28080 [20:09:06<35:03:10,  7.06s/it]
 36%|███▋      | 10196/28080 [20:09:13<35:11:03,  7.08s/it]
                                                           
{'loss': 0.6356, 'learning_rate': 0.00036809626592571954, 'epoch': 4.36}

 36%|███▋      | 10196/28080 [20:09:13<35:11:03,  7.08s/it]
 36%|███▋      | 10197/28080 [20:09:20<35:16:59,  7.10s/it]
                                                           
{'loss': 0.6335, 'learning_rate': 0.00036807084957027455, 'epoch': 4.36}

 36%|███▋      | 10197/28080 [20:09:20<35:16:59,  7.10s/it]
 36%|███▋      | 10198/28080 [20:09:27<35:20:16,  7.11s/it]
                                                           
{'loss': 0.5946, 'learning_rate': 0.00036804543164401865, 'epoch': 4.36}

 36%|███▋      | 10198/28080 [20:09:27<35:20:16,  7.11s/it]
 36%|███▋      | 10199/28080 [20:09:34<35:13:15,  7.09s/it]
                                                           
{'loss': 0.6367, 'learning_rate': 0.0003680200121472901, 'epoch': 4.36}

 36%|███▋      | 10199/28080 [20:09:34<35:13:15,  7.09s/it]
 36%|███▋      | 10200/28080 [20:09:41<35:13:27,  7.09s/it]
                                                           
{'loss': 0.6327, 'learning_rate': 0.00036799459108042697, 'epoch': 4.36}

 36%|███▋      | 10200/28080 [20:09:41<35:13:27,  7.09s/it]
 36%|███▋      | 10201/28080 [20:09:48<35:18:33,  7.11s/it]
                                                           
{'loss': 0.6258, 'learning_rate': 0.00036796916844376756, 'epoch': 4.36}

 36%|███▋      | 10201/28080 [20:09:48<35:18:33,  7.11s/it]
 36%|███▋      | 10202/28080 [20:09:55<35:17:33,  7.11s/it]
                                                           
{'loss': 0.6405, 'learning_rate': 0.0003679437442376501, 'epoch': 4.36}

 36%|███▋      | 10202/28080 [20:09:55<35:17:33,  7.11s/it]
 36%|███▋      | 10203/28080 [20:10:03<35:25:32,  7.13s/it]
                                                           
{'loss': 0.6329, 'learning_rate': 0.00036791831846241276, 'epoch': 4.36}

 36%|███▋      | 10203/28080 [20:10:03<35:25:32,  7.13s/it]
 36%|███▋      | 10204/28080 [20:10:10<35:22:20,  7.12s/it]
                                                           
{'loss': 0.6564, 'learning_rate': 0.0003678928911183939, 'epoch': 4.36}

 36%|███▋      | 10204/28080 [20:10:10<35:22:20,  7.12s/it]
 36%|███▋      | 10205/28080 [20:10:17<35:04:17,  7.06s/it]
                                                           
{'loss': 0.6213, 'learning_rate': 0.0003678674622059317, 'epoch': 4.36}

 36%|███▋      | 10205/28080 [20:10:17<35:04:17,  7.06s/it]
 36%|███▋      | 10206/28080 [20:10:24<34:56:29,  7.04s/it]
                                                           
{'loss': 0.6316, 'learning_rate': 0.00036784203172536453, 'epoch': 4.36}

 36%|███▋      | 10206/28080 [20:10:24<34:56:29,  7.04s/it]
 36%|███▋      | 10207/28080 [20:10:31<34:58:10,  7.04s/it]
                                                           
{'loss': 0.6432, 'learning_rate': 0.00036781659967703067, 'epoch': 4.36}

 36%|███▋      | 10207/28080 [20:10:31<34:58:10,  7.04s/it]
 36%|███▋      | 10208/28080 [20:10:38<35:01:55,  7.06s/it]
                                                           
{'loss': 0.6199, 'learning_rate': 0.0003677911660612685, 'epoch': 4.36}

 36%|███▋      | 10208/28080 [20:10:38<35:01:55,  7.06s/it]
 36%|███▋      | 10209/28080 [20:10:45<35:07:50,  7.08s/it]
                                                           
{'loss': 0.6221, 'learning_rate': 0.0003677657308784164, 'epoch': 4.36}

 36%|███▋      | 10209/28080 [20:10:45<35:07:50,  7.08s/it]
 36%|███▋      | 10210/28080 [20:10:52<35:05:54,  7.07s/it]
                                                           
{'loss': 0.6271, 'learning_rate': 0.0003677402941288127, 'epoch': 4.36}

 36%|███▋      | 10210/28080 [20:10:52<35:05:54,  7.07s/it]
 36%|███▋      | 10211/28080 [20:10:59<35:13:59,  7.10s/it]
                                                           
{'loss': 0.6484, 'learning_rate': 0.00036771485581279595, 'epoch': 4.36}

 36%|███▋      | 10211/28080 [20:10:59<35:13:59,  7.10s/it]
 36%|███▋      | 10212/28080 [20:11:06<35:09:10,  7.08s/it]
                                                           
{'loss': 0.6374, 'learning_rate': 0.0003676894159307044, 'epoch': 4.36}

 36%|███▋      | 10212/28080 [20:11:06<35:09:10,  7.08s/it]
 36%|███▋      | 10213/28080 [20:11:13<35:05:40,  7.07s/it]
                                                           
{'loss': 0.6239, 'learning_rate': 0.00036766397448287667, 'epoch': 4.36}

 36%|███▋      | 10213/28080 [20:11:13<35:05:40,  7.07s/it]
 36%|███▋      | 10214/28080 [20:11:20<34:59:39,  7.05s/it]
                                                           
{'loss': 0.64, 'learning_rate': 0.0003676385314696511, 'epoch': 4.36}

 36%|███▋      | 10214/28080 [20:11:20<34:59:39,  7.05s/it]
 36%|███▋      | 10215/28080 [20:11:27<35:09:23,  7.08s/it]
                                                           
{'loss': 0.631, 'learning_rate': 0.0003676130868913662, 'epoch': 4.36}

 36%|███▋      | 10215/28080 [20:11:27<35:09:23,  7.08s/it]
 36%|███▋      | 10216/28080 [20:11:35<35:13:49,  7.10s/it]
                                                           
{'loss': 0.652, 'learning_rate': 0.00036758764074836057, 'epoch': 4.36}

 36%|███▋      | 10216/28080 [20:11:35<35:13:49,  7.10s/it]
 36%|███▋      | 10217/28080 [20:11:42<35:14:51,  7.10s/it]
                                                           
{'loss': 0.6322, 'learning_rate': 0.0003675621930409726, 'epoch': 4.36}

 36%|███▋      | 10217/28080 [20:11:42<35:14:51,  7.10s/it]
 36%|███▋      | 10218/28080 [20:11:49<35:14:27,  7.10s/it]
                                                           
{'loss': 0.6391, 'learning_rate': 0.00036753674376954103, 'epoch': 4.37}

 36%|███▋      | 10218/28080 [20:11:49<35:14:27,  7.10s/it]
 36%|███▋      | 10219/28080 [20:11:56<35:14:04,  7.10s/it]
                                                           
{'loss': 0.6127, 'learning_rate': 0.00036751129293440427, 'epoch': 4.37}

 36%|███▋      | 10219/28080 [20:11:56<35:14:04,  7.10s/it]
 36%|███▋      | 10220/28080 [20:12:03<35:12:16,  7.10s/it]
                                                           
{'loss': 0.6267, 'learning_rate': 0.000367485840535901, 'epoch': 4.37}

 36%|███▋      | 10220/28080 [20:12:03<35:12:16,  7.10s/it]
 36%|███▋      | 10221/28080 [20:12:10<35:04:35,  7.07s/it]
                                                           
{'loss': 0.6335, 'learning_rate': 0.00036746038657436985, 'epoch': 4.37}

 36%|███▋      | 10221/28080 [20:12:10<35:04:35,  7.07s/it]
 36%|███▋      | 10222/28080 [20:12:17<35:03:17,  7.07s/it]
                                                           
{'loss': 0.6264, 'learning_rate': 0.0003674349310501494, 'epoch': 4.37}

 36%|███▋      | 10222/28080 [20:12:17<35:03:17,  7.07s/it]
 36%|███▋      | 10223/28080 [20:12:24<35:08:06,  7.08s/it]
                                                           
{'loss': 0.637, 'learning_rate': 0.0003674094739635784, 'epoch': 4.37}

 36%|███▋      | 10223/28080 [20:12:24<35:08:06,  7.08s/it]
 36%|███▋      | 10224/28080 [20:12:31<35:03:27,  7.07s/it]
                                                           
{'loss': 0.5993, 'learning_rate': 0.0003673840153149954, 'epoch': 4.37}

 36%|███▋      | 10224/28080 [20:12:31<35:03:27,  7.07s/it]
 36%|███▋      | 10225/28080 [20:12:38<35:05:10,  7.07s/it]
                                                           
{'loss': 0.638, 'learning_rate': 0.0003673585551047393, 'epoch': 4.37}

 36%|███▋      | 10225/28080 [20:12:38<35:05:10,  7.07s/it]
 36%|███▋      | 10226/28080 [20:12:45<35:11:16,  7.10s/it]
                                                           
{'loss': 0.6138, 'learning_rate': 0.00036733309333314857, 'epoch': 4.37}

 36%|███▋      | 10226/28080 [20:12:45<35:11:16,  7.10s/it]
 36%|███▋      | 10227/28080 [20:12:53<35:11:58,  7.10s/it]
                                                           
{'loss': 0.6349, 'learning_rate': 0.0003673076300005621, 'epoch': 4.37}

 36%|███▋      | 10227/28080 [20:12:53<35:11:58,  7.10s/it]
 36%|███▋      | 10228/28080 [20:13:00<35:15:56,  7.11s/it]
                                                           
{'loss': 0.6147, 'learning_rate': 0.00036728216510731863, 'epoch': 4.37}

 36%|███▋      | 10228/28080 [20:13:00<35:15:56,  7.11s/it]
 36%|███▋      | 10229/28080 [20:13:07<35:07:06,  7.08s/it]
                                                           
{'loss': 0.6267, 'learning_rate': 0.00036725669865375697, 'epoch': 4.37}

 36%|███▋      | 10229/28080 [20:13:07<35:07:06,  7.08s/it]
 36%|███▋      | 10230/28080 [20:13:14<35:08:05,  7.09s/it]
                                                           
{'loss': 0.6439, 'learning_rate': 0.0003672312306402159, 'epoch': 4.37}

 36%|███▋      | 10230/28080 [20:13:14<35:08:05,  7.09s/it]
 36%|███▋      | 10231/28080 [20:13:21<35:12:40,  7.10s/it]
                                                           
{'loss': 0.6347, 'learning_rate': 0.00036720576106703427, 'epoch': 4.37}

 36%|███▋      | 10231/28080 [20:13:21<35:12:40,  7.10s/it]
 36%|███▋      | 10232/28080 [20:13:28<35:09:36,  7.09s/it]
                                                           
{'loss': 0.6329, 'learning_rate': 0.00036718028993455086, 'epoch': 4.37}

 36%|███▋      | 10232/28080 [20:13:28<35:09:36,  7.09s/it]
 36%|███▋      | 10233/28080 [20:13:35<35:10:22,  7.09s/it]
                                                           
{'loss': 0.647, 'learning_rate': 0.00036715481724310464, 'epoch': 4.37}

 36%|███▋      | 10233/28080 [20:13:35<35:10:22,  7.09s/it]
 36%|███▋      | 10234/28080 [20:13:42<35:09:47,  7.09s/it]
                                                           
{'loss': 0.6339, 'learning_rate': 0.00036712934299303437, 'epoch': 4.37}

 36%|███▋      | 10234/28080 [20:13:42<35:09:47,  7.09s/it]
 36%|███▋      | 10235/28080 [20:13:49<35:06:18,  7.08s/it]
                                                           
{'loss': 0.6313, 'learning_rate': 0.000367103867184679, 'epoch': 4.37}

 36%|███▋      | 10235/28080 [20:13:49<35:06:18,  7.08s/it]
 36%|███▋      | 10236/28080 [20:13:56<35:11:48,  7.10s/it]
                                                           
{'loss': 0.641, 'learning_rate': 0.0003670783898183776, 'epoch': 4.37}

 36%|███▋      | 10236/28080 [20:13:56<35:11:48,  7.10s/it]
 36%|███▋      | 10237/28080 [20:14:03<35:06:27,  7.08s/it]
                                                           
{'loss': 0.6138, 'learning_rate': 0.00036705291089446894, 'epoch': 4.37}

 36%|███▋      | 10237/28080 [20:14:03<35:06:27,  7.08s/it]
 36%|███▋      | 10238/28080 [20:14:11<35:08:56,  7.09s/it]
                                                           
{'loss': 0.6187, 'learning_rate': 0.00036702743041329205, 'epoch': 4.37}

 36%|███▋      | 10238/28080 [20:14:11<35:08:56,  7.09s/it]
 36%|███▋      | 10239/28080 [20:14:18<35:14:00,  7.11s/it]
                                                           
{'loss': 0.6247, 'learning_rate': 0.000367001948375186, 'epoch': 4.37}

 36%|███▋      | 10239/28080 [20:14:18<35:14:00,  7.11s/it]
 36%|███▋      | 10240/28080 [20:14:25<35:10:22,  7.10s/it]
                                                           
{'loss': 0.6228, 'learning_rate': 0.0003669764647804896, 'epoch': 4.37}

 36%|███▋      | 10240/28080 [20:14:25<35:10:22,  7.10s/it]
 36%|███▋      | 10241/28080 [20:14:32<35:11:55,  7.10s/it]
                                                           
{'loss': 0.6184, 'learning_rate': 0.0003669509796295421, 'epoch': 4.37}

 36%|███▋      | 10241/28080 [20:14:32<35:11:55,  7.10s/it]
 36%|███▋      | 10242/28080 [20:14:39<35:04:57,  7.08s/it]
                                                           
{'loss': 0.6225, 'learning_rate': 0.00036692549292268253, 'epoch': 4.38}

 36%|███▋      | 10242/28080 [20:14:39<35:04:57,  7.08s/it]
 36%|███▋      | 10243/28080 [20:14:46<35:03:11,  7.07s/it]
                                                           
{'loss': 0.6483, 'learning_rate': 0.0003669000046602498, 'epoch': 4.38}

 36%|███▋      | 10243/28080 [20:14:46<35:03:11,  7.07s/it]
 36%|███▋      | 10244/28080 [20:14:53<34:58:24,  7.06s/it]
                                                           
{'loss': 0.6273, 'learning_rate': 0.00036687451484258317, 'epoch': 4.38}

 36%|███▋      | 10244/28080 [20:14:53<34:58:24,  7.06s/it]
 36%|███▋      | 10245/28080 [20:15:00<34:53:38,  7.04s/it]
                                                           
{'loss': 0.6482, 'learning_rate': 0.00036684902347002165, 'epoch': 4.38}

 36%|███▋      | 10245/28080 [20:15:00<34:53:38,  7.04s/it]
 36%|███▋      | 10246/28080 [20:15:07<34:50:41,  7.03s/it]
                                                           
{'loss': 0.6183, 'learning_rate': 0.00036682353054290443, 'epoch': 4.38}

 36%|███▋      | 10246/28080 [20:15:07<34:50:41,  7.03s/it]
 36%|███▋      | 10247/28080 [20:15:14<34:51:41,  7.04s/it]
                                                           
{'loss': 0.6337, 'learning_rate': 0.00036679803606157066, 'epoch': 4.38}

 36%|███▋      | 10247/28080 [20:15:14<34:51:41,  7.04s/it]
 36%|███▋      | 10248/28080 [20:15:21<34:55:56,  7.05s/it]
                                                           
{'loss': 0.6403, 'learning_rate': 0.00036677254002635953, 'epoch': 4.38}

 36%|███▋      | 10248/28080 [20:15:21<34:55:56,  7.05s/it]
 36%|███▋      | 10249/28080 [20:15:28<35:00:26,  7.07s/it]
                                                           
{'loss': 0.6126, 'learning_rate': 0.0003667470424376102, 'epoch': 4.38}

 36%|███▋      | 10249/28080 [20:15:28<35:00:26,  7.07s/it]
 37%|███▋      | 10250/28080 [20:15:35<35:07:17,  7.09s/it]
                                                           
{'loss': 0.6308, 'learning_rate': 0.00036672154329566185, 'epoch': 4.38}

 37%|███▋      | 10250/28080 [20:15:35<35:07:17,  7.09s/it]
 37%|███▋      | 10251/28080 [20:15:43<35:09:46,  7.10s/it]
                                                           
{'loss': 0.6265, 'learning_rate': 0.00036669604260085385, 'epoch': 4.38}

 37%|███▋      | 10251/28080 [20:15:43<35:09:46,  7.10s/it]
 37%|███▋      | 10252/28080 [20:15:50<35:14:13,  7.12s/it]
                                                           
{'loss': 0.6324, 'learning_rate': 0.0003666705403535254, 'epoch': 4.38}

 37%|███▋      | 10252/28080 [20:15:50<35:14:13,  7.12s/it]
 37%|███▋      | 10253/28080 [20:15:57<35:10:52,  7.10s/it]
                                                           
{'loss': 0.6122, 'learning_rate': 0.00036664503655401575, 'epoch': 4.38}

 37%|███▋      | 10253/28080 [20:15:57<35:10:52,  7.10s/it]
 37%|███▋      | 10254/28080 [20:16:04<35:18:01,  7.13s/it]
                                                           
{'loss': 0.6217, 'learning_rate': 0.0003666195312026642, 'epoch': 4.38}

 37%|███▋      | 10254/28080 [20:16:04<35:18:01,  7.13s/it]
 37%|███▋      | 10255/28080 [20:16:11<35:21:47,  7.14s/it]
                                                           
{'loss': 0.6138, 'learning_rate': 0.00036659402429981014, 'epoch': 4.38}

 37%|███▋      | 10255/28080 [20:16:11<35:21:47,  7.14s/it]
 37%|███▋      | 10256/28080 [20:16:18<35:12:20,  7.11s/it]
                                                           
{'loss': 0.6237, 'learning_rate': 0.00036656851584579295, 'epoch': 4.38}

 37%|███▋      | 10256/28080 [20:16:18<35:12:20,  7.11s/it]
 37%|███▋      | 10257/28080 [20:16:25<35:18:49,  7.13s/it]
                                                           
{'loss': 0.6234, 'learning_rate': 0.0003665430058409518, 'epoch': 4.38}

 37%|███▋      | 10257/28080 [20:16:25<35:18:49,  7.13s/it]
 37%|███▋      | 10258/28080 [20:16:32<35:18:53,  7.13s/it]
                                                           
{'loss': 0.6269, 'learning_rate': 0.0003665174942856261, 'epoch': 4.38}

 37%|███▋      | 10258/28080 [20:16:32<35:18:53,  7.13s/it]
 37%|███▋      | 10259/28080 [20:16:40<35:20:18,  7.14s/it]
                                                           
{'loss': 0.6088, 'learning_rate': 0.00036649198118015555, 'epoch': 4.38}

 37%|███▋      | 10259/28080 [20:16:40<35:20:18,  7.14s/it]
 37%|███▋      | 10260/28080 [20:16:47<35:11:18,  7.11s/it]
                                                           
{'loss': 0.6199, 'learning_rate': 0.00036646646652487925, 'epoch': 4.38}

 37%|███▋      | 10260/28080 [20:16:47<35:11:18,  7.11s/it]
 37%|███▋      | 10261/28080 [20:16:54<35:11:55,  7.11s/it]
                                                           
{'loss': 0.6317, 'learning_rate': 0.0003664409503201368, 'epoch': 4.38}

 37%|███▋      | 10261/28080 [20:16:54<35:11:55,  7.11s/it]
 37%|███▋      | 10262/28080 [20:17:01<35:09:44,  7.10s/it]
                                                           
{'loss': 0.6236, 'learning_rate': 0.0003664154325662676, 'epoch': 4.38}

 37%|███▋      | 10262/28080 [20:17:01<35:09:44,  7.10s/it]
 37%|███▋      | 10263/28080 [20:17:08<35:06:21,  7.09s/it]
                                                           
{'loss': 0.623, 'learning_rate': 0.00036638991326361117, 'epoch': 4.38}

 37%|███▋      | 10263/28080 [20:17:08<35:06:21,  7.09s/it]
 37%|███▋      | 10264/28080 [20:17:15<35:11:06,  7.11s/it]
                                                           
{'loss': 0.6167, 'learning_rate': 0.0003663643924125071, 'epoch': 4.38}

 37%|███▋      | 10264/28080 [20:17:15<35:11:06,  7.11s/it]
 37%|███▋      | 10265/28080 [20:17:22<35:16:51,  7.13s/it]
                                                           
{'loss': 0.6236, 'learning_rate': 0.0003663388700132947, 'epoch': 4.39}

 37%|███▋      | 10265/28080 [20:17:22<35:16:51,  7.13s/it]
 37%|███▋      | 10266/28080 [20:17:29<35:10:57,  7.11s/it]
                                                           
{'loss': 0.6201, 'learning_rate': 0.0003663133460663138, 'epoch': 4.39}

 37%|███▋      | 10266/28080 [20:17:29<35:10:57,  7.11s/it]
 37%|███▋      | 10267/28080 [20:17:36<35:11:12,  7.11s/it]
                                                           
{'loss': 0.6273, 'learning_rate': 0.0003662878205719037, 'epoch': 4.39}

 37%|███▋      | 10267/28080 [20:17:36<35:11:12,  7.11s/it]
 37%|███▋      | 10268/28080 [20:17:44<35:14:44,  7.12s/it]
                                                           
{'loss': 0.6359, 'learning_rate': 0.0003662622935304042, 'epoch': 4.39}

 37%|███▋      | 10268/28080 [20:17:44<35:14:44,  7.12s/it]
 37%|███▋      | 10269/28080 [20:17:51<35:09:52,  7.11s/it]
                                                           
{'loss': 0.644, 'learning_rate': 0.0003662367649421548, 'epoch': 4.39}

 37%|███▋      | 10269/28080 [20:17:51<35:09:52,  7.11s/it]
 37%|███▋      | 10270/28080 [20:17:58<35:00:41,  7.08s/it]
                                                           
{'loss': 0.6511, 'learning_rate': 0.00036621123480749514, 'epoch': 4.39}

 37%|███▋      | 10270/28080 [20:17:58<35:00:41,  7.08s/it]
 37%|███▋      | 10271/28080 [20:18:05<35:09:18,  7.11s/it]
                                                           
{'loss': 0.6194, 'learning_rate': 0.0003661857031267649, 'epoch': 4.39}

 37%|███▋      | 10271/28080 [20:18:05<35:09:18,  7.11s/it]
 37%|███▋      | 10272/28080 [20:18:12<35:14:31,  7.12s/it]
                                                           
{'loss': 0.6249, 'learning_rate': 0.00036616016990030376, 'epoch': 4.39}

 37%|███▋      | 10272/28080 [20:18:12<35:14:31,  7.12s/it]
 37%|███▋      | 10273/28080 [20:18:19<35:19:43,  7.14s/it]
                                                           
{'loss': 0.6516, 'learning_rate': 0.00036613463512845135, 'epoch': 4.39}

 37%|███▋      | 10273/28080 [20:18:19<35:19:43,  7.14s/it]
 37%|███▋      | 10274/28080 [20:18:26<35:21:03,  7.15s/it]
                                                           
{'loss': 0.6413, 'learning_rate': 0.0003661090988115475, 'epoch': 4.39}

 37%|███▋      | 10274/28080 [20:18:26<35:21:03,  7.15s/it]
 37%|███▋      | 10275/28080 [20:18:33<35:15:14,  7.13s/it]
                                                           
{'loss': 0.6318, 'learning_rate': 0.0003660835609499318, 'epoch': 4.39}

 37%|███▋      | 10275/28080 [20:18:33<35:15:14,  7.13s/it]
 37%|███▋      | 10276/28080 [20:18:40<35:02:48,  7.09s/it]
                                                           
{'loss': 0.6231, 'learning_rate': 0.0003660580215439441, 'epoch': 4.39}

 37%|███▋      | 10276/28080 [20:18:40<35:02:48,  7.09s/it]
 37%|███▋      | 10277/28080 [20:18:47<35:01:31,  7.08s/it]
                                                           
{'loss': 0.6304, 'learning_rate': 0.0003660324805939241, 'epoch': 4.39}

 37%|███▋      | 10277/28080 [20:18:47<35:01:31,  7.08s/it]
 37%|███▋      | 10278/28080 [20:18:55<35:03:49,  7.09s/it]
                                                           
{'loss': 0.6273, 'learning_rate': 0.0003660069381002118, 'epoch': 4.39}

 37%|███▋      | 10278/28080 [20:18:55<35:03:49,  7.09s/it]
 37%|███▋      | 10279/28080 [20:19:02<35:06:54,  7.10s/it]
                                                           
{'loss': 0.6367, 'learning_rate': 0.00036598139406314673, 'epoch': 4.39}

 37%|███▋      | 10279/28080 [20:19:02<35:06:54,  7.10s/it]
 37%|███▋      | 10280/28080 [20:19:09<35:05:09,  7.10s/it]
                                                           
{'loss': 0.6247, 'learning_rate': 0.00036595584848306896, 'epoch': 4.39}

 37%|███▋      | 10280/28080 [20:19:09<35:05:09,  7.10s/it]
 37%|███▋      | 10281/28080 [20:19:16<34:55:26,  7.06s/it]
                                                           
{'loss': 0.6328, 'learning_rate': 0.00036593030136031814, 'epoch': 4.39}

 37%|███▋      | 10281/28080 [20:19:16<34:55:26,  7.06s/it]
 37%|███▋      | 10282/28080 [20:19:23<34:52:27,  7.05s/it]
                                                           
{'loss': 0.6438, 'learning_rate': 0.0003659047526952343, 'epoch': 4.39}

 37%|███▋      | 10282/28080 [20:19:23<34:52:27,  7.05s/it]
 37%|███▋      | 10283/28080 [20:19:30<34:45:30,  7.03s/it]
                                                           
{'loss': 0.6434, 'learning_rate': 0.0003658792024881573, 'epoch': 4.39}

 37%|███▋      | 10283/28080 [20:19:30<34:45:30,  7.03s/it]
 37%|███▋      | 10284/28080 [20:19:37<34:52:50,  7.06s/it]
                                                           
{'loss': 0.629, 'learning_rate': 0.0003658536507394271, 'epoch': 4.39}

 37%|███▋      | 10284/28080 [20:19:37<34:52:50,  7.06s/it]
 37%|███▋      | 10285/28080 [20:19:44<34:58:17,  7.07s/it]
                                                           
{'loss': 0.6349, 'learning_rate': 0.0003658280974493836, 'epoch': 4.39}

 37%|███▋      | 10285/28080 [20:19:44<34:58:17,  7.07s/it]
 37%|███▋      | 10286/28080 [20:19:51<34:55:14,  7.07s/it]
                                                           
{'loss': 0.6369, 'learning_rate': 0.0003658025426183667, 'epoch': 4.39}

 37%|███▋      | 10286/28080 [20:19:51<34:55:14,  7.07s/it]
 37%|███▋      | 10287/28080 [20:19:58<34:51:22,  7.05s/it]
                                                           
{'loss': 0.6419, 'learning_rate': 0.00036577698624671646, 'epoch': 4.39}

 37%|███▋      | 10287/28080 [20:19:58<34:51:22,  7.05s/it]
 37%|███▋      | 10288/28080 [20:20:05<34:58:04,  7.08s/it]
                                                           
{'loss': 0.626, 'learning_rate': 0.00036575142833477286, 'epoch': 4.39}

 37%|███▋      | 10288/28080 [20:20:05<34:58:04,  7.08s/it]
 37%|███▋      | 10289/28080 [20:20:12<35:00:45,  7.08s/it]
                                                           
{'loss': 0.6308, 'learning_rate': 0.0003657258688828759, 'epoch': 4.4}

 37%|███▋      | 10289/28080 [20:20:12<35:00:45,  7.08s/it]
 37%|███▋      | 10290/28080 [20:20:19<35:00:26,  7.08s/it]
                                                           
{'loss': 0.6264, 'learning_rate': 0.00036570030789136567, 'epoch': 4.4}

 37%|███▋      | 10290/28080 [20:20:19<35:00:26,  7.08s/it]
 37%|███▋      | 10291/28080 [20:20:26<35:01:08,  7.09s/it]
                                                           
{'loss': 0.6224, 'learning_rate': 0.0003656747453605822, 'epoch': 4.4}

 37%|███▋      | 10291/28080 [20:20:27<35:01:08,  7.09s/it]
 37%|███▋      | 10292/28080 [20:20:34<35:05:58,  7.10s/it]
                                                           
{'loss': 0.6295, 'learning_rate': 0.00036564918129086563, 'epoch': 4.4}

 37%|███▋      | 10292/28080 [20:20:34<35:05:58,  7.10s/it]
 37%|███▋      | 10293/28080 [20:20:41<35:06:08,  7.10s/it]
                                                           
{'loss': 0.6347, 'learning_rate': 0.00036562361568255597, 'epoch': 4.4}

 37%|███▋      | 10293/28080 [20:20:41<35:06:08,  7.10s/it]
 37%|███▋      | 10294/28080 [20:20:48<35:00:33,  7.09s/it]
                                                           
{'loss': 0.6279, 'learning_rate': 0.00036559804853599333, 'epoch': 4.4}

 37%|███▋      | 10294/28080 [20:20:48<35:00:33,  7.09s/it]
 37%|███▋      | 10295/28080 [20:20:55<35:06:13,  7.11s/it]
                                                           
{'loss': 0.626, 'learning_rate': 0.000365572479851518, 'epoch': 4.4}

 37%|███▋      | 10295/28080 [20:20:55<35:06:13,  7.11s/it]
 37%|███▋      | 10296/28080 [20:21:02<35:03:01,  7.10s/it]
                                                           
{'loss': 0.6454, 'learning_rate': 0.00036554690962946996, 'epoch': 4.4}

 37%|███▋      | 10296/28080 [20:21:02<35:03:01,  7.10s/it]
 37%|███▋      | 10297/28080 [20:21:09<34:55:59,  7.07s/it]
                                                           
{'loss': 0.6363, 'learning_rate': 0.0003655213378701896, 'epoch': 4.4}

 37%|███▋      | 10297/28080 [20:21:09<34:55:59,  7.07s/it]
 37%|███▋      | 10298/28080 [20:21:16<35:03:27,  7.10s/it]
                                                           
{'loss': 0.6505, 'learning_rate': 0.0003654957645740169, 'epoch': 4.4}

 37%|███▋      | 10298/28080 [20:21:16<35:03:27,  7.10s/it]
 37%|███▋      | 10299/28080 [20:21:23<35:02:01,  7.09s/it]
                                                           
{'loss': 0.6101, 'learning_rate': 0.00036547018974129224, 'epoch': 4.4}

 37%|███▋      | 10299/28080 [20:21:23<35:02:01,  7.09s/it]
 37%|███▋      | 10300/28080 [20:21:30<35:01:45,  7.09s/it]
                                                           
{'loss': 0.6158, 'learning_rate': 0.0003654446133723559, 'epoch': 4.4}

 37%|███▋      | 10300/28080 [20:21:30<35:01:45,  7.09s/it]
 37%|███▋      | 10301/28080 [20:21:37<34:57:31,  7.08s/it]
                                                           
{'loss': 0.6242, 'learning_rate': 0.000365419035467548, 'epoch': 4.4}

 37%|███▋      | 10301/28080 [20:21:37<34:57:31,  7.08s/it]
 37%|███▋      | 10302/28080 [20:21:44<34:53:00,  7.06s/it]
                                                           
{'loss': 0.6158, 'learning_rate': 0.000365393456027209, 'epoch': 4.4}

 37%|███▋      | 10302/28080 [20:21:44<34:53:00,  7.06s/it]
 37%|███▋      | 10303/28080 [20:21:52<35:00:09,  7.09s/it]
                                                           
{'loss': 0.6238, 'learning_rate': 0.00036536787505167897, 'epoch': 4.4}

 37%|███▋      | 10303/28080 [20:21:52<35:00:09,  7.09s/it]
 37%|███▋      | 10304/28080 [20:21:59<35:06:27,  7.11s/it]
                                                           
{'loss': 0.6435, 'learning_rate': 0.0003653422925412985, 'epoch': 4.4}

 37%|███▋      | 10304/28080 [20:21:59<35:06:27,  7.11s/it]
 37%|███▋      | 10305/28080 [20:22:06<34:59:48,  7.09s/it]
                                                           
{'loss': 0.6411, 'learning_rate': 0.0003653167084964077, 'epoch': 4.4}

 37%|███▋      | 10305/28080 [20:22:06<34:59:48,  7.09s/it]
 37%|███▋      | 10306/28080 [20:22:13<35:01:51,  7.10s/it]
                                                           
{'loss': 0.6208, 'learning_rate': 0.0003652911229173471, 'epoch': 4.4}

 37%|███▋      | 10306/28080 [20:22:13<35:01:51,  7.10s/it]
 37%|███▋      | 10307/28080 [20:22:20<35:10:23,  7.12s/it]
                                                           
{'loss': 0.6353, 'learning_rate': 0.00036526553580445715, 'epoch': 4.4}

 37%|███▋      | 10307/28080 [20:22:20<35:10:23,  7.12s/it]
 37%|███▋      | 10308/28080 [20:22:27<35:06:18,  7.11s/it]
                                                           
{'loss': 0.6308, 'learning_rate': 0.00036523994715807805, 'epoch': 4.4}

 37%|███▋      | 10308/28080 [20:22:27<35:06:18,  7.11s/it]
 37%|███▋      | 10309/28080 [20:22:34<34:57:31,  7.08s/it]
                                                           
{'loss': 0.6246, 'learning_rate': 0.00036521435697855044, 'epoch': 4.4}

 37%|███▋      | 10309/28080 [20:22:34<34:57:31,  7.08s/it]
 37%|███▋      | 10310/28080 [20:22:41<34:57:32,  7.08s/it]
                                                           
{'loss': 0.6117, 'learning_rate': 0.00036518876526621456, 'epoch': 4.4}

 37%|███▋      | 10310/28080 [20:22:41<34:57:32,  7.08s/it]
 37%|███▋      | 10311/28080 [20:22:48<34:52:14,  7.06s/it]
                                                           
{'loss': 0.6379, 'learning_rate': 0.00036516317202141106, 'epoch': 4.4}

 37%|███▋      | 10311/28080 [20:22:48<34:52:14,  7.06s/it]
 37%|███▋      | 10312/28080 [20:22:55<34:50:54,  7.06s/it]
                                                           
{'loss': 0.6138, 'learning_rate': 0.0003651375772444803, 'epoch': 4.41}

 37%|███▋      | 10312/28080 [20:22:55<34:50:54,  7.06s/it]
 37%|███▋      | 10313/28080 [20:23:03<35:02:25,  7.10s/it]
                                                           
{'loss': 0.6139, 'learning_rate': 0.0003651119809357629, 'epoch': 4.41}

 37%|███▋      | 10313/28080 [20:23:03<35:02:25,  7.10s/it]
 37%|███▋      | 10314/28080 [20:23:10<35:07:55,  7.12s/it]
                                                           
{'loss': 0.6272, 'learning_rate': 0.0003650863830955994, 'epoch': 4.41}

 37%|███▋      | 10314/28080 [20:23:10<35:07:55,  7.12s/it]
 37%|███▋      | 10315/28080 [20:23:17<35:08:58,  7.12s/it]
                                                           
{'loss': 0.6336, 'learning_rate': 0.00036506078372433023, 'epoch': 4.41}

 37%|███▋      | 10315/28080 [20:23:17<35:08:58,  7.12s/it]
 37%|███▋      | 10316/28080 [20:23:24<35:03:18,  7.10s/it]
                                                           
{'loss': 0.6613, 'learning_rate': 0.0003650351828222961, 'epoch': 4.41}

 37%|███▋      | 10316/28080 [20:23:24<35:03:18,  7.10s/it]
 37%|███▋      | 10317/28080 [20:23:31<35:01:45,  7.10s/it]
                                                           
{'loss': 0.6402, 'learning_rate': 0.00036500958038983744, 'epoch': 4.41}

 37%|███▋      | 10317/28080 [20:23:31<35:01:45,  7.10s/it]
 37%|███▋      | 10318/28080 [20:23:38<34:58:42,  7.09s/it]
                                                           
{'loss': 0.6579, 'learning_rate': 0.000364983976427295, 'epoch': 4.41}

 37%|███▋      | 10318/28080 [20:23:38<34:58:42,  7.09s/it]
 37%|███▋      | 10319/28080 [20:23:45<35:05:59,  7.11s/it]
                                                           
{'loss': 0.6308, 'learning_rate': 0.00036495837093500946, 'epoch': 4.41}

 37%|███▋      | 10319/28080 [20:23:45<35:05:59,  7.11s/it]
 37%|███▋      | 10320/28080 [20:23:52<34:57:04,  7.08s/it]
                                                           
{'loss': 0.5998, 'learning_rate': 0.0003649327639133213, 'epoch': 4.41}

 37%|███▋      | 10320/28080 [20:23:52<34:57:04,  7.08s/it]
 37%|███▋      | 10321/28080 [20:23:59<34:55:05,  7.08s/it]
                                                           
{'loss': 0.6278, 'learning_rate': 0.0003649071553625713, 'epoch': 4.41}

 37%|███▋      | 10321/28080 [20:23:59<34:55:05,  7.08s/it]
 37%|███▋      | 10322/28080 [20:24:06<34:56:37,  7.08s/it]
                                                           
{'loss': 0.6241, 'learning_rate': 0.00036488154528310015, 'epoch': 4.41}

 37%|███▋      | 10322/28080 [20:24:06<34:56:37,  7.08s/it]
 37%|███▋      | 10323/28080 [20:24:13<34:43:59,  7.04s/it]
                                                           
{'loss': 0.6523, 'learning_rate': 0.0003648559336752485, 'epoch': 4.41}

 37%|███▋      | 10323/28080 [20:24:13<34:43:59,  7.04s/it]
 37%|███▋      | 10324/28080 [20:24:20<34:48:15,  7.06s/it]
                                                           
{'loss': 0.6229, 'learning_rate': 0.0003648303205393573, 'epoch': 4.41}

 37%|███▋      | 10324/28080 [20:24:20<34:48:15,  7.06s/it]
 37%|███▋      | 10325/28080 [20:24:27<34:41:16,  7.03s/it]
                                                           
{'loss': 0.6303, 'learning_rate': 0.00036480470587576695, 'epoch': 4.41}

 37%|███▋      | 10325/28080 [20:24:27<34:41:16,  7.03s/it]
 37%|███▋      | 10326/28080 [20:24:35<34:55:01,  7.08s/it]
                                                           
{'loss': 0.623, 'learning_rate': 0.00036477908968481857, 'epoch': 4.41}

 37%|███▋      | 10326/28080 [20:24:35<34:55:01,  7.08s/it]
 37%|███▋      | 10327/28080 [20:24:42<34:52:01,  7.07s/it]
                                                           
{'loss': 0.6329, 'learning_rate': 0.0003647534719668527, 'epoch': 4.41}

 37%|███▋      | 10327/28080 [20:24:42<34:52:01,  7.07s/it]
 37%|███▋      | 10328/28080 [20:24:49<34:55:20,  7.08s/it]
                                                           
{'loss': 0.6103, 'learning_rate': 0.00036472785272221035, 'epoch': 4.41}

 37%|███▋      | 10328/28080 [20:24:49<34:55:20,  7.08s/it]
 37%|███▋      | 10329/28080 [20:24:56<35:05:10,  7.12s/it]
                                                           
{'loss': 0.6344, 'learning_rate': 0.0003647022319512323, 'epoch': 4.41}

 37%|███▋      | 10329/28080 [20:24:56<35:05:10,  7.12s/it]
 37%|███▋      | 10330/28080 [20:25:03<34:59:30,  7.10s/it]
                                                           
{'loss': 0.6215, 'learning_rate': 0.0003646766096542593, 'epoch': 4.41}

 37%|███▋      | 10330/28080 [20:25:03<34:59:30,  7.10s/it]
 37%|███▋      | 10331/28080 [20:25:10<35:07:28,  7.12s/it]
                                                           
{'loss': 0.6285, 'learning_rate': 0.00036465098583163236, 'epoch': 4.41}

 37%|███▋      | 10331/28080 [20:25:10<35:07:28,  7.12s/it]
 37%|███▋      | 10332/28080 [20:25:17<35:14:56,  7.15s/it]
                                                           
{'loss': 0.6285, 'learning_rate': 0.0003646253604836923, 'epoch': 4.41}

 37%|███▋      | 10332/28080 [20:25:17<35:14:56,  7.15s/it]
 37%|███▋      | 10333/28080 [20:25:24<35:04:06,  7.11s/it]
                                                           
{'loss': 0.6425, 'learning_rate': 0.0003645997336107802, 'epoch': 4.41}

 37%|███▋      | 10333/28080 [20:25:24<35:04:06,  7.11s/it]
 37%|███▋      | 10334/28080 [20:25:31<34:57:40,  7.09s/it]
                                                           
{'loss': 0.6167, 'learning_rate': 0.0003645741052132368, 'epoch': 4.41}

 37%|███▋      | 10334/28080 [20:25:31<34:57:40,  7.09s/it]
 37%|███▋      | 10335/28080 [20:25:39<34:55:47,  7.09s/it]
                                                           
{'loss': 0.6379, 'learning_rate': 0.00036454847529140304, 'epoch': 4.42}

 37%|███▋      | 10335/28080 [20:25:39<34:55:47,  7.09s/it]
 37%|███▋      | 10336/28080 [20:25:46<35:02:30,  7.11s/it]
                                                           
{'loss': 0.6353, 'learning_rate': 0.00036452284384562005, 'epoch': 4.42}

 37%|███▋      | 10336/28080 [20:25:46<35:02:30,  7.11s/it]
 37%|███▋      | 10337/28080 [20:25:53<35:05:59,  7.12s/it]
                                                           
{'loss': 0.6157, 'learning_rate': 0.0003644972108762288, 'epoch': 4.42}

 37%|███▋      | 10337/28080 [20:25:53<35:05:59,  7.12s/it]
 37%|███▋      | 10338/28080 [20:26:00<35:11:06,  7.14s/it]
                                                           
{'loss': 0.6442, 'learning_rate': 0.0003644715763835702, 'epoch': 4.42}

 37%|███▋      | 10338/28080 [20:26:00<35:11:06,  7.14s/it]
 37%|███▋      | 10339/28080 [20:26:07<34:59:56,  7.10s/it]
                                                           
{'loss': 0.6188, 'learning_rate': 0.0003644459403679854, 'epoch': 4.42}

 37%|███▋      | 10339/28080 [20:26:07<34:59:56,  7.10s/it]
 37%|███▋      | 10340/28080 [20:26:14<35:01:19,  7.11s/it]
                                                           
{'loss': 0.6307, 'learning_rate': 0.00036442030282981554, 'epoch': 4.42}

 37%|███▋      | 10340/28080 [20:26:14<35:01:19,  7.11s/it]
 37%|███▋      | 10341/28080 [20:26:21<34:58:07,  7.10s/it]
                                                           
{'loss': 0.6314, 'learning_rate': 0.00036439466376940146, 'epoch': 4.42}

 37%|███▋      | 10341/28080 [20:26:21<34:58:07,  7.10s/it]
 37%|███▋      | 10342/28080 [20:26:28<35:01:21,  7.11s/it]
                                                           
{'loss': 0.6328, 'learning_rate': 0.00036436902318708443, 'epoch': 4.42}

 37%|███▋      | 10342/28080 [20:26:28<35:01:21,  7.11s/it]
 37%|███▋      | 10343/28080 [20:26:35<34:57:37,  7.10s/it]
                                                           
{'loss': 0.6402, 'learning_rate': 0.00036434338108320556, 'epoch': 4.42}

 37%|███▋      | 10343/28080 [20:26:35<34:57:37,  7.10s/it]
 37%|███▋      | 10344/28080 [20:26:43<35:00:21,  7.11s/it]
                                                           
{'loss': 0.6206, 'learning_rate': 0.00036431773745810594, 'epoch': 4.42}

 37%|███▋      | 10344/28080 [20:26:43<35:00:21,  7.11s/it]
 37%|███▋      | 10345/28080 [20:26:50<35:01:22,  7.11s/it]
                                                           
{'loss': 0.6519, 'learning_rate': 0.0003642920923121268, 'epoch': 4.42}

 37%|███▋      | 10345/28080 [20:26:50<35:01:22,  7.11s/it]
 37%|███▋      | 10346/28080 [20:26:57<35:08:46,  7.13s/it]
                                                           
{'loss': 0.6153, 'learning_rate': 0.00036426644564560925, 'epoch': 4.42}

 37%|███▋      | 10346/28080 [20:26:57<35:08:46,  7.13s/it]
 37%|███▋      | 10347/28080 [20:27:04<35:18:07,  7.17s/it]
                                                           
{'loss': 0.6452, 'learning_rate': 0.0003642407974588945, 'epoch': 4.42}

 37%|███▋      | 10347/28080 [20:27:04<35:18:07,  7.17s/it]
 37%|███▋      | 10348/28080 [20:27:11<35:20:14,  7.17s/it]
                                                           
{'loss': 0.5978, 'learning_rate': 0.0003642151477523238, 'epoch': 4.42}

 37%|███▋      | 10348/28080 [20:27:11<35:20:14,  7.17s/it]
 37%|███▋      | 10349/28080 [20:27:19<35:26:29,  7.20s/it]
                                                           
{'loss': 0.6541, 'learning_rate': 0.00036418949652623837, 'epoch': 4.42}

 37%|███▋      | 10349/28080 [20:27:19<35:26:29,  7.20s/it]
 37%|███▋      | 10350/28080 [20:27:26<35:29:48,  7.21s/it]
                                                           
{'loss': 0.6124, 'learning_rate': 0.0003641638437809796, 'epoch': 4.42}

 37%|███▋      | 10350/28080 [20:27:26<35:29:48,  7.21s/it]
 37%|███▋      | 10351/28080 [20:27:33<35:23:15,  7.19s/it]
                                                           
{'loss': 0.6185, 'learning_rate': 0.0003641381895168885, 'epoch': 4.42}

 37%|███▋      | 10351/28080 [20:27:33<35:23:15,  7.19s/it]
 37%|███▋      | 10352/28080 [20:27:40<35:11:57,  7.15s/it]
                                                           
{'loss': 0.6317, 'learning_rate': 0.0003641125337343067, 'epoch': 4.42}

 37%|███▋      | 10352/28080 [20:27:40<35:11:57,  7.15s/it]
 37%|███▋      | 10353/28080 [20:27:47<35:03:35,  7.12s/it]
                                                           
{'loss': 0.6286, 'learning_rate': 0.0003640868764335753, 'epoch': 4.42}

 37%|███▋      | 10353/28080 [20:27:47<35:03:35,  7.12s/it]
 37%|███▋      | 10354/28080 [20:27:54<35:10:45,  7.14s/it]
                                                           
{'loss': 0.6256, 'learning_rate': 0.00036406121761503563, 'epoch': 4.42}

 37%|███▋      | 10354/28080 [20:27:54<35:10:45,  7.14s/it]
 37%|███▋      | 10355/28080 [20:28:01<35:04:48,  7.12s/it]
                                                           
{'loss': 0.6317, 'learning_rate': 0.00036403555727902926, 'epoch': 4.42}

 37%|███▋      | 10355/28080 [20:28:01<35:04:48,  7.12s/it]
 37%|███▋      | 10356/28080 [20:28:08<35:05:08,  7.13s/it]
                                                           
{'loss': 0.6393, 'learning_rate': 0.0003640098954258974, 'epoch': 4.42}

 37%|███▋      | 10356/28080 [20:28:08<35:05:08,  7.13s/it]
 37%|███▋      | 10357/28080 [20:28:16<35:02:29,  7.12s/it]
                                                           
{'loss': 0.6297, 'learning_rate': 0.0003639842320559814, 'epoch': 4.42}

 37%|███▋      | 10357/28080 [20:28:16<35:02:29,  7.12s/it]
 37%|███▋      | 10358/28080 [20:28:23<35:02:48,  7.12s/it]
                                                           
{'loss': 0.6357, 'learning_rate': 0.0003639585671696229, 'epoch': 4.42}

 37%|███▋      | 10358/28080 [20:28:23<35:02:48,  7.12s/it]
 37%|███▋      | 10359/28080 [20:28:30<34:56:44,  7.10s/it]
                                                           
{'loss': 0.6318, 'learning_rate': 0.00036393290076716325, 'epoch': 4.43}

 37%|███▋      | 10359/28080 [20:28:30<34:56:44,  7.10s/it]
 37%|███▋      | 10360/28080 [20:28:37<34:54:11,  7.09s/it]
                                                           
{'loss': 0.633, 'learning_rate': 0.0003639072328489438, 'epoch': 4.43}

 37%|███▋      | 10360/28080 [20:28:37<34:54:11,  7.09s/it]
 37%|███▋      | 10361/28080 [20:28:44<34:55:02,  7.09s/it]
                                                           
{'loss': 0.6286, 'learning_rate': 0.0003638815634153061, 'epoch': 4.43}

 37%|███▋      | 10361/28080 [20:28:44<34:55:02,  7.09s/it]
 37%|███▋      | 10362/28080 [20:28:51<34:59:04,  7.11s/it]
                                                           
{'loss': 0.6145, 'learning_rate': 0.0003638558924665918, 'epoch': 4.43}

 37%|███▋      | 10362/28080 [20:28:51<34:59:04,  7.11s/it]
 37%|███▋      | 10363/28080 [20:28:58<34:54:01,  7.09s/it]
                                                           
{'loss': 0.6257, 'learning_rate': 0.0003638302200031422, 'epoch': 4.43}

 37%|███▋      | 10363/28080 [20:28:58<34:54:01,  7.09s/it]
 37%|███▋      | 10364/28080 [20:29:05<34:52:41,  7.09s/it]
                                                           
{'loss': 0.6104, 'learning_rate': 0.00036380454602529905, 'epoch': 4.43}

 37%|███▋      | 10364/28080 [20:29:05<34:52:41,  7.09s/it]
 37%|███▋      | 10365/28080 [20:29:12<35:00:17,  7.11s/it]
                                                           
{'loss': 0.6276, 'learning_rate': 0.00036377887053340376, 'epoch': 4.43}

 37%|███▋      | 10365/28080 [20:29:12<35:00:17,  7.11s/it]
 37%|███▋      | 10366/28080 [20:29:19<34:44:39,  7.06s/it]
                                                           
{'loss': 0.6425, 'learning_rate': 0.00036375319352779803, 'epoch': 4.43}

 37%|███▋      | 10366/28080 [20:29:19<34:44:39,  7.06s/it]
 37%|███▋      | 10367/28080 [20:29:26<34:55:07,  7.10s/it]
                                                           
{'loss': 0.6023, 'learning_rate': 0.00036372751500882334, 'epoch': 4.43}

 37%|███▋      | 10367/28080 [20:29:26<34:55:07,  7.10s/it]
 37%|███▋      | 10368/28080 [20:29:34<35:04:10,  7.13s/it]
                                                           
{'loss': 0.6234, 'learning_rate': 0.0003637018349768215, 'epoch': 4.43}

 37%|███▋      | 10368/28080 [20:29:34<35:04:10,  7.13s/it]
 37%|███▋      | 10369/28080 [20:29:41<34:55:42,  7.10s/it]
                                                           
{'loss': 0.6377, 'learning_rate': 0.00036367615343213403, 'epoch': 4.43}

 37%|███▋      | 10369/28080 [20:29:41<34:55:42,  7.10s/it]
 37%|███▋      | 10370/28080 [20:29:48<34:56:08,  7.10s/it]
                                                           
{'loss': 0.6398, 'learning_rate': 0.00036365047037510245, 'epoch': 4.43}

 37%|███▋      | 10370/28080 [20:29:48<34:56:08,  7.10s/it]
 37%|███▋      | 10371/28080 [20:29:55<34:50:38,  7.08s/it]
                                                           
{'loss': 0.6363, 'learning_rate': 0.0003636247858060687, 'epoch': 4.43}

 37%|███▋      | 10371/28080 [20:29:55<34:50:38,  7.08s/it]
 37%|███▋      | 10372/28080 [20:30:02<34:57:16,  7.11s/it]
                                                           
{'loss': 0.6399, 'learning_rate': 0.0003635990997253745, 'epoch': 4.43}

 37%|███▋      | 10372/28080 [20:30:02<34:57:16,  7.11s/it]
 37%|███▋      | 10373/28080 [20:30:09<34:53:21,  7.09s/it]
                                                           
{'loss': 0.6509, 'learning_rate': 0.0003635734121333613, 'epoch': 4.43}

 37%|███▋      | 10373/28080 [20:30:09<34:53:21,  7.09s/it]
 37%|███▋      | 10374/28080 [20:30:16<34:47:06,  7.07s/it]
                                                           
{'loss': 0.6387, 'learning_rate': 0.0003635477230303711, 'epoch': 4.43}

 37%|███▋      | 10374/28080 [20:30:16<34:47:06,  7.07s/it]
 37%|███▋      | 10375/28080 [20:30:23<34:45:27,  7.07s/it]
                                                           
{'loss': 0.6402, 'learning_rate': 0.00036352203241674563, 'epoch': 4.43}

 37%|███▋      | 10375/28080 [20:30:23<34:45:27,  7.07s/it]
 37%|███▋      | 10376/28080 [20:30:30<34:45:28,  7.07s/it]
                                                           
{'loss': 0.626, 'learning_rate': 0.00036349634029282657, 'epoch': 4.43}

 37%|███▋      | 10376/28080 [20:30:30<34:45:28,  7.07s/it]
 37%|███▋      | 10377/28080 [20:30:37<34:49:38,  7.08s/it]
                                                           
{'loss': 0.6271, 'learning_rate': 0.0003634706466589558, 'epoch': 4.43}

 37%|███▋      | 10377/28080 [20:30:37<34:49:38,  7.08s/it]
 37%|███▋      | 10378/28080 [20:30:44<34:44:46,  7.07s/it]
                                                           
{'loss': 0.6339, 'learning_rate': 0.0003634449515154751, 'epoch': 4.43}

 37%|███▋      | 10378/28080 [20:30:44<34:44:46,  7.07s/it]
 37%|███▋      | 10379/28080 [20:30:51<34:46:13,  7.07s/it]
                                                           
{'loss': 0.6374, 'learning_rate': 0.0003634192548627265, 'epoch': 4.43}

 37%|███▋      | 10379/28080 [20:30:51<34:46:13,  7.07s/it]
 37%|███▋      | 10380/28080 [20:30:59<34:51:24,  7.09s/it]
                                                           
{'loss': 0.6616, 'learning_rate': 0.00036339355670105157, 'epoch': 4.43}

 37%|███▋      | 10380/28080 [20:30:59<34:51:24,  7.09s/it]
 37%|███▋      | 10381/28080 [20:31:06<34:46:16,  7.07s/it]
                                                           
{'loss': 0.6298, 'learning_rate': 0.00036336785703079244, 'epoch': 4.43}

 37%|███▋      | 10381/28080 [20:31:06<34:46:16,  7.07s/it]
 37%|███▋      | 10382/28080 [20:31:13<34:48:00,  7.08s/it]
                                                           
{'loss': 0.6243, 'learning_rate': 0.0003633421558522909, 'epoch': 4.44}

 37%|███▋      | 10382/28080 [20:31:13<34:48:00,  7.08s/it]
 37%|███▋      | 10383/28080 [20:31:20<34:58:14,  7.11s/it]
                                                           
{'loss': 0.6123, 'learning_rate': 0.0003633164531658889, 'epoch': 4.44}

 37%|███▋      | 10383/28080 [20:31:20<34:58:14,  7.11s/it]
 37%|███▋      | 10384/28080 [20:31:27<34:55:03,  7.10s/it]
                                                           
{'loss': 0.6347, 'learning_rate': 0.00036329074897192837, 'epoch': 4.44}

 37%|███▋      | 10384/28080 [20:31:27<34:55:03,  7.10s/it]
 37%|███▋      | 10385/28080 [20:31:34<35:00:01,  7.12s/it]
                                                           
{'loss': 0.6106, 'learning_rate': 0.0003632650432707513, 'epoch': 4.44}

 37%|███▋      | 10385/28080 [20:31:34<35:00:01,  7.12s/it]
 37%|███▋      | 10386/28080 [20:31:41<34:51:40,  7.09s/it]
                                                           
{'loss': 0.6038, 'learning_rate': 0.0003632393360626997, 'epoch': 4.44}

 37%|███▋      | 10386/28080 [20:31:41<34:51:40,  7.09s/it]
 37%|███▋      | 10387/28080 [20:31:48<34:49:39,  7.09s/it]
                                                           
{'loss': 0.6462, 'learning_rate': 0.00036321362734811555, 'epoch': 4.44}

 37%|███▋      | 10387/28080 [20:31:48<34:49:39,  7.09s/it]
 37%|███▋      | 10388/28080 [20:31:55<34:57:55,  7.11s/it]
                                                           
{'loss': 0.6143, 'learning_rate': 0.00036318791712734087, 'epoch': 4.44}

 37%|███▋      | 10388/28080 [20:31:55<34:57:55,  7.11s/it]
 37%|███▋      | 10389/28080 [20:32:03<35:00:02,  7.12s/it]
                                                           
{'loss': 0.6192, 'learning_rate': 0.00036316220540071775, 'epoch': 4.44}

 37%|███▋      | 10389/28080 [20:32:03<35:00:02,  7.12s/it]
 37%|███▋      | 10390/28080 [20:32:10<34:44:13,  7.07s/it]
                                                           
{'loss': 0.632, 'learning_rate': 0.00036313649216858823, 'epoch': 4.44}

 37%|███▋      | 10390/28080 [20:32:10<34:44:13,  7.07s/it]
 37%|███▋      | 10391/28080 [20:32:17<34:40:32,  7.06s/it]
                                                           
{'loss': 0.6321, 'learning_rate': 0.0003631107774312944, 'epoch': 4.44}

 37%|███▋      | 10391/28080 [20:32:17<34:40:32,  7.06s/it]
 37%|███▋      | 10392/28080 [20:32:24<34:44:30,  7.07s/it]
                                                           
{'loss': 0.6238, 'learning_rate': 0.00036308506118917826, 'epoch': 4.44}

 37%|███▋      | 10392/28080 [20:32:24<34:44:30,  7.07s/it]
 37%|███▋      | 10393/28080 [20:32:31<34:44:57,  7.07s/it]
                                                           
{'loss': 0.5914, 'learning_rate': 0.0003630593434425823, 'epoch': 4.44}

 37%|███▋      | 10393/28080 [20:32:31<34:44:57,  7.07s/it]
 37%|███▋      | 10394/28080 [20:32:38<34:38:06,  7.05s/it]
                                                           
{'loss': 0.6609, 'learning_rate': 0.00036303362419184813, 'epoch': 4.44}

 37%|███▋      | 10394/28080 [20:32:38<34:38:06,  7.05s/it]
 37%|███▋      | 10395/28080 [20:32:45<34:40:52,  7.06s/it]
                                                           
{'loss': 0.6324, 'learning_rate': 0.0003630079034373184, 'epoch': 4.44}

 37%|███▋      | 10395/28080 [20:32:45<34:40:52,  7.06s/it]
 37%|███▋      | 10396/28080 [20:32:52<34:39:38,  7.06s/it]
                                                           
{'loss': 0.6409, 'learning_rate': 0.000362982181179335, 'epoch': 4.44}

 37%|███▋      | 10396/28080 [20:32:52<34:39:38,  7.06s/it]
 37%|███▋      | 10397/28080 [20:32:59<34:53:34,  7.10s/it]
                                                           
{'loss': 0.631, 'learning_rate': 0.0003629564574182402, 'epoch': 4.44}

 37%|███▋      | 10397/28080 [20:32:59<34:53:34,  7.10s/it]
 37%|███▋      | 10398/28080 [20:33:06<34:45:23,  7.08s/it]
                                                           
{'loss': 0.6266, 'learning_rate': 0.0003629307321543764, 'epoch': 4.44}

 37%|███▋      | 10398/28080 [20:33:06<34:45:23,  7.08s/it]
 37%|███▋      | 10399/28080 [20:33:13<34:46:21,  7.08s/it]
                                                           
{'loss': 0.6333, 'learning_rate': 0.00036290500538808555, 'epoch': 4.44}

 37%|███▋      | 10399/28080 [20:33:13<34:46:21,  7.08s/it]
 37%|███▋      | 10400/28080 [20:33:20<34:45:20,  7.08s/it]
                                                           
{'loss': 0.6114, 'learning_rate': 0.00036287927711971024, 'epoch': 4.44}

 37%|███▋      | 10400/28080 [20:33:20<34:45:20,  7.08s/it]
 37%|███▋      | 10401/28080 [20:33:27<34:44:03,  7.07s/it]
                                                           
{'loss': 0.6316, 'learning_rate': 0.0003628535473495925, 'epoch': 4.44}

 37%|███▋      | 10401/28080 [20:33:27<34:44:03,  7.07s/it]
 37%|███▋      | 10402/28080 [20:33:34<34:39:44,  7.06s/it]
                                                           
{'loss': 0.6226, 'learning_rate': 0.0003628278160780747, 'epoch': 4.44}

 37%|███▋      | 10402/28080 [20:33:34<34:39:44,  7.06s/it]
 37%|███▋      | 10403/28080 [20:33:41<34:42:29,  7.07s/it]
                                                           
{'loss': 0.6379, 'learning_rate': 0.00036280208330549934, 'epoch': 4.44}

 37%|███▋      | 10403/28080 [20:33:41<34:42:29,  7.07s/it]
 37%|███▋      | 10404/28080 [20:33:48<34:43:57,  7.07s/it]
                                                           
{'loss': 0.6341, 'learning_rate': 0.0003627763490322085, 'epoch': 4.44}

 37%|███▋      | 10404/28080 [20:33:48<34:43:57,  7.07s/it]
 37%|███▋      | 10405/28080 [20:33:56<34:48:07,  7.09s/it]
                                                           
{'loss': 0.6172, 'learning_rate': 0.0003627506132585448, 'epoch': 4.44}

 37%|███▋      | 10405/28080 [20:33:56<34:48:07,  7.09s/it]
 37%|███▋      | 10406/28080 [20:34:03<34:50:33,  7.10s/it]
                                                           
{'loss': 0.6068, 'learning_rate': 0.00036272487598485044, 'epoch': 4.45}

 37%|███▋      | 10406/28080 [20:34:03<34:50:33,  7.10s/it]
 37%|███▋      | 10407/28080 [20:34:10<34:48:57,  7.09s/it]
                                                           
{'loss': 0.6463, 'learning_rate': 0.0003626991372114679, 'epoch': 4.45}

 37%|███▋      | 10407/28080 [20:34:10<34:48:57,  7.09s/it]
 37%|███▋      | 10408/28080 [20:34:17<34:48:15,  7.09s/it]
                                                           
{'loss': 0.6062, 'learning_rate': 0.00036267339693873957, 'epoch': 4.45}

 37%|███▋      | 10408/28080 [20:34:17<34:48:15,  7.09s/it]
 37%|███▋      | 10409/28080 [20:34:24<34:48:29,  7.09s/it]
                                                           
{'loss': 0.6353, 'learning_rate': 0.000362647655167008, 'epoch': 4.45}

 37%|███▋      | 10409/28080 [20:34:24<34:48:29,  7.09s/it]
 37%|███▋      | 10410/28080 [20:34:31<34:47:53,  7.09s/it]
                                                           
{'loss': 0.6366, 'learning_rate': 0.0003626219118966156, 'epoch': 4.45}

 37%|███▋      | 10410/28080 [20:34:31<34:47:53,  7.09s/it]
 37%|███▋      | 10411/28080 [20:34:38<34:39:53,  7.06s/it]
                                                           
{'loss': 0.6192, 'learning_rate': 0.0003625961671279048, 'epoch': 4.45}

 37%|███▋      | 10411/28080 [20:34:38<34:39:53,  7.06s/it]
 37%|███▋      | 10412/28080 [20:34:45<34:40:28,  7.07s/it]
                                                           
{'loss': 0.6205, 'learning_rate': 0.00036257042086121816, 'epoch': 4.45}

 37%|███▋      | 10412/28080 [20:34:45<34:40:28,  7.07s/it]
 37%|███▋      | 10413/28080 [20:34:52<34:35:22,  7.05s/it]
                                                           
{'loss': 0.64, 'learning_rate': 0.0003625446730968982, 'epoch': 4.45}

 37%|███▋      | 10413/28080 [20:34:52<34:35:22,  7.05s/it]
 37%|███▋      | 10414/28080 [20:34:59<34:39:46,  7.06s/it]
                                                           
{'loss': 0.6391, 'learning_rate': 0.0003625189238352875, 'epoch': 4.45}

 37%|███▋      | 10414/28080 [20:34:59<34:39:46,  7.06s/it]
 37%|███▋      | 10415/28080 [20:35:06<34:31:17,  7.04s/it]
                                                           
{'loss': 0.6093, 'learning_rate': 0.0003624931730767286, 'epoch': 4.45}

 37%|███▋      | 10415/28080 [20:35:06<34:31:17,  7.04s/it]
 37%|███▋      | 10416/28080 [20:35:13<34:30:19,  7.03s/it]
                                                           
{'loss': 0.6367, 'learning_rate': 0.00036246742082156395, 'epoch': 4.45}

 37%|███▋      | 10416/28080 [20:35:13<34:30:19,  7.03s/it]
 37%|███▋      | 10417/28080 [20:35:20<34:34:18,  7.05s/it]
                                                           
{'loss': 0.6214, 'learning_rate': 0.0003624416670701365, 'epoch': 4.45}

 37%|███▋      | 10417/28080 [20:35:20<34:34:18,  7.05s/it]
 37%|███▋      | 10418/28080 [20:35:27<34:37:46,  7.06s/it]
                                                           
{'loss': 0.6443, 'learning_rate': 0.00036241591182278854, 'epoch': 4.45}

 37%|███▋      | 10418/28080 [20:35:27<34:37:46,  7.06s/it]
 37%|███▋      | 10419/28080 [20:35:35<34:41:23,  7.07s/it]
                                                           
{'loss': 0.6297, 'learning_rate': 0.0003623901550798629, 'epoch': 4.45}

 37%|███▋      | 10419/28080 [20:35:35<34:41:23,  7.07s/it]
 37%|███▋      | 10420/28080 [20:35:42<34:42:11,  7.07s/it]
                                                           
{'loss': 0.623, 'learning_rate': 0.0003623643968417022, 'epoch': 4.45}

 37%|███▋      | 10420/28080 [20:35:42<34:42:11,  7.07s/it]
 37%|███▋      | 10421/28080 [20:35:49<34:37:01,  7.06s/it]
                                                           
{'loss': 0.631, 'learning_rate': 0.00036233863710864907, 'epoch': 4.45}

 37%|███▋      | 10421/28080 [20:35:49<34:37:01,  7.06s/it]
 37%|███▋      | 10422/28080 [20:35:56<34:35:28,  7.05s/it]
                                                           
{'loss': 0.6286, 'learning_rate': 0.00036231287588104634, 'epoch': 4.45}

 37%|███▋      | 10422/28080 [20:35:56<34:35:28,  7.05s/it]
 37%|███▋      | 10423/28080 [20:36:03<34:33:11,  7.04s/it]
                                                           
{'loss': 0.6343, 'learning_rate': 0.0003622871131592366, 'epoch': 4.45}

 37%|███▋      | 10423/28080 [20:36:03<34:33:11,  7.04s/it]
 37%|███▋      | 10424/28080 [20:36:10<34:33:36,  7.05s/it]
                                                           
{'loss': 0.652, 'learning_rate': 0.00036226134894356264, 'epoch': 4.45}

 37%|███▋      | 10424/28080 [20:36:10<34:33:36,  7.05s/it]
 37%|███▋      | 10425/28080 [20:36:17<34:35:38,  7.05s/it]
                                                           
{'loss': 0.6379, 'learning_rate': 0.0003622355832343673, 'epoch': 4.45}

 37%|███▋      | 10425/28080 [20:36:17<34:35:38,  7.05s/it]
 37%|███▋      | 10426/28080 [20:36:24<34:38:43,  7.06s/it]
                                                           
{'loss': 0.6361, 'learning_rate': 0.0003622098160319932, 'epoch': 4.45}

 37%|███▋      | 10426/28080 [20:36:24<34:38:43,  7.06s/it]
 37%|███▋      | 10427/28080 [20:36:31<34:36:56,  7.06s/it]
                                                           
{'loss': 0.6222, 'learning_rate': 0.0003621840473367834, 'epoch': 4.45}

 37%|███▋      | 10427/28080 [20:36:31<34:36:56,  7.06s/it]
 37%|███▋      | 10428/28080 [20:36:38<34:47:09,  7.09s/it]
                                                           
{'loss': 0.6215, 'learning_rate': 0.0003621582771490805, 'epoch': 4.45}

 37%|███▋      | 10428/28080 [20:36:38<34:47:09,  7.09s/it]
 37%|███▋      | 10429/28080 [20:36:45<34:46:36,  7.09s/it]
                                                           
{'loss': 0.6207, 'learning_rate': 0.0003621325054692275, 'epoch': 4.46}

 37%|███▋      | 10429/28080 [20:36:45<34:46:36,  7.09s/it]
 37%|███▋      | 10430/28080 [20:36:52<34:51:38,  7.11s/it]
                                                           
{'loss': 0.639, 'learning_rate': 0.00036210673229756715, 'epoch': 4.46}

 37%|███▋      | 10430/28080 [20:36:52<34:51:38,  7.11s/it]
 37%|███▋      | 10431/28080 [20:36:59<34:51:43,  7.11s/it]
                                                           
{'loss': 0.6155, 'learning_rate': 0.00036208095763444237, 'epoch': 4.46}

 37%|███▋      | 10431/28080 [20:36:59<34:51:43,  7.11s/it]
 37%|███▋      | 10432/28080 [20:37:07<35:02:11,  7.15s/it]
                                                           
{'loss': 0.6116, 'learning_rate': 0.0003620551814801961, 'epoch': 4.46}

 37%|███▋      | 10432/28080 [20:37:07<35:02:11,  7.15s/it]
 37%|███▋      | 10433/28080 [20:37:14<35:04:58,  7.16s/it]
                                                           
{'loss': 0.6206, 'learning_rate': 0.00036202940383517124, 'epoch': 4.46}

 37%|███▋      | 10433/28080 [20:37:14<35:04:58,  7.16s/it]
 37%|███▋      | 10434/28080 [20:37:21<35:19:00,  7.21s/it]
                                                           
{'loss': 0.6251, 'learning_rate': 0.0003620036246997107, 'epoch': 4.46}

 37%|███▋      | 10434/28080 [20:37:21<35:19:00,  7.21s/it]
 37%|███▋      | 10435/28080 [20:37:29<35:40:49,  7.28s/it]
                                                           
{'loss': 0.6118, 'learning_rate': 0.0003619778440741575, 'epoch': 4.46}

 37%|███▋      | 10435/28080 [20:37:29<35:40:49,  7.28s/it]
 37%|███▋      | 10436/28080 [20:37:36<35:30:48,  7.25s/it]
                                                           
{'loss': 0.6339, 'learning_rate': 0.0003619520619588547, 'epoch': 4.46}

 37%|███▋      | 10436/28080 [20:37:36<35:30:48,  7.25s/it]
 37%|███▋      | 10437/28080 [20:37:43<35:21:26,  7.21s/it]
                                                           
{'loss': 0.5961, 'learning_rate': 0.0003619262783541451, 'epoch': 4.46}

 37%|███▋      | 10437/28080 [20:37:43<35:21:26,  7.21s/it]
 37%|███▋      | 10438/28080 [20:37:50<35:03:53,  7.16s/it]
                                                           
{'loss': 0.6241, 'learning_rate': 0.0003619004932603719, 'epoch': 4.46}

 37%|███▋      | 10438/28080 [20:37:50<35:03:53,  7.16s/it]
 37%|███▋      | 10439/28080 [20:37:57<34:52:22,  7.12s/it]
                                                           
{'loss': 0.6225, 'learning_rate': 0.00036187470667787804, 'epoch': 4.46}

 37%|███▋      | 10439/28080 [20:37:57<34:52:22,  7.12s/it]
 37%|███▋      | 10440/28080 [20:38:04<34:41:21,  7.08s/it]
                                                           
{'loss': 0.6509, 'learning_rate': 0.00036184891860700655, 'epoch': 4.46}

 37%|███▋      | 10440/28080 [20:38:04<34:41:21,  7.08s/it]
 37%|███▋      | 10441/28080 [20:38:11<34:42:09,  7.08s/it]
                                                           
{'loss': 0.6315, 'learning_rate': 0.00036182312904810065, 'epoch': 4.46}

 37%|███▋      | 10441/28080 [20:38:11<34:42:09,  7.08s/it]
 37%|███▋      | 10442/28080 [20:38:18<34:47:58,  7.10s/it]
                                                           
{'loss': 0.6156, 'learning_rate': 0.0003617973380015034, 'epoch': 4.46}

 37%|███▋      | 10442/28080 [20:38:18<34:47:58,  7.10s/it]
 37%|███▋      | 10443/28080 [20:38:25<34:31:02,  7.05s/it]
                                                           
{'loss': 0.6555, 'learning_rate': 0.000361771545467558, 'epoch': 4.46}

 37%|███▋      | 10443/28080 [20:38:25<34:31:02,  7.05s/it]
 37%|███▋      | 10444/28080 [20:38:32<34:37:04,  7.07s/it]
                                                           
{'loss': 0.6158, 'learning_rate': 0.00036174575144660737, 'epoch': 4.46}

 37%|███▋      | 10444/28080 [20:38:32<34:37:04,  7.07s/it]
 37%|███▋      | 10445/28080 [20:38:39<34:40:59,  7.08s/it]
                                                           
{'loss': 0.647, 'learning_rate': 0.0003617199559389948, 'epoch': 4.46}

 37%|███▋      | 10445/28080 [20:38:39<34:40:59,  7.08s/it]
 37%|███▋      | 10446/28080 [20:38:46<34:39:42,  7.08s/it]
                                                           
{'loss': 0.6262, 'learning_rate': 0.0003616941589450635, 'epoch': 4.46}

 37%|███▋      | 10446/28080 [20:38:46<34:39:42,  7.08s/it]
 37%|███▋      | 10447/28080 [20:38:54<34:38:13,  7.07s/it]
                                                           
{'loss': 0.6333, 'learning_rate': 0.00036166836046515663, 'epoch': 4.46}

 37%|███▋      | 10447/28080 [20:38:54<34:38:13,  7.07s/it]
 37%|███▋      | 10448/28080 [20:39:01<34:34:47,  7.06s/it]
                                                           
{'loss': 0.6368, 'learning_rate': 0.0003616425604996174, 'epoch': 4.46}

 37%|███▋      | 10448/28080 [20:39:01<34:34:47,  7.06s/it]
 37%|███▋      | 10449/28080 [20:39:08<34:38:50,  7.07s/it]
                                                           
{'loss': 0.6284, 'learning_rate': 0.0003616167590487891, 'epoch': 4.46}

 37%|███▋      | 10449/28080 [20:39:08<34:38:50,  7.07s/it]
 37%|███▋      | 10450/28080 [20:39:15<34:43:26,  7.09s/it]
                                                           
{'loss': 0.6385, 'learning_rate': 0.00036159095611301494, 'epoch': 4.46}

 37%|███▋      | 10450/28080 [20:39:15<34:43:26,  7.09s/it]
 37%|███▋      | 10451/28080 [20:39:22<34:43:19,  7.09s/it]
                                                           
{'loss': 0.6432, 'learning_rate': 0.0003615651516926383, 'epoch': 4.46}

 37%|███▋      | 10451/28080 [20:39:22<34:43:19,  7.09s/it]
 37%|███▋      | 10452/28080 [20:39:29<34:49:37,  7.11s/it]
                                                           
{'loss': 0.6202, 'learning_rate': 0.0003615393457880024, 'epoch': 4.46}

 37%|███▋      | 10452/28080 [20:39:29<34:49:37,  7.11s/it]
 37%|███▋      | 10453/28080 [20:39:36<34:51:45,  7.12s/it]
                                                           
{'loss': 0.6266, 'learning_rate': 0.00036151353839945056, 'epoch': 4.47}

 37%|███▋      | 10453/28080 [20:39:36<34:51:45,  7.12s/it]
 37%|███▋      | 10454/28080 [20:39:43<34:42:38,  7.09s/it]
                                                           
{'loss': 0.636, 'learning_rate': 0.0003614877295273261, 'epoch': 4.47}

 37%|███▋      | 10454/28080 [20:39:43<34:42:38,  7.09s/it]
 37%|███▋      | 10455/28080 [20:39:50<34:38:51,  7.08s/it]
                                                           
{'loss': 0.6441, 'learning_rate': 0.00036146191917197246, 'epoch': 4.47}

 37%|███▋      | 10455/28080 [20:39:50<34:38:51,  7.08s/it]
 37%|███▋      | 10456/28080 [20:39:57<34:38:25,  7.08s/it]
                                                           
{'loss': 0.6288, 'learning_rate': 0.00036143610733373297, 'epoch': 4.47}

 37%|███▋      | 10456/28080 [20:39:57<34:38:25,  7.08s/it]
 37%|███▋      | 10457/28080 [20:40:04<34:45:27,  7.10s/it]
                                                           
{'loss': 0.6243, 'learning_rate': 0.00036141029401295097, 'epoch': 4.47}

 37%|███▋      | 10457/28080 [20:40:04<34:45:27,  7.10s/it]
 37%|███▋      | 10458/28080 [20:40:12<34:50:54,  7.12s/it]
                                                           
{'loss': 0.6325, 'learning_rate': 0.00036138447920996996, 'epoch': 4.47}

 37%|███▋      | 10458/28080 [20:40:12<34:50:54,  7.12s/it]
 37%|███▋      | 10459/28080 [20:40:19<34:47:20,  7.11s/it]
                                                           
{'loss': 0.6552, 'learning_rate': 0.0003613586629251334, 'epoch': 4.47}

 37%|███▋      | 10459/28080 [20:40:19<34:47:20,  7.11s/it]
 37%|███▋      | 10460/28080 [20:40:26<34:44:12,  7.10s/it]
                                                           
{'loss': 0.6453, 'learning_rate': 0.0003613328451587847, 'epoch': 4.47}

 37%|███▋      | 10460/28080 [20:40:26<34:44:12,  7.10s/it]
 37%|███▋      | 10461/28080 [20:40:33<34:42:29,  7.09s/it]
                                                           
{'loss': 0.6318, 'learning_rate': 0.0003613070259112674, 'epoch': 4.47}

 37%|███▋      | 10461/28080 [20:40:33<34:42:29,  7.09s/it]
 37%|███▋      | 10462/28080 [20:40:40<34:40:17,  7.08s/it]
                                                           
{'loss': 0.6351, 'learning_rate': 0.0003612812051829249, 'epoch': 4.47}

 37%|███▋      | 10462/28080 [20:40:40<34:40:17,  7.08s/it]
 37%|███▋      | 10463/28080 [20:40:47<34:34:41,  7.07s/it]
                                                           
{'loss': 0.6222, 'learning_rate': 0.0003612553829741008, 'epoch': 4.47}

 37%|███▋      | 10463/28080 [20:40:47<34:34:41,  7.07s/it]
 37%|███▋      | 10464/28080 [20:40:54<34:35:14,  7.07s/it]
                                                           
{'loss': 0.6277, 'learning_rate': 0.0003612295592851385, 'epoch': 4.47}

 37%|███▋      | 10464/28080 [20:40:54<34:35:14,  7.07s/it]
 37%|███▋      | 10465/28080 [20:41:01<34:33:53,  7.06s/it]
                                                           
{'loss': 0.627, 'learning_rate': 0.0003612037341163818, 'epoch': 4.47}

 37%|███▋      | 10465/28080 [20:41:01<34:33:53,  7.06s/it]
 37%|███▋      | 10466/28080 [20:41:08<34:25:36,  7.04s/it]
                                                           
{'loss': 0.6303, 'learning_rate': 0.000361177907468174, 'epoch': 4.47}

 37%|███▋      | 10466/28080 [20:41:08<34:25:36,  7.04s/it]
 37%|███▋      | 10467/28080 [20:41:15<34:27:36,  7.04s/it]
                                                           
{'loss': 0.6454, 'learning_rate': 0.000361152079340859, 'epoch': 4.47}

 37%|███▋      | 10467/28080 [20:41:15<34:27:36,  7.04s/it]
 37%|███▋      | 10468/28080 [20:41:22<34:27:53,  7.04s/it]
                                                           
{'loss': 0.627, 'learning_rate': 0.0003611262497347802, 'epoch': 4.47}

 37%|███▋      | 10468/28080 [20:41:22<34:27:53,  7.04s/it]
 37%|███▋      | 10469/28080 [20:41:29<34:34:12,  7.07s/it]
                                                           
{'loss': 0.6267, 'learning_rate': 0.00036110041865028127, 'epoch': 4.47}

 37%|███▋      | 10469/28080 [20:41:29<34:34:12,  7.07s/it]
 37%|███▋      | 10470/28080 [20:41:36<34:38:19,  7.08s/it]
                                                           
{'loss': 0.6316, 'learning_rate': 0.0003610745860877059, 'epoch': 4.47}

 37%|███▋      | 10470/28080 [20:41:36<34:38:19,  7.08s/it]
 37%|███▋      | 10471/28080 [20:41:43<34:39:10,  7.08s/it]
                                                           
{'loss': 0.622, 'learning_rate': 0.00036104875204739765, 'epoch': 4.47}

 37%|███▋      | 10471/28080 [20:41:43<34:39:10,  7.08s/it]
 37%|███▋      | 10472/28080 [20:41:51<34:36:02,  7.07s/it]
                                                           
{'loss': 0.6455, 'learning_rate': 0.0003610229165297005, 'epoch': 4.47}

 37%|███▋      | 10472/28080 [20:41:51<34:36:02,  7.07s/it]
 37%|███▋      | 10473/28080 [20:41:58<34:38:10,  7.08s/it]
                                                           
{'loss': 0.6053, 'learning_rate': 0.00036099707953495783, 'epoch': 4.47}

 37%|███▋      | 10473/28080 [20:41:58<34:38:10,  7.08s/it]
 37%|███▋      | 10474/28080 [20:42:05<34:46:18,  7.11s/it]
                                                           
{'loss': 0.6458, 'learning_rate': 0.0003609712410635136, 'epoch': 4.47}

 37%|███▋      | 10474/28080 [20:42:05<34:46:18,  7.11s/it]
 37%|███▋      | 10475/28080 [20:42:12<34:50:14,  7.12s/it]
                                                           
{'loss': 0.6267, 'learning_rate': 0.00036094540111571144, 'epoch': 4.47}

 37%|███▋      | 10475/28080 [20:42:12<34:50:14,  7.12s/it]
 37%|███▋      | 10476/28080 [20:42:19<35:01:25,  7.16s/it]
                                                           
{'loss': 0.6364, 'learning_rate': 0.00036091955969189517, 'epoch': 4.48}

 37%|███▋      | 10476/28080 [20:42:19<35:01:25,  7.16s/it]
 37%|███▋      | 10477/28080 [20:42:27<35:12:29,  7.20s/it]
                                                           
{'loss': 0.6329, 'learning_rate': 0.0003608937167924087, 'epoch': 4.48}

 37%|███▋      | 10477/28080 [20:42:27<35:12:29,  7.20s/it]
 37%|███▋      | 10478/28080 [20:42:34<35:04:10,  7.17s/it]
                                                           
{'loss': 0.6343, 'learning_rate': 0.00036086787241759554, 'epoch': 4.48}

 37%|███▋      | 10478/28080 [20:42:34<35:04:10,  7.17s/it]
 37%|███▋      | 10479/28080 [20:42:41<35:00:05,  7.16s/it]
                                                           
{'loss': 0.6187, 'learning_rate': 0.0003608420265677999, 'epoch': 4.48}

 37%|███▋      | 10479/28080 [20:42:41<35:00:05,  7.16s/it]
 37%|███▋      | 10480/28080 [20:42:48<35:03:44,  7.17s/it]
                                                           
{'loss': 0.6082, 'learning_rate': 0.0003608161792433653, 'epoch': 4.48}

 37%|███▋      | 10480/28080 [20:42:48<35:03:44,  7.17s/it]
 37%|███▋      | 10481/28080 [20:42:55<34:51:25,  7.13s/it]
                                                           
{'loss': 0.6195, 'learning_rate': 0.00036079033044463584, 'epoch': 4.48}

 37%|███▋      | 10481/28080 [20:42:55<34:51:25,  7.13s/it]
 37%|███▋      | 10482/28080 [20:43:02<34:48:48,  7.12s/it]
                                                           
{'loss': 0.6104, 'learning_rate': 0.00036076448017195533, 'epoch': 4.48}

 37%|███▋      | 10482/28080 [20:43:02<34:48:48,  7.12s/it]
 37%|███▋      | 10483/28080 [20:43:09<34:51:33,  7.13s/it]
                                                           
{'loss': 0.6289, 'learning_rate': 0.0003607386284256676, 'epoch': 4.48}

 37%|███▋      | 10483/28080 [20:43:09<34:51:33,  7.13s/it]
 37%|███▋      | 10484/28080 [20:43:16<34:51:45,  7.13s/it]
                                                           
{'loss': 0.6427, 'learning_rate': 0.00036071277520611676, 'epoch': 4.48}

 37%|███▋      | 10484/28080 [20:43:16<34:51:45,  7.13s/it]
 37%|███▋      | 10485/28080 [20:43:24<34:59:32,  7.16s/it]
                                                           
{'loss': 0.6114, 'learning_rate': 0.0003606869205136467, 'epoch': 4.48}

 37%|███▋      | 10485/28080 [20:43:24<34:59:32,  7.16s/it]
 37%|███▋      | 10486/28080 [20:43:31<34:52:34,  7.14s/it]
                                                           
{'loss': 0.6173, 'learning_rate': 0.00036066106434860123, 'epoch': 4.48}

 37%|███▋      | 10486/28080 [20:43:31<34:52:34,  7.14s/it]
 37%|███▋      | 10487/28080 [20:43:38<34:42:55,  7.10s/it]
                                                           
{'loss': 0.6435, 'learning_rate': 0.0003606352067113245, 'epoch': 4.48}

 37%|███▋      | 10487/28080 [20:43:38<34:42:55,  7.10s/it]
 37%|███▋      | 10488/28080 [20:43:45<34:45:56,  7.11s/it]
                                                           
{'loss': 0.6257, 'learning_rate': 0.00036060934760216045, 'epoch': 4.48}

 37%|███▋      | 10488/28080 [20:43:45<34:45:56,  7.11s/it]
 37%|███▋      | 10489/28080 [20:43:52<34:40:22,  7.10s/it]
                                                           
{'loss': 0.6543, 'learning_rate': 0.0003605834870214532, 'epoch': 4.48}

 37%|███▋      | 10489/28080 [20:43:52<34:40:22,  7.10s/it]
 37%|███▋      | 10490/28080 [20:43:59<34:38:27,  7.09s/it]
                                                           
{'loss': 0.6217, 'learning_rate': 0.0003605576249695468, 'epoch': 4.48}

 37%|███▋      | 10490/28080 [20:43:59<34:38:27,  7.09s/it]
 37%|███▋      | 10491/28080 [20:44:06<34:47:30,  7.12s/it]
                                                           
{'loss': 0.6143, 'learning_rate': 0.0003605317614467851, 'epoch': 4.48}

 37%|███▋      | 10491/28080 [20:44:06<34:47:30,  7.12s/it]
 37%|███▋      | 10492/28080 [20:44:13<34:57:22,  7.16s/it]
                                                           
{'loss': 0.6377, 'learning_rate': 0.00036050589645351245, 'epoch': 4.48}

 37%|███▋      | 10492/28080 [20:44:13<34:57:22,  7.16s/it]
 37%|███▋      | 10493/28080 [20:44:21<35:03:40,  7.18s/it]
                                                           
{'loss': 0.6013, 'learning_rate': 0.00036048002999007286, 'epoch': 4.48}

 37%|███▋      | 10493/28080 [20:44:21<35:03:40,  7.18s/it]
 37%|███▋      | 10494/28080 [20:44:28<34:39:38,  7.10s/it]
                                                           
{'loss': 0.6155, 'learning_rate': 0.00036045416205681037, 'epoch': 4.48}

 37%|███▋      | 10494/28080 [20:44:28<34:39:38,  7.10s/it]
 37%|███▋      | 10495/28080 [20:44:35<34:43:21,  7.11s/it]
                                                           
{'loss': 0.6329, 'learning_rate': 0.00036042829265406926, 'epoch': 4.48}

 37%|███▋      | 10495/28080 [20:44:35<34:43:21,  7.11s/it]
 37%|███▋      | 10496/28080 [20:44:42<34:44:50,  7.11s/it]
                                                           
{'loss': 0.6247, 'learning_rate': 0.0003604024217821936, 'epoch': 4.48}

 37%|███▋      | 10496/28080 [20:44:42<34:44:50,  7.11s/it]
 37%|███▋      | 10497/28080 [20:44:49<34:48:19,  7.13s/it]
                                                           
{'loss': 0.6205, 'learning_rate': 0.00036037654944152763, 'epoch': 4.48}

 37%|███▋      | 10497/28080 [20:44:49<34:48:19,  7.13s/it]
 37%|███▋      | 10498/28080 [20:44:56<34:51:54,  7.14s/it]
                                                           
{'loss': 0.62, 'learning_rate': 0.0003603506756324156, 'epoch': 4.48}

 37%|███▋      | 10498/28080 [20:44:56<34:51:54,  7.14s/it]
 37%|███▋      | 10499/28080 [20:45:03<34:47:39,  7.12s/it]
                                                           
{'loss': 0.6102, 'learning_rate': 0.0003603248003552015, 'epoch': 4.49}

 37%|███▋      | 10499/28080 [20:45:03<34:47:39,  7.12s/it]
 37%|███▋      | 10500/28080 [20:45:10<34:44:05,  7.11s/it]
                                                           
{'loss': 0.6387, 'learning_rate': 0.0003602989236102299, 'epoch': 4.49}

 37%|███▋      | 10500/28080 [20:45:10<34:44:05,  7.11s/it]
 37%|███▋      | 10501/28080 [20:45:17<34:42:24,  7.11s/it]
                                                           
{'loss': 0.6558, 'learning_rate': 0.00036027304539784486, 'epoch': 4.49}

 37%|███▋      | 10501/28080 [20:45:17<34:42:24,  7.11s/it]
 37%|███▋      | 10502/28080 [20:45:25<34:46:05,  7.12s/it]
                                                           
{'loss': 0.6521, 'learning_rate': 0.0003602471657183908, 'epoch': 4.49}

 37%|███▋      | 10502/28080 [20:45:25<34:46:05,  7.12s/it]
 37%|███▋      | 10503/28080 [20:45:32<34:40:44,  7.10s/it]
                                                           
{'loss': 0.6497, 'learning_rate': 0.0003602212845722118, 'epoch': 4.49}

 37%|███▋      | 10503/28080 [20:45:32<34:40:44,  7.10s/it]
 37%|███▋      | 10504/28080 [20:45:39<34:32:51,  7.08s/it]
                                                           
{'loss': 0.6288, 'learning_rate': 0.0003601954019596524, 'epoch': 4.49}

 37%|███▋      | 10504/28080 [20:45:39<34:32:51,  7.08s/it]
 37%|███▋      | 10505/28080 [20:45:46<34:44:35,  7.12s/it]
                                                           
{'loss': 0.6325, 'learning_rate': 0.00036016951788105686, 'epoch': 4.49}

 37%|███▋      | 10505/28080 [20:45:46<34:44:35,  7.12s/it]
 37%|███▋      | 10506/28080 [20:45:53<34:43:54,  7.11s/it]
                                                           
{'loss': 0.6398, 'learning_rate': 0.0003601436323367695, 'epoch': 4.49}

 37%|███▋      | 10506/28080 [20:45:53<34:43:54,  7.11s/it]
 37%|███▋      | 10507/28080 [20:46:00<34:44:00,  7.12s/it]
                                                           
{'loss': 0.6242, 'learning_rate': 0.0003601177453271347, 'epoch': 4.49}

 37%|███▋      | 10507/28080 [20:46:00<34:44:00,  7.12s/it]
 37%|███▋      | 10508/28080 [20:46:07<34:48:13,  7.13s/it]
                                                           
{'loss': 0.6113, 'learning_rate': 0.000360091856852497, 'epoch': 4.49}

 37%|███▋      | 10508/28080 [20:46:07<34:48:13,  7.13s/it]
 37%|███▋      | 10509/28080 [20:46:14<34:42:15,  7.11s/it]
                                                           
{'loss': 0.6149, 'learning_rate': 0.00036006596691320067, 'epoch': 4.49}

 37%|███▋      | 10509/28080 [20:46:14<34:42:15,  7.11s/it]
 37%|███▋      | 10510/28080 [20:46:21<34:46:41,  7.13s/it]
                                                           
{'loss': 0.611, 'learning_rate': 0.00036004007550959023, 'epoch': 4.49}

 37%|███▋      | 10510/28080 [20:46:21<34:46:41,  7.13s/it]
 37%|███▋      | 10511/28080 [20:46:29<34:46:15,  7.12s/it]
                                                           
{'loss': 0.6539, 'learning_rate': 0.0003600141826420101, 'epoch': 4.49}

 37%|███▋      | 10511/28080 [20:46:29<34:46:15,  7.12s/it]
 37%|███▋      | 10512/28080 [20:46:36<34:47:41,  7.13s/it]
                                                           
{'loss': 0.6068, 'learning_rate': 0.0003599882883108047, 'epoch': 4.49}

 37%|███▋      | 10512/28080 [20:46:36<34:47:41,  7.13s/it]
 37%|███▋      | 10513/28080 [20:46:43<34:47:36,  7.13s/it]
                                                           
{'loss': 0.6114, 'learning_rate': 0.0003599623925163187, 'epoch': 4.49}

 37%|███▋      | 10513/28080 [20:46:43<34:47:36,  7.13s/it]
 37%|███▋      | 10514/28080 [20:46:50<34:47:45,  7.13s/it]
                                                           
{'loss': 0.6357, 'learning_rate': 0.0003599364952588964, 'epoch': 4.49}

 37%|███▋      | 10514/28080 [20:46:50<34:47:45,  7.13s/it]
 37%|███▋      | 10515/28080 [20:46:57<34:50:47,  7.14s/it]
                                                           
{'loss': 0.6025, 'learning_rate': 0.00035991059653888254, 'epoch': 4.49}

 37%|███▋      | 10515/28080 [20:46:57<34:50:47,  7.14s/it]
 37%|███▋      | 10516/28080 [20:47:04<34:47:52,  7.13s/it]
                                                           
{'loss': 0.6136, 'learning_rate': 0.00035988469635662144, 'epoch': 4.49}

 37%|███▋      | 10516/28080 [20:47:04<34:47:52,  7.13s/it]
 37%|███▋      | 10517/28080 [20:47:11<34:47:46,  7.13s/it]
                                                           
{'loss': 0.609, 'learning_rate': 0.00035985879471245796, 'epoch': 4.49}

 37%|███▋      | 10517/28080 [20:47:11<34:47:46,  7.13s/it]
 37%|███▋      | 10518/28080 [20:47:18<34:42:43,  7.12s/it]
                                                           
{'loss': 0.6437, 'learning_rate': 0.0003598328916067366, 'epoch': 4.49}

 37%|███▋      | 10518/28080 [20:47:18<34:42:43,  7.12s/it]
 37%|███▋      | 10519/28080 [20:47:26<34:44:54,  7.12s/it]
                                                           
{'loss': 0.6381, 'learning_rate': 0.0003598069870398018, 'epoch': 4.49}

 37%|███▋      | 10519/28080 [20:47:26<34:44:54,  7.12s/it]
 37%|███▋      | 10520/28080 [20:47:33<34:41:24,  7.11s/it]
                                                           
{'loss': 0.6111, 'learning_rate': 0.00035978108101199837, 'epoch': 4.49}

 37%|███▋      | 10520/28080 [20:47:33<34:41:24,  7.11s/it]
 37%|███▋      | 10521/28080 [20:47:40<34:34:16,  7.09s/it]
                                                           
{'loss': 0.6316, 'learning_rate': 0.00035975517352367087, 'epoch': 4.49}

 37%|███▋      | 10521/28080 [20:47:40<34:34:16,  7.09s/it]
 37%|███▋      | 10522/28080 [20:47:47<34:43:54,  7.12s/it]
                                                           
{'loss': 0.6198, 'learning_rate': 0.00035972926457516406, 'epoch': 4.49}

 37%|███▋      | 10522/28080 [20:47:47<34:43:54,  7.12s/it]
 37%|███▋      | 10523/28080 [20:47:54<34:32:28,  7.08s/it]
                                                           
{'loss': 0.6277, 'learning_rate': 0.00035970335416682256, 'epoch': 4.5}

 37%|███▋      | 10523/28080 [20:47:54<34:32:28,  7.08s/it]
 37%|███▋      | 10524/28080 [20:48:01<34:47:20,  7.13s/it]
                                                           
{'loss': 0.6171, 'learning_rate': 0.0003596774422989911, 'epoch': 4.5}

 37%|███▋      | 10524/28080 [20:48:01<34:47:20,  7.13s/it]
 37%|███▋      | 10525/28080 [20:48:08<34:42:41,  7.12s/it]
                                                           
{'loss': 0.6279, 'learning_rate': 0.0003596515289720144, 'epoch': 4.5}

 37%|███▋      | 10525/28080 [20:48:08<34:42:41,  7.12s/it]
 37%|███▋      | 10526/28080 [20:48:15<34:42:17,  7.12s/it]
                                                           
{'loss': 0.6248, 'learning_rate': 0.00035962561418623727, 'epoch': 4.5}

 37%|███▋      | 10526/28080 [20:48:15<34:42:17,  7.12s/it]
 37%|███▋      | 10527/28080 [20:48:23<34:44:27,  7.13s/it]
                                                           
{'loss': 0.6405, 'learning_rate': 0.0003595996979420044, 'epoch': 4.5}

 37%|███▋      | 10527/28080 [20:48:23<34:44:27,  7.13s/it]
 37%|███▋      | 10528/28080 [20:48:30<34:49:57,  7.14s/it]
                                                           
{'loss': 0.6311, 'learning_rate': 0.0003595737802396607, 'epoch': 4.5}

 37%|███▋      | 10528/28080 [20:48:30<34:49:57,  7.14s/it]
 37%|███▋      | 10529/28080 [20:48:37<34:37:18,  7.10s/it]
                                                           
{'loss': 0.6451, 'learning_rate': 0.00035954786107955086, 'epoch': 4.5}

 37%|███▋      | 10529/28080 [20:48:37<34:37:18,  7.10s/it]
 38%|███▊      | 10530/28080 [20:48:44<34:37:44,  7.10s/it]
                                                           
{'loss': 0.6158, 'learning_rate': 0.0003595219404620197, 'epoch': 4.5}

 38%|███▊      | 10530/28080 [20:48:44<34:37:44,  7.10s/it]
 38%|███▊      | 10531/28080 [20:48:51<34:35:36,  7.10s/it]
                                                           
{'loss': 0.6203, 'learning_rate': 0.0003594960183874121, 'epoch': 4.5}

 38%|███▊      | 10531/28080 [20:48:51<34:35:36,  7.10s/it]
 38%|███▊      | 10532/28080 [20:48:58<34:36:22,  7.10s/it]
                                                           
{'loss': 0.6062, 'learning_rate': 0.00035947009485607295, 'epoch': 4.5}

 38%|███▊      | 10532/28080 [20:48:58<34:36:22,  7.10s/it]
 38%|███▊      | 10533/28080 [20:49:05<34:32:51,  7.09s/it]
                                                           
{'loss': 0.627, 'learning_rate': 0.00035944416986834714, 'epoch': 4.5}

 38%|███▊      | 10533/28080 [20:49:05<34:32:51,  7.09s/it]
 38%|███▊      | 10534/28080 [20:49:12<34:33:38,  7.09s/it]
                                                           
{'loss': 0.6217, 'learning_rate': 0.00035941824342457956, 'epoch': 4.5}

 38%|███▊      | 10534/28080 [20:49:12<34:33:38,  7.09s/it]
 38%|███▊      | 10535/28080 [20:49:19<34:35:11,  7.10s/it]
                                                           
{'loss': 0.6225, 'learning_rate': 0.00035939231552511514, 'epoch': 4.5}

 38%|███▊      | 10535/28080 [20:49:19<34:35:11,  7.10s/it]
 38%|███▊      | 10536/28080 [20:49:26<34:41:14,  7.12s/it]
                                                           
{'loss': 0.6195, 'learning_rate': 0.0003593663861702988, 'epoch': 4.5}

 38%|███▊      | 10536/28080 [20:49:26<34:41:14,  7.12s/it]
 38%|███▊      | 10537/28080 [20:49:34<34:43:46,  7.13s/it]
                                                           
{'loss': 0.6347, 'learning_rate': 0.00035934045536047555, 'epoch': 4.5}

 38%|███▊      | 10537/28080 [20:49:34<34:43:46,  7.13s/it]
 38%|███▊      | 10538/28080 [20:49:41<34:39:57,  7.11s/it]
                                                           
{'loss': 0.6265, 'learning_rate': 0.00035931452309599025, 'epoch': 4.5}

 38%|███▊      | 10538/28080 [20:49:41<34:39:57,  7.11s/it]
 38%|███▊      | 10539/28080 [20:49:48<34:35:59,  7.10s/it]
                                                           
{'loss': 0.6256, 'learning_rate': 0.0003592885893771881, 'epoch': 4.5}

 38%|███▊      | 10539/28080 [20:49:48<34:35:59,  7.10s/it]
 38%|███▊      | 10540/28080 [20:49:55<34:42:45,  7.12s/it]
                                                           
{'loss': 0.6227, 'learning_rate': 0.00035926265420441395, 'epoch': 4.5}

 38%|███▊      | 10540/28080 [20:49:55<34:42:45,  7.12s/it]
 38%|███▊      | 10541/28080 [20:50:02<34:40:07,  7.12s/it]
                                                           
{'loss': 0.6639, 'learning_rate': 0.000359236717578013, 'epoch': 4.5}

 38%|███▊      | 10541/28080 [20:50:02<34:40:07,  7.12s/it]
 38%|███▊      | 10542/28080 [20:50:09<34:42:22,  7.12s/it]
                                                           
{'loss': 0.6239, 'learning_rate': 0.00035921077949833014, 'epoch': 4.5}

 38%|███▊      | 10542/28080 [20:50:09<34:42:22,  7.12s/it]
 38%|███▊      | 10543/28080 [20:50:16<34:42:31,  7.12s/it]
                                                           
{'loss': 0.622, 'learning_rate': 0.0003591848399657105, 'epoch': 4.5}

 38%|███▊      | 10543/28080 [20:50:16<34:42:31,  7.12s/it]
 38%|███▊      | 10544/28080 [20:50:23<34:39:28,  7.12s/it]
                                                           
{'loss': 0.6374, 'learning_rate': 0.00035915889898049925, 'epoch': 4.5}

 38%|███▊      | 10544/28080 [20:50:23<34:39:28,  7.12s/it]
 38%|███▊      | 10545/28080 [20:50:30<34:32:57,  7.09s/it]
                                                           
{'loss': 0.6163, 'learning_rate': 0.0003591329565430414, 'epoch': 4.5}

 38%|███▊      | 10545/28080 [20:50:30<34:32:57,  7.09s/it]
 38%|███▊      | 10546/28080 [20:50:38<34:37:59,  7.11s/it]
                                                           
{'loss': 0.6421, 'learning_rate': 0.00035910701265368225, 'epoch': 4.51}

 38%|███▊      | 10546/28080 [20:50:38<34:37:59,  7.11s/it]
 38%|███▊      | 10547/28080 [20:50:45<34:39:37,  7.12s/it]
                                                           
{'loss': 0.5956, 'learning_rate': 0.00035908106731276677, 'epoch': 4.51}

 38%|███▊      | 10547/28080 [20:50:45<34:39:37,  7.12s/it]
 38%|███▊      | 10548/28080 [20:50:52<34:46:11,  7.14s/it]
                                                           
{'loss': 0.6211, 'learning_rate': 0.00035905512052064023, 'epoch': 4.51}

 38%|███▊      | 10548/28080 [20:50:52<34:46:11,  7.14s/it]
 38%|███▊      | 10549/28080 [20:50:59<34:42:47,  7.13s/it]
                                                           
{'loss': 0.618, 'learning_rate': 0.00035902917227764784, 'epoch': 4.51}

 38%|███▊      | 10549/28080 [20:50:59<34:42:47,  7.13s/it]
 38%|███▊      | 10550/28080 [20:51:06<34:34:08,  7.10s/it]
                                                           
{'loss': 0.6243, 'learning_rate': 0.0003590032225841348, 'epoch': 4.51}

 38%|███▊      | 10550/28080 [20:51:06<34:34:08,  7.10s/it]
 38%|███▊      | 10551/28080 [20:51:13<34:37:41,  7.11s/it]
                                                           
{'loss': 0.6062, 'learning_rate': 0.00035897727144044636, 'epoch': 4.51}

 38%|███▊      | 10551/28080 [20:51:13<34:37:41,  7.11s/it]
 38%|███▊      | 10552/28080 [20:51:20<34:34:16,  7.10s/it]
                                                           
{'loss': 0.6369, 'learning_rate': 0.0003589513188469277, 'epoch': 4.51}

 38%|███▊      | 10552/28080 [20:51:20<34:34:16,  7.10s/it]
 38%|███▊      | 10553/28080 [20:51:27<34:41:46,  7.13s/it]
                                                           
{'loss': 0.6463, 'learning_rate': 0.00035892536480392417, 'epoch': 4.51}

 38%|███▊      | 10553/28080 [20:51:27<34:41:46,  7.13s/it]
 38%|███▊      | 10554/28080 [20:51:34<34:35:52,  7.11s/it]
                                                           
{'loss': 0.6422, 'learning_rate': 0.000358899409311781, 'epoch': 4.51}

 38%|███▊      | 10554/28080 [20:51:34<34:35:52,  7.11s/it]
 38%|███▊      | 10555/28080 [20:51:42<34:31:24,  7.09s/it]
                                                           
{'loss': 0.6384, 'learning_rate': 0.0003588734523708436, 'epoch': 4.51}

 38%|███▊      | 10555/28080 [20:51:42<34:31:24,  7.09s/it]
 38%|███▊      | 10556/28080 [20:51:49<34:33:32,  7.10s/it]
                                                           
{'loss': 0.624, 'learning_rate': 0.00035884749398145717, 'epoch': 4.51}

 38%|███▊      | 10556/28080 [20:51:49<34:33:32,  7.10s/it]
 38%|███▊      | 10557/28080 [20:51:56<34:35:53,  7.11s/it]
                                                           
{'loss': 0.6192, 'learning_rate': 0.0003588215341439671, 'epoch': 4.51}

 38%|███▊      | 10557/28080 [20:51:56<34:35:53,  7.11s/it]
 38%|███▊      | 10558/28080 [20:52:03<34:34:03,  7.10s/it]
                                                           
{'loss': 0.6456, 'learning_rate': 0.00035879557285871887, 'epoch': 4.51}

 38%|███▊      | 10558/28080 [20:52:03<34:34:03,  7.10s/it]
 38%|███▊      | 10559/28080 [20:52:10<34:36:44,  7.11s/it]
                                                           
{'loss': 0.6225, 'learning_rate': 0.0003587696101260577, 'epoch': 4.51}

 38%|███▊      | 10559/28080 [20:52:10<34:36:44,  7.11s/it]
 38%|███▊      | 10560/28080 [20:52:17<34:38:26,  7.12s/it]
                                                           
{'loss': 0.6343, 'learning_rate': 0.00035874364594632916, 'epoch': 4.51}

 38%|███▊      | 10560/28080 [20:52:17<34:38:26,  7.12s/it]
 38%|███▊      | 10561/28080 [20:52:24<34:39:53,  7.12s/it]
                                                           
{'loss': 0.6174, 'learning_rate': 0.0003587176803198785, 'epoch': 4.51}

 38%|███▊      | 10561/28080 [20:52:24<34:39:53,  7.12s/it]
 38%|███▊      | 10562/28080 [20:52:31<34:41:27,  7.13s/it]
                                                           
{'loss': 0.6134, 'learning_rate': 0.0003586917132470513, 'epoch': 4.51}

 38%|███▊      | 10562/28080 [20:52:31<34:41:27,  7.13s/it]
 38%|███▊      | 10563/28080 [20:52:39<34:39:45,  7.12s/it]
                                                           
{'loss': 0.608, 'learning_rate': 0.000358665744728193, 'epoch': 4.51}

 38%|███▊      | 10563/28080 [20:52:39<34:39:45,  7.12s/it]
 38%|███▊      | 10564/28080 [20:52:46<34:37:30,  7.12s/it]
                                                           
{'loss': 0.6243, 'learning_rate': 0.00035863977476364913, 'epoch': 4.51}

 38%|███▊      | 10564/28080 [20:52:46<34:37:30,  7.12s/it]
 38%|███▊      | 10565/28080 [20:52:53<34:33:22,  7.10s/it]
                                                           
{'loss': 0.633, 'learning_rate': 0.0003586138033537651, 'epoch': 4.51}

 38%|███▊      | 10565/28080 [20:52:53<34:33:22,  7.10s/it]
 38%|███▊      | 10566/28080 [20:53:00<34:31:55,  7.10s/it]
                                                           
{'loss': 0.6278, 'learning_rate': 0.0003585878304988864, 'epoch': 4.51}

 38%|███▊      | 10566/28080 [20:53:00<34:31:55,  7.10s/it]
 38%|███▊      | 10567/28080 [20:53:07<34:41:19,  7.13s/it]
                                                           
{'loss': 0.6246, 'learning_rate': 0.0003585618561993587, 'epoch': 4.51}

 38%|███▊      | 10567/28080 [20:53:07<34:41:19,  7.13s/it]
 38%|███▊      | 10568/28080 [20:53:14<34:44:24,  7.14s/it]
                                                           
{'loss': 0.6219, 'learning_rate': 0.00035853588045552755, 'epoch': 4.51}

 38%|███▊      | 10568/28080 [20:53:14<34:44:24,  7.14s/it]
 38%|███▊      | 10569/28080 [20:53:21<34:38:15,  7.12s/it]
                                                           
{'loss': 0.6288, 'learning_rate': 0.00035850990326773835, 'epoch': 4.51}

 38%|███▊      | 10569/28080 [20:53:21<34:38:15,  7.12s/it]
 38%|███▊      | 10570/28080 [20:53:28<34:35:21,  7.11s/it]
                                                           
{'loss': 0.63, 'learning_rate': 0.00035848392463633694, 'epoch': 4.52}

 38%|███▊      | 10570/28080 [20:53:28<34:35:21,  7.11s/it]
 38%|███▊      | 10571/28080 [20:53:35<34:40:22,  7.13s/it]
                                                           
{'loss': 0.6128, 'learning_rate': 0.00035845794456166875, 'epoch': 4.52}

 38%|███▊      | 10571/28080 [20:53:35<34:40:22,  7.13s/it]
 38%|███▊      | 10572/28080 [20:53:43<34:44:59,  7.15s/it]
                                                           
{'loss': 0.6155, 'learning_rate': 0.00035843196304407947, 'epoch': 4.52}

 38%|███▊      | 10572/28080 [20:53:43<34:44:59,  7.15s/it]
 38%|███▊      | 10573/28080 [20:53:50<34:42:19,  7.14s/it]
                                                           
{'loss': 0.625, 'learning_rate': 0.0003584059800839149, 'epoch': 4.52}

 38%|███▊      | 10573/28080 [20:53:50<34:42:19,  7.14s/it]
 38%|███▊      | 10574/28080 [20:53:57<34:42:33,  7.14s/it]
                                                           
{'loss': 0.6188, 'learning_rate': 0.0003583799956815205, 'epoch': 4.52}

 38%|███▊      | 10574/28080 [20:53:57<34:42:33,  7.14s/it]
 38%|███▊      | 10575/28080 [20:54:04<34:40:47,  7.13s/it]
                                                           
{'loss': 0.6106, 'learning_rate': 0.0003583540098372422, 'epoch': 4.52}

 38%|███▊      | 10575/28080 [20:54:04<34:40:47,  7.13s/it]
 38%|███▊      | 10576/28080 [20:54:11<34:40:42,  7.13s/it]
                                                           
{'loss': 0.628, 'learning_rate': 0.00035832802255142545, 'epoch': 4.52}

 38%|███▊      | 10576/28080 [20:54:11<34:40:42,  7.13s/it]
 38%|███▊      | 10577/28080 [20:54:18<34:41:22,  7.13s/it]
                                                           
{'loss': 0.633, 'learning_rate': 0.00035830203382441615, 'epoch': 4.52}

 38%|███▊      | 10577/28080 [20:54:18<34:41:22,  7.13s/it]
 38%|███▊      | 10578/28080 [20:54:25<34:24:29,  7.08s/it]
                                                           
{'loss': 0.6363, 'learning_rate': 0.00035827604365656, 'epoch': 4.52}

 38%|███▊      | 10578/28080 [20:54:25<34:24:29,  7.08s/it]
 38%|███▊      | 10579/28080 [20:54:32<34:23:54,  7.08s/it]
                                                           
{'loss': 0.6358, 'learning_rate': 0.00035825005204820283, 'epoch': 4.52}

 38%|███▊      | 10579/28080 [20:54:32<34:23:54,  7.08s/it]
 38%|███▊      | 10580/28080 [20:54:39<34:26:52,  7.09s/it]
                                                           
{'loss': 0.6295, 'learning_rate': 0.0003582240589996904, 'epoch': 4.52}

 38%|███▊      | 10580/28080 [20:54:39<34:26:52,  7.09s/it]
 38%|███▊      | 10581/28080 [20:54:47<34:26:26,  7.09s/it]
                                                           
{'loss': 0.6255, 'learning_rate': 0.00035819806451136847, 'epoch': 4.52}

 38%|███▊      | 10581/28080 [20:54:47<34:26:26,  7.09s/it]
 38%|███▊      | 10582/28080 [20:54:54<34:19:43,  7.06s/it]
                                                           
{'loss': 0.6364, 'learning_rate': 0.00035817206858358296, 'epoch': 4.52}

 38%|███▊      | 10582/28080 [20:54:54<34:19:43,  7.06s/it]
 38%|███▊      | 10583/28080 [20:55:01<34:29:13,  7.10s/it]
                                                           
{'loss': 0.6172, 'learning_rate': 0.00035814607121667963, 'epoch': 4.52}

 38%|███▊      | 10583/28080 [20:55:01<34:29:13,  7.10s/it]
 38%|███▊      | 10584/28080 [20:55:08<34:29:41,  7.10s/it]
                                                           
{'loss': 0.6221, 'learning_rate': 0.00035812007241100446, 'epoch': 4.52}

 38%|███▊      | 10584/28080 [20:55:08<34:29:41,  7.10s/it]
 38%|███▊      | 10585/28080 [20:55:15<34:22:49,  7.07s/it]
                                                           
{'loss': 0.6283, 'learning_rate': 0.0003580940721669032, 'epoch': 4.52}

 38%|███▊      | 10585/28080 [20:55:15<34:22:49,  7.07s/it]
 38%|███▊      | 10586/28080 [20:55:22<34:25:17,  7.08s/it]
                                                           
{'loss': 0.6389, 'learning_rate': 0.00035806807048472186, 'epoch': 4.52}

 38%|███▊      | 10586/28080 [20:55:22<34:25:17,  7.08s/it]
 38%|███▊      | 10587/28080 [20:55:29<34:32:27,  7.11s/it]
                                                           
{'loss': 0.6295, 'learning_rate': 0.0003580420673648063, 'epoch': 4.52}

 38%|███▊      | 10587/28080 [20:55:29<34:32:27,  7.11s/it]
 38%|███▊      | 10588/28080 [20:55:36<34:41:29,  7.14s/it]
                                                           
{'loss': 0.6183, 'learning_rate': 0.00035801606280750253, 'epoch': 4.52}

 38%|███▊      | 10588/28080 [20:55:36<34:41:29,  7.14s/it]
 38%|███▊      | 10589/28080 [20:55:43<34:37:37,  7.13s/it]
                                                           
{'loss': 0.6346, 'learning_rate': 0.0003579900568131564, 'epoch': 4.52}

 38%|███▊      | 10589/28080 [20:55:43<34:37:37,  7.13s/it]
 38%|███▊      | 10590/28080 [20:55:50<34:33:24,  7.11s/it]
                                                           
{'loss': 0.6291, 'learning_rate': 0.00035796404938211407, 'epoch': 4.52}

 38%|███▊      | 10590/28080 [20:55:50<34:33:24,  7.11s/it]
 38%|███▊      | 10591/28080 [20:55:57<34:22:21,  7.08s/it]
                                                           
{'loss': 0.6378, 'learning_rate': 0.00035793804051472143, 'epoch': 4.52}

 38%|███▊      | 10591/28080 [20:55:57<34:22:21,  7.08s/it]
 38%|███▊      | 10592/28080 [20:56:05<34:27:14,  7.09s/it]
                                                           
{'loss': 0.6295, 'learning_rate': 0.0003579120302113245, 'epoch': 4.52}

 38%|███▊      | 10592/28080 [20:56:05<34:27:14,  7.09s/it]
 38%|███▊      | 10593/28080 [20:56:12<34:18:12,  7.06s/it]
                                                           
{'loss': 0.6485, 'learning_rate': 0.0003578860184722693, 'epoch': 4.53}

 38%|███▊      | 10593/28080 [20:56:12<34:18:12,  7.06s/it]
 38%|███▊      | 10594/28080 [20:56:19<34:23:58,  7.08s/it]
                                                           
{'loss': 0.636, 'learning_rate': 0.000357860005297902, 'epoch': 4.53}

 38%|███▊      | 10594/28080 [20:56:19<34:23:58,  7.08s/it]
 38%|███▊      | 10595/28080 [20:56:26<34:28:26,  7.10s/it]
                                                           
{'loss': 0.6203, 'learning_rate': 0.0003578339906885685, 'epoch': 4.53}

 38%|███▊      | 10595/28080 [20:56:26<34:28:26,  7.10s/it]
 38%|███▊      | 10596/28080 [20:56:33<34:27:16,  7.09s/it]
                                                           
{'loss': 0.6264, 'learning_rate': 0.00035780797464461504, 'epoch': 4.53}

 38%|███▊      | 10596/28080 [20:56:33<34:27:16,  7.09s/it]
 38%|███▊      | 10597/28080 [20:56:40<34:37:17,  7.13s/it]
                                                           
{'loss': 0.6133, 'learning_rate': 0.0003577819571663877, 'epoch': 4.53}

 38%|███▊      | 10597/28080 [20:56:40<34:37:17,  7.13s/it]
 38%|███▊      | 10598/28080 [20:56:47<34:44:08,  7.15s/it]
                                                           
{'loss': 0.6223, 'learning_rate': 0.00035775593825423263, 'epoch': 4.53}

 38%|███▊      | 10598/28080 [20:56:47<34:44:08,  7.15s/it]
 38%|███▊      | 10599/28080 [20:56:55<34:44:09,  7.15s/it]
                                                           
{'loss': 0.6138, 'learning_rate': 0.00035772991790849595, 'epoch': 4.53}

 38%|███▊      | 10599/28080 [20:56:55<34:44:09,  7.15s/it]
 38%|███▊      | 10600/28080 [20:57:02<34:38:41,  7.14s/it]
                                                           
{'loss': 0.6182, 'learning_rate': 0.00035770389612952384, 'epoch': 4.53}

 38%|███▊      | 10600/28080 [20:57:02<34:38:41,  7.14s/it]
 38%|███▊      | 10601/28080 [20:57:09<34:36:56,  7.13s/it]
                                                           
{'loss': 0.6278, 'learning_rate': 0.00035767787291766256, 'epoch': 4.53}

 38%|███▊      | 10601/28080 [20:57:09<34:36:56,  7.13s/it]
 38%|███▊      | 10602/28080 [20:57:16<34:36:18,  7.13s/it]
                                                           
{'loss': 0.6374, 'learning_rate': 0.00035765184827325823, 'epoch': 4.53}

 38%|███▊      | 10602/28080 [20:57:16<34:36:18,  7.13s/it]
 38%|███▊      | 10603/28080 [20:57:23<34:35:25,  7.13s/it]
                                                           
{'loss': 0.6222, 'learning_rate': 0.0003576258221966571, 'epoch': 4.53}

 38%|███▊      | 10603/28080 [20:57:23<34:35:25,  7.13s/it]
 38%|███▊      | 10604/28080 [20:57:30<34:20:40,  7.07s/it]
                                                           
{'loss': 0.6479, 'learning_rate': 0.0003575997946882055, 'epoch': 4.53}

 38%|███▊      | 10604/28080 [20:57:30<34:20:40,  7.07s/it]
 38%|███▊      | 10605/28080 [20:57:37<34:28:52,  7.10s/it]
                                                           
{'loss': 0.6206, 'learning_rate': 0.0003575737657482495, 'epoch': 4.53}

 38%|███▊      | 10605/28080 [20:57:37<34:28:52,  7.10s/it]
 38%|███▊      | 10606/28080 [20:57:44<34:27:24,  7.10s/it]
                                                           
{'loss': 0.6107, 'learning_rate': 0.00035754773537713565, 'epoch': 4.53}

 38%|███▊      | 10606/28080 [20:57:44<34:27:24,  7.10s/it]
 38%|███▊      | 10607/28080 [20:57:51<34:36:00,  7.13s/it]
                                                           
{'loss': 0.6211, 'learning_rate': 0.0003575217035752101, 'epoch': 4.53}

 38%|███▊      | 10607/28080 [20:57:51<34:36:00,  7.13s/it]
 38%|███▊      | 10608/28080 [20:57:59<34:42:49,  7.15s/it]
                                                           
{'loss': 0.6257, 'learning_rate': 0.0003574956703428192, 'epoch': 4.53}

 38%|███▊      | 10608/28080 [20:57:59<34:42:49,  7.15s/it]
 38%|███▊      | 10609/28080 [20:58:06<34:53:50,  7.19s/it]
                                                           
{'loss': 0.6423, 'learning_rate': 0.00035746963568030924, 'epoch': 4.53}

 38%|███▊      | 10609/28080 [20:58:06<34:53:50,  7.19s/it]
 38%|███▊      | 10610/28080 [20:58:13<34:49:54,  7.18s/it]
                                                           
{'loss': 0.6245, 'learning_rate': 0.00035744359958802673, 'epoch': 4.53}

 38%|███▊      | 10610/28080 [20:58:13<34:49:54,  7.18s/it]
 38%|███▊      | 10611/28080 [20:58:20<34:45:37,  7.16s/it]
                                                           
{'loss': 0.6116, 'learning_rate': 0.000357417562066318, 'epoch': 4.53}

 38%|███▊      | 10611/28080 [20:58:20<34:45:37,  7.16s/it]
 38%|███▊      | 10612/28080 [20:58:27<34:46:00,  7.17s/it]
                                                           
{'loss': 0.6359, 'learning_rate': 0.00035739152311552934, 'epoch': 4.53}

 38%|███▊      | 10612/28080 [20:58:27<34:46:00,  7.17s/it]
 38%|███▊      | 10613/28080 [20:58:34<34:38:08,  7.14s/it]
                                                           
{'loss': 0.6406, 'learning_rate': 0.0003573654827360073, 'epoch': 4.53}

 38%|███▊      | 10613/28080 [20:58:34<34:38:08,  7.14s/it]
 38%|███▊      | 10614/28080 [20:58:42<34:37:25,  7.14s/it]
                                                           
{'loss': 0.6471, 'learning_rate': 0.0003573394409280982, 'epoch': 4.53}

 38%|███▊      | 10614/28080 [20:58:42<34:37:25,  7.14s/it]
 38%|███▊      | 10615/28080 [20:58:49<34:37:30,  7.14s/it]
                                                           
{'loss': 0.6421, 'learning_rate': 0.0003573133976921487, 'epoch': 4.53}

 38%|███▊      | 10615/28080 [20:58:49<34:37:30,  7.14s/it]
 38%|███▊      | 10616/28080 [20:58:56<34:31:13,  7.12s/it]
                                                           
{'loss': 0.6202, 'learning_rate': 0.0003572873530285051, 'epoch': 4.54}

 38%|███▊      | 10616/28080 [20:58:56<34:31:13,  7.12s/it]
 38%|███▊      | 10617/28080 [20:59:03<34:31:17,  7.12s/it]
                                                           
{'loss': 0.6247, 'learning_rate': 0.000357261306937514, 'epoch': 4.54}

 38%|███▊      | 10617/28080 [20:59:03<34:31:17,  7.12s/it]
 38%|███▊      | 10618/28080 [20:59:10<34:38:28,  7.14s/it]
                                                           
{'loss': 0.6084, 'learning_rate': 0.0003572352594195218, 'epoch': 4.54}

 38%|███▊      | 10618/28080 [20:59:10<34:38:28,  7.14s/it]
 38%|███▊      | 10619/28080 [20:59:17<34:30:13,  7.11s/it]
                                                           
{'loss': 0.6235, 'learning_rate': 0.0003572092104748751, 'epoch': 4.54}

 38%|███▊      | 10619/28080 [20:59:17<34:30:13,  7.11s/it]
 38%|███▊      | 10620/28080 [20:59:24<34:34:12,  7.13s/it]
                                                           
{'loss': 0.62, 'learning_rate': 0.0003571831601039204, 'epoch': 4.54}

 38%|███▊      | 10620/28080 [20:59:24<34:34:12,  7.13s/it]
 38%|███▊      | 10621/28080 [20:59:31<34:32:29,  7.12s/it]
                                                           
{'loss': 0.6342, 'learning_rate': 0.0003571571083070044, 'epoch': 4.54}

 38%|███▊      | 10621/28080 [20:59:31<34:32:29,  7.12s/it]
 38%|███▊      | 10622/28080 [20:59:39<34:33:04,  7.12s/it]
                                                           
{'loss': 0.629, 'learning_rate': 0.0003571310550844736, 'epoch': 4.54}

 38%|███▊      | 10622/28080 [20:59:39<34:33:04,  7.12s/it]
 38%|███▊      | 10623/28080 [20:59:46<34:34:16,  7.13s/it]
                                                           
{'loss': 0.6349, 'learning_rate': 0.0003571050004366747, 'epoch': 4.54}

 38%|███▊      | 10623/28080 [20:59:46<34:34:16,  7.13s/it]
 38%|███▊      | 10624/28080 [20:59:53<34:34:10,  7.13s/it]
                                                           
{'loss': 0.6183, 'learning_rate': 0.0003570789443639542, 'epoch': 4.54}

 38%|███▊      | 10624/28080 [20:59:53<34:34:10,  7.13s/it]
 38%|███▊      | 10625/28080 [21:00:00<34:33:18,  7.13s/it]
                                                           
{'loss': 0.6327, 'learning_rate': 0.0003570528868666589, 'epoch': 4.54}

 38%|███▊      | 10625/28080 [21:00:00<34:33:18,  7.13s/it]
 38%|███▊      | 10626/28080 [21:00:07<34:28:01,  7.11s/it]
                                                           
{'loss': 0.6105, 'learning_rate': 0.00035702682794513523, 'epoch': 4.54}

 38%|███▊      | 10626/28080 [21:00:07<34:28:01,  7.11s/it]
 38%|███▊      | 10627/28080 [21:00:14<34:26:16,  7.10s/it]
                                                           
{'loss': 0.6154, 'learning_rate': 0.0003570007675997301, 'epoch': 4.54}

 38%|███▊      | 10627/28080 [21:00:14<34:26:16,  7.10s/it]
 38%|███▊      | 10628/28080 [21:00:21<34:23:56,  7.10s/it]
                                                           
{'loss': 0.6192, 'learning_rate': 0.00035697470583079017, 'epoch': 4.54}

 38%|███▊      | 10628/28080 [21:00:21<34:23:56,  7.10s/it]
 38%|███▊      | 10629/28080 [21:00:28<34:21:41,  7.09s/it]
                                                           
{'loss': 0.6383, 'learning_rate': 0.0003569486426386621, 'epoch': 4.54}

 38%|███▊      | 10629/28080 [21:00:28<34:21:41,  7.09s/it]
 38%|███▊      | 10630/28080 [21:00:35<34:25:56,  7.10s/it]
                                                           
{'loss': 0.6315, 'learning_rate': 0.00035692257802369273, 'epoch': 4.54}

 38%|███▊      | 10630/28080 [21:00:35<34:25:56,  7.10s/it]
 38%|███▊      | 10631/28080 [21:00:42<34:21:10,  7.09s/it]
                                                           
{'loss': 0.6183, 'learning_rate': 0.0003568965119862287, 'epoch': 4.54}

 38%|███▊      | 10631/28080 [21:00:42<34:21:10,  7.09s/it]
 38%|███▊      | 10632/28080 [21:00:49<34:21:40,  7.09s/it]
                                                           
{'loss': 0.6232, 'learning_rate': 0.00035687044452661687, 'epoch': 4.54}

 38%|███▊      | 10632/28080 [21:00:49<34:21:40,  7.09s/it]
 38%|███▊      | 10633/28080 [21:00:57<34:17:24,  7.08s/it]
                                                           
{'loss': 0.6321, 'learning_rate': 0.00035684437564520406, 'epoch': 4.54}

 38%|███▊      | 10633/28080 [21:00:57<34:17:24,  7.08s/it]
 38%|███▊      | 10634/28080 [21:01:04<34:16:50,  7.07s/it]
                                                           
{'loss': 0.6216, 'learning_rate': 0.000356818305342337, 'epoch': 4.54}

 38%|███▊      | 10634/28080 [21:01:04<34:16:50,  7.07s/it]
 38%|███▊      | 10635/28080 [21:01:11<34:15:41,  7.07s/it]
                                                           
{'loss': 0.6136, 'learning_rate': 0.00035679223361836265, 'epoch': 4.54}

 38%|███▊      | 10635/28080 [21:01:11<34:15:41,  7.07s/it]
 38%|███▊      | 10636/28080 [21:01:18<34:19:59,  7.09s/it]
                                                           
{'loss': 0.6185, 'learning_rate': 0.0003567661604736278, 'epoch': 4.54}

 38%|███▊      | 10636/28080 [21:01:18<34:19:59,  7.09s/it]
 38%|███▊      | 10637/28080 [21:01:25<34:22:19,  7.09s/it]
                                                           
{'loss': 0.6345, 'learning_rate': 0.0003567400859084793, 'epoch': 4.54}

 38%|███▊      | 10637/28080 [21:01:25<34:22:19,  7.09s/it]
 38%|███▊      | 10638/28080 [21:01:32<34:28:26,  7.12s/it]
                                                           
{'loss': 0.6109, 'learning_rate': 0.0003567140099232641, 'epoch': 4.54}

 38%|███▊      | 10638/28080 [21:01:32<34:28:26,  7.12s/it]
 38%|███▊      | 10639/28080 [21:01:39<34:28:30,  7.12s/it]
                                                           
{'loss': 0.6213, 'learning_rate': 0.00035668793251832906, 'epoch': 4.54}

 38%|███▊      | 10639/28080 [21:01:39<34:28:30,  7.12s/it]
 38%|███▊      | 10640/28080 [21:01:46<34:24:18,  7.10s/it]
                                                           
{'loss': 0.6216, 'learning_rate': 0.00035666185369402116, 'epoch': 4.55}

 38%|███▊      | 10640/28080 [21:01:46<34:24:18,  7.10s/it]
 38%|███▊      | 10641/28080 [21:01:53<34:20:40,  7.09s/it]
                                                           
{'loss': 0.6248, 'learning_rate': 0.00035663577345068724, 'epoch': 4.55}

 38%|███▊      | 10641/28080 [21:01:53<34:20:40,  7.09s/it]
 38%|███▊      | 10642/28080 [21:02:00<34:15:44,  7.07s/it]
                                                           
{'loss': 0.6333, 'learning_rate': 0.00035660969178867455, 'epoch': 4.55}

 38%|███▊      | 10642/28080 [21:02:00<34:15:44,  7.07s/it]
 38%|███▊      | 10643/28080 [21:02:07<34:20:31,  7.09s/it]
                                                           
{'loss': 0.6352, 'learning_rate': 0.0003565836087083297, 'epoch': 4.55}

 38%|███▊      | 10643/28080 [21:02:07<34:20:31,  7.09s/it]
 38%|███▊      | 10644/28080 [21:02:14<34:07:33,  7.05s/it]
                                                           
{'loss': 0.6345, 'learning_rate': 0.00035655752421000003, 'epoch': 4.55}

 38%|███▊      | 10644/28080 [21:02:14<34:07:33,  7.05s/it]
 38%|███▊      | 10645/28080 [21:02:22<34:15:04,  7.07s/it]
                                                           
{'loss': 0.6192, 'learning_rate': 0.0003565314382940324, 'epoch': 4.55}

 38%|███▊      | 10645/28080 [21:02:22<34:15:04,  7.07s/it]
 38%|███▊      | 10646/28080 [21:02:29<34:07:22,  7.05s/it]
                                                           
{'loss': 0.6448, 'learning_rate': 0.00035650535096077386, 'epoch': 4.55}

 38%|███▊      | 10646/28080 [21:02:29<34:07:22,  7.05s/it]
 38%|███▊      | 10647/28080 [21:02:36<34:10:18,  7.06s/it]
                                                           
{'loss': 0.6314, 'learning_rate': 0.00035647926221057155, 'epoch': 4.55}

 38%|███▊      | 10647/28080 [21:02:36<34:10:18,  7.06s/it]
 38%|███▊      | 10648/28080 [21:02:43<34:17:28,  7.08s/it]
                                                           
{'loss': 0.6323, 'learning_rate': 0.0003564531720437724, 'epoch': 4.55}

 38%|███▊      | 10648/28080 [21:02:43<34:17:28,  7.08s/it]
 38%|███▊      | 10649/28080 [21:02:50<34:17:46,  7.08s/it]
                                                           
{'loss': 0.6128, 'learning_rate': 0.00035642708046072373, 'epoch': 4.55}

 38%|███▊      | 10649/28080 [21:02:50<34:17:46,  7.08s/it]
 38%|███▊      | 10650/28080 [21:02:57<34:20:57,  7.09s/it]
                                                           
{'loss': 0.6265, 'learning_rate': 0.0003564009874617725, 'epoch': 4.55}

 38%|███▊      | 10650/28080 [21:02:57<34:20:57,  7.09s/it]
 38%|███▊      | 10651/28080 [21:03:04<34:18:41,  7.09s/it]
                                                           
{'loss': 0.6269, 'learning_rate': 0.00035637489304726587, 'epoch': 4.55}

 38%|███▊      | 10651/28080 [21:03:04<34:18:41,  7.09s/it]
 38%|███▊      | 10652/28080 [21:03:11<34:15:04,  7.08s/it]
                                                           
{'loss': 0.6152, 'learning_rate': 0.00035634879721755107, 'epoch': 4.55}

 38%|███▊      | 10652/28080 [21:03:11<34:15:04,  7.08s/it]
 38%|███▊      | 10653/28080 [21:03:18<34:19:43,  7.09s/it]
                                                           
{'loss': 0.6071, 'learning_rate': 0.0003563226999729752, 'epoch': 4.55}

 38%|███▊      | 10653/28080 [21:03:18<34:19:43,  7.09s/it]
 38%|███▊      | 10654/28080 [21:03:25<34:15:43,  7.08s/it]
                                                           
{'loss': 0.608, 'learning_rate': 0.0003562966013138856, 'epoch': 4.55}

 38%|███▊      | 10654/28080 [21:03:25<34:15:43,  7.08s/it]
 38%|███▊      | 10655/28080 [21:03:32<34:02:43,  7.03s/it]
                                                           
{'loss': 0.6406, 'learning_rate': 0.00035627050124062925, 'epoch': 4.55}

 38%|███▊      | 10655/28080 [21:03:32<34:02:43,  7.03s/it]
 38%|███▊      | 10656/28080 [21:03:39<34:01:19,  7.03s/it]
                                                           
{'loss': 0.6451, 'learning_rate': 0.0003562443997535536, 'epoch': 4.55}

 38%|███▊      | 10656/28080 [21:03:39<34:01:19,  7.03s/it]
 38%|███▊      | 10657/28080 [21:03:46<34:16:20,  7.08s/it]
                                                           
{'loss': 0.6017, 'learning_rate': 0.00035621829685300577, 'epoch': 4.55}

 38%|███▊      | 10657/28080 [21:03:46<34:16:20,  7.08s/it]
 38%|███▊      | 10658/28080 [21:03:53<34:14:02,  7.07s/it]
                                                           
{'loss': 0.6044, 'learning_rate': 0.000356192192539333, 'epoch': 4.55}

 38%|███▊      | 10658/28080 [21:03:53<34:14:02,  7.07s/it]
 38%|███▊      | 10659/28080 [21:04:01<34:17:01,  7.08s/it]
                                                           
{'loss': 0.6188, 'learning_rate': 0.00035616608681288283, 'epoch': 4.55}

 38%|███▊      | 10659/28080 [21:04:01<34:17:01,  7.08s/it]
 38%|███▊      | 10660/28080 [21:04:08<34:08:56,  7.06s/it]
                                                           
{'loss': 0.624, 'learning_rate': 0.0003561399796740023, 'epoch': 4.55}

 38%|███▊      | 10660/28080 [21:04:08<34:08:56,  7.06s/it]
 38%|███▊      | 10661/28080 [21:04:15<34:16:31,  7.08s/it]
                                                           
{'loss': 0.6281, 'learning_rate': 0.0003561138711230389, 'epoch': 4.55}

 38%|███▊      | 10661/28080 [21:04:15<34:16:31,  7.08s/it]
 38%|███▊      | 10662/28080 [21:04:22<34:18:17,  7.09s/it]
                                                           
{'loss': 0.6317, 'learning_rate': 0.0003560877611603399, 'epoch': 4.55}

 38%|███▊      | 10662/28080 [21:04:22<34:18:17,  7.09s/it]
 38%|███▊      | 10663/28080 [21:04:29<34:17:03,  7.09s/it]
                                                           
{'loss': 0.6222, 'learning_rate': 0.00035606164978625266, 'epoch': 4.56}

 38%|███▊      | 10663/28080 [21:04:29<34:17:03,  7.09s/it]
 38%|███▊      | 10664/28080 [21:04:36<34:18:16,  7.09s/it]
                                                           
{'loss': 0.599, 'learning_rate': 0.00035603553700112455, 'epoch': 4.56}

 38%|███▊      | 10664/28080 [21:04:36<34:18:16,  7.09s/it]
 38%|███▊      | 10665/28080 [21:04:43<34:21:46,  7.10s/it]
                                                           
{'loss': 0.6406, 'learning_rate': 0.00035600942280530304, 'epoch': 4.56}

 38%|███▊      | 10665/28080 [21:04:43<34:21:46,  7.10s/it]
 38%|███▊      | 10666/28080 [21:04:50<34:26:58,  7.12s/it]
                                                           
{'loss': 0.627, 'learning_rate': 0.0003559833071991355, 'epoch': 4.56}

 38%|███▊      | 10666/28080 [21:04:50<34:26:58,  7.12s/it]
 38%|███▊      | 10667/28080 [21:04:57<34:28:13,  7.13s/it]
                                                           
{'loss': 0.6189, 'learning_rate': 0.00035595719018296953, 'epoch': 4.56}

 38%|███▊      | 10667/28080 [21:04:57<34:28:13,  7.13s/it]
 38%|███▊      | 10668/28080 [21:05:05<34:30:19,  7.13s/it]
                                                           
{'loss': 0.6301, 'learning_rate': 0.0003559310717571523, 'epoch': 4.56}

 38%|███▊      | 10668/28080 [21:05:05<34:30:19,  7.13s/it]
 38%|███▊      | 10669/28080 [21:05:12<34:30:07,  7.13s/it]
                                                           
{'loss': 0.6425, 'learning_rate': 0.00035590495192203153, 'epoch': 4.56}

 38%|███▊      | 10669/28080 [21:05:12<34:30:07,  7.13s/it]
 38%|███▊      | 10670/28080 [21:05:19<34:34:34,  7.15s/it]
                                                           
{'loss': 0.6372, 'learning_rate': 0.00035587883067795455, 'epoch': 4.56}

 38%|███▊      | 10670/28080 [21:05:19<34:34:34,  7.15s/it]
 38%|███▊      | 10671/28080 [21:05:26<34:37:47,  7.16s/it]
                                                           
{'loss': 0.6599, 'learning_rate': 0.00035585270802526904, 'epoch': 4.56}

 38%|███▊      | 10671/28080 [21:05:26<34:37:47,  7.16s/it]
 38%|███▊      | 10672/28080 [21:05:33<34:29:54,  7.13s/it]
                                                           
{'loss': 0.6074, 'learning_rate': 0.0003558265839643224, 'epoch': 4.56}

 38%|███▊      | 10672/28080 [21:05:33<34:29:54,  7.13s/it]
 38%|███▊      | 10673/28080 [21:05:40<34:20:55,  7.10s/it]
                                                           
{'loss': 0.6279, 'learning_rate': 0.0003558004584954623, 'epoch': 4.56}

 38%|███▊      | 10673/28080 [21:05:40<34:20:55,  7.10s/it]
 38%|███▊      | 10674/28080 [21:05:47<34:23:47,  7.11s/it]
                                                           
{'loss': 0.6288, 'learning_rate': 0.00035577433161903616, 'epoch': 4.56}

 38%|███▊      | 10674/28080 [21:05:47<34:23:47,  7.11s/it]
 38%|███▊      | 10675/28080 [21:05:55<34:28:43,  7.13s/it]
                                                           
{'loss': 0.65, 'learning_rate': 0.0003557482033353916, 'epoch': 4.56}

 38%|███▊      | 10675/28080 [21:05:55<34:28:43,  7.13s/it]
 38%|███▊      | 10676/28080 [21:06:02<34:30:51,  7.14s/it]
                                                           
{'loss': 0.6259, 'learning_rate': 0.0003557220736448765, 'epoch': 4.56}

 38%|███▊      | 10676/28080 [21:06:02<34:30:51,  7.14s/it]
 38%|███▊      | 10677/28080 [21:06:09<34:21:26,  7.11s/it]
                                                           
{'loss': 0.6464, 'learning_rate': 0.0003556959425478381, 'epoch': 4.56}

 38%|███▊      | 10677/28080 [21:06:09<34:21:26,  7.11s/it]
 38%|███▊      | 10678/28080 [21:06:16<34:32:48,  7.15s/it]
                                                           
{'loss': 0.6384, 'learning_rate': 0.00035566981004462434, 'epoch': 4.56}

 38%|███▊      | 10678/28080 [21:06:16<34:32:48,  7.15s/it]
 38%|███▊      | 10679/28080 [21:06:23<34:26:13,  7.12s/it]
                                                           
{'loss': 0.627, 'learning_rate': 0.0003556436761355827, 'epoch': 4.56}

 38%|███▊      | 10679/28080 [21:06:23<34:26:13,  7.12s/it]
 38%|███▊      | 10680/28080 [21:06:30<34:28:19,  7.13s/it]
                                                           
{'loss': 0.6263, 'learning_rate': 0.000355617540821061, 'epoch': 4.56}

 38%|███▊      | 10680/28080 [21:06:30<34:28:19,  7.13s/it]
 38%|███▊      | 10681/28080 [21:06:37<34:18:09,  7.10s/it]
                                                           
{'loss': 0.6283, 'learning_rate': 0.0003555914041014068, 'epoch': 4.56}

 38%|███▊      | 10681/28080 [21:06:37<34:18:09,  7.10s/it]
 38%|███▊      | 10682/28080 [21:06:44<34:10:00,  7.07s/it]
                                                           
{'loss': 0.6373, 'learning_rate': 0.0003555652659769679, 'epoch': 4.56}

 38%|███▊      | 10682/28080 [21:06:44<34:10:00,  7.07s/it]
 38%|███▊      | 10683/28080 [21:06:51<34:12:07,  7.08s/it]
                                                           
{'loss': 0.6438, 'learning_rate': 0.0003555391264480921, 'epoch': 4.56}

 38%|███▊      | 10683/28080 [21:06:51<34:12:07,  7.08s/it]
 38%|███▊      | 10684/28080 [21:06:58<34:14:42,  7.09s/it]
                                                           
{'loss': 0.6155, 'learning_rate': 0.0003555129855151271, 'epoch': 4.56}

 38%|███▊      | 10684/28080 [21:06:58<34:14:42,  7.09s/it]
 38%|███▊      | 10685/28080 [21:07:06<34:17:53,  7.10s/it]
                                                           
{'loss': 0.611, 'learning_rate': 0.00035548684317842066, 'epoch': 4.56}

 38%|███▊      | 10685/28080 [21:07:06<34:17:53,  7.10s/it]
 38%|███▊      | 10686/28080 [21:07:13<34:19:44,  7.11s/it]
                                                           
{'loss': 0.6105, 'learning_rate': 0.00035546069943832056, 'epoch': 4.56}

 38%|███▊      | 10686/28080 [21:07:13<34:19:44,  7.11s/it]
 38%|███▊      | 10687/28080 [21:07:20<34:06:13,  7.06s/it]
                                                           
{'loss': 0.6344, 'learning_rate': 0.00035543455429517466, 'epoch': 4.57}

 38%|███▊      | 10687/28080 [21:07:20<34:06:13,  7.06s/it]
 38%|███▊      | 10688/28080 [21:07:27<34:04:47,  7.05s/it]
                                                           
{'loss': 0.6193, 'learning_rate': 0.00035540840774933086, 'epoch': 4.57}

 38%|███▊      | 10688/28080 [21:07:27<34:04:47,  7.05s/it]
 38%|███▊      | 10689/28080 [21:07:34<34:04:50,  7.05s/it]
                                                           
{'loss': 0.6188, 'learning_rate': 0.0003553822598011369, 'epoch': 4.57}

 38%|███▊      | 10689/28080 [21:07:34<34:04:50,  7.05s/it]
 38%|███▊      | 10690/28080 [21:07:41<34:11:50,  7.08s/it]
                                                           
{'loss': 0.6269, 'learning_rate': 0.00035535611045094063, 'epoch': 4.57}

 38%|███▊      | 10690/28080 [21:07:41<34:11:50,  7.08s/it]
 38%|███▊      | 10691/28080 [21:07:48<34:10:49,  7.08s/it]
                                                           
{'loss': 0.6131, 'learning_rate': 0.00035532995969909004, 'epoch': 4.57}

 38%|███▊      | 10691/28080 [21:07:48<34:10:49,  7.08s/it]
 38%|███▊      | 10692/28080 [21:07:55<34:04:37,  7.06s/it]
                                                           
{'loss': 0.6396, 'learning_rate': 0.0003553038075459331, 'epoch': 4.57}

 38%|███▊      | 10692/28080 [21:07:55<34:04:37,  7.06s/it]
 38%|███▊      | 10693/28080 [21:08:02<34:09:04,  7.07s/it]
                                                           
{'loss': 0.6098, 'learning_rate': 0.00035527765399181755, 'epoch': 4.57}

 38%|███▊      | 10693/28080 [21:08:02<34:09:04,  7.07s/it]
 38%|███▊      | 10694/28080 [21:08:09<34:05:31,  7.06s/it]
                                                           
{'loss': 0.6378, 'learning_rate': 0.0003552514990370914, 'epoch': 4.57}

 38%|███▊      | 10694/28080 [21:08:09<34:05:31,  7.06s/it]
 38%|███▊      | 10695/28080 [21:08:16<34:09:02,  7.07s/it]
                                                           
{'loss': 0.6033, 'learning_rate': 0.00035522534268210267, 'epoch': 4.57}

 38%|███▊      | 10695/28080 [21:08:16<34:09:02,  7.07s/it]
 38%|███▊      | 10696/28080 [21:08:23<34:10:48,  7.08s/it]
                                                           
{'loss': 0.6243, 'learning_rate': 0.00035519918492719926, 'epoch': 4.57}

 38%|███▊      | 10696/28080 [21:08:23<34:10:48,  7.08s/it]
 38%|███▊      | 10697/28080 [21:08:30<34:10:14,  7.08s/it]
                                                           
{'loss': 0.6185, 'learning_rate': 0.0003551730257727293, 'epoch': 4.57}

 38%|███▊      | 10697/28080 [21:08:30<34:10:14,  7.08s/it]
 38%|███▊      | 10698/28080 [21:08:37<34:13:22,  7.09s/it]
                                                           
{'loss': 0.652, 'learning_rate': 0.00035514686521904065, 'epoch': 4.57}

 38%|███▊      | 10698/28080 [21:08:37<34:13:22,  7.09s/it]
 38%|███▊      | 10699/28080 [21:08:45<34:17:53,  7.10s/it]
                                                           
{'loss': 0.6291, 'learning_rate': 0.0003551207032664815, 'epoch': 4.57}

 38%|███▊      | 10699/28080 [21:08:45<34:17:53,  7.10s/it]
 38%|███▊      | 10700/28080 [21:08:52<34:31:11,  7.15s/it]
                                                           
{'loss': 0.6255, 'learning_rate': 0.0003550945399153998, 'epoch': 4.57}

 38%|███▊      | 10700/28080 [21:08:52<34:31:11,  7.15s/it]
 38%|███▊      | 10701/28080 [21:08:59<34:30:02,  7.15s/it]
                                                           
{'loss': 0.6507, 'learning_rate': 0.00035506837516614364, 'epoch': 4.57}

 38%|███▊      | 10701/28080 [21:08:59<34:30:02,  7.15s/it]
 38%|███▊      | 10702/28080 [21:09:06<34:27:24,  7.14s/it]
                                                           
{'loss': 0.619, 'learning_rate': 0.00035504220901906125, 'epoch': 4.57}

 38%|███▊      | 10702/28080 [21:09:06<34:27:24,  7.14s/it]
 38%|███▊      | 10703/28080 [21:09:13<34:21:31,  7.12s/it]
                                                           
{'loss': 0.6166, 'learning_rate': 0.00035501604147450053, 'epoch': 4.57}

 38%|███▊      | 10703/28080 [21:09:13<34:21:31,  7.12s/it]
 38%|███▊      | 10704/28080 [21:09:20<34:22:28,  7.12s/it]
                                                           
{'loss': 0.6264, 'learning_rate': 0.0003549898725328098, 'epoch': 4.57}

 38%|███▊      | 10704/28080 [21:09:20<34:22:28,  7.12s/it]
 38%|███▊      | 10705/28080 [21:09:27<34:26:01,  7.13s/it]
                                                           
{'loss': 0.6069, 'learning_rate': 0.00035496370219433704, 'epoch': 4.57}

 38%|███▊      | 10705/28080 [21:09:27<34:26:01,  7.13s/it]
 38%|███▊      | 10706/28080 [21:09:34<34:16:30,  7.10s/it]
                                                           
{'loss': 0.6196, 'learning_rate': 0.00035493753045943055, 'epoch': 4.57}

 38%|███▊      | 10706/28080 [21:09:34<34:16:30,  7.10s/it]
 38%|███▊      | 10707/28080 [21:09:42<34:18:31,  7.11s/it]
                                                           
{'loss': 0.6277, 'learning_rate': 0.0003549113573284385, 'epoch': 4.57}

 38%|███▊      | 10707/28080 [21:09:42<34:18:31,  7.11s/it]
 38%|███▊      | 10708/28080 [21:09:49<34:15:43,  7.10s/it]
                                                           
{'loss': 0.6367, 'learning_rate': 0.000354885182801709, 'epoch': 4.57}

 38%|███▊      | 10708/28080 [21:09:49<34:15:43,  7.10s/it]
 38%|███▊      | 10709/28080 [21:09:56<34:13:12,  7.09s/it]
                                                           
{'loss': 0.6377, 'learning_rate': 0.00035485900687959044, 'epoch': 4.57}

 38%|███▊      | 10709/28080 [21:09:56<34:13:12,  7.09s/it]
 38%|███▊      | 10710/28080 [21:10:03<34:16:56,  7.11s/it]
                                                           
{'loss': 0.6377, 'learning_rate': 0.0003548328295624309, 'epoch': 4.58}

 38%|███▊      | 10710/28080 [21:10:03<34:16:56,  7.11s/it]
 38%|███▊      | 10711/28080 [21:10:10<34:19:22,  7.11s/it]
                                                           
{'loss': 0.609, 'learning_rate': 0.0003548066508505787, 'epoch': 4.58}

 38%|███▊      | 10711/28080 [21:10:10<34:19:22,  7.11s/it]
 38%|███▊      | 10712/28080 [21:10:17<34:24:51,  7.13s/it]
                                                           
{'loss': 0.6187, 'learning_rate': 0.0003547804707443822, 'epoch': 4.58}

 38%|███▊      | 10712/28080 [21:10:17<34:24:51,  7.13s/it]
 38%|███▊      | 10713/28080 [21:10:24<34:25:36,  7.14s/it]
                                                           
{'loss': 0.6428, 'learning_rate': 0.0003547542892441896, 'epoch': 4.58}

 38%|███▊      | 10713/28080 [21:10:24<34:25:36,  7.14s/it]
 38%|███▊      | 10714/28080 [21:10:31<34:21:45,  7.12s/it]
                                                           
{'loss': 0.6231, 'learning_rate': 0.0003547281063503492, 'epoch': 4.58}

 38%|███▊      | 10714/28080 [21:10:31<34:21:45,  7.12s/it]
 38%|███▊      | 10715/28080 [21:10:38<34:10:55,  7.09s/it]
                                                           
{'loss': 0.641, 'learning_rate': 0.0003547019220632095, 'epoch': 4.58}

 38%|███▊      | 10715/28080 [21:10:38<34:10:55,  7.09s/it]
 38%|███▊      | 10716/28080 [21:10:46<34:09:49,  7.08s/it]
                                                           
{'loss': 0.6304, 'learning_rate': 0.0003546757363831187, 'epoch': 4.58}

 38%|███▊      | 10716/28080 [21:10:46<34:09:49,  7.08s/it]
 38%|███▊      | 10717/28080 [21:10:53<34:06:16,  7.07s/it]
                                                           
{'loss': 0.6317, 'learning_rate': 0.0003546495493104253, 'epoch': 4.58}

 38%|███▊      | 10717/28080 [21:10:53<34:06:16,  7.07s/it]
 38%|███▊      | 10718/28080 [21:11:00<34:06:49,  7.07s/it]
                                                           
{'loss': 0.6303, 'learning_rate': 0.0003546233608454774, 'epoch': 4.58}

 38%|███▊      | 10718/28080 [21:11:00<34:06:49,  7.07s/it]
 38%|███▊      | 10719/28080 [21:11:07<34:09:17,  7.08s/it]
                                                           
{'loss': 0.6326, 'learning_rate': 0.00035459717098862377, 'epoch': 4.58}

 38%|███▊      | 10719/28080 [21:11:07<34:09:17,  7.08s/it]
 38%|███▊      | 10720/28080 [21:11:14<34:13:01,  7.10s/it]
                                                           
{'loss': 0.6323, 'learning_rate': 0.00035457097974021264, 'epoch': 4.58}

 38%|███▊      | 10720/28080 [21:11:14<34:13:01,  7.10s/it]
 38%|███▊      | 10721/28080 [21:11:21<34:19:23,  7.12s/it]
                                                           
{'loss': 0.6202, 'learning_rate': 0.00035454478710059253, 'epoch': 4.58}

 38%|███▊      | 10721/28080 [21:11:21<34:19:23,  7.12s/it]
 38%|███▊      | 10722/28080 [21:11:28<34:14:25,  7.10s/it]
                                                           
{'loss': 0.6157, 'learning_rate': 0.0003545185930701118, 'epoch': 4.58}

 38%|███▊      | 10722/28080 [21:11:28<34:14:25,  7.10s/it]
 38%|███▊      | 10723/28080 [21:11:35<34:17:15,  7.11s/it]
                                                           
{'loss': 0.6411, 'learning_rate': 0.00035449239764911907, 'epoch': 4.58}

 38%|███▊      | 10723/28080 [21:11:35<34:17:15,  7.11s/it]
 38%|███▊      | 10724/28080 [21:11:42<34:20:33,  7.12s/it]
                                                           
{'loss': 0.6297, 'learning_rate': 0.00035446620083796275, 'epoch': 4.58}

 38%|███▊      | 10724/28080 [21:11:42<34:20:33,  7.12s/it]
 38%|███▊      | 10725/28080 [21:11:49<34:17:38,  7.11s/it]
                                                           
{'loss': 0.6201, 'learning_rate': 0.0003544400026369915, 'epoch': 4.58}

 38%|███▊      | 10725/28080 [21:11:49<34:17:38,  7.11s/it]
 38%|███▊      | 10726/28080 [21:11:57<34:15:49,  7.11s/it]
                                                           
{'loss': 0.6213, 'learning_rate': 0.00035441380304655366, 'epoch': 4.58}

 38%|███▊      | 10726/28080 [21:11:57<34:15:49,  7.11s/it]
 38%|███▊      | 10727/28080 [21:12:04<34:11:43,  7.09s/it]
                                                           
{'loss': 0.6262, 'learning_rate': 0.00035438760206699793, 'epoch': 4.58}

 38%|███▊      | 10727/28080 [21:12:04<34:11:43,  7.09s/it]
 38%|███▊      | 10728/28080 [21:12:11<34:05:45,  7.07s/it]
                                                           
{'loss': 0.6213, 'learning_rate': 0.00035436139969867285, 'epoch': 4.58}

 38%|███▊      | 10728/28080 [21:12:11<34:05:45,  7.07s/it]
 38%|███▊      | 10729/28080 [21:12:18<34:06:38,  7.08s/it]
                                                           
{'loss': 0.6149, 'learning_rate': 0.00035433519594192696, 'epoch': 4.58}

 38%|███▊      | 10729/28080 [21:12:18<34:06:38,  7.08s/it]
 38%|███▊      | 10730/28080 [21:12:25<34:04:04,  7.07s/it]
                                                           
{'loss': 0.614, 'learning_rate': 0.00035430899079710897, 'epoch': 4.58}

 38%|███▊      | 10730/28080 [21:12:25<34:04:04,  7.07s/it]
 38%|███▊      | 10731/28080 [21:12:32<34:03:16,  7.07s/it]
                                                           
{'loss': 0.6419, 'learning_rate': 0.0003542827842645675, 'epoch': 4.58}

 38%|███▊      | 10731/28080 [21:12:32<34:03:16,  7.07s/it]
 38%|███▊      | 10732/28080 [21:12:39<34:03:46,  7.07s/it]
                                                           
{'loss': 0.622, 'learning_rate': 0.00035425657634465115, 'epoch': 4.58}

 38%|███▊      | 10732/28080 [21:12:39<34:03:46,  7.07s/it]
 38%|███▊      | 10733/28080 [21:12:46<34:02:15,  7.06s/it]
                                                           
{'loss': 0.6336, 'learning_rate': 0.00035423036703770863, 'epoch': 4.59}

 38%|███▊      | 10733/28080 [21:12:46<34:02:15,  7.06s/it]
 38%|███▊      | 10734/28080 [21:12:53<34:11:17,  7.10s/it]
                                                           
{'loss': 0.6259, 'learning_rate': 0.0003542041563440885, 'epoch': 4.59}

 38%|███▊      | 10734/28080 [21:12:53<34:11:17,  7.10s/it]
 38%|███▊      | 10735/28080 [21:13:00<34:14:04,  7.11s/it]
                                                           
{'loss': 0.6319, 'learning_rate': 0.00035417794426413965, 'epoch': 4.59}

 38%|███▊      | 10735/28080 [21:13:00<34:14:04,  7.11s/it]
 38%|███▊      | 10736/28080 [21:13:07<34:02:20,  7.07s/it]
                                                           
{'loss': 0.6082, 'learning_rate': 0.0003541517307982107, 'epoch': 4.59}

 38%|███▊      | 10736/28080 [21:13:07<34:02:20,  7.07s/it]
 38%|███▊      | 10737/28080 [21:13:14<34:00:22,  7.06s/it]
                                                           
{'loss': 0.6219, 'learning_rate': 0.0003541255159466504, 'epoch': 4.59}

 38%|███▊      | 10737/28080 [21:13:14<34:00:22,  7.06s/it]
 38%|███▊      | 10738/28080 [21:13:21<33:56:18,  7.05s/it]
                                                           
{'loss': 0.6285, 'learning_rate': 0.00035409929970980756, 'epoch': 4.59}

 38%|███▊      | 10738/28080 [21:13:21<33:56:18,  7.05s/it]
 38%|███▊      | 10739/28080 [21:13:28<34:07:14,  7.08s/it]
                                                           
{'loss': 0.6332, 'learning_rate': 0.0003540730820880309, 'epoch': 4.59}

 38%|███▊      | 10739/28080 [21:13:28<34:07:14,  7.08s/it]
 38%|███▊      | 10740/28080 [21:13:36<34:03:38,  7.07s/it]
                                                           
{'loss': 0.6513, 'learning_rate': 0.00035404686308166934, 'epoch': 4.59}

 38%|███▊      | 10740/28080 [21:13:36<34:03:38,  7.07s/it]
 38%|███▊      | 10741/28080 [21:13:43<34:06:39,  7.08s/it]
                                                           
{'loss': 0.6394, 'learning_rate': 0.00035402064269107156, 'epoch': 4.59}

 38%|███▊      | 10741/28080 [21:13:43<34:06:39,  7.08s/it]
 38%|███▊      | 10742/28080 [21:13:50<34:09:14,  7.09s/it]
                                                           
{'loss': 0.6282, 'learning_rate': 0.0003539944209165864, 'epoch': 4.59}

 38%|███▊      | 10742/28080 [21:13:50<34:09:14,  7.09s/it]
 38%|███▊      | 10743/28080 [21:13:57<34:13:29,  7.11s/it]
                                                           
{'loss': 0.6142, 'learning_rate': 0.0003539681977585628, 'epoch': 4.59}

 38%|███▊      | 10743/28080 [21:13:57<34:13:29,  7.11s/it]
 38%|███▊      | 10744/28080 [21:14:04<34:17:05,  7.12s/it]
                                                           
{'loss': 0.6165, 'learning_rate': 0.00035394197321734957, 'epoch': 4.59}

 38%|███▊      | 10744/28080 [21:14:04<34:17:05,  7.12s/it]
 38%|███▊      | 10745/28080 [21:14:11<34:06:12,  7.08s/it]
                                                           
{'loss': 0.6447, 'learning_rate': 0.00035391574729329566, 'epoch': 4.59}

 38%|███▊      | 10745/28080 [21:14:11<34:06:12,  7.08s/it]
 38%|███▊      | 10746/28080 [21:14:18<34:03:49,  7.07s/it]
                                                           
{'loss': 0.6154, 'learning_rate': 0.0003538895199867499, 'epoch': 4.59}

 38%|███▊      | 10746/28080 [21:14:18<34:03:49,  7.07s/it]
 38%|███▊      | 10747/28080 [21:14:25<34:01:18,  7.07s/it]
                                                           
{'loss': 0.6523, 'learning_rate': 0.0003538632912980613, 'epoch': 4.59}

 38%|███▊      | 10747/28080 [21:14:25<34:01:18,  7.07s/it]
 38%|███▊      | 10748/28080 [21:14:32<34:03:26,  7.07s/it]
                                                           
{'loss': 0.6516, 'learning_rate': 0.00035383706122757864, 'epoch': 4.59}

 38%|███▊      | 10748/28080 [21:14:32<34:03:26,  7.07s/it]
 38%|███▊      | 10749/28080 [21:14:39<34:05:18,  7.08s/it]
                                                           
{'loss': 0.6276, 'learning_rate': 0.00035381082977565105, 'epoch': 4.59}

 38%|███▊      | 10749/28080 [21:14:39<34:05:18,  7.08s/it]
 38%|███▊      | 10750/28080 [21:14:46<34:07:13,  7.09s/it]
                                                           
{'loss': 0.6399, 'learning_rate': 0.0003537845969426275, 'epoch': 4.59}

 38%|███▊      | 10750/28080 [21:14:46<34:07:13,  7.09s/it]
 38%|███▊      | 10751/28080 [21:14:54<34:12:47,  7.11s/it]
                                                           
{'loss': 0.5981, 'learning_rate': 0.0003537583627288569, 'epoch': 4.59}

 38%|███▊      | 10751/28080 [21:14:54<34:12:47,  7.11s/it]
 38%|███▊      | 10752/28080 [21:15:01<34:12:11,  7.11s/it]
                                                           
{'loss': 0.6337, 'learning_rate': 0.0003537321271346884, 'epoch': 4.59}

 38%|███▊      | 10752/28080 [21:15:01<34:12:11,  7.11s/it]
 38%|███▊      | 10753/28080 [21:15:08<34:08:29,  7.09s/it]
                                                           
{'loss': 0.6219, 'learning_rate': 0.00035370589016047094, 'epoch': 4.59}

 38%|███▊      | 10753/28080 [21:15:08<34:08:29,  7.09s/it]
 38%|███▊      | 10754/28080 [21:15:15<34:08:46,  7.09s/it]
                                                           
{'loss': 0.6483, 'learning_rate': 0.00035367965180655353, 'epoch': 4.59}

 38%|███▊      | 10754/28080 [21:15:15<34:08:46,  7.09s/it]
 38%|███▊      | 10755/28080 [21:15:22<33:57:56,  7.06s/it]
                                                           
{'loss': 0.6346, 'learning_rate': 0.0003536534120732854, 'epoch': 4.59}

 38%|███▊      | 10755/28080 [21:15:22<33:57:56,  7.06s/it]
 38%|███▊      | 10756/28080 [21:15:29<33:55:52,  7.05s/it]
                                                           
{'loss': 0.6224, 'learning_rate': 0.0003536271709610155, 'epoch': 4.59}

 38%|███▊      | 10756/28080 [21:15:29<33:55:52,  7.05s/it]
 38%|███▊      | 10757/28080 [21:15:36<34:00:10,  7.07s/it]
                                                           
{'loss': 0.6439, 'learning_rate': 0.00035360092847009305, 'epoch': 4.6}

 38%|███▊      | 10757/28080 [21:15:36<34:00:10,  7.07s/it]
 38%|███▊      | 10758/28080 [21:15:43<34:10:08,  7.10s/it]
                                                           
{'loss': 0.6258, 'learning_rate': 0.00035357468460086704, 'epoch': 4.6}

 38%|███▊      | 10758/28080 [21:15:43<34:10:08,  7.10s/it]
 38%|███▊      | 10759/28080 [21:15:50<34:03:48,  7.08s/it]
                                                           
{'loss': 0.6243, 'learning_rate': 0.00035354843935368687, 'epoch': 4.6}

 38%|███▊      | 10759/28080 [21:15:50<34:03:48,  7.08s/it]
 38%|███▊      | 10760/28080 [21:15:57<34:00:58,  7.07s/it]
                                                           
{'loss': 0.6328, 'learning_rate': 0.0003535221927289014, 'epoch': 4.6}

 38%|███▊      | 10760/28080 [21:15:57<34:00:58,  7.07s/it]
 38%|███▊      | 10761/28080 [21:16:04<33:59:00,  7.06s/it]
                                                           
{'loss': 0.6267, 'learning_rate': 0.0003534959447268599, 'epoch': 4.6}

 38%|███▊      | 10761/28080 [21:16:04<33:59:00,  7.06s/it]
 38%|███▊      | 10762/28080 [21:16:11<34:02:57,  7.08s/it]
                                                           
{'loss': 0.606, 'learning_rate': 0.00035346969534791176, 'epoch': 4.6}

 38%|███▊      | 10762/28080 [21:16:11<34:02:57,  7.08s/it]
 38%|███▊      | 10763/28080 [21:16:18<34:03:12,  7.08s/it]
                                                           
{'loss': 0.6303, 'learning_rate': 0.000353443444592406, 'epoch': 4.6}

 38%|███▊      | 10763/28080 [21:16:18<34:03:12,  7.08s/it]
 38%|███▊      | 10764/28080 [21:16:26<34:06:28,  7.09s/it]
                                                           
{'loss': 0.6212, 'learning_rate': 0.000353417192460692, 'epoch': 4.6}

 38%|███▊      | 10764/28080 [21:16:26<34:06:28,  7.09s/it]
 38%|███▊      | 10765/28080 [21:16:33<34:09:54,  7.10s/it]
                                                           
{'loss': 0.6236, 'learning_rate': 0.00035339093895311885, 'epoch': 4.6}

 38%|███▊      | 10765/28080 [21:16:33<34:09:54,  7.10s/it]
 38%|███▊      | 10766/28080 [21:16:40<34:08:30,  7.10s/it]
                                                           
{'loss': 0.6373, 'learning_rate': 0.00035336468407003597, 'epoch': 4.6}

 38%|███▊      | 10766/28080 [21:16:40<34:08:30,  7.10s/it]
 38%|███▊      | 10767/28080 [21:16:47<33:55:09,  7.05s/it]
                                                           
{'loss': 0.6539, 'learning_rate': 0.00035333842781179263, 'epoch': 4.6}

 38%|███▊      | 10767/28080 [21:16:47<33:55:09,  7.05s/it]
 38%|███▊      | 10768/28080 [21:16:54<33:54:37,  7.05s/it]
                                                           
{'loss': 0.6442, 'learning_rate': 0.00035331217017873807, 'epoch': 4.6}

 38%|███▊      | 10768/28080 [21:16:54<33:54:37,  7.05s/it]
 38%|███▊      | 10769/28080 [21:17:01<34:06:21,  7.09s/it]
                                                           
{'loss': 0.6258, 'learning_rate': 0.00035328591117122165, 'epoch': 4.6}

 38%|███▊      | 10769/28080 [21:17:01<34:06:21,  7.09s/it]
 38%|███▊      | 10770/28080 [21:17:08<34:14:19,  7.12s/it]
                                                           
{'loss': 0.6283, 'learning_rate': 0.00035325965078959276, 'epoch': 4.6}

 38%|███▊      | 10770/28080 [21:17:08<34:14:19,  7.12s/it]
 38%|███▊      | 10771/28080 [21:17:15<34:14:25,  7.12s/it]
                                                           
{'loss': 0.6087, 'learning_rate': 0.0003532333890342008, 'epoch': 4.6}

 38%|███▊      | 10771/28080 [21:17:15<34:14:25,  7.12s/it]
 38%|███▊      | 10772/28080 [21:17:22<34:14:45,  7.12s/it]
                                                           
{'loss': 0.6129, 'learning_rate': 0.000353207125905395, 'epoch': 4.6}

 38%|███▊      | 10772/28080 [21:17:22<34:14:45,  7.12s/it]
 38%|███▊      | 10773/28080 [21:17:30<34:19:42,  7.14s/it]
                                                           
{'loss': 0.6158, 'learning_rate': 0.0003531808614035249, 'epoch': 4.6}

 38%|███▊      | 10773/28080 [21:17:30<34:19:42,  7.14s/it]
 38%|███▊      | 10774/28080 [21:17:37<34:19:38,  7.14s/it]
                                                           
{'loss': 0.6318, 'learning_rate': 0.0003531545955289399, 'epoch': 4.6}

 38%|███▊      | 10774/28080 [21:17:37<34:19:38,  7.14s/it]
 38%|███▊      | 10775/28080 [21:17:44<34:17:11,  7.13s/it]
                                                           
{'loss': 0.637, 'learning_rate': 0.00035312832828198945, 'epoch': 4.6}

 38%|███▊      | 10775/28080 [21:17:44<34:17:11,  7.13s/it]
 38%|███▊      | 10776/28080 [21:17:51<34:13:34,  7.12s/it]
                                                           
{'loss': 0.6201, 'learning_rate': 0.00035310205966302294, 'epoch': 4.6}

 38%|███▊      | 10776/28080 [21:17:51<34:13:34,  7.12s/it]
 38%|███▊      | 10777/28080 [21:17:58<34:16:14,  7.13s/it]
                                                           
{'loss': 0.6105, 'learning_rate': 0.0003530757896723899, 'epoch': 4.6}

 38%|███▊      | 10777/28080 [21:17:58<34:16:14,  7.13s/it]
 38%|███▊      | 10778/28080 [21:18:05<34:12:45,  7.12s/it]
                                                           
{'loss': 0.629, 'learning_rate': 0.00035304951831043984, 'epoch': 4.6}

 38%|███▊      | 10778/28080 [21:18:05<34:12:45,  7.12s/it]
 38%|███▊      | 10779/28080 [21:18:12<34:06:47,  7.10s/it]
                                                           
{'loss': 0.6073, 'learning_rate': 0.0003530232455775222, 'epoch': 4.6}

 38%|███▊      | 10779/28080 [21:18:12<34:06:47,  7.10s/it]
 38%|███▊      | 10780/28080 [21:18:19<33:57:15,  7.07s/it]
                                                           
{'loss': 0.622, 'learning_rate': 0.00035299697147398655, 'epoch': 4.61}

 38%|███▊      | 10780/28080 [21:18:19<33:57:15,  7.07s/it]
 38%|███▊      | 10781/28080 [21:18:26<34:00:06,  7.08s/it]
                                                           
{'loss': 0.6333, 'learning_rate': 0.0003529706960001825, 'epoch': 4.61}

 38%|███▊      | 10781/28080 [21:18:26<34:00:06,  7.08s/it]
 38%|███▊      | 10782/28080 [21:18:33<34:03:27,  7.09s/it]
                                                           
{'loss': 0.6314, 'learning_rate': 0.00035294441915645954, 'epoch': 4.61}

 38%|███▊      | 10782/28080 [21:18:33<34:03:27,  7.09s/it]
 38%|███▊      | 10783/28080 [21:18:41<34:03:37,  7.09s/it]
                                                           
{'loss': 0.6299, 'learning_rate': 0.0003529181409431673, 'epoch': 4.61}

 38%|███▊      | 10783/28080 [21:18:41<34:03:37,  7.09s/it]
 38%|███▊      | 10784/28080 [21:18:48<34:02:29,  7.09s/it]
                                                           
{'loss': 0.6286, 'learning_rate': 0.00035289186136065536, 'epoch': 4.61}

 38%|███▊      | 10784/28080 [21:18:48<34:02:29,  7.09s/it]
 38%|███▊      | 10785/28080 [21:18:55<34:00:57,  7.08s/it]
                                                           
{'loss': 0.6413, 'learning_rate': 0.0003528655804092734, 'epoch': 4.61}

 38%|███▊      | 10785/28080 [21:18:55<34:00:57,  7.08s/it]
 38%|███▊      | 10786/28080 [21:19:02<34:05:16,  7.10s/it]
                                                           
{'loss': 0.6211, 'learning_rate': 0.000352839298089371, 'epoch': 4.61}

 38%|███▊      | 10786/28080 [21:19:02<34:05:16,  7.10s/it]
 38%|███▊      | 10787/28080 [21:19:09<33:57:07,  7.07s/it]
                                                           
{'loss': 0.6053, 'learning_rate': 0.00035281301440129775, 'epoch': 4.61}

 38%|███▊      | 10787/28080 [21:19:09<33:57:07,  7.07s/it]
 38%|███▊      | 10788/28080 [21:19:16<34:04:48,  7.10s/it]
                                                           
{'loss': 0.6518, 'learning_rate': 0.0003527867293454035, 'epoch': 4.61}

 38%|███▊      | 10788/28080 [21:19:16<34:04:48,  7.10s/it]
 38%|███▊      | 10789/28080 [21:19:23<34:02:01,  7.09s/it]
                                                           
{'loss': 0.6143, 'learning_rate': 0.0003527604429220378, 'epoch': 4.61}

 38%|███▊      | 10789/28080 [21:19:23<34:02:01,  7.09s/it]
 38%|███▊      | 10790/28080 [21:19:30<34:05:08,  7.10s/it]
                                                           
{'loss': 0.6186, 'learning_rate': 0.0003527341551315505, 'epoch': 4.61}

 38%|███▊      | 10790/28080 [21:19:30<34:05:08,  7.10s/it]
 38%|███▊      | 10791/28080 [21:19:37<34:03:34,  7.09s/it]
                                                           
{'loss': 0.6266, 'learning_rate': 0.00035270786597429115, 'epoch': 4.61}

 38%|███▊      | 10791/28080 [21:19:37<34:03:34,  7.09s/it]
 38%|███▊      | 10792/28080 [21:19:44<34:10:26,  7.12s/it]
                                                           
{'loss': 0.5968, 'learning_rate': 0.0003526815754506096, 'epoch': 4.61}

 38%|███▊      | 10792/28080 [21:19:44<34:10:26,  7.12s/it]
 38%|███▊      | 10793/28080 [21:19:52<34:17:51,  7.14s/it]
                                                           
{'loss': 0.6253, 'learning_rate': 0.00035265528356085574, 'epoch': 4.61}

 38%|███▊      | 10793/28080 [21:19:52<34:17:51,  7.14s/it]
 38%|███▊      | 10794/28080 [21:19:59<34:19:54,  7.15s/it]
                                                           
{'loss': 0.6192, 'learning_rate': 0.00035262899030537916, 'epoch': 4.61}

 38%|███▊      | 10794/28080 [21:19:59<34:19:54,  7.15s/it]
 38%|███▊      | 10795/28080 [21:20:06<34:22:36,  7.16s/it]
                                                           
{'loss': 0.6156, 'learning_rate': 0.0003526026956845297, 'epoch': 4.61}

 38%|███▊      | 10795/28080 [21:20:06<34:22:36,  7.16s/it]
 38%|███▊      | 10796/28080 [21:20:13<34:23:55,  7.16s/it]
                                                           
{'loss': 0.637, 'learning_rate': 0.0003525763996986573, 'epoch': 4.61}

 38%|███▊      | 10796/28080 [21:20:13<34:23:55,  7.16s/it]
 38%|███▊      | 10797/28080 [21:20:20<34:19:50,  7.15s/it]
                                                           
{'loss': 0.6163, 'learning_rate': 0.0003525501023481117, 'epoch': 4.61}

 38%|███▊      | 10797/28080 [21:20:20<34:19:50,  7.15s/it]
 38%|███▊      | 10798/28080 [21:20:27<34:18:12,  7.15s/it]
                                                           
{'loss': 0.621, 'learning_rate': 0.0003525238036332428, 'epoch': 4.61}

 38%|███▊      | 10798/28080 [21:20:27<34:18:12,  7.15s/it]
 38%|███▊      | 10799/28080 [21:20:35<34:31:36,  7.19s/it]
                                                           
{'loss': 0.6169, 'learning_rate': 0.00035249750355440034, 'epoch': 4.61}

 38%|███▊      | 10799/28080 [21:20:35<34:31:36,  7.19s/it]
 38%|███▊      | 10800/28080 [21:20:42<34:25:06,  7.17s/it]
                                                           
{'loss': 0.6295, 'learning_rate': 0.0003524712021119345, 'epoch': 4.61}

 38%|███▊      | 10800/28080 [21:20:42<34:25:06,  7.17s/it]
 38%|███▊      | 10801/28080 [21:20:49<34:30:46,  7.19s/it]
                                                           
{'loss': 0.6116, 'learning_rate': 0.00035244489930619493, 'epoch': 4.61}

 38%|███▊      | 10801/28080 [21:20:49<34:30:46,  7.19s/it]
 38%|███▊      | 10802/28080 [21:20:56<34:23:22,  7.17s/it]
                                                           
{'loss': 0.6214, 'learning_rate': 0.0003524185951375317, 'epoch': 4.61}

 38%|███▊      | 10802/28080 [21:20:56<34:23:22,  7.17s/it]
 38%|███▊      | 10803/28080 [21:21:03<34:15:45,  7.14s/it]
                                                           
{'loss': 0.6221, 'learning_rate': 0.00035239228960629466, 'epoch': 4.61}

 38%|███▊      | 10803/28080 [21:21:03<34:15:45,  7.14s/it]
 38%|███▊      | 10804/28080 [21:21:10<34:17:36,  7.15s/it]
                                                           
{'loss': 0.6281, 'learning_rate': 0.0003523659827128339, 'epoch': 4.62}

 38%|███▊      | 10804/28080 [21:21:10<34:17:36,  7.15s/it]
 38%|███▊      | 10805/28080 [21:21:18<34:13:57,  7.13s/it]
                                                           
{'loss': 0.6279, 'learning_rate': 0.00035233967445749936, 'epoch': 4.62}

 38%|███▊      | 10805/28080 [21:21:18<34:13:57,  7.13s/it]
 38%|███▊      | 10806/28080 [21:21:25<34:08:49,  7.12s/it]
                                                           
{'loss': 0.6407, 'learning_rate': 0.000352313364840641, 'epoch': 4.62}

 38%|███▊      | 10806/28080 [21:21:25<34:08:49,  7.12s/it]
 38%|███▊      | 10807/28080 [21:21:32<34:02:01,  7.09s/it]
                                                           
{'loss': 0.6368, 'learning_rate': 0.00035228705386260883, 'epoch': 4.62}

 38%|███▊      | 10807/28080 [21:21:32<34:02:01,  7.09s/it]
 38%|███▊      | 10808/28080 [21:21:39<34:09:33,  7.12s/it]
                                                           
{'loss': 0.6187, 'learning_rate': 0.00035226074152375296, 'epoch': 4.62}

 38%|███▊      | 10808/28080 [21:21:39<34:09:33,  7.12s/it]
 38%|███▊      | 10809/28080 [21:21:46<34:12:56,  7.13s/it]
                                                           
{'loss': 0.6145, 'learning_rate': 0.0003522344278244235, 'epoch': 4.62}

 38%|███▊      | 10809/28080 [21:21:46<34:12:56,  7.13s/it]
 38%|███▊      | 10810/28080 [21:21:53<34:13:24,  7.13s/it]
                                                           
{'loss': 0.6267, 'learning_rate': 0.00035220811276497033, 'epoch': 4.62}

 38%|███▊      | 10810/28080 [21:21:53<34:13:24,  7.13s/it]
 39%|███▊      | 10811/28080 [21:22:00<34:13:10,  7.13s/it]
                                                           
{'loss': 0.6352, 'learning_rate': 0.0003521817963457437, 'epoch': 4.62}

 39%|███▊      | 10811/28080 [21:22:00<34:13:10,  7.13s/it]
 39%|███▊      | 10812/28080 [21:22:07<34:14:26,  7.14s/it]
                                                           
{'loss': 0.6542, 'learning_rate': 0.0003521554785670937, 'epoch': 4.62}

 39%|███▊      | 10812/28080 [21:22:07<34:14:26,  7.14s/it]
 39%|███▊      | 10813/28080 [21:22:15<34:16:09,  7.14s/it]
                                                           
{'loss': 0.6306, 'learning_rate': 0.00035212915942937044, 'epoch': 4.62}

 39%|███▊      | 10813/28080 [21:22:15<34:16:09,  7.14s/it]
 39%|███▊      | 10814/28080 [21:22:22<34:14:45,  7.14s/it]
                                                           
{'loss': 0.6103, 'learning_rate': 0.0003521028389329242, 'epoch': 4.62}

 39%|███▊      | 10814/28080 [21:22:22<34:14:45,  7.14s/it]
 39%|███▊      | 10815/28080 [21:22:29<34:16:27,  7.15s/it]
                                                           
{'loss': 0.615, 'learning_rate': 0.00035207651707810483, 'epoch': 4.62}

 39%|███▊      | 10815/28080 [21:22:29<34:16:27,  7.15s/it]
 39%|███▊      | 10816/28080 [21:22:36<34:11:48,  7.13s/it]
                                                           
{'loss': 0.629, 'learning_rate': 0.00035205019386526273, 'epoch': 4.62}

 39%|███▊      | 10816/28080 [21:22:36<34:11:48,  7.13s/it]
 39%|███▊      | 10817/28080 [21:22:43<34:17:14,  7.15s/it]
                                                           
{'loss': 0.6223, 'learning_rate': 0.00035202386929474825, 'epoch': 4.62}

 39%|███▊      | 10817/28080 [21:22:43<34:17:14,  7.15s/it]
 39%|███▊      | 10818/28080 [21:22:50<34:16:46,  7.15s/it]
                                                           
{'loss': 0.6307, 'learning_rate': 0.00035199754336691125, 'epoch': 4.62}

 39%|███▊      | 10818/28080 [21:22:50<34:16:46,  7.15s/it]
 39%|███▊      | 10819/28080 [21:22:57<34:22:25,  7.17s/it]
                                                           
{'loss': 0.6091, 'learning_rate': 0.00035197121608210227, 'epoch': 4.62}

 39%|███▊      | 10819/28080 [21:22:57<34:22:25,  7.17s/it]
 39%|███▊      | 10820/28080 [21:23:05<34:18:38,  7.16s/it]
                                                           
{'loss': 0.6311, 'learning_rate': 0.00035194488744067144, 'epoch': 4.62}

 39%|███▊      | 10820/28080 [21:23:05<34:18:38,  7.16s/it]
 39%|███▊      | 10821/28080 [21:23:12<34:12:17,  7.13s/it]
                                                           
{'loss': 0.6212, 'learning_rate': 0.00035191855744296896, 'epoch': 4.62}

 39%|███▊      | 10821/28080 [21:23:12<34:12:17,  7.13s/it]
 39%|███▊      | 10822/28080 [21:23:19<34:11:55,  7.13s/it]
                                                           
{'loss': 0.6095, 'learning_rate': 0.00035189222608934535, 'epoch': 4.62}

 39%|███▊      | 10822/28080 [21:23:19<34:11:55,  7.13s/it]
 39%|███▊      | 10823/28080 [21:23:26<34:21:47,  7.17s/it]
                                                           
{'loss': 0.632, 'learning_rate': 0.0003518658933801507, 'epoch': 4.62}

 39%|███▊      | 10823/28080 [21:23:26<34:21:47,  7.17s/it]
 39%|███▊      | 10824/28080 [21:23:33<34:16:57,  7.15s/it]
                                                           
{'loss': 0.6292, 'learning_rate': 0.0003518395593157355, 'epoch': 4.62}

 39%|███▊      | 10824/28080 [21:23:33<34:16:57,  7.15s/it]
 39%|███▊      | 10825/28080 [21:23:40<34:12:17,  7.14s/it]
                                                           
{'loss': 0.6482, 'learning_rate': 0.0003518132238964499, 'epoch': 4.62}

 39%|███▊      | 10825/28080 [21:23:40<34:12:17,  7.14s/it]
 39%|███▊      | 10826/28080 [21:23:47<33:59:45,  7.09s/it]
                                                           
{'loss': 0.6579, 'learning_rate': 0.00035178688712264453, 'epoch': 4.62}

 39%|███▊      | 10826/28080 [21:23:47<33:59:45,  7.09s/it]
 39%|███▊      | 10827/28080 [21:23:54<34:09:23,  7.13s/it]
                                                           
{'loss': 0.6129, 'learning_rate': 0.0003517605489946695, 'epoch': 4.63}

 39%|███▊      | 10827/28080 [21:23:54<34:09:23,  7.13s/it]
 39%|███▊      | 10828/28080 [21:24:02<33:59:35,  7.09s/it]
                                                           
{'loss': 0.619, 'learning_rate': 0.00035173420951287545, 'epoch': 4.63}

 39%|███▊      | 10828/28080 [21:24:02<33:59:35,  7.09s/it]
 39%|███▊      | 10829/28080 [21:24:09<34:02:41,  7.10s/it]
                                                           
{'loss': 0.6196, 'learning_rate': 0.0003517078686776127, 'epoch': 4.63}

 39%|███▊      | 10829/28080 [21:24:09<34:02:41,  7.10s/it]
 39%|███▊      | 10830/28080 [21:24:16<34:08:20,  7.12s/it]
                                                           
{'loss': 0.6331, 'learning_rate': 0.0003516815264892316, 'epoch': 4.63}

 39%|███▊      | 10830/28080 [21:24:16<34:08:20,  7.12s/it]
 39%|███▊      | 10831/28080 [21:24:23<34:07:09,  7.12s/it]
                                                           
{'loss': 0.63, 'learning_rate': 0.0003516551829480828, 'epoch': 4.63}

 39%|███▊      | 10831/28080 [21:24:23<34:07:09,  7.12s/it]
 39%|███▊      | 10832/28080 [21:24:30<34:03:27,  7.11s/it]
                                                           
{'loss': 0.6189, 'learning_rate': 0.00035162883805451656, 'epoch': 4.63}

 39%|███▊      | 10832/28080 [21:24:30<34:03:27,  7.11s/it]
 39%|███▊      | 10833/28080 [21:24:37<34:05:29,  7.12s/it]
                                                           
{'loss': 0.6272, 'learning_rate': 0.00035160249180888356, 'epoch': 4.63}

 39%|███▊      | 10833/28080 [21:24:37<34:05:29,  7.12s/it]
 39%|███▊      | 10834/28080 [21:24:44<34:06:44,  7.12s/it]
                                                           
{'loss': 0.5992, 'learning_rate': 0.0003515761442115342, 'epoch': 4.63}

 39%|███▊      | 10834/28080 [21:24:44<34:06:44,  7.12s/it]
 39%|███▊      | 10835/28080 [21:24:51<33:57:44,  7.09s/it]
                                                           
{'loss': 0.6153, 'learning_rate': 0.0003515497952628189, 'epoch': 4.63}

 39%|███▊      | 10835/28080 [21:24:51<33:57:44,  7.09s/it]
 39%|███▊      | 10836/28080 [21:24:58<33:53:49,  7.08s/it]
                                                           
{'loss': 0.6044, 'learning_rate': 0.0003515234449630885, 'epoch': 4.63}

 39%|███▊      | 10836/28080 [21:24:58<33:53:49,  7.08s/it]
 39%|███▊      | 10837/28080 [21:25:05<33:47:15,  7.05s/it]
                                                           
{'loss': 0.6239, 'learning_rate': 0.00035149709331269333, 'epoch': 4.63}

 39%|███▊      | 10837/28080 [21:25:05<33:47:15,  7.05s/it]
 39%|███▊      | 10838/28080 [21:25:12<33:47:10,  7.05s/it]
                                                           
{'loss': 0.6289, 'learning_rate': 0.00035147074031198413, 'epoch': 4.63}

 39%|███▊      | 10838/28080 [21:25:12<33:47:10,  7.05s/it]
 39%|███▊      | 10839/28080 [21:25:20<33:58:54,  7.10s/it]
                                                           
{'loss': 0.6092, 'learning_rate': 0.00035144438596131127, 'epoch': 4.63}

 39%|███▊      | 10839/28080 [21:25:20<33:58:54,  7.10s/it]
 39%|███▊      | 10840/28080 [21:25:27<33:52:44,  7.07s/it]
                                                           
{'loss': 0.6148, 'learning_rate': 0.00035141803026102566, 'epoch': 4.63}

 39%|███▊      | 10840/28080 [21:25:27<33:52:44,  7.07s/it]
 39%|███▊      | 10841/28080 [21:25:34<34:03:32,  7.11s/it]
                                                           
{'loss': 0.6346, 'learning_rate': 0.0003513916732114776, 'epoch': 4.63}

 39%|███▊      | 10841/28080 [21:25:34<34:03:32,  7.11s/it]
 39%|███▊      | 10842/28080 [21:25:41<33:57:56,  7.09s/it]
                                                           
{'loss': 0.6339, 'learning_rate': 0.0003513653148130181, 'epoch': 4.63}

 39%|███▊      | 10842/28080 [21:25:41<33:57:56,  7.09s/it]
 39%|███▊      | 10843/28080 [21:25:48<33:55:34,  7.09s/it]
                                                           
{'loss': 0.6375, 'learning_rate': 0.00035133895506599767, 'epoch': 4.63}

 39%|███▊      | 10843/28080 [21:25:48<33:55:34,  7.09s/it]
 39%|███▊      | 10844/28080 [21:25:55<33:51:04,  7.07s/it]
                                                           
{'loss': 0.6262, 'learning_rate': 0.0003513125939707669, 'epoch': 4.63}

 39%|███▊      | 10844/28080 [21:25:55<33:51:04,  7.07s/it]
 39%|███▊      | 10845/28080 [21:26:02<33:57:56,  7.09s/it]
                                                           
{'loss': 0.6049, 'learning_rate': 0.0003512862315276765, 'epoch': 4.63}

 39%|███▊      | 10845/28080 [21:26:02<33:57:56,  7.09s/it]
 39%|███▊      | 10846/28080 [21:26:09<33:50:35,  7.07s/it]
                                                           
{'loss': 0.6272, 'learning_rate': 0.0003512598677370775, 'epoch': 4.63}

 39%|███▊      | 10846/28080 [21:26:09<33:50:35,  7.07s/it]
 39%|███▊      | 10847/28080 [21:26:16<33:49:11,  7.07s/it]
                                                           
{'loss': 0.6298, 'learning_rate': 0.00035123350259932024, 'epoch': 4.63}

 39%|███▊      | 10847/28080 [21:26:16<33:49:11,  7.07s/it]
 39%|███▊      | 10848/28080 [21:26:23<33:54:11,  7.08s/it]
                                                           
{'loss': 0.6462, 'learning_rate': 0.0003512071361147557, 'epoch': 4.63}

 39%|███▊      | 10848/28080 [21:26:23<33:54:11,  7.08s/it]
 39%|███▊      | 10849/28080 [21:26:30<33:54:43,  7.09s/it]
                                                           
{'loss': 0.6315, 'learning_rate': 0.0003511807682837347, 'epoch': 4.63}

 39%|███▊      | 10849/28080 [21:26:30<33:54:43,  7.09s/it]
 39%|███▊      | 10850/28080 [21:26:38<33:57:35,  7.10s/it]
                                                           
{'loss': 0.6358, 'learning_rate': 0.0003511543991066079, 'epoch': 4.64}

 39%|███▊      | 10850/28080 [21:26:38<33:57:35,  7.10s/it]
 39%|███▊      | 10851/28080 [21:26:45<33:56:38,  7.09s/it]
                                                           
{'loss': 0.6203, 'learning_rate': 0.0003511280285837262, 'epoch': 4.64}

 39%|███▊      | 10851/28080 [21:26:45<33:56:38,  7.09s/it]
 39%|███▊      | 10852/28080 [21:26:52<33:50:27,  7.07s/it]
                                                           
{'loss': 0.6371, 'learning_rate': 0.00035110165671544037, 'epoch': 4.64}

 39%|███▊      | 10852/28080 [21:26:52<33:50:27,  7.07s/it]
 39%|███▊      | 10853/28080 [21:26:59<33:56:42,  7.09s/it]
                                                           
{'loss': 0.6159, 'learning_rate': 0.0003510752835021013, 'epoch': 4.64}

 39%|███▊      | 10853/28080 [21:26:59<33:56:42,  7.09s/it]
 39%|███▊      | 10854/28080 [21:27:06<34:02:50,  7.12s/it]
                                                           
{'loss': 0.6462, 'learning_rate': 0.0003510489089440599, 'epoch': 4.64}

 39%|███▊      | 10854/28080 [21:27:06<34:02:50,  7.12s/it]
 39%|███▊      | 10855/28080 [21:27:13<34:08:43,  7.14s/it]
                                                           
{'loss': 0.6167, 'learning_rate': 0.000351022533041667, 'epoch': 4.64}

 39%|███▊      | 10855/28080 [21:27:13<34:08:43,  7.14s/it]
 39%|███▊      | 10856/28080 [21:27:20<34:02:14,  7.11s/it]
                                                           
{'loss': 0.6179, 'learning_rate': 0.0003509961557952735, 'epoch': 4.64}

 39%|███▊      | 10856/28080 [21:27:20<34:02:14,  7.11s/it]
 39%|███▊      | 10857/28080 [21:27:27<34:01:19,  7.11s/it]
                                                           
{'loss': 0.6327, 'learning_rate': 0.00035096977720523037, 'epoch': 4.64}

 39%|███▊      | 10857/28080 [21:27:27<34:01:19,  7.11s/it]
 39%|███▊      | 10858/28080 [21:27:34<34:09:06,  7.14s/it]
                                                           
{'loss': 0.6119, 'learning_rate': 0.00035094339727188845, 'epoch': 4.64}

 39%|███▊      | 10858/28080 [21:27:34<34:09:06,  7.14s/it]
 39%|███▊      | 10859/28080 [21:27:42<34:05:44,  7.13s/it]
                                                           
{'loss': 0.6402, 'learning_rate': 0.00035091701599559885, 'epoch': 4.64}

 39%|███▊      | 10859/28080 [21:27:42<34:05:44,  7.13s/it]
 39%|███▊      | 10860/28080 [21:27:49<34:23:44,  7.19s/it]
                                                           
{'loss': 0.6222, 'learning_rate': 0.0003508906333767124, 'epoch': 4.64}

 39%|███▊      | 10860/28080 [21:27:49<34:23:44,  7.19s/it]
 39%|███▊      | 10861/28080 [21:27:56<34:24:33,  7.19s/it]
                                                           
{'loss': 0.6336, 'learning_rate': 0.00035086424941558014, 'epoch': 4.64}

 39%|███▊      | 10861/28080 [21:27:56<34:24:33,  7.19s/it]
 39%|███▊      | 10862/28080 [21:28:03<34:22:16,  7.19s/it]
                                                           
{'loss': 0.6521, 'learning_rate': 0.0003508378641125532, 'epoch': 4.64}

 39%|███▊      | 10862/28080 [21:28:03<34:22:16,  7.19s/it]
 39%|███▊      | 10863/28080 [21:28:10<34:17:48,  7.17s/it]
                                                           
{'loss': 0.6055, 'learning_rate': 0.00035081147746798244, 'epoch': 4.64}

 39%|███▊      | 10863/28080 [21:28:10<34:17:48,  7.17s/it]
 39%|███▊      | 10864/28080 [21:28:18<34:12:17,  7.15s/it]
                                                           
{'loss': 0.6153, 'learning_rate': 0.000350785089482219, 'epoch': 4.64}

 39%|███▊      | 10864/28080 [21:28:18<34:12:17,  7.15s/it]
 39%|███▊      | 10865/28080 [21:28:25<33:59:52,  7.11s/it]
                                                           
{'loss': 0.639, 'learning_rate': 0.00035075870015561383, 'epoch': 4.64}

 39%|███▊      | 10865/28080 [21:28:25<33:59:52,  7.11s/it]
 39%|███▊      | 10866/28080 [21:28:32<33:51:31,  7.08s/it]
                                                           
{'loss': 0.6594, 'learning_rate': 0.0003507323094885182, 'epoch': 4.64}

 39%|███▊      | 10866/28080 [21:28:32<33:51:31,  7.08s/it]
 39%|███▊      | 10867/28080 [21:28:39<33:54:49,  7.09s/it]
                                                           
{'loss': 0.6144, 'learning_rate': 0.00035070591748128315, 'epoch': 4.64}

 39%|███▊      | 10867/28080 [21:28:39<33:54:49,  7.09s/it]
 39%|███▊      | 10868/28080 [21:28:46<33:47:05,  7.07s/it]
                                                           
{'loss': 0.6416, 'learning_rate': 0.0003506795241342597, 'epoch': 4.64}

 39%|███▊      | 10868/28080 [21:28:46<33:47:05,  7.07s/it]
 39%|███▊      | 10869/28080 [21:28:53<33:51:19,  7.08s/it]
                                                           
{'loss': 0.6259, 'learning_rate': 0.000350653129447799, 'epoch': 4.64}

 39%|███▊      | 10869/28080 [21:28:53<33:51:19,  7.08s/it]
 39%|███▊      | 10870/28080 [21:29:00<34:00:39,  7.11s/it]
                                                           
{'loss': 0.6295, 'learning_rate': 0.00035062673342225233, 'epoch': 4.64}

 39%|███▊      | 10870/28080 [21:29:00<34:00:39,  7.11s/it]
 39%|███▊      | 10871/28080 [21:29:07<34:04:25,  7.13s/it]
                                                           
{'loss': 0.6478, 'learning_rate': 0.0003506003360579707, 'epoch': 4.64}

 39%|███▊      | 10871/28080 [21:29:07<34:04:25,  7.13s/it]
 39%|███▊      | 10872/28080 [21:29:14<34:07:49,  7.14s/it]
                                                           
{'loss': 0.6351, 'learning_rate': 0.0003505739373553055, 'epoch': 4.64}

 39%|███▊      | 10872/28080 [21:29:14<34:07:49,  7.14s/it]
 39%|███▊      | 10873/28080 [21:29:21<34:06:43,  7.14s/it]
                                                           
{'loss': 0.6484, 'learning_rate': 0.0003505475373146076, 'epoch': 4.64}

 39%|███▊      | 10873/28080 [21:29:21<34:06:43,  7.14s/it]
 39%|███▊      | 10874/28080 [21:29:29<34:06:11,  7.14s/it]
                                                           
{'loss': 0.6284, 'learning_rate': 0.0003505211359362287, 'epoch': 4.65}

 39%|███▊      | 10874/28080 [21:29:29<34:06:11,  7.14s/it]
 39%|███▊      | 10875/28080 [21:29:36<34:03:13,  7.13s/it]
                                                           
{'loss': 0.6349, 'learning_rate': 0.0003504947332205196, 'epoch': 4.65}

 39%|███▊      | 10875/28080 [21:29:36<34:03:13,  7.13s/it]
 39%|███▊      | 10876/28080 [21:29:43<33:57:21,  7.11s/it]
                                                           
{'loss': 0.6525, 'learning_rate': 0.0003504683291678318, 'epoch': 4.65}

 39%|███▊      | 10876/28080 [21:29:43<33:57:21,  7.11s/it]
 39%|███▊      | 10877/28080 [21:29:50<33:55:17,  7.10s/it]
                                                           
{'loss': 0.6077, 'learning_rate': 0.00035044192377851663, 'epoch': 4.65}

 39%|███▊      | 10877/28080 [21:29:50<33:55:17,  7.10s/it]
 39%|███▊      | 10878/28080 [21:29:57<33:56:56,  7.10s/it]
                                                           
{'loss': 0.6189, 'learning_rate': 0.0003504155170529252, 'epoch': 4.65}

 39%|███▊      | 10878/28080 [21:29:57<33:56:56,  7.10s/it]
 39%|███▊      | 10879/28080 [21:30:04<33:57:37,  7.11s/it]
                                                           
{'loss': 0.6048, 'learning_rate': 0.000350389108991409, 'epoch': 4.65}

 39%|███▊      | 10879/28080 [21:30:04<33:57:37,  7.11s/it]
 39%|███▊      | 10880/28080 [21:30:11<33:57:20,  7.11s/it]
                                                           
{'loss': 0.6306, 'learning_rate': 0.0003503626995943191, 'epoch': 4.65}

 39%|███▊      | 10880/28080 [21:30:11<33:57:20,  7.11s/it]
 39%|███▉      | 10881/28080 [21:30:18<33:58:15,  7.11s/it]
                                                           
{'loss': 0.6369, 'learning_rate': 0.00035033628886200715, 'epoch': 4.65}

 39%|███▉      | 10881/28080 [21:30:18<33:58:15,  7.11s/it]
 39%|███▉      | 10882/28080 [21:30:25<33:45:43,  7.07s/it]
                                                           
{'loss': 0.6241, 'learning_rate': 0.0003503098767948243, 'epoch': 4.65}

 39%|███▉      | 10882/28080 [21:30:25<33:45:43,  7.07s/it]
 39%|███▉      | 10883/28080 [21:30:32<33:49:07,  7.08s/it]
                                                           
{'loss': 0.6364, 'learning_rate': 0.00035028346339312206, 'epoch': 4.65}

 39%|███▉      | 10883/28080 [21:30:32<33:49:07,  7.08s/it]
 39%|███▉      | 10884/28080 [21:30:40<33:58:50,  7.11s/it]
                                                           
{'loss': 0.6251, 'learning_rate': 0.0003502570486572518, 'epoch': 4.65}

 39%|███▉      | 10884/28080 [21:30:40<33:58:50,  7.11s/it]
 39%|███▉      | 10885/28080 [21:30:47<33:58:48,  7.11s/it]
                                                           
{'loss': 0.6067, 'learning_rate': 0.00035023063258756494, 'epoch': 4.65}

 39%|███▉      | 10885/28080 [21:30:47<33:58:48,  7.11s/it]
 39%|███▉      | 10886/28080 [21:30:54<33:52:09,  7.09s/it]
                                                           
{'loss': 0.6384, 'learning_rate': 0.000350204215184413, 'epoch': 4.65}

 39%|███▉      | 10886/28080 [21:30:54<33:52:09,  7.09s/it]
 39%|███▉      | 10887/28080 [21:31:01<34:01:19,  7.12s/it]
                                                           
{'loss': 0.6158, 'learning_rate': 0.00035017779644814725, 'epoch': 4.65}

 39%|███▉      | 10887/28080 [21:31:01<34:01:19,  7.12s/it]
 39%|███▉      | 10888/28080 [21:31:08<34:08:14,  7.15s/it]
                                                           
{'loss': 0.6236, 'learning_rate': 0.0003501513763791193, 'epoch': 4.65}

 39%|███▉      | 10888/28080 [21:31:08<34:08:14,  7.15s/it]
 39%|███▉      | 10889/28080 [21:31:15<34:02:41,  7.13s/it]
                                                           
{'loss': 0.6192, 'learning_rate': 0.00035012495497768054, 'epoch': 4.65}

 39%|███▉      | 10889/28080 [21:31:15<34:02:41,  7.13s/it]
 39%|███▉      | 10890/28080 [21:31:22<34:10:37,  7.16s/it]
                                                           
{'loss': 0.6187, 'learning_rate': 0.0003500985322441826, 'epoch': 4.65}

 39%|███▉      | 10890/28080 [21:31:22<34:10:37,  7.16s/it]
 39%|███▉      | 10891/28080 [21:31:29<33:58:28,  7.12s/it]
                                                           
{'loss': 0.6348, 'learning_rate': 0.00035007210817897694, 'epoch': 4.65}

 39%|███▉      | 10891/28080 [21:31:29<33:58:28,  7.12s/it]
 39%|███▉      | 10892/28080 [21:31:36<33:41:16,  7.06s/it]
                                                           
{'loss': 0.6571, 'learning_rate': 0.00035004568278241524, 'epoch': 4.65}

 39%|███▉      | 10892/28080 [21:31:36<33:41:16,  7.06s/it]
 39%|███▉      | 10893/28080 [21:31:44<33:49:23,  7.08s/it]
                                                           
{'loss': 0.6244, 'learning_rate': 0.00035001925605484874, 'epoch': 4.65}

 39%|███▉      | 10893/28080 [21:31:44<33:49:23,  7.08s/it]
 39%|███▉      | 10894/28080 [21:31:51<33:49:46,  7.09s/it]
                                                           
{'loss': 0.6421, 'learning_rate': 0.00034999282799662936, 'epoch': 4.65}

 39%|███▉      | 10894/28080 [21:31:51<33:49:46,  7.09s/it]
 39%|███▉      | 10895/28080 [21:31:58<33:56:49,  7.11s/it]
                                                           
{'loss': 0.6193, 'learning_rate': 0.00034996639860810855, 'epoch': 4.65}

 39%|███▉      | 10895/28080 [21:31:58<33:56:49,  7.11s/it]
 39%|███▉      | 10896/28080 [21:32:05<34:05:36,  7.14s/it]
                                                           
{'loss': 0.6153, 'learning_rate': 0.0003499399678896379, 'epoch': 4.65}

 39%|███▉      | 10896/28080 [21:32:05<34:05:36,  7.14s/it]
 39%|███▉      | 10897/28080 [21:32:12<34:01:02,  7.13s/it]
                                                           
{'loss': 0.6284, 'learning_rate': 0.00034991353584156907, 'epoch': 4.66}

 39%|███▉      | 10897/28080 [21:32:12<34:01:02,  7.13s/it]
 39%|███▉      | 10898/28080 [21:32:19<34:02:53,  7.13s/it]
                                                           
{'loss': 0.6336, 'learning_rate': 0.0003498871024642538, 'epoch': 4.66}

 39%|███▉      | 10898/28080 [21:32:19<34:02:53,  7.13s/it]
 39%|███▉      | 10899/28080 [21:32:26<33:53:35,  7.10s/it]
                                                           
{'loss': 0.6428, 'learning_rate': 0.00034986066775804354, 'epoch': 4.66}

 39%|███▉      | 10899/28080 [21:32:26<33:53:35,  7.10s/it]
 39%|███▉      | 10900/28080 [21:32:33<33:57:15,  7.11s/it]
                                                           
{'loss': 0.6211, 'learning_rate': 0.0003498342317232902, 'epoch': 4.66}

 39%|███▉      | 10900/28080 [21:32:33<33:57:15,  7.11s/it]
 39%|███▉      | 10901/28080 [21:32:41<34:00:41,  7.13s/it]
                                                           
{'loss': 0.6233, 'learning_rate': 0.0003498077943603454, 'epoch': 4.66}

 39%|███▉      | 10901/28080 [21:32:41<34:00:41,  7.13s/it]
 39%|███▉      | 10902/28080 [21:32:48<33:59:37,  7.12s/it]
                                                           
{'loss': 0.637, 'learning_rate': 0.0003497813556695608, 'epoch': 4.66}

 39%|███▉      | 10902/28080 [21:32:48<33:59:37,  7.12s/it]
 39%|███▉      | 10903/28080 [21:32:55<33:59:54,  7.13s/it]
                                                           
{'loss': 0.6183, 'learning_rate': 0.0003497549156512883, 'epoch': 4.66}

 39%|███▉      | 10903/28080 [21:32:55<33:59:54,  7.13s/it]
 39%|███▉      | 10904/28080 [21:33:02<34:06:37,  7.15s/it]
                                                           
{'loss': 0.6316, 'learning_rate': 0.0003497284743058795, 'epoch': 4.66}

 39%|███▉      | 10904/28080 [21:33:02<34:06:37,  7.15s/it]
 39%|███▉      | 10905/28080 [21:33:09<34:03:38,  7.14s/it]
                                                           
{'loss': 0.6195, 'learning_rate': 0.0003497020316336863, 'epoch': 4.66}

 39%|███▉      | 10905/28080 [21:33:09<34:03:38,  7.14s/it]
 39%|███▉      | 10906/28080 [21:33:16<34:08:02,  7.16s/it]
                                                           
{'loss': 0.608, 'learning_rate': 0.0003496755876350604, 'epoch': 4.66}

 39%|███▉      | 10906/28080 [21:33:16<34:08:02,  7.16s/it]
 39%|███▉      | 10907/28080 [21:33:23<34:07:46,  7.15s/it]
                                                           
{'loss': 0.6207, 'learning_rate': 0.0003496491423103535, 'epoch': 4.66}

 39%|███▉      | 10907/28080 [21:33:23<34:07:46,  7.15s/it]
 39%|███▉      | 10908/28080 [21:33:30<33:53:10,  7.10s/it]
                                                           
{'loss': 0.6344, 'learning_rate': 0.0003496226956599177, 'epoch': 4.66}

 39%|███▉      | 10908/28080 [21:33:30<33:53:10,  7.10s/it]
 39%|███▉      | 10909/28080 [21:33:37<33:44:50,  7.08s/it]
                                                           
{'loss': 0.6212, 'learning_rate': 0.0003495962476841047, 'epoch': 4.66}

 39%|███▉      | 10909/28080 [21:33:37<33:44:50,  7.08s/it]
 39%|███▉      | 10910/28080 [21:33:45<33:49:42,  7.09s/it]
                                                           
{'loss': 0.6131, 'learning_rate': 0.00034956979838326633, 'epoch': 4.66}

 39%|███▉      | 10910/28080 [21:33:45<33:49:42,  7.09s/it]
 39%|███▉      | 10911/28080 [21:33:52<33:57:03,  7.12s/it]
                                                           
{'loss': 0.6172, 'learning_rate': 0.0003495433477577545, 'epoch': 4.66}

 39%|███▉      | 10911/28080 [21:33:52<33:57:03,  7.12s/it]
 39%|███▉      | 10912/28080 [21:33:59<33:57:12,  7.12s/it]
                                                           
{'loss': 0.6362, 'learning_rate': 0.00034951689580792124, 'epoch': 4.66}

 39%|███▉      | 10912/28080 [21:33:59<33:57:12,  7.12s/it]
 39%|███▉      | 10913/28080 [21:34:06<33:55:56,  7.12s/it]
                                                           
{'loss': 0.6115, 'learning_rate': 0.0003494904425341183, 'epoch': 4.66}

 39%|███▉      | 10913/28080 [21:34:06<33:55:56,  7.12s/it]
 39%|███▉      | 10914/28080 [21:34:13<33:54:10,  7.11s/it]
                                                           
{'loss': 0.6248, 'learning_rate': 0.00034946398793669756, 'epoch': 4.66}

 39%|███▉      | 10914/28080 [21:34:13<33:54:10,  7.11s/it]
 39%|███▉      | 10915/28080 [21:34:20<33:52:07,  7.10s/it]
                                                           
{'loss': 0.623, 'learning_rate': 0.00034943753201601113, 'epoch': 4.66}

 39%|███▉      | 10915/28080 [21:34:20<33:52:07,  7.10s/it]
 39%|███▉      | 10916/28080 [21:34:27<33:45:08,  7.08s/it]
                                                           
{'loss': 0.6205, 'learning_rate': 0.00034941107477241097, 'epoch': 4.66}

 39%|███▉      | 10916/28080 [21:34:27<33:45:08,  7.08s/it]
 39%|███▉      | 10917/28080 [21:34:34<33:51:47,  7.10s/it]
                                                           
{'loss': 0.5958, 'learning_rate': 0.00034938461620624895, 'epoch': 4.66}

 39%|███▉      | 10917/28080 [21:34:34<33:51:47,  7.10s/it]
 39%|███▉      | 10918/28080 [21:34:41<33:47:28,  7.09s/it]
                                                           
{'loss': 0.6003, 'learning_rate': 0.00034935815631787723, 'epoch': 4.66}

 39%|███▉      | 10918/28080 [21:34:41<33:47:28,  7.09s/it]
 39%|███▉      | 10919/28080 [21:34:48<33:46:42,  7.09s/it]
                                                           
{'loss': 0.616, 'learning_rate': 0.00034933169510764764, 'epoch': 4.66}

 39%|███▉      | 10919/28080 [21:34:49<33:46:42,  7.09s/it]
 39%|███▉      | 10920/28080 [21:34:56<33:50:47,  7.10s/it]
                                                           
{'loss': 0.6162, 'learning_rate': 0.0003493052325759124, 'epoch': 4.66}

 39%|███▉      | 10920/28080 [21:34:56<33:50:47,  7.10s/it]
 39%|███▉      | 10921/28080 [21:35:03<33:53:11,  7.11s/it]
                                                           
{'loss': 0.6299, 'learning_rate': 0.00034927876872302345, 'epoch': 4.67}

 39%|███▉      | 10921/28080 [21:35:03<33:53:11,  7.11s/it]
 39%|███▉      | 10922/28080 [21:35:10<33:59:12,  7.13s/it]
                                                           
{'loss': 0.618, 'learning_rate': 0.0003492523035493329, 'epoch': 4.67}

 39%|███▉      | 10922/28080 [21:35:10<33:59:12,  7.13s/it]
 39%|███▉      | 10923/28080 [21:35:17<33:52:24,  7.11s/it]
                                                           
{'loss': 0.6352, 'learning_rate': 0.00034922583705519284, 'epoch': 4.67}

 39%|███▉      | 10923/28080 [21:35:17<33:52:24,  7.11s/it]
 39%|███▉      | 10924/28080 [21:35:24<33:48:14,  7.09s/it]
                                                           
{'loss': 0.6179, 'learning_rate': 0.00034919936924095537, 'epoch': 4.67}

 39%|███▉      | 10924/28080 [21:35:24<33:48:14,  7.09s/it]
 39%|███▉      | 10925/28080 [21:35:31<33:46:57,  7.09s/it]
                                                           
{'loss': 0.6351, 'learning_rate': 0.00034917290010697265, 'epoch': 4.67}

 39%|███▉      | 10925/28080 [21:35:31<33:46:57,  7.09s/it]
 39%|███▉      | 10926/28080 [21:35:38<33:47:31,  7.09s/it]
                                                           
{'loss': 0.6129, 'learning_rate': 0.00034914642965359677, 'epoch': 4.67}

 39%|███▉      | 10926/28080 [21:35:38<33:47:31,  7.09s/it]
 39%|███▉      | 10927/28080 [21:35:45<33:53:00,  7.11s/it]
                                                           
{'loss': 0.6163, 'learning_rate': 0.00034911995788118003, 'epoch': 4.67}

 39%|███▉      | 10927/28080 [21:35:45<33:53:00,  7.11s/it]
 39%|███▉      | 10928/28080 [21:35:53<33:55:24,  7.12s/it]
                                                           
{'loss': 0.6168, 'learning_rate': 0.00034909348479007443, 'epoch': 4.67}

 39%|███▉      | 10928/28080 [21:35:53<33:55:24,  7.12s/it]
 39%|███▉      | 10929/28080 [21:36:00<33:53:17,  7.11s/it]
                                                           
{'loss': 0.6478, 'learning_rate': 0.0003490670103806323, 'epoch': 4.67}

 39%|███▉      | 10929/28080 [21:36:00<33:53:17,  7.11s/it]
 39%|███▉      | 10930/28080 [21:36:07<33:49:13,  7.10s/it]
                                                           
{'loss': 0.6503, 'learning_rate': 0.00034904053465320567, 'epoch': 4.67}

 39%|███▉      | 10930/28080 [21:36:07<33:49:13,  7.10s/it]
 39%|███▉      | 10931/28080 [21:36:14<33:54:21,  7.12s/it]
                                                           
{'loss': 0.6308, 'learning_rate': 0.00034901405760814696, 'epoch': 4.67}

 39%|███▉      | 10931/28080 [21:36:14<33:54:21,  7.12s/it]
 39%|███▉      | 10932/28080 [21:36:21<33:53:25,  7.11s/it]
                                                           
{'loss': 0.6201, 'learning_rate': 0.0003489875792458084, 'epoch': 4.67}

 39%|███▉      | 10932/28080 [21:36:21<33:53:25,  7.11s/it]
 39%|███▉      | 10933/28080 [21:36:28<33:46:23,  7.09s/it]
                                                           
{'loss': 0.6193, 'learning_rate': 0.0003489610995665422, 'epoch': 4.67}

 39%|███▉      | 10933/28080 [21:36:28<33:46:23,  7.09s/it]
 39%|███▉      | 10934/28080 [21:36:35<33:44:15,  7.08s/it]
                                                           
{'loss': 0.6162, 'learning_rate': 0.0003489346185707007, 'epoch': 4.67}

 39%|███▉      | 10934/28080 [21:36:35<33:44:15,  7.08s/it]
 39%|███▉      | 10935/28080 [21:36:42<33:41:16,  7.07s/it]
                                                           
{'loss': 0.6395, 'learning_rate': 0.0003489081362586361, 'epoch': 4.67}

 39%|███▉      | 10935/28080 [21:36:42<33:41:16,  7.07s/it]
 39%|███▉      | 10936/28080 [21:36:49<33:50:37,  7.11s/it]
                                                           
{'loss': 0.6332, 'learning_rate': 0.00034888165263070083, 'epoch': 4.67}

 39%|███▉      | 10936/28080 [21:36:49<33:50:37,  7.11s/it]
 39%|███▉      | 10937/28080 [21:36:56<33:48:38,  7.10s/it]
                                                           
{'loss': 0.6197, 'learning_rate': 0.0003488551676872472, 'epoch': 4.67}

 39%|███▉      | 10937/28080 [21:36:56<33:48:38,  7.10s/it]
 39%|███▉      | 10938/28080 [21:37:04<33:50:56,  7.11s/it]
                                                           
{'loss': 0.619, 'learning_rate': 0.0003488286814286275, 'epoch': 4.67}

 39%|███▉      | 10938/28080 [21:37:04<33:50:56,  7.11s/it]
 39%|███▉      | 10939/28080 [21:37:11<33:54:56,  7.12s/it]
                                                           
{'loss': 0.5933, 'learning_rate': 0.0003488021938551941, 'epoch': 4.67}

 39%|███▉      | 10939/28080 [21:37:11<33:54:56,  7.12s/it]
 39%|███▉      | 10940/28080 [21:37:18<34:02:09,  7.15s/it]
                                                           
{'loss': 0.6232, 'learning_rate': 0.0003487757049672995, 'epoch': 4.67}

 39%|███▉      | 10940/28080 [21:37:18<34:02:09,  7.15s/it]
 39%|███▉      | 10941/28080 [21:37:25<33:55:28,  7.13s/it]
                                                           
{'loss': 0.6342, 'learning_rate': 0.0003487492147652961, 'epoch': 4.67}

 39%|███▉      | 10941/28080 [21:37:25<33:55:28,  7.13s/it]
 39%|███▉      | 10942/28080 [21:37:32<33:48:00,  7.10s/it]
                                                           
{'loss': 0.608, 'learning_rate': 0.00034872272324953626, 'epoch': 4.67}

 39%|███▉      | 10942/28080 [21:37:32<33:48:00,  7.10s/it]
 39%|███▉      | 10943/28080 [21:37:39<33:45:56,  7.09s/it]
                                                           
{'loss': 0.6143, 'learning_rate': 0.00034869623042037235, 'epoch': 4.67}

 39%|███▉      | 10943/28080 [21:37:39<33:45:56,  7.09s/it]
 39%|███▉      | 10944/28080 [21:37:46<33:46:12,  7.09s/it]
                                                           
{'loss': 0.6084, 'learning_rate': 0.000348669736278157, 'epoch': 4.68}

 39%|███▉      | 10944/28080 [21:37:46<33:46:12,  7.09s/it]
 39%|███▉      | 10945/28080 [21:37:53<33:50:26,  7.11s/it]
                                                           
{'loss': 0.6186, 'learning_rate': 0.0003486432408232425, 'epoch': 4.68}

 39%|███▉      | 10945/28080 [21:37:53<33:50:26,  7.11s/it]
 39%|███▉      | 10946/28080 [21:38:00<33:54:03,  7.12s/it]
                                                           
{'loss': 0.6294, 'learning_rate': 0.00034861674405598154, 'epoch': 4.68}

 39%|███▉      | 10946/28080 [21:38:00<33:54:03,  7.12s/it]
 39%|███▉      | 10947/28080 [21:38:08<33:58:41,  7.14s/it]
                                                           
{'loss': 0.6349, 'learning_rate': 0.00034859024597672653, 'epoch': 4.68}

 39%|███▉      | 10947/28080 [21:38:08<33:58:41,  7.14s/it]
 39%|███▉      | 10948/28080 [21:38:15<33:55:32,  7.13s/it]
                                                           
{'loss': 0.6134, 'learning_rate': 0.0003485637465858299, 'epoch': 4.68}

 39%|███▉      | 10948/28080 [21:38:15<33:55:32,  7.13s/it]
 39%|███▉      | 10949/28080 [21:38:22<33:51:38,  7.12s/it]
                                                           
{'loss': 0.6572, 'learning_rate': 0.00034853724588364445, 'epoch': 4.68}

 39%|███▉      | 10949/28080 [21:38:22<33:51:38,  7.12s/it]
 39%|███▉      | 10950/28080 [21:38:29<33:49:51,  7.11s/it]
                                                           
{'loss': 0.6587, 'learning_rate': 0.0003485107438705225, 'epoch': 4.68}

 39%|███▉      | 10950/28080 [21:38:29<33:49:51,  7.11s/it]
 39%|███▉      | 10951/28080 [21:38:36<33:41:52,  7.08s/it]
                                                           
{'loss': 0.6349, 'learning_rate': 0.00034848424054681677, 'epoch': 4.68}

 39%|███▉      | 10951/28080 [21:38:36<33:41:52,  7.08s/it]
 39%|███▉      | 10952/28080 [21:38:43<33:48:11,  7.10s/it]
                                                           
{'loss': 0.6199, 'learning_rate': 0.0003484577359128798, 'epoch': 4.68}

 39%|███▉      | 10952/28080 [21:38:43<33:48:11,  7.10s/it]
 39%|███▉      | 10953/28080 [21:38:50<33:47:31,  7.10s/it]
                                                           
{'loss': 0.6326, 'learning_rate': 0.0003484312299690643, 'epoch': 4.68}

 39%|███▉      | 10953/28080 [21:38:50<33:47:31,  7.10s/it]
 39%|███▉      | 10954/28080 [21:38:57<33:49:50,  7.11s/it]
                                                           
{'loss': 0.6346, 'learning_rate': 0.00034840472271572274, 'epoch': 4.68}

 39%|███▉      | 10954/28080 [21:38:57<33:49:50,  7.11s/it]
 39%|███▉      | 10955/28080 [21:39:04<33:46:51,  7.10s/it]
                                                           
{'loss': 0.6358, 'learning_rate': 0.00034837821415320785, 'epoch': 4.68}

 39%|███▉      | 10955/28080 [21:39:04<33:46:51,  7.10s/it]
 39%|███▉      | 10956/28080 [21:39:12<33:52:03,  7.12s/it]
                                                           
{'loss': 0.6419, 'learning_rate': 0.00034835170428187235, 'epoch': 4.68}

 39%|███▉      | 10956/28080 [21:39:12<33:52:03,  7.12s/it]
 39%|███▉      | 10957/28080 [21:39:19<33:57:56,  7.14s/it]
                                                           
{'loss': 0.6304, 'learning_rate': 0.0003483251931020689, 'epoch': 4.68}

 39%|███▉      | 10957/28080 [21:39:19<33:57:56,  7.14s/it]
 39%|███▉      | 10958/28080 [21:39:26<33:54:09,  7.13s/it]
                                                           
{'loss': 0.6205, 'learning_rate': 0.0003482986806141502, 'epoch': 4.68}

 39%|███▉      | 10958/28080 [21:39:26<33:54:09,  7.13s/it]
 39%|███▉      | 10959/28080 [21:39:33<33:48:33,  7.11s/it]
                                                           
{'loss': 0.6372, 'learning_rate': 0.000348272166818469, 'epoch': 4.68}

 39%|███▉      | 10959/28080 [21:39:33<33:48:33,  7.11s/it]
 39%|███▉      | 10960/28080 [21:39:40<33:47:49,  7.11s/it]
                                                           
{'loss': 0.628, 'learning_rate': 0.0003482456517153779, 'epoch': 4.68}

 39%|███▉      | 10960/28080 [21:39:40<33:47:49,  7.11s/it]
 39%|███▉      | 10961/28080 [21:39:47<33:43:11,  7.09s/it]
                                                           
{'loss': 0.6281, 'learning_rate': 0.0003482191353052298, 'epoch': 4.68}

 39%|███▉      | 10961/28080 [21:39:47<33:43:11,  7.09s/it]
 39%|███▉      | 10962/28080 [21:39:54<33:37:23,  7.07s/it]
                                                           
{'loss': 0.6296, 'learning_rate': 0.0003481926175883774, 'epoch': 4.68}

 39%|███▉      | 10962/28080 [21:39:54<33:37:23,  7.07s/it]
 39%|███▉      | 10963/28080 [21:40:01<33:34:42,  7.06s/it]
                                                           
{'loss': 0.6303, 'learning_rate': 0.0003481660985651736, 'epoch': 4.68}

 39%|███▉      | 10963/28080 [21:40:01<33:34:42,  7.06s/it]
 39%|███▉      | 10964/28080 [21:40:08<33:41:29,  7.09s/it]
                                                           
{'loss': 0.6522, 'learning_rate': 0.00034813957823597106, 'epoch': 4.68}

 39%|███▉      | 10964/28080 [21:40:08<33:41:29,  7.09s/it]
 39%|███▉      | 10965/28080 [21:40:15<33:45:13,  7.10s/it]
                                                           
{'loss': 0.6164, 'learning_rate': 0.00034811305660112276, 'epoch': 4.68}

 39%|███▉      | 10965/28080 [21:40:15<33:45:13,  7.10s/it]
 39%|███▉      | 10966/28080 [21:40:22<33:36:38,  7.07s/it]
                                                           
{'loss': 0.634, 'learning_rate': 0.0003480865336609814, 'epoch': 4.68}

 39%|███▉      | 10966/28080 [21:40:22<33:36:38,  7.07s/it]
 39%|███▉      | 10967/28080 [21:40:30<33:41:31,  7.09s/it]
                                                           
{'loss': 0.6423, 'learning_rate': 0.00034806000941589994, 'epoch': 4.69}

 39%|███▉      | 10967/28080 [21:40:30<33:41:31,  7.09s/it]
 39%|███▉      | 10968/28080 [21:40:37<33:36:06,  7.07s/it]
                                                           
{'loss': 0.6166, 'learning_rate': 0.00034803348386623124, 'epoch': 4.69}

 39%|███▉      | 10968/28080 [21:40:37<33:36:06,  7.07s/it]
 39%|███▉      | 10969/28080 [21:40:44<33:42:28,  7.09s/it]
                                                           
{'loss': 0.6002, 'learning_rate': 0.0003480069570123281, 'epoch': 4.69}

 39%|███▉      | 10969/28080 [21:40:44<33:42:28,  7.09s/it]
 39%|███▉      | 10970/28080 [21:40:51<33:38:27,  7.08s/it]
                                                           
{'loss': 0.6229, 'learning_rate': 0.0003479804288545435, 'epoch': 4.69}

 39%|███▉      | 10970/28080 [21:40:51<33:38:27,  7.08s/it]
 39%|███▉      | 10971/28080 [21:40:58<33:58:28,  7.15s/it]
                                                           
{'loss': 0.6194, 'learning_rate': 0.00034795389939323043, 'epoch': 4.69}

 39%|███▉      | 10971/28080 [21:40:58<33:58:28,  7.15s/it]
 39%|███▉      | 10972/28080 [21:41:05<33:55:01,  7.14s/it]
                                                           
{'loss': 0.6175, 'learning_rate': 0.00034792736862874167, 'epoch': 4.69}

 39%|███▉      | 10972/28080 [21:41:05<33:55:01,  7.14s/it]
 39%|███▉      | 10973/28080 [21:41:12<33:48:27,  7.11s/it]
                                                           
{'loss': 0.6297, 'learning_rate': 0.0003479008365614305, 'epoch': 4.69}

 39%|███▉      | 10973/28080 [21:41:12<33:48:27,  7.11s/it]
 39%|███▉      | 10974/28080 [21:41:19<33:42:52,  7.10s/it]
                                                           
{'loss': 0.6442, 'learning_rate': 0.0003478743031916495, 'epoch': 4.69}

 39%|███▉      | 10974/28080 [21:41:19<33:42:52,  7.10s/it]
 39%|███▉      | 10975/28080 [21:41:26<33:40:07,  7.09s/it]
                                                           
{'loss': 0.6174, 'learning_rate': 0.000347847768519752, 'epoch': 4.69}

 39%|███▉      | 10975/28080 [21:41:26<33:40:07,  7.09s/it]
 39%|███▉      | 10976/28080 [21:41:33<33:41:12,  7.09s/it]
                                                           
{'loss': 0.6275, 'learning_rate': 0.0003478212325460908, 'epoch': 4.69}

 39%|███▉      | 10976/28080 [21:41:33<33:41:12,  7.09s/it]
 39%|███▉      | 10977/28080 [21:41:41<33:45:51,  7.11s/it]
                                                           
{'loss': 0.6247, 'learning_rate': 0.00034779469527101905, 'epoch': 4.69}

 39%|███▉      | 10977/28080 [21:41:41<33:45:51,  7.11s/it]
 39%|███▉      | 10978/28080 [21:41:48<33:37:32,  7.08s/it]
                                                           
{'loss': 0.6252, 'learning_rate': 0.0003477681566948897, 'epoch': 4.69}

 39%|███▉      | 10978/28080 [21:41:48<33:37:32,  7.08s/it]
 39%|███▉      | 10979/28080 [21:41:55<33:36:48,  7.08s/it]
                                                           
{'loss': 0.6207, 'learning_rate': 0.00034774161681805593, 'epoch': 4.69}

 39%|███▉      | 10979/28080 [21:41:55<33:36:48,  7.08s/it]
 39%|███▉      | 10980/28080 [21:42:02<33:30:21,  7.05s/it]
                                                           
{'loss': 0.6217, 'learning_rate': 0.00034771507564087086, 'epoch': 4.69}

 39%|███▉      | 10980/28080 [21:42:02<33:30:21,  7.05s/it]
 39%|███▉      | 10981/28080 [21:42:09<33:29:43,  7.05s/it]
                                                           
{'loss': 0.6157, 'learning_rate': 0.00034768853316368743, 'epoch': 4.69}

 39%|███▉      | 10981/28080 [21:42:09<33:29:43,  7.05s/it]
 39%|███▉      | 10982/28080 [21:42:16<33:33:43,  7.07s/it]
                                                           
{'loss': 0.6134, 'learning_rate': 0.0003476619893868589, 'epoch': 4.69}

 39%|███▉      | 10982/28080 [21:42:16<33:33:43,  7.07s/it]
 39%|███▉      | 10983/28080 [21:42:23<33:36:38,  7.08s/it]
                                                           
{'loss': 0.6347, 'learning_rate': 0.0003476354443107383, 'epoch': 4.69}

 39%|███▉      | 10983/28080 [21:42:23<33:36:38,  7.08s/it]
 39%|███▉      | 10984/28080 [21:42:30<33:38:18,  7.08s/it]
                                                           
{'loss': 0.6269, 'learning_rate': 0.0003476088979356789, 'epoch': 4.69}

 39%|███▉      | 10984/28080 [21:42:30<33:38:18,  7.08s/it]
 39%|███▉      | 10985/28080 [21:42:37<33:37:56,  7.08s/it]
                                                           
{'loss': 0.6305, 'learning_rate': 0.00034758235026203377, 'epoch': 4.69}

 39%|███▉      | 10985/28080 [21:42:37<33:37:56,  7.08s/it]
 39%|███▉      | 10986/28080 [21:42:44<33:39:59,  7.09s/it]
                                                           
{'loss': 0.6488, 'learning_rate': 0.0003475558012901561, 'epoch': 4.69}

 39%|███▉      | 10986/28080 [21:42:44<33:39:59,  7.09s/it]
 39%|███▉      | 10987/28080 [21:42:51<33:40:05,  7.09s/it]
                                                           
{'loss': 0.632, 'learning_rate': 0.00034752925102039925, 'epoch': 4.69}

 39%|███▉      | 10987/28080 [21:42:51<33:40:05,  7.09s/it]
 39%|███▉      | 10988/28080 [21:42:58<33:35:49,  7.08s/it]
                                                           
{'loss': 0.6263, 'learning_rate': 0.00034750269945311627, 'epoch': 4.69}

 39%|███▉      | 10988/28080 [21:42:58<33:35:49,  7.08s/it]
 39%|███▉      | 10989/28080 [21:43:06<33:45:16,  7.11s/it]
                                                           
{'loss': 0.6183, 'learning_rate': 0.00034747614658866047, 'epoch': 4.69}

 39%|███▉      | 10989/28080 [21:43:06<33:45:16,  7.11s/it]
 39%|███▉      | 10990/28080 [21:43:13<33:45:25,  7.11s/it]
                                                           
{'loss': 0.6232, 'learning_rate': 0.00034744959242738504, 'epoch': 4.69}

 39%|███▉      | 10990/28080 [21:43:13<33:45:25,  7.11s/it]
 39%|███▉      | 10991/28080 [21:43:20<33:44:43,  7.11s/it]
                                                           
{'loss': 0.6455, 'learning_rate': 0.0003474230369696434, 'epoch': 4.7}

 39%|███▉      | 10991/28080 [21:43:20<33:44:43,  7.11s/it]
 39%|███▉      | 10992/28080 [21:43:27<33:29:58,  7.06s/it]
                                                           
{'loss': 0.6297, 'learning_rate': 0.0003473964802157887, 'epoch': 4.7}

 39%|███▉      | 10992/28080 [21:43:27<33:29:58,  7.06s/it]
 39%|███▉      | 10993/28080 [21:43:34<33:43:56,  7.11s/it]
                                                           
{'loss': 0.6144, 'learning_rate': 0.00034736992216617436, 'epoch': 4.7}

 39%|███▉      | 10993/28080 [21:43:34<33:43:56,  7.11s/it]
 39%|███▉      | 10994/28080 [21:43:41<33:40:30,  7.10s/it]
                                                           
{'loss': 0.6351, 'learning_rate': 0.00034734336282115367, 'epoch': 4.7}

 39%|███▉      | 10994/28080 [21:43:41<33:40:30,  7.10s/it]
 39%|███▉      | 10995/28080 [21:43:48<33:43:49,  7.11s/it]
                                                           
{'loss': 0.6151, 'learning_rate': 0.0003473168021810799, 'epoch': 4.7}

 39%|███▉      | 10995/28080 [21:43:48<33:43:49,  7.11s/it]
 39%|███▉      | 10996/28080 [21:43:55<33:39:18,  7.09s/it]
                                                           
{'loss': 0.6622, 'learning_rate': 0.0003472902402463065, 'epoch': 4.7}

 39%|███▉      | 10996/28080 [21:43:55<33:39:18,  7.09s/it]
 39%|███▉      | 10997/28080 [21:44:02<33:35:33,  7.08s/it]
                                                           
{'loss': 0.6283, 'learning_rate': 0.00034726367701718683, 'epoch': 4.7}

 39%|███▉      | 10997/28080 [21:44:02<33:35:33,  7.08s/it]
 39%|███▉      | 10998/28080 [21:44:09<33:30:09,  7.06s/it]
                                                           
{'loss': 0.6205, 'learning_rate': 0.0003472371124940742, 'epoch': 4.7}

 39%|███▉      | 10998/28080 [21:44:09<33:30:09,  7.06s/it]
 39%|███▉      | 10999/28080 [21:44:16<33:34:18,  7.08s/it]
                                                           
{'loss': 0.6094, 'learning_rate': 0.0003472105466773222, 'epoch': 4.7}

 39%|███▉      | 10999/28080 [21:44:16<33:34:18,  7.08s/it]
 39%|███▉      | 11000/28080 [21:44:23<33:29:44,  7.06s/it]
                                                           
{'loss': 0.6272, 'learning_rate': 0.0003471839795672841, 'epoch': 4.7}

 39%|███▉      | 11000/28080 [21:44:23<33:29:44,  7.06s/it]
 39%|███▉      | 11001/28080 [21:44:30<33:27:00,  7.05s/it]
                                                           
{'loss': 0.6127, 'learning_rate': 0.0003471574111643135, 'epoch': 4.7}

 39%|███▉      | 11001/28080 [21:44:30<33:27:00,  7.05s/it]
 39%|███▉      | 11002/28080 [21:44:38<33:32:30,  7.07s/it]
                                                           
{'loss': 0.6303, 'learning_rate': 0.00034713084146876366, 'epoch': 4.7}

 39%|███▉      | 11002/28080 [21:44:38<33:32:30,  7.07s/it]
 39%|███▉      | 11003/28080 [21:44:45<33:35:22,  7.08s/it]
                                                           
{'loss': 0.65, 'learning_rate': 0.0003471042704809882, 'epoch': 4.7}

 39%|███▉      | 11003/28080 [21:44:45<33:35:22,  7.08s/it]
 39%|███▉      | 11004/28080 [21:44:52<33:41:51,  7.10s/it]
                                                           
{'loss': 0.6222, 'learning_rate': 0.00034707769820134065, 'epoch': 4.7}

 39%|███▉      | 11004/28080 [21:44:52<33:41:51,  7.10s/it]
 39%|███▉      | 11005/28080 [21:44:59<33:38:00,  7.09s/it]
                                                           
{'loss': 0.6367, 'learning_rate': 0.0003470511246301745, 'epoch': 4.7}

 39%|███▉      | 11005/28080 [21:44:59<33:38:00,  7.09s/it]
 39%|███▉      | 11006/28080 [21:45:06<33:41:10,  7.10s/it]
                                                           
{'loss': 0.6096, 'learning_rate': 0.0003470245497678432, 'epoch': 4.7}

 39%|███▉      | 11006/28080 [21:45:06<33:41:10,  7.10s/it]
 39%|███▉      | 11007/28080 [21:45:13<33:44:42,  7.12s/it]
                                                           
{'loss': 0.6406, 'learning_rate': 0.00034699797361470035, 'epoch': 4.7}

 39%|███▉      | 11007/28080 [21:45:13<33:44:42,  7.12s/it]
 39%|███▉      | 11008/28080 [21:45:20<33:42:17,  7.11s/it]
                                                           
{'loss': 0.6346, 'learning_rate': 0.00034697139617109957, 'epoch': 4.7}

 39%|███▉      | 11008/28080 [21:45:20<33:42:17,  7.11s/it]
 39%|███▉      | 11009/28080 [21:45:27<33:48:30,  7.13s/it]
                                                           
{'loss': 0.607, 'learning_rate': 0.0003469448174373944, 'epoch': 4.7}

 39%|███▉      | 11009/28080 [21:45:27<33:48:30,  7.13s/it]
 39%|███▉      | 11010/28080 [21:45:35<33:59:02,  7.17s/it]
                                                           
{'loss': 0.6272, 'learning_rate': 0.00034691823741393843, 'epoch': 4.7}

 39%|███▉      | 11010/28080 [21:45:35<33:59:02,  7.17s/it]
 39%|███▉      | 11011/28080 [21:45:42<33:46:23,  7.12s/it]
                                                           
{'loss': 0.6209, 'learning_rate': 0.0003468916561010853, 'epoch': 4.7}

 39%|███▉      | 11011/28080 [21:45:42<33:46:23,  7.12s/it]
 39%|███▉      | 11012/28080 [21:45:49<34:01:58,  7.18s/it]
                                                           
{'loss': 0.6222, 'learning_rate': 0.00034686507349918864, 'epoch': 4.7}

 39%|███▉      | 11012/28080 [21:45:49<34:01:58,  7.18s/it]
 39%|███▉      | 11013/28080 [21:45:56<34:11:33,  7.21s/it]
                                                           
{'loss': 0.6219, 'learning_rate': 0.0003468384896086021, 'epoch': 4.7}

 39%|███▉      | 11013/28080 [21:45:56<34:11:33,  7.21s/it]
 39%|███▉      | 11014/28080 [21:46:03<34:04:29,  7.19s/it]
                                                           
{'loss': 0.6359, 'learning_rate': 0.00034681190442967935, 'epoch': 4.71}

 39%|███▉      | 11014/28080 [21:46:03<34:04:29,  7.19s/it]
 39%|███▉      | 11015/28080 [21:46:11<34:02:27,  7.18s/it]
                                                           
{'loss': 0.6179, 'learning_rate': 0.0003467853179627741, 'epoch': 4.71}

 39%|███▉      | 11015/28080 [21:46:11<34:02:27,  7.18s/it]
 39%|███▉      | 11016/28080 [21:46:18<34:00:35,  7.18s/it]
                                                           
{'loss': 0.6267, 'learning_rate': 0.0003467587302082401, 'epoch': 4.71}

 39%|███▉      | 11016/28080 [21:46:18<34:00:35,  7.18s/it]
 39%|███▉      | 11017/28080 [21:46:25<33:59:59,  7.17s/it]
                                                           
{'loss': 0.6105, 'learning_rate': 0.0003467321411664309, 'epoch': 4.71}

 39%|███▉      | 11017/28080 [21:46:25<33:59:59,  7.17s/it]
 39%|███▉      | 11018/28080 [21:46:32<33:50:36,  7.14s/it]
                                                           
{'loss': 0.6285, 'learning_rate': 0.0003467055508377005, 'epoch': 4.71}

 39%|███▉      | 11018/28080 [21:46:32<33:50:36,  7.14s/it]
 39%|███▉      | 11019/28080 [21:46:39<33:46:37,  7.13s/it]
                                                           
{'loss': 0.6223, 'learning_rate': 0.00034667895922240247, 'epoch': 4.71}

 39%|███▉      | 11019/28080 [21:46:39<33:46:37,  7.13s/it]
 39%|███▉      | 11020/28080 [21:46:46<33:46:45,  7.13s/it]
                                                           
{'loss': 0.6351, 'learning_rate': 0.0003466523663208906, 'epoch': 4.71}

 39%|███▉      | 11020/28080 [21:46:46<33:46:45,  7.13s/it]
 39%|███▉      | 11021/28080 [21:46:53<33:48:20,  7.13s/it]
                                                           
{'loss': 0.6317, 'learning_rate': 0.00034662577213351867, 'epoch': 4.71}

 39%|███▉      | 11021/28080 [21:46:53<33:48:20,  7.13s/it]
 39%|███▉      | 11022/28080 [21:47:01<33:49:58,  7.14s/it]
                                                           
{'loss': 0.6107, 'learning_rate': 0.00034659917666064044, 'epoch': 4.71}

 39%|███▉      | 11022/28080 [21:47:01<33:49:58,  7.14s/it]
 39%|███▉      | 11023/28080 [21:47:08<33:54:43,  7.16s/it]
                                                           
{'loss': 0.6353, 'learning_rate': 0.00034657257990261, 'epoch': 4.71}

 39%|███▉      | 11023/28080 [21:47:08<33:54:43,  7.16s/it]
 39%|███▉      | 11024/28080 [21:47:15<33:43:45,  7.12s/it]
                                                           
{'loss': 0.6119, 'learning_rate': 0.00034654598185978095, 'epoch': 4.71}

 39%|███▉      | 11024/28080 [21:47:15<33:43:45,  7.12s/it]
 39%|███▉      | 11025/28080 [21:47:22<33:43:37,  7.12s/it]
                                                           
{'loss': 0.6148, 'learning_rate': 0.0003465193825325072, 'epoch': 4.71}

 39%|███▉      | 11025/28080 [21:47:22<33:43:37,  7.12s/it]
 39%|███▉      | 11026/28080 [21:47:29<33:41:26,  7.11s/it]
                                                           
{'loss': 0.6152, 'learning_rate': 0.00034649278192114264, 'epoch': 4.71}

 39%|███▉      | 11026/28080 [21:47:29<33:41:26,  7.11s/it]
 39%|███▉      | 11027/28080 [21:47:36<33:33:50,  7.09s/it]
                                                           
{'loss': 0.6121, 'learning_rate': 0.0003464661800260412, 'epoch': 4.71}

 39%|███▉      | 11027/28080 [21:47:36<33:33:50,  7.09s/it]
 39%|███▉      | 11028/28080 [21:47:43<33:31:16,  7.08s/it]
                                                           
{'loss': 0.6095, 'learning_rate': 0.0003464395768475567, 'epoch': 4.71}

 39%|███▉      | 11028/28080 [21:47:43<33:31:16,  7.08s/it]
 39%|███▉      | 11029/28080 [21:47:50<33:25:05,  7.06s/it]
                                                           
{'loss': 0.6078, 'learning_rate': 0.0003464129723860431, 'epoch': 4.71}

 39%|███▉      | 11029/28080 [21:47:50<33:25:05,  7.06s/it]
 39%|███▉      | 11030/28080 [21:47:57<33:25:29,  7.06s/it]
                                                           
{'loss': 0.623, 'learning_rate': 0.0003463863666418544, 'epoch': 4.71}

 39%|███▉      | 11030/28080 [21:47:57<33:25:29,  7.06s/it]
 39%|███▉      | 11031/28080 [21:48:04<33:33:09,  7.08s/it]
                                                           
{'loss': 0.6139, 'learning_rate': 0.0003463597596153445, 'epoch': 4.71}

 39%|███▉      | 11031/28080 [21:48:04<33:33:09,  7.08s/it]
 39%|███▉      | 11032/28080 [21:48:11<33:29:25,  7.07s/it]
                                                           
{'loss': 0.6449, 'learning_rate': 0.00034633315130686747, 'epoch': 4.71}

 39%|███▉      | 11032/28080 [21:48:11<33:29:25,  7.07s/it]
 39%|███▉      | 11033/28080 [21:48:18<33:30:52,  7.08s/it]
                                                           
{'loss': 0.6313, 'learning_rate': 0.00034630654171677723, 'epoch': 4.71}

 39%|███▉      | 11033/28080 [21:48:18<33:30:52,  7.08s/it]
 39%|███▉      | 11034/28080 [21:48:25<33:24:22,  7.06s/it]
                                                           
{'loss': 0.6236, 'learning_rate': 0.00034627993084542777, 'epoch': 4.71}

 39%|███▉      | 11034/28080 [21:48:25<33:24:22,  7.06s/it]
 39%|███▉      | 11035/28080 [21:48:32<33:26:46,  7.06s/it]
                                                           
{'loss': 0.6299, 'learning_rate': 0.0003462533186931732, 'epoch': 4.71}

 39%|███▉      | 11035/28080 [21:48:32<33:26:46,  7.06s/it]
 39%|███▉      | 11036/28080 [21:48:40<33:31:36,  7.08s/it]
                                                           
{'loss': 0.6422, 'learning_rate': 0.00034622670526036746, 'epoch': 4.71}

 39%|███▉      | 11036/28080 [21:48:40<33:31:36,  7.08s/it]
 39%|███▉      | 11037/28080 [21:48:47<33:29:22,  7.07s/it]
                                                           
{'loss': 0.6077, 'learning_rate': 0.00034620009054736476, 'epoch': 4.71}

 39%|███▉      | 11037/28080 [21:48:47<33:29:22,  7.07s/it]
 39%|███▉      | 11038/28080 [21:48:54<33:34:05,  7.09s/it]
                                                           
{'loss': 0.6338, 'learning_rate': 0.000346173474554519, 'epoch': 4.72}

 39%|███▉      | 11038/28080 [21:48:54<33:34:05,  7.09s/it]
 39%|███▉      | 11039/28080 [21:49:01<33:28:17,  7.07s/it]
                                                           
{'loss': 0.6093, 'learning_rate': 0.0003461468572821845, 'epoch': 4.72}

 39%|███▉      | 11039/28080 [21:49:01<33:28:17,  7.07s/it]
 39%|███▉      | 11040/28080 [21:49:08<33:26:11,  7.06s/it]
                                                           
{'loss': 0.6144, 'learning_rate': 0.0003461202387307152, 'epoch': 4.72}

 39%|███▉      | 11040/28080 [21:49:08<33:26:11,  7.06s/it]
 39%|███▉      | 11041/28080 [21:49:15<33:29:53,  7.08s/it]
                                                           
{'loss': 0.6099, 'learning_rate': 0.00034609361890046523, 'epoch': 4.72}

 39%|███▉      | 11041/28080 [21:49:15<33:29:53,  7.08s/it]
 39%|███▉      | 11042/28080 [21:49:22<33:37:02,  7.10s/it]
                                                           
{'loss': 0.6406, 'learning_rate': 0.00034606699779178893, 'epoch': 4.72}

 39%|███▉      | 11042/28080 [21:49:22<33:37:02,  7.10s/it]
 39%|███▉      | 11043/28080 [21:49:29<33:38:11,  7.11s/it]
                                                           
{'loss': 0.6075, 'learning_rate': 0.0003460403754050402, 'epoch': 4.72}

 39%|███▉      | 11043/28080 [21:49:29<33:38:11,  7.11s/it]
 39%|███▉      | 11044/28080 [21:49:36<33:35:31,  7.10s/it]
                                                           
{'loss': 0.635, 'learning_rate': 0.00034601375174057343, 'epoch': 4.72}

 39%|███▉      | 11044/28080 [21:49:36<33:35:31,  7.10s/it]
 39%|███▉      | 11045/28080 [21:49:43<33:37:56,  7.11s/it]
                                                           
{'loss': 0.6212, 'learning_rate': 0.0003459871267987427, 'epoch': 4.72}

 39%|███▉      | 11045/28080 [21:49:43<33:37:56,  7.11s/it]
 39%|███▉      | 11046/28080 [21:49:51<33:35:52,  7.10s/it]
                                                           
{'loss': 0.6185, 'learning_rate': 0.00034596050057990226, 'epoch': 4.72}

 39%|███▉      | 11046/28080 [21:49:51<33:35:52,  7.10s/it]
 39%|███▉      | 11047/28080 [21:49:58<33:33:00,  7.09s/it]
                                                           
{'loss': 0.6274, 'learning_rate': 0.0003459338730844064, 'epoch': 4.72}

 39%|███▉      | 11047/28080 [21:49:58<33:33:00,  7.09s/it]
 39%|███▉      | 11048/28080 [21:50:05<33:41:34,  7.12s/it]
                                                           
{'loss': 0.646, 'learning_rate': 0.0003459072443126092, 'epoch': 4.72}

 39%|███▉      | 11048/28080 [21:50:05<33:41:34,  7.12s/it]
 39%|███▉      | 11049/28080 [21:50:12<33:47:54,  7.14s/it]
                                                           
{'loss': 0.6281, 'learning_rate': 0.0003458806142648653, 'epoch': 4.72}

 39%|███▉      | 11049/28080 [21:50:12<33:47:54,  7.14s/it]
 39%|███▉      | 11050/28080 [21:50:19<34:01:33,  7.19s/it]
                                                           
{'loss': 0.6336, 'learning_rate': 0.00034585398294152854, 'epoch': 4.72}

 39%|███▉      | 11050/28080 [21:50:19<34:01:33,  7.19s/it]
 39%|███▉      | 11051/28080 [21:50:27<34:04:12,  7.20s/it]
                                                           
{'loss': 0.6277, 'learning_rate': 0.00034582735034295354, 'epoch': 4.72}

 39%|███▉      | 11051/28080 [21:50:27<34:04:12,  7.20s/it]
 39%|███▉      | 11052/28080 [21:50:34<33:58:01,  7.18s/it]
                                                           
{'loss': 0.6328, 'learning_rate': 0.0003458007164694944, 'epoch': 4.72}

 39%|███▉      | 11052/28080 [21:50:34<33:58:01,  7.18s/it]
 39%|███▉      | 11053/28080 [21:50:41<33:42:16,  7.13s/it]
                                                           
{'loss': 0.6426, 'learning_rate': 0.00034577408132150555, 'epoch': 4.72}

 39%|███▉      | 11053/28080 [21:50:41<33:42:16,  7.13s/it]
 39%|███▉      | 11054/28080 [21:50:48<33:46:07,  7.14s/it]
                                                           
{'loss': 0.6395, 'learning_rate': 0.0003457474448993415, 'epoch': 4.72}

 39%|███▉      | 11054/28080 [21:50:48<33:46:07,  7.14s/it]
 39%|███▉      | 11055/28080 [21:50:55<33:42:33,  7.13s/it]
                                                           
{'loss': 0.6242, 'learning_rate': 0.00034572080720335634, 'epoch': 4.72}

 39%|███▉      | 11055/28080 [21:50:55<33:42:33,  7.13s/it]
 39%|███▉      | 11056/28080 [21:51:02<33:25:39,  7.07s/it]
                                                           
{'loss': 0.6428, 'learning_rate': 0.00034569416823390463, 'epoch': 4.72}

 39%|███▉      | 11056/28080 [21:51:02<33:25:39,  7.07s/it]
 39%|███▉      | 11057/28080 [21:51:09<33:32:17,  7.09s/it]
                                                           
{'loss': 0.6003, 'learning_rate': 0.0003456675279913408, 'epoch': 4.72}

 39%|███▉      | 11057/28080 [21:51:09<33:32:17,  7.09s/it]
 39%|███▉      | 11058/28080 [21:51:16<33:33:02,  7.10s/it]
                                                           
{'loss': 0.6415, 'learning_rate': 0.0003456408864760191, 'epoch': 4.72}

 39%|███▉      | 11058/28080 [21:51:16<33:33:02,  7.10s/it]
 39%|███▉      | 11059/28080 [21:51:23<33:36:18,  7.11s/it]
                                                           
{'loss': 0.6225, 'learning_rate': 0.00034561424368829415, 'epoch': 4.72}

 39%|███▉      | 11059/28080 [21:51:23<33:36:18,  7.11s/it]
 39%|███▉      | 11060/28080 [21:51:30<33:29:21,  7.08s/it]
                                                           
{'loss': 0.6187, 'learning_rate': 0.00034558759962852024, 'epoch': 4.72}

 39%|███▉      | 11060/28080 [21:51:30<33:29:21,  7.08s/it]
 39%|███▉      | 11061/28080 [21:51:37<33:30:37,  7.09s/it]
                                                           
{'loss': 0.5982, 'learning_rate': 0.00034556095429705204, 'epoch': 4.73}

 39%|███▉      | 11061/28080 [21:51:37<33:30:37,  7.09s/it]
 39%|███▉      | 11062/28080 [21:51:45<33:44:02,  7.14s/it]
                                                           
{'loss': 0.6317, 'learning_rate': 0.0003455343076942438, 'epoch': 4.73}

 39%|███▉      | 11062/28080 [21:51:45<33:44:02,  7.14s/it]
 39%|███▉      | 11063/28080 [21:51:52<33:48:13,  7.15s/it]
                                                           
{'loss': 0.6216, 'learning_rate': 0.0003455076598204503, 'epoch': 4.73}

 39%|███▉      | 11063/28080 [21:51:52<33:48:13,  7.15s/it]
 39%|███▉      | 11064/28080 [21:51:59<33:43:17,  7.13s/it]
                                                           
{'loss': 0.618, 'learning_rate': 0.0003454810106760258, 'epoch': 4.73}

 39%|███▉      | 11064/28080 [21:51:59<33:43:17,  7.13s/it]
 39%|███▉      | 11065/28080 [21:52:06<33:48:48,  7.15s/it]
                                                           
{'loss': 0.6294, 'learning_rate': 0.000345454360261325, 'epoch': 4.73}

 39%|███▉      | 11065/28080 [21:52:06<33:48:48,  7.15s/it]
 39%|███▉      | 11066/28080 [21:52:13<33:38:39,  7.12s/it]
                                                           
{'loss': 0.6401, 'learning_rate': 0.0003454277085767024, 'epoch': 4.73}

 39%|███▉      | 11066/28080 [21:52:13<33:38:39,  7.12s/it]
 39%|███▉      | 11067/28080 [21:52:20<33:42:23,  7.13s/it]
                                                           
{'loss': 0.6195, 'learning_rate': 0.0003454010556225127, 'epoch': 4.73}

 39%|███▉      | 11067/28080 [21:52:20<33:42:23,  7.13s/it]
 39%|███▉      | 11068/28080 [21:52:27<33:39:17,  7.12s/it]
                                                           
{'loss': 0.6436, 'learning_rate': 0.00034537440139911026, 'epoch': 4.73}

 39%|███▉      | 11068/28080 [21:52:27<33:39:17,  7.12s/it]
 39%|███▉      | 11069/28080 [21:52:35<33:38:18,  7.12s/it]
                                                           
{'loss': 0.6078, 'learning_rate': 0.00034534774590684977, 'epoch': 4.73}

 39%|███▉      | 11069/28080 [21:52:35<33:38:18,  7.12s/it]
 39%|███▉      | 11070/28080 [21:52:42<33:30:51,  7.09s/it]
                                                           
{'loss': 0.6422, 'learning_rate': 0.0003453210891460859, 'epoch': 4.73}

 39%|███▉      | 11070/28080 [21:52:42<33:30:51,  7.09s/it]
 39%|███▉      | 11071/28080 [21:52:49<33:39:46,  7.12s/it]
                                                           
{'loss': 0.613, 'learning_rate': 0.0003452944311171733, 'epoch': 4.73}

 39%|███▉      | 11071/28080 [21:52:49<33:39:46,  7.12s/it]
 39%|███▉      | 11072/28080 [21:52:56<33:31:07,  7.09s/it]
                                                           
{'loss': 0.6296, 'learning_rate': 0.0003452677718204666, 'epoch': 4.73}

 39%|███▉      | 11072/28080 [21:52:56<33:31:07,  7.09s/it]
 39%|███▉      | 11073/28080 [21:53:03<33:34:20,  7.11s/it]
                                                           
{'loss': 0.6162, 'learning_rate': 0.0003452411112563205, 'epoch': 4.73}

 39%|███▉      | 11073/28080 [21:53:03<33:34:20,  7.11s/it]
 39%|███▉      | 11074/28080 [21:53:10<33:35:28,  7.11s/it]
                                                           
{'loss': 0.6173, 'learning_rate': 0.0003452144494250897, 'epoch': 4.73}

 39%|███▉      | 11074/28080 [21:53:10<33:35:28,  7.11s/it]
 39%|███▉      | 11075/28080 [21:53:17<33:32:51,  7.10s/it]
                                                           
{'loss': 0.6256, 'learning_rate': 0.00034518778632712884, 'epoch': 4.73}

 39%|███▉      | 11075/28080 [21:53:17<33:32:51,  7.10s/it]
 39%|███▉      | 11076/28080 [21:53:24<33:42:22,  7.14s/it]
                                                           
{'loss': 0.6216, 'learning_rate': 0.0003451611219627926, 'epoch': 4.73}

 39%|███▉      | 11076/28080 [21:53:24<33:42:22,  7.14s/it]
 39%|███▉      | 11077/28080 [21:53:31<33:39:04,  7.12s/it]
                                                           
{'loss': 0.6131, 'learning_rate': 0.0003451344563324359, 'epoch': 4.73}

 39%|███▉      | 11077/28080 [21:53:31<33:39:04,  7.12s/it]
 39%|███▉      | 11078/28080 [21:53:39<33:42:14,  7.14s/it]
                                                           
{'loss': 0.6113, 'learning_rate': 0.0003451077894364134, 'epoch': 4.73}

 39%|███▉      | 11078/28080 [21:53:39<33:42:14,  7.14s/it]
 39%|███▉      | 11079/28080 [21:53:46<33:38:57,  7.13s/it]
                                                           
{'loss': 0.6163, 'learning_rate': 0.00034508112127507983, 'epoch': 4.73}

 39%|███▉      | 11079/28080 [21:53:46<33:38:57,  7.13s/it]
 39%|███▉      | 11080/28080 [21:53:53<33:44:36,  7.15s/it]
                                                           
{'loss': 0.6237, 'learning_rate': 0.00034505445184879007, 'epoch': 4.73}

 39%|███▉      | 11080/28080 [21:53:53<33:44:36,  7.15s/it]
 39%|███▉      | 11081/28080 [21:54:00<33:32:17,  7.10s/it]
                                                           
{'loss': 0.632, 'learning_rate': 0.0003450277811578989, 'epoch': 4.73}

 39%|███▉      | 11081/28080 [21:54:00<33:32:17,  7.10s/it]
 39%|███▉      | 11082/28080 [21:54:07<33:28:38,  7.09s/it]
                                                           
{'loss': 0.6279, 'learning_rate': 0.00034500110920276114, 'epoch': 4.73}

 39%|███▉      | 11082/28080 [21:54:07<33:28:38,  7.09s/it]
 39%|███▉      | 11083/28080 [21:54:14<33:26:34,  7.08s/it]
                                                           
{'loss': 0.6061, 'learning_rate': 0.00034497443598373155, 'epoch': 4.73}

 39%|███▉      | 11083/28080 [21:54:14<33:26:34,  7.08s/it]
 39%|███▉      | 11084/28080 [21:54:21<33:22:46,  7.07s/it]
                                                           
{'loss': 0.6342, 'learning_rate': 0.00034494776150116515, 'epoch': 4.73}

 39%|███▉      | 11084/28080 [21:54:21<33:22:46,  7.07s/it]
 39%|███▉      | 11085/28080 [21:54:28<33:21:33,  7.07s/it]
                                                           
{'loss': 0.631, 'learning_rate': 0.0003449210857554167, 'epoch': 4.74}

 39%|███▉      | 11085/28080 [21:54:28<33:21:33,  7.07s/it]
 39%|███▉      | 11086/28080 [21:54:35<33:29:06,  7.09s/it]
                                                           
{'loss': 0.63, 'learning_rate': 0.0003448944087468411, 'epoch': 4.74}

 39%|███▉      | 11086/28080 [21:54:35<33:29:06,  7.09s/it]
 39%|███▉      | 11087/28080 [21:54:42<33:24:21,  7.08s/it]
                                                           
{'loss': 0.6287, 'learning_rate': 0.0003448677304757934, 'epoch': 4.74}

 39%|███▉      | 11087/28080 [21:54:42<33:24:21,  7.08s/it]
 39%|███▉      | 11088/28080 [21:54:49<33:21:48,  7.07s/it]
                                                           
{'loss': 0.6188, 'learning_rate': 0.0003448410509426283, 'epoch': 4.74}

 39%|███▉      | 11088/28080 [21:54:49<33:21:48,  7.07s/it]
 39%|███▉      | 11089/28080 [21:54:56<33:22:10,  7.07s/it]
                                                           
{'loss': 0.632, 'learning_rate': 0.00034481437014770094, 'epoch': 4.74}

 39%|███▉      | 11089/28080 [21:54:56<33:22:10,  7.07s/it]
 39%|███▉      | 11090/28080 [21:55:04<33:30:04,  7.10s/it]
                                                           
{'loss': 0.6477, 'learning_rate': 0.0003447876880913661, 'epoch': 4.74}

 39%|███▉      | 11090/28080 [21:55:04<33:30:04,  7.10s/it]
 39%|███▉      | 11091/28080 [21:55:11<33:38:46,  7.13s/it]
                                                           
{'loss': 0.6076, 'learning_rate': 0.0003447610047739789, 'epoch': 4.74}

 39%|███▉      | 11091/28080 [21:55:11<33:38:46,  7.13s/it]
 40%|███▉      | 11092/28080 [21:55:18<33:39:07,  7.13s/it]
                                                           
{'loss': 0.6225, 'learning_rate': 0.00034473432019589445, 'epoch': 4.74}

 40%|███▉      | 11092/28080 [21:55:18<33:39:07,  7.13s/it]
 40%|███▉      | 11093/28080 [21:55:25<33:27:51,  7.09s/it]
                                                           
{'loss': 0.6303, 'learning_rate': 0.0003447076343574674, 'epoch': 4.74}

 40%|███▉      | 11093/28080 [21:55:25<33:27:51,  7.09s/it]
 40%|███▉      | 11094/28080 [21:55:32<33:25:12,  7.08s/it]
                                                           
{'loss': 0.6362, 'learning_rate': 0.00034468094725905303, 'epoch': 4.74}

 40%|███▉      | 11094/28080 [21:55:32<33:25:12,  7.08s/it]
 40%|███▉      | 11095/28080 [21:55:39<33:23:01,  7.08s/it]
                                                           
{'loss': 0.634, 'learning_rate': 0.0003446542589010064, 'epoch': 4.74}

 40%|███▉      | 11095/28080 [21:55:39<33:23:01,  7.08s/it]
 40%|███▉      | 11096/28080 [21:55:46<33:36:07,  7.12s/it]
                                                           
{'loss': 0.6162, 'learning_rate': 0.00034462756928368244, 'epoch': 4.74}

 40%|███▉      | 11096/28080 [21:55:46<33:36:07,  7.12s/it]
 40%|███▉      | 11097/28080 [21:55:53<33:33:54,  7.12s/it]
                                                           
{'loss': 0.6339, 'learning_rate': 0.00034460087840743633, 'epoch': 4.74}

 40%|███▉      | 11097/28080 [21:55:53<33:33:54,  7.12s/it]
 40%|███▉      | 11098/28080 [21:56:00<33:19:03,  7.06s/it]
                                                           
{'loss': 0.6293, 'learning_rate': 0.00034457418627262303, 'epoch': 4.74}

 40%|███▉      | 11098/28080 [21:56:00<33:19:03,  7.06s/it]
 40%|███▉      | 11099/28080 [21:56:07<33:12:49,  7.04s/it]
                                                           
{'loss': 0.6337, 'learning_rate': 0.0003445474928795979, 'epoch': 4.74}

 40%|███▉      | 11099/28080 [21:56:07<33:12:49,  7.04s/it]
 40%|███▉      | 11100/28080 [21:56:14<33:20:19,  7.07s/it]
                                                           
{'loss': 0.6268, 'learning_rate': 0.0003445207982287158, 'epoch': 4.74}

 40%|███▉      | 11100/28080 [21:56:14<33:20:19,  7.07s/it]
 40%|███▉      | 11101/28080 [21:56:21<33:19:01,  7.06s/it]
                                                           
{'loss': 0.6218, 'learning_rate': 0.00034449410232033193, 'epoch': 4.74}

 40%|███▉      | 11101/28080 [21:56:21<33:19:01,  7.06s/it]
 40%|███▉      | 11102/28080 [21:56:29<33:25:59,  7.09s/it]
                                                           
{'loss': 0.6041, 'learning_rate': 0.0003444674051548017, 'epoch': 4.74}

 40%|███▉      | 11102/28080 [21:56:29<33:25:59,  7.09s/it]
 40%|███▉      | 11103/28080 [21:56:36<33:26:57,  7.09s/it]
                                                           
{'loss': 0.6225, 'learning_rate': 0.00034444070673247994, 'epoch': 4.74}

 40%|███▉      | 11103/28080 [21:56:36<33:26:57,  7.09s/it]
 40%|███▉      | 11104/28080 [21:56:43<33:34:38,  7.12s/it]
                                                           
{'loss': 0.6154, 'learning_rate': 0.00034441400705372216, 'epoch': 4.74}

 40%|███▉      | 11104/28080 [21:56:43<33:34:38,  7.12s/it]
 40%|███▉      | 11105/28080 [21:56:50<33:32:11,  7.11s/it]
                                                           
{'loss': 0.6054, 'learning_rate': 0.0003443873061188833, 'epoch': 4.74}

 40%|███▉      | 11105/28080 [21:56:50<33:32:11,  7.11s/it]
 40%|███▉      | 11106/28080 [21:56:57<33:32:11,  7.11s/it]
                                                           
{'loss': 0.6313, 'learning_rate': 0.00034436060392831875, 'epoch': 4.74}

 40%|███▉      | 11106/28080 [21:56:57<33:32:11,  7.11s/it]
 40%|███▉      | 11107/28080 [21:57:04<33:30:07,  7.11s/it]
                                                           
{'loss': 0.6263, 'learning_rate': 0.00034433390048238364, 'epoch': 4.74}

 40%|███▉      | 11107/28080 [21:57:04<33:30:07,  7.11s/it]
 40%|███▉      | 11108/28080 [21:57:11<33:29:32,  7.10s/it]
                                                           
{'loss': 0.626, 'learning_rate': 0.0003443071957814334, 'epoch': 4.75}

 40%|███▉      | 11108/28080 [21:57:11<33:29:32,  7.10s/it]
 40%|███▉      | 11109/28080 [21:57:18<33:34:11,  7.12s/it]
                                                           
{'loss': 0.6418, 'learning_rate': 0.0003442804898258232, 'epoch': 4.75}

 40%|███▉      | 11109/28080 [21:57:18<33:34:11,  7.12s/it]
 40%|███▉      | 11110/28080 [21:57:26<33:32:36,  7.12s/it]
                                                           
{'loss': 0.6441, 'learning_rate': 0.00034425378261590826, 'epoch': 4.75}

 40%|███▉      | 11110/28080 [21:57:26<33:32:36,  7.12s/it]
 40%|███▉      | 11111/28080 [21:57:33<33:24:10,  7.09s/it]
                                                           
{'loss': 0.6402, 'learning_rate': 0.0003442270741520441, 'epoch': 4.75}

 40%|███▉      | 11111/28080 [21:57:33<33:24:10,  7.09s/it]
 40%|███▉      | 11112/28080 [21:57:40<33:29:31,  7.11s/it]
                                                           
{'loss': 0.6317, 'learning_rate': 0.0003442003644345859, 'epoch': 4.75}

 40%|███▉      | 11112/28080 [21:57:40<33:29:31,  7.11s/it]
 40%|███▉      | 11113/28080 [21:57:47<33:32:22,  7.12s/it]
                                                           
{'loss': 0.6287, 'learning_rate': 0.000344173653463889, 'epoch': 4.75}

 40%|███▉      | 11113/28080 [21:57:47<33:32:22,  7.12s/it]
 40%|███▉      | 11114/28080 [21:57:54<33:31:20,  7.11s/it]
                                                           
{'loss': 0.6075, 'learning_rate': 0.00034414694124030877, 'epoch': 4.75}

 40%|███▉      | 11114/28080 [21:57:54<33:31:20,  7.11s/it]
 40%|███▉      | 11115/28080 [21:58:01<33:32:43,  7.12s/it]
                                                           
{'loss': 0.6113, 'learning_rate': 0.0003441202277642006, 'epoch': 4.75}

 40%|███▉      | 11115/28080 [21:58:01<33:32:43,  7.12s/it]
 40%|███▉      | 11116/28080 [21:58:08<33:21:15,  7.08s/it]
                                                           
{'loss': 0.6275, 'learning_rate': 0.00034409351303591997, 'epoch': 4.75}

 40%|███▉      | 11116/28080 [21:58:08<33:21:15,  7.08s/it]
 40%|███▉      | 11117/28080 [21:58:15<33:16:06,  7.06s/it]
                                                           
{'loss': 0.6362, 'learning_rate': 0.00034406679705582225, 'epoch': 4.75}

 40%|███▉      | 11117/28080 [21:58:15<33:16:06,  7.06s/it]
 40%|███▉      | 11118/28080 [21:58:22<33:12:54,  7.05s/it]
                                                           
{'loss': 0.6074, 'learning_rate': 0.0003440400798242627, 'epoch': 4.75}

 40%|███▉      | 11118/28080 [21:58:22<33:12:54,  7.05s/it]
 40%|███▉      | 11119/28080 [21:58:29<33:26:49,  7.10s/it]
                                                           
{'loss': 0.6232, 'learning_rate': 0.000344013361341597, 'epoch': 4.75}

 40%|███▉      | 11119/28080 [21:58:29<33:26:49,  7.10s/it]
 40%|███▉      | 11120/28080 [21:58:36<33:20:33,  7.08s/it]
                                                           
{'loss': 0.6239, 'learning_rate': 0.0003439866416081805, 'epoch': 4.75}

 40%|███▉      | 11120/28080 [21:58:36<33:20:33,  7.08s/it]
 40%|███▉      | 11121/28080 [21:58:44<33:25:39,  7.10s/it]
                                                           
{'loss': 0.6372, 'learning_rate': 0.0003439599206243687, 'epoch': 4.75}

 40%|███▉      | 11121/28080 [21:58:44<33:25:39,  7.10s/it]
 40%|███▉      | 11122/28080 [21:58:51<33:27:35,  7.10s/it]
                                                           
{'loss': 0.6386, 'learning_rate': 0.00034393319839051706, 'epoch': 4.75}

 40%|███▉      | 11122/28080 [21:58:51<33:27:35,  7.10s/it]
 40%|███▉      | 11123/28080 [21:58:58<33:29:53,  7.11s/it]
                                                           
{'loss': 0.6076, 'learning_rate': 0.00034390647490698114, 'epoch': 4.75}

 40%|███▉      | 11123/28080 [21:58:58<33:29:53,  7.11s/it]
 40%|███▉      | 11124/28080 [21:59:05<33:29:23,  7.11s/it]
                                                           
{'loss': 0.6224, 'learning_rate': 0.0003438797501741164, 'epoch': 4.75}

 40%|███▉      | 11124/28080 [21:59:05<33:29:23,  7.11s/it]
 40%|███▉      | 11125/28080 [21:59:12<33:27:41,  7.10s/it]
                                                           
{'loss': 0.6172, 'learning_rate': 0.00034385302419227847, 'epoch': 4.75}

 40%|███▉      | 11125/28080 [21:59:12<33:27:41,  7.10s/it]
 40%|███▉      | 11126/28080 [21:59:19<33:30:37,  7.12s/it]
                                                           
{'loss': 0.6319, 'learning_rate': 0.00034382629696182295, 'epoch': 4.75}

 40%|███▉      | 11126/28080 [21:59:19<33:30:37,  7.12s/it]
 40%|███▉      | 11127/28080 [21:59:26<33:29:45,  7.11s/it]
                                                           
{'loss': 0.6523, 'learning_rate': 0.00034379956848310525, 'epoch': 4.75}

 40%|███▉      | 11127/28080 [21:59:26<33:29:45,  7.11s/it]
 40%|███▉      | 11128/28080 [21:59:33<33:25:16,  7.10s/it]
                                                           
{'loss': 0.6234, 'learning_rate': 0.00034377283875648115, 'epoch': 4.75}

 40%|███▉      | 11128/28080 [21:59:33<33:25:16,  7.10s/it]
 40%|███▉      | 11129/28080 [21:59:40<33:29:55,  7.11s/it]
                                                           
{'loss': 0.6284, 'learning_rate': 0.0003437461077823061, 'epoch': 4.75}

 40%|███▉      | 11129/28080 [21:59:40<33:29:55,  7.11s/it]
 40%|███▉      | 11130/28080 [21:59:48<33:32:10,  7.12s/it]
                                                           
{'loss': 0.6321, 'learning_rate': 0.0003437193755609358, 'epoch': 4.75}

 40%|███▉      | 11130/28080 [21:59:48<33:32:10,  7.12s/it]
 40%|███▉      | 11131/28080 [21:59:55<33:25:07,  7.10s/it]
                                                           
{'loss': 0.6475, 'learning_rate': 0.0003436926420927259, 'epoch': 4.76}

 40%|███▉      | 11131/28080 [21:59:55<33:25:07,  7.10s/it]
 40%|███▉      | 11132/28080 [22:00:02<33:21:10,  7.08s/it]
                                                           
{'loss': 0.6155, 'learning_rate': 0.000343665907378032, 'epoch': 4.76}

 40%|███▉      | 11132/28080 [22:00:02<33:21:10,  7.08s/it]
 40%|███▉      | 11133/28080 [22:00:09<33:22:42,  7.09s/it]
                                                           
{'loss': 0.6353, 'learning_rate': 0.00034363917141720993, 'epoch': 4.76}

 40%|███▉      | 11133/28080 [22:00:09<33:22:42,  7.09s/it]
 40%|███▉      | 11134/28080 [22:00:16<33:30:52,  7.12s/it]
                                                           
{'loss': 0.6407, 'learning_rate': 0.00034361243421061525, 'epoch': 4.76}

 40%|███▉      | 11134/28080 [22:00:16<33:30:52,  7.12s/it]
 40%|███▉      | 11135/28080 [22:00:23<33:25:32,  7.10s/it]
                                                           
{'loss': 0.6388, 'learning_rate': 0.0003435856957586037, 'epoch': 4.76}

 40%|███▉      | 11135/28080 [22:00:23<33:25:32,  7.10s/it]
 40%|███▉      | 11136/28080 [22:00:30<33:25:07,  7.10s/it]
                                                           
{'loss': 0.6234, 'learning_rate': 0.000343558956061531, 'epoch': 4.76}

 40%|███▉      | 11136/28080 [22:00:30<33:25:07,  7.10s/it]
 40%|███▉      | 11137/28080 [22:00:37<33:20:40,  7.08s/it]
                                                           
{'loss': 0.6216, 'learning_rate': 0.000343532215119753, 'epoch': 4.76}

 40%|███▉      | 11137/28080 [22:00:37<33:20:40,  7.08s/it]
 40%|███▉      | 11138/28080 [22:00:44<33:22:08,  7.09s/it]
                                                           
{'loss': 0.6106, 'learning_rate': 0.00034350547293362523, 'epoch': 4.76}

 40%|███▉      | 11138/28080 [22:00:44<33:22:08,  7.09s/it]
 40%|███▉      | 11139/28080 [22:00:51<33:29:40,  7.12s/it]
                                                           
{'loss': 0.6211, 'learning_rate': 0.00034347872950350365, 'epoch': 4.76}

 40%|███▉      | 11139/28080 [22:00:51<33:29:40,  7.12s/it]
 40%|███▉      | 11140/28080 [22:00:59<33:37:04,  7.14s/it]
                                                           
{'loss': 0.6119, 'learning_rate': 0.00034345198482974406, 'epoch': 4.76}

 40%|███▉      | 11140/28080 [22:00:59<33:37:04,  7.14s/it]
 40%|███▉      | 11141/28080 [22:01:06<33:30:49,  7.12s/it]
                                                           
{'loss': 0.6234, 'learning_rate': 0.0003434252389127022, 'epoch': 4.76}

 40%|███▉      | 11141/28080 [22:01:06<33:30:49,  7.12s/it]
 40%|███▉      | 11142/28080 [22:01:13<33:22:19,  7.09s/it]
                                                           
{'loss': 0.6244, 'learning_rate': 0.00034339849175273393, 'epoch': 4.76}

 40%|███▉      | 11142/28080 [22:01:13<33:22:19,  7.09s/it]
 40%|███▉      | 11143/28080 [22:01:20<33:28:26,  7.11s/it]
                                                           
{'loss': 0.6161, 'learning_rate': 0.00034337174335019507, 'epoch': 4.76}

 40%|███▉      | 11143/28080 [22:01:20<33:28:26,  7.11s/it]
 40%|███▉      | 11144/28080 [22:01:27<33:20:57,  7.09s/it]
                                                           
{'loss': 0.6254, 'learning_rate': 0.0003433449937054415, 'epoch': 4.76}

 40%|███▉      | 11144/28080 [22:01:27<33:20:57,  7.09s/it]
 40%|███▉      | 11145/28080 [22:01:34<33:22:04,  7.09s/it]
                                                           
{'loss': 0.6286, 'learning_rate': 0.00034331824281882907, 'epoch': 4.76}

 40%|███▉      | 11145/28080 [22:01:34<33:22:04,  7.09s/it]
 40%|███▉      | 11146/28080 [22:01:41<33:28:18,  7.12s/it]
                                                           
{'loss': 0.6357, 'learning_rate': 0.0003432914906907136, 'epoch': 4.76}

 40%|███▉      | 11146/28080 [22:01:41<33:28:18,  7.12s/it]
 40%|███▉      | 11147/28080 [22:01:48<33:22:09,  7.09s/it]
                                                           
{'loss': 0.6361, 'learning_rate': 0.00034326473732145126, 'epoch': 4.76}

 40%|███▉      | 11147/28080 [22:01:48<33:22:09,  7.09s/it]
 40%|███▉      | 11148/28080 [22:01:55<33:24:58,  7.10s/it]
                                                           
{'loss': 0.6185, 'learning_rate': 0.0003432379827113977, 'epoch': 4.76}

 40%|███▉      | 11148/28080 [22:01:55<33:24:58,  7.10s/it]
 40%|███▉      | 11149/28080 [22:02:02<33:21:08,  7.09s/it]
                                                           
{'loss': 0.6214, 'learning_rate': 0.000343211226860909, 'epoch': 4.76}

 40%|███▉      | 11149/28080 [22:02:02<33:21:08,  7.09s/it]
 40%|███▉      | 11150/28080 [22:02:10<33:23:21,  7.10s/it]
                                                           
{'loss': 0.6155, 'learning_rate': 0.00034318446977034113, 'epoch': 4.76}

 40%|███▉      | 11150/28080 [22:02:10<33:23:21,  7.10s/it]
 40%|███▉      | 11151/28080 [22:02:17<33:16:59,  7.08s/it]
                                                           
{'loss': 0.6265, 'learning_rate': 0.0003431577114400499, 'epoch': 4.76}

 40%|███▉      | 11151/28080 [22:02:17<33:16:59,  7.08s/it]
 40%|███▉      | 11152/28080 [22:02:24<33:31:06,  7.13s/it]
                                                           
{'loss': 0.6201, 'learning_rate': 0.00034313095187039157, 'epoch': 4.76}

 40%|███▉      | 11152/28080 [22:02:24<33:31:06,  7.13s/it]
 40%|███▉      | 11153/28080 [22:02:31<33:28:02,  7.12s/it]
                                                           
{'loss': 0.6178, 'learning_rate': 0.00034310419106172184, 'epoch': 4.76}

 40%|███▉      | 11153/28080 [22:02:31<33:28:02,  7.12s/it]
 40%|███▉      | 11154/28080 [22:02:38<33:35:58,  7.15s/it]
                                                           
{'loss': 0.5975, 'learning_rate': 0.0003430774290143971, 'epoch': 4.76}

 40%|███▉      | 11154/28080 [22:02:38<33:35:58,  7.15s/it]
 40%|███▉      | 11155/28080 [22:02:45<33:35:07,  7.14s/it]
                                                           
{'loss': 0.5925, 'learning_rate': 0.000343050665728773, 'epoch': 4.77}

 40%|███▉      | 11155/28080 [22:02:45<33:35:07,  7.14s/it]
 40%|███▉      | 11156/28080 [22:02:52<33:29:10,  7.12s/it]
                                                           
{'loss': 0.6332, 'learning_rate': 0.00034302390120520586, 'epoch': 4.77}

 40%|███▉      | 11156/28080 [22:02:52<33:29:10,  7.12s/it]
 40%|███▉      | 11157/28080 [22:03:00<33:30:16,  7.13s/it]
                                                           
{'loss': 0.6359, 'learning_rate': 0.00034299713544405175, 'epoch': 4.77}

 40%|███▉      | 11157/28080 [22:03:00<33:30:16,  7.13s/it]
 40%|███▉      | 11158/28080 [22:03:07<33:29:15,  7.12s/it]
                                                           
{'loss': 0.6196, 'learning_rate': 0.0003429703684456666, 'epoch': 4.77}

 40%|███▉      | 11158/28080 [22:03:07<33:29:15,  7.12s/it]
 40%|███▉      | 11159/28080 [22:03:14<33:24:59,  7.11s/it]
                                                           
{'loss': 0.6271, 'learning_rate': 0.00034294360021040667, 'epoch': 4.77}

 40%|███▉      | 11159/28080 [22:03:14<33:24:59,  7.11s/it]
 40%|███▉      | 11160/28080 [22:03:21<33:25:39,  7.11s/it]
                                                           
{'loss': 0.6102, 'learning_rate': 0.000342916830738628, 'epoch': 4.77}

 40%|███▉      | 11160/28080 [22:03:21<33:25:39,  7.11s/it]
 40%|███▉      | 11161/28080 [22:03:28<33:28:21,  7.12s/it]
                                                           
{'loss': 0.6194, 'learning_rate': 0.00034289006003068674, 'epoch': 4.77}

 40%|███▉      | 11161/28080 [22:03:28<33:28:21,  7.12s/it]
 40%|███▉      | 11162/28080 [22:03:35<33:28:51,  7.12s/it]
                                                           
{'loss': 0.5962, 'learning_rate': 0.00034286328808693907, 'epoch': 4.77}

 40%|███▉      | 11162/28080 [22:03:35<33:28:51,  7.12s/it]
 40%|███▉      | 11163/28080 [22:03:42<33:24:34,  7.11s/it]
                                                           
{'loss': 0.6292, 'learning_rate': 0.00034283651490774113, 'epoch': 4.77}

 40%|███▉      | 11163/28080 [22:03:42<33:24:34,  7.11s/it]
 40%|███▉      | 11164/28080 [22:03:49<33:15:12,  7.08s/it]
                                                           
{'loss': 0.6288, 'learning_rate': 0.00034280974049344913, 'epoch': 4.77}

 40%|███▉      | 11164/28080 [22:03:49<33:15:12,  7.08s/it]
 40%|███▉      | 11165/28080 [22:03:56<33:16:31,  7.08s/it]
                                                           
{'loss': 0.6125, 'learning_rate': 0.00034278296484441934, 'epoch': 4.77}

 40%|███▉      | 11165/28080 [22:03:56<33:16:31,  7.08s/it]
 40%|███▉      | 11166/28080 [22:04:03<33:18:56,  7.09s/it]
                                                           
{'loss': 0.6374, 'learning_rate': 0.0003427561879610079, 'epoch': 4.77}

 40%|███▉      | 11166/28080 [22:04:03<33:18:56,  7.09s/it]
 40%|███▉      | 11167/28080 [22:04:10<33:17:51,  7.09s/it]
                                                           
{'loss': 0.6318, 'learning_rate': 0.0003427294098435711, 'epoch': 4.77}

 40%|███▉      | 11167/28080 [22:04:10<33:17:51,  7.09s/it]
 40%|███▉      | 11168/28080 [22:04:18<33:20:54,  7.10s/it]
                                                           
{'loss': 0.6086, 'learning_rate': 0.0003427026304924651, 'epoch': 4.77}

 40%|███▉      | 11168/28080 [22:04:18<33:20:54,  7.10s/it]
 40%|███▉      | 11169/28080 [22:04:25<33:23:02,  7.11s/it]
                                                           
{'loss': 0.605, 'learning_rate': 0.0003426758499080463, 'epoch': 4.77}

 40%|███▉      | 11169/28080 [22:04:25<33:23:02,  7.11s/it]
 40%|███▉      | 11170/28080 [22:04:32<33:24:29,  7.11s/it]
                                                           
{'loss': 0.6203, 'learning_rate': 0.00034264906809067084, 'epoch': 4.77}

 40%|███▉      | 11170/28080 [22:04:32<33:24:29,  7.11s/it]
 40%|███▉      | 11171/28080 [22:04:39<33:26:27,  7.12s/it]
                                                           
{'loss': 0.6077, 'learning_rate': 0.0003426222850406952, 'epoch': 4.77}

 40%|███▉      | 11171/28080 [22:04:39<33:26:27,  7.12s/it]
 40%|███▉      | 11172/28080 [22:04:46<33:23:39,  7.11s/it]
                                                           
{'loss': 0.6545, 'learning_rate': 0.00034259550075847555, 'epoch': 4.77}

 40%|███▉      | 11172/28080 [22:04:46<33:23:39,  7.11s/it]
 40%|███▉      | 11173/28080 [22:04:53<33:24:26,  7.11s/it]
                                                           
{'loss': 0.6411, 'learning_rate': 0.00034256871524436825, 'epoch': 4.77}

 40%|███▉      | 11173/28080 [22:04:53<33:24:26,  7.11s/it]
 40%|███▉      | 11174/28080 [22:05:00<33:23:06,  7.11s/it]
                                                           
{'loss': 0.6316, 'learning_rate': 0.0003425419284987298, 'epoch': 4.77}

 40%|███▉      | 11174/28080 [22:05:00<33:23:06,  7.11s/it]
 40%|███▉      | 11175/28080 [22:05:07<33:14:58,  7.08s/it]
                                                           
{'loss': 0.6407, 'learning_rate': 0.0003425151405219164, 'epoch': 4.77}

 40%|███▉      | 11175/28080 [22:05:07<33:14:58,  7.08s/it]
 40%|███▉      | 11176/28080 [22:05:14<33:13:44,  7.08s/it]
                                                           
{'loss': 0.6254, 'learning_rate': 0.0003424883513142845, 'epoch': 4.77}

 40%|███▉      | 11176/28080 [22:05:14<33:13:44,  7.08s/it]
 40%|███▉      | 11177/28080 [22:05:22<33:20:46,  7.10s/it]
                                                           
{'loss': 0.6145, 'learning_rate': 0.0003424615608761905, 'epoch': 4.77}

 40%|███▉      | 11177/28080 [22:05:22<33:20:46,  7.10s/it]
 40%|███▉      | 11178/28080 [22:05:29<33:10:38,  7.07s/it]
                                                           
{'loss': 0.6344, 'learning_rate': 0.0003424347692079909, 'epoch': 4.78}

 40%|███▉      | 11178/28080 [22:05:29<33:10:38,  7.07s/it]
 40%|███▉      | 11179/28080 [22:05:36<33:22:12,  7.11s/it]
                                                           
{'loss': 0.6306, 'learning_rate': 0.00034240797631004196, 'epoch': 4.78}

 40%|███▉      | 11179/28080 [22:05:36<33:22:12,  7.11s/it]
 40%|███▉      | 11180/28080 [22:05:43<33:25:26,  7.12s/it]
                                                           
{'loss': 0.6413, 'learning_rate': 0.0003423811821827002, 'epoch': 4.78}

 40%|███▉      | 11180/28080 [22:05:43<33:25:26,  7.12s/it]
 40%|███▉      | 11181/28080 [22:05:50<33:22:53,  7.11s/it]
                                                           
{'loss': 0.6258, 'learning_rate': 0.0003423543868263222, 'epoch': 4.78}

 40%|███▉      | 11181/28080 [22:05:50<33:22:53,  7.11s/it]
 40%|███▉      | 11182/28080 [22:05:57<33:23:22,  7.11s/it]
                                                           
{'loss': 0.6202, 'learning_rate': 0.0003423275902412643, 'epoch': 4.78}

 40%|███▉      | 11182/28080 [22:05:57<33:23:22,  7.11s/it]
 40%|███▉      | 11183/28080 [22:06:04<33:27:25,  7.13s/it]
                                                           
{'loss': 0.6212, 'learning_rate': 0.00034230079242788316, 'epoch': 4.78}

 40%|███▉      | 11183/28080 [22:06:04<33:27:25,  7.13s/it]
 40%|███▉      | 11184/28080 [22:06:11<33:29:18,  7.14s/it]
                                                           
{'loss': 0.6426, 'learning_rate': 0.00034227399338653507, 'epoch': 4.78}

 40%|███▉      | 11184/28080 [22:06:11<33:29:18,  7.14s/it]
 40%|███▉      | 11185/28080 [22:06:18<33:24:47,  7.12s/it]
                                                           
{'loss': 0.6288, 'learning_rate': 0.0003422471931175768, 'epoch': 4.78}

 40%|███▉      | 11185/28080 [22:06:18<33:24:47,  7.12s/it]
 40%|███▉      | 11186/28080 [22:06:26<33:17:26,  7.09s/it]
                                                           
{'loss': 0.6454, 'learning_rate': 0.00034222039162136464, 'epoch': 4.78}

 40%|███▉      | 11186/28080 [22:06:26<33:17:26,  7.09s/it]
 40%|███▉      | 11187/28080 [22:06:33<33:13:56,  7.08s/it]
                                                           
{'loss': 0.6132, 'learning_rate': 0.00034219358889825543, 'epoch': 4.78}

 40%|███▉      | 11187/28080 [22:06:33<33:13:56,  7.08s/it]
 40%|███▉      | 11188/28080 [22:06:40<33:15:06,  7.09s/it]
                                                           
{'loss': 0.6277, 'learning_rate': 0.00034216678494860566, 'epoch': 4.78}

 40%|███▉      | 11188/28080 [22:06:40<33:15:06,  7.09s/it]
 40%|███▉      | 11189/28080 [22:06:47<33:14:10,  7.08s/it]
                                                           
{'loss': 0.6072, 'learning_rate': 0.0003421399797727718, 'epoch': 4.78}

 40%|███▉      | 11189/28080 [22:06:47<33:14:10,  7.08s/it]
 40%|███▉      | 11190/28080 [22:06:54<33:23:52,  7.12s/it]
                                                           
{'loss': 0.6208, 'learning_rate': 0.00034211317337111066, 'epoch': 4.78}

 40%|███▉      | 11190/28080 [22:06:54<33:23:52,  7.12s/it]
 40%|███▉      | 11191/28080 [22:07:01<33:17:51,  7.10s/it]
                                                           
{'loss': 0.6154, 'learning_rate': 0.0003420863657439787, 'epoch': 4.78}

 40%|███▉      | 11191/28080 [22:07:01<33:17:51,  7.10s/it]
 40%|███▉      | 11192/28080 [22:07:08<33:12:27,  7.08s/it]
                                                           
{'loss': 0.644, 'learning_rate': 0.0003420595568917327, 'epoch': 4.78}

 40%|███▉      | 11192/28080 [22:07:08<33:12:27,  7.08s/it]
 40%|███▉      | 11193/28080 [22:07:15<33:15:26,  7.09s/it]
                                                           
{'loss': 0.638, 'learning_rate': 0.00034203274681472923, 'epoch': 4.78}

 40%|███▉      | 11193/28080 [22:07:15<33:15:26,  7.09s/it]
 40%|███▉      | 11194/28080 [22:07:22<33:15:31,  7.09s/it]
                                                           
{'loss': 0.615, 'learning_rate': 0.00034200593551332505, 'epoch': 4.78}

 40%|███▉      | 11194/28080 [22:07:22<33:15:31,  7.09s/it]
 40%|███▉      | 11195/28080 [22:07:29<33:21:36,  7.11s/it]
                                                           
{'loss': 0.6297, 'learning_rate': 0.00034197912298787673, 'epoch': 4.78}

 40%|███▉      | 11195/28080 [22:07:29<33:21:36,  7.11s/it]
 40%|███▉      | 11196/28080 [22:07:36<33:21:24,  7.11s/it]
                                                           
{'loss': 0.6231, 'learning_rate': 0.00034195230923874114, 'epoch': 4.78}

 40%|███▉      | 11196/28080 [22:07:36<33:21:24,  7.11s/it]
 40%|███▉      | 11197/28080 [22:07:44<33:17:27,  7.10s/it]
                                                           
{'loss': 0.6244, 'learning_rate': 0.0003419254942662749, 'epoch': 4.78}

 40%|███▉      | 11197/28080 [22:07:44<33:17:27,  7.10s/it]
 40%|███▉      | 11198/28080 [22:07:51<33:18:41,  7.10s/it]
                                                           
{'loss': 0.6283, 'learning_rate': 0.00034189867807083487, 'epoch': 4.78}

 40%|███▉      | 11198/28080 [22:07:51<33:18:41,  7.10s/it]
 40%|███▉      | 11199/28080 [22:07:58<33:20:01,  7.11s/it]
                                                           
{'loss': 0.6136, 'learning_rate': 0.00034187186065277766, 'epoch': 4.78}

 40%|███▉      | 11199/28080 [22:07:58<33:20:01,  7.11s/it]
 40%|███▉      | 11200/28080 [22:08:05<33:20:22,  7.11s/it]
                                                           
{'loss': 0.6178, 'learning_rate': 0.00034184504201246015, 'epoch': 4.78}

 40%|███▉      | 11200/28080 [22:08:05<33:20:22,  7.11s/it]
 40%|███▉      | 11201/28080 [22:08:12<33:20:15,  7.11s/it]
                                                           
{'loss': 0.6317, 'learning_rate': 0.00034181822215023904, 'epoch': 4.78}

 40%|███▉      | 11201/28080 [22:08:12<33:20:15,  7.11s/it]
 40%|███▉      | 11202/28080 [22:08:19<33:18:11,  7.10s/it]
                                                           
{'loss': 0.6453, 'learning_rate': 0.00034179140106647136, 'epoch': 4.79}

 40%|███▉      | 11202/28080 [22:08:19<33:18:11,  7.10s/it]
 40%|███▉      | 11203/28080 [22:08:26<33:20:30,  7.11s/it]
                                                           
{'loss': 0.6459, 'learning_rate': 0.00034176457876151364, 'epoch': 4.79}

 40%|███▉      | 11203/28080 [22:08:26<33:20:30,  7.11s/it]
 40%|███▉      | 11204/28080 [22:08:33<33:10:51,  7.08s/it]
                                                           
{'loss': 0.6285, 'learning_rate': 0.00034173775523572286, 'epoch': 4.79}

 40%|███▉      | 11204/28080 [22:08:33<33:10:51,  7.08s/it]
 40%|███▉      | 11205/28080 [22:08:40<33:19:43,  7.11s/it]
                                                           
{'loss': 0.6413, 'learning_rate': 0.000341710930489456, 'epoch': 4.79}

 40%|███▉      | 11205/28080 [22:08:40<33:19:43,  7.11s/it]
 40%|███▉      | 11206/28080 [22:08:47<33:14:25,  7.09s/it]
                                                           
{'loss': 0.6353, 'learning_rate': 0.00034168410452306975, 'epoch': 4.79}

 40%|███▉      | 11206/28080 [22:08:47<33:14:25,  7.09s/it]
 40%|███▉      | 11207/28080 [22:08:55<33:15:00,  7.09s/it]
                                                           
{'loss': 0.6094, 'learning_rate': 0.0003416572773369211, 'epoch': 4.79}

 40%|███▉      | 11207/28080 [22:08:55<33:15:00,  7.09s/it]
 40%|███▉      | 11208/28080 [22:09:02<33:20:19,  7.11s/it]
                                                           
{'loss': 0.6195, 'learning_rate': 0.0003416304489313669, 'epoch': 4.79}

 40%|███▉      | 11208/28080 [22:09:02<33:20:19,  7.11s/it]
 40%|███▉      | 11209/28080 [22:09:09<33:06:37,  7.07s/it]
                                                           
{'loss': 0.6338, 'learning_rate': 0.00034160361930676413, 'epoch': 4.79}

 40%|███▉      | 11209/28080 [22:09:09<33:06:37,  7.07s/it]
 40%|███▉      | 11210/28080 [22:09:16<33:00:09,  7.04s/it]
                                                           
{'loss': 0.6312, 'learning_rate': 0.0003415767884634697, 'epoch': 4.79}

 40%|███▉      | 11210/28080 [22:09:16<33:00:09,  7.04s/it]
 40%|███▉      | 11211/28080 [22:09:23<33:03:58,  7.06s/it]
                                                           
{'loss': 0.6264, 'learning_rate': 0.00034154995640184056, 'epoch': 4.79}

 40%|███▉      | 11211/28080 [22:09:23<33:03:58,  7.06s/it]
 40%|███▉      | 11212/28080 [22:09:30<33:05:37,  7.06s/it]
                                                           
{'loss': 0.6293, 'learning_rate': 0.00034152312312223375, 'epoch': 4.79}

 40%|███▉      | 11212/28080 [22:09:30<33:05:37,  7.06s/it]
 40%|███▉      | 11213/28080 [22:09:37<33:11:02,  7.08s/it]
                                                           
{'loss': 0.6314, 'learning_rate': 0.00034149628862500616, 'epoch': 4.79}

 40%|███▉      | 11213/28080 [22:09:37<33:11:02,  7.08s/it]
 40%|███▉      | 11214/28080 [22:09:44<33:11:52,  7.09s/it]
                                                           
{'loss': 0.6391, 'learning_rate': 0.0003414694529105149, 'epoch': 4.79}

 40%|███▉      | 11214/28080 [22:09:44<33:11:52,  7.09s/it]
 40%|███▉      | 11215/28080 [22:09:51<33:12:53,  7.09s/it]
                                                           
{'loss': 0.5881, 'learning_rate': 0.00034144261597911685, 'epoch': 4.79}

 40%|███▉      | 11215/28080 [22:09:51<33:12:53,  7.09s/it]
 40%|███▉      | 11216/28080 [22:09:58<33:12:10,  7.09s/it]
                                                           
{'loss': 0.6141, 'learning_rate': 0.00034141577783116924, 'epoch': 4.79}

 40%|███▉      | 11216/28080 [22:09:58<33:12:10,  7.09s/it]
 40%|███▉      | 11217/28080 [22:10:05<33:13:21,  7.09s/it]
                                                           
{'loss': 0.6114, 'learning_rate': 0.00034138893846702895, 'epoch': 4.79}

 40%|███▉      | 11217/28080 [22:10:05<33:13:21,  7.09s/it]
 40%|███▉      | 11218/28080 [22:10:12<33:03:23,  7.06s/it]
                                                           
{'loss': 0.6324, 'learning_rate': 0.00034136209788705307, 'epoch': 4.79}

 40%|███▉      | 11218/28080 [22:10:12<33:03:23,  7.06s/it]
 40%|███▉      | 11219/28080 [22:10:19<32:58:37,  7.04s/it]
                                                           
{'loss': 0.6393, 'learning_rate': 0.00034133525609159884, 'epoch': 4.79}

 40%|███▉      | 11219/28080 [22:10:19<32:58:37,  7.04s/it]
 40%|███▉      | 11220/28080 [22:10:26<32:59:50,  7.05s/it]
                                                           
{'loss': 0.6174, 'learning_rate': 0.00034130841308102313, 'epoch': 4.79}

 40%|███▉      | 11220/28080 [22:10:26<32:59:50,  7.05s/it]
 40%|███▉      | 11221/28080 [22:10:33<33:01:07,  7.05s/it]
                                                           
{'loss': 0.6179, 'learning_rate': 0.0003412815688556832, 'epoch': 4.79}

 40%|███▉      | 11221/28080 [22:10:33<33:01:07,  7.05s/it]
 40%|███▉      | 11222/28080 [22:10:40<32:55:07,  7.03s/it]
                                                           
{'loss': 0.6223, 'learning_rate': 0.00034125472341593624, 'epoch': 4.79}

 40%|███▉      | 11222/28080 [22:10:40<32:55:07,  7.03s/it]
 40%|███▉      | 11223/28080 [22:10:48<33:01:12,  7.05s/it]
                                                           
{'loss': 0.6308, 'learning_rate': 0.0003412278767621393, 'epoch': 4.79}

 40%|███▉      | 11223/28080 [22:10:48<33:01:12,  7.05s/it]
 40%|███▉      | 11224/28080 [22:10:55<32:55:15,  7.03s/it]
                                                           
{'loss': 0.6277, 'learning_rate': 0.00034120102889464955, 'epoch': 4.79}

 40%|███▉      | 11224/28080 [22:10:55<32:55:15,  7.03s/it]
 40%|███▉      | 11225/28080 [22:11:02<32:59:52,  7.05s/it]
                                                           
{'loss': 0.6259, 'learning_rate': 0.00034117417981382423, 'epoch': 4.8}

 40%|███▉      | 11225/28080 [22:11:02<32:59:52,  7.05s/it]
 40%|███▉      | 11226/28080 [22:11:09<33:08:41,  7.08s/it]
                                                           
{'loss': 0.6285, 'learning_rate': 0.00034114732952002046, 'epoch': 4.8}

 40%|███▉      | 11226/28080 [22:11:09<33:08:41,  7.08s/it]
 40%|███▉      | 11227/28080 [22:11:16<33:08:55,  7.08s/it]
                                                           
{'loss': 0.6485, 'learning_rate': 0.00034112047801359554, 'epoch': 4.8}

 40%|███▉      | 11227/28080 [22:11:16<33:08:55,  7.08s/it]
 40%|███▉      | 11228/28080 [22:11:23<33:08:14,  7.08s/it]
                                                           
{'loss': 0.6181, 'learning_rate': 0.0003410936252949066, 'epoch': 4.8}

 40%|███▉      | 11228/28080 [22:11:23<33:08:14,  7.08s/it]
 40%|███▉      | 11229/28080 [22:11:30<33:10:42,  7.09s/it]
                                                           
{'loss': 0.6519, 'learning_rate': 0.000341066771364311, 'epoch': 4.8}

 40%|███▉      | 11229/28080 [22:11:30<33:10:42,  7.09s/it]
 40%|███▉      | 11230/28080 [22:11:37<33:15:26,  7.11s/it]
                                                           
{'loss': 0.6263, 'learning_rate': 0.000341039916222166, 'epoch': 4.8}

 40%|███▉      | 11230/28080 [22:11:37<33:15:26,  7.11s/it]
 40%|███▉      | 11231/28080 [22:11:44<33:19:28,  7.12s/it]
                                                           
{'loss': 0.6216, 'learning_rate': 0.0003410130598688288, 'epoch': 4.8}

 40%|███▉      | 11231/28080 [22:11:44<33:19:28,  7.12s/it]
 40%|████      | 11232/28080 [22:11:51<33:08:41,  7.08s/it]
                                                           
{'loss': 0.6362, 'learning_rate': 0.0003409862023046567, 'epoch': 4.8}

 40%|████      | 11232/28080 [22:11:51<33:08:41,  7.08s/it]
 40%|████      | 11233/28080 [22:11:58<33:06:07,  7.07s/it]
                                                           
{'loss': 0.6413, 'learning_rate': 0.0003409593435300071, 'epoch': 4.8}

 40%|████      | 11233/28080 [22:11:58<33:06:07,  7.07s/it]
 40%|████      | 11234/28080 [22:12:05<33:02:01,  7.06s/it]
                                                           
{'loss': 0.6327, 'learning_rate': 0.0003409324835452372, 'epoch': 4.8}

 40%|████      | 11234/28080 [22:12:05<33:02:01,  7.06s/it]
 40%|████      | 11235/28080 [22:12:12<32:51:53,  7.02s/it]
                                                           
{'loss': 0.6442, 'learning_rate': 0.00034090562235070446, 'epoch': 4.8}

 40%|████      | 11235/28080 [22:12:12<32:51:53,  7.02s/it]
 40%|████      | 11236/28080 [22:12:19<33:02:35,  7.06s/it]
                                                           
{'loss': 0.6265, 'learning_rate': 0.0003408787599467662, 'epoch': 4.8}

 40%|████      | 11236/28080 [22:12:19<33:02:35,  7.06s/it]
 40%|████      | 11237/28080 [22:12:26<32:57:13,  7.04s/it]
                                                           
{'loss': 0.63, 'learning_rate': 0.0003408518963337798, 'epoch': 4.8}

 40%|████      | 11237/28080 [22:12:26<32:57:13,  7.04s/it]
 40%|████      | 11238/28080 [22:12:34<32:54:41,  7.03s/it]
                                                           
{'loss': 0.6202, 'learning_rate': 0.00034082503151210266, 'epoch': 4.8}

 40%|████      | 11238/28080 [22:12:34<32:54:41,  7.03s/it]
 40%|████      | 11239/28080 [22:12:41<33:00:28,  7.06s/it]
                                                           
{'loss': 0.6083, 'learning_rate': 0.00034079816548209207, 'epoch': 4.8}

 40%|████      | 11239/28080 [22:12:41<33:00:28,  7.06s/it]
 40%|████      | 11240/28080 [22:12:48<32:52:52,  7.03s/it]
                                                           
{'loss': 0.6276, 'learning_rate': 0.0003407712982441057, 'epoch': 4.8}

 40%|████      | 11240/28080 [22:12:48<32:52:52,  7.03s/it]
 40%|████      | 11241/28080 [22:12:55<32:56:50,  7.04s/it]
                                                           
{'loss': 0.6154, 'learning_rate': 0.00034074442979850086, 'epoch': 4.8}

 40%|████      | 11241/28080 [22:12:55<32:56:50,  7.04s/it]
 40%|████      | 11242/28080 [22:13:02<33:00:43,  7.06s/it]
                                                           
{'loss': 0.6114, 'learning_rate': 0.0003407175601456349, 'epoch': 4.8}

 40%|████      | 11242/28080 [22:13:02<33:00:43,  7.06s/it]
 40%|████      | 11243/28080 [22:13:09<32:58:41,  7.05s/it]
                                                           
{'loss': 0.6155, 'learning_rate': 0.00034069068928586547, 'epoch': 4.8}

 40%|████      | 11243/28080 [22:13:09<32:58:41,  7.05s/it]
 40%|████      | 11244/28080 [22:13:16<32:48:58,  7.02s/it]
                                                           
{'loss': 0.6404, 'learning_rate': 0.00034066381721954984, 'epoch': 4.8}

 40%|████      | 11244/28080 [22:13:16<32:48:58,  7.02s/it]
 40%|████      | 11245/28080 [22:13:23<32:55:14,  7.04s/it]
                                                           
{'loss': 0.6193, 'learning_rate': 0.0003406369439470458, 'epoch': 4.8}

 40%|████      | 11245/28080 [22:13:23<32:55:14,  7.04s/it]
 40%|████      | 11246/28080 [22:13:30<33:06:42,  7.08s/it]
                                                           
{'loss': 0.613, 'learning_rate': 0.00034061006946871066, 'epoch': 4.8}

 40%|████      | 11246/28080 [22:13:30<33:06:42,  7.08s/it]
 40%|████      | 11247/28080 [22:13:37<33:02:25,  7.07s/it]
                                                           
{'loss': 0.624, 'learning_rate': 0.000340583193784902, 'epoch': 4.8}

 40%|████      | 11247/28080 [22:13:37<33:02:25,  7.07s/it]
 40%|████      | 11248/28080 [22:13:44<32:56:16,  7.04s/it]
                                                           
{'loss': 0.6247, 'learning_rate': 0.00034055631689597745, 'epoch': 4.81}

 40%|████      | 11248/28080 [22:13:44<32:56:16,  7.04s/it]
 40%|████      | 11249/28080 [22:13:51<32:52:46,  7.03s/it]
                                                           
{'loss': 0.6392, 'learning_rate': 0.00034052943880229447, 'epoch': 4.81}

 40%|████      | 11249/28080 [22:13:51<32:52:46,  7.03s/it]
 40%|████      | 11250/28080 [22:13:58<33:25:24,  7.15s/it]
                                                           
{'loss': 0.6168, 'learning_rate': 0.0003405025595042107, 'epoch': 4.81}

 40%|████      | 11250/28080 [22:13:58<33:25:24,  7.15s/it]
 40%|████      | 11251/28080 [22:14:05<33:14:09,  7.11s/it]
                                                           
{'loss': 0.6316, 'learning_rate': 0.00034047567900208375, 'epoch': 4.81}

 40%|████      | 11251/28080 [22:14:05<33:14:09,  7.11s/it]
 40%|████      | 11252/28080 [22:14:13<33:09:34,  7.09s/it]
                                                           
{'loss': 0.6413, 'learning_rate': 0.00034044879729627124, 'epoch': 4.81}

 40%|████      | 11252/28080 [22:14:13<33:09:34,  7.09s/it]
 40%|████      | 11253/28080 [22:14:20<33:10:14,  7.10s/it]
                                                           
{'loss': 0.6404, 'learning_rate': 0.0003404219143871309, 'epoch': 4.81}

 40%|████      | 11253/28080 [22:14:20<33:10:14,  7.10s/it]
 40%|████      | 11254/28080 [22:14:27<33:23:29,  7.14s/it]
                                                           
{'loss': 0.6284, 'learning_rate': 0.00034039503027502013, 'epoch': 4.81}

 40%|████      | 11254/28080 [22:14:27<33:23:29,  7.14s/it]
 40%|████      | 11255/28080 [22:14:34<33:18:38,  7.13s/it]
                                                           
{'loss': 0.6242, 'learning_rate': 0.00034036814496029677, 'epoch': 4.81}

 40%|████      | 11255/28080 [22:14:34<33:18:38,  7.13s/it]
 40%|████      | 11256/28080 [22:14:41<33:09:38,  7.10s/it]
                                                           
{'loss': 0.6285, 'learning_rate': 0.0003403412584433185, 'epoch': 4.81}

 40%|████      | 11256/28080 [22:14:41<33:09:38,  7.10s/it]
 40%|████      | 11257/28080 [22:14:48<33:08:12,  7.09s/it]
                                                           
{'loss': 0.6349, 'learning_rate': 0.000340314370724443, 'epoch': 4.81}

 40%|████      | 11257/28080 [22:14:48<33:08:12,  7.09s/it]
 40%|████      | 11258/28080 [22:14:55<33:12:00,  7.11s/it]
                                                           
{'loss': 0.6211, 'learning_rate': 0.0003402874818040279, 'epoch': 4.81}

 40%|████      | 11258/28080 [22:14:55<33:12:00,  7.11s/it]
 40%|████      | 11259/28080 [22:15:02<33:14:07,  7.11s/it]
                                                           
{'loss': 0.639, 'learning_rate': 0.000340260591682431, 'epoch': 4.81}

 40%|████      | 11259/28080 [22:15:02<33:14:07,  7.11s/it]
 40%|████      | 11260/28080 [22:15:09<33:12:23,  7.11s/it]
                                                           
{'loss': 0.6146, 'learning_rate': 0.0003402337003600101, 'epoch': 4.81}

 40%|████      | 11260/28080 [22:15:09<33:12:23,  7.11s/it]
 40%|████      | 11261/28080 [22:15:16<33:01:48,  7.07s/it]
                                                           
{'loss': 0.6368, 'learning_rate': 0.0003402068078371229, 'epoch': 4.81}

 40%|████      | 11261/28080 [22:15:16<33:01:48,  7.07s/it]
 40%|████      | 11262/28080 [22:15:24<33:06:06,  7.09s/it]
                                                           
{'loss': 0.6333, 'learning_rate': 0.0003401799141141272, 'epoch': 4.81}

 40%|████      | 11262/28080 [22:15:24<33:06:06,  7.09s/it]
 40%|████      | 11263/28080 [22:15:31<33:06:04,  7.09s/it]
                                                           
{'loss': 0.6262, 'learning_rate': 0.00034015301919138074, 'epoch': 4.81}

 40%|████      | 11263/28080 [22:15:31<33:06:04,  7.09s/it]
 40%|████      | 11264/28080 [22:15:38<32:57:27,  7.06s/it]
                                                           
{'loss': 0.6168, 'learning_rate': 0.0003401261230692414, 'epoch': 4.81}

 40%|████      | 11264/28080 [22:15:38<32:57:27,  7.06s/it]
 40%|████      | 11265/28080 [22:15:45<32:47:46,  7.02s/it]
                                                           
{'loss': 0.635, 'learning_rate': 0.0003400992257480669, 'epoch': 4.81}

 40%|████      | 11265/28080 [22:15:45<32:47:46,  7.02s/it]
 40%|████      | 11266/28080 [22:15:52<32:50:59,  7.03s/it]
                                                           
{'loss': 0.6089, 'learning_rate': 0.00034007232722821525, 'epoch': 4.81}

 40%|████      | 11266/28080 [22:15:52<32:50:59,  7.03s/it]
 40%|████      | 11267/28080 [22:15:59<32:59:42,  7.06s/it]
                                                           
{'loss': 0.6114, 'learning_rate': 0.0003400454275100442, 'epoch': 4.81}

 40%|████      | 11267/28080 [22:15:59<32:59:42,  7.06s/it]
 40%|████      | 11268/28080 [22:16:06<32:54:39,  7.05s/it]
                                                           
{'loss': 0.6094, 'learning_rate': 0.0003400185265939115, 'epoch': 4.81}

 40%|████      | 11268/28080 [22:16:06<32:54:39,  7.05s/it]
 40%|████      | 11269/28080 [22:16:13<32:59:50,  7.07s/it]
                                                           
{'loss': 0.6327, 'learning_rate': 0.0003399916244801753, 'epoch': 4.81}

 40%|████      | 11269/28080 [22:16:13<32:59:50,  7.07s/it]
 40%|████      | 11270/28080 [22:16:20<33:01:05,  7.07s/it]
                                                           
{'loss': 0.6066, 'learning_rate': 0.0003399647211691933, 'epoch': 4.81}

 40%|████      | 11270/28080 [22:16:20<33:01:05,  7.07s/it]
 40%|████      | 11271/28080 [22:16:27<32:59:20,  7.07s/it]
                                                           
{'loss': 0.6347, 'learning_rate': 0.0003399378166613235, 'epoch': 4.81}

 40%|████      | 11271/28080 [22:16:27<32:59:20,  7.07s/it]
 40%|████      | 11272/28080 [22:16:34<32:59:43,  7.07s/it]
                                                           
{'loss': 0.6361, 'learning_rate': 0.00033991091095692395, 'epoch': 4.82}

 40%|████      | 11272/28080 [22:16:34<32:59:43,  7.07s/it]
 40%|████      | 11273/28080 [22:16:41<33:03:47,  7.08s/it]
                                                           
{'loss': 0.6151, 'learning_rate': 0.00033988400405635235, 'epoch': 4.82}

 40%|████      | 11273/28080 [22:16:41<33:03:47,  7.08s/it]
 40%|████      | 11274/28080 [22:16:48<32:49:41,  7.03s/it]
                                                           
{'loss': 0.6255, 'learning_rate': 0.0003398570959599669, 'epoch': 4.82}

 40%|████      | 11274/28080 [22:16:48<32:49:41,  7.03s/it]
 40%|████      | 11275/28080 [22:16:55<32:53:40,  7.05s/it]
                                                           
{'loss': 0.6162, 'learning_rate': 0.00033983018666812535, 'epoch': 4.82}

 40%|████      | 11275/28080 [22:16:55<32:53:40,  7.05s/it]
 40%|████      | 11276/28080 [22:17:02<32:58:02,  7.06s/it]
                                                           
{'loss': 0.6308, 'learning_rate': 0.000339803276181186, 'epoch': 4.82}

 40%|████      | 11276/28080 [22:17:02<32:58:02,  7.06s/it]
 40%|████      | 11277/28080 [22:17:09<32:55:19,  7.05s/it]
                                                           
{'loss': 0.6109, 'learning_rate': 0.0003397763644995066, 'epoch': 4.82}

 40%|████      | 11277/28080 [22:17:09<32:55:19,  7.05s/it]
 40%|████      | 11278/28080 [22:17:16<32:59:35,  7.07s/it]
                                                           
{'loss': 0.6332, 'learning_rate': 0.00033974945162344527, 'epoch': 4.82}

 40%|████      | 11278/28080 [22:17:16<32:59:35,  7.07s/it]
 40%|████      | 11279/28080 [22:17:24<33:07:55,  7.10s/it]
                                                           
{'loss': 0.622, 'learning_rate': 0.0003397225375533602, 'epoch': 4.82}

 40%|████      | 11279/28080 [22:17:24<33:07:55,  7.10s/it]
 40%|████      | 11280/28080 [22:17:31<33:00:20,  7.07s/it]
                                                           
{'loss': 0.6269, 'learning_rate': 0.00033969562228960927, 'epoch': 4.82}

 40%|████      | 11280/28080 [22:17:31<33:00:20,  7.07s/it]
 40%|████      | 11281/28080 [22:17:38<32:54:53,  7.05s/it]
                                                           
{'loss': 0.6245, 'learning_rate': 0.0003396687058325506, 'epoch': 4.82}

 40%|████      | 11281/28080 [22:17:38<32:54:53,  7.05s/it]
 40%|████      | 11282/28080 [22:17:45<33:00:29,  7.07s/it]
                                                           
{'loss': 0.6031, 'learning_rate': 0.0003396417881825423, 'epoch': 4.82}

 40%|████      | 11282/28080 [22:17:45<33:00:29,  7.07s/it]
 40%|████      | 11283/28080 [22:17:52<32:52:02,  7.04s/it]
                                                           
{'loss': 0.6338, 'learning_rate': 0.00033961486933994245, 'epoch': 4.82}

 40%|████      | 11283/28080 [22:17:52<32:52:02,  7.04s/it]
 40%|████      | 11284/28080 [22:17:59<32:51:52,  7.04s/it]
                                                           
{'loss': 0.6239, 'learning_rate': 0.00033958794930510927, 'epoch': 4.82}

 40%|████      | 11284/28080 [22:17:59<32:51:52,  7.04s/it]
 40%|████      | 11285/28080 [22:18:06<32:56:32,  7.06s/it]
                                                           
{'loss': 0.6338, 'learning_rate': 0.0003395610280784008, 'epoch': 4.82}

 40%|████      | 11285/28080 [22:18:06<32:56:32,  7.06s/it]
 40%|████      | 11286/28080 [22:18:13<33:01:21,  7.08s/it]
                                                           
{'loss': 0.5937, 'learning_rate': 0.0003395341056601754, 'epoch': 4.82}

 40%|████      | 11286/28080 [22:18:13<33:01:21,  7.08s/it]
 40%|████      | 11287/28080 [22:18:20<32:58:16,  7.07s/it]
                                                           
{'loss': 0.6256, 'learning_rate': 0.0003395071820507909, 'epoch': 4.82}

 40%|████      | 11287/28080 [22:18:20<32:58:16,  7.07s/it]
 40%|████      | 11288/28080 [22:18:27<33:01:34,  7.08s/it]
                                                           
{'loss': 0.6148, 'learning_rate': 0.0003394802572506058, 'epoch': 4.82}

 40%|████      | 11288/28080 [22:18:27<33:01:34,  7.08s/it]
 40%|████      | 11289/28080 [22:18:34<32:48:15,  7.03s/it]
                                                           
{'loss': 0.6392, 'learning_rate': 0.00033945333125997814, 'epoch': 4.82}

 40%|████      | 11289/28080 [22:18:34<32:48:15,  7.03s/it]
 40%|████      | 11290/28080 [22:18:41<32:42:30,  7.01s/it]
                                                           
{'loss': 0.6303, 'learning_rate': 0.0003394264040792662, 'epoch': 4.82}

 40%|████      | 11290/28080 [22:18:41<32:42:30,  7.01s/it]
 40%|████      | 11291/28080 [22:18:48<32:41:39,  7.01s/it]
                                                           
{'loss': 0.6309, 'learning_rate': 0.0003393994757088282, 'epoch': 4.82}

 40%|████      | 11291/28080 [22:18:48<32:41:39,  7.01s/it]
 40%|████      | 11292/28080 [22:18:55<32:39:20,  7.00s/it]
                                                           
{'loss': 0.6275, 'learning_rate': 0.00033937254614902244, 'epoch': 4.82}

 40%|████      | 11292/28080 [22:18:55<32:39:20,  7.00s/it]
 40%|████      | 11293/28080 [22:19:02<32:45:22,  7.02s/it]
                                                           
{'loss': 0.622, 'learning_rate': 0.00033934561540020715, 'epoch': 4.82}

 40%|████      | 11293/28080 [22:19:02<32:45:22,  7.02s/it]
 40%|████      | 11294/28080 [22:19:09<32:46:56,  7.03s/it]
                                                           
{'loss': 0.6287, 'learning_rate': 0.0003393186834627406, 'epoch': 4.82}

 40%|████      | 11294/28080 [22:19:09<32:46:56,  7.03s/it]
 40%|████      | 11295/28080 [22:19:16<32:41:26,  7.01s/it]
                                                           
{'loss': 0.6241, 'learning_rate': 0.00033929175033698105, 'epoch': 4.83}

 40%|████      | 11295/28080 [22:19:16<32:41:26,  7.01s/it]
 40%|████      | 11296/28080 [22:19:23<32:43:40,  7.02s/it]
                                                           
{'loss': 0.621, 'learning_rate': 0.00033926481602328696, 'epoch': 4.83}

 40%|████      | 11296/28080 [22:19:23<32:43:40,  7.02s/it]
 40%|████      | 11297/28080 [22:19:30<32:49:26,  7.04s/it]
                                                           
{'loss': 0.6155, 'learning_rate': 0.00033923788052201656, 'epoch': 4.83}

 40%|████      | 11297/28080 [22:19:30<32:49:26,  7.04s/it]
 40%|████      | 11298/28080 [22:19:37<32:48:53,  7.04s/it]
                                                           
{'loss': 0.6249, 'learning_rate': 0.00033921094383352826, 'epoch': 4.83}

 40%|████      | 11298/28080 [22:19:37<32:48:53,  7.04s/it]
 40%|████      | 11299/28080 [22:19:44<32:58:17,  7.07s/it]
                                                           
{'loss': 0.6049, 'learning_rate': 0.0003391840059581803, 'epoch': 4.83}

 40%|████      | 11299/28080 [22:19:44<32:58:17,  7.07s/it]
 40%|████      | 11300/28080 [22:19:51<32:56:56,  7.07s/it]
                                                           
{'loss': 0.6319, 'learning_rate': 0.0003391570668963312, 'epoch': 4.83}

 40%|████      | 11300/28080 [22:19:51<32:56:56,  7.07s/it]
 40%|████      | 11301/28080 [22:19:59<32:56:26,  7.07s/it]
                                                           
{'loss': 0.6209, 'learning_rate': 0.0003391301266483393, 'epoch': 4.83}

 40%|████      | 11301/28080 [22:19:59<32:56:26,  7.07s/it]
 40%|████      | 11302/28080 [22:20:06<32:58:49,  7.08s/it]
                                                           
{'loss': 0.6209, 'learning_rate': 0.00033910318521456303, 'epoch': 4.83}

 40%|████      | 11302/28080 [22:20:06<32:58:49,  7.08s/it]
 40%|████      | 11303/28080 [22:20:13<32:55:10,  7.06s/it]
                                                           
{'loss': 0.6288, 'learning_rate': 0.0003390762425953608, 'epoch': 4.83}

 40%|████      | 11303/28080 [22:20:13<32:55:10,  7.06s/it]
 40%|████      | 11304/28080 [22:20:20<32:56:55,  7.07s/it]
                                                           
{'loss': 0.6408, 'learning_rate': 0.00033904929879109106, 'epoch': 4.83}

 40%|████      | 11304/28080 [22:20:20<32:56:55,  7.07s/it]
 40%|████      | 11305/28080 [22:20:27<33:04:07,  7.10s/it]
                                                           
{'loss': 0.6213, 'learning_rate': 0.0003390223538021122, 'epoch': 4.83}

 40%|████      | 11305/28080 [22:20:27<33:04:07,  7.10s/it]
 40%|████      | 11306/28080 [22:20:34<32:59:55,  7.08s/it]
                                                           
{'loss': 0.6172, 'learning_rate': 0.00033899540762878275, 'epoch': 4.83}

 40%|████      | 11306/28080 [22:20:34<32:59:55,  7.08s/it]
 40%|████      | 11307/28080 [22:20:41<33:02:59,  7.09s/it]
                                                           
{'loss': 0.6344, 'learning_rate': 0.00033896846027146134, 'epoch': 4.83}

 40%|████      | 11307/28080 [22:20:41<33:02:59,  7.09s/it]
 40%|████      | 11308/28080 [22:20:48<32:58:23,  7.08s/it]
                                                           
{'loss': 0.6056, 'learning_rate': 0.0003389415117305063, 'epoch': 4.83}

 40%|████      | 11308/28080 [22:20:48<32:58:23,  7.08s/it]
 40%|████      | 11309/28080 [22:20:55<32:51:10,  7.05s/it]
                                                           
{'loss': 0.6417, 'learning_rate': 0.00033891456200627615, 'epoch': 4.83}

 40%|████      | 11309/28080 [22:20:55<32:51:10,  7.05s/it]
 40%|████      | 11310/28080 [22:21:02<32:42:34,  7.02s/it]
                                                           
{'loss': 0.636, 'learning_rate': 0.0003388876110991296, 'epoch': 4.83}

 40%|████      | 11310/28080 [22:21:02<32:42:34,  7.02s/it]
 40%|████      | 11311/28080 [22:21:09<32:47:08,  7.04s/it]
                                                           
{'loss': 0.6021, 'learning_rate': 0.0003388606590094249, 'epoch': 4.83}

 40%|████      | 11311/28080 [22:21:09<32:47:08,  7.04s/it]
 40%|████      | 11312/28080 [22:21:16<32:49:08,  7.05s/it]
                                                           
{'loss': 0.6052, 'learning_rate': 0.0003388337057375209, 'epoch': 4.83}

 40%|████      | 11312/28080 [22:21:16<32:49:08,  7.05s/it]
 40%|████      | 11313/28080 [22:21:23<32:51:52,  7.06s/it]
                                                           
{'loss': 0.6337, 'learning_rate': 0.0003388067512837761, 'epoch': 4.83}

 40%|████      | 11313/28080 [22:21:23<32:51:52,  7.06s/it]
 40%|████      | 11314/28080 [22:21:30<32:46:19,  7.04s/it]
                                                           
{'loss': 0.6186, 'learning_rate': 0.0003387797956485491, 'epoch': 4.83}

 40%|████      | 11314/28080 [22:21:30<32:46:19,  7.04s/it]
 40%|████      | 11315/28080 [22:21:37<32:37:45,  7.01s/it]
                                                           
{'loss': 0.6436, 'learning_rate': 0.0003387528388321985, 'epoch': 4.83}

 40%|████      | 11315/28080 [22:21:37<32:37:45,  7.01s/it]
 40%|████      | 11316/28080 [22:21:44<32:41:47,  7.02s/it]
                                                           
{'loss': 0.6323, 'learning_rate': 0.000338725880835083, 'epoch': 4.83}

 40%|████      | 11316/28080 [22:21:44<32:41:47,  7.02s/it]
 40%|████      | 11317/28080 [22:21:51<32:42:02,  7.02s/it]
                                                           
{'loss': 0.6177, 'learning_rate': 0.0003386989216575611, 'epoch': 4.83}

 40%|████      | 11317/28080 [22:21:51<32:42:02,  7.02s/it]
 40%|████      | 11318/28080 [22:21:58<32:43:17,  7.03s/it]
                                                           
{'loss': 0.6252, 'learning_rate': 0.00033867196129999156, 'epoch': 4.83}

 40%|████      | 11318/28080 [22:21:58<32:43:17,  7.03s/it]
 40%|████      | 11319/28080 [22:22:05<32:50:26,  7.05s/it]
                                                           
{'loss': 0.6223, 'learning_rate': 0.0003386449997627331, 'epoch': 4.84}

 40%|████      | 11319/28080 [22:22:05<32:50:26,  7.05s/it]
 40%|████      | 11320/28080 [22:22:13<32:55:16,  7.07s/it]
                                                           
{'loss': 0.6324, 'learning_rate': 0.00033861803704614437, 'epoch': 4.84}

 40%|████      | 11320/28080 [22:22:13<32:55:16,  7.07s/it]
 40%|████      | 11321/28080 [22:22:20<32:59:01,  7.09s/it]
                                                           
{'loss': 0.647, 'learning_rate': 0.000338591073150584, 'epoch': 4.84}

 40%|████      | 11321/28080 [22:22:20<32:59:01,  7.09s/it]
 40%|████      | 11322/28080 [22:22:27<32:53:16,  7.07s/it]
                                                           
{'loss': 0.6471, 'learning_rate': 0.00033856410807641085, 'epoch': 4.84}

 40%|████      | 11322/28080 [22:22:27<32:53:16,  7.07s/it]
 40%|████      | 11323/28080 [22:22:34<32:55:15,  7.07s/it]
                                                           
{'loss': 0.6225, 'learning_rate': 0.0003385371418239836, 'epoch': 4.84}

 40%|████      | 11323/28080 [22:22:34<32:55:15,  7.07s/it]
 40%|████      | 11324/28080 [22:22:41<32:57:00,  7.08s/it]
                                                           
{'loss': 0.6359, 'learning_rate': 0.00033851017439366106, 'epoch': 4.84}

 40%|████      | 11324/28080 [22:22:41<32:57:00,  7.08s/it]
 40%|████      | 11325/28080 [22:22:48<32:56:36,  7.08s/it]
                                                           
{'loss': 0.6146, 'learning_rate': 0.0003384832057858019, 'epoch': 4.84}

 40%|████      | 11325/28080 [22:22:48<32:56:36,  7.08s/it]
 40%|████      | 11326/28080 [22:22:55<32:50:37,  7.06s/it]
                                                           
{'loss': 0.6307, 'learning_rate': 0.00033845623600076494, 'epoch': 4.84}

 40%|████      | 11326/28080 [22:22:55<32:50:37,  7.06s/it]
 40%|████      | 11327/28080 [22:23:02<32:50:34,  7.06s/it]
                                                           
{'loss': 0.6323, 'learning_rate': 0.00033842926503890907, 'epoch': 4.84}

 40%|████      | 11327/28080 [22:23:02<32:50:34,  7.06s/it]
 40%|████      | 11328/28080 [22:23:09<32:55:47,  7.08s/it]
                                                           
{'loss': 0.6243, 'learning_rate': 0.00033840229290059307, 'epoch': 4.84}

 40%|████      | 11328/28080 [22:23:09<32:55:47,  7.08s/it]
 40%|████      | 11329/28080 [22:23:16<32:57:29,  7.08s/it]
                                                           
{'loss': 0.6222, 'learning_rate': 0.00033837531958617575, 'epoch': 4.84}

 40%|████      | 11329/28080 [22:23:16<32:57:29,  7.08s/it]
 40%|████      | 11330/28080 [22:23:23<32:55:02,  7.07s/it]
                                                           
{'loss': 0.6378, 'learning_rate': 0.000338348345096016, 'epoch': 4.84}

 40%|████      | 11330/28080 [22:23:23<32:55:02,  7.07s/it]
 40%|████      | 11331/28080 [22:23:30<33:02:40,  7.10s/it]
                                                           
{'loss': 0.6226, 'learning_rate': 0.0003383213694304726, 'epoch': 4.84}

 40%|████      | 11331/28080 [22:23:30<33:02:40,  7.10s/it]
 40%|████      | 11332/28080 [22:23:37<32:55:02,  7.08s/it]
                                                           
{'loss': 0.6131, 'learning_rate': 0.00033829439258990454, 'epoch': 4.84}

 40%|████      | 11332/28080 [22:23:37<32:55:02,  7.08s/it]
 40%|████      | 11333/28080 [22:23:44<32:49:15,  7.06s/it]
                                                           
{'loss': 0.6324, 'learning_rate': 0.0003382674145746706, 'epoch': 4.84}

 40%|████      | 11333/28080 [22:23:44<32:49:15,  7.06s/it]
 40%|████      | 11334/28080 [22:23:52<32:51:25,  7.06s/it]
                                                           
{'loss': 0.6542, 'learning_rate': 0.00033824043538512987, 'epoch': 4.84}

 40%|████      | 11334/28080 [22:23:52<32:51:25,  7.06s/it]
 40%|████      | 11335/28080 [22:23:59<32:45:00,  7.04s/it]
                                                           
{'loss': 0.642, 'learning_rate': 0.00033821345502164116, 'epoch': 4.84}

 40%|████      | 11335/28080 [22:23:59<32:45:00,  7.04s/it]
 40%|████      | 11336/28080 [22:24:06<32:53:23,  7.07s/it]
                                                           
{'loss': 0.6256, 'learning_rate': 0.0003381864734845634, 'epoch': 4.84}

 40%|████      | 11336/28080 [22:24:06<32:53:23,  7.07s/it]
 40%|████      | 11337/28080 [22:24:13<32:56:21,  7.08s/it]
                                                           
{'loss': 0.6198, 'learning_rate': 0.0003381594907742556, 'epoch': 4.84}

 40%|████      | 11337/28080 [22:24:13<32:56:21,  7.08s/it]
 40%|████      | 11338/28080 [22:24:20<32:56:42,  7.08s/it]
                                                           
{'loss': 0.6065, 'learning_rate': 0.0003381325068910767, 'epoch': 4.84}

 40%|████      | 11338/28080 [22:24:20<32:56:42,  7.08s/it]
 40%|████      | 11339/28080 [22:24:27<32:57:41,  7.09s/it]
                                                           
{'loss': 0.6288, 'learning_rate': 0.0003381055218353858, 'epoch': 4.84}

 40%|████      | 11339/28080 [22:24:27<32:57:41,  7.09s/it]
 40%|████      | 11340/28080 [22:24:34<32:54:41,  7.08s/it]
                                                           
{'loss': 0.6409, 'learning_rate': 0.00033807853560754173, 'epoch': 4.84}

 40%|████      | 11340/28080 [22:24:34<32:54:41,  7.08s/it]
 40%|████      | 11341/28080 [22:24:41<32:57:30,  7.09s/it]
                                                           
{'loss': 0.6249, 'learning_rate': 0.0003380515482079037, 'epoch': 4.84}

 40%|████      | 11341/28080 [22:24:41<32:57:30,  7.09s/it]
 40%|████      | 11342/28080 [22:24:48<33:01:05,  7.10s/it]
                                                           
{'loss': 0.6225, 'learning_rate': 0.0003380245596368306, 'epoch': 4.85}

 40%|████      | 11342/28080 [22:24:48<33:01:05,  7.10s/it]
 40%|████      | 11343/28080 [22:24:55<32:59:24,  7.10s/it]
                                                           
{'loss': 0.6169, 'learning_rate': 0.0003379975698946815, 'epoch': 4.85}

 40%|████      | 11343/28080 [22:24:55<32:59:24,  7.10s/it]
 40%|████      | 11344/28080 [22:25:02<32:56:52,  7.09s/it]
                                                           
{'loss': 0.6146, 'learning_rate': 0.0003379705789818156, 'epoch': 4.85}

 40%|████      | 11344/28080 [22:25:02<32:56:52,  7.09s/it]
 40%|████      | 11345/28080 [22:25:09<32:47:49,  7.06s/it]
                                                           
{'loss': 0.6264, 'learning_rate': 0.00033794358689859185, 'epoch': 4.85}

 40%|████      | 11345/28080 [22:25:09<32:47:49,  7.06s/it]
 40%|████      | 11346/28080 [22:25:17<32:56:29,  7.09s/it]
                                                           
{'loss': 0.6297, 'learning_rate': 0.0003379165936453694, 'epoch': 4.85}

 40%|████      | 11346/28080 [22:25:17<32:56:29,  7.09s/it]
 40%|████      | 11347/28080 [22:25:24<33:02:43,  7.11s/it]
                                                           
{'loss': 0.6498, 'learning_rate': 0.0003378895992225074, 'epoch': 4.85}

 40%|████      | 11347/28080 [22:25:24<33:02:43,  7.11s/it]
 40%|████      | 11348/28080 [22:25:31<32:56:59,  7.09s/it]
                                                           
{'loss': 0.6294, 'learning_rate': 0.00033786260363036496, 'epoch': 4.85}

 40%|████      | 11348/28080 [22:25:31<32:56:59,  7.09s/it]
 40%|████      | 11349/28080 [22:25:38<32:54:52,  7.08s/it]
                                                           
{'loss': 0.6077, 'learning_rate': 0.0003378356068693012, 'epoch': 4.85}

 40%|████      | 11349/28080 [22:25:38<32:54:52,  7.08s/it]
 40%|████      | 11350/28080 [22:25:45<32:55:05,  7.08s/it]
                                                           
{'loss': 0.6113, 'learning_rate': 0.0003378086089396753, 'epoch': 4.85}

 40%|████      | 11350/28080 [22:25:45<32:55:05,  7.08s/it]
 40%|████      | 11351/28080 [22:25:52<32:50:17,  7.07s/it]
                                                           
{'loss': 0.6159, 'learning_rate': 0.00033778160984184645, 'epoch': 4.85}

 40%|████      | 11351/28080 [22:25:52<32:50:17,  7.07s/it]
 40%|████      | 11352/28080 [22:25:59<32:53:39,  7.08s/it]
                                                           
{'loss': 0.6233, 'learning_rate': 0.0003377546095761739, 'epoch': 4.85}

 40%|████      | 11352/28080 [22:25:59<32:53:39,  7.08s/it]
 40%|████      | 11353/28080 [22:26:06<33:02:35,  7.11s/it]
                                                           
{'loss': 0.6194, 'learning_rate': 0.00033772760814301675, 'epoch': 4.85}

 40%|████      | 11353/28080 [22:26:06<33:02:35,  7.11s/it]
 40%|████      | 11354/28080 [22:26:13<33:00:45,  7.11s/it]
                                                           
{'loss': 0.6497, 'learning_rate': 0.00033770060554273425, 'epoch': 4.85}

 40%|████      | 11354/28080 [22:26:13<33:00:45,  7.11s/it]
 40%|████      | 11355/28080 [22:26:20<32:47:39,  7.06s/it]
                                                           
{'loss': 0.6447, 'learning_rate': 0.0003376736017756857, 'epoch': 4.85}

 40%|████      | 11355/28080 [22:26:20<32:47:39,  7.06s/it]
 40%|████      | 11356/28080 [22:26:27<32:35:21,  7.02s/it]
                                                           
{'loss': 0.6383, 'learning_rate': 0.0003376465968422303, 'epoch': 4.85}

 40%|████      | 11356/28080 [22:26:27<32:35:21,  7.02s/it]
 40%|████      | 11357/28080 [22:26:34<32:36:14,  7.02s/it]
                                                           
{'loss': 0.6182, 'learning_rate': 0.00033761959074272735, 'epoch': 4.85}

 40%|████      | 11357/28080 [22:26:34<32:36:14,  7.02s/it]
 40%|████      | 11358/28080 [22:26:41<32:37:52,  7.03s/it]
                                                           
{'loss': 0.6296, 'learning_rate': 0.0003375925834775362, 'epoch': 4.85}

 40%|████      | 11358/28080 [22:26:41<32:37:52,  7.03s/it]
 40%|████      | 11359/28080 [22:26:48<32:41:12,  7.04s/it]
                                                           
{'loss': 0.6104, 'learning_rate': 0.00033756557504701604, 'epoch': 4.85}

 40%|████      | 11359/28080 [22:26:48<32:41:12,  7.04s/it]
 40%|████      | 11360/28080 [22:26:55<32:45:50,  7.05s/it]
                                                           
{'loss': 0.6309, 'learning_rate': 0.0003375385654515262, 'epoch': 4.85}

 40%|████      | 11360/28080 [22:26:55<32:45:50,  7.05s/it]
 40%|████      | 11361/28080 [22:27:02<32:43:18,  7.05s/it]
                                                           
{'loss': 0.6345, 'learning_rate': 0.0003375115546914261, 'epoch': 4.85}

 40%|████      | 11361/28080 [22:27:02<32:43:18,  7.05s/it]
 40%|████      | 11362/28080 [22:27:09<32:34:18,  7.01s/it]
                                                           
{'loss': 0.6373, 'learning_rate': 0.0003374845427670751, 'epoch': 4.85}

 40%|████      | 11362/28080 [22:27:09<32:34:18,  7.01s/it]
 40%|████      | 11363/28080 [22:27:17<32:43:31,  7.05s/it]
                                                           
{'loss': 0.61, 'learning_rate': 0.0003374575296788324, 'epoch': 4.85}

 40%|████      | 11363/28080 [22:27:17<32:43:31,  7.05s/it]
 40%|████      | 11364/28080 [22:27:24<32:42:42,  7.04s/it]
                                                           
{'loss': 0.602, 'learning_rate': 0.00033743051542705753, 'epoch': 4.85}

 40%|████      | 11364/28080 [22:27:24<32:42:42,  7.04s/it]
 40%|████      | 11365/28080 [22:27:31<32:46:58,  7.06s/it]
                                                           
{'loss': 0.6145, 'learning_rate': 0.0003374035000121099, 'epoch': 4.86}

 40%|████      | 11365/28080 [22:27:31<32:46:58,  7.06s/it]
 40%|████      | 11366/28080 [22:27:38<32:41:24,  7.04s/it]
                                                           
{'loss': 0.6166, 'learning_rate': 0.0003373764834343489, 'epoch': 4.86}

 40%|████      | 11366/28080 [22:27:38<32:41:24,  7.04s/it]
 40%|████      | 11367/28080 [22:27:45<32:40:38,  7.04s/it]
                                                           
{'loss': 0.6085, 'learning_rate': 0.00033734946569413383, 'epoch': 4.86}

 40%|████      | 11367/28080 [22:27:45<32:40:38,  7.04s/it]
 40%|████      | 11368/28080 [22:27:52<32:45:40,  7.06s/it]
                                                           
{'loss': 0.6289, 'learning_rate': 0.00033732244679182433, 'epoch': 4.86}

 40%|████      | 11368/28080 [22:27:52<32:45:40,  7.06s/it]
 40%|████      | 11369/28080 [22:27:59<32:43:20,  7.05s/it]
                                                           
{'loss': 0.648, 'learning_rate': 0.0003372954267277797, 'epoch': 4.86}

 40%|████      | 11369/28080 [22:27:59<32:43:20,  7.05s/it]
 40%|████      | 11370/28080 [22:28:06<32:37:26,  7.03s/it]
                                                           
{'loss': 0.6478, 'learning_rate': 0.0003372684055023595, 'epoch': 4.86}

 40%|████      | 11370/28080 [22:28:06<32:37:26,  7.03s/it]
 40%|████      | 11371/28080 [22:28:13<32:40:36,  7.04s/it]
                                                           
{'loss': 0.6207, 'learning_rate': 0.0003372413831159231, 'epoch': 4.86}

 40%|████      | 11371/28080 [22:28:13<32:40:36,  7.04s/it]
 40%|████      | 11372/28080 [22:28:20<32:38:03,  7.03s/it]
                                                           
{'loss': 0.6395, 'learning_rate': 0.00033721435956883024, 'epoch': 4.86}

 40%|████      | 11372/28080 [22:28:20<32:38:03,  7.03s/it]
 41%|████      | 11373/28080 [22:28:27<32:41:26,  7.04s/it]
                                                           
{'loss': 0.6347, 'learning_rate': 0.00033718733486144014, 'epoch': 4.86}

 41%|████      | 11373/28080 [22:28:27<32:41:26,  7.04s/it]
 41%|████      | 11374/28080 [22:28:34<32:46:04,  7.06s/it]
                                                           
{'loss': 0.6165, 'learning_rate': 0.0003371603089941126, 'epoch': 4.86}

 41%|████      | 11374/28080 [22:28:34<32:46:04,  7.06s/it]
 41%|████      | 11375/28080 [22:28:41<32:49:48,  7.08s/it]
                                                           
{'loss': 0.5976, 'learning_rate': 0.0003371332819672071, 'epoch': 4.86}

 41%|████      | 11375/28080 [22:28:41<32:49:48,  7.08s/it]
 41%|████      | 11376/28080 [22:28:48<32:54:41,  7.09s/it]
                                                           
{'loss': 0.6179, 'learning_rate': 0.0003371062537810831, 'epoch': 4.86}

 41%|████      | 11376/28080 [22:28:48<32:54:41,  7.09s/it]
 41%|████      | 11377/28080 [22:28:55<32:52:24,  7.09s/it]
                                                           
{'loss': 0.6207, 'learning_rate': 0.00033707922443610035, 'epoch': 4.86}

 41%|████      | 11377/28080 [22:28:55<32:52:24,  7.09s/it]
 41%|████      | 11378/28080 [22:29:02<32:49:50,  7.08s/it]
                                                           
{'loss': 0.6181, 'learning_rate': 0.0003370521939326182, 'epoch': 4.86}

 41%|████      | 11378/28080 [22:29:02<32:49:50,  7.08s/it]
 41%|████      | 11379/28080 [22:29:09<32:46:58,  7.07s/it]
                                                           
{'loss': 0.6273, 'learning_rate': 0.0003370251622709966, 'epoch': 4.86}

 41%|████      | 11379/28080 [22:29:09<32:46:58,  7.07s/it]
 41%|████      | 11380/28080 [22:29:16<32:43:07,  7.05s/it]
                                                           
{'loss': 0.622, 'learning_rate': 0.00033699812945159487, 'epoch': 4.86}

 41%|████      | 11380/28080 [22:29:16<32:43:07,  7.05s/it]
 41%|████      | 11381/28080 [22:29:24<32:44:24,  7.06s/it]
                                                           
{'loss': 0.6195, 'learning_rate': 0.00033697109547477276, 'epoch': 4.86}

 41%|████      | 11381/28080 [22:29:24<32:44:24,  7.06s/it]
 41%|████      | 11382/28080 [22:29:31<32:52:07,  7.09s/it]
                                                           
{'loss': 0.6272, 'learning_rate': 0.00033694406034089005, 'epoch': 4.86}

 41%|████      | 11382/28080 [22:29:31<32:52:07,  7.09s/it]
 41%|████      | 11383/28080 [22:29:38<32:54:00,  7.09s/it]
                                                           
{'loss': 0.616, 'learning_rate': 0.00033691702405030623, 'epoch': 4.86}

 41%|████      | 11383/28080 [22:29:38<32:54:00,  7.09s/it]
 41%|████      | 11384/28080 [22:29:45<32:53:27,  7.09s/it]
                                                           
{'loss': 0.6159, 'learning_rate': 0.0003368899866033811, 'epoch': 4.86}

 41%|████      | 11384/28080 [22:29:45<32:53:27,  7.09s/it]
 41%|████      | 11385/28080 [22:29:52<32:55:13,  7.10s/it]
                                                           
{'loss': 0.6016, 'learning_rate': 0.00033686294800047435, 'epoch': 4.86}

 41%|████      | 11385/28080 [22:29:52<32:55:13,  7.10s/it]
 41%|████      | 11386/28080 [22:29:59<32:53:05,  7.09s/it]
                                                           
{'loss': 0.6042, 'learning_rate': 0.0003368359082419457, 'epoch': 4.86}

 41%|████      | 11386/28080 [22:29:59<32:53:05,  7.09s/it]
 41%|████      | 11387/28080 [22:30:06<32:51:05,  7.08s/it]
                                                           
{'loss': 0.6156, 'learning_rate': 0.00033680886732815484, 'epoch': 4.86}

 41%|████      | 11387/28080 [22:30:06<32:51:05,  7.08s/it]
 41%|████      | 11388/28080 [22:30:13<32:52:40,  7.09s/it]
                                                           
{'loss': 0.6246, 'learning_rate': 0.00033678182525946154, 'epoch': 4.86}

 41%|████      | 11388/28080 [22:30:13<32:52:40,  7.09s/it]
 41%|████      | 11389/28080 [22:30:20<32:59:16,  7.11s/it]
                                                           
{'loss': 0.6212, 'learning_rate': 0.00033675478203622563, 'epoch': 4.87}

 41%|████      | 11389/28080 [22:30:20<32:59:16,  7.11s/it]
 41%|████      | 11390/28080 [22:30:28<32:56:53,  7.11s/it]
                                                           
{'loss': 0.6342, 'learning_rate': 0.0003367277376588068, 'epoch': 4.87}

 41%|████      | 11390/28080 [22:30:28<32:56:53,  7.11s/it]
 41%|████      | 11391/28080 [22:30:35<33:02:18,  7.13s/it]
                                                           
{'loss': 0.6295, 'learning_rate': 0.00033670069212756495, 'epoch': 4.87}

 41%|████      | 11391/28080 [22:30:35<33:02:18,  7.13s/it]
 41%|████      | 11392/28080 [22:30:42<32:51:12,  7.09s/it]
                                                           
{'loss': 0.6312, 'learning_rate': 0.0003366736454428598, 'epoch': 4.87}

 41%|████      | 11392/28080 [22:30:42<32:51:12,  7.09s/it]
 41%|████      | 11393/28080 [22:30:49<32:44:02,  7.06s/it]
                                                           
{'loss': 0.6187, 'learning_rate': 0.00033664659760505123, 'epoch': 4.87}

 41%|████      | 11393/28080 [22:30:49<32:44:02,  7.06s/it]
 41%|████      | 11394/28080 [22:30:56<32:47:22,  7.07s/it]
                                                           
{'loss': 0.6185, 'learning_rate': 0.00033661954861449907, 'epoch': 4.87}

 41%|████      | 11394/28080 [22:30:56<32:47:22,  7.07s/it]
 41%|████      | 11395/28080 [22:31:03<32:43:03,  7.06s/it]
                                                           
{'loss': 0.6175, 'learning_rate': 0.00033659249847156316, 'epoch': 4.87}

 41%|████      | 11395/28080 [22:31:03<32:43:03,  7.06s/it]
 41%|████      | 11396/28080 [22:31:10<32:43:55,  7.06s/it]
                                                           
{'loss': 0.6061, 'learning_rate': 0.0003365654471766034, 'epoch': 4.87}

 41%|████      | 11396/28080 [22:31:10<32:43:55,  7.06s/it]
 41%|████      | 11397/28080 [22:31:17<32:33:16,  7.02s/it]
                                                           
{'loss': 0.6296, 'learning_rate': 0.00033653839472997966, 'epoch': 4.87}

 41%|████      | 11397/28080 [22:31:17<32:33:16,  7.02s/it]
 41%|████      | 11398/28080 [22:31:24<32:23:38,  6.99s/it]
                                                           
{'loss': 0.6407, 'learning_rate': 0.00033651134113205186, 'epoch': 4.87}

 41%|████      | 11398/28080 [22:31:24<32:23:38,  6.99s/it]
 41%|████      | 11399/28080 [22:31:31<32:24:44,  7.00s/it]
                                                           
{'loss': 0.6188, 'learning_rate': 0.0003364842863831799, 'epoch': 4.87}

 41%|████      | 11399/28080 [22:31:31<32:24:44,  7.00s/it]
 41%|████      | 11400/28080 [22:31:38<32:27:38,  7.01s/it]
                                                           
{'loss': 0.6233, 'learning_rate': 0.0003364572304837237, 'epoch': 4.87}

 41%|████      | 11400/28080 [22:31:38<32:27:38,  7.01s/it]
 41%|████      | 11401/28080 [22:31:45<32:38:12,  7.04s/it]
                                                           
{'loss': 0.6271, 'learning_rate': 0.00033643017343404336, 'epoch': 4.87}

 41%|████      | 11401/28080 [22:31:45<32:38:12,  7.04s/it]
 41%|████      | 11402/28080 [22:31:52<32:39:42,  7.05s/it]
                                                           
{'loss': 0.6046, 'learning_rate': 0.00033640311523449863, 'epoch': 4.87}

 41%|████      | 11402/28080 [22:31:52<32:39:42,  7.05s/it]
 41%|████      | 11403/28080 [22:31:59<32:41:47,  7.06s/it]
                                                           
{'loss': 0.6119, 'learning_rate': 0.00033637605588544964, 'epoch': 4.87}

 41%|████      | 11403/28080 [22:31:59<32:41:47,  7.06s/it]
 41%|████      | 11404/28080 [22:32:06<32:49:44,  7.09s/it]
                                                           
{'loss': 0.6232, 'learning_rate': 0.0003363489953872563, 'epoch': 4.87}

 41%|████      | 11404/28080 [22:32:06<32:49:44,  7.09s/it]
 41%|████      | 11405/28080 [22:32:13<32:49:02,  7.09s/it]
                                                           
{'loss': 0.6255, 'learning_rate': 0.00033632193374027856, 'epoch': 4.87}

 41%|████      | 11405/28080 [22:32:13<32:49:02,  7.09s/it]
 41%|████      | 11406/28080 [22:32:20<32:52:23,  7.10s/it]
                                                           
{'loss': 0.6207, 'learning_rate': 0.0003362948709448767, 'epoch': 4.87}

 41%|████      | 11406/28080 [22:32:20<32:52:23,  7.10s/it]
 41%|████      | 11407/28080 [22:32:28<32:53:00,  7.10s/it]
                                                           
{'loss': 0.6276, 'learning_rate': 0.00033626780700141053, 'epoch': 4.87}

 41%|████      | 11407/28080 [22:32:28<32:53:00,  7.10s/it]
 41%|████      | 11408/28080 [22:32:35<32:47:38,  7.08s/it]
                                                           
{'loss': 0.6346, 'learning_rate': 0.00033624074191024024, 'epoch': 4.87}

 41%|████      | 11408/28080 [22:32:35<32:47:38,  7.08s/it]
 41%|████      | 11409/28080 [22:32:42<32:54:07,  7.11s/it]
                                                           
{'loss': 0.6338, 'learning_rate': 0.0003362136756717258, 'epoch': 4.87}

 41%|████      | 11409/28080 [22:32:42<32:54:07,  7.11s/it]
 41%|████      | 11410/28080 [22:32:49<32:54:41,  7.11s/it]
                                                           
{'loss': 0.5994, 'learning_rate': 0.00033618660828622736, 'epoch': 4.87}

 41%|████      | 11410/28080 [22:32:49<32:54:41,  7.11s/it]
 41%|████      | 11411/28080 [22:32:56<32:42:26,  7.06s/it]
                                                           
{'loss': 0.6235, 'learning_rate': 0.000336159539754105, 'epoch': 4.87}

 41%|████      | 11411/28080 [22:32:56<32:42:26,  7.06s/it]
 41%|████      | 11412/28080 [22:33:03<32:44:03,  7.07s/it]
                                                           
{'loss': 0.6441, 'learning_rate': 0.0003361324700757189, 'epoch': 4.88}

 41%|████      | 11412/28080 [22:33:03<32:44:03,  7.07s/it]
 41%|████      | 11413/28080 [22:33:10<32:36:22,  7.04s/it]
                                                           
{'loss': 0.6416, 'learning_rate': 0.0003361053992514291, 'epoch': 4.88}

 41%|████      | 11413/28080 [22:33:10<32:36:22,  7.04s/it]
 41%|████      | 11414/28080 [22:33:17<32:30:59,  7.02s/it]
                                                           
{'loss': 0.6328, 'learning_rate': 0.00033607832728159583, 'epoch': 4.88}

 41%|████      | 11414/28080 [22:33:17<32:30:59,  7.02s/it]
 41%|████      | 11415/28080 [22:33:24<32:29:26,  7.02s/it]
                                                           
{'loss': 0.6271, 'learning_rate': 0.0003360512541665792, 'epoch': 4.88}

 41%|████      | 11415/28080 [22:33:24<32:29:26,  7.02s/it]
 41%|████      | 11416/28080 [22:33:31<32:36:39,  7.05s/it]
                                                           
{'loss': 0.6413, 'learning_rate': 0.0003360241799067394, 'epoch': 4.88}

 41%|████      | 11416/28080 [22:33:31<32:36:39,  7.05s/it]
 41%|████      | 11417/28080 [22:33:38<32:46:22,  7.08s/it]
                                                           
{'loss': 0.6255, 'learning_rate': 0.0003359971045024366, 'epoch': 4.88}

 41%|████      | 11417/28080 [22:33:38<32:46:22,  7.08s/it]
 41%|████      | 11418/28080 [22:33:45<32:50:00,  7.09s/it]
                                                           
{'loss': 0.6121, 'learning_rate': 0.00033597002795403107, 'epoch': 4.88}

 41%|████      | 11418/28080 [22:33:45<32:50:00,  7.09s/it]
 41%|████      | 11419/28080 [22:33:52<32:42:40,  7.07s/it]
                                                           
{'loss': 0.6203, 'learning_rate': 0.00033594295026188306, 'epoch': 4.88}

 41%|████      | 11419/28080 [22:33:52<32:42:40,  7.07s/it]
 41%|████      | 11420/28080 [22:33:59<32:42:22,  7.07s/it]
                                                           
{'loss': 0.6199, 'learning_rate': 0.00033591587142635273, 'epoch': 4.88}

 41%|████      | 11420/28080 [22:33:59<32:42:22,  7.07s/it]
 41%|████      | 11421/28080 [22:34:06<32:34:12,  7.04s/it]
                                                           
{'loss': 0.6115, 'learning_rate': 0.0003358887914478003, 'epoch': 4.88}

 41%|████      | 11421/28080 [22:34:06<32:34:12,  7.04s/it]
 41%|████      | 11422/28080 [22:34:13<32:30:27,  7.03s/it]
                                                           
{'loss': 0.6409, 'learning_rate': 0.00033586171032658614, 'epoch': 4.88}

 41%|████      | 11422/28080 [22:34:13<32:30:27,  7.03s/it]
 41%|████      | 11423/28080 [22:34:20<32:43:01,  7.07s/it]
                                                           
{'loss': 0.6154, 'learning_rate': 0.00033583462806307054, 'epoch': 4.88}

 41%|████      | 11423/28080 [22:34:20<32:43:01,  7.07s/it]
 41%|████      | 11424/28080 [22:34:28<32:45:11,  7.08s/it]
                                                           
{'loss': 0.6211, 'learning_rate': 0.0003358075446576137, 'epoch': 4.88}

 41%|████      | 11424/28080 [22:34:28<32:45:11,  7.08s/it]
 41%|████      | 11425/28080 [22:34:35<32:58:22,  7.13s/it]
                                                           
{'loss': 0.6378, 'learning_rate': 0.00033578046011057604, 'epoch': 4.88}

 41%|████      | 11425/28080 [22:34:35<32:58:22,  7.13s/it]
 41%|████      | 11426/28080 [22:34:42<32:50:55,  7.10s/it]
                                                           
{'loss': 0.6323, 'learning_rate': 0.0003357533744223179, 'epoch': 4.88}

 41%|████      | 11426/28080 [22:34:42<32:50:55,  7.10s/it]
 41%|████      | 11427/28080 [22:34:49<32:51:07,  7.10s/it]
                                                           
{'loss': 0.6258, 'learning_rate': 0.0003357262875931996, 'epoch': 4.88}

 41%|████      | 11427/28080 [22:34:49<32:51:07,  7.10s/it]
 41%|████      | 11428/28080 [22:34:56<32:49:52,  7.10s/it]
                                                           
{'loss': 0.6405, 'learning_rate': 0.0003356991996235813, 'epoch': 4.88}

 41%|████      | 11428/28080 [22:34:56<32:49:52,  7.10s/it]
 41%|████      | 11429/28080 [22:35:03<32:48:39,  7.09s/it]
                                                           
{'loss': 0.6553, 'learning_rate': 0.0003356721105138237, 'epoch': 4.88}

 41%|████      | 11429/28080 [22:35:03<32:48:39,  7.09s/it]
 41%|████      | 11430/28080 [22:35:10<32:46:39,  7.09s/it]
                                                           
{'loss': 0.6128, 'learning_rate': 0.0003356450202642871, 'epoch': 4.88}

 41%|████      | 11430/28080 [22:35:10<32:46:39,  7.09s/it]
 41%|████      | 11431/28080 [22:35:17<32:41:18,  7.07s/it]
                                                           
{'loss': 0.5989, 'learning_rate': 0.0003356179288753317, 'epoch': 4.88}

 41%|████      | 11431/28080 [22:35:17<32:41:18,  7.07s/it]
 41%|████      | 11432/28080 [22:35:24<32:41:03,  7.07s/it]
                                                           
{'loss': 0.6308, 'learning_rate': 0.00033559083634731825, 'epoch': 4.88}

 41%|████      | 11432/28080 [22:35:24<32:41:03,  7.07s/it]
 41%|████      | 11433/28080 [22:35:31<32:41:08,  7.07s/it]
                                                           
{'loss': 0.6104, 'learning_rate': 0.00033556374268060683, 'epoch': 4.88}

 41%|████      | 11433/28080 [22:35:31<32:41:08,  7.07s/it]
 41%|████      | 11434/28080 [22:35:38<32:38:54,  7.06s/it]
                                                           
{'loss': 0.6219, 'learning_rate': 0.00033553664787555826, 'epoch': 4.88}

 41%|████      | 11434/28080 [22:35:38<32:38:54,  7.06s/it]
 41%|████      | 11435/28080 [22:35:45<32:31:11,  7.03s/it]
                                                           
{'loss': 0.6262, 'learning_rate': 0.0003355095519325327, 'epoch': 4.88}

 41%|████      | 11435/28080 [22:35:45<32:31:11,  7.03s/it]
 41%|████      | 11436/28080 [22:35:52<32:28:48,  7.03s/it]
                                                           
{'loss': 0.6402, 'learning_rate': 0.00033548245485189086, 'epoch': 4.89}

 41%|████      | 11436/28080 [22:35:52<32:28:48,  7.03s/it]
 41%|████      | 11437/28080 [22:35:59<32:35:30,  7.05s/it]
                                                           
{'loss': 0.6318, 'learning_rate': 0.0003354553566339932, 'epoch': 4.89}

 41%|████      | 11437/28080 [22:35:59<32:35:30,  7.05s/it]
 41%|████      | 11438/28080 [22:36:07<32:38:06,  7.06s/it]
                                                           
{'loss': 0.6206, 'learning_rate': 0.0003354282572792001, 'epoch': 4.89}

 41%|████      | 11438/28080 [22:36:07<32:38:06,  7.06s/it]
 41%|████      | 11439/28080 [22:36:14<32:39:36,  7.07s/it]
                                                           
{'loss': 0.6246, 'learning_rate': 0.00033540115678787216, 'epoch': 4.89}

 41%|████      | 11439/28080 [22:36:14<32:39:36,  7.07s/it]
 41%|████      | 11440/28080 [22:36:21<32:43:17,  7.08s/it]
                                                           
{'loss': 0.6463, 'learning_rate': 0.0003353740551603699, 'epoch': 4.89}

 41%|████      | 11440/28080 [22:36:21<32:43:17,  7.08s/it]
 41%|████      | 11441/28080 [22:36:28<32:44:33,  7.08s/it]
                                                           
{'loss': 0.6138, 'learning_rate': 0.000335346952397054, 'epoch': 4.89}

 41%|████      | 11441/28080 [22:36:28<32:44:33,  7.08s/it]
 41%|████      | 11442/28080 [22:36:35<32:43:50,  7.08s/it]
                                                           
{'loss': 0.631, 'learning_rate': 0.00033531984849828497, 'epoch': 4.89}

 41%|████      | 11442/28080 [22:36:35<32:43:50,  7.08s/it]
 41%|████      | 11443/28080 [22:36:42<32:33:42,  7.05s/it]
                                                           
{'loss': 0.6417, 'learning_rate': 0.0003352927434644232, 'epoch': 4.89}

 41%|████      | 11443/28080 [22:36:42<32:33:42,  7.05s/it]
 41%|████      | 11444/28080 [22:36:49<32:37:43,  7.06s/it]
                                                           
{'loss': 0.6098, 'learning_rate': 0.00033526563729582967, 'epoch': 4.89}

 41%|████      | 11444/28080 [22:36:49<32:37:43,  7.06s/it]
 41%|████      | 11445/28080 [22:36:56<32:28:06,  7.03s/it]
                                                           
{'loss': 0.6389, 'learning_rate': 0.00033523852999286466, 'epoch': 4.89}

 41%|████      | 11445/28080 [22:36:56<32:28:06,  7.03s/it]
 41%|████      | 11446/28080 [22:37:03<32:27:25,  7.02s/it]
                                                           
{'loss': 0.6445, 'learning_rate': 0.00033521142155588896, 'epoch': 4.89}

 41%|████      | 11446/28080 [22:37:03<32:27:25,  7.02s/it]
 41%|████      | 11447/28080 [22:37:10<32:30:07,  7.03s/it]
                                                           
{'loss': 0.5994, 'learning_rate': 0.0003351843119852633, 'epoch': 4.89}

 41%|████      | 11447/28080 [22:37:10<32:30:07,  7.03s/it]
 41%|████      | 11448/28080 [22:37:17<32:34:43,  7.05s/it]
                                                           
{'loss': 0.614, 'learning_rate': 0.00033515720128134813, 'epoch': 4.89}

 41%|████      | 11448/28080 [22:37:17<32:34:43,  7.05s/it]
 41%|████      | 11449/28080 [22:37:24<32:32:58,  7.05s/it]
                                                           
{'loss': 0.6196, 'learning_rate': 0.0003351300894445044, 'epoch': 4.89}

 41%|████      | 11449/28080 [22:37:24<32:32:58,  7.05s/it]
 41%|████      | 11450/28080 [22:37:31<32:38:38,  7.07s/it]
                                                           
{'loss': 0.6359, 'learning_rate': 0.00033510297647509245, 'epoch': 4.89}

 41%|████      | 11450/28080 [22:37:31<32:38:38,  7.07s/it]
 41%|████      | 11451/28080 [22:37:38<32:40:55,  7.08s/it]
                                                           
{'loss': 0.6392, 'learning_rate': 0.00033507586237347336, 'epoch': 4.89}

 41%|████      | 11451/28080 [22:37:38<32:40:55,  7.08s/it]
 41%|████      | 11452/28080 [22:37:45<32:40:59,  7.08s/it]
                                                           
{'loss': 0.6288, 'learning_rate': 0.0003350487471400076, 'epoch': 4.89}

 41%|████      | 11452/28080 [22:37:45<32:40:59,  7.08s/it]
 41%|████      | 11453/28080 [22:37:52<32:39:31,  7.07s/it]
                                                           
{'loss': 0.6289, 'learning_rate': 0.000335021630775056, 'epoch': 4.89}

 41%|████      | 11453/28080 [22:37:52<32:39:31,  7.07s/it]
 41%|████      | 11454/28080 [22:38:00<32:36:50,  7.06s/it]
                                                           
{'loss': 0.6063, 'learning_rate': 0.00033499451327897935, 'epoch': 4.89}

 41%|████      | 11454/28080 [22:38:00<32:36:50,  7.06s/it]
 41%|████      | 11455/28080 [22:38:07<32:39:27,  7.07s/it]
                                                           
{'loss': 0.6197, 'learning_rate': 0.00033496739465213837, 'epoch': 4.89}

 41%|████      | 11455/28080 [22:38:07<32:39:27,  7.07s/it]
 41%|████      | 11456/28080 [22:38:14<32:38:39,  7.07s/it]
                                                           
{'loss': 0.6146, 'learning_rate': 0.0003349402748948939, 'epoch': 4.89}

 41%|████      | 11456/28080 [22:38:14<32:38:39,  7.07s/it]
 41%|████      | 11457/28080 [22:38:21<32:39:06,  7.07s/it]
                                                           
{'loss': 0.619, 'learning_rate': 0.00033491315400760663, 'epoch': 4.89}

 41%|████      | 11457/28080 [22:38:21<32:39:06,  7.07s/it]
 41%|████      | 11458/28080 [22:38:28<32:37:27,  7.07s/it]
                                                           
{'loss': 0.6088, 'learning_rate': 0.0003348860319906376, 'epoch': 4.89}

 41%|████      | 11458/28080 [22:38:28<32:37:27,  7.07s/it]
 41%|████      | 11459/28080 [22:38:35<32:32:04,  7.05s/it]
                                                           
{'loss': 0.62, 'learning_rate': 0.00033485890884434727, 'epoch': 4.9}

 41%|████      | 11459/28080 [22:38:35<32:32:04,  7.05s/it]
 41%|████      | 11460/28080 [22:38:42<32:28:41,  7.03s/it]
                                                           
{'loss': 0.6046, 'learning_rate': 0.0003348317845690968, 'epoch': 4.9}

 41%|████      | 11460/28080 [22:38:42<32:28:41,  7.03s/it]
 41%|████      | 11461/28080 [22:38:49<32:24:16,  7.02s/it]
                                                           
{'loss': 0.6259, 'learning_rate': 0.0003348046591652469, 'epoch': 4.9}

 41%|████      | 11461/28080 [22:38:49<32:24:16,  7.02s/it]
 41%|████      | 11462/28080 [22:38:56<32:30:35,  7.04s/it]
                                                           
{'loss': 0.6229, 'learning_rate': 0.0003347775326331586, 'epoch': 4.9}

 41%|████      | 11462/28080 [22:38:56<32:30:35,  7.04s/it]
 41%|████      | 11463/28080 [22:39:03<32:34:56,  7.06s/it]
                                                           
{'loss': 0.6278, 'learning_rate': 0.00033475040497319265, 'epoch': 4.9}

 41%|████      | 11463/28080 [22:39:03<32:34:56,  7.06s/it]
 41%|████      | 11464/28080 [22:39:10<32:33:14,  7.05s/it]
                                                           
{'loss': 0.6223, 'learning_rate': 0.00033472327618571, 'epoch': 4.9}

 41%|████      | 11464/28080 [22:39:10<32:33:14,  7.05s/it]
 41%|████      | 11465/28080 [22:39:17<32:36:52,  7.07s/it]
                                                           
{'loss': 0.6028, 'learning_rate': 0.0003346961462710716, 'epoch': 4.9}

 41%|████      | 11465/28080 [22:39:17<32:36:52,  7.07s/it]
 41%|████      | 11466/28080 [22:39:24<32:32:29,  7.05s/it]
                                                           
{'loss': 0.6548, 'learning_rate': 0.0003346690152296383, 'epoch': 4.9}

 41%|████      | 11466/28080 [22:39:24<32:32:29,  7.05s/it]
 41%|████      | 11467/28080 [22:39:31<32:29:47,  7.04s/it]
                                                           
{'loss': 0.6354, 'learning_rate': 0.00033464188306177106, 'epoch': 4.9}

 41%|████      | 11467/28080 [22:39:31<32:29:47,  7.04s/it]
 41%|████      | 11468/28080 [22:39:38<32:32:24,  7.05s/it]
                                                           
{'loss': 0.6269, 'learning_rate': 0.00033461474976783094, 'epoch': 4.9}

 41%|████      | 11468/28080 [22:39:38<32:32:24,  7.05s/it]
 41%|████      | 11469/28080 [22:39:45<32:26:25,  7.03s/it]
                                                           
{'loss': 0.6372, 'learning_rate': 0.00033458761534817884, 'epoch': 4.9}

 41%|████      | 11469/28080 [22:39:45<32:26:25,  7.03s/it]
 41%|████      | 11470/28080 [22:39:52<32:29:49,  7.04s/it]
                                                           
{'loss': 0.631, 'learning_rate': 0.0003345604798031758, 'epoch': 4.9}

 41%|████      | 11470/28080 [22:39:52<32:29:49,  7.04s/it]
 41%|████      | 11471/28080 [22:39:59<32:28:30,  7.04s/it]
                                                           
{'loss': 0.6156, 'learning_rate': 0.00033453334313318287, 'epoch': 4.9}

 41%|████      | 11471/28080 [22:39:59<32:28:30,  7.04s/it]
 41%|████      | 11472/28080 [22:40:06<32:31:20,  7.05s/it]
                                                           
{'loss': 0.6184, 'learning_rate': 0.0003345062053385609, 'epoch': 4.9}

 41%|████      | 11472/28080 [22:40:06<32:31:20,  7.05s/it]
 41%|████      | 11473/28080 [22:40:13<32:31:13,  7.05s/it]
                                                           
{'loss': 0.6245, 'learning_rate': 0.00033447906641967113, 'epoch': 4.9}

 41%|████      | 11473/28080 [22:40:13<32:31:13,  7.05s/it]
 41%|████      | 11474/28080 [22:40:21<32:32:19,  7.05s/it]
                                                           
{'loss': 0.6303, 'learning_rate': 0.0003344519263768745, 'epoch': 4.9}

 41%|████      | 11474/28080 [22:40:21<32:32:19,  7.05s/it]
 41%|████      | 11475/28080 [22:40:28<32:38:39,  7.08s/it]
                                                           
{'loss': 0.6258, 'learning_rate': 0.0003344247852105321, 'epoch': 4.9}

 41%|████      | 11475/28080 [22:40:28<32:38:39,  7.08s/it]
 41%|████      | 11476/28080 [22:40:35<32:37:41,  7.07s/it]
                                                           
{'loss': 0.6406, 'learning_rate': 0.00033439764292100507, 'epoch': 4.9}

 41%|████      | 11476/28080 [22:40:35<32:37:41,  7.07s/it]
 41%|████      | 11477/28080 [22:40:42<32:33:34,  7.06s/it]
                                                           
{'loss': 0.6176, 'learning_rate': 0.0003343704995086544, 'epoch': 4.9}

 41%|████      | 11477/28080 [22:40:42<32:33:34,  7.06s/it]
 41%|████      | 11478/28080 [22:40:49<32:37:05,  7.07s/it]
                                                           
{'loss': 0.6247, 'learning_rate': 0.0003343433549738413, 'epoch': 4.9}

 41%|████      | 11478/28080 [22:40:49<32:37:05,  7.07s/it]
 41%|████      | 11479/28080 [22:40:56<32:38:09,  7.08s/it]
                                                           
{'loss': 0.6291, 'learning_rate': 0.0003343162093169269, 'epoch': 4.9}

 41%|████      | 11479/28080 [22:40:56<32:38:09,  7.08s/it]
 41%|████      | 11480/28080 [22:41:03<32:32:13,  7.06s/it]
                                                           
{'loss': 0.6124, 'learning_rate': 0.00033428906253827234, 'epoch': 4.9}

 41%|████      | 11480/28080 [22:41:03<32:32:13,  7.06s/it]
 41%|████      | 11481/28080 [22:41:10<32:22:33,  7.02s/it]
                                                           
{'loss': 0.6072, 'learning_rate': 0.0003342619146382387, 'epoch': 4.9}

 41%|████      | 11481/28080 [22:41:10<32:22:33,  7.02s/it]
 41%|████      | 11482/28080 [22:41:17<32:29:23,  7.05s/it]
                                                           
{'loss': 0.6148, 'learning_rate': 0.0003342347656171873, 'epoch': 4.91}

 41%|████      | 11482/28080 [22:41:17<32:29:23,  7.05s/it]
 41%|████      | 11483/28080 [22:41:24<32:23:00,  7.02s/it]
                                                           
{'loss': 0.6164, 'learning_rate': 0.00033420761547547917, 'epoch': 4.91}

 41%|████      | 11483/28080 [22:41:24<32:23:00,  7.02s/it]
 41%|████      | 11484/28080 [22:41:31<32:23:23,  7.03s/it]
                                                           
{'loss': 0.6394, 'learning_rate': 0.0003341804642134756, 'epoch': 4.91}

 41%|████      | 11484/28080 [22:41:31<32:23:23,  7.03s/it]
 41%|████      | 11485/28080 [22:41:38<32:30:27,  7.05s/it]
                                                           
{'loss': 0.6203, 'learning_rate': 0.00033415331183153787, 'epoch': 4.91}

 41%|████      | 11485/28080 [22:41:38<32:30:27,  7.05s/it]
 41%|████      | 11486/28080 [22:41:45<32:30:33,  7.05s/it]
                                                           
{'loss': 0.6207, 'learning_rate': 0.000334126158330027, 'epoch': 4.91}

 41%|████      | 11486/28080 [22:41:45<32:30:33,  7.05s/it]
 41%|████      | 11487/28080 [22:41:52<32:28:53,  7.05s/it]
                                                           
{'loss': 0.6337, 'learning_rate': 0.00033409900370930454, 'epoch': 4.91}

 41%|████      | 11487/28080 [22:41:52<32:28:53,  7.05s/it]
 41%|████      | 11488/28080 [22:41:59<32:22:35,  7.02s/it]
                                                           
{'loss': 0.628, 'learning_rate': 0.00033407184796973145, 'epoch': 4.91}

 41%|████      | 11488/28080 [22:41:59<32:22:35,  7.02s/it]
 41%|████      | 11489/28080 [22:42:06<32:24:12,  7.03s/it]
                                                           
{'loss': 0.6286, 'learning_rate': 0.0003340446911116693, 'epoch': 4.91}

 41%|████      | 11489/28080 [22:42:06<32:24:12,  7.03s/it]
 41%|████      | 11490/28080 [22:42:13<32:29:26,  7.05s/it]
                                                           
{'loss': 0.6258, 'learning_rate': 0.0003340175331354791, 'epoch': 4.91}

 41%|████      | 11490/28080 [22:42:13<32:29:26,  7.05s/it]
 41%|████      | 11491/28080 [22:42:20<32:31:48,  7.06s/it]
                                                           
{'loss': 0.6226, 'learning_rate': 0.0003339903740415224, 'epoch': 4.91}

 41%|████      | 11491/28080 [22:42:20<32:31:48,  7.06s/it]
 41%|████      | 11492/28080 [22:42:27<32:36:36,  7.08s/it]
                                                           
{'loss': 0.6409, 'learning_rate': 0.00033396321383016045, 'epoch': 4.91}

 41%|████      | 11492/28080 [22:42:27<32:36:36,  7.08s/it]
 41%|████      | 11493/28080 [22:42:34<32:29:10,  7.05s/it]
                                                           
{'loss': 0.6401, 'learning_rate': 0.0003339360525017544, 'epoch': 4.91}

 41%|████      | 11493/28080 [22:42:34<32:29:10,  7.05s/it]
 41%|████      | 11494/28080 [22:42:42<32:29:52,  7.05s/it]
                                                           
{'loss': 0.6427, 'learning_rate': 0.00033390889005666585, 'epoch': 4.91}

 41%|████      | 11494/28080 [22:42:42<32:29:52,  7.05s/it]
 41%|████      | 11495/28080 [22:42:49<32:23:27,  7.03s/it]
                                                           
{'loss': 0.6558, 'learning_rate': 0.00033388172649525616, 'epoch': 4.91}

 41%|████      | 11495/28080 [22:42:49<32:23:27,  7.03s/it]
 41%|████      | 11496/28080 [22:42:56<32:25:06,  7.04s/it]
                                                           
{'loss': 0.625, 'learning_rate': 0.00033385456181788656, 'epoch': 4.91}

 41%|████      | 11496/28080 [22:42:56<32:25:06,  7.04s/it]
 41%|████      | 11497/28080 [22:43:03<32:25:39,  7.04s/it]
                                                           
{'loss': 0.6264, 'learning_rate': 0.0003338273960249185, 'epoch': 4.91}

 41%|████      | 11497/28080 [22:43:03<32:25:39,  7.04s/it]
 41%|████      | 11498/28080 [22:43:10<32:31:10,  7.06s/it]
                                                           
{'loss': 0.6364, 'learning_rate': 0.00033380022911671343, 'epoch': 4.91}

 41%|████      | 11498/28080 [22:43:10<32:31:10,  7.06s/it]
 41%|████      | 11499/28080 [22:43:17<32:35:46,  7.08s/it]
                                                           
{'loss': 0.631, 'learning_rate': 0.0003337730610936328, 'epoch': 4.91}

 41%|████      | 11499/28080 [22:43:17<32:35:46,  7.08s/it]
 41%|████      | 11500/28080 [22:43:24<32:33:44,  7.07s/it]
                                                           
{'loss': 0.6257, 'learning_rate': 0.000333745891956038, 'epoch': 4.91}

 41%|████      | 11500/28080 [22:43:24<32:33:44,  7.07s/it]
 41%|████      | 11501/28080 [22:43:31<32:30:27,  7.06s/it]
                                                           
{'loss': 0.616, 'learning_rate': 0.0003337187217042904, 'epoch': 4.91}

 41%|████      | 11501/28080 [22:43:31<32:30:27,  7.06s/it]
 41%|████      | 11502/28080 [22:43:38<32:30:10,  7.06s/it]
                                                           
{'loss': 0.6227, 'learning_rate': 0.0003336915503387518, 'epoch': 4.91}

 41%|████      | 11502/28080 [22:43:38<32:30:10,  7.06s/it]
 41%|████      | 11503/28080 [22:43:45<32:34:42,  7.07s/it]
                                                           
{'loss': 0.605, 'learning_rate': 0.0003336643778597832, 'epoch': 4.91}

 41%|████      | 11503/28080 [22:43:45<32:34:42,  7.07s/it]
 41%|████      | 11504/28080 [22:43:52<32:37:02,  7.08s/it]
                                                           
{'loss': 0.6164, 'learning_rate': 0.00033363720426774656, 'epoch': 4.91}

 41%|████      | 11504/28080 [22:43:52<32:37:02,  7.08s/it]
 41%|████      | 11505/28080 [22:43:59<32:33:11,  7.07s/it]
                                                           
{'loss': 0.6245, 'learning_rate': 0.0003336100295630031, 'epoch': 4.91}

 41%|████      | 11505/28080 [22:43:59<32:33:11,  7.07s/it]
 41%|████      | 11506/28080 [22:44:06<32:36:41,  7.08s/it]
                                                           
{'loss': 0.6252, 'learning_rate': 0.00033358285374591453, 'epoch': 4.92}

 41%|████      | 11506/28080 [22:44:06<32:36:41,  7.08s/it]
 41%|████      | 11507/28080 [22:44:13<32:24:56,  7.04s/it]
                                                           
{'loss': 0.6319, 'learning_rate': 0.00033355567681684224, 'epoch': 4.92}

 41%|████      | 11507/28080 [22:44:13<32:24:56,  7.04s/it]
 41%|████      | 11508/28080 [22:44:20<32:17:43,  7.02s/it]
                                                           
{'loss': 0.6431, 'learning_rate': 0.00033352849877614786, 'epoch': 4.92}

 41%|████      | 11508/28080 [22:44:20<32:17:43,  7.02s/it]
 41%|████      | 11509/28080 [22:44:27<32:09:13,  6.99s/it]
                                                           
{'loss': 0.628, 'learning_rate': 0.00033350131962419304, 'epoch': 4.92}

 41%|████      | 11509/28080 [22:44:27<32:09:13,  6.99s/it]
 41%|████      | 11510/28080 [22:44:34<32:17:26,  7.02s/it]
                                                           
{'loss': 0.6323, 'learning_rate': 0.0003334741393613393, 'epoch': 4.92}

 41%|████      | 11510/28080 [22:44:34<32:17:26,  7.02s/it]
 41%|████      | 11511/28080 [22:44:41<32:17:15,  7.02s/it]
                                                           
{'loss': 0.6332, 'learning_rate': 0.0003334469579879483, 'epoch': 4.92}

 41%|████      | 11511/28080 [22:44:41<32:17:15,  7.02s/it]
 41%|████      | 11512/28080 [22:44:48<32:14:41,  7.01s/it]
                                                           
{'loss': 0.6556, 'learning_rate': 0.0003334197755043815, 'epoch': 4.92}

 41%|████      | 11512/28080 [22:44:48<32:14:41,  7.01s/it]
 41%|████      | 11513/28080 [22:44:55<32:20:41,  7.03s/it]
                                                           
{'loss': 0.6256, 'learning_rate': 0.00033339259191100075, 'epoch': 4.92}

 41%|████      | 11513/28080 [22:44:55<32:20:41,  7.03s/it]
 41%|████      | 11514/28080 [22:45:02<32:15:09,  7.01s/it]
                                                           
{'loss': 0.6529, 'learning_rate': 0.0003333654072081675, 'epoch': 4.92}

 41%|████      | 11514/28080 [22:45:02<32:15:09,  7.01s/it]
 41%|████      | 11515/28080 [22:45:09<32:16:53,  7.02s/it]
                                                           
{'loss': 0.6185, 'learning_rate': 0.00033333822139624354, 'epoch': 4.92}

 41%|████      | 11515/28080 [22:45:09<32:16:53,  7.02s/it]
 41%|████      | 11516/28080 [22:45:16<32:21:07,  7.03s/it]
                                                           
{'loss': 0.646, 'learning_rate': 0.00033331103447559066, 'epoch': 4.92}

 41%|████      | 11516/28080 [22:45:16<32:21:07,  7.03s/it]
 41%|████      | 11517/28080 [22:45:24<32:28:36,  7.06s/it]
                                                           
{'loss': 0.6289, 'learning_rate': 0.00033328384644657025, 'epoch': 4.92}

 41%|████      | 11517/28080 [22:45:24<32:28:36,  7.06s/it]
 41%|████      | 11518/28080 [22:45:31<32:35:08,  7.08s/it]
                                                           
{'loss': 0.6073, 'learning_rate': 0.00033325665730954423, 'epoch': 4.92}

 41%|████      | 11518/28080 [22:45:31<32:35:08,  7.08s/it]
 41%|████      | 11519/28080 [22:45:38<32:35:00,  7.08s/it]
                                                           
{'loss': 0.6325, 'learning_rate': 0.00033322946706487423, 'epoch': 4.92}

 41%|████      | 11519/28080 [22:45:38<32:35:00,  7.08s/it]
 41%|████      | 11520/28080 [22:45:45<32:43:13,  7.11s/it]
                                                           
{'loss': 0.6343, 'learning_rate': 0.00033320227571292206, 'epoch': 4.92}

 41%|████      | 11520/28080 [22:45:45<32:43:13,  7.11s/it]
 41%|████      | 11521/28080 [22:45:52<32:45:11,  7.12s/it]
                                                           
{'loss': 0.6242, 'learning_rate': 0.00033317508325404944, 'epoch': 4.92}

 41%|████      | 11521/28080 [22:45:52<32:45:11,  7.12s/it]
 41%|████      | 11522/28080 [22:45:59<32:32:28,  7.08s/it]
                                                           
{'loss': 0.6465, 'learning_rate': 0.00033314788968861813, 'epoch': 4.92}

 41%|████      | 11522/28080 [22:45:59<32:32:28,  7.08s/it]
 41%|████      | 11523/28080 [22:46:06<32:35:38,  7.09s/it]
                                                           
{'loss': 0.6152, 'learning_rate': 0.00033312069501699, 'epoch': 4.92}

 41%|████      | 11523/28080 [22:46:06<32:35:38,  7.09s/it]
 41%|████      | 11524/28080 [22:46:13<32:27:19,  7.06s/it]
                                                           
{'loss': 0.6683, 'learning_rate': 0.0003330934992395267, 'epoch': 4.92}

 41%|████      | 11524/28080 [22:46:13<32:27:19,  7.06s/it]
 41%|████      | 11525/28080 [22:46:20<32:24:55,  7.05s/it]
                                                           
{'loss': 0.6404, 'learning_rate': 0.00033306630235659015, 'epoch': 4.92}

 41%|████      | 11525/28080 [22:46:20<32:24:55,  7.05s/it]
 41%|████      | 11526/28080 [22:46:27<32:38:01,  7.10s/it]
                                                           
{'loss': 0.6198, 'learning_rate': 0.0003330391043685421, 'epoch': 4.92}

 41%|████      | 11526/28080 [22:46:27<32:38:01,  7.10s/it]
 41%|████      | 11527/28080 [22:46:35<32:40:40,  7.11s/it]
                                                           
{'loss': 0.623, 'learning_rate': 0.0003330119052757445, 'epoch': 4.92}

 41%|████      | 11527/28080 [22:46:35<32:40:40,  7.11s/it]
 41%|████      | 11528/28080 [22:46:42<32:39:44,  7.10s/it]
                                                           
{'loss': 0.6205, 'learning_rate': 0.00033298470507855916, 'epoch': 4.92}

 41%|████      | 11528/28080 [22:46:42<32:39:44,  7.10s/it]
 41%|████      | 11529/28080 [22:46:49<32:37:25,  7.10s/it]
                                                           
{'loss': 0.629, 'learning_rate': 0.00033295750377734784, 'epoch': 4.93}

 41%|████      | 11529/28080 [22:46:49<32:37:25,  7.10s/it]
 41%|████      | 11530/28080 [22:46:56<32:30:59,  7.07s/it]
                                                           
{'loss': 0.638, 'learning_rate': 0.0003329303013724726, 'epoch': 4.93}

 41%|████      | 11530/28080 [22:46:56<32:30:59,  7.07s/it]
 41%|████      | 11531/28080 [22:47:03<32:31:20,  7.07s/it]
                                                           
{'loss': 0.6135, 'learning_rate': 0.0003329030978642952, 'epoch': 4.93}

 41%|████      | 11531/28080 [22:47:03<32:31:20,  7.07s/it]
 41%|████      | 11532/28080 [22:47:10<32:36:14,  7.09s/it]
                                                           
{'loss': 0.6313, 'learning_rate': 0.0003328758932531776, 'epoch': 4.93}

 41%|████      | 11532/28080 [22:47:10<32:36:14,  7.09s/it]
 41%|████      | 11533/28080 [22:47:17<32:33:33,  7.08s/it]
                                                           
{'loss': 0.6267, 'learning_rate': 0.00033284868753948174, 'epoch': 4.93}

 41%|████      | 11533/28080 [22:47:17<32:33:33,  7.08s/it]
 41%|████      | 11534/28080 [22:47:24<32:35:59,  7.09s/it]
                                                           
{'loss': 0.6211, 'learning_rate': 0.00033282148072356953, 'epoch': 4.93}

 41%|████      | 11534/28080 [22:47:24<32:35:59,  7.09s/it]
 41%|████      | 11535/28080 [22:47:31<32:41:39,  7.11s/it]
                                                           
{'loss': 0.6272, 'learning_rate': 0.00033279427280580304, 'epoch': 4.93}

 41%|████      | 11535/28080 [22:47:31<32:41:39,  7.11s/it]
 41%|████      | 11536/28080 [22:47:38<32:44:28,  7.12s/it]
                                                           
{'loss': 0.6214, 'learning_rate': 0.00033276706378654417, 'epoch': 4.93}

 41%|████      | 11536/28080 [22:47:38<32:44:28,  7.12s/it]
 41%|████      | 11537/28080 [22:47:46<32:44:35,  7.13s/it]
                                                           
{'loss': 0.6282, 'learning_rate': 0.0003327398536661549, 'epoch': 4.93}

 41%|████      | 11537/28080 [22:47:46<32:44:35,  7.13s/it]
 41%|████      | 11538/28080 [22:47:53<32:40:19,  7.11s/it]
                                                           
{'loss': 0.6467, 'learning_rate': 0.0003327126424449971, 'epoch': 4.93}

 41%|████      | 11538/28080 [22:47:53<32:40:19,  7.11s/it]
 41%|████      | 11539/28080 [22:48:00<32:32:29,  7.08s/it]
                                                           
{'loss': 0.6478, 'learning_rate': 0.00033268543012343306, 'epoch': 4.93}

 41%|████      | 11539/28080 [22:48:00<32:32:29,  7.08s/it]
 41%|████      | 11540/28080 [22:48:07<32:28:41,  7.07s/it]
                                                           
{'loss': 0.6308, 'learning_rate': 0.0003326582167018246, 'epoch': 4.93}

 41%|████      | 11540/28080 [22:48:07<32:28:41,  7.07s/it]
 41%|████      | 11541/28080 [22:48:14<32:34:19,  7.09s/it]
                                                           
{'loss': 0.6212, 'learning_rate': 0.0003326310021805339, 'epoch': 4.93}

 41%|████      | 11541/28080 [22:48:14<32:34:19,  7.09s/it]
 41%|████      | 11542/28080 [22:48:21<32:33:15,  7.09s/it]
                                                           
{'loss': 0.6325, 'learning_rate': 0.00033260378655992304, 'epoch': 4.93}

 41%|████      | 11542/28080 [22:48:21<32:33:15,  7.09s/it]
 41%|████      | 11543/28080 [22:48:28<32:40:24,  7.11s/it]
                                                           
{'loss': 0.6267, 'learning_rate': 0.0003325765698403539, 'epoch': 4.93}

 41%|████      | 11543/28080 [22:48:28<32:40:24,  7.11s/it]
 41%|████      | 11544/28080 [22:48:35<32:42:21,  7.12s/it]
                                                           
{'loss': 0.6569, 'learning_rate': 0.00033254935202218865, 'epoch': 4.93}

 41%|████      | 11544/28080 [22:48:35<32:42:21,  7.12s/it]
 41%|████      | 11545/28080 [22:48:42<32:37:47,  7.10s/it]
                                                           
{'loss': 0.6344, 'learning_rate': 0.0003325221331057895, 'epoch': 4.93}

 41%|████      | 11545/28080 [22:48:42<32:37:47,  7.10s/it]
 41%|████      | 11546/28080 [22:48:49<32:33:37,  7.09s/it]
                                                           
{'loss': 0.6196, 'learning_rate': 0.0003324949130915185, 'epoch': 4.93}

 41%|████      | 11546/28080 [22:48:49<32:33:37,  7.09s/it]
 41%|████      | 11547/28080 [22:48:56<32:38:54,  7.11s/it]
                                                           
{'loss': 0.6106, 'learning_rate': 0.0003324676919797378, 'epoch': 4.93}

 41%|████      | 11547/28080 [22:48:56<32:38:54,  7.11s/it]
 41%|████      | 11548/28080 [22:49:03<32:31:02,  7.08s/it]
                                                           
{'loss': 0.6225, 'learning_rate': 0.0003324404697708095, 'epoch': 4.93}

 41%|████      | 11548/28080 [22:49:03<32:31:02,  7.08s/it]
 41%|████      | 11549/28080 [22:49:11<32:31:07,  7.08s/it]
                                                           
{'loss': 0.6099, 'learning_rate': 0.00033241324646509577, 'epoch': 4.93}

 41%|████      | 11549/28080 [22:49:11<32:31:07,  7.08s/it]
 41%|████      | 11550/28080 [22:49:18<32:33:59,  7.09s/it]
                                                           
{'loss': 0.6155, 'learning_rate': 0.0003323860220629589, 'epoch': 4.93}

 41%|████      | 11550/28080 [22:49:18<32:33:59,  7.09s/it]
 41%|████      | 11551/28080 [22:49:25<32:39:38,  7.11s/it]
                                                           
{'loss': 0.6173, 'learning_rate': 0.0003323587965647609, 'epoch': 4.93}

 41%|████      | 11551/28080 [22:49:25<32:39:38,  7.11s/it]
 41%|████      | 11552/28080 [22:49:32<32:37:57,  7.11s/it]
                                                           
{'loss': 0.5936, 'learning_rate': 0.0003323315699708642, 'epoch': 4.93}

 41%|████      | 11552/28080 [22:49:32<32:37:57,  7.11s/it]
 41%|████      | 11553/28080 [22:49:39<32:28:06,  7.07s/it]
                                                           
{'loss': 0.6297, 'learning_rate': 0.0003323043422816308, 'epoch': 4.94}

 41%|████      | 11553/28080 [22:49:39<32:28:06,  7.07s/it]
 41%|████      | 11554/28080 [22:49:46<32:31:35,  7.09s/it]
                                                           
{'loss': 0.6323, 'learning_rate': 0.00033227711349742307, 'epoch': 4.94}

 41%|████      | 11554/28080 [22:49:46<32:31:35,  7.09s/it]
 41%|████      | 11555/28080 [22:49:53<32:30:59,  7.08s/it]
                                                           
{'loss': 0.6354, 'learning_rate': 0.0003322498836186032, 'epoch': 4.94}

 41%|████      | 11555/28080 [22:49:53<32:30:59,  7.08s/it]
 41%|████      | 11556/28080 [22:50:00<32:28:45,  7.08s/it]
                                                           
{'loss': 0.6184, 'learning_rate': 0.0003322226526455335, 'epoch': 4.94}

 41%|████      | 11556/28080 [22:50:00<32:28:45,  7.08s/it]
 41%|████      | 11557/28080 [22:50:07<32:27:08,  7.07s/it]
                                                           
{'loss': 0.6408, 'learning_rate': 0.0003321954205785762, 'epoch': 4.94}

 41%|████      | 11557/28080 [22:50:07<32:27:08,  7.07s/it]
 41%|████      | 11558/28080 [22:50:14<32:25:26,  7.06s/it]
                                                           
{'loss': 0.6283, 'learning_rate': 0.00033216818741809367, 'epoch': 4.94}

 41%|████      | 11558/28080 [22:50:14<32:25:26,  7.06s/it]
 41%|████      | 11559/28080 [22:50:21<32:30:51,  7.09s/it]
                                                           
{'loss': 0.6124, 'learning_rate': 0.0003321409531644482, 'epoch': 4.94}

 41%|████      | 11559/28080 [22:50:21<32:30:51,  7.09s/it]
 41%|████      | 11560/28080 [22:50:29<32:35:34,  7.10s/it]
                                                           
{'loss': 0.6165, 'learning_rate': 0.000332113717818002, 'epoch': 4.94}

 41%|████      | 11560/28080 [22:50:29<32:35:34,  7.10s/it]
 41%|████      | 11561/28080 [22:50:36<32:38:09,  7.11s/it]
                                                           
{'loss': 0.6263, 'learning_rate': 0.0003320864813791176, 'epoch': 4.94}

 41%|████      | 11561/28080 [22:50:36<32:38:09,  7.11s/it]
 41%|████      | 11562/28080 [22:50:43<32:43:47,  7.13s/it]
                                                           
{'loss': 0.6347, 'learning_rate': 0.00033205924384815716, 'epoch': 4.94}

 41%|████      | 11562/28080 [22:50:43<32:43:47,  7.13s/it]
 41%|████      | 11563/28080 [22:50:50<32:36:38,  7.11s/it]
                                                           
{'loss': 0.6452, 'learning_rate': 0.00033203200522548314, 'epoch': 4.94}

 41%|████      | 11563/28080 [22:50:50<32:36:38,  7.11s/it]
 41%|████      | 11564/28080 [22:50:57<32:36:09,  7.11s/it]
                                                           
{'loss': 0.6311, 'learning_rate': 0.00033200476551145804, 'epoch': 4.94}

 41%|████      | 11564/28080 [22:50:57<32:36:09,  7.11s/it]
 41%|████      | 11565/28080 [22:51:04<32:35:29,  7.10s/it]
                                                           
{'loss': 0.6135, 'learning_rate': 0.000331977524706444, 'epoch': 4.94}

 41%|████      | 11565/28080 [22:51:04<32:35:29,  7.10s/it]
 41%|████      | 11566/28080 [22:51:11<32:32:50,  7.10s/it]
                                                           
{'loss': 0.617, 'learning_rate': 0.0003319502828108037, 'epoch': 4.94}

 41%|████      | 11566/28080 [22:51:11<32:32:50,  7.10s/it]
 41%|████      | 11567/28080 [22:51:18<32:27:54,  7.08s/it]
                                                           
{'loss': 0.6435, 'learning_rate': 0.0003319230398248993, 'epoch': 4.94}

 41%|████      | 11567/28080 [22:51:18<32:27:54,  7.08s/it]
 41%|████      | 11568/28080 [22:51:25<32:22:48,  7.06s/it]
                                                           
{'loss': 0.6197, 'learning_rate': 0.0003318957957490934, 'epoch': 4.94}

 41%|████      | 11568/28080 [22:51:25<32:22:48,  7.06s/it]
 41%|████      | 11569/28080 [22:51:32<32:29:05,  7.08s/it]
                                                           
{'loss': 0.6264, 'learning_rate': 0.0003318685505837485, 'epoch': 4.94}

 41%|████      | 11569/28080 [22:51:32<32:29:05,  7.08s/it]
 41%|████      | 11570/28080 [22:51:40<32:31:09,  7.09s/it]
                                                           
{'loss': 0.6271, 'learning_rate': 0.0003318413043292269, 'epoch': 4.94}

 41%|████      | 11570/28080 [22:51:40<32:31:09,  7.09s/it]
 41%|████      | 11571/28080 [22:51:46<32:18:32,  7.05s/it]
                                                           
{'loss': 0.6291, 'learning_rate': 0.00033181405698589126, 'epoch': 4.94}

 41%|████      | 11571/28080 [22:51:46<32:18:32,  7.05s/it]
 41%|████      | 11572/28080 [22:51:54<32:24:24,  7.07s/it]
                                                           
{'loss': 0.611, 'learning_rate': 0.00033178680855410386, 'epoch': 4.94}

 41%|████      | 11572/28080 [22:51:54<32:24:24,  7.07s/it]
 41%|████      | 11573/28080 [22:52:01<32:22:16,  7.06s/it]
                                                           
{'loss': 0.6232, 'learning_rate': 0.0003317595590342275, 'epoch': 4.94}

 41%|████      | 11573/28080 [22:52:01<32:22:16,  7.06s/it]
 41%|████      | 11574/28080 [22:52:08<32:27:09,  7.08s/it]
                                                           
{'loss': 0.6377, 'learning_rate': 0.00033173230842662446, 'epoch': 4.94}

 41%|████      | 11574/28080 [22:52:08<32:27:09,  7.08s/it]
 41%|████      | 11575/28080 [22:52:15<32:33:30,  7.10s/it]
                                                           
{'loss': 0.6256, 'learning_rate': 0.00033170505673165736, 'epoch': 4.94}

 41%|████      | 11575/28080 [22:52:15<32:33:30,  7.10s/it]
 41%|████      | 11576/28080 [22:52:22<32:32:49,  7.10s/it]
                                                           
{'loss': 0.6618, 'learning_rate': 0.00033167780394968883, 'epoch': 4.95}

 41%|████      | 11576/28080 [22:52:22<32:32:49,  7.10s/it]
 41%|████      | 11577/28080 [22:52:29<32:33:47,  7.10s/it]
                                                           
{'loss': 0.6297, 'learning_rate': 0.00033165055008108134, 'epoch': 4.95}

 41%|████      | 11577/28080 [22:52:29<32:33:47,  7.10s/it]
 41%|████      | 11578/28080 [22:52:36<32:28:27,  7.08s/it]
                                                           
{'loss': 0.6233, 'learning_rate': 0.00033162329512619753, 'epoch': 4.95}

 41%|████      | 11578/28080 [22:52:36<32:28:27,  7.08s/it]
 41%|████      | 11579/28080 [22:52:43<32:24:14,  7.07s/it]
                                                           
{'loss': 0.6299, 'learning_rate': 0.0003315960390854, 'epoch': 4.95}

 41%|████      | 11579/28080 [22:52:43<32:24:14,  7.07s/it]
 41%|████      | 11580/28080 [22:52:50<32:19:54,  7.05s/it]
                                                           
{'loss': 0.6163, 'learning_rate': 0.0003315687819590514, 'epoch': 4.95}

 41%|████      | 11580/28080 [22:52:50<32:19:54,  7.05s/it]
 41%|████      | 11581/28080 [22:52:57<32:26:39,  7.08s/it]
                                                           
{'loss': 0.6308, 'learning_rate': 0.0003315415237475142, 'epoch': 4.95}

 41%|████      | 11581/28080 [22:52:57<32:26:39,  7.08s/it]
 41%|████      | 11582/28080 [22:53:04<32:24:17,  7.07s/it]
                                                           
{'loss': 0.6491, 'learning_rate': 0.0003315142644511511, 'epoch': 4.95}

 41%|████      | 11582/28080 [22:53:04<32:24:17,  7.07s/it]
 41%|████▏     | 11583/28080 [22:53:11<32:24:29,  7.07s/it]
                                                           
{'loss': 0.6136, 'learning_rate': 0.00033148700407032496, 'epoch': 4.95}

 41%|████▏     | 11583/28080 [22:53:11<32:24:29,  7.07s/it]
 41%|████▏     | 11584/28080 [22:53:18<32:19:48,  7.06s/it]
                                                           
{'loss': 0.6233, 'learning_rate': 0.0003314597426053982, 'epoch': 4.95}

 41%|████▏     | 11584/28080 [22:53:18<32:19:48,  7.06s/it]
 41%|████▏     | 11585/28080 [22:53:25<32:12:51,  7.03s/it]
                                                           
{'loss': 0.6306, 'learning_rate': 0.00033143248005673367, 'epoch': 4.95}

 41%|████▏     | 11585/28080 [22:53:25<32:12:51,  7.03s/it]
 41%|████▏     | 11586/28080 [22:53:32<32:12:22,  7.03s/it]
                                                           
{'loss': 0.6368, 'learning_rate': 0.000331405216424694, 'epoch': 4.95}

 41%|████▏     | 11586/28080 [22:53:32<32:12:22,  7.03s/it]
 41%|████▏     | 11587/28080 [22:53:40<32:15:36,  7.04s/it]
                                                           
{'loss': 0.6257, 'learning_rate': 0.0003313779517096418, 'epoch': 4.95}

 41%|████▏     | 11587/28080 [22:53:40<32:15:36,  7.04s/it]
 41%|████▏     | 11588/28080 [22:53:47<32:12:33,  7.03s/it]
                                                           
{'loss': 0.6289, 'learning_rate': 0.00033135068591194, 'epoch': 4.95}

 41%|████▏     | 11588/28080 [22:53:47<32:12:33,  7.03s/it]
 41%|████▏     | 11589/28080 [22:53:54<32:20:32,  7.06s/it]
                                                           
{'loss': 0.6176, 'learning_rate': 0.00033132341903195124, 'epoch': 4.95}

 41%|████▏     | 11589/28080 [22:53:54<32:20:32,  7.06s/it]
 41%|████▏     | 11590/28080 [22:54:01<32:28:38,  7.09s/it]
                                                           
{'loss': 0.6455, 'learning_rate': 0.0003312961510700383, 'epoch': 4.95}

 41%|████▏     | 11590/28080 [22:54:01<32:28:38,  7.09s/it]
 41%|████▏     | 11591/28080 [22:54:08<32:28:22,  7.09s/it]
                                                           
{'loss': 0.6247, 'learning_rate': 0.0003312688820265639, 'epoch': 4.95}

 41%|████▏     | 11591/28080 [22:54:08<32:28:22,  7.09s/it]
 41%|████▏     | 11592/28080 [22:54:15<32:29:58,  7.10s/it]
                                                           
{'loss': 0.6326, 'learning_rate': 0.0003312416119018909, 'epoch': 4.95}

 41%|████▏     | 11592/28080 [22:54:15<32:29:58,  7.10s/it]
 41%|████▏     | 11593/28080 [22:54:22<32:22:55,  7.07s/it]
                                                           
{'loss': 0.639, 'learning_rate': 0.00033121434069638205, 'epoch': 4.95}

 41%|████▏     | 11593/28080 [22:54:22<32:22:55,  7.07s/it]
 41%|████▏     | 11594/28080 [22:54:29<32:20:02,  7.06s/it]
                                                           
{'loss': 0.6395, 'learning_rate': 0.00033118706841040016, 'epoch': 4.95}

 41%|████▏     | 11594/28080 [22:54:29<32:20:02,  7.06s/it]
 41%|████▏     | 11595/28080 [22:54:36<32:16:44,  7.05s/it]
                                                           
{'loss': 0.6382, 'learning_rate': 0.0003311597950443081, 'epoch': 4.95}

 41%|████▏     | 11595/28080 [22:54:36<32:16:44,  7.05s/it]
 41%|████▏     | 11596/28080 [22:54:43<32:18:57,  7.06s/it]
                                                           
{'loss': 0.6088, 'learning_rate': 0.00033113252059846867, 'epoch': 4.95}

 41%|████▏     | 11596/28080 [22:54:43<32:18:57,  7.06s/it]
 41%|████▏     | 11597/28080 [22:54:50<32:18:14,  7.06s/it]
                                                           
{'loss': 0.6241, 'learning_rate': 0.0003311052450732448, 'epoch': 4.95}

 41%|████▏     | 11597/28080 [22:54:50<32:18:14,  7.06s/it]
 41%|████▏     | 11598/28080 [22:54:57<32:23:50,  7.08s/it]
                                                           
{'loss': 0.6163, 'learning_rate': 0.00033107796846899927, 'epoch': 4.95}

 41%|████▏     | 11598/28080 [22:54:57<32:23:50,  7.08s/it]
 41%|████▏     | 11599/28080 [22:55:04<32:21:50,  7.07s/it]
                                                           
{'loss': 0.6258, 'learning_rate': 0.000331050690786095, 'epoch': 4.95}

 41%|████▏     | 11599/28080 [22:55:04<32:21:50,  7.07s/it]
 41%|████▏     | 11600/28080 [22:55:11<32:21:30,  7.07s/it]
                                                           
{'loss': 0.6201, 'learning_rate': 0.000331023412024895, 'epoch': 4.96}

 41%|████▏     | 11600/28080 [22:55:11<32:21:30,  7.07s/it]
 41%|████▏     | 11601/28080 [22:55:19<32:30:18,  7.10s/it]
                                                           
{'loss': 0.6141, 'learning_rate': 0.00033099613218576197, 'epoch': 4.96}

 41%|████▏     | 11601/28080 [22:55:19<32:30:18,  7.10s/it]
 41%|████▏     | 11602/28080 [22:55:26<32:34:41,  7.12s/it]
                                                           
{'loss': 0.6309, 'learning_rate': 0.00033096885126905905, 'epoch': 4.96}

 41%|████▏     | 11602/28080 [22:55:26<32:34:41,  7.12s/it]
 41%|████▏     | 11603/28080 [22:55:33<32:34:26,  7.12s/it]
                                                           
{'loss': 0.6326, 'learning_rate': 0.00033094156927514906, 'epoch': 4.96}

 41%|████▏     | 11603/28080 [22:55:33<32:34:26,  7.12s/it]
 41%|████▏     | 11604/28080 [22:55:40<32:36:18,  7.12s/it]
                                                           
{'loss': 0.6106, 'learning_rate': 0.000330914286204395, 'epoch': 4.96}

 41%|████▏     | 11604/28080 [22:55:40<32:36:18,  7.12s/it]
 41%|████▏     | 11605/28080 [22:55:47<32:19:39,  7.06s/it]
                                                           
{'loss': 0.6383, 'learning_rate': 0.0003308870020571598, 'epoch': 4.96}

 41%|████▏     | 11605/28080 [22:55:47<32:19:39,  7.06s/it]
 41%|████▏     | 11606/28080 [22:55:54<32:16:47,  7.05s/it]
                                                           
{'loss': 0.6351, 'learning_rate': 0.00033085971683380653, 'epoch': 4.96}

 41%|████▏     | 11606/28080 [22:55:54<32:16:47,  7.05s/it]
 41%|████▏     | 11607/28080 [22:56:01<32:19:11,  7.06s/it]
                                                           
{'loss': 0.649, 'learning_rate': 0.00033083243053469815, 'epoch': 4.96}

 41%|████▏     | 11607/28080 [22:56:01<32:19:11,  7.06s/it]
 41%|████▏     | 11608/28080 [22:56:08<32:16:02,  7.05s/it]
                                                           
{'loss': 0.6287, 'learning_rate': 0.0003308051431601976, 'epoch': 4.96}

 41%|████▏     | 11608/28080 [22:56:08<32:16:02,  7.05s/it]
 41%|████▏     | 11609/28080 [22:56:15<32:20:20,  7.07s/it]
                                                           
{'loss': 0.6214, 'learning_rate': 0.0003307778547106681, 'epoch': 4.96}

 41%|████▏     | 11609/28080 [22:56:15<32:20:20,  7.07s/it]
 41%|████▏     | 11610/28080 [22:56:22<32:26:10,  7.09s/it]
                                                           
{'loss': 0.6271, 'learning_rate': 0.0003307505651864725, 'epoch': 4.96}

 41%|████▏     | 11610/28080 [22:56:22<32:26:10,  7.09s/it]
 41%|████▏     | 11611/28080 [22:56:29<32:27:04,  7.09s/it]
                                                           
{'loss': 0.6354, 'learning_rate': 0.000330723274587974, 'epoch': 4.96}

 41%|████▏     | 11611/28080 [22:56:29<32:27:04,  7.09s/it]
 41%|████▏     | 11612/28080 [22:56:37<32:24:56,  7.09s/it]
                                                           
{'loss': 0.6564, 'learning_rate': 0.00033069598291553547, 'epoch': 4.96}

 41%|████▏     | 11612/28080 [22:56:37<32:24:56,  7.09s/it]
 41%|████▏     | 11613/28080 [22:56:44<32:24:49,  7.09s/it]
                                                           
{'loss': 0.6225, 'learning_rate': 0.0003306686901695202, 'epoch': 4.96}

 41%|████▏     | 11613/28080 [22:56:44<32:24:49,  7.09s/it]
 41%|████▏     | 11614/28080 [22:56:51<32:23:34,  7.08s/it]
                                                           
{'loss': 0.6217, 'learning_rate': 0.00033064139635029135, 'epoch': 4.96}

 41%|████▏     | 11614/28080 [22:56:51<32:23:34,  7.08s/it]
 41%|████▏     | 11615/28080 [22:56:58<32:25:45,  7.09s/it]
                                                           
{'loss': 0.6147, 'learning_rate': 0.0003306141014582118, 'epoch': 4.96}

 41%|████▏     | 11615/28080 [22:56:58<32:25:45,  7.09s/it]
 41%|████▏     | 11616/28080 [22:57:05<32:27:10,  7.10s/it]
                                                           
{'loss': 0.6468, 'learning_rate': 0.00033058680549364483, 'epoch': 4.96}

 41%|████▏     | 11616/28080 [22:57:05<32:27:10,  7.10s/it]
 41%|████▏     | 11617/28080 [22:57:12<32:30:56,  7.11s/it]
                                                           
{'loss': 0.6248, 'learning_rate': 0.00033055950845695353, 'epoch': 4.96}

 41%|████▏     | 11617/28080 [22:57:12<32:30:56,  7.11s/it]
 41%|████▏     | 11618/28080 [22:57:19<32:29:45,  7.11s/it]
                                                           
{'loss': 0.6091, 'learning_rate': 0.00033053221034850107, 'epoch': 4.96}

 41%|████▏     | 11618/28080 [22:57:19<32:29:45,  7.11s/it]
 41%|████▏     | 11619/28080 [22:57:26<32:22:16,  7.08s/it]
                                                           
{'loss': 0.6057, 'learning_rate': 0.0003305049111686507, 'epoch': 4.96}

 41%|████▏     | 11619/28080 [22:57:26<32:22:16,  7.08s/it]
 41%|████▏     | 11620/28080 [22:57:33<32:22:37,  7.08s/it]
                                                           
{'loss': 0.63, 'learning_rate': 0.00033047761091776546, 'epoch': 4.96}

 41%|████▏     | 11620/28080 [22:57:33<32:22:37,  7.08s/it]
 41%|████▏     | 11621/28080 [22:57:40<32:22:55,  7.08s/it]
                                                           
{'loss': 0.6301, 'learning_rate': 0.0003304503095962087, 'epoch': 4.96}

 41%|████▏     | 11621/28080 [22:57:40<32:22:55,  7.08s/it]
 41%|████▏     | 11622/28080 [22:57:47<32:21:13,  7.08s/it]
                                                           
{'loss': 0.5956, 'learning_rate': 0.0003304230072043435, 'epoch': 4.96}

 41%|████▏     | 11622/28080 [22:57:47<32:21:13,  7.08s/it]
 41%|████▏     | 11623/28080 [22:57:55<32:22:48,  7.08s/it]
                                                           
{'loss': 0.6433, 'learning_rate': 0.00033039570374253314, 'epoch': 4.97}

 41%|████▏     | 11623/28080 [22:57:55<32:22:48,  7.08s/it]
 41%|████▏     | 11624/28080 [22:58:02<32:24:02,  7.09s/it]
                                                           
{'loss': 0.634, 'learning_rate': 0.0003303683992111409, 'epoch': 4.97}

 41%|████▏     | 11624/28080 [22:58:02<32:24:02,  7.09s/it]
 41%|████▏     | 11625/28080 [22:58:09<32:19:52,  7.07s/it]
                                                           
{'loss': 0.5984, 'learning_rate': 0.00033034109361053, 'epoch': 4.97}

 41%|████▏     | 11625/28080 [22:58:09<32:19:52,  7.07s/it]
 41%|████▏     | 11626/28080 [22:58:16<32:15:32,  7.06s/it]
                                                           
{'loss': 0.6306, 'learning_rate': 0.00033031378694106385, 'epoch': 4.97}

 41%|████▏     | 11626/28080 [22:58:16<32:15:32,  7.06s/it]
 41%|████▏     | 11627/28080 [22:58:23<32:19:32,  7.07s/it]
                                                           
{'loss': 0.6161, 'learning_rate': 0.00033028647920310553, 'epoch': 4.97}

 41%|████▏     | 11627/28080 [22:58:23<32:19:32,  7.07s/it]
 41%|████▏     | 11628/28080 [22:58:30<32:10:17,  7.04s/it]
                                                           
{'loss': 0.6266, 'learning_rate': 0.00033025917039701845, 'epoch': 4.97}

 41%|████▏     | 11628/28080 [22:58:30<32:10:17,  7.04s/it]
 41%|████▏     | 11629/28080 [22:58:37<32:09:05,  7.04s/it]
                                                           
{'loss': 0.6342, 'learning_rate': 0.0003302318605231659, 'epoch': 4.97}

 41%|████▏     | 11629/28080 [22:58:37<32:09:05,  7.04s/it]
 41%|████▏     | 11630/28080 [22:58:44<32:14:17,  7.06s/it]
                                                           
{'loss': 0.6155, 'learning_rate': 0.00033020454958191113, 'epoch': 4.97}

 41%|████▏     | 11630/28080 [22:58:44<32:14:17,  7.06s/it]
 41%|████▏     | 11631/28080 [22:58:51<32:14:02,  7.05s/it]
                                                           
{'loss': 0.6212, 'learning_rate': 0.00033017723757361775, 'epoch': 4.97}

 41%|████▏     | 11631/28080 [22:58:51<32:14:02,  7.05s/it]
 41%|████▏     | 11632/28080 [22:58:58<32:15:47,  7.06s/it]
                                                           
{'loss': 0.6245, 'learning_rate': 0.00033014992449864876, 'epoch': 4.97}

 41%|████▏     | 11632/28080 [22:58:58<32:15:47,  7.06s/it]
 41%|████▏     | 11633/28080 [22:59:05<32:17:36,  7.07s/it]
                                                           
{'loss': 0.6363, 'learning_rate': 0.00033012261035736786, 'epoch': 4.97}

 41%|████▏     | 11633/28080 [22:59:05<32:17:36,  7.07s/it]
 41%|████▏     | 11634/28080 [22:59:12<32:14:15,  7.06s/it]
                                                           
{'loss': 0.6548, 'learning_rate': 0.0003300952951501382, 'epoch': 4.97}

 41%|████▏     | 11634/28080 [22:59:12<32:14:15,  7.06s/it]
 41%|████▏     | 11635/28080 [22:59:19<32:13:38,  7.05s/it]
                                                           
{'loss': 0.6337, 'learning_rate': 0.0003300679788773233, 'epoch': 4.97}

 41%|████▏     | 11635/28080 [22:59:19<32:13:38,  7.05s/it]
 41%|████▏     | 11636/28080 [22:59:26<32:19:21,  7.08s/it]
                                                           
{'loss': 0.6131, 'learning_rate': 0.00033004066153928654, 'epoch': 4.97}

 41%|████▏     | 11636/28080 [22:59:26<32:19:21,  7.08s/it]
 41%|████▏     | 11637/28080 [22:59:33<32:17:15,  7.07s/it]
                                                           
{'loss': 0.619, 'learning_rate': 0.0003300133431363913, 'epoch': 4.97}

 41%|████▏     | 11637/28080 [22:59:33<32:17:15,  7.07s/it]
 41%|████▏     | 11638/28080 [22:59:41<32:25:13,  7.10s/it]
                                                           
{'loss': 0.6425, 'learning_rate': 0.00032998602366900116, 'epoch': 4.97}

 41%|████▏     | 11638/28080 [22:59:41<32:25:13,  7.10s/it]
 41%|████▏     | 11639/28080 [22:59:48<32:25:37,  7.10s/it]
                                                           
{'loss': 0.6113, 'learning_rate': 0.00032995870313747943, 'epoch': 4.97}

 41%|████▏     | 11639/28080 [22:59:48<32:25:37,  7.10s/it]
 41%|████▏     | 11640/28080 [22:59:55<32:26:02,  7.10s/it]
                                                           
{'loss': 0.6334, 'learning_rate': 0.0003299313815421897, 'epoch': 4.97}

 41%|████▏     | 11640/28080 [22:59:55<32:26:02,  7.10s/it]
 41%|████▏     | 11641/28080 [23:00:02<32:23:13,  7.09s/it]
                                                           
{'loss': 0.6297, 'learning_rate': 0.0003299040588834954, 'epoch': 4.97}

 41%|████▏     | 11641/28080 [23:00:02<32:23:13,  7.09s/it]
 41%|████▏     | 11642/28080 [23:00:09<32:25:00,  7.10s/it]
                                                           
{'loss': 0.6239, 'learning_rate': 0.00032987673516175997, 'epoch': 4.97}

 41%|████▏     | 11642/28080 [23:00:09<32:25:00,  7.10s/it]
 41%|████▏     | 11643/28080 [23:00:16<32:33:39,  7.13s/it]
                                                           
{'loss': 0.607, 'learning_rate': 0.000329849410377347, 'epoch': 4.97}

 41%|████▏     | 11643/28080 [23:00:16<32:33:39,  7.13s/it]
 41%|████▏     | 11644/28080 [23:00:23<32:21:02,  7.09s/it]
                                                           
{'loss': 0.6585, 'learning_rate': 0.00032982208453062004, 'epoch': 4.97}

 41%|████▏     | 11644/28080 [23:00:23<32:21:02,  7.09s/it]
 41%|████▏     | 11645/28080 [23:00:30<32:19:48,  7.08s/it]
                                                           
{'loss': 0.6201, 'learning_rate': 0.00032979475762194257, 'epoch': 4.97}

 41%|████▏     | 11645/28080 [23:00:30<32:19:48,  7.08s/it]
 41%|████▏     | 11646/28080 [23:00:37<32:24:06,  7.10s/it]
                                                           
{'loss': 0.6072, 'learning_rate': 0.00032976742965167813, 'epoch': 4.98}

 41%|████▏     | 11646/28080 [23:00:37<32:24:06,  7.10s/it]
 41%|████▏     | 11647/28080 [23:00:44<32:26:22,  7.11s/it]
                                                           
{'loss': 0.6166, 'learning_rate': 0.0003297401006201903, 'epoch': 4.98}

 41%|████▏     | 11647/28080 [23:00:44<32:26:22,  7.11s/it]
 41%|████▏     | 11648/28080 [23:00:52<32:26:19,  7.11s/it]
                                                           
{'loss': 0.5997, 'learning_rate': 0.00032971277052784283, 'epoch': 4.98}

 41%|████▏     | 11648/28080 [23:00:52<32:26:19,  7.11s/it]
 41%|████▏     | 11649/28080 [23:00:59<32:34:36,  7.14s/it]
                                                           
{'loss': 0.6098, 'learning_rate': 0.0003296854393749991, 'epoch': 4.98}

 41%|████▏     | 11649/28080 [23:00:59<32:34:36,  7.14s/it]
 41%|████▏     | 11650/28080 [23:01:06<32:29:26,  7.12s/it]
                                                           
{'loss': 0.6336, 'learning_rate': 0.00032965810716202283, 'epoch': 4.98}

 41%|████▏     | 11650/28080 [23:01:06<32:29:26,  7.12s/it]
 41%|████▏     | 11651/28080 [23:01:13<32:21:46,  7.09s/it]
                                                           
{'loss': 0.6285, 'learning_rate': 0.00032963077388927756, 'epoch': 4.98}

 41%|████▏     | 11651/28080 [23:01:13<32:21:46,  7.09s/it]
 41%|████▏     | 11652/28080 [23:01:20<32:20:24,  7.09s/it]
                                                           
{'loss': 0.6189, 'learning_rate': 0.00032960343955712706, 'epoch': 4.98}

 41%|████▏     | 11652/28080 [23:01:20<32:20:24,  7.09s/it]
 41%|████▏     | 11653/28080 [23:01:27<32:13:45,  7.06s/it]
                                                           
{'loss': 0.6247, 'learning_rate': 0.0003295761041659349, 'epoch': 4.98}

 41%|████▏     | 11653/28080 [23:01:27<32:13:45,  7.06s/it]
 42%|████▏     | 11654/28080 [23:01:34<32:11:19,  7.05s/it]
                                                           
{'loss': 0.6221, 'learning_rate': 0.00032954876771606475, 'epoch': 4.98}

 42%|████▏     | 11654/28080 [23:01:34<32:11:19,  7.05s/it]
 42%|████▏     | 11655/28080 [23:01:41<32:04:48,  7.03s/it]
                                                           
{'loss': 0.642, 'learning_rate': 0.0003295214302078803, 'epoch': 4.98}

 42%|████▏     | 11655/28080 [23:01:41<32:04:48,  7.03s/it]
 42%|████▏     | 11656/28080 [23:01:48<32:09:29,  7.05s/it]
                                                           
{'loss': 0.6281, 'learning_rate': 0.00032949409164174524, 'epoch': 4.98}

 42%|████▏     | 11656/28080 [23:01:48<32:09:29,  7.05s/it]
 42%|████▏     | 11657/28080 [23:01:55<32:22:37,  7.10s/it]
                                                           
{'loss': 0.6183, 'learning_rate': 0.0003294667520180235, 'epoch': 4.98}

 42%|████▏     | 11657/28080 [23:01:55<32:22:37,  7.10s/it]
 42%|████▏     | 11658/28080 [23:02:02<32:19:56,  7.09s/it]
                                                           
{'loss': 0.5904, 'learning_rate': 0.00032943941133707833, 'epoch': 4.98}

 42%|████▏     | 11658/28080 [23:02:02<32:19:56,  7.09s/it]
 42%|████▏     | 11659/28080 [23:02:09<32:22:09,  7.10s/it]
                                                           
{'loss': 0.6156, 'learning_rate': 0.00032941206959927395, 'epoch': 4.98}

 42%|████▏     | 11659/28080 [23:02:09<32:22:09,  7.10s/it]
 42%|████▏     | 11660/28080 [23:02:17<32:24:31,  7.11s/it]
                                                           
{'loss': 0.6193, 'learning_rate': 0.0003293847268049738, 'epoch': 4.98}

 42%|████▏     | 11660/28080 [23:02:17<32:24:31,  7.11s/it]
 42%|████▏     | 11661/28080 [23:02:24<32:25:04,  7.11s/it]
                                                           
{'loss': 0.6215, 'learning_rate': 0.0003293573829545418, 'epoch': 4.98}

 42%|████▏     | 11661/28080 [23:02:24<32:25:04,  7.11s/it]
 42%|████▏     | 11662/28080 [23:02:31<32:24:29,  7.11s/it]
                                                           
{'loss': 0.632, 'learning_rate': 0.0003293300380483417, 'epoch': 4.98}

 42%|████▏     | 11662/28080 [23:02:31<32:24:29,  7.11s/it]
 42%|████▏     | 11663/28080 [23:02:38<32:22:39,  7.10s/it]
                                                           
{'loss': 0.6142, 'learning_rate': 0.00032930269208673716, 'epoch': 4.98}

 42%|████▏     | 11663/28080 [23:02:38<32:22:39,  7.10s/it]
 42%|████▏     | 11664/28080 [23:02:45<32:14:12,  7.07s/it]
                                                           
{'loss': 0.6341, 'learning_rate': 0.00032927534507009226, 'epoch': 4.98}

 42%|████▏     | 11664/28080 [23:02:45<32:14:12,  7.07s/it]
 42%|████▏     | 11665/28080 [23:02:52<32:22:19,  7.10s/it]
                                                           
{'loss': 0.63, 'learning_rate': 0.0003292479969987706, 'epoch': 4.98}

 42%|████▏     | 11665/28080 [23:02:52<32:22:19,  7.10s/it]
 42%|████▏     | 11666/28080 [23:02:59<32:16:16,  7.08s/it]
                                                           
{'loss': 0.6321, 'learning_rate': 0.0003292206478731362, 'epoch': 4.98}

 42%|████▏     | 11666/28080 [23:02:59<32:16:16,  7.08s/it]
 42%|████▏     | 11667/28080 [23:03:06<32:20:52,  7.10s/it]
                                                           
{'loss': 0.6262, 'learning_rate': 0.00032919329769355273, 'epoch': 4.98}

 42%|████▏     | 11667/28080 [23:03:06<32:20:52,  7.10s/it]
 42%|████▏     | 11668/28080 [23:03:13<32:22:29,  7.10s/it]
                                                           
{'loss': 0.6194, 'learning_rate': 0.0003291659464603841, 'epoch': 4.98}

 42%|████▏     | 11668/28080 [23:03:13<32:22:29,  7.10s/it]
 42%|████▏     | 11669/28080 [23:03:20<32:18:50,  7.09s/it]
                                                           
{'loss': 0.6036, 'learning_rate': 0.00032913859417399427, 'epoch': 4.98}

 42%|████▏     | 11669/28080 [23:03:20<32:18:50,  7.09s/it]
 42%|████▏     | 11670/28080 [23:03:27<32:20:55,  7.10s/it]
                                                           
{'loss': 0.6461, 'learning_rate': 0.0003291112408347471, 'epoch': 4.99}

 42%|████▏     | 11670/28080 [23:03:27<32:20:55,  7.10s/it]
 42%|████▏     | 11671/28080 [23:03:35<32:23:08,  7.11s/it]
                                                           
{'loss': 0.6127, 'learning_rate': 0.00032908388644300643, 'epoch': 4.99}

 42%|████▏     | 11671/28080 [23:03:35<32:23:08,  7.11s/it]
 42%|████▏     | 11672/28080 [23:03:42<32:26:04,  7.12s/it]
                                                           
{'loss': 0.6111, 'learning_rate': 0.00032905653099913625, 'epoch': 4.99}

 42%|████▏     | 11672/28080 [23:03:42<32:26:04,  7.12s/it]
 42%|████▏     | 11673/28080 [23:03:49<32:16:22,  7.08s/it]
                                                           
{'loss': 0.6335, 'learning_rate': 0.0003290291745035005, 'epoch': 4.99}

 42%|████▏     | 11673/28080 [23:03:49<32:16:22,  7.08s/it]
 42%|████▏     | 11674/28080 [23:03:56<32:23:01,  7.11s/it]
                                                           
{'loss': 0.6288, 'learning_rate': 0.00032900181695646313, 'epoch': 4.99}

 42%|████▏     | 11674/28080 [23:03:56<32:23:01,  7.11s/it]
 42%|████▏     | 11675/28080 [23:04:03<32:22:47,  7.11s/it]
                                                           
{'loss': 0.6357, 'learning_rate': 0.000328974458358388, 'epoch': 4.99}

 42%|████▏     | 11675/28080 [23:04:03<32:22:47,  7.11s/it]
 42%|████▏     | 11676/28080 [23:04:10<32:17:40,  7.09s/it]
                                                           
{'loss': 0.6372, 'learning_rate': 0.0003289470987096394, 'epoch': 4.99}

 42%|████▏     | 11676/28080 [23:04:10<32:17:40,  7.09s/it]
 42%|████▏     | 11677/28080 [23:04:17<32:12:02,  7.07s/it]
                                                           
{'loss': 0.6214, 'learning_rate': 0.0003289197380105808, 'epoch': 4.99}

 42%|████▏     | 11677/28080 [23:04:17<32:12:02,  7.07s/it]
 42%|████▏     | 11678/28080 [23:04:24<32:10:21,  7.06s/it]
                                                           
{'loss': 0.6251, 'learning_rate': 0.00032889237626157665, 'epoch': 4.99}

 42%|████▏     | 11678/28080 [23:04:24<32:10:21,  7.06s/it]
 42%|████▏     | 11679/28080 [23:04:31<32:14:53,  7.08s/it]
                                                           
{'loss': 0.6282, 'learning_rate': 0.0003288650134629909, 'epoch': 4.99}

 42%|████▏     | 11679/28080 [23:04:31<32:14:53,  7.08s/it]
 42%|████▏     | 11680/28080 [23:04:38<32:06:40,  7.05s/it]
                                                           
{'loss': 0.6224, 'learning_rate': 0.00032883764961518734, 'epoch': 4.99}

 42%|████▏     | 11680/28080 [23:04:38<32:06:40,  7.05s/it]
 42%|████▏     | 11681/28080 [23:04:45<32:09:56,  7.06s/it]
                                                           
{'loss': 0.6185, 'learning_rate': 0.0003288102847185303, 'epoch': 4.99}

 42%|████▏     | 11681/28080 [23:04:45<32:09:56,  7.06s/it]
 42%|████▏     | 11682/28080 [23:04:52<32:06:24,  7.05s/it]
                                                           
{'loss': 0.6329, 'learning_rate': 0.00032878291877338366, 'epoch': 4.99}

 42%|████▏     | 11682/28080 [23:04:52<32:06:24,  7.05s/it]
 42%|████▏     | 11683/28080 [23:04:59<32:08:47,  7.06s/it]
                                                           
{'loss': 0.6158, 'learning_rate': 0.00032875555178011164, 'epoch': 4.99}

 42%|████▏     | 11683/28080 [23:04:59<32:08:47,  7.06s/it]
 42%|████▏     | 11684/28080 [23:05:06<32:08:36,  7.06s/it]
                                                           
{'loss': 0.6378, 'learning_rate': 0.0003287281837390782, 'epoch': 4.99}

 42%|████▏     | 11684/28080 [23:05:06<32:08:36,  7.06s/it]
 42%|████▏     | 11685/28080 [23:05:14<32:09:29,  7.06s/it]
                                                           
{'loss': 0.6235, 'learning_rate': 0.00032870081465064747, 'epoch': 4.99}

 42%|████▏     | 11685/28080 [23:05:14<32:09:29,  7.06s/it]
 42%|████▏     | 11686/28080 [23:05:21<32:21:06,  7.10s/it]
                                                           
{'loss': 0.6232, 'learning_rate': 0.00032867344451518364, 'epoch': 4.99}

 42%|████▏     | 11686/28080 [23:05:21<32:21:06,  7.10s/it]
 42%|████▏     | 11687/28080 [23:05:28<32:29:37,  7.14s/it]
                                                           
{'loss': 0.631, 'learning_rate': 0.00032864607333305077, 'epoch': 4.99}

 42%|████▏     | 11687/28080 [23:05:28<32:29:37,  7.14s/it]
 42%|████▏     | 11688/28080 [23:05:35<32:39:00,  7.17s/it]
                                                           
{'loss': 0.6106, 'learning_rate': 0.00032861870110461304, 'epoch': 4.99}

 42%|████▏     | 11688/28080 [23:05:35<32:39:00,  7.17s/it]
 42%|████▏     | 11689/28080 [23:05:42<32:45:09,  7.19s/it]
                                                           
{'loss': 0.6326, 'learning_rate': 0.0003285913278302346, 'epoch': 4.99}

 42%|████▏     | 11689/28080 [23:05:42<32:45:09,  7.19s/it]
 42%|████▏     | 11690/28080 [23:05:49<32:32:49,  7.15s/it]
                                                           
{'loss': 0.6334, 'learning_rate': 0.0003285639535102796, 'epoch': 4.99}

 42%|████▏     | 11690/28080 [23:05:50<32:32:49,  7.15s/it]
 42%|████▏     | 11691/28080 [23:05:57<32:30:02,  7.14s/it]
                                                           
{'loss': 0.6343, 'learning_rate': 0.00032853657814511234, 'epoch': 4.99}

 42%|████▏     | 11691/28080 [23:05:57<32:30:02,  7.14s/it]
 42%|████▏     | 11692/28080 [23:06:04<32:31:51,  7.15s/it]
                                                           
{'loss': 0.5907, 'learning_rate': 0.0003285092017350968, 'epoch': 4.99}

 42%|████▏     | 11692/28080 [23:06:04<32:31:51,  7.15s/it]
 42%|████▏     | 11693/28080 [23:06:11<32:24:34,  7.12s/it]
                                                           
{'loss': 0.6197, 'learning_rate': 0.00032848182428059743, 'epoch': 5.0}

 42%|████▏     | 11693/28080 [23:06:11<32:24:34,  7.12s/it]
 42%|████▏     | 11694/28080 [23:06:18<32:17:34,  7.09s/it]
                                                           
{'loss': 0.646, 'learning_rate': 0.0003284544457819783, 'epoch': 5.0}

 42%|████▏     | 11694/28080 [23:06:18<32:17:34,  7.09s/it]
 42%|████▏     | 11695/28080 [23:06:25<32:32:39,  7.15s/it]
                                                           
{'loss': 0.6346, 'learning_rate': 0.00032842706623960365, 'epoch': 5.0}

 42%|████▏     | 11695/28080 [23:06:25<32:32:39,  7.15s/it]
 42%|████▏     | 11696/28080 [23:06:32<32:27:11,  7.13s/it]
                                                           
{'loss': 0.6236, 'learning_rate': 0.0003283996856538379, 'epoch': 5.0}

 42%|████▏     | 11696/28080 [23:06:32<32:27:11,  7.13s/it]
 42%|████▏     | 11697/28080 [23:06:39<32:33:31,  7.15s/it]
                                                           
{'loss': 0.6126, 'learning_rate': 0.00032837230402504516, 'epoch': 5.0}

 42%|████▏     | 11697/28080 [23:06:39<32:33:31,  7.15s/it]
 42%|████▏     | 11698/28080 [23:06:47<32:28:56,  7.14s/it]
                                                           
{'loss': 0.605, 'learning_rate': 0.0003283449213535898, 'epoch': 5.0}

 42%|████▏     | 11698/28080 [23:06:47<32:28:56,  7.14s/it]
 42%|████▏     | 11699/28080 [23:06:54<32:29:28,  7.14s/it]
                                                           
{'loss': 0.629, 'learning_rate': 0.00032831753763983603, 'epoch': 5.0}

 42%|████▏     | 11699/28080 [23:06:54<32:29:28,  7.14s/it]
 42%|████▏     | 11700/28080 [23:07:01<32:33:27,  7.16s/it]
                                                           
{'loss': 0.6352, 'learning_rate': 0.00032829015288414823, 'epoch': 5.0}

 42%|████▏     | 11700/28080 [23:07:01<32:33:27,  7.16s/it]
 42%|████▏     | 11701/28080 [23:07:08<32:16:43,  7.09s/it]
                                                           
{'loss': 0.6614, 'learning_rate': 0.00032826276708689076, 'epoch': 5.0}

 42%|████▏     | 11701/28080 [23:07:08<32:16:43,  7.09s/it]
 42%|████▏     | 11702/28080 [23:07:15<32:29:27,  7.14s/it]
                                                           
{'loss': 0.6265, 'learning_rate': 0.0003282353802484278, 'epoch': 5.0}

 42%|████▏     | 11702/28080 [23:07:15<32:29:27,  7.14s/it]
 42%|████▏     | 11703/28080 [23:07:22<32:33:01,  7.16s/it]
                                                           
{'loss': 0.6268, 'learning_rate': 0.0003282079923691239, 'epoch': 5.0}

 42%|████▏     | 11703/28080 [23:07:22<32:33:01,  7.16s/it]
 42%|████▏     | 11704/28080 [23:07:29<32:25:54,  7.13s/it]
                                                           
{'loss': 0.61, 'learning_rate': 0.00032818060344934336, 'epoch': 5.0}

 42%|████▏     | 11704/28080 [23:07:29<32:25:54,  7.13s/it]
 42%|████▏     | 11705/28080 [23:07:37<33:15:20,  7.31s/it]
                                                           
{'loss': 0.6478, 'learning_rate': 0.00032815321348945054, 'epoch': 5.0}

 42%|████▏     | 11705/28080 [23:07:37<33:15:20,  7.31s/it]
 42%|████▏     | 11706/28080 [23:07:45<33:24:51,  7.35s/it]
                                                           
{'loss': 0.628, 'learning_rate': 0.00032812582248980984, 'epoch': 5.0}

 42%|████▏     | 11706/28080 [23:07:45<33:24:51,  7.35s/it]
 42%|████▏     | 11707/28080 [23:07:52<33:08:51,  7.29s/it]
                                                           
{'loss': 0.6449, 'learning_rate': 0.0003280984304507856, 'epoch': 5.0}

 42%|████▏     | 11707/28080 [23:07:52<33:08:51,  7.29s/it]
 42%|████▏     | 11708/28080 [23:07:59<32:55:23,  7.24s/it]
                                                           
{'loss': 0.6111, 'learning_rate': 0.0003280710373727424, 'epoch': 5.0}

 42%|████▏     | 11708/28080 [23:07:59<32:55:23,  7.24s/it]
 42%|████▏     | 11709/28080 [23:08:06<32:50:45,  7.22s/it]
                                                           
{'loss': 0.6137, 'learning_rate': 0.00032804364325604454, 'epoch': 5.0}

 42%|████▏     | 11709/28080 [23:08:06<32:50:45,  7.22s/it]
 42%|████▏     | 11710/28080 [23:08:13<32:41:44,  7.19s/it]
                                                           
{'loss': 0.6339, 'learning_rate': 0.00032801624810105656, 'epoch': 5.0}

 42%|████▏     | 11710/28080 [23:08:13<32:41:44,  7.19s/it]
 42%|████▏     | 11711/28080 [23:08:20<32:41:28,  7.19s/it]
                                                           
{'loss': 0.6235, 'learning_rate': 0.0003279888519081428, 'epoch': 5.0}

 42%|████▏     | 11711/28080 [23:08:20<32:41:28,  7.19s/it]
 42%|████▏     | 11712/28080 [23:08:27<32:40:37,  7.19s/it]
                                                           
{'loss': 0.6327, 'learning_rate': 0.0003279614546776679, 'epoch': 5.0}

 42%|████▏     | 11712/28080 [23:08:27<32:40:37,  7.19s/it]
 42%|████▏     | 11713/28080 [23:08:35<32:37:42,  7.18s/it]
                                                           
{'loss': 0.6195, 'learning_rate': 0.0003279340564099963, 'epoch': 5.0}

 42%|████▏     | 11713/28080 [23:08:35<32:37:42,  7.18s/it]
 42%|████▏     | 11714/28080 [23:08:42<32:39:31,  7.18s/it]
                                                           
{'loss': 0.6283, 'learning_rate': 0.00032790665710549246, 'epoch': 5.0}

 42%|████▏     | 11714/28080 [23:08:42<32:39:31,  7.18s/it]
 42%|████▏     | 11715/28080 [23:08:49<32:33:34,  7.16s/it]
                                                           
{'loss': 0.6158, 'learning_rate': 0.00032787925676452083, 'epoch': 5.0}

 42%|████▏     | 11715/28080 [23:08:49<32:33:34,  7.16s/it]
 42%|████▏     | 11716/28080 [23:08:56<32:29:53,  7.15s/it]
                                                           
{'loss': 0.6286, 'learning_rate': 0.00032785185538744614, 'epoch': 5.0}

 42%|████▏     | 11716/28080 [23:08:56<32:29:53,  7.15s/it]
 42%|████▏     | 11717/28080 [23:09:03<32:24:46,  7.13s/it]
                                                           
{'loss': 0.6064, 'learning_rate': 0.0003278244529746328, 'epoch': 5.01}

 42%|████▏     | 11717/28080 [23:09:03<32:24:46,  7.13s/it]
 42%|████▏     | 11718/28080 [23:09:10<32:26:43,  7.14s/it]
                                                           
{'loss': 0.6207, 'learning_rate': 0.0003277970495264454, 'epoch': 5.01}

 42%|████▏     | 11718/28080 [23:09:10<32:26:43,  7.14s/it]
 42%|████▏     | 11719/28080 [23:09:17<32:27:51,  7.14s/it]
                                                           
{'loss': 0.6321, 'learning_rate': 0.00032776964504324847, 'epoch': 5.01}

 42%|████▏     | 11719/28080 [23:09:17<32:27:51,  7.14s/it]
 42%|████▏     | 11720/28080 [23:09:25<32:50:53,  7.23s/it]
                                                           
{'loss': 0.6268, 'learning_rate': 0.00032774223952540673, 'epoch': 5.01}

 42%|████▏     | 11720/28080 [23:09:25<32:50:53,  7.23s/it]
 42%|████▏     | 11721/28080 [23:09:32<32:39:41,  7.19s/it]
                                                           
{'loss': 0.6026, 'learning_rate': 0.0003277148329732846, 'epoch': 5.01}

 42%|████▏     | 11721/28080 [23:09:32<32:39:41,  7.19s/it]
 42%|████▏     | 11722/28080 [23:09:39<32:36:45,  7.18s/it]
                                                           
{'loss': 0.6112, 'learning_rate': 0.0003276874253872468, 'epoch': 5.01}

 42%|████▏     | 11722/28080 [23:09:39<32:36:45,  7.18s/it]
 42%|████▏     | 11723/28080 [23:09:46<32:31:39,  7.16s/it]
                                                           
{'loss': 0.6339, 'learning_rate': 0.00032766001676765797, 'epoch': 5.01}

 42%|████▏     | 11723/28080 [23:09:46<32:31:39,  7.16s/it]
 42%|████▏     | 11724/28080 [23:09:53<32:24:25,  7.13s/it]
                                                           
{'loss': 0.6461, 'learning_rate': 0.0003276326071148828, 'epoch': 5.01}

 42%|████▏     | 11724/28080 [23:09:53<32:24:25,  7.13s/it]
 42%|████▏     | 11725/28080 [23:10:00<32:25:33,  7.14s/it]
                                                           
{'loss': 0.6377, 'learning_rate': 0.00032760519642928583, 'epoch': 5.01}

 42%|████▏     | 11725/28080 [23:10:00<32:25:33,  7.14s/it]
 42%|████▏     | 11726/28080 [23:10:08<32:27:07,  7.14s/it]
                                                           
{'loss': 0.6086, 'learning_rate': 0.0003275777847112317, 'epoch': 5.01}

 42%|████▏     | 11726/28080 [23:10:08<32:27:07,  7.14s/it]
 42%|████▏     | 11727/28080 [23:10:15<32:26:22,  7.14s/it]
                                                           
{'loss': 0.599, 'learning_rate': 0.0003275503719610853, 'epoch': 5.01}

 42%|████▏     | 11727/28080 [23:10:15<32:26:22,  7.14s/it]
 42%|████▏     | 11728/28080 [23:10:22<32:22:17,  7.13s/it]
                                                           
{'loss': 0.5966, 'learning_rate': 0.00032752295817921117, 'epoch': 5.01}

 42%|████▏     | 11728/28080 [23:10:22<32:22:17,  7.13s/it]
 42%|████▏     | 11729/28080 [23:10:29<32:29:22,  7.15s/it]
                                                           
{'loss': 0.6163, 'learning_rate': 0.0003274955433659741, 'epoch': 5.01}

 42%|████▏     | 11729/28080 [23:10:29<32:29:22,  7.15s/it]
 42%|████▏     | 11730/28080 [23:10:36<32:35:47,  7.18s/it]
                                                           
{'loss': 0.6398, 'learning_rate': 0.0003274681275217387, 'epoch': 5.01}

 42%|████▏     | 11730/28080 [23:10:36<32:35:47,  7.18s/it]
 42%|████▏     | 11731/28080 [23:10:43<32:29:48,  7.16s/it]
                                                           
{'loss': 0.6289, 'learning_rate': 0.0003274407106468698, 'epoch': 5.01}

 42%|████▏     | 11731/28080 [23:10:43<32:29:48,  7.16s/it]
 42%|████▏     | 11732/28080 [23:10:50<32:17:25,  7.11s/it]
                                                           
{'loss': 0.6317, 'learning_rate': 0.00032741329274173215, 'epoch': 5.01}

 42%|████▏     | 11732/28080 [23:10:50<32:17:25,  7.11s/it]
 42%|████▏     | 11733/28080 [23:10:58<32:22:02,  7.13s/it]
                                                           
{'loss': 0.6259, 'learning_rate': 0.00032738587380669044, 'epoch': 5.01}

 42%|████▏     | 11733/28080 [23:10:58<32:22:02,  7.13s/it]
 42%|████▏     | 11734/28080 [23:11:05<32:21:40,  7.13s/it]
                                                           
{'loss': 0.6039, 'learning_rate': 0.0003273584538421096, 'epoch': 5.01}

 42%|████▏     | 11734/28080 [23:11:05<32:21:40,  7.13s/it]
 42%|████▏     | 11735/28080 [23:11:12<32:17:38,  7.11s/it]
                                                           
{'loss': 0.6307, 'learning_rate': 0.0003273310328483543, 'epoch': 5.01}

 42%|████▏     | 11735/28080 [23:11:12<32:17:38,  7.11s/it]
 42%|████▏     | 11736/28080 [23:11:19<32:30:52,  7.16s/it]
                                                           
{'loss': 0.6258, 'learning_rate': 0.0003273036108257894, 'epoch': 5.01}

 42%|████▏     | 11736/28080 [23:11:19<32:30:52,  7.16s/it]
 42%|████▏     | 11737/28080 [23:11:26<32:25:03,  7.14s/it]
                                                           
{'loss': 0.6378, 'learning_rate': 0.0003272761877747797, 'epoch': 5.01}

 42%|████▏     | 11737/28080 [23:11:26<32:25:03,  7.14s/it]
 42%|████▏     | 11738/28080 [23:11:33<32:27:48,  7.15s/it]
                                                           
{'loss': 0.619, 'learning_rate': 0.00032724876369569006, 'epoch': 5.01}

 42%|████▏     | 11738/28080 [23:11:33<32:27:48,  7.15s/it]
 42%|████▏     | 11739/28080 [23:11:41<32:33:45,  7.17s/it]
                                                           
{'loss': 0.617, 'learning_rate': 0.00032722133858888527, 'epoch': 5.01}

 42%|████▏     | 11739/28080 [23:11:41<32:33:45,  7.17s/it]
 42%|████▏     | 11740/28080 [23:11:48<32:27:23,  7.15s/it]
                                                           
{'loss': 0.6131, 'learning_rate': 0.00032719391245473025, 'epoch': 5.02}

 42%|████▏     | 11740/28080 [23:11:48<32:27:23,  7.15s/it]
 42%|████▏     | 11741/28080 [23:11:55<32:33:31,  7.17s/it]
                                                           
{'loss': 0.6267, 'learning_rate': 0.0003271664852935899, 'epoch': 5.02}

 42%|████▏     | 11741/28080 [23:11:55<32:33:31,  7.17s/it]
 42%|████▏     | 11742/28080 [23:12:02<32:36:00,  7.18s/it]
                                                           
{'loss': 0.6278, 'learning_rate': 0.00032713905710582907, 'epoch': 5.02}

 42%|████▏     | 11742/28080 [23:12:02<32:36:00,  7.18s/it]
 42%|████▏     | 11743/28080 [23:12:09<32:33:33,  7.17s/it]
                                                           
{'loss': 0.6347, 'learning_rate': 0.0003271116278918126, 'epoch': 5.02}

 42%|████▏     | 11743/28080 [23:12:09<32:33:33,  7.17s/it]
 42%|████▏     | 11744/28080 [23:12:16<32:25:05,  7.14s/it]
                                                           
{'loss': 0.6482, 'learning_rate': 0.00032708419765190553, 'epoch': 5.02}

 42%|████▏     | 11744/28080 [23:12:16<32:25:05,  7.14s/it]
 42%|████▏     | 11745/28080 [23:12:23<32:20:14,  7.13s/it]
                                                           
{'loss': 0.6337, 'learning_rate': 0.00032705676638647267, 'epoch': 5.02}

 42%|████▏     | 11745/28080 [23:12:23<32:20:14,  7.13s/it]
 42%|████▏     | 11746/28080 [23:12:30<32:18:57,  7.12s/it]
                                                           
{'loss': 0.632, 'learning_rate': 0.00032702933409587917, 'epoch': 5.02}

 42%|████▏     | 11746/28080 [23:12:30<32:18:57,  7.12s/it]
 42%|████▏     | 11747/28080 [23:12:38<32:23:29,  7.14s/it]
                                                           
{'loss': 0.6298, 'learning_rate': 0.0003270019007804897, 'epoch': 5.02}

 42%|████▏     | 11747/28080 [23:12:38<32:23:29,  7.14s/it]
 42%|████▏     | 11748/28080 [23:12:45<32:21:06,  7.13s/it]
                                                           
{'loss': 0.6241, 'learning_rate': 0.00032697446644066946, 'epoch': 5.02}

 42%|████▏     | 11748/28080 [23:12:45<32:21:06,  7.13s/it]
 42%|████▏     | 11749/28080 [23:12:52<32:13:40,  7.10s/it]
                                                           
{'loss': 0.6215, 'learning_rate': 0.0003269470310767833, 'epoch': 5.02}

 42%|████▏     | 11749/28080 [23:12:52<32:13:40,  7.10s/it]
 42%|████▏     | 11750/28080 [23:12:59<32:24:31,  7.14s/it]
                                                           
{'loss': 0.6275, 'learning_rate': 0.0003269195946891963, 'epoch': 5.02}

 42%|████▏     | 11750/28080 [23:12:59<32:24:31,  7.14s/it]
 42%|████▏     | 11751/28080 [23:13:06<32:29:51,  7.16s/it]
                                                           
{'loss': 0.6273, 'learning_rate': 0.0003268921572782734, 'epoch': 5.02}

 42%|████▏     | 11751/28080 [23:13:06<32:29:51,  7.16s/it]
 42%|████▏     | 11752/28080 [23:13:13<32:23:38,  7.14s/it]
                                                           
{'loss': 0.6499, 'learning_rate': 0.00032686471884437975, 'epoch': 5.02}

 42%|████▏     | 11752/28080 [23:13:13<32:23:38,  7.14s/it]
 42%|████▏     | 11753/28080 [23:13:20<32:16:39,  7.12s/it]
                                                           
{'loss': 0.642, 'learning_rate': 0.00032683727938788025, 'epoch': 5.02}

 42%|████▏     | 11753/28080 [23:13:20<32:16:39,  7.12s/it]
 42%|████▏     | 11754/28080 [23:13:28<32:20:11,  7.13s/it]
                                                           
{'loss': 0.624, 'learning_rate': 0.0003268098389091401, 'epoch': 5.02}

 42%|████▏     | 11754/28080 [23:13:28<32:20:11,  7.13s/it]
 42%|████▏     | 11755/28080 [23:13:35<32:32:20,  7.18s/it]
                                                           
{'loss': 0.6099, 'learning_rate': 0.00032678239740852424, 'epoch': 5.02}

 42%|████▏     | 11755/28080 [23:13:35<32:32:20,  7.18s/it]
 42%|████▏     | 11756/28080 [23:13:42<32:36:49,  7.19s/it]
                                                           
{'loss': 0.5884, 'learning_rate': 0.0003267549548863977, 'epoch': 5.02}

 42%|████▏     | 11756/28080 [23:13:42<32:36:49,  7.19s/it]
 42%|████▏     | 11757/28080 [23:13:49<32:33:08,  7.18s/it]
                                                           
{'loss': 0.6279, 'learning_rate': 0.00032672751134312574, 'epoch': 5.02}

 42%|████▏     | 11757/28080 [23:13:49<32:33:08,  7.18s/it]
 42%|████▏     | 11758/28080 [23:13:56<32:24:38,  7.15s/it]
                                                           
{'loss': 0.63, 'learning_rate': 0.00032670006677907345, 'epoch': 5.02}

 42%|████▏     | 11758/28080 [23:13:56<32:24:38,  7.15s/it]
 42%|████▏     | 11759/28080 [23:14:03<32:16:26,  7.12s/it]
                                                           
{'loss': 0.6233, 'learning_rate': 0.0003266726211946058, 'epoch': 5.02}

 42%|████▏     | 11759/28080 [23:14:03<32:16:26,  7.12s/it]
 42%|████▏     | 11760/28080 [23:14:10<32:16:39,  7.12s/it]
                                                           
{'loss': 0.6113, 'learning_rate': 0.00032664517459008813, 'epoch': 5.02}

 42%|████▏     | 11760/28080 [23:14:11<32:16:39,  7.12s/it]
 42%|████▏     | 11761/28080 [23:14:18<32:17:32,  7.12s/it]
                                                           
{'loss': 0.6119, 'learning_rate': 0.0003266177269658854, 'epoch': 5.02}

 42%|████▏     | 11761/28080 [23:14:18<32:17:32,  7.12s/it]
 42%|████▏     | 11762/28080 [23:14:25<32:19:34,  7.13s/it]
                                                           
{'loss': 0.6059, 'learning_rate': 0.0003265902783223629, 'epoch': 5.02}

 42%|████▏     | 11762/28080 [23:14:25<32:19:34,  7.13s/it]
 42%|████▏     | 11763/28080 [23:14:32<31:56:47,  7.05s/it]
                                                           
{'loss': 0.6261, 'learning_rate': 0.00032656282865988574, 'epoch': 5.03}

 42%|████▏     | 11763/28080 [23:14:32<31:56:47,  7.05s/it]
 42%|████▏     | 11764/28080 [23:14:39<32:05:26,  7.08s/it]
                                                           
{'loss': 0.609, 'learning_rate': 0.00032653537797881917, 'epoch': 5.03}

 42%|████▏     | 11764/28080 [23:14:39<32:05:26,  7.08s/it]
 42%|████▏     | 11765/28080 [23:14:46<32:05:16,  7.08s/it]
                                                           
{'loss': 0.6402, 'learning_rate': 0.0003265079262795283, 'epoch': 5.03}

 42%|████▏     | 11765/28080 [23:14:46<32:05:16,  7.08s/it]
 42%|████▏     | 11766/28080 [23:14:53<32:10:54,  7.10s/it]
                                                           
{'loss': 0.6481, 'learning_rate': 0.00032648047356237847, 'epoch': 5.03}

 42%|████▏     | 11766/28080 [23:14:53<32:10:54,  7.10s/it]
 42%|████▏     | 11767/28080 [23:15:00<32:12:31,  7.11s/it]
                                                           
{'loss': 0.6289, 'learning_rate': 0.00032645301982773476, 'epoch': 5.03}

 42%|████▏     | 11767/28080 [23:15:00<32:12:31,  7.11s/it]
 42%|████▏     | 11768/28080 [23:15:07<32:16:19,  7.12s/it]
                                                           
{'loss': 0.647, 'learning_rate': 0.00032642556507596256, 'epoch': 5.03}

 42%|████▏     | 11768/28080 [23:15:07<32:16:19,  7.12s/it]
 42%|████▏     | 11769/28080 [23:15:15<32:26:58,  7.16s/it]
                                                           
{'loss': 0.6161, 'learning_rate': 0.000326398109307427, 'epoch': 5.03}

 42%|████▏     | 11769/28080 [23:15:15<32:26:58,  7.16s/it]
 42%|████▏     | 11770/28080 [23:15:22<32:25:43,  7.16s/it]
                                                           
{'loss': 0.595, 'learning_rate': 0.00032637065252249343, 'epoch': 5.03}

 42%|████▏     | 11770/28080 [23:15:22<32:25:43,  7.16s/it]
 42%|████▏     | 11771/28080 [23:15:29<32:18:16,  7.13s/it]
                                                           
{'loss': 0.6341, 'learning_rate': 0.00032634319472152714, 'epoch': 5.03}

 42%|████▏     | 11771/28080 [23:15:29<32:18:16,  7.13s/it]
 42%|████▏     | 11772/28080 [23:15:36<32:18:38,  7.13s/it]
                                                           
{'loss': 0.617, 'learning_rate': 0.0003263157359048934, 'epoch': 5.03}

 42%|████▏     | 11772/28080 [23:15:36<32:18:38,  7.13s/it]
 42%|████▏     | 11773/28080 [23:15:43<32:29:55,  7.17s/it]
                                                           
{'loss': 0.6231, 'learning_rate': 0.00032628827607295745, 'epoch': 5.03}

 42%|████▏     | 11773/28080 [23:15:43<32:29:55,  7.17s/it]
 42%|████▏     | 11774/28080 [23:15:50<32:29:38,  7.17s/it]
                                                           
{'loss': 0.6208, 'learning_rate': 0.00032626081522608476, 'epoch': 5.03}

 42%|████▏     | 11774/28080 [23:15:50<32:29:38,  7.17s/it]
 42%|████▏     | 11775/28080 [23:15:58<32:31:01,  7.18s/it]
                                                           
{'loss': 0.6108, 'learning_rate': 0.0003262333533646406, 'epoch': 5.03}

 42%|████▏     | 11775/28080 [23:15:58<32:31:01,  7.18s/it]
 42%|████▏     | 11776/28080 [23:16:05<32:29:55,  7.18s/it]
                                                           
{'loss': 0.6357, 'learning_rate': 0.0003262058904889903, 'epoch': 5.03}

 42%|████▏     | 11776/28080 [23:16:05<32:29:55,  7.18s/it]
 42%|████▏     | 11777/28080 [23:16:12<32:21:26,  7.15s/it]
                                                           
{'loss': 0.6169, 'learning_rate': 0.00032617842659949926, 'epoch': 5.03}

 42%|████▏     | 11777/28080 [23:16:12<32:21:26,  7.15s/it]
 42%|████▏     | 11778/28080 [23:16:19<32:16:17,  7.13s/it]
                                                           
{'loss': 0.6313, 'learning_rate': 0.0003261509616965328, 'epoch': 5.03}

 42%|████▏     | 11778/28080 [23:16:19<32:16:17,  7.13s/it]
 42%|████▏     | 11779/28080 [23:16:26<32:40:14,  7.22s/it]
                                                           
{'loss': 0.6273, 'learning_rate': 0.0003261234957804564, 'epoch': 5.03}

 42%|████▏     | 11779/28080 [23:16:26<32:40:14,  7.22s/it]
 42%|████▏     | 11780/28080 [23:16:33<32:34:59,  7.20s/it]
                                                           
{'loss': 0.6202, 'learning_rate': 0.00032609602885163544, 'epoch': 5.03}

 42%|████▏     | 11780/28080 [23:16:33<32:34:59,  7.20s/it]
 42%|████▏     | 11781/28080 [23:16:40<32:21:08,  7.15s/it]
                                                           
{'loss': 0.6162, 'learning_rate': 0.00032606856091043523, 'epoch': 5.03}

 42%|████▏     | 11781/28080 [23:16:40<32:21:08,  7.15s/it]
 42%|████▏     | 11782/28080 [23:16:48<32:20:05,  7.14s/it]
                                                           
{'loss': 0.6482, 'learning_rate': 0.00032604109195722136, 'epoch': 5.03}

 42%|████▏     | 11782/28080 [23:16:48<32:20:05,  7.14s/it]
 42%|████▏     | 11783/28080 [23:16:55<32:20:01,  7.14s/it]
                                                           
{'loss': 0.6344, 'learning_rate': 0.0003260136219923592, 'epoch': 5.03}

 42%|████▏     | 11783/28080 [23:16:55<32:20:01,  7.14s/it]
 42%|████▏     | 11784/28080 [23:17:02<32:24:49,  7.16s/it]
                                                           
{'loss': 0.6073, 'learning_rate': 0.00032598615101621424, 'epoch': 5.03}

 42%|████▏     | 11784/28080 [23:17:02<32:24:49,  7.16s/it]
 42%|████▏     | 11785/28080 [23:17:09<32:28:51,  7.18s/it]
                                                           
{'loss': 0.6218, 'learning_rate': 0.00032595867902915186, 'epoch': 5.03}

 42%|████▏     | 11785/28080 [23:17:09<32:28:51,  7.18s/it]
 42%|████▏     | 11786/28080 [23:17:16<32:15:17,  7.13s/it]
                                                           
{'loss': 0.6256, 'learning_rate': 0.0003259312060315377, 'epoch': 5.03}

 42%|████▏     | 11786/28080 [23:17:16<32:15:17,  7.13s/it]
 42%|████▏     | 11787/28080 [23:17:23<32:22:15,  7.15s/it]
                                                           
{'loss': 0.6146, 'learning_rate': 0.00032590373202373715, 'epoch': 5.04}

 42%|████▏     | 11787/28080 [23:17:23<32:22:15,  7.15s/it]
 42%|████▏     | 11788/28080 [23:17:30<32:18:21,  7.14s/it]
                                                           
{'loss': 0.6363, 'learning_rate': 0.0003258762570061157, 'epoch': 5.04}

 42%|████▏     | 11788/28080 [23:17:30<32:18:21,  7.14s/it]
 42%|████▏     | 11789/28080 [23:17:38<32:31:41,  7.19s/it]
                                                           
{'loss': 0.6153, 'learning_rate': 0.00032584878097903904, 'epoch': 5.04}

 42%|████▏     | 11789/28080 [23:17:38<32:31:41,  7.19s/it]
 42%|████▏     | 11790/28080 [23:17:45<32:30:34,  7.18s/it]
                                                           
{'loss': 0.6073, 'learning_rate': 0.00032582130394287245, 'epoch': 5.04}

 42%|████▏     | 11790/28080 [23:17:45<32:30:34,  7.18s/it]
 42%|████▏     | 11791/28080 [23:17:52<32:26:01,  7.17s/it]
                                                           
{'loss': 0.6291, 'learning_rate': 0.00032579382589798184, 'epoch': 5.04}

 42%|████▏     | 11791/28080 [23:17:52<32:26:01,  7.17s/it]
 42%|████▏     | 11792/28080 [23:17:59<32:07:43,  7.10s/it]
                                                           
{'loss': 0.6251, 'learning_rate': 0.00032576634684473236, 'epoch': 5.04}

 42%|████▏     | 11792/28080 [23:17:59<32:07:43,  7.10s/it]
 42%|████▏     | 11793/28080 [23:18:06<32:21:37,  7.15s/it]
                                                           
{'loss': 0.6272, 'learning_rate': 0.00032573886678348993, 'epoch': 5.04}

 42%|████▏     | 11793/28080 [23:18:06<32:21:37,  7.15s/it]
 42%|████▏     | 11794/28080 [23:18:13<32:11:56,  7.12s/it]
                                                           
{'loss': 0.6252, 'learning_rate': 0.0003257113857146199, 'epoch': 5.04}

 42%|████▏     | 11794/28080 [23:18:13<32:11:56,  7.12s/it]
 42%|████▏     | 11795/28080 [23:18:21<32:20:30,  7.15s/it]
                                                           
{'loss': 0.6322, 'learning_rate': 0.0003256839036384881, 'epoch': 5.04}

 42%|████▏     | 11795/28080 [23:18:21<32:20:30,  7.15s/it]
 42%|████▏     | 11796/28080 [23:18:28<32:17:45,  7.14s/it]
                                                           
{'loss': 0.6378, 'learning_rate': 0.00032565642055546005, 'epoch': 5.04}

 42%|████▏     | 11796/28080 [23:18:28<32:17:45,  7.14s/it]
 42%|████▏     | 11797/28080 [23:18:35<32:25:22,  7.17s/it]
                                                           
{'loss': 0.6152, 'learning_rate': 0.00032562893646590125, 'epoch': 5.04}

 42%|████▏     | 11797/28080 [23:18:35<32:25:22,  7.17s/it]
 42%|████▏     | 11798/28080 [23:18:42<32:27:50,  7.18s/it]
                                                           
{'loss': 0.6146, 'learning_rate': 0.0003256014513701776, 'epoch': 5.04}

 42%|████▏     | 11798/28080 [23:18:42<32:27:50,  7.18s/it]
 42%|████▏     | 11799/28080 [23:18:49<32:21:13,  7.15s/it]
                                                           
{'loss': 0.6282, 'learning_rate': 0.0003255739652686545, 'epoch': 5.04}

 42%|████▏     | 11799/28080 [23:18:49<32:21:13,  7.15s/it]
 42%|████▏     | 11800/28080 [23:18:56<32:14:22,  7.13s/it]
                                                           
{'loss': 0.6315, 'learning_rate': 0.0003255464781616978, 'epoch': 5.04}

 42%|████▏     | 11800/28080 [23:18:56<32:14:22,  7.13s/it]
 42%|████▏     | 11801/28080 [23:19:04<32:28:32,  7.18s/it]
                                                           
{'loss': 0.6432, 'learning_rate': 0.0003255189900496732, 'epoch': 5.04}

 42%|████▏     | 11801/28080 [23:19:04<32:28:32,  7.18s/it]
 42%|████▏     | 11802/28080 [23:19:11<32:28:32,  7.18s/it]
                                                           
{'loss': 0.651, 'learning_rate': 0.00032549150093294635, 'epoch': 5.04}

 42%|████▏     | 11802/28080 [23:19:11<32:28:32,  7.18s/it]
 42%|████▏     | 11803/28080 [23:19:18<32:18:19,  7.15s/it]
                                                           
{'loss': 0.6289, 'learning_rate': 0.00032546401081188294, 'epoch': 5.04}

 42%|████▏     | 11803/28080 [23:19:18<32:18:19,  7.15s/it]
 42%|████▏     | 11804/28080 [23:19:25<32:12:52,  7.13s/it]
                                                           
{'loss': 0.6466, 'learning_rate': 0.00032543651968684875, 'epoch': 5.04}

 42%|████▏     | 11804/28080 [23:19:25<32:12:52,  7.13s/it]
 42%|████▏     | 11805/28080 [23:19:32<32:20:31,  7.15s/it]
                                                           
{'loss': 0.6361, 'learning_rate': 0.0003254090275582094, 'epoch': 5.04}

 42%|████▏     | 11805/28080 [23:19:32<32:20:31,  7.15s/it]
 42%|████▏     | 11806/28080 [23:19:39<32:15:13,  7.13s/it]
                                                           
{'loss': 0.6243, 'learning_rate': 0.0003253815344263308, 'epoch': 5.04}

 42%|████▏     | 11806/28080 [23:19:39<32:15:13,  7.13s/it]
 42%|████▏     | 11807/28080 [23:19:46<32:19:27,  7.15s/it]
                                                           
{'loss': 0.6316, 'learning_rate': 0.0003253540402915786, 'epoch': 5.04}

 42%|████▏     | 11807/28080 [23:19:46<32:19:27,  7.15s/it]
 42%|████▏     | 11808/28080 [23:19:54<32:27:56,  7.18s/it]
                                                           
{'loss': 0.6063, 'learning_rate': 0.0003253265451543187, 'epoch': 5.04}

 42%|████▏     | 11808/28080 [23:19:54<32:27:56,  7.18s/it]
 42%|████▏     | 11809/28080 [23:20:01<32:25:14,  7.17s/it]
                                                           
{'loss': 0.6176, 'learning_rate': 0.0003252990490149167, 'epoch': 5.04}

 42%|████▏     | 11809/28080 [23:20:01<32:25:14,  7.17s/it]
 42%|████▏     | 11810/28080 [23:20:08<32:17:18,  7.14s/it]
                                                           
{'loss': 0.6329, 'learning_rate': 0.0003252715518737387, 'epoch': 5.05}

 42%|████▏     | 11810/28080 [23:20:08<32:17:18,  7.14s/it]
 42%|████▏     | 11811/28080 [23:20:15<32:07:10,  7.11s/it]
                                                           
{'loss': 0.6497, 'learning_rate': 0.0003252440537311503, 'epoch': 5.05}

 42%|████▏     | 11811/28080 [23:20:15<32:07:10,  7.11s/it]
 42%|████▏     | 11812/28080 [23:20:22<32:17:23,  7.15s/it]
                                                           
{'loss': 0.6421, 'learning_rate': 0.0003252165545875173, 'epoch': 5.05}

 42%|████▏     | 11812/28080 [23:20:22<32:17:23,  7.15s/it]
 42%|████▏     | 11813/28080 [23:20:29<32:06:33,  7.11s/it]
                                                           
{'loss': 0.6348, 'learning_rate': 0.0003251890544432058, 'epoch': 5.05}

 42%|████▏     | 11813/28080 [23:20:29<32:06:33,  7.11s/it]
 42%|████▏     | 11814/28080 [23:20:36<32:16:00,  7.14s/it]
                                                           
{'loss': 0.6091, 'learning_rate': 0.00032516155329858135, 'epoch': 5.05}

 42%|████▏     | 11814/28080 [23:20:36<32:16:00,  7.14s/it]
 42%|████▏     | 11815/28080 [23:20:44<32:15:05,  7.14s/it]
                                                           
{'loss': 0.6217, 'learning_rate': 0.00032513405115401005, 'epoch': 5.05}

 42%|████▏     | 11815/28080 [23:20:44<32:15:05,  7.14s/it]
 42%|████▏     | 11816/28080 [23:20:51<32:16:50,  7.15s/it]
                                                           
{'loss': 0.6131, 'learning_rate': 0.00032510654800985774, 'epoch': 5.05}

 42%|████▏     | 11816/28080 [23:20:51<32:16:50,  7.15s/it]
 42%|████▏     | 11817/28080 [23:20:58<32:19:17,  7.15s/it]
                                                           
{'loss': 0.5981, 'learning_rate': 0.00032507904386649023, 'epoch': 5.05}

 42%|████▏     | 11817/28080 [23:20:58<32:19:17,  7.15s/it]
 42%|████▏     | 11818/28080 [23:21:05<32:07:40,  7.11s/it]
                                                           
{'loss': 0.6212, 'learning_rate': 0.0003250515387242735, 'epoch': 5.05}

 42%|████▏     | 11818/28080 [23:21:05<32:07:40,  7.11s/it]
 42%|████▏     | 11819/28080 [23:21:12<31:54:58,  7.07s/it]
                                                           
{'loss': 0.6279, 'learning_rate': 0.0003250240325835735, 'epoch': 5.05}

 42%|████▏     | 11819/28080 [23:21:12<31:54:58,  7.07s/it]
 42%|████▏     | 11820/28080 [23:21:19<32:01:10,  7.09s/it]
                                                           
{'loss': 0.6266, 'learning_rate': 0.00032499652544475615, 'epoch': 5.05}

 42%|████▏     | 11820/28080 [23:21:19<32:01:10,  7.09s/it]
 42%|████▏     | 11821/28080 [23:21:26<32:03:43,  7.10s/it]
                                                           
{'loss': 0.6132, 'learning_rate': 0.0003249690173081874, 'epoch': 5.05}

 42%|████▏     | 11821/28080 [23:21:26<32:03:43,  7.10s/it]
 42%|████▏     | 11822/28080 [23:21:33<32:05:48,  7.11s/it]
                                                           
{'loss': 0.623, 'learning_rate': 0.0003249415081742332, 'epoch': 5.05}

 42%|████▏     | 11822/28080 [23:21:33<32:05:48,  7.11s/it]
 42%|████▏     | 11823/28080 [23:21:41<32:19:32,  7.16s/it]
                                                           
{'loss': 0.6206, 'learning_rate': 0.0003249139980432595, 'epoch': 5.05}

 42%|████▏     | 11823/28080 [23:21:41<32:19:32,  7.16s/it]
 42%|████▏     | 11824/28080 [23:21:48<32:21:17,  7.17s/it]
                                                           
{'loss': 0.649, 'learning_rate': 0.00032488648691563236, 'epoch': 5.05}

 42%|████▏     | 11824/28080 [23:21:48<32:21:17,  7.17s/it]
 42%|████▏     | 11825/28080 [23:21:55<32:06:37,  7.11s/it]
                                                           
{'loss': 0.6408, 'learning_rate': 0.00032485897479171786, 'epoch': 5.05}

 42%|████▏     | 11825/28080 [23:21:55<32:06:37,  7.11s/it]
 42%|████▏     | 11826/28080 [23:22:02<32:02:06,  7.10s/it]
                                                           
{'loss': 0.6298, 'learning_rate': 0.0003248314616718818, 'epoch': 5.05}

 42%|████▏     | 11826/28080 [23:22:02<32:02:06,  7.10s/it]
 42%|████▏     | 11827/28080 [23:22:09<32:02:44,  7.10s/it]
                                                           
{'loss': 0.6157, 'learning_rate': 0.00032480394755649044, 'epoch': 5.05}

 42%|████▏     | 11827/28080 [23:22:09<32:02:44,  7.10s/it]
 42%|████▏     | 11828/28080 [23:22:16<31:55:47,  7.07s/it]
                                                           
{'loss': 0.6143, 'learning_rate': 0.00032477643244590963, 'epoch': 5.05}

 42%|████▏     | 11828/28080 [23:22:16<31:55:47,  7.07s/it]
 42%|████▏     | 11829/28080 [23:22:23<32:02:02,  7.10s/it]
                                                           
{'loss': 0.6226, 'learning_rate': 0.0003247489163405056, 'epoch': 5.05}

 42%|████▏     | 11829/28080 [23:22:23<32:02:02,  7.10s/it]
 42%|████▏     | 11830/28080 [23:22:30<32:05:43,  7.11s/it]
                                                           
{'loss': 0.6197, 'learning_rate': 0.0003247213992406444, 'epoch': 5.05}

 42%|████▏     | 11830/28080 [23:22:30<32:05:43,  7.11s/it]
 42%|████▏     | 11831/28080 [23:22:37<32:05:50,  7.11s/it]
                                                           
{'loss': 0.6245, 'learning_rate': 0.00032469388114669194, 'epoch': 5.05}

 42%|████▏     | 11831/28080 [23:22:37<32:05:50,  7.11s/it]
 42%|████▏     | 11832/28080 [23:22:44<31:58:46,  7.09s/it]
                                                           
{'loss': 0.626, 'learning_rate': 0.0003246663620590146, 'epoch': 5.05}

 42%|████▏     | 11832/28080 [23:22:44<31:58:46,  7.09s/it]
 42%|████▏     | 11833/28080 [23:22:51<32:05:52,  7.11s/it]
                                                           
{'loss': 0.6044, 'learning_rate': 0.0003246388419779782, 'epoch': 5.05}

 42%|████▏     | 11833/28080 [23:22:51<32:05:52,  7.11s/it]
 42%|████▏     | 11834/28080 [23:22:59<32:00:52,  7.09s/it]
                                                           
{'loss': 0.6439, 'learning_rate': 0.00032461132090394907, 'epoch': 5.06}

 42%|████▏     | 11834/28080 [23:22:59<32:00:52,  7.09s/it]
 42%|████▏     | 11835/28080 [23:23:06<32:09:35,  7.13s/it]
                                                           
{'loss': 0.5851, 'learning_rate': 0.0003245837988372933, 'epoch': 5.06}

 42%|████▏     | 11835/28080 [23:23:06<32:09:35,  7.13s/it]
 42%|████▏     | 11836/28080 [23:23:13<32:06:31,  7.12s/it]
                                                           
{'loss': 0.6241, 'learning_rate': 0.000324556275778377, 'epoch': 5.06}

 42%|████▏     | 11836/28080 [23:23:13<32:06:31,  7.12s/it]
 42%|████▏     | 11837/28080 [23:23:20<32:09:43,  7.13s/it]
                                                           
{'loss': 0.6416, 'learning_rate': 0.00032452875172756635, 'epoch': 5.06}

 42%|████▏     | 11837/28080 [23:23:20<32:09:43,  7.13s/it]
 42%|████▏     | 11838/28080 [23:23:27<32:03:25,  7.11s/it]
                                                           
{'loss': 0.6433, 'learning_rate': 0.0003245012266852276, 'epoch': 5.06}

 42%|████▏     | 11838/28080 [23:23:27<32:03:25,  7.11s/it]
 42%|████▏     | 11839/28080 [23:23:34<32:01:24,  7.10s/it]
                                                           
{'loss': 0.6267, 'learning_rate': 0.0003244737006517269, 'epoch': 5.06}

 42%|████▏     | 11839/28080 [23:23:34<32:01:24,  7.10s/it]
 42%|████▏     | 11840/28080 [23:23:41<32:12:24,  7.14s/it]
                                                           
{'loss': 0.6045, 'learning_rate': 0.00032444617362743035, 'epoch': 5.06}

 42%|████▏     | 11840/28080 [23:23:41<32:12:24,  7.14s/it]
 42%|████▏     | 11841/28080 [23:23:48<32:12:26,  7.14s/it]
                                                           
{'loss': 0.6104, 'learning_rate': 0.00032441864561270434, 'epoch': 5.06}

 42%|████▏     | 11841/28080 [23:23:48<32:12:26,  7.14s/it]
 42%|████▏     | 11842/28080 [23:23:55<31:56:27,  7.08s/it]
                                                           
{'loss': 0.6163, 'learning_rate': 0.00032439111660791505, 'epoch': 5.06}

 42%|████▏     | 11842/28080 [23:23:55<31:56:27,  7.08s/it]
 42%|████▏     | 11843/28080 [23:24:03<32:03:52,  7.11s/it]
                                                           
{'loss': 0.6057, 'learning_rate': 0.0003243635866134286, 'epoch': 5.06}

 42%|████▏     | 11843/28080 [23:24:03<32:03:52,  7.11s/it]
 42%|████▏     | 11844/28080 [23:24:10<32:08:56,  7.13s/it]
                                                           
{'loss': 0.5944, 'learning_rate': 0.0003243360556296114, 'epoch': 5.06}

 42%|████▏     | 11844/28080 [23:24:10<32:08:56,  7.13s/it]
 42%|████▏     | 11845/28080 [23:24:17<32:00:09,  7.10s/it]
                                                           
{'loss': 0.6461, 'learning_rate': 0.00032430852365682974, 'epoch': 5.06}

 42%|████▏     | 11845/28080 [23:24:17<32:00:09,  7.10s/it]
 42%|████▏     | 11846/28080 [23:24:24<31:58:46,  7.09s/it]
                                                           
{'loss': 0.6357, 'learning_rate': 0.00032428099069544975, 'epoch': 5.06}

 42%|████▏     | 11846/28080 [23:24:24<31:58:46,  7.09s/it]
 42%|████▏     | 11847/28080 [23:24:31<32:08:37,  7.13s/it]
                                                           
{'loss': 0.6129, 'learning_rate': 0.0003242534567458378, 'epoch': 5.06}

 42%|████▏     | 11847/28080 [23:24:31<32:08:37,  7.13s/it]
 42%|████▏     | 11848/28080 [23:24:38<32:07:04,  7.12s/it]
                                                           
{'loss': 0.6192, 'learning_rate': 0.0003242259218083602, 'epoch': 5.06}

 42%|████▏     | 11848/28080 [23:24:38<32:07:04,  7.12s/it]
 42%|████▏     | 11849/28080 [23:24:45<31:59:39,  7.10s/it]
                                                           
{'loss': 0.6076, 'learning_rate': 0.00032419838588338334, 'epoch': 5.06}

 42%|████▏     | 11849/28080 [23:24:45<31:59:39,  7.10s/it]
 42%|████▏     | 11850/28080 [23:24:52<31:58:29,  7.09s/it]
                                                           
{'loss': 0.6234, 'learning_rate': 0.00032417084897127347, 'epoch': 5.06}

 42%|████▏     | 11850/28080 [23:24:52<31:58:29,  7.09s/it]
 42%|████▏     | 11851/28080 [23:24:59<31:54:33,  7.08s/it]
                                                           
{'loss': 0.6393, 'learning_rate': 0.000324143311072397, 'epoch': 5.06}

 42%|████▏     | 11851/28080 [23:24:59<31:54:33,  7.08s/it]
 42%|████▏     | 11852/28080 [23:25:06<31:48:10,  7.06s/it]
                                                           
{'loss': 0.6123, 'learning_rate': 0.00032411577218712016, 'epoch': 5.06}

 42%|████▏     | 11852/28080 [23:25:06<31:48:10,  7.06s/it]
 42%|████▏     | 11853/28080 [23:25:13<31:54:14,  7.08s/it]
                                                           
{'loss': 0.609, 'learning_rate': 0.0003240882323158096, 'epoch': 5.06}

 42%|████▏     | 11853/28080 [23:25:13<31:54:14,  7.08s/it]
 42%|████▏     | 11854/28080 [23:25:21<31:52:37,  7.07s/it]
                                                           
{'loss': 0.6271, 'learning_rate': 0.0003240606914588314, 'epoch': 5.06}

 42%|████▏     | 11854/28080 [23:25:21<31:52:37,  7.07s/it]
 42%|████▏     | 11855/28080 [23:25:28<31:56:37,  7.09s/it]
                                                           
{'loss': 0.6163, 'learning_rate': 0.00032403314961655216, 'epoch': 5.06}

 42%|████▏     | 11855/28080 [23:25:28<31:56:37,  7.09s/it]
 42%|████▏     | 11856/28080 [23:25:35<32:05:48,  7.12s/it]
                                                           
{'loss': 0.6318, 'learning_rate': 0.00032400560678933827, 'epoch': 5.06}

 42%|████▏     | 11856/28080 [23:25:35<32:05:48,  7.12s/it]
 42%|████▏     | 11857/28080 [23:25:42<32:02:46,  7.11s/it]
                                                           
{'loss': 0.6546, 'learning_rate': 0.00032397806297755605, 'epoch': 5.07}

 42%|████▏     | 11857/28080 [23:25:42<32:02:46,  7.11s/it]
 42%|████▏     | 11858/28080 [23:25:49<32:02:22,  7.11s/it]
                                                           
{'loss': 0.6178, 'learning_rate': 0.00032395051818157213, 'epoch': 5.07}

 42%|████▏     | 11858/28080 [23:25:49<32:02:22,  7.11s/it]
 42%|████▏     | 11859/28080 [23:25:56<32:05:07,  7.12s/it]
                                                           
{'loss': 0.6299, 'learning_rate': 0.0003239229724017528, 'epoch': 5.07}

 42%|████▏     | 11859/28080 [23:25:56<32:05:07,  7.12s/it]
 42%|████▏     | 11860/28080 [23:26:03<32:08:20,  7.13s/it]
                                                           
{'loss': 0.6364, 'learning_rate': 0.00032389542563846457, 'epoch': 5.07}

 42%|████▏     | 11860/28080 [23:26:03<32:08:20,  7.13s/it]
 42%|████▏     | 11861/28080 [23:26:10<32:00:29,  7.10s/it]
                                                           
{'loss': 0.6212, 'learning_rate': 0.00032386787789207396, 'epoch': 5.07}

 42%|████▏     | 11861/28080 [23:26:10<32:00:29,  7.10s/it]
 42%|████▏     | 11862/28080 [23:26:17<31:55:52,  7.09s/it]
                                                           
{'loss': 0.6071, 'learning_rate': 0.0003238403291629474, 'epoch': 5.07}

 42%|████▏     | 11862/28080 [23:26:17<31:55:52,  7.09s/it]
 42%|████▏     | 11863/28080 [23:26:25<31:54:45,  7.08s/it]
                                                           
{'loss': 0.6321, 'learning_rate': 0.0003238127794514515, 'epoch': 5.07}

 42%|████▏     | 11863/28080 [23:26:25<31:54:45,  7.08s/it]
 42%|████▏     | 11864/28080 [23:26:32<32:00:13,  7.10s/it]
                                                           
{'loss': 0.6121, 'learning_rate': 0.0003237852287579526, 'epoch': 5.07}

 42%|████▏     | 11864/28080 [23:26:32<32:00:13,  7.10s/it]
 42%|████▏     | 11865/28080 [23:26:39<31:59:46,  7.10s/it]
                                                           
{'loss': 0.6238, 'learning_rate': 0.0003237576770828175, 'epoch': 5.07}

 42%|████▏     | 11865/28080 [23:26:39<31:59:46,  7.10s/it]
 42%|████▏     | 11866/28080 [23:26:46<32:13:45,  7.16s/it]
                                                           
{'loss': 0.6287, 'learning_rate': 0.0003237301244264126, 'epoch': 5.07}

 42%|████▏     | 11866/28080 [23:26:46<32:13:45,  7.16s/it]
 42%|████▏     | 11867/28080 [23:26:53<32:08:51,  7.14s/it]
                                                           
{'loss': 0.6372, 'learning_rate': 0.0003237025707891044, 'epoch': 5.07}

 42%|████▏     | 11867/28080 [23:26:53<32:08:51,  7.14s/it]
 42%|████▏     | 11868/28080 [23:27:00<32:15:47,  7.16s/it]
                                                           
{'loss': 0.6242, 'learning_rate': 0.0003236750161712595, 'epoch': 5.07}

 42%|████▏     | 11868/28080 [23:27:00<32:15:47,  7.16s/it]
 42%|████▏     | 11869/28080 [23:27:08<32:12:01,  7.15s/it]
                                                           
{'loss': 0.6443, 'learning_rate': 0.0003236474605732445, 'epoch': 5.07}

 42%|████▏     | 11869/28080 [23:27:08<32:12:01,  7.15s/it]
 42%|████▏     | 11870/28080 [23:27:15<32:04:14,  7.12s/it]
                                                           
{'loss': 0.6354, 'learning_rate': 0.0003236199039954261, 'epoch': 5.07}

 42%|████▏     | 11870/28080 [23:27:15<32:04:14,  7.12s/it]
 42%|████▏     | 11871/28080 [23:27:22<31:56:42,  7.09s/it]
                                                           
{'loss': 0.6308, 'learning_rate': 0.0003235923464381708, 'epoch': 5.07}

 42%|████▏     | 11871/28080 [23:27:22<31:56:42,  7.09s/it]
 42%|████▏     | 11872/28080 [23:27:29<32:08:20,  7.14s/it]
                                                           
{'loss': 0.6015, 'learning_rate': 0.0003235647879018452, 'epoch': 5.07}

 42%|████▏     | 11872/28080 [23:27:29<32:08:20,  7.14s/it]
 42%|████▏     | 11873/28080 [23:27:36<32:09:28,  7.14s/it]
                                                           
{'loss': 0.6306, 'learning_rate': 0.00032353722838681596, 'epoch': 5.07}

 42%|████▏     | 11873/28080 [23:27:36<32:09:28,  7.14s/it]
 42%|████▏     | 11874/28080 [23:27:43<31:59:26,  7.11s/it]
                                                           
{'loss': 0.6204, 'learning_rate': 0.00032350966789344984, 'epoch': 5.07}

 42%|████▏     | 11874/28080 [23:27:43<31:59:26,  7.11s/it]
 42%|████▏     | 11875/28080 [23:27:50<32:05:04,  7.13s/it]
                                                           
{'loss': 0.639, 'learning_rate': 0.0003234821064221134, 'epoch': 5.07}

 42%|████▏     | 11875/28080 [23:27:50<32:05:04,  7.13s/it]
 42%|████▏     | 11876/28080 [23:27:57<31:59:36,  7.11s/it]
                                                           
{'loss': 0.6254, 'learning_rate': 0.00032345454397317335, 'epoch': 5.07}

 42%|████▏     | 11876/28080 [23:27:57<31:59:36,  7.11s/it]
 42%|████▏     | 11877/28080 [23:28:04<31:59:19,  7.11s/it]
                                                           
{'loss': 0.6358, 'learning_rate': 0.0003234269805469964, 'epoch': 5.07}

 42%|████▏     | 11877/28080 [23:28:04<31:59:19,  7.11s/it]
 42%|████▏     | 11878/28080 [23:28:12<32:04:17,  7.13s/it]
                                                           
{'loss': 0.62, 'learning_rate': 0.0003233994161439492, 'epoch': 5.07}

 42%|████▏     | 11878/28080 [23:28:12<32:04:17,  7.13s/it]
 42%|████▏     | 11879/28080 [23:28:19<32:07:33,  7.14s/it]
                                                           
{'loss': 0.634, 'learning_rate': 0.00032337185076439847, 'epoch': 5.07}

 42%|████▏     | 11879/28080 [23:28:19<32:07:33,  7.14s/it]
 42%|████▏     | 11880/28080 [23:28:26<32:11:42,  7.15s/it]
                                                           
{'loss': 0.6091, 'learning_rate': 0.0003233442844087109, 'epoch': 5.08}

 42%|████▏     | 11880/28080 [23:28:26<32:11:42,  7.15s/it]
 42%|████▏     | 11881/28080 [23:28:33<32:04:53,  7.13s/it]
                                                           
{'loss': 0.6238, 'learning_rate': 0.0003233167170772534, 'epoch': 5.08}

 42%|████▏     | 11881/28080 [23:28:33<32:04:53,  7.13s/it]
 42%|████▏     | 11882/28080 [23:28:40<32:15:42,  7.17s/it]
                                                           
{'loss': 0.6496, 'learning_rate': 0.00032328914877039264, 'epoch': 5.08}

 42%|████▏     | 11882/28080 [23:28:40<32:15:42,  7.17s/it]
 42%|████▏     | 11883/28080 [23:28:47<32:10:15,  7.15s/it]
                                                           
{'loss': 0.6358, 'learning_rate': 0.0003232615794884952, 'epoch': 5.08}

 42%|████▏     | 11883/28080 [23:28:47<32:10:15,  7.15s/it]
 42%|████▏     | 11884/28080 [23:28:54<32:03:31,  7.13s/it]
                                                           
{'loss': 0.6278, 'learning_rate': 0.0003232340092319282, 'epoch': 5.08}

 42%|████▏     | 11884/28080 [23:28:54<32:03:31,  7.13s/it]
 42%|████▏     | 11885/28080 [23:29:02<32:05:24,  7.13s/it]
                                                           
{'loss': 0.6224, 'learning_rate': 0.00032320643800105815, 'epoch': 5.08}

 42%|████▏     | 11885/28080 [23:29:02<32:05:24,  7.13s/it]
 42%|████▏     | 11886/28080 [23:29:09<32:10:28,  7.15s/it]
                                                           
{'loss': 0.6303, 'learning_rate': 0.000323178865796252, 'epoch': 5.08}

 42%|████▏     | 11886/28080 [23:29:09<32:10:28,  7.15s/it]
 42%|████▏     | 11887/28080 [23:29:16<32:32:53,  7.24s/it]
                                                           
{'loss': 0.625, 'learning_rate': 0.0003231512926178766, 'epoch': 5.08}

 42%|████▏     | 11887/28080 [23:29:16<32:32:53,  7.24s/it]
 42%|████▏     | 11888/28080 [23:29:23<32:22:13,  7.20s/it]
                                                           
{'loss': 0.624, 'learning_rate': 0.0003231237184662986, 'epoch': 5.08}

 42%|████▏     | 11888/28080 [23:29:23<32:22:13,  7.20s/it]
 42%|████▏     | 11889/28080 [23:29:30<32:10:17,  7.15s/it]
                                                           
{'loss': 0.6169, 'learning_rate': 0.000323096143341885, 'epoch': 5.08}

 42%|████▏     | 11889/28080 [23:29:30<32:10:17,  7.15s/it]
 42%|████▏     | 11890/28080 [23:29:37<31:56:58,  7.10s/it]
                                                           
{'loss': 0.63, 'learning_rate': 0.0003230685672450027, 'epoch': 5.08}

 42%|████▏     | 11890/28080 [23:29:37<31:56:58,  7.10s/it]
 42%|████▏     | 11891/28080 [23:29:44<31:49:25,  7.08s/it]
                                                           
{'loss': 0.6397, 'learning_rate': 0.0003230409901760184, 'epoch': 5.08}

 42%|████▏     | 11891/28080 [23:29:44<31:49:25,  7.08s/it]
 42%|████▏     | 11892/28080 [23:29:51<31:53:12,  7.09s/it]
                                                           
{'loss': 0.598, 'learning_rate': 0.0003230134121352991, 'epoch': 5.08}

 42%|████▏     | 11892/28080 [23:29:51<31:53:12,  7.09s/it]
 42%|████▏     | 11893/28080 [23:29:59<31:50:05,  7.08s/it]
                                                           
{'loss': 0.6268, 'learning_rate': 0.0003229858331232117, 'epoch': 5.08}

 42%|████▏     | 11893/28080 [23:29:59<31:50:05,  7.08s/it]
 42%|████▏     | 11894/28080 [23:30:06<32:01:42,  7.12s/it]
                                                           
{'loss': 0.6379, 'learning_rate': 0.0003229582531401231, 'epoch': 5.08}

 42%|████▏     | 11894/28080 [23:30:06<32:01:42,  7.12s/it]
 42%|████▏     | 11895/28080 [23:30:13<31:59:43,  7.12s/it]
                                                           
{'loss': 0.6208, 'learning_rate': 0.00032293067218640016, 'epoch': 5.08}

 42%|████▏     | 11895/28080 [23:30:13<31:59:43,  7.12s/it]
 42%|████▏     | 11896/28080 [23:30:20<31:53:52,  7.10s/it]
                                                           
{'loss': 0.6319, 'learning_rate': 0.00032290309026240983, 'epoch': 5.08}

 42%|████▏     | 11896/28080 [23:30:20<31:53:52,  7.10s/it]
 42%|████▏     | 11897/28080 [23:30:27<31:50:00,  7.08s/it]
                                                           
{'loss': 0.6205, 'learning_rate': 0.00032287550736851924, 'epoch': 5.08}

 42%|████▏     | 11897/28080 [23:30:27<31:50:00,  7.08s/it]
 42%|████▏     | 11898/28080 [23:30:34<31:55:10,  7.10s/it]
                                                           
{'loss': 0.642, 'learning_rate': 0.00032284792350509506, 'epoch': 5.08}

 42%|████▏     | 11898/28080 [23:30:34<31:55:10,  7.10s/it]
 42%|████▏     | 11899/28080 [23:30:41<31:51:24,  7.09s/it]
                                                           
{'loss': 0.6632, 'learning_rate': 0.0003228203386725045, 'epoch': 5.08}

 42%|████▏     | 11899/28080 [23:30:41<31:51:24,  7.09s/it]
 42%|████▏     | 11900/28080 [23:30:48<31:55:53,  7.10s/it]
                                                           
{'loss': 0.6088, 'learning_rate': 0.0003227927528711144, 'epoch': 5.08}

 42%|████▏     | 11900/28080 [23:30:48<31:55:53,  7.10s/it]
 42%|████▏     | 11901/28080 [23:30:55<31:56:59,  7.11s/it]
                                                           
{'loss': 0.6227, 'learning_rate': 0.0003227651661012919, 'epoch': 5.08}

 42%|████▏     | 11901/28080 [23:30:55<31:56:59,  7.11s/it]
 42%|████▏     | 11902/28080 [23:31:02<31:55:42,  7.10s/it]
                                                           
{'loss': 0.6193, 'learning_rate': 0.0003227375783634038, 'epoch': 5.08}

 42%|████▏     | 11902/28080 [23:31:03<31:55:42,  7.10s/it]
 42%|████▏     | 11903/28080 [23:31:10<32:00:58,  7.12s/it]
                                                           
{'loss': 0.6226, 'learning_rate': 0.00032270998965781736, 'epoch': 5.08}

 42%|████▏     | 11903/28080 [23:31:10<32:00:58,  7.12s/it]
 42%|████▏     | 11904/28080 [23:31:17<31:57:15,  7.11s/it]
                                                           
{'loss': 0.6145, 'learning_rate': 0.00032268239998489945, 'epoch': 5.09}

 42%|████▏     | 11904/28080 [23:31:17<31:57:15,  7.11s/it]
 42%|████▏     | 11905/28080 [23:31:24<32:09:56,  7.16s/it]
                                                           
{'loss': 0.6223, 'learning_rate': 0.00032265480934501724, 'epoch': 5.09}

 42%|████▏     | 11905/28080 [23:31:24<32:09:56,  7.16s/it]
 42%|████▏     | 11906/28080 [23:31:31<31:55:03,  7.10s/it]
                                                           
{'loss': 0.6576, 'learning_rate': 0.0003226272177385378, 'epoch': 5.09}

 42%|████▏     | 11906/28080 [23:31:31<31:55:03,  7.10s/it]
 42%|████▏     | 11907/28080 [23:31:38<31:57:04,  7.11s/it]
                                                           
{'loss': 0.6011, 'learning_rate': 0.00032259962516582803, 'epoch': 5.09}

 42%|████▏     | 11907/28080 [23:31:38<31:57:04,  7.11s/it]
 42%|████▏     | 11908/28080 [23:31:45<32:02:11,  7.13s/it]
                                                           
{'loss': 0.6457, 'learning_rate': 0.00032257203162725526, 'epoch': 5.09}

 42%|████▏     | 11908/28080 [23:31:45<32:02:11,  7.13s/it]
 42%|████▏     | 11909/28080 [23:31:52<31:51:34,  7.09s/it]
                                                           
{'loss': 0.6417, 'learning_rate': 0.00032254443712318636, 'epoch': 5.09}

 42%|████▏     | 11909/28080 [23:31:52<31:51:34,  7.09s/it]
 42%|████▏     | 11910/28080 [23:31:59<31:56:03,  7.11s/it]
                                                           
{'loss': 0.6194, 'learning_rate': 0.00032251684165398865, 'epoch': 5.09}

 42%|████▏     | 11910/28080 [23:31:59<31:56:03,  7.11s/it]
 42%|████▏     | 11911/28080 [23:32:07<31:55:09,  7.11s/it]
                                                           
{'loss': 0.6298, 'learning_rate': 0.00032248924522002915, 'epoch': 5.09}

 42%|████▏     | 11911/28080 [23:32:07<31:55:09,  7.11s/it]
 42%|████▏     | 11912/28080 [23:32:14<31:49:59,  7.09s/it]
                                                           
{'loss': 0.6196, 'learning_rate': 0.000322461647821675, 'epoch': 5.09}

 42%|████▏     | 11912/28080 [23:32:14<31:49:59,  7.09s/it]
 42%|████▏     | 11913/28080 [23:32:21<31:57:29,  7.12s/it]
                                                           
{'loss': 0.6186, 'learning_rate': 0.00032243404945929346, 'epoch': 5.09}

 42%|████▏     | 11913/28080 [23:32:21<31:57:29,  7.12s/it]
 42%|████▏     | 11914/28080 [23:32:28<31:57:46,  7.12s/it]
                                                           
{'loss': 0.6252, 'learning_rate': 0.00032240645013325154, 'epoch': 5.09}

 42%|████▏     | 11914/28080 [23:32:28<31:57:46,  7.12s/it]
 42%|████▏     | 11915/28080 [23:32:35<31:57:30,  7.12s/it]
                                                           
{'loss': 0.6369, 'learning_rate': 0.00032237884984391655, 'epoch': 5.09}

 42%|████▏     | 11915/28080 [23:32:35<31:57:30,  7.12s/it]
 42%|████▏     | 11916/28080 [23:32:42<31:51:09,  7.09s/it]
                                                           
{'loss': 0.6216, 'learning_rate': 0.00032235124859165563, 'epoch': 5.09}

 42%|████▏     | 11916/28080 [23:32:42<31:51:09,  7.09s/it]
 42%|████▏     | 11917/28080 [23:32:49<31:55:24,  7.11s/it]
                                                           
{'loss': 0.6285, 'learning_rate': 0.0003223236463768359, 'epoch': 5.09}

 42%|████▏     | 11917/28080 [23:32:49<31:55:24,  7.11s/it]
 42%|████▏     | 11918/28080 [23:32:56<31:50:07,  7.09s/it]
                                                           
{'loss': 0.6183, 'learning_rate': 0.0003222960431998248, 'epoch': 5.09}

 42%|████▏     | 11918/28080 [23:32:56<31:50:07,  7.09s/it]
 42%|████▏     | 11919/28080 [23:33:03<31:57:35,  7.12s/it]
                                                           
{'loss': 0.646, 'learning_rate': 0.00032226843906098935, 'epoch': 5.09}

 42%|████▏     | 11919/28080 [23:33:03<31:57:35,  7.12s/it]
 42%|████▏     | 11920/28080 [23:33:11<32:05:40,  7.15s/it]
                                                           
{'loss': 0.6204, 'learning_rate': 0.00032224083396069684, 'epoch': 5.09}

 42%|████▏     | 11920/28080 [23:33:11<32:05:40,  7.15s/it]
 42%|████▏     | 11921/28080 [23:33:18<31:59:08,  7.13s/it]
                                                           
{'loss': 0.6157, 'learning_rate': 0.0003222132278993146, 'epoch': 5.09}

 42%|████▏     | 11921/28080 [23:33:18<31:59:08,  7.13s/it]
 42%|████▏     | 11922/28080 [23:33:25<31:55:30,  7.11s/it]
                                                           
{'loss': 0.63, 'learning_rate': 0.0003221856208772099, 'epoch': 5.09}

 42%|████▏     | 11922/28080 [23:33:25<31:55:30,  7.11s/it]
 42%|████▏     | 11923/28080 [23:33:32<31:54:52,  7.11s/it]
                                                           
{'loss': 0.6368, 'learning_rate': 0.00032215801289474995, 'epoch': 5.09}

 42%|████▏     | 11923/28080 [23:33:32<31:54:52,  7.11s/it]
 42%|████▏     | 11924/28080 [23:33:39<31:59:29,  7.13s/it]
                                                           
{'loss': 0.6116, 'learning_rate': 0.00032213040395230206, 'epoch': 5.09}

 42%|████▏     | 11924/28080 [23:33:39<31:59:29,  7.13s/it]
 42%|████▏     | 11925/28080 [23:33:46<32:11:06,  7.17s/it]
                                                           
{'loss': 0.6095, 'learning_rate': 0.00032210279405023355, 'epoch': 5.09}

 42%|████▏     | 11925/28080 [23:33:46<32:11:06,  7.17s/it]
 42%|████▏     | 11926/28080 [23:33:53<31:59:35,  7.13s/it]
                                                           
{'loss': 0.6188, 'learning_rate': 0.0003220751831889118, 'epoch': 5.09}

 42%|████▏     | 11926/28080 [23:33:53<31:59:35,  7.13s/it]
 42%|████▏     | 11927/28080 [23:34:01<31:58:05,  7.12s/it]
                                                           
{'loss': 0.624, 'learning_rate': 0.00032204757136870403, 'epoch': 5.1}

 42%|████▏     | 11927/28080 [23:34:01<31:58:05,  7.12s/it]
 42%|████▏     | 11928/28080 [23:34:08<31:48:01,  7.09s/it]
                                                           
{'loss': 0.6142, 'learning_rate': 0.00032201995858997773, 'epoch': 5.1}

 42%|████▏     | 11928/28080 [23:34:08<31:48:01,  7.09s/it]
 42%|████▏     | 11929/28080 [23:34:15<31:50:09,  7.10s/it]
                                                           
{'loss': 0.6153, 'learning_rate': 0.0003219923448531001, 'epoch': 5.1}

 42%|████▏     | 11929/28080 [23:34:15<31:50:09,  7.10s/it]
 42%|████▏     | 11930/28080 [23:34:22<31:47:44,  7.09s/it]
                                                           
{'loss': 0.6287, 'learning_rate': 0.0003219647301584387, 'epoch': 5.1}

 42%|████▏     | 11930/28080 [23:34:22<31:47:44,  7.09s/it]
 42%|████▏     | 11931/28080 [23:34:29<31:53:58,  7.11s/it]
                                                           
{'loss': 0.6236, 'learning_rate': 0.0003219371145063607, 'epoch': 5.1}

 42%|████▏     | 11931/28080 [23:34:29<31:53:58,  7.11s/it]
 42%|████▏     | 11932/28080 [23:34:36<31:56:20,  7.12s/it]
                                                           
{'loss': 0.6557, 'learning_rate': 0.0003219094978972337, 'epoch': 5.1}

 42%|████▏     | 11932/28080 [23:34:36<31:56:20,  7.12s/it]
 42%|████▏     | 11933/28080 [23:34:43<31:49:44,  7.10s/it]
                                                           
{'loss': 0.6238, 'learning_rate': 0.0003218818803314249, 'epoch': 5.1}

 42%|████▏     | 11933/28080 [23:34:43<31:49:44,  7.10s/it]
 42%|████▎     | 11934/28080 [23:34:50<31:53:36,  7.11s/it]
                                                           
{'loss': 0.6395, 'learning_rate': 0.0003218542618093019, 'epoch': 5.1}

 42%|████▎     | 11934/28080 [23:34:50<31:53:36,  7.11s/it]
 43%|████▎     | 11935/28080 [23:34:57<31:49:58,  7.10s/it]
                                                           
{'loss': 0.6263, 'learning_rate': 0.0003218266423312321, 'epoch': 5.1}

 43%|████▎     | 11935/28080 [23:34:57<31:49:58,  7.10s/it]
 43%|████▎     | 11936/28080 [23:35:04<31:47:24,  7.09s/it]
                                                           
{'loss': 0.634, 'learning_rate': 0.00032179902189758287, 'epoch': 5.1}

 43%|████▎     | 11936/28080 [23:35:04<31:47:24,  7.09s/it]
 43%|████▎     | 11937/28080 [23:35:12<31:58:38,  7.13s/it]
                                                           
{'loss': 0.6123, 'learning_rate': 0.0003217714005087218, 'epoch': 5.1}

 43%|████▎     | 11937/28080 [23:35:12<31:58:38,  7.13s/it]
 43%|████▎     | 11938/28080 [23:35:19<32:02:51,  7.15s/it]
                                                           
{'loss': 0.6257, 'learning_rate': 0.0003217437781650162, 'epoch': 5.1}

 43%|████▎     | 11938/28080 [23:35:19<32:02:51,  7.15s/it]
 43%|████▎     | 11939/28080 [23:35:26<32:04:54,  7.16s/it]
                                                           
{'loss': 0.6146, 'learning_rate': 0.0003217161548668337, 'epoch': 5.1}

 43%|████▎     | 11939/28080 [23:35:26<32:04:54,  7.16s/it]
 43%|████▎     | 11940/28080 [23:35:33<31:58:48,  7.13s/it]
                                                           
{'loss': 0.6268, 'learning_rate': 0.0003216885306145417, 'epoch': 5.1}

 43%|████▎     | 11940/28080 [23:35:33<31:58:48,  7.13s/it]
 43%|████▎     | 11941/28080 [23:35:40<31:58:19,  7.13s/it]
                                                           
{'loss': 0.6226, 'learning_rate': 0.0003216609054085078, 'epoch': 5.1}

 43%|████▎     | 11941/28080 [23:35:40<31:58:19,  7.13s/it]
 43%|████▎     | 11942/28080 [23:35:47<32:02:12,  7.15s/it]
                                                           
{'loss': 0.6112, 'learning_rate': 0.0003216332792490995, 'epoch': 5.1}

 43%|████▎     | 11942/28080 [23:35:47<32:02:12,  7.15s/it]
 43%|████▎     | 11943/28080 [23:35:54<31:56:02,  7.12s/it]
                                                           
{'loss': 0.63, 'learning_rate': 0.00032160565213668426, 'epoch': 5.1}

 43%|████▎     | 11943/28080 [23:35:54<31:56:02,  7.12s/it]
 43%|████▎     | 11944/28080 [23:36:02<32:03:06,  7.15s/it]
                                                           
{'loss': 0.6227, 'learning_rate': 0.0003215780240716297, 'epoch': 5.1}

 43%|████▎     | 11944/28080 [23:36:02<32:03:06,  7.15s/it]
 43%|████▎     | 11945/28080 [23:36:09<32:00:50,  7.14s/it]
                                                           
{'loss': 0.5999, 'learning_rate': 0.00032155039505430343, 'epoch': 5.1}

 43%|████▎     | 11945/28080 [23:36:09<32:00:50,  7.14s/it]
 43%|████▎     | 11946/28080 [23:36:16<31:48:44,  7.10s/it]
                                                           
{'loss': 0.6469, 'learning_rate': 0.0003215227650850729, 'epoch': 5.1}

 43%|████▎     | 11946/28080 [23:36:16<31:48:44,  7.10s/it]
 43%|████▎     | 11947/28080 [23:36:23<31:51:19,  7.11s/it]
                                                           
{'loss': 0.6101, 'learning_rate': 0.0003214951341643058, 'epoch': 5.1}

 43%|████▎     | 11947/28080 [23:36:23<31:51:19,  7.11s/it]
 43%|████▎     | 11948/28080 [23:36:30<31:52:51,  7.11s/it]
                                                           
{'loss': 0.6232, 'learning_rate': 0.00032146750229236973, 'epoch': 5.1}

 43%|████▎     | 11948/28080 [23:36:30<31:52:51,  7.11s/it]
 43%|████▎     | 11949/28080 [23:36:37<31:53:35,  7.12s/it]
                                                           
{'loss': 0.6177, 'learning_rate': 0.0003214398694696322, 'epoch': 5.1}

 43%|████▎     | 11949/28080 [23:36:37<31:53:35,  7.12s/it]
 43%|████▎     | 11950/28080 [23:36:44<31:51:45,  7.11s/it]
                                                           
{'loss': 0.6192, 'learning_rate': 0.0003214122356964609, 'epoch': 5.1}

 43%|████▎     | 11950/28080 [23:36:44<31:51:45,  7.11s/it]
 43%|████▎     | 11951/28080 [23:36:51<31:53:56,  7.12s/it]
                                                           
{'loss': 0.6202, 'learning_rate': 0.0003213846009732235, 'epoch': 5.11}

 43%|████▎     | 11951/28080 [23:36:51<31:53:56,  7.12s/it]
 43%|████▎     | 11952/28080 [23:36:58<31:50:06,  7.11s/it]
                                                           
{'loss': 0.6384, 'learning_rate': 0.0003213569653002877, 'epoch': 5.11}

 43%|████▎     | 11952/28080 [23:36:58<31:50:06,  7.11s/it]
 43%|████▎     | 11953/28080 [23:37:06<31:50:26,  7.11s/it]
                                                           
{'loss': 0.6206, 'learning_rate': 0.000321329328678021, 'epoch': 5.11}

 43%|████▎     | 11953/28080 [23:37:06<31:50:26,  7.11s/it]
 43%|████▎     | 11954/28080 [23:37:13<31:48:44,  7.10s/it]
                                                           
{'loss': 0.6313, 'learning_rate': 0.0003213016911067912, 'epoch': 5.11}

 43%|████▎     | 11954/28080 [23:37:13<31:48:44,  7.10s/it]
 43%|████▎     | 11955/28080 [23:37:20<31:47:53,  7.10s/it]
                                                           
{'loss': 0.6515, 'learning_rate': 0.000321274052586966, 'epoch': 5.11}

 43%|████▎     | 11955/28080 [23:37:20<31:47:53,  7.10s/it]
 43%|████▎     | 11956/28080 [23:37:27<31:59:51,  7.14s/it]
                                                           
{'loss': 0.6566, 'learning_rate': 0.00032124641311891307, 'epoch': 5.11}

 43%|████▎     | 11956/28080 [23:37:27<31:59:51,  7.14s/it]
 43%|████▎     | 11957/28080 [23:37:34<32:06:13,  7.17s/it]
                                                           
{'loss': 0.6198, 'learning_rate': 0.000321218772703, 'epoch': 5.11}

 43%|████▎     | 11957/28080 [23:37:34<32:06:13,  7.17s/it]
 43%|████▎     | 11958/28080 [23:37:41<31:56:51,  7.13s/it]
                                                           
{'loss': 0.6471, 'learning_rate': 0.0003211911313395947, 'epoch': 5.11}

 43%|████▎     | 11958/28080 [23:37:41<31:56:51,  7.13s/it]
 43%|████▎     | 11959/28080 [23:37:48<31:39:45,  7.07s/it]
                                                           
{'loss': 0.6294, 'learning_rate': 0.00032116348902906487, 'epoch': 5.11}

 43%|████▎     | 11959/28080 [23:37:48<31:39:45,  7.07s/it]
 43%|████▎     | 11960/28080 [23:37:55<31:43:29,  7.08s/it]
                                                           
{'loss': 0.6163, 'learning_rate': 0.0003211358457717782, 'epoch': 5.11}

 43%|████▎     | 11960/28080 [23:37:55<31:43:29,  7.08s/it]
 43%|████▎     | 11961/28080 [23:38:02<31:37:47,  7.06s/it]
                                                           
{'loss': 0.6298, 'learning_rate': 0.0003211082015681025, 'epoch': 5.11}

 43%|████▎     | 11961/28080 [23:38:02<31:37:47,  7.06s/it]
 43%|████▎     | 11962/28080 [23:38:09<31:38:50,  7.07s/it]
                                                           
{'loss': 0.6319, 'learning_rate': 0.0003210805564184055, 'epoch': 5.11}

 43%|████▎     | 11962/28080 [23:38:09<31:38:50,  7.07s/it]
 43%|████▎     | 11963/28080 [23:38:17<31:51:21,  7.12s/it]
                                                           
{'loss': 0.6417, 'learning_rate': 0.00032105291032305506, 'epoch': 5.11}

 43%|████▎     | 11963/28080 [23:38:17<31:51:21,  7.12s/it]
 43%|████▎     | 11964/28080 [23:38:24<31:50:44,  7.11s/it]
                                                           
{'loss': 0.6216, 'learning_rate': 0.00032102526328241893, 'epoch': 5.11}

 43%|████▎     | 11964/28080 [23:38:24<31:50:44,  7.11s/it]
 43%|████▎     | 11965/28080 [23:38:31<31:44:00,  7.09s/it]
                                                           
{'loss': 0.6309, 'learning_rate': 0.000320997615296865, 'epoch': 5.11}

 43%|████▎     | 11965/28080 [23:38:31<31:44:00,  7.09s/it]
 43%|████▎     | 11966/28080 [23:38:38<31:42:28,  7.08s/it]
                                                           
{'loss': 0.6145, 'learning_rate': 0.000320969966366761, 'epoch': 5.11}

 43%|████▎     | 11966/28080 [23:38:38<31:42:28,  7.08s/it]
 43%|████▎     | 11967/28080 [23:38:45<31:47:18,  7.10s/it]
                                                           
{'loss': 0.6722, 'learning_rate': 0.0003209423164924748, 'epoch': 5.11}

 43%|████▎     | 11967/28080 [23:38:45<31:47:18,  7.10s/it]
 43%|████▎     | 11968/28080 [23:38:52<31:41:42,  7.08s/it]
                                                           
{'loss': 0.631, 'learning_rate': 0.0003209146656743743, 'epoch': 5.11}

 43%|████▎     | 11968/28080 [23:38:52<31:41:42,  7.08s/it]
 43%|████▎     | 11969/28080 [23:38:59<31:39:31,  7.07s/it]
                                                           
{'loss': 0.6312, 'learning_rate': 0.00032088701391282733, 'epoch': 5.11}

 43%|████▎     | 11969/28080 [23:38:59<31:39:31,  7.07s/it]
 43%|████▎     | 11970/28080 [23:39:06<31:45:53,  7.10s/it]
                                                           
{'loss': 0.6476, 'learning_rate': 0.0003208593612082017, 'epoch': 5.11}

 43%|████▎     | 11970/28080 [23:39:06<31:45:53,  7.10s/it]
 43%|████▎     | 11971/28080 [23:39:13<31:46:05,  7.10s/it]
                                                           
{'loss': 0.6251, 'learning_rate': 0.0003208317075608654, 'epoch': 5.11}

 43%|████▎     | 11971/28080 [23:39:13<31:46:05,  7.10s/it]
 43%|████▎     | 11972/28080 [23:39:20<31:48:59,  7.11s/it]
                                                           
{'loss': 0.601, 'learning_rate': 0.00032080405297118636, 'epoch': 5.11}

 43%|████▎     | 11972/28080 [23:39:20<31:48:59,  7.11s/it]
 43%|████▎     | 11973/28080 [23:39:28<31:57:55,  7.14s/it]
                                                           
{'loss': 0.6125, 'learning_rate': 0.00032077639743953245, 'epoch': 5.11}

 43%|████▎     | 11973/28080 [23:39:28<31:57:55,  7.14s/it]
 43%|████▎     | 11974/28080 [23:39:35<31:59:29,  7.15s/it]
                                                           
{'loss': 0.6269, 'learning_rate': 0.0003207487409662715, 'epoch': 5.12}

 43%|████▎     | 11974/28080 [23:39:35<31:59:29,  7.15s/it]
 43%|████▎     | 11975/28080 [23:39:42<32:00:13,  7.15s/it]
                                                           
{'loss': 0.6163, 'learning_rate': 0.00032072108355177156, 'epoch': 5.12}

 43%|████▎     | 11975/28080 [23:39:42<32:00:13,  7.15s/it]
 43%|████▎     | 11976/28080 [23:39:49<31:53:09,  7.13s/it]
                                                           
{'loss': 0.64, 'learning_rate': 0.0003206934251964006, 'epoch': 5.12}

 43%|████▎     | 11976/28080 [23:39:49<31:53:09,  7.13s/it]
 43%|████▎     | 11977/28080 [23:39:56<31:55:55,  7.14s/it]
                                                           
{'loss': 0.6252, 'learning_rate': 0.0003206657659005265, 'epoch': 5.12}

 43%|████▎     | 11977/28080 [23:39:56<31:55:55,  7.14s/it]
 43%|████▎     | 11978/28080 [23:40:03<31:59:55,  7.15s/it]
                                                           
{'loss': 0.6166, 'learning_rate': 0.0003206381056645173, 'epoch': 5.12}

 43%|████▎     | 11978/28080 [23:40:03<31:59:55,  7.15s/it]
 43%|████▎     | 11979/28080 [23:40:11<31:56:21,  7.14s/it]
                                                           
{'loss': 0.6196, 'learning_rate': 0.00032061044448874104, 'epoch': 5.12}

 43%|████▎     | 11979/28080 [23:40:11<31:56:21,  7.14s/it]
 43%|████▎     | 11980/28080 [23:40:18<32:00:50,  7.16s/it]
                                                           
{'loss': 0.6358, 'learning_rate': 0.00032058278237356565, 'epoch': 5.12}

 43%|████▎     | 11980/28080 [23:40:18<32:00:50,  7.16s/it]
 43%|████▎     | 11981/28080 [23:40:25<31:55:30,  7.14s/it]
                                                           
{'loss': 0.6188, 'learning_rate': 0.0003205551193193591, 'epoch': 5.12}

 43%|████▎     | 11981/28080 [23:40:25<31:55:30,  7.14s/it]
 43%|████▎     | 11982/28080 [23:40:32<31:54:32,  7.14s/it]
                                                           
{'loss': 0.6313, 'learning_rate': 0.0003205274553264895, 'epoch': 5.12}

 43%|████▎     | 11982/28080 [23:40:32<31:54:32,  7.14s/it]
 43%|████▎     | 11983/28080 [23:40:39<31:51:09,  7.12s/it]
                                                           
{'loss': 0.6001, 'learning_rate': 0.00032049979039532484, 'epoch': 5.12}

 43%|████▎     | 11983/28080 [23:40:39<31:51:09,  7.12s/it]
 43%|████▎     | 11984/28080 [23:40:46<31:53:11,  7.13s/it]
                                                           
{'loss': 0.6516, 'learning_rate': 0.00032047212452623327, 'epoch': 5.12}

 43%|████▎     | 11984/28080 [23:40:46<31:53:11,  7.13s/it]
 43%|████▎     | 11985/28080 [23:40:53<31:53:28,  7.13s/it]
                                                           
{'loss': 0.6538, 'learning_rate': 0.00032044445771958275, 'epoch': 5.12}

 43%|████▎     | 11985/28080 [23:40:53<31:53:28,  7.13s/it]
 43%|████▎     | 11986/28080 [23:41:00<31:49:22,  7.12s/it]
                                                           
{'loss': 0.6264, 'learning_rate': 0.00032041678997574136, 'epoch': 5.12}

 43%|████▎     | 11986/28080 [23:41:00<31:49:22,  7.12s/it]
 43%|████▎     | 11987/28080 [23:41:08<31:51:14,  7.13s/it]
                                                           
{'loss': 0.625, 'learning_rate': 0.00032038912129507725, 'epoch': 5.12}

 43%|████▎     | 11987/28080 [23:41:08<31:51:14,  7.13s/it]
 43%|████▎     | 11988/28080 [23:41:15<31:45:59,  7.11s/it]
                                                           
{'loss': 0.6236, 'learning_rate': 0.0003203614516779585, 'epoch': 5.12}

 43%|████▎     | 11988/28080 [23:41:15<31:45:59,  7.11s/it]
 43%|████▎     | 11989/28080 [23:41:22<31:46:05,  7.11s/it]
                                                           
{'loss': 0.6394, 'learning_rate': 0.0003203337811247532, 'epoch': 5.12}

 43%|████▎     | 11989/28080 [23:41:22<31:46:05,  7.11s/it]
 43%|████▎     | 11990/28080 [23:41:29<31:51:17,  7.13s/it]
                                                           
{'loss': 0.6025, 'learning_rate': 0.00032030610963582957, 'epoch': 5.12}

 43%|████▎     | 11990/28080 [23:41:29<31:51:17,  7.13s/it]
 43%|████▎     | 11991/28080 [23:41:36<31:55:29,  7.14s/it]
                                                           
{'loss': 0.6265, 'learning_rate': 0.00032027843721155565, 'epoch': 5.12}

 43%|████▎     | 11991/28080 [23:41:36<31:55:29,  7.14s/it]
 43%|████▎     | 11992/28080 [23:41:43<31:40:58,  7.09s/it]
                                                           
{'loss': 0.6317, 'learning_rate': 0.00032025076385229956, 'epoch': 5.12}

 43%|████▎     | 11992/28080 [23:41:43<31:40:58,  7.09s/it]
 43%|████▎     | 11993/28080 [23:41:50<31:35:16,  7.07s/it]
                                                           
{'loss': 0.6213, 'learning_rate': 0.0003202230895584296, 'epoch': 5.12}

 43%|████▎     | 11993/28080 [23:41:50<31:35:16,  7.07s/it]
 43%|████▎     | 11994/28080 [23:41:57<31:29:30,  7.05s/it]
                                                           
{'loss': 0.6354, 'learning_rate': 0.0003201954143303138, 'epoch': 5.12}

 43%|████▎     | 11994/28080 [23:41:57<31:29:30,  7.05s/it]
 43%|████▎     | 11995/28080 [23:42:04<31:37:11,  7.08s/it]
                                                           
{'loss': 0.6037, 'learning_rate': 0.0003201677381683206, 'epoch': 5.12}

 43%|████▎     | 11995/28080 [23:42:04<31:37:11,  7.08s/it]
 43%|████▎     | 11996/28080 [23:42:11<31:41:45,  7.09s/it]
                                                           
{'loss': 0.6269, 'learning_rate': 0.00032014006107281787, 'epoch': 5.12}

 43%|████▎     | 11996/28080 [23:42:11<31:41:45,  7.09s/it]
 43%|████▎     | 11997/28080 [23:42:18<31:47:16,  7.12s/it]
                                                           
{'loss': 0.6107, 'learning_rate': 0.000320112383044174, 'epoch': 5.13}

 43%|████▎     | 11997/28080 [23:42:18<31:47:16,  7.12s/it]
 43%|████▎     | 11998/28080 [23:42:26<31:53:23,  7.14s/it]
                                                           
{'loss': 0.5993, 'learning_rate': 0.00032008470408275726, 'epoch': 5.13}

 43%|████▎     | 11998/28080 [23:42:26<31:53:23,  7.14s/it]
 43%|████▎     | 11999/28080 [23:42:33<31:46:44,  7.11s/it]
                                                           
{'loss': 0.6291, 'learning_rate': 0.0003200570241889358, 'epoch': 5.13}

 43%|████▎     | 11999/28080 [23:42:33<31:46:44,  7.11s/it]
 43%|████▎     | 12000/28080 [23:42:40<31:54:12,  7.14s/it]
                                                           
{'loss': 0.6117, 'learning_rate': 0.00032002934336307793, 'epoch': 5.13}

 43%|████▎     | 12000/28080 [23:42:40<31:54:12,  7.14s/it]
 43%|████▎     | 12001/28080 [23:42:47<31:53:31,  7.14s/it]
                                                           
{'loss': 0.6169, 'learning_rate': 0.0003200016616055519, 'epoch': 5.13}

 43%|████▎     | 12001/28080 [23:42:47<31:53:31,  7.14s/it]
 43%|████▎     | 12002/28080 [23:42:54<31:51:30,  7.13s/it]
                                                           
{'loss': 0.6308, 'learning_rate': 0.000319973978916726, 'epoch': 5.13}

 43%|████▎     | 12002/28080 [23:42:54<31:51:30,  7.13s/it]
 43%|████▎     | 12003/28080 [23:43:01<31:43:55,  7.11s/it]
                                                           
{'loss': 0.6072, 'learning_rate': 0.0003199462952969684, 'epoch': 5.13}

 43%|████▎     | 12003/28080 [23:43:01<31:43:55,  7.11s/it]
 43%|████▎     | 12004/28080 [23:43:08<31:48:37,  7.12s/it]
                                                           
{'loss': 0.603, 'learning_rate': 0.0003199186107466476, 'epoch': 5.13}

 43%|████▎     | 12004/28080 [23:43:08<31:48:37,  7.12s/it]
 43%|████▎     | 12005/28080 [23:43:15<31:44:51,  7.11s/it]
                                                           
{'loss': 0.6163, 'learning_rate': 0.00031989092526613175, 'epoch': 5.13}

 43%|████▎     | 12005/28080 [23:43:15<31:44:51,  7.11s/it]
 43%|████▎     | 12006/28080 [23:43:23<31:49:07,  7.13s/it]
                                                           
{'loss': 0.633, 'learning_rate': 0.00031986323885578924, 'epoch': 5.13}

 43%|████▎     | 12006/28080 [23:43:23<31:49:07,  7.13s/it]
 43%|████▎     | 12007/28080 [23:43:30<31:46:52,  7.12s/it]
                                                           
{'loss': 0.6208, 'learning_rate': 0.0003198355515159884, 'epoch': 5.13}

 43%|████▎     | 12007/28080 [23:43:30<31:46:52,  7.12s/it]
 43%|████▎     | 12008/28080 [23:43:37<31:46:49,  7.12s/it]
                                                           
{'loss': 0.6262, 'learning_rate': 0.00031980786324709763, 'epoch': 5.13}

 43%|████▎     | 12008/28080 [23:43:37<31:46:49,  7.12s/it]
 43%|████▎     | 12009/28080 [23:43:44<31:50:49,  7.13s/it]
                                                           
{'loss': 0.6182, 'learning_rate': 0.00031978017404948536, 'epoch': 5.13}

 43%|████▎     | 12009/28080 [23:43:44<31:50:49,  7.13s/it]
 43%|████▎     | 12010/28080 [23:43:51<31:52:18,  7.14s/it]
                                                           
{'loss': 0.6205, 'learning_rate': 0.00031975248392351966, 'epoch': 5.13}

 43%|████▎     | 12010/28080 [23:43:51<31:52:18,  7.14s/it]
 43%|████▎     | 12011/28080 [23:43:58<31:53:05,  7.14s/it]
                                                           
{'loss': 0.6379, 'learning_rate': 0.0003197247928695693, 'epoch': 5.13}

 43%|████▎     | 12011/28080 [23:43:58<31:53:05,  7.14s/it]
 43%|████▎     | 12012/28080 [23:44:05<31:48:42,  7.13s/it]
                                                           
{'loss': 0.6237, 'learning_rate': 0.0003196971008880024, 'epoch': 5.13}

 43%|████▎     | 12012/28080 [23:44:05<31:48:42,  7.13s/it]
 43%|████▎     | 12013/28080 [23:44:13<31:46:44,  7.12s/it]
                                                           
{'loss': 0.6436, 'learning_rate': 0.0003196694079791874, 'epoch': 5.13}

 43%|████▎     | 12013/28080 [23:44:13<31:46:44,  7.12s/it]
 43%|████▎     | 12014/28080 [23:44:20<31:42:06,  7.10s/it]
                                                           
{'loss': 0.6234, 'learning_rate': 0.00031964171414349294, 'epoch': 5.13}

 43%|████▎     | 12014/28080 [23:44:20<31:42:06,  7.10s/it]
 43%|████▎     | 12015/28080 [23:44:27<31:45:29,  7.12s/it]
                                                           
{'loss': 0.5928, 'learning_rate': 0.0003196140193812874, 'epoch': 5.13}

 43%|████▎     | 12015/28080 [23:44:27<31:45:29,  7.12s/it]
 43%|████▎     | 12016/28080 [23:44:34<31:50:01,  7.13s/it]
                                                           
{'loss': 0.6297, 'learning_rate': 0.00031958632369293895, 'epoch': 5.13}

 43%|████▎     | 12016/28080 [23:44:34<31:50:01,  7.13s/it]
 43%|████▎     | 12017/28080 [23:44:41<31:47:49,  7.13s/it]
                                                           
{'loss': 0.6185, 'learning_rate': 0.00031955862707881634, 'epoch': 5.13}

 43%|████▎     | 12017/28080 [23:44:41<31:47:49,  7.13s/it]
 43%|████▎     | 12018/28080 [23:44:48<31:36:18,  7.08s/it]
                                                           
{'loss': 0.6297, 'learning_rate': 0.00031953092953928793, 'epoch': 5.13}

 43%|████▎     | 12018/28080 [23:44:48<31:36:18,  7.08s/it]
 43%|████▎     | 12019/28080 [23:44:55<31:44:10,  7.11s/it]
                                                           
{'loss': 0.6287, 'learning_rate': 0.0003195032310747223, 'epoch': 5.13}

 43%|████▎     | 12019/28080 [23:44:55<31:44:10,  7.11s/it]
 43%|████▎     | 12020/28080 [23:45:02<31:49:19,  7.13s/it]
                                                           
{'loss': 0.6341, 'learning_rate': 0.00031947553168548785, 'epoch': 5.13}

 43%|████▎     | 12020/28080 [23:45:02<31:49:19,  7.13s/it]
 43%|████▎     | 12021/28080 [23:45:10<31:50:55,  7.14s/it]
                                                           
{'loss': 0.6253, 'learning_rate': 0.0003194478313719531, 'epoch': 5.14}

 43%|████▎     | 12021/28080 [23:45:10<31:50:55,  7.14s/it]
 43%|████▎     | 12022/28080 [23:45:17<31:51:58,  7.14s/it]
                                                           
{'loss': 0.6314, 'learning_rate': 0.0003194201301344866, 'epoch': 5.14}

 43%|████▎     | 12022/28080 [23:45:17<31:51:58,  7.14s/it]
 43%|████▎     | 12023/28080 [23:45:24<31:55:44,  7.16s/it]
                                                           
{'loss': 0.6269, 'learning_rate': 0.0003193924279734568, 'epoch': 5.14}

 43%|████▎     | 12023/28080 [23:45:24<31:55:44,  7.16s/it]
 43%|████▎     | 12024/28080 [23:45:31<32:04:45,  7.19s/it]
                                                           
{'loss': 0.6123, 'learning_rate': 0.00031936472488923245, 'epoch': 5.14}

 43%|████▎     | 12024/28080 [23:45:31<32:04:45,  7.19s/it]
 43%|████▎     | 12025/28080 [23:45:38<31:58:30,  7.17s/it]
                                                           
{'loss': 0.6278, 'learning_rate': 0.000319337020882182, 'epoch': 5.14}

 43%|████▎     | 12025/28080 [23:45:38<31:58:30,  7.17s/it]
 43%|████▎     | 12026/28080 [23:45:45<31:59:10,  7.17s/it]
                                                           
{'loss': 0.6249, 'learning_rate': 0.000319309315952674, 'epoch': 5.14}

 43%|████▎     | 12026/28080 [23:45:45<31:59:10,  7.17s/it]
 43%|████▎     | 12027/28080 [23:45:53<31:56:39,  7.16s/it]
                                                           
{'loss': 0.6248, 'learning_rate': 0.00031928161010107706, 'epoch': 5.14}

 43%|████▎     | 12027/28080 [23:45:53<31:56:39,  7.16s/it]
 43%|████▎     | 12028/28080 [23:46:00<31:45:59,  7.12s/it]
                                                           
{'loss': 0.599, 'learning_rate': 0.00031925390332775974, 'epoch': 5.14}

 43%|████▎     | 12028/28080 [23:46:00<31:45:59,  7.12s/it]
 43%|████▎     | 12029/28080 [23:46:07<31:50:39,  7.14s/it]
                                                           
{'loss': 0.6078, 'learning_rate': 0.00031922619563309066, 'epoch': 5.14}

 43%|████▎     | 12029/28080 [23:46:07<31:50:39,  7.14s/it]
 43%|████▎     | 12030/28080 [23:46:14<31:56:57,  7.17s/it]
                                                           
{'loss': 0.6186, 'learning_rate': 0.00031919848701743845, 'epoch': 5.14}

 43%|████▎     | 12030/28080 [23:46:14<31:56:57,  7.17s/it]
 43%|████▎     | 12031/28080 [23:46:21<31:43:56,  7.12s/it]
                                                           
{'loss': 0.6252, 'learning_rate': 0.00031917077748117186, 'epoch': 5.14}

 43%|████▎     | 12031/28080 [23:46:21<31:43:56,  7.12s/it]
 43%|████▎     | 12032/28080 [23:46:28<31:43:34,  7.12s/it]
                                                           
{'loss': 0.6101, 'learning_rate': 0.00031914306702465935, 'epoch': 5.14}

 43%|████▎     | 12032/28080 [23:46:28<31:43:34,  7.12s/it]
 43%|████▎     | 12033/28080 [23:46:35<31:49:18,  7.14s/it]
                                                           
{'loss': 0.6271, 'learning_rate': 0.0003191153556482697, 'epoch': 5.14}

 43%|████▎     | 12033/28080 [23:46:35<31:49:18,  7.14s/it]
 43%|████▎     | 12034/28080 [23:46:42<31:44:50,  7.12s/it]
                                                           
{'loss': 0.618, 'learning_rate': 0.00031908764335237156, 'epoch': 5.14}

 43%|████▎     | 12034/28080 [23:46:42<31:44:50,  7.12s/it]
 43%|████▎     | 12035/28080 [23:46:50<31:44:35,  7.12s/it]
                                                           
{'loss': 0.6197, 'learning_rate': 0.0003190599301373336, 'epoch': 5.14}

 43%|████▎     | 12035/28080 [23:46:50<31:44:35,  7.12s/it]
 43%|████▎     | 12036/28080 [23:46:57<31:44:59,  7.12s/it]
                                                           
{'loss': 0.6088, 'learning_rate': 0.00031903221600352444, 'epoch': 5.14}

 43%|████▎     | 12036/28080 [23:46:57<31:44:59,  7.12s/it]
 43%|████▎     | 12037/28080 [23:47:04<31:45:31,  7.13s/it]
                                                           
{'loss': 0.6215, 'learning_rate': 0.0003190045009513129, 'epoch': 5.14}

 43%|████▎     | 12037/28080 [23:47:04<31:45:31,  7.13s/it]
 43%|████▎     | 12038/28080 [23:47:11<31:47:14,  7.13s/it]
                                                           
{'loss': 0.6142, 'learning_rate': 0.0003189767849810677, 'epoch': 5.14}

 43%|████▎     | 12038/28080 [23:47:11<31:47:14,  7.13s/it]
 43%|████▎     | 12039/28080 [23:47:18<31:45:59,  7.13s/it]
                                                           
{'loss': 0.6151, 'learning_rate': 0.0003189490680931575, 'epoch': 5.14}

 43%|████▎     | 12039/28080 [23:47:18<31:45:59,  7.13s/it]
 43%|████▎     | 12040/28080 [23:47:25<31:34:06,  7.09s/it]
                                                           
{'loss': 0.6455, 'learning_rate': 0.0003189213502879512, 'epoch': 5.14}

 43%|████▎     | 12040/28080 [23:47:25<31:34:06,  7.09s/it]
 43%|████▎     | 12041/28080 [23:47:32<31:44:29,  7.12s/it]
                                                           
{'loss': 0.6308, 'learning_rate': 0.0003188936315658173, 'epoch': 5.14}

 43%|████▎     | 12041/28080 [23:47:32<31:44:29,  7.12s/it]
 43%|████▎     | 12042/28080 [23:47:39<31:35:08,  7.09s/it]
                                                           
{'loss': 0.6133, 'learning_rate': 0.00031886591192712473, 'epoch': 5.14}

 43%|████▎     | 12042/28080 [23:47:39<31:35:08,  7.09s/it]
 43%|████▎     | 12043/28080 [23:47:46<31:39:09,  7.11s/it]
                                                           
{'loss': 0.5974, 'learning_rate': 0.0003188381913722422, 'epoch': 5.14}

 43%|████▎     | 12043/28080 [23:47:46<31:39:09,  7.11s/it]
 43%|████▎     | 12044/28080 [23:47:53<31:32:55,  7.08s/it]
                                                           
{'loss': 0.6104, 'learning_rate': 0.0003188104699015386, 'epoch': 5.15}

 43%|████▎     | 12044/28080 [23:47:53<31:32:55,  7.08s/it]
 43%|████▎     | 12045/28080 [23:48:01<31:39:28,  7.11s/it]
                                                           
{'loss': 0.63, 'learning_rate': 0.0003187827475153828, 'epoch': 5.15}

 43%|████▎     | 12045/28080 [23:48:01<31:39:28,  7.11s/it]
 43%|████▎     | 12046/28080 [23:48:08<31:42:29,  7.12s/it]
                                                           
{'loss': 0.632, 'learning_rate': 0.0003187550242141433, 'epoch': 5.15}

 43%|████▎     | 12046/28080 [23:48:08<31:42:29,  7.12s/it]
 43%|████▎     | 12047/28080 [23:48:15<31:32:45,  7.08s/it]
                                                           
{'loss': 0.6383, 'learning_rate': 0.0003187272999981892, 'epoch': 5.15}

 43%|████▎     | 12047/28080 [23:48:15<31:32:45,  7.08s/it]
 43%|████▎     | 12048/28080 [23:48:22<31:37:52,  7.10s/it]
                                                           
{'loss': 0.6305, 'learning_rate': 0.0003186995748678894, 'epoch': 5.15}

 43%|████▎     | 12048/28080 [23:48:22<31:37:52,  7.10s/it]
 43%|████▎     | 12049/28080 [23:48:29<31:38:57,  7.11s/it]
                                                           
{'loss': 0.626, 'learning_rate': 0.00031867184882361244, 'epoch': 5.15}

 43%|████▎     | 12049/28080 [23:48:29<31:38:57,  7.11s/it]
 43%|████▎     | 12050/28080 [23:48:36<31:42:46,  7.12s/it]
                                                           
{'loss': 0.6007, 'learning_rate': 0.00031864412186572756, 'epoch': 5.15}

 43%|████▎     | 12050/28080 [23:48:36<31:42:46,  7.12s/it]
 43%|████▎     | 12051/28080 [23:48:43<31:44:14,  7.13s/it]
                                                           
{'loss': 0.6068, 'learning_rate': 0.0003186163939946033, 'epoch': 5.15}

 43%|████▎     | 12051/28080 [23:48:43<31:44:14,  7.13s/it]
 43%|████▎     | 12052/28080 [23:48:51<31:54:04,  7.17s/it]
                                                           
{'loss': 0.6104, 'learning_rate': 0.0003185886652106088, 'epoch': 5.15}

 43%|████▎     | 12052/28080 [23:48:51<31:54:04,  7.17s/it]
 43%|████▎     | 12053/28080 [23:48:58<31:49:55,  7.15s/it]
                                                           
{'loss': 0.6345, 'learning_rate': 0.0003185609355141128, 'epoch': 5.15}

 43%|████▎     | 12053/28080 [23:48:58<31:49:55,  7.15s/it]
 43%|████▎     | 12054/28080 [23:49:05<31:53:07,  7.16s/it]
                                                           
{'loss': 0.6287, 'learning_rate': 0.0003185332049054843, 'epoch': 5.15}

 43%|████▎     | 12054/28080 [23:49:05<31:53:07,  7.16s/it]
 43%|████▎     | 12055/28080 [23:49:12<31:46:05,  7.14s/it]
                                                           
{'loss': 0.6078, 'learning_rate': 0.00031850547338509226, 'epoch': 5.15}

 43%|████▎     | 12055/28080 [23:49:12<31:46:05,  7.14s/it]
 43%|████▎     | 12056/28080 [23:49:19<31:46:03,  7.14s/it]
                                                           
{'loss': 0.6373, 'learning_rate': 0.0003184777409533055, 'epoch': 5.15}

 43%|████▎     | 12056/28080 [23:49:19<31:46:03,  7.14s/it]
 43%|████▎     | 12057/28080 [23:49:26<31:48:27,  7.15s/it]
                                                           
{'loss': 0.6169, 'learning_rate': 0.00031845000761049314, 'epoch': 5.15}

 43%|████▎     | 12057/28080 [23:49:26<31:48:27,  7.15s/it]
 43%|████▎     | 12058/28080 [23:49:33<31:52:28,  7.16s/it]
                                                           
{'loss': 0.6376, 'learning_rate': 0.00031842227335702393, 'epoch': 5.15}

 43%|████▎     | 12058/28080 [23:49:33<31:52:28,  7.16s/it]
 43%|████▎     | 12059/28080 [23:49:41<31:45:15,  7.14s/it]
                                                           
{'loss': 0.6252, 'learning_rate': 0.0003183945381932671, 'epoch': 5.15}

 43%|████▎     | 12059/28080 [23:49:41<31:45:15,  7.14s/it]
 43%|████▎     | 12060/28080 [23:49:48<31:45:38,  7.14s/it]
                                                           
{'loss': 0.6104, 'learning_rate': 0.00031836680211959134, 'epoch': 5.15}

 43%|████▎     | 12060/28080 [23:49:48<31:45:38,  7.14s/it]
 43%|████▎     | 12061/28080 [23:49:55<31:40:47,  7.12s/it]
                                                           
{'loss': 0.6259, 'learning_rate': 0.0003183390651363659, 'epoch': 5.15}

 43%|████▎     | 12061/28080 [23:49:55<31:40:47,  7.12s/it]
 43%|████▎     | 12062/28080 [23:50:02<31:35:00,  7.10s/it]
                                                           
{'loss': 0.6121, 'learning_rate': 0.00031831132724395974, 'epoch': 5.15}

 43%|████▎     | 12062/28080 [23:50:02<31:35:00,  7.10s/it]
 43%|████▎     | 12063/28080 [23:50:09<31:46:54,  7.14s/it]
                                                           
{'loss': 0.6132, 'learning_rate': 0.00031828358844274173, 'epoch': 5.15}

 43%|████▎     | 12063/28080 [23:50:09<31:46:54,  7.14s/it]
 43%|████▎     | 12064/28080 [23:50:16<31:43:08,  7.13s/it]
                                                           
{'loss': 0.6072, 'learning_rate': 0.0003182558487330811, 'epoch': 5.15}

 43%|████▎     | 12064/28080 [23:50:16<31:43:08,  7.13s/it]
 43%|████▎     | 12065/28080 [23:50:23<31:43:42,  7.13s/it]
                                                           
{'loss': 0.6425, 'learning_rate': 0.0003182281081153468, 'epoch': 5.15}

 43%|████▎     | 12065/28080 [23:50:23<31:43:42,  7.13s/it]
 43%|████▎     | 12066/28080 [23:50:30<31:42:07,  7.13s/it]
                                                           
{'loss': 0.6448, 'learning_rate': 0.00031820036658990793, 'epoch': 5.15}

 43%|████▎     | 12066/28080 [23:50:30<31:42:07,  7.13s/it]
 43%|████▎     | 12067/28080 [23:50:38<31:43:02,  7.13s/it]
                                                           
{'loss': 0.6277, 'learning_rate': 0.0003181726241571335, 'epoch': 5.15}

 43%|████▎     | 12067/28080 [23:50:38<31:43:02,  7.13s/it]
 43%|████▎     | 12068/28080 [23:50:45<31:42:40,  7.13s/it]
                                                           
{'loss': 0.6411, 'learning_rate': 0.0003181448808173926, 'epoch': 5.16}

 43%|████▎     | 12068/28080 [23:50:45<31:42:40,  7.13s/it]
 43%|████▎     | 12069/28080 [23:50:52<31:52:16,  7.17s/it]
                                                           
{'loss': 0.6397, 'learning_rate': 0.00031811713657105446, 'epoch': 5.16}

 43%|████▎     | 12069/28080 [23:50:52<31:52:16,  7.17s/it]
 43%|████▎     | 12070/28080 [23:50:59<31:47:59,  7.15s/it]
                                                           
{'loss': 0.6327, 'learning_rate': 0.00031808939141848803, 'epoch': 5.16}

 43%|████▎     | 12070/28080 [23:50:59<31:47:59,  7.15s/it]
 43%|████▎     | 12071/28080 [23:51:06<31:50:45,  7.16s/it]
                                                           
{'loss': 0.6379, 'learning_rate': 0.00031806164536006255, 'epoch': 5.16}

 43%|████▎     | 12071/28080 [23:51:06<31:50:45,  7.16s/it]
 43%|████▎     | 12072/28080 [23:51:13<31:48:26,  7.15s/it]
                                                           
{'loss': 0.6373, 'learning_rate': 0.00031803389839614704, 'epoch': 5.16}

 43%|████▎     | 12072/28080 [23:51:13<31:48:26,  7.15s/it]
 43%|████▎     | 12073/28080 [23:51:20<31:45:16,  7.14s/it]
                                                           
{'loss': 0.6325, 'learning_rate': 0.0003180061505271107, 'epoch': 5.16}

 43%|████▎     | 12073/28080 [23:51:20<31:45:16,  7.14s/it]
 43%|████▎     | 12074/28080 [23:51:28<31:53:30,  7.17s/it]
                                                           
{'loss': 0.6059, 'learning_rate': 0.0003179784017533227, 'epoch': 5.16}

 43%|████▎     | 12074/28080 [23:51:28<31:53:30,  7.17s/it]
 43%|████▎     | 12075/28080 [23:51:35<31:47:36,  7.15s/it]
                                                           
{'loss': 0.6252, 'learning_rate': 0.0003179506520751522, 'epoch': 5.16}

 43%|████▎     | 12075/28080 [23:51:35<31:47:36,  7.15s/it]
 43%|████▎     | 12076/28080 [23:51:42<31:39:17,  7.12s/it]
                                                           
{'loss': 0.6247, 'learning_rate': 0.0003179229014929683, 'epoch': 5.16}

 43%|████▎     | 12076/28080 [23:51:42<31:39:17,  7.12s/it]
 43%|████▎     | 12077/28080 [23:51:49<31:44:18,  7.14s/it]
                                                           
{'loss': 0.6296, 'learning_rate': 0.0003178951500071403, 'epoch': 5.16}

 43%|████▎     | 12077/28080 [23:51:49<31:44:18,  7.14s/it]
 43%|████▎     | 12078/28080 [23:51:56<31:40:14,  7.13s/it]
                                                           
{'loss': 0.6433, 'learning_rate': 0.0003178673976180374, 'epoch': 5.16}

 43%|████▎     | 12078/28080 [23:51:56<31:40:14,  7.13s/it]
 43%|████▎     | 12079/28080 [23:52:03<31:40:30,  7.13s/it]
                                                           
{'loss': 0.6288, 'learning_rate': 0.00031783964432602883, 'epoch': 5.16}

 43%|████▎     | 12079/28080 [23:52:03<31:40:30,  7.13s/it]
 43%|████▎     | 12080/28080 [23:52:10<31:40:50,  7.13s/it]
                                                           
{'loss': 0.6436, 'learning_rate': 0.0003178118901314837, 'epoch': 5.16}

 43%|████▎     | 12080/28080 [23:52:10<31:40:50,  7.13s/it]
 43%|████▎     | 12081/28080 [23:52:18<31:50:38,  7.17s/it]
                                                           
{'loss': 0.6253, 'learning_rate': 0.00031778413503477144, 'epoch': 5.16}

 43%|████▎     | 12081/28080 [23:52:18<31:50:38,  7.17s/it]
 43%|████▎     | 12082/28080 [23:52:25<31:47:54,  7.16s/it]
                                                           
{'loss': 0.6091, 'learning_rate': 0.0003177563790362611, 'epoch': 5.16}

 43%|████▎     | 12082/28080 [23:52:25<31:47:54,  7.16s/it]
 43%|████▎     | 12083/28080 [23:52:32<31:44:07,  7.14s/it]
                                                           
{'loss': 0.6129, 'learning_rate': 0.00031772862213632204, 'epoch': 5.16}

 43%|████▎     | 12083/28080 [23:52:32<31:44:07,  7.14s/it]
 43%|████▎     | 12084/28080 [23:52:39<31:46:16,  7.15s/it]
                                                           
{'loss': 0.617, 'learning_rate': 0.0003177008643353235, 'epoch': 5.16}

 43%|████▎     | 12084/28080 [23:52:39<31:46:16,  7.15s/it]
 43%|████▎     | 12085/28080 [23:52:46<31:41:51,  7.13s/it]
                                                           
{'loss': 0.6234, 'learning_rate': 0.0003176731056336349, 'epoch': 5.16}

 43%|████▎     | 12085/28080 [23:52:46<31:41:51,  7.13s/it]
 43%|████▎     | 12086/28080 [23:52:53<31:34:55,  7.11s/it]
                                                           
{'loss': 0.6324, 'learning_rate': 0.0003176453460316254, 'epoch': 5.16}

 43%|████▎     | 12086/28080 [23:52:53<31:34:55,  7.11s/it]
 43%|████▎     | 12087/28080 [23:53:00<31:39:55,  7.13s/it]
                                                           
{'loss': 0.6221, 'learning_rate': 0.0003176175855296644, 'epoch': 5.16}

 43%|████▎     | 12087/28080 [23:53:00<31:39:55,  7.13s/it]
 43%|████▎     | 12088/28080 [23:53:08<31:42:08,  7.14s/it]
                                                           
{'loss': 0.613, 'learning_rate': 0.0003175898241281211, 'epoch': 5.16}

 43%|████▎     | 12088/28080 [23:53:08<31:42:08,  7.14s/it]
 43%|████▎     | 12089/28080 [23:53:15<31:41:20,  7.13s/it]
                                                           
{'loss': 0.614, 'learning_rate': 0.0003175620618273649, 'epoch': 5.16}

 43%|████▎     | 12089/28080 [23:53:15<31:41:20,  7.13s/it]
 43%|████▎     | 12090/28080 [23:53:22<31:42:50,  7.14s/it]
                                                           
{'loss': 0.5952, 'learning_rate': 0.00031753429862776527, 'epoch': 5.16}

 43%|████▎     | 12090/28080 [23:53:22<31:42:50,  7.14s/it]
 43%|████▎     | 12091/28080 [23:53:29<31:34:13,  7.11s/it]
                                                           
{'loss': 0.6334, 'learning_rate': 0.00031750653452969146, 'epoch': 5.17}

 43%|████▎     | 12091/28080 [23:53:29<31:34:13,  7.11s/it]
 43%|████▎     | 12092/28080 [23:53:36<31:33:17,  7.11s/it]
                                                           
{'loss': 0.606, 'learning_rate': 0.0003174787695335128, 'epoch': 5.17}

 43%|████▎     | 12092/28080 [23:53:36<31:33:17,  7.11s/it]
 43%|████▎     | 12093/28080 [23:53:43<31:35:29,  7.11s/it]
                                                           
{'loss': 0.6428, 'learning_rate': 0.0003174510036395988, 'epoch': 5.17}

 43%|████▎     | 12093/28080 [23:53:43<31:35:29,  7.11s/it]
 43%|████▎     | 12094/28080 [23:53:50<31:31:50,  7.10s/it]
                                                           
{'loss': 0.6105, 'learning_rate': 0.0003174232368483186, 'epoch': 5.17}

 43%|████▎     | 12094/28080 [23:53:50<31:31:50,  7.10s/it]
 43%|████▎     | 12095/28080 [23:53:57<31:31:20,  7.10s/it]
                                                           
{'loss': 0.6063, 'learning_rate': 0.00031739546916004197, 'epoch': 5.17}

 43%|████▎     | 12095/28080 [23:53:57<31:31:20,  7.10s/it]
 43%|████▎     | 12096/28080 [23:54:04<31:36:03,  7.12s/it]
                                                           
{'loss': 0.6221, 'learning_rate': 0.0003173677005751381, 'epoch': 5.17}

 43%|████▎     | 12096/28080 [23:54:04<31:36:03,  7.12s/it]
 43%|████▎     | 12097/28080 [23:54:12<31:34:01,  7.11s/it]
                                                           
{'loss': 0.6308, 'learning_rate': 0.0003173399310939764, 'epoch': 5.17}

 43%|████▎     | 12097/28080 [23:54:12<31:34:01,  7.11s/it]
 43%|████▎     | 12098/28080 [23:54:19<31:39:26,  7.13s/it]
                                                           
{'loss': 0.63, 'learning_rate': 0.00031731216071692646, 'epoch': 5.17}

 43%|████▎     | 12098/28080 [23:54:19<31:39:26,  7.13s/it]
 43%|████▎     | 12099/28080 [23:54:26<31:43:50,  7.15s/it]
                                                           
{'loss': 0.6176, 'learning_rate': 0.00031728438944435766, 'epoch': 5.17}

 43%|████▎     | 12099/28080 [23:54:26<31:43:50,  7.15s/it]
 43%|████▎     | 12100/28080 [23:54:33<31:40:18,  7.14s/it]
                                                           
{'loss': 0.6145, 'learning_rate': 0.0003172566172766395, 'epoch': 5.17}

 43%|████▎     | 12100/28080 [23:54:33<31:40:18,  7.14s/it]
 43%|████▎     | 12101/28080 [23:54:40<31:39:27,  7.13s/it]
                                                           
{'loss': 0.6305, 'learning_rate': 0.0003172288442141414, 'epoch': 5.17}

 43%|████▎     | 12101/28080 [23:54:40<31:39:27,  7.13s/it]
 43%|████▎     | 12102/28080 [23:54:47<31:39:50,  7.13s/it]
                                                           
{'loss': 0.6317, 'learning_rate': 0.0003172010702572329, 'epoch': 5.17}

 43%|████▎     | 12102/28080 [23:54:47<31:39:50,  7.13s/it]
 43%|████▎     | 12103/28080 [23:54:54<31:34:31,  7.11s/it]
                                                           
{'loss': 0.6302, 'learning_rate': 0.00031717329540628344, 'epoch': 5.17}

 43%|████▎     | 12103/28080 [23:54:54<31:34:31,  7.11s/it]
 43%|████▎     | 12104/28080 [23:55:01<31:32:34,  7.11s/it]
                                                           
{'loss': 0.628, 'learning_rate': 0.0003171455196616626, 'epoch': 5.17}

 43%|████▎     | 12104/28080 [23:55:01<31:32:34,  7.11s/it]
 43%|████▎     | 12105/28080 [23:55:09<31:34:01,  7.11s/it]
                                                           
{'loss': 0.6124, 'learning_rate': 0.0003171177430237399, 'epoch': 5.17}

 43%|████▎     | 12105/28080 [23:55:09<31:34:01,  7.11s/it]
 43%|████▎     | 12106/28080 [23:55:16<31:30:23,  7.10s/it]
                                                           
{'loss': 0.6077, 'learning_rate': 0.00031708996549288486, 'epoch': 5.17}

 43%|████▎     | 12106/28080 [23:55:16<31:30:23,  7.10s/it]
 43%|████▎     | 12107/28080 [23:55:23<31:34:58,  7.12s/it]
                                                           
{'loss': 0.6122, 'learning_rate': 0.0003170621870694671, 'epoch': 5.17}

 43%|████▎     | 12107/28080 [23:55:23<31:34:58,  7.12s/it]
 43%|████▎     | 12108/28080 [23:55:30<31:38:35,  7.13s/it]
                                                           
{'loss': 0.6237, 'learning_rate': 0.00031703440775385607, 'epoch': 5.17}

 43%|████▎     | 12108/28080 [23:55:30<31:38:35,  7.13s/it]
 43%|████▎     | 12109/28080 [23:55:37<31:39:11,  7.13s/it]
                                                           
{'loss': 0.6132, 'learning_rate': 0.0003170066275464214, 'epoch': 5.17}

 43%|████▎     | 12109/28080 [23:55:37<31:39:11,  7.13s/it]
 43%|████▎     | 12110/28080 [23:55:44<31:43:42,  7.15s/it]
                                                           
{'loss': 0.6253, 'learning_rate': 0.0003169788464475327, 'epoch': 5.17}

 43%|████▎     | 12110/28080 [23:55:44<31:43:42,  7.15s/it]
 43%|████▎     | 12111/28080 [23:55:51<31:42:40,  7.15s/it]
                                                           
{'loss': 0.6398, 'learning_rate': 0.0003169510644575595, 'epoch': 5.17}

 43%|████▎     | 12111/28080 [23:55:51<31:42:40,  7.15s/it]
 43%|████▎     | 12112/28080 [23:55:59<31:44:54,  7.16s/it]
                                                           
{'loss': 0.6098, 'learning_rate': 0.00031692328157687156, 'epoch': 5.17}

 43%|████▎     | 12112/28080 [23:55:59<31:44:54,  7.16s/it]
 43%|████▎     | 12113/28080 [23:56:06<31:31:00,  7.11s/it]
                                                           
{'loss': 0.6276, 'learning_rate': 0.00031689549780583825, 'epoch': 5.17}

 43%|████▎     | 12113/28080 [23:56:06<31:31:00,  7.11s/it]
 43%|████▎     | 12114/28080 [23:56:13<31:31:46,  7.11s/it]
                                                           
{'loss': 0.6174, 'learning_rate': 0.00031686771314482946, 'epoch': 5.17}

 43%|████▎     | 12114/28080 [23:56:13<31:31:46,  7.11s/it]
 43%|████▎     | 12115/28080 [23:56:20<31:31:44,  7.11s/it]
                                                           
{'loss': 0.6138, 'learning_rate': 0.0003168399275942148, 'epoch': 5.18}

 43%|████▎     | 12115/28080 [23:56:20<31:31:44,  7.11s/it]
 43%|████▎     | 12116/28080 [23:56:27<31:26:09,  7.09s/it]
                                                           
{'loss': 0.6214, 'learning_rate': 0.0003168121411543637, 'epoch': 5.18}

 43%|████▎     | 12116/28080 [23:56:27<31:26:09,  7.09s/it]
 43%|████▎     | 12117/28080 [23:56:34<31:36:13,  7.13s/it]
                                                           
{'loss': 0.6134, 'learning_rate': 0.00031678435382564605, 'epoch': 5.18}

 43%|████▎     | 12117/28080 [23:56:34<31:36:13,  7.13s/it]
 43%|████▎     | 12118/28080 [23:56:41<31:39:32,  7.14s/it]
                                                           
{'loss': 0.601, 'learning_rate': 0.00031675656560843147, 'epoch': 5.18}

 43%|████▎     | 12118/28080 [23:56:41<31:39:32,  7.14s/it]
 43%|████▎     | 12119/28080 [23:56:48<31:38:18,  7.14s/it]
                                                           
{'loss': 0.6376, 'learning_rate': 0.00031672877650308975, 'epoch': 5.18}

 43%|████▎     | 12119/28080 [23:56:48<31:38:18,  7.14s/it]
 43%|████▎     | 12120/28080 [23:56:55<31:38:53,  7.14s/it]
                                                           
{'loss': 0.6347, 'learning_rate': 0.00031670098650999034, 'epoch': 5.18}

 43%|████▎     | 12120/28080 [23:56:56<31:38:53,  7.14s/it]
 43%|████▎     | 12121/28080 [23:57:03<31:33:09,  7.12s/it]
                                                           
{'loss': 0.6292, 'learning_rate': 0.00031667319562950317, 'epoch': 5.18}

 43%|████▎     | 12121/28080 [23:57:03<31:33:09,  7.12s/it]
 43%|████▎     | 12122/28080 [23:57:10<31:30:49,  7.11s/it]
                                                           
{'loss': 0.6217, 'learning_rate': 0.00031664540386199794, 'epoch': 5.18}

 43%|████▎     | 12122/28080 [23:57:10<31:30:49,  7.11s/it]
 43%|████▎     | 12123/28080 [23:57:17<31:36:47,  7.13s/it]
                                                           
{'loss': 0.624, 'learning_rate': 0.0003166176112078443, 'epoch': 5.18}

 43%|████▎     | 12123/28080 [23:57:17<31:36:47,  7.13s/it]
 43%|████▎     | 12124/28080 [23:57:24<31:40:00,  7.14s/it]
                                                           
{'loss': 0.6033, 'learning_rate': 0.00031658981766741217, 'epoch': 5.18}

 43%|████▎     | 12124/28080 [23:57:24<31:40:00,  7.14s/it]
 43%|████▎     | 12125/28080 [23:57:31<31:41:49,  7.15s/it]
                                                           
{'loss': 0.6326, 'learning_rate': 0.0003165620232410711, 'epoch': 5.18}

 43%|████▎     | 12125/28080 [23:57:31<31:41:49,  7.15s/it]
 43%|████▎     | 12126/28080 [23:57:38<31:32:58,  7.12s/it]
                                                           
{'loss': 0.6533, 'learning_rate': 0.00031653422792919113, 'epoch': 5.18}

 43%|████▎     | 12126/28080 [23:57:38<31:32:58,  7.12s/it]
 43%|████▎     | 12127/28080 [23:57:45<31:43:13,  7.16s/it]
                                                           
{'loss': 0.6153, 'learning_rate': 0.00031650643173214177, 'epoch': 5.18}

 43%|████▎     | 12127/28080 [23:57:45<31:43:13,  7.16s/it]
 43%|████▎     | 12128/28080 [23:57:53<31:37:09,  7.14s/it]
                                                           
{'loss': 0.6423, 'learning_rate': 0.00031647863465029296, 'epoch': 5.18}

 43%|████▎     | 12128/28080 [23:57:53<31:37:09,  7.14s/it]
 43%|████▎     | 12129/28080 [23:58:00<31:36:40,  7.13s/it]
                                                           
{'loss': 0.6301, 'learning_rate': 0.0003164508366840146, 'epoch': 5.18}

 43%|████▎     | 12129/28080 [23:58:00<31:36:40,  7.13s/it]
 43%|████▎     | 12130/28080 [23:58:07<31:34:57,  7.13s/it]
                                                           
{'loss': 0.6191, 'learning_rate': 0.0003164230378336763, 'epoch': 5.18}

 43%|████▎     | 12130/28080 [23:58:07<31:34:57,  7.13s/it]
 43%|████▎     | 12131/28080 [23:58:14<31:32:17,  7.12s/it]
                                                           
{'loss': 0.634, 'learning_rate': 0.00031639523809964804, 'epoch': 5.18}

 43%|████▎     | 12131/28080 [23:58:14<31:32:17,  7.12s/it]
 43%|████▎     | 12132/28080 [23:58:21<31:37:19,  7.14s/it]
                                                           
{'loss': 0.6095, 'learning_rate': 0.00031636743748229964, 'epoch': 5.18}

 43%|████▎     | 12132/28080 [23:58:21<31:37:19,  7.14s/it]
 43%|████▎     | 12133/28080 [23:58:28<31:31:08,  7.12s/it]
                                                           
{'loss': 0.6127, 'learning_rate': 0.000316339635982001, 'epoch': 5.18}

 43%|████▎     | 12133/28080 [23:58:28<31:31:08,  7.12s/it]
 43%|████▎     | 12134/28080 [23:58:35<31:36:21,  7.14s/it]
                                                           
{'loss': 0.6065, 'learning_rate': 0.00031631183359912186, 'epoch': 5.18}

 43%|████▎     | 12134/28080 [23:58:35<31:36:21,  7.14s/it]
 43%|████▎     | 12135/28080 [23:58:42<31:34:36,  7.13s/it]
                                                           
{'loss': 0.6437, 'learning_rate': 0.00031628403033403217, 'epoch': 5.18}

 43%|████▎     | 12135/28080 [23:58:42<31:34:36,  7.13s/it]
 43%|████▎     | 12136/28080 [23:58:50<31:34:33,  7.13s/it]
                                                           
{'loss': 0.6268, 'learning_rate': 0.00031625622618710193, 'epoch': 5.18}

 43%|████▎     | 12136/28080 [23:58:50<31:34:33,  7.13s/it]
 43%|████▎     | 12137/28080 [23:58:57<31:39:23,  7.15s/it]
                                                           
{'loss': 0.6541, 'learning_rate': 0.0003162284211587009, 'epoch': 5.18}

 43%|████▎     | 12137/28080 [23:58:57<31:39:23,  7.15s/it]
 43%|████▎     | 12138/28080 [23:59:04<31:40:13,  7.15s/it]
                                                           
{'loss': 0.6221, 'learning_rate': 0.00031620061524919907, 'epoch': 5.19}

 43%|████▎     | 12138/28080 [23:59:04<31:40:13,  7.15s/it]
 43%|████▎     | 12139/28080 [23:59:11<31:38:05,  7.14s/it]
                                                           
{'loss': 0.6209, 'learning_rate': 0.0003161728084589663, 'epoch': 5.19}

 43%|████▎     | 12139/28080 [23:59:11<31:38:05,  7.14s/it]
 43%|████▎     | 12140/28080 [23:59:18<31:39:21,  7.15s/it]
                                                           
{'loss': 0.6107, 'learning_rate': 0.0003161450007883726, 'epoch': 5.19}

 43%|████▎     | 12140/28080 [23:59:18<31:39:21,  7.15s/it]
 43%|████▎     | 12141/28080 [23:59:25<31:33:52,  7.13s/it]
                                                           
{'loss': 0.616, 'learning_rate': 0.000316117192237788, 'epoch': 5.19}

 43%|████▎     | 12141/28080 [23:59:25<31:33:52,  7.13s/it]
 43%|████▎     | 12142/28080 [23:59:32<31:27:57,  7.11s/it]
                                                           
{'loss': 0.6216, 'learning_rate': 0.00031608938280758227, 'epoch': 5.19}

 43%|████▎     | 12142/28080 [23:59:32<31:27:57,  7.11s/it]
 43%|████▎     | 12143/28080 [23:59:39<31:22:10,  7.09s/it]
                                                           
{'loss': 0.6315, 'learning_rate': 0.0003160615724981255, 'epoch': 5.19}

 43%|████▎     | 12143/28080 [23:59:39<31:22:10,  7.09s/it]
 43%|████▎     | 12144/28080 [23:59:46<31:20:48,  7.08s/it]
                                                           
{'loss': 0.6033, 'learning_rate': 0.00031603376130978763, 'epoch': 5.19}

 43%|████▎     | 12144/28080 [23:59:46<31:20:48,  7.08s/it]
 43%|████▎     | 12145/28080 [23:59:54<31:26:13,  7.10s/it]
                                                           
{'loss': 0.6329, 'learning_rate': 0.0003160059492429387, 'epoch': 5.19}

 43%|████▎     | 12145/28080 [23:59:54<31:26:13,  7.10s/it]
 43%|████▎     | 12146/28080 [24:00:01<31:31:08,  7.12s/it]
                                                           
{'loss': 0.5953, 'learning_rate': 0.00031597813629794875, 'epoch': 5.19}

 43%|████▎     | 12146/28080 [24:00:01<31:31:08,  7.12s/it]
 43%|████▎     | 12147/28080 [24:00:08<31:37:19,  7.14s/it]
                                                           
{'loss': 0.6251, 'learning_rate': 0.00031595032247518773, 'epoch': 5.19}

 43%|████▎     | 12147/28080 [24:00:08<31:37:19,  7.14s/it]
 43%|████▎     | 12148/28080 [24:00:15<31:33:52,  7.13s/it]
                                                           
{'loss': 0.6335, 'learning_rate': 0.00031592250777502575, 'epoch': 5.19}

 43%|████▎     | 12148/28080 [24:00:15<31:33:52,  7.13s/it]
 43%|████▎     | 12149/28080 [24:00:22<31:36:04,  7.14s/it]
                                                           
{'loss': 0.6296, 'learning_rate': 0.00031589469219783274, 'epoch': 5.19}

 43%|████▎     | 12149/28080 [24:00:22<31:36:04,  7.14s/it]
 43%|████▎     | 12150/28080 [24:00:30<31:46:03,  7.18s/it]
                                                           
{'loss': 0.6107, 'learning_rate': 0.0003158668757439789, 'epoch': 5.19}

 43%|████▎     | 12150/28080 [24:00:30<31:46:03,  7.18s/it]
 43%|████▎     | 12151/28080 [24:00:37<31:46:17,  7.18s/it]
                                                           
{'loss': 0.6355, 'learning_rate': 0.00031583905841383415, 'epoch': 5.19}

 43%|████▎     | 12151/28080 [24:00:37<31:46:17,  7.18s/it]
 43%|████▎     | 12152/28080 [24:00:44<31:47:46,  7.19s/it]
                                                           
{'loss': 0.6179, 'learning_rate': 0.0003158112402077687, 'epoch': 5.19}

 43%|████▎     | 12152/28080 [24:00:44<31:47:46,  7.19s/it]
 43%|████▎     | 12153/28080 [24:00:51<31:48:06,  7.19s/it]
                                                           
{'loss': 0.6238, 'learning_rate': 0.0003157834211261526, 'epoch': 5.19}

 43%|████▎     | 12153/28080 [24:00:51<31:48:06,  7.19s/it]
 43%|████▎     | 12154/28080 [24:00:58<31:37:02,  7.15s/it]
                                                           
{'loss': 0.6203, 'learning_rate': 0.0003157556011693559, 'epoch': 5.19}

 43%|████▎     | 12154/28080 [24:00:58<31:37:02,  7.15s/it]
 43%|████▎     | 12155/28080 [24:01:05<31:42:38,  7.17s/it]
                                                           
{'loss': 0.6082, 'learning_rate': 0.00031572778033774887, 'epoch': 5.19}

 43%|████▎     | 12155/28080 [24:01:05<31:42:38,  7.17s/it]
 43%|████▎     | 12156/28080 [24:01:12<31:32:03,  7.13s/it]
                                                           
{'loss': 0.6409, 'learning_rate': 0.00031569995863170143, 'epoch': 5.19}

 43%|████▎     | 12156/28080 [24:01:12<31:32:03,  7.13s/it]
 43%|████▎     | 12157/28080 [24:01:20<31:33:47,  7.14s/it]
                                                           
{'loss': 0.6276, 'learning_rate': 0.00031567213605158387, 'epoch': 5.19}

 43%|████▎     | 12157/28080 [24:01:20<31:33:47,  7.14s/it]
 43%|████▎     | 12158/28080 [24:01:27<31:34:41,  7.14s/it]
                                                           
{'loss': 0.6173, 'learning_rate': 0.0003156443125977662, 'epoch': 5.19}

 43%|████▎     | 12158/28080 [24:01:27<31:34:41,  7.14s/it]
 43%|████▎     | 12159/28080 [24:01:34<31:35:48,  7.14s/it]
                                                           
{'loss': 0.6192, 'learning_rate': 0.0003156164882706187, 'epoch': 5.19}

 43%|████▎     | 12159/28080 [24:01:34<31:35:48,  7.14s/it]
 43%|████▎     | 12160/28080 [24:01:41<31:32:48,  7.13s/it]
                                                           
{'loss': 0.6138, 'learning_rate': 0.0003155886630705116, 'epoch': 5.19}

 43%|████▎     | 12160/28080 [24:01:41<31:32:48,  7.13s/it]
 43%|████▎     | 12161/28080 [24:01:48<31:44:57,  7.18s/it]
                                                           
{'loss': 0.6318, 'learning_rate': 0.00031556083699781496, 'epoch': 5.2}

 43%|████▎     | 12161/28080 [24:01:48<31:44:57,  7.18s/it]
 43%|████▎     | 12162/28080 [24:01:55<31:38:57,  7.16s/it]
                                                           
{'loss': 0.6296, 'learning_rate': 0.00031553301005289905, 'epoch': 5.2}

 43%|████▎     | 12162/28080 [24:01:55<31:38:57,  7.16s/it]
 43%|████▎     | 12163/28080 [24:02:02<31:34:24,  7.14s/it]
                                                           
{'loss': 0.6197, 'learning_rate': 0.000315505182236134, 'epoch': 5.2}

 43%|████▎     | 12163/28080 [24:02:02<31:34:24,  7.14s/it]
 43%|████▎     | 12164/28080 [24:02:10<31:39:47,  7.16s/it]
                                                           
{'loss': 0.6063, 'learning_rate': 0.00031547735354789006, 'epoch': 5.2}

 43%|████▎     | 12164/28080 [24:02:10<31:39:47,  7.16s/it]
 43%|████▎     | 12165/28080 [24:02:17<31:41:19,  7.17s/it]
                                                           
{'loss': 0.6238, 'learning_rate': 0.0003154495239885376, 'epoch': 5.2}

 43%|████▎     | 12165/28080 [24:02:17<31:41:19,  7.17s/it]
 43%|████▎     | 12166/28080 [24:02:24<31:41:05,  7.17s/it]
                                                           
{'loss': 0.6158, 'learning_rate': 0.00031542169355844665, 'epoch': 5.2}

 43%|████▎     | 12166/28080 [24:02:24<31:41:05,  7.17s/it]
 43%|████▎     | 12167/28080 [24:02:31<31:37:58,  7.16s/it]
                                                           
{'loss': 0.594, 'learning_rate': 0.00031539386225798763, 'epoch': 5.2}

 43%|████▎     | 12167/28080 [24:02:31<31:37:58,  7.16s/it]
 43%|████▎     | 12168/28080 [24:02:38<31:37:43,  7.16s/it]
                                                           
{'loss': 0.6346, 'learning_rate': 0.00031536603008753064, 'epoch': 5.2}

 43%|████▎     | 12168/28080 [24:02:38<31:37:43,  7.16s/it]
 43%|████▎     | 12169/28080 [24:02:45<31:31:38,  7.13s/it]
                                                           
{'loss': 0.6374, 'learning_rate': 0.00031533819704744604, 'epoch': 5.2}

 43%|████▎     | 12169/28080 [24:02:45<31:31:38,  7.13s/it]
 43%|████▎     | 12170/28080 [24:02:53<31:33:12,  7.14s/it]
                                                           
{'loss': 0.6162, 'learning_rate': 0.0003153103631381042, 'epoch': 5.2}

 43%|████▎     | 12170/28080 [24:02:53<31:33:12,  7.14s/it]
 43%|████▎     | 12171/28080 [24:03:00<31:34:12,  7.14s/it]
                                                           
{'loss': 0.6193, 'learning_rate': 0.0003152825283598753, 'epoch': 5.2}

 43%|████▎     | 12171/28080 [24:03:00<31:34:12,  7.14s/it]
 43%|████▎     | 12172/28080 [24:03:07<31:34:01,  7.14s/it]
                                                           
{'loss': 0.6353, 'learning_rate': 0.0003152546927131298, 'epoch': 5.2}

 43%|████▎     | 12172/28080 [24:03:07<31:34:01,  7.14s/it]
 43%|████▎     | 12173/28080 [24:03:14<31:36:41,  7.15s/it]
                                                           
{'loss': 0.6322, 'learning_rate': 0.00031522685619823784, 'epoch': 5.2}

 43%|████▎     | 12173/28080 [24:03:14<31:36:41,  7.15s/it]
 43%|████▎     | 12174/28080 [24:03:21<31:23:42,  7.11s/it]
                                                           
{'loss': 0.6209, 'learning_rate': 0.00031519901881556987, 'epoch': 5.2}

 43%|████▎     | 12174/28080 [24:03:21<31:23:42,  7.11s/it]
 43%|████▎     | 12175/28080 [24:03:28<31:22:23,  7.10s/it]
                                                           
{'loss': 0.6197, 'learning_rate': 0.00031517118056549625, 'epoch': 5.2}

 43%|████▎     | 12175/28080 [24:03:28<31:22:23,  7.10s/it]
 43%|████▎     | 12176/28080 [24:03:35<31:19:27,  7.09s/it]
                                                           
{'loss': 0.6192, 'learning_rate': 0.0003151433414483873, 'epoch': 5.2}

 43%|████▎     | 12176/28080 [24:03:35<31:19:27,  7.09s/it]
 43%|████▎     | 12177/28080 [24:03:42<31:15:48,  7.08s/it]
                                                           
{'loss': 0.6316, 'learning_rate': 0.00031511550146461336, 'epoch': 5.2}

 43%|████▎     | 12177/28080 [24:03:42<31:15:48,  7.08s/it]
 43%|████▎     | 12178/28080 [24:03:49<31:23:29,  7.11s/it]
                                                           
{'loss': 0.6012, 'learning_rate': 0.00031508766061454487, 'epoch': 5.2}

 43%|████▎     | 12178/28080 [24:03:49<31:23:29,  7.11s/it]
 43%|████▎     | 12179/28080 [24:03:56<31:16:26,  7.08s/it]
                                                           
{'loss': 0.6254, 'learning_rate': 0.00031505981889855223, 'epoch': 5.2}

 43%|████▎     | 12179/28080 [24:03:56<31:16:26,  7.08s/it]
 43%|████▎     | 12180/28080 [24:04:03<31:13:30,  7.07s/it]
                                                           
{'loss': 0.6193, 'learning_rate': 0.0003150319763170058, 'epoch': 5.2}

 43%|████▎     | 12180/28080 [24:04:03<31:13:30,  7.07s/it]
 43%|████▎     | 12181/28080 [24:04:11<31:19:13,  7.09s/it]
                                                           
{'loss': 0.6187, 'learning_rate': 0.000315004132870276, 'epoch': 5.2}

 43%|████▎     | 12181/28080 [24:04:11<31:19:13,  7.09s/it]
 43%|████▎     | 12182/28080 [24:04:18<31:32:33,  7.14s/it]
                                                           
{'loss': 0.6101, 'learning_rate': 0.0003149762885587333, 'epoch': 5.2}

 43%|████▎     | 12182/28080 [24:04:18<31:32:33,  7.14s/it]
 43%|████▎     | 12183/28080 [24:04:25<31:22:03,  7.10s/it]
                                                           
{'loss': 0.6198, 'learning_rate': 0.00031494844338274806, 'epoch': 5.2}

 43%|████▎     | 12183/28080 [24:04:25<31:22:03,  7.10s/it]
 43%|████▎     | 12184/28080 [24:04:32<31:23:46,  7.11s/it]
                                                           
{'loss': 0.6245, 'learning_rate': 0.00031492059734269083, 'epoch': 5.2}

 43%|████▎     | 12184/28080 [24:04:32<31:23:46,  7.11s/it]
 43%|████▎     | 12185/28080 [24:04:39<31:23:59,  7.11s/it]
                                                           
{'loss': 0.626, 'learning_rate': 0.000314892750438932, 'epoch': 5.21}

 43%|████▎     | 12185/28080 [24:04:39<31:23:59,  7.11s/it]
 43%|████▎     | 12186/28080 [24:04:46<31:28:54,  7.13s/it]
                                                           
{'loss': 0.6298, 'learning_rate': 0.00031486490267184215, 'epoch': 5.21}

 43%|████▎     | 12186/28080 [24:04:46<31:28:54,  7.13s/it]
 43%|████▎     | 12187/28080 [24:04:53<31:31:59,  7.14s/it]
                                                           
{'loss': 0.6276, 'learning_rate': 0.0003148370540417916, 'epoch': 5.21}

 43%|████▎     | 12187/28080 [24:04:53<31:31:59,  7.14s/it]
 43%|████▎     | 12188/28080 [24:05:01<31:38:22,  7.17s/it]
                                                           
{'loss': 0.6233, 'learning_rate': 0.000314809204549151, 'epoch': 5.21}

 43%|████▎     | 12188/28080 [24:05:01<31:38:22,  7.17s/it]
 43%|████▎     | 12189/28080 [24:05:08<31:31:25,  7.14s/it]
                                                           
{'loss': 0.638, 'learning_rate': 0.00031478135419429074, 'epoch': 5.21}

 43%|████▎     | 12189/28080 [24:05:08<31:31:25,  7.14s/it]
 43%|████▎     | 12190/28080 [24:05:15<31:28:09,  7.13s/it]
                                                           
{'loss': 0.6254, 'learning_rate': 0.00031475350297758143, 'epoch': 5.21}

 43%|████▎     | 12190/28080 [24:05:15<31:28:09,  7.13s/it]
 43%|████▎     | 12191/28080 [24:05:22<31:28:52,  7.13s/it]
                                                           
{'loss': 0.6362, 'learning_rate': 0.00031472565089939354, 'epoch': 5.21}

 43%|████▎     | 12191/28080 [24:05:22<31:28:52,  7.13s/it]
 43%|████▎     | 12192/28080 [24:05:29<31:27:29,  7.13s/it]
                                                           
{'loss': 0.6294, 'learning_rate': 0.00031469779796009764, 'epoch': 5.21}

 43%|████▎     | 12192/28080 [24:05:29<31:27:29,  7.13s/it]
 43%|████▎     | 12193/28080 [24:05:36<31:25:47,  7.12s/it]
                                                           
{'loss': 0.6321, 'learning_rate': 0.00031466994416006426, 'epoch': 5.21}

 43%|████▎     | 12193/28080 [24:05:36<31:25:47,  7.12s/it]
 43%|████▎     | 12194/28080 [24:05:43<31:22:11,  7.11s/it]
                                                           
{'loss': 0.649, 'learning_rate': 0.00031464208949966404, 'epoch': 5.21}

 43%|████▎     | 12194/28080 [24:05:43<31:22:11,  7.11s/it]
 43%|████▎     | 12195/28080 [24:05:51<31:32:23,  7.15s/it]
                                                           
{'loss': 0.6355, 'learning_rate': 0.00031461423397926745, 'epoch': 5.21}

 43%|████▎     | 12195/28080 [24:05:51<31:32:23,  7.15s/it]
 43%|████▎     | 12196/28080 [24:05:58<31:27:26,  7.13s/it]
                                                           
{'loss': 0.6234, 'learning_rate': 0.0003145863775992452, 'epoch': 5.21}

 43%|████▎     | 12196/28080 [24:05:58<31:27:26,  7.13s/it]
 43%|████▎     | 12197/28080 [24:06:05<31:31:07,  7.14s/it]
                                                           
{'loss': 0.649, 'learning_rate': 0.0003145585203599678, 'epoch': 5.21}

 43%|████▎     | 12197/28080 [24:06:05<31:31:07,  7.14s/it]
 43%|████▎     | 12198/28080 [24:06:12<31:30:36,  7.14s/it]
                                                           
{'loss': 0.6482, 'learning_rate': 0.0003145306622618059, 'epoch': 5.21}

 43%|████▎     | 12198/28080 [24:06:12<31:30:36,  7.14s/it]
 43%|████▎     | 12199/28080 [24:06:19<31:31:47,  7.15s/it]
                                                           
{'loss': 0.6025, 'learning_rate': 0.00031450280330513, 'epoch': 5.21}

 43%|████▎     | 12199/28080 [24:06:19<31:31:47,  7.15s/it]
 43%|████▎     | 12200/28080 [24:06:26<31:26:01,  7.13s/it]
                                                           
{'loss': 0.6299, 'learning_rate': 0.00031447494349031097, 'epoch': 5.21}

 43%|████▎     | 12200/28080 [24:06:26<31:26:01,  7.13s/it]
 43%|████▎     | 12201/28080 [24:06:33<31:26:05,  7.13s/it]
                                                           
{'loss': 0.6223, 'learning_rate': 0.00031444708281771935, 'epoch': 5.21}

 43%|████▎     | 12201/28080 [24:06:33<31:26:05,  7.13s/it]
 43%|████▎     | 12202/28080 [24:06:40<31:24:02,  7.12s/it]
                                                           
{'loss': 0.6119, 'learning_rate': 0.0003144192212877257, 'epoch': 5.21}

 43%|████▎     | 12202/28080 [24:06:40<31:24:02,  7.12s/it]
 43%|████▎     | 12203/28080 [24:06:48<31:23:13,  7.12s/it]
                                                           
{'loss': 0.6267, 'learning_rate': 0.0003143913589007008, 'epoch': 5.21}

 43%|████▎     | 12203/28080 [24:06:48<31:23:13,  7.12s/it]
 43%|████▎     | 12204/28080 [24:06:55<31:24:30,  7.12s/it]
                                                           
{'loss': 0.6324, 'learning_rate': 0.0003143634956570153, 'epoch': 5.21}

 43%|████▎     | 12204/28080 [24:06:55<31:24:30,  7.12s/it]
 43%|████▎     | 12205/28080 [24:07:02<31:15:07,  7.09s/it]
                                                           
{'loss': 0.6205, 'learning_rate': 0.0003143356315570399, 'epoch': 5.21}

 43%|████▎     | 12205/28080 [24:07:02<31:15:07,  7.09s/it]
 43%|████▎     | 12206/28080 [24:07:09<31:21:08,  7.11s/it]
                                                           
{'loss': 0.6208, 'learning_rate': 0.0003143077666011453, 'epoch': 5.21}

 43%|████▎     | 12206/28080 [24:07:09<31:21:08,  7.11s/it]
 43%|████▎     | 12207/28080 [24:07:16<31:27:28,  7.13s/it]
                                                           
{'loss': 0.6106, 'learning_rate': 0.00031427990078970215, 'epoch': 5.21}

 43%|████▎     | 12207/28080 [24:07:16<31:27:28,  7.13s/it]
 43%|████▎     | 12208/28080 [24:07:23<31:25:26,  7.13s/it]
                                                           
{'loss': 0.6199, 'learning_rate': 0.0003142520341230813, 'epoch': 5.22}

 43%|████▎     | 12208/28080 [24:07:23<31:25:26,  7.13s/it]
 43%|████▎     | 12209/28080 [24:07:30<31:26:05,  7.13s/it]
                                                           
{'loss': 0.6051, 'learning_rate': 0.00031422416660165336, 'epoch': 5.22}

 43%|████▎     | 12209/28080 [24:07:30<31:26:05,  7.13s/it]
 43%|████▎     | 12210/28080 [24:07:37<31:23:30,  7.12s/it]
                                                           
{'loss': 0.6302, 'learning_rate': 0.0003141962982257892, 'epoch': 5.22}

 43%|████▎     | 12210/28080 [24:07:37<31:23:30,  7.12s/it]
 43%|████▎     | 12211/28080 [24:07:45<31:31:56,  7.15s/it]
                                                           
{'loss': 0.6113, 'learning_rate': 0.00031416842899585954, 'epoch': 5.22}

 43%|████▎     | 12211/28080 [24:07:45<31:31:56,  7.15s/it]
 43%|████▎     | 12212/28080 [24:07:52<31:37:23,  7.17s/it]
                                                           
{'loss': 0.614, 'learning_rate': 0.00031414055891223504, 'epoch': 5.22}

 43%|████▎     | 12212/28080 [24:07:52<31:37:23,  7.17s/it]
 43%|████▎     | 12213/28080 [24:07:59<31:31:09,  7.15s/it]
                                                           
{'loss': 0.6213, 'learning_rate': 0.00031411268797528657, 'epoch': 5.22}

 43%|████▎     | 12213/28080 [24:07:59<31:31:09,  7.15s/it]
 43%|████▎     | 12214/28080 [24:08:06<31:31:33,  7.15s/it]
                                                           
{'loss': 0.6214, 'learning_rate': 0.00031408481618538497, 'epoch': 5.22}

 43%|████▎     | 12214/28080 [24:08:06<31:31:33,  7.15s/it]
 44%|████▎     | 12215/28080 [24:08:13<31:28:33,  7.14s/it]
                                                           
{'loss': 0.6011, 'learning_rate': 0.00031405694354290115, 'epoch': 5.22}

 44%|████▎     | 12215/28080 [24:08:13<31:28:33,  7.14s/it]
 44%|████▎     | 12216/28080 [24:08:20<31:32:26,  7.16s/it]
                                                           
{'loss': 0.6153, 'learning_rate': 0.0003140290700482056, 'epoch': 5.22}

 44%|████▎     | 12216/28080 [24:08:20<31:32:26,  7.16s/it]
 44%|████▎     | 12217/28080 [24:08:28<31:38:00,  7.18s/it]
                                                           
{'loss': 0.6197, 'learning_rate': 0.0003140011957016693, 'epoch': 5.22}

 44%|████▎     | 12217/28080 [24:08:28<31:38:00,  7.18s/it]
 44%|████▎     | 12218/28080 [24:08:35<31:27:46,  7.14s/it]
                                                           
{'loss': 0.6098, 'learning_rate': 0.0003139733205036632, 'epoch': 5.22}

 44%|████▎     | 12218/28080 [24:08:35<31:27:46,  7.14s/it]
 44%|████▎     | 12219/28080 [24:08:42<31:23:59,  7.13s/it]
                                                           
{'loss': 0.6272, 'learning_rate': 0.0003139454444545581, 'epoch': 5.22}

 44%|████▎     | 12219/28080 [24:08:42<31:23:59,  7.13s/it]
 44%|████▎     | 12220/28080 [24:08:49<31:21:32,  7.12s/it]
                                                           
{'loss': 0.6165, 'learning_rate': 0.00031391756755472477, 'epoch': 5.22}

 44%|████▎     | 12220/28080 [24:08:49<31:21:32,  7.12s/it]
 44%|████▎     | 12221/28080 [24:08:56<31:12:01,  7.08s/it]
                                                           
{'loss': 0.6285, 'learning_rate': 0.00031388968980453416, 'epoch': 5.22}

 44%|████▎     | 12221/28080 [24:08:56<31:12:01,  7.08s/it]
 44%|████▎     | 12222/28080 [24:09:03<31:07:07,  7.06s/it]
                                                           
{'loss': 0.6299, 'learning_rate': 0.0003138618112043572, 'epoch': 5.22}

 44%|████▎     | 12222/28080 [24:09:03<31:07:07,  7.06s/it]
 44%|████▎     | 12223/28080 [24:09:10<31:09:05,  7.07s/it]
                                                           
{'loss': 0.6138, 'learning_rate': 0.0003138339317545646, 'epoch': 5.22}

 44%|████▎     | 12223/28080 [24:09:10<31:09:05,  7.07s/it]
 44%|████▎     | 12224/28080 [24:09:17<31:12:31,  7.09s/it]
                                                           
{'loss': 0.6249, 'learning_rate': 0.0003138060514555274, 'epoch': 5.22}

 44%|████▎     | 12224/28080 [24:09:17<31:12:31,  7.09s/it]
 44%|████▎     | 12225/28080 [24:09:24<31:11:55,  7.08s/it]
                                                           
{'loss': 0.6167, 'learning_rate': 0.0003137781703076166, 'epoch': 5.22}

 44%|████▎     | 12225/28080 [24:09:24<31:11:55,  7.08s/it]
 44%|████▎     | 12226/28080 [24:09:31<31:15:43,  7.10s/it]
                                                           
{'loss': 0.611, 'learning_rate': 0.000313750288311203, 'epoch': 5.22}

 44%|████▎     | 12226/28080 [24:09:31<31:15:43,  7.10s/it]
 44%|████▎     | 12227/28080 [24:09:38<31:16:35,  7.10s/it]
                                                           
{'loss': 0.6312, 'learning_rate': 0.00031372240546665765, 'epoch': 5.22}

 44%|████▎     | 12227/28080 [24:09:38<31:16:35,  7.10s/it]
 44%|████▎     | 12228/28080 [24:09:46<31:19:54,  7.12s/it]
                                                           
{'loss': 0.6225, 'learning_rate': 0.0003136945217743513, 'epoch': 5.22}

 44%|████▎     | 12228/28080 [24:09:46<31:19:54,  7.12s/it]
 44%|████▎     | 12229/28080 [24:09:53<31:20:56,  7.12s/it]
                                                           
{'loss': 0.6455, 'learning_rate': 0.00031366663723465517, 'epoch': 5.22}

 44%|████▎     | 12229/28080 [24:09:53<31:20:56,  7.12s/it]
 44%|████▎     | 12230/28080 [24:10:00<31:19:54,  7.12s/it]
                                                           
{'loss': 0.6191, 'learning_rate': 0.00031363875184794, 'epoch': 5.22}

 44%|████▎     | 12230/28080 [24:10:00<31:19:54,  7.12s/it]
 44%|████▎     | 12231/28080 [24:10:07<31:17:49,  7.11s/it]
                                                           
{'loss': 0.6338, 'learning_rate': 0.00031361086561457695, 'epoch': 5.22}

 44%|████▎     | 12231/28080 [24:10:07<31:17:49,  7.11s/it]
 44%|████▎     | 12232/28080 [24:10:14<31:20:20,  7.12s/it]
                                                           
{'loss': 0.6243, 'learning_rate': 0.000313582978534937, 'epoch': 5.23}

 44%|████▎     | 12232/28080 [24:10:14<31:20:20,  7.12s/it]
 44%|████▎     | 12233/28080 [24:10:21<31:20:21,  7.12s/it]
                                                           
{'loss': 0.6259, 'learning_rate': 0.000313555090609391, 'epoch': 5.23}

 44%|████▎     | 12233/28080 [24:10:21<31:20:21,  7.12s/it]
 44%|████▎     | 12234/28080 [24:10:28<31:21:24,  7.12s/it]
                                                           
{'loss': 0.6359, 'learning_rate': 0.00031352720183831025, 'epoch': 5.23}

 44%|████▎     | 12234/28080 [24:10:28<31:21:24,  7.12s/it]
 44%|████▎     | 12235/28080 [24:10:35<31:23:59,  7.13s/it]
                                                           
{'loss': 0.6238, 'learning_rate': 0.00031349931222206544, 'epoch': 5.23}

 44%|████▎     | 12235/28080 [24:10:35<31:23:59,  7.13s/it]
 44%|████▎     | 12236/28080 [24:10:43<31:23:41,  7.13s/it]
                                                           
{'loss': 0.6214, 'learning_rate': 0.00031347142176102797, 'epoch': 5.23}

 44%|████▎     | 12236/28080 [24:10:43<31:23:41,  7.13s/it]
 44%|████▎     | 12237/28080 [24:10:50<31:14:34,  7.10s/it]
                                                           
{'loss': 0.6218, 'learning_rate': 0.0003134435304555686, 'epoch': 5.23}

 44%|████▎     | 12237/28080 [24:10:50<31:14:34,  7.10s/it]
 44%|████▎     | 12238/28080 [24:10:57<31:14:07,  7.10s/it]
                                                           
{'loss': 0.6433, 'learning_rate': 0.00031341563830605845, 'epoch': 5.23}

 44%|████▎     | 12238/28080 [24:10:57<31:14:07,  7.10s/it]
 44%|████▎     | 12239/28080 [24:11:04<31:22:10,  7.13s/it]
                                                           
{'loss': 0.6112, 'learning_rate': 0.00031338774531286875, 'epoch': 5.23}

 44%|████▎     | 12239/28080 [24:11:04<31:22:10,  7.13s/it]
 44%|████▎     | 12240/28080 [24:11:11<31:17:26,  7.11s/it]
                                                           
{'loss': 0.6234, 'learning_rate': 0.0003133598514763705, 'epoch': 5.23}

 44%|████▎     | 12240/28080 [24:11:11<31:17:26,  7.11s/it]
 44%|████▎     | 12241/28080 [24:11:18<31:21:36,  7.13s/it]
                                                           
{'loss': 0.6067, 'learning_rate': 0.0003133319567969348, 'epoch': 5.23}

 44%|████▎     | 12241/28080 [24:11:18<31:21:36,  7.13s/it]
 44%|████▎     | 12242/28080 [24:11:25<31:20:58,  7.13s/it]
                                                           
{'loss': 0.6165, 'learning_rate': 0.0003133040612749327, 'epoch': 5.23}

 44%|████▎     | 12242/28080 [24:11:25<31:20:58,  7.13s/it]
 44%|████▎     | 12243/28080 [24:11:32<31:08:52,  7.08s/it]
                                                           
{'loss': 0.6148, 'learning_rate': 0.0003132761649107354, 'epoch': 5.23}

 44%|████▎     | 12243/28080 [24:11:32<31:08:52,  7.08s/it]
 44%|████▎     | 12244/28080 [24:11:39<31:07:35,  7.08s/it]
                                                           
{'loss': 0.6206, 'learning_rate': 0.000313248267704714, 'epoch': 5.23}

 44%|████▎     | 12244/28080 [24:11:39<31:07:35,  7.08s/it]
 44%|████▎     | 12245/28080 [24:11:46<31:09:28,  7.08s/it]
                                                           
{'loss': 0.6243, 'learning_rate': 0.0003132203696572396, 'epoch': 5.23}

 44%|████▎     | 12245/28080 [24:11:46<31:09:28,  7.08s/it]
 44%|████▎     | 12246/28080 [24:11:54<31:18:46,  7.12s/it]
                                                           
{'loss': 0.6083, 'learning_rate': 0.0003131924707686835, 'epoch': 5.23}

 44%|████▎     | 12246/28080 [24:11:54<31:18:46,  7.12s/it]
 44%|████▎     | 12247/28080 [24:12:01<31:23:41,  7.14s/it]
                                                           
{'loss': 0.6019, 'learning_rate': 0.00031316457103941665, 'epoch': 5.23}

 44%|████▎     | 12247/28080 [24:12:01<31:23:41,  7.14s/it]
 44%|████▎     | 12248/28080 [24:12:08<31:12:56,  7.10s/it]
                                                           
{'loss': 0.6121, 'learning_rate': 0.00031313667046981036, 'epoch': 5.23}

 44%|████▎     | 12248/28080 [24:12:08<31:12:56,  7.10s/it]
 44%|████▎     | 12249/28080 [24:12:15<31:06:04,  7.07s/it]
                                                           
{'loss': 0.6559, 'learning_rate': 0.0003131087690602359, 'epoch': 5.23}

 44%|████▎     | 12249/28080 [24:12:15<31:06:04,  7.07s/it]
 44%|████▎     | 12250/28080 [24:12:22<31:20:44,  7.13s/it]
                                                           
{'loss': 0.606, 'learning_rate': 0.0003130808668110643, 'epoch': 5.23}

 44%|████▎     | 12250/28080 [24:12:22<31:20:44,  7.13s/it]
 44%|████▎     | 12251/28080 [24:12:29<31:17:22,  7.12s/it]
                                                           
{'loss': 0.6282, 'learning_rate': 0.0003130529637226669, 'epoch': 5.23}

 44%|████▎     | 12251/28080 [24:12:29<31:17:22,  7.12s/it]
 44%|████▎     | 12252/28080 [24:12:36<31:12:30,  7.10s/it]
                                                           
{'loss': 0.6137, 'learning_rate': 0.0003130250597954148, 'epoch': 5.23}

 44%|████▎     | 12252/28080 [24:12:36<31:12:30,  7.10s/it]
 44%|████▎     | 12253/28080 [24:12:43<31:11:43,  7.10s/it]
                                                           
{'loss': 0.6259, 'learning_rate': 0.00031299715502967933, 'epoch': 5.23}

 44%|████▎     | 12253/28080 [24:12:43<31:11:43,  7.10s/it]
 44%|████▎     | 12254/28080 [24:12:50<31:08:54,  7.09s/it]
                                                           
{'loss': 0.6123, 'learning_rate': 0.00031296924942583173, 'epoch': 5.23}

 44%|████▎     | 12254/28080 [24:12:50<31:08:54,  7.09s/it]
 44%|████▎     | 12255/28080 [24:12:57<31:12:31,  7.10s/it]
                                                           
{'loss': 0.6266, 'learning_rate': 0.0003129413429842431, 'epoch': 5.24}

 44%|████▎     | 12255/28080 [24:12:57<31:12:31,  7.10s/it]
 44%|████▎     | 12256/28080 [24:13:05<31:09:06,  7.09s/it]
                                                           
{'loss': 0.6635, 'learning_rate': 0.000312913435705285, 'epoch': 5.24}

 44%|████▎     | 12256/28080 [24:13:05<31:09:06,  7.09s/it]
 44%|████▎     | 12257/28080 [24:13:12<31:07:40,  7.08s/it]
                                                           
{'loss': 0.62, 'learning_rate': 0.0003128855275893285, 'epoch': 5.24}

 44%|████▎     | 12257/28080 [24:13:12<31:07:40,  7.08s/it]
 44%|████▎     | 12258/28080 [24:13:19<31:03:35,  7.07s/it]
                                                           
{'loss': 0.6327, 'learning_rate': 0.0003128576186367449, 'epoch': 5.24}

 44%|████▎     | 12258/28080 [24:13:19<31:03:35,  7.07s/it]
 44%|████▎     | 12259/28080 [24:13:26<31:02:36,  7.06s/it]
                                                           
{'loss': 0.6408, 'learning_rate': 0.00031282970884790554, 'epoch': 5.24}

 44%|████▎     | 12259/28080 [24:13:26<31:02:36,  7.06s/it]
 44%|████▎     | 12260/28080 [24:13:33<31:15:50,  7.11s/it]
                                                           
{'loss': 0.6328, 'learning_rate': 0.0003128017982231817, 'epoch': 5.24}

 44%|████▎     | 12260/28080 [24:13:33<31:15:50,  7.11s/it]
 44%|████▎     | 12261/28080 [24:13:40<31:16:02,  7.12s/it]
                                                           
{'loss': 0.6309, 'learning_rate': 0.0003127738867629448, 'epoch': 5.24}

 44%|████▎     | 12261/28080 [24:13:40<31:16:02,  7.12s/it]
 44%|████▎     | 12262/28080 [24:13:47<31:15:42,  7.11s/it]
                                                           
{'loss': 0.62, 'learning_rate': 0.00031274597446756595, 'epoch': 5.24}

 44%|████▎     | 12262/28080 [24:13:47<31:15:42,  7.11s/it]
 44%|████▎     | 12263/28080 [24:13:54<31:14:31,  7.11s/it]
                                                           
{'loss': 0.6156, 'learning_rate': 0.0003127180613374168, 'epoch': 5.24}

 44%|████▎     | 12263/28080 [24:13:54<31:14:31,  7.11s/it]
 44%|████▎     | 12264/28080 [24:14:01<31:14:41,  7.11s/it]
                                                           
{'loss': 0.6369, 'learning_rate': 0.00031269014737286843, 'epoch': 5.24}

 44%|████▎     | 12264/28080 [24:14:01<31:14:41,  7.11s/it]
 44%|████▎     | 12265/28080 [24:14:09<31:20:51,  7.14s/it]
                                                           
{'loss': 0.628, 'learning_rate': 0.0003126622325742924, 'epoch': 5.24}

 44%|████▎     | 12265/28080 [24:14:09<31:20:51,  7.14s/it]
 44%|████▎     | 12266/28080 [24:14:16<31:27:26,  7.16s/it]
                                                           
{'loss': 0.6047, 'learning_rate': 0.00031263431694206, 'epoch': 5.24}

 44%|████▎     | 12266/28080 [24:14:16<31:27:26,  7.16s/it]
 44%|████▎     | 12267/28080 [24:14:23<31:23:56,  7.15s/it]
                                                           
{'loss': 0.6187, 'learning_rate': 0.0003126064004765426, 'epoch': 5.24}

 44%|████▎     | 12267/28080 [24:14:23<31:23:56,  7.15s/it]
 44%|████▎     | 12268/28080 [24:14:30<31:18:29,  7.13s/it]
                                                           
{'loss': 0.6223, 'learning_rate': 0.00031257848317811166, 'epoch': 5.24}

 44%|████▎     | 12268/28080 [24:14:30<31:18:29,  7.13s/it]
 44%|████▎     | 12269/28080 [24:14:37<31:23:10,  7.15s/it]
                                                           
{'loss': 0.5993, 'learning_rate': 0.0003125505650471385, 'epoch': 5.24}

 44%|████▎     | 12269/28080 [24:14:37<31:23:10,  7.15s/it]
 44%|████▎     | 12270/28080 [24:14:44<31:20:22,  7.14s/it]
                                                           
{'loss': 0.6229, 'learning_rate': 0.0003125226460839947, 'epoch': 5.24}

 44%|████▎     | 12270/28080 [24:14:44<31:20:22,  7.14s/it]
 44%|████▎     | 12271/28080 [24:14:51<31:18:38,  7.13s/it]
                                                           
{'loss': 0.6249, 'learning_rate': 0.0003124947262890515, 'epoch': 5.24}

 44%|████▎     | 12271/28080 [24:14:51<31:18:38,  7.13s/it]
 44%|████▎     | 12272/28080 [24:14:58<31:14:42,  7.12s/it]
                                                           
{'loss': 0.6234, 'learning_rate': 0.00031246680566268046, 'epoch': 5.24}

 44%|████▎     | 12272/28080 [24:14:58<31:14:42,  7.12s/it]
 44%|████▎     | 12273/28080 [24:15:06<31:21:34,  7.14s/it]
                                                           
{'loss': 0.6442, 'learning_rate': 0.0003124388842052531, 'epoch': 5.24}

 44%|████▎     | 12273/28080 [24:15:06<31:21:34,  7.14s/it]
 44%|████▎     | 12274/28080 [24:15:13<31:22:55,  7.15s/it]
                                                           
{'loss': 0.6051, 'learning_rate': 0.00031241096191714067, 'epoch': 5.24}

 44%|████▎     | 12274/28080 [24:15:13<31:22:55,  7.15s/it]
 44%|████▎     | 12275/28080 [24:15:20<31:30:10,  7.18s/it]
                                                           
{'loss': 0.6227, 'learning_rate': 0.0003123830387987149, 'epoch': 5.24}

 44%|████▎     | 12275/28080 [24:15:20<31:30:10,  7.18s/it]
 44%|████▎     | 12276/28080 [24:15:27<31:28:17,  7.17s/it]
                                                           
{'loss': 0.6326, 'learning_rate': 0.00031235511485034706, 'epoch': 5.24}

 44%|████▎     | 12276/28080 [24:15:27<31:28:17,  7.17s/it]
 44%|████▎     | 12277/28080 [24:15:34<31:19:56,  7.14s/it]
                                                           
{'loss': 0.6295, 'learning_rate': 0.00031232719007240876, 'epoch': 5.24}

 44%|████▎     | 12277/28080 [24:15:34<31:19:56,  7.14s/it]
 44%|████▎     | 12278/28080 [24:15:41<31:23:42,  7.15s/it]
                                                           
{'loss': 0.6523, 'learning_rate': 0.0003122992644652715, 'epoch': 5.25}

 44%|████▎     | 12278/28080 [24:15:41<31:23:42,  7.15s/it]
 44%|████▎     | 12279/28080 [24:15:49<31:23:39,  7.15s/it]
                                                           
{'loss': 0.6068, 'learning_rate': 0.0003122713380293068, 'epoch': 5.25}

 44%|████▎     | 12279/28080 [24:15:49<31:23:39,  7.15s/it]
 44%|████▎     | 12280/28080 [24:15:56<31:19:28,  7.14s/it]
                                                           
{'loss': 0.6318, 'learning_rate': 0.00031224341076488627, 'epoch': 5.25}

 44%|████▎     | 12280/28080 [24:15:56<31:19:28,  7.14s/it]
 44%|████▎     | 12281/28080 [24:16:03<31:17:02,  7.13s/it]
                                                           
{'loss': 0.6237, 'learning_rate': 0.00031221548267238125, 'epoch': 5.25}

 44%|████▎     | 12281/28080 [24:16:03<31:17:02,  7.13s/it]
 44%|████▎     | 12282/28080 [24:16:10<31:29:16,  7.18s/it]
                                                           
{'loss': 0.6137, 'learning_rate': 0.0003121875537521635, 'epoch': 5.25}

 44%|████▎     | 12282/28080 [24:16:10<31:29:16,  7.18s/it]
 44%|████▎     | 12283/28080 [24:16:17<31:24:32,  7.16s/it]
                                                           
{'loss': 0.6215, 'learning_rate': 0.00031215962400460445, 'epoch': 5.25}

 44%|████▎     | 12283/28080 [24:16:17<31:24:32,  7.16s/it]
 44%|████▎     | 12284/28080 [24:16:24<31:20:48,  7.14s/it]
                                                           
{'loss': 0.6206, 'learning_rate': 0.0003121316934300758, 'epoch': 5.25}

 44%|████▎     | 12284/28080 [24:16:24<31:20:48,  7.14s/it]
 44%|████▍     | 12285/28080 [24:16:32<31:20:56,  7.15s/it]
                                                           
{'loss': 0.6244, 'learning_rate': 0.000312103762028949, 'epoch': 5.25}

 44%|████▍     | 12285/28080 [24:16:32<31:20:56,  7.15s/it]
 44%|████▍     | 12286/28080 [24:16:39<31:19:51,  7.14s/it]
                                                           
{'loss': 0.6035, 'learning_rate': 0.0003120758298015957, 'epoch': 5.25}

 44%|████▍     | 12286/28080 [24:16:39<31:19:51,  7.14s/it]
 44%|████▍     | 12287/28080 [24:16:46<31:19:16,  7.14s/it]
                                                           
{'loss': 0.6199, 'learning_rate': 0.0003120478967483876, 'epoch': 5.25}

 44%|████▍     | 12287/28080 [24:16:46<31:19:16,  7.14s/it]
 44%|████▍     | 12288/28080 [24:16:53<31:10:45,  7.11s/it]
                                                           
{'loss': 0.6553, 'learning_rate': 0.00031201996286969616, 'epoch': 5.25}

 44%|████▍     | 12288/28080 [24:16:53<31:10:45,  7.11s/it]
 44%|████▍     | 12289/28080 [24:17:00<31:05:23,  7.09s/it]
                                                           
{'loss': 0.6295, 'learning_rate': 0.00031199202816589315, 'epoch': 5.25}

 44%|████▍     | 12289/28080 [24:17:00<31:05:23,  7.09s/it]
 44%|████▍     | 12290/28080 [24:17:07<31:13:14,  7.12s/it]
                                                           
{'loss': 0.6503, 'learning_rate': 0.0003119640926373502, 'epoch': 5.25}

 44%|████▍     | 12290/28080 [24:17:07<31:13:14,  7.12s/it]
 44%|████▍     | 12291/28080 [24:17:14<31:14:05,  7.12s/it]
                                                           
{'loss': 0.6112, 'learning_rate': 0.00031193615628443886, 'epoch': 5.25}

 44%|████▍     | 12291/28080 [24:17:14<31:14:05,  7.12s/it]
 44%|████▍     | 12292/28080 [24:17:21<31:17:11,  7.13s/it]
                                                           
{'loss': 0.6136, 'learning_rate': 0.00031190821910753085, 'epoch': 5.25}

 44%|████▍     | 12292/28080 [24:17:21<31:17:11,  7.13s/it]
 44%|████▍     | 12293/28080 [24:17:28<31:15:39,  7.13s/it]
                                                           
{'loss': 0.6097, 'learning_rate': 0.0003118802811069979, 'epoch': 5.25}

 44%|████▍     | 12293/28080 [24:17:28<31:15:39,  7.13s/it]
 44%|████▍     | 12294/28080 [24:17:36<31:20:33,  7.15s/it]
                                                           
{'loss': 0.6125, 'learning_rate': 0.00031185234228321164, 'epoch': 5.25}

 44%|████▍     | 12294/28080 [24:17:36<31:20:33,  7.15s/it]
 44%|████▍     | 12295/28080 [24:17:43<31:14:09,  7.12s/it]
                                                           
{'loss': 0.6133, 'learning_rate': 0.0003118244026365437, 'epoch': 5.25}

 44%|████▍     | 12295/28080 [24:17:43<31:14:09,  7.12s/it]
 44%|████▍     | 12296/28080 [24:17:50<31:11:29,  7.11s/it]
                                                           
{'loss': 0.6343, 'learning_rate': 0.0003117964621673659, 'epoch': 5.25}

 44%|████▍     | 12296/28080 [24:17:50<31:11:29,  7.11s/it]
 44%|████▍     | 12297/28080 [24:17:57<31:09:38,  7.11s/it]
                                                           
{'loss': 0.627, 'learning_rate': 0.00031176852087604995, 'epoch': 5.25}

 44%|████▍     | 12297/28080 [24:17:57<31:09:38,  7.11s/it]
 44%|████▍     | 12298/28080 [24:18:04<31:04:12,  7.09s/it]
                                                           
{'loss': 0.6322, 'learning_rate': 0.0003117405787629676, 'epoch': 5.25}

 44%|████▍     | 12298/28080 [24:18:04<31:04:12,  7.09s/it]
 44%|████▍     | 12299/28080 [24:18:11<31:06:59,  7.10s/it]
                                                           
{'loss': 0.6315, 'learning_rate': 0.00031171263582849046, 'epoch': 5.25}

 44%|████▍     | 12299/28080 [24:18:11<31:06:59,  7.10s/it]
 44%|████▍     | 12300/28080 [24:18:18<31:14:13,  7.13s/it]
                                                           
{'loss': 0.6125, 'learning_rate': 0.0003116846920729904, 'epoch': 5.25}

 44%|████▍     | 12300/28080 [24:18:18<31:14:13,  7.13s/it]
 44%|████▍     | 12301/28080 [24:18:25<31:16:19,  7.13s/it]
                                                           
{'loss': 0.6133, 'learning_rate': 0.00031165674749683916, 'epoch': 5.25}

 44%|████▍     | 12301/28080 [24:18:25<31:16:19,  7.13s/it]
 44%|████▍     | 12302/28080 [24:18:32<31:09:23,  7.11s/it]
                                                           
{'loss': 0.6265, 'learning_rate': 0.00031162880210040844, 'epoch': 5.26}

 44%|████▍     | 12302/28080 [24:18:32<31:09:23,  7.11s/it]
 44%|████▍     | 12303/28080 [24:18:39<31:01:02,  7.08s/it]
                                                           
{'loss': 0.6476, 'learning_rate': 0.0003116008558840701, 'epoch': 5.26}

 44%|████▍     | 12303/28080 [24:18:39<31:01:02,  7.08s/it]
 44%|████▍     | 12304/28080 [24:18:47<31:04:58,  7.09s/it]
                                                           
{'loss': 0.6352, 'learning_rate': 0.000311572908848196, 'epoch': 5.26}

 44%|████▍     | 12304/28080 [24:18:47<31:04:58,  7.09s/it]
 44%|████▍     | 12305/28080 [24:18:54<31:12:50,  7.12s/it]
                                                           
{'loss': 0.6193, 'learning_rate': 0.00031154496099315774, 'epoch': 5.26}

 44%|████▍     | 12305/28080 [24:18:54<31:12:50,  7.12s/it]
 44%|████▍     | 12306/28080 [24:19:01<31:05:00,  7.09s/it]
                                                           
{'loss': 0.6241, 'learning_rate': 0.00031151701231932745, 'epoch': 5.26}

 44%|████▍     | 12306/28080 [24:19:01<31:05:00,  7.09s/it]
 44%|████▍     | 12307/28080 [24:19:08<31:06:46,  7.10s/it]
                                                           
{'loss': 0.6368, 'learning_rate': 0.00031148906282707663, 'epoch': 5.26}

 44%|████▍     | 12307/28080 [24:19:08<31:06:46,  7.10s/it]
 44%|████▍     | 12308/28080 [24:19:15<31:04:35,  7.09s/it]
                                                           
{'loss': 0.6231, 'learning_rate': 0.0003114611125167773, 'epoch': 5.26}

 44%|████▍     | 12308/28080 [24:19:15<31:04:35,  7.09s/it]
 44%|████▍     | 12309/28080 [24:19:22<31:10:25,  7.12s/it]
                                                           
{'loss': 0.6102, 'learning_rate': 0.0003114331613888013, 'epoch': 5.26}

 44%|████▍     | 12309/28080 [24:19:22<31:10:25,  7.12s/it]
 44%|████▍     | 12310/28080 [24:19:29<31:12:06,  7.12s/it]
                                                           
{'loss': 0.6301, 'learning_rate': 0.0003114052094435204, 'epoch': 5.26}

 44%|████▍     | 12310/28080 [24:19:29<31:12:06,  7.12s/it]
 44%|████▍     | 12311/28080 [24:19:36<31:10:59,  7.12s/it]
                                                           
{'loss': 0.6204, 'learning_rate': 0.00031137725668130663, 'epoch': 5.26}

 44%|████▍     | 12311/28080 [24:19:36<31:10:59,  7.12s/it]
 44%|████▍     | 12312/28080 [24:19:43<31:07:08,  7.10s/it]
                                                           
{'loss': 0.6462, 'learning_rate': 0.00031134930310253167, 'epoch': 5.26}

 44%|████▍     | 12312/28080 [24:19:43<31:07:08,  7.10s/it]
 44%|████▍     | 12313/28080 [24:19:51<31:06:14,  7.10s/it]
                                                           
{'loss': 0.6279, 'learning_rate': 0.00031132134870756763, 'epoch': 5.26}

 44%|████▍     | 12313/28080 [24:19:51<31:06:14,  7.10s/it]
 44%|████▍     | 12314/28080 [24:19:58<31:05:27,  7.10s/it]
                                                           
{'loss': 0.6181, 'learning_rate': 0.00031129339349678624, 'epoch': 5.26}

 44%|████▍     | 12314/28080 [24:19:58<31:05:27,  7.10s/it]
 44%|████▍     | 12315/28080 [24:20:05<31:13:53,  7.13s/it]
                                                           
{'loss': 0.6092, 'learning_rate': 0.00031126543747055953, 'epoch': 5.26}

 44%|████▍     | 12315/28080 [24:20:05<31:13:53,  7.13s/it]
 44%|████▍     | 12316/28080 [24:20:12<31:00:58,  7.08s/it]
                                                           
{'loss': 0.6109, 'learning_rate': 0.0003112374806292594, 'epoch': 5.26}

 44%|████▍     | 12316/28080 [24:20:12<31:00:58,  7.08s/it]
 44%|████▍     | 12317/28080 [24:20:19<31:04:05,  7.10s/it]
                                                           
{'loss': 0.6378, 'learning_rate': 0.00031120952297325764, 'epoch': 5.26}

 44%|████▍     | 12317/28080 [24:20:19<31:04:05,  7.10s/it]
 44%|████▍     | 12318/28080 [24:20:26<31:06:25,  7.10s/it]
                                                           
{'loss': 0.6009, 'learning_rate': 0.00031118156450292645, 'epoch': 5.26}

 44%|████▍     | 12318/28080 [24:20:26<31:06:25,  7.10s/it]
 44%|████▍     | 12319/28080 [24:20:33<31:15:00,  7.14s/it]
                                                           
{'loss': 0.6444, 'learning_rate': 0.0003111536052186376, 'epoch': 5.26}

 44%|████▍     | 12319/28080 [24:20:33<31:15:00,  7.14s/it]
 44%|████▍     | 12320/28080 [24:20:41<31:19:29,  7.16s/it]
                                                           
{'loss': 0.6306, 'learning_rate': 0.00031112564512076317, 'epoch': 5.26}

 44%|████▍     | 12320/28080 [24:20:41<31:19:29,  7.16s/it]
 44%|████▍     | 12321/28080 [24:20:48<31:18:56,  7.15s/it]
                                                           
{'loss': 0.6094, 'learning_rate': 0.00031109768420967506, 'epoch': 5.26}

 44%|████▍     | 12321/28080 [24:20:48<31:18:56,  7.15s/it]
 44%|████▍     | 12322/28080 [24:20:55<31:09:42,  7.12s/it]
                                                           
{'loss': 0.6099, 'learning_rate': 0.00031106972248574525, 'epoch': 5.26}

 44%|████▍     | 12322/28080 [24:20:55<31:09:42,  7.12s/it]
 44%|████▍     | 12323/28080 [24:21:02<31:14:51,  7.14s/it]
                                                           
{'loss': 0.6253, 'learning_rate': 0.0003110417599493459, 'epoch': 5.26}

 44%|████▍     | 12323/28080 [24:21:02<31:14:51,  7.14s/it]
 44%|████▍     | 12324/28080 [24:21:09<31:10:55,  7.12s/it]
                                                           
{'loss': 0.6226, 'learning_rate': 0.0003110137966008487, 'epoch': 5.26}

 44%|████▍     | 12324/28080 [24:21:09<31:10:55,  7.12s/it]
 44%|████▍     | 12325/28080 [24:21:16<31:10:45,  7.12s/it]
                                                           
{'loss': 0.625, 'learning_rate': 0.00031098583244062604, 'epoch': 5.27}

 44%|████▍     | 12325/28080 [24:21:16<31:10:45,  7.12s/it]
 44%|████▍     | 12326/28080 [24:21:23<31:13:33,  7.14s/it]
                                                           
{'loss': 0.6361, 'learning_rate': 0.0003109578674690498, 'epoch': 5.27}

 44%|████▍     | 12326/28080 [24:21:23<31:13:33,  7.14s/it]
 44%|████▍     | 12327/28080 [24:21:30<31:05:20,  7.10s/it]
                                                           
{'loss': 0.6058, 'learning_rate': 0.00031092990168649196, 'epoch': 5.27}

 44%|████▍     | 12327/28080 [24:21:30<31:05:20,  7.10s/it]
 44%|████▍     | 12328/28080 [24:21:37<31:08:23,  7.12s/it]
                                                           
{'loss': 0.6185, 'learning_rate': 0.00031090193509332464, 'epoch': 5.27}

 44%|████▍     | 12328/28080 [24:21:37<31:08:23,  7.12s/it]
 44%|████▍     | 12329/28080 [24:21:44<31:01:16,  7.09s/it]
                                                           
{'loss': 0.6326, 'learning_rate': 0.0003108739676899199, 'epoch': 5.27}

 44%|████▍     | 12329/28080 [24:21:44<31:01:16,  7.09s/it]
 44%|████▍     | 12330/28080 [24:21:52<31:00:42,  7.09s/it]
                                                           
{'loss': 0.6094, 'learning_rate': 0.00031084599947664996, 'epoch': 5.27}

 44%|████▍     | 12330/28080 [24:21:52<31:00:42,  7.09s/it]
 44%|████▍     | 12331/28080 [24:21:59<31:03:07,  7.10s/it]
                                                           
{'loss': 0.637, 'learning_rate': 0.00031081803045388657, 'epoch': 5.27}

 44%|████▍     | 12331/28080 [24:21:59<31:03:07,  7.10s/it]
 44%|████▍     | 12332/28080 [24:22:06<30:50:59,  7.05s/it]
                                                           
{'loss': 0.6519, 'learning_rate': 0.0003107900606220022, 'epoch': 5.27}

 44%|████▍     | 12332/28080 [24:22:06<30:50:59,  7.05s/it]
 44%|████▍     | 12333/28080 [24:22:13<30:50:21,  7.05s/it]
                                                           
{'loss': 0.6176, 'learning_rate': 0.0003107620899813686, 'epoch': 5.27}

 44%|████▍     | 12333/28080 [24:22:13<30:50:21,  7.05s/it]
 44%|████▍     | 12334/28080 [24:22:20<30:56:16,  7.07s/it]
                                                           
{'loss': 0.6231, 'learning_rate': 0.00031073411853235815, 'epoch': 5.27}

 44%|████▍     | 12334/28080 [24:22:20<30:56:16,  7.07s/it]
 44%|████▍     | 12335/28080 [24:22:27<31:04:01,  7.10s/it]
                                                           
{'loss': 0.6177, 'learning_rate': 0.00031070614627534297, 'epoch': 5.27}

 44%|████▍     | 12335/28080 [24:22:27<31:04:01,  7.10s/it]
 44%|████▍     | 12336/28080 [24:22:34<31:04:00,  7.10s/it]
                                                           
{'loss': 0.6275, 'learning_rate': 0.0003106781732106951, 'epoch': 5.27}

 44%|████▍     | 12336/28080 [24:22:34<31:04:00,  7.10s/it]
 44%|████▍     | 12337/28080 [24:22:41<31:08:45,  7.12s/it]
                                                           
{'loss': 0.6257, 'learning_rate': 0.00031065019933878673, 'epoch': 5.27}

 44%|████▍     | 12337/28080 [24:22:41<31:08:45,  7.12s/it]
 44%|████▍     | 12338/28080 [24:22:48<31:02:06,  7.10s/it]
                                                           
{'loss': 0.6113, 'learning_rate': 0.00031062222465999003, 'epoch': 5.27}

 44%|████▍     | 12338/28080 [24:22:48<31:02:06,  7.10s/it]
 44%|████▍     | 12339/28080 [24:22:55<31:05:12,  7.11s/it]
                                                           
{'loss': 0.6117, 'learning_rate': 0.00031059424917467723, 'epoch': 5.27}

 44%|████▍     | 12339/28080 [24:22:55<31:05:12,  7.11s/it]
 44%|████▍     | 12340/28080 [24:23:02<30:57:16,  7.08s/it]
                                                           
{'loss': 0.625, 'learning_rate': 0.00031056627288322044, 'epoch': 5.27}

 44%|████▍     | 12340/28080 [24:23:02<30:57:16,  7.08s/it]
 44%|████▍     | 12341/28080 [24:23:10<30:59:22,  7.09s/it]
                                                           
{'loss': 0.6154, 'learning_rate': 0.0003105382957859918, 'epoch': 5.27}

 44%|████▍     | 12341/28080 [24:23:10<30:59:22,  7.09s/it]
 44%|████▍     | 12342/28080 [24:23:17<30:57:52,  7.08s/it]
                                                           
{'loss': 0.6207, 'learning_rate': 0.00031051031788336363, 'epoch': 5.27}

 44%|████▍     | 12342/28080 [24:23:17<30:57:52,  7.08s/it]
 44%|████▍     | 12343/28080 [24:23:24<31:06:58,  7.12s/it]
                                                           
{'loss': 0.6345, 'learning_rate': 0.0003104823391757081, 'epoch': 5.27}

 44%|████▍     | 12343/28080 [24:23:24<31:06:58,  7.12s/it]
 44%|████▍     | 12344/28080 [24:23:31<31:02:51,  7.10s/it]
                                                           
{'loss': 0.6279, 'learning_rate': 0.00031045435966339747, 'epoch': 5.27}

 44%|████▍     | 12344/28080 [24:23:31<31:02:51,  7.10s/it]
 44%|████▍     | 12345/28080 [24:23:38<31:12:58,  7.14s/it]
                                                           
{'loss': 0.615, 'learning_rate': 0.00031042637934680385, 'epoch': 5.27}

 44%|████▍     | 12345/28080 [24:23:38<31:12:58,  7.14s/it]
 44%|████▍     | 12346/28080 [24:23:45<31:11:53,  7.14s/it]
                                                           
{'loss': 0.6201, 'learning_rate': 0.0003103983982262997, 'epoch': 5.27}

 44%|████▍     | 12346/28080 [24:23:45<31:11:53,  7.14s/it]
 44%|████▍     | 12347/28080 [24:23:52<31:11:27,  7.14s/it]
                                                           
{'loss': 0.6251, 'learning_rate': 0.0003103704163022572, 'epoch': 5.27}

 44%|████▍     | 12347/28080 [24:23:52<31:11:27,  7.14s/it]
 44%|████▍     | 12348/28080 [24:23:59<31:09:07,  7.13s/it]
                                                           
{'loss': 0.6273, 'learning_rate': 0.00031034243357504844, 'epoch': 5.27}

 44%|████▍     | 12348/28080 [24:23:59<31:09:07,  7.13s/it]
 44%|████▍     | 12349/28080 [24:24:07<31:10:12,  7.13s/it]
                                                           
{'loss': 0.6146, 'learning_rate': 0.000310314450045046, 'epoch': 5.28}

 44%|████▍     | 12349/28080 [24:24:07<31:10:12,  7.13s/it]
 44%|████▍     | 12350/28080 [24:24:14<31:12:40,  7.14s/it]
                                                           
{'loss': 0.5935, 'learning_rate': 0.0003102864657126219, 'epoch': 5.28}

 44%|████▍     | 12350/28080 [24:24:14<31:12:40,  7.14s/it]
 44%|████▍     | 12351/28080 [24:24:21<31:10:52,  7.14s/it]
                                                           
{'loss': 0.6114, 'learning_rate': 0.00031025848057814867, 'epoch': 5.28}

 44%|████▍     | 12351/28080 [24:24:21<31:10:52,  7.14s/it]
 44%|████▍     | 12352/28080 [24:24:28<31:01:27,  7.10s/it]
                                                           
{'loss': 0.611, 'learning_rate': 0.00031023049464199847, 'epoch': 5.28}

 44%|████▍     | 12352/28080 [24:24:28<31:01:27,  7.10s/it]
 44%|████▍     | 12353/28080 [24:24:35<31:07:04,  7.12s/it]
                                                           
{'loss': 0.6145, 'learning_rate': 0.00031020250790454365, 'epoch': 5.28}

 44%|████▍     | 12353/28080 [24:24:35<31:07:04,  7.12s/it]
 44%|████▍     | 12354/28080 [24:24:42<31:02:58,  7.11s/it]
                                                           
{'loss': 0.6202, 'learning_rate': 0.0003101745203661566, 'epoch': 5.28}

 44%|████▍     | 12354/28080 [24:24:42<31:02:58,  7.11s/it]
 44%|████▍     | 12355/28080 [24:24:49<31:03:02,  7.11s/it]
                                                           
{'loss': 0.596, 'learning_rate': 0.00031014653202720964, 'epoch': 5.28}

 44%|████▍     | 12355/28080 [24:24:49<31:03:02,  7.11s/it]
 44%|████▍     | 12356/28080 [24:24:56<31:10:59,  7.14s/it]
                                                           
{'loss': 0.6343, 'learning_rate': 0.00031011854288807517, 'epoch': 5.28}

 44%|████▍     | 12356/28080 [24:24:57<31:10:59,  7.14s/it]
 44%|████▍     | 12357/28080 [24:25:04<31:12:36,  7.15s/it]
                                                           
{'loss': 0.622, 'learning_rate': 0.00031009055294912546, 'epoch': 5.28}

 44%|████▍     | 12357/28080 [24:25:04<31:12:36,  7.15s/it]
 44%|████▍     | 12358/28080 [24:25:11<30:59:43,  7.10s/it]
                                                           
{'loss': 0.6356, 'learning_rate': 0.00031006256221073294, 'epoch': 5.28}

 44%|████▍     | 12358/28080 [24:25:11<30:59:43,  7.10s/it]
 44%|████▍     | 12359/28080 [24:25:18<30:54:47,  7.08s/it]
                                                           
{'loss': 0.629, 'learning_rate': 0.00031003457067327, 'epoch': 5.28}

 44%|████▍     | 12359/28080 [24:25:18<30:54:47,  7.08s/it]
 44%|████▍     | 12360/28080 [24:25:25<30:55:07,  7.08s/it]
                                                           
{'loss': 0.6114, 'learning_rate': 0.000310006578337109, 'epoch': 5.28}

 44%|████▍     | 12360/28080 [24:25:25<30:55:07,  7.08s/it]
 44%|████▍     | 12361/28080 [24:25:32<30:57:20,  7.09s/it]
                                                           
{'loss': 0.6382, 'learning_rate': 0.0003099785852026224, 'epoch': 5.28}

 44%|████▍     | 12361/28080 [24:25:32<30:57:20,  7.09s/it]
 44%|████▍     | 12362/28080 [24:25:39<30:56:49,  7.09s/it]
                                                           
{'loss': 0.6068, 'learning_rate': 0.0003099505912701826, 'epoch': 5.28}

 44%|████▍     | 12362/28080 [24:25:39<30:56:49,  7.09s/it]
 44%|████▍     | 12363/28080 [24:25:46<30:58:53,  7.10s/it]
                                                           
{'loss': 0.6256, 'learning_rate': 0.00030992259654016207, 'epoch': 5.28}

 44%|████▍     | 12363/28080 [24:25:46<30:58:53,  7.10s/it]
 44%|████▍     | 12364/28080 [24:25:53<30:52:29,  7.07s/it]
                                                           
{'loss': 0.6237, 'learning_rate': 0.00030989460101293317, 'epoch': 5.28}

 44%|████▍     | 12364/28080 [24:25:53<30:52:29,  7.07s/it]
 44%|████▍     | 12365/28080 [24:26:00<30:51:09,  7.07s/it]
                                                           
{'loss': 0.6062, 'learning_rate': 0.0003098666046888684, 'epoch': 5.28}

 44%|████▍     | 12365/28080 [24:26:00<30:51:09,  7.07s/it]
 44%|████▍     | 12366/28080 [24:26:07<30:53:51,  7.08s/it]
                                                           
{'loss': 0.634, 'learning_rate': 0.00030983860756834025, 'epoch': 5.28}

 44%|████▍     | 12366/28080 [24:26:07<30:53:51,  7.08s/it]
 44%|████▍     | 12367/28080 [24:26:14<30:55:45,  7.09s/it]
                                                           
{'loss': 0.6202, 'learning_rate': 0.0003098106096517211, 'epoch': 5.28}

 44%|████▍     | 12367/28080 [24:26:14<30:55:45,  7.09s/it]
 44%|████▍     | 12368/28080 [24:26:21<30:58:15,  7.10s/it]
                                                           
{'loss': 0.5999, 'learning_rate': 0.00030978261093938354, 'epoch': 5.28}

 44%|████▍     | 12368/28080 [24:26:21<30:58:15,  7.10s/it]
 44%|████▍     | 12369/28080 [24:26:29<31:00:30,  7.11s/it]
                                                           
{'loss': 0.6116, 'learning_rate': 0.00030975461143169995, 'epoch': 5.28}

 44%|████▍     | 12369/28080 [24:26:29<31:00:30,  7.11s/it]
 44%|████▍     | 12370/28080 [24:26:36<31:10:23,  7.14s/it]
                                                           
{'loss': 0.6192, 'learning_rate': 0.00030972661112904296, 'epoch': 5.28}

 44%|████▍     | 12370/28080 [24:26:36<31:10:23,  7.14s/it]
 44%|████▍     | 12371/28080 [24:26:43<31:08:39,  7.14s/it]
                                                           
{'loss': 0.6311, 'learning_rate': 0.00030969861003178503, 'epoch': 5.28}

 44%|████▍     | 12371/28080 [24:26:43<31:08:39,  7.14s/it]
 44%|████▍     | 12372/28080 [24:26:50<31:05:28,  7.13s/it]
                                                           
{'loss': 0.6176, 'learning_rate': 0.00030967060814029865, 'epoch': 5.29}

 44%|████▍     | 12372/28080 [24:26:50<31:05:28,  7.13s/it]
 44%|████▍     | 12373/28080 [24:26:57<31:02:27,  7.11s/it]
                                                           
{'loss': 0.6337, 'learning_rate': 0.00030964260545495635, 'epoch': 5.29}

 44%|████▍     | 12373/28080 [24:26:57<31:02:27,  7.11s/it]
 44%|████▍     | 12374/28080 [24:27:04<30:55:01,  7.09s/it]
                                                           
{'loss': 0.6279, 'learning_rate': 0.0003096146019761308, 'epoch': 5.29}

 44%|████▍     | 12374/28080 [24:27:04<30:55:01,  7.09s/it]
 44%|████▍     | 12375/28080 [24:27:11<31:00:31,  7.11s/it]
                                                           
{'loss': 0.6279, 'learning_rate': 0.00030958659770419445, 'epoch': 5.29}

 44%|████▍     | 12375/28080 [24:27:11<31:00:31,  7.11s/it]
 44%|████▍     | 12376/28080 [24:27:18<31:01:00,  7.11s/it]
                                                           
{'loss': 0.6227, 'learning_rate': 0.0003095585926395198, 'epoch': 5.29}

 44%|████▍     | 12376/28080 [24:27:18<31:01:00,  7.11s/it]
 44%|████▍     | 12377/28080 [24:27:26<31:07:33,  7.14s/it]
                                                           
{'loss': 0.6251, 'learning_rate': 0.00030953058678247957, 'epoch': 5.29}

 44%|████▍     | 12377/28080 [24:27:26<31:07:33,  7.14s/it]
 44%|████▍     | 12378/28080 [24:27:33<31:08:18,  7.14s/it]
                                                           
{'loss': 0.6097, 'learning_rate': 0.00030950258013344635, 'epoch': 5.29}

 44%|████▍     | 12378/28080 [24:27:33<31:08:18,  7.14s/it]
 44%|████▍     | 12379/28080 [24:27:40<31:03:49,  7.12s/it]
                                                           
{'loss': 0.6216, 'learning_rate': 0.00030947457269279267, 'epoch': 5.29}

 44%|████▍     | 12379/28080 [24:27:40<31:03:49,  7.12s/it]
 44%|████▍     | 12380/28080 [24:27:47<31:04:16,  7.12s/it]
                                                           
{'loss': 0.6039, 'learning_rate': 0.0003094465644608911, 'epoch': 5.29}

 44%|████▍     | 12380/28080 [24:27:47<31:04:16,  7.12s/it]
 44%|████▍     | 12381/28080 [24:27:54<31:06:48,  7.13s/it]
                                                           
{'loss': 0.6255, 'learning_rate': 0.0003094185554381144, 'epoch': 5.29}

 44%|████▍     | 12381/28080 [24:27:54<31:06:48,  7.13s/it]
 44%|████▍     | 12382/28080 [24:28:01<31:06:42,  7.13s/it]
                                                           
{'loss': 0.6219, 'learning_rate': 0.00030939054562483507, 'epoch': 5.29}

 44%|████▍     | 12382/28080 [24:28:01<31:06:42,  7.13s/it]
 44%|████▍     | 12383/28080 [24:28:08<31:02:14,  7.12s/it]
                                                           
{'loss': 0.624, 'learning_rate': 0.0003093625350214258, 'epoch': 5.29}

 44%|████▍     | 12383/28080 [24:28:08<31:02:14,  7.12s/it]
 44%|████▍     | 12384/28080 [24:28:15<30:56:27,  7.10s/it]
                                                           
{'loss': 0.6262, 'learning_rate': 0.0003093345236282592, 'epoch': 5.29}

 44%|████▍     | 12384/28080 [24:28:15<30:56:27,  7.10s/it]
 44%|████▍     | 12385/28080 [24:28:23<30:56:05,  7.10s/it]
                                                           
{'loss': 0.6286, 'learning_rate': 0.0003093065114457081, 'epoch': 5.29}

 44%|████▍     | 12385/28080 [24:28:23<30:56:05,  7.10s/it]
 44%|████▍     | 12386/28080 [24:28:30<30:52:37,  7.08s/it]
                                                           
{'loss': 0.6236, 'learning_rate': 0.0003092784984741449, 'epoch': 5.29}

 44%|████▍     | 12386/28080 [24:28:30<30:52:37,  7.08s/it]
 44%|████▍     | 12387/28080 [24:28:37<30:52:22,  7.08s/it]
                                                           
{'loss': 0.6369, 'learning_rate': 0.00030925048471394255, 'epoch': 5.29}

 44%|████▍     | 12387/28080 [24:28:37<30:52:22,  7.08s/it]
 44%|████▍     | 12388/28080 [24:28:44<30:56:18,  7.10s/it]
                                                           
{'loss': 0.6249, 'learning_rate': 0.00030922247016547356, 'epoch': 5.29}

 44%|████▍     | 12388/28080 [24:28:44<30:56:18,  7.10s/it]
 44%|████▍     | 12389/28080 [24:28:51<30:52:46,  7.08s/it]
                                                           
{'loss': 0.6265, 'learning_rate': 0.0003091944548291107, 'epoch': 5.29}

 44%|████▍     | 12389/28080 [24:28:51<30:52:46,  7.08s/it]
 44%|████▍     | 12390/28080 [24:28:58<30:56:02,  7.10s/it]
                                                           
{'loss': 0.6211, 'learning_rate': 0.00030916643870522676, 'epoch': 5.29}

 44%|████▍     | 12390/28080 [24:28:58<30:56:02,  7.10s/it]
 44%|████▍     | 12391/28080 [24:29:05<30:58:05,  7.11s/it]
                                                           
{'loss': 0.6336, 'learning_rate': 0.00030913842179419433, 'epoch': 5.29}

 44%|████▍     | 12391/28080 [24:29:05<30:58:05,  7.11s/it]
 44%|████▍     | 12392/28080 [24:29:12<31:01:01,  7.12s/it]
                                                           
{'loss': 0.6202, 'learning_rate': 0.00030911040409638626, 'epoch': 5.29}

 44%|████▍     | 12392/28080 [24:29:12<31:01:01,  7.12s/it]
 44%|████▍     | 12393/28080 [24:29:19<31:02:45,  7.12s/it]
                                                           
{'loss': 0.6066, 'learning_rate': 0.0003090823856121752, 'epoch': 5.29}

 44%|████▍     | 12393/28080 [24:29:19<31:02:45,  7.12s/it]
 44%|████▍     | 12394/28080 [24:29:26<31:03:02,  7.13s/it]
                                                           
{'loss': 0.6139, 'learning_rate': 0.0003090543663419339, 'epoch': 5.29}

 44%|████▍     | 12394/28080 [24:29:26<31:03:02,  7.13s/it]
 44%|████▍     | 12395/28080 [24:29:34<30:59:57,  7.11s/it]
                                                           
{'loss': 0.6126, 'learning_rate': 0.0003090263462860353, 'epoch': 5.3}

 44%|████▍     | 12395/28080 [24:29:34<30:59:57,  7.11s/it]
 44%|████▍     | 12396/28080 [24:29:41<30:55:25,  7.10s/it]
                                                           
{'loss': 0.6285, 'learning_rate': 0.00030899832544485195, 'epoch': 5.3}

 44%|████▍     | 12396/28080 [24:29:41<30:55:25,  7.10s/it]
 44%|████▍     | 12397/28080 [24:29:48<30:57:10,  7.11s/it]
                                                           
{'loss': 0.6047, 'learning_rate': 0.0003089703038187568, 'epoch': 5.3}

 44%|████▍     | 12397/28080 [24:29:48<30:57:10,  7.11s/it]
 44%|████▍     | 12398/28080 [24:29:55<30:49:15,  7.08s/it]
                                                           
{'loss': 0.5981, 'learning_rate': 0.00030894228140812254, 'epoch': 5.3}

 44%|████▍     | 12398/28080 [24:29:55<30:49:15,  7.08s/it]
 44%|████▍     | 12399/28080 [24:30:02<30:48:10,  7.07s/it]
                                                           
{'loss': 0.6225, 'learning_rate': 0.00030891425821332207, 'epoch': 5.3}

 44%|████▍     | 12399/28080 [24:30:02<30:48:10,  7.07s/it]
 44%|████▍     | 12400/28080 [24:30:09<30:51:26,  7.08s/it]
                                                           
{'loss': 0.6062, 'learning_rate': 0.00030888623423472815, 'epoch': 5.3}

 44%|████▍     | 12400/28080 [24:30:09<30:51:26,  7.08s/it]
 44%|████▍     | 12401/28080 [24:30:16<30:51:16,  7.08s/it]
                                                           
{'loss': 0.6226, 'learning_rate': 0.00030885820947271366, 'epoch': 5.3}

 44%|████▍     | 12401/28080 [24:30:16<30:51:16,  7.08s/it]
 44%|████▍     | 12402/28080 [24:30:23<30:54:09,  7.10s/it]
                                                           
{'loss': 0.6184, 'learning_rate': 0.00030883018392765144, 'epoch': 5.3}

 44%|████▍     | 12402/28080 [24:30:23<30:54:09,  7.10s/it]
 44%|████▍     | 12403/28080 [24:30:30<30:59:54,  7.12s/it]
                                                           
{'loss': 0.6093, 'learning_rate': 0.00030880215759991424, 'epoch': 5.3}

 44%|████▍     | 12403/28080 [24:30:30<30:59:54,  7.12s/it]
 44%|████▍     | 12404/28080 [24:30:37<30:56:44,  7.11s/it]
                                                           
{'loss': 0.6441, 'learning_rate': 0.0003087741304898751, 'epoch': 5.3}

 44%|████▍     | 12404/28080 [24:30:37<30:56:44,  7.11s/it]
 44%|████▍     | 12405/28080 [24:30:45<30:59:14,  7.12s/it]
                                                           
{'loss': 0.6227, 'learning_rate': 0.0003087461025979067, 'epoch': 5.3}

 44%|████▍     | 12405/28080 [24:30:45<30:59:14,  7.12s/it]
 44%|████▍     | 12406/28080 [24:30:52<31:02:55,  7.13s/it]
                                                           
{'loss': 0.6241, 'learning_rate': 0.00030871807392438206, 'epoch': 5.3}

 44%|████▍     | 12406/28080 [24:30:52<31:02:55,  7.13s/it]
 44%|████▍     | 12407/28080 [24:30:59<31:05:03,  7.14s/it]
                                                           
{'loss': 0.6154, 'learning_rate': 0.00030869004446967396, 'epoch': 5.3}

 44%|████▍     | 12407/28080 [24:30:59<31:05:03,  7.14s/it]
 44%|████▍     | 12408/28080 [24:31:06<30:59:51,  7.12s/it]
                                                           
{'loss': 0.6367, 'learning_rate': 0.00030866201423415543, 'epoch': 5.3}

 44%|████▍     | 12408/28080 [24:31:06<30:59:51,  7.12s/it]
 44%|████▍     | 12409/28080 [24:31:13<30:50:41,  7.09s/it]
                                                           
{'loss': 0.6334, 'learning_rate': 0.0003086339832181993, 'epoch': 5.3}

 44%|████▍     | 12409/28080 [24:31:13<30:50:41,  7.09s/it]
 44%|████▍     | 12410/28080 [24:31:20<30:56:30,  7.11s/it]
                                                           
{'loss': 0.6292, 'learning_rate': 0.0003086059514221785, 'epoch': 5.3}

 44%|████▍     | 12410/28080 [24:31:20<30:56:30,  7.11s/it]
 44%|████▍     | 12411/28080 [24:31:27<30:52:12,  7.09s/it]
                                                           
{'loss': 0.5957, 'learning_rate': 0.000308577918846466, 'epoch': 5.3}

 44%|████▍     | 12411/28080 [24:31:27<30:52:12,  7.09s/it]
 44%|████▍     | 12412/28080 [24:31:34<30:52:20,  7.09s/it]
                                                           
{'loss': 0.5891, 'learning_rate': 0.0003085498854914347, 'epoch': 5.3}

 44%|████▍     | 12412/28080 [24:31:34<30:52:20,  7.09s/it]
 44%|████▍     | 12413/28080 [24:31:42<31:03:58,  7.14s/it]
                                                           
{'loss': 0.6053, 'learning_rate': 0.0003085218513574576, 'epoch': 5.3}

 44%|████▍     | 12413/28080 [24:31:42<31:03:58,  7.14s/it]
 44%|████▍     | 12414/28080 [24:31:49<30:58:15,  7.12s/it]
                                                           
{'loss': 0.6299, 'learning_rate': 0.0003084938164449076, 'epoch': 5.3}

 44%|████▍     | 12414/28080 [24:31:49<30:58:15,  7.12s/it]
 44%|████▍     | 12415/28080 [24:31:56<31:03:57,  7.14s/it]
                                                           
{'loss': 0.6203, 'learning_rate': 0.0003084657807541578, 'epoch': 5.3}

 44%|████▍     | 12415/28080 [24:31:56<31:03:57,  7.14s/it]
 44%|████▍     | 12416/28080 [24:32:03<31:07:19,  7.15s/it]
                                                           
{'loss': 0.6127, 'learning_rate': 0.00030843774428558103, 'epoch': 5.3}

 44%|████▍     | 12416/28080 [24:32:03<31:07:19,  7.15s/it]
 44%|████▍     | 12417/28080 [24:32:10<31:07:49,  7.16s/it]
                                                           
{'loss': 0.6303, 'learning_rate': 0.00030840970703955033, 'epoch': 5.3}

 44%|████▍     | 12417/28080 [24:32:10<31:07:49,  7.16s/it]
 44%|████▍     | 12418/28080 [24:32:17<31:03:42,  7.14s/it]
                                                           
{'loss': 0.6174, 'learning_rate': 0.00030838166901643875, 'epoch': 5.3}

 44%|████▍     | 12418/28080 [24:32:17<31:03:42,  7.14s/it]
 44%|████▍     | 12419/28080 [24:32:24<31:04:03,  7.14s/it]
                                                           
{'loss': 0.6286, 'learning_rate': 0.0003083536302166194, 'epoch': 5.31}

 44%|████▍     | 12419/28080 [24:32:24<31:04:03,  7.14s/it]
 44%|████▍     | 12420/28080 [24:32:32<31:07:43,  7.16s/it]
                                                           
{'loss': 0.6287, 'learning_rate': 0.00030832559064046506, 'epoch': 5.31}

 44%|████▍     | 12420/28080 [24:32:32<31:07:43,  7.16s/it]
 44%|████▍     | 12421/28080 [24:32:39<30:59:18,  7.12s/it]
                                                           
{'loss': 0.6241, 'learning_rate': 0.000308297550288349, 'epoch': 5.31}

 44%|████▍     | 12421/28080 [24:32:39<30:59:18,  7.12s/it]
 44%|████▍     | 12422/28080 [24:32:46<31:01:41,  7.13s/it]
                                                           
{'loss': 0.6071, 'learning_rate': 0.0003082695091606441, 'epoch': 5.31}

 44%|████▍     | 12422/28080 [24:32:46<31:01:41,  7.13s/it]
 44%|████▍     | 12423/28080 [24:32:53<31:09:41,  7.16s/it]
                                                           
{'loss': 0.6108, 'learning_rate': 0.00030824146725772357, 'epoch': 5.31}

 44%|████▍     | 12423/28080 [24:32:53<31:09:41,  7.16s/it]
 44%|████▍     | 12424/28080 [24:33:00<31:02:03,  7.14s/it]
                                                           
{'loss': 0.6288, 'learning_rate': 0.0003082134245799604, 'epoch': 5.31}

 44%|████▍     | 12424/28080 [24:33:00<31:02:03,  7.14s/it]
 44%|████▍     | 12425/28080 [24:33:07<30:54:11,  7.11s/it]
                                                           
{'loss': 0.6223, 'learning_rate': 0.00030818538112772757, 'epoch': 5.31}

 44%|████▍     | 12425/28080 [24:33:07<30:54:11,  7.11s/it]
 44%|████▍     | 12426/28080 [24:33:14<30:53:45,  7.11s/it]
                                                           
{'loss': 0.6151, 'learning_rate': 0.00030815733690139836, 'epoch': 5.31}

 44%|████▍     | 12426/28080 [24:33:14<30:53:45,  7.11s/it]
 44%|████▍     | 12427/28080 [24:33:21<31:00:06,  7.13s/it]
                                                           
{'loss': 0.6237, 'learning_rate': 0.00030812929190134574, 'epoch': 5.31}

 44%|████▍     | 12427/28080 [24:33:21<31:00:06,  7.13s/it]
 44%|████▍     | 12428/28080 [24:33:29<31:05:57,  7.15s/it]
                                                           
{'loss': 0.6154, 'learning_rate': 0.0003081012461279429, 'epoch': 5.31}

 44%|████▍     | 12428/28080 [24:33:29<31:05:57,  7.15s/it]
 44%|████▍     | 12429/28080 [24:33:36<30:51:40,  7.10s/it]
                                                           
{'loss': 0.6366, 'learning_rate': 0.0003080731995815629, 'epoch': 5.31}

 44%|████▍     | 12429/28080 [24:33:36<30:51:40,  7.10s/it]
 44%|████▍     | 12430/28080 [24:33:43<30:57:21,  7.12s/it]
                                                           
{'loss': 0.6298, 'learning_rate': 0.00030804515226257897, 'epoch': 5.31}

 44%|████▍     | 12430/28080 [24:33:43<30:57:21,  7.12s/it]
 44%|████▍     | 12431/28080 [24:33:50<30:57:24,  7.12s/it]
                                                           
{'loss': 0.6185, 'learning_rate': 0.00030801710417136403, 'epoch': 5.31}

 44%|████▍     | 12431/28080 [24:33:50<30:57:24,  7.12s/it]
 44%|████▍     | 12432/28080 [24:33:57<31:15:34,  7.19s/it]
                                                           
{'loss': 0.6251, 'learning_rate': 0.0003079890553082914, 'epoch': 5.31}

 44%|████▍     | 12432/28080 [24:33:57<31:15:34,  7.19s/it]
 44%|████▍     | 12433/28080 [24:34:04<31:07:06,  7.16s/it]
                                                           
{'loss': 0.6161, 'learning_rate': 0.0003079610056737343, 'epoch': 5.31}

 44%|████▍     | 12433/28080 [24:34:04<31:07:06,  7.16s/it]
 44%|████▍     | 12434/28080 [24:34:11<31:02:15,  7.14s/it]
                                                           
{'loss': 0.6111, 'learning_rate': 0.00030793295526806573, 'epoch': 5.31}

 44%|████▍     | 12434/28080 [24:34:11<31:02:15,  7.14s/it]
 44%|████▍     | 12435/28080 [24:34:19<31:01:09,  7.14s/it]
                                                           
{'loss': 0.6391, 'learning_rate': 0.000307904904091659, 'epoch': 5.31}

 44%|████▍     | 12435/28080 [24:34:19<31:01:09,  7.14s/it]
 44%|████▍     | 12436/28080 [24:34:26<31:00:54,  7.14s/it]
                                                           
{'loss': 0.6257, 'learning_rate': 0.00030787685214488726, 'epoch': 5.31}

 44%|████▍     | 12436/28080 [24:34:26<31:00:54,  7.14s/it]
 44%|████▍     | 12437/28080 [24:34:33<31:04:29,  7.15s/it]
                                                           
{'loss': 0.6249, 'learning_rate': 0.00030784879942812374, 'epoch': 5.31}

 44%|████▍     | 12437/28080 [24:34:33<31:04:29,  7.15s/it]
 44%|████▍     | 12438/28080 [24:34:40<30:58:58,  7.13s/it]
                                                           
{'loss': 0.6285, 'learning_rate': 0.0003078207459417415, 'epoch': 5.31}

 44%|████▍     | 12438/28080 [24:34:40<30:58:58,  7.13s/it]
 44%|████▍     | 12439/28080 [24:34:47<31:01:22,  7.14s/it]
                                                           
{'loss': 0.6134, 'learning_rate': 0.00030779269168611397, 'epoch': 5.31}

 44%|████▍     | 12439/28080 [24:34:47<31:01:22,  7.14s/it]
 44%|████▍     | 12440/28080 [24:34:54<30:57:29,  7.13s/it]
                                                           
{'loss': 0.6228, 'learning_rate': 0.00030776463666161435, 'epoch': 5.31}

 44%|████▍     | 12440/28080 [24:34:54<30:57:29,  7.13s/it]
 44%|████▍     | 12441/28080 [24:35:01<30:56:10,  7.12s/it]
                                                           
{'loss': 0.6279, 'learning_rate': 0.00030773658086861576, 'epoch': 5.31}

 44%|████▍     | 12441/28080 [24:35:01<30:56:10,  7.12s/it]
 44%|████▍     | 12442/28080 [24:35:08<30:52:21,  7.11s/it]
                                                           
{'loss': 0.6241, 'learning_rate': 0.00030770852430749154, 'epoch': 5.32}

 44%|████▍     | 12442/28080 [24:35:08<30:52:21,  7.11s/it]
 44%|████▍     | 12443/28080 [24:35:16<30:55:46,  7.12s/it]
                                                           
{'loss': 0.6139, 'learning_rate': 0.00030768046697861497, 'epoch': 5.32}

 44%|████▍     | 12443/28080 [24:35:16<30:55:46,  7.12s/it]
 44%|████▍     | 12444/28080 [24:35:23<30:51:23,  7.10s/it]
                                                           
{'loss': 0.635, 'learning_rate': 0.00030765240888235923, 'epoch': 5.32}

 44%|████▍     | 12444/28080 [24:35:23<30:51:23,  7.10s/it]
 44%|████▍     | 12445/28080 [24:35:30<30:50:51,  7.10s/it]
                                                           
{'loss': 0.629, 'learning_rate': 0.00030762435001909774, 'epoch': 5.32}

 44%|████▍     | 12445/28080 [24:35:30<30:50:51,  7.10s/it]
 44%|████▍     | 12446/28080 [24:35:37<30:45:40,  7.08s/it]
                                                           
{'loss': 0.6336, 'learning_rate': 0.00030759629038920366, 'epoch': 5.32}

 44%|████▍     | 12446/28080 [24:35:37<30:45:40,  7.08s/it]
 44%|████▍     | 12447/28080 [24:35:44<30:48:53,  7.10s/it]
                                                           
{'loss': 0.6137, 'learning_rate': 0.0003075682299930504, 'epoch': 5.32}

 44%|████▍     | 12447/28080 [24:35:44<30:48:53,  7.10s/it]
 44%|████▍     | 12448/28080 [24:35:51<30:50:04,  7.10s/it]
                                                           
{'loss': 0.6458, 'learning_rate': 0.00030754016883101116, 'epoch': 5.32}

 44%|████▍     | 12448/28080 [24:35:51<30:50:04,  7.10s/it]
 44%|████▍     | 12449/28080 [24:35:58<30:45:35,  7.08s/it]
                                                           
{'loss': 0.6332, 'learning_rate': 0.00030751210690345936, 'epoch': 5.32}

 44%|████▍     | 12449/28080 [24:35:58<30:45:35,  7.08s/it]
 44%|████▍     | 12450/28080 [24:36:05<30:56:13,  7.13s/it]
                                                           
{'loss': 0.6158, 'learning_rate': 0.00030748404421076836, 'epoch': 5.32}

 44%|████▍     | 12450/28080 [24:36:05<30:56:13,  7.13s/it]
 44%|████▍     | 12451/28080 [24:36:12<30:59:35,  7.14s/it]
                                                           
{'loss': 0.627, 'learning_rate': 0.0003074559807533114, 'epoch': 5.32}

 44%|████▍     | 12451/28080 [24:36:12<30:59:35,  7.14s/it]
 44%|████▍     | 12452/28080 [24:36:20<30:58:34,  7.14s/it]
                                                           
{'loss': 0.6218, 'learning_rate': 0.000307427916531462, 'epoch': 5.32}

 44%|████▍     | 12452/28080 [24:36:20<30:58:34,  7.14s/it]
 44%|████▍     | 12453/28080 [24:36:27<30:56:50,  7.13s/it]
                                                           
{'loss': 0.6342, 'learning_rate': 0.00030739985154559324, 'epoch': 5.32}

 44%|████▍     | 12453/28080 [24:36:27<30:56:50,  7.13s/it]
 44%|████▍     | 12454/28080 [24:36:34<30:58:01,  7.13s/it]
                                                           
{'loss': 0.6384, 'learning_rate': 0.00030737178579607884, 'epoch': 5.32}

 44%|████▍     | 12454/28080 [24:36:34<30:58:01,  7.13s/it]
 44%|████▍     | 12455/28080 [24:36:41<30:55:46,  7.13s/it]
                                                           
{'loss': 0.6305, 'learning_rate': 0.00030734371928329185, 'epoch': 5.32}

 44%|████▍     | 12455/28080 [24:36:41<30:55:46,  7.13s/it]
 44%|████▍     | 12456/28080 [24:36:48<30:55:59,  7.13s/it]
                                                           
{'loss': 0.6211, 'learning_rate': 0.0003073156520076059, 'epoch': 5.32}

 44%|████▍     | 12456/28080 [24:36:48<30:55:59,  7.13s/it]
 44%|████▍     | 12457/28080 [24:36:55<30:53:31,  7.12s/it]
                                                           
{'loss': 0.6135, 'learning_rate': 0.0003072875839693944, 'epoch': 5.32}

 44%|████▍     | 12457/28080 [24:36:55<30:53:31,  7.12s/it]
 44%|████▍     | 12458/28080 [24:37:02<30:52:59,  7.12s/it]
                                                           
{'loss': 0.6103, 'learning_rate': 0.00030725951516903064, 'epoch': 5.32}

 44%|████▍     | 12458/28080 [24:37:02<30:52:59,  7.12s/it]
 44%|████▍     | 12459/28080 [24:37:09<30:59:04,  7.14s/it]
                                                           
{'loss': 0.6193, 'learning_rate': 0.0003072314456068881, 'epoch': 5.32}

 44%|████▍     | 12459/28080 [24:37:09<30:59:04,  7.14s/it]
 44%|████▍     | 12460/28080 [24:37:17<30:54:59,  7.13s/it]
                                                           
{'loss': 0.6179, 'learning_rate': 0.00030720337528334024, 'epoch': 5.32}

 44%|████▍     | 12460/28080 [24:37:17<30:54:59,  7.13s/it]
 44%|████▍     | 12461/28080 [24:37:24<30:56:29,  7.13s/it]
                                                           
{'loss': 0.6292, 'learning_rate': 0.0003071753041987605, 'epoch': 5.32}

 44%|████▍     | 12461/28080 [24:37:24<30:56:29,  7.13s/it]
 44%|████▍     | 12462/28080 [24:37:31<31:06:32,  7.17s/it]
                                                           
{'loss': 0.647, 'learning_rate': 0.0003071472323535223, 'epoch': 5.32}

 44%|████▍     | 12462/28080 [24:37:31<31:06:32,  7.17s/it]
 44%|████▍     | 12463/28080 [24:37:38<31:09:28,  7.18s/it]
                                                           
{'loss': 0.6135, 'learning_rate': 0.0003071191597479991, 'epoch': 5.32}

 44%|████▍     | 12463/28080 [24:37:38<31:09:28,  7.18s/it]
 44%|████▍     | 12464/28080 [24:37:45<31:05:01,  7.17s/it]
                                                           
{'loss': 0.6289, 'learning_rate': 0.00030709108638256446, 'epoch': 5.32}

 44%|████▍     | 12464/28080 [24:37:45<31:05:01,  7.17s/it]
 44%|████▍     | 12465/28080 [24:37:52<30:54:21,  7.13s/it]
                                                           
{'loss': 0.6698, 'learning_rate': 0.00030706301225759175, 'epoch': 5.32}

 44%|████▍     | 12465/28080 [24:37:52<30:54:21,  7.13s/it]
 44%|████▍     | 12466/28080 [24:37:59<30:56:54,  7.14s/it]
                                                           
{'loss': 0.6204, 'learning_rate': 0.00030703493737345455, 'epoch': 5.33}

 44%|████▍     | 12466/28080 [24:37:59<30:56:54,  7.14s/it]
 44%|████▍     | 12467/28080 [24:38:07<30:59:35,  7.15s/it]
                                                           
{'loss': 0.6381, 'learning_rate': 0.00030700686173052637, 'epoch': 5.33}

 44%|████▍     | 12467/28080 [24:38:07<30:59:35,  7.15s/it]
 44%|████▍     | 12468/28080 [24:38:14<30:58:26,  7.14s/it]
                                                           
{'loss': 0.6454, 'learning_rate': 0.0003069787853291807, 'epoch': 5.33}

 44%|████▍     | 12468/28080 [24:38:14<30:58:26,  7.14s/it]
 44%|████▍     | 12469/28080 [24:38:21<30:52:25,  7.12s/it]
                                                           
{'loss': 0.6223, 'learning_rate': 0.0003069507081697911, 'epoch': 5.33}

 44%|████▍     | 12469/28080 [24:38:21<30:52:25,  7.12s/it]
 44%|████▍     | 12470/28080 [24:38:28<30:58:25,  7.14s/it]
                                                           
{'loss': 0.635, 'learning_rate': 0.000306922630252731, 'epoch': 5.33}

 44%|████▍     | 12470/28080 [24:38:28<30:58:25,  7.14s/it]
 44%|████▍     | 12471/28080 [24:38:35<30:48:21,  7.10s/it]
                                                           
{'loss': 0.6161, 'learning_rate': 0.00030689455157837417, 'epoch': 5.33}

 44%|████▍     | 12471/28080 [24:38:35<30:48:21,  7.10s/it]
 44%|████▍     | 12472/28080 [24:38:42<30:46:06,  7.10s/it]
                                                           
{'loss': 0.6249, 'learning_rate': 0.0003068664721470939, 'epoch': 5.33}

 44%|████▍     | 12472/28080 [24:38:42<30:46:06,  7.10s/it]
 44%|████▍     | 12473/28080 [24:38:49<30:46:41,  7.10s/it]
                                                           
{'loss': 0.6373, 'learning_rate': 0.0003068383919592639, 'epoch': 5.33}

 44%|████▍     | 12473/28080 [24:38:49<30:46:41,  7.10s/it]
 44%|████▍     | 12474/28080 [24:38:56<30:48:23,  7.11s/it]
                                                           
{'loss': 0.6391, 'learning_rate': 0.00030681031101525774, 'epoch': 5.33}

 44%|████▍     | 12474/28080 [24:38:56<30:48:23,  7.11s/it]
 44%|████▍     | 12475/28080 [24:39:03<30:49:01,  7.11s/it]
                                                           
{'loss': 0.6361, 'learning_rate': 0.00030678222931544897, 'epoch': 5.33}

 44%|████▍     | 12475/28080 [24:39:03<30:49:01,  7.11s/it]
 44%|████▍     | 12476/28080 [24:39:11<30:48:51,  7.11s/it]
                                                           
{'loss': 0.6009, 'learning_rate': 0.0003067541468602113, 'epoch': 5.33}

 44%|████▍     | 12476/28080 [24:39:11<30:48:51,  7.11s/it]
 44%|████▍     | 12477/28080 [24:39:18<30:48:01,  7.11s/it]
                                                           
{'loss': 0.6244, 'learning_rate': 0.00030672606364991824, 'epoch': 5.33}

 44%|████▍     | 12477/28080 [24:39:18<30:48:01,  7.11s/it]
 44%|████▍     | 12478/28080 [24:39:25<30:45:58,  7.10s/it]
                                                           
{'loss': 0.6236, 'learning_rate': 0.0003066979796849434, 'epoch': 5.33}

 44%|████▍     | 12478/28080 [24:39:25<30:45:58,  7.10s/it]
 44%|████▍     | 12479/28080 [24:39:32<30:48:26,  7.11s/it]
                                                           
{'loss': 0.6184, 'learning_rate': 0.00030666989496566037, 'epoch': 5.33}

 44%|████▍     | 12479/28080 [24:39:32<30:48:26,  7.11s/it]
 44%|████▍     | 12480/28080 [24:39:39<31:00:26,  7.16s/it]
                                                           
{'loss': 0.6135, 'learning_rate': 0.00030664180949244293, 'epoch': 5.33}

 44%|████▍     | 12480/28080 [24:39:39<31:00:26,  7.16s/it]
 44%|████▍     | 12481/28080 [24:39:46<31:00:25,  7.16s/it]
                                                           
{'loss': 0.6196, 'learning_rate': 0.00030661372326566466, 'epoch': 5.33}

 44%|████▍     | 12481/28080 [24:39:46<31:00:25,  7.16s/it]
 44%|████▍     | 12482/28080 [24:39:53<31:00:13,  7.16s/it]
                                                           
{'loss': 0.622, 'learning_rate': 0.00030658563628569916, 'epoch': 5.33}

 44%|████▍     | 12482/28080 [24:39:53<31:00:13,  7.16s/it]
 44%|████▍     | 12483/28080 [24:40:01<30:57:32,  7.15s/it]
                                                           
{'loss': 0.6182, 'learning_rate': 0.00030655754855292015, 'epoch': 5.33}

 44%|████▍     | 12483/28080 [24:40:01<30:57:32,  7.15s/it]
 44%|████▍     | 12484/28080 [24:40:08<30:56:20,  7.14s/it]
                                                           
{'loss': 0.608, 'learning_rate': 0.0003065294600677013, 'epoch': 5.33}

 44%|████▍     | 12484/28080 [24:40:08<30:56:20,  7.14s/it]
 44%|████▍     | 12485/28080 [24:40:15<30:52:23,  7.13s/it]
                                                           
{'loss': 0.6289, 'learning_rate': 0.0003065013708304163, 'epoch': 5.33}

 44%|████▍     | 12485/28080 [24:40:15<30:52:23,  7.13s/it]
 44%|████▍     | 12486/28080 [24:40:22<30:47:36,  7.11s/it]
                                                           
{'loss': 0.615, 'learning_rate': 0.0003064732808414389, 'epoch': 5.33}

 44%|████▍     | 12486/28080 [24:40:22<30:47:36,  7.11s/it]
 44%|████▍     | 12487/28080 [24:40:29<31:00:05,  7.16s/it]
                                                           
{'loss': 0.6015, 'learning_rate': 0.0003064451901011427, 'epoch': 5.33}

 44%|████▍     | 12487/28080 [24:40:29<31:00:05,  7.16s/it]
 44%|████▍     | 12488/28080 [24:40:36<30:54:31,  7.14s/it]
                                                           
{'loss': 0.6102, 'learning_rate': 0.0003064170986099015, 'epoch': 5.33}

 44%|████▍     | 12488/28080 [24:40:36<30:54:31,  7.14s/it]
 44%|████▍     | 12489/28080 [24:40:43<31:01:17,  7.16s/it]
                                                           
{'loss': 0.623, 'learning_rate': 0.000306389006368089, 'epoch': 5.34}

 44%|████▍     | 12489/28080 [24:40:43<31:01:17,  7.16s/it]
 44%|████▍     | 12490/28080 [24:40:51<31:00:12,  7.16s/it]
                                                           
{'loss': 0.6223, 'learning_rate': 0.000306360913376079, 'epoch': 5.34}

 44%|████▍     | 12490/28080 [24:40:51<31:00:12,  7.16s/it]
 44%|████▍     | 12491/28080 [24:40:58<30:53:43,  7.13s/it]
                                                           
{'loss': 0.6218, 'learning_rate': 0.0003063328196342452, 'epoch': 5.34}

 44%|████▍     | 12491/28080 [24:40:58<30:53:43,  7.13s/it]
 44%|████▍     | 12492/28080 [24:41:05<30:57:56,  7.15s/it]
                                                           
{'loss': 0.6205, 'learning_rate': 0.0003063047251429613, 'epoch': 5.34}

 44%|████▍     | 12492/28080 [24:41:05<30:57:56,  7.15s/it]
 44%|████▍     | 12493/28080 [24:41:12<30:55:35,  7.14s/it]
                                                           
{'loss': 0.631, 'learning_rate': 0.0003062766299026011, 'epoch': 5.34}

 44%|████▍     | 12493/28080 [24:41:12<30:55:35,  7.14s/it]
 44%|████▍     | 12494/28080 [24:41:19<30:51:33,  7.13s/it]
                                                           
{'loss': 0.6259, 'learning_rate': 0.0003062485339135384, 'epoch': 5.34}

 44%|████▍     | 12494/28080 [24:41:19<30:51:33,  7.13s/it]
 44%|████▍     | 12495/28080 [24:41:26<30:52:43,  7.13s/it]
                                                           
{'loss': 0.6211, 'learning_rate': 0.000306220437176147, 'epoch': 5.34}

 44%|████▍     | 12495/28080 [24:41:26<30:52:43,  7.13s/it]
 45%|████▍     | 12496/28080 [24:41:33<30:49:48,  7.12s/it]
                                                           
{'loss': 0.6386, 'learning_rate': 0.00030619233969080066, 'epoch': 5.34}

 45%|████▍     | 12496/28080 [24:41:33<30:49:48,  7.12s/it]
 45%|████▍     | 12497/28080 [24:41:40<30:51:05,  7.13s/it]
                                                           
{'loss': 0.6284, 'learning_rate': 0.0003061642414578732, 'epoch': 5.34}

 45%|████▍     | 12497/28080 [24:41:40<30:51:05,  7.13s/it]
 45%|████▍     | 12498/28080 [24:41:48<30:51:09,  7.13s/it]
                                                           
{'loss': 0.6021, 'learning_rate': 0.0003061361424777385, 'epoch': 5.34}

 45%|████▍     | 12498/28080 [24:41:48<30:51:09,  7.13s/it]
 45%|████▍     | 12499/28080 [24:41:55<30:48:06,  7.12s/it]
                                                           
{'loss': 0.6161, 'learning_rate': 0.0003061080427507703, 'epoch': 5.34}

 45%|████▍     | 12499/28080 [24:41:55<30:48:06,  7.12s/it]
 45%|████▍     | 12500/28080 [24:42:02<30:52:23,  7.13s/it]
                                                           
{'loss': 0.6195, 'learning_rate': 0.00030607994227734253, 'epoch': 5.34}

 45%|████▍     | 12500/28080 [24:42:02<30:52:23,  7.13s/it]
 45%|████▍     | 12501/28080 [24:42:09<30:58:02,  7.16s/it]
                                                           
{'loss': 0.6349, 'learning_rate': 0.0003060518410578289, 'epoch': 5.34}

 45%|████▍     | 12501/28080 [24:42:09<30:58:02,  7.16s/it]
 45%|████▍     | 12502/28080 [24:42:16<30:47:36,  7.12s/it]
                                                           
{'loss': 0.5954, 'learning_rate': 0.00030602373909260346, 'epoch': 5.34}

 45%|████▍     | 12502/28080 [24:42:16<30:47:36,  7.12s/it]
 45%|████▍     | 12503/28080 [24:42:23<30:37:55,  7.08s/it]
                                                           
{'loss': 0.6347, 'learning_rate': 0.0003059956363820399, 'epoch': 5.34}

 45%|████▍     | 12503/28080 [24:42:23<30:37:55,  7.08s/it]
 45%|████▍     | 12504/28080 [24:42:30<30:44:16,  7.10s/it]
                                                           
{'loss': 0.6457, 'learning_rate': 0.0003059675329265121, 'epoch': 5.34}

 45%|████▍     | 12504/28080 [24:42:30<30:44:16,  7.10s/it]
 45%|████▍     | 12505/28080 [24:42:37<30:42:13,  7.10s/it]
                                                           
{'loss': 0.6253, 'learning_rate': 0.0003059394287263941, 'epoch': 5.34}

 45%|████▍     | 12505/28080 [24:42:37<30:42:13,  7.10s/it]
 45%|████▍     | 12506/28080 [24:42:44<30:43:35,  7.10s/it]
                                                           
{'loss': 0.6167, 'learning_rate': 0.00030591132378205967, 'epoch': 5.34}

 45%|████▍     | 12506/28080 [24:42:44<30:43:35,  7.10s/it]
 45%|████▍     | 12507/28080 [24:42:52<30:51:49,  7.13s/it]
                                                           
{'loss': 0.6198, 'learning_rate': 0.0003058832180938828, 'epoch': 5.34}

 45%|████▍     | 12507/28080 [24:42:52<30:51:49,  7.13s/it]
 45%|████▍     | 12508/28080 [24:42:59<30:57:35,  7.16s/it]
                                                           
{'loss': 0.644, 'learning_rate': 0.0003058551116622373, 'epoch': 5.34}

 45%|████▍     | 12508/28080 [24:42:59<30:57:35,  7.16s/it]
 45%|████▍     | 12509/28080 [24:43:06<30:49:04,  7.13s/it]
                                                           
{'loss': 0.628, 'learning_rate': 0.00030582700448749723, 'epoch': 5.34}

 45%|████▍     | 12509/28080 [24:43:06<30:49:04,  7.13s/it]
 45%|████▍     | 12510/28080 [24:43:13<30:53:46,  7.14s/it]
                                                           
{'loss': 0.6189, 'learning_rate': 0.0003057988965700364, 'epoch': 5.34}

 45%|████▍     | 12510/28080 [24:43:13<30:53:46,  7.14s/it]
 45%|████▍     | 12511/28080 [24:43:20<30:49:18,  7.13s/it]
                                                           
{'loss': 0.612, 'learning_rate': 0.00030577078791022884, 'epoch': 5.34}

 45%|████▍     | 12511/28080 [24:43:20<30:49:18,  7.13s/it]
 45%|████▍     | 12512/28080 [24:43:27<30:46:58,  7.12s/it]
                                                           
{'loss': 0.6093, 'learning_rate': 0.0003057426785084485, 'epoch': 5.35}

 45%|████▍     | 12512/28080 [24:43:27<30:46:58,  7.12s/it]
 45%|████▍     | 12513/28080 [24:43:34<30:47:50,  7.12s/it]
                                                           
{'loss': 0.6429, 'learning_rate': 0.00030571456836506926, 'epoch': 5.35}

 45%|████▍     | 12513/28080 [24:43:34<30:47:50,  7.12s/it]
 45%|████▍     | 12514/28080 [24:43:42<30:48:00,  7.12s/it]
                                                           
{'loss': 0.6238, 'learning_rate': 0.0003056864574804653, 'epoch': 5.35}

 45%|████▍     | 12514/28080 [24:43:42<30:48:00,  7.12s/it]
 45%|████▍     | 12515/28080 [24:43:49<30:50:52,  7.13s/it]
                                                           
{'loss': 0.6053, 'learning_rate': 0.0003056583458550104, 'epoch': 5.35}

 45%|████▍     | 12515/28080 [24:43:49<30:50:52,  7.13s/it]
 45%|████▍     | 12516/28080 [24:43:56<30:52:39,  7.14s/it]
                                                           
{'loss': 0.61, 'learning_rate': 0.0003056302334890786, 'epoch': 5.35}

 45%|████▍     | 12516/28080 [24:43:56<30:52:39,  7.14s/it]
 45%|████▍     | 12517/28080 [24:44:03<30:48:04,  7.12s/it]
                                                           
{'loss': 0.6106, 'learning_rate': 0.000305602120383044, 'epoch': 5.35}

 45%|████▍     | 12517/28080 [24:44:03<30:48:04,  7.12s/it]
 45%|████▍     | 12518/28080 [24:44:10<30:44:17,  7.11s/it]
                                                           
{'loss': 0.6422, 'learning_rate': 0.0003055740065372805, 'epoch': 5.35}

 45%|████▍     | 12518/28080 [24:44:10<30:44:17,  7.11s/it]
 45%|████▍     | 12519/28080 [24:44:17<30:38:36,  7.09s/it]
                                                           
{'loss': 0.6679, 'learning_rate': 0.0003055458919521622, 'epoch': 5.35}

 45%|████▍     | 12519/28080 [24:44:17<30:38:36,  7.09s/it]
 45%|████▍     | 12520/28080 [24:44:24<30:40:50,  7.10s/it]
                                                           
{'loss': 0.6398, 'learning_rate': 0.00030551777662806307, 'epoch': 5.35}

 45%|████▍     | 12520/28080 [24:44:24<30:40:50,  7.10s/it]
 45%|████▍     | 12521/28080 [24:44:31<30:43:35,  7.11s/it]
                                                           
{'loss': 0.6234, 'learning_rate': 0.00030548966056535723, 'epoch': 5.35}

 45%|████▍     | 12521/28080 [24:44:31<30:43:35,  7.11s/it]
 45%|████▍     | 12522/28080 [24:44:38<30:39:18,  7.09s/it]
                                                           
{'loss': 0.6222, 'learning_rate': 0.00030546154376441873, 'epoch': 5.35}

 45%|████▍     | 12522/28080 [24:44:38<30:39:18,  7.09s/it]
 45%|████▍     | 12523/28080 [24:44:46<30:48:02,  7.13s/it]
                                                           
{'loss': 0.6245, 'learning_rate': 0.0003054334262256215, 'epoch': 5.35}

 45%|████▍     | 12523/28080 [24:44:46<30:48:02,  7.13s/it]
 45%|████▍     | 12524/28080 [24:44:53<31:00:41,  7.18s/it]
                                                           
{'loss': 0.6132, 'learning_rate': 0.00030540530794933977, 'epoch': 5.35}

 45%|████▍     | 12524/28080 [24:44:53<31:00:41,  7.18s/it]
 45%|████▍     | 12525/28080 [24:45:00<31:02:12,  7.18s/it]
                                                           
{'loss': 0.6503, 'learning_rate': 0.00030537718893594763, 'epoch': 5.35}

 45%|████▍     | 12525/28080 [24:45:00<31:02:12,  7.18s/it]
 45%|████▍     | 12526/28080 [24:45:07<30:51:27,  7.14s/it]
                                                           
{'loss': 0.6033, 'learning_rate': 0.00030534906918581914, 'epoch': 5.35}

 45%|████▍     | 12526/28080 [24:45:07<30:51:27,  7.14s/it]
 45%|████▍     | 12527/28080 [24:45:14<30:49:26,  7.13s/it]
                                                           
{'loss': 0.6382, 'learning_rate': 0.0003053209486993282, 'epoch': 5.35}

 45%|████▍     | 12527/28080 [24:45:14<30:49:26,  7.13s/it]
 45%|████▍     | 12528/28080 [24:45:21<30:54:49,  7.16s/it]
                                                           
{'loss': 0.6319, 'learning_rate': 0.0003052928274768493, 'epoch': 5.35}

 45%|████▍     | 12528/28080 [24:45:21<30:54:49,  7.16s/it]
 45%|████▍     | 12529/28080 [24:45:29<30:57:25,  7.17s/it]
                                                           
{'loss': 0.6474, 'learning_rate': 0.00030526470551875634, 'epoch': 5.35}

 45%|████▍     | 12529/28080 [24:45:29<30:57:25,  7.17s/it]
 45%|████▍     | 12530/28080 [24:45:36<30:48:39,  7.13s/it]
                                                           
{'loss': 0.6292, 'learning_rate': 0.0003052365828254234, 'epoch': 5.35}

 45%|████▍     | 12530/28080 [24:45:36<30:48:39,  7.13s/it]
 45%|████▍     | 12531/28080 [24:45:43<30:47:38,  7.13s/it]
                                                           
{'loss': 0.6392, 'learning_rate': 0.0003052084593972248, 'epoch': 5.35}

 45%|████▍     | 12531/28080 [24:45:43<30:47:38,  7.13s/it]
 45%|████▍     | 12532/28080 [24:45:50<30:47:28,  7.13s/it]
                                                           
{'loss': 0.6271, 'learning_rate': 0.0003051803352345346, 'epoch': 5.35}

 45%|████▍     | 12532/28080 [24:45:50<30:47:28,  7.13s/it]
 45%|████▍     | 12533/28080 [24:45:57<30:53:28,  7.15s/it]
                                                           
{'loss': 0.645, 'learning_rate': 0.00030515221033772694, 'epoch': 5.35}

 45%|████▍     | 12533/28080 [24:45:57<30:53:28,  7.15s/it]
 45%|████▍     | 12534/28080 [24:46:04<30:51:37,  7.15s/it]
                                                           
{'loss': 0.6373, 'learning_rate': 0.000305124084707176, 'epoch': 5.35}

 45%|████▍     | 12534/28080 [24:46:04<30:51:37,  7.15s/it]
 45%|████▍     | 12535/28080 [24:46:11<30:51:47,  7.15s/it]
                                                           
{'loss': 0.6522, 'learning_rate': 0.000305095958343256, 'epoch': 5.35}

 45%|████▍     | 12535/28080 [24:46:11<30:51:47,  7.15s/it]
 45%|████▍     | 12536/28080 [24:46:19<30:48:17,  7.13s/it]
                                                           
{'loss': 0.6206, 'learning_rate': 0.00030506783124634114, 'epoch': 5.36}

 45%|████▍     | 12536/28080 [24:46:19<30:48:17,  7.13s/it]
 45%|████▍     | 12537/28080 [24:46:26<30:36:20,  7.09s/it]
                                                           
{'loss': 0.6356, 'learning_rate': 0.00030503970341680555, 'epoch': 5.36}

 45%|████▍     | 12537/28080 [24:46:26<30:36:20,  7.09s/it]
 45%|████▍     | 12538/28080 [24:46:33<30:38:31,  7.10s/it]
                                                           
{'loss': 0.6145, 'learning_rate': 0.0003050115748550235, 'epoch': 5.36}

 45%|████▍     | 12538/28080 [24:46:33<30:38:31,  7.10s/it]
 45%|████▍     | 12539/28080 [24:46:40<30:47:44,  7.13s/it]
                                                           
{'loss': 0.6279, 'learning_rate': 0.0003049834455613692, 'epoch': 5.36}

 45%|████▍     | 12539/28080 [24:46:40<30:47:44,  7.13s/it]
 45%|████▍     | 12540/28080 [24:46:47<30:46:15,  7.13s/it]
                                                           
{'loss': 0.6256, 'learning_rate': 0.00030495531553621693, 'epoch': 5.36}

 45%|████▍     | 12540/28080 [24:46:47<30:46:15,  7.13s/it]
 45%|████▍     | 12541/28080 [24:46:54<30:45:30,  7.13s/it]
                                                           
{'loss': 0.6299, 'learning_rate': 0.00030492718477994084, 'epoch': 5.36}

 45%|████▍     | 12541/28080 [24:46:54<30:45:30,  7.13s/it]
 45%|████▍     | 12542/28080 [24:47:01<30:45:38,  7.13s/it]
                                                           
{'loss': 0.6178, 'learning_rate': 0.0003048990532929152, 'epoch': 5.36}

 45%|████▍     | 12542/28080 [24:47:01<30:45:38,  7.13s/it]
 45%|████▍     | 12543/28080 [24:47:08<30:44:21,  7.12s/it]
                                                           
{'loss': 0.6267, 'learning_rate': 0.00030487092107551436, 'epoch': 5.36}

 45%|████▍     | 12543/28080 [24:47:08<30:44:21,  7.12s/it]
 45%|████▍     | 12544/28080 [24:47:16<30:47:33,  7.14s/it]
                                                           
{'loss': 0.6129, 'learning_rate': 0.0003048427881281124, 'epoch': 5.36}

 45%|████▍     | 12544/28080 [24:47:16<30:47:33,  7.14s/it]
 45%|████▍     | 12545/28080 [24:47:23<30:40:34,  7.11s/it]
                                                           
{'loss': 0.6322, 'learning_rate': 0.0003048146544510838, 'epoch': 5.36}

 45%|████▍     | 12545/28080 [24:47:23<30:40:34,  7.11s/it]
 45%|████▍     | 12546/28080 [24:47:30<30:37:54,  7.10s/it]
                                                           
{'loss': 0.589, 'learning_rate': 0.00030478652004480277, 'epoch': 5.36}

 45%|████▍     | 12546/28080 [24:47:30<30:37:54,  7.10s/it]
 45%|████▍     | 12547/28080 [24:47:37<30:47:38,  7.14s/it]
                                                           
{'loss': 0.6174, 'learning_rate': 0.00030475838490964357, 'epoch': 5.36}

 45%|████▍     | 12547/28080 [24:47:37<30:47:38,  7.14s/it]
 45%|████▍     | 12548/28080 [24:47:44<30:50:31,  7.15s/it]
                                                           
{'loss': 0.6283, 'learning_rate': 0.00030473024904598063, 'epoch': 5.36}

 45%|████▍     | 12548/28080 [24:47:44<30:50:31,  7.15s/it]
 45%|████▍     | 12549/28080 [24:47:51<30:43:29,  7.12s/it]
                                                           
{'loss': 0.6118, 'learning_rate': 0.0003047021124541881, 'epoch': 5.36}

 45%|████▍     | 12549/28080 [24:47:51<30:43:29,  7.12s/it]
 45%|████▍     | 12550/28080 [24:47:58<30:48:49,  7.14s/it]
                                                           
{'loss': 0.6258, 'learning_rate': 0.0003046739751346405, 'epoch': 5.36}

 45%|████▍     | 12550/28080 [24:47:58<30:48:49,  7.14s/it]
 45%|████▍     | 12551/28080 [24:48:05<30:44:32,  7.13s/it]
                                                           
{'loss': 0.6335, 'learning_rate': 0.000304645837087712, 'epoch': 5.36}

 45%|████▍     | 12551/28080 [24:48:05<30:44:32,  7.13s/it]
 45%|████▍     | 12552/28080 [24:48:12<30:42:51,  7.12s/it]
                                                           
{'loss': 0.6323, 'learning_rate': 0.00030461769831377695, 'epoch': 5.36}

 45%|████▍     | 12552/28080 [24:48:12<30:42:51,  7.12s/it]
 45%|████▍     | 12553/28080 [24:48:20<30:40:36,  7.11s/it]
                                                           
{'loss': 0.6379, 'learning_rate': 0.00030458955881320986, 'epoch': 5.36}

 45%|████▍     | 12553/28080 [24:48:20<30:40:36,  7.11s/it]
 45%|████▍     | 12554/28080 [24:48:27<30:38:19,  7.10s/it]
                                                           
{'loss': 0.6177, 'learning_rate': 0.00030456141858638497, 'epoch': 5.36}

 45%|████▍     | 12554/28080 [24:48:27<30:38:19,  7.10s/it]
 45%|████▍     | 12555/28080 [24:48:34<30:39:29,  7.11s/it]
                                                           
{'loss': 0.6022, 'learning_rate': 0.0003045332776336768, 'epoch': 5.36}

 45%|████▍     | 12555/28080 [24:48:34<30:39:29,  7.11s/it]
 45%|████▍     | 12556/28080 [24:48:41<30:36:42,  7.10s/it]
                                                           
{'loss': 0.6284, 'learning_rate': 0.00030450513595545945, 'epoch': 5.36}

 45%|████▍     | 12556/28080 [24:48:41<30:36:42,  7.10s/it]
 45%|████▍     | 12557/28080 [24:48:48<30:36:10,  7.10s/it]
                                                           
{'loss': 0.6546, 'learning_rate': 0.00030447699355210764, 'epoch': 5.36}

 45%|████▍     | 12557/28080 [24:48:48<30:36:10,  7.10s/it]
 45%|████▍     | 12558/28080 [24:48:55<30:25:00,  7.05s/it]
                                                           
{'loss': 0.6244, 'learning_rate': 0.00030444885042399557, 'epoch': 5.36}

 45%|████▍     | 12558/28080 [24:48:55<30:25:00,  7.05s/it]
 45%|████▍     | 12559/28080 [24:49:02<30:41:09,  7.12s/it]
                                                           
{'loss': 0.6232, 'learning_rate': 0.00030442070657149767, 'epoch': 5.37}

 45%|████▍     | 12559/28080 [24:49:02<30:41:09,  7.12s/it]
 45%|████▍     | 12560/28080 [24:49:09<30:35:06,  7.09s/it]
                                                           
{'loss': 0.6504, 'learning_rate': 0.0003043925619949885, 'epoch': 5.37}

 45%|████▍     | 12560/28080 [24:49:09<30:35:06,  7.09s/it]
 45%|████▍     | 12561/28080 [24:49:16<30:35:34,  7.10s/it]
                                                           
{'loss': 0.6422, 'learning_rate': 0.0003043644166948423, 'epoch': 5.37}

 45%|████▍     | 12561/28080 [24:49:16<30:35:34,  7.10s/it]
 45%|████▍     | 12562/28080 [24:49:24<30:44:49,  7.13s/it]
                                                           
{'loss': 0.6291, 'learning_rate': 0.0003043362706714338, 'epoch': 5.37}

 45%|████▍     | 12562/28080 [24:49:24<30:44:49,  7.13s/it]
 45%|████▍     | 12563/28080 [24:49:31<30:39:05,  7.11s/it]
                                                           
{'loss': 0.6391, 'learning_rate': 0.0003043081239251371, 'epoch': 5.37}

 45%|████▍     | 12563/28080 [24:49:31<30:39:05,  7.11s/it]
 45%|████▍     | 12564/28080 [24:49:38<30:33:06,  7.09s/it]
                                                           
{'loss': 0.621, 'learning_rate': 0.00030427997645632695, 'epoch': 5.37}

 45%|████▍     | 12564/28080 [24:49:38<30:33:06,  7.09s/it]
 45%|████▍     | 12565/28080 [24:49:45<30:39:09,  7.11s/it]
                                                           
{'loss': 0.6392, 'learning_rate': 0.0003042518282653777, 'epoch': 5.37}

 45%|████▍     | 12565/28080 [24:49:45<30:39:09,  7.11s/it]
 45%|████▍     | 12566/28080 [24:49:52<30:34:53,  7.10s/it]
                                                           
{'loss': 0.6149, 'learning_rate': 0.00030422367935266375, 'epoch': 5.37}

 45%|████▍     | 12566/28080 [24:49:52<30:34:53,  7.10s/it]
 45%|████▍     | 12567/28080 [24:49:59<30:34:33,  7.10s/it]
                                                           
{'loss': 0.6228, 'learning_rate': 0.0003041955297185598, 'epoch': 5.37}

 45%|████▍     | 12567/28080 [24:49:59<30:34:33,  7.10s/it]
 45%|████▍     | 12568/28080 [24:50:06<30:27:40,  7.07s/it]
                                                           
{'loss': 0.6432, 'learning_rate': 0.0003041673793634402, 'epoch': 5.37}

 45%|████▍     | 12568/28080 [24:50:06<30:27:40,  7.07s/it]
 45%|████▍     | 12569/28080 [24:50:13<30:34:47,  7.10s/it]
                                                           
{'loss': 0.6634, 'learning_rate': 0.00030413922828767943, 'epoch': 5.37}

 45%|████▍     | 12569/28080 [24:50:13<30:34:47,  7.10s/it]
 45%|████▍     | 12570/28080 [24:50:20<30:34:10,  7.10s/it]
                                                           
{'loss': 0.6287, 'learning_rate': 0.0003041110764916521, 'epoch': 5.37}

 45%|████▍     | 12570/28080 [24:50:20<30:34:10,  7.10s/it]
 45%|████▍     | 12571/28080 [24:50:27<30:34:38,  7.10s/it]
                                                           
{'loss': 0.6287, 'learning_rate': 0.0003040829239757328, 'epoch': 5.37}

 45%|████▍     | 12571/28080 [24:50:27<30:34:38,  7.10s/it]
 45%|████▍     | 12572/28080 [24:50:34<30:34:18,  7.10s/it]
                                                           
{'loss': 0.6127, 'learning_rate': 0.00030405477074029597, 'epoch': 5.37}

 45%|████▍     | 12572/28080 [24:50:34<30:34:18,  7.10s/it]
 45%|████▍     | 12573/28080 [24:50:42<30:39:20,  7.12s/it]
                                                           
{'loss': 0.6337, 'learning_rate': 0.0003040266167857161, 'epoch': 5.37}

 45%|████▍     | 12573/28080 [24:50:42<30:39:20,  7.12s/it]
 45%|████▍     | 12574/28080 [24:50:49<30:41:42,  7.13s/it]
                                                           
{'loss': 0.6081, 'learning_rate': 0.00030399846211236794, 'epoch': 5.37}

 45%|████▍     | 12574/28080 [24:50:49<30:41:42,  7.13s/it]
 45%|████▍     | 12575/28080 [24:50:56<30:45:00,  7.14s/it]
                                                           
{'loss': 0.6235, 'learning_rate': 0.00030397030672062587, 'epoch': 5.37}

 45%|████▍     | 12575/28080 [24:50:56<30:45:00,  7.14s/it]
 45%|████▍     | 12576/28080 [24:51:03<30:48:08,  7.15s/it]
                                                           
{'loss': 0.6382, 'learning_rate': 0.0003039421506108645, 'epoch': 5.37}

 45%|████▍     | 12576/28080 [24:51:03<30:48:08,  7.15s/it]
 45%|████▍     | 12577/28080 [24:51:10<30:48:14,  7.15s/it]
                                                           
{'loss': 0.6228, 'learning_rate': 0.0003039139937834586, 'epoch': 5.37}

 45%|████▍     | 12577/28080 [24:51:10<30:48:14,  7.15s/it]
 45%|████▍     | 12578/28080 [24:51:17<30:42:18,  7.13s/it]
                                                           
{'loss': 0.6181, 'learning_rate': 0.00030388583623878253, 'epoch': 5.37}

 45%|████▍     | 12578/28080 [24:51:17<30:42:18,  7.13s/it]
 45%|████▍     | 12579/28080 [24:51:24<30:47:07,  7.15s/it]
                                                           
{'loss': 0.6278, 'learning_rate': 0.00030385767797721104, 'epoch': 5.37}

 45%|████▍     | 12579/28080 [24:51:24<30:47:07,  7.15s/it]
 45%|████▍     | 12580/28080 [24:51:32<30:49:31,  7.16s/it]
                                                           
{'loss': 0.6171, 'learning_rate': 0.00030382951899911873, 'epoch': 5.37}

 45%|████▍     | 12580/28080 [24:51:32<30:49:31,  7.16s/it]
 45%|████▍     | 12581/28080 [24:51:39<30:46:51,  7.15s/it]
                                                           
{'loss': 0.6214, 'learning_rate': 0.0003038013593048802, 'epoch': 5.37}

 45%|████▍     | 12581/28080 [24:51:39<30:46:51,  7.15s/it]
 45%|████▍     | 12582/28080 [24:51:46<30:46:51,  7.15s/it]
                                                           
{'loss': 0.62, 'learning_rate': 0.00030377319889487, 'epoch': 5.37}

 45%|████▍     | 12582/28080 [24:51:46<30:46:51,  7.15s/it]
 45%|████▍     | 12583/28080 [24:51:53<30:44:20,  7.14s/it]
                                                           
{'loss': 0.6166, 'learning_rate': 0.00030374503776946286, 'epoch': 5.38}

 45%|████▍     | 12583/28080 [24:51:53<30:44:20,  7.14s/it]
 45%|████▍     | 12584/28080 [24:52:00<30:27:48,  7.08s/it]
                                                           
{'loss': 0.6259, 'learning_rate': 0.00030371687592903356, 'epoch': 5.38}

 45%|████▍     | 12584/28080 [24:52:00<30:27:48,  7.08s/it]
 45%|████▍     | 12585/28080 [24:52:07<30:30:12,  7.09s/it]
                                                           
{'loss': 0.6321, 'learning_rate': 0.00030368871337395657, 'epoch': 5.38}

 45%|████▍     | 12585/28080 [24:52:07<30:30:12,  7.09s/it]
 45%|████▍     | 12586/28080 [24:52:14<30:33:49,  7.10s/it]
                                                           
{'loss': 0.6322, 'learning_rate': 0.0003036605501046067, 'epoch': 5.38}

 45%|████▍     | 12586/28080 [24:52:14<30:33:49,  7.10s/it]
 45%|████▍     | 12587/28080 [24:52:21<30:39:59,  7.13s/it]
                                                           
{'loss': 0.6347, 'learning_rate': 0.00030363238612135854, 'epoch': 5.38}

 45%|████▍     | 12587/28080 [24:52:21<30:39:59,  7.13s/it]
 45%|████▍     | 12588/28080 [24:52:29<30:35:32,  7.11s/it]
                                                           
{'loss': 0.6351, 'learning_rate': 0.00030360422142458674, 'epoch': 5.38}

 45%|████▍     | 12588/28080 [24:52:29<30:35:32,  7.11s/it]
 45%|████▍     | 12589/28080 [24:52:36<30:37:02,  7.12s/it]
                                                           
{'loss': 0.6462, 'learning_rate': 0.00030357605601466617, 'epoch': 5.38}

 45%|████▍     | 12589/28080 [24:52:36<30:37:02,  7.12s/it]
 45%|████▍     | 12590/28080 [24:52:43<30:41:48,  7.13s/it]
                                                           
{'loss': 0.6257, 'learning_rate': 0.0003035478898919714, 'epoch': 5.38}

 45%|████▍     | 12590/28080 [24:52:43<30:41:48,  7.13s/it]
 45%|████▍     | 12591/28080 [24:52:50<30:49:45,  7.17s/it]
                                                           
{'loss': 0.6256, 'learning_rate': 0.00030351972305687726, 'epoch': 5.38}

 45%|████▍     | 12591/28080 [24:52:50<30:49:45,  7.17s/it]
 45%|████▍     | 12592/28080 [24:52:57<30:43:14,  7.14s/it]
                                                           
{'loss': 0.6537, 'learning_rate': 0.00030349155550975834, 'epoch': 5.38}

 45%|████▍     | 12592/28080 [24:52:57<30:43:14,  7.14s/it]
 45%|████▍     | 12593/28080 [24:53:04<30:46:47,  7.15s/it]
                                                           
{'loss': 0.6269, 'learning_rate': 0.0003034633872509895, 'epoch': 5.38}

 45%|████▍     | 12593/28080 [24:53:04<30:46:47,  7.15s/it]
 45%|████▍     | 12594/28080 [24:53:11<30:46:12,  7.15s/it]
                                                           
{'loss': 0.6306, 'learning_rate': 0.0003034352182809454, 'epoch': 5.38}

 45%|████▍     | 12594/28080 [24:53:11<30:46:12,  7.15s/it]
 45%|████▍     | 12595/28080 [24:53:19<30:38:10,  7.12s/it]
                                                           
{'loss': 0.6212, 'learning_rate': 0.00030340704860000087, 'epoch': 5.38}

 45%|████▍     | 12595/28080 [24:53:19<30:38:10,  7.12s/it]
 45%|████▍     | 12596/28080 [24:53:26<30:43:41,  7.14s/it]
                                                           
{'loss': 0.6354, 'learning_rate': 0.00030337887820853067, 'epoch': 5.38}

 45%|████▍     | 12596/28080 [24:53:26<30:43:41,  7.14s/it]
 45%|████▍     | 12597/28080 [24:53:33<30:40:35,  7.13s/it]
                                                           
{'loss': 0.6326, 'learning_rate': 0.0003033507071069095, 'epoch': 5.38}

 45%|████▍     | 12597/28080 [24:53:33<30:40:35,  7.13s/it]
 45%|████▍     | 12598/28080 [24:53:40<30:39:52,  7.13s/it]
                                                           
{'loss': 0.6189, 'learning_rate': 0.0003033225352955123, 'epoch': 5.38}

 45%|████▍     | 12598/28080 [24:53:40<30:39:52,  7.13s/it]
 45%|████▍     | 12599/28080 [24:53:47<30:45:28,  7.15s/it]
                                                           
{'loss': 0.6341, 'learning_rate': 0.0003032943627747137, 'epoch': 5.38}

 45%|████▍     | 12599/28080 [24:53:47<30:45:28,  7.15s/it]
 45%|████▍     | 12600/28080 [24:53:54<30:43:51,  7.15s/it]
                                                           
{'loss': 0.6483, 'learning_rate': 0.0003032661895448886, 'epoch': 5.38}

 45%|████▍     | 12600/28080 [24:53:54<30:43:51,  7.15s/it]
 45%|████▍     | 12601/28080 [24:54:01<30:40:54,  7.14s/it]
                                                           
{'loss': 0.6202, 'learning_rate': 0.00030323801560641183, 'epoch': 5.38}

 45%|████▍     | 12601/28080 [24:54:01<30:40:54,  7.14s/it]
 45%|████▍     | 12602/28080 [24:54:09<30:40:28,  7.13s/it]
                                                           
{'loss': 0.6121, 'learning_rate': 0.0003032098409596582, 'epoch': 5.38}

 45%|████▍     | 12602/28080 [24:54:09<30:40:28,  7.13s/it]
 45%|████▍     | 12603/28080 [24:54:16<30:43:46,  7.15s/it]
                                                           
{'loss': 0.6313, 'learning_rate': 0.00030318166560500256, 'epoch': 5.38}

 45%|████▍     | 12603/28080 [24:54:16<30:43:46,  7.15s/it]
 45%|████▍     | 12604/28080 [24:54:23<30:34:09,  7.11s/it]
                                                           
{'loss': 0.6263, 'learning_rate': 0.0003031534895428196, 'epoch': 5.38}

 45%|████▍     | 12604/28080 [24:54:23<30:34:09,  7.11s/it]
 45%|████▍     | 12605/28080 [24:54:30<30:38:11,  7.13s/it]
                                                           
{'loss': 0.6093, 'learning_rate': 0.0003031253127734844, 'epoch': 5.38}

 45%|████▍     | 12605/28080 [24:54:30<30:38:11,  7.13s/it]
 45%|████▍     | 12606/28080 [24:54:37<30:37:57,  7.13s/it]
                                                           
{'loss': 0.6003, 'learning_rate': 0.0003030971352973717, 'epoch': 5.39}

 45%|████▍     | 12606/28080 [24:54:37<30:37:57,  7.13s/it]
 45%|████▍     | 12607/28080 [24:54:44<30:37:40,  7.13s/it]
                                                           
{'loss': 0.6317, 'learning_rate': 0.0003030689571148563, 'epoch': 5.39}

 45%|████▍     | 12607/28080 [24:54:44<30:37:40,  7.13s/it]
 45%|████▍     | 12608/28080 [24:54:51<30:43:42,  7.15s/it]
                                                           
{'loss': 0.6054, 'learning_rate': 0.00030304077822631333, 'epoch': 5.39}

 45%|████▍     | 12608/28080 [24:54:51<30:43:42,  7.15s/it]
 45%|████▍     | 12609/28080 [24:54:58<30:39:29,  7.13s/it]
                                                           
{'loss': 0.5999, 'learning_rate': 0.00030301259863211737, 'epoch': 5.39}

 45%|████▍     | 12609/28080 [24:54:58<30:39:29,  7.13s/it]
 45%|████▍     | 12610/28080 [24:55:06<30:40:05,  7.14s/it]
                                                           
{'loss': 0.6132, 'learning_rate': 0.0003029844183326436, 'epoch': 5.39}

 45%|████▍     | 12610/28080 [24:55:06<30:40:05,  7.14s/it]
 45%|████▍     | 12611/28080 [24:55:13<30:30:17,  7.10s/it]
                                                           
{'loss': 0.615, 'learning_rate': 0.00030295623732826674, 'epoch': 5.39}

 45%|████▍     | 12611/28080 [24:55:13<30:30:17,  7.10s/it]
 45%|████▍     | 12612/28080 [24:55:20<30:32:39,  7.11s/it]
                                                           
{'loss': 0.6279, 'learning_rate': 0.00030292805561936187, 'epoch': 5.39}

 45%|████▍     | 12612/28080 [24:55:20<30:32:39,  7.11s/it]
 45%|████▍     | 12613/28080 [24:55:27<30:31:10,  7.10s/it]
                                                           
{'loss': 0.6093, 'learning_rate': 0.0003028998732063037, 'epoch': 5.39}

 45%|████▍     | 12613/28080 [24:55:27<30:31:10,  7.10s/it]
 45%|████▍     | 12614/28080 [24:55:34<30:29:24,  7.10s/it]
                                                           
{'loss': 0.6099, 'learning_rate': 0.0003028716900894673, 'epoch': 5.39}

 45%|████▍     | 12614/28080 [24:55:34<30:29:24,  7.10s/it]
 45%|████▍     | 12615/28080 [24:55:41<30:37:16,  7.13s/it]
                                                           
{'loss': 0.6282, 'learning_rate': 0.0003028435062692277, 'epoch': 5.39}

 45%|████▍     | 12615/28080 [24:55:41<30:37:16,  7.13s/it]
 45%|████▍     | 12616/28080 [24:55:48<30:33:56,  7.12s/it]
                                                           
{'loss': 0.6287, 'learning_rate': 0.0003028153217459597, 'epoch': 5.39}

 45%|████▍     | 12616/28080 [24:55:48<30:33:56,  7.12s/it]
 45%|████▍     | 12617/28080 [24:55:55<30:28:41,  7.10s/it]
                                                           
{'loss': 0.6166, 'learning_rate': 0.00030278713652003844, 'epoch': 5.39}

 45%|████▍     | 12617/28080 [24:55:55<30:28:41,  7.10s/it]
 45%|████▍     | 12618/28080 [24:56:02<30:32:43,  7.11s/it]
                                                           
{'loss': 0.6188, 'learning_rate': 0.0003027589505918386, 'epoch': 5.39}

 45%|████▍     | 12618/28080 [24:56:02<30:32:43,  7.11s/it]
 45%|████▍     | 12619/28080 [24:56:10<30:38:58,  7.14s/it]
                                                           
{'loss': 0.6198, 'learning_rate': 0.0003027307639617354, 'epoch': 5.39}

 45%|████▍     | 12619/28080 [24:56:10<30:38:58,  7.14s/it]
 45%|████▍     | 12620/28080 [24:56:17<30:37:18,  7.13s/it]
                                                           
{'loss': 0.6344, 'learning_rate': 0.0003027025766301039, 'epoch': 5.39}

 45%|████▍     | 12620/28080 [24:56:17<30:37:18,  7.13s/it]
 45%|████▍     | 12621/28080 [24:56:24<30:43:10,  7.15s/it]
                                                           
{'loss': 0.6299, 'learning_rate': 0.0003026743885973189, 'epoch': 5.39}

 45%|████▍     | 12621/28080 [24:56:24<30:43:10,  7.15s/it]
 45%|████▍     | 12622/28080 [24:56:31<30:44:04,  7.16s/it]
                                                           
{'loss': 0.63, 'learning_rate': 0.00030264619986375554, 'epoch': 5.39}

 45%|████▍     | 12622/28080 [24:56:31<30:44:04,  7.16s/it]
 45%|████▍     | 12623/28080 [24:56:38<30:36:51,  7.13s/it]
                                                           
{'loss': 0.6207, 'learning_rate': 0.00030261801042978876, 'epoch': 5.39}

 45%|████▍     | 12623/28080 [24:56:38<30:36:51,  7.13s/it]
 45%|████▍     | 12624/28080 [24:56:45<30:32:37,  7.11s/it]
                                                           
{'loss': 0.6198, 'learning_rate': 0.0003025898202957936, 'epoch': 5.39}

 45%|████▍     | 12624/28080 [24:56:45<30:32:37,  7.11s/it]
 45%|████▍     | 12625/28080 [24:56:52<30:24:22,  7.08s/it]
                                                           
{'loss': 0.5992, 'learning_rate': 0.00030256162946214524, 'epoch': 5.39}

 45%|████▍     | 12625/28080 [24:56:52<30:24:22,  7.08s/it]
 45%|████▍     | 12626/28080 [24:56:59<30:35:56,  7.13s/it]
                                                           
{'loss': 0.6399, 'learning_rate': 0.0003025334379292185, 'epoch': 5.39}

 45%|████▍     | 12626/28080 [24:56:59<30:35:56,  7.13s/it]
 45%|████▍     | 12627/28080 [24:57:07<30:35:59,  7.13s/it]
                                                           
{'loss': 0.6423, 'learning_rate': 0.0003025052456973887, 'epoch': 5.39}

 45%|████▍     | 12627/28080 [24:57:07<30:35:59,  7.13s/it]
 45%|████▍     | 12628/28080 [24:57:14<30:36:30,  7.13s/it]
                                                           
{'loss': 0.6231, 'learning_rate': 0.00030247705276703065, 'epoch': 5.39}

 45%|████▍     | 12628/28080 [24:57:14<30:36:30,  7.13s/it]
 45%|████▍     | 12629/28080 [24:57:21<30:30:42,  7.11s/it]
                                                           
{'loss': 0.6291, 'learning_rate': 0.0003024488591385197, 'epoch': 5.39}

 45%|████▍     | 12629/28080 [24:57:21<30:30:42,  7.11s/it]
 45%|████▍     | 12630/28080 [24:57:28<30:38:31,  7.14s/it]
                                                           
{'loss': 0.615, 'learning_rate': 0.0003024206648122306, 'epoch': 5.4}

 45%|████▍     | 12630/28080 [24:57:28<30:38:31,  7.14s/it]
 45%|████▍     | 12631/28080 [24:57:35<30:33:43,  7.12s/it]
                                                           
{'loss': 0.6136, 'learning_rate': 0.00030239246978853876, 'epoch': 5.4}

 45%|████▍     | 12631/28080 [24:57:35<30:33:43,  7.12s/it]
 45%|████▍     | 12632/28080 [24:57:42<30:31:34,  7.11s/it]
                                                           
{'loss': 0.6189, 'learning_rate': 0.0003023642740678191, 'epoch': 5.4}

 45%|████▍     | 12632/28080 [24:57:42<30:31:34,  7.11s/it]
 45%|████▍     | 12633/28080 [24:57:49<30:35:18,  7.13s/it]
                                                           
{'loss': 0.6094, 'learning_rate': 0.0003023360776504468, 'epoch': 5.4}

 45%|████▍     | 12633/28080 [24:57:49<30:35:18,  7.13s/it]
 45%|████▍     | 12634/28080 [24:57:56<30:36:14,  7.13s/it]
                                                           
{'loss': 0.6159, 'learning_rate': 0.00030230788053679705, 'epoch': 5.4}

 45%|████▍     | 12634/28080 [24:57:56<30:36:14,  7.13s/it]
 45%|████▍     | 12635/28080 [24:58:04<30:38:19,  7.14s/it]
                                                           
{'loss': 0.6183, 'learning_rate': 0.0003022796827272448, 'epoch': 5.4}

 45%|████▍     | 12635/28080 [24:58:04<30:38:19,  7.14s/it]
 45%|████▌     | 12636/28080 [24:58:11<30:36:58,  7.14s/it]
                                                           
{'loss': 0.6121, 'learning_rate': 0.0003022514842221654, 'epoch': 5.4}

 45%|████▌     | 12636/28080 [24:58:11<30:36:58,  7.14s/it]
 45%|████▌     | 12637/28080 [24:58:18<30:38:27,  7.14s/it]
                                                           
{'loss': 0.6145, 'learning_rate': 0.00030222328502193385, 'epoch': 5.4}

 45%|████▌     | 12637/28080 [24:58:18<30:38:27,  7.14s/it]
 45%|████▌     | 12638/28080 [24:58:25<30:37:51,  7.14s/it]
                                                           
{'loss': 0.6122, 'learning_rate': 0.0003021950851269254, 'epoch': 5.4}

 45%|████▌     | 12638/28080 [24:58:25<30:37:51,  7.14s/it]
 45%|████▌     | 12639/28080 [24:58:32<30:38:49,  7.15s/it]
                                                           
{'loss': 0.6197, 'learning_rate': 0.0003021668845375152, 'epoch': 5.4}

 45%|████▌     | 12639/28080 [24:58:32<30:38:49,  7.15s/it]
 45%|████▌     | 12640/28080 [24:58:39<30:41:16,  7.16s/it]
                                                           
{'loss': 0.6309, 'learning_rate': 0.00030213868325407845, 'epoch': 5.4}

 45%|████▌     | 12640/28080 [24:58:39<30:41:16,  7.16s/it]
 45%|████▌     | 12641/28080 [24:58:47<30:38:49,  7.15s/it]
                                                           
{'loss': 0.6203, 'learning_rate': 0.00030211048127699023, 'epoch': 5.4}

 45%|████▌     | 12641/28080 [24:58:47<30:38:49,  7.15s/it]
 45%|████▌     | 12642/28080 [24:58:54<30:35:16,  7.13s/it]
                                                           
{'loss': 0.6209, 'learning_rate': 0.00030208227860662585, 'epoch': 5.4}

 45%|████▌     | 12642/28080 [24:58:54<30:35:16,  7.13s/it]
 45%|████▌     | 12643/28080 [24:59:01<30:38:19,  7.15s/it]
                                                           
{'loss': 0.5961, 'learning_rate': 0.0003020540752433605, 'epoch': 5.4}

 45%|████▌     | 12643/28080 [24:59:01<30:38:19,  7.15s/it]
 45%|████▌     | 12644/28080 [24:59:08<30:38:40,  7.15s/it]
                                                           
{'loss': 0.6263, 'learning_rate': 0.00030202587118756933, 'epoch': 5.4}

 45%|████▌     | 12644/28080 [24:59:08<30:38:40,  7.15s/it]
 45%|████▌     | 12645/28080 [24:59:15<30:40:45,  7.16s/it]
                                                           
{'loss': 0.6127, 'learning_rate': 0.0003019976664396277, 'epoch': 5.4}

 45%|████▌     | 12645/28080 [24:59:15<30:40:45,  7.16s/it]
 45%|████▌     | 12646/28080 [24:59:22<30:33:14,  7.13s/it]
                                                           
{'loss': 0.5992, 'learning_rate': 0.0003019694609999107, 'epoch': 5.4}

 45%|████▌     | 12646/28080 [24:59:22<30:33:14,  7.13s/it]
 45%|████▌     | 12647/28080 [24:59:29<30:28:55,  7.11s/it]
                                                           
{'loss': 0.618, 'learning_rate': 0.0003019412548687936, 'epoch': 5.4}

 45%|████▌     | 12647/28080 [24:59:29<30:28:55,  7.11s/it]
 45%|████▌     | 12648/28080 [24:59:36<30:34:11,  7.13s/it]
                                                           
{'loss': 0.6284, 'learning_rate': 0.00030191304804665173, 'epoch': 5.4}

 45%|████▌     | 12648/28080 [24:59:36<30:34:11,  7.13s/it]
 45%|████▌     | 12649/28080 [24:59:44<30:29:43,  7.11s/it]
                                                           
{'loss': 0.6241, 'learning_rate': 0.0003018848405338603, 'epoch': 5.4}

 45%|████▌     | 12649/28080 [24:59:44<30:29:43,  7.11s/it]
 45%|████▌     | 12650/28080 [24:59:51<30:28:14,  7.11s/it]
                                                           
{'loss': 0.6402, 'learning_rate': 0.00030185663233079464, 'epoch': 5.4}

 45%|████▌     | 12650/28080 [24:59:51<30:28:14,  7.11s/it]
 45%|████▌     | 12651/28080 [24:59:58<30:24:10,  7.09s/it]
                                                           
{'loss': 0.6485, 'learning_rate': 0.00030182842343782996, 'epoch': 5.4}

 45%|████▌     | 12651/28080 [24:59:58<30:24:10,  7.09s/it]
 45%|████▌     | 12652/28080 [25:00:05<30:31:50,  7.12s/it]
                                                           
{'loss': 0.6189, 'learning_rate': 0.0003018002138553415, 'epoch': 5.4}

 45%|████▌     | 12652/28080 [25:00:05<30:31:50,  7.12s/it]
 45%|████▌     | 12653/28080 [25:00:12<30:38:10,  7.15s/it]
                                                           
{'loss': 0.6233, 'learning_rate': 0.0003017720035837048, 'epoch': 5.41}

 45%|████▌     | 12653/28080 [25:00:12<30:38:10,  7.15s/it]
 45%|████▌     | 12654/28080 [25:00:19<30:34:03,  7.13s/it]
                                                           
{'loss': 0.6349, 'learning_rate': 0.00030174379262329484, 'epoch': 5.41}

 45%|████▌     | 12654/28080 [25:00:19<30:34:03,  7.13s/it]
 45%|████▌     | 12655/28080 [25:00:26<30:36:40,  7.14s/it]
                                                           
{'loss': 0.653, 'learning_rate': 0.0003017155809744872, 'epoch': 5.41}

 45%|████▌     | 12655/28080 [25:00:26<30:36:40,  7.14s/it]
 45%|████▌     | 12656/28080 [25:00:33<30:31:45,  7.13s/it]
                                                           
{'loss': 0.6096, 'learning_rate': 0.00030168736863765705, 'epoch': 5.41}

 45%|████▌     | 12656/28080 [25:00:33<30:31:45,  7.13s/it]
 45%|████▌     | 12657/28080 [25:00:41<30:38:04,  7.15s/it]
                                                           
{'loss': 0.6186, 'learning_rate': 0.00030165915561317975, 'epoch': 5.41}

 45%|████▌     | 12657/28080 [25:00:41<30:38:04,  7.15s/it]
 45%|████▌     | 12658/28080 [25:00:48<30:39:21,  7.16s/it]
                                                           
{'loss': 0.6162, 'learning_rate': 0.00030163094190143076, 'epoch': 5.41}

 45%|████▌     | 12658/28080 [25:00:48<30:39:21,  7.16s/it]
 45%|████▌     | 12659/28080 [25:00:55<30:29:57,  7.12s/it]
                                                           
{'loss': 0.6192, 'learning_rate': 0.0003016027275027853, 'epoch': 5.41}

 45%|████▌     | 12659/28080 [25:00:55<30:29:57,  7.12s/it]
 45%|████▌     | 12660/28080 [25:01:02<30:19:27,  7.08s/it]
                                                           
{'loss': 0.6297, 'learning_rate': 0.00030157451241761884, 'epoch': 5.41}

 45%|████▌     | 12660/28080 [25:01:02<30:19:27,  7.08s/it]
 45%|████▌     | 12661/28080 [25:01:09<30:16:01,  7.07s/it]
                                                           
{'loss': 0.6296, 'learning_rate': 0.00030154629664630667, 'epoch': 5.41}

 45%|████▌     | 12661/28080 [25:01:09<30:16:01,  7.07s/it]
 45%|████▌     | 12662/28080 [25:01:16<30:05:05,  7.02s/it]
                                                           
{'loss': 0.6264, 'learning_rate': 0.00030151808018922415, 'epoch': 5.41}

 45%|████▌     | 12662/28080 [25:01:16<30:05:05,  7.02s/it]
 45%|████▌     | 12663/28080 [25:01:23<30:03:26,  7.02s/it]
                                                           
{'loss': 0.6178, 'learning_rate': 0.0003014898630467468, 'epoch': 5.41}

 45%|████▌     | 12663/28080 [25:01:23<30:03:26,  7.02s/it]
 45%|████▌     | 12664/28080 [25:01:30<30:13:14,  7.06s/it]
                                                           
{'loss': 0.613, 'learning_rate': 0.00030146164521924993, 'epoch': 5.41}

 45%|████▌     | 12664/28080 [25:01:30<30:13:14,  7.06s/it]
 45%|████▌     | 12665/28080 [25:01:37<30:18:44,  7.08s/it]
                                                           
{'loss': 0.6154, 'learning_rate': 0.000301433426707109, 'epoch': 5.41}

 45%|████▌     | 12665/28080 [25:01:37<30:18:44,  7.08s/it]
 45%|████▌     | 12666/28080 [25:01:44<30:20:19,  7.09s/it]
                                                           
{'loss': 0.6179, 'learning_rate': 0.00030140520751069925, 'epoch': 5.41}

 45%|████▌     | 12666/28080 [25:01:44<30:20:19,  7.09s/it]
 45%|████▌     | 12667/28080 [25:01:51<30:17:07,  7.07s/it]
                                                           
{'loss': 0.629, 'learning_rate': 0.0003013769876303963, 'epoch': 5.41}

 45%|████▌     | 12667/28080 [25:01:51<30:17:07,  7.07s/it]
 45%|████▌     | 12668/28080 [25:01:58<30:19:28,  7.08s/it]
                                                           
{'loss': 0.6373, 'learning_rate': 0.0003013487670665757, 'epoch': 5.41}

 45%|████▌     | 12668/28080 [25:01:58<30:19:28,  7.08s/it]
 45%|████▌     | 12669/28080 [25:02:05<30:25:14,  7.11s/it]
                                                           
{'loss': 0.6157, 'learning_rate': 0.0003013205458196125, 'epoch': 5.41}

 45%|████▌     | 12669/28080 [25:02:05<30:25:14,  7.11s/it]
 45%|████▌     | 12670/28080 [25:02:13<30:25:38,  7.11s/it]
                                                           
{'loss': 0.6466, 'learning_rate': 0.00030129232388988246, 'epoch': 5.41}

 45%|████▌     | 12670/28080 [25:02:13<30:25:38,  7.11s/it]
 45%|████▌     | 12671/28080 [25:02:20<30:30:31,  7.13s/it]
                                                           
{'loss': 0.6429, 'learning_rate': 0.000301264101277761, 'epoch': 5.41}

 45%|████▌     | 12671/28080 [25:02:20<30:30:31,  7.13s/it]
 45%|████▌     | 12672/28080 [25:02:27<30:21:13,  7.09s/it]
                                                           
{'loss': 0.6344, 'learning_rate': 0.0003012358779836236, 'epoch': 5.41}

 45%|████▌     | 12672/28080 [25:02:27<30:21:13,  7.09s/it]
 45%|████▌     | 12673/28080 [25:02:34<30:20:34,  7.09s/it]
                                                           
{'loss': 0.5962, 'learning_rate': 0.00030120765400784555, 'epoch': 5.41}

 45%|████▌     | 12673/28080 [25:02:34<30:20:34,  7.09s/it]
 45%|████▌     | 12674/28080 [25:02:41<30:24:19,  7.11s/it]
                                                           
{'loss': 0.6135, 'learning_rate': 0.0003011794293508026, 'epoch': 5.41}

 45%|████▌     | 12674/28080 [25:02:41<30:24:19,  7.11s/it]
 45%|████▌     | 12675/28080 [25:02:48<30:25:20,  7.11s/it]
                                                           
{'loss': 0.6209, 'learning_rate': 0.0003011512040128701, 'epoch': 5.41}

 45%|████▌     | 12675/28080 [25:02:48<30:25:20,  7.11s/it]
 45%|████▌     | 12676/28080 [25:02:55<30:28:29,  7.12s/it]
                                                           
{'loss': 0.6399, 'learning_rate': 0.0003011229779944236, 'epoch': 5.42}

 45%|████▌     | 12676/28080 [25:02:55<30:28:29,  7.12s/it]
 45%|████▌     | 12677/28080 [25:03:02<30:27:46,  7.12s/it]
                                                           
{'loss': 0.6367, 'learning_rate': 0.00030109475129583865, 'epoch': 5.42}

 45%|████▌     | 12677/28080 [25:03:02<30:27:46,  7.12s/it]
 45%|████▌     | 12678/28080 [25:03:09<30:27:33,  7.12s/it]
                                                           
{'loss': 0.6239, 'learning_rate': 0.0003010665239174907, 'epoch': 5.42}

 45%|████▌     | 12678/28080 [25:03:09<30:27:33,  7.12s/it]
 45%|████▌     | 12679/28080 [25:03:17<30:24:30,  7.11s/it]
                                                           
{'loss': 0.6275, 'learning_rate': 0.00030103829585975537, 'epoch': 5.42}

 45%|████▌     | 12679/28080 [25:03:17<30:24:30,  7.11s/it]
 45%|████▌     | 12680/28080 [25:03:24<30:25:39,  7.11s/it]
                                                           
{'loss': 0.6436, 'learning_rate': 0.00030101006712300815, 'epoch': 5.42}

 45%|████▌     | 12680/28080 [25:03:24<30:25:39,  7.11s/it]
 45%|████▌     | 12681/28080 [25:03:31<30:26:10,  7.12s/it]
                                                           
{'loss': 0.6224, 'learning_rate': 0.0003009818377076246, 'epoch': 5.42}

 45%|████▌     | 12681/28080 [25:03:31<30:26:10,  7.12s/it]
 45%|████▌     | 12682/28080 [25:03:38<30:27:13,  7.12s/it]
                                                           
{'loss': 0.6187, 'learning_rate': 0.00030095360761398036, 'epoch': 5.42}

 45%|████▌     | 12682/28080 [25:03:38<30:27:13,  7.12s/it]
 45%|████▌     | 12683/28080 [25:03:45<30:21:41,  7.10s/it]
                                                           
{'loss': 0.6151, 'learning_rate': 0.00030092537684245086, 'epoch': 5.42}

 45%|████▌     | 12683/28080 [25:03:45<30:21:41,  7.10s/it]
 45%|████▌     | 12684/28080 [25:03:52<30:22:54,  7.10s/it]
                                                           
{'loss': 0.6129, 'learning_rate': 0.00030089714539341183, 'epoch': 5.42}

 45%|████▌     | 12684/28080 [25:03:52<30:22:54,  7.10s/it]
 45%|████▌     | 12685/28080 [25:03:59<30:24:33,  7.11s/it]
                                                           
{'loss': 0.6196, 'learning_rate': 0.0003008689132672387, 'epoch': 5.42}

 45%|████▌     | 12685/28080 [25:03:59<30:24:33,  7.11s/it]
 45%|████▌     | 12686/28080 [25:04:06<30:28:17,  7.13s/it]
                                                           
{'loss': 0.6268, 'learning_rate': 0.0003008406804643072, 'epoch': 5.42}

 45%|████▌     | 12686/28080 [25:04:06<30:28:17,  7.13s/it]
 45%|████▌     | 12687/28080 [25:04:14<30:30:13,  7.13s/it]
                                                           
{'loss': 0.6123, 'learning_rate': 0.00030081244698499293, 'epoch': 5.42}

 45%|████▌     | 12687/28080 [25:04:14<30:30:13,  7.13s/it]
 45%|████▌     | 12688/28080 [25:04:21<30:26:02,  7.12s/it]
                                                           
{'loss': 0.6395, 'learning_rate': 0.0003007842128296714, 'epoch': 5.42}

 45%|████▌     | 12688/28080 [25:04:21<30:26:02,  7.12s/it]
 45%|████▌     | 12689/28080 [25:04:28<30:16:12,  7.08s/it]
                                                           
{'loss': 0.6271, 'learning_rate': 0.00030075597799871846, 'epoch': 5.42}

 45%|████▌     | 12689/28080 [25:04:28<30:16:12,  7.08s/it]
 45%|████▌     | 12690/28080 [25:04:35<30:15:52,  7.08s/it]
                                                           
{'loss': 0.6129, 'learning_rate': 0.00030072774249250946, 'epoch': 5.42}

 45%|████▌     | 12690/28080 [25:04:35<30:15:52,  7.08s/it]
 45%|████▌     | 12691/28080 [25:04:42<30:08:21,  7.05s/it]
                                                           
{'loss': 0.6231, 'learning_rate': 0.0003006995063114202, 'epoch': 5.42}

 45%|████▌     | 12691/28080 [25:04:42<30:08:21,  7.05s/it]
 45%|████▌     | 12692/28080 [25:04:49<30:11:25,  7.06s/it]
                                                           
{'loss': 0.6339, 'learning_rate': 0.0003006712694558263, 'epoch': 5.42}

 45%|████▌     | 12692/28080 [25:04:49<30:11:25,  7.06s/it]
 45%|████▌     | 12693/28080 [25:04:56<30:09:04,  7.05s/it]
                                                           
{'loss': 0.6414, 'learning_rate': 0.00030064303192610343, 'epoch': 5.42}

 45%|████▌     | 12693/28080 [25:04:56<30:09:04,  7.05s/it]
 45%|████▌     | 12694/28080 [25:05:03<30:21:08,  7.10s/it]
                                                           
{'loss': 0.61, 'learning_rate': 0.00030061479372262733, 'epoch': 5.42}

 45%|████▌     | 12694/28080 [25:05:03<30:21:08,  7.10s/it]
 45%|████▌     | 12695/28080 [25:05:10<30:16:33,  7.08s/it]
                                                           
{'loss': 0.6509, 'learning_rate': 0.0003005865548457736, 'epoch': 5.42}

 45%|████▌     | 12695/28080 [25:05:10<30:16:33,  7.08s/it]
 45%|████▌     | 12696/28080 [25:05:17<30:11:10,  7.06s/it]
                                                           
{'loss': 0.624, 'learning_rate': 0.00030055831529591793, 'epoch': 5.42}

 45%|████▌     | 12696/28080 [25:05:17<30:11:10,  7.06s/it]
 45%|████▌     | 12697/28080 [25:05:24<30:21:16,  7.10s/it]
                                                           
{'loss': 0.6373, 'learning_rate': 0.000300530075073436, 'epoch': 5.42}

 45%|████▌     | 12697/28080 [25:05:24<30:21:16,  7.10s/it]
 45%|████▌     | 12698/28080 [25:05:31<30:27:57,  7.13s/it]
                                                           
{'loss': 0.6443, 'learning_rate': 0.00030050183417870354, 'epoch': 5.42}

 45%|████▌     | 12698/28080 [25:05:31<30:27:57,  7.13s/it]
 45%|████▌     | 12699/28080 [25:05:39<30:28:04,  7.13s/it]
                                                           
{'loss': 0.6363, 'learning_rate': 0.0003004735926120963, 'epoch': 5.42}

 45%|████▌     | 12699/28080 [25:05:39<30:28:04,  7.13s/it]
 45%|████▌     | 12700/28080 [25:05:46<30:32:37,  7.15s/it]
                                                           
{'loss': 0.6194, 'learning_rate': 0.00030044535037399, 'epoch': 5.43}

 45%|████▌     | 12700/28080 [25:05:46<30:32:37,  7.15s/it]
 45%|████▌     | 12701/28080 [25:05:53<30:35:51,  7.16s/it]
                                                           
{'loss': 0.5984, 'learning_rate': 0.0003004171074647604, 'epoch': 5.43}

 45%|████▌     | 12701/28080 [25:05:53<30:35:51,  7.16s/it]
 45%|████▌     | 12702/28080 [25:06:00<30:30:20,  7.14s/it]
                                                           
{'loss': 0.5937, 'learning_rate': 0.0003003888638847831, 'epoch': 5.43}

 45%|████▌     | 12702/28080 [25:06:00<30:30:20,  7.14s/it]
 45%|████▌     | 12703/28080 [25:06:07<30:28:43,  7.14s/it]
                                                           
{'loss': 0.6375, 'learning_rate': 0.000300360619634434, 'epoch': 5.43}

 45%|████▌     | 12703/28080 [25:06:07<30:28:43,  7.14s/it]
 45%|████▌     | 12704/28080 [25:06:14<30:19:13,  7.10s/it]
                                                           
{'loss': 0.6257, 'learning_rate': 0.0003003323747140888, 'epoch': 5.43}

 45%|████▌     | 12704/28080 [25:06:14<30:19:13,  7.10s/it]
 45%|████▌     | 12705/28080 [25:06:22<30:34:51,  7.16s/it]
                                                           
{'loss': 0.6074, 'learning_rate': 0.0003003041291241232, 'epoch': 5.43}

 45%|████▌     | 12705/28080 [25:06:22<30:34:51,  7.16s/it]
 45%|████▌     | 12706/28080 [25:06:29<30:34:28,  7.16s/it]
                                                           
{'loss': 0.636, 'learning_rate': 0.00030027588286491325, 'epoch': 5.43}

 45%|████▌     | 12706/28080 [25:06:29<30:34:28,  7.16s/it]
 45%|████▌     | 12707/28080 [25:06:36<30:26:35,  7.13s/it]
                                                           
{'loss': 0.636, 'learning_rate': 0.0003002476359368344, 'epoch': 5.43}

 45%|████▌     | 12707/28080 [25:06:36<30:26:35,  7.13s/it]
 45%|████▌     | 12708/28080 [25:06:43<30:29:12,  7.14s/it]
                                                           
{'loss': 0.6139, 'learning_rate': 0.0003002193883402626, 'epoch': 5.43}

 45%|████▌     | 12708/28080 [25:06:43<30:29:12,  7.14s/it]
 45%|████▌     | 12709/28080 [25:06:50<30:17:54,  7.10s/it]
                                                           
{'loss': 0.6117, 'learning_rate': 0.0003001911400755737, 'epoch': 5.43}

 45%|████▌     | 12709/28080 [25:06:50<30:17:54,  7.10s/it]
 45%|████▌     | 12710/28080 [25:06:57<30:15:14,  7.09s/it]
                                                           
{'loss': 0.6323, 'learning_rate': 0.0003001628911431434, 'epoch': 5.43}

 45%|████▌     | 12710/28080 [25:06:57<30:15:14,  7.09s/it]
 45%|████▌     | 12711/28080 [25:07:04<30:21:09,  7.11s/it]
                                                           
{'loss': 0.6102, 'learning_rate': 0.0003001346415433476, 'epoch': 5.43}

 45%|████▌     | 12711/28080 [25:07:04<30:21:09,  7.11s/it]
 45%|████▌     | 12712/28080 [25:07:11<30:25:01,  7.13s/it]
                                                           
{'loss': 0.6113, 'learning_rate': 0.00030010639127656217, 'epoch': 5.43}

 45%|████▌     | 12712/28080 [25:07:11<30:25:01,  7.13s/it]
 45%|████▌     | 12713/28080 [25:07:18<30:27:58,  7.14s/it]
                                                           
{'loss': 0.6088, 'learning_rate': 0.0003000781403431629, 'epoch': 5.43}

 45%|████▌     | 12713/28080 [25:07:18<30:27:58,  7.14s/it]
 45%|████▌     | 12714/28080 [25:07:26<30:32:08,  7.15s/it]
                                                           
{'loss': 0.6247, 'learning_rate': 0.0003000498887435256, 'epoch': 5.43}

 45%|████▌     | 12714/28080 [25:07:26<30:32:08,  7.15s/it]
 45%|████▌     | 12715/28080 [25:07:33<30:24:42,  7.13s/it]
                                                           
{'loss': 0.6221, 'learning_rate': 0.0003000216364780261, 'epoch': 5.43}

 45%|████▌     | 12715/28080 [25:07:33<30:24:42,  7.13s/it]
 45%|████▌     | 12716/28080 [25:07:40<30:27:19,  7.14s/it]
                                                           
{'loss': 0.6191, 'learning_rate': 0.0002999933835470404, 'epoch': 5.43}

 45%|████▌     | 12716/28080 [25:07:40<30:27:19,  7.14s/it]
 45%|████▌     | 12717/28080 [25:07:47<30:28:13,  7.14s/it]
                                                           
{'loss': 0.6194, 'learning_rate': 0.00029996512995094434, 'epoch': 5.43}

 45%|████▌     | 12717/28080 [25:07:47<30:28:13,  7.14s/it]
 45%|████▌     | 12718/28080 [25:07:54<30:31:25,  7.15s/it]
                                                           
{'loss': 0.6148, 'learning_rate': 0.00029993687569011373, 'epoch': 5.43}

 45%|████▌     | 12718/28080 [25:07:54<30:31:25,  7.15s/it]
 45%|████▌     | 12719/28080 [25:08:01<30:34:55,  7.17s/it]
                                                           
{'loss': 0.6292, 'learning_rate': 0.0002999086207649245, 'epoch': 5.43}

 45%|████▌     | 12719/28080 [25:08:01<30:34:55,  7.17s/it]
 45%|████▌     | 12720/28080 [25:08:08<30:27:05,  7.14s/it]
                                                           
{'loss': 0.6001, 'learning_rate': 0.0002998803651757526, 'epoch': 5.43}

 45%|████▌     | 12720/28080 [25:08:08<30:27:05,  7.14s/it]
 45%|████▌     | 12721/28080 [25:08:16<30:30:37,  7.15s/it]
                                                           
{'loss': 0.6194, 'learning_rate': 0.0002998521089229738, 'epoch': 5.43}

 45%|████▌     | 12721/28080 [25:08:16<30:30:37,  7.15s/it]
 45%|████▌     | 12722/28080 [25:08:23<30:30:01,  7.15s/it]
                                                           
{'loss': 0.6052, 'learning_rate': 0.00029982385200696417, 'epoch': 5.43}

 45%|████▌     | 12722/28080 [25:08:23<30:30:01,  7.15s/it]
 45%|████▌     | 12723/28080 [25:08:30<30:22:40,  7.12s/it]
                                                           
{'loss': 0.6152, 'learning_rate': 0.0002997955944280996, 'epoch': 5.44}

 45%|████▌     | 12723/28080 [25:08:30<30:22:40,  7.12s/it]
 45%|████▌     | 12724/28080 [25:08:37<30:19:42,  7.11s/it]
                                                           
{'loss': 0.6176, 'learning_rate': 0.000299767336186756, 'epoch': 5.44}

 45%|████▌     | 12724/28080 [25:08:37<30:19:42,  7.11s/it]
 45%|████▌     | 12725/28080 [25:08:44<30:15:40,  7.09s/it]
                                                           
{'loss': 0.6156, 'learning_rate': 0.0002997390772833094, 'epoch': 5.44}

 45%|████▌     | 12725/28080 [25:08:44<30:15:40,  7.09s/it]
 45%|████▌     | 12726/28080 [25:08:51<30:21:17,  7.12s/it]
                                                           
{'loss': 0.621, 'learning_rate': 0.0002997108177181356, 'epoch': 5.44}

 45%|████▌     | 12726/28080 [25:08:51<30:21:17,  7.12s/it]
 45%|████▌     | 12727/28080 [25:08:58<30:25:36,  7.13s/it]
                                                           
{'loss': 0.6167, 'learning_rate': 0.00029968255749161077, 'epoch': 5.44}

 45%|████▌     | 12727/28080 [25:08:58<30:25:36,  7.13s/it]
 45%|████▌     | 12728/28080 [25:09:05<30:22:34,  7.12s/it]
                                                           
{'loss': 0.6187, 'learning_rate': 0.00029965429660411063, 'epoch': 5.44}

 45%|████▌     | 12728/28080 [25:09:05<30:22:34,  7.12s/it]
 45%|████▌     | 12729/28080 [25:09:13<30:23:24,  7.13s/it]
                                                           
{'loss': 0.6165, 'learning_rate': 0.00029962603505601136, 'epoch': 5.44}

 45%|████▌     | 12729/28080 [25:09:13<30:23:24,  7.13s/it]
 45%|████▌     | 12730/28080 [25:09:20<30:13:05,  7.09s/it]
                                                           
{'loss': 0.6477, 'learning_rate': 0.000299597772847689, 'epoch': 5.44}

 45%|████▌     | 12730/28080 [25:09:20<30:13:05,  7.09s/it]
 45%|████▌     | 12731/28080 [25:09:27<30:13:25,  7.09s/it]
                                                           
{'loss': 0.6043, 'learning_rate': 0.00029956950997951924, 'epoch': 5.44}

 45%|████▌     | 12731/28080 [25:09:27<30:13:25,  7.09s/it]
 45%|████▌     | 12732/28080 [25:09:34<30:18:07,  7.11s/it]
                                                           
{'loss': 0.6234, 'learning_rate': 0.0002995412464518784, 'epoch': 5.44}

 45%|████▌     | 12732/28080 [25:09:34<30:18:07,  7.11s/it]
 45%|████▌     | 12733/28080 [25:09:41<30:21:10,  7.12s/it]
                                                           
{'loss': 0.6106, 'learning_rate': 0.00029951298226514237, 'epoch': 5.44}

 45%|████▌     | 12733/28080 [25:09:41<30:21:10,  7.12s/it]
 45%|████▌     | 12734/28080 [25:09:48<30:27:47,  7.15s/it]
                                                           
{'loss': 0.6185, 'learning_rate': 0.00029948471741968717, 'epoch': 5.44}

 45%|████▌     | 12734/28080 [25:09:48<30:27:47,  7.15s/it]
 45%|████▌     | 12735/28080 [25:09:55<30:26:00,  7.14s/it]
                                                           
{'loss': 0.6205, 'learning_rate': 0.0002994564519158889, 'epoch': 5.44}

 45%|████▌     | 12735/28080 [25:09:55<30:26:00,  7.14s/it]
 45%|████▌     | 12736/28080 [25:10:02<30:20:37,  7.12s/it]
                                                           
{'loss': 0.6599, 'learning_rate': 0.00029942818575412353, 'epoch': 5.44}

 45%|████▌     | 12736/28080 [25:10:02<30:20:37,  7.12s/it]
 45%|████▌     | 12737/28080 [25:10:09<30:14:23,  7.10s/it]
                                                           
{'loss': 0.6335, 'learning_rate': 0.00029939991893476714, 'epoch': 5.44}

 45%|████▌     | 12737/28080 [25:10:09<30:14:23,  7.10s/it]
 45%|████▌     | 12738/28080 [25:10:17<30:18:12,  7.11s/it]
                                                           
{'loss': 0.6025, 'learning_rate': 0.00029937165145819576, 'epoch': 5.44}

 45%|████▌     | 12738/28080 [25:10:17<30:18:12,  7.11s/it]
 45%|████▌     | 12739/28080 [25:10:24<30:20:53,  7.12s/it]
                                                           
{'loss': 0.6416, 'learning_rate': 0.0002993433833247856, 'epoch': 5.44}

 45%|████▌     | 12739/28080 [25:10:24<30:20:53,  7.12s/it]
 45%|████▌     | 12740/28080 [25:10:31<30:11:40,  7.09s/it]
                                                           
{'loss': 0.635, 'learning_rate': 0.00029931511453491256, 'epoch': 5.44}

 45%|████▌     | 12740/28080 [25:10:31<30:11:40,  7.09s/it]
 45%|████▌     | 12741/28080 [25:10:38<30:06:39,  7.07s/it]
                                                           
{'loss': 0.6209, 'learning_rate': 0.00029928684508895276, 'epoch': 5.44}

 45%|████▌     | 12741/28080 [25:10:38<30:06:39,  7.07s/it]
 45%|████▌     | 12742/28080 [25:10:45<30:07:38,  7.07s/it]
                                                           
{'loss': 0.6311, 'learning_rate': 0.0002992585749872824, 'epoch': 5.44}

 45%|████▌     | 12742/28080 [25:10:45<30:07:38,  7.07s/it]
 45%|████▌     | 12743/28080 [25:10:52<30:16:44,  7.11s/it]
                                                           
{'loss': 0.6167, 'learning_rate': 0.0002992303042302774, 'epoch': 5.44}

 45%|████▌     | 12743/28080 [25:10:52<30:16:44,  7.11s/it]
 45%|████▌     | 12744/28080 [25:10:59<30:18:09,  7.11s/it]
                                                           
{'loss': 0.6194, 'learning_rate': 0.00029920203281831413, 'epoch': 5.44}

 45%|████▌     | 12744/28080 [25:10:59<30:18:09,  7.11s/it]
 45%|████▌     | 12745/28080 [25:11:06<30:07:36,  7.07s/it]
                                                           
{'loss': 0.6179, 'learning_rate': 0.0002991737607517685, 'epoch': 5.44}

 45%|████▌     | 12745/28080 [25:11:06<30:07:36,  7.07s/it]
 45%|████▌     | 12746/28080 [25:11:13<30:18:17,  7.11s/it]
                                                           
{'loss': 0.6095, 'learning_rate': 0.0002991454880310167, 'epoch': 5.44}

 45%|████▌     | 12746/28080 [25:11:13<30:18:17,  7.11s/it]
 45%|████▌     | 12747/28080 [25:11:20<30:15:30,  7.10s/it]
                                                           
{'loss': 0.6237, 'learning_rate': 0.00029911721465643494, 'epoch': 5.45}

 45%|████▌     | 12747/28080 [25:11:20<30:15:30,  7.10s/it]
 45%|████▌     | 12748/28080 [25:11:27<30:10:26,  7.08s/it]
                                                           
{'loss': 0.6283, 'learning_rate': 0.00029908894062839926, 'epoch': 5.45}

 45%|████▌     | 12748/28080 [25:11:27<30:10:26,  7.08s/it]
 45%|████▌     | 12749/28080 [25:11:35<30:15:32,  7.11s/it]
                                                           
{'loss': 0.6023, 'learning_rate': 0.0002990606659472859, 'epoch': 5.45}

 45%|████▌     | 12749/28080 [25:11:35<30:15:32,  7.11s/it]
 45%|████▌     | 12750/28080 [25:11:42<30:11:38,  7.09s/it]
                                                           
{'loss': 0.6083, 'learning_rate': 0.000299032390613471, 'epoch': 5.45}

 45%|████▌     | 12750/28080 [25:11:42<30:11:38,  7.09s/it]
 45%|████▌     | 12751/28080 [25:11:49<30:19:48,  7.12s/it]
                                                           
{'loss': 0.6337, 'learning_rate': 0.0002990041146273307, 'epoch': 5.45}

 45%|████▌     | 12751/28080 [25:11:49<30:19:48,  7.12s/it]
 45%|████▌     | 12752/28080 [25:11:56<30:24:18,  7.14s/it]
                                                           
{'loss': 0.6198, 'learning_rate': 0.00029897583798924114, 'epoch': 5.45}

 45%|████▌     | 12752/28080 [25:11:56<30:24:18,  7.14s/it]
 45%|████▌     | 12753/28080 [25:12:03<30:29:07,  7.16s/it]
                                                           
{'loss': 0.6104, 'learning_rate': 0.00029894756069957865, 'epoch': 5.45}

 45%|████▌     | 12753/28080 [25:12:03<30:29:07,  7.16s/it]
 45%|████▌     | 12754/28080 [25:12:10<30:32:55,  7.18s/it]
                                                           
{'loss': 0.6166, 'learning_rate': 0.0002989192827587194, 'epoch': 5.45}

 45%|████▌     | 12754/28080 [25:12:10<30:32:55,  7.18s/it]
 45%|████▌     | 12755/28080 [25:12:17<30:18:45,  7.12s/it]
                                                           
{'loss': 0.6401, 'learning_rate': 0.0002988910041670395, 'epoch': 5.45}

 45%|████▌     | 12755/28080 [25:12:17<30:18:45,  7.12s/it]
 45%|████▌     | 12756/28080 [25:12:25<30:16:30,  7.11s/it]
                                                           
{'loss': 0.6296, 'learning_rate': 0.0002988627249249153, 'epoch': 5.45}

 45%|████▌     | 12756/28080 [25:12:25<30:16:30,  7.11s/it]
 45%|████▌     | 12757/28080 [25:12:32<30:06:10,  7.07s/it]
                                                           
{'loss': 0.6014, 'learning_rate': 0.0002988344450327229, 'epoch': 5.45}

 45%|████▌     | 12757/28080 [25:12:32<30:06:10,  7.07s/it]
 45%|████▌     | 12758/28080 [25:12:39<30:03:19,  7.06s/it]
                                                           
{'loss': 0.6343, 'learning_rate': 0.00029880616449083863, 'epoch': 5.45}

 45%|████▌     | 12758/28080 [25:12:39<30:03:19,  7.06s/it]
 45%|████▌     | 12759/28080 [25:12:46<29:59:55,  7.05s/it]
                                                           
{'loss': 0.6257, 'learning_rate': 0.00029877788329963863, 'epoch': 5.45}

 45%|████▌     | 12759/28080 [25:12:46<29:59:55,  7.05s/it]
 45%|████▌     | 12760/28080 [25:12:53<30:05:02,  7.07s/it]
                                                           
{'loss': 0.6178, 'learning_rate': 0.0002987496014594992, 'epoch': 5.45}

 45%|████▌     | 12760/28080 [25:12:53<30:05:02,  7.07s/it]
 45%|████▌     | 12761/28080 [25:13:00<30:12:20,  7.10s/it]
                                                           
{'loss': 0.6185, 'learning_rate': 0.00029872131897079666, 'epoch': 5.45}

 45%|████▌     | 12761/28080 [25:13:00<30:12:20,  7.10s/it]
 45%|████▌     | 12762/28080 [25:13:07<30:15:04,  7.11s/it]
                                                           
{'loss': 0.6192, 'learning_rate': 0.00029869303583390723, 'epoch': 5.45}

 45%|████▌     | 12762/28080 [25:13:07<30:15:04,  7.11s/it]
 45%|████▌     | 12763/28080 [25:13:14<30:12:17,  7.10s/it]
                                                           
{'loss': 0.6148, 'learning_rate': 0.0002986647520492072, 'epoch': 5.45}

 45%|████▌     | 12763/28080 [25:13:14<30:12:17,  7.10s/it]
 45%|████▌     | 12764/28080 [25:13:21<30:22:18,  7.14s/it]
                                                           
{'loss': 0.6188, 'learning_rate': 0.0002986364676170729, 'epoch': 5.45}

 45%|████▌     | 12764/28080 [25:13:21<30:22:18,  7.14s/it]
 45%|████▌     | 12765/28080 [25:13:28<30:10:38,  7.09s/it]
                                                           
{'loss': 0.6278, 'learning_rate': 0.00029860818253788055, 'epoch': 5.45}

 45%|████▌     | 12765/28080 [25:13:28<30:10:38,  7.09s/it]
 45%|████▌     | 12766/28080 [25:13:35<30:13:18,  7.10s/it]
                                                           
{'loss': 0.6171, 'learning_rate': 0.0002985798968120064, 'epoch': 5.45}

 45%|████▌     | 12766/28080 [25:13:35<30:13:18,  7.10s/it]
 45%|████▌     | 12767/28080 [25:13:42<30:11:20,  7.10s/it]
                                                           
{'loss': 0.6236, 'learning_rate': 0.00029855161043982687, 'epoch': 5.45}

 45%|████▌     | 12767/28080 [25:13:42<30:11:20,  7.10s/it]
 45%|████▌     | 12768/28080 [25:13:50<30:20:02,  7.13s/it]
                                                           
{'loss': 0.6218, 'learning_rate': 0.0002985233234217183, 'epoch': 5.45}

 45%|████▌     | 12768/28080 [25:13:50<30:20:02,  7.13s/it]
 45%|████▌     | 12769/28080 [25:13:57<30:18:22,  7.13s/it]
                                                           
{'loss': 0.6136, 'learning_rate': 0.0002984950357580569, 'epoch': 5.45}

 45%|████▌     | 12769/28080 [25:13:57<30:18:22,  7.13s/it]
 45%|████▌     | 12770/28080 [25:14:04<30:11:03,  7.10s/it]
                                                           
{'loss': 0.621, 'learning_rate': 0.0002984667474492191, 'epoch': 5.46}

 45%|████▌     | 12770/28080 [25:14:04<30:11:03,  7.10s/it]
 45%|████▌     | 12771/28080 [25:14:11<30:14:15,  7.11s/it]
                                                           
{'loss': 0.6274, 'learning_rate': 0.0002984384584955813, 'epoch': 5.46}

 45%|████▌     | 12771/28080 [25:14:11<30:14:15,  7.11s/it]
 45%|████▌     | 12772/28080 [25:14:18<30:15:24,  7.12s/it]
                                                           
{'loss': 0.6168, 'learning_rate': 0.0002984101688975197, 'epoch': 5.46}

 45%|████▌     | 12772/28080 [25:14:18<30:15:24,  7.12s/it]
 45%|████▌     | 12773/28080 [25:14:25<30:16:16,  7.12s/it]
                                                           
{'loss': 0.6295, 'learning_rate': 0.00029838187865541076, 'epoch': 5.46}

 45%|████▌     | 12773/28080 [25:14:25<30:16:16,  7.12s/it]
 45%|████▌     | 12774/28080 [25:14:32<30:16:21,  7.12s/it]
                                                           
{'loss': 0.6297, 'learning_rate': 0.0002983535877696308, 'epoch': 5.46}

 45%|████▌     | 12774/28080 [25:14:32<30:16:21,  7.12s/it]
 45%|████▌     | 12775/28080 [25:14:40<30:20:05,  7.14s/it]
                                                           
{'loss': 0.6353, 'learning_rate': 0.00029832529624055634, 'epoch': 5.46}

 45%|████▌     | 12775/28080 [25:14:40<30:20:05,  7.14s/it]
 45%|████▌     | 12776/28080 [25:14:47<30:17:03,  7.12s/it]
                                                           
{'loss': 0.618, 'learning_rate': 0.00029829700406856357, 'epoch': 5.46}

 45%|████▌     | 12776/28080 [25:14:47<30:17:03,  7.12s/it]
 46%|████▌     | 12777/28080 [25:14:54<30:18:09,  7.13s/it]
                                                           
{'loss': 0.6225, 'learning_rate': 0.000298268711254029, 'epoch': 5.46}

 46%|████▌     | 12777/28080 [25:14:54<30:18:09,  7.13s/it]
 46%|████▌     | 12778/28080 [25:15:01<30:22:38,  7.15s/it]
                                                           
{'loss': 0.6134, 'learning_rate': 0.0002982404177973291, 'epoch': 5.46}

 46%|████▌     | 12778/28080 [25:15:01<30:22:38,  7.15s/it]
 46%|████▌     | 12779/28080 [25:15:08<30:18:40,  7.13s/it]
                                                           
{'loss': 0.6214, 'learning_rate': 0.00029821212369884014, 'epoch': 5.46}

 46%|████▌     | 12779/28080 [25:15:08<30:18:40,  7.13s/it]
 46%|████▌     | 12780/28080 [25:15:15<30:20:11,  7.14s/it]
                                                           
{'loss': 0.617, 'learning_rate': 0.00029818382895893864, 'epoch': 5.46}

 46%|████▌     | 12780/28080 [25:15:15<30:20:11,  7.14s/it]
 46%|████▌     | 12781/28080 [25:15:22<30:18:14,  7.13s/it]
                                                           
{'loss': 0.6321, 'learning_rate': 0.00029815553357800094, 'epoch': 5.46}

 46%|████▌     | 12781/28080 [25:15:22<30:18:14,  7.13s/it]
 46%|████▌     | 12782/28080 [25:15:29<30:14:34,  7.12s/it]
                                                           
{'loss': 0.6164, 'learning_rate': 0.00029812723755640367, 'epoch': 5.46}

 46%|████▌     | 12782/28080 [25:15:29<30:14:34,  7.12s/it]
 46%|████▌     | 12783/28080 [25:15:37<30:13:30,  7.11s/it]
                                                           
{'loss': 0.6192, 'learning_rate': 0.00029809894089452305, 'epoch': 5.46}

 46%|████▌     | 12783/28080 [25:15:37<30:13:30,  7.11s/it]
 46%|████▌     | 12784/28080 [25:15:44<30:17:42,  7.13s/it]
                                                           
{'loss': 0.6, 'learning_rate': 0.0002980706435927357, 'epoch': 5.46}

 46%|████▌     | 12784/28080 [25:15:44<30:17:42,  7.13s/it]
 46%|████▌     | 12785/28080 [25:15:51<30:13:17,  7.11s/it]
                                                           
{'loss': 0.6186, 'learning_rate': 0.00029804234565141796, 'epoch': 5.46}

 46%|████▌     | 12785/28080 [25:15:51<30:13:17,  7.11s/it]
 46%|████▌     | 12786/28080 [25:15:58<30:12:25,  7.11s/it]
                                                           
{'loss': 0.6014, 'learning_rate': 0.0002980140470709464, 'epoch': 5.46}

 46%|████▌     | 12786/28080 [25:15:58<30:12:25,  7.11s/it]
 46%|████▌     | 12787/28080 [25:16:05<30:16:18,  7.13s/it]
                                                           
{'loss': 0.6106, 'learning_rate': 0.0002979857478516975, 'epoch': 5.46}

 46%|████▌     | 12787/28080 [25:16:05<30:16:18,  7.13s/it]
 46%|████▌     | 12788/28080 [25:16:12<30:17:03,  7.13s/it]
                                                           
{'loss': 0.6239, 'learning_rate': 0.00029795744799404774, 'epoch': 5.46}

 46%|████▌     | 12788/28080 [25:16:12<30:17:03,  7.13s/it]
 46%|████▌     | 12789/28080 [25:16:19<30:15:26,  7.12s/it]
                                                           
{'loss': 0.6143, 'learning_rate': 0.00029792914749837365, 'epoch': 5.46}

 46%|████▌     | 12789/28080 [25:16:19<30:15:26,  7.12s/it]
 46%|████▌     | 12790/28080 [25:16:26<30:17:33,  7.13s/it]
                                                           
{'loss': 0.629, 'learning_rate': 0.00029790084636505164, 'epoch': 5.46}

 46%|████▌     | 12790/28080 [25:16:26<30:17:33,  7.13s/it]
 46%|████▌     | 12791/28080 [25:16:34<30:17:34,  7.13s/it]
                                                           
{'loss': 0.615, 'learning_rate': 0.00029787254459445826, 'epoch': 5.46}

 46%|████▌     | 12791/28080 [25:16:34<30:17:34,  7.13s/it]
 46%|████▌     | 12792/28080 [25:16:41<30:21:08,  7.15s/it]
                                                           
{'loss': 0.6069, 'learning_rate': 0.00029784424218697015, 'epoch': 5.46}

 46%|████▌     | 12792/28080 [25:16:41<30:21:08,  7.15s/it]
 46%|████▌     | 12793/28080 [25:16:48<30:22:02,  7.15s/it]
                                                           
{'loss': 0.6151, 'learning_rate': 0.00029781593914296364, 'epoch': 5.47}

 46%|████▌     | 12793/28080 [25:16:48<30:22:02,  7.15s/it]
 46%|████▌     | 12794/28080 [25:16:55<30:22:22,  7.15s/it]
                                                           
{'loss': 0.6152, 'learning_rate': 0.0002977876354628154, 'epoch': 5.47}

 46%|████▌     | 12794/28080 [25:16:55<30:22:22,  7.15s/it]
 46%|████▌     | 12795/28080 [25:17:02<30:28:30,  7.18s/it]
                                                           
{'loss': 0.6386, 'learning_rate': 0.0002977593311469021, 'epoch': 5.47}

 46%|████▌     | 12795/28080 [25:17:02<30:28:30,  7.18s/it]
 46%|████▌     | 12796/28080 [25:17:10<30:37:05,  7.21s/it]
                                                           
{'loss': 0.6377, 'learning_rate': 0.0002977310261956, 'epoch': 5.47}

 46%|████▌     | 12796/28080 [25:17:10<30:37:05,  7.21s/it]
 46%|████▌     | 12797/28080 [25:17:17<30:32:10,  7.19s/it]
                                                           
{'loss': 0.6321, 'learning_rate': 0.00029770272060928595, 'epoch': 5.47}

 46%|████▌     | 12797/28080 [25:17:17<30:32:10,  7.19s/it]
 46%|████▌     | 12798/28080 [25:17:24<30:19:42,  7.14s/it]
                                                           
{'loss': 0.6263, 'learning_rate': 0.00029767441438833636, 'epoch': 5.47}

 46%|████▌     | 12798/28080 [25:17:24<30:19:42,  7.14s/it]
 46%|████▌     | 12799/28080 [25:17:31<30:14:12,  7.12s/it]
                                                           
{'loss': 0.6248, 'learning_rate': 0.00029764610753312795, 'epoch': 5.47}

 46%|████▌     | 12799/28080 [25:17:31<30:14:12,  7.12s/it]
 46%|████▌     | 12800/28080 [25:17:38<30:20:30,  7.15s/it]
                                                           
{'loss': 0.6022, 'learning_rate': 0.00029761780004403717, 'epoch': 5.47}

 46%|████▌     | 12800/28080 [25:17:38<30:20:30,  7.15s/it]
 46%|████▌     | 12801/28080 [25:17:45<30:15:37,  7.13s/it]
                                                           
{'loss': 0.6301, 'learning_rate': 0.00029758949192144066, 'epoch': 5.47}

 46%|████▌     | 12801/28080 [25:17:45<30:15:37,  7.13s/it]
 46%|████▌     | 12802/28080 [25:17:52<30:16:29,  7.13s/it]
                                                           
{'loss': 0.6086, 'learning_rate': 0.00029756118316571513, 'epoch': 5.47}

 46%|████▌     | 12802/28080 [25:17:52<30:16:29,  7.13s/it]
 46%|████▌     | 12803/28080 [25:17:59<30:15:58,  7.13s/it]
                                                           
{'loss': 0.6334, 'learning_rate': 0.000297532873777237, 'epoch': 5.47}

 46%|████▌     | 12803/28080 [25:17:59<30:15:58,  7.13s/it]
 46%|████▌     | 12804/28080 [25:18:07<30:15:59,  7.13s/it]
                                                           
{'loss': 0.6222, 'learning_rate': 0.00029750456375638313, 'epoch': 5.47}

 46%|████▌     | 12804/28080 [25:18:07<30:15:59,  7.13s/it]
 46%|████▌     | 12805/28080 [25:18:14<30:10:53,  7.11s/it]
                                                           
{'loss': 0.6346, 'learning_rate': 0.00029747625310352997, 'epoch': 5.47}

 46%|████▌     | 12805/28080 [25:18:14<30:10:53,  7.11s/it]
 46%|████▌     | 12806/28080 [25:18:21<30:11:58,  7.12s/it]
                                                           
{'loss': 0.6197, 'learning_rate': 0.0002974479418190544, 'epoch': 5.47}

 46%|████▌     | 12806/28080 [25:18:21<30:11:58,  7.12s/it]
 46%|████▌     | 12807/28080 [25:18:28<30:09:44,  7.11s/it]
                                                           
{'loss': 0.6427, 'learning_rate': 0.0002974196299033328, 'epoch': 5.47}

 46%|████▌     | 12807/28080 [25:18:28<30:09:44,  7.11s/it]
 46%|████▌     | 12808/28080 [25:18:35<30:00:32,  7.07s/it]
                                                           
{'loss': 0.6529, 'learning_rate': 0.00029739131735674184, 'epoch': 5.47}

 46%|████▌     | 12808/28080 [25:18:35<30:00:32,  7.07s/it]
 46%|████▌     | 12809/28080 [25:18:42<30:09:38,  7.11s/it]
                                                           
{'loss': 0.6325, 'learning_rate': 0.00029736300417965844, 'epoch': 5.47}

 46%|████▌     | 12809/28080 [25:18:42<30:09:38,  7.11s/it]
 46%|████▌     | 12810/28080 [25:18:49<30:09:53,  7.11s/it]
                                                           
{'loss': 0.6286, 'learning_rate': 0.0002973346903724591, 'epoch': 5.47}

 46%|████▌     | 12810/28080 [25:18:49<30:09:53,  7.11s/it]
 46%|████▌     | 12811/28080 [25:18:56<30:17:44,  7.14s/it]
                                                           
{'loss': 0.6163, 'learning_rate': 0.00029730637593552056, 'epoch': 5.47}

 46%|████▌     | 12811/28080 [25:18:56<30:17:44,  7.14s/it]
 46%|████▌     | 12812/28080 [25:19:03<30:10:49,  7.12s/it]
                                                           
{'loss': 0.6467, 'learning_rate': 0.00029727806086921944, 'epoch': 5.47}

 46%|████▌     | 12812/28080 [25:19:03<30:10:49,  7.12s/it]
 46%|████▌     | 12813/28080 [25:19:10<30:05:55,  7.10s/it]
                                                           
{'loss': 0.6137, 'learning_rate': 0.00029724974517393257, 'epoch': 5.47}

 46%|████▌     | 12813/28080 [25:19:10<30:05:55,  7.10s/it]
 46%|████▌     | 12814/28080 [25:19:17<30:02:17,  7.08s/it]
                                                           
{'loss': 0.6324, 'learning_rate': 0.0002972214288500365, 'epoch': 5.47}

 46%|████▌     | 12814/28080 [25:19:18<30:02:17,  7.08s/it]
 46%|████▌     | 12815/28080 [25:19:25<29:56:32,  7.06s/it]
                                                           
{'loss': 0.6381, 'learning_rate': 0.00029719311189790805, 'epoch': 5.47}

 46%|████▌     | 12815/28080 [25:19:25<29:56:32,  7.06s/it]
 46%|████▌     | 12816/28080 [25:19:32<30:02:54,  7.09s/it]
                                                           
{'loss': 0.5951, 'learning_rate': 0.000297164794317924, 'epoch': 5.47}

 46%|████▌     | 12816/28080 [25:19:32<30:02:54,  7.09s/it]
 46%|████▌     | 12817/28080 [25:19:39<30:09:06,  7.11s/it]
                                                           
{'loss': 0.6062, 'learning_rate': 0.0002971364761104609, 'epoch': 5.48}

 46%|████▌     | 12817/28080 [25:19:39<30:09:06,  7.11s/it]
 46%|████▌     | 12818/28080 [25:19:46<30:12:07,  7.12s/it]
                                                           
{'loss': 0.6176, 'learning_rate': 0.0002971081572758957, 'epoch': 5.48}

 46%|████▌     | 12818/28080 [25:19:46<30:12:07,  7.12s/it]
 46%|████▌     | 12819/28080 [25:19:53<30:07:56,  7.11s/it]
                                                           
{'loss': 0.6145, 'learning_rate': 0.0002970798378146051, 'epoch': 5.48}

 46%|████▌     | 12819/28080 [25:19:53<30:07:56,  7.11s/it]
 46%|████▌     | 12820/28080 [25:20:00<30:10:29,  7.12s/it]
                                                           
{'loss': 0.6257, 'learning_rate': 0.0002970515177269657, 'epoch': 5.48}

 46%|████▌     | 12820/28080 [25:20:00<30:10:29,  7.12s/it]
 46%|████▌     | 12821/28080 [25:20:07<30:01:43,  7.08s/it]
                                                           
{'loss': 0.6261, 'learning_rate': 0.0002970231970133545, 'epoch': 5.48}

 46%|████▌     | 12821/28080 [25:20:07<30:01:43,  7.08s/it]
 46%|████▌     | 12822/28080 [25:20:14<30:06:07,  7.10s/it]
                                                           
{'loss': 0.6087, 'learning_rate': 0.0002969948756741481, 'epoch': 5.48}

 46%|████▌     | 12822/28080 [25:20:14<30:06:07,  7.10s/it]
 46%|████▌     | 12823/28080 [25:20:21<30:06:59,  7.11s/it]
                                                           
{'loss': 0.6159, 'learning_rate': 0.0002969665537097235, 'epoch': 5.48}

 46%|████▌     | 12823/28080 [25:20:21<30:06:59,  7.11s/it]
 46%|████▌     | 12824/28080 [25:20:29<30:13:04,  7.13s/it]
                                                           
{'loss': 0.6031, 'learning_rate': 0.0002969382311204572, 'epoch': 5.48}

 46%|████▌     | 12824/28080 [25:20:29<30:13:04,  7.13s/it]
 46%|████▌     | 12825/28080 [25:20:36<30:04:17,  7.10s/it]
                                                           
{'loss': 0.6447, 'learning_rate': 0.00029690990790672624, 'epoch': 5.48}

 46%|████▌     | 12825/28080 [25:20:36<30:04:17,  7.10s/it]
 46%|████▌     | 12826/28080 [25:20:43<30:02:07,  7.09s/it]
                                                           
{'loss': 0.6164, 'learning_rate': 0.0002968815840689073, 'epoch': 5.48}

 46%|████▌     | 12826/28080 [25:20:43<30:02:07,  7.09s/it]
 46%|████▌     | 12827/28080 [25:20:50<30:11:08,  7.12s/it]
                                                           
{'loss': 0.6139, 'learning_rate': 0.0002968532596073773, 'epoch': 5.48}

 46%|████▌     | 12827/28080 [25:20:50<30:11:08,  7.12s/it]
 46%|████▌     | 12828/28080 [25:20:57<30:12:58,  7.13s/it]
                                                           
{'loss': 0.6006, 'learning_rate': 0.00029682493452251303, 'epoch': 5.48}

 46%|████▌     | 12828/28080 [25:20:57<30:12:58,  7.13s/it]
 46%|████▌     | 12829/28080 [25:21:04<30:13:12,  7.13s/it]
                                                           
{'loss': 0.6246, 'learning_rate': 0.0002967966088146912, 'epoch': 5.48}

 46%|████▌     | 12829/28080 [25:21:04<30:13:12,  7.13s/it]
 46%|████▌     | 12830/28080 [25:21:11<30:02:45,  7.09s/it]
                                                           
{'loss': 0.6314, 'learning_rate': 0.0002967682824842889, 'epoch': 5.48}

 46%|████▌     | 12830/28080 [25:21:11<30:02:45,  7.09s/it]
 46%|████▌     | 12831/28080 [25:21:18<30:06:04,  7.11s/it]
                                                           
{'loss': 0.6156, 'learning_rate': 0.00029673995553168277, 'epoch': 5.48}

 46%|████▌     | 12831/28080 [25:21:18<30:06:04,  7.11s/it]
 46%|████▌     | 12832/28080 [25:21:25<30:07:40,  7.11s/it]
                                                           
{'loss': 0.6388, 'learning_rate': 0.00029671162795724974, 'epoch': 5.48}

 46%|████▌     | 12832/28080 [25:21:25<30:07:40,  7.11s/it]
 46%|████▌     | 12833/28080 [25:21:33<30:07:15,  7.11s/it]
                                                           
{'loss': 0.6268, 'learning_rate': 0.0002966832997613668, 'epoch': 5.48}

 46%|████▌     | 12833/28080 [25:21:33<30:07:15,  7.11s/it]
 46%|████▌     | 12834/28080 [25:21:40<30:00:36,  7.09s/it]
                                                           
{'loss': 0.6146, 'learning_rate': 0.0002966549709444106, 'epoch': 5.48}

 46%|████▌     | 12834/28080 [25:21:40<30:00:36,  7.09s/it]
 46%|████▌     | 12835/28080 [25:21:47<30:07:29,  7.11s/it]
                                                           
{'loss': 0.6254, 'learning_rate': 0.0002966266415067582, 'epoch': 5.48}

 46%|████▌     | 12835/28080 [25:21:47<30:07:29,  7.11s/it]
 46%|████▌     | 12836/28080 [25:21:54<30:02:12,  7.09s/it]
                                                           
{'loss': 0.6205, 'learning_rate': 0.0002965983114487864, 'epoch': 5.48}

 46%|████▌     | 12836/28080 [25:21:54<30:02:12,  7.09s/it]
 46%|████▌     | 12837/28080 [25:22:01<30:05:47,  7.11s/it]
                                                           
{'loss': 0.6197, 'learning_rate': 0.0002965699807708722, 'epoch': 5.48}

 46%|████▌     | 12837/28080 [25:22:01<30:05:47,  7.11s/it]
 46%|████▌     | 12838/28080 [25:22:08<30:06:41,  7.11s/it]
                                                           
{'loss': 0.6333, 'learning_rate': 0.0002965416494733924, 'epoch': 5.48}

 46%|████▌     | 12838/28080 [25:22:08<30:06:41,  7.11s/it]
 46%|████▌     | 12839/28080 [25:22:15<30:09:30,  7.12s/it]
                                                           
{'loss': 0.6285, 'learning_rate': 0.000296513317556724, 'epoch': 5.48}

 46%|████▌     | 12839/28080 [25:22:15<30:09:30,  7.12s/it]
 46%|████▌     | 12840/28080 [25:22:22<30:13:53,  7.14s/it]
                                                           
{'loss': 0.6115, 'learning_rate': 0.0002964849850212439, 'epoch': 5.49}

 46%|████▌     | 12840/28080 [25:22:22<30:13:53,  7.14s/it]
 46%|████▌     | 12841/28080 [25:22:30<30:13:11,  7.14s/it]
                                                           
{'loss': 0.6298, 'learning_rate': 0.00029645665186732895, 'epoch': 5.49}

 46%|████▌     | 12841/28080 [25:22:30<30:13:11,  7.14s/it]
 46%|████▌     | 12842/28080 [25:22:37<30:12:00,  7.13s/it]
                                                           
{'loss': 0.6145, 'learning_rate': 0.0002964283180953563, 'epoch': 5.49}

 46%|████▌     | 12842/28080 [25:22:37<30:12:00,  7.13s/it]
 46%|████▌     | 12843/28080 [25:22:44<30:06:28,  7.11s/it]
                                                           
{'loss': 0.6116, 'learning_rate': 0.00029639998370570265, 'epoch': 5.49}

 46%|████▌     | 12843/28080 [25:22:44<30:06:28,  7.11s/it]
 46%|████▌     | 12844/28080 [25:22:51<30:07:35,  7.12s/it]
                                                           
{'loss': 0.6245, 'learning_rate': 0.00029637164869874514, 'epoch': 5.49}

 46%|████▌     | 12844/28080 [25:22:51<30:07:35,  7.12s/it]
 46%|████▌     | 12845/28080 [25:22:58<30:06:40,  7.12s/it]
                                                           
{'loss': 0.6365, 'learning_rate': 0.00029634331307486065, 'epoch': 5.49}

 46%|████▌     | 12845/28080 [25:22:58<30:06:40,  7.12s/it]
 46%|████▌     | 12846/28080 [25:23:05<30:07:31,  7.12s/it]
                                                           
{'loss': 0.6334, 'learning_rate': 0.0002963149768344262, 'epoch': 5.49}

 46%|████▌     | 12846/28080 [25:23:05<30:07:31,  7.12s/it]
 46%|████▌     | 12847/28080 [25:23:12<29:58:49,  7.09s/it]
                                                           
{'loss': 0.6236, 'learning_rate': 0.00029628663997781883, 'epoch': 5.49}

 46%|████▌     | 12847/28080 [25:23:12<29:58:49,  7.09s/it]
 46%|████▌     | 12848/28080 [25:23:19<30:04:30,  7.11s/it]
                                                           
{'loss': 0.6031, 'learning_rate': 0.0002962583025054154, 'epoch': 5.49}

 46%|████▌     | 12848/28080 [25:23:19<30:04:30,  7.11s/it]
 46%|████▌     | 12849/28080 [25:23:26<30:08:08,  7.12s/it]
                                                           
{'loss': 0.6089, 'learning_rate': 0.000296229964417593, 'epoch': 5.49}

 46%|████▌     | 12849/28080 [25:23:26<30:08:08,  7.12s/it]
 46%|████▌     | 12850/28080 [25:23:34<30:08:03,  7.12s/it]
                                                           
{'loss': 0.6143, 'learning_rate': 0.0002962016257147286, 'epoch': 5.49}

 46%|████▌     | 12850/28080 [25:23:34<30:08:03,  7.12s/it]
 46%|████▌     | 12851/28080 [25:23:41<30:00:40,  7.09s/it]
                                                           
{'loss': 0.6378, 'learning_rate': 0.00029617328639719925, 'epoch': 5.49}

 46%|████▌     | 12851/28080 [25:23:41<30:00:40,  7.09s/it]
 46%|████▌     | 12852/28080 [25:23:48<29:54:18,  7.07s/it]
                                                           
{'loss': 0.6411, 'learning_rate': 0.00029614494646538195, 'epoch': 5.49}

 46%|████▌     | 12852/28080 [25:23:48<29:54:18,  7.07s/it]
 46%|████▌     | 12853/28080 [25:23:55<29:54:05,  7.07s/it]
                                                           
{'loss': 0.6286, 'learning_rate': 0.0002961166059196538, 'epoch': 5.49}

 46%|████▌     | 12853/28080 [25:23:55<29:54:05,  7.07s/it]
 46%|████▌     | 12854/28080 [25:24:02<29:54:56,  7.07s/it]
                                                           
{'loss': 0.6457, 'learning_rate': 0.00029608826476039174, 'epoch': 5.49}

 46%|████▌     | 12854/28080 [25:24:02<29:54:56,  7.07s/it]
 46%|████▌     | 12855/28080 [25:24:09<29:56:23,  7.08s/it]
                                                           
{'loss': 0.6293, 'learning_rate': 0.0002960599229879728, 'epoch': 5.49}

 46%|████▌     | 12855/28080 [25:24:09<29:56:23,  7.08s/it]
 46%|████▌     | 12856/28080 [25:24:16<29:49:27,  7.05s/it]
                                                           
{'loss': 0.6112, 'learning_rate': 0.0002960315806027741, 'epoch': 5.49}

 46%|████▌     | 12856/28080 [25:24:16<29:49:27,  7.05s/it]
 46%|████▌     | 12857/28080 [25:24:23<29:51:40,  7.06s/it]
                                                           
{'loss': 0.6277, 'learning_rate': 0.0002960032376051728, 'epoch': 5.49}

 46%|████▌     | 12857/28080 [25:24:23<29:51:40,  7.06s/it]
 46%|████▌     | 12858/28080 [25:24:30<29:52:18,  7.06s/it]
                                                           
{'loss': 0.6316, 'learning_rate': 0.0002959748939955459, 'epoch': 5.49}

 46%|████▌     | 12858/28080 [25:24:30<29:52:18,  7.06s/it]
 46%|████▌     | 12859/28080 [25:24:37<29:57:50,  7.09s/it]
                                                           
{'loss': 0.6359, 'learning_rate': 0.00029594654977427044, 'epoch': 5.49}

 46%|████▌     | 12859/28080 [25:24:37<29:57:50,  7.09s/it]
 46%|████▌     | 12860/28080 [25:24:44<29:57:33,  7.09s/it]
                                                           
{'loss': 0.6255, 'learning_rate': 0.00029591820494172347, 'epoch': 5.49}

 46%|████▌     | 12860/28080 [25:24:44<29:57:33,  7.09s/it]
 46%|████▌     | 12861/28080 [25:24:51<30:02:08,  7.10s/it]
                                                           
{'loss': 0.6207, 'learning_rate': 0.00029588985949828225, 'epoch': 5.49}

 46%|████▌     | 12861/28080 [25:24:51<30:02:08,  7.10s/it]
 46%|████▌     | 12862/28080 [25:24:58<30:00:36,  7.10s/it]
                                                           
{'loss': 0.6222, 'learning_rate': 0.00029586151344432364, 'epoch': 5.49}

 46%|████▌     | 12862/28080 [25:24:58<30:00:36,  7.10s/it]
 46%|████▌     | 12863/28080 [25:25:05<29:53:49,  7.07s/it]
                                                           
{'loss': 0.6317, 'learning_rate': 0.00029583316678022506, 'epoch': 5.49}

 46%|████▌     | 12863/28080 [25:25:05<29:53:49,  7.07s/it]
 46%|████▌     | 12864/28080 [25:25:13<29:56:05,  7.08s/it]
                                                           
{'loss': 0.6153, 'learning_rate': 0.0002958048195063635, 'epoch': 5.5}

 46%|████▌     | 12864/28080 [25:25:13<29:56:05,  7.08s/it]
 46%|████▌     | 12865/28080 [25:25:20<30:01:31,  7.10s/it]
                                                           
{'loss': 0.6219, 'learning_rate': 0.0002957764716231159, 'epoch': 5.5}

 46%|████▌     | 12865/28080 [25:25:20<30:01:31,  7.10s/it]
 46%|████▌     | 12866/28080 [25:25:27<29:55:59,  7.08s/it]
                                                           
{'loss': 0.6257, 'learning_rate': 0.00029574812313085976, 'epoch': 5.5}

 46%|████▌     | 12866/28080 [25:25:27<29:55:59,  7.08s/it]
 46%|████▌     | 12867/28080 [25:25:34<29:53:47,  7.07s/it]
                                                           
{'loss': 0.6324, 'learning_rate': 0.00029571977402997185, 'epoch': 5.5}

 46%|████▌     | 12867/28080 [25:25:34<29:53:47,  7.07s/it]
 46%|████▌     | 12868/28080 [25:25:41<29:56:24,  7.09s/it]
                                                           
{'loss': 0.6315, 'learning_rate': 0.0002956914243208296, 'epoch': 5.5}

 46%|████▌     | 12868/28080 [25:25:41<29:56:24,  7.09s/it]
 46%|████▌     | 12869/28080 [25:25:48<29:55:37,  7.08s/it]
                                                           
{'loss': 0.6154, 'learning_rate': 0.0002956630740038101, 'epoch': 5.5}

 46%|████▌     | 12869/28080 [25:25:48<29:55:37,  7.08s/it]
 46%|████▌     | 12870/28080 [25:25:55<29:57:17,  7.09s/it]
                                                           
{'loss': 0.6084, 'learning_rate': 0.00029563472307929053, 'epoch': 5.5}

 46%|████▌     | 12870/28080 [25:25:55<29:57:17,  7.09s/it]
 46%|████▌     | 12871/28080 [25:26:02<30:03:19,  7.11s/it]
                                                           
{'loss': 0.6168, 'learning_rate': 0.000295606371547648, 'epoch': 5.5}

 46%|████▌     | 12871/28080 [25:26:02<30:03:19,  7.11s/it]
 46%|████▌     | 12872/28080 [25:26:09<30:05:56,  7.12s/it]
                                                           
{'loss': 0.614, 'learning_rate': 0.00029557801940925974, 'epoch': 5.5}

 46%|████▌     | 12872/28080 [25:26:09<30:05:56,  7.12s/it]
 46%|████▌     | 12873/28080 [25:26:16<30:00:18,  7.10s/it]
                                                           
{'loss': 0.6021, 'learning_rate': 0.000295549666664503, 'epoch': 5.5}

 46%|████▌     | 12873/28080 [25:26:16<30:00:18,  7.10s/it]
 46%|████▌     | 12874/28080 [25:26:24<30:01:20,  7.11s/it]
                                                           
{'loss': 0.645, 'learning_rate': 0.0002955213133137549, 'epoch': 5.5}

 46%|████▌     | 12874/28080 [25:26:24<30:01:20,  7.11s/it]
 46%|████▌     | 12875/28080 [25:26:31<30:07:26,  7.13s/it]
                                                           
{'loss': 0.6189, 'learning_rate': 0.0002954929593573927, 'epoch': 5.5}

 46%|████▌     | 12875/28080 [25:26:31<30:07:26,  7.13s/it]
 46%|████▌     | 12876/28080 [25:26:38<30:06:58,  7.13s/it]
                                                           
{'loss': 0.6154, 'learning_rate': 0.00029546460479579364, 'epoch': 5.5}

 46%|████▌     | 12876/28080 [25:26:38<30:06:58,  7.13s/it]
 46%|████▌     | 12877/28080 [25:26:45<30:07:08,  7.13s/it]
                                                           
{'loss': 0.6249, 'learning_rate': 0.00029543624962933483, 'epoch': 5.5}

 46%|████▌     | 12877/28080 [25:26:45<30:07:08,  7.13s/it]
 46%|████▌     | 12878/28080 [25:26:52<30:04:51,  7.12s/it]
                                                           
{'loss': 0.6273, 'learning_rate': 0.0002954078938583937, 'epoch': 5.5}

 46%|████▌     | 12878/28080 [25:26:52<30:04:51,  7.12s/it]
 46%|████▌     | 12879/28080 [25:26:59<30:02:49,  7.12s/it]
                                                           
{'loss': 0.6443, 'learning_rate': 0.0002953795374833473, 'epoch': 5.5}

 46%|████▌     | 12879/28080 [25:26:59<30:02:49,  7.12s/it]
 46%|████▌     | 12880/28080 [25:27:06<30:09:06,  7.14s/it]
                                                           
{'loss': 0.6312, 'learning_rate': 0.000295351180504573, 'epoch': 5.5}

 46%|████▌     | 12880/28080 [25:27:06<30:09:06,  7.14s/it]
 46%|████▌     | 12881/28080 [25:27:14<30:07:30,  7.14s/it]
                                                           
{'loss': 0.6032, 'learning_rate': 0.00029532282292244806, 'epoch': 5.5}

 46%|████▌     | 12881/28080 [25:27:14<30:07:30,  7.14s/it]
 46%|████▌     | 12882/28080 [25:27:21<30:01:42,  7.11s/it]
                                                           
{'loss': 0.6222, 'learning_rate': 0.0002952944647373496, 'epoch': 5.5}

 46%|████▌     | 12882/28080 [25:27:21<30:01:42,  7.11s/it]
 46%|████▌     | 12883/28080 [25:27:28<30:02:41,  7.12s/it]
                                                           
{'loss': 0.6259, 'learning_rate': 0.00029526610594965517, 'epoch': 5.5}

 46%|████▌     | 12883/28080 [25:27:28<30:02:41,  7.12s/it]
 46%|████▌     | 12884/28080 [25:27:35<29:54:09,  7.08s/it]
                                                           
{'loss': 0.6578, 'learning_rate': 0.00029523774655974177, 'epoch': 5.5}

 46%|████▌     | 12884/28080 [25:27:35<29:54:09,  7.08s/it]
 46%|████▌     | 12885/28080 [25:27:42<29:59:42,  7.11s/it]
                                                           
{'loss': 0.6211, 'learning_rate': 0.000295209386567987, 'epoch': 5.5}

 46%|████▌     | 12885/28080 [25:27:42<29:59:42,  7.11s/it]
 46%|████▌     | 12886/28080 [25:27:49<30:06:11,  7.13s/it]
                                                           
{'loss': 0.6051, 'learning_rate': 0.0002951810259747678, 'epoch': 5.5}

 46%|████▌     | 12886/28080 [25:27:49<30:06:11,  7.13s/it]
 46%|████▌     | 12887/28080 [25:27:57<30:24:07,  7.20s/it]
                                                           
{'loss': 0.6243, 'learning_rate': 0.00029515266478046166, 'epoch': 5.51}

 46%|████▌     | 12887/28080 [25:27:57<30:24:07,  7.20s/it]
 46%|████▌     | 12888/28080 [25:28:04<30:21:01,  7.19s/it]
                                                           
{'loss': 0.623, 'learning_rate': 0.000295124302985446, 'epoch': 5.51}

 46%|████▌     | 12888/28080 [25:28:04<30:21:01,  7.19s/it]
 46%|████▌     | 12889/28080 [25:28:11<30:21:02,  7.19s/it]
                                                           
{'loss': 0.6268, 'learning_rate': 0.00029509594059009804, 'epoch': 5.51}

 46%|████▌     | 12889/28080 [25:28:11<30:21:02,  7.19s/it]
 46%|████▌     | 12890/28080 [25:28:18<30:17:05,  7.18s/it]
                                                           
{'loss': 0.6075, 'learning_rate': 0.0002950675775947951, 'epoch': 5.51}

 46%|████▌     | 12890/28080 [25:28:18<30:17:05,  7.18s/it]
 46%|████▌     | 12891/28080 [25:28:25<30:12:03,  7.16s/it]
                                                           
{'loss': 0.6155, 'learning_rate': 0.0002950392139999145, 'epoch': 5.51}

 46%|████▌     | 12891/28080 [25:28:25<30:12:03,  7.16s/it]
 46%|████▌     | 12892/28080 [25:28:32<30:07:51,  7.14s/it]
                                                           
{'loss': 0.6166, 'learning_rate': 0.00029501084980583357, 'epoch': 5.51}

 46%|████▌     | 12892/28080 [25:28:32<30:07:51,  7.14s/it]
 46%|████▌     | 12893/28080 [25:28:39<30:12:04,  7.16s/it]
                                                           
{'loss': 0.6233, 'learning_rate': 0.00029498248501292983, 'epoch': 5.51}

 46%|████▌     | 12893/28080 [25:28:39<30:12:04,  7.16s/it]
 46%|████▌     | 12894/28080 [25:28:47<30:06:11,  7.14s/it]
                                                           
{'loss': 0.6194, 'learning_rate': 0.0002949541196215805, 'epoch': 5.51}

 46%|████▌     | 12894/28080 [25:28:47<30:06:11,  7.14s/it]
 46%|████▌     | 12895/28080 [25:28:54<30:04:11,  7.13s/it]
                                                           
{'loss': 0.6259, 'learning_rate': 0.00029492575363216294, 'epoch': 5.51}

 46%|████▌     | 12895/28080 [25:28:54<30:04:11,  7.13s/it]
 46%|████▌     | 12896/28080 [25:29:01<30:04:23,  7.13s/it]
                                                           
{'loss': 0.6066, 'learning_rate': 0.0002948973870450546, 'epoch': 5.51}

 46%|████▌     | 12896/28080 [25:29:01<30:04:23,  7.13s/it]
 46%|████▌     | 12897/28080 [25:29:08<30:03:58,  7.13s/it]
                                                           
{'loss': 0.6215, 'learning_rate': 0.00029486901986063284, 'epoch': 5.51}

 46%|████▌     | 12897/28080 [25:29:08<30:03:58,  7.13s/it]
 46%|████▌     | 12898/28080 [25:29:15<30:04:27,  7.13s/it]
                                                           
{'loss': 0.6445, 'learning_rate': 0.00029484065207927506, 'epoch': 5.51}

 46%|████▌     | 12898/28080 [25:29:15<30:04:27,  7.13s/it]
 46%|████▌     | 12899/28080 [25:29:22<29:58:20,  7.11s/it]
                                                           
{'loss': 0.6319, 'learning_rate': 0.00029481228370135867, 'epoch': 5.51}

 46%|████▌     | 12899/28080 [25:29:22<29:58:20,  7.11s/it]
 46%|████▌     | 12900/28080 [25:29:29<29:54:35,  7.09s/it]
                                                           
{'loss': 0.6326, 'learning_rate': 0.0002947839147272611, 'epoch': 5.51}

 46%|████▌     | 12900/28080 [25:29:29<29:54:35,  7.09s/it]
 46%|████▌     | 12901/28080 [25:29:36<29:51:19,  7.08s/it]
                                                           
{'loss': 0.6263, 'learning_rate': 0.0002947555451573597, 'epoch': 5.51}

 46%|████▌     | 12901/28080 [25:29:36<29:51:19,  7.08s/it]
 46%|████▌     | 12902/28080 [25:29:43<29:53:42,  7.09s/it]
                                                           
{'loss': 0.6209, 'learning_rate': 0.000294727174992032, 'epoch': 5.51}

 46%|████▌     | 12902/28080 [25:29:43<29:53:42,  7.09s/it]
 46%|████▌     | 12903/28080 [25:29:51<30:03:34,  7.13s/it]
                                                           
{'loss': 0.616, 'learning_rate': 0.0002946988042316553, 'epoch': 5.51}

 46%|████▌     | 12903/28080 [25:29:51<30:03:34,  7.13s/it]
 46%|████▌     | 12904/28080 [25:29:58<30:05:55,  7.14s/it]
                                                           
{'loss': 0.6284, 'learning_rate': 0.0002946704328766072, 'epoch': 5.51}

 46%|████▌     | 12904/28080 [25:29:58<30:05:55,  7.14s/it]
 46%|████▌     | 12905/28080 [25:30:05<29:58:03,  7.11s/it]
                                                           
{'loss': 0.6446, 'learning_rate': 0.00029464206092726504, 'epoch': 5.51}

 46%|████▌     | 12905/28080 [25:30:05<29:58:03,  7.11s/it]
 46%|████▌     | 12906/28080 [25:30:12<30:00:45,  7.12s/it]
                                                           
{'loss': 0.6261, 'learning_rate': 0.00029461368838400626, 'epoch': 5.51}

 46%|████▌     | 12906/28080 [25:30:12<30:00:45,  7.12s/it]
 46%|████▌     | 12907/28080 [25:30:19<29:58:47,  7.11s/it]
                                                           
{'loss': 0.6182, 'learning_rate': 0.0002945853152472085, 'epoch': 5.51}

 46%|████▌     | 12907/28080 [25:30:19<29:58:47,  7.11s/it]
 46%|████▌     | 12908/28080 [25:30:26<30:03:35,  7.13s/it]
                                                           
{'loss': 0.6181, 'learning_rate': 0.000294556941517249, 'epoch': 5.51}

 46%|████▌     | 12908/28080 [25:30:26<30:03:35,  7.13s/it]
 46%|████▌     | 12909/28080 [25:30:33<30:05:45,  7.14s/it]
                                                           
{'loss': 0.6176, 'learning_rate': 0.0002945285671945055, 'epoch': 5.51}

 46%|████▌     | 12909/28080 [25:30:33<30:05:45,  7.14s/it]
 46%|████▌     | 12910/28080 [25:30:40<29:56:20,  7.10s/it]
                                                           
{'loss': 0.637, 'learning_rate': 0.0002945001922793552, 'epoch': 5.52}

 46%|████▌     | 12910/28080 [25:30:40<29:56:20,  7.10s/it]
 46%|████▌     | 12911/28080 [25:30:48<30:04:42,  7.14s/it]
                                                           
{'loss': 0.6062, 'learning_rate': 0.00029447181677217575, 'epoch': 5.52}

 46%|████▌     | 12911/28080 [25:30:48<30:04:42,  7.14s/it]
 46%|████▌     | 12912/28080 [25:30:55<30:05:40,  7.14s/it]
                                                           
{'loss': 0.6232, 'learning_rate': 0.0002944434406733448, 'epoch': 5.52}

 46%|████▌     | 12912/28080 [25:30:55<30:05:40,  7.14s/it]
 46%|████▌     | 12913/28080 [25:31:02<30:02:50,  7.13s/it]
                                                           
{'loss': 0.6154, 'learning_rate': 0.00029441506398323957, 'epoch': 5.52}

 46%|████▌     | 12913/28080 [25:31:02<30:02:50,  7.13s/it]
 46%|████▌     | 12914/28080 [25:31:09<30:14:01,  7.18s/it]
                                                           
{'loss': 0.6337, 'learning_rate': 0.00029438668670223793, 'epoch': 5.52}

 46%|████▌     | 12914/28080 [25:31:09<30:14:01,  7.18s/it]
 46%|████▌     | 12915/28080 [25:31:16<30:09:57,  7.16s/it]
                                                           
{'loss': 0.6232, 'learning_rate': 0.00029435830883071707, 'epoch': 5.52}

 46%|████▌     | 12915/28080 [25:31:16<30:09:57,  7.16s/it]
 46%|████▌     | 12916/28080 [25:31:23<29:56:05,  7.11s/it]
                                                           
{'loss': 0.6057, 'learning_rate': 0.00029432993036905466, 'epoch': 5.52}

 46%|████▌     | 12916/28080 [25:31:23<29:56:05,  7.11s/it]
 46%|████▌     | 12917/28080 [25:31:30<29:50:03,  7.08s/it]
                                                           
{'loss': 0.613, 'learning_rate': 0.00029430155131762834, 'epoch': 5.52}

 46%|████▌     | 12917/28080 [25:31:30<29:50:03,  7.08s/it]
 46%|████▌     | 12918/28080 [25:31:37<29:47:49,  7.07s/it]
                                                           
{'loss': 0.6041, 'learning_rate': 0.0002942731716768155, 'epoch': 5.52}

 46%|████▌     | 12918/28080 [25:31:37<29:47:49,  7.07s/it]
 46%|████▌     | 12919/28080 [25:31:44<29:51:51,  7.09s/it]
                                                           
{'loss': 0.6203, 'learning_rate': 0.00029424479144699386, 'epoch': 5.52}

 46%|████▌     | 12919/28080 [25:31:44<29:51:51,  7.09s/it]
 46%|████▌     | 12920/28080 [25:31:52<29:57:20,  7.11s/it]
                                                           
{'loss': 0.6213, 'learning_rate': 0.00029421641062854086, 'epoch': 5.52}

 46%|████▌     | 12920/28080 [25:31:52<29:57:20,  7.11s/it]
 46%|████▌     | 12921/28080 [25:31:59<30:05:20,  7.15s/it]
                                                           
{'loss': 0.6064, 'learning_rate': 0.0002941880292218342, 'epoch': 5.52}

 46%|████▌     | 12921/28080 [25:31:59<30:05:20,  7.15s/it]
 46%|████▌     | 12922/28080 [25:32:06<30:04:56,  7.14s/it]
                                                           
{'loss': 0.631, 'learning_rate': 0.0002941596472272513, 'epoch': 5.52}

 46%|████▌     | 12922/28080 [25:32:06<30:04:56,  7.14s/it]
 46%|████▌     | 12923/28080 [25:32:13<29:59:09,  7.12s/it]
                                                           
{'loss': 0.6445, 'learning_rate': 0.00029413126464516987, 'epoch': 5.52}

 46%|████▌     | 12923/28080 [25:32:13<29:59:09,  7.12s/it]
 46%|████▌     | 12924/28080 [25:32:20<29:56:50,  7.11s/it]
                                                           
{'loss': 0.6242, 'learning_rate': 0.00029410288147596755, 'epoch': 5.52}

 46%|████▌     | 12924/28080 [25:32:20<29:56:50,  7.11s/it]
 46%|████▌     | 12925/28080 [25:32:27<29:55:56,  7.11s/it]
                                                           
{'loss': 0.6356, 'learning_rate': 0.0002940744977200218, 'epoch': 5.52}

 46%|████▌     | 12925/28080 [25:32:27<29:55:56,  7.11s/it]
 46%|████▌     | 12926/28080 [25:32:34<29:54:28,  7.10s/it]
                                                           
{'loss': 0.6311, 'learning_rate': 0.00029404611337771044, 'epoch': 5.52}

 46%|████▌     | 12926/28080 [25:32:34<29:54:28,  7.10s/it]
 46%|████▌     | 12927/28080 [25:32:41<29:58:09,  7.12s/it]
                                                           
{'loss': 0.6201, 'learning_rate': 0.00029401772844941086, 'epoch': 5.52}

 46%|████▌     | 12927/28080 [25:32:41<29:58:09,  7.12s/it]
 46%|████▌     | 12928/28080 [25:32:48<29:51:37,  7.09s/it]
                                                           
{'loss': 0.6171, 'learning_rate': 0.00029398934293550094, 'epoch': 5.52}

 46%|████▌     | 12928/28080 [25:32:48<29:51:37,  7.09s/it]
 46%|████▌     | 12929/28080 [25:32:55<29:44:57,  7.07s/it]
                                                           
{'loss': 0.6135, 'learning_rate': 0.0002939609568363581, 'epoch': 5.52}

 46%|████▌     | 12929/28080 [25:32:55<29:44:57,  7.07s/it]
 46%|████▌     | 12930/28080 [25:33:03<29:48:06,  7.08s/it]
                                                           
{'loss': 0.6186, 'learning_rate': 0.00029393257015236006, 'epoch': 5.52}

 46%|████▌     | 12930/28080 [25:33:03<29:48:06,  7.08s/it]
 46%|████▌     | 12931/28080 [25:33:10<29:48:34,  7.08s/it]
                                                           
{'loss': 0.6192, 'learning_rate': 0.00029390418288388463, 'epoch': 5.52}

 46%|████▌     | 12931/28080 [25:33:10<29:48:34,  7.08s/it]
 46%|████▌     | 12932/28080 [25:33:17<29:55:32,  7.11s/it]
                                                           
{'loss': 0.6126, 'learning_rate': 0.00029387579503130926, 'epoch': 5.52}

 46%|████▌     | 12932/28080 [25:33:17<29:55:32,  7.11s/it]
 46%|████▌     | 12933/28080 [25:33:24<29:57:25,  7.12s/it]
                                                           
{'loss': 0.6067, 'learning_rate': 0.0002938474065950117, 'epoch': 5.52}

 46%|████▌     | 12933/28080 [25:33:24<29:57:25,  7.12s/it]
 46%|████▌     | 12934/28080 [25:33:31<30:04:21,  7.15s/it]
                                                           
{'loss': 0.6371, 'learning_rate': 0.0002938190175753696, 'epoch': 5.53}

 46%|████▌     | 12934/28080 [25:33:31<30:04:21,  7.15s/it]
 46%|████▌     | 12935/28080 [25:33:38<29:55:40,  7.11s/it]
                                                           
{'loss': 0.6371, 'learning_rate': 0.00029379062797276075, 'epoch': 5.53}

 46%|████▌     | 12935/28080 [25:33:38<29:55:40,  7.11s/it]
 46%|████▌     | 12936/28080 [25:33:45<29:50:25,  7.09s/it]
                                                           
{'loss': 0.6037, 'learning_rate': 0.00029376223778756274, 'epoch': 5.53}

 46%|████▌     | 12936/28080 [25:33:45<29:50:25,  7.09s/it]
 46%|████▌     | 12937/28080 [25:33:52<29:52:07,  7.10s/it]
                                                           
{'loss': 0.6124, 'learning_rate': 0.00029373384702015325, 'epoch': 5.53}

 46%|████▌     | 12937/28080 [25:33:52<29:52:07,  7.10s/it]
 46%|████▌     | 12938/28080 [25:34:00<29:52:05,  7.10s/it]
                                                           
{'loss': 0.6077, 'learning_rate': 0.00029370545567091014, 'epoch': 5.53}

 46%|████▌     | 12938/28080 [25:34:00<29:52:05,  7.10s/it]
 46%|████▌     | 12939/28080 [25:34:07<30:01:03,  7.14s/it]
                                                           
{'loss': 0.6112, 'learning_rate': 0.00029367706374021097, 'epoch': 5.53}

 46%|████▌     | 12939/28080 [25:34:07<30:01:03,  7.14s/it]
 46%|████▌     | 12940/28080 [25:34:14<30:07:36,  7.16s/it]
                                                           
{'loss': 0.6099, 'learning_rate': 0.00029364867122843354, 'epoch': 5.53}

 46%|████▌     | 12940/28080 [25:34:14<30:07:36,  7.16s/it]
 46%|████▌     | 12941/28080 [25:34:21<30:05:59,  7.16s/it]
                                                           
{'loss': 0.6015, 'learning_rate': 0.0002936202781359556, 'epoch': 5.53}

 46%|████▌     | 12941/28080 [25:34:21<30:05:59,  7.16s/it]
 46%|████▌     | 12942/28080 [25:34:28<29:56:16,  7.12s/it]
                                                           
{'loss': 0.612, 'learning_rate': 0.0002935918844631548, 'epoch': 5.53}

 46%|████▌     | 12942/28080 [25:34:28<29:56:16,  7.12s/it]
 46%|████▌     | 12943/28080 [25:34:35<29:59:28,  7.13s/it]
                                                           
{'loss': 0.6118, 'learning_rate': 0.00029356349021040894, 'epoch': 5.53}

 46%|████▌     | 12943/28080 [25:34:35<29:59:28,  7.13s/it]
 46%|████▌     | 12944/28080 [25:34:42<29:51:01,  7.10s/it]
                                                           
{'loss': 0.6153, 'learning_rate': 0.0002935350953780958, 'epoch': 5.53}

 46%|████▌     | 12944/28080 [25:34:42<29:51:01,  7.10s/it]
 46%|████▌     | 12945/28080 [25:34:49<29:53:07,  7.11s/it]
                                                           
{'loss': 0.6284, 'learning_rate': 0.00029350669996659317, 'epoch': 5.53}

 46%|████▌     | 12945/28080 [25:34:49<29:53:07,  7.11s/it]
 46%|████▌     | 12946/28080 [25:34:57<29:53:14,  7.11s/it]
                                                           
{'loss': 0.6089, 'learning_rate': 0.0002934783039762788, 'epoch': 5.53}

 46%|████▌     | 12946/28080 [25:34:57<29:53:14,  7.11s/it]
 46%|████▌     | 12947/28080 [25:35:04<29:57:50,  7.13s/it]
                                                           
{'loss': 0.6231, 'learning_rate': 0.00029344990740753034, 'epoch': 5.53}

 46%|████▌     | 12947/28080 [25:35:04<29:57:50,  7.13s/it]
 46%|████▌     | 12948/28080 [25:35:11<29:58:40,  7.13s/it]
                                                           
{'loss': 0.6228, 'learning_rate': 0.0002934215102607258, 'epoch': 5.53}

 46%|████▌     | 12948/28080 [25:35:11<29:58:40,  7.13s/it]
 46%|████▌     | 12949/28080 [25:35:18<30:05:21,  7.16s/it]
                                                           
{'loss': 0.6206, 'learning_rate': 0.0002933931125362428, 'epoch': 5.53}

 46%|████▌     | 12949/28080 [25:35:18<30:05:21,  7.16s/it]
 46%|████▌     | 12950/28080 [25:35:25<30:09:34,  7.18s/it]
                                                           
{'loss': 0.6247, 'learning_rate': 0.00029336471423445923, 'epoch': 5.53}

 46%|████▌     | 12950/28080 [25:35:25<30:09:34,  7.18s/it]
 46%|████▌     | 12951/28080 [25:35:32<30:04:48,  7.16s/it]
                                                           
{'loss': 0.6263, 'learning_rate': 0.00029333631535575285, 'epoch': 5.53}

 46%|████▌     | 12951/28080 [25:35:32<30:04:48,  7.16s/it]
 46%|████▌     | 12952/28080 [25:35:40<30:08:29,  7.17s/it]
                                                           
{'loss': 0.6051, 'learning_rate': 0.0002933079159005015, 'epoch': 5.53}

 46%|████▌     | 12952/28080 [25:35:40<30:08:29,  7.17s/it]
 46%|████▌     | 12953/28080 [25:35:47<30:08:42,  7.17s/it]
                                                           
{'loss': 0.6161, 'learning_rate': 0.00029327951586908304, 'epoch': 5.53}

 46%|████▌     | 12953/28080 [25:35:47<30:08:42,  7.17s/it]
 46%|████▌     | 12954/28080 [25:35:54<30:03:50,  7.16s/it]
                                                           
{'loss': 0.6277, 'learning_rate': 0.0002932511152618752, 'epoch': 5.53}

 46%|████▌     | 12954/28080 [25:35:54<30:03:50,  7.16s/it]
 46%|████▌     | 12955/28080 [25:36:01<30:01:48,  7.15s/it]
                                                           
{'loss': 0.647, 'learning_rate': 0.000293222714079256, 'epoch': 5.53}

 46%|████▌     | 12955/28080 [25:36:01<30:01:48,  7.15s/it]
 46%|████▌     | 12956/28080 [25:36:08<30:05:55,  7.16s/it]
                                                           
{'loss': 0.6357, 'learning_rate': 0.0002931943123216031, 'epoch': 5.53}

 46%|████▌     | 12956/28080 [25:36:08<30:05:55,  7.16s/it]
 46%|████▌     | 12957/28080 [25:36:15<30:08:21,  7.17s/it]
                                                           
{'loss': 0.6268, 'learning_rate': 0.0002931659099892945, 'epoch': 5.54}

 46%|████▌     | 12957/28080 [25:36:15<30:08:21,  7.17s/it]
 46%|████▌     | 12958/28080 [25:36:23<30:02:54,  7.15s/it]
                                                           
{'loss': 0.6085, 'learning_rate': 0.00029313750708270786, 'epoch': 5.54}

 46%|████▌     | 12958/28080 [25:36:23<30:02:54,  7.15s/it]
 46%|████▌     | 12959/28080 [25:36:30<30:00:22,  7.14s/it]
                                                           
{'loss': 0.648, 'learning_rate': 0.0002931091036022213, 'epoch': 5.54}

 46%|████▌     | 12959/28080 [25:36:30<30:00:22,  7.14s/it]
 46%|████▌     | 12960/28080 [25:36:37<30:06:34,  7.17s/it]
                                                           
{'loss': 0.6111, 'learning_rate': 0.0002930806995482126, 'epoch': 5.54}

 46%|████▌     | 12960/28080 [25:36:37<30:06:34,  7.17s/it]
 46%|████▌     | 12961/28080 [25:36:44<30:01:20,  7.15s/it]
                                                           
{'loss': 0.6245, 'learning_rate': 0.00029305229492105955, 'epoch': 5.54}

 46%|████▌     | 12961/28080 [25:36:44<30:01:20,  7.15s/it]
 46%|████▌     | 12962/28080 [25:36:51<29:58:36,  7.14s/it]
                                                           
{'loss': 0.6223, 'learning_rate': 0.00029302388972114024, 'epoch': 5.54}

 46%|████▌     | 12962/28080 [25:36:51<29:58:36,  7.14s/it]
 46%|████▌     | 12963/28080 [25:36:58<29:56:59,  7.13s/it]
                                                           
{'loss': 0.6279, 'learning_rate': 0.0002929954839488324, 'epoch': 5.54}

 46%|████▌     | 12963/28080 [25:36:58<29:56:59,  7.13s/it]
 46%|████▌     | 12964/28080 [25:37:05<29:59:10,  7.14s/it]
                                                           
{'loss': 0.6158, 'learning_rate': 0.00029296707760451406, 'epoch': 5.54}

 46%|████▌     | 12964/28080 [25:37:05<29:59:10,  7.14s/it]
 46%|████▌     | 12965/28080 [25:37:13<29:56:29,  7.13s/it]
                                                           
{'loss': 0.6235, 'learning_rate': 0.0002929386706885631, 'epoch': 5.54}

 46%|████▌     | 12965/28080 [25:37:13<29:56:29,  7.13s/it]
 46%|████▌     | 12966/28080 [25:37:20<29:54:09,  7.12s/it]
                                                           
{'loss': 0.6214, 'learning_rate': 0.0002929102632013573, 'epoch': 5.54}

 46%|████▌     | 12966/28080 [25:37:20<29:54:09,  7.12s/it]
 46%|████▌     | 12967/28080 [25:37:27<29:59:19,  7.14s/it]
                                                           
{'loss': 0.619, 'learning_rate': 0.0002928818551432748, 'epoch': 5.54}

 46%|████▌     | 12967/28080 [25:37:27<29:59:19,  7.14s/it]
 46%|████▌     | 12968/28080 [25:37:34<29:54:53,  7.13s/it]
                                                           
{'loss': 0.6175, 'learning_rate': 0.0002928534465146934, 'epoch': 5.54}

 46%|████▌     | 12968/28080 [25:37:34<29:54:53,  7.13s/it]
 46%|████▌     | 12969/28080 [25:37:41<29:58:01,  7.14s/it]
                                                           
{'loss': 0.6181, 'learning_rate': 0.0002928250373159912, 'epoch': 5.54}

 46%|████▌     | 12969/28080 [25:37:41<29:58:01,  7.14s/it]
 46%|████▌     | 12970/28080 [25:37:48<29:53:23,  7.12s/it]
                                                           
{'loss': 0.6146, 'learning_rate': 0.000292796627547546, 'epoch': 5.54}

 46%|████▌     | 12970/28080 [25:37:48<29:53:23,  7.12s/it]
 46%|████▌     | 12971/28080 [25:37:55<29:56:41,  7.13s/it]
                                                           
{'loss': 0.6001, 'learning_rate': 0.0002927682172097357, 'epoch': 5.54}

 46%|████▌     | 12971/28080 [25:37:55<29:56:41,  7.13s/it]
 46%|████▌     | 12972/28080 [25:38:02<29:52:48,  7.12s/it]
                                                           
{'loss': 0.6084, 'learning_rate': 0.0002927398063029386, 'epoch': 5.54}

 46%|████▌     | 12972/28080 [25:38:02<29:52:48,  7.12s/it]
 46%|████▌     | 12973/28080 [25:38:09<29:51:30,  7.12s/it]
                                                           
{'loss': 0.6162, 'learning_rate': 0.00029271139482753235, 'epoch': 5.54}

 46%|████▌     | 12973/28080 [25:38:09<29:51:30,  7.12s/it]
 46%|████▌     | 12974/28080 [25:38:17<29:54:39,  7.13s/it]
                                                           
{'loss': 0.6315, 'learning_rate': 0.0002926829827838951, 'epoch': 5.54}

 46%|████▌     | 12974/28080 [25:38:17<29:54:39,  7.13s/it]
 46%|████▌     | 12975/28080 [25:38:24<29:57:12,  7.14s/it]
                                                           
{'loss': 0.6297, 'learning_rate': 0.0002926545701724048, 'epoch': 5.54}

 46%|████▌     | 12975/28080 [25:38:24<29:57:12,  7.14s/it]
 46%|████▌     | 12976/28080 [25:38:31<29:50:18,  7.11s/it]
                                                           
{'loss': 0.6243, 'learning_rate': 0.0002926261569934394, 'epoch': 5.54}

 46%|████▌     | 12976/28080 [25:38:31<29:50:18,  7.11s/it]
 46%|████▌     | 12977/28080 [25:38:38<29:53:13,  7.12s/it]
                                                           
{'loss': 0.6254, 'learning_rate': 0.00029259774324737696, 'epoch': 5.54}

 46%|████▌     | 12977/28080 [25:38:38<29:53:13,  7.12s/it]
 46%|████▌     | 12978/28080 [25:38:45<30:02:35,  7.16s/it]
                                                           
{'loss': 0.6224, 'learning_rate': 0.00029256932893459556, 'epoch': 5.54}

 46%|████▌     | 12978/28080 [25:38:45<30:02:35,  7.16s/it]
 46%|████▌     | 12979/28080 [25:38:53<30:20:06,  7.23s/it]
                                                           
{'loss': 0.6208, 'learning_rate': 0.0002925409140554731, 'epoch': 5.54}

 46%|████▌     | 12979/28080 [25:38:53<30:20:06,  7.23s/it]
 46%|████▌     | 12980/28080 [25:39:00<30:17:08,  7.22s/it]
                                                           
{'loss': 0.6158, 'learning_rate': 0.00029251249861038766, 'epoch': 5.54}

 46%|████▌     | 12980/28080 [25:39:00<30:17:08,  7.22s/it]
 46%|████▌     | 12981/28080 [25:39:07<30:07:36,  7.18s/it]
                                                           
{'loss': 0.6279, 'learning_rate': 0.0002924840825997173, 'epoch': 5.55}

 46%|████▌     | 12981/28080 [25:39:07<30:07:36,  7.18s/it]
 46%|████▌     | 12982/28080 [25:39:14<30:10:33,  7.20s/it]
                                                           
{'loss': 0.6132, 'learning_rate': 0.00029245566602384003, 'epoch': 5.55}

 46%|████▌     | 12982/28080 [25:39:14<30:10:33,  7.20s/it]
 46%|████▌     | 12983/28080 [25:39:21<30:08:08,  7.19s/it]
                                                           
{'loss': 0.6297, 'learning_rate': 0.000292427248883134, 'epoch': 5.55}

 46%|████▌     | 12983/28080 [25:39:21<30:08:08,  7.19s/it]
 46%|████▌     | 12984/28080 [25:39:28<29:55:49,  7.14s/it]
                                                           
{'loss': 0.6425, 'learning_rate': 0.0002923988311779771, 'epoch': 5.55}

 46%|████▌     | 12984/28080 [25:39:28<29:55:49,  7.14s/it]
 46%|████▌     | 12985/28080 [25:39:36<30:02:20,  7.16s/it]
                                                           
{'loss': 0.6288, 'learning_rate': 0.00029237041290874747, 'epoch': 5.55}

 46%|████▌     | 12985/28080 [25:39:36<30:02:20,  7.16s/it]
 46%|████▌     | 12986/28080 [25:39:43<30:02:56,  7.17s/it]
                                                           
{'loss': 0.6109, 'learning_rate': 0.00029234199407582334, 'epoch': 5.55}

 46%|████▌     | 12986/28080 [25:39:43<30:02:56,  7.17s/it]
 46%|████▋     | 12987/28080 [25:39:50<30:01:18,  7.16s/it]
                                                           
{'loss': 0.653, 'learning_rate': 0.0002923135746795825, 'epoch': 5.55}

 46%|████▋     | 12987/28080 [25:39:50<30:01:18,  7.16s/it]
 46%|████▋     | 12988/28080 [25:39:57<30:04:46,  7.18s/it]
                                                           
{'loss': 0.6308, 'learning_rate': 0.00029228515472040336, 'epoch': 5.55}

 46%|████▋     | 12988/28080 [25:39:57<30:04:46,  7.18s/it]
 46%|████▋     | 12989/28080 [25:40:04<30:08:54,  7.19s/it]
                                                           
{'loss': 0.6348, 'learning_rate': 0.00029225673419866385, 'epoch': 5.55}

 46%|████▋     | 12989/28080 [25:40:04<30:08:54,  7.19s/it]
 46%|████▋     | 12990/28080 [25:40:11<30:00:48,  7.16s/it]
                                                           
{'loss': 0.6254, 'learning_rate': 0.000292228313114742, 'epoch': 5.55}

 46%|████▋     | 12990/28080 [25:40:11<30:00:48,  7.16s/it]
 46%|████▋     | 12991/28080 [25:40:19<29:55:17,  7.14s/it]
                                                           
{'loss': 0.6186, 'learning_rate': 0.00029219989146901605, 'epoch': 5.55}

 46%|████▋     | 12991/28080 [25:40:19<29:55:17,  7.14s/it]
 46%|████▋     | 12992/28080 [25:40:26<30:07:21,  7.19s/it]
                                                           
{'loss': 0.6314, 'learning_rate': 0.000292171469261864, 'epoch': 5.55}

 46%|████▋     | 12992/28080 [25:40:26<30:07:21,  7.19s/it]
 46%|████▋     | 12993/28080 [25:40:33<30:10:20,  7.20s/it]
                                                           
{'loss': 0.6162, 'learning_rate': 0.0002921430464936642, 'epoch': 5.55}

 46%|████▋     | 12993/28080 [25:40:33<30:10:20,  7.20s/it]
 46%|████▋     | 12994/28080 [25:40:40<29:58:49,  7.15s/it]
                                                           
{'loss': 0.6091, 'learning_rate': 0.00029211462316479445, 'epoch': 5.55}

 46%|████▋     | 12994/28080 [25:40:40<29:58:49,  7.15s/it]
 46%|████▋     | 12995/28080 [25:40:47<30:03:20,  7.17s/it]
                                                           
{'loss': 0.6151, 'learning_rate': 0.00029208619927563326, 'epoch': 5.55}

 46%|████▋     | 12995/28080 [25:40:47<30:03:20,  7.17s/it]
 46%|████▋     | 12996/28080 [25:40:54<29:57:55,  7.15s/it]
                                                           
{'loss': 0.6183, 'learning_rate': 0.0002920577748265585, 'epoch': 5.55}

 46%|████▋     | 12996/28080 [25:40:54<29:57:55,  7.15s/it]
 46%|████▋     | 12997/28080 [25:41:02<29:57:16,  7.15s/it]
                                                           
{'loss': 0.6039, 'learning_rate': 0.0002920293498179485, 'epoch': 5.55}

 46%|████▋     | 12997/28080 [25:41:02<29:57:16,  7.15s/it]
 46%|████▋     | 12998/28080 [25:41:09<29:55:16,  7.14s/it]
                                                           
{'loss': 0.6511, 'learning_rate': 0.0002920009242501813, 'epoch': 5.55}

 46%|████▋     | 12998/28080 [25:41:09<29:55:16,  7.14s/it]
 46%|████▋     | 12999/28080 [25:41:16<29:58:32,  7.16s/it]
                                                           
{'loss': 0.6205, 'learning_rate': 0.0002919724981236352, 'epoch': 5.55}

 46%|████▋     | 12999/28080 [25:41:16<29:58:32,  7.16s/it]
 46%|████▋     | 13000/28080 [25:41:23<30:06:00,  7.19s/it]
                                                           
{'loss': 0.6221, 'learning_rate': 0.0002919440714386883, 'epoch': 5.55}

 46%|████▋     | 13000/28080 [25:41:23<30:06:00,  7.19s/it]
 46%|████▋     | 13001/28080 [25:41:30<29:59:58,  7.16s/it]
                                                           
{'loss': 0.603, 'learning_rate': 0.00029191564419571875, 'epoch': 5.55}

 46%|████▋     | 13001/28080 [25:41:30<29:59:58,  7.16s/it]
 46%|████▋     | 13002/28080 [25:41:37<30:02:04,  7.17s/it]
                                                           
{'loss': 0.6328, 'learning_rate': 0.00029188721639510486, 'epoch': 5.55}

 46%|████▋     | 13002/28080 [25:41:37<30:02:04,  7.17s/it]
 46%|████▋     | 13003/28080 [25:41:45<30:05:08,  7.18s/it]
                                                           
{'loss': 0.627, 'learning_rate': 0.0002918587880372247, 'epoch': 5.55}

 46%|████▋     | 13003/28080 [25:41:45<30:05:08,  7.18s/it]
 46%|████▋     | 13004/28080 [25:41:52<29:58:12,  7.16s/it]
                                                           
{'loss': 0.6311, 'learning_rate': 0.0002918303591224566, 'epoch': 5.56}

 46%|████▋     | 13004/28080 [25:41:52<29:58:12,  7.16s/it]
 46%|████▋     | 13005/28080 [25:41:59<29:58:03,  7.16s/it]
                                                           
{'loss': 0.6249, 'learning_rate': 0.00029180192965117874, 'epoch': 5.56}

 46%|████▋     | 13005/28080 [25:41:59<29:58:03,  7.16s/it]
 46%|████▋     | 13006/28080 [25:42:06<29:48:08,  7.12s/it]
                                                           
{'loss': 0.6253, 'learning_rate': 0.0002917734996237693, 'epoch': 5.56}

 46%|████▋     | 13006/28080 [25:42:06<29:48:08,  7.12s/it]
 46%|████▋     | 13007/28080 [25:42:13<29:42:26,  7.10s/it]
                                                           
{'loss': 0.6315, 'learning_rate': 0.00029174506904060656, 'epoch': 5.56}

 46%|████▋     | 13007/28080 [25:42:13<29:42:26,  7.10s/it]
 46%|████▋     | 13008/28080 [25:42:20<29:39:15,  7.08s/it]
                                                           
{'loss': 0.6296, 'learning_rate': 0.0002917166379020687, 'epoch': 5.56}

 46%|████▋     | 13008/28080 [25:42:20<29:39:15,  7.08s/it]
 46%|████▋     | 13009/28080 [25:42:27<29:49:16,  7.12s/it]
                                                           
{'loss': 0.615, 'learning_rate': 0.000291688206208534, 'epoch': 5.56}

 46%|████▋     | 13009/28080 [25:42:27<29:49:16,  7.12s/it]
 46%|████▋     | 13010/28080 [25:42:34<29:45:18,  7.11s/it]
                                                           
{'loss': 0.6147, 'learning_rate': 0.0002916597739603808, 'epoch': 5.56}

 46%|████▋     | 13010/28080 [25:42:34<29:45:18,  7.11s/it]
 46%|████▋     | 13011/28080 [25:42:41<29:37:02,  7.08s/it]
                                                           
{'loss': 0.619, 'learning_rate': 0.0002916313411579872, 'epoch': 5.56}

 46%|████▋     | 13011/28080 [25:42:41<29:37:02,  7.08s/it]
 46%|████▋     | 13012/28080 [25:42:48<29:32:26,  7.06s/it]
                                                           
{'loss': 0.6338, 'learning_rate': 0.00029160290780173165, 'epoch': 5.56}

 46%|████▋     | 13012/28080 [25:42:48<29:32:26,  7.06s/it]
 46%|████▋     | 13013/28080 [25:42:55<29:32:35,  7.06s/it]
                                                           
{'loss': 0.6261, 'learning_rate': 0.0002915744738919923, 'epoch': 5.56}

 46%|████▋     | 13013/28080 [25:42:55<29:32:35,  7.06s/it]
 46%|████▋     | 13014/28080 [25:43:02<29:35:55,  7.07s/it]
                                                           
{'loss': 0.601, 'learning_rate': 0.00029154603942914745, 'epoch': 5.56}

 46%|████▋     | 13014/28080 [25:43:02<29:35:55,  7.07s/it]
 46%|████▋     | 13015/28080 [25:43:10<29:32:04,  7.06s/it]
                                                           
{'loss': 0.619, 'learning_rate': 0.00029151760441357543, 'epoch': 5.56}

 46%|████▋     | 13015/28080 [25:43:10<29:32:04,  7.06s/it]
 46%|████▋     | 13016/28080 [25:43:17<29:33:56,  7.07s/it]
                                                           
{'loss': 0.617, 'learning_rate': 0.00029148916884565445, 'epoch': 5.56}

 46%|████▋     | 13016/28080 [25:43:17<29:33:56,  7.07s/it]
 46%|████▋     | 13017/28080 [25:43:24<29:38:30,  7.08s/it]
                                                           
{'loss': 0.6365, 'learning_rate': 0.00029146073272576294, 'epoch': 5.56}

 46%|████▋     | 13017/28080 [25:43:24<29:38:30,  7.08s/it]
 46%|████▋     | 13018/28080 [25:43:31<29:47:19,  7.12s/it]
                                                           
{'loss': 0.6277, 'learning_rate': 0.0002914322960542791, 'epoch': 5.56}

 46%|████▋     | 13018/28080 [25:43:31<29:47:19,  7.12s/it]
 46%|████▋     | 13019/28080 [25:43:38<29:52:36,  7.14s/it]
                                                           
{'loss': 0.603, 'learning_rate': 0.00029140385883158135, 'epoch': 5.56}

 46%|████▋     | 13019/28080 [25:43:38<29:52:36,  7.14s/it]
 46%|████▋     | 13020/28080 [25:43:45<29:56:34,  7.16s/it]
                                                           
{'loss': 0.6325, 'learning_rate': 0.000291375421058048, 'epoch': 5.56}

 46%|████▋     | 13020/28080 [25:43:45<29:56:34,  7.16s/it]
 46%|████▋     | 13021/28080 [25:43:52<29:53:19,  7.15s/it]
                                                           
{'loss': 0.6162, 'learning_rate': 0.0002913469827340572, 'epoch': 5.56}

 46%|████▋     | 13021/28080 [25:43:52<29:53:19,  7.15s/it]
 46%|████▋     | 13022/28080 [25:44:00<29:47:49,  7.12s/it]
                                                           
{'loss': 0.6142, 'learning_rate': 0.0002913185438599877, 'epoch': 5.56}

 46%|████▋     | 13022/28080 [25:44:00<29:47:49,  7.12s/it]
 46%|████▋     | 13023/28080 [25:44:07<29:50:01,  7.13s/it]
                                                           
{'loss': 0.6122, 'learning_rate': 0.0002912901044362174, 'epoch': 5.56}

 46%|████▋     | 13023/28080 [25:44:07<29:50:01,  7.13s/it]
 46%|████▋     | 13024/28080 [25:44:14<29:42:15,  7.10s/it]
                                                           
{'loss': 0.619, 'learning_rate': 0.00029126166446312495, 'epoch': 5.56}

 46%|████▋     | 13024/28080 [25:44:14<29:42:15,  7.10s/it]
 46%|████▋     | 13025/28080 [25:44:21<29:36:58,  7.08s/it]
                                                           
{'loss': 0.6256, 'learning_rate': 0.0002912332239410886, 'epoch': 5.56}

 46%|████▋     | 13025/28080 [25:44:21<29:36:58,  7.08s/it]
 46%|████▋     | 13026/28080 [25:44:28<29:45:00,  7.11s/it]
                                                           
{'loss': 0.6168, 'learning_rate': 0.0002912047828704867, 'epoch': 5.56}

 46%|████▋     | 13026/28080 [25:44:28<29:45:00,  7.11s/it]
 46%|████▋     | 13027/28080 [25:44:35<29:47:08,  7.12s/it]
                                                           
{'loss': 0.6482, 'learning_rate': 0.0002911763412516977, 'epoch': 5.57}

 46%|████▋     | 13027/28080 [25:44:35<29:47:08,  7.12s/it]
 46%|████▋     | 13028/28080 [25:44:42<29:46:43,  7.12s/it]
                                                           
{'loss': 0.6389, 'learning_rate': 0.0002911478990851, 'epoch': 5.57}

 46%|████▋     | 13028/28080 [25:44:42<29:46:43,  7.12s/it]
 46%|████▋     | 13029/28080 [25:44:49<29:50:15,  7.14s/it]
                                                           
{'loss': 0.6212, 'learning_rate': 0.00029111945637107196, 'epoch': 5.57}

 46%|████▋     | 13029/28080 [25:44:49<29:50:15,  7.14s/it]
 46%|████▋     | 13030/28080 [25:44:56<29:41:44,  7.10s/it]
                                                           
{'loss': 0.6165, 'learning_rate': 0.0002910910131099919, 'epoch': 5.57}

 46%|████▋     | 13030/28080 [25:44:56<29:41:44,  7.10s/it]
 46%|████▋     | 13031/28080 [25:45:04<29:45:26,  7.12s/it]
                                                           
{'loss': 0.6105, 'learning_rate': 0.00029106256930223835, 'epoch': 5.57}

 46%|████▋     | 13031/28080 [25:45:04<29:45:26,  7.12s/it]
 46%|████▋     | 13032/28080 [25:45:11<29:44:36,  7.12s/it]
                                                           
{'loss': 0.6479, 'learning_rate': 0.00029103412494818967, 'epoch': 5.57}

 46%|████▋     | 13032/28080 [25:45:11<29:44:36,  7.12s/it]
 46%|████▋     | 13033/28080 [25:45:18<29:44:40,  7.12s/it]
                                                           
{'loss': 0.6107, 'learning_rate': 0.00029100568004822427, 'epoch': 5.57}

 46%|████▋     | 13033/28080 [25:45:18<29:44:40,  7.12s/it]
 46%|████▋     | 13034/28080 [25:45:25<29:43:55,  7.11s/it]
                                                           
{'loss': 0.6355, 'learning_rate': 0.00029097723460272065, 'epoch': 5.57}

 46%|████▋     | 13034/28080 [25:45:25<29:43:55,  7.11s/it]
 46%|████▋     | 13035/28080 [25:45:32<29:36:45,  7.09s/it]
                                                           
{'loss': 0.618, 'learning_rate': 0.0002909487886120571, 'epoch': 5.57}

 46%|████▋     | 13035/28080 [25:45:32<29:36:45,  7.09s/it]
 46%|████▋     | 13036/28080 [25:45:39<29:40:25,  7.10s/it]
                                                           
{'loss': 0.6302, 'learning_rate': 0.0002909203420766122, 'epoch': 5.57}

 46%|████▋     | 13036/28080 [25:45:39<29:40:25,  7.10s/it]
 46%|████▋     | 13037/28080 [25:45:46<29:48:10,  7.13s/it]
                                                           
{'loss': 0.6174, 'learning_rate': 0.0002908918949967644, 'epoch': 5.57}

 46%|████▋     | 13037/28080 [25:45:46<29:48:10,  7.13s/it]
 46%|████▋     | 13038/28080 [25:45:53<29:47:10,  7.13s/it]
                                                           
{'loss': 0.6346, 'learning_rate': 0.0002908634473728922, 'epoch': 5.57}

 46%|████▋     | 13038/28080 [25:45:53<29:47:10,  7.13s/it]
 46%|████▋     | 13039/28080 [25:46:00<29:45:06,  7.12s/it]
                                                           
{'loss': 0.6345, 'learning_rate': 0.0002908349992053739, 'epoch': 5.57}

 46%|████▋     | 13039/28080 [25:46:00<29:45:06,  7.12s/it]
 46%|████▋     | 13040/28080 [25:46:08<29:51:20,  7.15s/it]
                                                           
{'loss': 0.6264, 'learning_rate': 0.000290806550494588, 'epoch': 5.57}

 46%|████▋     | 13040/28080 [25:46:08<29:51:20,  7.15s/it]
 46%|████▋     | 13041/28080 [25:46:15<29:54:03,  7.16s/it]
                                                           
{'loss': 0.6378, 'learning_rate': 0.0002907781012409131, 'epoch': 5.57}

 46%|████▋     | 13041/28080 [25:46:15<29:54:03,  7.16s/it]
 46%|████▋     | 13042/28080 [25:46:22<29:41:25,  7.11s/it]
                                                           
{'loss': 0.6201, 'learning_rate': 0.0002907496514447277, 'epoch': 5.57}

 46%|████▋     | 13042/28080 [25:46:22<29:41:25,  7.11s/it]
 46%|████▋     | 13043/28080 [25:46:29<29:43:34,  7.12s/it]
                                                           
{'loss': 0.6306, 'learning_rate': 0.0002907212011064101, 'epoch': 5.57}

 46%|████▋     | 13043/28080 [25:46:29<29:43:34,  7.12s/it]
 46%|████▋     | 13044/28080 [25:46:36<29:48:14,  7.14s/it]
                                                           
{'loss': 0.6142, 'learning_rate': 0.000290692750226339, 'epoch': 5.57}

 46%|████▋     | 13044/28080 [25:46:36<29:48:14,  7.14s/it]
 46%|████▋     | 13045/28080 [25:46:43<29:41:25,  7.11s/it]
                                                           
{'loss': 0.6317, 'learning_rate': 0.0002906642988048929, 'epoch': 5.57}

 46%|████▋     | 13045/28080 [25:46:43<29:41:25,  7.11s/it]
 46%|████▋     | 13046/28080 [25:46:50<29:43:25,  7.12s/it]
                                                           
{'loss': 0.611, 'learning_rate': 0.00029063584684245014, 'epoch': 5.57}

 46%|████▋     | 13046/28080 [25:46:50<29:43:25,  7.12s/it]
 46%|████▋     | 13047/28080 [25:46:58<29:50:00,  7.14s/it]
                                                           
{'loss': 0.6069, 'learning_rate': 0.00029060739433938945, 'epoch': 5.57}

 46%|████▋     | 13047/28080 [25:46:58<29:50:00,  7.14s/it]
 46%|████▋     | 13048/28080 [25:47:05<29:52:42,  7.16s/it]
                                                           
{'loss': 0.6215, 'learning_rate': 0.0002905789412960892, 'epoch': 5.57}

 46%|████▋     | 13048/28080 [25:47:05<29:52:42,  7.16s/it]
 46%|████▋     | 13049/28080 [25:47:12<29:45:25,  7.13s/it]
                                                           
{'loss': 0.6215, 'learning_rate': 0.00029055048771292803, 'epoch': 5.57}

 46%|████▋     | 13049/28080 [25:47:12<29:45:25,  7.13s/it]
 46%|████▋     | 13050/28080 [25:47:19<29:49:07,  7.14s/it]
                                                           
{'loss': 0.6228, 'learning_rate': 0.0002905220335902844, 'epoch': 5.57}

 46%|████▋     | 13050/28080 [25:47:19<29:49:07,  7.14s/it]
 46%|████▋     | 13051/28080 [25:47:26<30:01:42,  7.19s/it]
                                                           
{'loss': 0.6161, 'learning_rate': 0.000290493578928537, 'epoch': 5.58}

 46%|████▋     | 13051/28080 [25:47:26<30:01:42,  7.19s/it]
 46%|████▋     | 13052/28080 [25:47:33<30:00:44,  7.19s/it]
                                                           
{'loss': 0.6348, 'learning_rate': 0.00029046512372806426, 'epoch': 5.58}

 46%|████▋     | 13052/28080 [25:47:33<30:00:44,  7.19s/it]
 46%|████▋     | 13053/28080 [25:47:41<30:04:59,  7.21s/it]
                                                           
{'loss': 0.6178, 'learning_rate': 0.00029043666798924485, 'epoch': 5.58}

 46%|████▋     | 13053/28080 [25:47:41<30:04:59,  7.21s/it]
 46%|████▋     | 13054/28080 [25:47:48<30:00:28,  7.19s/it]
                                                           
{'loss': 0.6323, 'learning_rate': 0.0002904082117124572, 'epoch': 5.58}

 46%|████▋     | 13054/28080 [25:47:48<30:00:28,  7.19s/it]
 46%|████▋     | 13055/28080 [25:47:55<29:50:16,  7.15s/it]
                                                           
{'loss': 0.6456, 'learning_rate': 0.0002903797548980801, 'epoch': 5.58}

 46%|████▋     | 13055/28080 [25:47:55<29:50:16,  7.15s/it]
 46%|████▋     | 13056/28080 [25:48:02<29:48:37,  7.14s/it]
                                                           
{'loss': 0.6349, 'learning_rate': 0.00029035129754649195, 'epoch': 5.58}

 46%|████▋     | 13056/28080 [25:48:02<29:48:37,  7.14s/it]
 46%|████▋     | 13057/28080 [25:48:09<29:47:45,  7.14s/it]
                                                           
{'loss': 0.6322, 'learning_rate': 0.00029032283965807135, 'epoch': 5.58}

 46%|████▋     | 13057/28080 [25:48:09<29:47:45,  7.14s/it]
 47%|████▋     | 13058/28080 [25:48:16<29:45:55,  7.13s/it]
                                                           
{'loss': 0.6412, 'learning_rate': 0.00029029438123319705, 'epoch': 5.58}

 47%|████▋     | 13058/28080 [25:48:16<29:45:55,  7.13s/it]
 47%|████▋     | 13059/28080 [25:48:23<29:49:47,  7.15s/it]
                                                           
{'loss': 0.6148, 'learning_rate': 0.0002902659222722475, 'epoch': 5.58}

 47%|████▋     | 13059/28080 [25:48:23<29:49:47,  7.15s/it]
 47%|████▋     | 13060/28080 [25:48:31<29:54:16,  7.17s/it]
                                                           
{'loss': 0.6237, 'learning_rate': 0.0002902374627756015, 'epoch': 5.58}

 47%|████▋     | 13060/28080 [25:48:31<29:54:16,  7.17s/it]
 47%|████▋     | 13061/28080 [25:48:38<29:46:27,  7.14s/it]
                                                           
{'loss': 0.6169, 'learning_rate': 0.0002902090027436375, 'epoch': 5.58}

 47%|████▋     | 13061/28080 [25:48:38<29:46:27,  7.14s/it]
 47%|████▋     | 13062/28080 [25:48:45<29:48:15,  7.14s/it]
                                                           
{'loss': 0.6306, 'learning_rate': 0.0002901805421767343, 'epoch': 5.58}

 47%|████▋     | 13062/28080 [25:48:45<29:48:15,  7.14s/it]
 47%|████▋     | 13063/28080 [25:48:52<29:45:00,  7.13s/it]
                                                           
{'loss': 0.6081, 'learning_rate': 0.0002901520810752703, 'epoch': 5.58}

 47%|████▋     | 13063/28080 [25:48:52<29:45:00,  7.13s/it]
 47%|████▋     | 13064/28080 [25:48:59<29:40:07,  7.11s/it]
                                                           
{'loss': 0.6176, 'learning_rate': 0.00029012361943962436, 'epoch': 5.58}

 47%|████▋     | 13064/28080 [25:48:59<29:40:07,  7.11s/it]
 47%|████▋     | 13065/28080 [25:49:06<29:37:13,  7.10s/it]
                                                           
{'loss': 0.626, 'learning_rate': 0.00029009515727017505, 'epoch': 5.58}

 47%|████▋     | 13065/28080 [25:49:06<29:37:13,  7.10s/it]
 47%|████▋     | 13066/28080 [25:49:13<29:48:15,  7.15s/it]
                                                           
{'loss': 0.6227, 'learning_rate': 0.000290066694567301, 'epoch': 5.58}

 47%|████▋     | 13066/28080 [25:49:13<29:48:15,  7.15s/it]
 47%|████▋     | 13067/28080 [25:49:21<29:48:23,  7.15s/it]
                                                           
{'loss': 0.6277, 'learning_rate': 0.0002900382313313809, 'epoch': 5.58}

 47%|████▋     | 13067/28080 [25:49:21<29:48:23,  7.15s/it]
 47%|████▋     | 13068/28080 [25:49:28<29:43:30,  7.13s/it]
                                                           
{'loss': 0.6205, 'learning_rate': 0.0002900097675627935, 'epoch': 5.58}

 47%|████▋     | 13068/28080 [25:49:28<29:43:30,  7.13s/it]
 47%|████▋     | 13069/28080 [25:49:35<29:37:59,  7.11s/it]
                                                           
{'loss': 0.6278, 'learning_rate': 0.0002899813032619174, 'epoch': 5.58}

 47%|████▋     | 13069/28080 [25:49:35<29:37:59,  7.11s/it]
 47%|████▋     | 13070/28080 [25:49:42<29:45:49,  7.14s/it]
                                                           
{'loss': 0.6193, 'learning_rate': 0.00028995283842913136, 'epoch': 5.58}

 47%|████▋     | 13070/28080 [25:49:42<29:45:49,  7.14s/it]
 47%|████▋     | 13071/28080 [25:49:49<29:47:51,  7.15s/it]
                                                           
{'loss': 0.6111, 'learning_rate': 0.0002899243730648139, 'epoch': 5.58}

 47%|████▋     | 13071/28080 [25:49:49<29:47:51,  7.15s/it]
 47%|████▋     | 13072/28080 [25:49:56<29:46:12,  7.14s/it]
                                                           
{'loss': 0.638, 'learning_rate': 0.00028989590716934396, 'epoch': 5.58}

 47%|████▋     | 13072/28080 [25:49:56<29:46:12,  7.14s/it]
 47%|████▋     | 13073/28080 [25:50:03<29:45:28,  7.14s/it]
                                                           
{'loss': 0.6189, 'learning_rate': 0.0002898674407431001, 'epoch': 5.58}

 47%|████▋     | 13073/28080 [25:50:03<29:45:28,  7.14s/it]
 47%|████▋     | 13074/28080 [25:50:10<29:47:20,  7.15s/it]
                                                           
{'loss': 0.6312, 'learning_rate': 0.00028983897378646097, 'epoch': 5.59}

 47%|████▋     | 13074/28080 [25:50:10<29:47:20,  7.15s/it]
 47%|████▋     | 13075/28080 [25:50:18<29:42:01,  7.13s/it]
                                                           
{'loss': 0.6203, 'learning_rate': 0.0002898105062998055, 'epoch': 5.59}

 47%|████▋     | 13075/28080 [25:50:18<29:42:01,  7.13s/it]
 47%|████▋     | 13076/28080 [25:50:25<29:40:24,  7.12s/it]
                                                           
{'loss': 0.6364, 'learning_rate': 0.00028978203828351225, 'epoch': 5.59}

 47%|████▋     | 13076/28080 [25:50:25<29:40:24,  7.12s/it]
 47%|████▋     | 13077/28080 [25:50:32<29:46:00,  7.14s/it]
                                                           
{'loss': 0.6474, 'learning_rate': 0.00028975356973796006, 'epoch': 5.59}

 47%|████▋     | 13077/28080 [25:50:32<29:46:00,  7.14s/it]
 47%|████▋     | 13078/28080 [25:50:39<29:48:25,  7.15s/it]
                                                           
{'loss': 0.6289, 'learning_rate': 0.00028972510066352765, 'epoch': 5.59}

 47%|████▋     | 13078/28080 [25:50:39<29:48:25,  7.15s/it]
 47%|████▋     | 13079/28080 [25:50:46<29:52:37,  7.17s/it]
                                                           
{'loss': 0.6203, 'learning_rate': 0.00028969663106059374, 'epoch': 5.59}

 47%|████▋     | 13079/28080 [25:50:46<29:52:37,  7.17s/it]
 47%|████▋     | 13080/28080 [25:50:53<29:45:29,  7.14s/it]
                                                           
{'loss': 0.6169, 'learning_rate': 0.00028966816092953714, 'epoch': 5.59}

 47%|████▋     | 13080/28080 [25:50:53<29:45:29,  7.14s/it]
 47%|████▋     | 13081/28080 [25:51:00<29:40:59,  7.12s/it]
                                                           
{'loss': 0.6087, 'learning_rate': 0.0002896396902707365, 'epoch': 5.59}

 47%|████▋     | 13081/28080 [25:51:00<29:40:59,  7.12s/it]
 47%|████▋     | 13082/28080 [25:51:08<29:37:43,  7.11s/it]
                                                           
{'loss': 0.6304, 'learning_rate': 0.0002896112190845708, 'epoch': 5.59}

 47%|████▋     | 13082/28080 [25:51:08<29:37:43,  7.11s/it]
 47%|████▋     | 13083/28080 [25:51:15<29:44:47,  7.14s/it]
                                                           
{'loss': 0.6149, 'learning_rate': 0.00028958274737141853, 'epoch': 5.59}

 47%|████▋     | 13083/28080 [25:51:15<29:44:47,  7.14s/it]
 47%|████▋     | 13084/28080 [25:51:22<29:41:55,  7.13s/it]
                                                           
{'loss': 0.647, 'learning_rate': 0.00028955427513165875, 'epoch': 5.59}

 47%|████▋     | 13084/28080 [25:51:22<29:41:55,  7.13s/it]
 47%|████▋     | 13085/28080 [25:51:29<29:40:45,  7.13s/it]
                                                           
{'loss': 0.6169, 'learning_rate': 0.0002895258023656701, 'epoch': 5.59}

 47%|████▋     | 13085/28080 [25:51:29<29:40:45,  7.13s/it]
 47%|████▋     | 13086/28080 [25:51:36<29:43:08,  7.14s/it]
                                                           
{'loss': 0.6032, 'learning_rate': 0.00028949732907383155, 'epoch': 5.59}

 47%|████▋     | 13086/28080 [25:51:36<29:43:08,  7.14s/it]
 47%|████▋     | 13087/28080 [25:51:43<29:41:33,  7.13s/it]
                                                           
{'loss': 0.6533, 'learning_rate': 0.0002894688552565216, 'epoch': 5.59}

 47%|████▋     | 13087/28080 [25:51:43<29:41:33,  7.13s/it]
 47%|████▋     | 13088/28080 [25:51:50<29:43:34,  7.14s/it]
                                                           
{'loss': 0.6413, 'learning_rate': 0.00028944038091411933, 'epoch': 5.59}

 47%|████▋     | 13088/28080 [25:51:50<29:43:34,  7.14s/it]
 47%|████▋     | 13089/28080 [25:51:57<29:43:13,  7.14s/it]
                                                           
{'loss': 0.6163, 'learning_rate': 0.0002894119060470036, 'epoch': 5.59}

 47%|████▋     | 13089/28080 [25:51:58<29:43:13,  7.14s/it]
 47%|████▋     | 13090/28080 [25:52:05<29:39:35,  7.12s/it]
                                                           
{'loss': 0.6258, 'learning_rate': 0.00028938343065555293, 'epoch': 5.59}

 47%|████▋     | 13090/28080 [25:52:05<29:39:35,  7.12s/it]
 47%|████▋     | 13091/28080 [25:52:12<29:30:14,  7.09s/it]
                                                           
{'loss': 0.6442, 'learning_rate': 0.00028935495474014645, 'epoch': 5.59}

 47%|████▋     | 13091/28080 [25:52:12<29:30:14,  7.09s/it]
 47%|████▋     | 13092/28080 [25:52:19<29:33:37,  7.10s/it]
                                                           
{'loss': 0.6001, 'learning_rate': 0.00028932647830116285, 'epoch': 5.59}

 47%|████▋     | 13092/28080 [25:52:19<29:33:37,  7.10s/it]
 47%|████▋     | 13093/28080 [25:52:26<29:33:49,  7.10s/it]
                                                           
{'loss': 0.6355, 'learning_rate': 0.000289298001338981, 'epoch': 5.59}

 47%|████▋     | 13093/28080 [25:52:26<29:33:49,  7.10s/it]
 47%|████▋     | 13094/28080 [25:52:33<29:36:11,  7.11s/it]
                                                           
{'loss': 0.6089, 'learning_rate': 0.0002892695238539799, 'epoch': 5.59}

 47%|████▋     | 13094/28080 [25:52:33<29:36:11,  7.11s/it]
 47%|████▋     | 13095/28080 [25:52:40<29:33:41,  7.10s/it]
                                                           
{'loss': 0.6027, 'learning_rate': 0.0002892410458465382, 'epoch': 5.59}

 47%|████▋     | 13095/28080 [25:52:40<29:33:41,  7.10s/it]
 47%|████▋     | 13096/28080 [25:52:47<29:28:17,  7.08s/it]
                                                           
{'loss': 0.6223, 'learning_rate': 0.00028921256731703494, 'epoch': 5.59}

 47%|████▋     | 13096/28080 [25:52:47<29:28:17,  7.08s/it]
 47%|████▋     | 13097/28080 [25:52:54<29:31:58,  7.10s/it]
                                                           
{'loss': 0.6177, 'learning_rate': 0.0002891840882658488, 'epoch': 5.59}

 47%|████▋     | 13097/28080 [25:52:54<29:31:58,  7.10s/it]
 47%|████▋     | 13098/28080 [25:53:01<29:32:22,  7.10s/it]
                                                           
{'loss': 0.6122, 'learning_rate': 0.0002891556086933589, 'epoch': 5.6}

 47%|████▋     | 13098/28080 [25:53:01<29:32:22,  7.10s/it]
 47%|████▋     | 13099/28080 [25:53:08<29:32:47,  7.10s/it]
                                                           
{'loss': 0.6424, 'learning_rate': 0.000289127128599944, 'epoch': 5.6}

 47%|████▋     | 13099/28080 [25:53:08<29:32:47,  7.10s/it]
 47%|████▋     | 13100/28080 [25:53:15<29:26:44,  7.08s/it]
                                                           
{'loss': 0.6055, 'learning_rate': 0.00028909864798598296, 'epoch': 5.6}

 47%|████▋     | 13100/28080 [25:53:15<29:26:44,  7.08s/it]
 47%|████▋     | 13101/28080 [25:53:23<29:30:16,  7.09s/it]
                                                           
{'loss': 0.6044, 'learning_rate': 0.0002890701668518548, 'epoch': 5.6}

 47%|████▋     | 13101/28080 [25:53:23<29:30:16,  7.09s/it]
 47%|████▋     | 13102/28080 [25:53:30<29:35:23,  7.11s/it]
                                                           
{'loss': 0.6277, 'learning_rate': 0.0002890416851979384, 'epoch': 5.6}

 47%|████▋     | 13102/28080 [25:53:30<29:35:23,  7.11s/it]
 47%|████▋     | 13103/28080 [25:53:37<29:38:53,  7.13s/it]
                                                           
{'loss': 0.6122, 'learning_rate': 0.00028901320302461266, 'epoch': 5.6}

 47%|████▋     | 13103/28080 [25:53:37<29:38:53,  7.13s/it]
 47%|████▋     | 13104/28080 [25:53:44<29:32:57,  7.10s/it]
                                                           
{'loss': 0.6239, 'learning_rate': 0.0002889847203322564, 'epoch': 5.6}

 47%|████▋     | 13104/28080 [25:53:44<29:32:57,  7.10s/it]
 47%|████▋     | 13105/28080 [25:53:51<29:25:37,  7.07s/it]
                                                           
{'loss': 0.6028, 'learning_rate': 0.0002889562371212487, 'epoch': 5.6}

 47%|████▋     | 13105/28080 [25:53:51<29:25:37,  7.07s/it]
 47%|████▋     | 13106/28080 [25:53:58<29:33:16,  7.11s/it]
                                                           
{'loss': 0.6066, 'learning_rate': 0.00028892775339196846, 'epoch': 5.6}

 47%|████▋     | 13106/28080 [25:53:58<29:33:16,  7.11s/it]
 47%|████▋     | 13107/28080 [25:54:05<29:38:19,  7.13s/it]
                                                           
{'loss': 0.6169, 'learning_rate': 0.0002888992691447946, 'epoch': 5.6}

 47%|████▋     | 13107/28080 [25:54:05<29:38:19,  7.13s/it]
 47%|████▋     | 13108/28080 [25:54:12<29:30:52,  7.10s/it]
                                                           
{'loss': 0.6262, 'learning_rate': 0.0002888707843801062, 'epoch': 5.6}

 47%|████▋     | 13108/28080 [25:54:12<29:30:52,  7.10s/it]
 47%|████▋     | 13109/28080 [25:54:19<29:31:36,  7.10s/it]
                                                           
{'loss': 0.6113, 'learning_rate': 0.00028884229909828204, 'epoch': 5.6}

 47%|████▋     | 13109/28080 [25:54:19<29:31:36,  7.10s/it]
 47%|████▋     | 13110/28080 [25:54:26<29:26:07,  7.08s/it]
                                                           
{'loss': 0.6309, 'learning_rate': 0.0002888138132997012, 'epoch': 5.6}

 47%|████▋     | 13110/28080 [25:54:26<29:26:07,  7.08s/it]
 47%|████▋     | 13111/28080 [25:54:34<29:28:06,  7.09s/it]
                                                           
{'loss': 0.6076, 'learning_rate': 0.0002887853269847425, 'epoch': 5.6}

 47%|████▋     | 13111/28080 [25:54:34<29:28:06,  7.09s/it]
 47%|████▋     | 13112/28080 [25:54:41<29:30:29,  7.10s/it]
                                                           
{'loss': 0.6293, 'learning_rate': 0.0002887568401537851, 'epoch': 5.6}

 47%|████▋     | 13112/28080 [25:54:41<29:30:29,  7.10s/it]
 47%|████▋     | 13113/28080 [25:54:48<29:35:06,  7.12s/it]
                                                           
{'loss': 0.6074, 'learning_rate': 0.000288728352807208, 'epoch': 5.6}

 47%|████▋     | 13113/28080 [25:54:48<29:35:06,  7.12s/it]
 47%|████▋     | 13114/28080 [25:54:55<29:34:31,  7.11s/it]
                                                           
{'loss': 0.6059, 'learning_rate': 0.00028869986494539006, 'epoch': 5.6}

 47%|████▋     | 13114/28080 [25:54:55<29:34:31,  7.11s/it]
 47%|████▋     | 13115/28080 [25:55:02<29:35:47,  7.12s/it]
                                                           
{'loss': 0.6076, 'learning_rate': 0.0002886713765687104, 'epoch': 5.6}

 47%|████▋     | 13115/28080 [25:55:02<29:35:47,  7.12s/it]
 47%|████▋     | 13116/28080 [25:55:09<29:36:06,  7.12s/it]
                                                           
{'loss': 0.6233, 'learning_rate': 0.0002886428876775479, 'epoch': 5.6}

 47%|████▋     | 13116/28080 [25:55:09<29:36:06,  7.12s/it]
 47%|████▋     | 13117/28080 [25:55:16<29:47:01,  7.17s/it]
                                                           
{'loss': 0.6205, 'learning_rate': 0.00028861439827228166, 'epoch': 5.6}

 47%|████▋     | 13117/28080 [25:55:16<29:47:01,  7.17s/it]
 47%|████▋     | 13118/28080 [25:55:24<29:48:32,  7.17s/it]
                                                           
{'loss': 0.6327, 'learning_rate': 0.0002885859083532907, 'epoch': 5.6}

 47%|████▋     | 13118/28080 [25:55:24<29:48:32,  7.17s/it]
 47%|████▋     | 13119/28080 [25:55:31<29:44:57,  7.16s/it]
                                                           
{'loss': 0.6177, 'learning_rate': 0.00028855741792095397, 'epoch': 5.6}

 47%|████▋     | 13119/28080 [25:55:31<29:44:57,  7.16s/it]
 47%|████▋     | 13120/28080 [25:55:38<29:48:43,  7.17s/it]
                                                           
{'loss': 0.6192, 'learning_rate': 0.0002885289269756506, 'epoch': 5.6}

 47%|████▋     | 13120/28080 [25:55:38<29:48:43,  7.17s/it]
 47%|████▋     | 13121/28080 [25:55:45<29:34:26,  7.12s/it]
                                                           
{'loss': 0.6298, 'learning_rate': 0.0002885004355177597, 'epoch': 5.61}

 47%|████▋     | 13121/28080 [25:55:45<29:34:26,  7.12s/it]
 47%|████▋     | 13122/28080 [25:55:52<29:41:26,  7.15s/it]
                                                           
{'loss': 0.6295, 'learning_rate': 0.00028847194354766014, 'epoch': 5.61}

 47%|████▋     | 13122/28080 [25:55:52<29:41:26,  7.15s/it]
 47%|████▋     | 13123/28080 [25:55:59<29:39:51,  7.14s/it]
                                                           
{'loss': 0.5997, 'learning_rate': 0.00028844345106573103, 'epoch': 5.61}

 47%|████▋     | 13123/28080 [25:55:59<29:39:51,  7.14s/it]
 47%|████▋     | 13124/28080 [25:56:06<29:35:13,  7.12s/it]
                                                           
{'loss': 0.644, 'learning_rate': 0.0002884149580723515, 'epoch': 5.61}

 47%|████▋     | 13124/28080 [25:56:06<29:35:13,  7.12s/it]
 47%|████▋     | 13125/28080 [25:56:14<29:39:02,  7.14s/it]
                                                           
{'loss': 0.5978, 'learning_rate': 0.00028838646456790066, 'epoch': 5.61}

 47%|████▋     | 13125/28080 [25:56:14<29:39:02,  7.14s/it]
 47%|████▋     | 13126/28080 [25:56:21<29:35:31,  7.12s/it]
                                                           
{'loss': 0.6233, 'learning_rate': 0.00028835797055275735, 'epoch': 5.61}

 47%|████▋     | 13126/28080 [25:56:21<29:35:31,  7.12s/it]
 47%|████▋     | 13127/28080 [25:56:28<29:33:48,  7.12s/it]
                                                           
{'loss': 0.6067, 'learning_rate': 0.00028832947602730095, 'epoch': 5.61}

 47%|████▋     | 13127/28080 [25:56:28<29:33:48,  7.12s/it]
 47%|████▋     | 13128/28080 [25:56:35<29:34:34,  7.12s/it]
                                                           
{'loss': 0.6236, 'learning_rate': 0.0002883009809919104, 'epoch': 5.61}

 47%|████▋     | 13128/28080 [25:56:35<29:34:34,  7.12s/it]
 47%|████▋     | 13129/28080 [25:56:42<29:33:43,  7.12s/it]
                                                           
{'loss': 0.6015, 'learning_rate': 0.0002882724854469647, 'epoch': 5.61}

 47%|████▋     | 13129/28080 [25:56:42<29:33:43,  7.12s/it]
 47%|████▋     | 13130/28080 [25:56:49<29:24:50,  7.08s/it]
                                                           
{'loss': 0.6259, 'learning_rate': 0.0002882439893928432, 'epoch': 5.61}

 47%|████▋     | 13130/28080 [25:56:49<29:24:50,  7.08s/it]
 47%|████▋     | 13131/28080 [25:56:56<29:30:41,  7.11s/it]
                                                           
{'loss': 0.606, 'learning_rate': 0.00028821549282992474, 'epoch': 5.61}

 47%|████▋     | 13131/28080 [25:56:56<29:30:41,  7.11s/it]
 47%|████▋     | 13132/28080 [25:57:03<29:31:27,  7.11s/it]
                                                           
{'loss': 0.6229, 'learning_rate': 0.0002881869957585887, 'epoch': 5.61}

 47%|████▋     | 13132/28080 [25:57:03<29:31:27,  7.11s/it]
 47%|████▋     | 13133/28080 [25:57:10<29:38:20,  7.14s/it]
                                                           
{'loss': 0.6053, 'learning_rate': 0.00028815849817921403, 'epoch': 5.61}

 47%|████▋     | 13133/28080 [25:57:11<29:38:20,  7.14s/it]
 47%|████▋     | 13134/28080 [25:57:18<29:44:17,  7.16s/it]
                                                           
{'loss': 0.6027, 'learning_rate': 0.00028813000009217995, 'epoch': 5.61}

 47%|████▋     | 13134/28080 [25:57:18<29:44:17,  7.16s/it]
 47%|████▋     | 13135/28080 [25:57:25<29:46:41,  7.17s/it]
                                                           
{'loss': 0.6136, 'learning_rate': 0.00028810150149786545, 'epoch': 5.61}

 47%|████▋     | 13135/28080 [25:57:25<29:46:41,  7.17s/it]
 47%|████▋     | 13136/28080 [25:57:32<29:39:13,  7.14s/it]
                                                           
{'loss': 0.6146, 'learning_rate': 0.0002880730023966498, 'epoch': 5.61}

 47%|████▋     | 13136/28080 [25:57:32<29:39:13,  7.14s/it]
 47%|████▋     | 13137/28080 [25:57:39<29:40:04,  7.15s/it]
                                                           
{'loss': 0.6104, 'learning_rate': 0.0002880445027889123, 'epoch': 5.61}

 47%|████▋     | 13137/28080 [25:57:39<29:40:04,  7.15s/it]
 47%|████▋     | 13138/28080 [25:57:46<29:39:27,  7.15s/it]
                                                           
{'loss': 0.6087, 'learning_rate': 0.0002880160026750317, 'epoch': 5.61}

 47%|████▋     | 13138/28080 [25:57:46<29:39:27,  7.15s/it]
 47%|████▋     | 13139/28080 [25:57:53<29:39:23,  7.15s/it]
                                                           
{'loss': 0.6423, 'learning_rate': 0.00028798750205538757, 'epoch': 5.61}

 47%|████▋     | 13139/28080 [25:57:53<29:39:23,  7.15s/it]
 47%|████▋     | 13140/28080 [25:58:01<29:38:35,  7.14s/it]
                                                           
{'loss': 0.6119, 'learning_rate': 0.0002879590009303589, 'epoch': 5.61}

 47%|████▋     | 13140/28080 [25:58:01<29:38:35,  7.14s/it]
 47%|████▋     | 13141/28080 [25:58:08<29:40:10,  7.15s/it]
                                                           
{'loss': 0.612, 'learning_rate': 0.00028793049930032476, 'epoch': 5.61}

 47%|████▋     | 13141/28080 [25:58:08<29:40:10,  7.15s/it]
 47%|████▋     | 13142/28080 [25:58:15<29:46:26,  7.18s/it]
                                                           
{'loss': 0.6098, 'learning_rate': 0.0002879019971656646, 'epoch': 5.61}

 47%|████▋     | 13142/28080 [25:58:15<29:46:26,  7.18s/it]
 47%|████▋     | 13143/28080 [25:58:22<29:50:47,  7.19s/it]
                                                           
{'loss': 0.6118, 'learning_rate': 0.0002878734945267574, 'epoch': 5.61}

 47%|████▋     | 13143/28080 [25:58:22<29:50:47,  7.19s/it]
 47%|████▋     | 13144/28080 [25:58:29<29:34:53,  7.13s/it]
                                                           
{'loss': 0.6267, 'learning_rate': 0.00028784499138398244, 'epoch': 5.61}

 47%|████▋     | 13144/28080 [25:58:29<29:34:53,  7.13s/it]
 47%|████▋     | 13145/28080 [25:58:36<29:30:42,  7.11s/it]
                                                           
{'loss': 0.6402, 'learning_rate': 0.0002878164877377189, 'epoch': 5.62}

 47%|████▋     | 13145/28080 [25:58:36<29:30:42,  7.11s/it]
 47%|████▋     | 13146/28080 [25:58:43<29:32:02,  7.12s/it]
                                                           
{'loss': 0.6393, 'learning_rate': 0.00028778798358834604, 'epoch': 5.62}

 47%|████▋     | 13146/28080 [25:58:43<29:32:02,  7.12s/it]
 47%|████▋     | 13147/28080 [25:58:50<29:18:47,  7.07s/it]
                                                           
{'loss': 0.642, 'learning_rate': 0.000287759478936243, 'epoch': 5.62}

 47%|████▋     | 13147/28080 [25:58:50<29:18:47,  7.07s/it]
 47%|████▋     | 13148/28080 [25:58:57<29:19:17,  7.07s/it]
                                                           
{'loss': 0.6119, 'learning_rate': 0.000287730973781789, 'epoch': 5.62}

 47%|████▋     | 13148/28080 [25:58:57<29:19:17,  7.07s/it]
 47%|████▋     | 13149/28080 [25:59:05<29:23:03,  7.08s/it]
                                                           
{'loss': 0.6293, 'learning_rate': 0.00028770246812536343, 'epoch': 5.62}

 47%|████▋     | 13149/28080 [25:59:05<29:23:03,  7.08s/it]
 47%|████▋     | 13150/28080 [25:59:12<29:31:14,  7.12s/it]
                                                           
{'loss': 0.6209, 'learning_rate': 0.0002876739619673453, 'epoch': 5.62}

 47%|████▋     | 13150/28080 [25:59:12<29:31:14,  7.12s/it]
 47%|████▋     | 13151/28080 [25:59:19<29:29:26,  7.11s/it]
                                                           
{'loss': 0.6081, 'learning_rate': 0.0002876454553081141, 'epoch': 5.62}

 47%|████▋     | 13151/28080 [25:59:19<29:29:26,  7.11s/it]
 47%|████▋     | 13152/28080 [25:59:26<29:26:11,  7.10s/it]
                                                           
{'loss': 0.625, 'learning_rate': 0.0002876169481480488, 'epoch': 5.62}

 47%|████▋     | 13152/28080 [25:59:26<29:26:11,  7.10s/it]
 47%|████▋     | 13153/28080 [25:59:33<29:21:37,  7.08s/it]
                                                           
{'loss': 0.6099, 'learning_rate': 0.00028758844048752896, 'epoch': 5.62}

 47%|████▋     | 13153/28080 [25:59:33<29:21:37,  7.08s/it]
 47%|████▋     | 13154/28080 [25:59:40<29:26:10,  7.10s/it]
                                                           
{'loss': 0.6178, 'learning_rate': 0.00028755993232693365, 'epoch': 5.62}

 47%|████▋     | 13154/28080 [25:59:40<29:26:10,  7.10s/it]
 47%|████▋     | 13155/28080 [25:59:47<29:27:37,  7.11s/it]
                                                           
{'loss': 0.6334, 'learning_rate': 0.00028753142366664213, 'epoch': 5.62}

 47%|████▋     | 13155/28080 [25:59:47<29:27:37,  7.11s/it]
 47%|████▋     | 13156/28080 [25:59:54<29:20:25,  7.08s/it]
                                                           
{'loss': 0.6229, 'learning_rate': 0.0002875029145070338, 'epoch': 5.62}

 47%|████▋     | 13156/28080 [25:59:54<29:20:25,  7.08s/it]
 47%|████▋     | 13157/28080 [26:00:01<29:26:33,  7.10s/it]
                                                           
{'loss': 0.601, 'learning_rate': 0.00028747440484848787, 'epoch': 5.62}

 47%|████▋     | 13157/28080 [26:00:01<29:26:33,  7.10s/it]
 47%|████▋     | 13158/28080 [26:00:08<29:24:07,  7.09s/it]
                                                           
{'loss': 0.6072, 'learning_rate': 0.00028744589469138364, 'epoch': 5.62}

 47%|████▋     | 13158/28080 [26:00:08<29:24:07,  7.09s/it]
 47%|████▋     | 13159/28080 [26:00:16<29:31:26,  7.12s/it]
                                                           
{'loss': 0.6275, 'learning_rate': 0.0002874173840361004, 'epoch': 5.62}

 47%|████▋     | 13159/28080 [26:00:16<29:31:26,  7.12s/it]
 47%|████▋     | 13160/28080 [26:00:23<29:25:07,  7.10s/it]
                                                           
{'loss': 0.6304, 'learning_rate': 0.0002873888728830175, 'epoch': 5.62}

 47%|████▋     | 13160/28080 [26:00:23<29:25:07,  7.10s/it]
 47%|████▋     | 13161/28080 [26:00:30<29:35:14,  7.14s/it]
                                                           
{'loss': 0.6192, 'learning_rate': 0.0002873603612325142, 'epoch': 5.62}

 47%|████▋     | 13161/28080 [26:00:30<29:35:14,  7.14s/it]
 47%|████▋     | 13162/28080 [26:00:37<29:30:07,  7.12s/it]
                                                           
{'loss': 0.623, 'learning_rate': 0.00028733184908496986, 'epoch': 5.62}

 47%|████▋     | 13162/28080 [26:00:37<29:30:07,  7.12s/it]
 47%|████▋     | 13163/28080 [26:00:44<29:34:13,  7.14s/it]
                                                           
{'loss': 0.6211, 'learning_rate': 0.00028730333644076374, 'epoch': 5.62}

 47%|████▋     | 13163/28080 [26:00:44<29:34:13,  7.14s/it]
 47%|████▋     | 13164/28080 [26:00:51<29:25:13,  7.10s/it]
                                                           
{'loss': 0.6318, 'learning_rate': 0.00028727482330027525, 'epoch': 5.62}

 47%|████▋     | 13164/28080 [26:00:51<29:25:13,  7.10s/it]
 47%|████▋     | 13165/28080 [26:00:58<29:28:43,  7.12s/it]
                                                           
{'loss': 0.607, 'learning_rate': 0.0002872463096638836, 'epoch': 5.62}

 47%|████▋     | 13165/28080 [26:00:58<29:28:43,  7.12s/it]
 47%|████▋     | 13166/28080 [26:01:05<29:28:55,  7.12s/it]
                                                           
{'loss': 0.6317, 'learning_rate': 0.00028721779553196836, 'epoch': 5.62}

 47%|████▋     | 13166/28080 [26:01:05<29:28:55,  7.12s/it]
 47%|████▋     | 13167/28080 [26:01:13<29:27:15,  7.11s/it]
                                                           
{'loss': 0.6195, 'learning_rate': 0.0002871892809049087, 'epoch': 5.62}

 47%|████▋     | 13167/28080 [26:01:13<29:27:15,  7.11s/it]
 47%|████▋     | 13168/28080 [26:01:20<29:30:35,  7.12s/it]
                                                           
{'loss': 0.6364, 'learning_rate': 0.00028716076578308403, 'epoch': 5.63}

 47%|████▋     | 13168/28080 [26:01:20<29:30:35,  7.12s/it]
 47%|████▋     | 13169/28080 [26:01:27<29:34:00,  7.14s/it]
                                                           
{'loss': 0.6253, 'learning_rate': 0.0002871322501668736, 'epoch': 5.63}

 47%|████▋     | 13169/28080 [26:01:27<29:34:00,  7.14s/it]
 47%|████▋     | 13170/28080 [26:01:34<29:29:59,  7.12s/it]
                                                           
{'loss': 0.6428, 'learning_rate': 0.000287103734056657, 'epoch': 5.63}

 47%|████▋     | 13170/28080 [26:01:34<29:29:59,  7.12s/it]
 47%|████▋     | 13171/28080 [26:01:41<29:30:18,  7.12s/it]
                                                           
{'loss': 0.6257, 'learning_rate': 0.0002870752174528135, 'epoch': 5.63}

 47%|████▋     | 13171/28080 [26:01:41<29:30:18,  7.12s/it]
 47%|████▋     | 13172/28080 [26:01:48<29:34:10,  7.14s/it]
                                                           
{'loss': 0.5871, 'learning_rate': 0.00028704670035572237, 'epoch': 5.63}

 47%|████▋     | 13172/28080 [26:01:48<29:34:10,  7.14s/it]
 47%|████▋     | 13173/28080 [26:01:55<29:30:33,  7.13s/it]
                                                           
{'loss': 0.6206, 'learning_rate': 0.00028701818276576324, 'epoch': 5.63}

 47%|████▋     | 13173/28080 [26:01:55<29:30:33,  7.13s/it]
 47%|████▋     | 13174/28080 [26:02:02<29:29:50,  7.12s/it]
                                                           
{'loss': 0.6342, 'learning_rate': 0.00028698966468331536, 'epoch': 5.63}

 47%|████▋     | 13174/28080 [26:02:02<29:29:50,  7.12s/it]
 47%|████▋     | 13175/28080 [26:02:10<29:23:22,  7.10s/it]
                                                           
{'loss': 0.6126, 'learning_rate': 0.00028696114610875814, 'epoch': 5.63}

 47%|████▋     | 13175/28080 [26:02:10<29:23:22,  7.10s/it]
 47%|████▋     | 13176/28080 [26:02:17<29:28:56,  7.12s/it]
                                                           
{'loss': 0.6192, 'learning_rate': 0.0002869326270424709, 'epoch': 5.63}

 47%|████▋     | 13176/28080 [26:02:17<29:28:56,  7.12s/it]
 47%|████▋     | 13177/28080 [26:02:24<29:32:29,  7.14s/it]
                                                           
{'loss': 0.6042, 'learning_rate': 0.00028690410748483325, 'epoch': 5.63}

 47%|████▋     | 13177/28080 [26:02:24<29:32:29,  7.14s/it]
 47%|████▋     | 13178/28080 [26:02:31<29:35:45,  7.15s/it]
                                                           
{'loss': 0.6163, 'learning_rate': 0.00028687558743622447, 'epoch': 5.63}

 47%|████▋     | 13178/28080 [26:02:31<29:35:45,  7.15s/it]
 47%|████▋     | 13179/28080 [26:02:38<29:33:03,  7.14s/it]
                                                           
{'loss': 0.5949, 'learning_rate': 0.0002868470668970241, 'epoch': 5.63}

 47%|████▋     | 13179/28080 [26:02:38<29:33:03,  7.14s/it]
 47%|████▋     | 13180/28080 [26:02:45<29:30:51,  7.13s/it]
                                                           
{'loss': 0.6138, 'learning_rate': 0.0002868185458676115, 'epoch': 5.63}

 47%|████▋     | 13180/28080 [26:02:45<29:30:51,  7.13s/it]
 47%|████▋     | 13181/28080 [26:02:52<29:31:44,  7.13s/it]
                                                           
{'loss': 0.6148, 'learning_rate': 0.0002867900243483661, 'epoch': 5.63}

 47%|████▋     | 13181/28080 [26:02:52<29:31:44,  7.13s/it]
 47%|████▋     | 13182/28080 [26:03:00<29:28:03,  7.12s/it]
                                                           
{'loss': 0.6203, 'learning_rate': 0.0002867615023396675, 'epoch': 5.63}

 47%|████▋     | 13182/28080 [26:03:00<29:28:03,  7.12s/it]
 47%|████▋     | 13183/28080 [26:03:07<29:31:31,  7.14s/it]
                                                           
{'loss': 0.6134, 'learning_rate': 0.0002867329798418949, 'epoch': 5.63}

 47%|████▋     | 13183/28080 [26:03:07<29:31:31,  7.14s/it]
 47%|████▋     | 13184/28080 [26:03:14<29:26:15,  7.11s/it]
                                                           
{'loss': 0.6251, 'learning_rate': 0.00028670445685542793, 'epoch': 5.63}

 47%|████▋     | 13184/28080 [26:03:14<29:26:15,  7.11s/it]
 47%|████▋     | 13185/28080 [26:03:21<29:24:37,  7.11s/it]
                                                           
{'loss': 0.5962, 'learning_rate': 0.000286675933380646, 'epoch': 5.63}

 47%|████▋     | 13185/28080 [26:03:21<29:24:37,  7.11s/it]
 47%|████▋     | 13186/28080 [26:03:28<29:29:57,  7.13s/it]
                                                           
{'loss': 0.6293, 'learning_rate': 0.00028664740941792866, 'epoch': 5.63}

 47%|████▋     | 13186/28080 [26:03:28<29:29:57,  7.13s/it]
 47%|████▋     | 13187/28080 [26:03:35<29:22:39,  7.10s/it]
                                                           
{'loss': 0.6404, 'learning_rate': 0.00028661888496765535, 'epoch': 5.63}

 47%|████▋     | 13187/28080 [26:03:35<29:22:39,  7.10s/it]
 47%|████▋     | 13188/28080 [26:03:42<29:21:07,  7.10s/it]
                                                           
{'loss': 0.6246, 'learning_rate': 0.00028659036003020555, 'epoch': 5.63}

 47%|████▋     | 13188/28080 [26:03:42<29:21:07,  7.10s/it]
 47%|████▋     | 13189/28080 [26:03:49<29:28:20,  7.13s/it]
                                                           
{'loss': 0.6091, 'learning_rate': 0.00028656183460595874, 'epoch': 5.63}

 47%|████▋     | 13189/28080 [26:03:49<29:28:20,  7.13s/it]
 47%|████▋     | 13190/28080 [26:03:56<29:29:46,  7.13s/it]
                                                           
{'loss': 0.627, 'learning_rate': 0.00028653330869529454, 'epoch': 5.63}

 47%|████▋     | 13190/28080 [26:03:56<29:29:46,  7.13s/it]
 47%|████▋     | 13191/28080 [26:04:04<29:32:18,  7.14s/it]
                                                           
{'loss': 0.6234, 'learning_rate': 0.0002865047822985922, 'epoch': 5.64}

 47%|████▋     | 13191/28080 [26:04:04<29:32:18,  7.14s/it]
 47%|████▋     | 13192/28080 [26:04:11<29:31:11,  7.14s/it]
                                                           
{'loss': 0.6342, 'learning_rate': 0.0002864762554162315, 'epoch': 5.64}

 47%|████▋     | 13192/28080 [26:04:11<29:31:11,  7.14s/it]
 47%|████▋     | 13193/28080 [26:04:18<29:34:37,  7.15s/it]
                                                           
{'loss': 0.6062, 'learning_rate': 0.00028644772804859174, 'epoch': 5.64}

 47%|████▋     | 13193/28080 [26:04:18<29:34:37,  7.15s/it]
 47%|████▋     | 13194/28080 [26:04:25<29:25:49,  7.12s/it]
                                                           
{'loss': 0.6502, 'learning_rate': 0.0002864192001960527, 'epoch': 5.64}

 47%|████▋     | 13194/28080 [26:04:25<29:25:49,  7.12s/it]
 47%|████▋     | 13195/28080 [26:04:32<29:23:50,  7.11s/it]
                                                           
{'loss': 0.6232, 'learning_rate': 0.0002863906718589937, 'epoch': 5.64}

 47%|████▋     | 13195/28080 [26:04:32<29:23:50,  7.11s/it]
 47%|████▋     | 13196/28080 [26:04:39<29:24:45,  7.11s/it]
                                                           
{'loss': 0.6196, 'learning_rate': 0.0002863621430377943, 'epoch': 5.64}

 47%|████▋     | 13196/28080 [26:04:39<29:24:45,  7.11s/it]
 47%|████▋     | 13197/28080 [26:04:46<29:23:29,  7.11s/it]
                                                           
{'loss': 0.6092, 'learning_rate': 0.0002863336137328342, 'epoch': 5.64}

 47%|████▋     | 13197/28080 [26:04:46<29:23:29,  7.11s/it]
 47%|████▋     | 13198/28080 [26:04:53<29:22:17,  7.11s/it]
                                                           
{'loss': 0.6222, 'learning_rate': 0.0002863050839444928, 'epoch': 5.64}

 47%|████▋     | 13198/28080 [26:04:53<29:22:17,  7.11s/it]
 47%|████▋     | 13199/28080 [26:05:00<29:15:03,  7.08s/it]
                                                           
{'loss': 0.6308, 'learning_rate': 0.0002862765536731498, 'epoch': 5.64}

 47%|████▋     | 13199/28080 [26:05:00<29:15:03,  7.08s/it]
 47%|████▋     | 13200/28080 [26:05:08<29:19:34,  7.10s/it]
                                                           
{'loss': 0.6136, 'learning_rate': 0.0002862480229191845, 'epoch': 5.64}

 47%|████▋     | 13200/28080 [26:05:08<29:19:34,  7.10s/it]
 47%|████▋     | 13201/28080 [26:05:15<29:23:00,  7.11s/it]
                                                           
{'loss': 0.6162, 'learning_rate': 0.00028621949168297677, 'epoch': 5.64}

 47%|████▋     | 13201/28080 [26:05:15<29:23:00,  7.11s/it]
 47%|████▋     | 13202/28080 [26:05:22<29:18:42,  7.09s/it]
                                                           
{'loss': 0.6105, 'learning_rate': 0.00028619095996490604, 'epoch': 5.64}

 47%|████▋     | 13202/28080 [26:05:22<29:18:42,  7.09s/it]
 47%|████▋     | 13203/28080 [26:05:29<29:21:55,  7.11s/it]
                                                           
{'loss': 0.6184, 'learning_rate': 0.0002861624277653519, 'epoch': 5.64}

 47%|████▋     | 13203/28080 [26:05:29<29:21:55,  7.11s/it]
 47%|████▋     | 13204/28080 [26:05:36<29:12:40,  7.07s/it]
                                                           
{'loss': 0.6333, 'learning_rate': 0.000286133895084694, 'epoch': 5.64}

 47%|████▋     | 13204/28080 [26:05:36<29:12:40,  7.07s/it]
 47%|████▋     | 13205/28080 [26:05:43<29:13:37,  7.07s/it]
                                                           
{'loss': 0.6139, 'learning_rate': 0.0002861053619233119, 'epoch': 5.64}

 47%|████▋     | 13205/28080 [26:05:43<29:13:37,  7.07s/it]
 47%|████▋     | 13206/28080 [26:05:50<29:20:52,  7.10s/it]
                                                           
{'loss': 0.6438, 'learning_rate': 0.0002860768282815852, 'epoch': 5.64}

 47%|████▋     | 13206/28080 [26:05:50<29:20:52,  7.10s/it]
 47%|████▋     | 13207/28080 [26:05:57<29:15:27,  7.08s/it]
                                                           
{'loss': 0.6236, 'learning_rate': 0.00028604829415989356, 'epoch': 5.64}

 47%|████▋     | 13207/28080 [26:05:57<29:15:27,  7.08s/it]
 47%|████▋     | 13208/28080 [26:06:04<29:22:32,  7.11s/it]
                                                           
{'loss': 0.5987, 'learning_rate': 0.0002860197595586165, 'epoch': 5.64}

 47%|████▋     | 13208/28080 [26:06:04<29:22:32,  7.11s/it]
 47%|████▋     | 13209/28080 [26:06:11<29:21:05,  7.11s/it]
                                                           
{'loss': 0.6203, 'learning_rate': 0.0002859912244781337, 'epoch': 5.64}

 47%|████▋     | 13209/28080 [26:06:11<29:21:05,  7.11s/it]
 47%|████▋     | 13210/28080 [26:06:19<29:23:42,  7.12s/it]
                                                           
{'loss': 0.6178, 'learning_rate': 0.0002859626889188248, 'epoch': 5.64}

 47%|████▋     | 13210/28080 [26:06:19<29:23:42,  7.12s/it]
 47%|████▋     | 13211/28080 [26:06:26<29:27:56,  7.13s/it]
                                                           
{'loss': 0.6323, 'learning_rate': 0.00028593415288106946, 'epoch': 5.64}

 47%|████▋     | 13211/28080 [26:06:26<29:27:56,  7.13s/it]
 47%|████▋     | 13212/28080 [26:06:33<29:21:53,  7.11s/it]
                                                           
{'loss': 0.6461, 'learning_rate': 0.0002859056163652472, 'epoch': 5.64}

 47%|████▋     | 13212/28080 [26:06:33<29:21:53,  7.11s/it]
 47%|████▋     | 13213/28080 [26:06:40<29:21:06,  7.11s/it]
                                                           
{'loss': 0.639, 'learning_rate': 0.00028587707937173783, 'epoch': 5.64}

 47%|████▋     | 13213/28080 [26:06:40<29:21:06,  7.11s/it]
 47%|████▋     | 13214/28080 [26:06:47<29:26:18,  7.13s/it]
                                                           
{'loss': 0.6157, 'learning_rate': 0.00028584854190092095, 'epoch': 5.64}

 47%|████▋     | 13214/28080 [26:06:47<29:26:18,  7.13s/it]
 47%|████▋     | 13215/28080 [26:06:54<29:19:38,  7.10s/it]
                                                           
{'loss': 0.6331, 'learning_rate': 0.0002858200039531762, 'epoch': 5.65}

 47%|████▋     | 13215/28080 [26:06:54<29:19:38,  7.10s/it]
 47%|████▋     | 13216/28080 [26:07:01<29:18:28,  7.10s/it]
                                                           
{'loss': 0.5918, 'learning_rate': 0.00028579146552888327, 'epoch': 5.65}

 47%|████▋     | 13216/28080 [26:07:01<29:18:28,  7.10s/it]
 47%|████▋     | 13217/28080 [26:07:08<29:24:36,  7.12s/it]
                                                           
{'loss': 0.626, 'learning_rate': 0.0002857629266284217, 'epoch': 5.65}

 47%|████▋     | 13217/28080 [26:07:08<29:24:36,  7.12s/it]
 47%|████▋     | 13218/28080 [26:07:16<29:24:36,  7.12s/it]
                                                           
{'loss': 0.6339, 'learning_rate': 0.00028573438725217136, 'epoch': 5.65}

 47%|████▋     | 13218/28080 [26:07:16<29:24:36,  7.12s/it]
 47%|████▋     | 13219/28080 [26:07:23<29:31:58,  7.15s/it]
                                                           
{'loss': 0.6334, 'learning_rate': 0.0002857058474005118, 'epoch': 5.65}

 47%|████▋     | 13219/28080 [26:07:23<29:31:58,  7.15s/it]
 47%|████▋     | 13220/28080 [26:07:30<29:30:49,  7.15s/it]
                                                           
{'loss': 0.622, 'learning_rate': 0.0002856773070738228, 'epoch': 5.65}

 47%|████▋     | 13220/28080 [26:07:30<29:30:49,  7.15s/it]
 47%|████▋     | 13221/28080 [26:07:37<29:25:33,  7.13s/it]
                                                           
{'loss': 0.6408, 'learning_rate': 0.00028564876627248416, 'epoch': 5.65}

 47%|████▋     | 13221/28080 [26:07:37<29:25:33,  7.13s/it]
 47%|████▋     | 13222/28080 [26:07:44<29:13:15,  7.08s/it]
                                                           
{'loss': 0.6343, 'learning_rate': 0.0002856202249968753, 'epoch': 5.65}

 47%|████▋     | 13222/28080 [26:07:44<29:13:15,  7.08s/it]
 47%|████▋     | 13223/28080 [26:07:51<29:14:53,  7.09s/it]
                                                           
{'loss': 0.6571, 'learning_rate': 0.00028559168324737624, 'epoch': 5.65}

 47%|████▋     | 13223/28080 [26:07:51<29:14:53,  7.09s/it]
 47%|████▋     | 13224/28080 [26:07:58<29:20:38,  7.11s/it]
                                                           
{'loss': 0.6068, 'learning_rate': 0.0002855631410243664, 'epoch': 5.65}

 47%|████▋     | 13224/28080 [26:07:58<29:20:38,  7.11s/it]
 47%|████▋     | 13225/28080 [26:08:05<29:20:31,  7.11s/it]
                                                           
{'loss': 0.615, 'learning_rate': 0.00028553459832822577, 'epoch': 5.65}

 47%|████▋     | 13225/28080 [26:08:05<29:20:31,  7.11s/it]
 47%|████▋     | 13226/28080 [26:08:12<29:24:58,  7.13s/it]
                                                           
{'loss': 0.6338, 'learning_rate': 0.0002855060551593339, 'epoch': 5.65}

 47%|████▋     | 13226/28080 [26:08:12<29:24:58,  7.13s/it]
 47%|████▋     | 13227/28080 [26:08:20<29:25:16,  7.13s/it]
                                                           
{'loss': 0.6368, 'learning_rate': 0.0002854775115180706, 'epoch': 5.65}

 47%|████▋     | 13227/28080 [26:08:20<29:25:16,  7.13s/it]
 47%|████▋     | 13228/28080 [26:08:27<29:21:55,  7.12s/it]
                                                           
{'loss': 0.6258, 'learning_rate': 0.00028544896740481565, 'epoch': 5.65}

 47%|████▋     | 13228/28080 [26:08:27<29:21:55,  7.12s/it]
 47%|████▋     | 13229/28080 [26:08:34<29:25:57,  7.13s/it]
                                                           
{'loss': 0.6082, 'learning_rate': 0.00028542042281994875, 'epoch': 5.65}

 47%|████▋     | 13229/28080 [26:08:34<29:25:57,  7.13s/it]
 47%|████▋     | 13230/28080 [26:08:41<29:22:49,  7.12s/it]
                                                           
{'loss': 0.6382, 'learning_rate': 0.0002853918777638497, 'epoch': 5.65}

 47%|████▋     | 13230/28080 [26:08:41<29:22:49,  7.12s/it]
 47%|████▋     | 13231/28080 [26:08:48<29:16:17,  7.10s/it]
                                                           
{'loss': 0.6272, 'learning_rate': 0.00028536333223689816, 'epoch': 5.65}

 47%|████▋     | 13231/28080 [26:08:48<29:16:17,  7.10s/it]
 47%|████▋     | 13232/28080 [26:08:55<29:10:22,  7.07s/it]
                                                           
{'loss': 0.6103, 'learning_rate': 0.00028533478623947396, 'epoch': 5.65}

 47%|████▋     | 13232/28080 [26:08:55<29:10:22,  7.07s/it]
 47%|████▋     | 13233/28080 [26:09:02<29:07:13,  7.06s/it]
                                                           
{'loss': 0.631, 'learning_rate': 0.00028530623977195694, 'epoch': 5.65}

 47%|████▋     | 13233/28080 [26:09:02<29:07:13,  7.06s/it]
 47%|████▋     | 13234/28080 [26:09:09<29:08:03,  7.06s/it]
                                                           
{'loss': 0.6117, 'learning_rate': 0.0002852776928347267, 'epoch': 5.65}

 47%|████▋     | 13234/28080 [26:09:09<29:08:03,  7.06s/it]
 47%|████▋     | 13235/28080 [26:09:16<29:06:54,  7.06s/it]
                                                           
{'loss': 0.6358, 'learning_rate': 0.00028524914542816333, 'epoch': 5.65}

 47%|████▋     | 13235/28080 [26:09:16<29:06:54,  7.06s/it]
 47%|████▋     | 13236/28080 [26:09:23<29:08:52,  7.07s/it]
                                                           
{'loss': 0.6134, 'learning_rate': 0.00028522059755264634, 'epoch': 5.65}

 47%|████▋     | 13236/28080 [26:09:23<29:08:52,  7.07s/it]
 47%|████▋     | 13237/28080 [26:09:30<29:10:17,  7.08s/it]
                                                           
{'loss': 0.6295, 'learning_rate': 0.00028519204920855566, 'epoch': 5.65}

 47%|████▋     | 13237/28080 [26:09:30<29:10:17,  7.08s/it]
 47%|████▋     | 13238/28080 [26:09:37<29:07:04,  7.06s/it]
                                                           
{'loss': 0.6179, 'learning_rate': 0.00028516350039627103, 'epoch': 5.66}

 47%|████▋     | 13238/28080 [26:09:37<29:07:04,  7.06s/it]
 47%|████▋     | 13239/28080 [26:09:44<29:05:32,  7.06s/it]
                                                           
{'loss': 0.628, 'learning_rate': 0.0002851349511161724, 'epoch': 5.66}

 47%|████▋     | 13239/28080 [26:09:44<29:05:32,  7.06s/it]
 47%|████▋     | 13240/28080 [26:09:52<29:07:06,  7.06s/it]
                                                           
{'loss': 0.6326, 'learning_rate': 0.0002851064013686395, 'epoch': 5.66}

 47%|████▋     | 13240/28080 [26:09:52<29:07:06,  7.06s/it]
 47%|████▋     | 13241/28080 [26:09:59<29:06:00,  7.06s/it]
                                                           
{'loss': 0.6234, 'learning_rate': 0.000285077851154052, 'epoch': 5.66}

 47%|████▋     | 13241/28080 [26:09:59<29:06:00,  7.06s/it]
 47%|████▋     | 13242/28080 [26:10:06<29:13:39,  7.09s/it]
                                                           
{'loss': 0.6224, 'learning_rate': 0.00028504930047279, 'epoch': 5.66}

 47%|████▋     | 13242/28080 [26:10:06<29:13:39,  7.09s/it]
 47%|████▋     | 13243/28080 [26:10:13<29:13:58,  7.09s/it]
                                                           
{'loss': 0.6017, 'learning_rate': 0.00028502074932523313, 'epoch': 5.66}

 47%|████▋     | 13243/28080 [26:10:13<29:13:58,  7.09s/it]
 47%|████▋     | 13244/28080 [26:10:20<29:13:03,  7.09s/it]
                                                           
{'loss': 0.6096, 'learning_rate': 0.0002849921977117614, 'epoch': 5.66}

 47%|████▋     | 13244/28080 [26:10:20<29:13:03,  7.09s/it]
 47%|████▋     | 13245/28080 [26:10:27<29:15:51,  7.10s/it]
                                                           
{'loss': 0.6044, 'learning_rate': 0.0002849636456327545, 'epoch': 5.66}

 47%|████▋     | 13245/28080 [26:10:27<29:15:51,  7.10s/it]
 47%|████▋     | 13246/28080 [26:10:34<29:27:34,  7.15s/it]
                                                           
{'loss': 0.5983, 'learning_rate': 0.0002849350930885924, 'epoch': 5.66}

 47%|████▋     | 13246/28080 [26:10:34<29:27:34,  7.15s/it]
 47%|████▋     | 13247/28080 [26:10:41<29:23:38,  7.13s/it]
                                                           
{'loss': 0.6195, 'learning_rate': 0.000284906540079655, 'epoch': 5.66}

 47%|████▋     | 13247/28080 [26:10:41<29:23:38,  7.13s/it]
 47%|████▋     | 13248/28080 [26:10:49<29:22:37,  7.13s/it]
                                                           
{'loss': 0.6125, 'learning_rate': 0.000284877986606322, 'epoch': 5.66}

 47%|████▋     | 13248/28080 [26:10:49<29:22:37,  7.13s/it]
 47%|████▋     | 13249/28080 [26:10:56<29:19:20,  7.12s/it]
                                                           
{'loss': 0.6334, 'learning_rate': 0.0002848494326689734, 'epoch': 5.66}

 47%|████▋     | 13249/28080 [26:10:56<29:19:20,  7.12s/it]
 47%|████▋     | 13250/28080 [26:11:03<29:25:49,  7.14s/it]
                                                           
{'loss': 0.6288, 'learning_rate': 0.000284820878267989, 'epoch': 5.66}

 47%|████▋     | 13250/28080 [26:11:03<29:25:49,  7.14s/it]
 47%|████▋     | 13251/28080 [26:11:10<29:21:12,  7.13s/it]
                                                           
{'loss': 0.6216, 'learning_rate': 0.0002847923234037488, 'epoch': 5.66}

 47%|████▋     | 13251/28080 [26:11:10<29:21:12,  7.13s/it]
 47%|████▋     | 13252/28080 [26:11:17<29:23:50,  7.14s/it]
                                                           
{'loss': 0.6292, 'learning_rate': 0.0002847637680766326, 'epoch': 5.66}

 47%|████▋     | 13252/28080 [26:11:17<29:23:50,  7.14s/it]
 47%|████▋     | 13253/28080 [26:11:24<29:21:27,  7.13s/it]
                                                           
{'loss': 0.6147, 'learning_rate': 0.00028473521228702036, 'epoch': 5.66}

 47%|████▋     | 13253/28080 [26:11:24<29:21:27,  7.13s/it]
 47%|████▋     | 13254/28080 [26:11:31<29:10:23,  7.08s/it]
                                                           
{'loss': 0.6645, 'learning_rate': 0.000284706656035292, 'epoch': 5.66}

 47%|████▋     | 13254/28080 [26:11:31<29:10:23,  7.08s/it]
 47%|████▋     | 13255/28080 [26:11:38<29:10:17,  7.08s/it]
                                                           
{'loss': 0.644, 'learning_rate': 0.0002846780993218273, 'epoch': 5.66}

 47%|████▋     | 13255/28080 [26:11:38<29:10:17,  7.08s/it]
 47%|████▋     | 13256/28080 [26:11:45<29:16:09,  7.11s/it]
                                                           
{'loss': 0.6122, 'learning_rate': 0.00028464954214700626, 'epoch': 5.66}

 47%|████▋     | 13256/28080 [26:11:45<29:16:09,  7.11s/it]
 47%|████▋     | 13257/28080 [26:11:53<29:18:06,  7.12s/it]
                                                           
{'loss': 0.62, 'learning_rate': 0.00028462098451120885, 'epoch': 5.66}

 47%|████▋     | 13257/28080 [26:11:53<29:18:06,  7.12s/it]
 47%|████▋     | 13258/28080 [26:12:00<29:16:21,  7.11s/it]
                                                           
{'loss': 0.6119, 'learning_rate': 0.00028459242641481493, 'epoch': 5.66}

 47%|████▋     | 13258/28080 [26:12:00<29:16:21,  7.11s/it]
 47%|████▋     | 13259/28080 [26:12:07<29:13:34,  7.10s/it]
                                                           
{'loss': 0.6435, 'learning_rate': 0.00028456386785820456, 'epoch': 5.66}

 47%|████▋     | 13259/28080 [26:12:07<29:13:34,  7.10s/it]
 47%|████▋     | 13260/28080 [26:12:14<29:14:59,  7.11s/it]
                                                           
{'loss': 0.6149, 'learning_rate': 0.00028453530884175744, 'epoch': 5.66}

 47%|████▋     | 13260/28080 [26:12:14<29:14:59,  7.11s/it]
 47%|████▋     | 13261/28080 [26:12:21<29:10:35,  7.09s/it]
                                                           
{'loss': 0.6401, 'learning_rate': 0.00028450674936585373, 'epoch': 5.66}

 47%|████▋     | 13261/28080 [26:12:21<29:10:35,  7.09s/it]
 47%|████▋     | 13262/28080 [26:12:28<29:13:55,  7.10s/it]
                                                           
{'loss': 0.6172, 'learning_rate': 0.00028447818943087334, 'epoch': 5.67}

 47%|████▋     | 13262/28080 [26:12:28<29:13:55,  7.10s/it]
 47%|████▋     | 13263/28080 [26:12:35<29:16:44,  7.11s/it]
                                                           
{'loss': 0.6338, 'learning_rate': 0.0002844496290371962, 'epoch': 5.67}

 47%|████▋     | 13263/28080 [26:12:35<29:16:44,  7.11s/it]
 47%|████▋     | 13264/28080 [26:12:42<29:19:03,  7.12s/it]
                                                           
{'loss': 0.6323, 'learning_rate': 0.0002844210681852023, 'epoch': 5.67}

 47%|████▋     | 13264/28080 [26:12:42<29:19:03,  7.12s/it]
 47%|████▋     | 13265/28080 [26:12:49<29:18:11,  7.12s/it]
                                                           
{'loss': 0.6544, 'learning_rate': 0.00028439250687527153, 'epoch': 5.67}

 47%|████▋     | 13265/28080 [26:12:49<29:18:11,  7.12s/it]
 47%|████▋     | 13266/28080 [26:12:57<29:20:33,  7.13s/it]
                                                           
{'loss': 0.6168, 'learning_rate': 0.000284363945107784, 'epoch': 5.67}

 47%|████▋     | 13266/28080 [26:12:57<29:20:33,  7.13s/it]
 47%|████▋     | 13267/28080 [26:13:04<29:20:07,  7.13s/it]
                                                           
{'loss': 0.6177, 'learning_rate': 0.0002843353828831196, 'epoch': 5.67}

 47%|████▋     | 13267/28080 [26:13:04<29:20:07,  7.13s/it]
 47%|████▋     | 13268/28080 [26:13:11<29:21:36,  7.14s/it]
                                                           
{'loss': 0.6245, 'learning_rate': 0.00028430682020165834, 'epoch': 5.67}

 47%|████▋     | 13268/28080 [26:13:11<29:21:36,  7.14s/it]
 47%|████▋     | 13269/28080 [26:13:18<29:15:35,  7.11s/it]
                                                           
{'loss': 0.6248, 'learning_rate': 0.0002842782570637803, 'epoch': 5.67}

 47%|████▋     | 13269/28080 [26:13:18<29:15:35,  7.11s/it]
 47%|████▋     | 13270/28080 [26:13:25<29:10:29,  7.09s/it]
                                                           
{'loss': 0.6251, 'learning_rate': 0.00028424969346986533, 'epoch': 5.67}

 47%|████▋     | 13270/28080 [26:13:25<29:10:29,  7.09s/it]
 47%|████▋     | 13271/28080 [26:13:32<29:19:39,  7.13s/it]
                                                           
{'loss': 0.6146, 'learning_rate': 0.0002842211294202936, 'epoch': 5.67}

 47%|████▋     | 13271/28080 [26:13:32<29:19:39,  7.13s/it]
 47%|████▋     | 13272/28080 [26:13:39<29:14:26,  7.11s/it]
                                                           
{'loss': 0.5945, 'learning_rate': 0.000284192564915445, 'epoch': 5.67}

 47%|████▋     | 13272/28080 [26:13:39<29:14:26,  7.11s/it]
 47%|████▋     | 13273/28080 [26:13:46<29:11:39,  7.10s/it]
                                                           
{'loss': 0.6243, 'learning_rate': 0.0002841639999556996, 'epoch': 5.67}

 47%|████▋     | 13273/28080 [26:13:46<29:11:39,  7.10s/it]
 47%|████▋     | 13274/28080 [26:13:54<29:21:22,  7.14s/it]
                                                           
{'loss': 0.6009, 'learning_rate': 0.00028413543454143737, 'epoch': 5.67}

 47%|████▋     | 13274/28080 [26:13:54<29:21:22,  7.14s/it]
 47%|████▋     | 13275/28080 [26:14:01<29:17:52,  7.12s/it]
                                                           
{'loss': 0.6095, 'learning_rate': 0.00028410686867303846, 'epoch': 5.67}

 47%|████▋     | 13275/28080 [26:14:01<29:17:52,  7.12s/it]
 47%|████▋     | 13276/28080 [26:14:08<29:20:18,  7.13s/it]
                                                           
{'loss': 0.6015, 'learning_rate': 0.00028407830235088283, 'epoch': 5.67}

 47%|████▋     | 13276/28080 [26:14:08<29:20:18,  7.13s/it]
 47%|████▋     | 13277/28080 [26:14:15<29:22:25,  7.14s/it]
                                                           
{'loss': 0.6173, 'learning_rate': 0.00028404973557535055, 'epoch': 5.67}

 47%|████▋     | 13277/28080 [26:14:15<29:22:25,  7.14s/it]
 47%|████▋     | 13278/28080 [26:14:22<29:17:32,  7.12s/it]
                                                           
{'loss': 0.6017, 'learning_rate': 0.00028402116834682175, 'epoch': 5.67}

 47%|████▋     | 13278/28080 [26:14:22<29:17:32,  7.12s/it]
 47%|████▋     | 13279/28080 [26:14:29<29:19:54,  7.13s/it]
                                                           
{'loss': 0.6206, 'learning_rate': 0.00028399260066567627, 'epoch': 5.67}

 47%|████▋     | 13279/28080 [26:14:29<29:19:54,  7.13s/it]
 47%|████▋     | 13280/28080 [26:14:36<29:21:20,  7.14s/it]
                                                           
{'loss': 0.6349, 'learning_rate': 0.0002839640325322944, 'epoch': 5.67}

 47%|████▋     | 13280/28080 [26:14:36<29:21:20,  7.14s/it]
 47%|████▋     | 13281/28080 [26:14:44<29:26:30,  7.16s/it]
                                                           
{'loss': 0.6096, 'learning_rate': 0.00028393546394705604, 'epoch': 5.67}

 47%|████▋     | 13281/28080 [26:14:44<29:26:30,  7.16s/it]
 47%|████▋     | 13282/28080 [26:14:51<29:20:47,  7.14s/it]
                                                           
{'loss': 0.637, 'learning_rate': 0.00028390689491034136, 'epoch': 5.67}

 47%|████▋     | 13282/28080 [26:14:51<29:20:47,  7.14s/it]
 47%|████▋     | 13283/28080 [26:14:58<29:12:34,  7.11s/it]
                                                           
{'loss': 0.6262, 'learning_rate': 0.00028387832542253044, 'epoch': 5.67}

 47%|████▋     | 13283/28080 [26:14:58<29:12:34,  7.11s/it]
 47%|████▋     | 13284/28080 [26:15:05<29:12:50,  7.11s/it]
                                                           
{'loss': 0.6373, 'learning_rate': 0.0002838497554840034, 'epoch': 5.67}

 47%|████▋     | 13284/28080 [26:15:05<29:12:50,  7.11s/it]
 47%|████▋     | 13285/28080 [26:15:12<29:17:16,  7.13s/it]
                                                           
{'loss': 0.6361, 'learning_rate': 0.0002838211850951402, 'epoch': 5.68}

 47%|████▋     | 13285/28080 [26:15:12<29:17:16,  7.13s/it]
 47%|████▋     | 13286/28080 [26:15:19<29:14:51,  7.12s/it]
                                                           
{'loss': 0.6504, 'learning_rate': 0.0002837926142563211, 'epoch': 5.68}

 47%|████▋     | 13286/28080 [26:15:19<29:14:51,  7.12s/it]
 47%|████▋     | 13287/28080 [26:15:26<29:16:54,  7.13s/it]
                                                           
{'loss': 0.618, 'learning_rate': 0.0002837640429679261, 'epoch': 5.68}

 47%|████▋     | 13287/28080 [26:15:26<29:16:54,  7.13s/it]
 47%|████▋     | 13288/28080 [26:15:33<29:18:32,  7.13s/it]
                                                           
{'loss': 0.615, 'learning_rate': 0.00028373547123033526, 'epoch': 5.68}

 47%|████▋     | 13288/28080 [26:15:33<29:18:32,  7.13s/it]
 47%|████▋     | 13289/28080 [26:15:40<29:08:04,  7.09s/it]
                                                           
{'loss': 0.6468, 'learning_rate': 0.00028370689904392893, 'epoch': 5.68}

 47%|████▋     | 13289/28080 [26:15:40<29:08:04,  7.09s/it]
 47%|████▋     | 13290/28080 [26:15:47<29:13:23,  7.11s/it]
                                                           
{'loss': 0.6133, 'learning_rate': 0.00028367832640908703, 'epoch': 5.68}

 47%|████▋     | 13290/28080 [26:15:47<29:13:23,  7.11s/it]
 47%|████▋     | 13291/28080 [26:15:55<29:11:32,  7.11s/it]
                                                           
{'loss': 0.6318, 'learning_rate': 0.0002836497533261897, 'epoch': 5.68}

 47%|████▋     | 13291/28080 [26:15:55<29:11:32,  7.11s/it]
 47%|████▋     | 13292/28080 [26:16:02<29:11:17,  7.11s/it]
                                                           
{'loss': 0.6355, 'learning_rate': 0.0002836211797956171, 'epoch': 5.68}

 47%|████▋     | 13292/28080 [26:16:02<29:11:17,  7.11s/it]
 47%|████▋     | 13293/28080 [26:16:09<29:18:16,  7.13s/it]
                                                           
{'loss': 0.6089, 'learning_rate': 0.0002835926058177494, 'epoch': 5.68}

 47%|████▋     | 13293/28080 [26:16:09<29:18:16,  7.13s/it]
 47%|████▋     | 13294/28080 [26:16:16<29:13:39,  7.12s/it]
                                                           
{'loss': 0.6224, 'learning_rate': 0.00028356403139296677, 'epoch': 5.68}

 47%|████▋     | 13294/28080 [26:16:16<29:13:39,  7.12s/it]
 47%|████▋     | 13295/28080 [26:16:23<29:18:01,  7.13s/it]
                                                           
{'loss': 0.5846, 'learning_rate': 0.00028353545652164933, 'epoch': 5.68}

 47%|████▋     | 13295/28080 [26:16:23<29:18:01,  7.13s/it]
 47%|████▋     | 13296/28080 [26:16:30<29:19:05,  7.14s/it]
                                                           
{'loss': 0.625, 'learning_rate': 0.00028350688120417717, 'epoch': 5.68}

 47%|████▋     | 13296/28080 [26:16:30<29:19:05,  7.14s/it]
 47%|████▋     | 13297/28080 [26:16:38<29:27:28,  7.17s/it]
                                                           
{'loss': 0.6225, 'learning_rate': 0.0002834783054409306, 'epoch': 5.68}

 47%|████▋     | 13297/28080 [26:16:38<29:27:28,  7.17s/it]
 47%|████▋     | 13298/28080 [26:16:45<29:24:42,  7.16s/it]
                                                           
{'loss': 0.6234, 'learning_rate': 0.0002834497292322897, 'epoch': 5.68}

 47%|████▋     | 13298/28080 [26:16:45<29:24:42,  7.16s/it]
 47%|████▋     | 13299/28080 [26:16:52<29:25:53,  7.17s/it]
                                                           
{'loss': 0.6343, 'learning_rate': 0.0002834211525786346, 'epoch': 5.68}

 47%|████▋     | 13299/28080 [26:16:52<29:25:53,  7.17s/it]
 47%|████▋     | 13300/28080 [26:16:59<29:19:11,  7.14s/it]
                                                           
{'loss': 0.6485, 'learning_rate': 0.00028339257548034566, 'epoch': 5.68}

 47%|████▋     | 13300/28080 [26:16:59<29:19:11,  7.14s/it]
 47%|████▋     | 13301/28080 [26:17:06<29:22:20,  7.15s/it]
                                                           
{'loss': 0.6364, 'learning_rate': 0.00028336399793780283, 'epoch': 5.68}

 47%|████▋     | 13301/28080 [26:17:06<29:22:20,  7.15s/it]
 47%|████▋     | 13302/28080 [26:17:13<29:15:17,  7.13s/it]
                                                           
{'loss': 0.6415, 'learning_rate': 0.0002833354199513865, 'epoch': 5.68}

 47%|████▋     | 13302/28080 [26:17:13<29:15:17,  7.13s/it]
 47%|████▋     | 13303/28080 [26:17:20<29:11:55,  7.11s/it]
                                                           
{'loss': 0.6228, 'learning_rate': 0.00028330684152147673, 'epoch': 5.68}

 47%|████▋     | 13303/28080 [26:17:20<29:11:55,  7.11s/it]
 47%|████▋     | 13304/28080 [26:17:27<29:11:00,  7.11s/it]
                                                           
{'loss': 0.6164, 'learning_rate': 0.0002832782626484539, 'epoch': 5.68}

 47%|████▋     | 13304/28080 [26:17:27<29:11:00,  7.11s/it]
 47%|████▋     | 13305/28080 [26:17:35<29:17:05,  7.14s/it]
                                                           
{'loss': 0.6128, 'learning_rate': 0.000283249683332698, 'epoch': 5.68}

 47%|████▋     | 13305/28080 [26:17:35<29:17:05,  7.14s/it]
 47%|████▋     | 13306/28080 [26:17:42<29:20:16,  7.15s/it]
                                                           
{'loss': 0.6185, 'learning_rate': 0.0002832211035745894, 'epoch': 5.68}

 47%|████▋     | 13306/28080 [26:17:42<29:20:16,  7.15s/it]
 47%|████▋     | 13307/28080 [26:17:49<29:15:37,  7.13s/it]
                                                           
{'loss': 0.6234, 'learning_rate': 0.0002831925233745084, 'epoch': 5.68}

 47%|████▋     | 13307/28080 [26:17:49<29:15:37,  7.13s/it]
 47%|████▋     | 13308/28080 [26:17:56<29:14:26,  7.13s/it]
                                                           
{'loss': 0.5848, 'learning_rate': 0.00028316394273283495, 'epoch': 5.69}

 47%|████▋     | 13308/28080 [26:17:56<29:14:26,  7.13s/it]
 47%|████▋     | 13309/28080 [26:18:03<29:09:33,  7.11s/it]
                                                           
{'loss': 0.6181, 'learning_rate': 0.0002831353616499496, 'epoch': 5.69}

 47%|████▋     | 13309/28080 [26:18:03<29:09:33,  7.11s/it]
 47%|████▋     | 13310/28080 [26:18:10<29:05:32,  7.09s/it]
                                                           
{'loss': 0.6359, 'learning_rate': 0.00028310678012623237, 'epoch': 5.69}

 47%|████▋     | 13310/28080 [26:18:10<29:05:32,  7.09s/it]
 47%|████▋     | 13311/28080 [26:18:17<29:05:02,  7.09s/it]
                                                           
{'loss': 0.6465, 'learning_rate': 0.0002830781981620636, 'epoch': 5.69}

 47%|████▋     | 13311/28080 [26:18:17<29:05:02,  7.09s/it]
 47%|████▋     | 13312/28080 [26:18:24<29:12:48,  7.12s/it]
                                                           
{'loss': 0.6062, 'learning_rate': 0.00028304961575782353, 'epoch': 5.69}

 47%|████▋     | 13312/28080 [26:18:24<29:12:48,  7.12s/it]
 47%|████▋     | 13313/28080 [26:18:31<29:11:37,  7.12s/it]
                                                           
{'loss': 0.6391, 'learning_rate': 0.00028302103291389237, 'epoch': 5.69}

 47%|████▋     | 13313/28080 [26:18:31<29:11:37,  7.12s/it]
 47%|████▋     | 13314/28080 [26:18:38<29:04:10,  7.09s/it]
                                                           
{'loss': 0.6199, 'learning_rate': 0.00028299244963065056, 'epoch': 5.69}

 47%|████▋     | 13314/28080 [26:18:38<29:04:10,  7.09s/it]
 47%|████▋     | 13315/28080 [26:18:46<29:09:30,  7.11s/it]
                                                           
{'loss': 0.6291, 'learning_rate': 0.0002829638659084781, 'epoch': 5.69}

 47%|████▋     | 13315/28080 [26:18:46<29:09:30,  7.11s/it]
 47%|████▋     | 13316/28080 [26:18:53<29:18:45,  7.15s/it]
                                                           
{'loss': 0.5954, 'learning_rate': 0.00028293528174775544, 'epoch': 5.69}

 47%|████▋     | 13316/28080 [26:18:53<29:18:45,  7.15s/it]
 47%|████▋     | 13317/28080 [26:19:00<29:18:14,  7.15s/it]
                                                           
{'loss': 0.6303, 'learning_rate': 0.0002829066971488629, 'epoch': 5.69}

 47%|████▋     | 13317/28080 [26:19:00<29:18:14,  7.15s/it]
 47%|████▋     | 13318/28080 [26:19:07<29:16:07,  7.14s/it]
                                                           
{'loss': 0.6312, 'learning_rate': 0.0002828781121121807, 'epoch': 5.69}

 47%|████▋     | 13318/28080 [26:19:07<29:16:07,  7.14s/it]
 47%|████▋     | 13319/28080 [26:19:14<29:16:52,  7.14s/it]
                                                           
{'loss': 0.6447, 'learning_rate': 0.0002828495266380891, 'epoch': 5.69}

 47%|████▋     | 13319/28080 [26:19:14<29:16:52,  7.14s/it]
 47%|████▋     | 13320/28080 [26:19:21<29:21:32,  7.16s/it]
                                                           
{'loss': 0.6142, 'learning_rate': 0.0002828209407269684, 'epoch': 5.69}

 47%|████▋     | 13320/28080 [26:19:21<29:21:32,  7.16s/it]
 47%|████▋     | 13321/28080 [26:19:29<29:16:18,  7.14s/it]
                                                           
{'loss': 0.6238, 'learning_rate': 0.000282792354379199, 'epoch': 5.69}

 47%|████▋     | 13321/28080 [26:19:29<29:16:18,  7.14s/it]
 47%|████▋     | 13322/28080 [26:19:36<29:11:27,  7.12s/it]
                                                           
{'loss': 0.6146, 'learning_rate': 0.00028276376759516116, 'epoch': 5.69}

 47%|████▋     | 13322/28080 [26:19:36<29:11:27,  7.12s/it]
 47%|████▋     | 13323/28080 [26:19:43<29:09:50,  7.11s/it]
                                                           
{'loss': 0.6193, 'learning_rate': 0.00028273518037523514, 'epoch': 5.69}

 47%|████▋     | 13323/28080 [26:19:43<29:09:50,  7.11s/it]
 47%|████▋     | 13324/28080 [26:19:50<29:10:05,  7.12s/it]
                                                           
{'loss': 0.6242, 'learning_rate': 0.0002827065927198014, 'epoch': 5.69}

 47%|████▋     | 13324/28080 [26:19:50<29:10:05,  7.12s/it]
 47%|████▋     | 13325/28080 [26:19:57<28:57:29,  7.07s/it]
                                                           
{'loss': 0.6374, 'learning_rate': 0.0002826780046292401, 'epoch': 5.69}

 47%|████▋     | 13325/28080 [26:19:57<28:57:29,  7.07s/it]
 47%|████▋     | 13326/28080 [26:20:04<28:55:59,  7.06s/it]
                                                           
{'loss': 0.6169, 'learning_rate': 0.0002826494161039317, 'epoch': 5.69}

 47%|████▋     | 13326/28080 [26:20:04<28:55:59,  7.06s/it]
 47%|████▋     | 13327/28080 [26:20:11<29:04:34,  7.10s/it]
                                                           
{'loss': 0.6131, 'learning_rate': 0.0002826208271442565, 'epoch': 5.69}

 47%|████▋     | 13327/28080 [26:20:11<29:04:34,  7.10s/it]
 47%|████▋     | 13328/28080 [26:20:18<29:10:46,  7.12s/it]
                                                           
{'loss': 0.6385, 'learning_rate': 0.00028259223775059484, 'epoch': 5.69}

 47%|████▋     | 13328/28080 [26:20:18<29:10:46,  7.12s/it]
 47%|████▋     | 13329/28080 [26:20:25<29:09:02,  7.11s/it]
                                                           
{'loss': 0.6094, 'learning_rate': 0.0002825636479233271, 'epoch': 5.69}

 47%|████▋     | 13329/28080 [26:20:25<29:09:02,  7.11s/it]
 47%|████▋     | 13330/28080 [26:20:33<29:16:03,  7.14s/it]
                                                           
{'loss': 0.6007, 'learning_rate': 0.00028253505766283354, 'epoch': 5.69}

 47%|████▋     | 13330/28080 [26:20:33<29:16:03,  7.14s/it]
 47%|████▋     | 13331/28080 [26:20:40<29:08:52,  7.11s/it]
                                                           
{'loss': 0.6135, 'learning_rate': 0.0002825064669694947, 'epoch': 5.69}

 47%|████▋     | 13331/28080 [26:20:40<29:08:52,  7.11s/it]
 47%|████▋     | 13332/28080 [26:20:47<29:12:21,  7.13s/it]
                                                           
{'loss': 0.6162, 'learning_rate': 0.00028247787584369076, 'epoch': 5.7}

 47%|████▋     | 13332/28080 [26:20:47<29:12:21,  7.13s/it]
 47%|████▋     | 13333/28080 [26:20:54<29:10:54,  7.12s/it]
                                                           
{'loss': 0.6259, 'learning_rate': 0.0002824492842858023, 'epoch': 5.7}

 47%|████▋     | 13333/28080 [26:20:54<29:10:54,  7.12s/it]
 47%|████▋     | 13334/28080 [26:21:01<29:10:32,  7.12s/it]
                                                           
{'loss': 0.6252, 'learning_rate': 0.00028242069229620953, 'epoch': 5.7}

 47%|████▋     | 13334/28080 [26:21:01<29:10:32,  7.12s/it]
 47%|████▋     | 13335/28080 [26:21:08<29:14:33,  7.14s/it]
                                                           
{'loss': 0.6269, 'learning_rate': 0.0002823920998752929, 'epoch': 5.7}

 47%|████▋     | 13335/28080 [26:21:08<29:14:33,  7.14s/it]
 47%|████▋     | 13336/28080 [26:21:15<29:07:35,  7.11s/it]
                                                           
{'loss': 0.6297, 'learning_rate': 0.00028236350702343283, 'epoch': 5.7}

 47%|████▋     | 13336/28080 [26:21:15<29:07:35,  7.11s/it]
 47%|████▋     | 13337/28080 [26:21:22<29:08:46,  7.12s/it]
                                                           
{'loss': 0.6025, 'learning_rate': 0.00028233491374100964, 'epoch': 5.7}

 47%|████▋     | 13337/28080 [26:21:22<29:08:46,  7.12s/it]
 48%|████▊     | 13338/28080 [26:21:30<29:14:00,  7.14s/it]
                                                           
{'loss': 0.6132, 'learning_rate': 0.0002823063200284038, 'epoch': 5.7}

 48%|████▊     | 13338/28080 [26:21:30<29:14:00,  7.14s/it]
 48%|████▊     | 13339/28080 [26:21:37<29:14:11,  7.14s/it]
                                                           
{'loss': 0.6038, 'learning_rate': 0.00028227772588599573, 'epoch': 5.7}

 48%|████▊     | 13339/28080 [26:21:37<29:14:11,  7.14s/it]
 48%|████▊     | 13340/28080 [26:21:44<29:08:02,  7.12s/it]
                                                           
{'loss': 0.6071, 'learning_rate': 0.00028224913131416575, 'epoch': 5.7}

 48%|████▊     | 13340/28080 [26:21:44<29:08:02,  7.12s/it]
 48%|████▊     | 13341/28080 [26:21:51<29:09:24,  7.12s/it]
                                                           
{'loss': 0.6068, 'learning_rate': 0.0002822205363132944, 'epoch': 5.7}

 48%|████▊     | 13341/28080 [26:21:51<29:09:24,  7.12s/it]
 48%|████▊     | 13342/28080 [26:21:58<29:07:49,  7.12s/it]
                                                           
{'loss': 0.6037, 'learning_rate': 0.000282191940883762, 'epoch': 5.7}

 48%|████▊     | 13342/28080 [26:21:58<29:07:49,  7.12s/it]
 48%|████▊     | 13343/28080 [26:22:05<29:20:52,  7.17s/it]
                                                           
{'loss': 0.6272, 'learning_rate': 0.0002821633450259491, 'epoch': 5.7}

 48%|████▊     | 13343/28080 [26:22:05<29:20:52,  7.17s/it]
 48%|████▊     | 13344/28080 [26:22:12<29:15:17,  7.15s/it]
                                                           
{'loss': 0.6129, 'learning_rate': 0.000282134748740236, 'epoch': 5.7}

 48%|████▊     | 13344/28080 [26:22:12<29:15:17,  7.15s/it]
 48%|████▊     | 13345/28080 [26:22:19<29:02:49,  7.10s/it]
                                                           
{'loss': 0.6201, 'learning_rate': 0.0002821061520270033, 'epoch': 5.7}

 48%|████▊     | 13345/28080 [26:22:19<29:02:49,  7.10s/it]
 48%|████▊     | 13346/28080 [26:22:26<29:05:48,  7.11s/it]
                                                           
{'loss': 0.6339, 'learning_rate': 0.0002820775548866313, 'epoch': 5.7}

 48%|████▊     | 13346/28080 [26:22:26<29:05:48,  7.11s/it]
 48%|████▊     | 13347/28080 [26:22:34<29:03:10,  7.10s/it]
                                                           
{'loss': 0.6206, 'learning_rate': 0.0002820489573195006, 'epoch': 5.7}

 48%|████▊     | 13347/28080 [26:22:34<29:03:10,  7.10s/it]
 48%|████▊     | 13348/28080 [26:22:41<28:58:52,  7.08s/it]
                                                           
{'loss': 0.6476, 'learning_rate': 0.0002820203593259915, 'epoch': 5.7}

 48%|████▊     | 13348/28080 [26:22:41<28:58:52,  7.08s/it]
 48%|████▊     | 13349/28080 [26:22:48<28:55:02,  7.07s/it]
                                                           
{'loss': 0.6338, 'learning_rate': 0.0002819917609064846, 'epoch': 5.7}

 48%|████▊     | 13349/28080 [26:22:48<28:55:02,  7.07s/it]
 48%|████▊     | 13350/28080 [26:22:55<28:51:37,  7.05s/it]
                                                           
{'loss': 0.6196, 'learning_rate': 0.00028196316206136035, 'epoch': 5.7}

 48%|████▊     | 13350/28080 [26:22:55<28:51:37,  7.05s/it]
 48%|████▊     | 13351/28080 [26:23:02<28:54:09,  7.06s/it]
                                                           
{'loss': 0.6199, 'learning_rate': 0.00028193456279099915, 'epoch': 5.7}

 48%|████▊     | 13351/28080 [26:23:02<28:54:09,  7.06s/it]
 48%|████▊     | 13352/28080 [26:23:09<29:03:54,  7.10s/it]
                                                           
{'loss': 0.6106, 'learning_rate': 0.0002819059630957816, 'epoch': 5.7}

 48%|████▊     | 13352/28080 [26:23:09<29:03:54,  7.10s/it]
 48%|████▊     | 13353/28080 [26:23:16<29:05:52,  7.11s/it]
                                                           
{'loss': 0.615, 'learning_rate': 0.0002818773629760881, 'epoch': 5.7}

 48%|████▊     | 13353/28080 [26:23:16<29:05:52,  7.11s/it]
 48%|████▊     | 13354/28080 [26:23:23<29:11:32,  7.14s/it]
                                                           
{'loss': 0.6184, 'learning_rate': 0.0002818487624322991, 'epoch': 5.7}

 48%|████▊     | 13354/28080 [26:23:23<29:11:32,  7.14s/it]
 48%|████▊     | 13355/28080 [26:23:30<29:11:19,  7.14s/it]
                                                           
{'loss': 0.6186, 'learning_rate': 0.00028182016146479526, 'epoch': 5.71}

 48%|████▊     | 13355/28080 [26:23:30<29:11:19,  7.14s/it]
 48%|████▊     | 13356/28080 [26:23:38<29:12:24,  7.14s/it]
                                                           
{'loss': 0.6123, 'learning_rate': 0.000281791560073957, 'epoch': 5.71}

 48%|████▊     | 13356/28080 [26:23:38<29:12:24,  7.14s/it]
 48%|████▊     | 13357/28080 [26:23:45<29:08:23,  7.13s/it]
                                                           
{'loss': 0.6363, 'learning_rate': 0.0002817629582601648, 'epoch': 5.71}

 48%|████▊     | 13357/28080 [26:23:45<29:08:23,  7.13s/it]
 48%|████▊     | 13358/28080 [26:23:52<29:07:05,  7.12s/it]
                                                           
{'loss': 0.6047, 'learning_rate': 0.0002817343560237992, 'epoch': 5.71}

 48%|████▊     | 13358/28080 [26:23:52<29:07:05,  7.12s/it]
 48%|████▊     | 13359/28080 [26:23:59<29:07:49,  7.12s/it]
                                                           
{'loss': 0.6117, 'learning_rate': 0.00028170575336524073, 'epoch': 5.71}

 48%|████▊     | 13359/28080 [26:23:59<29:07:49,  7.12s/it]
 48%|████▊     | 13360/28080 [26:24:06<29:04:09,  7.11s/it]
                                                           
{'loss': 0.5997, 'learning_rate': 0.00028167715028487, 'epoch': 5.71}

 48%|████▊     | 13360/28080 [26:24:06<29:04:09,  7.11s/it]
 48%|████▊     | 13361/28080 [26:24:13<29:07:49,  7.12s/it]
                                                           
{'loss': 0.5962, 'learning_rate': 0.00028164854678306735, 'epoch': 5.71}

 48%|████▊     | 13361/28080 [26:24:13<29:07:49,  7.12s/it]
 48%|████▊     | 13362/28080 [26:24:20<29:03:29,  7.11s/it]
                                                           
{'loss': 0.6425, 'learning_rate': 0.00028161994286021345, 'epoch': 5.71}

 48%|████▊     | 13362/28080 [26:24:20<29:03:29,  7.11s/it]
 48%|████▊     | 13363/28080 [26:24:27<29:01:15,  7.10s/it]
                                                           
{'loss': 0.6349, 'learning_rate': 0.0002815913385166889, 'epoch': 5.71}

 48%|████▊     | 13363/28080 [26:24:27<29:01:15,  7.10s/it]
 48%|████▊     | 13364/28080 [26:24:34<29:01:11,  7.10s/it]
                                                           
{'loss': 0.6149, 'learning_rate': 0.00028156273375287423, 'epoch': 5.71}

 48%|████▊     | 13364/28080 [26:24:34<29:01:11,  7.10s/it]
 48%|████▊     | 13365/28080 [26:24:41<29:00:24,  7.10s/it]
                                                           
{'loss': 0.626, 'learning_rate': 0.00028153412856914985, 'epoch': 5.71}

 48%|████▊     | 13365/28080 [26:24:41<29:00:24,  7.10s/it]
 48%|████▊     | 13366/28080 [26:24:49<29:01:04,  7.10s/it]
                                                           
{'loss': 0.6117, 'learning_rate': 0.0002815055229658964, 'epoch': 5.71}

 48%|████▊     | 13366/28080 [26:24:49<29:01:04,  7.10s/it]
 48%|████▊     | 13367/28080 [26:24:56<29:03:54,  7.11s/it]
                                                           
{'loss': 0.6308, 'learning_rate': 0.0002814769169434945, 'epoch': 5.71}

 48%|████▊     | 13367/28080 [26:24:56<29:03:54,  7.11s/it]
 48%|████▊     | 13368/28080 [26:25:03<29:07:55,  7.13s/it]
                                                           
{'loss': 0.6353, 'learning_rate': 0.00028144831050232465, 'epoch': 5.71}

 48%|████▊     | 13368/28080 [26:25:03<29:07:55,  7.13s/it]
 48%|████▊     | 13369/28080 [26:25:10<29:05:53,  7.12s/it]
                                                           
{'loss': 0.6359, 'learning_rate': 0.00028141970364276757, 'epoch': 5.71}

 48%|████▊     | 13369/28080 [26:25:10<29:05:53,  7.12s/it]
 48%|████▊     | 13370/28080 [26:25:17<29:13:00,  7.15s/it]
                                                           
{'loss': 0.6129, 'learning_rate': 0.0002813910963652037, 'epoch': 5.71}

 48%|████▊     | 13370/28080 [26:25:17<29:13:00,  7.15s/it]
 48%|████▊     | 13371/28080 [26:25:24<29:15:56,  7.16s/it]
                                                           
{'loss': 0.6254, 'learning_rate': 0.00028136248867001364, 'epoch': 5.71}

 48%|████▊     | 13371/28080 [26:25:24<29:15:56,  7.16s/it]
 48%|████▊     | 13372/28080 [26:25:31<29:09:39,  7.14s/it]
                                                           
{'loss': 0.6116, 'learning_rate': 0.00028133388055757806, 'epoch': 5.71}

 48%|████▊     | 13372/28080 [26:25:31<29:09:39,  7.14s/it]
 48%|████▊     | 13373/28080 [26:25:39<29:11:12,  7.14s/it]
                                                           
{'loss': 0.6062, 'learning_rate': 0.00028130527202827754, 'epoch': 5.71}

 48%|████▊     | 13373/28080 [26:25:39<29:11:12,  7.14s/it]
 48%|████▊     | 13374/28080 [26:25:46<29:09:14,  7.14s/it]
                                                           
{'loss': 0.6171, 'learning_rate': 0.0002812766630824927, 'epoch': 5.71}

 48%|████▊     | 13374/28080 [26:25:46<29:09:14,  7.14s/it]
 48%|████▊     | 13375/28080 [26:25:53<29:07:34,  7.13s/it]
                                                           
{'loss': 0.6176, 'learning_rate': 0.00028124805372060403, 'epoch': 5.71}

 48%|████▊     | 13375/28080 [26:25:53<29:07:34,  7.13s/it]
 48%|████▊     | 13376/28080 [26:26:00<29:01:32,  7.11s/it]
                                                           
{'loss': 0.6167, 'learning_rate': 0.0002812194439429923, 'epoch': 5.71}

 48%|████▊     | 13376/28080 [26:26:00<29:01:32,  7.11s/it]
 48%|████▊     | 13377/28080 [26:26:07<28:58:25,  7.09s/it]
                                                           
{'loss': 0.6221, 'learning_rate': 0.00028119083375003804, 'epoch': 5.71}

 48%|████▊     | 13377/28080 [26:26:07<28:58:25,  7.09s/it]
 48%|████▊     | 13378/28080 [26:26:14<28:52:25,  7.07s/it]
                                                           
{'loss': 0.649, 'learning_rate': 0.0002811622231421219, 'epoch': 5.71}

 48%|████▊     | 13378/28080 [26:26:14<28:52:25,  7.07s/it]
 48%|████▊     | 13379/28080 [26:26:21<28:55:39,  7.08s/it]
                                                           
{'loss': 0.6228, 'learning_rate': 0.0002811336121196246, 'epoch': 5.72}

 48%|████▊     | 13379/28080 [26:26:21<28:55:39,  7.08s/it]
 48%|████▊     | 13380/28080 [26:26:28<29:06:24,  7.13s/it]
                                                           
{'loss': 0.6242, 'learning_rate': 0.0002811050006829267, 'epoch': 5.72}

 48%|████▊     | 13380/28080 [26:26:28<29:06:24,  7.13s/it]
 48%|████▊     | 13381/28080 [26:26:35<29:00:22,  7.10s/it]
                                                           
{'loss': 0.6165, 'learning_rate': 0.0002810763888324089, 'epoch': 5.72}

 48%|████▊     | 13381/28080 [26:26:35<29:00:22,  7.10s/it]
 48%|████▊     | 13382/28080 [26:26:42<28:58:27,  7.10s/it]
                                                           
{'loss': 0.6225, 'learning_rate': 0.0002810477765684517, 'epoch': 5.72}

 48%|████▊     | 13382/28080 [26:26:42<28:58:27,  7.10s/it]
 48%|████▊     | 13383/28080 [26:26:50<29:04:43,  7.12s/it]
                                                           
{'loss': 0.6318, 'learning_rate': 0.0002810191638914359, 'epoch': 5.72}

 48%|████▊     | 13383/28080 [26:26:50<29:04:43,  7.12s/it]
 48%|████▊     | 13384/28080 [26:26:57<28:59:22,  7.10s/it]
                                                           
{'loss': 0.6152, 'learning_rate': 0.0002809905508017421, 'epoch': 5.72}

 48%|████▊     | 13384/28080 [26:26:57<28:59:22,  7.10s/it]
 48%|████▊     | 13385/28080 [26:27:04<29:05:01,  7.12s/it]
                                                           
{'loss': 0.596, 'learning_rate': 0.000280961937299751, 'epoch': 5.72}

 48%|████▊     | 13385/28080 [26:27:04<29:05:01,  7.12s/it]
 48%|████▊     | 13386/28080 [26:27:11<29:02:34,  7.12s/it]
                                                           
{'loss': 0.6156, 'learning_rate': 0.0002809333233858433, 'epoch': 5.72}

 48%|████▊     | 13386/28080 [26:27:11<29:02:34,  7.12s/it]
 48%|████▊     | 13387/28080 [26:27:18<28:56:05,  7.09s/it]
                                                           
{'loss': 0.6142, 'learning_rate': 0.00028090470906039965, 'epoch': 5.72}

 48%|████▊     | 13387/28080 [26:27:18<28:56:05,  7.09s/it]
 48%|████▊     | 13388/28080 [26:27:25<29:03:50,  7.12s/it]
                                                           
{'loss': 0.6, 'learning_rate': 0.0002808760943238008, 'epoch': 5.72}

 48%|████▊     | 13388/28080 [26:27:25<29:03:50,  7.12s/it]
 48%|████▊     | 13389/28080 [26:27:32<29:07:02,  7.14s/it]
                                                           
{'loss': 0.6243, 'learning_rate': 0.0002808474791764273, 'epoch': 5.72}

 48%|████▊     | 13389/28080 [26:27:32<29:07:02,  7.14s/it]
 48%|████▊     | 13390/28080 [26:27:39<29:05:42,  7.13s/it]
                                                           
{'loss': 0.6086, 'learning_rate': 0.00028081886361865983, 'epoch': 5.72}

 48%|████▊     | 13390/28080 [26:27:39<29:05:42,  7.13s/it]
 48%|████▊     | 13391/28080 [26:27:47<29:03:32,  7.12s/it]
                                                           
{'loss': 0.613, 'learning_rate': 0.00028079024765087924, 'epoch': 5.72}

 48%|████▊     | 13391/28080 [26:27:47<29:03:32,  7.12s/it]
 48%|████▊     | 13392/28080 [26:27:54<28:58:30,  7.10s/it]
                                                           
{'loss': 0.6287, 'learning_rate': 0.00028076163127346615, 'epoch': 5.72}

 48%|████▊     | 13392/28080 [26:27:54<28:58:30,  7.10s/it]
 48%|████▊     | 13393/28080 [26:28:01<28:52:41,  7.08s/it]
                                                           
{'loss': 0.6369, 'learning_rate': 0.0002807330144868013, 'epoch': 5.72}

 48%|████▊     | 13393/28080 [26:28:01<28:52:41,  7.08s/it]
 48%|████▊     | 13394/28080 [26:28:08<28:47:33,  7.06s/it]
                                                           
{'loss': 0.6133, 'learning_rate': 0.0002807043972912654, 'epoch': 5.72}

 48%|████▊     | 13394/28080 [26:28:08<28:47:33,  7.06s/it]
 48%|████▊     | 13395/28080 [26:28:15<28:46:47,  7.06s/it]
                                                           
{'loss': 0.6358, 'learning_rate': 0.00028067577968723923, 'epoch': 5.72}

 48%|████▊     | 13395/28080 [26:28:15<28:46:47,  7.06s/it]
 48%|████▊     | 13396/28080 [26:28:22<28:54:07,  7.09s/it]
                                                           
{'loss': 0.6093, 'learning_rate': 0.0002806471616751034, 'epoch': 5.72}

 48%|████▊     | 13396/28080 [26:28:22<28:54:07,  7.09s/it]
 48%|████▊     | 13397/28080 [26:28:29<28:58:50,  7.11s/it]
                                                           
{'loss': 0.617, 'learning_rate': 0.00028061854325523865, 'epoch': 5.72}

 48%|████▊     | 13397/28080 [26:28:29<28:58:50,  7.11s/it]
 48%|████▊     | 13398/28080 [26:28:36<28:56:42,  7.10s/it]
                                                           
{'loss': 0.6222, 'learning_rate': 0.0002805899244280258, 'epoch': 5.72}

 48%|████▊     | 13398/28080 [26:28:36<28:56:42,  7.10s/it]
 48%|████▊     | 13399/28080 [26:28:43<28:51:49,  7.08s/it]
                                                           
{'loss': 0.6076, 'learning_rate': 0.0002805613051938456, 'epoch': 5.72}

 48%|████▊     | 13399/28080 [26:28:43<28:51:49,  7.08s/it]
 48%|████▊     | 13400/28080 [26:28:50<28:52:37,  7.08s/it]
                                                           
{'loss': 0.6161, 'learning_rate': 0.0002805326855530788, 'epoch': 5.72}

 48%|████▊     | 13400/28080 [26:28:50<28:52:37,  7.08s/it]
 48%|████▊     | 13401/28080 [26:28:57<28:54:11,  7.09s/it]
                                                           
{'loss': 0.635, 'learning_rate': 0.000280504065506106, 'epoch': 5.72}

 48%|████▊     | 13401/28080 [26:28:57<28:54:11,  7.09s/it]
 48%|████▊     | 13402/28080 [26:29:05<29:01:52,  7.12s/it]
                                                           
{'loss': 0.6147, 'learning_rate': 0.00028047544505330815, 'epoch': 5.73}

 48%|████▊     | 13402/28080 [26:29:05<29:01:52,  7.12s/it]
 48%|████▊     | 13403/28080 [26:29:12<28:58:21,  7.11s/it]
                                                           
{'loss': 0.6236, 'learning_rate': 0.00028044682419506593, 'epoch': 5.73}

 48%|████▊     | 13403/28080 [26:29:12<28:58:21,  7.11s/it]
 48%|████▊     | 13404/28080 [26:29:19<28:57:00,  7.10s/it]
                                                           
{'loss': 0.6146, 'learning_rate': 0.0002804182029317602, 'epoch': 5.73}

 48%|████▊     | 13404/28080 [26:29:19<28:57:00,  7.10s/it]
 48%|████▊     | 13405/28080 [26:29:26<28:55:25,  7.10s/it]
                                                           
{'loss': 0.6284, 'learning_rate': 0.0002803895812637716, 'epoch': 5.73}

 48%|████▊     | 13405/28080 [26:29:26<28:55:25,  7.10s/it]
 48%|████▊     | 13406/28080 [26:29:33<28:59:14,  7.11s/it]
                                                           
{'loss': 0.6276, 'learning_rate': 0.0002803609591914809, 'epoch': 5.73}

 48%|████▊     | 13406/28080 [26:29:33<28:59:14,  7.11s/it]
 48%|████▊     | 13407/28080 [26:29:40<29:06:08,  7.14s/it]
                                                           
{'loss': 0.6385, 'learning_rate': 0.0002803323367152691, 'epoch': 5.73}

 48%|████▊     | 13407/28080 [26:29:40<29:06:08,  7.14s/it]
 48%|████▊     | 13408/28080 [26:29:47<29:07:42,  7.15s/it]
                                                           
{'loss': 0.6152, 'learning_rate': 0.0002803037138355167, 'epoch': 5.73}

 48%|████▊     | 13408/28080 [26:29:47<29:07:42,  7.15s/it]
 48%|████▊     | 13409/28080 [26:29:54<29:10:05,  7.16s/it]
                                                           
{'loss': 0.6276, 'learning_rate': 0.00028027509055260477, 'epoch': 5.73}

 48%|████▊     | 13409/28080 [26:29:54<29:10:05,  7.16s/it]
 48%|████▊     | 13410/28080 [26:30:02<29:11:56,  7.17s/it]
                                                           
{'loss': 0.6107, 'learning_rate': 0.0002802464668669139, 'epoch': 5.73}

 48%|████▊     | 13410/28080 [26:30:02<29:11:56,  7.17s/it]
 48%|████▊     | 13411/28080 [26:30:09<29:08:31,  7.15s/it]
                                                           
{'loss': 0.5967, 'learning_rate': 0.00028021784277882506, 'epoch': 5.73}

 48%|████▊     | 13411/28080 [26:30:09<29:08:31,  7.15s/it]
 48%|████▊     | 13412/28080 [26:30:16<29:01:42,  7.12s/it]
                                                           
{'loss': 0.6433, 'learning_rate': 0.000280189218288719, 'epoch': 5.73}

 48%|████▊     | 13412/28080 [26:30:16<29:01:42,  7.12s/it]
 48%|████▊     | 13413/28080 [26:30:23<28:54:47,  7.10s/it]
                                                           
{'loss': 0.6263, 'learning_rate': 0.0002801605933969765, 'epoch': 5.73}

 48%|████▊     | 13413/28080 [26:30:23<28:54:47,  7.10s/it]
 48%|████▊     | 13414/28080 [26:30:30<28:59:50,  7.12s/it]
                                                           
{'loss': 0.6054, 'learning_rate': 0.00028013196810397847, 'epoch': 5.73}

 48%|████▊     | 13414/28080 [26:30:30<28:59:50,  7.12s/it]
 48%|████▊     | 13415/28080 [26:30:37<29:05:14,  7.14s/it]
                                                           
{'loss': 0.6198, 'learning_rate': 0.00028010334241010567, 'epoch': 5.73}

 48%|████▊     | 13415/28080 [26:30:37<29:05:14,  7.14s/it]
 48%|████▊     | 13416/28080 [26:30:44<29:00:02,  7.12s/it]
                                                           
{'loss': 0.6298, 'learning_rate': 0.0002800747163157389, 'epoch': 5.73}

 48%|████▊     | 13416/28080 [26:30:44<29:00:02,  7.12s/it]
 48%|████▊     | 13417/28080 [26:30:51<29:02:47,  7.13s/it]
                                                           
{'loss': 0.598, 'learning_rate': 0.0002800460898212591, 'epoch': 5.73}

 48%|████▊     | 13417/28080 [26:30:51<29:02:47,  7.13s/it]
 48%|████▊     | 13418/28080 [26:30:59<28:59:25,  7.12s/it]
                                                           
{'loss': 0.6432, 'learning_rate': 0.00028001746292704704, 'epoch': 5.73}

 48%|████▊     | 13418/28080 [26:30:59<28:59:25,  7.12s/it]
 48%|████▊     | 13419/28080 [26:31:06<28:57:04,  7.11s/it]
                                                           
{'loss': 0.6368, 'learning_rate': 0.0002799888356334837, 'epoch': 5.73}

 48%|████▊     | 13419/28080 [26:31:06<28:57:04,  7.11s/it]
 48%|████▊     | 13420/28080 [26:31:13<28:59:47,  7.12s/it]
                                                           
{'loss': 0.6178, 'learning_rate': 0.0002799602079409497, 'epoch': 5.73}

 48%|████▊     | 13420/28080 [26:31:13<28:59:47,  7.12s/it]
 48%|████▊     | 13421/28080 [26:31:20<29:02:21,  7.13s/it]
                                                           
{'loss': 0.5983, 'learning_rate': 0.0002799315798498261, 'epoch': 5.73}

 48%|████▊     | 13421/28080 [26:31:20<29:02:21,  7.13s/it]
 48%|████▊     | 13422/28080 [26:31:27<28:59:56,  7.12s/it]
                                                           
{'loss': 0.6079, 'learning_rate': 0.00027990295136049375, 'epoch': 5.73}

 48%|████▊     | 13422/28080 [26:31:27<28:59:56,  7.12s/it]
 48%|████▊     | 13423/28080 [26:31:34<29:06:20,  7.15s/it]
                                                           
{'loss': 0.6324, 'learning_rate': 0.00027987432247333346, 'epoch': 5.73}

 48%|████▊     | 13423/28080 [26:31:34<29:06:20,  7.15s/it]
 48%|████▊     | 13424/28080 [26:31:41<28:57:32,  7.11s/it]
                                                           
{'loss': 0.6253, 'learning_rate': 0.0002798456931887261, 'epoch': 5.73}

 48%|████▊     | 13424/28080 [26:31:41<28:57:32,  7.11s/it]
 48%|████▊     | 13425/28080 [26:31:48<28:56:01,  7.11s/it]
                                                           
{'loss': 0.6206, 'learning_rate': 0.0002798170635070526, 'epoch': 5.74}

 48%|████▊     | 13425/28080 [26:31:48<28:56:01,  7.11s/it]
 48%|████▊     | 13426/28080 [26:31:55<28:55:47,  7.11s/it]
                                                           
{'loss': 0.6343, 'learning_rate': 0.00027978843342869387, 'epoch': 5.74}

 48%|████▊     | 13426/28080 [26:31:55<28:55:47,  7.11s/it]
 48%|████▊     | 13427/28080 [26:32:03<28:59:14,  7.12s/it]
                                                           
{'loss': 0.6116, 'learning_rate': 0.0002797598029540307, 'epoch': 5.74}

 48%|████▊     | 13427/28080 [26:32:03<28:59:14,  7.12s/it]
 48%|████▊     | 13428/28080 [26:32:10<28:54:01,  7.10s/it]
                                                           
{'loss': 0.6528, 'learning_rate': 0.0002797311720834441, 'epoch': 5.74}

 48%|████▊     | 13428/28080 [26:32:10<28:54:01,  7.10s/it]
 48%|████▊     | 13429/28080 [26:32:17<28:54:26,  7.10s/it]
                                                           
{'loss': 0.6324, 'learning_rate': 0.00027970254081731487, 'epoch': 5.74}

 48%|████▊     | 13429/28080 [26:32:17<28:54:26,  7.10s/it]
 48%|████▊     | 13430/28080 [26:32:24<28:52:20,  7.09s/it]
                                                           
{'loss': 0.6326, 'learning_rate': 0.00027967390915602404, 'epoch': 5.74}

 48%|████▊     | 13430/28080 [26:32:24<28:52:20,  7.09s/it]
 48%|████▊     | 13431/28080 [26:32:31<28:49:42,  7.08s/it]
                                                           
{'loss': 0.6258, 'learning_rate': 0.00027964527709995244, 'epoch': 5.74}

 48%|████▊     | 13431/28080 [26:32:31<28:49:42,  7.08s/it]
 48%|████▊     | 13432/28080 [26:32:38<28:48:48,  7.08s/it]
                                                           
{'loss': 0.6133, 'learning_rate': 0.000279616644649481, 'epoch': 5.74}

 48%|████▊     | 13432/28080 [26:32:38<28:48:48,  7.08s/it]
 48%|████▊     | 13433/28080 [26:32:45<28:50:33,  7.09s/it]
                                                           
{'loss': 0.6185, 'learning_rate': 0.0002795880118049906, 'epoch': 5.74}

 48%|████▊     | 13433/28080 [26:32:45<28:50:33,  7.09s/it]
 48%|████▊     | 13434/28080 [26:32:52<29:00:55,  7.13s/it]
                                                           
{'loss': 0.6239, 'learning_rate': 0.0002795593785668623, 'epoch': 5.74}

 48%|████▊     | 13434/28080 [26:32:52<29:00:55,  7.13s/it]
 48%|████▊     | 13435/28080 [26:32:59<28:58:46,  7.12s/it]
                                                           
{'loss': 0.614, 'learning_rate': 0.00027953074493547697, 'epoch': 5.74}

 48%|████▊     | 13435/28080 [26:32:59<28:58:46,  7.12s/it]
 48%|████▊     | 13436/28080 [26:33:06<28:51:42,  7.10s/it]
                                                           
{'loss': 0.6423, 'learning_rate': 0.00027950211091121554, 'epoch': 5.74}

 48%|████▊     | 13436/28080 [26:33:06<28:51:42,  7.10s/it]
 48%|████▊     | 13437/28080 [26:33:14<28:50:19,  7.09s/it]
                                                           
{'loss': 0.6284, 'learning_rate': 0.00027947347649445893, 'epoch': 5.74}

 48%|████▊     | 13437/28080 [26:33:14<28:50:19,  7.09s/it]
 48%|████▊     | 13438/28080 [26:33:21<28:50:37,  7.09s/it]
                                                           
{'loss': 0.631, 'learning_rate': 0.00027944484168558815, 'epoch': 5.74}

 48%|████▊     | 13438/28080 [26:33:21<28:50:37,  7.09s/it]
 48%|████▊     | 13439/28080 [26:33:28<28:48:29,  7.08s/it]
                                                           
{'loss': 0.6356, 'learning_rate': 0.00027941620648498416, 'epoch': 5.74}

 48%|████▊     | 13439/28080 [26:33:28<28:48:29,  7.08s/it]
 48%|████▊     | 13440/28080 [26:33:35<28:52:21,  7.10s/it]
                                                           
{'loss': 0.6252, 'learning_rate': 0.0002793875708930278, 'epoch': 5.74}

 48%|████▊     | 13440/28080 [26:33:35<28:52:21,  7.10s/it]
 48%|████▊     | 13441/28080 [26:33:42<28:54:55,  7.11s/it]
                                                           
{'loss': 0.609, 'learning_rate': 0.00027935893491010024, 'epoch': 5.74}

 48%|████▊     | 13441/28080 [26:33:42<28:54:55,  7.11s/it]
 48%|████▊     | 13442/28080 [26:33:49<29:01:00,  7.14s/it]
                                                           
{'loss': 0.6215, 'learning_rate': 0.0002793302985365822, 'epoch': 5.74}

 48%|████▊     | 13442/28080 [26:33:49<29:01:00,  7.14s/it]
 48%|████▊     | 13443/28080 [26:33:56<28:57:49,  7.12s/it]
                                                           
{'loss': 0.6102, 'learning_rate': 0.0002793016617728549, 'epoch': 5.74}

 48%|████▊     | 13443/28080 [26:33:56<28:57:49,  7.12s/it]
 48%|████▊     | 13444/28080 [26:34:03<28:55:17,  7.11s/it]
                                                           
{'loss': 0.6006, 'learning_rate': 0.0002792730246192992, 'epoch': 5.74}

 48%|████▊     | 13444/28080 [26:34:03<28:55:17,  7.11s/it]
 48%|████▊     | 13445/28080 [26:34:11<28:58:38,  7.13s/it]
                                                           
{'loss': 0.613, 'learning_rate': 0.0002792443870762961, 'epoch': 5.74}

 48%|████▊     | 13445/28080 [26:34:11<28:58:38,  7.13s/it]
 48%|████▊     | 13446/28080 [26:34:18<28:57:53,  7.13s/it]
                                                           
{'loss': 0.6177, 'learning_rate': 0.0002792157491442266, 'epoch': 5.74}

 48%|████▊     | 13446/28080 [26:34:18<28:57:53,  7.13s/it]
 48%|████▊     | 13447/28080 [26:34:25<29:00:04,  7.13s/it]
                                                           
{'loss': 0.6018, 'learning_rate': 0.0002791871108234716, 'epoch': 5.74}

 48%|████▊     | 13447/28080 [26:34:25<29:00:04,  7.13s/it]
 48%|████▊     | 13448/28080 [26:34:32<28:58:31,  7.13s/it]
                                                           
{'loss': 0.6149, 'learning_rate': 0.00027915847211441234, 'epoch': 5.74}

 48%|████▊     | 13448/28080 [26:34:32<28:58:31,  7.13s/it]
 48%|████▊     | 13449/28080 [26:34:39<29:02:05,  7.14s/it]
                                                           
{'loss': 0.62, 'learning_rate': 0.00027912983301742964, 'epoch': 5.75}

 48%|████▊     | 13449/28080 [26:34:39<29:02:05,  7.14s/it]
 48%|████▊     | 13450/28080 [26:34:46<29:01:25,  7.14s/it]
                                                           
{'loss': 0.6062, 'learning_rate': 0.00027910119353290457, 'epoch': 5.75}

 48%|████▊     | 13450/28080 [26:34:46<29:01:25,  7.14s/it]
 48%|████▊     | 13451/28080 [26:34:53<29:07:31,  7.17s/it]
                                                           
{'loss': 0.6377, 'learning_rate': 0.00027907255366121816, 'epoch': 5.75}

 48%|████▊     | 13451/28080 [26:34:53<29:07:31,  7.17s/it]
 48%|████▊     | 13452/28080 [26:35:01<29:03:04,  7.15s/it]
                                                           
{'loss': 0.6342, 'learning_rate': 0.00027904391340275136, 'epoch': 5.75}

 48%|████▊     | 13452/28080 [26:35:01<29:03:04,  7.15s/it]
 48%|████▊     | 13453/28080 [26:35:08<29:04:24,  7.16s/it]
                                                           
{'loss': 0.5987, 'learning_rate': 0.0002790152727578853, 'epoch': 5.75}

 48%|████▊     | 13453/28080 [26:35:08<29:04:24,  7.16s/it]
 48%|████▊     | 13454/28080 [26:35:15<29:04:40,  7.16s/it]
                                                           
{'loss': 0.6172, 'learning_rate': 0.00027898663172700095, 'epoch': 5.75}

 48%|████▊     | 13454/28080 [26:35:15<29:04:40,  7.16s/it]
 48%|████▊     | 13455/28080 [26:35:22<29:04:04,  7.16s/it]
                                                           
{'loss': 0.6047, 'learning_rate': 0.00027895799031047943, 'epoch': 5.75}

 48%|████▊     | 13455/28080 [26:35:22<29:04:04,  7.16s/it]
 48%|████▊     | 13456/28080 [26:35:29<28:55:14,  7.12s/it]
                                                           
{'loss': 0.6193, 'learning_rate': 0.00027892934850870163, 'epoch': 5.75}

 48%|████▊     | 13456/28080 [26:35:29<28:55:14,  7.12s/it]
 48%|████▊     | 13457/28080 [26:35:36<29:01:02,  7.14s/it]
                                                           
{'loss': 0.6142, 'learning_rate': 0.00027890070632204876, 'epoch': 5.75}

 48%|████▊     | 13457/28080 [26:35:36<29:01:02,  7.14s/it]
 48%|████▊     | 13458/28080 [26:35:43<28:56:22,  7.13s/it]
                                                           
{'loss': 0.6163, 'learning_rate': 0.00027887206375090174, 'epoch': 5.75}

 48%|████▊     | 13458/28080 [26:35:43<28:56:22,  7.13s/it]
 48%|████▊     | 13459/28080 [26:35:50<28:55:54,  7.12s/it]
                                                           
{'loss': 0.6258, 'learning_rate': 0.00027884342079564174, 'epoch': 5.75}

 48%|████▊     | 13459/28080 [26:35:50<28:55:54,  7.12s/it]
 48%|████▊     | 13460/28080 [26:35:58<28:51:49,  7.11s/it]
                                                           
{'loss': 0.6528, 'learning_rate': 0.0002788147774566498, 'epoch': 5.75}

 48%|████▊     | 13460/28080 [26:35:58<28:51:49,  7.11s/it]
 48%|████▊     | 13461/28080 [26:36:05<28:55:50,  7.12s/it]
                                                           
{'loss': 0.6125, 'learning_rate': 0.00027878613373430694, 'epoch': 5.75}

 48%|████▊     | 13461/28080 [26:36:05<28:55:50,  7.12s/it]
 48%|████▊     | 13462/28080 [26:36:12<28:55:32,  7.12s/it]
                                                           
{'loss': 0.6172, 'learning_rate': 0.0002787574896289943, 'epoch': 5.75}

 48%|████▊     | 13462/28080 [26:36:12<28:55:32,  7.12s/it]
 48%|████▊     | 13463/28080 [26:36:19<28:55:45,  7.12s/it]
                                                           
{'loss': 0.6091, 'learning_rate': 0.0002787288451410929, 'epoch': 5.75}

 48%|████▊     | 13463/28080 [26:36:19<28:55:45,  7.12s/it]
 48%|████▊     | 13464/28080 [26:36:26<28:56:24,  7.13s/it]
                                                           
{'loss': 0.6072, 'learning_rate': 0.0002787002002709839, 'epoch': 5.75}

 48%|████▊     | 13464/28080 [26:36:26<28:56:24,  7.13s/it]
 48%|████▊     | 13465/28080 [26:36:33<28:59:44,  7.14s/it]
                                                           
{'loss': 0.611, 'learning_rate': 0.0002786715550190483, 'epoch': 5.75}

 48%|████▊     | 13465/28080 [26:36:33<28:59:44,  7.14s/it]
 48%|████▊     | 13466/28080 [26:36:40<28:57:52,  7.14s/it]
                                                           
{'loss': 0.639, 'learning_rate': 0.0002786429093856672, 'epoch': 5.75}

 48%|████▊     | 13466/28080 [26:36:40<28:57:52,  7.14s/it]
 48%|████▊     | 13467/28080 [26:36:48<28:56:26,  7.13s/it]
                                                           
{'loss': 0.6237, 'learning_rate': 0.0002786142633712218, 'epoch': 5.75}

 48%|████▊     | 13467/28080 [26:36:48<28:56:26,  7.13s/it]
 48%|████▊     | 13468/28080 [26:36:55<29:00:21,  7.15s/it]
                                                           
{'loss': 0.6382, 'learning_rate': 0.00027858561697609313, 'epoch': 5.75}

 48%|████▊     | 13468/28080 [26:36:55<29:00:21,  7.15s/it]
 48%|████▊     | 13469/28080 [26:37:02<28:54:04,  7.12s/it]
                                                           
{'loss': 0.6012, 'learning_rate': 0.0002785569702006623, 'epoch': 5.75}

 48%|████▊     | 13469/28080 [26:37:02<28:54:04,  7.12s/it]
 48%|████▊     | 13470/28080 [26:37:09<28:52:32,  7.12s/it]
                                                           
{'loss': 0.6112, 'learning_rate': 0.0002785283230453105, 'epoch': 5.75}

 48%|████▊     | 13470/28080 [26:37:09<28:52:32,  7.12s/it]
 48%|████▊     | 13471/28080 [26:37:16<28:55:16,  7.13s/it]
                                                           
{'loss': 0.6202, 'learning_rate': 0.00027849967551041874, 'epoch': 5.75}

 48%|████▊     | 13471/28080 [26:37:16<28:55:16,  7.13s/it]
 48%|████▊     | 13472/28080 [26:37:23<28:53:43,  7.12s/it]
                                                           
{'loss': 0.6342, 'learning_rate': 0.0002784710275963682, 'epoch': 5.76}

 48%|████▊     | 13472/28080 [26:37:23<28:53:43,  7.12s/it]
 48%|████▊     | 13473/28080 [26:37:30<28:51:01,  7.11s/it]
                                                           
{'loss': 0.6068, 'learning_rate': 0.00027844237930353997, 'epoch': 5.76}

 48%|████▊     | 13473/28080 [26:37:30<28:51:01,  7.11s/it]
 48%|████▊     | 13474/28080 [26:37:37<28:51:40,  7.11s/it]
                                                           
{'loss': 0.6066, 'learning_rate': 0.00027841373063231537, 'epoch': 5.76}

 48%|████▊     | 13474/28080 [26:37:37<28:51:40,  7.11s/it]
 48%|████▊     | 13475/28080 [26:37:45<28:56:46,  7.14s/it]
                                                           
{'loss': 0.6178, 'learning_rate': 0.00027838508158307523, 'epoch': 5.76}

 48%|████▊     | 13475/28080 [26:37:45<28:56:46,  7.14s/it]
 48%|████▊     | 13476/28080 [26:37:52<29:03:51,  7.16s/it]
                                                           
{'loss': 0.6067, 'learning_rate': 0.0002783564321562009, 'epoch': 5.76}

 48%|████▊     | 13476/28080 [26:37:52<29:03:51,  7.16s/it]
 48%|████▊     | 13477/28080 [26:37:59<29:03:49,  7.16s/it]
                                                           
{'loss': 0.607, 'learning_rate': 0.00027832778235207357, 'epoch': 5.76}

 48%|████▊     | 13477/28080 [26:37:59<29:03:49,  7.16s/it]
 48%|████▊     | 13478/28080 [26:38:06<28:50:38,  7.11s/it]
                                                           
{'loss': 0.617, 'learning_rate': 0.0002782991321710743, 'epoch': 5.76}

 48%|████▊     | 13478/28080 [26:38:06<28:50:38,  7.11s/it]
 48%|████▊     | 13479/28080 [26:38:13<28:51:59,  7.12s/it]
                                                           
{'loss': 0.6328, 'learning_rate': 0.00027827048161358425, 'epoch': 5.76}

 48%|████▊     | 13479/28080 [26:38:13<28:51:59,  7.12s/it]
 48%|████▊     | 13480/28080 [26:38:20<28:55:31,  7.13s/it]
                                                           
{'loss': 0.6167, 'learning_rate': 0.0002782418306799846, 'epoch': 5.76}

 48%|████▊     | 13480/28080 [26:38:20<28:55:31,  7.13s/it]
 48%|████▊     | 13481/28080 [26:38:27<28:50:15,  7.11s/it]
                                                           
{'loss': 0.6213, 'learning_rate': 0.00027821317937065654, 'epoch': 5.76}

 48%|████▊     | 13481/28080 [26:38:27<28:50:15,  7.11s/it]
 48%|████▊     | 13482/28080 [26:38:34<28:47:32,  7.10s/it]
                                                           
{'loss': 0.6256, 'learning_rate': 0.00027818452768598123, 'epoch': 5.76}

 48%|████▊     | 13482/28080 [26:38:34<28:47:32,  7.10s/it]
 48%|████▊     | 13483/28080 [26:38:41<28:49:26,  7.11s/it]
                                                           
{'loss': 0.6228, 'learning_rate': 0.0002781558756263398, 'epoch': 5.76}

 48%|████▊     | 13483/28080 [26:38:41<28:49:26,  7.11s/it]
 48%|████▊     | 13484/28080 [26:38:48<28:42:00,  7.08s/it]
                                                           
{'loss': 0.6286, 'learning_rate': 0.0002781272231921136, 'epoch': 5.76}

 48%|████▊     | 13484/28080 [26:38:48<28:42:00,  7.08s/it]
 48%|████▊     | 13485/28080 [26:38:56<28:46:27,  7.10s/it]
                                                           
{'loss': 0.628, 'learning_rate': 0.00027809857038368365, 'epoch': 5.76}

 48%|████▊     | 13485/28080 [26:38:56<28:46:27,  7.10s/it]
 48%|████▊     | 13486/28080 [26:39:03<28:52:21,  7.12s/it]
                                                           
{'loss': 0.6273, 'learning_rate': 0.0002780699172014312, 'epoch': 5.76}

 48%|████▊     | 13486/28080 [26:39:03<28:52:21,  7.12s/it]
 48%|████▊     | 13487/28080 [26:39:10<28:50:08,  7.11s/it]
                                                           
{'loss': 0.6296, 'learning_rate': 0.00027804126364573743, 'epoch': 5.76}

 48%|████▊     | 13487/28080 [26:39:10<28:50:08,  7.11s/it]
 48%|████▊     | 13488/28080 [26:39:17<28:49:55,  7.11s/it]
                                                           
{'loss': 0.6097, 'learning_rate': 0.0002780126097169837, 'epoch': 5.76}

 48%|████▊     | 13488/28080 [26:39:17<28:49:55,  7.11s/it]
 48%|████▊     | 13489/28080 [26:39:24<28:49:58,  7.11s/it]
                                                           
{'loss': 0.6326, 'learning_rate': 0.0002779839554155511, 'epoch': 5.76}

 48%|████▊     | 13489/28080 [26:39:24<28:49:58,  7.11s/it]
 48%|████▊     | 13490/28080 [26:39:31<28:53:13,  7.13s/it]
                                                           
{'loss': 0.6357, 'learning_rate': 0.0002779553007418207, 'epoch': 5.76}

 48%|████▊     | 13490/28080 [26:39:31<28:53:13,  7.13s/it]
 48%|████▊     | 13491/28080 [26:39:39<29:03:44,  7.17s/it]
                                                           
{'loss': 0.6395, 'learning_rate': 0.00027792664569617395, 'epoch': 5.76}

 48%|████▊     | 13491/28080 [26:39:39<29:03:44,  7.17s/it]
 48%|████▊     | 13492/28080 [26:39:46<28:56:44,  7.14s/it]
                                                           
{'loss': 0.6374, 'learning_rate': 0.00027789799027899193, 'epoch': 5.76}

 48%|████▊     | 13492/28080 [26:39:46<28:56:44,  7.14s/it]
 48%|████▊     | 13493/28080 [26:39:53<28:52:01,  7.12s/it]
                                                           
{'loss': 0.6374, 'learning_rate': 0.0002778693344906559, 'epoch': 5.76}

 48%|████▊     | 13493/28080 [26:39:53<28:52:01,  7.12s/it]
 48%|████▊     | 13494/28080 [26:40:00<28:53:09,  7.13s/it]
                                                           
{'loss': 0.6374, 'learning_rate': 0.00027784067833154725, 'epoch': 5.76}

 48%|████▊     | 13494/28080 [26:40:00<28:53:09,  7.13s/it]
 48%|████▊     | 13495/28080 [26:40:07<28:49:40,  7.12s/it]
                                                           
{'loss': 0.6263, 'learning_rate': 0.000277812021802047, 'epoch': 5.76}

 48%|████▊     | 13495/28080 [26:40:07<28:49:40,  7.12s/it]
 48%|████▊     | 13496/28080 [26:40:14<28:45:07,  7.10s/it]
                                                           
{'loss': 0.6243, 'learning_rate': 0.0002777833649025366, 'epoch': 5.77}

 48%|████▊     | 13496/28080 [26:40:14<28:45:07,  7.10s/it]
 48%|████▊     | 13497/28080 [26:40:21<28:46:49,  7.10s/it]
                                                           
{'loss': 0.6191, 'learning_rate': 0.0002777547076333971, 'epoch': 5.77}

 48%|████▊     | 13497/28080 [26:40:21<28:46:49,  7.10s/it]
 48%|████▊     | 13498/28080 [26:40:28<28:52:27,  7.13s/it]
                                                           
{'loss': 0.6172, 'learning_rate': 0.00027772604999500987, 'epoch': 5.77}

 48%|████▊     | 13498/28080 [26:40:28<28:52:27,  7.13s/it]
 48%|████▊     | 13499/28080 [26:40:35<28:56:42,  7.15s/it]
                                                           
{'loss': 0.6303, 'learning_rate': 0.00027769739198775615, 'epoch': 5.77}

 48%|████▊     | 13499/28080 [26:40:35<28:56:42,  7.15s/it]
 48%|████▊     | 13500/28080 [26:40:43<29:00:27,  7.16s/it]
                                                           
{'loss': 0.6388, 'learning_rate': 0.0002776687336120172, 'epoch': 5.77}

 48%|████▊     | 13500/28080 [26:40:43<29:00:27,  7.16s/it]
 48%|████▊     | 13501/28080 [26:40:50<28:56:42,  7.15s/it]
                                                           
{'loss': 0.6217, 'learning_rate': 0.0002776400748681743, 'epoch': 5.77}

 48%|████▊     | 13501/28080 [26:40:50<28:56:42,  7.15s/it]
 48%|████▊     | 13502/28080 [26:40:57<28:56:21,  7.15s/it]
                                                           
{'loss': 0.6321, 'learning_rate': 0.0002776114157566087, 'epoch': 5.77}

 48%|████▊     | 13502/28080 [26:40:57<28:56:21,  7.15s/it]
 48%|████▊     | 13503/28080 [26:41:04<28:48:03,  7.11s/it]
                                                           
{'loss': 0.6306, 'learning_rate': 0.0002775827562777017, 'epoch': 5.77}

 48%|████▊     | 13503/28080 [26:41:04<28:48:03,  7.11s/it]
 48%|████▊     | 13504/28080 [26:41:11<28:48:51,  7.12s/it]
                                                           
{'loss': 0.617, 'learning_rate': 0.0002775540964318346, 'epoch': 5.77}

 48%|████▊     | 13504/28080 [26:41:11<28:48:51,  7.12s/it]
 48%|████▊     | 13505/28080 [26:41:18<28:51:37,  7.13s/it]
                                                           
{'loss': 0.604, 'learning_rate': 0.0002775254362193887, 'epoch': 5.77}

 48%|████▊     | 13505/28080 [26:41:18<28:51:37,  7.13s/it]
 48%|████▊     | 13506/28080 [26:41:25<28:46:44,  7.11s/it]
                                                           
{'loss': 0.6363, 'learning_rate': 0.0002774967756407452, 'epoch': 5.77}

 48%|████▊     | 13506/28080 [26:41:25<28:46:44,  7.11s/it]
 48%|████▊     | 13507/28080 [26:41:32<28:51:08,  7.13s/it]
                                                           
{'loss': 0.6044, 'learning_rate': 0.00027746811469628546, 'epoch': 5.77}

 48%|████▊     | 13507/28080 [26:41:32<28:51:08,  7.13s/it]
 48%|████▊     | 13508/28080 [26:41:40<28:52:43,  7.13s/it]
                                                           
{'loss': 0.6256, 'learning_rate': 0.00027743945338639086, 'epoch': 5.77}

 48%|████▊     | 13508/28080 [26:41:40<28:52:43,  7.13s/it]
 48%|████▊     | 13509/28080 [26:41:47<28:58:45,  7.16s/it]
                                                           
{'loss': 0.6235, 'learning_rate': 0.0002774107917114426, 'epoch': 5.77}

 48%|████▊     | 13509/28080 [26:41:47<28:58:45,  7.16s/it]
 48%|████▊     | 13510/28080 [26:41:54<28:54:49,  7.14s/it]
                                                           
{'loss': 0.6162, 'learning_rate': 0.00027738212967182206, 'epoch': 5.77}

 48%|████▊     | 13510/28080 [26:41:54<28:54:49,  7.14s/it]
 48%|████▊     | 13511/28080 [26:42:01<28:48:04,  7.12s/it]
                                                           
{'loss': 0.6289, 'learning_rate': 0.00027735346726791055, 'epoch': 5.77}

 48%|████▊     | 13511/28080 [26:42:01<28:48:04,  7.12s/it]
 48%|████▊     | 13512/28080 [26:42:08<28:36:38,  7.07s/it]
                                                           
{'loss': 0.629, 'learning_rate': 0.0002773248045000894, 'epoch': 5.77}

 48%|████▊     | 13512/28080 [26:42:08<28:36:38,  7.07s/it]
 48%|████▊     | 13513/28080 [26:42:15<28:40:30,  7.09s/it]
                                                           
{'loss': 0.6204, 'learning_rate': 0.00027729614136873986, 'epoch': 5.77}

 48%|████▊     | 13513/28080 [26:42:15<28:40:30,  7.09s/it]
 48%|████▊     | 13514/28080 [26:42:22<28:42:33,  7.10s/it]
                                                           
{'loss': 0.626, 'learning_rate': 0.0002772674778742433, 'epoch': 5.77}

 48%|████▊     | 13514/28080 [26:42:22<28:42:33,  7.10s/it]
 48%|████▊     | 13515/28080 [26:42:29<28:40:03,  7.09s/it]
                                                           
{'loss': 0.6405, 'learning_rate': 0.0002772388140169811, 'epoch': 5.77}

 48%|████▊     | 13515/28080 [26:42:29<28:40:03,  7.09s/it]
 48%|████▊     | 13516/28080 [26:42:36<28:46:25,  7.11s/it]
                                                           
{'loss': 0.6523, 'learning_rate': 0.0002772101497973346, 'epoch': 5.77}

 48%|████▊     | 13516/28080 [26:42:36<28:46:25,  7.11s/it]
 48%|████▊     | 13517/28080 [26:42:44<28:47:06,  7.12s/it]
                                                           
{'loss': 0.623, 'learning_rate': 0.0002771814852156851, 'epoch': 5.77}

 48%|████▊     | 13517/28080 [26:42:44<28:47:06,  7.12s/it]
 48%|████▊     | 13518/28080 [26:42:51<28:48:34,  7.12s/it]
                                                           
{'loss': 0.6214, 'learning_rate': 0.00027715282027241403, 'epoch': 5.77}

 48%|████▊     | 13518/28080 [26:42:51<28:48:34,  7.12s/it]
 48%|████▊     | 13519/28080 [26:42:58<28:47:52,  7.12s/it]
                                                           
{'loss': 0.6203, 'learning_rate': 0.0002771241549679026, 'epoch': 5.78}

 48%|████▊     | 13519/28080 [26:42:58<28:47:52,  7.12s/it]
 48%|████▊     | 13520/28080 [26:43:05<28:38:58,  7.08s/it]
                                                           
{'loss': 0.6147, 'learning_rate': 0.00027709548930253235, 'epoch': 5.78}

 48%|████▊     | 13520/28080 [26:43:05<28:38:58,  7.08s/it]
 48%|████▊     | 13521/28080 [26:43:12<28:38:19,  7.08s/it]
                                                           
{'loss': 0.6357, 'learning_rate': 0.00027706682327668453, 'epoch': 5.78}

 48%|████▊     | 13521/28080 [26:43:12<28:38:19,  7.08s/it]
 48%|████▊     | 13522/28080 [26:43:19<28:49:32,  7.13s/it]
                                                           
{'loss': 0.603, 'learning_rate': 0.00027703815689074065, 'epoch': 5.78}

 48%|████▊     | 13522/28080 [26:43:19<28:49:32,  7.13s/it]
 48%|████▊     | 13523/28080 [26:43:26<28:53:51,  7.15s/it]
                                                           
{'loss': 0.6117, 'learning_rate': 0.0002770094901450818, 'epoch': 5.78}

 48%|████▊     | 13523/28080 [26:43:26<28:53:51,  7.15s/it]
 48%|████▊     | 13524/28080 [26:43:33<28:44:17,  7.11s/it]
                                                           
{'loss': 0.6323, 'learning_rate': 0.00027698082304008966, 'epoch': 5.78}

 48%|████▊     | 13524/28080 [26:43:33<28:44:17,  7.11s/it]
 48%|████▊     | 13525/28080 [26:43:41<28:55:13,  7.15s/it]
                                                           
{'loss': 0.614, 'learning_rate': 0.0002769521555761455, 'epoch': 5.78}

 48%|████▊     | 13525/28080 [26:43:41<28:55:13,  7.15s/it]
 48%|████▊     | 13526/28080 [26:43:48<28:55:36,  7.16s/it]
                                                           
{'loss': 0.5947, 'learning_rate': 0.00027692348775363066, 'epoch': 5.78}

 48%|████▊     | 13526/28080 [26:43:48<28:55:36,  7.16s/it]
 48%|████▊     | 13527/28080 [26:43:55<28:48:26,  7.13s/it]
                                                           
{'loss': 0.6403, 'learning_rate': 0.00027689481957292675, 'epoch': 5.78}

 48%|████▊     | 13527/28080 [26:43:55<28:48:26,  7.13s/it]
 48%|████▊     | 13528/28080 [26:44:02<28:45:56,  7.12s/it]
                                                           
{'loss': 0.6234, 'learning_rate': 0.00027686615103441486, 'epoch': 5.78}

 48%|████▊     | 13528/28080 [26:44:02<28:45:56,  7.12s/it]
 48%|████▊     | 13529/28080 [26:44:09<28:46:05,  7.12s/it]
                                                           
{'loss': 0.6402, 'learning_rate': 0.0002768374821384766, 'epoch': 5.78}

 48%|████▊     | 13529/28080 [26:44:09<28:46:05,  7.12s/it]
 48%|████▊     | 13530/28080 [26:44:16<28:39:27,  7.09s/it]
                                                           
{'loss': 0.6389, 'learning_rate': 0.0002768088128854933, 'epoch': 5.78}

 48%|████▊     | 13530/28080 [26:44:16<28:39:27,  7.09s/it]
 48%|████▊     | 13531/28080 [26:44:23<28:40:38,  7.10s/it]
                                                           
{'loss': 0.6307, 'learning_rate': 0.0002767801432758464, 'epoch': 5.78}

 48%|████▊     | 13531/28080 [26:44:23<28:40:38,  7.10s/it]
 48%|████▊     | 13532/28080 [26:44:30<28:44:07,  7.11s/it]
                                                           
{'loss': 0.6149, 'learning_rate': 0.00027675147330991735, 'epoch': 5.78}

 48%|████▊     | 13532/28080 [26:44:30<28:44:07,  7.11s/it]
 48%|████▊     | 13533/28080 [26:44:37<28:37:50,  7.09s/it]
                                                           
{'loss': 0.6213, 'learning_rate': 0.0002767228029880875, 'epoch': 5.78}

 48%|████▊     | 13533/28080 [26:44:37<28:37:50,  7.09s/it]
 48%|████▊     | 13534/28080 [26:44:44<28:36:47,  7.08s/it]
                                                           
{'loss': 0.6048, 'learning_rate': 0.00027669413231073845, 'epoch': 5.78}

 48%|████▊     | 13534/28080 [26:44:44<28:36:47,  7.08s/it]
 48%|████▊     | 13535/28080 [26:44:52<28:41:23,  7.10s/it]
                                                           
{'loss': 0.6165, 'learning_rate': 0.0002766654612782514, 'epoch': 5.78}

 48%|████▊     | 13535/28080 [26:44:52<28:41:23,  7.10s/it]
 48%|████▊     | 13536/28080 [26:44:59<28:48:27,  7.13s/it]
                                                           
{'loss': 0.6138, 'learning_rate': 0.0002766367898910079, 'epoch': 5.78}

 48%|████▊     | 13536/28080 [26:44:59<28:48:27,  7.13s/it]
 48%|████▊     | 13537/28080 [26:45:06<28:45:32,  7.12s/it]
                                                           
{'loss': 0.6118, 'learning_rate': 0.0002766081181493894, 'epoch': 5.78}

 48%|████▊     | 13537/28080 [26:45:06<28:45:32,  7.12s/it]
 48%|████▊     | 13538/28080 [26:45:13<28:42:08,  7.11s/it]
                                                           
{'loss': 0.631, 'learning_rate': 0.00027657944605377735, 'epoch': 5.78}

 48%|████▊     | 13538/28080 [26:45:13<28:42:08,  7.11s/it]
 48%|████▊     | 13539/28080 [26:45:20<28:50:09,  7.14s/it]
                                                           
{'loss': 0.618, 'learning_rate': 0.0002765507736045532, 'epoch': 5.78}

 48%|████▊     | 13539/28080 [26:45:20<28:50:09,  7.14s/it]
 48%|████▊     | 13540/28080 [26:45:27<28:44:30,  7.12s/it]
                                                           
{'loss': 0.6091, 'learning_rate': 0.0002765221008020984, 'epoch': 5.78}

 48%|████▊     | 13540/28080 [26:45:27<28:44:30,  7.12s/it]
 48%|████▊     | 13541/28080 [26:45:34<28:43:22,  7.11s/it]
                                                           
{'loss': 0.6069, 'learning_rate': 0.00027649342764679433, 'epoch': 5.78}

 48%|████▊     | 13541/28080 [26:45:34<28:43:22,  7.11s/it]
 48%|████▊     | 13542/28080 [26:45:41<28:37:36,  7.09s/it]
                                                           
{'loss': 0.6268, 'learning_rate': 0.00027646475413902263, 'epoch': 5.79}

 48%|████▊     | 13542/28080 [26:45:41<28:37:36,  7.09s/it]
 48%|████▊     | 13543/28080 [26:45:48<28:35:00,  7.08s/it]
                                                           
{'loss': 0.6267, 'learning_rate': 0.00027643608027916463, 'epoch': 5.79}

 48%|████▊     | 13543/28080 [26:45:48<28:35:00,  7.08s/it]
 48%|████▊     | 13544/28080 [26:45:56<28:44:52,  7.12s/it]
                                                           
{'loss': 0.6288, 'learning_rate': 0.0002764074060676019, 'epoch': 5.79}

 48%|████▊     | 13544/28080 [26:45:56<28:44:52,  7.12s/it]
 48%|████▊     | 13545/28080 [26:46:03<28:40:36,  7.10s/it]
                                                           
{'loss': 0.628, 'learning_rate': 0.0002763787315047158, 'epoch': 5.79}

 48%|████▊     | 13545/28080 [26:46:03<28:40:36,  7.10s/it]
 48%|████▊     | 13546/28080 [26:46:10<28:42:44,  7.11s/it]
                                                           
{'loss': 0.6174, 'learning_rate': 0.000276350056590888, 'epoch': 5.79}

 48%|████▊     | 13546/28080 [26:46:10<28:42:44,  7.11s/it]
 48%|████▊     | 13547/28080 [26:46:17<28:45:56,  7.13s/it]
                                                           
{'loss': 0.6271, 'learning_rate': 0.0002763213813264998, 'epoch': 5.79}

 48%|████▊     | 13547/28080 [26:46:17<28:45:56,  7.13s/it]
 48%|████▊     | 13548/28080 [26:46:24<28:35:41,  7.08s/it]
                                                           
{'loss': 0.6203, 'learning_rate': 0.00027629270571193277, 'epoch': 5.79}

 48%|████▊     | 13548/28080 [26:46:24<28:35:41,  7.08s/it]
 48%|████▊     | 13549/28080 [26:46:31<28:40:06,  7.10s/it]
                                                           
{'loss': 0.5906, 'learning_rate': 0.0002762640297475684, 'epoch': 5.79}

 48%|████▊     | 13549/28080 [26:46:31<28:40:06,  7.10s/it]
 48%|████▊     | 13550/28080 [26:46:38<28:32:23,  7.07s/it]
                                                           
{'loss': 0.6214, 'learning_rate': 0.00027623535343378826, 'epoch': 5.79}

 48%|████▊     | 13550/28080 [26:46:38<28:32:23,  7.07s/it]
 48%|████▊     | 13551/28080 [26:46:45<28:36:40,  7.09s/it]
                                                           
{'loss': 0.6478, 'learning_rate': 0.0002762066767709738, 'epoch': 5.79}

 48%|████▊     | 13551/28080 [26:46:45<28:36:40,  7.09s/it]
 48%|████▊     | 13552/28080 [26:46:52<28:39:04,  7.10s/it]
                                                           
{'loss': 0.6253, 'learning_rate': 0.0002761779997595065, 'epoch': 5.79}

 48%|████▊     | 13552/28080 [26:46:52<28:39:04,  7.10s/it]
 48%|████▊     | 13553/28080 [26:46:59<28:34:08,  7.08s/it]
                                                           
{'loss': 0.6307, 'learning_rate': 0.000276149322399768, 'epoch': 5.79}

 48%|████▊     | 13553/28080 [26:46:59<28:34:08,  7.08s/it]
 48%|████▊     | 13554/28080 [26:47:06<28:36:05,  7.09s/it]
                                                           
{'loss': 0.6362, 'learning_rate': 0.0002761206446921397, 'epoch': 5.79}

 48%|████▊     | 13554/28080 [26:47:06<28:36:05,  7.09s/it]
 48%|████▊     | 13555/28080 [26:47:14<28:46:58,  7.13s/it]
                                                           
{'loss': 0.6382, 'learning_rate': 0.00027609196663700314, 'epoch': 5.79}

 48%|████▊     | 13555/28080 [26:47:14<28:46:58,  7.13s/it]
 48%|████▊     | 13556/28080 [26:47:21<28:43:51,  7.12s/it]
                                                           
{'loss': 0.6137, 'learning_rate': 0.00027606328823473995, 'epoch': 5.79}

 48%|████▊     | 13556/28080 [26:47:21<28:43:51,  7.12s/it]
 48%|████▊     | 13557/28080 [26:47:28<28:43:14,  7.12s/it]
                                                           
{'loss': 0.6182, 'learning_rate': 0.00027603460948573156, 'epoch': 5.79}

 48%|████▊     | 13557/28080 [26:47:28<28:43:14,  7.12s/it]
 48%|████▊     | 13558/28080 [26:47:35<28:45:42,  7.13s/it]
                                                           
{'loss': 0.6102, 'learning_rate': 0.00027600593039035955, 'epoch': 5.79}

 48%|████▊     | 13558/28080 [26:47:35<28:45:42,  7.13s/it]
 48%|████▊     | 13559/28080 [26:47:42<28:50:23,  7.15s/it]
                                                           
{'loss': 0.6096, 'learning_rate': 0.00027597725094900545, 'epoch': 5.79}

 48%|████▊     | 13559/28080 [26:47:42<28:50:23,  7.15s/it]
 48%|████▊     | 13560/28080 [26:47:49<28:37:34,  7.10s/it]
                                                           
{'loss': 0.6116, 'learning_rate': 0.00027594857116205085, 'epoch': 5.79}

 48%|████▊     | 13560/28080 [26:47:49<28:37:34,  7.10s/it]
 48%|████▊     | 13561/28080 [26:47:56<28:43:05,  7.12s/it]
                                                           
{'loss': 0.598, 'learning_rate': 0.0002759198910298772, 'epoch': 5.79}

 48%|████▊     | 13561/28080 [26:47:56<28:43:05,  7.12s/it]
 48%|████▊     | 13562/28080 [26:48:04<28:42:27,  7.12s/it]
                                                           
{'loss': 0.6174, 'learning_rate': 0.00027589121055286627, 'epoch': 5.79}

 48%|████▊     | 13562/28080 [26:48:04<28:42:27,  7.12s/it]
 48%|████▊     | 13563/28080 [26:48:11<28:39:36,  7.11s/it]
                                                           
{'loss': 0.5957, 'learning_rate': 0.00027586252973139946, 'epoch': 5.79}

 48%|████▊     | 13563/28080 [26:48:11<28:39:36,  7.11s/it]
 48%|████▊     | 13564/28080 [26:48:18<28:47:50,  7.14s/it]
                                                           
{'loss': 0.6087, 'learning_rate': 0.0002758338485658584, 'epoch': 5.79}

 48%|████▊     | 13564/28080 [26:48:18<28:47:50,  7.14s/it]
 48%|████▊     | 13565/28080 [26:48:25<28:47:12,  7.14s/it]
                                                           
{'loss': 0.6211, 'learning_rate': 0.0002758051670566245, 'epoch': 5.79}

 48%|████▊     | 13565/28080 [26:48:25<28:47:12,  7.14s/it]
 48%|████▊     | 13566/28080 [26:48:32<28:43:04,  7.12s/it]
                                                           
{'loss': 0.6237, 'learning_rate': 0.0002757764852040796, 'epoch': 5.8}

 48%|████▊     | 13566/28080 [26:48:32<28:43:04,  7.12s/it]
 48%|████▊     | 13567/28080 [26:48:39<28:44:14,  7.13s/it]
                                                           
{'loss': 0.607, 'learning_rate': 0.0002757478030086051, 'epoch': 5.8}

 48%|████▊     | 13567/28080 [26:48:39<28:44:14,  7.13s/it]
 48%|████▊     | 13568/28080 [26:48:46<28:47:01,  7.14s/it]
                                                           
{'loss': 0.6153, 'learning_rate': 0.0002757191204705827, 'epoch': 5.8}

 48%|████▊     | 13568/28080 [26:48:46<28:47:01,  7.14s/it]
 48%|████▊     | 13569/28080 [26:48:54<28:51:18,  7.16s/it]
                                                           
{'loss': 0.6174, 'learning_rate': 0.0002756904375903938, 'epoch': 5.8}

 48%|████▊     | 13569/28080 [26:48:54<28:51:18,  7.16s/it]
 48%|████▊     | 13570/28080 [26:49:01<28:44:17,  7.13s/it]
                                                           
{'loss': 0.6128, 'learning_rate': 0.0002756617543684203, 'epoch': 5.8}

 48%|████▊     | 13570/28080 [26:49:01<28:44:17,  7.13s/it]
 48%|████▊     | 13571/28080 [26:49:08<28:42:12,  7.12s/it]
                                                           
{'loss': 0.61, 'learning_rate': 0.00027563307080504353, 'epoch': 5.8}

 48%|████▊     | 13571/28080 [26:49:08<28:42:12,  7.12s/it]
 48%|████▊     | 13572/28080 [26:49:15<28:41:37,  7.12s/it]
                                                           
{'loss': 0.6191, 'learning_rate': 0.00027560438690064513, 'epoch': 5.8}

 48%|████▊     | 13572/28080 [26:49:15<28:41:37,  7.12s/it]
 48%|████▊     | 13573/28080 [26:49:22<28:43:38,  7.13s/it]
                                                           
{'loss': 0.6337, 'learning_rate': 0.00027557570265560695, 'epoch': 5.8}

 48%|████▊     | 13573/28080 [26:49:22<28:43:38,  7.13s/it]
 48%|████▊     | 13574/28080 [26:49:29<28:38:37,  7.11s/it]
                                                           
{'loss': 0.6207, 'learning_rate': 0.0002755470180703103, 'epoch': 5.8}

 48%|████▊     | 13574/28080 [26:49:29<28:38:37,  7.11s/it]
 48%|████▊     | 13575/28080 [26:49:36<28:38:51,  7.11s/it]
                                                           
{'loss': 0.6095, 'learning_rate': 0.000275518333145137, 'epoch': 5.8}

 48%|████▊     | 13575/28080 [26:49:36<28:38:51,  7.11s/it]
 48%|████▊     | 13576/28080 [26:49:43<28:39:49,  7.11s/it]
                                                           
{'loss': 0.6255, 'learning_rate': 0.0002754896478804686, 'epoch': 5.8}

 48%|████▊     | 13576/28080 [26:49:43<28:39:49,  7.11s/it]
 48%|████▊     | 13577/28080 [26:49:50<28:38:36,  7.11s/it]
                                                           
{'loss': 0.6384, 'learning_rate': 0.0002754609622766867, 'epoch': 5.8}

 48%|████▊     | 13577/28080 [26:49:50<28:38:36,  7.11s/it]
 48%|████▊     | 13578/28080 [26:49:58<28:49:30,  7.16s/it]
                                                           
{'loss': 0.6075, 'learning_rate': 0.000275432276334173, 'epoch': 5.8}

 48%|████▊     | 13578/28080 [26:49:58<28:49:30,  7.16s/it]
 48%|████▊     | 13579/28080 [26:50:05<28:45:37,  7.14s/it]
                                                           
{'loss': 0.6166, 'learning_rate': 0.000275403590053309, 'epoch': 5.8}

 48%|████▊     | 13579/28080 [26:50:05<28:45:37,  7.14s/it]
 48%|████▊     | 13580/28080 [26:50:12<28:44:41,  7.14s/it]
                                                           
{'loss': 0.6254, 'learning_rate': 0.0002753749034344766, 'epoch': 5.8}

 48%|████▊     | 13580/28080 [26:50:12<28:44:41,  7.14s/it]
 48%|████▊     | 13581/28080 [26:50:19<28:46:42,  7.15s/it]
                                                           
{'loss': 0.6386, 'learning_rate': 0.00027534621647805715, 'epoch': 5.8}

 48%|████▊     | 13581/28080 [26:50:19<28:46:42,  7.15s/it]
 48%|████▊     | 13582/28080 [26:50:26<28:50:03,  7.16s/it]
                                                           
{'loss': 0.6102, 'learning_rate': 0.0002753175291844325, 'epoch': 5.8}

 48%|████▊     | 13582/28080 [26:50:26<28:50:03,  7.16s/it]
 48%|████▊     | 13583/28080 [26:50:33<28:47:41,  7.15s/it]
                                                           
{'loss': 0.6219, 'learning_rate': 0.00027528884155398427, 'epoch': 5.8}

 48%|████▊     | 13583/28080 [26:50:33<28:47:41,  7.15s/it]
 48%|████▊     | 13584/28080 [26:50:40<28:40:51,  7.12s/it]
                                                           
{'loss': 0.6346, 'learning_rate': 0.00027526015358709404, 'epoch': 5.8}

 48%|████▊     | 13584/28080 [26:50:40<28:40:51,  7.12s/it]
 48%|████▊     | 13585/28080 [26:50:48<28:43:14,  7.13s/it]
                                                           
{'loss': 0.6106, 'learning_rate': 0.00027523146528414354, 'epoch': 5.8}

 48%|████▊     | 13585/28080 [26:50:48<28:43:14,  7.13s/it]
 48%|████▊     | 13586/28080 [26:50:55<28:45:21,  7.14s/it]
                                                           
{'loss': 0.6268, 'learning_rate': 0.0002752027766455144, 'epoch': 5.8}

 48%|████▊     | 13586/28080 [26:50:55<28:45:21,  7.14s/it]
 48%|████▊     | 13587/28080 [26:51:02<28:38:06,  7.11s/it]
                                                           
{'loss': 0.6086, 'learning_rate': 0.0002751740876715884, 'epoch': 5.8}

 48%|████▊     | 13587/28080 [26:51:02<28:38:06,  7.11s/it]
 48%|████▊     | 13588/28080 [26:51:09<28:46:24,  7.15s/it]
                                                           
{'loss': 0.6143, 'learning_rate': 0.0002751453983627471, 'epoch': 5.8}

 48%|████▊     | 13588/28080 [26:51:09<28:46:24,  7.15s/it]
 48%|████▊     | 13589/28080 [26:51:16<28:42:17,  7.13s/it]
                                                           
{'loss': 0.6318, 'learning_rate': 0.00027511670871937214, 'epoch': 5.81}

 48%|████▊     | 13589/28080 [26:51:16<28:42:17,  7.13s/it]
 48%|████▊     | 13590/28080 [26:51:23<28:43:10,  7.14s/it]
                                                           
{'loss': 0.5994, 'learning_rate': 0.0002750880187418454, 'epoch': 5.81}

 48%|████▊     | 13590/28080 [26:51:23<28:43:10,  7.14s/it]
 48%|████▊     | 13591/28080 [26:51:30<28:46:03,  7.15s/it]
                                                           
{'loss': 0.6238, 'learning_rate': 0.00027505932843054835, 'epoch': 5.81}

 48%|████▊     | 13591/28080 [26:51:30<28:46:03,  7.15s/it]
 48%|████▊     | 13592/28080 [26:51:38<28:39:22,  7.12s/it]
                                                           
{'loss': 0.6056, 'learning_rate': 0.0002750306377858629, 'epoch': 5.81}

 48%|████▊     | 13592/28080 [26:51:38<28:39:22,  7.12s/it]
 48%|████▊     | 13593/28080 [26:51:45<28:34:52,  7.10s/it]
                                                           
{'loss': 0.6066, 'learning_rate': 0.0002750019468081705, 'epoch': 5.81}

 48%|████▊     | 13593/28080 [26:51:45<28:34:52,  7.10s/it]
 48%|████▊     | 13594/28080 [26:51:52<28:34:41,  7.10s/it]
                                                           
{'loss': 0.6321, 'learning_rate': 0.00027497325549785315, 'epoch': 5.81}

 48%|████▊     | 13594/28080 [26:51:52<28:34:41,  7.10s/it]
 48%|████▊     | 13595/28080 [26:51:59<28:47:26,  7.16s/it]
                                                           
{'loss': 0.6085, 'learning_rate': 0.0002749445638552922, 'epoch': 5.81}

 48%|████▊     | 13595/28080 [26:51:59<28:47:26,  7.16s/it]
 48%|████▊     | 13596/28080 [26:52:06<28:45:13,  7.15s/it]
                                                           
{'loss': 0.5904, 'learning_rate': 0.00027491587188086967, 'epoch': 5.81}

 48%|████▊     | 13596/28080 [26:52:06<28:45:13,  7.15s/it]
 48%|████▊     | 13597/28080 [26:52:13<28:45:19,  7.15s/it]
                                                           
{'loss': 0.6176, 'learning_rate': 0.00027488717957496723, 'epoch': 5.81}

 48%|████▊     | 13597/28080 [26:52:13<28:45:19,  7.15s/it]
 48%|████▊     | 13598/28080 [26:52:20<28:44:18,  7.14s/it]
                                                           
{'loss': 0.6335, 'learning_rate': 0.00027485848693796646, 'epoch': 5.81}

 48%|████▊     | 13598/28080 [26:52:20<28:44:18,  7.14s/it]
 48%|████▊     | 13599/28080 [26:52:27<28:37:38,  7.12s/it]
                                                           
{'loss': 0.6326, 'learning_rate': 0.0002748297939702492, 'epoch': 5.81}

 48%|████▊     | 13599/28080 [26:52:27<28:37:38,  7.12s/it]
 48%|████▊     | 13600/28080 [26:52:35<28:35:29,  7.11s/it]
                                                           
{'loss': 0.6253, 'learning_rate': 0.0002748011006721971, 'epoch': 5.81}

 48%|████▊     | 13600/28080 [26:52:35<28:35:29,  7.11s/it]
 48%|████▊     | 13601/28080 [26:52:42<28:38:58,  7.12s/it]
                                                           
{'loss': 0.6205, 'learning_rate': 0.000274772407044192, 'epoch': 5.81}

 48%|████▊     | 13601/28080 [26:52:42<28:38:58,  7.12s/it]
 48%|████▊     | 13602/28080 [26:52:49<28:44:01,  7.14s/it]
                                                           
{'loss': 0.6294, 'learning_rate': 0.0002747437130866155, 'epoch': 5.81}

 48%|████▊     | 13602/28080 [26:52:49<28:44:01,  7.14s/it]
 48%|████▊     | 13603/28080 [26:52:56<28:38:46,  7.12s/it]
                                                           
{'loss': 0.6303, 'learning_rate': 0.00027471501879984946, 'epoch': 5.81}

 48%|████▊     | 13603/28080 [26:52:56<28:38:46,  7.12s/it]
 48%|████▊     | 13604/28080 [26:53:03<28:43:58,  7.15s/it]
                                                           
{'loss': 0.624, 'learning_rate': 0.0002746863241842756, 'epoch': 5.81}

 48%|████▊     | 13604/28080 [26:53:03<28:43:58,  7.15s/it]
 48%|████▊     | 13605/28080 [26:53:10<28:42:36,  7.14s/it]
                                                           
{'loss': 0.6086, 'learning_rate': 0.0002746576292402757, 'epoch': 5.81}

 48%|████▊     | 13605/28080 [26:53:10<28:42:36,  7.14s/it]
 48%|████▊     | 13606/28080 [26:53:17<28:31:00,  7.09s/it]
                                                           
{'loss': 0.6196, 'learning_rate': 0.0002746289339682315, 'epoch': 5.81}

 48%|████▊     | 13606/28080 [26:53:17<28:31:00,  7.09s/it]
 48%|████▊     | 13607/28080 [26:53:24<28:24:34,  7.07s/it]
                                                           
{'loss': 0.6239, 'learning_rate': 0.00027460023836852463, 'epoch': 5.81}

 48%|████▊     | 13607/28080 [26:53:24<28:24:34,  7.07s/it]
 48%|████▊     | 13608/28080 [26:53:31<28:26:09,  7.07s/it]
                                                           
{'loss': 0.611, 'learning_rate': 0.0002745715424415371, 'epoch': 5.81}

 48%|████▊     | 13608/28080 [26:53:31<28:26:09,  7.07s/it]
 48%|████▊     | 13609/28080 [26:53:39<28:33:46,  7.11s/it]
                                                           
{'loss': 0.6336, 'learning_rate': 0.0002745428461876504, 'epoch': 5.81}

 48%|████▊     | 13609/28080 [26:53:39<28:33:46,  7.11s/it]
 48%|████▊     | 13610/28080 [26:53:46<28:35:36,  7.11s/it]
                                                           
{'loss': 0.6264, 'learning_rate': 0.0002745141496072465, 'epoch': 5.81}

 48%|████▊     | 13610/28080 [26:53:46<28:35:36,  7.11s/it]
 48%|████▊     | 13611/28080 [26:53:53<28:24:01,  7.07s/it]
                                                           
{'loss': 0.6354, 'learning_rate': 0.00027448545270070726, 'epoch': 5.81}

 48%|████▊     | 13611/28080 [26:53:53<28:24:01,  7.07s/it]
 48%|████▊     | 13612/28080 [26:54:00<28:16:29,  7.04s/it]
                                                           
{'loss': 0.6048, 'learning_rate': 0.00027445675546841413, 'epoch': 5.81}

 48%|████▊     | 13612/28080 [26:54:00<28:16:29,  7.04s/it]
 48%|████▊     | 13613/28080 [26:54:07<28:26:28,  7.08s/it]
                                                           
{'loss': 0.6232, 'learning_rate': 0.00027442805791074934, 'epoch': 5.82}

 48%|████▊     | 13613/28080 [26:54:07<28:26:28,  7.08s/it]
 48%|████▊     | 13614/28080 [26:54:14<28:24:36,  7.07s/it]
                                                           
{'loss': 0.6242, 'learning_rate': 0.00027439936002809424, 'epoch': 5.82}

 48%|████▊     | 13614/28080 [26:54:14<28:24:36,  7.07s/it]
 48%|████▊     | 13615/28080 [26:54:21<28:23:25,  7.07s/it]
                                                           
{'loss': 0.6196, 'learning_rate': 0.00027437066182083085, 'epoch': 5.82}

 48%|████▊     | 13615/28080 [26:54:21<28:23:25,  7.07s/it]
 48%|████▊     | 13616/28080 [26:54:28<28:29:33,  7.09s/it]
                                                           
{'loss': 0.6099, 'learning_rate': 0.00027434196328934103, 'epoch': 5.82}

 48%|████▊     | 13616/28080 [26:54:28<28:29:33,  7.09s/it]
 48%|████▊     | 13617/28080 [26:54:35<28:27:29,  7.08s/it]
                                                           
{'loss': 0.63, 'learning_rate': 0.00027431326443400647, 'epoch': 5.82}

 48%|████▊     | 13617/28080 [26:54:35<28:27:29,  7.08s/it]
 48%|████▊     | 13618/28080 [26:54:42<28:24:38,  7.07s/it]
                                                           
{'loss': 0.6311, 'learning_rate': 0.00027428456525520903, 'epoch': 5.82}

 48%|████▊     | 13618/28080 [26:54:42<28:24:38,  7.07s/it]
 49%|████▊     | 13619/28080 [26:54:49<28:22:34,  7.06s/it]
                                                           
{'loss': 0.6172, 'learning_rate': 0.0002742558657533304, 'epoch': 5.82}

 49%|████▊     | 13619/28080 [26:54:49<28:22:34,  7.06s/it]
 49%|████▊     | 13620/28080 [26:54:56<28:30:46,  7.10s/it]
                                                           
{'loss': 0.5933, 'learning_rate': 0.0002742271659287525, 'epoch': 5.82}

 49%|████▊     | 13620/28080 [26:54:56<28:30:46,  7.10s/it]
 49%|████▊     | 13621/28080 [26:55:03<28:28:15,  7.09s/it]
                                                           
{'loss': 0.6299, 'learning_rate': 0.00027419846578185733, 'epoch': 5.82}

 49%|████▊     | 13621/28080 [26:55:03<28:28:15,  7.09s/it]
 49%|████▊     | 13622/28080 [26:55:11<28:37:34,  7.13s/it]
                                                           
{'loss': 0.6027, 'learning_rate': 0.00027416976531302633, 'epoch': 5.82}

 49%|████▊     | 13622/28080 [26:55:11<28:37:34,  7.13s/it]
 49%|████▊     | 13623/28080 [26:55:18<28:31:54,  7.10s/it]
                                                           
{'loss': 0.6247, 'learning_rate': 0.0002741410645226417, 'epoch': 5.82}

 49%|████▊     | 13623/28080 [26:55:18<28:31:54,  7.10s/it]
 49%|████▊     | 13624/28080 [26:55:25<28:35:48,  7.12s/it]
                                                           
{'loss': 0.6235, 'learning_rate': 0.00027411236341108505, 'epoch': 5.82}

 49%|████▊     | 13624/28080 [26:55:25<28:35:48,  7.12s/it]
 49%|████▊     | 13625/28080 [26:55:32<28:46:23,  7.17s/it]
                                                           
{'loss': 0.6347, 'learning_rate': 0.00027408366197873826, 'epoch': 5.82}

 49%|████▊     | 13625/28080 [26:55:32<28:46:23,  7.17s/it]
 49%|████▊     | 13626/28080 [26:55:39<28:47:23,  7.17s/it]
                                                           
{'loss': 0.6461, 'learning_rate': 0.0002740549602259832, 'epoch': 5.82}

 49%|████▊     | 13626/28080 [26:55:39<28:47:23,  7.17s/it]
 49%|████▊     | 13627/28080 [26:55:46<28:40:47,  7.14s/it]
                                                           
{'loss': 0.6275, 'learning_rate': 0.00027402625815320164, 'epoch': 5.82}

 49%|████▊     | 13627/28080 [26:55:46<28:40:47,  7.14s/it]
 49%|████▊     | 13628/28080 [26:55:54<28:40:49,  7.14s/it]
                                                           
{'loss': 0.6304, 'learning_rate': 0.0002739975557607756, 'epoch': 5.82}

 49%|████▊     | 13628/28080 [26:55:54<28:40:49,  7.14s/it]
 49%|████▊     | 13629/28080 [26:56:01<28:43:30,  7.16s/it]
                                                           
{'loss': 0.6218, 'learning_rate': 0.0002739688530490868, 'epoch': 5.82}

 49%|████▊     | 13629/28080 [26:56:01<28:43:30,  7.16s/it]
 49%|████▊     | 13630/28080 [26:56:08<28:37:29,  7.13s/it]
                                                           
{'loss': 0.6366, 'learning_rate': 0.00027394015001851716, 'epoch': 5.82}

 49%|████▊     | 13630/28080 [26:56:08<28:37:29,  7.13s/it]
 49%|████▊     | 13631/28080 [26:56:15<28:36:12,  7.13s/it]
                                                           
{'loss': 0.6207, 'learning_rate': 0.0002739114466694485, 'epoch': 5.82}

 49%|████▊     | 13631/28080 [26:56:15<28:36:12,  7.13s/it]
 49%|████▊     | 13632/28080 [26:56:22<28:27:49,  7.09s/it]
                                                           
{'loss': 0.6167, 'learning_rate': 0.0002738827430022628, 'epoch': 5.82}

 49%|████▊     | 13632/28080 [26:56:22<28:27:49,  7.09s/it]
 49%|████▊     | 13633/28080 [26:56:29<28:26:28,  7.09s/it]
                                                           
{'loss': 0.6196, 'learning_rate': 0.00027385403901734174, 'epoch': 5.82}

 49%|████▊     | 13633/28080 [26:56:29<28:26:28,  7.09s/it]
 49%|████▊     | 13634/28080 [26:56:36<28:29:29,  7.10s/it]
                                                           
{'loss': 0.618, 'learning_rate': 0.00027382533471506724, 'epoch': 5.82}

 49%|████▊     | 13634/28080 [26:56:36<28:29:29,  7.10s/it]
 49%|████▊     | 13635/28080 [26:56:43<28:29:10,  7.10s/it]
                                                           
{'loss': 0.6164, 'learning_rate': 0.0002737966300958214, 'epoch': 5.82}

 49%|████▊     | 13635/28080 [26:56:43<28:29:10,  7.10s/it]
 49%|████▊     | 13636/28080 [26:56:50<28:35:04,  7.12s/it]
                                                           
{'loss': 0.6241, 'learning_rate': 0.00027376792515998585, 'epoch': 5.83}

 49%|████▊     | 13636/28080 [26:56:50<28:35:04,  7.12s/it]
 49%|████▊     | 13637/28080 [26:56:58<28:37:20,  7.13s/it]
                                                           
{'loss': 0.5939, 'learning_rate': 0.00027373921990794266, 'epoch': 5.83}

 49%|████▊     | 13637/28080 [26:56:58<28:37:20,  7.13s/it]
 49%|████▊     | 13638/28080 [26:57:05<28:36:49,  7.13s/it]
                                                           
{'loss': 0.6072, 'learning_rate': 0.0002737105143400736, 'epoch': 5.83}

 49%|████▊     | 13638/28080 [26:57:05<28:36:49,  7.13s/it]
 49%|████▊     | 13639/28080 [26:57:12<28:39:41,  7.15s/it]
                                                           
{'loss': 0.6039, 'learning_rate': 0.00027368180845676053, 'epoch': 5.83}

 49%|████▊     | 13639/28080 [26:57:12<28:39:41,  7.15s/it]
 49%|████▊     | 13640/28080 [26:57:19<28:41:23,  7.15s/it]
                                                           
{'loss': 0.621, 'learning_rate': 0.0002736531022583855, 'epoch': 5.83}

 49%|████▊     | 13640/28080 [26:57:19<28:41:23,  7.15s/it]
 49%|████▊     | 13641/28080 [26:57:26<28:41:58,  7.16s/it]
                                                           
{'loss': 0.6213, 'learning_rate': 0.0002736243957453303, 'epoch': 5.83}

 49%|████▊     | 13641/28080 [26:57:26<28:41:58,  7.16s/it]
 49%|████▊     | 13642/28080 [26:57:33<28:36:27,  7.13s/it]
                                                           
{'loss': 0.6167, 'learning_rate': 0.000273595688917977, 'epoch': 5.83}

 49%|████▊     | 13642/28080 [26:57:33<28:36:27,  7.13s/it]
 49%|████▊     | 13643/28080 [26:57:40<28:38:13,  7.14s/it]
                                                           
{'loss': 0.6244, 'learning_rate': 0.00027356698177670723, 'epoch': 5.83}

 49%|████▊     | 13643/28080 [26:57:40<28:38:13,  7.14s/it]
 49%|████▊     | 13644/28080 [26:57:48<28:33:41,  7.12s/it]
                                                           
{'loss': 0.637, 'learning_rate': 0.0002735382743219033, 'epoch': 5.83}

 49%|████▊     | 13644/28080 [26:57:48<28:33:41,  7.12s/it]
 49%|████▊     | 13645/28080 [26:57:55<28:37:59,  7.14s/it]
                                                           
{'loss': 0.6536, 'learning_rate': 0.00027350956655394673, 'epoch': 5.83}

 49%|████▊     | 13645/28080 [26:57:55<28:37:59,  7.14s/it]
 49%|████▊     | 13646/28080 [26:58:02<28:35:14,  7.13s/it]
                                                           
{'loss': 0.6178, 'learning_rate': 0.00027348085847321964, 'epoch': 5.83}

 49%|████▊     | 13646/28080 [26:58:02<28:35:14,  7.13s/it]
 49%|████▊     | 13647/28080 [26:58:09<28:36:02,  7.13s/it]
                                                           
{'loss': 0.6124, 'learning_rate': 0.000273452150080104, 'epoch': 5.83}

 49%|████▊     | 13647/28080 [26:58:09<28:36:02,  7.13s/it]
 49%|████▊     | 13648/28080 [26:58:16<28:33:29,  7.12s/it]
                                                           
{'loss': 0.6194, 'learning_rate': 0.0002734234413749817, 'epoch': 5.83}

 49%|████▊     | 13648/28080 [26:58:16<28:33:29,  7.12s/it]
 49%|████▊     | 13649/28080 [26:58:23<28:34:59,  7.13s/it]
                                                           
{'loss': 0.611, 'learning_rate': 0.0002733947323582347, 'epoch': 5.83}

 49%|████▊     | 13649/28080 [26:58:23<28:34:59,  7.13s/it]
 49%|████▊     | 13650/28080 [26:58:30<28:28:43,  7.10s/it]
                                                           
{'loss': 0.6155, 'learning_rate': 0.00027336602303024485, 'epoch': 5.83}

 49%|████▊     | 13650/28080 [26:58:30<28:28:43,  7.10s/it]
 49%|████▊     | 13651/28080 [26:58:37<28:33:36,  7.13s/it]
                                                           
{'loss': 0.6347, 'learning_rate': 0.0002733373133913942, 'epoch': 5.83}

 49%|████▊     | 13651/28080 [26:58:37<28:33:36,  7.13s/it]
 49%|████▊     | 13652/28080 [26:58:45<28:31:30,  7.12s/it]
                                                           
{'loss': 0.6116, 'learning_rate': 0.0002733086034420647, 'epoch': 5.83}

 49%|████▊     | 13652/28080 [26:58:45<28:31:30,  7.12s/it]
 49%|████▊     | 13653/28080 [26:58:52<28:25:18,  7.09s/it]
                                                           
{'loss': 0.6159, 'learning_rate': 0.0002732798931826382, 'epoch': 5.83}

 49%|████▊     | 13653/28080 [26:58:52<28:25:18,  7.09s/it]
 49%|████▊     | 13654/28080 [26:58:59<28:23:59,  7.09s/it]
                                                           
{'loss': 0.5976, 'learning_rate': 0.0002732511826134969, 'epoch': 5.83}

 49%|████▊     | 13654/28080 [26:58:59<28:23:59,  7.09s/it]
 49%|████▊     | 13655/28080 [26:59:06<28:27:32,  7.10s/it]
                                                           
{'loss': 0.6115, 'learning_rate': 0.0002732224717350224, 'epoch': 5.83}

 49%|████▊     | 13655/28080 [26:59:06<28:27:32,  7.10s/it]
 49%|████▊     | 13656/28080 [26:59:13<28:25:34,  7.09s/it]
                                                           
{'loss': 0.6135, 'learning_rate': 0.00027319376054759704, 'epoch': 5.83}

 49%|████▊     | 13656/28080 [26:59:13<28:25:34,  7.09s/it]
 49%|████▊     | 13657/28080 [26:59:20<28:27:18,  7.10s/it]
                                                           
{'loss': 0.6119, 'learning_rate': 0.0002731650490516025, 'epoch': 5.83}

 49%|████▊     | 13657/28080 [26:59:20<28:27:18,  7.10s/it]
 49%|████▊     | 13658/28080 [26:59:27<28:28:19,  7.11s/it]
                                                           
{'loss': 0.6133, 'learning_rate': 0.0002731363372474209, 'epoch': 5.83}

 49%|████▊     | 13658/28080 [26:59:27<28:28:19,  7.11s/it]
 49%|████▊     | 13659/28080 [26:59:34<28:26:05,  7.10s/it]
                                                           
{'loss': 0.6102, 'learning_rate': 0.0002731076251354343, 'epoch': 5.83}

 49%|████▊     | 13659/28080 [26:59:34<28:26:05,  7.10s/it]
 49%|████▊     | 13660/28080 [26:59:41<28:33:58,  7.13s/it]
                                                           
{'loss': 0.6196, 'learning_rate': 0.00027307891271602445, 'epoch': 5.84}

 49%|████▊     | 13660/28080 [26:59:41<28:33:58,  7.13s/it]
 49%|████▊     | 13661/28080 [26:59:48<28:31:01,  7.12s/it]
                                                           
{'loss': 0.6123, 'learning_rate': 0.00027305019998957356, 'epoch': 5.84}

 49%|████▊     | 13661/28080 [26:59:48<28:31:01,  7.12s/it]
 49%|████▊     | 13662/28080 [26:59:56<28:33:20,  7.13s/it]
                                                           
{'loss': 0.6179, 'learning_rate': 0.00027302148695646357, 'epoch': 5.84}

 49%|████▊     | 13662/28080 [26:59:56<28:33:20,  7.13s/it]
 49%|████▊     | 13663/28080 [27:00:03<28:29:34,  7.11s/it]
                                                           
{'loss': 0.6082, 'learning_rate': 0.00027299277361707644, 'epoch': 5.84}

 49%|████▊     | 13663/28080 [27:00:03<28:29:34,  7.11s/it]
 49%|████▊     | 13664/28080 [27:00:10<28:27:59,  7.11s/it]
                                                           
{'loss': 0.6236, 'learning_rate': 0.00027296405997179413, 'epoch': 5.84}

 49%|████▊     | 13664/28080 [27:00:10<28:27:59,  7.11s/it]
 49%|████▊     | 13665/28080 [27:00:17<28:27:03,  7.11s/it]
                                                           
{'loss': 0.639, 'learning_rate': 0.00027293534602099867, 'epoch': 5.84}

 49%|████▊     | 13665/28080 [27:00:17<28:27:03,  7.11s/it]
 49%|████▊     | 13666/28080 [27:00:24<28:34:51,  7.14s/it]
                                                           
{'loss': 0.6046, 'learning_rate': 0.0002729066317650722, 'epoch': 5.84}

 49%|████▊     | 13666/28080 [27:00:24<28:34:51,  7.14s/it]
 49%|████▊     | 13667/28080 [27:00:31<28:27:33,  7.11s/it]
                                                           
{'loss': 0.6226, 'learning_rate': 0.00027287791720439645, 'epoch': 5.84}

 49%|████▊     | 13667/28080 [27:00:31<28:27:33,  7.11s/it]
 49%|████▊     | 13668/28080 [27:00:38<28:22:19,  7.09s/it]
                                                           
{'loss': 0.6394, 'learning_rate': 0.0002728492023393538, 'epoch': 5.84}

 49%|████▊     | 13668/28080 [27:00:38<28:22:19,  7.09s/it]
 49%|████▊     | 13669/28080 [27:00:45<28:20:28,  7.08s/it]
                                                           
{'loss': 0.5981, 'learning_rate': 0.00027282048717032595, 'epoch': 5.84}

 49%|████▊     | 13669/28080 [27:00:45<28:20:28,  7.08s/it]
 49%|████▊     | 13670/28080 [27:00:52<28:16:20,  7.06s/it]
                                                           
{'loss': 0.6229, 'learning_rate': 0.0002727917716976951, 'epoch': 5.84}

 49%|████▊     | 13670/28080 [27:00:52<28:16:20,  7.06s/it]
 49%|████▊     | 13671/28080 [27:00:59<28:12:36,  7.05s/it]
                                                           
{'loss': 0.6322, 'learning_rate': 0.00027276305592184325, 'epoch': 5.84}

 49%|████▊     | 13671/28080 [27:00:59<28:12:36,  7.05s/it]
 49%|████▊     | 13672/28080 [27:01:06<28:21:37,  7.09s/it]
                                                           
{'loss': 0.6245, 'learning_rate': 0.00027273433984315243, 'epoch': 5.84}

 49%|████▊     | 13672/28080 [27:01:06<28:21:37,  7.09s/it]
 49%|████▊     | 13673/28080 [27:01:13<28:18:33,  7.07s/it]
                                                           
{'loss': 0.6264, 'learning_rate': 0.00027270562346200466, 'epoch': 5.84}

 49%|████▊     | 13673/28080 [27:01:13<28:18:33,  7.07s/it]
 49%|████▊     | 13674/28080 [27:01:21<28:24:04,  7.10s/it]
                                                           
{'loss': 0.6171, 'learning_rate': 0.00027267690677878196, 'epoch': 5.84}

 49%|████▊     | 13674/28080 [27:01:21<28:24:04,  7.10s/it]
 49%|████▊     | 13675/28080 [27:01:28<28:30:55,  7.13s/it]
                                                           
{'loss': 0.6221, 'learning_rate': 0.0002726481897938665, 'epoch': 5.84}

 49%|████▊     | 13675/28080 [27:01:28<28:30:55,  7.13s/it]
 49%|████▊     | 13676/28080 [27:01:35<28:21:05,  7.09s/it]
                                                           
{'loss': 0.6331, 'learning_rate': 0.0002726194725076402, 'epoch': 5.84}

 49%|████▊     | 13676/28080 [27:01:35<28:21:05,  7.09s/it]
 49%|████▊     | 13677/28080 [27:01:42<28:23:44,  7.10s/it]
                                                           
{'loss': 0.616, 'learning_rate': 0.0002725907549204851, 'epoch': 5.84}

 49%|████▊     | 13677/28080 [27:01:42<28:23:44,  7.10s/it]
 49%|████▊     | 13678/28080 [27:01:49<28:28:36,  7.12s/it]
                                                           
{'loss': 0.6269, 'learning_rate': 0.00027256203703278337, 'epoch': 5.84}

 49%|████▊     | 13678/28080 [27:01:49<28:28:36,  7.12s/it]
 49%|████▊     | 13679/28080 [27:01:56<28:33:20,  7.14s/it]
                                                           
{'loss': 0.6314, 'learning_rate': 0.000272533318844917, 'epoch': 5.84}

 49%|████▊     | 13679/28080 [27:01:56<28:33:20,  7.14s/it]
 49%|████▊     | 13680/28080 [27:02:04<28:38:41,  7.16s/it]
                                                           
{'loss': 0.6248, 'learning_rate': 0.0002725046003572681, 'epoch': 5.84}

 49%|████▊     | 13680/28080 [27:02:04<28:38:41,  7.16s/it]
 49%|████▊     | 13681/28080 [27:02:11<28:29:58,  7.13s/it]
                                                           
{'loss': 0.6291, 'learning_rate': 0.0002724758815702186, 'epoch': 5.84}

 49%|████▊     | 13681/28080 [27:02:11<28:29:58,  7.13s/it]
 49%|████▊     | 13682/28080 [27:02:18<28:29:40,  7.12s/it]
                                                           
{'loss': 0.6125, 'learning_rate': 0.00027244716248415074, 'epoch': 5.84}

 49%|████▊     | 13682/28080 [27:02:18<28:29:40,  7.12s/it]
 49%|████▊     | 13683/28080 [27:02:25<28:21:19,  7.09s/it]
                                                           
{'loss': 0.6275, 'learning_rate': 0.00027241844309944664, 'epoch': 5.85}

 49%|████▊     | 13683/28080 [27:02:25<28:21:19,  7.09s/it]
 49%|████▊     | 13684/28080 [27:02:32<28:27:33,  7.12s/it]
                                                           
{'loss': 0.6135, 'learning_rate': 0.00027238972341648817, 'epoch': 5.85}

 49%|████▊     | 13684/28080 [27:02:32<28:27:33,  7.12s/it]
 49%|████▊     | 13685/28080 [27:02:39<28:30:55,  7.13s/it]
                                                           
{'loss': 0.6162, 'learning_rate': 0.00027236100343565756, 'epoch': 5.85}

 49%|████▊     | 13685/28080 [27:02:39<28:30:55,  7.13s/it]
 49%|████▊     | 13686/28080 [27:02:46<28:35:36,  7.15s/it]
                                                           
{'loss': 0.6153, 'learning_rate': 0.00027233228315733685, 'epoch': 5.85}

 49%|████▊     | 13686/28080 [27:02:46<28:35:36,  7.15s/it]
 49%|████▊     | 13687/28080 [27:02:53<28:34:12,  7.15s/it]
                                                           
{'loss': 0.6286, 'learning_rate': 0.0002723035625819082, 'epoch': 5.85}

 49%|████▊     | 13687/28080 [27:02:53<28:34:12,  7.15s/it]
 49%|████▊     | 13688/28080 [27:03:00<28:25:47,  7.11s/it]
                                                           
{'loss': 0.6423, 'learning_rate': 0.00027227484170975363, 'epoch': 5.85}

 49%|████▊     | 13688/28080 [27:03:00<28:25:47,  7.11s/it]
 49%|████▉     | 13689/28080 [27:03:07<28:23:45,  7.10s/it]
                                                           
{'loss': 0.6393, 'learning_rate': 0.0002722461205412552, 'epoch': 5.85}

 49%|████▉     | 13689/28080 [27:03:07<28:23:45,  7.10s/it]
 49%|████▉     | 13690/28080 [27:03:14<28:17:05,  7.08s/it]
                                                           
{'loss': 0.6275, 'learning_rate': 0.00027221739907679526, 'epoch': 5.85}

 49%|████▉     | 13690/28080 [27:03:14<28:17:05,  7.08s/it]
 49%|████▉     | 13691/28080 [27:03:22<28:19:04,  7.08s/it]
                                                           
{'loss': 0.6114, 'learning_rate': 0.0002721886773167556, 'epoch': 5.85}

 49%|████▉     | 13691/28080 [27:03:22<28:19:04,  7.08s/it]
 49%|████▉     | 13692/28080 [27:03:29<28:27:56,  7.12s/it]
                                                           
{'loss': 0.5978, 'learning_rate': 0.00027215995526151855, 'epoch': 5.85}

 49%|████▉     | 13692/28080 [27:03:29<28:27:56,  7.12s/it]
 49%|████▉     | 13693/28080 [27:03:36<28:29:45,  7.13s/it]
                                                           
{'loss': 0.613, 'learning_rate': 0.0002721312329114661, 'epoch': 5.85}

 49%|████▉     | 13693/28080 [27:03:36<28:29:45,  7.13s/it]
 49%|████▉     | 13694/28080 [27:03:43<28:27:41,  7.12s/it]
                                                           
{'loss': 0.6345, 'learning_rate': 0.0002721025102669804, 'epoch': 5.85}

 49%|████▉     | 13694/28080 [27:03:43<28:27:41,  7.12s/it]
 49%|████▉     | 13695/28080 [27:03:50<28:30:45,  7.14s/it]
                                                           
{'loss': 0.6224, 'learning_rate': 0.0002720737873284437, 'epoch': 5.85}

 49%|████▉     | 13695/28080 [27:03:50<28:30:45,  7.14s/it]
 49%|████▉     | 13696/28080 [27:03:57<28:29:53,  7.13s/it]
                                                           
{'loss': 0.622, 'learning_rate': 0.000272045064096238, 'epoch': 5.85}

 49%|████▉     | 13696/28080 [27:03:57<28:29:53,  7.13s/it]
 49%|████▉     | 13697/28080 [27:04:04<28:30:28,  7.14s/it]
                                                           
{'loss': 0.5855, 'learning_rate': 0.00027201634057074547, 'epoch': 5.85}

 49%|████▉     | 13697/28080 [27:04:04<28:30:28,  7.14s/it]
 49%|████▉     | 13698/28080 [27:04:12<28:26:52,  7.12s/it]
                                                           
{'loss': 0.614, 'learning_rate': 0.00027198761675234815, 'epoch': 5.85}

 49%|████▉     | 13698/28080 [27:04:12<28:26:52,  7.12s/it]
 49%|████▉     | 13699/28080 [27:04:19<28:26:52,  7.12s/it]
                                                           
{'loss': 0.6091, 'learning_rate': 0.0002719588926414284, 'epoch': 5.85}

 49%|████▉     | 13699/28080 [27:04:19<28:26:52,  7.12s/it]
 49%|████▉     | 13700/28080 [27:04:26<28:23:16,  7.11s/it]
                                                           
{'loss': 0.622, 'learning_rate': 0.0002719301682383682, 'epoch': 5.85}

 49%|████▉     | 13700/28080 [27:04:26<28:23:16,  7.11s/it]
 49%|████▉     | 13701/28080 [27:04:33<28:23:31,  7.11s/it]
                                                           
{'loss': 0.6154, 'learning_rate': 0.00027190144354354966, 'epoch': 5.85}

 49%|████▉     | 13701/28080 [27:04:33<28:23:31,  7.11s/it]
 49%|████▉     | 13702/28080 [27:04:40<28:28:30,  7.13s/it]
                                                           
{'loss': 0.6221, 'learning_rate': 0.0002718727185573551, 'epoch': 5.85}

 49%|████▉     | 13702/28080 [27:04:40<28:28:30,  7.13s/it]
 49%|████▉     | 13703/28080 [27:04:47<28:27:47,  7.13s/it]
                                                           
{'loss': 0.6222, 'learning_rate': 0.0002718439932801665, 'epoch': 5.85}

 49%|████▉     | 13703/28080 [27:04:47<28:27:47,  7.13s/it]
 49%|████▉     | 13704/28080 [27:04:54<28:25:51,  7.12s/it]
                                                           
{'loss': 0.6012, 'learning_rate': 0.0002718152677123662, 'epoch': 5.85}

 49%|████▉     | 13704/28080 [27:04:54<28:25:51,  7.12s/it]
 49%|████▉     | 13705/28080 [27:05:01<28:31:46,  7.14s/it]
                                                           
{'loss': 0.5959, 'learning_rate': 0.00027178654185433624, 'epoch': 5.85}

 49%|████▉     | 13705/28080 [27:05:01<28:31:46,  7.14s/it]
 49%|████▉     | 13706/28080 [27:05:09<28:43:27,  7.19s/it]
                                                           
{'loss': 0.6141, 'learning_rate': 0.0002717578157064588, 'epoch': 5.86}

 49%|████▉     | 13706/28080 [27:05:09<28:43:27,  7.19s/it]
 49%|████▉     | 13707/28080 [27:05:16<28:38:36,  7.17s/it]
                                                           
{'loss': 0.6193, 'learning_rate': 0.00027172908926911604, 'epoch': 5.86}

 49%|████▉     | 13707/28080 [27:05:16<28:38:36,  7.17s/it]
 49%|████▉     | 13708/28080 [27:05:23<28:31:36,  7.15s/it]
                                                           
{'loss': 0.6276, 'learning_rate': 0.0002717003625426902, 'epoch': 5.86}

 49%|████▉     | 13708/28080 [27:05:23<28:31:36,  7.15s/it]
 49%|████▉     | 13709/28080 [27:05:30<28:33:40,  7.15s/it]
                                                           
{'loss': 0.6038, 'learning_rate': 0.00027167163552756343, 'epoch': 5.86}

 49%|████▉     | 13709/28080 [27:05:30<28:33:40,  7.15s/it]
 49%|████▉     | 13710/28080 [27:05:37<28:36:51,  7.17s/it]
                                                           
{'loss': 0.6294, 'learning_rate': 0.0002716429082241179, 'epoch': 5.86}

 49%|████▉     | 13710/28080 [27:05:37<28:36:51,  7.17s/it]
 49%|████▉     | 13711/28080 [27:05:44<28:27:08,  7.13s/it]
                                                           
{'loss': 0.6209, 'learning_rate': 0.0002716141806327358, 'epoch': 5.86}

 49%|████▉     | 13711/28080 [27:05:44<28:27:08,  7.13s/it]
 49%|████▉     | 13712/28080 [27:05:52<28:26:16,  7.13s/it]
                                                           
{'loss': 0.6171, 'learning_rate': 0.0002715854527537993, 'epoch': 5.86}

 49%|████▉     | 13712/28080 [27:05:52<28:26:16,  7.13s/it]
 49%|████▉     | 13713/28080 [27:05:59<28:24:52,  7.12s/it]
                                                           
{'loss': 0.615, 'learning_rate': 0.00027155672458769063, 'epoch': 5.86}

 49%|████▉     | 13713/28080 [27:05:59<28:24:52,  7.12s/it]
 49%|████▉     | 13714/28080 [27:06:06<28:24:43,  7.12s/it]
                                                           
{'loss': 0.6436, 'learning_rate': 0.0002715279961347921, 'epoch': 5.86}

 49%|████▉     | 13714/28080 [27:06:06<28:24:43,  7.12s/it]
 49%|████▉     | 13715/28080 [27:06:13<28:27:34,  7.13s/it]
                                                           
{'loss': 0.629, 'learning_rate': 0.00027149926739548566, 'epoch': 5.86}

 49%|████▉     | 13715/28080 [27:06:13<28:27:34,  7.13s/it]
 49%|████▉     | 13716/28080 [27:06:20<28:25:48,  7.13s/it]
                                                           
{'loss': 0.6109, 'learning_rate': 0.0002714705383701537, 'epoch': 5.86}

 49%|████▉     | 13716/28080 [27:06:20<28:25:48,  7.13s/it]
 49%|████▉     | 13717/28080 [27:06:27<28:24:11,  7.12s/it]
                                                           
{'loss': 0.6134, 'learning_rate': 0.00027144180905917825, 'epoch': 5.86}

 49%|████▉     | 13717/28080 [27:06:27<28:24:11,  7.12s/it]
 49%|████▉     | 13718/28080 [27:06:34<28:27:17,  7.13s/it]
                                                           
{'loss': 0.6309, 'learning_rate': 0.00027141307946294173, 'epoch': 5.86}

 49%|████▉     | 13718/28080 [27:06:34<28:27:17,  7.13s/it]
 49%|████▉     | 13719/28080 [27:06:41<28:19:25,  7.10s/it]
                                                           
{'loss': 0.6389, 'learning_rate': 0.0002713843495818263, 'epoch': 5.86}

 49%|████▉     | 13719/28080 [27:06:41<28:19:25,  7.10s/it]
 49%|████▉     | 13720/28080 [27:06:48<28:20:33,  7.11s/it]
                                                           
{'loss': 0.607, 'learning_rate': 0.00027135561941621415, 'epoch': 5.86}

 49%|████▉     | 13720/28080 [27:06:48<28:20:33,  7.11s/it]
 49%|████▉     | 13721/28080 [27:06:56<28:18:23,  7.10s/it]
                                                           
{'loss': 0.6354, 'learning_rate': 0.00027132688896648756, 'epoch': 5.86}

 49%|████▉     | 13721/28080 [27:06:56<28:18:23,  7.10s/it]
 49%|████▉     | 13722/28080 [27:07:03<28:24:01,  7.12s/it]
                                                           
{'loss': 0.6126, 'learning_rate': 0.0002712981582330287, 'epoch': 5.86}

 49%|████▉     | 13722/28080 [27:07:03<28:24:01,  7.12s/it]
 49%|████▉     | 13723/28080 [27:07:10<28:11:51,  7.07s/it]
                                                           
{'loss': 0.6531, 'learning_rate': 0.0002712694272162198, 'epoch': 5.86}

 49%|████▉     | 13723/28080 [27:07:10<28:11:51,  7.07s/it]
 49%|████▉     | 13724/28080 [27:07:17<28:10:04,  7.06s/it]
                                                           
{'loss': 0.6374, 'learning_rate': 0.0002712406959164431, 'epoch': 5.86}

 49%|████▉     | 13724/28080 [27:07:17<28:10:04,  7.06s/it]
 49%|████▉     | 13725/28080 [27:07:24<28:16:58,  7.09s/it]
                                                           
{'loss': 0.6201, 'learning_rate': 0.0002712119643340808, 'epoch': 5.86}

 49%|████▉     | 13725/28080 [27:07:24<28:16:58,  7.09s/it]
 49%|████▉     | 13726/28080 [27:07:31<28:16:24,  7.09s/it]
                                                           
{'loss': 0.622, 'learning_rate': 0.00027118323246951525, 'epoch': 5.86}

 49%|████▉     | 13726/28080 [27:07:31<28:16:24,  7.09s/it]
 49%|████▉     | 13727/28080 [27:07:38<28:21:41,  7.11s/it]
                                                           
{'loss': 0.6281, 'learning_rate': 0.00027115450032312864, 'epoch': 5.86}

 49%|████▉     | 13727/28080 [27:07:38<28:21:41,  7.11s/it]
 49%|████▉     | 13728/28080 [27:07:45<28:23:39,  7.12s/it]
                                                           
{'loss': 0.6221, 'learning_rate': 0.0002711257678953033, 'epoch': 5.86}

 49%|████▉     | 13728/28080 [27:07:45<28:23:39,  7.12s/it]
 49%|████▉     | 13729/28080 [27:07:52<28:27:41,  7.14s/it]
                                                           
{'loss': 0.6039, 'learning_rate': 0.0002710970351864213, 'epoch': 5.86}

 49%|████▉     | 13729/28080 [27:07:52<28:27:41,  7.14s/it]
 49%|████▉     | 13730/28080 [27:08:00<28:29:48,  7.15s/it]
                                                           
{'loss': 0.6137, 'learning_rate': 0.0002710683021968651, 'epoch': 5.87}

 49%|████▉     | 13730/28080 [27:08:00<28:29:48,  7.15s/it]
 49%|████▉     | 13731/28080 [27:08:07<28:18:54,  7.10s/it]
                                                           
{'loss': 0.6149, 'learning_rate': 0.0002710395689270168, 'epoch': 5.87}

 49%|████▉     | 13731/28080 [27:08:07<28:18:54,  7.10s/it]
 49%|████▉     | 13732/28080 [27:08:14<28:20:07,  7.11s/it]
                                                           
{'loss': 0.6111, 'learning_rate': 0.0002710108353772587, 'epoch': 5.87}

 49%|████▉     | 13732/28080 [27:08:14<28:20:07,  7.11s/it]
 49%|████▉     | 13733/28080 [27:08:21<28:19:34,  7.11s/it]
                                                           
{'loss': 0.6283, 'learning_rate': 0.0002709821015479733, 'epoch': 5.87}

 49%|████▉     | 13733/28080 [27:08:21<28:19:34,  7.11s/it]
 49%|████▉     | 13734/28080 [27:08:28<28:20:49,  7.11s/it]
                                                           
{'loss': 0.6227, 'learning_rate': 0.00027095336743954254, 'epoch': 5.87}

 49%|████▉     | 13734/28080 [27:08:28<28:20:49,  7.11s/it]
 49%|████▉     | 13735/28080 [27:08:35<28:24:39,  7.13s/it]
                                                           
{'loss': 0.6097, 'learning_rate': 0.0002709246330523489, 'epoch': 5.87}

 49%|████▉     | 13735/28080 [27:08:35<28:24:39,  7.13s/it]
 49%|████▉     | 13736/28080 [27:08:42<28:27:41,  7.14s/it]
                                                           
{'loss': 0.6215, 'learning_rate': 0.00027089589838677453, 'epoch': 5.87}

 49%|████▉     | 13736/28080 [27:08:42<28:27:41,  7.14s/it]
 49%|████▉     | 13737/28080 [27:08:49<28:25:22,  7.13s/it]
                                                           
{'loss': 0.5959, 'learning_rate': 0.0002708671634432019, 'epoch': 5.87}

 49%|████▉     | 13737/28080 [27:08:49<28:25:22,  7.13s/it]
 49%|████▉     | 13738/28080 [27:08:56<28:19:48,  7.11s/it]
                                                           
{'loss': 0.6242, 'learning_rate': 0.0002708384282220131, 'epoch': 5.87}

 49%|████▉     | 13738/28080 [27:08:56<28:19:48,  7.11s/it]
 49%|████▉     | 13739/28080 [27:09:04<28:24:35,  7.13s/it]
                                                           
{'loss': 0.6008, 'learning_rate': 0.0002708096927235905, 'epoch': 5.87}

 49%|████▉     | 13739/28080 [27:09:04<28:24:35,  7.13s/it]
 49%|████▉     | 13740/28080 [27:09:11<28:14:30,  7.09s/it]
                                                           
{'loss': 0.6238, 'learning_rate': 0.0002707809569483165, 'epoch': 5.87}

 49%|████▉     | 13740/28080 [27:09:11<28:14:30,  7.09s/it]
 49%|████▉     | 13741/28080 [27:09:18<28:19:06,  7.11s/it]
                                                           
{'loss': 0.6217, 'learning_rate': 0.00027075222089657325, 'epoch': 5.87}

 49%|████▉     | 13741/28080 [27:09:18<28:19:06,  7.11s/it]
 49%|████▉     | 13742/28080 [27:09:25<28:20:50,  7.12s/it]
                                                           
{'loss': 0.6089, 'learning_rate': 0.0002707234845687431, 'epoch': 5.87}

 49%|████▉     | 13742/28080 [27:09:25<28:20:50,  7.12s/it]
 49%|████▉     | 13743/28080 [27:09:32<28:22:06,  7.12s/it]
                                                           
{'loss': 0.6353, 'learning_rate': 0.00027069474796520836, 'epoch': 5.87}

 49%|████▉     | 13743/28080 [27:09:32<28:22:06,  7.12s/it]
 49%|████▉     | 13744/28080 [27:09:39<28:13:40,  7.09s/it]
                                                           
{'loss': 0.6356, 'learning_rate': 0.0002706660110863514, 'epoch': 5.87}

 49%|████▉     | 13744/28080 [27:09:39<28:13:40,  7.09s/it]
 49%|████▉     | 13745/28080 [27:09:46<28:17:10,  7.10s/it]
                                                           
{'loss': 0.6415, 'learning_rate': 0.00027063727393255443, 'epoch': 5.87}

 49%|████▉     | 13745/28080 [27:09:46<28:17:10,  7.10s/it]
 49%|████▉     | 13746/28080 [27:09:53<28:15:17,  7.10s/it]
                                                           
{'loss': 0.6213, 'learning_rate': 0.0002706085365041998, 'epoch': 5.87}

 49%|████▉     | 13746/28080 [27:09:53<28:15:17,  7.10s/it]
 49%|████▉     | 13747/28080 [27:10:00<28:18:10,  7.11s/it]
                                                           
{'loss': 0.6328, 'learning_rate': 0.00027057979880166995, 'epoch': 5.87}

 49%|████▉     | 13747/28080 [27:10:00<28:18:10,  7.11s/it]
 49%|████▉     | 13748/28080 [27:10:07<28:14:39,  7.09s/it]
                                                           
{'loss': 0.6218, 'learning_rate': 0.000270551060825347, 'epoch': 5.87}

 49%|████▉     | 13748/28080 [27:10:07<28:14:39,  7.09s/it]
 49%|████▉     | 13749/28080 [27:10:15<28:12:04,  7.08s/it]
                                                           
{'loss': 0.6192, 'learning_rate': 0.0002705223225756134, 'epoch': 5.87}

 49%|████▉     | 13749/28080 [27:10:15<28:12:04,  7.08s/it]
 49%|████▉     | 13750/28080 [27:10:22<28:14:56,  7.10s/it]
                                                           
{'loss': 0.5999, 'learning_rate': 0.0002704935840528515, 'epoch': 5.87}

 49%|████▉     | 13750/28080 [27:10:22<28:14:56,  7.10s/it]
 49%|████▉     | 13751/28080 [27:10:29<28:14:00,  7.09s/it]
                                                           
{'loss': 0.6178, 'learning_rate': 0.0002704648452574436, 'epoch': 5.87}

 49%|████▉     | 13751/28080 [27:10:29<28:14:00,  7.09s/it]
 49%|████▉     | 13752/28080 [27:10:36<28:16:44,  7.11s/it]
                                                           
{'loss': 0.6293, 'learning_rate': 0.00027043610618977213, 'epoch': 5.87}

 49%|████▉     | 13752/28080 [27:10:36<28:16:44,  7.11s/it]
 49%|████▉     | 13753/28080 [27:10:43<28:17:55,  7.11s/it]
                                                           
{'loss': 0.6206, 'learning_rate': 0.0002704073668502192, 'epoch': 5.88}

 49%|████▉     | 13753/28080 [27:10:43<28:17:55,  7.11s/it]
 49%|████▉     | 13754/28080 [27:10:50<28:19:16,  7.12s/it]
                                                           
{'loss': 0.6564, 'learning_rate': 0.00027037862723916744, 'epoch': 5.88}

 49%|████▉     | 13754/28080 [27:10:50<28:19:16,  7.12s/it]
 49%|████▉     | 13755/28080 [27:10:57<28:19:51,  7.12s/it]
                                                           
{'loss': 0.6142, 'learning_rate': 0.000270349887356999, 'epoch': 5.88}

 49%|████▉     | 13755/28080 [27:10:57<28:19:51,  7.12s/it]
 49%|████▉     | 13756/28080 [27:11:04<28:14:04,  7.10s/it]
                                                           
{'loss': 0.6278, 'learning_rate': 0.00027032114720409626, 'epoch': 5.88}

 49%|████▉     | 13756/28080 [27:11:04<28:14:04,  7.10s/it]
 49%|████▉     | 13757/28080 [27:11:11<28:08:06,  7.07s/it]
                                                           
{'loss': 0.5983, 'learning_rate': 0.0002702924067808417, 'epoch': 5.88}

 49%|████▉     | 13757/28080 [27:11:11<28:08:06,  7.07s/it]
 49%|████▉     | 13758/28080 [27:11:18<28:13:12,  7.09s/it]
                                                           
{'loss': 0.6194, 'learning_rate': 0.00027026366608761754, 'epoch': 5.88}

 49%|████▉     | 13758/28080 [27:11:18<28:13:12,  7.09s/it]
 49%|████▉     | 13759/28080 [27:11:26<28:13:25,  7.09s/it]
                                                           
{'loss': 0.6177, 'learning_rate': 0.0002702349251248063, 'epoch': 5.88}

 49%|████▉     | 13759/28080 [27:11:26<28:13:25,  7.09s/it]
 49%|████▉     | 13760/28080 [27:11:33<28:08:05,  7.07s/it]
                                                           
{'loss': 0.6277, 'learning_rate': 0.00027020618389279015, 'epoch': 5.88}

 49%|████▉     | 13760/28080 [27:11:33<28:08:05,  7.07s/it]
 49%|████▉     | 13761/28080 [27:11:40<28:13:18,  7.10s/it]
                                                           
{'loss': 0.6246, 'learning_rate': 0.0002701774423919517, 'epoch': 5.88}

 49%|████▉     | 13761/28080 [27:11:40<28:13:18,  7.10s/it]
 49%|████▉     | 13762/28080 [27:11:47<28:13:07,  7.10s/it]
                                                           
{'loss': 0.6287, 'learning_rate': 0.00027014870062267305, 'epoch': 5.88}

 49%|████▉     | 13762/28080 [27:11:47<28:13:07,  7.10s/it]
 49%|████▉     | 13763/28080 [27:11:54<28:13:41,  7.10s/it]
                                                           
{'loss': 0.613, 'learning_rate': 0.00027011995858533685, 'epoch': 5.88}

 49%|████▉     | 13763/28080 [27:11:54<28:13:41,  7.10s/it]
 49%|████▉     | 13764/28080 [27:12:01<28:18:10,  7.12s/it]
                                                           
{'loss': 0.6329, 'learning_rate': 0.0002700912162803253, 'epoch': 5.88}

 49%|████▉     | 13764/28080 [27:12:01<28:18:10,  7.12s/it]
 49%|████▉     | 13765/28080 [27:12:08<28:05:18,  7.06s/it]
                                                           
{'loss': 0.6256, 'learning_rate': 0.00027006247370802084, 'epoch': 5.88}

 49%|████▉     | 13765/28080 [27:12:08<28:05:18,  7.06s/it]
 49%|████▉     | 13766/28080 [27:12:15<28:03:19,  7.06s/it]
                                                           
{'loss': 0.6406, 'learning_rate': 0.00027003373086880583, 'epoch': 5.88}

 49%|████▉     | 13766/28080 [27:12:15<28:03:19,  7.06s/it]
 49%|████▉     | 13767/28080 [27:12:22<28:10:55,  7.09s/it]
                                                           
{'loss': 0.6252, 'learning_rate': 0.00027000498776306276, 'epoch': 5.88}

 49%|████▉     | 13767/28080 [27:12:22<28:10:55,  7.09s/it]
 49%|████▉     | 13768/28080 [27:12:29<28:11:20,  7.09s/it]
                                                           
{'loss': 0.6238, 'learning_rate': 0.0002699762443911739, 'epoch': 5.88}

 49%|████▉     | 13768/28080 [27:12:29<28:11:20,  7.09s/it]
 49%|████▉     | 13769/28080 [27:12:37<28:17:10,  7.12s/it]
                                                           
{'loss': 0.6023, 'learning_rate': 0.0002699475007535218, 'epoch': 5.88}

 49%|████▉     | 13769/28080 [27:12:37<28:17:10,  7.12s/it]
 49%|████▉     | 13770/28080 [27:12:44<28:28:09,  7.16s/it]
                                                           
{'loss': 0.6172, 'learning_rate': 0.0002699187568504887, 'epoch': 5.88}

 49%|████▉     | 13770/28080 [27:12:44<28:28:09,  7.16s/it]
 49%|████▉     | 13771/28080 [27:12:51<28:23:22,  7.14s/it]
                                                           
{'loss': 0.6066, 'learning_rate': 0.00026989001268245714, 'epoch': 5.88}

 49%|████▉     | 13771/28080 [27:12:51<28:23:22,  7.14s/it]
 49%|████▉     | 13772/28080 [27:12:58<28:25:07,  7.15s/it]
                                                           
{'loss': 0.6258, 'learning_rate': 0.0002698612682498095, 'epoch': 5.88}

 49%|████▉     | 13772/28080 [27:12:58<28:25:07,  7.15s/it]
 49%|████▉     | 13773/28080 [27:13:05<28:27:24,  7.16s/it]
                                                           
{'loss': 0.6315, 'learning_rate': 0.0002698325235529281, 'epoch': 5.88}

 49%|████▉     | 13773/28080 [27:13:05<28:27:24,  7.16s/it]
 49%|████▉     | 13774/28080 [27:13:12<28:29:45,  7.17s/it]
                                                           
{'loss': 0.6186, 'learning_rate': 0.00026980377859219554, 'epoch': 5.88}

 49%|████▉     | 13774/28080 [27:13:12<28:29:45,  7.17s/it]
 49%|████▉     | 13775/28080 [27:13:19<28:18:34,  7.12s/it]
                                                           
{'loss': 0.6277, 'learning_rate': 0.000269775033367994, 'epoch': 5.88}

 49%|████▉     | 13775/28080 [27:13:19<28:18:34,  7.12s/it]
 49%|████▉     | 13776/28080 [27:13:26<28:10:20,  7.09s/it]
                                                           
{'loss': 0.6307, 'learning_rate': 0.00026974628788070616, 'epoch': 5.88}

 49%|████▉     | 13776/28080 [27:13:26<28:10:20,  7.09s/it]
 49%|████▉     | 13777/28080 [27:13:34<28:08:46,  7.08s/it]
                                                           
{'loss': 0.6201, 'learning_rate': 0.00026971754213071423, 'epoch': 5.89}

 49%|████▉     | 13777/28080 [27:13:34<28:08:46,  7.08s/it]
 49%|████▉     | 13778/28080 [27:13:41<28:14:26,  7.11s/it]
                                                           
{'loss': 0.6363, 'learning_rate': 0.0002696887961184009, 'epoch': 5.89}

 49%|████▉     | 13778/28080 [27:13:41<28:14:26,  7.11s/it]
 49%|████▉     | 13779/28080 [27:13:48<28:12:03,  7.10s/it]
                                                           
{'loss': 0.623, 'learning_rate': 0.00026966004984414825, 'epoch': 5.89}

 49%|████▉     | 13779/28080 [27:13:48<28:12:03,  7.10s/it]
 49%|████▉     | 13780/28080 [27:13:55<28:16:37,  7.12s/it]
                                                           
{'loss': 0.6303, 'learning_rate': 0.000269631303308339, 'epoch': 5.89}

 49%|████▉     | 13780/28080 [27:13:55<28:16:37,  7.12s/it]
 49%|████▉     | 13781/28080 [27:14:02<28:13:07,  7.10s/it]
                                                           
{'loss': 0.6454, 'learning_rate': 0.0002696025565113556, 'epoch': 5.89}

 49%|████▉     | 13781/28080 [27:14:02<28:13:07,  7.10s/it]
 49%|████▉     | 13782/28080 [27:14:09<28:16:19,  7.12s/it]
                                                           
{'loss': 0.5951, 'learning_rate': 0.0002695738094535803, 'epoch': 5.89}

 49%|████▉     | 13782/28080 [27:14:09<28:16:19,  7.12s/it]
 49%|████▉     | 13783/28080 [27:14:16<28:12:00,  7.10s/it]
                                                           
{'loss': 0.62, 'learning_rate': 0.00026954506213539573, 'epoch': 5.89}

 49%|████▉     | 13783/28080 [27:14:16<28:12:00,  7.10s/it]
 49%|████▉     | 13784/28080 [27:14:23<28:11:34,  7.10s/it]
                                                           
{'loss': 0.6268, 'learning_rate': 0.00026951631455718425, 'epoch': 5.89}

 49%|████▉     | 13784/28080 [27:14:23<28:11:34,  7.10s/it]
 49%|████▉     | 13785/28080 [27:14:31<28:20:53,  7.14s/it]
                                                           
{'loss': 0.6275, 'learning_rate': 0.0002694875667193283, 'epoch': 5.89}

 49%|████▉     | 13785/28080 [27:14:31<28:20:53,  7.14s/it]
 49%|████▉     | 13786/28080 [27:14:38<28:17:39,  7.13s/it]
                                                           
{'loss': 0.6175, 'learning_rate': 0.00026945881862221036, 'epoch': 5.89}

 49%|████▉     | 13786/28080 [27:14:38<28:17:39,  7.13s/it]
 49%|████▉     | 13787/28080 [27:14:45<28:02:51,  7.06s/it]
                                                           
{'loss': 0.6409, 'learning_rate': 0.00026943007026621296, 'epoch': 5.89}

 49%|████▉     | 13787/28080 [27:14:45<28:02:51,  7.06s/it]
 49%|████▉     | 13788/28080 [27:14:52<28:06:06,  7.08s/it]
                                                           
{'loss': 0.6259, 'learning_rate': 0.0002694013216517186, 'epoch': 5.89}

 49%|████▉     | 13788/28080 [27:14:52<28:06:06,  7.08s/it]
 49%|████▉     | 13789/28080 [27:14:59<28:11:07,  7.10s/it]
                                                           
{'loss': 0.6166, 'learning_rate': 0.0002693725727791096, 'epoch': 5.89}

 49%|████▉     | 13789/28080 [27:14:59<28:11:07,  7.10s/it]
 49%|████▉     | 13790/28080 [27:15:06<28:12:20,  7.11s/it]
                                                           
{'loss': 0.6342, 'learning_rate': 0.00026934382364876845, 'epoch': 5.89}

 49%|████▉     | 13790/28080 [27:15:06<28:12:20,  7.11s/it]
 49%|████▉     | 13791/28080 [27:15:13<28:19:48,  7.14s/it]
                                                           
{'loss': 0.6222, 'learning_rate': 0.00026931507426107776, 'epoch': 5.89}

 49%|████▉     | 13791/28080 [27:15:13<28:19:48,  7.14s/it]
 49%|████▉     | 13792/28080 [27:15:20<28:21:51,  7.15s/it]
                                                           
{'loss': 0.6087, 'learning_rate': 0.0002692863246164199, 'epoch': 5.89}

 49%|████▉     | 13792/28080 [27:15:20<28:21:51,  7.15s/it]
 49%|████▉     | 13793/28080 [27:15:28<28:26:17,  7.17s/it]
                                                           
{'loss': 0.6229, 'learning_rate': 0.00026925757471517737, 'epoch': 5.89}

 49%|████▉     | 13793/28080 [27:15:28<28:26:17,  7.17s/it]
 49%|████▉     | 13794/28080 [27:15:35<28:29:40,  7.18s/it]
                                                           
{'loss': 0.638, 'learning_rate': 0.0002692288245577327, 'epoch': 5.89}

 49%|████▉     | 13794/28080 [27:15:35<28:29:40,  7.18s/it]
 49%|████▉     | 13795/28080 [27:15:42<28:27:03,  7.17s/it]
                                                           
{'loss': 0.6199, 'learning_rate': 0.0002692000741444683, 'epoch': 5.89}

 49%|████▉     | 13795/28080 [27:15:42<28:27:03,  7.17s/it]
 49%|████▉     | 13796/28080 [27:15:49<28:26:25,  7.17s/it]
                                                           
{'loss': 0.6208, 'learning_rate': 0.00026917132347576686, 'epoch': 5.89}

 49%|████▉     | 13796/28080 [27:15:49<28:26:25,  7.17s/it]
 49%|████▉     | 13797/28080 [27:15:56<28:31:53,  7.19s/it]
                                                           
{'loss': 0.6045, 'learning_rate': 0.00026914257255201057, 'epoch': 5.89}

 49%|████▉     | 13797/28080 [27:15:56<28:31:53,  7.19s/it]
 49%|████▉     | 13798/28080 [27:16:03<28:30:11,  7.18s/it]
                                                           
{'loss': 0.632, 'learning_rate': 0.0002691138213735822, 'epoch': 5.89}

 49%|████▉     | 13798/28080 [27:16:03<28:30:11,  7.18s/it]
 49%|████▉     | 13799/28080 [27:16:10<28:12:36,  7.11s/it]
                                                           
{'loss': 0.6339, 'learning_rate': 0.0002690850699408641, 'epoch': 5.89}

 49%|████▉     | 13799/28080 [27:16:10<28:12:36,  7.11s/it]
 49%|████▉     | 13800/28080 [27:16:18<28:15:38,  7.12s/it]
                                                           
{'loss': 0.6174, 'learning_rate': 0.00026905631825423893, 'epoch': 5.9}

 49%|████▉     | 13800/28080 [27:16:18<28:15:38,  7.12s/it]
 49%|████▉     | 13801/28080 [27:16:25<28:12:49,  7.11s/it]
                                                           
{'loss': 0.6096, 'learning_rate': 0.000269027566314089, 'epoch': 5.9}

 49%|████▉     | 13801/28080 [27:16:25<28:12:49,  7.11s/it]
 49%|████▉     | 13802/28080 [27:16:32<28:09:07,  7.10s/it]
                                                           
{'loss': 0.6191, 'learning_rate': 0.00026899881412079704, 'epoch': 5.9}

 49%|████▉     | 13802/28080 [27:16:32<28:09:07,  7.10s/it]
 49%|████▉     | 13803/28080 [27:16:39<28:16:57,  7.13s/it]
                                                           
{'loss': 0.6054, 'learning_rate': 0.0002689700616747454, 'epoch': 5.9}

 49%|████▉     | 13803/28080 [27:16:39<28:16:57,  7.13s/it]
 49%|████▉     | 13804/28080 [27:16:46<28:26:25,  7.17s/it]
                                                           
{'loss': 0.6356, 'learning_rate': 0.00026894130897631656, 'epoch': 5.9}

 49%|████▉     | 13804/28080 [27:16:46<28:26:25,  7.17s/it]
 49%|████▉     | 13805/28080 [27:16:53<28:31:50,  7.20s/it]
                                                           
{'loss': 0.6186, 'learning_rate': 0.00026891255602589325, 'epoch': 5.9}

 49%|████▉     | 13805/28080 [27:16:53<28:31:50,  7.20s/it]
 49%|████▉     | 13806/28080 [27:17:00<28:19:52,  7.15s/it]
                                                           
{'loss': 0.628, 'learning_rate': 0.0002688838028238579, 'epoch': 5.9}

 49%|████▉     | 13806/28080 [27:17:00<28:19:52,  7.15s/it]
 49%|████▉     | 13807/28080 [27:17:08<28:16:32,  7.13s/it]
                                                           
{'loss': 0.6066, 'learning_rate': 0.00026885504937059304, 'epoch': 5.9}

 49%|████▉     | 13807/28080 [27:17:08<28:16:32,  7.13s/it]
 49%|████▉     | 13808/28080 [27:17:15<28:21:31,  7.15s/it]
                                                           
{'loss': 0.628, 'learning_rate': 0.00026882629566648116, 'epoch': 5.9}

 49%|████▉     | 13808/28080 [27:17:15<28:21:31,  7.15s/it]
 49%|████▉     | 13809/28080 [27:17:22<28:15:34,  7.13s/it]
                                                           
{'loss': 0.6091, 'learning_rate': 0.00026879754171190486, 'epoch': 5.9}

 49%|████▉     | 13809/28080 [27:17:22<28:15:34,  7.13s/it]
 49%|████▉     | 13810/28080 [27:17:29<28:15:54,  7.13s/it]
                                                           
{'loss': 0.6047, 'learning_rate': 0.00026876878750724665, 'epoch': 5.9}

 49%|████▉     | 13810/28080 [27:17:29<28:15:54,  7.13s/it]
 49%|████▉     | 13811/28080 [27:17:36<28:13:47,  7.12s/it]
                                                           
{'loss': 0.5993, 'learning_rate': 0.00026874003305288904, 'epoch': 5.9}

 49%|████▉     | 13811/28080 [27:17:36<28:13:47,  7.12s/it]
 49%|████▉     | 13812/28080 [27:17:43<28:09:30,  7.10s/it]
                                                           
{'loss': 0.6128, 'learning_rate': 0.0002687112783492147, 'epoch': 5.9}

 49%|████▉     | 13812/28080 [27:17:43<28:09:30,  7.10s/it]
 49%|████▉     | 13813/28080 [27:17:50<28:16:08,  7.13s/it]
                                                           
{'loss': 0.5906, 'learning_rate': 0.00026868252339660607, 'epoch': 5.9}

 49%|████▉     | 13813/28080 [27:17:50<28:16:08,  7.13s/it]
 49%|████▉     | 13814/28080 [27:17:58<28:18:51,  7.15s/it]
                                                           
{'loss': 0.6234, 'learning_rate': 0.0002686537681954457, 'epoch': 5.9}

 49%|████▉     | 13814/28080 [27:17:58<28:18:51,  7.15s/it]
 49%|████▉     | 13815/28080 [27:18:05<28:12:16,  7.12s/it]
                                                           
{'loss': 0.6124, 'learning_rate': 0.0002686250127461163, 'epoch': 5.9}

 49%|████▉     | 13815/28080 [27:18:05<28:12:16,  7.12s/it]
 49%|████▉     | 13816/28080 [27:18:12<28:15:28,  7.13s/it]
                                                           
{'loss': 0.6194, 'learning_rate': 0.00026859625704900026, 'epoch': 5.9}

 49%|████▉     | 13816/28080 [27:18:12<28:15:28,  7.13s/it]
 49%|████▉     | 13817/28080 [27:18:19<28:16:03,  7.13s/it]
                                                           
{'loss': 0.6082, 'learning_rate': 0.00026856750110448017, 'epoch': 5.9}

 49%|████▉     | 13817/28080 [27:18:19<28:16:03,  7.13s/it]
 49%|████▉     | 13818/28080 [27:18:26<28:13:44,  7.13s/it]
                                                           
{'loss': 0.6179, 'learning_rate': 0.00026853874491293865, 'epoch': 5.9}

 49%|████▉     | 13818/28080 [27:18:26<28:13:44,  7.13s/it]
 49%|████▉     | 13819/28080 [27:18:33<28:19:29,  7.15s/it]
                                                           
{'loss': 0.6428, 'learning_rate': 0.0002685099884747583, 'epoch': 5.9}

 49%|████▉     | 13819/28080 [27:18:33<28:19:29,  7.15s/it]
 49%|████▉     | 13820/28080 [27:18:40<28:15:56,  7.14s/it]
                                                           
{'loss': 0.6204, 'learning_rate': 0.00026848123179032163, 'epoch': 5.9}

 49%|████▉     | 13820/28080 [27:18:40<28:15:56,  7.14s/it]
 49%|████▉     | 13821/28080 [27:18:47<28:18:41,  7.15s/it]
                                                           
{'loss': 0.614, 'learning_rate': 0.0002684524748600112, 'epoch': 5.9}

 49%|████▉     | 13821/28080 [27:18:47<28:18:41,  7.15s/it]
 49%|████▉     | 13822/28080 [27:18:54<28:06:39,  7.10s/it]
                                                           
{'loss': 0.6613, 'learning_rate': 0.00026842371768420964, 'epoch': 5.9}

 49%|████▉     | 13822/28080 [27:18:54<28:06:39,  7.10s/it]
 49%|████▉     | 13823/28080 [27:19:02<28:12:46,  7.12s/it]
                                                           
{'loss': 0.6075, 'learning_rate': 0.0002683949602632995, 'epoch': 5.91}

 49%|████▉     | 13823/28080 [27:19:02<28:12:46,  7.12s/it]
 49%|████▉     | 13824/28080 [27:19:09<28:10:04,  7.11s/it]
                                                           
{'loss': 0.6338, 'learning_rate': 0.0002683662025976635, 'epoch': 5.91}

 49%|████▉     | 13824/28080 [27:19:09<28:10:04,  7.11s/it]
 49%|████▉     | 13825/28080 [27:19:16<28:05:49,  7.10s/it]
                                                           
{'loss': 0.6337, 'learning_rate': 0.00026833744468768403, 'epoch': 5.91}

 49%|████▉     | 13825/28080 [27:19:16<28:05:49,  7.10s/it]
 49%|████▉     | 13826/28080 [27:19:23<28:05:09,  7.09s/it]
                                                           
{'loss': 0.6158, 'learning_rate': 0.0002683086865337438, 'epoch': 5.91}

 49%|████▉     | 13826/28080 [27:19:23<28:05:09,  7.09s/it]
 49%|████▉     | 13827/28080 [27:19:30<28:04:29,  7.09s/it]
                                                           
{'loss': 0.6212, 'learning_rate': 0.00026827992813622533, 'epoch': 5.91}

 49%|████▉     | 13827/28080 [27:19:30<28:04:29,  7.09s/it]
 49%|████▉     | 13828/28080 [27:19:37<28:04:40,  7.09s/it]
                                                           
{'loss': 0.5997, 'learning_rate': 0.0002682511694955113, 'epoch': 5.91}

 49%|████▉     | 13828/28080 [27:19:37<28:04:40,  7.09s/it]
 49%|████▉     | 13829/28080 [27:19:44<28:00:40,  7.08s/it]
                                                           
{'loss': 0.6381, 'learning_rate': 0.00026822241061198434, 'epoch': 5.91}

 49%|████▉     | 13829/28080 [27:19:44<28:00:40,  7.08s/it]
 49%|████▉     | 13830/28080 [27:19:51<28:00:27,  7.08s/it]
                                                           
{'loss': 0.6212, 'learning_rate': 0.0002681936514860269, 'epoch': 5.91}

 49%|████▉     | 13830/28080 [27:19:51<28:00:27,  7.08s/it]
 49%|████▉     | 13831/28080 [27:19:58<28:04:51,  7.09s/it]
                                                           
{'loss': 0.6096, 'learning_rate': 0.00026816489211802186, 'epoch': 5.91}

 49%|████▉     | 13831/28080 [27:19:58<28:04:51,  7.09s/it]
 49%|████▉     | 13832/28080 [27:20:05<28:07:36,  7.11s/it]
                                                           
{'loss': 0.6108, 'learning_rate': 0.00026813613250835155, 'epoch': 5.91}

 49%|████▉     | 13832/28080 [27:20:05<28:07:36,  7.11s/it]
 49%|████▉     | 13833/28080 [27:20:12<28:03:10,  7.09s/it]
                                                           
{'loss': 0.6341, 'learning_rate': 0.00026810737265739877, 'epoch': 5.91}

 49%|████▉     | 13833/28080 [27:20:12<28:03:10,  7.09s/it]
 49%|████▉     | 13834/28080 [27:20:20<28:08:56,  7.11s/it]
                                                           
{'loss': 0.6048, 'learning_rate': 0.000268078612565546, 'epoch': 5.91}

 49%|████▉     | 13834/28080 [27:20:20<28:08:56,  7.11s/it]
 49%|████▉     | 13835/28080 [27:20:27<28:11:32,  7.12s/it]
                                                           
{'loss': 0.6124, 'learning_rate': 0.000268049852233176, 'epoch': 5.91}

 49%|████▉     | 13835/28080 [27:20:27<28:11:32,  7.12s/it]
 49%|████▉     | 13836/28080 [27:20:34<28:16:39,  7.15s/it]
                                                           
{'loss': 0.5904, 'learning_rate': 0.0002680210916606713, 'epoch': 5.91}

 49%|████▉     | 13836/28080 [27:20:34<28:16:39,  7.15s/it]
 49%|████▉     | 13837/28080 [27:20:41<28:21:36,  7.17s/it]
                                                           
{'loss': 0.6419, 'learning_rate': 0.0002679923308484146, 'epoch': 5.91}

 49%|████▉     | 13837/28080 [27:20:41<28:21:36,  7.17s/it]
 49%|████▉     | 13838/28080 [27:20:48<28:20:52,  7.17s/it]
                                                           
{'loss': 0.6012, 'learning_rate': 0.0002679635697967885, 'epoch': 5.91}

 49%|████▉     | 13838/28080 [27:20:48<28:20:52,  7.17s/it]
 49%|████▉     | 13839/28080 [27:20:56<28:26:15,  7.19s/it]
                                                           
{'loss': 0.6213, 'learning_rate': 0.00026793480850617564, 'epoch': 5.91}

 49%|████▉     | 13839/28080 [27:20:56<28:26:15,  7.19s/it]
 49%|████▉     | 13840/28080 [27:21:03<28:18:32,  7.16s/it]
                                                           
{'loss': 0.6226, 'learning_rate': 0.00026790604697695867, 'epoch': 5.91}

 49%|████▉     | 13840/28080 [27:21:03<28:18:32,  7.16s/it]
 49%|████▉     | 13841/28080 [27:21:10<28:16:03,  7.15s/it]
                                                           
{'loss': 0.6186, 'learning_rate': 0.00026787728520952014, 'epoch': 5.91}

 49%|████▉     | 13841/28080 [27:21:10<28:16:03,  7.15s/it]
 49%|████▉     | 13842/28080 [27:21:17<28:20:36,  7.17s/it]
                                                           
{'loss': 0.6167, 'learning_rate': 0.0002678485232042428, 'epoch': 5.91}

 49%|████▉     | 13842/28080 [27:21:17<28:20:36,  7.17s/it]
 49%|████▉     | 13843/28080 [27:21:24<28:17:41,  7.15s/it]
                                                           
{'loss': 0.6119, 'learning_rate': 0.00026781976096150933, 'epoch': 5.91}

 49%|████▉     | 13843/28080 [27:21:24<28:17:41,  7.15s/it]
 49%|████▉     | 13844/28080 [27:21:31<28:09:30,  7.12s/it]
                                                           
{'loss': 0.623, 'learning_rate': 0.0002677909984817023, 'epoch': 5.91}

 49%|████▉     | 13844/28080 [27:21:31<28:09:30,  7.12s/it]
 49%|████▉     | 13845/28080 [27:21:38<27:56:26,  7.07s/it]
                                                           
{'loss': 0.6348, 'learning_rate': 0.0002677622357652043, 'epoch': 5.91}

 49%|████▉     | 13845/28080 [27:21:38<27:56:26,  7.07s/it]
 49%|████▉     | 13846/28080 [27:21:45<28:08:18,  7.12s/it]
                                                           
{'loss': 0.6399, 'learning_rate': 0.0002677334728123982, 'epoch': 5.91}

 49%|████▉     | 13846/28080 [27:21:45<28:08:18,  7.12s/it]
 49%|████▉     | 13847/28080 [27:21:53<28:21:18,  7.17s/it]
                                                           
{'loss': 0.6415, 'learning_rate': 0.0002677047096236664, 'epoch': 5.92}

 49%|████▉     | 13847/28080 [27:21:53<28:21:18,  7.17s/it]
 49%|████▉     | 13848/28080 [27:22:00<28:15:13,  7.15s/it]
                                                           
{'loss': 0.6292, 'learning_rate': 0.0002676759461993919, 'epoch': 5.92}

 49%|████▉     | 13848/28080 [27:22:00<28:15:13,  7.15s/it]
 49%|████▉     | 13849/28080 [27:22:07<28:10:04,  7.13s/it]
                                                           
{'loss': 0.6251, 'learning_rate': 0.00026764718253995703, 'epoch': 5.92}

 49%|████▉     | 13849/28080 [27:22:07<28:10:04,  7.13s/it]
 49%|████▉     | 13850/28080 [27:22:14<28:12:39,  7.14s/it]
                                                           
{'loss': 0.6352, 'learning_rate': 0.00026761841864574466, 'epoch': 5.92}

 49%|████▉     | 13850/28080 [27:22:14<28:12:39,  7.14s/it]
 49%|████▉     | 13851/28080 [27:22:21<28:17:55,  7.16s/it]
                                                           
{'loss': 0.6344, 'learning_rate': 0.00026758965451713736, 'epoch': 5.92}

 49%|████▉     | 13851/28080 [27:22:21<28:17:55,  7.16s/it]
 49%|████▉     | 13852/28080 [27:22:28<28:09:08,  7.12s/it]
                                                           
{'loss': 0.6175, 'learning_rate': 0.0002675608901545178, 'epoch': 5.92}

 49%|████▉     | 13852/28080 [27:22:28<28:09:08,  7.12s/it]
 49%|████▉     | 13853/28080 [27:22:35<28:06:27,  7.11s/it]
                                                           
{'loss': 0.6182, 'learning_rate': 0.0002675321255582689, 'epoch': 5.92}

 49%|████▉     | 13853/28080 [27:22:35<28:06:27,  7.11s/it]
 49%|████▉     | 13854/28080 [27:22:42<28:05:34,  7.11s/it]
                                                           
{'loss': 0.6247, 'learning_rate': 0.000267503360728773, 'epoch': 5.92}

 49%|████▉     | 13854/28080 [27:22:42<28:05:34,  7.11s/it]
 49%|████▉     | 13855/28080 [27:22:50<28:05:48,  7.11s/it]
                                                           
{'loss': 0.6166, 'learning_rate': 0.000267474595666413, 'epoch': 5.92}

 49%|████▉     | 13855/28080 [27:22:50<28:05:48,  7.11s/it]
 49%|████▉     | 13856/28080 [27:22:57<28:00:07,  7.09s/it]
                                                           
{'loss': 0.6115, 'learning_rate': 0.0002674458303715715, 'epoch': 5.92}

 49%|████▉     | 13856/28080 [27:22:57<28:00:07,  7.09s/it]
 49%|████▉     | 13857/28080 [27:23:04<27:59:59,  7.09s/it]
                                                           
{'loss': 0.6118, 'learning_rate': 0.0002674170648446313, 'epoch': 5.92}

 49%|████▉     | 13857/28080 [27:23:04<27:59:59,  7.09s/it]
 49%|████▉     | 13858/28080 [27:23:11<28:08:07,  7.12s/it]
                                                           
{'loss': 0.5915, 'learning_rate': 0.000267388299085975, 'epoch': 5.92}

 49%|████▉     | 13858/28080 [27:23:11<28:08:07,  7.12s/it]
 49%|████▉     | 13859/28080 [27:23:18<28:07:48,  7.12s/it]
                                                           
{'loss': 0.5961, 'learning_rate': 0.0002673595330959852, 'epoch': 5.92}

 49%|████▉     | 13859/28080 [27:23:18<28:07:48,  7.12s/it]
 49%|████▉     | 13860/28080 [27:23:25<28:11:01,  7.14s/it]
                                                           
{'loss': 0.6183, 'learning_rate': 0.00026733076687504483, 'epoch': 5.92}

 49%|████▉     | 13860/28080 [27:23:25<28:11:01,  7.14s/it]
 49%|████▉     | 13861/28080 [27:23:32<28:05:48,  7.11s/it]
                                                           
{'loss': 0.6129, 'learning_rate': 0.0002673020004235364, 'epoch': 5.92}

 49%|████▉     | 13861/28080 [27:23:32<28:05:48,  7.11s/it]
 49%|████▉     | 13862/28080 [27:23:39<28:06:55,  7.12s/it]
                                                           
{'loss': 0.6066, 'learning_rate': 0.00026727323374184283, 'epoch': 5.92}

 49%|████▉     | 13862/28080 [27:23:39<28:06:55,  7.12s/it]
 49%|████▉     | 13863/28080 [27:23:47<28:09:57,  7.13s/it]
                                                           
{'loss': 0.6188, 'learning_rate': 0.00026724446683034666, 'epoch': 5.92}

 49%|████▉     | 13863/28080 [27:23:47<28:09:57,  7.13s/it]
 49%|████▉     | 13864/28080 [27:23:54<28:06:08,  7.12s/it]
                                                           
{'loss': 0.6237, 'learning_rate': 0.0002672156996894306, 'epoch': 5.92}

 49%|████▉     | 13864/28080 [27:23:54<28:06:08,  7.12s/it]
 49%|████▉     | 13865/28080 [27:24:01<28:14:01,  7.15s/it]
                                                           
{'loss': 0.612, 'learning_rate': 0.0002671869323194775, 'epoch': 5.92}

 49%|████▉     | 13865/28080 [27:24:01<28:14:01,  7.15s/it]
 49%|████▉     | 13866/28080 [27:24:08<28:08:56,  7.13s/it]
                                                           
{'loss': 0.6193, 'learning_rate': 0.0002671581647208699, 'epoch': 5.92}

 49%|████▉     | 13866/28080 [27:24:08<28:08:56,  7.13s/it]
 49%|████▉     | 13867/28080 [27:24:15<28:12:38,  7.15s/it]
                                                           
{'loss': 0.6044, 'learning_rate': 0.00026712939689399066, 'epoch': 5.92}

 49%|████▉     | 13867/28080 [27:24:15<28:12:38,  7.15s/it]
 49%|████▉     | 13868/28080 [27:24:22<28:15:17,  7.16s/it]
                                                           
{'loss': 0.6407, 'learning_rate': 0.0002671006288392225, 'epoch': 5.92}

 49%|████▉     | 13868/28080 [27:24:22<28:15:17,  7.16s/it]
 49%|████▉     | 13869/28080 [27:24:29<28:11:48,  7.14s/it]
                                                           
{'loss': 0.6244, 'learning_rate': 0.00026707186055694804, 'epoch': 5.92}

 49%|████▉     | 13869/28080 [27:24:29<28:11:48,  7.14s/it]
 49%|████▉     | 13870/28080 [27:24:36<28:03:47,  7.11s/it]
                                                           
{'loss': 0.6292, 'learning_rate': 0.00026704309204755015, 'epoch': 5.93}

 49%|████▉     | 13870/28080 [27:24:36<28:03:47,  7.11s/it]
 49%|████▉     | 13871/28080 [27:24:44<28:04:15,  7.11s/it]
                                                           
{'loss': 0.6321, 'learning_rate': 0.00026701432331141143, 'epoch': 5.93}

 49%|████▉     | 13871/28080 [27:24:44<28:04:15,  7.11s/it]
 49%|████▉     | 13872/28080 [27:24:51<28:08:43,  7.13s/it]
                                                           
{'loss': 0.6178, 'learning_rate': 0.00026698555434891483, 'epoch': 5.93}

 49%|████▉     | 13872/28080 [27:24:51<28:08:43,  7.13s/it]
 49%|████▉     | 13873/28080 [27:24:58<28:04:11,  7.11s/it]
                                                           
{'loss': 0.6439, 'learning_rate': 0.0002669567851604428, 'epoch': 5.93}

 49%|████▉     | 13873/28080 [27:24:58<28:04:11,  7.11s/it]
 49%|████▉     | 13874/28080 [27:25:05<27:52:20,  7.06s/it]
                                                           
{'loss': 0.6292, 'learning_rate': 0.00026692801574637837, 'epoch': 5.93}

 49%|████▉     | 13874/28080 [27:25:05<27:52:20,  7.06s/it]
 49%|████▉     | 13875/28080 [27:25:12<27:52:25,  7.06s/it]
                                                           
{'loss': 0.6066, 'learning_rate': 0.000266899246107104, 'epoch': 5.93}

 49%|████▉     | 13875/28080 [27:25:12<27:52:25,  7.06s/it]
 49%|████▉     | 13876/28080 [27:25:19<27:55:19,  7.08s/it]
                                                           
{'loss': 0.6107, 'learning_rate': 0.0002668704762430027, 'epoch': 5.93}

 49%|████▉     | 13876/28080 [27:25:19<27:55:19,  7.08s/it]
 49%|████▉     | 13877/28080 [27:25:26<27:52:57,  7.07s/it]
                                                           
{'loss': 0.6273, 'learning_rate': 0.00026684170615445715, 'epoch': 5.93}

 49%|████▉     | 13877/28080 [27:25:26<27:52:57,  7.07s/it]
 49%|████▉     | 13878/28080 [27:25:33<28:00:09,  7.10s/it]
                                                           
{'loss': 0.6068, 'learning_rate': 0.00026681293584185, 'epoch': 5.93}

 49%|████▉     | 13878/28080 [27:25:33<28:00:09,  7.10s/it]
 49%|████▉     | 13879/28080 [27:25:40<28:01:16,  7.10s/it]
                                                           
{'loss': 0.6262, 'learning_rate': 0.0002667841653055641, 'epoch': 5.93}

 49%|████▉     | 13879/28080 [27:25:40<28:01:16,  7.10s/it]
 49%|████▉     | 13880/28080 [27:25:47<27:56:43,  7.08s/it]
                                                           
{'loss': 0.6301, 'learning_rate': 0.0002667553945459822, 'epoch': 5.93}

 49%|████▉     | 13880/28080 [27:25:47<27:56:43,  7.08s/it]
 49%|████▉     | 13881/28080 [27:25:54<27:58:41,  7.09s/it]
                                                           
{'loss': 0.6478, 'learning_rate': 0.0002667266235634871, 'epoch': 5.93}

 49%|████▉     | 13881/28080 [27:25:54<27:58:41,  7.09s/it]
 49%|████▉     | 13882/28080 [27:26:02<28:00:58,  7.10s/it]
                                                           
{'loss': 0.5983, 'learning_rate': 0.00026669785235846147, 'epoch': 5.93}

 49%|████▉     | 13882/28080 [27:26:02<28:00:58,  7.10s/it]
 49%|████▉     | 13883/28080 [27:26:09<28:01:18,  7.11s/it]
                                                           
{'loss': 0.6172, 'learning_rate': 0.0002666690809312881, 'epoch': 5.93}

 49%|████▉     | 13883/28080 [27:26:09<28:01:18,  7.11s/it]
 49%|████▉     | 13884/28080 [27:26:16<27:58:43,  7.10s/it]
                                                           
{'loss': 0.602, 'learning_rate': 0.0002666403092823499, 'epoch': 5.93}

 49%|████▉     | 13884/28080 [27:26:16<27:58:43,  7.10s/it]
 49%|████▉     | 13885/28080 [27:26:23<28:07:27,  7.13s/it]
                                                           
{'loss': 0.5963, 'learning_rate': 0.00026661153741202947, 'epoch': 5.93}

 49%|████▉     | 13885/28080 [27:26:23<28:07:27,  7.13s/it]
 49%|████▉     | 13886/28080 [27:26:30<28:01:42,  7.11s/it]
                                                           
{'loss': 0.607, 'learning_rate': 0.0002665827653207098, 'epoch': 5.93}

 49%|████▉     | 13886/28080 [27:26:30<28:01:42,  7.11s/it]
 49%|████▉     | 13887/28080 [27:26:37<27:52:11,  7.07s/it]
                                                           
{'loss': 0.6069, 'learning_rate': 0.0002665539930087734, 'epoch': 5.93}

 49%|████▉     | 13887/28080 [27:26:37<27:52:11,  7.07s/it]
 49%|████▉     | 13888/28080 [27:26:44<27:57:32,  7.09s/it]
                                                           
{'loss': 0.6066, 'learning_rate': 0.0002665252204766033, 'epoch': 5.93}

 49%|████▉     | 13888/28080 [27:26:44<27:57:32,  7.09s/it]
 49%|████▉     | 13889/28080 [27:26:51<27:55:29,  7.08s/it]
                                                           
{'loss': 0.6154, 'learning_rate': 0.0002664964477245822, 'epoch': 5.93}

 49%|████▉     | 13889/28080 [27:26:51<27:55:29,  7.08s/it]
 49%|████▉     | 13890/28080 [27:26:58<27:59:39,  7.10s/it]
                                                           
{'loss': 0.6185, 'learning_rate': 0.0002664676747530928, 'epoch': 5.93}

 49%|████▉     | 13890/28080 [27:26:58<27:59:39,  7.10s/it]
 49%|████▉     | 13891/28080 [27:27:05<28:04:29,  7.12s/it]
                                                           
{'loss': 0.6154, 'learning_rate': 0.000266438901562518, 'epoch': 5.93}

 49%|████▉     | 13891/28080 [27:27:05<28:04:29,  7.12s/it]
 49%|████▉     | 13892/28080 [27:27:13<28:09:45,  7.15s/it]
                                                           
{'loss': 0.6089, 'learning_rate': 0.00026641012815324064, 'epoch': 5.93}

 49%|████▉     | 13892/28080 [27:27:13<28:09:45,  7.15s/it]
 49%|████▉     | 13893/28080 [27:27:20<28:06:55,  7.13s/it]
                                                           
{'loss': 0.6262, 'learning_rate': 0.0002663813545256434, 'epoch': 5.93}

 49%|████▉     | 13893/28080 [27:27:20<28:06:55,  7.13s/it]
 49%|████▉     | 13894/28080 [27:27:27<28:07:28,  7.14s/it]
                                                           
{'loss': 0.6308, 'learning_rate': 0.00026635258068010917, 'epoch': 5.94}

 49%|████▉     | 13894/28080 [27:27:27<28:07:28,  7.14s/it]
 49%|████▉     | 13895/28080 [27:27:34<28:04:24,  7.12s/it]
                                                           
{'loss': 0.5945, 'learning_rate': 0.0002663238066170207, 'epoch': 5.94}

 49%|████▉     | 13895/28080 [27:27:34<28:04:24,  7.12s/it]
 49%|████▉     | 13896/28080 [27:27:41<28:04:53,  7.13s/it]
                                                           
{'loss': 0.6181, 'learning_rate': 0.00026629503233676076, 'epoch': 5.94}

 49%|████▉     | 13896/28080 [27:27:41<28:04:53,  7.13s/it]
 49%|████▉     | 13897/28080 [27:27:48<28:04:00,  7.12s/it]
                                                           
{'loss': 0.6316, 'learning_rate': 0.00026626625783971234, 'epoch': 5.94}

 49%|████▉     | 13897/28080 [27:27:48<28:04:00,  7.12s/it]
 49%|████▉     | 13898/28080 [27:27:55<28:01:22,  7.11s/it]
                                                           
{'loss': 0.6282, 'learning_rate': 0.0002662374831262581, 'epoch': 5.94}

 49%|████▉     | 13898/28080 [27:27:55<28:01:22,  7.11s/it]
 49%|████▉     | 13899/28080 [27:28:03<28:02:06,  7.12s/it]
                                                           
{'loss': 0.6285, 'learning_rate': 0.0002662087081967808, 'epoch': 5.94}

 49%|████▉     | 13899/28080 [27:28:03<28:02:06,  7.12s/it]
 50%|████▉     | 13900/28080 [27:28:10<27:57:32,  7.10s/it]
                                                           
{'loss': 0.612, 'learning_rate': 0.00026617993305166345, 'epoch': 5.94}

 50%|████▉     | 13900/28080 [27:28:10<27:57:32,  7.10s/it]
 50%|████▉     | 13901/28080 [27:28:17<27:59:07,  7.11s/it]
                                                           
{'loss': 0.6193, 'learning_rate': 0.0002661511576912888, 'epoch': 5.94}

 50%|████▉     | 13901/28080 [27:28:17<27:59:07,  7.11s/it]
 50%|████▉     | 13902/28080 [27:28:24<28:01:17,  7.12s/it]
                                                           
{'loss': 0.6319, 'learning_rate': 0.00026612238211603964, 'epoch': 5.94}

 50%|████▉     | 13902/28080 [27:28:24<28:01:17,  7.12s/it]
 50%|████▉     | 13903/28080 [27:28:31<27:59:50,  7.11s/it]
                                                           
{'loss': 0.6218, 'learning_rate': 0.0002660936063262988, 'epoch': 5.94}

 50%|████▉     | 13903/28080 [27:28:31<27:59:50,  7.11s/it]
 50%|████▉     | 13904/28080 [27:28:38<27:59:13,  7.11s/it]
                                                           
{'loss': 0.6344, 'learning_rate': 0.0002660648303224491, 'epoch': 5.94}

 50%|████▉     | 13904/28080 [27:28:38<27:59:13,  7.11s/it]
 50%|████▉     | 13905/28080 [27:28:45<27:58:12,  7.10s/it]
                                                           
{'loss': 0.6319, 'learning_rate': 0.0002660360541048735, 'epoch': 5.94}

 50%|████▉     | 13905/28080 [27:28:45<27:58:12,  7.10s/it]
 50%|████▉     | 13906/28080 [27:28:52<28:03:41,  7.13s/it]
                                                           
{'loss': 0.6308, 'learning_rate': 0.00026600727767395465, 'epoch': 5.94}

 50%|████▉     | 13906/28080 [27:28:52<28:03:41,  7.13s/it]
 50%|████▉     | 13907/28080 [27:28:59<28:00:29,  7.11s/it]
                                                           
{'loss': 0.6185, 'learning_rate': 0.00026597850103007555, 'epoch': 5.94}

 50%|████▉     | 13907/28080 [27:28:59<28:00:29,  7.11s/it]
 50%|████▉     | 13908/28080 [27:29:06<27:59:23,  7.11s/it]
                                                           
{'loss': 0.6063, 'learning_rate': 0.00026594972417361894, 'epoch': 5.94}

 50%|████▉     | 13908/28080 [27:29:06<27:59:23,  7.11s/it]
 50%|████▉     | 13909/28080 [27:29:14<27:57:35,  7.10s/it]
                                                           
{'loss': 0.6035, 'learning_rate': 0.00026592094710496775, 'epoch': 5.94}

 50%|████▉     | 13909/28080 [27:29:14<27:57:35,  7.10s/it]
 50%|████▉     | 13910/28080 [27:29:21<27:56:36,  7.10s/it]
                                                           
{'loss': 0.6217, 'learning_rate': 0.00026589216982450477, 'epoch': 5.94}

 50%|████▉     | 13910/28080 [27:29:21<27:56:36,  7.10s/it]
 50%|████▉     | 13911/28080 [27:29:28<27:54:00,  7.09s/it]
                                                           
{'loss': 0.627, 'learning_rate': 0.0002658633923326128, 'epoch': 5.94}

 50%|████▉     | 13911/28080 [27:29:28<27:54:00,  7.09s/it]
 50%|████▉     | 13912/28080 [27:29:35<27:53:17,  7.09s/it]
                                                           
{'loss': 0.6327, 'learning_rate': 0.00026583461462967485, 'epoch': 5.94}

 50%|████▉     | 13912/28080 [27:29:35<27:53:17,  7.09s/it]
 50%|████▉     | 13913/28080 [27:29:42<28:03:36,  7.13s/it]
                                                           
{'loss': 0.6349, 'learning_rate': 0.0002658058367160737, 'epoch': 5.94}

 50%|████▉     | 13913/28080 [27:29:42<28:03:36,  7.13s/it]
 50%|████▉     | 13914/28080 [27:29:49<27:59:58,  7.12s/it]
                                                           
{'loss': 0.6283, 'learning_rate': 0.0002657770585921921, 'epoch': 5.94}

 50%|████▉     | 13914/28080 [27:29:49<27:59:58,  7.12s/it]
 50%|████▉     | 13915/28080 [27:29:56<27:58:53,  7.11s/it]
                                                           
{'loss': 0.6366, 'learning_rate': 0.00026574828025841305, 'epoch': 5.94}

 50%|████▉     | 13915/28080 [27:29:56<27:58:53,  7.11s/it]
 50%|████▉     | 13916/28080 [27:30:03<27:56:37,  7.10s/it]
                                                           
{'loss': 0.657, 'learning_rate': 0.0002657195017151194, 'epoch': 5.94}

 50%|████▉     | 13916/28080 [27:30:03<27:56:37,  7.10s/it]
 50%|████▉     | 13917/28080 [27:30:10<27:51:58,  7.08s/it]
                                                           
{'loss': 0.6197, 'learning_rate': 0.00026569072296269396, 'epoch': 5.95}

 50%|████▉     | 13917/28080 [27:30:10<27:51:58,  7.08s/it]
 50%|████▉     | 13918/28080 [27:30:17<27:51:10,  7.08s/it]
                                                           
{'loss': 0.6165, 'learning_rate': 0.0002656619440015197, 'epoch': 5.95}

 50%|████▉     | 13918/28080 [27:30:17<27:51:10,  7.08s/it]
 50%|████▉     | 13919/28080 [27:30:25<27:52:57,  7.09s/it]
                                                           
{'loss': 0.6305, 'learning_rate': 0.0002656331648319793, 'epoch': 5.95}

 50%|████▉     | 13919/28080 [27:30:25<27:52:57,  7.09s/it]
 50%|████▉     | 13920/28080 [27:30:32<28:04:27,  7.14s/it]
                                                           
{'loss': 0.6072, 'learning_rate': 0.0002656043854544559, 'epoch': 5.95}

 50%|████▉     | 13920/28080 [27:30:32<28:04:27,  7.14s/it]
 50%|████▉     | 13921/28080 [27:30:39<28:02:00,  7.13s/it]
                                                           
{'loss': 0.6197, 'learning_rate': 0.0002655756058693322, 'epoch': 5.95}

 50%|████▉     | 13921/28080 [27:30:39<28:02:00,  7.13s/it]
 50%|████▉     | 13922/28080 [27:30:46<28:06:30,  7.15s/it]
                                                           
{'loss': 0.6165, 'learning_rate': 0.0002655468260769912, 'epoch': 5.95}

 50%|████▉     | 13922/28080 [27:30:46<28:06:30,  7.15s/it]
 50%|████▉     | 13923/28080 [27:30:53<28:06:39,  7.15s/it]
                                                           
{'loss': 0.6253, 'learning_rate': 0.0002655180460778156, 'epoch': 5.95}

 50%|████▉     | 13923/28080 [27:30:53<28:06:39,  7.15s/it]
 50%|████▉     | 13924/28080 [27:31:00<28:04:24,  7.14s/it]
                                                           
{'loss': 0.6064, 'learning_rate': 0.0002654892658721884, 'epoch': 5.95}

 50%|████▉     | 13924/28080 [27:31:00<28:04:24,  7.14s/it]
 50%|████▉     | 13925/28080 [27:31:07<28:03:35,  7.14s/it]
                                                           
{'loss': 0.6162, 'learning_rate': 0.00026546048546049263, 'epoch': 5.95}

 50%|████▉     | 13925/28080 [27:31:07<28:03:35,  7.14s/it]
 50%|████▉     | 13926/28080 [27:31:15<28:06:53,  7.15s/it]
                                                           
{'loss': 0.6209, 'learning_rate': 0.00026543170484311096, 'epoch': 5.95}

 50%|████▉     | 13926/28080 [27:31:15<28:06:53,  7.15s/it]
 50%|████▉     | 13927/28080 [27:31:22<28:02:32,  7.13s/it]
                                                           
{'loss': 0.6263, 'learning_rate': 0.00026540292402042645, 'epoch': 5.95}

 50%|████▉     | 13927/28080 [27:31:22<28:02:32,  7.13s/it]
 50%|████▉     | 13928/28080 [27:31:29<27:58:21,  7.12s/it]
                                                           
{'loss': 0.6258, 'learning_rate': 0.0002653741429928218, 'epoch': 5.95}

 50%|████▉     | 13928/28080 [27:31:29<27:58:21,  7.12s/it]
 50%|████▉     | 13929/28080 [27:31:36<28:01:23,  7.13s/it]
                                                           
{'loss': 0.6114, 'learning_rate': 0.00026534536176068017, 'epoch': 5.95}

 50%|████▉     | 13929/28080 [27:31:36<28:01:23,  7.13s/it]
 50%|████▉     | 13930/28080 [27:31:43<27:53:32,  7.10s/it]
                                                           
{'loss': 0.6021, 'learning_rate': 0.0002653165803243843, 'epoch': 5.95}

 50%|████▉     | 13930/28080 [27:31:43<27:53:32,  7.10s/it]
 50%|████▉     | 13931/28080 [27:31:50<27:51:01,  7.09s/it]
                                                           
{'loss': 0.6253, 'learning_rate': 0.0002652877986843171, 'epoch': 5.95}

 50%|████▉     | 13931/28080 [27:31:50<27:51:01,  7.09s/it]
 50%|████▉     | 13932/28080 [27:31:57<27:55:54,  7.11s/it]
                                                           
{'loss': 0.6078, 'learning_rate': 0.0002652590168408615, 'epoch': 5.95}

 50%|████▉     | 13932/28080 [27:31:57<27:55:54,  7.11s/it]
 50%|████▉     | 13933/28080 [27:32:04<27:54:45,  7.10s/it]
                                                           
{'loss': 0.6144, 'learning_rate': 0.0002652302347944004, 'epoch': 5.95}

 50%|████▉     | 13933/28080 [27:32:04<27:54:45,  7.10s/it]
 50%|████▉     | 13934/28080 [27:32:11<27:44:43,  7.06s/it]
                                                           
{'loss': 0.6313, 'learning_rate': 0.0002652014525453168, 'epoch': 5.95}

 50%|████▉     | 13934/28080 [27:32:11<27:44:43,  7.06s/it]
 50%|████▉     | 13935/28080 [27:32:18<27:49:28,  7.08s/it]
                                                           
{'loss': 0.6195, 'learning_rate': 0.0002651726700939935, 'epoch': 5.95}

 50%|████▉     | 13935/28080 [27:32:18<27:49:28,  7.08s/it]
 50%|████▉     | 13936/28080 [27:32:25<27:44:34,  7.06s/it]
                                                           
{'loss': 0.6456, 'learning_rate': 0.00026514388744081356, 'epoch': 5.95}

 50%|████▉     | 13936/28080 [27:32:25<27:44:34,  7.06s/it]
 50%|████▉     | 13937/28080 [27:32:33<27:47:24,  7.07s/it]
                                                           
{'loss': 0.6247, 'learning_rate': 0.0002651151045861598, 'epoch': 5.95}

 50%|████▉     | 13937/28080 [27:32:33<27:47:24,  7.07s/it]
 50%|████▉     | 13938/28080 [27:32:40<27:56:09,  7.11s/it]
                                                           
{'loss': 0.622, 'learning_rate': 0.00026508632153041513, 'epoch': 5.95}

 50%|████▉     | 13938/28080 [27:32:40<27:56:09,  7.11s/it]
 50%|████▉     | 13939/28080 [27:32:47<27:50:11,  7.09s/it]
                                                           
{'loss': 0.6174, 'learning_rate': 0.0002650575382739626, 'epoch': 5.95}

 50%|████▉     | 13939/28080 [27:32:47<27:50:11,  7.09s/it]
 50%|████▉     | 13940/28080 [27:32:54<27:55:37,  7.11s/it]
                                                           
{'loss': 0.6311, 'learning_rate': 0.00026502875481718494, 'epoch': 5.96}

 50%|████▉     | 13940/28080 [27:32:54<27:55:37,  7.11s/it]
 50%|████▉     | 13941/28080 [27:33:01<27:55:59,  7.11s/it]
                                                           
{'loss': 0.6264, 'learning_rate': 0.0002649999711604653, 'epoch': 5.96}

 50%|████▉     | 13941/28080 [27:33:01<27:55:59,  7.11s/it]
 50%|████▉     | 13942/28080 [27:33:08<27:57:40,  7.12s/it]
                                                           
{'loss': 0.6118, 'learning_rate': 0.0002649711873041864, 'epoch': 5.96}

 50%|████▉     | 13942/28080 [27:33:08<27:57:40,  7.12s/it]
 50%|████▉     | 13943/28080 [27:33:15<28:05:55,  7.16s/it]
                                                           
{'loss': 0.6001, 'learning_rate': 0.00026494240324873133, 'epoch': 5.96}

 50%|████▉     | 13943/28080 [27:33:15<28:05:55,  7.16s/it]
 50%|████▉     | 13944/28080 [27:33:23<28:08:06,  7.17s/it]
                                                           
{'loss': 0.5905, 'learning_rate': 0.0002649136189944831, 'epoch': 5.96}

 50%|████▉     | 13944/28080 [27:33:23<28:08:06,  7.17s/it]
 50%|████▉     | 13945/28080 [27:33:30<28:03:23,  7.15s/it]
                                                           
{'loss': 0.6344, 'learning_rate': 0.00026488483454182443, 'epoch': 5.96}

 50%|████▉     | 13945/28080 [27:33:30<28:03:23,  7.15s/it]
 50%|████▉     | 13946/28080 [27:33:37<28:03:26,  7.15s/it]
                                                           
{'loss': 0.6195, 'learning_rate': 0.0002648560498911385, 'epoch': 5.96}

 50%|████▉     | 13946/28080 [27:33:37<28:03:26,  7.15s/it]
 50%|████▉     | 13947/28080 [27:33:44<27:56:18,  7.12s/it]
                                                           
{'loss': 0.6089, 'learning_rate': 0.00026482726504280804, 'epoch': 5.96}

 50%|████▉     | 13947/28080 [27:33:44<27:56:18,  7.12s/it]
 50%|████▉     | 13948/28080 [27:33:51<28:03:11,  7.15s/it]
                                                           
{'loss': 0.6295, 'learning_rate': 0.0002647984799972162, 'epoch': 5.96}

 50%|████▉     | 13948/28080 [27:33:51<28:03:11,  7.15s/it]
 50%|████▉     | 13949/28080 [27:33:58<28:06:58,  7.16s/it]
                                                           
{'loss': 0.6111, 'learning_rate': 0.00026476969475474585, 'epoch': 5.96}

 50%|████▉     | 13949/28080 [27:33:58<28:06:58,  7.16s/it]
 50%|████▉     | 13950/28080 [27:34:05<27:56:58,  7.12s/it]
                                                           
{'loss': 0.6227, 'learning_rate': 0.00026474090931577986, 'epoch': 5.96}

 50%|████▉     | 13950/28080 [27:34:05<27:56:58,  7.12s/it]
 50%|████▉     | 13951/28080 [27:34:12<27:56:10,  7.12s/it]
                                                           
{'loss': 0.6193, 'learning_rate': 0.0002647121236807014, 'epoch': 5.96}

 50%|████▉     | 13951/28080 [27:34:12<27:56:10,  7.12s/it]
 50%|████▉     | 13952/28080 [27:34:20<27:52:57,  7.10s/it]
                                                           
{'loss': 0.6164, 'learning_rate': 0.0002646833378498932, 'epoch': 5.96}

 50%|████▉     | 13952/28080 [27:34:20<27:52:57,  7.10s/it]
 50%|████▉     | 13953/28080 [27:34:27<27:53:42,  7.11s/it]
                                                           
{'loss': 0.6234, 'learning_rate': 0.0002646545518237384, 'epoch': 5.96}

 50%|████▉     | 13953/28080 [27:34:27<27:53:42,  7.11s/it]
 50%|████▉     | 13954/28080 [27:34:34<27:52:55,  7.11s/it]
                                                           
{'loss': 0.6266, 'learning_rate': 0.0002646257656026199, 'epoch': 5.96}

 50%|████▉     | 13954/28080 [27:34:34<27:52:55,  7.11s/it]
 50%|████▉     | 13955/28080 [27:34:41<27:50:58,  7.10s/it]
                                                           
{'loss': 0.6192, 'learning_rate': 0.00026459697918692065, 'epoch': 5.96}

 50%|████▉     | 13955/28080 [27:34:41<27:50:58,  7.10s/it]
 50%|████▉     | 13956/28080 [27:34:48<27:58:03,  7.13s/it]
                                                           
{'loss': 0.6087, 'learning_rate': 0.0002645681925770237, 'epoch': 5.96}

 50%|████▉     | 13956/28080 [27:34:48<27:58:03,  7.13s/it]
 50%|████▉     | 13957/28080 [27:34:55<27:50:04,  7.10s/it]
                                                           
{'loss': 0.6198, 'learning_rate': 0.0002645394057733119, 'epoch': 5.96}

 50%|████▉     | 13957/28080 [27:34:55<27:50:04,  7.10s/it]
 50%|████▉     | 13958/28080 [27:35:02<27:58:44,  7.13s/it]
                                                           
{'loss': 0.6014, 'learning_rate': 0.00026451061877616846, 'epoch': 5.96}

 50%|████▉     | 13958/28080 [27:35:02<27:58:44,  7.13s/it]
 50%|████▉     | 13959/28080 [27:35:09<27:53:34,  7.11s/it]
                                                           
{'loss': 0.6263, 'learning_rate': 0.00026448183158597603, 'epoch': 5.96}

 50%|████▉     | 13959/28080 [27:35:09<27:53:34,  7.11s/it]
 50%|████▉     | 13960/28080 [27:35:16<27:51:21,  7.10s/it]
                                                           
{'loss': 0.6187, 'learning_rate': 0.0002644530442031179, 'epoch': 5.96}

 50%|████▉     | 13960/28080 [27:35:16<27:51:21,  7.10s/it]
 50%|████▉     | 13961/28080 [27:35:24<27:56:29,  7.12s/it]
                                                           
{'loss': 0.6033, 'learning_rate': 0.00026442425662797687, 'epoch': 5.96}

 50%|████▉     | 13961/28080 [27:35:24<27:56:29,  7.12s/it]
 50%|████▉     | 13962/28080 [27:35:31<28:04:12,  7.16s/it]
                                                           
{'loss': 0.6146, 'learning_rate': 0.000264395468860936, 'epoch': 5.96}

 50%|████▉     | 13962/28080 [27:35:31<28:04:12,  7.16s/it]
 50%|████▉     | 13963/28080 [27:35:38<28:05:01,  7.16s/it]
                                                           
{'loss': 0.6156, 'learning_rate': 0.0002643666809023783, 'epoch': 5.96}

 50%|████▉     | 13963/28080 [27:35:38<28:05:01,  7.16s/it]
 50%|████▉     | 13964/28080 [27:35:45<28:00:38,  7.14s/it]
                                                           
{'loss': 0.6398, 'learning_rate': 0.0002643378927526867, 'epoch': 5.97}

 50%|████▉     | 13964/28080 [27:35:45<28:00:38,  7.14s/it]
 50%|████▉     | 13965/28080 [27:35:52<28:02:43,  7.15s/it]
                                                           
{'loss': 0.6227, 'learning_rate': 0.0002643091044122442, 'epoch': 5.97}

 50%|████▉     | 13965/28080 [27:35:52<28:02:43,  7.15s/it]
 50%|████▉     | 13966/28080 [27:35:59<28:01:36,  7.15s/it]
                                                           
{'loss': 0.6312, 'learning_rate': 0.0002642803158814338, 'epoch': 5.97}

 50%|████▉     | 13966/28080 [27:35:59<28:01:36,  7.15s/it]
 50%|████▉     | 13967/28080 [27:36:06<27:58:28,  7.14s/it]
                                                           
{'loss': 0.6145, 'learning_rate': 0.00026425152716063856, 'epoch': 5.97}

 50%|████▉     | 13967/28080 [27:36:06<27:58:28,  7.14s/it]
 50%|████▉     | 13968/28080 [27:36:14<27:57:21,  7.13s/it]
                                                           
{'loss': 0.6078, 'learning_rate': 0.00026422273825024153, 'epoch': 5.97}

 50%|████▉     | 13968/28080 [27:36:14<27:57:21,  7.13s/it]
 50%|████▉     | 13969/28080 [27:36:21<27:48:53,  7.10s/it]
                                                           
{'loss': 0.6164, 'learning_rate': 0.0002641939491506256, 'epoch': 5.97}

 50%|████▉     | 13969/28080 [27:36:21<27:48:53,  7.10s/it]
 50%|████▉     | 13970/28080 [27:36:28<27:51:29,  7.11s/it]
                                                           
{'loss': 0.6171, 'learning_rate': 0.00026416515986217375, 'epoch': 5.97}

 50%|████▉     | 13970/28080 [27:36:28<27:51:29,  7.11s/it]
 50%|████▉     | 13971/28080 [27:36:35<27:52:54,  7.11s/it]
                                                           
{'loss': 0.6153, 'learning_rate': 0.0002641363703852691, 'epoch': 5.97}

 50%|████▉     | 13971/28080 [27:36:35<27:52:54,  7.11s/it]
 50%|████▉     | 13972/28080 [27:36:42<27:51:14,  7.11s/it]
                                                           
{'loss': 0.6245, 'learning_rate': 0.0002641075807202947, 'epoch': 5.97}

 50%|████▉     | 13972/28080 [27:36:42<27:51:14,  7.11s/it]
 50%|████▉     | 13973/28080 [27:36:49<27:59:12,  7.14s/it]
                                                           
{'loss': 0.6085, 'learning_rate': 0.0002640787908676334, 'epoch': 5.97}

 50%|████▉     | 13973/28080 [27:36:49<27:59:12,  7.14s/it]
 50%|████▉     | 13974/28080 [27:36:56<27:51:14,  7.11s/it]
                                                           
{'loss': 0.6076, 'learning_rate': 0.0002640500008276683, 'epoch': 5.97}

 50%|████▉     | 13974/28080 [27:36:56<27:51:14,  7.11s/it]
 50%|████▉     | 13975/28080 [27:37:03<27:54:55,  7.12s/it]
                                                           
{'loss': 0.6004, 'learning_rate': 0.0002640212106007825, 'epoch': 5.97}

 50%|████▉     | 13975/28080 [27:37:03<27:54:55,  7.12s/it]
 50%|████▉     | 13976/28080 [27:37:11<27:55:32,  7.13s/it]
                                                           
{'loss': 0.6162, 'learning_rate': 0.0002639924201873589, 'epoch': 5.97}

 50%|████▉     | 13976/28080 [27:37:11<27:55:32,  7.13s/it]
 50%|████▉     | 13977/28080 [27:37:18<27:50:18,  7.11s/it]
                                                           
{'loss': 0.6294, 'learning_rate': 0.00026396362958778065, 'epoch': 5.97}

 50%|████▉     | 13977/28080 [27:37:18<27:50:18,  7.11s/it]
 50%|████▉     | 13978/28080 [27:37:25<27:52:27,  7.12s/it]
                                                           
{'loss': 0.6187, 'learning_rate': 0.00026393483880243063, 'epoch': 5.97}

 50%|████▉     | 13978/28080 [27:37:25<27:52:27,  7.12s/it]
 50%|████▉     | 13979/28080 [27:37:32<27:58:24,  7.14s/it]
                                                           
{'loss': 0.5952, 'learning_rate': 0.00026390604783169206, 'epoch': 5.97}

 50%|████▉     | 13979/28080 [27:37:32<27:58:24,  7.14s/it]
 50%|████▉     | 13980/28080 [27:37:39<27:51:48,  7.11s/it]
                                                           
{'loss': 0.6186, 'learning_rate': 0.0002638772566759478, 'epoch': 5.97}

 50%|████▉     | 13980/28080 [27:37:39<27:51:48,  7.11s/it]
 50%|████▉     | 13981/28080 [27:37:46<27:54:11,  7.12s/it]
                                                           
{'loss': 0.618, 'learning_rate': 0.00026384846533558095, 'epoch': 5.97}

 50%|████▉     | 13981/28080 [27:37:46<27:54:11,  7.12s/it]
 50%|████▉     | 13982/28080 [27:37:53<27:44:59,  7.09s/it]
                                                           
{'loss': 0.6541, 'learning_rate': 0.0002638196738109746, 'epoch': 5.97}

 50%|████▉     | 13982/28080 [27:37:53<27:44:59,  7.09s/it]
 50%|████▉     | 13983/28080 [27:38:00<27:49:33,  7.11s/it]
                                                           
{'loss': 0.5925, 'learning_rate': 0.00026379088210251166, 'epoch': 5.97}

 50%|████▉     | 13983/28080 [27:38:00<27:49:33,  7.11s/it]
 50%|████▉     | 13984/28080 [27:38:07<27:43:41,  7.08s/it]
                                                           
{'loss': 0.6299, 'learning_rate': 0.0002637620902105754, 'epoch': 5.97}

 50%|████▉     | 13984/28080 [27:38:07<27:43:41,  7.08s/it]
 50%|████▉     | 13985/28080 [27:38:14<27:45:40,  7.09s/it]
                                                           
{'loss': 0.6189, 'learning_rate': 0.00026373329813554863, 'epoch': 5.97}

 50%|████▉     | 13985/28080 [27:38:14<27:45:40,  7.09s/it]
 50%|████▉     | 13986/28080 [27:38:22<27:49:53,  7.11s/it]
                                                           
{'loss': 0.609, 'learning_rate': 0.0002637045058778145, 'epoch': 5.97}

 50%|████▉     | 13986/28080 [27:38:22<27:49:53,  7.11s/it]
 50%|████▉     | 13987/28080 [27:38:29<27:50:20,  7.11s/it]
                                                           
{'loss': 0.6319, 'learning_rate': 0.0002636757134377561, 'epoch': 5.98}

 50%|████▉     | 13987/28080 [27:38:29<27:50:20,  7.11s/it]
 50%|████▉     | 13988/28080 [27:38:36<27:54:13,  7.13s/it]
                                                           
{'loss': 0.6279, 'learning_rate': 0.0002636469208157564, 'epoch': 5.98}

 50%|████▉     | 13988/28080 [27:38:36<27:54:13,  7.13s/it]
 50%|████▉     | 13989/28080 [27:38:43<27:56:13,  7.14s/it]
                                                           
{'loss': 0.6121, 'learning_rate': 0.0002636181280121986, 'epoch': 5.98}

 50%|████▉     | 13989/28080 [27:38:43<27:56:13,  7.14s/it]
 50%|████▉     | 13990/28080 [27:38:50<27:59:41,  7.15s/it]
                                                           
{'loss': 0.6241, 'learning_rate': 0.0002635893350274655, 'epoch': 5.98}

 50%|████▉     | 13990/28080 [27:38:50<27:59:41,  7.15s/it]
 50%|████▉     | 13991/28080 [27:38:57<27:55:59,  7.14s/it]
                                                           
{'loss': 0.6138, 'learning_rate': 0.0002635605418619404, 'epoch': 5.98}

 50%|████▉     | 13991/28080 [27:38:57<27:55:59,  7.14s/it]
 50%|████▉     | 13992/28080 [27:39:05<28:02:43,  7.17s/it]
                                                           
{'loss': 0.609, 'learning_rate': 0.0002635317485160063, 'epoch': 5.98}

 50%|████▉     | 13992/28080 [27:39:05<28:02:43,  7.17s/it]
 50%|████▉     | 13993/28080 [27:39:12<28:02:11,  7.16s/it]
                                                           
{'loss': 0.6158, 'learning_rate': 0.0002635029549900462, 'epoch': 5.98}

 50%|████▉     | 13993/28080 [27:39:12<28:02:11,  7.16s/it]
 50%|████▉     | 13994/28080 [27:39:19<28:01:39,  7.16s/it]
                                                           
{'loss': 0.6033, 'learning_rate': 0.00026347416128444324, 'epoch': 5.98}

 50%|████▉     | 13994/28080 [27:39:19<28:01:39,  7.16s/it]
 50%|████▉     | 13995/28080 [27:39:26<28:02:35,  7.17s/it]
                                                           
{'loss': 0.5973, 'learning_rate': 0.00026344536739958044, 'epoch': 5.98}

 50%|████▉     | 13995/28080 [27:39:26<28:02:35,  7.17s/it]
 50%|████▉     | 13996/28080 [27:39:33<28:00:36,  7.16s/it]
                                                           
{'loss': 0.6003, 'learning_rate': 0.0002634165733358409, 'epoch': 5.98}

 50%|████▉     | 13996/28080 [27:39:33<28:00:36,  7.16s/it]
 50%|████▉     | 13997/28080 [27:39:40<28:01:34,  7.16s/it]
                                                           
{'loss': 0.6047, 'learning_rate': 0.00026338777909360773, 'epoch': 5.98}

 50%|████▉     | 13997/28080 [27:39:40<28:01:34,  7.16s/it]
 50%|████▉     | 13998/28080 [27:39:48<28:01:25,  7.16s/it]
                                                           
{'loss': 0.6052, 'learning_rate': 0.00026335898467326393, 'epoch': 5.98}

 50%|████▉     | 13998/28080 [27:39:48<28:01:25,  7.16s/it]
 50%|████▉     | 13999/28080 [27:39:55<27:56:51,  7.15s/it]
                                                           
{'loss': 0.6227, 'learning_rate': 0.00026333019007519266, 'epoch': 5.98}

 50%|████▉     | 13999/28080 [27:39:55<27:56:51,  7.15s/it]
 50%|████▉     | 14000/28080 [27:40:02<27:54:34,  7.14s/it]
                                                           
{'loss': 0.6391, 'learning_rate': 0.00026330139529977687, 'epoch': 5.98}

 50%|████▉     | 14000/28080 [27:40:02<27:54:34,  7.14s/it]
 50%|████▉     | 14001/28080 [27:40:09<27:48:01,  7.11s/it]
                                                           
{'loss': 0.6255, 'learning_rate': 0.0002632726003473999, 'epoch': 5.98}

 50%|████▉     | 14001/28080 [27:40:09<27:48:01,  7.11s/it]
 50%|████▉     | 14002/28080 [27:40:16<27:56:41,  7.15s/it]
                                                           
{'loss': 0.6186, 'learning_rate': 0.00026324380521844447, 'epoch': 5.98}

 50%|████▉     | 14002/28080 [27:40:16<27:56:41,  7.15s/it]
 50%|████▉     | 14003/28080 [27:40:23<27:55:23,  7.14s/it]
                                                           
{'loss': 0.6314, 'learning_rate': 0.00026321500991329406, 'epoch': 5.98}

 50%|████▉     | 14003/28080 [27:40:23<27:55:23,  7.14s/it]
 50%|████▉     | 14004/28080 [27:40:30<27:53:20,  7.13s/it]
                                                           
{'loss': 0.6289, 'learning_rate': 0.0002631862144323315, 'epoch': 5.98}

 50%|████▉     | 14004/28080 [27:40:30<27:53:20,  7.13s/it]
 50%|████▉     | 14005/28080 [27:40:37<27:52:05,  7.13s/it]
                                                           
{'loss': 0.6111, 'learning_rate': 0.0002631574187759399, 'epoch': 5.98}

 50%|████▉     | 14005/28080 [27:40:37<27:52:05,  7.13s/it]
 50%|████▉     | 14006/28080 [27:40:44<27:51:28,  7.13s/it]
                                                           
{'loss': 0.6187, 'learning_rate': 0.0002631286229445025, 'epoch': 5.98}

 50%|████▉     | 14006/28080 [27:40:44<27:51:28,  7.13s/it]
 50%|████▉     | 14007/28080 [27:40:52<27:49:18,  7.12s/it]
                                                           
{'loss': 0.6132, 'learning_rate': 0.0002630998269384023, 'epoch': 5.98}

 50%|████▉     | 14007/28080 [27:40:52<27:49:18,  7.12s/it]
 50%|████▉     | 14008/28080 [27:40:59<27:38:22,  7.07s/it]
                                                           
{'loss': 0.6307, 'learning_rate': 0.0002630710307580224, 'epoch': 5.98}

 50%|████▉     | 14008/28080 [27:40:59<27:38:22,  7.07s/it]
 50%|████▉     | 14009/28080 [27:41:06<27:42:46,  7.09s/it]
                                                           
{'loss': 0.5896, 'learning_rate': 0.00026304223440374593, 'epoch': 5.98}

 50%|████▉     | 14009/28080 [27:41:06<27:42:46,  7.09s/it]
 50%|████▉     | 14010/28080 [27:41:13<27:43:27,  7.09s/it]
                                                           
{'loss': 0.6135, 'learning_rate': 0.000263013437875956, 'epoch': 5.98}

 50%|████▉     | 14010/28080 [27:41:13<27:43:27,  7.09s/it]
 50%|████▉     | 14011/28080 [27:41:20<27:41:07,  7.08s/it]
                                                           
{'loss': 0.6337, 'learning_rate': 0.00026298464117503566, 'epoch': 5.99}

 50%|████▉     | 14011/28080 [27:41:20<27:41:07,  7.08s/it]
 50%|████▉     | 14012/28080 [27:41:27<27:44:35,  7.10s/it]
                                                           
{'loss': 0.6108, 'learning_rate': 0.0002629558443013681, 'epoch': 5.99}

 50%|████▉     | 14012/28080 [27:41:27<27:44:35,  7.10s/it]
 50%|████▉     | 14013/28080 [27:41:34<27:40:49,  7.08s/it]
                                                           
{'loss': 0.6279, 'learning_rate': 0.00026292704725533646, 'epoch': 5.99}

 50%|████▉     | 14013/28080 [27:41:34<27:40:49,  7.08s/it]
 50%|████▉     | 14014/28080 [27:41:41<27:45:27,  7.10s/it]
                                                           
{'loss': 0.6276, 'learning_rate': 0.0002628982500373237, 'epoch': 5.99}

 50%|████▉     | 14014/28080 [27:41:41<27:45:27,  7.10s/it]
 50%|████▉     | 14015/28080 [27:41:48<27:46:20,  7.11s/it]
                                                           
{'loss': 0.6062, 'learning_rate': 0.00026286945264771303, 'epoch': 5.99}

 50%|████▉     | 14015/28080 [27:41:48<27:46:20,  7.11s/it]
 50%|████▉     | 14016/28080 [27:41:55<27:47:32,  7.11s/it]
                                                           
{'loss': 0.6077, 'learning_rate': 0.00026284065508688765, 'epoch': 5.99}

 50%|████▉     | 14016/28080 [27:41:55<27:47:32,  7.11s/it]
 50%|████▉     | 14017/28080 [27:42:03<28:01:26,  7.17s/it]
                                                           
{'loss': 0.637, 'learning_rate': 0.0002628118573552305, 'epoch': 5.99}

 50%|████▉     | 14017/28080 [27:42:03<28:01:26,  7.17s/it]
 50%|████▉     | 14018/28080 [27:42:10<27:50:18,  7.13s/it]
                                                           
{'loss': 0.6357, 'learning_rate': 0.00026278305945312487, 'epoch': 5.99}

 50%|████▉     | 14018/28080 [27:42:10<27:50:18,  7.13s/it]
 50%|████▉     | 14019/28080 [27:42:17<27:46:15,  7.11s/it]
                                                           
{'loss': 0.6459, 'learning_rate': 0.0002627542613809538, 'epoch': 5.99}

 50%|████▉     | 14019/28080 [27:42:17<27:46:15,  7.11s/it]
 50%|████▉     | 14020/28080 [27:42:24<27:42:26,  7.09s/it]
                                                           
{'loss': 0.6135, 'learning_rate': 0.0002627254631391005, 'epoch': 5.99}

 50%|████▉     | 14020/28080 [27:42:24<27:42:26,  7.09s/it]
 50%|████▉     | 14021/28080 [27:42:31<27:46:32,  7.11s/it]
                                                           
{'loss': 0.6268, 'learning_rate': 0.0002626966647279479, 'epoch': 5.99}

 50%|████▉     | 14021/28080 [27:42:31<27:46:32,  7.11s/it]
 50%|████▉     | 14022/28080 [27:42:38<27:41:10,  7.09s/it]
                                                           
{'loss': 0.6194, 'learning_rate': 0.00026266786614787934, 'epoch': 5.99}

 50%|████▉     | 14022/28080 [27:42:38<27:41:10,  7.09s/it]
 50%|████▉     | 14023/28080 [27:42:45<27:47:39,  7.12s/it]
                                                           
{'loss': 0.6306, 'learning_rate': 0.00026263906739927795, 'epoch': 5.99}

 50%|████▉     | 14023/28080 [27:42:45<27:47:39,  7.12s/it]
 50%|████▉     | 14024/28080 [27:42:52<27:46:14,  7.11s/it]
                                                           
{'loss': 0.6037, 'learning_rate': 0.0002626102684825267, 'epoch': 5.99}

 50%|████▉     | 14024/28080 [27:42:52<27:46:14,  7.11s/it]
 50%|████▉     | 14025/28080 [27:43:00<27:53:17,  7.14s/it]
                                                           
{'loss': 0.6232, 'learning_rate': 0.00026258146939800897, 'epoch': 5.99}

 50%|████▉     | 14025/28080 [27:43:00<27:53:17,  7.14s/it]
 50%|████▉     | 14026/28080 [27:43:07<27:57:03,  7.16s/it]
                                                           
{'loss': 0.6143, 'learning_rate': 0.00026255267014610765, 'epoch': 5.99}

 50%|████▉     | 14026/28080 [27:43:07<27:57:03,  7.16s/it]
 50%|████▉     | 14027/28080 [27:43:14<27:54:34,  7.15s/it]
                                                           
{'loss': 0.6122, 'learning_rate': 0.0002625238707272061, 'epoch': 5.99}

 50%|████▉     | 14027/28080 [27:43:14<27:54:34,  7.15s/it]
 50%|████▉     | 14028/28080 [27:43:21<27:53:22,  7.15s/it]
                                                           
{'loss': 0.6135, 'learning_rate': 0.0002624950711416873, 'epoch': 5.99}

 50%|████▉     | 14028/28080 [27:43:21<27:53:22,  7.15s/it]
 50%|████▉     | 14029/28080 [27:43:28<27:58:00,  7.17s/it]
                                                           
{'loss': 0.6085, 'learning_rate': 0.0002624662713899345, 'epoch': 5.99}

 50%|████▉     | 14029/28080 [27:43:28<27:58:00,  7.17s/it]
 50%|████▉     | 14030/28080 [27:43:35<27:49:51,  7.13s/it]
                                                           
{'loss': 0.6173, 'learning_rate': 0.0002624374714723308, 'epoch': 5.99}

 50%|████▉     | 14030/28080 [27:43:35<27:49:51,  7.13s/it]
 50%|████▉     | 14031/28080 [27:43:43<27:56:22,  7.16s/it]
                                                           
{'loss': 0.6223, 'learning_rate': 0.0002624086713892594, 'epoch': 5.99}

 50%|████▉     | 14031/28080 [27:43:43<27:56:22,  7.16s/it]
 50%|████▉     | 14032/28080 [27:43:50<27:50:21,  7.13s/it]
                                                           
{'loss': 0.6268, 'learning_rate': 0.00026237987114110346, 'epoch': 5.99}

 50%|████▉     | 14032/28080 [27:43:50<27:50:21,  7.13s/it]
 50%|████▉     | 14033/28080 [27:43:57<27:50:38,  7.14s/it]
                                                           
{'loss': 0.6166, 'learning_rate': 0.000262351070728246, 'epoch': 5.99}

 50%|████▉     | 14033/28080 [27:43:57<27:50:38,  7.14s/it]
 50%|████▉     | 14034/28080 [27:44:04<27:52:17,  7.14s/it]
                                                           
{'loss': 0.6208, 'learning_rate': 0.0002623222701510704, 'epoch': 6.0}

 50%|████▉     | 14034/28080 [27:44:04<27:52:17,  7.14s/it]
 50%|████▉     | 14035/28080 [27:44:11<27:55:34,  7.16s/it]
                                                           
{'loss': 0.622, 'learning_rate': 0.0002622934694099596, 'epoch': 6.0}

 50%|████▉     | 14035/28080 [27:44:11<27:55:34,  7.16s/it]
 50%|████▉     | 14036/28080 [27:44:18<27:52:19,  7.14s/it]
                                                           
{'loss': 0.6293, 'learning_rate': 0.0002622646685052969, 'epoch': 6.0}

 50%|████▉     | 14036/28080 [27:44:18<27:52:19,  7.14s/it]
 50%|████▉     | 14037/28080 [27:44:25<27:49:40,  7.13s/it]
                                                           
{'loss': 0.6081, 'learning_rate': 0.00026223586743746554, 'epoch': 6.0}

 50%|████▉     | 14037/28080 [27:44:25<27:49:40,  7.13s/it]
 50%|████▉     | 14038/28080 [27:44:32<27:50:00,  7.14s/it]
                                                           
{'loss': 0.6244, 'learning_rate': 0.0002622070662068485, 'epoch': 6.0}

 50%|████▉     | 14038/28080 [27:44:32<27:50:00,  7.14s/it]
 50%|████▉     | 14039/28080 [27:44:40<27:45:10,  7.12s/it]
                                                           
{'loss': 0.6044, 'learning_rate': 0.0002621782648138291, 'epoch': 6.0}

 50%|████▉     | 14039/28080 [27:44:40<27:45:10,  7.12s/it]
 50%|█████     | 14040/28080 [27:44:47<27:43:05,  7.11s/it]
                                                           
{'loss': 0.6121, 'learning_rate': 0.00026214946325879036, 'epoch': 6.0}

 50%|█████     | 14040/28080 [27:44:47<27:43:05,  7.11s/it]
 50%|█████     | 14041/28080 [27:44:54<27:37:37,  7.08s/it]
                                                           
{'loss': 0.6114, 'learning_rate': 0.00026212066154211554, 'epoch': 6.0}

 50%|█████     | 14041/28080 [27:44:54<27:37:37,  7.08s/it]
 50%|█████     | 14042/28080 [27:45:01<27:40:00,  7.10s/it]
                                                           
{'loss': 0.6047, 'learning_rate': 0.0002620918596641879, 'epoch': 6.0}

 50%|█████     | 14042/28080 [27:45:01<27:40:00,  7.10s/it]
 50%|█████     | 14043/28080 [27:45:08<27:41:54,  7.10s/it]
                                                           
{'loss': 0.6063, 'learning_rate': 0.0002620630576253905, 'epoch': 6.0}

 50%|█████     | 14043/28080 [27:45:08<27:41:54,  7.10s/it]
 50%|█████     | 14044/28080 [27:45:15<27:45:57,  7.12s/it]
                                                           
{'loss': 0.5979, 'learning_rate': 0.0002620342554261066, 'epoch': 6.0}

 50%|█████     | 14044/28080 [27:45:15<27:45:57,  7.12s/it]
 50%|█████     | 14045/28080 [27:45:22<27:47:18,  7.13s/it]
                                                           
{'loss': 0.6282, 'learning_rate': 0.0002620054530667193, 'epoch': 6.0}

 50%|█████     | 14045/28080 [27:45:22<27:47:18,  7.13s/it]
 50%|█████     | 14046/28080 [27:45:30<28:22:56,  7.28s/it]
                                                           
{'loss': 0.6212, 'learning_rate': 0.00026197665054761185, 'epoch': 6.0}

 50%|█████     | 14046/28080 [27:45:30<28:22:56,  7.28s/it]
 50%|█████     | 14047/28080 [27:45:37<28:09:57,  7.23s/it]
                                                           
{'loss': 0.6326, 'learning_rate': 0.0002619478478691674, 'epoch': 6.0}

 50%|█████     | 14047/28080 [27:45:37<28:09:57,  7.23s/it]
 50%|█████     | 14048/28080 [27:45:44<28:03:47,  7.20s/it]
                                                           
{'loss': 0.6099, 'learning_rate': 0.0002619190450317692, 'epoch': 6.0}

 50%|█████     | 14048/28080 [27:45:44<28:03:47,  7.20s/it]
 50%|█████     | 14049/28080 [27:45:51<27:58:55,  7.18s/it]
                                                           
{'loss': 0.6049, 'learning_rate': 0.0002618902420358004, 'epoch': 6.0}

 50%|█████     | 14049/28080 [27:45:51<27:58:55,  7.18s/it]
 50%|█████     | 14050/28080 [27:45:58<27:52:00,  7.15s/it]
                                                           
{'loss': 0.6142, 'learning_rate': 0.00026186143888164414, 'epoch': 6.0}

 50%|█████     | 14050/28080 [27:45:58<27:52:00,  7.15s/it]
 50%|█████     | 14051/28080 [27:46:05<27:45:55,  7.12s/it]
                                                           
{'loss': 0.6381, 'learning_rate': 0.0002618326355696838, 'epoch': 6.0}

 50%|█████     | 14051/28080 [27:46:05<27:45:55,  7.12s/it]
 50%|█████     | 14052/28080 [27:46:12<27:46:44,  7.13s/it]
                                                           
{'loss': 0.6225, 'learning_rate': 0.0002618038321003023, 'epoch': 6.0}

 50%|█████     | 14052/28080 [27:46:12<27:46:44,  7.13s/it]
 50%|█████     | 14053/28080 [27:46:20<27:54:55,  7.16s/it]
                                                           
{'loss': 0.5985, 'learning_rate': 0.00026177502847388303, 'epoch': 6.0}

 50%|█████     | 14053/28080 [27:46:20<27:54:55,  7.16s/it]
 50%|█████     | 14054/28080 [27:46:27<27:53:34,  7.16s/it]
                                                           
{'loss': 0.6155, 'learning_rate': 0.00026174622469080924, 'epoch': 6.0}

 50%|█████     | 14054/28080 [27:46:27<27:53:34,  7.16s/it]
 50%|█████     | 14055/28080 [27:46:34<27:49:08,  7.14s/it]
                                                           
{'loss': 0.6089, 'learning_rate': 0.0002617174207514639, 'epoch': 6.0}

 50%|█████     | 14055/28080 [27:46:34<27:49:08,  7.14s/it]
 50%|█████     | 14056/28080 [27:46:41<27:44:47,  7.12s/it]
                                                           
{'loss': 0.614, 'learning_rate': 0.0002616886166562305, 'epoch': 6.0}

 50%|█████     | 14056/28080 [27:46:41<27:44:47,  7.12s/it]
 50%|█████     | 14057/28080 [27:46:48<27:42:12,  7.11s/it]
                                                           
{'loss': 0.6373, 'learning_rate': 0.0002616598124054921, 'epoch': 6.01}

 50%|█████     | 14057/28080 [27:46:48<27:42:12,  7.11s/it]
 50%|█████     | 14058/28080 [27:46:55<27:47:40,  7.14s/it]
                                                           
{'loss': 0.5998, 'learning_rate': 0.00026163100799963184, 'epoch': 6.01}

 50%|█████     | 14058/28080 [27:46:55<27:47:40,  7.14s/it]
 50%|█████     | 14059/28080 [27:47:02<27:47:09,  7.13s/it]
                                                           
{'loss': 0.6313, 'learning_rate': 0.0002616022034390331, 'epoch': 6.01}

 50%|█████     | 14059/28080 [27:47:02<27:47:09,  7.13s/it]
 50%|█████     | 14060/28080 [27:47:10<27:42:07,  7.11s/it]
                                                           
{'loss': 0.6203, 'learning_rate': 0.00026157339872407895, 'epoch': 6.01}

 50%|█████     | 14060/28080 [27:47:10<27:42:07,  7.11s/it]
 50%|█████     | 14061/28080 [27:47:17<27:44:09,  7.12s/it]
                                                           
{'loss': 0.6199, 'learning_rate': 0.0002615445938551527, 'epoch': 6.01}

 50%|█████     | 14061/28080 [27:47:17<27:44:09,  7.12s/it]
 50%|█████     | 14062/28080 [27:47:24<27:38:51,  7.10s/it]
                                                           
{'loss': 0.6195, 'learning_rate': 0.00026151578883263754, 'epoch': 6.01}

 50%|█████     | 14062/28080 [27:47:24<27:38:51,  7.10s/it]
 50%|█████     | 14063/28080 [27:47:31<27:39:51,  7.11s/it]
                                                           
{'loss': 0.6018, 'learning_rate': 0.0002614869836569167, 'epoch': 6.01}

 50%|█████     | 14063/28080 [27:47:31<27:39:51,  7.11s/it]
 50%|█████     | 14064/28080 [27:47:38<27:39:39,  7.10s/it]
                                                           
{'loss': 0.6247, 'learning_rate': 0.00026145817832837345, 'epoch': 6.01}

 50%|█████     | 14064/28080 [27:47:38<27:39:39,  7.10s/it]
 50%|█████     | 14065/28080 [27:47:45<27:36:10,  7.09s/it]
                                                           
{'loss': 0.6252, 'learning_rate': 0.0002614293728473908, 'epoch': 6.01}

 50%|█████     | 14065/28080 [27:47:45<27:36:10,  7.09s/it]
 50%|█████     | 14066/28080 [27:47:52<27:38:52,  7.10s/it]
                                                           
{'loss': 0.6213, 'learning_rate': 0.00026140056721435227, 'epoch': 6.01}

 50%|█████     | 14066/28080 [27:47:52<27:38:52,  7.10s/it]
 50%|█████     | 14067/28080 [27:47:59<27:38:06,  7.10s/it]
                                                           
{'loss': 0.6326, 'learning_rate': 0.0002613717614296409, 'epoch': 6.01}

 50%|█████     | 14067/28080 [27:47:59<27:38:06,  7.10s/it]
 50%|█████     | 14068/28080 [27:48:06<27:33:52,  7.08s/it]
                                                           
{'loss': 0.6135, 'learning_rate': 0.00026134295549364, 'epoch': 6.01}

 50%|█████     | 14068/28080 [27:48:06<27:33:52,  7.08s/it]
 50%|█████     | 14069/28080 [27:48:14<27:48:30,  7.15s/it]
                                                           
{'loss': 0.6135, 'learning_rate': 0.00026131414940673277, 'epoch': 6.01}

 50%|█████     | 14069/28080 [27:48:14<27:48:30,  7.15s/it]
 50%|█████     | 14070/28080 [27:48:21<27:39:29,  7.11s/it]
                                                           
{'loss': 0.6164, 'learning_rate': 0.0002612853431693024, 'epoch': 6.01}

 50%|█████     | 14070/28080 [27:48:21<27:39:29,  7.11s/it]
 50%|█████     | 14071/28080 [27:48:28<27:45:08,  7.13s/it]
                                                           
{'loss': 0.6267, 'learning_rate': 0.00026125653678173226, 'epoch': 6.01}

 50%|█████     | 14071/28080 [27:48:28<27:45:08,  7.13s/it]
 50%|█████     | 14072/28080 [27:48:35<27:47:11,  7.14s/it]
                                                           
{'loss': 0.6322, 'learning_rate': 0.0002612277302444054, 'epoch': 6.01}

 50%|█████     | 14072/28080 [27:48:35<27:47:11,  7.14s/it]
 50%|█████     | 14073/28080 [27:48:42<27:45:18,  7.13s/it]
                                                           
{'loss': 0.6068, 'learning_rate': 0.0002611989235577054, 'epoch': 6.01}

 50%|█████     | 14073/28080 [27:48:42<27:45:18,  7.13s/it]
 50%|█████     | 14074/28080 [27:48:49<27:47:30,  7.14s/it]
                                                           
{'loss': 0.6067, 'learning_rate': 0.000261170116722015, 'epoch': 6.01}

 50%|█████     | 14074/28080 [27:48:49<27:47:30,  7.14s/it]
 50%|█████     | 14075/28080 [27:48:56<27:41:14,  7.12s/it]
                                                           
{'loss': 0.6055, 'learning_rate': 0.00026114130973771795, 'epoch': 6.01}

 50%|█████     | 14075/28080 [27:48:56<27:41:14,  7.12s/it]
 50%|█████     | 14076/28080 [27:49:03<27:41:27,  7.12s/it]
                                                           
{'loss': 0.605, 'learning_rate': 0.0002611125026051971, 'epoch': 6.01}

 50%|█████     | 14076/28080 [27:49:03<27:41:27,  7.12s/it]
 50%|█████     | 14077/28080 [27:49:11<27:47:46,  7.15s/it]
                                                           
{'loss': 0.6108, 'learning_rate': 0.0002610836953248359, 'epoch': 6.01}

 50%|█████     | 14077/28080 [27:49:11<27:47:46,  7.15s/it]
 50%|█████     | 14078/28080 [27:49:18<27:43:34,  7.13s/it]
                                                           
{'loss': 0.6434, 'learning_rate': 0.00026105488789701767, 'epoch': 6.01}

 50%|█████     | 14078/28080 [27:49:18<27:43:34,  7.13s/it]
 50%|█████     | 14079/28080 [27:49:25<27:42:53,  7.13s/it]
                                                           
{'loss': 0.6169, 'learning_rate': 0.00026102608032212545, 'epoch': 6.01}

 50%|█████     | 14079/28080 [27:49:25<27:42:53,  7.13s/it]
 50%|█████     | 14080/28080 [27:49:32<27:27:39,  7.06s/it]
                                                           
{'loss': 0.6196, 'learning_rate': 0.0002609972726005427, 'epoch': 6.01}

 50%|█████     | 14080/28080 [27:49:32<27:27:39,  7.06s/it]
 50%|█████     | 14081/28080 [27:49:39<27:33:28,  7.09s/it]
                                                           
{'loss': 0.6252, 'learning_rate': 0.00026096846473265247, 'epoch': 6.02}

 50%|█████     | 14081/28080 [27:49:39<27:33:28,  7.09s/it]
 50%|█████     | 14082/28080 [27:49:46<27:41:24,  7.12s/it]
                                                           
{'loss': 0.6287, 'learning_rate': 0.00026093965671883824, 'epoch': 6.02}

 50%|█████     | 14082/28080 [27:49:46<27:41:24,  7.12s/it]
 50%|█████     | 14083/28080 [27:49:53<27:34:19,  7.09s/it]
                                                           
{'loss': 0.6327, 'learning_rate': 0.0002609108485594831, 'epoch': 6.02}

 50%|█████     | 14083/28080 [27:49:53<27:34:19,  7.09s/it]
 50%|█████     | 14084/28080 [27:50:00<27:38:17,  7.11s/it]
                                                           
{'loss': 0.6505, 'learning_rate': 0.00026088204025497035, 'epoch': 6.02}

 50%|█████     | 14084/28080 [27:50:00<27:38:17,  7.11s/it]
 50%|█████     | 14085/28080 [27:50:07<27:45:00,  7.14s/it]
                                                           
{'loss': 0.6182, 'learning_rate': 0.0002608532318056834, 'epoch': 6.02}

 50%|█████     | 14085/28080 [27:50:07<27:45:00,  7.14s/it]
 50%|█████     | 14086/28080 [27:50:15<27:42:15,  7.13s/it]
                                                           
{'loss': 0.6193, 'learning_rate': 0.00026082442321200526, 'epoch': 6.02}

 50%|█████     | 14086/28080 [27:50:15<27:42:15,  7.13s/it]
 50%|█████     | 14087/28080 [27:50:22<27:43:24,  7.13s/it]
                                                           
{'loss': 0.6133, 'learning_rate': 0.00026079561447431944, 'epoch': 6.02}

 50%|█████     | 14087/28080 [27:50:22<27:43:24,  7.13s/it]
 50%|█████     | 14088/28080 [27:50:29<27:38:58,  7.11s/it]
                                                           
{'loss': 0.6356, 'learning_rate': 0.0002607668055930091, 'epoch': 6.02}

 50%|█████     | 14088/28080 [27:50:29<27:38:58,  7.11s/it]
 50%|█████     | 14089/28080 [27:50:36<27:37:27,  7.11s/it]
                                                           
{'loss': 0.6316, 'learning_rate': 0.0002607379965684574, 'epoch': 6.02}

 50%|█████     | 14089/28080 [27:50:36<27:37:27,  7.11s/it]
 50%|█████     | 14090/28080 [27:50:43<27:42:00,  7.13s/it]
                                                           
{'loss': 0.6011, 'learning_rate': 0.0002607091874010479, 'epoch': 6.02}

 50%|█████     | 14090/28080 [27:50:43<27:42:00,  7.13s/it]
 50%|█████     | 14091/28080 [27:50:50<27:42:40,  7.13s/it]
                                                           
{'loss': 0.6061, 'learning_rate': 0.0002606803780911636, 'epoch': 6.02}

 50%|█████     | 14091/28080 [27:50:50<27:42:40,  7.13s/it]
 50%|█████     | 14092/28080 [27:50:57<27:44:27,  7.14s/it]
                                                           
{'loss': 0.6376, 'learning_rate': 0.0002606515686391879, 'epoch': 6.02}

 50%|█████     | 14092/28080 [27:50:57<27:44:27,  7.14s/it]
 50%|█████     | 14093/28080 [27:51:04<27:39:32,  7.12s/it]
                                                           
{'loss': 0.6291, 'learning_rate': 0.0002606227590455041, 'epoch': 6.02}

 50%|█████     | 14093/28080 [27:51:04<27:39:32,  7.12s/it]
 50%|█████     | 14094/28080 [27:51:12<27:46:20,  7.15s/it]
                                                           
{'loss': 0.6408, 'learning_rate': 0.0002605939493104954, 'epoch': 6.02}

 50%|█████     | 14094/28080 [27:51:12<27:46:20,  7.15s/it]
 50%|█████     | 14095/28080 [27:51:19<27:47:18,  7.15s/it]
                                                           
{'loss': 0.6177, 'learning_rate': 0.00026056513943454516, 'epoch': 6.02}

 50%|█████     | 14095/28080 [27:51:19<27:47:18,  7.15s/it]
 50%|█████     | 14096/28080 [27:51:26<27:47:20,  7.15s/it]
                                                           
{'loss': 0.6031, 'learning_rate': 0.0002605363294180367, 'epoch': 6.02}

 50%|█████     | 14096/28080 [27:51:26<27:47:20,  7.15s/it]
 50%|█████     | 14097/28080 [27:51:33<27:50:21,  7.17s/it]
                                                           
{'loss': 0.6125, 'learning_rate': 0.0002605075192613532, 'epoch': 6.02}

 50%|█████     | 14097/28080 [27:51:33<27:50:21,  7.17s/it]
 50%|█████     | 14098/28080 [27:51:40<27:49:01,  7.16s/it]
                                                           
{'loss': 0.6136, 'learning_rate': 0.000260478708964878, 'epoch': 6.02}

 50%|█████     | 14098/28080 [27:51:40<27:49:01,  7.16s/it]
 50%|█████     | 14099/28080 [27:51:47<27:41:51,  7.13s/it]
                                                           
{'loss': 0.6359, 'learning_rate': 0.00026044989852899437, 'epoch': 6.02}

 50%|█████     | 14099/28080 [27:51:47<27:41:51,  7.13s/it]
 50%|█████     | 14100/28080 [27:51:55<27:47:56,  7.16s/it]
                                                           
{'loss': 0.6333, 'learning_rate': 0.0002604210879540856, 'epoch': 6.02}

 50%|█████     | 14100/28080 [27:51:55<27:47:56,  7.16s/it]
 50%|█████     | 14101/28080 [27:52:02<27:44:56,  7.15s/it]
                                                           
{'loss': 0.6276, 'learning_rate': 0.00026039227724053497, 'epoch': 6.02}

 50%|█████     | 14101/28080 [27:52:02<27:44:56,  7.15s/it]
 50%|█████     | 14102/28080 [27:52:09<27:46:02,  7.15s/it]
                                                           
{'loss': 0.6209, 'learning_rate': 0.0002603634663887259, 'epoch': 6.02}

 50%|█████     | 14102/28080 [27:52:09<27:46:02,  7.15s/it]
 50%|█████     | 14103/28080 [27:52:16<27:45:50,  7.15s/it]
                                                           
{'loss': 0.6375, 'learning_rate': 0.00026033465539904155, 'epoch': 6.02}

 50%|█████     | 14103/28080 [27:52:16<27:45:50,  7.15s/it]
 50%|█████     | 14104/28080 [27:52:23<27:37:40,  7.12s/it]
                                                           
{'loss': 0.6266, 'learning_rate': 0.0002603058442718653, 'epoch': 6.03}

 50%|█████     | 14104/28080 [27:52:23<27:37:40,  7.12s/it]
 50%|█████     | 14105/28080 [27:52:30<27:43:18,  7.14s/it]
                                                           
{'loss': 0.6412, 'learning_rate': 0.00026027703300758045, 'epoch': 6.03}

 50%|█████     | 14105/28080 [27:52:30<27:43:18,  7.14s/it]
 50%|█████     | 14106/28080 [27:52:37<27:44:12,  7.15s/it]
                                                           
{'loss': 0.5972, 'learning_rate': 0.00026024822160657026, 'epoch': 6.03}

 50%|█████     | 14106/28080 [27:52:37<27:44:12,  7.15s/it]
 50%|█████     | 14107/28080 [27:52:44<27:41:05,  7.13s/it]
                                                           
{'loss': 0.6121, 'learning_rate': 0.000260219410069218, 'epoch': 6.03}

 50%|█████     | 14107/28080 [27:52:44<27:41:05,  7.13s/it]
 50%|█████     | 14108/28080 [27:52:52<27:44:37,  7.15s/it]
                                                           
{'loss': 0.6279, 'learning_rate': 0.0002601905983959071, 'epoch': 6.03}

 50%|█████     | 14108/28080 [27:52:52<27:44:37,  7.15s/it]
 50%|█████     | 14109/28080 [27:52:59<27:41:26,  7.14s/it]
                                                           
{'loss': 0.6425, 'learning_rate': 0.0002601617865870208, 'epoch': 6.03}

 50%|█████     | 14109/28080 [27:52:59<27:41:26,  7.14s/it]
 50%|█████     | 14110/28080 [27:53:06<27:35:09,  7.11s/it]
                                                           
{'loss': 0.6215, 'learning_rate': 0.00026013297464294236, 'epoch': 6.03}

 50%|█████     | 14110/28080 [27:53:06<27:35:09,  7.11s/it]
 50%|█████     | 14111/28080 [27:53:13<27:39:15,  7.13s/it]
                                                           
{'loss': 0.6282, 'learning_rate': 0.00026010416256405514, 'epoch': 6.03}

 50%|█████     | 14111/28080 [27:53:13<27:39:15,  7.13s/it]
 50%|█████     | 14112/28080 [27:53:20<27:33:13,  7.10s/it]
                                                           
{'loss': 0.6212, 'learning_rate': 0.0002600753503507426, 'epoch': 6.03}

 50%|█████     | 14112/28080 [27:53:20<27:33:13,  7.10s/it]
 50%|█████     | 14113/28080 [27:53:27<27:29:30,  7.09s/it]
                                                           
{'loss': 0.6281, 'learning_rate': 0.00026004653800338777, 'epoch': 6.03}

 50%|█████     | 14113/28080 [27:53:27<27:29:30,  7.09s/it]
 50%|█████     | 14114/28080 [27:53:34<27:31:04,  7.09s/it]
                                                           
{'loss': 0.6193, 'learning_rate': 0.0002600177255223742, 'epoch': 6.03}

 50%|█████     | 14114/28080 [27:53:34<27:31:04,  7.09s/it]
 50%|█████     | 14115/28080 [27:53:41<27:37:34,  7.12s/it]
                                                           
{'loss': 0.6217, 'learning_rate': 0.00025998891290808507, 'epoch': 6.03}

 50%|█████     | 14115/28080 [27:53:41<27:37:34,  7.12s/it]
 50%|█████     | 14116/28080 [27:53:49<27:41:41,  7.14s/it]
                                                           
{'loss': 0.6247, 'learning_rate': 0.00025996010016090377, 'epoch': 6.03}

 50%|█████     | 14116/28080 [27:53:49<27:41:41,  7.14s/it]
 50%|█████     | 14117/28080 [27:53:56<27:41:50,  7.14s/it]
                                                           
{'loss': 0.6248, 'learning_rate': 0.0002599312872812136, 'epoch': 6.03}

 50%|█████     | 14117/28080 [27:53:56<27:41:50,  7.14s/it]
 50%|█████     | 14118/28080 [27:54:03<27:42:33,  7.14s/it]
                                                           
{'loss': 0.6375, 'learning_rate': 0.0002599024742693979, 'epoch': 6.03}

 50%|█████     | 14118/28080 [27:54:03<27:42:33,  7.14s/it]
 50%|█████     | 14119/28080 [27:54:10<27:34:58,  7.11s/it]
                                                           
{'loss': 0.608, 'learning_rate': 0.00025987366112584004, 'epoch': 6.03}

 50%|█████     | 14119/28080 [27:54:10<27:34:58,  7.11s/it]
 50%|█████     | 14120/28080 [27:54:17<27:40:17,  7.14s/it]
                                                           
{'loss': 0.6066, 'learning_rate': 0.00025984484785092327, 'epoch': 6.03}

 50%|█████     | 14120/28080 [27:54:17<27:40:17,  7.14s/it]
 50%|█████     | 14121/28080 [27:54:24<27:43:55,  7.15s/it]
                                                           
{'loss': 0.6088, 'learning_rate': 0.000259816034445031, 'epoch': 6.03}

 50%|█████     | 14121/28080 [27:54:24<27:43:55,  7.15s/it]
 50%|█████     | 14122/28080 [27:54:31<27:39:18,  7.13s/it]
                                                           
{'loss': 0.6502, 'learning_rate': 0.00025978722090854643, 'epoch': 6.03}

 50%|█████     | 14122/28080 [27:54:31<27:39:18,  7.13s/it]
 50%|█████     | 14123/28080 [27:54:38<27:35:15,  7.12s/it]
                                                           
{'loss': 0.619, 'learning_rate': 0.00025975840724185305, 'epoch': 6.03}

 50%|█████     | 14123/28080 [27:54:38<27:35:15,  7.12s/it]
 50%|█████     | 14124/28080 [27:54:46<27:34:09,  7.11s/it]
                                                           
{'loss': 0.6182, 'learning_rate': 0.0002597295934453341, 'epoch': 6.03}

 50%|█████     | 14124/28080 [27:54:46<27:34:09,  7.11s/it]
 50%|█████     | 14125/28080 [27:54:53<27:37:22,  7.13s/it]
                                                           
{'loss': 0.6201, 'learning_rate': 0.00025970077951937296, 'epoch': 6.03}

 50%|█████     | 14125/28080 [27:54:53<27:37:22,  7.13s/it]
 50%|█████     | 14126/28080 [27:55:00<27:36:04,  7.12s/it]
                                                           
{'loss': 0.6202, 'learning_rate': 0.00025967196546435294, 'epoch': 6.03}

 50%|█████     | 14126/28080 [27:55:00<27:36:04,  7.12s/it]
 50%|█████     | 14127/28080 [27:55:07<27:37:56,  7.13s/it]
                                                           
{'loss': 0.6354, 'learning_rate': 0.00025964315128065743, 'epoch': 6.03}

 50%|█████     | 14127/28080 [27:55:07<27:37:56,  7.13s/it]
 50%|█████     | 14128/28080 [27:55:14<27:44:31,  7.16s/it]
                                                           
{'loss': 0.6122, 'learning_rate': 0.0002596143369686697, 'epoch': 6.04}

 50%|█████     | 14128/28080 [27:55:14<27:44:31,  7.16s/it]
 50%|█████     | 14129/28080 [27:55:21<27:33:05,  7.11s/it]
                                                           
{'loss': 0.6366, 'learning_rate': 0.00025958552252877313, 'epoch': 6.04}

 50%|█████     | 14129/28080 [27:55:21<27:33:05,  7.11s/it]
 50%|█████     | 14130/28080 [27:55:28<27:30:34,  7.10s/it]
                                                           
{'loss': 0.6292, 'learning_rate': 0.00025955670796135114, 'epoch': 6.04}

 50%|█████     | 14130/28080 [27:55:28<27:30:34,  7.10s/it]
 50%|█████     | 14131/28080 [27:55:35<27:34:23,  7.12s/it]
                                                           
{'loss': 0.6268, 'learning_rate': 0.00025952789326678694, 'epoch': 6.04}

 50%|█████     | 14131/28080 [27:55:35<27:34:23,  7.12s/it]
 50%|█████     | 14132/28080 [27:55:43<27:42:04,  7.15s/it]
                                                           
{'loss': 0.5985, 'learning_rate': 0.000259499078445464, 'epoch': 6.04}

 50%|█████     | 14132/28080 [27:55:43<27:42:04,  7.15s/it]
 50%|█████     | 14133/28080 [27:55:50<27:44:32,  7.16s/it]
                                                           
{'loss': 0.6179, 'learning_rate': 0.0002594702634977656, 'epoch': 6.04}

 50%|█████     | 14133/28080 [27:55:50<27:44:32,  7.16s/it]
 50%|█████     | 14134/28080 [27:55:57<27:35:36,  7.12s/it]
                                                           
{'loss': 0.639, 'learning_rate': 0.00025944144842407507, 'epoch': 6.04}

 50%|█████     | 14134/28080 [27:55:57<27:35:36,  7.12s/it]
 50%|█████     | 14135/28080 [27:56:04<27:39:08,  7.14s/it]
                                                           
{'loss': 0.6118, 'learning_rate': 0.00025941263322477593, 'epoch': 6.04}

 50%|█████     | 14135/28080 [27:56:04<27:39:08,  7.14s/it]
 50%|█████     | 14136/28080 [27:56:11<27:41:33,  7.15s/it]
                                                           
{'loss': 0.6271, 'learning_rate': 0.0002593838179002513, 'epoch': 6.04}

 50%|█████     | 14136/28080 [27:56:11<27:41:33,  7.15s/it]
 50%|█████     | 14137/28080 [27:56:18<27:33:48,  7.12s/it]
                                                           
{'loss': 0.607, 'learning_rate': 0.0002593550024508847, 'epoch': 6.04}

 50%|█████     | 14137/28080 [27:56:18<27:33:48,  7.12s/it]
 50%|█████     | 14138/28080 [27:56:25<27:35:15,  7.12s/it]
                                                           
{'loss': 0.6123, 'learning_rate': 0.0002593261868770595, 'epoch': 6.04}

 50%|█████     | 14138/28080 [27:56:25<27:35:15,  7.12s/it]
 50%|█████     | 14139/28080 [27:56:33<27:35:53,  7.13s/it]
                                                           
{'loss': 0.6147, 'learning_rate': 0.00025929737117915894, 'epoch': 6.04}

 50%|█████     | 14139/28080 [27:56:33<27:35:53,  7.13s/it]
 50%|█████     | 14140/28080 [27:56:40<27:32:23,  7.11s/it]
                                                           
{'loss': 0.597, 'learning_rate': 0.00025926855535756646, 'epoch': 6.04}

 50%|█████     | 14140/28080 [27:56:40<27:32:23,  7.11s/it]
 50%|█████     | 14141/28080 [27:56:47<27:40:09,  7.15s/it]
                                                           
{'loss': 0.6022, 'learning_rate': 0.0002592397394126654, 'epoch': 6.04}

 50%|█████     | 14141/28080 [27:56:47<27:40:09,  7.15s/it]
 50%|█████     | 14142/28080 [27:56:54<27:36:05,  7.13s/it]
                                                           
{'loss': 0.623, 'learning_rate': 0.00025921092334483907, 'epoch': 6.04}

 50%|█████     | 14142/28080 [27:56:54<27:36:05,  7.13s/it]
 50%|█████     | 14143/28080 [27:57:01<27:38:50,  7.14s/it]
                                                           
{'loss': 0.6115, 'learning_rate': 0.000259182107154471, 'epoch': 6.04}

 50%|█████     | 14143/28080 [27:57:01<27:38:50,  7.14s/it]
 50%|█████     | 14144/28080 [27:57:08<27:28:30,  7.10s/it]
                                                           
{'loss': 0.6232, 'learning_rate': 0.0002591532908419444, 'epoch': 6.04}

 50%|█████     | 14144/28080 [27:57:08<27:28:30,  7.10s/it]
 50%|█████     | 14145/28080 [27:57:15<27:25:47,  7.09s/it]
                                                           
{'loss': 0.6088, 'learning_rate': 0.0002591244744076428, 'epoch': 6.04}

 50%|█████     | 14145/28080 [27:57:15<27:25:47,  7.09s/it]
 50%|█████     | 14146/28080 [27:57:22<27:19:11,  7.06s/it]
                                                           
{'loss': 0.6231, 'learning_rate': 0.00025909565785194944, 'epoch': 6.04}

 50%|█████     | 14146/28080 [27:57:22<27:19:11,  7.06s/it]
 50%|█████     | 14147/28080 [27:57:29<27:26:02,  7.09s/it]
                                                           
{'loss': 0.6247, 'learning_rate': 0.00025906684117524775, 'epoch': 6.04}

 50%|█████     | 14147/28080 [27:57:29<27:26:02,  7.09s/it]
 50%|█████     | 14148/28080 [27:57:36<27:18:51,  7.06s/it]
                                                           
{'loss': 0.6375, 'learning_rate': 0.000259038024377921, 'epoch': 6.04}

 50%|█████     | 14148/28080 [27:57:36<27:18:51,  7.06s/it]
 50%|█████     | 14149/28080 [27:57:43<27:20:34,  7.07s/it]
                                                           
{'loss': 0.6107, 'learning_rate': 0.0002590092074603527, 'epoch': 6.04}

 50%|█████     | 14149/28080 [27:57:43<27:20:34,  7.07s/it]
 50%|█████     | 14150/28080 [27:57:50<27:18:15,  7.06s/it]
                                                           
{'loss': 0.6181, 'learning_rate': 0.0002589803904229263, 'epoch': 6.04}

 50%|█████     | 14150/28080 [27:57:50<27:18:15,  7.06s/it]
 50%|█████     | 14151/28080 [27:57:58<27:25:07,  7.09s/it]
                                                           
{'loss': 0.6192, 'learning_rate': 0.000258951573266025, 'epoch': 6.05}

 50%|█████     | 14151/28080 [27:57:58<27:25:07,  7.09s/it]
 50%|█████     | 14152/28080 [27:58:05<27:28:31,  7.10s/it]
                                                           
{'loss': 0.6189, 'learning_rate': 0.0002589227559900322, 'epoch': 6.05}

 50%|█████     | 14152/28080 [27:58:05<27:28:31,  7.10s/it]
 50%|█████     | 14153/28080 [27:58:12<27:28:07,  7.10s/it]
                                                           
{'loss': 0.6134, 'learning_rate': 0.0002588939385953314, 'epoch': 6.05}

 50%|█████     | 14153/28080 [27:58:12<27:28:07,  7.10s/it]
 50%|█████     | 14154/28080 [27:58:19<27:35:14,  7.13s/it]
                                                           
{'loss': 0.6203, 'learning_rate': 0.0002588651210823059, 'epoch': 6.05}

 50%|█████     | 14154/28080 [27:58:19<27:35:14,  7.13s/it]
 50%|█████     | 14155/28080 [27:58:26<27:35:23,  7.13s/it]
                                                           
{'loss': 0.625, 'learning_rate': 0.0002588363034513391, 'epoch': 6.05}

 50%|█████     | 14155/28080 [27:58:26<27:35:23,  7.13s/it]
 50%|█████     | 14156/28080 [27:58:33<27:38:57,  7.15s/it]
                                                           
{'loss': 0.6271, 'learning_rate': 0.0002588074857028144, 'epoch': 6.05}

 50%|█████     | 14156/28080 [27:58:33<27:38:57,  7.15s/it]
 50%|█████     | 14157/28080 [27:58:40<27:37:46,  7.14s/it]
                                                           
{'loss': 0.6276, 'learning_rate': 0.00025877866783711523, 'epoch': 6.05}

 50%|█████     | 14157/28080 [27:58:40<27:37:46,  7.14s/it]
 50%|█████     | 14158/28080 [27:58:48<27:38:21,  7.15s/it]
                                                           
{'loss': 0.6168, 'learning_rate': 0.00025874984985462484, 'epoch': 6.05}

 50%|█████     | 14158/28080 [27:58:48<27:38:21,  7.15s/it]
 50%|█████     | 14159/28080 [27:58:55<27:29:31,  7.11s/it]
                                                           
{'loss': 0.6375, 'learning_rate': 0.00025872103175572685, 'epoch': 6.05}

 50%|█████     | 14159/28080 [27:58:55<27:29:31,  7.11s/it]
 50%|█████     | 14160/28080 [27:59:02<27:33:54,  7.13s/it]
                                                           
{'loss': 0.6019, 'learning_rate': 0.0002586922135408045, 'epoch': 6.05}

 50%|█████     | 14160/28080 [27:59:02<27:33:54,  7.13s/it]
 50%|█████     | 14161/28080 [27:59:09<27:39:19,  7.15s/it]
                                                           
{'loss': 0.6277, 'learning_rate': 0.0002586633952102412, 'epoch': 6.05}

 50%|█████     | 14161/28080 [27:59:09<27:39:19,  7.15s/it]
 50%|█████     | 14162/28080 [27:59:16<27:38:47,  7.15s/it]
                                                           
{'loss': 0.6147, 'learning_rate': 0.0002586345767644204, 'epoch': 6.05}

 50%|█████     | 14162/28080 [27:59:16<27:38:47,  7.15s/it]
 50%|█████     | 14163/28080 [27:59:23<27:36:25,  7.14s/it]
                                                           
{'loss': 0.5929, 'learning_rate': 0.00025860575820372536, 'epoch': 6.05}

 50%|█████     | 14163/28080 [27:59:23<27:36:25,  7.14s/it]
 50%|█████     | 14164/28080 [27:59:30<27:36:33,  7.14s/it]
                                                           
{'loss': 0.609, 'learning_rate': 0.00025857693952853966, 'epoch': 6.05}

 50%|█████     | 14164/28080 [27:59:30<27:36:33,  7.14s/it]
 50%|█████     | 14165/28080 [27:59:38<27:37:04,  7.15s/it]
                                                           
{'loss': 0.6074, 'learning_rate': 0.0002585481207392466, 'epoch': 6.05}

 50%|█████     | 14165/28080 [27:59:38<27:37:04,  7.15s/it]
 50%|█████     | 14166/28080 [27:59:45<27:33:38,  7.13s/it]
                                                           
{'loss': 0.6346, 'learning_rate': 0.00025851930183622964, 'epoch': 6.05}

 50%|█████     | 14166/28080 [27:59:45<27:33:38,  7.13s/it]
 50%|█████     | 14167/28080 [27:59:52<27:33:21,  7.13s/it]
                                                           
{'loss': 0.6475, 'learning_rate': 0.00025849048281987214, 'epoch': 6.05}

 50%|█████     | 14167/28080 [27:59:52<27:33:21,  7.13s/it]
 50%|█████     | 14168/28080 [27:59:59<27:34:45,  7.14s/it]
                                                           
{'loss': 0.6013, 'learning_rate': 0.00025846166369055746, 'epoch': 6.05}

 50%|█████     | 14168/28080 [27:59:59<27:34:45,  7.14s/it]
 50%|█████     | 14169/28080 [28:00:06<27:33:32,  7.13s/it]
                                                           
{'loss': 0.6255, 'learning_rate': 0.0002584328444486692, 'epoch': 6.05}

 50%|█████     | 14169/28080 [28:00:06<27:33:32,  7.13s/it]
 50%|█████     | 14170/28080 [28:00:13<27:29:46,  7.12s/it]
                                                           
{'loss': 0.632, 'learning_rate': 0.0002584040250945905, 'epoch': 6.05}

 50%|█████     | 14170/28080 [28:00:13<27:29:46,  7.12s/it]
 50%|█████     | 14171/28080 [28:00:20<27:30:26,  7.12s/it]
                                                           
{'loss': 0.5913, 'learning_rate': 0.00025837520562870507, 'epoch': 6.05}

 50%|█████     | 14171/28080 [28:00:20<27:30:26,  7.12s/it]
 50%|█████     | 14172/28080 [28:00:27<27:33:42,  7.13s/it]
                                                           
{'loss': 0.6273, 'learning_rate': 0.0002583463860513961, 'epoch': 6.05}

 50%|█████     | 14172/28080 [28:00:27<27:33:42,  7.13s/it]
 50%|█████     | 14173/28080 [28:00:34<27:26:30,  7.10s/it]
                                                           
{'loss': 0.6067, 'learning_rate': 0.00025831756636304705, 'epoch': 6.05}

 50%|█████     | 14173/28080 [28:00:34<27:26:30,  7.10s/it]
 50%|█████     | 14174/28080 [28:00:42<27:23:42,  7.09s/it]
                                                           
{'loss': 0.5931, 'learning_rate': 0.0002582887465640414, 'epoch': 6.06}

 50%|█████     | 14174/28080 [28:00:42<27:23:42,  7.09s/it]
 50%|█████     | 14175/28080 [28:00:49<27:24:26,  7.10s/it]
                                                           
{'loss': 0.6291, 'learning_rate': 0.0002582599266547625, 'epoch': 6.06}

 50%|█████     | 14175/28080 [28:00:49<27:24:26,  7.10s/it]
 50%|█████     | 14176/28080 [28:00:56<27:25:25,  7.10s/it]
                                                           
{'loss': 0.6372, 'learning_rate': 0.00025823110663559384, 'epoch': 6.06}

 50%|█████     | 14176/28080 [28:00:56<27:25:25,  7.10s/it]
 50%|█████     | 14177/28080 [28:01:03<27:33:57,  7.14s/it]
                                                           
{'loss': 0.6253, 'learning_rate': 0.00025820228650691874, 'epoch': 6.06}

 50%|█████     | 14177/28080 [28:01:03<27:33:57,  7.14s/it]
 50%|█████     | 14178/28080 [28:01:10<27:32:23,  7.13s/it]
                                                           
{'loss': 0.6134, 'learning_rate': 0.00025817346626912075, 'epoch': 6.06}

 50%|█████     | 14178/28080 [28:01:10<27:32:23,  7.13s/it]
 50%|█████     | 14179/28080 [28:01:17<27:34:11,  7.14s/it]
                                                           
{'loss': 0.6219, 'learning_rate': 0.00025814464592258313, 'epoch': 6.06}

 50%|█████     | 14179/28080 [28:01:17<27:34:11,  7.14s/it]
 50%|█████     | 14180/28080 [28:01:24<27:34:12,  7.14s/it]
                                                           
{'loss': 0.6135, 'learning_rate': 0.00025811582546768943, 'epoch': 6.06}

 50%|█████     | 14180/28080 [28:01:24<27:34:12,  7.14s/it]
 51%|█████     | 14181/28080 [28:01:32<27:33:14,  7.14s/it]
                                                           
{'loss': 0.6019, 'learning_rate': 0.0002580870049048231, 'epoch': 6.06}

 51%|█████     | 14181/28080 [28:01:32<27:33:14,  7.14s/it]
 51%|█████     | 14182/28080 [28:01:39<27:35:29,  7.15s/it]
                                                           
{'loss': 0.6174, 'learning_rate': 0.00025805818423436743, 'epoch': 6.06}

 51%|█████     | 14182/28080 [28:01:39<27:35:29,  7.15s/it]
 51%|█████     | 14183/28080 [28:01:46<27:33:38,  7.14s/it]
                                                           
{'loss': 0.6379, 'learning_rate': 0.00025802936345670604, 'epoch': 6.06}

 51%|█████     | 14183/28080 [28:01:46<27:33:38,  7.14s/it]
 51%|█████     | 14184/28080 [28:01:53<27:29:11,  7.12s/it]
                                                           
{'loss': 0.6141, 'learning_rate': 0.00025800054257222216, 'epoch': 6.06}

 51%|█████     | 14184/28080 [28:01:53<27:29:11,  7.12s/it]
 51%|█████     | 14185/28080 [28:02:00<27:29:09,  7.12s/it]
                                                           
{'loss': 0.6171, 'learning_rate': 0.0002579717215812994, 'epoch': 6.06}

 51%|█████     | 14185/28080 [28:02:00<27:29:09,  7.12s/it]
 51%|█████     | 14186/28080 [28:02:07<27:36:51,  7.15s/it]
                                                           
{'loss': 0.6211, 'learning_rate': 0.000257942900484321, 'epoch': 6.06}

 51%|█████     | 14186/28080 [28:02:07<27:36:51,  7.15s/it]
 51%|█████     | 14187/28080 [28:02:14<27:37:08,  7.16s/it]
                                                           
{'loss': 0.6303, 'learning_rate': 0.0002579140792816706, 'epoch': 6.06}

 51%|█████     | 14187/28080 [28:02:14<27:37:08,  7.16s/it]
 51%|█████     | 14188/28080 [28:02:21<27:27:37,  7.12s/it]
                                                           
{'loss': 0.6123, 'learning_rate': 0.00025788525797373153, 'epoch': 6.06}

 51%|█████     | 14188/28080 [28:02:21<27:27:37,  7.12s/it]
 51%|█████     | 14189/28080 [28:02:29<27:26:52,  7.11s/it]
                                                           
{'loss': 0.6098, 'learning_rate': 0.00025785643656088715, 'epoch': 6.06}

 51%|█████     | 14189/28080 [28:02:29<27:26:52,  7.11s/it]
 51%|█████     | 14190/28080 [28:02:36<27:23:32,  7.10s/it]
                                                           
{'loss': 0.6283, 'learning_rate': 0.0002578276150435211, 'epoch': 6.06}

 51%|█████     | 14190/28080 [28:02:36<27:23:32,  7.10s/it]
 51%|█████     | 14191/28080 [28:02:43<27:24:01,  7.10s/it]
                                                           
{'loss': 0.6146, 'learning_rate': 0.0002577987934220166, 'epoch': 6.06}

 51%|█████     | 14191/28080 [28:02:43<27:24:01,  7.10s/it]
 51%|█████     | 14192/28080 [28:02:50<27:33:40,  7.14s/it]
                                                           
{'loss': 0.6016, 'learning_rate': 0.00025776997169675727, 'epoch': 6.06}

 51%|█████     | 14192/28080 [28:02:50<27:33:40,  7.14s/it]
 51%|█████     | 14193/28080 [28:02:57<27:39:25,  7.17s/it]
                                                           
{'loss': 0.6127, 'learning_rate': 0.00025774114986812645, 'epoch': 6.06}

 51%|█████     | 14193/28080 [28:02:57<27:39:25,  7.17s/it]
 51%|█████     | 14194/28080 [28:03:04<27:39:28,  7.17s/it]
                                                           
{'loss': 0.6254, 'learning_rate': 0.0002577123279365076, 'epoch': 6.06}

 51%|█████     | 14194/28080 [28:03:04<27:39:28,  7.17s/it]
 51%|█████     | 14195/28080 [28:03:11<27:29:19,  7.13s/it]
                                                           
{'loss': 0.6269, 'learning_rate': 0.00025768350590228424, 'epoch': 6.06}

 51%|█████     | 14195/28080 [28:03:11<27:29:19,  7.13s/it]
 51%|█████     | 14196/28080 [28:03:18<27:25:27,  7.11s/it]
                                                           
{'loss': 0.6224, 'learning_rate': 0.00025765468376583975, 'epoch': 6.06}

 51%|█████     | 14196/28080 [28:03:18<27:25:27,  7.11s/it]
 51%|█████     | 14197/28080 [28:03:26<27:26:35,  7.12s/it]
                                                           
{'loss': 0.6152, 'learning_rate': 0.00025762586152755756, 'epoch': 6.06}

 51%|█████     | 14197/28080 [28:03:26<27:26:35,  7.12s/it]
 51%|█████     | 14198/28080 [28:03:33<27:21:38,  7.10s/it]
                                                           
{'loss': 0.6077, 'learning_rate': 0.0002575970391878211, 'epoch': 6.07}

 51%|█████     | 14198/28080 [28:03:33<27:21:38,  7.10s/it]
 51%|█████     | 14199/28080 [28:03:40<27:22:15,  7.10s/it]
                                                           
{'loss': 0.6319, 'learning_rate': 0.0002575682167470139, 'epoch': 6.07}

 51%|█████     | 14199/28080 [28:03:40<27:22:15,  7.10s/it]
 51%|█████     | 14200/28080 [28:03:47<27:22:39,  7.10s/it]
                                                           
{'loss': 0.6119, 'learning_rate': 0.00025753939420551945, 'epoch': 6.07}

 51%|█████     | 14200/28080 [28:03:47<27:22:39,  7.10s/it]
 51%|█████     | 14201/28080 [28:03:54<27:23:32,  7.11s/it]
                                                           
{'loss': 0.6513, 'learning_rate': 0.0002575105715637211, 'epoch': 6.07}

 51%|█████     | 14201/28080 [28:03:54<27:23:32,  7.11s/it]
 51%|█████     | 14202/28080 [28:04:01<27:18:37,  7.08s/it]
                                                           
{'loss': 0.6274, 'learning_rate': 0.0002574817488220024, 'epoch': 6.07}

 51%|█████     | 14202/28080 [28:04:01<27:18:37,  7.08s/it]
 51%|█████     | 14203/28080 [28:04:08<27:18:50,  7.09s/it]
                                                           
{'loss': 0.6189, 'learning_rate': 0.00025745292598074664, 'epoch': 6.07}

 51%|█████     | 14203/28080 [28:04:08<27:18:50,  7.09s/it]
 51%|█████     | 14204/28080 [28:04:15<27:15:39,  7.07s/it]
                                                           
{'loss': 0.6324, 'learning_rate': 0.0002574241030403374, 'epoch': 6.07}

 51%|█████     | 14204/28080 [28:04:15<27:15:39,  7.07s/it]
 51%|█████     | 14205/28080 [28:04:22<27:22:23,  7.10s/it]
                                                           
{'loss': 0.6055, 'learning_rate': 0.00025739528000115827, 'epoch': 6.07}

 51%|█████     | 14205/28080 [28:04:22<27:22:23,  7.10s/it]
 51%|█████     | 14206/28080 [28:04:30<27:29:46,  7.13s/it]
                                                           
{'loss': 0.6084, 'learning_rate': 0.0002573664568635924, 'epoch': 6.07}

 51%|█████     | 14206/28080 [28:04:30<27:29:46,  7.13s/it]
 51%|█████     | 14207/28080 [28:04:37<27:27:44,  7.13s/it]
                                                           
{'loss': 0.6082, 'learning_rate': 0.00025733763362802354, 'epoch': 6.07}

 51%|█████     | 14207/28080 [28:04:37<27:27:44,  7.13s/it]
 51%|█████     | 14208/28080 [28:04:44<27:30:05,  7.14s/it]
                                                           
{'loss': 0.5865, 'learning_rate': 0.00025730881029483496, 'epoch': 6.07}

 51%|█████     | 14208/28080 [28:04:44<27:30:05,  7.14s/it]
 51%|█████     | 14209/28080 [28:04:51<27:24:29,  7.11s/it]
                                                           
{'loss': 0.616, 'learning_rate': 0.00025727998686441025, 'epoch': 6.07}

 51%|█████     | 14209/28080 [28:04:51<27:24:29,  7.11s/it]
 51%|█████     | 14210/28080 [28:04:58<27:30:05,  7.14s/it]
                                                           
{'loss': 0.6102, 'learning_rate': 0.0002572511633371328, 'epoch': 6.07}

 51%|█████     | 14210/28080 [28:04:58<27:30:05,  7.14s/it]
 51%|█████     | 14211/28080 [28:05:05<27:27:54,  7.13s/it]
                                                           
{'loss': 0.6109, 'learning_rate': 0.00025722233971338604, 'epoch': 6.07}

 51%|█████     | 14211/28080 [28:05:05<27:27:54,  7.13s/it]
 51%|█████     | 14212/28080 [28:05:12<27:27:13,  7.13s/it]
                                                           
{'loss': 0.6287, 'learning_rate': 0.0002571935159935537, 'epoch': 6.07}

 51%|█████     | 14212/28080 [28:05:12<27:27:13,  7.13s/it]
 51%|█████     | 14213/28080 [28:05:19<27:29:39,  7.14s/it]
                                                           
{'loss': 0.6141, 'learning_rate': 0.00025716469217801883, 'epoch': 6.07}

 51%|█████     | 14213/28080 [28:05:19<27:29:39,  7.14s/it]
 51%|█████     | 14214/28080 [28:05:27<27:28:05,  7.13s/it]
                                                           
{'loss': 0.6066, 'learning_rate': 0.0002571358682671653, 'epoch': 6.07}

 51%|█████     | 14214/28080 [28:05:27<27:28:05,  7.13s/it]
 51%|█████     | 14215/28080 [28:05:34<27:34:38,  7.16s/it]
                                                           
{'loss': 0.6318, 'learning_rate': 0.00025710704426137627, 'epoch': 6.07}

 51%|█████     | 14215/28080 [28:05:34<27:34:38,  7.16s/it]
 51%|█████     | 14216/28080 [28:05:41<27:33:38,  7.16s/it]
                                                           
{'loss': 0.6344, 'learning_rate': 0.0002570782201610354, 'epoch': 6.07}

 51%|█████     | 14216/28080 [28:05:41<27:33:38,  7.16s/it]
 51%|█████     | 14217/28080 [28:05:48<27:32:43,  7.15s/it]
                                                           
{'loss': 0.6243, 'learning_rate': 0.0002570493959665261, 'epoch': 6.07}

 51%|█████     | 14217/28080 [28:05:48<27:32:43,  7.15s/it]
 51%|█████     | 14218/28080 [28:05:55<27:19:35,  7.10s/it]
                                                           
{'loss': 0.6178, 'learning_rate': 0.00025702057167823183, 'epoch': 6.07}

 51%|█████     | 14218/28080 [28:05:55<27:19:35,  7.10s/it]
 51%|█████     | 14219/28080 [28:06:02<27:22:02,  7.11s/it]
                                                           
{'loss': 0.6218, 'learning_rate': 0.0002569917472965362, 'epoch': 6.07}

 51%|█████     | 14219/28080 [28:06:02<27:22:02,  7.11s/it]
 51%|█████     | 14220/28080 [28:06:09<27:24:47,  7.12s/it]
                                                           
{'loss': 0.5924, 'learning_rate': 0.00025696292282182244, 'epoch': 6.07}

 51%|█████     | 14220/28080 [28:06:09<27:24:47,  7.12s/it]
 51%|█████     | 14221/28080 [28:06:16<27:24:50,  7.12s/it]
                                                           
{'loss': 0.6215, 'learning_rate': 0.0002569340982544743, 'epoch': 6.08}

 51%|█████     | 14221/28080 [28:06:16<27:24:50,  7.12s/it]
 51%|█████     | 14222/28080 [28:06:24<27:21:24,  7.11s/it]
                                                           
{'loss': 0.6471, 'learning_rate': 0.00025690527359487503, 'epoch': 6.08}

 51%|█████     | 14222/28080 [28:06:24<27:21:24,  7.11s/it]
 51%|█████     | 14223/28080 [28:06:31<27:16:06,  7.08s/it]
                                                           
{'loss': 0.6422, 'learning_rate': 0.00025687644884340825, 'epoch': 6.08}

 51%|█████     | 14223/28080 [28:06:31<27:16:06,  7.08s/it]
 51%|█████     | 14224/28080 [28:06:38<27:14:45,  7.08s/it]
                                                           
{'loss': 0.6561, 'learning_rate': 0.00025684762400045747, 'epoch': 6.08}

 51%|█████     | 14224/28080 [28:06:38<27:14:45,  7.08s/it]
 51%|█████     | 14225/28080 [28:06:45<27:15:10,  7.08s/it]
                                                           
{'loss': 0.6335, 'learning_rate': 0.00025681879906640605, 'epoch': 6.08}

 51%|█████     | 14225/28080 [28:06:45<27:15:10,  7.08s/it]
 51%|█████     | 14226/28080 [28:06:52<27:18:28,  7.10s/it]
                                                           
{'loss': 0.607, 'learning_rate': 0.0002567899740416376, 'epoch': 6.08}

 51%|█████     | 14226/28080 [28:06:52<27:18:28,  7.10s/it]
 51%|█████     | 14227/28080 [28:06:59<27:15:35,  7.08s/it]
                                                           
{'loss': 0.6168, 'learning_rate': 0.00025676114892653554, 'epoch': 6.08}

 51%|█████     | 14227/28080 [28:06:59<27:15:35,  7.08s/it]
 51%|█████     | 14228/28080 [28:07:06<27:20:10,  7.10s/it]
                                                           
{'loss': 0.6053, 'learning_rate': 0.00025673232372148334, 'epoch': 6.08}

 51%|█████     | 14228/28080 [28:07:06<27:20:10,  7.10s/it]
 51%|█████     | 14229/28080 [28:07:13<27:20:09,  7.10s/it]
                                                           
{'loss': 0.6123, 'learning_rate': 0.0002567034984268645, 'epoch': 6.08}

 51%|█████     | 14229/28080 [28:07:13<27:20:09,  7.10s/it]
 51%|█████     | 14230/28080 [28:07:20<27:24:32,  7.12s/it]
                                                           
{'loss': 0.6098, 'learning_rate': 0.00025667467304306256, 'epoch': 6.08}

 51%|█████     | 14230/28080 [28:07:20<27:24:32,  7.12s/it]
 51%|█████     | 14231/28080 [28:07:27<27:23:26,  7.12s/it]
                                                           
{'loss': 0.5946, 'learning_rate': 0.00025664584757046103, 'epoch': 6.08}

 51%|█████     | 14231/28080 [28:07:27<27:23:26,  7.12s/it]
 51%|█████     | 14232/28080 [28:07:35<27:24:51,  7.13s/it]
                                                           
{'loss': 0.6069, 'learning_rate': 0.00025661702200944326, 'epoch': 6.08}

 51%|█████     | 14232/28080 [28:07:35<27:24:51,  7.13s/it]
 51%|█████     | 14233/28080 [28:07:42<27:22:19,  7.12s/it]
                                                           
{'loss': 0.6178, 'learning_rate': 0.00025658819636039293, 'epoch': 6.08}

 51%|█████     | 14233/28080 [28:07:42<27:22:19,  7.12s/it]
 51%|█████     | 14234/28080 [28:07:49<27:16:55,  7.09s/it]
                                                           
{'loss': 0.6043, 'learning_rate': 0.00025655937062369336, 'epoch': 6.08}

 51%|█████     | 14234/28080 [28:07:49<27:16:55,  7.09s/it]
 51%|█████     | 14235/28080 [28:07:56<27:00:28,  7.02s/it]
                                                           
{'loss': 0.6352, 'learning_rate': 0.00025653054479972816, 'epoch': 6.08}

 51%|█████     | 14235/28080 [28:07:56<27:00:28,  7.02s/it]
 51%|█████     | 14236/28080 [28:08:03<27:10:38,  7.07s/it]
                                                           
{'loss': 0.6303, 'learning_rate': 0.00025650171888888084, 'epoch': 6.08}

 51%|█████     | 14236/28080 [28:08:03<27:10:38,  7.07s/it]
 51%|█████     | 14237/28080 [28:08:10<27:25:09,  7.13s/it]
                                                           
{'loss': 0.6139, 'learning_rate': 0.00025647289289153485, 'epoch': 6.08}

 51%|█████     | 14237/28080 [28:08:10<27:25:09,  7.13s/it]
 51%|█████     | 14238/28080 [28:08:17<27:18:19,  7.10s/it]
                                                           
{'loss': 0.6162, 'learning_rate': 0.0002564440668080737, 'epoch': 6.08}

 51%|█████     | 14238/28080 [28:08:17<27:18:19,  7.10s/it]
 51%|█████     | 14239/28080 [28:08:24<27:19:37,  7.11s/it]
                                                           
{'loss': 0.6069, 'learning_rate': 0.0002564152406388809, 'epoch': 6.08}

 51%|█████     | 14239/28080 [28:08:24<27:19:37,  7.11s/it]
 51%|█████     | 14240/28080 [28:08:31<27:19:52,  7.11s/it]
                                                           
{'loss': 0.5988, 'learning_rate': 0.0002563864143843398, 'epoch': 6.08}

 51%|█████     | 14240/28080 [28:08:31<27:19:52,  7.11s/it]
 51%|█████     | 14241/28080 [28:08:38<27:13:46,  7.08s/it]
                                                           
{'loss': 0.605, 'learning_rate': 0.0002563575880448342, 'epoch': 6.08}

 51%|█████     | 14241/28080 [28:08:38<27:13:46,  7.08s/it]
 51%|█████     | 14242/28080 [28:08:46<27:22:54,  7.12s/it]
                                                           
{'loss': 0.6117, 'learning_rate': 0.00025632876162074743, 'epoch': 6.08}

 51%|█████     | 14242/28080 [28:08:46<27:22:54,  7.12s/it]
 51%|█████     | 14243/28080 [28:08:53<27:28:13,  7.15s/it]
                                                           
{'loss': 0.606, 'learning_rate': 0.000256299935112463, 'epoch': 6.08}

 51%|█████     | 14243/28080 [28:08:53<27:28:13,  7.15s/it]
 51%|█████     | 14244/28080 [28:09:00<27:26:43,  7.14s/it]
                                                           
{'loss': 0.6074, 'learning_rate': 0.0002562711085203644, 'epoch': 6.08}

 51%|█████     | 14244/28080 [28:09:00<27:26:43,  7.14s/it]
 51%|█████     | 14245/28080 [28:09:07<27:28:11,  7.15s/it]
                                                           
{'loss': 0.6187, 'learning_rate': 0.00025624228184483523, 'epoch': 6.09}

 51%|█████     | 14245/28080 [28:09:07<27:28:11,  7.15s/it]
 51%|█████     | 14246/28080 [28:09:14<27:28:54,  7.15s/it]
                                                           
{'loss': 0.6222, 'learning_rate': 0.0002562134550862588, 'epoch': 6.09}

 51%|█████     | 14246/28080 [28:09:14<27:28:54,  7.15s/it]
 51%|█████     | 14247/28080 [28:09:21<27:36:40,  7.19s/it]
                                                           
{'loss': 0.6471, 'learning_rate': 0.00025618462824501885, 'epoch': 6.09}

 51%|█████     | 14247/28080 [28:09:21<27:36:40,  7.19s/it]
 51%|█████     | 14248/28080 [28:09:29<27:28:52,  7.15s/it]
                                                           
{'loss': 0.6408, 'learning_rate': 0.00025615580132149884, 'epoch': 6.09}

 51%|█████     | 14248/28080 [28:09:29<27:28:52,  7.15s/it]
 51%|█████     | 14249/28080 [28:09:36<27:30:01,  7.16s/it]
                                                           
{'loss': 0.636, 'learning_rate': 0.0002561269743160822, 'epoch': 6.09}

 51%|█████     | 14249/28080 [28:09:36<27:30:01,  7.16s/it]
 51%|█████     | 14250/28080 [28:09:43<27:27:25,  7.15s/it]
                                                           
{'loss': 0.6099, 'learning_rate': 0.00025609814722915255, 'epoch': 6.09}

 51%|█████     | 14250/28080 [28:09:43<27:27:25,  7.15s/it]
 51%|█████     | 14251/28080 [28:09:50<27:21:41,  7.12s/it]
                                                           
{'loss': 0.6236, 'learning_rate': 0.0002560693200610933, 'epoch': 6.09}

 51%|█████     | 14251/28080 [28:09:50<27:21:41,  7.12s/it]
 51%|█████     | 14252/28080 [28:09:57<27:18:23,  7.11s/it]
                                                           
{'loss': 0.6346, 'learning_rate': 0.000256040492812288, 'epoch': 6.09}

 51%|█████     | 14252/28080 [28:09:57<27:18:23,  7.11s/it]
 51%|█████     | 14253/28080 [28:10:04<27:20:38,  7.12s/it]
                                                           
{'loss': 0.6052, 'learning_rate': 0.00025601166548312016, 'epoch': 6.09}

 51%|█████     | 14253/28080 [28:10:04<27:20:38,  7.12s/it]
 51%|█████     | 14254/28080 [28:10:11<27:26:51,  7.15s/it]
                                                           
{'loss': 0.6229, 'learning_rate': 0.0002559828380739733, 'epoch': 6.09}

 51%|█████     | 14254/28080 [28:10:11<27:26:51,  7.15s/it]
 51%|█████     | 14255/28080 [28:10:18<27:23:00,  7.13s/it]
                                                           
{'loss': 0.6332, 'learning_rate': 0.000255954010585231, 'epoch': 6.09}

 51%|█████     | 14255/28080 [28:10:18<27:23:00,  7.13s/it]
 51%|█████     | 14256/28080 [28:10:26<27:21:46,  7.13s/it]
                                                           
{'loss': 0.6163, 'learning_rate': 0.0002559251830172767, 'epoch': 6.09}

 51%|█████     | 14256/28080 [28:10:26<27:21:46,  7.13s/it]
 51%|█████     | 14257/28080 [28:10:33<27:25:44,  7.14s/it]
                                                           
{'loss': 0.61, 'learning_rate': 0.00025589635537049397, 'epoch': 6.09}

 51%|█████     | 14257/28080 [28:10:33<27:25:44,  7.14s/it]
 51%|█████     | 14258/28080 [28:10:40<27:23:23,  7.13s/it]
                                                           
{'loss': 0.6033, 'learning_rate': 0.00025586752764526636, 'epoch': 6.09}

 51%|█████     | 14258/28080 [28:10:40<27:23:23,  7.13s/it]
 51%|█████     | 14259/28080 [28:10:47<27:31:48,  7.17s/it]
                                                           
{'loss': 0.5996, 'learning_rate': 0.00025583869984197727, 'epoch': 6.09}

 51%|█████     | 14259/28080 [28:10:47<27:31:48,  7.17s/it]
 51%|█████     | 14260/28080 [28:10:54<27:31:26,  7.17s/it]
                                                           
{'loss': 0.6155, 'learning_rate': 0.0002558098719610103, 'epoch': 6.09}

 51%|█████     | 14260/28080 [28:10:54<27:31:26,  7.17s/it]
 51%|█████     | 14261/28080 [28:11:01<27:32:47,  7.18s/it]
                                                           
{'loss': 0.6343, 'learning_rate': 0.000255781044002749, 'epoch': 6.09}

 51%|█████     | 14261/28080 [28:11:01<27:32:47,  7.18s/it]
 51%|█████     | 14262/28080 [28:11:09<27:29:06,  7.16s/it]
                                                           
{'loss': 0.6211, 'learning_rate': 0.000255752215967577, 'epoch': 6.09}

 51%|█████     | 14262/28080 [28:11:09<27:29:06,  7.16s/it]
 51%|█████     | 14263/28080 [28:11:16<27:28:32,  7.16s/it]
                                                           
{'loss': 0.6146, 'learning_rate': 0.00025572338785587753, 'epoch': 6.09}

 51%|█████     | 14263/28080 [28:11:16<27:28:32,  7.16s/it]
 51%|█████     | 14264/28080 [28:11:23<27:28:48,  7.16s/it]
                                                           
{'loss': 0.6003, 'learning_rate': 0.0002556945596680343, 'epoch': 6.09}

 51%|█████     | 14264/28080 [28:11:23<27:28:48,  7.16s/it]
 51%|█████     | 14265/28080 [28:11:30<27:25:17,  7.15s/it]
                                                           
{'loss': 0.6166, 'learning_rate': 0.0002556657314044309, 'epoch': 6.09}

 51%|█████     | 14265/28080 [28:11:30<27:25:17,  7.15s/it]
 51%|█████     | 14266/28080 [28:11:37<27:23:58,  7.14s/it]
                                                           
{'loss': 0.6316, 'learning_rate': 0.0002556369030654507, 'epoch': 6.09}

 51%|█████     | 14266/28080 [28:11:37<27:23:58,  7.14s/it]
 51%|█████     | 14267/28080 [28:11:44<27:18:36,  7.12s/it]
                                                           
{'loss': 0.6242, 'learning_rate': 0.00025560807465147743, 'epoch': 6.09}

 51%|█████     | 14267/28080 [28:11:44<27:18:36,  7.12s/it]
 51%|█████     | 14268/28080 [28:11:51<27:19:38,  7.12s/it]
                                                           
{'loss': 0.6017, 'learning_rate': 0.00025557924616289446, 'epoch': 6.1}

 51%|█████     | 14268/28080 [28:11:51<27:19:38,  7.12s/it]
 51%|█████     | 14269/28080 [28:11:58<27:23:30,  7.14s/it]
                                                           
{'loss': 0.6152, 'learning_rate': 0.00025555041760008543, 'epoch': 6.1}

 51%|█████     | 14269/28080 [28:11:58<27:23:30,  7.14s/it]
 51%|█████     | 14270/28080 [28:12:06<27:15:36,  7.11s/it]
                                                           
{'loss': 0.626, 'learning_rate': 0.00025552158896343367, 'epoch': 6.1}

 51%|█████     | 14270/28080 [28:12:06<27:15:36,  7.11s/it]
 51%|█████     | 14271/28080 [28:12:13<27:15:58,  7.11s/it]
                                                           
{'loss': 0.6065, 'learning_rate': 0.000255492760253323, 'epoch': 6.1}

 51%|█████     | 14271/28080 [28:12:13<27:15:58,  7.11s/it]
 51%|█████     | 14272/28080 [28:12:20<27:14:25,  7.10s/it]
                                                           
{'loss': 0.6057, 'learning_rate': 0.0002554639314701368, 'epoch': 6.1}

 51%|█████     | 14272/28080 [28:12:20<27:14:25,  7.10s/it]
 51%|█████     | 14273/28080 [28:12:27<27:11:31,  7.09s/it]
                                                           
{'loss': 0.6141, 'learning_rate': 0.00025543510261425854, 'epoch': 6.1}

 51%|█████     | 14273/28080 [28:12:27<27:11:31,  7.09s/it]
 51%|█████     | 14274/28080 [28:12:34<27:11:26,  7.09s/it]
                                                           
{'loss': 0.6369, 'learning_rate': 0.000255406273686072, 'epoch': 6.1}

 51%|█████     | 14274/28080 [28:12:34<27:11:26,  7.09s/it]
 51%|█████     | 14275/28080 [28:12:41<27:09:15,  7.08s/it]
                                                           
{'loss': 0.6183, 'learning_rate': 0.00025537744468596046, 'epoch': 6.1}

 51%|█████     | 14275/28080 [28:12:41<27:09:15,  7.08s/it]
 51%|█████     | 14276/28080 [28:12:48<27:12:48,  7.10s/it]
                                                           
{'loss': 0.6043, 'learning_rate': 0.0002553486156143076, 'epoch': 6.1}

 51%|█████     | 14276/28080 [28:12:48<27:12:48,  7.10s/it]
 51%|█████     | 14277/28080 [28:12:55<27:18:20,  7.12s/it]
                                                           
{'loss': 0.6053, 'learning_rate': 0.0002553197864714969, 'epoch': 6.1}

 51%|█████     | 14277/28080 [28:12:55<27:18:20,  7.12s/it]
 51%|█████     | 14278/28080 [28:13:02<27:20:31,  7.13s/it]
                                                           
{'loss': 0.6241, 'learning_rate': 0.0002552909572579119, 'epoch': 6.1}

 51%|█████     | 14278/28080 [28:13:02<27:20:31,  7.13s/it]
 51%|█████     | 14279/28080 [28:13:09<27:11:48,  7.09s/it]
                                                           
{'loss': 0.6285, 'learning_rate': 0.00025526212797393627, 'epoch': 6.1}

 51%|█████     | 14279/28080 [28:13:09<27:11:48,  7.09s/it]
 51%|█████     | 14280/28080 [28:13:17<27:12:33,  7.10s/it]
                                                           
{'loss': 0.6143, 'learning_rate': 0.00025523329861995336, 'epoch': 6.1}

 51%|█████     | 14280/28080 [28:13:17<27:12:33,  7.10s/it]
 51%|█████     | 14281/28080 [28:13:23<26:59:10,  7.04s/it]
                                                           
{'loss': 0.6149, 'learning_rate': 0.0002552044691963469, 'epoch': 6.1}

 51%|█████     | 14281/28080 [28:13:23<26:59:10,  7.04s/it]
 51%|█████     | 14282/28080 [28:13:31<27:06:13,  7.07s/it]
                                                           
{'loss': 0.6194, 'learning_rate': 0.00025517563970350025, 'epoch': 6.1}

 51%|█████     | 14282/28080 [28:13:31<27:06:13,  7.07s/it]
 51%|█████     | 14283/28080 [28:13:38<27:09:46,  7.09s/it]
                                                           
{'loss': 0.595, 'learning_rate': 0.0002551468101417971, 'epoch': 6.1}

 51%|█████     | 14283/28080 [28:13:38<27:09:46,  7.09s/it]
 51%|█████     | 14284/28080 [28:13:45<27:10:16,  7.09s/it]
                                                           
{'loss': 0.6096, 'learning_rate': 0.00025511798051162097, 'epoch': 6.1}

 51%|█████     | 14284/28080 [28:13:45<27:10:16,  7.09s/it]
 51%|█████     | 14285/28080 [28:13:52<27:11:56,  7.10s/it]
                                                           
{'loss': 0.6214, 'learning_rate': 0.00025508915081335536, 'epoch': 6.1}

 51%|█████     | 14285/28080 [28:13:52<27:11:56,  7.10s/it]
 51%|█████     | 14286/28080 [28:13:59<27:19:03,  7.13s/it]
                                                           
{'loss': 0.6107, 'learning_rate': 0.0002550603210473839, 'epoch': 6.1}

 51%|█████     | 14286/28080 [28:13:59<27:19:03,  7.13s/it]
 51%|█████     | 14287/28080 [28:14:06<27:17:10,  7.12s/it]
                                                           
{'loss': 0.6103, 'learning_rate': 0.0002550314912140901, 'epoch': 6.1}

 51%|█████     | 14287/28080 [28:14:06<27:17:10,  7.12s/it]
 51%|█████     | 14288/28080 [28:14:13<27:15:55,  7.12s/it]
                                                           
{'loss': 0.6295, 'learning_rate': 0.0002550026613138574, 'epoch': 6.1}

 51%|█████     | 14288/28080 [28:14:13<27:15:55,  7.12s/it]
 51%|█████     | 14289/28080 [28:14:21<27:21:41,  7.14s/it]
                                                           
{'loss': 0.6308, 'learning_rate': 0.00025497383134706955, 'epoch': 6.1}

 51%|█████     | 14289/28080 [28:14:21<27:21:41,  7.14s/it]
 51%|█████     | 14290/28080 [28:14:28<27:18:29,  7.13s/it]
                                                           
{'loss': 0.6154, 'learning_rate': 0.0002549450013141099, 'epoch': 6.1}

 51%|█████     | 14290/28080 [28:14:28<27:18:29,  7.13s/it]
 51%|█████     | 14291/28080 [28:14:35<27:17:55,  7.13s/it]
                                                           
{'loss': 0.6063, 'learning_rate': 0.00025491617121536225, 'epoch': 6.1}

 51%|█████     | 14291/28080 [28:14:35<27:17:55,  7.13s/it]
 51%|█████     | 14292/28080 [28:14:42<27:16:29,  7.12s/it]
                                                           
{'loss': 0.6184, 'learning_rate': 0.00025488734105120987, 'epoch': 6.11}

 51%|█████     | 14292/28080 [28:14:42<27:16:29,  7.12s/it]
 51%|█████     | 14293/28080 [28:14:49<27:14:03,  7.11s/it]
                                                           
{'loss': 0.6059, 'learning_rate': 0.0002548585108220366, 'epoch': 6.11}

 51%|█████     | 14293/28080 [28:14:49<27:14:03,  7.11s/it]
 51%|█████     | 14294/28080 [28:14:56<27:08:51,  7.09s/it]
                                                           
{'loss': 0.6289, 'learning_rate': 0.00025482968052822577, 'epoch': 6.11}

 51%|█████     | 14294/28080 [28:14:56<27:08:51,  7.09s/it]
 51%|█████     | 14295/28080 [28:15:03<27:06:14,  7.08s/it]
                                                           
{'loss': 0.6354, 'learning_rate': 0.00025480085017016096, 'epoch': 6.11}

 51%|█████     | 14295/28080 [28:15:03<27:06:14,  7.08s/it]
 51%|█████     | 14296/28080 [28:15:10<27:04:02,  7.07s/it]
                                                           
{'loss': 0.6288, 'learning_rate': 0.0002547720197482259, 'epoch': 6.11}

 51%|█████     | 14296/28080 [28:15:10<27:04:02,  7.07s/it]
 51%|█████     | 14297/28080 [28:15:17<27:00:10,  7.05s/it]
                                                           
{'loss': 0.609, 'learning_rate': 0.000254743189262804, 'epoch': 6.11}

 51%|█████     | 14297/28080 [28:15:17<27:00:10,  7.05s/it]
 51%|█████     | 14298/28080 [28:15:24<27:04:23,  7.07s/it]
                                                           
{'loss': 0.6108, 'learning_rate': 0.00025471435871427884, 'epoch': 6.11}

 51%|█████     | 14298/28080 [28:15:24<27:04:23,  7.07s/it]
 51%|█████     | 14299/28080 [28:15:31<26:57:49,  7.04s/it]
                                                           
{'loss': 0.5963, 'learning_rate': 0.000254685528103034, 'epoch': 6.11}

 51%|█████     | 14299/28080 [28:15:31<26:57:49,  7.04s/it]
 51%|█████     | 14300/28080 [28:15:38<27:11:01,  7.10s/it]
                                                           
{'loss': 0.604, 'learning_rate': 0.00025465669742945313, 'epoch': 6.11}

 51%|█████     | 14300/28080 [28:15:38<27:11:01,  7.10s/it]
 51%|█████     | 14301/28080 [28:15:45<27:07:57,  7.09s/it]
                                                           
{'loss': 0.6182, 'learning_rate': 0.0002546278666939196, 'epoch': 6.11}

 51%|█████     | 14301/28080 [28:15:45<27:07:57,  7.09s/it]
 51%|█████     | 14302/28080 [28:15:53<27:14:51,  7.12s/it]
                                                           
{'loss': 0.6296, 'learning_rate': 0.0002545990358968171, 'epoch': 6.11}

 51%|█████     | 14302/28080 [28:15:53<27:14:51,  7.12s/it]
 51%|█████     | 14303/28080 [28:16:00<27:16:58,  7.13s/it]
                                                           
{'loss': 0.6333, 'learning_rate': 0.00025457020503852926, 'epoch': 6.11}

 51%|█████     | 14303/28080 [28:16:00<27:16:58,  7.13s/it]
 51%|█████     | 14304/28080 [28:16:07<27:14:41,  7.12s/it]
                                                           
{'loss': 0.6064, 'learning_rate': 0.00025454137411943937, 'epoch': 6.11}

 51%|█████     | 14304/28080 [28:16:07<27:14:41,  7.12s/it]
 51%|█████     | 14305/28080 [28:16:14<27:19:18,  7.14s/it]
                                                           
{'loss': 0.6064, 'learning_rate': 0.0002545125431399314, 'epoch': 6.11}

 51%|█████     | 14305/28080 [28:16:14<27:19:18,  7.14s/it]
 51%|█████     | 14306/28080 [28:16:21<27:15:06,  7.12s/it]
                                                           
{'loss': 0.6178, 'learning_rate': 0.00025448371210038854, 'epoch': 6.11}

 51%|█████     | 14306/28080 [28:16:21<27:15:06,  7.12s/it]
 51%|█████     | 14307/28080 [28:16:28<27:10:20,  7.10s/it]
                                                           
{'loss': 0.6019, 'learning_rate': 0.0002544548810011946, 'epoch': 6.11}

 51%|█████     | 14307/28080 [28:16:28<27:10:20,  7.10s/it]
 51%|█████     | 14308/28080 [28:16:35<27:11:09,  7.11s/it]
                                                           
{'loss': 0.6222, 'learning_rate': 0.00025442604984273306, 'epoch': 6.11}

 51%|█████     | 14308/28080 [28:16:35<27:11:09,  7.11s/it]
 51%|█████     | 14309/28080 [28:16:42<27:13:47,  7.12s/it]
                                                           
{'loss': 0.6023, 'learning_rate': 0.0002543972186253874, 'epoch': 6.11}

 51%|█████     | 14309/28080 [28:16:43<27:13:47,  7.12s/it]
 51%|█████     | 14310/28080 [28:16:50<27:16:11,  7.13s/it]
                                                           
{'loss': 0.6076, 'learning_rate': 0.00025436838734954137, 'epoch': 6.11}

 51%|█████     | 14310/28080 [28:16:50<27:16:11,  7.13s/it]
 51%|█████     | 14311/28080 [28:16:57<27:07:58,  7.09s/it]
                                                           
{'loss': 0.6027, 'learning_rate': 0.00025433955601557843, 'epoch': 6.11}

 51%|█████     | 14311/28080 [28:16:57<27:07:58,  7.09s/it]
 51%|█████     | 14312/28080 [28:17:04<27:06:15,  7.09s/it]
                                                           
{'loss': 0.6156, 'learning_rate': 0.0002543107246238822, 'epoch': 6.11}

 51%|█████     | 14312/28080 [28:17:04<27:06:15,  7.09s/it]
 51%|█████     | 14313/28080 [28:17:11<27:17:04,  7.13s/it]
                                                           
{'loss': 0.6387, 'learning_rate': 0.00025428189317483626, 'epoch': 6.11}

 51%|█████     | 14313/28080 [28:17:11<27:17:04,  7.13s/it]
 51%|█████     | 14314/28080 [28:17:18<27:20:02,  7.15s/it]
                                                           
{'loss': 0.6145, 'learning_rate': 0.00025425306166882404, 'epoch': 6.11}

 51%|█████     | 14314/28080 [28:17:18<27:20:02,  7.15s/it]
 51%|█████     | 14315/28080 [28:17:25<27:24:47,  7.17s/it]
                                                           
{'loss': 0.623, 'learning_rate': 0.0002542242301062293, 'epoch': 6.12}

 51%|█████     | 14315/28080 [28:17:25<27:24:47,  7.17s/it]
 51%|█████     | 14316/28080 [28:17:32<27:15:34,  7.13s/it]
                                                           
{'loss': 0.6273, 'learning_rate': 0.0002541953984874355, 'epoch': 6.12}

 51%|█████     | 14316/28080 [28:17:32<27:15:34,  7.13s/it]
 51%|█████     | 14317/28080 [28:17:40<27:14:58,  7.13s/it]
                                                           
{'loss': 0.6205, 'learning_rate': 0.0002541665668128263, 'epoch': 6.12}

 51%|█████     | 14317/28080 [28:17:40<27:14:58,  7.13s/it]
 51%|█████     | 14318/28080 [28:17:47<27:12:38,  7.12s/it]
                                                           
{'loss': 0.6269, 'learning_rate': 0.0002541377350827852, 'epoch': 6.12}

 51%|█████     | 14318/28080 [28:17:47<27:12:38,  7.12s/it]
 51%|█████     | 14319/28080 [28:17:54<27:14:37,  7.13s/it]
                                                           
{'loss': 0.6033, 'learning_rate': 0.00025410890329769577, 'epoch': 6.12}

 51%|█████     | 14319/28080 [28:17:54<27:14:37,  7.13s/it]
 51%|█████     | 14320/28080 [28:18:01<27:20:46,  7.15s/it]
                                                           
{'loss': 0.6234, 'learning_rate': 0.0002540800714579417, 'epoch': 6.12}

 51%|█████     | 14320/28080 [28:18:01<27:20:46,  7.15s/it]
 51%|█████     | 14321/28080 [28:18:08<27:21:26,  7.16s/it]
                                                           
{'loss': 0.6241, 'learning_rate': 0.00025405123956390635, 'epoch': 6.12}

 51%|█████     | 14321/28080 [28:18:08<27:21:26,  7.16s/it]
 51%|█████     | 14322/28080 [28:18:15<27:23:06,  7.17s/it]
                                                           
{'loss': 0.6279, 'learning_rate': 0.00025402240761597354, 'epoch': 6.12}

 51%|█████     | 14322/28080 [28:18:15<27:23:06,  7.17s/it]
 51%|█████     | 14323/28080 [28:18:23<27:27:57,  7.19s/it]
                                                           
{'loss': 0.6302, 'learning_rate': 0.00025399357561452674, 'epoch': 6.12}

 51%|█████     | 14323/28080 [28:18:23<27:27:57,  7.19s/it]
 51%|█████     | 14324/28080 [28:18:30<27:29:48,  7.20s/it]
                                                           
{'loss': 0.6262, 'learning_rate': 0.00025396474355994953, 'epoch': 6.12}

 51%|█████     | 14324/28080 [28:18:30<27:29:48,  7.20s/it]
 51%|█████     | 14325/28080 [28:18:37<27:20:54,  7.16s/it]
                                                           
{'loss': 0.6308, 'learning_rate': 0.00025393591145262545, 'epoch': 6.12}

 51%|█████     | 14325/28080 [28:18:37<27:20:54,  7.16s/it]
 51%|█████     | 14326/28080 [28:18:44<27:16:12,  7.14s/it]
                                                           
{'loss': 0.6226, 'learning_rate': 0.00025390707929293815, 'epoch': 6.12}

 51%|█████     | 14326/28080 [28:18:44<27:16:12,  7.14s/it]
 51%|█████     | 14327/28080 [28:18:51<27:14:21,  7.13s/it]
                                                           
{'loss': 0.6144, 'learning_rate': 0.00025387824708127127, 'epoch': 6.12}

 51%|█████     | 14327/28080 [28:18:51<27:14:21,  7.13s/it]
 51%|█████     | 14328/28080 [28:18:58<27:15:59,  7.14s/it]
                                                           
{'loss': 0.592, 'learning_rate': 0.00025384941481800823, 'epoch': 6.12}

 51%|█████     | 14328/28080 [28:18:58<27:15:59,  7.14s/it]
 51%|█████     | 14329/28080 [28:19:05<27:15:33,  7.14s/it]
                                                           
{'loss': 0.6072, 'learning_rate': 0.00025382058250353275, 'epoch': 6.12}

 51%|█████     | 14329/28080 [28:19:05<27:15:33,  7.14s/it]
 51%|█████     | 14330/28080 [28:19:13<27:16:10,  7.14s/it]
                                                           
{'loss': 0.6304, 'learning_rate': 0.0002537917501382283, 'epoch': 6.12}

 51%|█████     | 14330/28080 [28:19:13<27:16:10,  7.14s/it]
 51%|█████     | 14331/28080 [28:19:20<27:16:06,  7.14s/it]
                                                           
{'loss': 0.6017, 'learning_rate': 0.0002537629177224786, 'epoch': 6.12}

 51%|█████     | 14331/28080 [28:19:20<27:16:06,  7.14s/it]
 51%|█████     | 14332/28080 [28:19:27<27:16:15,  7.14s/it]
                                                           
{'loss': 0.63, 'learning_rate': 0.0002537340852566671, 'epoch': 6.12}

 51%|█████     | 14332/28080 [28:19:27<27:16:15,  7.14s/it]
 51%|█████     | 14333/28080 [28:19:34<27:13:01,  7.13s/it]
                                                           
{'loss': 0.6148, 'learning_rate': 0.00025370525274117744, 'epoch': 6.12}

 51%|█████     | 14333/28080 [28:19:34<27:13:01,  7.13s/it]
 51%|█████     | 14334/28080 [28:19:41<27:15:48,  7.14s/it]
                                                           
{'loss': 0.6184, 'learning_rate': 0.00025367642017639323, 'epoch': 6.12}

 51%|█████     | 14334/28080 [28:19:41<27:15:48,  7.14s/it]
 51%|█████     | 14335/28080 [28:19:48<27:10:31,  7.12s/it]
                                                           
{'loss': 0.613, 'learning_rate': 0.00025364758756269806, 'epoch': 6.12}

 51%|█████     | 14335/28080 [28:19:48<27:10:31,  7.12s/it]
 51%|█████     | 14336/28080 [28:19:55<27:05:24,  7.10s/it]
                                                           
{'loss': 0.6111, 'learning_rate': 0.0002536187549004755, 'epoch': 6.12}

 51%|█████     | 14336/28080 [28:19:55<27:05:24,  7.10s/it]
 51%|█████     | 14337/28080 [28:20:02<27:10:53,  7.12s/it]
                                                           
{'loss': 0.5989, 'learning_rate': 0.0002535899221901092, 'epoch': 6.12}

 51%|█████     | 14337/28080 [28:20:02<27:10:53,  7.12s/it]
 51%|█████     | 14338/28080 [28:20:09<27:04:14,  7.09s/it]
                                                           
{'loss': 0.6205, 'learning_rate': 0.00025356108943198257, 'epoch': 6.13}

 51%|█████     | 14338/28080 [28:20:09<27:04:14,  7.09s/it]
 51%|█████     | 14339/28080 [28:20:16<27:01:23,  7.08s/it]
                                                           
{'loss': 0.6175, 'learning_rate': 0.00025353225662647945, 'epoch': 6.13}

 51%|█████     | 14339/28080 [28:20:16<27:01:23,  7.08s/it]
 51%|█████     | 14340/28080 [28:20:24<27:01:53,  7.08s/it]
                                                           
{'loss': 0.6276, 'learning_rate': 0.00025350342377398316, 'epoch': 6.13}

 51%|█████     | 14340/28080 [28:20:24<27:01:53,  7.08s/it]
 51%|█████     | 14341/28080 [28:20:31<27:06:37,  7.10s/it]
                                                           
{'loss': 0.623, 'learning_rate': 0.00025347459087487757, 'epoch': 6.13}

 51%|█████     | 14341/28080 [28:20:31<27:06:37,  7.10s/it]
 51%|█████     | 14342/28080 [28:20:38<27:05:32,  7.10s/it]
                                                           
{'loss': 0.6154, 'learning_rate': 0.000253445757929546, 'epoch': 6.13}

 51%|█████     | 14342/28080 [28:20:38<27:05:32,  7.10s/it]
 51%|█████     | 14343/28080 [28:20:45<27:06:19,  7.10s/it]
                                                           
{'loss': 0.6221, 'learning_rate': 0.0002534169249383722, 'epoch': 6.13}

 51%|█████     | 14343/28080 [28:20:45<27:06:19,  7.10s/it]
 51%|█████     | 14344/28080 [28:20:52<27:05:40,  7.10s/it]
                                                           
{'loss': 0.628, 'learning_rate': 0.00025338809190173986, 'epoch': 6.13}

 51%|█████     | 14344/28080 [28:20:52<27:05:40,  7.10s/it]
 51%|█████     | 14345/28080 [28:20:59<27:06:19,  7.10s/it]
                                                           
{'loss': 0.6088, 'learning_rate': 0.0002533592588200323, 'epoch': 6.13}

 51%|█████     | 14345/28080 [28:20:59<27:06:19,  7.10s/it]
 51%|█████     | 14346/28080 [28:21:06<27:05:56,  7.10s/it]
                                                           
{'loss': 0.6431, 'learning_rate': 0.00025333042569363335, 'epoch': 6.13}

 51%|█████     | 14346/28080 [28:21:06<27:05:56,  7.10s/it]
 51%|█████     | 14347/28080 [28:21:13<27:12:37,  7.13s/it]
                                                           
{'loss': 0.6233, 'learning_rate': 0.00025330159252292644, 'epoch': 6.13}

 51%|█████     | 14347/28080 [28:21:13<27:12:37,  7.13s/it]
 51%|█████     | 14348/28080 [28:21:20<27:09:11,  7.12s/it]
                                                           
{'loss': 0.63, 'learning_rate': 0.00025327275930829535, 'epoch': 6.13}

 51%|█████     | 14348/28080 [28:21:20<27:09:11,  7.12s/it]
 51%|█████     | 14349/28080 [28:21:28<27:15:47,  7.15s/it]
                                                           
{'loss': 0.6112, 'learning_rate': 0.0002532439260501235, 'epoch': 6.13}

 51%|█████     | 14349/28080 [28:21:28<27:15:47,  7.15s/it]
 51%|█████     | 14350/28080 [28:21:35<27:14:08,  7.14s/it]
                                                           
{'loss': 0.6256, 'learning_rate': 0.00025321509274879464, 'epoch': 6.13}

 51%|█████     | 14350/28080 [28:21:35<27:14:08,  7.14s/it]
 51%|█████     | 14351/28080 [28:21:42<27:18:02,  7.16s/it]
                                                           
{'loss': 0.61, 'learning_rate': 0.00025318625940469225, 'epoch': 6.13}

 51%|█████     | 14351/28080 [28:21:42<27:18:02,  7.16s/it]
 51%|█████     | 14352/28080 [28:21:49<27:11:50,  7.13s/it]
                                                           
{'loss': 0.6324, 'learning_rate': 0.0002531574260181999, 'epoch': 6.13}

 51%|█████     | 14352/28080 [28:21:49<27:11:50,  7.13s/it]
 51%|█████     | 14353/28080 [28:21:56<27:13:54,  7.14s/it]
                                                           
{'loss': 0.6162, 'learning_rate': 0.00025312859258970136, 'epoch': 6.13}

 51%|█████     | 14353/28080 [28:21:56<27:13:54,  7.14s/it]
 51%|█████     | 14354/28080 [28:22:03<27:06:18,  7.11s/it]
                                                           
{'loss': 0.6139, 'learning_rate': 0.00025309975911958003, 'epoch': 6.13}

 51%|█████     | 14354/28080 [28:22:03<27:06:18,  7.11s/it]
 51%|█████     | 14355/28080 [28:22:10<27:07:29,  7.11s/it]
                                                           
{'loss': 0.6155, 'learning_rate': 0.0002530709256082197, 'epoch': 6.13}

 51%|█████     | 14355/28080 [28:22:10<27:07:29,  7.11s/it]
 51%|█████     | 14356/28080 [28:22:18<27:10:23,  7.13s/it]
                                                           
{'loss': 0.6261, 'learning_rate': 0.0002530420920560038, 'epoch': 6.13}

 51%|█████     | 14356/28080 [28:22:18<27:10:23,  7.13s/it]
 51%|█████     | 14357/28080 [28:22:25<27:03:36,  7.10s/it]
                                                           
{'loss': 0.6343, 'learning_rate': 0.000253013258463316, 'epoch': 6.13}

 51%|█████     | 14357/28080 [28:22:25<27:03:36,  7.10s/it]
 51%|█████     | 14358/28080 [28:22:32<27:02:41,  7.10s/it]
                                                           
{'loss': 0.5967, 'learning_rate': 0.00025298442483054, 'epoch': 6.13}

 51%|█████     | 14358/28080 [28:22:32<27:02:41,  7.10s/it]
 51%|█████     | 14359/28080 [28:22:39<27:04:56,  7.11s/it]
                                                           
{'loss': 0.6092, 'learning_rate': 0.00025295559115805916, 'epoch': 6.13}

 51%|█████     | 14359/28080 [28:22:39<27:04:56,  7.11s/it]
 51%|█████     | 14360/28080 [28:22:46<26:58:34,  7.08s/it]
                                                           
{'loss': 0.6483, 'learning_rate': 0.0002529267574462573, 'epoch': 6.13}

 51%|█████     | 14360/28080 [28:22:46<26:58:34,  7.08s/it]
 51%|█████     | 14361/28080 [28:22:53<26:58:30,  7.08s/it]
                                                           
{'loss': 0.6125, 'learning_rate': 0.00025289792369551794, 'epoch': 6.13}

 51%|█████     | 14361/28080 [28:22:53<26:58:30,  7.08s/it]
 51%|█████     | 14362/28080 [28:23:00<26:51:20,  7.05s/it]
                                                           
{'loss': 0.6142, 'learning_rate': 0.00025286908990622474, 'epoch': 6.14}

 51%|█████     | 14362/28080 [28:23:00<26:51:20,  7.05s/it]
 51%|█████     | 14363/28080 [28:23:07<26:53:53,  7.06s/it]
                                                           
{'loss': 0.6171, 'learning_rate': 0.0002528402560787613, 'epoch': 6.14}

 51%|█████     | 14363/28080 [28:23:07<26:53:53,  7.06s/it]
 51%|█████     | 14364/28080 [28:23:14<27:05:45,  7.11s/it]
                                                           
{'loss': 0.6076, 'learning_rate': 0.00025281142221351104, 'epoch': 6.14}

 51%|█████     | 14364/28080 [28:23:14<27:05:45,  7.11s/it]
 51%|█████     | 14365/28080 [28:23:21<27:08:09,  7.12s/it]
                                                           
{'loss': 0.5973, 'learning_rate': 0.00025278258831085783, 'epoch': 6.14}

 51%|█████     | 14365/28080 [28:23:21<27:08:09,  7.12s/it]
 51%|█████     | 14366/28080 [28:23:29<27:12:53,  7.14s/it]
                                                           
{'loss': 0.6245, 'learning_rate': 0.0002527537543711851, 'epoch': 6.14}

 51%|█████     | 14366/28080 [28:23:29<27:12:53,  7.14s/it]
 51%|█████     | 14367/28080 [28:23:36<27:07:22,  7.12s/it]
                                                           
{'loss': 0.6296, 'learning_rate': 0.0002527249203948765, 'epoch': 6.14}

 51%|█████     | 14367/28080 [28:23:36<27:07:22,  7.12s/it]
 51%|█████     | 14368/28080 [28:23:43<27:04:46,  7.11s/it]
                                                           
{'loss': 0.6055, 'learning_rate': 0.0002526960863823157, 'epoch': 6.14}

 51%|█████     | 14368/28080 [28:23:43<27:04:46,  7.11s/it]
 51%|█████     | 14369/28080 [28:23:50<27:03:52,  7.11s/it]
                                                           
{'loss': 0.625, 'learning_rate': 0.00025266725233388614, 'epoch': 6.14}

 51%|█████     | 14369/28080 [28:23:50<27:03:52,  7.11s/it]
 51%|█████     | 14370/28080 [28:23:57<27:10:14,  7.13s/it]
                                                           
{'loss': 0.6007, 'learning_rate': 0.0002526384182499716, 'epoch': 6.14}

 51%|█████     | 14370/28080 [28:23:57<27:10:14,  7.13s/it]
 51%|█████     | 14371/28080 [28:24:04<27:09:50,  7.13s/it]
                                                           
{'loss': 0.6152, 'learning_rate': 0.0002526095841309556, 'epoch': 6.14}

 51%|█████     | 14371/28080 [28:24:04<27:09:50,  7.13s/it]
 51%|█████     | 14372/28080 [28:24:11<27:09:43,  7.13s/it]
                                                           
{'loss': 0.6208, 'learning_rate': 0.0002525807499772219, 'epoch': 6.14}

 51%|█████     | 14372/28080 [28:24:11<27:09:43,  7.13s/it]
 51%|█████     | 14373/28080 [28:24:18<27:08:00,  7.13s/it]
                                                           
{'loss': 0.6049, 'learning_rate': 0.0002525519157891539, 'epoch': 6.14}

 51%|█████     | 14373/28080 [28:24:18<27:08:00,  7.13s/it]
 51%|█████     | 14374/28080 [28:24:25<27:06:38,  7.12s/it]
                                                           
{'loss': 0.6239, 'learning_rate': 0.0002525230815671352, 'epoch': 6.14}

 51%|█████     | 14374/28080 [28:24:25<27:06:38,  7.12s/it]
 51%|█████     | 14375/28080 [28:24:33<27:10:42,  7.14s/it]
                                                           
{'loss': 0.6173, 'learning_rate': 0.00025249424731154963, 'epoch': 6.14}

 51%|█████     | 14375/28080 [28:24:33<27:10:42,  7.14s/it]
 51%|█████     | 14376/28080 [28:24:40<27:10:30,  7.14s/it]
                                                           
{'loss': 0.6248, 'learning_rate': 0.00025246541302278064, 'epoch': 6.14}

 51%|█████     | 14376/28080 [28:24:40<27:10:30,  7.14s/it]
 51%|█████     | 14377/28080 [28:24:47<27:16:15,  7.16s/it]
                                                           
{'loss': 0.63, 'learning_rate': 0.0002524365787012119, 'epoch': 6.14}

 51%|█████     | 14377/28080 [28:24:47<27:16:15,  7.16s/it]
 51%|█████     | 14378/28080 [28:24:54<27:14:43,  7.16s/it]
                                                           
{'loss': 0.6146, 'learning_rate': 0.00025240774434722693, 'epoch': 6.14}

 51%|█████     | 14378/28080 [28:24:54<27:14:43,  7.16s/it]
 51%|█████     | 14379/28080 [28:25:01<27:14:45,  7.16s/it]
                                                           
{'loss': 0.6475, 'learning_rate': 0.00025237890996120945, 'epoch': 6.14}

 51%|█████     | 14379/28080 [28:25:01<27:14:45,  7.16s/it]
 51%|█████     | 14380/28080 [28:25:08<27:15:03,  7.16s/it]
                                                           
{'loss': 0.6116, 'learning_rate': 0.00025235007554354303, 'epoch': 6.14}

 51%|█████     | 14380/28080 [28:25:08<27:15:03,  7.16s/it]
 51%|█████     | 14381/28080 [28:25:16<27:11:52,  7.15s/it]
                                                           
{'loss': 0.6128, 'learning_rate': 0.0002523212410946112, 'epoch': 6.14}

 51%|█████     | 14381/28080 [28:25:16<27:11:52,  7.15s/it]
 51%|█████     | 14382/28080 [28:25:23<27:08:44,  7.13s/it]
                                                           
{'loss': 0.618, 'learning_rate': 0.00025229240661479776, 'epoch': 6.14}

 51%|█████     | 14382/28080 [28:25:23<27:08:44,  7.13s/it]
 51%|█████     | 14383/28080 [28:25:30<27:09:15,  7.14s/it]
                                                           
{'loss': 0.6169, 'learning_rate': 0.00025226357210448615, 'epoch': 6.14}

 51%|█████     | 14383/28080 [28:25:30<27:09:15,  7.14s/it]
 51%|█████     | 14384/28080 [28:25:37<27:13:59,  7.16s/it]
                                                           
{'loss': 0.6415, 'learning_rate': 0.00025223473756406006, 'epoch': 6.14}

 51%|█████     | 14384/28080 [28:25:37<27:13:59,  7.16s/it]
 51%|█████     | 14385/28080 [28:25:44<27:16:17,  7.17s/it]
                                                           
{'loss': 0.6191, 'learning_rate': 0.0002522059029939031, 'epoch': 6.15}

 51%|█████     | 14385/28080 [28:25:44<27:16:17,  7.17s/it]
 51%|█████     | 14386/28080 [28:25:51<27:14:38,  7.16s/it]
                                                           
{'loss': 0.5986, 'learning_rate': 0.0002521770683943989, 'epoch': 6.15}

 51%|█████     | 14386/28080 [28:25:51<27:14:38,  7.16s/it]
 51%|█████     | 14387/28080 [28:25:59<27:11:08,  7.15s/it]
                                                           
{'loss': 0.6048, 'learning_rate': 0.00025214823376593104, 'epoch': 6.15}

 51%|█████     | 14387/28080 [28:25:59<27:11:08,  7.15s/it]
 51%|█████     | 14388/28080 [28:26:06<27:08:02,  7.13s/it]
                                                           
{'loss': 0.6028, 'learning_rate': 0.0002521193991088831, 'epoch': 6.15}

 51%|█████     | 14388/28080 [28:26:06<27:08:02,  7.13s/it]
 51%|█████     | 14389/28080 [28:26:13<26:58:12,  7.09s/it]
                                                           
{'loss': 0.6201, 'learning_rate': 0.0002520905644236388, 'epoch': 6.15}

 51%|█████     | 14389/28080 [28:26:13<26:58:12,  7.09s/it]
 51%|█████     | 14390/28080 [28:26:20<26:54:41,  7.08s/it]
                                                           
{'loss': 0.6406, 'learning_rate': 0.00025206172971058166, 'epoch': 6.15}

 51%|█████     | 14390/28080 [28:26:20<26:54:41,  7.08s/it]
 51%|█████▏    | 14391/28080 [28:26:27<26:54:53,  7.08s/it]
                                                           
{'loss': 0.6174, 'learning_rate': 0.00025203289497009534, 'epoch': 6.15}

 51%|█████▏    | 14391/28080 [28:26:27<26:54:53,  7.08s/it]
 51%|█████▏    | 14392/28080 [28:26:34<26:43:45,  7.03s/it]
                                                           
{'loss': 0.6471, 'learning_rate': 0.0002520040602025635, 'epoch': 6.15}

 51%|█████▏    | 14392/28080 [28:26:34<26:43:45,  7.03s/it]
 51%|█████▏    | 14393/28080 [28:26:41<26:54:57,  7.08s/it]
                                                           
{'loss': 0.6225, 'learning_rate': 0.0002519752254083696, 'epoch': 6.15}

 51%|█████▏    | 14393/28080 [28:26:41<26:54:57,  7.08s/it]
 51%|█████▏    | 14394/28080 [28:26:48<26:51:37,  7.07s/it]
                                                           
{'loss': 0.6164, 'learning_rate': 0.0002519463905878975, 'epoch': 6.15}

 51%|█████▏    | 14394/28080 [28:26:48<26:51:37,  7.07s/it]
 51%|█████▏    | 14395/28080 [28:26:55<26:56:08,  7.09s/it]
                                                           
{'loss': 0.6264, 'learning_rate': 0.00025191755574153053, 'epoch': 6.15}

 51%|█████▏    | 14395/28080 [28:26:55<26:56:08,  7.09s/it]
 51%|█████▏    | 14396/28080 [28:27:02<26:59:57,  7.10s/it]
                                                           
{'loss': 0.6202, 'learning_rate': 0.00025188872086965257, 'epoch': 6.15}

 51%|█████▏    | 14396/28080 [28:27:02<26:59:57,  7.10s/it]
 51%|█████▏    | 14397/28080 [28:27:09<27:00:25,  7.11s/it]
                                                           
{'loss': 0.6267, 'learning_rate': 0.0002518598859726471, 'epoch': 6.15}

 51%|█████▏    | 14397/28080 [28:27:09<27:00:25,  7.11s/it]
 51%|█████▏    | 14398/28080 [28:27:16<27:06:20,  7.13s/it]
                                                           
{'loss': 0.6047, 'learning_rate': 0.0002518310510508977, 'epoch': 6.15}

 51%|█████▏    | 14398/28080 [28:27:16<27:06:20,  7.13s/it]
 51%|█████▏    | 14399/28080 [28:27:24<27:10:18,  7.15s/it]
                                                           
{'loss': 0.6322, 'learning_rate': 0.00025180221610478817, 'epoch': 6.15}

 51%|█████▏    | 14399/28080 [28:27:24<27:10:18,  7.15s/it]
 51%|█████▏    | 14400/28080 [28:27:31<27:10:00,  7.15s/it]
                                                           
{'loss': 0.6322, 'learning_rate': 0.00025177338113470193, 'epoch': 6.15}

 51%|█████▏    | 14400/28080 [28:27:31<27:10:00,  7.15s/it]
 51%|█████▏    | 14401/28080 [28:27:38<27:14:35,  7.17s/it]
                                                           
{'loss': 0.5993, 'learning_rate': 0.0002517445461410227, 'epoch': 6.15}

 51%|█████▏    | 14401/28080 [28:27:38<27:14:35,  7.17s/it]
 51%|█████▏    | 14402/28080 [28:27:45<27:13:39,  7.17s/it]
                                                           
{'loss': 0.6269, 'learning_rate': 0.0002517157111241341, 'epoch': 6.15}

 51%|█████▏    | 14402/28080 [28:27:45<27:13:39,  7.17s/it]
 51%|█████▏    | 14403/28080 [28:27:52<27:08:25,  7.14s/it]
                                                           
{'loss': 0.6063, 'learning_rate': 0.00025168687608441973, 'epoch': 6.15}

 51%|█████▏    | 14403/28080 [28:27:52<27:08:25,  7.14s/it]
 51%|█████▏    | 14404/28080 [28:27:59<27:08:37,  7.15s/it]
                                                           
{'loss': 0.6263, 'learning_rate': 0.0002516580410222632, 'epoch': 6.15}

 51%|█████▏    | 14404/28080 [28:27:59<27:08:37,  7.15s/it]
 51%|█████▏    | 14405/28080 [28:28:06<27:00:22,  7.11s/it]
                                                           
{'loss': 0.6084, 'learning_rate': 0.00025162920593804815, 'epoch': 6.15}

 51%|█████▏    | 14405/28080 [28:28:06<27:00:22,  7.11s/it]
 51%|█████▏    | 14406/28080 [28:28:14<26:58:58,  7.10s/it]
                                                           
{'loss': 0.6128, 'learning_rate': 0.0002516003708321582, 'epoch': 6.15}

 51%|█████▏    | 14406/28080 [28:28:14<26:58:58,  7.10s/it]
 51%|█████▏    | 14407/28080 [28:28:21<27:02:27,  7.12s/it]
                                                           
{'loss': 0.6183, 'learning_rate': 0.000251571535704977, 'epoch': 6.15}

 51%|█████▏    | 14407/28080 [28:28:21<27:02:27,  7.12s/it]
 51%|█████▏    | 14408/28080 [28:28:28<27:05:18,  7.13s/it]
                                                           
{'loss': 0.6205, 'learning_rate': 0.0002515427005568881, 'epoch': 6.15}

 51%|█████▏    | 14408/28080 [28:28:28<27:05:18,  7.13s/it]
 51%|█████▏    | 14409/28080 [28:28:35<27:03:15,  7.12s/it]
                                                           
{'loss': 0.6229, 'learning_rate': 0.0002515138653882751, 'epoch': 6.16}

 51%|█████▏    | 14409/28080 [28:28:35<27:03:15,  7.12s/it]
 51%|█████▏    | 14410/28080 [28:28:42<27:02:35,  7.12s/it]
                                                           
{'loss': 0.6217, 'learning_rate': 0.00025148503019952183, 'epoch': 6.16}

 51%|█████▏    | 14410/28080 [28:28:42<27:02:35,  7.12s/it]
 51%|█████▏    | 14411/28080 [28:28:49<26:59:31,  7.11s/it]
                                                           
{'loss': 0.622, 'learning_rate': 0.0002514561949910116, 'epoch': 6.16}

 51%|█████▏    | 14411/28080 [28:28:49<26:59:31,  7.11s/it]
 51%|█████▏    | 14412/28080 [28:28:56<26:55:46,  7.09s/it]
                                                           
{'loss': 0.6285, 'learning_rate': 0.00025142735976312834, 'epoch': 6.16}

 51%|█████▏    | 14412/28080 [28:28:56<26:55:46,  7.09s/it]
 51%|█████▏    | 14413/28080 [28:29:03<26:59:22,  7.11s/it]
                                                           
{'loss': 0.6259, 'learning_rate': 0.0002513985245162556, 'epoch': 6.16}

 51%|█████▏    | 14413/28080 [28:29:03<26:59:22,  7.11s/it]
 51%|█████▏    | 14414/28080 [28:29:10<26:56:32,  7.10s/it]
                                                           
{'loss': 0.6207, 'learning_rate': 0.00025136968925077677, 'epoch': 6.16}

 51%|█████▏    | 14414/28080 [28:29:10<26:56:32,  7.10s/it]
 51%|█████▏    | 14415/28080 [28:29:18<26:56:25,  7.10s/it]
                                                           
{'loss': 0.6321, 'learning_rate': 0.00025134085396707567, 'epoch': 6.16}

 51%|█████▏    | 14415/28080 [28:29:18<26:56:25,  7.10s/it]
 51%|█████▏    | 14416/28080 [28:29:25<26:57:56,  7.10s/it]
                                                           
{'loss': 0.6112, 'learning_rate': 0.00025131201866553587, 'epoch': 6.16}

 51%|█████▏    | 14416/28080 [28:29:25<26:57:56,  7.10s/it]
 51%|█████▏    | 14417/28080 [28:29:32<26:54:28,  7.09s/it]
                                                           
{'loss': 0.6457, 'learning_rate': 0.000251283183346541, 'epoch': 6.16}

 51%|█████▏    | 14417/28080 [28:29:32<26:54:28,  7.09s/it]
 51%|█████▏    | 14418/28080 [28:29:39<26:53:30,  7.09s/it]
                                                           
{'loss': 0.617, 'learning_rate': 0.00025125434801047473, 'epoch': 6.16}

 51%|█████▏    | 14418/28080 [28:29:39<26:53:30,  7.09s/it]
 51%|█████▏    | 14419/28080 [28:29:46<26:49:38,  7.07s/it]
                                                           
{'loss': 0.6002, 'learning_rate': 0.0002512255126577207, 'epoch': 6.16}

 51%|█████▏    | 14419/28080 [28:29:46<26:49:38,  7.07s/it]
 51%|█████▏    | 14420/28080 [28:29:53<26:50:39,  7.07s/it]
                                                           
{'loss': 0.6196, 'learning_rate': 0.00025119667728866246, 'epoch': 6.16}

 51%|█████▏    | 14420/28080 [28:29:53<26:50:39,  7.07s/it]
 51%|█████▏    | 14421/28080 [28:30:00<26:52:04,  7.08s/it]
                                                           
{'loss': 0.632, 'learning_rate': 0.00025116784190368365, 'epoch': 6.16}

 51%|█████▏    | 14421/28080 [28:30:00<26:52:04,  7.08s/it]
 51%|█████▏    | 14422/28080 [28:30:07<26:51:53,  7.08s/it]
                                                           
{'loss': 0.6178, 'learning_rate': 0.0002511390065031679, 'epoch': 6.16}

 51%|█████▏    | 14422/28080 [28:30:07<26:51:53,  7.08s/it]
 51%|█████▏    | 14423/28080 [28:30:14<26:57:29,  7.11s/it]
                                                           
{'loss': 0.6349, 'learning_rate': 0.0002511101710874989, 'epoch': 6.16}

 51%|█████▏    | 14423/28080 [28:30:14<26:57:29,  7.11s/it]
 51%|█████▏    | 14424/28080 [28:30:21<27:02:33,  7.13s/it]
                                                           
{'loss': 0.6352, 'learning_rate': 0.00025108133565706015, 'epoch': 6.16}

 51%|█████▏    | 14424/28080 [28:30:21<27:02:33,  7.13s/it]
 51%|█████▏    | 14425/28080 [28:30:29<27:07:49,  7.15s/it]
                                                           
{'loss': 0.6348, 'learning_rate': 0.0002510525002122354, 'epoch': 6.16}

 51%|█████▏    | 14425/28080 [28:30:29<27:07:49,  7.15s/it]
 51%|█████▏    | 14426/28080 [28:30:36<27:00:16,  7.12s/it]
                                                           
{'loss': 0.6151, 'learning_rate': 0.00025102366475340815, 'epoch': 6.16}

 51%|█████▏    | 14426/28080 [28:30:36<27:00:16,  7.12s/it]
 51%|█████▏    | 14427/28080 [28:30:43<27:00:06,  7.12s/it]
                                                           
{'loss': 0.6153, 'learning_rate': 0.0002509948292809622, 'epoch': 6.16}

 51%|█████▏    | 14427/28080 [28:30:43<27:00:06,  7.12s/it]
 51%|█████▏    | 14428/28080 [28:30:50<26:54:19,  7.09s/it]
                                                           
{'loss': 0.6242, 'learning_rate': 0.00025096599379528095, 'epoch': 6.16}

 51%|█████▏    | 14428/28080 [28:30:50<26:54:19,  7.09s/it]
 51%|█████▏    | 14429/28080 [28:30:57<26:51:53,  7.08s/it]
                                                           
{'loss': 0.6156, 'learning_rate': 0.0002509371582967482, 'epoch': 6.16}

 51%|█████▏    | 14429/28080 [28:30:57<26:51:53,  7.08s/it]
 51%|█████▏    | 14430/28080 [28:31:04<26:57:37,  7.11s/it]
                                                           
{'loss': 0.6002, 'learning_rate': 0.00025090832278574756, 'epoch': 6.16}

 51%|█████▏    | 14430/28080 [28:31:04<26:57:37,  7.11s/it]
 51%|█████▏    | 14431/28080 [28:31:11<26:58:21,  7.11s/it]
                                                           
{'loss': 0.6199, 'learning_rate': 0.0002508794872626626, 'epoch': 6.16}

 51%|█████▏    | 14431/28080 [28:31:11<26:58:21,  7.11s/it]
 51%|█████▏    | 14432/28080 [28:31:18<26:58:51,  7.12s/it]
                                                           
{'loss': 0.6251, 'learning_rate': 0.00025085065172787696, 'epoch': 6.17}

 51%|█████▏    | 14432/28080 [28:31:18<26:58:51,  7.12s/it]
 51%|█████▏    | 14433/28080 [28:31:26<27:11:06,  7.17s/it]
                                                           
{'loss': 0.6109, 'learning_rate': 0.0002508218161817743, 'epoch': 6.17}

 51%|█████▏    | 14433/28080 [28:31:26<27:11:06,  7.17s/it]
 51%|█████▏    | 14434/28080 [28:31:33<27:03:09,  7.14s/it]
                                                           
{'loss': 0.6309, 'learning_rate': 0.0002507929806247382, 'epoch': 6.17}

 51%|█████▏    | 14434/28080 [28:31:33<27:03:09,  7.14s/it]
 51%|█████▏    | 14435/28080 [28:31:40<27:04:39,  7.14s/it]
                                                           
{'loss': 0.6084, 'learning_rate': 0.0002507641450571523, 'epoch': 6.17}

 51%|█████▏    | 14435/28080 [28:31:40<27:04:39,  7.14s/it]
 51%|█████▏    | 14436/28080 [28:31:47<27:02:50,  7.14s/it]
                                                           
{'loss': 0.6465, 'learning_rate': 0.00025073530947940025, 'epoch': 6.17}

 51%|█████▏    | 14436/28080 [28:31:47<27:02:50,  7.14s/it]
 51%|█████▏    | 14437/28080 [28:31:54<26:59:25,  7.12s/it]
                                                           
{'loss': 0.5996, 'learning_rate': 0.00025070647389186575, 'epoch': 6.17}

 51%|█████▏    | 14437/28080 [28:31:54<26:59:25,  7.12s/it]
 51%|█████▏    | 14438/28080 [28:32:01<26:54:23,  7.10s/it]
                                                           
{'loss': 0.632, 'learning_rate': 0.00025067763829493225, 'epoch': 6.17}

 51%|█████▏    | 14438/28080 [28:32:01<26:54:23,  7.10s/it]
 51%|█████▏    | 14439/28080 [28:32:08<26:44:32,  7.06s/it]
                                                           
{'loss': 0.6254, 'learning_rate': 0.0002506488026889835, 'epoch': 6.17}

 51%|█████▏    | 14439/28080 [28:32:08<26:44:32,  7.06s/it]
 51%|█████▏    | 14440/28080 [28:32:15<26:45:02,  7.06s/it]
                                                           
{'loss': 0.6214, 'learning_rate': 0.0002506199670744031, 'epoch': 6.17}

 51%|█████▏    | 14440/28080 [28:32:15<26:45:02,  7.06s/it]
 51%|█████▏    | 14441/28080 [28:32:22<26:50:42,  7.09s/it]
                                                           
{'loss': 0.6244, 'learning_rate': 0.00025059113145157466, 'epoch': 6.17}

 51%|█████▏    | 14441/28080 [28:32:22<26:50:42,  7.09s/it]
 51%|█████▏    | 14442/28080 [28:32:29<26:53:55,  7.10s/it]
                                                           
{'loss': 0.6169, 'learning_rate': 0.0002505622958208818, 'epoch': 6.17}

 51%|█████▏    | 14442/28080 [28:32:29<26:53:55,  7.10s/it]
 51%|█████▏    | 14443/28080 [28:32:36<26:47:27,  7.07s/it]
                                                           
{'loss': 0.6247, 'learning_rate': 0.00025053346018270823, 'epoch': 6.17}

 51%|█████▏    | 14443/28080 [28:32:36<26:47:27,  7.07s/it]
 51%|█████▏    | 14444/28080 [28:32:44<26:54:45,  7.11s/it]
                                                           
{'loss': 0.6089, 'learning_rate': 0.00025050462453743747, 'epoch': 6.17}

 51%|█████▏    | 14444/28080 [28:32:44<26:54:45,  7.11s/it]
 51%|█████▏    | 14445/28080 [28:32:51<26:51:52,  7.09s/it]
                                                           
{'loss': 0.6267, 'learning_rate': 0.0002504757888854532, 'epoch': 6.17}

 51%|█████▏    | 14445/28080 [28:32:51<26:51:52,  7.09s/it]
 51%|█████▏    | 14446/28080 [28:32:58<26:50:32,  7.09s/it]
                                                           
{'loss': 0.6083, 'learning_rate': 0.0002504469532271392, 'epoch': 6.17}

 51%|█████▏    | 14446/28080 [28:32:58<26:50:32,  7.09s/it]
 51%|█████▏    | 14447/28080 [28:33:05<26:53:12,  7.10s/it]
                                                           
{'loss': 0.6094, 'learning_rate': 0.00025041811756287873, 'epoch': 6.17}

 51%|█████▏    | 14447/28080 [28:33:05<26:53:12,  7.10s/it]
 51%|█████▏    | 14448/28080 [28:33:12<26:54:18,  7.11s/it]
                                                           
{'loss': 0.6229, 'learning_rate': 0.0002503892818930557, 'epoch': 6.17}

 51%|█████▏    | 14448/28080 [28:33:12<26:54:18,  7.11s/it]
 51%|█████▏    | 14449/28080 [28:33:19<26:54:33,  7.11s/it]
                                                           
{'loss': 0.6027, 'learning_rate': 0.00025036044621805375, 'epoch': 6.17}

 51%|█████▏    | 14449/28080 [28:33:19<26:54:33,  7.11s/it]
 51%|█████▏    | 14450/28080 [28:33:26<26:50:34,  7.09s/it]
                                                           
{'loss': 0.6391, 'learning_rate': 0.00025033161053825636, 'epoch': 6.17}

 51%|█████▏    | 14450/28080 [28:33:26<26:50:34,  7.09s/it]
 51%|█████▏    | 14451/28080 [28:33:33<27:01:32,  7.14s/it]
                                                           
{'loss': 0.6203, 'learning_rate': 0.00025030277485404734, 'epoch': 6.17}

 51%|█████▏    | 14451/28080 [28:33:33<27:01:32,  7.14s/it]
 51%|█████▏    | 14452/28080 [28:33:40<26:57:49,  7.12s/it]
                                                           
{'loss': 0.6108, 'learning_rate': 0.0002502739391658101, 'epoch': 6.17}

 51%|█████▏    | 14452/28080 [28:33:40<26:57:49,  7.12s/it]
 51%|█████▏    | 14453/28080 [28:33:48<26:58:40,  7.13s/it]
                                                           
{'loss': 0.641, 'learning_rate': 0.00025024510347392844, 'epoch': 6.17}

 51%|█████▏    | 14453/28080 [28:33:48<26:58:40,  7.13s/it]
 51%|█████▏    | 14454/28080 [28:33:55<26:52:01,  7.10s/it]
                                                           
{'loss': 0.6169, 'learning_rate': 0.0002502162677787859, 'epoch': 6.17}

 51%|█████▏    | 14454/28080 [28:33:55<26:52:01,  7.10s/it]
 51%|█████▏    | 14455/28080 [28:34:02<26:54:21,  7.11s/it]
                                                           
{'loss': 0.6138, 'learning_rate': 0.00025018743208076615, 'epoch': 6.18}

 51%|█████▏    | 14455/28080 [28:34:02<26:54:21,  7.11s/it]
 51%|█████▏    | 14456/28080 [28:34:09<26:51:54,  7.10s/it]
                                                           
{'loss': 0.6158, 'learning_rate': 0.00025015859638025285, 'epoch': 6.18}

 51%|█████▏    | 14456/28080 [28:34:09<26:51:54,  7.10s/it]
 51%|█████▏    | 14457/28080 [28:34:16<26:53:50,  7.11s/it]
                                                           
{'loss': 0.628, 'learning_rate': 0.00025012976067762953, 'epoch': 6.18}

 51%|█████▏    | 14457/28080 [28:34:16<26:53:50,  7.11s/it]
 51%|█████▏    | 14458/28080 [28:34:23<26:51:56,  7.10s/it]
                                                           
{'loss': 0.6377, 'learning_rate': 0.0002501009249732799, 'epoch': 6.18}

 51%|█████▏    | 14458/28080 [28:34:23<26:51:56,  7.10s/it]
 51%|█████▏    | 14459/28080 [28:34:30<26:56:27,  7.12s/it]
                                                           
{'loss': 0.6229, 'learning_rate': 0.00025007208926758757, 'epoch': 6.18}

 51%|█████▏    | 14459/28080 [28:34:30<26:56:27,  7.12s/it]
 51%|█████▏    | 14460/28080 [28:34:37<26:58:54,  7.13s/it]
                                                           
{'loss': 0.6198, 'learning_rate': 0.00025004325356093617, 'epoch': 6.18}

 51%|█████▏    | 14460/28080 [28:34:37<26:58:54,  7.13s/it]
 51%|█████▏    | 14461/28080 [28:34:44<26:55:59,  7.12s/it]
                                                           
{'loss': 0.6067, 'learning_rate': 0.0002500144178537093, 'epoch': 6.18}

 51%|█████▏    | 14461/28080 [28:34:44<26:55:59,  7.12s/it]
 52%|█████▏    | 14462/28080 [28:34:52<26:54:39,  7.11s/it]
                                                           
{'loss': 0.6453, 'learning_rate': 0.0002499855821462907, 'epoch': 6.18}

 52%|█████▏    | 14462/28080 [28:34:52<26:54:39,  7.11s/it]
 52%|█████▏    | 14463/28080 [28:34:59<27:01:01,  7.14s/it]
                                                           
{'loss': 0.6086, 'learning_rate': 0.0002499567464390639, 'epoch': 6.18}

 52%|█████▏    | 14463/28080 [28:34:59<27:01:01,  7.14s/it]
 52%|█████▏    | 14464/28080 [28:35:06<26:51:43,  7.10s/it]
                                                           
{'loss': 0.6395, 'learning_rate': 0.00024992791073241244, 'epoch': 6.18}

 52%|█████▏    | 14464/28080 [28:35:06<26:51:43,  7.10s/it]
 52%|█████▏    | 14465/28080 [28:35:13<26:46:00,  7.08s/it]
                                                           
{'loss': 0.6157, 'learning_rate': 0.0002498990750267201, 'epoch': 6.18}

 52%|█████▏    | 14465/28080 [28:35:13<26:46:00,  7.08s/it]
 52%|█████▏    | 14466/28080 [28:35:20<26:48:34,  7.09s/it]
                                                           
{'loss': 0.6254, 'learning_rate': 0.0002498702393223705, 'epoch': 6.18}

 52%|█████▏    | 14466/28080 [28:35:20<26:48:34,  7.09s/it]
 52%|█████▏    | 14467/28080 [28:35:27<26:57:09,  7.13s/it]
                                                           
{'loss': 0.6123, 'learning_rate': 0.0002498414036197472, 'epoch': 6.18}

 52%|█████▏    | 14467/28080 [28:35:27<26:57:09,  7.13s/it]
 52%|█████▏    | 14468/28080 [28:35:34<27:01:34,  7.15s/it]
                                                           
{'loss': 0.6041, 'learning_rate': 0.0002498125679192338, 'epoch': 6.18}

 52%|█████▏    | 14468/28080 [28:35:34<27:01:34,  7.15s/it]
 52%|█████▏    | 14469/28080 [28:35:41<26:59:25,  7.14s/it]
                                                           
{'loss': 0.6391, 'learning_rate': 0.0002497837322212141, 'epoch': 6.18}

 52%|█████▏    | 14469/28080 [28:35:41<26:59:25,  7.14s/it]
 52%|█████▏    | 14470/28080 [28:35:49<26:57:52,  7.13s/it]
                                                           
{'loss': 0.5963, 'learning_rate': 0.00024975489652607157, 'epoch': 6.18}

 52%|█████▏    | 14470/28080 [28:35:49<26:57:52,  7.13s/it]
 52%|█████▏    | 14471/28080 [28:35:56<26:50:26,  7.10s/it]
                                                           
{'loss': 0.6301, 'learning_rate': 0.0002497260608341899, 'epoch': 6.18}

 52%|█████▏    | 14471/28080 [28:35:56<26:50:26,  7.10s/it]
 52%|█████▏    | 14472/28080 [28:36:03<26:48:15,  7.09s/it]
                                                           
{'loss': 0.6148, 'learning_rate': 0.00024969722514595267, 'epoch': 6.18}

 52%|█████▏    | 14472/28080 [28:36:03<26:48:15,  7.09s/it]
 52%|█████▏    | 14473/28080 [28:36:10<26:51:41,  7.11s/it]
                                                           
{'loss': 0.6007, 'learning_rate': 0.00024966838946174365, 'epoch': 6.18}

 52%|█████▏    | 14473/28080 [28:36:10<26:51:41,  7.11s/it]
 52%|█████▏    | 14474/28080 [28:36:17<26:58:50,  7.14s/it]
                                                           
{'loss': 0.6327, 'learning_rate': 0.0002496395537819463, 'epoch': 6.18}

 52%|█████▏    | 14474/28080 [28:36:17<26:58:50,  7.14s/it]
 52%|█████▏    | 14475/28080 [28:36:24<26:52:00,  7.11s/it]
                                                           
{'loss': 0.6097, 'learning_rate': 0.0002496107181069443, 'epoch': 6.18}

 52%|█████▏    | 14475/28080 [28:36:24<26:52:00,  7.11s/it]
 52%|█████▏    | 14476/28080 [28:36:31<27:00:35,  7.15s/it]
                                                           
{'loss': 0.6372, 'learning_rate': 0.00024958188243712133, 'epoch': 6.18}

 52%|█████▏    | 14476/28080 [28:36:31<27:00:35,  7.15s/it]
 52%|█████▏    | 14477/28080 [28:36:39<27:06:56,  7.18s/it]
                                                           
{'loss': 0.6194, 'learning_rate': 0.0002495530467728609, 'epoch': 6.18}

 52%|█████▏    | 14477/28080 [28:36:39<27:06:56,  7.18s/it]
 52%|█████▏    | 14478/28080 [28:36:46<27:01:55,  7.15s/it]
                                                           
{'loss': 0.6125, 'learning_rate': 0.00024952421111454684, 'epoch': 6.18}

 52%|█████▏    | 14478/28080 [28:36:46<27:01:55,  7.15s/it]
 52%|█████▏    | 14479/28080 [28:36:53<26:53:53,  7.12s/it]
                                                           
{'loss': 0.6393, 'learning_rate': 0.00024949537546256254, 'epoch': 6.19}

 52%|█████▏    | 14479/28080 [28:36:53<26:53:53,  7.12s/it]
 52%|█████▏    | 14480/28080 [28:37:00<26:50:10,  7.10s/it]
                                                           
{'loss': 0.6111, 'learning_rate': 0.0002494665398172919, 'epoch': 6.19}

 52%|█████▏    | 14480/28080 [28:37:00<26:50:10,  7.10s/it]
 52%|█████▏    | 14481/28080 [28:37:07<26:44:06,  7.08s/it]
                                                           
{'loss': 0.6414, 'learning_rate': 0.0002494377041791182, 'epoch': 6.19}

 52%|█████▏    | 14481/28080 [28:37:07<26:44:06,  7.08s/it]
 52%|█████▏    | 14482/28080 [28:37:14<26:45:19,  7.08s/it]
                                                           
{'loss': 0.6428, 'learning_rate': 0.0002494088685484254, 'epoch': 6.19}

 52%|█████▏    | 14482/28080 [28:37:14<26:45:19,  7.08s/it]
 52%|█████▏    | 14483/28080 [28:37:21<26:53:45,  7.12s/it]
                                                           
{'loss': 0.6395, 'learning_rate': 0.000249380032925597, 'epoch': 6.19}

 52%|█████▏    | 14483/28080 [28:37:21<26:53:45,  7.12s/it]
 52%|█████▏    | 14484/28080 [28:37:28<26:52:36,  7.12s/it]
                                                           
{'loss': 0.6263, 'learning_rate': 0.00024935119731101657, 'epoch': 6.19}

 52%|█████▏    | 14484/28080 [28:37:28<26:52:36,  7.12s/it]
 52%|█████▏    | 14485/28080 [28:37:35<26:51:58,  7.11s/it]
                                                           
{'loss': 0.6131, 'learning_rate': 0.0002493223617050678, 'epoch': 6.19}

 52%|█████▏    | 14485/28080 [28:37:35<26:51:58,  7.11s/it]
 52%|█████▏    | 14486/28080 [28:37:42<26:55:12,  7.13s/it]
                                                           
{'loss': 0.6105, 'learning_rate': 0.00024929352610813437, 'epoch': 6.19}

 52%|█████▏    | 14486/28080 [28:37:42<26:55:12,  7.13s/it]
 52%|█████▏    | 14487/28080 [28:37:50<27:03:24,  7.17s/it]
                                                           
{'loss': 0.6079, 'learning_rate': 0.00024926469052059976, 'epoch': 6.19}

 52%|█████▏    | 14487/28080 [28:37:50<27:03:24,  7.17s/it]
 52%|█████▏    | 14488/28080 [28:37:57<26:59:21,  7.15s/it]
                                                           
{'loss': 0.6234, 'learning_rate': 0.00024923585494284774, 'epoch': 6.19}

 52%|█████▏    | 14488/28080 [28:37:57<26:59:21,  7.15s/it]
 52%|█████▏    | 14489/28080 [28:38:04<27:00:59,  7.16s/it]
                                                           
{'loss': 0.5787, 'learning_rate': 0.00024920701937526185, 'epoch': 6.19}

 52%|█████▏    | 14489/28080 [28:38:04<27:00:59,  7.16s/it]
 52%|█████▏    | 14490/28080 [28:38:11<26:59:22,  7.15s/it]
                                                           
{'loss': 0.6242, 'learning_rate': 0.00024917818381822574, 'epoch': 6.19}

 52%|█████▏    | 14490/28080 [28:38:11<26:59:22,  7.15s/it]
 52%|█████▏    | 14491/28080 [28:38:18<26:57:41,  7.14s/it]
                                                           
{'loss': 0.6197, 'learning_rate': 0.000249149348272123, 'epoch': 6.19}

 52%|█████▏    | 14491/28080 [28:38:18<26:57:41,  7.14s/it]
 52%|█████▏    | 14492/28080 [28:38:25<26:56:47,  7.14s/it]
                                                           
{'loss': 0.6234, 'learning_rate': 0.0002491205127373375, 'epoch': 6.19}

 52%|█████▏    | 14492/28080 [28:38:25<26:56:47,  7.14s/it]
 52%|█████▏    | 14493/28080 [28:38:32<26:53:40,  7.13s/it]
                                                           
{'loss': 0.6007, 'learning_rate': 0.0002490916772142524, 'epoch': 6.19}

 52%|█████▏    | 14493/28080 [28:38:32<26:53:40,  7.13s/it]
 52%|█████▏    | 14494/28080 [28:38:40<27:01:02,  7.16s/it]
                                                           
{'loss': 0.6155, 'learning_rate': 0.00024906284170325184, 'epoch': 6.19}

 52%|█████▏    | 14494/28080 [28:38:40<27:01:02,  7.16s/it]
 52%|█████▏    | 14495/28080 [28:38:47<27:00:09,  7.16s/it]
                                                           
{'loss': 0.6295, 'learning_rate': 0.000249034006204719, 'epoch': 6.19}

 52%|█████▏    | 14495/28080 [28:38:47<27:00:09,  7.16s/it]
 52%|█████▏    | 14496/28080 [28:38:54<27:01:47,  7.16s/it]
                                                           
{'loss': 0.6207, 'learning_rate': 0.00024900517071903787, 'epoch': 6.19}

 52%|█████▏    | 14496/28080 [28:38:54<27:01:47,  7.16s/it]
 52%|█████▏    | 14497/28080 [28:39:01<27:01:39,  7.16s/it]
                                                           
{'loss': 0.6205, 'learning_rate': 0.0002489763352465918, 'epoch': 6.19}

 52%|█████▏    | 14497/28080 [28:39:01<27:01:39,  7.16s/it]
 52%|█████▏    | 14498/28080 [28:39:08<26:54:10,  7.13s/it]
                                                           
{'loss': 0.6289, 'learning_rate': 0.00024894749978776463, 'epoch': 6.19}

 52%|█████▏    | 14498/28080 [28:39:08<26:54:10,  7.13s/it]
 52%|█████▏    | 14499/28080 [28:39:15<26:57:34,  7.15s/it]
                                                           
{'loss': 0.6241, 'learning_rate': 0.0002489186643429399, 'epoch': 6.19}

 52%|█████▏    | 14499/28080 [28:39:15<26:57:34,  7.15s/it]
 52%|█████▏    | 14500/28080 [28:39:23<27:05:42,  7.18s/it]
                                                           
{'loss': 0.619, 'learning_rate': 0.00024888982891250116, 'epoch': 6.19}

 52%|█████▏    | 14500/28080 [28:39:23<27:05:42,  7.18s/it]
 52%|█████▏    | 14501/28080 [28:39:30<27:07:58,  7.19s/it]
                                                           
{'loss': 0.6109, 'learning_rate': 0.00024886099349683216, 'epoch': 6.19}

 52%|█████▏    | 14501/28080 [28:39:30<27:07:58,  7.19s/it]
 52%|█████▏    | 14502/28080 [28:39:37<26:52:19,  7.12s/it]
                                                           
{'loss': 0.6353, 'learning_rate': 0.0002488321580963164, 'epoch': 6.2}

 52%|█████▏    | 14502/28080 [28:39:37<26:52:19,  7.12s/it]
 52%|█████▏    | 14503/28080 [28:39:44<26:53:26,  7.13s/it]
                                                           
{'loss': 0.6615, 'learning_rate': 0.0002488033227113376, 'epoch': 6.2}

 52%|█████▏    | 14503/28080 [28:39:44<26:53:26,  7.13s/it]
 52%|█████▏    | 14504/28080 [28:39:51<26:50:11,  7.12s/it]
                                                           
{'loss': 0.6313, 'learning_rate': 0.0002487744873422793, 'epoch': 6.2}

 52%|█████▏    | 14504/28080 [28:39:51<26:50:11,  7.12s/it]
 52%|█████▏    | 14505/28080 [28:39:58<26:49:37,  7.11s/it]
                                                           
{'loss': 0.6226, 'learning_rate': 0.00024874565198952533, 'epoch': 6.2}

 52%|█████▏    | 14505/28080 [28:39:58<26:49:37,  7.11s/it]
 52%|█████▏    | 14506/28080 [28:40:05<26:42:29,  7.08s/it]
                                                           
{'loss': 0.6266, 'learning_rate': 0.000248716816653459, 'epoch': 6.2}

 52%|█████▏    | 14506/28080 [28:40:05<26:42:29,  7.08s/it]
 52%|█████▏    | 14507/28080 [28:40:12<26:43:42,  7.09s/it]
                                                           
{'loss': 0.6223, 'learning_rate': 0.00024868798133446425, 'epoch': 6.2}

 52%|█████▏    | 14507/28080 [28:40:12<26:43:42,  7.09s/it]
 52%|█████▏    | 14508/28080 [28:40:19<26:42:01,  7.08s/it]
                                                           
{'loss': 0.6159, 'learning_rate': 0.0002486591460329244, 'epoch': 6.2}

 52%|█████▏    | 14508/28080 [28:40:19<26:42:01,  7.08s/it]
 52%|█████▏    | 14509/28080 [28:40:27<26:50:08,  7.12s/it]
                                                           
{'loss': 0.6252, 'learning_rate': 0.0002486303107492234, 'epoch': 6.2}

 52%|█████▏    | 14509/28080 [28:40:27<26:50:08,  7.12s/it]
 52%|█████▏    | 14510/28080 [28:40:34<26:48:16,  7.11s/it]
                                                           
{'loss': 0.6365, 'learning_rate': 0.0002486014754837445, 'epoch': 6.2}

 52%|█████▏    | 14510/28080 [28:40:34<26:48:16,  7.11s/it]
 52%|█████▏    | 14511/28080 [28:40:41<26:42:34,  7.09s/it]
                                                           
{'loss': 0.6158, 'learning_rate': 0.00024857264023687173, 'epoch': 6.2}

 52%|█████▏    | 14511/28080 [28:40:41<26:42:34,  7.09s/it]
 52%|█████▏    | 14512/28080 [28:40:48<26:39:24,  7.07s/it]
                                                           
{'loss': 0.6306, 'learning_rate': 0.00024854380500898834, 'epoch': 6.2}

 52%|█████▏    | 14512/28080 [28:40:48<26:39:24,  7.07s/it]
 52%|█████▏    | 14513/28080 [28:40:55<26:40:14,  7.08s/it]
                                                           
{'loss': 0.6047, 'learning_rate': 0.00024851496980047823, 'epoch': 6.2}

 52%|█████▏    | 14513/28080 [28:40:55<26:40:14,  7.08s/it]
 52%|█████▏    | 14514/28080 [28:41:02<26:40:46,  7.08s/it]
                                                           
{'loss': 0.6077, 'learning_rate': 0.00024848613461172484, 'epoch': 6.2}

 52%|█████▏    | 14514/28080 [28:41:02<26:40:46,  7.08s/it]
 52%|█████▏    | 14515/28080 [28:41:09<26:43:51,  7.09s/it]
                                                           
{'loss': 0.6213, 'learning_rate': 0.00024845729944311196, 'epoch': 6.2}

 52%|█████▏    | 14515/28080 [28:41:09<26:43:51,  7.09s/it]
 52%|█████▏    | 14516/28080 [28:41:16<26:48:04,  7.11s/it]
                                                           
{'loss': 0.633, 'learning_rate': 0.00024842846429502303, 'epoch': 6.2}

 52%|█████▏    | 14516/28080 [28:41:16<26:48:04,  7.11s/it]
 52%|█████▏    | 14517/28080 [28:41:23<26:52:11,  7.13s/it]
                                                           
{'loss': 0.6292, 'learning_rate': 0.0002483996291678418, 'epoch': 6.2}

 52%|█████▏    | 14517/28080 [28:41:23<26:52:11,  7.13s/it]
 52%|█████▏    | 14518/28080 [28:41:30<26:46:49,  7.11s/it]
                                                           
{'loss': 0.5954, 'learning_rate': 0.00024837079406195186, 'epoch': 6.2}

 52%|█████▏    | 14518/28080 [28:41:30<26:46:49,  7.11s/it]
 52%|█████▏    | 14519/28080 [28:41:38<26:47:57,  7.11s/it]
                                                           
{'loss': 0.6057, 'learning_rate': 0.00024834195897773686, 'epoch': 6.2}

 52%|█████▏    | 14519/28080 [28:41:38<26:47:57,  7.11s/it]
 52%|█████▏    | 14520/28080 [28:41:45<26:48:41,  7.12s/it]
                                                           
{'loss': 0.6136, 'learning_rate': 0.0002483131239155803, 'epoch': 6.2}

 52%|█████▏    | 14520/28080 [28:41:45<26:48:41,  7.12s/it]
 52%|█████▏    | 14521/28080 [28:41:52<26:48:17,  7.12s/it]
                                                           
{'loss': 0.6162, 'learning_rate': 0.0002482842888758659, 'epoch': 6.2}

 52%|█████▏    | 14521/28080 [28:41:52<26:48:17,  7.12s/it]
 52%|█████▏    | 14522/28080 [28:41:59<26:42:40,  7.09s/it]
                                                           
{'loss': 0.6142, 'learning_rate': 0.0002482554538589772, 'epoch': 6.2}

 52%|█████▏    | 14522/28080 [28:41:59<26:42:40,  7.09s/it]
 52%|█████▏    | 14523/28080 [28:42:06<26:40:06,  7.08s/it]
                                                           
{'loss': 0.6421, 'learning_rate': 0.00024822661886529814, 'epoch': 6.2}

 52%|█████▏    | 14523/28080 [28:42:06<26:40:06,  7.08s/it]
 52%|█████▏    | 14524/28080 [28:42:13<26:40:39,  7.08s/it]
                                                           
{'loss': 0.6102, 'learning_rate': 0.00024819778389521195, 'epoch': 6.2}

 52%|█████▏    | 14524/28080 [28:42:13<26:40:39,  7.08s/it]
 52%|█████▏    | 14525/28080 [28:42:20<26:34:03,  7.06s/it]
                                                           
{'loss': 0.6274, 'learning_rate': 0.00024816894894910235, 'epoch': 6.2}

 52%|█████▏    | 14525/28080 [28:42:20<26:34:03,  7.06s/it]
 52%|█████▏    | 14526/28080 [28:42:27<26:37:36,  7.07s/it]
                                                           
{'loss': 0.5989, 'learning_rate': 0.000248140114027353, 'epoch': 6.21}

 52%|█████▏    | 14526/28080 [28:42:27<26:37:36,  7.07s/it]
 52%|█████▏    | 14527/28080 [28:42:34<26:45:08,  7.11s/it]
                                                           
{'loss': 0.6078, 'learning_rate': 0.00024811127913034744, 'epoch': 6.21}

 52%|█████▏    | 14527/28080 [28:42:34<26:45:08,  7.11s/it]
 52%|█████▏    | 14528/28080 [28:42:41<26:50:18,  7.13s/it]
                                                           
{'loss': 0.6281, 'learning_rate': 0.00024808244425846953, 'epoch': 6.21}

 52%|█████▏    | 14528/28080 [28:42:41<26:50:18,  7.13s/it]
 52%|█████▏    | 14529/28080 [28:42:48<26:43:24,  7.10s/it]
                                                           
{'loss': 0.6115, 'learning_rate': 0.0002480536094121026, 'epoch': 6.21}

 52%|█████▏    | 14529/28080 [28:42:48<26:43:24,  7.10s/it]
 52%|█████▏    | 14530/28080 [28:42:56<26:50:24,  7.13s/it]
                                                           
{'loss': 0.616, 'learning_rate': 0.00024802477459163043, 'epoch': 6.21}

 52%|█████▏    | 14530/28080 [28:42:56<26:50:24,  7.13s/it]
 52%|█████▏    | 14531/28080 [28:43:03<26:49:05,  7.13s/it]
                                                           
{'loss': 0.6219, 'learning_rate': 0.0002479959397974366, 'epoch': 6.21}

 52%|█████▏    | 14531/28080 [28:43:03<26:49:05,  7.13s/it]
 52%|█████▏    | 14532/28080 [28:43:10<26:53:55,  7.15s/it]
                                                           
{'loss': 0.6109, 'learning_rate': 0.00024796710502990473, 'epoch': 6.21}

 52%|█████▏    | 14532/28080 [28:43:10<26:53:55,  7.15s/it]
 52%|█████▏    | 14533/28080 [28:43:17<26:54:53,  7.15s/it]
                                                           
{'loss': 0.6052, 'learning_rate': 0.00024793827028941835, 'epoch': 6.21}

 52%|█████▏    | 14533/28080 [28:43:17<26:54:53,  7.15s/it]
 52%|█████▏    | 14534/28080 [28:43:24<26:49:45,  7.13s/it]
                                                           
{'loss': 0.6395, 'learning_rate': 0.00024790943557636126, 'epoch': 6.21}

 52%|█████▏    | 14534/28080 [28:43:24<26:49:45,  7.13s/it]
 52%|█████▏    | 14535/28080 [28:43:31<26:51:02,  7.14s/it]
                                                           
{'loss': 0.6131, 'learning_rate': 0.00024788060089111694, 'epoch': 6.21}

 52%|█████▏    | 14535/28080 [28:43:31<26:51:02,  7.14s/it]
 52%|█████▏    | 14536/28080 [28:43:39<26:56:05,  7.16s/it]
                                                           
{'loss': 0.6326, 'learning_rate': 0.00024785176623406903, 'epoch': 6.21}

 52%|█████▏    | 14536/28080 [28:43:39<26:56:05,  7.16s/it]
 52%|█████▏    | 14537/28080 [28:43:46<26:48:34,  7.13s/it]
                                                           
{'loss': 0.618, 'learning_rate': 0.0002478229316056012, 'epoch': 6.21}

 52%|█████▏    | 14537/28080 [28:43:46<26:48:34,  7.13s/it]
 52%|█████▏    | 14538/28080 [28:43:53<26:46:13,  7.12s/it]
                                                           
{'loss': 0.6081, 'learning_rate': 0.00024779409700609697, 'epoch': 6.21}

 52%|█████▏    | 14538/28080 [28:43:53<26:46:13,  7.12s/it]
 52%|█████▏    | 14539/28080 [28:44:00<26:49:53,  7.13s/it]
                                                           
{'loss': 0.6069, 'learning_rate': 0.0002477652624359399, 'epoch': 6.21}

 52%|█████▏    | 14539/28080 [28:44:00<26:49:53,  7.13s/it]
 52%|█████▏    | 14540/28080 [28:44:07<26:47:17,  7.12s/it]
                                                           
{'loss': 0.611, 'learning_rate': 0.0002477364278955139, 'epoch': 6.21}

 52%|█████▏    | 14540/28080 [28:44:07<26:47:17,  7.12s/it]
 52%|█████▏    | 14541/28080 [28:44:14<26:46:07,  7.12s/it]
                                                           
{'loss': 0.6191, 'learning_rate': 0.00024770759338520225, 'epoch': 6.21}

 52%|█████▏    | 14541/28080 [28:44:14<26:46:07,  7.12s/it]
 52%|█████▏    | 14542/28080 [28:44:21<26:46:09,  7.12s/it]
                                                           
{'loss': 0.5845, 'learning_rate': 0.00024767875890538887, 'epoch': 6.21}

 52%|█████▏    | 14542/28080 [28:44:21<26:46:09,  7.12s/it]
 52%|█████▏    | 14543/28080 [28:44:28<26:44:14,  7.11s/it]
                                                           
{'loss': 0.6139, 'learning_rate': 0.000247649924456457, 'epoch': 6.21}

 52%|█████▏    | 14543/28080 [28:44:28<26:44:14,  7.11s/it]
 52%|█████▏    | 14544/28080 [28:44:35<26:45:46,  7.12s/it]
                                                           
{'loss': 0.5889, 'learning_rate': 0.00024762109003879056, 'epoch': 6.21}

 52%|█████▏    | 14544/28080 [28:44:35<26:45:46,  7.12s/it]
 52%|█████▏    | 14545/28080 [28:44:43<26:42:42,  7.10s/it]
                                                           
{'loss': 0.6296, 'learning_rate': 0.0002475922556527731, 'epoch': 6.21}

 52%|█████▏    | 14545/28080 [28:44:43<26:42:42,  7.10s/it]
 52%|█████▏    | 14546/28080 [28:44:50<26:45:48,  7.12s/it]
                                                           
{'loss': 0.6203, 'learning_rate': 0.0002475634212987882, 'epoch': 6.21}

 52%|█████▏    | 14546/28080 [28:44:50<26:45:48,  7.12s/it]
 52%|█████▏    | 14547/28080 [28:44:57<26:42:13,  7.10s/it]
                                                           
{'loss': 0.6355, 'learning_rate': 0.00024753458697721937, 'epoch': 6.21}

 52%|█████▏    | 14547/28080 [28:44:57<26:42:13,  7.10s/it]
 52%|█████▏    | 14548/28080 [28:45:04<26:44:39,  7.11s/it]
                                                           
{'loss': 0.6245, 'learning_rate': 0.0002475057526884504, 'epoch': 6.21}

 52%|█████▏    | 14548/28080 [28:45:04<26:44:39,  7.11s/it]
 52%|█████▏    | 14549/28080 [28:45:11<26:50:47,  7.14s/it]
                                                           
{'loss': 0.6155, 'learning_rate': 0.0002474769184328648, 'epoch': 6.22}

 52%|█████▏    | 14549/28080 [28:45:11<26:50:47,  7.14s/it]
 52%|█████▏    | 14550/28080 [28:45:18<26:45:48,  7.12s/it]
                                                           
{'loss': 0.6166, 'learning_rate': 0.0002474480842108462, 'epoch': 6.22}

 52%|█████▏    | 14550/28080 [28:45:18<26:45:48,  7.12s/it]
 52%|█████▏    | 14551/28080 [28:45:25<26:41:00,  7.10s/it]
                                                           
{'loss': 0.5945, 'learning_rate': 0.0002474192500227782, 'epoch': 6.22}

 52%|█████▏    | 14551/28080 [28:45:25<26:41:00,  7.10s/it]
 52%|█████▏    | 14552/28080 [28:45:32<26:42:48,  7.11s/it]
                                                           
{'loss': 0.6116, 'learning_rate': 0.0002473904158690444, 'epoch': 6.22}

 52%|█████▏    | 14552/28080 [28:45:32<26:42:48,  7.11s/it]
 52%|█████▏    | 14553/28080 [28:45:39<26:33:18,  7.07s/it]
                                                           
{'loss': 0.6072, 'learning_rate': 0.00024736158175002845, 'epoch': 6.22}

 52%|█████▏    | 14553/28080 [28:45:39<26:33:18,  7.07s/it]
 52%|█████▏    | 14554/28080 [28:45:46<26:36:35,  7.08s/it]
                                                           
{'loss': 0.6234, 'learning_rate': 0.0002473327476661139, 'epoch': 6.22}

 52%|█████▏    | 14554/28080 [28:45:46<26:36:35,  7.08s/it]
 52%|█████▏    | 14555/28080 [28:45:54<26:41:43,  7.11s/it]
                                                           
{'loss': 0.6241, 'learning_rate': 0.0002473039136176845, 'epoch': 6.22}

 52%|█████▏    | 14555/28080 [28:45:54<26:41:43,  7.11s/it]
 52%|█████▏    | 14556/28080 [28:46:01<26:43:44,  7.12s/it]
                                                           
{'loss': 0.5935, 'learning_rate': 0.0002472750796051236, 'epoch': 6.22}

 52%|█████▏    | 14556/28080 [28:46:01<26:43:44,  7.12s/it]
 52%|█████▏    | 14557/28080 [28:46:08<26:38:50,  7.09s/it]
                                                           
{'loss': 0.6197, 'learning_rate': 0.000247246245628815, 'epoch': 6.22}

 52%|█████▏    | 14557/28080 [28:46:08<26:38:50,  7.09s/it]
 52%|█████▏    | 14558/28080 [28:46:15<26:38:56,  7.09s/it]
                                                           
{'loss': 0.604, 'learning_rate': 0.0002472174116891422, 'epoch': 6.22}

 52%|█████▏    | 14558/28080 [28:46:15<26:38:56,  7.09s/it]
 52%|█████▏    | 14559/28080 [28:46:22<26:31:27,  7.06s/it]
                                                           
{'loss': 0.6312, 'learning_rate': 0.00024718857778648903, 'epoch': 6.22}

 52%|█████▏    | 14559/28080 [28:46:22<26:31:27,  7.06s/it]
 52%|█████▏    | 14560/28080 [28:46:29<26:31:21,  7.06s/it]
                                                           
{'loss': 0.6175, 'learning_rate': 0.0002471597439212388, 'epoch': 6.22}

 52%|█████▏    | 14560/28080 [28:46:29<26:31:21,  7.06s/it]
 52%|█████▏    | 14561/28080 [28:46:36<26:35:38,  7.08s/it]
                                                           
{'loss': 0.6033, 'learning_rate': 0.00024713091009377527, 'epoch': 6.22}

 52%|█████▏    | 14561/28080 [28:46:36<26:35:38,  7.08s/it]
 52%|█████▏    | 14562/28080 [28:46:43<26:38:17,  7.09s/it]
                                                           
{'loss': 0.6305, 'learning_rate': 0.000247102076304482, 'epoch': 6.22}

 52%|█████▏    | 14562/28080 [28:46:43<26:38:17,  7.09s/it]
 52%|█████▏    | 14563/28080 [28:46:50<26:31:02,  7.06s/it]
                                                           
{'loss': 0.6172, 'learning_rate': 0.0002470732425537427, 'epoch': 6.22}

 52%|█████▏    | 14563/28080 [28:46:50<26:31:02,  7.06s/it]
 52%|█████▏    | 14564/28080 [28:46:57<26:31:19,  7.06s/it]
                                                           
{'loss': 0.6395, 'learning_rate': 0.0002470444088419408, 'epoch': 6.22}

 52%|█████▏    | 14564/28080 [28:46:57<26:31:19,  7.06s/it]
 52%|█████▏    | 14565/28080 [28:47:04<26:41:57,  7.11s/it]
                                                           
{'loss': 0.6136, 'learning_rate': 0.0002470155751694601, 'epoch': 6.22}

 52%|█████▏    | 14565/28080 [28:47:04<26:41:57,  7.11s/it]
 52%|█████▏    | 14566/28080 [28:47:12<26:39:22,  7.10s/it]
                                                           
{'loss': 0.6195, 'learning_rate': 0.000246986741536684, 'epoch': 6.22}

 52%|█████▏    | 14566/28080 [28:47:12<26:39:22,  7.10s/it]
 52%|█████▏    | 14567/28080 [28:47:19<26:38:26,  7.10s/it]
                                                           
{'loss': 0.6344, 'learning_rate': 0.00024695790794399626, 'epoch': 6.22}

 52%|█████▏    | 14567/28080 [28:47:19<26:38:26,  7.10s/it]
 52%|█████▏    | 14568/28080 [28:47:26<26:43:35,  7.12s/it]
                                                           
{'loss': 0.6109, 'learning_rate': 0.00024692907439178034, 'epoch': 6.22}

 52%|█████▏    | 14568/28080 [28:47:26<26:43:35,  7.12s/it]
 52%|█████▏    | 14569/28080 [28:47:33<26:51:47,  7.16s/it]
                                                           
{'loss': 0.6084, 'learning_rate': 0.00024690024088042, 'epoch': 6.22}

 52%|█████▏    | 14569/28080 [28:47:33<26:51:47,  7.16s/it]
 52%|█████▏    | 14570/28080 [28:47:40<26:51:07,  7.16s/it]
                                                           
{'loss': 0.6316, 'learning_rate': 0.0002468714074102986, 'epoch': 6.22}

 52%|█████▏    | 14570/28080 [28:47:40<26:51:07,  7.16s/it]
 52%|█████▏    | 14571/28080 [28:47:47<26:56:25,  7.18s/it]
                                                           
{'loss': 0.5905, 'learning_rate': 0.0002468425739818001, 'epoch': 6.22}

 52%|█████▏    | 14571/28080 [28:47:47<26:56:25,  7.18s/it]
 52%|█████▏    | 14572/28080 [28:47:55<26:48:15,  7.14s/it]
                                                           
{'loss': 0.6383, 'learning_rate': 0.00024681374059530776, 'epoch': 6.23}

 52%|█████▏    | 14572/28080 [28:47:55<26:48:15,  7.14s/it]
 52%|█████▏    | 14573/28080 [28:48:02<26:45:04,  7.13s/it]
                                                           
{'loss': 0.6123, 'learning_rate': 0.0002467849072512054, 'epoch': 6.23}

 52%|█████▏    | 14573/28080 [28:48:02<26:45:04,  7.13s/it]
 52%|█████▏    | 14574/28080 [28:48:09<26:50:04,  7.15s/it]
                                                           
{'loss': 0.6219, 'learning_rate': 0.00024675607394987654, 'epoch': 6.23}

 52%|█████▏    | 14574/28080 [28:48:09<26:50:04,  7.15s/it]
 52%|█████▏    | 14575/28080 [28:48:16<26:45:43,  7.13s/it]
                                                           
{'loss': 0.6209, 'learning_rate': 0.00024672724069170466, 'epoch': 6.23}

 52%|█████▏    | 14575/28080 [28:48:16<26:45:43,  7.13s/it]
 52%|█████▏    | 14576/28080 [28:48:23<26:46:42,  7.14s/it]
                                                           
{'loss': 0.6195, 'learning_rate': 0.0002466984074770736, 'epoch': 6.23}

 52%|█████▏    | 14576/28080 [28:48:23<26:46:42,  7.14s/it]
 52%|█████▏    | 14577/28080 [28:48:30<26:34:54,  7.09s/it]
                                                           
{'loss': 0.6151, 'learning_rate': 0.0002466695743063667, 'epoch': 6.23}

 52%|█████▏    | 14577/28080 [28:48:30<26:34:54,  7.09s/it]
 52%|█████▏    | 14578/28080 [28:48:37<26:36:03,  7.09s/it]
                                                           
{'loss': 0.5976, 'learning_rate': 0.0002466407411799678, 'epoch': 6.23}

 52%|█████▏    | 14578/28080 [28:48:37<26:36:03,  7.09s/it]
 52%|█████▏    | 14579/28080 [28:48:44<26:32:23,  7.08s/it]
                                                           
{'loss': 0.6072, 'learning_rate': 0.0002466119080982602, 'epoch': 6.23}

 52%|█████▏    | 14579/28080 [28:48:44<26:32:23,  7.08s/it]
 52%|█████▏    | 14580/28080 [28:48:51<26:31:38,  7.07s/it]
                                                           
{'loss': 0.625, 'learning_rate': 0.00024658307506162785, 'epoch': 6.23}

 52%|█████▏    | 14580/28080 [28:48:51<26:31:38,  7.07s/it]
 52%|█████▏    | 14581/28080 [28:48:58<26:35:50,  7.09s/it]
                                                           
{'loss': 0.6271, 'learning_rate': 0.000246554242070454, 'epoch': 6.23}

 52%|█████▏    | 14581/28080 [28:48:58<26:35:50,  7.09s/it]
 52%|█████▏    | 14582/28080 [28:49:06<26:39:23,  7.11s/it]
                                                           
{'loss': 0.6219, 'learning_rate': 0.00024652540912512255, 'epoch': 6.23}

 52%|█████▏    | 14582/28080 [28:49:06<26:39:23,  7.11s/it]
 52%|█████▏    | 14583/28080 [28:49:13<26:36:14,  7.10s/it]
                                                           
{'loss': 0.6284, 'learning_rate': 0.00024649657622601685, 'epoch': 6.23}

 52%|█████▏    | 14583/28080 [28:49:13<26:36:14,  7.10s/it]
 52%|█████▏    | 14584/28080 [28:49:20<26:26:39,  7.05s/it]
                                                           
{'loss': 0.6373, 'learning_rate': 0.00024646774337352067, 'epoch': 6.23}

 52%|█████▏    | 14584/28080 [28:49:20<26:26:39,  7.05s/it]
 52%|█████▏    | 14585/28080 [28:49:27<26:32:14,  7.08s/it]
                                                           
{'loss': 0.6176, 'learning_rate': 0.00024643891056801745, 'epoch': 6.23}

 52%|█████▏    | 14585/28080 [28:49:27<26:32:14,  7.08s/it]
 52%|█████▏    | 14586/28080 [28:49:34<26:39:29,  7.11s/it]
                                                           
{'loss': 0.611, 'learning_rate': 0.0002464100778098909, 'epoch': 6.23}

 52%|█████▏    | 14586/28080 [28:49:34<26:39:29,  7.11s/it]
 52%|█████▏    | 14587/28080 [28:49:41<26:46:28,  7.14s/it]
                                                           
{'loss': 0.6146, 'learning_rate': 0.0002463812450995245, 'epoch': 6.23}

 52%|█████▏    | 14587/28080 [28:49:41<26:46:28,  7.14s/it]
 52%|█████▏    | 14588/28080 [28:49:48<26:48:42,  7.15s/it]
                                                           
{'loss': 0.6177, 'learning_rate': 0.00024635241243730195, 'epoch': 6.23}

 52%|█████▏    | 14588/28080 [28:49:48<26:48:42,  7.15s/it]
 52%|█████▏    | 14589/28080 [28:49:55<26:44:20,  7.14s/it]
                                                           
{'loss': 0.6132, 'learning_rate': 0.0002463235798236067, 'epoch': 6.23}

 52%|█████▏    | 14589/28080 [28:49:55<26:44:20,  7.14s/it]
 52%|█████▏    | 14590/28080 [28:50:02<26:43:33,  7.13s/it]
                                                           
{'loss': 0.5956, 'learning_rate': 0.0002462947472588226, 'epoch': 6.23}

 52%|█████▏    | 14590/28080 [28:50:02<26:43:33,  7.13s/it]
 52%|█████▏    | 14591/28080 [28:50:10<26:39:23,  7.11s/it]
                                                           
{'loss': 0.6047, 'learning_rate': 0.0002462659147433329, 'epoch': 6.23}

 52%|█████▏    | 14591/28080 [28:50:10<26:39:23,  7.11s/it]
 52%|█████▏    | 14592/28080 [28:50:17<26:33:20,  7.09s/it]
                                                           
{'loss': 0.6143, 'learning_rate': 0.00024623708227752145, 'epoch': 6.23}

 52%|█████▏    | 14592/28080 [28:50:17<26:33:20,  7.09s/it]
 52%|█████▏    | 14593/28080 [28:50:24<26:38:23,  7.11s/it]
                                                           
{'loss': 0.6234, 'learning_rate': 0.00024620824986177167, 'epoch': 6.23}

 52%|█████▏    | 14593/28080 [28:50:24<26:38:23,  7.11s/it]
 52%|█████▏    | 14594/28080 [28:50:31<26:34:05,  7.09s/it]
                                                           
{'loss': 0.6185, 'learning_rate': 0.0002461794174964673, 'epoch': 6.23}

 52%|█████▏    | 14594/28080 [28:50:31<26:34:05,  7.09s/it]
 52%|█████▏    | 14595/28080 [28:50:38<26:41:40,  7.13s/it]
                                                           
{'loss': 0.6022, 'learning_rate': 0.0002461505851819918, 'epoch': 6.23}

 52%|█████▏    | 14595/28080 [28:50:38<26:41:40,  7.13s/it]
 52%|█████▏    | 14596/28080 [28:50:45<26:50:24,  7.17s/it]
                                                           
{'loss': 0.629, 'learning_rate': 0.00024612175291872874, 'epoch': 6.24}

 52%|█████▏    | 14596/28080 [28:50:45<26:50:24,  7.17s/it]
 52%|█████▏    | 14597/28080 [28:50:52<26:42:19,  7.13s/it]
                                                           
{'loss': 0.6228, 'learning_rate': 0.0002460929207070618, 'epoch': 6.24}

 52%|█████▏    | 14597/28080 [28:50:52<26:42:19,  7.13s/it]
 52%|█████▏    | 14598/28080 [28:50:59<26:37:22,  7.11s/it]
                                                           
{'loss': 0.6206, 'learning_rate': 0.00024606408854737456, 'epoch': 6.24}

 52%|█████▏    | 14598/28080 [28:50:59<26:37:22,  7.11s/it]
 52%|█████▏    | 14599/28080 [28:51:07<26:40:09,  7.12s/it]
                                                           
{'loss': 0.6022, 'learning_rate': 0.00024603525644005053, 'epoch': 6.24}

 52%|█████▏    | 14599/28080 [28:51:07<26:40:09,  7.12s/it]
 52%|█████▏    | 14600/28080 [28:51:14<26:42:52,  7.13s/it]
                                                           
{'loss': 0.6076, 'learning_rate': 0.00024600642438547327, 'epoch': 6.24}

 52%|█████▏    | 14600/28080 [28:51:14<26:42:52,  7.13s/it]
 52%|█████▏    | 14601/28080 [28:51:21<26:42:02,  7.13s/it]
                                                           
{'loss': 0.6326, 'learning_rate': 0.0002459775923840265, 'epoch': 6.24}

 52%|█████▏    | 14601/28080 [28:51:21<26:42:02,  7.13s/it]
 52%|█████▏    | 14602/28080 [28:51:28<26:34:30,  7.10s/it]
                                                           
{'loss': 0.6086, 'learning_rate': 0.00024594876043609366, 'epoch': 6.24}

 52%|█████▏    | 14602/28080 [28:51:28<26:34:30,  7.10s/it]
 52%|█████▏    | 14603/28080 [28:51:35<26:34:19,  7.10s/it]
                                                           
{'loss': 0.6079, 'learning_rate': 0.00024591992854205844, 'epoch': 6.24}

 52%|█████▏    | 14603/28080 [28:51:35<26:34:19,  7.10s/it]
 52%|█████▏    | 14604/28080 [28:51:42<26:31:55,  7.09s/it]
                                                           
{'loss': 0.5942, 'learning_rate': 0.0002458910967023043, 'epoch': 6.24}

 52%|█████▏    | 14604/28080 [28:51:42<26:31:55,  7.09s/it]
 52%|█████▏    | 14605/28080 [28:51:49<26:31:37,  7.09s/it]
                                                           
{'loss': 0.6244, 'learning_rate': 0.0002458622649172149, 'epoch': 6.24}

 52%|█████▏    | 14605/28080 [28:51:49<26:31:37,  7.09s/it]
 52%|█████▏    | 14606/28080 [28:51:56<26:34:06,  7.10s/it]
                                                           
{'loss': 0.6355, 'learning_rate': 0.00024583343318717373, 'epoch': 6.24}

 52%|█████▏    | 14606/28080 [28:51:56<26:34:06,  7.10s/it]
 52%|█████▏    | 14607/28080 [28:52:03<26:33:35,  7.10s/it]
                                                           
{'loss': 0.6255, 'learning_rate': 0.0002458046015125646, 'epoch': 6.24}

 52%|█████▏    | 14607/28080 [28:52:03<26:33:35,  7.10s/it]
 52%|█████▏    | 14608/28080 [28:52:10<26:37:58,  7.12s/it]
                                                           
{'loss': 0.6087, 'learning_rate': 0.0002457757698937707, 'epoch': 6.24}

 52%|█████▏    | 14608/28080 [28:52:10<26:37:58,  7.12s/it]
 52%|█████▏    | 14609/28080 [28:52:18<26:39:33,  7.12s/it]
                                                           
{'loss': 0.6242, 'learning_rate': 0.00024574693833117597, 'epoch': 6.24}

 52%|█████▏    | 14609/28080 [28:52:18<26:39:33,  7.12s/it]
 52%|█████▏    | 14610/28080 [28:52:25<26:41:42,  7.13s/it]
                                                           
{'loss': 0.6291, 'learning_rate': 0.0002457181068251638, 'epoch': 6.24}

 52%|█████▏    | 14610/28080 [28:52:25<26:41:42,  7.13s/it]
 52%|█████▏    | 14611/28080 [28:52:32<26:42:59,  7.14s/it]
                                                           
{'loss': 0.5908, 'learning_rate': 0.0002456892753761178, 'epoch': 6.24}

 52%|█████▏    | 14611/28080 [28:52:32<26:42:59,  7.14s/it]
 52%|█████▏    | 14612/28080 [28:52:39<26:46:53,  7.16s/it]
                                                           
{'loss': 0.6103, 'learning_rate': 0.0002456604439844216, 'epoch': 6.24}

 52%|█████▏    | 14612/28080 [28:52:39<26:46:53,  7.16s/it]
 52%|█████▏    | 14613/28080 [28:52:46<26:34:45,  7.11s/it]
                                                           
{'loss': 0.6351, 'learning_rate': 0.00024563161265045864, 'epoch': 6.24}

 52%|█████▏    | 14613/28080 [28:52:46<26:34:45,  7.11s/it]
 52%|█████▏    | 14614/28080 [28:52:53<26:41:17,  7.13s/it]
                                                           
{'loss': 0.6466, 'learning_rate': 0.00024560278137461257, 'epoch': 6.24}

 52%|█████▏    | 14614/28080 [28:52:53<26:41:17,  7.13s/it]
 52%|█████▏    | 14615/28080 [28:53:00<26:45:20,  7.15s/it]
                                                           
{'loss': 0.6233, 'learning_rate': 0.000245573950157267, 'epoch': 6.24}

 52%|█████▏    | 14615/28080 [28:53:00<26:45:20,  7.15s/it]
 52%|█████▏    | 14616/28080 [28:53:08<26:41:29,  7.14s/it]
                                                           
{'loss': 0.646, 'learning_rate': 0.00024554511899880545, 'epoch': 6.24}

 52%|█████▏    | 14616/28080 [28:53:08<26:41:29,  7.14s/it]
 52%|█████▏    | 14617/28080 [28:53:15<26:35:40,  7.11s/it]
                                                           
{'loss': 0.6056, 'learning_rate': 0.0002455162878996115, 'epoch': 6.24}

 52%|█████▏    | 14617/28080 [28:53:15<26:35:40,  7.11s/it]
 52%|█████▏    | 14618/28080 [28:53:22<26:41:12,  7.14s/it]
                                                           
{'loss': 0.6084, 'learning_rate': 0.00024548745686006867, 'epoch': 6.24}

 52%|█████▏    | 14618/28080 [28:53:22<26:41:12,  7.14s/it]
 52%|█████▏    | 14619/28080 [28:53:29<26:43:07,  7.15s/it]
                                                           
{'loss': 0.6377, 'learning_rate': 0.00024545862588056064, 'epoch': 6.25}

 52%|█████▏    | 14619/28080 [28:53:29<26:43:07,  7.15s/it]
 52%|█████▏    | 14620/28080 [28:53:36<26:42:12,  7.14s/it]
                                                           
{'loss': 0.6137, 'learning_rate': 0.00024542979496147075, 'epoch': 6.25}

 52%|█████▏    | 14620/28080 [28:53:36<26:42:12,  7.14s/it]
 52%|█████▏    | 14621/28080 [28:53:43<26:30:26,  7.09s/it]
                                                           
{'loss': 0.6359, 'learning_rate': 0.0002454009641031829, 'epoch': 6.25}

 52%|█████▏    | 14621/28080 [28:53:43<26:30:26,  7.09s/it]
 52%|█████▏    | 14622/28080 [28:53:50<26:33:03,  7.10s/it]
                                                           
{'loss': 0.6217, 'learning_rate': 0.00024537213330608036, 'epoch': 6.25}

 52%|█████▏    | 14622/28080 [28:53:50<26:33:03,  7.10s/it]
 52%|█████▏    | 14623/28080 [28:53:57<26:31:19,  7.10s/it]
                                                           
{'loss': 0.6199, 'learning_rate': 0.00024534330257054693, 'epoch': 6.25}

 52%|█████▏    | 14623/28080 [28:53:57<26:31:19,  7.10s/it]
 52%|█████▏    | 14624/28080 [28:54:04<26:35:36,  7.11s/it]
                                                           
{'loss': 0.6272, 'learning_rate': 0.00024531447189696606, 'epoch': 6.25}

 52%|█████▏    | 14624/28080 [28:54:04<26:35:36,  7.11s/it]
 52%|█████▏    | 14625/28080 [28:54:12<26:41:47,  7.14s/it]
                                                           
{'loss': 0.6268, 'learning_rate': 0.0002452856412857212, 'epoch': 6.25}

 52%|█████▏    | 14625/28080 [28:54:12<26:41:47,  7.14s/it]
 52%|█████▏    | 14626/28080 [28:54:19<26:37:31,  7.12s/it]
                                                           
{'loss': 0.6159, 'learning_rate': 0.00024525681073719614, 'epoch': 6.25}

 52%|█████▏    | 14626/28080 [28:54:19<26:37:31,  7.12s/it]
 52%|█████▏    | 14627/28080 [28:54:26<26:32:48,  7.10s/it]
                                                           
{'loss': 0.6257, 'learning_rate': 0.00024522798025177416, 'epoch': 6.25}

 52%|█████▏    | 14627/28080 [28:54:26<26:32:48,  7.10s/it]
 52%|█████▏    | 14628/28080 [28:54:33<26:34:57,  7.11s/it]
                                                           
{'loss': 0.6274, 'learning_rate': 0.00024519914982983906, 'epoch': 6.25}

 52%|█████▏    | 14628/28080 [28:54:33<26:34:57,  7.11s/it]
 52%|█████▏    | 14629/28080 [28:54:40<26:38:00,  7.13s/it]
                                                           
{'loss': 0.6199, 'learning_rate': 0.0002451703194717743, 'epoch': 6.25}

 52%|█████▏    | 14629/28080 [28:54:40<26:38:00,  7.13s/it]
 52%|█████▏    | 14630/28080 [28:54:47<26:32:30,  7.10s/it]
                                                           
{'loss': 0.6194, 'learning_rate': 0.00024514148917796353, 'epoch': 6.25}

 52%|█████▏    | 14630/28080 [28:54:47<26:32:30,  7.10s/it]
 52%|█████▏    | 14631/28080 [28:54:54<26:39:22,  7.14s/it]
                                                           
{'loss': 0.635, 'learning_rate': 0.00024511265894879014, 'epoch': 6.25}

 52%|█████▏    | 14631/28080 [28:54:54<26:39:22,  7.14s/it]
 52%|█████▏    | 14632/28080 [28:55:01<26:32:01,  7.10s/it]
                                                           
{'loss': 0.637, 'learning_rate': 0.00024508382878463787, 'epoch': 6.25}

 52%|█████▏    | 14632/28080 [28:55:01<26:32:01,  7.10s/it]
 52%|█████▏    | 14633/28080 [28:55:09<26:36:18,  7.12s/it]
                                                           
{'loss': 0.6296, 'learning_rate': 0.0002450549986858901, 'epoch': 6.25}

 52%|█████▏    | 14633/28080 [28:55:09<26:36:18,  7.12s/it]
 52%|█████▏    | 14634/28080 [28:55:16<26:36:21,  7.12s/it]
                                                           
{'loss': 0.6315, 'learning_rate': 0.0002450261686529305, 'epoch': 6.25}

 52%|█████▏    | 14634/28080 [28:55:16<26:36:21,  7.12s/it]
 52%|█████▏    | 14635/28080 [28:55:23<26:31:44,  7.10s/it]
                                                           
{'loss': 0.6172, 'learning_rate': 0.0002449973386861426, 'epoch': 6.25}

 52%|█████▏    | 14635/28080 [28:55:23<26:31:44,  7.10s/it]
 52%|█████▏    | 14636/28080 [28:55:30<26:40:36,  7.14s/it]
                                                           
{'loss': 0.5976, 'learning_rate': 0.00024496850878591, 'epoch': 6.25}

 52%|█████▏    | 14636/28080 [28:55:30<26:40:36,  7.14s/it]
 52%|█████▏    | 14637/28080 [28:55:37<26:34:00,  7.11s/it]
                                                           
{'loss': 0.62, 'learning_rate': 0.0002449396789526161, 'epoch': 6.25}

 52%|█████▏    | 14637/28080 [28:55:37<26:34:00,  7.11s/it]
 52%|█████▏    | 14638/28080 [28:55:44<26:38:27,  7.13s/it]
                                                           
{'loss': 0.6319, 'learning_rate': 0.00024491084918664465, 'epoch': 6.25}

 52%|█████▏    | 14638/28080 [28:55:44<26:38:27,  7.13s/it]
 52%|█████▏    | 14639/28080 [28:55:51<26:31:36,  7.10s/it]
                                                           
{'loss': 0.6157, 'learning_rate': 0.000244882019488379, 'epoch': 6.25}

 52%|█████▏    | 14639/28080 [28:55:51<26:31:36,  7.10s/it]
 52%|█████▏    | 14640/28080 [28:55:58<26:39:38,  7.14s/it]
                                                           
{'loss': 0.6407, 'learning_rate': 0.0002448531898582029, 'epoch': 6.25}

 52%|█████▏    | 14640/28080 [28:55:58<26:39:38,  7.14s/it]
 52%|█████▏    | 14641/28080 [28:56:06<26:34:32,  7.12s/it]
                                                           
{'loss': 0.6196, 'learning_rate': 0.0002448243602964997, 'epoch': 6.25}

 52%|█████▏    | 14641/28080 [28:56:06<26:34:32,  7.12s/it]
 52%|█████▏    | 14642/28080 [28:56:13<26:36:56,  7.13s/it]
                                                           
{'loss': 0.62, 'learning_rate': 0.0002447955308036531, 'epoch': 6.25}

 52%|█████▏    | 14642/28080 [28:56:13<26:36:56,  7.13s/it]
 52%|█████▏    | 14643/28080 [28:56:20<26:34:33,  7.12s/it]
                                                           
{'loss': 0.6228, 'learning_rate': 0.0002447667013800466, 'epoch': 6.26}

 52%|█████▏    | 14643/28080 [28:56:20<26:34:33,  7.12s/it]
 52%|█████▏    | 14644/28080 [28:56:27<26:32:32,  7.11s/it]
                                                           
{'loss': 0.6165, 'learning_rate': 0.00024473787202606374, 'epoch': 6.26}

 52%|█████▏    | 14644/28080 [28:56:27<26:32:32,  7.11s/it]
 52%|█████▏    | 14645/28080 [28:56:34<26:24:35,  7.08s/it]
                                                           
{'loss': 0.634, 'learning_rate': 0.0002447090427420881, 'epoch': 6.26}

 52%|█████▏    | 14645/28080 [28:56:34<26:24:35,  7.08s/it]
 52%|█████▏    | 14646/28080 [28:56:41<26:28:58,  7.10s/it]
                                                           
{'loss': 0.6077, 'learning_rate': 0.00024468021352850314, 'epoch': 6.26}

 52%|█████▏    | 14646/28080 [28:56:41<26:28:58,  7.10s/it]
 52%|█████▏    | 14647/28080 [28:56:48<26:29:12,  7.10s/it]
                                                           
{'loss': 0.6176, 'learning_rate': 0.0002446513843856924, 'epoch': 6.26}

 52%|█████▏    | 14647/28080 [28:56:48<26:29:12,  7.10s/it]
 52%|█████▏    | 14648/28080 [28:56:55<26:27:09,  7.09s/it]
                                                           
{'loss': 0.6306, 'learning_rate': 0.0002446225553140396, 'epoch': 6.26}

 52%|█████▏    | 14648/28080 [28:56:55<26:27:09,  7.09s/it]
 52%|█████▏    | 14649/28080 [28:57:02<26:25:35,  7.08s/it]
                                                           
{'loss': 0.6318, 'learning_rate': 0.00024459372631392814, 'epoch': 6.26}

 52%|█████▏    | 14649/28080 [28:57:02<26:25:35,  7.08s/it]
 52%|█████▏    | 14650/28080 [28:57:10<26:36:48,  7.13s/it]
                                                           
{'loss': 0.6142, 'learning_rate': 0.00024456489738574147, 'epoch': 6.26}

 52%|█████▏    | 14650/28080 [28:57:10<26:36:48,  7.13s/it]
 52%|█████▏    | 14651/28080 [28:57:17<26:32:03,  7.11s/it]
                                                           
{'loss': 0.63, 'learning_rate': 0.00024453606852986327, 'epoch': 6.26}

 52%|█████▏    | 14651/28080 [28:57:17<26:32:03,  7.11s/it]
 52%|█████▏    | 14652/28080 [28:57:24<26:34:24,  7.12s/it]
                                                           
{'loss': 0.6345, 'learning_rate': 0.0002445072397466771, 'epoch': 6.26}

 52%|█████▏    | 14652/28080 [28:57:24<26:34:24,  7.12s/it]
 52%|█████▏    | 14653/28080 [28:57:31<26:30:27,  7.11s/it]
                                                           
{'loss': 0.6286, 'learning_rate': 0.0002444784110365664, 'epoch': 6.26}

 52%|█████▏    | 14653/28080 [28:57:31<26:30:27,  7.11s/it]
 52%|█████▏    | 14654/28080 [28:57:38<26:24:54,  7.08s/it]
                                                           
{'loss': 0.6166, 'learning_rate': 0.00024444958239991463, 'epoch': 6.26}

 52%|█████▏    | 14654/28080 [28:57:38<26:24:54,  7.08s/it]
 52%|█████▏    | 14655/28080 [28:57:45<26:27:48,  7.10s/it]
                                                           
{'loss': 0.6143, 'learning_rate': 0.0002444207538371056, 'epoch': 6.26}

 52%|█████▏    | 14655/28080 [28:57:45<26:27:48,  7.10s/it]
 52%|█████▏    | 14656/28080 [28:57:52<26:36:33,  7.14s/it]
                                                           
{'loss': 0.6064, 'learning_rate': 0.0002443919253485226, 'epoch': 6.26}

 52%|█████▏    | 14656/28080 [28:57:52<26:36:33,  7.14s/it]
 52%|█████▏    | 14657/28080 [28:57:59<26:34:47,  7.13s/it]
                                                           
{'loss': 0.6356, 'learning_rate': 0.00024436309693454935, 'epoch': 6.26}

 52%|█████▏    | 14657/28080 [28:57:59<26:34:47,  7.13s/it]
 52%|█████▏    | 14658/28080 [28:58:06<26:28:06,  7.10s/it]
                                                           
{'loss': 0.6199, 'learning_rate': 0.0002443342685955691, 'epoch': 6.26}

 52%|█████▏    | 14658/28080 [28:58:06<26:28:06,  7.10s/it]
 52%|█████▏    | 14659/28080 [28:58:13<26:28:13,  7.10s/it]
                                                           
{'loss': 0.6092, 'learning_rate': 0.0002443054403319657, 'epoch': 6.26}

 52%|█████▏    | 14659/28080 [28:58:13<26:28:13,  7.10s/it]
 52%|█████▏    | 14660/28080 [28:58:20<26:24:59,  7.09s/it]
                                                           
{'loss': 0.6304, 'learning_rate': 0.00024427661214412253, 'epoch': 6.26}

 52%|█████▏    | 14660/28080 [28:58:20<26:24:59,  7.09s/it]
 52%|█████▏    | 14661/28080 [28:58:28<26:23:49,  7.08s/it]
                                                           
{'loss': 0.6151, 'learning_rate': 0.00024424778403242314, 'epoch': 6.26}

 52%|█████▏    | 14661/28080 [28:58:28<26:23:49,  7.08s/it]
 52%|█████▏    | 14662/28080 [28:58:35<26:18:23,  7.06s/it]
                                                           
{'loss': 0.6157, 'learning_rate': 0.000244218955997251, 'epoch': 6.26}

 52%|█████▏    | 14662/28080 [28:58:35<26:18:23,  7.06s/it]
 52%|█████▏    | 14663/28080 [28:58:42<26:20:05,  7.07s/it]
                                                           
{'loss': 0.6121, 'learning_rate': 0.0002441901280389897, 'epoch': 6.26}

 52%|█████▏    | 14663/28080 [28:58:42<26:20:05,  7.07s/it]
 52%|█████▏    | 14664/28080 [28:58:49<26:20:41,  7.07s/it]
                                                           
{'loss': 0.6261, 'learning_rate': 0.00024416130015802274, 'epoch': 6.26}

 52%|█████▏    | 14664/28080 [28:58:49<26:20:41,  7.07s/it]
 52%|█████▏    | 14665/28080 [28:58:56<26:20:26,  7.07s/it]
                                                           
{'loss': 0.615, 'learning_rate': 0.00024413247235473374, 'epoch': 6.26}

 52%|█████▏    | 14665/28080 [28:58:56<26:20:26,  7.07s/it]
 52%|█████▏    | 14666/28080 [28:59:03<26:22:37,  7.08s/it]
                                                           
{'loss': 0.622, 'learning_rate': 0.00024410364462950604, 'epoch': 6.27}

 52%|█████▏    | 14666/28080 [28:59:03<26:22:37,  7.08s/it]
 52%|█████▏    | 14667/28080 [28:59:10<26:26:19,  7.10s/it]
                                                           
{'loss': 0.6181, 'learning_rate': 0.00024407481698272336, 'epoch': 6.27}

 52%|█████▏    | 14667/28080 [28:59:10<26:26:19,  7.10s/it]
 52%|█████▏    | 14668/28080 [28:59:17<26:22:23,  7.08s/it]
                                                           
{'loss': 0.5993, 'learning_rate': 0.00024404598941476897, 'epoch': 6.27}

 52%|█████▏    | 14668/28080 [28:59:17<26:22:23,  7.08s/it]
 52%|█████▏    | 14669/28080 [28:59:24<26:21:40,  7.08s/it]
                                                           
{'loss': 0.6243, 'learning_rate': 0.00024401716192602675, 'epoch': 6.27}

 52%|█████▏    | 14669/28080 [28:59:24<26:21:40,  7.08s/it]
 52%|█████▏    | 14670/28080 [28:59:31<26:26:48,  7.10s/it]
                                                           
{'loss': 0.6346, 'learning_rate': 0.00024398833451687982, 'epoch': 6.27}

 52%|█████▏    | 14670/28080 [28:59:31<26:26:48,  7.10s/it]
 52%|█████▏    | 14671/28080 [28:59:38<26:26:57,  7.10s/it]
                                                           
{'loss': 0.6085, 'learning_rate': 0.00024395950718771205, 'epoch': 6.27}

 52%|█████▏    | 14671/28080 [28:59:38<26:26:57,  7.10s/it]
 52%|█████▏    | 14672/28080 [28:59:45<26:20:21,  7.07s/it]
                                                           
{'loss': 0.6049, 'learning_rate': 0.00024393067993890672, 'epoch': 6.27}

 52%|█████▏    | 14672/28080 [28:59:45<26:20:21,  7.07s/it]
 52%|█████▏    | 14673/28080 [28:59:53<26:23:57,  7.09s/it]
                                                           
{'loss': 0.6243, 'learning_rate': 0.00024390185277084752, 'epoch': 6.27}

 52%|█████▏    | 14673/28080 [28:59:53<26:23:57,  7.09s/it]
 52%|█████▏    | 14674/28080 [29:00:00<26:27:20,  7.10s/it]
                                                           
{'loss': 0.6252, 'learning_rate': 0.00024387302568391788, 'epoch': 6.27}

 52%|█████▏    | 14674/28080 [29:00:00<26:27:20,  7.10s/it]
 52%|█████▏    | 14675/28080 [29:00:07<26:32:28,  7.13s/it]
                                                           
{'loss': 0.6236, 'learning_rate': 0.00024384419867850117, 'epoch': 6.27}

 52%|█████▏    | 14675/28080 [29:00:07<26:32:28,  7.13s/it]
 52%|█████▏    | 14676/28080 [29:00:14<26:33:32,  7.13s/it]
                                                           
{'loss': 0.605, 'learning_rate': 0.00024381537175498116, 'epoch': 6.27}

 52%|█████▏    | 14676/28080 [29:00:14<26:33:32,  7.13s/it]
 52%|█████▏    | 14677/28080 [29:00:21<26:33:56,  7.14s/it]
                                                           
{'loss': 0.6067, 'learning_rate': 0.0002437865449137412, 'epoch': 6.27}

 52%|█████▏    | 14677/28080 [29:00:21<26:33:56,  7.14s/it]
 52%|█████▏    | 14678/28080 [29:00:28<26:31:35,  7.13s/it]
                                                           
{'loss': 0.6329, 'learning_rate': 0.0002437577181551649, 'epoch': 6.27}

 52%|█████▏    | 14678/28080 [29:00:28<26:31:35,  7.13s/it]
 52%|█████▏    | 14679/28080 [29:00:36<26:41:37,  7.17s/it]
                                                           
{'loss': 0.6238, 'learning_rate': 0.00024372889147963568, 'epoch': 6.27}

 52%|█████▏    | 14679/28080 [29:00:36<26:41:37,  7.17s/it]
 52%|█████▏    | 14680/28080 [29:00:43<26:29:58,  7.12s/it]
                                                           
{'loss': 0.6291, 'learning_rate': 0.00024370006488753712, 'epoch': 6.27}

 52%|█████▏    | 14680/28080 [29:00:43<26:29:58,  7.12s/it]
 52%|█████▏    | 14681/28080 [29:00:50<26:25:48,  7.10s/it]
                                                           
{'loss': 0.6075, 'learning_rate': 0.00024367123837925264, 'epoch': 6.27}

 52%|█████▏    | 14681/28080 [29:00:50<26:25:48,  7.10s/it]
 52%|█████▏    | 14682/28080 [29:00:57<26:26:56,  7.11s/it]
                                                           
{'loss': 0.5916, 'learning_rate': 0.00024364241195516586, 'epoch': 6.27}

 52%|█████▏    | 14682/28080 [29:00:57<26:26:56,  7.11s/it]
 52%|█████▏    | 14683/28080 [29:01:04<26:19:03,  7.07s/it]
                                                           
{'loss': 0.6391, 'learning_rate': 0.00024361358561566019, 'epoch': 6.27}

 52%|█████▏    | 14683/28080 [29:01:04<26:19:03,  7.07s/it]
 52%|█████▏    | 14684/28080 [29:01:11<26:23:42,  7.09s/it]
                                                           
{'loss': 0.616, 'learning_rate': 0.00024358475936111924, 'epoch': 6.27}

 52%|█████▏    | 14684/28080 [29:01:11<26:23:42,  7.09s/it]
 52%|█████▏    | 14685/28080 [29:01:18<26:24:06,  7.10s/it]
                                                           
{'loss': 0.6373, 'learning_rate': 0.0002435559331919263, 'epoch': 6.27}

 52%|█████▏    | 14685/28080 [29:01:18<26:24:06,  7.10s/it]
 52%|█████▏    | 14686/28080 [29:01:25<26:29:49,  7.12s/it]
                                                           
{'loss': 0.6245, 'learning_rate': 0.00024352710710846525, 'epoch': 6.27}

 52%|█████▏    | 14686/28080 [29:01:25<26:29:49,  7.12s/it]
 52%|█████▏    | 14687/28080 [29:01:32<26:34:13,  7.14s/it]
                                                           
{'loss': 0.6411, 'learning_rate': 0.00024349828111111914, 'epoch': 6.27}

 52%|█████▏    | 14687/28080 [29:01:32<26:34:13,  7.14s/it]
 52%|█████▏    | 14688/28080 [29:01:39<26:28:30,  7.12s/it]
                                                           
{'loss': 0.6339, 'learning_rate': 0.00024346945520027185, 'epoch': 6.27}

 52%|█████▏    | 14688/28080 [29:01:39<26:28:30,  7.12s/it]
 52%|█████▏    | 14689/28080 [29:01:47<26:35:37,  7.15s/it]
                                                           
{'loss': 0.6, 'learning_rate': 0.0002434406293763066, 'epoch': 6.28}

 52%|█████▏    | 14689/28080 [29:01:47<26:35:37,  7.15s/it]
 52%|█████▏    | 14690/28080 [29:01:54<26:29:50,  7.12s/it]
                                                           
{'loss': 0.604, 'learning_rate': 0.0002434118036396071, 'epoch': 6.28}

 52%|█████▏    | 14690/28080 [29:01:54<26:29:50,  7.12s/it]
 52%|█████▏    | 14691/28080 [29:02:01<26:34:58,  7.15s/it]
                                                           
{'loss': 0.625, 'learning_rate': 0.0002433829779905567, 'epoch': 6.28}

 52%|█████▏    | 14691/28080 [29:02:01<26:34:58,  7.15s/it]
 52%|█████▏    | 14692/28080 [29:02:08<26:28:33,  7.12s/it]
                                                           
{'loss': 0.6299, 'learning_rate': 0.000243354152429539, 'epoch': 6.28}

 52%|█████▏    | 14692/28080 [29:02:08<26:28:33,  7.12s/it]
 52%|█████▏    | 14693/28080 [29:02:15<26:35:06,  7.15s/it]
                                                           
{'loss': 0.6182, 'learning_rate': 0.0002433253269569374, 'epoch': 6.28}

 52%|█████▏    | 14693/28080 [29:02:15<26:35:06,  7.15s/it]
 52%|█████▏    | 14694/28080 [29:02:22<26:35:06,  7.15s/it]
                                                           
{'loss': 0.6233, 'learning_rate': 0.0002432965015731355, 'epoch': 6.28}

 52%|█████▏    | 14694/28080 [29:02:22<26:35:06,  7.15s/it]
 52%|█████▏    | 14695/28080 [29:02:29<26:32:04,  7.14s/it]
                                                           
{'loss': 0.627, 'learning_rate': 0.00024326767627851667, 'epoch': 6.28}

 52%|█████▏    | 14695/28080 [29:02:29<26:32:04,  7.14s/it]
 52%|█████▏    | 14696/28080 [29:02:37<26:30:58,  7.13s/it]
                                                           
{'loss': 0.6451, 'learning_rate': 0.00024323885107346453, 'epoch': 6.28}

 52%|█████▏    | 14696/28080 [29:02:37<26:30:58,  7.13s/it]
 52%|█████▏    | 14697/28080 [29:02:44<26:27:49,  7.12s/it]
                                                           
{'loss': 0.6229, 'learning_rate': 0.0002432100259583624, 'epoch': 6.28}

 52%|█████▏    | 14697/28080 [29:02:44<26:27:49,  7.12s/it]
 52%|█████▏    | 14698/28080 [29:02:51<26:36:40,  7.16s/it]
                                                           
{'loss': 0.62, 'learning_rate': 0.00024318120093359398, 'epoch': 6.28}

 52%|█████▏    | 14698/28080 [29:02:51<26:36:40,  7.16s/it]
 52%|█████▏    | 14699/28080 [29:02:58<26:33:41,  7.15s/it]
                                                           
{'loss': 0.6481, 'learning_rate': 0.00024315237599954262, 'epoch': 6.28}

 52%|█████▏    | 14699/28080 [29:02:58<26:33:41,  7.15s/it]
 52%|█████▏    | 14700/28080 [29:03:05<26:27:52,  7.12s/it]
                                                           
{'loss': 0.619, 'learning_rate': 0.00024312355115659176, 'epoch': 6.28}

 52%|█████▏    | 14700/28080 [29:03:05<26:27:52,  7.12s/it]
 52%|█████▏    | 14701/28080 [29:03:12<26:31:36,  7.14s/it]
                                                           
{'loss': 0.6083, 'learning_rate': 0.00024309472640512506, 'epoch': 6.28}

 52%|█████▏    | 14701/28080 [29:03:12<26:31:36,  7.14s/it]
 52%|█████▏    | 14702/28080 [29:03:19<26:31:19,  7.14s/it]
                                                           
{'loss': 0.6072, 'learning_rate': 0.00024306590174552576, 'epoch': 6.28}

 52%|█████▏    | 14702/28080 [29:03:19<26:31:19,  7.14s/it]
 52%|█████▏    | 14703/28080 [29:03:26<26:31:38,  7.14s/it]
                                                           
{'loss': 0.5936, 'learning_rate': 0.00024303707717817765, 'epoch': 6.28}

 52%|█████▏    | 14703/28080 [29:03:26<26:31:38,  7.14s/it]
 52%|█████▏    | 14704/28080 [29:03:34<26:28:54,  7.13s/it]
                                                           
{'loss': 0.6263, 'learning_rate': 0.00024300825270346388, 'epoch': 6.28}

 52%|█████▏    | 14704/28080 [29:03:34<26:28:54,  7.13s/it]
 52%|█████▏    | 14705/28080 [29:03:41<26:28:18,  7.13s/it]
                                                           
{'loss': 0.5978, 'learning_rate': 0.0002429794283217683, 'epoch': 6.28}

 52%|█████▏    | 14705/28080 [29:03:41<26:28:18,  7.13s/it]
 52%|█████▏    | 14706/28080 [29:03:48<26:25:57,  7.12s/it]
                                                           
{'loss': 0.628, 'learning_rate': 0.00024295060403347398, 'epoch': 6.28}

 52%|█████▏    | 14706/28080 [29:03:48<26:25:57,  7.12s/it]
 52%|█████▏    | 14707/28080 [29:03:55<26:38:12,  7.17s/it]
                                                           
{'loss': 0.6243, 'learning_rate': 0.00024292177983896467, 'epoch': 6.28}

 52%|█████▏    | 14707/28080 [29:03:55<26:38:12,  7.17s/it]
 52%|█████▏    | 14708/28080 [29:04:02<26:37:16,  7.17s/it]
                                                           
{'loss': 0.6191, 'learning_rate': 0.00024289295573862377, 'epoch': 6.28}

 52%|█████▏    | 14708/28080 [29:04:02<26:37:16,  7.17s/it]
 52%|█████▏    | 14709/28080 [29:04:09<26:36:56,  7.17s/it]
                                                           
{'loss': 0.6144, 'learning_rate': 0.00024286413173283484, 'epoch': 6.28}

 52%|█████▏    | 14709/28080 [29:04:09<26:36:56,  7.17s/it]
 52%|█████▏    | 14710/28080 [29:04:16<26:26:13,  7.12s/it]
                                                           
{'loss': 0.6418, 'learning_rate': 0.00024283530782198118, 'epoch': 6.28}

 52%|█████▏    | 14710/28080 [29:04:16<26:26:13,  7.12s/it]
 52%|█████▏    | 14711/28080 [29:04:24<26:31:31,  7.14s/it]
                                                           
{'loss': 0.6177, 'learning_rate': 0.00024280648400644642, 'epoch': 6.28}

 52%|█████▏    | 14711/28080 [29:04:24<26:31:31,  7.14s/it]
 52%|█████▏    | 14712/28080 [29:04:31<26:16:32,  7.08s/it]
                                                           
{'loss': 0.629, 'learning_rate': 0.00024277766028661392, 'epoch': 6.28}

 52%|█████▏    | 14712/28080 [29:04:31<26:16:32,  7.08s/it]
 52%|█████▏    | 14713/28080 [29:04:38<26:19:38,  7.09s/it]
                                                           
{'loss': 0.594, 'learning_rate': 0.00024274883666286726, 'epoch': 6.29}

 52%|█████▏    | 14713/28080 [29:04:38<26:19:38,  7.09s/it]
 52%|█████▏    | 14714/28080 [29:04:45<26:19:48,  7.09s/it]
                                                           
{'loss': 0.6198, 'learning_rate': 0.0002427200131355898, 'epoch': 6.29}

 52%|█████▏    | 14714/28080 [29:04:45<26:19:48,  7.09s/it]
 52%|█████▏    | 14715/28080 [29:04:52<26:17:55,  7.08s/it]
                                                           
{'loss': 0.6299, 'learning_rate': 0.00024269118970516508, 'epoch': 6.29}

 52%|█████▏    | 14715/28080 [29:04:52<26:17:55,  7.08s/it]
 52%|█████▏    | 14716/28080 [29:04:59<26:17:43,  7.08s/it]
                                                           
{'loss': 0.6317, 'learning_rate': 0.00024266236637197645, 'epoch': 6.29}

 52%|█████▏    | 14716/28080 [29:04:59<26:17:43,  7.08s/it]
 52%|█████▏    | 14717/28080 [29:05:06<26:19:52,  7.09s/it]
                                                           
{'loss': 0.6079, 'learning_rate': 0.00024263354313640761, 'epoch': 6.29}

 52%|█████▏    | 14717/28080 [29:05:06<26:19:52,  7.09s/it]
 52%|█████▏    | 14718/28080 [29:05:13<26:16:56,  7.08s/it]
                                                           
{'loss': 0.6163, 'learning_rate': 0.00024260471999884177, 'epoch': 6.29}

 52%|█████▏    | 14718/28080 [29:05:13<26:16:56,  7.08s/it]
 52%|█████▏    | 14719/28080 [29:05:20<26:20:29,  7.10s/it]
                                                           
{'loss': 0.5933, 'learning_rate': 0.0002425758969596626, 'epoch': 6.29}

 52%|█████▏    | 14719/28080 [29:05:20<26:20:29,  7.10s/it]
 52%|█████▏    | 14720/28080 [29:05:27<26:23:01,  7.11s/it]
                                                           
{'loss': 0.6141, 'learning_rate': 0.00024254707401925334, 'epoch': 6.29}

 52%|█████▏    | 14720/28080 [29:05:27<26:23:01,  7.11s/it]
 52%|█████▏    | 14721/28080 [29:05:35<26:27:38,  7.13s/it]
                                                           
{'loss': 0.5862, 'learning_rate': 0.00024251825117799767, 'epoch': 6.29}

 52%|█████▏    | 14721/28080 [29:05:35<26:27:38,  7.13s/it]
 52%|█████▏    | 14722/28080 [29:05:42<26:27:08,  7.13s/it]
                                                           
{'loss': 0.6257, 'learning_rate': 0.0002424894284362789, 'epoch': 6.29}

 52%|█████▏    | 14722/28080 [29:05:42<26:27:08,  7.13s/it]
 52%|█████▏    | 14723/28080 [29:05:49<26:32:11,  7.15s/it]
                                                           
{'loss': 0.6103, 'learning_rate': 0.00024246060579448056, 'epoch': 6.29}

 52%|█████▏    | 14723/28080 [29:05:49<26:32:11,  7.15s/it]
 52%|█████▏    | 14724/28080 [29:05:56<26:28:50,  7.14s/it]
                                                           
{'loss': 0.6082, 'learning_rate': 0.00024243178325298608, 'epoch': 6.29}

 52%|█████▏    | 14724/28080 [29:05:56<26:28:50,  7.14s/it]
 52%|█████▏    | 14725/28080 [29:06:03<26:22:12,  7.11s/it]
                                                           
{'loss': 0.6088, 'learning_rate': 0.0002424029608121789, 'epoch': 6.29}

 52%|█████▏    | 14725/28080 [29:06:03<26:22:12,  7.11s/it]
 52%|█████▏    | 14726/28080 [29:06:10<26:27:07,  7.13s/it]
                                                           
{'loss': 0.5834, 'learning_rate': 0.00024237413847244256, 'epoch': 6.29}

 52%|█████▏    | 14726/28080 [29:06:10<26:27:07,  7.13s/it]
 52%|█████▏    | 14727/28080 [29:06:17<26:27:29,  7.13s/it]
                                                           
{'loss': 0.6021, 'learning_rate': 0.00024234531623416034, 'epoch': 6.29}

 52%|█████▏    | 14727/28080 [29:06:17<26:27:29,  7.13s/it]
 52%|█████▏    | 14728/28080 [29:06:24<26:22:17,  7.11s/it]
                                                           
{'loss': 0.6281, 'learning_rate': 0.00024231649409771586, 'epoch': 6.29}

 52%|█████▏    | 14728/28080 [29:06:24<26:22:17,  7.11s/it]
 52%|█████▏    | 14729/28080 [29:06:31<26:21:45,  7.11s/it]
                                                           
{'loss': 0.626, 'learning_rate': 0.00024228767206349244, 'epoch': 6.29}

 52%|█████▏    | 14729/28080 [29:06:31<26:21:45,  7.11s/it]
 52%|█████▏    | 14730/28080 [29:06:39<26:23:07,  7.12s/it]
                                                           
{'loss': 0.6249, 'learning_rate': 0.00024225885013187364, 'epoch': 6.29}

 52%|█████▏    | 14730/28080 [29:06:39<26:23:07,  7.12s/it]
 52%|█████▏    | 14731/28080 [29:06:46<26:20:00,  7.10s/it]
                                                           
{'loss': 0.5935, 'learning_rate': 0.00024223002830324282, 'epoch': 6.29}

 52%|█████▏    | 14731/28080 [29:06:46<26:20:00,  7.10s/it]
 52%|█████▏    | 14732/28080 [29:06:53<26:12:02,  7.07s/it]
                                                           
{'loss': 0.6006, 'learning_rate': 0.0002422012065779835, 'epoch': 6.29}

 52%|█████▏    | 14732/28080 [29:06:53<26:12:02,  7.07s/it]
 52%|█████▏    | 14733/28080 [29:07:00<26:14:22,  7.08s/it]
                                                           
{'loss': 0.6221, 'learning_rate': 0.00024217238495647894, 'epoch': 6.29}

 52%|█████▏    | 14733/28080 [29:07:00<26:14:22,  7.08s/it]
 52%|█████▏    | 14734/28080 [29:07:07<26:10:21,  7.06s/it]
                                                           
{'loss': 0.6211, 'learning_rate': 0.00024214356343911291, 'epoch': 6.29}

 52%|█████▏    | 14734/28080 [29:07:07<26:10:21,  7.06s/it]
 52%|█████▏    | 14735/28080 [29:07:14<26:11:41,  7.07s/it]
                                                           
{'loss': 0.6287, 'learning_rate': 0.00024211474202626853, 'epoch': 6.29}

 52%|█████▏    | 14735/28080 [29:07:14<26:11:41,  7.07s/it]
 52%|█████▏    | 14736/28080 [29:07:21<26:13:11,  7.07s/it]
                                                           
{'loss': 0.6093, 'learning_rate': 0.00024208592071832952, 'epoch': 6.3}

 52%|█████▏    | 14736/28080 [29:07:21<26:13:11,  7.07s/it]
 52%|█████▏    | 14737/28080 [29:07:28<26:17:33,  7.09s/it]
                                                           
{'loss': 0.6199, 'learning_rate': 0.000242057099515679, 'epoch': 6.3}

 52%|█████▏    | 14737/28080 [29:07:28<26:17:33,  7.09s/it]
 52%|█████▏    | 14738/28080 [29:07:35<26:12:38,  7.07s/it]
                                                           
{'loss': 0.6192, 'learning_rate': 0.00024202827841870067, 'epoch': 6.3}

 52%|█████▏    | 14738/28080 [29:07:35<26:12:38,  7.07s/it]
 52%|█████▏    | 14739/28080 [29:07:42<26:12:53,  7.07s/it]
                                                           
{'loss': 0.6209, 'learning_rate': 0.00024199945742777785, 'epoch': 6.3}

 52%|█████▏    | 14739/28080 [29:07:42<26:12:53,  7.07s/it]
 52%|█████▏    | 14740/28080 [29:07:49<26:13:29,  7.08s/it]
                                                           
{'loss': 0.6235, 'learning_rate': 0.000241970636543294, 'epoch': 6.3}

 52%|█████▏    | 14740/28080 [29:07:49<26:13:29,  7.08s/it]
 52%|█████▏    | 14741/28080 [29:07:56<26:13:14,  7.08s/it]
                                                           
{'loss': 0.6145, 'learning_rate': 0.00024194181576563253, 'epoch': 6.3}

 52%|█████▏    | 14741/28080 [29:07:56<26:13:14,  7.08s/it]
 52%|█████▎    | 14742/28080 [29:08:04<26:20:25,  7.11s/it]
                                                           
{'loss': 0.6134, 'learning_rate': 0.00024191299509517694, 'epoch': 6.3}

 52%|█████▎    | 14742/28080 [29:08:04<26:20:25,  7.11s/it]
 53%|█████▎    | 14743/28080 [29:08:11<26:14:20,  7.08s/it]
                                                           
{'loss': 0.6357, 'learning_rate': 0.00024188417453231055, 'epoch': 6.3}

 53%|█████▎    | 14743/28080 [29:08:11<26:14:20,  7.08s/it]
 53%|█████▎    | 14744/28080 [29:08:18<26:09:13,  7.06s/it]
                                                           
{'loss': 0.6443, 'learning_rate': 0.0002418553540774169, 'epoch': 6.3}

 53%|█████▎    | 14744/28080 [29:08:18<26:09:13,  7.06s/it]
 53%|█████▎    | 14745/28080 [29:08:25<26:16:34,  7.09s/it]
                                                           
{'loss': 0.6215, 'learning_rate': 0.00024182653373087932, 'epoch': 6.3}

 53%|█████▎    | 14745/28080 [29:08:25<26:16:34,  7.09s/it]
 53%|█████▎    | 14746/28080 [29:08:32<26:19:33,  7.11s/it]
                                                           
{'loss': 0.6124, 'learning_rate': 0.0002417977134930813, 'epoch': 6.3}

 53%|█████▎    | 14746/28080 [29:08:32<26:19:33,  7.11s/it]
 53%|█████▎    | 14747/28080 [29:08:39<26:09:32,  7.06s/it]
                                                           
{'loss': 0.6533, 'learning_rate': 0.00024176889336440617, 'epoch': 6.3}

 53%|█████▎    | 14747/28080 [29:08:39<26:09:32,  7.06s/it]
 53%|█████▎    | 14748/28080 [29:08:46<26:04:30,  7.04s/it]
                                                           
{'loss': 0.6448, 'learning_rate': 0.00024174007334523754, 'epoch': 6.3}

 53%|█████▎    | 14748/28080 [29:08:46<26:04:30,  7.04s/it]
 53%|█████▎    | 14749/28080 [29:08:53<26:12:13,  7.08s/it]
                                                           
{'loss': 0.6237, 'learning_rate': 0.00024171125343595867, 'epoch': 6.3}

 53%|█████▎    | 14749/28080 [29:08:53<26:12:13,  7.08s/it]
 53%|█████▎    | 14750/28080 [29:09:00<26:25:01,  7.13s/it]
                                                           
{'loss': 0.6205, 'learning_rate': 0.000241682433636953, 'epoch': 6.3}

 53%|█████▎    | 14750/28080 [29:09:00<26:25:01,  7.13s/it]
 53%|█████▎    | 14751/28080 [29:09:07<26:16:24,  7.10s/it]
                                                           
{'loss': 0.6373, 'learning_rate': 0.000241653613948604, 'epoch': 6.3}

 53%|█████▎    | 14751/28080 [29:09:07<26:16:24,  7.10s/it]
 53%|█████▎    | 14752/28080 [29:09:14<26:21:02,  7.12s/it]
                                                           
{'loss': 0.6202, 'learning_rate': 0.00024162479437129494, 'epoch': 6.3}

 53%|█████▎    | 14752/28080 [29:09:14<26:21:02,  7.12s/it]
 53%|█████▎    | 14753/28080 [29:09:22<26:21:57,  7.12s/it]
                                                           
{'loss': 0.6154, 'learning_rate': 0.00024159597490540954, 'epoch': 6.3}

 53%|█████▎    | 14753/28080 [29:09:22<26:21:57,  7.12s/it]
 53%|█████▎    | 14754/28080 [29:09:29<26:26:28,  7.14s/it]
                                                           
{'loss': 0.6023, 'learning_rate': 0.00024156715555133086, 'epoch': 6.3}

 53%|█████▎    | 14754/28080 [29:09:29<26:26:28,  7.14s/it]
 53%|█████▎    | 14755/28080 [29:09:36<26:27:17,  7.15s/it]
                                                           
{'loss': 0.6, 'learning_rate': 0.00024153833630944255, 'epoch': 6.3}

 53%|█████▎    | 14755/28080 [29:09:36<26:27:17,  7.15s/it]
 53%|█████▎    | 14756/28080 [29:09:43<26:32:52,  7.17s/it]
                                                           
{'loss': 0.6201, 'learning_rate': 0.00024150951718012793, 'epoch': 6.3}

 53%|█████▎    | 14756/28080 [29:09:43<26:32:52,  7.17s/it]
 53%|█████▎    | 14757/28080 [29:09:50<26:33:34,  7.18s/it]
                                                           
{'loss': 0.5913, 'learning_rate': 0.00024148069816377045, 'epoch': 6.3}

 53%|█████▎    | 14757/28080 [29:09:50<26:33:34,  7.18s/it]
 53%|█████▎    | 14758/28080 [29:09:57<26:28:02,  7.15s/it]
                                                           
{'loss': 0.6084, 'learning_rate': 0.00024145187926075346, 'epoch': 6.3}

 53%|█████▎    | 14758/28080 [29:09:57<26:28:02,  7.15s/it]
 53%|█████▎    | 14759/28080 [29:10:04<26:20:08,  7.12s/it]
                                                           
{'loss': 0.6254, 'learning_rate': 0.00024142306047146044, 'epoch': 6.3}

 53%|█████▎    | 14759/28080 [29:10:04<26:20:08,  7.12s/it]
 53%|█████▎    | 14760/28080 [29:10:12<26:20:56,  7.12s/it]
                                                           
{'loss': 0.6242, 'learning_rate': 0.00024139424179627468, 'epoch': 6.31}

 53%|█████▎    | 14760/28080 [29:10:12<26:20:56,  7.12s/it]
 53%|█████▎    | 14761/28080 [29:10:19<26:25:23,  7.14s/it]
                                                           
{'loss': 0.6252, 'learning_rate': 0.00024136542323557972, 'epoch': 6.31}

 53%|█████▎    | 14761/28080 [29:10:19<26:25:23,  7.14s/it]
 53%|█████▎    | 14762/28080 [29:10:26<26:21:09,  7.12s/it]
                                                           
{'loss': 0.6256, 'learning_rate': 0.00024133660478975886, 'epoch': 6.31}

 53%|█████▎    | 14762/28080 [29:10:26<26:21:09,  7.12s/it]
 53%|█████▎    | 14763/28080 [29:10:33<26:30:51,  7.17s/it]
                                                           
{'loss': 0.5962, 'learning_rate': 0.00024130778645919558, 'epoch': 6.31}

 53%|█████▎    | 14763/28080 [29:10:33<26:30:51,  7.17s/it]
 53%|█████▎    | 14764/28080 [29:10:40<26:32:04,  7.17s/it]
                                                           
{'loss': 0.6015, 'learning_rate': 0.0002412789682442731, 'epoch': 6.31}

 53%|█████▎    | 14764/28080 [29:10:40<26:32:04,  7.17s/it]
 53%|█████▎    | 14765/28080 [29:10:47<26:29:56,  7.16s/it]
                                                           
{'loss': 0.6008, 'learning_rate': 0.00024125015014537515, 'epoch': 6.31}

 53%|█████▎    | 14765/28080 [29:10:47<26:29:56,  7.16s/it]
 53%|█████▎    | 14766/28080 [29:10:55<26:21:28,  7.13s/it]
                                                           
{'loss': 0.652, 'learning_rate': 0.00024122133216288478, 'epoch': 6.31}

 53%|█████▎    | 14766/28080 [29:10:55<26:21:28,  7.13s/it]
 53%|█████▎    | 14767/28080 [29:11:02<26:24:58,  7.14s/it]
                                                           
{'loss': 0.6043, 'learning_rate': 0.00024119251429718564, 'epoch': 6.31}

 53%|█████▎    | 14767/28080 [29:11:02<26:24:58,  7.14s/it]
 53%|█████▎    | 14768/28080 [29:11:09<26:15:01,  7.10s/it]
                                                           
{'loss': 0.6363, 'learning_rate': 0.0002411636965486609, 'epoch': 6.31}

 53%|█████▎    | 14768/28080 [29:11:09<26:15:01,  7.10s/it]
 53%|█████▎    | 14769/28080 [29:11:16<26:23:38,  7.14s/it]
                                                           
{'loss': 0.6046, 'learning_rate': 0.00024113487891769413, 'epoch': 6.31}

 53%|█████▎    | 14769/28080 [29:11:16<26:23:38,  7.14s/it]
 53%|█████▎    | 14770/28080 [29:11:23<26:15:08,  7.10s/it]
                                                           
{'loss': 0.6342, 'learning_rate': 0.0002411060614046686, 'epoch': 6.31}

 53%|█████▎    | 14770/28080 [29:11:23<26:15:08,  7.10s/it]
 53%|█████▎    | 14771/28080 [29:11:30<26:22:30,  7.13s/it]
                                                           
{'loss': 0.6192, 'learning_rate': 0.0002410772440099678, 'epoch': 6.31}

 53%|█████▎    | 14771/28080 [29:11:30<26:22:30,  7.13s/it]
 53%|█████▎    | 14772/28080 [29:11:37<26:31:31,  7.18s/it]
                                                           
{'loss': 0.5965, 'learning_rate': 0.00024104842673397503, 'epoch': 6.31}

 53%|█████▎    | 14772/28080 [29:11:37<26:31:31,  7.18s/it]
 53%|█████▎    | 14773/28080 [29:11:45<26:29:49,  7.17s/it]
                                                           
{'loss': 0.5965, 'learning_rate': 0.00024101960957707375, 'epoch': 6.31}

 53%|█████▎    | 14773/28080 [29:11:45<26:29:49,  7.17s/it]
 53%|█████▎    | 14774/28080 [29:11:52<26:31:29,  7.18s/it]
                                                           
{'loss': 0.6, 'learning_rate': 0.00024099079253964728, 'epoch': 6.31}

 53%|█████▎    | 14774/28080 [29:11:52<26:31:29,  7.18s/it]
 53%|█████▎    | 14775/28080 [29:11:59<26:31:01,  7.17s/it]
                                                           
{'loss': 0.6067, 'learning_rate': 0.000240961975622079, 'epoch': 6.31}

 53%|█████▎    | 14775/28080 [29:11:59<26:31:01,  7.17s/it]
 53%|█████▎    | 14776/28080 [29:12:06<26:29:22,  7.17s/it]
                                                           
{'loss': 0.611, 'learning_rate': 0.00024093315882475237, 'epoch': 6.31}

 53%|█████▎    | 14776/28080 [29:12:06<26:29:22,  7.17s/it]
 53%|█████▎    | 14777/28080 [29:12:13<26:24:55,  7.15s/it]
                                                           
{'loss': 0.611, 'learning_rate': 0.00024090434214805062, 'epoch': 6.31}

 53%|█████▎    | 14777/28080 [29:12:13<26:24:55,  7.15s/it]
 53%|█████▎    | 14778/28080 [29:12:20<26:16:38,  7.11s/it]
                                                           
{'loss': 0.6169, 'learning_rate': 0.00024087552559235728, 'epoch': 6.31}

 53%|█████▎    | 14778/28080 [29:12:20<26:16:38,  7.11s/it]
 53%|█████▎    | 14779/28080 [29:12:27<26:11:58,  7.09s/it]
                                                           
{'loss': 0.5986, 'learning_rate': 0.00024084670915805562, 'epoch': 6.31}

 53%|█████▎    | 14779/28080 [29:12:27<26:11:58,  7.09s/it]
 53%|█████▎    | 14780/28080 [29:12:34<26:16:03,  7.11s/it]
                                                           
{'loss': 0.6176, 'learning_rate': 0.00024081789284552909, 'epoch': 6.31}

 53%|█████▎    | 14780/28080 [29:12:34<26:16:03,  7.11s/it]
 53%|█████▎    | 14781/28080 [29:12:41<26:13:52,  7.10s/it]
                                                           
{'loss': 0.6287, 'learning_rate': 0.00024078907665516097, 'epoch': 6.31}

 53%|█████▎    | 14781/28080 [29:12:41<26:13:52,  7.10s/it]
 53%|█████▎    | 14782/28080 [29:12:49<26:16:00,  7.11s/it]
                                                           
{'loss': 0.6061, 'learning_rate': 0.00024076026058733474, 'epoch': 6.31}

 53%|█████▎    | 14782/28080 [29:12:49<26:16:00,  7.11s/it]
 53%|█████▎    | 14783/28080 [29:12:56<26:18:00,  7.12s/it]
                                                           
{'loss': 0.6081, 'learning_rate': 0.0002407314446424336, 'epoch': 6.32}

 53%|█████▎    | 14783/28080 [29:12:56<26:18:00,  7.12s/it]
 53%|█████▎    | 14784/28080 [29:13:03<26:23:38,  7.15s/it]
                                                           
{'loss': 0.6066, 'learning_rate': 0.0002407026288208412, 'epoch': 6.32}

 53%|█████▎    | 14784/28080 [29:13:03<26:23:38,  7.15s/it]
 53%|█████▎    | 14785/28080 [29:13:10<26:23:55,  7.15s/it]
                                                           
{'loss': 0.638, 'learning_rate': 0.00024067381312294057, 'epoch': 6.32}

 53%|█████▎    | 14785/28080 [29:13:10<26:23:55,  7.15s/it]
 53%|█████▎    | 14786/28080 [29:13:17<26:14:35,  7.11s/it]
                                                           
{'loss': 0.6072, 'learning_rate': 0.00024064499754911531, 'epoch': 6.32}

 53%|█████▎    | 14786/28080 [29:13:17<26:14:35,  7.11s/it]
 53%|█████▎    | 14787/28080 [29:13:24<26:12:12,  7.10s/it]
                                                           
{'loss': 0.6081, 'learning_rate': 0.0002406161820997487, 'epoch': 6.32}

 53%|█████▎    | 14787/28080 [29:13:24<26:12:12,  7.10s/it]
 53%|█████▎    | 14788/28080 [29:13:31<26:14:35,  7.11s/it]
                                                           
{'loss': 0.6221, 'learning_rate': 0.00024058736677522413, 'epoch': 6.32}

 53%|█████▎    | 14788/28080 [29:13:31<26:14:35,  7.11s/it]
 53%|█████▎    | 14789/28080 [29:13:38<26:12:22,  7.10s/it]
                                                           
{'loss': 0.6203, 'learning_rate': 0.0002405585515759249, 'epoch': 6.32}

 53%|█████▎    | 14789/28080 [29:13:38<26:12:22,  7.10s/it]
 53%|█████▎    | 14790/28080 [29:13:46<26:19:55,  7.13s/it]
                                                           
{'loss': 0.6395, 'learning_rate': 0.00024052973650223443, 'epoch': 6.32}

 53%|█████▎    | 14790/28080 [29:13:46<26:19:55,  7.13s/it]
 53%|█████▎    | 14791/28080 [29:13:53<26:16:12,  7.12s/it]
                                                           
{'loss': 0.6072, 'learning_rate': 0.00024050092155453602, 'epoch': 6.32}

 53%|█████▎    | 14791/28080 [29:13:53<26:16:12,  7.12s/it]
 53%|█████▎    | 14792/28080 [29:14:00<26:20:15,  7.14s/it]
                                                           
{'loss': 0.6091, 'learning_rate': 0.00024047210673321307, 'epoch': 6.32}

 53%|█████▎    | 14792/28080 [29:14:00<26:20:15,  7.14s/it]
 53%|█████▎    | 14793/28080 [29:14:07<26:19:33,  7.13s/it]
                                                           
{'loss': 0.6271, 'learning_rate': 0.00024044329203864887, 'epoch': 6.32}

 53%|█████▎    | 14793/28080 [29:14:07<26:19:33,  7.13s/it]
 53%|█████▎    | 14794/28080 [29:14:14<26:09:20,  7.09s/it]
                                                           
{'loss': 0.6346, 'learning_rate': 0.00024041447747122688, 'epoch': 6.32}

 53%|█████▎    | 14794/28080 [29:14:14<26:09:20,  7.09s/it]
 53%|█████▎    | 14795/28080 [29:14:21<26:13:01,  7.10s/it]
                                                           
{'loss': 0.6084, 'learning_rate': 0.00024038566303133025, 'epoch': 6.32}

 53%|█████▎    | 14795/28080 [29:14:21<26:13:01,  7.10s/it]
 53%|█████▎    | 14796/28080 [29:14:28<26:18:56,  7.13s/it]
                                                           
{'loss': 0.5935, 'learning_rate': 0.00024035684871934264, 'epoch': 6.32}

 53%|█████▎    | 14796/28080 [29:14:28<26:18:56,  7.13s/it]
 53%|█████▎    | 14797/28080 [29:14:35<26:17:54,  7.13s/it]
                                                           
{'loss': 0.6052, 'learning_rate': 0.00024032803453564704, 'epoch': 6.32}

 53%|█████▎    | 14797/28080 [29:14:35<26:17:54,  7.13s/it]
 53%|█████▎    | 14798/28080 [29:14:43<26:18:23,  7.13s/it]
                                                           
{'loss': 0.6404, 'learning_rate': 0.0002402992204806271, 'epoch': 6.32}

 53%|█████▎    | 14798/28080 [29:14:43<26:18:23,  7.13s/it]
 53%|█████▎    | 14799/28080 [29:14:50<26:19:39,  7.14s/it]
                                                           
{'loss': 0.622, 'learning_rate': 0.000240270406554666, 'epoch': 6.32}

 53%|█████▎    | 14799/28080 [29:14:50<26:19:39,  7.14s/it]
 53%|█████▎    | 14800/28080 [29:14:57<26:19:11,  7.13s/it]
                                                           
{'loss': 0.6158, 'learning_rate': 0.00024024159275814696, 'epoch': 6.32}

 53%|█████▎    | 14800/28080 [29:14:57<26:19:11,  7.13s/it]
 53%|█████▎    | 14801/28080 [29:15:04<26:16:18,  7.12s/it]
                                                           
{'loss': 0.6156, 'learning_rate': 0.00024021277909145366, 'epoch': 6.32}

 53%|█████▎    | 14801/28080 [29:15:04<26:16:18,  7.12s/it]
 53%|█████▎    | 14802/28080 [29:15:11<26:17:14,  7.13s/it]
                                                           
{'loss': 0.5912, 'learning_rate': 0.00024018396555496908, 'epoch': 6.32}

 53%|█████▎    | 14802/28080 [29:15:11<26:17:14,  7.13s/it]
 53%|█████▎    | 14803/28080 [29:15:18<26:14:10,  7.11s/it]
                                                           
{'loss': 0.6249, 'learning_rate': 0.0002401551521490768, 'epoch': 6.32}

 53%|█████▎    | 14803/28080 [29:15:18<26:14:10,  7.11s/it]
 53%|█████▎    | 14804/28080 [29:15:25<26:08:39,  7.09s/it]
                                                           
{'loss': 0.6407, 'learning_rate': 0.00024012633887416, 'epoch': 6.32}

 53%|█████▎    | 14804/28080 [29:15:25<26:08:39,  7.09s/it]
 53%|█████▎    | 14805/28080 [29:15:32<26:12:43,  7.11s/it]
                                                           
{'loss': 0.6447, 'learning_rate': 0.00024009752573060213, 'epoch': 6.32}

 53%|█████▎    | 14805/28080 [29:15:32<26:12:43,  7.11s/it]
 53%|█████▎    | 14806/28080 [29:15:40<26:14:40,  7.12s/it]
                                                           
{'loss': 0.5992, 'learning_rate': 0.00024006871271878643, 'epoch': 6.32}

 53%|█████▎    | 14806/28080 [29:15:40<26:14:40,  7.12s/it]
 53%|█████▎    | 14807/28080 [29:15:47<26:16:16,  7.13s/it]
                                                           
{'loss': 0.6092, 'learning_rate': 0.00024003989983909633, 'epoch': 6.33}

 53%|█████▎    | 14807/28080 [29:15:47<26:16:16,  7.13s/it]
 53%|█████▎    | 14808/28080 [29:15:54<26:15:06,  7.12s/it]
                                                           
{'loss': 0.6106, 'learning_rate': 0.000240011087091915, 'epoch': 6.33}

 53%|█████▎    | 14808/28080 [29:15:54<26:15:06,  7.12s/it]
 53%|█████▎    | 14809/28080 [29:16:01<26:10:33,  7.10s/it]
                                                           
{'loss': 0.5912, 'learning_rate': 0.00023998227447762592, 'epoch': 6.33}

 53%|█████▎    | 14809/28080 [29:16:01<26:10:33,  7.10s/it]
 53%|█████▎    | 14810/28080 [29:16:08<26:07:35,  7.09s/it]
                                                           
{'loss': 0.631, 'learning_rate': 0.00023995346199661227, 'epoch': 6.33}

 53%|█████▎    | 14810/28080 [29:16:08<26:07:35,  7.09s/it]
 53%|█████▎    | 14811/28080 [29:16:15<26:08:09,  7.09s/it]
                                                           
{'loss': 0.6127, 'learning_rate': 0.00023992464964925754, 'epoch': 6.33}

 53%|█████▎    | 14811/28080 [29:16:15<26:08:09,  7.09s/it]
 53%|█████▎    | 14812/28080 [29:16:22<26:11:03,  7.10s/it]
                                                           
{'loss': 0.6062, 'learning_rate': 0.00023989583743594484, 'epoch': 6.33}

 53%|█████▎    | 14812/28080 [29:16:22<26:11:03,  7.10s/it]
 53%|█████▎    | 14813/28080 [29:16:29<26:08:40,  7.09s/it]
                                                           
{'loss': 0.6261, 'learning_rate': 0.0002398670253570577, 'epoch': 6.33}

 53%|█████▎    | 14813/28080 [29:16:29<26:08:40,  7.09s/it]
 53%|█████▎    | 14814/28080 [29:16:36<26:11:34,  7.11s/it]
                                                           
{'loss': 0.5926, 'learning_rate': 0.0002398382134129792, 'epoch': 6.33}

 53%|█████▎    | 14814/28080 [29:16:36<26:11:34,  7.11s/it]
 53%|█████▎    | 14815/28080 [29:16:43<26:12:16,  7.11s/it]
                                                           
{'loss': 0.6174, 'learning_rate': 0.00023980940160409295, 'epoch': 6.33}

 53%|█████▎    | 14815/28080 [29:16:43<26:12:16,  7.11s/it]
 53%|█████▎    | 14816/28080 [29:16:51<26:14:37,  7.12s/it]
                                                           
{'loss': 0.6101, 'learning_rate': 0.00023978058993078194, 'epoch': 6.33}

 53%|█████▎    | 14816/28080 [29:16:51<26:14:37,  7.12s/it]
 53%|█████▎    | 14817/28080 [29:16:58<26:15:47,  7.13s/it]
                                                           
{'loss': 0.6026, 'learning_rate': 0.00023975177839342975, 'epoch': 6.33}

 53%|█████▎    | 14817/28080 [29:16:58<26:15:47,  7.13s/it]
 53%|█████▎    | 14818/28080 [29:17:05<26:12:45,  7.12s/it]
                                                           
{'loss': 0.5951, 'learning_rate': 0.00023972296699241956, 'epoch': 6.33}

 53%|█████▎    | 14818/28080 [29:17:05<26:12:45,  7.12s/it]
 53%|█████▎    | 14819/28080 [29:17:12<26:14:51,  7.13s/it]
                                                           
{'loss': 0.6103, 'learning_rate': 0.0002396941557281347, 'epoch': 6.33}

 53%|█████▎    | 14819/28080 [29:17:12<26:14:51,  7.13s/it]
 53%|█████▎    | 14820/28080 [29:17:19<26:13:24,  7.12s/it]
                                                           
{'loss': 0.6182, 'learning_rate': 0.00023966534460095844, 'epoch': 6.33}

 53%|█████▎    | 14820/28080 [29:17:19<26:13:24,  7.12s/it]
 53%|█████▎    | 14821/28080 [29:17:26<26:13:00,  7.12s/it]
                                                           
{'loss': 0.5928, 'learning_rate': 0.00023963653361127414, 'epoch': 6.33}

 53%|█████▎    | 14821/28080 [29:17:26<26:13:00,  7.12s/it]
 53%|█████▎    | 14822/28080 [29:17:33<26:14:35,  7.13s/it]
                                                           
{'loss': 0.6042, 'learning_rate': 0.000239607722759465, 'epoch': 6.33}

 53%|█████▎    | 14822/28080 [29:17:33<26:14:35,  7.13s/it]
 53%|█████▎    | 14823/28080 [29:17:40<26:13:06,  7.12s/it]
                                                           
{'loss': 0.6206, 'learning_rate': 0.0002395789120459145, 'epoch': 6.33}

 53%|█████▎    | 14823/28080 [29:17:40<26:13:06,  7.12s/it]
 53%|█████▎    | 14824/28080 [29:17:48<26:16:46,  7.14s/it]
                                                           
{'loss': 0.6013, 'learning_rate': 0.00023955010147100575, 'epoch': 6.33}

 53%|█████▎    | 14824/28080 [29:17:48<26:16:46,  7.14s/it]
 53%|█████▎    | 14825/28080 [29:17:55<26:19:19,  7.15s/it]
                                                           
{'loss': 0.6132, 'learning_rate': 0.0002395212910351221, 'epoch': 6.33}

 53%|█████▎    | 14825/28080 [29:17:55<26:19:19,  7.15s/it]
 53%|█████▎    | 14826/28080 [29:18:02<26:20:11,  7.15s/it]
                                                           
{'loss': 0.6236, 'learning_rate': 0.00023949248073864695, 'epoch': 6.33}

 53%|█████▎    | 14826/28080 [29:18:02<26:20:11,  7.15s/it]
 53%|█████▎    | 14827/28080 [29:18:09<26:13:16,  7.12s/it]
                                                           
{'loss': 0.6124, 'learning_rate': 0.0002394636705819634, 'epoch': 6.33}

 53%|█████▎    | 14827/28080 [29:18:09<26:13:16,  7.12s/it]
 53%|█████▎    | 14828/28080 [29:18:16<26:11:49,  7.12s/it]
                                                           
{'loss': 0.6292, 'learning_rate': 0.0002394348605654549, 'epoch': 6.33}

 53%|█████▎    | 14828/28080 [29:18:16<26:11:49,  7.12s/it]
 53%|█████▎    | 14829/28080 [29:18:23<26:11:57,  7.12s/it]
                                                           
{'loss': 0.6137, 'learning_rate': 0.00023940605068950463, 'epoch': 6.33}

 53%|█████▎    | 14829/28080 [29:18:23<26:11:57,  7.12s/it]
 53%|█████▎    | 14830/28080 [29:18:30<26:13:27,  7.13s/it]
                                                           
{'loss': 0.6004, 'learning_rate': 0.000239377240954496, 'epoch': 6.34}

 53%|█████▎    | 14830/28080 [29:18:30<26:13:27,  7.13s/it]
 53%|█████▎    | 14831/28080 [29:18:38<26:16:41,  7.14s/it]
                                                           
{'loss': 0.6233, 'learning_rate': 0.0002393484313608121, 'epoch': 6.34}

 53%|█████▎    | 14831/28080 [29:18:38<26:16:41,  7.14s/it]
 53%|█████▎    | 14832/28080 [29:18:45<26:14:14,  7.13s/it]
                                                           
{'loss': 0.6171, 'learning_rate': 0.00023931962190883648, 'epoch': 6.34}

 53%|█████▎    | 14832/28080 [29:18:45<26:14:14,  7.13s/it]
 53%|█████▎    | 14833/28080 [29:18:52<26:13:32,  7.13s/it]
                                                           
{'loss': 0.604, 'learning_rate': 0.00023929081259895215, 'epoch': 6.34}

 53%|█████▎    | 14833/28080 [29:18:52<26:13:32,  7.13s/it]
 53%|█████▎    | 14834/28080 [29:18:59<26:10:24,  7.11s/it]
                                                           
{'loss': 0.6162, 'learning_rate': 0.0002392620034315426, 'epoch': 6.34}

 53%|█████▎    | 14834/28080 [29:18:59<26:10:24,  7.11s/it]
 53%|█████▎    | 14835/28080 [29:19:06<26:06:57,  7.10s/it]
                                                           
{'loss': 0.635, 'learning_rate': 0.00023923319440699096, 'epoch': 6.34}

 53%|█████▎    | 14835/28080 [29:19:06<26:06:57,  7.10s/it]
 53%|█████▎    | 14836/28080 [29:19:13<26:12:39,  7.12s/it]
                                                           
{'loss': 0.5995, 'learning_rate': 0.0002392043855256806, 'epoch': 6.34}

 53%|█████▎    | 14836/28080 [29:19:13<26:12:39,  7.12s/it]
 53%|█████▎    | 14837/28080 [29:19:20<26:10:38,  7.12s/it]
                                                           
{'loss': 0.6398, 'learning_rate': 0.00023917557678799473, 'epoch': 6.34}

 53%|█████▎    | 14837/28080 [29:19:20<26:10:38,  7.12s/it]
 53%|█████▎    | 14838/28080 [29:19:27<26:10:30,  7.12s/it]
                                                           
{'loss': 0.6132, 'learning_rate': 0.0002391467681943167, 'epoch': 6.34}

 53%|█████▎    | 14838/28080 [29:19:27<26:10:30,  7.12s/it]
 53%|█████▎    | 14839/28080 [29:19:35<26:14:45,  7.14s/it]
                                                           
{'loss': 0.6293, 'learning_rate': 0.0002391179597450296, 'epoch': 6.34}

 53%|█████▎    | 14839/28080 [29:19:35<26:14:45,  7.14s/it]
 53%|█████▎    | 14840/28080 [29:19:42<26:19:00,  7.16s/it]
                                                           
{'loss': 0.6158, 'learning_rate': 0.00023908915144051697, 'epoch': 6.34}

 53%|█████▎    | 14840/28080 [29:19:42<26:19:00,  7.16s/it]
 53%|█████▎    | 14841/28080 [29:19:49<26:19:22,  7.16s/it]
                                                           
{'loss': 0.621, 'learning_rate': 0.0002390603432811618, 'epoch': 6.34}

 53%|█████▎    | 14841/28080 [29:19:49<26:19:22,  7.16s/it]
 53%|█████▎    | 14842/28080 [29:19:56<26:19:55,  7.16s/it]
                                                           
{'loss': 0.6055, 'learning_rate': 0.00023903153526734754, 'epoch': 6.34}

 53%|█████▎    | 14842/28080 [29:19:56<26:19:55,  7.16s/it]
 53%|█████▎    | 14843/28080 [29:20:03<26:05:40,  7.10s/it]
                                                           
{'loss': 0.6207, 'learning_rate': 0.00023900272739945736, 'epoch': 6.34}

 53%|█████▎    | 14843/28080 [29:20:03<26:05:40,  7.10s/it]
 53%|█████▎    | 14844/28080 [29:20:10<26:09:26,  7.11s/it]
                                                           
{'loss': 0.6329, 'learning_rate': 0.0002389739196778746, 'epoch': 6.34}

 53%|█████▎    | 14844/28080 [29:20:10<26:09:26,  7.11s/it]
 53%|█████▎    | 14845/28080 [29:20:17<26:14:14,  7.14s/it]
                                                           
{'loss': 0.6078, 'learning_rate': 0.00023894511210298234, 'epoch': 6.34}

 53%|█████▎    | 14845/28080 [29:20:17<26:14:14,  7.14s/it]
 53%|█████▎    | 14846/28080 [29:20:24<26:10:24,  7.12s/it]
                                                           
{'loss': 0.6173, 'learning_rate': 0.00023891630467516413, 'epoch': 6.34}

 53%|█████▎    | 14846/28080 [29:20:24<26:10:24,  7.12s/it]
 53%|█████▎    | 14847/28080 [29:20:31<26:05:52,  7.10s/it]
                                                           
{'loss': 0.5945, 'learning_rate': 0.00023888749739480285, 'epoch': 6.34}

 53%|█████▎    | 14847/28080 [29:20:31<26:05:52,  7.10s/it]
 53%|█████▎    | 14848/28080 [29:20:39<26:05:18,  7.10s/it]
                                                           
{'loss': 0.6256, 'learning_rate': 0.00023885869026228214, 'epoch': 6.34}

 53%|█████▎    | 14848/28080 [29:20:39<26:05:18,  7.10s/it]
 53%|█████▎    | 14849/28080 [29:20:46<26:06:13,  7.10s/it]
                                                           
{'loss': 0.6221, 'learning_rate': 0.00023882988327798504, 'epoch': 6.34}

 53%|█████▎    | 14849/28080 [29:20:46<26:06:13,  7.10s/it]
 53%|█████▎    | 14850/28080 [29:20:53<26:03:16,  7.09s/it]
                                                           
{'loss': 0.6138, 'learning_rate': 0.0002388010764422947, 'epoch': 6.34}

 53%|█████▎    | 14850/28080 [29:20:53<26:03:16,  7.09s/it]
 53%|█████▎    | 14851/28080 [29:21:00<26:03:55,  7.09s/it]
                                                           
{'loss': 0.6164, 'learning_rate': 0.00023877226975559457, 'epoch': 6.34}

 53%|█████▎    | 14851/28080 [29:21:00<26:03:55,  7.09s/it]
 53%|█████▎    | 14852/28080 [29:21:07<26:01:53,  7.08s/it]
                                                           
{'loss': 0.6141, 'learning_rate': 0.00023874346321826778, 'epoch': 6.34}

 53%|█████▎    | 14852/28080 [29:21:07<26:01:53,  7.08s/it]
 53%|█████▎    | 14853/28080 [29:21:14<26:08:02,  7.11s/it]
                                                           
{'loss': 0.6478, 'learning_rate': 0.00023871465683069764, 'epoch': 6.35}

 53%|█████▎    | 14853/28080 [29:21:14<26:08:02,  7.11s/it]
 53%|█████▎    | 14854/28080 [29:21:21<26:03:35,  7.09s/it]
                                                           
{'loss': 0.6084, 'learning_rate': 0.0002386858505932673, 'epoch': 6.35}

 53%|█████▎    | 14854/28080 [29:21:21<26:03:35,  7.09s/it]
 53%|█████▎    | 14855/28080 [29:21:28<26:03:53,  7.10s/it]
                                                           
{'loss': 0.6083, 'learning_rate': 0.00023865704450636008, 'epoch': 6.35}

 53%|█████▎    | 14855/28080 [29:21:28<26:03:53,  7.10s/it]
 53%|█████▎    | 14856/28080 [29:21:35<26:09:34,  7.12s/it]
                                                           
{'loss': 0.6168, 'learning_rate': 0.00023862823857035914, 'epoch': 6.35}

 53%|█████▎    | 14856/28080 [29:21:35<26:09:34,  7.12s/it]
 53%|█████▎    | 14857/28080 [29:21:42<26:06:07,  7.11s/it]
                                                           
{'loss': 0.6443, 'learning_rate': 0.0002385994327856478, 'epoch': 6.35}

 53%|█████▎    | 14857/28080 [29:21:42<26:06:07,  7.11s/it]
 53%|█████▎    | 14858/28080 [29:21:49<25:56:51,  7.06s/it]
                                                           
{'loss': 0.647, 'learning_rate': 0.0002385706271526092, 'epoch': 6.35}

 53%|█████▎    | 14858/28080 [29:21:49<25:56:51,  7.06s/it]
 53%|█████▎    | 14859/28080 [29:21:57<25:58:51,  7.07s/it]
                                                           
{'loss': 0.6329, 'learning_rate': 0.0002385418216716267, 'epoch': 6.35}

 53%|█████▎    | 14859/28080 [29:21:57<25:58:51,  7.07s/it]
 53%|█████▎    | 14860/28080 [29:22:04<26:04:56,  7.10s/it]
                                                           
{'loss': 0.6136, 'learning_rate': 0.00023851301634308334, 'epoch': 6.35}

 53%|█████▎    | 14860/28080 [29:22:04<26:04:56,  7.10s/it]
 53%|█████▎    | 14861/28080 [29:22:11<26:06:16,  7.11s/it]
                                                           
{'loss': 0.6191, 'learning_rate': 0.00023848421116736253, 'epoch': 6.35}

 53%|█████▎    | 14861/28080 [29:22:11<26:06:16,  7.11s/it]
 53%|█████▎    | 14862/28080 [29:22:18<26:11:42,  7.13s/it]
                                                           
{'loss': 0.6221, 'learning_rate': 0.0002384554061448473, 'epoch': 6.35}

 53%|█████▎    | 14862/28080 [29:22:18<26:11:42,  7.13s/it]
 53%|█████▎    | 14863/28080 [29:22:25<26:15:45,  7.15s/it]
                                                           
{'loss': 0.6194, 'learning_rate': 0.0002384266012759211, 'epoch': 6.35}

 53%|█████▎    | 14863/28080 [29:22:25<26:15:45,  7.15s/it]
 53%|█████▎    | 14864/28080 [29:22:32<26:12:15,  7.14s/it]
                                                           
{'loss': 0.6184, 'learning_rate': 0.0002383977965609669, 'epoch': 6.35}

 53%|█████▎    | 14864/28080 [29:22:32<26:12:15,  7.14s/it]
 53%|█████▎    | 14865/28080 [29:22:39<26:12:07,  7.14s/it]
                                                           
{'loss': 0.6357, 'learning_rate': 0.00023836899200036817, 'epoch': 6.35}

 53%|█████▎    | 14865/28080 [29:22:39<26:12:07,  7.14s/it]
 53%|█████▎    | 14866/28080 [29:22:47<26:07:08,  7.12s/it]
                                                           
{'loss': 0.6371, 'learning_rate': 0.00023834018759450793, 'epoch': 6.35}

 53%|█████▎    | 14866/28080 [29:22:47<26:07:08,  7.12s/it]
 53%|█████▎    | 14867/28080 [29:22:54<26:08:50,  7.12s/it]
                                                           
{'loss': 0.6147, 'learning_rate': 0.00023831138334376954, 'epoch': 6.35}

 53%|█████▎    | 14867/28080 [29:22:54<26:08:50,  7.12s/it]
 53%|█████▎    | 14868/28080 [29:23:01<26:01:02,  7.09s/it]
                                                           
{'loss': 0.6039, 'learning_rate': 0.00023828257924853605, 'epoch': 6.35}

 53%|█████▎    | 14868/28080 [29:23:01<26:01:02,  7.09s/it]
 53%|█████▎    | 14869/28080 [29:23:08<26:02:37,  7.10s/it]
                                                           
{'loss': 0.6276, 'learning_rate': 0.00023825377530919083, 'epoch': 6.35}

 53%|█████▎    | 14869/28080 [29:23:08<26:02:37,  7.10s/it]
 53%|█████▎    | 14870/28080 [29:23:15<26:12:25,  7.14s/it]
                                                           
{'loss': 0.6397, 'learning_rate': 0.00023822497152611695, 'epoch': 6.35}

 53%|█████▎    | 14870/28080 [29:23:15<26:12:25,  7.14s/it]
 53%|█████▎    | 14871/28080 [29:23:22<26:09:27,  7.13s/it]
                                                           
{'loss': 0.6265, 'learning_rate': 0.00023819616789969773, 'epoch': 6.35}

 53%|█████▎    | 14871/28080 [29:23:22<26:09:27,  7.13s/it]
 53%|█████▎    | 14872/28080 [29:23:29<26:07:59,  7.12s/it]
                                                           
{'loss': 0.615, 'learning_rate': 0.00023816736443031629, 'epoch': 6.35}

 53%|█████▎    | 14872/28080 [29:23:29<26:07:59,  7.12s/it]
 53%|█████▎    | 14873/28080 [29:23:36<26:09:44,  7.13s/it]
                                                           
{'loss': 0.6293, 'learning_rate': 0.0002381385611183559, 'epoch': 6.35}

 53%|█████▎    | 14873/28080 [29:23:36<26:09:44,  7.13s/it]
 53%|█████▎    | 14874/28080 [29:23:44<26:08:00,  7.12s/it]
                                                           
{'loss': 0.6123, 'learning_rate': 0.00023810975796419967, 'epoch': 6.35}

 53%|█████▎    | 14874/28080 [29:23:44<26:08:00,  7.12s/it]
 53%|█████▎    | 14875/28080 [29:23:51<26:06:55,  7.12s/it]
                                                           
{'loss': 0.5788, 'learning_rate': 0.00023808095496823085, 'epoch': 6.35}

 53%|█████▎    | 14875/28080 [29:23:51<26:06:55,  7.12s/it]
 53%|█████▎    | 14876/28080 [29:23:58<26:08:27,  7.13s/it]
                                                           
{'loss': 0.5957, 'learning_rate': 0.00023805215213083263, 'epoch': 6.35}

 53%|█████▎    | 14876/28080 [29:23:58<26:08:27,  7.13s/it]
 53%|█████▎    | 14877/28080 [29:24:05<26:05:31,  7.11s/it]
                                                           
{'loss': 0.6146, 'learning_rate': 0.00023802334945238822, 'epoch': 6.36}

 53%|█████▎    | 14877/28080 [29:24:05<26:05:31,  7.11s/it]
 53%|█████▎    | 14878/28080 [29:24:12<26:10:40,  7.14s/it]
                                                           
{'loss': 0.5993, 'learning_rate': 0.00023799454693328078, 'epoch': 6.36}

 53%|█████▎    | 14878/28080 [29:24:12<26:10:40,  7.14s/it]
 53%|█████▎    | 14879/28080 [29:24:19<26:10:38,  7.14s/it]
                                                           
{'loss': 0.6201, 'learning_rate': 0.00023796574457389343, 'epoch': 6.36}

 53%|█████▎    | 14879/28080 [29:24:19<26:10:38,  7.14s/it]
 53%|█████▎    | 14880/28080 [29:24:26<26:17:05,  7.17s/it]
                                                           
{'loss': 0.6053, 'learning_rate': 0.0002379369423746096, 'epoch': 6.36}

 53%|█████▎    | 14880/28080 [29:24:26<26:17:05,  7.17s/it]
 53%|█████▎    | 14881/28080 [29:24:34<26:13:18,  7.15s/it]
                                                           
{'loss': 0.6041, 'learning_rate': 0.0002379081403358121, 'epoch': 6.36}

 53%|█████▎    | 14881/28080 [29:24:34<26:13:18,  7.15s/it]
 53%|█████▎    | 14882/28080 [29:24:41<26:08:48,  7.13s/it]
                                                           
{'loss': 0.6134, 'learning_rate': 0.00023787933845788444, 'epoch': 6.36}

 53%|█████▎    | 14882/28080 [29:24:41<26:08:48,  7.13s/it]
 53%|█████▎    | 14883/28080 [29:24:48<26:05:12,  7.12s/it]
                                                           
{'loss': 0.6244, 'learning_rate': 0.00023785053674120965, 'epoch': 6.36}

 53%|█████▎    | 14883/28080 [29:24:48<26:05:12,  7.12s/it]
 53%|█████▎    | 14884/28080 [29:24:55<26:00:07,  7.09s/it]
                                                           
{'loss': 0.619, 'learning_rate': 0.00023782173518617101, 'epoch': 6.36}

 53%|█████▎    | 14884/28080 [29:24:55<26:00:07,  7.09s/it]
 53%|█████▎    | 14885/28080 [29:25:02<26:02:33,  7.11s/it]
                                                           
{'loss': 0.6022, 'learning_rate': 0.00023779293379315152, 'epoch': 6.36}

 53%|█████▎    | 14885/28080 [29:25:02<26:02:33,  7.11s/it]
 53%|█████▎    | 14886/28080 [29:25:09<26:07:18,  7.13s/it]
                                                           
{'loss': 0.6125, 'learning_rate': 0.00023776413256253453, 'epoch': 6.36}

 53%|█████▎    | 14886/28080 [29:25:09<26:07:18,  7.13s/it]
 53%|█████▎    | 14887/28080 [29:25:16<26:05:32,  7.12s/it]
                                                           
{'loss': 0.6098, 'learning_rate': 0.00023773533149470307, 'epoch': 6.36}

 53%|█████▎    | 14887/28080 [29:25:16<26:05:32,  7.12s/it]
 53%|█████▎    | 14888/28080 [29:25:23<26:12:41,  7.15s/it]
                                                           
{'loss': 0.6079, 'learning_rate': 0.0002377065305900404, 'epoch': 6.36}

 53%|█████▎    | 14888/28080 [29:25:23<26:12:41,  7.15s/it]
 53%|█████▎    | 14889/28080 [29:25:31<26:23:00,  7.20s/it]
                                                           
{'loss': 0.6283, 'learning_rate': 0.00023767772984892966, 'epoch': 6.36}

 53%|█████▎    | 14889/28080 [29:25:31<26:23:00,  7.20s/it]
 53%|█████▎    | 14890/28080 [29:25:38<26:13:24,  7.16s/it]
                                                           
{'loss': 0.6339, 'learning_rate': 0.00023764892927175403, 'epoch': 6.36}

 53%|█████▎    | 14890/28080 [29:25:38<26:13:24,  7.16s/it]
 53%|█████▎    | 14891/28080 [29:25:45<26:23:23,  7.20s/it]
                                                           
{'loss': 0.6102, 'learning_rate': 0.0002376201288588966, 'epoch': 6.36}

 53%|█████▎    | 14891/28080 [29:25:45<26:23:23,  7.20s/it]
 53%|█████▎    | 14892/28080 [29:25:52<26:17:21,  7.18s/it]
                                                           
{'loss': 0.6273, 'learning_rate': 0.00023759132861074064, 'epoch': 6.36}

 53%|█████▎    | 14892/28080 [29:25:52<26:17:21,  7.18s/it]
 53%|█████▎    | 14893/28080 [29:25:59<26:14:39,  7.16s/it]
                                                           
{'loss': 0.6189, 'learning_rate': 0.00023756252852766917, 'epoch': 6.36}

 53%|█████▎    | 14893/28080 [29:25:59<26:14:39,  7.16s/it]
 53%|█████▎    | 14894/28080 [29:26:06<26:14:45,  7.17s/it]
                                                           
{'loss': 0.6204, 'learning_rate': 0.00023753372861006557, 'epoch': 6.36}

 53%|█████▎    | 14894/28080 [29:26:06<26:14:45,  7.17s/it]
 53%|█████▎    | 14895/28080 [29:26:14<26:14:29,  7.16s/it]
                                                           
{'loss': 0.6122, 'learning_rate': 0.00023750492885831265, 'epoch': 6.36}

 53%|█████▎    | 14895/28080 [29:26:14<26:14:29,  7.16s/it]
 53%|█████▎    | 14896/28080 [29:26:21<26:07:44,  7.13s/it]
                                                           
{'loss': 0.6221, 'learning_rate': 0.00023747612927279391, 'epoch': 6.36}

 53%|█████▎    | 14896/28080 [29:26:21<26:07:44,  7.13s/it]
 53%|█████▎    | 14897/28080 [29:26:28<26:14:09,  7.16s/it]
                                                           
{'loss': 0.6107, 'learning_rate': 0.0002374473298538923, 'epoch': 6.36}

 53%|█████▎    | 14897/28080 [29:26:28<26:14:09,  7.16s/it]
 53%|█████▎    | 14898/28080 [29:26:35<26:08:11,  7.14s/it]
                                                           
{'loss': 0.621, 'learning_rate': 0.00023741853060199106, 'epoch': 6.36}

 53%|█████▎    | 14898/28080 [29:26:35<26:08:11,  7.14s/it]
 53%|█████▎    | 14899/28080 [29:26:42<26:06:30,  7.13s/it]
                                                           
{'loss': 0.6167, 'learning_rate': 0.00023738973151747335, 'epoch': 6.36}

 53%|█████▎    | 14899/28080 [29:26:42<26:06:30,  7.13s/it]
 53%|█████▎    | 14900/28080 [29:26:49<26:08:34,  7.14s/it]
                                                           
{'loss': 0.6095, 'learning_rate': 0.0002373609326007221, 'epoch': 6.37}

 53%|█████▎    | 14900/28080 [29:26:49<26:08:34,  7.14s/it]
 53%|█████▎    | 14901/28080 [29:26:57<26:17:49,  7.18s/it]
                                                           
{'loss': 0.6064, 'learning_rate': 0.0002373321338521207, 'epoch': 6.37}

 53%|█████▎    | 14901/28080 [29:26:57<26:17:49,  7.18s/it]
 53%|█████▎    | 14902/28080 [29:27:04<26:14:49,  7.17s/it]
                                                           
{'loss': 0.6166, 'learning_rate': 0.0002373033352720521, 'epoch': 6.37}

 53%|█████▎    | 14902/28080 [29:27:04<26:14:49,  7.17s/it]
 53%|█████▎    | 14903/28080 [29:27:11<26:04:30,  7.12s/it]
                                                           
{'loss': 0.641, 'learning_rate': 0.00023727453686089964, 'epoch': 6.37}

 53%|█████▎    | 14903/28080 [29:27:11<26:04:30,  7.12s/it]
 53%|█████▎    | 14904/28080 [29:27:18<25:56:40,  7.09s/it]
                                                           
{'loss': 0.6361, 'learning_rate': 0.00023724573861904624, 'epoch': 6.37}

 53%|█████▎    | 14904/28080 [29:27:18<25:56:40,  7.09s/it]
 53%|█████▎    | 14905/28080 [29:27:25<25:55:38,  7.08s/it]
                                                           
{'loss': 0.623, 'learning_rate': 0.0002372169405468752, 'epoch': 6.37}

 53%|█████▎    | 14905/28080 [29:27:25<25:55:38,  7.08s/it]
 53%|█████▎    | 14906/28080 [29:27:32<26:02:04,  7.11s/it]
                                                           
{'loss': 0.6028, 'learning_rate': 0.00023718814264476955, 'epoch': 6.37}

 53%|█████▎    | 14906/28080 [29:27:32<26:02:04,  7.11s/it]
 53%|█████▎    | 14907/28080 [29:27:39<26:00:43,  7.11s/it]
                                                           
{'loss': 0.6223, 'learning_rate': 0.00023715934491311247, 'epoch': 6.37}

 53%|█████▎    | 14907/28080 [29:27:39<26:00:43,  7.11s/it]
 53%|█████▎    | 14908/28080 [29:27:46<26:03:56,  7.12s/it]
                                                           
{'loss': 0.6157, 'learning_rate': 0.000237130547352287, 'epoch': 6.37}

 53%|█████▎    | 14908/28080 [29:27:46<26:03:56,  7.12s/it]
 53%|█████▎    | 14909/28080 [29:27:53<25:58:20,  7.10s/it]
                                                           
{'loss': 0.6113, 'learning_rate': 0.00023710174996267638, 'epoch': 6.37}

 53%|█████▎    | 14909/28080 [29:27:53<25:58:20,  7.10s/it]
 53%|█████▎    | 14910/28080 [29:28:00<26:00:55,  7.11s/it]
                                                           
{'loss': 0.6124, 'learning_rate': 0.00023707295274466355, 'epoch': 6.37}

 53%|█████▎    | 14910/28080 [29:28:00<26:00:55,  7.11s/it]
 53%|█████▎    | 14911/28080 [29:28:08<25:58:18,  7.10s/it]
                                                           
{'loss': 0.6267, 'learning_rate': 0.00023704415569863194, 'epoch': 6.37}

 53%|█████▎    | 14911/28080 [29:28:08<25:58:18,  7.10s/it]
 53%|█████▎    | 14912/28080 [29:28:15<25:55:29,  7.09s/it]
                                                           
{'loss': 0.6435, 'learning_rate': 0.0002370153588249643, 'epoch': 6.37}

 53%|█████▎    | 14912/28080 [29:28:15<25:55:29,  7.09s/it]
 53%|█████▎    | 14913/28080 [29:28:22<25:58:19,  7.10s/it]
                                                           
{'loss': 0.6335, 'learning_rate': 0.00023698656212404405, 'epoch': 6.37}

 53%|█████▎    | 14913/28080 [29:28:22<25:58:19,  7.10s/it]
 53%|█████▎    | 14914/28080 [29:28:29<25:52:10,  7.07s/it]
                                                           
{'loss': 0.6161, 'learning_rate': 0.00023695776559625408, 'epoch': 6.37}

 53%|█████▎    | 14914/28080 [29:28:29<25:52:10,  7.07s/it]
 53%|█████▎    | 14915/28080 [29:28:36<25:57:31,  7.10s/it]
                                                           
{'loss': 0.5857, 'learning_rate': 0.00023692896924197763, 'epoch': 6.37}

 53%|█████▎    | 14915/28080 [29:28:36<25:57:31,  7.10s/it]
 53%|█████▎    | 14916/28080 [29:28:43<26:06:24,  7.14s/it]
                                                           
{'loss': 0.605, 'learning_rate': 0.00023690017306159773, 'epoch': 6.37}

 53%|█████▎    | 14916/28080 [29:28:43<26:06:24,  7.14s/it]
 53%|█████▎    | 14917/28080 [29:28:50<26:05:37,  7.14s/it]
                                                           
{'loss': 0.6029, 'learning_rate': 0.00023687137705549752, 'epoch': 6.37}

 53%|█████▎    | 14917/28080 [29:28:50<26:05:37,  7.14s/it]
 53%|█████▎    | 14918/28080 [29:28:57<26:02:47,  7.12s/it]
                                                           
{'loss': 0.6186, 'learning_rate': 0.00023684258122406009, 'epoch': 6.37}

 53%|█████▎    | 14918/28080 [29:28:57<26:02:47,  7.12s/it]
 53%|█████▎    | 14919/28080 [29:29:04<25:59:56,  7.11s/it]
                                                           
{'loss': 0.611, 'learning_rate': 0.00023681378556766858, 'epoch': 6.37}

 53%|█████▎    | 14919/28080 [29:29:04<25:59:56,  7.11s/it]
 53%|█████▎    | 14920/28080 [29:29:11<25:53:29,  7.08s/it]
                                                           
{'loss': 0.6258, 'learning_rate': 0.00023678499008670598, 'epoch': 6.37}

 53%|█████▎    | 14920/28080 [29:29:11<25:53:29,  7.08s/it]
 53%|█████▎    | 14921/28080 [29:29:19<26:00:05,  7.11s/it]
                                                           
{'loss': 0.6022, 'learning_rate': 0.00023675619478155554, 'epoch': 6.37}

 53%|█████▎    | 14921/28080 [29:29:19<26:00:05,  7.11s/it]
 53%|█████▎    | 14922/28080 [29:29:26<26:04:12,  7.13s/it]
                                                           
{'loss': 0.6199, 'learning_rate': 0.0002367273996526002, 'epoch': 6.37}

 53%|█████▎    | 14922/28080 [29:29:26<26:04:12,  7.13s/it]
 53%|█████▎    | 14923/28080 [29:29:33<26:03:57,  7.13s/it]
                                                           
{'loss': 0.6212, 'learning_rate': 0.00023669860470022317, 'epoch': 6.37}

 53%|█████▎    | 14923/28080 [29:29:33<26:03:57,  7.13s/it]
 53%|█████▎    | 14924/28080 [29:29:40<26:07:12,  7.15s/it]
                                                           
{'loss': 0.625, 'learning_rate': 0.00023666980992480746, 'epoch': 6.38}

 53%|█████▎    | 14924/28080 [29:29:40<26:07:12,  7.15s/it]
 53%|█████▎    | 14925/28080 [29:29:47<26:04:58,  7.14s/it]
                                                           
{'loss': 0.6075, 'learning_rate': 0.00023664101532673616, 'epoch': 6.38}

 53%|█████▎    | 14925/28080 [29:29:47<26:04:58,  7.14s/it]
 53%|█████▎    | 14926/28080 [29:29:54<26:04:01,  7.13s/it]
                                                           
{'loss': 0.6305, 'learning_rate': 0.00023661222090639239, 'epoch': 6.38}

 53%|█████▎    | 14926/28080 [29:29:54<26:04:01,  7.13s/it]
 53%|█████▎    | 14927/28080 [29:30:01<25:51:16,  7.08s/it]
                                                           
{'loss': 0.635, 'learning_rate': 0.00023658342666415912, 'epoch': 6.38}

 53%|█████▎    | 14927/28080 [29:30:01<25:51:16,  7.08s/it]
 53%|█████▎    | 14928/28080 [29:30:08<25:49:46,  7.07s/it]
                                                           
{'loss': 0.6101, 'learning_rate': 0.00023655463260041968, 'epoch': 6.38}

 53%|█████▎    | 14928/28080 [29:30:08<25:49:46,  7.07s/it]
 53%|█████▎    | 14929/28080 [29:30:15<25:49:34,  7.07s/it]
                                                           
{'loss': 0.6265, 'learning_rate': 0.0002365258387155568, 'epoch': 6.38}

 53%|█████▎    | 14929/28080 [29:30:15<25:49:34,  7.07s/it]
 53%|█████▎    | 14930/28080 [29:30:23<25:55:16,  7.10s/it]
                                                           
{'loss': 0.6152, 'learning_rate': 0.00023649704500995392, 'epoch': 6.38}

 53%|█████▎    | 14930/28080 [29:30:23<25:55:16,  7.10s/it]
 53%|█████▎    | 14931/28080 [29:30:30<25:58:29,  7.11s/it]
                                                           
{'loss': 0.6252, 'learning_rate': 0.00023646825148399375, 'epoch': 6.38}

 53%|█████▎    | 14931/28080 [29:30:30<25:58:29,  7.11s/it]
 53%|█████▎    | 14932/28080 [29:30:37<25:54:05,  7.09s/it]
                                                           
{'loss': 0.6221, 'learning_rate': 0.00023643945813805965, 'epoch': 6.38}

 53%|█████▎    | 14932/28080 [29:30:37<25:54:05,  7.09s/it]
 53%|█████▎    | 14933/28080 [29:30:44<25:56:14,  7.10s/it]
                                                           
{'loss': 0.6313, 'learning_rate': 0.0002364106649725345, 'epoch': 6.38}

 53%|█████▎    | 14933/28080 [29:30:44<25:56:14,  7.10s/it]
 53%|█████▎    | 14934/28080 [29:30:51<25:57:08,  7.11s/it]
                                                           
{'loss': 0.6067, 'learning_rate': 0.00023638187198780152, 'epoch': 6.38}

 53%|█████▎    | 14934/28080 [29:30:51<25:57:08,  7.11s/it]
 53%|█████▎    | 14935/28080 [29:30:58<26:03:50,  7.14s/it]
                                                           
{'loss': 0.61, 'learning_rate': 0.0002363530791842436, 'epoch': 6.38}

 53%|█████▎    | 14935/28080 [29:30:58<26:03:50,  7.14s/it]
 53%|█████▎    | 14936/28080 [29:31:05<26:04:02,  7.14s/it]
                                                           
{'loss': 0.6129, 'learning_rate': 0.00023632428656224395, 'epoch': 6.38}

 53%|█████▎    | 14936/28080 [29:31:05<26:04:02,  7.14s/it]
 53%|█████▎    | 14937/28080 [29:31:13<26:09:30,  7.17s/it]
                                                           
{'loss': 0.5884, 'learning_rate': 0.0002362954941221855, 'epoch': 6.38}

 53%|█████▎    | 14937/28080 [29:31:13<26:09:30,  7.17s/it]
 53%|█████▎    | 14938/28080 [29:31:20<26:01:54,  7.13s/it]
                                                           
{'loss': 0.6091, 'learning_rate': 0.00023626670186445144, 'epoch': 6.38}

 53%|█████▎    | 14938/28080 [29:31:20<26:01:54,  7.13s/it]
 53%|█████▎    | 14939/28080 [29:31:27<26:02:38,  7.13s/it]
                                                           
{'loss': 0.6018, 'learning_rate': 0.00023623790978942463, 'epoch': 6.38}

 53%|█████▎    | 14939/28080 [29:31:27<26:02:38,  7.13s/it]
 53%|█████▎    | 14940/28080 [29:31:34<26:00:47,  7.13s/it]
                                                           
{'loss': 0.604, 'learning_rate': 0.00023620911789748832, 'epoch': 6.38}

 53%|█████▎    | 14940/28080 [29:31:34<26:00:47,  7.13s/it]
 53%|█████▎    | 14941/28080 [29:31:41<26:06:18,  7.15s/it]
                                                           
{'loss': 0.6009, 'learning_rate': 0.00023618032618902537, 'epoch': 6.38}

 53%|█████▎    | 14941/28080 [29:31:41<26:06:18,  7.15s/it]
 53%|█████▎    | 14942/28080 [29:31:48<26:03:16,  7.14s/it]
                                                           
{'loss': 0.619, 'learning_rate': 0.0002361515346644191, 'epoch': 6.38}

 53%|█████▎    | 14942/28080 [29:31:48<26:03:16,  7.14s/it]
 53%|█████▎    | 14943/28080 [29:31:55<25:59:23,  7.12s/it]
                                                           
{'loss': 0.61, 'learning_rate': 0.0002361227433240522, 'epoch': 6.38}

 53%|█████▎    | 14943/28080 [29:31:55<25:59:23,  7.12s/it]
 53%|█████▎    | 14944/28080 [29:32:02<25:58:22,  7.12s/it]
                                                           
{'loss': 0.6426, 'learning_rate': 0.00023609395216830798, 'epoch': 6.38}

 53%|█████▎    | 14944/28080 [29:32:02<25:58:22,  7.12s/it]
 53%|█████▎    | 14945/28080 [29:32:09<25:55:33,  7.11s/it]
                                                           
{'loss': 0.6197, 'learning_rate': 0.00023606516119756933, 'epoch': 6.38}

 53%|█████▎    | 14945/28080 [29:32:09<25:55:33,  7.11s/it]
 53%|█████▎    | 14946/28080 [29:32:17<26:01:56,  7.14s/it]
                                                           
{'loss': 0.6243, 'learning_rate': 0.00023603637041221939, 'epoch': 6.38}

 53%|█████▎    | 14946/28080 [29:32:17<26:01:56,  7.14s/it]
 53%|█████▎    | 14947/28080 [29:32:24<26:01:17,  7.13s/it]
                                                           
{'loss': 0.6222, 'learning_rate': 0.0002360075798126411, 'epoch': 6.39}

 53%|█████▎    | 14947/28080 [29:32:24<26:01:17,  7.13s/it]
 53%|█████▎    | 14948/28080 [29:32:31<26:01:56,  7.14s/it]
                                                           
{'loss': 0.6291, 'learning_rate': 0.00023597878939921754, 'epoch': 6.39}

 53%|█████▎    | 14948/28080 [29:32:31<26:01:56,  7.14s/it]
 53%|█████▎    | 14949/28080 [29:32:38<26:01:53,  7.14s/it]
                                                           
{'loss': 0.6122, 'learning_rate': 0.00023594999917233176, 'epoch': 6.39}

 53%|█████▎    | 14949/28080 [29:32:38<26:01:53,  7.14s/it]
 53%|█████▎    | 14950/28080 [29:32:45<26:08:23,  7.17s/it]
                                                           
{'loss': 0.5947, 'learning_rate': 0.00023592120913236666, 'epoch': 6.39}

 53%|█████▎    | 14950/28080 [29:32:45<26:08:23,  7.17s/it]
 53%|█████▎    | 14951/28080 [29:32:52<26:06:07,  7.16s/it]
                                                           
{'loss': 0.6286, 'learning_rate': 0.00023589241927970543, 'epoch': 6.39}

 53%|█████▎    | 14951/28080 [29:32:52<26:06:07,  7.16s/it]
 53%|█████▎    | 14952/28080 [29:33:00<26:07:33,  7.16s/it]
                                                           
{'loss': 0.6102, 'learning_rate': 0.00023586362961473093, 'epoch': 6.39}

 53%|█████▎    | 14952/28080 [29:33:00<26:07:33,  7.16s/it]
 53%|█████▎    | 14953/28080 [29:33:07<26:04:36,  7.15s/it]
                                                           
{'loss': 0.6155, 'learning_rate': 0.00023583484013782634, 'epoch': 6.39}

 53%|█████▎    | 14953/28080 [29:33:07<26:04:36,  7.15s/it]
 53%|█████▎    | 14954/28080 [29:33:14<26:07:40,  7.17s/it]
                                                           
{'loss': 0.6074, 'learning_rate': 0.00023580605084937451, 'epoch': 6.39}

 53%|█████▎    | 14954/28080 [29:33:14<26:07:40,  7.17s/it]
 53%|█████▎    | 14955/28080 [29:33:21<26:04:04,  7.15s/it]
                                                           
{'loss': 0.59, 'learning_rate': 0.0002357772617497586, 'epoch': 6.39}

 53%|█████▎    | 14955/28080 [29:33:21<26:04:04,  7.15s/it]
 53%|█████▎    | 14956/28080 [29:33:28<26:00:57,  7.14s/it]
                                                           
{'loss': 0.6261, 'learning_rate': 0.00023574847283936145, 'epoch': 6.39}

 53%|█████▎    | 14956/28080 [29:33:28<26:00:57,  7.14s/it]
 53%|█████▎    | 14957/28080 [29:33:35<25:59:09,  7.13s/it]
                                                           
{'loss': 0.6146, 'learning_rate': 0.00023571968411856628, 'epoch': 6.39}

 53%|█████▎    | 14957/28080 [29:33:35<25:59:09,  7.13s/it]
 53%|█████▎    | 14958/28080 [29:33:43<26:04:45,  7.15s/it]
                                                           
{'loss': 0.6265, 'learning_rate': 0.00023569089558775583, 'epoch': 6.39}

 53%|█████▎    | 14958/28080 [29:33:43<26:04:45,  7.15s/it]
 53%|█████▎    | 14959/28080 [29:33:50<26:07:29,  7.17s/it]
                                                           
{'loss': 0.6155, 'learning_rate': 0.00023566210724731347, 'epoch': 6.39}

 53%|█████▎    | 14959/28080 [29:33:50<26:07:29,  7.17s/it]
 53%|█████▎    | 14960/28080 [29:33:57<26:11:01,  7.18s/it]
                                                           
{'loss': 0.6288, 'learning_rate': 0.00023563331909762176, 'epoch': 6.39}

 53%|█████▎    | 14960/28080 [29:33:57<26:11:01,  7.18s/it]
 53%|█████▎    | 14961/28080 [29:34:04<25:57:05,  7.12s/it]
                                                           
{'loss': 0.6267, 'learning_rate': 0.00023560453113906412, 'epoch': 6.39}

 53%|█████▎    | 14961/28080 [29:34:04<25:57:05,  7.12s/it]
 53%|█████▎    | 14962/28080 [29:34:11<25:53:24,  7.11s/it]
                                                           
{'loss': 0.6124, 'learning_rate': 0.00023557574337202314, 'epoch': 6.39}

 53%|█████▎    | 14962/28080 [29:34:11<25:53:24,  7.11s/it]
 53%|█████▎    | 14963/28080 [29:34:18<25:59:21,  7.13s/it]
                                                           
{'loss': 0.6203, 'learning_rate': 0.00023554695579688215, 'epoch': 6.39}

 53%|█████▎    | 14963/28080 [29:34:18<25:59:21,  7.13s/it]
 53%|█████▎    | 14964/28080 [29:34:25<25:55:44,  7.12s/it]
                                                           
{'loss': 0.6385, 'learning_rate': 0.00023551816841402393, 'epoch': 6.39}

 53%|█████▎    | 14964/28080 [29:34:25<25:55:44,  7.12s/it]
 53%|█████▎    | 14965/28080 [29:34:32<25:47:18,  7.08s/it]
                                                           
{'loss': 0.6504, 'learning_rate': 0.00023548938122383163, 'epoch': 6.39}

 53%|█████▎    | 14965/28080 [29:34:32<25:47:18,  7.08s/it]
 53%|█████▎    | 14966/28080 [29:34:39<25:47:27,  7.08s/it]
                                                           
{'loss': 0.6486, 'learning_rate': 0.00023546059422668806, 'epoch': 6.39}

 53%|█████▎    | 14966/28080 [29:34:39<25:47:27,  7.08s/it]
 53%|█████▎    | 14967/28080 [29:34:46<25:40:40,  7.05s/it]
                                                           
{'loss': 0.637, 'learning_rate': 0.00023543180742297635, 'epoch': 6.39}

 53%|█████▎    | 14967/28080 [29:34:46<25:40:40,  7.05s/it]
 53%|█████▎    | 14968/28080 [29:34:53<25:42:17,  7.06s/it]
                                                           
{'loss': 0.6399, 'learning_rate': 0.00023540302081307934, 'epoch': 6.39}

 53%|█████▎    | 14968/28080 [29:34:53<25:42:17,  7.06s/it]
 53%|█████▎    | 14969/28080 [29:35:00<25:43:19,  7.06s/it]
                                                           
{'loss': 0.6276, 'learning_rate': 0.00023537423439738014, 'epoch': 6.39}

 53%|█████▎    | 14969/28080 [29:35:00<25:43:19,  7.06s/it]
 53%|█████▎    | 14970/28080 [29:35:08<25:44:57,  7.07s/it]
                                                           
{'loss': 0.6112, 'learning_rate': 0.0002353454481762616, 'epoch': 6.4}

 53%|█████▎    | 14970/28080 [29:35:08<25:44:57,  7.07s/it]
 53%|█████▎    | 14971/28080 [29:35:15<25:47:16,  7.08s/it]
                                                           
{'loss': 0.6179, 'learning_rate': 0.00023531666215010683, 'epoch': 6.4}

 53%|█████▎    | 14971/28080 [29:35:15<25:47:16,  7.08s/it]
 53%|█████▎    | 14972/28080 [29:35:22<25:53:01,  7.11s/it]
                                                           
{'loss': 0.6145, 'learning_rate': 0.00023528787631929863, 'epoch': 6.4}

 53%|█████▎    | 14972/28080 [29:35:22<25:53:01,  7.11s/it]
 53%|█████▎    | 14973/28080 [29:35:29<25:53:27,  7.11s/it]
                                                           
{'loss': 0.6095, 'learning_rate': 0.0002352590906842202, 'epoch': 6.4}

 53%|█████▎    | 14973/28080 [29:35:29<25:53:27,  7.11s/it]
 53%|█████▎    | 14974/28080 [29:35:36<25:54:48,  7.12s/it]
                                                           
{'loss': 0.616, 'learning_rate': 0.0002352303052452543, 'epoch': 6.4}

 53%|█████▎    | 14974/28080 [29:35:36<25:54:48,  7.12s/it]
 53%|█████▎    | 14975/28080 [29:35:43<25:56:00,  7.12s/it]
                                                           
{'loss': 0.603, 'learning_rate': 0.00023520152000278382, 'epoch': 6.4}

 53%|█████▎    | 14975/28080 [29:35:43<25:56:00,  7.12s/it]
 53%|█████▎    | 14976/28080 [29:35:50<25:43:34,  7.07s/it]
                                                           
{'loss': 0.6385, 'learning_rate': 0.00023517273495719205, 'epoch': 6.4}

 53%|█████▎    | 14976/28080 [29:35:50<25:43:34,  7.07s/it]
 53%|█████▎    | 14977/28080 [29:35:57<25:51:13,  7.10s/it]
                                                           
{'loss': 0.6299, 'learning_rate': 0.0002351439501088616, 'epoch': 6.4}

 53%|█████▎    | 14977/28080 [29:35:57<25:51:13,  7.10s/it]
 53%|█████▎    | 14978/28080 [29:36:04<25:47:59,  7.09s/it]
                                                           
{'loss': 0.5935, 'learning_rate': 0.00023511516545817569, 'epoch': 6.4}

 53%|█████▎    | 14978/28080 [29:36:04<25:47:59,  7.09s/it]
 53%|█████▎    | 14979/28080 [29:36:12<25:54:18,  7.12s/it]
                                                           
{'loss': 0.6241, 'learning_rate': 0.000235086381005517, 'epoch': 6.4}

 53%|█████▎    | 14979/28080 [29:36:12<25:54:18,  7.12s/it]
 53%|█████▎    | 14980/28080 [29:36:19<26:09:24,  7.19s/it]
                                                           
{'loss': 0.6135, 'learning_rate': 0.00023505759675126873, 'epoch': 6.4}

 53%|█████▎    | 14980/28080 [29:36:19<26:09:24,  7.19s/it]
 53%|█████▎    | 14981/28080 [29:36:26<26:00:58,  7.15s/it]
                                                           
{'loss': 0.6148, 'learning_rate': 0.00023502881269581367, 'epoch': 6.4}

 53%|█████▎    | 14981/28080 [29:36:26<26:00:58,  7.15s/it]
 53%|█████▎    | 14982/28080 [29:36:33<25:59:57,  7.15s/it]
                                                           
{'loss': 0.6118, 'learning_rate': 0.00023500002883953484, 'epoch': 6.4}

 53%|█████▎    | 14982/28080 [29:36:33<25:59:57,  7.15s/it]
 53%|█████▎    | 14983/28080 [29:36:40<25:59:13,  7.14s/it]
                                                           
{'loss': 0.6161, 'learning_rate': 0.00023497124518281513, 'epoch': 6.4}

 53%|█████▎    | 14983/28080 [29:36:40<25:59:13,  7.14s/it]
 53%|█████▎    | 14984/28080 [29:36:47<26:02:50,  7.16s/it]
                                                           
{'loss': 0.5963, 'learning_rate': 0.00023494246172603753, 'epoch': 6.4}

 53%|█████▎    | 14984/28080 [29:36:47<26:02:50,  7.16s/it]
 53%|█████▎    | 14985/28080 [29:36:55<25:59:46,  7.15s/it]
                                                           
{'loss': 0.6111, 'learning_rate': 0.0002349136784695849, 'epoch': 6.4}

 53%|█████▎    | 14985/28080 [29:36:55<25:59:46,  7.15s/it]
 53%|█████▎    | 14986/28080 [29:37:02<26:00:49,  7.15s/it]
                                                           
{'loss': 0.6426, 'learning_rate': 0.00023488489541384028, 'epoch': 6.4}

 53%|█████▎    | 14986/28080 [29:37:02<26:00:49,  7.15s/it]
 53%|█████▎    | 14987/28080 [29:37:09<25:57:21,  7.14s/it]
                                                           
{'loss': 0.628, 'learning_rate': 0.00023485611255918645, 'epoch': 6.4}

 53%|█████▎    | 14987/28080 [29:37:09<25:57:21,  7.14s/it]
 53%|█████▎    | 14988/28080 [29:37:16<25:49:49,  7.10s/it]
                                                           
{'loss': 0.6181, 'learning_rate': 0.0002348273299060065, 'epoch': 6.4}

 53%|█████▎    | 14988/28080 [29:37:16<25:49:49,  7.10s/it]
 53%|█████▎    | 14989/28080 [29:37:23<25:47:42,  7.09s/it]
                                                           
{'loss': 0.6274, 'learning_rate': 0.00023479854745468316, 'epoch': 6.4}

 53%|█████▎    | 14989/28080 [29:37:23<25:47:42,  7.09s/it]
 53%|█████▎    | 14990/28080 [29:37:30<25:54:27,  7.13s/it]
                                                           
{'loss': 0.615, 'learning_rate': 0.0002347697652055996, 'epoch': 6.4}

 53%|█████▎    | 14990/28080 [29:37:30<25:54:27,  7.13s/it]
 53%|█████▎    | 14991/28080 [29:37:37<25:52:35,  7.12s/it]
                                                           
{'loss': 0.6031, 'learning_rate': 0.0002347409831591385, 'epoch': 6.4}

 53%|█████▎    | 14991/28080 [29:37:37<25:52:35,  7.12s/it]
 53%|█████▎    | 14992/28080 [29:37:44<25:51:11,  7.11s/it]
                                                           
{'loss': 0.6153, 'learning_rate': 0.000234712201315683, 'epoch': 6.4}

 53%|█████▎    | 14992/28080 [29:37:44<25:51:11,  7.11s/it]
 53%|█████▎    | 14993/28080 [29:37:52<25:56:00,  7.13s/it]
                                                           
{'loss': 0.6029, 'learning_rate': 0.0002346834196756157, 'epoch': 6.4}

 53%|█████▎    | 14993/28080 [29:37:52<25:56:00,  7.13s/it]
 53%|█████▎    | 14994/28080 [29:37:59<25:54:30,  7.13s/it]
                                                           
{'loss': 0.6162, 'learning_rate': 0.00023465463823931987, 'epoch': 6.41}

 53%|█████▎    | 14994/28080 [29:37:59<25:54:30,  7.13s/it]
 53%|█████▎    | 14995/28080 [29:38:06<25:43:08,  7.08s/it]
                                                           
{'loss': 0.6351, 'learning_rate': 0.00023462585700717814, 'epoch': 6.41}

 53%|█████▎    | 14995/28080 [29:38:06<25:43:08,  7.08s/it]
 53%|█████▎    | 14996/28080 [29:38:13<25:37:44,  7.05s/it]
                                                           
{'loss': 0.6077, 'learning_rate': 0.00023459707597957362, 'epoch': 6.41}

 53%|█████▎    | 14996/28080 [29:38:13<25:37:44,  7.05s/it]
 53%|█████▎    | 14997/28080 [29:38:20<25:45:12,  7.09s/it]
                                                           
{'loss': 0.5924, 'learning_rate': 0.00023456829515688902, 'epoch': 6.41}

 53%|█████▎    | 14997/28080 [29:38:20<25:45:12,  7.09s/it]
 53%|█████▎    | 14998/28080 [29:38:27<25:42:28,  7.07s/it]
                                                           
{'loss': 0.6202, 'learning_rate': 0.0002345395145395074, 'epoch': 6.41}

 53%|█████▎    | 14998/28080 [29:38:27<25:42:28,  7.07s/it]
 53%|█████▎    | 14999/28080 [29:38:34<25:42:34,  7.08s/it]
                                                           
{'loss': 0.615, 'learning_rate': 0.0002345107341278116, 'epoch': 6.41}

 53%|█████▎    | 14999/28080 [29:38:34<25:42:34,  7.08s/it]
 53%|█████▎    | 15000/28080 [29:38:41<25:41:27,  7.07s/it]
                                                           
{'loss': 0.6144, 'learning_rate': 0.00023448195392218444, 'epoch': 6.41}

 53%|█████▎    | 15000/28080 [29:38:41<25:41:27,  7.07s/it]
 53%|█████▎    | 15001/28080 [29:38:48<25:44:12,  7.08s/it]
                                                           
{'loss': 0.6122, 'learning_rate': 0.00023445317392300894, 'epoch': 6.41}

 53%|█████▎    | 15001/28080 [29:38:48<25:44:12,  7.08s/it]
 53%|█████▎    | 15002/28080 [29:38:55<25:45:55,  7.09s/it]
                                                           
{'loss': 0.6156, 'learning_rate': 0.00023442439413066786, 'epoch': 6.41}

 53%|█████▎    | 15002/28080 [29:38:55<25:45:55,  7.09s/it]
 53%|█████▎    | 15003/28080 [29:39:02<25:45:29,  7.09s/it]
                                                           
{'loss': 0.5929, 'learning_rate': 0.0002343956145455442, 'epoch': 6.41}

 53%|█████▎    | 15003/28080 [29:39:02<25:45:29,  7.09s/it]
 53%|█████▎    | 15004/28080 [29:39:09<25:39:54,  7.07s/it]
                                                           
{'loss': 0.6292, 'learning_rate': 0.00023436683516802074, 'epoch': 6.41}

 53%|█████▎    | 15004/28080 [29:39:09<25:39:54,  7.07s/it]
 53%|█████▎    | 15005/28080 [29:39:16<25:45:51,  7.09s/it]
                                                           
{'loss': 0.6266, 'learning_rate': 0.00023433805599848046, 'epoch': 6.41}

 53%|█████▎    | 15005/28080 [29:39:16<25:45:51,  7.09s/it]
 53%|█████▎    | 15006/28080 [29:39:23<25:43:17,  7.08s/it]
                                                           
{'loss': 0.6213, 'learning_rate': 0.00023430927703730606, 'epoch': 6.41}

 53%|█████▎    | 15006/28080 [29:39:23<25:43:17,  7.08s/it]
 53%|█████▎    | 15007/28080 [29:39:31<25:42:16,  7.08s/it]
                                                           
{'loss': 0.6154, 'learning_rate': 0.00023428049828488074, 'epoch': 6.41}

 53%|█████▎    | 15007/28080 [29:39:31<25:42:16,  7.08s/it]
 53%|█████▎    | 15008/28080 [29:39:38<25:53:49,  7.13s/it]
                                                           
{'loss': 0.6051, 'learning_rate': 0.00023425171974158699, 'epoch': 6.41}

 53%|█████▎    | 15008/28080 [29:39:38<25:53:49,  7.13s/it]
 53%|█████▎    | 15009/28080 [29:39:45<25:56:25,  7.14s/it]
                                                           
{'loss': 0.629, 'learning_rate': 0.00023422294140780804, 'epoch': 6.41}

 53%|█████▎    | 15009/28080 [29:39:45<25:56:25,  7.14s/it]
 53%|█████▎    | 15010/28080 [29:39:52<26:00:50,  7.17s/it]
                                                           
{'loss': 0.6286, 'learning_rate': 0.0002341941632839264, 'epoch': 6.41}

 53%|█████▎    | 15010/28080 [29:39:52<26:00:50,  7.17s/it]
 53%|█████▎    | 15011/28080 [29:39:59<25:59:01,  7.16s/it]
                                                           
{'loss': 0.6273, 'learning_rate': 0.00023416538537032522, 'epoch': 6.41}

 53%|█████▎    | 15011/28080 [29:39:59<25:59:01,  7.16s/it]
 53%|█████▎    | 15012/28080 [29:40:06<25:50:47,  7.12s/it]
                                                           
{'loss': 0.6119, 'learning_rate': 0.0002341366076673872, 'epoch': 6.41}

 53%|█████▎    | 15012/28080 [29:40:06<25:50:47,  7.12s/it]
 53%|█████▎    | 15013/28080 [29:40:13<25:50:23,  7.12s/it]
                                                           
{'loss': 0.616, 'learning_rate': 0.0002341078301754953, 'epoch': 6.41}

 53%|█████▎    | 15013/28080 [29:40:13<25:50:23,  7.12s/it]
 53%|█████▎    | 15014/28080 [29:40:21<25:53:43,  7.13s/it]
                                                           
{'loss': 0.6227, 'learning_rate': 0.0002340790528950323, 'epoch': 6.41}

 53%|█████▎    | 15014/28080 [29:40:21<25:53:43,  7.13s/it]
 53%|█████▎    | 15015/28080 [29:40:28<25:53:01,  7.13s/it]
                                                           
{'loss': 0.6209, 'learning_rate': 0.00023405027582638107, 'epoch': 6.41}

 53%|█████▎    | 15015/28080 [29:40:28<25:53:01,  7.13s/it]
 53%|█████▎    | 15016/28080 [29:40:35<25:52:04,  7.13s/it]
                                                           
{'loss': 0.631, 'learning_rate': 0.00023402149896992446, 'epoch': 6.41}

 53%|█████▎    | 15016/28080 [29:40:35<25:52:04,  7.13s/it]
 53%|█████▎    | 15017/28080 [29:40:42<25:53:00,  7.13s/it]
                                                           
{'loss': 0.6216, 'learning_rate': 0.00023399272232604536, 'epoch': 6.42}

 53%|█████▎    | 15017/28080 [29:40:42<25:53:00,  7.13s/it]
 53%|█████▎    | 15018/28080 [29:40:49<25:50:23,  7.12s/it]
                                                           
{'loss': 0.6139, 'learning_rate': 0.00023396394589512653, 'epoch': 6.42}

 53%|█████▎    | 15018/28080 [29:40:49<25:50:23,  7.12s/it]
 53%|█████▎    | 15019/28080 [29:40:56<25:46:41,  7.11s/it]
                                                           
{'loss': 0.6025, 'learning_rate': 0.0002339351696775509, 'epoch': 6.42}

 53%|█████▎    | 15019/28080 [29:40:56<25:46:41,  7.11s/it]
 53%|█████▎    | 15020/28080 [29:41:03<25:50:48,  7.12s/it]
                                                           
{'loss': 0.6002, 'learning_rate': 0.00023390639367370117, 'epoch': 6.42}

 53%|█████▎    | 15020/28080 [29:41:03<25:50:48,  7.12s/it]
 53%|█████▎    | 15021/28080 [29:41:10<25:51:43,  7.13s/it]
                                                           
{'loss': 0.6181, 'learning_rate': 0.00023387761788396045, 'epoch': 6.42}

 53%|█████▎    | 15021/28080 [29:41:10<25:51:43,  7.13s/it]
 53%|█████▎    | 15022/28080 [29:41:18<25:45:58,  7.10s/it]
                                                           
{'loss': 0.6135, 'learning_rate': 0.0002338488423087112, 'epoch': 6.42}

 53%|█████▎    | 15022/28080 [29:41:18<25:45:58,  7.10s/it]
 54%|█████▎    | 15023/28080 [29:41:25<25:41:31,  7.08s/it]
                                                           
{'loss': 0.6294, 'learning_rate': 0.0002338200669483366, 'epoch': 6.42}

 54%|█████▎    | 15023/28080 [29:41:25<25:41:31,  7.08s/it]
 54%|█████▎    | 15024/28080 [29:41:32<25:45:54,  7.10s/it]
                                                           
{'loss': 0.6162, 'learning_rate': 0.0002337912918032193, 'epoch': 6.42}

 54%|█████▎    | 15024/28080 [29:41:32<25:45:54,  7.10s/it]
 54%|█████▎    | 15025/28080 [29:41:39<25:51:56,  7.13s/it]
                                                           
{'loss': 0.5927, 'learning_rate': 0.00023376251687374198, 'epoch': 6.42}

 54%|█████▎    | 15025/28080 [29:41:39<25:51:56,  7.13s/it]
 54%|█████▎    | 15026/28080 [29:41:46<25:51:43,  7.13s/it]
                                                           
{'loss': 0.6426, 'learning_rate': 0.0002337337421602878, 'epoch': 6.42}

 54%|█████▎    | 15026/28080 [29:41:46<25:51:43,  7.13s/it]
 54%|█████▎    | 15027/28080 [29:41:53<25:45:22,  7.10s/it]
                                                           
{'loss': 0.6198, 'learning_rate': 0.00023370496766323925, 'epoch': 6.42}

 54%|█████▎    | 15027/28080 [29:41:53<25:45:22,  7.10s/it]
 54%|█████▎    | 15028/28080 [29:42:00<25:51:38,  7.13s/it]
                                                           
{'loss': 0.6143, 'learning_rate': 0.0002336761933829794, 'epoch': 6.42}

 54%|█████▎    | 15028/28080 [29:42:00<25:51:38,  7.13s/it]
 54%|█████▎    | 15029/28080 [29:42:07<25:52:59,  7.14s/it]
                                                           
{'loss': 0.6295, 'learning_rate': 0.0002336474193198909, 'epoch': 6.42}

 54%|█████▎    | 15029/28080 [29:42:07<25:52:59,  7.14s/it]
 54%|█████▎    | 15030/28080 [29:42:15<25:54:28,  7.15s/it]
                                                           
{'loss': 0.628, 'learning_rate': 0.00023361864547435666, 'epoch': 6.42}

 54%|█████▎    | 15030/28080 [29:42:15<25:54:28,  7.15s/it]
 54%|█████▎    | 15031/28080 [29:42:22<25:50:02,  7.13s/it]
                                                           
{'loss': 0.6085, 'learning_rate': 0.0002335898718467594, 'epoch': 6.42}

 54%|█████▎    | 15031/28080 [29:42:22<25:50:02,  7.13s/it]
 54%|█████▎    | 15032/28080 [29:42:29<25:56:40,  7.16s/it]
                                                           
{'loss': 0.6262, 'learning_rate': 0.000233561098437482, 'epoch': 6.42}

 54%|█████▎    | 15032/28080 [29:42:29<25:56:40,  7.16s/it]
 54%|█████▎    | 15033/28080 [29:42:36<25:52:37,  7.14s/it]
                                                           
{'loss': 0.6132, 'learning_rate': 0.0002335323252469072, 'epoch': 6.42}

 54%|█████▎    | 15033/28080 [29:42:36<25:52:37,  7.14s/it]
 54%|█████▎    | 15034/28080 [29:42:43<25:46:02,  7.11s/it]
                                                           
{'loss': 0.6158, 'learning_rate': 0.0002335035522754179, 'epoch': 6.42}

 54%|█████▎    | 15034/28080 [29:42:43<25:46:02,  7.11s/it]
 54%|█████▎    | 15035/28080 [29:42:50<25:48:41,  7.12s/it]
                                                           
{'loss': 0.6087, 'learning_rate': 0.00023347477952339671, 'epoch': 6.42}

 54%|█████▎    | 15035/28080 [29:42:50<25:48:41,  7.12s/it]
 54%|█████▎    | 15036/28080 [29:42:57<25:46:25,  7.11s/it]
                                                           
{'loss': 0.6312, 'learning_rate': 0.0002334460069912266, 'epoch': 6.42}

 54%|█████▎    | 15036/28080 [29:42:57<25:46:25,  7.11s/it]
 54%|█████▎    | 15037/28080 [29:43:04<25:48:31,  7.12s/it]
                                                           
{'loss': 0.6091, 'learning_rate': 0.00023341723467929022, 'epoch': 6.42}

 54%|█████▎    | 15037/28080 [29:43:04<25:48:31,  7.12s/it]
 54%|█████▎    | 15038/28080 [29:43:12<25:48:43,  7.12s/it]
                                                           
{'loss': 0.5989, 'learning_rate': 0.00023338846258797054, 'epoch': 6.42}

 54%|█████▎    | 15038/28080 [29:43:12<25:48:43,  7.12s/it]
 54%|█████▎    | 15039/28080 [29:43:19<25:55:44,  7.16s/it]
                                                           
{'loss': 0.6078, 'learning_rate': 0.00023335969071765005, 'epoch': 6.42}

 54%|█████▎    | 15039/28080 [29:43:19<25:55:44,  7.16s/it]
 54%|█████▎    | 15040/28080 [29:43:26<25:55:28,  7.16s/it]
                                                           
{'loss': 0.6374, 'learning_rate': 0.00023333091906871194, 'epoch': 6.42}

 54%|█████▎    | 15040/28080 [29:43:26<25:55:28,  7.16s/it]
 54%|█████▎    | 15041/28080 [29:43:33<25:51:51,  7.14s/it]
                                                           
{'loss': 0.6212, 'learning_rate': 0.00023330214764153855, 'epoch': 6.43}

 54%|█████▎    | 15041/28080 [29:43:33<25:51:51,  7.14s/it]
 54%|█████▎    | 15042/28080 [29:43:40<25:50:43,  7.14s/it]
                                                           
{'loss': 0.63, 'learning_rate': 0.00023327337643651297, 'epoch': 6.43}

 54%|█████▎    | 15042/28080 [29:43:40<25:50:43,  7.14s/it]
 54%|█████▎    | 15043/28080 [29:43:47<25:38:21,  7.08s/it]
                                                           
{'loss': 0.6115, 'learning_rate': 0.0002332446054540178, 'epoch': 6.43}

 54%|█████▎    | 15043/28080 [29:43:47<25:38:21,  7.08s/it]
 54%|█████▎    | 15044/28080 [29:43:54<25:36:51,  7.07s/it]
                                                           
{'loss': 0.6032, 'learning_rate': 0.00023321583469443593, 'epoch': 6.43}

 54%|█████▎    | 15044/28080 [29:43:54<25:36:51,  7.07s/it]
 54%|█████▎    | 15045/28080 [29:44:01<25:48:20,  7.13s/it]
                                                           
{'loss': 0.6104, 'learning_rate': 0.00023318706415815003, 'epoch': 6.43}

 54%|█████▎    | 15045/28080 [29:44:01<25:48:20,  7.13s/it]
 54%|█████▎    | 15046/28080 [29:44:09<25:48:42,  7.13s/it]
                                                           
{'loss': 0.6097, 'learning_rate': 0.00023315829384554294, 'epoch': 6.43}

 54%|█████▎    | 15046/28080 [29:44:09<25:48:42,  7.13s/it]
 54%|█████▎    | 15047/28080 [29:44:16<25:48:19,  7.13s/it]
                                                           
{'loss': 0.6196, 'learning_rate': 0.0002331295237569973, 'epoch': 6.43}

 54%|█████▎    | 15047/28080 [29:44:16<25:48:19,  7.13s/it]
 54%|█████▎    | 15048/28080 [29:44:23<25:49:12,  7.13s/it]
                                                           
{'loss': 0.6268, 'learning_rate': 0.000233100753892896, 'epoch': 6.43}

 54%|█████▎    | 15048/28080 [29:44:23<25:49:12,  7.13s/it]
 54%|█████▎    | 15049/28080 [29:44:30<25:50:05,  7.14s/it]
                                                           
{'loss': 0.6271, 'learning_rate': 0.00023307198425362175, 'epoch': 6.43}

 54%|█████▎    | 15049/28080 [29:44:30<25:50:05,  7.14s/it]
 54%|█████▎    | 15050/28080 [29:44:37<25:39:31,  7.09s/it]
                                                           
{'loss': 0.6122, 'learning_rate': 0.00023304321483955722, 'epoch': 6.43}

 54%|█████▎    | 15050/28080 [29:44:37<25:39:31,  7.09s/it]
 54%|█████▎    | 15051/28080 [29:44:44<25:37:23,  7.08s/it]
                                                           
{'loss': 0.6121, 'learning_rate': 0.0002330144456510853, 'epoch': 6.43}

 54%|█████▎    | 15051/28080 [29:44:44<25:37:23,  7.08s/it]
 54%|█████▎    | 15052/28080 [29:44:51<25:38:21,  7.08s/it]
                                                           
{'loss': 0.6427, 'learning_rate': 0.00023298567668858858, 'epoch': 6.43}

 54%|█████▎    | 15052/28080 [29:44:51<25:38:21,  7.08s/it]
 54%|█████▎    | 15053/28080 [29:44:58<25:33:29,  7.06s/it]
                                                           
{'loss': 0.6195, 'learning_rate': 0.00023295690795244994, 'epoch': 6.43}

 54%|█████▎    | 15053/28080 [29:44:58<25:33:29,  7.06s/it]
 54%|█████▎    | 15054/28080 [29:45:05<25:36:13,  7.08s/it]
                                                           
{'loss': 0.621, 'learning_rate': 0.00023292813944305202, 'epoch': 6.43}

 54%|█████▎    | 15054/28080 [29:45:05<25:36:13,  7.08s/it]
 54%|█████▎    | 15055/28080 [29:45:12<25:37:01,  7.08s/it]
                                                           
{'loss': 0.6246, 'learning_rate': 0.0002328993711607776, 'epoch': 6.43}

 54%|█████▎    | 15055/28080 [29:45:12<25:37:01,  7.08s/it]
 54%|█████▎    | 15056/28080 [29:45:19<25:34:11,  7.07s/it]
                                                           
{'loss': 0.6034, 'learning_rate': 0.00023287060310600935, 'epoch': 6.43}

 54%|█████▎    | 15056/28080 [29:45:19<25:34:11,  7.07s/it]
 54%|█████▎    | 15057/28080 [29:45:27<25:39:37,  7.09s/it]
                                                           
{'loss': 0.6237, 'learning_rate': 0.0002328418352791302, 'epoch': 6.43}

 54%|█████▎    | 15057/28080 [29:45:27<25:39:37,  7.09s/it]
 54%|█████▎    | 15058/28080 [29:45:34<25:39:33,  7.09s/it]
                                                           
{'loss': 0.6013, 'learning_rate': 0.00023281306768052254, 'epoch': 6.43}

 54%|█████▎    | 15058/28080 [29:45:34<25:39:33,  7.09s/it]
 54%|█████▎    | 15059/28080 [29:45:41<25:45:11,  7.12s/it]
                                                           
{'loss': 0.6132, 'learning_rate': 0.00023278430031056945, 'epoch': 6.43}

 54%|█████▎    | 15059/28080 [29:45:41<25:45:11,  7.12s/it]
 54%|█████▎    | 15060/28080 [29:45:48<25:46:21,  7.13s/it]
                                                           
{'loss': 0.6292, 'learning_rate': 0.00023275553316965336, 'epoch': 6.43}

 54%|█████▎    | 15060/28080 [29:45:48<25:46:21,  7.13s/it]
 54%|█████▎    | 15061/28080 [29:45:55<25:47:34,  7.13s/it]
                                                           
{'loss': 0.6283, 'learning_rate': 0.00023272676625815723, 'epoch': 6.43}

 54%|█████▎    | 15061/28080 [29:45:55<25:47:34,  7.13s/it]
 54%|█████▎    | 15062/28080 [29:46:02<25:49:52,  7.14s/it]
                                                           
{'loss': 0.6345, 'learning_rate': 0.00023269799957646356, 'epoch': 6.43}

 54%|█████▎    | 15062/28080 [29:46:02<25:49:52,  7.14s/it]
 54%|█████▎    | 15063/28080 [29:46:09<25:50:09,  7.15s/it]
                                                           
{'loss': 0.6161, 'learning_rate': 0.00023266923312495523, 'epoch': 6.43}

 54%|█████▎    | 15063/28080 [29:46:09<25:50:09,  7.15s/it]
 54%|█████▎    | 15064/28080 [29:46:17<25:48:32,  7.14s/it]
                                                           
{'loss': 0.6084, 'learning_rate': 0.0002326404669040148, 'epoch': 6.44}

 54%|█████▎    | 15064/28080 [29:46:17<25:48:32,  7.14s/it]
 54%|█████▎    | 15065/28080 [29:46:24<25:46:30,  7.13s/it]
                                                           
{'loss': 0.6077, 'learning_rate': 0.00023261170091402512, 'epoch': 6.44}

 54%|█████▎    | 15065/28080 [29:46:24<25:46:30,  7.13s/it]
 54%|█████▎    | 15066/28080 [29:46:31<25:44:57,  7.12s/it]
                                                           
{'loss': 0.6214, 'learning_rate': 0.00023258293515536878, 'epoch': 6.44}

 54%|█████▎    | 15066/28080 [29:46:31<25:44:57,  7.12s/it]
 54%|█████▎    | 15067/28080 [29:46:38<25:43:52,  7.12s/it]
                                                           
{'loss': 0.6363, 'learning_rate': 0.00023255416962842854, 'epoch': 6.44}

 54%|█████▎    | 15067/28080 [29:46:38<25:43:52,  7.12s/it]
 54%|█████▎    | 15068/28080 [29:46:45<25:49:05,  7.14s/it]
                                                           
{'loss': 0.6156, 'learning_rate': 0.00023252540433358696, 'epoch': 6.44}

 54%|█████▎    | 15068/28080 [29:46:45<25:49:05,  7.14s/it]
 54%|█████▎    | 15069/28080 [29:46:52<25:51:07,  7.15s/it]
                                                           
{'loss': 0.6293, 'learning_rate': 0.00023249663927122705, 'epoch': 6.44}

 54%|█████▎    | 15069/28080 [29:46:52<25:51:07,  7.15s/it]
 54%|█████▎    | 15070/28080 [29:46:59<25:44:03,  7.12s/it]
                                                           
{'loss': 0.6203, 'learning_rate': 0.0002324678744417311, 'epoch': 6.44}

 54%|█████▎    | 15070/28080 [29:46:59<25:44:03,  7.12s/it]
 54%|█████▎    | 15071/28080 [29:47:07<25:57:00,  7.18s/it]
                                                           
{'loss': 0.6093, 'learning_rate': 0.00023243910984548219, 'epoch': 6.44}

 54%|█████▎    | 15071/28080 [29:47:07<25:57:00,  7.18s/it]
 54%|█████▎    | 15072/28080 [29:47:14<25:52:06,  7.16s/it]
                                                           
{'loss': 0.6183, 'learning_rate': 0.0002324103454828626, 'epoch': 6.44}

 54%|█████▎    | 15072/28080 [29:47:14<25:52:06,  7.16s/it]
 54%|█████▎    | 15073/28080 [29:47:21<25:44:17,  7.12s/it]
                                                           
{'loss': 0.6306, 'learning_rate': 0.00023238158135425535, 'epoch': 6.44}

 54%|█████▎    | 15073/28080 [29:47:21<25:44:17,  7.12s/it]
 54%|█████▎    | 15074/28080 [29:47:28<25:43:27,  7.12s/it]
                                                           
{'loss': 0.6185, 'learning_rate': 0.00023235281746004306, 'epoch': 6.44}

 54%|█████▎    | 15074/28080 [29:47:28<25:43:27,  7.12s/it]
 54%|█████▎    | 15075/28080 [29:47:35<25:48:07,  7.14s/it]
                                                           
{'loss': 0.6146, 'learning_rate': 0.00023232405380060815, 'epoch': 6.44}

 54%|█████▎    | 15075/28080 [29:47:35<25:48:07,  7.14s/it]
 54%|█████▎    | 15076/28080 [29:47:42<25:45:41,  7.13s/it]
                                                           
{'loss': 0.634, 'learning_rate': 0.00023229529037633356, 'epoch': 6.44}

 54%|█████▎    | 15076/28080 [29:47:42<25:45:41,  7.13s/it]
 54%|█████▎    | 15077/28080 [29:47:49<25:42:12,  7.12s/it]
                                                           
{'loss': 0.6268, 'learning_rate': 0.00023226652718760183, 'epoch': 6.44}

 54%|█████▎    | 15077/28080 [29:47:49<25:42:12,  7.12s/it]
 54%|█████▎    | 15078/28080 [29:47:56<25:45:35,  7.13s/it]
                                                           
{'loss': 0.6114, 'learning_rate': 0.00023223776423479572, 'epoch': 6.44}

 54%|█████▎    | 15078/28080 [29:47:56<25:45:35,  7.13s/it]
 54%|█████▎    | 15079/28080 [29:48:04<25:41:20,  7.11s/it]
                                                           
{'loss': 0.6097, 'learning_rate': 0.00023220900151829776, 'epoch': 6.44}

 54%|█████▎    | 15079/28080 [29:48:04<25:41:20,  7.11s/it]
 54%|█████▎    | 15080/28080 [29:48:11<25:36:43,  7.09s/it]
                                                           
{'loss': 0.609, 'learning_rate': 0.00023218023903849076, 'epoch': 6.44}

 54%|█████▎    | 15080/28080 [29:48:11<25:36:43,  7.09s/it]
 54%|█████▎    | 15081/28080 [29:48:18<25:32:28,  7.07s/it]
                                                           
{'loss': 0.6235, 'learning_rate': 0.00023215147679575722, 'epoch': 6.44}

 54%|█████▎    | 15081/28080 [29:48:18<25:32:28,  7.07s/it]
 54%|█████▎    | 15082/28080 [29:48:25<25:41:29,  7.12s/it]
                                                           
{'loss': 0.5934, 'learning_rate': 0.00023212271479047995, 'epoch': 6.44}

 54%|█████▎    | 15082/28080 [29:48:25<25:41:29,  7.12s/it]
 54%|█████▎    | 15083/28080 [29:48:32<25:38:31,  7.10s/it]
                                                           
{'loss': 0.6163, 'learning_rate': 0.00023209395302304143, 'epoch': 6.44}

 54%|█████▎    | 15083/28080 [29:48:32<25:38:31,  7.10s/it]
 54%|█████▎    | 15084/28080 [29:48:39<25:42:48,  7.12s/it]
                                                           
{'loss': 0.6075, 'learning_rate': 0.00023206519149382445, 'epoch': 6.44}

 54%|█████▎    | 15084/28080 [29:48:39<25:42:48,  7.12s/it]
 54%|█████▎    | 15085/28080 [29:48:46<25:38:33,  7.10s/it]
                                                           
{'loss': 0.6276, 'learning_rate': 0.00023203643020321154, 'epoch': 6.44}

 54%|█████▎    | 15085/28080 [29:48:46<25:38:33,  7.10s/it]
 54%|█████▎    | 15086/28080 [29:48:53<25:34:49,  7.09s/it]
                                                           
{'loss': 0.6171, 'learning_rate': 0.00023200766915158546, 'epoch': 6.44}

 54%|█████▎    | 15086/28080 [29:48:53<25:34:49,  7.09s/it]
 54%|█████▎    | 15087/28080 [29:49:00<25:33:28,  7.08s/it]
                                                           
{'loss': 0.6349, 'learning_rate': 0.00023197890833932867, 'epoch': 6.45}

 54%|█████▎    | 15087/28080 [29:49:00<25:33:28,  7.08s/it]
 54%|█████▎    | 15088/28080 [29:49:07<25:38:44,  7.11s/it]
                                                           
{'loss': 0.6209, 'learning_rate': 0.00023195014776682409, 'epoch': 6.45}

 54%|█████▎    | 15088/28080 [29:49:07<25:38:44,  7.11s/it]
 54%|█████▎    | 15089/28080 [29:49:14<25:34:45,  7.09s/it]
                                                           
{'loss': 0.6206, 'learning_rate': 0.000231921387434454, 'epoch': 6.45}

 54%|█████▎    | 15089/28080 [29:49:14<25:34:45,  7.09s/it]
 54%|█████▎    | 15090/28080 [29:49:21<25:33:08,  7.08s/it]
                                                           
{'loss': 0.6397, 'learning_rate': 0.0002318926273426013, 'epoch': 6.45}

 54%|█████▎    | 15090/28080 [29:49:21<25:33:08,  7.08s/it]
 54%|█████▎    | 15091/28080 [29:49:29<25:37:44,  7.10s/it]
                                                           
{'loss': 0.6218, 'learning_rate': 0.00023186386749164846, 'epoch': 6.45}

 54%|█████▎    | 15091/28080 [29:49:29<25:37:44,  7.10s/it]
 54%|█████▎    | 15092/28080 [29:49:36<25:28:43,  7.06s/it]
                                                           
{'loss': 0.6279, 'learning_rate': 0.0002318351078819782, 'epoch': 6.45}

 54%|█████▎    | 15092/28080 [29:49:36<25:28:43,  7.06s/it]
 54%|█████▍    | 15093/28080 [29:49:43<25:32:59,  7.08s/it]
                                                           
{'loss': 0.6019, 'learning_rate': 0.00023180634851397303, 'epoch': 6.45}

 54%|█████▍    | 15093/28080 [29:49:43<25:32:59,  7.08s/it]
 54%|█████▍    | 15094/28080 [29:49:50<25:42:59,  7.13s/it]
                                                           
{'loss': 0.5998, 'learning_rate': 0.0002317775893880157, 'epoch': 6.45}

 54%|█████▍    | 15094/28080 [29:49:50<25:42:59,  7.13s/it]
 54%|█████▍    | 15095/28080 [29:49:57<25:34:51,  7.09s/it]
                                                           
{'loss': 0.6117, 'learning_rate': 0.00023174883050448868, 'epoch': 6.45}

 54%|█████▍    | 15095/28080 [29:49:57<25:34:51,  7.09s/it]
 54%|█████▍    | 15096/28080 [29:50:04<25:41:51,  7.13s/it]
                                                           
{'loss': 0.622, 'learning_rate': 0.0002317200718637747, 'epoch': 6.45}

 54%|█████▍    | 15096/28080 [29:50:04<25:41:51,  7.13s/it]
 54%|█████▍    | 15097/28080 [29:50:11<25:39:16,  7.11s/it]
                                                           
{'loss': 0.6053, 'learning_rate': 0.00023169131346625628, 'epoch': 6.45}

 54%|█████▍    | 15097/28080 [29:50:11<25:39:16,  7.11s/it]
 54%|█████▍    | 15098/28080 [29:50:18<25:41:50,  7.13s/it]
                                                           
{'loss': 0.6225, 'learning_rate': 0.00023166255531231606, 'epoch': 6.45}

 54%|█████▍    | 15098/28080 [29:50:18<25:41:50,  7.13s/it]
 54%|█████▍    | 15099/28080 [29:50:26<25:40:51,  7.12s/it]
                                                           
{'loss': 0.5942, 'learning_rate': 0.00023163379740233662, 'epoch': 6.45}

 54%|█████▍    | 15099/28080 [29:50:26<25:40:51,  7.12s/it]
 54%|█████▍    | 15100/28080 [29:50:33<25:43:10,  7.13s/it]
                                                           
{'loss': 0.6299, 'learning_rate': 0.00023160503973670052, 'epoch': 6.45}

 54%|█████▍    | 15100/28080 [29:50:33<25:43:10,  7.13s/it]
 54%|█████▍    | 15101/28080 [29:50:40<25:41:16,  7.13s/it]
                                                           
{'loss': 0.6103, 'learning_rate': 0.00023157628231579045, 'epoch': 6.45}

 54%|█████▍    | 15101/28080 [29:50:40<25:41:16,  7.13s/it]
 54%|█████▍    | 15102/28080 [29:50:47<25:28:33,  7.07s/it]
                                                           
{'loss': 0.6292, 'learning_rate': 0.00023154752513998886, 'epoch': 6.45}

 54%|█████▍    | 15102/28080 [29:50:47<25:28:33,  7.07s/it]
 54%|█████▍    | 15103/28080 [29:50:54<25:22:37,  7.04s/it]
                                                           
{'loss': 0.6161, 'learning_rate': 0.0002315187682096785, 'epoch': 6.45}

 54%|█████▍    | 15103/28080 [29:50:54<25:22:37,  7.04s/it]
 54%|█████▍    | 15104/28080 [29:51:01<25:23:59,  7.05s/it]
                                                           
{'loss': 0.6129, 'learning_rate': 0.00023149001152524172, 'epoch': 6.45}

 54%|█████▍    | 15104/28080 [29:51:01<25:23:59,  7.05s/it]
 54%|█████▍    | 15105/28080 [29:51:08<25:28:17,  7.07s/it]
                                                           
{'loss': 0.6085, 'learning_rate': 0.00023146125508706142, 'epoch': 6.45}

 54%|█████▍    | 15105/28080 [29:51:08<25:28:17,  7.07s/it]
 54%|█████▍    | 15106/28080 [29:51:15<25:23:36,  7.05s/it]
                                                           
{'loss': 0.6032, 'learning_rate': 0.00023143249889551982, 'epoch': 6.45}

 54%|█████▍    | 15106/28080 [29:51:15<25:23:36,  7.05s/it]
 54%|█████▍    | 15107/28080 [29:51:22<25:29:20,  7.07s/it]
                                                           
{'loss': 0.6019, 'learning_rate': 0.0002314037429509998, 'epoch': 6.45}

 54%|█████▍    | 15107/28080 [29:51:22<25:29:20,  7.07s/it]
 54%|█████▍    | 15108/28080 [29:51:29<25:25:14,  7.05s/it]
                                                           
{'loss': 0.6104, 'learning_rate': 0.00023137498725388372, 'epoch': 6.45}

 54%|█████▍    | 15108/28080 [29:51:29<25:25:14,  7.05s/it]
 54%|█████▍    | 15109/28080 [29:51:36<25:26:45,  7.06s/it]
                                                           
{'loss': 0.6098, 'learning_rate': 0.0002313462318045543, 'epoch': 6.45}

 54%|█████▍    | 15109/28080 [29:51:36<25:26:45,  7.06s/it]
 54%|█████▍    | 15110/28080 [29:51:43<25:31:08,  7.08s/it]
                                                           
{'loss': 0.6047, 'learning_rate': 0.00023131747660339394, 'epoch': 6.45}

 54%|█████▍    | 15110/28080 [29:51:43<25:31:08,  7.08s/it]
 54%|█████▍    | 15111/28080 [29:51:50<25:31:51,  7.09s/it]
                                                           
{'loss': 0.6241, 'learning_rate': 0.00023128872165078534, 'epoch': 6.46}

 54%|█████▍    | 15111/28080 [29:51:50<25:31:51,  7.09s/it]
 54%|█████▍    | 15112/28080 [29:51:57<25:28:53,  7.07s/it]
                                                           
{'loss': 0.6163, 'learning_rate': 0.00023125996694711094, 'epoch': 6.46}

 54%|█████▍    | 15112/28080 [29:51:57<25:28:53,  7.07s/it]
 54%|█████▍    | 15113/28080 [29:52:05<25:36:40,  7.11s/it]
                                                           
{'loss': 0.6224, 'learning_rate': 0.0002312312124927534, 'epoch': 6.46}

 54%|█████▍    | 15113/28080 [29:52:05<25:36:40,  7.11s/it]
 54%|█████▍    | 15114/28080 [29:52:12<25:36:17,  7.11s/it]
                                                           
{'loss': 0.6082, 'learning_rate': 0.0002312024582880952, 'epoch': 6.46}

 54%|█████▍    | 15114/28080 [29:52:12<25:36:17,  7.11s/it]
 54%|█████▍    | 15115/28080 [29:52:19<25:33:49,  7.10s/it]
                                                           
{'loss': 0.6341, 'learning_rate': 0.0002311737043335189, 'epoch': 6.46}

 54%|█████▍    | 15115/28080 [29:52:19<25:33:49,  7.10s/it]
 54%|█████▍    | 15116/28080 [29:52:26<25:32:05,  7.09s/it]
                                                           
{'loss': 0.6115, 'learning_rate': 0.00023114495062940703, 'epoch': 6.46}

 54%|█████▍    | 15116/28080 [29:52:26<25:32:05,  7.09s/it]
 54%|█████▍    | 15117/28080 [29:52:33<25:40:02,  7.13s/it]
                                                           
{'loss': 0.63, 'learning_rate': 0.00023111619717614215, 'epoch': 6.46}

 54%|█████▍    | 15117/28080 [29:52:33<25:40:02,  7.13s/it]
 54%|█████▍    | 15118/28080 [29:52:40<25:42:12,  7.14s/it]
                                                           
{'loss': 0.5999, 'learning_rate': 0.00023108744397410668, 'epoch': 6.46}

 54%|█████▍    | 15118/28080 [29:52:40<25:42:12,  7.14s/it]
 54%|█████▍    | 15119/28080 [29:52:47<25:42:17,  7.14s/it]
                                                           
{'loss': 0.5917, 'learning_rate': 0.00023105869102368345, 'epoch': 6.46}

 54%|█████▍    | 15119/28080 [29:52:47<25:42:17,  7.14s/it]
 54%|█████▍    | 15120/28080 [29:52:54<25:34:08,  7.10s/it]
                                                           
{'loss': 0.6166, 'learning_rate': 0.00023102993832525465, 'epoch': 6.46}

 54%|█████▍    | 15120/28080 [29:52:54<25:34:08,  7.10s/it]
 54%|█████▍    | 15121/28080 [29:53:01<25:32:08,  7.09s/it]
                                                           
{'loss': 0.6116, 'learning_rate': 0.00023100118587920303, 'epoch': 6.46}

 54%|█████▍    | 15121/28080 [29:53:01<25:32:08,  7.09s/it]
 54%|█████▍    | 15122/28080 [29:53:09<25:34:48,  7.11s/it]
                                                           
{'loss': 0.6061, 'learning_rate': 0.00023097243368591096, 'epoch': 6.46}

 54%|█████▍    | 15122/28080 [29:53:09<25:34:48,  7.11s/it]
 54%|█████▍    | 15123/28080 [29:53:16<25:32:45,  7.10s/it]
                                                           
{'loss': 0.6171, 'learning_rate': 0.0002309436817457611, 'epoch': 6.46}

 54%|█████▍    | 15123/28080 [29:53:16<25:32:45,  7.10s/it]
 54%|█████▍    | 15124/28080 [29:53:23<25:36:43,  7.12s/it]
                                                           
{'loss': 0.6066, 'learning_rate': 0.0002309149300591359, 'epoch': 6.46}

 54%|█████▍    | 15124/28080 [29:53:23<25:36:43,  7.12s/it]
 54%|█████▍    | 15125/28080 [29:53:30<25:42:36,  7.14s/it]
                                                           
{'loss': 0.6153, 'learning_rate': 0.0002308861786264178, 'epoch': 6.46}

 54%|█████▍    | 15125/28080 [29:53:30<25:42:36,  7.14s/it]
 54%|█████▍    | 15126/28080 [29:53:37<25:46:55,  7.16s/it]
                                                           
{'loss': 0.6303, 'learning_rate': 0.00023085742744798947, 'epoch': 6.46}

 54%|█████▍    | 15126/28080 [29:53:37<25:46:55,  7.16s/it]
 54%|█████▍    | 15127/28080 [29:53:44<25:42:07,  7.14s/it]
                                                           
{'loss': 0.6399, 'learning_rate': 0.00023082867652423323, 'epoch': 6.46}

 54%|█████▍    | 15127/28080 [29:53:44<25:42:07,  7.14s/it]
 54%|█████▍    | 15128/28080 [29:53:51<25:33:41,  7.10s/it]
                                                           
{'loss': 0.6268, 'learning_rate': 0.0002307999258555317, 'epoch': 6.46}

 54%|█████▍    | 15128/28080 [29:53:51<25:33:41,  7.10s/it]
 54%|█████▍    | 15129/28080 [29:53:58<25:32:11,  7.10s/it]
                                                           
{'loss': 0.6103, 'learning_rate': 0.00023077117544226735, 'epoch': 6.46}

 54%|█████▍    | 15129/28080 [29:53:58<25:32:11,  7.10s/it]
 54%|█████▍    | 15130/28080 [29:54:06<25:30:59,  7.09s/it]
                                                           
{'loss': 0.6118, 'learning_rate': 0.0002307424252848227, 'epoch': 6.46}

 54%|█████▍    | 15130/28080 [29:54:06<25:30:59,  7.09s/it]
 54%|█████▍    | 15131/28080 [29:54:13<25:30:47,  7.09s/it]
                                                           
{'loss': 0.6138, 'learning_rate': 0.00023071367538358018, 'epoch': 6.46}

 54%|█████▍    | 15131/28080 [29:54:13<25:30:47,  7.09s/it]
 54%|█████▍    | 15132/28080 [29:54:20<25:31:06,  7.10s/it]
                                                           
{'loss': 0.6105, 'learning_rate': 0.00023068492573892233, 'epoch': 6.46}

 54%|█████▍    | 15132/28080 [29:54:20<25:31:06,  7.10s/it]
 54%|█████▍    | 15133/28080 [29:54:27<25:27:06,  7.08s/it]
                                                           
{'loss': 0.6427, 'learning_rate': 0.0002306561763512316, 'epoch': 6.46}

 54%|█████▍    | 15133/28080 [29:54:27<25:27:06,  7.08s/it]
 54%|█████▍    | 15134/28080 [29:54:34<25:34:46,  7.11s/it]
                                                           
{'loss': 0.6083, 'learning_rate': 0.00023062742722089054, 'epoch': 6.47}

 54%|█████▍    | 15134/28080 [29:54:34<25:34:46,  7.11s/it]
 54%|█████▍    | 15135/28080 [29:54:41<25:42:50,  7.15s/it]
                                                           
{'loss': 0.6199, 'learning_rate': 0.0002305986783482814, 'epoch': 6.47}

 54%|█████▍    | 15135/28080 [29:54:41<25:42:50,  7.15s/it]
 54%|█████▍    | 15136/28080 [29:54:48<25:39:05,  7.13s/it]
                                                           
{'loss': 0.6303, 'learning_rate': 0.00023056992973378708, 'epoch': 6.47}

 54%|█████▍    | 15136/28080 [29:54:48<25:39:05,  7.13s/it]
 54%|█████▍    | 15137/28080 [29:54:55<25:35:46,  7.12s/it]
                                                           
{'loss': 0.6297, 'learning_rate': 0.0002305411813777896, 'epoch': 6.47}

 54%|█████▍    | 15137/28080 [29:54:55<25:35:46,  7.12s/it]
 54%|█████▍    | 15138/28080 [29:55:03<25:39:41,  7.14s/it]
                                                           
{'loss': 0.6233, 'learning_rate': 0.00023051243328067172, 'epoch': 6.47}

 54%|█████▍    | 15138/28080 [29:55:03<25:39:41,  7.14s/it]
 54%|█████▍    | 15139/28080 [29:55:10<25:41:14,  7.15s/it]
                                                           
{'loss': 0.6238, 'learning_rate': 0.00023048368544281578, 'epoch': 6.47}

 54%|█████▍    | 15139/28080 [29:55:10<25:41:14,  7.15s/it]
 54%|█████▍    | 15140/28080 [29:55:17<25:35:40,  7.12s/it]
                                                           
{'loss': 0.6302, 'learning_rate': 0.0002304549378646043, 'epoch': 6.47}

 54%|█████▍    | 15140/28080 [29:55:17<25:35:40,  7.12s/it]
 54%|█████▍    | 15141/28080 [29:55:24<25:28:42,  7.09s/it]
                                                           
{'loss': 0.608, 'learning_rate': 0.0002304261905464197, 'epoch': 6.47}

 54%|█████▍    | 15141/28080 [29:55:24<25:28:42,  7.09s/it]
 54%|█████▍    | 15142/28080 [29:55:31<25:31:27,  7.10s/it]
                                                           
{'loss': 0.6096, 'learning_rate': 0.00023039744348864443, 'epoch': 6.47}

 54%|█████▍    | 15142/28080 [29:55:31<25:31:27,  7.10s/it]
 54%|█████▍    | 15143/28080 [29:55:38<25:29:21,  7.09s/it]
                                                           
{'loss': 0.6213, 'learning_rate': 0.00023036869669166096, 'epoch': 6.47}

 54%|█████▍    | 15143/28080 [29:55:38<25:29:21,  7.09s/it]
 54%|█████▍    | 15144/28080 [29:55:45<25:33:41,  7.11s/it]
                                                           
{'loss': 0.6365, 'learning_rate': 0.00023033995015585176, 'epoch': 6.47}

 54%|█████▍    | 15144/28080 [29:55:45<25:33:41,  7.11s/it]
 54%|█████▍    | 15145/28080 [29:55:52<25:35:28,  7.12s/it]
                                                           
{'loss': 0.6338, 'learning_rate': 0.00023031120388159918, 'epoch': 6.47}

 54%|█████▍    | 15145/28080 [29:55:52<25:35:28,  7.12s/it]
 54%|█████▍    | 15146/28080 [29:55:59<25:32:28,  7.11s/it]
                                                           
{'loss': 0.6046, 'learning_rate': 0.00023028245786928578, 'epoch': 6.47}

 54%|█████▍    | 15146/28080 [29:55:59<25:32:28,  7.11s/it]
 54%|█████▍    | 15147/28080 [29:56:06<25:25:27,  7.08s/it]
                                                           
{'loss': 0.6234, 'learning_rate': 0.00023025371211929388, 'epoch': 6.47}

 54%|█████▍    | 15147/28080 [29:56:06<25:25:27,  7.08s/it]
 54%|█████▍    | 15148/28080 [29:56:13<25:26:07,  7.08s/it]
                                                           
{'loss': 0.6204, 'learning_rate': 0.00023022496663200603, 'epoch': 6.47}

 54%|█████▍    | 15148/28080 [29:56:13<25:26:07,  7.08s/it]
 54%|█████▍    | 15149/28080 [29:56:21<25:30:06,  7.10s/it]
                                                           
{'loss': 0.6166, 'learning_rate': 0.00023019622140780458, 'epoch': 6.47}

 54%|█████▍    | 15149/28080 [29:56:21<25:30:06,  7.10s/it]
 54%|█████▍    | 15150/28080 [29:56:28<25:28:14,  7.09s/it]
                                                           
{'loss': 0.6133, 'learning_rate': 0.00023016747644707196, 'epoch': 6.47}

 54%|█████▍    | 15150/28080 [29:56:28<25:28:14,  7.09s/it]
 54%|█████▍    | 15151/28080 [29:56:35<25:29:58,  7.10s/it]
                                                           
{'loss': 0.6181, 'learning_rate': 0.00023013873175019062, 'epoch': 6.47}

 54%|█████▍    | 15151/28080 [29:56:35<25:29:58,  7.10s/it]
 54%|█████▍    | 15152/28080 [29:56:42<25:23:56,  7.07s/it]
                                                           
{'loss': 0.6235, 'learning_rate': 0.00023010998731754287, 'epoch': 6.47}

 54%|█████▍    | 15152/28080 [29:56:42<25:23:56,  7.07s/it]
 54%|█████▍    | 15153/28080 [29:56:49<25:25:23,  7.08s/it]
                                                           
{'loss': 0.6223, 'learning_rate': 0.00023008124314951138, 'epoch': 6.47}

 54%|█████▍    | 15153/28080 [29:56:49<25:25:23,  7.08s/it]
 54%|█████▍    | 15154/28080 [29:56:56<25:29:12,  7.10s/it]
                                                           
{'loss': 0.634, 'learning_rate': 0.00023005249924647824, 'epoch': 6.47}

 54%|█████▍    | 15154/28080 [29:56:56<25:29:12,  7.10s/it]
 54%|█████▍    | 15155/28080 [29:57:03<25:37:47,  7.14s/it]
                                                           
{'loss': 0.5998, 'learning_rate': 0.00023002375560882612, 'epoch': 6.47}

 54%|█████▍    | 15155/28080 [29:57:03<25:37:47,  7.14s/it]
 54%|█████▍    | 15156/28080 [29:57:10<25:30:34,  7.11s/it]
                                                           
{'loss': 0.6093, 'learning_rate': 0.00022999501223693728, 'epoch': 6.47}

 54%|█████▍    | 15156/28080 [29:57:10<25:30:34,  7.11s/it]
 54%|█████▍    | 15157/28080 [29:57:17<25:30:02,  7.10s/it]
                                                           
{'loss': 0.5958, 'learning_rate': 0.0002299662691311942, 'epoch': 6.47}

 54%|█████▍    | 15157/28080 [29:57:17<25:30:02,  7.10s/it]
 54%|█████▍    | 15158/28080 [29:57:24<25:29:48,  7.10s/it]
                                                           
{'loss': 0.6145, 'learning_rate': 0.0002299375262919792, 'epoch': 6.48}

 54%|█████▍    | 15158/28080 [29:57:25<25:29:48,  7.10s/it]
 54%|█████▍    | 15159/28080 [29:57:32<25:27:09,  7.09s/it]
                                                           
{'loss': 0.6226, 'learning_rate': 0.00022990878371967476, 'epoch': 6.48}

 54%|█████▍    | 15159/28080 [29:57:32<25:27:09,  7.09s/it]
 54%|█████▍    | 15160/28080 [29:57:39<25:24:14,  7.08s/it]
                                                           
{'loss': 0.5973, 'learning_rate': 0.00022988004141466322, 'epoch': 6.48}

 54%|█████▍    | 15160/28080 [29:57:39<25:24:14,  7.08s/it]
 54%|█████▍    | 15161/28080 [29:57:46<25:31:41,  7.11s/it]
                                                           
{'loss': 0.6234, 'learning_rate': 0.00022985129937732696, 'epoch': 6.48}

 54%|█████▍    | 15161/28080 [29:57:46<25:31:41,  7.11s/it]
 54%|█████▍    | 15162/28080 [29:57:53<25:40:58,  7.16s/it]
                                                           
{'loss': 0.5999, 'learning_rate': 0.00022982255760804835, 'epoch': 6.48}

 54%|█████▍    | 15162/28080 [29:57:53<25:40:58,  7.16s/it]
 54%|█████▍    | 15163/28080 [29:58:00<25:41:10,  7.16s/it]
                                                           
{'loss': 0.6175, 'learning_rate': 0.00022979381610720986, 'epoch': 6.48}

 54%|█████▍    | 15163/28080 [29:58:00<25:41:10,  7.16s/it]
 54%|█████▍    | 15164/28080 [29:58:07<25:34:04,  7.13s/it]
                                                           
{'loss': 0.6152, 'learning_rate': 0.00022976507487519374, 'epoch': 6.48}

 54%|█████▍    | 15164/28080 [29:58:07<25:34:04,  7.13s/it]
 54%|█████▍    | 15165/28080 [29:58:14<25:31:52,  7.12s/it]
                                                           
{'loss': 0.6247, 'learning_rate': 0.00022973633391238247, 'epoch': 6.48}

 54%|█████▍    | 15165/28080 [29:58:14<25:31:52,  7.12s/it]
 54%|█████▍    | 15166/28080 [29:58:22<25:32:39,  7.12s/it]
                                                           
{'loss': 0.6179, 'learning_rate': 0.00022970759321915826, 'epoch': 6.48}

 54%|█████▍    | 15166/28080 [29:58:22<25:32:39,  7.12s/it]
 54%|█████▍    | 15167/28080 [29:58:29<25:32:16,  7.12s/it]
                                                           
{'loss': 0.6379, 'learning_rate': 0.00022967885279590375, 'epoch': 6.48}

 54%|█████▍    | 15167/28080 [29:58:29<25:32:16,  7.12s/it]
 54%|█████▍    | 15168/28080 [29:58:36<25:29:38,  7.11s/it]
                                                           
{'loss': 0.6115, 'learning_rate': 0.00022965011264300102, 'epoch': 6.48}

 54%|█████▍    | 15168/28080 [29:58:36<25:29:38,  7.11s/it]
 54%|█████▍    | 15169/28080 [29:58:43<25:29:11,  7.11s/it]
                                                           
{'loss': 0.6305, 'learning_rate': 0.00022962137276083262, 'epoch': 6.48}

 54%|█████▍    | 15169/28080 [29:58:43<25:29:11,  7.11s/it]
 54%|█████▍    | 15170/28080 [29:58:50<25:30:39,  7.11s/it]
                                                           
{'loss': 0.6131, 'learning_rate': 0.00022959263314978077, 'epoch': 6.48}

 54%|█████▍    | 15170/28080 [29:58:50<25:30:39,  7.11s/it]
 54%|█████▍    | 15171/28080 [29:58:57<25:36:27,  7.14s/it]
                                                           
{'loss': 0.612, 'learning_rate': 0.00022956389381022794, 'epoch': 6.48}

 54%|█████▍    | 15171/28080 [29:58:57<25:36:27,  7.14s/it]
 54%|█████▍    | 15172/28080 [29:59:04<25:28:43,  7.11s/it]
                                                           
{'loss': 0.6183, 'learning_rate': 0.00022953515474255636, 'epoch': 6.48}

 54%|█████▍    | 15172/28080 [29:59:04<25:28:43,  7.11s/it]
 54%|█████▍    | 15173/28080 [29:59:11<25:27:51,  7.10s/it]
                                                           
{'loss': 0.6386, 'learning_rate': 0.0002295064159471485, 'epoch': 6.48}

 54%|█████▍    | 15173/28080 [29:59:11<25:27:51,  7.10s/it]
 54%|█████▍    | 15174/28080 [29:59:18<25:29:10,  7.11s/it]
                                                           
{'loss': 0.612, 'learning_rate': 0.00022947767742438664, 'epoch': 6.48}

 54%|█████▍    | 15174/28080 [29:59:18<25:29:10,  7.11s/it]
 54%|█████▍    | 15175/28080 [29:59:26<25:31:35,  7.12s/it]
                                                           
{'loss': 0.6262, 'learning_rate': 0.00022944893917465305, 'epoch': 6.48}

 54%|█████▍    | 15175/28080 [29:59:26<25:31:35,  7.12s/it]
 54%|█████▍    | 15176/28080 [29:59:33<25:25:52,  7.09s/it]
                                                           
{'loss': 0.6295, 'learning_rate': 0.00022942020119833017, 'epoch': 6.48}

 54%|█████▍    | 15176/28080 [29:59:33<25:25:52,  7.09s/it]
 54%|█████▍    | 15177/28080 [29:59:40<25:25:14,  7.09s/it]
                                                           
{'loss': 0.6065, 'learning_rate': 0.00022939146349580024, 'epoch': 6.48}

 54%|█████▍    | 15177/28080 [29:59:40<25:25:14,  7.09s/it]
 54%|█████▍    | 15178/28080 [29:59:47<25:32:43,  7.13s/it]
                                                           
{'loss': 0.6215, 'learning_rate': 0.00022936272606744569, 'epoch': 6.48}

 54%|█████▍    | 15178/28080 [29:59:47<25:32:43,  7.13s/it]
 54%|█████▍    | 15179/28080 [29:59:54<25:32:28,  7.13s/it]
                                                           
{'loss': 0.6316, 'learning_rate': 0.00022933398891364872, 'epoch': 6.48}

 54%|█████▍    | 15179/28080 [29:59:54<25:32:28,  7.13s/it]
 54%|█████▍    | 15180/28080 [30:00:01<25:31:45,  7.12s/it]
                                                           
{'loss': 0.5957, 'learning_rate': 0.0002293052520347917, 'epoch': 6.48}

 54%|█████▍    | 15180/28080 [30:00:01<25:31:45,  7.12s/it]
 54%|█████▍    | 15181/28080 [30:00:08<25:26:59,  7.10s/it]
                                                           
{'loss': 0.6289, 'learning_rate': 0.000229276515431257, 'epoch': 6.49}

 54%|█████▍    | 15181/28080 [30:00:08<25:26:59,  7.10s/it]
 54%|█████▍    | 15182/28080 [30:00:15<25:21:25,  7.08s/it]
                                                           
{'loss': 0.6289, 'learning_rate': 0.00022924777910342687, 'epoch': 6.49}

 54%|█████▍    | 15182/28080 [30:00:15<25:21:25,  7.08s/it]
 54%|█████▍    | 15183/28080 [30:00:22<25:16:51,  7.06s/it]
                                                           
{'loss': 0.6225, 'learning_rate': 0.00022921904305168354, 'epoch': 6.49}

 54%|█████▍    | 15183/28080 [30:00:22<25:16:51,  7.06s/it]
 54%|█████▍    | 15184/28080 [30:00:29<25:24:22,  7.09s/it]
                                                           
{'loss': 0.6142, 'learning_rate': 0.00022919030727640955, 'epoch': 6.49}

 54%|█████▍    | 15184/28080 [30:00:29<25:24:22,  7.09s/it]
 54%|█████▍    | 15185/28080 [30:00:36<25:26:15,  7.10s/it]
                                                           
{'loss': 0.6187, 'learning_rate': 0.0002291615717779869, 'epoch': 6.49}

 54%|█████▍    | 15185/28080 [30:00:36<25:26:15,  7.10s/it]
 54%|█████▍    | 15186/28080 [30:00:44<25:24:30,  7.09s/it]
                                                           
{'loss': 0.623, 'learning_rate': 0.00022913283655679817, 'epoch': 6.49}

 54%|█████▍    | 15186/28080 [30:00:44<25:24:30,  7.09s/it]
 54%|█████▍    | 15187/28080 [30:00:51<25:32:10,  7.13s/it]
                                                           
{'loss': 0.6072, 'learning_rate': 0.00022910410161322545, 'epoch': 6.49}

 54%|█████▍    | 15187/28080 [30:00:51<25:32:10,  7.13s/it]
 54%|█████▍    | 15188/28080 [30:00:58<25:28:45,  7.11s/it]
                                                           
{'loss': 0.6346, 'learning_rate': 0.00022907536694765116, 'epoch': 6.49}

 54%|█████▍    | 15188/28080 [30:00:58<25:28:45,  7.11s/it]
 54%|█████▍    | 15189/28080 [30:01:05<25:28:34,  7.11s/it]
                                                           
{'loss': 0.6216, 'learning_rate': 0.00022904663256045747, 'epoch': 6.49}

 54%|█████▍    | 15189/28080 [30:01:05<25:28:34,  7.11s/it]
 54%|█████▍    | 15190/28080 [30:01:12<25:24:24,  7.10s/it]
                                                           
{'loss': 0.611, 'learning_rate': 0.00022901789845202679, 'epoch': 6.49}

 54%|█████▍    | 15190/28080 [30:01:12<25:24:24,  7.10s/it]
 54%|█████▍    | 15191/28080 [30:01:19<25:22:41,  7.09s/it]
                                                           
{'loss': 0.6089, 'learning_rate': 0.00022898916462274125, 'epoch': 6.49}

 54%|█████▍    | 15191/28080 [30:01:19<25:22:41,  7.09s/it]
 54%|█████▍    | 15192/28080 [30:01:26<25:27:27,  7.11s/it]
                                                           
{'loss': 0.5993, 'learning_rate': 0.00022896043107298325, 'epoch': 6.49}

 54%|█████▍    | 15192/28080 [30:01:26<25:27:27,  7.11s/it]
 54%|█████▍    | 15193/28080 [30:01:33<25:29:24,  7.12s/it]
                                                           
{'loss': 0.6315, 'learning_rate': 0.00022893169780313494, 'epoch': 6.49}

 54%|█████▍    | 15193/28080 [30:01:33<25:29:24,  7.12s/it]
 54%|█████▍    | 15194/28080 [30:01:40<25:24:15,  7.10s/it]
                                                           
{'loss': 0.6174, 'learning_rate': 0.00022890296481357876, 'epoch': 6.49}

 54%|█████▍    | 15194/28080 [30:01:40<25:24:15,  7.10s/it]
 54%|█████▍    | 15195/28080 [30:01:48<25:32:32,  7.14s/it]
                                                           
{'loss': 0.595, 'learning_rate': 0.00022887423210469677, 'epoch': 6.49}

 54%|█████▍    | 15195/28080 [30:01:48<25:32:32,  7.14s/it]
 54%|█████▍    | 15196/28080 [30:01:55<25:31:43,  7.13s/it]
                                                           
{'loss': 0.6246, 'learning_rate': 0.0002288454996768714, 'epoch': 6.49}

 54%|█████▍    | 15196/28080 [30:01:55<25:31:43,  7.13s/it]
 54%|█████▍    | 15197/28080 [30:02:02<25:22:50,  7.09s/it]
                                                           
{'loss': 0.6345, 'learning_rate': 0.0002288167675304847, 'epoch': 6.49}

 54%|█████▍    | 15197/28080 [30:02:02<25:22:50,  7.09s/it]
 54%|█████▍    | 15198/28080 [30:02:09<25:22:55,  7.09s/it]
                                                           
{'loss': 0.6547, 'learning_rate': 0.00022878803566591928, 'epoch': 6.49}

 54%|█████▍    | 15198/28080 [30:02:09<25:22:55,  7.09s/it]
 54%|█████▍    | 15199/28080 [30:02:16<25:20:19,  7.08s/it]
                                                           
{'loss': 0.6205, 'learning_rate': 0.00022875930408355706, 'epoch': 6.49}

 54%|█████▍    | 15199/28080 [30:02:16<25:20:19,  7.08s/it]
 54%|█████▍    | 15200/28080 [30:02:23<25:25:18,  7.11s/it]
                                                           
{'loss': 0.6199, 'learning_rate': 0.00022873057278378027, 'epoch': 6.49}

 54%|█████▍    | 15200/28080 [30:02:23<25:25:18,  7.11s/it]
 54%|█████▍    | 15201/28080 [30:02:30<25:26:00,  7.11s/it]
                                                           
{'loss': 0.6062, 'learning_rate': 0.00022870184176697144, 'epoch': 6.49}

 54%|█████▍    | 15201/28080 [30:02:30<25:26:00,  7.11s/it]
 54%|█████▍    | 15202/28080 [30:02:37<25:35:17,  7.15s/it]
                                                           
{'loss': 0.5987, 'learning_rate': 0.00022867311103351245, 'epoch': 6.49}

 54%|█████▍    | 15202/28080 [30:02:37<25:35:17,  7.15s/it]
 54%|█████▍    | 15203/28080 [30:02:45<25:30:24,  7.13s/it]
                                                           
{'loss': 0.6297, 'learning_rate': 0.0002286443805837859, 'epoch': 6.49}

 54%|█████▍    | 15203/28080 [30:02:45<25:30:24,  7.13s/it]
 54%|█████▍    | 15204/28080 [30:02:52<25:35:04,  7.15s/it]
                                                           
{'loss': 0.5969, 'learning_rate': 0.00022861565041817369, 'epoch': 6.5}

 54%|█████▍    | 15204/28080 [30:02:52<25:35:04,  7.15s/it]
 54%|█████▍    | 15205/28080 [30:02:59<25:34:31,  7.15s/it]
                                                           
{'loss': 0.6069, 'learning_rate': 0.00022858692053705828, 'epoch': 6.5}

 54%|█████▍    | 15205/28080 [30:02:59<25:34:31,  7.15s/it]
 54%|█████▍    | 15206/28080 [30:03:06<25:33:33,  7.15s/it]
                                                           
{'loss': 0.6099, 'learning_rate': 0.00022855819094082176, 'epoch': 6.5}

 54%|█████▍    | 15206/28080 [30:03:06<25:33:33,  7.15s/it]
 54%|█████▍    | 15207/28080 [30:03:13<25:35:51,  7.16s/it]
                                                           
{'loss': 0.6272, 'learning_rate': 0.00022852946162984646, 'epoch': 6.5}

 54%|█████▍    | 15207/28080 [30:03:13<25:35:51,  7.16s/it]
 54%|█████▍    | 15208/28080 [30:03:20<25:35:40,  7.16s/it]
                                                           
{'loss': 0.6019, 'learning_rate': 0.00022850073260451443, 'epoch': 6.5}

 54%|█████▍    | 15208/28080 [30:03:20<25:35:40,  7.16s/it]
 54%|█████▍    | 15209/28080 [30:03:27<25:31:06,  7.14s/it]
                                                           
{'loss': 0.6035, 'learning_rate': 0.00022847200386520803, 'epoch': 6.5}

 54%|█████▍    | 15209/28080 [30:03:27<25:31:06,  7.14s/it]
 54%|█████▍    | 15210/28080 [30:03:35<25:37:02,  7.17s/it]
                                                           
{'loss': 0.6053, 'learning_rate': 0.00022844327541230935, 'epoch': 6.5}

 54%|█████▍    | 15210/28080 [30:03:35<25:37:02,  7.17s/it]
 54%|█████▍    | 15211/28080 [30:03:42<25:34:03,  7.15s/it]
                                                           
{'loss': 0.5944, 'learning_rate': 0.00022841454724620075, 'epoch': 6.5}

 54%|█████▍    | 15211/28080 [30:03:42<25:34:03,  7.15s/it]
 54%|█████▍    | 15212/28080 [30:03:49<25:32:15,  7.14s/it]
                                                           
{'loss': 0.6103, 'learning_rate': 0.00022838581936726425, 'epoch': 6.5}

 54%|█████▍    | 15212/28080 [30:03:49<25:32:15,  7.14s/it]
 54%|█████▍    | 15213/28080 [30:03:56<25:24:08,  7.11s/it]
                                                           
{'loss': 0.6045, 'learning_rate': 0.0002283570917758822, 'epoch': 6.5}

 54%|█████▍    | 15213/28080 [30:03:56<25:24:08,  7.11s/it]
 54%|█████▍    | 15214/28080 [30:04:03<25:27:02,  7.12s/it]
                                                           
{'loss': 0.6099, 'learning_rate': 0.00022832836447243655, 'epoch': 6.5}

 54%|█████▍    | 15214/28080 [30:04:03<25:27:02,  7.12s/it]
 54%|█████▍    | 15215/28080 [30:04:10<25:25:03,  7.11s/it]
                                                           
{'loss': 0.6024, 'learning_rate': 0.00022829963745730987, 'epoch': 6.5}

 54%|█████▍    | 15215/28080 [30:04:10<25:25:03,  7.11s/it]
 54%|█████▍    | 15216/28080 [30:04:17<25:22:39,  7.10s/it]
                                                           
{'loss': 0.6148, 'learning_rate': 0.00022827091073088394, 'epoch': 6.5}

 54%|█████▍    | 15216/28080 [30:04:17<25:22:39,  7.10s/it]
 54%|█████▍    | 15217/28080 [30:04:24<25:14:04,  7.06s/it]
                                                           
{'loss': 0.6194, 'learning_rate': 0.00022824218429354123, 'epoch': 6.5}

 54%|█████▍    | 15217/28080 [30:04:24<25:14:04,  7.06s/it]
 54%|█████▍    | 15218/28080 [30:04:31<25:21:18,  7.10s/it]
                                                           
{'loss': 0.6125, 'learning_rate': 0.00022821345814566377, 'epoch': 6.5}

 54%|█████▍    | 15218/28080 [30:04:31<25:21:18,  7.10s/it]
 54%|█████▍    | 15219/28080 [30:04:39<25:28:41,  7.13s/it]
                                                           
{'loss': 0.6316, 'learning_rate': 0.0002281847322876338, 'epoch': 6.5}

 54%|█████▍    | 15219/28080 [30:04:39<25:28:41,  7.13s/it]
 54%|█████▍    | 15220/28080 [30:04:46<25:23:05,  7.11s/it]
                                                           
{'loss': 0.633, 'learning_rate': 0.00022815600671983343, 'epoch': 6.5}

 54%|█████▍    | 15220/28080 [30:04:46<25:23:05,  7.11s/it]
 54%|█████▍    | 15221/28080 [30:04:53<25:18:30,  7.09s/it]
                                                           
{'loss': 0.6412, 'learning_rate': 0.00022812728144264494, 'epoch': 6.5}

 54%|█████▍    | 15221/28080 [30:04:53<25:18:30,  7.09s/it]
 54%|█████▍    | 15222/28080 [30:05:00<25:13:24,  7.06s/it]
                                                           
{'loss': 0.6481, 'learning_rate': 0.00022809855645645032, 'epoch': 6.5}

 54%|█████▍    | 15222/28080 [30:05:00<25:13:24,  7.06s/it]
 54%|█████▍    | 15223/28080 [30:05:07<25:23:17,  7.11s/it]
                                                           
{'loss': 0.6098, 'learning_rate': 0.00022806983176163186, 'epoch': 6.5}

 54%|█████▍    | 15223/28080 [30:05:07<25:23:17,  7.11s/it]
 54%|█████▍    | 15224/28080 [30:05:14<25:24:19,  7.11s/it]
                                                           
{'loss': 0.6014, 'learning_rate': 0.0002280411073585717, 'epoch': 6.5}

 54%|█████▍    | 15224/28080 [30:05:14<25:24:19,  7.11s/it]
 54%|█████▍    | 15225/28080 [30:05:21<25:18:17,  7.09s/it]
                                                           
{'loss': 0.6063, 'learning_rate': 0.00022801238324765186, 'epoch': 6.5}

 54%|█████▍    | 15225/28080 [30:05:21<25:18:17,  7.09s/it]
 54%|█████▍    | 15226/28080 [30:05:28<25:14:14,  7.07s/it]
                                                           
{'loss': 0.5922, 'learning_rate': 0.00022798365942925465, 'epoch': 6.5}

 54%|█████▍    | 15226/28080 [30:05:28<25:14:14,  7.07s/it]
 54%|█████▍    | 15227/28080 [30:05:35<25:11:41,  7.06s/it]
                                                           
{'loss': 0.6149, 'learning_rate': 0.00022795493590376206, 'epoch': 6.5}

 54%|█████▍    | 15227/28080 [30:05:35<25:11:41,  7.06s/it]
 54%|█████▍    | 15228/28080 [30:05:42<25:15:26,  7.07s/it]
                                                           
{'loss': 0.5988, 'learning_rate': 0.00022792621267155638, 'epoch': 6.51}

 54%|█████▍    | 15228/28080 [30:05:42<25:15:26,  7.07s/it]
 54%|█████▍    | 15229/28080 [30:05:49<25:18:33,  7.09s/it]
                                                           
{'loss': 0.614, 'learning_rate': 0.0002278974897330196, 'epoch': 6.51}

 54%|█████▍    | 15229/28080 [30:05:49<25:18:33,  7.09s/it]
 54%|█████▍    | 15230/28080 [30:05:57<25:21:05,  7.10s/it]
                                                           
{'loss': 0.6107, 'learning_rate': 0.000227868767088534, 'epoch': 6.51}

 54%|█████▍    | 15230/28080 [30:05:57<25:21:05,  7.10s/it]
 54%|█████▍    | 15231/28080 [30:06:04<25:25:58,  7.13s/it]
                                                           
{'loss': 0.6155, 'learning_rate': 0.0002278400447384815, 'epoch': 6.51}

 54%|█████▍    | 15231/28080 [30:06:04<25:25:58,  7.13s/it]
 54%|█████▍    | 15232/28080 [30:06:11<25:19:14,  7.09s/it]
                                                           
{'loss': 0.6293, 'learning_rate': 0.0002278113226832445, 'epoch': 6.51}

 54%|█████▍    | 15232/28080 [30:06:11<25:19:14,  7.09s/it]
 54%|█████▍    | 15233/28080 [30:06:18<25:24:05,  7.12s/it]
                                                           
{'loss': 0.6006, 'learning_rate': 0.0002277826009232048, 'epoch': 6.51}

 54%|█████▍    | 15233/28080 [30:06:18<25:24:05,  7.12s/it]
 54%|█████▍    | 15234/28080 [30:06:25<25:20:39,  7.10s/it]
                                                           
{'loss': 0.6221, 'learning_rate': 0.00022775387945874484, 'epoch': 6.51}

 54%|█████▍    | 15234/28080 [30:06:25<25:20:39,  7.10s/it]
 54%|█████▍    | 15235/28080 [30:06:32<25:22:49,  7.11s/it]
                                                           
{'loss': 0.5963, 'learning_rate': 0.0002277251582902464, 'epoch': 6.51}

 54%|█████▍    | 15235/28080 [30:06:32<25:22:49,  7.11s/it]
 54%|█████▍    | 15236/28080 [30:06:39<25:14:16,  7.07s/it]
                                                           
{'loss': 0.6285, 'learning_rate': 0.00022769643741809184, 'epoch': 6.51}

 54%|█████▍    | 15236/28080 [30:06:39<25:14:16,  7.07s/it]
 54%|█████▍    | 15237/28080 [30:06:46<25:17:21,  7.09s/it]
                                                           
{'loss': 0.6138, 'learning_rate': 0.00022766771684266314, 'epoch': 6.51}

 54%|█████▍    | 15237/28080 [30:06:46<25:17:21,  7.09s/it]
 54%|█████▍    | 15238/28080 [30:06:53<25:17:17,  7.09s/it]
                                                           
{'loss': 0.628, 'learning_rate': 0.00022763899656434247, 'epoch': 6.51}

 54%|█████▍    | 15238/28080 [30:06:53<25:17:17,  7.09s/it]
 54%|█████▍    | 15239/28080 [30:07:01<25:24:34,  7.12s/it]
                                                           
{'loss': 0.6039, 'learning_rate': 0.00022761027658351184, 'epoch': 6.51}

 54%|█████▍    | 15239/28080 [30:07:01<25:24:34,  7.12s/it]
 54%|█████▍    | 15240/28080 [30:07:08<25:26:26,  7.13s/it]
                                                           
{'loss': 0.6182, 'learning_rate': 0.00022758155690055342, 'epoch': 6.51}

 54%|█████▍    | 15240/28080 [30:07:08<25:26:26,  7.13s/it]
 54%|█████▍    | 15241/28080 [30:07:15<25:19:33,  7.10s/it]
                                                           
{'loss': 0.6024, 'learning_rate': 0.00022755283751584924, 'epoch': 6.51}

 54%|█████▍    | 15241/28080 [30:07:15<25:19:33,  7.10s/it]
 54%|█████▍    | 15242/28080 [30:07:22<25:19:36,  7.10s/it]
                                                           
{'loss': 0.6162, 'learning_rate': 0.00022752411842978142, 'epoch': 6.51}

 54%|█████▍    | 15242/28080 [30:07:22<25:19:36,  7.10s/it]
 54%|█████▍    | 15243/28080 [30:07:29<25:21:58,  7.11s/it]
                                                           
{'loss': 0.6214, 'learning_rate': 0.00022749539964273197, 'epoch': 6.51}

 54%|█████▍    | 15243/28080 [30:07:29<25:21:58,  7.11s/it]
 54%|█████▍    | 15244/28080 [30:07:36<25:26:47,  7.14s/it]
                                                           
{'loss': 0.6169, 'learning_rate': 0.00022746668115508306, 'epoch': 6.51}

 54%|█████▍    | 15244/28080 [30:07:36<25:26:47,  7.14s/it]
 54%|█████▍    | 15245/28080 [30:07:43<25:29:42,  7.15s/it]
                                                           
{'loss': 0.6222, 'learning_rate': 0.0002274379629672166, 'epoch': 6.51}

 54%|█████▍    | 15245/28080 [30:07:43<25:29:42,  7.15s/it]
 54%|█████▍    | 15246/28080 [30:07:50<25:25:56,  7.13s/it]
                                                           
{'loss': 0.598, 'learning_rate': 0.00022740924507951493, 'epoch': 6.51}

 54%|█████▍    | 15246/28080 [30:07:50<25:25:56,  7.13s/it]
 54%|█████▍    | 15247/28080 [30:07:58<25:27:30,  7.14s/it]
                                                           
{'loss': 0.6211, 'learning_rate': 0.00022738052749235983, 'epoch': 6.51}

 54%|█████▍    | 15247/28080 [30:07:58<25:27:30,  7.14s/it]
 54%|█████▍    | 15248/28080 [30:08:05<25:18:19,  7.10s/it]
                                                           
{'loss': 0.6234, 'learning_rate': 0.0002273518102061335, 'epoch': 6.51}

 54%|█████▍    | 15248/28080 [30:08:05<25:18:19,  7.10s/it]
 54%|█████▍    | 15249/28080 [30:08:12<25:10:54,  7.07s/it]
                                                           
{'loss': 0.6548, 'learning_rate': 0.0002273230932212181, 'epoch': 6.51}

 54%|█████▍    | 15249/28080 [30:08:12<25:10:54,  7.07s/it]
 54%|█████▍    | 15250/28080 [30:08:19<25:14:59,  7.08s/it]
                                                           
{'loss': 0.6323, 'learning_rate': 0.00022729437653799537, 'epoch': 6.51}

 54%|█████▍    | 15250/28080 [30:08:19<25:14:59,  7.08s/it]
 54%|█████▍    | 15251/28080 [30:08:26<25:15:14,  7.09s/it]
                                                           
{'loss': 0.6418, 'learning_rate': 0.00022726566015684768, 'epoch': 6.52}

 54%|█████▍    | 15251/28080 [30:08:26<25:15:14,  7.09s/it]
 54%|█████▍    | 15252/28080 [30:08:33<25:11:13,  7.07s/it]
                                                           
{'loss': 0.6233, 'learning_rate': 0.00022723694407815676, 'epoch': 6.52}

 54%|█████▍    | 15252/28080 [30:08:33<25:11:13,  7.07s/it]
 54%|█████▍    | 15253/28080 [30:08:40<25:08:45,  7.06s/it]
                                                           
{'loss': 0.6321, 'learning_rate': 0.00022720822830230494, 'epoch': 6.52}

 54%|█████▍    | 15253/28080 [30:08:40<25:08:45,  7.06s/it]
 54%|█████▍    | 15254/28080 [30:08:47<25:19:43,  7.11s/it]
                                                           
{'loss': 0.6177, 'learning_rate': 0.00022717951282967409, 'epoch': 6.52}

 54%|█████▍    | 15254/28080 [30:08:47<25:19:43,  7.11s/it]
 54%|█████▍    | 15255/28080 [30:08:54<25:15:21,  7.09s/it]
                                                           
{'loss': 0.6357, 'learning_rate': 0.00022715079766064632, 'epoch': 6.52}

 54%|█████▍    | 15255/28080 [30:08:54<25:15:21,  7.09s/it]
 54%|█████▍    | 15256/28080 [30:09:01<25:17:39,  7.10s/it]
                                                           
{'loss': 0.6175, 'learning_rate': 0.00022712208279560356, 'epoch': 6.52}

 54%|█████▍    | 15256/28080 [30:09:01<25:17:39,  7.10s/it]
 54%|█████▍    | 15257/28080 [30:09:08<25:20:49,  7.12s/it]
                                                           
{'loss': 0.6176, 'learning_rate': 0.00022709336823492794, 'epoch': 6.52}

 54%|█████▍    | 15257/28080 [30:09:08<25:20:49,  7.12s/it]
 54%|█████▍    | 15258/28080 [30:09:15<25:18:16,  7.10s/it]
                                                           
{'loss': 0.6115, 'learning_rate': 0.00022706465397900137, 'epoch': 6.52}

 54%|█████▍    | 15258/28080 [30:09:15<25:18:16,  7.10s/it]
 54%|█████▍    | 15259/28080 [30:09:23<25:17:06,  7.10s/it]
                                                           
{'loss': 0.6013, 'learning_rate': 0.00022703594002820596, 'epoch': 6.52}

 54%|█████▍    | 15259/28080 [30:09:23<25:17:06,  7.10s/it]
 54%|█████▍    | 15260/28080 [30:09:30<25:16:48,  7.10s/it]
                                                           
{'loss': 0.6044, 'learning_rate': 0.00022700722638292365, 'epoch': 6.52}

 54%|█████▍    | 15260/28080 [30:09:30<25:16:48,  7.10s/it]
 54%|█████▍    | 15261/28080 [30:09:37<25:14:07,  7.09s/it]
                                                           
{'loss': 0.6126, 'learning_rate': 0.0002269785130435365, 'epoch': 6.52}

 54%|█████▍    | 15261/28080 [30:09:37<25:14:07,  7.09s/it]
 54%|█████▍    | 15262/28080 [30:09:44<25:19:52,  7.11s/it]
                                                           
{'loss': 0.5997, 'learning_rate': 0.00022694980001042637, 'epoch': 6.52}

 54%|█████▍    | 15262/28080 [30:09:44<25:19:52,  7.11s/it]
 54%|█████▍    | 15263/28080 [30:09:51<25:17:38,  7.10s/it]
                                                           
{'loss': 0.6152, 'learning_rate': 0.00022692108728397556, 'epoch': 6.52}

 54%|█████▍    | 15263/28080 [30:09:51<25:17:38,  7.10s/it]
 54%|█████▍    | 15264/28080 [30:09:58<25:13:19,  7.08s/it]
                                                           
{'loss': 0.6229, 'learning_rate': 0.0002268923748645657, 'epoch': 6.52}

 54%|█████▍    | 15264/28080 [30:09:58<25:13:19,  7.08s/it]
 54%|█████▍    | 15265/28080 [30:10:05<25:18:59,  7.11s/it]
                                                           
{'loss': 0.6147, 'learning_rate': 0.00022686366275257913, 'epoch': 6.52}

 54%|█████▍    | 15265/28080 [30:10:05<25:18:59,  7.11s/it]
 54%|█████▍    | 15266/28080 [30:10:12<25:18:42,  7.11s/it]
                                                           
{'loss': 0.6281, 'learning_rate': 0.00022683495094839748, 'epoch': 6.52}

 54%|█████▍    | 15266/28080 [30:10:12<25:18:42,  7.11s/it]
 54%|█████▍    | 15267/28080 [30:10:19<25:20:27,  7.12s/it]
                                                           
{'loss': 0.6161, 'learning_rate': 0.00022680623945240302, 'epoch': 6.52}

 54%|█████▍    | 15267/28080 [30:10:19<25:20:27,  7.12s/it]
 54%|█████▍    | 15268/28080 [30:10:26<25:14:42,  7.09s/it]
                                                           
{'loss': 0.6053, 'learning_rate': 0.00022677752826497755, 'epoch': 6.52}

 54%|█████▍    | 15268/28080 [30:10:26<25:14:42,  7.09s/it]
 54%|█████▍    | 15269/28080 [30:10:34<25:15:43,  7.10s/it]
                                                           
{'loss': 0.6292, 'learning_rate': 0.0002267488173865032, 'epoch': 6.52}

 54%|█████▍    | 15269/28080 [30:10:34<25:15:43,  7.10s/it]
 54%|█████▍    | 15270/28080 [30:10:41<25:16:07,  7.10s/it]
                                                           
{'loss': 0.6117, 'learning_rate': 0.00022672010681736178, 'epoch': 6.52}

 54%|█████▍    | 15270/28080 [30:10:41<25:16:07,  7.10s/it]
 54%|█████▍    | 15271/28080 [30:10:48<25:21:38,  7.13s/it]
                                                           
{'loss': 0.6254, 'learning_rate': 0.00022669139655793536, 'epoch': 6.52}

 54%|█████▍    | 15271/28080 [30:10:48<25:21:38,  7.13s/it]
 54%|█████▍    | 15272/28080 [30:10:55<25:25:42,  7.15s/it]
                                                           
{'loss': 0.6059, 'learning_rate': 0.0002266626866086058, 'epoch': 6.52}

 54%|█████▍    | 15272/28080 [30:10:55<25:25:42,  7.15s/it]
 54%|█████▍    | 15273/28080 [30:11:02<25:24:44,  7.14s/it]
                                                           
{'loss': 0.6043, 'learning_rate': 0.0002266339769697552, 'epoch': 6.52}

 54%|█████▍    | 15273/28080 [30:11:02<25:24:44,  7.14s/it]
 54%|█████▍    | 15274/28080 [30:11:09<25:26:35,  7.15s/it]
                                                           
{'loss': 0.6143, 'learning_rate': 0.00022660526764176542, 'epoch': 6.52}

 54%|█████▍    | 15274/28080 [30:11:09<25:26:35,  7.15s/it]
 54%|█████▍    | 15275/28080 [30:11:17<25:28:22,  7.16s/it]
                                                           
{'loss': 0.606, 'learning_rate': 0.00022657655862501835, 'epoch': 6.53}

 54%|█████▍    | 15275/28080 [30:11:17<25:28:22,  7.16s/it]
 54%|█████▍    | 15276/28080 [30:11:24<25:30:03,  7.17s/it]
                                                           
{'loss': 0.648, 'learning_rate': 0.00022654784991989608, 'epoch': 6.53}

 54%|█████▍    | 15276/28080 [30:11:24<25:30:03,  7.17s/it]
 54%|█████▍    | 15277/28080 [30:11:31<25:25:29,  7.15s/it]
                                                           
{'loss': 0.626, 'learning_rate': 0.0002265191415267804, 'epoch': 6.53}

 54%|█████▍    | 15277/28080 [30:11:31<25:25:29,  7.15s/it]
 54%|█████▍    | 15278/28080 [30:11:38<25:19:55,  7.12s/it]
                                                           
{'loss': 0.6296, 'learning_rate': 0.0002264904334460534, 'epoch': 6.53}

 54%|█████▍    | 15278/28080 [30:11:38<25:19:55,  7.12s/it]
 54%|█████▍    | 15279/28080 [30:11:45<25:15:02,  7.10s/it]
                                                           
{'loss': 0.6292, 'learning_rate': 0.0002264617256780968, 'epoch': 6.53}

 54%|█████▍    | 15279/28080 [30:11:45<25:15:02,  7.10s/it]
 54%|█████▍    | 15280/28080 [30:11:52<25:11:32,  7.09s/it]
                                                           
{'loss': 0.5982, 'learning_rate': 0.0002264330182232928, 'epoch': 6.53}

 54%|█████▍    | 15280/28080 [30:11:52<25:11:32,  7.09s/it]
 54%|█████▍    | 15281/28080 [30:11:59<25:06:20,  7.06s/it]
                                                           
{'loss': 0.6022, 'learning_rate': 0.00022640431108202305, 'epoch': 6.53}

 54%|█████▍    | 15281/28080 [30:11:59<25:06:20,  7.06s/it]
 54%|█████▍    | 15282/28080 [30:12:06<25:11:01,  7.08s/it]
                                                           
{'loss': 0.618, 'learning_rate': 0.00022637560425466978, 'epoch': 6.53}

 54%|█████▍    | 15282/28080 [30:12:06<25:11:01,  7.08s/it]
 54%|█████▍    | 15283/28080 [30:12:13<25:12:03,  7.09s/it]
                                                           
{'loss': 0.622, 'learning_rate': 0.00022634689774161452, 'epoch': 6.53}

 54%|█████▍    | 15283/28080 [30:12:13<25:12:03,  7.09s/it]
 54%|█████▍    | 15284/28080 [30:12:20<25:17:36,  7.12s/it]
                                                           
{'loss': 0.6241, 'learning_rate': 0.0002263181915432395, 'epoch': 6.53}

 54%|█████▍    | 15284/28080 [30:12:20<25:17:36,  7.12s/it]
 54%|█████▍    | 15285/28080 [30:12:28<25:19:44,  7.13s/it]
                                                           
{'loss': 0.6007, 'learning_rate': 0.00022628948565992646, 'epoch': 6.53}

 54%|█████▍    | 15285/28080 [30:12:28<25:19:44,  7.13s/it]
 54%|█████▍    | 15286/28080 [30:12:35<25:14:44,  7.10s/it]
                                                           
{'loss': 0.5962, 'learning_rate': 0.0002262607800920574, 'epoch': 6.53}

 54%|█████▍    | 15286/28080 [30:12:35<25:14:44,  7.10s/it]
 54%|█████▍    | 15287/28080 [30:12:42<25:14:58,  7.11s/it]
                                                           
{'loss': 0.6276, 'learning_rate': 0.00022623207484001413, 'epoch': 6.53}

 54%|█████▍    | 15287/28080 [30:12:42<25:14:58,  7.11s/it]
 54%|█████▍    | 15288/28080 [30:12:49<25:15:44,  7.11s/it]
                                                           
{'loss': 0.6325, 'learning_rate': 0.00022620336990417865, 'epoch': 6.53}

 54%|█████▍    | 15288/28080 [30:12:49<25:15:44,  7.11s/it]
 54%|█████▍    | 15289/28080 [30:12:56<25:15:32,  7.11s/it]
                                                           
{'loss': 0.6167, 'learning_rate': 0.0002261746652849327, 'epoch': 6.53}

 54%|█████▍    | 15289/28080 [30:12:56<25:15:32,  7.11s/it]
 54%|█████▍    | 15290/28080 [30:13:03<25:16:57,  7.12s/it]
                                                           
{'loss': 0.6199, 'learning_rate': 0.00022614596098265833, 'epoch': 6.53}

 54%|█████▍    | 15290/28080 [30:13:03<25:16:57,  7.12s/it]
 54%|█████▍    | 15291/28080 [30:13:10<25:11:02,  7.09s/it]
                                                           
{'loss': 0.6196, 'learning_rate': 0.00022611725699773724, 'epoch': 6.53}

 54%|█████▍    | 15291/28080 [30:13:10<25:11:02,  7.09s/it]
 54%|█████▍    | 15292/28080 [30:13:17<25:17:42,  7.12s/it]
                                                           
{'loss': 0.6202, 'learning_rate': 0.0002260885533305515, 'epoch': 6.53}

 54%|█████▍    | 15292/28080 [30:13:17<25:17:42,  7.12s/it]
 54%|█████▍    | 15293/28080 [30:13:24<25:04:30,  7.06s/it]
                                                           
{'loss': 0.6107, 'learning_rate': 0.0002260598499814828, 'epoch': 6.53}

 54%|█████▍    | 15293/28080 [30:13:24<25:04:30,  7.06s/it]
 54%|█████▍    | 15294/28080 [30:13:31<25:10:52,  7.09s/it]
                                                           
{'loss': 0.6005, 'learning_rate': 0.00022603114695091323, 'epoch': 6.53}

 54%|█████▍    | 15294/28080 [30:13:31<25:10:52,  7.09s/it]
 54%|█████▍    | 15295/28080 [30:13:38<25:09:13,  7.08s/it]
                                                           
{'loss': 0.6119, 'learning_rate': 0.00022600244423922437, 'epoch': 6.53}

 54%|█████▍    | 15295/28080 [30:13:38<25:09:13,  7.08s/it]
 54%|█████▍    | 15296/28080 [30:13:46<25:13:13,  7.10s/it]
                                                           
{'loss': 0.6239, 'learning_rate': 0.00022597374184679837, 'epoch': 6.53}

 54%|█████▍    | 15296/28080 [30:13:46<25:13:13,  7.10s/it]
 54%|█████▍    | 15297/28080 [30:13:53<25:17:59,  7.13s/it]
                                                           
{'loss': 0.6055, 'learning_rate': 0.0002259450397740168, 'epoch': 6.53}

 54%|█████▍    | 15297/28080 [30:13:53<25:17:59,  7.13s/it]
 54%|█████▍    | 15298/28080 [30:14:00<25:18:23,  7.13s/it]
                                                           
{'loss': 0.6147, 'learning_rate': 0.0002259163380212618, 'epoch': 6.54}

 54%|█████▍    | 15298/28080 [30:14:00<25:18:23,  7.13s/it]
 54%|█████▍    | 15299/28080 [30:14:07<25:20:39,  7.14s/it]
                                                           
{'loss': 0.6135, 'learning_rate': 0.0002258876365889151, 'epoch': 6.54}

 54%|█████▍    | 15299/28080 [30:14:07<25:20:39,  7.14s/it]
 54%|█████▍    | 15300/28080 [30:14:14<25:17:36,  7.12s/it]
                                                           
{'loss': 0.6203, 'learning_rate': 0.00022585893547735837, 'epoch': 6.54}

 54%|█████▍    | 15300/28080 [30:14:14<25:17:36,  7.12s/it]
 54%|█████▍    | 15301/28080 [30:14:21<25:13:31,  7.11s/it]
                                                           
{'loss': 0.6131, 'learning_rate': 0.00022583023468697368, 'epoch': 6.54}

 54%|█████▍    | 15301/28080 [30:14:21<25:13:31,  7.11s/it]
 54%|█████▍    | 15302/28080 [30:14:28<25:19:22,  7.13s/it]
                                                           
{'loss': 0.6171, 'learning_rate': 0.00022580153421814276, 'epoch': 6.54}

 54%|█████▍    | 15302/28080 [30:14:28<25:19:22,  7.13s/it]
 54%|█████▍    | 15303/28080 [30:14:36<25:17:53,  7.13s/it]
                                                           
{'loss': 0.6416, 'learning_rate': 0.00022577283407124749, 'epoch': 6.54}

 54%|█████▍    | 15303/28080 [30:14:36<25:17:53,  7.13s/it]
 55%|█████▍    | 15304/28080 [30:14:43<25:22:02,  7.15s/it]
                                                           
{'loss': 0.6248, 'learning_rate': 0.00022574413424666963, 'epoch': 6.54}

 55%|█████▍    | 15304/28080 [30:14:43<25:22:02,  7.15s/it]
 55%|█████▍    | 15305/28080 [30:14:50<25:18:39,  7.13s/it]
                                                           
{'loss': 0.6139, 'learning_rate': 0.00022571543474479111, 'epoch': 6.54}

 55%|█████▍    | 15305/28080 [30:14:50<25:18:39,  7.13s/it]
 55%|█████▍    | 15306/28080 [30:14:57<25:20:23,  7.14s/it]
                                                           
{'loss': 0.5848, 'learning_rate': 0.00022568673556599362, 'epoch': 6.54}

 55%|█████▍    | 15306/28080 [30:14:57<25:20:23,  7.14s/it]
 55%|█████▍    | 15307/28080 [30:15:04<25:16:35,  7.12s/it]
                                                           
{'loss': 0.6247, 'learning_rate': 0.00022565803671065904, 'epoch': 6.54}

 55%|█████▍    | 15307/28080 [30:15:04<25:16:35,  7.12s/it]
 55%|█████▍    | 15308/28080 [30:15:11<25:10:37,  7.10s/it]
                                                           
{'loss': 0.626, 'learning_rate': 0.00022562933817916916, 'epoch': 6.54}

 55%|█████▍    | 15308/28080 [30:15:11<25:10:37,  7.10s/it]
 55%|█████▍    | 15309/28080 [30:15:18<25:16:10,  7.12s/it]
                                                           
{'loss': 0.6182, 'learning_rate': 0.00022560063997190583, 'epoch': 6.54}

 55%|█████▍    | 15309/28080 [30:15:18<25:16:10,  7.12s/it]
 55%|█████▍    | 15310/28080 [30:15:25<25:16:06,  7.12s/it]
                                                           
{'loss': 0.6011, 'learning_rate': 0.00022557194208925073, 'epoch': 6.54}

 55%|█████▍    | 15310/28080 [30:15:25<25:16:06,  7.12s/it]
 55%|█████▍    | 15311/28080 [30:15:33<25:21:23,  7.15s/it]
                                                           
{'loss': 0.6173, 'learning_rate': 0.00022554324453158588, 'epoch': 6.54}

 55%|█████▍    | 15311/28080 [30:15:33<25:21:23,  7.15s/it]
 55%|█████▍    | 15312/28080 [30:15:40<25:19:43,  7.14s/it]
                                                           
{'loss': 0.6237, 'learning_rate': 0.00022551454729929278, 'epoch': 6.54}

 55%|█████▍    | 15312/28080 [30:15:40<25:19:43,  7.14s/it]
 55%|█████▍    | 15313/28080 [30:15:47<25:25:03,  7.17s/it]
                                                           
{'loss': 0.6191, 'learning_rate': 0.00022548585039275352, 'epoch': 6.54}

 55%|█████▍    | 15313/28080 [30:15:47<25:25:03,  7.17s/it]
 55%|█████▍    | 15314/28080 [30:15:54<25:22:04,  7.15s/it]
                                                           
{'loss': 0.628, 'learning_rate': 0.00022545715381234956, 'epoch': 6.54}

 55%|█████▍    | 15314/28080 [30:15:54<25:22:04,  7.15s/it]
 55%|█████▍    | 15315/28080 [30:16:01<25:21:56,  7.15s/it]
                                                           
{'loss': 0.6108, 'learning_rate': 0.00022542845755846297, 'epoch': 6.54}

 55%|█████▍    | 15315/28080 [30:16:01<25:21:56,  7.15s/it]
 55%|█████▍    | 15316/28080 [30:16:08<25:13:26,  7.11s/it]
                                                           
{'loss': 0.6114, 'learning_rate': 0.00022539976163147535, 'epoch': 6.54}

 55%|█████▍    | 15316/28080 [30:16:08<25:13:26,  7.11s/it]
 55%|█████▍    | 15317/28080 [30:16:15<25:11:09,  7.10s/it]
                                                           
{'loss': 0.6036, 'learning_rate': 0.00022537106603176858, 'epoch': 6.54}

 55%|█████▍    | 15317/28080 [30:16:15<25:11:09,  7.10s/it]
 55%|█████▍    | 15318/28080 [30:16:22<25:09:22,  7.10s/it]
                                                           
{'loss': 0.6168, 'learning_rate': 0.0002253423707597243, 'epoch': 6.54}

 55%|█████▍    | 15318/28080 [30:16:22<25:09:22,  7.10s/it]
 55%|█████▍    | 15319/28080 [30:16:30<25:11:06,  7.10s/it]
                                                           
{'loss': 0.603, 'learning_rate': 0.0002253136758157244, 'epoch': 6.54}

 55%|█████▍    | 15319/28080 [30:16:30<25:11:06,  7.10s/it]
 55%|█████▍    | 15320/28080 [30:16:37<25:17:49,  7.14s/it]
                                                           
{'loss': 0.5948, 'learning_rate': 0.00022528498120015053, 'epoch': 6.54}

 55%|█████▍    | 15320/28080 [30:16:37<25:17:49,  7.14s/it]
 55%|█████▍    | 15321/28080 [30:16:44<25:21:21,  7.15s/it]
                                                           
{'loss': 0.617, 'learning_rate': 0.00022525628691338453, 'epoch': 6.54}

 55%|█████▍    | 15321/28080 [30:16:44<25:21:21,  7.15s/it]
 55%|█████▍    | 15322/28080 [30:16:51<25:16:28,  7.13s/it]
                                                           
{'loss': 0.613, 'learning_rate': 0.00022522759295580806, 'epoch': 6.55}

 55%|█████▍    | 15322/28080 [30:16:51<25:16:28,  7.13s/it]
 55%|█████▍    | 15323/28080 [30:16:58<25:18:12,  7.14s/it]
                                                           
{'loss': 0.6297, 'learning_rate': 0.00022519889932780298, 'epoch': 6.55}

 55%|█████▍    | 15323/28080 [30:16:58<25:18:12,  7.14s/it]
 55%|█████▍    | 15324/28080 [30:17:05<25:16:43,  7.13s/it]
                                                           
{'loss': 0.6243, 'learning_rate': 0.00022517020602975092, 'epoch': 6.55}

 55%|█████▍    | 15324/28080 [30:17:05<25:16:43,  7.13s/it]
 55%|█████▍    | 15325/28080 [30:17:13<25:17:22,  7.14s/it]
                                                           
{'loss': 0.6319, 'learning_rate': 0.00022514151306203363, 'epoch': 6.55}

 55%|█████▍    | 15325/28080 [30:17:13<25:17:22,  7.14s/it]
 55%|█████▍    | 15326/28080 [30:17:20<25:22:49,  7.16s/it]
                                                           
{'loss': 0.6128, 'learning_rate': 0.0002251128204250329, 'epoch': 6.55}

 55%|█████▍    | 15326/28080 [30:17:20<25:22:49,  7.16s/it]
 55%|█████▍    | 15327/28080 [30:17:27<25:22:24,  7.16s/it]
                                                           
{'loss': 0.5963, 'learning_rate': 0.00022508412811913036, 'epoch': 6.55}

 55%|█████▍    | 15327/28080 [30:17:27<25:22:24,  7.16s/it]
 55%|█████▍    | 15328/28080 [30:17:34<25:17:10,  7.14s/it]
                                                           
{'loss': 0.6133, 'learning_rate': 0.00022505543614470785, 'epoch': 6.55}

 55%|█████▍    | 15328/28080 [30:17:34<25:17:10,  7.14s/it]
 55%|█████▍    | 15329/28080 [30:17:41<25:11:12,  7.11s/it]
                                                           
{'loss': 0.6244, 'learning_rate': 0.00022502674450214694, 'epoch': 6.55}

 55%|█████▍    | 15329/28080 [30:17:41<25:11:12,  7.11s/it]
 55%|█████▍    | 15330/28080 [30:17:48<25:14:45,  7.13s/it]
                                                           
{'loss': 0.6118, 'learning_rate': 0.0002249980531918296, 'epoch': 6.55}

 55%|█████▍    | 15330/28080 [30:17:48<25:14:45,  7.13s/it]
 55%|█████▍    | 15331/28080 [30:17:55<25:11:14,  7.11s/it]
                                                           
{'loss': 0.6069, 'learning_rate': 0.00022496936221413715, 'epoch': 6.55}

 55%|█████▍    | 15331/28080 [30:17:55<25:11:14,  7.11s/it]
 55%|█████▍    | 15332/28080 [30:18:02<25:14:18,  7.13s/it]
                                                           
{'loss': 0.603, 'learning_rate': 0.00022494067156945166, 'epoch': 6.55}

 55%|█████▍    | 15332/28080 [30:18:02<25:14:18,  7.13s/it]
 55%|█████▍    | 15333/28080 [30:18:10<25:11:54,  7.12s/it]
                                                           
{'loss': 0.6027, 'learning_rate': 0.00022491198125815465, 'epoch': 6.55}

 55%|█████▍    | 15333/28080 [30:18:10<25:11:54,  7.12s/it]
 55%|█████▍    | 15334/28080 [30:18:17<25:16:07,  7.14s/it]
                                                           
{'loss': 0.6004, 'learning_rate': 0.00022488329128062787, 'epoch': 6.55}

 55%|█████▍    | 15334/28080 [30:18:17<25:16:07,  7.14s/it]
 55%|█████▍    | 15335/28080 [30:18:24<25:20:19,  7.16s/it]
                                                           
{'loss': 0.6329, 'learning_rate': 0.00022485460163725293, 'epoch': 6.55}

 55%|█████▍    | 15335/28080 [30:18:24<25:20:19,  7.16s/it]
 55%|█████▍    | 15336/28080 [30:18:31<25:18:30,  7.15s/it]
                                                           
{'loss': 0.5991, 'learning_rate': 0.00022482591232841166, 'epoch': 6.55}

 55%|█████▍    | 15336/28080 [30:18:31<25:18:30,  7.15s/it]
 55%|█████▍    | 15337/28080 [30:18:38<25:14:51,  7.13s/it]
                                                           
{'loss': 0.6333, 'learning_rate': 0.00022479722335448556, 'epoch': 6.55}

 55%|█████▍    | 15337/28080 [30:18:38<25:14:51,  7.13s/it]
 55%|█████▍    | 15338/28080 [30:18:45<25:15:44,  7.14s/it]
                                                           
{'loss': 0.6136, 'learning_rate': 0.0002247685347158565, 'epoch': 6.55}

 55%|█████▍    | 15338/28080 [30:18:45<25:15:44,  7.14s/it]
 55%|█████▍    | 15339/28080 [30:18:53<25:21:37,  7.17s/it]
                                                           
{'loss': 0.6258, 'learning_rate': 0.000224739846412906, 'epoch': 6.55}

 55%|█████▍    | 15339/28080 [30:18:53<25:21:37,  7.17s/it]
 55%|█████▍    | 15340/28080 [30:19:00<25:20:40,  7.16s/it]
                                                           
{'loss': 0.6239, 'learning_rate': 0.0002247111584460158, 'epoch': 6.55}

 55%|█████▍    | 15340/28080 [30:19:00<25:20:40,  7.16s/it]
 55%|█████▍    | 15341/28080 [30:19:07<25:16:56,  7.14s/it]
                                                           
{'loss': 0.6333, 'learning_rate': 0.00022468247081556744, 'epoch': 6.55}

 55%|█████▍    | 15341/28080 [30:19:07<25:16:56,  7.14s/it]
 55%|█████▍    | 15342/28080 [30:19:14<25:25:24,  7.19s/it]
                                                           
{'loss': 0.602, 'learning_rate': 0.0002246537835219429, 'epoch': 6.55}

 55%|█████▍    | 15342/28080 [30:19:14<25:25:24,  7.19s/it]
 55%|█████▍    | 15343/28080 [30:19:21<25:18:25,  7.15s/it]
                                                           
{'loss': 0.6066, 'learning_rate': 0.0002246250965655234, 'epoch': 6.55}

 55%|█████▍    | 15343/28080 [30:19:21<25:18:25,  7.15s/it]
 55%|█████▍    | 15344/28080 [30:19:28<25:17:38,  7.15s/it]
                                                           
{'loss': 0.6348, 'learning_rate': 0.00022459640994669102, 'epoch': 6.55}

 55%|█████▍    | 15344/28080 [30:19:28<25:17:38,  7.15s/it]
 55%|█████▍    | 15345/28080 [30:19:35<25:21:09,  7.17s/it]
                                                           
{'loss': 0.6153, 'learning_rate': 0.000224567723665827, 'epoch': 6.56}

 55%|█████▍    | 15345/28080 [30:19:35<25:21:09,  7.17s/it]
 55%|█████▍    | 15346/28080 [30:19:43<25:15:58,  7.14s/it]
                                                           
{'loss': 0.6102, 'learning_rate': 0.00022453903772331332, 'epoch': 6.56}

 55%|█████▍    | 15346/28080 [30:19:43<25:15:58,  7.14s/it]
 55%|█████▍    | 15347/28080 [30:19:50<25:12:11,  7.13s/it]
                                                           
{'loss': 0.6034, 'learning_rate': 0.00022451035211953143, 'epoch': 6.56}

 55%|█████▍    | 15347/28080 [30:19:50<25:12:11,  7.13s/it]
 55%|█████▍    | 15348/28080 [30:19:57<25:16:13,  7.15s/it]
                                                           
{'loss': 0.6203, 'learning_rate': 0.000224481666854863, 'epoch': 6.56}

 55%|█████▍    | 15348/28080 [30:19:57<25:16:13,  7.15s/it]
 55%|█████▍    | 15349/28080 [30:20:04<25:13:56,  7.14s/it]
                                                           
{'loss': 0.6246, 'learning_rate': 0.00022445298192968972, 'epoch': 6.56}

 55%|█████▍    | 15349/28080 [30:20:04<25:13:56,  7.14s/it]
 55%|█████▍    | 15350/28080 [30:20:11<25:05:37,  7.10s/it]
                                                           
{'loss': 0.6234, 'learning_rate': 0.0002244242973443931, 'epoch': 6.56}

 55%|█████▍    | 15350/28080 [30:20:11<25:05:37,  7.10s/it]
 55%|█████▍    | 15351/28080 [30:20:18<25:04:03,  7.09s/it]
                                                           
{'loss': 0.6278, 'learning_rate': 0.00022439561309935485, 'epoch': 6.56}

 55%|█████▍    | 15351/28080 [30:20:18<25:04:03,  7.09s/it]
 55%|█████▍    | 15352/28080 [30:20:25<25:10:37,  7.12s/it]
                                                           
{'loss': 0.6254, 'learning_rate': 0.00022436692919495656, 'epoch': 6.56}

 55%|█████▍    | 15352/28080 [30:20:25<25:10:37,  7.12s/it]
 55%|█████▍    | 15353/28080 [30:20:32<25:05:27,  7.10s/it]
                                                           
{'loss': 0.6349, 'learning_rate': 0.0002243382456315798, 'epoch': 6.56}

 55%|█████▍    | 15353/28080 [30:20:32<25:05:27,  7.10s/it]
 55%|█████▍    | 15354/28080 [30:20:39<24:59:38,  7.07s/it]
                                                           
{'loss': 0.6044, 'learning_rate': 0.0002243095624096062, 'epoch': 6.56}

 55%|█████▍    | 15354/28080 [30:20:39<24:59:38,  7.07s/it]
 55%|█████▍    | 15355/28080 [30:20:46<25:01:04,  7.08s/it]
                                                           
{'loss': 0.606, 'learning_rate': 0.00022428087952941744, 'epoch': 6.56}

 55%|█████▍    | 15355/28080 [30:20:46<25:01:04,  7.08s/it]
 55%|█████▍    | 15356/28080 [30:20:53<25:04:30,  7.09s/it]
                                                           
{'loss': 0.5979, 'learning_rate': 0.00022425219699139496, 'epoch': 6.56}

 55%|█████▍    | 15356/28080 [30:20:54<25:04:30,  7.09s/it]
 55%|█████▍    | 15357/28080 [30:21:01<25:09:18,  7.12s/it]
                                                           
{'loss': 0.6089, 'learning_rate': 0.0002242235147959205, 'epoch': 6.56}

 55%|█████▍    | 15357/28080 [30:21:01<25:09:18,  7.12s/it]
 55%|█████▍    | 15358/28080 [30:21:08<25:07:04,  7.11s/it]
                                                           
{'loss': 0.6249, 'learning_rate': 0.00022419483294337553, 'epoch': 6.56}

 55%|█████▍    | 15358/28080 [30:21:08<25:07:04,  7.11s/it]
 55%|█████▍    | 15359/28080 [30:21:15<25:11:05,  7.13s/it]
                                                           
{'loss': 0.6178, 'learning_rate': 0.00022416615143414176, 'epoch': 6.56}

 55%|█████▍    | 15359/28080 [30:21:15<25:11:05,  7.13s/it]
 55%|█████▍    | 15360/28080 [30:21:22<25:08:44,  7.12s/it]
                                                           
{'loss': 0.6063, 'learning_rate': 0.00022413747026860055, 'epoch': 6.56}

 55%|█████▍    | 15360/28080 [30:21:22<25:08:44,  7.12s/it]
 55%|█████▍    | 15361/28080 [30:21:29<25:13:16,  7.14s/it]
                                                           
{'loss': 0.5988, 'learning_rate': 0.00022410878944713382, 'epoch': 6.56}

 55%|█████▍    | 15361/28080 [30:21:29<25:13:16,  7.14s/it]
 55%|█████▍    | 15362/28080 [30:21:36<25:08:17,  7.12s/it]
                                                           
{'loss': 0.6068, 'learning_rate': 0.00022408010897012273, 'epoch': 6.56}

 55%|█████▍    | 15362/28080 [30:21:36<25:08:17,  7.12s/it]
 55%|█████▍    | 15363/28080 [30:21:43<25:08:17,  7.12s/it]
                                                           
{'loss': 0.5988, 'learning_rate': 0.0002240514288379492, 'epoch': 6.56}

 55%|█████▍    | 15363/28080 [30:21:43<25:08:17,  7.12s/it]
 55%|█████▍    | 15364/28080 [30:21:50<25:06:40,  7.11s/it]
                                                           
{'loss': 0.6038, 'learning_rate': 0.00022402274905099453, 'epoch': 6.56}

 55%|█████▍    | 15364/28080 [30:21:50<25:06:40,  7.11s/it]
 55%|█████▍    | 15365/28080 [30:21:58<25:09:09,  7.12s/it]
                                                           
{'loss': 0.6295, 'learning_rate': 0.00022399406960964046, 'epoch': 6.56}

 55%|█████▍    | 15365/28080 [30:21:58<25:09:09,  7.12s/it]
 55%|█████▍    | 15366/28080 [30:22:05<25:09:20,  7.12s/it]
                                                           
{'loss': 0.6231, 'learning_rate': 0.00022396539051426845, 'epoch': 6.56}

 55%|█████▍    | 15366/28080 [30:22:05<25:09:20,  7.12s/it]
 55%|█████▍    | 15367/28080 [30:22:12<25:03:46,  7.10s/it]
                                                           
{'loss': 0.6199, 'learning_rate': 0.00022393671176526009, 'epoch': 6.56}

 55%|█████▍    | 15367/28080 [30:22:12<25:03:46,  7.10s/it]
 55%|█████▍    | 15368/28080 [30:22:19<25:04:45,  7.10s/it]
                                                           
{'loss': 0.6288, 'learning_rate': 0.00022390803336299684, 'epoch': 6.57}

 55%|█████▍    | 15368/28080 [30:22:19<25:04:45,  7.10s/it]
 55%|█████▍    | 15369/28080 [30:22:26<25:08:14,  7.12s/it]
                                                           
{'loss': 0.6006, 'learning_rate': 0.00022387935530786033, 'epoch': 6.57}

 55%|█████▍    | 15369/28080 [30:22:26<25:08:14,  7.12s/it]
 55%|█████▍    | 15370/28080 [30:22:33<25:11:47,  7.14s/it]
                                                           
{'loss': 0.6153, 'learning_rate': 0.000223850677600232, 'epoch': 6.57}

 55%|█████▍    | 15370/28080 [30:22:33<25:11:47,  7.14s/it]
 55%|█████▍    | 15371/28080 [30:22:40<25:15:23,  7.15s/it]
                                                           
{'loss': 0.6109, 'learning_rate': 0.00022382200024049348, 'epoch': 6.57}

 55%|█████▍    | 15371/28080 [30:22:40<25:15:23,  7.15s/it]
 55%|█████▍    | 15372/28080 [30:22:47<25:06:52,  7.11s/it]
                                                           
{'loss': 0.6383, 'learning_rate': 0.00022379332322902616, 'epoch': 6.57}

 55%|█████▍    | 15372/28080 [30:22:47<25:06:52,  7.11s/it]
 55%|█████▍    | 15373/28080 [30:22:54<25:01:29,  7.09s/it]
                                                           
{'loss': 0.6321, 'learning_rate': 0.00022376464656621175, 'epoch': 6.57}

 55%|█████▍    | 15373/28080 [30:22:55<25:01:29,  7.09s/it]
 55%|█████▍    | 15374/28080 [30:23:02<25:03:26,  7.10s/it]
                                                           
{'loss': 0.611, 'learning_rate': 0.00022373597025243165, 'epoch': 6.57}

 55%|█████▍    | 15374/28080 [30:23:02<25:03:26,  7.10s/it]
 55%|█████▍    | 15375/28080 [30:23:09<25:07:37,  7.12s/it]
                                                           
{'loss': 0.6039, 'learning_rate': 0.0002237072942880673, 'epoch': 6.57}

 55%|█████▍    | 15375/28080 [30:23:09<25:07:37,  7.12s/it]
 55%|█████▍    | 15376/28080 [30:23:16<25:12:00,  7.14s/it]
                                                           
{'loss': 0.6084, 'learning_rate': 0.0002236786186735003, 'epoch': 6.57}

 55%|█████▍    | 15376/28080 [30:23:16<25:12:00,  7.14s/it]
 55%|█████▍    | 15377/28080 [30:23:23<25:17:23,  7.17s/it]
                                                           
{'loss': 0.631, 'learning_rate': 0.00022364994340911203, 'epoch': 6.57}

 55%|█████▍    | 15377/28080 [30:23:23<25:17:23,  7.17s/it]
 55%|█████▍    | 15378/28080 [30:23:30<25:13:40,  7.15s/it]
                                                           
{'loss': 0.6254, 'learning_rate': 0.00022362126849528427, 'epoch': 6.57}

 55%|█████▍    | 15378/28080 [30:23:30<25:13:40,  7.15s/it]
 55%|█████▍    | 15379/28080 [30:23:37<25:13:20,  7.15s/it]
                                                           
{'loss': 0.6147, 'learning_rate': 0.00022359259393239813, 'epoch': 6.57}

 55%|█████▍    | 15379/28080 [30:23:37<25:13:20,  7.15s/it]
 55%|█████▍    | 15380/28080 [30:23:45<25:15:29,  7.16s/it]
                                                           
{'loss': 0.6072, 'learning_rate': 0.00022356391972083543, 'epoch': 6.57}

 55%|█████▍    | 15380/28080 [30:23:45<25:15:29,  7.16s/it]
 55%|█████▍    | 15381/28080 [30:23:52<25:13:26,  7.15s/it]
                                                           
{'loss': 0.6294, 'learning_rate': 0.0002235352458609774, 'epoch': 6.57}

 55%|█████▍    | 15381/28080 [30:23:52<25:13:26,  7.15s/it]
 55%|█████▍    | 15382/28080 [30:23:59<25:08:29,  7.13s/it]
                                                           
{'loss': 0.6258, 'learning_rate': 0.0002235065723532057, 'epoch': 6.57}

 55%|█████▍    | 15382/28080 [30:23:59<25:08:29,  7.13s/it]
 55%|█████▍    | 15383/28080 [30:24:06<25:07:51,  7.13s/it]
                                                           
{'loss': 0.6173, 'learning_rate': 0.0002234778991979017, 'epoch': 6.57}

 55%|█████▍    | 15383/28080 [30:24:06<25:07:51,  7.13s/it]
 55%|█████▍    | 15384/28080 [30:24:13<25:05:26,  7.11s/it]
                                                           
{'loss': 0.6216, 'learning_rate': 0.00022344922639544687, 'epoch': 6.57}

 55%|█████▍    | 15384/28080 [30:24:13<25:05:26,  7.11s/it]
 55%|█████▍    | 15385/28080 [30:24:20<25:03:14,  7.10s/it]
                                                           
{'loss': 0.6141, 'learning_rate': 0.00022342055394622269, 'epoch': 6.57}

 55%|█████▍    | 15385/28080 [30:24:20<25:03:14,  7.10s/it]
 55%|█████▍    | 15386/28080 [30:24:27<25:08:42,  7.13s/it]
                                                           
{'loss': 0.6076, 'learning_rate': 0.00022339188185061066, 'epoch': 6.57}

 55%|█████▍    | 15386/28080 [30:24:27<25:08:42,  7.13s/it]
 55%|█████▍    | 15387/28080 [30:24:34<25:01:25,  7.10s/it]
                                                           
{'loss': 0.6264, 'learning_rate': 0.00022336321010899213, 'epoch': 6.57}

 55%|█████▍    | 15387/28080 [30:24:34<25:01:25,  7.10s/it]
 55%|█████▍    | 15388/28080 [30:24:42<25:07:09,  7.12s/it]
                                                           
{'loss': 0.6302, 'learning_rate': 0.0002233345387217487, 'epoch': 6.57}

 55%|█████▍    | 15388/28080 [30:24:42<25:07:09,  7.12s/it]
 55%|█████▍    | 15389/28080 [30:24:49<25:02:28,  7.10s/it]
                                                           
{'loss': 0.6253, 'learning_rate': 0.00022330586768926165, 'epoch': 6.57}

 55%|█████▍    | 15389/28080 [30:24:49<25:02:28,  7.10s/it]
 55%|█████▍    | 15390/28080 [30:24:56<25:00:27,  7.09s/it]
                                                           
{'loss': 0.6134, 'learning_rate': 0.0002232771970119125, 'epoch': 6.57}

 55%|█████▍    | 15390/28080 [30:24:56<25:00:27,  7.09s/it]
 55%|█████▍    | 15391/28080 [30:25:03<25:01:09,  7.10s/it]
                                                           
{'loss': 0.6157, 'learning_rate': 0.00022324852669008263, 'epoch': 6.57}

 55%|█████▍    | 15391/28080 [30:25:03<25:01:09,  7.10s/it]
 55%|█████▍    | 15392/28080 [30:25:10<25:02:46,  7.11s/it]
                                                           
{'loss': 0.6046, 'learning_rate': 0.00022321985672415365, 'epoch': 6.58}

 55%|█████▍    | 15392/28080 [30:25:10<25:02:46,  7.11s/it]
 55%|█████▍    | 15393/28080 [30:25:17<25:00:35,  7.10s/it]
                                                           
{'loss': 0.6286, 'learning_rate': 0.0002231911871145067, 'epoch': 6.58}

 55%|█████▍    | 15393/28080 [30:25:17<25:00:35,  7.10s/it]
 55%|█████▍    | 15394/28080 [30:25:24<25:00:50,  7.10s/it]
                                                           
{'loss': 0.6192, 'learning_rate': 0.00022316251786152344, 'epoch': 6.58}

 55%|█████▍    | 15394/28080 [30:25:24<25:00:50,  7.10s/it]
 55%|█████▍    | 15395/28080 [30:25:31<25:07:50,  7.13s/it]
                                                           
{'loss': 0.6173, 'learning_rate': 0.00022313384896558515, 'epoch': 6.58}

 55%|█████▍    | 15395/28080 [30:25:31<25:07:50,  7.13s/it]
 55%|█████▍    | 15396/28080 [30:25:38<25:05:38,  7.12s/it]
                                                           
{'loss': 0.6265, 'learning_rate': 0.00022310518042707332, 'epoch': 6.58}

 55%|█████▍    | 15396/28080 [30:25:38<25:05:38,  7.12s/it]
 55%|█████▍    | 15397/28080 [30:25:46<25:12:24,  7.15s/it]
                                                           
{'loss': 0.6064, 'learning_rate': 0.00022307651224636927, 'epoch': 6.58}

 55%|█████▍    | 15397/28080 [30:25:46<25:12:24,  7.15s/it]
 55%|█████▍    | 15398/28080 [30:25:53<25:15:59,  7.17s/it]
                                                           
{'loss': 0.5968, 'learning_rate': 0.0002230478444238545, 'epoch': 6.58}

 55%|█████▍    | 15398/28080 [30:25:53<25:15:59,  7.17s/it]
 55%|█████▍    | 15399/28080 [30:26:00<25:12:39,  7.16s/it]
                                                           
{'loss': 0.6106, 'learning_rate': 0.0002230191769599104, 'epoch': 6.58}

 55%|█████▍    | 15399/28080 [30:26:00<25:12:39,  7.16s/it]
 55%|█████▍    | 15400/28080 [30:26:07<25:08:51,  7.14s/it]
                                                           
{'loss': 0.6131, 'learning_rate': 0.0002229905098549182, 'epoch': 6.58}

 55%|█████▍    | 15400/28080 [30:26:07<25:08:51,  7.14s/it]
 55%|█████▍    | 15401/28080 [30:26:14<25:11:52,  7.15s/it]
                                                           
{'loss': 0.6035, 'learning_rate': 0.0002229618431092595, 'epoch': 6.58}

 55%|█████▍    | 15401/28080 [30:26:14<25:11:52,  7.15s/it]
 55%|█████▍    | 15402/28080 [30:26:21<25:13:31,  7.16s/it]
                                                           
{'loss': 0.5978, 'learning_rate': 0.0002229331767233155, 'epoch': 6.58}

 55%|█████▍    | 15402/28080 [30:26:21<25:13:31,  7.16s/it]
 55%|█████▍    | 15403/28080 [30:26:29<25:13:30,  7.16s/it]
                                                           
{'loss': 0.6147, 'learning_rate': 0.00022290451069746772, 'epoch': 6.58}

 55%|█████▍    | 15403/28080 [30:26:29<25:13:30,  7.16s/it]
 55%|█████▍    | 15404/28080 [30:26:36<25:11:56,  7.16s/it]
                                                           
{'loss': 0.5902, 'learning_rate': 0.00022287584503209742, 'epoch': 6.58}

 55%|█████▍    | 15404/28080 [30:26:36<25:11:56,  7.16s/it]
 55%|█████▍    | 15405/28080 [30:26:43<25:07:34,  7.14s/it]
                                                           
{'loss': 0.6209, 'learning_rate': 0.0002228471797275861, 'epoch': 6.58}

 55%|█████▍    | 15405/28080 [30:26:43<25:07:34,  7.14s/it]
 55%|█████▍    | 15406/28080 [30:26:50<24:57:36,  7.09s/it]
                                                           
{'loss': 0.6181, 'learning_rate': 0.00022281851478431495, 'epoch': 6.58}

 55%|█████▍    | 15406/28080 [30:26:50<24:57:36,  7.09s/it]
 55%|█████▍    | 15407/28080 [30:26:57<24:48:30,  7.05s/it]
                                                           
{'loss': 0.6226, 'learning_rate': 0.00022278985020266552, 'epoch': 6.58}

 55%|█████▍    | 15407/28080 [30:26:57<24:48:30,  7.05s/it]
 55%|█████▍    | 15408/28080 [30:27:04<24:56:23,  7.09s/it]
                                                           
{'loss': 0.6053, 'learning_rate': 0.0002227611859830189, 'epoch': 6.58}

 55%|█████▍    | 15408/28080 [30:27:04<24:56:23,  7.09s/it]
 55%|█████▍    | 15409/28080 [30:27:11<25:00:24,  7.10s/it]
                                                           
{'loss': 0.602, 'learning_rate': 0.00022273252212575678, 'epoch': 6.58}

 55%|█████▍    | 15409/28080 [30:27:11<25:00:24,  7.10s/it]
 55%|█████▍    | 15410/28080 [30:27:18<24:59:42,  7.10s/it]
                                                           
{'loss': 0.5885, 'learning_rate': 0.00022270385863126015, 'epoch': 6.58}

 55%|█████▍    | 15410/28080 [30:27:18<24:59:42,  7.10s/it]
 55%|█████▍    | 15411/28080 [30:27:25<25:02:43,  7.12s/it]
                                                           
{'loss': 0.626, 'learning_rate': 0.00022267519549991067, 'epoch': 6.58}

 55%|█████▍    | 15411/28080 [30:27:25<25:02:43,  7.12s/it]
 55%|█████▍    | 15412/28080 [30:27:32<25:02:41,  7.12s/it]
                                                           
{'loss': 0.6065, 'learning_rate': 0.00022264653273208944, 'epoch': 6.58}

 55%|█████▍    | 15412/28080 [30:27:32<25:02:41,  7.12s/it]
 55%|█████▍    | 15413/28080 [30:27:40<24:59:51,  7.10s/it]
                                                           
{'loss': 0.6167, 'learning_rate': 0.00022261787032817792, 'epoch': 6.58}

 55%|█████▍    | 15413/28080 [30:27:40<24:59:51,  7.10s/it]
 55%|█████▍    | 15414/28080 [30:27:47<25:02:40,  7.12s/it]
                                                           
{'loss': 0.6168, 'learning_rate': 0.00022258920828855736, 'epoch': 6.58}

 55%|█████▍    | 15414/28080 [30:27:47<25:02:40,  7.12s/it]
 55%|█████▍    | 15415/28080 [30:27:54<25:05:13,  7.13s/it]
                                                           
{'loss': 0.6143, 'learning_rate': 0.00022256054661360915, 'epoch': 6.59}

 55%|█████▍    | 15415/28080 [30:27:54<25:05:13,  7.13s/it]
 55%|█████▍    | 15416/28080 [30:28:01<25:08:33,  7.15s/it]
                                                           
{'loss': 0.6094, 'learning_rate': 0.0002225318853037145, 'epoch': 6.59}

 55%|█████▍    | 15416/28080 [30:28:01<25:08:33,  7.15s/it]
 55%|█████▍    | 15417/28080 [30:28:08<25:00:01,  7.11s/it]
                                                           
{'loss': 0.6244, 'learning_rate': 0.00022250322435925481, 'epoch': 6.59}

 55%|█████▍    | 15417/28080 [30:28:08<25:00:01,  7.11s/it]
 55%|█████▍    | 15418/28080 [30:28:15<25:03:50,  7.13s/it]
                                                           
{'loss': 0.6045, 'learning_rate': 0.00022247456378061135, 'epoch': 6.59}

 55%|█████▍    | 15418/28080 [30:28:15<25:03:50,  7.13s/it]
 55%|█████▍    | 15419/28080 [30:28:22<25:07:01,  7.14s/it]
                                                           
{'loss': 0.6111, 'learning_rate': 0.00022244590356816543, 'epoch': 6.59}

 55%|█████▍    | 15419/28080 [30:28:22<25:07:01,  7.14s/it]
 55%|█████▍    | 15420/28080 [30:28:30<25:11:37,  7.16s/it]
                                                           
{'loss': 0.6025, 'learning_rate': 0.00022241724372229832, 'epoch': 6.59}

 55%|█████▍    | 15420/28080 [30:28:30<25:11:37,  7.16s/it]
 55%|█████▍    | 15421/28080 [30:28:37<25:11:30,  7.16s/it]
                                                           
{'loss': 0.6045, 'learning_rate': 0.00022238858424339134, 'epoch': 6.59}

 55%|█████▍    | 15421/28080 [30:28:37<25:11:30,  7.16s/it]
 55%|█████▍    | 15422/28080 [30:28:44<25:04:43,  7.13s/it]
                                                           
{'loss': 0.6186, 'learning_rate': 0.00022235992513182568, 'epoch': 6.59}

 55%|█████▍    | 15422/28080 [30:28:44<25:04:43,  7.13s/it]
 55%|█████▍    | 15423/28080 [30:28:51<25:09:21,  7.16s/it]
                                                           
{'loss': 0.5901, 'learning_rate': 0.00022233126638798286, 'epoch': 6.59}

 55%|█████▍    | 15423/28080 [30:28:51<25:09:21,  7.16s/it]
 55%|█████▍    | 15424/28080 [30:28:58<25:00:38,  7.11s/it]
                                                           
{'loss': 0.6166, 'learning_rate': 0.00022230260801224395, 'epoch': 6.59}

 55%|█████▍    | 15424/28080 [30:28:58<25:00:38,  7.11s/it]
 55%|█████▍    | 15425/28080 [30:29:05<25:01:20,  7.12s/it]
                                                           
{'loss': 0.6539, 'learning_rate': 0.00022227395000499014, 'epoch': 6.59}

 55%|█████▍    | 15425/28080 [30:29:05<25:01:20,  7.12s/it]
 55%|█████▍    | 15426/28080 [30:29:12<25:01:02,  7.12s/it]
                                                           
{'loss': 0.623, 'learning_rate': 0.00022224529236660302, 'epoch': 6.59}

 55%|█████▍    | 15426/28080 [30:29:12<25:01:02,  7.12s/it]
 55%|█████▍    | 15427/28080 [30:29:19<25:03:12,  7.13s/it]
                                                           
{'loss': 0.6007, 'learning_rate': 0.00022221663509746346, 'epoch': 6.59}

 55%|█████▍    | 15427/28080 [30:29:19<25:03:12,  7.13s/it]
 55%|█████▍    | 15428/28080 [30:29:27<25:08:32,  7.15s/it]
                                                           
{'loss': 0.6094, 'learning_rate': 0.00022218797819795305, 'epoch': 6.59}

 55%|█████▍    | 15428/28080 [30:29:27<25:08:32,  7.15s/it]
 55%|█████▍    | 15429/28080 [30:29:34<25:11:14,  7.17s/it]
                                                           
{'loss': 0.6065, 'learning_rate': 0.00022215932166845276, 'epoch': 6.59}

 55%|█████▍    | 15429/28080 [30:29:34<25:11:14,  7.17s/it]
 55%|█████▍    | 15430/28080 [30:29:41<25:08:15,  7.15s/it]
                                                           
{'loss': 0.6127, 'learning_rate': 0.00022213066550934407, 'epoch': 6.59}

 55%|█████▍    | 15430/28080 [30:29:41<25:08:15,  7.15s/it]
 55%|█████▍    | 15431/28080 [30:29:48<25:12:32,  7.17s/it]
                                                           
{'loss': 0.6013, 'learning_rate': 0.0002221020097210081, 'epoch': 6.59}

 55%|█████▍    | 15431/28080 [30:29:48<25:12:32,  7.17s/it]
 55%|█████▍    | 15432/28080 [30:29:55<25:10:19,  7.16s/it]
                                                           
{'loss': 0.6244, 'learning_rate': 0.00022207335430382615, 'epoch': 6.59}

 55%|█████▍    | 15432/28080 [30:29:55<25:10:19,  7.16s/it]
 55%|█████▍    | 15433/28080 [30:30:02<25:05:52,  7.14s/it]
                                                           
{'loss': 0.594, 'learning_rate': 0.00022204469925817934, 'epoch': 6.59}

 55%|█████▍    | 15433/28080 [30:30:02<25:05:52,  7.14s/it]
 55%|█████▍    | 15434/28080 [30:30:10<25:12:07,  7.17s/it]
                                                           
{'loss': 0.6179, 'learning_rate': 0.00022201604458444904, 'epoch': 6.59}

 55%|█████▍    | 15434/28080 [30:30:10<25:12:07,  7.17s/it]
 55%|█████▍    | 15435/28080 [30:30:17<25:11:41,  7.17s/it]
                                                           
{'loss': 0.6253, 'learning_rate': 0.00022198739028301634, 'epoch': 6.59}

 55%|█████▍    | 15435/28080 [30:30:17<25:11:41,  7.17s/it]
 55%|█████▍    | 15436/28080 [30:30:24<25:01:13,  7.12s/it]
                                                           
{'loss': 0.63, 'learning_rate': 0.00022195873635426255, 'epoch': 6.59}

 55%|█████▍    | 15436/28080 [30:30:24<25:01:13,  7.12s/it]
 55%|█████▍    | 15437/28080 [30:30:31<25:00:18,  7.12s/it]
                                                           
{'loss': 0.6052, 'learning_rate': 0.0002219300827985688, 'epoch': 6.59}

 55%|█████▍    | 15437/28080 [30:30:31<25:00:18,  7.12s/it]
 55%|█████▍    | 15438/28080 [30:30:38<24:49:05,  7.07s/it]
                                                           
{'loss': 0.6264, 'learning_rate': 0.00022190142961631641, 'epoch': 6.59}

 55%|█████▍    | 15438/28080 [30:30:38<24:49:05,  7.07s/it]
 55%|█████▍    | 15439/28080 [30:30:45<25:01:23,  7.13s/it]
                                                           
{'loss': 0.6053, 'learning_rate': 0.0002218727768078864, 'epoch': 6.6}

 55%|█████▍    | 15439/28080 [30:30:45<25:01:23,  7.13s/it]
 55%|█████▍    | 15440/28080 [30:30:52<24:51:57,  7.08s/it]
                                                           
{'loss': 0.6211, 'learning_rate': 0.00022184412437366023, 'epoch': 6.6}

 55%|█████▍    | 15440/28080 [30:30:52<24:51:57,  7.08s/it]
 55%|█████▍    | 15441/28080 [30:30:59<24:57:59,  7.11s/it]
                                                           
{'loss': 0.606, 'learning_rate': 0.00022181547231401878, 'epoch': 6.6}

 55%|█████▍    | 15441/28080 [30:30:59<24:57:59,  7.11s/it]
 55%|█████▍    | 15442/28080 [30:31:06<24:58:06,  7.11s/it]
                                                           
{'loss': 0.5966, 'learning_rate': 0.0002217868206293435, 'epoch': 6.6}

 55%|█████▍    | 15442/28080 [30:31:06<24:58:06,  7.11s/it]
 55%|█████▍    | 15443/28080 [30:31:14<24:57:38,  7.11s/it]
                                                           
{'loss': 0.6091, 'learning_rate': 0.0002217581693200154, 'epoch': 6.6}

 55%|█████▍    | 15443/28080 [30:31:14<24:57:38,  7.11s/it]
 55%|█████▌    | 15444/28080 [30:31:21<24:59:41,  7.12s/it]
                                                           
{'loss': 0.618, 'learning_rate': 0.0002217295183864158, 'epoch': 6.6}

 55%|█████▌    | 15444/28080 [30:31:21<24:59:41,  7.12s/it]
 55%|█████▌    | 15445/28080 [30:31:28<24:58:20,  7.12s/it]
                                                           
{'loss': 0.6306, 'learning_rate': 0.00022170086782892571, 'epoch': 6.6}

 55%|█████▌    | 15445/28080 [30:31:28<24:58:20,  7.12s/it]
 55%|█████▌    | 15446/28080 [30:31:35<25:05:44,  7.15s/it]
                                                           
{'loss': 0.6101, 'learning_rate': 0.00022167221764792644, 'epoch': 6.6}

 55%|█████▌    | 15446/28080 [30:31:35<25:05:44,  7.15s/it]
 55%|█████▌    | 15447/28080 [30:31:42<25:03:26,  7.14s/it]
                                                           
{'loss': 0.6156, 'learning_rate': 0.00022164356784379905, 'epoch': 6.6}

 55%|█████▌    | 15447/28080 [30:31:42<25:03:26,  7.14s/it]
 55%|█████▌    | 15448/28080 [30:31:49<25:00:10,  7.13s/it]
                                                           
{'loss': 0.6195, 'learning_rate': 0.0002216149184169248, 'epoch': 6.6}

 55%|█████▌    | 15448/28080 [30:31:49<25:00:10,  7.13s/it]
 55%|█████▌    | 15449/28080 [30:31:56<25:05:07,  7.15s/it]
                                                           
{'loss': 0.5911, 'learning_rate': 0.00022158626936768475, 'epoch': 6.6}

 55%|█████▌    | 15449/28080 [30:31:56<25:05:07,  7.15s/it]
 55%|█████▌    | 15450/28080 [30:32:04<25:00:46,  7.13s/it]
                                                           
{'loss': 0.6133, 'learning_rate': 0.00022155762069646004, 'epoch': 6.6}

 55%|█████▌    | 15450/28080 [30:32:04<25:00:46,  7.13s/it]
 55%|█████▌    | 15451/28080 [30:32:11<25:03:58,  7.15s/it]
                                                           
{'loss': 0.6054, 'learning_rate': 0.00022152897240363187, 'epoch': 6.6}

 55%|█████▌    | 15451/28080 [30:32:11<25:03:58,  7.15s/it]
 55%|█████▌    | 15452/28080 [30:32:18<25:02:37,  7.14s/it]
                                                           
{'loss': 0.6176, 'learning_rate': 0.00022150032448958133, 'epoch': 6.6}

 55%|█████▌    | 15452/28080 [30:32:18<25:02:37,  7.14s/it]
 55%|█████▌    | 15453/28080 [30:32:25<25:02:11,  7.14s/it]
                                                           
{'loss': 0.6162, 'learning_rate': 0.00022147167695468962, 'epoch': 6.6}

 55%|█████▌    | 15453/28080 [30:32:25<25:02:11,  7.14s/it]
 55%|█████▌    | 15454/28080 [30:32:32<24:58:21,  7.12s/it]
                                                           
{'loss': 0.5827, 'learning_rate': 0.00022144302979933776, 'epoch': 6.6}

 55%|█████▌    | 15454/28080 [30:32:32<24:58:21,  7.12s/it]
 55%|█████▌    | 15455/28080 [30:32:39<24:55:56,  7.11s/it]
                                                           
{'loss': 0.616, 'learning_rate': 0.00022141438302390696, 'epoch': 6.6}

 55%|█████▌    | 15455/28080 [30:32:39<24:55:56,  7.11s/it]
 55%|█████▌    | 15456/28080 [30:32:46<25:01:41,  7.14s/it]
                                                           
{'loss': 0.6176, 'learning_rate': 0.0002213857366287782, 'epoch': 6.6}

 55%|█████▌    | 15456/28080 [30:32:46<25:01:41,  7.14s/it]
 55%|█████▌    | 15457/28080 [30:32:53<24:57:49,  7.12s/it]
                                                           
{'loss': 0.607, 'learning_rate': 0.00022135709061433287, 'epoch': 6.6}

 55%|█████▌    | 15457/28080 [30:32:53<24:57:49,  7.12s/it]
 55%|█████▌    | 15458/28080 [30:33:01<25:05:00,  7.15s/it]
                                                           
{'loss': 0.6076, 'learning_rate': 0.00022132844498095176, 'epoch': 6.6}

 55%|█████▌    | 15458/28080 [30:33:01<25:05:00,  7.15s/it]
 55%|█████▌    | 15459/28080 [30:33:08<25:05:39,  7.16s/it]
                                                           
{'loss': 0.6105, 'learning_rate': 0.00022129979972901624, 'epoch': 6.6}

 55%|█████▌    | 15459/28080 [30:33:08<25:05:39,  7.16s/it]
 55%|█████▌    | 15460/28080 [30:33:15<24:58:23,  7.12s/it]
                                                           
{'loss': 0.6156, 'learning_rate': 0.00022127115485890713, 'epoch': 6.6}

 55%|█████▌    | 15460/28080 [30:33:15<24:58:23,  7.12s/it]
 55%|█████▌    | 15461/28080 [30:33:22<24:57:09,  7.12s/it]
                                                           
{'loss': 0.5987, 'learning_rate': 0.00022124251037100576, 'epoch': 6.6}

 55%|█████▌    | 15461/28080 [30:33:22<24:57:09,  7.12s/it]
 55%|█████▌    | 15462/28080 [30:33:29<25:00:04,  7.13s/it]
                                                           
{'loss': 0.6343, 'learning_rate': 0.00022121386626569307, 'epoch': 6.61}

 55%|█████▌    | 15462/28080 [30:33:29<25:00:04,  7.13s/it]
 55%|█████▌    | 15463/28080 [30:33:36<25:01:48,  7.14s/it]
                                                           
{'loss': 0.6165, 'learning_rate': 0.00022118522254335025, 'epoch': 6.61}

 55%|█████▌    | 15463/28080 [30:33:36<25:01:48,  7.14s/it]
 55%|█████▌    | 15464/28080 [30:33:43<24:56:37,  7.12s/it]
                                                           
{'loss': 0.6081, 'learning_rate': 0.00022115657920435827, 'epoch': 6.61}

 55%|█████▌    | 15464/28080 [30:33:43<24:56:37,  7.12s/it]
 55%|█████▌    | 15465/28080 [30:33:50<24:54:21,  7.11s/it]
                                                           
{'loss': 0.6179, 'learning_rate': 0.0002211279362490983, 'epoch': 6.61}

 55%|█████▌    | 15465/28080 [30:33:50<24:54:21,  7.11s/it]
 55%|█████▌    | 15466/28080 [30:33:58<24:53:07,  7.10s/it]
                                                           
{'loss': 0.6129, 'learning_rate': 0.00022109929367795128, 'epoch': 6.61}

 55%|█████▌    | 15466/28080 [30:33:58<24:53:07,  7.10s/it]
 55%|█████▌    | 15467/28080 [30:34:05<24:58:00,  7.13s/it]
                                                           
{'loss': 0.5994, 'learning_rate': 0.00022107065149129843, 'epoch': 6.61}

 55%|█████▌    | 15467/28080 [30:34:05<24:58:00,  7.13s/it]
 55%|█████▌    | 15468/28080 [30:34:12<24:56:48,  7.12s/it]
                                                           
{'loss': 0.5998, 'learning_rate': 0.00022104200968952063, 'epoch': 6.61}

 55%|█████▌    | 15468/28080 [30:34:12<24:56:48,  7.12s/it]
 55%|█████▌    | 15469/28080 [30:34:19<25:00:30,  7.14s/it]
                                                           
{'loss': 0.6214, 'learning_rate': 0.00022101336827299908, 'epoch': 6.61}

 55%|█████▌    | 15469/28080 [30:34:19<25:00:30,  7.14s/it]
 55%|█████▌    | 15470/28080 [30:34:26<25:03:09,  7.15s/it]
                                                           
{'loss': 0.6306, 'learning_rate': 0.00022098472724211467, 'epoch': 6.61}

 55%|█████▌    | 15470/28080 [30:34:26<25:03:09,  7.15s/it]
 55%|█████▌    | 15471/28080 [30:34:33<25:08:09,  7.18s/it]
                                                           
{'loss': 0.6288, 'learning_rate': 0.0002209560865972487, 'epoch': 6.61}

 55%|█████▌    | 15471/28080 [30:34:33<25:08:09,  7.18s/it]
 55%|█████▌    | 15472/28080 [30:34:41<25:11:03,  7.19s/it]
                                                           
{'loss': 0.6026, 'learning_rate': 0.00022092744633878185, 'epoch': 6.61}

 55%|█████▌    | 15472/28080 [30:34:41<25:11:03,  7.19s/it]
 55%|█████▌    | 15473/28080 [30:34:48<25:13:19,  7.20s/it]
                                                           
{'loss': 0.6169, 'learning_rate': 0.00022089880646709541, 'epoch': 6.61}

 55%|█████▌    | 15473/28080 [30:34:48<25:13:19,  7.20s/it]
 55%|█████▌    | 15474/28080 [30:34:55<25:12:28,  7.20s/it]
                                                           
{'loss': 0.6092, 'learning_rate': 0.00022087016698257045, 'epoch': 6.61}

 55%|█████▌    | 15474/28080 [30:34:55<25:12:28,  7.20s/it]
 55%|█████▌    | 15475/28080 [30:35:02<24:58:47,  7.13s/it]
                                                           
{'loss': 0.6238, 'learning_rate': 0.00022084152788558767, 'epoch': 6.61}

 55%|█████▌    | 15475/28080 [30:35:02<24:58:47,  7.13s/it]
 55%|█████▌    | 15476/28080 [30:35:09<24:57:27,  7.13s/it]
                                                           
{'loss': 0.6337, 'learning_rate': 0.00022081288917652844, 'epoch': 6.61}

 55%|█████▌    | 15476/28080 [30:35:09<24:57:27,  7.13s/it]
 55%|█████▌    | 15477/28080 [30:35:16<24:56:11,  7.12s/it]
                                                           
{'loss': 0.6062, 'learning_rate': 0.00022078425085577346, 'epoch': 6.61}

 55%|█████▌    | 15477/28080 [30:35:16<24:56:11,  7.12s/it]
 55%|█████▌    | 15478/28080 [30:35:23<24:55:55,  7.12s/it]
                                                           
{'loss': 0.6607, 'learning_rate': 0.00022075561292370397, 'epoch': 6.61}

 55%|█████▌    | 15478/28080 [30:35:23<24:55:55,  7.12s/it]
 55%|█████▌    | 15479/28080 [30:35:30<24:49:38,  7.09s/it]
                                                           
{'loss': 0.6224, 'learning_rate': 0.00022072697538070085, 'epoch': 6.61}

 55%|█████▌    | 15479/28080 [30:35:30<24:49:38,  7.09s/it]
 55%|█████▌    | 15480/28080 [30:35:38<24:52:47,  7.11s/it]
                                                           
{'loss': 0.6247, 'learning_rate': 0.00022069833822714515, 'epoch': 6.61}

 55%|█████▌    | 15480/28080 [30:35:38<24:52:47,  7.11s/it]
 55%|█████▌    | 15481/28080 [30:35:45<24:56:12,  7.13s/it]
                                                           
{'loss': 0.6031, 'learning_rate': 0.0002206697014634178, 'epoch': 6.61}

 55%|█████▌    | 15481/28080 [30:35:45<24:56:12,  7.13s/it]
 55%|█████▌    | 15482/28080 [30:35:52<24:54:50,  7.12s/it]
                                                           
{'loss': 0.6142, 'learning_rate': 0.00022064106508989988, 'epoch': 6.61}

 55%|█████▌    | 15482/28080 [30:35:52<24:54:50,  7.12s/it]
 55%|█████▌    | 15483/28080 [30:35:59<24:58:14,  7.14s/it]
                                                           
{'loss': 0.6126, 'learning_rate': 0.0002206124291069722, 'epoch': 6.61}

 55%|█████▌    | 15483/28080 [30:35:59<24:58:14,  7.14s/it]
 55%|█████▌    | 15484/28080 [30:36:06<24:50:16,  7.10s/it]
                                                           
{'loss': 0.6246, 'learning_rate': 0.00022058379351501593, 'epoch': 6.61}

 55%|█████▌    | 15484/28080 [30:36:06<24:50:16,  7.10s/it]
 55%|█████▌    | 15485/28080 [30:36:13<24:52:17,  7.11s/it]
                                                           
{'loss': 0.6242, 'learning_rate': 0.00022055515831441186, 'epoch': 6.62}

 55%|█████▌    | 15485/28080 [30:36:13<24:52:17,  7.11s/it]
 55%|█████▌    | 15486/28080 [30:36:20<24:55:12,  7.12s/it]
                                                           
{'loss': 0.6199, 'learning_rate': 0.0002205265235055411, 'epoch': 6.62}

 55%|█████▌    | 15486/28080 [30:36:20<24:55:12,  7.12s/it]
 55%|█████▌    | 15487/28080 [30:36:27<24:56:01,  7.13s/it]
                                                           
{'loss': 0.6048, 'learning_rate': 0.00022049788908878442, 'epoch': 6.62}

 55%|█████▌    | 15487/28080 [30:36:27<24:56:01,  7.13s/it]
 55%|█████▌    | 15488/28080 [30:36:35<24:55:40,  7.13s/it]
                                                           
{'loss': 0.6076, 'learning_rate': 0.0002204692550645231, 'epoch': 6.62}

 55%|█████▌    | 15488/28080 [30:36:35<24:55:40,  7.13s/it]
 55%|█████▌    | 15489/28080 [30:36:42<24:52:09,  7.11s/it]
                                                           
{'loss': 0.6134, 'learning_rate': 0.00022044062143313764, 'epoch': 6.62}

 55%|█████▌    | 15489/28080 [30:36:42<24:52:09,  7.11s/it]
 55%|█████▌    | 15490/28080 [30:36:49<25:01:42,  7.16s/it]
                                                           
{'loss': 0.5973, 'learning_rate': 0.00022041198819500944, 'epoch': 6.62}

 55%|█████▌    | 15490/28080 [30:36:49<25:01:42,  7.16s/it]
 55%|█████▌    | 15491/28080 [30:36:56<25:00:19,  7.15s/it]
                                                           
{'loss': 0.5938, 'learning_rate': 0.00022038335535051902, 'epoch': 6.62}

 55%|█████▌    | 15491/28080 [30:36:56<25:00:19,  7.15s/it]
 55%|█████▌    | 15492/28080 [30:37:03<24:58:09,  7.14s/it]
                                                           
{'loss': 0.6066, 'learning_rate': 0.0002203547229000476, 'epoch': 6.62}

 55%|█████▌    | 15492/28080 [30:37:03<24:58:09,  7.14s/it]
 55%|█████▌    | 15493/28080 [30:37:10<24:55:06,  7.13s/it]
                                                           
{'loss': 0.5969, 'learning_rate': 0.00022032609084397597, 'epoch': 6.62}

 55%|█████▌    | 15493/28080 [30:37:10<24:55:06,  7.13s/it]
 55%|█████▌    | 15494/28080 [30:37:17<24:54:18,  7.12s/it]
                                                           
{'loss': 0.6246, 'learning_rate': 0.00022029745918268514, 'epoch': 6.62}

 55%|█████▌    | 15494/28080 [30:37:17<24:54:18,  7.12s/it]
 55%|█████▌    | 15495/28080 [30:37:25<24:56:57,  7.14s/it]
                                                           
{'loss': 0.5987, 'learning_rate': 0.00022026882791655595, 'epoch': 6.62}

 55%|█████▌    | 15495/28080 [30:37:25<24:56:57,  7.14s/it]
 55%|█████▌    | 15496/28080 [30:37:32<24:55:49,  7.13s/it]
                                                           
{'loss': 0.6217, 'learning_rate': 0.00022024019704596935, 'epoch': 6.62}

 55%|█████▌    | 15496/28080 [30:37:32<24:55:49,  7.13s/it]
 55%|█████▌    | 15497/28080 [30:37:39<24:57:18,  7.14s/it]
                                                           
{'loss': 0.595, 'learning_rate': 0.00022021156657130617, 'epoch': 6.62}

 55%|█████▌    | 15497/28080 [30:37:39<24:57:18,  7.14s/it]
 55%|█████▌    | 15498/28080 [30:37:46<24:54:02,  7.12s/it]
                                                           
{'loss': 0.6139, 'learning_rate': 0.00022018293649294743, 'epoch': 6.62}

 55%|█████▌    | 15498/28080 [30:37:46<24:54:02,  7.12s/it]
 55%|█████▌    | 15499/28080 [30:37:53<24:58:08,  7.14s/it]
                                                           
{'loss': 0.6029, 'learning_rate': 0.00022015430681127397, 'epoch': 6.62}

 55%|█████▌    | 15499/28080 [30:37:53<24:58:08,  7.14s/it]
 55%|█████▌    | 15500/28080 [30:38:00<25:00:09,  7.16s/it]
                                                           
{'loss': 0.5914, 'learning_rate': 0.0002201256775266666, 'epoch': 6.62}

 55%|█████▌    | 15500/28080 [30:38:00<25:00:09,  7.16s/it]
 55%|█████▌    | 15501/28080 [30:38:07<24:47:46,  7.10s/it]
                                                           
{'loss': 0.6022, 'learning_rate': 0.00022009704863950634, 'epoch': 6.62}

 55%|█████▌    | 15501/28080 [30:38:07<24:47:46,  7.10s/it]
 55%|█████▌    | 15502/28080 [30:38:14<24:50:55,  7.11s/it]
                                                           
{'loss': 0.6303, 'learning_rate': 0.00022006842015017392, 'epoch': 6.62}

 55%|█████▌    | 15502/28080 [30:38:14<24:50:55,  7.11s/it]
 55%|█████▌    | 15503/28080 [30:38:21<24:50:05,  7.11s/it]
                                                           
{'loss': 0.6123, 'learning_rate': 0.00022003979205905037, 'epoch': 6.62}

 55%|█████▌    | 15503/28080 [30:38:21<24:50:05,  7.11s/it]
 55%|█████▌    | 15504/28080 [30:38:29<24:52:53,  7.12s/it]
                                                           
{'loss': 0.6222, 'learning_rate': 0.00022001116436651635, 'epoch': 6.62}

 55%|█████▌    | 15504/28080 [30:38:29<24:52:53,  7.12s/it]
 55%|█████▌    | 15505/28080 [30:38:36<24:44:35,  7.08s/it]
                                                           
{'loss': 0.6171, 'learning_rate': 0.00021998253707295303, 'epoch': 6.62}

 55%|█████▌    | 15505/28080 [30:38:36<24:44:35,  7.08s/it]
 55%|█████▌    | 15506/28080 [30:38:43<24:44:19,  7.08s/it]
                                                           
{'loss': 0.6231, 'learning_rate': 0.00021995391017874092, 'epoch': 6.62}

 55%|█████▌    | 15506/28080 [30:38:43<24:44:19,  7.08s/it]
 55%|█████▌    | 15507/28080 [30:38:50<24:52:05,  7.12s/it]
                                                           
{'loss': 0.617, 'learning_rate': 0.0002199252836842612, 'epoch': 6.62}

 55%|█████▌    | 15507/28080 [30:38:50<24:52:05,  7.12s/it]
 55%|█████▌    | 15508/28080 [30:38:57<24:46:08,  7.09s/it]
                                                           
{'loss': 0.6329, 'learning_rate': 0.00021989665758989437, 'epoch': 6.62}

 55%|█████▌    | 15508/28080 [30:38:57<24:46:08,  7.09s/it]
 55%|█████▌    | 15509/28080 [30:39:04<24:43:30,  7.08s/it]
                                                           
{'loss': 0.6157, 'learning_rate': 0.0002198680318960216, 'epoch': 6.63}

 55%|█████▌    | 15509/28080 [30:39:04<24:43:30,  7.08s/it]
 55%|█████▌    | 15510/28080 [30:39:11<24:46:46,  7.10s/it]
                                                           
{'loss': 0.5955, 'learning_rate': 0.0002198394066030235, 'epoch': 6.63}

 55%|█████▌    | 15510/28080 [30:39:11<24:46:46,  7.10s/it]
 55%|█████▌    | 15511/28080 [30:39:18<24:48:36,  7.11s/it]
                                                           
{'loss': 0.6267, 'learning_rate': 0.00021981078171128104, 'epoch': 6.63}

 55%|█████▌    | 15511/28080 [30:39:18<24:48:36,  7.11s/it]
 55%|█████▌    | 15512/28080 [30:39:25<24:45:57,  7.09s/it]
                                                           
{'loss': 0.6129, 'learning_rate': 0.00021978215722117493, 'epoch': 6.63}

 55%|█████▌    | 15512/28080 [30:39:25<24:45:57,  7.09s/it]
 55%|█████▌    | 15513/28080 [30:39:32<24:47:03,  7.10s/it]
                                                           
{'loss': 0.6256, 'learning_rate': 0.0002197535331330861, 'epoch': 6.63}

 55%|█████▌    | 15513/28080 [30:39:32<24:47:03,  7.10s/it]
 55%|█████▌    | 15514/28080 [30:39:40<24:53:16,  7.13s/it]
                                                           
{'loss': 0.6001, 'learning_rate': 0.00021972490944739527, 'epoch': 6.63}

 55%|█████▌    | 15514/28080 [30:39:40<24:53:16,  7.13s/it]
 55%|█████▌    | 15515/28080 [30:39:47<24:39:43,  7.07s/it]
                                                           
{'loss': 0.6446, 'learning_rate': 0.00021969628616448332, 'epoch': 6.63}

 55%|█████▌    | 15515/28080 [30:39:47<24:39:43,  7.07s/it]
 55%|█████▌    | 15516/28080 [30:39:54<24:49:04,  7.11s/it]
                                                           
{'loss': 0.6086, 'learning_rate': 0.00021966766328473098, 'epoch': 6.63}

 55%|█████▌    | 15516/28080 [30:39:54<24:49:04,  7.11s/it]
 55%|█████▌    | 15517/28080 [30:40:01<24:47:06,  7.10s/it]
                                                           
{'loss': 0.6134, 'learning_rate': 0.00021963904080851912, 'epoch': 6.63}

 55%|█████▌    | 15517/28080 [30:40:01<24:47:06,  7.10s/it]
 55%|█████▌    | 15518/28080 [30:40:08<24:48:03,  7.11s/it]
                                                           
{'loss': 0.6017, 'learning_rate': 0.0002196104187362284, 'epoch': 6.63}

 55%|█████▌    | 15518/28080 [30:40:08<24:48:03,  7.11s/it]
 55%|█████▌    | 15519/28080 [30:40:15<24:52:09,  7.13s/it]
                                                           
{'loss': 0.5931, 'learning_rate': 0.00021958179706823989, 'epoch': 6.63}

 55%|█████▌    | 15519/28080 [30:40:15<24:52:09,  7.13s/it]
 55%|█████▌    | 15520/28080 [30:40:22<24:51:54,  7.13s/it]
                                                           
{'loss': 0.6067, 'learning_rate': 0.000219553175804934, 'epoch': 6.63}

 55%|█████▌    | 15520/28080 [30:40:22<24:51:54,  7.13s/it]
 55%|█████▌    | 15521/28080 [30:40:29<24:52:08,  7.13s/it]
                                                           
{'loss': 0.5987, 'learning_rate': 0.0002195245549466919, 'epoch': 6.63}

 55%|█████▌    | 15521/28080 [30:40:29<24:52:08,  7.13s/it]
 55%|█████▌    | 15522/28080 [30:40:37<24:51:18,  7.13s/it]
                                                           
{'loss': 0.6262, 'learning_rate': 0.00021949593449389394, 'epoch': 6.63}

 55%|█████▌    | 15522/28080 [30:40:37<24:51:18,  7.13s/it]
 55%|█████▌    | 15523/28080 [30:40:44<24:52:09,  7.13s/it]
                                                           
{'loss': 0.6041, 'learning_rate': 0.00021946731444692126, 'epoch': 6.63}

 55%|█████▌    | 15523/28080 [30:40:44<24:52:09,  7.13s/it]
 55%|█████▌    | 15524/28080 [30:40:51<24:47:37,  7.11s/it]
                                                           
{'loss': 0.6144, 'learning_rate': 0.00021943869480615447, 'epoch': 6.63}

 55%|█████▌    | 15524/28080 [30:40:51<24:47:37,  7.11s/it]
 55%|█████▌    | 15525/28080 [30:40:58<24:38:59,  7.07s/it]
                                                           
{'loss': 0.6143, 'learning_rate': 0.00021941007557197418, 'epoch': 6.63}

 55%|█████▌    | 15525/28080 [30:40:58<24:38:59,  7.07s/it]
 55%|█████▌    | 15526/28080 [30:41:05<24:45:48,  7.10s/it]
                                                           
{'loss': 0.6152, 'learning_rate': 0.0002193814567447614, 'epoch': 6.63}

 55%|█████▌    | 15526/28080 [30:41:05<24:45:48,  7.10s/it]
 55%|█████▌    | 15527/28080 [30:41:12<24:47:12,  7.11s/it]
                                                           
{'loss': 0.6046, 'learning_rate': 0.00021935283832489667, 'epoch': 6.63}

 55%|█████▌    | 15527/28080 [30:41:12<24:47:12,  7.11s/it]
 55%|█████▌    | 15528/28080 [30:41:19<24:50:30,  7.12s/it]
                                                           
{'loss': 0.6093, 'learning_rate': 0.00021932422031276086, 'epoch': 6.63}

 55%|█████▌    | 15528/28080 [30:41:19<24:50:30,  7.12s/it]
 55%|█████▌    | 15529/28080 [30:41:26<24:51:22,  7.13s/it]
                                                           
{'loss': 0.6314, 'learning_rate': 0.0002192956027087346, 'epoch': 6.63}

 55%|█████▌    | 15529/28080 [30:41:26<24:51:22,  7.13s/it]
 55%|█████▌    | 15530/28080 [30:41:33<24:50:59,  7.13s/it]
                                                           
{'loss': 0.5947, 'learning_rate': 0.00021926698551319877, 'epoch': 6.63}

 55%|█████▌    | 15530/28080 [30:41:33<24:50:59,  7.13s/it]
 55%|█████▌    | 15531/28080 [30:41:40<24:43:36,  7.09s/it]
                                                           
{'loss': 0.6168, 'learning_rate': 0.0002192383687265339, 'epoch': 6.63}

 55%|█████▌    | 15531/28080 [30:41:40<24:43:36,  7.09s/it]
 55%|█████▌    | 15532/28080 [30:41:48<24:43:39,  7.09s/it]
                                                           
{'loss': 0.5963, 'learning_rate': 0.00021920975234912082, 'epoch': 6.64}

 55%|█████▌    | 15532/28080 [30:41:48<24:43:39,  7.09s/it]
 55%|█████▌    | 15533/28080 [30:41:55<24:44:15,  7.10s/it]
                                                           
{'loss': 0.6086, 'learning_rate': 0.0002191811363813402, 'epoch': 6.64}

 55%|█████▌    | 15533/28080 [30:41:55<24:44:15,  7.10s/it]
 55%|█████▌    | 15534/28080 [30:42:02<24:43:02,  7.09s/it]
                                                           
{'loss': 0.6159, 'learning_rate': 0.00021915252082357285, 'epoch': 6.64}

 55%|█████▌    | 15534/28080 [30:42:02<24:43:02,  7.09s/it]
 55%|█████▌    | 15535/28080 [30:42:09<24:42:11,  7.09s/it]
                                                           
{'loss': 0.6017, 'learning_rate': 0.00021912390567619926, 'epoch': 6.64}

 55%|█████▌    | 15535/28080 [30:42:09<24:42:11,  7.09s/it]
 55%|█████▌    | 15536/28080 [30:42:16<24:40:42,  7.08s/it]
                                                           
{'loss': 0.6274, 'learning_rate': 0.0002190952909396004, 'epoch': 6.64}

 55%|█████▌    | 15536/28080 [30:42:16<24:40:42,  7.08s/it]
 55%|█████▌    | 15537/28080 [30:42:23<24:43:06,  7.09s/it]
                                                           
{'loss': 0.6294, 'learning_rate': 0.00021906667661415662, 'epoch': 6.64}

 55%|█████▌    | 15537/28080 [30:42:23<24:43:06,  7.09s/it]
 55%|█████▌    | 15538/28080 [30:42:30<24:46:03,  7.11s/it]
                                                           
{'loss': 0.6259, 'learning_rate': 0.000219038062700249, 'epoch': 6.64}

 55%|█████▌    | 15538/28080 [30:42:30<24:46:03,  7.11s/it]
 55%|█████▌    | 15539/28080 [30:42:37<24:52:39,  7.14s/it]
                                                           
{'loss': 0.6085, 'learning_rate': 0.00021900944919825784, 'epoch': 6.64}

 55%|█████▌    | 15539/28080 [30:42:37<24:52:39,  7.14s/it]
 55%|█████▌    | 15540/28080 [30:42:44<24:45:01,  7.11s/it]
                                                           
{'loss': 0.6378, 'learning_rate': 0.0002189808361085641, 'epoch': 6.64}

 55%|█████▌    | 15540/28080 [30:42:44<24:45:01,  7.11s/it]
 55%|█████▌    | 15541/28080 [30:42:51<24:45:13,  7.11s/it]
                                                           
{'loss': 0.6004, 'learning_rate': 0.00021895222343154831, 'epoch': 6.64}

 55%|█████▌    | 15541/28080 [30:42:51<24:45:13,  7.11s/it]
 55%|█████▌    | 15542/28080 [30:42:59<24:48:04,  7.12s/it]
                                                           
{'loss': 0.6159, 'learning_rate': 0.0002189236111675912, 'epoch': 6.64}

 55%|█████▌    | 15542/28080 [30:42:59<24:48:04,  7.12s/it]
 55%|█████▌    | 15543/28080 [30:43:06<24:48:00,  7.12s/it]
                                                           
{'loss': 0.6259, 'learning_rate': 0.0002188949993170733, 'epoch': 6.64}

 55%|█████▌    | 15543/28080 [30:43:06<24:48:00,  7.12s/it]
 55%|█████▌    | 15544/28080 [30:43:13<24:46:36,  7.12s/it]
                                                           
{'loss': 0.5917, 'learning_rate': 0.00021886638788037538, 'epoch': 6.64}

 55%|█████▌    | 15544/28080 [30:43:13<24:46:36,  7.12s/it]
 55%|█████▌    | 15545/28080 [30:43:20<24:53:28,  7.15s/it]
                                                           
{'loss': 0.6344, 'learning_rate': 0.00021883777685787804, 'epoch': 6.64}

 55%|█████▌    | 15545/28080 [30:43:20<24:53:28,  7.15s/it]
 55%|█████▌    | 15546/28080 [30:43:27<24:56:22,  7.16s/it]
                                                           
{'loss': 0.615, 'learning_rate': 0.00021880916624996197, 'epoch': 6.64}

 55%|█████▌    | 15546/28080 [30:43:27<24:56:22,  7.16s/it]
 55%|█████▌    | 15547/28080 [30:43:34<24:48:52,  7.13s/it]
                                                           
{'loss': 0.6298, 'learning_rate': 0.00021878055605700772, 'epoch': 6.64}

 55%|█████▌    | 15547/28080 [30:43:34<24:48:52,  7.13s/it]
 55%|█████▌    | 15548/28080 [30:43:41<24:50:09,  7.13s/it]
                                                           
{'loss': 0.6121, 'learning_rate': 0.000218751946279396, 'epoch': 6.64}

 55%|█████▌    | 15548/28080 [30:43:41<24:50:09,  7.13s/it]
 55%|█████▌    | 15549/28080 [30:43:49<24:50:24,  7.14s/it]
                                                           
{'loss': 0.6093, 'learning_rate': 0.00021872333691750742, 'epoch': 6.64}

 55%|█████▌    | 15549/28080 [30:43:49<24:50:24,  7.14s/it]
 55%|█████▌    | 15550/28080 [30:43:56<24:54:20,  7.16s/it]
                                                           
{'loss': 0.6289, 'learning_rate': 0.00021869472797172253, 'epoch': 6.64}

 55%|█████▌    | 15550/28080 [30:43:56<24:54:20,  7.16s/it]
 55%|█████▌    | 15551/28080 [30:44:03<24:56:20,  7.17s/it]
                                                           
{'loss': 0.6245, 'learning_rate': 0.00021866611944242197, 'epoch': 6.64}

 55%|█████▌    | 15551/28080 [30:44:03<24:56:20,  7.17s/it]
 55%|█████▌    | 15552/28080 [30:44:10<24:57:52,  7.17s/it]
                                                           
{'loss': 0.6173, 'learning_rate': 0.0002186375113299864, 'epoch': 6.64}

 55%|█████▌    | 15552/28080 [30:44:10<24:57:52,  7.17s/it]
 55%|█████▌    | 15553/28080 [30:44:17<24:55:37,  7.16s/it]
                                                           
{'loss': 0.6088, 'learning_rate': 0.0002186089036347964, 'epoch': 6.64}

 55%|█████▌    | 15553/28080 [30:44:17<24:55:37,  7.16s/it]
 55%|█████▌    | 15554/28080 [30:44:25<24:54:56,  7.16s/it]
                                                           
{'loss': 0.6018, 'learning_rate': 0.00021858029635723244, 'epoch': 6.64}

 55%|█████▌    | 15554/28080 [30:44:25<24:54:56,  7.16s/it]
 55%|█████▌    | 15555/28080 [30:44:32<24:46:11,  7.12s/it]
                                                           
{'loss': 0.6264, 'learning_rate': 0.0002185516894976754, 'epoch': 6.64}

 55%|█████▌    | 15555/28080 [30:44:32<24:46:11,  7.12s/it]
 55%|█████▌    | 15556/28080 [30:44:39<24:47:08,  7.12s/it]
                                                           
{'loss': 0.6155, 'learning_rate': 0.00021852308305650553, 'epoch': 6.65}

 55%|█████▌    | 15556/28080 [30:44:39<24:47:08,  7.12s/it]
 55%|█████▌    | 15557/28080 [30:44:46<24:44:35,  7.11s/it]
                                                           
{'loss': 0.5926, 'learning_rate': 0.00021849447703410366, 'epoch': 6.65}

 55%|█████▌    | 15557/28080 [30:44:46<24:44:35,  7.11s/it]
 55%|█████▌    | 15558/28080 [30:44:53<24:47:58,  7.13s/it]
                                                           
{'loss': 0.6201, 'learning_rate': 0.00021846587143085024, 'epoch': 6.65}

 55%|█████▌    | 15558/28080 [30:44:53<24:47:58,  7.13s/it]
 55%|█████▌    | 15559/28080 [30:45:00<24:46:44,  7.12s/it]
                                                           
{'loss': 0.6258, 'learning_rate': 0.0002184372662471259, 'epoch': 6.65}

 55%|█████▌    | 15559/28080 [30:45:00<24:46:44,  7.12s/it]
 55%|█████▌    | 15560/28080 [30:45:07<24:50:33,  7.14s/it]
                                                           
{'loss': 0.5906, 'learning_rate': 0.00021840866148331112, 'epoch': 6.65}

 55%|█████▌    | 15560/28080 [30:45:07<24:50:33,  7.14s/it]
 55%|█████▌    | 15561/28080 [30:45:14<24:45:34,  7.12s/it]
                                                           
{'loss': 0.6003, 'learning_rate': 0.00021838005713978656, 'epoch': 6.65}

 55%|█████▌    | 15561/28080 [30:45:14<24:45:34,  7.12s/it]
 55%|█████▌    | 15562/28080 [30:45:22<24:53:47,  7.16s/it]
                                                           
{'loss': 0.6157, 'learning_rate': 0.00021835145321693266, 'epoch': 6.65}

 55%|█████▌    | 15562/28080 [30:45:22<24:53:47,  7.16s/it]
 55%|█████▌    | 15563/28080 [30:45:29<24:53:07,  7.16s/it]
                                                           
{'loss': 0.6229, 'learning_rate': 0.00021832284971513011, 'epoch': 6.65}

 55%|█████▌    | 15563/28080 [30:45:29<24:53:07,  7.16s/it]
 55%|█████▌    | 15564/28080 [30:45:36<24:55:43,  7.17s/it]
                                                           
{'loss': 0.6202, 'learning_rate': 0.00021829424663475928, 'epoch': 6.65}

 55%|█████▌    | 15564/28080 [30:45:36<24:55:43,  7.17s/it]
 55%|█████▌    | 15565/28080 [30:45:43<24:55:17,  7.17s/it]
                                                           
{'loss': 0.6335, 'learning_rate': 0.00021826564397620085, 'epoch': 6.65}

 55%|█████▌    | 15565/28080 [30:45:43<24:55:17,  7.17s/it]
 55%|█████▌    | 15566/28080 [30:45:50<24:56:00,  7.17s/it]
                                                           
{'loss': 0.621, 'learning_rate': 0.0002182370417398352, 'epoch': 6.65}

 55%|█████▌    | 15566/28080 [30:45:50<24:56:00,  7.17s/it]
 55%|█████▌    | 15567/28080 [30:45:57<24:53:19,  7.16s/it]
                                                           
{'loss': 0.6206, 'learning_rate': 0.00021820843992604309, 'epoch': 6.65}

 55%|█████▌    | 15567/28080 [30:45:57<24:53:19,  7.16s/it]
 55%|█████▌    | 15568/28080 [30:46:04<24:47:01,  7.13s/it]
                                                           
{'loss': 0.6179, 'learning_rate': 0.00021817983853520472, 'epoch': 6.65}

 55%|█████▌    | 15568/28080 [30:46:04<24:47:01,  7.13s/it]
 55%|█████▌    | 15569/28080 [30:46:12<24:45:02,  7.12s/it]
                                                           
{'loss': 0.6079, 'learning_rate': 0.00021815123756770092, 'epoch': 6.65}

 55%|█████▌    | 15569/28080 [30:46:12<24:45:02,  7.12s/it]
 55%|█████▌    | 15570/28080 [30:46:19<24:43:10,  7.11s/it]
                                                           
{'loss': 0.6281, 'learning_rate': 0.0002181226370239119, 'epoch': 6.65}

 55%|█████▌    | 15570/28080 [30:46:19<24:43:10,  7.11s/it]
 55%|█████▌    | 15571/28080 [30:46:26<24:43:29,  7.12s/it]
                                                           
{'loss': 0.6056, 'learning_rate': 0.00021809403690421843, 'epoch': 6.65}

 55%|█████▌    | 15571/28080 [30:46:26<24:43:29,  7.12s/it]
 55%|█████▌    | 15572/28080 [30:46:33<24:40:20,  7.10s/it]
                                                           
{'loss': 0.6223, 'learning_rate': 0.00021806543720900084, 'epoch': 6.65}

 55%|█████▌    | 15572/28080 [30:46:33<24:40:20,  7.10s/it]
 55%|█████▌    | 15573/28080 [30:46:40<24:41:39,  7.11s/it]
                                                           
{'loss': 0.6219, 'learning_rate': 0.00021803683793863968, 'epoch': 6.65}

 55%|█████▌    | 15573/28080 [30:46:40<24:41:39,  7.11s/it]
 55%|█████▌    | 15574/28080 [30:46:47<24:40:36,  7.10s/it]
                                                           
{'loss': 0.6202, 'learning_rate': 0.00021800823909351542, 'epoch': 6.65}

 55%|█████▌    | 15574/28080 [30:46:47<24:40:36,  7.10s/it]
 55%|█████▌    | 15575/28080 [30:46:54<24:43:57,  7.12s/it]
                                                           
{'loss': 0.5925, 'learning_rate': 0.00021797964067400848, 'epoch': 6.65}

 55%|█████▌    | 15575/28080 [30:46:54<24:43:57,  7.12s/it]
 55%|█████▌    | 15576/28080 [30:47:01<24:43:42,  7.12s/it]
                                                           
{'loss': 0.6248, 'learning_rate': 0.0002179510426804995, 'epoch': 6.65}

 55%|█████▌    | 15576/28080 [30:47:01<24:43:42,  7.12s/it]
 55%|█████▌    | 15577/28080 [30:47:09<24:51:01,  7.16s/it]
                                                           
{'loss': 0.6155, 'learning_rate': 0.00021792244511336872, 'epoch': 6.65}

 55%|█████▌    | 15577/28080 [30:47:09<24:51:01,  7.16s/it]
 55%|█████▌    | 15578/28080 [30:47:16<24:52:28,  7.16s/it]
                                                           
{'loss': 0.6003, 'learning_rate': 0.00021789384797299676, 'epoch': 6.65}

 55%|█████▌    | 15578/28080 [30:47:16<24:52:28,  7.16s/it]
 55%|█████▌    | 15579/28080 [30:47:23<24:56:44,  7.18s/it]
                                                           
{'loss': 0.6078, 'learning_rate': 0.00021786525125976403, 'epoch': 6.66}

 55%|█████▌    | 15579/28080 [30:47:23<24:56:44,  7.18s/it]
 55%|█████▌    | 15580/28080 [30:47:30<24:58:45,  7.19s/it]
                                                           
{'loss': 0.5925, 'learning_rate': 0.000217836654974051, 'epoch': 6.66}

 55%|█████▌    | 15580/28080 [30:47:30<24:58:45,  7.19s/it]
 55%|█████▌    | 15581/28080 [30:47:38<25:07:39,  7.24s/it]
                                                           
{'loss': 0.6212, 'learning_rate': 0.00021780805911623803, 'epoch': 6.66}

 55%|█████▌    | 15581/28080 [30:47:38<25:07:39,  7.24s/it]
 55%|█████▌    | 15582/28080 [30:47:45<25:01:45,  7.21s/it]
                                                           
{'loss': 0.6158, 'learning_rate': 0.0002177794636867057, 'epoch': 6.66}

 55%|█████▌    | 15582/28080 [30:47:45<25:01:45,  7.21s/it]
 55%|█████▌    | 15583/28080 [30:47:52<24:48:37,  7.15s/it]
                                                           
{'loss': 0.6391, 'learning_rate': 0.0002177508686858343, 'epoch': 6.66}

 55%|█████▌    | 15583/28080 [30:47:52<24:48:37,  7.15s/it]
 55%|█████▌    | 15584/28080 [30:47:59<24:46:39,  7.14s/it]
                                                           
{'loss': 0.6006, 'learning_rate': 0.0002177222741140044, 'epoch': 6.66}

 55%|█████▌    | 15584/28080 [30:47:59<24:46:39,  7.14s/it]
 56%|█████▌    | 15585/28080 [30:48:06<24:45:19,  7.13s/it]
                                                           
{'loss': 0.6044, 'learning_rate': 0.0002176936799715962, 'epoch': 6.66}

 56%|█████▌    | 15585/28080 [30:48:06<24:45:19,  7.13s/it]
 56%|█████▌    | 15586/28080 [30:48:13<24:44:04,  7.13s/it]
                                                           
{'loss': 0.6023, 'learning_rate': 0.00021766508625899045, 'epoch': 6.66}

 56%|█████▌    | 15586/28080 [30:48:13<24:44:04,  7.13s/it]
 56%|█████▌    | 15587/28080 [30:48:20<24:49:31,  7.15s/it]
                                                           
{'loss': 0.6236, 'learning_rate': 0.00021763649297656718, 'epoch': 6.66}

 56%|█████▌    | 15587/28080 [30:48:20<24:49:31,  7.15s/it]
 56%|█████▌    | 15588/28080 [30:48:27<24:48:37,  7.15s/it]
                                                           
{'loss': 0.6088, 'learning_rate': 0.00021760790012470712, 'epoch': 6.66}

 56%|█████▌    | 15588/28080 [30:48:27<24:48:37,  7.15s/it]
 56%|█████▌    | 15589/28080 [30:48:34<24:41:40,  7.12s/it]
                                                           
{'loss': 0.6391, 'learning_rate': 0.00021757930770379045, 'epoch': 6.66}

 56%|█████▌    | 15589/28080 [30:48:34<24:41:40,  7.12s/it]
 56%|█████▌    | 15590/28080 [30:48:42<24:42:20,  7.12s/it]
                                                           
{'loss': 0.6024, 'learning_rate': 0.0002175507157141977, 'epoch': 6.66}

 56%|█████▌    | 15590/28080 [30:48:42<24:42:20,  7.12s/it]
 56%|█████▌    | 15591/28080 [30:48:49<24:39:12,  7.11s/it]
                                                           
{'loss': 0.6292, 'learning_rate': 0.00021752212415630917, 'epoch': 6.66}

 56%|█████▌    | 15591/28080 [30:48:49<24:39:12,  7.11s/it]
 56%|█████▌    | 15592/28080 [30:48:56<24:41:37,  7.12s/it]
                                                           
{'loss': 0.602, 'learning_rate': 0.00021749353303050534, 'epoch': 6.66}

 56%|█████▌    | 15592/28080 [30:48:56<24:41:37,  7.12s/it]
 56%|█████▌    | 15593/28080 [30:49:03<24:43:53,  7.13s/it]
                                                           
{'loss': 0.6146, 'learning_rate': 0.00021746494233716645, 'epoch': 6.66}

 56%|█████▌    | 15593/28080 [30:49:03<24:43:53,  7.13s/it]
 56%|█████▌    | 15594/28080 [30:49:10<24:52:03,  7.17s/it]
                                                           
{'loss': 0.615, 'learning_rate': 0.00021743635207667296, 'epoch': 6.66}

 56%|█████▌    | 15594/28080 [30:49:10<24:52:03,  7.17s/it]
 56%|█████▌    | 15595/28080 [30:49:17<24:50:02,  7.16s/it]
                                                           
{'loss': 0.6094, 'learning_rate': 0.00021740776224940517, 'epoch': 6.66}

 56%|█████▌    | 15595/28080 [30:49:17<24:50:02,  7.16s/it]
 56%|█████▌    | 15596/28080 [30:49:24<24:39:14,  7.11s/it]
                                                           
{'loss': 0.6423, 'learning_rate': 0.00021737917285574355, 'epoch': 6.66}

 56%|█████▌    | 15596/28080 [30:49:24<24:39:14,  7.11s/it]
 56%|█████▌    | 15597/28080 [30:49:31<24:43:16,  7.13s/it]
                                                           
{'loss': 0.6087, 'learning_rate': 0.00021735058389606827, 'epoch': 6.66}

 56%|█████▌    | 15597/28080 [30:49:31<24:43:16,  7.13s/it]
 56%|█████▌    | 15598/28080 [30:49:39<24:50:26,  7.16s/it]
                                                           
{'loss': 0.6248, 'learning_rate': 0.00021732199537075994, 'epoch': 6.66}

 56%|█████▌    | 15598/28080 [30:49:39<24:50:26,  7.16s/it]
 56%|█████▌    | 15599/28080 [30:49:46<24:45:42,  7.14s/it]
                                                           
{'loss': 0.607, 'learning_rate': 0.00021729340728019868, 'epoch': 6.66}

 56%|█████▌    | 15599/28080 [30:49:46<24:45:42,  7.14s/it]
 56%|█████▌    | 15600/28080 [30:49:53<24:37:03,  7.10s/it]
                                                           
{'loss': 0.6294, 'learning_rate': 0.00021726481962476492, 'epoch': 6.66}

 56%|█████▌    | 15600/28080 [30:49:53<24:37:03,  7.10s/it]
 56%|█████▌    | 15601/28080 [30:50:00<24:32:01,  7.08s/it]
                                                           
{'loss': 0.6295, 'learning_rate': 0.00021723623240483894, 'epoch': 6.66}

 56%|█████▌    | 15601/28080 [30:50:00<24:32:01,  7.08s/it]
 56%|█████▌    | 15602/28080 [30:50:07<24:31:49,  7.08s/it]
                                                           
{'loss': 0.627, 'learning_rate': 0.000217207645620801, 'epoch': 6.67}

 56%|█████▌    | 15602/28080 [30:50:07<24:31:49,  7.08s/it]
 56%|█████▌    | 15603/28080 [30:50:14<24:39:04,  7.11s/it]
                                                           
{'loss': 0.6265, 'learning_rate': 0.00021717905927303168, 'epoch': 6.67}

 56%|█████▌    | 15603/28080 [30:50:14<24:39:04,  7.11s/it]
 56%|█████▌    | 15604/28080 [30:50:21<24:43:38,  7.14s/it]
                                                           
{'loss': 0.6039, 'learning_rate': 0.00021715047336191094, 'epoch': 6.67}

 56%|█████▌    | 15604/28080 [30:50:21<24:43:38,  7.14s/it]
 56%|█████▌    | 15605/28080 [30:50:28<24:45:29,  7.14s/it]
                                                           
{'loss': 0.6451, 'learning_rate': 0.00021712188788781936, 'epoch': 6.67}

 56%|█████▌    | 15605/28080 [30:50:28<24:45:29,  7.14s/it]
 56%|█████▌    | 15606/28080 [30:50:36<24:43:46,  7.14s/it]
                                                           
{'loss': 0.5853, 'learning_rate': 0.0002170933028511371, 'epoch': 6.67}

 56%|█████▌    | 15606/28080 [30:50:36<24:43:46,  7.14s/it]
 56%|█████▌    | 15607/28080 [30:50:43<24:35:27,  7.10s/it]
                                                           
{'loss': 0.6301, 'learning_rate': 0.00021706471825224454, 'epoch': 6.67}

 56%|█████▌    | 15607/28080 [30:50:43<24:35:27,  7.10s/it]
 56%|█████▌    | 15608/28080 [30:50:50<24:37:43,  7.11s/it]
                                                           
{'loss': 0.6216, 'learning_rate': 0.00021703613409152192, 'epoch': 6.67}

 56%|█████▌    | 15608/28080 [30:50:50<24:37:43,  7.11s/it]
 56%|█████▌    | 15609/28080 [30:50:57<24:41:39,  7.13s/it]
                                                           
{'loss': 0.6161, 'learning_rate': 0.00021700755036934956, 'epoch': 6.67}

 56%|█████▌    | 15609/28080 [30:50:57<24:41:39,  7.13s/it]
 56%|█████▌    | 15610/28080 [30:51:04<24:35:14,  7.10s/it]
                                                           
{'loss': 0.6385, 'learning_rate': 0.00021697896708610761, 'epoch': 6.67}

 56%|█████▌    | 15610/28080 [30:51:04<24:35:14,  7.10s/it]
 56%|█████▌    | 15611/28080 [30:51:11<24:41:47,  7.13s/it]
                                                           
{'loss': 0.6116, 'learning_rate': 0.00021695038424217656, 'epoch': 6.67}

 56%|█████▌    | 15611/28080 [30:51:11<24:41:47,  7.13s/it]
 56%|█████▌    | 15612/28080 [30:51:18<24:39:22,  7.12s/it]
                                                           
{'loss': 0.6336, 'learning_rate': 0.00021692180183793645, 'epoch': 6.67}

 56%|█████▌    | 15612/28080 [30:51:18<24:39:22,  7.12s/it]
 56%|█████▌    | 15613/28080 [30:51:25<24:45:23,  7.15s/it]
                                                           
{'loss': 0.6196, 'learning_rate': 0.0002168932198737677, 'epoch': 6.67}

 56%|█████▌    | 15613/28080 [30:51:25<24:45:23,  7.15s/it]
 56%|█████▌    | 15614/28080 [30:51:33<24:42:56,  7.14s/it]
                                                           
{'loss': 0.6044, 'learning_rate': 0.00021686463835005046, 'epoch': 6.67}

 56%|█████▌    | 15614/28080 [30:51:33<24:42:56,  7.14s/it]
 56%|█████▌    | 15615/28080 [30:51:40<24:45:39,  7.15s/it]
                                                           
{'loss': 0.6135, 'learning_rate': 0.00021683605726716506, 'epoch': 6.67}

 56%|█████▌    | 15615/28080 [30:51:40<24:45:39,  7.15s/it]
 56%|█████▌    | 15616/28080 [30:51:47<24:50:18,  7.17s/it]
                                                           
{'loss': 0.5989, 'learning_rate': 0.00021680747662549164, 'epoch': 6.67}

 56%|█████▌    | 15616/28080 [30:51:47<24:50:18,  7.17s/it]
 56%|█████▌    | 15617/28080 [30:51:54<24:45:28,  7.15s/it]
                                                           
{'loss': 0.618, 'learning_rate': 0.00021677889642541062, 'epoch': 6.67}

 56%|█████▌    | 15617/28080 [30:51:54<24:45:28,  7.15s/it]
 56%|█████▌    | 15618/28080 [30:52:01<24:56:05,  7.20s/it]
                                                           
{'loss': 0.6012, 'learning_rate': 0.00021675031666730196, 'epoch': 6.67}

 56%|█████▌    | 15618/28080 [30:52:01<24:56:05,  7.20s/it]
 56%|█████▌    | 15619/28080 [30:52:09<24:54:11,  7.19s/it]
                                                           
{'loss': 0.6166, 'learning_rate': 0.00021672173735154615, 'epoch': 6.67}

 56%|█████▌    | 15619/28080 [30:52:09<24:54:11,  7.19s/it]
 56%|█████▌    | 15620/28080 [30:52:16<24:52:51,  7.19s/it]
                                                           
{'loss': 0.6216, 'learning_rate': 0.00021669315847852325, 'epoch': 6.67}

 56%|█████▌    | 15620/28080 [30:52:16<24:52:51,  7.19s/it]
 56%|█████▌    | 15621/28080 [30:52:23<24:43:42,  7.15s/it]
                                                           
{'loss': 0.6066, 'learning_rate': 0.00021666458004861356, 'epoch': 6.67}

 56%|█████▌    | 15621/28080 [30:52:23<24:43:42,  7.15s/it]
 56%|█████▌    | 15622/28080 [30:52:30<24:44:35,  7.15s/it]
                                                           
{'loss': 0.6097, 'learning_rate': 0.00021663600206219715, 'epoch': 6.67}

 56%|█████▌    | 15622/28080 [30:52:30<24:44:35,  7.15s/it]
 56%|█████▌    | 15623/28080 [30:52:37<24:43:11,  7.14s/it]
                                                           
{'loss': 0.6338, 'learning_rate': 0.00021660742451965444, 'epoch': 6.67}

 56%|█████▌    | 15623/28080 [30:52:37<24:43:11,  7.14s/it]
 56%|█████▌    | 15624/28080 [30:52:44<24:41:11,  7.13s/it]
                                                           
{'loss': 0.6243, 'learning_rate': 0.00021657884742136543, 'epoch': 6.67}

 56%|█████▌    | 15624/28080 [30:52:44<24:41:11,  7.13s/it]
 56%|█████▌    | 15625/28080 [30:52:51<24:42:15,  7.14s/it]
                                                           
{'loss': 0.6308, 'learning_rate': 0.00021655027076771037, 'epoch': 6.67}

 56%|█████▌    | 15625/28080 [30:52:51<24:42:15,  7.14s/it]
 56%|█████▌    | 15626/28080 [30:52:58<24:41:15,  7.14s/it]
                                                           
{'loss': 0.5974, 'learning_rate': 0.00021652169455906947, 'epoch': 6.68}

 56%|█████▌    | 15626/28080 [30:52:58<24:41:15,  7.14s/it]
 56%|█████▌    | 15627/28080 [30:53:06<24:34:33,  7.10s/it]
                                                           
{'loss': 0.6209, 'learning_rate': 0.00021649311879582284, 'epoch': 6.68}

 56%|█████▌    | 15627/28080 [30:53:06<24:34:33,  7.10s/it]
 56%|█████▌    | 15628/28080 [30:53:13<24:34:02,  7.10s/it]
                                                           
{'loss': 0.6433, 'learning_rate': 0.00021646454347835076, 'epoch': 6.68}

 56%|█████▌    | 15628/28080 [30:53:13<24:34:02,  7.10s/it]
 56%|█████▌    | 15629/28080 [30:53:20<24:28:12,  7.08s/it]
                                                           
{'loss': 0.6522, 'learning_rate': 0.0002164359686070333, 'epoch': 6.68}

 56%|█████▌    | 15629/28080 [30:53:20<24:28:12,  7.08s/it]
 56%|█████▌    | 15630/28080 [30:53:27<24:35:03,  7.11s/it]
                                                           
{'loss': 0.6082, 'learning_rate': 0.00021640739418225067, 'epoch': 6.68}

 56%|█████▌    | 15630/28080 [30:53:27<24:35:03,  7.11s/it]
 56%|█████▌    | 15631/28080 [30:53:34<24:31:06,  7.09s/it]
                                                           
{'loss': 0.6165, 'learning_rate': 0.00021637882020438296, 'epoch': 6.68}

 56%|█████▌    | 15631/28080 [30:53:34<24:31:06,  7.09s/it]
 56%|█████▌    | 15632/28080 [30:53:41<24:38:02,  7.12s/it]
                                                           
{'loss': 0.6049, 'learning_rate': 0.00021635024667381042, 'epoch': 6.68}

 56%|█████▌    | 15632/28080 [30:53:41<24:38:02,  7.12s/it]
 56%|█████▌    | 15633/28080 [30:53:48<24:37:27,  7.12s/it]
                                                           
{'loss': 0.631, 'learning_rate': 0.00021632167359091303, 'epoch': 6.68}

 56%|█████▌    | 15633/28080 [30:53:48<24:37:27,  7.12s/it]
 56%|█████▌    | 15634/28080 [30:53:55<24:30:29,  7.09s/it]
                                                           
{'loss': 0.6022, 'learning_rate': 0.0002162931009560712, 'epoch': 6.68}

 56%|█████▌    | 15634/28080 [30:53:55<24:30:29,  7.09s/it]
 56%|█████▌    | 15635/28080 [30:54:02<24:34:36,  7.11s/it]
                                                           
{'loss': 0.6142, 'learning_rate': 0.0002162645287696647, 'epoch': 6.68}

 56%|█████▌    | 15635/28080 [30:54:02<24:34:36,  7.11s/it]
 56%|█████▌    | 15636/28080 [30:54:09<24:32:16,  7.10s/it]
                                                           
{'loss': 0.62, 'learning_rate': 0.00021623595703207393, 'epoch': 6.68}

 56%|█████▌    | 15636/28080 [30:54:09<24:32:16,  7.10s/it]
 56%|█████▌    | 15637/28080 [30:54:17<24:33:01,  7.10s/it]
                                                           
{'loss': 0.6203, 'learning_rate': 0.00021620738574367894, 'epoch': 6.68}

 56%|█████▌    | 15637/28080 [30:54:17<24:33:01,  7.10s/it]
 56%|█████▌    | 15638/28080 [30:54:24<24:29:25,  7.09s/it]
                                                           
{'loss': 0.6098, 'learning_rate': 0.0002161788149048598, 'epoch': 6.68}

 56%|█████▌    | 15638/28080 [30:54:24<24:29:25,  7.09s/it]
 56%|█████▌    | 15639/28080 [30:54:31<24:33:12,  7.10s/it]
                                                           
{'loss': 0.6053, 'learning_rate': 0.00021615024451599664, 'epoch': 6.68}

 56%|█████▌    | 15639/28080 [30:54:31<24:33:12,  7.10s/it]
 56%|█████▌    | 15640/28080 [30:54:38<24:34:27,  7.11s/it]
                                                           
{'loss': 0.6363, 'learning_rate': 0.00021612167457746957, 'epoch': 6.68}

 56%|█████▌    | 15640/28080 [30:54:38<24:34:27,  7.11s/it]
 56%|█████▌    | 15641/28080 [30:54:45<24:31:07,  7.10s/it]
                                                           
{'loss': 0.6267, 'learning_rate': 0.00021609310508965862, 'epoch': 6.68}

 56%|█████▌    | 15641/28080 [30:54:45<24:31:07,  7.10s/it]
 56%|█████▌    | 15642/28080 [30:54:52<24:29:32,  7.09s/it]
                                                           
{'loss': 0.6268, 'learning_rate': 0.000216064536052944, 'epoch': 6.68}

 56%|█████▌    | 15642/28080 [30:54:52<24:29:32,  7.09s/it]
 56%|█████▌    | 15643/28080 [30:54:59<24:27:56,  7.08s/it]
                                                           
{'loss': 0.6139, 'learning_rate': 0.00021603596746770564, 'epoch': 6.68}

 56%|█████▌    | 15643/28080 [30:54:59<24:27:56,  7.08s/it]
 56%|█████▌    | 15644/28080 [30:55:06<24:31:58,  7.10s/it]
                                                           
{'loss': 0.6086, 'learning_rate': 0.0002160073993343238, 'epoch': 6.68}

 56%|█████▌    | 15644/28080 [30:55:06<24:31:58,  7.10s/it]
 56%|█████▌    | 15645/28080 [30:55:13<24:37:23,  7.13s/it]
                                                           
{'loss': 0.61, 'learning_rate': 0.00021597883165317834, 'epoch': 6.68}

 56%|█████▌    | 15645/28080 [30:55:13<24:37:23,  7.13s/it]
 56%|█████▌    | 15646/28080 [30:55:21<24:39:03,  7.14s/it]
                                                           
{'loss': 0.6283, 'learning_rate': 0.00021595026442464948, 'epoch': 6.68}

 56%|█████▌    | 15646/28080 [30:55:21<24:39:03,  7.14s/it]
 56%|█████▌    | 15647/28080 [30:55:28<24:36:12,  7.12s/it]
                                                           
{'loss': 0.6146, 'learning_rate': 0.00021592169764911713, 'epoch': 6.68}

 56%|█████▌    | 15647/28080 [30:55:28<24:36:12,  7.12s/it]
 56%|█████▌    | 15648/28080 [30:55:35<24:36:37,  7.13s/it]
                                                           
{'loss': 0.5958, 'learning_rate': 0.00021589313132696158, 'epoch': 6.68}

 56%|█████▌    | 15648/28080 [30:55:35<24:36:37,  7.13s/it]
 56%|█████▌    | 15649/28080 [30:55:42<24:36:49,  7.13s/it]
                                                           
{'loss': 0.6059, 'learning_rate': 0.0002158645654585627, 'epoch': 6.69}

 56%|█████▌    | 15649/28080 [30:55:42<24:36:49,  7.13s/it]
 56%|█████▌    | 15650/28080 [30:55:49<24:38:22,  7.14s/it]
                                                           
{'loss': 0.607, 'learning_rate': 0.00021583600004430046, 'epoch': 6.69}

 56%|█████▌    | 15650/28080 [30:55:49<24:38:22,  7.14s/it]
 56%|█████▌    | 15651/28080 [30:55:56<24:35:47,  7.12s/it]
                                                           
{'loss': 0.6289, 'learning_rate': 0.00021580743508455512, 'epoch': 6.69}

 56%|█████▌    | 15651/28080 [30:55:56<24:35:47,  7.12s/it]
 56%|█████▌    | 15652/28080 [30:56:03<24:29:45,  7.10s/it]
                                                           
{'loss': 0.6257, 'learning_rate': 0.00021577887057970646, 'epoch': 6.69}

 56%|█████▌    | 15652/28080 [30:56:03<24:29:45,  7.10s/it]
 56%|█████▌    | 15653/28080 [30:56:10<24:35:05,  7.12s/it]
                                                           
{'loss': 0.6006, 'learning_rate': 0.00021575030653013473, 'epoch': 6.69}

 56%|█████▌    | 15653/28080 [30:56:10<24:35:05,  7.12s/it]
 56%|█████▌    | 15654/28080 [30:56:18<24:40:39,  7.15s/it]
                                                           
{'loss': 0.6154, 'learning_rate': 0.00021572174293621978, 'epoch': 6.69}

 56%|█████▌    | 15654/28080 [30:56:18<24:40:39,  7.15s/it]
 56%|█████▌    | 15655/28080 [30:56:25<24:35:00,  7.12s/it]
                                                           
{'loss': 0.6211, 'learning_rate': 0.0002156931797983417, 'epoch': 6.69}

 56%|█████▌    | 15655/28080 [30:56:25<24:35:00,  7.12s/it]
 56%|█████▌    | 15656/28080 [30:56:32<24:30:24,  7.10s/it]
                                                           
{'loss': 0.6271, 'learning_rate': 0.00021566461711688042, 'epoch': 6.69}

 56%|█████▌    | 15656/28080 [30:56:32<24:30:24,  7.10s/it]
 56%|█████▌    | 15657/28080 [30:56:39<24:22:03,  7.06s/it]
                                                           
{'loss': 0.6233, 'learning_rate': 0.00021563605489221608, 'epoch': 6.69}

 56%|█████▌    | 15657/28080 [30:56:39<24:22:03,  7.06s/it]
 56%|█████▌    | 15658/28080 [30:56:46<24:29:52,  7.10s/it]
                                                           
{'loss': 0.6073, 'learning_rate': 0.00021560749312472848, 'epoch': 6.69}

 56%|█████▌    | 15658/28080 [30:56:46<24:29:52,  7.10s/it]
 56%|█████▌    | 15659/28080 [30:56:53<24:29:32,  7.10s/it]
                                                           
{'loss': 0.6097, 'learning_rate': 0.00021557893181479778, 'epoch': 6.69}

 56%|█████▌    | 15659/28080 [30:56:53<24:29:32,  7.10s/it]
 56%|█████▌    | 15660/28080 [30:57:00<24:28:26,  7.09s/it]
                                                           
{'loss': 0.6161, 'learning_rate': 0.00021555037096280383, 'epoch': 6.69}

 56%|█████▌    | 15660/28080 [30:57:00<24:28:26,  7.09s/it]
 56%|█████▌    | 15661/28080 [30:57:07<24:34:58,  7.13s/it]
                                                           
{'loss': 0.6011, 'learning_rate': 0.00021552181056912672, 'epoch': 6.69}

 56%|█████▌    | 15661/28080 [30:57:07<24:34:58,  7.13s/it]
 56%|█████▌    | 15662/28080 [30:57:14<24:39:05,  7.15s/it]
                                                           
{'loss': 0.625, 'learning_rate': 0.00021549325063414628, 'epoch': 6.69}

 56%|█████▌    | 15662/28080 [30:57:14<24:39:05,  7.15s/it]
 56%|█████▌    | 15663/28080 [30:57:22<24:39:26,  7.15s/it]
                                                           
{'loss': 0.63, 'learning_rate': 0.0002154646911582426, 'epoch': 6.69}

 56%|█████▌    | 15663/28080 [30:57:22<24:39:26,  7.15s/it]
 56%|█████▌    | 15664/28080 [30:57:29<24:35:36,  7.13s/it]
                                                           
{'loss': 0.6216, 'learning_rate': 0.00021543613214179547, 'epoch': 6.69}

 56%|█████▌    | 15664/28080 [30:57:29<24:35:36,  7.13s/it]
 56%|█████▌    | 15665/28080 [30:57:36<24:40:47,  7.16s/it]
                                                           
{'loss': 0.6125, 'learning_rate': 0.0002154075735851851, 'epoch': 6.69}

 56%|█████▌    | 15665/28080 [30:57:36<24:40:47,  7.16s/it]
 56%|█████▌    | 15666/28080 [30:57:43<24:35:32,  7.13s/it]
                                                           
{'loss': 0.6273, 'learning_rate': 0.00021537901548879113, 'epoch': 6.69}

 56%|█████▌    | 15666/28080 [30:57:43<24:35:32,  7.13s/it]
 56%|█████▌    | 15667/28080 [30:57:50<24:37:25,  7.14s/it]
                                                           
{'loss': 0.6119, 'learning_rate': 0.00021535045785299372, 'epoch': 6.69}

 56%|█████▌    | 15667/28080 [30:57:50<24:37:25,  7.14s/it]
 56%|█████▌    | 15668/28080 [30:57:57<24:40:30,  7.16s/it]
                                                           
{'loss': 0.6053, 'learning_rate': 0.0002153219006781727, 'epoch': 6.69}

 56%|█████▌    | 15668/28080 [30:57:57<24:40:30,  7.16s/it]
 56%|█████▌    | 15669/28080 [30:58:04<24:41:58,  7.16s/it]
                                                           
{'loss': 0.6098, 'learning_rate': 0.00021529334396470806, 'epoch': 6.69}

 56%|█████▌    | 15669/28080 [30:58:04<24:41:58,  7.16s/it]
 56%|█████▌    | 15670/28080 [30:58:12<24:42:37,  7.17s/it]
                                                           
{'loss': 0.6088, 'learning_rate': 0.00021526478771297965, 'epoch': 6.69}

 56%|█████▌    | 15670/28080 [30:58:12<24:42:37,  7.17s/it]
 56%|█████▌    | 15671/28080 [30:58:19<24:53:49,  7.22s/it]
                                                           
{'loss': 0.591, 'learning_rate': 0.0002152362319233674, 'epoch': 6.69}

 56%|█████▌    | 15671/28080 [30:58:19<24:53:49,  7.22s/it]
 56%|█████▌    | 15672/28080 [30:58:26<24:49:55,  7.20s/it]
                                                           
{'loss': 0.5937, 'learning_rate': 0.00021520767659625117, 'epoch': 6.69}

 56%|█████▌    | 15672/28080 [30:58:26<24:49:55,  7.20s/it]
 56%|█████▌    | 15673/28080 [30:58:33<24:46:38,  7.19s/it]
                                                           
{'loss': 0.6315, 'learning_rate': 0.00021517912173201102, 'epoch': 6.7}

 56%|█████▌    | 15673/28080 [30:58:33<24:46:38,  7.19s/it]
 56%|█████▌    | 15674/28080 [30:58:41<24:50:37,  7.21s/it]
                                                           
{'loss': 0.6327, 'learning_rate': 0.00021515056733102667, 'epoch': 6.7}

 56%|█████▌    | 15674/28080 [30:58:41<24:50:37,  7.21s/it]
 56%|█████▌    | 15675/28080 [30:58:48<24:42:18,  7.17s/it]
                                                           
{'loss': 0.6232, 'learning_rate': 0.00021512201339367806, 'epoch': 6.7}

 56%|█████▌    | 15675/28080 [30:58:48<24:42:18,  7.17s/it]
 56%|█████▌    | 15676/28080 [30:58:55<24:36:24,  7.14s/it]
                                                           
{'loss': 0.6033, 'learning_rate': 0.00021509345992034513, 'epoch': 6.7}

 56%|█████▌    | 15676/28080 [30:58:55<24:36:24,  7.14s/it]
 56%|█████▌    | 15677/28080 [30:59:02<24:30:49,  7.12s/it]
                                                           
{'loss': 0.5891, 'learning_rate': 0.00021506490691140763, 'epoch': 6.7}

 56%|█████▌    | 15677/28080 [30:59:02<24:30:49,  7.12s/it]
 56%|█████▌    | 15678/28080 [30:59:09<24:30:16,  7.11s/it]
                                                           
{'loss': 0.6496, 'learning_rate': 0.00021503635436724556, 'epoch': 6.7}

 56%|█████▌    | 15678/28080 [30:59:09<24:30:16,  7.11s/it]
 56%|█████▌    | 15679/28080 [30:59:16<24:32:51,  7.13s/it]
                                                           
{'loss': 0.6215, 'learning_rate': 0.0002150078022882387, 'epoch': 6.7}

 56%|█████▌    | 15679/28080 [30:59:16<24:32:51,  7.13s/it]
 56%|█████▌    | 15680/28080 [30:59:23<24:27:53,  7.10s/it]
                                                           
{'loss': 0.6068, 'learning_rate': 0.00021497925067476696, 'epoch': 6.7}

 56%|█████▌    | 15680/28080 [30:59:23<24:27:53,  7.10s/it]
 56%|█████▌    | 15681/28080 [30:59:30<24:28:23,  7.11s/it]
                                                           
{'loss': 0.6436, 'learning_rate': 0.00021495069952721002, 'epoch': 6.7}

 56%|█████▌    | 15681/28080 [30:59:30<24:28:23,  7.11s/it]
 56%|█████▌    | 15682/28080 [30:59:37<24:32:25,  7.13s/it]
                                                           
{'loss': 0.6169, 'learning_rate': 0.00021492214884594809, 'epoch': 6.7}

 56%|█████▌    | 15682/28080 [30:59:37<24:32:25,  7.13s/it]
 56%|█████▌    | 15683/28080 [30:59:44<24:30:27,  7.12s/it]
                                                           
{'loss': 0.6301, 'learning_rate': 0.0002148935986313606, 'epoch': 6.7}

 56%|█████▌    | 15683/28080 [30:59:45<24:30:27,  7.12s/it]
 56%|█████▌    | 15684/28080 [30:59:52<24:26:49,  7.10s/it]
                                                           
{'loss': 0.6161, 'learning_rate': 0.00021486504888382766, 'epoch': 6.7}

 56%|█████▌    | 15684/28080 [30:59:52<24:26:49,  7.10s/it]
 56%|█████▌    | 15685/28080 [30:59:59<24:26:08,  7.10s/it]
                                                           
{'loss': 0.6315, 'learning_rate': 0.00021483649960372893, 'epoch': 6.7}

 56%|█████▌    | 15685/28080 [30:59:59<24:26:08,  7.10s/it]
 56%|█████▌    | 15686/28080 [31:00:06<24:29:34,  7.11s/it]
                                                           
{'loss': 0.6073, 'learning_rate': 0.00021480795079144437, 'epoch': 6.7}

 56%|█████▌    | 15686/28080 [31:00:06<24:29:34,  7.11s/it]
 56%|█████▌    | 15687/28080 [31:00:13<24:33:11,  7.13s/it]
                                                           
{'loss': 0.6212, 'learning_rate': 0.00021477940244735367, 'epoch': 6.7}

 56%|█████▌    | 15687/28080 [31:00:13<24:33:11,  7.13s/it]
 56%|█████▌    | 15688/28080 [31:00:20<24:31:39,  7.13s/it]
                                                           
{'loss': 0.6322, 'learning_rate': 0.00021475085457183673, 'epoch': 6.7}

 56%|█████▌    | 15688/28080 [31:00:20<24:31:39,  7.13s/it]
 56%|█████▌    | 15689/28080 [31:00:27<24:34:38,  7.14s/it]
                                                           
{'loss': 0.6335, 'learning_rate': 0.00021472230716527323, 'epoch': 6.7}

 56%|█████▌    | 15689/28080 [31:00:27<24:34:38,  7.14s/it]
 56%|█████▌    | 15690/28080 [31:00:34<24:38:58,  7.16s/it]
                                                           
{'loss': 0.6061, 'learning_rate': 0.00021469376022804313, 'epoch': 6.7}

 56%|█████▌    | 15690/28080 [31:00:34<24:38:58,  7.16s/it]
 56%|█████▌    | 15691/28080 [31:00:42<24:35:30,  7.15s/it]
                                                           
{'loss': 0.6154, 'learning_rate': 0.00021466521376052605, 'epoch': 6.7}

 56%|█████▌    | 15691/28080 [31:00:42<24:35:30,  7.15s/it]
 56%|█████▌    | 15692/28080 [31:00:49<24:28:33,  7.11s/it]
                                                           
{'loss': 0.6271, 'learning_rate': 0.00021463666776310193, 'epoch': 6.7}

 56%|█████▌    | 15692/28080 [31:00:49<24:28:33,  7.11s/it]
 56%|█████▌    | 15693/28080 [31:00:56<24:29:30,  7.12s/it]
                                                           
{'loss': 0.6244, 'learning_rate': 0.0002146081222361504, 'epoch': 6.7}

 56%|█████▌    | 15693/28080 [31:00:56<24:29:30,  7.12s/it]
 56%|█████▌    | 15694/28080 [31:01:03<24:29:55,  7.12s/it]
                                                           
{'loss': 0.6071, 'learning_rate': 0.00021457957718005135, 'epoch': 6.7}

 56%|█████▌    | 15694/28080 [31:01:03<24:29:55,  7.12s/it]
 56%|█████▌    | 15695/28080 [31:01:10<24:31:43,  7.13s/it]
                                                           
{'loss': 0.5902, 'learning_rate': 0.00021455103259518434, 'epoch': 6.7}

 56%|█████▌    | 15695/28080 [31:01:10<24:31:43,  7.13s/it]
 56%|█████▌    | 15696/28080 [31:01:17<24:34:08,  7.14s/it]
                                                           
{'loss': 0.6199, 'learning_rate': 0.00021452248848192944, 'epoch': 6.71}

 56%|█████▌    | 15696/28080 [31:01:17<24:34:08,  7.14s/it]
 56%|█████▌    | 15697/28080 [31:01:24<24:32:58,  7.14s/it]
                                                           
{'loss': 0.6153, 'learning_rate': 0.00021449394484066608, 'epoch': 6.71}

 56%|█████▌    | 15697/28080 [31:01:24<24:32:58,  7.14s/it]
 56%|█████▌    | 15698/28080 [31:01:31<24:33:43,  7.14s/it]
                                                           
{'loss': 0.602, 'learning_rate': 0.0002144654016717743, 'epoch': 6.71}

 56%|█████▌    | 15698/28080 [31:01:31<24:33:43,  7.14s/it]
 56%|█████▌    | 15699/28080 [31:01:39<24:34:06,  7.14s/it]
                                                           
{'loss': 0.6139, 'learning_rate': 0.0002144368589756337, 'epoch': 6.71}

 56%|█████▌    | 15699/28080 [31:01:39<24:34:06,  7.14s/it]
 56%|█████▌    | 15700/28080 [31:01:46<24:36:43,  7.16s/it]
                                                           
{'loss': 0.6043, 'learning_rate': 0.00021440831675262386, 'epoch': 6.71}

 56%|█████▌    | 15700/28080 [31:01:46<24:36:43,  7.16s/it]
 56%|█████▌    | 15701/28080 [31:01:53<24:37:19,  7.16s/it]
                                                           
{'loss': 0.5928, 'learning_rate': 0.00021437977500312477, 'epoch': 6.71}

 56%|█████▌    | 15701/28080 [31:01:53<24:37:19,  7.16s/it]
 56%|█████▌    | 15702/28080 [31:02:00<24:28:32,  7.12s/it]
                                                           
{'loss': 0.6346, 'learning_rate': 0.0002143512337275159, 'epoch': 6.71}

 56%|█████▌    | 15702/28080 [31:02:00<24:28:32,  7.12s/it]
 56%|█████▌    | 15703/28080 [31:02:07<24:32:48,  7.14s/it]
                                                           
{'loss': 0.6191, 'learning_rate': 0.0002143226929261772, 'epoch': 6.71}

 56%|█████▌    | 15703/28080 [31:02:07<24:32:48,  7.14s/it]
 56%|█████▌    | 15704/28080 [31:02:14<24:35:10,  7.15s/it]
                                                           
{'loss': 0.6015, 'learning_rate': 0.0002142941525994882, 'epoch': 6.71}

 56%|█████▌    | 15704/28080 [31:02:14<24:35:10,  7.15s/it]
 56%|█████▌    | 15705/28080 [31:02:21<24:33:30,  7.14s/it]
                                                           
{'loss': 0.6282, 'learning_rate': 0.00021426561274782874, 'epoch': 6.71}

 56%|█████▌    | 15705/28080 [31:02:21<24:33:30,  7.14s/it]
 56%|█████▌    | 15706/28080 [31:02:29<24:38:29,  7.17s/it]
                                                           
{'loss': 0.6176, 'learning_rate': 0.00021423707337157836, 'epoch': 6.71}

 56%|█████▌    | 15706/28080 [31:02:29<24:38:29,  7.17s/it]
 56%|█████▌    | 15707/28080 [31:02:36<24:28:50,  7.12s/it]
                                                           
{'loss': 0.6139, 'learning_rate': 0.00021420853447111688, 'epoch': 6.71}

 56%|█████▌    | 15707/28080 [31:02:36<24:28:50,  7.12s/it]
 56%|█████▌    | 15708/28080 [31:02:43<24:27:44,  7.12s/it]
                                                           
{'loss': 0.609, 'learning_rate': 0.00021417999604682387, 'epoch': 6.71}

 56%|█████▌    | 15708/28080 [31:02:43<24:27:44,  7.12s/it]
 56%|█████▌    | 15709/28080 [31:02:50<24:24:45,  7.10s/it]
                                                           
{'loss': 0.6051, 'learning_rate': 0.00021415145809907914, 'epoch': 6.71}

 56%|█████▌    | 15709/28080 [31:02:50<24:24:45,  7.10s/it]
 56%|█████▌    | 15710/28080 [31:02:57<24:28:05,  7.12s/it]
                                                           
{'loss': 0.6183, 'learning_rate': 0.00021412292062826218, 'epoch': 6.71}

 56%|█████▌    | 15710/28080 [31:02:57<24:28:05,  7.12s/it]
 56%|█████▌    | 15711/28080 [31:03:04<24:32:28,  7.14s/it]
                                                           
{'loss': 0.6314, 'learning_rate': 0.0002140943836347528, 'epoch': 6.71}

 56%|█████▌    | 15711/28080 [31:03:04<24:32:28,  7.14s/it]
 56%|█████▌    | 15712/28080 [31:03:11<24:20:18,  7.08s/it]
                                                           
{'loss': 0.6057, 'learning_rate': 0.00021406584711893055, 'epoch': 6.71}

 56%|█████▌    | 15712/28080 [31:03:11<24:20:18,  7.08s/it]
 56%|█████▌    | 15713/28080 [31:03:18<24:21:33,  7.09s/it]
                                                           
{'loss': 0.6105, 'learning_rate': 0.00021403731108117523, 'epoch': 6.71}

 56%|█████▌    | 15713/28080 [31:03:18<24:21:33,  7.09s/it]
 56%|█████▌    | 15714/28080 [31:03:26<24:28:44,  7.13s/it]
                                                           
{'loss': 0.6072, 'learning_rate': 0.00021400877552186628, 'epoch': 6.71}

 56%|█████▌    | 15714/28080 [31:03:26<24:28:44,  7.13s/it]
 56%|█████▌    | 15715/28080 [31:03:33<24:24:29,  7.11s/it]
                                                           
{'loss': 0.6186, 'learning_rate': 0.00021398024044138353, 'epoch': 6.71}

 56%|█████▌    | 15715/28080 [31:03:33<24:24:29,  7.11s/it]
 56%|█████▌    | 15716/28080 [31:03:40<24:29:55,  7.13s/it]
                                                           
{'loss': 0.6047, 'learning_rate': 0.00021395170584010645, 'epoch': 6.71}

 56%|█████▌    | 15716/28080 [31:03:40<24:29:55,  7.13s/it]
 56%|█████▌    | 15717/28080 [31:03:47<24:25:00,  7.11s/it]
                                                           
{'loss': 0.625, 'learning_rate': 0.0002139231717184148, 'epoch': 6.71}

 56%|█████▌    | 15717/28080 [31:03:47<24:25:00,  7.11s/it]
 56%|█████▌    | 15718/28080 [31:03:54<24:30:35,  7.14s/it]
                                                           
{'loss': 0.6193, 'learning_rate': 0.0002138946380766881, 'epoch': 6.71}

 56%|█████▌    | 15718/28080 [31:03:54<24:30:35,  7.14s/it]
 56%|█████▌    | 15719/28080 [31:04:01<24:28:23,  7.13s/it]
                                                           
{'loss': 0.5997, 'learning_rate': 0.00021386610491530602, 'epoch': 6.72}

 56%|█████▌    | 15719/28080 [31:04:01<24:28:23,  7.13s/it]
 56%|█████▌    | 15720/28080 [31:04:08<24:30:28,  7.14s/it]
                                                           
{'loss': 0.6372, 'learning_rate': 0.0002138375722346481, 'epoch': 6.72}

 56%|█████▌    | 15720/28080 [31:04:08<24:30:28,  7.14s/it]
 56%|█████▌    | 15721/28080 [31:04:16<24:36:02,  7.17s/it]
                                                           
{'loss': 0.6315, 'learning_rate': 0.00021380904003509403, 'epoch': 6.72}

 56%|█████▌    | 15721/28080 [31:04:16<24:36:02,  7.17s/it]
 56%|█████▌    | 15722/28080 [31:04:23<24:35:28,  7.16s/it]
                                                           
{'loss': 0.6091, 'learning_rate': 0.00021378050831702324, 'epoch': 6.72}

 56%|█████▌    | 15722/28080 [31:04:23<24:35:28,  7.16s/it]
 56%|█████▌    | 15723/28080 [31:04:30<24:28:46,  7.13s/it]
                                                           
{'loss': 0.6036, 'learning_rate': 0.00021375197708081554, 'epoch': 6.72}

 56%|█████▌    | 15723/28080 [31:04:30<24:28:46,  7.13s/it]
 56%|█████▌    | 15724/28080 [31:04:37<24:34:39,  7.16s/it]
                                                           
{'loss': 0.5941, 'learning_rate': 0.00021372344632685037, 'epoch': 6.72}

 56%|█████▌    | 15724/28080 [31:04:37<24:34:39,  7.16s/it]
 56%|█████▌    | 15725/28080 [31:04:44<24:37:25,  7.17s/it]
                                                           
{'loss': 0.6308, 'learning_rate': 0.00021369491605550725, 'epoch': 6.72}

 56%|█████▌    | 15725/28080 [31:04:44<24:37:25,  7.17s/it]
 56%|█████▌    | 15726/28080 [31:04:51<24:34:39,  7.16s/it]
                                                           
{'loss': 0.6152, 'learning_rate': 0.0002136663862671659, 'epoch': 6.72}

 56%|█████▌    | 15726/28080 [31:04:51<24:34:39,  7.16s/it]
 56%|█████▌    | 15727/28080 [31:04:58<24:29:14,  7.14s/it]
                                                           
{'loss': 0.6122, 'learning_rate': 0.00021363785696220573, 'epoch': 6.72}

 56%|█████▌    | 15727/28080 [31:04:58<24:29:14,  7.14s/it]
 56%|█████▌    | 15728/28080 [31:05:06<24:31:08,  7.15s/it]
                                                           
{'loss': 0.6454, 'learning_rate': 0.0002136093281410064, 'epoch': 6.72}

 56%|█████▌    | 15728/28080 [31:05:06<24:31:08,  7.15s/it]
 56%|█████▌    | 15729/28080 [31:05:13<24:38:37,  7.18s/it]
                                                           
{'loss': 0.6241, 'learning_rate': 0.00021358079980394735, 'epoch': 6.72}

 56%|█████▌    | 15729/28080 [31:05:13<24:38:37,  7.18s/it]
 56%|█████▌    | 15730/28080 [31:05:20<24:46:03,  7.22s/it]
                                                           
{'loss': 0.6212, 'learning_rate': 0.0002135522719514083, 'epoch': 6.72}

 56%|█████▌    | 15730/28080 [31:05:20<24:46:03,  7.22s/it]
 56%|█████▌    | 15731/28080 [31:05:27<24:37:13,  7.18s/it]
                                                           
{'loss': 0.6004, 'learning_rate': 0.00021352374458376855, 'epoch': 6.72}

 56%|█████▌    | 15731/28080 [31:05:27<24:37:13,  7.18s/it]
 56%|█████▌    | 15732/28080 [31:05:34<24:28:39,  7.14s/it]
                                                           
{'loss': 0.6263, 'learning_rate': 0.0002134952177014079, 'epoch': 6.72}

 56%|█████▌    | 15732/28080 [31:05:34<24:28:39,  7.14s/it]
 56%|█████▌    | 15733/28080 [31:05:41<24:33:50,  7.16s/it]
                                                           
{'loss': 0.6329, 'learning_rate': 0.00021346669130470553, 'epoch': 6.72}

 56%|█████▌    | 15733/28080 [31:05:41<24:33:50,  7.16s/it]
 56%|█████▌    | 15734/28080 [31:05:49<24:31:47,  7.15s/it]
                                                           
{'loss': 0.6065, 'learning_rate': 0.00021343816539404125, 'epoch': 6.72}

 56%|█████▌    | 15734/28080 [31:05:49<24:31:47,  7.15s/it]
 56%|█████▌    | 15735/28080 [31:05:56<24:36:17,  7.18s/it]
                                                           
{'loss': 0.6081, 'learning_rate': 0.00021340963996979446, 'epoch': 6.72}

 56%|█████▌    | 15735/28080 [31:05:56<24:36:17,  7.18s/it]
 56%|█████▌    | 15736/28080 [31:06:03<24:29:10,  7.14s/it]
                                                           
{'loss': 0.6027, 'learning_rate': 0.00021338111503234466, 'epoch': 6.72}

 56%|█████▌    | 15736/28080 [31:06:03<24:29:10,  7.14s/it]
 56%|█████▌    | 15737/28080 [31:06:10<24:22:51,  7.11s/it]
                                                           
{'loss': 0.6107, 'learning_rate': 0.00021335259058207132, 'epoch': 6.72}

 56%|█████▌    | 15737/28080 [31:06:10<24:22:51,  7.11s/it]
 56%|█████▌    | 15738/28080 [31:06:17<24:18:05,  7.09s/it]
                                                           
{'loss': 0.608, 'learning_rate': 0.000213324066619354, 'epoch': 6.72}

 56%|█████▌    | 15738/28080 [31:06:17<24:18:05,  7.09s/it]
 56%|█████▌    | 15739/28080 [31:06:24<24:24:11,  7.12s/it]
                                                           
{'loss': 0.6277, 'learning_rate': 0.00021329554314457208, 'epoch': 6.72}

 56%|█████▌    | 15739/28080 [31:06:24<24:24:11,  7.12s/it]
 56%|█████▌    | 15740/28080 [31:06:31<24:24:30,  7.12s/it]
                                                           
{'loss': 0.5904, 'learning_rate': 0.00021326702015810517, 'epoch': 6.72}

 56%|█████▌    | 15740/28080 [31:06:31<24:24:30,  7.12s/it]
 56%|█████▌    | 15741/28080 [31:06:38<24:22:02,  7.11s/it]
                                                           
{'loss': 0.6012, 'learning_rate': 0.00021323849766033257, 'epoch': 6.72}

 56%|█████▌    | 15741/28080 [31:06:38<24:22:02,  7.11s/it]
 56%|█████▌    | 15742/28080 [31:06:46<24:24:29,  7.12s/it]
                                                           
{'loss': 0.6021, 'learning_rate': 0.0002132099756516339, 'epoch': 6.72}

 56%|█████▌    | 15742/28080 [31:06:46<24:24:29,  7.12s/it]
 56%|█████▌    | 15743/28080 [31:06:53<24:25:09,  7.13s/it]
                                                           
{'loss': 0.6033, 'learning_rate': 0.00021318145413238846, 'epoch': 6.73}

 56%|█████▌    | 15743/28080 [31:06:53<24:25:09,  7.13s/it]
 56%|█████▌    | 15744/28080 [31:07:00<24:28:06,  7.14s/it]
                                                           
{'loss': 0.6023, 'learning_rate': 0.00021315293310297594, 'epoch': 6.73}

 56%|█████▌    | 15744/28080 [31:07:00<24:28:06,  7.14s/it]
 56%|█████▌    | 15745/28080 [31:07:07<24:28:09,  7.14s/it]
                                                           
{'loss': 0.6466, 'learning_rate': 0.00021312441256377546, 'epoch': 6.73}

 56%|█████▌    | 15745/28080 [31:07:07<24:28:09,  7.14s/it]
 56%|█████▌    | 15746/28080 [31:07:14<24:21:38,  7.11s/it]
                                                           
{'loss': 0.6157, 'learning_rate': 0.00021309589251516676, 'epoch': 6.73}

 56%|█████▌    | 15746/28080 [31:07:14<24:21:38,  7.11s/it]
 56%|█████▌    | 15747/28080 [31:07:21<24:21:13,  7.11s/it]
                                                           
{'loss': 0.6173, 'learning_rate': 0.0002130673729575291, 'epoch': 6.73}

 56%|█████▌    | 15747/28080 [31:07:21<24:21:13,  7.11s/it]
 56%|█████▌    | 15748/28080 [31:07:28<24:19:25,  7.10s/it]
                                                           
{'loss': 0.6407, 'learning_rate': 0.00021303885389124195, 'epoch': 6.73}

 56%|█████▌    | 15748/28080 [31:07:28<24:19:25,  7.10s/it]
 56%|█████▌    | 15749/28080 [31:07:35<24:24:30,  7.13s/it]
                                                           
{'loss': 0.5909, 'learning_rate': 0.0002130103353166848, 'epoch': 6.73}

 56%|█████▌    | 15749/28080 [31:07:35<24:24:30,  7.13s/it]
 56%|█████▌    | 15750/28080 [31:07:42<24:22:47,  7.12s/it]
                                                           
{'loss': 0.618, 'learning_rate': 0.0002129818172342368, 'epoch': 6.73}

 56%|█████▌    | 15750/28080 [31:07:43<24:22:47,  7.12s/it]
 56%|█████▌    | 15751/28080 [31:07:50<24:20:48,  7.11s/it]
                                                           
{'loss': 0.607, 'learning_rate': 0.00021295329964427764, 'epoch': 6.73}

 56%|█████▌    | 15751/28080 [31:07:50<24:20:48,  7.11s/it]
 56%|█████▌    | 15752/28080 [31:07:57<24:11:05,  7.06s/it]
                                                           
{'loss': 0.6237, 'learning_rate': 0.00021292478254718655, 'epoch': 6.73}

 56%|█████▌    | 15752/28080 [31:07:57<24:11:05,  7.06s/it]
 56%|█████▌    | 15753/28080 [31:08:04<24:12:33,  7.07s/it]
                                                           
{'loss': 0.6242, 'learning_rate': 0.00021289626594334305, 'epoch': 6.73}

 56%|█████▌    | 15753/28080 [31:08:04<24:12:33,  7.07s/it]
 56%|█████▌    | 15754/28080 [31:08:11<24:10:52,  7.06s/it]
                                                           
{'loss': 0.6223, 'learning_rate': 0.0002128677498331264, 'epoch': 6.73}

 56%|█████▌    | 15754/28080 [31:08:11<24:10:52,  7.06s/it]
 56%|█████▌    | 15755/28080 [31:08:18<24:05:55,  7.04s/it]
                                                           
{'loss': 0.6273, 'learning_rate': 0.00021283923421691608, 'epoch': 6.73}

 56%|█████▌    | 15755/28080 [31:08:18<24:05:55,  7.04s/it]
 56%|█████▌    | 15756/28080 [31:08:25<24:08:12,  7.05s/it]
                                                           
{'loss': 0.6149, 'learning_rate': 0.00021281071909509138, 'epoch': 6.73}

 56%|█████▌    | 15756/28080 [31:08:25<24:08:12,  7.05s/it]
 56%|█████▌    | 15757/28080 [31:08:32<24:09:28,  7.06s/it]
                                                           
{'loss': 0.6134, 'learning_rate': 0.0002127822044680317, 'epoch': 6.73}

 56%|█████▌    | 15757/28080 [31:08:32<24:09:28,  7.06s/it]
 56%|█████▌    | 15758/28080 [31:08:39<24:12:07,  7.07s/it]
                                                           
{'loss': 0.6134, 'learning_rate': 0.00021275369033611638, 'epoch': 6.73}

 56%|█████▌    | 15758/28080 [31:08:39<24:12:07,  7.07s/it]
 56%|█████▌    | 15759/28080 [31:08:46<24:18:53,  7.10s/it]
                                                           
{'loss': 0.6042, 'learning_rate': 0.00021272517669972482, 'epoch': 6.73}

 56%|█████▌    | 15759/28080 [31:08:46<24:18:53,  7.10s/it]
 56%|█████▌    | 15760/28080 [31:08:53<24:18:01,  7.10s/it]
                                                           
{'loss': 0.6347, 'learning_rate': 0.00021269666355923622, 'epoch': 6.73}

 56%|█████▌    | 15760/28080 [31:08:53<24:18:01,  7.10s/it]
 56%|█████▌    | 15761/28080 [31:09:00<24:19:18,  7.11s/it]
                                                           
{'loss': 0.6219, 'learning_rate': 0.00021266815091503023, 'epoch': 6.73}

 56%|█████▌    | 15761/28080 [31:09:00<24:19:18,  7.11s/it]
 56%|█████▌    | 15762/28080 [31:09:07<24:20:14,  7.11s/it]
                                                           
{'loss': 0.6325, 'learning_rate': 0.00021263963876748577, 'epoch': 6.73}

 56%|█████▌    | 15762/28080 [31:09:07<24:20:14,  7.11s/it]
 56%|█████▌    | 15763/28080 [31:09:15<24:21:39,  7.12s/it]
                                                           
{'loss': 0.6211, 'learning_rate': 0.00021261112711698255, 'epoch': 6.73}

 56%|█████▌    | 15763/28080 [31:09:15<24:21:39,  7.12s/it]
 56%|█████▌    | 15764/28080 [31:09:22<24:19:07,  7.11s/it]
                                                           
{'loss': 0.6205, 'learning_rate': 0.00021258261596389955, 'epoch': 6.73}

 56%|█████▌    | 15764/28080 [31:09:22<24:19:07,  7.11s/it]
 56%|█████▌    | 15765/28080 [31:09:29<24:24:28,  7.14s/it]
                                                           
{'loss': 0.6249, 'learning_rate': 0.00021255410530861634, 'epoch': 6.73}

 56%|█████▌    | 15765/28080 [31:09:29<24:24:28,  7.14s/it]
 56%|█████▌    | 15766/28080 [31:09:36<24:32:20,  7.17s/it]
                                                           
{'loss': 0.6266, 'learning_rate': 0.0002125255951515121, 'epoch': 6.74}

 56%|█████▌    | 15766/28080 [31:09:36<24:32:20,  7.17s/it]
 56%|█████▌    | 15767/28080 [31:09:43<24:36:24,  7.19s/it]
                                                           
{'loss': 0.6055, 'learning_rate': 0.0002124970854929662, 'epoch': 6.74}

 56%|█████▌    | 15767/28080 [31:09:43<24:36:24,  7.19s/it]
 56%|█████▌    | 15768/28080 [31:09:50<24:31:33,  7.17s/it]
                                                           
{'loss': 0.6216, 'learning_rate': 0.00021246857633335783, 'epoch': 6.74}

 56%|█████▌    | 15768/28080 [31:09:50<24:31:33,  7.17s/it]
 56%|█████▌    | 15769/28080 [31:09:58<24:27:06,  7.15s/it]
                                                           
{'loss': 0.606, 'learning_rate': 0.0002124400676730664, 'epoch': 6.74}

 56%|█████▌    | 15769/28080 [31:09:58<24:27:06,  7.15s/it]
 56%|█████▌    | 15770/28080 [31:10:05<24:28:50,  7.16s/it]
                                                           
{'loss': 0.6009, 'learning_rate': 0.00021241155951247105, 'epoch': 6.74}

 56%|█████▌    | 15770/28080 [31:10:05<24:28:50,  7.16s/it]
 56%|█████▌    | 15771/28080 [31:10:12<24:30:33,  7.17s/it]
                                                           
{'loss': 0.6262, 'learning_rate': 0.00021238305185195116, 'epoch': 6.74}

 56%|█████▌    | 15771/28080 [31:10:12<24:30:33,  7.17s/it]
 56%|█████▌    | 15772/28080 [31:10:19<24:30:15,  7.17s/it]
                                                           
{'loss': 0.6345, 'learning_rate': 0.00021235454469188594, 'epoch': 6.74}

 56%|█████▌    | 15772/28080 [31:10:19<24:30:15,  7.17s/it]
 56%|█████▌    | 15773/28080 [31:10:26<24:25:52,  7.15s/it]
                                                           
{'loss': 0.6278, 'learning_rate': 0.0002123260380326547, 'epoch': 6.74}

 56%|█████▌    | 15773/28080 [31:10:26<24:25:52,  7.15s/it]
 56%|█████▌    | 15774/28080 [31:10:33<24:25:26,  7.15s/it]
                                                           
{'loss': 0.6117, 'learning_rate': 0.0002122975318746367, 'epoch': 6.74}

 56%|█████▌    | 15774/28080 [31:10:33<24:25:26,  7.15s/it]
 56%|█████▌    | 15775/28080 [31:10:40<24:22:58,  7.13s/it]
                                                           
{'loss': 0.6374, 'learning_rate': 0.00021226902621821104, 'epoch': 6.74}

 56%|█████▌    | 15775/28080 [31:10:40<24:22:58,  7.13s/it]
 56%|█████▌    | 15776/28080 [31:10:48<24:26:18,  7.15s/it]
                                                           
{'loss': 0.6306, 'learning_rate': 0.00021224052106375712, 'epoch': 6.74}

 56%|█████▌    | 15776/28080 [31:10:48<24:26:18,  7.15s/it]
 56%|█████▌    | 15777/28080 [31:10:55<24:26:46,  7.15s/it]
                                                           
{'loss': 0.6109, 'learning_rate': 0.00021221201641165403, 'epoch': 6.74}

 56%|█████▌    | 15777/28080 [31:10:55<24:26:46,  7.15s/it]
 56%|█████▌    | 15778/28080 [31:11:02<24:26:19,  7.15s/it]
                                                           
{'loss': 0.6159, 'learning_rate': 0.00021218351226228122, 'epoch': 6.74}

 56%|█████▌    | 15778/28080 [31:11:02<24:26:19,  7.15s/it]
 56%|█████▌    | 15779/28080 [31:11:09<24:26:55,  7.16s/it]
                                                           
{'loss': 0.6092, 'learning_rate': 0.0002121550086160176, 'epoch': 6.74}

 56%|█████▌    | 15779/28080 [31:11:09<24:26:55,  7.16s/it]
 56%|█████▌    | 15780/28080 [31:11:16<24:21:41,  7.13s/it]
                                                           
{'loss': 0.6001, 'learning_rate': 0.00021212650547324272, 'epoch': 6.74}

 56%|█████▌    | 15780/28080 [31:11:16<24:21:41,  7.13s/it]
 56%|█████▌    | 15781/28080 [31:11:23<24:19:29,  7.12s/it]
                                                           
{'loss': 0.6354, 'learning_rate': 0.00021209800283433544, 'epoch': 6.74}

 56%|█████▌    | 15781/28080 [31:11:23<24:19:29,  7.12s/it]
 56%|█████▌    | 15782/28080 [31:11:31<24:29:12,  7.17s/it]
                                                           
{'loss': 0.6245, 'learning_rate': 0.00021206950069967525, 'epoch': 6.74}

 56%|█████▌    | 15782/28080 [31:11:31<24:29:12,  7.17s/it]
 56%|█████▌    | 15783/28080 [31:11:38<24:24:53,  7.15s/it]
                                                           
{'loss': 0.6455, 'learning_rate': 0.00021204099906964115, 'epoch': 6.74}

 56%|█████▌    | 15783/28080 [31:11:38<24:24:53,  7.15s/it]
 56%|█████▌    | 15784/28080 [31:11:45<24:15:20,  7.10s/it]
                                                           
{'loss': 0.6203, 'learning_rate': 0.00021201249794461247, 'epoch': 6.74}

 56%|█████▌    | 15784/28080 [31:11:45<24:15:20,  7.10s/it]
 56%|█████▌    | 15785/28080 [31:11:52<24:14:56,  7.10s/it]
                                                           
{'loss': 0.6039, 'learning_rate': 0.00021198399732496825, 'epoch': 6.74}

 56%|█████▌    | 15785/28080 [31:11:52<24:14:56,  7.10s/it]
 56%|█████▌    | 15786/28080 [31:11:59<24:14:30,  7.10s/it]
                                                           
{'loss': 0.6173, 'learning_rate': 0.0002119554972110878, 'epoch': 6.74}

 56%|█████▌    | 15786/28080 [31:11:59<24:14:30,  7.10s/it]
 56%|█████▌    | 15787/28080 [31:12:06<24:08:59,  7.07s/it]
                                                           
{'loss': 0.6159, 'learning_rate': 0.00021192699760335016, 'epoch': 6.74}

 56%|█████▌    | 15787/28080 [31:12:06<24:08:59,  7.07s/it]
 56%|█████▌    | 15788/28080 [31:12:13<24:13:55,  7.10s/it]
                                                           
{'loss': 0.6218, 'learning_rate': 0.0002118984985021346, 'epoch': 6.74}

 56%|█████▌    | 15788/28080 [31:12:13<24:13:55,  7.10s/it]
 56%|█████▌    | 15789/28080 [31:12:20<24:14:37,  7.10s/it]
                                                           
{'loss': 0.6033, 'learning_rate': 0.00021186999990782014, 'epoch': 6.74}

 56%|█████▌    | 15789/28080 [31:12:20<24:14:37,  7.10s/it]
 56%|█████▌    | 15790/28080 [31:12:27<24:19:33,  7.13s/it]
                                                           
{'loss': 0.6186, 'learning_rate': 0.000211841501820786, 'epoch': 6.75}

 56%|█████▌    | 15790/28080 [31:12:27<24:19:33,  7.13s/it]
 56%|█████▌    | 15791/28080 [31:12:34<24:17:12,  7.11s/it]
                                                           
{'loss': 0.6176, 'learning_rate': 0.00021181300424141124, 'epoch': 6.75}

 56%|█████▌    | 15791/28080 [31:12:34<24:17:12,  7.11s/it]
 56%|█████▌    | 15792/28080 [31:12:42<24:23:07,  7.14s/it]
                                                           
{'loss': 0.6015, 'learning_rate': 0.00021178450717007524, 'epoch': 6.75}

 56%|█████▌    | 15792/28080 [31:12:42<24:23:07,  7.14s/it]
 56%|█████▌    | 15793/28080 [31:12:49<24:16:00,  7.11s/it]
                                                           
{'loss': 0.5884, 'learning_rate': 0.0002117560106071568, 'epoch': 6.75}

 56%|█████▌    | 15793/28080 [31:12:49<24:16:00,  7.11s/it]
 56%|█████▌    | 15794/28080 [31:12:56<24:27:10,  7.17s/it]
                                                           
{'loss': 0.6152, 'learning_rate': 0.0002117275145530353, 'epoch': 6.75}

 56%|█████▌    | 15794/28080 [31:12:56<24:27:10,  7.17s/it]
 56%|█████▋    | 15795/28080 [31:13:03<24:23:54,  7.15s/it]
                                                           
{'loss': 0.6041, 'learning_rate': 0.00021169901900808962, 'epoch': 6.75}

 56%|█████▋    | 15795/28080 [31:13:03<24:23:54,  7.15s/it]
 56%|█████▋    | 15796/28080 [31:13:10<24:21:18,  7.14s/it]
                                                           
{'loss': 0.6288, 'learning_rate': 0.0002116705239726991, 'epoch': 6.75}

 56%|█████▋    | 15796/28080 [31:13:10<24:21:18,  7.14s/it]
 56%|█████▋    | 15797/28080 [31:13:17<24:20:42,  7.14s/it]
                                                           
{'loss': 0.6265, 'learning_rate': 0.00021164202944724258, 'epoch': 6.75}

 56%|█████▋    | 15797/28080 [31:13:17<24:20:42,  7.14s/it]
 56%|█████▋    | 15798/28080 [31:13:24<24:19:53,  7.13s/it]
                                                           
{'loss': 0.5981, 'learning_rate': 0.0002116135354320994, 'epoch': 6.75}

 56%|█████▋    | 15798/28080 [31:13:24<24:19:53,  7.13s/it]
 56%|█████▋    | 15799/28080 [31:13:32<24:21:19,  7.14s/it]
                                                           
{'loss': 0.6167, 'learning_rate': 0.00021158504192764856, 'epoch': 6.75}

 56%|█████▋    | 15799/28080 [31:13:32<24:21:19,  7.14s/it]
 56%|█████▋    | 15800/28080 [31:13:39<24:21:23,  7.14s/it]
                                                           
{'loss': 0.6207, 'learning_rate': 0.00021155654893426898, 'epoch': 6.75}

 56%|█████▋    | 15800/28080 [31:13:39<24:21:23,  7.14s/it]
 56%|█████▋    | 15801/28080 [31:13:46<24:20:22,  7.14s/it]
                                                           
{'loss': 0.6003, 'learning_rate': 0.00021152805645233995, 'epoch': 6.75}

 56%|█████▋    | 15801/28080 [31:13:46<24:20:22,  7.14s/it]
 56%|█████▋    | 15802/28080 [31:13:53<24:24:27,  7.16s/it]
                                                           
{'loss': 0.6104, 'learning_rate': 0.00021149956448224039, 'epoch': 6.75}

 56%|█████▋    | 15802/28080 [31:13:53<24:24:27,  7.16s/it]
 56%|█████▋    | 15803/28080 [31:14:00<24:25:45,  7.16s/it]
                                                           
{'loss': 0.6118, 'learning_rate': 0.00021147107302434942, 'epoch': 6.75}

 56%|█████▋    | 15803/28080 [31:14:00<24:25:45,  7.16s/it]
 56%|█████▋    | 15804/28080 [31:14:07<24:27:33,  7.17s/it]
                                                           
{'loss': 0.5907, 'learning_rate': 0.00021144258207904607, 'epoch': 6.75}

 56%|█████▋    | 15804/28080 [31:14:07<24:27:33,  7.17s/it]
 56%|█████▋    | 15805/28080 [31:14:15<24:23:44,  7.15s/it]
                                                           
{'loss': 0.6191, 'learning_rate': 0.00021141409164670942, 'epoch': 6.75}

 56%|█████▋    | 15805/28080 [31:14:15<24:23:44,  7.15s/it]
 56%|█████▋    | 15806/28080 [31:14:22<24:20:51,  7.14s/it]
                                                           
{'loss': 0.6308, 'learning_rate': 0.00021138560172771843, 'epoch': 6.75}

 56%|█████▋    | 15806/28080 [31:14:22<24:20:51,  7.14s/it]
 56%|█████▋    | 15807/28080 [31:14:29<24:23:03,  7.15s/it]
                                                           
{'loss': 0.6218, 'learning_rate': 0.0002113571123224522, 'epoch': 6.75}

 56%|█████▋    | 15807/28080 [31:14:29<24:23:03,  7.15s/it]
 56%|█████▋    | 15808/28080 [31:14:36<24:26:04,  7.17s/it]
                                                           
{'loss': 0.6012, 'learning_rate': 0.00021132862343128963, 'epoch': 6.75}

 56%|█████▋    | 15808/28080 [31:14:36<24:26:04,  7.17s/it]
 56%|█████▋    | 15809/28080 [31:14:43<24:26:37,  7.17s/it]
                                                           
{'loss': 0.6026, 'learning_rate': 0.00021130013505461, 'epoch': 6.75}

 56%|█████▋    | 15809/28080 [31:14:43<24:26:37,  7.17s/it]
 56%|█████▋    | 15810/28080 [31:14:50<24:30:46,  7.19s/it]
                                                           
{'loss': 0.6048, 'learning_rate': 0.000211271647192792, 'epoch': 6.75}

 56%|█████▋    | 15810/28080 [31:14:50<24:30:46,  7.19s/it]
 56%|█████▋    | 15811/28080 [31:14:58<24:33:11,  7.20s/it]
                                                           
{'loss': 0.5974, 'learning_rate': 0.00021124315984621491, 'epoch': 6.75}

 56%|█████▋    | 15811/28080 [31:14:58<24:33:11,  7.20s/it]
 56%|█████▋    | 15812/28080 [31:15:05<24:27:01,  7.17s/it]
                                                           
{'loss': 0.6386, 'learning_rate': 0.00021121467301525747, 'epoch': 6.75}

 56%|█████▋    | 15812/28080 [31:15:05<24:27:01,  7.17s/it]
 56%|█████▋    | 15813/28080 [31:15:12<24:21:21,  7.15s/it]
                                                           
{'loss': 0.6235, 'learning_rate': 0.00021118618670029886, 'epoch': 6.76}

 56%|█████▋    | 15813/28080 [31:15:12<24:21:21,  7.15s/it]
 56%|█████▋    | 15814/28080 [31:15:19<24:19:42,  7.14s/it]
                                                           
{'loss': 0.6243, 'learning_rate': 0.00021115770090171797, 'epoch': 6.76}

 56%|█████▋    | 15814/28080 [31:15:19<24:19:42,  7.14s/it]
 56%|█████▋    | 15815/28080 [31:15:26<24:17:33,  7.13s/it]
                                                           
{'loss': 0.6245, 'learning_rate': 0.00021112921561989385, 'epoch': 6.76}

 56%|█████▋    | 15815/28080 [31:15:26<24:17:33,  7.13s/it]
 56%|█████▋    | 15816/28080 [31:15:33<24:09:39,  7.09s/it]
                                                           
{'loss': 0.6188, 'learning_rate': 0.00021110073085520533, 'epoch': 6.76}

 56%|█████▋    | 15816/28080 [31:15:33<24:09:39,  7.09s/it]
 56%|█████▋    | 15817/28080 [31:15:40<24:09:35,  7.09s/it]
                                                           
{'loss': 0.6061, 'learning_rate': 0.00021107224660803155, 'epoch': 6.76}

 56%|█████▋    | 15817/28080 [31:15:40<24:09:35,  7.09s/it]
 56%|█████▋    | 15818/28080 [31:15:47<24:13:32,  7.11s/it]
                                                           
{'loss': 0.6157, 'learning_rate': 0.0002110437628787513, 'epoch': 6.76}

 56%|█████▋    | 15818/28080 [31:15:47<24:13:32,  7.11s/it]
 56%|█████▋    | 15819/28080 [31:15:54<24:15:40,  7.12s/it]
                                                           
{'loss': 0.6144, 'learning_rate': 0.00021101527966774363, 'epoch': 6.76}

 56%|█████▋    | 15819/28080 [31:15:54<24:15:40,  7.12s/it]
 56%|█████▋    | 15820/28080 [31:16:02<24:16:35,  7.13s/it]
                                                           
{'loss': 0.6233, 'learning_rate': 0.0002109867969753874, 'epoch': 6.76}

 56%|█████▋    | 15820/28080 [31:16:02<24:16:35,  7.13s/it]
 56%|█████▋    | 15821/28080 [31:16:09<24:15:10,  7.12s/it]
                                                           
{'loss': 0.6078, 'learning_rate': 0.0002109583148020617, 'epoch': 6.76}

 56%|█████▋    | 15821/28080 [31:16:09<24:15:10,  7.12s/it]
 56%|█████▋    | 15822/28080 [31:16:16<24:13:50,  7.12s/it]
                                                           
{'loss': 0.6224, 'learning_rate': 0.00021092983314814517, 'epoch': 6.76}

 56%|█████▋    | 15822/28080 [31:16:16<24:13:50,  7.12s/it]
 56%|█████▋    | 15823/28080 [31:16:23<24:11:41,  7.11s/it]
                                                           
{'loss': 0.5916, 'learning_rate': 0.00021090135201401708, 'epoch': 6.76}

 56%|█████▋    | 15823/28080 [31:16:23<24:11:41,  7.11s/it]
 56%|█████▋    | 15824/28080 [31:16:30<24:09:44,  7.10s/it]
                                                           
{'loss': 0.6205, 'learning_rate': 0.0002108728714000561, 'epoch': 6.76}

 56%|█████▋    | 15824/28080 [31:16:30<24:09:44,  7.10s/it]
 56%|█████▋    | 15825/28080 [31:16:37<24:15:19,  7.13s/it]
                                                           
{'loss': 0.6138, 'learning_rate': 0.00021084439130664119, 'epoch': 6.76}

 56%|█████▋    | 15825/28080 [31:16:37<24:15:19,  7.13s/it]
 56%|█████▋    | 15826/28080 [31:16:44<24:13:57,  7.12s/it]
                                                           
{'loss': 0.602, 'learning_rate': 0.00021081591173415128, 'epoch': 6.76}

 56%|█████▋    | 15826/28080 [31:16:44<24:13:57,  7.12s/it]
 56%|█████▋    | 15827/28080 [31:16:51<24:17:47,  7.14s/it]
                                                           
{'loss': 0.6091, 'learning_rate': 0.00021078743268296513, 'epoch': 6.76}

 56%|█████▋    | 15827/28080 [31:16:51<24:17:47,  7.14s/it]
 56%|█████▋    | 15828/28080 [31:16:59<24:15:51,  7.13s/it]
                                                           
{'loss': 0.6109, 'learning_rate': 0.0002107589541534619, 'epoch': 6.76}

 56%|█████▋    | 15828/28080 [31:16:59<24:15:51,  7.13s/it]
 56%|█████▋    | 15829/28080 [31:17:06<24:07:19,  7.09s/it]
                                                           
{'loss': 0.6166, 'learning_rate': 0.00021073047614602014, 'epoch': 6.76}

 56%|█████▋    | 15829/28080 [31:17:06<24:07:19,  7.09s/it]
 56%|█████▋    | 15830/28080 [31:17:13<24:06:51,  7.09s/it]
                                                           
{'loss': 0.6194, 'learning_rate': 0.00021070199866101902, 'epoch': 6.76}

 56%|█████▋    | 15830/28080 [31:17:13<24:06:51,  7.09s/it]
 56%|█████▋    | 15831/28080 [31:17:20<24:09:39,  7.10s/it]
                                                           
{'loss': 0.6222, 'learning_rate': 0.0002106735216988372, 'epoch': 6.76}

 56%|█████▋    | 15831/28080 [31:17:20<24:09:39,  7.10s/it]
 56%|█████▋    | 15832/28080 [31:17:27<24:13:40,  7.12s/it]
                                                           
{'loss': 0.6072, 'learning_rate': 0.00021064504525985362, 'epoch': 6.76}

 56%|█████▋    | 15832/28080 [31:17:27<24:13:40,  7.12s/it]
 56%|█████▋    | 15833/28080 [31:17:34<24:14:51,  7.13s/it]
                                                           
{'loss': 0.6119, 'learning_rate': 0.00021061656934444708, 'epoch': 6.76}

 56%|█████▋    | 15833/28080 [31:17:34<24:14:51,  7.13s/it]
 56%|█████▋    | 15834/28080 [31:17:41<24:15:50,  7.13s/it]
                                                           
{'loss': 0.6264, 'learning_rate': 0.00021058809395299653, 'epoch': 6.76}

 56%|█████▋    | 15834/28080 [31:17:41<24:15:50,  7.13s/it]
 56%|█████▋    | 15835/28080 [31:17:48<24:13:44,  7.12s/it]
                                                           
{'loss': 0.5995, 'learning_rate': 0.00021055961908588068, 'epoch': 6.76}

 56%|█████▋    | 15835/28080 [31:17:48<24:13:44,  7.12s/it]
 56%|█████▋    | 15836/28080 [31:17:55<24:09:56,  7.11s/it]
                                                           
{'loss': 0.6015, 'learning_rate': 0.00021053114474347843, 'epoch': 6.76}

 56%|█████▋    | 15836/28080 [31:17:55<24:09:56,  7.11s/it]
 56%|█████▋    | 15837/28080 [31:18:03<24:12:05,  7.12s/it]
                                                           
{'loss': 0.6316, 'learning_rate': 0.00021050267092616854, 'epoch': 6.77}

 56%|█████▋    | 15837/28080 [31:18:03<24:12:05,  7.12s/it]
 56%|█████▋    | 15838/28080 [31:18:10<24:11:47,  7.12s/it]
                                                           
{'loss': 0.622, 'learning_rate': 0.0002104741976343299, 'epoch': 6.77}

 56%|█████▋    | 15838/28080 [31:18:10<24:11:47,  7.12s/it]
 56%|█████▋    | 15839/28080 [31:18:17<24:17:23,  7.14s/it]
                                                           
{'loss': 0.6307, 'learning_rate': 0.0002104457248683412, 'epoch': 6.77}

 56%|█████▋    | 15839/28080 [31:18:17<24:17:23,  7.14s/it]
 56%|█████▋    | 15840/28080 [31:18:24<24:13:15,  7.12s/it]
                                                           
{'loss': 0.6235, 'learning_rate': 0.0002104172526285815, 'epoch': 6.77}

 56%|█████▋    | 15840/28080 [31:18:24<24:13:15,  7.12s/it]
 56%|█████▋    | 15841/28080 [31:18:31<24:08:52,  7.10s/it]
                                                           
{'loss': 0.6012, 'learning_rate': 0.00021038878091542924, 'epoch': 6.77}

 56%|█████▋    | 15841/28080 [31:18:31<24:08:52,  7.10s/it]
 56%|█████▋    | 15842/28080 [31:18:38<24:11:17,  7.12s/it]
                                                           
{'loss': 0.6119, 'learning_rate': 0.00021036030972926354, 'epoch': 6.77}

 56%|█████▋    | 15842/28080 [31:18:38<24:11:17,  7.12s/it]
 56%|█████▋    | 15843/28080 [31:18:45<24:08:33,  7.10s/it]
                                                           
{'loss': 0.6129, 'learning_rate': 0.0002103318390704629, 'epoch': 6.77}

 56%|█████▋    | 15843/28080 [31:18:45<24:08:33,  7.10s/it]
 56%|█████▋    | 15844/28080 [31:18:52<24:12:46,  7.12s/it]
                                                           
{'loss': 0.6171, 'learning_rate': 0.00021030336893940627, 'epoch': 6.77}

 56%|█████▋    | 15844/28080 [31:18:52<24:12:46,  7.12s/it]
 56%|█████▋    | 15845/28080 [31:18:59<24:09:32,  7.11s/it]
                                                           
{'loss': 0.6022, 'learning_rate': 0.00021027489933647233, 'epoch': 6.77}

 56%|█████▋    | 15845/28080 [31:18:59<24:09:32,  7.11s/it]
 56%|█████▋    | 15846/28080 [31:19:07<24:15:58,  7.14s/it]
                                                           
{'loss': 0.6072, 'learning_rate': 0.00021024643026203992, 'epoch': 6.77}

 56%|█████▋    | 15846/28080 [31:19:07<24:15:58,  7.14s/it]
 56%|█████▋    | 15847/28080 [31:19:14<24:14:05,  7.13s/it]
                                                           
{'loss': 0.616, 'learning_rate': 0.0002102179617164877, 'epoch': 6.77}

 56%|█████▋    | 15847/28080 [31:19:14<24:14:05,  7.13s/it]
 56%|█████▋    | 15848/28080 [31:19:21<24:14:56,  7.14s/it]
                                                           
{'loss': 0.6175, 'learning_rate': 0.00021018949370019455, 'epoch': 6.77}

 56%|█████▋    | 15848/28080 [31:19:21<24:14:56,  7.14s/it]
 56%|█████▋    | 15849/28080 [31:19:28<24:14:06,  7.13s/it]
                                                           
{'loss': 0.6158, 'learning_rate': 0.0002101610262135391, 'epoch': 6.77}

 56%|█████▋    | 15849/28080 [31:19:28<24:14:06,  7.13s/it]
 56%|█████▋    | 15850/28080 [31:19:35<24:13:38,  7.13s/it]
                                                           
{'loss': 0.6081, 'learning_rate': 0.0002101325592569, 'epoch': 6.77}

 56%|█████▋    | 15850/28080 [31:19:35<24:13:38,  7.13s/it]
 56%|█████▋    | 15851/28080 [31:19:42<24:11:39,  7.12s/it]
                                                           
{'loss': 0.6, 'learning_rate': 0.00021010409283065616, 'epoch': 6.77}

 56%|█████▋    | 15851/28080 [31:19:42<24:11:39,  7.12s/it]
 56%|█████▋    | 15852/28080 [31:19:50<24:18:27,  7.16s/it]
                                                           
{'loss': 0.6288, 'learning_rate': 0.0002100756269351861, 'epoch': 6.77}

 56%|█████▋    | 15852/28080 [31:19:50<24:18:27,  7.16s/it]
 56%|█████▋    | 15853/28080 [31:19:57<24:18:37,  7.16s/it]
                                                           
{'loss': 0.593, 'learning_rate': 0.00021004716157086876, 'epoch': 6.77}

 56%|█████▋    | 15853/28080 [31:19:57<24:18:37,  7.16s/it]
 56%|█████▋    | 15854/28080 [31:20:04<24:19:50,  7.16s/it]
                                                           
{'loss': 0.6148, 'learning_rate': 0.00021001869673808264, 'epoch': 6.77}

 56%|█████▋    | 15854/28080 [31:20:04<24:19:50,  7.16s/it]
 56%|█████▋    | 15855/28080 [31:20:11<24:20:49,  7.17s/it]
                                                           
{'loss': 0.6022, 'learning_rate': 0.00020999023243720654, 'epoch': 6.77}

 56%|█████▋    | 15855/28080 [31:20:11<24:20:49,  7.17s/it]
 56%|█████▋    | 15856/28080 [31:20:18<24:12:06,  7.13s/it]
                                                           
{'loss': 0.5997, 'learning_rate': 0.0002099617686686191, 'epoch': 6.77}

 56%|█████▋    | 15856/28080 [31:20:18<24:12:06,  7.13s/it]
 56%|█████▋    | 15857/28080 [31:20:25<24:06:34,  7.10s/it]
                                                           
{'loss': 0.6236, 'learning_rate': 0.00020993330543269905, 'epoch': 6.77}

 56%|█████▋    | 15857/28080 [31:20:25<24:06:34,  7.10s/it]
 56%|█████▋    | 15858/28080 [31:20:32<24:12:35,  7.13s/it]
                                                           
{'loss': 0.6239, 'learning_rate': 0.00020990484272982496, 'epoch': 6.77}

 56%|█████▋    | 15858/28080 [31:20:32<24:12:35,  7.13s/it]
 56%|█████▋    | 15859/28080 [31:20:39<24:10:28,  7.12s/it]
                                                           
{'loss': 0.6124, 'learning_rate': 0.00020987638056037573, 'epoch': 6.77}

 56%|█████▋    | 15859/28080 [31:20:39<24:10:28,  7.12s/it]
 56%|█████▋    | 15860/28080 [31:20:47<24:13:35,  7.14s/it]
                                                           
{'loss': 0.6067, 'learning_rate': 0.0002098479189247297, 'epoch': 6.78}

 56%|█████▋    | 15860/28080 [31:20:47<24:13:35,  7.14s/it]
 56%|█████▋    | 15861/28080 [31:20:54<24:14:06,  7.14s/it]
                                                           
{'loss': 0.6136, 'learning_rate': 0.00020981945782326577, 'epoch': 6.78}

 56%|█████▋    | 15861/28080 [31:20:54<24:14:06,  7.14s/it]
 56%|█████▋    | 15862/28080 [31:21:01<24:14:42,  7.14s/it]
                                                           
{'loss': 0.6131, 'learning_rate': 0.00020979099725636246, 'epoch': 6.78}

 56%|█████▋    | 15862/28080 [31:21:01<24:14:42,  7.14s/it]
 56%|█████▋    | 15863/28080 [31:21:08<24:09:08,  7.12s/it]
                                                           
{'loss': 0.6052, 'learning_rate': 0.00020976253722439854, 'epoch': 6.78}

 56%|█████▋    | 15863/28080 [31:21:08<24:09:08,  7.12s/it]
 56%|█████▋    | 15864/28080 [31:21:15<24:11:01,  7.13s/it]
                                                           
{'loss': 0.6139, 'learning_rate': 0.00020973407772775242, 'epoch': 6.78}

 56%|█████▋    | 15864/28080 [31:21:15<24:11:01,  7.13s/it]
 56%|█████▋    | 15865/28080 [31:21:22<24:12:09,  7.13s/it]
                                                           
{'loss': 0.6182, 'learning_rate': 0.00020970561876680299, 'epoch': 6.78}

 56%|█████▋    | 15865/28080 [31:21:22<24:12:09,  7.13s/it]
 57%|█████▋    | 15866/28080 [31:21:29<24:17:44,  7.16s/it]
                                                           
{'loss': 0.6179, 'learning_rate': 0.00020967716034192864, 'epoch': 6.78}

 57%|█████▋    | 15866/28080 [31:21:29<24:17:44,  7.16s/it]
 57%|█████▋    | 15867/28080 [31:21:37<24:16:22,  7.15s/it]
                                                           
{'loss': 0.6088, 'learning_rate': 0.00020964870245350814, 'epoch': 6.78}

 57%|█████▋    | 15867/28080 [31:21:37<24:16:22,  7.15s/it]
 57%|█████▋    | 15868/28080 [31:21:44<24:19:59,  7.17s/it]
                                                           
{'loss': 0.6357, 'learning_rate': 0.00020962024510191995, 'epoch': 6.78}

 57%|█████▋    | 15868/28080 [31:21:44<24:19:59,  7.17s/it]
 57%|█████▋    | 15869/28080 [31:21:51<24:10:28,  7.13s/it]
                                                           
{'loss': 0.6178, 'learning_rate': 0.00020959178828754282, 'epoch': 6.78}

 57%|█████▋    | 15869/28080 [31:21:51<24:10:28,  7.13s/it]
 57%|█████▋    | 15870/28080 [31:21:58<24:06:16,  7.11s/it]
                                                           
{'loss': 0.6231, 'learning_rate': 0.00020956333201075514, 'epoch': 6.78}

 57%|█████▋    | 15870/28080 [31:21:58<24:06:16,  7.11s/it]
 57%|█████▋    | 15871/28080 [31:22:05<23:59:16,  7.07s/it]
                                                           
{'loss': 0.6384, 'learning_rate': 0.00020953487627193575, 'epoch': 6.78}

 57%|█████▋    | 15871/28080 [31:22:05<23:59:16,  7.07s/it]
 57%|█████▋    | 15872/28080 [31:22:12<24:05:45,  7.11s/it]
                                                           
{'loss': 0.6208, 'learning_rate': 0.00020950642107146297, 'epoch': 6.78}

 57%|█████▋    | 15872/28080 [31:22:12<24:05:45,  7.11s/it]
 57%|█████▋    | 15873/28080 [31:22:19<24:07:28,  7.11s/it]
                                                           
{'loss': 0.6319, 'learning_rate': 0.0002094779664097156, 'epoch': 6.78}

 57%|█████▋    | 15873/28080 [31:22:19<24:07:28,  7.11s/it]
 57%|█████▋    | 15874/28080 [31:22:26<24:01:32,  7.09s/it]
                                                           
{'loss': 0.6078, 'learning_rate': 0.00020944951228707206, 'epoch': 6.78}

 57%|█████▋    | 15874/28080 [31:22:26<24:01:32,  7.09s/it]
 57%|█████▋    | 15875/28080 [31:22:33<24:04:51,  7.10s/it]
                                                           
{'loss': 0.6172, 'learning_rate': 0.00020942105870391082, 'epoch': 6.78}

 57%|█████▋    | 15875/28080 [31:22:33<24:04:51,  7.10s/it]
 57%|█████▋    | 15876/28080 [31:22:41<24:09:52,  7.13s/it]
                                                           
{'loss': 0.6176, 'learning_rate': 0.0002093926056606107, 'epoch': 6.78}

 57%|█████▋    | 15876/28080 [31:22:41<24:09:52,  7.13s/it]
 57%|█████▋    | 15877/28080 [31:22:48<24:07:17,  7.12s/it]
                                                           
{'loss': 0.6198, 'learning_rate': 0.00020936415315754987, 'epoch': 6.78}

 57%|█████▋    | 15877/28080 [31:22:48<24:07:17,  7.12s/it]
 57%|█████▋    | 15878/28080 [31:22:55<24:06:08,  7.11s/it]
                                                           
{'loss': 0.6272, 'learning_rate': 0.0002093357011951072, 'epoch': 6.78}

 57%|█████▋    | 15878/28080 [31:22:55<24:06:08,  7.11s/it]
 57%|█████▋    | 15879/28080 [31:23:02<24:01:50,  7.09s/it]
                                                           
{'loss': 0.6147, 'learning_rate': 0.000209307249773661, 'epoch': 6.78}

 57%|█████▋    | 15879/28080 [31:23:02<24:01:50,  7.09s/it]
 57%|█████▋    | 15880/28080 [31:23:09<24:02:33,  7.09s/it]
                                                           
{'loss': 0.6181, 'learning_rate': 0.00020927879889358992, 'epoch': 6.78}

 57%|█████▋    | 15880/28080 [31:23:09<24:02:33,  7.09s/it]
 57%|█████▋    | 15881/28080 [31:23:16<24:08:20,  7.12s/it]
                                                           
{'loss': 0.5904, 'learning_rate': 0.00020925034855527236, 'epoch': 6.78}

 57%|█████▋    | 15881/28080 [31:23:16<24:08:20,  7.12s/it]
 57%|█████▋    | 15882/28080 [31:23:23<24:11:19,  7.14s/it]
                                                           
{'loss': 0.6183, 'learning_rate': 0.00020922189875908692, 'epoch': 6.78}

 57%|█████▋    | 15882/28080 [31:23:23<24:11:19,  7.14s/it]
 57%|█████▋    | 15883/28080 [31:23:30<24:07:01,  7.12s/it]
                                                           
{'loss': 0.5966, 'learning_rate': 0.00020919344950541202, 'epoch': 6.79}

 57%|█████▋    | 15883/28080 [31:23:30<24:07:01,  7.12s/it]
 57%|█████▋    | 15884/28080 [31:23:38<24:09:21,  7.13s/it]
                                                           
{'loss': 0.6099, 'learning_rate': 0.00020916500079462623, 'epoch': 6.79}

 57%|█████▋    | 15884/28080 [31:23:38<24:09:21,  7.13s/it]
 57%|█████▋    | 15885/28080 [31:23:45<24:07:22,  7.12s/it]
                                                           
{'loss': 0.5932, 'learning_rate': 0.0002091365526271079, 'epoch': 6.79}

 57%|█████▋    | 15885/28080 [31:23:45<24:07:22,  7.12s/it]
 57%|█████▋    | 15886/28080 [31:23:52<24:12:24,  7.15s/it]
                                                           
{'loss': 0.6226, 'learning_rate': 0.00020910810500323563, 'epoch': 6.79}

 57%|█████▋    | 15886/28080 [31:23:52<24:12:24,  7.15s/it]
 57%|█████▋    | 15887/28080 [31:23:59<24:06:57,  7.12s/it]
                                                           
{'loss': 0.6231, 'learning_rate': 0.0002090796579233878, 'epoch': 6.79}

 57%|█████▋    | 15887/28080 [31:23:59<24:06:57,  7.12s/it]
 57%|█████▋    | 15888/28080 [31:24:06<24:04:10,  7.11s/it]
                                                           
{'loss': 0.6006, 'learning_rate': 0.00020905121138794296, 'epoch': 6.79}

 57%|█████▋    | 15888/28080 [31:24:06<24:04:10,  7.11s/it]
 57%|█████▋    | 15889/28080 [31:24:13<24:09:37,  7.13s/it]
                                                           
{'loss': 0.5959, 'learning_rate': 0.0002090227653972794, 'epoch': 6.79}

 57%|█████▋    | 15889/28080 [31:24:13<24:09:37,  7.13s/it]
 57%|█████▋    | 15890/28080 [31:24:20<24:11:20,  7.14s/it]
                                                           
{'loss': 0.6235, 'learning_rate': 0.00020899431995177582, 'epoch': 6.79}

 57%|█████▋    | 15890/28080 [31:24:20<24:11:20,  7.14s/it]
 57%|█████▋    | 15891/28080 [31:24:28<24:17:53,  7.18s/it]
                                                           
{'loss': 0.6224, 'learning_rate': 0.00020896587505181037, 'epoch': 6.79}

 57%|█████▋    | 15891/28080 [31:24:28<24:17:53,  7.18s/it]
 57%|█████▋    | 15892/28080 [31:24:35<24:16:19,  7.17s/it]
                                                           
{'loss': 0.608, 'learning_rate': 0.00020893743069776168, 'epoch': 6.79}

 57%|█████▋    | 15892/28080 [31:24:35<24:16:19,  7.17s/it]
 57%|█████▋    | 15893/28080 [31:24:42<24:11:51,  7.15s/it]
                                                           
{'loss': 0.5951, 'learning_rate': 0.00020890898689000808, 'epoch': 6.79}

 57%|█████▋    | 15893/28080 [31:24:42<24:11:51,  7.15s/it]
 57%|█████▋    | 15894/28080 [31:24:49<24:11:40,  7.15s/it]
                                                           
{'loss': 0.6072, 'learning_rate': 0.0002088805436289281, 'epoch': 6.79}

 57%|█████▋    | 15894/28080 [31:24:49<24:11:40,  7.15s/it]
 57%|█████▋    | 15895/28080 [31:24:56<24:09:34,  7.14s/it]
                                                           
{'loss': 0.6123, 'learning_rate': 0.0002088521009149, 'epoch': 6.79}

 57%|█████▋    | 15895/28080 [31:24:56<24:09:34,  7.14s/it]
 57%|█████▋    | 15896/28080 [31:25:03<24:07:35,  7.13s/it]
                                                           
{'loss': 0.6021, 'learning_rate': 0.00020882365874830232, 'epoch': 6.79}

 57%|█████▋    | 15896/28080 [31:25:03<24:07:35,  7.13s/it]
 57%|█████▋    | 15897/28080 [31:25:10<24:07:45,  7.13s/it]
                                                           
{'loss': 0.6061, 'learning_rate': 0.00020879521712951335, 'epoch': 6.79}

 57%|█████▋    | 15897/28080 [31:25:10<24:07:45,  7.13s/it]
 57%|█████▋    | 15898/28080 [31:25:17<24:08:30,  7.13s/it]
                                                           
{'loss': 0.6134, 'learning_rate': 0.00020876677605891148, 'epoch': 6.79}

 57%|█████▋    | 15898/28080 [31:25:17<24:08:30,  7.13s/it]
 57%|█████▋    | 15899/28080 [31:25:25<24:03:09,  7.11s/it]
                                                           
{'loss': 0.6114, 'learning_rate': 0.00020873833553687512, 'epoch': 6.79}

 57%|█████▋    | 15899/28080 [31:25:25<24:03:09,  7.11s/it]
 57%|█████▋    | 15900/28080 [31:25:32<24:08:29,  7.14s/it]
                                                           
{'loss': 0.6072, 'learning_rate': 0.00020870989556378265, 'epoch': 6.79}

 57%|█████▋    | 15900/28080 [31:25:32<24:08:29,  7.14s/it]
 57%|█████▋    | 15901/28080 [31:25:39<24:07:06,  7.13s/it]
                                                           
{'loss': 0.647, 'learning_rate': 0.00020868145614001243, 'epoch': 6.79}

 57%|█████▋    | 15901/28080 [31:25:39<24:07:06,  7.13s/it]
 57%|█████▋    | 15902/28080 [31:25:46<24:06:33,  7.13s/it]
                                                           
{'loss': 0.6165, 'learning_rate': 0.00020865301726594277, 'epoch': 6.79}

 57%|█████▋    | 15902/28080 [31:25:46<24:06:33,  7.13s/it]
 57%|█████▋    | 15903/28080 [31:25:53<24:04:00,  7.12s/it]
                                                           
{'loss': 0.6218, 'learning_rate': 0.00020862457894195213, 'epoch': 6.79}

 57%|█████▋    | 15903/28080 [31:25:53<24:04:00,  7.12s/it]
 57%|█████▋    | 15904/28080 [31:26:00<24:03:16,  7.11s/it]
                                                           
{'loss': 0.6171, 'learning_rate': 0.00020859614116841872, 'epoch': 6.79}

 57%|█████▋    | 15904/28080 [31:26:00<24:03:16,  7.11s/it]
 57%|█████▋    | 15905/28080 [31:26:07<24:07:20,  7.13s/it]
                                                           
{'loss': 0.6276, 'learning_rate': 0.00020856770394572097, 'epoch': 6.79}

 57%|█████▋    | 15905/28080 [31:26:07<24:07:20,  7.13s/it]
 57%|█████▋    | 15906/28080 [31:26:14<24:04:40,  7.12s/it]
                                                           
{'loss': 0.6231, 'learning_rate': 0.00020853926727423707, 'epoch': 6.79}

 57%|█████▋    | 15906/28080 [31:26:14<24:04:40,  7.12s/it]
 57%|█████▋    | 15907/28080 [31:26:22<24:05:07,  7.12s/it]
                                                           
{'loss': 0.5823, 'learning_rate': 0.00020851083115434562, 'epoch': 6.8}

 57%|█████▋    | 15907/28080 [31:26:22<24:05:07,  7.12s/it]
 57%|█████▋    | 15908/28080 [31:26:29<24:05:06,  7.12s/it]
                                                           
{'loss': 0.586, 'learning_rate': 0.00020848239558642463, 'epoch': 6.8}

 57%|█████▋    | 15908/28080 [31:26:29<24:05:06,  7.12s/it]
 57%|█████▋    | 15909/28080 [31:26:36<23:59:30,  7.10s/it]
                                                           
{'loss': 0.6393, 'learning_rate': 0.0002084539605708526, 'epoch': 6.8}

 57%|█████▋    | 15909/28080 [31:26:36<23:59:30,  7.10s/it]
 57%|█████▋    | 15910/28080 [31:26:43<24:05:38,  7.13s/it]
                                                           
{'loss': 0.6113, 'learning_rate': 0.00020842552610800773, 'epoch': 6.8}

 57%|█████▋    | 15910/28080 [31:26:43<24:05:38,  7.13s/it]
 57%|█████▋    | 15911/28080 [31:26:50<24:04:08,  7.12s/it]
                                                           
{'loss': 0.6147, 'learning_rate': 0.0002083970921982684, 'epoch': 6.8}

 57%|█████▋    | 15911/28080 [31:26:50<24:04:08,  7.12s/it]
 57%|█████▋    | 15912/28080 [31:26:57<24:04:29,  7.12s/it]
                                                           
{'loss': 0.6249, 'learning_rate': 0.00020836865884201277, 'epoch': 6.8}

 57%|█████▋    | 15912/28080 [31:26:57<24:04:29,  7.12s/it]
 57%|█████▋    | 15913/28080 [31:27:04<24:00:18,  7.10s/it]
                                                           
{'loss': 0.6378, 'learning_rate': 0.00020834022603961923, 'epoch': 6.8}

 57%|█████▋    | 15913/28080 [31:27:04<24:00:18,  7.10s/it]
 57%|█████▋    | 15914/28080 [31:27:11<24:01:41,  7.11s/it]
                                                           
{'loss': 0.602, 'learning_rate': 0.00020831179379146597, 'epoch': 6.8}

 57%|█████▋    | 15914/28080 [31:27:11<24:01:41,  7.11s/it]
 57%|█████▋    | 15915/28080 [31:27:18<23:56:17,  7.08s/it]
                                                           
{'loss': 0.6314, 'learning_rate': 0.00020828336209793136, 'epoch': 6.8}

 57%|█████▋    | 15915/28080 [31:27:18<23:56:17,  7.08s/it]
 57%|█████▋    | 15916/28080 [31:27:25<23:57:36,  7.09s/it]
                                                           
{'loss': 0.6031, 'learning_rate': 0.00020825493095939348, 'epoch': 6.8}

 57%|█████▋    | 15916/28080 [31:27:25<23:57:36,  7.09s/it]
 57%|█████▋    | 15917/28080 [31:27:33<23:58:29,  7.10s/it]
                                                           
{'loss': 0.6036, 'learning_rate': 0.00020822650037623076, 'epoch': 6.8}

 57%|█████▋    | 15917/28080 [31:27:33<23:58:29,  7.10s/it]
 57%|█████▋    | 15918/28080 [31:27:40<24:08:17,  7.14s/it]
                                                           
{'loss': 0.621, 'learning_rate': 0.0002081980703488213, 'epoch': 6.8}

 57%|█████▋    | 15918/28080 [31:27:40<24:08:17,  7.14s/it]
 57%|█████▋    | 15919/28080 [31:27:47<24:06:46,  7.14s/it]
                                                           
{'loss': 0.6126, 'learning_rate': 0.00020816964087754344, 'epoch': 6.8}

 57%|█████▋    | 15919/28080 [31:27:47<24:06:46,  7.14s/it]
 57%|█████▋    | 15920/28080 [31:27:54<24:10:54,  7.16s/it]
                                                           
{'loss': 0.6122, 'learning_rate': 0.00020814121196277525, 'epoch': 6.8}

 57%|█████▋    | 15920/28080 [31:27:54<24:10:54,  7.16s/it]
 57%|█████▋    | 15921/28080 [31:28:01<24:00:31,  7.11s/it]
                                                           
{'loss': 0.6231, 'learning_rate': 0.0002081127836048952, 'epoch': 6.8}

 57%|█████▋    | 15921/28080 [31:28:01<24:00:31,  7.11s/it]
 57%|█████▋    | 15922/28080 [31:28:08<24:02:03,  7.12s/it]
                                                           
{'loss': 0.6032, 'learning_rate': 0.0002080843558042813, 'epoch': 6.8}

 57%|█████▋    | 15922/28080 [31:28:08<24:02:03,  7.12s/it]
 57%|█████▋    | 15923/28080 [31:28:15<23:58:22,  7.10s/it]
                                                           
{'loss': 0.6162, 'learning_rate': 0.00020805592856131173, 'epoch': 6.8}

 57%|█████▋    | 15923/28080 [31:28:15<23:58:22,  7.10s/it]
 57%|█████▋    | 15924/28080 [31:28:23<24:03:52,  7.13s/it]
                                                           
{'loss': 0.6161, 'learning_rate': 0.0002080275018763649, 'epoch': 6.8}

 57%|█████▋    | 15924/28080 [31:28:23<24:03:52,  7.13s/it]
 57%|█████▋    | 15925/28080 [31:28:30<24:02:03,  7.12s/it]
                                                           
{'loss': 0.5926, 'learning_rate': 0.0002079990757498187, 'epoch': 6.8}

 57%|█████▋    | 15925/28080 [31:28:30<24:02:03,  7.12s/it]
 57%|█████▋    | 15926/28080 [31:28:37<24:04:41,  7.13s/it]
                                                           
{'loss': 0.5995, 'learning_rate': 0.00020797065018205154, 'epoch': 6.8}

 57%|█████▋    | 15926/28080 [31:28:37<24:04:41,  7.13s/it]
 57%|█████▋    | 15927/28080 [31:28:44<24:11:26,  7.17s/it]
                                                           
{'loss': 0.6013, 'learning_rate': 0.00020794222517344152, 'epoch': 6.8}

 57%|█████▋    | 15927/28080 [31:28:44<24:11:26,  7.17s/it]
 57%|█████▋    | 15928/28080 [31:28:51<24:15:55,  7.19s/it]
                                                           
{'loss': 0.6312, 'learning_rate': 0.00020791380072436683, 'epoch': 6.8}

 57%|█████▋    | 15928/28080 [31:28:51<24:15:55,  7.19s/it]
 57%|█████▋    | 15929/28080 [31:28:58<24:08:52,  7.15s/it]
                                                           
{'loss': 0.614, 'learning_rate': 0.00020788537683520553, 'epoch': 6.8}

 57%|█████▋    | 15929/28080 [31:28:58<24:08:52,  7.15s/it]
 57%|█████▋    | 15930/28080 [31:29:05<23:59:37,  7.11s/it]
                                                           
{'loss': 0.6303, 'learning_rate': 0.00020785695350633592, 'epoch': 6.81}

 57%|█████▋    | 15930/28080 [31:29:05<23:59:37,  7.11s/it]
 57%|█████▋    | 15931/28080 [31:29:12<23:57:46,  7.10s/it]
                                                           
{'loss': 0.619, 'learning_rate': 0.00020782853073813602, 'epoch': 6.81}

 57%|█████▋    | 15931/28080 [31:29:12<23:57:46,  7.10s/it]
 57%|█████▋    | 15932/28080 [31:29:20<24:03:55,  7.13s/it]
                                                           
{'loss': 0.6119, 'learning_rate': 0.00020780010853098407, 'epoch': 6.81}

 57%|█████▋    | 15932/28080 [31:29:20<24:03:55,  7.13s/it]
 57%|█████▋    | 15933/28080 [31:29:27<23:56:45,  7.10s/it]
                                                           
{'loss': 0.6254, 'learning_rate': 0.00020777168688525808, 'epoch': 6.81}

 57%|█████▋    | 15933/28080 [31:29:27<23:56:45,  7.10s/it]
 57%|█████▋    | 15934/28080 [31:29:34<24:00:50,  7.12s/it]
                                                           
{'loss': 0.5939, 'learning_rate': 0.0002077432658013363, 'epoch': 6.81}

 57%|█████▋    | 15934/28080 [31:29:34<24:00:50,  7.12s/it]
 57%|█████▋    | 15935/28080 [31:29:41<24:01:44,  7.12s/it]
                                                           
{'loss': 0.6052, 'learning_rate': 0.00020771484527959665, 'epoch': 6.81}

 57%|█████▋    | 15935/28080 [31:29:41<24:01:44,  7.12s/it]
 57%|█████▋    | 15936/28080 [31:29:48<24:05:14,  7.14s/it]
                                                           
{'loss': 0.6117, 'learning_rate': 0.00020768642532041748, 'epoch': 6.81}

 57%|█████▋    | 15936/28080 [31:29:48<24:05:14,  7.14s/it]
 57%|█████▋    | 15937/28080 [31:29:55<24:06:32,  7.15s/it]
                                                           
{'loss': 0.6047, 'learning_rate': 0.00020765800592417667, 'epoch': 6.81}

 57%|█████▋    | 15937/28080 [31:29:55<24:06:32,  7.15s/it]
 57%|█████▋    | 15938/28080 [31:30:02<24:02:34,  7.13s/it]
                                                           
{'loss': 0.6268, 'learning_rate': 0.00020762958709125254, 'epoch': 6.81}

 57%|█████▋    | 15938/28080 [31:30:02<24:02:34,  7.13s/it]
 57%|█████▋    | 15939/28080 [31:30:10<24:03:16,  7.13s/it]
                                                           
{'loss': 0.6109, 'learning_rate': 0.0002076011688220229, 'epoch': 6.81}

 57%|█████▋    | 15939/28080 [31:30:10<24:03:16,  7.13s/it]
 57%|█████▋    | 15940/28080 [31:30:17<23:55:27,  7.09s/it]
                                                           
{'loss': 0.6117, 'learning_rate': 0.00020757275111686605, 'epoch': 6.81}

 57%|█████▋    | 15940/28080 [31:30:17<23:55:27,  7.09s/it]
 57%|█████▋    | 15941/28080 [31:30:24<23:59:39,  7.12s/it]
                                                           
{'loss': 0.6144, 'learning_rate': 0.00020754433397615992, 'epoch': 6.81}

 57%|█████▋    | 15941/28080 [31:30:24<23:59:39,  7.12s/it]
 57%|█████▋    | 15942/28080 [31:30:31<23:55:25,  7.10s/it]
                                                           
{'loss': 0.6064, 'learning_rate': 0.00020751591740028272, 'epoch': 6.81}

 57%|█████▋    | 15942/28080 [31:30:31<23:55:25,  7.10s/it]
 57%|█████▋    | 15943/28080 [31:30:38<23:51:58,  7.08s/it]
                                                           
{'loss': 0.6243, 'learning_rate': 0.00020748750138961232, 'epoch': 6.81}

 57%|█████▋    | 15943/28080 [31:30:38<23:51:58,  7.08s/it]
 57%|█████▋    | 15944/28080 [31:30:45<23:59:04,  7.11s/it]
                                                           
{'loss': 0.6007, 'learning_rate': 0.00020745908594452695, 'epoch': 6.81}

 57%|█████▋    | 15944/28080 [31:30:45<23:59:04,  7.11s/it]
 57%|█████▋    | 15945/28080 [31:30:52<24:00:39,  7.12s/it]
                                                           
{'loss': 0.61, 'learning_rate': 0.00020743067106540448, 'epoch': 6.81}

 57%|█████▋    | 15945/28080 [31:30:52<24:00:39,  7.12s/it]
 57%|█████▋    | 15946/28080 [31:30:59<23:58:07,  7.11s/it]
                                                           
{'loss': 0.5983, 'learning_rate': 0.00020740225675262305, 'epoch': 6.81}

 57%|█████▋    | 15946/28080 [31:30:59<23:58:07,  7.11s/it]
 57%|█████▋    | 15947/28080 [31:31:06<23:55:59,  7.10s/it]
                                                           
{'loss': 0.6076, 'learning_rate': 0.00020737384300656067, 'epoch': 6.81}

 57%|█████▋    | 15947/28080 [31:31:06<23:55:59,  7.10s/it]
 57%|█████▋    | 15948/28080 [31:31:13<23:52:01,  7.08s/it]
                                                           
{'loss': 0.5913, 'learning_rate': 0.00020734542982759528, 'epoch': 6.81}

 57%|█████▋    | 15948/28080 [31:31:13<23:52:01,  7.08s/it]
 57%|█████▋    | 15949/28080 [31:31:21<23:58:58,  7.12s/it]
                                                           
{'loss': 0.609, 'learning_rate': 0.000207317017216105, 'epoch': 6.81}

 57%|█████▋    | 15949/28080 [31:31:21<23:58:58,  7.12s/it]
 57%|█████▋    | 15950/28080 [31:31:28<23:57:32,  7.11s/it]
                                                           
{'loss': 0.6197, 'learning_rate': 0.0002072886051724677, 'epoch': 6.81}

 57%|█████▋    | 15950/28080 [31:31:28<23:57:32,  7.11s/it]
 57%|█████▋    | 15951/28080 [31:31:35<24:03:37,  7.14s/it]
                                                           
{'loss': 0.6328, 'learning_rate': 0.0002072601936970615, 'epoch': 6.81}

 57%|█████▋    | 15951/28080 [31:31:35<24:03:37,  7.14s/it]
 57%|█████▋    | 15952/28080 [31:31:42<24:08:22,  7.17s/it]
                                                           
{'loss': 0.6173, 'learning_rate': 0.00020723178279026427, 'epoch': 6.81}

 57%|█████▋    | 15952/28080 [31:31:42<24:08:22,  7.17s/it]
 57%|█████▋    | 15953/28080 [31:31:49<23:53:35,  7.09s/it]
                                                           
{'loss': 0.6269, 'learning_rate': 0.00020720337245245412, 'epoch': 6.81}

 57%|█████▋    | 15953/28080 [31:31:49<23:53:35,  7.09s/it]
 57%|█████▋    | 15954/28080 [31:31:56<23:54:13,  7.10s/it]
                                                           
{'loss': 0.6204, 'learning_rate': 0.00020717496268400884, 'epoch': 6.82}

 57%|█████▋    | 15954/28080 [31:31:56<23:54:13,  7.10s/it]
 57%|█████▋    | 15955/28080 [31:32:03<23:54:36,  7.10s/it]
                                                           
{'loss': 0.6137, 'learning_rate': 0.00020714655348530667, 'epoch': 6.82}

 57%|█████▋    | 15955/28080 [31:32:03<23:54:36,  7.10s/it]
 57%|█████▋    | 15956/28080 [31:32:10<23:56:06,  7.11s/it]
                                                           
{'loss': 0.6103, 'learning_rate': 0.00020711814485672523, 'epoch': 6.82}

 57%|█████▋    | 15956/28080 [31:32:10<23:56:06,  7.11s/it]
 57%|█████▋    | 15957/28080 [31:32:17<23:58:22,  7.12s/it]
                                                           
{'loss': 0.6181, 'learning_rate': 0.00020708973679864272, 'epoch': 6.82}

 57%|█████▋    | 15957/28080 [31:32:17<23:58:22,  7.12s/it]
 57%|█████▋    | 15958/28080 [31:32:25<23:55:00,  7.10s/it]
                                                           
{'loss': 0.6195, 'learning_rate': 0.00020706132931143698, 'epoch': 6.82}

 57%|█████▋    | 15958/28080 [31:32:25<23:55:00,  7.10s/it]
 57%|█████▋    | 15959/28080 [31:32:32<23:49:28,  7.08s/it]
                                                           
{'loss': 0.6271, 'learning_rate': 0.00020703292239548598, 'epoch': 6.82}

 57%|█████▋    | 15959/28080 [31:32:32<23:49:28,  7.08s/it]
 57%|█████▋    | 15960/28080 [31:32:39<23:51:02,  7.08s/it]
                                                           
{'loss': 0.6002, 'learning_rate': 0.00020700451605116756, 'epoch': 6.82}

 57%|█████▋    | 15960/28080 [31:32:39<23:51:02,  7.08s/it]
 57%|█████▋    | 15961/28080 [31:32:46<23:53:13,  7.10s/it]
                                                           
{'loss': 0.6074, 'learning_rate': 0.00020697611027885977, 'epoch': 6.82}

 57%|█████▋    | 15961/28080 [31:32:46<23:53:13,  7.10s/it]
 57%|█████▋    | 15962/28080 [31:32:53<23:54:26,  7.10s/it]
                                                           
{'loss': 0.6073, 'learning_rate': 0.0002069477050789404, 'epoch': 6.82}

 57%|█████▋    | 15962/28080 [31:32:53<23:54:26,  7.10s/it]
 57%|█████▋    | 15963/28080 [31:33:00<23:56:58,  7.12s/it]
                                                           
{'loss': 0.6006, 'learning_rate': 0.00020691930045178743, 'epoch': 6.82}

 57%|█████▋    | 15963/28080 [31:33:00<23:56:58,  7.12s/it]
 57%|█████▋    | 15964/28080 [31:33:07<23:54:51,  7.11s/it]
                                                           
{'loss': 0.6168, 'learning_rate': 0.0002068908963977787, 'epoch': 6.82}

 57%|█████▋    | 15964/28080 [31:33:07<23:54:51,  7.11s/it]
 57%|█████▋    | 15965/28080 [31:33:14<23:53:04,  7.10s/it]
                                                           
{'loss': 0.6253, 'learning_rate': 0.00020686249291729215, 'epoch': 6.82}

 57%|█████▋    | 15965/28080 [31:33:14<23:53:04,  7.10s/it]
 57%|█████▋    | 15966/28080 [31:33:21<24:01:04,  7.14s/it]
                                                           
{'loss': 0.5991, 'learning_rate': 0.00020683409001070557, 'epoch': 6.82}

 57%|█████▋    | 15966/28080 [31:33:21<24:01:04,  7.14s/it]
 57%|█████▋    | 15967/28080 [31:33:29<24:02:44,  7.15s/it]
                                                           
{'loss': 0.5991, 'learning_rate': 0.00020680568767839696, 'epoch': 6.82}

 57%|█████▋    | 15967/28080 [31:33:29<24:02:44,  7.15s/it]
 57%|█████▋    | 15968/28080 [31:33:36<23:59:43,  7.13s/it]
                                                           
{'loss': 0.6147, 'learning_rate': 0.000206777285920744, 'epoch': 6.82}

 57%|█████▋    | 15968/28080 [31:33:36<23:59:43,  7.13s/it]
 57%|█████▋    | 15969/28080 [31:33:43<23:59:45,  7.13s/it]
                                                           
{'loss': 0.607, 'learning_rate': 0.00020674888473812484, 'epoch': 6.82}

 57%|█████▋    | 15969/28080 [31:33:43<23:59:45,  7.13s/it]
 57%|█████▋    | 15970/28080 [31:33:50<24:03:02,  7.15s/it]
                                                           
{'loss': 0.6295, 'learning_rate': 0.000206720484130917, 'epoch': 6.82}

 57%|█████▋    | 15970/28080 [31:33:50<24:03:02,  7.15s/it]
 57%|█████▋    | 15971/28080 [31:33:57<23:59:48,  7.13s/it]
                                                           
{'loss': 0.6266, 'learning_rate': 0.00020669208409949852, 'epoch': 6.82}

 57%|█████▋    | 15971/28080 [31:33:57<23:59:48,  7.13s/it]
 57%|█████▋    | 15972/28080 [31:34:04<23:54:04,  7.11s/it]
                                                           
{'loss': 0.6189, 'learning_rate': 0.0002066636846442473, 'epoch': 6.82}

 57%|█████▋    | 15972/28080 [31:34:04<23:54:04,  7.11s/it]
 57%|█████▋    | 15973/28080 [31:34:11<23:58:30,  7.13s/it]
                                                           
{'loss': 0.5982, 'learning_rate': 0.0002066352857655408, 'epoch': 6.82}

 57%|█████▋    | 15973/28080 [31:34:11<23:58:30,  7.13s/it]
 57%|█████▋    | 15974/28080 [31:34:18<23:59:50,  7.14s/it]
                                                           
{'loss': 0.6092, 'learning_rate': 0.00020660688746375734, 'epoch': 6.82}

 57%|█████▋    | 15974/28080 [31:34:18<23:59:50,  7.14s/it]
 57%|█████▋    | 15975/28080 [31:34:26<23:57:09,  7.12s/it]
                                                           
{'loss': 0.6109, 'learning_rate': 0.00020657848973927427, 'epoch': 6.82}

 57%|█████▋    | 15975/28080 [31:34:26<23:57:09,  7.12s/it]
 57%|█████▋    | 15976/28080 [31:34:33<23:59:09,  7.13s/it]
                                                           
{'loss': 0.5936, 'learning_rate': 0.0002065500925924697, 'epoch': 6.82}

 57%|█████▋    | 15976/28080 [31:34:33<23:59:09,  7.13s/it]
 57%|█████▋    | 15977/28080 [31:34:40<23:55:36,  7.12s/it]
                                                           
{'loss': 0.6376, 'learning_rate': 0.00020652169602372128, 'epoch': 6.83}

 57%|█████▋    | 15977/28080 [31:34:40<23:55:36,  7.12s/it]
 57%|█████▋    | 15978/28080 [31:34:47<23:55:27,  7.12s/it]
                                                           
{'loss': 0.6206, 'learning_rate': 0.0002064933000334069, 'epoch': 6.83}

 57%|█████▋    | 15978/28080 [31:34:47<23:55:27,  7.12s/it]
 57%|█████▋    | 15979/28080 [31:34:54<23:54:50,  7.11s/it]
                                                           
{'loss': 0.595, 'learning_rate': 0.0002064649046219042, 'epoch': 6.83}

 57%|█████▋    | 15979/28080 [31:34:54<23:54:50,  7.11s/it]
 57%|█████▋    | 15980/28080 [31:35:01<23:57:07,  7.13s/it]
                                                           
{'loss': 0.5962, 'learning_rate': 0.0002064365097895911, 'epoch': 6.83}

 57%|█████▋    | 15980/28080 [31:35:01<23:57:07,  7.13s/it]
 57%|█████▋    | 15981/28080 [31:35:08<23:59:47,  7.14s/it]
                                                           
{'loss': 0.604, 'learning_rate': 0.00020640811553684527, 'epoch': 6.83}

 57%|█████▋    | 15981/28080 [31:35:08<23:59:47,  7.14s/it]
 57%|█████▋    | 15982/28080 [31:35:16<24:01:04,  7.15s/it]
                                                           
{'loss': 0.6171, 'learning_rate': 0.00020637972186404453, 'epoch': 6.83}

 57%|█████▋    | 15982/28080 [31:35:16<24:01:04,  7.15s/it]
 57%|█████▋    | 15983/28080 [31:35:23<24:07:06,  7.18s/it]
                                                           
{'loss': 0.6319, 'learning_rate': 0.00020635132877156652, 'epoch': 6.83}

 57%|█████▋    | 15983/28080 [31:35:23<24:07:06,  7.18s/it]
 57%|█████▋    | 15984/28080 [31:35:30<24:08:54,  7.19s/it]
                                                           
{'loss': 0.6145, 'learning_rate': 0.00020632293625978912, 'epoch': 6.83}

 57%|█████▋    | 15984/28080 [31:35:30<24:08:54,  7.19s/it]
 57%|█████▋    | 15985/28080 [31:35:37<24:09:25,  7.19s/it]
                                                           
{'loss': 0.6231, 'learning_rate': 0.00020629454432908987, 'epoch': 6.83}

 57%|█████▋    | 15985/28080 [31:35:37<24:09:25,  7.19s/it]
 57%|█████▋    | 15986/28080 [31:35:44<24:06:59,  7.18s/it]
                                                           
{'loss': 0.6016, 'learning_rate': 0.0002062661529798468, 'epoch': 6.83}

 57%|█████▋    | 15986/28080 [31:35:44<24:06:59,  7.18s/it]
 57%|█████▋    | 15987/28080 [31:35:51<24:00:31,  7.15s/it]
                                                           
{'loss': 0.5976, 'learning_rate': 0.00020623776221243727, 'epoch': 6.83}

 57%|█████▋    | 15987/28080 [31:35:51<24:00:31,  7.15s/it]
 57%|█████▋    | 15988/28080 [31:35:59<24:02:15,  7.16s/it]
                                                           
{'loss': 0.5998, 'learning_rate': 0.00020620937202723926, 'epoch': 6.83}

 57%|█████▋    | 15988/28080 [31:35:59<24:02:15,  7.16s/it]
 57%|█████▋    | 15989/28080 [31:36:06<23:56:17,  7.13s/it]
                                                           
{'loss': 0.6146, 'learning_rate': 0.00020618098242463037, 'epoch': 6.83}

 57%|█████▋    | 15989/28080 [31:36:06<23:56:17,  7.13s/it]
 57%|█████▋    | 15990/28080 [31:36:13<23:57:56,  7.14s/it]
                                                           
{'loss': 0.6051, 'learning_rate': 0.00020615259340498832, 'epoch': 6.83}

 57%|█████▋    | 15990/28080 [31:36:13<23:57:56,  7.14s/it]
 57%|█████▋    | 15991/28080 [31:36:20<24:03:36,  7.16s/it]
                                                           
{'loss': 0.6027, 'learning_rate': 0.00020612420496869075, 'epoch': 6.83}

 57%|█████▋    | 15991/28080 [31:36:20<24:03:36,  7.16s/it]
 57%|█████▋    | 15992/28080 [31:36:27<24:03:45,  7.17s/it]
                                                           
{'loss': 0.6221, 'learning_rate': 0.0002060958171161154, 'epoch': 6.83}

 57%|█████▋    | 15992/28080 [31:36:27<24:03:45,  7.17s/it]
 57%|█████▋    | 15993/28080 [31:36:34<24:00:16,  7.15s/it]
                                                           
{'loss': 0.6009, 'learning_rate': 0.00020606742984763987, 'epoch': 6.83}

 57%|█████▋    | 15993/28080 [31:36:34<24:00:16,  7.15s/it]
 57%|█████▋    | 15994/28080 [31:36:41<24:02:14,  7.16s/it]
                                                           
{'loss': 0.6093, 'learning_rate': 0.00020603904316364191, 'epoch': 6.83}

 57%|█████▋    | 15994/28080 [31:36:42<24:02:14,  7.16s/it]
 57%|█████▋    | 15995/28080 [31:36:49<24:08:11,  7.19s/it]
                                                           
{'loss': 0.6178, 'learning_rate': 0.0002060106570644991, 'epoch': 6.83}

 57%|█████▋    | 15995/28080 [31:36:49<24:08:11,  7.19s/it]
 57%|█████▋    | 15996/28080 [31:36:56<24:04:31,  7.17s/it]
                                                           
{'loss': 0.6251, 'learning_rate': 0.00020598227155058912, 'epoch': 6.83}

 57%|█████▋    | 15996/28080 [31:36:56<24:04:31,  7.17s/it]
 57%|█████▋    | 15997/28080 [31:37:03<24:03:15,  7.17s/it]
                                                           
{'loss': 0.6261, 'learning_rate': 0.00020595388662228965, 'epoch': 6.83}

 57%|█████▋    | 15997/28080 [31:37:03<24:03:15,  7.17s/it]
 57%|█████▋    | 15998/28080 [31:37:10<24:03:02,  7.17s/it]
                                                           
{'loss': 0.5986, 'learning_rate': 0.00020592550227997822, 'epoch': 6.83}

 57%|█████▋    | 15998/28080 [31:37:10<24:03:02,  7.17s/it]
 57%|█████▋    | 15999/28080 [31:37:17<24:05:38,  7.18s/it]
                                                           
{'loss': 0.6024, 'learning_rate': 0.00020589711852403257, 'epoch': 6.83}

 57%|█████▋    | 15999/28080 [31:37:17<24:05:38,  7.18s/it]
 57%|█████▋    | 16000/28080 [31:37:25<24:07:14,  7.19s/it]
                                                           
{'loss': 0.595, 'learning_rate': 0.0002058687353548302, 'epoch': 6.84}

 57%|█████▋    | 16000/28080 [31:37:25<24:07:14,  7.19s/it]
 57%|█████▋    | 16001/28080 [31:37:32<24:00:20,  7.15s/it]
                                                           
{'loss': 0.6188, 'learning_rate': 0.0002058403527727488, 'epoch': 6.84}

 57%|█████▋    | 16001/28080 [31:37:32<24:00:20,  7.15s/it]
 57%|█████▋    | 16002/28080 [31:37:39<23:55:20,  7.13s/it]
                                                           
{'loss': 0.641, 'learning_rate': 0.0002058119707781659, 'epoch': 6.84}

 57%|█████▋    | 16002/28080 [31:37:39<23:55:20,  7.13s/it]
 57%|█████▋    | 16003/28080 [31:37:46<23:50:52,  7.11s/it]
                                                           
{'loss': 0.6123, 'learning_rate': 0.00020578358937145923, 'epoch': 6.84}

 57%|█████▋    | 16003/28080 [31:37:46<23:50:52,  7.11s/it]
 57%|█████▋    | 16004/28080 [31:37:53<23:52:22,  7.12s/it]
                                                           
{'loss': 0.5938, 'learning_rate': 0.00020575520855300617, 'epoch': 6.84}

 57%|█████▋    | 16004/28080 [31:37:53<23:52:22,  7.12s/it]
 57%|█████▋    | 16005/28080 [31:38:00<23:49:07,  7.10s/it]
                                                           
{'loss': 0.6131, 'learning_rate': 0.0002057268283231846, 'epoch': 6.84}

 57%|█████▋    | 16005/28080 [31:38:00<23:49:07,  7.10s/it]
 57%|█████▋    | 16006/28080 [31:38:07<23:49:56,  7.11s/it]
                                                           
{'loss': 0.6075, 'learning_rate': 0.0002056984486823717, 'epoch': 6.84}

 57%|█████▋    | 16006/28080 [31:38:07<23:49:56,  7.11s/it]
 57%|█████▋    | 16007/28080 [31:38:14<23:54:28,  7.13s/it]
                                                           
{'loss': 0.5994, 'learning_rate': 0.00020567006963094538, 'epoch': 6.84}

 57%|█████▋    | 16007/28080 [31:38:14<23:54:28,  7.13s/it]
 57%|█████▋    | 16008/28080 [31:38:21<23:53:06,  7.12s/it]
                                                           
{'loss': 0.6113, 'learning_rate': 0.00020564169116928297, 'epoch': 6.84}

 57%|█████▋    | 16008/28080 [31:38:21<23:53:06,  7.12s/it]
 57%|█████▋    | 16009/28080 [31:38:29<23:56:13,  7.14s/it]
                                                           
{'loss': 0.6117, 'learning_rate': 0.00020561331329776216, 'epoch': 6.84}

 57%|█████▋    | 16009/28080 [31:38:29<23:56:13,  7.14s/it]
 57%|█████▋    | 16010/28080 [31:38:36<23:46:30,  7.09s/it]
                                                           
{'loss': 0.628, 'learning_rate': 0.00020558493601676036, 'epoch': 6.84}

 57%|█████▋    | 16010/28080 [31:38:36<23:46:30,  7.09s/it]
 57%|█████▋    | 16011/28080 [31:38:43<23:52:09,  7.12s/it]
                                                           
{'loss': 0.5966, 'learning_rate': 0.00020555655932665524, 'epoch': 6.84}

 57%|█████▋    | 16011/28080 [31:38:43<23:52:09,  7.12s/it]
 57%|█████▋    | 16012/28080 [31:38:50<23:55:39,  7.14s/it]
                                                           
{'loss': 0.5988, 'learning_rate': 0.00020552818322782418, 'epoch': 6.84}

 57%|█████▋    | 16012/28080 [31:38:50<23:55:39,  7.14s/it]
 57%|█████▋    | 16013/28080 [31:38:57<23:52:24,  7.12s/it]
                                                           
{'loss': 0.6264, 'learning_rate': 0.00020549980772064484, 'epoch': 6.84}

 57%|█████▋    | 16013/28080 [31:38:57<23:52:24,  7.12s/it]
 57%|█████▋    | 16014/28080 [31:39:04<23:45:08,  7.09s/it]
                                                           
{'loss': 0.6316, 'learning_rate': 0.00020547143280549458, 'epoch': 6.84}

 57%|█████▋    | 16014/28080 [31:39:04<23:45:08,  7.09s/it]
 57%|█████▋    | 16015/28080 [31:39:11<23:45:57,  7.09s/it]
                                                           
{'loss': 0.6021, 'learning_rate': 0.000205443058482751, 'epoch': 6.84}

 57%|█████▋    | 16015/28080 [31:39:11<23:45:57,  7.09s/it]
 57%|█████▋    | 16016/28080 [31:39:18<23:55:00,  7.14s/it]
                                                           
{'loss': 0.6121, 'learning_rate': 0.00020541468475279148, 'epoch': 6.84}

 57%|█████▋    | 16016/28080 [31:39:18<23:55:00,  7.14s/it]
 57%|█████▋    | 16017/28080 [31:39:25<23:50:13,  7.11s/it]
                                                           
{'loss': 0.6066, 'learning_rate': 0.00020538631161599375, 'epoch': 6.84}

 57%|█████▋    | 16017/28080 [31:39:25<23:50:13,  7.11s/it]
 57%|█████▋    | 16018/28080 [31:39:33<23:51:49,  7.12s/it]
                                                           
{'loss': 0.6098, 'learning_rate': 0.00020535793907273494, 'epoch': 6.84}

 57%|█████▋    | 16018/28080 [31:39:33<23:51:49,  7.12s/it]
 57%|█████▋    | 16019/28080 [31:39:40<23:56:41,  7.15s/it]
                                                           
{'loss': 0.6241, 'learning_rate': 0.00020532956712339282, 'epoch': 6.84}

 57%|█████▋    | 16019/28080 [31:39:40<23:56:41,  7.15s/it]
 57%|█████▋    | 16020/28080 [31:39:47<23:51:38,  7.12s/it]
                                                           
{'loss': 0.615, 'learning_rate': 0.00020530119576834467, 'epoch': 6.84}

 57%|█████▋    | 16020/28080 [31:39:47<23:51:38,  7.12s/it]
 57%|█████▋    | 16021/28080 [31:39:54<23:44:56,  7.09s/it]
                                                           
{'loss': 0.6363, 'learning_rate': 0.00020527282500796805, 'epoch': 6.84}

 57%|█████▋    | 16021/28080 [31:39:54<23:44:56,  7.09s/it]
 57%|█████▋    | 16022/28080 [31:40:01<23:49:34,  7.11s/it]
                                                           
{'loss': 0.6134, 'learning_rate': 0.00020524445484264037, 'epoch': 6.84}

 57%|█████▋    | 16022/28080 [31:40:01<23:49:34,  7.11s/it]
 57%|█████▋    | 16023/28080 [31:40:08<23:44:57,  7.09s/it]
                                                           
{'loss': 0.6117, 'learning_rate': 0.00020521608527273894, 'epoch': 6.84}

 57%|█████▋    | 16023/28080 [31:40:08<23:44:57,  7.09s/it]
 57%|█████▋    | 16024/28080 [31:40:15<23:48:07,  7.11s/it]
                                                           
{'loss': 0.63, 'learning_rate': 0.00020518771629864134, 'epoch': 6.85}

 57%|█████▋    | 16024/28080 [31:40:15<23:48:07,  7.11s/it]
 57%|█████▋    | 16025/28080 [31:40:22<23:47:57,  7.11s/it]
                                                           
{'loss': 0.6082, 'learning_rate': 0.00020515934792072495, 'epoch': 6.85}

 57%|█████▋    | 16025/28080 [31:40:22<23:47:57,  7.11s/it]
 57%|█████▋    | 16026/28080 [31:40:29<23:48:41,  7.11s/it]
                                                           
{'loss': 0.6015, 'learning_rate': 0.00020513098013936722, 'epoch': 6.85}

 57%|█████▋    | 16026/28080 [31:40:29<23:48:41,  7.11s/it]
 57%|█████▋    | 16027/28080 [31:40:37<23:52:41,  7.13s/it]
                                                           
{'loss': 0.6111, 'learning_rate': 0.00020510261295494543, 'epoch': 6.85}

 57%|█████▋    | 16027/28080 [31:40:37<23:52:41,  7.13s/it]
 57%|█████▋    | 16028/28080 [31:40:44<23:53:52,  7.14s/it]
                                                           
{'loss': 0.6006, 'learning_rate': 0.00020507424636783712, 'epoch': 6.85}

 57%|█████▋    | 16028/28080 [31:40:44<23:53:52,  7.14s/it]
 57%|█████▋    | 16029/28080 [31:40:51<23:54:28,  7.14s/it]
                                                           
{'loss': 0.6128, 'learning_rate': 0.00020504588037841955, 'epoch': 6.85}

 57%|█████▋    | 16029/28080 [31:40:51<23:54:28,  7.14s/it]
 57%|█████▋    | 16030/28080 [31:40:58<23:56:04,  7.15s/it]
                                                           
{'loss': 0.6318, 'learning_rate': 0.00020501751498707026, 'epoch': 6.85}

 57%|█████▋    | 16030/28080 [31:40:58<23:56:04,  7.15s/it]
 57%|█████▋    | 16031/28080 [31:41:05<23:56:59,  7.16s/it]
                                                           
{'loss': 0.6126, 'learning_rate': 0.00020498915019416642, 'epoch': 6.85}

 57%|█████▋    | 16031/28080 [31:41:05<23:56:59,  7.16s/it]
 57%|█████▋    | 16032/28080 [31:41:13<24:02:27,  7.18s/it]
                                                           
{'loss': 0.6019, 'learning_rate': 0.00020496078600008562, 'epoch': 6.85}

 57%|█████▋    | 16032/28080 [31:41:13<24:02:27,  7.18s/it]
 57%|█████▋    | 16033/28080 [31:41:20<23:56:57,  7.16s/it]
                                                           
{'loss': 0.6167, 'learning_rate': 0.00020493242240520493, 'epoch': 6.85}

 57%|█████▋    | 16033/28080 [31:41:20<23:56:57,  7.16s/it]
 57%|█████▋    | 16034/28080 [31:41:27<23:56:27,  7.15s/it]
                                                           
{'loss': 0.6496, 'learning_rate': 0.00020490405940990202, 'epoch': 6.85}

 57%|█████▋    | 16034/28080 [31:41:27<23:56:27,  7.15s/it]
 57%|█████▋    | 16035/28080 [31:41:34<23:51:28,  7.13s/it]
                                                           
{'loss': 0.6126, 'learning_rate': 0.00020487569701455396, 'epoch': 6.85}

 57%|█████▋    | 16035/28080 [31:41:34<23:51:28,  7.13s/it]
 57%|█████▋    | 16036/28080 [31:41:41<23:55:57,  7.15s/it]
                                                           
{'loss': 0.626, 'learning_rate': 0.00020484733521953835, 'epoch': 6.85}

 57%|█████▋    | 16036/28080 [31:41:41<23:55:57,  7.15s/it]
 57%|█████▋    | 16037/28080 [31:41:48<23:56:11,  7.16s/it]
                                                           
{'loss': 0.6105, 'learning_rate': 0.0002048189740252322, 'epoch': 6.85}

 57%|█████▋    | 16037/28080 [31:41:48<23:56:11,  7.16s/it]
 57%|█████▋    | 16038/28080 [31:41:55<23:50:04,  7.13s/it]
                                                           
{'loss': 0.6051, 'learning_rate': 0.0002047906134320131, 'epoch': 6.85}

 57%|█████▋    | 16038/28080 [31:41:55<23:50:04,  7.13s/it]
 57%|█████▋    | 16039/28080 [31:42:02<23:43:51,  7.10s/it]
                                                           
{'loss': 0.6213, 'learning_rate': 0.00020476225344025816, 'epoch': 6.85}

 57%|█████▋    | 16039/28080 [31:42:02<23:43:51,  7.10s/it]
 57%|█████▋    | 16040/28080 [31:42:09<23:48:52,  7.12s/it]
                                                           
{'loss': 0.6249, 'learning_rate': 0.00020473389405034487, 'epoch': 6.85}

 57%|█████▋    | 16040/28080 [31:42:09<23:48:52,  7.12s/it]
 57%|█████▋    | 16041/28080 [31:42:17<23:46:36,  7.11s/it]
                                                           
{'loss': 0.6121, 'learning_rate': 0.00020470553526265035, 'epoch': 6.85}

 57%|█████▋    | 16041/28080 [31:42:17<23:46:36,  7.11s/it]
 57%|█████▋    | 16042/28080 [31:42:24<23:43:05,  7.09s/it]
                                                           
{'loss': 0.6198, 'learning_rate': 0.000204677177077552, 'epoch': 6.85}

 57%|█████▋    | 16042/28080 [31:42:24<23:43:05,  7.09s/it]
 57%|█████▋    | 16043/28080 [31:42:31<23:47:18,  7.11s/it]
                                                           
{'loss': 0.6061, 'learning_rate': 0.000204648819495427, 'epoch': 6.85}

 57%|█████▋    | 16043/28080 [31:42:31<23:47:18,  7.11s/it]
 57%|█████▋    | 16044/28080 [31:42:38<23:39:57,  7.08s/it]
                                                           
{'loss': 0.6252, 'learning_rate': 0.00020462046251665275, 'epoch': 6.85}

 57%|█████▋    | 16044/28080 [31:42:38<23:39:57,  7.08s/it]
 57%|█████▋    | 16045/28080 [31:42:45<23:41:35,  7.09s/it]
                                                           
{'loss': 0.601, 'learning_rate': 0.00020459210614160638, 'epoch': 6.85}

 57%|█████▋    | 16045/28080 [31:42:45<23:41:35,  7.09s/it]
 57%|█████▋    | 16046/28080 [31:42:52<23:47:53,  7.12s/it]
                                                           
{'loss': 0.6224, 'learning_rate': 0.0002045637503706652, 'epoch': 6.85}

 57%|█████▋    | 16046/28080 [31:42:52<23:47:53,  7.12s/it]
 57%|█████▋    | 16047/28080 [31:42:59<23:51:05,  7.14s/it]
                                                           
{'loss': 0.6185, 'learning_rate': 0.00020453539520420648, 'epoch': 6.86}

 57%|█████▋    | 16047/28080 [31:42:59<23:51:05,  7.14s/it]
 57%|█████▋    | 16048/28080 [31:43:06<23:46:45,  7.11s/it]
                                                           
{'loss': 0.6316, 'learning_rate': 0.00020450704064260737, 'epoch': 6.86}

 57%|█████▋    | 16048/28080 [31:43:06<23:46:45,  7.11s/it]
 57%|█████▋    | 16049/28080 [31:43:13<23:41:13,  7.09s/it]
                                                           
{'loss': 0.6061, 'learning_rate': 0.0002044786866862452, 'epoch': 6.86}

 57%|█████▋    | 16049/28080 [31:43:13<23:41:13,  7.09s/it]
 57%|█████▋    | 16050/28080 [31:43:21<23:46:19,  7.11s/it]
                                                           
{'loss': 0.6186, 'learning_rate': 0.00020445033333549702, 'epoch': 6.86}

 57%|█████▋    | 16050/28080 [31:43:21<23:46:19,  7.11s/it]
 57%|█████▋    | 16051/28080 [31:43:28<23:49:48,  7.13s/it]
                                                           
{'loss': 0.5935, 'learning_rate': 0.00020442198059074035, 'epoch': 6.86}

 57%|█████▋    | 16051/28080 [31:43:28<23:49:48,  7.13s/it]
 57%|█████▋    | 16052/28080 [31:43:35<23:50:56,  7.14s/it]
                                                           
{'loss': 0.5992, 'learning_rate': 0.00020439362845235201, 'epoch': 6.86}

 57%|█████▋    | 16052/28080 [31:43:35<23:50:56,  7.14s/it]
 57%|█████▋    | 16053/28080 [31:43:42<23:48:04,  7.12s/it]
                                                           
{'loss': 0.6374, 'learning_rate': 0.00020436527692070962, 'epoch': 6.86}

 57%|█████▋    | 16053/28080 [31:43:42<23:48:04,  7.12s/it]
 57%|█████▋    | 16054/28080 [31:43:49<23:51:00,  7.14s/it]
                                                           
{'loss': 0.6231, 'learning_rate': 0.0002043369259961899, 'epoch': 6.86}

 57%|█████▋    | 16054/28080 [31:43:49<23:51:00,  7.14s/it]
 57%|█████▋    | 16055/28080 [31:43:56<23:51:15,  7.14s/it]
                                                           
{'loss': 0.6255, 'learning_rate': 0.00020430857567917043, 'epoch': 6.86}

 57%|█████▋    | 16055/28080 [31:43:56<23:51:15,  7.14s/it]
 57%|█████▋    | 16056/28080 [31:44:03<23:43:04,  7.10s/it]
                                                           
{'loss': 0.6188, 'learning_rate': 0.00020428022597002816, 'epoch': 6.86}

 57%|█████▋    | 16056/28080 [31:44:03<23:43:04,  7.10s/it]
 57%|█████▋    | 16057/28080 [31:44:10<23:41:37,  7.09s/it]
                                                           
{'loss': 0.6112, 'learning_rate': 0.00020425187686914036, 'epoch': 6.86}

 57%|█████▋    | 16057/28080 [31:44:10<23:41:37,  7.09s/it]
 57%|█████▋    | 16058/28080 [31:44:18<23:45:59,  7.12s/it]
                                                           
{'loss': 0.5999, 'learning_rate': 0.0002042235283768841, 'epoch': 6.86}

 57%|█████▋    | 16058/28080 [31:44:18<23:45:59,  7.12s/it]
 57%|█████▋    | 16059/28080 [31:44:25<23:50:21,  7.14s/it]
                                                           
{'loss': 0.6316, 'learning_rate': 0.00020419518049363662, 'epoch': 6.86}

 57%|█████▋    | 16059/28080 [31:44:25<23:50:21,  7.14s/it]
 57%|█████▋    | 16060/28080 [31:44:32<23:56:20,  7.17s/it]
                                                           
{'loss': 0.5956, 'learning_rate': 0.00020416683321977498, 'epoch': 6.86}

 57%|█████▋    | 16060/28080 [31:44:32<23:56:20,  7.17s/it]
 57%|█████▋    | 16061/28080 [31:44:39<23:56:46,  7.17s/it]
                                                           
{'loss': 0.6121, 'learning_rate': 0.00020413848655567634, 'epoch': 6.86}

 57%|█████▋    | 16061/28080 [31:44:39<23:56:46,  7.17s/it]
 57%|█████▋    | 16062/28080 [31:44:46<23:54:40,  7.16s/it]
                                                           
{'loss': 0.6139, 'learning_rate': 0.00020411014050171784, 'epoch': 6.86}

 57%|█████▋    | 16062/28080 [31:44:46<23:54:40,  7.16s/it]
 57%|█████▋    | 16063/28080 [31:44:53<23:51:13,  7.15s/it]
                                                           
{'loss': 0.6117, 'learning_rate': 0.00020408179505827657, 'epoch': 6.86}

 57%|█████▋    | 16063/28080 [31:44:53<23:51:13,  7.15s/it]
 57%|█████▋    | 16064/28080 [31:45:00<23:43:35,  7.11s/it]
                                                           
{'loss': 0.6171, 'learning_rate': 0.00020405345022572957, 'epoch': 6.86}

 57%|█████▋    | 16064/28080 [31:45:00<23:43:35,  7.11s/it]
 57%|█████▋    | 16065/28080 [31:45:08<23:49:49,  7.14s/it]
                                                           
{'loss': 0.6077, 'learning_rate': 0.00020402510600445417, 'epoch': 6.86}

 57%|█████▋    | 16065/28080 [31:45:08<23:49:49,  7.14s/it]
 57%|█████▋    | 16066/28080 [31:45:15<23:52:52,  7.16s/it]
                                                           
{'loss': 0.6171, 'learning_rate': 0.0002039967623948271, 'epoch': 6.86}

 57%|█████▋    | 16066/28080 [31:45:15<23:52:52,  7.16s/it]
 57%|█████▋    | 16067/28080 [31:45:22<23:47:58,  7.13s/it]
                                                           
{'loss': 0.6279, 'learning_rate': 0.0002039684193972259, 'epoch': 6.86}

 57%|█████▋    | 16067/28080 [31:45:22<23:47:58,  7.13s/it]
 57%|█████▋    | 16068/28080 [31:45:29<23:49:12,  7.14s/it]
                                                           
{'loss': 0.6062, 'learning_rate': 0.00020394007701202716, 'epoch': 6.86}

 57%|█████▋    | 16068/28080 [31:45:29<23:49:12,  7.14s/it]
 57%|█████▋    | 16069/28080 [31:45:36<23:47:17,  7.13s/it]
                                                           
{'loss': 0.6225, 'learning_rate': 0.00020391173523960832, 'epoch': 6.86}

 57%|█████▋    | 16069/28080 [31:45:36<23:47:17,  7.13s/it]
 57%|█████▋    | 16070/28080 [31:45:43<23:48:51,  7.14s/it]
                                                           
{'loss': 0.6215, 'learning_rate': 0.00020388339408034624, 'epoch': 6.86}

 57%|█████▋    | 16070/28080 [31:45:43<23:48:51,  7.14s/it]
 57%|█████▋    | 16071/28080 [31:45:50<23:47:19,  7.13s/it]
                                                           
{'loss': 0.6093, 'learning_rate': 0.00020385505353461806, 'epoch': 6.87}

 57%|█████▋    | 16071/28080 [31:45:50<23:47:19,  7.13s/it]
 57%|█████▋    | 16072/28080 [31:45:58<23:48:54,  7.14s/it]
                                                           
{'loss': 0.6279, 'learning_rate': 0.0002038267136028008, 'epoch': 6.87}

 57%|█████▋    | 16072/28080 [31:45:58<23:48:54,  7.14s/it]
 57%|█████▋    | 16073/28080 [31:46:05<23:50:05,  7.15s/it]
                                                           
{'loss': 0.6161, 'learning_rate': 0.00020379837428527139, 'epoch': 6.87}

 57%|█████▋    | 16073/28080 [31:46:05<23:50:05,  7.15s/it]
 57%|█████▋    | 16074/28080 [31:46:12<24:02:11,  7.21s/it]
                                                           
{'loss': 0.5946, 'learning_rate': 0.00020377003558240707, 'epoch': 6.87}

 57%|█████▋    | 16074/28080 [31:46:12<24:02:11,  7.21s/it]
 57%|█████▋    | 16075/28080 [31:46:19<24:01:53,  7.21s/it]
                                                           
{'loss': 0.6077, 'learning_rate': 0.00020374169749458462, 'epoch': 6.87}

 57%|█████▋    | 16075/28080 [31:46:19<24:01:53,  7.21s/it]
 57%|█████▋    | 16076/28080 [31:46:26<23:58:43,  7.19s/it]
                                                           
{'loss': 0.6015, 'learning_rate': 0.00020371336002218124, 'epoch': 6.87}

 57%|█████▋    | 16076/28080 [31:46:26<23:58:43,  7.19s/it]
 57%|█████▋    | 16077/28080 [31:46:34<23:52:19,  7.16s/it]
                                                           
{'loss': 0.6092, 'learning_rate': 0.00020368502316557381, 'epoch': 6.87}

 57%|█████▋    | 16077/28080 [31:46:34<23:52:19,  7.16s/it]
 57%|█████▋    | 16078/28080 [31:46:41<23:43:22,  7.12s/it]
                                                           
{'loss': 0.6075, 'learning_rate': 0.00020365668692513939, 'epoch': 6.87}

 57%|█████▋    | 16078/28080 [31:46:41<23:43:22,  7.12s/it]
 57%|█████▋    | 16079/28080 [31:46:48<23:39:12,  7.10s/it]
                                                           
{'loss': 0.6068, 'learning_rate': 0.00020362835130125493, 'epoch': 6.87}

 57%|█████▋    | 16079/28080 [31:46:48<23:39:12,  7.10s/it]
 57%|█████▋    | 16080/28080 [31:46:55<23:46:12,  7.13s/it]
                                                           
{'loss': 0.6362, 'learning_rate': 0.00020360001629429744, 'epoch': 6.87}

 57%|█████▋    | 16080/28080 [31:46:55<23:46:12,  7.13s/it]
 57%|█████▋    | 16081/28080 [31:47:02<23:44:16,  7.12s/it]
                                                           
{'loss': 0.628, 'learning_rate': 0.00020357168190464375, 'epoch': 6.87}

 57%|█████▋    | 16081/28080 [31:47:02<23:44:16,  7.12s/it]
 57%|█████▋    | 16082/28080 [31:47:09<23:41:21,  7.11s/it]
                                                           
{'loss': 0.6094, 'learning_rate': 0.00020354334813267111, 'epoch': 6.87}

 57%|█████▋    | 16082/28080 [31:47:09<23:41:21,  7.11s/it]
 57%|█████▋    | 16083/28080 [31:47:16<23:44:05,  7.12s/it]
                                                           
{'loss': 0.6132, 'learning_rate': 0.00020351501497875617, 'epoch': 6.87}

 57%|█████▋    | 16083/28080 [31:47:16<23:44:05,  7.12s/it]
 57%|█████▋    | 16084/28080 [31:47:23<23:42:42,  7.12s/it]
                                                           
{'loss': 0.6187, 'learning_rate': 0.0002034866824432761, 'epoch': 6.87}

 57%|█████▋    | 16084/28080 [31:47:23<23:42:42,  7.12s/it]
 57%|█████▋    | 16085/28080 [31:47:30<23:42:50,  7.12s/it]
                                                           
{'loss': 0.6189, 'learning_rate': 0.0002034583505266076, 'epoch': 6.87}

 57%|█████▋    | 16085/28080 [31:47:30<23:42:50,  7.12s/it]
 57%|█████▋    | 16086/28080 [31:47:38<23:50:35,  7.16s/it]
                                                           
{'loss': 0.6201, 'learning_rate': 0.00020343001922912786, 'epoch': 6.87}

 57%|█████▋    | 16086/28080 [31:47:38<23:50:35,  7.16s/it]
 57%|█████▋    | 16087/28080 [31:47:45<23:48:37,  7.15s/it]
                                                           
{'loss': 0.6032, 'learning_rate': 0.00020340168855121358, 'epoch': 6.87}

 57%|█████▋    | 16087/28080 [31:47:45<23:48:37,  7.15s/it]
 57%|█████▋    | 16088/28080 [31:47:52<23:49:19,  7.15s/it]
                                                           
{'loss': 0.6074, 'learning_rate': 0.00020337335849324184, 'epoch': 6.87}

 57%|█████▋    | 16088/28080 [31:47:52<23:49:19,  7.15s/it]
 57%|█████▋    | 16089/28080 [31:47:59<23:49:00,  7.15s/it]
                                                           
{'loss': 0.5893, 'learning_rate': 0.0002033450290555894, 'epoch': 6.87}

 57%|█████▋    | 16089/28080 [31:47:59<23:49:00,  7.15s/it]
 57%|█████▋    | 16090/28080 [31:48:06<23:44:14,  7.13s/it]
                                                           
{'loss': 0.6236, 'learning_rate': 0.00020331670023863326, 'epoch': 6.87}

 57%|█████▋    | 16090/28080 [31:48:06<23:44:14,  7.13s/it]
 57%|█████▋    | 16091/28080 [31:48:13<23:45:04,  7.13s/it]
                                                           
{'loss': 0.593, 'learning_rate': 0.00020328837204275024, 'epoch': 6.87}

 57%|█████▋    | 16091/28080 [31:48:13<23:45:04,  7.13s/it]
 57%|█████▋    | 16092/28080 [31:48:20<23:38:49,  7.10s/it]
                                                           
{'loss': 0.6141, 'learning_rate': 0.00020326004446831727, 'epoch': 6.87}

 57%|█████▋    | 16092/28080 [31:48:20<23:38:49,  7.10s/it]
 57%|█████▋    | 16093/28080 [31:48:27<23:36:14,  7.09s/it]
                                                           
{'loss': 0.6119, 'learning_rate': 0.00020323171751571116, 'epoch': 6.87}

 57%|█████▋    | 16093/28080 [31:48:27<23:36:14,  7.09s/it]
 57%|█████▋    | 16094/28080 [31:48:35<23:40:33,  7.11s/it]
                                                           
{'loss': 0.6016, 'learning_rate': 0.0002032033911853088, 'epoch': 6.88}

 57%|█████▋    | 16094/28080 [31:48:35<23:40:33,  7.11s/it]
 57%|█████▋    | 16095/28080 [31:48:42<23:36:56,  7.09s/it]
                                                           
{'loss': 0.5978, 'learning_rate': 0.00020317506547748698, 'epoch': 6.88}

 57%|█████▋    | 16095/28080 [31:48:42<23:36:56,  7.09s/it]
 57%|█████▋    | 16096/28080 [31:48:49<23:32:32,  7.07s/it]
                                                           
{'loss': 0.6109, 'learning_rate': 0.00020314674039262278, 'epoch': 6.88}

 57%|█████▋    | 16096/28080 [31:48:49<23:32:32,  7.07s/it]
 57%|█████▋    | 16097/28080 [31:48:56<23:31:05,  7.07s/it]
                                                           
{'loss': 0.6111, 'learning_rate': 0.00020311841593109275, 'epoch': 6.88}

 57%|█████▋    | 16097/28080 [31:48:56<23:31:05,  7.07s/it]
 57%|█████▋    | 16098/28080 [31:49:03<23:33:53,  7.08s/it]
                                                           
{'loss': 0.6036, 'learning_rate': 0.00020309009209327383, 'epoch': 6.88}

 57%|█████▋    | 16098/28080 [31:49:03<23:33:53,  7.08s/it]
 57%|█████▋    | 16099/28080 [31:49:10<23:30:36,  7.06s/it]
                                                           
{'loss': 0.6189, 'learning_rate': 0.0002030617688795429, 'epoch': 6.88}

 57%|█████▋    | 16099/28080 [31:49:10<23:30:36,  7.06s/it]
 57%|█████▋    | 16100/28080 [31:49:17<23:32:50,  7.08s/it]
                                                           
{'loss': 0.6239, 'learning_rate': 0.0002030334462902766, 'epoch': 6.88}

 57%|█████▋    | 16100/28080 [31:49:17<23:32:50,  7.08s/it]
 57%|█████▋    | 16101/28080 [31:49:24<23:38:24,  7.10s/it]
                                                           
{'loss': 0.6052, 'learning_rate': 0.00020300512432585197, 'epoch': 6.88}

 57%|█████▋    | 16101/28080 [31:49:24<23:38:24,  7.10s/it]
 57%|█████▋    | 16102/28080 [31:49:31<23:38:20,  7.10s/it]
                                                           
{'loss': 0.6157, 'learning_rate': 0.00020297680298664552, 'epoch': 6.88}

 57%|█████▋    | 16102/28080 [31:49:31<23:38:20,  7.10s/it]
 57%|█████▋    | 16103/28080 [31:49:38<23:42:22,  7.13s/it]
                                                           
{'loss': 0.6112, 'learning_rate': 0.00020294848227303433, 'epoch': 6.88}

 57%|█████▋    | 16103/28080 [31:49:38<23:42:22,  7.13s/it]
 57%|█████▋    | 16104/28080 [31:49:46<23:47:57,  7.15s/it]
                                                           
{'loss': 0.6161, 'learning_rate': 0.00020292016218539499, 'epoch': 6.88}

 57%|█████▋    | 16104/28080 [31:49:46<23:47:57,  7.15s/it]
 57%|█████▋    | 16105/28080 [31:49:53<23:46:11,  7.15s/it]
                                                           
{'loss': 0.6132, 'learning_rate': 0.00020289184272410436, 'epoch': 6.88}

 57%|█████▋    | 16105/28080 [31:49:53<23:46:11,  7.15s/it]
 57%|█████▋    | 16106/28080 [31:50:00<23:47:06,  7.15s/it]
                                                           
{'loss': 0.6101, 'learning_rate': 0.0002028635238895391, 'epoch': 6.88}

 57%|█████▋    | 16106/28080 [31:50:00<23:47:06,  7.15s/it]
 57%|█████▋    | 16107/28080 [31:50:07<23:45:53,  7.15s/it]
                                                           
{'loss': 0.6205, 'learning_rate': 0.0002028352056820761, 'epoch': 6.88}

 57%|█████▋    | 16107/28080 [31:50:07<23:45:53,  7.15s/it]
 57%|█████▋    | 16108/28080 [31:50:14<23:42:49,  7.13s/it]
                                                           
{'loss': 0.6472, 'learning_rate': 0.00020280688810209196, 'epoch': 6.88}

 57%|█████▋    | 16108/28080 [31:50:14<23:42:49,  7.13s/it]
 57%|█████▋    | 16109/28080 [31:50:21<23:35:53,  7.10s/it]
                                                           
{'loss': 0.6182, 'learning_rate': 0.00020277857114996356, 'epoch': 6.88}

 57%|█████▋    | 16109/28080 [31:50:21<23:35:53,  7.10s/it]
 57%|█████▋    | 16110/28080 [31:50:28<23:41:12,  7.12s/it]
                                                           
{'loss': 0.6008, 'learning_rate': 0.00020275025482606752, 'epoch': 6.88}

 57%|█████▋    | 16110/28080 [31:50:28<23:41:12,  7.12s/it]
 57%|█████▋    | 16111/28080 [31:50:35<23:41:23,  7.13s/it]
                                                           
{'loss': 0.6263, 'learning_rate': 0.00020272193913078063, 'epoch': 6.88}

 57%|█████▋    | 16111/28080 [31:50:35<23:41:23,  7.13s/it]
 57%|█████▋    | 16112/28080 [31:50:43<23:44:48,  7.14s/it]
                                                           
{'loss': 0.6026, 'learning_rate': 0.00020269362406447945, 'epoch': 6.88}

 57%|█████▋    | 16112/28080 [31:50:43<23:44:48,  7.14s/it]
 57%|█████▋    | 16113/28080 [31:50:50<23:43:25,  7.14s/it]
                                                           
{'loss': 0.606, 'learning_rate': 0.00020266530962754096, 'epoch': 6.88}

 57%|█████▋    | 16113/28080 [31:50:50<23:43:25,  7.14s/it]
 57%|█████▋    | 16114/28080 [31:50:57<23:43:17,  7.14s/it]
                                                           
{'loss': 0.6068, 'learning_rate': 0.00020263699582034154, 'epoch': 6.88}

 57%|█████▋    | 16114/28080 [31:50:57<23:43:17,  7.14s/it]
 57%|█████▋    | 16115/28080 [31:51:04<23:35:28,  7.10s/it]
                                                           
{'loss': 0.5855, 'learning_rate': 0.00020260868264325815, 'epoch': 6.88}

 57%|█████▋    | 16115/28080 [31:51:04<23:35:28,  7.10s/it]
 57%|█████▋    | 16116/28080 [31:51:11<23:35:28,  7.10s/it]
                                                           
{'loss': 0.6218, 'learning_rate': 0.00020258037009666724, 'epoch': 6.88}

 57%|█████▋    | 16116/28080 [31:51:11<23:35:28,  7.10s/it]
 57%|█████▋    | 16117/28080 [31:51:18<23:40:49,  7.13s/it]
                                                           
{'loss': 0.6038, 'learning_rate': 0.00020255205818094568, 'epoch': 6.89}

 57%|█████▋    | 16117/28080 [31:51:18<23:40:49,  7.13s/it]
 57%|█████▋    | 16118/28080 [31:51:25<23:33:26,  7.09s/it]
                                                           
{'loss': 0.6287, 'learning_rate': 0.00020252374689646996, 'epoch': 6.89}

 57%|█████▋    | 16118/28080 [31:51:25<23:33:26,  7.09s/it]
 57%|█████▋    | 16119/28080 [31:51:32<23:39:55,  7.12s/it]
                                                           
{'loss': 0.603, 'learning_rate': 0.00020249543624361688, 'epoch': 6.89}

 57%|█████▋    | 16119/28080 [31:51:32<23:39:55,  7.12s/it]
 57%|█████▋    | 16120/28080 [31:51:39<23:38:39,  7.12s/it]
                                                           
{'loss': 0.6218, 'learning_rate': 0.00020246712622276297, 'epoch': 6.89}

 57%|█████▋    | 16120/28080 [31:51:39<23:38:39,  7.12s/it]
 57%|█████▋    | 16121/28080 [31:51:46<23:31:17,  7.08s/it]
                                                           
{'loss': 0.6166, 'learning_rate': 0.00020243881683428493, 'epoch': 6.89}

 57%|█████▋    | 16121/28080 [31:51:46<23:31:17,  7.08s/it]
 57%|█████▋    | 16122/28080 [31:51:53<23:28:51,  7.07s/it]
                                                           
{'loss': 0.6197, 'learning_rate': 0.0002024105080785594, 'epoch': 6.89}

 57%|█████▋    | 16122/28080 [31:51:54<23:28:51,  7.07s/it]
 57%|█████▋    | 16123/28080 [31:52:01<23:29:18,  7.07s/it]
                                                           
{'loss': 0.6145, 'learning_rate': 0.00020238219995596292, 'epoch': 6.89}

 57%|█████▋    | 16123/28080 [31:52:01<23:29:18,  7.07s/it]
 57%|█████▋    | 16124/28080 [31:52:08<23:35:46,  7.10s/it]
                                                           
{'loss': 0.6252, 'learning_rate': 0.00020235389246687217, 'epoch': 6.89}

 57%|█████▋    | 16124/28080 [31:52:08<23:35:46,  7.10s/it]
 57%|█████▋    | 16125/28080 [31:52:15<23:33:18,  7.09s/it]
                                                           
{'loss': 0.6272, 'learning_rate': 0.00020232558561166368, 'epoch': 6.89}

 57%|█████▋    | 16125/28080 [31:52:15<23:33:18,  7.09s/it]
 57%|█████▋    | 16126/28080 [31:52:22<23:45:52,  7.16s/it]
                                                           
{'loss': 0.5943, 'learning_rate': 0.00020229727939071414, 'epoch': 6.89}

 57%|█████▋    | 16126/28080 [31:52:22<23:45:52,  7.16s/it]
 57%|█████▋    | 16127/28080 [31:52:29<23:48:12,  7.17s/it]
                                                           
{'loss': 0.6251, 'learning_rate': 0.00020226897380440001, 'epoch': 6.89}

 57%|█████▋    | 16127/28080 [31:52:29<23:48:12,  7.17s/it]
 57%|█████▋    | 16128/28080 [31:52:36<23:44:58,  7.15s/it]
                                                           
{'loss': 0.6139, 'learning_rate': 0.00020224066885309806, 'epoch': 6.89}

 57%|█████▋    | 16128/28080 [31:52:36<23:44:58,  7.15s/it]
 57%|█████▋    | 16129/28080 [31:52:43<23:38:05,  7.12s/it]
                                                           
{'loss': 0.6101, 'learning_rate': 0.0002022123645371846, 'epoch': 6.89}

 57%|█████▋    | 16129/28080 [31:52:43<23:38:05,  7.12s/it]
 57%|█████▋    | 16130/28080 [31:52:51<23:40:07,  7.13s/it]
                                                           
{'loss': 0.5947, 'learning_rate': 0.00020218406085703645, 'epoch': 6.89}

 57%|█████▋    | 16130/28080 [31:52:51<23:40:07,  7.13s/it]
 57%|█████▋    | 16131/28080 [31:52:58<23:45:01,  7.16s/it]
                                                           
{'loss': 0.6324, 'learning_rate': 0.00020215575781302992, 'epoch': 6.89}

 57%|█████▋    | 16131/28080 [31:52:58<23:45:01,  7.16s/it]
 57%|█████▋    | 16132/28080 [31:53:05<23:37:50,  7.12s/it]
                                                           
{'loss': 0.617, 'learning_rate': 0.00020212745540554183, 'epoch': 6.89}

 57%|█████▋    | 16132/28080 [31:53:05<23:37:50,  7.12s/it]
 57%|█████▋    | 16133/28080 [31:53:12<23:36:47,  7.12s/it]
                                                           
{'loss': 0.6116, 'learning_rate': 0.0002020991536349484, 'epoch': 6.89}

 57%|█████▋    | 16133/28080 [31:53:12<23:36:47,  7.12s/it]
 57%|█████▋    | 16134/28080 [31:53:19<23:34:41,  7.11s/it]
                                                           
{'loss': 0.6102, 'learning_rate': 0.00020207085250162644, 'epoch': 6.89}

 57%|█████▋    | 16134/28080 [31:53:19<23:34:41,  7.11s/it]
 57%|█████▋    | 16135/28080 [31:53:26<23:35:54,  7.11s/it]
                                                           
{'loss': 0.6238, 'learning_rate': 0.00020204255200595225, 'epoch': 6.89}

 57%|█████▋    | 16135/28080 [31:53:26<23:35:54,  7.11s/it]
 57%|█████▋    | 16136/28080 [31:53:33<23:41:23,  7.14s/it]
                                                           
{'loss': 0.6199, 'learning_rate': 0.0002020142521483025, 'epoch': 6.89}

 57%|█████▋    | 16136/28080 [31:53:33<23:41:23,  7.14s/it]
 57%|█████▋    | 16137/28080 [31:53:41<23:44:47,  7.16s/it]
                                                           
{'loss': 0.6091, 'learning_rate': 0.00020198595292905358, 'epoch': 6.89}

 57%|█████▋    | 16137/28080 [31:53:41<23:44:47,  7.16s/it]
 57%|█████▋    | 16138/28080 [31:53:48<23:44:21,  7.16s/it]
                                                           
{'loss': 0.6111, 'learning_rate': 0.00020195765434858205, 'epoch': 6.89}

 57%|█████▋    | 16138/28080 [31:53:48<23:44:21,  7.16s/it]
 57%|█████▋    | 16139/28080 [31:53:55<23:38:19,  7.13s/it]
                                                           
{'loss': 0.6308, 'learning_rate': 0.00020192935640726435, 'epoch': 6.89}

 57%|█████▋    | 16139/28080 [31:53:55<23:38:19,  7.13s/it]
 57%|█████▋    | 16140/28080 [31:54:02<23:39:46,  7.13s/it]
                                                           
{'loss': 0.6001, 'learning_rate': 0.00020190105910547699, 'epoch': 6.89}

 57%|█████▋    | 16140/28080 [31:54:02<23:39:46,  7.13s/it]
 57%|█████▋    | 16141/28080 [31:54:09<23:36:28,  7.12s/it]
                                                           
{'loss': 0.6211, 'learning_rate': 0.00020187276244359637, 'epoch': 6.9}

 57%|█████▋    | 16141/28080 [31:54:09<23:36:28,  7.12s/it]
 57%|█████▋    | 16142/28080 [31:54:16<23:42:26,  7.15s/it]
                                                           
{'loss': 0.6075, 'learning_rate': 0.00020184446642199905, 'epoch': 6.9}

 57%|█████▋    | 16142/28080 [31:54:16<23:42:26,  7.15s/it]
 57%|█████▋    | 16143/28080 [31:54:23<23:39:05,  7.13s/it]
                                                           
{'loss': 0.6181, 'learning_rate': 0.00020181617104106134, 'epoch': 6.9}

 57%|█████▋    | 16143/28080 [31:54:23<23:39:05,  7.13s/it]
 57%|█████▋    | 16144/28080 [31:54:31<23:42:25,  7.15s/it]
                                                           
{'loss': 0.6152, 'learning_rate': 0.0002017878763011599, 'epoch': 6.9}

 57%|█████▋    | 16144/28080 [31:54:31<23:42:25,  7.15s/it]
 57%|█████▋    | 16145/28080 [31:54:38<23:40:58,  7.14s/it]
                                                           
{'loss': 0.6121, 'learning_rate': 0.00020175958220267087, 'epoch': 6.9}

 57%|█████▋    | 16145/28080 [31:54:38<23:40:58,  7.14s/it]
 57%|█████▊    | 16146/28080 [31:54:45<23:31:06,  7.09s/it]
                                                           
{'loss': 0.6167, 'learning_rate': 0.00020173128874597103, 'epoch': 6.9}

 57%|█████▊    | 16146/28080 [31:54:45<23:31:06,  7.09s/it]
 58%|█████▊    | 16147/28080 [31:54:52<23:33:27,  7.11s/it]
                                                           
{'loss': 0.6067, 'learning_rate': 0.00020170299593143652, 'epoch': 6.9}

 58%|█████▊    | 16147/28080 [31:54:52<23:33:27,  7.11s/it]
 58%|█████▊    | 16148/28080 [31:54:59<23:36:25,  7.12s/it]
                                                           
{'loss': 0.5876, 'learning_rate': 0.0002016747037594437, 'epoch': 6.9}

 58%|█████▊    | 16148/28080 [31:54:59<23:36:25,  7.12s/it]
 58%|█████▊    | 16149/28080 [31:55:06<23:37:31,  7.13s/it]
                                                           
{'loss': 0.6093, 'learning_rate': 0.00020164641223036927, 'epoch': 6.9}

 58%|█████▊    | 16149/28080 [31:55:06<23:37:31,  7.13s/it]
 58%|█████▊    | 16150/28080 [31:55:13<23:31:52,  7.10s/it]
                                                           
{'loss': 0.608, 'learning_rate': 0.00020161812134458925, 'epoch': 6.9}

 58%|█████▊    | 16150/28080 [31:55:13<23:31:52,  7.10s/it]
 58%|█████▊    | 16151/28080 [31:55:20<23:31:42,  7.10s/it]
                                                           
{'loss': 0.6205, 'learning_rate': 0.00020158983110248036, 'epoch': 6.9}

 58%|█████▊    | 16151/28080 [31:55:20<23:31:42,  7.10s/it]
 58%|█████▊    | 16152/28080 [31:55:27<23:37:31,  7.13s/it]
                                                           
{'loss': 0.6335, 'learning_rate': 0.00020156154150441876, 'epoch': 6.9}

 58%|█████▊    | 16152/28080 [31:55:27<23:37:31,  7.13s/it]
 58%|█████▊    | 16153/28080 [31:55:35<23:37:24,  7.13s/it]
                                                           
{'loss': 0.629, 'learning_rate': 0.00020153325255078093, 'epoch': 6.9}

 58%|█████▊    | 16153/28080 [31:55:35<23:37:24,  7.13s/it]
 58%|█████▊    | 16154/28080 [31:55:42<23:43:03,  7.16s/it]
                                                           
{'loss': 0.607, 'learning_rate': 0.00020150496424194313, 'epoch': 6.9}

 58%|█████▊    | 16154/28080 [31:55:42<23:43:03,  7.16s/it]
 58%|█████▊    | 16155/28080 [31:55:49<23:34:42,  7.12s/it]
                                                           
{'loss': 0.6109, 'learning_rate': 0.00020147667657828178, 'epoch': 6.9}

 58%|█████▊    | 16155/28080 [31:55:49<23:34:42,  7.12s/it]
 58%|█████▊    | 16156/28080 [31:55:56<23:34:08,  7.12s/it]
                                                           
{'loss': 0.6233, 'learning_rate': 0.00020144838956017314, 'epoch': 6.9}

 58%|█████▊    | 16156/28080 [31:55:56<23:34:08,  7.12s/it]
 58%|█████▊    | 16157/28080 [31:56:03<23:36:50,  7.13s/it]
                                                           
{'loss': 0.6074, 'learning_rate': 0.00020142010318799366, 'epoch': 6.9}

 58%|█████▊    | 16157/28080 [31:56:03<23:36:50,  7.13s/it]
 58%|█████▊    | 16158/28080 [31:56:10<23:37:38,  7.13s/it]
                                                           
{'loss': 0.606, 'learning_rate': 0.00020139181746211954, 'epoch': 6.9}

 58%|█████▊    | 16158/28080 [31:56:10<23:37:38,  7.13s/it]
 58%|█████▊    | 16159/28080 [31:56:17<23:31:36,  7.10s/it]
                                                           
{'loss': 0.6158, 'learning_rate': 0.0002013635323829272, 'epoch': 6.9}

 58%|█████▊    | 16159/28080 [31:56:17<23:31:36,  7.10s/it]
 58%|█████▊    | 16160/28080 [31:56:24<23:33:54,  7.12s/it]
                                                           
{'loss': 0.5994, 'learning_rate': 0.00020133524795079281, 'epoch': 6.9}

 58%|█████▊    | 16160/28080 [31:56:24<23:33:54,  7.12s/it]
 58%|█████▊    | 16161/28080 [31:56:32<23:37:20,  7.13s/it]
                                                           
{'loss': 0.6072, 'learning_rate': 0.00020130696416609278, 'epoch': 6.9}

 58%|█████▊    | 16161/28080 [31:56:32<23:37:20,  7.13s/it]
 58%|█████▊    | 16162/28080 [31:56:39<23:34:54,  7.12s/it]
                                                           
{'loss': 0.6149, 'learning_rate': 0.0002012786810292033, 'epoch': 6.9}

 58%|█████▊    | 16162/28080 [31:56:39<23:34:54,  7.12s/it]
 58%|█████▊    | 16163/28080 [31:56:46<23:34:33,  7.12s/it]
                                                           
{'loss': 0.6289, 'learning_rate': 0.00020125039854050085, 'epoch': 6.9}

 58%|█████▊    | 16163/28080 [31:56:46<23:34:33,  7.12s/it]
 58%|█████▊    | 16164/28080 [31:56:53<23:49:03,  7.20s/it]
                                                           
{'loss': 0.5892, 'learning_rate': 0.00020122211670036138, 'epoch': 6.91}

 58%|█████▊    | 16164/28080 [31:56:53<23:49:03,  7.20s/it]
 58%|█████▊    | 16165/28080 [31:57:00<23:40:22,  7.15s/it]
                                                           
{'loss': 0.6187, 'learning_rate': 0.00020119383550916143, 'epoch': 6.91}

 58%|█████▊    | 16165/28080 [31:57:00<23:40:22,  7.15s/it]
 58%|█████▊    | 16166/28080 [31:57:07<23:42:03,  7.16s/it]
                                                           
{'loss': 0.6039, 'learning_rate': 0.0002011655549672771, 'epoch': 6.91}

 58%|█████▊    | 16166/28080 [31:57:07<23:42:03,  7.16s/it]
 58%|█████▊    | 16167/28080 [31:57:14<23:31:41,  7.11s/it]
                                                           
{'loss': 0.6197, 'learning_rate': 0.00020113727507508472, 'epoch': 6.91}

 58%|█████▊    | 16167/28080 [31:57:14<23:31:41,  7.11s/it]
 58%|█████▊    | 16168/28080 [31:57:22<23:35:49,  7.13s/it]
                                                           
{'loss': 0.6256, 'learning_rate': 0.00020110899583296047, 'epoch': 6.91}

 58%|█████▊    | 16168/28080 [31:57:22<23:35:49,  7.13s/it]
 58%|█████▊    | 16169/28080 [31:57:29<23:37:24,  7.14s/it]
                                                           
{'loss': 0.6112, 'learning_rate': 0.00020108071724128063, 'epoch': 6.91}

 58%|█████▊    | 16169/28080 [31:57:29<23:37:24,  7.14s/it]
 58%|█████▊    | 16170/28080 [31:57:36<23:38:20,  7.15s/it]
                                                           
{'loss': 0.6447, 'learning_rate': 0.00020105243930042133, 'epoch': 6.91}

 58%|█████▊    | 16170/28080 [31:57:36<23:38:20,  7.15s/it]
 58%|█████▊    | 16171/28080 [31:57:43<23:36:27,  7.14s/it]
                                                           
{'loss': 0.6237, 'learning_rate': 0.00020102416201075884, 'epoch': 6.91}

 58%|█████▊    | 16171/28080 [31:57:43<23:36:27,  7.14s/it]
 58%|█████▊    | 16172/28080 [31:57:50<23:34:15,  7.13s/it]
                                                           
{'loss': 0.6163, 'learning_rate': 0.00020099588537266942, 'epoch': 6.91}

 58%|█████▊    | 16172/28080 [31:57:50<23:34:15,  7.13s/it]
 58%|█████▊    | 16173/28080 [31:57:57<23:31:44,  7.11s/it]
                                                           
{'loss': 0.6278, 'learning_rate': 0.0002009676093865291, 'epoch': 6.91}

 58%|█████▊    | 16173/28080 [31:57:57<23:31:44,  7.11s/it]
 58%|█████▊    | 16174/28080 [31:58:04<23:30:27,  7.11s/it]
                                                           
{'loss': 0.6332, 'learning_rate': 0.0002009393340527142, 'epoch': 6.91}

 58%|█████▊    | 16174/28080 [31:58:04<23:30:27,  7.11s/it]
 58%|█████▊    | 16175/28080 [31:58:12<23:38:50,  7.15s/it]
                                                           
{'loss': 0.6289, 'learning_rate': 0.00020091105937160078, 'epoch': 6.91}

 58%|█████▊    | 16175/28080 [31:58:12<23:38:50,  7.15s/it]
 58%|█████▊    | 16176/28080 [31:58:19<23:36:16,  7.14s/it]
                                                           
{'loss': 0.6116, 'learning_rate': 0.00020088278534356516, 'epoch': 6.91}

 58%|█████▊    | 16176/28080 [31:58:19<23:36:16,  7.14s/it]
 58%|█████▊    | 16177/28080 [31:58:26<23:23:42,  7.08s/it]
                                                           
{'loss': 0.6158, 'learning_rate': 0.00020085451196898336, 'epoch': 6.91}

 58%|█████▊    | 16177/28080 [31:58:26<23:23:42,  7.08s/it]
 58%|█████▊    | 16178/28080 [31:58:33<23:21:39,  7.07s/it]
                                                           
{'loss': 0.6335, 'learning_rate': 0.00020082623924823158, 'epoch': 6.91}

 58%|█████▊    | 16178/28080 [31:58:33<23:21:39,  7.07s/it]
 58%|█████▊    | 16179/28080 [31:58:40<23:29:45,  7.11s/it]
                                                           
{'loss': 0.6123, 'learning_rate': 0.0002007979671816859, 'epoch': 6.91}

 58%|█████▊    | 16179/28080 [31:58:40<23:29:45,  7.11s/it]
 58%|█████▊    | 16180/28080 [31:58:47<23:32:10,  7.12s/it]
                                                           
{'loss': 0.6152, 'learning_rate': 0.00020076969576972265, 'epoch': 6.91}

 58%|█████▊    | 16180/28080 [31:58:47<23:32:10,  7.12s/it]
 58%|█████▊    | 16181/28080 [31:58:54<23:33:24,  7.13s/it]
                                                           
{'loss': 0.5961, 'learning_rate': 0.00020074142501271767, 'epoch': 6.91}

 58%|█████▊    | 16181/28080 [31:58:54<23:33:24,  7.13s/it]
 58%|█████▊    | 16182/28080 [31:59:01<23:29:10,  7.11s/it]
                                                           
{'loss': 0.6308, 'learning_rate': 0.0002007131549110473, 'epoch': 6.91}

 58%|█████▊    | 16182/28080 [31:59:01<23:29:10,  7.11s/it]
 58%|█████▊    | 16183/28080 [31:59:08<23:24:18,  7.08s/it]
                                                           
{'loss': 0.6359, 'learning_rate': 0.0002006848854650875, 'epoch': 6.91}

 58%|█████▊    | 16183/28080 [31:59:08<23:24:18,  7.08s/it]
 58%|█████▊    | 16184/28080 [31:59:15<23:24:37,  7.08s/it]
                                                           
{'loss': 0.5935, 'learning_rate': 0.00020065661667521449, 'epoch': 6.91}

 58%|█████▊    | 16184/28080 [31:59:15<23:24:37,  7.08s/it]
 58%|█████▊    | 16185/28080 [31:59:23<23:31:52,  7.12s/it]
                                                           
{'loss': 0.604, 'learning_rate': 0.00020062834854180423, 'epoch': 6.91}

 58%|█████▊    | 16185/28080 [31:59:23<23:31:52,  7.12s/it]
 58%|█████▊    | 16186/28080 [31:59:30<23:31:23,  7.12s/it]
                                                           
{'loss': 0.595, 'learning_rate': 0.00020060008106523292, 'epoch': 6.91}

 58%|█████▊    | 16186/28080 [31:59:30<23:31:23,  7.12s/it]
 58%|█████▊    | 16187/28080 [31:59:37<23:33:39,  7.13s/it]
                                                           
{'loss': 0.6358, 'learning_rate': 0.0002005718142458765, 'epoch': 6.91}

 58%|█████▊    | 16187/28080 [31:59:37<23:33:39,  7.13s/it]
 58%|█████▊    | 16188/28080 [31:59:44<23:33:43,  7.13s/it]
                                                           
{'loss': 0.6195, 'learning_rate': 0.00020054354808411116, 'epoch': 6.92}

 58%|█████▊    | 16188/28080 [31:59:44<23:33:43,  7.13s/it]
 58%|█████▊    | 16189/28080 [31:59:51<23:28:36,  7.11s/it]
                                                           
{'loss': 0.623, 'learning_rate': 0.00020051528258031281, 'epoch': 6.92}

 58%|█████▊    | 16189/28080 [31:59:51<23:28:36,  7.11s/it]
 58%|█████▊    | 16190/28080 [31:59:58<23:31:43,  7.12s/it]
                                                           
{'loss': 0.6228, 'learning_rate': 0.00020048701773485767, 'epoch': 6.92}

 58%|█████▊    | 16190/28080 [31:59:58<23:31:43,  7.12s/it]
 58%|█████▊    | 16191/28080 [32:00:05<23:37:28,  7.15s/it]
                                                           
{'loss': 0.6171, 'learning_rate': 0.00020045875354812162, 'epoch': 6.92}

 58%|█████▊    | 16191/28080 [32:00:05<23:37:28,  7.15s/it]
 58%|█████▊    | 16192/28080 [32:00:12<23:36:22,  7.15s/it]
                                                           
{'loss': 0.6069, 'learning_rate': 0.0002004304900204808, 'epoch': 6.92}

 58%|█████▊    | 16192/28080 [32:00:12<23:36:22,  7.15s/it]
 58%|█████▊    | 16193/28080 [32:00:20<23:41:16,  7.17s/it]
                                                           
{'loss': 0.6084, 'learning_rate': 0.00020040222715231104, 'epoch': 6.92}

 58%|█████▊    | 16193/28080 [32:00:20<23:41:16,  7.17s/it]
 58%|█████▊    | 16194/28080 [32:00:27<23:36:24,  7.15s/it]
                                                           
{'loss': 0.6154, 'learning_rate': 0.00020037396494398865, 'epoch': 6.92}

 58%|█████▊    | 16194/28080 [32:00:27<23:36:24,  7.15s/it]
 58%|█████▊    | 16195/28080 [32:00:34<23:33:23,  7.14s/it]
                                                           
{'loss': 0.6179, 'learning_rate': 0.0002003457033958893, 'epoch': 6.92}

 58%|█████▊    | 16195/28080 [32:00:34<23:33:23,  7.14s/it]
 58%|█████▊    | 16196/28080 [32:00:41<23:37:46,  7.16s/it]
                                                           
{'loss': 0.6037, 'learning_rate': 0.0002003174425083893, 'epoch': 6.92}

 58%|█████▊    | 16196/28080 [32:00:41<23:37:46,  7.16s/it]
 58%|█████▊    | 16197/28080 [32:00:48<23:35:09,  7.15s/it]
                                                           
{'loss': 0.6298, 'learning_rate': 0.00020028918228186447, 'epoch': 6.92}

 58%|█████▊    | 16197/28080 [32:00:48<23:35:09,  7.15s/it]
 58%|█████▊    | 16198/28080 [32:00:55<23:31:09,  7.13s/it]
                                                           
{'loss': 0.628, 'learning_rate': 0.0002002609227166906, 'epoch': 6.92}

 58%|█████▊    | 16198/28080 [32:00:55<23:31:09,  7.13s/it]
 58%|█████▊    | 16199/28080 [32:01:02<23:33:02,  7.14s/it]
                                                           
{'loss': 0.6029, 'learning_rate': 0.00020023266381324407, 'epoch': 6.92}

 58%|█████▊    | 16199/28080 [32:01:02<23:33:02,  7.14s/it]
 58%|█████▊    | 16200/28080 [32:01:10<23:29:41,  7.12s/it]
                                                           
{'loss': 0.6351, 'learning_rate': 0.0002002044055719004, 'epoch': 6.92}

 58%|█████▊    | 16200/28080 [32:01:10<23:29:41,  7.12s/it]
 58%|█████▊    | 16201/28080 [32:01:17<23:34:57,  7.15s/it]
                                                           
{'loss': 0.6148, 'learning_rate': 0.00020017614799303584, 'epoch': 6.92}

 58%|█████▊    | 16201/28080 [32:01:17<23:34:57,  7.15s/it]
 58%|█████▊    | 16202/28080 [32:01:24<23:27:19,  7.11s/it]
                                                           
{'loss': 0.6303, 'learning_rate': 0.0002001478910770262, 'epoch': 6.92}

 58%|█████▊    | 16202/28080 [32:01:24<23:27:19,  7.11s/it]
 58%|█████▊    | 16203/28080 [32:01:31<23:28:12,  7.11s/it]
                                                           
{'loss': 0.6061, 'learning_rate': 0.00020011963482424752, 'epoch': 6.92}

 58%|█████▊    | 16203/28080 [32:01:31<23:28:12,  7.11s/it]
 58%|█████▊    | 16204/28080 [32:01:38<23:35:28,  7.15s/it]
                                                           
{'loss': 0.6254, 'learning_rate': 0.00020009137923507556, 'epoch': 6.92}

 58%|█████▊    | 16204/28080 [32:01:38<23:35:28,  7.15s/it]
 58%|█████▊    | 16205/28080 [32:01:45<23:33:17,  7.14s/it]
                                                           
{'loss': 0.6093, 'learning_rate': 0.00020006312430988636, 'epoch': 6.92}

 58%|█████▊    | 16205/28080 [32:01:45<23:33:17,  7.14s/it]
 58%|█████▊    | 16206/28080 [32:01:52<23:35:15,  7.15s/it]
                                                           
{'loss': 0.6119, 'learning_rate': 0.00020003487004905573, 'epoch': 6.92}

 58%|█████▊    | 16206/28080 [32:01:52<23:35:15,  7.15s/it]
 58%|█████▊    | 16207/28080 [32:02:00<23:30:55,  7.13s/it]
                                                           
{'loss': 0.627, 'learning_rate': 0.00020000661645295964, 'epoch': 6.92}

 58%|█████▊    | 16207/28080 [32:02:00<23:30:55,  7.13s/it]
 58%|█████▊    | 16208/28080 [32:02:07<23:31:55,  7.14s/it]
                                                           
{'loss': 0.5862, 'learning_rate': 0.0001999783635219739, 'epoch': 6.92}

 58%|█████▊    | 16208/28080 [32:02:07<23:31:55,  7.14s/it]
 58%|█████▊    | 16209/28080 [32:02:14<23:38:17,  7.17s/it]
                                                           
{'loss': 0.5961, 'learning_rate': 0.0001999501112564745, 'epoch': 6.92}

 58%|█████▊    | 16209/28080 [32:02:14<23:38:17,  7.17s/it]
 58%|█████▊    | 16210/28080 [32:02:21<23:27:13,  7.11s/it]
                                                           
{'loss': 0.6254, 'learning_rate': 0.00019992185965683713, 'epoch': 6.92}

 58%|█████▊    | 16210/28080 [32:02:21<23:27:13,  7.11s/it]
 58%|█████▊    | 16211/28080 [32:02:28<23:29:13,  7.12s/it]
                                                           
{'loss': 0.6177, 'learning_rate': 0.0001998936087234379, 'epoch': 6.93}

 58%|█████▊    | 16211/28080 [32:02:28<23:29:13,  7.12s/it]
 58%|█████▊    | 16212/28080 [32:02:35<23:25:30,  7.11s/it]
                                                           
{'loss': 0.6373, 'learning_rate': 0.00019986535845665235, 'epoch': 6.93}

 58%|█████▊    | 16212/28080 [32:02:35<23:25:30,  7.11s/it]
 58%|█████▊    | 16213/28080 [32:02:42<23:24:03,  7.10s/it]
                                                           
{'loss': 0.6373, 'learning_rate': 0.00019983710885685657, 'epoch': 6.93}

 58%|█████▊    | 16213/28080 [32:02:42<23:24:03,  7.10s/it]
 58%|█████▊    | 16214/28080 [32:02:49<23:28:21,  7.12s/it]
                                                           
{'loss': 0.6176, 'learning_rate': 0.00019980885992442628, 'epoch': 6.93}

 58%|█████▊    | 16214/28080 [32:02:49<23:28:21,  7.12s/it]
 58%|█████▊    | 16215/28080 [32:02:56<23:23:36,  7.10s/it]
                                                           
{'loss': 0.6278, 'learning_rate': 0.00019978061165973741, 'epoch': 6.93}

 58%|█████▊    | 16215/28080 [32:02:56<23:23:36,  7.10s/it]
 58%|█████▊    | 16216/28080 [32:03:04<23:31:41,  7.14s/it]
                                                           
{'loss': 0.6107, 'learning_rate': 0.0001997523640631656, 'epoch': 6.93}

 58%|█████▊    | 16216/28080 [32:03:04<23:31:41,  7.14s/it]
 58%|█████▊    | 16217/28080 [32:03:11<23:33:41,  7.15s/it]
                                                           
{'loss': 0.6292, 'learning_rate': 0.00019972411713508681, 'epoch': 6.93}

 58%|█████▊    | 16217/28080 [32:03:11<23:33:41,  7.15s/it]
 58%|█████▊    | 16218/28080 [32:03:18<23:27:23,  7.12s/it]
                                                           
{'loss': 0.6219, 'learning_rate': 0.00019969587087587673, 'epoch': 6.93}

 58%|█████▊    | 16218/28080 [32:03:18<23:27:23,  7.12s/it]
 58%|█████▊    | 16219/28080 [32:03:25<23:26:33,  7.12s/it]
                                                           
{'loss': 0.6282, 'learning_rate': 0.00019966762528591126, 'epoch': 6.93}

 58%|█████▊    | 16219/28080 [32:03:25<23:26:33,  7.12s/it]
 58%|█████▊    | 16220/28080 [32:03:32<23:24:58,  7.11s/it]
                                                           
{'loss': 0.6266, 'learning_rate': 0.00019963938036556602, 'epoch': 6.93}

 58%|█████▊    | 16220/28080 [32:03:32<23:24:58,  7.11s/it]
 58%|█████▊    | 16221/28080 [32:03:39<23:22:54,  7.10s/it]
                                                           
{'loss': 0.601, 'learning_rate': 0.00019961113611521695, 'epoch': 6.93}

 58%|█████▊    | 16221/28080 [32:03:39<23:22:54,  7.10s/it]
 58%|█████▊    | 16222/28080 [32:03:46<23:30:05,  7.13s/it]
                                                           
{'loss': 0.6094, 'learning_rate': 0.00019958289253523971, 'epoch': 6.93}

 58%|█████▊    | 16222/28080 [32:03:46<23:30:05,  7.13s/it]
 58%|█████▊    | 16223/28080 [32:03:53<23:27:34,  7.12s/it]
                                                           
{'loss': 0.6327, 'learning_rate': 0.00019955464962601006, 'epoch': 6.93}

 58%|█████▊    | 16223/28080 [32:03:53<23:27:34,  7.12s/it]
 58%|█████▊    | 16224/28080 [32:04:01<23:30:24,  7.14s/it]
                                                           
{'loss': 0.5971, 'learning_rate': 0.00019952640738790377, 'epoch': 6.93}

 58%|█████▊    | 16224/28080 [32:04:01<23:30:24,  7.14s/it]
 58%|█████▊    | 16225/28080 [32:04:08<23:37:01,  7.17s/it]
                                                           
{'loss': 0.61, 'learning_rate': 0.00019949816582129652, 'epoch': 6.93}

 58%|█████▊    | 16225/28080 [32:04:08<23:37:01,  7.17s/it]
 58%|█████▊    | 16226/28080 [32:04:15<23:35:37,  7.17s/it]
                                                           
{'loss': 0.6248, 'learning_rate': 0.0001994699249265641, 'epoch': 6.93}

 58%|█████▊    | 16226/28080 [32:04:15<23:35:37,  7.17s/it]
 58%|█████▊    | 16227/28080 [32:04:22<23:28:42,  7.13s/it]
                                                           
{'loss': 0.6386, 'learning_rate': 0.00019944168470408213, 'epoch': 6.93}

 58%|█████▊    | 16227/28080 [32:04:22<23:28:42,  7.13s/it]
 58%|█████▊    | 16228/28080 [32:04:29<23:30:45,  7.14s/it]
                                                           
{'loss': 0.6166, 'learning_rate': 0.0001994134451542265, 'epoch': 6.93}

 58%|█████▊    | 16228/28080 [32:04:29<23:30:45,  7.14s/it]
 58%|█████▊    | 16229/28080 [32:04:36<23:31:02,  7.14s/it]
                                                           
{'loss': 0.6209, 'learning_rate': 0.00019938520627737268, 'epoch': 6.93}

 58%|█████▊    | 16229/28080 [32:04:36<23:31:02,  7.14s/it]
 58%|█████▊    | 16230/28080 [32:04:43<23:22:23,  7.10s/it]
                                                           
{'loss': 0.6117, 'learning_rate': 0.00019935696807389663, 'epoch': 6.93}

 58%|█████▊    | 16230/28080 [32:04:43<23:22:23,  7.10s/it]
 58%|█████▊    | 16231/28080 [32:04:50<23:21:19,  7.10s/it]
                                                           
{'loss': 0.6138, 'learning_rate': 0.0001993287305441737, 'epoch': 6.93}

 58%|█████▊    | 16231/28080 [32:04:51<23:21:19,  7.10s/it]
 58%|█████▊    | 16232/28080 [32:04:58<23:23:25,  7.11s/it]
                                                           
{'loss': 0.6259, 'learning_rate': 0.00019930049368857986, 'epoch': 6.93}

 58%|█████▊    | 16232/28080 [32:04:58<23:23:25,  7.11s/it]
 58%|█████▊    | 16233/28080 [32:05:05<23:19:07,  7.09s/it]
                                                           
{'loss': 0.5998, 'learning_rate': 0.00019927225750749058, 'epoch': 6.93}

 58%|█████▊    | 16233/28080 [32:05:05<23:19:07,  7.09s/it]
 58%|█████▊    | 16234/28080 [32:05:12<23:26:19,  7.12s/it]
                                                           
{'loss': 0.6084, 'learning_rate': 0.00019924402200128163, 'epoch': 6.94}

 58%|█████▊    | 16234/28080 [32:05:12<23:26:19,  7.12s/it]
 58%|█████▊    | 16235/28080 [32:05:19<23:28:52,  7.14s/it]
                                                           
{'loss': 0.6075, 'learning_rate': 0.00019921578717032858, 'epoch': 6.94}

 58%|█████▊    | 16235/28080 [32:05:19<23:28:52,  7.14s/it]
 58%|█████▊    | 16236/28080 [32:05:26<23:31:59,  7.15s/it]
                                                           
{'loss': 0.6139, 'learning_rate': 0.00019918755301500714, 'epoch': 6.94}

 58%|█████▊    | 16236/28080 [32:05:26<23:31:59,  7.15s/it]
 58%|█████▊    | 16237/28080 [32:05:33<23:30:15,  7.14s/it]
                                                           
{'loss': 0.6321, 'learning_rate': 0.00019915931953569277, 'epoch': 6.94}

 58%|█████▊    | 16237/28080 [32:05:33<23:30:15,  7.14s/it]
 58%|█████▊    | 16238/28080 [32:05:41<23:32:02,  7.15s/it]
                                                           
{'loss': 0.6137, 'learning_rate': 0.00019913108673276131, 'epoch': 6.94}

 58%|█████▊    | 16238/28080 [32:05:41<23:32:02,  7.15s/it]
 58%|█████▊    | 16239/28080 [32:05:48<23:26:33,  7.13s/it]
                                                           
{'loss': 0.6114, 'learning_rate': 0.00019910285460658823, 'epoch': 6.94}

 58%|█████▊    | 16239/28080 [32:05:48<23:26:33,  7.13s/it]
 58%|█████▊    | 16240/28080 [32:05:55<23:29:21,  7.14s/it]
                                                           
{'loss': 0.6039, 'learning_rate': 0.00019907462315754917, 'epoch': 6.94}

 58%|█████▊    | 16240/28080 [32:05:55<23:29:21,  7.14s/it]
 58%|█████▊    | 16241/28080 [32:06:02<23:27:16,  7.13s/it]
                                                           
{'loss': 0.6039, 'learning_rate': 0.00019904639238601962, 'epoch': 6.94}

 58%|█████▊    | 16241/28080 [32:06:02<23:27:16,  7.13s/it]
 58%|█████▊    | 16242/28080 [32:06:09<23:26:02,  7.13s/it]
                                                           
{'loss': 0.6132, 'learning_rate': 0.00019901816229237545, 'epoch': 6.94}

 58%|█████▊    | 16242/28080 [32:06:09<23:26:02,  7.13s/it]
 58%|█████▊    | 16243/28080 [32:06:16<23:31:28,  7.15s/it]
                                                           
{'loss': 0.6126, 'learning_rate': 0.00019898993287699183, 'epoch': 6.94}

 58%|█████▊    | 16243/28080 [32:06:16<23:31:28,  7.15s/it]
 58%|█████▊    | 16244/28080 [32:06:23<23:30:33,  7.15s/it]
                                                           
{'loss': 0.6111, 'learning_rate': 0.00019896170414024464, 'epoch': 6.94}

 58%|█████▊    | 16244/28080 [32:06:23<23:30:33,  7.15s/it]
 58%|█████▊    | 16245/28080 [32:06:31<23:31:32,  7.16s/it]
                                                           
{'loss': 0.6165, 'learning_rate': 0.00019893347608250929, 'epoch': 6.94}

 58%|█████▊    | 16245/28080 [32:06:31<23:31:32,  7.16s/it]
 58%|█████▊    | 16246/28080 [32:06:38<23:28:13,  7.14s/it]
                                                           
{'loss': 0.6102, 'learning_rate': 0.00019890524870416139, 'epoch': 6.94}

 58%|█████▊    | 16246/28080 [32:06:38<23:28:13,  7.14s/it]
 58%|█████▊    | 16247/28080 [32:06:45<23:25:38,  7.13s/it]
                                                           
{'loss': 0.5951, 'learning_rate': 0.0001988770220055765, 'epoch': 6.94}

 58%|█████▊    | 16247/28080 [32:06:45<23:25:38,  7.13s/it]
 58%|█████▊    | 16248/28080 [32:06:52<23:27:54,  7.14s/it]
                                                           
{'loss': 0.5961, 'learning_rate': 0.00019884879598712992, 'epoch': 6.94}

 58%|█████▊    | 16248/28080 [32:06:52<23:27:54,  7.14s/it]
 58%|█████▊    | 16249/28080 [32:06:59<23:32:28,  7.16s/it]
                                                           
{'loss': 0.6101, 'learning_rate': 0.0001988205706491975, 'epoch': 6.94}

 58%|█████▊    | 16249/28080 [32:06:59<23:32:28,  7.16s/it]
 58%|█████▊    | 16250/28080 [32:07:06<23:27:07,  7.14s/it]
                                                           
{'loss': 0.604, 'learning_rate': 0.00019879234599215449, 'epoch': 6.94}

 58%|█████▊    | 16250/28080 [32:07:06<23:27:07,  7.14s/it]
 58%|█████▊    | 16251/28080 [32:07:13<23:19:09,  7.10s/it]
                                                           
{'loss': 0.6097, 'learning_rate': 0.00019876412201637656, 'epoch': 6.94}

 58%|█████▊    | 16251/28080 [32:07:13<23:19:09,  7.10s/it]
 58%|█████▊    | 16252/28080 [32:07:20<23:15:08,  7.08s/it]
                                                           
{'loss': 0.601, 'learning_rate': 0.00019873589872223909, 'epoch': 6.94}

 58%|█████▊    | 16252/28080 [32:07:20<23:15:08,  7.08s/it]
 58%|█████▊    | 16253/28080 [32:07:27<23:16:30,  7.08s/it]
                                                           
{'loss': 0.6105, 'learning_rate': 0.00019870767611011758, 'epoch': 6.94}

 58%|█████▊    | 16253/28080 [32:07:27<23:16:30,  7.08s/it]
 58%|█████▊    | 16254/28080 [32:07:34<23:13:58,  7.07s/it]
                                                           
{'loss': 0.5968, 'learning_rate': 0.00019867945418038755, 'epoch': 6.94}

 58%|█████▊    | 16254/28080 [32:07:34<23:13:58,  7.07s/it]
 58%|█████▊    | 16255/28080 [32:07:42<23:30:06,  7.15s/it]
                                                           
{'loss': 0.6118, 'learning_rate': 0.00019865123293342447, 'epoch': 6.94}

 58%|█████▊    | 16255/28080 [32:07:42<23:30:06,  7.15s/it]
 58%|█████▊    | 16256/28080 [32:07:49<23:30:00,  7.15s/it]
                                                           
{'loss': 0.5956, 'learning_rate': 0.0001986230123696037, 'epoch': 6.94}

 58%|█████▊    | 16256/28080 [32:07:49<23:30:00,  7.15s/it]
 58%|█████▊    | 16257/28080 [32:07:56<23:24:03,  7.13s/it]
                                                           
{'loss': 0.622, 'learning_rate': 0.0001985947924893008, 'epoch': 6.94}

 58%|█████▊    | 16257/28080 [32:07:56<23:24:03,  7.13s/it]
 58%|█████▊    | 16258/28080 [32:08:03<23:19:07,  7.10s/it]
                                                           
{'loss': 0.6241, 'learning_rate': 0.00019856657329289103, 'epoch': 6.95}

 58%|█████▊    | 16258/28080 [32:08:03<23:19:07,  7.10s/it]
 58%|█████▊    | 16259/28080 [32:08:10<23:18:32,  7.10s/it]
                                                           
{'loss': 0.6239, 'learning_rate': 0.00019853835478075014, 'epoch': 6.95}

 58%|█████▊    | 16259/28080 [32:08:10<23:18:32,  7.10s/it]
 58%|█████▊    | 16260/28080 [32:08:17<23:26:08,  7.14s/it]
                                                           
{'loss': 0.6228, 'learning_rate': 0.00019851013695325318, 'epoch': 6.95}

 58%|█████▊    | 16260/28080 [32:08:17<23:26:08,  7.14s/it]
 58%|█████▊    | 16261/28080 [32:08:24<23:25:34,  7.14s/it]
                                                           
{'loss': 0.6246, 'learning_rate': 0.00019848191981077588, 'epoch': 6.95}

 58%|█████▊    | 16261/28080 [32:08:24<23:25:34,  7.14s/it]
 58%|█████▊    | 16262/28080 [32:08:32<23:27:56,  7.15s/it]
                                                           
{'loss': 0.6118, 'learning_rate': 0.00019845370335369334, 'epoch': 6.95}

 58%|█████▊    | 16262/28080 [32:08:32<23:27:56,  7.15s/it]
 58%|█████▊    | 16263/28080 [32:08:39<23:27:18,  7.15s/it]
                                                           
{'loss': 0.6096, 'learning_rate': 0.0001984254875823812, 'epoch': 6.95}

 58%|█████▊    | 16263/28080 [32:08:39<23:27:18,  7.15s/it]
 58%|█████▊    | 16264/28080 [32:08:46<23:24:52,  7.13s/it]
                                                           
{'loss': 0.6177, 'learning_rate': 0.00019839727249721468, 'epoch': 6.95}

 58%|█████▊    | 16264/28080 [32:08:46<23:24:52,  7.13s/it]
 58%|█████▊    | 16265/28080 [32:08:53<23:16:36,  7.09s/it]
                                                           
{'loss': 0.6296, 'learning_rate': 0.00019836905809856925, 'epoch': 6.95}

 58%|█████▊    | 16265/28080 [32:08:53<23:16:36,  7.09s/it]
 58%|█████▊    | 16266/28080 [32:09:00<23:12:18,  7.07s/it]
                                                           
{'loss': 0.6159, 'learning_rate': 0.0001983408443868202, 'epoch': 6.95}

 58%|█████▊    | 16266/28080 [32:09:00<23:12:18,  7.07s/it]
 58%|█████▊    | 16267/28080 [32:09:07<23:10:11,  7.06s/it]
                                                           
{'loss': 0.5916, 'learning_rate': 0.00019831263136234302, 'epoch': 6.95}

 58%|█████▊    | 16267/28080 [32:09:07<23:10:11,  7.06s/it]
 58%|█████▊    | 16268/28080 [32:09:14<23:07:58,  7.05s/it]
                                                           
{'loss': 0.6247, 'learning_rate': 0.00019828441902551284, 'epoch': 6.95}

 58%|█████▊    | 16268/28080 [32:09:14<23:07:58,  7.05s/it]
 58%|█████▊    | 16269/28080 [32:09:21<23:17:25,  7.10s/it]
                                                           
{'loss': 0.6161, 'learning_rate': 0.0001982562073767052, 'epoch': 6.95}

 58%|█████▊    | 16269/28080 [32:09:21<23:17:25,  7.10s/it]
 58%|█████▊    | 16270/28080 [32:09:28<23:17:06,  7.10s/it]
                                                           
{'loss': 0.6193, 'learning_rate': 0.00019822799641629527, 'epoch': 6.95}

 58%|█████▊    | 16270/28080 [32:09:28<23:17:06,  7.10s/it]
 58%|█████▊    | 16271/28080 [32:09:35<23:11:39,  7.07s/it]
                                                           
{'loss': 0.6283, 'learning_rate': 0.0001981997861446585, 'epoch': 6.95}

 58%|█████▊    | 16271/28080 [32:09:35<23:11:39,  7.07s/it]
 58%|█████▊    | 16272/28080 [32:09:42<23:13:23,  7.08s/it]
                                                           
{'loss': 0.5897, 'learning_rate': 0.00019817157656217013, 'epoch': 6.95}

 58%|█████▊    | 16272/28080 [32:09:42<23:13:23,  7.08s/it]
 58%|█████▊    | 16273/28080 [32:09:49<23:08:30,  7.06s/it]
                                                           
{'loss': 0.6225, 'learning_rate': 0.00019814336766920543, 'epoch': 6.95}

 58%|█████▊    | 16273/28080 [32:09:49<23:08:30,  7.06s/it]
 58%|█████▊    | 16274/28080 [32:09:56<23:12:41,  7.08s/it]
                                                           
{'loss': 0.6107, 'learning_rate': 0.00019811515946613977, 'epoch': 6.95}

 58%|█████▊    | 16274/28080 [32:09:56<23:12:41,  7.08s/it]
 58%|█████▊    | 16275/28080 [32:10:04<23:19:24,  7.11s/it]
                                                           
{'loss': 0.5899, 'learning_rate': 0.00019808695195334825, 'epoch': 6.95}

 58%|█████▊    | 16275/28080 [32:10:04<23:19:24,  7.11s/it]
 58%|█████▊    | 16276/28080 [32:10:11<23:22:32,  7.13s/it]
                                                           
{'loss': 0.6111, 'learning_rate': 0.00019805874513120647, 'epoch': 6.95}

 58%|█████▊    | 16276/28080 [32:10:11<23:22:32,  7.13s/it]
 58%|█████▊    | 16277/28080 [32:10:18<23:23:30,  7.13s/it]
                                                           
{'loss': 0.6284, 'learning_rate': 0.00019803053900008933, 'epoch': 6.95}

 58%|█████▊    | 16277/28080 [32:10:18<23:23:30,  7.13s/it]
 58%|█████▊    | 16278/28080 [32:10:25<23:16:57,  7.10s/it]
                                                           
{'loss': 0.6443, 'learning_rate': 0.00019800233356037243, 'epoch': 6.95}

 58%|█████▊    | 16278/28080 [32:10:25<23:16:57,  7.10s/it]
 58%|█████▊    | 16279/28080 [32:10:32<23:20:53,  7.12s/it]
                                                           
{'loss': 0.6227, 'learning_rate': 0.00019797412881243065, 'epoch': 6.95}

 58%|█████▊    | 16279/28080 [32:10:32<23:20:53,  7.12s/it]
 58%|█████▊    | 16280/28080 [32:10:39<23:20:05,  7.12s/it]
                                                           
{'loss': 0.6167, 'learning_rate': 0.00019794592475663955, 'epoch': 6.95}

 58%|█████▊    | 16280/28080 [32:10:39<23:20:05,  7.12s/it]
 58%|█████▊    | 16281/28080 [32:10:46<23:19:23,  7.12s/it]
                                                           
{'loss': 0.6035, 'learning_rate': 0.00019791772139337416, 'epoch': 6.96}

 58%|█████▊    | 16281/28080 [32:10:46<23:19:23,  7.12s/it]
 58%|█████▊    | 16282/28080 [32:10:54<23:18:10,  7.11s/it]
                                                           
{'loss': 0.604, 'learning_rate': 0.0001978895187230098, 'epoch': 6.96}

 58%|█████▊    | 16282/28080 [32:10:54<23:18:10,  7.11s/it]
 58%|█████▊    | 16283/28080 [32:11:01<23:18:09,  7.11s/it]
                                                           
{'loss': 0.6028, 'learning_rate': 0.0001978613167459216, 'epoch': 6.96}

 58%|█████▊    | 16283/28080 [32:11:01<23:18:09,  7.11s/it]
 58%|█████▊    | 16284/28080 [32:11:08<23:17:24,  7.11s/it]
                                                           
{'loss': 0.6193, 'learning_rate': 0.00019783311546248483, 'epoch': 6.96}

 58%|█████▊    | 16284/28080 [32:11:08<23:17:24,  7.11s/it]
 58%|█████▊    | 16285/28080 [32:11:15<23:19:49,  7.12s/it]
                                                           
{'loss': 0.6133, 'learning_rate': 0.0001978049148730746, 'epoch': 6.96}

 58%|█████▊    | 16285/28080 [32:11:15<23:19:49,  7.12s/it]
 58%|█████▊    | 16286/28080 [32:11:22<23:22:04,  7.13s/it]
                                                           
{'loss': 0.6229, 'learning_rate': 0.00019777671497806616, 'epoch': 6.96}

 58%|█████▊    | 16286/28080 [32:11:22<23:22:04,  7.13s/it]
 58%|█████▊    | 16287/28080 [32:11:29<23:28:10,  7.16s/it]
                                                           
{'loss': 0.6104, 'learning_rate': 0.00019774851577783462, 'epoch': 6.96}

 58%|█████▊    | 16287/28080 [32:11:29<23:28:10,  7.16s/it]
 58%|█████▊    | 16288/28080 [32:11:36<23:23:58,  7.14s/it]
                                                           
{'loss': 0.6233, 'learning_rate': 0.0001977203172727552, 'epoch': 6.96}

 58%|█████▊    | 16288/28080 [32:11:36<23:23:58,  7.14s/it]
 58%|█████▊    | 16289/28080 [32:11:43<23:15:18,  7.10s/it]
                                                           
{'loss': 0.606, 'learning_rate': 0.00019769211946320297, 'epoch': 6.96}

 58%|█████▊    | 16289/28080 [32:11:43<23:15:18,  7.10s/it]
 58%|█████▊    | 16290/28080 [32:11:51<23:17:33,  7.11s/it]
                                                           
{'loss': 0.5766, 'learning_rate': 0.00019766392234955323, 'epoch': 6.96}

 58%|█████▊    | 16290/28080 [32:11:51<23:17:33,  7.11s/it]
 58%|█████▊    | 16291/28080 [32:11:58<23:21:27,  7.13s/it]
                                                           
{'loss': 0.6047, 'learning_rate': 0.00019763572593218086, 'epoch': 6.96}

 58%|█████▊    | 16291/28080 [32:11:58<23:21:27,  7.13s/it]
 58%|█████▊    | 16292/28080 [32:12:05<23:27:11,  7.16s/it]
                                                           
{'loss': 0.6245, 'learning_rate': 0.00019760753021146133, 'epoch': 6.96}

 58%|█████▊    | 16292/28080 [32:12:05<23:27:11,  7.16s/it]
 58%|█████▊    | 16293/28080 [32:12:12<23:26:07,  7.16s/it]
                                                           
{'loss': 0.6104, 'learning_rate': 0.00019757933518776939, 'epoch': 6.96}

 58%|█████▊    | 16293/28080 [32:12:12<23:26:07,  7.16s/it]
 58%|█████▊    | 16294/28080 [32:12:19<23:25:57,  7.16s/it]
                                                           
{'loss': 0.595, 'learning_rate': 0.0001975511408614804, 'epoch': 6.96}

 58%|█████▊    | 16294/28080 [32:12:19<23:25:57,  7.16s/it]
 58%|█████▊    | 16295/28080 [32:12:26<23:19:58,  7.13s/it]
                                                           
{'loss': 0.6126, 'learning_rate': 0.00019752294723296933, 'epoch': 6.96}

 58%|█████▊    | 16295/28080 [32:12:26<23:19:58,  7.13s/it]
 58%|█████▊    | 16296/28080 [32:12:33<23:24:24,  7.15s/it]
                                                           
{'loss': 0.5881, 'learning_rate': 0.00019749475430261138, 'epoch': 6.96}

 58%|█████▊    | 16296/28080 [32:12:33<23:24:24,  7.15s/it]
 58%|█████▊    | 16297/28080 [32:12:41<23:26:40,  7.16s/it]
                                                           
{'loss': 0.625, 'learning_rate': 0.00019746656207078153, 'epoch': 6.96}

 58%|█████▊    | 16297/28080 [32:12:41<23:26:40,  7.16s/it]
 58%|█████▊    | 16298/28080 [32:12:48<23:16:51,  7.11s/it]
                                                           
{'loss': 0.6339, 'learning_rate': 0.00019743837053785482, 'epoch': 6.96}

 58%|█████▊    | 16298/28080 [32:12:48<23:16:51,  7.11s/it]
 58%|█████▊    | 16299/28080 [32:12:55<23:20:10,  7.13s/it]
                                                           
{'loss': 0.5886, 'learning_rate': 0.00019741017970420643, 'epoch': 6.96}

 58%|█████▊    | 16299/28080 [32:12:55<23:20:10,  7.13s/it]
 58%|█████▊    | 16300/28080 [32:13:02<23:14:01,  7.10s/it]
                                                           
{'loss': 0.6198, 'learning_rate': 0.0001973819895702113, 'epoch': 6.96}

 58%|█████▊    | 16300/28080 [32:13:02<23:14:01,  7.10s/it]
 58%|█████▊    | 16301/28080 [32:13:09<23:16:32,  7.11s/it]
                                                           
{'loss': 0.6482, 'learning_rate': 0.00019735380013624458, 'epoch': 6.96}

 58%|█████▊    | 16301/28080 [32:13:09<23:16:32,  7.11s/it]
 58%|█████▊    | 16302/28080 [32:13:16<23:16:15,  7.11s/it]
                                                           
{'loss': 0.6259, 'learning_rate': 0.00019732561140268115, 'epoch': 6.96}

 58%|█████▊    | 16302/28080 [32:13:16<23:16:15,  7.11s/it]
 58%|█████▊    | 16303/28080 [32:13:23<23:20:22,  7.13s/it]
                                                           
{'loss': 0.6206, 'learning_rate': 0.0001972974233698962, 'epoch': 6.96}

 58%|█████▊    | 16303/28080 [32:13:23<23:20:22,  7.13s/it]
 58%|█████▊    | 16304/28080 [32:13:30<23:23:09,  7.15s/it]
                                                           
{'loss': 0.6153, 'learning_rate': 0.00019726923603826462, 'epoch': 6.96}

 58%|█████▊    | 16304/28080 [32:13:30<23:23:09,  7.15s/it]
 58%|█████▊    | 16305/28080 [32:13:38<23:25:41,  7.16s/it]
                                                           
{'loss': 0.6193, 'learning_rate': 0.00019724104940816145, 'epoch': 6.97}

 58%|█████▊    | 16305/28080 [32:13:38<23:25:41,  7.16s/it]
 58%|█████▊    | 16306/28080 [32:13:45<23:21:27,  7.14s/it]
                                                           
{'loss': 0.5858, 'learning_rate': 0.00019721286347996165, 'epoch': 6.97}

 58%|█████▊    | 16306/28080 [32:13:45<23:21:27,  7.14s/it]
 58%|█████▊    | 16307/28080 [32:13:52<23:25:12,  7.16s/it]
                                                           
{'loss': 0.5936, 'learning_rate': 0.00019718467825404035, 'epoch': 6.97}

 58%|█████▊    | 16307/28080 [32:13:52<23:25:12,  7.16s/it]
 58%|█████▊    | 16308/28080 [32:13:59<23:25:30,  7.16s/it]
                                                           
{'loss': 0.6238, 'learning_rate': 0.00019715649373077228, 'epoch': 6.97}

 58%|█████▊    | 16308/28080 [32:13:59<23:25:30,  7.16s/it]
 58%|█████▊    | 16309/28080 [32:14:06<23:19:49,  7.14s/it]
                                                           
{'loss': 0.6263, 'learning_rate': 0.0001971283099105327, 'epoch': 6.97}

 58%|█████▊    | 16309/28080 [32:14:06<23:19:49,  7.14s/it]
 58%|█████▊    | 16310/28080 [32:14:13<23:20:10,  7.14s/it]
                                                           
{'loss': 0.6208, 'learning_rate': 0.00019710012679369628, 'epoch': 6.97}

 58%|█████▊    | 16310/28080 [32:14:13<23:20:10,  7.14s/it]
 58%|█████▊    | 16311/28080 [32:14:20<23:13:32,  7.10s/it]
                                                           
{'loss': 0.6331, 'learning_rate': 0.0001970719443806382, 'epoch': 6.97}

 58%|█████▊    | 16311/28080 [32:14:20<23:13:32,  7.10s/it]
 58%|█████▊    | 16312/28080 [32:14:28<23:19:57,  7.14s/it]
                                                           
{'loss': 0.6286, 'learning_rate': 0.0001970437626717332, 'epoch': 6.97}

 58%|█████▊    | 16312/28080 [32:14:28<23:19:57,  7.14s/it]
 58%|█████▊    | 16313/28080 [32:14:35<23:13:42,  7.11s/it]
                                                           
{'loss': 0.6165, 'learning_rate': 0.00019701558166735638, 'epoch': 6.97}

 58%|█████▊    | 16313/28080 [32:14:35<23:13:42,  7.11s/it]
 58%|█████▊    | 16314/28080 [32:14:42<23:13:24,  7.11s/it]
                                                           
{'loss': 0.595, 'learning_rate': 0.00019698740136788256, 'epoch': 6.97}

 58%|█████▊    | 16314/28080 [32:14:42<23:13:24,  7.11s/it]
 58%|█████▊    | 16315/28080 [32:14:49<23:14:59,  7.11s/it]
                                                           
{'loss': 0.6124, 'learning_rate': 0.00019695922177368673, 'epoch': 6.97}

 58%|█████▊    | 16315/28080 [32:14:49<23:14:59,  7.11s/it]
 58%|█████▊    | 16316/28080 [32:14:56<23:11:05,  7.10s/it]
                                                           
{'loss': 0.6292, 'learning_rate': 0.00019693104288514367, 'epoch': 6.97}

 58%|█████▊    | 16316/28080 [32:14:56<23:11:05,  7.10s/it]
 58%|█████▊    | 16317/28080 [32:15:03<23:18:55,  7.14s/it]
                                                           
{'loss': 0.6058, 'learning_rate': 0.00019690286470262837, 'epoch': 6.97}

 58%|█████▊    | 16317/28080 [32:15:03<23:18:55,  7.14s/it]
 58%|█████▊    | 16318/28080 [32:15:10<23:17:02,  7.13s/it]
                                                           
{'loss': 0.6033, 'learning_rate': 0.00019687468722651564, 'epoch': 6.97}

 58%|█████▊    | 16318/28080 [32:15:10<23:17:02,  7.13s/it]
 58%|█████▊    | 16319/28080 [32:15:18<23:27:43,  7.18s/it]
                                                           
{'loss': 0.599, 'learning_rate': 0.00019684651045718044, 'epoch': 6.97}

 58%|█████▊    | 16319/28080 [32:15:18<23:27:43,  7.18s/it]
 58%|█████▊    | 16320/28080 [32:15:25<23:23:21,  7.16s/it]
                                                           
{'loss': 0.5935, 'learning_rate': 0.00019681833439499748, 'epoch': 6.97}

 58%|█████▊    | 16320/28080 [32:15:25<23:23:21,  7.16s/it]
 58%|█████▊    | 16321/28080 [32:15:32<23:10:49,  7.10s/it]
                                                           
{'loss': 0.6237, 'learning_rate': 0.00019679015904034187, 'epoch': 6.97}

 58%|█████▊    | 16321/28080 [32:15:32<23:10:49,  7.10s/it]
 58%|█████▊    | 16322/28080 [32:15:39<23:08:39,  7.09s/it]
                                                           
{'loss': 0.6159, 'learning_rate': 0.00019676198439358823, 'epoch': 6.97}

 58%|█████▊    | 16322/28080 [32:15:39<23:08:39,  7.09s/it]
 58%|█████▊    | 16323/28080 [32:15:46<23:14:36,  7.12s/it]
                                                           
{'loss': 0.6077, 'learning_rate': 0.00019673381045511143, 'epoch': 6.97}

 58%|█████▊    | 16323/28080 [32:15:46<23:14:36,  7.12s/it]
 58%|█████▊    | 16324/28080 [32:15:53<23:12:12,  7.11s/it]
                                                           
{'loss': 0.6011, 'learning_rate': 0.00019670563722528638, 'epoch': 6.97}

 58%|█████▊    | 16324/28080 [32:15:53<23:12:12,  7.11s/it]
 58%|█████▊    | 16325/28080 [32:16:00<23:17:05,  7.13s/it]
                                                           
{'loss': 0.6185, 'learning_rate': 0.00019667746470448775, 'epoch': 6.97}

 58%|█████▊    | 16325/28080 [32:16:00<23:17:05,  7.13s/it]
 58%|█████▊    | 16326/28080 [32:16:07<23:20:51,  7.15s/it]
                                                           
{'loss': 0.6148, 'learning_rate': 0.00019664929289309058, 'epoch': 6.97}

 58%|█████▊    | 16326/28080 [32:16:07<23:20:51,  7.15s/it]
 58%|█████▊    | 16327/28080 [32:16:14<23:19:12,  7.14s/it]
                                                           
{'loss': 0.6201, 'learning_rate': 0.0001966211217914694, 'epoch': 6.97}

 58%|█████▊    | 16327/28080 [32:16:14<23:19:12,  7.14s/it]
 58%|█████▊    | 16328/28080 [32:16:22<23:20:51,  7.15s/it]
                                                           
{'loss': 0.6335, 'learning_rate': 0.00019659295139999922, 'epoch': 6.98}

 58%|█████▊    | 16328/28080 [32:16:22<23:20:51,  7.15s/it]
 58%|█████▊    | 16329/28080 [32:16:29<23:14:44,  7.12s/it]
                                                           
{'loss': 0.6324, 'learning_rate': 0.00019656478171905465, 'epoch': 6.98}

 58%|█████▊    | 16329/28080 [32:16:29<23:14:44,  7.12s/it]
 58%|█████▊    | 16330/28080 [32:16:36<23:12:27,  7.11s/it]
                                                           
{'loss': 0.6156, 'learning_rate': 0.0001965366127490106, 'epoch': 6.98}

 58%|█████▊    | 16330/28080 [32:16:36<23:12:27,  7.11s/it]
 58%|█████▊    | 16331/28080 [32:16:43<23:16:59,  7.13s/it]
                                                           
{'loss': 0.6072, 'learning_rate': 0.00019650844449024173, 'epoch': 6.98}

 58%|█████▊    | 16331/28080 [32:16:43<23:16:59,  7.13s/it]
 58%|█████▊    | 16332/28080 [32:16:50<23:10:08,  7.10s/it]
                                                           
{'loss': 0.6376, 'learning_rate': 0.00019648027694312288, 'epoch': 6.98}

 58%|█████▊    | 16332/28080 [32:16:50<23:10:08,  7.10s/it]
 58%|█████▊    | 16333/28080 [32:16:57<23:15:55,  7.13s/it]
                                                           
{'loss': 0.6129, 'learning_rate': 0.00019645211010802863, 'epoch': 6.98}

 58%|█████▊    | 16333/28080 [32:16:57<23:15:55,  7.13s/it]
 58%|█████▊    | 16334/28080 [32:17:04<23:19:08,  7.15s/it]
                                                           
{'loss': 0.6035, 'learning_rate': 0.0001964239439853339, 'epoch': 6.98}

 58%|█████▊    | 16334/28080 [32:17:04<23:19:08,  7.15s/it]
 58%|█████▊    | 16335/28080 [32:17:12<23:17:21,  7.14s/it]
                                                           
{'loss': 0.6156, 'learning_rate': 0.00019639577857541327, 'epoch': 6.98}

 58%|█████▊    | 16335/28080 [32:17:12<23:17:21,  7.14s/it]
 58%|█████▊    | 16336/28080 [32:17:19<23:21:57,  7.16s/it]
                                                           
{'loss': 0.6055, 'learning_rate': 0.00019636761387864155, 'epoch': 6.98}

 58%|█████▊    | 16336/28080 [32:17:19<23:21:57,  7.16s/it]
 58%|█████▊    | 16337/28080 [32:17:26<23:23:59,  7.17s/it]
                                                           
{'loss': 0.6237, 'learning_rate': 0.00019633944989539328, 'epoch': 6.98}

 58%|█████▊    | 16337/28080 [32:17:26<23:23:59,  7.17s/it]
 58%|█████▊    | 16338/28080 [32:17:33<23:25:20,  7.18s/it]
                                                           
{'loss': 0.6219, 'learning_rate': 0.00019631128662604347, 'epoch': 6.98}

 58%|█████▊    | 16338/28080 [32:17:33<23:25:20,  7.18s/it]
 58%|█████▊    | 16339/28080 [32:17:40<23:21:20,  7.16s/it]
                                                           
{'loss': 0.6137, 'learning_rate': 0.0001962831240709664, 'epoch': 6.98}

 58%|█████▊    | 16339/28080 [32:17:40<23:21:20,  7.16s/it]
 58%|█████▊    | 16340/28080 [32:17:47<23:20:59,  7.16s/it]
                                                           
{'loss': 0.6104, 'learning_rate': 0.00019625496223053712, 'epoch': 6.98}

 58%|█████▊    | 16340/28080 [32:17:47<23:20:59,  7.16s/it]
 58%|█████▊    | 16341/28080 [32:17:55<23:18:44,  7.15s/it]
                                                           
{'loss': 0.6169, 'learning_rate': 0.00019622680110512996, 'epoch': 6.98}

 58%|█████▊    | 16341/28080 [32:17:55<23:18:44,  7.15s/it]
 58%|█████▊    | 16342/28080 [32:18:02<23:10:35,  7.11s/it]
                                                           
{'loss': 0.6038, 'learning_rate': 0.0001961986406951199, 'epoch': 6.98}

 58%|█████▊    | 16342/28080 [32:18:02<23:10:35,  7.11s/it]
 58%|█████▊    | 16343/28080 [32:18:09<23:09:50,  7.10s/it]
                                                           
{'loss': 0.6136, 'learning_rate': 0.0001961704810008813, 'epoch': 6.98}

 58%|█████▊    | 16343/28080 [32:18:09<23:09:50,  7.10s/it]
 58%|█████▊    | 16344/28080 [32:18:16<23:12:48,  7.12s/it]
                                                           
{'loss': 0.6073, 'learning_rate': 0.00019614232202278898, 'epoch': 6.98}

 58%|█████▊    | 16344/28080 [32:18:16<23:12:48,  7.12s/it]
 58%|█████▊    | 16345/28080 [32:18:23<23:16:12,  7.14s/it]
                                                           
{'loss': 0.5994, 'learning_rate': 0.00019611416376121745, 'epoch': 6.98}

 58%|█████▊    | 16345/28080 [32:18:23<23:16:12,  7.14s/it]
 58%|█████▊    | 16346/28080 [32:18:30<23:12:23,  7.12s/it]
                                                           
{'loss': 0.6202, 'learning_rate': 0.00019608600621654146, 'epoch': 6.98}

 58%|█████▊    | 16346/28080 [32:18:30<23:12:23,  7.12s/it]
 58%|█████▊    | 16347/28080 [32:18:37<23:11:42,  7.12s/it]
                                                           
{'loss': 0.6185, 'learning_rate': 0.00019605784938913552, 'epoch': 6.98}

 58%|█████▊    | 16347/28080 [32:18:37<23:11:42,  7.12s/it]
 58%|█████▊    | 16348/28080 [32:18:44<23:11:35,  7.12s/it]
                                                           
{'loss': 0.6241, 'learning_rate': 0.0001960296932793742, 'epoch': 6.98}

 58%|█████▊    | 16348/28080 [32:18:44<23:11:35,  7.12s/it]
 58%|█████▊    | 16349/28080 [32:18:51<23:11:51,  7.12s/it]
                                                           
{'loss': 0.601, 'learning_rate': 0.0001960015378876322, 'epoch': 6.98}

 58%|█████▊    | 16349/28080 [32:18:51<23:11:51,  7.12s/it]
 58%|█████▊    | 16350/28080 [32:18:58<23:05:19,  7.09s/it]
                                                           
{'loss': 0.5908, 'learning_rate': 0.00019597338321428393, 'epoch': 6.98}

 58%|█████▊    | 16350/28080 [32:18:58<23:05:19,  7.09s/it]
 58%|█████▊    | 16351/28080 [32:19:05<23:02:48,  7.07s/it]
                                                           
{'loss': 0.6072, 'learning_rate': 0.00019594522925970415, 'epoch': 6.98}

 58%|█████▊    | 16351/28080 [32:19:05<23:02:48,  7.07s/it]
 58%|█████▊    | 16352/28080 [32:19:13<23:04:14,  7.08s/it]
                                                           
{'loss': 0.5989, 'learning_rate': 0.00019591707602426727, 'epoch': 6.99}

 58%|█████▊    | 16352/28080 [32:19:13<23:04:14,  7.08s/it]
 58%|█████▊    | 16353/28080 [32:19:20<23:05:37,  7.09s/it]
                                                           
{'loss': 0.6311, 'learning_rate': 0.00019588892350834794, 'epoch': 6.99}

 58%|█████▊    | 16353/28080 [32:19:20<23:05:37,  7.09s/it]
 58%|█████▊    | 16354/28080 [32:19:27<23:09:02,  7.11s/it]
                                                           
{'loss': 0.6152, 'learning_rate': 0.00019586077171232063, 'epoch': 6.99}

 58%|█████▊    | 16354/28080 [32:19:27<23:09:02,  7.11s/it]
 58%|█████▊    | 16355/28080 [32:19:34<23:10:45,  7.12s/it]
                                                           
{'loss': 0.6085, 'learning_rate': 0.00019583262063655994, 'epoch': 6.99}

 58%|█████▊    | 16355/28080 [32:19:34<23:10:45,  7.12s/it]
 58%|█████▊    | 16356/28080 [32:19:41<23:06:57,  7.10s/it]
                                                           
{'loss': 0.611, 'learning_rate': 0.00019580447028144025, 'epoch': 6.99}

 58%|█████▊    | 16356/28080 [32:19:41<23:06:57,  7.10s/it]
 58%|█████▊    | 16357/28080 [32:19:48<23:09:53,  7.11s/it]
                                                           
{'loss': 0.6237, 'learning_rate': 0.0001957763206473363, 'epoch': 6.99}

 58%|█████▊    | 16357/28080 [32:19:48<23:09:53,  7.11s/it]
 58%|█████▊    | 16358/28080 [32:19:55<23:09:16,  7.11s/it]
                                                           
{'loss': 0.6245, 'learning_rate': 0.00019574817173462233, 'epoch': 6.99}

 58%|█████▊    | 16358/28080 [32:19:55<23:09:16,  7.11s/it]
 58%|█████▊    | 16359/28080 [32:20:02<23:09:58,  7.12s/it]
                                                           
{'loss': 0.6234, 'learning_rate': 0.00019572002354367306, 'epoch': 6.99}

 58%|█████▊    | 16359/28080 [32:20:02<23:09:58,  7.12s/it]
 58%|█████▊    | 16360/28080 [32:20:10<23:12:02,  7.13s/it]
                                                           
{'loss': 0.6068, 'learning_rate': 0.0001956918760748629, 'epoch': 6.99}

 58%|█████▊    | 16360/28080 [32:20:10<23:12:02,  7.13s/it]
 58%|█████▊    | 16361/28080 [32:20:17<23:06:11,  7.10s/it]
                                                           
{'loss': 0.6085, 'learning_rate': 0.00019566372932856626, 'epoch': 6.99}

 58%|█████▊    | 16361/28080 [32:20:17<23:06:11,  7.10s/it]
 58%|█████▊    | 16362/28080 [32:20:24<23:12:35,  7.13s/it]
                                                           
{'loss': 0.6057, 'learning_rate': 0.00019563558330515764, 'epoch': 6.99}

 58%|█████▊    | 16362/28080 [32:20:24<23:12:35,  7.13s/it]
 58%|█████▊    | 16363/28080 [32:20:31<23:15:15,  7.14s/it]
                                                           
{'loss': 0.6225, 'learning_rate': 0.00019560743800501153, 'epoch': 6.99}

 58%|█████▊    | 16363/28080 [32:20:31<23:15:15,  7.14s/it]
 58%|█████▊    | 16364/28080 [32:20:38<23:12:07,  7.13s/it]
                                                           
{'loss': 0.6051, 'learning_rate': 0.0001955792934285023, 'epoch': 6.99}

 58%|█████▊    | 16364/28080 [32:20:38<23:12:07,  7.13s/it]
 58%|█████▊    | 16365/28080 [32:20:45<23:09:58,  7.12s/it]
                                                           
{'loss': 0.6106, 'learning_rate': 0.0001955511495760045, 'epoch': 6.99}

 58%|█████▊    | 16365/28080 [32:20:45<23:09:58,  7.12s/it]
 58%|█████▊    | 16366/28080 [32:20:52<23:11:19,  7.13s/it]
                                                           
{'loss': 0.6164, 'learning_rate': 0.0001955230064478924, 'epoch': 6.99}

 58%|█████▊    | 16366/28080 [32:20:52<23:11:19,  7.13s/it]
 58%|█████▊    | 16367/28080 [32:20:59<23:13:30,  7.14s/it]
                                                           
{'loss': 0.6067, 'learning_rate': 0.00019549486404454056, 'epoch': 6.99}

 58%|█████▊    | 16367/28080 [32:20:59<23:13:30,  7.14s/it]
 58%|█████▊    | 16368/28080 [32:21:06<23:07:37,  7.11s/it]
                                                           
{'loss': 0.6247, 'learning_rate': 0.00019546672236632324, 'epoch': 6.99}

 58%|█████▊    | 16368/28080 [32:21:06<23:07:37,  7.11s/it]
 58%|█████▊    | 16369/28080 [32:21:14<23:11:52,  7.13s/it]
                                                           
{'loss': 0.613, 'learning_rate': 0.00019543858141361504, 'epoch': 6.99}

 58%|█████▊    | 16369/28080 [32:21:14<23:11:52,  7.13s/it]
 58%|█████▊    | 16370/28080 [32:21:21<23:08:45,  7.12s/it]
                                                           
{'loss': 0.6168, 'learning_rate': 0.00019541044118679012, 'epoch': 6.99}

 58%|█████▊    | 16370/28080 [32:21:21<23:08:45,  7.12s/it]
 58%|█████▊    | 16371/28080 [32:21:28<23:00:38,  7.07s/it]
                                                           
{'loss': 0.6307, 'learning_rate': 0.00019538230168622306, 'epoch': 6.99}

 58%|█████▊    | 16371/28080 [32:21:28<23:00:38,  7.07s/it]
 58%|█████▊    | 16372/28080 [32:21:35<23:04:26,  7.09s/it]
                                                           
{'loss': 0.6073, 'learning_rate': 0.00019535416291228814, 'epoch': 6.99}

 58%|█████▊    | 16372/28080 [32:21:35<23:04:26,  7.09s/it]
 58%|█████▊    | 16373/28080 [32:21:42<23:04:08,  7.09s/it]
                                                           
{'loss': 0.62, 'learning_rate': 0.00019532602486535956, 'epoch': 6.99}

 58%|█████▊    | 16373/28080 [32:21:42<23:04:08,  7.09s/it]
 58%|█████▊    | 16374/28080 [32:21:49<23:00:36,  7.08s/it]
                                                           
{'loss': 0.6249, 'learning_rate': 0.00019529788754581195, 'epoch': 6.99}

 58%|█████▊    | 16374/28080 [32:21:49<23:00:36,  7.08s/it]
 58%|█████▊    | 16375/28080 [32:21:56<22:59:49,  7.07s/it]
                                                           
{'loss': 0.5944, 'learning_rate': 0.0001952697509540194, 'epoch': 7.0}

 58%|█████▊    | 16375/28080 [32:21:56<22:59:49,  7.07s/it]
 58%|█████▊    | 16376/28080 [32:22:03<23:08:14,  7.12s/it]
                                                           
{'loss': 0.6275, 'learning_rate': 0.00019524161509035647, 'epoch': 7.0}

 58%|█████▊    | 16376/28080 [32:22:03<23:08:14,  7.12s/it]
 58%|█████▊    | 16377/28080 [32:22:10<23:09:37,  7.12s/it]
                                                           
{'loss': 0.6192, 'learning_rate': 0.0001952134799551973, 'epoch': 7.0}

 58%|█████▊    | 16377/28080 [32:22:10<23:09:37,  7.12s/it]
 58%|█████▊    | 16378/28080 [32:22:18<23:12:44,  7.14s/it]
                                                           
{'loss': 0.6015, 'learning_rate': 0.00019518534554891626, 'epoch': 7.0}

 58%|█████▊    | 16378/28080 [32:22:18<23:12:44,  7.14s/it]
 58%|█████▊    | 16379/28080 [32:22:25<23:07:43,  7.12s/it]
                                                           
{'loss': 0.6053, 'learning_rate': 0.00019515721187188763, 'epoch': 7.0}

 58%|█████▊    | 16379/28080 [32:22:25<23:07:43,  7.12s/it]
 58%|█████▊    | 16380/28080 [32:22:32<23:05:47,  7.11s/it]
                                                           
{'loss': 0.6081, 'learning_rate': 0.00019512907892448578, 'epoch': 7.0}

 58%|█████▊    | 16380/28080 [32:22:32<23:05:47,  7.11s/it]
 58%|█████▊    | 16381/28080 [32:22:39<23:08:27,  7.12s/it]
                                                           
{'loss': 0.6286, 'learning_rate': 0.00019510094670708488, 'epoch': 7.0}

 58%|█████▊    | 16381/28080 [32:22:39<23:08:27,  7.12s/it]
 58%|█████▊    | 16382/28080 [32:22:46<23:13:15,  7.15s/it]
                                                           
{'loss': 0.6144, 'learning_rate': 0.00019507281522005926, 'epoch': 7.0}

 58%|█████▊    | 16382/28080 [32:22:46<23:13:15,  7.15s/it]
 58%|█████▊    | 16383/28080 [32:22:53<23:07:51,  7.12s/it]
                                                           
{'loss': 0.6316, 'learning_rate': 0.00019504468446378316, 'epoch': 7.0}

 58%|█████▊    | 16383/28080 [32:22:53<23:07:51,  7.12s/it]
 58%|█████▊    | 16384/28080 [32:23:00<23:05:04,  7.11s/it]
                                                           
{'loss': 0.6278, 'learning_rate': 0.00019501655443863086, 'epoch': 7.0}

 58%|█████▊    | 16384/28080 [32:23:00<23:05:04,  7.11s/it]
 58%|█████▊    | 16385/28080 [32:23:08<23:16:11,  7.16s/it]
                                                           
{'loss': 0.6187, 'learning_rate': 0.00019498842514497657, 'epoch': 7.0}

 58%|█████▊    | 16385/28080 [32:23:08<23:16:11,  7.16s/it]
 58%|█████▊    | 16386/28080 [32:23:15<23:18:13,  7.17s/it]
                                                           
{'loss': 0.6083, 'learning_rate': 0.00019496029658319452, 'epoch': 7.0}

 58%|█████▊    | 16386/28080 [32:23:15<23:18:13,  7.17s/it]
 58%|█████▊    | 16387/28080 [32:23:22<23:48:34,  7.33s/it]
                                                           
{'loss': 0.633, 'learning_rate': 0.00019493216875365887, 'epoch': 7.0}

 58%|█████▊    | 16387/28080 [32:23:22<23:48:34,  7.33s/it]
 58%|█████▊    | 16388/28080 [32:23:30<23:34:58,  7.26s/it]
                                                           
{'loss': 0.6155, 'learning_rate': 0.00019490404165674408, 'epoch': 7.0}

 58%|█████▊    | 16388/28080 [32:23:30<23:34:58,  7.26s/it]
 58%|█████▊    | 16389/28080 [32:23:37<23:26:38,  7.22s/it]
                                                           
{'loss': 0.615, 'learning_rate': 0.000194875915292824, 'epoch': 7.0}

 58%|█████▊    | 16389/28080 [32:23:37<23:26:38,  7.22s/it]
 58%|█████▊    | 16390/28080 [32:23:44<23:19:13,  7.18s/it]
                                                           
{'loss': 0.5967, 'learning_rate': 0.0001948477896622731, 'epoch': 7.0}

 58%|█████▊    | 16390/28080 [32:23:44<23:19:13,  7.18s/it]
 58%|█████▊    | 16391/28080 [32:23:51<23:13:23,  7.15s/it]
                                                           
{'loss': 0.6316, 'learning_rate': 0.00019481966476546543, 'epoch': 7.0}

 58%|█████▊    | 16391/28080 [32:23:51<23:13:23,  7.15s/it]
 58%|█████▊    | 16392/28080 [32:23:58<23:12:24,  7.15s/it]
                                                           
{'loss': 0.5839, 'learning_rate': 0.0001947915406027752, 'epoch': 7.0}

 58%|█████▊    | 16392/28080 [32:23:58<23:12:24,  7.15s/it]
 58%|█████▊    | 16393/28080 [32:24:05<23:10:33,  7.14s/it]
                                                           
{'loss': 0.6026, 'learning_rate': 0.00019476341717457657, 'epoch': 7.0}

 58%|█████▊    | 16393/28080 [32:24:05<23:10:33,  7.14s/it]
 58%|█████▊    | 16394/28080 [32:24:12<23:06:14,  7.12s/it]
                                                           
{'loss': 0.5928, 'learning_rate': 0.00019473529448124372, 'epoch': 7.0}

 58%|█████▊    | 16394/28080 [32:24:12<23:06:14,  7.12s/it]
 58%|█████▊    | 16395/28080 [32:24:19<23:10:49,  7.14s/it]
                                                           
{'loss': 0.6251, 'learning_rate': 0.0001947071725231507, 'epoch': 7.0}

 58%|█████▊    | 16395/28080 [32:24:19<23:10:49,  7.14s/it]
 58%|█████▊    | 16396/28080 [32:24:26<23:08:52,  7.13s/it]
                                                           
{'loss': 0.5941, 'learning_rate': 0.00019467905130067176, 'epoch': 7.0}

 58%|█████▊    | 16396/28080 [32:24:26<23:08:52,  7.13s/it]
 58%|█████▊    | 16397/28080 [32:24:34<23:11:17,  7.15s/it]
                                                           
{'loss': 0.6059, 'learning_rate': 0.000194650930814181, 'epoch': 7.0}

 58%|█████▊    | 16397/28080 [32:24:34<23:11:17,  7.15s/it]
 58%|█████▊    | 16398/28080 [32:24:41<23:05:26,  7.12s/it]
                                                           
{'loss': 0.6035, 'learning_rate': 0.0001946228110640524, 'epoch': 7.01}

 58%|█████▊    | 16398/28080 [32:24:41<23:05:26,  7.12s/it]
 58%|█████▊    | 16399/28080 [32:24:48<22:58:05,  7.08s/it]
                                                           
{'loss': 0.6112, 'learning_rate': 0.00019459469205066027, 'epoch': 7.01}

 58%|█████▊    | 16399/28080 [32:24:48<22:58:05,  7.08s/it]
 58%|█████▊    | 16400/28080 [32:24:55<22:55:34,  7.07s/it]
                                                           
{'loss': 0.6222, 'learning_rate': 0.00019456657377437853, 'epoch': 7.01}

 58%|█████▊    | 16400/28080 [32:24:55<22:55:34,  7.07s/it]
 58%|█████▊    | 16401/28080 [32:25:02<23:00:03,  7.09s/it]
                                                           
{'loss': 0.614, 'learning_rate': 0.00019453845623558142, 'epoch': 7.01}

 58%|█████▊    | 16401/28080 [32:25:02<23:00:03,  7.09s/it]
 58%|█████▊    | 16402/28080 [32:25:09<23:03:40,  7.11s/it]
                                                           
{'loss': 0.6178, 'learning_rate': 0.00019451033943464286, 'epoch': 7.01}

 58%|█████▊    | 16402/28080 [32:25:09<23:03:40,  7.11s/it]
 58%|█████▊    | 16403/28080 [32:25:16<23:04:16,  7.11s/it]
                                                           
{'loss': 0.6054, 'learning_rate': 0.00019448222337193702, 'epoch': 7.01}

 58%|█████▊    | 16403/28080 [32:25:16<23:04:16,  7.11s/it]
 58%|█████▊    | 16404/28080 [32:25:23<23:08:38,  7.14s/it]
                                                           
{'loss': 0.5913, 'learning_rate': 0.00019445410804783784, 'epoch': 7.01}

 58%|█████▊    | 16404/28080 [32:25:23<23:08:38,  7.14s/it]
 58%|█████▊    | 16405/28080 [32:25:30<23:07:16,  7.13s/it]
                                                           
{'loss': 0.6101, 'learning_rate': 0.0001944259934627196, 'epoch': 7.01}

 58%|█████▊    | 16405/28080 [32:25:30<23:07:16,  7.13s/it]
 58%|█████▊    | 16406/28080 [32:25:38<23:04:20,  7.12s/it]
                                                           
{'loss': 0.6045, 'learning_rate': 0.00019439787961695603, 'epoch': 7.01}

 58%|█████▊    | 16406/28080 [32:25:38<23:04:20,  7.12s/it]
 58%|█████▊    | 16407/28080 [32:25:45<23:06:29,  7.13s/it]
                                                           
{'loss': 0.5831, 'learning_rate': 0.00019436976651092142, 'epoch': 7.01}

 58%|█████▊    | 16407/28080 [32:25:45<23:06:29,  7.13s/it]
 58%|█████▊    | 16408/28080 [32:25:52<23:04:30,  7.12s/it]
                                                           
{'loss': 0.6088, 'learning_rate': 0.00019434165414498962, 'epoch': 7.01}

 58%|█████▊    | 16408/28080 [32:25:52<23:04:30,  7.12s/it]
 58%|█████▊    | 16409/28080 [32:25:59<23:04:39,  7.12s/it]
                                                           
{'loss': 0.6078, 'learning_rate': 0.00019431354251953477, 'epoch': 7.01}

 58%|█████▊    | 16409/28080 [32:25:59<23:04:39,  7.12s/it]
 58%|█████▊    | 16410/28080 [32:26:06<23:04:57,  7.12s/it]
                                                           
{'loss': 0.6171, 'learning_rate': 0.00019428543163493067, 'epoch': 7.01}

 58%|█████▊    | 16410/28080 [32:26:06<23:04:57,  7.12s/it]
 58%|█████▊    | 16411/28080 [32:26:13<23:11:23,  7.15s/it]
                                                           
{'loss': 0.6027, 'learning_rate': 0.00019425732149155154, 'epoch': 7.01}

 58%|█████▊    | 16411/28080 [32:26:13<23:11:23,  7.15s/it]
 58%|█████▊    | 16412/28080 [32:26:20<23:14:32,  7.17s/it]
                                                           
{'loss': 0.6242, 'learning_rate': 0.00019422921208977115, 'epoch': 7.01}

 58%|█████▊    | 16412/28080 [32:26:20<23:14:32,  7.17s/it]
 58%|█████▊    | 16413/28080 [32:26:28<23:08:01,  7.14s/it]
                                                           
{'loss': 0.6387, 'learning_rate': 0.00019420110342996364, 'epoch': 7.01}

 58%|█████▊    | 16413/28080 [32:26:28<23:08:01,  7.14s/it]
 58%|█████▊    | 16414/28080 [32:26:35<23:00:53,  7.10s/it]
                                                           
{'loss': 0.6285, 'learning_rate': 0.0001941729955125028, 'epoch': 7.01}

 58%|█████▊    | 16414/28080 [32:26:35<23:00:53,  7.10s/it]
 58%|█████▊    | 16415/28080 [32:26:42<22:56:04,  7.08s/it]
                                                           
{'loss': 0.6433, 'learning_rate': 0.00019414488833776271, 'epoch': 7.01}

 58%|█████▊    | 16415/28080 [32:26:42<22:56:04,  7.08s/it]
 58%|█████▊    | 16416/28080 [32:26:49<23:00:11,  7.10s/it]
                                                           
{'loss': 0.6128, 'learning_rate': 0.0001941167819061172, 'epoch': 7.01}

 58%|█████▊    | 16416/28080 [32:26:49<23:00:11,  7.10s/it]
 58%|█████▊    | 16417/28080 [32:26:56<23:03:18,  7.12s/it]
                                                           
{'loss': 0.5995, 'learning_rate': 0.00019408867621794037, 'epoch': 7.01}

 58%|█████▊    | 16417/28080 [32:26:56<23:03:18,  7.12s/it]
 58%|█████▊    | 16418/28080 [32:27:03<23:01:32,  7.11s/it]
                                                           
{'loss': 0.6281, 'learning_rate': 0.0001940605712736059, 'epoch': 7.01}

 58%|█████▊    | 16418/28080 [32:27:03<23:01:32,  7.11s/it]
 58%|█████▊    | 16419/28080 [32:27:10<23:00:50,  7.10s/it]
                                                           
{'loss': 0.6203, 'learning_rate': 0.00019403246707348795, 'epoch': 7.01}

 58%|█████▊    | 16419/28080 [32:27:10<23:00:50,  7.10s/it]
 58%|█████▊    | 16420/28080 [32:27:17<23:00:26,  7.10s/it]
                                                           
{'loss': 0.62, 'learning_rate': 0.00019400436361796013, 'epoch': 7.01}

 58%|█████▊    | 16420/28080 [32:27:17<23:00:26,  7.10s/it]
 58%|█████▊    | 16421/28080 [32:27:24<22:54:51,  7.08s/it]
                                                           
{'loss': 0.6392, 'learning_rate': 0.00019397626090739663, 'epoch': 7.01}

 58%|█████▊    | 16421/28080 [32:27:24<22:54:51,  7.08s/it]
 58%|█████▊    | 16422/28080 [32:27:31<22:55:02,  7.08s/it]
                                                           
{'loss': 0.6358, 'learning_rate': 0.00019394815894217119, 'epoch': 7.02}

 58%|█████▊    | 16422/28080 [32:27:31<22:55:02,  7.08s/it]
 58%|█████▊    | 16423/28080 [32:27:38<23:01:53,  7.11s/it]
                                                           
{'loss': 0.6014, 'learning_rate': 0.00019392005772265753, 'epoch': 7.02}

 58%|█████▊    | 16423/28080 [32:27:38<23:01:53,  7.11s/it]
 58%|█████▊    | 16424/28080 [32:27:46<23:04:11,  7.13s/it]
                                                           
{'loss': 0.6326, 'learning_rate': 0.00019389195724922972, 'epoch': 7.02}

 58%|█████▊    | 16424/28080 [32:27:46<23:04:11,  7.13s/it]
 58%|█████▊    | 16425/28080 [32:27:53<22:55:09,  7.08s/it]
                                                           
{'loss': 0.6226, 'learning_rate': 0.00019386385752226152, 'epoch': 7.02}

 58%|█████▊    | 16425/28080 [32:27:53<22:55:09,  7.08s/it]
 58%|█████▊    | 16426/28080 [32:28:00<22:52:20,  7.07s/it]
                                                           
{'loss': 0.6043, 'learning_rate': 0.00019383575854212682, 'epoch': 7.02}

 58%|█████▊    | 16426/28080 [32:28:00<22:52:20,  7.07s/it]
 59%|█████▊    | 16427/28080 [32:28:07<22:56:42,  7.09s/it]
                                                           
{'loss': 0.6275, 'learning_rate': 0.00019380766030919938, 'epoch': 7.02}

 59%|█████▊    | 16427/28080 [32:28:07<22:56:42,  7.09s/it]
 59%|█████▊    | 16428/28080 [32:28:14<22:59:51,  7.11s/it]
                                                           
{'loss': 0.6028, 'learning_rate': 0.00019377956282385308, 'epoch': 7.02}

 59%|█████▊    | 16428/28080 [32:28:14<22:59:51,  7.11s/it]
 59%|█████▊    | 16429/28080 [32:28:21<23:02:35,  7.12s/it]
                                                           
{'loss': 0.6056, 'learning_rate': 0.00019375146608646167, 'epoch': 7.02}

 59%|█████▊    | 16429/28080 [32:28:21<23:02:35,  7.12s/it]
 59%|█████▊    | 16430/28080 [32:28:28<23:01:34,  7.12s/it]
                                                           
{'loss': 0.6235, 'learning_rate': 0.000193723370097399, 'epoch': 7.02}

 59%|█████▊    | 16430/28080 [32:28:28<23:01:34,  7.12s/it]
 59%|█████▊    | 16431/28080 [32:28:35<23:08:01,  7.15s/it]
                                                           
{'loss': 0.5974, 'learning_rate': 0.0001936952748570388, 'epoch': 7.02}

 59%|█████▊    | 16431/28080 [32:28:35<23:08:01,  7.15s/it]
 59%|█████▊    | 16432/28080 [32:28:43<23:10:22,  7.16s/it]
                                                           
{'loss': 0.6079, 'learning_rate': 0.0001936671803657549, 'epoch': 7.02}

 59%|█████▊    | 16432/28080 [32:28:43<23:10:22,  7.16s/it]
 59%|█████▊    | 16433/28080 [32:28:50<23:05:06,  7.14s/it]
                                                           
{'loss': 0.6304, 'learning_rate': 0.00019363908662392102, 'epoch': 7.02}

 59%|█████▊    | 16433/28080 [32:28:50<23:05:06,  7.14s/it]
 59%|█████▊    | 16434/28080 [32:28:57<23:03:14,  7.13s/it]
                                                           
{'loss': 0.6173, 'learning_rate': 0.000193610993631911, 'epoch': 7.02}

 59%|█████▊    | 16434/28080 [32:28:57<23:03:14,  7.13s/it]
 59%|█████▊    | 16435/28080 [32:29:04<23:03:05,  7.13s/it]
                                                           
{'loss': 0.604, 'learning_rate': 0.00019358290139009844, 'epoch': 7.02}

 59%|█████▊    | 16435/28080 [32:29:04<23:03:05,  7.13s/it]
 59%|█████▊    | 16436/28080 [32:29:11<23:06:47,  7.15s/it]
                                                           
{'loss': 0.6394, 'learning_rate': 0.0001935548098988573, 'epoch': 7.02}

 59%|█████▊    | 16436/28080 [32:29:11<23:06:47,  7.15s/it]
 59%|█████▊    | 16437/28080 [32:29:18<23:03:11,  7.13s/it]
                                                           
{'loss': 0.6081, 'learning_rate': 0.00019352671915856106, 'epoch': 7.02}

 59%|█████▊    | 16437/28080 [32:29:18<23:03:11,  7.13s/it]
 59%|█████▊    | 16438/28080 [32:29:25<22:58:50,  7.11s/it]
                                                           
{'loss': 0.6273, 'learning_rate': 0.00019349862916958366, 'epoch': 7.02}

 59%|█████▊    | 16438/28080 [32:29:25<22:58:50,  7.11s/it]
 59%|█████▊    | 16439/28080 [32:29:32<23:02:22,  7.13s/it]
                                                           
{'loss': 0.5887, 'learning_rate': 0.0001934705399322987, 'epoch': 7.02}

 59%|█████▊    | 16439/28080 [32:29:32<23:02:22,  7.13s/it]
 59%|█████▊    | 16440/28080 [32:29:39<23:03:04,  7.13s/it]
                                                           
{'loss': 0.5818, 'learning_rate': 0.00019344245144707986, 'epoch': 7.02}

 59%|█████▊    | 16440/28080 [32:29:40<23:03:04,  7.13s/it]
 59%|█████▊    | 16441/28080 [32:29:47<23:06:49,  7.15s/it]
                                                           
{'loss': 0.6189, 'learning_rate': 0.00019341436371430085, 'epoch': 7.02}

 59%|█████▊    | 16441/28080 [32:29:47<23:06:49,  7.15s/it]
 59%|█████▊    | 16442/28080 [32:29:54<23:00:56,  7.12s/it]
                                                           
{'loss': 0.6184, 'learning_rate': 0.0001933862767343354, 'epoch': 7.02}

 59%|█████▊    | 16442/28080 [32:29:54<23:00:56,  7.12s/it]
 59%|█████▊    | 16443/28080 [32:30:01<22:56:52,  7.10s/it]
                                                           
{'loss': 0.6284, 'learning_rate': 0.00019335819050755708, 'epoch': 7.02}

 59%|█████▊    | 16443/28080 [32:30:01<22:56:52,  7.10s/it]
 59%|█████▊    | 16444/28080 [32:30:08<22:59:35,  7.11s/it]
                                                           
{'loss': 0.5901, 'learning_rate': 0.00019333010503433965, 'epoch': 7.02}

 59%|█████▊    | 16444/28080 [32:30:08<22:59:35,  7.11s/it]
 59%|█████▊    | 16445/28080 [32:30:15<23:01:02,  7.12s/it]
                                                           
{'loss': 0.5989, 'learning_rate': 0.00019330202031505664, 'epoch': 7.03}

 59%|█████▊    | 16445/28080 [32:30:15<23:01:02,  7.12s/it]
 59%|█████▊    | 16446/28080 [32:30:22<22:55:17,  7.09s/it]
                                                           
{'loss': 0.6168, 'learning_rate': 0.00019327393635008183, 'epoch': 7.03}

 59%|█████▊    | 16446/28080 [32:30:22<22:55:17,  7.09s/it]
 59%|█████▊    | 16447/28080 [32:30:29<22:51:21,  7.07s/it]
                                                           
{'loss': 0.6102, 'learning_rate': 0.00019324585313978875, 'epoch': 7.03}

 59%|█████▊    | 16447/28080 [32:30:29<22:51:21,  7.07s/it]
 59%|█████▊    | 16448/28080 [32:30:36<22:47:52,  7.06s/it]
                                                           
{'loss': 0.6134, 'learning_rate': 0.00019321777068455104, 'epoch': 7.03}

 59%|█████▊    | 16448/28080 [32:30:36<22:47:52,  7.06s/it]
 59%|█████▊    | 16449/28080 [32:30:43<22:49:07,  7.06s/it]
                                                           
{'loss': 0.6045, 'learning_rate': 0.00019318968898474236, 'epoch': 7.03}

 59%|█████▊    | 16449/28080 [32:30:43<22:49:07,  7.06s/it]
 59%|█████▊    | 16450/28080 [32:30:50<22:50:00,  7.07s/it]
                                                           
{'loss': 0.6184, 'learning_rate': 0.00019316160804073619, 'epoch': 7.03}

 59%|█████▊    | 16450/28080 [32:30:50<22:50:00,  7.07s/it]
 59%|█████▊    | 16451/28080 [32:30:57<22:48:44,  7.06s/it]
                                                           
{'loss': 0.6183, 'learning_rate': 0.00019313352785290622, 'epoch': 7.03}

 59%|█████▊    | 16451/28080 [32:30:57<22:48:44,  7.06s/it]
 59%|█████▊    | 16452/28080 [32:31:05<22:53:46,  7.09s/it]
                                                           
{'loss': 0.6231, 'learning_rate': 0.00019310544842162592, 'epoch': 7.03}

 59%|█████▊    | 16452/28080 [32:31:05<22:53:46,  7.09s/it]
 59%|█████▊    | 16453/28080 [32:31:12<22:57:31,  7.11s/it]
                                                           
{'loss': 0.6038, 'learning_rate': 0.00019307736974726907, 'epoch': 7.03}

 59%|█████▊    | 16453/28080 [32:31:12<22:57:31,  7.11s/it]
 59%|█████▊    | 16454/28080 [32:31:19<22:53:10,  7.09s/it]
                                                           
{'loss': 0.5872, 'learning_rate': 0.00019304929183020894, 'epoch': 7.03}

 59%|█████▊    | 16454/28080 [32:31:19<22:53:10,  7.09s/it]
 59%|█████▊    | 16455/28080 [32:31:26<23:01:41,  7.13s/it]
                                                           
{'loss': 0.6303, 'learning_rate': 0.00019302121467081935, 'epoch': 7.03}

 59%|█████▊    | 16455/28080 [32:31:26<23:01:41,  7.13s/it]
 59%|█████▊    | 16456/28080 [32:31:33<22:51:59,  7.08s/it]
                                                           
{'loss': 0.6101, 'learning_rate': 0.00019299313826947362, 'epoch': 7.03}

 59%|█████▊    | 16456/28080 [32:31:33<22:51:59,  7.08s/it]
 59%|█████▊    | 16457/28080 [32:31:40<22:53:41,  7.09s/it]
                                                           
{'loss': 0.6204, 'learning_rate': 0.0001929650626265455, 'epoch': 7.03}

 59%|█████▊    | 16457/28080 [32:31:40<22:53:41,  7.09s/it]
 59%|█████▊    | 16458/28080 [32:31:47<23:00:49,  7.13s/it]
                                                           
{'loss': 0.6157, 'learning_rate': 0.00019293698774240826, 'epoch': 7.03}

 59%|█████▊    | 16458/28080 [32:31:47<23:00:49,  7.13s/it]
 59%|█████▊    | 16459/28080 [32:31:54<23:00:07,  7.13s/it]
                                                           
{'loss': 0.6208, 'learning_rate': 0.00019290891361743563, 'epoch': 7.03}

 59%|█████▊    | 16459/28080 [32:31:54<23:00:07,  7.13s/it]
 59%|█████▊    | 16460/28080 [32:32:02<23:03:26,  7.14s/it]
                                                           
{'loss': 0.628, 'learning_rate': 0.0001928808402520009, 'epoch': 7.03}

 59%|█████▊    | 16460/28080 [32:32:02<23:03:26,  7.14s/it]
 59%|█████▊    | 16461/28080 [32:32:09<23:06:34,  7.16s/it]
                                                           
{'loss': 0.5909, 'learning_rate': 0.00019285276764647777, 'epoch': 7.03}

 59%|█████▊    | 16461/28080 [32:32:09<23:06:34,  7.16s/it]
 59%|█████▊    | 16462/28080 [32:32:16<23:04:55,  7.15s/it]
                                                           
{'loss': 0.6074, 'learning_rate': 0.00019282469580123954, 'epoch': 7.03}

 59%|█████▊    | 16462/28080 [32:32:16<23:04:55,  7.15s/it]
 59%|█████▊    | 16463/28080 [32:32:23<22:55:32,  7.10s/it]
                                                           
{'loss': 0.6359, 'learning_rate': 0.00019279662471665982, 'epoch': 7.03}

 59%|█████▊    | 16463/28080 [32:32:23<22:55:32,  7.10s/it]
 59%|█████▊    | 16464/28080 [32:32:30<22:55:33,  7.11s/it]
                                                           
{'loss': 0.5973, 'learning_rate': 0.0001927685543931119, 'epoch': 7.03}

 59%|█████▊    | 16464/28080 [32:32:30<22:55:33,  7.11s/it]
 59%|█████▊    | 16465/28080 [32:32:37<22:50:00,  7.08s/it]
                                                           
{'loss': 0.6207, 'learning_rate': 0.0001927404848309694, 'epoch': 7.03}

 59%|█████▊    | 16465/28080 [32:32:37<22:50:00,  7.08s/it]
 59%|█████▊    | 16466/28080 [32:32:44<22:53:49,  7.10s/it]
                                                           
{'loss': 0.6117, 'learning_rate': 0.00019271241603060558, 'epoch': 7.03}

 59%|█████▊    | 16466/28080 [32:32:44<22:53:49,  7.10s/it]
 59%|█████▊    | 16467/28080 [32:32:51<22:59:00,  7.12s/it]
                                                           
{'loss': 0.6279, 'learning_rate': 0.0001926843479923941, 'epoch': 7.03}

 59%|█████▊    | 16467/28080 [32:32:51<22:59:00,  7.12s/it]
 59%|█████▊    | 16468/28080 [32:32:59<23:05:33,  7.16s/it]
                                                           
{'loss': 0.6206, 'learning_rate': 0.0001926562807167081, 'epoch': 7.03}

 59%|█████▊    | 16468/28080 [32:32:59<23:05:33,  7.16s/it]
 59%|█████▊    | 16469/28080 [32:33:06<22:59:17,  7.13s/it]
                                                           
{'loss': 0.6381, 'learning_rate': 0.00019262821420392123, 'epoch': 7.04}

 59%|█████▊    | 16469/28080 [32:33:06<22:59:17,  7.13s/it]
 59%|█████▊    | 16470/28080 [32:33:13<22:58:01,  7.12s/it]
                                                           
{'loss': 0.6248, 'learning_rate': 0.00019260014845440675, 'epoch': 7.04}

 59%|█████▊    | 16470/28080 [32:33:13<22:58:01,  7.12s/it]
 59%|█████▊    | 16471/28080 [32:33:20<23:03:10,  7.15s/it]
                                                           
{'loss': 0.6237, 'learning_rate': 0.0001925720834685381, 'epoch': 7.04}

 59%|█████▊    | 16471/28080 [32:33:20<23:03:10,  7.15s/it]
 59%|█████▊    | 16472/28080 [32:33:27<22:50:50,  7.09s/it]
                                                           
{'loss': 0.6284, 'learning_rate': 0.0001925440192466887, 'epoch': 7.04}

 59%|█████▊    | 16472/28080 [32:33:27<22:50:50,  7.09s/it]
 59%|█████▊    | 16473/28080 [32:33:34<22:49:26,  7.08s/it]
                                                           
{'loss': 0.6448, 'learning_rate': 0.00019251595578923168, 'epoch': 7.04}

 59%|█████▊    | 16473/28080 [32:33:34<22:49:26,  7.08s/it]
 59%|█████▊    | 16474/28080 [32:33:41<22:48:39,  7.08s/it]
                                                           
{'loss': 0.6298, 'learning_rate': 0.00019248789309654068, 'epoch': 7.04}

 59%|█████▊    | 16474/28080 [32:33:41<22:48:39,  7.08s/it]
 59%|█████▊    | 16475/28080 [32:33:48<22:51:58,  7.09s/it]
                                                           
{'loss': 0.6317, 'learning_rate': 0.00019245983116898885, 'epoch': 7.04}

 59%|█████▊    | 16475/28080 [32:33:48<22:51:58,  7.09s/it]
 59%|█████▊    | 16476/28080 [32:33:55<22:56:36,  7.12s/it]
                                                           
{'loss': 0.6174, 'learning_rate': 0.0001924317700069497, 'epoch': 7.04}

 59%|█████▊    | 16476/28080 [32:33:55<22:56:36,  7.12s/it]
 59%|█████▊    | 16477/28080 [32:34:02<22:51:11,  7.09s/it]
                                                           
{'loss': 0.6149, 'learning_rate': 0.0001924037096107964, 'epoch': 7.04}

 59%|█████▊    | 16477/28080 [32:34:02<22:51:11,  7.09s/it]
 59%|█████▊    | 16478/28080 [32:34:10<22:59:52,  7.14s/it]
                                                           
{'loss': 0.6029, 'learning_rate': 0.00019237564998090238, 'epoch': 7.04}

 59%|█████▊    | 16478/28080 [32:34:10<22:59:52,  7.14s/it]
 59%|█████▊    | 16479/28080 [32:34:17<23:00:56,  7.14s/it]
                                                           
{'loss': 0.6241, 'learning_rate': 0.0001923475911176408, 'epoch': 7.04}

 59%|█████▊    | 16479/28080 [32:34:17<23:00:56,  7.14s/it]
 59%|█████▊    | 16480/28080 [32:34:24<22:58:38,  7.13s/it]
                                                           
{'loss': 0.5999, 'learning_rate': 0.00019231953302138513, 'epoch': 7.04}

 59%|█████▊    | 16480/28080 [32:34:24<22:58:38,  7.13s/it]
 59%|█████▊    | 16481/28080 [32:34:31<22:52:32,  7.10s/it]
                                                           
{'loss': 0.6149, 'learning_rate': 0.00019229147569250853, 'epoch': 7.04}

 59%|█████▊    | 16481/28080 [32:34:31<22:52:32,  7.10s/it]
 59%|█████▊    | 16482/28080 [32:34:38<22:50:10,  7.09s/it]
                                                           
{'loss': 0.5956, 'learning_rate': 0.0001922634191313843, 'epoch': 7.04}

 59%|█████▊    | 16482/28080 [32:34:38<22:50:10,  7.09s/it]
 59%|█████▊    | 16483/28080 [32:34:45<22:52:51,  7.10s/it]
                                                           
{'loss': 0.6341, 'learning_rate': 0.00019223536333838566, 'epoch': 7.04}

 59%|█████▊    | 16483/28080 [32:34:45<22:52:51,  7.10s/it]
 59%|█████▊    | 16484/28080 [32:34:52<22:58:22,  7.13s/it]
                                                           
{'loss': 0.5881, 'learning_rate': 0.00019220730831388607, 'epoch': 7.04}

 59%|█████▊    | 16484/28080 [32:34:52<22:58:22,  7.13s/it]
 59%|█████▊    | 16485/28080 [32:34:59<22:58:52,  7.14s/it]
                                                           
{'loss': 0.5985, 'learning_rate': 0.00019217925405825848, 'epoch': 7.04}

 59%|█████▊    | 16485/28080 [32:34:59<22:58:52,  7.14s/it]
 59%|█████▊    | 16486/28080 [32:35:07<22:59:06,  7.14s/it]
                                                           
{'loss': 0.6056, 'learning_rate': 0.00019215120057187635, 'epoch': 7.04}

 59%|█████▊    | 16486/28080 [32:35:07<22:59:06,  7.14s/it]
 59%|█████▊    | 16487/28080 [32:35:14<22:50:27,  7.09s/it]
                                                           
{'loss': 0.6191, 'learning_rate': 0.00019212314785511275, 'epoch': 7.04}

 59%|█████▊    | 16487/28080 [32:35:14<22:50:27,  7.09s/it]
 59%|█████▊    | 16488/28080 [32:35:21<22:54:52,  7.12s/it]
                                                           
{'loss': 0.5935, 'learning_rate': 0.000192095095908341, 'epoch': 7.04}

 59%|█████▊    | 16488/28080 [32:35:21<22:54:52,  7.12s/it]
 59%|█████▊    | 16489/28080 [32:35:28<22:53:09,  7.11s/it]
                                                           
{'loss': 0.6346, 'learning_rate': 0.00019206704473193425, 'epoch': 7.04}

 59%|█████▊    | 16489/28080 [32:35:28<22:53:09,  7.11s/it]
 59%|█████▊    | 16490/28080 [32:35:35<22:49:02,  7.09s/it]
                                                           
{'loss': 0.6193, 'learning_rate': 0.00019203899432626575, 'epoch': 7.04}

 59%|█████▊    | 16490/28080 [32:35:35<22:49:02,  7.09s/it]
 59%|█████▊    | 16491/28080 [32:35:42<22:46:10,  7.07s/it]
                                                           
{'loss': 0.6144, 'learning_rate': 0.00019201094469170857, 'epoch': 7.04}

 59%|█████▊    | 16491/28080 [32:35:42<22:46:10,  7.07s/it]
 59%|█████▊    | 16492/28080 [32:35:49<22:50:17,  7.10s/it]
                                                           
{'loss': 0.6099, 'learning_rate': 0.000191982895828636, 'epoch': 7.05}

 59%|█████▊    | 16492/28080 [32:35:49<22:50:17,  7.10s/it]
 59%|█████▊    | 16493/28080 [32:35:56<22:54:13,  7.12s/it]
                                                           
{'loss': 0.5881, 'learning_rate': 0.0001919548477374211, 'epoch': 7.05}

 59%|█████▊    | 16493/28080 [32:35:56<22:54:13,  7.12s/it]
 59%|█████▊    | 16494/28080 [32:36:03<22:49:17,  7.09s/it]
                                                           
{'loss': 0.6093, 'learning_rate': 0.00019192680041843713, 'epoch': 7.05}

 59%|█████▊    | 16494/28080 [32:36:03<22:49:17,  7.09s/it]
 59%|█████▊    | 16495/28080 [32:36:10<22:48:51,  7.09s/it]
                                                           
{'loss': 0.6315, 'learning_rate': 0.0001918987538720571, 'epoch': 7.05}

 59%|█████▊    | 16495/28080 [32:36:10<22:48:51,  7.09s/it]
 59%|█████▊    | 16496/28080 [32:36:17<22:44:18,  7.07s/it]
                                                           
{'loss': 0.6228, 'learning_rate': 0.00019187070809865427, 'epoch': 7.05}

 59%|█████▊    | 16496/28080 [32:36:17<22:44:18,  7.07s/it]
 59%|█████▉    | 16497/28080 [32:36:24<22:44:11,  7.07s/it]
                                                           
{'loss': 0.6061, 'learning_rate': 0.0001918426630986017, 'epoch': 7.05}

 59%|█████▉    | 16497/28080 [32:36:24<22:44:11,  7.07s/it]
 59%|█████▉    | 16498/28080 [32:36:31<22:40:37,  7.05s/it]
                                                           
{'loss': 0.644, 'learning_rate': 0.00019181461887227247, 'epoch': 7.05}

 59%|█████▉    | 16498/28080 [32:36:31<22:40:37,  7.05s/it]
 59%|█████▉    | 16499/28080 [32:36:39<22:48:07,  7.09s/it]
                                                           
{'loss': 0.6282, 'learning_rate': 0.00019178657542003974, 'epoch': 7.05}

 59%|█████▉    | 16499/28080 [32:36:39<22:48:07,  7.09s/it]
 59%|█████▉    | 16500/28080 [32:36:46<22:51:59,  7.11s/it]
                                                           
{'loss': 0.6159, 'learning_rate': 0.00019175853274227644, 'epoch': 7.05}

 59%|█████▉    | 16500/28080 [32:36:46<22:51:59,  7.11s/it]
 59%|█████▉    | 16501/28080 [32:36:53<22:58:40,  7.14s/it]
                                                           
{'loss': 0.6115, 'learning_rate': 0.00019173049083935599, 'epoch': 7.05}

 59%|█████▉    | 16501/28080 [32:36:53<22:58:40,  7.14s/it]
 59%|█████▉    | 16502/28080 [32:37:00<22:52:15,  7.11s/it]
                                                           
{'loss': 0.6222, 'learning_rate': 0.00019170244971165103, 'epoch': 7.05}

 59%|█████▉    | 16502/28080 [32:37:00<22:52:15,  7.11s/it]
 59%|█████▉    | 16503/28080 [32:37:07<22:56:46,  7.14s/it]
                                                           
{'loss': 0.6026, 'learning_rate': 0.00019167440935953503, 'epoch': 7.05}

 59%|█████▉    | 16503/28080 [32:37:07<22:56:46,  7.14s/it]
 59%|█████▉    | 16504/28080 [32:37:14<22:57:49,  7.14s/it]
                                                           
{'loss': 0.6267, 'learning_rate': 0.0001916463697833807, 'epoch': 7.05}

 59%|█████▉    | 16504/28080 [32:37:14<22:57:49,  7.14s/it]
 59%|█████▉    | 16505/28080 [32:37:22<23:00:18,  7.15s/it]
                                                           
{'loss': 0.613, 'learning_rate': 0.00019161833098356126, 'epoch': 7.05}

 59%|█████▉    | 16505/28080 [32:37:22<23:00:18,  7.15s/it]
 59%|█████▉    | 16506/28080 [32:37:29<22:55:07,  7.13s/it]
                                                           
{'loss': 0.612, 'learning_rate': 0.00019159029296044968, 'epoch': 7.05}

 59%|█████▉    | 16506/28080 [32:37:29<22:55:07,  7.13s/it]
 59%|█████▉    | 16507/28080 [32:37:36<22:56:52,  7.14s/it]
                                                           
{'loss': 0.5977, 'learning_rate': 0.00019156225571441906, 'epoch': 7.05}

 59%|█████▉    | 16507/28080 [32:37:36<22:56:52,  7.14s/it]
 59%|█████▉    | 16508/28080 [32:37:43<22:55:41,  7.13s/it]
                                                           
{'loss': 0.6326, 'learning_rate': 0.0001915342192458423, 'epoch': 7.05}

 59%|█████▉    | 16508/28080 [32:37:43<22:55:41,  7.13s/it]
 59%|█████▉    | 16509/28080 [32:37:50<22:56:53,  7.14s/it]
                                                           
{'loss': 0.5978, 'learning_rate': 0.00019150618355509246, 'epoch': 7.05}

 59%|█████▉    | 16509/28080 [32:37:50<22:56:53,  7.14s/it]
 59%|█████▉    | 16510/28080 [32:37:57<22:53:35,  7.12s/it]
                                                           
{'loss': 0.6134, 'learning_rate': 0.00019147814864254245, 'epoch': 7.05}

 59%|█████▉    | 16510/28080 [32:37:57<22:53:35,  7.12s/it]
 59%|█████▉    | 16511/28080 [32:38:04<22:52:13,  7.12s/it]
                                                           
{'loss': 0.598, 'learning_rate': 0.00019145011450856535, 'epoch': 7.05}

 59%|█████▉    | 16511/28080 [32:38:04<22:52:13,  7.12s/it]
 59%|█████▉    | 16512/28080 [32:38:11<22:51:18,  7.11s/it]
                                                           
{'loss': 0.6157, 'learning_rate': 0.00019142208115353405, 'epoch': 7.05}

 59%|█████▉    | 16512/28080 [32:38:11<22:51:18,  7.11s/it]
 59%|█████▉    | 16513/28080 [32:38:18<22:53:38,  7.13s/it]
                                                           
{'loss': 0.6171, 'learning_rate': 0.00019139404857782157, 'epoch': 7.05}

 59%|█████▉    | 16513/28080 [32:38:18<22:53:38,  7.13s/it]
 59%|█████▉    | 16514/28080 [32:38:26<22:58:13,  7.15s/it]
                                                           
{'loss': 0.6039, 'learning_rate': 0.0001913660167818007, 'epoch': 7.05}

 59%|█████▉    | 16514/28080 [32:38:26<22:58:13,  7.15s/it]
 59%|█████▉    | 16515/28080 [32:38:33<22:58:21,  7.15s/it]
                                                           
{'loss': 0.6036, 'learning_rate': 0.00019133798576584463, 'epoch': 7.06}

 59%|█████▉    | 16515/28080 [32:38:33<22:58:21,  7.15s/it]
 59%|█████▉    | 16516/28080 [32:38:40<22:57:05,  7.15s/it]
                                                           
{'loss': 0.6126, 'learning_rate': 0.000191309955530326, 'epoch': 7.06}

 59%|█████▉    | 16516/28080 [32:38:40<22:57:05,  7.15s/it]
 59%|█████▉    | 16517/28080 [32:38:47<22:51:38,  7.12s/it]
                                                           
{'loss': 0.6109, 'learning_rate': 0.00019128192607561798, 'epoch': 7.06}

 59%|█████▉    | 16517/28080 [32:38:47<22:51:38,  7.12s/it]
 59%|█████▉    | 16518/28080 [32:38:54<22:56:14,  7.14s/it]
                                                           
{'loss': 0.6101, 'learning_rate': 0.0001912538974020933, 'epoch': 7.06}

 59%|█████▉    | 16518/28080 [32:38:54<22:56:14,  7.14s/it]
 59%|█████▉    | 16519/28080 [32:39:01<23:00:04,  7.16s/it]
                                                           
{'loss': 0.6296, 'learning_rate': 0.00019122586951012495, 'epoch': 7.06}

 59%|█████▉    | 16519/28080 [32:39:01<23:00:04,  7.16s/it]
 59%|█████▉    | 16520/28080 [32:39:09<23:00:25,  7.16s/it]
                                                           
{'loss': 0.6218, 'learning_rate': 0.00019119784240008572, 'epoch': 7.06}

 59%|█████▉    | 16520/28080 [32:39:09<23:00:25,  7.16s/it]
 59%|█████▉    | 16521/28080 [32:39:16<23:04:44,  7.19s/it]
                                                           
{'loss': 0.5948, 'learning_rate': 0.0001911698160723486, 'epoch': 7.06}

 59%|█████▉    | 16521/28080 [32:39:16<23:04:44,  7.19s/it]
 59%|█████▉    | 16522/28080 [32:39:23<23:01:55,  7.17s/it]
                                                           
{'loss': 0.6346, 'learning_rate': 0.00019114179052728635, 'epoch': 7.06}

 59%|█████▉    | 16522/28080 [32:39:23<23:01:55,  7.17s/it]
 59%|█████▉    | 16523/28080 [32:39:30<23:05:02,  7.19s/it]
                                                           
{'loss': 0.6176, 'learning_rate': 0.00019111376576527183, 'epoch': 7.06}

 59%|█████▉    | 16523/28080 [32:39:30<23:05:02,  7.19s/it]
 59%|█████▉    | 16524/28080 [32:39:37<23:02:05,  7.18s/it]
                                                           
{'loss': 0.6149, 'learning_rate': 0.00019108574178667797, 'epoch': 7.06}

 59%|█████▉    | 16524/28080 [32:39:37<23:02:05,  7.18s/it]
 59%|█████▉    | 16525/28080 [32:39:44<22:55:48,  7.14s/it]
                                                           
{'loss': 0.6236, 'learning_rate': 0.00019105771859187747, 'epoch': 7.06}

 59%|█████▉    | 16525/28080 [32:39:44<22:55:48,  7.14s/it]
 59%|█████▉    | 16526/28080 [32:39:51<22:48:03,  7.10s/it]
                                                           
{'loss': 0.6394, 'learning_rate': 0.0001910296961812433, 'epoch': 7.06}

 59%|█████▉    | 16526/28080 [32:39:51<22:48:03,  7.10s/it]
 59%|█████▉    | 16527/28080 [32:39:59<22:46:56,  7.10s/it]
                                                           
{'loss': 0.6113, 'learning_rate': 0.00019100167455514812, 'epoch': 7.06}

 59%|█████▉    | 16527/28080 [32:39:59<22:46:56,  7.10s/it]
 59%|█████▉    | 16528/28080 [32:40:06<22:57:44,  7.16s/it]
                                                           
{'loss': 0.6071, 'learning_rate': 0.00019097365371396484, 'epoch': 7.06}

 59%|█████▉    | 16528/28080 [32:40:06<22:57:44,  7.16s/it]
 59%|█████▉    | 16529/28080 [32:40:13<22:53:25,  7.13s/it]
                                                           
{'loss': 0.6237, 'learning_rate': 0.00019094563365806613, 'epoch': 7.06}

 59%|█████▉    | 16529/28080 [32:40:13<22:53:25,  7.13s/it]
 59%|█████▉    | 16530/28080 [32:40:20<22:50:12,  7.12s/it]
                                                           
{'loss': 0.615, 'learning_rate': 0.0001909176143878249, 'epoch': 7.06}

 59%|█████▉    | 16530/28080 [32:40:20<22:50:12,  7.12s/it]
 59%|█████▉    | 16531/28080 [32:40:27<22:50:38,  7.12s/it]
                                                           
{'loss': 0.6079, 'learning_rate': 0.00019088959590361377, 'epoch': 7.06}

 59%|█████▉    | 16531/28080 [32:40:27<22:50:38,  7.12s/it]
 59%|█████▉    | 16532/28080 [32:40:34<22:48:10,  7.11s/it]
                                                           
{'loss': 0.6206, 'learning_rate': 0.00019086157820580573, 'epoch': 7.06}

 59%|█████▉    | 16532/28080 [32:40:34<22:48:10,  7.11s/it]
 59%|█████▉    | 16533/28080 [32:40:41<22:48:38,  7.11s/it]
                                                           
{'loss': 0.6245, 'learning_rate': 0.00019083356129477325, 'epoch': 7.06}

 59%|█████▉    | 16533/28080 [32:40:41<22:48:38,  7.11s/it]
 59%|█████▉    | 16534/28080 [32:40:49<22:54:38,  7.14s/it]
                                                           
{'loss': 0.6311, 'learning_rate': 0.00019080554517088934, 'epoch': 7.06}

 59%|█████▉    | 16534/28080 [32:40:49<22:54:38,  7.14s/it]
 59%|█████▉    | 16535/28080 [32:40:56<22:55:47,  7.15s/it]
                                                           
{'loss': 0.6125, 'learning_rate': 0.00019077752983452642, 'epoch': 7.06}

 59%|█████▉    | 16535/28080 [32:40:56<22:55:47,  7.15s/it]
 59%|█████▉    | 16536/28080 [32:41:03<22:52:41,  7.13s/it]
                                                           
{'loss': 0.5926, 'learning_rate': 0.0001907495152860575, 'epoch': 7.06}

 59%|█████▉    | 16536/28080 [32:41:03<22:52:41,  7.13s/it]
 59%|█████▉    | 16537/28080 [32:41:10<22:58:25,  7.17s/it]
                                                           
{'loss': 0.5948, 'learning_rate': 0.00019072150152585509, 'epoch': 7.06}

 59%|█████▉    | 16537/28080 [32:41:10<22:58:25,  7.17s/it]
 59%|█████▉    | 16538/28080 [32:41:17<22:48:42,  7.12s/it]
                                                           
{'loss': 0.6154, 'learning_rate': 0.00019069348855429196, 'epoch': 7.06}

 59%|█████▉    | 16538/28080 [32:41:17<22:48:42,  7.12s/it]
 59%|█████▉    | 16539/28080 [32:41:24<22:51:17,  7.13s/it]
                                                           
{'loss': 0.613, 'learning_rate': 0.00019066547637174077, 'epoch': 7.07}

 59%|█████▉    | 16539/28080 [32:41:24<22:51:17,  7.13s/it]
 59%|█████▉    | 16540/28080 [32:41:31<22:50:02,  7.12s/it]
                                                           
{'loss': 0.6063, 'learning_rate': 0.00019063746497857426, 'epoch': 7.07}

 59%|█████▉    | 16540/28080 [32:41:31<22:50:02,  7.12s/it]
 59%|█████▉    | 16541/28080 [32:41:38<22:52:16,  7.14s/it]
                                                           
{'loss': 0.597, 'learning_rate': 0.00019060945437516497, 'epoch': 7.07}

 59%|█████▉    | 16541/28080 [32:41:38<22:52:16,  7.14s/it]
 59%|█████▉    | 16542/28080 [32:41:46<22:57:56,  7.17s/it]
                                                           
{'loss': 0.6151, 'learning_rate': 0.00019058144456188567, 'epoch': 7.07}

 59%|█████▉    | 16542/28080 [32:41:46<22:57:56,  7.17s/it]
 59%|█████▉    | 16543/28080 [32:41:53<22:52:28,  7.14s/it]
                                                           
{'loss': 0.6293, 'learning_rate': 0.0001905534355391089, 'epoch': 7.07}

 59%|█████▉    | 16543/28080 [32:41:53<22:52:28,  7.14s/it]
 59%|█████▉    | 16544/28080 [32:42:00<22:51:16,  7.13s/it]
                                                           
{'loss': 0.6355, 'learning_rate': 0.0001905254273072074, 'epoch': 7.07}

 59%|█████▉    | 16544/28080 [32:42:00<22:51:16,  7.13s/it]
 59%|█████▉    | 16545/28080 [32:42:07<22:45:42,  7.10s/it]
                                                           
{'loss': 0.6117, 'learning_rate': 0.0001904974198665536, 'epoch': 7.07}

 59%|█████▉    | 16545/28080 [32:42:07<22:45:42,  7.10s/it]
 59%|█████▉    | 16546/28080 [32:42:14<22:40:52,  7.08s/it]
                                                           
{'loss': 0.6008, 'learning_rate': 0.00019046941321752044, 'epoch': 7.07}

 59%|█████▉    | 16546/28080 [32:42:14<22:40:52,  7.08s/it]
 59%|█████▉    | 16547/28080 [32:42:21<22:35:46,  7.05s/it]
                                                           
{'loss': 0.6104, 'learning_rate': 0.00019044140736048027, 'epoch': 7.07}

 59%|█████▉    | 16547/28080 [32:42:21<22:35:46,  7.05s/it]
 59%|█████▉    | 16548/28080 [32:42:28<22:35:30,  7.05s/it]
                                                           
{'loss': 0.6171, 'learning_rate': 0.00019041340229580562, 'epoch': 7.07}

 59%|█████▉    | 16548/28080 [32:42:28<22:35:30,  7.05s/it]
 59%|█████▉    | 16549/28080 [32:42:35<22:39:41,  7.07s/it]
                                                           
{'loss': 0.5944, 'learning_rate': 0.00019038539802386934, 'epoch': 7.07}

 59%|█████▉    | 16549/28080 [32:42:35<22:39:41,  7.07s/it]
 59%|█████▉    | 16550/28080 [32:42:42<22:36:46,  7.06s/it]
                                                           
{'loss': 0.6078, 'learning_rate': 0.00019035739454504363, 'epoch': 7.07}

 59%|█████▉    | 16550/28080 [32:42:42<22:36:46,  7.06s/it]
 59%|█████▉    | 16551/28080 [32:42:49<22:43:48,  7.10s/it]
                                                           
{'loss': 0.6028, 'learning_rate': 0.0001903293918597015, 'epoch': 7.07}

 59%|█████▉    | 16551/28080 [32:42:49<22:43:48,  7.10s/it]
 59%|█████▉    | 16552/28080 [32:42:56<22:41:50,  7.09s/it]
                                                           
{'loss': 0.6379, 'learning_rate': 0.00019030138996821503, 'epoch': 7.07}

 59%|█████▉    | 16552/28080 [32:42:56<22:41:50,  7.09s/it]
 59%|█████▉    | 16553/28080 [32:43:03<22:42:06,  7.09s/it]
                                                           
{'loss': 0.6058, 'learning_rate': 0.0001902733888709571, 'epoch': 7.07}

 59%|█████▉    | 16553/28080 [32:43:03<22:42:06,  7.09s/it]
 59%|█████▉    | 16554/28080 [32:43:11<22:45:14,  7.11s/it]
                                                           
{'loss': 0.5945, 'learning_rate': 0.0001902453885683001, 'epoch': 7.07}

 59%|█████▉    | 16554/28080 [32:43:11<22:45:14,  7.11s/it]
 59%|█████▉    | 16555/28080 [32:43:18<22:52:31,  7.15s/it]
                                                           
{'loss': 0.6217, 'learning_rate': 0.00019021738906061655, 'epoch': 7.07}

 59%|█████▉    | 16555/28080 [32:43:18<22:52:31,  7.15s/it]
 59%|█████▉    | 16556/28080 [32:43:25<22:47:50,  7.12s/it]
                                                           
{'loss': 0.6075, 'learning_rate': 0.00019018939034827896, 'epoch': 7.07}

 59%|█████▉    | 16556/28080 [32:43:25<22:47:50,  7.12s/it]
 59%|█████▉    | 16557/28080 [32:43:32<22:43:48,  7.10s/it]
                                                           
{'loss': 0.5996, 'learning_rate': 0.00019016139243165987, 'epoch': 7.07}

 59%|█████▉    | 16557/28080 [32:43:32<22:43:48,  7.10s/it]
 59%|█████▉    | 16558/28080 [32:43:39<22:44:43,  7.11s/it]
                                                           
{'loss': 0.6174, 'learning_rate': 0.00019013339531113164, 'epoch': 7.07}

 59%|█████▉    | 16558/28080 [32:43:39<22:44:43,  7.11s/it]
 59%|█████▉    | 16559/28080 [32:43:46<22:46:49,  7.12s/it]
                                                           
{'loss': 0.6037, 'learning_rate': 0.00019010539898706692, 'epoch': 7.07}

 59%|█████▉    | 16559/28080 [32:43:46<22:46:49,  7.12s/it]
 59%|█████▉    | 16560/28080 [32:43:53<22:50:51,  7.14s/it]
                                                           
{'loss': 0.6205, 'learning_rate': 0.00019007740345983797, 'epoch': 7.07}

 59%|█████▉    | 16560/28080 [32:43:53<22:50:51,  7.14s/it]
 59%|█████▉    | 16561/28080 [32:44:01<22:50:07,  7.14s/it]
                                                           
{'loss': 0.6639, 'learning_rate': 0.00019004940872981746, 'epoch': 7.07}

 59%|█████▉    | 16561/28080 [32:44:01<22:50:07,  7.14s/it]
 59%|█████▉    | 16562/28080 [32:44:08<22:44:31,  7.11s/it]
                                                           
{'loss': 0.6324, 'learning_rate': 0.00019002141479737756, 'epoch': 7.08}

 59%|█████▉    | 16562/28080 [32:44:08<22:44:31,  7.11s/it]
 59%|█████▉    | 16563/28080 [32:44:15<22:40:51,  7.09s/it]
                                                           
{'loss': 0.6123, 'learning_rate': 0.00018999342166289108, 'epoch': 7.08}

 59%|█████▉    | 16563/28080 [32:44:15<22:40:51,  7.09s/it]
 59%|█████▉    | 16564/28080 [32:44:22<22:46:07,  7.12s/it]
                                                           
{'loss': 0.6098, 'learning_rate': 0.00018996542932673, 'epoch': 7.08}

 59%|█████▉    | 16564/28080 [32:44:22<22:46:07,  7.12s/it]
 59%|█████▉    | 16565/28080 [32:44:29<22:49:01,  7.13s/it]
                                                           
{'loss': 0.5988, 'learning_rate': 0.00018993743778926715, 'epoch': 7.08}

 59%|█████▉    | 16565/28080 [32:44:29<22:49:01,  7.13s/it]
 59%|█████▉    | 16566/28080 [32:44:36<22:49:30,  7.14s/it]
                                                           
{'loss': 0.5937, 'learning_rate': 0.00018990944705087455, 'epoch': 7.08}

 59%|█████▉    | 16566/28080 [32:44:36<22:49:30,  7.14s/it]
 59%|█████▉    | 16567/28080 [32:44:43<22:47:41,  7.13s/it]
                                                           
{'loss': 0.601, 'learning_rate': 0.00018988145711192487, 'epoch': 7.08}

 59%|█████▉    | 16567/28080 [32:44:43<22:47:41,  7.13s/it]
 59%|█████▉    | 16568/28080 [32:44:50<22:46:32,  7.12s/it]
                                                           
{'loss': 0.6212, 'learning_rate': 0.00018985346797279032, 'epoch': 7.08}

 59%|█████▉    | 16568/28080 [32:44:50<22:46:32,  7.12s/it]
 59%|█████▉    | 16569/28080 [32:44:57<22:42:52,  7.10s/it]
                                                           
{'loss': 0.5998, 'learning_rate': 0.00018982547963384338, 'epoch': 7.08}

 59%|█████▉    | 16569/28080 [32:44:57<22:42:52,  7.10s/it]
 59%|█████▉    | 16570/28080 [32:45:04<22:39:41,  7.09s/it]
                                                           
{'loss': 0.6229, 'learning_rate': 0.00018979749209545633, 'epoch': 7.08}

 59%|█████▉    | 16570/28080 [32:45:04<22:39:41,  7.09s/it]
 59%|█████▉    | 16571/28080 [32:45:12<22:39:16,  7.09s/it]
                                                           
{'loss': 0.6369, 'learning_rate': 0.00018976950535800157, 'epoch': 7.08}

 59%|█████▉    | 16571/28080 [32:45:12<22:39:16,  7.09s/it]
 59%|█████▉    | 16572/28080 [32:45:19<22:39:33,  7.09s/it]
                                                           
{'loss': 0.6183, 'learning_rate': 0.00018974151942185142, 'epoch': 7.08}

 59%|█████▉    | 16572/28080 [32:45:19<22:39:33,  7.09s/it]
 59%|█████▉    | 16573/28080 [32:45:26<22:37:05,  7.08s/it]
                                                           
{'loss': 0.625, 'learning_rate': 0.00018971353428737814, 'epoch': 7.08}

 59%|█████▉    | 16573/28080 [32:45:26<22:37:05,  7.08s/it]
 59%|█████▉    | 16574/28080 [32:45:33<22:31:16,  7.05s/it]
                                                           
{'loss': 0.6037, 'learning_rate': 0.00018968554995495412, 'epoch': 7.08}

 59%|█████▉    | 16574/28080 [32:45:33<22:31:16,  7.05s/it]
 59%|█████▉    | 16575/28080 [32:45:40<22:39:44,  7.09s/it]
                                                           
{'loss': 0.6186, 'learning_rate': 0.0001896575664249516, 'epoch': 7.08}

 59%|█████▉    | 16575/28080 [32:45:40<22:39:44,  7.09s/it]
 59%|█████▉    | 16576/28080 [32:45:47<22:39:18,  7.09s/it]
                                                           
{'loss': 0.6068, 'learning_rate': 0.00018962958369774297, 'epoch': 7.08}

 59%|█████▉    | 16576/28080 [32:45:47<22:39:18,  7.09s/it]
 59%|█████▉    | 16577/28080 [32:45:54<22:41:35,  7.10s/it]
                                                           
{'loss': 0.6265, 'learning_rate': 0.00018960160177370039, 'epoch': 7.08}

 59%|█████▉    | 16577/28080 [32:45:54<22:41:35,  7.10s/it]
 59%|█████▉    | 16578/28080 [32:46:01<22:43:36,  7.11s/it]
                                                           
{'loss': 0.6193, 'learning_rate': 0.00018957362065319622, 'epoch': 7.08}

 59%|█████▉    | 16578/28080 [32:46:01<22:43:36,  7.11s/it]
 59%|█████▉    | 16579/28080 [32:46:08<22:40:55,  7.10s/it]
                                                           
{'loss': 0.5969, 'learning_rate': 0.0001895456403366026, 'epoch': 7.08}

 59%|█████▉    | 16579/28080 [32:46:08<22:40:55,  7.10s/it]
 59%|█████▉    | 16580/28080 [32:46:15<22:42:21,  7.11s/it]
                                                           
{'loss': 0.6126, 'learning_rate': 0.000189517660824292, 'epoch': 7.08}

 59%|█████▉    | 16580/28080 [32:46:15<22:42:21,  7.11s/it]
 59%|█████▉    | 16581/28080 [32:46:22<22:38:45,  7.09s/it]
                                                           
{'loss': 0.5951, 'learning_rate': 0.0001894896821166364, 'epoch': 7.08}

 59%|█████▉    | 16581/28080 [32:46:22<22:38:45,  7.09s/it]
 59%|█████▉    | 16582/28080 [32:46:30<22:37:01,  7.08s/it]
                                                           
{'loss': 0.606, 'learning_rate': 0.00018946170421400832, 'epoch': 7.08}

 59%|█████▉    | 16582/28080 [32:46:30<22:37:01,  7.08s/it]
 59%|█████▉    | 16583/28080 [32:46:37<22:44:25,  7.12s/it]
                                                           
{'loss': 0.603, 'learning_rate': 0.00018943372711677963, 'epoch': 7.08}

 59%|█████▉    | 16583/28080 [32:46:37<22:44:25,  7.12s/it]
 59%|█████▉    | 16584/28080 [32:46:44<22:40:21,  7.10s/it]
                                                           
{'loss': 0.6177, 'learning_rate': 0.00018940575082532283, 'epoch': 7.08}

 59%|█████▉    | 16584/28080 [32:46:44<22:40:21,  7.10s/it]
 59%|█████▉    | 16585/28080 [32:46:51<22:30:20,  7.05s/it]
                                                           
{'loss': 0.6323, 'learning_rate': 0.00018937777534000993, 'epoch': 7.08}

 59%|█████▉    | 16585/28080 [32:46:51<22:30:20,  7.05s/it]
 59%|█████▉    | 16586/28080 [32:46:58<22:32:28,  7.06s/it]
                                                           
{'loss': 0.614, 'learning_rate': 0.0001893498006612133, 'epoch': 7.09}

 59%|█████▉    | 16586/28080 [32:46:58<22:32:28,  7.06s/it]
 59%|█████▉    | 16587/28080 [32:47:05<22:34:47,  7.07s/it]
                                                           
{'loss': 0.6019, 'learning_rate': 0.0001893218267893049, 'epoch': 7.09}

 59%|█████▉    | 16587/28080 [32:47:05<22:34:47,  7.07s/it]
 59%|█████▉    | 16588/28080 [32:47:12<22:39:14,  7.10s/it]
                                                           
{'loss': 0.6112, 'learning_rate': 0.00018929385372465707, 'epoch': 7.09}

 59%|█████▉    | 16588/28080 [32:47:12<22:39:14,  7.10s/it]
 59%|█████▉    | 16589/28080 [32:47:19<22:38:54,  7.10s/it]
                                                           
{'loss': 0.6305, 'learning_rate': 0.0001892658814676418, 'epoch': 7.09}

 59%|█████▉    | 16589/28080 [32:47:19<22:38:54,  7.10s/it]
 59%|█████▉    | 16590/28080 [32:47:26<22:35:42,  7.08s/it]
                                                           
{'loss': 0.6273, 'learning_rate': 0.00018923791001863145, 'epoch': 7.09}

 59%|█████▉    | 16590/28080 [32:47:26<22:35:42,  7.08s/it]
 59%|█████▉    | 16591/28080 [32:47:33<22:31:28,  7.06s/it]
                                                           
{'loss': 0.6254, 'learning_rate': 0.0001892099393779979, 'epoch': 7.09}

 59%|█████▉    | 16591/28080 [32:47:33<22:31:28,  7.06s/it]
 59%|█████▉    | 16592/28080 [32:47:40<22:33:16,  7.07s/it]
                                                           
{'loss': 0.601, 'learning_rate': 0.00018918196954611347, 'epoch': 7.09}

 59%|█████▉    | 16592/28080 [32:47:40<22:33:16,  7.07s/it]
 59%|█████▉    | 16593/28080 [32:47:47<22:33:40,  7.07s/it]
                                                           
{'loss': 0.6194, 'learning_rate': 0.00018915400052335008, 'epoch': 7.09}

 59%|█████▉    | 16593/28080 [32:47:47<22:33:40,  7.07s/it]
 59%|█████▉    | 16594/28080 [32:47:54<22:31:27,  7.06s/it]
                                                           
{'loss': 0.6093, 'learning_rate': 0.0001891260323100801, 'epoch': 7.09}

 59%|█████▉    | 16594/28080 [32:47:54<22:31:27,  7.06s/it]
 59%|█████▉    | 16595/28080 [32:48:01<22:31:28,  7.06s/it]
                                                           
{'loss': 0.6086, 'learning_rate': 0.00018909806490667531, 'epoch': 7.09}

 59%|█████▉    | 16595/28080 [32:48:01<22:31:28,  7.06s/it]
 59%|█████▉    | 16596/28080 [32:48:09<22:35:01,  7.08s/it]
                                                           
{'loss': 0.5913, 'learning_rate': 0.0001890700983135081, 'epoch': 7.09}

 59%|█████▉    | 16596/28080 [32:48:09<22:35:01,  7.08s/it]
 59%|█████▉    | 16597/28080 [32:48:16<22:39:46,  7.10s/it]
                                                           
{'loss': 0.6207, 'learning_rate': 0.00018904213253095032, 'epoch': 7.09}

 59%|█████▉    | 16597/28080 [32:48:16<22:39:46,  7.10s/it]
 59%|█████▉    | 16598/28080 [32:48:23<22:40:05,  7.11s/it]
                                                           
{'loss': 0.6192, 'learning_rate': 0.00018901416755937394, 'epoch': 7.09}

 59%|█████▉    | 16598/28080 [32:48:23<22:40:05,  7.11s/it]
 59%|█████▉    | 16599/28080 [32:48:30<22:38:49,  7.10s/it]
                                                           
{'loss': 0.5964, 'learning_rate': 0.00018898620339915135, 'epoch': 7.09}

 59%|█████▉    | 16599/28080 [32:48:30<22:38:49,  7.10s/it]
 59%|█████▉    | 16600/28080 [32:48:37<22:45:00,  7.13s/it]
                                                           
{'loss': 0.6107, 'learning_rate': 0.00018895824005065422, 'epoch': 7.09}

 59%|█████▉    | 16600/28080 [32:48:37<22:45:00,  7.13s/it]
 59%|█████▉    | 16601/28080 [32:48:44<22:46:15,  7.14s/it]
                                                           
{'loss': 0.6146, 'learning_rate': 0.0001889302775142548, 'epoch': 7.09}

 59%|█████▉    | 16601/28080 [32:48:44<22:46:15,  7.14s/it]
 59%|█████▉    | 16602/28080 [32:48:52<22:48:07,  7.15s/it]
                                                           
{'loss': 0.6059, 'learning_rate': 0.00018890231579032503, 'epoch': 7.09}

 59%|█████▉    | 16602/28080 [32:48:52<22:48:07,  7.15s/it]
 59%|█████▉    | 16603/28080 [32:48:59<22:43:19,  7.13s/it]
                                                           
{'loss': 0.6041, 'learning_rate': 0.00018887435487923693, 'epoch': 7.09}

 59%|█████▉    | 16603/28080 [32:48:59<22:43:19,  7.13s/it]
 59%|█████▉    | 16604/28080 [32:49:06<22:44:42,  7.14s/it]
                                                           
{'loss': 0.6087, 'learning_rate': 0.00018884639478136241, 'epoch': 7.09}

 59%|█████▉    | 16604/28080 [32:49:06<22:44:42,  7.14s/it]
 59%|█████▉    | 16605/28080 [32:49:13<22:48:44,  7.16s/it]
                                                           
{'loss': 0.6024, 'learning_rate': 0.00018881843549707362, 'epoch': 7.09}

 59%|█████▉    | 16605/28080 [32:49:13<22:48:44,  7.16s/it]
 59%|█████▉    | 16606/28080 [32:49:20<22:43:28,  7.13s/it]
                                                           
{'loss': 0.6124, 'learning_rate': 0.00018879047702674234, 'epoch': 7.09}

 59%|█████▉    | 16606/28080 [32:49:20<22:43:28,  7.13s/it]
 59%|█████▉    | 16607/28080 [32:49:27<22:43:43,  7.13s/it]
                                                           
{'loss': 0.6153, 'learning_rate': 0.0001887625193707407, 'epoch': 7.09}

 59%|█████▉    | 16607/28080 [32:49:27<22:43:43,  7.13s/it]
 59%|█████▉    | 16608/28080 [32:49:34<22:42:28,  7.13s/it]
                                                           
{'loss': 0.604, 'learning_rate': 0.00018873456252944048, 'epoch': 7.09}

 59%|█████▉    | 16608/28080 [32:49:34<22:42:28,  7.13s/it]
 59%|█████▉    | 16609/28080 [32:49:41<22:34:16,  7.08s/it]
                                                           
{'loss': 0.6, 'learning_rate': 0.0001887066065032138, 'epoch': 7.1}

 59%|█████▉    | 16609/28080 [32:49:41<22:34:16,  7.08s/it]
 59%|█████▉    | 16610/28080 [32:49:48<22:31:40,  7.07s/it]
                                                           
{'loss': 0.6515, 'learning_rate': 0.00018867865129243232, 'epoch': 7.1}

 59%|█████▉    | 16610/28080 [32:49:48<22:31:40,  7.07s/it]
 59%|█████▉    | 16611/28080 [32:49:55<22:37:38,  7.10s/it]
                                                           
{'loss': 0.5944, 'learning_rate': 0.00018865069689746834, 'epoch': 7.1}

 59%|█████▉    | 16611/28080 [32:49:55<22:37:38,  7.10s/it]
 59%|█████▉    | 16612/28080 [32:50:03<22:42:02,  7.13s/it]
                                                           
{'loss': 0.6049, 'learning_rate': 0.00018862274331869335, 'epoch': 7.1}

 59%|█████▉    | 16612/28080 [32:50:03<22:42:02,  7.13s/it]
 59%|█████▉    | 16613/28080 [32:50:10<22:42:56,  7.13s/it]
                                                           
{'loss': 0.5962, 'learning_rate': 0.00018859479055647962, 'epoch': 7.1}

 59%|█████▉    | 16613/28080 [32:50:10<22:42:56,  7.13s/it]
 59%|█████▉    | 16614/28080 [32:50:17<22:37:07,  7.10s/it]
                                                           
{'loss': 0.6135, 'learning_rate': 0.0001885668386111987, 'epoch': 7.1}

 59%|█████▉    | 16614/28080 [32:50:17<22:37:07,  7.10s/it]
 59%|█████▉    | 16615/28080 [32:50:24<22:41:37,  7.13s/it]
                                                           
{'loss': 0.5974, 'learning_rate': 0.0001885388874832227, 'epoch': 7.1}

 59%|█████▉    | 16615/28080 [32:50:24<22:41:37,  7.13s/it]
 59%|█████▉    | 16616/28080 [32:50:31<22:40:26,  7.12s/it]
                                                           
{'loss': 0.631, 'learning_rate': 0.00018851093717292335, 'epoch': 7.1}

 59%|█████▉    | 16616/28080 [32:50:31<22:40:26,  7.12s/it]
 59%|█████▉    | 16617/28080 [32:50:38<22:44:53,  7.14s/it]
                                                           
{'loss': 0.6161, 'learning_rate': 0.00018848298768067262, 'epoch': 7.1}

 59%|█████▉    | 16617/28080 [32:50:38<22:44:53,  7.14s/it]
 59%|█████▉    | 16618/28080 [32:50:45<22:43:19,  7.14s/it]
                                                           
{'loss': 0.6318, 'learning_rate': 0.0001884550390068422, 'epoch': 7.1}

 59%|█████▉    | 16618/28080 [32:50:45<22:43:19,  7.14s/it]
 59%|█████▉    | 16619/28080 [32:50:53<22:40:58,  7.12s/it]
                                                           
{'loss': 0.5989, 'learning_rate': 0.00018842709115180406, 'epoch': 7.1}

 59%|█████▉    | 16619/28080 [32:50:53<22:40:58,  7.12s/it]
 59%|█████▉    | 16620/28080 [32:51:00<22:36:54,  7.10s/it]
                                                           
{'loss': 0.6091, 'learning_rate': 0.00018839914411592987, 'epoch': 7.1}

 59%|█████▉    | 16620/28080 [32:51:00<22:36:54,  7.10s/it]
 59%|█████▉    | 16621/28080 [32:51:07<22:34:13,  7.09s/it]
                                                           
{'loss': 0.6011, 'learning_rate': 0.0001883711978995916, 'epoch': 7.1}

 59%|█████▉    | 16621/28080 [32:51:07<22:34:13,  7.09s/it]
 59%|█████▉    | 16622/28080 [32:51:14<22:27:57,  7.06s/it]
                                                           
{'loss': 0.6132, 'learning_rate': 0.00018834325250316095, 'epoch': 7.1}

 59%|█████▉    | 16622/28080 [32:51:14<22:27:57,  7.06s/it]
 59%|█████▉    | 16623/28080 [32:51:21<22:29:54,  7.07s/it]
                                                           
{'loss': 0.5988, 'learning_rate': 0.00018831530792700967, 'epoch': 7.1}

 59%|█████▉    | 16623/28080 [32:51:21<22:29:54,  7.07s/it]
 59%|█████▉    | 16624/28080 [32:51:28<22:32:41,  7.08s/it]
                                                           
{'loss': 0.6181, 'learning_rate': 0.00018828736417150963, 'epoch': 7.1}

 59%|█████▉    | 16624/28080 [32:51:28<22:32:41,  7.08s/it]
 59%|█████▉    | 16625/28080 [32:51:35<22:42:41,  7.14s/it]
                                                           
{'loss': 0.6079, 'learning_rate': 0.00018825942123703248, 'epoch': 7.1}

 59%|█████▉    | 16625/28080 [32:51:35<22:42:41,  7.14s/it]
 59%|█████▉    | 16626/28080 [32:51:42<22:42:13,  7.14s/it]
                                                           
{'loss': 0.6139, 'learning_rate': 0.00018823147912395012, 'epoch': 7.1}

 59%|█████▉    | 16626/28080 [32:51:42<22:42:13,  7.14s/it]
 59%|█████▉    | 16627/28080 [32:51:49<22:38:00,  7.11s/it]
                                                           
{'loss': 0.616, 'learning_rate': 0.00018820353783263413, 'epoch': 7.1}

 59%|█████▉    | 16627/28080 [32:51:49<22:38:00,  7.11s/it]
 59%|█████▉    | 16628/28080 [32:51:56<22:39:47,  7.12s/it]
                                                           
{'loss': 0.6011, 'learning_rate': 0.00018817559736345637, 'epoch': 7.1}

 59%|█████▉    | 16628/28080 [32:51:56<22:39:47,  7.12s/it]
 59%|█████▉    | 16629/28080 [32:52:03<22:34:51,  7.10s/it]
                                                           
{'loss': 0.6097, 'learning_rate': 0.0001881476577167884, 'epoch': 7.1}

 59%|█████▉    | 16629/28080 [32:52:03<22:34:51,  7.10s/it]
 59%|█████▉    | 16630/28080 [32:52:11<22:31:39,  7.08s/it]
                                                           
{'loss': 0.6282, 'learning_rate': 0.00018811971889300222, 'epoch': 7.1}

 59%|█████▉    | 16630/28080 [32:52:11<22:31:39,  7.08s/it]
 59%|█████▉    | 16631/28080 [32:52:18<22:36:06,  7.11s/it]
                                                           
{'loss': 0.5899, 'learning_rate': 0.00018809178089246914, 'epoch': 7.1}

 59%|█████▉    | 16631/28080 [32:52:18<22:36:06,  7.11s/it]
 59%|█████▉    | 16632/28080 [32:52:25<22:37:34,  7.12s/it]
                                                           
{'loss': 0.5916, 'learning_rate': 0.0001880638437155612, 'epoch': 7.11}

 59%|█████▉    | 16632/28080 [32:52:25<22:37:34,  7.12s/it]
 59%|█████▉    | 16633/28080 [32:52:32<22:40:35,  7.13s/it]
                                                           
{'loss': 0.602, 'learning_rate': 0.00018803590736264986, 'epoch': 7.11}

 59%|█████▉    | 16633/28080 [32:52:32<22:40:35,  7.13s/it]
 59%|█████▉    | 16634/28080 [32:52:39<22:41:19,  7.14s/it]
                                                           
{'loss': 0.6107, 'learning_rate': 0.00018800797183410686, 'epoch': 7.11}

 59%|█████▉    | 16634/28080 [32:52:39<22:41:19,  7.14s/it]
 59%|█████▉    | 16635/28080 [32:52:46<22:43:45,  7.15s/it]
                                                           
{'loss': 0.5947, 'learning_rate': 0.00018798003713030382, 'epoch': 7.11}

 59%|█████▉    | 16635/28080 [32:52:46<22:43:45,  7.15s/it]
 59%|█████▉    | 16636/28080 [32:52:53<22:44:26,  7.15s/it]
                                                           
{'loss': 0.626, 'learning_rate': 0.00018795210325161247, 'epoch': 7.11}

 59%|█████▉    | 16636/28080 [32:52:53<22:44:26,  7.15s/it]
 59%|█████▉    | 16637/28080 [32:53:01<22:44:12,  7.15s/it]
                                                           
{'loss': 0.6163, 'learning_rate': 0.0001879241701984043, 'epoch': 7.11}

 59%|█████▉    | 16637/28080 [32:53:01<22:44:12,  7.15s/it]
 59%|█████▉    | 16638/28080 [32:53:08<22:54:18,  7.21s/it]
                                                           
{'loss': 0.6142, 'learning_rate': 0.00018789623797105107, 'epoch': 7.11}

 59%|█████▉    | 16638/28080 [32:53:08<22:54:18,  7.21s/it]
 59%|█████▉    | 16639/28080 [32:53:15<22:51:07,  7.19s/it]
                                                           
{'loss': 0.6169, 'learning_rate': 0.00018786830656992426, 'epoch': 7.11}

 59%|█████▉    | 16639/28080 [32:53:15<22:51:07,  7.19s/it]
 59%|█████▉    | 16640/28080 [32:53:22<22:45:25,  7.16s/it]
                                                           
{'loss': 0.603, 'learning_rate': 0.0001878403759953956, 'epoch': 7.11}

 59%|█████▉    | 16640/28080 [32:53:22<22:45:25,  7.16s/it]
 59%|█████▉    | 16641/28080 [32:53:29<22:42:25,  7.15s/it]
                                                           
{'loss': 0.6308, 'learning_rate': 0.0001878124462478365, 'epoch': 7.11}

 59%|█████▉    | 16641/28080 [32:53:29<22:42:25,  7.15s/it]
 59%|█████▉    | 16642/28080 [32:53:36<22:35:31,  7.11s/it]
                                                           
{'loss': 0.6282, 'learning_rate': 0.0001877845173276188, 'epoch': 7.11}

 59%|█████▉    | 16642/28080 [32:53:36<22:35:31,  7.11s/it]
 59%|█████▉    | 16643/28080 [32:53:44<22:38:41,  7.13s/it]
                                                           
{'loss': 0.607, 'learning_rate': 0.00018775658923511374, 'epoch': 7.11}

 59%|█████▉    | 16643/28080 [32:53:44<22:38:41,  7.13s/it]
 59%|█████▉    | 16644/28080 [32:53:51<22:34:32,  7.11s/it]
                                                           
{'loss': 0.6016, 'learning_rate': 0.0001877286619706932, 'epoch': 7.11}

 59%|█████▉    | 16644/28080 [32:53:51<22:34:32,  7.11s/it]
 59%|█████▉    | 16645/28080 [32:53:58<22:35:45,  7.11s/it]
                                                           
{'loss': 0.6015, 'learning_rate': 0.00018770073553472846, 'epoch': 7.11}

 59%|█████▉    | 16645/28080 [32:53:58<22:35:45,  7.11s/it]
 59%|█████▉    | 16646/28080 [32:54:05<22:36:05,  7.12s/it]
                                                           
{'loss': 0.6143, 'learning_rate': 0.00018767280992759125, 'epoch': 7.11}

 59%|█████▉    | 16646/28080 [32:54:05<22:36:05,  7.12s/it]
 59%|█████▉    | 16647/28080 [32:54:12<22:29:53,  7.08s/it]
                                                           
{'loss': 0.6057, 'learning_rate': 0.00018764488514965306, 'epoch': 7.11}

 59%|█████▉    | 16647/28080 [32:54:12<22:29:53,  7.08s/it]
 59%|█████▉    | 16648/28080 [32:54:19<22:33:45,  7.11s/it]
                                                           
{'loss': 0.6214, 'learning_rate': 0.00018761696120128517, 'epoch': 7.11}

 59%|█████▉    | 16648/28080 [32:54:19<22:33:45,  7.11s/it]
 59%|█████▉    | 16649/28080 [32:54:26<22:34:45,  7.11s/it]
                                                           
{'loss': 0.5936, 'learning_rate': 0.00018758903808285937, 'epoch': 7.11}

 59%|█████▉    | 16649/28080 [32:54:26<22:34:45,  7.11s/it]
 59%|█████▉    | 16650/28080 [32:54:33<22:31:14,  7.09s/it]
                                                           
{'loss': 0.6079, 'learning_rate': 0.00018756111579474696, 'epoch': 7.11}

 59%|█████▉    | 16650/28080 [32:54:33<22:31:14,  7.09s/it]
 59%|█████▉    | 16651/28080 [32:54:40<22:37:18,  7.13s/it]
                                                           
{'loss': 0.6077, 'learning_rate': 0.00018753319433731957, 'epoch': 7.11}

 59%|█████▉    | 16651/28080 [32:54:40<22:37:18,  7.13s/it]
 59%|█████▉    | 16652/28080 [32:54:47<22:36:51,  7.12s/it]
                                                           
{'loss': 0.599, 'learning_rate': 0.00018750527371094852, 'epoch': 7.11}

 59%|█████▉    | 16652/28080 [32:54:47<22:36:51,  7.12s/it]
 59%|█████▉    | 16653/28080 [32:54:55<22:34:31,  7.11s/it]
                                                           
{'loss': 0.6068, 'learning_rate': 0.0001874773539160054, 'epoch': 7.11}

 59%|█████▉    | 16653/28080 [32:54:55<22:34:31,  7.11s/it]
 59%|█████▉    | 16654/28080 [32:55:02<22:33:54,  7.11s/it]
                                                           
{'loss': 0.6008, 'learning_rate': 0.0001874494349528615, 'epoch': 7.11}

 59%|█████▉    | 16654/28080 [32:55:02<22:33:54,  7.11s/it]
 59%|█████▉    | 16655/28080 [32:55:09<22:42:18,  7.15s/it]
                                                           
{'loss': 0.5985, 'learning_rate': 0.0001874215168218884, 'epoch': 7.11}

 59%|█████▉    | 16655/28080 [32:55:09<22:42:18,  7.15s/it]
 59%|█████▉    | 16656/28080 [32:55:16<22:40:05,  7.14s/it]
                                                           
{'loss': 0.6216, 'learning_rate': 0.0001873935995234574, 'epoch': 7.12}

 59%|█████▉    | 16656/28080 [32:55:16<22:40:05,  7.14s/it]
 59%|█████▉    | 16657/28080 [32:55:23<22:34:43,  7.12s/it]
                                                           
{'loss': 0.6087, 'learning_rate': 0.0001873656830579401, 'epoch': 7.12}

 59%|█████▉    | 16657/28080 [32:55:23<22:34:43,  7.12s/it]
 59%|█████▉    | 16658/28080 [32:55:30<22:31:42,  7.10s/it]
                                                           
{'loss': 0.6327, 'learning_rate': 0.00018733776742570763, 'epoch': 7.12}

 59%|█████▉    | 16658/28080 [32:55:30<22:31:42,  7.10s/it]
 59%|█████▉    | 16659/28080 [32:55:37<22:34:03,  7.11s/it]
                                                           
{'loss': 0.6087, 'learning_rate': 0.0001873098526271316, 'epoch': 7.12}

 59%|█████▉    | 16659/28080 [32:55:37<22:34:03,  7.11s/it]
 59%|█████▉    | 16660/28080 [32:55:44<22:21:11,  7.05s/it]
                                                           
{'loss': 0.6378, 'learning_rate': 0.0001872819386625832, 'epoch': 7.12}

 59%|█████▉    | 16660/28080 [32:55:44<22:21:11,  7.05s/it]
 59%|█████▉    | 16661/28080 [32:55:51<22:19:16,  7.04s/it]
                                                           
{'loss': 0.5988, 'learning_rate': 0.00018725402553243408, 'epoch': 7.12}

 59%|█████▉    | 16661/28080 [32:55:51<22:19:16,  7.04s/it]
 59%|█████▉    | 16662/28080 [32:55:58<22:32:14,  7.11s/it]
                                                           
{'loss': 0.6222, 'learning_rate': 0.00018722611323705523, 'epoch': 7.12}

 59%|█████▉    | 16662/28080 [32:55:58<22:32:14,  7.11s/it]
 59%|█████▉    | 16663/28080 [32:56:06<22:36:19,  7.13s/it]
                                                           
{'loss': 0.6095, 'learning_rate': 0.00018719820177681828, 'epoch': 7.12}

 59%|█████▉    | 16663/28080 [32:56:06<22:36:19,  7.13s/it]
 59%|█████▉    | 16664/28080 [32:56:13<22:37:40,  7.14s/it]
                                                           
{'loss': 0.6385, 'learning_rate': 0.00018717029115209447, 'epoch': 7.12}

 59%|█████▉    | 16664/28080 [32:56:13<22:37:40,  7.14s/it]
 59%|█████▉    | 16665/28080 [32:56:20<22:33:43,  7.12s/it]
                                                           
{'loss': 0.6236, 'learning_rate': 0.0001871423813632551, 'epoch': 7.12}

 59%|█████▉    | 16665/28080 [32:56:20<22:33:43,  7.12s/it]
 59%|█████▉    | 16666/28080 [32:56:27<22:36:11,  7.13s/it]
                                                           
{'loss': 0.6393, 'learning_rate': 0.00018711447241067153, 'epoch': 7.12}

 59%|█████▉    | 16666/28080 [32:56:27<22:36:11,  7.13s/it]
 59%|█████▉    | 16667/28080 [32:56:34<22:32:07,  7.11s/it]
                                                           
{'loss': 0.5983, 'learning_rate': 0.00018708656429471506, 'epoch': 7.12}

 59%|█████▉    | 16667/28080 [32:56:34<22:32:07,  7.11s/it]
 59%|█████▉    | 16668/28080 [32:56:41<22:30:34,  7.10s/it]
                                                           
{'loss': 0.6266, 'learning_rate': 0.00018705865701575683, 'epoch': 7.12}

 59%|█████▉    | 16668/28080 [32:56:41<22:30:34,  7.10s/it]
 59%|█████▉    | 16669/28080 [32:56:48<22:31:19,  7.11s/it]
                                                           
{'loss': 0.6189, 'learning_rate': 0.00018703075057416836, 'epoch': 7.12}

 59%|█████▉    | 16669/28080 [32:56:48<22:31:19,  7.11s/it]
 59%|█████▉    | 16670/28080 [32:56:55<22:33:33,  7.12s/it]
                                                           
{'loss': 0.613, 'learning_rate': 0.00018700284497032068, 'epoch': 7.12}

 59%|█████▉    | 16670/28080 [32:56:55<22:33:33,  7.12s/it]
 59%|█████▉    | 16671/28080 [32:57:03<22:33:42,  7.12s/it]
                                                           
{'loss': 0.5949, 'learning_rate': 0.00018697494020458524, 'epoch': 7.12}

 59%|█████▉    | 16671/28080 [32:57:03<22:33:42,  7.12s/it]
 59%|█████▉    | 16672/28080 [32:57:10<22:31:42,  7.11s/it]
                                                           
{'loss': 0.6011, 'learning_rate': 0.00018694703627733324, 'epoch': 7.12}

 59%|█████▉    | 16672/28080 [32:57:10<22:31:42,  7.11s/it]
 59%|█████▉    | 16673/28080 [32:57:17<22:41:23,  7.16s/it]
                                                           
{'loss': 0.587, 'learning_rate': 0.00018691913318893575, 'epoch': 7.12}

 59%|█████▉    | 16673/28080 [32:57:17<22:41:23,  7.16s/it]
 59%|█████▉    | 16674/28080 [32:57:24<22:41:49,  7.16s/it]
                                                           
{'loss': 0.6035, 'learning_rate': 0.00018689123093976418, 'epoch': 7.12}

 59%|█████▉    | 16674/28080 [32:57:24<22:41:49,  7.16s/it]
 59%|█████▉    | 16675/28080 [32:57:31<22:37:47,  7.14s/it]
                                                           
{'loss': 0.6309, 'learning_rate': 0.00018686332953018968, 'epoch': 7.12}

 59%|█████▉    | 16675/28080 [32:57:31<22:37:47,  7.14s/it]
 59%|█████▉    | 16676/28080 [32:57:38<22:30:32,  7.11s/it]
                                                           
{'loss': 0.6081, 'learning_rate': 0.00018683542896058344, 'epoch': 7.12}

 59%|█████▉    | 16676/28080 [32:57:38<22:30:32,  7.11s/it]
 59%|█████▉    | 16677/28080 [32:57:45<22:27:42,  7.09s/it]
                                                           
{'loss': 0.6272, 'learning_rate': 0.00018680752923131658, 'epoch': 7.12}

 59%|█████▉    | 16677/28080 [32:57:45<22:27:42,  7.09s/it]
 59%|█████▉    | 16678/28080 [32:57:52<22:30:43,  7.11s/it]
                                                           
{'loss': 0.6087, 'learning_rate': 0.00018677963034276053, 'epoch': 7.12}

 59%|█████▉    | 16678/28080 [32:57:52<22:30:43,  7.11s/it]
 59%|█████▉    | 16679/28080 [32:58:00<22:35:03,  7.13s/it]
                                                           
{'loss': 0.6255, 'learning_rate': 0.00018675173229528604, 'epoch': 7.13}

 59%|█████▉    | 16679/28080 [32:58:00<22:35:03,  7.13s/it]
 59%|█████▉    | 16680/28080 [32:58:07<22:34:59,  7.13s/it]
                                                           
{'loss': 0.5934, 'learning_rate': 0.00018672383508926466, 'epoch': 7.13}

 59%|█████▉    | 16680/28080 [32:58:07<22:34:59,  7.13s/it]
 59%|█████▉    | 16681/28080 [32:58:14<22:32:55,  7.12s/it]
                                                           
{'loss': 0.6085, 'learning_rate': 0.00018669593872506734, 'epoch': 7.13}

 59%|█████▉    | 16681/28080 [32:58:14<22:32:55,  7.12s/it]
 59%|█████▉    | 16682/28080 [32:58:21<22:38:49,  7.15s/it]
                                                           
{'loss': 0.6115, 'learning_rate': 0.0001866680432030653, 'epoch': 7.13}

 59%|█████▉    | 16682/28080 [32:58:21<22:38:49,  7.15s/it]
 59%|█████▉    | 16683/28080 [32:58:28<22:36:11,  7.14s/it]
                                                           
{'loss': 0.6199, 'learning_rate': 0.00018664014852362953, 'epoch': 7.13}

 59%|█████▉    | 16683/28080 [32:58:28<22:36:11,  7.14s/it]
 59%|█████▉    | 16684/28080 [32:58:35<22:35:59,  7.14s/it]
                                                           
{'loss': 0.6124, 'learning_rate': 0.00018661225468713128, 'epoch': 7.13}

 59%|█████▉    | 16684/28080 [32:58:35<22:35:59,  7.14s/it]
 59%|█████▉    | 16685/28080 [32:58:43<22:40:25,  7.16s/it]
                                                           
{'loss': 0.6228, 'learning_rate': 0.00018658436169394154, 'epoch': 7.13}

 59%|█████▉    | 16685/28080 [32:58:43<22:40:25,  7.16s/it]
 59%|█████▉    | 16686/28080 [32:58:50<22:39:41,  7.16s/it]
                                                           
{'loss': 0.6119, 'learning_rate': 0.0001865564695444315, 'epoch': 7.13}

 59%|█████▉    | 16686/28080 [32:58:50<22:39:41,  7.16s/it]
 59%|█████▉    | 16687/28080 [32:58:57<22:38:55,  7.16s/it]
                                                           
{'loss': 0.6272, 'learning_rate': 0.00018652857823897213, 'epoch': 7.13}

 59%|█████▉    | 16687/28080 [32:58:57<22:38:55,  7.16s/it]
 59%|█████▉    | 16688/28080 [32:59:04<22:35:00,  7.14s/it]
                                                           
{'loss': 0.634, 'learning_rate': 0.00018650068777793455, 'epoch': 7.13}

 59%|█████▉    | 16688/28080 [32:59:04<22:35:00,  7.14s/it]
 59%|█████▉    | 16689/28080 [32:59:11<22:37:07,  7.15s/it]
                                                           
{'loss': 0.6158, 'learning_rate': 0.00018647279816168982, 'epoch': 7.13}

 59%|█████▉    | 16689/28080 [32:59:11<22:37:07,  7.15s/it]
 59%|█████▉    | 16690/28080 [32:59:18<22:35:19,  7.14s/it]
                                                           
{'loss': 0.6352, 'learning_rate': 0.000186444909390609, 'epoch': 7.13}

 59%|█████▉    | 16690/28080 [32:59:18<22:35:19,  7.14s/it]
 59%|█████▉    | 16691/28080 [32:59:25<22:31:52,  7.12s/it]
                                                           
{'loss': 0.6097, 'learning_rate': 0.00018641702146506302, 'epoch': 7.13}

 59%|█████▉    | 16691/28080 [32:59:25<22:31:52,  7.12s/it]
 59%|█████▉    | 16692/28080 [32:59:32<22:33:54,  7.13s/it]
                                                           
{'loss': 0.6159, 'learning_rate': 0.00018638913438542308, 'epoch': 7.13}

 59%|█████▉    | 16692/28080 [32:59:32<22:33:54,  7.13s/it]
 59%|█████▉    | 16693/28080 [32:59:40<22:32:23,  7.13s/it]
                                                           
{'loss': 0.6116, 'learning_rate': 0.00018636124815205995, 'epoch': 7.13}

 59%|█████▉    | 16693/28080 [32:59:40<22:32:23,  7.13s/it]
 59%|█████▉    | 16694/28080 [32:59:47<22:29:02,  7.11s/it]
                                                           
{'loss': 0.6213, 'learning_rate': 0.00018633336276534487, 'epoch': 7.13}

 59%|█████▉    | 16694/28080 [32:59:47<22:29:02,  7.11s/it]
 59%|█████▉    | 16695/28080 [32:59:54<22:26:32,  7.10s/it]
                                                           
{'loss': 0.5975, 'learning_rate': 0.0001863054782256487, 'epoch': 7.13}

 59%|█████▉    | 16695/28080 [32:59:54<22:26:32,  7.10s/it]
 59%|█████▉    | 16696/28080 [33:00:01<22:25:23,  7.09s/it]
                                                           
{'loss': 0.6282, 'learning_rate': 0.00018627759453334242, 'epoch': 7.13}

 59%|█████▉    | 16696/28080 [33:00:01<22:25:23,  7.09s/it]
 59%|█████▉    | 16697/28080 [33:00:08<22:30:27,  7.12s/it]
                                                           
{'loss': 0.6057, 'learning_rate': 0.00018624971168879705, 'epoch': 7.13}

 59%|█████▉    | 16697/28080 [33:00:08<22:30:27,  7.12s/it]
 59%|█████▉    | 16698/28080 [33:00:15<22:23:58,  7.08s/it]
                                                           
{'loss': 0.6131, 'learning_rate': 0.00018622182969238343, 'epoch': 7.13}

 59%|█████▉    | 16698/28080 [33:00:15<22:23:58,  7.08s/it]
 59%|█████▉    | 16699/28080 [33:00:22<22:31:36,  7.13s/it]
                                                           
{'loss': 0.5942, 'learning_rate': 0.00018619394854447262, 'epoch': 7.13}

 59%|█████▉    | 16699/28080 [33:00:22<22:31:36,  7.13s/it]
 59%|█████▉    | 16700/28080 [33:00:29<22:30:14,  7.12s/it]
                                                           
{'loss': 0.6134, 'learning_rate': 0.00018616606824543543, 'epoch': 7.13}

 59%|█████▉    | 16700/28080 [33:00:29<22:30:14,  7.12s/it]
 59%|█████▉    | 16701/28080 [33:00:36<22:31:10,  7.12s/it]
                                                           
{'loss': 0.603, 'learning_rate': 0.00018613818879564294, 'epoch': 7.13}

 59%|█████▉    | 16701/28080 [33:00:36<22:31:10,  7.12s/it]
 59%|█████▉    | 16702/28080 [33:00:44<22:29:49,  7.12s/it]
                                                           
{'loss': 0.6108, 'learning_rate': 0.00018611031019546588, 'epoch': 7.13}

 59%|█████▉    | 16702/28080 [33:00:44<22:29:49,  7.12s/it]
 59%|█████▉    | 16703/28080 [33:00:51<22:33:40,  7.14s/it]
                                                           
{'loss': 0.6421, 'learning_rate': 0.0001860824324452753, 'epoch': 7.14}

 59%|█████▉    | 16703/28080 [33:00:51<22:33:40,  7.14s/it]
 59%|█████▉    | 16704/28080 [33:00:58<22:29:11,  7.12s/it]
                                                           
{'loss': 0.6146, 'learning_rate': 0.00018605455554544198, 'epoch': 7.14}

 59%|█████▉    | 16704/28080 [33:00:58<22:29:11,  7.12s/it]
 59%|█████▉    | 16705/28080 [33:01:05<22:30:48,  7.13s/it]
                                                           
{'loss': 0.6089, 'learning_rate': 0.00018602667949633683, 'epoch': 7.14}

 59%|█████▉    | 16705/28080 [33:01:05<22:30:48,  7.13s/it]
 59%|█████▉    | 16706/28080 [33:01:12<22:25:49,  7.10s/it]
                                                           
{'loss': 0.6056, 'learning_rate': 0.00018599880429833073, 'epoch': 7.14}

 59%|█████▉    | 16706/28080 [33:01:12<22:25:49,  7.10s/it]
 59%|█████▉    | 16707/28080 [33:01:19<22:32:27,  7.14s/it]
                                                           
{'loss': 0.6046, 'learning_rate': 0.0001859709299517945, 'epoch': 7.14}

 59%|█████▉    | 16707/28080 [33:01:19<22:32:27,  7.14s/it]
 60%|█████▉    | 16708/28080 [33:01:26<22:33:58,  7.14s/it]
                                                           
{'loss': 0.6181, 'learning_rate': 0.00018594305645709892, 'epoch': 7.14}

 60%|█████▉    | 16708/28080 [33:01:26<22:33:58,  7.14s/it]
 60%|█████▉    | 16709/28080 [33:01:34<22:37:47,  7.16s/it]
                                                           
{'loss': 0.611, 'learning_rate': 0.00018591518381461504, 'epoch': 7.14}

 60%|█████▉    | 16709/28080 [33:01:34<22:37:47,  7.16s/it]
 60%|█████▉    | 16710/28080 [33:01:41<22:44:51,  7.20s/it]
                                                           
{'loss': 0.598, 'learning_rate': 0.00018588731202471336, 'epoch': 7.14}

 60%|█████▉    | 16710/28080 [33:01:41<22:44:51,  7.20s/it]
 60%|█████▉    | 16711/28080 [33:01:48<22:40:31,  7.18s/it]
                                                           
{'loss': 0.6019, 'learning_rate': 0.00018585944108776497, 'epoch': 7.14}

 60%|█████▉    | 16711/28080 [33:01:48<22:40:31,  7.18s/it]
 60%|█████▉    | 16712/28080 [33:01:55<22:34:23,  7.15s/it]
                                                           
{'loss': 0.6201, 'learning_rate': 0.0001858315710041405, 'epoch': 7.14}

 60%|█████▉    | 16712/28080 [33:01:55<22:34:23,  7.15s/it]
 60%|█████▉    | 16713/28080 [33:02:02<22:31:12,  7.13s/it]
                                                           
{'loss': 0.6227, 'learning_rate': 0.00018580370177421083, 'epoch': 7.14}

 60%|█████▉    | 16713/28080 [33:02:02<22:31:12,  7.13s/it]
 60%|█████▉    | 16714/28080 [33:02:09<22:29:11,  7.12s/it]
                                                           
{'loss': 0.6342, 'learning_rate': 0.00018577583339834665, 'epoch': 7.14}

 60%|█████▉    | 16714/28080 [33:02:09<22:29:11,  7.12s/it]
 60%|█████▉    | 16715/28080 [33:02:16<22:31:45,  7.14s/it]
                                                           
{'loss': 0.6185, 'learning_rate': 0.00018574796587691872, 'epoch': 7.14}

 60%|█████▉    | 16715/28080 [33:02:16<22:31:45,  7.14s/it]
 60%|█████▉    | 16716/28080 [33:02:24<22:33:20,  7.15s/it]
                                                           
{'loss': 0.6054, 'learning_rate': 0.00018572009921029783, 'epoch': 7.14}

 60%|█████▉    | 16716/28080 [33:02:24<22:33:20,  7.15s/it]
 60%|█████▉    | 16717/28080 [33:02:31<22:32:48,  7.14s/it]
                                                           
{'loss': 0.6128, 'learning_rate': 0.00018569223339885476, 'epoch': 7.14}

 60%|█████▉    | 16717/28080 [33:02:31<22:32:48,  7.14s/it]
 60%|█████▉    | 16718/28080 [33:02:38<22:29:48,  7.13s/it]
                                                           
{'loss': 0.6174, 'learning_rate': 0.00018566436844296013, 'epoch': 7.14}

 60%|█████▉    | 16718/28080 [33:02:38<22:29:48,  7.13s/it]
 60%|█████▉    | 16719/28080 [33:02:45<22:41:29,  7.19s/it]
                                                           
{'loss': 0.5863, 'learning_rate': 0.00018563650434298473, 'epoch': 7.14}

 60%|█████▉    | 16719/28080 [33:02:45<22:41:29,  7.19s/it]
 60%|█████▉    | 16720/28080 [33:02:52<22:34:56,  7.16s/it]
                                                           
{'loss': 0.5997, 'learning_rate': 0.0001856086410992992, 'epoch': 7.14}

 60%|█████▉    | 16720/28080 [33:02:52<22:34:56,  7.16s/it]
 60%|█████▉    | 16721/28080 [33:02:59<22:37:15,  7.17s/it]
                                                           
{'loss': 0.5971, 'learning_rate': 0.00018558077871227435, 'epoch': 7.14}

 60%|█████▉    | 16721/28080 [33:02:59<22:37:15,  7.17s/it]
 60%|█████▉    | 16722/28080 [33:03:06<22:30:14,  7.13s/it]
                                                           
{'loss': 0.6148, 'learning_rate': 0.00018555291718228074, 'epoch': 7.14}

 60%|█████▉    | 16722/28080 [33:03:06<22:30:14,  7.13s/it]
 60%|█████▉    | 16723/28080 [33:03:14<22:29:21,  7.13s/it]
                                                           
{'loss': 0.6198, 'learning_rate': 0.00018552505650968904, 'epoch': 7.14}

 60%|█████▉    | 16723/28080 [33:03:14<22:29:21,  7.13s/it]
 60%|█████▉    | 16724/28080 [33:03:21<22:27:42,  7.12s/it]
                                                           
{'loss': 0.5972, 'learning_rate': 0.00018549719669487002, 'epoch': 7.14}

 60%|█████▉    | 16724/28080 [33:03:21<22:27:42,  7.12s/it]
 60%|█████▉    | 16725/28080 [33:03:28<22:29:55,  7.13s/it]
                                                           
{'loss': 0.6112, 'learning_rate': 0.00018546933773819414, 'epoch': 7.14}

 60%|█████▉    | 16725/28080 [33:03:28<22:29:55,  7.13s/it]
 60%|█████▉    | 16726/28080 [33:03:35<22:27:13,  7.12s/it]
                                                           
{'loss': 0.5988, 'learning_rate': 0.00018544147964003234, 'epoch': 7.15}

 60%|█████▉    | 16726/28080 [33:03:35<22:27:13,  7.12s/it]
 60%|█████▉    | 16727/28080 [33:03:42<22:29:03,  7.13s/it]
                                                           
{'loss': 0.6061, 'learning_rate': 0.00018541362240075482, 'epoch': 7.15}

 60%|█████▉    | 16727/28080 [33:03:42<22:29:03,  7.13s/it]
 60%|█████▉    | 16728/28080 [33:03:49<22:31:01,  7.14s/it]
                                                           
{'loss': 0.5988, 'learning_rate': 0.0001853857660207326, 'epoch': 7.15}

 60%|█████▉    | 16728/28080 [33:03:49<22:31:01,  7.14s/it]
 60%|█████▉    | 16729/28080 [33:03:56<22:25:44,  7.11s/it]
                                                           
{'loss': 0.6411, 'learning_rate': 0.000185357910500336, 'epoch': 7.15}

 60%|█████▉    | 16729/28080 [33:03:56<22:25:44,  7.11s/it]
 60%|█████▉    | 16730/28080 [33:04:03<22:27:29,  7.12s/it]
                                                           
{'loss': 0.6237, 'learning_rate': 0.00018533005583993577, 'epoch': 7.15}

 60%|█████▉    | 16730/28080 [33:04:03<22:27:29,  7.12s/it]
 60%|█████▉    | 16731/28080 [33:04:11<22:22:49,  7.10s/it]
                                                           
{'loss': 0.6354, 'learning_rate': 0.0001853022020399024, 'epoch': 7.15}

 60%|█████▉    | 16731/28080 [33:04:11<22:22:49,  7.10s/it]
 60%|█████▉    | 16732/28080 [33:04:18<22:21:20,  7.09s/it]
                                                           
{'loss': 0.6084, 'learning_rate': 0.00018527434910060652, 'epoch': 7.15}

 60%|█████▉    | 16732/28080 [33:04:18<22:21:20,  7.09s/it]
 60%|█████▉    | 16733/28080 [33:04:25<22:18:11,  7.08s/it]
                                                           
{'loss': 0.6089, 'learning_rate': 0.00018524649702241863, 'epoch': 7.15}

 60%|█████▉    | 16733/28080 [33:04:25<22:18:11,  7.08s/it]
 60%|█████▉    | 16734/28080 [33:04:32<22:18:18,  7.08s/it]
                                                           
{'loss': 0.5871, 'learning_rate': 0.00018521864580570933, 'epoch': 7.15}

 60%|█████▉    | 16734/28080 [33:04:32<22:18:18,  7.08s/it]
 60%|█████▉    | 16735/28080 [33:04:39<22:20:38,  7.09s/it]
                                                           
{'loss': 0.5948, 'learning_rate': 0.00018519079545084905, 'epoch': 7.15}

 60%|█████▉    | 16735/28080 [33:04:39<22:20:38,  7.09s/it]
 60%|█████▉    | 16736/28080 [33:04:46<22:26:48,  7.12s/it]
                                                           
{'loss': 0.612, 'learning_rate': 0.00018516294595820844, 'epoch': 7.15}

 60%|█████▉    | 16736/28080 [33:04:46<22:26:48,  7.12s/it]
 60%|█████▉    | 16737/28080 [33:04:53<22:23:39,  7.11s/it]
                                                           
{'loss': 0.6054, 'learning_rate': 0.0001851350973281579, 'epoch': 7.15}

 60%|█████▉    | 16737/28080 [33:04:53<22:23:39,  7.11s/it]
 60%|█████▉    | 16738/28080 [33:05:00<22:25:09,  7.12s/it]
                                                           
{'loss': 0.6058, 'learning_rate': 0.000185107249561068, 'epoch': 7.15}

 60%|█████▉    | 16738/28080 [33:05:00<22:25:09,  7.12s/it]
 60%|█████▉    | 16739/28080 [33:05:07<22:27:08,  7.13s/it]
                                                           
{'loss': 0.6126, 'learning_rate': 0.00018507940265730913, 'epoch': 7.15}

 60%|█████▉    | 16739/28080 [33:05:07<22:27:08,  7.13s/it]
 60%|█████▉    | 16740/28080 [33:05:14<22:24:04,  7.11s/it]
                                                           
{'loss': 0.6204, 'learning_rate': 0.00018505155661725198, 'epoch': 7.15}

 60%|█████▉    | 16740/28080 [33:05:14<22:24:04,  7.11s/it]
 60%|█████▉    | 16741/28080 [33:05:22<22:24:39,  7.12s/it]
                                                           
{'loss': 0.617, 'learning_rate': 0.0001850237114412667, 'epoch': 7.15}

 60%|█████▉    | 16741/28080 [33:05:22<22:24:39,  7.12s/it]
 60%|█████▉    | 16742/28080 [33:05:29<22:29:09,  7.14s/it]
                                                           
{'loss': 0.6159, 'learning_rate': 0.00018499586712972398, 'epoch': 7.15}

 60%|█████▉    | 16742/28080 [33:05:29<22:29:09,  7.14s/it]
 60%|█████▉    | 16743/28080 [33:05:36<22:29:44,  7.14s/it]
                                                           
{'loss': 0.5785, 'learning_rate': 0.00018496802368299421, 'epoch': 7.15}

 60%|█████▉    | 16743/28080 [33:05:36<22:29:44,  7.14s/it]
 60%|█████▉    | 16744/28080 [33:05:43<22:27:24,  7.13s/it]
                                                           
{'loss': 0.6088, 'learning_rate': 0.00018494018110144778, 'epoch': 7.15}

 60%|█████▉    | 16744/28080 [33:05:43<22:27:24,  7.13s/it]
 60%|█████▉    | 16745/28080 [33:05:50<22:27:01,  7.13s/it]
                                                           
{'loss': 0.597, 'learning_rate': 0.0001849123393854551, 'epoch': 7.15}

 60%|█████▉    | 16745/28080 [33:05:50<22:27:01,  7.13s/it]
 60%|█████▉    | 16746/28080 [33:05:57<22:30:33,  7.15s/it]
                                                           
{'loss': 0.597, 'learning_rate': 0.00018488449853538662, 'epoch': 7.15}

 60%|█████▉    | 16746/28080 [33:05:57<22:30:33,  7.15s/it]
 60%|█████▉    | 16747/28080 [33:06:05<22:34:55,  7.17s/it]
                                                           
{'loss': 0.611, 'learning_rate': 0.00018485665855161277, 'epoch': 7.15}

 60%|█████▉    | 16747/28080 [33:06:05<22:34:55,  7.17s/it]
 60%|█████▉    | 16748/28080 [33:06:12<22:24:01,  7.12s/it]
                                                           
{'loss': 0.6093, 'learning_rate': 0.0001848288194345038, 'epoch': 7.15}

 60%|█████▉    | 16748/28080 [33:06:12<22:24:01,  7.12s/it]
 60%|█████▉    | 16749/28080 [33:06:19<22:23:12,  7.11s/it]
                                                           
{'loss': 0.6112, 'learning_rate': 0.00018480098118443016, 'epoch': 7.16}

 60%|█████▉    | 16749/28080 [33:06:19<22:23:12,  7.11s/it]
 60%|█████▉    | 16750/28080 [33:06:26<22:16:10,  7.08s/it]
                                                           
{'loss': 0.6094, 'learning_rate': 0.0001847731438017622, 'epoch': 7.16}

 60%|█████▉    | 16750/28080 [33:06:26<22:16:10,  7.08s/it]
 60%|█████▉    | 16751/28080 [33:06:33<22:22:18,  7.11s/it]
                                                           
{'loss': 0.6027, 'learning_rate': 0.00018474530728687031, 'epoch': 7.16}

 60%|█████▉    | 16751/28080 [33:06:33<22:22:18,  7.11s/it]
 60%|█████▉    | 16752/28080 [33:06:40<22:21:53,  7.11s/it]
                                                           
{'loss': 0.6138, 'learning_rate': 0.00018471747164012473, 'epoch': 7.16}

 60%|█████▉    | 16752/28080 [33:06:40<22:21:53,  7.11s/it]
 60%|█████▉    | 16753/28080 [33:06:47<22:14:42,  7.07s/it]
                                                           
{'loss': 0.6239, 'learning_rate': 0.00018468963686189588, 'epoch': 7.16}

 60%|█████▉    | 16753/28080 [33:06:47<22:14:42,  7.07s/it]
 60%|█████▉    | 16754/28080 [33:06:54<22:11:39,  7.05s/it]
                                                           
{'loss': 0.6074, 'learning_rate': 0.00018466180295255403, 'epoch': 7.16}

 60%|█████▉    | 16754/28080 [33:06:54<22:11:39,  7.05s/it]
 60%|█████▉    | 16755/28080 [33:07:01<22:13:35,  7.07s/it]
                                                           
{'loss': 0.6098, 'learning_rate': 0.0001846339699124695, 'epoch': 7.16}

 60%|█████▉    | 16755/28080 [33:07:01<22:13:35,  7.07s/it]
 60%|█████▉    | 16756/28080 [33:07:08<22:16:03,  7.08s/it]
                                                           
{'loss': 0.6314, 'learning_rate': 0.00018460613774201246, 'epoch': 7.16}

 60%|█████▉    | 16756/28080 [33:07:08<22:16:03,  7.08s/it]
 60%|█████▉    | 16757/28080 [33:07:15<22:16:08,  7.08s/it]
                                                           
{'loss': 0.6111, 'learning_rate': 0.00018457830644155347, 'epoch': 7.16}

 60%|█████▉    | 16757/28080 [33:07:15<22:16:08,  7.08s/it]
 60%|█████▉    | 16758/28080 [33:07:22<22:21:37,  7.11s/it]
                                                           
{'loss': 0.5918, 'learning_rate': 0.00018455047601146244, 'epoch': 7.16}

 60%|█████▉    | 16758/28080 [33:07:22<22:21:37,  7.11s/it]
 60%|█████▉    | 16759/28080 [33:07:30<22:19:34,  7.10s/it]
                                                           
{'loss': 0.601, 'learning_rate': 0.00018452264645210992, 'epoch': 7.16}

 60%|█████▉    | 16759/28080 [33:07:30<22:19:34,  7.10s/it]
 60%|█████▉    | 16760/28080 [33:07:37<22:22:13,  7.11s/it]
                                                           
{'loss': 0.5989, 'learning_rate': 0.000184494817763866, 'epoch': 7.16}

 60%|█████▉    | 16760/28080 [33:07:37<22:22:13,  7.11s/it]
 60%|█████▉    | 16761/28080 [33:07:44<22:16:33,  7.08s/it]
                                                           
{'loss': 0.5995, 'learning_rate': 0.00018446698994710098, 'epoch': 7.16}

 60%|█████▉    | 16761/28080 [33:07:44<22:16:33,  7.08s/it]
 60%|█████▉    | 16762/28080 [33:07:51<22:16:07,  7.08s/it]
                                                           
{'loss': 0.6036, 'learning_rate': 0.00018443916300218502, 'epoch': 7.16}

 60%|█████▉    | 16762/28080 [33:07:51<22:16:07,  7.08s/it]
 60%|█████▉    | 16763/28080 [33:07:58<22:13:33,  7.07s/it]
                                                           
{'loss': 0.6148, 'learning_rate': 0.00018441133692948843, 'epoch': 7.16}

 60%|█████▉    | 16763/28080 [33:07:58<22:13:33,  7.07s/it]
 60%|█████▉    | 16764/28080 [33:08:05<22:21:03,  7.11s/it]
                                                           
{'loss': 0.6429, 'learning_rate': 0.00018438351172938121, 'epoch': 7.16}

 60%|█████▉    | 16764/28080 [33:08:05<22:21:03,  7.11s/it]
 60%|█████▉    | 16765/28080 [33:08:12<22:13:41,  7.07s/it]
                                                           
{'loss': 0.6144, 'learning_rate': 0.0001843556874022338, 'epoch': 7.16}

 60%|█████▉    | 16765/28080 [33:08:12<22:13:41,  7.07s/it]
 60%|█████▉    | 16766/28080 [33:08:19<22:22:38,  7.12s/it]
                                                           
{'loss': 0.6102, 'learning_rate': 0.0001843278639484162, 'epoch': 7.16}

 60%|█████▉    | 16766/28080 [33:08:19<22:22:38,  7.12s/it]
 60%|█████▉    | 16767/28080 [33:08:26<22:21:28,  7.11s/it]
                                                           
{'loss': 0.591, 'learning_rate': 0.00018430004136829863, 'epoch': 7.16}

 60%|█████▉    | 16767/28080 [33:08:26<22:21:28,  7.11s/it]
 60%|█████▉    | 16768/28080 [33:08:33<22:15:54,  7.09s/it]
                                                           
{'loss': 0.6476, 'learning_rate': 0.00018427221966225123, 'epoch': 7.16}

 60%|█████▉    | 16768/28080 [33:08:33<22:15:54,  7.09s/it]
 60%|█████▉    | 16769/28080 [33:08:40<22:15:11,  7.08s/it]
                                                           
{'loss': 0.6141, 'learning_rate': 0.00018424439883064415, 'epoch': 7.16}

 60%|█████▉    | 16769/28080 [33:08:40<22:15:11,  7.08s/it]
 60%|█████▉    | 16770/28080 [33:08:48<22:16:09,  7.09s/it]
                                                           
{'loss': 0.6204, 'learning_rate': 0.00018421657887384742, 'epoch': 7.16}

 60%|█████▉    | 16770/28080 [33:08:48<22:16:09,  7.09s/it]
 60%|█████▉    | 16771/28080 [33:08:55<22:21:20,  7.12s/it]
                                                           
{'loss': 0.6231, 'learning_rate': 0.0001841887597922314, 'epoch': 7.16}

 60%|█████▉    | 16771/28080 [33:08:55<22:21:20,  7.12s/it]
 60%|█████▉    | 16772/28080 [33:09:02<22:20:06,  7.11s/it]
                                                           
{'loss': 0.6115, 'learning_rate': 0.00018416094158616591, 'epoch': 7.16}

 60%|█████▉    | 16772/28080 [33:09:02<22:20:06,  7.11s/it]
 60%|█████▉    | 16773/28080 [33:09:09<22:20:31,  7.11s/it]
                                                           
{'loss': 0.616, 'learning_rate': 0.00018413312425602117, 'epoch': 7.17}

 60%|█████▉    | 16773/28080 [33:09:09<22:20:31,  7.11s/it]
 60%|█████▉    | 16774/28080 [33:09:16<22:19:58,  7.11s/it]
                                                           
{'loss': 0.623, 'learning_rate': 0.00018410530780216738, 'epoch': 7.17}

 60%|█████▉    | 16774/28080 [33:09:16<22:19:58,  7.11s/it]
 60%|█████▉    | 16775/28080 [33:09:23<22:20:10,  7.11s/it]
                                                           
{'loss': 0.6308, 'learning_rate': 0.00018407749222497434, 'epoch': 7.17}

 60%|█████▉    | 16775/28080 [33:09:23<22:20:10,  7.11s/it]
 60%|█████▉    | 16776/28080 [33:09:30<22:21:01,  7.12s/it]
                                                           
{'loss': 0.6102, 'learning_rate': 0.0001840496775248124, 'epoch': 7.17}

 60%|█████▉    | 16776/28080 [33:09:30<22:21:01,  7.12s/it]
 60%|█████▉    | 16777/28080 [33:09:37<22:16:37,  7.10s/it]
                                                           
{'loss': 0.6198, 'learning_rate': 0.0001840218637020513, 'epoch': 7.17}

 60%|█████▉    | 16777/28080 [33:09:37<22:16:37,  7.10s/it]
 60%|█████▉    | 16778/28080 [33:09:44<22:18:13,  7.10s/it]
                                                           
{'loss': 0.6031, 'learning_rate': 0.00018399405075706136, 'epoch': 7.17}

 60%|█████▉    | 16778/28080 [33:09:44<22:18:13,  7.10s/it]
 60%|█████▉    | 16779/28080 [33:09:52<22:20:43,  7.12s/it]
                                                           
{'loss': 0.6053, 'learning_rate': 0.0001839662386902124, 'epoch': 7.17}

 60%|█████▉    | 16779/28080 [33:09:52<22:20:43,  7.12s/it]
 60%|█████▉    | 16780/28080 [33:09:59<22:15:51,  7.09s/it]
                                                           
{'loss': 0.6211, 'learning_rate': 0.0001839384275018746, 'epoch': 7.17}

 60%|█████▉    | 16780/28080 [33:09:59<22:15:51,  7.09s/it]
 60%|█████▉    | 16781/28080 [33:10:06<22:16:28,  7.10s/it]
                                                           
{'loss': 0.6156, 'learning_rate': 0.0001839106171924178, 'epoch': 7.17}

 60%|█████▉    | 16781/28080 [33:10:06<22:16:28,  7.10s/it]
 60%|█████▉    | 16782/28080 [33:10:13<22:19:38,  7.11s/it]
                                                           
{'loss': 0.6142, 'learning_rate': 0.0001838828077622121, 'epoch': 7.17}

 60%|█████▉    | 16782/28080 [33:10:13<22:19:38,  7.11s/it]
 60%|█████▉    | 16783/28080 [33:10:20<22:25:05,  7.14s/it]
                                                           
{'loss': 0.6256, 'learning_rate': 0.0001838549992116274, 'epoch': 7.17}

 60%|█████▉    | 16783/28080 [33:10:20<22:25:05,  7.14s/it]
 60%|█████▉    | 16784/28080 [33:10:27<22:22:17,  7.13s/it]
                                                           
{'loss': 0.6119, 'learning_rate': 0.00018382719154103375, 'epoch': 7.17}

 60%|█████▉    | 16784/28080 [33:10:27<22:22:17,  7.13s/it]
 60%|█████▉    | 16785/28080 [33:10:34<22:19:17,  7.11s/it]
                                                           
{'loss': 0.5967, 'learning_rate': 0.000183799384750801, 'epoch': 7.17}

 60%|█████▉    | 16785/28080 [33:10:34<22:19:17,  7.11s/it]
 60%|█████▉    | 16786/28080 [33:10:41<22:19:13,  7.11s/it]
                                                           
{'loss': 0.5955, 'learning_rate': 0.0001837715788412992, 'epoch': 7.17}

 60%|█████▉    | 16786/28080 [33:10:41<22:19:13,  7.11s/it]
 60%|█████▉    | 16787/28080 [33:10:48<22:19:11,  7.12s/it]
                                                           
{'loss': 0.6126, 'learning_rate': 0.00018374377381289808, 'epoch': 7.17}

 60%|█████▉    | 16787/28080 [33:10:49<22:19:11,  7.12s/it]
 60%|█████▉    | 16788/28080 [33:10:56<22:15:30,  7.10s/it]
                                                           
{'loss': 0.6166, 'learning_rate': 0.00018371596966596787, 'epoch': 7.17}

 60%|█████▉    | 16788/28080 [33:10:56<22:15:30,  7.10s/it]
 60%|█████▉    | 16789/28080 [33:11:03<22:07:49,  7.06s/it]
                                                           
{'loss': 0.6197, 'learning_rate': 0.00018368816640087815, 'epoch': 7.17}

 60%|█████▉    | 16789/28080 [33:11:03<22:07:49,  7.06s/it]
 60%|█████▉    | 16790/28080 [33:11:10<22:04:19,  7.04s/it]
                                                           
{'loss': 0.6054, 'learning_rate': 0.00018366036401799908, 'epoch': 7.17}

 60%|█████▉    | 16790/28080 [33:11:10<22:04:19,  7.04s/it]
 60%|█████▉    | 16791/28080 [33:11:17<22:05:29,  7.04s/it]
                                                           
{'loss': 0.5947, 'learning_rate': 0.00018363256251770037, 'epoch': 7.17}

 60%|█████▉    | 16791/28080 [33:11:17<22:05:29,  7.04s/it]
 60%|█████▉    | 16792/28080 [33:11:24<22:13:24,  7.09s/it]
                                                           
{'loss': 0.5973, 'learning_rate': 0.00018360476190035197, 'epoch': 7.17}

 60%|█████▉    | 16792/28080 [33:11:24<22:13:24,  7.09s/it]
 60%|█████▉    | 16793/28080 [33:11:31<22:19:13,  7.12s/it]
                                                           
{'loss': 0.5974, 'learning_rate': 0.00018357696216632368, 'epoch': 7.17}

 60%|█████▉    | 16793/28080 [33:11:31<22:19:13,  7.12s/it]
 60%|█████▉    | 16794/28080 [33:11:38<22:22:17,  7.14s/it]
                                                           
{'loss': 0.601, 'learning_rate': 0.0001835491633159855, 'epoch': 7.17}

 60%|█████▉    | 16794/28080 [33:11:38<22:22:17,  7.14s/it]
 60%|█████▉    | 16795/28080 [33:11:45<22:25:13,  7.15s/it]
                                                           
{'loss': 0.6051, 'learning_rate': 0.000183521365349707, 'epoch': 7.17}

 60%|█████▉    | 16795/28080 [33:11:45<22:25:13,  7.15s/it]
 60%|█████▉    | 16796/28080 [33:11:52<22:21:54,  7.14s/it]
                                                           
{'loss': 0.6128, 'learning_rate': 0.00018349356826785824, 'epoch': 7.18}

 60%|█████▉    | 16796/28080 [33:11:52<22:21:54,  7.14s/it]
 60%|█████▉    | 16797/28080 [33:12:00<22:21:12,  7.13s/it]
                                                           
{'loss': 0.6023, 'learning_rate': 0.00018346577207080896, 'epoch': 7.18}

 60%|█████▉    | 16797/28080 [33:12:00<22:21:12,  7.13s/it]
 60%|█████▉    | 16798/28080 [33:12:07<22:13:20,  7.09s/it]
                                                           
{'loss': 0.6284, 'learning_rate': 0.00018343797675892886, 'epoch': 7.18}

 60%|█████▉    | 16798/28080 [33:12:07<22:13:20,  7.09s/it]
 60%|█████▉    | 16799/28080 [33:12:14<22:10:34,  7.08s/it]
                                                           
{'loss': 0.605, 'learning_rate': 0.0001834101823325879, 'epoch': 7.18}

 60%|█████▉    | 16799/28080 [33:12:14<22:10:34,  7.08s/it]
 60%|█████▉    | 16800/28080 [33:12:21<22:09:22,  7.07s/it]
                                                           
{'loss': 0.6087, 'learning_rate': 0.0001833823887921557, 'epoch': 7.18}

 60%|█████▉    | 16800/28080 [33:12:21<22:09:22,  7.07s/it]
 60%|█████▉    | 16801/28080 [33:12:28<22:18:14,  7.12s/it]
                                                           
{'loss': 0.6456, 'learning_rate': 0.00018335459613800216, 'epoch': 7.18}

 60%|█████▉    | 16801/28080 [33:12:28<22:18:14,  7.12s/it]
 60%|█████▉    | 16802/28080 [33:12:35<22:17:13,  7.11s/it]
                                                           
{'loss': 0.6121, 'learning_rate': 0.00018332680437049687, 'epoch': 7.18}

 60%|█████▉    | 16802/28080 [33:12:35<22:17:13,  7.11s/it]
 60%|█████▉    | 16803/28080 [33:12:42<22:10:18,  7.08s/it]
                                                           
{'loss': 0.6247, 'learning_rate': 0.00018329901349000975, 'epoch': 7.18}

 60%|█████▉    | 16803/28080 [33:12:42<22:10:18,  7.08s/it]
 60%|█████▉    | 16804/28080 [33:12:49<22:09:23,  7.07s/it]
                                                           
{'loss': 0.5924, 'learning_rate': 0.00018327122349691034, 'epoch': 7.18}

 60%|█████▉    | 16804/28080 [33:12:49<22:09:23,  7.07s/it]
 60%|█████▉    | 16805/28080 [33:12:56<22:11:43,  7.09s/it]
                                                           
{'loss': 0.5938, 'learning_rate': 0.0001832434343915686, 'epoch': 7.18}

 60%|█████▉    | 16805/28080 [33:12:56<22:11:43,  7.09s/it]
 60%|█████▉    | 16806/28080 [33:13:03<22:15:22,  7.11s/it]
                                                           
{'loss': 0.6007, 'learning_rate': 0.00018321564617435393, 'epoch': 7.18}

 60%|█████▉    | 16806/28080 [33:13:03<22:15:22,  7.11s/it]
 60%|█████▉    | 16807/28080 [33:13:10<22:15:13,  7.11s/it]
                                                           
{'loss': 0.6094, 'learning_rate': 0.00018318785884563637, 'epoch': 7.18}

 60%|█████▉    | 16807/28080 [33:13:10<22:15:13,  7.11s/it]
 60%|█████▉    | 16808/28080 [33:13:18<22:15:40,  7.11s/it]
                                                           
{'loss': 0.6123, 'learning_rate': 0.00018316007240578525, 'epoch': 7.18}

 60%|█████▉    | 16808/28080 [33:13:18<22:15:40,  7.11s/it]
 60%|█████▉    | 16809/28080 [33:13:25<22:23:02,  7.15s/it]
                                                           
{'loss': 0.6237, 'learning_rate': 0.00018313228685517052, 'epoch': 7.18}

 60%|█████▉    | 16809/28080 [33:13:25<22:23:02,  7.15s/it]
 60%|█████▉    | 16810/28080 [33:13:32<22:20:22,  7.14s/it]
                                                           
{'loss': 0.6098, 'learning_rate': 0.0001831045021941617, 'epoch': 7.18}

 60%|█████▉    | 16810/28080 [33:13:32<22:20:22,  7.14s/it]
 60%|█████▉    | 16811/28080 [33:13:39<22:19:12,  7.13s/it]
                                                           
{'loss': 0.6075, 'learning_rate': 0.0001830767184231285, 'epoch': 7.18}

 60%|█████▉    | 16811/28080 [33:13:39<22:19:12,  7.13s/it]
 60%|█████▉    | 16812/28080 [33:13:46<22:18:47,  7.13s/it]
                                                           
{'loss': 0.6337, 'learning_rate': 0.00018304893554244047, 'epoch': 7.18}

 60%|█████▉    | 16812/28080 [33:13:46<22:18:47,  7.13s/it]
 60%|█████▉    | 16813/28080 [33:13:53<22:14:59,  7.11s/it]
                                                           
{'loss': 0.6194, 'learning_rate': 0.00018302115355246735, 'epoch': 7.18}

 60%|█████▉    | 16813/28080 [33:13:53<22:14:59,  7.11s/it]
 60%|█████▉    | 16814/28080 [33:14:00<22:17:09,  7.12s/it]
                                                           
{'loss': 0.6107, 'learning_rate': 0.0001829933724535786, 'epoch': 7.18}

 60%|█████▉    | 16814/28080 [33:14:00<22:17:09,  7.12s/it]
 60%|█████▉    | 16815/28080 [33:14:07<22:13:41,  7.10s/it]
                                                           
{'loss': 0.6097, 'learning_rate': 0.000182965592246144, 'epoch': 7.18}

 60%|█████▉    | 16815/28080 [33:14:07<22:13:41,  7.10s/it]
 60%|█████▉    | 16816/28080 [33:14:14<22:13:14,  7.10s/it]
                                                           
{'loss': 0.6084, 'learning_rate': 0.00018293781293053293, 'epoch': 7.18}

 60%|█████▉    | 16816/28080 [33:14:14<22:13:14,  7.10s/it]
 60%|█████▉    | 16817/28080 [33:14:22<22:18:13,  7.13s/it]
                                                           
{'loss': 0.5953, 'learning_rate': 0.00018291003450711518, 'epoch': 7.18}

 60%|█████▉    | 16817/28080 [33:14:22<22:18:13,  7.13s/it]
 60%|█████▉    | 16818/28080 [33:14:29<22:15:12,  7.11s/it]
                                                           
{'loss': 0.6263, 'learning_rate': 0.00018288225697626006, 'epoch': 7.18}

 60%|█████▉    | 16818/28080 [33:14:29<22:15:12,  7.11s/it]
 60%|█████▉    | 16819/28080 [33:14:36<22:12:40,  7.10s/it]
                                                           
{'loss': 0.6105, 'learning_rate': 0.00018285448033833745, 'epoch': 7.18}

 60%|█████▉    | 16819/28080 [33:14:36<22:12:40,  7.10s/it]
 60%|█████▉    | 16820/28080 [33:14:43<22:17:36,  7.13s/it]
                                                           
{'loss': 0.6046, 'learning_rate': 0.00018282670459371654, 'epoch': 7.19}

 60%|█████▉    | 16820/28080 [33:14:43<22:17:36,  7.13s/it]
 60%|█████▉    | 16821/28080 [33:14:50<22:14:17,  7.11s/it]
                                                           
{'loss': 0.59, 'learning_rate': 0.00018279892974276712, 'epoch': 7.19}

 60%|█████▉    | 16821/28080 [33:14:50<22:14:17,  7.11s/it]
 60%|█████▉    | 16822/28080 [33:14:57<22:16:40,  7.12s/it]
                                                           
{'loss': 0.6095, 'learning_rate': 0.00018277115578585874, 'epoch': 7.19}

 60%|█████▉    | 16822/28080 [33:14:57<22:16:40,  7.12s/it]
 60%|█████▉    | 16823/28080 [33:15:04<22:13:53,  7.11s/it]
                                                           
{'loss': 0.6082, 'learning_rate': 0.00018274338272336054, 'epoch': 7.19}

 60%|█████▉    | 16823/28080 [33:15:04<22:13:53,  7.11s/it]
 60%|█████▉    | 16824/28080 [33:15:12<22:22:12,  7.15s/it]
                                                           
{'loss': 0.5939, 'learning_rate': 0.00018271561055564244, 'epoch': 7.19}

 60%|█████▉    | 16824/28080 [33:15:12<22:22:12,  7.15s/it]
 60%|█████▉    | 16825/28080 [33:15:19<22:18:17,  7.13s/it]
                                                           
{'loss': 0.6204, 'learning_rate': 0.00018268783928307352, 'epoch': 7.19}

 60%|█████▉    | 16825/28080 [33:15:19<22:18:17,  7.13s/it]
 60%|█████▉    | 16826/28080 [33:15:26<22:19:10,  7.14s/it]
                                                           
{'loss': 0.6145, 'learning_rate': 0.0001826600689060236, 'epoch': 7.19}

 60%|█████▉    | 16826/28080 [33:15:26<22:19:10,  7.14s/it]
 60%|█████▉    | 16827/28080 [33:15:33<22:21:58,  7.16s/it]
                                                           
{'loss': 0.6467, 'learning_rate': 0.00018263229942486198, 'epoch': 7.19}

 60%|█████▉    | 16827/28080 [33:15:33<22:21:58,  7.16s/it]
 60%|█████▉    | 16828/28080 [33:15:40<22:27:52,  7.19s/it]
                                                           
{'loss': 0.6132, 'learning_rate': 0.0001826045308399581, 'epoch': 7.19}

 60%|█████▉    | 16828/28080 [33:15:40<22:27:52,  7.19s/it]
 60%|█████▉    | 16829/28080 [33:15:47<22:24:45,  7.17s/it]
                                                           
{'loss': 0.607, 'learning_rate': 0.00018257676315168138, 'epoch': 7.19}

 60%|█████▉    | 16829/28080 [33:15:47<22:24:45,  7.17s/it]
 60%|█████▉    | 16830/28080 [33:15:54<22:20:13,  7.15s/it]
                                                           
{'loss': 0.6078, 'learning_rate': 0.00018254899636040134, 'epoch': 7.19}

 60%|█████▉    | 16830/28080 [33:15:54<22:20:13,  7.15s/it]
 60%|█████▉    | 16831/28080 [33:16:01<22:12:37,  7.11s/it]
                                                           
{'loss': 0.6116, 'learning_rate': 0.00018252123046648728, 'epoch': 7.19}

 60%|█████▉    | 16831/28080 [33:16:02<22:12:37,  7.11s/it]
 60%|█████▉    | 16832/28080 [33:16:09<22:21:53,  7.16s/it]
                                                           
{'loss': 0.6076, 'learning_rate': 0.00018249346547030866, 'epoch': 7.19}

 60%|█████▉    | 16832/28080 [33:16:09<22:21:53,  7.16s/it]
 60%|█████▉    | 16833/28080 [33:16:16<22:18:57,  7.14s/it]
                                                           
{'loss': 0.6069, 'learning_rate': 0.0001824657013722348, 'epoch': 7.19}

 60%|█████▉    | 16833/28080 [33:16:16<22:18:57,  7.14s/it]
 60%|█████▉    | 16834/28080 [33:16:23<22:18:00,  7.14s/it]
                                                           
{'loss': 0.6119, 'learning_rate': 0.0001824379381726351, 'epoch': 7.19}

 60%|█████▉    | 16834/28080 [33:16:23<22:18:00,  7.14s/it]
 60%|█████▉    | 16835/28080 [33:16:30<22:21:02,  7.16s/it]
                                                           
{'loss': 0.6131, 'learning_rate': 0.00018241017587187892, 'epoch': 7.19}

 60%|█████▉    | 16835/28080 [33:16:30<22:21:02,  7.16s/it]
 60%|█████▉    | 16836/28080 [33:16:37<22:22:27,  7.16s/it]
                                                           
{'loss': 0.6251, 'learning_rate': 0.00018238241447033571, 'epoch': 7.19}

 60%|█████▉    | 16836/28080 [33:16:37<22:22:27,  7.16s/it]
 60%|█████▉    | 16837/28080 [33:16:45<22:22:47,  7.17s/it]
                                                           
{'loss': 0.6012, 'learning_rate': 0.0001823546539683746, 'epoch': 7.19}

 60%|█████▉    | 16837/28080 [33:16:45<22:22:47,  7.17s/it]
 60%|█████▉    | 16838/28080 [33:16:52<22:19:50,  7.15s/it]
                                                           
{'loss': 0.6093, 'learning_rate': 0.0001823268943663652, 'epoch': 7.19}

 60%|█████▉    | 16838/28080 [33:16:52<22:19:50,  7.15s/it]
 60%|█████▉    | 16839/28080 [33:16:59<22:17:58,  7.14s/it]
                                                           
{'loss': 0.609, 'learning_rate': 0.00018229913566467646, 'epoch': 7.19}

 60%|█████▉    | 16839/28080 [33:16:59<22:17:58,  7.14s/it]
 60%|█████▉    | 16840/28080 [33:17:06<22:19:30,  7.15s/it]
                                                           
{'loss': 0.6238, 'learning_rate': 0.00018227137786367797, 'epoch': 7.19}

 60%|█████▉    | 16840/28080 [33:17:06<22:19:30,  7.15s/it]
 60%|█████▉    | 16841/28080 [33:17:13<22:26:07,  7.19s/it]
                                                           
{'loss': 0.5989, 'learning_rate': 0.0001822436209637389, 'epoch': 7.19}

 60%|█████▉    | 16841/28080 [33:17:13<22:26:07,  7.19s/it]
 60%|█████▉    | 16842/28080 [33:17:20<22:19:49,  7.15s/it]
                                                           
{'loss': 0.6266, 'learning_rate': 0.00018221586496522862, 'epoch': 7.19}

 60%|█████▉    | 16842/28080 [33:17:20<22:19:49,  7.15s/it]
 60%|█████▉    | 16843/28080 [33:17:28<22:23:57,  7.18s/it]
                                                           
{'loss': 0.6024, 'learning_rate': 0.0001821881098685163, 'epoch': 7.2}

 60%|█████▉    | 16843/28080 [33:17:28<22:23:57,  7.18s/it]
 60%|█████▉    | 16844/28080 [33:17:35<22:23:06,  7.17s/it]
                                                           
{'loss': 0.6228, 'learning_rate': 0.0001821603556739712, 'epoch': 7.2}

 60%|█████▉    | 16844/28080 [33:17:35<22:23:06,  7.17s/it]
 60%|█████▉    | 16845/28080 [33:17:42<22:19:53,  7.16s/it]
                                                           
{'loss': 0.618, 'learning_rate': 0.00018213260238196259, 'epoch': 7.2}

 60%|█████▉    | 16845/28080 [33:17:42<22:19:53,  7.16s/it]
 60%|█████▉    | 16846/28080 [33:17:49<22:24:32,  7.18s/it]
                                                           
{'loss': 0.618, 'learning_rate': 0.0001821048499928597, 'epoch': 7.2}

 60%|█████▉    | 16846/28080 [33:17:49<22:24:32,  7.18s/it]
 60%|█████▉    | 16847/28080 [33:17:56<22:24:36,  7.18s/it]
                                                           
{'loss': 0.6108, 'learning_rate': 0.00018207709850703177, 'epoch': 7.2}

 60%|█████▉    | 16847/28080 [33:17:56<22:24:36,  7.18s/it]
 60%|██████    | 16848/28080 [33:18:03<22:24:52,  7.18s/it]
                                                           
{'loss': 0.6137, 'learning_rate': 0.00018204934792484789, 'epoch': 7.2}

 60%|██████    | 16848/28080 [33:18:03<22:24:52,  7.18s/it]
 60%|██████    | 16849/28080 [33:18:11<22:20:13,  7.16s/it]
                                                           
{'loss': 0.6029, 'learning_rate': 0.00018202159824667741, 'epoch': 7.2}

 60%|██████    | 16849/28080 [33:18:11<22:20:13,  7.16s/it]
 60%|██████    | 16850/28080 [33:18:18<22:15:12,  7.13s/it]
                                                           
{'loss': 0.6059, 'learning_rate': 0.0001819938494728894, 'epoch': 7.2}

 60%|██████    | 16850/28080 [33:18:18<22:15:12,  7.13s/it]
 60%|██████    | 16851/28080 [33:18:25<22:17:45,  7.15s/it]
                                                           
{'loss': 0.6104, 'learning_rate': 0.00018196610160385308, 'epoch': 7.2}

 60%|██████    | 16851/28080 [33:18:25<22:17:45,  7.15s/it]
 60%|██████    | 16852/28080 [33:18:32<22:09:49,  7.11s/it]
                                                           
{'loss': 0.6156, 'learning_rate': 0.00018193835463993748, 'epoch': 7.2}

 60%|██████    | 16852/28080 [33:18:32<22:09:49,  7.11s/it]
 60%|██████    | 16853/28080 [33:18:39<22:11:53,  7.12s/it]
                                                           
{'loss': 0.5993, 'learning_rate': 0.00018191060858151203, 'epoch': 7.2}

 60%|██████    | 16853/28080 [33:18:39<22:11:53,  7.12s/it]
 60%|██████    | 16854/28080 [33:18:46<22:07:16,  7.09s/it]
                                                           
{'loss': 0.6104, 'learning_rate': 0.00018188286342894555, 'epoch': 7.2}

 60%|██████    | 16854/28080 [33:18:46<22:07:16,  7.09s/it]
 60%|██████    | 16855/28080 [33:18:53<22:09:06,  7.10s/it]
                                                           
{'loss': 0.5959, 'learning_rate': 0.00018185511918260744, 'epoch': 7.2}

 60%|██████    | 16855/28080 [33:18:53<22:09:06,  7.10s/it]
 60%|██████    | 16856/28080 [33:19:00<22:07:45,  7.10s/it]
                                                           
{'loss': 0.6108, 'learning_rate': 0.0001818273758428665, 'epoch': 7.2}

 60%|██████    | 16856/28080 [33:19:00<22:07:45,  7.10s/it]
 60%|██████    | 16857/28080 [33:19:07<22:08:41,  7.10s/it]
                                                           
{'loss': 0.6068, 'learning_rate': 0.00018179963341009216, 'epoch': 7.2}

 60%|██████    | 16857/28080 [33:19:07<22:08:41,  7.10s/it]
 60%|██████    | 16858/28080 [33:19:14<22:07:45,  7.10s/it]
                                                           
{'loss': 0.5944, 'learning_rate': 0.0001817718918846532, 'epoch': 7.2}

 60%|██████    | 16858/28080 [33:19:14<22:07:45,  7.10s/it]
 60%|██████    | 16859/28080 [33:19:22<22:08:31,  7.10s/it]
                                                           
{'loss': 0.6098, 'learning_rate': 0.00018174415126691895, 'epoch': 7.2}

 60%|██████    | 16859/28080 [33:19:22<22:08:31,  7.10s/it]
 60%|██████    | 16860/28080 [33:19:29<22:13:59,  7.13s/it]
                                                           
{'loss': 0.6141, 'learning_rate': 0.00018171641155725828, 'epoch': 7.2}

 60%|██████    | 16860/28080 [33:19:29<22:13:59,  7.13s/it]
 60%|██████    | 16861/28080 [33:19:36<22:14:52,  7.14s/it]
                                                           
{'loss': 0.6069, 'learning_rate': 0.00018168867275604033, 'epoch': 7.2}

 60%|██████    | 16861/28080 [33:19:36<22:14:52,  7.14s/it]
 60%|██████    | 16862/28080 [33:19:43<22:19:38,  7.17s/it]
                                                           
{'loss': 0.6118, 'learning_rate': 0.00018166093486363412, 'epoch': 7.2}

 60%|██████    | 16862/28080 [33:19:43<22:19:38,  7.17s/it]
 60%|██████    | 16863/28080 [33:19:50<22:10:54,  7.12s/it]
                                                           
{'loss': 0.632, 'learning_rate': 0.00018163319788040867, 'epoch': 7.2}

 60%|██████    | 16863/28080 [33:19:50<22:10:54,  7.12s/it]
 60%|██████    | 16864/28080 [33:19:57<22:10:56,  7.12s/it]
                                                           
{'loss': 0.5988, 'learning_rate': 0.00018160546180673296, 'epoch': 7.2}

 60%|██████    | 16864/28080 [33:19:57<22:10:56,  7.12s/it]
 60%|██████    | 16865/28080 [33:20:04<22:09:10,  7.11s/it]
                                                           
{'loss': 0.6223, 'learning_rate': 0.00018157772664297606, 'epoch': 7.2}

 60%|██████    | 16865/28080 [33:20:04<22:09:10,  7.11s/it]
 60%|██████    | 16866/28080 [33:20:11<22:11:00,  7.12s/it]
                                                           
{'loss': 0.5884, 'learning_rate': 0.00018154999238950684, 'epoch': 7.2}

 60%|██████    | 16866/28080 [33:20:11<22:11:00,  7.12s/it]
 60%|██████    | 16867/28080 [33:20:19<22:15:17,  7.15s/it]
                                                           
{'loss': 0.59, 'learning_rate': 0.0001815222590466945, 'epoch': 7.21}

 60%|██████    | 16867/28080 [33:20:19<22:15:17,  7.15s/it]
 60%|██████    | 16868/28080 [33:20:26<22:11:21,  7.12s/it]
                                                           
{'loss': 0.5946, 'learning_rate': 0.00018149452661490772, 'epoch': 7.21}

 60%|██████    | 16868/28080 [33:20:26<22:11:21,  7.12s/it]
 60%|██████    | 16869/28080 [33:20:33<22:05:25,  7.09s/it]
                                                           
{'loss': 0.5926, 'learning_rate': 0.00018146679509451575, 'epoch': 7.21}

 60%|██████    | 16869/28080 [33:20:33<22:05:25,  7.09s/it]
 60%|██████    | 16870/28080 [33:20:40<22:04:12,  7.09s/it]
                                                           
{'loss': 0.6179, 'learning_rate': 0.00018143906448588715, 'epoch': 7.21}

 60%|██████    | 16870/28080 [33:20:40<22:04:12,  7.09s/it]
 60%|██████    | 16871/28080 [33:20:47<22:08:46,  7.11s/it]
                                                           
{'loss': 0.624, 'learning_rate': 0.00018141133478939123, 'epoch': 7.21}

 60%|██████    | 16871/28080 [33:20:47<22:08:46,  7.11s/it]
 60%|██████    | 16872/28080 [33:20:54<22:14:12,  7.14s/it]
                                                           
{'loss': 0.6102, 'learning_rate': 0.00018138360600539676, 'epoch': 7.21}

 60%|██████    | 16872/28080 [33:20:54<22:14:12,  7.14s/it]
 60%|██████    | 16873/28080 [33:21:01<22:15:32,  7.15s/it]
                                                           
{'loss': 0.6014, 'learning_rate': 0.0001813558781342725, 'epoch': 7.21}

 60%|██████    | 16873/28080 [33:21:01<22:15:32,  7.15s/it]
 60%|██████    | 16874/28080 [33:21:08<22:09:35,  7.12s/it]
                                                           
{'loss': 0.6423, 'learning_rate': 0.00018132815117638757, 'epoch': 7.21}

 60%|██████    | 16874/28080 [33:21:08<22:09:35,  7.12s/it]
 60%|██████    | 16875/28080 [33:21:16<22:14:55,  7.15s/it]
                                                           
{'loss': 0.6222, 'learning_rate': 0.00018130042513211068, 'epoch': 7.21}

 60%|██████    | 16875/28080 [33:21:16<22:14:55,  7.15s/it]
 60%|██████    | 16876/28080 [33:21:23<22:13:01,  7.14s/it]
                                                           
{'loss': 0.6125, 'learning_rate': 0.0001812727000018108, 'epoch': 7.21}

 60%|██████    | 16876/28080 [33:21:23<22:13:01,  7.14s/it]
 60%|██████    | 16877/28080 [33:21:30<22:19:29,  7.17s/it]
                                                           
{'loss': 0.6287, 'learning_rate': 0.00018124497578585669, 'epoch': 7.21}

 60%|██████    | 16877/28080 [33:21:30<22:19:29,  7.17s/it]
 60%|██████    | 16878/28080 [33:21:37<22:21:27,  7.19s/it]
                                                           
{'loss': 0.5983, 'learning_rate': 0.00018121725248461734, 'epoch': 7.21}

 60%|██████    | 16878/28080 [33:21:37<22:21:27,  7.19s/it]
 60%|██████    | 16879/28080 [33:21:44<22:22:26,  7.19s/it]
                                                           
{'loss': 0.6274, 'learning_rate': 0.00018118953009846139, 'epoch': 7.21}

 60%|██████    | 16879/28080 [33:21:44<22:22:26,  7.19s/it]
 60%|██████    | 16880/28080 [33:21:52<22:19:08,  7.17s/it]
                                                           
{'loss': 0.6127, 'learning_rate': 0.00018116180862775782, 'epoch': 7.21}

 60%|██████    | 16880/28080 [33:21:52<22:19:08,  7.17s/it]
 60%|██████    | 16881/28080 [33:21:59<22:16:38,  7.16s/it]
                                                           
{'loss': 0.5948, 'learning_rate': 0.00018113408807287536, 'epoch': 7.21}

 60%|██████    | 16881/28080 [33:21:59<22:16:38,  7.16s/it]
 60%|██████    | 16882/28080 [33:22:06<22:19:00,  7.17s/it]
                                                           
{'loss': 0.5929, 'learning_rate': 0.0001811063684341828, 'epoch': 7.21}

 60%|██████    | 16882/28080 [33:22:06<22:19:00,  7.17s/it]
 60%|██████    | 16883/28080 [33:22:13<22:15:29,  7.16s/it]
                                                           
{'loss': 0.6148, 'learning_rate': 0.00018107864971204885, 'epoch': 7.21}

 60%|██████    | 16883/28080 [33:22:13<22:15:29,  7.16s/it]
 60%|██████    | 16884/28080 [33:22:20<22:08:17,  7.12s/it]
                                                           
{'loss': 0.6005, 'learning_rate': 0.00018105093190684253, 'epoch': 7.21}

 60%|██████    | 16884/28080 [33:22:20<22:08:17,  7.12s/it]
 60%|██████    | 16885/28080 [33:22:27<22:11:46,  7.14s/it]
                                                           
{'loss': 0.6169, 'learning_rate': 0.00018102321501893226, 'epoch': 7.21}

 60%|██████    | 16885/28080 [33:22:27<22:11:46,  7.14s/it]
 60%|██████    | 16886/28080 [33:22:34<22:14:01,  7.15s/it]
                                                           
{'loss': 0.607, 'learning_rate': 0.00018099549904868712, 'epoch': 7.21}

 60%|██████    | 16886/28080 [33:22:34<22:14:01,  7.15s/it]
 60%|██████    | 16887/28080 [33:22:42<22:10:16,  7.13s/it]
                                                           
{'loss': 0.6009, 'learning_rate': 0.00018096778399647552, 'epoch': 7.21}

 60%|██████    | 16887/28080 [33:22:42<22:10:16,  7.13s/it]
 60%|██████    | 16888/28080 [33:22:49<22:15:57,  7.16s/it]
                                                           
{'loss': 0.6204, 'learning_rate': 0.00018094006986266645, 'epoch': 7.21}

 60%|██████    | 16888/28080 [33:22:49<22:15:57,  7.16s/it]
 60%|██████    | 16889/28080 [33:22:56<22:15:37,  7.16s/it]
                                                           
{'loss': 0.5957, 'learning_rate': 0.00018091235664762845, 'epoch': 7.21}

 60%|██████    | 16889/28080 [33:22:56<22:15:37,  7.16s/it]
 60%|██████    | 16890/28080 [33:23:03<22:15:56,  7.16s/it]
                                                           
{'loss': 0.6258, 'learning_rate': 0.0001808846443517303, 'epoch': 7.22}

 60%|██████    | 16890/28080 [33:23:03<22:15:56,  7.16s/it]
 60%|██████    | 16891/28080 [33:23:10<22:24:51,  7.21s/it]
                                                           
{'loss': 0.6282, 'learning_rate': 0.00018085693297534064, 'epoch': 7.22}

 60%|██████    | 16891/28080 [33:23:10<22:24:51,  7.21s/it]
 60%|██████    | 16892/28080 [33:23:17<22:11:57,  7.14s/it]
                                                           
{'loss': 0.6241, 'learning_rate': 0.00018082922251882818, 'epoch': 7.22}

 60%|██████    | 16892/28080 [33:23:17<22:11:57,  7.14s/it]
 60%|██████    | 16893/28080 [33:23:25<22:12:08,  7.14s/it]
                                                           
{'loss': 0.5883, 'learning_rate': 0.00018080151298256153, 'epoch': 7.22}

 60%|██████    | 16893/28080 [33:23:25<22:12:08,  7.14s/it]
 60%|██████    | 16894/28080 [33:23:32<22:16:16,  7.17s/it]
                                                           
{'loss': 0.611, 'learning_rate': 0.00018077380436690938, 'epoch': 7.22}

 60%|██████    | 16894/28080 [33:23:32<22:16:16,  7.17s/it]
 60%|██████    | 16895/28080 [33:23:39<22:08:49,  7.13s/it]
                                                           
{'loss': 0.6143, 'learning_rate': 0.00018074609667224033, 'epoch': 7.22}

 60%|██████    | 16895/28080 [33:23:39<22:08:49,  7.13s/it]
 60%|██████    | 16896/28080 [33:23:46<22:06:58,  7.12s/it]
                                                           
{'loss': 0.6001, 'learning_rate': 0.00018071838989892303, 'epoch': 7.22}

 60%|██████    | 16896/28080 [33:23:46<22:06:58,  7.12s/it]
 60%|██████    | 16897/28080 [33:23:53<22:03:39,  7.10s/it]
                                                           
{'loss': 0.6162, 'learning_rate': 0.0001806906840473261, 'epoch': 7.22}

 60%|██████    | 16897/28080 [33:23:53<22:03:39,  7.10s/it]
 60%|██████    | 16898/28080 [33:24:00<21:56:34,  7.06s/it]
                                                           
{'loss': 0.6088, 'learning_rate': 0.00018066297911781807, 'epoch': 7.22}

 60%|██████    | 16898/28080 [33:24:00<21:56:34,  7.06s/it]
 60%|██████    | 16899/28080 [33:24:07<21:53:12,  7.05s/it]
                                                           
{'loss': 0.6298, 'learning_rate': 0.00018063527511076762, 'epoch': 7.22}

 60%|██████    | 16899/28080 [33:24:07<21:53:12,  7.05s/it]
 60%|██████    | 16900/28080 [33:24:14<22:00:28,  7.09s/it]
                                                           
{'loss': 0.6237, 'learning_rate': 0.0001806075720265432, 'epoch': 7.22}

 60%|██████    | 16900/28080 [33:24:14<22:00:28,  7.09s/it]
 60%|██████    | 16901/28080 [33:24:21<22:01:31,  7.09s/it]
                                                           
{'loss': 0.6352, 'learning_rate': 0.00018057986986551357, 'epoch': 7.22}

 60%|██████    | 16901/28080 [33:24:21<22:01:31,  7.09s/it]
 60%|██████    | 16902/28080 [33:24:28<22:03:31,  7.10s/it]
                                                           
{'loss': 0.6166, 'learning_rate': 0.00018055216862804697, 'epoch': 7.22}

 60%|██████    | 16902/28080 [33:24:28<22:03:31,  7.10s/it]
 60%|██████    | 16903/28080 [33:24:35<22:03:17,  7.10s/it]
                                                           
{'loss': 0.6186, 'learning_rate': 0.0001805244683145123, 'epoch': 7.22}

 60%|██████    | 16903/28080 [33:24:35<22:03:17,  7.10s/it]
 60%|██████    | 16904/28080 [33:24:43<22:05:13,  7.11s/it]
                                                           
{'loss': 0.6118, 'learning_rate': 0.00018049676892527774, 'epoch': 7.22}

 60%|██████    | 16904/28080 [33:24:43<22:05:13,  7.11s/it]
 60%|██████    | 16905/28080 [33:24:50<22:11:52,  7.15s/it]
                                                           
{'loss': 0.6081, 'learning_rate': 0.0001804690704607121, 'epoch': 7.22}

 60%|██████    | 16905/28080 [33:24:50<22:11:52,  7.15s/it]
 60%|██████    | 16906/28080 [33:24:57<22:06:39,  7.12s/it]
                                                           
{'loss': 0.5985, 'learning_rate': 0.00018044137292118367, 'epoch': 7.22}

 60%|██████    | 16906/28080 [33:24:57<22:06:39,  7.12s/it]
 60%|██████    | 16907/28080 [33:25:04<22:05:14,  7.12s/it]
                                                           
{'loss': 0.6053, 'learning_rate': 0.00018041367630706106, 'epoch': 7.22}

 60%|██████    | 16907/28080 [33:25:04<22:05:14,  7.12s/it]
 60%|██████    | 16908/28080 [33:25:11<22:04:16,  7.11s/it]
                                                           
{'loss': 0.6222, 'learning_rate': 0.0001803859806187127, 'epoch': 7.22}

 60%|██████    | 16908/28080 [33:25:11<22:04:16,  7.11s/it]
 60%|██████    | 16909/28080 [33:25:18<22:02:32,  7.10s/it]
                                                           
{'loss': 0.6183, 'learning_rate': 0.00018035828585650704, 'epoch': 7.22}

 60%|██████    | 16909/28080 [33:25:18<22:02:32,  7.10s/it]
 60%|██████    | 16910/28080 [33:25:25<22:06:18,  7.12s/it]
                                                           
{'loss': 0.6168, 'learning_rate': 0.00018033059202081253, 'epoch': 7.22}

 60%|██████    | 16910/28080 [33:25:25<22:06:18,  7.12s/it]
 60%|██████    | 16911/28080 [33:25:32<22:03:35,  7.11s/it]
                                                           
{'loss': 0.5878, 'learning_rate': 0.00018030289911199766, 'epoch': 7.22}

 60%|██████    | 16911/28080 [33:25:32<22:03:35,  7.11s/it]
 60%|██████    | 16912/28080 [33:25:40<22:04:34,  7.12s/it]
                                                           
{'loss': 0.5966, 'learning_rate': 0.00018027520713043079, 'epoch': 7.22}

 60%|██████    | 16912/28080 [33:25:40<22:04:34,  7.12s/it]
 60%|██████    | 16913/28080 [33:25:47<22:02:22,  7.11s/it]
                                                           
{'loss': 0.6179, 'learning_rate': 0.00018024751607648035, 'epoch': 7.23}

 60%|██████    | 16913/28080 [33:25:47<22:02:22,  7.11s/it]
 60%|██████    | 16914/28080 [33:25:54<22:06:35,  7.13s/it]
                                                           
{'loss': 0.5984, 'learning_rate': 0.00018021982595051468, 'epoch': 7.23}

 60%|██████    | 16914/28080 [33:25:54<22:06:35,  7.13s/it]
 60%|██████    | 16915/28080 [33:26:01<22:05:18,  7.12s/it]
                                                           
{'loss': 0.6346, 'learning_rate': 0.00018019213675290238, 'epoch': 7.23}

 60%|██████    | 16915/28080 [33:26:01<22:05:18,  7.12s/it]
 60%|██████    | 16916/28080 [33:26:08<22:05:36,  7.12s/it]
                                                           
{'loss': 0.603, 'learning_rate': 0.00018016444848401153, 'epoch': 7.23}

 60%|██████    | 16916/28080 [33:26:08<22:05:36,  7.12s/it]
 60%|██████    | 16917/28080 [33:26:15<22:01:28,  7.10s/it]
                                                           
{'loss': 0.6229, 'learning_rate': 0.00018013676114421082, 'epoch': 7.23}

 60%|██████    | 16917/28080 [33:26:15<22:01:28,  7.10s/it]
 60%|██████    | 16918/28080 [33:26:22<22:01:40,  7.10s/it]
                                                           
{'loss': 0.6036, 'learning_rate': 0.00018010907473386826, 'epoch': 7.23}

 60%|██████    | 16918/28080 [33:26:22<22:01:40,  7.10s/it]
 60%|██████    | 16919/28080 [33:26:29<22:03:49,  7.12s/it]
                                                           
{'loss': 0.6236, 'learning_rate': 0.00018008138925335246, 'epoch': 7.23}

 60%|██████    | 16919/28080 [33:26:29<22:03:49,  7.12s/it]
 60%|██████    | 16920/28080 [33:26:36<22:01:47,  7.11s/it]
                                                           
{'loss': 0.6056, 'learning_rate': 0.0001800537047030316, 'epoch': 7.23}

 60%|██████    | 16920/28080 [33:26:36<22:01:47,  7.11s/it]
 60%|██████    | 16921/28080 [33:26:44<22:04:08,  7.12s/it]
                                                           
{'loss': 0.6033, 'learning_rate': 0.00018002602108327408, 'epoch': 7.23}

 60%|██████    | 16921/28080 [33:26:44<22:04:08,  7.12s/it]
 60%|██████    | 16922/28080 [33:26:51<22:00:49,  7.10s/it]
                                                           
{'loss': 0.6033, 'learning_rate': 0.00017999833839444818, 'epoch': 7.23}

 60%|██████    | 16922/28080 [33:26:51<22:00:49,  7.10s/it]
 60%|██████    | 16923/28080 [33:26:58<21:58:39,  7.09s/it]
                                                           
{'loss': 0.602, 'learning_rate': 0.0001799706566369221, 'epoch': 7.23}

 60%|██████    | 16923/28080 [33:26:58<21:58:39,  7.09s/it]
 60%|██████    | 16924/28080 [33:27:05<22:01:29,  7.11s/it]
                                                           
{'loss': 0.6161, 'learning_rate': 0.00017994297581106424, 'epoch': 7.23}

 60%|██████    | 16924/28080 [33:27:05<22:01:29,  7.11s/it]
 60%|██████    | 16925/28080 [33:27:12<22:02:04,  7.11s/it]
                                                           
{'loss': 0.6151, 'learning_rate': 0.00017991529591724278, 'epoch': 7.23}

 60%|██████    | 16925/28080 [33:27:12<22:02:04,  7.11s/it]
 60%|██████    | 16926/28080 [33:27:19<22:02:44,  7.12s/it]
                                                           
{'loss': 0.6046, 'learning_rate': 0.00017988761695582605, 'epoch': 7.23}

 60%|██████    | 16926/28080 [33:27:19<22:02:44,  7.12s/it]
 60%|██████    | 16927/28080 [33:27:26<22:03:18,  7.12s/it]
                                                           
{'loss': 0.6038, 'learning_rate': 0.0001798599389271822, 'epoch': 7.23}

 60%|██████    | 16927/28080 [33:27:26<22:03:18,  7.12s/it]
 60%|██████    | 16928/28080 [33:27:33<22:06:17,  7.14s/it]
                                                           
{'loss': 0.5961, 'learning_rate': 0.00017983226183167954, 'epoch': 7.23}

 60%|██████    | 16928/28080 [33:27:33<22:06:17,  7.14s/it]
 60%|██████    | 16929/28080 [33:27:40<21:57:02,  7.09s/it]
                                                           
{'loss': 0.6128, 'learning_rate': 0.0001798045856696862, 'epoch': 7.23}

 60%|██████    | 16929/28080 [33:27:40<21:57:02,  7.09s/it]
 60%|██████    | 16930/28080 [33:27:48<22:02:00,  7.11s/it]
                                                           
{'loss': 0.6159, 'learning_rate': 0.0001797769104415705, 'epoch': 7.23}

 60%|██████    | 16930/28080 [33:27:48<22:02:00,  7.11s/it]
 60%|██████    | 16931/28080 [33:27:55<21:58:46,  7.10s/it]
                                                           
{'loss': 0.643, 'learning_rate': 0.0001797492361477005, 'epoch': 7.23}

 60%|██████    | 16931/28080 [33:27:55<21:58:46,  7.10s/it]
 60%|██████    | 16932/28080 [33:28:02<22:00:44,  7.11s/it]
                                                           
{'loss': 0.6104, 'learning_rate': 0.0001797215627884445, 'epoch': 7.23}

 60%|██████    | 16932/28080 [33:28:02<22:00:44,  7.11s/it]
 60%|██████    | 16933/28080 [33:28:09<22:04:22,  7.13s/it]
                                                           
{'loss': 0.6045, 'learning_rate': 0.00017969389036417044, 'epoch': 7.23}

 60%|██████    | 16933/28080 [33:28:09<22:04:22,  7.13s/it]
 60%|██████    | 16934/28080 [33:28:16<22:05:30,  7.14s/it]
                                                           
{'loss': 0.5879, 'learning_rate': 0.00017966621887524688, 'epoch': 7.23}

 60%|██████    | 16934/28080 [33:28:16<22:05:30,  7.14s/it]
 60%|██████    | 16935/28080 [33:28:23<22:06:18,  7.14s/it]
                                                           
{'loss': 0.6002, 'learning_rate': 0.00017963854832204153, 'epoch': 7.23}

 60%|██████    | 16935/28080 [33:28:23<22:06:18,  7.14s/it]
 60%|██████    | 16936/28080 [33:28:30<22:00:30,  7.11s/it]
                                                           
{'loss': 0.6177, 'learning_rate': 0.00017961087870492276, 'epoch': 7.23}

 60%|██████    | 16936/28080 [33:28:30<22:00:30,  7.11s/it]
 60%|██████    | 16937/28080 [33:28:37<21:56:46,  7.09s/it]
                                                           
{'loss': 0.6103, 'learning_rate': 0.00017958321002425865, 'epoch': 7.24}

 60%|██████    | 16937/28080 [33:28:37<21:56:46,  7.09s/it]
 60%|██████    | 16938/28080 [33:28:44<21:53:34,  7.07s/it]
                                                           
{'loss': 0.622, 'learning_rate': 0.00017955554228041732, 'epoch': 7.24}

 60%|██████    | 16938/28080 [33:28:44<21:53:34,  7.07s/it]
 60%|██████    | 16939/28080 [33:28:51<21:51:49,  7.06s/it]
                                                           
{'loss': 0.6058, 'learning_rate': 0.00017952787547376677, 'epoch': 7.24}

 60%|██████    | 16939/28080 [33:28:51<21:51:49,  7.06s/it]
 60%|██████    | 16940/28080 [33:28:58<21:52:04,  7.07s/it]
                                                           
{'loss': 0.6243, 'learning_rate': 0.00017950020960467517, 'epoch': 7.24}

 60%|██████    | 16940/28080 [33:28:58<21:52:04,  7.07s/it]
 60%|██████    | 16941/28080 [33:29:06<21:58:08,  7.10s/it]
                                                           
{'loss': 0.6064, 'learning_rate': 0.00017947254467351052, 'epoch': 7.24}

 60%|██████    | 16941/28080 [33:29:06<21:58:08,  7.10s/it]
 60%|██████    | 16942/28080 [33:29:13<21:58:28,  7.10s/it]
                                                           
{'loss': 0.6408, 'learning_rate': 0.00017944488068064095, 'epoch': 7.24}

 60%|██████    | 16942/28080 [33:29:13<21:58:28,  7.10s/it]
 60%|██████    | 16943/28080 [33:29:20<21:57:06,  7.10s/it]
                                                           
{'loss': 0.629, 'learning_rate': 0.00017941721762643436, 'epoch': 7.24}

 60%|██████    | 16943/28080 [33:29:20<21:57:06,  7.10s/it]
 60%|██████    | 16944/28080 [33:29:27<21:53:25,  7.08s/it]
                                                           
{'loss': 0.5927, 'learning_rate': 0.000179389555511259, 'epoch': 7.24}

 60%|██████    | 16944/28080 [33:29:27<21:53:25,  7.08s/it]
 60%|██████    | 16945/28080 [33:29:34<21:48:29,  7.05s/it]
                                                           
{'loss': 0.6352, 'learning_rate': 0.0001793618943354826, 'epoch': 7.24}

 60%|██████    | 16945/28080 [33:29:34<21:48:29,  7.05s/it]
 60%|██████    | 16946/28080 [33:29:41<21:48:16,  7.05s/it]
                                                           
{'loss': 0.6202, 'learning_rate': 0.00017933423409947352, 'epoch': 7.24}

 60%|██████    | 16946/28080 [33:29:41<21:48:16,  7.05s/it]
 60%|██████    | 16947/28080 [33:29:48<21:56:16,  7.09s/it]
                                                           
{'loss': 0.6184, 'learning_rate': 0.00017930657480359947, 'epoch': 7.24}

 60%|██████    | 16947/28080 [33:29:48<21:56:16,  7.09s/it]
 60%|██████    | 16948/28080 [33:29:55<22:00:06,  7.12s/it]
                                                           
{'loss': 0.6234, 'learning_rate': 0.00017927891644822848, 'epoch': 7.24}

 60%|██████    | 16948/28080 [33:29:55<22:00:06,  7.12s/it]
 60%|██████    | 16949/28080 [33:30:02<22:00:17,  7.12s/it]
                                                           
{'loss': 0.6011, 'learning_rate': 0.00017925125903372858, 'epoch': 7.24}

 60%|██████    | 16949/28080 [33:30:02<22:00:17,  7.12s/it]
 60%|██████    | 16950/28080 [33:30:10<22:01:54,  7.13s/it]
                                                           
{'loss': 0.6188, 'learning_rate': 0.00017922360256046762, 'epoch': 7.24}

 60%|██████    | 16950/28080 [33:30:10<22:01:54,  7.13s/it]
 60%|██████    | 16951/28080 [33:30:17<22:06:40,  7.15s/it]
                                                           
{'loss': 0.5931, 'learning_rate': 0.00017919594702881376, 'epoch': 7.24}

 60%|██████    | 16951/28080 [33:30:17<22:06:40,  7.15s/it]
 60%|██████    | 16952/28080 [33:30:24<22:06:29,  7.15s/it]
                                                           
{'loss': 0.5925, 'learning_rate': 0.00017916829243913457, 'epoch': 7.24}

 60%|██████    | 16952/28080 [33:30:24<22:06:29,  7.15s/it]
 60%|██████    | 16953/28080 [33:30:31<22:02:05,  7.13s/it]
                                                           
{'loss': 0.6398, 'learning_rate': 0.00017914063879179832, 'epoch': 7.24}

 60%|██████    | 16953/28080 [33:30:31<22:02:05,  7.13s/it]
 60%|██████    | 16954/28080 [33:30:38<22:01:16,  7.13s/it]
                                                           
{'loss': 0.6179, 'learning_rate': 0.00017911298608717273, 'epoch': 7.24}

 60%|██████    | 16954/28080 [33:30:38<22:01:16,  7.13s/it]
 60%|██████    | 16955/28080 [33:30:45<22:01:44,  7.13s/it]
                                                           
{'loss': 0.6086, 'learning_rate': 0.0001790853343256258, 'epoch': 7.24}

 60%|██████    | 16955/28080 [33:30:45<22:01:44,  7.13s/it]
 60%|██████    | 16956/28080 [33:30:52<22:03:05,  7.14s/it]
                                                           
{'loss': 0.6051, 'learning_rate': 0.00017905768350752523, 'epoch': 7.24}

 60%|██████    | 16956/28080 [33:30:52<22:03:05,  7.14s/it]
 60%|██████    | 16957/28080 [33:30:59<21:56:05,  7.10s/it]
                                                           
{'loss': 0.6236, 'learning_rate': 0.00017903003363323904, 'epoch': 7.24}

 60%|██████    | 16957/28080 [33:30:59<21:56:05,  7.10s/it]
 60%|██████    | 16958/28080 [33:31:06<21:48:57,  7.06s/it]
                                                           
{'loss': 0.6329, 'learning_rate': 0.00017900238470313506, 'epoch': 7.24}

 60%|██████    | 16958/28080 [33:31:06<21:48:57,  7.06s/it]
 60%|██████    | 16959/28080 [33:31:14<21:55:56,  7.10s/it]
                                                           
{'loss': 0.6108, 'learning_rate': 0.0001789747367175811, 'epoch': 7.24}

 60%|██████    | 16959/28080 [33:31:14<21:55:56,  7.10s/it]
 60%|██████    | 16960/28080 [33:31:21<21:49:45,  7.07s/it]
                                                           
{'loss': 0.6261, 'learning_rate': 0.00017894708967694495, 'epoch': 7.25}

 60%|██████    | 16960/28080 [33:31:21<21:49:45,  7.07s/it]
 60%|██████    | 16961/28080 [33:31:28<21:54:34,  7.09s/it]
                                                           
{'loss': 0.6009, 'learning_rate': 0.00017891944358159456, 'epoch': 7.25}

 60%|██████    | 16961/28080 [33:31:28<21:54:34,  7.09s/it]
 60%|██████    | 16962/28080 [33:31:35<21:53:05,  7.09s/it]
                                                           
{'loss': 0.6112, 'learning_rate': 0.00017889179843189756, 'epoch': 7.25}

 60%|██████    | 16962/28080 [33:31:35<21:53:05,  7.09s/it]
 60%|██████    | 16963/28080 [33:31:42<21:56:50,  7.11s/it]
                                                           
{'loss': 0.621, 'learning_rate': 0.0001788641542282219, 'epoch': 7.25}

 60%|██████    | 16963/28080 [33:31:42<21:56:50,  7.11s/it]
 60%|██████    | 16964/28080 [33:31:49<21:56:52,  7.11s/it]
                                                           
{'loss': 0.6115, 'learning_rate': 0.0001788365109709351, 'epoch': 7.25}

 60%|██████    | 16964/28080 [33:31:49<21:56:52,  7.11s/it]
 60%|██████    | 16965/28080 [33:31:56<22:00:19,  7.13s/it]
                                                           
{'loss': 0.611, 'learning_rate': 0.00017880886866040535, 'epoch': 7.25}

 60%|██████    | 16965/28080 [33:31:56<22:00:19,  7.13s/it]
 60%|██████    | 16966/28080 [33:32:03<21:51:30,  7.08s/it]
                                                           
{'loss': 0.6075, 'learning_rate': 0.00017878122729699997, 'epoch': 7.25}

 60%|██████    | 16966/28080 [33:32:03<21:51:30,  7.08s/it]
 60%|██████    | 16967/28080 [33:32:10<21:49:08,  7.07s/it]
                                                           
{'loss': 0.6222, 'learning_rate': 0.000178753586881087, 'epoch': 7.25}

 60%|██████    | 16967/28080 [33:32:10<21:49:08,  7.07s/it]
 60%|██████    | 16968/28080 [33:32:17<21:51:28,  7.08s/it]
                                                           
{'loss': 0.6125, 'learning_rate': 0.000178725947413034, 'epoch': 7.25}

 60%|██████    | 16968/28080 [33:32:17<21:51:28,  7.08s/it]
 60%|██████    | 16969/28080 [33:32:24<21:53:55,  7.10s/it]
                                                           
{'loss': 0.6273, 'learning_rate': 0.00017869830889320876, 'epoch': 7.25}

 60%|██████    | 16969/28080 [33:32:24<21:53:55,  7.10s/it]
 60%|██████    | 16970/28080 [33:32:32<21:59:51,  7.13s/it]
                                                           
{'loss': 0.6105, 'learning_rate': 0.00017867067132197896, 'epoch': 7.25}

 60%|██████    | 16970/28080 [33:32:32<21:59:51,  7.13s/it]
 60%|██████    | 16971/28080 [33:32:39<22:03:26,  7.15s/it]
                                                           
{'loss': 0.6249, 'learning_rate': 0.00017864303469971232, 'epoch': 7.25}

 60%|██████    | 16971/28080 [33:32:39<22:03:26,  7.15s/it]
 60%|██████    | 16972/28080 [33:32:46<22:11:16,  7.19s/it]
                                                           
{'loss': 0.5991, 'learning_rate': 0.0001786153990267765, 'epoch': 7.25}

 60%|██████    | 16972/28080 [33:32:46<22:11:16,  7.19s/it]
 60%|██████    | 16973/28080 [33:32:53<22:07:19,  7.17s/it]
                                                           
{'loss': 0.6077, 'learning_rate': 0.0001785877643035391, 'epoch': 7.25}

 60%|██████    | 16973/28080 [33:32:53<22:07:19,  7.17s/it]
 60%|██████    | 16974/28080 [33:33:00<22:02:38,  7.15s/it]
                                                           
{'loss': 0.5881, 'learning_rate': 0.00017856013053036784, 'epoch': 7.25}

 60%|██████    | 16974/28080 [33:33:00<22:02:38,  7.15s/it]
 60%|██████    | 16975/28080 [33:33:07<21:59:38,  7.13s/it]
                                                           
{'loss': 0.6213, 'learning_rate': 0.00017853249770763036, 'epoch': 7.25}

 60%|██████    | 16975/28080 [33:33:07<21:59:38,  7.13s/it]
 60%|██████    | 16976/28080 [33:33:15<22:00:09,  7.13s/it]
                                                           
{'loss': 0.6159, 'learning_rate': 0.00017850486583569425, 'epoch': 7.25}

 60%|██████    | 16976/28080 [33:33:15<22:00:09,  7.13s/it]
 60%|██████    | 16977/28080 [33:33:22<22:00:15,  7.13s/it]
                                                           
{'loss': 0.6378, 'learning_rate': 0.00017847723491492713, 'epoch': 7.25}

 60%|██████    | 16977/28080 [33:33:22<22:00:15,  7.13s/it]
 60%|██████    | 16978/28080 [33:33:29<21:55:10,  7.11s/it]
                                                           
{'loss': 0.6418, 'learning_rate': 0.00017844960494569668, 'epoch': 7.25}

 60%|██████    | 16978/28080 [33:33:29<21:55:10,  7.11s/it]
 60%|██████    | 16979/28080 [33:33:36<21:53:22,  7.10s/it]
                                                           
{'loss': 0.6258, 'learning_rate': 0.00017842197592837035, 'epoch': 7.25}

 60%|██████    | 16979/28080 [33:33:36<21:53:22,  7.10s/it]
 60%|██████    | 16980/28080 [33:33:43<22:01:43,  7.14s/it]
                                                           
{'loss': 0.6106, 'learning_rate': 0.00017839434786331583, 'epoch': 7.25}

 60%|██████    | 16980/28080 [33:33:43<22:01:43,  7.14s/it]
 60%|██████    | 16981/28080 [33:33:50<22:04:10,  7.16s/it]
                                                           
{'loss': 0.6103, 'learning_rate': 0.00017836672075090054, 'epoch': 7.25}

 60%|██████    | 16981/28080 [33:33:50<22:04:10,  7.16s/it]
 60%|██████    | 16982/28080 [33:33:57<22:03:04,  7.15s/it]
                                                           
{'loss': 0.6045, 'learning_rate': 0.0001783390945914923, 'epoch': 7.25}

 60%|██████    | 16982/28080 [33:33:57<22:03:04,  7.15s/it]
 60%|██████    | 16983/28080 [33:34:04<21:55:09,  7.11s/it]
                                                           
{'loss': 0.6259, 'learning_rate': 0.00017831146938545827, 'epoch': 7.25}

 60%|██████    | 16983/28080 [33:34:04<21:55:09,  7.11s/it]
 60%|██████    | 16984/28080 [33:34:12<21:59:21,  7.13s/it]
                                                           
{'loss': 0.62, 'learning_rate': 0.00017828384513316633, 'epoch': 7.26}

 60%|██████    | 16984/28080 [33:34:12<21:59:21,  7.13s/it]
 60%|██████    | 16985/28080 [33:34:19<22:01:17,  7.15s/it]
                                                           
{'loss': 0.6246, 'learning_rate': 0.0001782562218349838, 'epoch': 7.26}

 60%|██████    | 16985/28080 [33:34:19<22:01:17,  7.15s/it]
 60%|██████    | 16986/28080 [33:34:26<21:58:27,  7.13s/it]
                                                           
{'loss': 0.6367, 'learning_rate': 0.0001782285994912783, 'epoch': 7.26}

 60%|██████    | 16986/28080 [33:34:26<21:58:27,  7.13s/it]
 60%|██████    | 16987/28080 [33:34:33<22:01:13,  7.15s/it]
                                                           
{'loss': 0.6046, 'learning_rate': 0.00017820097810241714, 'epoch': 7.26}

 60%|██████    | 16987/28080 [33:34:33<22:01:13,  7.15s/it]
 60%|██████    | 16988/28080 [33:34:40<21:58:05,  7.13s/it]
                                                           
{'loss': 0.6156, 'learning_rate': 0.00017817335766876798, 'epoch': 7.26}

 60%|██████    | 16988/28080 [33:34:40<21:58:05,  7.13s/it]
 61%|██████    | 16989/28080 [33:34:47<22:01:04,  7.15s/it]
                                                           
{'loss': 0.615, 'learning_rate': 0.0001781457381906981, 'epoch': 7.26}

 61%|██████    | 16989/28080 [33:34:47<22:01:04,  7.15s/it]
 61%|██████    | 16990/28080 [33:34:55<22:02:39,  7.16s/it]
                                                           
{'loss': 0.5966, 'learning_rate': 0.00017811811966857513, 'epoch': 7.26}

 61%|██████    | 16990/28080 [33:34:55<22:02:39,  7.16s/it]
 61%|██████    | 16991/28080 [33:35:01<21:51:43,  7.10s/it]
                                                           
{'loss': 0.6124, 'learning_rate': 0.00017809050210276637, 'epoch': 7.26}

 61%|██████    | 16991/28080 [33:35:02<21:51:43,  7.10s/it]
 61%|██████    | 16992/28080 [33:35:09<21:53:29,  7.11s/it]
                                                           
{'loss': 0.6064, 'learning_rate': 0.00017806288549363934, 'epoch': 7.26}

 61%|██████    | 16992/28080 [33:35:09<21:53:29,  7.11s/it]
 61%|██████    | 16993/28080 [33:35:16<21:53:02,  7.11s/it]
                                                           
{'loss': 0.596, 'learning_rate': 0.00017803526984156134, 'epoch': 7.26}

 61%|██████    | 16993/28080 [33:35:16<21:53:02,  7.11s/it]
 61%|██████    | 16994/28080 [33:35:23<21:54:24,  7.11s/it]
                                                           
{'loss': 0.6149, 'learning_rate': 0.00017800765514689994, 'epoch': 7.26}

 61%|██████    | 16994/28080 [33:35:23<21:54:24,  7.11s/it]
 61%|██████    | 16995/28080 [33:35:30<21:55:58,  7.12s/it]
                                                           
{'loss': 0.6136, 'learning_rate': 0.00017798004141002225, 'epoch': 7.26}

 61%|██████    | 16995/28080 [33:35:30<21:55:58,  7.12s/it]
 61%|██████    | 16996/28080 [33:35:37<22:00:52,  7.15s/it]
                                                           
{'loss': 0.6075, 'learning_rate': 0.00017795242863129598, 'epoch': 7.26}

 61%|██████    | 16996/28080 [33:35:37<22:00:52,  7.15s/it]
 61%|██████    | 16997/28080 [33:35:44<22:04:08,  7.17s/it]
                                                           
{'loss': 0.6093, 'learning_rate': 0.0001779248168110883, 'epoch': 7.26}

 61%|██████    | 16997/28080 [33:35:44<22:04:08,  7.17s/it]
 61%|██████    | 16998/28080 [33:35:52<22:01:58,  7.16s/it]
                                                           
{'loss': 0.6136, 'learning_rate': 0.00017789720594976643, 'epoch': 7.26}

 61%|██████    | 16998/28080 [33:35:52<22:01:58,  7.16s/it]
 61%|██████    | 16999/28080 [33:35:59<21:55:54,  7.13s/it]
                                                           
{'loss': 0.6228, 'learning_rate': 0.00017786959604769803, 'epoch': 7.26}

 61%|██████    | 16999/28080 [33:35:59<21:55:54,  7.13s/it]
 61%|██████    | 17000/28080 [33:36:06<21:58:19,  7.14s/it]
                                                           
{'loss': 0.5891, 'learning_rate': 0.00017784198710525006, 'epoch': 7.26}

 61%|██████    | 17000/28080 [33:36:06<21:58:19,  7.14s/it]
 61%|██████    | 17001/28080 [33:36:13<21:57:14,  7.13s/it]
                                                           
{'loss': 0.6189, 'learning_rate': 0.00017781437912279017, 'epoch': 7.26}

 61%|██████    | 17001/28080 [33:36:13<21:57:14,  7.13s/it]
 61%|██████    | 17002/28080 [33:36:20<21:58:05,  7.14s/it]
                                                           
{'loss': 0.6388, 'learning_rate': 0.0001777867721006854, 'epoch': 7.26}

 61%|██████    | 17002/28080 [33:36:20<21:58:05,  7.14s/it]
 61%|██████    | 17003/28080 [33:36:27<21:58:22,  7.14s/it]
                                                           
{'loss': 0.601, 'learning_rate': 0.0001777591660393032, 'epoch': 7.26}

 61%|██████    | 17003/28080 [33:36:27<21:58:22,  7.14s/it]
 61%|██████    | 17004/28080 [33:36:34<21:59:33,  7.15s/it]
                                                           
{'loss': 0.6251, 'learning_rate': 0.00017773156093901072, 'epoch': 7.26}

 61%|██████    | 17004/28080 [33:36:34<21:59:33,  7.15s/it]
 61%|██████    | 17005/28080 [33:36:41<21:57:12,  7.14s/it]
                                                           
{'loss': 0.6078, 'learning_rate': 0.0001777039568001753, 'epoch': 7.26}

 61%|██████    | 17005/28080 [33:36:41<21:57:12,  7.14s/it]
 61%|██████    | 17006/28080 [33:36:49<22:00:32,  7.15s/it]
                                                           
{'loss': 0.6073, 'learning_rate': 0.0001776763536231641, 'epoch': 7.26}

 61%|██████    | 17006/28080 [33:36:49<22:00:32,  7.15s/it]
 61%|██████    | 17007/28080 [33:36:56<21:56:24,  7.13s/it]
                                                           
{'loss': 0.6134, 'learning_rate': 0.00017764875140834446, 'epoch': 7.27}

 61%|██████    | 17007/28080 [33:36:56<21:56:24,  7.13s/it]
 61%|██████    | 17008/28080 [33:37:03<21:55:34,  7.13s/it]
                                                           
{'loss': 0.5995, 'learning_rate': 0.0001776211501560835, 'epoch': 7.27}

 61%|██████    | 17008/28080 [33:37:03<21:55:34,  7.13s/it]
 61%|██████    | 17009/28080 [33:37:10<21:53:40,  7.12s/it]
                                                           
{'loss': 0.6237, 'learning_rate': 0.00017759354986674852, 'epoch': 7.27}

 61%|██████    | 17009/28080 [33:37:10<21:53:40,  7.12s/it]
 61%|██████    | 17010/28080 [33:37:17<21:52:37,  7.11s/it]
                                                           
{'loss': 0.6203, 'learning_rate': 0.00017756595054070658, 'epoch': 7.27}

 61%|██████    | 17010/28080 [33:37:17<21:52:37,  7.11s/it]
 61%|██████    | 17011/28080 [33:37:24<21:52:00,  7.11s/it]
                                                           
{'loss': 0.6284, 'learning_rate': 0.00017753835217832503, 'epoch': 7.27}

 61%|██████    | 17011/28080 [33:37:24<21:52:00,  7.11s/it]
 61%|██████    | 17012/28080 [33:37:31<21:55:31,  7.13s/it]
                                                           
{'loss': 0.6243, 'learning_rate': 0.0001775107547799708, 'epoch': 7.27}

 61%|██████    | 17012/28080 [33:37:31<21:55:31,  7.13s/it]
 61%|██████    | 17013/28080 [33:37:38<21:55:06,  7.13s/it]
                                                           
{'loss': 0.5913, 'learning_rate': 0.00017748315834601141, 'epoch': 7.27}

 61%|██████    | 17013/28080 [33:37:38<21:55:06,  7.13s/it]
 61%|██████    | 17014/28080 [33:37:46<21:53:31,  7.12s/it]
                                                           
{'loss': 0.6247, 'learning_rate': 0.00017745556287681357, 'epoch': 7.27}

 61%|██████    | 17014/28080 [33:37:46<21:53:31,  7.12s/it]
 61%|██████    | 17015/28080 [33:37:53<21:56:31,  7.14s/it]
                                                           
{'loss': 0.6081, 'learning_rate': 0.00017742796837274478, 'epoch': 7.27}

 61%|██████    | 17015/28080 [33:37:53<21:56:31,  7.14s/it]
 61%|██████    | 17016/28080 [33:38:00<21:54:26,  7.13s/it]
                                                           
{'loss': 0.602, 'learning_rate': 0.00017740037483417192, 'epoch': 7.27}

 61%|██████    | 17016/28080 [33:38:00<21:54:26,  7.13s/it]
 61%|██████    | 17017/28080 [33:38:07<22:04:52,  7.19s/it]
                                                           
{'loss': 0.5974, 'learning_rate': 0.00017737278226146225, 'epoch': 7.27}

 61%|██████    | 17017/28080 [33:38:07<22:04:52,  7.19s/it]
 61%|██████    | 17018/28080 [33:38:14<22:04:46,  7.19s/it]
                                                           
{'loss': 0.6045, 'learning_rate': 0.00017734519065498272, 'epoch': 7.27}

 61%|██████    | 17018/28080 [33:38:14<22:04:46,  7.19s/it]
 61%|██████    | 17019/28080 [33:38:22<22:04:15,  7.18s/it]
                                                           
{'loss': 0.6097, 'learning_rate': 0.00017731760001510056, 'epoch': 7.27}

 61%|██████    | 17019/28080 [33:38:22<22:04:15,  7.18s/it]
 61%|██████    | 17020/28080 [33:38:29<22:03:06,  7.18s/it]
                                                           
{'loss': 0.6364, 'learning_rate': 0.00017729001034218268, 'epoch': 7.27}

 61%|██████    | 17020/28080 [33:38:29<22:03:06,  7.18s/it]
 61%|██████    | 17021/28080 [33:38:36<22:00:03,  7.16s/it]
                                                           
{'loss': 0.6063, 'learning_rate': 0.00017726242163659624, 'epoch': 7.27}

 61%|██████    | 17021/28080 [33:38:36<22:00:03,  7.16s/it]
 61%|██████    | 17022/28080 [33:38:43<21:55:01,  7.14s/it]
                                                           
{'loss': 0.5969, 'learning_rate': 0.00017723483389870824, 'epoch': 7.27}

 61%|██████    | 17022/28080 [33:38:43<21:55:01,  7.14s/it]
 61%|██████    | 17023/28080 [33:38:50<21:59:04,  7.16s/it]
                                                           
{'loss': 0.596, 'learning_rate': 0.00017720724712888563, 'epoch': 7.27}

 61%|██████    | 17023/28080 [33:38:50<21:59:04,  7.16s/it]
 61%|██████    | 17024/28080 [33:38:57<21:58:26,  7.16s/it]
                                                           
{'loss': 0.6293, 'learning_rate': 0.0001771796613274956, 'epoch': 7.27}

 61%|██████    | 17024/28080 [33:38:57<21:58:26,  7.16s/it]
 61%|██████    | 17025/28080 [33:39:04<21:55:44,  7.14s/it]
                                                           
{'loss': 0.5955, 'learning_rate': 0.000177152076494905, 'epoch': 7.27}

 61%|██████    | 17025/28080 [33:39:04<21:55:44,  7.14s/it]
 61%|██████    | 17026/28080 [33:39:12<21:57:00,  7.15s/it]
                                                           
{'loss': 0.6118, 'learning_rate': 0.0001771244926314809, 'epoch': 7.27}

 61%|██████    | 17026/28080 [33:39:12<21:57:00,  7.15s/it]
 61%|██████    | 17027/28080 [33:39:19<21:58:45,  7.16s/it]
                                                           
{'loss': 0.607, 'learning_rate': 0.00017709690973759018, 'epoch': 7.27}

 61%|██████    | 17027/28080 [33:39:19<21:58:45,  7.16s/it]
 61%|██████    | 17028/28080 [33:39:26<21:51:47,  7.12s/it]
                                                           
{'loss': 0.6313, 'learning_rate': 0.00017706932781359994, 'epoch': 7.27}

 61%|██████    | 17028/28080 [33:39:26<21:51:47,  7.12s/it]
 61%|██████    | 17029/28080 [33:39:33<21:51:31,  7.12s/it]
                                                           
{'loss': 0.6073, 'learning_rate': 0.00017704174685987696, 'epoch': 7.27}

 61%|██████    | 17029/28080 [33:39:33<21:51:31,  7.12s/it]
 61%|██████    | 17030/28080 [33:39:40<21:48:47,  7.11s/it]
                                                           
{'loss': 0.6101, 'learning_rate': 0.0001770141668767884, 'epoch': 7.28}

 61%|██████    | 17030/28080 [33:39:40<21:48:47,  7.11s/it]
 61%|██████    | 17031/28080 [33:39:47<21:53:49,  7.13s/it]
                                                           
{'loss': 0.6074, 'learning_rate': 0.0001769865878647009, 'epoch': 7.28}

 61%|██████    | 17031/28080 [33:39:47<21:53:49,  7.13s/it]
 61%|██████    | 17032/28080 [33:39:54<21:51:11,  7.12s/it]
                                                           
{'loss': 0.6278, 'learning_rate': 0.00017695900982398163, 'epoch': 7.28}

 61%|██████    | 17032/28080 [33:39:54<21:51:11,  7.12s/it]
 61%|██████    | 17033/28080 [33:40:01<21:56:28,  7.15s/it]
                                                           
{'loss': 0.61, 'learning_rate': 0.00017693143275499735, 'epoch': 7.28}

 61%|██████    | 17033/28080 [33:40:01<21:56:28,  7.15s/it]
 61%|██████    | 17034/28080 [33:40:09<22:00:46,  7.17s/it]
                                                           
{'loss': 0.6138, 'learning_rate': 0.00017690385665811503, 'epoch': 7.28}

 61%|██████    | 17034/28080 [33:40:09<22:00:46,  7.17s/it]
 61%|██████    | 17035/28080 [33:40:16<22:01:43,  7.18s/it]
                                                           
{'loss': 0.6084, 'learning_rate': 0.0001768762815337014, 'epoch': 7.28}

 61%|██████    | 17035/28080 [33:40:16<22:01:43,  7.18s/it]
 61%|██████    | 17036/28080 [33:40:23<21:58:14,  7.16s/it]
                                                           
{'loss': 0.6068, 'learning_rate': 0.0001768487073821235, 'epoch': 7.28}

 61%|██████    | 17036/28080 [33:40:23<21:58:14,  7.16s/it]
 61%|██████    | 17037/28080 [33:40:30<21:56:12,  7.15s/it]
                                                           
{'loss': 0.6237, 'learning_rate': 0.00017682113420374802, 'epoch': 7.28}

 61%|██████    | 17037/28080 [33:40:30<21:56:12,  7.15s/it]
 61%|██████    | 17038/28080 [33:40:37<21:58:08,  7.16s/it]
                                                           
{'loss': 0.596, 'learning_rate': 0.00017679356199894186, 'epoch': 7.28}

 61%|██████    | 17038/28080 [33:40:37<21:58:08,  7.16s/it]
 61%|██████    | 17039/28080 [33:40:44<21:55:47,  7.15s/it]
                                                           
{'loss': 0.6059, 'learning_rate': 0.00017676599076807184, 'epoch': 7.28}

 61%|██████    | 17039/28080 [33:40:44<21:55:47,  7.15s/it]
 61%|██████    | 17040/28080 [33:40:52<21:54:38,  7.14s/it]
                                                           
{'loss': 0.6155, 'learning_rate': 0.00017673842051150478, 'epoch': 7.28}

 61%|██████    | 17040/28080 [33:40:52<21:54:38,  7.14s/it]
 61%|██████    | 17041/28080 [33:40:59<21:56:46,  7.16s/it]
                                                           
{'loss': 0.6264, 'learning_rate': 0.00017671085122960745, 'epoch': 7.28}

 61%|██████    | 17041/28080 [33:40:59<21:56:46,  7.16s/it]
 61%|██████    | 17042/28080 [33:41:06<21:56:02,  7.15s/it]
                                                           
{'loss': 0.6079, 'learning_rate': 0.00017668328292274666, 'epoch': 7.28}

 61%|██████    | 17042/28080 [33:41:06<21:56:02,  7.15s/it]
 61%|██████    | 17043/28080 [33:41:13<21:53:30,  7.14s/it]
                                                           
{'loss': 0.6235, 'learning_rate': 0.000176655715591289, 'epoch': 7.28}

 61%|██████    | 17043/28080 [33:41:13<21:53:30,  7.14s/it]
 61%|██████    | 17044/28080 [33:41:20<21:52:56,  7.14s/it]
                                                           
{'loss': 0.6185, 'learning_rate': 0.00017662814923560162, 'epoch': 7.28}

 61%|██████    | 17044/28080 [33:41:20<21:52:56,  7.14s/it]
 61%|██████    | 17045/28080 [33:41:27<21:57:09,  7.16s/it]
                                                           
{'loss': 0.6153, 'learning_rate': 0.0001766005838560508, 'epoch': 7.28}

 61%|██████    | 17045/28080 [33:41:27<21:57:09,  7.16s/it]
 61%|██████    | 17046/28080 [33:41:34<21:51:38,  7.13s/it]
                                                           
{'loss': 0.6332, 'learning_rate': 0.00017657301945300363, 'epoch': 7.28}

 61%|██████    | 17046/28080 [33:41:34<21:51:38,  7.13s/it]
 61%|██████    | 17047/28080 [33:41:41<21:43:03,  7.09s/it]
                                                           
{'loss': 0.6301, 'learning_rate': 0.00017654545602682674, 'epoch': 7.28}

 61%|██████    | 17047/28080 [33:41:41<21:43:03,  7.09s/it]
 61%|██████    | 17048/28080 [33:41:49<21:47:26,  7.11s/it]
                                                           
{'loss': 0.6133, 'learning_rate': 0.0001765178935778866, 'epoch': 7.28}

 61%|██████    | 17048/28080 [33:41:49<21:47:26,  7.11s/it]
 61%|██████    | 17049/28080 [33:41:56<21:48:51,  7.12s/it]
                                                           
{'loss': 0.6192, 'learning_rate': 0.00017649033210655025, 'epoch': 7.28}

 61%|██████    | 17049/28080 [33:41:56<21:48:51,  7.12s/it]
 61%|██████    | 17050/28080 [33:42:03<21:45:06,  7.10s/it]
                                                           
{'loss': 0.6247, 'learning_rate': 0.00017646277161318402, 'epoch': 7.28}

 61%|██████    | 17050/28080 [33:42:03<21:45:06,  7.10s/it]
 61%|██████    | 17051/28080 [33:42:10<21:47:48,  7.11s/it]
                                                           
{'loss': 0.6021, 'learning_rate': 0.0001764352120981549, 'epoch': 7.28}

 61%|██████    | 17051/28080 [33:42:10<21:47:48,  7.11s/it]
 61%|██████    | 17052/28080 [33:42:17<21:47:13,  7.11s/it]
                                                           
{'loss': 0.6052, 'learning_rate': 0.0001764076535618293, 'epoch': 7.28}

 61%|██████    | 17052/28080 [33:42:17<21:47:13,  7.11s/it]
 61%|██████    | 17053/28080 [33:42:24<21:40:51,  7.08s/it]
                                                           
{'loss': 0.6218, 'learning_rate': 0.000176380096004574, 'epoch': 7.28}

 61%|██████    | 17053/28080 [33:42:24<21:40:51,  7.08s/it]
 61%|██████    | 17054/28080 [33:42:31<21:40:31,  7.08s/it]
                                                           
{'loss': 0.624, 'learning_rate': 0.00017635253942675552, 'epoch': 7.29}

 61%|██████    | 17054/28080 [33:42:31<21:40:31,  7.08s/it]
 61%|██████    | 17055/28080 [33:42:38<21:43:51,  7.10s/it]
                                                           
{'loss': 0.6023, 'learning_rate': 0.0001763249838287406, 'epoch': 7.29}

 61%|██████    | 17055/28080 [33:42:38<21:43:51,  7.10s/it]
 61%|██████    | 17056/28080 [33:42:45<21:52:35,  7.14s/it]
                                                           
{'loss': 0.6355, 'learning_rate': 0.0001762974292108957, 'epoch': 7.29}

 61%|██████    | 17056/28080 [33:42:46<21:52:35,  7.14s/it]
 61%|██████    | 17057/28080 [33:42:53<21:56:17,  7.16s/it]
                                                           
{'loss': 0.6221, 'learning_rate': 0.00017626987557358754, 'epoch': 7.29}

 61%|██████    | 17057/28080 [33:42:53<21:56:17,  7.16s/it]
 61%|██████    | 17058/28080 [33:43:00<21:58:20,  7.18s/it]
                                                           
{'loss': 0.6133, 'learning_rate': 0.0001762423229171825, 'epoch': 7.29}

 61%|██████    | 17058/28080 [33:43:00<21:58:20,  7.18s/it]
 61%|██████    | 17059/28080 [33:43:07<21:58:27,  7.18s/it]
                                                           
{'loss': 0.6098, 'learning_rate': 0.0001762147712420474, 'epoch': 7.29}

 61%|██████    | 17059/28080 [33:43:07<21:58:27,  7.18s/it]
 61%|██████    | 17060/28080 [33:43:14<21:56:58,  7.17s/it]
                                                           
{'loss': 0.6292, 'learning_rate': 0.00017618722054854848, 'epoch': 7.29}

 61%|██████    | 17060/28080 [33:43:14<21:56:58,  7.17s/it]
 61%|██████    | 17061/28080 [33:43:21<22:00:15,  7.19s/it]
                                                           
{'loss': 0.6021, 'learning_rate': 0.00017615967083705263, 'epoch': 7.29}

 61%|██████    | 17061/28080 [33:43:21<22:00:15,  7.19s/it]
 61%|██████    | 17062/28080 [33:43:29<22:02:08,  7.20s/it]
                                                           
{'loss': 0.6324, 'learning_rate': 0.00017613212210792603, 'epoch': 7.29}

 61%|██████    | 17062/28080 [33:43:29<22:02:08,  7.20s/it]
 61%|██████    | 17063/28080 [33:43:36<21:59:10,  7.18s/it]
                                                           
{'loss': 0.6104, 'learning_rate': 0.00017610457436153542, 'epoch': 7.29}

 61%|██████    | 17063/28080 [33:43:36<21:59:10,  7.18s/it]
 61%|██████    | 17064/28080 [33:43:43<22:01:25,  7.20s/it]
                                                           
{'loss': 0.6012, 'learning_rate': 0.0001760770275982472, 'epoch': 7.29}

 61%|██████    | 17064/28080 [33:43:43<22:01:25,  7.20s/it]
 61%|██████    | 17065/28080 [33:43:50<22:00:57,  7.20s/it]
                                                           
{'loss': 0.6067, 'learning_rate': 0.00017604948181842788, 'epoch': 7.29}

 61%|██████    | 17065/28080 [33:43:50<22:00:57,  7.20s/it]
 61%|██████    | 17066/28080 [33:43:57<21:51:30,  7.14s/it]
                                                           
{'loss': 0.6012, 'learning_rate': 0.0001760219370224439, 'epoch': 7.29}

 61%|██████    | 17066/28080 [33:43:57<21:51:30,  7.14s/it]
 61%|██████    | 17067/28080 [33:44:04<21:48:47,  7.13s/it]
                                                           
{'loss': 0.6176, 'learning_rate': 0.00017599439321066177, 'epoch': 7.29}

 61%|██████    | 17067/28080 [33:44:04<21:48:47,  7.13s/it]
 61%|██████    | 17068/28080 [33:44:12<21:48:04,  7.13s/it]
                                                           
{'loss': 0.6313, 'learning_rate': 0.00017596685038344785, 'epoch': 7.29}

 61%|██████    | 17068/28080 [33:44:12<21:48:04,  7.13s/it]
 61%|██████    | 17069/28080 [33:44:19<21:42:33,  7.10s/it]
                                                           
{'loss': 0.6065, 'learning_rate': 0.00017593930854116862, 'epoch': 7.29}

 61%|██████    | 17069/28080 [33:44:19<21:42:33,  7.10s/it]
 61%|██████    | 17070/28080 [33:44:26<21:49:54,  7.14s/it]
                                                           
{'loss': 0.6033, 'learning_rate': 0.00017591176768419044, 'epoch': 7.29}

 61%|██████    | 17070/28080 [33:44:26<21:49:54,  7.14s/it]
 61%|██████    | 17071/28080 [33:44:33<21:54:41,  7.17s/it]
                                                           
{'loss': 0.6105, 'learning_rate': 0.00017588422781287982, 'epoch': 7.29}

 61%|██████    | 17071/28080 [33:44:33<21:54:41,  7.17s/it]
 61%|██████    | 17072/28080 [33:44:40<21:52:41,  7.15s/it]
                                                           
{'loss': 0.5937, 'learning_rate': 0.0001758566889276031, 'epoch': 7.29}

 61%|██████    | 17072/28080 [33:44:40<21:52:41,  7.15s/it]
 61%|██████    | 17073/28080 [33:44:47<21:56:01,  7.17s/it]
                                                           
{'loss': 0.6048, 'learning_rate': 0.0001758291510287266, 'epoch': 7.29}

 61%|██████    | 17073/28080 [33:44:47<21:56:01,  7.17s/it]
 61%|██████    | 17074/28080 [33:44:54<21:53:43,  7.16s/it]
                                                           
{'loss': 0.6299, 'learning_rate': 0.00017580161411661678, 'epoch': 7.29}

 61%|██████    | 17074/28080 [33:44:54<21:53:43,  7.16s/it]
 61%|██████    | 17075/28080 [33:45:02<21:54:53,  7.17s/it]
                                                           
{'loss': 0.6148, 'learning_rate': 0.00017577407819163984, 'epoch': 7.29}

 61%|██████    | 17075/28080 [33:45:02<21:54:53,  7.17s/it]
 61%|██████    | 17076/28080 [33:45:09<21:58:35,  7.19s/it]
                                                           
{'loss': 0.6144, 'learning_rate': 0.0001757465432541623, 'epoch': 7.29}

 61%|██████    | 17076/28080 [33:45:09<21:58:35,  7.19s/it]
 61%|██████    | 17077/28080 [33:45:16<21:52:42,  7.16s/it]
                                                           
{'loss': 0.6125, 'learning_rate': 0.0001757190093045503, 'epoch': 7.3}

 61%|██████    | 17077/28080 [33:45:16<21:52:42,  7.16s/it]
 61%|██████    | 17078/28080 [33:45:23<21:49:46,  7.14s/it]
                                                           
{'loss': 0.6235, 'learning_rate': 0.0001756914763431704, 'epoch': 7.3}

 61%|██████    | 17078/28080 [33:45:23<21:49:46,  7.14s/it]
 61%|██████    | 17079/28080 [33:45:30<21:51:26,  7.15s/it]
                                                           
{'loss': 0.6334, 'learning_rate': 0.00017566394437038859, 'epoch': 7.3}

 61%|██████    | 17079/28080 [33:45:30<21:51:26,  7.15s/it]
 61%|██████    | 17080/28080 [33:45:37<21:48:53,  7.14s/it]
                                                           
{'loss': 0.5971, 'learning_rate': 0.00017563641338657149, 'epoch': 7.3}

 61%|██████    | 17080/28080 [33:45:37<21:48:53,  7.14s/it]
 61%|██████    | 17081/28080 [33:45:44<21:43:50,  7.11s/it]
                                                           
{'loss': 0.6024, 'learning_rate': 0.000175608883392085, 'epoch': 7.3}

 61%|██████    | 17081/28080 [33:45:44<21:43:50,  7.11s/it]
 61%|██████    | 17082/28080 [33:45:51<21:38:36,  7.08s/it]
                                                           
{'loss': 0.6138, 'learning_rate': 0.0001755813543872957, 'epoch': 7.3}

 61%|██████    | 17082/28080 [33:45:51<21:38:36,  7.08s/it]
 61%|██████    | 17083/28080 [33:45:59<21:42:44,  7.11s/it]
                                                           
{'loss': 0.6246, 'learning_rate': 0.0001755538263725696, 'epoch': 7.3}

 61%|██████    | 17083/28080 [33:45:59<21:42:44,  7.11s/it]
 61%|██████    | 17084/28080 [33:46:06<21:37:41,  7.08s/it]
                                                           
{'loss': 0.6108, 'learning_rate': 0.00017552629934827318, 'epoch': 7.3}

 61%|██████    | 17084/28080 [33:46:06<21:37:41,  7.08s/it]
 61%|██████    | 17085/28080 [33:46:13<21:40:16,  7.10s/it]
                                                           
{'loss': 0.5984, 'learning_rate': 0.00017549877331477244, 'epoch': 7.3}

 61%|██████    | 17085/28080 [33:46:13<21:40:16,  7.10s/it]
 61%|██████    | 17086/28080 [33:46:20<21:40:31,  7.10s/it]
                                                           
{'loss': 0.6062, 'learning_rate': 0.00017547124827243366, 'epoch': 7.3}

 61%|██████    | 17086/28080 [33:46:20<21:40:31,  7.10s/it]
 61%|██████    | 17087/28080 [33:46:27<21:39:36,  7.09s/it]
                                                           
{'loss': 0.6226, 'learning_rate': 0.00017544372422162303, 'epoch': 7.3}

 61%|██████    | 17087/28080 [33:46:27<21:39:36,  7.09s/it]
 61%|██████    | 17088/28080 [33:46:34<21:47:49,  7.14s/it]
                                                           
{'loss': 0.5988, 'learning_rate': 0.00017541620116270676, 'epoch': 7.3}

 61%|██████    | 17088/28080 [33:46:34<21:47:49,  7.14s/it]
 61%|██████    | 17089/28080 [33:46:41<21:50:14,  7.15s/it]
                                                           
{'loss': 0.5974, 'learning_rate': 0.00017538867909605094, 'epoch': 7.3}

 61%|██████    | 17089/28080 [33:46:41<21:50:14,  7.15s/it]
 61%|██████    | 17090/28080 [33:46:49<21:51:18,  7.16s/it]
                                                           
{'loss': 0.6103, 'learning_rate': 0.00017536115802202184, 'epoch': 7.3}

 61%|██████    | 17090/28080 [33:46:49<21:51:18,  7.16s/it]
 61%|██████    | 17091/28080 [33:46:56<21:45:46,  7.13s/it]
                                                           
{'loss': 0.6206, 'learning_rate': 0.00017533363794098545, 'epoch': 7.3}

 61%|██████    | 17091/28080 [33:46:56<21:45:46,  7.13s/it]
 61%|██████    | 17092/28080 [33:47:03<21:50:41,  7.16s/it]
                                                           
{'loss': 0.6087, 'learning_rate': 0.0001753061188533081, 'epoch': 7.3}

 61%|██████    | 17092/28080 [33:47:03<21:50:41,  7.16s/it]
 61%|██████    | 17093/28080 [33:47:10<21:50:35,  7.16s/it]
                                                           
{'loss': 0.607, 'learning_rate': 0.00017527860075935563, 'epoch': 7.3}

 61%|██████    | 17093/28080 [33:47:10<21:50:35,  7.16s/it]
 61%|██████    | 17094/28080 [33:47:17<21:51:58,  7.17s/it]
                                                           
{'loss': 0.6141, 'learning_rate': 0.0001752510836594944, 'epoch': 7.3}

 61%|██████    | 17094/28080 [33:47:17<21:51:58,  7.17s/it]
 61%|██████    | 17095/28080 [33:47:24<21:47:29,  7.14s/it]
                                                           
{'loss': 0.6217, 'learning_rate': 0.00017522356755409033, 'epoch': 7.3}

 61%|██████    | 17095/28080 [33:47:24<21:47:29,  7.14s/it]
 61%|██████    | 17096/28080 [33:47:31<21:50:35,  7.16s/it]
                                                           
{'loss': 0.5965, 'learning_rate': 0.00017519605244350963, 'epoch': 7.3}

 61%|██████    | 17096/28080 [33:47:31<21:50:35,  7.16s/it]
 61%|██████    | 17097/28080 [33:47:39<21:44:47,  7.13s/it]
                                                           
{'loss': 0.6076, 'learning_rate': 0.0001751685383281183, 'epoch': 7.3}

 61%|██████    | 17097/28080 [33:47:39<21:44:47,  7.13s/it]
 61%|██████    | 17098/28080 [33:47:46<21:45:32,  7.13s/it]
                                                           
{'loss': 0.6193, 'learning_rate': 0.00017514102520828223, 'epoch': 7.3}

 61%|██████    | 17098/28080 [33:47:46<21:45:32,  7.13s/it]
 61%|██████    | 17099/28080 [33:47:53<21:51:26,  7.17s/it]
                                                           
{'loss': 0.6011, 'learning_rate': 0.00017511351308436768, 'epoch': 7.3}

 61%|██████    | 17099/28080 [33:47:53<21:51:26,  7.17s/it]
 61%|██████    | 17100/28080 [33:48:00<21:53:32,  7.18s/it]
                                                           
{'loss': 0.6056, 'learning_rate': 0.0001750860019567405, 'epoch': 7.3}

 61%|██████    | 17100/28080 [33:48:00<21:53:32,  7.18s/it]
 61%|██████    | 17101/28080 [33:48:07<21:49:32,  7.16s/it]
                                                           
{'loss': 0.6154, 'learning_rate': 0.0001750584918257669, 'epoch': 7.31}

 61%|██████    | 17101/28080 [33:48:07<21:49:32,  7.16s/it]
 61%|██████    | 17102/28080 [33:48:14<21:43:17,  7.12s/it]
                                                           
{'loss': 0.6093, 'learning_rate': 0.00017503098269181267, 'epoch': 7.31}

 61%|██████    | 17102/28080 [33:48:14<21:43:17,  7.12s/it]
 61%|██████    | 17103/28080 [33:48:21<21:48:06,  7.15s/it]
                                                           
{'loss': 0.6393, 'learning_rate': 0.00017500347455524394, 'epoch': 7.31}

 61%|██████    | 17103/28080 [33:48:21<21:48:06,  7.15s/it]
 61%|██████    | 17104/28080 [33:48:29<21:49:48,  7.16s/it]
                                                           
{'loss': 0.6103, 'learning_rate': 0.00017497596741642655, 'epoch': 7.31}

 61%|██████    | 17104/28080 [33:48:29<21:49:48,  7.16s/it]
 61%|██████    | 17105/28080 [33:48:36<21:48:43,  7.15s/it]
                                                           
{'loss': 0.6047, 'learning_rate': 0.00017494846127572657, 'epoch': 7.31}

 61%|██████    | 17105/28080 [33:48:36<21:48:43,  7.15s/it]
 61%|██████    | 17106/28080 [33:48:43<21:49:34,  7.16s/it]
                                                           
{'loss': 0.6111, 'learning_rate': 0.00017492095613350984, 'epoch': 7.31}

 61%|██████    | 17106/28080 [33:48:43<21:49:34,  7.16s/it]
 61%|██████    | 17107/28080 [33:48:50<21:51:43,  7.17s/it]
                                                           
{'loss': 0.592, 'learning_rate': 0.00017489345199014233, 'epoch': 7.31}

 61%|██████    | 17107/28080 [33:48:50<21:51:43,  7.17s/it]
 61%|██████    | 17108/28080 [33:48:57<21:50:11,  7.16s/it]
                                                           
{'loss': 0.5875, 'learning_rate': 0.0001748659488459899, 'epoch': 7.31}

 61%|██████    | 17108/28080 [33:48:57<21:50:11,  7.16s/it]
 61%|██████    | 17109/28080 [33:49:04<21:45:26,  7.14s/it]
                                                           
{'loss': 0.6044, 'learning_rate': 0.0001748384467014187, 'epoch': 7.31}

 61%|██████    | 17109/28080 [33:49:04<21:45:26,  7.14s/it]
 61%|██████    | 17110/28080 [33:49:11<21:42:39,  7.12s/it]
                                                           
{'loss': 0.6152, 'learning_rate': 0.00017481094555679423, 'epoch': 7.31}

 61%|██████    | 17110/28080 [33:49:12<21:42:39,  7.12s/it]
 61%|██████    | 17111/28080 [33:49:19<21:38:21,  7.10s/it]
                                                           
{'loss': 0.6008, 'learning_rate': 0.0001747834454124827, 'epoch': 7.31}

 61%|██████    | 17111/28080 [33:49:19<21:38:21,  7.10s/it]
 61%|██████    | 17112/28080 [33:49:25<21:28:00,  7.05s/it]
                                                           
{'loss': 0.6143, 'learning_rate': 0.00017475594626884973, 'epoch': 7.31}

 61%|██████    | 17112/28080 [33:49:25<21:28:00,  7.05s/it]
 61%|██████    | 17113/28080 [33:49:33<21:34:38,  7.08s/it]
                                                           
{'loss': 0.6269, 'learning_rate': 0.00017472844812626133, 'epoch': 7.31}

 61%|██████    | 17113/28080 [33:49:33<21:34:38,  7.08s/it]
 61%|██████    | 17114/28080 [33:49:40<21:36:26,  7.09s/it]
                                                           
{'loss': 0.6121, 'learning_rate': 0.0001747009509850832, 'epoch': 7.31}

 61%|██████    | 17114/28080 [33:49:40<21:36:26,  7.09s/it]
 61%|██████    | 17115/28080 [33:49:47<21:40:26,  7.12s/it]
                                                           
{'loss': 0.6182, 'learning_rate': 0.00017467345484568136, 'epoch': 7.31}

 61%|██████    | 17115/28080 [33:49:47<21:40:26,  7.12s/it]
 61%|██████    | 17116/28080 [33:49:54<21:39:04,  7.11s/it]
                                                           
{'loss': 0.6083, 'learning_rate': 0.0001746459597084214, 'epoch': 7.31}

 61%|██████    | 17116/28080 [33:49:54<21:39:04,  7.11s/it]
 61%|██████    | 17117/28080 [33:50:01<21:39:13,  7.11s/it]
                                                           
{'loss': 0.5991, 'learning_rate': 0.00017461846557366924, 'epoch': 7.31}

 61%|██████    | 17117/28080 [33:50:01<21:39:13,  7.11s/it]
 61%|██████    | 17118/28080 [33:50:08<21:39:04,  7.11s/it]
                                                           
{'loss': 0.6012, 'learning_rate': 0.0001745909724417906, 'epoch': 7.31}

 61%|██████    | 17118/28080 [33:50:08<21:39:04,  7.11s/it]
 61%|██████    | 17119/28080 [33:50:15<21:37:59,  7.11s/it]
                                                           
{'loss': 0.6137, 'learning_rate': 0.00017456348031315134, 'epoch': 7.31}

 61%|██████    | 17119/28080 [33:50:15<21:37:59,  7.11s/it]
 61%|██████    | 17120/28080 [33:50:23<21:43:03,  7.13s/it]
                                                           
{'loss': 0.6449, 'learning_rate': 0.00017453598918811707, 'epoch': 7.31}

 61%|██████    | 17120/28080 [33:50:23<21:43:03,  7.13s/it]
 61%|██████    | 17121/28080 [33:50:30<21:42:57,  7.13s/it]
                                                           
{'loss': 0.6197, 'learning_rate': 0.0001745084990670537, 'epoch': 7.31}

 61%|██████    | 17121/28080 [33:50:30<21:42:57,  7.13s/it]
 61%|██████    | 17122/28080 [33:50:37<21:42:05,  7.13s/it]
                                                           
{'loss': 0.6069, 'learning_rate': 0.00017448100995032684, 'epoch': 7.31}

 61%|██████    | 17122/28080 [33:50:37<21:42:05,  7.13s/it]
 61%|██████    | 17123/28080 [33:50:44<21:41:01,  7.12s/it]
                                                           
{'loss': 0.604, 'learning_rate': 0.0001744535218383022, 'epoch': 7.31}

 61%|██████    | 17123/28080 [33:50:44<21:41:01,  7.12s/it]
 61%|██████    | 17124/28080 [33:50:51<21:40:26,  7.12s/it]
                                                           
{'loss': 0.6381, 'learning_rate': 0.00017442603473134555, 'epoch': 7.32}

 61%|██████    | 17124/28080 [33:50:51<21:40:26,  7.12s/it]
 61%|██████    | 17125/28080 [33:50:58<21:42:05,  7.13s/it]
                                                           
{'loss': 0.6167, 'learning_rate': 0.00017439854862982246, 'epoch': 7.32}

 61%|██████    | 17125/28080 [33:50:58<21:42:05,  7.13s/it]
 61%|██████    | 17126/28080 [33:51:05<21:42:42,  7.14s/it]
                                                           
{'loss': 0.6018, 'learning_rate': 0.00017437106353409881, 'epoch': 7.32}

 61%|██████    | 17126/28080 [33:51:05<21:42:42,  7.14s/it]
 61%|██████    | 17127/28080 [33:51:12<21:41:06,  7.13s/it]
                                                           
{'loss': 0.6073, 'learning_rate': 0.00017434357944454005, 'epoch': 7.32}

 61%|██████    | 17127/28080 [33:51:12<21:41:06,  7.13s/it]
 61%|██████    | 17128/28080 [33:51:20<21:41:09,  7.13s/it]
                                                           
{'loss': 0.5971, 'learning_rate': 0.000174316096361512, 'epoch': 7.32}

 61%|██████    | 17128/28080 [33:51:20<21:41:09,  7.13s/it]
 61%|██████    | 17129/28080 [33:51:27<21:44:43,  7.15s/it]
                                                           
{'loss': 0.6133, 'learning_rate': 0.00017428861428538006, 'epoch': 7.32}

 61%|██████    | 17129/28080 [33:51:27<21:44:43,  7.15s/it]
 61%|██████    | 17130/28080 [33:51:34<21:46:31,  7.16s/it]
                                                           
{'loss': 0.6152, 'learning_rate': 0.00017426113321651013, 'epoch': 7.32}

 61%|██████    | 17130/28080 [33:51:34<21:46:31,  7.16s/it]
 61%|██████    | 17131/28080 [33:51:41<21:43:17,  7.14s/it]
                                                           
{'loss': 0.6102, 'learning_rate': 0.00017423365315526762, 'epoch': 7.32}

 61%|██████    | 17131/28080 [33:51:41<21:43:17,  7.14s/it]
 61%|██████    | 17132/28080 [33:51:48<21:36:02,  7.10s/it]
                                                           
{'loss': 0.6404, 'learning_rate': 0.00017420617410201828, 'epoch': 7.32}

 61%|██████    | 17132/28080 [33:51:48<21:36:02,  7.10s/it]
 61%|██████    | 17133/28080 [33:51:55<21:38:25,  7.12s/it]
                                                           
{'loss': 0.6224, 'learning_rate': 0.0001741786960571275, 'epoch': 7.32}

 61%|██████    | 17133/28080 [33:51:55<21:38:25,  7.12s/it]
 61%|██████    | 17134/28080 [33:52:02<21:35:40,  7.10s/it]
                                                           
{'loss': 0.6368, 'learning_rate': 0.00017415121902096103, 'epoch': 7.32}

 61%|██████    | 17134/28080 [33:52:02<21:35:40,  7.10s/it]
 61%|██████    | 17135/28080 [33:52:09<21:36:11,  7.11s/it]
                                                           
{'loss': 0.5999, 'learning_rate': 0.00017412374299388429, 'epoch': 7.32}

 61%|██████    | 17135/28080 [33:52:09<21:36:11,  7.11s/it]
 61%|██████    | 17136/28080 [33:52:17<21:40:06,  7.13s/it]
                                                           
{'loss': 0.6111, 'learning_rate': 0.0001740962679762629, 'epoch': 7.32}

 61%|██████    | 17136/28080 [33:52:17<21:40:06,  7.13s/it]
 61%|██████    | 17137/28080 [33:52:24<21:44:24,  7.15s/it]
                                                           
{'loss': 0.6016, 'learning_rate': 0.0001740687939684623, 'epoch': 7.32}

 61%|██████    | 17137/28080 [33:52:24<21:44:24,  7.15s/it]
 61%|██████    | 17138/28080 [33:52:31<21:39:50,  7.13s/it]
                                                           
{'loss': 0.6307, 'learning_rate': 0.00017404132097084812, 'epoch': 7.32}

 61%|██████    | 17138/28080 [33:52:31<21:39:50,  7.13s/it]
 61%|██████    | 17139/28080 [33:52:38<21:40:46,  7.13s/it]
                                                           
{'loss': 0.608, 'learning_rate': 0.00017401384898378574, 'epoch': 7.32}

 61%|██████    | 17139/28080 [33:52:38<21:40:46,  7.13s/it]
 61%|██████    | 17140/28080 [33:52:45<21:36:47,  7.11s/it]
                                                           
{'loss': 0.5965, 'learning_rate': 0.00017398637800764084, 'epoch': 7.32}

 61%|██████    | 17140/28080 [33:52:45<21:36:47,  7.11s/it]
 61%|██████    | 17141/28080 [33:52:52<21:31:45,  7.09s/it]
                                                           
{'loss': 0.6188, 'learning_rate': 0.00017395890804277857, 'epoch': 7.32}

 61%|██████    | 17141/28080 [33:52:52<21:31:45,  7.09s/it]
 61%|██████    | 17142/28080 [33:52:59<21:36:23,  7.11s/it]
                                                           
{'loss': 0.6016, 'learning_rate': 0.0001739314390895648, 'epoch': 7.32}

 61%|██████    | 17142/28080 [33:52:59<21:36:23,  7.11s/it]
 61%|██████    | 17143/28080 [33:53:06<21:39:27,  7.13s/it]
                                                           
{'loss': 0.6127, 'learning_rate': 0.0001739039711483646, 'epoch': 7.32}

 61%|██████    | 17143/28080 [33:53:06<21:39:27,  7.13s/it]
 61%|██████    | 17144/28080 [33:53:13<21:36:55,  7.12s/it]
                                                           
{'loss': 0.624, 'learning_rate': 0.0001738765042195436, 'epoch': 7.32}

 61%|██████    | 17144/28080 [33:53:13<21:36:55,  7.12s/it]
 61%|██████    | 17145/28080 [33:53:21<21:37:03,  7.12s/it]
                                                           
{'loss': 0.5996, 'learning_rate': 0.00017384903830346715, 'epoch': 7.32}

 61%|██████    | 17145/28080 [33:53:21<21:37:03,  7.12s/it]
 61%|██████    | 17146/28080 [33:53:28<21:37:15,  7.12s/it]
                                                           
{'loss': 0.6018, 'learning_rate': 0.00017382157340050075, 'epoch': 7.32}

 61%|██████    | 17146/28080 [33:53:28<21:37:15,  7.12s/it]
 61%|██████    | 17147/28080 [33:53:35<21:38:06,  7.12s/it]
                                                           
{'loss': 0.6012, 'learning_rate': 0.00017379410951100978, 'epoch': 7.33}

 61%|██████    | 17147/28080 [33:53:35<21:38:06,  7.12s/it]
 61%|██████    | 17148/28080 [33:53:42<21:37:05,  7.12s/it]
                                                           
{'loss': 0.6134, 'learning_rate': 0.00017376664663535944, 'epoch': 7.33}

 61%|██████    | 17148/28080 [33:53:42<21:37:05,  7.12s/it]
 61%|██████    | 17149/28080 [33:53:49<21:36:51,  7.12s/it]
                                                           
{'loss': 0.6243, 'learning_rate': 0.00017373918477391528, 'epoch': 7.33}

 61%|██████    | 17149/28080 [33:53:49<21:36:51,  7.12s/it]
 61%|██████    | 17150/28080 [33:53:56<21:39:29,  7.13s/it]
                                                           
{'loss': 0.6173, 'learning_rate': 0.00017371172392704253, 'epoch': 7.33}

 61%|██████    | 17150/28080 [33:53:56<21:39:29,  7.13s/it]
 61%|██████    | 17151/28080 [33:54:03<21:30:37,  7.09s/it]
                                                           
{'loss': 0.6234, 'learning_rate': 0.0001736842640951067, 'epoch': 7.33}

 61%|██████    | 17151/28080 [33:54:03<21:30:37,  7.09s/it]
 61%|██████    | 17152/28080 [33:54:10<21:30:21,  7.08s/it]
                                                           
{'loss': 0.6203, 'learning_rate': 0.00017365680527847292, 'epoch': 7.33}

 61%|██████    | 17152/28080 [33:54:10<21:30:21,  7.08s/it]
 61%|██████    | 17153/28080 [33:54:18<21:37:03,  7.12s/it]
                                                           
{'loss': 0.6035, 'learning_rate': 0.00017362934747750663, 'epoch': 7.33}

 61%|██████    | 17153/28080 [33:54:18<21:37:03,  7.12s/it]
 61%|██████    | 17154/28080 [33:54:25<21:37:39,  7.13s/it]
                                                           
{'loss': 0.6103, 'learning_rate': 0.00017360189069257303, 'epoch': 7.33}

 61%|██████    | 17154/28080 [33:54:25<21:37:39,  7.13s/it]
 61%|██████    | 17155/28080 [33:54:32<21:40:08,  7.14s/it]
                                                           
{'loss': 0.5946, 'learning_rate': 0.00017357443492403756, 'epoch': 7.33}

 61%|██████    | 17155/28080 [33:54:32<21:40:08,  7.14s/it]
 61%|██████    | 17156/28080 [33:54:39<21:39:13,  7.14s/it]
                                                           
{'loss': 0.6303, 'learning_rate': 0.00017354698017226522, 'epoch': 7.33}

 61%|██████    | 17156/28080 [33:54:39<21:39:13,  7.14s/it]
 61%|██████    | 17157/28080 [33:54:46<21:36:27,  7.12s/it]
                                                           
{'loss': 0.6135, 'learning_rate': 0.00017351952643762165, 'epoch': 7.33}

 61%|██████    | 17157/28080 [33:54:46<21:36:27,  7.12s/it]
 61%|██████    | 17158/28080 [33:54:53<21:38:08,  7.13s/it]
                                                           
{'loss': 0.5937, 'learning_rate': 0.00017349207372047165, 'epoch': 7.33}

 61%|██████    | 17158/28080 [33:54:53<21:38:08,  7.13s/it]
 61%|██████    | 17159/28080 [33:55:00<21:34:05,  7.11s/it]
                                                           
{'loss': 0.6258, 'learning_rate': 0.00017346462202118092, 'epoch': 7.33}

 61%|██████    | 17159/28080 [33:55:00<21:34:05,  7.11s/it]
 61%|██████    | 17160/28080 [33:55:07<21:34:32,  7.11s/it]
                                                           
{'loss': 0.5952, 'learning_rate': 0.00017343717134011422, 'epoch': 7.33}

 61%|██████    | 17160/28080 [33:55:07<21:34:32,  7.11s/it]
 61%|██████    | 17161/28080 [33:55:15<21:37:57,  7.13s/it]
                                                           
{'loss': 0.5965, 'learning_rate': 0.0001734097216776371, 'epoch': 7.33}

 61%|██████    | 17161/28080 [33:55:15<21:37:57,  7.13s/it]
 61%|██████    | 17162/28080 [33:55:22<21:34:22,  7.11s/it]
                                                           
{'loss': 0.6226, 'learning_rate': 0.00017338227303411458, 'epoch': 7.33}

 61%|██████    | 17162/28080 [33:55:22<21:34:22,  7.11s/it]
 61%|██████    | 17163/28080 [33:55:29<21:36:34,  7.13s/it]
                                                           
{'loss': 0.5958, 'learning_rate': 0.0001733548254099119, 'epoch': 7.33}

 61%|██████    | 17163/28080 [33:55:29<21:36:34,  7.13s/it]
 61%|██████    | 17164/28080 [33:55:36<21:35:59,  7.12s/it]
                                                           
{'loss': 0.609, 'learning_rate': 0.00017332737880539417, 'epoch': 7.33}

 61%|██████    | 17164/28080 [33:55:36<21:35:59,  7.12s/it]
 61%|██████    | 17165/28080 [33:55:43<21:35:37,  7.12s/it]
                                                           
{'loss': 0.5945, 'learning_rate': 0.00017329993322092658, 'epoch': 7.33}

 61%|██████    | 17165/28080 [33:55:43<21:35:37,  7.12s/it]
 61%|██████    | 17166/28080 [33:55:50<21:42:43,  7.16s/it]
                                                           
{'loss': 0.5988, 'learning_rate': 0.00017327248865687422, 'epoch': 7.33}

 61%|██████    | 17166/28080 [33:55:50<21:42:43,  7.16s/it]
 61%|██████    | 17167/28080 [33:55:57<21:42:01,  7.16s/it]
                                                           
{'loss': 0.5986, 'learning_rate': 0.00017324504511360232, 'epoch': 7.33}

 61%|██████    | 17167/28080 [33:55:57<21:42:01,  7.16s/it]
 61%|██████    | 17168/28080 [33:56:04<21:32:07,  7.10s/it]
                                                           
{'loss': 0.6063, 'learning_rate': 0.00017321760259147586, 'epoch': 7.33}

 61%|██████    | 17168/28080 [33:56:04<21:32:07,  7.10s/it]
 61%|██████    | 17169/28080 [33:56:12<21:32:56,  7.11s/it]
                                                           
{'loss': 0.629, 'learning_rate': 0.00017319016109086, 'epoch': 7.33}

 61%|██████    | 17169/28080 [33:56:12<21:32:56,  7.11s/it]
 61%|██████    | 17170/28080 [33:56:19<21:31:05,  7.10s/it]
                                                           
{'loss': 0.6088, 'learning_rate': 0.00017316272061211968, 'epoch': 7.33}

 61%|██████    | 17170/28080 [33:56:19<21:31:05,  7.10s/it]
 61%|██████    | 17171/28080 [33:56:26<21:28:20,  7.09s/it]
                                                           
{'loss': 0.6128, 'learning_rate': 0.00017313528115562034, 'epoch': 7.34}

 61%|██████    | 17171/28080 [33:56:26<21:28:20,  7.09s/it]
 61%|██████    | 17172/28080 [33:56:33<21:35:12,  7.12s/it]
                                                           
{'loss': 0.6236, 'learning_rate': 0.00017310784272172664, 'epoch': 7.34}

 61%|██████    | 17172/28080 [33:56:33<21:35:12,  7.12s/it]
 61%|██████    | 17173/28080 [33:56:40<21:32:04,  7.11s/it]
                                                           
{'loss': 0.5958, 'learning_rate': 0.00017308040531080376, 'epoch': 7.34}

 61%|██████    | 17173/28080 [33:56:40<21:32:04,  7.11s/it]
 61%|██████    | 17174/28080 [33:56:47<21:36:35,  7.13s/it]
                                                           
{'loss': 0.6266, 'learning_rate': 0.00017305296892321682, 'epoch': 7.34}

 61%|██████    | 17174/28080 [33:56:47<21:36:35,  7.13s/it]
 61%|██████    | 17175/28080 [33:56:54<21:36:54,  7.14s/it]
                                                           
{'loss': 0.6194, 'learning_rate': 0.0001730255335593306, 'epoch': 7.34}

 61%|██████    | 17175/28080 [33:56:54<21:36:54,  7.14s/it]
 61%|██████    | 17176/28080 [33:57:01<21:37:09,  7.14s/it]
                                                           
{'loss': 0.6116, 'learning_rate': 0.00017299809921951037, 'epoch': 7.34}

 61%|██████    | 17176/28080 [33:57:01<21:37:09,  7.14s/it]
 61%|██████    | 17177/28080 [33:57:08<21:33:48,  7.12s/it]
                                                           
{'loss': 0.6046, 'learning_rate': 0.00017297066590412093, 'epoch': 7.34}

 61%|██████    | 17177/28080 [33:57:08<21:33:48,  7.12s/it]
 61%|██████    | 17178/28080 [33:57:16<21:36:39,  7.14s/it]
                                                           
{'loss': 0.6336, 'learning_rate': 0.00017294323361352731, 'epoch': 7.34}

 61%|██████    | 17178/28080 [33:57:16<21:36:39,  7.14s/it]
 61%|██████    | 17179/28080 [33:57:23<21:33:23,  7.12s/it]
                                                           
{'loss': 0.6162, 'learning_rate': 0.0001729158023480945, 'epoch': 7.34}

 61%|██████    | 17179/28080 [33:57:23<21:33:23,  7.12s/it]
 61%|██████    | 17180/28080 [33:57:30<21:31:39,  7.11s/it]
                                                           
{'loss': 0.6124, 'learning_rate': 0.00017288837210818742, 'epoch': 7.34}

 61%|██████    | 17180/28080 [33:57:30<21:31:39,  7.11s/it]
 61%|██████    | 17181/28080 [33:57:37<21:24:38,  7.07s/it]
                                                           
{'loss': 0.6319, 'learning_rate': 0.000172860942894171, 'epoch': 7.34}

 61%|██████    | 17181/28080 [33:57:37<21:24:38,  7.07s/it]
 61%|██████    | 17182/28080 [33:57:44<21:29:42,  7.10s/it]
                                                           
{'loss': 0.6089, 'learning_rate': 0.00017283351470641015, 'epoch': 7.34}

 61%|██████    | 17182/28080 [33:57:44<21:29:42,  7.10s/it]
 61%|██████    | 17183/28080 [33:57:51<21:32:52,  7.12s/it]
                                                           
{'loss': 0.6254, 'learning_rate': 0.00017280608754526974, 'epoch': 7.34}

 61%|██████    | 17183/28080 [33:57:51<21:32:52,  7.12s/it]
 61%|██████    | 17184/28080 [33:57:58<21:34:35,  7.13s/it]
                                                           
{'loss': 0.6038, 'learning_rate': 0.00017277866141111477, 'epoch': 7.34}

 61%|██████    | 17184/28080 [33:57:58<21:34:35,  7.13s/it]
 61%|██████    | 17185/28080 [33:58:05<21:32:09,  7.12s/it]
                                                           
{'loss': 0.5928, 'learning_rate': 0.00017275123630430998, 'epoch': 7.34}

 61%|██████    | 17185/28080 [33:58:05<21:32:09,  7.12s/it]
 61%|██████    | 17186/28080 [33:58:12<21:31:00,  7.11s/it]
                                                           
{'loss': 0.6128, 'learning_rate': 0.00017272381222522036, 'epoch': 7.34}

 61%|██████    | 17186/28080 [33:58:12<21:31:00,  7.11s/it]
 61%|██████    | 17187/28080 [33:58:20<21:26:10,  7.08s/it]
                                                           
{'loss': 0.6152, 'learning_rate': 0.00017269638917421056, 'epoch': 7.34}

 61%|██████    | 17187/28080 [33:58:20<21:26:10,  7.08s/it]
 61%|██████    | 17188/28080 [33:58:27<21:28:41,  7.10s/it]
                                                           
{'loss': 0.5845, 'learning_rate': 0.00017266896715164575, 'epoch': 7.34}

 61%|██████    | 17188/28080 [33:58:27<21:28:41,  7.10s/it]
 61%|██████    | 17189/28080 [33:58:34<21:30:32,  7.11s/it]
                                                           
{'loss': 0.6032, 'learning_rate': 0.0001726415461578904, 'epoch': 7.34}

 61%|██████    | 17189/28080 [33:58:34<21:30:32,  7.11s/it]
 61%|██████    | 17190/28080 [33:58:41<21:34:39,  7.13s/it]
                                                           
{'loss': 0.6102, 'learning_rate': 0.00017261412619330957, 'epoch': 7.34}

 61%|██████    | 17190/28080 [33:58:41<21:34:39,  7.13s/it]
 61%|██████    | 17191/28080 [33:58:48<21:27:31,  7.09s/it]
                                                           
{'loss': 0.6199, 'learning_rate': 0.00017258670725826787, 'epoch': 7.34}

 61%|██████    | 17191/28080 [33:58:48<21:27:31,  7.09s/it]
 61%|██████    | 17192/28080 [33:58:55<21:26:23,  7.09s/it]
                                                           
{'loss': 0.6248, 'learning_rate': 0.00017255928935313024, 'epoch': 7.34}

 61%|██████    | 17192/28080 [33:58:55<21:26:23,  7.09s/it]
 61%|██████    | 17193/28080 [33:59:02<21:26:37,  7.09s/it]
                                                           
{'loss': 0.6213, 'learning_rate': 0.0001725318724782613, 'epoch': 7.34}

 61%|██████    | 17193/28080 [33:59:02<21:26:37,  7.09s/it]
 61%|██████    | 17194/28080 [33:59:09<21:35:25,  7.14s/it]
                                                           
{'loss': 0.6116, 'learning_rate': 0.00017250445663402597, 'epoch': 7.35}

 61%|██████    | 17194/28080 [33:59:09<21:35:25,  7.14s/it]
 61%|██████    | 17195/28080 [33:59:16<21:32:31,  7.12s/it]
                                                           
{'loss': 0.6096, 'learning_rate': 0.00017247704182078884, 'epoch': 7.35}

 61%|██████    | 17195/28080 [33:59:16<21:32:31,  7.12s/it]
 61%|██████    | 17196/28080 [33:59:24<21:31:51,  7.12s/it]
                                                           
{'loss': 0.6032, 'learning_rate': 0.00017244962803891474, 'epoch': 7.35}

 61%|██████    | 17196/28080 [33:59:24<21:31:51,  7.12s/it]
 61%|██████    | 17197/28080 [33:59:31<21:39:29,  7.16s/it]
                                                           
{'loss': 0.596, 'learning_rate': 0.00017242221528876827, 'epoch': 7.35}

 61%|██████    | 17197/28080 [33:59:31<21:39:29,  7.16s/it]
 61%|██████    | 17198/28080 [33:59:38<21:35:59,  7.15s/it]
                                                           
{'loss': 0.6019, 'learning_rate': 0.00017239480357071423, 'epoch': 7.35}

 61%|██████    | 17198/28080 [33:59:38<21:35:59,  7.15s/it]
 61%|██████▏   | 17199/28080 [33:59:45<21:33:30,  7.13s/it]
                                                           
{'loss': 0.6164, 'learning_rate': 0.00017236739288511727, 'epoch': 7.35}

 61%|██████▏   | 17199/28080 [33:59:45<21:33:30,  7.13s/it]
 61%|██████▏   | 17200/28080 [33:59:52<21:40:44,  7.17s/it]
                                                           
{'loss': 0.6076, 'learning_rate': 0.00017233998323234204, 'epoch': 7.35}

 61%|██████▏   | 17200/28080 [33:59:52<21:40:44,  7.17s/it]
 61%|██████▏   | 17201/28080 [34:00:00<21:43:00,  7.19s/it]
                                                           
{'loss': 0.595, 'learning_rate': 0.00017231257461275323, 'epoch': 7.35}

 61%|██████▏   | 17201/28080 [34:00:00<21:43:00,  7.19s/it]
 61%|██████▏   | 17202/28080 [34:00:07<21:39:29,  7.17s/it]
                                                           
{'loss': 0.6016, 'learning_rate': 0.00017228516702671545, 'epoch': 7.35}

 61%|██████▏   | 17202/28080 [34:00:07<21:39:29,  7.17s/it]
 61%|██████▏   | 17203/28080 [34:00:14<21:40:10,  7.17s/it]
                                                           
{'loss': 0.6009, 'learning_rate': 0.00017225776047459341, 'epoch': 7.35}

 61%|██████▏   | 17203/28080 [34:00:14<21:40:10,  7.17s/it]
 61%|██████▏   | 17204/28080 [34:00:21<21:36:38,  7.15s/it]
                                                           
{'loss': 0.6078, 'learning_rate': 0.00017223035495675157, 'epoch': 7.35}

 61%|██████▏   | 17204/28080 [34:00:21<21:36:38,  7.15s/it]
 61%|██████▏   | 17205/28080 [34:00:28<21:38:59,  7.17s/it]
                                                           
{'loss': 0.6189, 'learning_rate': 0.00017220295047355472, 'epoch': 7.35}

 61%|██████▏   | 17205/28080 [34:00:28<21:38:59,  7.17s/it]
 61%|██████▏   | 17206/28080 [34:00:35<21:42:38,  7.19s/it]
                                                           
{'loss': 0.6213, 'learning_rate': 0.0001721755470253672, 'epoch': 7.35}

 61%|██████▏   | 17206/28080 [34:00:35<21:42:38,  7.19s/it]
 61%|██████▏   | 17207/28080 [34:00:43<21:41:27,  7.18s/it]
                                                           
{'loss': 0.6108, 'learning_rate': 0.00017214814461255395, 'epoch': 7.35}

 61%|██████▏   | 17207/28080 [34:00:43<21:41:27,  7.18s/it]
 61%|██████▏   | 17208/28080 [34:00:50<21:42:38,  7.19s/it]
                                                           
{'loss': 0.6011, 'learning_rate': 0.00017212074323547913, 'epoch': 7.35}

 61%|██████▏   | 17208/28080 [34:00:50<21:42:38,  7.19s/it]
 61%|██████▏   | 17209/28080 [34:00:57<21:36:18,  7.15s/it]
                                                           
{'loss': 0.5968, 'learning_rate': 0.0001720933428945076, 'epoch': 7.35}

 61%|██████▏   | 17209/28080 [34:00:57<21:36:18,  7.15s/it]
 61%|██████▏   | 17210/28080 [34:01:04<21:36:45,  7.16s/it]
                                                           
{'loss': 0.6231, 'learning_rate': 0.0001720659435900037, 'epoch': 7.35}

 61%|██████▏   | 17210/28080 [34:01:04<21:36:45,  7.16s/it]
 61%|██████▏   | 17211/28080 [34:01:11<21:32:15,  7.13s/it]
                                                           
{'loss': 0.6034, 'learning_rate': 0.00017203854532233209, 'epoch': 7.35}

 61%|██████▏   | 17211/28080 [34:01:11<21:32:15,  7.13s/it]
 61%|██████▏   | 17212/28080 [34:01:18<21:38:14,  7.17s/it]
                                                           
{'loss': 0.6329, 'learning_rate': 0.00017201114809185713, 'epoch': 7.35}

 61%|██████▏   | 17212/28080 [34:01:18<21:38:14,  7.17s/it]
 61%|██████▏   | 17213/28080 [34:01:26<21:38:54,  7.17s/it]
                                                           
{'loss': 0.6125, 'learning_rate': 0.0001719837518989435, 'epoch': 7.35}

 61%|██████▏   | 17213/28080 [34:01:26<21:38:54,  7.17s/it]
 61%|██████▏   | 17214/28080 [34:01:33<21:35:24,  7.15s/it]
                                                           
{'loss': 0.6086, 'learning_rate': 0.00017195635674395547, 'epoch': 7.35}

 61%|██████▏   | 17214/28080 [34:01:33<21:35:24,  7.15s/it]
 61%|██████▏   | 17215/28080 [34:01:40<21:33:37,  7.14s/it]
                                                           
{'loss': 0.6071, 'learning_rate': 0.00017192896262725765, 'epoch': 7.35}

 61%|██████▏   | 17215/28080 [34:01:40<21:33:37,  7.14s/it]
 61%|██████▏   | 17216/28080 [34:01:47<21:32:44,  7.14s/it]
                                                           
{'loss': 0.6189, 'learning_rate': 0.00017190156954921437, 'epoch': 7.35}

 61%|██████▏   | 17216/28080 [34:01:47<21:32:44,  7.14s/it]
 61%|██████▏   | 17217/28080 [34:01:54<21:34:53,  7.15s/it]
                                                           
{'loss': 0.5894, 'learning_rate': 0.00017187417751019025, 'epoch': 7.35}

 61%|██████▏   | 17217/28080 [34:01:54<21:34:53,  7.15s/it]
 61%|██████▏   | 17218/28080 [34:02:01<21:36:42,  7.16s/it]
                                                           
{'loss': 0.6098, 'learning_rate': 0.00017184678651054945, 'epoch': 7.36}

 61%|██████▏   | 17218/28080 [34:02:01<21:36:42,  7.16s/it]
 61%|██████▏   | 17219/28080 [34:02:08<21:37:57,  7.17s/it]
                                                           
{'loss': 0.5934, 'learning_rate': 0.0001718193965506567, 'epoch': 7.36}

 61%|██████▏   | 17219/28080 [34:02:08<21:37:57,  7.17s/it]
 61%|██████▏   | 17220/28080 [34:02:15<21:30:54,  7.13s/it]
                                                           
{'loss': 0.608, 'learning_rate': 0.00017179200763087606, 'epoch': 7.36}

 61%|██████▏   | 17220/28080 [34:02:15<21:30:54,  7.13s/it]
 61%|██████▏   | 17221/28080 [34:02:23<21:31:17,  7.13s/it]
                                                           
{'loss': 0.6067, 'learning_rate': 0.00017176461975157222, 'epoch': 7.36}

 61%|██████▏   | 17221/28080 [34:02:23<21:31:17,  7.13s/it]
 61%|██████▏   | 17222/28080 [34:02:30<21:33:52,  7.15s/it]
                                                           
{'loss': 0.632, 'learning_rate': 0.00017173723291310938, 'epoch': 7.36}

 61%|██████▏   | 17222/28080 [34:02:30<21:33:52,  7.15s/it]
 61%|██████▏   | 17223/28080 [34:02:37<21:31:48,  7.14s/it]
                                                           
{'loss': 0.5984, 'learning_rate': 0.0001717098471158518, 'epoch': 7.36}

 61%|██████▏   | 17223/28080 [34:02:37<21:31:48,  7.14s/it]
 61%|██████▏   | 17224/28080 [34:02:44<21:33:19,  7.15s/it]
                                                           
{'loss': 0.615, 'learning_rate': 0.0001716824623601641, 'epoch': 7.36}

 61%|██████▏   | 17224/28080 [34:02:44<21:33:19,  7.15s/it]
 61%|██████▏   | 17225/28080 [34:02:51<21:35:41,  7.16s/it]
                                                           
{'loss': 0.6185, 'learning_rate': 0.0001716550786464103, 'epoch': 7.36}

 61%|██████▏   | 17225/28080 [34:02:51<21:35:41,  7.16s/it]
 61%|██████▏   | 17226/28080 [34:02:58<21:34:30,  7.16s/it]
                                                           
{'loss': 0.6025, 'learning_rate': 0.00017162769597495493, 'epoch': 7.36}

 61%|██████▏   | 17226/28080 [34:02:58<21:34:30,  7.16s/it]
 61%|██████▏   | 17227/28080 [34:03:06<21:32:44,  7.15s/it]
                                                           
{'loss': 0.6179, 'learning_rate': 0.00017160031434616213, 'epoch': 7.36}

 61%|██████▏   | 17227/28080 [34:03:06<21:32:44,  7.15s/it]
 61%|██████▏   | 17228/28080 [34:03:13<21:36:44,  7.17s/it]
                                                           
{'loss': 0.5943, 'learning_rate': 0.00017157293376039636, 'epoch': 7.36}

 61%|██████▏   | 17228/28080 [34:03:13<21:36:44,  7.17s/it]
 61%|██████▏   | 17229/28080 [34:03:20<21:33:10,  7.15s/it]
                                                           
{'loss': 0.6337, 'learning_rate': 0.00017154555421802176, 'epoch': 7.36}

 61%|██████▏   | 17229/28080 [34:03:20<21:33:10,  7.15s/it]
 61%|██████▏   | 17230/28080 [34:03:27<21:33:33,  7.15s/it]
                                                           
{'loss': 0.6226, 'learning_rate': 0.00017151817571940266, 'epoch': 7.36}

 61%|██████▏   | 17230/28080 [34:03:27<21:33:33,  7.15s/it]
 61%|██████▏   | 17231/28080 [34:03:34<21:32:28,  7.15s/it]
                                                           
{'loss': 0.614, 'learning_rate': 0.0001714907982649032, 'epoch': 7.36}

 61%|██████▏   | 17231/28080 [34:03:34<21:32:28,  7.15s/it]
 61%|██████▏   | 17232/28080 [34:03:41<21:28:28,  7.13s/it]
                                                           
{'loss': 0.6234, 'learning_rate': 0.00017146342185488775, 'epoch': 7.36}

 61%|██████▏   | 17232/28080 [34:03:41<21:28:28,  7.13s/it]
 61%|██████▏   | 17233/28080 [34:03:48<21:31:41,  7.14s/it]
                                                           
{'loss': 0.612, 'learning_rate': 0.00017143604648972037, 'epoch': 7.36}

 61%|██████▏   | 17233/28080 [34:03:48<21:31:41,  7.14s/it]
 61%|██████▏   | 17234/28080 [34:03:56<21:28:31,  7.13s/it]
                                                           
{'loss': 0.6408, 'learning_rate': 0.00017140867216976544, 'epoch': 7.36}

 61%|██████▏   | 17234/28080 [34:03:56<21:28:31,  7.13s/it]
 61%|██████▏   | 17235/28080 [34:04:02<21:16:04,  7.06s/it]
                                                           
{'loss': 0.6228, 'learning_rate': 0.00017138129889538697, 'epoch': 7.36}

 61%|██████▏   | 17235/28080 [34:04:02<21:16:04,  7.06s/it]
 61%|██████▏   | 17236/28080 [34:04:10<21:18:27,  7.07s/it]
                                                           
{'loss': 0.6248, 'learning_rate': 0.00017135392666694927, 'epoch': 7.36}

 61%|██████▏   | 17236/28080 [34:04:10<21:18:27,  7.07s/it]
 61%|██████▏   | 17237/28080 [34:04:17<21:20:42,  7.09s/it]
                                                           
{'loss': 0.6139, 'learning_rate': 0.00017132655548481634, 'epoch': 7.36}

 61%|██████▏   | 17237/28080 [34:04:17<21:20:42,  7.09s/it]
 61%|██████▏   | 17238/28080 [34:04:24<21:24:58,  7.11s/it]
                                                           
{'loss': 0.6304, 'learning_rate': 0.00017129918534935257, 'epoch': 7.36}

 61%|██████▏   | 17238/28080 [34:04:24<21:24:58,  7.11s/it]
 61%|██████▏   | 17239/28080 [34:04:31<21:17:22,  7.07s/it]
                                                           
{'loss': 0.6162, 'learning_rate': 0.0001712718162609218, 'epoch': 7.36}

 61%|██████▏   | 17239/28080 [34:04:31<21:17:22,  7.07s/it]
 61%|██████▏   | 17240/28080 [34:04:38<21:17:19,  7.07s/it]
                                                           
{'loss': 0.6227, 'learning_rate': 0.00017124444821988837, 'epoch': 7.36}

 61%|██████▏   | 17240/28080 [34:04:38<21:17:19,  7.07s/it]
 61%|██████▏   | 17241/28080 [34:04:45<21:16:09,  7.06s/it]
                                                           
{'loss': 0.6093, 'learning_rate': 0.0001712170812266163, 'epoch': 7.37}

 61%|██████▏   | 17241/28080 [34:04:45<21:16:09,  7.06s/it]
 61%|██████▏   | 17242/28080 [34:04:52<21:20:50,  7.09s/it]
                                                           
{'loss': 0.6019, 'learning_rate': 0.0001711897152814697, 'epoch': 7.37}

 61%|██████▏   | 17242/28080 [34:04:52<21:20:50,  7.09s/it]
 61%|██████▏   | 17243/28080 [34:04:59<21:22:49,  7.10s/it]
                                                           
{'loss': 0.6061, 'learning_rate': 0.00017116235038481262, 'epoch': 7.37}

 61%|██████▏   | 17243/28080 [34:04:59<21:22:49,  7.10s/it]
 61%|██████▏   | 17244/28080 [34:05:06<21:24:42,  7.11s/it]
                                                           
{'loss': 0.6107, 'learning_rate': 0.00017113498653700918, 'epoch': 7.37}

 61%|██████▏   | 17244/28080 [34:05:06<21:24:42,  7.11s/it]
 61%|██████▏   | 17245/28080 [34:05:14<21:30:49,  7.15s/it]
                                                           
{'loss': 0.614, 'learning_rate': 0.0001711076237384233, 'epoch': 7.37}

 61%|██████▏   | 17245/28080 [34:05:14<21:30:49,  7.15s/it]
 61%|██████▏   | 17246/28080 [34:05:21<21:24:32,  7.11s/it]
                                                           
{'loss': 0.6109, 'learning_rate': 0.0001710802619894192, 'epoch': 7.37}

 61%|██████▏   | 17246/28080 [34:05:21<21:24:32,  7.11s/it]
 61%|██████▏   | 17247/28080 [34:05:28<21:27:02,  7.13s/it]
                                                           
{'loss': 0.6093, 'learning_rate': 0.00017105290129036077, 'epoch': 7.37}

 61%|██████▏   | 17247/28080 [34:05:28<21:27:02,  7.13s/it]
 61%|██████▏   | 17248/28080 [34:05:35<21:27:14,  7.13s/it]
                                                           
{'loss': 0.619, 'learning_rate': 0.00017102554164161198, 'epoch': 7.37}

 61%|██████▏   | 17248/28080 [34:05:35<21:27:14,  7.13s/it]
 61%|██████▏   | 17249/28080 [34:05:42<21:27:04,  7.13s/it]
                                                           
{'loss': 0.6244, 'learning_rate': 0.00017099818304353696, 'epoch': 7.37}

 61%|██████▏   | 17249/28080 [34:05:42<21:27:04,  7.13s/it]
 61%|██████▏   | 17250/28080 [34:05:49<21:24:32,  7.12s/it]
                                                           
{'loss': 0.6122, 'learning_rate': 0.00017097082549649955, 'epoch': 7.37}

 61%|██████▏   | 17250/28080 [34:05:49<21:24:32,  7.12s/it]
 61%|██████▏   | 17251/28080 [34:05:56<21:19:13,  7.09s/it]
                                                           
{'loss': 0.6196, 'learning_rate': 0.00017094346900086381, 'epoch': 7.37}

 61%|██████▏   | 17251/28080 [34:05:56<21:19:13,  7.09s/it]
 61%|██████▏   | 17252/28080 [34:06:03<21:23:12,  7.11s/it]
                                                           
{'loss': 0.6327, 'learning_rate': 0.00017091611355699366, 'epoch': 7.37}

 61%|██████▏   | 17252/28080 [34:06:03<21:23:12,  7.11s/it]
 61%|██████▏   | 17253/28080 [34:06:10<21:17:50,  7.08s/it]
                                                           
{'loss': 0.608, 'learning_rate': 0.00017088875916525305, 'epoch': 7.37}

 61%|██████▏   | 17253/28080 [34:06:10<21:17:50,  7.08s/it]
 61%|██████▏   | 17254/28080 [34:06:17<21:16:39,  7.08s/it]
                                                           
{'loss': 0.6143, 'learning_rate': 0.00017086140582600576, 'epoch': 7.37}

 61%|██████▏   | 17254/28080 [34:06:17<21:16:39,  7.08s/it]
 61%|██████▏   | 17255/28080 [34:06:25<21:26:56,  7.13s/it]
                                                           
{'loss': 0.6196, 'learning_rate': 0.00017083405353961602, 'epoch': 7.37}

 61%|██████▏   | 17255/28080 [34:06:25<21:26:56,  7.13s/it]
 61%|██████▏   | 17256/28080 [34:06:32<21:30:02,  7.15s/it]
                                                           
{'loss': 0.5899, 'learning_rate': 0.00017080670230644734, 'epoch': 7.37}

 61%|██████▏   | 17256/28080 [34:06:32<21:30:02,  7.15s/it]
 61%|██████▏   | 17257/28080 [34:06:39<21:24:27,  7.12s/it]
                                                           
{'loss': 0.6072, 'learning_rate': 0.0001707793521268639, 'epoch': 7.37}

 61%|██████▏   | 17257/28080 [34:06:39<21:24:27,  7.12s/it]
 61%|██████▏   | 17258/28080 [34:06:46<21:28:30,  7.14s/it]
                                                           
{'loss': 0.6071, 'learning_rate': 0.0001707520030012294, 'epoch': 7.37}

 61%|██████▏   | 17258/28080 [34:06:46<21:28:30,  7.14s/it]
 61%|██████▏   | 17259/28080 [34:06:53<21:24:26,  7.12s/it]
                                                           
{'loss': 0.609, 'learning_rate': 0.0001707246549299078, 'epoch': 7.37}

 61%|██████▏   | 17259/28080 [34:06:53<21:24:26,  7.12s/it]
 61%|██████▏   | 17260/28080 [34:07:00<21:28:27,  7.14s/it]
                                                           
{'loss': 0.5971, 'learning_rate': 0.00017069730791326282, 'epoch': 7.37}

 61%|██████▏   | 17260/28080 [34:07:00<21:28:27,  7.14s/it]
 61%|██████▏   | 17261/28080 [34:07:07<21:27:13,  7.14s/it]
                                                           
{'loss': 0.6243, 'learning_rate': 0.0001706699619516584, 'epoch': 7.37}

 61%|██████▏   | 17261/28080 [34:07:07<21:27:13,  7.14s/it]
 61%|██████▏   | 17262/28080 [34:07:15<21:28:11,  7.14s/it]
                                                           
{'loss': 0.6195, 'learning_rate': 0.00017064261704545825, 'epoch': 7.37}

 61%|██████▏   | 17262/28080 [34:07:15<21:28:11,  7.14s/it]
 61%|██████▏   | 17263/28080 [34:07:22<21:26:48,  7.14s/it]
                                                           
{'loss': 0.6103, 'learning_rate': 0.00017061527319502627, 'epoch': 7.37}

 61%|██████▏   | 17263/28080 [34:07:22<21:26:48,  7.14s/it]
 61%|██████▏   | 17264/28080 [34:07:29<21:18:48,  7.09s/it]
                                                           
{'loss': 0.6128, 'learning_rate': 0.00017058793040072612, 'epoch': 7.38}

 61%|██████▏   | 17264/28080 [34:07:29<21:18:48,  7.09s/it]
 61%|██████▏   | 17265/28080 [34:07:36<21:21:32,  7.11s/it]
                                                           
{'loss': 0.6244, 'learning_rate': 0.00017056058866292168, 'epoch': 7.38}

 61%|██████▏   | 17265/28080 [34:07:36<21:21:32,  7.11s/it]
 61%|██████▏   | 17266/28080 [34:07:43<21:24:20,  7.13s/it]
                                                           
{'loss': 0.6068, 'learning_rate': 0.00017053324798197662, 'epoch': 7.38}

 61%|██████▏   | 17266/28080 [34:07:43<21:24:20,  7.13s/it]
 61%|██████▏   | 17267/28080 [34:07:50<21:27:04,  7.14s/it]
                                                           
{'loss': 0.6288, 'learning_rate': 0.00017050590835825474, 'epoch': 7.38}

 61%|██████▏   | 17267/28080 [34:07:50<21:27:04,  7.14s/it]
 61%|██████▏   | 17268/28080 [34:07:57<21:26:30,  7.14s/it]
                                                           
{'loss': 0.5986, 'learning_rate': 0.00017047856979211969, 'epoch': 7.38}

 61%|██████▏   | 17268/28080 [34:07:57<21:26:30,  7.14s/it]
 61%|██████▏   | 17269/28080 [34:08:04<21:23:42,  7.12s/it]
                                                           
{'loss': 0.6074, 'learning_rate': 0.00017045123228393534, 'epoch': 7.38}

 61%|██████▏   | 17269/28080 [34:08:04<21:23:42,  7.12s/it]
 62%|██████▏   | 17270/28080 [34:08:12<21:24:15,  7.13s/it]
                                                           
{'loss': 0.5975, 'learning_rate': 0.00017042389583406508, 'epoch': 7.38}

 62%|██████▏   | 17270/28080 [34:08:12<21:24:15,  7.13s/it]
 62%|██████▏   | 17271/28080 [34:08:19<21:22:37,  7.12s/it]
                                                           
{'loss': 0.612, 'learning_rate': 0.000170396560442873, 'epoch': 7.38}

 62%|██████▏   | 17271/28080 [34:08:19<21:22:37,  7.12s/it]
 62%|██████▏   | 17272/28080 [34:08:26<21:24:32,  7.13s/it]
                                                           
{'loss': 0.6245, 'learning_rate': 0.00017036922611072253, 'epoch': 7.38}

 62%|██████▏   | 17272/28080 [34:08:26<21:24:32,  7.13s/it]
 62%|██████▏   | 17273/28080 [34:08:33<21:28:05,  7.15s/it]
                                                           
{'loss': 0.6027, 'learning_rate': 0.00017034189283797723, 'epoch': 7.38}

 62%|██████▏   | 17273/28080 [34:08:33<21:28:05,  7.15s/it]
 62%|██████▏   | 17274/28080 [34:08:40<21:22:02,  7.12s/it]
                                                           
{'loss': 0.6253, 'learning_rate': 0.00017031456062500104, 'epoch': 7.38}

 62%|██████▏   | 17274/28080 [34:08:40<21:22:02,  7.12s/it]
 62%|██████▏   | 17275/28080 [34:08:47<21:14:42,  7.08s/it]
                                                           
{'loss': 0.6156, 'learning_rate': 0.00017028722947215724, 'epoch': 7.38}

 62%|██████▏   | 17275/28080 [34:08:47<21:14:42,  7.08s/it]
 62%|██████▏   | 17276/28080 [34:08:54<21:15:26,  7.08s/it]
                                                           
{'loss': 0.6199, 'learning_rate': 0.00017025989937980975, 'epoch': 7.38}

 62%|██████▏   | 17276/28080 [34:08:54<21:15:26,  7.08s/it]
 62%|██████▏   | 17277/28080 [34:09:01<21:20:58,  7.11s/it]
                                                           
{'loss': 0.6191, 'learning_rate': 0.00017023257034832194, 'epoch': 7.38}

 62%|██████▏   | 17277/28080 [34:09:01<21:20:58,  7.11s/it]
 62%|██████▏   | 17278/28080 [34:09:08<21:19:48,  7.11s/it]
                                                           
{'loss': 0.6313, 'learning_rate': 0.00017020524237805755, 'epoch': 7.38}

 62%|██████▏   | 17278/28080 [34:09:08<21:19:48,  7.11s/it]
 62%|██████▏   | 17279/28080 [34:09:16<21:24:55,  7.14s/it]
                                                           
{'loss': 0.617, 'learning_rate': 0.00017017791546938005, 'epoch': 7.38}

 62%|██████▏   | 17279/28080 [34:09:16<21:24:55,  7.14s/it]
 62%|██████▏   | 17280/28080 [34:09:23<21:20:48,  7.12s/it]
                                                           
{'loss': 0.6065, 'learning_rate': 0.00017015058962265307, 'epoch': 7.38}

 62%|██████▏   | 17280/28080 [34:09:23<21:20:48,  7.12s/it]
 62%|██████▏   | 17281/28080 [34:09:30<21:25:34,  7.14s/it]
                                                           
{'loss': 0.6318, 'learning_rate': 0.0001701232648382401, 'epoch': 7.38}

 62%|██████▏   | 17281/28080 [34:09:30<21:25:34,  7.14s/it]
 62%|██████▏   | 17282/28080 [34:09:37<21:22:23,  7.13s/it]
                                                           
{'loss': 0.6257, 'learning_rate': 0.00017009594111650473, 'epoch': 7.38}

 62%|██████▏   | 17282/28080 [34:09:37<21:22:23,  7.13s/it]
 62%|██████▏   | 17283/28080 [34:09:44<21:19:20,  7.11s/it]
                                                           
{'loss': 0.6224, 'learning_rate': 0.00017006861845781035, 'epoch': 7.38}

 62%|██████▏   | 17283/28080 [34:09:44<21:19:20,  7.11s/it]
 62%|██████▏   | 17284/28080 [34:09:51<21:21:48,  7.12s/it]
                                                           
{'loss': 0.6085, 'learning_rate': 0.00017004129686252063, 'epoch': 7.38}

 62%|██████▏   | 17284/28080 [34:09:51<21:21:48,  7.12s/it]
 62%|██████▏   | 17285/28080 [34:09:58<21:18:08,  7.10s/it]
                                                           
{'loss': 0.6282, 'learning_rate': 0.00017001397633099882, 'epoch': 7.38}

 62%|██████▏   | 17285/28080 [34:09:58<21:18:08,  7.10s/it]
 62%|██████▏   | 17286/28080 [34:10:05<21:12:47,  7.07s/it]
                                                           
{'loss': 0.6351, 'learning_rate': 0.00016998665686360873, 'epoch': 7.38}

 62%|██████▏   | 17286/28080 [34:10:05<21:12:47,  7.07s/it]
 62%|██████▏   | 17287/28080 [34:10:12<21:13:19,  7.08s/it]
                                                           
{'loss': 0.603, 'learning_rate': 0.00016995933846071347, 'epoch': 7.38}

 62%|██████▏   | 17287/28080 [34:10:12<21:13:19,  7.08s/it]
 62%|██████▏   | 17288/28080 [34:10:20<21:19:44,  7.11s/it]
                                                           
{'loss': 0.634, 'learning_rate': 0.0001699320211226767, 'epoch': 7.39}

 62%|██████▏   | 17288/28080 [34:10:20<21:19:44,  7.11s/it]
 62%|██████▏   | 17289/28080 [34:10:27<21:15:59,  7.09s/it]
                                                           
{'loss': 0.6277, 'learning_rate': 0.0001699047048498618, 'epoch': 7.39}

 62%|██████▏   | 17289/28080 [34:10:27<21:15:59,  7.09s/it]
 62%|██████▏   | 17290/28080 [34:10:34<21:19:22,  7.11s/it]
                                                           
{'loss': 0.592, 'learning_rate': 0.00016987738964263215, 'epoch': 7.39}

 62%|██████▏   | 17290/28080 [34:10:34<21:19:22,  7.11s/it]
 62%|██████▏   | 17291/28080 [34:10:41<21:24:14,  7.14s/it]
                                                           
{'loss': 0.6027, 'learning_rate': 0.00016985007550135116, 'epoch': 7.39}

 62%|██████▏   | 17291/28080 [34:10:41<21:24:14,  7.14s/it]
 62%|██████▏   | 17292/28080 [34:10:48<21:23:37,  7.14s/it]
                                                           
{'loss': 0.5974, 'learning_rate': 0.0001698227624263823, 'epoch': 7.39}

 62%|██████▏   | 17292/28080 [34:10:48<21:23:37,  7.14s/it]
 62%|██████▏   | 17293/28080 [34:10:55<21:19:04,  7.11s/it]
                                                           
{'loss': 0.594, 'learning_rate': 0.0001697954504180888, 'epoch': 7.39}

 62%|██████▏   | 17293/28080 [34:10:55<21:19:04,  7.11s/it]
 62%|██████▏   | 17294/28080 [34:11:02<21:20:07,  7.12s/it]
                                                           
{'loss': 0.5966, 'learning_rate': 0.00016976813947683418, 'epoch': 7.39}

 62%|██████▏   | 17294/28080 [34:11:02<21:20:07,  7.12s/it]
 62%|██████▏   | 17295/28080 [34:11:09<21:18:50,  7.11s/it]
                                                           
{'loss': 0.5828, 'learning_rate': 0.0001697408296029816, 'epoch': 7.39}

 62%|██████▏   | 17295/28080 [34:11:09<21:18:50,  7.11s/it]
 62%|██████▏   | 17296/28080 [34:11:17<21:28:08,  7.17s/it]
                                                           
{'loss': 0.6047, 'learning_rate': 0.00016971352079689453, 'epoch': 7.39}

 62%|██████▏   | 17296/28080 [34:11:17<21:28:08,  7.17s/it]
 62%|██████▏   | 17297/28080 [34:11:24<21:29:39,  7.18s/it]
                                                           
{'loss': 0.6241, 'learning_rate': 0.00016968621305893624, 'epoch': 7.39}

 62%|██████▏   | 17297/28080 [34:11:24<21:29:39,  7.18s/it]
 62%|██████▏   | 17298/28080 [34:11:31<21:25:36,  7.15s/it]
                                                           
{'loss': 0.6254, 'learning_rate': 0.00016965890638947, 'epoch': 7.39}

 62%|██████▏   | 17298/28080 [34:11:31<21:25:36,  7.15s/it]
 62%|██████▏   | 17299/28080 [34:11:38<21:24:51,  7.15s/it]
                                                           
{'loss': 0.6194, 'learning_rate': 0.00016963160078885918, 'epoch': 7.39}

 62%|██████▏   | 17299/28080 [34:11:38<21:24:51,  7.15s/it]
 62%|██████▏   | 17300/28080 [34:11:45<21:28:33,  7.17s/it]
                                                           
{'loss': 0.5917, 'learning_rate': 0.00016960429625746692, 'epoch': 7.39}

 62%|██████▏   | 17300/28080 [34:11:45<21:28:33,  7.17s/it]
 62%|██████▏   | 17301/28080 [34:11:52<21:23:07,  7.14s/it]
                                                           
{'loss': 0.6096, 'learning_rate': 0.00016957699279565664, 'epoch': 7.39}

 62%|██████▏   | 17301/28080 [34:11:52<21:23:07,  7.14s/it]
 62%|██████▏   | 17302/28080 [34:12:00<21:23:21,  7.14s/it]
                                                           
{'loss': 0.6029, 'learning_rate': 0.00016954969040379136, 'epoch': 7.39}

 62%|██████▏   | 17302/28080 [34:12:00<21:23:21,  7.14s/it]
 62%|██████▏   | 17303/28080 [34:12:07<21:27:23,  7.17s/it]
                                                           
{'loss': 0.6175, 'learning_rate': 0.00016952238908223466, 'epoch': 7.39}

 62%|██████▏   | 17303/28080 [34:12:07<21:27:23,  7.17s/it]
 62%|██████▏   | 17304/28080 [34:12:14<21:25:21,  7.16s/it]
                                                           
{'loss': 0.6224, 'learning_rate': 0.00016949508883134934, 'epoch': 7.39}

 62%|██████▏   | 17304/28080 [34:12:14<21:25:21,  7.16s/it]
 62%|██████▏   | 17305/28080 [34:12:21<21:16:56,  7.11s/it]
                                                           
{'loss': 0.6094, 'learning_rate': 0.000169467789651499, 'epoch': 7.39}

 62%|██████▏   | 17305/28080 [34:12:21<21:16:56,  7.11s/it]
 62%|██████▏   | 17306/28080 [34:12:28<21:20:39,  7.13s/it]
                                                           
{'loss': 0.6171, 'learning_rate': 0.00016944049154304648, 'epoch': 7.39}

 62%|██████▏   | 17306/28080 [34:12:28<21:20:39,  7.13s/it]
 62%|██████▏   | 17307/28080 [34:12:35<21:24:21,  7.15s/it]
                                                           
{'loss': 0.6176, 'learning_rate': 0.00016941319450635524, 'epoch': 7.39}

 62%|██████▏   | 17307/28080 [34:12:35<21:24:21,  7.15s/it]
 62%|██████▏   | 17308/28080 [34:12:43<21:24:20,  7.15s/it]
                                                           
{'loss': 0.621, 'learning_rate': 0.0001693858985417882, 'epoch': 7.39}

 62%|██████▏   | 17308/28080 [34:12:43<21:24:20,  7.15s/it]
 62%|██████▏   | 17309/28080 [34:12:50<21:15:22,  7.10s/it]
                                                           
{'loss': 0.6286, 'learning_rate': 0.00016935860364970874, 'epoch': 7.39}

 62%|██████▏   | 17309/28080 [34:12:50<21:15:22,  7.10s/it]
 62%|██████▏   | 17310/28080 [34:12:57<21:20:17,  7.13s/it]
                                                           
{'loss': 0.5975, 'learning_rate': 0.00016933130983047974, 'epoch': 7.39}

 62%|██████▏   | 17310/28080 [34:12:57<21:20:17,  7.13s/it]
 62%|██████▏   | 17311/28080 [34:13:04<21:22:09,  7.14s/it]
                                                           
{'loss': 0.6142, 'learning_rate': 0.00016930401708446452, 'epoch': 7.4}

 62%|██████▏   | 17311/28080 [34:13:04<21:22:09,  7.14s/it]
 62%|██████▏   | 17312/28080 [34:13:11<21:15:21,  7.11s/it]
                                                           
{'loss': 0.5976, 'learning_rate': 0.00016927672541202604, 'epoch': 7.4}

 62%|██████▏   | 17312/28080 [34:13:11<21:15:21,  7.11s/it]
 62%|██████▏   | 17313/28080 [34:13:18<21:18:52,  7.13s/it]
                                                           
{'loss': 0.6214, 'learning_rate': 0.00016924943481352756, 'epoch': 7.4}

 62%|██████▏   | 17313/28080 [34:13:18<21:18:52,  7.13s/it]
 62%|██████▏   | 17314/28080 [34:13:25<21:16:31,  7.11s/it]
                                                           
{'loss': 0.6095, 'learning_rate': 0.00016922214528933193, 'epoch': 7.4}

 62%|██████▏   | 17314/28080 [34:13:25<21:16:31,  7.11s/it]
 62%|██████▏   | 17315/28080 [34:13:32<21:20:28,  7.14s/it]
                                                           
{'loss': 0.6104, 'learning_rate': 0.0001691948568398024, 'epoch': 7.4}

 62%|██████▏   | 17315/28080 [34:13:32<21:20:28,  7.14s/it]
 62%|██████▏   | 17316/28080 [34:13:39<21:12:34,  7.09s/it]
                                                           
{'loss': 0.6185, 'learning_rate': 0.0001691675694653018, 'epoch': 7.4}

 62%|██████▏   | 17316/28080 [34:13:39<21:12:34,  7.09s/it]
 62%|██████▏   | 17317/28080 [34:13:47<21:22:29,  7.15s/it]
                                                           
{'loss': 0.6053, 'learning_rate': 0.0001691402831661935, 'epoch': 7.4}

 62%|██████▏   | 17317/28080 [34:13:47<21:22:29,  7.15s/it]
 62%|██████▏   | 17318/28080 [34:13:54<21:23:51,  7.16s/it]
                                                           
{'loss': 0.6072, 'learning_rate': 0.00016911299794284017, 'epoch': 7.4}

 62%|██████▏   | 17318/28080 [34:13:54<21:23:51,  7.16s/it]
 62%|██████▏   | 17319/28080 [34:14:01<21:15:34,  7.11s/it]
                                                           
{'loss': 0.6166, 'learning_rate': 0.000169085713795605, 'epoch': 7.4}

 62%|██████▏   | 17319/28080 [34:14:01<21:15:34,  7.11s/it]
 62%|██████▏   | 17320/28080 [34:14:08<21:14:41,  7.11s/it]
                                                           
{'loss': 0.6242, 'learning_rate': 0.00016905843072485095, 'epoch': 7.4}

 62%|██████▏   | 17320/28080 [34:14:08<21:14:41,  7.11s/it]
 62%|██████▏   | 17321/28080 [34:14:15<21:15:37,  7.11s/it]
                                                           
{'loss': 0.6103, 'learning_rate': 0.00016903114873094096, 'epoch': 7.4}

 62%|██████▏   | 17321/28080 [34:14:15<21:15:37,  7.11s/it]
 62%|██████▏   | 17322/28080 [34:14:22<21:24:13,  7.16s/it]
                                                           
{'loss': 0.6006, 'learning_rate': 0.0001690038678142381, 'epoch': 7.4}

 62%|██████▏   | 17322/28080 [34:14:22<21:24:13,  7.16s/it]
 62%|██████▏   | 17323/28080 [34:14:29<21:11:18,  7.09s/it]
                                                           
{'loss': 0.617, 'learning_rate': 0.00016897658797510506, 'epoch': 7.4}

 62%|██████▏   | 17323/28080 [34:14:29<21:11:18,  7.09s/it]
 62%|██████▏   | 17324/28080 [34:14:36<21:14:09,  7.11s/it]
                                                           
{'loss': 0.5967, 'learning_rate': 0.000168949309213905, 'epoch': 7.4}

 62%|██████▏   | 17324/28080 [34:14:36<21:14:09,  7.11s/it]
 62%|██████▏   | 17325/28080 [34:14:43<21:14:00,  7.11s/it]
                                                           
{'loss': 0.607, 'learning_rate': 0.00016892203153100077, 'epoch': 7.4}

 62%|██████▏   | 17325/28080 [34:14:43<21:14:00,  7.11s/it]
 62%|██████▏   | 17326/28080 [34:14:50<21:09:37,  7.08s/it]
                                                           
{'loss': 0.6375, 'learning_rate': 0.00016889475492675528, 'epoch': 7.4}

 62%|██████▏   | 17326/28080 [34:14:51<21:09:37,  7.08s/it]
 62%|██████▏   | 17327/28080 [34:14:58<21:08:07,  7.08s/it]
                                                           
{'loss': 0.6045, 'learning_rate': 0.00016886747940153137, 'epoch': 7.4}

 62%|██████▏   | 17327/28080 [34:14:58<21:08:07,  7.08s/it]
 62%|██████▏   | 17328/28080 [34:15:05<21:12:45,  7.10s/it]
                                                           
{'loss': 0.6374, 'learning_rate': 0.00016884020495569197, 'epoch': 7.4}

 62%|██████▏   | 17328/28080 [34:15:05<21:12:45,  7.10s/it]
 62%|██████▏   | 17329/28080 [34:15:12<21:10:52,  7.09s/it]
                                                           
{'loss': 0.615, 'learning_rate': 0.00016881293158959988, 'epoch': 7.4}

 62%|██████▏   | 17329/28080 [34:15:12<21:10:52,  7.09s/it]
 62%|██████▏   | 17330/28080 [34:15:19<21:14:16,  7.11s/it]
                                                           
{'loss': 0.6238, 'learning_rate': 0.00016878565930361807, 'epoch': 7.4}

 62%|██████▏   | 17330/28080 [34:15:19<21:14:16,  7.11s/it]
 62%|██████▏   | 17331/28080 [34:15:26<21:22:19,  7.16s/it]
                                                           
{'loss': 0.6072, 'learning_rate': 0.00016875838809810918, 'epoch': 7.4}

 62%|██████▏   | 17331/28080 [34:15:26<21:22:19,  7.16s/it]
 62%|██████▏   | 17332/28080 [34:15:33<21:22:39,  7.16s/it]
                                                           
{'loss': 0.6156, 'learning_rate': 0.00016873111797343615, 'epoch': 7.4}

 62%|██████▏   | 17332/28080 [34:15:33<21:22:39,  7.16s/it]
 62%|██████▏   | 17333/28080 [34:15:41<21:23:52,  7.17s/it]
                                                           
{'loss': 0.6159, 'learning_rate': 0.0001687038489299617, 'epoch': 7.4}

 62%|██████▏   | 17333/28080 [34:15:41<21:23:52,  7.17s/it]
 62%|██████▏   | 17334/28080 [34:15:48<21:15:09,  7.12s/it]
                                                           
{'loss': 0.5943, 'learning_rate': 0.00016867658096804882, 'epoch': 7.4}

 62%|██████▏   | 17334/28080 [34:15:48<21:15:09,  7.12s/it]
 62%|██████▏   | 17335/28080 [34:15:55<21:14:50,  7.12s/it]
                                                           
{'loss': 0.6144, 'learning_rate': 0.00016864931408805997, 'epoch': 7.41}

 62%|██████▏   | 17335/28080 [34:15:55<21:14:50,  7.12s/it]
 62%|██████▏   | 17336/28080 [34:16:02<21:12:37,  7.11s/it]
                                                           
{'loss': 0.6093, 'learning_rate': 0.00016862204829035823, 'epoch': 7.41}

 62%|██████▏   | 17336/28080 [34:16:02<21:12:37,  7.11s/it]
 62%|██████▏   | 17337/28080 [34:16:09<21:13:49,  7.11s/it]
                                                           
{'loss': 0.6264, 'learning_rate': 0.00016859478357530603, 'epoch': 7.41}

 62%|██████▏   | 17337/28080 [34:16:09<21:13:49,  7.11s/it]
 62%|██████▏   | 17338/28080 [34:16:16<21:18:30,  7.14s/it]
                                                           
{'loss': 0.6262, 'learning_rate': 0.00016856751994326637, 'epoch': 7.41}

 62%|██████▏   | 17338/28080 [34:16:16<21:18:30,  7.14s/it]
 62%|██████▏   | 17339/28080 [34:16:23<21:17:04,  7.13s/it]
                                                           
{'loss': 0.6199, 'learning_rate': 0.00016854025739460176, 'epoch': 7.41}

 62%|██████▏   | 17339/28080 [34:16:23<21:17:04,  7.13s/it]
 62%|██████▏   | 17340/28080 [34:16:30<21:18:55,  7.14s/it]
                                                           
{'loss': 0.5896, 'learning_rate': 0.00016851299592967505, 'epoch': 7.41}

 62%|██████▏   | 17340/28080 [34:16:30<21:18:55,  7.14s/it]
 62%|██████▏   | 17341/28080 [34:16:37<21:13:34,  7.12s/it]
                                                           
{'loss': 0.6395, 'learning_rate': 0.00016848573554884884, 'epoch': 7.41}

 62%|██████▏   | 17341/28080 [34:16:37<21:13:34,  7.12s/it]
 62%|██████▏   | 17342/28080 [34:16:45<21:13:32,  7.12s/it]
                                                           
{'loss': 0.6068, 'learning_rate': 0.00016845847625248587, 'epoch': 7.41}

 62%|██████▏   | 17342/28080 [34:16:45<21:13:32,  7.12s/it]
 62%|██████▏   | 17343/28080 [34:16:52<21:09:33,  7.09s/it]
                                                           
{'loss': 0.6341, 'learning_rate': 0.0001684312180409487, 'epoch': 7.41}

 62%|██████▏   | 17343/28080 [34:16:52<21:09:33,  7.09s/it]
 62%|██████▏   | 17344/28080 [34:16:59<21:12:07,  7.11s/it]
                                                           
{'loss': 0.6261, 'learning_rate': 0.00016840396091460005, 'epoch': 7.41}

 62%|██████▏   | 17344/28080 [34:16:59<21:12:07,  7.11s/it]
 62%|██████▏   | 17345/28080 [34:17:06<21:11:54,  7.11s/it]
                                                           
{'loss': 0.6087, 'learning_rate': 0.00016837670487380253, 'epoch': 7.41}

 62%|██████▏   | 17345/28080 [34:17:06<21:11:54,  7.11s/it]
 62%|██████▏   | 17346/28080 [34:17:13<21:17:00,  7.14s/it]
                                                           
{'loss': 0.6169, 'learning_rate': 0.0001683494499189187, 'epoch': 7.41}

 62%|██████▏   | 17346/28080 [34:17:13<21:17:00,  7.14s/it]
 62%|██████▏   | 17347/28080 [34:17:20<21:16:16,  7.13s/it]
                                                           
{'loss': 0.6052, 'learning_rate': 0.00016832219605031126, 'epoch': 7.41}

 62%|██████▏   | 17347/28080 [34:17:20<21:16:16,  7.13s/it]
 62%|██████▏   | 17348/28080 [34:17:27<21:17:47,  7.14s/it]
                                                           
{'loss': 0.6033, 'learning_rate': 0.0001682949432683427, 'epoch': 7.41}

 62%|██████▏   | 17348/28080 [34:17:27<21:17:47,  7.14s/it]
 62%|██████▏   | 17349/28080 [34:17:35<21:19:30,  7.15s/it]
                                                           
{'loss': 0.6136, 'learning_rate': 0.00016826769157337568, 'epoch': 7.41}

 62%|██████▏   | 17349/28080 [34:17:35<21:19:30,  7.15s/it]
 62%|██████▏   | 17350/28080 [34:17:42<21:12:02,  7.11s/it]
                                                           
{'loss': 0.588, 'learning_rate': 0.00016824044096577258, 'epoch': 7.41}

 62%|██████▏   | 17350/28080 [34:17:42<21:12:02,  7.11s/it]
 62%|██████▏   | 17351/28080 [34:17:49<21:10:18,  7.10s/it]
                                                           
{'loss': 0.6203, 'learning_rate': 0.00016821319144589623, 'epoch': 7.41}

 62%|██████▏   | 17351/28080 [34:17:49<21:10:18,  7.10s/it]
 62%|██████▏   | 17352/28080 [34:17:56<21:13:21,  7.12s/it]
                                                           
{'loss': 0.6094, 'learning_rate': 0.00016818594301410883, 'epoch': 7.41}

 62%|██████▏   | 17352/28080 [34:17:56<21:13:21,  7.12s/it]
 62%|██████▏   | 17353/28080 [34:18:03<21:09:28,  7.10s/it]
                                                           
{'loss': 0.6366, 'learning_rate': 0.00016815869567077322, 'epoch': 7.41}

 62%|██████▏   | 17353/28080 [34:18:03<21:09:28,  7.10s/it]
 62%|██████▏   | 17354/28080 [34:18:10<21:07:02,  7.09s/it]
                                                           
{'loss': 0.6188, 'learning_rate': 0.00016813144941625158, 'epoch': 7.41}

 62%|██████▏   | 17354/28080 [34:18:10<21:07:02,  7.09s/it]
 62%|██████▏   | 17355/28080 [34:18:17<21:06:24,  7.08s/it]
                                                           
{'loss': 0.6101, 'learning_rate': 0.00016810420425090664, 'epoch': 7.41}

 62%|██████▏   | 17355/28080 [34:18:17<21:06:24,  7.08s/it]
 62%|██████▏   | 17356/28080 [34:18:24<21:07:16,  7.09s/it]
                                                           
{'loss': 0.6165, 'learning_rate': 0.00016807696017510072, 'epoch': 7.41}

 62%|██████▏   | 17356/28080 [34:18:24<21:07:16,  7.09s/it]
 62%|██████▏   | 17357/28080 [34:18:31<21:06:07,  7.08s/it]
                                                           
{'loss': 0.6354, 'learning_rate': 0.0001680497171891964, 'epoch': 7.41}

 62%|██████▏   | 17357/28080 [34:18:31<21:06:07,  7.08s/it]
 62%|██████▏   | 17358/28080 [34:18:38<21:06:33,  7.09s/it]
                                                           
{'loss': 0.6245, 'learning_rate': 0.000168022475293556, 'epoch': 7.42}

 62%|██████▏   | 17358/28080 [34:18:38<21:06:33,  7.09s/it]
 62%|██████▏   | 17359/28080 [34:18:45<21:08:41,  7.10s/it]
                                                           
{'loss': 0.6091, 'learning_rate': 0.00016799523448854205, 'epoch': 7.42}

 62%|██████▏   | 17359/28080 [34:18:45<21:08:41,  7.10s/it]
 62%|██████▏   | 17360/28080 [34:18:53<21:13:57,  7.13s/it]
                                                           
{'loss': 0.6195, 'learning_rate': 0.0001679679947745168, 'epoch': 7.42}

 62%|██████▏   | 17360/28080 [34:18:53<21:13:57,  7.13s/it]
 62%|██████▏   | 17361/28080 [34:19:00<21:15:27,  7.14s/it]
                                                           
{'loss': 0.597, 'learning_rate': 0.00016794075615184285, 'epoch': 7.42}

 62%|██████▏   | 17361/28080 [34:19:00<21:15:27,  7.14s/it]
 62%|██████▏   | 17362/28080 [34:19:07<21:12:03,  7.12s/it]
                                                           
{'loss': 0.5856, 'learning_rate': 0.00016791351862088243, 'epoch': 7.42}

 62%|██████▏   | 17362/28080 [34:19:07<21:12:03,  7.12s/it]
 62%|██████▏   | 17363/28080 [34:19:14<21:19:01,  7.16s/it]
                                                           
{'loss': 0.595, 'learning_rate': 0.000167886282181998, 'epoch': 7.42}

 62%|██████▏   | 17363/28080 [34:19:14<21:19:01,  7.16s/it]
 62%|██████▏   | 17364/28080 [34:19:21<21:17:04,  7.15s/it]
                                                           
{'loss': 0.6305, 'learning_rate': 0.0001678590468355518, 'epoch': 7.42}

 62%|██████▏   | 17364/28080 [34:19:21<21:17:04,  7.15s/it]
 62%|██████▏   | 17365/28080 [34:19:28<21:14:39,  7.14s/it]
                                                           
{'loss': 0.5981, 'learning_rate': 0.00016783181258190634, 'epoch': 7.42}

 62%|██████▏   | 17365/28080 [34:19:28<21:14:39,  7.14s/it]
 62%|██████▏   | 17366/28080 [34:19:35<21:11:42,  7.12s/it]
                                                           
{'loss': 0.6001, 'learning_rate': 0.00016780457942142373, 'epoch': 7.42}

 62%|██████▏   | 17366/28080 [34:19:35<21:11:42,  7.12s/it]
 62%|██████▏   | 17367/28080 [34:19:43<21:13:40,  7.13s/it]
                                                           
{'loss': 0.6284, 'learning_rate': 0.00016777734735446654, 'epoch': 7.42}

 62%|██████▏   | 17367/28080 [34:19:43<21:13:40,  7.13s/it]
 62%|██████▏   | 17368/28080 [34:19:50<21:18:25,  7.16s/it]
                                                           
{'loss': 0.5999, 'learning_rate': 0.00016775011638139677, 'epoch': 7.42}

 62%|██████▏   | 17368/28080 [34:19:50<21:18:25,  7.16s/it]
 62%|██████▏   | 17369/28080 [34:19:57<21:18:18,  7.16s/it]
                                                           
{'loss': 0.6014, 'learning_rate': 0.00016772288650257694, 'epoch': 7.42}

 62%|██████▏   | 17369/28080 [34:19:57<21:18:18,  7.16s/it]
 62%|██████▏   | 17370/28080 [34:20:04<21:17:41,  7.16s/it]
                                                           
{'loss': 0.6255, 'learning_rate': 0.0001676956577183693, 'epoch': 7.42}

 62%|██████▏   | 17370/28080 [34:20:04<21:17:41,  7.16s/it]
 62%|██████▏   | 17371/28080 [34:20:11<21:25:14,  7.20s/it]
                                                           
{'loss': 0.6155, 'learning_rate': 0.00016766843002913588, 'epoch': 7.42}

 62%|██████▏   | 17371/28080 [34:20:11<21:25:14,  7.20s/it]
 62%|██████▏   | 17372/28080 [34:20:19<21:21:18,  7.18s/it]
                                                           
{'loss': 0.6255, 'learning_rate': 0.00016764120343523914, 'epoch': 7.42}

 62%|██████▏   | 17372/28080 [34:20:19<21:21:18,  7.18s/it]
 62%|██████▏   | 17373/28080 [34:20:26<21:21:21,  7.18s/it]
                                                           
{'loss': 0.6021, 'learning_rate': 0.00016761397793704113, 'epoch': 7.42}

 62%|██████▏   | 17373/28080 [34:20:26<21:21:21,  7.18s/it]
 62%|██████▏   | 17374/28080 [34:20:33<21:19:33,  7.17s/it]
                                                           
{'loss': 0.6, 'learning_rate': 0.00016758675353490426, 'epoch': 7.42}

 62%|██████▏   | 17374/28080 [34:20:33<21:19:33,  7.17s/it]
 62%|██████▏   | 17375/28080 [34:20:40<21:14:56,  7.15s/it]
                                                           
{'loss': 0.6001, 'learning_rate': 0.00016755953022919056, 'epoch': 7.42}

 62%|██████▏   | 17375/28080 [34:20:40<21:14:56,  7.15s/it]
 62%|██████▏   | 17376/28080 [34:20:47<21:10:54,  7.12s/it]
                                                           
{'loss': 0.641, 'learning_rate': 0.0001675323080202623, 'epoch': 7.42}

 62%|██████▏   | 17376/28080 [34:20:47<21:10:54,  7.12s/it]
 62%|██████▏   | 17377/28080 [34:20:54<21:08:12,  7.11s/it]
                                                           
{'loss': 0.6188, 'learning_rate': 0.00016750508690848155, 'epoch': 7.42}

 62%|██████▏   | 17377/28080 [34:20:54<21:08:12,  7.11s/it]
 62%|██████▏   | 17378/28080 [34:21:01<21:06:14,  7.10s/it]
                                                           
{'loss': 0.6291, 'learning_rate': 0.00016747786689421057, 'epoch': 7.42}

 62%|██████▏   | 17378/28080 [34:21:01<21:06:14,  7.10s/it]
 62%|██████▏   | 17379/28080 [34:21:08<21:09:18,  7.12s/it]
                                                           
{'loss': 0.6173, 'learning_rate': 0.00016745064797781139, 'epoch': 7.42}

 62%|██████▏   | 17379/28080 [34:21:08<21:09:18,  7.12s/it]
 62%|██████▏   | 17380/28080 [34:21:16<21:13:00,  7.14s/it]
                                                           
{'loss': 0.5975, 'learning_rate': 0.00016742343015964622, 'epoch': 7.42}

 62%|██████▏   | 17380/28080 [34:21:16<21:13:00,  7.14s/it]
 62%|██████▏   | 17381/28080 [34:21:23<21:11:59,  7.13s/it]
                                                           
{'loss': 0.6123, 'learning_rate': 0.00016739621344007702, 'epoch': 7.43}

 62%|██████▏   | 17381/28080 [34:21:23<21:11:59,  7.13s/it]
 62%|██████▏   | 17382/28080 [34:21:30<21:10:14,  7.12s/it]
                                                           
{'loss': 0.6221, 'learning_rate': 0.00016736899781946612, 'epoch': 7.43}

 62%|██████▏   | 17382/28080 [34:21:30<21:10:14,  7.12s/it]
 62%|██████▏   | 17383/28080 [34:21:37<21:05:26,  7.10s/it]
                                                           
{'loss': 0.626, 'learning_rate': 0.00016734178329817534, 'epoch': 7.43}

 62%|██████▏   | 17383/28080 [34:21:37<21:05:26,  7.10s/it]
 62%|██████▏   | 17384/28080 [34:21:44<21:10:24,  7.13s/it]
                                                           
{'loss': 0.6088, 'learning_rate': 0.000167314569876567, 'epoch': 7.43}

 62%|██████▏   | 17384/28080 [34:21:44<21:10:24,  7.13s/it]
 62%|██████▏   | 17385/28080 [34:21:51<21:08:39,  7.12s/it]
                                                           
{'loss': 0.6288, 'learning_rate': 0.00016728735755500284, 'epoch': 7.43}

 62%|██████▏   | 17385/28080 [34:21:51<21:08:39,  7.12s/it]
 62%|██████▏   | 17386/28080 [34:21:58<21:12:16,  7.14s/it]
                                                           
{'loss': 0.6013, 'learning_rate': 0.00016726014633384518, 'epoch': 7.43}

 62%|██████▏   | 17386/28080 [34:21:58<21:12:16,  7.14s/it]
 62%|██████▏   | 17387/28080 [34:22:05<21:04:57,  7.10s/it]
                                                           
{'loss': 0.6092, 'learning_rate': 0.00016723293621345587, 'epoch': 7.43}

 62%|██████▏   | 17387/28080 [34:22:05<21:04:57,  7.10s/it]
 62%|██████▏   | 17388/28080 [34:22:12<21:08:15,  7.12s/it]
                                                           
{'loss': 0.6026, 'learning_rate': 0.00016720572719419697, 'epoch': 7.43}

 62%|██████▏   | 17388/28080 [34:22:12<21:08:15,  7.12s/it]
 62%|██████▏   | 17389/28080 [34:22:19<21:05:16,  7.10s/it]
                                                           
{'loss': 0.6014, 'learning_rate': 0.00016717851927643043, 'epoch': 7.43}

 62%|██████▏   | 17389/28080 [34:22:19<21:05:16,  7.10s/it]
 62%|██████▏   | 17390/28080 [34:22:27<21:04:22,  7.10s/it]
                                                           
{'loss': 0.5896, 'learning_rate': 0.0001671513124605183, 'epoch': 7.43}

 62%|██████▏   | 17390/28080 [34:22:27<21:04:22,  7.10s/it]
 62%|██████▏   | 17391/28080 [34:22:34<21:04:53,  7.10s/it]
                                                           
{'loss': 0.6209, 'learning_rate': 0.00016712410674682242, 'epoch': 7.43}

 62%|██████▏   | 17391/28080 [34:22:34<21:04:53,  7.10s/it]
 62%|██████▏   | 17392/28080 [34:22:41<21:06:17,  7.11s/it]
                                                           
{'loss': 0.6226, 'learning_rate': 0.00016709690213570488, 'epoch': 7.43}

 62%|██████▏   | 17392/28080 [34:22:41<21:06:17,  7.11s/it]
 62%|██████▏   | 17393/28080 [34:22:48<21:15:28,  7.16s/it]
                                                           
{'loss': 0.5867, 'learning_rate': 0.00016706969862752746, 'epoch': 7.43}

 62%|██████▏   | 17393/28080 [34:22:48<21:15:28,  7.16s/it]
 62%|██████▏   | 17394/28080 [34:22:55<21:17:04,  7.17s/it]
                                                           
{'loss': 0.6059, 'learning_rate': 0.00016704249622265222, 'epoch': 7.43}

 62%|██████▏   | 17394/28080 [34:22:55<21:17:04,  7.17s/it]
 62%|██████▏   | 17395/28080 [34:23:02<21:19:58,  7.19s/it]
                                                           
{'loss': 0.599, 'learning_rate': 0.00016701529492144096, 'epoch': 7.43}

 62%|██████▏   | 17395/28080 [34:23:03<21:19:58,  7.19s/it]
 62%|██████▏   | 17396/28080 [34:23:10<21:12:54,  7.15s/it]
                                                           
{'loss': 0.5986, 'learning_rate': 0.00016698809472425553, 'epoch': 7.43}

 62%|██████▏   | 17396/28080 [34:23:10<21:12:54,  7.15s/it]
 62%|██████▏   | 17397/28080 [34:23:17<21:12:54,  7.15s/it]
                                                           
{'loss': 0.6144, 'learning_rate': 0.00016696089563145796, 'epoch': 7.43}

 62%|██████▏   | 17397/28080 [34:23:17<21:12:54,  7.15s/it]
 62%|██████▏   | 17398/28080 [34:23:24<21:09:40,  7.13s/it]
                                                           
{'loss': 0.6307, 'learning_rate': 0.00016693369764340992, 'epoch': 7.43}

 62%|██████▏   | 17398/28080 [34:23:24<21:09:40,  7.13s/it]
 62%|██████▏   | 17399/28080 [34:23:31<21:11:25,  7.14s/it]
                                                           
{'loss': 0.6205, 'learning_rate': 0.00016690650076047337, 'epoch': 7.43}

 62%|██████▏   | 17399/28080 [34:23:31<21:11:25,  7.14s/it]
 62%|██████▏   | 17400/28080 [34:23:38<21:05:27,  7.11s/it]
                                                           
{'loss': 0.6349, 'learning_rate': 0.00016687930498301002, 'epoch': 7.43}

 62%|██████▏   | 17400/28080 [34:23:38<21:05:27,  7.11s/it]
 62%|██████▏   | 17401/28080 [34:23:45<21:01:05,  7.09s/it]
                                                           
{'loss': 0.6128, 'learning_rate': 0.00016685211031138193, 'epoch': 7.43}

 62%|██████▏   | 17401/28080 [34:23:45<21:01:05,  7.09s/it]
 62%|██████▏   | 17402/28080 [34:23:52<20:58:21,  7.07s/it]
                                                           
{'loss': 0.6237, 'learning_rate': 0.00016682491674595057, 'epoch': 7.43}

 62%|██████▏   | 17402/28080 [34:23:52<20:58:21,  7.07s/it]
 62%|██████▏   | 17403/28080 [34:23:59<20:59:19,  7.08s/it]
                                                           
{'loss': 0.6181, 'learning_rate': 0.000166797724287078, 'epoch': 7.43}

 62%|██████▏   | 17403/28080 [34:23:59<20:59:19,  7.08s/it]
 62%|██████▏   | 17404/28080 [34:24:06<20:54:49,  7.05s/it]
                                                           
{'loss': 0.6095, 'learning_rate': 0.0001667705329351258, 'epoch': 7.43}

 62%|██████▏   | 17404/28080 [34:24:06<20:54:49,  7.05s/it]
 62%|██████▏   | 17405/28080 [34:24:13<21:05:58,  7.12s/it]
                                                           
{'loss': 0.6108, 'learning_rate': 0.00016674334269045589, 'epoch': 7.44}

 62%|██████▏   | 17405/28080 [34:24:13<21:05:58,  7.12s/it]
 62%|██████▏   | 17406/28080 [34:24:21<21:12:02,  7.15s/it]
                                                           
{'loss': 0.6055, 'learning_rate': 0.00016671615355342984, 'epoch': 7.44}

 62%|██████▏   | 17406/28080 [34:24:21<21:12:02,  7.15s/it]
 62%|██████▏   | 17407/28080 [34:24:28<21:13:40,  7.16s/it]
                                                           
{'loss': 0.6224, 'learning_rate': 0.0001666889655244095, 'epoch': 7.44}

 62%|██████▏   | 17407/28080 [34:24:28<21:13:40,  7.16s/it]
 62%|██████▏   | 17408/28080 [34:24:35<21:13:03,  7.16s/it]
                                                           
{'loss': 0.6093, 'learning_rate': 0.00016666177860375644, 'epoch': 7.44}

 62%|██████▏   | 17408/28080 [34:24:35<21:13:03,  7.16s/it]
 62%|██████▏   | 17409/28080 [34:24:42<21:10:22,  7.14s/it]
                                                           
{'loss': 0.6093, 'learning_rate': 0.00016663459279183253, 'epoch': 7.44}

 62%|██████▏   | 17409/28080 [34:24:42<21:10:22,  7.14s/it]
 62%|██████▏   | 17410/28080 [34:24:49<21:13:44,  7.16s/it]
                                                           
{'loss': 0.6115, 'learning_rate': 0.0001666074080889993, 'epoch': 7.44}

 62%|██████▏   | 17410/28080 [34:24:49<21:13:44,  7.16s/it]
 62%|██████▏   | 17411/28080 [34:24:56<21:08:29,  7.13s/it]
                                                           
{'loss': 0.607, 'learning_rate': 0.00016658022449561854, 'epoch': 7.44}

 62%|██████▏   | 17411/28080 [34:24:56<21:08:29,  7.13s/it]
 62%|██████▏   | 17412/28080 [34:25:03<21:04:49,  7.11s/it]
                                                           
{'loss': 0.6199, 'learning_rate': 0.00016655304201205172, 'epoch': 7.44}

 62%|██████▏   | 17412/28080 [34:25:03<21:04:49,  7.11s/it]
 62%|██████▏   | 17413/28080 [34:25:11<21:04:29,  7.11s/it]
                                                           
{'loss': 0.6, 'learning_rate': 0.0001665258606386607, 'epoch': 7.44}

 62%|██████▏   | 17413/28080 [34:25:11<21:04:29,  7.11s/it]
 62%|██████▏   | 17414/28080 [34:25:18<21:06:36,  7.13s/it]
                                                           
{'loss': 0.6093, 'learning_rate': 0.00016649868037580689, 'epoch': 7.44}

 62%|██████▏   | 17414/28080 [34:25:18<21:06:36,  7.13s/it]
 62%|██████▏   | 17415/28080 [34:25:25<21:01:10,  7.10s/it]
                                                           
{'loss': 0.6095, 'learning_rate': 0.00016647150122385212, 'epoch': 7.44}

 62%|██████▏   | 17415/28080 [34:25:25<21:01:10,  7.10s/it]
 62%|██████▏   | 17416/28080 [34:25:32<20:58:07,  7.08s/it]
                                                           
{'loss': 0.6245, 'learning_rate': 0.00016644432318315772, 'epoch': 7.44}

 62%|██████▏   | 17416/28080 [34:25:32<20:58:07,  7.08s/it]
 62%|██████▏   | 17417/28080 [34:25:39<21:01:22,  7.10s/it]
                                                           
{'loss': 0.5924, 'learning_rate': 0.0001664171462540855, 'epoch': 7.44}

 62%|██████▏   | 17417/28080 [34:25:39<21:01:22,  7.10s/it]
 62%|██████▏   | 17418/28080 [34:25:46<21:01:29,  7.10s/it]
                                                           
{'loss': 0.6171, 'learning_rate': 0.0001663899704369969, 'epoch': 7.44}

 62%|██████▏   | 17418/28080 [34:25:46<21:01:29,  7.10s/it]
 62%|██████▏   | 17419/28080 [34:25:53<21:05:33,  7.12s/it]
                                                           
{'loss': 0.6255, 'learning_rate': 0.0001663627957322535, 'epoch': 7.44}

 62%|██████▏   | 17419/28080 [34:25:53<21:05:33,  7.12s/it]
 62%|██████▏   | 17420/28080 [34:26:00<21:06:12,  7.13s/it]
                                                           
{'loss': 0.6158, 'learning_rate': 0.0001663356221402168, 'epoch': 7.44}

 62%|██████▏   | 17420/28080 [34:26:00<21:06:12,  7.13s/it]
 62%|██████▏   | 17421/28080 [34:26:07<21:08:37,  7.14s/it]
                                                           
{'loss': 0.6072, 'learning_rate': 0.0001663084496612483, 'epoch': 7.44}

 62%|██████▏   | 17421/28080 [34:26:07<21:08:37,  7.14s/it]
 62%|██████▏   | 17422/28080 [34:26:15<21:07:15,  7.13s/it]
                                                           
{'loss': 0.6122, 'learning_rate': 0.0001662812782957096, 'epoch': 7.44}

 62%|██████▏   | 17422/28080 [34:26:15<21:07:15,  7.13s/it]
 62%|██████▏   | 17423/28080 [34:26:22<21:06:42,  7.13s/it]
                                                           
{'loss': 0.6189, 'learning_rate': 0.00016625410804396208, 'epoch': 7.44}

 62%|██████▏   | 17423/28080 [34:26:22<21:06:42,  7.13s/it]
 62%|██████▏   | 17424/28080 [34:26:29<21:05:55,  7.13s/it]
                                                           
{'loss': 0.638, 'learning_rate': 0.00016622693890636732, 'epoch': 7.44}

 62%|██████▏   | 17424/28080 [34:26:29<21:05:55,  7.13s/it]
 62%|██████▏   | 17425/28080 [34:26:36<20:59:52,  7.09s/it]
                                                           
{'loss': 0.6262, 'learning_rate': 0.00016619977088328663, 'epoch': 7.44}

 62%|██████▏   | 17425/28080 [34:26:36<20:59:52,  7.09s/it]
 62%|██████▏   | 17426/28080 [34:26:43<21:01:08,  7.10s/it]
                                                           
{'loss': 0.6193, 'learning_rate': 0.0001661726039750816, 'epoch': 7.44}

 62%|██████▏   | 17426/28080 [34:26:43<21:01:08,  7.10s/it]
 62%|██████▏   | 17427/28080 [34:26:50<21:04:04,  7.12s/it]
                                                           
{'loss': 0.6151, 'learning_rate': 0.00016614543818211353, 'epoch': 7.44}

 62%|██████▏   | 17427/28080 [34:26:50<21:04:04,  7.12s/it]
 62%|██████▏   | 17428/28080 [34:26:57<21:02:33,  7.11s/it]
                                                           
{'loss': 0.6048, 'learning_rate': 0.00016611827350474396, 'epoch': 7.45}

 62%|██████▏   | 17428/28080 [34:26:57<21:02:33,  7.11s/it]
 62%|██████▏   | 17429/28080 [34:27:04<21:03:19,  7.12s/it]
                                                           
{'loss': 0.6234, 'learning_rate': 0.0001660911099433342, 'epoch': 7.45}

 62%|██████▏   | 17429/28080 [34:27:04<21:03:19,  7.12s/it]
 62%|██████▏   | 17430/28080 [34:27:12<21:04:43,  7.13s/it]
                                                           
{'loss': 0.6191, 'learning_rate': 0.00016606394749824565, 'epoch': 7.45}

 62%|██████▏   | 17430/28080 [34:27:12<21:04:43,  7.13s/it]
 62%|██████▏   | 17431/28080 [34:27:19<21:05:34,  7.13s/it]
                                                           
{'loss': 0.5966, 'learning_rate': 0.00016603678616983964, 'epoch': 7.45}

 62%|██████▏   | 17431/28080 [34:27:19<21:05:34,  7.13s/it]
 62%|██████▏   | 17432/28080 [34:27:26<21:02:22,  7.11s/it]
                                                           
{'loss': 0.6033, 'learning_rate': 0.00016600962595847768, 'epoch': 7.45}

 62%|██████▏   | 17432/28080 [34:27:26<21:02:22,  7.11s/it]
 62%|██████▏   | 17433/28080 [34:27:33<21:03:06,  7.12s/it]
                                                           
{'loss': 0.6008, 'learning_rate': 0.00016598246686452088, 'epoch': 7.45}

 62%|██████▏   | 17433/28080 [34:27:33<21:03:06,  7.12s/it]
 62%|██████▏   | 17434/28080 [34:27:40<20:55:46,  7.08s/it]
                                                           
{'loss': 0.6074, 'learning_rate': 0.00016595530888833076, 'epoch': 7.45}

 62%|██████▏   | 17434/28080 [34:27:40<20:55:46,  7.08s/it]
 62%|██████▏   | 17435/28080 [34:27:47<20:58:44,  7.09s/it]
                                                           
{'loss': 0.5969, 'learning_rate': 0.0001659281520302685, 'epoch': 7.45}

 62%|██████▏   | 17435/28080 [34:27:47<20:58:44,  7.09s/it]
 62%|██████▏   | 17436/28080 [34:27:54<20:57:02,  7.09s/it]
                                                           
{'loss': 0.6043, 'learning_rate': 0.00016590099629069553, 'epoch': 7.45}

 62%|██████▏   | 17436/28080 [34:27:54<20:57:02,  7.09s/it]
 62%|██████▏   | 17437/28080 [34:28:01<20:56:58,  7.09s/it]
                                                           
{'loss': 0.5986, 'learning_rate': 0.00016587384166997295, 'epoch': 7.45}

 62%|██████▏   | 17437/28080 [34:28:01<20:56:58,  7.09s/it]
 62%|██████▏   | 17438/28080 [34:28:08<20:55:45,  7.08s/it]
                                                           
{'loss': 0.6212, 'learning_rate': 0.00016584668816846222, 'epoch': 7.45}

 62%|██████▏   | 17438/28080 [34:28:08<20:55:45,  7.08s/it]
 62%|██████▏   | 17439/28080 [34:28:15<21:01:07,  7.11s/it]
                                                           
{'loss': 0.5962, 'learning_rate': 0.00016581953578652438, 'epoch': 7.45}

 62%|██████▏   | 17439/28080 [34:28:15<21:01:07,  7.11s/it]
 62%|██████▏   | 17440/28080 [34:28:23<21:01:48,  7.12s/it]
                                                           
{'loss': 0.6041, 'learning_rate': 0.00016579238452452084, 'epoch': 7.45}

 62%|██████▏   | 17440/28080 [34:28:23<21:01:48,  7.12s/it]
 62%|██████▏   | 17441/28080 [34:28:30<21:02:55,  7.12s/it]
                                                           
{'loss': 0.6063, 'learning_rate': 0.0001657652343828127, 'epoch': 7.45}

 62%|██████▏   | 17441/28080 [34:28:30<21:02:55,  7.12s/it]
 62%|██████▏   | 17442/28080 [34:28:37<21:02:57,  7.12s/it]
                                                           
{'loss': 0.6012, 'learning_rate': 0.0001657380853617613, 'epoch': 7.45}

 62%|██████▏   | 17442/28080 [34:28:37<21:02:57,  7.12s/it]
 62%|██████▏   | 17443/28080 [34:28:44<21:02:30,  7.12s/it]
                                                           
{'loss': 0.6219, 'learning_rate': 0.00016571093746172761, 'epoch': 7.45}

 62%|██████▏   | 17443/28080 [34:28:44<21:02:30,  7.12s/it]
 62%|██████▏   | 17444/28080 [34:28:51<21:02:55,  7.12s/it]
                                                           
{'loss': 0.6262, 'learning_rate': 0.0001656837906830731, 'epoch': 7.45}

 62%|██████▏   | 17444/28080 [34:28:51<21:02:55,  7.12s/it]
 62%|██████▏   | 17445/28080 [34:28:58<21:11:08,  7.17s/it]
                                                           
{'loss': 0.6132, 'learning_rate': 0.00016565664502615873, 'epoch': 7.45}

 62%|██████▏   | 17445/28080 [34:28:58<21:11:08,  7.17s/it]
 62%|██████▏   | 17446/28080 [34:29:05<21:08:11,  7.16s/it]
                                                           
{'loss': 0.6087, 'learning_rate': 0.00016562950049134564, 'epoch': 7.45}

 62%|██████▏   | 17446/28080 [34:29:05<21:08:11,  7.16s/it]
 62%|██████▏   | 17447/28080 [34:29:13<21:05:47,  7.14s/it]
                                                           
{'loss': 0.6277, 'learning_rate': 0.00016560235707899508, 'epoch': 7.45}

 62%|██████▏   | 17447/28080 [34:29:13<21:05:47,  7.14s/it]
 62%|██████▏   | 17448/28080 [34:29:20<21:05:03,  7.14s/it]
                                                           
{'loss': 0.6343, 'learning_rate': 0.00016557521478946792, 'epoch': 7.45}

 62%|██████▏   | 17448/28080 [34:29:20<21:05:03,  7.14s/it]
 62%|██████▏   | 17449/28080 [34:29:27<21:05:57,  7.14s/it]
                                                           
{'loss': 0.6123, 'learning_rate': 0.00016554807362312562, 'epoch': 7.45}

 62%|██████▏   | 17449/28080 [34:29:27<21:05:57,  7.14s/it]
 62%|██████▏   | 17450/28080 [34:29:34<21:07:08,  7.15s/it]
                                                           
{'loss': 0.6122, 'learning_rate': 0.00016552093358032893, 'epoch': 7.45}

 62%|██████▏   | 17450/28080 [34:29:34<21:07:08,  7.15s/it]
 62%|██████▏   | 17451/28080 [34:29:41<21:05:05,  7.14s/it]
                                                           
{'loss': 0.6049, 'learning_rate': 0.00016549379466143915, 'epoch': 7.45}

 62%|██████▏   | 17451/28080 [34:29:41<21:05:05,  7.14s/it]
 62%|██████▏   | 17452/28080 [34:29:48<21:04:12,  7.14s/it]
                                                           
{'loss': 0.6175, 'learning_rate': 0.00016546665686681722, 'epoch': 7.46}

 62%|██████▏   | 17452/28080 [34:29:48<21:04:12,  7.14s/it]
 62%|██████▏   | 17453/28080 [34:29:55<20:59:41,  7.11s/it]
                                                           
{'loss': 0.6051, 'learning_rate': 0.00016543952019682426, 'epoch': 7.46}

 62%|██████▏   | 17453/28080 [34:29:55<20:59:41,  7.11s/it]
 62%|██████▏   | 17454/28080 [34:30:02<20:59:17,  7.11s/it]
                                                           
{'loss': 0.6046, 'learning_rate': 0.00016541238465182117, 'epoch': 7.46}

 62%|██████▏   | 17454/28080 [34:30:02<20:59:17,  7.11s/it]
 62%|██████▏   | 17455/28080 [34:30:10<21:02:40,  7.13s/it]
                                                           
{'loss': 0.6224, 'learning_rate': 0.00016538525023216912, 'epoch': 7.46}

 62%|██████▏   | 17455/28080 [34:30:10<21:02:40,  7.13s/it]
 62%|██████▏   | 17456/28080 [34:30:17<21:00:02,  7.12s/it]
                                                           
{'loss': 0.5997, 'learning_rate': 0.00016535811693822898, 'epoch': 7.46}

 62%|██████▏   | 17456/28080 [34:30:17<21:00:02,  7.12s/it]
 62%|██████▏   | 17457/28080 [34:30:24<21:06:11,  7.15s/it]
                                                           
{'loss': 0.5871, 'learning_rate': 0.0001653309847703618, 'epoch': 7.46}

 62%|██████▏   | 17457/28080 [34:30:24<21:06:11,  7.15s/it]
 62%|██████▏   | 17458/28080 [34:30:31<20:56:48,  7.10s/it]
                                                           
{'loss': 0.6114, 'learning_rate': 0.00016530385372892848, 'epoch': 7.46}

 62%|██████▏   | 17458/28080 [34:30:31<20:56:48,  7.10s/it]
 62%|██████▏   | 17459/28080 [34:30:38<21:02:59,  7.13s/it]
                                                           
{'loss': 0.5951, 'learning_rate': 0.00016527672381429003, 'epoch': 7.46}

 62%|██████▏   | 17459/28080 [34:30:38<21:02:59,  7.13s/it]
 62%|██████▏   | 17460/28080 [34:30:45<20:59:22,  7.12s/it]
                                                           
{'loss': 0.633, 'learning_rate': 0.00016524959502680736, 'epoch': 7.46}

 62%|██████▏   | 17460/28080 [34:30:45<20:59:22,  7.12s/it]
 62%|██████▏   | 17461/28080 [34:30:52<20:56:25,  7.10s/it]
                                                           
{'loss': 0.6163, 'learning_rate': 0.00016522246736684143, 'epoch': 7.46}

 62%|██████▏   | 17461/28080 [34:30:52<20:56:25,  7.10s/it]
 62%|██████▏   | 17462/28080 [34:30:59<20:55:09,  7.09s/it]
                                                           
{'loss': 0.6492, 'learning_rate': 0.000165195340834753, 'epoch': 7.46}

 62%|██████▏   | 17462/28080 [34:30:59<20:55:09,  7.09s/it]
 62%|██████▏   | 17463/28080 [34:31:06<20:56:56,  7.10s/it]
                                                           
{'loss': 0.6448, 'learning_rate': 0.00016516821543090327, 'epoch': 7.46}

 62%|██████▏   | 17463/28080 [34:31:06<20:56:56,  7.10s/it]
 62%|██████▏   | 17464/28080 [34:31:14<21:00:14,  7.12s/it]
                                                           
{'loss': 0.6184, 'learning_rate': 0.0001651410911556527, 'epoch': 7.46}

 62%|██████▏   | 17464/28080 [34:31:14<21:00:14,  7.12s/it]
 62%|██████▏   | 17465/28080 [34:31:21<20:55:06,  7.09s/it]
                                                           
{'loss': 0.6163, 'learning_rate': 0.00016511396800936252, 'epoch': 7.46}

 62%|██████▏   | 17465/28080 [34:31:21<20:55:06,  7.09s/it]
 62%|██████▏   | 17466/28080 [34:31:28<20:59:22,  7.12s/it]
                                                           
{'loss': 0.614, 'learning_rate': 0.00016508684599239332, 'epoch': 7.46}

 62%|██████▏   | 17466/28080 [34:31:28<20:59:22,  7.12s/it]
 62%|██████▏   | 17467/28080 [34:31:35<20:57:21,  7.11s/it]
                                                           
{'loss': 0.6199, 'learning_rate': 0.00016505972510510615, 'epoch': 7.46}

 62%|██████▏   | 17467/28080 [34:31:35<20:57:21,  7.11s/it]
 62%|██████▏   | 17468/28080 [34:31:42<20:54:34,  7.09s/it]
                                                           
{'loss': 0.6043, 'learning_rate': 0.00016503260534786161, 'epoch': 7.46}

 62%|██████▏   | 17468/28080 [34:31:42<20:54:34,  7.09s/it]
 62%|██████▏   | 17469/28080 [34:31:49<21:02:29,  7.14s/it]
                                                           
{'loss': 0.6136, 'learning_rate': 0.00016500548672102066, 'epoch': 7.46}

 62%|██████▏   | 17469/28080 [34:31:49<21:02:29,  7.14s/it]
 62%|██████▏   | 17470/28080 [34:31:56<20:59:32,  7.12s/it]
                                                           
{'loss': 0.6118, 'learning_rate': 0.00016497836922494403, 'epoch': 7.46}

 62%|██████▏   | 17470/28080 [34:31:56<20:59:32,  7.12s/it]
 62%|██████▏   | 17471/28080 [34:32:03<21:00:28,  7.13s/it]
                                                           
{'loss': 0.6141, 'learning_rate': 0.00016495125285999245, 'epoch': 7.46}

 62%|██████▏   | 17471/28080 [34:32:03<21:00:28,  7.13s/it]
 62%|██████▏   | 17472/28080 [34:32:11<20:59:06,  7.12s/it]
                                                           
{'loss': 0.5814, 'learning_rate': 0.00016492413762652676, 'epoch': 7.46}

 62%|██████▏   | 17472/28080 [34:32:11<20:59:06,  7.12s/it]
 62%|██████▏   | 17473/28080 [34:32:18<21:01:33,  7.14s/it]
                                                           
{'loss': 0.6275, 'learning_rate': 0.00016489702352490756, 'epoch': 7.46}

 62%|██████▏   | 17473/28080 [34:32:18<21:01:33,  7.14s/it]
 62%|██████▏   | 17474/28080 [34:32:25<21:05:56,  7.16s/it]
                                                           
{'loss': 0.6097, 'learning_rate': 0.00016486991055549575, 'epoch': 7.46}

 62%|██████▏   | 17474/28080 [34:32:25<21:05:56,  7.16s/it]
 62%|██████▏   | 17475/28080 [34:32:32<21:03:45,  7.15s/it]
                                                           
{'loss': 0.6085, 'learning_rate': 0.0001648427987186519, 'epoch': 7.47}

 62%|██████▏   | 17475/28080 [34:32:32<21:03:45,  7.15s/it]
 62%|██████▏   | 17476/28080 [34:32:39<21:01:51,  7.14s/it]
                                                           
{'loss': 0.597, 'learning_rate': 0.0001648156880147368, 'epoch': 7.47}

 62%|██████▏   | 17476/28080 [34:32:39<21:01:51,  7.14s/it]
 62%|██████▏   | 17477/28080 [34:32:46<21:05:14,  7.16s/it]
                                                           
{'loss': 0.629, 'learning_rate': 0.00016478857844411105, 'epoch': 7.47}

 62%|██████▏   | 17477/28080 [34:32:46<21:05:14,  7.16s/it]
 62%|██████▏   | 17478/28080 [34:32:53<20:57:45,  7.12s/it]
                                                           
{'loss': 0.6196, 'learning_rate': 0.00016476147000713543, 'epoch': 7.47}

 62%|██████▏   | 17478/28080 [34:32:53<20:57:45,  7.12s/it]
 62%|██████▏   | 17479/28080 [34:33:01<21:00:06,  7.13s/it]
                                                           
{'loss': 0.5942, 'learning_rate': 0.0001647343627041704, 'epoch': 7.47}

 62%|██████▏   | 17479/28080 [34:33:01<21:00:06,  7.13s/it]
 62%|██████▏   | 17480/28080 [34:33:08<21:01:41,  7.14s/it]
                                                           
{'loss': 0.6168, 'learning_rate': 0.00016470725653557685, 'epoch': 7.47}

 62%|██████▏   | 17480/28080 [34:33:08<21:01:41,  7.14s/it]
 62%|██████▏   | 17481/28080 [34:33:15<21:00:09,  7.13s/it]
                                                           
{'loss': 0.6002, 'learning_rate': 0.00016468015150171512, 'epoch': 7.47}

 62%|██████▏   | 17481/28080 [34:33:15<21:00:09,  7.13s/it]
 62%|██████▏   | 17482/28080 [34:33:22<20:54:02,  7.10s/it]
                                                           
{'loss': 0.6221, 'learning_rate': 0.00016465304760294604, 'epoch': 7.47}

 62%|██████▏   | 17482/28080 [34:33:22<20:54:02,  7.10s/it]
 62%|██████▏   | 17483/28080 [34:33:29<20:48:35,  7.07s/it]
                                                           
{'loss': 0.6024, 'learning_rate': 0.00016462594483963007, 'epoch': 7.47}

 62%|██████▏   | 17483/28080 [34:33:29<20:48:35,  7.07s/it]
 62%|██████▏   | 17484/28080 [34:33:36<20:51:53,  7.09s/it]
                                                           
{'loss': 0.6034, 'learning_rate': 0.00016459884321212787, 'epoch': 7.47}

 62%|██████▏   | 17484/28080 [34:33:36<20:51:53,  7.09s/it]
 62%|██████▏   | 17485/28080 [34:33:43<20:53:50,  7.10s/it]
                                                           
{'loss': 0.6238, 'learning_rate': 0.00016457174272079995, 'epoch': 7.47}

 62%|██████▏   | 17485/28080 [34:33:43<20:53:50,  7.10s/it]
 62%|██████▏   | 17486/28080 [34:33:50<20:55:28,  7.11s/it]
                                                           
{'loss': 0.6256, 'learning_rate': 0.00016454464336600685, 'epoch': 7.47}

 62%|██████▏   | 17486/28080 [34:33:50<20:55:28,  7.11s/it]
 62%|██████▏   | 17487/28080 [34:33:57<20:55:03,  7.11s/it]
                                                           
{'loss': 0.6371, 'learning_rate': 0.0001645175451481091, 'epoch': 7.47}

 62%|██████▏   | 17487/28080 [34:33:57<20:55:03,  7.11s/it]
 62%|██████▏   | 17488/28080 [34:34:04<20:51:11,  7.09s/it]
                                                           
{'loss': 0.6167, 'learning_rate': 0.00016449044806746726, 'epoch': 7.47}

 62%|██████▏   | 17488/28080 [34:34:04<20:51:11,  7.09s/it]
 62%|██████▏   | 17489/28080 [34:34:11<20:51:02,  7.09s/it]
                                                           
{'loss': 0.6265, 'learning_rate': 0.00016446335212444175, 'epoch': 7.47}

 62%|██████▏   | 17489/28080 [34:34:11<20:51:02,  7.09s/it]
 62%|██████▏   | 17490/28080 [34:34:19<20:54:13,  7.11s/it]
                                                           
{'loss': 0.6226, 'learning_rate': 0.00016443625731939315, 'epoch': 7.47}

 62%|██████▏   | 17490/28080 [34:34:19<20:54:13,  7.11s/it]
 62%|██████▏   | 17491/28080 [34:34:26<20:53:45,  7.10s/it]
                                                           
{'loss': 0.6139, 'learning_rate': 0.00016440916365268184, 'epoch': 7.47}

 62%|██████▏   | 17491/28080 [34:34:26<20:53:45,  7.10s/it]
 62%|██████▏   | 17492/28080 [34:34:33<20:54:47,  7.11s/it]
                                                           
{'loss': 0.5983, 'learning_rate': 0.00016438207112466833, 'epoch': 7.47}

 62%|██████▏   | 17492/28080 [34:34:33<20:54:47,  7.11s/it]
 62%|██████▏   | 17493/28080 [34:34:40<20:56:38,  7.12s/it]
                                                           
{'loss': 0.6103, 'learning_rate': 0.00016435497973571296, 'epoch': 7.47}

 62%|██████▏   | 17493/28080 [34:34:40<20:56:38,  7.12s/it]
 62%|██████▏   | 17494/28080 [34:34:47<20:52:29,  7.10s/it]
                                                           
{'loss': 0.6118, 'learning_rate': 0.00016432788948617637, 'epoch': 7.47}

 62%|██████▏   | 17494/28080 [34:34:47<20:52:29,  7.10s/it]
 62%|██████▏   | 17495/28080 [34:34:54<20:54:04,  7.11s/it]
                                                           
{'loss': 0.6296, 'learning_rate': 0.00016430080037641877, 'epoch': 7.47}

 62%|██████▏   | 17495/28080 [34:34:54<20:54:04,  7.11s/it]
 62%|██████▏   | 17496/28080 [34:35:01<20:58:26,  7.13s/it]
                                                           
{'loss': 0.5992, 'learning_rate': 0.0001642737124068005, 'epoch': 7.47}

 62%|██████▏   | 17496/28080 [34:35:01<20:58:26,  7.13s/it]
 62%|██████▏   | 17497/28080 [34:35:09<20:59:13,  7.14s/it]
                                                           
{'loss': 0.6221, 'learning_rate': 0.0001642466255776822, 'epoch': 7.47}

 62%|██████▏   | 17497/28080 [34:35:09<20:59:13,  7.14s/it]
 62%|██████▏   | 17498/28080 [34:35:16<20:56:23,  7.12s/it]
                                                           
{'loss': 0.5868, 'learning_rate': 0.00016421953988942395, 'epoch': 7.47}

 62%|██████▏   | 17498/28080 [34:35:16<20:56:23,  7.12s/it]
 62%|██████▏   | 17499/28080 [34:35:23<20:52:41,  7.10s/it]
                                                           
{'loss': 0.6174, 'learning_rate': 0.00016419245534238632, 'epoch': 7.48}

 62%|██████▏   | 17499/28080 [34:35:23<20:52:41,  7.10s/it]
 62%|██████▏   | 17500/28080 [34:35:30<20:55:39,  7.12s/it]
                                                           
{'loss': 0.6036, 'learning_rate': 0.0001641653719369295, 'epoch': 7.48}

 62%|██████▏   | 17500/28080 [34:35:30<20:55:39,  7.12s/it]
 62%|██████▏   | 17501/28080 [34:35:37<20:59:21,  7.14s/it]
                                                           
{'loss': 0.6109, 'learning_rate': 0.0001641382896734139, 'epoch': 7.48}

 62%|██████▏   | 17501/28080 [34:35:37<20:59:21,  7.14s/it]
 62%|██████▏   | 17502/28080 [34:35:44<20:59:24,  7.14s/it]
                                                           
{'loss': 0.6108, 'learning_rate': 0.00016411120855219975, 'epoch': 7.48}

 62%|██████▏   | 17502/28080 [34:35:44<20:59:24,  7.14s/it]
 62%|██████▏   | 17503/28080 [34:35:51<20:53:39,  7.11s/it]
                                                           
{'loss': 0.642, 'learning_rate': 0.00016408412857364738, 'epoch': 7.48}

 62%|██████▏   | 17503/28080 [34:35:51<20:53:39,  7.11s/it]
 62%|██████▏   | 17504/28080 [34:35:58<20:54:02,  7.11s/it]
                                                           
{'loss': 0.6015, 'learning_rate': 0.000164057049738117, 'epoch': 7.48}

 62%|██████▏   | 17504/28080 [34:35:58<20:54:02,  7.11s/it]
 62%|██████▏   | 17505/28080 [34:36:05<20:56:21,  7.13s/it]
                                                           
{'loss': 0.6199, 'learning_rate': 0.00016402997204596897, 'epoch': 7.48}

 62%|██████▏   | 17505/28080 [34:36:05<20:56:21,  7.13s/it]
 62%|██████▏   | 17506/28080 [34:36:13<20:56:20,  7.13s/it]
                                                           
{'loss': 0.6034, 'learning_rate': 0.00016400289549756342, 'epoch': 7.48}

 62%|██████▏   | 17506/28080 [34:36:13<20:56:20,  7.13s/it]
 62%|██████▏   | 17507/28080 [34:36:20<20:57:33,  7.14s/it]
                                                           
{'loss': 0.5929, 'learning_rate': 0.00016397582009326068, 'epoch': 7.48}

 62%|██████▏   | 17507/28080 [34:36:20<20:57:33,  7.14s/it]
 62%|██████▏   | 17508/28080 [34:36:27<21:02:36,  7.17s/it]
                                                           
{'loss': 0.6169, 'learning_rate': 0.00016394874583342084, 'epoch': 7.48}

 62%|██████▏   | 17508/28080 [34:36:27<21:02:36,  7.17s/it]
 62%|██████▏   | 17509/28080 [34:36:34<21:01:15,  7.16s/it]
                                                           
{'loss': 0.6138, 'learning_rate': 0.00016392167271840423, 'epoch': 7.48}

 62%|██████▏   | 17509/28080 [34:36:34<21:01:15,  7.16s/it]
 62%|██████▏   | 17510/28080 [34:36:41<21:00:21,  7.15s/it]
                                                           
{'loss': 0.6028, 'learning_rate': 0.00016389460074857088, 'epoch': 7.48}

 62%|██████▏   | 17510/28080 [34:36:41<21:00:21,  7.15s/it]
 62%|██████▏   | 17511/28080 [34:36:48<21:01:49,  7.16s/it]
                                                           
{'loss': 0.6198, 'learning_rate': 0.00016386752992428115, 'epoch': 7.48}

 62%|██████▏   | 17511/28080 [34:36:48<21:01:49,  7.16s/it]
 62%|██████▏   | 17512/28080 [34:36:56<21:05:55,  7.19s/it]
                                                           
{'loss': 0.6097, 'learning_rate': 0.00016384046024589495, 'epoch': 7.48}

 62%|██████▏   | 17512/28080 [34:36:56<21:05:55,  7.19s/it]
 62%|██████▏   | 17513/28080 [34:37:03<21:02:11,  7.17s/it]
                                                           
{'loss': 0.6269, 'learning_rate': 0.00016381339171377262, 'epoch': 7.48}

 62%|██████▏   | 17513/28080 [34:37:03<21:02:11,  7.17s/it]
 62%|██████▏   | 17514/28080 [34:37:10<21:00:59,  7.16s/it]
                                                           
{'loss': 0.6149, 'learning_rate': 0.00016378632432827416, 'epoch': 7.48}

 62%|██████▏   | 17514/28080 [34:37:10<21:00:59,  7.16s/it]
 62%|██████▏   | 17515/28080 [34:37:17<20:57:31,  7.14s/it]
                                                           
{'loss': 0.6129, 'learning_rate': 0.00016375925808975977, 'epoch': 7.48}

 62%|██████▏   | 17515/28080 [34:37:17<20:57:31,  7.14s/it]
 62%|██████▏   | 17516/28080 [34:37:24<20:51:36,  7.11s/it]
                                                           
{'loss': 0.6044, 'learning_rate': 0.00016373219299858942, 'epoch': 7.48}

 62%|██████▏   | 17516/28080 [34:37:24<20:51:36,  7.11s/it]
 62%|██████▏   | 17517/28080 [34:37:31<20:53:06,  7.12s/it]
                                                           
{'loss': 0.6022, 'learning_rate': 0.00016370512905512332, 'epoch': 7.48}

 62%|██████▏   | 17517/28080 [34:37:31<20:53:06,  7.12s/it]
 62%|██████▏   | 17518/28080 [34:37:38<20:55:12,  7.13s/it]
                                                           
{'loss': 0.6063, 'learning_rate': 0.0001636780662597214, 'epoch': 7.48}

 62%|██████▏   | 17518/28080 [34:37:38<20:55:12,  7.13s/it]
 62%|██████▏   | 17519/28080 [34:37:46<20:57:35,  7.14s/it]
                                                           
{'loss': 0.5865, 'learning_rate': 0.0001636510046127438, 'epoch': 7.48}

 62%|██████▏   | 17519/28080 [34:37:46<20:57:35,  7.14s/it]
 62%|██████▏   | 17520/28080 [34:37:53<20:56:08,  7.14s/it]
                                                           
{'loss': 0.611, 'learning_rate': 0.00016362394411455048, 'epoch': 7.48}

 62%|██████▏   | 17520/28080 [34:37:53<20:56:08,  7.14s/it]
 62%|██████▏   | 17521/28080 [34:38:00<20:58:21,  7.15s/it]
                                                           
{'loss': 0.609, 'learning_rate': 0.00016359688476550143, 'epoch': 7.48}

 62%|██████▏   | 17521/28080 [34:38:00<20:58:21,  7.15s/it]
 62%|██████▏   | 17522/28080 [34:38:07<20:50:22,  7.11s/it]
                                                           
{'loss': 0.6373, 'learning_rate': 0.00016356982656595676, 'epoch': 7.49}

 62%|██████▏   | 17522/28080 [34:38:07<20:50:22,  7.11s/it]
 62%|██████▏   | 17523/28080 [34:38:14<20:50:49,  7.11s/it]
                                                           
{'loss': 0.6217, 'learning_rate': 0.00016354276951627633, 'epoch': 7.49}

 62%|██████▏   | 17523/28080 [34:38:14<20:50:49,  7.11s/it]
 62%|██████▏   | 17524/28080 [34:38:21<20:45:31,  7.08s/it]
                                                           
{'loss': 0.6211, 'learning_rate': 0.00016351571361682019, 'epoch': 7.49}

 62%|██████▏   | 17524/28080 [34:38:21<20:45:31,  7.08s/it]
 62%|██████▏   | 17525/28080 [34:38:28<20:44:33,  7.07s/it]
                                                           
{'loss': 0.6207, 'learning_rate': 0.00016348865886794823, 'epoch': 7.49}

 62%|██████▏   | 17525/28080 [34:38:28<20:44:33,  7.07s/it]
 62%|██████▏   | 17526/28080 [34:38:35<20:48:51,  7.10s/it]
                                                           
{'loss': 0.6071, 'learning_rate': 0.00016346160527002046, 'epoch': 7.49}

 62%|██████▏   | 17526/28080 [34:38:35<20:48:51,  7.10s/it]
 62%|██████▏   | 17527/28080 [34:38:42<20:51:47,  7.12s/it]
                                                           
{'loss': 0.6064, 'learning_rate': 0.00016343455282339663, 'epoch': 7.49}

 62%|██████▏   | 17527/28080 [34:38:42<20:51:47,  7.12s/it]
 62%|██████▏   | 17528/28080 [34:38:50<21:03:55,  7.19s/it]
                                                           
{'loss': 0.6114, 'learning_rate': 0.00016340750152843696, 'epoch': 7.49}

 62%|██████▏   | 17528/28080 [34:38:50<21:03:55,  7.19s/it]
 62%|██████▏   | 17529/28080 [34:38:57<21:00:09,  7.17s/it]
                                                           
{'loss': 0.617, 'learning_rate': 0.00016338045138550094, 'epoch': 7.49}

 62%|██████▏   | 17529/28080 [34:38:57<21:00:09,  7.17s/it]
 62%|██████▏   | 17530/28080 [34:39:04<20:50:36,  7.11s/it]
                                                           
{'loss': 0.599, 'learning_rate': 0.0001633534023949488, 'epoch': 7.49}

 62%|██████▏   | 17530/28080 [34:39:04<20:50:36,  7.11s/it]
 62%|██████▏   | 17531/28080 [34:39:11<20:48:01,  7.10s/it]
                                                           
{'loss': 0.6048, 'learning_rate': 0.0001633263545571402, 'epoch': 7.49}

 62%|██████▏   | 17531/28080 [34:39:11<20:48:01,  7.10s/it]
 62%|██████▏   | 17532/28080 [34:39:18<20:51:20,  7.12s/it]
                                                           
{'loss': 0.5926, 'learning_rate': 0.0001632993078724351, 'epoch': 7.49}

 62%|██████▏   | 17532/28080 [34:39:18<20:51:20,  7.12s/it]
 62%|██████▏   | 17533/28080 [34:39:25<20:52:03,  7.12s/it]
                                                           
{'loss': 0.5929, 'learning_rate': 0.00016327226234119318, 'epoch': 7.49}

 62%|██████▏   | 17533/28080 [34:39:25<20:52:03,  7.12s/it]
 62%|██████▏   | 17534/28080 [34:39:32<20:49:01,  7.11s/it]
                                                           
{'loss': 0.6033, 'learning_rate': 0.0001632452179637744, 'epoch': 7.49}

 62%|██████▏   | 17534/28080 [34:39:32<20:49:01,  7.11s/it]
 62%|██████▏   | 17535/28080 [34:39:39<20:54:54,  7.14s/it]
                                                           
{'loss': 0.6087, 'learning_rate': 0.00016321817474053847, 'epoch': 7.49}

 62%|██████▏   | 17535/28080 [34:39:39<20:54:54,  7.14s/it]
 62%|██████▏   | 17536/28080 [34:39:47<20:58:53,  7.16s/it]
                                                           
{'loss': 0.6088, 'learning_rate': 0.00016319113267184522, 'epoch': 7.49}

 62%|██████▏   | 17536/28080 [34:39:47<20:58:53,  7.16s/it]
 62%|██████▏   | 17537/28080 [34:39:54<20:55:11,  7.14s/it]
                                                           
{'loss': 0.6164, 'learning_rate': 0.00016316409175805435, 'epoch': 7.49}

 62%|██████▏   | 17537/28080 [34:39:54<20:55:11,  7.14s/it]
 62%|██████▏   | 17538/28080 [34:40:01<20:51:20,  7.12s/it]
                                                           
{'loss': 0.6019, 'learning_rate': 0.00016313705199952572, 'epoch': 7.49}

 62%|██████▏   | 17538/28080 [34:40:01<20:51:20,  7.12s/it]
 62%|██████▏   | 17539/28080 [34:40:08<20:50:39,  7.12s/it]
                                                           
{'loss': 0.5835, 'learning_rate': 0.0001631100133966189, 'epoch': 7.49}

 62%|██████▏   | 17539/28080 [34:40:08<20:50:39,  7.12s/it]
 62%|██████▏   | 17540/28080 [34:40:15<20:54:36,  7.14s/it]
                                                           
{'loss': 0.5989, 'learning_rate': 0.00016308297594969383, 'epoch': 7.49}

 62%|██████▏   | 17540/28080 [34:40:15<20:54:36,  7.14s/it]
 62%|██████▏   | 17541/28080 [34:40:22<20:51:54,  7.13s/it]
                                                           
{'loss': 0.6343, 'learning_rate': 0.00016305593965910994, 'epoch': 7.49}

 62%|██████▏   | 17541/28080 [34:40:22<20:51:54,  7.13s/it]
 62%|██████▏   | 17542/28080 [34:40:29<20:47:06,  7.10s/it]
                                                           
{'loss': 0.6377, 'learning_rate': 0.00016302890452522727, 'epoch': 7.49}

 62%|██████▏   | 17542/28080 [34:40:29<20:47:06,  7.10s/it]
 62%|██████▏   | 17543/28080 [34:40:36<20:44:28,  7.09s/it]
                                                           
{'loss': 0.6071, 'learning_rate': 0.00016300187054840514, 'epoch': 7.49}

 62%|██████▏   | 17543/28080 [34:40:36<20:44:28,  7.09s/it]
 62%|██████▏   | 17544/28080 [34:40:43<20:46:54,  7.10s/it]
                                                           
{'loss': 0.6006, 'learning_rate': 0.00016297483772900346, 'epoch': 7.49}

 62%|██████▏   | 17544/28080 [34:40:44<20:46:54,  7.10s/it]
 62%|██████▏   | 17545/28080 [34:40:51<20:48:35,  7.11s/it]
                                                           
{'loss': 0.6151, 'learning_rate': 0.00016294780606738185, 'epoch': 7.5}

 62%|██████▏   | 17545/28080 [34:40:51<20:48:35,  7.11s/it]
 62%|██████▏   | 17546/28080 [34:40:58<20:52:04,  7.13s/it]
                                                           
{'loss': 0.6031, 'learning_rate': 0.00016292077556389971, 'epoch': 7.5}

 62%|██████▏   | 17546/28080 [34:40:58<20:52:04,  7.13s/it]
 62%|██████▏   | 17547/28080 [34:41:05<20:50:35,  7.12s/it]
                                                           
{'loss': 0.6005, 'learning_rate': 0.000162893746218917, 'epoch': 7.5}

 62%|██████▏   | 17547/28080 [34:41:05<20:50:35,  7.12s/it]
 62%|██████▏   | 17548/28080 [34:41:12<20:49:01,  7.12s/it]
                                                           
{'loss': 0.5989, 'learning_rate': 0.00016286671803279295, 'epoch': 7.5}

 62%|██████▏   | 17548/28080 [34:41:12<20:49:01,  7.12s/it]
 62%|██████▏   | 17549/28080 [34:41:19<20:45:34,  7.10s/it]
                                                           
{'loss': 0.5941, 'learning_rate': 0.0001628396910058874, 'epoch': 7.5}

 62%|██████▏   | 17549/28080 [34:41:19<20:45:34,  7.10s/it]
 62%|██████▎   | 17550/28080 [34:41:26<20:48:47,  7.12s/it]
                                                           
{'loss': 0.586, 'learning_rate': 0.00016281266513855987, 'epoch': 7.5}

 62%|██████▎   | 17550/28080 [34:41:26<20:48:47,  7.12s/it]
 63%|██████▎   | 17551/28080 [34:41:33<20:54:10,  7.15s/it]
                                                           
{'loss': 0.6075, 'learning_rate': 0.00016278564043116988, 'epoch': 7.5}

 63%|██████▎   | 17551/28080 [34:41:33<20:54:10,  7.15s/it]
 63%|██████▎   | 17552/28080 [34:41:41<20:50:28,  7.13s/it]
                                                           
{'loss': 0.633, 'learning_rate': 0.00016275861688407693, 'epoch': 7.5}

 63%|██████▎   | 17552/28080 [34:41:41<20:50:28,  7.13s/it]
 63%|██████▎   | 17553/28080 [34:41:48<20:42:33,  7.08s/it]
                                                           
{'loss': 0.6155, 'learning_rate': 0.00016273159449764062, 'epoch': 7.5}

 63%|██████▎   | 17553/28080 [34:41:48<20:42:33,  7.08s/it]
 63%|██████▎   | 17554/28080 [34:41:55<20:44:18,  7.09s/it]
                                                           
{'loss': 0.5912, 'learning_rate': 0.0001627045732722204, 'epoch': 7.5}

 63%|██████▎   | 17554/28080 [34:41:55<20:44:18,  7.09s/it]
 63%|██████▎   | 17555/28080 [34:42:02<20:42:44,  7.08s/it]
                                                           
{'loss': 0.6041, 'learning_rate': 0.0001626775532081758, 'epoch': 7.5}

 63%|██████▎   | 17555/28080 [34:42:02<20:42:44,  7.08s/it]
 63%|██████▎   | 17556/28080 [34:42:09<20:49:06,  7.12s/it]
                                                           
{'loss': 0.5885, 'learning_rate': 0.0001626505343058662, 'epoch': 7.5}

 63%|██████▎   | 17556/28080 [34:42:09<20:49:06,  7.12s/it]
 63%|██████▎   | 17557/28080 [34:42:16<20:50:24,  7.13s/it]
                                                           
{'loss': 0.6239, 'learning_rate': 0.0001626235165656512, 'epoch': 7.5}

 63%|██████▎   | 17557/28080 [34:42:16<20:50:24,  7.13s/it]
 63%|██████▎   | 17558/28080 [34:42:23<20:54:39,  7.15s/it]
                                                           
{'loss': 0.6065, 'learning_rate': 0.00016259649998789005, 'epoch': 7.5}

 63%|██████▎   | 17558/28080 [34:42:23<20:54:39,  7.15s/it]
 63%|██████▎   | 17559/28080 [34:42:30<20:54:18,  7.15s/it]
                                                           
{'loss': 0.595, 'learning_rate': 0.00016256948457294248, 'epoch': 7.5}

 63%|██████▎   | 17559/28080 [34:42:30<20:54:18,  7.15s/it]
 63%|██████▎   | 17560/28080 [34:42:38<20:53:17,  7.15s/it]
                                                           
{'loss': 0.6249, 'learning_rate': 0.00016254247032116757, 'epoch': 7.5}

 63%|██████▎   | 17560/28080 [34:42:38<20:53:17,  7.15s/it]
 63%|██████▎   | 17561/28080 [34:42:45<20:55:07,  7.16s/it]
                                                           
{'loss': 0.6166, 'learning_rate': 0.00016251545723292493, 'epoch': 7.5}

 63%|██████▎   | 17561/28080 [34:42:45<20:55:07,  7.16s/it]
 63%|██████▎   | 17562/28080 [34:42:52<20:58:24,  7.18s/it]
                                                           
{'loss': 0.6246, 'learning_rate': 0.00016248844530857386, 'epoch': 7.5}

 63%|██████▎   | 17562/28080 [34:42:52<20:58:24,  7.18s/it]
 63%|██████▎   | 17563/28080 [34:42:59<20:54:17,  7.16s/it]
                                                           
{'loss': 0.639, 'learning_rate': 0.0001624614345484738, 'epoch': 7.5}

 63%|██████▎   | 17563/28080 [34:42:59<20:54:17,  7.16s/it]
 63%|██████▎   | 17564/28080 [34:43:06<20:46:06,  7.11s/it]
                                                           
{'loss': 0.6245, 'learning_rate': 0.000162434424952984, 'epoch': 7.5}

 63%|██████▎   | 17564/28080 [34:43:06<20:46:06,  7.11s/it]
 63%|██████▎   | 17565/28080 [34:43:13<20:35:51,  7.05s/it]
                                                           
{'loss': 0.609, 'learning_rate': 0.0001624074165224639, 'epoch': 7.5}

 63%|██████▎   | 17565/28080 [34:43:13<20:35:51,  7.05s/it]
 63%|██████▎   | 17566/28080 [34:43:20<20:38:02,  7.07s/it]
                                                           
{'loss': 0.6023, 'learning_rate': 0.00016238040925727266, 'epoch': 7.5}

 63%|██████▎   | 17566/28080 [34:43:20<20:38:02,  7.07s/it]
 63%|██████▎   | 17567/28080 [34:43:27<20:38:29,  7.07s/it]
                                                           
{'loss': 0.5943, 'learning_rate': 0.00016235340315776976, 'epoch': 7.5}

 63%|██████▎   | 17567/28080 [34:43:27<20:38:29,  7.07s/it]
 63%|██████▎   | 17568/28080 [34:43:34<20:44:20,  7.10s/it]
                                                           
{'loss': 0.61, 'learning_rate': 0.00016232639822431433, 'epoch': 7.5}

 63%|██████▎   | 17568/28080 [34:43:34<20:44:20,  7.10s/it]
 63%|██████▎   | 17569/28080 [34:43:41<20:47:09,  7.12s/it]
                                                           
{'loss': 0.6108, 'learning_rate': 0.00016229939445726581, 'epoch': 7.51}

 63%|██████▎   | 17569/28080 [34:43:41<20:47:09,  7.12s/it]
 63%|██████▎   | 17570/28080 [34:43:49<20:42:37,  7.09s/it]
                                                           
{'loss': 0.6214, 'learning_rate': 0.00016227239185698337, 'epoch': 7.51}

 63%|██████▎   | 17570/28080 [34:43:49<20:42:37,  7.09s/it]
 63%|██████▎   | 17571/28080 [34:43:56<20:41:45,  7.09s/it]
                                                           
{'loss': 0.6199, 'learning_rate': 0.00016224539042382618, 'epoch': 7.51}

 63%|██████▎   | 17571/28080 [34:43:56<20:41:45,  7.09s/it]
 63%|██████▎   | 17572/28080 [34:44:03<20:44:03,  7.10s/it]
                                                           
{'loss': 0.6161, 'learning_rate': 0.00016221839015815359, 'epoch': 7.51}

 63%|██████▎   | 17572/28080 [34:44:03<20:44:03,  7.10s/it]
 63%|██████▎   | 17573/28080 [34:44:10<20:41:20,  7.09s/it]
                                                           
{'loss': 0.6146, 'learning_rate': 0.00016219139106032473, 'epoch': 7.51}

 63%|██████▎   | 17573/28080 [34:44:10<20:41:20,  7.09s/it]
 63%|██████▎   | 17574/28080 [34:44:17<20:41:35,  7.09s/it]
                                                           
{'loss': 0.6198, 'learning_rate': 0.00016216439313069885, 'epoch': 7.51}

 63%|██████▎   | 17574/28080 [34:44:17<20:41:35,  7.09s/it]
 63%|██████▎   | 17575/28080 [34:44:24<20:48:48,  7.13s/it]
                                                           
{'loss': 0.6115, 'learning_rate': 0.00016213739636963503, 'epoch': 7.51}

 63%|██████▎   | 17575/28080 [34:44:24<20:48:48,  7.13s/it]
 63%|██████▎   | 17576/28080 [34:44:31<20:49:16,  7.14s/it]
                                                           
{'loss': 0.6159, 'learning_rate': 0.00016211040077749266, 'epoch': 7.51}

 63%|██████▎   | 17576/28080 [34:44:31<20:49:16,  7.14s/it]
 63%|██████▎   | 17577/28080 [34:44:38<20:48:17,  7.13s/it]
                                                           
{'loss': 0.6092, 'learning_rate': 0.0001620834063546306, 'epoch': 7.51}

 63%|██████▎   | 17577/28080 [34:44:38<20:48:17,  7.13s/it]
 63%|██████▎   | 17578/28080 [34:44:46<20:49:44,  7.14s/it]
                                                           
{'loss': 0.6165, 'learning_rate': 0.00016205641310140822, 'epoch': 7.51}

 63%|██████▎   | 17578/28080 [34:44:46<20:49:44,  7.14s/it]
 63%|██████▎   | 17579/28080 [34:44:53<20:46:11,  7.12s/it]
                                                           
{'loss': 0.5973, 'learning_rate': 0.00016202942101818443, 'epoch': 7.51}

 63%|██████▎   | 17579/28080 [34:44:53<20:46:11,  7.12s/it]
 63%|██████▎   | 17580/28080 [34:45:00<20:51:48,  7.15s/it]
                                                           
{'loss': 0.626, 'learning_rate': 0.0001620024301053185, 'epoch': 7.51}

 63%|██████▎   | 17580/28080 [34:45:00<20:51:48,  7.15s/it]
 63%|██████▎   | 17581/28080 [34:45:07<20:52:56,  7.16s/it]
                                                           
{'loss': 0.5894, 'learning_rate': 0.00016197544036316948, 'epoch': 7.51}

 63%|██████▎   | 17581/28080 [34:45:07<20:52:56,  7.16s/it]
 63%|██████▎   | 17582/28080 [34:45:14<20:52:43,  7.16s/it]
                                                           
{'loss': 0.6084, 'learning_rate': 0.00016194845179209638, 'epoch': 7.51}

 63%|██████▎   | 17582/28080 [34:45:14<20:52:43,  7.16s/it]
 63%|██████▎   | 17583/28080 [34:45:21<20:53:10,  7.16s/it]
                                                           
{'loss': 0.6084, 'learning_rate': 0.0001619214643924583, 'epoch': 7.51}

 63%|██████▎   | 17583/28080 [34:45:21<20:53:10,  7.16s/it]
 63%|██████▎   | 17584/28080 [34:45:28<20:43:39,  7.11s/it]
                                                           
{'loss': 0.6124, 'learning_rate': 0.0001618944781646143, 'epoch': 7.51}

 63%|██████▎   | 17584/28080 [34:45:28<20:43:39,  7.11s/it]
 63%|██████▎   | 17585/28080 [34:45:36<20:47:59,  7.13s/it]
                                                           
{'loss': 0.6102, 'learning_rate': 0.0001618674931089233, 'epoch': 7.51}

 63%|██████▎   | 17585/28080 [34:45:36<20:47:59,  7.13s/it]
 63%|██████▎   | 17586/28080 [34:45:43<20:51:08,  7.15s/it]
                                                           
{'loss': 0.6224, 'learning_rate': 0.00016184050922574445, 'epoch': 7.51}

 63%|██████▎   | 17586/28080 [34:45:43<20:51:08,  7.15s/it]
 63%|██████▎   | 17587/28080 [34:45:50<20:51:59,  7.16s/it]
                                                           
{'loss': 0.6133, 'learning_rate': 0.00016181352651543663, 'epoch': 7.51}

 63%|██████▎   | 17587/28080 [34:45:50<20:51:59,  7.16s/it]
 63%|██████▎   | 17588/28080 [34:45:57<20:49:53,  7.15s/it]
                                                           
{'loss': 0.627, 'learning_rate': 0.00016178654497835893, 'epoch': 7.51}

 63%|██████▎   | 17588/28080 [34:45:57<20:49:53,  7.15s/it]
 63%|██████▎   | 17589/28080 [34:46:04<20:48:58,  7.14s/it]
                                                           
{'loss': 0.6132, 'learning_rate': 0.00016175956461487014, 'epoch': 7.51}

 63%|██████▎   | 17589/28080 [34:46:04<20:48:58,  7.14s/it]
 63%|██████▎   | 17590/28080 [34:46:11<20:47:00,  7.13s/it]
                                                           
{'loss': 0.6084, 'learning_rate': 0.00016173258542532943, 'epoch': 7.51}

 63%|██████▎   | 17590/28080 [34:46:11<20:47:00,  7.13s/it]
 63%|██████▎   | 17591/28080 [34:46:18<20:48:13,  7.14s/it]
                                                           
{'loss': 0.6359, 'learning_rate': 0.0001617056074100955, 'epoch': 7.51}

 63%|██████▎   | 17591/28080 [34:46:18<20:48:13,  7.14s/it]
 63%|██████▎   | 17592/28080 [34:46:26<20:48:20,  7.14s/it]
                                                           
{'loss': 0.5953, 'learning_rate': 0.00016167863056952743, 'epoch': 7.52}

 63%|██████▎   | 17592/28080 [34:46:26<20:48:20,  7.14s/it]
 63%|██████▎   | 17593/28080 [34:46:33<20:49:51,  7.15s/it]
                                                           
{'loss': 0.6108, 'learning_rate': 0.00016165165490398403, 'epoch': 7.52}

 63%|██████▎   | 17593/28080 [34:46:33<20:49:51,  7.15s/it]
 63%|██████▎   | 17594/28080 [34:46:40<20:44:36,  7.12s/it]
                                                           
{'loss': 0.6371, 'learning_rate': 0.00016162468041382426, 'epoch': 7.52}

 63%|██████▎   | 17594/28080 [34:46:40<20:44:36,  7.12s/it]
 63%|██████▎   | 17595/28080 [34:46:47<20:44:50,  7.12s/it]
                                                           
{'loss': 0.6297, 'learning_rate': 0.00016159770709940703, 'epoch': 7.52}

 63%|██████▎   | 17595/28080 [34:46:47<20:44:50,  7.12s/it]
 63%|██████▎   | 17596/28080 [34:46:54<20:44:41,  7.12s/it]
                                                           
{'loss': 0.5893, 'learning_rate': 0.00016157073496109092, 'epoch': 7.52}

 63%|██████▎   | 17596/28080 [34:46:54<20:44:41,  7.12s/it]
 63%|██████▎   | 17597/28080 [34:47:01<20:43:24,  7.12s/it]
                                                           
{'loss': 0.615, 'learning_rate': 0.0001615437639992351, 'epoch': 7.52}

 63%|██████▎   | 17597/28080 [34:47:01<20:43:24,  7.12s/it]
 63%|██████▎   | 17598/28080 [34:47:08<20:47:58,  7.14s/it]
                                                           
{'loss': 0.6019, 'learning_rate': 0.00016151679421419815, 'epoch': 7.52}

 63%|██████▎   | 17598/28080 [34:47:08<20:47:58,  7.14s/it]
 63%|██████▎   | 17599/28080 [34:47:15<20:46:42,  7.14s/it]
                                                           
{'loss': 0.6072, 'learning_rate': 0.00016148982560633903, 'epoch': 7.52}

 63%|██████▎   | 17599/28080 [34:47:15<20:46:42,  7.14s/it]
 63%|██████▎   | 17600/28080 [34:47:23<20:47:35,  7.14s/it]
                                                           
{'loss': 0.6179, 'learning_rate': 0.00016146285817601644, 'epoch': 7.52}

 63%|██████▎   | 17600/28080 [34:47:23<20:47:35,  7.14s/it]
 63%|██████▎   | 17601/28080 [34:47:30<20:44:51,  7.13s/it]
                                                           
{'loss': 0.6149, 'learning_rate': 0.00016143589192358921, 'epoch': 7.52}

 63%|██████▎   | 17601/28080 [34:47:30<20:44:51,  7.13s/it]
 63%|██████▎   | 17602/28080 [34:47:37<20:41:57,  7.11s/it]
                                                           
{'loss': 0.6278, 'learning_rate': 0.00016140892684941605, 'epoch': 7.52}

 63%|██████▎   | 17602/28080 [34:47:37<20:41:57,  7.11s/it]
 63%|██████▎   | 17603/28080 [34:47:44<20:44:28,  7.13s/it]
                                                           
{'loss': 0.6095, 'learning_rate': 0.00016138196295385575, 'epoch': 7.52}

 63%|██████▎   | 17603/28080 [34:47:44<20:44:28,  7.13s/it]
 63%|██████▎   | 17604/28080 [34:47:51<20:44:00,  7.12s/it]
                                                           
{'loss': 0.6093, 'learning_rate': 0.00016135500023726696, 'epoch': 7.52}

 63%|██████▎   | 17604/28080 [34:47:51<20:44:00,  7.12s/it]
 63%|██████▎   | 17605/28080 [34:47:58<20:41:38,  7.11s/it]
                                                           
{'loss': 0.6208, 'learning_rate': 0.0001613280387000085, 'epoch': 7.52}

 63%|██████▎   | 17605/28080 [34:47:58<20:41:38,  7.11s/it]
 63%|██████▎   | 17606/28080 [34:48:05<20:45:29,  7.13s/it]
                                                           
{'loss': 0.5987, 'learning_rate': 0.0001613010783424389, 'epoch': 7.52}

 63%|██████▎   | 17606/28080 [34:48:05<20:45:29,  7.13s/it]
 63%|██████▎   | 17607/28080 [34:48:12<20:46:10,  7.14s/it]
                                                           
{'loss': 0.6053, 'learning_rate': 0.0001612741191649171, 'epoch': 7.52}

 63%|██████▎   | 17607/28080 [34:48:12<20:46:10,  7.14s/it]
 63%|██████▎   | 17608/28080 [34:48:20<20:42:22,  7.12s/it]
                                                           
{'loss': 0.5993, 'learning_rate': 0.00016124716116780146, 'epoch': 7.52}

 63%|██████▎   | 17608/28080 [34:48:20<20:42:22,  7.12s/it]
 63%|██████▎   | 17609/28080 [34:48:27<20:44:32,  7.13s/it]
                                                           
{'loss': 0.6265, 'learning_rate': 0.00016122020435145097, 'epoch': 7.52}

 63%|██████▎   | 17609/28080 [34:48:27<20:44:32,  7.13s/it]
 63%|██████▎   | 17610/28080 [34:48:34<20:45:38,  7.14s/it]
                                                           
{'loss': 0.6116, 'learning_rate': 0.00016119324871622387, 'epoch': 7.52}

 63%|██████▎   | 17610/28080 [34:48:34<20:45:38,  7.14s/it]
 63%|██████▎   | 17611/28080 [34:48:41<20:41:14,  7.11s/it]
                                                           
{'loss': 0.6254, 'learning_rate': 0.0001611662942624791, 'epoch': 7.52}

 63%|██████▎   | 17611/28080 [34:48:41<20:41:14,  7.11s/it]
 63%|██████▎   | 17612/28080 [34:48:48<20:35:15,  7.08s/it]
                                                           
{'loss': 0.5924, 'learning_rate': 0.00016113934099057505, 'epoch': 7.52}

 63%|██████▎   | 17612/28080 [34:48:48<20:35:15,  7.08s/it]
 63%|██████▎   | 17613/28080 [34:48:55<20:31:58,  7.06s/it]
                                                           
{'loss': 0.6026, 'learning_rate': 0.00016111238890087048, 'epoch': 7.52}

 63%|██████▎   | 17613/28080 [34:48:55<20:31:58,  7.06s/it]
 63%|██████▎   | 17614/28080 [34:49:02<20:37:39,  7.10s/it]
                                                           
{'loss': 0.6045, 'learning_rate': 0.00016108543799372383, 'epoch': 7.52}

 63%|██████▎   | 17614/28080 [34:49:02<20:37:39,  7.10s/it]
 63%|██████▎   | 17615/28080 [34:49:09<20:38:18,  7.10s/it]
                                                           
{'loss': 0.5984, 'learning_rate': 0.00016105848826949377, 'epoch': 7.52}

 63%|██████▎   | 17615/28080 [34:49:09<20:38:18,  7.10s/it]
 63%|██████▎   | 17616/28080 [34:49:16<20:36:41,  7.09s/it]
                                                           
{'loss': 0.5957, 'learning_rate': 0.00016103153972853867, 'epoch': 7.53}

 63%|██████▎   | 17616/28080 [34:49:16<20:36:41,  7.09s/it]
 63%|██████▎   | 17617/28080 [34:49:23<20:39:40,  7.11s/it]
                                                           
{'loss': 0.6241, 'learning_rate': 0.00016100459237121723, 'epoch': 7.53}

 63%|██████▎   | 17617/28080 [34:49:23<20:39:40,  7.11s/it]
 63%|██████▎   | 17618/28080 [34:49:31<20:41:48,  7.12s/it]
                                                           
{'loss': 0.5946, 'learning_rate': 0.0001609776461978878, 'epoch': 7.53}

 63%|██████▎   | 17618/28080 [34:49:31<20:41:48,  7.12s/it]
 63%|██████▎   | 17619/28080 [34:49:38<20:47:56,  7.16s/it]
                                                           
{'loss': 0.6347, 'learning_rate': 0.00016095070120890903, 'epoch': 7.53}

 63%|██████▎   | 17619/28080 [34:49:38<20:47:56,  7.16s/it]
 63%|██████▎   | 17620/28080 [34:49:45<20:38:11,  7.10s/it]
                                                           
{'loss': 0.607, 'learning_rate': 0.0001609237574046393, 'epoch': 7.53}

 63%|██████▎   | 17620/28080 [34:49:45<20:38:11,  7.10s/it]
 63%|██████▎   | 17621/28080 [34:49:52<20:39:43,  7.11s/it]
                                                           
{'loss': 0.6108, 'learning_rate': 0.00016089681478543706, 'epoch': 7.53}

 63%|██████▎   | 17621/28080 [34:49:52<20:39:43,  7.11s/it]
 63%|██████▎   | 17622/28080 [34:49:59<20:42:12,  7.13s/it]
                                                           
{'loss': 0.5975, 'learning_rate': 0.00016086987335166077, 'epoch': 7.53}

 63%|██████▎   | 17622/28080 [34:49:59<20:42:12,  7.13s/it]
 63%|██████▎   | 17623/28080 [34:50:06<20:41:45,  7.12s/it]
                                                           
{'loss': 0.6265, 'learning_rate': 0.00016084293310366878, 'epoch': 7.53}

 63%|██████▎   | 17623/28080 [34:50:06<20:41:45,  7.12s/it]
 63%|██████▎   | 17624/28080 [34:50:13<20:42:42,  7.13s/it]
                                                           
{'loss': 0.6141, 'learning_rate': 0.0001608159940418198, 'epoch': 7.53}

 63%|██████▎   | 17624/28080 [34:50:13<20:42:42,  7.13s/it]
 63%|██████▎   | 17625/28080 [34:50:21<20:44:00,  7.14s/it]
                                                           
{'loss': 0.6002, 'learning_rate': 0.00016078905616647178, 'epoch': 7.53}

 63%|██████▎   | 17625/28080 [34:50:21<20:44:00,  7.14s/it]
 63%|██████▎   | 17626/28080 [34:50:28<20:39:37,  7.11s/it]
                                                           
{'loss': 0.6289, 'learning_rate': 0.00016076211947798353, 'epoch': 7.53}

 63%|██████▎   | 17626/28080 [34:50:28<20:39:37,  7.11s/it]
 63%|██████▎   | 17627/28080 [34:50:35<20:44:13,  7.14s/it]
                                                           
{'loss': 0.6089, 'learning_rate': 0.00016073518397671305, 'epoch': 7.53}

 63%|██████▎   | 17627/28080 [34:50:35<20:44:13,  7.14s/it]
 63%|██████▎   | 17628/28080 [34:50:42<20:47:23,  7.16s/it]
                                                           
{'loss': 0.5987, 'learning_rate': 0.00016070824966301898, 'epoch': 7.53}

 63%|██████▎   | 17628/28080 [34:50:42<20:47:23,  7.16s/it]
 63%|██████▎   | 17629/28080 [34:50:49<20:41:28,  7.13s/it]
                                                           
{'loss': 0.6183, 'learning_rate': 0.00016068131653725946, 'epoch': 7.53}

 63%|██████▎   | 17629/28080 [34:50:49<20:41:28,  7.13s/it]
 63%|██████▎   | 17630/28080 [34:50:56<20:40:41,  7.12s/it]
                                                           
{'loss': 0.6018, 'learning_rate': 0.00016065438459979291, 'epoch': 7.53}

 63%|██████▎   | 17630/28080 [34:50:56<20:40:41,  7.12s/it]
 63%|██████▎   | 17631/28080 [34:51:03<20:43:10,  7.14s/it]
                                                           
{'loss': 0.5995, 'learning_rate': 0.0001606274538509776, 'epoch': 7.53}

 63%|██████▎   | 17631/28080 [34:51:03<20:43:10,  7.14s/it]
 63%|██████▎   | 17632/28080 [34:51:11<20:46:35,  7.16s/it]
                                                           
{'loss': 0.6197, 'learning_rate': 0.00016060052429117184, 'epoch': 7.53}

 63%|██████▎   | 17632/28080 [34:51:11<20:46:35,  7.16s/it]
 63%|██████▎   | 17633/28080 [34:51:18<20:45:15,  7.15s/it]
                                                           
{'loss': 0.6052, 'learning_rate': 0.00016057359592073383, 'epoch': 7.53}

 63%|██████▎   | 17633/28080 [34:51:18<20:45:15,  7.15s/it]
 63%|██████▎   | 17634/28080 [34:51:25<20:44:16,  7.15s/it]
                                                           
{'loss': 0.6008, 'learning_rate': 0.0001605466687400219, 'epoch': 7.53}

 63%|██████▎   | 17634/28080 [34:51:25<20:44:16,  7.15s/it]
 63%|██████▎   | 17635/28080 [34:51:32<20:46:57,  7.16s/it]
                                                           
{'loss': 0.592, 'learning_rate': 0.00016051974274939424, 'epoch': 7.53}

 63%|██████▎   | 17635/28080 [34:51:32<20:46:57,  7.16s/it]
 63%|██████▎   | 17636/28080 [34:51:39<20:45:28,  7.16s/it]
                                                           
{'loss': 0.5945, 'learning_rate': 0.0001604928179492091, 'epoch': 7.53}

 63%|██████▎   | 17636/28080 [34:51:39<20:45:28,  7.16s/it]
 63%|██████▎   | 17637/28080 [34:51:46<20:43:24,  7.14s/it]
                                                           
{'loss': 0.6038, 'learning_rate': 0.00016046589433982463, 'epoch': 7.53}

 63%|██████▎   | 17637/28080 [34:51:46<20:43:24,  7.14s/it]
 63%|██████▎   | 17638/28080 [34:51:53<20:41:48,  7.14s/it]
                                                           
{'loss': 0.6361, 'learning_rate': 0.00016043897192159916, 'epoch': 7.53}

 63%|██████▎   | 17638/28080 [34:51:53<20:41:48,  7.14s/it]
 63%|██████▎   | 17639/28080 [34:52:01<20:41:46,  7.14s/it]
                                                           
{'loss': 0.6116, 'learning_rate': 0.00016041205069489066, 'epoch': 7.54}

 63%|██████▎   | 17639/28080 [34:52:01<20:41:46,  7.14s/it]
 63%|██████▎   | 17640/28080 [34:52:08<20:38:15,  7.12s/it]
                                                           
{'loss': 0.6207, 'learning_rate': 0.00016038513066005757, 'epoch': 7.54}

 63%|██████▎   | 17640/28080 [34:52:08<20:38:15,  7.12s/it]
 63%|██████▎   | 17641/28080 [34:52:15<20:40:31,  7.13s/it]
                                                           
{'loss': 0.6141, 'learning_rate': 0.00016035821181745768, 'epoch': 7.54}

 63%|██████▎   | 17641/28080 [34:52:15<20:40:31,  7.13s/it]
 63%|██████▎   | 17642/28080 [34:52:22<20:42:29,  7.14s/it]
                                                           
{'loss': 0.5987, 'learning_rate': 0.00016033129416744943, 'epoch': 7.54}

 63%|██████▎   | 17642/28080 [34:52:22<20:42:29,  7.14s/it]
 63%|██████▎   | 17643/28080 [34:52:29<20:37:43,  7.12s/it]
                                                           
{'loss': 0.632, 'learning_rate': 0.00016030437771039074, 'epoch': 7.54}

 63%|██████▎   | 17643/28080 [34:52:29<20:37:43,  7.12s/it]
 63%|██████▎   | 17644/28080 [34:52:36<20:37:36,  7.12s/it]
                                                           
{'loss': 0.5949, 'learning_rate': 0.00016027746244663983, 'epoch': 7.54}

 63%|██████▎   | 17644/28080 [34:52:36<20:37:36,  7.12s/it]
 63%|██████▎   | 17645/28080 [34:52:43<20:41:07,  7.14s/it]
                                                           
{'loss': 0.6288, 'learning_rate': 0.00016025054837655472, 'epoch': 7.54}

 63%|██████▎   | 17645/28080 [34:52:43<20:41:07,  7.14s/it]
 63%|██████▎   | 17646/28080 [34:52:50<20:36:56,  7.11s/it]
                                                           
{'loss': 0.6264, 'learning_rate': 0.0001602236355004934, 'epoch': 7.54}

 63%|██████▎   | 17646/28080 [34:52:50<20:36:56,  7.11s/it]
 63%|██████▎   | 17647/28080 [34:52:58<20:42:19,  7.14s/it]
                                                           
{'loss': 0.6077, 'learning_rate': 0.00016019672381881409, 'epoch': 7.54}

 63%|██████▎   | 17647/28080 [34:52:58<20:42:19,  7.14s/it]
 63%|██████▎   | 17648/28080 [34:53:05<20:38:42,  7.12s/it]
                                                           
{'loss': 0.6015, 'learning_rate': 0.00016016981333187463, 'epoch': 7.54}

 63%|██████▎   | 17648/28080 [34:53:05<20:38:42,  7.12s/it]
 63%|██████▎   | 17649/28080 [34:53:12<20:43:00,  7.15s/it]
                                                           
{'loss': 0.62, 'learning_rate': 0.0001601429040400332, 'epoch': 7.54}

 63%|██████▎   | 17649/28080 [34:53:12<20:43:00,  7.15s/it]
 63%|██████▎   | 17650/28080 [34:53:19<20:39:41,  7.13s/it]
                                                           
{'loss': 0.6138, 'learning_rate': 0.00016011599594364768, 'epoch': 7.54}

 63%|██████▎   | 17650/28080 [34:53:19<20:39:41,  7.13s/it]
 63%|██████▎   | 17651/28080 [34:53:26<20:32:02,  7.09s/it]
                                                           
{'loss': 0.6101, 'learning_rate': 0.00016008908904307617, 'epoch': 7.54}

 63%|██████▎   | 17651/28080 [34:53:26<20:32:02,  7.09s/it]
 63%|██████▎   | 17652/28080 [34:53:33<20:28:07,  7.07s/it]
                                                           
{'loss': 0.6119, 'learning_rate': 0.0001600621833386765, 'epoch': 7.54}

 63%|██████▎   | 17652/28080 [34:53:33<20:28:07,  7.07s/it]
 63%|██████▎   | 17653/28080 [34:53:40<20:31:59,  7.09s/it]
                                                           
{'loss': 0.6033, 'learning_rate': 0.00016003527883080677, 'epoch': 7.54}

 63%|██████▎   | 17653/28080 [34:53:40<20:31:59,  7.09s/it]
 63%|██████▎   | 17654/28080 [34:53:47<20:37:53,  7.12s/it]
                                                           
{'loss': 0.6023, 'learning_rate': 0.0001600083755198247, 'epoch': 7.54}

 63%|██████▎   | 17654/28080 [34:53:47<20:37:53,  7.12s/it]
 63%|██████▎   | 17655/28080 [34:53:54<20:37:37,  7.12s/it]
                                                           
{'loss': 0.5967, 'learning_rate': 0.00015998147340608854, 'epoch': 7.54}

 63%|██████▎   | 17655/28080 [34:53:54<20:37:37,  7.12s/it]
 63%|██████▎   | 17656/28080 [34:54:01<20:34:33,  7.11s/it]
                                                           
{'loss': 0.6153, 'learning_rate': 0.00015995457248995588, 'epoch': 7.54}

 63%|██████▎   | 17656/28080 [34:54:01<20:34:33,  7.11s/it]
 63%|██████▎   | 17657/28080 [34:54:09<20:35:24,  7.11s/it]
                                                           
{'loss': 0.6083, 'learning_rate': 0.00015992767277178484, 'epoch': 7.54}

 63%|██████▎   | 17657/28080 [34:54:09<20:35:24,  7.11s/it]
 63%|██████▎   | 17658/28080 [34:54:16<20:32:47,  7.10s/it]
                                                           
{'loss': 0.6097, 'learning_rate': 0.00015990077425193306, 'epoch': 7.54}

 63%|██████▎   | 17658/28080 [34:54:16<20:32:47,  7.10s/it]
 63%|██████▎   | 17659/28080 [34:54:23<20:36:39,  7.12s/it]
                                                           
{'loss': 0.6173, 'learning_rate': 0.00015987387693075866, 'epoch': 7.54}

 63%|██████▎   | 17659/28080 [34:54:23<20:36:39,  7.12s/it]
 63%|██████▎   | 17660/28080 [34:54:30<20:31:13,  7.09s/it]
                                                           
{'loss': 0.6138, 'learning_rate': 0.00015984698080861925, 'epoch': 7.54}

 63%|██████▎   | 17660/28080 [34:54:30<20:31:13,  7.09s/it]
 63%|██████▎   | 17661/28080 [34:54:37<20:32:10,  7.10s/it]
                                                           
{'loss': 0.6262, 'learning_rate': 0.00015982008588587282, 'epoch': 7.54}

 63%|██████▎   | 17661/28080 [34:54:37<20:32:10,  7.10s/it]
 63%|██████▎   | 17662/28080 [34:54:44<20:33:20,  7.10s/it]
                                                           
{'loss': 0.6172, 'learning_rate': 0.0001597931921628771, 'epoch': 7.55}

 63%|██████▎   | 17662/28080 [34:54:44<20:33:20,  7.10s/it]
 63%|██████▎   | 17663/28080 [34:54:51<20:35:22,  7.12s/it]
                                                           
{'loss': 0.5987, 'learning_rate': 0.0001597662996399899, 'epoch': 7.55}

 63%|██████▎   | 17663/28080 [34:54:51<20:35:22,  7.12s/it]
 63%|██████▎   | 17664/28080 [34:54:58<20:36:20,  7.12s/it]
                                                           
{'loss': 0.6183, 'learning_rate': 0.00015973940831756893, 'epoch': 7.55}

 63%|██████▎   | 17664/28080 [34:54:58<20:36:20,  7.12s/it]
 63%|██████▎   | 17665/28080 [34:55:05<20:32:34,  7.10s/it]
                                                           
{'loss': 0.6168, 'learning_rate': 0.00015971251819597214, 'epoch': 7.55}

 63%|██████▎   | 17665/28080 [34:55:05<20:32:34,  7.10s/it]
 63%|██████▎   | 17666/28080 [34:55:13<20:36:42,  7.13s/it]
                                                           
{'loss': 0.6187, 'learning_rate': 0.00015968562927555705, 'epoch': 7.55}

 63%|██████▎   | 17666/28080 [34:55:13<20:36:42,  7.13s/it]
 63%|██████▎   | 17667/28080 [34:55:20<20:35:32,  7.12s/it]
                                                           
{'loss': 0.6343, 'learning_rate': 0.00015965874155668153, 'epoch': 7.55}

 63%|██████▎   | 17667/28080 [34:55:20<20:35:32,  7.12s/it]
 63%|██████▎   | 17668/28080 [34:55:27<20:31:38,  7.10s/it]
                                                           
{'loss': 0.6432, 'learning_rate': 0.0001596318550397032, 'epoch': 7.55}

 63%|██████▎   | 17668/28080 [34:55:27<20:31:38,  7.10s/it]
 63%|██████▎   | 17669/28080 [34:55:34<20:29:17,  7.08s/it]
                                                           
{'loss': 0.5979, 'learning_rate': 0.00015960496972497993, 'epoch': 7.55}

 63%|██████▎   | 17669/28080 [34:55:34<20:29:17,  7.08s/it]
 63%|██████▎   | 17670/28080 [34:55:41<20:27:51,  7.08s/it]
                                                           
{'loss': 0.619, 'learning_rate': 0.00015957808561286923, 'epoch': 7.55}

 63%|██████▎   | 17670/28080 [34:55:41<20:27:51,  7.08s/it]
 63%|██████▎   | 17671/28080 [34:55:48<20:27:34,  7.08s/it]
                                                           
{'loss': 0.5967, 'learning_rate': 0.00015955120270372877, 'epoch': 7.55}

 63%|██████▎   | 17671/28080 [34:55:48<20:27:34,  7.08s/it]
 63%|██████▎   | 17672/28080 [34:55:55<20:27:31,  7.08s/it]
                                                           
{'loss': 0.6109, 'learning_rate': 0.00015952432099791632, 'epoch': 7.55}

 63%|██████▎   | 17672/28080 [34:55:55<20:27:31,  7.08s/it]
 63%|██████▎   | 17673/28080 [34:56:02<20:37:12,  7.13s/it]
                                                           
{'loss': 0.6105, 'learning_rate': 0.0001594974404957893, 'epoch': 7.55}

 63%|██████▎   | 17673/28080 [34:56:02<20:37:12,  7.13s/it]
 63%|██████▎   | 17674/28080 [34:56:09<20:35:44,  7.13s/it]
                                                           
{'loss': 0.5947, 'learning_rate': 0.00015947056119770565, 'epoch': 7.55}

 63%|██████▎   | 17674/28080 [34:56:09<20:35:44,  7.13s/it]
 63%|██████▎   | 17675/28080 [34:56:16<20:32:57,  7.11s/it]
                                                           
{'loss': 0.6193, 'learning_rate': 0.00015944368310402262, 'epoch': 7.55}

 63%|██████▎   | 17675/28080 [34:56:16<20:32:57,  7.11s/it]
 63%|██████▎   | 17676/28080 [34:56:24<20:33:37,  7.11s/it]
                                                           
{'loss': 0.6319, 'learning_rate': 0.00015941680621509808, 'epoch': 7.55}

 63%|██████▎   | 17676/28080 [34:56:24<20:33:37,  7.11s/it]
 63%|██████▎   | 17677/28080 [34:56:31<20:39:15,  7.15s/it]
                                                           
{'loss': 0.6026, 'learning_rate': 0.0001593899305312894, 'epoch': 7.55}

 63%|██████▎   | 17677/28080 [34:56:31<20:39:15,  7.15s/it]
 63%|██████▎   | 17678/28080 [34:56:38<20:41:06,  7.16s/it]
                                                           
{'loss': 0.6145, 'learning_rate': 0.0001593630560529543, 'epoch': 7.55}

 63%|██████▎   | 17678/28080 [34:56:38<20:41:06,  7.16s/it]
 63%|██████▎   | 17679/28080 [34:56:45<20:38:55,  7.15s/it]
                                                           
{'loss': 0.6102, 'learning_rate': 0.0001593361827804502, 'epoch': 7.55}

 63%|██████▎   | 17679/28080 [34:56:45<20:38:55,  7.15s/it]
 63%|██████▎   | 17680/28080 [34:56:52<20:35:52,  7.13s/it]
                                                           
{'loss': 0.6088, 'learning_rate': 0.00015930931071413468, 'epoch': 7.55}

 63%|██████▎   | 17680/28080 [34:56:52<20:35:52,  7.13s/it]
 63%|██████▎   | 17681/28080 [34:56:59<20:32:35,  7.11s/it]
                                                           
{'loss': 0.6239, 'learning_rate': 0.00015928243985436515, 'epoch': 7.55}

 63%|██████▎   | 17681/28080 [34:56:59<20:32:35,  7.11s/it]
 63%|██████▎   | 17682/28080 [34:57:06<20:31:58,  7.11s/it]
                                                           
{'loss': 0.6267, 'learning_rate': 0.0001592555702014993, 'epoch': 7.55}

 63%|██████▎   | 17682/28080 [34:57:06<20:31:58,  7.11s/it]
 63%|██████▎   | 17683/28080 [34:57:14<20:32:04,  7.11s/it]
                                                           
{'loss': 0.6274, 'learning_rate': 0.00015922870175589434, 'epoch': 7.55}

 63%|██████▎   | 17683/28080 [34:57:14<20:32:04,  7.11s/it]
 63%|██████▎   | 17684/28080 [34:57:21<20:40:13,  7.16s/it]
                                                           
{'loss': 0.6131, 'learning_rate': 0.00015920183451790794, 'epoch': 7.55}

 63%|██████▎   | 17684/28080 [34:57:21<20:40:13,  7.16s/it]
 63%|██████▎   | 17685/28080 [34:57:28<20:42:42,  7.17s/it]
                                                           
{'loss': 0.5971, 'learning_rate': 0.00015917496848789735, 'epoch': 7.55}

 63%|██████▎   | 17685/28080 [34:57:28<20:42:42,  7.17s/it]
 63%|██████▎   | 17686/28080 [34:57:35<20:46:48,  7.20s/it]
                                                           
{'loss': 0.6, 'learning_rate': 0.00015914810366622024, 'epoch': 7.56}

 63%|██████▎   | 17686/28080 [34:57:35<20:46:48,  7.20s/it]
 63%|██████▎   | 17687/28080 [34:57:42<20:41:31,  7.17s/it]
                                                           
{'loss': 0.6182, 'learning_rate': 0.00015912124005323374, 'epoch': 7.56}

 63%|██████▎   | 17687/28080 [34:57:42<20:41:31,  7.17s/it]
 63%|██████▎   | 17688/28080 [34:57:50<20:44:09,  7.18s/it]
                                                           
{'loss': 0.6124, 'learning_rate': 0.00015909437764929558, 'epoch': 7.56}

 63%|██████▎   | 17688/28080 [34:57:50<20:44:09,  7.18s/it]
 63%|██████▎   | 17689/28080 [34:57:57<20:40:29,  7.16s/it]
                                                           
{'loss': 0.6191, 'learning_rate': 0.00015906751645476276, 'epoch': 7.56}

 63%|██████▎   | 17689/28080 [34:57:57<20:40:29,  7.16s/it]
 63%|██████▎   | 17690/28080 [34:58:04<20:37:00,  7.14s/it]
                                                           
{'loss': 0.5938, 'learning_rate': 0.00015904065646999294, 'epoch': 7.56}

 63%|██████▎   | 17690/28080 [34:58:04<20:37:00,  7.14s/it]
 63%|██████▎   | 17691/28080 [34:58:11<20:34:26,  7.13s/it]
                                                           
{'loss': 0.6471, 'learning_rate': 0.0001590137976953433, 'epoch': 7.56}

 63%|██████▎   | 17691/28080 [34:58:11<20:34:26,  7.13s/it]
 63%|██████▎   | 17692/28080 [34:58:18<20:29:08,  7.10s/it]
                                                           
{'loss': 0.6259, 'learning_rate': 0.00015898694013117125, 'epoch': 7.56}

 63%|██████▎   | 17692/28080 [34:58:18<20:29:08,  7.10s/it]
 63%|██████▎   | 17693/28080 [34:58:25<20:32:45,  7.12s/it]
                                                           
{'loss': 0.6001, 'learning_rate': 0.000158960083777834, 'epoch': 7.56}

 63%|██████▎   | 17693/28080 [34:58:25<20:32:45,  7.12s/it]
 63%|██████▎   | 17694/28080 [34:58:32<20:29:39,  7.10s/it]
                                                           
{'loss': 0.6167, 'learning_rate': 0.00015893322863568899, 'epoch': 7.56}

 63%|██████▎   | 17694/28080 [34:58:32<20:29:39,  7.10s/it]
 63%|██████▎   | 17695/28080 [34:58:39<20:30:23,  7.11s/it]
                                                           
{'loss': 0.6039, 'learning_rate': 0.00015890637470509345, 'epoch': 7.56}

 63%|██████▎   | 17695/28080 [34:58:39<20:30:23,  7.11s/it]
 63%|██████▎   | 17696/28080 [34:58:46<20:31:54,  7.12s/it]
                                                           
{'loss': 0.6165, 'learning_rate': 0.00015887952198640452, 'epoch': 7.56}

 63%|██████▎   | 17696/28080 [34:58:46<20:31:54,  7.12s/it]
 63%|██████▎   | 17697/28080 [34:58:54<20:35:28,  7.14s/it]
                                                           
{'loss': 0.6162, 'learning_rate': 0.0001588526704799796, 'epoch': 7.56}

 63%|██████▎   | 17697/28080 [34:58:54<20:35:28,  7.14s/it]
 63%|██████▎   | 17698/28080 [34:59:01<20:35:31,  7.14s/it]
                                                           
{'loss': 0.6213, 'learning_rate': 0.00015882582018617586, 'epoch': 7.56}

 63%|██████▎   | 17698/28080 [34:59:01<20:35:31,  7.14s/it]
 63%|██████▎   | 17699/28080 [34:59:08<20:29:32,  7.11s/it]
                                                           
{'loss': 0.6073, 'learning_rate': 0.00015879897110535052, 'epoch': 7.56}

 63%|██████▎   | 17699/28080 [34:59:08<20:29:32,  7.11s/it]
 63%|██████▎   | 17700/28080 [34:59:15<20:25:47,  7.09s/it]
                                                           
{'loss': 0.5932, 'learning_rate': 0.00015877212323786078, 'epoch': 7.56}

 63%|██████▎   | 17700/28080 [34:59:15<20:25:47,  7.09s/it]
 63%|██████▎   | 17701/28080 [34:59:22<20:24:09,  7.08s/it]
                                                           
{'loss': 0.5888, 'learning_rate': 0.00015874527658406385, 'epoch': 7.56}

 63%|██████▎   | 17701/28080 [34:59:22<20:24:09,  7.08s/it]
 63%|██████▎   | 17702/28080 [34:59:29<20:32:50,  7.13s/it]
                                                           
{'loss': 0.6055, 'learning_rate': 0.00015871843114431683, 'epoch': 7.56}

 63%|██████▎   | 17702/28080 [34:59:29<20:32:50,  7.13s/it]
 63%|██████▎   | 17703/28080 [34:59:36<20:31:20,  7.12s/it]
                                                           
{'loss': 0.5945, 'learning_rate': 0.00015869158691897694, 'epoch': 7.56}

 63%|██████▎   | 17703/28080 [34:59:36<20:31:20,  7.12s/it]
 63%|██████▎   | 17704/28080 [34:59:43<20:31:51,  7.12s/it]
                                                           
{'loss': 0.5948, 'learning_rate': 0.00015866474390840125, 'epoch': 7.56}

 63%|██████▎   | 17704/28080 [34:59:43<20:31:51,  7.12s/it]
 63%|██████▎   | 17705/28080 [34:59:50<20:25:33,  7.09s/it]
                                                           
{'loss': 0.6099, 'learning_rate': 0.00015863790211294703, 'epoch': 7.56}

 63%|██████▎   | 17705/28080 [34:59:50<20:25:33,  7.09s/it]
 63%|██████▎   | 17706/28080 [34:59:57<20:26:30,  7.09s/it]
                                                           
{'loss': 0.6249, 'learning_rate': 0.00015861106153297112, 'epoch': 7.56}

 63%|██████▎   | 17706/28080 [34:59:57<20:26:30,  7.09s/it]
 63%|██████▎   | 17707/28080 [35:00:05<20:32:42,  7.13s/it]
                                                           
{'loss': 0.6112, 'learning_rate': 0.00015858422216883083, 'epoch': 7.56}

 63%|██████▎   | 17707/28080 [35:00:05<20:32:42,  7.13s/it]
 63%|██████▎   | 17708/28080 [35:00:12<20:35:36,  7.15s/it]
                                                           
{'loss': 0.6069, 'learning_rate': 0.00015855738402088313, 'epoch': 7.56}

 63%|██████▎   | 17708/28080 [35:00:12<20:35:36,  7.15s/it]
 63%|██████▎   | 17709/28080 [35:00:19<20:34:29,  7.14s/it]
                                                           
{'loss': 0.6033, 'learning_rate': 0.00015853054708948517, 'epoch': 7.57}

 63%|██████▎   | 17709/28080 [35:00:19<20:34:29,  7.14s/it]
 63%|██████▎   | 17710/28080 [35:00:26<20:41:34,  7.18s/it]
                                                           
{'loss': 0.5924, 'learning_rate': 0.00015850371137499382, 'epoch': 7.57}

 63%|██████▎   | 17710/28080 [35:00:26<20:41:34,  7.18s/it]
 63%|██████▎   | 17711/28080 [35:00:33<20:35:39,  7.15s/it]
                                                           
{'loss': 0.637, 'learning_rate': 0.00015847687687776629, 'epoch': 7.57}

 63%|██████▎   | 17711/28080 [35:00:33<20:35:39,  7.15s/it]
 63%|██████▎   | 17712/28080 [35:00:40<20:35:52,  7.15s/it]
                                                           
{'loss': 0.5907, 'learning_rate': 0.0001584500435981594, 'epoch': 7.57}

 63%|██████▎   | 17712/28080 [35:00:40<20:35:52,  7.15s/it]
 63%|██████▎   | 17713/28080 [35:00:48<20:36:37,  7.16s/it]
                                                           
{'loss': 0.632, 'learning_rate': 0.00015842321153653033, 'epoch': 7.57}

 63%|██████▎   | 17713/28080 [35:00:48<20:36:37,  7.16s/it]
 63%|██████▎   | 17714/28080 [35:00:55<20:39:16,  7.17s/it]
                                                           
{'loss': 0.6071, 'learning_rate': 0.00015839638069323585, 'epoch': 7.57}

 63%|██████▎   | 17714/28080 [35:00:55<20:39:16,  7.17s/it]
 63%|██████▎   | 17715/28080 [35:01:02<20:38:10,  7.17s/it]
                                                           
{'loss': 0.5999, 'learning_rate': 0.00015836955106863316, 'epoch': 7.57}

 63%|██████▎   | 17715/28080 [35:01:02<20:38:10,  7.17s/it]
 63%|██████▎   | 17716/28080 [35:01:09<20:31:57,  7.13s/it]
                                                           
{'loss': 0.6234, 'learning_rate': 0.00015834272266307888, 'epoch': 7.57}

 63%|██████▎   | 17716/28080 [35:01:09<20:31:57,  7.13s/it]
 63%|██████▎   | 17717/28080 [35:01:16<20:32:30,  7.14s/it]
                                                           
{'loss': 0.6283, 'learning_rate': 0.0001583158954769303, 'epoch': 7.57}

 63%|██████▎   | 17717/28080 [35:01:16<20:32:30,  7.14s/it]
 63%|██████▎   | 17718/28080 [35:01:23<20:24:34,  7.09s/it]
                                                           
{'loss': 0.6421, 'learning_rate': 0.000158289069510544, 'epoch': 7.57}

 63%|██████▎   | 17718/28080 [35:01:23<20:24:34,  7.09s/it]
 63%|██████▎   | 17719/28080 [35:01:30<20:29:22,  7.12s/it]
                                                           
{'loss': 0.6259, 'learning_rate': 0.00015826224476427718, 'epoch': 7.57}

 63%|██████▎   | 17719/28080 [35:01:30<20:29:22,  7.12s/it]
 63%|██████▎   | 17720/28080 [35:01:38<20:30:55,  7.13s/it]
                                                           
{'loss': 0.6337, 'learning_rate': 0.00015823542123848648, 'epoch': 7.57}

 63%|██████▎   | 17720/28080 [35:01:38<20:30:55,  7.13s/it]
 63%|██████▎   | 17721/28080 [35:01:45<20:29:49,  7.12s/it]
                                                           
{'loss': 0.6013, 'learning_rate': 0.00015820859893352874, 'epoch': 7.57}

 63%|██████▎   | 17721/28080 [35:01:45<20:29:49,  7.12s/it]
 63%|██████▎   | 17722/28080 [35:01:52<20:26:17,  7.10s/it]
                                                           
{'loss': 0.6094, 'learning_rate': 0.00015818177784976105, 'epoch': 7.57}

 63%|██████▎   | 17722/28080 [35:01:52<20:26:17,  7.10s/it]
 63%|██████▎   | 17723/28080 [35:01:59<20:32:06,  7.14s/it]
                                                           
{'loss': 0.6106, 'learning_rate': 0.00015815495798753994, 'epoch': 7.57}

 63%|██████▎   | 17723/28080 [35:01:59<20:32:06,  7.14s/it]
 63%|██████▎   | 17724/28080 [35:02:06<20:24:26,  7.09s/it]
                                                           
{'loss': 0.619, 'learning_rate': 0.00015812813934722243, 'epoch': 7.57}

 63%|██████▎   | 17724/28080 [35:02:06<20:24:26,  7.09s/it]
 63%|██████▎   | 17725/28080 [35:02:13<20:27:48,  7.11s/it]
                                                           
{'loss': 0.5973, 'learning_rate': 0.00015810132192916522, 'epoch': 7.57}

 63%|██████▎   | 17725/28080 [35:02:13<20:27:48,  7.11s/it]
 63%|██████▎   | 17726/28080 [35:02:20<20:22:06,  7.08s/it]
                                                           
{'loss': 0.602, 'learning_rate': 0.00015807450573372515, 'epoch': 7.57}

 63%|██████▎   | 17726/28080 [35:02:20<20:22:06,  7.08s/it]
 63%|██████▎   | 17727/28080 [35:02:27<20:23:49,  7.09s/it]
                                                           
{'loss': 0.5979, 'learning_rate': 0.0001580476907612589, 'epoch': 7.57}

 63%|██████▎   | 17727/28080 [35:02:27<20:23:49,  7.09s/it]
 63%|██████▎   | 17728/28080 [35:02:34<20:18:13,  7.06s/it]
                                                           
{'loss': 0.6322, 'learning_rate': 0.0001580208770121233, 'epoch': 7.57}

 63%|██████▎   | 17728/28080 [35:02:34<20:18:13,  7.06s/it]
 63%|██████▎   | 17729/28080 [35:02:41<20:26:08,  7.11s/it]
                                                           
{'loss': 0.61, 'learning_rate': 0.00015799406448667504, 'epoch': 7.57}

 63%|██████▎   | 17729/28080 [35:02:41<20:26:08,  7.11s/it]
 63%|██████▎   | 17730/28080 [35:02:48<20:26:00,  7.11s/it]
                                                           
{'loss': 0.5998, 'learning_rate': 0.00015796725318527083, 'epoch': 7.57}

 63%|██████▎   | 17730/28080 [35:02:49<20:26:00,  7.11s/it]
 63%|██████▎   | 17731/28080 [35:02:56<20:23:42,  7.09s/it]
                                                           
{'loss': 0.6309, 'learning_rate': 0.00015794044310826739, 'epoch': 7.57}

 63%|██████▎   | 17731/28080 [35:02:56<20:23:42,  7.09s/it]
 63%|██████▎   | 17732/28080 [35:03:03<20:25:33,  7.11s/it]
                                                           
{'loss': 0.5787, 'learning_rate': 0.00015791363425602138, 'epoch': 7.57}

 63%|██████▎   | 17732/28080 [35:03:03<20:25:33,  7.11s/it]
 63%|██████▎   | 17733/28080 [35:03:10<20:24:54,  7.10s/it]
                                                           
{'loss': 0.6047, 'learning_rate': 0.00015788682662888943, 'epoch': 7.58}

 63%|██████▎   | 17733/28080 [35:03:10<20:24:54,  7.10s/it]
 63%|██████▎   | 17734/28080 [35:03:17<20:22:16,  7.09s/it]
                                                           
{'loss': 0.5936, 'learning_rate': 0.00015786002022722824, 'epoch': 7.58}

 63%|██████▎   | 17734/28080 [35:03:17<20:22:16,  7.09s/it]
 63%|██████▎   | 17735/28080 [35:03:24<20:21:54,  7.09s/it]
                                                           
{'loss': 0.5986, 'learning_rate': 0.00015783321505139435, 'epoch': 7.58}

 63%|██████▎   | 17735/28080 [35:03:24<20:21:54,  7.09s/it]
 63%|██████▎   | 17736/28080 [35:03:31<20:28:26,  7.13s/it]
                                                           
{'loss': 0.587, 'learning_rate': 0.00015780641110174463, 'epoch': 7.58}

 63%|██████▎   | 17736/28080 [35:03:31<20:28:26,  7.13s/it]
 63%|██████▎   | 17737/28080 [35:03:38<20:30:44,  7.14s/it]
                                                           
{'loss': 0.6279, 'learning_rate': 0.00015777960837863532, 'epoch': 7.58}

 63%|██████▎   | 17737/28080 [35:03:38<20:30:44,  7.14s/it]
 63%|██████▎   | 17738/28080 [35:03:45<20:26:58,  7.12s/it]
                                                           
{'loss': 0.6091, 'learning_rate': 0.00015775280688242328, 'epoch': 7.58}

 63%|██████▎   | 17738/28080 [35:03:45<20:26:58,  7.12s/it]
 63%|██████▎   | 17739/28080 [35:03:53<20:31:39,  7.15s/it]
                                                           
{'loss': 0.6039, 'learning_rate': 0.00015772600661346492, 'epoch': 7.58}

 63%|██████▎   | 17739/28080 [35:03:53<20:31:39,  7.15s/it]
 63%|██████▎   | 17740/28080 [35:04:00<20:26:26,  7.12s/it]
                                                           
{'loss': 0.6105, 'learning_rate': 0.00015769920757211693, 'epoch': 7.58}

 63%|██████▎   | 17740/28080 [35:04:00<20:26:26,  7.12s/it]
 63%|██████▎   | 17741/28080 [35:04:07<20:22:20,  7.09s/it]
                                                           
{'loss': 0.6179, 'learning_rate': 0.0001576724097587357, 'epoch': 7.58}

 63%|██████▎   | 17741/28080 [35:04:07<20:22:20,  7.09s/it]
 63%|██████▎   | 17742/28080 [35:04:14<20:28:14,  7.13s/it]
                                                           
{'loss': 0.6148, 'learning_rate': 0.00015764561317367783, 'epoch': 7.58}

 63%|██████▎   | 17742/28080 [35:04:14<20:28:14,  7.13s/it]
 63%|██████▎   | 17743/28080 [35:04:21<20:26:00,  7.12s/it]
                                                           
{'loss': 0.6182, 'learning_rate': 0.00015761881781729977, 'epoch': 7.58}

 63%|██████▎   | 17743/28080 [35:04:21<20:26:00,  7.12s/it]
 63%|██████▎   | 17744/28080 [35:04:28<20:24:24,  7.11s/it]
                                                           
{'loss': 0.6091, 'learning_rate': 0.0001575920236899581, 'epoch': 7.58}

 63%|██████▎   | 17744/28080 [35:04:28<20:24:24,  7.11s/it]
 63%|██████▎   | 17745/28080 [35:04:35<20:24:26,  7.11s/it]
                                                           
{'loss': 0.6086, 'learning_rate': 0.00015756523079200923, 'epoch': 7.58}

 63%|██████▎   | 17745/28080 [35:04:35<20:24:26,  7.11s/it]
 63%|██████▎   | 17746/28080 [35:04:42<20:25:27,  7.12s/it]
                                                           
{'loss': 0.6163, 'learning_rate': 0.00015753843912380953, 'epoch': 7.58}

 63%|██████▎   | 17746/28080 [35:04:42<20:25:27,  7.12s/it]
 63%|██████▎   | 17747/28080 [35:04:49<20:24:42,  7.11s/it]
                                                           
{'loss': 0.6082, 'learning_rate': 0.00015751164868571554, 'epoch': 7.58}

 63%|██████▎   | 17747/28080 [35:04:49<20:24:42,  7.11s/it]
 63%|██████▎   | 17748/28080 [35:04:57<20:25:29,  7.12s/it]
                                                           
{'loss': 0.5947, 'learning_rate': 0.00015748485947808367, 'epoch': 7.58}

 63%|██████▎   | 17748/28080 [35:04:57<20:25:29,  7.12s/it]
 63%|██████▎   | 17749/28080 [35:05:04<20:24:05,  7.11s/it]
                                                           
{'loss': 0.6082, 'learning_rate': 0.0001574580715012703, 'epoch': 7.58}

 63%|██████▎   | 17749/28080 [35:05:04<20:24:05,  7.11s/it]
 63%|██████▎   | 17750/28080 [35:05:11<20:26:15,  7.12s/it]
                                                           
{'loss': 0.5899, 'learning_rate': 0.00015743128475563176, 'epoch': 7.58}

 63%|██████▎   | 17750/28080 [35:05:11<20:26:15,  7.12s/it]
 63%|██████▎   | 17751/28080 [35:05:18<20:31:24,  7.15s/it]
                                                           
{'loss': 0.6062, 'learning_rate': 0.00015740449924152454, 'epoch': 7.58}

 63%|██████▎   | 17751/28080 [35:05:18<20:31:24,  7.15s/it]
 63%|██████▎   | 17752/28080 [35:05:25<20:32:49,  7.16s/it]
                                                           
{'loss': 0.6152, 'learning_rate': 0.00015737771495930483, 'epoch': 7.58}

 63%|██████▎   | 17752/28080 [35:05:25<20:32:49,  7.16s/it]
 63%|██████▎   | 17753/28080 [35:05:32<20:32:09,  7.16s/it]
                                                           
{'loss': 0.6115, 'learning_rate': 0.00015735093190932925, 'epoch': 7.58}

 63%|██████▎   | 17753/28080 [35:05:32<20:32:09,  7.16s/it]
 63%|██████▎   | 17754/28080 [35:05:40<20:32:29,  7.16s/it]
                                                           
{'loss': 0.6048, 'learning_rate': 0.00015732415009195376, 'epoch': 7.58}

 63%|██████▎   | 17754/28080 [35:05:40<20:32:29,  7.16s/it]
 63%|██████▎   | 17755/28080 [35:05:47<20:26:06,  7.13s/it]
                                                           
{'loss': 0.628, 'learning_rate': 0.00015729736950753493, 'epoch': 7.58}

 63%|██████▎   | 17755/28080 [35:05:47<20:26:06,  7.13s/it]
 63%|██████▎   | 17756/28080 [35:05:54<20:29:28,  7.15s/it]
                                                           
{'loss': 0.623, 'learning_rate': 0.00015727059015642895, 'epoch': 7.59}

 63%|██████▎   | 17756/28080 [35:05:54<20:29:28,  7.15s/it]
 63%|██████▎   | 17757/28080 [35:06:01<20:33:41,  7.17s/it]
                                                           
{'loss': 0.606, 'learning_rate': 0.00015724381203899212, 'epoch': 7.59}

 63%|██████▎   | 17757/28080 [35:06:01<20:33:41,  7.17s/it]
 63%|██████▎   | 17758/28080 [35:06:08<20:36:13,  7.19s/it]
                                                           
{'loss': 0.622, 'learning_rate': 0.00015721703515558067, 'epoch': 7.59}

 63%|██████▎   | 17758/28080 [35:06:08<20:36:13,  7.19s/it]
 63%|██████▎   | 17759/28080 [35:06:15<20:22:48,  7.11s/it]
                                                           
{'loss': 0.6268, 'learning_rate': 0.00015719025950655086, 'epoch': 7.59}

 63%|██████▎   | 17759/28080 [35:06:15<20:22:48,  7.11s/it]
 63%|██████▎   | 17760/28080 [35:06:22<20:21:54,  7.10s/it]
                                                           
{'loss': 0.6229, 'learning_rate': 0.00015716348509225886, 'epoch': 7.59}

 63%|██████▎   | 17760/28080 [35:06:22<20:21:54,  7.10s/it]
 63%|██████▎   | 17761/28080 [35:06:29<20:22:25,  7.11s/it]
                                                           
{'loss': 0.6195, 'learning_rate': 0.000157136711913061, 'epoch': 7.59}

 63%|██████▎   | 17761/28080 [35:06:29<20:22:25,  7.11s/it]
 63%|██████▎   | 17762/28080 [35:06:36<20:17:22,  7.08s/it]
                                                           
{'loss': 0.5997, 'learning_rate': 0.00015710993996931327, 'epoch': 7.59}

 63%|██████▎   | 17762/28080 [35:06:36<20:17:22,  7.08s/it]
 63%|██████▎   | 17763/28080 [35:06:43<20:16:58,  7.08s/it]
                                                           
{'loss': 0.614, 'learning_rate': 0.00015708316926137206, 'epoch': 7.59}

 63%|██████▎   | 17763/28080 [35:06:43<20:16:58,  7.08s/it]
 63%|██████▎   | 17764/28080 [35:06:50<20:16:23,  7.07s/it]
                                                           
{'loss': 0.6181, 'learning_rate': 0.00015705639978959337, 'epoch': 7.59}

 63%|██████▎   | 17764/28080 [35:06:50<20:16:23,  7.07s/it]
 63%|██████▎   | 17765/28080 [35:06:58<20:14:03,  7.06s/it]
                                                           
{'loss': 0.6359, 'learning_rate': 0.00015702963155433345, 'epoch': 7.59}

 63%|██████▎   | 17765/28080 [35:06:58<20:14:03,  7.06s/it]
 63%|██████▎   | 17766/28080 [35:07:05<20:16:28,  7.08s/it]
                                                           
{'loss': 0.6054, 'learning_rate': 0.00015700286455594826, 'epoch': 7.59}

 63%|██████▎   | 17766/28080 [35:07:05<20:16:28,  7.08s/it]
 63%|██████▎   | 17767/28080 [35:07:12<20:18:54,  7.09s/it]
                                                           
{'loss': 0.5977, 'learning_rate': 0.00015697609879479417, 'epoch': 7.59}

 63%|██████▎   | 17767/28080 [35:07:12<20:18:54,  7.09s/it]
 63%|██████▎   | 17768/28080 [35:07:19<20:21:21,  7.11s/it]
                                                           
{'loss': 0.6126, 'learning_rate': 0.000156949334271227, 'epoch': 7.59}

 63%|██████▎   | 17768/28080 [35:07:19<20:21:21,  7.11s/it]
 63%|██████▎   | 17769/28080 [35:07:26<20:22:21,  7.11s/it]
                                                           
{'loss': 0.6086, 'learning_rate': 0.00015692257098560297, 'epoch': 7.59}

 63%|██████▎   | 17769/28080 [35:07:26<20:22:21,  7.11s/it]
 63%|██████▎   | 17770/28080 [35:07:33<20:13:52,  7.06s/it]
                                                           
{'loss': 0.6115, 'learning_rate': 0.0001568958089382782, 'epoch': 7.59}

 63%|██████▎   | 17770/28080 [35:07:33<20:13:52,  7.06s/it]
 63%|██████▎   | 17771/28080 [35:07:40<20:19:53,  7.10s/it]
                                                           
{'loss': 0.6122, 'learning_rate': 0.0001568690481296085, 'epoch': 7.59}

 63%|██████▎   | 17771/28080 [35:07:40<20:19:53,  7.10s/it]
 63%|██████▎   | 17772/28080 [35:07:47<20:21:59,  7.11s/it]
                                                           
{'loss': 0.6051, 'learning_rate': 0.00015684228855995013, 'epoch': 7.59}

 63%|██████▎   | 17772/28080 [35:07:47<20:21:59,  7.11s/it]
 63%|██████▎   | 17773/28080 [35:07:54<20:22:18,  7.12s/it]
                                                           
{'loss': 0.6102, 'learning_rate': 0.00015681553022965893, 'epoch': 7.59}

 63%|██████▎   | 17773/28080 [35:07:54<20:22:18,  7.12s/it]
 63%|██████▎   | 17774/28080 [35:08:02<20:23:35,  7.12s/it]
                                                           
{'loss': 0.6116, 'learning_rate': 0.00015678877313909107, 'epoch': 7.59}

 63%|██████▎   | 17774/28080 [35:08:02<20:23:35,  7.12s/it]
 63%|██████▎   | 17775/28080 [35:08:09<20:25:00,  7.13s/it]
                                                           
{'loss': 0.6077, 'learning_rate': 0.00015676201728860234, 'epoch': 7.59}

 63%|██████▎   | 17775/28080 [35:08:09<20:25:00,  7.13s/it]
 63%|██████▎   | 17776/28080 [35:08:16<20:26:26,  7.14s/it]
                                                           
{'loss': 0.6064, 'learning_rate': 0.00015673526267854883, 'epoch': 7.59}

 63%|██████▎   | 17776/28080 [35:08:16<20:26:26,  7.14s/it]
 63%|██████▎   | 17777/28080 [35:08:23<20:22:43,  7.12s/it]
                                                           
{'loss': 0.6188, 'learning_rate': 0.00015670850930928637, 'epoch': 7.59}

 63%|██████▎   | 17777/28080 [35:08:23<20:22:43,  7.12s/it]
 63%|██████▎   | 17778/28080 [35:08:30<20:22:50,  7.12s/it]
                                                           
{'loss': 0.5965, 'learning_rate': 0.00015668175718117102, 'epoch': 7.59}

 63%|██████▎   | 17778/28080 [35:08:30<20:22:50,  7.12s/it]
 63%|██████▎   | 17779/28080 [35:08:37<20:20:03,  7.11s/it]
                                                           
{'loss': 0.595, 'learning_rate': 0.00015665500629455858, 'epoch': 7.6}

 63%|██████▎   | 17779/28080 [35:08:37<20:20:03,  7.11s/it]
 63%|██████▎   | 17780/28080 [35:08:44<20:23:15,  7.13s/it]
                                                           
{'loss': 0.5934, 'learning_rate': 0.00015662825664980502, 'epoch': 7.6}

 63%|██████▎   | 17780/28080 [35:08:44<20:23:15,  7.13s/it]
 63%|██████▎   | 17781/28080 [35:08:51<20:24:57,  7.14s/it]
                                                           
{'loss': 0.6063, 'learning_rate': 0.00015660150824726616, 'epoch': 7.6}

 63%|██████▎   | 17781/28080 [35:08:51<20:24:57,  7.14s/it]
 63%|██████▎   | 17782/28080 [35:08:59<20:26:19,  7.15s/it]
                                                           
{'loss': 0.626, 'learning_rate': 0.00015657476108729788, 'epoch': 7.6}

 63%|██████▎   | 17782/28080 [35:08:59<20:26:19,  7.15s/it]
 63%|██████▎   | 17783/28080 [35:09:06<20:23:17,  7.13s/it]
                                                           
{'loss': 0.6163, 'learning_rate': 0.00015654801517025593, 'epoch': 7.6}

 63%|██████▎   | 17783/28080 [35:09:06<20:23:17,  7.13s/it]
 63%|██████▎   | 17784/28080 [35:09:13<20:15:18,  7.08s/it]
                                                           
{'loss': 0.6413, 'learning_rate': 0.0001565212704964964, 'epoch': 7.6}

 63%|██████▎   | 17784/28080 [35:09:13<20:15:18,  7.08s/it]
 63%|██████▎   | 17785/28080 [35:09:20<20:20:00,  7.11s/it]
                                                           
{'loss': 0.6203, 'learning_rate': 0.00015649452706637475, 'epoch': 7.6}

 63%|██████▎   | 17785/28080 [35:09:20<20:20:00,  7.11s/it]
 63%|██████▎   | 17786/28080 [35:09:27<20:21:25,  7.12s/it]
                                                           
{'loss': 0.6032, 'learning_rate': 0.0001564677848802471, 'epoch': 7.6}

 63%|██████▎   | 17786/28080 [35:09:27<20:21:25,  7.12s/it]
 63%|██████▎   | 17787/28080 [35:09:34<20:20:20,  7.11s/it]
                                                           
{'loss': 0.6038, 'learning_rate': 0.00015644104393846897, 'epoch': 7.6}

 63%|██████▎   | 17787/28080 [35:09:34<20:20:20,  7.11s/it]
 63%|██████▎   | 17788/28080 [35:09:41<20:15:19,  7.09s/it]
                                                           
{'loss': 0.6043, 'learning_rate': 0.00015641430424139636, 'epoch': 7.6}

 63%|██████▎   | 17788/28080 [35:09:41<20:15:19,  7.09s/it]
 63%|██████▎   | 17789/28080 [35:09:48<20:21:23,  7.12s/it]
                                                           
{'loss': 0.6033, 'learning_rate': 0.0001563875657893848, 'epoch': 7.6}

 63%|██████▎   | 17789/28080 [35:09:48<20:21:23,  7.12s/it]
 63%|██████▎   | 17790/28080 [35:09:55<20:15:58,  7.09s/it]
                                                           
{'loss': 0.6175, 'learning_rate': 0.0001563608285827901, 'epoch': 7.6}

 63%|██████▎   | 17790/28080 [35:09:55<20:15:58,  7.09s/it]
 63%|██████▎   | 17791/28080 [35:10:03<20:20:03,  7.11s/it]
                                                           
{'loss': 0.6002, 'learning_rate': 0.00015633409262196795, 'epoch': 7.6}

 63%|██████▎   | 17791/28080 [35:10:03<20:20:03,  7.11s/it]
 63%|██████▎   | 17792/28080 [35:10:10<20:17:18,  7.10s/it]
                                                           
{'loss': 0.6037, 'learning_rate': 0.00015630735790727416, 'epoch': 7.6}

 63%|██████▎   | 17792/28080 [35:10:10<20:17:18,  7.10s/it]
 63%|██████▎   | 17793/28080 [35:10:17<20:16:56,  7.10s/it]
                                                           
{'loss': 0.607, 'learning_rate': 0.00015628062443906425, 'epoch': 7.6}

 63%|██████▎   | 17793/28080 [35:10:17<20:16:56,  7.10s/it]
 63%|██████▎   | 17794/28080 [35:10:24<20:10:28,  7.06s/it]
                                                           
{'loss': 0.6133, 'learning_rate': 0.00015625389221769398, 'epoch': 7.6}

 63%|██████▎   | 17794/28080 [35:10:24<20:10:28,  7.06s/it]
 63%|██████▎   | 17795/28080 [35:10:31<20:18:01,  7.11s/it]
                                                           
{'loss': 0.5954, 'learning_rate': 0.00015622716124351896, 'epoch': 7.6}

 63%|██████▎   | 17795/28080 [35:10:31<20:18:01,  7.11s/it]
 63%|██████▎   | 17796/28080 [35:10:38<20:24:30,  7.14s/it]
                                                           
{'loss': 0.6046, 'learning_rate': 0.00015620043151689478, 'epoch': 7.6}

 63%|██████▎   | 17796/28080 [35:10:38<20:24:30,  7.14s/it]
 63%|██████▎   | 17797/28080 [35:10:45<20:27:27,  7.16s/it]
                                                           
{'loss': 0.5997, 'learning_rate': 0.00015617370303817714, 'epoch': 7.6}

 63%|██████▎   | 17797/28080 [35:10:45<20:27:27,  7.16s/it]
 63%|██████▎   | 17798/28080 [35:10:52<20:16:43,  7.10s/it]
                                                           
{'loss': 0.6015, 'learning_rate': 0.00015614697580772154, 'epoch': 7.6}

 63%|██████▎   | 17798/28080 [35:10:52<20:16:43,  7.10s/it]
 63%|██████▎   | 17799/28080 [35:10:59<20:20:51,  7.12s/it]
                                                           
{'loss': 0.6021, 'learning_rate': 0.00015612024982588363, 'epoch': 7.6}

 63%|██████▎   | 17799/28080 [35:10:59<20:20:51,  7.12s/it]
 63%|██████▎   | 17800/28080 [35:11:07<20:19:09,  7.12s/it]
                                                           
{'loss': 0.6013, 'learning_rate': 0.0001560935250930189, 'epoch': 7.6}

 63%|██████▎   | 17800/28080 [35:11:07<20:19:09,  7.12s/it]
 63%|██████▎   | 17801/28080 [35:11:14<20:26:52,  7.16s/it]
                                                           
{'loss': 0.6032, 'learning_rate': 0.00015606680160948306, 'epoch': 7.6}

 63%|██████▎   | 17801/28080 [35:11:14<20:26:52,  7.16s/it]
 63%|██████▎   | 17802/28080 [35:11:21<20:22:06,  7.13s/it]
                                                           
{'loss': 0.6153, 'learning_rate': 0.00015604007937563134, 'epoch': 7.6}

 63%|██████▎   | 17802/28080 [35:11:21<20:22:06,  7.13s/it]
 63%|██████▎   | 17803/28080 [35:11:28<20:20:51,  7.13s/it]
                                                           
{'loss': 0.605, 'learning_rate': 0.00015601335839181957, 'epoch': 7.61}

 63%|██████▎   | 17803/28080 [35:11:28<20:20:51,  7.13s/it]
 63%|██████▎   | 17804/28080 [35:11:35<20:17:30,  7.11s/it]
                                                           
{'loss': 0.6345, 'learning_rate': 0.000155986638658403, 'epoch': 7.61}

 63%|██████▎   | 17804/28080 [35:11:35<20:17:30,  7.11s/it]
 63%|██████▎   | 17805/28080 [35:11:42<20:16:53,  7.11s/it]
                                                           
{'loss': 0.5968, 'learning_rate': 0.00015595992017573734, 'epoch': 7.61}

 63%|██████▎   | 17805/28080 [35:11:42<20:16:53,  7.11s/it]
 63%|██████▎   | 17806/28080 [35:11:49<20:18:54,  7.12s/it]
                                                           
{'loss': 0.6116, 'learning_rate': 0.00015593320294417785, 'epoch': 7.61}

 63%|██████▎   | 17806/28080 [35:11:49<20:18:54,  7.12s/it]
 63%|██████▎   | 17807/28080 [35:11:57<20:23:00,  7.14s/it]
                                                           
{'loss': 0.5937, 'learning_rate': 0.00015590648696408007, 'epoch': 7.61}

 63%|██████▎   | 17807/28080 [35:11:57<20:23:00,  7.14s/it]
 63%|██████▎   | 17808/28080 [35:12:04<20:26:23,  7.16s/it]
                                                           
{'loss': 0.6104, 'learning_rate': 0.00015587977223579938, 'epoch': 7.61}

 63%|██████▎   | 17808/28080 [35:12:04<20:26:23,  7.16s/it]
 63%|██████▎   | 17809/28080 [35:12:11<20:21:47,  7.14s/it]
                                                           
{'loss': 0.6097, 'learning_rate': 0.0001558530587596913, 'epoch': 7.61}

 63%|██████▎   | 17809/28080 [35:12:11<20:21:47,  7.14s/it]
 63%|██████▎   | 17810/28080 [35:12:18<20:14:27,  7.10s/it]
                                                           
{'loss': 0.6312, 'learning_rate': 0.00015582634653611105, 'epoch': 7.61}

 63%|██████▎   | 17810/28080 [35:12:18<20:14:27,  7.10s/it]
 63%|██████▎   | 17811/28080 [35:12:25<20:15:13,  7.10s/it]
                                                           
{'loss': 0.6132, 'learning_rate': 0.00015579963556541418, 'epoch': 7.61}

 63%|██████▎   | 17811/28080 [35:12:25<20:15:13,  7.10s/it]
 63%|██████▎   | 17812/28080 [35:12:32<20:17:08,  7.11s/it]
                                                           
{'loss': 0.6017, 'learning_rate': 0.00015577292584795593, 'epoch': 7.61}

 63%|██████▎   | 17812/28080 [35:12:32<20:17:08,  7.11s/it]
 63%|██████▎   | 17813/28080 [35:12:39<20:20:25,  7.13s/it]
                                                           
{'loss': 0.6282, 'learning_rate': 0.00015574621738409172, 'epoch': 7.61}

 63%|██████▎   | 17813/28080 [35:12:39<20:20:25,  7.13s/it]
 63%|██████▎   | 17814/28080 [35:12:46<20:19:39,  7.13s/it]
                                                           
{'loss': 0.6297, 'learning_rate': 0.0001557195101741768, 'epoch': 7.61}

 63%|██████▎   | 17814/28080 [35:12:46<20:19:39,  7.13s/it]
 63%|██████▎   | 17815/28080 [35:12:54<20:23:22,  7.15s/it]
                                                           
{'loss': 0.6335, 'learning_rate': 0.00015569280421856663, 'epoch': 7.61}

 63%|██████▎   | 17815/28080 [35:12:54<20:23:22,  7.15s/it]
 63%|██████▎   | 17816/28080 [35:13:01<20:16:59,  7.11s/it]
                                                           
{'loss': 0.5978, 'learning_rate': 0.00015566609951761629, 'epoch': 7.61}

 63%|██████▎   | 17816/28080 [35:13:01<20:16:59,  7.11s/it]
 63%|██████▎   | 17817/28080 [35:13:08<20:17:54,  7.12s/it]
                                                           
{'loss': 0.6084, 'learning_rate': 0.00015563939607168126, 'epoch': 7.61}

 63%|██████▎   | 17817/28080 [35:13:08<20:17:54,  7.12s/it]
 63%|██████▎   | 17818/28080 [35:13:15<20:20:36,  7.14s/it]
                                                           
{'loss': 0.618, 'learning_rate': 0.0001556126938811167, 'epoch': 7.61}

 63%|██████▎   | 17818/28080 [35:13:15<20:20:36,  7.14s/it]
 63%|██████▎   | 17819/28080 [35:13:22<20:22:53,  7.15s/it]
                                                           
{'loss': 0.6063, 'learning_rate': 0.0001555859929462779, 'epoch': 7.61}

 63%|██████▎   | 17819/28080 [35:13:22<20:22:53,  7.15s/it]
 63%|██████▎   | 17820/28080 [35:13:29<20:18:24,  7.13s/it]
                                                           
{'loss': 0.6059, 'learning_rate': 0.0001555592932675201, 'epoch': 7.61}

 63%|██████▎   | 17820/28080 [35:13:29<20:18:24,  7.13s/it]
 63%|██████▎   | 17821/28080 [35:13:36<20:19:27,  7.13s/it]
                                                           
{'loss': 0.6161, 'learning_rate': 0.00015553259484519833, 'epoch': 7.61}

 63%|██████▎   | 17821/28080 [35:13:36<20:19:27,  7.13s/it]
 63%|██████▎   | 17822/28080 [35:13:43<20:20:24,  7.14s/it]
                                                           
{'loss': 0.6069, 'learning_rate': 0.00015550589767966805, 'epoch': 7.61}

 63%|██████▎   | 17822/28080 [35:13:43<20:20:24,  7.14s/it]
 63%|██████▎   | 17823/28080 [35:13:51<20:21:02,  7.14s/it]
                                                           
{'loss': 0.6101, 'learning_rate': 0.00015547920177128428, 'epoch': 7.61}

 63%|██████▎   | 17823/28080 [35:13:51<20:21:02,  7.14s/it]
 63%|██████▎   | 17824/28080 [35:13:58<20:19:51,  7.14s/it]
                                                           
{'loss': 0.6159, 'learning_rate': 0.00015545250712040222, 'epoch': 7.61}

 63%|██████▎   | 17824/28080 [35:13:58<20:19:51,  7.14s/it]
 63%|██████▎   | 17825/28080 [35:14:05<20:16:47,  7.12s/it]
                                                           
{'loss': 0.6216, 'learning_rate': 0.00015542581372737698, 'epoch': 7.61}

 63%|██████▎   | 17825/28080 [35:14:05<20:16:47,  7.12s/it]
 63%|██████▎   | 17826/28080 [35:14:12<20:14:59,  7.11s/it]
                                                           
{'loss': 0.6368, 'learning_rate': 0.00015539912159256378, 'epoch': 7.62}

 63%|██████▎   | 17826/28080 [35:14:12<20:14:59,  7.11s/it]
 63%|██████▎   | 17827/28080 [35:14:19<20:15:03,  7.11s/it]
                                                           
{'loss': 0.6238, 'learning_rate': 0.00015537243071631762, 'epoch': 7.62}

 63%|██████▎   | 17827/28080 [35:14:19<20:15:03,  7.11s/it]
 63%|██████▎   | 17828/28080 [35:14:26<20:15:45,  7.12s/it]
                                                           
{'loss': 0.6202, 'learning_rate': 0.00015534574109899368, 'epoch': 7.62}

 63%|██████▎   | 17828/28080 [35:14:26<20:15:45,  7.12s/it]
 63%|██████▎   | 17829/28080 [35:14:33<20:23:12,  7.16s/it]
                                                           
{'loss': 0.5954, 'learning_rate': 0.00015531905274094698, 'epoch': 7.62}

 63%|██████▎   | 17829/28080 [35:14:33<20:23:12,  7.16s/it]
 63%|██████▎   | 17830/28080 [35:14:40<20:17:25,  7.13s/it]
                                                           
{'loss': 0.6178, 'learning_rate': 0.00015529236564253268, 'epoch': 7.62}

 63%|██████▎   | 17830/28080 [35:14:40<20:17:25,  7.13s/it]
 64%|██████▎   | 17831/28080 [35:14:48<20:22:15,  7.16s/it]
                                                           
{'loss': 0.6089, 'learning_rate': 0.0001552656798041056, 'epoch': 7.62}

 64%|██████▎   | 17831/28080 [35:14:48<20:22:15,  7.16s/it]
 64%|██████▎   | 17832/28080 [35:14:55<20:13:13,  7.10s/it]
                                                           
{'loss': 0.633, 'learning_rate': 0.0001552389952260211, 'epoch': 7.62}

 64%|██████▎   | 17832/28080 [35:14:55<20:13:13,  7.10s/it]
 64%|██████▎   | 17833/28080 [35:15:02<20:17:27,  7.13s/it]
                                                           
{'loss': 0.5784, 'learning_rate': 0.00015521231190863383, 'epoch': 7.62}

 64%|██████▎   | 17833/28080 [35:15:02<20:17:27,  7.13s/it]
 64%|██████▎   | 17834/28080 [35:15:09<20:19:42,  7.14s/it]
                                                           
{'loss': 0.6119, 'learning_rate': 0.00015518562985229913, 'epoch': 7.62}

 64%|██████▎   | 17834/28080 [35:15:09<20:19:42,  7.14s/it]
 64%|██████▎   | 17835/28080 [35:15:16<20:21:28,  7.15s/it]
                                                           
{'loss': 0.6197, 'learning_rate': 0.0001551589490573717, 'epoch': 7.62}

 64%|██████▎   | 17835/28080 [35:15:16<20:21:28,  7.15s/it]
 64%|██████▎   | 17836/28080 [35:15:23<20:24:53,  7.17s/it]
                                                           
{'loss': 0.5852, 'learning_rate': 0.00015513226952420668, 'epoch': 7.62}

 64%|██████▎   | 17836/28080 [35:15:23<20:24:53,  7.17s/it]
 64%|██████▎   | 17837/28080 [35:15:31<20:20:40,  7.15s/it]
                                                           
{'loss': 0.6158, 'learning_rate': 0.00015510559125315887, 'epoch': 7.62}

 64%|██████▎   | 17837/28080 [35:15:31<20:20:40,  7.15s/it]
 64%|██████▎   | 17838/28080 [35:15:38<20:20:49,  7.15s/it]
                                                           
{'loss': 0.6083, 'learning_rate': 0.0001550789142445833, 'epoch': 7.62}

 64%|██████▎   | 17838/28080 [35:15:38<20:20:49,  7.15s/it]
 64%|██████▎   | 17839/28080 [35:15:45<20:19:57,  7.15s/it]
                                                           
{'loss': 0.6194, 'learning_rate': 0.00015505223849883486, 'epoch': 7.62}

 64%|██████▎   | 17839/28080 [35:15:45<20:19:57,  7.15s/it]
 64%|██████▎   | 17840/28080 [35:15:52<20:22:18,  7.16s/it]
                                                           
{'loss': 0.5883, 'learning_rate': 0.0001550255640162685, 'epoch': 7.62}

 64%|██████▎   | 17840/28080 [35:15:52<20:22:18,  7.16s/it]
 64%|██████▎   | 17841/28080 [35:15:59<20:13:56,  7.11s/it]
                                                           
{'loss': 0.5933, 'learning_rate': 0.00015499889079723892, 'epoch': 7.62}

 64%|██████▎   | 17841/28080 [35:15:59<20:13:56,  7.11s/it]
 64%|██████▎   | 17842/28080 [35:16:06<20:07:37,  7.08s/it]
                                                           
{'loss': 0.6115, 'learning_rate': 0.00015497221884210117, 'epoch': 7.62}

 64%|██████▎   | 17842/28080 [35:16:06<20:07:37,  7.08s/it]
 64%|██████▎   | 17843/28080 [35:16:13<20:03:13,  7.05s/it]
                                                           
{'loss': 0.6118, 'learning_rate': 0.00015494554815120994, 'epoch': 7.62}

 64%|██████▎   | 17843/28080 [35:16:13<20:03:13,  7.05s/it]
 64%|██████▎   | 17844/28080 [35:16:20<20:06:03,  7.07s/it]
                                                           
{'loss': 0.6137, 'learning_rate': 0.00015491887872492023, 'epoch': 7.62}

 64%|██████▎   | 17844/28080 [35:16:20<20:06:03,  7.07s/it]
 64%|██████▎   | 17845/28080 [35:16:27<20:06:48,  7.07s/it]
                                                           
{'loss': 0.6031, 'learning_rate': 0.0001548922105635867, 'epoch': 7.62}

 64%|██████▎   | 17845/28080 [35:16:27<20:06:48,  7.07s/it]
 64%|██████▎   | 17846/28080 [35:16:34<20:10:47,  7.10s/it]
                                                           
{'loss': 0.5971, 'learning_rate': 0.00015486554366756416, 'epoch': 7.62}

 64%|██████▎   | 17846/28080 [35:16:34<20:10:47,  7.10s/it]
 64%|██████▎   | 17847/28080 [35:16:41<20:10:15,  7.10s/it]
                                                           
{'loss': 0.5985, 'learning_rate': 0.00015483887803720747, 'epoch': 7.62}

 64%|██████▎   | 17847/28080 [35:16:41<20:10:15,  7.10s/it]
 64%|██████▎   | 17848/28080 [35:16:48<20:09:11,  7.09s/it]
                                                           
{'loss': 0.6145, 'learning_rate': 0.00015481221367287125, 'epoch': 7.62}

 64%|██████▎   | 17848/28080 [35:16:48<20:09:11,  7.09s/it]
 64%|██████▎   | 17849/28080 [35:16:56<20:08:54,  7.09s/it]
                                                           
{'loss': 0.5883, 'learning_rate': 0.00015478555057491045, 'epoch': 7.62}

 64%|██████▎   | 17849/28080 [35:16:56<20:08:54,  7.09s/it]
 64%|██████▎   | 17850/28080 [35:17:03<20:04:46,  7.07s/it]
                                                           
{'loss': 0.6109, 'learning_rate': 0.00015475888874367952, 'epoch': 7.63}

 64%|██████▎   | 17850/28080 [35:17:03<20:04:46,  7.07s/it]
 64%|██████▎   | 17851/28080 [35:17:10<20:08:34,  7.09s/it]
                                                           
{'loss': 0.603, 'learning_rate': 0.00015473222817953346, 'epoch': 7.63}

 64%|██████▎   | 17851/28080 [35:17:10<20:08:34,  7.09s/it]
 64%|██████▎   | 17852/28080 [35:17:17<20:10:14,  7.10s/it]
                                                           
{'loss': 0.6083, 'learning_rate': 0.00015470556888282671, 'epoch': 7.63}

 64%|██████▎   | 17852/28080 [35:17:17<20:10:14,  7.10s/it]
 64%|██████▎   | 17853/28080 [35:17:24<20:11:19,  7.11s/it]
                                                           
{'loss': 0.6184, 'learning_rate': 0.00015467891085391413, 'epoch': 7.63}

 64%|██████▎   | 17853/28080 [35:17:24<20:11:19,  7.11s/it]
 64%|██████▎   | 17854/28080 [35:17:31<20:11:23,  7.11s/it]
                                                           
{'loss': 0.6035, 'learning_rate': 0.00015465225409315027, 'epoch': 7.63}

 64%|██████▎   | 17854/28080 [35:17:31<20:11:23,  7.11s/it]
 64%|██████▎   | 17855/28080 [35:17:38<20:07:57,  7.09s/it]
                                                           
{'loss': 0.6062, 'learning_rate': 0.00015462559860088986, 'epoch': 7.63}

 64%|██████▎   | 17855/28080 [35:17:38<20:07:57,  7.09s/it]
 64%|██████▎   | 17856/28080 [35:17:45<20:15:04,  7.13s/it]
                                                           
{'loss': 0.5802, 'learning_rate': 0.00015459894437748738, 'epoch': 7.63}

 64%|██████▎   | 17856/28080 [35:17:45<20:15:04,  7.13s/it]
 64%|██████▎   | 17857/28080 [35:17:52<20:09:45,  7.10s/it]
                                                           
{'loss': 0.6022, 'learning_rate': 0.0001545722914232976, 'epoch': 7.63}

 64%|██████▎   | 17857/28080 [35:17:52<20:09:45,  7.10s/it]
 64%|██████▎   | 17858/28080 [35:18:00<20:11:25,  7.11s/it]
                                                           
{'loss': 0.6234, 'learning_rate': 0.00015454563973867503, 'epoch': 7.63}

 64%|██████▎   | 17858/28080 [35:18:00<20:11:25,  7.11s/it]
 64%|██████▎   | 17859/28080 [35:18:07<20:10:08,  7.10s/it]
                                                           
{'loss': 0.6122, 'learning_rate': 0.00015451898932397422, 'epoch': 7.63}

 64%|██████▎   | 17859/28080 [35:18:07<20:10:08,  7.10s/it]
 64%|██████▎   | 17860/28080 [35:18:14<20:07:32,  7.09s/it]
                                                           
{'loss': 0.6083, 'learning_rate': 0.00015449234017954976, 'epoch': 7.63}

 64%|██████▎   | 17860/28080 [35:18:14<20:07:32,  7.09s/it]
 64%|██████▎   | 17861/28080 [35:18:21<20:08:04,  7.09s/it]
                                                           
{'loss': 0.6077, 'learning_rate': 0.00015446569230575619, 'epoch': 7.63}

 64%|██████▎   | 17861/28080 [35:18:21<20:08:04,  7.09s/it]
 64%|██████▎   | 17862/28080 [35:18:28<20:06:59,  7.09s/it]
                                                           
{'loss': 0.6135, 'learning_rate': 0.00015443904570294797, 'epoch': 7.63}

 64%|██████▎   | 17862/28080 [35:18:28<20:06:59,  7.09s/it]
 64%|██████▎   | 17863/28080 [35:18:35<20:02:30,  7.06s/it]
                                                           
{'loss': 0.5948, 'learning_rate': 0.0001544124003714798, 'epoch': 7.63}

 64%|██████▎   | 17863/28080 [35:18:35<20:02:30,  7.06s/it]
 64%|██████▎   | 17864/28080 [35:18:42<20:02:47,  7.06s/it]
                                                           
{'loss': 0.635, 'learning_rate': 0.00015438575631170588, 'epoch': 7.63}

 64%|██████▎   | 17864/28080 [35:18:42<20:02:47,  7.06s/it]
 64%|██████▎   | 17865/28080 [35:18:49<20:03:38,  7.07s/it]
                                                           
{'loss': 0.6345, 'learning_rate': 0.0001543591135239809, 'epoch': 7.63}

 64%|██████▎   | 17865/28080 [35:18:49<20:03:38,  7.07s/it]
 64%|██████▎   | 17866/28080 [35:18:56<20:05:18,  7.08s/it]
                                                           
{'loss': 0.6233, 'learning_rate': 0.00015433247200865923, 'epoch': 7.63}

 64%|██████▎   | 17866/28080 [35:18:56<20:05:18,  7.08s/it]
 64%|██████▎   | 17867/28080 [35:19:03<20:09:43,  7.11s/it]
                                                           
{'loss': 0.625, 'learning_rate': 0.00015430583176609535, 'epoch': 7.63}

 64%|██████▎   | 17867/28080 [35:19:03<20:09:43,  7.11s/it]
 64%|██████▎   | 17868/28080 [35:19:10<20:05:39,  7.08s/it]
                                                           
{'loss': 0.6077, 'learning_rate': 0.00015427919279664364, 'epoch': 7.63}

 64%|██████▎   | 17868/28080 [35:19:10<20:05:39,  7.08s/it]
 64%|██████▎   | 17869/28080 [35:19:17<20:03:44,  7.07s/it]
                                                           
{'loss': 0.6057, 'learning_rate': 0.00015425255510065854, 'epoch': 7.63}

 64%|██████▎   | 17869/28080 [35:19:17<20:03:44,  7.07s/it]
 64%|██████▎   | 17870/28080 [35:19:24<20:05:50,  7.09s/it]
                                                           
{'loss': 0.6277, 'learning_rate': 0.00015422591867849444, 'epoch': 7.63}

 64%|██████▎   | 17870/28080 [35:19:24<20:05:50,  7.09s/it]
 64%|██████▎   | 17871/28080 [35:19:32<20:07:04,  7.09s/it]
                                                           
{'loss': 0.6043, 'learning_rate': 0.00015419928353050565, 'epoch': 7.63}

 64%|██████▎   | 17871/28080 [35:19:32<20:07:04,  7.09s/it]
 64%|██████▎   | 17872/28080 [35:19:39<20:09:55,  7.11s/it]
                                                           
{'loss': 0.6175, 'learning_rate': 0.00015417264965704658, 'epoch': 7.63}

 64%|██████▎   | 17872/28080 [35:19:39<20:09:55,  7.11s/it]
 64%|██████▎   | 17873/28080 [35:19:46<20:08:07,  7.10s/it]
                                                           
{'loss': 0.5969, 'learning_rate': 0.0001541460170584715, 'epoch': 7.64}

 64%|██████▎   | 17873/28080 [35:19:46<20:08:07,  7.10s/it]
 64%|██████▎   | 17874/28080 [35:19:53<20:09:07,  7.11s/it]
                                                           
{'loss': 0.6129, 'learning_rate': 0.00015411938573513484, 'epoch': 7.64}

 64%|██████▎   | 17874/28080 [35:19:53<20:09:07,  7.11s/it]
 64%|██████▎   | 17875/28080 [35:20:00<20:12:49,  7.13s/it]
                                                           
{'loss': 0.5878, 'learning_rate': 0.0001540927556873908, 'epoch': 7.64}

 64%|██████▎   | 17875/28080 [35:20:00<20:12:49,  7.13s/it]
 64%|██████▎   | 17876/28080 [35:20:07<20:17:49,  7.16s/it]
                                                           
{'loss': 0.6028, 'learning_rate': 0.00015406612691559371, 'epoch': 7.64}

 64%|██████▎   | 17876/28080 [35:20:07<20:17:49,  7.16s/it]
 64%|██████▎   | 17877/28080 [35:20:14<20:13:14,  7.13s/it]
                                                           
{'loss': 0.6145, 'learning_rate': 0.00015403949942009783, 'epoch': 7.64}

 64%|██████▎   | 17877/28080 [35:20:14<20:13:14,  7.13s/it]
 64%|██████▎   | 17878/28080 [35:20:21<20:09:37,  7.11s/it]
                                                           
{'loss': 0.595, 'learning_rate': 0.00015401287320125742, 'epoch': 7.64}

 64%|██████▎   | 17878/28080 [35:20:22<20:09:37,  7.11s/it]
 64%|██████▎   | 17879/28080 [35:20:29<20:10:06,  7.12s/it]
                                                           
{'loss': 0.6325, 'learning_rate': 0.00015398624825942663, 'epoch': 7.64}

 64%|██████▎   | 17879/28080 [35:20:29<20:10:06,  7.12s/it]
 64%|██████▎   | 17880/28080 [35:20:36<20:10:46,  7.12s/it]
                                                           
{'loss': 0.6054, 'learning_rate': 0.0001539596245949599, 'epoch': 7.64}

 64%|██████▎   | 17880/28080 [35:20:36<20:10:46,  7.12s/it]
 64%|██████▎   | 17881/28080 [35:20:43<20:05:01,  7.09s/it]
                                                           
{'loss': 0.6177, 'learning_rate': 0.00015393300220821116, 'epoch': 7.64}

 64%|██████▎   | 17881/28080 [35:20:43<20:05:01,  7.09s/it]
 64%|██████▎   | 17882/28080 [35:20:50<20:04:01,  7.08s/it]
                                                           
{'loss': 0.6065, 'learning_rate': 0.00015390638109953484, 'epoch': 7.64}

 64%|██████▎   | 17882/28080 [35:20:50<20:04:01,  7.08s/it]
 64%|██████▎   | 17883/28080 [35:20:57<20:06:20,  7.10s/it]
                                                           
{'loss': 0.5991, 'learning_rate': 0.00015387976126928483, 'epoch': 7.64}

 64%|██████▎   | 17883/28080 [35:20:57<20:06:20,  7.10s/it]
 64%|██████▎   | 17884/28080 [35:21:04<20:07:05,  7.10s/it]
                                                           
{'loss': 0.6153, 'learning_rate': 0.00015385314271781553, 'epoch': 7.64}

 64%|██████▎   | 17884/28080 [35:21:04<20:07:05,  7.10s/it]
 64%|██████▎   | 17885/28080 [35:21:11<20:07:44,  7.11s/it]
                                                           
{'loss': 0.6113, 'learning_rate': 0.000153826525445481, 'epoch': 7.64}

 64%|██████▎   | 17885/28080 [35:21:11<20:07:44,  7.11s/it]
 64%|██████▎   | 17886/28080 [35:21:18<20:11:38,  7.13s/it]
                                                           
{'loss': 0.607, 'learning_rate': 0.00015379990945263528, 'epoch': 7.64}

 64%|██████▎   | 17886/28080 [35:21:18<20:11:38,  7.13s/it]
 64%|██████▎   | 17887/28080 [35:21:26<20:13:15,  7.14s/it]
                                                           
{'loss': 0.5872, 'learning_rate': 0.00015377329473963253, 'epoch': 7.64}

 64%|██████▎   | 17887/28080 [35:21:26<20:13:15,  7.14s/it]
 64%|██████▎   | 17888/28080 [35:21:32<20:02:44,  7.08s/it]
                                                           
{'loss': 0.5963, 'learning_rate': 0.00015374668130682683, 'epoch': 7.64}

 64%|██████▎   | 17888/28080 [35:21:32<20:02:44,  7.08s/it]
 64%|██████▎   | 17889/28080 [35:21:40<20:04:26,  7.09s/it]
                                                           
{'loss': 0.6056, 'learning_rate': 0.00015372006915457224, 'epoch': 7.64}

 64%|██████▎   | 17889/28080 [35:21:40<20:04:26,  7.09s/it]
 64%|██████▎   | 17890/28080 [35:21:47<20:04:16,  7.09s/it]
                                                           
{'loss': 0.5922, 'learning_rate': 0.00015369345828322283, 'epoch': 7.64}

 64%|██████▎   | 17890/28080 [35:21:47<20:04:16,  7.09s/it]
 64%|██████▎   | 17891/28080 [35:21:54<20:07:12,  7.11s/it]
                                                           
{'loss': 0.6108, 'learning_rate': 0.00015366684869313254, 'epoch': 7.64}

 64%|██████▎   | 17891/28080 [35:21:54<20:07:12,  7.11s/it]
 64%|██████▎   | 17892/28080 [35:22:01<20:06:06,  7.10s/it]
                                                           
{'loss': 0.6305, 'learning_rate': 0.0001536402403846555, 'epoch': 7.64}

 64%|██████▎   | 17892/28080 [35:22:01<20:06:06,  7.10s/it]
 64%|██████▎   | 17893/28080 [35:22:08<20:08:09,  7.12s/it]
                                                           
{'loss': 0.5916, 'learning_rate': 0.00015361363335814556, 'epoch': 7.64}

 64%|██████▎   | 17893/28080 [35:22:08<20:08:09,  7.12s/it]
 64%|██████▎   | 17894/28080 [35:22:15<20:06:17,  7.11s/it]
                                                           
{'loss': 0.6191, 'learning_rate': 0.00015358702761395697, 'epoch': 7.64}

 64%|██████▎   | 17894/28080 [35:22:15<20:06:17,  7.11s/it]
 64%|██████▎   | 17895/28080 [35:22:22<20:03:50,  7.09s/it]
                                                           
{'loss': 0.5933, 'learning_rate': 0.0001535604231524434, 'epoch': 7.64}

 64%|██████▎   | 17895/28080 [35:22:22<20:03:50,  7.09s/it]
 64%|██████▎   | 17896/28080 [35:22:29<20:08:42,  7.12s/it]
                                                           
{'loss': 0.6159, 'learning_rate': 0.00015353381997395887, 'epoch': 7.65}

 64%|██████▎   | 17896/28080 [35:22:29<20:08:42,  7.12s/it]
 64%|██████▎   | 17897/28080 [35:22:36<20:02:46,  7.09s/it]
                                                           
{'loss': 0.6094, 'learning_rate': 0.00015350721807885748, 'epoch': 7.65}

 64%|██████▎   | 17897/28080 [35:22:36<20:02:46,  7.09s/it]
 64%|██████▎   | 17898/28080 [35:22:43<20:00:12,  7.07s/it]
                                                           
{'loss': 0.6036, 'learning_rate': 0.00015348061746749283, 'epoch': 7.65}

 64%|██████▎   | 17898/28080 [35:22:43<20:00:12,  7.07s/it]
 64%|██████▎   | 17899/28080 [35:22:51<20:02:12,  7.08s/it]
                                                           
{'loss': 0.6087, 'learning_rate': 0.00015345401814021917, 'epoch': 7.65}

 64%|██████▎   | 17899/28080 [35:22:51<20:02:12,  7.08s/it]
 64%|██████▎   | 17900/28080 [35:22:58<20:02:17,  7.09s/it]
                                                           
{'loss': 0.6104, 'learning_rate': 0.00015342742009739001, 'epoch': 7.65}

 64%|██████▎   | 17900/28080 [35:22:58<20:02:17,  7.09s/it]
 64%|██████▍   | 17901/28080 [35:23:05<20:02:45,  7.09s/it]
                                                           
{'loss': 0.6033, 'learning_rate': 0.00015340082333935957, 'epoch': 7.65}

 64%|██████▍   | 17901/28080 [35:23:05<20:02:45,  7.09s/it]
 64%|██████▍   | 17902/28080 [35:23:12<20:08:26,  7.12s/it]
                                                           
{'loss': 0.5928, 'learning_rate': 0.00015337422786648142, 'epoch': 7.65}

 64%|██████▍   | 17902/28080 [35:23:12<20:08:26,  7.12s/it]
 64%|██████▍   | 17903/28080 [35:23:19<20:07:06,  7.12s/it]
                                                           
{'loss': 0.5934, 'learning_rate': 0.00015334763367910953, 'epoch': 7.65}

 64%|██████▍   | 17903/28080 [35:23:19<20:07:06,  7.12s/it]
 64%|██████▍   | 17904/28080 [35:23:26<20:08:24,  7.13s/it]
                                                           
{'loss': 0.626, 'learning_rate': 0.00015332104077759763, 'epoch': 7.65}

 64%|██████▍   | 17904/28080 [35:23:26<20:08:24,  7.13s/it]
 64%|██████▍   | 17905/28080 [35:23:33<20:05:37,  7.11s/it]
                                                           
{'loss': 0.6216, 'learning_rate': 0.00015329444916229956, 'epoch': 7.65}

 64%|██████▍   | 17905/28080 [35:23:33<20:05:37,  7.11s/it]
 64%|██████▍   | 17906/28080 [35:23:40<20:05:19,  7.11s/it]
                                                           
{'loss': 0.6067, 'learning_rate': 0.00015326785883356908, 'epoch': 7.65}

 64%|██████▍   | 17906/28080 [35:23:40<20:05:19,  7.11s/it]
 64%|██████▍   | 17907/28080 [35:23:48<20:06:01,  7.11s/it]
                                                           
{'loss': 0.5953, 'learning_rate': 0.00015324126979175996, 'epoch': 7.65}

 64%|██████▍   | 17907/28080 [35:23:48<20:06:01,  7.11s/it]
 64%|██████▍   | 17908/28080 [35:23:55<20:05:07,  7.11s/it]
                                                           
{'loss': 0.6284, 'learning_rate': 0.0001532146820372259, 'epoch': 7.65}

 64%|██████▍   | 17908/28080 [35:23:55<20:05:07,  7.11s/it]
 64%|██████▍   | 17909/28080 [35:24:02<19:57:35,  7.06s/it]
                                                           
{'loss': 0.6011, 'learning_rate': 0.00015318809557032068, 'epoch': 7.65}

 64%|██████▍   | 17909/28080 [35:24:02<19:57:35,  7.06s/it]
 64%|██████▍   | 17910/28080 [35:24:09<19:56:00,  7.06s/it]
                                                           
{'loss': 0.613, 'learning_rate': 0.00015316151039139787, 'epoch': 7.65}

 64%|██████▍   | 17910/28080 [35:24:09<19:56:00,  7.06s/it]
 64%|██████▍   | 17911/28080 [35:24:16<19:55:47,  7.06s/it]
                                                           
{'loss': 0.6139, 'learning_rate': 0.00015313492650081143, 'epoch': 7.65}

 64%|██████▍   | 17911/28080 [35:24:16<19:55:47,  7.06s/it]
 64%|██████▍   | 17912/28080 [35:24:23<20:04:48,  7.11s/it]
                                                           
{'loss': 0.6016, 'learning_rate': 0.00015310834389891471, 'epoch': 7.65}

 64%|██████▍   | 17912/28080 [35:24:23<20:04:48,  7.11s/it]
 64%|██████▍   | 17913/28080 [35:24:30<20:05:30,  7.11s/it]
                                                           
{'loss': 0.6305, 'learning_rate': 0.00015308176258606166, 'epoch': 7.65}

 64%|██████▍   | 17913/28080 [35:24:30<20:05:30,  7.11s/it]
 64%|██████▍   | 17914/28080 [35:24:37<20:01:26,  7.09s/it]
                                                           
{'loss': 0.6048, 'learning_rate': 0.00015305518256260558, 'epoch': 7.65}

 64%|██████▍   | 17914/28080 [35:24:37<20:01:26,  7.09s/it]
 64%|██████▍   | 17915/28080 [35:24:44<20:07:23,  7.13s/it]
                                                           
{'loss': 0.597, 'learning_rate': 0.00015302860382890044, 'epoch': 7.65}

 64%|██████▍   | 17915/28080 [35:24:44<20:07:23,  7.13s/it]
 64%|██████▍   | 17916/28080 [35:24:51<20:06:48,  7.12s/it]
                                                           
{'loss': 0.6082, 'learning_rate': 0.00015300202638529964, 'epoch': 7.65}

 64%|██████▍   | 17916/28080 [35:24:51<20:06:48,  7.12s/it]
 64%|██████▍   | 17917/28080 [35:24:58<20:02:13,  7.10s/it]
                                                           
{'loss': 0.6352, 'learning_rate': 0.00015297545023215683, 'epoch': 7.65}

 64%|██████▍   | 17917/28080 [35:24:58<20:02:13,  7.10s/it]
 64%|██████▍   | 17918/28080 [35:25:05<19:55:07,  7.06s/it]
                                                           
{'loss': 0.6228, 'learning_rate': 0.00015294887536982554, 'epoch': 7.65}

 64%|██████▍   | 17918/28080 [35:25:05<19:55:07,  7.06s/it]
 64%|██████▍   | 17919/28080 [35:25:13<19:59:46,  7.08s/it]
                                                           
{'loss': 0.6015, 'learning_rate': 0.00015292230179865936, 'epoch': 7.65}

 64%|██████▍   | 17919/28080 [35:25:13<19:59:46,  7.08s/it]
 64%|██████▍   | 17920/28080 [35:25:20<20:00:36,  7.09s/it]
                                                           
{'loss': 0.5933, 'learning_rate': 0.00015289572951901183, 'epoch': 7.66}

 64%|██████▍   | 17920/28080 [35:25:20<20:00:36,  7.09s/it]
 64%|██████▍   | 17921/28080 [35:25:27<20:05:49,  7.12s/it]
                                                           
{'loss': 0.6068, 'learning_rate': 0.0001528691585312364, 'epoch': 7.66}

 64%|██████▍   | 17921/28080 [35:25:27<20:05:49,  7.12s/it]
 64%|██████▍   | 17922/28080 [35:25:34<20:06:22,  7.13s/it]
                                                           
{'loss': 0.5976, 'learning_rate': 0.00015284258883568663, 'epoch': 7.66}

 64%|██████▍   | 17922/28080 [35:25:34<20:06:22,  7.13s/it]
 64%|██████▍   | 17923/28080 [35:25:41<20:08:15,  7.14s/it]
                                                           
{'loss': 0.6141, 'learning_rate': 0.0001528160204327159, 'epoch': 7.66}

 64%|██████▍   | 17923/28080 [35:25:41<20:08:15,  7.14s/it]
 64%|██████▍   | 17924/28080 [35:25:48<20:09:41,  7.15s/it]
                                                           
{'loss': 0.5952, 'learning_rate': 0.00015278945332267792, 'epoch': 7.66}

 64%|██████▍   | 17924/28080 [35:25:48<20:09:41,  7.15s/it]
 64%|██████▍   | 17925/28080 [35:25:55<20:09:31,  7.15s/it]
                                                           
{'loss': 0.6134, 'learning_rate': 0.00015276288750592582, 'epoch': 7.66}

 64%|██████▍   | 17925/28080 [35:25:55<20:09:31,  7.15s/it]
 64%|██████▍   | 17926/28080 [35:26:03<20:06:05,  7.13s/it]
                                                           
{'loss': 0.6098, 'learning_rate': 0.00015273632298281331, 'epoch': 7.66}

 64%|██████▍   | 17926/28080 [35:26:03<20:06:05,  7.13s/it]
 64%|██████▍   | 17927/28080 [35:26:10<20:05:00,  7.12s/it]
                                                           
{'loss': 0.5957, 'learning_rate': 0.00015270975975369356, 'epoch': 7.66}

 64%|██████▍   | 17927/28080 [35:26:10<20:05:00,  7.12s/it]
 64%|██████▍   | 17928/28080 [35:26:17<20:06:38,  7.13s/it]
                                                           
{'loss': 0.6214, 'learning_rate': 0.0001526831978189202, 'epoch': 7.66}

 64%|██████▍   | 17928/28080 [35:26:17<20:06:38,  7.13s/it]
 64%|██████▍   | 17929/28080 [35:26:24<20:09:56,  7.15s/it]
                                                           
{'loss': 0.5996, 'learning_rate': 0.00015265663717884637, 'epoch': 7.66}

 64%|██████▍   | 17929/28080 [35:26:24<20:09:56,  7.15s/it]
 64%|██████▍   | 17930/28080 [35:26:31<20:13:33,  7.17s/it]
                                                           
{'loss': 0.6253, 'learning_rate': 0.00015263007783382574, 'epoch': 7.66}

 64%|██████▍   | 17930/28080 [35:26:31<20:13:33,  7.17s/it]
 64%|██████▍   | 17931/28080 [35:26:38<20:06:08,  7.13s/it]
                                                           
{'loss': 0.6154, 'learning_rate': 0.00015260351978421127, 'epoch': 7.66}

 64%|██████▍   | 17931/28080 [35:26:38<20:06:08,  7.13s/it]
 64%|██████▍   | 17932/28080 [35:26:45<20:01:59,  7.11s/it]
                                                           
{'loss': 0.6215, 'learning_rate': 0.00015257696303035663, 'epoch': 7.66}

 64%|██████▍   | 17932/28080 [35:26:45<20:01:59,  7.11s/it]
 64%|██████▍   | 17933/28080 [35:26:52<20:04:02,  7.12s/it]
                                                           
{'loss': 0.624, 'learning_rate': 0.00015255040757261495, 'epoch': 7.66}

 64%|██████▍   | 17933/28080 [35:26:52<20:04:02,  7.12s/it]
 64%|██████▍   | 17934/28080 [35:27:00<20:02:44,  7.11s/it]
                                                           
{'loss': 0.6143, 'learning_rate': 0.0001525238534113396, 'epoch': 7.66}

 64%|██████▍   | 17934/28080 [35:27:00<20:02:44,  7.11s/it]
 64%|██████▍   | 17935/28080 [35:27:07<20:00:39,  7.10s/it]
                                                           
{'loss': 0.606, 'learning_rate': 0.00015249730054688377, 'epoch': 7.66}

 64%|██████▍   | 17935/28080 [35:27:07<20:00:39,  7.10s/it]
 64%|██████▍   | 17936/28080 [35:27:14<19:59:43,  7.10s/it]
                                                           
{'loss': 0.601, 'learning_rate': 0.0001524707489796008, 'epoch': 7.66}

 64%|██████▍   | 17936/28080 [35:27:14<19:59:43,  7.10s/it]
 64%|██████▍   | 17937/28080 [35:27:21<20:00:28,  7.10s/it]
                                                           
{'loss': 0.6247, 'learning_rate': 0.00015244419870984386, 'epoch': 7.66}

 64%|██████▍   | 17937/28080 [35:27:21<20:00:28,  7.10s/it]
 64%|██████▍   | 17938/28080 [35:27:28<20:00:55,  7.10s/it]
                                                           
{'loss': 0.6056, 'learning_rate': 0.00015241764973796627, 'epoch': 7.66}

 64%|██████▍   | 17938/28080 [35:27:28<20:00:55,  7.10s/it]
 64%|██████▍   | 17939/28080 [35:27:35<20:00:37,  7.10s/it]
                                                           
{'loss': 0.6223, 'learning_rate': 0.00015239110206432112, 'epoch': 7.66}

 64%|██████▍   | 17939/28080 [35:27:35<20:00:37,  7.10s/it]
 64%|██████▍   | 17940/28080 [35:27:42<20:05:08,  7.13s/it]
                                                           
{'loss': 0.6058, 'learning_rate': 0.00015236455568926172, 'epoch': 7.66}

 64%|██████▍   | 17940/28080 [35:27:42<20:05:08,  7.13s/it]
 64%|██████▍   | 17941/28080 [35:27:49<20:05:34,  7.13s/it]
                                                           
{'loss': 0.6068, 'learning_rate': 0.00015233801061314105, 'epoch': 7.66}

 64%|██████▍   | 17941/28080 [35:27:49<20:05:34,  7.13s/it]
 64%|██████▍   | 17942/28080 [35:27:57<20:07:03,  7.14s/it]
                                                           
{'loss': 0.6188, 'learning_rate': 0.00015231146683631258, 'epoch': 7.66}

 64%|██████▍   | 17942/28080 [35:27:57<20:07:03,  7.14s/it]
 64%|██████▍   | 17943/28080 [35:28:04<20:01:39,  7.11s/it]
                                                           
{'loss': 0.6139, 'learning_rate': 0.0001522849243591291, 'epoch': 7.67}

 64%|██████▍   | 17943/28080 [35:28:04<20:01:39,  7.11s/it]
 64%|██████▍   | 17944/28080 [35:28:11<19:58:08,  7.09s/it]
                                                           
{'loss': 0.628, 'learning_rate': 0.00015225838318194408, 'epoch': 7.67}

 64%|██████▍   | 17944/28080 [35:28:11<19:58:08,  7.09s/it]
 64%|██████▍   | 17945/28080 [35:28:18<19:57:32,  7.09s/it]
                                                           
{'loss': 0.604, 'learning_rate': 0.00015223184330511035, 'epoch': 7.67}

 64%|██████▍   | 17945/28080 [35:28:18<19:57:32,  7.09s/it]
 64%|██████▍   | 17946/28080 [35:28:25<19:58:35,  7.10s/it]
                                                           
{'loss': 0.62, 'learning_rate': 0.00015220530472898096, 'epoch': 7.67}

 64%|██████▍   | 17946/28080 [35:28:25<19:58:35,  7.10s/it]
 64%|██████▍   | 17947/28080 [35:28:32<20:01:47,  7.12s/it]
                                                           
{'loss': 0.5918, 'learning_rate': 0.00015217876745390933, 'epoch': 7.67}

 64%|██████▍   | 17947/28080 [35:28:32<20:01:47,  7.12s/it]
 64%|██████▍   | 17948/28080 [35:28:39<20:03:23,  7.13s/it]
                                                           
{'loss': 0.6319, 'learning_rate': 0.0001521522314802481, 'epoch': 7.67}

 64%|██████▍   | 17948/28080 [35:28:39<20:03:23,  7.13s/it]
 64%|██████▍   | 17949/28080 [35:28:46<20:02:27,  7.12s/it]
                                                           
{'loss': 0.5991, 'learning_rate': 0.00015212569680835055, 'epoch': 7.67}

 64%|██████▍   | 17949/28080 [35:28:46<20:02:27,  7.12s/it]
 64%|██████▍   | 17950/28080 [35:28:53<20:00:34,  7.11s/it]
                                                           
{'loss': 0.6209, 'learning_rate': 0.0001520991634385696, 'epoch': 7.67}

 64%|██████▍   | 17950/28080 [35:28:53<20:00:34,  7.11s/it]
 64%|██████▍   | 17951/28080 [35:29:00<20:01:19,  7.12s/it]
                                                           
{'loss': 0.6041, 'learning_rate': 0.00015207263137125834, 'epoch': 7.67}

 64%|██████▍   | 17951/28080 [35:29:00<20:01:19,  7.12s/it]
 64%|██████▍   | 17952/28080 [35:29:08<20:05:20,  7.14s/it]
                                                           
{'loss': 0.6317, 'learning_rate': 0.00015204610060676966, 'epoch': 7.67}

 64%|██████▍   | 17952/28080 [35:29:08<20:05:20,  7.14s/it]
 64%|██████▍   | 17953/28080 [35:29:15<20:04:47,  7.14s/it]
                                                           
{'loss': 0.5952, 'learning_rate': 0.00015201957114545657, 'epoch': 7.67}

 64%|██████▍   | 17953/28080 [35:29:15<20:04:47,  7.14s/it]
 64%|██████▍   | 17954/28080 [35:29:22<20:01:27,  7.12s/it]
                                                           
{'loss': 0.6341, 'learning_rate': 0.00015199304298767197, 'epoch': 7.67}

 64%|██████▍   | 17954/28080 [35:29:22<20:01:27,  7.12s/it]
 64%|██████▍   | 17955/28080 [35:29:29<19:58:28,  7.10s/it]
                                                           
{'loss': 0.5971, 'learning_rate': 0.00015196651613376888, 'epoch': 7.67}

 64%|██████▍   | 17955/28080 [35:29:29<19:58:28,  7.10s/it]
 64%|██████▍   | 17956/28080 [35:29:36<20:00:06,  7.11s/it]
                                                           
{'loss': 0.6358, 'learning_rate': 0.00015193999058410012, 'epoch': 7.67}

 64%|██████▍   | 17956/28080 [35:29:36<20:00:06,  7.11s/it]
 64%|██████▍   | 17957/28080 [35:29:43<19:59:54,  7.11s/it]
                                                           
{'loss': 0.6017, 'learning_rate': 0.00015191346633901864, 'epoch': 7.67}

 64%|██████▍   | 17957/28080 [35:29:43<19:59:54,  7.11s/it]
 64%|██████▍   | 17958/28080 [35:29:50<20:03:27,  7.13s/it]
                                                           
{'loss': 0.6161, 'learning_rate': 0.00015188694339887722, 'epoch': 7.67}

 64%|██████▍   | 17958/28080 [35:29:50<20:03:27,  7.13s/it]
 64%|██████▍   | 17959/28080 [35:29:57<19:58:08,  7.10s/it]
                                                           
{'loss': 0.6355, 'learning_rate': 0.00015186042176402895, 'epoch': 7.67}

 64%|██████▍   | 17959/28080 [35:29:57<19:58:08,  7.10s/it]
 64%|██████▍   | 17960/28080 [35:30:04<19:54:57,  7.08s/it]
                                                           
{'loss': 0.6111, 'learning_rate': 0.0001518339014348264, 'epoch': 7.67}

 64%|██████▍   | 17960/28080 [35:30:04<19:54:57,  7.08s/it]
 64%|██████▍   | 17961/28080 [35:30:12<19:55:37,  7.09s/it]
                                                           
{'loss': 0.602, 'learning_rate': 0.0001518073824116226, 'epoch': 7.67}

 64%|██████▍   | 17961/28080 [35:30:12<19:55:37,  7.09s/it]
 64%|██████▍   | 17962/28080 [35:30:19<19:59:39,  7.11s/it]
                                                           
{'loss': 0.6171, 'learning_rate': 0.0001517808646947702, 'epoch': 7.67}

 64%|██████▍   | 17962/28080 [35:30:19<19:59:39,  7.11s/it]
 64%|██████▍   | 17963/28080 [35:30:26<20:00:20,  7.12s/it]
                                                           
{'loss': 0.6021, 'learning_rate': 0.00015175434828462213, 'epoch': 7.67}

 64%|██████▍   | 17963/28080 [35:30:26<20:00:20,  7.12s/it]
 64%|██████▍   | 17964/28080 [35:30:33<20:01:28,  7.13s/it]
                                                           
{'loss': 0.5916, 'learning_rate': 0.00015172783318153106, 'epoch': 7.67}

 64%|██████▍   | 17964/28080 [35:30:33<20:01:28,  7.13s/it]
 64%|██████▍   | 17965/28080 [35:30:40<20:01:03,  7.12s/it]
                                                           
{'loss': 0.5874, 'learning_rate': 0.00015170131938584982, 'epoch': 7.67}

 64%|██████▍   | 17965/28080 [35:30:40<20:01:03,  7.12s/it]
 64%|██████▍   | 17966/28080 [35:30:47<20:02:08,  7.13s/it]
                                                           
{'loss': 0.5973, 'learning_rate': 0.0001516748068979311, 'epoch': 7.67}

 64%|██████▍   | 17966/28080 [35:30:47<20:02:08,  7.13s/it]
 64%|██████▍   | 17967/28080 [35:30:54<20:03:21,  7.14s/it]
                                                           
{'loss': 0.6066, 'learning_rate': 0.00015164829571812766, 'epoch': 7.68}

 64%|██████▍   | 17967/28080 [35:30:54<20:03:21,  7.14s/it]
 64%|██████▍   | 17968/28080 [35:31:02<20:01:43,  7.13s/it]
                                                           
{'loss': 0.6122, 'learning_rate': 0.00015162178584679216, 'epoch': 7.68}

 64%|██████▍   | 17968/28080 [35:31:02<20:01:43,  7.13s/it]
 64%|██████▍   | 17969/28080 [35:31:09<20:03:19,  7.14s/it]
                                                           
{'loss': 0.6124, 'learning_rate': 0.00015159527728427733, 'epoch': 7.68}

 64%|██████▍   | 17969/28080 [35:31:09<20:03:19,  7.14s/it]
 64%|██████▍   | 17970/28080 [35:31:16<20:07:48,  7.17s/it]
                                                           
{'loss': 0.6042, 'learning_rate': 0.00015156877003093583, 'epoch': 7.68}

 64%|██████▍   | 17970/28080 [35:31:16<20:07:48,  7.17s/it]
 64%|██████▍   | 17971/28080 [35:31:23<20:04:44,  7.15s/it]
                                                           
{'loss': 0.5903, 'learning_rate': 0.00015154226408712023, 'epoch': 7.68}

 64%|██████▍   | 17971/28080 [35:31:23<20:04:44,  7.15s/it]
 64%|██████▍   | 17972/28080 [35:31:30<20:02:04,  7.14s/it]
                                                           
{'loss': 0.6232, 'learning_rate': 0.0001515157594531833, 'epoch': 7.68}

 64%|██████▍   | 17972/28080 [35:31:30<20:02:04,  7.14s/it]
 64%|██████▍   | 17973/28080 [35:31:37<20:06:44,  7.16s/it]
                                                           
{'loss': 0.6029, 'learning_rate': 0.00015148925612947756, 'epoch': 7.68}

 64%|██████▍   | 17973/28080 [35:31:37<20:06:44,  7.16s/it]
 64%|██████▍   | 17974/28080 [35:31:44<20:05:53,  7.16s/it]
                                                           
{'loss': 0.6028, 'learning_rate': 0.00015146275411635565, 'epoch': 7.68}

 64%|██████▍   | 17974/28080 [35:31:44<20:05:53,  7.16s/it]
 64%|██████▍   | 17975/28080 [35:31:51<19:56:25,  7.10s/it]
                                                           
{'loss': 0.6218, 'learning_rate': 0.00015143625341417012, 'epoch': 7.68}

 64%|██████▍   | 17975/28080 [35:31:51<19:56:25,  7.10s/it]
 64%|██████▍   | 17976/28080 [35:31:59<19:57:18,  7.11s/it]
                                                           
{'loss': 0.6347, 'learning_rate': 0.00015140975402327362, 'epoch': 7.68}

 64%|██████▍   | 17976/28080 [35:31:59<19:57:18,  7.11s/it]
 64%|██████▍   | 17977/28080 [35:32:06<19:54:40,  7.09s/it]
                                                           
{'loss': 0.6094, 'learning_rate': 0.00015138325594401847, 'epoch': 7.68}

 64%|██████▍   | 17977/28080 [35:32:06<19:54:40,  7.09s/it]
 64%|██████▍   | 17978/28080 [35:32:13<19:55:40,  7.10s/it]
                                                           
{'loss': 0.604, 'learning_rate': 0.00015135675917675757, 'epoch': 7.68}

 64%|██████▍   | 17978/28080 [35:32:13<19:55:40,  7.10s/it]
 64%|██████▍   | 17979/28080 [35:32:20<19:56:59,  7.11s/it]
                                                           
{'loss': 0.6155, 'learning_rate': 0.00015133026372184306, 'epoch': 7.68}

 64%|██████▍   | 17979/28080 [35:32:20<19:56:59,  7.11s/it]
 64%|██████▍   | 17980/28080 [35:32:27<19:57:40,  7.11s/it]
                                                           
{'loss': 0.6069, 'learning_rate': 0.00015130376957962768, 'epoch': 7.68}

 64%|██████▍   | 17980/28080 [35:32:27<19:57:40,  7.11s/it]
 64%|██████▍   | 17981/28080 [35:32:34<19:54:32,  7.10s/it]
                                                           
{'loss': 0.6029, 'learning_rate': 0.00015127727675046378, 'epoch': 7.68}

 64%|██████▍   | 17981/28080 [35:32:34<19:54:32,  7.10s/it]
 64%|██████▍   | 17982/28080 [35:32:41<19:52:28,  7.09s/it]
                                                           
{'loss': 0.6198, 'learning_rate': 0.00015125078523470394, 'epoch': 7.68}

 64%|██████▍   | 17982/28080 [35:32:41<19:52:28,  7.09s/it]
 64%|██████▍   | 17983/28080 [35:32:48<19:59:09,  7.13s/it]
                                                           
{'loss': 0.6241, 'learning_rate': 0.00015122429503270046, 'epoch': 7.68}

 64%|██████▍   | 17983/28080 [35:32:48<19:59:09,  7.13s/it]
 64%|██████▍   | 17984/28080 [35:32:56<20:03:03,  7.15s/it]
                                                           
{'loss': 0.6145, 'learning_rate': 0.00015119780614480588, 'epoch': 7.68}

 64%|██████▍   | 17984/28080 [35:32:56<20:03:03,  7.15s/it]
 64%|██████▍   | 17985/28080 [35:33:03<20:05:00,  7.16s/it]
                                                           
{'loss': 0.6134, 'learning_rate': 0.00015117131857137254, 'epoch': 7.68}

 64%|██████▍   | 17985/28080 [35:33:03<20:05:00,  7.16s/it]
 64%|██████▍   | 17986/28080 [35:33:10<19:58:17,  7.12s/it]
                                                           
{'loss': 0.6265, 'learning_rate': 0.0001511448323127529, 'epoch': 7.68}

 64%|██████▍   | 17986/28080 [35:33:10<19:58:17,  7.12s/it]
 64%|██████▍   | 17987/28080 [35:33:17<19:56:11,  7.11s/it]
                                                           
{'loss': 0.6177, 'learning_rate': 0.0001511183473692992, 'epoch': 7.68}

 64%|██████▍   | 17987/28080 [35:33:17<19:56:11,  7.11s/it]
 64%|██████▍   | 17988/28080 [35:33:24<19:55:48,  7.11s/it]
                                                           
{'loss': 0.6125, 'learning_rate': 0.00015109186374136395, 'epoch': 7.68}

 64%|██████▍   | 17988/28080 [35:33:24<19:55:48,  7.11s/it]
 64%|██████▍   | 17989/28080 [35:33:31<19:56:11,  7.11s/it]
                                                           
{'loss': 0.6203, 'learning_rate': 0.00015106538142929928, 'epoch': 7.68}

 64%|██████▍   | 17989/28080 [35:33:31<19:56:11,  7.11s/it]
 64%|██████▍   | 17990/28080 [35:33:38<19:59:04,  7.13s/it]
                                                           
{'loss': 0.6098, 'learning_rate': 0.00015103890043345784, 'epoch': 7.69}

 64%|██████▍   | 17990/28080 [35:33:38<19:59:04,  7.13s/it]
 64%|██████▍   | 17991/28080 [35:33:45<19:59:28,  7.13s/it]
                                                           
{'loss': 0.6016, 'learning_rate': 0.0001510124207541916, 'epoch': 7.69}

 64%|██████▍   | 17991/28080 [35:33:45<19:59:28,  7.13s/it]
 64%|██████▍   | 17992/28080 [35:33:53<19:58:32,  7.13s/it]
                                                           
{'loss': 0.6049, 'learning_rate': 0.00015098594239185308, 'epoch': 7.69}

 64%|██████▍   | 17992/28080 [35:33:53<19:58:32,  7.13s/it]
 64%|██████▍   | 17993/28080 [35:34:00<19:57:59,  7.13s/it]
                                                           
{'loss': 0.5986, 'learning_rate': 0.00015095946534679432, 'epoch': 7.69}

 64%|██████▍   | 17993/28080 [35:34:00<19:57:59,  7.13s/it]
 64%|██████▍   | 17994/28080 [35:34:07<19:50:04,  7.08s/it]
                                                           
{'loss': 0.6294, 'learning_rate': 0.0001509329896193678, 'epoch': 7.69}

 64%|██████▍   | 17994/28080 [35:34:07<19:50:04,  7.08s/it]
 64%|██████▍   | 17995/28080 [35:34:14<19:56:47,  7.12s/it]
                                                           
{'loss': 0.5976, 'learning_rate': 0.0001509065152099257, 'epoch': 7.69}

 64%|██████▍   | 17995/28080 [35:34:14<19:56:47,  7.12s/it]
 64%|██████▍   | 17996/28080 [35:34:21<19:58:53,  7.13s/it]
                                                           
{'loss': 0.6063, 'learning_rate': 0.00015088004211882, 'epoch': 7.69}

 64%|██████▍   | 17996/28080 [35:34:21<19:58:53,  7.13s/it]
 64%|██████▍   | 17997/28080 [35:34:28<19:57:46,  7.13s/it]
                                                           
{'loss': 0.6103, 'learning_rate': 0.00015085357034640324, 'epoch': 7.69}

 64%|██████▍   | 17997/28080 [35:34:28<19:57:46,  7.13s/it]
 64%|██████▍   | 17998/28080 [35:34:35<19:57:34,  7.13s/it]
                                                           
{'loss': 0.5995, 'learning_rate': 0.00015082709989302736, 'epoch': 7.69}

 64%|██████▍   | 17998/28080 [35:34:35<19:57:34,  7.13s/it]
 64%|██████▍   | 17999/28080 [35:34:42<19:51:43,  7.09s/it]
                                                           
{'loss': 0.6253, 'learning_rate': 0.0001508006307590447, 'epoch': 7.69}

 64%|██████▍   | 17999/28080 [35:34:42<19:51:43,  7.09s/it]
 64%|██████▍   | 18000/28080 [35:34:49<19:56:43,  7.12s/it]
                                                           
{'loss': 0.6092, 'learning_rate': 0.00015077416294480723, 'epoch': 7.69}

 64%|██████▍   | 18000/28080 [35:34:49<19:56:43,  7.12s/it]
 64%|██████▍   | 18001/28080 [35:34:56<19:52:50,  7.10s/it]
                                                           
{'loss': 0.6171, 'learning_rate': 0.0001507476964506672, 'epoch': 7.69}

 64%|██████▍   | 18001/28080 [35:34:56<19:52:50,  7.10s/it]
 64%|██████▍   | 18002/28080 [35:35:04<19:53:49,  7.11s/it]
                                                           
{'loss': 0.6062, 'learning_rate': 0.0001507212312769766, 'epoch': 7.69}

 64%|██████▍   | 18002/28080 [35:35:04<19:53:49,  7.11s/it]
 64%|██████▍   | 18003/28080 [35:35:11<19:58:00,  7.13s/it]
                                                           
{'loss': 0.5882, 'learning_rate': 0.0001506947674240877, 'epoch': 7.69}

 64%|██████▍   | 18003/28080 [35:35:11<19:58:00,  7.13s/it]
 64%|██████▍   | 18004/28080 [35:35:18<19:58:11,  7.13s/it]
                                                           
{'loss': 0.5925, 'learning_rate': 0.0001506683048923524, 'epoch': 7.69}

 64%|██████▍   | 18004/28080 [35:35:18<19:58:11,  7.13s/it]
 64%|██████▍   | 18005/28080 [35:35:25<19:54:10,  7.11s/it]
                                                           
{'loss': 0.6276, 'learning_rate': 0.00015064184368212286, 'epoch': 7.69}

 64%|██████▍   | 18005/28080 [35:35:25<19:54:10,  7.11s/it]
 64%|██████▍   | 18006/28080 [35:35:32<19:55:27,  7.12s/it]
                                                           
{'loss': 0.6047, 'learning_rate': 0.00015061538379375106, 'epoch': 7.69}

 64%|██████▍   | 18006/28080 [35:35:32<19:55:27,  7.12s/it]
 64%|██████▍   | 18007/28080 [35:35:39<19:49:21,  7.08s/it]
                                                           
{'loss': 0.6093, 'learning_rate': 0.0001505889252275891, 'epoch': 7.69}

 64%|██████▍   | 18007/28080 [35:35:39<19:49:21,  7.08s/it]
 64%|██████▍   | 18008/28080 [35:35:46<19:51:00,  7.09s/it]
                                                           
{'loss': 0.6053, 'learning_rate': 0.00015056246798398883, 'epoch': 7.69}

 64%|██████▍   | 18008/28080 [35:35:46<19:51:00,  7.09s/it]
 64%|██████▍   | 18009/28080 [35:35:53<19:55:02,  7.12s/it]
                                                           
{'loss': 0.6056, 'learning_rate': 0.00015053601206330247, 'epoch': 7.69}

 64%|██████▍   | 18009/28080 [35:35:53<19:55:02,  7.12s/it]
 64%|██████▍   | 18010/28080 [35:36:01<19:54:33,  7.12s/it]
                                                           
{'loss': 0.6021, 'learning_rate': 0.00015050955746588173, 'epoch': 7.69}

 64%|██████▍   | 18010/28080 [35:36:01<19:54:33,  7.12s/it]
 64%|██████▍   | 18011/28080 [35:36:08<19:53:25,  7.11s/it]
                                                           
{'loss': 0.5891, 'learning_rate': 0.00015048310419207877, 'epoch': 7.69}

 64%|██████▍   | 18011/28080 [35:36:08<19:53:25,  7.11s/it]
 64%|██████▍   | 18012/28080 [35:36:15<19:54:46,  7.12s/it]
                                                           
{'loss': 0.5887, 'learning_rate': 0.0001504566522422454, 'epoch': 7.69}

 64%|██████▍   | 18012/28080 [35:36:15<19:54:46,  7.12s/it]
 64%|██████▍   | 18013/28080 [35:36:22<19:56:24,  7.13s/it]
                                                           
{'loss': 0.612, 'learning_rate': 0.00015043020161673365, 'epoch': 7.69}

 64%|██████▍   | 18013/28080 [35:36:22<19:56:24,  7.13s/it]
 64%|██████▍   | 18014/28080 [35:36:29<19:51:59,  7.11s/it]
                                                           
{'loss': 0.6053, 'learning_rate': 0.0001504037523158953, 'epoch': 7.7}

 64%|██████▍   | 18014/28080 [35:36:29<19:51:59,  7.11s/it]
 64%|██████▍   | 18015/28080 [35:36:36<19:49:17,  7.09s/it]
                                                           
{'loss': 0.5996, 'learning_rate': 0.00015037730434008228, 'epoch': 7.7}

 64%|██████▍   | 18015/28080 [35:36:36<19:49:17,  7.09s/it]
 64%|██████▍   | 18016/28080 [35:36:43<19:52:18,  7.11s/it]
                                                           
{'loss': 0.6035, 'learning_rate': 0.00015035085768964646, 'epoch': 7.7}

 64%|██████▍   | 18016/28080 [35:36:43<19:52:18,  7.11s/it]
 64%|██████▍   | 18017/28080 [35:36:50<19:51:46,  7.11s/it]
                                                           
{'loss': 0.62, 'learning_rate': 0.0001503244123649397, 'epoch': 7.7}

 64%|██████▍   | 18017/28080 [35:36:50<19:51:46,  7.11s/it]
 64%|██████▍   | 18018/28080 [35:36:57<19:50:19,  7.10s/it]
                                                           
{'loss': 0.6067, 'learning_rate': 0.00015029796836631376, 'epoch': 7.7}

 64%|██████▍   | 18018/28080 [35:36:57<19:50:19,  7.10s/it]
 64%|██████▍   | 18019/28080 [35:37:05<19:54:34,  7.12s/it]
                                                           
{'loss': 0.5937, 'learning_rate': 0.00015027152569412053, 'epoch': 7.7}

 64%|██████▍   | 18019/28080 [35:37:05<19:54:34,  7.12s/it]
 64%|██████▍   | 18020/28080 [35:37:12<19:56:21,  7.14s/it]
                                                           
{'loss': 0.5932, 'learning_rate': 0.00015024508434871177, 'epoch': 7.7}

 64%|██████▍   | 18020/28080 [35:37:12<19:56:21,  7.14s/it]
 64%|██████▍   | 18021/28080 [35:37:19<20:00:07,  7.16s/it]
                                                           
{'loss': 0.6077, 'learning_rate': 0.0001502186443304392, 'epoch': 7.7}

 64%|██████▍   | 18021/28080 [35:37:19<20:00:07,  7.16s/it]
 64%|██████▍   | 18022/28080 [35:37:26<19:52:22,  7.11s/it]
                                                           
{'loss': 0.6023, 'learning_rate': 0.0001501922056396547, 'epoch': 7.7}

 64%|██████▍   | 18022/28080 [35:37:26<19:52:22,  7.11s/it]
 64%|██████▍   | 18023/28080 [35:37:33<19:56:06,  7.14s/it]
                                                           
{'loss': 0.6192, 'learning_rate': 0.00015016576827670987, 'epoch': 7.7}

 64%|██████▍   | 18023/28080 [35:37:33<19:56:06,  7.14s/it]
 64%|██████▍   | 18024/28080 [35:37:40<19:51:15,  7.11s/it]
                                                           
{'loss': 0.6023, 'learning_rate': 0.00015013933224195653, 'epoch': 7.7}

 64%|██████▍   | 18024/28080 [35:37:40<19:51:15,  7.11s/it]
 64%|██████▍   | 18025/28080 [35:37:47<19:51:25,  7.11s/it]
                                                           
{'loss': 0.6077, 'learning_rate': 0.0001501128975357463, 'epoch': 7.7}

 64%|██████▍   | 18025/28080 [35:37:47<19:51:25,  7.11s/it]
 64%|██████▍   | 18026/28080 [35:37:54<19:50:54,  7.11s/it]
                                                           
{'loss': 0.6184, 'learning_rate': 0.00015008646415843102, 'epoch': 7.7}

 64%|██████▍   | 18026/28080 [35:37:54<19:50:54,  7.11s/it]
 64%|██████▍   | 18027/28080 [35:38:02<19:51:59,  7.11s/it]
                                                           
{'loss': 0.5975, 'learning_rate': 0.00015006003211036212, 'epoch': 7.7}

 64%|██████▍   | 18027/28080 [35:38:02<19:51:59,  7.11s/it]
 64%|██████▍   | 18028/28080 [35:38:09<19:55:00,  7.13s/it]
                                                           
{'loss': 0.6208, 'learning_rate': 0.00015003360139189155, 'epoch': 7.7}

 64%|██████▍   | 18028/28080 [35:38:09<19:55:00,  7.13s/it]
 64%|██████▍   | 18029/28080 [35:38:16<20:02:02,  7.18s/it]
                                                           
{'loss': 0.6503, 'learning_rate': 0.00015000717200337066, 'epoch': 7.7}

 64%|██████▍   | 18029/28080 [35:38:16<20:02:02,  7.18s/it]
 64%|██████▍   | 18030/28080 [35:38:23<19:57:42,  7.15s/it]
                                                           
{'loss': 0.5945, 'learning_rate': 0.00014998074394515128, 'epoch': 7.7}

 64%|██████▍   | 18030/28080 [35:38:23<19:57:42,  7.15s/it]
 64%|██████▍   | 18031/28080 [35:38:30<19:58:01,  7.15s/it]
                                                           
{'loss': 0.6288, 'learning_rate': 0.00014995431721758485, 'epoch': 7.7}

 64%|██████▍   | 18031/28080 [35:38:30<19:58:01,  7.15s/it]
 64%|██████▍   | 18032/28080 [35:38:37<19:56:28,  7.14s/it]
                                                           
{'loss': 0.6066, 'learning_rate': 0.00014992789182102307, 'epoch': 7.7}

 64%|██████▍   | 18032/28080 [35:38:37<19:56:28,  7.14s/it]
 64%|██████▍   | 18033/28080 [35:38:45<19:58:11,  7.16s/it]
                                                           
{'loss': 0.626, 'learning_rate': 0.0001499014677558174, 'epoch': 7.7}

 64%|██████▍   | 18033/28080 [35:38:45<19:58:11,  7.16s/it]
 64%|██████▍   | 18034/28080 [35:38:52<19:56:30,  7.15s/it]
                                                           
{'loss': 0.6209, 'learning_rate': 0.00014987504502231947, 'epoch': 7.7}

 64%|██████▍   | 18034/28080 [35:38:52<19:56:30,  7.15s/it]
 64%|██████▍   | 18035/28080 [35:38:59<20:01:06,  7.17s/it]
                                                           
{'loss': 0.6066, 'learning_rate': 0.00014984862362088074, 'epoch': 7.7}

 64%|██████▍   | 18035/28080 [35:38:59<20:01:06,  7.17s/it]
 64%|██████▍   | 18036/28080 [35:39:06<19:59:03,  7.16s/it]
                                                           
{'loss': 0.6094, 'learning_rate': 0.00014982220355185284, 'epoch': 7.7}

 64%|██████▍   | 18036/28080 [35:39:06<19:59:03,  7.16s/it]
 64%|██████▍   | 18037/28080 [35:39:13<19:57:15,  7.15s/it]
                                                           
{'loss': 0.6278, 'learning_rate': 0.0001497957848155871, 'epoch': 7.71}

 64%|██████▍   | 18037/28080 [35:39:13<19:57:15,  7.15s/it]
 64%|██████▍   | 18038/28080 [35:39:20<19:51:40,  7.12s/it]
                                                           
{'loss': 0.5979, 'learning_rate': 0.00014976936741243507, 'epoch': 7.71}

 64%|██████▍   | 18038/28080 [35:39:20<19:51:40,  7.12s/it]
 64%|██████▍   | 18039/28080 [35:39:27<19:52:20,  7.12s/it]
                                                           
{'loss': 0.5893, 'learning_rate': 0.00014974295134274814, 'epoch': 7.71}

 64%|██████▍   | 18039/28080 [35:39:27<19:52:20,  7.12s/it]
 64%|██████▍   | 18040/28080 [35:39:34<19:51:06,  7.12s/it]
                                                           
{'loss': 0.5974, 'learning_rate': 0.00014971653660687798, 'epoch': 7.71}

 64%|██████▍   | 18040/28080 [35:39:34<19:51:06,  7.12s/it]
 64%|██████▍   | 18041/28080 [35:39:42<19:54:29,  7.14s/it]
                                                           
{'loss': 0.6061, 'learning_rate': 0.00014969012320517567, 'epoch': 7.71}

 64%|██████▍   | 18041/28080 [35:39:42<19:54:29,  7.14s/it]
 64%|██████▍   | 18042/28080 [35:39:49<19:56:15,  7.15s/it]
                                                           
{'loss': 0.6198, 'learning_rate': 0.00014966371113799291, 'epoch': 7.71}

 64%|██████▍   | 18042/28080 [35:39:49<19:56:15,  7.15s/it]
 64%|██████▍   | 18043/28080 [35:39:56<19:52:19,  7.13s/it]
                                                           
{'loss': 0.6114, 'learning_rate': 0.00014963730040568087, 'epoch': 7.71}

 64%|██████▍   | 18043/28080 [35:39:56<19:52:19,  7.13s/it]
 64%|██████▍   | 18044/28080 [35:40:03<19:53:59,  7.14s/it]
                                                           
{'loss': 0.6085, 'learning_rate': 0.0001496108910085911, 'epoch': 7.71}

 64%|██████▍   | 18044/28080 [35:40:03<19:53:59,  7.14s/it]
 64%|██████▍   | 18045/28080 [35:40:10<19:53:49,  7.14s/it]
                                                           
{'loss': 0.5979, 'learning_rate': 0.00014958448294707488, 'epoch': 7.71}

 64%|██████▍   | 18045/28080 [35:40:10<19:53:49,  7.14s/it]
 64%|██████▍   | 18046/28080 [35:40:17<19:56:10,  7.15s/it]
                                                           
{'loss': 0.6126, 'learning_rate': 0.0001495580762214834, 'epoch': 7.71}

 64%|██████▍   | 18046/28080 [35:40:17<19:56:10,  7.15s/it]
 64%|██████▍   | 18047/28080 [35:40:24<19:48:52,  7.11s/it]
                                                           
{'loss': 0.6309, 'learning_rate': 0.00014953167083216816, 'epoch': 7.71}

 64%|██████▍   | 18047/28080 [35:40:24<19:48:52,  7.11s/it]
 64%|██████▍   | 18048/28080 [35:40:31<19:47:54,  7.10s/it]
                                                           
{'loss': 0.6009, 'learning_rate': 0.0001495052667794804, 'epoch': 7.71}

 64%|██████▍   | 18048/28080 [35:40:31<19:47:54,  7.10s/it]
 64%|██████▍   | 18049/28080 [35:40:39<19:49:51,  7.12s/it]
                                                           
{'loss': 0.6013, 'learning_rate': 0.0001494788640637714, 'epoch': 7.71}

 64%|██████▍   | 18049/28080 [35:40:39<19:49:51,  7.12s/it]
 64%|██████▍   | 18050/28080 [35:40:46<19:52:38,  7.13s/it]
                                                           
{'loss': 0.5962, 'learning_rate': 0.00014945246268539236, 'epoch': 7.71}

 64%|██████▍   | 18050/28080 [35:40:46<19:52:38,  7.13s/it]
 64%|██████▍   | 18051/28080 [35:40:53<19:50:11,  7.12s/it]
                                                           
{'loss': 0.6092, 'learning_rate': 0.00014942606264469464, 'epoch': 7.71}

 64%|██████▍   | 18051/28080 [35:40:53<19:50:11,  7.12s/it]
 64%|██████▍   | 18052/28080 [35:41:00<19:51:12,  7.13s/it]
                                                           
{'loss': 0.602, 'learning_rate': 0.00014939966394202932, 'epoch': 7.71}

 64%|██████▍   | 18052/28080 [35:41:00<19:51:12,  7.13s/it]
 64%|██████▍   | 18053/28080 [35:41:07<19:51:58,  7.13s/it]
                                                           
{'loss': 0.6274, 'learning_rate': 0.0001493732665777478, 'epoch': 7.71}

 64%|██████▍   | 18053/28080 [35:41:07<19:51:58,  7.13s/it]
 64%|██████▍   | 18054/28080 [35:41:14<19:48:50,  7.11s/it]
                                                           
{'loss': 0.6074, 'learning_rate': 0.00014934687055220104, 'epoch': 7.71}

 64%|██████▍   | 18054/28080 [35:41:14<19:48:50,  7.11s/it]
 64%|██████▍   | 18055/28080 [35:41:21<19:43:30,  7.08s/it]
                                                           
{'loss': 0.6194, 'learning_rate': 0.00014932047586574044, 'epoch': 7.71}

 64%|██████▍   | 18055/28080 [35:41:21<19:43:30,  7.08s/it]
 64%|██████▍   | 18056/28080 [35:41:28<19:48:35,  7.11s/it]
                                                           
{'loss': 0.6173, 'learning_rate': 0.00014929408251871691, 'epoch': 7.71}

 64%|██████▍   | 18056/28080 [35:41:28<19:48:35,  7.11s/it]
 64%|██████▍   | 18057/28080 [35:41:36<19:47:42,  7.11s/it]
                                                           
{'loss': 0.6119, 'learning_rate': 0.00014926769051148183, 'epoch': 7.71}

 64%|██████▍   | 18057/28080 [35:41:36<19:47:42,  7.11s/it]
 64%|██████▍   | 18058/28080 [35:41:43<19:47:17,  7.11s/it]
                                                           
{'loss': 0.6187, 'learning_rate': 0.00014924129984438613, 'epoch': 7.71}

 64%|██████▍   | 18058/28080 [35:41:43<19:47:17,  7.11s/it]
 64%|██████▍   | 18059/28080 [35:41:50<19:46:43,  7.11s/it]
                                                           
{'loss': 0.5865, 'learning_rate': 0.00014921491051778102, 'epoch': 7.71}

 64%|██████▍   | 18059/28080 [35:41:50<19:46:43,  7.11s/it]
 64%|██████▍   | 18060/28080 [35:41:57<19:48:11,  7.11s/it]
                                                           
{'loss': 0.604, 'learning_rate': 0.00014918852253201757, 'epoch': 7.72}

 64%|██████▍   | 18060/28080 [35:41:57<19:48:11,  7.11s/it]
 64%|██████▍   | 18061/28080 [35:42:04<19:50:01,  7.13s/it]
                                                           
{'loss': 0.5919, 'learning_rate': 0.00014916213588744682, 'epoch': 7.72}

 64%|██████▍   | 18061/28080 [35:42:04<19:50:01,  7.13s/it]
 64%|██████▍   | 18062/28080 [35:42:11<19:50:34,  7.13s/it]
                                                           
{'loss': 0.6009, 'learning_rate': 0.00014913575058441981, 'epoch': 7.72}

 64%|██████▍   | 18062/28080 [35:42:11<19:50:34,  7.13s/it]
 64%|██████▍   | 18063/28080 [35:42:18<19:49:34,  7.13s/it]
                                                           
{'loss': 0.613, 'learning_rate': 0.0001491093666232876, 'epoch': 7.72}

 64%|██████▍   | 18063/28080 [35:42:18<19:49:34,  7.13s/it]
 64%|██████▍   | 18064/28080 [35:42:25<19:48:08,  7.12s/it]
                                                           
{'loss': 0.6047, 'learning_rate': 0.0001490829840044012, 'epoch': 7.72}

 64%|██████▍   | 18064/28080 [35:42:25<19:48:08,  7.12s/it]
 64%|██████▍   | 18065/28080 [35:42:33<19:50:04,  7.13s/it]
                                                           
{'loss': 0.6003, 'learning_rate': 0.00014905660272811157, 'epoch': 7.72}

 64%|██████▍   | 18065/28080 [35:42:33<19:50:04,  7.13s/it]
 64%|██████▍   | 18066/28080 [35:42:40<19:51:29,  7.14s/it]
                                                           
{'loss': 0.5862, 'learning_rate': 0.0001490302227947697, 'epoch': 7.72}

 64%|██████▍   | 18066/28080 [35:42:40<19:51:29,  7.14s/it]
 64%|██████▍   | 18067/28080 [35:42:47<19:53:02,  7.15s/it]
                                                           
{'loss': 0.6153, 'learning_rate': 0.00014900384420472656, 'epoch': 7.72}

 64%|██████▍   | 18067/28080 [35:42:47<19:53:02,  7.15s/it]
 64%|██████▍   | 18068/28080 [35:42:54<19:55:21,  7.16s/it]
                                                           
{'loss': 0.6189, 'learning_rate': 0.00014897746695833304, 'epoch': 7.72}

 64%|██████▍   | 18068/28080 [35:42:54<19:55:21,  7.16s/it]
 64%|██████▍   | 18069/28080 [35:43:01<19:54:39,  7.16s/it]
                                                           
{'loss': 0.6112, 'learning_rate': 0.00014895109105594016, 'epoch': 7.72}

 64%|██████▍   | 18069/28080 [35:43:01<19:54:39,  7.16s/it]
 64%|██████▍   | 18070/28080 [35:43:08<19:50:53,  7.14s/it]
                                                           
{'loss': 0.597, 'learning_rate': 0.00014892471649789876, 'epoch': 7.72}

 64%|██████▍   | 18070/28080 [35:43:08<19:50:53,  7.14s/it]
 64%|██████▍   | 18071/28080 [35:43:15<19:47:09,  7.12s/it]
                                                           
{'loss': 0.6184, 'learning_rate': 0.0001488983432845597, 'epoch': 7.72}

 64%|██████▍   | 18071/28080 [35:43:15<19:47:09,  7.12s/it]
 64%|██████▍   | 18072/28080 [35:43:23<19:51:01,  7.14s/it]
                                                           
{'loss': 0.6078, 'learning_rate': 0.0001488719714162739, 'epoch': 7.72}

 64%|██████▍   | 18072/28080 [35:43:23<19:51:01,  7.14s/it]
 64%|██████▍   | 18073/28080 [35:43:30<19:52:47,  7.15s/it]
                                                           
{'loss': 0.6247, 'learning_rate': 0.0001488456008933921, 'epoch': 7.72}

 64%|██████▍   | 18073/28080 [35:43:30<19:52:47,  7.15s/it]
 64%|██████▍   | 18074/28080 [35:43:37<19:53:24,  7.16s/it]
                                                           
{'loss': 0.61, 'learning_rate': 0.00014881923171626544, 'epoch': 7.72}

 64%|██████▍   | 18074/28080 [35:43:37<19:53:24,  7.16s/it]
 64%|██████▍   | 18075/28080 [35:43:44<19:56:27,  7.18s/it]
                                                           
{'loss': 0.6248, 'learning_rate': 0.00014879286388524429, 'epoch': 7.72}

 64%|██████▍   | 18075/28080 [35:43:44<19:56:27,  7.18s/it]
 64%|██████▍   | 18076/28080 [35:43:51<19:53:08,  7.16s/it]
                                                           
{'loss': 0.6374, 'learning_rate': 0.00014876649740067988, 'epoch': 7.72}

 64%|██████▍   | 18076/28080 [35:43:51<19:53:08,  7.16s/it]
 64%|██████▍   | 18077/28080 [35:43:58<19:49:55,  7.14s/it]
                                                           
{'loss': 0.6, 'learning_rate': 0.0001487401322629226, 'epoch': 7.72}

 64%|██████▍   | 18077/28080 [35:43:58<19:49:55,  7.14s/it]
 64%|██████▍   | 18078/28080 [35:44:05<19:50:08,  7.14s/it]
                                                           
{'loss': 0.6288, 'learning_rate': 0.00014871376847232348, 'epoch': 7.72}

 64%|██████▍   | 18078/28080 [35:44:05<19:50:08,  7.14s/it]
 64%|██████▍   | 18079/28080 [35:44:13<19:49:38,  7.14s/it]
                                                           
{'loss': 0.6132, 'learning_rate': 0.00014868740602923318, 'epoch': 7.72}

 64%|██████▍   | 18079/28080 [35:44:13<19:49:38,  7.14s/it]
 64%|██████▍   | 18080/28080 [35:44:20<19:50:05,  7.14s/it]
                                                           
{'loss': 0.5989, 'learning_rate': 0.00014866104493400245, 'epoch': 7.72}

 64%|██████▍   | 18080/28080 [35:44:20<19:50:05,  7.14s/it]
 64%|██████▍   | 18081/28080 [35:44:27<19:47:32,  7.13s/it]
                                                           
{'loss': 0.6131, 'learning_rate': 0.00014863468518698191, 'epoch': 7.72}

 64%|██████▍   | 18081/28080 [35:44:27<19:47:32,  7.13s/it]
 64%|██████▍   | 18082/28080 [35:44:34<19:44:17,  7.11s/it]
                                                           
{'loss': 0.6022, 'learning_rate': 0.00014860832678852237, 'epoch': 7.72}

 64%|██████▍   | 18082/28080 [35:44:34<19:44:17,  7.11s/it]
 64%|██████▍   | 18083/28080 [35:44:41<19:48:41,  7.13s/it]
                                                           
{'loss': 0.5945, 'learning_rate': 0.00014858196973897443, 'epoch': 7.72}

 64%|██████▍   | 18083/28080 [35:44:41<19:48:41,  7.13s/it]
 64%|██████▍   | 18084/28080 [35:44:48<19:49:12,  7.14s/it]
                                                           
{'loss': 0.6193, 'learning_rate': 0.00014855561403868874, 'epoch': 7.73}

 64%|██████▍   | 18084/28080 [35:44:48<19:49:12,  7.14s/it]
 64%|██████▍   | 18085/28080 [35:44:55<19:47:25,  7.13s/it]
                                                           
{'loss': 0.6181, 'learning_rate': 0.00014852925968801594, 'epoch': 7.73}

 64%|██████▍   | 18085/28080 [35:44:55<19:47:25,  7.13s/it]
 64%|██████▍   | 18086/28080 [35:45:03<19:51:44,  7.15s/it]
                                                           
{'loss': 0.6152, 'learning_rate': 0.0001485029066873067, 'epoch': 7.73}

 64%|██████▍   | 18086/28080 [35:45:03<19:51:44,  7.15s/it]
 64%|██████▍   | 18087/28080 [35:45:10<19:48:44,  7.14s/it]
                                                           
{'loss': 0.6125, 'learning_rate': 0.00014847655503691148, 'epoch': 7.73}

 64%|██████▍   | 18087/28080 [35:45:10<19:48:44,  7.14s/it]
 64%|██████▍   | 18088/28080 [35:45:17<19:52:06,  7.16s/it]
                                                           
{'loss': 0.6092, 'learning_rate': 0.0001484502047371811, 'epoch': 7.73}

 64%|██████▍   | 18088/28080 [35:45:17<19:52:06,  7.16s/it]
 64%|██████▍   | 18089/28080 [35:45:24<19:49:29,  7.14s/it]
                                                           
{'loss': 0.6044, 'learning_rate': 0.00014842385578846585, 'epoch': 7.73}

 64%|██████▍   | 18089/28080 [35:45:24<19:49:29,  7.14s/it]
 64%|██████▍   | 18090/28080 [35:45:31<19:48:35,  7.14s/it]
                                                           
{'loss': 0.5958, 'learning_rate': 0.00014839750819111648, 'epoch': 7.73}

 64%|██████▍   | 18090/28080 [35:45:31<19:48:35,  7.14s/it]
 64%|██████▍   | 18091/28080 [35:45:38<19:46:09,  7.12s/it]
                                                           
{'loss': 0.5989, 'learning_rate': 0.00014837116194548342, 'epoch': 7.73}

 64%|██████▍   | 18091/28080 [35:45:38<19:46:09,  7.12s/it]
 64%|██████▍   | 18092/28080 [35:45:45<19:49:10,  7.14s/it]
                                                           
{'loss': 0.6181, 'learning_rate': 0.00014834481705191727, 'epoch': 7.73}

 64%|██████▍   | 18092/28080 [35:45:45<19:49:10,  7.14s/it]
 64%|██████▍   | 18093/28080 [35:45:53<19:47:37,  7.14s/it]
                                                           
{'loss': 0.6009, 'learning_rate': 0.0001483184735107684, 'epoch': 7.73}

 64%|██████▍   | 18093/28080 [35:45:53<19:47:37,  7.14s/it]
 64%|██████▍   | 18094/28080 [35:46:00<19:49:13,  7.15s/it]
                                                           
{'loss': 0.5874, 'learning_rate': 0.00014829213132238733, 'epoch': 7.73}

 64%|██████▍   | 18094/28080 [35:46:00<19:49:13,  7.15s/it]
 64%|██████▍   | 18095/28080 [35:46:07<19:51:16,  7.16s/it]
                                                           
{'loss': 0.5996, 'learning_rate': 0.0001482657904871246, 'epoch': 7.73}

 64%|██████▍   | 18095/28080 [35:46:07<19:51:16,  7.16s/it]
 64%|██████▍   | 18096/28080 [35:46:14<19:45:14,  7.12s/it]
                                                           
{'loss': 0.6058, 'learning_rate': 0.00014823945100533048, 'epoch': 7.73}

 64%|██████▍   | 18096/28080 [35:46:14<19:45:14,  7.12s/it]
 64%|██████▍   | 18097/28080 [35:46:21<19:44:53,  7.12s/it]
                                                           
{'loss': 0.6197, 'learning_rate': 0.00014821311287735556, 'epoch': 7.73}

 64%|██████▍   | 18097/28080 [35:46:21<19:44:53,  7.12s/it]
 64%|██████▍   | 18098/28080 [35:46:28<19:41:33,  7.10s/it]
                                                           
{'loss': 0.6069, 'learning_rate': 0.0001481867761035501, 'epoch': 7.73}

 64%|██████▍   | 18098/28080 [35:46:28<19:41:33,  7.10s/it]
 64%|██████▍   | 18099/28080 [35:46:35<19:40:54,  7.10s/it]
                                                           
{'loss': 0.6174, 'learning_rate': 0.00014816044068426462, 'epoch': 7.73}

 64%|██████▍   | 18099/28080 [35:46:35<19:40:54,  7.10s/it]
 64%|██████▍   | 18100/28080 [35:46:42<19:43:48,  7.12s/it]
                                                           
{'loss': 0.6103, 'learning_rate': 0.00014813410661984936, 'epoch': 7.73}

 64%|██████▍   | 18100/28080 [35:46:42<19:43:48,  7.12s/it]
 64%|██████▍   | 18101/28080 [35:46:49<19:42:16,  7.11s/it]
                                                           
{'loss': 0.6098, 'learning_rate': 0.00014810777391065477, 'epoch': 7.73}

 64%|██████▍   | 18101/28080 [35:46:49<19:42:16,  7.11s/it]
 64%|██████▍   | 18102/28080 [35:46:57<19:41:58,  7.11s/it]
                                                           
{'loss': 0.6113, 'learning_rate': 0.00014808144255703108, 'epoch': 7.73}

 64%|██████▍   | 18102/28080 [35:46:57<19:41:58,  7.11s/it]
 64%|██████▍   | 18103/28080 [35:47:04<19:39:38,  7.09s/it]
                                                           
{'loss': 0.6032, 'learning_rate': 0.00014805511255932868, 'epoch': 7.73}

 64%|██████▍   | 18103/28080 [35:47:04<19:39:38,  7.09s/it]
 64%|██████▍   | 18104/28080 [35:47:11<19:37:21,  7.08s/it]
                                                           
{'loss': 0.6228, 'learning_rate': 0.00014802878391789774, 'epoch': 7.73}

 64%|██████▍   | 18104/28080 [35:47:11<19:37:21,  7.08s/it]
 64%|██████▍   | 18105/28080 [35:47:18<19:38:50,  7.09s/it]
                                                           
{'loss': 0.6324, 'learning_rate': 0.00014800245663308881, 'epoch': 7.73}

 64%|██████▍   | 18105/28080 [35:47:18<19:38:50,  7.09s/it]
 64%|██████▍   | 18106/28080 [35:47:25<19:43:39,  7.12s/it]
                                                           
{'loss': 0.604, 'learning_rate': 0.00014797613070525182, 'epoch': 7.73}

 64%|██████▍   | 18106/28080 [35:47:25<19:43:39,  7.12s/it]
 64%|██████▍   | 18107/28080 [35:47:32<19:42:14,  7.11s/it]
                                                           
{'loss': 0.5882, 'learning_rate': 0.0001479498061347373, 'epoch': 7.74}

 64%|██████▍   | 18107/28080 [35:47:32<19:42:14,  7.11s/it]
 64%|██████▍   | 18108/28080 [35:47:39<19:41:57,  7.11s/it]
                                                           
{'loss': 0.6274, 'learning_rate': 0.00014792348292189518, 'epoch': 7.74}

 64%|██████▍   | 18108/28080 [35:47:39<19:41:57,  7.11s/it]
 64%|██████▍   | 18109/28080 [35:47:46<19:44:31,  7.13s/it]
                                                           
{'loss': 0.5794, 'learning_rate': 0.0001478971610670759, 'epoch': 7.74}

 64%|██████▍   | 18109/28080 [35:47:46<19:44:31,  7.13s/it]
 64%|██████▍   | 18110/28080 [35:47:53<19:44:27,  7.13s/it]
                                                           
{'loss': 0.5895, 'learning_rate': 0.0001478708405706295, 'epoch': 7.74}

 64%|██████▍   | 18110/28080 [35:47:53<19:44:27,  7.13s/it]
 64%|██████▍   | 18111/28080 [35:48:01<19:42:44,  7.12s/it]
                                                           
{'loss': 0.6113, 'learning_rate': 0.00014784452143290627, 'epoch': 7.74}

 64%|██████▍   | 18111/28080 [35:48:01<19:42:44,  7.12s/it]
 65%|██████▍   | 18112/28080 [35:48:08<19:44:29,  7.13s/it]
                                                           
{'loss': 0.6133, 'learning_rate': 0.00014781820365425627, 'epoch': 7.74}

 65%|██████▍   | 18112/28080 [35:48:08<19:44:29,  7.13s/it]
 65%|██████▍   | 18113/28080 [35:48:15<19:38:01,  7.09s/it]
                                                           
{'loss': 0.6248, 'learning_rate': 0.00014779188723502968, 'epoch': 7.74}

 65%|██████▍   | 18113/28080 [35:48:15<19:38:01,  7.09s/it]
 65%|██████▍   | 18114/28080 [35:48:22<19:38:45,  7.10s/it]
                                                           
{'loss': 0.5988, 'learning_rate': 0.00014776557217557654, 'epoch': 7.74}

 65%|██████▍   | 18114/28080 [35:48:22<19:38:45,  7.10s/it]
 65%|██████▍   | 18115/28080 [35:48:29<19:40:53,  7.11s/it]
                                                           
{'loss': 0.6232, 'learning_rate': 0.00014773925847624703, 'epoch': 7.74}

 65%|██████▍   | 18115/28080 [35:48:29<19:40:53,  7.11s/it]
 65%|██████▍   | 18116/28080 [35:48:36<19:44:17,  7.13s/it]
                                                           
{'loss': 0.5967, 'learning_rate': 0.00014771294613739116, 'epoch': 7.74}

 65%|██████▍   | 18116/28080 [35:48:36<19:44:17,  7.13s/it]
 65%|██████▍   | 18117/28080 [35:48:43<19:44:19,  7.13s/it]
                                                           
{'loss': 0.5897, 'learning_rate': 0.00014768663515935906, 'epoch': 7.74}

 65%|██████▍   | 18117/28080 [35:48:43<19:44:19,  7.13s/it]
 65%|██████▍   | 18118/28080 [35:48:50<19:48:10,  7.16s/it]
                                                           
{'loss': 0.596, 'learning_rate': 0.00014766032554250065, 'epoch': 7.74}

 65%|██████▍   | 18118/28080 [35:48:50<19:48:10,  7.16s/it]
 65%|██████▍   | 18119/28080 [35:48:58<19:50:17,  7.17s/it]
                                                           
{'loss': 0.6191, 'learning_rate': 0.00014763401728716614, 'epoch': 7.74}

 65%|██████▍   | 18119/28080 [35:48:58<19:50:17,  7.17s/it]
 65%|██████▍   | 18120/28080 [35:49:05<19:45:36,  7.14s/it]
                                                           
{'loss': 0.5888, 'learning_rate': 0.0001476077103937054, 'epoch': 7.74}

 65%|██████▍   | 18120/28080 [35:49:05<19:45:36,  7.14s/it]
 65%|██████▍   | 18121/28080 [35:49:12<19:47:13,  7.15s/it]
                                                           
{'loss': 0.6161, 'learning_rate': 0.00014758140486246835, 'epoch': 7.74}

 65%|██████▍   | 18121/28080 [35:49:12<19:47:13,  7.15s/it]
 65%|██████▍   | 18122/28080 [35:49:19<19:44:26,  7.14s/it]
                                                           
{'loss': 0.6069, 'learning_rate': 0.0001475551006938052, 'epoch': 7.74}

 65%|██████▍   | 18122/28080 [35:49:19<19:44:26,  7.14s/it]
 65%|██████▍   | 18123/28080 [35:49:26<19:45:07,  7.14s/it]
                                                           
{'loss': 0.6057, 'learning_rate': 0.00014752879788806556, 'epoch': 7.74}

 65%|██████▍   | 18123/28080 [35:49:26<19:45:07,  7.14s/it]
 65%|██████▍   | 18124/28080 [35:49:33<19:33:35,  7.07s/it]
                                                           
{'loss': 0.6247, 'learning_rate': 0.0001475024964455997, 'epoch': 7.74}

 65%|██████▍   | 18124/28080 [35:49:33<19:33:35,  7.07s/it]
 65%|██████▍   | 18125/28080 [35:49:40<19:39:28,  7.11s/it]
                                                           
{'loss': 0.6422, 'learning_rate': 0.0001474761963667573, 'epoch': 7.74}

 65%|██████▍   | 18125/28080 [35:49:40<19:39:28,  7.11s/it]
 65%|██████▍   | 18126/28080 [35:49:48<19:45:08,  7.14s/it]
                                                           
{'loss': 0.6092, 'learning_rate': 0.00014744989765188839, 'epoch': 7.74}

 65%|██████▍   | 18126/28080 [35:49:48<19:45:08,  7.14s/it]
 65%|██████▍   | 18127/28080 [35:49:55<19:45:32,  7.15s/it]
                                                           
{'loss': 0.5984, 'learning_rate': 0.00014742360030134275, 'epoch': 7.74}

 65%|██████▍   | 18127/28080 [35:49:55<19:45:32,  7.15s/it]
 65%|██████▍   | 18128/28080 [35:50:02<19:40:16,  7.12s/it]
                                                           
{'loss': 0.6139, 'learning_rate': 0.00014739730431547032, 'epoch': 7.74}

 65%|██████▍   | 18128/28080 [35:50:02<19:40:16,  7.12s/it]
 65%|██████▍   | 18129/28080 [35:50:09<19:40:51,  7.12s/it]
                                                           
{'loss': 0.6021, 'learning_rate': 0.0001473710096946209, 'epoch': 7.74}

 65%|██████▍   | 18129/28080 [35:50:09<19:40:51,  7.12s/it]
 65%|██████▍   | 18130/28080 [35:50:16<19:40:32,  7.12s/it]
                                                           
{'loss': 0.6036, 'learning_rate': 0.00014734471643914433, 'epoch': 7.74}

 65%|██████▍   | 18130/28080 [35:50:16<19:40:32,  7.12s/it]
 65%|██████▍   | 18131/28080 [35:50:23<19:41:49,  7.13s/it]
                                                           
{'loss': 0.6025, 'learning_rate': 0.00014731842454939037, 'epoch': 7.75}

 65%|██████▍   | 18131/28080 [35:50:23<19:41:49,  7.13s/it]
 65%|██████▍   | 18132/28080 [35:50:30<19:41:03,  7.12s/it]
                                                           
{'loss': 0.6249, 'learning_rate': 0.0001472921340257089, 'epoch': 7.75}

 65%|██████▍   | 18132/28080 [35:50:30<19:41:03,  7.12s/it]
 65%|██████▍   | 18133/28080 [35:50:37<19:42:27,  7.13s/it]
                                                           
{'loss': 0.6111, 'learning_rate': 0.00014726584486844958, 'epoch': 7.75}

 65%|██████▍   | 18133/28080 [35:50:37<19:42:27,  7.13s/it]
 65%|██████▍   | 18134/28080 [35:50:45<19:43:34,  7.14s/it]
                                                           
{'loss': 0.6114, 'learning_rate': 0.00014723955707796226, 'epoch': 7.75}

 65%|██████▍   | 18134/28080 [35:50:45<19:43:34,  7.14s/it]
 65%|██████▍   | 18135/28080 [35:50:52<19:42:42,  7.14s/it]
                                                           
{'loss': 0.5974, 'learning_rate': 0.0001472132706545965, 'epoch': 7.75}

 65%|██████▍   | 18135/28080 [35:50:52<19:42:42,  7.14s/it]
 65%|██████▍   | 18136/28080 [35:50:59<19:45:04,  7.15s/it]
                                                           
{'loss': 0.6009, 'learning_rate': 0.0001471869855987023, 'epoch': 7.75}

 65%|██████▍   | 18136/28080 [35:50:59<19:45:04,  7.15s/it]
 65%|██████▍   | 18137/28080 [35:51:06<19:43:14,  7.14s/it]
                                                           
{'loss': 0.6095, 'learning_rate': 0.00014716070191062903, 'epoch': 7.75}

 65%|██████▍   | 18137/28080 [35:51:06<19:43:14,  7.14s/it]
 65%|██████▍   | 18138/28080 [35:51:13<19:42:04,  7.13s/it]
                                                           
{'loss': 0.6079, 'learning_rate': 0.00014713441959072668, 'epoch': 7.75}

 65%|██████▍   | 18138/28080 [35:51:13<19:42:04,  7.13s/it]
 65%|██████▍   | 18139/28080 [35:51:20<19:36:58,  7.10s/it]
                                                           
{'loss': 0.6217, 'learning_rate': 0.0001471081386393446, 'epoch': 7.75}

 65%|██████▍   | 18139/28080 [35:51:20<19:36:58,  7.10s/it]
 65%|██████▍   | 18140/28080 [35:51:27<19:40:03,  7.12s/it]
                                                           
{'loss': 0.6043, 'learning_rate': 0.0001470818590568327, 'epoch': 7.75}

 65%|██████▍   | 18140/28080 [35:51:27<19:40:03,  7.12s/it]
 65%|██████▍   | 18141/28080 [35:51:34<19:39:20,  7.12s/it]
                                                           
{'loss': 0.6129, 'learning_rate': 0.00014705558084354041, 'epoch': 7.75}

 65%|██████▍   | 18141/28080 [35:51:34<19:39:20,  7.12s/it]
 65%|██████▍   | 18142/28080 [35:51:42<19:39:09,  7.12s/it]
                                                           
{'loss': 0.6042, 'learning_rate': 0.0001470293039998175, 'epoch': 7.75}

 65%|██████▍   | 18142/28080 [35:51:42<19:39:09,  7.12s/it]
 65%|██████▍   | 18143/28080 [35:51:49<19:40:04,  7.13s/it]
                                                           
{'loss': 0.5975, 'learning_rate': 0.00014700302852601344, 'epoch': 7.75}

 65%|██████▍   | 18143/28080 [35:51:49<19:40:04,  7.13s/it]
 65%|██████▍   | 18144/28080 [35:51:56<19:42:30,  7.14s/it]
                                                           
{'loss': 0.6113, 'learning_rate': 0.00014697675442247785, 'epoch': 7.75}

 65%|██████▍   | 18144/28080 [35:51:56<19:42:30,  7.14s/it]
 65%|██████▍   | 18145/28080 [35:52:03<19:41:06,  7.13s/it]
                                                           
{'loss': 0.6024, 'learning_rate': 0.00014695048168956028, 'epoch': 7.75}

 65%|██████▍   | 18145/28080 [35:52:03<19:41:06,  7.13s/it]
 65%|██████▍   | 18146/28080 [35:52:10<19:43:31,  7.15s/it]
                                                           
{'loss': 0.6073, 'learning_rate': 0.00014692421032761016, 'epoch': 7.75}

 65%|██████▍   | 18146/28080 [35:52:10<19:43:31,  7.15s/it]
 65%|██████▍   | 18147/28080 [35:52:17<19:46:39,  7.17s/it]
                                                           
{'loss': 0.6121, 'learning_rate': 0.00014689794033697715, 'epoch': 7.75}

 65%|██████▍   | 18147/28080 [35:52:17<19:46:39,  7.17s/it]
 65%|██████▍   | 18148/28080 [35:52:24<19:45:41,  7.16s/it]
                                                           
{'loss': 0.6131, 'learning_rate': 0.00014687167171801064, 'epoch': 7.75}

 65%|██████▍   | 18148/28080 [35:52:25<19:45:41,  7.16s/it]
 65%|██████▍   | 18149/28080 [35:52:32<19:50:03,  7.19s/it]
                                                           
{'loss': 0.59, 'learning_rate': 0.00014684540447106015, 'epoch': 7.75}

 65%|██████▍   | 18149/28080 [35:52:32<19:50:03,  7.19s/it]
 65%|██████▍   | 18150/28080 [35:52:39<19:49:38,  7.19s/it]
                                                           
{'loss': 0.5924, 'learning_rate': 0.00014681913859647514, 'epoch': 7.75}

 65%|██████▍   | 18150/28080 [35:52:39<19:49:38,  7.19s/it]
 65%|██████▍   | 18151/28080 [35:52:46<19:41:53,  7.14s/it]
                                                           
{'loss': 0.603, 'learning_rate': 0.00014679287409460507, 'epoch': 7.75}

 65%|██████▍   | 18151/28080 [35:52:46<19:41:53,  7.14s/it]
 65%|██████▍   | 18152/28080 [35:52:53<19:41:14,  7.14s/it]
                                                           
{'loss': 0.6112, 'learning_rate': 0.00014676661096579924, 'epoch': 7.75}

 65%|██████▍   | 18152/28080 [35:52:53<19:41:14,  7.14s/it]
 65%|██████▍   | 18153/28080 [35:53:00<19:42:20,  7.15s/it]
                                                           
{'loss': 0.5977, 'learning_rate': 0.0001467403492104073, 'epoch': 7.75}

 65%|██████▍   | 18153/28080 [35:53:00<19:42:20,  7.15s/it]
 65%|██████▍   | 18154/28080 [35:53:07<19:36:31,  7.11s/it]
                                                           
{'loss': 0.5891, 'learning_rate': 0.00014671408882877834, 'epoch': 7.76}

 65%|██████▍   | 18154/28080 [35:53:07<19:36:31,  7.11s/it]
 65%|██████▍   | 18155/28080 [35:53:14<19:39:15,  7.13s/it]
                                                           
{'loss': 0.6181, 'learning_rate': 0.00014668782982126203, 'epoch': 7.76}

 65%|██████▍   | 18155/28080 [35:53:14<19:39:15,  7.13s/it]
 65%|██████▍   | 18156/28080 [35:53:22<19:39:37,  7.13s/it]
                                                           
{'loss': 0.5935, 'learning_rate': 0.0001466615721882074, 'epoch': 7.76}

 65%|██████▍   | 18156/28080 [35:53:22<19:39:37,  7.13s/it]
 65%|██████▍   | 18157/28080 [35:53:29<19:39:26,  7.13s/it]
                                                           
{'loss': 0.6147, 'learning_rate': 0.00014663531592996404, 'epoch': 7.76}

 65%|██████▍   | 18157/28080 [35:53:29<19:39:26,  7.13s/it]
 65%|██████▍   | 18158/28080 [35:53:36<19:36:37,  7.12s/it]
                                                           
{'loss': 0.6152, 'learning_rate': 0.00014660906104688116, 'epoch': 7.76}

 65%|██████▍   | 18158/28080 [35:53:36<19:36:37,  7.12s/it]
 65%|██████▍   | 18159/28080 [35:53:43<19:41:38,  7.15s/it]
                                                           
{'loss': 0.6004, 'learning_rate': 0.00014658280753930805, 'epoch': 7.76}

 65%|██████▍   | 18159/28080 [35:53:43<19:41:38,  7.15s/it]
 65%|██████▍   | 18160/28080 [35:53:50<19:40:01,  7.14s/it]
                                                           
{'loss': 0.6035, 'learning_rate': 0.000146556555407594, 'epoch': 7.76}

 65%|██████▍   | 18160/28080 [35:53:50<19:40:01,  7.14s/it]
 65%|██████▍   | 18161/28080 [35:53:57<19:34:52,  7.11s/it]
                                                           
{'loss': 0.622, 'learning_rate': 0.00014653030465208827, 'epoch': 7.76}

 65%|██████▍   | 18161/28080 [35:53:57<19:34:52,  7.11s/it]
 65%|██████▍   | 18162/28080 [35:54:04<19:40:15,  7.14s/it]
                                                           
{'loss': 0.6006, 'learning_rate': 0.00014650405527314003, 'epoch': 7.76}

 65%|██████▍   | 18162/28080 [35:54:04<19:40:15,  7.14s/it]
 65%|██████▍   | 18163/28080 [35:54:11<19:33:04,  7.10s/it]
                                                           
{'loss': 0.6161, 'learning_rate': 0.00014647780727109866, 'epoch': 7.76}

 65%|██████▍   | 18163/28080 [35:54:11<19:33:04,  7.10s/it]
 65%|██████▍   | 18164/28080 [35:54:19<19:34:01,  7.10s/it]
                                                           
{'loss': 0.6113, 'learning_rate': 0.0001464515606463132, 'epoch': 7.76}

 65%|██████▍   | 18164/28080 [35:54:19<19:34:01,  7.10s/it]
 65%|██████▍   | 18165/28080 [35:54:26<19:44:03,  7.17s/it]
                                                           
{'loss': 0.6083, 'learning_rate': 0.00014642531539913294, 'epoch': 7.76}

 65%|██████▍   | 18165/28080 [35:54:26<19:44:03,  7.17s/it]
 65%|██████▍   | 18166/28080 [35:54:33<19:39:12,  7.14s/it]
                                                           
{'loss': 0.6114, 'learning_rate': 0.00014639907152990694, 'epoch': 7.76}

 65%|██████▍   | 18166/28080 [35:54:33<19:39:12,  7.14s/it]
 65%|██████▍   | 18167/28080 [35:54:40<19:32:12,  7.09s/it]
                                                           
{'loss': 0.6207, 'learning_rate': 0.00014637282903898452, 'epoch': 7.76}

 65%|██████▍   | 18167/28080 [35:54:40<19:32:12,  7.09s/it]
 65%|██████▍   | 18168/28080 [35:54:47<19:33:13,  7.10s/it]
                                                           
{'loss': 0.6141, 'learning_rate': 0.00014634658792671458, 'epoch': 7.76}

 65%|██████▍   | 18168/28080 [35:54:47<19:33:13,  7.10s/it]
 65%|██████▍   | 18169/28080 [35:54:54<19:32:10,  7.10s/it]
                                                           
{'loss': 0.6006, 'learning_rate': 0.0001463203481934465, 'epoch': 7.76}

 65%|██████▍   | 18169/28080 [35:54:54<19:32:10,  7.10s/it]
 65%|██████▍   | 18170/28080 [35:55:01<19:29:11,  7.08s/it]
                                                           
{'loss': 0.6295, 'learning_rate': 0.00014629410983952917, 'epoch': 7.76}

 65%|██████▍   | 18170/28080 [35:55:01<19:29:11,  7.08s/it]
 65%|██████▍   | 18171/28080 [35:55:08<19:28:54,  7.08s/it]
                                                           
{'loss': 0.6158, 'learning_rate': 0.00014626787286531163, 'epoch': 7.76}

 65%|██████▍   | 18171/28080 [35:55:08<19:28:54,  7.08s/it]
 65%|██████▍   | 18172/28080 [35:55:15<19:30:01,  7.09s/it]
                                                           
{'loss': 0.6129, 'learning_rate': 0.00014624163727114316, 'epoch': 7.76}

 65%|██████▍   | 18172/28080 [35:55:15<19:30:01,  7.09s/it]
 65%|██████▍   | 18173/28080 [35:55:22<19:32:13,  7.10s/it]
                                                           
{'loss': 0.5996, 'learning_rate': 0.00014621540305737255, 'epoch': 7.76}

 65%|██████▍   | 18173/28080 [35:55:22<19:32:13,  7.10s/it]
 65%|██████▍   | 18174/28080 [35:55:30<19:31:50,  7.10s/it]
                                                           
{'loss': 0.6118, 'learning_rate': 0.000146189170224349, 'epoch': 7.76}

 65%|██████▍   | 18174/28080 [35:55:30<19:31:50,  7.10s/it]
 65%|██████▍   | 18175/28080 [35:55:37<19:35:56,  7.12s/it]
                                                           
{'loss': 0.5987, 'learning_rate': 0.00014616293877242143, 'epoch': 7.76}

 65%|██████▍   | 18175/28080 [35:55:37<19:35:56,  7.12s/it]
 65%|██████▍   | 18176/28080 [35:55:44<19:34:27,  7.12s/it]
                                                           
{'loss': 0.6171, 'learning_rate': 0.00014613670870193885, 'epoch': 7.76}

 65%|██████▍   | 18176/28080 [35:55:44<19:34:27,  7.12s/it]
 65%|██████▍   | 18177/28080 [35:55:51<19:31:43,  7.10s/it]
                                                           
{'loss': 0.6181, 'learning_rate': 0.00014611048001325017, 'epoch': 7.77}

 65%|██████▍   | 18177/28080 [35:55:51<19:31:43,  7.10s/it]
 65%|██████▍   | 18178/28080 [35:55:58<19:33:08,  7.11s/it]
                                                           
{'loss': 0.6142, 'learning_rate': 0.00014608425270670446, 'epoch': 7.77}

 65%|██████▍   | 18178/28080 [35:55:58<19:33:08,  7.11s/it]
 65%|██████▍   | 18179/28080 [35:56:05<19:35:56,  7.13s/it]
                                                           
{'loss': 0.6357, 'learning_rate': 0.00014605802678265044, 'epoch': 7.77}

 65%|██████▍   | 18179/28080 [35:56:05<19:35:56,  7.13s/it]
 65%|██████▍   | 18180/28080 [35:56:12<19:31:34,  7.10s/it]
                                                           
{'loss': 0.6031, 'learning_rate': 0.00014603180224143726, 'epoch': 7.77}

 65%|██████▍   | 18180/28080 [35:56:12<19:31:34,  7.10s/it]
 65%|██████▍   | 18181/28080 [35:56:19<19:33:01,  7.11s/it]
                                                           
{'loss': 0.6176, 'learning_rate': 0.00014600557908341362, 'epoch': 7.77}

 65%|██████▍   | 18181/28080 [35:56:19<19:33:01,  7.11s/it]
 65%|██████▍   | 18182/28080 [35:56:26<19:26:41,  7.07s/it]
                                                           
{'loss': 0.6318, 'learning_rate': 0.0001459793573089285, 'epoch': 7.77}

 65%|██████▍   | 18182/28080 [35:56:26<19:26:41,  7.07s/it]
 65%|██████▍   | 18183/28080 [35:56:33<19:25:45,  7.07s/it]
                                                           
{'loss': 0.6257, 'learning_rate': 0.0001459531369183306, 'epoch': 7.77}

 65%|██████▍   | 18183/28080 [35:56:33<19:25:45,  7.07s/it]
 65%|██████▍   | 18184/28080 [35:56:41<19:29:02,  7.09s/it]
                                                           
{'loss': 0.6229, 'learning_rate': 0.00014592691791196906, 'epoch': 7.77}

 65%|██████▍   | 18184/28080 [35:56:41<19:29:02,  7.09s/it]
 65%|██████▍   | 18185/28080 [35:56:48<19:31:27,  7.10s/it]
                                                           
{'loss': 0.6106, 'learning_rate': 0.00014590070029019245, 'epoch': 7.77}

 65%|██████▍   | 18185/28080 [35:56:48<19:31:27,  7.10s/it]
 65%|██████▍   | 18186/28080 [35:56:55<19:35:10,  7.13s/it]
                                                           
{'loss': 0.5898, 'learning_rate': 0.00014587448405334964, 'epoch': 7.77}

 65%|██████▍   | 18186/28080 [35:56:55<19:35:10,  7.13s/it]
 65%|██████▍   | 18187/28080 [35:57:02<19:36:55,  7.14s/it]
                                                           
{'loss': 0.6072, 'learning_rate': 0.0001458482692017893, 'epoch': 7.77}

 65%|██████▍   | 18187/28080 [35:57:02<19:36:55,  7.14s/it]
 65%|██████▍   | 18188/28080 [35:57:09<19:36:07,  7.13s/it]
                                                           
{'loss': 0.6522, 'learning_rate': 0.00014582205573586039, 'epoch': 7.77}

 65%|██████▍   | 18188/28080 [35:57:09<19:36:07,  7.13s/it]
 65%|██████▍   | 18189/28080 [35:57:16<19:35:33,  7.13s/it]
                                                           
{'loss': 0.6099, 'learning_rate': 0.00014579584365591154, 'epoch': 7.77}

 65%|██████▍   | 18189/28080 [35:57:16<19:35:33,  7.13s/it]
 65%|██████▍   | 18190/28080 [35:57:23<19:34:19,  7.12s/it]
                                                           
{'loss': 0.6252, 'learning_rate': 0.00014576963296229151, 'epoch': 7.77}

 65%|██████▍   | 18190/28080 [35:57:23<19:34:19,  7.12s/it]
 65%|██████▍   | 18191/28080 [35:57:31<19:35:02,  7.13s/it]
                                                           
{'loss': 0.5833, 'learning_rate': 0.00014574342365534888, 'epoch': 7.77}

 65%|██████▍   | 18191/28080 [35:57:31<19:35:02,  7.13s/it]
 65%|██████▍   | 18192/28080 [35:57:38<19:39:36,  7.16s/it]
                                                           
{'loss': 0.6308, 'learning_rate': 0.00014571721573543254, 'epoch': 7.77}

 65%|██████▍   | 18192/28080 [35:57:38<19:39:36,  7.16s/it]
 65%|██████▍   | 18193/28080 [35:57:45<19:34:13,  7.13s/it]
                                                           
{'loss': 0.5909, 'learning_rate': 0.00014569100920289096, 'epoch': 7.77}

 65%|██████▍   | 18193/28080 [35:57:45<19:34:13,  7.13s/it]
 65%|██████▍   | 18194/28080 [35:57:52<19:36:16,  7.14s/it]
                                                           
{'loss': 0.5956, 'learning_rate': 0.00014566480405807296, 'epoch': 7.77}

 65%|██████▍   | 18194/28080 [35:57:52<19:36:16,  7.14s/it]
 65%|██████▍   | 18195/28080 [35:57:59<19:34:23,  7.13s/it]
                                                           
{'loss': 0.6202, 'learning_rate': 0.00014563860030132725, 'epoch': 7.77}

 65%|██████▍   | 18195/28080 [35:57:59<19:34:23,  7.13s/it]
 65%|██████▍   | 18196/28080 [35:58:06<19:29:16,  7.10s/it]
                                                           
{'loss': 0.6149, 'learning_rate': 0.0001456123979330021, 'epoch': 7.77}

 65%|██████▍   | 18196/28080 [35:58:06<19:29:16,  7.10s/it]
 65%|██████▍   | 18197/28080 [35:58:13<19:25:29,  7.08s/it]
                                                           
{'loss': 0.625, 'learning_rate': 0.00014558619695344638, 'epoch': 7.77}

 65%|██████▍   | 18197/28080 [35:58:13<19:25:29,  7.08s/it]
 65%|██████▍   | 18198/28080 [35:58:20<19:30:06,  7.10s/it]
                                                           
{'loss': 0.6031, 'learning_rate': 0.0001455599973630085, 'epoch': 7.77}

 65%|██████▍   | 18198/28080 [35:58:20<19:30:06,  7.10s/it]
 65%|██████▍   | 18199/28080 [35:58:27<19:29:01,  7.10s/it]
                                                           
{'loss': 0.6143, 'learning_rate': 0.00014553379916203724, 'epoch': 7.77}

 65%|██████▍   | 18199/28080 [35:58:27<19:29:01,  7.10s/it]
 65%|██████▍   | 18200/28080 [35:58:35<19:33:34,  7.13s/it]
                                                           
{'loss': 0.6015, 'learning_rate': 0.00014550760235088097, 'epoch': 7.77}

 65%|██████▍   | 18200/28080 [35:58:35<19:33:34,  7.13s/it]
 65%|██████▍   | 18201/28080 [35:58:42<19:29:30,  7.10s/it]
                                                           
{'loss': 0.6137, 'learning_rate': 0.0001454814069298883, 'epoch': 7.78}

 65%|██████▍   | 18201/28080 [35:58:42<19:29:30,  7.10s/it]
 65%|██████▍   | 18202/28080 [35:58:49<19:32:33,  7.12s/it]
                                                           
{'loss': 0.6252, 'learning_rate': 0.00014545521289940756, 'epoch': 7.78}

 65%|██████▍   | 18202/28080 [35:58:49<19:32:33,  7.12s/it]
 65%|██████▍   | 18203/28080 [35:58:56<19:30:33,  7.11s/it]
                                                           
{'loss': 0.6289, 'learning_rate': 0.00014542902025978743, 'epoch': 7.78}

 65%|██████▍   | 18203/28080 [35:58:56<19:30:33,  7.11s/it]
 65%|██████▍   | 18204/28080 [35:59:03<19:28:12,  7.10s/it]
                                                           
{'loss': 0.6042, 'learning_rate': 0.00014540282901137633, 'epoch': 7.78}

 65%|██████▍   | 18204/28080 [35:59:03<19:28:12,  7.10s/it]
 65%|██████▍   | 18205/28080 [35:59:10<19:34:43,  7.14s/it]
                                                           
{'loss': 0.6112, 'learning_rate': 0.00014537663915452267, 'epoch': 7.78}

 65%|██████▍   | 18205/28080 [35:59:10<19:34:43,  7.14s/it]
 65%|██████▍   | 18206/28080 [35:59:17<19:33:40,  7.13s/it]
                                                           
{'loss': 0.5945, 'learning_rate': 0.0001453504506895748, 'epoch': 7.78}

 65%|██████▍   | 18206/28080 [35:59:17<19:33:40,  7.13s/it]
 65%|██████▍   | 18207/28080 [35:59:24<19:31:39,  7.12s/it]
                                                           
{'loss': 0.6088, 'learning_rate': 0.00014532426361688134, 'epoch': 7.78}

 65%|██████▍   | 18207/28080 [35:59:24<19:31:39,  7.12s/it]
 65%|██████▍   | 18208/28080 [35:59:31<19:32:09,  7.12s/it]
                                                           
{'loss': 0.6153, 'learning_rate': 0.00014529807793679046, 'epoch': 7.78}

 65%|██████▍   | 18208/28080 [35:59:32<19:32:09,  7.12s/it]
 65%|██████▍   | 18209/28080 [35:59:39<19:29:43,  7.11s/it]
                                                           
{'loss': 0.6118, 'learning_rate': 0.00014527189364965082, 'epoch': 7.78}

 65%|██████▍   | 18209/28080 [35:59:39<19:29:43,  7.11s/it]
 65%|██████▍   | 18210/28080 [35:59:46<19:32:30,  7.13s/it]
                                                           
{'loss': 0.6228, 'learning_rate': 0.0001452457107558104, 'epoch': 7.78}

 65%|██████▍   | 18210/28080 [35:59:46<19:32:30,  7.13s/it]
 65%|██████▍   | 18211/28080 [35:59:53<19:26:19,  7.09s/it]
                                                           
{'loss': 0.6318, 'learning_rate': 0.00014521952925561783, 'epoch': 7.78}

 65%|██████▍   | 18211/28080 [35:59:53<19:26:19,  7.09s/it]
 65%|██████▍   | 18212/28080 [36:00:00<19:24:40,  7.08s/it]
                                                           
{'loss': 0.6158, 'learning_rate': 0.00014519334914942124, 'epoch': 7.78}

 65%|██████▍   | 18212/28080 [36:00:00<19:24:40,  7.08s/it]
 65%|██████▍   | 18213/28080 [36:00:07<19:24:07,  7.08s/it]
                                                           
{'loss': 0.6283, 'learning_rate': 0.00014516717043756912, 'epoch': 7.78}

 65%|██████▍   | 18213/28080 [36:00:07<19:24:07,  7.08s/it]
 65%|██████▍   | 18214/28080 [36:00:14<19:26:00,  7.09s/it]
                                                           
{'loss': 0.6087, 'learning_rate': 0.0001451409931204096, 'epoch': 7.78}

 65%|██████▍   | 18214/28080 [36:00:14<19:26:00,  7.09s/it]
 65%|██████▍   | 18215/28080 [36:00:21<19:28:22,  7.11s/it]
                                                           
{'loss': 0.6019, 'learning_rate': 0.00014511481719829103, 'epoch': 7.78}

 65%|██████▍   | 18215/28080 [36:00:21<19:28:22,  7.11s/it]
 65%|██████▍   | 18216/28080 [36:00:28<19:32:33,  7.13s/it]
                                                           
{'loss': 0.6392, 'learning_rate': 0.0001450886426715615, 'epoch': 7.78}

 65%|██████▍   | 18216/28080 [36:00:28<19:32:33,  7.13s/it]
 65%|██████▍   | 18217/28080 [36:00:35<19:32:12,  7.13s/it]
                                                           
{'loss': 0.6083, 'learning_rate': 0.00014506246954056946, 'epoch': 7.78}

 65%|██████▍   | 18217/28080 [36:00:35<19:32:12,  7.13s/it]
 65%|██████▍   | 18218/28080 [36:00:42<19:25:30,  7.09s/it]
                                                           
{'loss': 0.6098, 'learning_rate': 0.000145036297805663, 'epoch': 7.78}

 65%|██████▍   | 18218/28080 [36:00:42<19:25:30,  7.09s/it]
 65%|██████▍   | 18219/28080 [36:00:50<19:24:53,  7.09s/it]
                                                           
{'loss': 0.6151, 'learning_rate': 0.0001450101274671903, 'epoch': 7.78}

 65%|██████▍   | 18219/28080 [36:00:50<19:24:53,  7.09s/it]
 65%|██████▍   | 18220/28080 [36:00:57<19:29:49,  7.12s/it]
                                                           
{'loss': 0.6265, 'learning_rate': 0.00014498395852549956, 'epoch': 7.78}

 65%|██████▍   | 18220/28080 [36:00:57<19:29:49,  7.12s/it]
 65%|██████▍   | 18221/28080 [36:01:04<19:28:04,  7.11s/it]
                                                           
{'loss': 0.6096, 'learning_rate': 0.00014495779098093882, 'epoch': 7.78}

 65%|██████▍   | 18221/28080 [36:01:04<19:28:04,  7.11s/it]
 65%|██████▍   | 18222/28080 [36:01:11<19:32:30,  7.14s/it]
                                                           
{'loss': 0.6167, 'learning_rate': 0.00014493162483385637, 'epoch': 7.78}

 65%|██████▍   | 18222/28080 [36:01:11<19:32:30,  7.14s/it]
 65%|██████▍   | 18223/28080 [36:01:18<19:31:59,  7.13s/it]
                                                           
{'loss': 0.5968, 'learning_rate': 0.00014490546008460027, 'epoch': 7.78}

 65%|██████▍   | 18223/28080 [36:01:18<19:31:59,  7.13s/it]
 65%|██████▍   | 18224/28080 [36:01:25<19:28:42,  7.11s/it]
                                                           
{'loss': 0.6149, 'learning_rate': 0.00014487929673351864, 'epoch': 7.79}

 65%|██████▍   | 18224/28080 [36:01:25<19:28:42,  7.11s/it]
 65%|██████▍   | 18225/28080 [36:01:32<19:26:02,  7.10s/it]
                                                           
{'loss': 0.6244, 'learning_rate': 0.0001448531347809594, 'epoch': 7.79}

 65%|██████▍   | 18225/28080 [36:01:32<19:26:02,  7.10s/it]
 65%|██████▍   | 18226/28080 [36:01:39<19:28:55,  7.12s/it]
                                                           
{'loss': 0.6309, 'learning_rate': 0.00014482697422727082, 'epoch': 7.79}

 65%|██████▍   | 18226/28080 [36:01:39<19:28:55,  7.12s/it]
 65%|██████▍   | 18227/28080 [36:01:46<19:25:57,  7.10s/it]
                                                           
{'loss': 0.6198, 'learning_rate': 0.00014480081507280075, 'epoch': 7.79}

 65%|██████▍   | 18227/28080 [36:01:47<19:25:57,  7.10s/it]
 65%|██████▍   | 18228/28080 [36:01:54<19:29:20,  7.12s/it]
                                                           
{'loss': 0.6108, 'learning_rate': 0.00014477465731789745, 'epoch': 7.79}

 65%|██████▍   | 18228/28080 [36:01:54<19:29:20,  7.12s/it]
 65%|██████▍   | 18229/28080 [36:02:01<19:28:40,  7.12s/it]
                                                           
{'loss': 0.64, 'learning_rate': 0.00014474850096290865, 'epoch': 7.79}

 65%|██████▍   | 18229/28080 [36:02:01<19:28:40,  7.12s/it]
 65%|██████▍   | 18230/28080 [36:02:08<19:27:20,  7.11s/it]
                                                           
{'loss': 0.6209, 'learning_rate': 0.00014472234600818257, 'epoch': 7.79}

 65%|██████▍   | 18230/28080 [36:02:08<19:27:20,  7.11s/it]
 65%|██████▍   | 18231/28080 [36:02:15<19:27:15,  7.11s/it]
                                                           
{'loss': 0.5927, 'learning_rate': 0.00014469619245406694, 'epoch': 7.79}

 65%|██████▍   | 18231/28080 [36:02:15<19:27:15,  7.11s/it]
 65%|██████▍   | 18232/28080 [36:02:22<19:27:57,  7.12s/it]
                                                           
{'loss': 0.6088, 'learning_rate': 0.00014467004030090992, 'epoch': 7.79}

 65%|██████▍   | 18232/28080 [36:02:22<19:27:57,  7.12s/it]
 65%|██████▍   | 18233/28080 [36:02:29<19:28:23,  7.12s/it]
                                                           
{'loss': 0.5977, 'learning_rate': 0.00014464388954905938, 'epoch': 7.79}

 65%|██████▍   | 18233/28080 [36:02:29<19:28:23,  7.12s/it]
 65%|██████▍   | 18234/28080 [36:02:36<19:27:29,  7.11s/it]
                                                           
{'loss': 0.6083, 'learning_rate': 0.0001446177401988632, 'epoch': 7.79}

 65%|██████▍   | 18234/28080 [36:02:36<19:27:29,  7.11s/it]
 65%|██████▍   | 18235/28080 [36:02:44<19:32:43,  7.15s/it]
                                                           
{'loss': 0.6128, 'learning_rate': 0.00014459159225066915, 'epoch': 7.79}

 65%|██████▍   | 18235/28080 [36:02:44<19:32:43,  7.15s/it]
 65%|██████▍   | 18236/28080 [36:02:51<19:33:35,  7.15s/it]
                                                           
{'loss': 0.6052, 'learning_rate': 0.00014456544570482532, 'epoch': 7.79}

 65%|██████▍   | 18236/28080 [36:02:51<19:33:35,  7.15s/it]
 65%|██████▍   | 18237/28080 [36:02:58<19:28:54,  7.13s/it]
                                                           
{'loss': 0.6111, 'learning_rate': 0.00014453930056167947, 'epoch': 7.79}

 65%|██████▍   | 18237/28080 [36:02:58<19:28:54,  7.13s/it]
 65%|██████▍   | 18238/28080 [36:03:05<19:34:49,  7.16s/it]
                                                           
{'loss': 0.6, 'learning_rate': 0.00014451315682157946, 'epoch': 7.79}

 65%|██████▍   | 18238/28080 [36:03:05<19:34:49,  7.16s/it]
 65%|██████▍   | 18239/28080 [36:03:12<19:38:55,  7.19s/it]
                                                           
{'loss': 0.5617, 'learning_rate': 0.0001444870144848729, 'epoch': 7.79}

 65%|██████▍   | 18239/28080 [36:03:12<19:38:55,  7.19s/it]
 65%|██████▍   | 18240/28080 [36:03:19<19:33:04,  7.15s/it]
                                                           
{'loss': 0.5965, 'learning_rate': 0.00014446087355190793, 'epoch': 7.79}

 65%|██████▍   | 18240/28080 [36:03:19<19:33:04,  7.15s/it]
 65%|██████▍   | 18241/28080 [36:03:27<19:34:59,  7.17s/it]
                                                           
{'loss': 0.6206, 'learning_rate': 0.00014443473402303203, 'epoch': 7.79}

 65%|██████▍   | 18241/28080 [36:03:27<19:34:59,  7.17s/it]
 65%|██████▍   | 18242/28080 [36:03:34<19:34:33,  7.16s/it]
                                                           
{'loss': 0.6183, 'learning_rate': 0.00014440859589859317, 'epoch': 7.79}

 65%|██████▍   | 18242/28080 [36:03:34<19:34:33,  7.16s/it]
 65%|██████▍   | 18243/28080 [36:03:41<19:32:47,  7.15s/it]
                                                           
{'loss': 0.6035, 'learning_rate': 0.00014438245917893904, 'epoch': 7.79}

 65%|██████▍   | 18243/28080 [36:03:41<19:32:47,  7.15s/it]
 65%|██████▍   | 18244/28080 [36:03:48<19:29:18,  7.13s/it]
                                                           
{'loss': 0.6095, 'learning_rate': 0.00014435632386441732, 'epoch': 7.79}

 65%|██████▍   | 18244/28080 [36:03:48<19:29:18,  7.13s/it]
 65%|██████▍   | 18245/28080 [36:03:55<19:32:53,  7.16s/it]
                                                           
{'loss': 0.612, 'learning_rate': 0.00014433018995537575, 'epoch': 7.79}

 65%|██████▍   | 18245/28080 [36:03:55<19:32:53,  7.16s/it]
 65%|██████▍   | 18246/28080 [36:04:02<19:32:08,  7.15s/it]
                                                           
{'loss': 0.6049, 'learning_rate': 0.00014430405745216186, 'epoch': 7.79}

 65%|██████▍   | 18246/28080 [36:04:02<19:32:08,  7.15s/it]
 65%|██████▍   | 18247/28080 [36:04:09<19:33:36,  7.16s/it]
                                                           
{'loss': 0.6121, 'learning_rate': 0.00014427792635512355, 'epoch': 7.79}

 65%|██████▍   | 18247/28080 [36:04:09<19:33:36,  7.16s/it]
 65%|██████▍   | 18248/28080 [36:04:17<19:27:57,  7.13s/it]
                                                           
{'loss': 0.6095, 'learning_rate': 0.00014425179666460836, 'epoch': 7.8}

 65%|██████▍   | 18248/28080 [36:04:17<19:27:57,  7.13s/it]
 65%|██████▍   | 18249/28080 [36:04:24<19:28:13,  7.13s/it]
                                                           
{'loss': 0.6087, 'learning_rate': 0.00014422566838096393, 'epoch': 7.8}

 65%|██████▍   | 18249/28080 [36:04:24<19:28:13,  7.13s/it]
 65%|██████▍   | 18250/28080 [36:04:31<19:28:14,  7.13s/it]
                                                           
{'loss': 0.596, 'learning_rate': 0.00014419954150453776, 'epoch': 7.8}

 65%|██████▍   | 18250/28080 [36:04:31<19:28:14,  7.13s/it]
 65%|██████▍   | 18251/28080 [36:04:38<19:29:23,  7.14s/it]
                                                           
{'loss': 0.5843, 'learning_rate': 0.00014417341603567763, 'epoch': 7.8}

 65%|██████▍   | 18251/28080 [36:04:38<19:29:23,  7.14s/it]
 65%|██████▌   | 18252/28080 [36:04:45<19:30:44,  7.15s/it]
                                                           
{'loss': 0.595, 'learning_rate': 0.00014414729197473103, 'epoch': 7.8}

 65%|██████▌   | 18252/28080 [36:04:45<19:30:44,  7.15s/it]
 65%|██████▌   | 18253/28080 [36:04:52<19:26:37,  7.12s/it]
                                                           
{'loss': 0.6173, 'learning_rate': 0.00014412116932204552, 'epoch': 7.8}

 65%|██████▌   | 18253/28080 [36:04:52<19:26:37,  7.12s/it]
 65%|██████▌   | 18254/28080 [36:04:59<19:26:30,  7.12s/it]
                                                           
{'loss': 0.6166, 'learning_rate': 0.00014409504807796854, 'epoch': 7.8}

 65%|██████▌   | 18254/28080 [36:04:59<19:26:30,  7.12s/it]
 65%|██████▌   | 18255/28080 [36:05:06<19:26:08,  7.12s/it]
                                                           
{'loss': 0.6161, 'learning_rate': 0.00014406892824284773, 'epoch': 7.8}

 65%|██████▌   | 18255/28080 [36:05:06<19:26:08,  7.12s/it]
 65%|██████▌   | 18256/28080 [36:05:13<19:23:13,  7.10s/it]
                                                           
{'loss': 0.6251, 'learning_rate': 0.0001440428098170305, 'epoch': 7.8}

 65%|██████▌   | 18256/28080 [36:05:13<19:23:13,  7.10s/it]
 65%|██████▌   | 18257/28080 [36:05:21<19:23:17,  7.11s/it]
                                                           
{'loss': 0.5983, 'learning_rate': 0.00014401669280086454, 'epoch': 7.8}

 65%|██████▌   | 18257/28080 [36:05:21<19:23:17,  7.11s/it]
 65%|██████▌   | 18258/28080 [36:05:28<19:25:27,  7.12s/it]
                                                           
{'loss': 0.5964, 'learning_rate': 0.00014399057719469697, 'epoch': 7.8}

 65%|██████▌   | 18258/28080 [36:05:28<19:25:27,  7.12s/it]
 65%|██████▌   | 18259/28080 [36:05:35<19:23:38,  7.11s/it]
                                                           
{'loss': 0.6155, 'learning_rate': 0.0001439644629988755, 'epoch': 7.8}

 65%|██████▌   | 18259/28080 [36:05:35<19:23:38,  7.11s/it]
 65%|██████▌   | 18260/28080 [36:05:42<19:22:12,  7.10s/it]
                                                           
{'loss': 0.6099, 'learning_rate': 0.00014393835021374736, 'epoch': 7.8}

 65%|██████▌   | 18260/28080 [36:05:42<19:22:12,  7.10s/it]
 65%|██████▌   | 18261/28080 [36:05:49<19:20:15,  7.09s/it]
                                                           
{'loss': 0.6253, 'learning_rate': 0.00014391223883966015, 'epoch': 7.8}

 65%|██████▌   | 18261/28080 [36:05:49<19:20:15,  7.09s/it]
 65%|██████▌   | 18262/28080 [36:05:56<19:29:13,  7.15s/it]
                                                           
{'loss': 0.5947, 'learning_rate': 0.00014388612887696116, 'epoch': 7.8}

 65%|██████▌   | 18262/28080 [36:05:56<19:29:13,  7.15s/it]
 65%|██████▌   | 18263/28080 [36:06:03<19:23:41,  7.11s/it]
                                                           
{'loss': 0.6067, 'learning_rate': 0.00014386002032599774, 'epoch': 7.8}

 65%|██████▌   | 18263/28080 [36:06:03<19:23:41,  7.11s/it]
 65%|██████▌   | 18264/28080 [36:06:10<19:20:47,  7.10s/it]
                                                           
{'loss': 0.6086, 'learning_rate': 0.00014383391318711713, 'epoch': 7.8}

 65%|██████▌   | 18264/28080 [36:06:10<19:20:47,  7.10s/it]
 65%|██████▌   | 18265/28080 [36:06:18<19:25:41,  7.13s/it]
                                                           
{'loss': 0.5967, 'learning_rate': 0.00014380780746066693, 'epoch': 7.8}

 65%|██████▌   | 18265/28080 [36:06:18<19:25:41,  7.13s/it]
 65%|██████▌   | 18266/28080 [36:06:25<19:24:33,  7.12s/it]
                                                           
{'loss': 0.623, 'learning_rate': 0.0001437817031469943, 'epoch': 7.8}

 65%|██████▌   | 18266/28080 [36:06:25<19:24:33,  7.12s/it]
 65%|██████▌   | 18267/28080 [36:06:32<19:27:11,  7.14s/it]
                                                           
{'loss': 0.6076, 'learning_rate': 0.0001437556002464465, 'epoch': 7.8}

 65%|██████▌   | 18267/28080 [36:06:32<19:27:11,  7.14s/it]
 65%|██████▌   | 18268/28080 [36:06:39<19:29:38,  7.15s/it]
                                                           
{'loss': 0.616, 'learning_rate': 0.00014372949875937074, 'epoch': 7.8}

 65%|██████▌   | 18268/28080 [36:06:39<19:29:38,  7.15s/it]
 65%|██████▌   | 18269/28080 [36:06:46<19:23:30,  7.12s/it]
                                                           
{'loss': 0.5966, 'learning_rate': 0.0001437033986861145, 'epoch': 7.8}

 65%|██████▌   | 18269/28080 [36:06:46<19:23:30,  7.12s/it]
 65%|██████▌   | 18270/28080 [36:06:53<19:19:45,  7.09s/it]
                                                           
{'loss': 0.6026, 'learning_rate': 0.00014367730002702483, 'epoch': 7.8}

 65%|██████▌   | 18270/28080 [36:06:53<19:19:45,  7.09s/it]
 65%|██████▌   | 18271/28080 [36:07:00<19:19:32,  7.09s/it]
                                                           
{'loss': 0.6006, 'learning_rate': 0.000143651202782449, 'epoch': 7.81}

 65%|██████▌   | 18271/28080 [36:07:00<19:19:32,  7.09s/it]
 65%|██████▌   | 18272/28080 [36:07:07<19:25:25,  7.13s/it]
                                                           
{'loss': 0.6376, 'learning_rate': 0.00014362510695273422, 'epoch': 7.81}

 65%|██████▌   | 18272/28080 [36:07:07<19:25:25,  7.13s/it]
 65%|██████▌   | 18273/28080 [36:07:14<19:21:40,  7.11s/it]
                                                           
{'loss': 0.6095, 'learning_rate': 0.00014359901253822754, 'epoch': 7.81}

 65%|██████▌   | 18273/28080 [36:07:14<19:21:40,  7.11s/it]
 65%|██████▌   | 18274/28080 [36:07:21<19:18:32,  7.09s/it]
                                                           
{'loss': 0.6181, 'learning_rate': 0.00014357291953927636, 'epoch': 7.81}

 65%|██████▌   | 18274/28080 [36:07:21<19:18:32,  7.09s/it]
 65%|██████▌   | 18275/28080 [36:07:29<19:22:17,  7.11s/it]
                                                           
{'loss': 0.5975, 'learning_rate': 0.00014354682795622757, 'epoch': 7.81}

 65%|██████▌   | 18275/28080 [36:07:29<19:22:17,  7.11s/it]
 65%|██████▌   | 18276/28080 [36:07:36<19:23:19,  7.12s/it]
                                                           
{'loss': 0.6082, 'learning_rate': 0.0001435207377894286, 'epoch': 7.81}

 65%|██████▌   | 18276/28080 [36:07:36<19:23:19,  7.12s/it]
 65%|██████▌   | 18277/28080 [36:07:43<19:22:05,  7.11s/it]
                                                           
{'loss': 0.5991, 'learning_rate': 0.00014349464903922618, 'epoch': 7.81}

 65%|██████▌   | 18277/28080 [36:07:43<19:22:05,  7.11s/it]
 65%|██████▌   | 18278/28080 [36:07:50<19:21:31,  7.11s/it]
                                                           
{'loss': 0.624, 'learning_rate': 0.00014346856170596766, 'epoch': 7.81}

 65%|██████▌   | 18278/28080 [36:07:50<19:21:31,  7.11s/it]
 65%|██████▌   | 18279/28080 [36:07:57<19:18:17,  7.09s/it]
                                                           
{'loss': 0.6354, 'learning_rate': 0.00014344247578999998, 'epoch': 7.81}

 65%|██████▌   | 18279/28080 [36:07:57<19:18:17,  7.09s/it]
 65%|██████▌   | 18280/28080 [36:08:04<19:21:29,  7.11s/it]
                                                           
{'loss': 0.6094, 'learning_rate': 0.00014341639129167029, 'epoch': 7.81}

 65%|██████▌   | 18280/28080 [36:08:04<19:21:29,  7.11s/it]
 65%|██████▌   | 18281/28080 [36:08:11<19:18:13,  7.09s/it]
                                                           
{'loss': 0.6066, 'learning_rate': 0.00014339030821132554, 'epoch': 7.81}

 65%|██████▌   | 18281/28080 [36:08:11<19:18:13,  7.09s/it]
 65%|██████▌   | 18282/28080 [36:08:18<19:20:07,  7.10s/it]
                                                           
{'loss': 0.6072, 'learning_rate': 0.00014336422654931278, 'epoch': 7.81}

 65%|██████▌   | 18282/28080 [36:08:18<19:20:07,  7.10s/it]
 65%|██████▌   | 18283/28080 [36:08:25<19:19:38,  7.10s/it]
                                                           
{'loss': 0.6069, 'learning_rate': 0.00014333814630597885, 'epoch': 7.81}

 65%|██████▌   | 18283/28080 [36:08:25<19:19:38,  7.10s/it]
 65%|██████▌   | 18284/28080 [36:08:33<19:25:34,  7.14s/it]
                                                           
{'loss': 0.6156, 'learning_rate': 0.00014331206748167098, 'epoch': 7.81}

 65%|██████▌   | 18284/28080 [36:08:33<19:25:34,  7.14s/it]
 65%|██████▌   | 18285/28080 [36:08:40<19:23:19,  7.13s/it]
                                                           
{'loss': 0.6377, 'learning_rate': 0.00014328599007673598, 'epoch': 7.81}

 65%|██████▌   | 18285/28080 [36:08:40<19:23:19,  7.13s/it]
 65%|██████▌   | 18286/28080 [36:08:47<19:23:00,  7.12s/it]
                                                           
{'loss': 0.6382, 'learning_rate': 0.00014325991409152078, 'epoch': 7.81}

 65%|██████▌   | 18286/28080 [36:08:47<19:23:00,  7.12s/it]
 65%|██████▌   | 18287/28080 [36:08:54<19:23:06,  7.13s/it]
                                                           
{'loss': 0.6266, 'learning_rate': 0.0001432338395263722, 'epoch': 7.81}

 65%|██████▌   | 18287/28080 [36:08:54<19:23:06,  7.13s/it]
 65%|██████▌   | 18288/28080 [36:09:01<19:20:11,  7.11s/it]
                                                           
{'loss': 0.6044, 'learning_rate': 0.0001432077663816374, 'epoch': 7.81}

 65%|██████▌   | 18288/28080 [36:09:01<19:20:11,  7.11s/it]
 65%|██████▌   | 18289/28080 [36:09:08<19:23:48,  7.13s/it]
                                                           
{'loss': 0.6338, 'learning_rate': 0.00014318169465766292, 'epoch': 7.81}

 65%|██████▌   | 18289/28080 [36:09:08<19:23:48,  7.13s/it]
 65%|██████▌   | 18290/28080 [36:09:15<19:24:58,  7.14s/it]
                                                           
{'loss': 0.6055, 'learning_rate': 0.000143155624354796, 'epoch': 7.81}

 65%|██████▌   | 18290/28080 [36:09:15<19:24:58,  7.14s/it]
 65%|██████▌   | 18291/28080 [36:09:22<19:17:17,  7.09s/it]
                                                           
{'loss': 0.6213, 'learning_rate': 0.00014312955547338314, 'epoch': 7.81}

 65%|██████▌   | 18291/28080 [36:09:22<19:17:17,  7.09s/it]
 65%|██████▌   | 18292/28080 [36:09:30<19:24:08,  7.14s/it]
                                                           
{'loss': 0.6068, 'learning_rate': 0.00014310348801377132, 'epoch': 7.81}

 65%|██████▌   | 18292/28080 [36:09:30<19:24:08,  7.14s/it]
 65%|██████▌   | 18293/28080 [36:09:37<19:25:42,  7.15s/it]
                                                           
{'loss': 0.6013, 'learning_rate': 0.00014307742197630725, 'epoch': 7.81}

 65%|██████▌   | 18293/28080 [36:09:37<19:25:42,  7.15s/it]
 65%|██████▌   | 18294/28080 [36:09:44<19:24:11,  7.14s/it]
                                                           
{'loss': 0.5916, 'learning_rate': 0.00014305135736133786, 'epoch': 7.82}

 65%|██████▌   | 18294/28080 [36:09:44<19:24:11,  7.14s/it]
 65%|██████▌   | 18295/28080 [36:09:51<19:19:17,  7.11s/it]
                                                           
{'loss': 0.626, 'learning_rate': 0.00014302529416920985, 'epoch': 7.82}

 65%|██████▌   | 18295/28080 [36:09:51<19:19:17,  7.11s/it]
 65%|██████▌   | 18296/28080 [36:09:58<19:19:42,  7.11s/it]
                                                           
{'loss': 0.6188, 'learning_rate': 0.00014299923240026992, 'epoch': 7.82}

 65%|██████▌   | 18296/28080 [36:09:58<19:19:42,  7.11s/it]
 65%|██████▌   | 18297/28080 [36:10:05<19:20:34,  7.12s/it]
                                                           
{'loss': 0.6012, 'learning_rate': 0.0001429731720548648, 'epoch': 7.82}

 65%|██████▌   | 18297/28080 [36:10:05<19:20:34,  7.12s/it]
 65%|██████▌   | 18298/28080 [36:10:12<19:23:41,  7.14s/it]
                                                           
{'loss': 0.5941, 'learning_rate': 0.00014294711313334117, 'epoch': 7.82}

 65%|██████▌   | 18298/28080 [36:10:12<19:23:41,  7.14s/it]
 65%|██████▌   | 18299/28080 [36:10:20<19:21:34,  7.13s/it]
                                                           
{'loss': 0.6128, 'learning_rate': 0.00014292105563604583, 'epoch': 7.82}

 65%|██████▌   | 18299/28080 [36:10:20<19:21:34,  7.13s/it]
 65%|██████▌   | 18300/28080 [36:10:27<19:20:07,  7.12s/it]
                                                           
{'loss': 0.6342, 'learning_rate': 0.00014289499956332536, 'epoch': 7.82}

 65%|██████▌   | 18300/28080 [36:10:27<19:20:07,  7.12s/it]
 65%|██████▌   | 18301/28080 [36:10:34<19:15:35,  7.09s/it]
                                                           
{'loss': 0.6414, 'learning_rate': 0.00014286894491552643, 'epoch': 7.82}

 65%|██████▌   | 18301/28080 [36:10:34<19:15:35,  7.09s/it]
 65%|██████▌   | 18302/28080 [36:10:41<19:20:32,  7.12s/it]
                                                           
{'loss': 0.6108, 'learning_rate': 0.00014284289169299558, 'epoch': 7.82}

 65%|██████▌   | 18302/28080 [36:10:41<19:20:32,  7.12s/it]
 65%|██████▌   | 18303/28080 [36:10:48<19:12:17,  7.07s/it]
                                                           
{'loss': 0.6217, 'learning_rate': 0.00014281683989607962, 'epoch': 7.82}

 65%|██████▌   | 18303/28080 [36:10:48<19:12:17,  7.07s/it]
 65%|██████▌   | 18304/28080 [36:10:55<19:16:05,  7.10s/it]
                                                           
{'loss': 0.5881, 'learning_rate': 0.00014279078952512492, 'epoch': 7.82}

 65%|██████▌   | 18304/28080 [36:10:55<19:16:05,  7.10s/it]
 65%|██████▌   | 18305/28080 [36:11:02<19:11:20,  7.07s/it]
                                                           
{'loss': 0.5735, 'learning_rate': 0.00014276474058047835, 'epoch': 7.82}

 65%|██████▌   | 18305/28080 [36:11:02<19:11:20,  7.07s/it]
 65%|██████▌   | 18306/28080 [36:11:09<19:11:11,  7.07s/it]
                                                           
{'loss': 0.6202, 'learning_rate': 0.00014273869306248606, 'epoch': 7.82}

 65%|██████▌   | 18306/28080 [36:11:09<19:11:11,  7.07s/it]
 65%|██████▌   | 18307/28080 [36:11:16<19:10:11,  7.06s/it]
                                                           
{'loss': 0.6089, 'learning_rate': 0.00014271264697149493, 'epoch': 7.82}

 65%|██████▌   | 18307/28080 [36:11:16<19:10:11,  7.06s/it]
 65%|██████▌   | 18308/28080 [36:11:23<19:12:47,  7.08s/it]
                                                           
{'loss': 0.6185, 'learning_rate': 0.00014268660230785124, 'epoch': 7.82}

 65%|██████▌   | 18308/28080 [36:11:23<19:12:47,  7.08s/it]
 65%|██████▌   | 18309/28080 [36:11:30<19:19:13,  7.12s/it]
                                                           
{'loss': 0.6185, 'learning_rate': 0.00014266055907190172, 'epoch': 7.82}

 65%|██████▌   | 18309/28080 [36:11:30<19:19:13,  7.12s/it]
 65%|██████▌   | 18310/28080 [36:11:37<19:17:47,  7.11s/it]
                                                           
{'loss': 0.6102, 'learning_rate': 0.00014263451726399272, 'epoch': 7.82}

 65%|██████▌   | 18310/28080 [36:11:37<19:17:47,  7.11s/it]
 65%|██████▌   | 18311/28080 [36:11:45<19:17:20,  7.11s/it]
                                                           
{'loss': 0.6009, 'learning_rate': 0.0001426084768844707, 'epoch': 7.82}

 65%|██████▌   | 18311/28080 [36:11:45<19:17:20,  7.11s/it]
 65%|██████▌   | 18312/28080 [36:11:52<19:12:22,  7.08s/it]
                                                           
{'loss': 0.6217, 'learning_rate': 0.000142582437933682, 'epoch': 7.82}

 65%|██████▌   | 18312/28080 [36:11:52<19:12:22,  7.08s/it]
 65%|██████▌   | 18313/28080 [36:11:59<19:14:46,  7.09s/it]
                                                           
{'loss': 0.6081, 'learning_rate': 0.00014255640041197325, 'epoch': 7.82}

 65%|██████▌   | 18313/28080 [36:11:59<19:14:46,  7.09s/it]
 65%|██████▌   | 18314/28080 [36:12:06<19:16:03,  7.10s/it]
                                                           
{'loss': 0.6127, 'learning_rate': 0.00014253036431969074, 'epoch': 7.82}

 65%|██████▌   | 18314/28080 [36:12:06<19:16:03,  7.10s/it]
 65%|██████▌   | 18315/28080 [36:12:13<19:14:03,  7.09s/it]
                                                           
{'loss': 0.6093, 'learning_rate': 0.00014250432965718087, 'epoch': 7.82}

 65%|██████▌   | 18315/28080 [36:12:13<19:14:03,  7.09s/it]
 65%|██████▌   | 18316/28080 [36:12:20<19:13:45,  7.09s/it]
                                                           
{'loss': 0.6091, 'learning_rate': 0.0001424782964247899, 'epoch': 7.82}

 65%|██████▌   | 18316/28080 [36:12:20<19:13:45,  7.09s/it]
 65%|██████▌   | 18317/28080 [36:12:27<19:10:46,  7.07s/it]
                                                           
{'loss': 0.6279, 'learning_rate': 0.00014245226462286436, 'epoch': 7.82}

 65%|██████▌   | 18317/28080 [36:12:27<19:10:46,  7.07s/it]
 65%|██████▌   | 18318/28080 [36:12:34<19:06:59,  7.05s/it]
                                                           
{'loss': 0.6152, 'learning_rate': 0.00014242623425175042, 'epoch': 7.83}

 65%|██████▌   | 18318/28080 [36:12:34<19:06:59,  7.05s/it]
 65%|██████▌   | 18319/28080 [36:12:41<19:12:56,  7.09s/it]
                                                           
{'loss': 0.5976, 'learning_rate': 0.00014240020531179463, 'epoch': 7.83}

 65%|██████▌   | 18319/28080 [36:12:41<19:12:56,  7.09s/it]
 65%|██████▌   | 18320/28080 [36:12:48<19:13:09,  7.09s/it]
                                                           
{'loss': 0.6049, 'learning_rate': 0.000142374177803343, 'epoch': 7.83}

 65%|██████▌   | 18320/28080 [36:12:48<19:13:09,  7.09s/it]
 65%|██████▌   | 18321/28080 [36:12:55<19:13:46,  7.09s/it]
                                                           
{'loss': 0.6154, 'learning_rate': 0.0001423481517267418, 'epoch': 7.83}

 65%|██████▌   | 18321/28080 [36:12:55<19:13:46,  7.09s/it]
 65%|██████▌   | 18322/28080 [36:13:03<19:15:43,  7.11s/it]
                                                           
{'loss': 0.6146, 'learning_rate': 0.0001423221270823375, 'epoch': 7.83}

 65%|██████▌   | 18322/28080 [36:13:03<19:15:43,  7.11s/it]
 65%|██████▌   | 18323/28080 [36:13:10<19:12:46,  7.09s/it]
                                                           
{'loss': 0.5973, 'learning_rate': 0.0001422961038704761, 'epoch': 7.83}

 65%|██████▌   | 18323/28080 [36:13:10<19:12:46,  7.09s/it]
 65%|██████▌   | 18324/28080 [36:13:17<19:16:49,  7.11s/it]
                                                           
{'loss': 0.6023, 'learning_rate': 0.00014227008209150417, 'epoch': 7.83}

 65%|██████▌   | 18324/28080 [36:13:17<19:16:49,  7.11s/it]
 65%|██████▌   | 18325/28080 [36:13:24<19:19:28,  7.13s/it]
                                                           
{'loss': 0.5998, 'learning_rate': 0.0001422440617457674, 'epoch': 7.83}

 65%|██████▌   | 18325/28080 [36:13:24<19:19:28,  7.13s/it]
 65%|██████▌   | 18326/28080 [36:13:31<19:20:03,  7.14s/it]
                                                           
{'loss': 0.5981, 'learning_rate': 0.00014221804283361233, 'epoch': 7.83}

 65%|██████▌   | 18326/28080 [36:13:31<19:20:03,  7.14s/it]
 65%|██████▌   | 18327/28080 [36:13:38<19:16:31,  7.11s/it]
                                                           
{'loss': 0.6145, 'learning_rate': 0.00014219202535538494, 'epoch': 7.83}

 65%|██████▌   | 18327/28080 [36:13:38<19:16:31,  7.11s/it]
 65%|██████▌   | 18328/28080 [36:13:45<19:15:48,  7.11s/it]
                                                           
{'loss': 0.5833, 'learning_rate': 0.00014216600931143153, 'epoch': 7.83}

 65%|██████▌   | 18328/28080 [36:13:45<19:15:48,  7.11s/it]
 65%|██████▌   | 18329/28080 [36:13:52<19:14:46,  7.11s/it]
                                                           
{'loss': 0.606, 'learning_rate': 0.0001421399947020981, 'epoch': 7.83}

 65%|██████▌   | 18329/28080 [36:13:52<19:14:46,  7.11s/it]
 65%|██████▌   | 18330/28080 [36:14:00<19:19:34,  7.14s/it]
                                                           
{'loss': 0.6114, 'learning_rate': 0.00014211398152773076, 'epoch': 7.83}

 65%|██████▌   | 18330/28080 [36:14:00<19:19:34,  7.14s/it]
 65%|██████▌   | 18331/28080 [36:14:07<19:22:40,  7.16s/it]
                                                           
{'loss': 0.6206, 'learning_rate': 0.00014208796978867552, 'epoch': 7.83}

 65%|██████▌   | 18331/28080 [36:14:07<19:22:40,  7.16s/it]
 65%|██████▌   | 18332/28080 [36:14:14<19:20:44,  7.14s/it]
                                                           
{'loss': 0.6168, 'learning_rate': 0.0001420619594852786, 'epoch': 7.83}

 65%|██████▌   | 18332/28080 [36:14:14<19:20:44,  7.14s/it]
 65%|██████▌   | 18333/28080 [36:14:21<19:22:47,  7.16s/it]
                                                           
{'loss': 0.598, 'learning_rate': 0.00014203595061788597, 'epoch': 7.83}

 65%|██████▌   | 18333/28080 [36:14:21<19:22:47,  7.16s/it]
 65%|██████▌   | 18334/28080 [36:14:28<19:15:41,  7.11s/it]
                                                           
{'loss': 0.6115, 'learning_rate': 0.00014200994318684364, 'epoch': 7.83}

 65%|██████▌   | 18334/28080 [36:14:28<19:15:41,  7.11s/it]
 65%|██████▌   | 18335/28080 [36:14:35<19:13:25,  7.10s/it]
                                                           
{'loss': 0.6354, 'learning_rate': 0.00014198393719249748, 'epoch': 7.83}

 65%|██████▌   | 18335/28080 [36:14:35<19:13:25,  7.10s/it]
 65%|██████▌   | 18336/28080 [36:14:42<19:10:44,  7.09s/it]
                                                           
{'loss': 0.5855, 'learning_rate': 0.00014195793263519372, 'epoch': 7.83}

 65%|██████▌   | 18336/28080 [36:14:42<19:10:44,  7.09s/it]
 65%|██████▌   | 18337/28080 [36:14:49<19:13:51,  7.11s/it]
                                                           
{'loss': 0.6065, 'learning_rate': 0.00014193192951527812, 'epoch': 7.83}

 65%|██████▌   | 18337/28080 [36:14:49<19:13:51,  7.11s/it]
 65%|██████▌   | 18338/28080 [36:14:56<19:13:06,  7.10s/it]
                                                           
{'loss': 0.624, 'learning_rate': 0.00014190592783309687, 'epoch': 7.83}

 65%|██████▌   | 18338/28080 [36:14:56<19:13:06,  7.10s/it]
 65%|██████▌   | 18339/28080 [36:15:04<19:16:08,  7.12s/it]
                                                           
{'loss': 0.5976, 'learning_rate': 0.00014187992758899558, 'epoch': 7.83}

 65%|██████▌   | 18339/28080 [36:15:04<19:16:08,  7.12s/it]
 65%|██████▌   | 18340/28080 [36:15:11<19:17:55,  7.13s/it]
                                                           
{'loss': 0.6079, 'learning_rate': 0.00014185392878332038, 'epoch': 7.83}

 65%|██████▌   | 18340/28080 [36:15:11<19:17:55,  7.13s/it]
 65%|██████▌   | 18341/28080 [36:15:18<19:19:36,  7.14s/it]
                                                           
{'loss': 0.6232, 'learning_rate': 0.00014182793141641697, 'epoch': 7.84}

 65%|██████▌   | 18341/28080 [36:15:18<19:19:36,  7.14s/it]
 65%|██████▌   | 18342/28080 [36:15:25<19:18:36,  7.14s/it]
                                                           
{'loss': 0.6054, 'learning_rate': 0.00014180193548863149, 'epoch': 7.84}

 65%|██████▌   | 18342/28080 [36:15:25<19:18:36,  7.14s/it]
 65%|██████▌   | 18343/28080 [36:15:32<19:17:40,  7.13s/it]
                                                           
{'loss': 0.6144, 'learning_rate': 0.0001417759410003096, 'epoch': 7.84}

 65%|██████▌   | 18343/28080 [36:15:32<19:17:40,  7.13s/it]
 65%|██████▌   | 18344/28080 [36:15:39<19:15:06,  7.12s/it]
                                                           
{'loss': 0.6161, 'learning_rate': 0.00014174994795179718, 'epoch': 7.84}

 65%|██████▌   | 18344/28080 [36:15:39<19:15:06,  7.12s/it]
 65%|██████▌   | 18345/28080 [36:15:46<19:16:58,  7.13s/it]
                                                           
{'loss': 0.5968, 'learning_rate': 0.00014172395634344005, 'epoch': 7.84}

 65%|██████▌   | 18345/28080 [36:15:46<19:16:58,  7.13s/it]
 65%|██████▌   | 18346/28080 [36:15:54<19:13:58,  7.11s/it]
                                                           
{'loss': 0.6224, 'learning_rate': 0.00014169796617558383, 'epoch': 7.84}

 65%|██████▌   | 18346/28080 [36:15:54<19:13:58,  7.11s/it]
 65%|██████▌   | 18347/28080 [36:16:01<19:14:44,  7.12s/it]
                                                           
{'loss': 0.6206, 'learning_rate': 0.0001416719774485746, 'epoch': 7.84}

 65%|██████▌   | 18347/28080 [36:16:01<19:14:44,  7.12s/it]
 65%|██████▌   | 18348/28080 [36:16:08<19:12:56,  7.11s/it]
                                                           
{'loss': 0.6071, 'learning_rate': 0.00014164599016275791, 'epoch': 7.84}

 65%|██████▌   | 18348/28080 [36:16:08<19:12:56,  7.11s/it]
 65%|██████▌   | 18349/28080 [36:16:15<19:10:42,  7.10s/it]
                                                           
{'loss': 0.6223, 'learning_rate': 0.00014162000431847954, 'epoch': 7.84}

 65%|██████▌   | 18349/28080 [36:16:15<19:10:42,  7.10s/it]
 65%|██████▌   | 18350/28080 [36:16:22<19:08:38,  7.08s/it]
                                                           
{'loss': 0.6187, 'learning_rate': 0.00014159401991608512, 'epoch': 7.84}

 65%|██████▌   | 18350/28080 [36:16:22<19:08:38,  7.08s/it]
 65%|██████▌   | 18351/28080 [36:16:29<19:06:40,  7.07s/it]
                                                           
{'loss': 0.6166, 'learning_rate': 0.0001415680369559205, 'epoch': 7.84}

 65%|██████▌   | 18351/28080 [36:16:29<19:06:40,  7.07s/it]
 65%|██████▌   | 18352/28080 [36:16:36<19:12:18,  7.11s/it]
                                                           
{'loss': 0.6115, 'learning_rate': 0.00014154205543833134, 'epoch': 7.84}

 65%|██████▌   | 18352/28080 [36:16:36<19:12:18,  7.11s/it]
 65%|██████▌   | 18353/28080 [36:16:43<19:16:37,  7.13s/it]
                                                           
{'loss': 0.6099, 'learning_rate': 0.0001415160753636632, 'epoch': 7.84}

 65%|██████▌   | 18353/28080 [36:16:43<19:16:37,  7.13s/it]
 65%|██████▌   | 18354/28080 [36:16:50<19:15:23,  7.13s/it]
                                                           
{'loss': 0.6203, 'learning_rate': 0.0001414900967322617, 'epoch': 7.84}

 65%|██████▌   | 18354/28080 [36:16:50<19:15:23,  7.13s/it]
 65%|██████▌   | 18355/28080 [36:16:58<19:16:16,  7.13s/it]
                                                           
{'loss': 0.6094, 'learning_rate': 0.00014146411954447257, 'epoch': 7.84}

 65%|██████▌   | 18355/28080 [36:16:58<19:16:16,  7.13s/it]
 65%|██████▌   | 18356/28080 [36:17:05<19:18:46,  7.15s/it]
                                                           
{'loss': 0.6277, 'learning_rate': 0.00014143814380064129, 'epoch': 7.84}

 65%|██████▌   | 18356/28080 [36:17:05<19:18:46,  7.15s/it]
 65%|██████▌   | 18357/28080 [36:17:12<19:16:24,  7.14s/it]
                                                           
{'loss': 0.6026, 'learning_rate': 0.00014141216950111358, 'epoch': 7.84}

 65%|██████▌   | 18357/28080 [36:17:12<19:16:24,  7.14s/it]
 65%|██████▌   | 18358/28080 [36:17:19<19:13:45,  7.12s/it]
                                                           
{'loss': 0.6151, 'learning_rate': 0.00014138619664623499, 'epoch': 7.84}

 65%|██████▌   | 18358/28080 [36:17:19<19:13:45,  7.12s/it]
 65%|██████▌   | 18359/28080 [36:17:26<19:13:40,  7.12s/it]
                                                           
{'loss': 0.6087, 'learning_rate': 0.00014136022523635093, 'epoch': 7.84}

 65%|██████▌   | 18359/28080 [36:17:26<19:13:40,  7.12s/it]
 65%|██████▌   | 18360/28080 [36:17:33<19:16:42,  7.14s/it]
                                                           
{'loss': 0.601, 'learning_rate': 0.00014133425527180693, 'epoch': 7.84}

 65%|██████▌   | 18360/28080 [36:17:33<19:16:42,  7.14s/it]
 65%|██████▌   | 18361/28080 [36:17:40<19:18:36,  7.15s/it]
                                                           
{'loss': 0.5972, 'learning_rate': 0.00014130828675294865, 'epoch': 7.84}

 65%|██████▌   | 18361/28080 [36:17:40<19:18:36,  7.15s/it]
 65%|██████▌   | 18362/28080 [36:17:47<19:13:09,  7.12s/it]
                                                           
{'loss': 0.6208, 'learning_rate': 0.00014128231968012152, 'epoch': 7.84}

 65%|██████▌   | 18362/28080 [36:17:47<19:13:09,  7.12s/it]
 65%|██████▌   | 18363/28080 [36:17:54<19:08:11,  7.09s/it]
                                                           
{'loss': 0.6394, 'learning_rate': 0.00014125635405367093, 'epoch': 7.84}

 65%|██████▌   | 18363/28080 [36:17:54<19:08:11,  7.09s/it]
 65%|██████▌   | 18364/28080 [36:18:02<19:10:15,  7.10s/it]
                                                           
{'loss': 0.6029, 'learning_rate': 0.00014123038987394227, 'epoch': 7.84}

 65%|██████▌   | 18364/28080 [36:18:02<19:10:15,  7.10s/it]
 65%|██████▌   | 18365/28080 [36:18:09<19:06:26,  7.08s/it]
                                                           
{'loss': 0.5991, 'learning_rate': 0.00014120442714128117, 'epoch': 7.85}

 65%|██████▌   | 18365/28080 [36:18:09<19:06:26,  7.08s/it]
 65%|██████▌   | 18366/28080 [36:18:16<19:08:19,  7.09s/it]
                                                           
{'loss': 0.6152, 'learning_rate': 0.00014117846585603284, 'epoch': 7.85}

 65%|██████▌   | 18366/28080 [36:18:16<19:08:19,  7.09s/it]
 65%|██████▌   | 18367/28080 [36:18:23<19:15:25,  7.14s/it]
                                                           
{'loss': 0.6291, 'learning_rate': 0.00014115250601854292, 'epoch': 7.85}

 65%|██████▌   | 18367/28080 [36:18:23<19:15:25,  7.14s/it]
 65%|██████▌   | 18368/28080 [36:18:30<19:17:25,  7.15s/it]
                                                           
{'loss': 0.6235, 'learning_rate': 0.00014112654762915645, 'epoch': 7.85}

 65%|██████▌   | 18368/28080 [36:18:30<19:17:25,  7.15s/it]
 65%|██████▌   | 18369/28080 [36:18:37<19:15:52,  7.14s/it]
                                                           
{'loss': 0.6325, 'learning_rate': 0.00014110059068821903, 'epoch': 7.85}

 65%|██████▌   | 18369/28080 [36:18:37<19:15:52,  7.14s/it]
 65%|██████▌   | 18370/28080 [36:18:45<19:19:52,  7.17s/it]
                                                           
{'loss': 0.62, 'learning_rate': 0.00014107463519607593, 'epoch': 7.85}

 65%|██████▌   | 18370/28080 [36:18:45<19:19:52,  7.17s/it]
 65%|██████▌   | 18371/28080 [36:18:52<19:18:32,  7.16s/it]
                                                           
{'loss': 0.6025, 'learning_rate': 0.0001410486811530723, 'epoch': 7.85}

 65%|██████▌   | 18371/28080 [36:18:52<19:18:32,  7.16s/it]
 65%|██████▌   | 18372/28080 [36:18:59<19:22:27,  7.18s/it]
                                                           
{'loss': 0.5939, 'learning_rate': 0.00014102272855955378, 'epoch': 7.85}

 65%|██████▌   | 18372/28080 [36:18:59<19:22:27,  7.18s/it]
 65%|██████▌   | 18373/28080 [36:19:06<19:21:07,  7.18s/it]
                                                           
{'loss': 0.6119, 'learning_rate': 0.00014099677741586525, 'epoch': 7.85}

 65%|██████▌   | 18373/28080 [36:19:06<19:21:07,  7.18s/it]
 65%|██████▌   | 18374/28080 [36:19:13<19:20:31,  7.17s/it]
                                                           
{'loss': 0.6208, 'learning_rate': 0.0001409708277223522, 'epoch': 7.85}

 65%|██████▌   | 18374/28080 [36:19:13<19:20:31,  7.17s/it]
 65%|██████▌   | 18375/28080 [36:19:20<19:16:53,  7.15s/it]
                                                           
{'loss': 0.6078, 'learning_rate': 0.00014094487947935975, 'epoch': 7.85}

 65%|██████▌   | 18375/28080 [36:19:20<19:16:53,  7.15s/it]
 65%|██████▌   | 18376/28080 [36:19:27<19:16:28,  7.15s/it]
                                                           
{'loss': 0.6243, 'learning_rate': 0.00014091893268723327, 'epoch': 7.85}

 65%|██████▌   | 18376/28080 [36:19:27<19:16:28,  7.15s/it]
 65%|██████▌   | 18377/28080 [36:19:35<19:15:46,  7.15s/it]
                                                           
{'loss': 0.6129, 'learning_rate': 0.00014089298734631784, 'epoch': 7.85}

 65%|██████▌   | 18377/28080 [36:19:35<19:15:46,  7.15s/it]
 65%|██████▌   | 18378/28080 [36:19:42<19:16:33,  7.15s/it]
                                                           
{'loss': 0.595, 'learning_rate': 0.00014086704345695866, 'epoch': 7.85}

 65%|██████▌   | 18378/28080 [36:19:42<19:16:33,  7.15s/it]
 65%|██████▌   | 18379/28080 [36:19:49<19:15:43,  7.15s/it]
                                                           
{'loss': 0.6187, 'learning_rate': 0.0001408411010195008, 'epoch': 7.85}

 65%|██████▌   | 18379/28080 [36:19:49<19:15:43,  7.15s/it]
 65%|██████▌   | 18380/28080 [36:19:56<19:07:46,  7.10s/it]
                                                           
{'loss': 0.5999, 'learning_rate': 0.00014081516003428956, 'epoch': 7.85}

 65%|██████▌   | 18380/28080 [36:19:56<19:07:46,  7.10s/it]
 65%|██████▌   | 18381/28080 [36:20:03<19:07:21,  7.10s/it]
                                                           
{'loss': 0.6181, 'learning_rate': 0.00014078922050166998, 'epoch': 7.85}

 65%|██████▌   | 18381/28080 [36:20:03<19:07:21,  7.10s/it]
 65%|██████▌   | 18382/28080 [36:20:10<19:02:51,  7.07s/it]
                                                           
{'loss': 0.6526, 'learning_rate': 0.00014076328242198716, 'epoch': 7.85}

 65%|██████▌   | 18382/28080 [36:20:10<19:02:51,  7.07s/it]
 65%|██████▌   | 18383/28080 [36:20:17<19:01:22,  7.06s/it]
                                                           
{'loss': 0.6099, 'learning_rate': 0.00014073734579558606, 'epoch': 7.85}

 65%|██████▌   | 18383/28080 [36:20:17<19:01:22,  7.06s/it]
 65%|██████▌   | 18384/28080 [36:20:24<19:06:29,  7.09s/it]
                                                           
{'loss': 0.6104, 'learning_rate': 0.00014071141062281195, 'epoch': 7.85}

 65%|██████▌   | 18384/28080 [36:20:24<19:06:29,  7.09s/it]
 65%|██████▌   | 18385/28080 [36:20:31<19:01:19,  7.06s/it]
                                                           
{'loss': 0.6302, 'learning_rate': 0.00014068547690400968, 'epoch': 7.85}

 65%|██████▌   | 18385/28080 [36:20:31<19:01:19,  7.06s/it]
 65%|██████▌   | 18386/28080 [36:20:38<19:04:44,  7.09s/it]
                                                           
{'loss': 0.6194, 'learning_rate': 0.00014065954463952457, 'epoch': 7.85}

 65%|██████▌   | 18386/28080 [36:20:38<19:04:44,  7.09s/it]
 65%|██████▌   | 18387/28080 [36:20:45<19:04:39,  7.09s/it]
                                                           
{'loss': 0.6024, 'learning_rate': 0.0001406336138297012, 'epoch': 7.85}

 65%|██████▌   | 18387/28080 [36:20:45<19:04:39,  7.09s/it]
 65%|██████▌   | 18388/28080 [36:20:53<19:04:52,  7.09s/it]
                                                           
{'loss': 0.6199, 'learning_rate': 0.00014060768447488492, 'epoch': 7.86}

 65%|██████▌   | 18388/28080 [36:20:53<19:04:52,  7.09s/it]
 65%|██████▌   | 18389/28080 [36:21:00<19:00:39,  7.06s/it]
                                                           
{'loss': 0.6201, 'learning_rate': 0.00014058175657542042, 'epoch': 7.86}

 65%|██████▌   | 18389/28080 [36:21:00<19:00:39,  7.06s/it]
 65%|██████▌   | 18390/28080 [36:21:07<19:00:21,  7.06s/it]
                                                           
{'loss': 0.6264, 'learning_rate': 0.00014055583013165284, 'epoch': 7.86}

 65%|██████▌   | 18390/28080 [36:21:07<19:00:21,  7.06s/it]
 65%|██████▌   | 18391/28080 [36:21:14<19:00:21,  7.06s/it]
                                                           
{'loss': 0.6116, 'learning_rate': 0.00014052990514392704, 'epoch': 7.86}

 65%|██████▌   | 18391/28080 [36:21:14<19:00:21,  7.06s/it]
 65%|██████▌   | 18392/28080 [36:21:21<19:00:18,  7.06s/it]
                                                           
{'loss': 0.6063, 'learning_rate': 0.00014050398161258795, 'epoch': 7.86}

 65%|██████▌   | 18392/28080 [36:21:21<19:00:18,  7.06s/it]
 66%|██████▌   | 18393/28080 [36:21:28<19:02:03,  7.07s/it]
                                                           
{'loss': 0.5911, 'learning_rate': 0.00014047805953798032, 'epoch': 7.86}

 66%|██████▌   | 18393/28080 [36:21:28<19:02:03,  7.07s/it]
 66%|██████▌   | 18394/28080 [36:21:35<19:03:31,  7.08s/it]
                                                           
{'loss': 0.6147, 'learning_rate': 0.0001404521389204492, 'epoch': 7.86}

 66%|██████▌   | 18394/28080 [36:21:35<19:03:31,  7.08s/it]
 66%|██████▌   | 18395/28080 [36:21:42<19:06:02,  7.10s/it]
                                                           
{'loss': 0.6128, 'learning_rate': 0.00014042621976033938, 'epoch': 7.86}

 66%|██████▌   | 18395/28080 [36:21:42<19:06:02,  7.10s/it]
 66%|██████▌   | 18396/28080 [36:21:49<19:01:41,  7.07s/it]
                                                           
{'loss': 0.6204, 'learning_rate': 0.00014040030205799564, 'epoch': 7.86}

 66%|██████▌   | 18396/28080 [36:21:49<19:01:41,  7.07s/it]
 66%|██████▌   | 18397/28080 [36:21:56<18:57:20,  7.05s/it]
                                                           
{'loss': 0.609, 'learning_rate': 0.00014037438581376282, 'epoch': 7.86}

 66%|██████▌   | 18397/28080 [36:21:56<18:57:20,  7.05s/it]
 66%|██████▌   | 18398/28080 [36:22:03<19:03:05,  7.08s/it]
                                                           
{'loss': 0.6007, 'learning_rate': 0.0001403484710279856, 'epoch': 7.86}

 66%|██████▌   | 18398/28080 [36:22:03<19:03:05,  7.08s/it]
 66%|██████▌   | 18399/28080 [36:22:10<19:02:29,  7.08s/it]
                                                           
{'loss': 0.5997, 'learning_rate': 0.00014032255770100895, 'epoch': 7.86}

 66%|██████▌   | 18399/28080 [36:22:10<19:02:29,  7.08s/it]
 66%|██████▌   | 18400/28080 [36:22:17<19:02:31,  7.08s/it]
                                                           
{'loss': 0.6163, 'learning_rate': 0.00014029664583317753, 'epoch': 7.86}

 66%|██████▌   | 18400/28080 [36:22:17<19:02:31,  7.08s/it]
 66%|██████▌   | 18401/28080 [36:22:25<19:04:39,  7.10s/it]
                                                           
{'loss': 0.6053, 'learning_rate': 0.00014027073542483608, 'epoch': 7.86}

 66%|██████▌   | 18401/28080 [36:22:25<19:04:39,  7.10s/it]
 66%|██████▌   | 18402/28080 [36:22:32<19:04:58,  7.10s/it]
                                                           
{'loss': 0.6108, 'learning_rate': 0.0001402448264763292, 'epoch': 7.86}

 66%|██████▌   | 18402/28080 [36:22:32<19:04:58,  7.10s/it]
 66%|██████▌   | 18403/28080 [36:22:39<19:07:58,  7.12s/it]
                                                           
{'loss': 0.6011, 'learning_rate': 0.0001402189189880017, 'epoch': 7.86}

 66%|██████▌   | 18403/28080 [36:22:39<19:07:58,  7.12s/it]
 66%|██████▌   | 18404/28080 [36:22:46<19:09:31,  7.13s/it]
                                                           
{'loss': 0.605, 'learning_rate': 0.0001401930129601982, 'epoch': 7.86}

 66%|██████▌   | 18404/28080 [36:22:46<19:09:31,  7.13s/it]
 66%|██████▌   | 18405/28080 [36:22:53<19:11:27,  7.14s/it]
                                                           
{'loss': 0.615, 'learning_rate': 0.00014016710839326346, 'epoch': 7.86}

 66%|██████▌   | 18405/28080 [36:22:53<19:11:27,  7.14s/it]
 66%|██████▌   | 18406/28080 [36:23:00<19:09:12,  7.13s/it]
                                                           
{'loss': 0.6134, 'learning_rate': 0.00014014120528754205, 'epoch': 7.86}

 66%|██████▌   | 18406/28080 [36:23:00<19:09:12,  7.13s/it]
 66%|██████▌   | 18407/28080 [36:23:07<19:10:59,  7.14s/it]
                                                           
{'loss': 0.6088, 'learning_rate': 0.00014011530364337854, 'epoch': 7.86}

 66%|██████▌   | 18407/28080 [36:23:07<19:10:59,  7.14s/it]
 66%|██████▌   | 18408/28080 [36:23:14<19:09:20,  7.13s/it]
                                                           
{'loss': 0.6186, 'learning_rate': 0.0001400894034611175, 'epoch': 7.86}

 66%|██████▌   | 18408/28080 [36:23:14<19:09:20,  7.13s/it]
 66%|██████▌   | 18409/28080 [36:23:22<19:14:27,  7.16s/it]
                                                           
{'loss': 0.6121, 'learning_rate': 0.00014006350474110357, 'epoch': 7.86}

 66%|██████▌   | 18409/28080 [36:23:22<19:14:27,  7.16s/it]
 66%|██████▌   | 18410/28080 [36:23:29<19:12:06,  7.15s/it]
                                                           
{'loss': 0.6078, 'learning_rate': 0.0001400376074836814, 'epoch': 7.86}

 66%|██████▌   | 18410/28080 [36:23:29<19:12:06,  7.15s/it]
 66%|██████▌   | 18411/28080 [36:23:36<19:11:34,  7.15s/it]
                                                           
{'loss': 0.6123, 'learning_rate': 0.00014001171168919534, 'epoch': 7.87}

 66%|██████▌   | 18411/28080 [36:23:36<19:11:34,  7.15s/it]
 66%|██████▌   | 18412/28080 [36:23:43<19:13:51,  7.16s/it]
                                                           
{'loss': 0.5996, 'learning_rate': 0.00013998581735798993, 'epoch': 7.87}

 66%|██████▌   | 18412/28080 [36:23:43<19:13:51,  7.16s/it]
 66%|██████▌   | 18413/28080 [36:23:50<19:10:30,  7.14s/it]
                                                           
{'loss': 0.6203, 'learning_rate': 0.0001399599244904098, 'epoch': 7.87}

 66%|██████▌   | 18413/28080 [36:23:50<19:10:30,  7.14s/it]
 66%|██████▌   | 18414/28080 [36:23:57<19:11:38,  7.15s/it]
                                                           
{'loss': 0.6055, 'learning_rate': 0.00013993403308679936, 'epoch': 7.87}

 66%|██████▌   | 18414/28080 [36:23:57<19:11:38,  7.15s/it]
 66%|██████▌   | 18415/28080 [36:24:05<19:12:52,  7.16s/it]
                                                           
{'loss': 0.6112, 'learning_rate': 0.00013990814314750308, 'epoch': 7.87}

 66%|██████▌   | 18415/28080 [36:24:05<19:12:52,  7.16s/it]
 66%|██████▌   | 18416/28080 [36:24:12<19:11:27,  7.15s/it]
                                                           
{'loss': 0.606, 'learning_rate': 0.00013988225467286526, 'epoch': 7.87}

 66%|██████▌   | 18416/28080 [36:24:12<19:11:27,  7.15s/it]
 66%|██████▌   | 18417/28080 [36:24:19<19:12:12,  7.15s/it]
                                                           
{'loss': 0.5945, 'learning_rate': 0.00013985636766323056, 'epoch': 7.87}

 66%|██████▌   | 18417/28080 [36:24:19<19:12:12,  7.15s/it]
 66%|██████▌   | 18418/28080 [36:24:26<19:14:55,  7.17s/it]
                                                           
{'loss': 0.5955, 'learning_rate': 0.00013983048211894312, 'epoch': 7.87}

 66%|██████▌   | 18418/28080 [36:24:26<19:14:55,  7.17s/it]
 66%|██████▌   | 18419/28080 [36:24:33<19:15:19,  7.18s/it]
                                                           
{'loss': 0.6127, 'learning_rate': 0.00013980459804034762, 'epoch': 7.87}

 66%|██████▌   | 18419/28080 [36:24:33<19:15:19,  7.18s/it]
 66%|██████▌   | 18420/28080 [36:24:40<19:14:12,  7.17s/it]
                                                           
{'loss': 0.5987, 'learning_rate': 0.00013977871542778832, 'epoch': 7.87}

 66%|██████▌   | 18420/28080 [36:24:40<19:14:12,  7.17s/it]
 66%|██████▌   | 18421/28080 [36:24:48<19:11:08,  7.15s/it]
                                                           
{'loss': 0.6168, 'learning_rate': 0.00013975283428160928, 'epoch': 7.87}

 66%|██████▌   | 18421/28080 [36:24:48<19:11:08,  7.15s/it]
 66%|██████▌   | 18422/28080 [36:24:55<19:09:13,  7.14s/it]
                                                           
{'loss': 0.6313, 'learning_rate': 0.00013972695460215517, 'epoch': 7.87}

 66%|██████▌   | 18422/28080 [36:24:55<19:09:13,  7.14s/it]
 66%|██████▌   | 18423/28080 [36:25:02<19:05:10,  7.12s/it]
                                                           
{'loss': 0.6185, 'learning_rate': 0.00013970107638977008, 'epoch': 7.87}

 66%|██████▌   | 18423/28080 [36:25:02<19:05:10,  7.12s/it]
 66%|██████▌   | 18424/28080 [36:25:09<19:07:13,  7.13s/it]
                                                           
{'loss': 0.6099, 'learning_rate': 0.00013967519964479846, 'epoch': 7.87}

 66%|██████▌   | 18424/28080 [36:25:09<19:07:13,  7.13s/it]
 66%|██████▌   | 18425/28080 [36:25:16<19:05:09,  7.12s/it]
                                                           
{'loss': 0.6174, 'learning_rate': 0.0001396493243675845, 'epoch': 7.87}

 66%|██████▌   | 18425/28080 [36:25:16<19:05:09,  7.12s/it]
 66%|██████▌   | 18426/28080 [36:25:23<19:02:47,  7.10s/it]
                                                           
{'loss': 0.6022, 'learning_rate': 0.00013962345055847244, 'epoch': 7.87}

 66%|██████▌   | 18426/28080 [36:25:23<19:02:47,  7.10s/it]
 66%|██████▌   | 18427/28080 [36:25:30<19:06:52,  7.13s/it]
                                                           
{'loss': 0.6085, 'learning_rate': 0.0001395975782178064, 'epoch': 7.87}

 66%|██████▌   | 18427/28080 [36:25:30<19:06:52,  7.13s/it]
 66%|██████▌   | 18428/28080 [36:25:37<19:11:27,  7.16s/it]
                                                           
{'loss': 0.6096, 'learning_rate': 0.00013957170734593078, 'epoch': 7.87}

 66%|██████▌   | 18428/28080 [36:25:37<19:11:27,  7.16s/it]
 66%|██████▌   | 18429/28080 [36:25:44<19:04:56,  7.12s/it]
                                                           
{'loss': 0.6242, 'learning_rate': 0.0001395458379431897, 'epoch': 7.87}

 66%|██████▌   | 18429/28080 [36:25:44<19:04:56,  7.12s/it]
 66%|██████▌   | 18430/28080 [36:25:52<19:02:35,  7.10s/it]
                                                           
{'loss': 0.6314, 'learning_rate': 0.00013951997000992728, 'epoch': 7.87}

 66%|██████▌   | 18430/28080 [36:25:52<19:02:35,  7.10s/it]
 66%|██████▌   | 18431/28080 [36:25:59<18:58:01,  7.08s/it]
                                                           
{'loss': 0.6459, 'learning_rate': 0.00013949410354648756, 'epoch': 7.87}

 66%|██████▌   | 18431/28080 [36:25:59<18:58:01,  7.08s/it]
 66%|██████▌   | 18432/28080 [36:26:06<18:58:48,  7.08s/it]
                                                           
{'loss': 0.6188, 'learning_rate': 0.00013946823855321487, 'epoch': 7.87}

 66%|██████▌   | 18432/28080 [36:26:06<18:58:48,  7.08s/it]
 66%|██████▌   | 18433/28080 [36:26:13<18:51:37,  7.04s/it]
                                                           
{'loss': 0.6458, 'learning_rate': 0.0001394423750304532, 'epoch': 7.87}

 66%|██████▌   | 18433/28080 [36:26:13<18:51:37,  7.04s/it]
 66%|██████▌   | 18434/28080 [36:26:20<18:54:36,  7.06s/it]
                                                           
{'loss': 0.6127, 'learning_rate': 0.00013941651297854686, 'epoch': 7.87}

 66%|██████▌   | 18434/28080 [36:26:20<18:54:36,  7.06s/it]
 66%|██████▌   | 18435/28080 [36:26:27<19:00:19,  7.09s/it]
                                                           
{'loss': 0.6168, 'learning_rate': 0.0001393906523978395, 'epoch': 7.88}

 66%|██████▌   | 18435/28080 [36:26:27<19:00:19,  7.09s/it]
 66%|██████▌   | 18436/28080 [36:26:34<19:04:18,  7.12s/it]
                                                           
{'loss': 0.6206, 'learning_rate': 0.00013936479328867553, 'epoch': 7.88}

 66%|██████▌   | 18436/28080 [36:26:34<19:04:18,  7.12s/it]
 66%|██████▌   | 18437/28080 [36:26:41<18:59:38,  7.09s/it]
                                                           
{'loss': 0.6202, 'learning_rate': 0.00013933893565139875, 'epoch': 7.88}

 66%|██████▌   | 18437/28080 [36:26:41<18:59:38,  7.09s/it]
 66%|██████▌   | 18438/28080 [36:26:48<18:57:47,  7.08s/it]
                                                           
{'loss': 0.6254, 'learning_rate': 0.00013931307948635336, 'epoch': 7.88}

 66%|██████▌   | 18438/28080 [36:26:48<18:57:47,  7.08s/it]
 66%|██████▌   | 18439/28080 [36:26:55<18:57:51,  7.08s/it]
                                                           
{'loss': 0.6086, 'learning_rate': 0.00013928722479388322, 'epoch': 7.88}

 66%|██████▌   | 18439/28080 [36:26:55<18:57:51,  7.08s/it]
 66%|██████▌   | 18440/28080 [36:27:02<19:02:38,  7.11s/it]
                                                           
{'loss': 0.6235, 'learning_rate': 0.00013926137157433237, 'epoch': 7.88}

 66%|██████▌   | 18440/28080 [36:27:02<19:02:38,  7.11s/it]
 66%|██████▌   | 18441/28080 [36:27:09<18:59:13,  7.09s/it]
                                                           
{'loss': 0.6173, 'learning_rate': 0.00013923551982804465, 'epoch': 7.88}

 66%|██████▌   | 18441/28080 [36:27:09<18:59:13,  7.09s/it]
 66%|██████▌   | 18442/28080 [36:27:17<19:02:53,  7.11s/it]
                                                           
{'loss': 0.6073, 'learning_rate': 0.00013920966955536417, 'epoch': 7.88}

 66%|██████▌   | 18442/28080 [36:27:17<19:02:53,  7.11s/it]
 66%|██████▌   | 18443/28080 [36:27:24<19:08:04,  7.15s/it]
                                                           
{'loss': 0.5859, 'learning_rate': 0.00013918382075663472, 'epoch': 7.88}

 66%|██████▌   | 18443/28080 [36:27:24<19:08:04,  7.15s/it]
 66%|██████▌   | 18444/28080 [36:27:31<19:07:33,  7.15s/it]
                                                           
{'loss': 0.6319, 'learning_rate': 0.0001391579734322002, 'epoch': 7.88}

 66%|██████▌   | 18444/28080 [36:27:31<19:07:33,  7.15s/it]
 66%|██████▌   | 18445/28080 [36:27:38<19:07:28,  7.15s/it]
                                                           
{'loss': 0.6129, 'learning_rate': 0.0001391321275824045, 'epoch': 7.88}

 66%|██████▌   | 18445/28080 [36:27:38<19:07:28,  7.15s/it]
 66%|██████▌   | 18446/28080 [36:27:45<19:05:36,  7.13s/it]
                                                           
{'loss': 0.5925, 'learning_rate': 0.0001391062832075914, 'epoch': 7.88}

 66%|██████▌   | 18446/28080 [36:27:45<19:05:36,  7.13s/it]
 66%|██████▌   | 18447/28080 [36:27:52<19:02:55,  7.12s/it]
                                                           
{'loss': 0.608, 'learning_rate': 0.00013908044030810484, 'epoch': 7.88}

 66%|██████▌   | 18447/28080 [36:27:52<19:02:55,  7.12s/it]
 66%|██████▌   | 18448/28080 [36:27:59<18:59:52,  7.10s/it]
                                                           
{'loss': 0.6086, 'learning_rate': 0.00013905459888428865, 'epoch': 7.88}

 66%|██████▌   | 18448/28080 [36:27:59<18:59:52,  7.10s/it]
 66%|██████▌   | 18449/28080 [36:28:06<18:57:25,  7.09s/it]
                                                           
{'loss': 0.6159, 'learning_rate': 0.00013902875893648654, 'epoch': 7.88}

 66%|██████▌   | 18449/28080 [36:28:06<18:57:25,  7.09s/it]
 66%|██████▌   | 18450/28080 [36:28:14<19:01:31,  7.11s/it]
                                                           
{'loss': 0.5968, 'learning_rate': 0.0001390029204650422, 'epoch': 7.88}

 66%|██████▌   | 18450/28080 [36:28:14<19:01:31,  7.11s/it]
 66%|██████▌   | 18451/28080 [36:28:21<19:02:50,  7.12s/it]
                                                           
{'loss': 0.6207, 'learning_rate': 0.00013897708347029964, 'epoch': 7.88}

 66%|██████▌   | 18451/28080 [36:28:21<19:02:50,  7.12s/it]
 66%|██████▌   | 18452/28080 [36:28:28<19:01:39,  7.11s/it]
                                                           
{'loss': 0.6176, 'learning_rate': 0.00013895124795260228, 'epoch': 7.88}

 66%|██████▌   | 18452/28080 [36:28:28<19:01:39,  7.11s/it]
 66%|██████▌   | 18453/28080 [36:28:35<19:03:24,  7.13s/it]
                                                           
{'loss': 0.5988, 'learning_rate': 0.00013892541391229414, 'epoch': 7.88}

 66%|██████▌   | 18453/28080 [36:28:35<19:03:24,  7.13s/it]
 66%|██████▌   | 18454/28080 [36:28:42<19:00:38,  7.11s/it]
                                                           
{'loss': 0.6189, 'learning_rate': 0.0001388995813497188, 'epoch': 7.88}

 66%|██████▌   | 18454/28080 [36:28:42<19:00:38,  7.11s/it]
 66%|██████▌   | 18455/28080 [36:28:49<19:00:49,  7.11s/it]
                                                           
{'loss': 0.611, 'learning_rate': 0.00013887375026521987, 'epoch': 7.88}

 66%|██████▌   | 18455/28080 [36:28:49<19:00:49,  7.11s/it]
 66%|██████▌   | 18456/28080 [36:28:56<18:58:54,  7.10s/it]
                                                           
{'loss': 0.6002, 'learning_rate': 0.00013884792065914099, 'epoch': 7.88}

 66%|██████▌   | 18456/28080 [36:28:56<18:58:54,  7.10s/it]
 66%|██████▌   | 18457/28080 [36:29:03<18:56:22,  7.09s/it]
                                                           
{'loss': 0.6105, 'learning_rate': 0.00013882209253182593, 'epoch': 7.88}

 66%|██████▌   | 18457/28080 [36:29:03<18:56:22,  7.09s/it]
 66%|██████▌   | 18458/28080 [36:29:10<18:59:37,  7.11s/it]
                                                           
{'loss': 0.6022, 'learning_rate': 0.00013879626588361824, 'epoch': 7.89}

 66%|██████▌   | 18458/28080 [36:29:10<18:59:37,  7.11s/it]
 66%|██████▌   | 18459/28080 [36:29:18<18:57:48,  7.10s/it]
                                                           
{'loss': 0.5963, 'learning_rate': 0.0001387704407148615, 'epoch': 7.89}

 66%|██████▌   | 18459/28080 [36:29:18<18:57:48,  7.10s/it]
 66%|██████▌   | 18460/28080 [36:29:25<19:02:55,  7.13s/it]
                                                           
{'loss': 0.5982, 'learning_rate': 0.0001387446170258992, 'epoch': 7.89}

 66%|██████▌   | 18460/28080 [36:29:25<19:02:55,  7.13s/it]
 66%|██████▌   | 18461/28080 [36:29:32<19:00:39,  7.12s/it]
                                                           
{'loss': 0.6149, 'learning_rate': 0.0001387187948170751, 'epoch': 7.89}

 66%|██████▌   | 18461/28080 [36:29:32<19:00:39,  7.12s/it]
 66%|██████▌   | 18462/28080 [36:29:39<19:02:21,  7.13s/it]
                                                           
{'loss': 0.6015, 'learning_rate': 0.00013869297408873265, 'epoch': 7.89}

 66%|██████▌   | 18462/28080 [36:29:39<19:02:21,  7.13s/it]
 66%|██████▌   | 18463/28080 [36:29:46<19:00:28,  7.12s/it]
                                                           
{'loss': 0.6303, 'learning_rate': 0.00013866715484121535, 'epoch': 7.89}

 66%|██████▌   | 18463/28080 [36:29:46<19:00:28,  7.12s/it]
 66%|██████▌   | 18464/28080 [36:29:53<19:02:16,  7.13s/it]
                                                           
{'loss': 0.5782, 'learning_rate': 0.00013864133707486658, 'epoch': 7.89}

 66%|██████▌   | 18464/28080 [36:29:53<19:02:16,  7.13s/it]
 66%|██████▌   | 18465/28080 [36:30:00<18:57:55,  7.10s/it]
                                                           
{'loss': 0.6102, 'learning_rate': 0.00013861552079003002, 'epoch': 7.89}

 66%|██████▌   | 18465/28080 [36:30:00<18:57:55,  7.10s/it]
 66%|██████▌   | 18466/28080 [36:30:07<18:57:53,  7.10s/it]
                                                           
{'loss': 0.6134, 'learning_rate': 0.00013858970598704898, 'epoch': 7.89}

 66%|██████▌   | 18466/28080 [36:30:07<18:57:53,  7.10s/it]
 66%|██████▌   | 18467/28080 [36:30:14<18:56:09,  7.09s/it]
                                                           
{'loss': 0.6175, 'learning_rate': 0.00013856389266626707, 'epoch': 7.89}

 66%|██████▌   | 18467/28080 [36:30:14<18:56:09,  7.09s/it]
 66%|██████▌   | 18468/28080 [36:30:22<18:58:46,  7.11s/it]
                                                           
{'loss': 0.6153, 'learning_rate': 0.00013853808082802757, 'epoch': 7.89}

 66%|██████▌   | 18468/28080 [36:30:22<18:58:46,  7.11s/it]
 66%|██████▌   | 18469/28080 [36:30:29<18:55:10,  7.09s/it]
                                                           
{'loss': 0.6086, 'learning_rate': 0.00013851227047267394, 'epoch': 7.89}

 66%|██████▌   | 18469/28080 [36:30:29<18:55:10,  7.09s/it]
 66%|██████▌   | 18470/28080 [36:30:36<19:02:46,  7.13s/it]
                                                           
{'loss': 0.599, 'learning_rate': 0.00013848646160054953, 'epoch': 7.89}

 66%|██████▌   | 18470/28080 [36:30:36<19:02:46,  7.13s/it]
 66%|██████▌   | 18471/28080 [36:30:43<19:03:28,  7.14s/it]
                                                           
{'loss': 0.623, 'learning_rate': 0.00013846065421199762, 'epoch': 7.89}

 66%|██████▌   | 18471/28080 [36:30:43<19:03:28,  7.14s/it]
 66%|██████▌   | 18472/28080 [36:30:50<19:01:31,  7.13s/it]
                                                           
{'loss': 0.606, 'learning_rate': 0.00013843484830736172, 'epoch': 7.89}

 66%|██████▌   | 18472/28080 [36:30:50<19:01:31,  7.13s/it]
 66%|██████▌   | 18473/28080 [36:30:57<18:58:42,  7.11s/it]
                                                           
{'loss': 0.5985, 'learning_rate': 0.0001384090438869851, 'epoch': 7.89}

 66%|██████▌   | 18473/28080 [36:30:57<18:58:42,  7.11s/it]
 66%|██████▌   | 18474/28080 [36:31:04<18:54:33,  7.09s/it]
                                                           
{'loss': 0.6035, 'learning_rate': 0.00013838324095121098, 'epoch': 7.89}

 66%|██████▌   | 18474/28080 [36:31:04<18:54:33,  7.09s/it]
 66%|██████▌   | 18475/28080 [36:31:11<18:58:46,  7.11s/it]
                                                           
{'loss': 0.6258, 'learning_rate': 0.0001383574395003826, 'epoch': 7.89}

 66%|██████▌   | 18475/28080 [36:31:11<18:58:46,  7.11s/it]
 66%|██████▌   | 18476/28080 [36:31:19<18:59:54,  7.12s/it]
                                                           
{'loss': 0.6273, 'learning_rate': 0.00013833163953484346, 'epoch': 7.89}

 66%|██████▌   | 18476/28080 [36:31:19<18:59:54,  7.12s/it]
 66%|██████▌   | 18477/28080 [36:31:26<19:00:45,  7.13s/it]
                                                           
{'loss': 0.61, 'learning_rate': 0.0001383058410549366, 'epoch': 7.89}

 66%|██████▌   | 18477/28080 [36:31:26<19:00:45,  7.13s/it]
 66%|██████▌   | 18478/28080 [36:31:33<18:59:59,  7.12s/it]
                                                           
{'loss': 0.6397, 'learning_rate': 0.00013828004406100532, 'epoch': 7.89}

 66%|██████▌   | 18478/28080 [36:31:33<18:59:59,  7.12s/it]
 66%|██████▌   | 18479/28080 [36:31:40<18:57:15,  7.11s/it]
                                                           
{'loss': 0.6062, 'learning_rate': 0.0001382542485533927, 'epoch': 7.89}

 66%|██████▌   | 18479/28080 [36:31:40<18:57:15,  7.11s/it]
 66%|██████▌   | 18480/28080 [36:31:47<18:58:48,  7.12s/it]
                                                           
{'loss': 0.6194, 'learning_rate': 0.0001382284545324421, 'epoch': 7.89}

 66%|██████▌   | 18480/28080 [36:31:47<18:58:48,  7.12s/it]
 66%|██████▌   | 18481/28080 [36:31:54<18:57:49,  7.11s/it]
                                                           
{'loss': 0.6108, 'learning_rate': 0.00013820266199849652, 'epoch': 7.89}

 66%|██████▌   | 18481/28080 [36:31:54<18:57:49,  7.11s/it]
 66%|██████▌   | 18482/28080 [36:32:01<18:58:17,  7.12s/it]
                                                           
{'loss': 0.614, 'learning_rate': 0.00013817687095189941, 'epoch': 7.9}

 66%|██████▌   | 18482/28080 [36:32:01<18:58:17,  7.12s/it]
 66%|██████▌   | 18483/28080 [36:32:08<18:58:57,  7.12s/it]
                                                           
{'loss': 0.6047, 'learning_rate': 0.00013815108139299343, 'epoch': 7.9}

 66%|██████▌   | 18483/28080 [36:32:08<18:58:57,  7.12s/it]
 66%|██████▌   | 18484/28080 [36:32:15<18:51:59,  7.08s/it]
                                                           
{'loss': 0.6086, 'learning_rate': 0.00013812529332212203, 'epoch': 7.9}

 66%|██████▌   | 18484/28080 [36:32:15<18:51:59,  7.08s/it]
 66%|██████▌   | 18485/28080 [36:32:23<18:58:11,  7.12s/it]
                                                           
{'loss': 0.624, 'learning_rate': 0.00013809950673962813, 'epoch': 7.9}

 66%|██████▌   | 18485/28080 [36:32:23<18:58:11,  7.12s/it]
 66%|██████▌   | 18486/28080 [36:32:30<19:00:12,  7.13s/it]
                                                           
{'loss': 0.596, 'learning_rate': 0.00013807372164585492, 'epoch': 7.9}

 66%|██████▌   | 18486/28080 [36:32:30<19:00:12,  7.13s/it]
 66%|██████▌   | 18487/28080 [36:32:37<18:59:41,  7.13s/it]
                                                           
{'loss': 0.6058, 'learning_rate': 0.00013804793804114536, 'epoch': 7.9}

 66%|██████▌   | 18487/28080 [36:32:37<18:59:41,  7.13s/it]
 66%|██████▌   | 18488/28080 [36:32:44<19:02:35,  7.15s/it]
                                                           
{'loss': 0.6014, 'learning_rate': 0.00013802215592584248, 'epoch': 7.9}

 66%|██████▌   | 18488/28080 [36:32:44<19:02:35,  7.15s/it]
 66%|██████▌   | 18489/28080 [36:32:51<18:54:58,  7.10s/it]
                                                           
{'loss': 0.6111, 'learning_rate': 0.00013799637530028926, 'epoch': 7.9}

 66%|██████▌   | 18489/28080 [36:32:51<18:54:58,  7.10s/it]
 66%|██████▌   | 18490/28080 [36:32:58<18:55:05,  7.10s/it]
                                                           
{'loss': 0.5948, 'learning_rate': 0.00013797059616482878, 'epoch': 7.9}

 66%|██████▌   | 18490/28080 [36:32:58<18:55:05,  7.10s/it]
 66%|██████▌   | 18491/28080 [36:33:05<18:56:07,  7.11s/it]
                                                           
{'loss': 0.6262, 'learning_rate': 0.00013794481851980392, 'epoch': 7.9}

 66%|██████▌   | 18491/28080 [36:33:05<18:56:07,  7.11s/it]
 66%|██████▌   | 18492/28080 [36:33:12<18:54:27,  7.10s/it]
                                                           
{'loss': 0.6097, 'learning_rate': 0.0001379190423655577, 'epoch': 7.9}

 66%|██████▌   | 18492/28080 [36:33:12<18:54:27,  7.10s/it]
 66%|██████▌   | 18493/28080 [36:33:19<18:53:55,  7.10s/it]
                                                           
{'loss': 0.6139, 'learning_rate': 0.00013789326770243286, 'epoch': 7.9}

 66%|██████▌   | 18493/28080 [36:33:19<18:53:55,  7.10s/it]
 66%|██████▌   | 18494/28080 [36:33:27<18:56:45,  7.12s/it]
                                                           
{'loss': 0.6158, 'learning_rate': 0.00013786749453077252, 'epoch': 7.9}

 66%|██████▌   | 18494/28080 [36:33:27<18:56:45,  7.12s/it]
 66%|██████▌   | 18495/28080 [36:33:34<18:53:29,  7.10s/it]
                                                           
{'loss': 0.6128, 'learning_rate': 0.0001378417228509195, 'epoch': 7.9}

 66%|██████▌   | 18495/28080 [36:33:34<18:53:29,  7.10s/it]
 66%|██████▌   | 18496/28080 [36:33:41<18:52:48,  7.09s/it]
                                                           
{'loss': 0.6222, 'learning_rate': 0.00013781595266321666, 'epoch': 7.9}

 66%|██████▌   | 18496/28080 [36:33:41<18:52:48,  7.09s/it]
 66%|██████▌   | 18497/28080 [36:33:48<18:55:18,  7.11s/it]
                                                           
{'loss': 0.6193, 'learning_rate': 0.00013779018396800686, 'epoch': 7.9}

 66%|██████▌   | 18497/28080 [36:33:48<18:55:18,  7.11s/it]
 66%|██████▌   | 18498/28080 [36:33:55<18:57:04,  7.12s/it]
                                                           
{'loss': 0.6116, 'learning_rate': 0.0001377644167656328, 'epoch': 7.9}

 66%|██████▌   | 18498/28080 [36:33:55<18:57:04,  7.12s/it]
 66%|██████▌   | 18499/28080 [36:34:02<18:55:25,  7.11s/it]
                                                           
{'loss': 0.6136, 'learning_rate': 0.00013773865105643743, 'epoch': 7.9}

 66%|██████▌   | 18499/28080 [36:34:02<18:55:25,  7.11s/it]
 66%|██████▌   | 18500/28080 [36:34:09<18:55:20,  7.11s/it]
                                                           
{'loss': 0.6322, 'learning_rate': 0.00013771288684076344, 'epoch': 7.9}

 66%|██████▌   | 18500/28080 [36:34:09<18:55:20,  7.11s/it]
 66%|██████▌   | 18501/28080 [36:34:16<18:52:02,  7.09s/it]
                                                           
{'loss': 0.5996, 'learning_rate': 0.00013768712411895386, 'epoch': 7.9}

 66%|██████▌   | 18501/28080 [36:34:16<18:52:02,  7.09s/it]
 66%|██████▌   | 18502/28080 [36:34:23<18:50:40,  7.08s/it]
                                                           
{'loss': 0.6041, 'learning_rate': 0.00013766136289135097, 'epoch': 7.9}

 66%|██████▌   | 18502/28080 [36:34:23<18:50:40,  7.08s/it]
 66%|██████▌   | 18503/28080 [36:34:30<18:54:29,  7.11s/it]
                                                           
{'loss': 0.616, 'learning_rate': 0.0001376356031582979, 'epoch': 7.9}

 66%|██████▌   | 18503/28080 [36:34:30<18:54:29,  7.11s/it]
 66%|██████▌   | 18504/28080 [36:34:38<18:59:20,  7.14s/it]
                                                           
{'loss': 0.6116, 'learning_rate': 0.00013760984492013713, 'epoch': 7.9}

 66%|██████▌   | 18504/28080 [36:34:38<18:59:20,  7.14s/it]
 66%|██████▌   | 18505/28080 [36:34:45<18:59:44,  7.14s/it]
                                                           
{'loss': 0.6448, 'learning_rate': 0.00013758408817721147, 'epoch': 7.91}

 66%|██████▌   | 18505/28080 [36:34:45<18:59:44,  7.14s/it]
 66%|██████▌   | 18506/28080 [36:34:52<18:59:06,  7.14s/it]
                                                           
{'loss': 0.615, 'learning_rate': 0.00013755833292986358, 'epoch': 7.91}

 66%|██████▌   | 18506/28080 [36:34:52<18:59:06,  7.14s/it]
 66%|██████▌   | 18507/28080 [36:34:59<19:02:28,  7.16s/it]
                                                           
{'loss': 0.6014, 'learning_rate': 0.00013753257917843603, 'epoch': 7.91}

 66%|██████▌   | 18507/28080 [36:34:59<19:02:28,  7.16s/it]
 66%|██████▌   | 18508/28080 [36:35:06<18:59:07,  7.14s/it]
                                                           
{'loss': 0.6228, 'learning_rate': 0.00013750682692327144, 'epoch': 7.91}

 66%|██████▌   | 18508/28080 [36:35:06<18:59:07,  7.14s/it]
 66%|██████▌   | 18509/28080 [36:35:13<19:00:09,  7.15s/it]
                                                           
{'loss': 0.6201, 'learning_rate': 0.00013748107616471257, 'epoch': 7.91}

 66%|██████▌   | 18509/28080 [36:35:13<19:00:09,  7.15s/it]
 66%|██████▌   | 18510/28080 [36:35:21<18:59:18,  7.14s/it]
                                                           
{'loss': 0.5924, 'learning_rate': 0.00013745532690310187, 'epoch': 7.91}

 66%|██████▌   | 18510/28080 [36:35:21<18:59:18,  7.14s/it]
 66%|██████▌   | 18511/28080 [36:35:28<18:59:20,  7.14s/it]
                                                           
{'loss': 0.6038, 'learning_rate': 0.00013742957913878194, 'epoch': 7.91}

 66%|██████▌   | 18511/28080 [36:35:28<18:59:20,  7.14s/it]
 66%|██████▌   | 18512/28080 [36:35:35<19:02:10,  7.16s/it]
                                                           
{'loss': 0.6115, 'learning_rate': 0.00013740383287209524, 'epoch': 7.91}

 66%|██████▌   | 18512/28080 [36:35:35<19:02:10,  7.16s/it]
 66%|██████▌   | 18513/28080 [36:35:42<19:01:19,  7.16s/it]
                                                           
{'loss': 0.6079, 'learning_rate': 0.0001373780881033845, 'epoch': 7.91}

 66%|██████▌   | 18513/28080 [36:35:42<19:01:19,  7.16s/it]
 66%|██████▌   | 18514/28080 [36:35:49<19:00:48,  7.16s/it]
                                                           
{'loss': 0.6022, 'learning_rate': 0.00013735234483299198, 'epoch': 7.91}

 66%|██████▌   | 18514/28080 [36:35:49<19:00:48,  7.16s/it]
 66%|██████▌   | 18515/28080 [36:35:56<19:01:09,  7.16s/it]
                                                           
{'loss': 0.6187, 'learning_rate': 0.00013732660306126039, 'epoch': 7.91}

 66%|██████▌   | 18515/28080 [36:35:56<19:01:09,  7.16s/it]
 66%|██████▌   | 18516/28080 [36:36:03<18:52:53,  7.11s/it]
                                                           
{'loss': 0.6022, 'learning_rate': 0.00013730086278853214, 'epoch': 7.91}

 66%|██████▌   | 18516/28080 [36:36:03<18:52:53,  7.11s/it]
 66%|██████▌   | 18517/28080 [36:36:10<18:53:17,  7.11s/it]
                                                           
{'loss': 0.5993, 'learning_rate': 0.00013727512401514962, 'epoch': 7.91}

 66%|██████▌   | 18517/28080 [36:36:10<18:53:17,  7.11s/it]
 66%|██████▌   | 18518/28080 [36:36:18<18:54:18,  7.12s/it]
                                                           
{'loss': 0.6193, 'learning_rate': 0.0001372493867414552, 'epoch': 7.91}

 66%|██████▌   | 18518/28080 [36:36:18<18:54:18,  7.12s/it]
 66%|██████▌   | 18519/28080 [36:36:25<18:50:51,  7.10s/it]
                                                           
{'loss': 0.6399, 'learning_rate': 0.00013722365096779146, 'epoch': 7.91}

 66%|██████▌   | 18519/28080 [36:36:25<18:50:51,  7.10s/it]
 66%|██████▌   | 18520/28080 [36:36:32<18:51:15,  7.10s/it]
                                                           
{'loss': 0.6093, 'learning_rate': 0.00013719791669450072, 'epoch': 7.91}

 66%|██████▌   | 18520/28080 [36:36:32<18:51:15,  7.10s/it]
 66%|██████▌   | 18521/28080 [36:36:39<18:54:03,  7.12s/it]
                                                           
{'loss': 0.588, 'learning_rate': 0.0001371721839219253, 'epoch': 7.91}

 66%|██████▌   | 18521/28080 [36:36:39<18:54:03,  7.12s/it]
 66%|██████▌   | 18522/28080 [36:36:46<18:52:57,  7.11s/it]
                                                           
{'loss': 0.6198, 'learning_rate': 0.0001371464526504076, 'epoch': 7.91}

 66%|██████▌   | 18522/28080 [36:36:46<18:52:57,  7.11s/it]
 66%|██████▌   | 18523/28080 [36:36:53<18:51:07,  7.10s/it]
                                                           
{'loss': 0.6164, 'learning_rate': 0.00013712072288028982, 'epoch': 7.91}

 66%|██████▌   | 18523/28080 [36:36:53<18:51:07,  7.10s/it]
 66%|██████▌   | 18524/28080 [36:37:00<18:49:53,  7.09s/it]
                                                           
{'loss': 0.6046, 'learning_rate': 0.00013709499461191443, 'epoch': 7.91}

 66%|██████▌   | 18524/28080 [36:37:00<18:49:53,  7.09s/it]
 66%|██████▌   | 18525/28080 [36:37:07<18:46:13,  7.07s/it]
                                                           
{'loss': 0.6219, 'learning_rate': 0.00013706926784562372, 'epoch': 7.91}

 66%|██████▌   | 18525/28080 [36:37:07<18:46:13,  7.07s/it]
 66%|██████▌   | 18526/28080 [36:37:14<18:54:27,  7.12s/it]
                                                           
{'loss': 0.5941, 'learning_rate': 0.00013704354258175984, 'epoch': 7.91}

 66%|██████▌   | 18526/28080 [36:37:14<18:54:27,  7.12s/it]
 66%|██████▌   | 18527/28080 [36:37:22<18:51:53,  7.11s/it]
                                                           
{'loss': 0.6206, 'learning_rate': 0.00013701781882066505, 'epoch': 7.91}

 66%|██████▌   | 18527/28080 [36:37:22<18:51:53,  7.11s/it]
 66%|██████▌   | 18528/28080 [36:37:29<18:50:19,  7.10s/it]
                                                           
{'loss': 0.623, 'learning_rate': 0.00013699209656268168, 'epoch': 7.91}

 66%|██████▌   | 18528/28080 [36:37:29<18:50:19,  7.10s/it]
 66%|██████▌   | 18529/28080 [36:37:36<18:53:39,  7.12s/it]
                                                           
{'loss': 0.59, 'learning_rate': 0.0001369663758081518, 'epoch': 7.92}

 66%|██████▌   | 18529/28080 [36:37:36<18:53:39,  7.12s/it]
 66%|██████▌   | 18530/28080 [36:37:43<18:59:34,  7.16s/it]
                                                           
{'loss': 0.5957, 'learning_rate': 0.0001369406565574179, 'epoch': 7.92}

 66%|██████▌   | 18530/28080 [36:37:43<18:59:34,  7.16s/it]
 66%|██████▌   | 18531/28080 [36:37:50<19:01:47,  7.17s/it]
                                                           
{'loss': 0.6244, 'learning_rate': 0.00013691493881082167, 'epoch': 7.92}

 66%|██████▌   | 18531/28080 [36:37:50<19:01:47,  7.17s/it]
 66%|██████▌   | 18532/28080 [36:37:57<19:03:52,  7.19s/it]
                                                           
{'loss': 0.5984, 'learning_rate': 0.00013688922256870566, 'epoch': 7.92}

 66%|██████▌   | 18532/28080 [36:37:57<19:03:52,  7.19s/it]
 66%|██████▌   | 18533/28080 [36:38:05<18:57:16,  7.15s/it]
                                                           
{'loss': 0.5911, 'learning_rate': 0.00013686350783141178, 'epoch': 7.92}

 66%|██████▌   | 18533/28080 [36:38:05<18:57:16,  7.15s/it]
 66%|██████▌   | 18534/28080 [36:38:12<18:55:45,  7.14s/it]
                                                           
{'loss': 0.6045, 'learning_rate': 0.00013683779459928224, 'epoch': 7.92}

 66%|██████▌   | 18534/28080 [36:38:12<18:55:45,  7.14s/it]
 66%|██████▌   | 18535/28080 [36:38:19<18:55:15,  7.14s/it]
                                                           
{'loss': 0.6002, 'learning_rate': 0.00013681208287265914, 'epoch': 7.92}

 66%|██████▌   | 18535/28080 [36:38:19<18:55:15,  7.14s/it]
 66%|██████▌   | 18536/28080 [36:38:26<18:56:31,  7.14s/it]
                                                           
{'loss': 0.6172, 'learning_rate': 0.00013678637265188452, 'epoch': 7.92}

 66%|██████▌   | 18536/28080 [36:38:26<18:56:31,  7.14s/it]
 66%|██████▌   | 18537/28080 [36:38:33<18:59:14,  7.16s/it]
                                                           
{'loss': 0.5855, 'learning_rate': 0.0001367606639373003, 'epoch': 7.92}

 66%|██████▌   | 18537/28080 [36:38:33<18:59:14,  7.16s/it]
 66%|██████▌   | 18538/28080 [36:38:40<18:53:02,  7.12s/it]
                                                           
{'loss': 0.583, 'learning_rate': 0.0001367349567292487, 'epoch': 7.92}

 66%|██████▌   | 18538/28080 [36:38:40<18:53:02,  7.12s/it]
 66%|██████▌   | 18539/28080 [36:38:47<18:52:47,  7.12s/it]
                                                           
{'loss': 0.6128, 'learning_rate': 0.0001367092510280717, 'epoch': 7.92}

 66%|██████▌   | 18539/28080 [36:38:47<18:52:47,  7.12s/it]
 66%|██████▌   | 18540/28080 [36:38:54<18:53:05,  7.13s/it]
                                                           
{'loss': 0.6165, 'learning_rate': 0.00013668354683411121, 'epoch': 7.92}

 66%|██████▌   | 18540/28080 [36:38:54<18:53:05,  7.13s/it]
 66%|██████▌   | 18541/28080 [36:39:02<18:53:51,  7.13s/it]
                                                           
{'loss': 0.6209, 'learning_rate': 0.00013665784414770916, 'epoch': 7.92}

 66%|██████▌   | 18541/28080 [36:39:02<18:53:51,  7.13s/it]
 66%|██████▌   | 18542/28080 [36:39:09<18:48:43,  7.10s/it]
                                                           
{'loss': 0.6209, 'learning_rate': 0.00013663214296920763, 'epoch': 7.92}

 66%|██████▌   | 18542/28080 [36:39:09<18:48:43,  7.10s/it]
 66%|██████▌   | 18543/28080 [36:39:16<18:48:05,  7.10s/it]
                                                           
{'loss': 0.6436, 'learning_rate': 0.00013660644329894838, 'epoch': 7.92}

 66%|██████▌   | 18543/28080 [36:39:16<18:48:05,  7.10s/it]
 66%|██████▌   | 18544/28080 [36:39:23<18:48:36,  7.10s/it]
                                                           
{'loss': 0.6066, 'learning_rate': 0.00013658074513727363, 'epoch': 7.92}

 66%|██████▌   | 18544/28080 [36:39:23<18:48:36,  7.10s/it]
 66%|██████▌   | 18545/28080 [36:39:30<18:44:30,  7.08s/it]
                                                           
{'loss': 0.5943, 'learning_rate': 0.00013655504848452494, 'epoch': 7.92}

 66%|██████▌   | 18545/28080 [36:39:30<18:44:30,  7.08s/it]
 66%|██████▌   | 18546/28080 [36:39:37<18:46:51,  7.09s/it]
                                                           
{'loss': 0.614, 'learning_rate': 0.00013652935334104423, 'epoch': 7.92}

 66%|██████▌   | 18546/28080 [36:39:37<18:46:51,  7.09s/it]
 66%|██████▌   | 18547/28080 [36:39:44<18:49:22,  7.11s/it]
                                                           
{'loss': 0.6046, 'learning_rate': 0.0001365036597071735, 'epoch': 7.92}

 66%|██████▌   | 18547/28080 [36:39:44<18:49:22,  7.11s/it]
 66%|██████▌   | 18548/28080 [36:39:51<18:48:41,  7.10s/it]
                                                           
{'loss': 0.5982, 'learning_rate': 0.00013647796758325438, 'epoch': 7.92}

 66%|██████▌   | 18548/28080 [36:39:51<18:48:41,  7.10s/it]
 66%|██████▌   | 18549/28080 [36:39:58<18:49:46,  7.11s/it]
                                                           
{'loss': 0.6178, 'learning_rate': 0.00013645227696962897, 'epoch': 7.92}

 66%|██████▌   | 18549/28080 [36:39:58<18:49:46,  7.11s/it]
 66%|██████▌   | 18550/28080 [36:40:06<18:55:09,  7.15s/it]
                                                           
{'loss': 0.6075, 'learning_rate': 0.00013642658786663873, 'epoch': 7.92}

 66%|██████▌   | 18550/28080 [36:40:06<18:55:09,  7.15s/it]
 66%|██████▌   | 18551/28080 [36:40:13<18:56:34,  7.16s/it]
                                                           
{'loss': 0.625, 'learning_rate': 0.00013640090027462566, 'epoch': 7.92}

 66%|██████▌   | 18551/28080 [36:40:13<18:56:34,  7.16s/it]
 66%|██████▌   | 18552/28080 [36:40:20<18:56:04,  7.15s/it]
                                                           
{'loss': 0.6096, 'learning_rate': 0.00013637521419393128, 'epoch': 7.93}

 66%|██████▌   | 18552/28080 [36:40:20<18:56:04,  7.15s/it]
 66%|██████▌   | 18553/28080 [36:40:27<18:51:39,  7.13s/it]
                                                           
{'loss': 0.6194, 'learning_rate': 0.00013634952962489756, 'epoch': 7.93}

 66%|██████▌   | 18553/28080 [36:40:27<18:51:39,  7.13s/it]
 66%|██████▌   | 18554/28080 [36:40:34<18:47:58,  7.10s/it]
                                                           
{'loss': 0.606, 'learning_rate': 0.00013632384656786612, 'epoch': 7.93}

 66%|██████▌   | 18554/28080 [36:40:34<18:47:58,  7.10s/it]
 66%|██████▌   | 18555/28080 [36:40:41<18:50:14,  7.12s/it]
                                                           
{'loss': 0.5892, 'learning_rate': 0.0001362981650231786, 'epoch': 7.93}

 66%|██████▌   | 18555/28080 [36:40:41<18:50:14,  7.12s/it]
 66%|██████▌   | 18556/28080 [36:40:48<18:49:21,  7.11s/it]
                                                           
{'loss': 0.5941, 'learning_rate': 0.00013627248499117664, 'epoch': 7.93}

 66%|██████▌   | 18556/28080 [36:40:48<18:49:21,  7.11s/it]
 66%|██████▌   | 18557/28080 [36:40:55<18:49:32,  7.12s/it]
                                                           
{'loss': 0.6249, 'learning_rate': 0.000136246806472202, 'epoch': 7.93}

 66%|██████▌   | 18557/28080 [36:40:55<18:49:32,  7.12s/it]
 66%|██████▌   | 18558/28080 [36:41:02<18:50:45,  7.13s/it]
                                                           
{'loss': 0.6227, 'learning_rate': 0.00013622112946659625, 'epoch': 7.93}

 66%|██████▌   | 18558/28080 [36:41:02<18:50:45,  7.13s/it]
 66%|██████▌   | 18559/28080 [36:41:10<18:45:13,  7.09s/it]
                                                           
{'loss': 0.6115, 'learning_rate': 0.00013619545397470105, 'epoch': 7.93}

 66%|██████▌   | 18559/28080 [36:41:10<18:45:13,  7.09s/it]
 66%|██████▌   | 18560/28080 [36:41:17<18:43:49,  7.08s/it]
                                                           
{'loss': 0.6138, 'learning_rate': 0.00013616977999685777, 'epoch': 7.93}

 66%|██████▌   | 18560/28080 [36:41:17<18:43:49,  7.08s/it]
 66%|██████▌   | 18561/28080 [36:41:24<18:44:13,  7.09s/it]
                                                           
{'loss': 0.6039, 'learning_rate': 0.00013614410753340827, 'epoch': 7.93}

 66%|██████▌   | 18561/28080 [36:41:24<18:44:13,  7.09s/it]
 66%|██████▌   | 18562/28080 [36:41:31<18:46:43,  7.10s/it]
                                                           
{'loss': 0.6067, 'learning_rate': 0.00013611843658469384, 'epoch': 7.93}

 66%|██████▌   | 18562/28080 [36:41:31<18:46:43,  7.10s/it]
 66%|██████▌   | 18563/28080 [36:41:38<18:50:08,  7.12s/it]
                                                           
{'loss': 0.6138, 'learning_rate': 0.00013609276715105634, 'epoch': 7.93}

 66%|██████▌   | 18563/28080 [36:41:38<18:50:08,  7.12s/it]
 66%|██████▌   | 18564/28080 [36:41:45<18:51:34,  7.13s/it]
                                                           
{'loss': 0.6047, 'learning_rate': 0.00013606709923283684, 'epoch': 7.93}

 66%|██████▌   | 18564/28080 [36:41:45<18:51:34,  7.13s/it]
 66%|██████▌   | 18565/28080 [36:41:52<18:52:26,  7.14s/it]
                                                           
{'loss': 0.5971, 'learning_rate': 0.00013604143283037714, 'epoch': 7.93}

 66%|██████▌   | 18565/28080 [36:41:52<18:52:26,  7.14s/it]
 66%|██████▌   | 18566/28080 [36:41:59<18:52:51,  7.14s/it]
                                                           
{'loss': 0.6087, 'learning_rate': 0.00013601576794401853, 'epoch': 7.93}

 66%|██████▌   | 18566/28080 [36:41:59<18:52:51,  7.14s/it]
 66%|██████▌   | 18567/28080 [36:42:07<18:50:05,  7.13s/it]
                                                           
{'loss': 0.6033, 'learning_rate': 0.00013599010457410266, 'epoch': 7.93}

 66%|██████▌   | 18567/28080 [36:42:07<18:50:05,  7.13s/it]
 66%|██████▌   | 18568/28080 [36:42:14<18:49:51,  7.13s/it]
                                                           
{'loss': 0.6014, 'learning_rate': 0.0001359644427209708, 'epoch': 7.93}

 66%|██████▌   | 18568/28080 [36:42:14<18:49:51,  7.13s/it]
 66%|██████▌   | 18569/28080 [36:42:21<18:53:47,  7.15s/it]
                                                           
{'loss': 0.6152, 'learning_rate': 0.00013593878238496438, 'epoch': 7.93}

 66%|██████▌   | 18569/28080 [36:42:21<18:53:47,  7.15s/it]
 66%|██████▌   | 18570/28080 [36:42:28<18:49:07,  7.12s/it]
                                                           
{'loss': 0.6206, 'learning_rate': 0.00013591312356642482, 'epoch': 7.93}

 66%|██████▌   | 18570/28080 [36:42:28<18:49:07,  7.12s/it]
 66%|██████▌   | 18571/28080 [36:42:35<18:50:07,  7.13s/it]
                                                           
{'loss': 0.6022, 'learning_rate': 0.00013588746626569333, 'epoch': 7.93}

 66%|██████▌   | 18571/28080 [36:42:35<18:50:07,  7.13s/it]
 66%|██████▌   | 18572/28080 [36:42:42<18:50:21,  7.13s/it]
                                                           
{'loss': 0.6174, 'learning_rate': 0.00013586181048311146, 'epoch': 7.93}

 66%|██████▌   | 18572/28080 [36:42:42<18:50:21,  7.13s/it]
 66%|██████▌   | 18573/28080 [36:42:49<18:53:51,  7.16s/it]
                                                           
{'loss': 0.6255, 'learning_rate': 0.0001358361562190205, 'epoch': 7.93}

 66%|██████▌   | 18573/28080 [36:42:49<18:53:51,  7.16s/it]
 66%|██████▌   | 18574/28080 [36:42:56<18:47:05,  7.11s/it]
                                                           
{'loss': 0.6337, 'learning_rate': 0.00013581050347376167, 'epoch': 7.93}

 66%|██████▌   | 18574/28080 [36:42:56<18:47:05,  7.11s/it]
 66%|██████▌   | 18575/28080 [36:43:04<18:48:13,  7.12s/it]
                                                           
{'loss': 0.6055, 'learning_rate': 0.00013578485224767623, 'epoch': 7.94}

 66%|██████▌   | 18575/28080 [36:43:04<18:48:13,  7.12s/it]
 66%|██████▌   | 18576/28080 [36:43:11<18:44:49,  7.10s/it]
                                                           
{'loss': 0.6045, 'learning_rate': 0.00013575920254110558, 'epoch': 7.94}

 66%|██████▌   | 18576/28080 [36:43:11<18:44:49,  7.10s/it]
 66%|██████▌   | 18577/28080 [36:43:18<18:43:03,  7.09s/it]
                                                           
{'loss': 0.6165, 'learning_rate': 0.00013573355435439076, 'epoch': 7.94}

 66%|██████▌   | 18577/28080 [36:43:18<18:43:03,  7.09s/it]
 66%|██████▌   | 18578/28080 [36:43:25<18:38:43,  7.06s/it]
                                                           
{'loss': 0.6066, 'learning_rate': 0.00013570790768787334, 'epoch': 7.94}

 66%|██████▌   | 18578/28080 [36:43:25<18:38:43,  7.06s/it]
 66%|██████▌   | 18579/28080 [36:43:32<18:41:36,  7.08s/it]
                                                           
{'loss': 0.6077, 'learning_rate': 0.00013568226254189407, 'epoch': 7.94}

 66%|██████▌   | 18579/28080 [36:43:32<18:41:36,  7.08s/it]
 66%|██████▌   | 18580/28080 [36:43:39<18:40:43,  7.08s/it]
                                                           
{'loss': 0.6155, 'learning_rate': 0.00013565661891679447, 'epoch': 7.94}

 66%|██████▌   | 18580/28080 [36:43:39<18:40:43,  7.08s/it]
 66%|██████▌   | 18581/28080 [36:43:46<18:46:31,  7.12s/it]
                                                           
{'loss': 0.6257, 'learning_rate': 0.00013563097681291552, 'epoch': 7.94}

 66%|██████▌   | 18581/28080 [36:43:46<18:46:31,  7.12s/it]
 66%|██████▌   | 18582/28080 [36:43:53<18:46:53,  7.12s/it]
                                                           
{'loss': 0.597, 'learning_rate': 0.00013560533623059853, 'epoch': 7.94}

 66%|██████▌   | 18582/28080 [36:43:53<18:46:53,  7.12s/it]
 66%|██████▌   | 18583/28080 [36:44:00<18:48:56,  7.13s/it]
                                                           
{'loss': 0.6277, 'learning_rate': 0.00013557969717018452, 'epoch': 7.94}

 66%|██████▌   | 18583/28080 [36:44:00<18:48:56,  7.13s/it]
 66%|██████▌   | 18584/28080 [36:44:08<18:47:47,  7.13s/it]
                                                           
{'loss': 0.6061, 'learning_rate': 0.00013555405963201463, 'epoch': 7.94}

 66%|██████▌   | 18584/28080 [36:44:08<18:47:47,  7.13s/it]
 66%|██████▌   | 18585/28080 [36:44:15<18:45:46,  7.11s/it]
                                                           
{'loss': 0.6047, 'learning_rate': 0.00013552842361642974, 'epoch': 7.94}

 66%|██████▌   | 18585/28080 [36:44:15<18:45:46,  7.11s/it]
 66%|██████▌   | 18586/28080 [36:44:22<18:49:59,  7.14s/it]
                                                           
{'loss': 0.5992, 'learning_rate': 0.00013550278912377123, 'epoch': 7.94}

 66%|██████▌   | 18586/28080 [36:44:22<18:49:59,  7.14s/it]
 66%|██████▌   | 18587/28080 [36:44:29<18:51:01,  7.15s/it]
                                                           
{'loss': 0.5906, 'learning_rate': 0.00013547715615438, 'epoch': 7.94}

 66%|██████▌   | 18587/28080 [36:44:29<18:51:01,  7.15s/it]
 66%|██████▌   | 18588/28080 [36:44:36<18:54:06,  7.17s/it]
                                                           
{'loss': 0.6006, 'learning_rate': 0.00013545152470859705, 'epoch': 7.94}

 66%|██████▌   | 18588/28080 [36:44:36<18:54:06,  7.17s/it]
 66%|██████▌   | 18589/28080 [36:44:43<18:55:23,  7.18s/it]
                                                           
{'loss': 0.5933, 'learning_rate': 0.00013542589478676326, 'epoch': 7.94}

 66%|██████▌   | 18589/28080 [36:44:43<18:55:23,  7.18s/it]
 66%|██████▌   | 18590/28080 [36:44:51<18:53:42,  7.17s/it]
                                                           
{'loss': 0.6197, 'learning_rate': 0.00013540026638921988, 'epoch': 7.94}

 66%|██████▌   | 18590/28080 [36:44:51<18:53:42,  7.17s/it]
 66%|██████▌   | 18591/28080 [36:44:58<18:55:09,  7.18s/it]
                                                           
{'loss': 0.5987, 'learning_rate': 0.00013537463951630757, 'epoch': 7.94}

 66%|██████▌   | 18591/28080 [36:44:58<18:55:09,  7.18s/it]
 66%|██████▌   | 18592/28080 [36:45:05<18:48:10,  7.13s/it]
                                                           
{'loss': 0.619, 'learning_rate': 0.0001353490141683677, 'epoch': 7.94}

 66%|██████▌   | 18592/28080 [36:45:05<18:48:10,  7.13s/it]
 66%|██████▌   | 18593/28080 [36:45:12<18:41:45,  7.09s/it]
                                                           
{'loss': 0.6027, 'learning_rate': 0.00013532339034574067, 'epoch': 7.94}

 66%|██████▌   | 18593/28080 [36:45:12<18:41:45,  7.09s/it]
 66%|██████▌   | 18594/28080 [36:45:19<18:45:33,  7.12s/it]
                                                           
{'loss': 0.6084, 'learning_rate': 0.00013529776804876775, 'epoch': 7.94}

 66%|██████▌   | 18594/28080 [36:45:19<18:45:33,  7.12s/it]
 66%|██████▌   | 18595/28080 [36:45:26<18:47:28,  7.13s/it]
                                                           
{'loss': 0.5999, 'learning_rate': 0.00013527214727778968, 'epoch': 7.94}

 66%|██████▌   | 18595/28080 [36:45:26<18:47:28,  7.13s/it]
 66%|██████▌   | 18596/28080 [36:45:33<18:45:19,  7.12s/it]
                                                           
{'loss': 0.5948, 'learning_rate': 0.00013524652803314724, 'epoch': 7.94}

 66%|██████▌   | 18596/28080 [36:45:33<18:45:19,  7.12s/it]
 66%|██████▌   | 18597/28080 [36:45:40<18:48:28,  7.14s/it]
                                                           
{'loss': 0.5822, 'learning_rate': 0.00013522091031518158, 'epoch': 7.94}

 66%|██████▌   | 18597/28080 [36:45:40<18:48:28,  7.14s/it]
 66%|██████▌   | 18598/28080 [36:45:47<18:43:20,  7.11s/it]
                                                           
{'loss': 0.6061, 'learning_rate': 0.00013519529412423306, 'epoch': 7.94}

 66%|██████▌   | 18598/28080 [36:45:47<18:43:20,  7.11s/it]
 66%|██████▌   | 18599/28080 [36:45:54<18:36:35,  7.07s/it]
                                                           
{'loss': 0.6138, 'learning_rate': 0.00013516967946064284, 'epoch': 7.95}

 66%|██████▌   | 18599/28080 [36:45:54<18:36:35,  7.07s/it]
 66%|██████▌   | 18600/28080 [36:46:01<18:36:41,  7.07s/it]
                                                           
{'loss': 0.6075, 'learning_rate': 0.00013514406632475146, 'epoch': 7.95}

 66%|██████▌   | 18600/28080 [36:46:01<18:36:41,  7.07s/it]
 66%|██████▌   | 18601/28080 [36:46:09<18:41:11,  7.10s/it]
                                                           
{'loss': 0.5997, 'learning_rate': 0.0001351184547168999, 'epoch': 7.95}

 66%|██████▌   | 18601/28080 [36:46:09<18:41:11,  7.10s/it]
 66%|██████▌   | 18602/28080 [36:46:16<18:43:15,  7.11s/it]
                                                           
{'loss': 0.6261, 'learning_rate': 0.00013509284463742878, 'epoch': 7.95}

 66%|██████▌   | 18602/28080 [36:46:16<18:43:15,  7.11s/it]
 66%|██████▋   | 18603/28080 [36:46:23<18:42:12,  7.10s/it]
                                                           
{'loss': 0.6255, 'learning_rate': 0.00013506723608667882, 'epoch': 7.95}

 66%|██████▋   | 18603/28080 [36:46:23<18:42:12,  7.10s/it]
 66%|██████▋   | 18604/28080 [36:46:30<18:39:46,  7.09s/it]
                                                           
{'loss': 0.6147, 'learning_rate': 0.0001350416290649906, 'epoch': 7.95}

 66%|██████▋   | 18604/28080 [36:46:30<18:39:46,  7.09s/it]
 66%|██████▋   | 18605/28080 [36:46:37<18:38:29,  7.08s/it]
                                                           
{'loss': 0.6245, 'learning_rate': 0.00013501602357270502, 'epoch': 7.95}

 66%|██████▋   | 18605/28080 [36:46:37<18:38:29,  7.08s/it]
 66%|██████▋   | 18606/28080 [36:46:44<18:41:10,  7.10s/it]
                                                           
{'loss': 0.6015, 'learning_rate': 0.00013499041961016262, 'epoch': 7.95}

 66%|██████▋   | 18606/28080 [36:46:44<18:41:10,  7.10s/it]
 66%|██████▋   | 18607/28080 [36:46:51<18:43:43,  7.12s/it]
                                                           
{'loss': 0.5973, 'learning_rate': 0.00013496481717770404, 'epoch': 7.95}

 66%|██████▋   | 18607/28080 [36:46:51<18:43:43,  7.12s/it]
 66%|██████▋   | 18608/28080 [36:46:58<18:42:36,  7.11s/it]
                                                           
{'loss': 0.6117, 'learning_rate': 0.00013493921627566978, 'epoch': 7.95}

 66%|██████▋   | 18608/28080 [36:46:58<18:42:36,  7.11s/it]
 66%|██████▋   | 18609/28080 [36:47:05<18:41:18,  7.10s/it]
                                                           
{'loss': 0.6115, 'learning_rate': 0.00013491361690440065, 'epoch': 7.95}

 66%|██████▋   | 18609/28080 [36:47:05<18:41:18,  7.10s/it]
 66%|██████▋   | 18610/28080 [36:47:12<18:37:56,  7.08s/it]
                                                           
{'loss': 0.603, 'learning_rate': 0.00013488801906423703, 'epoch': 7.95}

 66%|██████▋   | 18610/28080 [36:47:12<18:37:56,  7.08s/it]
 66%|██████▋   | 18611/28080 [36:47:20<18:39:17,  7.09s/it]
                                                           
{'loss': 0.6034, 'learning_rate': 0.00013486242275551974, 'epoch': 7.95}

 66%|██████▋   | 18611/28080 [36:47:20<18:39:17,  7.09s/it]
 66%|██████▋   | 18612/28080 [36:47:27<18:41:24,  7.11s/it]
                                                           
{'loss': 0.6141, 'learning_rate': 0.00013483682797858898, 'epoch': 7.95}

 66%|██████▋   | 18612/28080 [36:47:27<18:41:24,  7.11s/it]
 66%|██████▋   | 18613/28080 [36:47:34<18:43:48,  7.12s/it]
                                                           
{'loss': 0.5951, 'learning_rate': 0.00013481123473378548, 'epoch': 7.95}

 66%|██████▋   | 18613/28080 [36:47:34<18:43:48,  7.12s/it]
 66%|██████▋   | 18614/28080 [36:47:41<18:46:18,  7.14s/it]
                                                           
{'loss': 0.5927, 'learning_rate': 0.00013478564302144957, 'epoch': 7.95}

 66%|██████▋   | 18614/28080 [36:47:41<18:46:18,  7.14s/it]
 66%|██████▋   | 18615/28080 [36:47:48<18:44:35,  7.13s/it]
                                                           
{'loss': 0.6351, 'learning_rate': 0.00013476005284192194, 'epoch': 7.95}

 66%|██████▋   | 18615/28080 [36:47:48<18:44:35,  7.13s/it]
 66%|██████▋   | 18616/28080 [36:47:55<18:47:57,  7.15s/it]
                                                           
{'loss': 0.5906, 'learning_rate': 0.00013473446419554289, 'epoch': 7.95}

 66%|██████▋   | 18616/28080 [36:47:55<18:47:57,  7.15s/it]
 66%|██████▋   | 18617/28080 [36:48:02<18:45:11,  7.13s/it]
                                                           
{'loss': 0.598, 'learning_rate': 0.00013470887708265288, 'epoch': 7.95}

 66%|██████▋   | 18617/28080 [36:48:02<18:45:11,  7.13s/it]
 66%|██████▋   | 18618/28080 [36:48:10<18:44:08,  7.13s/it]
                                                           
{'loss': 0.6223, 'learning_rate': 0.00013468329150359226, 'epoch': 7.95}

 66%|██████▋   | 18618/28080 [36:48:10<18:44:08,  7.13s/it]
 66%|██████▋   | 18619/28080 [36:48:17<18:52:23,  7.18s/it]
                                                           
{'loss': 0.6208, 'learning_rate': 0.00013465770745870156, 'epoch': 7.95}

 66%|██████▋   | 18619/28080 [36:48:17<18:52:23,  7.18s/it]
 66%|██████▋   | 18620/28080 [36:48:24<18:47:52,  7.15s/it]
                                                           
{'loss': 0.6163, 'learning_rate': 0.00013463212494832107, 'epoch': 7.95}

 66%|██████▋   | 18620/28080 [36:48:24<18:47:52,  7.15s/it]
 66%|██████▋   | 18621/28080 [36:48:31<18:43:46,  7.13s/it]
                                                           
{'loss': 0.5731, 'learning_rate': 0.00013460654397279116, 'epoch': 7.95}

 66%|██████▋   | 18621/28080 [36:48:31<18:43:46,  7.13s/it]
 66%|██████▋   | 18622/28080 [36:48:38<18:45:10,  7.14s/it]
                                                           
{'loss': 0.6048, 'learning_rate': 0.00013458096453245212, 'epoch': 7.96}

 66%|██████▋   | 18622/28080 [36:48:38<18:45:10,  7.14s/it]
 66%|██████▋   | 18623/28080 [36:48:45<18:38:14,  7.09s/it]
                                                           
{'loss': 0.5923, 'learning_rate': 0.00013455538662764417, 'epoch': 7.96}

 66%|██████▋   | 18623/28080 [36:48:45<18:38:14,  7.09s/it]
 66%|██████▋   | 18624/28080 [36:48:52<18:37:43,  7.09s/it]
                                                           
{'loss': 0.6049, 'learning_rate': 0.00013452981025870777, 'epoch': 7.96}

 66%|██████▋   | 18624/28080 [36:48:52<18:37:43,  7.09s/it]
 66%|██████▋   | 18625/28080 [36:48:59<18:39:18,  7.10s/it]
                                                           
{'loss': 0.6078, 'learning_rate': 0.00013450423542598318, 'epoch': 7.96}

 66%|██████▋   | 18625/28080 [36:48:59<18:39:18,  7.10s/it]
 66%|██████▋   | 18626/28080 [36:49:07<18:42:24,  7.12s/it]
                                                           
{'loss': 0.5951, 'learning_rate': 0.00013447866212981056, 'epoch': 7.96}

 66%|██████▋   | 18626/28080 [36:49:07<18:42:24,  7.12s/it]
 66%|██████▋   | 18627/28080 [36:49:14<18:38:59,  7.10s/it]
                                                           
{'loss': 0.6244, 'learning_rate': 0.00013445309037053005, 'epoch': 7.96}

 66%|██████▋   | 18627/28080 [36:49:14<18:38:59,  7.10s/it]
 66%|██████▋   | 18628/28080 [36:49:21<18:40:02,  7.11s/it]
                                                           
{'loss': 0.6139, 'learning_rate': 0.0001344275201484821, 'epoch': 7.96}

 66%|██████▋   | 18628/28080 [36:49:21<18:40:02,  7.11s/it]
 66%|██████▋   | 18629/28080 [36:49:28<18:40:48,  7.12s/it]
                                                           
{'loss': 0.6206, 'learning_rate': 0.00013440195146400662, 'epoch': 7.96}

 66%|██████▋   | 18629/28080 [36:49:28<18:40:48,  7.12s/it]
 66%|██████▋   | 18630/28080 [36:49:35<18:34:46,  7.08s/it]
                                                           
{'loss': 0.61, 'learning_rate': 0.0001343763843174441, 'epoch': 7.96}

 66%|██████▋   | 18630/28080 [36:49:35<18:34:46,  7.08s/it]
 66%|██████▋   | 18631/28080 [36:49:42<18:37:30,  7.10s/it]
                                                           
{'loss': 0.5883, 'learning_rate': 0.00013435081870913444, 'epoch': 7.96}

 66%|██████▋   | 18631/28080 [36:49:42<18:37:30,  7.10s/it]
 66%|██████▋   | 18632/28080 [36:49:49<18:37:28,  7.10s/it]
                                                           
{'loss': 0.5995, 'learning_rate': 0.00013432525463941787, 'epoch': 7.96}

 66%|██████▋   | 18632/28080 [36:49:49<18:37:28,  7.10s/it]
 66%|██████▋   | 18633/28080 [36:49:56<18:41:57,  7.13s/it]
                                                           
{'loss': 0.6115, 'learning_rate': 0.0001342996921086343, 'epoch': 7.96}

 66%|██████▋   | 18633/28080 [36:49:56<18:41:57,  7.13s/it]
 66%|██████▋   | 18634/28080 [36:50:03<18:40:33,  7.12s/it]
                                                           
{'loss': 0.5999, 'learning_rate': 0.0001342741311171241, 'epoch': 7.96}

 66%|██████▋   | 18634/28080 [36:50:03<18:40:33,  7.12s/it]
 66%|██████▋   | 18635/28080 [36:50:10<18:37:10,  7.10s/it]
                                                           
{'loss': 0.6233, 'learning_rate': 0.00013424857166522718, 'epoch': 7.96}

 66%|██████▋   | 18635/28080 [36:50:10<18:37:10,  7.10s/it]
 66%|██████▋   | 18636/28080 [36:50:18<18:39:17,  7.11s/it]
                                                           
{'loss': 0.6202, 'learning_rate': 0.0001342230137532836, 'epoch': 7.96}

 66%|██████▋   | 18636/28080 [36:50:18<18:39:17,  7.11s/it]
 66%|██████▋   | 18637/28080 [36:50:25<18:43:27,  7.14s/it]
                                                           
{'loss': 0.5777, 'learning_rate': 0.00013419745738163332, 'epoch': 7.96}

 66%|██████▋   | 18637/28080 [36:50:25<18:43:27,  7.14s/it]
 66%|██████▋   | 18638/28080 [36:50:32<18:43:57,  7.14s/it]
                                                           
{'loss': 0.6079, 'learning_rate': 0.00013417190255061645, 'epoch': 7.96}

 66%|██████▋   | 18638/28080 [36:50:32<18:43:57,  7.14s/it]
 66%|██████▋   | 18639/28080 [36:50:39<18:36:19,  7.09s/it]
                                                           
{'loss': 0.5911, 'learning_rate': 0.00013414634926057285, 'epoch': 7.96}

 66%|██████▋   | 18639/28080 [36:50:39<18:36:19,  7.09s/it]
 66%|██████▋   | 18640/28080 [36:50:46<18:38:15,  7.11s/it]
                                                           
{'loss': 0.6276, 'learning_rate': 0.00013412079751184275, 'epoch': 7.96}

 66%|██████▋   | 18640/28080 [36:50:46<18:38:15,  7.11s/it]
 66%|██████▋   | 18641/28080 [36:50:53<18:41:56,  7.13s/it]
                                                           
{'loss': 0.5996, 'learning_rate': 0.00013409524730476568, 'epoch': 7.96}

 66%|██████▋   | 18641/28080 [36:50:53<18:41:56,  7.13s/it]
 66%|██████▋   | 18642/28080 [36:51:00<18:35:21,  7.09s/it]
                                                           
{'loss': 0.6069, 'learning_rate': 0.0001340696986396819, 'epoch': 7.96}

 66%|██████▋   | 18642/28080 [36:51:00<18:35:21,  7.09s/it]
 66%|██████▋   | 18643/28080 [36:51:07<18:34:22,  7.09s/it]
                                                           
{'loss': 0.6068, 'learning_rate': 0.00013404415151693105, 'epoch': 7.96}

 66%|██████▋   | 18643/28080 [36:51:07<18:34:22,  7.09s/it]
 66%|██████▋   | 18644/28080 [36:51:14<18:34:36,  7.09s/it]
                                                           
{'loss': 0.6149, 'learning_rate': 0.00013401860593685328, 'epoch': 7.96}

 66%|██████▋   | 18644/28080 [36:51:14<18:34:36,  7.09s/it]
 66%|██████▋   | 18645/28080 [36:51:22<18:35:57,  7.10s/it]
                                                           
{'loss': 0.6017, 'learning_rate': 0.00013399306189978838, 'epoch': 7.96}

 66%|██████▋   | 18645/28080 [36:51:22<18:35:57,  7.10s/it]
 66%|██████▋   | 18646/28080 [36:51:29<18:40:47,  7.13s/it]
                                                           
{'loss': 0.6108, 'learning_rate': 0.0001339675194060759, 'epoch': 7.97}

 66%|██████▋   | 18646/28080 [36:51:29<18:40:47,  7.13s/it]
 66%|██████▋   | 18647/28080 [36:51:36<18:42:49,  7.14s/it]
                                                           
{'loss': 0.5948, 'learning_rate': 0.000133941978456056, 'epoch': 7.97}

 66%|██████▋   | 18647/28080 [36:51:36<18:42:49,  7.14s/it]
 66%|██████▋   | 18648/28080 [36:51:43<18:39:50,  7.12s/it]
                                                           
{'loss': 0.5987, 'learning_rate': 0.00013391643905006823, 'epoch': 7.97}

 66%|██████▋   | 18648/28080 [36:51:43<18:39:50,  7.12s/it]
 66%|██████▋   | 18649/28080 [36:51:50<18:39:23,  7.12s/it]
                                                           
{'loss': 0.6227, 'learning_rate': 0.0001338909011884526, 'epoch': 7.97}

 66%|██████▋   | 18649/28080 [36:51:50<18:39:23,  7.12s/it]
 66%|██████▋   | 18650/28080 [36:51:57<18:38:34,  7.12s/it]
                                                           
{'loss': 0.6149, 'learning_rate': 0.0001338653648715487, 'epoch': 7.97}

 66%|██████▋   | 18650/28080 [36:51:57<18:38:34,  7.12s/it]
 66%|██████▋   | 18651/28080 [36:52:04<18:36:55,  7.11s/it]
                                                           
{'loss': 0.6079, 'learning_rate': 0.00013383983009969635, 'epoch': 7.97}

 66%|██████▋   | 18651/28080 [36:52:04<18:36:55,  7.11s/it]
 66%|██████▋   | 18652/28080 [36:52:11<18:35:32,  7.10s/it]
                                                           
{'loss': 0.6188, 'learning_rate': 0.00013381429687323512, 'epoch': 7.97}

 66%|██████▋   | 18652/28080 [36:52:11<18:35:32,  7.10s/it]
 66%|██████▋   | 18653/28080 [36:52:19<18:37:52,  7.11s/it]
                                                           
{'loss': 0.6065, 'learning_rate': 0.0001337887651925049, 'epoch': 7.97}

 66%|██████▋   | 18653/28080 [36:52:19<18:37:52,  7.11s/it]
 66%|██████▋   | 18654/28080 [36:52:26<18:39:31,  7.13s/it]
                                                           
{'loss': 0.6363, 'learning_rate': 0.00013376323505784527, 'epoch': 7.97}

 66%|██████▋   | 18654/28080 [36:52:26<18:39:31,  7.13s/it]
 66%|██████▋   | 18655/28080 [36:52:33<18:33:52,  7.09s/it]
                                                           
{'loss': 0.6164, 'learning_rate': 0.00013373770646959591, 'epoch': 7.97}

 66%|██████▋   | 18655/28080 [36:52:33<18:33:52,  7.09s/it]
 66%|██████▋   | 18656/28080 [36:52:40<18:27:53,  7.05s/it]
                                                           
{'loss': 0.5939, 'learning_rate': 0.0001337121794280963, 'epoch': 7.97}

 66%|██████▋   | 18656/28080 [36:52:40<18:27:53,  7.05s/it]
 66%|██████▋   | 18657/28080 [36:52:47<18:32:19,  7.08s/it]
                                                           
{'loss': 0.6234, 'learning_rate': 0.00013368665393368627, 'epoch': 7.97}

 66%|██████▋   | 18657/28080 [36:52:47<18:32:19,  7.08s/it]
 66%|██████▋   | 18658/28080 [36:52:54<18:32:50,  7.09s/it]
                                                           
{'loss': 0.6087, 'learning_rate': 0.00013366112998670522, 'epoch': 7.97}

 66%|██████▋   | 18658/28080 [36:52:54<18:32:50,  7.09s/it]
 66%|██████▋   | 18659/28080 [36:53:01<18:37:50,  7.12s/it]
                                                           
{'loss': 0.5933, 'learning_rate': 0.00013363560758749302, 'epoch': 7.97}

 66%|██████▋   | 18659/28080 [36:53:01<18:37:50,  7.12s/it]
 66%|██████▋   | 18660/28080 [36:53:08<18:39:48,  7.13s/it]
                                                           
{'loss': 0.6024, 'learning_rate': 0.0001336100867363888, 'epoch': 7.97}

 66%|██████▋   | 18660/28080 [36:53:08<18:39:48,  7.13s/it]
 66%|██████▋   | 18661/28080 [36:53:15<18:37:11,  7.12s/it]
                                                           
{'loss': 0.625, 'learning_rate': 0.00013358456743373242, 'epoch': 7.97}

 66%|██████▋   | 18661/28080 [36:53:15<18:37:11,  7.12s/it]
 66%|██████▋   | 18662/28080 [36:53:22<18:37:39,  7.12s/it]
                                                           
{'loss': 0.6038, 'learning_rate': 0.00013355904967986317, 'epoch': 7.97}

 66%|██████▋   | 18662/28080 [36:53:22<18:37:39,  7.12s/it]
 66%|██████▋   | 18663/28080 [36:53:30<18:39:18,  7.13s/it]
                                                           
{'loss': 0.6089, 'learning_rate': 0.00013353353347512077, 'epoch': 7.97}

 66%|██████▋   | 18663/28080 [36:53:30<18:39:18,  7.13s/it]
 66%|██████▋   | 18664/28080 [36:53:37<18:38:25,  7.13s/it]
                                                           
{'loss': 0.6085, 'learning_rate': 0.00013350801881984448, 'epoch': 7.97}

 66%|██████▋   | 18664/28080 [36:53:37<18:38:25,  7.13s/it]
 66%|██████▋   | 18665/28080 [36:53:44<18:32:53,  7.09s/it]
                                                           
{'loss': 0.5946, 'learning_rate': 0.00013348250571437387, 'epoch': 7.97}

 66%|██████▋   | 18665/28080 [36:53:44<18:32:53,  7.09s/it]
 66%|██████▋   | 18666/28080 [36:53:51<18:35:48,  7.11s/it]
                                                           
{'loss': 0.5923, 'learning_rate': 0.00013345699415904822, 'epoch': 7.97}

 66%|██████▋   | 18666/28080 [36:53:51<18:35:48,  7.11s/it]
 66%|██████▋   | 18667/28080 [36:53:58<18:37:51,  7.13s/it]
                                                           
{'loss': 0.6184, 'learning_rate': 0.00013343148415420714, 'epoch': 7.97}

 66%|██████▋   | 18667/28080 [36:53:58<18:37:51,  7.13s/it]
 66%|██████▋   | 18668/28080 [36:54:05<18:39:51,  7.14s/it]
                                                           
{'loss': 0.6075, 'learning_rate': 0.00013340597570018987, 'epoch': 7.97}

 66%|██████▋   | 18668/28080 [36:54:05<18:39:51,  7.14s/it]
 66%|██████▋   | 18669/28080 [36:54:12<18:36:52,  7.12s/it]
                                                           
{'loss': 0.5977, 'learning_rate': 0.00013338046879733583, 'epoch': 7.98}

 66%|██████▋   | 18669/28080 [36:54:12<18:36:52,  7.12s/it]
 66%|██████▋   | 18670/28080 [36:54:19<18:32:00,  7.09s/it]
                                                           
{'loss': 0.6233, 'learning_rate': 0.00013335496344598437, 'epoch': 7.98}

 66%|██████▋   | 18670/28080 [36:54:19<18:32:00,  7.09s/it]
 66%|██████▋   | 18671/28080 [36:54:26<18:31:24,  7.09s/it]
                                                           
{'loss': 0.6017, 'learning_rate': 0.00013332945964647465, 'epoch': 7.98}

 66%|██████▋   | 18671/28080 [36:54:26<18:31:24,  7.09s/it]
 66%|██████▋   | 18672/28080 [36:54:34<18:32:05,  7.09s/it]
                                                           
{'loss': 0.6331, 'learning_rate': 0.0001333039573991462, 'epoch': 7.98}

 66%|██████▋   | 18672/28080 [36:54:34<18:32:05,  7.09s/it]
 66%|██████▋   | 18673/28080 [36:54:41<18:38:20,  7.13s/it]
                                                           
{'loss': 0.5992, 'learning_rate': 0.00013327845670433821, 'epoch': 7.98}

 66%|██████▋   | 18673/28080 [36:54:41<18:38:20,  7.13s/it]
 67%|██████▋   | 18674/28080 [36:54:48<18:40:29,  7.15s/it]
                                                           
{'loss': 0.6079, 'learning_rate': 0.00013325295756238994, 'epoch': 7.98}

 67%|██████▋   | 18674/28080 [36:54:48<18:40:29,  7.15s/it]
 67%|██████▋   | 18675/28080 [36:54:55<18:37:57,  7.13s/it]
                                                           
{'loss': 0.6302, 'learning_rate': 0.00013322745997364056, 'epoch': 7.98}

 67%|██████▋   | 18675/28080 [36:54:55<18:37:57,  7.13s/it]
 67%|██████▋   | 18676/28080 [36:55:02<18:38:33,  7.14s/it]
                                                           
{'loss': 0.6201, 'learning_rate': 0.00013320196393842943, 'epoch': 7.98}

 67%|██████▋   | 18676/28080 [36:55:02<18:38:33,  7.14s/it]
 67%|██████▋   | 18677/28080 [36:55:09<18:42:37,  7.16s/it]
                                                           
{'loss': 0.6173, 'learning_rate': 0.00013317646945709558, 'epoch': 7.98}

 67%|██████▋   | 18677/28080 [36:55:09<18:42:37,  7.16s/it]
 67%|██████▋   | 18678/28080 [36:55:17<18:39:44,  7.15s/it]
                                                           
{'loss': 0.6141, 'learning_rate': 0.00013315097652997836, 'epoch': 7.98}

 67%|██████▋   | 18678/28080 [36:55:17<18:39:44,  7.15s/it]
 67%|██████▋   | 18679/28080 [36:55:24<18:41:38,  7.16s/it]
                                                           
{'loss': 0.6113, 'learning_rate': 0.0001331254851574169, 'epoch': 7.98}

 67%|██████▋   | 18679/28080 [36:55:24<18:41:38,  7.16s/it]
 67%|██████▋   | 18680/28080 [36:55:31<18:39:49,  7.15s/it]
                                                           
{'loss': 0.6003, 'learning_rate': 0.00013309999533975026, 'epoch': 7.98}

 67%|██████▋   | 18680/28080 [36:55:31<18:39:49,  7.15s/it]
 67%|██████▋   | 18681/28080 [36:55:38<18:39:46,  7.15s/it]
                                                           
{'loss': 0.6121, 'learning_rate': 0.0001330745070773175, 'epoch': 7.98}

 67%|██████▋   | 18681/28080 [36:55:38<18:39:46,  7.15s/it]
 67%|██████▋   | 18682/28080 [36:55:45<18:39:31,  7.15s/it]
                                                           
{'loss': 0.6131, 'learning_rate': 0.0001330490203704579, 'epoch': 7.98}

 67%|██████▋   | 18682/28080 [36:55:45<18:39:31,  7.15s/it]
 67%|██████▋   | 18683/28080 [36:55:52<18:38:10,  7.14s/it]
                                                           
{'loss': 0.6317, 'learning_rate': 0.00013302353521951038, 'epoch': 7.98}

 67%|██████▋   | 18683/28080 [36:55:52<18:38:10,  7.14s/it]
 67%|██████▋   | 18684/28080 [36:55:59<18:40:37,  7.16s/it]
                                                           
{'loss': 0.6208, 'learning_rate': 0.0001329980516248141, 'epoch': 7.98}

 67%|██████▋   | 18684/28080 [36:55:59<18:40:37,  7.16s/it]
 67%|██████▋   | 18685/28080 [36:56:07<18:38:13,  7.14s/it]
                                                           
{'loss': 0.6178, 'learning_rate': 0.00013297256958670793, 'epoch': 7.98}

 67%|██████▋   | 18685/28080 [36:56:07<18:38:13,  7.14s/it]
 67%|██████▋   | 18686/28080 [36:56:14<18:38:02,  7.14s/it]
                                                           
{'loss': 0.596, 'learning_rate': 0.00013294708910553107, 'epoch': 7.98}

 67%|██████▋   | 18686/28080 [36:56:14<18:38:02,  7.14s/it]
 67%|██████▋   | 18687/28080 [36:56:21<18:34:48,  7.12s/it]
                                                           
{'loss': 0.6282, 'learning_rate': 0.00013292161018162247, 'epoch': 7.98}

 67%|██████▋   | 18687/28080 [36:56:21<18:34:48,  7.12s/it]
 67%|██████▋   | 18688/28080 [36:56:28<18:34:03,  7.12s/it]
                                                           
{'loss': 0.6222, 'learning_rate': 0.00013289613281532105, 'epoch': 7.98}

 67%|██████▋   | 18688/28080 [36:56:28<18:34:03,  7.12s/it]
 67%|██████▋   | 18689/28080 [36:56:35<18:34:00,  7.12s/it]
                                                           
{'loss': 0.652, 'learning_rate': 0.00013287065700696564, 'epoch': 7.98}

 67%|██████▋   | 18689/28080 [36:56:35<18:34:00,  7.12s/it]
 67%|██████▋   | 18690/28080 [36:56:42<18:31:16,  7.10s/it]
                                                           
{'loss': 0.6161, 'learning_rate': 0.00013284518275689543, 'epoch': 7.98}

 67%|██████▋   | 18690/28080 [36:56:42<18:31:16,  7.10s/it]
 67%|██████▋   | 18691/28080 [36:56:49<18:35:24,  7.13s/it]
                                                           
{'loss': 0.5951, 'learning_rate': 0.00013281971006544907, 'epoch': 7.98}

 67%|██████▋   | 18691/28080 [36:56:49<18:35:24,  7.13s/it]
 67%|██████▋   | 18692/28080 [36:56:56<18:32:46,  7.11s/it]
                                                           
{'loss': 0.6034, 'learning_rate': 0.00013279423893296571, 'epoch': 7.99}

 67%|██████▋   | 18692/28080 [36:56:56<18:32:46,  7.11s/it]
 67%|██████▋   | 18693/28080 [36:57:03<18:33:40,  7.12s/it]
                                                           
{'loss': 0.6097, 'learning_rate': 0.0001327687693597841, 'epoch': 7.99}

 67%|██████▋   | 18693/28080 [36:57:03<18:33:40,  7.12s/it]
 67%|██████▋   | 18694/28080 [36:57:11<18:36:25,  7.14s/it]
                                                           
{'loss': 0.6116, 'learning_rate': 0.00013274330134624307, 'epoch': 7.99}

 67%|██████▋   | 18694/28080 [36:57:11<18:36:25,  7.14s/it]
 67%|██████▋   | 18695/28080 [36:57:18<18:32:27,  7.11s/it]
                                                           
{'loss': 0.608, 'learning_rate': 0.0001327178348926814, 'epoch': 7.99}

 67%|██████▋   | 18695/28080 [36:57:18<18:32:27,  7.11s/it]
 67%|██████▋   | 18696/28080 [36:57:25<18:34:32,  7.13s/it]
                                                           
{'loss': 0.6059, 'learning_rate': 0.0001326923699994379, 'epoch': 7.99}

 67%|██████▋   | 18696/28080 [36:57:25<18:34:32,  7.13s/it]
 67%|██████▋   | 18697/28080 [36:57:32<18:34:26,  7.13s/it]
                                                           
{'loss': 0.6095, 'learning_rate': 0.0001326669066668515, 'epoch': 7.99}

 67%|██████▋   | 18697/28080 [36:57:32<18:34:26,  7.13s/it]
 67%|██████▋   | 18698/28080 [36:57:39<18:36:16,  7.14s/it]
                                                           
{'loss': 0.6006, 'learning_rate': 0.00013264144489526082, 'epoch': 7.99}

 67%|██████▋   | 18698/28080 [36:57:39<18:36:16,  7.14s/it]
 67%|██████▋   | 18699/28080 [36:57:46<18:37:35,  7.15s/it]
                                                           
{'loss': 0.6097, 'learning_rate': 0.00013261598468500467, 'epoch': 7.99}

 67%|██████▋   | 18699/28080 [36:57:46<18:37:35,  7.15s/it]
 67%|██████▋   | 18700/28080 [36:57:53<18:37:40,  7.15s/it]
                                                           
{'loss': 0.6168, 'learning_rate': 0.00013259052603642165, 'epoch': 7.99}

 67%|██████▋   | 18700/28080 [36:57:53<18:37:40,  7.15s/it]
 67%|██████▋   | 18701/28080 [36:58:01<18:37:26,  7.15s/it]
                                                           
{'loss': 0.6223, 'learning_rate': 0.0001325650689498506, 'epoch': 7.99}

 67%|██████▋   | 18701/28080 [36:58:01<18:37:26,  7.15s/it]
 67%|██████▋   | 18702/28080 [36:58:08<18:33:59,  7.13s/it]
                                                           
{'loss': 0.6037, 'learning_rate': 0.0001325396134256302, 'epoch': 7.99}

 67%|██████▋   | 18702/28080 [36:58:08<18:33:59,  7.13s/it]
 67%|██████▋   | 18703/28080 [36:58:15<18:29:49,  7.10s/it]
                                                           
{'loss': 0.6028, 'learning_rate': 0.00013251415946409907, 'epoch': 7.99}

 67%|██████▋   | 18703/28080 [36:58:15<18:29:49,  7.10s/it]
 67%|██████▋   | 18704/28080 [36:58:22<18:33:15,  7.12s/it]
                                                           
{'loss': 0.6056, 'learning_rate': 0.00013248870706559574, 'epoch': 7.99}

 67%|██████▋   | 18704/28080 [36:58:22<18:33:15,  7.12s/it]
 67%|██████▋   | 18705/28080 [36:58:29<18:31:57,  7.12s/it]
                                                           
{'loss': 0.6048, 'learning_rate': 0.00013246325623045903, 'epoch': 7.99}

 67%|██████▋   | 18705/28080 [36:58:29<18:31:57,  7.12s/it]
 67%|██████▋   | 18706/28080 [36:58:36<18:29:25,  7.10s/it]
                                                           
{'loss': 0.618, 'learning_rate': 0.00013243780695902736, 'epoch': 7.99}

 67%|██████▋   | 18706/28080 [36:58:36<18:29:25,  7.10s/it]
 67%|██████▋   | 18707/28080 [36:58:43<18:28:57,  7.10s/it]
                                                           
{'loss': 0.6293, 'learning_rate': 0.00013241235925163958, 'epoch': 7.99}

 67%|██████▋   | 18707/28080 [36:58:43<18:28:57,  7.10s/it]
 67%|██████▋   | 18708/28080 [36:58:50<18:31:47,  7.12s/it]
                                                           
{'loss': 0.6148, 'learning_rate': 0.00013238691310863383, 'epoch': 7.99}

 67%|██████▋   | 18708/28080 [36:58:50<18:31:47,  7.12s/it]
 67%|██████▋   | 18709/28080 [36:58:58<18:34:11,  7.13s/it]
                                                           
{'loss': 0.6068, 'learning_rate': 0.00013236146853034896, 'epoch': 7.99}

 67%|██████▋   | 18709/28080 [36:58:58<18:34:11,  7.13s/it]
 67%|██████▋   | 18710/28080 [36:59:05<18:34:18,  7.14s/it]
                                                           
{'loss': 0.6144, 'learning_rate': 0.00013233602551712331, 'epoch': 7.99}

 67%|██████▋   | 18710/28080 [36:59:05<18:34:18,  7.14s/it]
 67%|██████▋   | 18711/28080 [36:59:12<18:35:45,  7.15s/it]
                                                           
{'loss': 0.6043, 'learning_rate': 0.00013231058406929557, 'epoch': 7.99}

 67%|██████▋   | 18711/28080 [36:59:12<18:35:45,  7.15s/it]
 67%|██████▋   | 18712/28080 [36:59:19<18:31:42,  7.12s/it]
                                                           
{'loss': 0.6144, 'learning_rate': 0.00013228514418720406, 'epoch': 7.99}

 67%|██████▋   | 18712/28080 [36:59:19<18:31:42,  7.12s/it]
 67%|██████▋   | 18713/28080 [36:59:26<18:34:11,  7.14s/it]
                                                           
{'loss': 0.6324, 'learning_rate': 0.0001322597058711873, 'epoch': 7.99}

 67%|██████▋   | 18713/28080 [36:59:26<18:34:11,  7.14s/it]
 67%|██████▋   | 18714/28080 [36:59:33<18:30:02,  7.11s/it]
                                                           
{'loss': 0.6103, 'learning_rate': 0.00013223426912158356, 'epoch': 7.99}

 67%|██████▋   | 18714/28080 [36:59:33<18:30:02,  7.11s/it]
 67%|██████▋   | 18715/28080 [36:59:40<18:28:38,  7.10s/it]
                                                           
{'loss': 0.6258, 'learning_rate': 0.0001322088339387315, 'epoch': 7.99}

 67%|██████▋   | 18715/28080 [36:59:40<18:28:38,  7.10s/it]
 67%|██████▋   | 18716/28080 [36:59:47<18:27:20,  7.10s/it]
                                                           
{'loss': 0.5966, 'learning_rate': 0.00013218340032296937, 'epoch': 8.0}

 67%|██████▋   | 18716/28080 [36:59:47<18:27:20,  7.10s/it]
 67%|██████▋   | 18717/28080 [36:59:54<18:29:36,  7.11s/it]
                                                           
{'loss': 0.6281, 'learning_rate': 0.00013215796827463556, 'epoch': 8.0}

 67%|██████▋   | 18717/28080 [36:59:54<18:29:36,  7.11s/it]
 67%|██████▋   | 18718/28080 [37:00:01<18:20:54,  7.06s/it]
                                                           
{'loss': 0.632, 'learning_rate': 0.0001321325377940683, 'epoch': 8.0}

 67%|██████▋   | 18718/28080 [37:00:01<18:20:54,  7.06s/it]
 67%|██████▋   | 18719/28080 [37:00:08<18:25:01,  7.08s/it]
                                                           
{'loss': 0.6122, 'learning_rate': 0.00013210710888160617, 'epoch': 8.0}

 67%|██████▋   | 18719/28080 [37:00:08<18:25:01,  7.08s/it]
 67%|██████▋   | 18720/28080 [37:00:16<18:24:38,  7.08s/it]
                                                           
{'loss': 0.6187, 'learning_rate': 0.00013208168153758726, 'epoch': 8.0}

 67%|██████▋   | 18720/28080 [37:00:16<18:24:38,  7.08s/it]
 67%|██████▋   | 18721/28080 [37:00:23<18:24:01,  7.08s/it]
                                                           
{'loss': 0.6169, 'learning_rate': 0.00013205625576234996, 'epoch': 8.0}

 67%|██████▋   | 18721/28080 [37:00:23<18:24:01,  7.08s/it]
 67%|██████▋   | 18722/28080 [37:00:30<18:29:03,  7.11s/it]
                                                           
{'loss': 0.5894, 'learning_rate': 0.00013203083155623253, 'epoch': 8.0}

 67%|██████▋   | 18722/28080 [37:00:30<18:29:03,  7.11s/it]
 67%|██████▋   | 18723/28080 [37:00:37<18:28:11,  7.11s/it]
                                                           
{'loss': 0.611, 'learning_rate': 0.00013200540891957307, 'epoch': 8.0}

 67%|██████▋   | 18723/28080 [37:00:37<18:28:11,  7.11s/it]
 67%|██████▋   | 18724/28080 [37:00:44<18:32:48,  7.14s/it]
                                                           
{'loss': 0.5837, 'learning_rate': 0.00013197998785270998, 'epoch': 8.0}

 67%|██████▋   | 18724/28080 [37:00:44<18:32:48,  7.14s/it]
 67%|██████▋   | 18725/28080 [37:00:51<18:32:09,  7.13s/it]
                                                           
{'loss': 0.615, 'learning_rate': 0.00013195456835598136, 'epoch': 8.0}

 67%|██████▋   | 18725/28080 [37:00:51<18:32:09,  7.13s/it]
 67%|██████▋   | 18726/28080 [37:00:58<18:33:15,  7.14s/it]
                                                           
{'loss': 0.6095, 'learning_rate': 0.00013192915042972548, 'epoch': 8.0}

 67%|██████▋   | 18726/28080 [37:00:58<18:33:15,  7.14s/it]
 67%|██████▋   | 18727/28080 [37:01:06<18:40:40,  7.19s/it]
                                                           
{'loss': 0.6, 'learning_rate': 0.00013190373407428047, 'epoch': 8.0}

 67%|██████▋   | 18727/28080 [37:01:06<18:40:40,  7.19s/it]
 67%|██████▋   | 18728/28080 [37:01:13<18:59:26,  7.31s/it]
                                                           
{'loss': 0.5859, 'learning_rate': 0.0001318783192899844, 'epoch': 8.0}

 67%|██████▋   | 18728/28080 [37:01:13<18:59:26,  7.31s/it]
 67%|██████▋   | 18729/28080 [37:01:20<18:54:09,  7.28s/it]
                                                           
{'loss': 0.6143, 'learning_rate': 0.0001318529060771754, 'epoch': 8.0}

 67%|██████▋   | 18729/28080 [37:01:21<18:54:09,  7.28s/it]
 67%|██████▋   | 18730/28080 [37:01:28<18:44:23,  7.22s/it]
                                                           
{'loss': 0.6188, 'learning_rate': 0.00013182749443619167, 'epoch': 8.0}

 67%|██████▋   | 18730/28080 [37:01:28<18:44:23,  7.22s/it]
 67%|██████▋   | 18731/28080 [37:01:35<18:41:08,  7.20s/it]
                                                           
{'loss': 0.5868, 'learning_rate': 0.0001318020843673712, 'epoch': 8.0}

 67%|██████▋   | 18731/28080 [37:01:35<18:41:08,  7.20s/it]
 67%|██████▋   | 18732/28080 [37:01:42<18:31:17,  7.13s/it]
                                                           
{'loss': 0.611, 'learning_rate': 0.00013177667587105208, 'epoch': 8.0}

 67%|██████▋   | 18732/28080 [37:01:42<18:31:17,  7.13s/it]
 67%|██████▋   | 18733/28080 [37:01:49<18:30:14,  7.13s/it]
                                                           
{'loss': 0.5967, 'learning_rate': 0.0001317512689475722, 'epoch': 8.0}

 67%|██████▋   | 18733/28080 [37:01:49<18:30:14,  7.13s/it]
 67%|██████▋   | 18734/28080 [37:01:56<18:29:03,  7.12s/it]
                                                           
{'loss': 0.589, 'learning_rate': 0.00013172586359726983, 'epoch': 8.0}

 67%|██████▋   | 18734/28080 [37:01:56<18:29:03,  7.12s/it]
 67%|██████▋   | 18735/28080 [37:02:03<18:29:04,  7.12s/it]
                                                           
{'loss': 0.5954, 'learning_rate': 0.0001317004598204828, 'epoch': 8.0}

 67%|██████▋   | 18735/28080 [37:02:03<18:29:04,  7.12s/it]
 67%|██████▋   | 18736/28080 [37:02:10<18:27:12,  7.11s/it]
                                                           
{'loss': 0.6099, 'learning_rate': 0.00013167505761754912, 'epoch': 8.0}

 67%|██████▋   | 18736/28080 [37:02:10<18:27:12,  7.11s/it]
 67%|██████▋   | 18737/28080 [37:02:17<18:30:21,  7.13s/it]
                                                           
{'loss': 0.6206, 'learning_rate': 0.00013164965698880663, 'epoch': 8.0}

 67%|██████▋   | 18737/28080 [37:02:17<18:30:21,  7.13s/it]
 67%|██████▋   | 18738/28080 [37:02:24<18:23:42,  7.09s/it]
                                                           
{'loss': 0.5944, 'learning_rate': 0.00013162425793459347, 'epoch': 8.0}

 67%|██████▋   | 18738/28080 [37:02:24<18:23:42,  7.09s/it]
 67%|██████▋   | 18739/28080 [37:02:31<18:25:11,  7.10s/it]
                                                           
{'loss': 0.6052, 'learning_rate': 0.0001315988604552473, 'epoch': 8.01}

 67%|██████▋   | 18739/28080 [37:02:31<18:25:11,  7.10s/it]
 67%|██████▋   | 18740/28080 [37:02:39<18:28:03,  7.12s/it]
                                                           
{'loss': 0.584, 'learning_rate': 0.00013157346455110628, 'epoch': 8.01}

 67%|██████▋   | 18740/28080 [37:02:39<18:28:03,  7.12s/it]
 67%|██████▋   | 18741/28080 [37:02:46<18:30:30,  7.13s/it]
                                                           
{'loss': 0.6021, 'learning_rate': 0.00013154807022250811, 'epoch': 8.01}

 67%|██████▋   | 18741/28080 [37:02:46<18:30:30,  7.13s/it]
 67%|██████▋   | 18742/28080 [37:02:53<18:30:01,  7.13s/it]
                                                           
{'loss': 0.6116, 'learning_rate': 0.00013152267746979068, 'epoch': 8.01}

 67%|██████▋   | 18742/28080 [37:02:53<18:30:01,  7.13s/it]
 67%|██████▋   | 18743/28080 [37:03:00<18:33:37,  7.16s/it]
                                                           
{'loss': 0.6014, 'learning_rate': 0.00013149728629329173, 'epoch': 8.01}

 67%|██████▋   | 18743/28080 [37:03:00<18:33:37,  7.16s/it]
 67%|██████▋   | 18744/28080 [37:03:07<18:29:20,  7.13s/it]
                                                           
{'loss': 0.6164, 'learning_rate': 0.00013147189669334919, 'epoch': 8.01}

 67%|██████▋   | 18744/28080 [37:03:07<18:29:20,  7.13s/it]
 67%|██████▋   | 18745/28080 [37:03:14<18:26:19,  7.11s/it]
                                                           
{'loss': 0.6267, 'learning_rate': 0.0001314465086703008, 'epoch': 8.01}

 67%|██████▋   | 18745/28080 [37:03:14<18:26:19,  7.11s/it]
 67%|██████▋   | 18746/28080 [37:03:21<18:22:40,  7.09s/it]
                                                           
{'loss': 0.596, 'learning_rate': 0.00013142112222448433, 'epoch': 8.01}

 67%|██████▋   | 18746/28080 [37:03:21<18:22:40,  7.09s/it]
 67%|██████▋   | 18747/28080 [37:03:28<18:20:06,  7.07s/it]
                                                           
{'loss': 0.629, 'learning_rate': 0.00013139573735623745, 'epoch': 8.01}

 67%|██████▋   | 18747/28080 [37:03:28<18:20:06,  7.07s/it]
 67%|██████▋   | 18748/28080 [37:03:35<18:21:04,  7.08s/it]
                                                           
{'loss': 0.5962, 'learning_rate': 0.00013137035406589787, 'epoch': 8.01}

 67%|██████▋   | 18748/28080 [37:03:35<18:21:04,  7.08s/it]
 67%|██████▋   | 18749/28080 [37:03:42<18:21:32,  7.08s/it]
                                                           
{'loss': 0.6243, 'learning_rate': 0.00013134497235380344, 'epoch': 8.01}

 67%|██████▋   | 18749/28080 [37:03:42<18:21:32,  7.08s/it]
 67%|██████▋   | 18750/28080 [37:03:50<18:23:40,  7.10s/it]
                                                           
{'loss': 0.6257, 'learning_rate': 0.0001313195922202917, 'epoch': 8.01}

 67%|██████▋   | 18750/28080 [37:03:50<18:23:40,  7.10s/it]
 67%|██████▋   | 18751/28080 [37:03:57<18:23:03,  7.09s/it]
                                                           
{'loss': 0.6136, 'learning_rate': 0.00013129421366570037, 'epoch': 8.01}

 67%|██████▋   | 18751/28080 [37:03:57<18:23:03,  7.09s/it]
 67%|██████▋   | 18752/28080 [37:04:04<18:21:14,  7.08s/it]
                                                           
{'loss': 0.6229, 'learning_rate': 0.00013126883669036698, 'epoch': 8.01}

 67%|██████▋   | 18752/28080 [37:04:04<18:21:14,  7.08s/it]
 67%|██████▋   | 18753/28080 [37:04:11<18:30:01,  7.14s/it]
                                                           
{'loss': 0.6085, 'learning_rate': 0.00013124346129462936, 'epoch': 8.01}

 67%|██████▋   | 18753/28080 [37:04:11<18:30:01,  7.14s/it]
 67%|██████▋   | 18754/28080 [37:04:18<18:36:58,  7.19s/it]
                                                           
{'loss': 0.6287, 'learning_rate': 0.00013121808747882486, 'epoch': 8.01}

 67%|██████▋   | 18754/28080 [37:04:18<18:36:58,  7.19s/it]
 67%|██████▋   | 18755/28080 [37:04:26<18:38:04,  7.19s/it]
                                                           
{'loss': 0.6093, 'learning_rate': 0.00013119271524329132, 'epoch': 8.01}

 67%|██████▋   | 18755/28080 [37:04:26<18:38:04,  7.19s/it]
 67%|██████▋   | 18756/28080 [37:04:33<18:30:28,  7.15s/it]
                                                           
{'loss': 0.5933, 'learning_rate': 0.00013116734458836597, 'epoch': 8.01}

 67%|██████▋   | 18756/28080 [37:04:33<18:30:28,  7.15s/it]
 67%|██████▋   | 18757/28080 [37:04:40<18:32:31,  7.16s/it]
                                                           
{'loss': 0.6103, 'learning_rate': 0.00013114197551438662, 'epoch': 8.01}

 67%|██████▋   | 18757/28080 [37:04:40<18:32:31,  7.16s/it]
 67%|██████▋   | 18758/28080 [37:04:47<18:27:39,  7.13s/it]
                                                           
{'loss': 0.6291, 'learning_rate': 0.0001311166080216905, 'epoch': 8.01}

 67%|██████▋   | 18758/28080 [37:04:47<18:27:39,  7.13s/it]
 67%|██████▋   | 18759/28080 [37:04:54<18:25:00,  7.11s/it]
                                                           
{'loss': 0.6047, 'learning_rate': 0.00013109124211061545, 'epoch': 8.01}

 67%|██████▋   | 18759/28080 [37:04:54<18:25:00,  7.11s/it]
 67%|██████▋   | 18760/28080 [37:05:01<18:27:56,  7.13s/it]
                                                           
{'loss': 0.6055, 'learning_rate': 0.0001310658777814987, 'epoch': 8.01}

 67%|██████▋   | 18760/28080 [37:05:01<18:27:56,  7.13s/it]
 67%|██████▋   | 18761/28080 [37:05:08<18:28:26,  7.14s/it]
                                                           
{'loss': 0.6036, 'learning_rate': 0.00013104051503467777, 'epoch': 8.01}

 67%|██████▋   | 18761/28080 [37:05:08<18:28:26,  7.14s/it]
 67%|██████▋   | 18762/28080 [37:05:15<18:22:26,  7.10s/it]
                                                           
{'loss': 0.6099, 'learning_rate': 0.00013101515387048995, 'epoch': 8.01}

 67%|██████▋   | 18762/28080 [37:05:15<18:22:26,  7.10s/it]
 67%|██████▋   | 18763/28080 [37:05:22<18:24:24,  7.11s/it]
                                                           
{'loss': 0.5823, 'learning_rate': 0.00013098979428927287, 'epoch': 8.02}

 67%|██████▋   | 18763/28080 [37:05:22<18:24:24,  7.11s/it]
 67%|██████▋   | 18764/28080 [37:05:30<18:25:44,  7.12s/it]
                                                           
{'loss': 0.6108, 'learning_rate': 0.00013096443629136378, 'epoch': 8.02}

 67%|██████▋   | 18764/28080 [37:05:30<18:25:44,  7.12s/it]
 67%|██████▋   | 18765/28080 [37:05:37<18:27:03,  7.13s/it]
                                                           
{'loss': 0.6022, 'learning_rate': 0.00013093907987710008, 'epoch': 8.02}

 67%|██████▋   | 18765/28080 [37:05:37<18:27:03,  7.13s/it]
 67%|██████▋   | 18766/28080 [37:05:44<18:22:04,  7.10s/it]
                                                           
{'loss': 0.6247, 'learning_rate': 0.000130913725046819, 'epoch': 8.02}

 67%|██████▋   | 18766/28080 [37:05:44<18:22:04,  7.10s/it]
 67%|██████▋   | 18767/28080 [37:05:51<18:23:44,  7.11s/it]
                                                           
{'loss': 0.6264, 'learning_rate': 0.00013088837180085804, 'epoch': 8.02}

 67%|██████▋   | 18767/28080 [37:05:51<18:23:44,  7.11s/it]
 67%|██████▋   | 18768/28080 [37:05:58<18:21:17,  7.10s/it]
                                                           
{'loss': 0.627, 'learning_rate': 0.00013086302013955444, 'epoch': 8.02}

 67%|██████▋   | 18768/28080 [37:05:58<18:21:17,  7.10s/it]
 67%|██████▋   | 18769/28080 [37:06:05<18:25:50,  7.13s/it]
                                                           
{'loss': 0.5867, 'learning_rate': 0.00013083767006324542, 'epoch': 8.02}

 67%|██████▋   | 18769/28080 [37:06:05<18:25:50,  7.13s/it]
 67%|██████▋   | 18770/28080 [37:06:12<18:28:26,  7.14s/it]
                                                           
{'loss': 0.591, 'learning_rate': 0.0001308123215722683, 'epoch': 8.02}

 67%|██████▋   | 18770/28080 [37:06:12<18:28:26,  7.14s/it]
 67%|██████▋   | 18771/28080 [37:06:19<18:24:46,  7.12s/it]
                                                           
{'loss': 0.6167, 'learning_rate': 0.00013078697466696016, 'epoch': 8.02}

 67%|██████▋   | 18771/28080 [37:06:19<18:24:46,  7.12s/it]
 67%|██████▋   | 18772/28080 [37:06:26<18:22:16,  7.11s/it]
                                                           
{'loss': 0.62, 'learning_rate': 0.00013076162934765842, 'epoch': 8.02}

 67%|██████▋   | 18772/28080 [37:06:26<18:22:16,  7.11s/it]
 67%|██████▋   | 18773/28080 [37:06:34<18:23:34,  7.11s/it]
                                                           
{'loss': 0.6034, 'learning_rate': 0.0001307362856147001, 'epoch': 8.02}

 67%|██████▋   | 18773/28080 [37:06:34<18:23:34,  7.11s/it]
 67%|██████▋   | 18774/28080 [37:06:41<18:24:54,  7.12s/it]
                                                           
{'loss': 0.6186, 'learning_rate': 0.00013071094346842266, 'epoch': 8.02}

 67%|██████▋   | 18774/28080 [37:06:41<18:24:54,  7.12s/it]
 67%|██████▋   | 18775/28080 [37:06:48<18:23:48,  7.12s/it]
                                                           
{'loss': 0.6086, 'learning_rate': 0.00013068560290916287, 'epoch': 8.02}

 67%|██████▋   | 18775/28080 [37:06:48<18:23:48,  7.12s/it]
 67%|██████▋   | 18776/28080 [37:06:55<18:21:12,  7.10s/it]
                                                           
{'loss': 0.6141, 'learning_rate': 0.00013066026393725814, 'epoch': 8.02}

 67%|██████▋   | 18776/28080 [37:06:55<18:21:12,  7.10s/it]
 67%|██████▋   | 18777/28080 [37:07:02<18:22:21,  7.11s/it]
                                                           
{'loss': 0.6152, 'learning_rate': 0.00013063492655304539, 'epoch': 8.02}

 67%|██████▋   | 18777/28080 [37:07:02<18:22:21,  7.11s/it]
 67%|██████▋   | 18778/28080 [37:07:09<18:20:36,  7.10s/it]
                                                           
{'loss': 0.63, 'learning_rate': 0.00013060959075686187, 'epoch': 8.02}

 67%|██████▋   | 18778/28080 [37:07:09<18:20:36,  7.10s/it]
 67%|██████▋   | 18779/28080 [37:07:16<18:18:08,  7.08s/it]
                                                           
{'loss': 0.6206, 'learning_rate': 0.0001305842565490446, 'epoch': 8.02}

 67%|██████▋   | 18779/28080 [37:07:16<18:18:08,  7.08s/it]
 67%|██████▋   | 18780/28080 [37:07:23<18:18:54,  7.09s/it]
                                                           
{'loss': 0.606, 'learning_rate': 0.0001305589239299306, 'epoch': 8.02}

 67%|██████▋   | 18780/28080 [37:07:23<18:18:54,  7.09s/it]
 67%|██████▋   | 18781/28080 [37:07:30<18:21:30,  7.11s/it]
                                                           
{'loss': 0.6009, 'learning_rate': 0.00013053359289985677, 'epoch': 8.02}

 67%|██████▋   | 18781/28080 [37:07:30<18:21:30,  7.11s/it]
 67%|██████▋   | 18782/28080 [37:07:37<18:22:18,  7.11s/it]
                                                           
{'loss': 0.6175, 'learning_rate': 0.0001305082634591604, 'epoch': 8.02}

 67%|██████▋   | 18782/28080 [37:07:38<18:22:18,  7.11s/it]
 67%|██████▋   | 18783/28080 [37:07:45<18:22:03,  7.11s/it]
                                                           
{'loss': 0.6331, 'learning_rate': 0.00013048293560817827, 'epoch': 8.02}

 67%|██████▋   | 18783/28080 [37:07:45<18:22:03,  7.11s/it]
 67%|██████▋   | 18784/28080 [37:07:52<18:20:40,  7.10s/it]
                                                           
{'loss': 0.6121, 'learning_rate': 0.00013045760934724738, 'epoch': 8.02}

 67%|██████▋   | 18784/28080 [37:07:52<18:20:40,  7.10s/it]
 67%|██████▋   | 18785/28080 [37:07:59<18:26:25,  7.14s/it]
                                                           
{'loss': 0.6098, 'learning_rate': 0.0001304322846767046, 'epoch': 8.02}

 67%|██████▋   | 18785/28080 [37:07:59<18:26:25,  7.14s/it]
 67%|██████▋   | 18786/28080 [37:08:06<18:28:36,  7.16s/it]
                                                           
{'loss': 0.5951, 'learning_rate': 0.00013040696159688698, 'epoch': 8.03}

 67%|██████▋   | 18786/28080 [37:08:06<18:28:36,  7.16s/it]
 67%|██████▋   | 18787/28080 [37:08:13<18:27:27,  7.15s/it]
                                                           
{'loss': 0.6079, 'learning_rate': 0.00013038164010813127, 'epoch': 8.03}

 67%|██████▋   | 18787/28080 [37:08:13<18:27:27,  7.15s/it]
 67%|██████▋   | 18788/28080 [37:08:20<18:29:27,  7.16s/it]
                                                           
{'loss': 0.6014, 'learning_rate': 0.00013035632021077457, 'epoch': 8.03}

 67%|██████▋   | 18788/28080 [37:08:20<18:29:27,  7.16s/it]
 67%|██████▋   | 18789/28080 [37:08:28<18:27:28,  7.15s/it]
                                                           
{'loss': 0.5882, 'learning_rate': 0.00013033100190515358, 'epoch': 8.03}

 67%|██████▋   | 18789/28080 [37:08:28<18:27:28,  7.15s/it]
 67%|██████▋   | 18790/28080 [37:08:35<18:25:09,  7.14s/it]
                                                           
{'loss': 0.6021, 'learning_rate': 0.00013030568519160513, 'epoch': 8.03}

 67%|██████▋   | 18790/28080 [37:08:35<18:25:09,  7.14s/it]
 67%|██████▋   | 18791/28080 [37:08:42<18:21:40,  7.12s/it]
                                                           
{'loss': 0.6122, 'learning_rate': 0.00013028037007046598, 'epoch': 8.03}

 67%|██████▋   | 18791/28080 [37:08:42<18:21:40,  7.12s/it]
 67%|██████▋   | 18792/28080 [37:08:49<18:22:52,  7.12s/it]
                                                           
{'loss': 0.6062, 'learning_rate': 0.0001302550565420731, 'epoch': 8.03}

 67%|██████▋   | 18792/28080 [37:08:49<18:22:52,  7.12s/it]
 67%|██████▋   | 18793/28080 [37:08:56<18:17:20,  7.09s/it]
                                                           
{'loss': 0.6104, 'learning_rate': 0.00013022974460676315, 'epoch': 8.03}

 67%|██████▋   | 18793/28080 [37:08:56<18:17:20,  7.09s/it]
 67%|██████▋   | 18794/28080 [37:09:03<18:18:22,  7.10s/it]
                                                           
{'loss': 0.6022, 'learning_rate': 0.0001302044342648729, 'epoch': 8.03}

 67%|██████▋   | 18794/28080 [37:09:03<18:18:22,  7.10s/it]
 67%|██████▋   | 18795/28080 [37:09:10<18:18:10,  7.10s/it]
                                                           
{'loss': 0.623, 'learning_rate': 0.00013017912551673905, 'epoch': 8.03}

 67%|██████▋   | 18795/28080 [37:09:10<18:18:10,  7.10s/it]
 67%|██████▋   | 18796/28080 [37:09:17<18:17:24,  7.09s/it]
                                                           
{'loss': 0.6001, 'learning_rate': 0.00013015381836269823, 'epoch': 8.03}

 67%|██████▋   | 18796/28080 [37:09:17<18:17:24,  7.09s/it]
 67%|██████▋   | 18797/28080 [37:09:24<18:18:09,  7.10s/it]
                                                           
{'loss': 0.6373, 'learning_rate': 0.0001301285128030873, 'epoch': 8.03}

 67%|██████▋   | 18797/28080 [37:09:24<18:18:09,  7.10s/it]
 67%|██████▋   | 18798/28080 [37:09:31<18:18:33,  7.10s/it]
                                                           
{'loss': 0.6128, 'learning_rate': 0.00013010320883824288, 'epoch': 8.03}

 67%|██████▋   | 18798/28080 [37:09:31<18:18:33,  7.10s/it]
 67%|██████▋   | 18799/28080 [37:09:39<18:32:34,  7.19s/it]
                                                           
{'loss': 0.5938, 'learning_rate': 0.00013007790646850153, 'epoch': 8.03}

 67%|██████▋   | 18799/28080 [37:09:39<18:32:34,  7.19s/it]
 67%|██████▋   | 18800/28080 [37:09:46<18:28:52,  7.17s/it]
                                                           
{'loss': 0.6144, 'learning_rate': 0.00013005260569419987, 'epoch': 8.03}

 67%|██████▋   | 18800/28080 [37:09:46<18:28:52,  7.17s/it]
 67%|██████▋   | 18801/28080 [37:09:53<18:23:08,  7.13s/it]
                                                           
{'loss': 0.609, 'learning_rate': 0.00013002730651567464, 'epoch': 8.03}

 67%|██████▋   | 18801/28080 [37:09:53<18:23:08,  7.13s/it]
 67%|██████▋   | 18802/28080 [37:10:00<18:20:13,  7.12s/it]
                                                           
{'loss': 0.6084, 'learning_rate': 0.0001300020089332622, 'epoch': 8.03}

 67%|██████▋   | 18802/28080 [37:10:00<18:20:13,  7.12s/it]
 67%|██████▋   | 18803/28080 [37:10:07<18:19:42,  7.11s/it]
                                                           
{'loss': 0.6075, 'learning_rate': 0.00012997671294729944, 'epoch': 8.03}

 67%|██████▋   | 18803/28080 [37:10:07<18:19:42,  7.11s/it]
 67%|██████▋   | 18804/28080 [37:10:14<18:18:04,  7.10s/it]
                                                           
{'loss': 0.6074, 'learning_rate': 0.0001299514185581225, 'epoch': 8.03}

 67%|██████▋   | 18804/28080 [37:10:14<18:18:04,  7.10s/it]
 67%|██████▋   | 18805/28080 [37:10:21<18:19:26,  7.11s/it]
                                                           
{'loss': 0.623, 'learning_rate': 0.00012992612576606818, 'epoch': 8.03}

 67%|██████▋   | 18805/28080 [37:10:21<18:19:26,  7.11s/it]
 67%|██████▋   | 18806/28080 [37:10:29<18:23:57,  7.14s/it]
                                                           
{'loss': 0.5969, 'learning_rate': 0.0001299008345714728, 'epoch': 8.03}

 67%|██████▋   | 18806/28080 [37:10:29<18:23:57,  7.14s/it]
 67%|██████▋   | 18807/28080 [37:10:36<18:25:41,  7.15s/it]
                                                           
{'loss': 0.6236, 'learning_rate': 0.00012987554497467303, 'epoch': 8.03}

 67%|██████▋   | 18807/28080 [37:10:36<18:25:41,  7.15s/it]
 67%|██████▋   | 18808/28080 [37:10:43<18:25:52,  7.16s/it]
                                                           
{'loss': 0.6047, 'learning_rate': 0.00012985025697600516, 'epoch': 8.03}

 67%|██████▋   | 18808/28080 [37:10:43<18:25:52,  7.16s/it]
 67%|██████▋   | 18809/28080 [37:10:50<18:23:02,  7.14s/it]
                                                           
{'loss': 0.5928, 'learning_rate': 0.0001298249705758057, 'epoch': 8.04}

 67%|██████▋   | 18809/28080 [37:10:50<18:23:02,  7.14s/it]
 67%|██████▋   | 18810/28080 [37:10:57<18:25:50,  7.16s/it]
                                                           
{'loss': 0.5998, 'learning_rate': 0.0001297996857744109, 'epoch': 8.04}

 67%|██████▋   | 18810/28080 [37:10:57<18:25:50,  7.16s/it]
 67%|██████▋   | 18811/28080 [37:11:04<18:23:25,  7.14s/it]
                                                           
{'loss': 0.6023, 'learning_rate': 0.00012977440257215745, 'epoch': 8.04}

 67%|██████▋   | 18811/28080 [37:11:04<18:23:25,  7.14s/it]
 67%|██████▋   | 18812/28080 [37:11:11<18:22:43,  7.14s/it]
                                                           
{'loss': 0.6129, 'learning_rate': 0.00012974912096938145, 'epoch': 8.04}

 67%|██████▋   | 18812/28080 [37:11:11<18:22:43,  7.14s/it]
 67%|██████▋   | 18813/28080 [37:11:19<18:19:40,  7.12s/it]
                                                           
{'loss': 0.6052, 'learning_rate': 0.00012972384096641943, 'epoch': 8.04}

 67%|██████▋   | 18813/28080 [37:11:19<18:19:40,  7.12s/it]
 67%|██████▋   | 18814/28080 [37:11:26<18:16:46,  7.10s/it]
                                                           
{'loss': 0.6102, 'learning_rate': 0.00012969856256360746, 'epoch': 8.04}

 67%|██████▋   | 18814/28080 [37:11:26<18:16:46,  7.10s/it]
 67%|██████▋   | 18815/28080 [37:11:33<18:20:20,  7.13s/it]
                                                           
{'loss': 0.5935, 'learning_rate': 0.0001296732857612821, 'epoch': 8.04}

 67%|██████▋   | 18815/28080 [37:11:33<18:20:20,  7.13s/it]
 67%|██████▋   | 18816/28080 [37:11:40<18:17:54,  7.11s/it]
                                                           
{'loss': 0.6086, 'learning_rate': 0.00012964801055977948, 'epoch': 8.04}

 67%|██████▋   | 18816/28080 [37:11:40<18:17:54,  7.11s/it]
 67%|██████▋   | 18817/28080 [37:11:47<18:19:49,  7.12s/it]
                                                           
{'loss': 0.6056, 'learning_rate': 0.0001296227369594361, 'epoch': 8.04}

 67%|██████▋   | 18817/28080 [37:11:47<18:19:49,  7.12s/it]
 67%|██████▋   | 18818/28080 [37:11:54<18:19:20,  7.12s/it]
                                                           
{'loss': 0.6098, 'learning_rate': 0.00012959746496058795, 'epoch': 8.04}

 67%|██████▋   | 18818/28080 [37:11:54<18:19:20,  7.12s/it]
 67%|██████▋   | 18819/28080 [37:12:01<18:21:56,  7.14s/it]
                                                           
{'loss': 0.6093, 'learning_rate': 0.00012957219456357117, 'epoch': 8.04}

 67%|██████▋   | 18819/28080 [37:12:01<18:21:56,  7.14s/it]
 67%|██████▋   | 18820/28080 [37:12:08<18:22:51,  7.15s/it]
                                                           
{'loss': 0.6259, 'learning_rate': 0.00012954692576872223, 'epoch': 8.04}

 67%|██████▋   | 18820/28080 [37:12:08<18:22:51,  7.15s/it]
 67%|██████▋   | 18821/28080 [37:12:15<18:14:17,  7.09s/it]
                                                           
{'loss': 0.5891, 'learning_rate': 0.00012952165857637706, 'epoch': 8.04}

 67%|██████▋   | 18821/28080 [37:12:15<18:14:17,  7.09s/it]
 67%|██████▋   | 18822/28080 [37:12:23<18:16:06,  7.10s/it]
                                                           
{'loss': 0.6303, 'learning_rate': 0.00012949639298687215, 'epoch': 8.04}

 67%|██████▋   | 18822/28080 [37:12:23<18:16:06,  7.10s/it]
 67%|██████▋   | 18823/28080 [37:12:30<18:22:00,  7.14s/it]
                                                           
{'loss': 0.5893, 'learning_rate': 0.0001294711290005432, 'epoch': 8.04}

 67%|██████▋   | 18823/28080 [37:12:30<18:22:00,  7.14s/it]
 67%|██████▋   | 18824/28080 [37:12:37<18:17:53,  7.12s/it]
                                                           
{'loss': 0.5851, 'learning_rate': 0.00012944586661772667, 'epoch': 8.04}

 67%|██████▋   | 18824/28080 [37:12:37<18:17:53,  7.12s/it]
 67%|██████▋   | 18825/28080 [37:12:44<18:18:10,  7.12s/it]
                                                           
{'loss': 0.6131, 'learning_rate': 0.00012942060583875836, 'epoch': 8.04}

 67%|██████▋   | 18825/28080 [37:12:44<18:18:10,  7.12s/it]
 67%|██████▋   | 18826/28080 [37:12:51<18:16:20,  7.11s/it]
                                                           
{'loss': 0.6114, 'learning_rate': 0.00012939534666397463, 'epoch': 8.04}

 67%|██████▋   | 18826/28080 [37:12:51<18:16:20,  7.11s/it]
 67%|██████▋   | 18827/28080 [37:12:58<18:14:29,  7.10s/it]
                                                           
{'loss': 0.5892, 'learning_rate': 0.0001293700890937114, 'epoch': 8.04}

 67%|██████▋   | 18827/28080 [37:12:58<18:14:29,  7.10s/it]
 67%|██████▋   | 18828/28080 [37:13:05<18:15:28,  7.10s/it]
                                                           
{'loss': 0.6189, 'learning_rate': 0.00012934483312830467, 'epoch': 8.04}

 67%|██████▋   | 18828/28080 [37:13:05<18:15:28,  7.10s/it]
 67%|██████▋   | 18829/28080 [37:13:12<18:13:23,  7.09s/it]
                                                           
{'loss': 0.6431, 'learning_rate': 0.00012931957876809037, 'epoch': 8.04}

 67%|██████▋   | 18829/28080 [37:13:12<18:13:23,  7.09s/it]
 67%|██████▋   | 18830/28080 [37:13:19<18:15:04,  7.10s/it]
                                                           
{'loss': 0.5971, 'learning_rate': 0.00012929432601340465, 'epoch': 8.04}

 67%|██████▋   | 18830/28080 [37:13:19<18:15:04,  7.10s/it]
 67%|██████▋   | 18831/28080 [37:13:27<18:14:29,  7.10s/it]
                                                           
{'loss': 0.6026, 'learning_rate': 0.00012926907486458344, 'epoch': 8.04}

 67%|██████▋   | 18831/28080 [37:13:27<18:14:29,  7.10s/it]
 67%|██████▋   | 18832/28080 [37:13:34<18:11:44,  7.08s/it]
                                                           
{'loss': 0.6052, 'learning_rate': 0.0001292438253219626, 'epoch': 8.04}

 67%|██████▋   | 18832/28080 [37:13:34<18:11:44,  7.08s/it]
 67%|██████▋   | 18833/28080 [37:13:41<18:15:48,  7.11s/it]
                                                           
{'loss': 0.5897, 'learning_rate': 0.000129218577385878, 'epoch': 8.05}

 67%|██████▋   | 18833/28080 [37:13:41<18:15:48,  7.11s/it]
 67%|██████▋   | 18834/28080 [37:13:48<18:15:03,  7.11s/it]
                                                           
{'loss': 0.6237, 'learning_rate': 0.00012919333105666575, 'epoch': 8.05}

 67%|██████▋   | 18834/28080 [37:13:48<18:15:03,  7.11s/it]
 67%|██████▋   | 18835/28080 [37:13:55<18:14:52,  7.11s/it]
                                                           
{'loss': 0.614, 'learning_rate': 0.0001291680863346615, 'epoch': 8.05}

 67%|██████▋   | 18835/28080 [37:13:55<18:14:52,  7.11s/it]
 67%|██████▋   | 18836/28080 [37:14:02<18:17:03,  7.12s/it]
                                                           
{'loss': 0.6254, 'learning_rate': 0.00012914284322020135, 'epoch': 8.05}

 67%|██████▋   | 18836/28080 [37:14:02<18:17:03,  7.12s/it]
 67%|██████▋   | 18837/28080 [37:14:09<18:16:37,  7.12s/it]
                                                           
{'loss': 0.5997, 'learning_rate': 0.00012911760171362081, 'epoch': 8.05}

 67%|██████▋   | 18837/28080 [37:14:09<18:16:37,  7.12s/it]
 67%|██████▋   | 18838/28080 [37:14:16<18:13:38,  7.10s/it]
                                                           
{'loss': 0.6143, 'learning_rate': 0.00012909236181525598, 'epoch': 8.05}

 67%|██████▋   | 18838/28080 [37:14:16<18:13:38,  7.10s/it]
 67%|██████▋   | 18839/28080 [37:14:23<18:15:09,  7.11s/it]
                                                           
{'loss': 0.6104, 'learning_rate': 0.00012906712352544247, 'epoch': 8.05}

 67%|██████▋   | 18839/28080 [37:14:23<18:15:09,  7.11s/it]
 67%|██████▋   | 18840/28080 [37:14:31<18:15:38,  7.11s/it]
                                                           
{'loss': 0.6231, 'learning_rate': 0.00012904188684451619, 'epoch': 8.05}

 67%|██████▋   | 18840/28080 [37:14:31<18:15:38,  7.11s/it]
 67%|██████▋   | 18841/28080 [37:14:38<18:14:36,  7.11s/it]
                                                           
{'loss': 0.5947, 'learning_rate': 0.00012901665177281283, 'epoch': 8.05}

 67%|██████▋   | 18841/28080 [37:14:38<18:14:36,  7.11s/it]
 67%|██████▋   | 18842/28080 [37:14:45<18:20:56,  7.15s/it]
                                                           
{'loss': 0.6158, 'learning_rate': 0.0001289914183106681, 'epoch': 8.05}

 67%|██████▋   | 18842/28080 [37:14:45<18:20:56,  7.15s/it]
 67%|██████▋   | 18843/28080 [37:14:52<18:23:33,  7.17s/it]
                                                           
{'loss': 0.6156, 'learning_rate': 0.00012896618645841774, 'epoch': 8.05}

 67%|██████▋   | 18843/28080 [37:14:52<18:23:33,  7.17s/it]
 67%|██████▋   | 18844/28080 [37:14:59<18:25:14,  7.18s/it]
                                                           
{'loss': 0.6053, 'learning_rate': 0.0001289409562163973, 'epoch': 8.05}

 67%|██████▋   | 18844/28080 [37:14:59<18:25:14,  7.18s/it]
 67%|██████▋   | 18845/28080 [37:15:06<18:17:23,  7.13s/it]
                                                           
{'loss': 0.6095, 'learning_rate': 0.0001289157275849426, 'epoch': 8.05}

 67%|██████▋   | 18845/28080 [37:15:06<18:17:23,  7.13s/it]
 67%|██████▋   | 18846/28080 [37:15:13<18:17:23,  7.13s/it]
                                                           
{'loss': 0.6098, 'learning_rate': 0.00012889050056438928, 'epoch': 8.05}

 67%|██████▋   | 18846/28080 [37:15:13<18:17:23,  7.13s/it]
 67%|██████▋   | 18847/28080 [37:15:21<18:17:29,  7.13s/it]
                                                           
{'loss': 0.6127, 'learning_rate': 0.0001288652751550729, 'epoch': 8.05}

 67%|██████▋   | 18847/28080 [37:15:21<18:17:29,  7.13s/it]
 67%|██████▋   | 18848/28080 [37:15:28<18:13:55,  7.11s/it]
                                                           
{'loss': 0.6021, 'learning_rate': 0.00012884005135732892, 'epoch': 8.05}

 67%|██████▋   | 18848/28080 [37:15:28<18:13:55,  7.11s/it]
 67%|██████▋   | 18849/28080 [37:15:35<18:11:02,  7.09s/it]
                                                           
{'loss': 0.6071, 'learning_rate': 0.0001288148291714932, 'epoch': 8.05}

 67%|██████▋   | 18849/28080 [37:15:35<18:11:02,  7.09s/it]
 67%|██████▋   | 18850/28080 [37:15:42<18:10:34,  7.09s/it]
                                                           
{'loss': 0.6261, 'learning_rate': 0.00012878960859790105, 'epoch': 8.05}

 67%|██████▋   | 18850/28080 [37:15:42<18:10:34,  7.09s/it]
 67%|██████▋   | 18851/28080 [37:15:49<18:05:45,  7.06s/it]
                                                           
{'loss': 0.6177, 'learning_rate': 0.00012876438963688834, 'epoch': 8.05}

 67%|██████▋   | 18851/28080 [37:15:49<18:05:45,  7.06s/it]
 67%|██████▋   | 18852/28080 [37:15:56<18:05:43,  7.06s/it]
                                                           
{'loss': 0.6115, 'learning_rate': 0.00012873917228879012, 'epoch': 8.05}

 67%|██████▋   | 18852/28080 [37:15:56<18:05:43,  7.06s/it]
 67%|██████▋   | 18853/28080 [37:16:03<18:11:15,  7.10s/it]
                                                           
{'loss': 0.603, 'learning_rate': 0.00012871395655394223, 'epoch': 8.05}

 67%|██████▋   | 18853/28080 [37:16:03<18:11:15,  7.10s/it]
 67%|██████▋   | 18854/28080 [37:16:10<18:10:45,  7.09s/it]
                                                           
{'loss': 0.5913, 'learning_rate': 0.0001286887424326799, 'epoch': 8.05}

 67%|██████▋   | 18854/28080 [37:16:10<18:10:45,  7.09s/it]
 67%|██████▋   | 18855/28080 [37:16:17<18:11:13,  7.10s/it]
                                                           
{'loss': 0.6009, 'learning_rate': 0.00012866352992533882, 'epoch': 8.05}

 67%|██████▋   | 18855/28080 [37:16:17<18:11:13,  7.10s/it]
 67%|██████▋   | 18856/28080 [37:16:24<18:06:10,  7.07s/it]
                                                           
{'loss': 0.6212, 'learning_rate': 0.00012863831903225432, 'epoch': 8.06}

 67%|██████▋   | 18856/28080 [37:16:24<18:06:10,  7.07s/it]
 67%|██████▋   | 18857/28080 [37:16:31<18:11:20,  7.10s/it]
                                                           
{'loss': 0.623, 'learning_rate': 0.0001286131097537618, 'epoch': 8.06}

 67%|██████▋   | 18857/28080 [37:16:31<18:11:20,  7.10s/it]
 67%|██████▋   | 18858/28080 [37:16:39<18:15:11,  7.13s/it]
                                                           
{'loss': 0.6022, 'learning_rate': 0.00012858790209019643, 'epoch': 8.06}

 67%|██████▋   | 18858/28080 [37:16:39<18:15:11,  7.13s/it]
 67%|██████▋   | 18859/28080 [37:16:46<18:14:06,  7.12s/it]
                                                           
{'loss': 0.6104, 'learning_rate': 0.00012856269604189397, 'epoch': 8.06}

 67%|██████▋   | 18859/28080 [37:16:46<18:14:06,  7.12s/it]
 67%|██████▋   | 18860/28080 [37:16:53<18:09:25,  7.09s/it]
                                                           
{'loss': 0.6067, 'learning_rate': 0.00012853749160918952, 'epoch': 8.06}

 67%|██████▋   | 18860/28080 [37:16:53<18:09:25,  7.09s/it]
 67%|██████▋   | 18861/28080 [37:17:00<18:11:55,  7.11s/it]
                                                           
{'loss': 0.5923, 'learning_rate': 0.00012851228879241845, 'epoch': 8.06}

 67%|██████▋   | 18861/28080 [37:17:00<18:11:55,  7.11s/it]
 67%|██████▋   | 18862/28080 [37:17:07<18:08:38,  7.09s/it]
                                                           
{'loss': 0.6058, 'learning_rate': 0.00012848708759191592, 'epoch': 8.06}

 67%|██████▋   | 18862/28080 [37:17:07<18:08:38,  7.09s/it]
 67%|██████▋   | 18863/28080 [37:17:14<18:10:14,  7.10s/it]
                                                           
{'loss': 0.595, 'learning_rate': 0.00012846188800801745, 'epoch': 8.06}

 67%|██████▋   | 18863/28080 [37:17:14<18:10:14,  7.10s/it]
 67%|██████▋   | 18864/28080 [37:17:21<18:09:56,  7.10s/it]
                                                           
{'loss': 0.608, 'learning_rate': 0.00012843669004105807, 'epoch': 8.06}

 67%|██████▋   | 18864/28080 [37:17:21<18:09:56,  7.10s/it]
 67%|██████▋   | 18865/28080 [37:17:28<18:14:53,  7.13s/it]
                                                           
{'loss': 0.6177, 'learning_rate': 0.0001284114936913733, 'epoch': 8.06}

 67%|██████▋   | 18865/28080 [37:17:28<18:14:53,  7.13s/it]
 67%|██████▋   | 18866/28080 [37:17:35<18:14:39,  7.13s/it]
                                                           
{'loss': 0.6123, 'learning_rate': 0.000128386298959298, 'epoch': 8.06}

 67%|██████▋   | 18866/28080 [37:17:35<18:14:39,  7.13s/it]
 67%|██████▋   | 18867/28080 [37:17:42<18:10:25,  7.10s/it]
                                                           
{'loss': 0.6115, 'learning_rate': 0.00012836110584516763, 'epoch': 8.06}

 67%|██████▋   | 18867/28080 [37:17:42<18:10:25,  7.10s/it]
 67%|██████▋   | 18868/28080 [37:17:50<18:15:12,  7.13s/it]
                                                           
{'loss': 0.5995, 'learning_rate': 0.00012833591434931725, 'epoch': 8.06}

 67%|██████▋   | 18868/28080 [37:17:50<18:15:12,  7.13s/it]
 67%|██████▋   | 18869/28080 [37:17:57<18:18:31,  7.16s/it]
                                                           
{'loss': 0.6242, 'learning_rate': 0.00012831072447208193, 'epoch': 8.06}

 67%|██████▋   | 18869/28080 [37:17:57<18:18:31,  7.16s/it]
 67%|██████▋   | 18870/28080 [37:18:04<18:14:00,  7.13s/it]
                                                           
{'loss': 0.5982, 'learning_rate': 0.00012828553621379703, 'epoch': 8.06}

 67%|██████▋   | 18870/28080 [37:18:04<18:14:00,  7.13s/it]
 67%|██████▋   | 18871/28080 [37:18:11<18:08:30,  7.09s/it]
                                                           
{'loss': 0.6328, 'learning_rate': 0.00012826034957479735, 'epoch': 8.06}

 67%|██████▋   | 18871/28080 [37:18:11<18:08:30,  7.09s/it]
 67%|██████▋   | 18872/28080 [37:18:18<18:09:03,  7.10s/it]
                                                           
{'loss': 0.6304, 'learning_rate': 0.00012823516455541824, 'epoch': 8.06}

 67%|██████▋   | 18872/28080 [37:18:18<18:09:03,  7.10s/it]
 67%|██████▋   | 18873/28080 [37:18:25<18:11:12,  7.11s/it]
                                                           
{'loss': 0.5962, 'learning_rate': 0.00012820998115599454, 'epoch': 8.06}

 67%|██████▋   | 18873/28080 [37:18:25<18:11:12,  7.11s/it]
 67%|██████▋   | 18874/28080 [37:18:32<18:15:25,  7.14s/it]
                                                           
{'loss': 0.5975, 'learning_rate': 0.00012818479937686146, 'epoch': 8.06}

 67%|██████▋   | 18874/28080 [37:18:32<18:15:25,  7.14s/it]
 67%|██████▋   | 18875/28080 [37:18:40<18:21:09,  7.18s/it]
                                                           
{'loss': 0.611, 'learning_rate': 0.00012815961921835395, 'epoch': 8.06}

 67%|██████▋   | 18875/28080 [37:18:40<18:21:09,  7.18s/it]
 67%|██████▋   | 18876/28080 [37:18:47<18:18:43,  7.16s/it]
                                                           
{'loss': 0.6088, 'learning_rate': 0.00012813444068080705, 'epoch': 8.06}

 67%|██████▋   | 18876/28080 [37:18:47<18:18:43,  7.16s/it]
 67%|██████▋   | 18877/28080 [37:18:54<18:13:20,  7.13s/it]
                                                           
{'loss': 0.6278, 'learning_rate': 0.00012810926376455558, 'epoch': 8.06}

 67%|██████▋   | 18877/28080 [37:18:54<18:13:20,  7.13s/it]
 67%|██████▋   | 18878/28080 [37:19:01<18:11:49,  7.12s/it]
                                                           
{'loss': 0.6182, 'learning_rate': 0.00012808408846993474, 'epoch': 8.06}

 67%|██████▋   | 18878/28080 [37:19:01<18:11:49,  7.12s/it]
 67%|██████▋   | 18879/28080 [37:19:08<18:07:23,  7.09s/it]
                                                           
{'loss': 0.6038, 'learning_rate': 0.00012805891479727928, 'epoch': 8.06}

 67%|██████▋   | 18879/28080 [37:19:08<18:07:23,  7.09s/it]
 67%|██████▋   | 18880/28080 [37:19:15<18:10:39,  7.11s/it]
                                                           
{'loss': 0.6031, 'learning_rate': 0.00012803374274692419, 'epoch': 8.07}

 67%|██████▋   | 18880/28080 [37:19:15<18:10:39,  7.11s/it]
 67%|██████▋   | 18881/28080 [37:19:22<18:03:17,  7.07s/it]
                                                           
{'loss': 0.6203, 'learning_rate': 0.00012800857231920422, 'epoch': 8.07}

 67%|██████▋   | 18881/28080 [37:19:22<18:03:17,  7.07s/it]
 67%|██████▋   | 18882/28080 [37:19:29<18:02:27,  7.06s/it]
                                                           
{'loss': 0.6045, 'learning_rate': 0.00012798340351445443, 'epoch': 8.07}

 67%|██████▋   | 18882/28080 [37:19:29<18:02:27,  7.06s/it]
 67%|██████▋   | 18883/28080 [37:19:36<18:04:50,  7.08s/it]
                                                           
{'loss': 0.5966, 'learning_rate': 0.00012795823633300952, 'epoch': 8.07}

 67%|██████▋   | 18883/28080 [37:19:36<18:04:50,  7.08s/it]
 67%|██████▋   | 18884/28080 [37:19:43<18:05:47,  7.08s/it]
                                                           
{'loss': 0.6015, 'learning_rate': 0.0001279330707752045, 'epoch': 8.07}

 67%|██████▋   | 18884/28080 [37:19:43<18:05:47,  7.08s/it]
 67%|██████▋   | 18885/28080 [37:19:50<18:08:29,  7.10s/it]
                                                           
{'loss': 0.6094, 'learning_rate': 0.0001279079068413739, 'epoch': 8.07}

 67%|██████▋   | 18885/28080 [37:19:50<18:08:29,  7.10s/it]
 67%|██████▋   | 18886/28080 [37:19:58<18:07:35,  7.10s/it]
                                                           
{'loss': 0.5964, 'learning_rate': 0.00012788274453185273, 'epoch': 8.07}

 67%|██████▋   | 18886/28080 [37:19:58<18:07:35,  7.10s/it]
 67%|██████▋   | 18887/28080 [37:20:05<18:05:51,  7.09s/it]
                                                           
{'loss': 0.5968, 'learning_rate': 0.00012785758384697556, 'epoch': 8.07}

 67%|██████▋   | 18887/28080 [37:20:05<18:05:51,  7.09s/it]
 67%|██████▋   | 18888/28080 [37:20:12<18:08:36,  7.11s/it]
                                                           
{'loss': 0.5979, 'learning_rate': 0.00012783242478707734, 'epoch': 8.07}

 67%|██████▋   | 18888/28080 [37:20:12<18:08:36,  7.11s/it]
 67%|██████▋   | 18889/28080 [37:20:19<18:08:27,  7.11s/it]
                                                           
{'loss': 0.6141, 'learning_rate': 0.00012780726735249265, 'epoch': 8.07}

 67%|██████▋   | 18889/28080 [37:20:19<18:08:27,  7.11s/it]
 67%|██████▋   | 18890/28080 [37:20:26<18:15:35,  7.15s/it]
                                                           
{'loss': 0.6171, 'learning_rate': 0.00012778211154355624, 'epoch': 8.07}

 67%|██████▋   | 18890/28080 [37:20:26<18:15:35,  7.15s/it]
 67%|██████▋   | 18891/28080 [37:20:33<18:14:07,  7.14s/it]
                                                           
{'loss': 0.6231, 'learning_rate': 0.00012775695736060263, 'epoch': 8.07}

 67%|██████▋   | 18891/28080 [37:20:33<18:14:07,  7.14s/it]
 67%|██████▋   | 18892/28080 [37:20:40<18:14:23,  7.15s/it]
                                                           
{'loss': 0.6124, 'learning_rate': 0.0001277318048039667, 'epoch': 8.07}

 67%|██████▋   | 18892/28080 [37:20:40<18:14:23,  7.15s/it]
 67%|██████▋   | 18893/28080 [37:20:48<18:14:24,  7.15s/it]
                                                           
{'loss': 0.6235, 'learning_rate': 0.00012770665387398298, 'epoch': 8.07}

 67%|██████▋   | 18893/28080 [37:20:48<18:14:24,  7.15s/it]
 67%|██████▋   | 18894/28080 [37:20:55<18:11:57,  7.13s/it]
                                                           
{'loss': 0.5972, 'learning_rate': 0.00012768150457098605, 'epoch': 8.07}

 67%|██████▋   | 18894/28080 [37:20:55<18:11:57,  7.13s/it]
 67%|██████▋   | 18895/28080 [37:21:02<18:05:43,  7.09s/it]
                                                           
{'loss': 0.5954, 'learning_rate': 0.00012765635689531053, 'epoch': 8.07}

 67%|██████▋   | 18895/28080 [37:21:02<18:05:43,  7.09s/it]
 67%|██████▋   | 18896/28080 [37:21:09<18:05:49,  7.09s/it]
                                                           
{'loss': 0.5888, 'learning_rate': 0.00012763121084729084, 'epoch': 8.07}

 67%|██████▋   | 18896/28080 [37:21:09<18:05:49,  7.09s/it]
 67%|██████▋   | 18897/28080 [37:21:16<18:06:24,  7.10s/it]
                                                           
{'loss': 0.6086, 'learning_rate': 0.00012760606642726175, 'epoch': 8.07}

 67%|██████▋   | 18897/28080 [37:21:16<18:06:24,  7.10s/it]
 67%|██████▋   | 18898/28080 [37:21:23<18:13:07,  7.14s/it]
                                                           
{'loss': 0.6214, 'learning_rate': 0.0001275809236355577, 'epoch': 8.07}

 67%|██████▋   | 18898/28080 [37:21:23<18:13:07,  7.14s/it]
 67%|██████▋   | 18899/28080 [37:21:30<18:13:58,  7.15s/it]
                                                           
{'loss': 0.6198, 'learning_rate': 0.00012755578247251314, 'epoch': 8.07}

 67%|██████▋   | 18899/28080 [37:21:30<18:13:58,  7.15s/it]
 67%|██████▋   | 18900/28080 [37:21:37<18:11:57,  7.14s/it]
                                                           
{'loss': 0.6243, 'learning_rate': 0.0001275306429384625, 'epoch': 8.07}

 67%|██████▋   | 18900/28080 [37:21:37<18:11:57,  7.14s/it]
 67%|██████▋   | 18901/28080 [37:21:45<18:13:46,  7.15s/it]
                                                           
{'loss': 0.6172, 'learning_rate': 0.00012750550503374042, 'epoch': 8.07}

 67%|██████▋   | 18901/28080 [37:21:45<18:13:46,  7.15s/it]
 67%|██████▋   | 18902/28080 [37:21:52<18:15:49,  7.16s/it]
                                                           
{'loss': 0.6076, 'learning_rate': 0.00012748036875868114, 'epoch': 8.07}

 67%|██████▋   | 18902/28080 [37:21:52<18:15:49,  7.16s/it]
 67%|██████▋   | 18903/28080 [37:21:59<18:14:00,  7.15s/it]
                                                           
{'loss': 0.6151, 'learning_rate': 0.0001274552341136192, 'epoch': 8.08}

 67%|██████▋   | 18903/28080 [37:21:59<18:14:00,  7.15s/it]
 67%|██████▋   | 18904/28080 [37:22:06<18:12:39,  7.14s/it]
                                                           
{'loss': 0.6485, 'learning_rate': 0.00012743010109888896, 'epoch': 8.08}

 67%|██████▋   | 18904/28080 [37:22:06<18:12:39,  7.14s/it]
 67%|██████▋   | 18905/28080 [37:22:13<18:09:24,  7.12s/it]
                                                           
{'loss': 0.6216, 'learning_rate': 0.0001274049697148248, 'epoch': 8.08}

 67%|██████▋   | 18905/28080 [37:22:13<18:09:24,  7.12s/it]
 67%|██████▋   | 18906/28080 [37:22:20<18:04:57,  7.10s/it]
                                                           
{'loss': 0.6024, 'learning_rate': 0.00012737983996176095, 'epoch': 8.08}

 67%|██████▋   | 18906/28080 [37:22:20<18:04:57,  7.10s/it]
 67%|██████▋   | 18907/28080 [37:22:27<18:08:37,  7.12s/it]
                                                           
{'loss': 0.5977, 'learning_rate': 0.00012735471184003192, 'epoch': 8.08}

 67%|██████▋   | 18907/28080 [37:22:27<18:08:37,  7.12s/it]
 67%|██████▋   | 18908/28080 [37:22:34<18:06:19,  7.11s/it]
                                                           
{'loss': 0.605, 'learning_rate': 0.00012732958534997192, 'epoch': 8.08}

 67%|██████▋   | 18908/28080 [37:22:34<18:06:19,  7.11s/it]
 67%|██████▋   | 18909/28080 [37:22:41<18:04:54,  7.10s/it]
                                                           
{'loss': 0.6008, 'learning_rate': 0.00012730446049191523, 'epoch': 8.08}

 67%|██████▋   | 18909/28080 [37:22:41<18:04:54,  7.10s/it]
 67%|██████▋   | 18910/28080 [37:22:49<18:10:46,  7.14s/it]
                                                           
{'loss': 0.6309, 'learning_rate': 0.00012727933726619604, 'epoch': 8.08}

 67%|██████▋   | 18910/28080 [37:22:49<18:10:46,  7.14s/it]
 67%|██████▋   | 18911/28080 [37:22:56<18:09:04,  7.13s/it]
                                                           
{'loss': 0.6283, 'learning_rate': 0.0001272542156731487, 'epoch': 8.08}

 67%|██████▋   | 18911/28080 [37:22:56<18:09:04,  7.13s/it]
 67%|██████▋   | 18912/28080 [37:23:03<18:04:17,  7.10s/it]
                                                           
{'loss': 0.6019, 'learning_rate': 0.00012722909571310736, 'epoch': 8.08}

 67%|██████▋   | 18912/28080 [37:23:03<18:04:17,  7.10s/it]
 67%|██████▋   | 18913/28080 [37:23:10<18:08:09,  7.12s/it]
                                                           
{'loss': 0.6072, 'learning_rate': 0.00012720397738640642, 'epoch': 8.08}

 67%|██████▋   | 18913/28080 [37:23:10<18:08:09,  7.12s/it]
 67%|██████▋   | 18914/28080 [37:23:17<18:08:29,  7.13s/it]
                                                           
{'loss': 0.6142, 'learning_rate': 0.0001271788606933797, 'epoch': 8.08}

 67%|██████▋   | 18914/28080 [37:23:17<18:08:29,  7.13s/it]
 67%|██████▋   | 18915/28080 [37:23:24<18:01:33,  7.08s/it]
                                                           
{'loss': 0.6004, 'learning_rate': 0.0001271537456343616, 'epoch': 8.08}

 67%|██████▋   | 18915/28080 [37:23:24<18:01:33,  7.08s/it]
 67%|██████▋   | 18916/28080 [37:23:31<18:02:52,  7.09s/it]
                                                           
{'loss': 0.5905, 'learning_rate': 0.00012712863220968606, 'epoch': 8.08}

 67%|██████▋   | 18916/28080 [37:23:31<18:02:52,  7.09s/it]
 67%|██████▋   | 18917/28080 [37:23:38<18:04:59,  7.10s/it]
                                                           
{'loss': 0.6172, 'learning_rate': 0.00012710352041968748, 'epoch': 8.08}

 67%|██████▋   | 18917/28080 [37:23:38<18:04:59,  7.10s/it]
 67%|██████▋   | 18918/28080 [37:23:46<18:13:13,  7.16s/it]
                                                           
{'loss': 0.6241, 'learning_rate': 0.0001270784102646998, 'epoch': 8.08}

 67%|██████▋   | 18918/28080 [37:23:46<18:13:13,  7.16s/it]
 67%|██████▋   | 18919/28080 [37:23:53<18:09:23,  7.13s/it]
                                                           
{'loss': 0.6077, 'learning_rate': 0.0001270533017450569, 'epoch': 8.08}

 67%|██████▋   | 18919/28080 [37:23:53<18:09:23,  7.13s/it]
 67%|██████▋   | 18920/28080 [37:24:00<18:06:42,  7.12s/it]
                                                           
{'loss': 0.6185, 'learning_rate': 0.00012702819486109306, 'epoch': 8.08}

 67%|██████▋   | 18920/28080 [37:24:00<18:06:42,  7.12s/it]
 67%|██████▋   | 18921/28080 [37:24:07<18:05:20,  7.11s/it]
                                                           
{'loss': 0.5908, 'learning_rate': 0.00012700308961314217, 'epoch': 8.08}

 67%|██████▋   | 18921/28080 [37:24:07<18:05:20,  7.11s/it]
 67%|██████▋   | 18922/28080 [37:24:14<18:07:55,  7.13s/it]
                                                           
{'loss': 0.5974, 'learning_rate': 0.00012697798600153838, 'epoch': 8.08}

 67%|██████▋   | 18922/28080 [37:24:14<18:07:55,  7.13s/it]
 67%|██████▋   | 18923/28080 [37:24:21<18:08:04,  7.13s/it]
                                                           
{'loss': 0.6035, 'learning_rate': 0.00012695288402661553, 'epoch': 8.08}

 67%|██████▋   | 18923/28080 [37:24:21<18:08:04,  7.13s/it]
 67%|██████▋   | 18924/28080 [37:24:28<18:06:52,  7.12s/it]
                                                           
{'loss': 0.6087, 'learning_rate': 0.00012692778368870764, 'epoch': 8.08}

 67%|██████▋   | 18924/28080 [37:24:28<18:06:52,  7.12s/it]
 67%|██████▋   | 18925/28080 [37:24:35<18:02:09,  7.09s/it]
                                                           
{'loss': 0.644, 'learning_rate': 0.0001269026849881485, 'epoch': 8.08}

 67%|██████▋   | 18925/28080 [37:24:35<18:02:09,  7.09s/it]
 67%|██████▋   | 18926/28080 [37:24:42<18:00:50,  7.08s/it]
                                                           
{'loss': 0.6183, 'learning_rate': 0.00012687758792527225, 'epoch': 8.09}

 67%|██████▋   | 18926/28080 [37:24:42<18:00:50,  7.08s/it]
 67%|██████▋   | 18927/28080 [37:24:50<18:06:43,  7.12s/it]
                                                           
{'loss': 0.6111, 'learning_rate': 0.0001268524925004127, 'epoch': 8.09}

 67%|██████▋   | 18927/28080 [37:24:50<18:06:43,  7.12s/it]
 67%|██████▋   | 18928/28080 [37:24:57<18:05:57,  7.12s/it]
                                                           
{'loss': 0.5914, 'learning_rate': 0.0001268273987139037, 'epoch': 8.09}

 67%|██████▋   | 18928/28080 [37:24:57<18:05:57,  7.12s/it]
 67%|██████▋   | 18929/28080 [37:25:04<18:05:51,  7.12s/it]
                                                           
{'loss': 0.6079, 'learning_rate': 0.00012680230656607894, 'epoch': 8.09}

 67%|██████▋   | 18929/28080 [37:25:04<18:05:51,  7.12s/it]
 67%|██████▋   | 18930/28080 [37:25:11<18:01:03,  7.09s/it]
                                                           
{'loss': 0.6138, 'learning_rate': 0.00012677721605727256, 'epoch': 8.09}

 67%|██████▋   | 18930/28080 [37:25:11<18:01:03,  7.09s/it]
 67%|██████▋   | 18931/28080 [37:25:18<18:04:06,  7.11s/it]
                                                           
{'loss': 0.5953, 'learning_rate': 0.00012675212718781803, 'epoch': 8.09}

 67%|██████▋   | 18931/28080 [37:25:18<18:04:06,  7.11s/it]
 67%|██████▋   | 18932/28080 [37:25:25<17:58:45,  7.08s/it]
                                                           
{'loss': 0.6219, 'learning_rate': 0.00012672703995804955, 'epoch': 8.09}

 67%|██████▋   | 18932/28080 [37:25:25<17:58:45,  7.08s/it]
 67%|██████▋   | 18933/28080 [37:25:32<18:02:38,  7.10s/it]
                                                           
{'loss': 0.6038, 'learning_rate': 0.0001267019543683004, 'epoch': 8.09}

 67%|██████▋   | 18933/28080 [37:25:32<18:02:38,  7.10s/it]
 67%|██████▋   | 18934/28080 [37:25:39<17:59:49,  7.08s/it]
                                                           
{'loss': 0.6167, 'learning_rate': 0.0001266768704189047, 'epoch': 8.09}

 67%|██████▋   | 18934/28080 [37:25:39<17:59:49,  7.08s/it]
 67%|██████▋   | 18935/28080 [37:25:46<18:02:41,  7.10s/it]
                                                           
{'loss': 0.6083, 'learning_rate': 0.00012665178811019584, 'epoch': 8.09}

 67%|██████▋   | 18935/28080 [37:25:46<18:02:41,  7.10s/it]
 67%|██████▋   | 18936/28080 [37:25:53<18:03:42,  7.11s/it]
                                                           
{'loss': 0.6207, 'learning_rate': 0.0001266267074425078, 'epoch': 8.09}

 67%|██████▋   | 18936/28080 [37:25:53<18:03:42,  7.11s/it]
 67%|██████▋   | 18937/28080 [37:26:01<18:00:02,  7.09s/it]
                                                           
{'loss': 0.6305, 'learning_rate': 0.00012660162841617416, 'epoch': 8.09}

 67%|██████▋   | 18937/28080 [37:26:01<18:00:02,  7.09s/it]
 67%|██████▋   | 18938/28080 [37:26:08<18:03:52,  7.11s/it]
                                                           
{'loss': 0.6105, 'learning_rate': 0.00012657655103152858, 'epoch': 8.09}

 67%|██████▋   | 18938/28080 [37:26:08<18:03:52,  7.11s/it]
 67%|██████▋   | 18939/28080 [37:26:15<18:04:04,  7.12s/it]
                                                           
{'loss': 0.6032, 'learning_rate': 0.00012655147528890454, 'epoch': 8.09}

 67%|██████▋   | 18939/28080 [37:26:15<18:04:04,  7.12s/it]
 67%|██████▋   | 18940/28080 [37:26:22<18:01:00,  7.10s/it]
                                                           
{'loss': 0.6101, 'learning_rate': 0.00012652640118863585, 'epoch': 8.09}

 67%|██████▋   | 18940/28080 [37:26:22<18:01:00,  7.10s/it]
 67%|██████▋   | 18941/28080 [37:26:29<18:01:03,  7.10s/it]
                                                           
{'loss': 0.5823, 'learning_rate': 0.00012650132873105602, 'epoch': 8.09}

 67%|██████▋   | 18941/28080 [37:26:29<18:01:03,  7.10s/it]
 67%|██████▋   | 18942/28080 [37:26:36<18:00:28,  7.09s/it]
                                                           
{'loss': 0.6, 'learning_rate': 0.00012647625791649858, 'epoch': 8.09}

 67%|██████▋   | 18942/28080 [37:26:36<18:00:28,  7.09s/it]
 67%|██████▋   | 18943/28080 [37:26:43<17:57:56,  7.08s/it]
                                                           
{'loss': 0.6271, 'learning_rate': 0.00012645118874529714, 'epoch': 8.09}

 67%|██████▋   | 18943/28080 [37:26:43<17:57:56,  7.08s/it]
 67%|██████▋   | 18944/28080 [37:26:50<17:57:50,  7.08s/it]
                                                           
{'loss': 0.6238, 'learning_rate': 0.00012642612121778506, 'epoch': 8.09}

 67%|██████▋   | 18944/28080 [37:26:50<17:57:50,  7.08s/it]
 67%|██████▋   | 18945/28080 [37:26:57<18:01:25,  7.10s/it]
                                                           
{'loss': 0.6003, 'learning_rate': 0.00012640105533429606, 'epoch': 8.09}

 67%|██████▋   | 18945/28080 [37:26:57<18:01:25,  7.10s/it]
 67%|██████▋   | 18946/28080 [37:27:04<17:59:04,  7.09s/it]
                                                           
{'loss': 0.6029, 'learning_rate': 0.00012637599109516348, 'epoch': 8.09}

 67%|██████▋   | 18946/28080 [37:27:04<17:59:04,  7.09s/it]
 67%|██████▋   | 18947/28080 [37:27:11<17:58:14,  7.08s/it]
                                                           
{'loss': 0.6053, 'learning_rate': 0.00012635092850072082, 'epoch': 8.09}

 67%|██████▋   | 18947/28080 [37:27:11<17:58:14,  7.08s/it]
 67%|██████▋   | 18948/28080 [37:27:19<18:01:43,  7.11s/it]
                                                           
{'loss': 0.5913, 'learning_rate': 0.0001263258675513014, 'epoch': 8.09}

 67%|██████▋   | 18948/28080 [37:27:19<18:01:43,  7.11s/it]
 67%|██████▋   | 18949/28080 [37:27:26<18:06:25,  7.14s/it]
                                                           
{'loss': 0.6033, 'learning_rate': 0.00012630080824723884, 'epoch': 8.09}

 67%|██████▋   | 18949/28080 [37:27:26<18:06:25,  7.14s/it]
 67%|██████▋   | 18950/28080 [37:27:33<18:03:35,  7.12s/it]
                                                           
{'loss': 0.6198, 'learning_rate': 0.00012627575058886628, 'epoch': 8.1}

 67%|██████▋   | 18950/28080 [37:27:33<18:03:35,  7.12s/it]
 67%|██████▋   | 18951/28080 [37:27:40<18:02:06,  7.11s/it]
                                                           
{'loss': 0.6136, 'learning_rate': 0.00012625069457651732, 'epoch': 8.1}

 67%|██████▋   | 18951/28080 [37:27:40<18:02:06,  7.11s/it]
 67%|██████▋   | 18952/28080 [37:27:47<18:03:32,  7.12s/it]
                                                           
{'loss': 0.6152, 'learning_rate': 0.00012622564021052524, 'epoch': 8.1}

 67%|██████▋   | 18952/28080 [37:27:47<18:03:32,  7.12s/it]
 67%|██████▋   | 18953/28080 [37:27:54<18:04:36,  7.13s/it]
                                                           
{'loss': 0.5962, 'learning_rate': 0.0001262005874912233, 'epoch': 8.1}

 67%|██████▋   | 18953/28080 [37:27:54<18:04:36,  7.13s/it]
 68%|██████▊   | 18954/28080 [37:28:01<17:59:41,  7.10s/it]
                                                           
{'loss': 0.6026, 'learning_rate': 0.0001261755364189447, 'epoch': 8.1}

 68%|██████▊   | 18954/28080 [37:28:01<17:59:41,  7.10s/it]
 68%|██████▊   | 18955/28080 [37:28:08<17:58:43,  7.09s/it]
                                                           
{'loss': 0.6263, 'learning_rate': 0.000126150486994023, 'epoch': 8.1}

 68%|██████▊   | 18955/28080 [37:28:08<17:58:43,  7.09s/it]
 68%|██████▊   | 18956/28080 [37:28:16<18:05:18,  7.14s/it]
                                                           
{'loss': 0.6128, 'learning_rate': 0.00012612543921679126, 'epoch': 8.1}

 68%|██████▊   | 18956/28080 [37:28:16<18:05:18,  7.14s/it]
 68%|██████▊   | 18957/28080 [37:28:23<18:08:56,  7.16s/it]
                                                           
{'loss': 0.5976, 'learning_rate': 0.00012610039308758278, 'epoch': 8.1}

 68%|██████▊   | 18957/28080 [37:28:23<18:08:56,  7.16s/it]
 68%|██████▊   | 18958/28080 [37:28:30<18:05:29,  7.14s/it]
                                                           
{'loss': 0.634, 'learning_rate': 0.00012607534860673066, 'epoch': 8.1}

 68%|██████▊   | 18958/28080 [37:28:30<18:05:29,  7.14s/it]
 68%|██████▊   | 18959/28080 [37:28:37<18:05:13,  7.14s/it]
                                                           
{'loss': 0.6122, 'learning_rate': 0.00012605030577456824, 'epoch': 8.1}

 68%|██████▊   | 18959/28080 [37:28:37<18:05:13,  7.14s/it]
 68%|██████▊   | 18960/28080 [37:28:44<18:03:29,  7.13s/it]
                                                           
{'loss': 0.6117, 'learning_rate': 0.00012602526459142867, 'epoch': 8.1}

 68%|██████▊   | 18960/28080 [37:28:44<18:03:29,  7.13s/it]
 68%|██████▊   | 18961/28080 [37:28:51<18:01:51,  7.12s/it]
                                                           
{'loss': 0.6208, 'learning_rate': 0.00012600022505764502, 'epoch': 8.1}

 68%|██████▊   | 18961/28080 [37:28:51<18:01:51,  7.12s/it]
 68%|██████▊   | 18962/28080 [37:28:58<18:05:28,  7.14s/it]
                                                           
{'loss': 0.6136, 'learning_rate': 0.00012597518717355038, 'epoch': 8.1}

 68%|██████▊   | 18962/28080 [37:28:59<18:05:28,  7.14s/it]
 68%|██████▊   | 18963/28080 [37:29:06<18:05:05,  7.14s/it]
                                                           
{'loss': 0.6034, 'learning_rate': 0.00012595015093947804, 'epoch': 8.1}

 68%|██████▊   | 18963/28080 [37:29:06<18:05:05,  7.14s/it]
 68%|██████▊   | 18964/28080 [37:29:13<18:11:01,  7.18s/it]
                                                           
{'loss': 0.5856, 'learning_rate': 0.0001259251163557608, 'epoch': 8.1}

 68%|██████▊   | 18964/28080 [37:29:13<18:11:01,  7.18s/it]
 68%|██████▊   | 18965/28080 [37:29:20<18:16:18,  7.22s/it]
                                                           
{'loss': 0.6133, 'learning_rate': 0.00012590008342273207, 'epoch': 8.1}

 68%|██████▊   | 18965/28080 [37:29:20<18:16:18,  7.22s/it]
 68%|██████▊   | 18966/28080 [37:29:27<18:11:07,  7.18s/it]
                                                           
{'loss': 0.6079, 'learning_rate': 0.00012587505214072464, 'epoch': 8.1}

 68%|██████▊   | 18966/28080 [37:29:27<18:11:07,  7.18s/it]
 68%|██████▊   | 18967/28080 [37:29:35<18:12:51,  7.20s/it]
                                                           
{'loss': 0.584, 'learning_rate': 0.00012585002251007163, 'epoch': 8.1}

 68%|██████▊   | 18967/28080 [37:29:35<18:12:51,  7.20s/it]
 68%|██████▊   | 18968/28080 [37:29:42<18:06:23,  7.15s/it]
                                                           
{'loss': 0.5973, 'learning_rate': 0.00012582499453110595, 'epoch': 8.1}

 68%|██████▊   | 18968/28080 [37:29:42<18:06:23,  7.15s/it]
 68%|██████▊   | 18969/28080 [37:29:49<18:03:42,  7.14s/it]
                                                           
{'loss': 0.5924, 'learning_rate': 0.00012579996820416057, 'epoch': 8.1}

 68%|██████▊   | 18969/28080 [37:29:49<18:03:42,  7.14s/it]
 68%|██████▊   | 18970/28080 [37:29:56<18:03:54,  7.14s/it]
                                                           
{'loss': 0.6029, 'learning_rate': 0.00012577494352956854, 'epoch': 8.1}

 68%|██████▊   | 18970/28080 [37:29:56<18:03:54,  7.14s/it]
 68%|██████▊   | 18971/28080 [37:30:03<17:56:27,  7.09s/it]
                                                           
{'loss': 0.6211, 'learning_rate': 0.00012574992050766277, 'epoch': 8.1}

 68%|██████▊   | 18971/28080 [37:30:03<17:56:27,  7.09s/it]
 68%|██████▊   | 18972/28080 [37:30:10<18:00:03,  7.12s/it]
                                                           
{'loss': 0.6086, 'learning_rate': 0.00012572489913877607, 'epoch': 8.1}

 68%|██████▊   | 18972/28080 [37:30:10<18:00:03,  7.12s/it]
 68%|██████▊   | 18973/28080 [37:30:17<17:55:39,  7.09s/it]
                                                           
{'loss': 0.63, 'learning_rate': 0.00012569987942324132, 'epoch': 8.11}

 68%|██████▊   | 18973/28080 [37:30:17<17:55:39,  7.09s/it]
 68%|██████▊   | 18974/28080 [37:30:24<17:56:28,  7.09s/it]
                                                           
{'loss': 0.6154, 'learning_rate': 0.0001256748613613915, 'epoch': 8.11}

 68%|██████▊   | 18974/28080 [37:30:24<17:56:28,  7.09s/it]
 68%|██████▊   | 18975/28080 [37:30:31<17:53:28,  7.07s/it]
                                                           
{'loss': 0.6164, 'learning_rate': 0.00012564984495355943, 'epoch': 8.11}

 68%|██████▊   | 18975/28080 [37:30:31<17:53:28,  7.07s/it]
 68%|██████▊   | 18976/28080 [37:30:38<17:55:59,  7.09s/it]
                                                           
{'loss': 0.5928, 'learning_rate': 0.00012562483020007786, 'epoch': 8.11}

 68%|██████▊   | 18976/28080 [37:30:38<17:55:59,  7.09s/it]
 68%|██████▊   | 18977/28080 [37:30:45<17:56:06,  7.09s/it]
                                                           
{'loss': 0.605, 'learning_rate': 0.00012559981710127954, 'epoch': 8.11}

 68%|██████▊   | 18977/28080 [37:30:45<17:56:06,  7.09s/it]
 68%|██████▊   | 18978/28080 [37:30:53<18:02:30,  7.14s/it]
                                                           
{'loss': 0.5984, 'learning_rate': 0.0001255748056574974, 'epoch': 8.11}

 68%|██████▊   | 18978/28080 [37:30:53<18:02:30,  7.14s/it]
 68%|██████▊   | 18979/28080 [37:31:00<17:58:43,  7.11s/it]
                                                           
{'loss': 0.6002, 'learning_rate': 0.00012554979586906404, 'epoch': 8.11}

 68%|██████▊   | 18979/28080 [37:31:00<17:58:43,  7.11s/it]
 68%|██████▊   | 18980/28080 [37:31:07<18:07:42,  7.17s/it]
                                                           
{'loss': 0.583, 'learning_rate': 0.00012552478773631242, 'epoch': 8.11}

 68%|██████▊   | 18980/28080 [37:31:07<18:07:42,  7.17s/it]
 68%|██████▊   | 18981/28080 [37:31:14<18:10:47,  7.19s/it]
                                                           
{'loss': 0.5936, 'learning_rate': 0.0001254997812595749, 'epoch': 8.11}

 68%|██████▊   | 18981/28080 [37:31:14<18:10:47,  7.19s/it]
 68%|██████▊   | 18982/28080 [37:31:21<18:09:07,  7.18s/it]
                                                           
{'loss': 0.6315, 'learning_rate': 0.00012547477643918447, 'epoch': 8.11}

 68%|██████▊   | 18982/28080 [37:31:21<18:09:07,  7.18s/it]
 68%|██████▊   | 18983/28080 [37:31:28<18:04:04,  7.15s/it]
                                                           
{'loss': 0.6063, 'learning_rate': 0.00012544977327547354, 'epoch': 8.11}

 68%|██████▊   | 18983/28080 [37:31:28<18:04:04,  7.15s/it]
 68%|██████▊   | 18984/28080 [37:31:36<18:00:09,  7.13s/it]
                                                           
{'loss': 0.5872, 'learning_rate': 0.000125424771768775, 'epoch': 8.11}

 68%|██████▊   | 18984/28080 [37:31:36<18:00:09,  7.13s/it]
 68%|██████▊   | 18985/28080 [37:31:43<17:58:48,  7.12s/it]
                                                           
{'loss': 0.6092, 'learning_rate': 0.00012539977191942136, 'epoch': 8.11}

 68%|██████▊   | 18985/28080 [37:31:43<17:58:48,  7.12s/it]
 68%|██████▊   | 18986/28080 [37:31:50<18:01:41,  7.14s/it]
                                                           
{'loss': 0.6144, 'learning_rate': 0.00012537477372774519, 'epoch': 8.11}

 68%|██████▊   | 18986/28080 [37:31:50<18:01:41,  7.14s/it]
 68%|██████▊   | 18987/28080 [37:31:57<18:02:43,  7.14s/it]
                                                           
{'loss': 0.5931, 'learning_rate': 0.00012534977719407903, 'epoch': 8.11}

 68%|██████▊   | 18987/28080 [37:31:57<18:02:43,  7.14s/it]
 68%|██████▊   | 18988/28080 [37:32:04<18:01:54,  7.14s/it]
                                                           
{'loss': 0.5908, 'learning_rate': 0.00012532478231875555, 'epoch': 8.11}

 68%|██████▊   | 18988/28080 [37:32:04<18:01:54,  7.14s/it]
 68%|██████▊   | 18989/28080 [37:32:11<18:02:14,  7.14s/it]
                                                           
{'loss': 0.5985, 'learning_rate': 0.00012529978910210722, 'epoch': 8.11}

 68%|██████▊   | 18989/28080 [37:32:11<18:02:14,  7.14s/it]
 68%|██████▊   | 18990/28080 [37:32:18<18:04:04,  7.16s/it]
                                                           
{'loss': 0.5957, 'learning_rate': 0.0001252747975444666, 'epoch': 8.11}

 68%|██████▊   | 18990/28080 [37:32:18<18:04:04,  7.16s/it]
 68%|██████▊   | 18991/28080 [37:32:25<17:58:10,  7.12s/it]
                                                           
{'loss': 0.6131, 'learning_rate': 0.00012524980764616595, 'epoch': 8.11}

 68%|██████▊   | 18991/28080 [37:32:25<17:58:10,  7.12s/it]
 68%|██████▊   | 18992/28080 [37:32:33<17:59:22,  7.13s/it]
                                                           
{'loss': 0.6109, 'learning_rate': 0.00012522481940753806, 'epoch': 8.11}

 68%|██████▊   | 18992/28080 [37:32:33<17:59:22,  7.13s/it]
 68%|██████▊   | 18993/28080 [37:32:40<17:59:36,  7.13s/it]
                                                           
{'loss': 0.5921, 'learning_rate': 0.00012519983282891523, 'epoch': 8.11}

 68%|██████▊   | 18993/28080 [37:32:40<17:59:36,  7.13s/it]
 68%|██████▊   | 18994/28080 [37:32:47<18:02:11,  7.15s/it]
                                                           
{'loss': 0.6073, 'learning_rate': 0.00012517484791062984, 'epoch': 8.11}

 68%|██████▊   | 18994/28080 [37:32:47<18:02:11,  7.15s/it]
 68%|██████▊   | 18995/28080 [37:32:54<18:03:04,  7.15s/it]
                                                           
{'loss': 0.6101, 'learning_rate': 0.00012514986465301438, 'epoch': 8.11}

 68%|██████▊   | 18995/28080 [37:32:54<18:03:04,  7.15s/it]
 68%|██████▊   | 18996/28080 [37:33:01<18:06:11,  7.17s/it]
                                                           
{'loss': 0.596, 'learning_rate': 0.000125124883056401, 'epoch': 8.11}

 68%|██████▊   | 18996/28080 [37:33:01<18:06:11,  7.17s/it]
 68%|██████▊   | 18997/28080 [37:33:08<17:58:51,  7.13s/it]
                                                           
{'loss': 0.6211, 'learning_rate': 0.00012509990312112234, 'epoch': 8.12}

 68%|██████▊   | 18997/28080 [37:33:08<17:58:51,  7.13s/it]
 68%|██████▊   | 18998/28080 [37:33:15<17:56:45,  7.11s/it]
                                                           
{'loss': 0.6062, 'learning_rate': 0.00012507492484751053, 'epoch': 8.12}

 68%|██████▊   | 18998/28080 [37:33:15<17:56:45,  7.11s/it]
 68%|██████▊   | 18999/28080 [37:33:23<18:00:17,  7.14s/it]
                                                           
{'loss': 0.5956, 'learning_rate': 0.0001250499482358982, 'epoch': 8.12}

 68%|██████▊   | 18999/28080 [37:33:23<18:00:17,  7.14s/it]
 68%|██████▊   | 19000/28080 [37:33:30<17:57:51,  7.12s/it]
                                                           
{'loss': 0.5987, 'learning_rate': 0.00012502497328661715, 'epoch': 8.12}

 68%|██████▊   | 19000/28080 [37:33:30<17:57:51,  7.12s/it]
 68%|██████▊   | 19001/28080 [37:33:37<17:56:19,  7.11s/it]
                                                           
{'loss': 0.6018, 'learning_rate': 0.00012500000000000006, 'epoch': 8.12}

 68%|██████▊   | 19001/28080 [37:33:37<17:56:19,  7.11s/it]
 68%|██████▊   | 19002/28080 [37:33:44<17:57:19,  7.12s/it]
                                                           
{'loss': 0.6222, 'learning_rate': 0.0001249750283763789, 'epoch': 8.12}

 68%|██████▊   | 19002/28080 [37:33:44<17:57:19,  7.12s/it]
 68%|██████▊   | 19003/28080 [37:33:51<17:56:59,  7.12s/it]
                                                           
{'loss': 0.5988, 'learning_rate': 0.00012495005841608607, 'epoch': 8.12}

 68%|██████▊   | 19003/28080 [37:33:51<17:56:59,  7.12s/it]
 68%|██████▊   | 19004/28080 [37:33:58<17:54:01,  7.10s/it]
                                                           
{'loss': 0.5803, 'learning_rate': 0.00012492509011945372, 'epoch': 8.12}

 68%|██████▊   | 19004/28080 [37:33:58<17:54:01,  7.10s/it]
 68%|██████▊   | 19005/28080 [37:34:05<17:56:11,  7.12s/it]
                                                           
{'loss': 0.6227, 'learning_rate': 0.000124900123486814, 'epoch': 8.12}

 68%|██████▊   | 19005/28080 [37:34:05<17:56:11,  7.12s/it]
 68%|██████▊   | 19006/28080 [37:34:12<17:55:16,  7.11s/it]
                                                           
{'loss': 0.6132, 'learning_rate': 0.000124875158518499, 'epoch': 8.12}

 68%|██████▊   | 19006/28080 [37:34:12<17:55:16,  7.11s/it]
 68%|██████▊   | 19007/28080 [37:34:19<17:55:48,  7.11s/it]
                                                           
{'loss': 0.6091, 'learning_rate': 0.00012485019521484104, 'epoch': 8.12}

 68%|██████▊   | 19007/28080 [37:34:19<17:55:48,  7.11s/it]
 68%|██████▊   | 19008/28080 [37:34:27<17:52:58,  7.10s/it]
                                                           
{'loss': 0.6119, 'learning_rate': 0.00012482523357617211, 'epoch': 8.12}

 68%|██████▊   | 19008/28080 [37:34:27<17:52:58,  7.10s/it]
 68%|██████▊   | 19009/28080 [37:34:34<17:54:13,  7.11s/it]
                                                           
{'loss': 0.6284, 'learning_rate': 0.00012480027360282431, 'epoch': 8.12}

 68%|██████▊   | 19009/28080 [37:34:34<17:54:13,  7.11s/it]
 68%|██████▊   | 19010/28080 [37:34:41<17:57:43,  7.13s/it]
                                                           
{'loss': 0.6183, 'learning_rate': 0.00012477531529512962, 'epoch': 8.12}

 68%|██████▊   | 19010/28080 [37:34:41<17:57:43,  7.13s/it]
 68%|██████▊   | 19011/28080 [37:34:48<17:56:27,  7.12s/it]
                                                           
{'loss': 0.6261, 'learning_rate': 0.00012475035865342027, 'epoch': 8.12}

 68%|██████▊   | 19011/28080 [37:34:48<17:56:27,  7.12s/it]
 68%|██████▊   | 19012/28080 [37:34:55<17:50:53,  7.09s/it]
                                                           
{'loss': 0.6116, 'learning_rate': 0.00012472540367802805, 'epoch': 8.12}

 68%|██████▊   | 19012/28080 [37:34:55<17:50:53,  7.09s/it]
 68%|██████▊   | 19013/28080 [37:35:02<17:55:24,  7.12s/it]
                                                           
{'loss': 0.6238, 'learning_rate': 0.00012470045036928526, 'epoch': 8.12}

 68%|██████▊   | 19013/28080 [37:35:02<17:55:24,  7.12s/it]
 68%|██████▊   | 19014/28080 [37:35:09<17:50:26,  7.08s/it]
                                                           
{'loss': 0.6142, 'learning_rate': 0.00012467549872752367, 'epoch': 8.12}

 68%|██████▊   | 19014/28080 [37:35:09<17:50:26,  7.08s/it]
 68%|██████▊   | 19015/28080 [37:35:16<17:47:13,  7.06s/it]
                                                           
{'loss': 0.6074, 'learning_rate': 0.00012465054875307528, 'epoch': 8.12}

 68%|██████▊   | 19015/28080 [37:35:16<17:47:13,  7.06s/it]
 68%|██████▊   | 19016/28080 [37:35:23<17:44:27,  7.05s/it]
                                                           
{'loss': 0.5969, 'learning_rate': 0.00012462560044627195, 'epoch': 8.12}

 68%|██████▊   | 19016/28080 [37:35:23<17:44:27,  7.05s/it]
 68%|██████▊   | 19017/28080 [37:35:30<17:47:26,  7.07s/it]
                                                           
{'loss': 0.622, 'learning_rate': 0.00012460065380744573, 'epoch': 8.12}

 68%|██████▊   | 19017/28080 [37:35:30<17:47:26,  7.07s/it]
 68%|██████▊   | 19018/28080 [37:35:37<17:45:55,  7.06s/it]
                                                           
{'loss': 0.6228, 'learning_rate': 0.00012457570883692845, 'epoch': 8.12}

 68%|██████▊   | 19018/28080 [37:35:37<17:45:55,  7.06s/it]
 68%|██████▊   | 19019/28080 [37:35:44<17:45:55,  7.06s/it]
                                                           
{'loss': 0.6102, 'learning_rate': 0.00012455076553505198, 'epoch': 8.12}

 68%|██████▊   | 19019/28080 [37:35:44<17:45:55,  7.06s/it]
 68%|██████▊   | 19020/28080 [37:35:52<17:50:53,  7.09s/it]
                                                           
{'loss': 0.6137, 'learning_rate': 0.00012452582390214817, 'epoch': 8.13}

 68%|██████▊   | 19020/28080 [37:35:52<17:50:53,  7.09s/it]
 68%|██████▊   | 19021/28080 [37:35:59<17:49:34,  7.08s/it]
                                                           
{'loss': 0.609, 'learning_rate': 0.00012450088393854873, 'epoch': 8.13}

 68%|██████▊   | 19021/28080 [37:35:59<17:49:34,  7.08s/it]
 68%|██████▊   | 19022/28080 [37:36:06<17:47:57,  7.07s/it]
                                                           
{'loss': 0.596, 'learning_rate': 0.00012447594564458562, 'epoch': 8.13}

 68%|██████▊   | 19022/28080 [37:36:06<17:47:57,  7.07s/it]
 68%|██████▊   | 19023/28080 [37:36:13<17:49:36,  7.09s/it]
                                                           
{'loss': 0.6063, 'learning_rate': 0.0001244510090205906, 'epoch': 8.13}

 68%|██████▊   | 19023/28080 [37:36:13<17:49:36,  7.09s/it]
 68%|██████▊   | 19024/28080 [37:36:20<17:50:31,  7.09s/it]
                                                           
{'loss': 0.6134, 'learning_rate': 0.00012442607406689535, 'epoch': 8.13}

 68%|██████▊   | 19024/28080 [37:36:20<17:50:31,  7.09s/it]
 68%|██████▊   | 19025/28080 [37:36:27<17:52:00,  7.10s/it]
                                                           
{'loss': 0.6052, 'learning_rate': 0.00012440114078383156, 'epoch': 8.13}

 68%|██████▊   | 19025/28080 [37:36:27<17:52:00,  7.10s/it]
 68%|██████▊   | 19026/28080 [37:36:34<17:52:27,  7.11s/it]
                                                           
{'loss': 0.6037, 'learning_rate': 0.0001243762091717311, 'epoch': 8.13}

 68%|██████▊   | 19026/28080 [37:36:34<17:52:27,  7.11s/it]
 68%|██████▊   | 19027/28080 [37:36:41<17:58:23,  7.15s/it]
                                                           
{'loss': 0.6209, 'learning_rate': 0.0001243512792309255, 'epoch': 8.13}

 68%|██████▊   | 19027/28080 [37:36:41<17:58:23,  7.15s/it]
 68%|██████▊   | 19028/28080 [37:36:49<17:59:11,  7.15s/it]
                                                           
{'loss': 0.6009, 'learning_rate': 0.00012432635096174666, 'epoch': 8.13}

 68%|██████▊   | 19028/28080 [37:36:49<17:59:11,  7.15s/it]
 68%|██████▊   | 19029/28080 [37:36:56<17:59:17,  7.15s/it]
                                                           
{'loss': 0.6056, 'learning_rate': 0.00012430142436452592, 'epoch': 8.13}

 68%|██████▊   | 19029/28080 [37:36:56<17:59:17,  7.15s/it]
 68%|██████▊   | 19030/28080 [37:37:03<17:55:32,  7.13s/it]
                                                           
{'loss': 0.5891, 'learning_rate': 0.00012427649943959514, 'epoch': 8.13}

 68%|██████▊   | 19030/28080 [37:37:03<17:55:32,  7.13s/it]
 68%|██████▊   | 19031/28080 [37:37:10<17:56:01,  7.13s/it]
                                                           
{'loss': 0.608, 'learning_rate': 0.0001242515761872857, 'epoch': 8.13}

 68%|██████▊   | 19031/28080 [37:37:10<17:56:01,  7.13s/it]
 68%|██████▊   | 19032/28080 [37:37:17<17:57:47,  7.15s/it]
                                                           
{'loss': 0.5905, 'learning_rate': 0.00012422665460792945, 'epoch': 8.13}

 68%|██████▊   | 19032/28080 [37:37:17<17:57:47,  7.15s/it]
 68%|██████▊   | 19033/28080 [37:37:24<17:54:57,  7.13s/it]
                                                           
{'loss': 0.597, 'learning_rate': 0.0001242017347018578, 'epoch': 8.13}

 68%|██████▊   | 19033/28080 [37:37:24<17:54:57,  7.13s/it]
 68%|██████▊   | 19034/28080 [37:37:31<17:54:35,  7.13s/it]
                                                           
{'loss': 0.6024, 'learning_rate': 0.0001241768164694023, 'epoch': 8.13}

 68%|██████▊   | 19034/28080 [37:37:31<17:54:35,  7.13s/it]
 68%|██████▊   | 19035/28080 [37:37:38<17:57:56,  7.15s/it]
                                                           
{'loss': 0.6063, 'learning_rate': 0.00012415189991089434, 'epoch': 8.13}

 68%|██████▊   | 19035/28080 [37:37:39<17:57:56,  7.15s/it]
 68%|██████▊   | 19036/28080 [37:37:46<17:56:58,  7.14s/it]
                                                           
{'loss': 0.609, 'learning_rate': 0.0001241269850266656, 'epoch': 8.13}

 68%|██████▊   | 19036/28080 [37:37:46<17:56:58,  7.14s/it]
 68%|██████▊   | 19037/28080 [37:37:53<17:57:25,  7.15s/it]
                                                           
{'loss': 0.5802, 'learning_rate': 0.00012410207181704752, 'epoch': 8.13}

 68%|██████▊   | 19037/28080 [37:37:53<17:57:25,  7.15s/it]
 68%|██████▊   | 19038/28080 [37:38:00<17:55:57,  7.14s/it]
                                                           
{'loss': 0.6098, 'learning_rate': 0.00012407716028237147, 'epoch': 8.13}

 68%|██████▊   | 19038/28080 [37:38:00<17:55:57,  7.14s/it]
 68%|██████▊   | 19039/28080 [37:38:07<17:58:36,  7.16s/it]
                                                           
{'loss': 0.5934, 'learning_rate': 0.00012405225042296878, 'epoch': 8.13}

 68%|██████▊   | 19039/28080 [37:38:07<17:58:36,  7.16s/it]
 68%|██████▊   | 19040/28080 [37:38:14<18:00:45,  7.17s/it]
                                                           
{'loss': 0.5953, 'learning_rate': 0.00012402734223917105, 'epoch': 8.13}

 68%|██████▊   | 19040/28080 [37:38:14<18:00:45,  7.17s/it]
 68%|██████▊   | 19041/28080 [37:38:21<17:52:52,  7.12s/it]
                                                           
{'loss': 0.6052, 'learning_rate': 0.0001240024357313095, 'epoch': 8.13}

 68%|██████▊   | 19041/28080 [37:38:21<17:52:52,  7.12s/it]
 68%|██████▊   | 19042/28080 [37:38:28<17:52:05,  7.12s/it]
                                                           
{'loss': 0.624, 'learning_rate': 0.0001239775308997158, 'epoch': 8.13}

 68%|██████▊   | 19042/28080 [37:38:28<17:52:05,  7.12s/it]
 68%|██████▊   | 19043/28080 [37:38:36<17:52:23,  7.12s/it]
                                                           
{'loss': 0.6112, 'learning_rate': 0.00012395262774472085, 'epoch': 8.13}

 68%|██████▊   | 19043/28080 [37:38:36<17:52:23,  7.12s/it]
 68%|██████▊   | 19044/28080 [37:38:43<17:48:38,  7.10s/it]
                                                           
{'loss': 0.6305, 'learning_rate': 0.0001239277262666561, 'epoch': 8.14}

 68%|██████▊   | 19044/28080 [37:38:43<17:48:38,  7.10s/it]
 68%|██████▊   | 19045/28080 [37:38:50<17:47:23,  7.09s/it]
                                                           
{'loss': 0.636, 'learning_rate': 0.00012390282646585298, 'epoch': 8.14}

 68%|██████▊   | 19045/28080 [37:38:50<17:47:23,  7.09s/it]
 68%|██████▊   | 19046/28080 [37:38:57<17:50:07,  7.11s/it]
                                                           
{'loss': 0.6154, 'learning_rate': 0.0001238779283426426, 'epoch': 8.14}

 68%|██████▊   | 19046/28080 [37:38:57<17:50:07,  7.11s/it]
 68%|██████▊   | 19047/28080 [37:39:04<17:49:48,  7.11s/it]
                                                           
{'loss': 0.5897, 'learning_rate': 0.00012385303189735644, 'epoch': 8.14}

 68%|██████▊   | 19047/28080 [37:39:04<17:49:48,  7.11s/it]
 68%|██████▊   | 19048/28080 [37:39:11<17:48:10,  7.10s/it]
                                                           
{'loss': 0.6008, 'learning_rate': 0.00012382813713032536, 'epoch': 8.14}

 68%|██████▊   | 19048/28080 [37:39:11<17:48:10,  7.10s/it]
 68%|██████▊   | 19049/28080 [37:39:18<17:50:51,  7.11s/it]
                                                           
{'loss': 0.6054, 'learning_rate': 0.00012380324404188085, 'epoch': 8.14}

 68%|██████▊   | 19049/28080 [37:39:18<17:50:51,  7.11s/it]
 68%|██████▊   | 19050/28080 [37:39:25<17:48:38,  7.10s/it]
                                                           
{'loss': 0.6215, 'learning_rate': 0.00012377835263235388, 'epoch': 8.14}

 68%|██████▊   | 19050/28080 [37:39:25<17:48:38,  7.10s/it]
 68%|██████▊   | 19051/28080 [37:39:32<17:50:16,  7.11s/it]
                                                           
{'loss': 0.6065, 'learning_rate': 0.00012375346290207582, 'epoch': 8.14}

 68%|██████▊   | 19051/28080 [37:39:32<17:50:16,  7.11s/it]
 68%|██████▊   | 19052/28080 [37:39:40<17:51:51,  7.12s/it]
                                                           
{'loss': 0.6016, 'learning_rate': 0.0001237285748513777, 'epoch': 8.14}

 68%|██████▊   | 19052/28080 [37:39:40<17:51:51,  7.12s/it]
 68%|██████▊   | 19053/28080 [37:39:47<17:55:05,  7.15s/it]
                                                           
{'loss': 0.6243, 'learning_rate': 0.0001237036884805906, 'epoch': 8.14}

 68%|██████▊   | 19053/28080 [37:39:47<17:55:05,  7.15s/it]
 68%|██████▊   | 19054/28080 [37:39:54<17:55:36,  7.15s/it]
                                                           
{'loss': 0.609, 'learning_rate': 0.00012367880379004557, 'epoch': 8.14}

 68%|██████▊   | 19054/28080 [37:39:54<17:55:36,  7.15s/it]
 68%|██████▊   | 19055/28080 [37:40:01<17:55:00,  7.15s/it]
                                                           
{'loss': 0.6109, 'learning_rate': 0.00012365392078007381, 'epoch': 8.14}

 68%|██████▊   | 19055/28080 [37:40:01<17:55:00,  7.15s/it]
 68%|██████▊   | 19056/28080 [37:40:08<18:03:26,  7.20s/it]
                                                           
{'loss': 0.612, 'learning_rate': 0.00012362903945100628, 'epoch': 8.14}

 68%|██████▊   | 19056/28080 [37:40:08<18:03:26,  7.20s/it]
 68%|██████▊   | 19057/28080 [37:40:16<18:05:24,  7.22s/it]
                                                           
{'loss': 0.6182, 'learning_rate': 0.00012360415980317406, 'epoch': 8.14}

 68%|██████▊   | 19057/28080 [37:40:16<18:05:24,  7.22s/it]
 68%|██████▊   | 19058/28080 [37:40:23<18:00:00,  7.18s/it]
                                                           
{'loss': 0.609, 'learning_rate': 0.00012357928183690794, 'epoch': 8.14}

 68%|██████▊   | 19058/28080 [37:40:23<18:00:00,  7.18s/it]
 68%|██████▊   | 19059/28080 [37:40:30<17:57:29,  7.17s/it]
                                                           
{'loss': 0.6249, 'learning_rate': 0.0001235544055525392, 'epoch': 8.14}

 68%|██████▊   | 19059/28080 [37:40:30<17:57:29,  7.17s/it]
 68%|██████▊   | 19060/28080 [37:40:37<18:03:36,  7.21s/it]
                                                           
{'loss': 0.6045, 'learning_rate': 0.00012352953095039855, 'epoch': 8.14}

 68%|██████▊   | 19060/28080 [37:40:37<18:03:36,  7.21s/it]
 68%|██████▊   | 19061/28080 [37:40:44<17:54:34,  7.15s/it]
                                                           
{'loss': 0.5925, 'learning_rate': 0.00012350465803081717, 'epoch': 8.14}

 68%|██████▊   | 19061/28080 [37:40:44<17:54:34,  7.15s/it]
 68%|██████▊   | 19062/28080 [37:40:51<17:56:13,  7.16s/it]
                                                           
{'loss': 0.6237, 'learning_rate': 0.00012347978679412563, 'epoch': 8.14}

 68%|██████▊   | 19062/28080 [37:40:51<17:56:13,  7.16s/it]
 68%|██████▊   | 19063/28080 [37:40:58<17:52:11,  7.13s/it]
                                                           
{'loss': 0.6087, 'learning_rate': 0.00012345491724065515, 'epoch': 8.14}

 68%|██████▊   | 19063/28080 [37:40:58<17:52:11,  7.13s/it]
 68%|██████▊   | 19064/28080 [37:41:05<17:47:18,  7.10s/it]
                                                           
{'loss': 0.6213, 'learning_rate': 0.0001234300493707363, 'epoch': 8.14}

 68%|██████▊   | 19064/28080 [37:41:05<17:47:18,  7.10s/it]
 68%|██████▊   | 19065/28080 [37:41:12<17:45:36,  7.09s/it]
                                                           
{'loss': 0.6193, 'learning_rate': 0.00012340518318470017, 'epoch': 8.14}

 68%|██████▊   | 19065/28080 [37:41:12<17:45:36,  7.09s/it]
 68%|██████▊   | 19066/28080 [37:41:20<17:50:15,  7.12s/it]
                                                           
{'loss': 0.5965, 'learning_rate': 0.0001233803186828775, 'epoch': 8.14}

 68%|██████▊   | 19066/28080 [37:41:20<17:50:15,  7.12s/it]
 68%|██████▊   | 19067/28080 [37:41:27<17:51:08,  7.13s/it]
                                                           
{'loss': 0.6039, 'learning_rate': 0.00012335545586559905, 'epoch': 8.15}

 68%|██████▊   | 19067/28080 [37:41:27<17:51:08,  7.13s/it]
 68%|██████▊   | 19068/28080 [37:41:34<17:52:10,  7.14s/it]
                                                           
{'loss': 0.605, 'learning_rate': 0.0001233305947331956, 'epoch': 8.15}

 68%|██████▊   | 19068/28080 [37:41:34<17:52:10,  7.14s/it]
 68%|██████▊   | 19069/28080 [37:41:41<17:50:46,  7.13s/it]
                                                           
{'loss': 0.595, 'learning_rate': 0.00012330573528599785, 'epoch': 8.15}

 68%|██████▊   | 19069/28080 [37:41:41<17:50:46,  7.13s/it]
 68%|██████▊   | 19070/28080 [37:41:48<17:51:58,  7.14s/it]
                                                           
{'loss': 0.6172, 'learning_rate': 0.00012328087752433664, 'epoch': 8.15}

 68%|██████▊   | 19070/28080 [37:41:48<17:51:58,  7.14s/it]
 68%|██████▊   | 19071/28080 [37:41:56<17:59:11,  7.19s/it]
                                                           
{'loss': 0.6327, 'learning_rate': 0.00012325602144854265, 'epoch': 8.15}

 68%|██████▊   | 19071/28080 [37:41:56<17:59:11,  7.19s/it]
 68%|██████▊   | 19072/28080 [37:42:03<17:55:50,  7.17s/it]
                                                           
{'loss': 0.5991, 'learning_rate': 0.00012323116705894652, 'epoch': 8.15}

 68%|██████▊   | 19072/28080 [37:42:03<17:55:50,  7.17s/it]
 68%|██████▊   | 19073/28080 [37:42:10<17:54:46,  7.16s/it]
                                                           
{'loss': 0.6219, 'learning_rate': 0.00012320631435587884, 'epoch': 8.15}

 68%|██████▊   | 19073/28080 [37:42:10<17:54:46,  7.16s/it]
 68%|██████▊   | 19074/28080 [37:42:17<17:53:07,  7.15s/it]
                                                           
{'loss': 0.5963, 'learning_rate': 0.00012318146333967046, 'epoch': 8.15}

 68%|██████▊   | 19074/28080 [37:42:17<17:53:07,  7.15s/it]
 68%|██████▊   | 19075/28080 [37:42:24<17:52:08,  7.14s/it]
                                                           
{'loss': 0.5896, 'learning_rate': 0.00012315661401065176, 'epoch': 8.15}

 68%|██████▊   | 19075/28080 [37:42:24<17:52:08,  7.14s/it]
 68%|██████▊   | 19076/28080 [37:42:31<17:49:27,  7.13s/it]
                                                           
{'loss': 0.6056, 'learning_rate': 0.00012313176636915367, 'epoch': 8.15}

 68%|██████▊   | 19076/28080 [37:42:31<17:49:27,  7.13s/it]
 68%|██████▊   | 19077/28080 [37:42:38<17:43:47,  7.09s/it]
                                                           
{'loss': 0.6135, 'learning_rate': 0.00012310692041550634, 'epoch': 8.15}

 68%|██████▊   | 19077/28080 [37:42:38<17:43:47,  7.09s/it]
 68%|██████▊   | 19078/28080 [37:42:45<17:44:22,  7.09s/it]
                                                           
{'loss': 0.6006, 'learning_rate': 0.00012308207615004062, 'epoch': 8.15}

 68%|██████▊   | 19078/28080 [37:42:45<17:44:22,  7.09s/it]
 68%|██████▊   | 19079/28080 [37:42:53<17:50:24,  7.14s/it]
                                                           
{'loss': 0.6166, 'learning_rate': 0.00012305723357308685, 'epoch': 8.15}

 68%|██████▊   | 19079/28080 [37:42:53<17:50:24,  7.14s/it]
 68%|██████▊   | 19080/28080 [37:43:00<17:47:52,  7.12s/it]
                                                           
{'loss': 0.5937, 'learning_rate': 0.0001230323926849757, 'epoch': 8.15}

 68%|██████▊   | 19080/28080 [37:43:00<17:47:52,  7.12s/it]
 68%|██████▊   | 19081/28080 [37:43:07<17:50:23,  7.14s/it]
                                                           
{'loss': 0.6113, 'learning_rate': 0.0001230075534860376, 'epoch': 8.15}

 68%|██████▊   | 19081/28080 [37:43:07<17:50:23,  7.14s/it]
 68%|██████▊   | 19082/28080 [37:43:14<17:51:35,  7.15s/it]
                                                           
{'loss': 0.6101, 'learning_rate': 0.000122982715976603, 'epoch': 8.15}

 68%|██████▊   | 19082/28080 [37:43:14<17:51:35,  7.15s/it]
 68%|██████▊   | 19083/28080 [37:43:21<17:49:57,  7.14s/it]
                                                           
{'loss': 0.5953, 'learning_rate': 0.00012295788015700225, 'epoch': 8.15}

 68%|██████▊   | 19083/28080 [37:43:21<17:49:57,  7.14s/it]
 68%|██████▊   | 19084/28080 [37:43:28<17:46:28,  7.11s/it]
                                                           
{'loss': 0.613, 'learning_rate': 0.00012293304602756588, 'epoch': 8.15}

 68%|██████▊   | 19084/28080 [37:43:28<17:46:28,  7.11s/it]
 68%|██████▊   | 19085/28080 [37:43:35<17:48:49,  7.13s/it]
                                                           
{'loss': 0.6186, 'learning_rate': 0.00012290821358862427, 'epoch': 8.15}

 68%|██████▊   | 19085/28080 [37:43:35<17:48:49,  7.13s/it]
 68%|██████▊   | 19086/28080 [37:43:42<17:48:43,  7.13s/it]
                                                           
{'loss': 0.6029, 'learning_rate': 0.00012288338284050779, 'epoch': 8.15}

 68%|██████▊   | 19086/28080 [37:43:42<17:48:43,  7.13s/it]
 68%|██████▊   | 19087/28080 [37:43:50<17:48:40,  7.13s/it]
                                                           
{'loss': 0.5935, 'learning_rate': 0.00012285855378354666, 'epoch': 8.15}

 68%|██████▊   | 19087/28080 [37:43:50<17:48:40,  7.13s/it]
 68%|██████▊   | 19088/28080 [37:43:57<17:50:36,  7.14s/it]
                                                           
{'loss': 0.6248, 'learning_rate': 0.0001228337264180714, 'epoch': 8.15}

 68%|██████▊   | 19088/28080 [37:43:57<17:50:36,  7.14s/it]
 68%|██████▊   | 19089/28080 [37:44:04<17:50:42,  7.15s/it]
                                                           
{'loss': 0.6043, 'learning_rate': 0.00012280890074441208, 'epoch': 8.15}

 68%|██████▊   | 19089/28080 [37:44:04<17:50:42,  7.15s/it]
 68%|██████▊   | 19090/28080 [37:44:11<17:48:56,  7.13s/it]
                                                           
{'loss': 0.6184, 'learning_rate': 0.0001227840767628994, 'epoch': 8.16}

 68%|██████▊   | 19090/28080 [37:44:11<17:48:56,  7.13s/it]
 68%|██████▊   | 19091/28080 [37:44:18<17:49:12,  7.14s/it]
                                                           
{'loss': 0.6185, 'learning_rate': 0.00012275925447386305, 'epoch': 8.16}

 68%|██████▊   | 19091/28080 [37:44:18<17:49:12,  7.14s/it]
 68%|██████▊   | 19092/28080 [37:44:25<17:49:58,  7.14s/it]
                                                           
{'loss': 0.5747, 'learning_rate': 0.00012273443387763368, 'epoch': 8.16}

 68%|██████▊   | 19092/28080 [37:44:25<17:49:58,  7.14s/it]
 68%|██████▊   | 19093/28080 [37:44:32<17:50:15,  7.15s/it]
                                                           
{'loss': 0.613, 'learning_rate': 0.00012270961497454138, 'epoch': 8.16}

 68%|██████▊   | 19093/28080 [37:44:32<17:50:15,  7.15s/it]
 68%|██████▊   | 19094/28080 [37:44:40<17:51:51,  7.16s/it]
                                                           
{'loss': 0.6018, 'learning_rate': 0.00012268479776491627, 'epoch': 8.16}

 68%|██████▊   | 19094/28080 [37:44:40<17:51:51,  7.16s/it]
 68%|██████▊   | 19095/28080 [37:44:47<17:51:11,  7.15s/it]
                                                           
{'loss': 0.6225, 'learning_rate': 0.00012265998224908877, 'epoch': 8.16}

 68%|██████▊   | 19095/28080 [37:44:47<17:51:11,  7.15s/it]
 68%|██████▊   | 19096/28080 [37:44:54<17:51:36,  7.16s/it]
                                                           
{'loss': 0.6198, 'learning_rate': 0.00012263516842738858, 'epoch': 8.16}

 68%|██████▊   | 19096/28080 [37:44:54<17:51:36,  7.16s/it]
 68%|██████▊   | 19097/28080 [37:45:01<17:52:35,  7.16s/it]
                                                           
{'loss': 0.6061, 'learning_rate': 0.00012261035630014623, 'epoch': 8.16}

 68%|██████▊   | 19097/28080 [37:45:01<17:52:35,  7.16s/it]
 68%|██████▊   | 19098/28080 [37:45:08<17:55:38,  7.19s/it]
                                                           
{'loss': 0.6178, 'learning_rate': 0.00012258554586769155, 'epoch': 8.16}

 68%|██████▊   | 19098/28080 [37:45:08<17:55:38,  7.19s/it]
 68%|██████▊   | 19099/28080 [37:45:15<17:52:24,  7.16s/it]
                                                           
{'loss': 0.5769, 'learning_rate': 0.00012256073713035485, 'epoch': 8.16}

 68%|██████▊   | 19099/28080 [37:45:15<17:52:24,  7.16s/it]
 68%|██████▊   | 19100/28080 [37:45:23<17:48:12,  7.14s/it]
                                                           
{'loss': 0.6068, 'learning_rate': 0.00012253593008846605, 'epoch': 8.16}

 68%|██████▊   | 19100/28080 [37:45:23<17:48:12,  7.14s/it]
 68%|██████▊   | 19101/28080 [37:45:30<17:49:23,  7.15s/it]
                                                           
{'loss': 0.6155, 'learning_rate': 0.00012251112474235523, 'epoch': 8.16}

 68%|██████▊   | 19101/28080 [37:45:30<17:49:23,  7.15s/it]
 68%|██████▊   | 19102/28080 [37:45:37<17:45:19,  7.12s/it]
                                                           
{'loss': 0.6227, 'learning_rate': 0.00012248632109235227, 'epoch': 8.16}

 68%|██████▊   | 19102/28080 [37:45:37<17:45:19,  7.12s/it]
 68%|██████▊   | 19103/28080 [37:45:44<17:43:49,  7.11s/it]
                                                           
{'loss': 0.6025, 'learning_rate': 0.00012246151913878733, 'epoch': 8.16}

 68%|██████▊   | 19103/28080 [37:45:44<17:43:49,  7.11s/it]
 68%|██████▊   | 19104/28080 [37:45:51<17:40:57,  7.09s/it]
                                                           
{'loss': 0.6258, 'learning_rate': 0.00012243671888199033, 'epoch': 8.16}

 68%|██████▊   | 19104/28080 [37:45:51<17:40:57,  7.09s/it]
 68%|██████▊   | 19105/28080 [37:45:58<17:40:26,  7.09s/it]
                                                           
{'loss': 0.6215, 'learning_rate': 0.00012241192032229117, 'epoch': 8.16}

 68%|██████▊   | 19105/28080 [37:45:58<17:40:26,  7.09s/it]
 68%|██████▊   | 19106/28080 [37:46:05<17:42:06,  7.10s/it]
                                                           
{'loss': 0.6031, 'learning_rate': 0.0001223871234600197, 'epoch': 8.16}

 68%|██████▊   | 19106/28080 [37:46:05<17:42:06,  7.10s/it]
 68%|██████▊   | 19107/28080 [37:46:12<17:45:26,  7.12s/it]
                                                           
{'loss': 0.617, 'learning_rate': 0.000122362328295506, 'epoch': 8.16}

 68%|██████▊   | 19107/28080 [37:46:12<17:45:26,  7.12s/it]
 68%|██████▊   | 19108/28080 [37:46:19<17:42:28,  7.11s/it]
                                                           
{'loss': 0.6084, 'learning_rate': 0.00012233753482907974, 'epoch': 8.16}

 68%|██████▊   | 19108/28080 [37:46:19<17:42:28,  7.11s/it]
 68%|██████▊   | 19109/28080 [37:46:26<17:40:32,  7.09s/it]
                                                           
{'loss': 0.6148, 'learning_rate': 0.00012231274306107108, 'epoch': 8.16}

 68%|██████▊   | 19109/28080 [37:46:26<17:40:32,  7.09s/it]
 68%|██████▊   | 19110/28080 [37:46:34<17:43:12,  7.11s/it]
                                                           
{'loss': 0.6047, 'learning_rate': 0.00012228795299180944, 'epoch': 8.16}

 68%|██████▊   | 19110/28080 [37:46:34<17:43:12,  7.11s/it]
 68%|██████▊   | 19111/28080 [37:46:41<17:43:41,  7.12s/it]
                                                           
{'loss': 0.623, 'learning_rate': 0.00012226316462162493, 'epoch': 8.16}

 68%|██████▊   | 19111/28080 [37:46:41<17:43:41,  7.12s/it]
 68%|██████▊   | 19112/28080 [37:46:48<17:41:55,  7.10s/it]
                                                           
{'loss': 0.6182, 'learning_rate': 0.00012223837795084715, 'epoch': 8.16}

 68%|██████▊   | 19112/28080 [37:46:48<17:41:55,  7.10s/it]
 68%|██████▊   | 19113/28080 [37:46:55<17:45:44,  7.13s/it]
                                                           
{'loss': 0.629, 'learning_rate': 0.00012221359297980602, 'epoch': 8.16}

 68%|██████▊   | 19113/28080 [37:46:55<17:45:44,  7.13s/it]
 68%|██████▊   | 19114/28080 [37:47:02<17:49:35,  7.16s/it]
                                                           
{'loss': 0.598, 'learning_rate': 0.00012218880970883122, 'epoch': 8.17}

 68%|██████▊   | 19114/28080 [37:47:02<17:49:35,  7.16s/it]
 68%|██████▊   | 19115/28080 [37:47:09<17:51:10,  7.17s/it]
                                                           
{'loss': 0.6021, 'learning_rate': 0.0001221640281382525, 'epoch': 8.17}

 68%|██████▊   | 19115/28080 [37:47:09<17:51:10,  7.17s/it]
 68%|██████▊   | 19116/28080 [37:47:16<17:48:57,  7.15s/it]
                                                           
{'loss': 0.6101, 'learning_rate': 0.00012213924826839933, 'epoch': 8.17}

 68%|██████▊   | 19116/28080 [37:47:16<17:48:57,  7.15s/it]
 68%|██████▊   | 19117/28080 [37:47:24<17:44:47,  7.13s/it]
                                                           
{'loss': 0.579, 'learning_rate': 0.0001221144700996017, 'epoch': 8.17}

 68%|██████▊   | 19117/28080 [37:47:24<17:44:47,  7.13s/it]
 68%|██████▊   | 19118/28080 [37:47:31<17:48:47,  7.16s/it]
                                                           
{'loss': 0.601, 'learning_rate': 0.00012208969363218907, 'epoch': 8.17}

 68%|██████▊   | 19118/28080 [37:47:31<17:48:47,  7.16s/it]
 68%|██████▊   | 19119/28080 [37:47:38<17:47:15,  7.15s/it]
                                                           
{'loss': 0.6332, 'learning_rate': 0.00012206491886649116, 'epoch': 8.17}

 68%|██████▊   | 19119/28080 [37:47:38<17:47:15,  7.15s/it]
 68%|██████▊   | 19120/28080 [37:47:45<17:46:07,  7.14s/it]
                                                           
{'loss': 0.6006, 'learning_rate': 0.00012204014580283749, 'epoch': 8.17}

 68%|██████▊   | 19120/28080 [37:47:45<17:46:07,  7.14s/it]
 68%|██████▊   | 19121/28080 [37:47:52<17:49:55,  7.17s/it]
                                                           
{'loss': 0.6131, 'learning_rate': 0.00012201537444155758, 'epoch': 8.17}

 68%|██████▊   | 19121/28080 [37:47:52<17:49:55,  7.17s/it]
 68%|██████▊   | 19122/28080 [37:47:59<17:49:03,  7.16s/it]
                                                           
{'loss': 0.6023, 'learning_rate': 0.00012199060478298118, 'epoch': 8.17}

 68%|██████▊   | 19122/28080 [37:47:59<17:49:03,  7.16s/it]
 68%|██████▊   | 19123/28080 [37:48:06<17:44:58,  7.13s/it]
                                                           
{'loss': 0.5892, 'learning_rate': 0.00012196583682743772, 'epoch': 8.17}

 68%|██████▊   | 19123/28080 [37:48:06<17:44:58,  7.13s/it]
 68%|██████▊   | 19124/28080 [37:48:14<17:46:27,  7.14s/it]
                                                           
{'loss': 0.6039, 'learning_rate': 0.00012194107057525672, 'epoch': 8.17}

 68%|██████▊   | 19124/28080 [37:48:14<17:46:27,  7.14s/it]
 68%|██████▊   | 19125/28080 [37:48:21<17:41:46,  7.11s/it]
                                                           
{'loss': 0.6133, 'learning_rate': 0.00012191630602676757, 'epoch': 8.17}

 68%|██████▊   | 19125/28080 [37:48:21<17:41:46,  7.11s/it]
 68%|██████▊   | 19126/28080 [37:48:28<17:40:04,  7.10s/it]
                                                           
{'loss': 0.6294, 'learning_rate': 0.00012189154318229992, 'epoch': 8.17}

 68%|██████▊   | 19126/28080 [37:48:28<17:40:04,  7.10s/it]
 68%|██████▊   | 19127/28080 [37:48:35<17:40:34,  7.11s/it]
                                                           
{'loss': 0.6018, 'learning_rate': 0.00012186678204218302, 'epoch': 8.17}

 68%|██████▊   | 19127/28080 [37:48:35<17:40:34,  7.11s/it]
 68%|██████▊   | 19128/28080 [37:48:42<17:37:31,  7.09s/it]
                                                           
{'loss': 0.6041, 'learning_rate': 0.00012184202260674652, 'epoch': 8.17}

 68%|██████▊   | 19128/28080 [37:48:42<17:37:31,  7.09s/it]
 68%|██████▊   | 19129/28080 [37:48:49<17:35:52,  7.08s/it]
                                                           
{'loss': 0.6168, 'learning_rate': 0.00012181726487631967, 'epoch': 8.17}

 68%|██████▊   | 19129/28080 [37:48:49<17:35:52,  7.08s/it]
 68%|██████▊   | 19130/28080 [37:48:56<17:42:48,  7.12s/it]
                                                           
{'loss': 0.6052, 'learning_rate': 0.00012179250885123189, 'epoch': 8.17}

 68%|██████▊   | 19130/28080 [37:48:56<17:42:48,  7.12s/it]
 68%|██████▊   | 19131/28080 [37:49:03<17:40:25,  7.11s/it]
                                                           
{'loss': 0.6076, 'learning_rate': 0.00012176775453181241, 'epoch': 8.17}

 68%|██████▊   | 19131/28080 [37:49:03<17:40:25,  7.11s/it]
 68%|██████▊   | 19132/28080 [37:49:10<17:37:56,  7.09s/it]
                                                           
{'loss': 0.5998, 'learning_rate': 0.00012174300191839074, 'epoch': 8.17}

 68%|██████▊   | 19132/28080 [37:49:10<17:37:56,  7.09s/it]
 68%|██████▊   | 19133/28080 [37:49:17<17:37:31,  7.09s/it]
                                                           
{'loss': 0.6002, 'learning_rate': 0.00012171825101129616, 'epoch': 8.17}

 68%|██████▊   | 19133/28080 [37:49:17<17:37:31,  7.09s/it]
 68%|██████▊   | 19134/28080 [37:49:25<17:40:31,  7.11s/it]
                                                           
{'loss': 0.6111, 'learning_rate': 0.0001216935018108579, 'epoch': 8.17}

 68%|██████▊   | 19134/28080 [37:49:25<17:40:31,  7.11s/it]
 68%|██████▊   | 19135/28080 [37:49:32<17:45:12,  7.15s/it]
                                                           
{'loss': 0.5943, 'learning_rate': 0.00012166875431740509, 'epoch': 8.17}

 68%|██████▊   | 19135/28080 [37:49:32<17:45:12,  7.15s/it]
 68%|██████▊   | 19136/28080 [37:49:39<17:44:16,  7.14s/it]
                                                           
{'loss': 0.6198, 'learning_rate': 0.00012164400853126725, 'epoch': 8.17}

 68%|██████▊   | 19136/28080 [37:49:39<17:44:16,  7.14s/it]
 68%|██████▊   | 19137/28080 [37:49:46<17:39:23,  7.11s/it]
                                                           
{'loss': 0.6008, 'learning_rate': 0.00012161926445277335, 'epoch': 8.18}

 68%|██████▊   | 19137/28080 [37:49:46<17:39:23,  7.11s/it]
 68%|██████▊   | 19138/28080 [37:49:53<17:36:39,  7.09s/it]
                                                           
{'loss': 0.62, 'learning_rate': 0.0001215945220822529, 'epoch': 8.18}

 68%|██████▊   | 19138/28080 [37:49:53<17:36:39,  7.09s/it]
 68%|██████▊   | 19139/28080 [37:50:00<17:36:23,  7.09s/it]
                                                           
{'loss': 0.6127, 'learning_rate': 0.00012156978142003466, 'epoch': 8.18}

 68%|██████▊   | 19139/28080 [37:50:00<17:36:23,  7.09s/it]
 68%|██████▊   | 19140/28080 [37:50:07<17:36:09,  7.09s/it]
                                                           
{'loss': 0.6027, 'learning_rate': 0.0001215450424664481, 'epoch': 8.18}

 68%|██████▊   | 19140/28080 [37:50:07<17:36:09,  7.09s/it]
 68%|██████▊   | 19141/28080 [37:50:14<17:40:52,  7.12s/it]
                                                           
{'loss': 0.5901, 'learning_rate': 0.00012152030522182212, 'epoch': 8.18}

 68%|██████▊   | 19141/28080 [37:50:14<17:40:52,  7.12s/it]
 68%|██████▊   | 19142/28080 [37:50:22<17:42:03,  7.13s/it]
                                                           
{'loss': 0.606, 'learning_rate': 0.000121495569686486, 'epoch': 8.18}

 68%|██████▊   | 19142/28080 [37:50:22<17:42:03,  7.13s/it]
 68%|██████▊   | 19143/28080 [37:50:29<17:45:18,  7.15s/it]
                                                           
{'loss': 0.6008, 'learning_rate': 0.0001214708358607689, 'epoch': 8.18}

 68%|██████▊   | 19143/28080 [37:50:29<17:45:18,  7.15s/it]
 68%|██████▊   | 19144/28080 [37:50:36<17:46:10,  7.16s/it]
                                                           
{'loss': 0.6269, 'learning_rate': 0.0001214461037449995, 'epoch': 8.18}

 68%|██████▊   | 19144/28080 [37:50:36<17:46:10,  7.16s/it]
 68%|██████▊   | 19145/28080 [37:50:43<17:47:06,  7.17s/it]
                                                           
{'loss': 0.6031, 'learning_rate': 0.0001214213733395072, 'epoch': 8.18}

 68%|██████▊   | 19145/28080 [37:50:43<17:47:06,  7.17s/it]
 68%|██████▊   | 19146/28080 [37:50:50<17:51:41,  7.20s/it]
                                                           
{'loss': 0.6026, 'learning_rate': 0.00012139664464462078, 'epoch': 8.18}

 68%|██████▊   | 19146/28080 [37:50:50<17:51:41,  7.20s/it]
 68%|██████▊   | 19147/28080 [37:50:57<17:48:40,  7.18s/it]
                                                           
{'loss': 0.5877, 'learning_rate': 0.0001213719176606694, 'epoch': 8.18}

 68%|██████▊   | 19147/28080 [37:50:57<17:48:40,  7.18s/it]
 68%|██████▊   | 19148/28080 [37:51:05<17:47:02,  7.17s/it]
                                                           
{'loss': 0.6124, 'learning_rate': 0.00012134719238798197, 'epoch': 8.18}

 68%|██████▊   | 19148/28080 [37:51:05<17:47:02,  7.17s/it]
 68%|██████▊   | 19149/28080 [37:51:12<17:46:51,  7.17s/it]
                                                           
{'loss': 0.6124, 'learning_rate': 0.00012132246882688742, 'epoch': 8.18}

 68%|██████▊   | 19149/28080 [37:51:12<17:46:51,  7.17s/it]
 68%|██████▊   | 19150/28080 [37:51:19<17:40:22,  7.12s/it]
                                                           
{'loss': 0.6014, 'learning_rate': 0.00012129774697771459, 'epoch': 8.18}

 68%|██████▊   | 19150/28080 [37:51:19<17:40:22,  7.12s/it]
 68%|██████▊   | 19151/28080 [37:51:26<17:39:55,  7.12s/it]
                                                           
{'loss': 0.6077, 'learning_rate': 0.00012127302684079253, 'epoch': 8.18}

 68%|██████▊   | 19151/28080 [37:51:26<17:39:55,  7.12s/it]
 68%|██████▊   | 19152/28080 [37:51:33<17:35:50,  7.10s/it]
                                                           
{'loss': 0.6277, 'learning_rate': 0.00012124830841645007, 'epoch': 8.18}

 68%|██████▊   | 19152/28080 [37:51:33<17:35:50,  7.10s/it]
 68%|██████▊   | 19153/28080 [37:51:40<17:38:09,  7.11s/it]
                                                           
{'loss': 0.6083, 'learning_rate': 0.00012122359170501604, 'epoch': 8.18}

 68%|██████▊   | 19153/28080 [37:51:40<17:38:09,  7.11s/it]
 68%|██████▊   | 19154/28080 [37:51:47<17:39:09,  7.12s/it]
                                                           
{'loss': 0.6087, 'learning_rate': 0.00012119887670681918, 'epoch': 8.18}

 68%|██████▊   | 19154/28080 [37:51:47<17:39:09,  7.12s/it]
 68%|██████▊   | 19155/28080 [37:51:54<17:38:46,  7.12s/it]
                                                           
{'loss': 0.6079, 'learning_rate': 0.00012117416342218845, 'epoch': 8.18}

 68%|██████▊   | 19155/28080 [37:51:54<17:38:46,  7.12s/it]
 68%|██████▊   | 19156/28080 [37:52:01<17:35:12,  7.09s/it]
                                                           
{'loss': 0.6119, 'learning_rate': 0.00012114945185145251, 'epoch': 8.18}

 68%|██████▊   | 19156/28080 [37:52:01<17:35:12,  7.09s/it]
 68%|██████▊   | 19157/28080 [37:52:09<17:39:28,  7.12s/it]
                                                           
{'loss': 0.6257, 'learning_rate': 0.00012112474199494036, 'epoch': 8.18}

 68%|██████▊   | 19157/28080 [37:52:09<17:39:28,  7.12s/it]
 68%|██████▊   | 19158/28080 [37:52:16<17:42:12,  7.14s/it]
                                                           
{'loss': 0.593, 'learning_rate': 0.00012110003385298041, 'epoch': 8.18}

 68%|██████▊   | 19158/28080 [37:52:16<17:42:12,  7.14s/it]
 68%|██████▊   | 19159/28080 [37:52:23<17:46:27,  7.17s/it]
                                                           
{'loss': 0.5825, 'learning_rate': 0.00012107532742590158, 'epoch': 8.18}

 68%|██████▊   | 19159/28080 [37:52:23<17:46:27,  7.17s/it]
 68%|██████▊   | 19160/28080 [37:52:30<17:44:55,  7.16s/it]
                                                           
{'loss': 0.6066, 'learning_rate': 0.00012105062271403244, 'epoch': 8.18}

 68%|██████▊   | 19160/28080 [37:52:30<17:44:55,  7.16s/it]
 68%|██████▊   | 19161/28080 [37:52:37<17:43:16,  7.15s/it]
                                                           
{'loss': 0.5906, 'learning_rate': 0.00012102591971770183, 'epoch': 8.19}

 68%|██████▊   | 19161/28080 [37:52:37<17:43:16,  7.15s/it]
 68%|██████▊   | 19162/28080 [37:52:44<17:42:19,  7.15s/it]
                                                           
{'loss': 0.6042, 'learning_rate': 0.0001210012184372383, 'epoch': 8.19}

 68%|██████▊   | 19162/28080 [37:52:44<17:42:19,  7.15s/it]
 68%|██████▊   | 19163/28080 [37:52:52<17:43:51,  7.16s/it]
                                                           
{'loss': 0.6155, 'learning_rate': 0.00012097651887297048, 'epoch': 8.19}

 68%|██████▊   | 19163/28080 [37:52:52<17:43:51,  7.16s/it]
 68%|██████▊   | 19164/28080 [37:52:59<17:42:07,  7.15s/it]
                                                           
{'loss': 0.5919, 'learning_rate': 0.00012095182102522689, 'epoch': 8.19}

 68%|██████▊   | 19164/28080 [37:52:59<17:42:07,  7.15s/it]
 68%|██████▊   | 19165/28080 [37:53:06<17:42:24,  7.15s/it]
                                                           
{'loss': 0.598, 'learning_rate': 0.00012092712489433628, 'epoch': 8.19}

 68%|██████▊   | 19165/28080 [37:53:06<17:42:24,  7.15s/it]
 68%|██████▊   | 19166/28080 [37:53:13<17:47:17,  7.18s/it]
                                                           
{'loss': 0.6024, 'learning_rate': 0.0001209024304806271, 'epoch': 8.19}

 68%|██████▊   | 19166/28080 [37:53:13<17:47:17,  7.18s/it]
 68%|██████▊   | 19167/28080 [37:53:20<17:45:43,  7.17s/it]
                                                           
{'loss': 0.6025, 'learning_rate': 0.0001208777377844279, 'epoch': 8.19}

 68%|██████▊   | 19167/28080 [37:53:20<17:45:43,  7.17s/it]
 68%|██████▊   | 19168/28080 [37:53:27<17:44:18,  7.17s/it]
                                                           
{'loss': 0.5971, 'learning_rate': 0.0001208530468060672, 'epoch': 8.19}

 68%|██████▊   | 19168/28080 [37:53:27<17:44:18,  7.17s/it]
 68%|██████▊   | 19169/28080 [37:53:35<17:45:23,  7.17s/it]
                                                           
{'loss': 0.6019, 'learning_rate': 0.00012082835754587338, 'epoch': 8.19}

 68%|██████▊   | 19169/28080 [37:53:35<17:45:23,  7.17s/it]
 68%|██████▊   | 19170/28080 [37:53:42<17:41:23,  7.15s/it]
                                                           
{'loss': 0.6039, 'learning_rate': 0.00012080367000417511, 'epoch': 8.19}

 68%|██████▊   | 19170/28080 [37:53:42<17:41:23,  7.15s/it]
 68%|██████▊   | 19171/28080 [37:53:49<17:41:54,  7.15s/it]
                                                           
{'loss': 0.6116, 'learning_rate': 0.00012077898418130071, 'epoch': 8.19}

 68%|██████▊   | 19171/28080 [37:53:49<17:41:54,  7.15s/it]
 68%|██████▊   | 19172/28080 [37:53:56<17:41:57,  7.15s/it]
                                                           
{'loss': 0.6153, 'learning_rate': 0.00012075430007757862, 'epoch': 8.19}

 68%|██████▊   | 19172/28080 [37:53:56<17:41:57,  7.15s/it]
 68%|██████▊   | 19173/28080 [37:54:03<17:36:21,  7.12s/it]
                                                           
{'loss': 0.5864, 'learning_rate': 0.00012072961769333713, 'epoch': 8.19}

 68%|██████▊   | 19173/28080 [37:54:03<17:36:21,  7.12s/it]
 68%|██████▊   | 19174/28080 [37:54:10<17:40:41,  7.15s/it]
                                                           
{'loss': 0.6134, 'learning_rate': 0.00012070493702890481, 'epoch': 8.19}

 68%|██████▊   | 19174/28080 [37:54:10<17:40:41,  7.15s/it]
 68%|██████▊   | 19175/28080 [37:54:18<17:46:52,  7.19s/it]
                                                           
{'loss': 0.5909, 'learning_rate': 0.00012068025808460984, 'epoch': 8.19}

 68%|██████▊   | 19175/28080 [37:54:18<17:46:52,  7.19s/it]
 68%|██████▊   | 19176/28080 [37:54:25<17:42:00,  7.16s/it]
                                                           
{'loss': 0.6234, 'learning_rate': 0.00012065558086078071, 'epoch': 8.19}

 68%|██████▊   | 19176/28080 [37:54:25<17:42:00,  7.16s/it]
 68%|██████▊   | 19177/28080 [37:54:32<17:39:56,  7.14s/it]
                                                           
{'loss': 0.6092, 'learning_rate': 0.00012063090535774566, 'epoch': 8.19}

 68%|██████▊   | 19177/28080 [37:54:32<17:39:56,  7.14s/it]
 68%|██████▊   | 19178/28080 [37:54:39<17:36:55,  7.12s/it]
                                                           
{'loss': 0.6064, 'learning_rate': 0.00012060623157583292, 'epoch': 8.19}

 68%|██████▊   | 19178/28080 [37:54:39<17:36:55,  7.12s/it]
 68%|██████▊   | 19179/28080 [37:54:46<17:34:31,  7.11s/it]
                                                           
{'loss': 0.6319, 'learning_rate': 0.0001205815595153707, 'epoch': 8.19}

 68%|██████▊   | 19179/28080 [37:54:46<17:34:31,  7.11s/it]
 68%|██████▊   | 19180/28080 [37:54:53<17:33:52,  7.10s/it]
                                                           
{'loss': 0.6105, 'learning_rate': 0.00012055688917668739, 'epoch': 8.19}

 68%|██████▊   | 19180/28080 [37:54:53<17:33:52,  7.10s/it]
 68%|██████▊   | 19181/28080 [37:55:00<17:34:43,  7.11s/it]
                                                           
{'loss': 0.5998, 'learning_rate': 0.00012053222056011115, 'epoch': 8.19}

 68%|██████▊   | 19181/28080 [37:55:00<17:34:43,  7.11s/it]
 68%|██████▊   | 19182/28080 [37:55:07<17:33:34,  7.10s/it]
                                                           
{'loss': 0.6038, 'learning_rate': 0.00012050755366597016, 'epoch': 8.19}

 68%|██████▊   | 19182/28080 [37:55:07<17:33:34,  7.10s/it]
 68%|██████▊   | 19183/28080 [37:55:14<17:35:12,  7.12s/it]
                                                           
{'loss': 0.5942, 'learning_rate': 0.00012048288849459246, 'epoch': 8.19}

 68%|██████▊   | 19183/28080 [37:55:14<17:35:12,  7.12s/it]
 68%|██████▊   | 19184/28080 [37:55:22<17:37:46,  7.13s/it]
                                                           
{'loss': 0.5975, 'learning_rate': 0.00012045822504630644, 'epoch': 8.2}

 68%|██████▊   | 19184/28080 [37:55:22<17:37:46,  7.13s/it]
 68%|██████▊   | 19185/28080 [37:55:29<17:36:14,  7.12s/it]
                                                           
{'loss': 0.611, 'learning_rate': 0.00012043356332144006, 'epoch': 8.2}

 68%|██████▊   | 19185/28080 [37:55:29<17:36:14,  7.12s/it]
 68%|██████▊   | 19186/28080 [37:55:36<17:39:11,  7.15s/it]
                                                           
{'loss': 0.5967, 'learning_rate': 0.00012040890332032147, 'epoch': 8.2}

 68%|██████▊   | 19186/28080 [37:55:36<17:39:11,  7.15s/it]
 68%|██████▊   | 19187/28080 [37:55:43<17:35:30,  7.12s/it]
                                                           
{'loss': 0.5937, 'learning_rate': 0.00012038424504327863, 'epoch': 8.2}

 68%|██████▊   | 19187/28080 [37:55:43<17:35:30,  7.12s/it]
 68%|██████▊   | 19188/28080 [37:55:50<17:37:21,  7.13s/it]
                                                           
{'loss': 0.6354, 'learning_rate': 0.0001203595884906398, 'epoch': 8.2}

 68%|██████▊   | 19188/28080 [37:55:50<17:37:21,  7.13s/it]
 68%|██████▊   | 19189/28080 [37:55:57<17:40:16,  7.16s/it]
                                                           
{'loss': 0.6069, 'learning_rate': 0.00012033493366273282, 'epoch': 8.2}

 68%|██████▊   | 19189/28080 [37:55:57<17:40:16,  7.16s/it]
 68%|██████▊   | 19190/28080 [37:56:04<17:37:44,  7.14s/it]
                                                           
{'loss': 0.6074, 'learning_rate': 0.00012031028055988585, 'epoch': 8.2}

 68%|██████▊   | 19190/28080 [37:56:04<17:37:44,  7.14s/it]
 68%|██████▊   | 19191/28080 [37:56:12<17:38:52,  7.15s/it]
                                                           
{'loss': 0.5869, 'learning_rate': 0.0001202856291824268, 'epoch': 8.2}

 68%|██████▊   | 19191/28080 [37:56:12<17:38:52,  7.15s/it]
 68%|██████▊   | 19192/28080 [37:56:19<17:36:19,  7.13s/it]
                                                           
{'loss': 0.6008, 'learning_rate': 0.00012026097953068366, 'epoch': 8.2}

 68%|██████▊   | 19192/28080 [37:56:19<17:36:19,  7.13s/it]
 68%|██████▊   | 19193/28080 [37:56:26<17:36:32,  7.13s/it]
                                                           
{'loss': 0.6117, 'learning_rate': 0.00012023633160498432, 'epoch': 8.2}

 68%|██████▊   | 19193/28080 [37:56:26<17:36:32,  7.13s/it]
 68%|██████▊   | 19194/28080 [37:56:33<17:36:42,  7.14s/it]
                                                           
{'loss': 0.6136, 'learning_rate': 0.00012021168540565663, 'epoch': 8.2}

 68%|██████▊   | 19194/28080 [37:56:33<17:36:42,  7.14s/it]
 68%|██████▊   | 19195/28080 [37:56:40<17:34:56,  7.12s/it]
                                                           
{'loss': 0.6219, 'learning_rate': 0.00012018704093302865, 'epoch': 8.2}

 68%|██████▊   | 19195/28080 [37:56:40<17:34:56,  7.12s/it]
 68%|██████▊   | 19196/28080 [37:56:47<17:30:20,  7.09s/it]
                                                           
{'loss': 0.6289, 'learning_rate': 0.00012016239818742819, 'epoch': 8.2}

 68%|██████▊   | 19196/28080 [37:56:47<17:30:20,  7.09s/it]
 68%|██████▊   | 19197/28080 [37:56:54<17:32:38,  7.11s/it]
                                                           
{'loss': 0.6007, 'learning_rate': 0.00012013775716918307, 'epoch': 8.2}

 68%|██████▊   | 19197/28080 [37:56:54<17:32:38,  7.11s/it]
 68%|██████▊   | 19198/28080 [37:57:01<17:34:54,  7.13s/it]
                                                           
{'loss': 0.5957, 'learning_rate': 0.00012011311787862103, 'epoch': 8.2}

 68%|██████▊   | 19198/28080 [37:57:01<17:34:54,  7.13s/it]
 68%|██████▊   | 19199/28080 [37:57:08<17:31:16,  7.10s/it]
                                                           
{'loss': 0.5985, 'learning_rate': 0.00012008848031607006, 'epoch': 8.2}

 68%|██████▊   | 19199/28080 [37:57:08<17:31:16,  7.10s/it]
 68%|██████▊   | 19200/28080 [37:57:15<17:29:41,  7.09s/it]
                                                           
{'loss': 0.6096, 'learning_rate': 0.00012006384448185781, 'epoch': 8.2}

 68%|██████▊   | 19200/28080 [37:57:15<17:29:41,  7.09s/it]
 68%|██████▊   | 19201/28080 [37:57:23<17:31:10,  7.10s/it]
                                                           
{'loss': 0.6051, 'learning_rate': 0.00012003921037631211, 'epoch': 8.2}

 68%|██████▊   | 19201/28080 [37:57:23<17:31:10,  7.10s/it]
 68%|██████▊   | 19202/28080 [37:57:30<17:41:29,  7.17s/it]
                                                           
{'loss': 0.612, 'learning_rate': 0.00012001457799976051, 'epoch': 8.2}

 68%|██████▊   | 19202/28080 [37:57:30<17:41:29,  7.17s/it]
 68%|██████▊   | 19203/28080 [37:57:37<17:38:40,  7.16s/it]
                                                           
{'loss': 0.6103, 'learning_rate': 0.00011998994735253094, 'epoch': 8.2}

 68%|██████▊   | 19203/28080 [37:57:37<17:38:40,  7.16s/it]
 68%|██████▊   | 19204/28080 [37:57:44<17:38:19,  7.15s/it]
                                                           
{'loss': 0.6002, 'learning_rate': 0.00011996531843495093, 'epoch': 8.2}

 68%|██████▊   | 19204/28080 [37:57:44<17:38:19,  7.15s/it]
 68%|██████▊   | 19205/28080 [37:57:51<17:42:54,  7.19s/it]
                                                           
{'loss': 0.6114, 'learning_rate': 0.00011994069124734838, 'epoch': 8.2}

 68%|██████▊   | 19205/28080 [37:57:51<17:42:54,  7.19s/it]
 68%|██████▊   | 19206/28080 [37:57:59<17:40:08,  7.17s/it]
                                                           
{'loss': 0.6137, 'learning_rate': 0.00011991606579005057, 'epoch': 8.2}

 68%|██████▊   | 19206/28080 [37:57:59<17:40:08,  7.17s/it]
 68%|██████▊   | 19207/28080 [37:58:06<17:37:52,  7.15s/it]
                                                           
{'loss': 0.618, 'learning_rate': 0.0001198914420633854, 'epoch': 8.21}

 68%|██████▊   | 19207/28080 [37:58:06<17:37:52,  7.15s/it]
 68%|██████▊   | 19208/28080 [37:58:13<17:32:35,  7.12s/it]
                                                           
{'loss': 0.6028, 'learning_rate': 0.00011986682006768026, 'epoch': 8.21}

 68%|██████▊   | 19208/28080 [37:58:13<17:32:35,  7.12s/it]
 68%|██████▊   | 19209/28080 [37:58:20<17:30:52,  7.11s/it]
                                                           
{'loss': 0.6053, 'learning_rate': 0.00011984219980326295, 'epoch': 8.21}

 68%|██████▊   | 19209/28080 [37:58:20<17:30:52,  7.11s/it]
 68%|██████▊   | 19210/28080 [37:58:27<17:26:53,  7.08s/it]
                                                           
{'loss': 0.6268, 'learning_rate': 0.00011981758127046089, 'epoch': 8.21}

 68%|██████▊   | 19210/28080 [37:58:27<17:26:53,  7.08s/it]
 68%|██████▊   | 19211/28080 [37:58:34<17:22:52,  7.06s/it]
                                                           
{'loss': 0.6326, 'learning_rate': 0.00011979296446960159, 'epoch': 8.21}

 68%|██████▊   | 19211/28080 [37:58:34<17:22:52,  7.06s/it]
 68%|██████▊   | 19212/28080 [37:58:41<17:29:40,  7.10s/it]
                                                           
{'loss': 0.6168, 'learning_rate': 0.0001197683494010125, 'epoch': 8.21}

 68%|██████▊   | 19212/28080 [37:58:41<17:29:40,  7.10s/it]
 68%|██████▊   | 19213/28080 [37:58:48<17:27:30,  7.09s/it]
                                                           
{'loss': 0.6051, 'learning_rate': 0.00011974373606502123, 'epoch': 8.21}

 68%|██████▊   | 19213/28080 [37:58:48<17:27:30,  7.09s/it]
 68%|██████▊   | 19214/28080 [37:58:55<17:23:55,  7.06s/it]
                                                           
{'loss': 0.6134, 'learning_rate': 0.00011971912446195521, 'epoch': 8.21}

 68%|██████▊   | 19214/28080 [37:58:55<17:23:55,  7.06s/it]
 68%|██████▊   | 19215/28080 [37:59:02<17:24:22,  7.07s/it]
                                                           
{'loss': 0.588, 'learning_rate': 0.00011969451459214182, 'epoch': 8.21}

 68%|██████▊   | 19215/28080 [37:59:02<17:24:22,  7.07s/it]
 68%|██████▊   | 19216/28080 [37:59:09<17:28:57,  7.10s/it]
                                                           
{'loss': 0.608, 'learning_rate': 0.00011966990645590839, 'epoch': 8.21}

 68%|██████▊   | 19216/28080 [37:59:09<17:28:57,  7.10s/it]
 68%|██████▊   | 19217/28080 [37:59:17<17:31:42,  7.12s/it]
                                                           
{'loss': 0.6075, 'learning_rate': 0.00011964530005358248, 'epoch': 8.21}

 68%|██████▊   | 19217/28080 [37:59:17<17:31:42,  7.12s/it]
 68%|██████▊   | 19218/28080 [37:59:24<17:28:10,  7.10s/it]
                                                           
{'loss': 0.6164, 'learning_rate': 0.00011962069538549139, 'epoch': 8.21}

 68%|██████▊   | 19218/28080 [37:59:24<17:28:10,  7.10s/it]
 68%|██████▊   | 19219/28080 [37:59:31<17:25:26,  7.08s/it]
                                                           
{'loss': 0.6158, 'learning_rate': 0.00011959609245196245, 'epoch': 8.21}

 68%|██████▊   | 19219/28080 [37:59:31<17:25:26,  7.08s/it]
 68%|██████▊   | 19220/28080 [37:59:38<17:20:12,  7.04s/it]
                                                           
{'loss': 0.6016, 'learning_rate': 0.00011957149125332298, 'epoch': 8.21}

 68%|██████▊   | 19220/28080 [37:59:38<17:20:12,  7.04s/it]
 68%|██████▊   | 19221/28080 [37:59:45<17:21:44,  7.06s/it]
                                                           
{'loss': 0.6152, 'learning_rate': 0.00011954689178990014, 'epoch': 8.21}

 68%|██████▊   | 19221/28080 [37:59:45<17:21:44,  7.06s/it]
 68%|██████▊   | 19222/28080 [37:59:52<17:27:12,  7.09s/it]
                                                           
{'loss': 0.6091, 'learning_rate': 0.00011952229406202142, 'epoch': 8.21}

 68%|██████▊   | 19222/28080 [37:59:52<17:27:12,  7.09s/it]
 68%|██████▊   | 19223/28080 [37:59:59<17:22:26,  7.06s/it]
                                                           
{'loss': 0.6039, 'learning_rate': 0.0001194976980700139, 'epoch': 8.21}

 68%|██████▊   | 19223/28080 [37:59:59<17:22:26,  7.06s/it]
 68%|██████▊   | 19224/28080 [38:00:06<17:24:00,  7.07s/it]
                                                           
{'loss': 0.597, 'learning_rate': 0.00011947310381420495, 'epoch': 8.21}

 68%|██████▊   | 19224/28080 [38:00:06<17:24:00,  7.07s/it]
 68%|██████▊   | 19225/28080 [38:00:13<17:25:03,  7.08s/it]
                                                           
{'loss': 0.6174, 'learning_rate': 0.00011944851129492171, 'epoch': 8.21}

 68%|██████▊   | 19225/28080 [38:00:13<17:25:03,  7.08s/it]
 68%|██████▊   | 19226/28080 [38:00:20<17:21:44,  7.06s/it]
                                                           
{'loss': 0.6312, 'learning_rate': 0.00011942392051249132, 'epoch': 8.21}

 68%|██████▊   | 19226/28080 [38:00:20<17:21:44,  7.06s/it]
 68%|██████▊   | 19227/28080 [38:00:27<17:27:02,  7.10s/it]
                                                           
{'loss': 0.5858, 'learning_rate': 0.00011939933146724089, 'epoch': 8.21}

 68%|██████▊   | 19227/28080 [38:00:27<17:27:02,  7.10s/it]
 68%|██████▊   | 19228/28080 [38:00:34<17:28:02,  7.10s/it]
                                                           
{'loss': 0.6171, 'learning_rate': 0.0001193747441594977, 'epoch': 8.21}

 68%|██████▊   | 19228/28080 [38:00:34<17:28:02,  7.10s/it]
 68%|██████▊   | 19229/28080 [38:00:41<17:25:33,  7.09s/it]
                                                           
{'loss': 0.6073, 'learning_rate': 0.00011935015858958878, 'epoch': 8.21}

 68%|██████▊   | 19229/28080 [38:00:41<17:25:33,  7.09s/it]
 68%|██████▊   | 19230/28080 [38:00:48<17:24:23,  7.08s/it]
                                                           
{'loss': 0.6188, 'learning_rate': 0.00011932557475784123, 'epoch': 8.21}

 68%|██████▊   | 19230/28080 [38:00:48<17:24:23,  7.08s/it]
 68%|██████▊   | 19231/28080 [38:00:56<17:29:33,  7.12s/it]
                                                           
{'loss': 0.6043, 'learning_rate': 0.000119300992664582, 'epoch': 8.22}

 68%|██████▊   | 19231/28080 [38:00:56<17:29:33,  7.12s/it]
 68%|██████▊   | 19232/28080 [38:01:03<17:36:49,  7.17s/it]
                                                           
{'loss': 0.6143, 'learning_rate': 0.00011927641231013833, 'epoch': 8.22}

 68%|██████▊   | 19232/28080 [38:01:03<17:36:49,  7.17s/it]
 68%|██████▊   | 19233/28080 [38:01:10<17:36:27,  7.16s/it]
                                                           
{'loss': 0.6103, 'learning_rate': 0.00011925183369483714, 'epoch': 8.22}

 68%|██████▊   | 19233/28080 [38:01:10<17:36:27,  7.16s/it]
 68%|██████▊   | 19234/28080 [38:01:17<17:37:38,  7.17s/it]
                                                           
{'loss': 0.6003, 'learning_rate': 0.0001192272568190054, 'epoch': 8.22}

 68%|██████▊   | 19234/28080 [38:01:17<17:37:38,  7.17s/it]
 69%|██████▊   | 19235/28080 [38:01:24<17:31:32,  7.13s/it]
                                                           
{'loss': 0.6263, 'learning_rate': 0.00011920268168296999, 'epoch': 8.22}

 69%|██████▊   | 19235/28080 [38:01:24<17:31:32,  7.13s/it]
 69%|██████▊   | 19236/28080 [38:01:32<17:32:39,  7.14s/it]
                                                           
{'loss': 0.6184, 'learning_rate': 0.00011917810828705808, 'epoch': 8.22}

 69%|██████▊   | 19236/28080 [38:01:32<17:32:39,  7.14s/it]
 69%|██████▊   | 19237/28080 [38:01:39<17:35:30,  7.16s/it]
                                                           
{'loss': 0.607, 'learning_rate': 0.00011915353663159637, 'epoch': 8.22}

 69%|██████▊   | 19237/28080 [38:01:39<17:35:30,  7.16s/it]
 69%|██████▊   | 19238/28080 [38:01:46<17:33:51,  7.15s/it]
                                                           
{'loss': 0.6031, 'learning_rate': 0.00011912896671691198, 'epoch': 8.22}

 69%|██████▊   | 19238/28080 [38:01:46<17:33:51,  7.15s/it]
 69%|██████▊   | 19239/28080 [38:01:53<17:33:35,  7.15s/it]
                                                           
{'loss': 0.656, 'learning_rate': 0.00011910439854333165, 'epoch': 8.22}

 69%|██████▊   | 19239/28080 [38:01:53<17:33:35,  7.15s/it]
 69%|██████▊   | 19240/28080 [38:02:00<17:29:17,  7.12s/it]
                                                           
{'loss': 0.6099, 'learning_rate': 0.00011907983211118229, 'epoch': 8.22}

 69%|██████▊   | 19240/28080 [38:02:00<17:29:17,  7.12s/it]
 69%|██████▊   | 19241/28080 [38:02:07<17:26:53,  7.11s/it]
                                                           
{'loss': 0.5993, 'learning_rate': 0.0001190552674207906, 'epoch': 8.22}

 69%|██████▊   | 19241/28080 [38:02:07<17:26:53,  7.11s/it]
 69%|██████▊   | 19242/28080 [38:02:14<17:28:19,  7.12s/it]
                                                           
{'loss': 0.6362, 'learning_rate': 0.00011903070447248357, 'epoch': 8.22}

 69%|██████▊   | 19242/28080 [38:02:14<17:28:19,  7.12s/it]
 69%|██████▊   | 19243/28080 [38:02:21<17:30:21,  7.13s/it]
                                                           
{'loss': 0.5997, 'learning_rate': 0.0001190061432665879, 'epoch': 8.22}

 69%|██████▊   | 19243/28080 [38:02:21<17:30:21,  7.13s/it]
 69%|██████▊   | 19244/28080 [38:02:29<17:31:40,  7.14s/it]
                                                           
{'loss': 0.6376, 'learning_rate': 0.00011898158380343035, 'epoch': 8.22}

 69%|██████▊   | 19244/28080 [38:02:29<17:31:40,  7.14s/it]
 69%|██████▊   | 19245/28080 [38:02:36<17:31:51,  7.14s/it]
                                                           
{'loss': 0.621, 'learning_rate': 0.0001189570260833377, 'epoch': 8.22}

 69%|██████▊   | 19245/28080 [38:02:36<17:31:51,  7.14s/it]
 69%|██████▊   | 19246/28080 [38:02:43<17:30:03,  7.13s/it]
                                                           
{'loss': 0.6175, 'learning_rate': 0.00011893247010663649, 'epoch': 8.22}

 69%|██████▊   | 19246/28080 [38:02:43<17:30:03,  7.13s/it]
 69%|██████▊   | 19247/28080 [38:02:50<17:28:55,  7.13s/it]
                                                           
{'loss': 0.6018, 'learning_rate': 0.00011890791587365368, 'epoch': 8.22}

 69%|██████▊   | 19247/28080 [38:02:50<17:28:55,  7.13s/it]
 69%|██████▊   | 19248/28080 [38:02:57<17:35:12,  7.17s/it]
                                                           
{'loss': 0.5881, 'learning_rate': 0.00011888336338471581, 'epoch': 8.22}

 69%|██████▊   | 19248/28080 [38:02:57<17:35:12,  7.17s/it]
 69%|██████▊   | 19249/28080 [38:03:04<17:34:33,  7.16s/it]
                                                           
{'loss': 0.5946, 'learning_rate': 0.0001188588126401495, 'epoch': 8.22}

 69%|██████▊   | 19249/28080 [38:03:04<17:34:33,  7.16s/it]
 69%|██████▊   | 19250/28080 [38:03:11<17:28:54,  7.13s/it]
                                                           
{'loss': 0.6278, 'learning_rate': 0.0001188342636402813, 'epoch': 8.22}

 69%|██████▊   | 19250/28080 [38:03:11<17:28:54,  7.13s/it]
 69%|██████▊   | 19251/28080 [38:03:19<17:31:50,  7.15s/it]
                                                           
{'loss': 0.5945, 'learning_rate': 0.00011880971638543803, 'epoch': 8.22}

 69%|██████▊   | 19251/28080 [38:03:19<17:31:50,  7.15s/it]
 69%|██████▊   | 19252/28080 [38:03:26<17:32:53,  7.16s/it]
                                                           
{'loss': 0.5904, 'learning_rate': 0.00011878517087594601, 'epoch': 8.22}

 69%|██████▊   | 19252/28080 [38:03:26<17:32:53,  7.16s/it]
 69%|██████▊   | 19253/28080 [38:03:33<17:38:32,  7.20s/it]
                                                           
{'loss': 0.6014, 'learning_rate': 0.00011876062711213214, 'epoch': 8.22}

 69%|██████▊   | 19253/28080 [38:03:33<17:38:32,  7.20s/it]
 69%|██████▊   | 19254/28080 [38:03:40<17:36:39,  7.18s/it]
                                                           
{'loss': 0.6218, 'learning_rate': 0.00011873608509432255, 'epoch': 8.23}

 69%|██████▊   | 19254/28080 [38:03:40<17:36:39,  7.18s/it]
 69%|██████▊   | 19255/28080 [38:03:47<17:33:57,  7.17s/it]
                                                           
{'loss': 0.6056, 'learning_rate': 0.00011871154482284402, 'epoch': 8.23}

 69%|██████▊   | 19255/28080 [38:03:47<17:33:57,  7.17s/it]
 69%|██████▊   | 19256/28080 [38:03:54<17:30:53,  7.15s/it]
                                                           
{'loss': 0.6062, 'learning_rate': 0.00011868700629802284, 'epoch': 8.23}

 69%|██████▊   | 19256/28080 [38:03:54<17:30:53,  7.15s/it]
 69%|██████▊   | 19257/28080 [38:04:02<17:27:07,  7.12s/it]
                                                           
{'loss': 0.5852, 'learning_rate': 0.00011866246952018567, 'epoch': 8.23}

 69%|██████▊   | 19257/28080 [38:04:02<17:27:07,  7.12s/it]
 69%|██████▊   | 19258/28080 [38:04:09<17:27:39,  7.13s/it]
                                                           
{'loss': 0.6141, 'learning_rate': 0.00011863793448965884, 'epoch': 8.23}

 69%|██████▊   | 19258/28080 [38:04:09<17:27:39,  7.13s/it]
 69%|██████▊   | 19259/28080 [38:04:16<17:30:25,  7.14s/it]
                                                           
{'loss': 0.6019, 'learning_rate': 0.00011861340120676877, 'epoch': 8.23}

 69%|██████▊   | 19259/28080 [38:04:16<17:30:25,  7.14s/it]
 69%|██████▊   | 19260/28080 [38:04:23<17:31:39,  7.15s/it]
                                                           
{'loss': 0.5988, 'learning_rate': 0.0001185888696718418, 'epoch': 8.23}

 69%|██████▊   | 19260/28080 [38:04:23<17:31:39,  7.15s/it]
 69%|██████▊   | 19261/28080 [38:04:30<17:30:03,  7.14s/it]
                                                           
{'loss': 0.605, 'learning_rate': 0.0001185643398852044, 'epoch': 8.23}

 69%|██████▊   | 19261/28080 [38:04:30<17:30:03,  7.14s/it]
 69%|██████▊   | 19262/28080 [38:04:37<17:31:16,  7.15s/it]
                                                           
{'loss': 0.6032, 'learning_rate': 0.00011853981184718288, 'epoch': 8.23}

 69%|██████▊   | 19262/28080 [38:04:37<17:31:16,  7.15s/it]
 69%|██████▊   | 19263/28080 [38:04:44<17:31:58,  7.16s/it]
                                                           
{'loss': 0.6035, 'learning_rate': 0.00011851528555810353, 'epoch': 8.23}

 69%|██████▊   | 19263/28080 [38:04:44<17:31:58,  7.16s/it]
 69%|██████▊   | 19264/28080 [38:04:51<17:24:44,  7.11s/it]
                                                           
{'loss': 0.6005, 'learning_rate': 0.0001184907610182926, 'epoch': 8.23}

 69%|██████▊   | 19264/28080 [38:04:51<17:24:44,  7.11s/it]
 69%|██████▊   | 19265/28080 [38:04:59<17:26:28,  7.12s/it]
                                                           
{'loss': 0.5862, 'learning_rate': 0.00011846623822807648, 'epoch': 8.23}

 69%|██████▊   | 19265/28080 [38:04:59<17:26:28,  7.12s/it]
 69%|██████▊   | 19266/28080 [38:05:06<17:28:40,  7.14s/it]
                                                           
{'loss': 0.5937, 'learning_rate': 0.00011844171718778129, 'epoch': 8.23}

 69%|██████▊   | 19266/28080 [38:05:06<17:28:40,  7.14s/it]
 69%|██████▊   | 19267/28080 [38:05:13<17:23:18,  7.10s/it]
                                                           
{'loss': 0.6116, 'learning_rate': 0.00011841719789773353, 'epoch': 8.23}

 69%|██████▊   | 19267/28080 [38:05:13<17:23:18,  7.10s/it]
 69%|██████▊   | 19268/28080 [38:05:20<17:22:15,  7.10s/it]
                                                           
{'loss': 0.6165, 'learning_rate': 0.0001183926803582591, 'epoch': 8.23}

 69%|██████▊   | 19268/28080 [38:05:20<17:22:15,  7.10s/it]
 69%|██████▊   | 19269/28080 [38:05:27<17:24:53,  7.12s/it]
                                                           
{'loss': 0.6016, 'learning_rate': 0.00011836816456968419, 'epoch': 8.23}

 69%|██████▊   | 19269/28080 [38:05:27<17:24:53,  7.12s/it]
 69%|██████▊   | 19270/28080 [38:05:34<17:27:45,  7.14s/it]
                                                           
{'loss': 0.6143, 'learning_rate': 0.00011834365053233514, 'epoch': 8.23}

 69%|██████▊   | 19270/28080 [38:05:34<17:27:45,  7.14s/it]
 69%|██████▊   | 19271/28080 [38:05:41<17:21:45,  7.10s/it]
                                                           
{'loss': 0.5919, 'learning_rate': 0.00011831913824653792, 'epoch': 8.23}

 69%|██████▊   | 19271/28080 [38:05:41<17:21:45,  7.10s/it]
 69%|██████▊   | 19272/28080 [38:05:48<17:22:49,  7.10s/it]
                                                           
{'loss': 0.6095, 'learning_rate': 0.00011829462771261889, 'epoch': 8.23}

 69%|██████▊   | 19272/28080 [38:05:48<17:22:49,  7.10s/it]
 69%|██████▊   | 19273/28080 [38:05:55<17:19:06,  7.08s/it]
                                                           
{'loss': 0.5837, 'learning_rate': 0.00011827011893090379, 'epoch': 8.23}

 69%|██████▊   | 19273/28080 [38:05:55<17:19:06,  7.08s/it]
 69%|██████▊   | 19274/28080 [38:06:03<17:21:41,  7.10s/it]
                                                           
{'loss': 0.59, 'learning_rate': 0.00011824561190171895, 'epoch': 8.23}

 69%|██████▊   | 19274/28080 [38:06:03<17:21:41,  7.10s/it]
 69%|██████▊   | 19275/28080 [38:06:10<17:26:40,  7.13s/it]
                                                           
{'loss': 0.616, 'learning_rate': 0.0001182211066253902, 'epoch': 8.23}

 69%|██████▊   | 19275/28080 [38:06:10<17:26:40,  7.13s/it]
 69%|██████▊   | 19276/28080 [38:06:17<17:22:13,  7.10s/it]
                                                           
{'loss': 0.6107, 'learning_rate': 0.00011819660310224381, 'epoch': 8.23}

 69%|██████▊   | 19276/28080 [38:06:17<17:22:13,  7.10s/it]
 69%|██████▊   | 19277/28080 [38:06:24<17:22:10,  7.10s/it]
                                                           
{'loss': 0.6005, 'learning_rate': 0.00011817210133260564, 'epoch': 8.23}

 69%|██████▊   | 19277/28080 [38:06:24<17:22:10,  7.10s/it]
 69%|██████▊   | 19278/28080 [38:06:31<17:19:04,  7.08s/it]
                                                           
{'loss': 0.6063, 'learning_rate': 0.00011814760131680163, 'epoch': 8.24}

 69%|██████▊   | 19278/28080 [38:06:31<17:19:04,  7.08s/it]
 69%|██████▊   | 19279/28080 [38:06:38<17:22:18,  7.11s/it]
                                                           
{'loss': 0.6102, 'learning_rate': 0.00011812310305515769, 'epoch': 8.24}

 69%|██████▊   | 19279/28080 [38:06:38<17:22:18,  7.11s/it]
 69%|██████▊   | 19280/28080 [38:06:45<17:27:08,  7.14s/it]
                                                           
{'loss': 0.6242, 'learning_rate': 0.00011809860654799992, 'epoch': 8.24}

 69%|██████▊   | 19280/28080 [38:06:45<17:27:08,  7.14s/it]
 69%|██████▊   | 19281/28080 [38:06:52<17:25:03,  7.13s/it]
                                                           
{'loss': 0.6061, 'learning_rate': 0.00011807411179565408, 'epoch': 8.24}

 69%|██████▊   | 19281/28080 [38:06:52<17:25:03,  7.13s/it]
 69%|██████▊   | 19282/28080 [38:06:59<17:21:05,  7.10s/it]
                                                           
{'loss': 0.5853, 'learning_rate': 0.00011804961879844611, 'epoch': 8.24}

 69%|██████▊   | 19282/28080 [38:06:59<17:21:05,  7.10s/it]
 69%|██████▊   | 19283/28080 [38:07:07<17:20:06,  7.09s/it]
                                                           
{'loss': 0.6254, 'learning_rate': 0.00011802512755670173, 'epoch': 8.24}

 69%|██████▊   | 19283/28080 [38:07:07<17:20:06,  7.09s/it]
 69%|██████▊   | 19284/28080 [38:07:14<17:24:00,  7.12s/it]
                                                           
{'loss': 0.5887, 'learning_rate': 0.00011800063807074699, 'epoch': 8.24}

 69%|██████▊   | 19284/28080 [38:07:14<17:24:00,  7.12s/it]
 69%|██████▊   | 19285/28080 [38:07:21<17:23:23,  7.12s/it]
                                                           
{'loss': 0.5992, 'learning_rate': 0.00011797615034090747, 'epoch': 8.24}

 69%|██████▊   | 19285/28080 [38:07:21<17:23:23,  7.12s/it]
 69%|██████▊   | 19286/28080 [38:07:28<17:24:04,  7.12s/it]
                                                           
{'loss': 0.6154, 'learning_rate': 0.00011795166436750918, 'epoch': 8.24}

 69%|██████▊   | 19286/28080 [38:07:28<17:24:04,  7.12s/it]
 69%|██████▊   | 19287/28080 [38:07:35<17:20:49,  7.10s/it]
                                                           
{'loss': 0.6195, 'learning_rate': 0.00011792718015087775, 'epoch': 8.24}

 69%|██████▊   | 19287/28080 [38:07:35<17:20:49,  7.10s/it]
 69%|██████▊   | 19288/28080 [38:07:42<17:25:28,  7.13s/it]
                                                           
{'loss': 0.6038, 'learning_rate': 0.00011790269769133893, 'epoch': 8.24}

 69%|██████▊   | 19288/28080 [38:07:42<17:25:28,  7.13s/it]
 69%|██████▊   | 19289/28080 [38:07:49<17:26:21,  7.14s/it]
                                                           
{'loss': 0.6007, 'learning_rate': 0.00011787821698921835, 'epoch': 8.24}

 69%|██████▊   | 19289/28080 [38:07:49<17:26:21,  7.14s/it]
 69%|██████▊   | 19290/28080 [38:07:57<17:32:22,  7.18s/it]
                                                           
{'loss': 0.5947, 'learning_rate': 0.0001178537380448419, 'epoch': 8.24}

 69%|██████▊   | 19290/28080 [38:07:57<17:32:22,  7.18s/it]
 69%|██████▊   | 19291/28080 [38:08:04<17:26:08,  7.14s/it]
                                                           
{'loss': 0.6005, 'learning_rate': 0.00011782926085853513, 'epoch': 8.24}

 69%|██████▊   | 19291/28080 [38:08:04<17:26:08,  7.14s/it]
 69%|██████▊   | 19292/28080 [38:08:11<17:26:34,  7.15s/it]
                                                           
{'loss': 0.5928, 'learning_rate': 0.0001178047854306237, 'epoch': 8.24}

 69%|██████▊   | 19292/28080 [38:08:11<17:26:34,  7.15s/it]
 69%|██████▊   | 19293/28080 [38:08:18<17:23:40,  7.13s/it]
                                                           
{'loss': 0.5963, 'learning_rate': 0.0001177803117614332, 'epoch': 8.24}

 69%|██████▊   | 19293/28080 [38:08:18<17:23:40,  7.13s/it]
 69%|██████▊   | 19294/28080 [38:08:25<17:25:56,  7.14s/it]
                                                           
{'loss': 0.6177, 'learning_rate': 0.00011775583985128918, 'epoch': 8.24}

 69%|██████▊   | 19294/28080 [38:08:25<17:25:56,  7.14s/it]
 69%|██████▊   | 19295/28080 [38:08:32<17:29:43,  7.17s/it]
                                                           
{'loss': 0.5876, 'learning_rate': 0.00011773136970051734, 'epoch': 8.24}

 69%|██████▊   | 19295/28080 [38:08:32<17:29:43,  7.17s/it]
 69%|██████▊   | 19296/28080 [38:08:40<17:28:39,  7.16s/it]
                                                           
{'loss': 0.5873, 'learning_rate': 0.00011770690130944323, 'epoch': 8.24}

 69%|██████▊   | 19296/28080 [38:08:40<17:28:39,  7.16s/it]
 69%|██████▊   | 19297/28080 [38:08:47<17:23:44,  7.13s/it]
                                                           
{'loss': 0.6264, 'learning_rate': 0.00011768243467839227, 'epoch': 8.24}

 69%|██████▊   | 19297/28080 [38:08:47<17:23:44,  7.13s/it]
 69%|██████▊   | 19298/28080 [38:08:54<17:24:57,  7.14s/it]
                                                           
{'loss': 0.6097, 'learning_rate': 0.00011765796980768991, 'epoch': 8.24}

 69%|██████▊   | 19298/28080 [38:08:54<17:24:57,  7.14s/it]
 69%|██████▊   | 19299/28080 [38:09:01<17:14:44,  7.07s/it]
                                                           
{'loss': 0.6068, 'learning_rate': 0.00011763350669766187, 'epoch': 8.24}

 69%|██████▊   | 19299/28080 [38:09:01<17:14:44,  7.07s/it]
 69%|██████▊   | 19300/28080 [38:09:08<17:14:19,  7.07s/it]
                                                           
{'loss': 0.594, 'learning_rate': 0.00011760904534863334, 'epoch': 8.24}

 69%|██████▊   | 19300/28080 [38:09:08<17:14:19,  7.07s/it]
 69%|██████▊   | 19301/28080 [38:09:15<17:15:21,  7.08s/it]
                                                           
{'loss': 0.603, 'learning_rate': 0.0001175845857609301, 'epoch': 8.25}

 69%|██████▊   | 19301/28080 [38:09:15<17:15:21,  7.08s/it]
 69%|██████▊   | 19302/28080 [38:09:22<17:15:08,  7.08s/it]
                                                           
{'loss': 0.6069, 'learning_rate': 0.00011756012793487714, 'epoch': 8.25}

 69%|██████▊   | 19302/28080 [38:09:22<17:15:08,  7.08s/it]
 69%|██████▊   | 19303/28080 [38:09:29<17:23:19,  7.13s/it]
                                                           
{'loss': 0.5958, 'learning_rate': 0.00011753567187080014, 'epoch': 8.25}

 69%|██████▊   | 19303/28080 [38:09:29<17:23:19,  7.13s/it]
 69%|██████▊   | 19304/28080 [38:09:36<17:16:28,  7.09s/it]
                                                           
{'loss': 0.5977, 'learning_rate': 0.00011751121756902425, 'epoch': 8.25}

 69%|██████▊   | 19304/28080 [38:09:36<17:16:28,  7.09s/it]
 69%|██████▉   | 19305/28080 [38:09:43<17:14:43,  7.08s/it]
                                                           
{'loss': 0.6034, 'learning_rate': 0.00011748676502987507, 'epoch': 8.25}

 69%|██████▉   | 19305/28080 [38:09:43<17:14:43,  7.08s/it]
 69%|██████▉   | 19306/28080 [38:09:50<17:17:26,  7.09s/it]
                                                           
{'loss': 0.5959, 'learning_rate': 0.00011746231425367773, 'epoch': 8.25}

 69%|██████▉   | 19306/28080 [38:09:50<17:17:26,  7.09s/it]
 69%|██████▉   | 19307/28080 [38:09:57<17:14:27,  7.07s/it]
                                                           
{'loss': 0.6125, 'learning_rate': 0.00011743786524075759, 'epoch': 8.25}

 69%|██████▉   | 19307/28080 [38:09:57<17:14:27,  7.07s/it]
 69%|██████▉   | 19308/28080 [38:10:04<17:14:38,  7.08s/it]
                                                           
{'loss': 0.5994, 'learning_rate': 0.00011741341799143981, 'epoch': 8.25}

 69%|██████▉   | 19308/28080 [38:10:04<17:14:38,  7.08s/it]
 69%|██████▉   | 19309/28080 [38:10:11<17:12:37,  7.06s/it]
                                                           
{'loss': 0.6064, 'learning_rate': 0.00011738897250604979, 'epoch': 8.25}

 69%|██████▉   | 19309/28080 [38:10:11<17:12:37,  7.06s/it]
 69%|██████▉   | 19310/28080 [38:10:18<17:11:02,  7.05s/it]
                                                           
{'loss': 0.6091, 'learning_rate': 0.00011736452878491272, 'epoch': 8.25}

 69%|██████▉   | 19310/28080 [38:10:18<17:11:02,  7.05s/it]
 69%|██████▉   | 19311/28080 [38:10:26<17:12:01,  7.06s/it]
                                                           
{'loss': 0.6071, 'learning_rate': 0.00011734008682835374, 'epoch': 8.25}

 69%|██████▉   | 19311/28080 [38:10:26<17:12:01,  7.06s/it]
 69%|██████▉   | 19312/28080 [38:10:33<17:13:10,  7.07s/it]
                                                           
{'loss': 0.5957, 'learning_rate': 0.00011731564663669795, 'epoch': 8.25}

 69%|██████▉   | 19312/28080 [38:10:33<17:13:10,  7.07s/it]
 69%|██████▉   | 19313/28080 [38:10:40<17:14:21,  7.08s/it]
                                                           
{'loss': 0.5925, 'learning_rate': 0.0001172912082102707, 'epoch': 8.25}

 69%|██████▉   | 19313/28080 [38:10:40<17:14:21,  7.08s/it]
 69%|██████▉   | 19314/28080 [38:10:47<17:14:59,  7.08s/it]
                                                           
{'loss': 0.5984, 'learning_rate': 0.00011726677154939691, 'epoch': 8.25}

 69%|██████▉   | 19314/28080 [38:10:47<17:14:59,  7.08s/it]
 69%|██████▉   | 19315/28080 [38:10:54<17:18:10,  7.11s/it]
                                                           
{'loss': 0.5966, 'learning_rate': 0.00011724233665440201, 'epoch': 8.25}

 69%|██████▉   | 19315/28080 [38:10:54<17:18:10,  7.11s/it]
 69%|██████▉   | 19316/28080 [38:11:01<17:14:28,  7.08s/it]
                                                           
{'loss': 0.6217, 'learning_rate': 0.00011721790352561065, 'epoch': 8.25}

 69%|██████▉   | 19316/28080 [38:11:01<17:14:28,  7.08s/it]
 69%|██████▉   | 19317/28080 [38:11:08<17:20:31,  7.12s/it]
                                                           
{'loss': 0.5955, 'learning_rate': 0.00011719347216334819, 'epoch': 8.25}

 69%|██████▉   | 19317/28080 [38:11:08<17:20:31,  7.12s/it]
 69%|██████▉   | 19318/28080 [38:11:15<17:17:50,  7.11s/it]
                                                           
{'loss': 0.5976, 'learning_rate': 0.00011716904256793959, 'epoch': 8.25}

 69%|██████▉   | 19318/28080 [38:11:15<17:17:50,  7.11s/it]
 69%|██████▉   | 19319/28080 [38:11:22<17:12:25,  7.07s/it]
                                                           
{'loss': 0.6152, 'learning_rate': 0.00011714461473970975, 'epoch': 8.25}

 69%|██████▉   | 19319/28080 [38:11:22<17:12:25,  7.07s/it]
 69%|██████▉   | 19320/28080 [38:11:30<17:19:30,  7.12s/it]
                                                           
{'loss': 0.615, 'learning_rate': 0.00011712018867898391, 'epoch': 8.25}

 69%|██████▉   | 19320/28080 [38:11:30<17:19:30,  7.12s/it]
 69%|██████▉   | 19321/28080 [38:11:37<17:18:17,  7.11s/it]
                                                           
{'loss': 0.6114, 'learning_rate': 0.00011709576438608671, 'epoch': 8.25}

 69%|██████▉   | 19321/28080 [38:11:37<17:18:17,  7.11s/it]
 69%|██████▉   | 19322/28080 [38:11:44<17:18:45,  7.12s/it]
                                                           
{'loss': 0.6072, 'learning_rate': 0.00011707134186134336, 'epoch': 8.25}

 69%|██████▉   | 19322/28080 [38:11:44<17:18:45,  7.12s/it]
 69%|██████▉   | 19323/28080 [38:11:51<17:13:49,  7.08s/it]
                                                           
{'loss': 0.6178, 'learning_rate': 0.00011704692110507855, 'epoch': 8.25}

 69%|██████▉   | 19323/28080 [38:11:51<17:13:49,  7.08s/it]
 69%|██████▉   | 19324/28080 [38:11:58<17:16:46,  7.10s/it]
                                                           
{'loss': 0.5903, 'learning_rate': 0.00011702250211761741, 'epoch': 8.26}

 69%|██████▉   | 19324/28080 [38:11:58<17:16:46,  7.10s/it]
 69%|██████▉   | 19325/28080 [38:12:05<17:17:48,  7.11s/it]
                                                           
{'loss': 0.6097, 'learning_rate': 0.00011699808489928471, 'epoch': 8.26}

 69%|██████▉   | 19325/28080 [38:12:05<17:17:48,  7.11s/it]
 69%|██████▉   | 19326/28080 [38:12:12<17:15:11,  7.10s/it]
                                                           
{'loss': 0.6184, 'learning_rate': 0.00011697366945040525, 'epoch': 8.26}

 69%|██████▉   | 19326/28080 [38:12:12<17:15:11,  7.10s/it]
 69%|██████▉   | 19327/28080 [38:12:19<17:18:37,  7.12s/it]
                                                           
{'loss': 0.6011, 'learning_rate': 0.0001169492557713038, 'epoch': 8.26}

 69%|██████▉   | 19327/28080 [38:12:19<17:18:37,  7.12s/it]
 69%|██████▉   | 19328/28080 [38:12:26<17:20:51,  7.14s/it]
                                                           
{'loss': 0.6086, 'learning_rate': 0.00011692484386230532, 'epoch': 8.26}

 69%|██████▉   | 19328/28080 [38:12:26<17:20:51,  7.14s/it]
 69%|██████▉   | 19329/28080 [38:12:33<17:15:39,  7.10s/it]
                                                           
{'loss': 0.5924, 'learning_rate': 0.00011690043372373452, 'epoch': 8.26}

 69%|██████▉   | 19329/28080 [38:12:33<17:15:39,  7.10s/it]
 69%|██████▉   | 19330/28080 [38:12:41<17:17:13,  7.11s/it]
                                                           
{'loss': 0.5968, 'learning_rate': 0.00011687602535591615, 'epoch': 8.26}

 69%|██████▉   | 19330/28080 [38:12:41<17:17:13,  7.11s/it]
 69%|██████▉   | 19331/28080 [38:12:48<17:13:34,  7.09s/it]
                                                           
{'loss': 0.6075, 'learning_rate': 0.0001168516187591748, 'epoch': 8.26}

 69%|██████▉   | 19331/28080 [38:12:48<17:13:34,  7.09s/it]
 69%|██████▉   | 19332/28080 [38:12:55<17:14:07,  7.09s/it]
                                                           
{'loss': 0.601, 'learning_rate': 0.00011682721393383541, 'epoch': 8.26}

 69%|██████▉   | 19332/28080 [38:12:55<17:14:07,  7.09s/it]
 69%|██████▉   | 19333/28080 [38:13:02<17:13:09,  7.09s/it]
                                                           
{'loss': 0.6103, 'learning_rate': 0.00011680281088022249, 'epoch': 8.26}

 69%|██████▉   | 19333/28080 [38:13:02<17:13:09,  7.09s/it]
 69%|██████▉   | 19334/28080 [38:13:09<17:14:41,  7.10s/it]
                                                           
{'loss': 0.6001, 'learning_rate': 0.0001167784095986609, 'epoch': 8.26}

 69%|██████▉   | 19334/28080 [38:13:09<17:14:41,  7.10s/it]
 69%|██████▉   | 19335/28080 [38:13:16<17:14:39,  7.10s/it]
                                                           
{'loss': 0.6028, 'learning_rate': 0.00011675401008947498, 'epoch': 8.26}

 69%|██████▉   | 19335/28080 [38:13:16<17:14:39,  7.10s/it]
 69%|██████▉   | 19336/28080 [38:13:23<17:15:25,  7.10s/it]
                                                           
{'loss': 0.5957, 'learning_rate': 0.00011672961235298956, 'epoch': 8.26}

 69%|██████▉   | 19336/28080 [38:13:23<17:15:25,  7.10s/it]
 69%|██████▉   | 19337/28080 [38:13:30<17:13:43,  7.09s/it]
                                                           
{'loss': 0.5973, 'learning_rate': 0.00011670521638952907, 'epoch': 8.26}

 69%|██████▉   | 19337/28080 [38:13:30<17:13:43,  7.09s/it]
 69%|██████▉   | 19338/28080 [38:13:38<17:22:44,  7.16s/it]
                                                           
{'loss': 0.5878, 'learning_rate': 0.00011668082219941828, 'epoch': 8.26}

 69%|██████▉   | 19338/28080 [38:13:38<17:22:44,  7.16s/it]
 69%|██████▉   | 19339/28080 [38:13:45<17:18:38,  7.13s/it]
                                                           
{'loss': 0.6081, 'learning_rate': 0.0001166564297829816, 'epoch': 8.26}

 69%|██████▉   | 19339/28080 [38:13:45<17:18:38,  7.13s/it]
 69%|██████▉   | 19340/28080 [38:13:52<17:18:41,  7.13s/it]
                                                           
{'loss': 0.6132, 'learning_rate': 0.00011663203914054354, 'epoch': 8.26}

 69%|██████▉   | 19340/28080 [38:13:52<17:18:41,  7.13s/it]
 69%|██████▉   | 19341/28080 [38:13:59<17:17:35,  7.12s/it]
                                                           
{'loss': 0.5938, 'learning_rate': 0.00011660765027242856, 'epoch': 8.26}

 69%|██████▉   | 19341/28080 [38:13:59<17:17:35,  7.12s/it]
 69%|██████▉   | 19342/28080 [38:14:06<17:12:47,  7.09s/it]
                                                           
{'loss': 0.5973, 'learning_rate': 0.00011658326317896123, 'epoch': 8.26}

 69%|██████▉   | 19342/28080 [38:14:06<17:12:47,  7.09s/it]
 69%|██████▉   | 19343/28080 [38:14:13<17:11:14,  7.08s/it]
                                                           
{'loss': 0.6095, 'learning_rate': 0.00011655887786046595, 'epoch': 8.26}

 69%|██████▉   | 19343/28080 [38:14:13<17:11:14,  7.08s/it]
 69%|██████▉   | 19344/28080 [38:14:20<17:13:31,  7.10s/it]
                                                           
{'loss': 0.6157, 'learning_rate': 0.00011653449431726718, 'epoch': 8.26}

 69%|██████▉   | 19344/28080 [38:14:20<17:13:31,  7.10s/it]
 69%|██████▉   | 19345/28080 [38:14:27<17:11:36,  7.09s/it]
                                                           
{'loss': 0.6221, 'learning_rate': 0.00011651011254968923, 'epoch': 8.26}

 69%|██████▉   | 19345/28080 [38:14:27<17:11:36,  7.09s/it]
 69%|██████▉   | 19346/28080 [38:14:34<17:16:09,  7.12s/it]
                                                           
{'loss': 0.6078, 'learning_rate': 0.00011648573255805645, 'epoch': 8.26}

 69%|██████▉   | 19346/28080 [38:14:34<17:16:09,  7.12s/it]
 69%|██████▉   | 19347/28080 [38:14:41<17:15:03,  7.11s/it]
                                                           
{'loss': 0.596, 'learning_rate': 0.00011646135434269334, 'epoch': 8.26}

 69%|██████▉   | 19347/28080 [38:14:41<17:15:03,  7.11s/it]
 69%|██████▉   | 19348/28080 [38:14:49<17:16:06,  7.12s/it]
                                                           
{'loss': 0.6132, 'learning_rate': 0.00011643697790392405, 'epoch': 8.27}

 69%|██████▉   | 19348/28080 [38:14:49<17:16:06,  7.12s/it]
 69%|██████▉   | 19349/28080 [38:14:56<17:14:21,  7.11s/it]
                                                           
{'loss': 0.6194, 'learning_rate': 0.00011641260324207318, 'epoch': 8.27}

 69%|██████▉   | 19349/28080 [38:14:56<17:14:21,  7.11s/it]
 69%|██████▉   | 19350/28080 [38:15:03<17:10:37,  7.08s/it]
                                                           
{'loss': 0.6097, 'learning_rate': 0.0001163882303574646, 'epoch': 8.27}

 69%|██████▉   | 19350/28080 [38:15:03<17:10:37,  7.08s/it]
 69%|██████▉   | 19351/28080 [38:15:10<17:12:07,  7.09s/it]
                                                           
{'loss': 0.6055, 'learning_rate': 0.0001163638592504229, 'epoch': 8.27}

 69%|██████▉   | 19351/28080 [38:15:10<17:12:07,  7.09s/it]
 69%|██████▉   | 19352/28080 [38:15:17<17:13:25,  7.10s/it]
                                                           
{'loss': 0.598, 'learning_rate': 0.00011633948992127207, 'epoch': 8.27}

 69%|██████▉   | 19352/28080 [38:15:17<17:13:25,  7.10s/it]
 69%|██████▉   | 19353/28080 [38:15:24<17:13:04,  7.10s/it]
                                                           
{'loss': 0.6051, 'learning_rate': 0.00011631512237033653, 'epoch': 8.27}

 69%|██████▉   | 19353/28080 [38:15:24<17:13:04,  7.10s/it]
 69%|██████▉   | 19354/28080 [38:15:31<17:14:45,  7.11s/it]
                                                           
{'loss': 0.604, 'learning_rate': 0.00011629075659794039, 'epoch': 8.27}

 69%|██████▉   | 19354/28080 [38:15:31<17:14:45,  7.11s/it]
 69%|██████▉   | 19355/28080 [38:15:38<17:21:37,  7.16s/it]
                                                           
{'loss': 0.6038, 'learning_rate': 0.00011626639260440777, 'epoch': 8.27}

 69%|██████▉   | 19355/28080 [38:15:38<17:21:37,  7.16s/it]
 69%|██████▉   | 19356/28080 [38:15:45<17:14:47,  7.12s/it]
                                                           
{'loss': 0.6098, 'learning_rate': 0.00011624203039006276, 'epoch': 8.27}

 69%|██████▉   | 19356/28080 [38:15:45<17:14:47,  7.12s/it]
 69%|██████▉   | 19357/28080 [38:15:52<17:12:03,  7.10s/it]
                                                           
{'loss': 0.5978, 'learning_rate': 0.00011621766995522961, 'epoch': 8.27}

 69%|██████▉   | 19357/28080 [38:15:52<17:12:03,  7.10s/it]
 69%|██████▉   | 19358/28080 [38:16:00<17:09:51,  7.08s/it]
                                                           
{'loss': 0.6004, 'learning_rate': 0.0001161933113002324, 'epoch': 8.27}

 69%|██████▉   | 19358/28080 [38:16:00<17:09:51,  7.08s/it]
 69%|██████▉   | 19359/28080 [38:16:07<17:12:12,  7.10s/it]
                                                           
{'loss': 0.5876, 'learning_rate': 0.00011616895442539507, 'epoch': 8.27}

 69%|██████▉   | 19359/28080 [38:16:07<17:12:12,  7.10s/it]
 69%|██████▉   | 19360/28080 [38:16:14<17:13:24,  7.11s/it]
                                                           
{'loss': 0.6128, 'learning_rate': 0.00011614459933104168, 'epoch': 8.27}

 69%|██████▉   | 19360/28080 [38:16:14<17:13:24,  7.11s/it]
 69%|██████▉   | 19361/28080 [38:16:21<17:12:52,  7.11s/it]
                                                           
{'loss': 0.6184, 'learning_rate': 0.0001161202460174964, 'epoch': 8.27}

 69%|██████▉   | 19361/28080 [38:16:21<17:12:52,  7.11s/it]
 69%|██████▉   | 19362/28080 [38:16:28<17:12:42,  7.11s/it]
                                                           
{'loss': 0.635, 'learning_rate': 0.00011609589448508304, 'epoch': 8.27}

 69%|██████▉   | 19362/28080 [38:16:28<17:12:42,  7.11s/it]
 69%|██████▉   | 19363/28080 [38:16:35<17:15:42,  7.13s/it]
                                                           
{'loss': 0.5867, 'learning_rate': 0.00011607154473412584, 'epoch': 8.27}

 69%|██████▉   | 19363/28080 [38:16:35<17:15:42,  7.13s/it]
 69%|██████▉   | 19364/28080 [38:16:42<17:17:15,  7.14s/it]
                                                           
{'loss': 0.5837, 'learning_rate': 0.0001160471967649484, 'epoch': 8.27}

 69%|██████▉   | 19364/28080 [38:16:42<17:17:15,  7.14s/it]
 69%|██████▉   | 19365/28080 [38:16:50<17:18:59,  7.15s/it]
                                                           
{'loss': 0.6206, 'learning_rate': 0.0001160228505778749, 'epoch': 8.27}

 69%|██████▉   | 19365/28080 [38:16:50<17:18:59,  7.15s/it]
 69%|██████▉   | 19366/28080 [38:16:57<17:17:41,  7.15s/it]
                                                           
{'loss': 0.5934, 'learning_rate': 0.00011599850617322907, 'epoch': 8.27}

 69%|██████▉   | 19366/28080 [38:16:57<17:17:41,  7.15s/it]
 69%|██████▉   | 19367/28080 [38:17:04<17:11:10,  7.10s/it]
                                                           
{'loss': 0.6254, 'learning_rate': 0.00011597416355133495, 'epoch': 8.27}

 69%|██████▉   | 19367/28080 [38:17:04<17:11:10,  7.10s/it]
 69%|██████▉   | 19368/28080 [38:17:11<17:12:53,  7.11s/it]
                                                           
{'loss': 0.6159, 'learning_rate': 0.00011594982271251642, 'epoch': 8.27}

 69%|██████▉   | 19368/28080 [38:17:11<17:12:53,  7.11s/it]
 69%|██████▉   | 19369/28080 [38:17:18<17:10:31,  7.10s/it]
                                                           
{'loss': 0.606, 'learning_rate': 0.00011592548365709701, 'epoch': 8.27}

 69%|██████▉   | 19369/28080 [38:17:18<17:10:31,  7.10s/it]
 69%|██████▉   | 19370/28080 [38:17:25<17:08:12,  7.08s/it]
                                                           
{'loss': 0.6305, 'learning_rate': 0.00011590114638540083, 'epoch': 8.27}

 69%|██████▉   | 19370/28080 [38:17:25<17:08:12,  7.08s/it]
 69%|██████▉   | 19371/28080 [38:17:32<17:09:12,  7.09s/it]
                                                           
{'loss': 0.6323, 'learning_rate': 0.00011587681089775145, 'epoch': 8.28}

 69%|██████▉   | 19371/28080 [38:17:32<17:09:12,  7.09s/it]
 69%|██████▉   | 19372/28080 [38:17:39<17:09:27,  7.09s/it]
                                                           
{'loss': 0.6087, 'learning_rate': 0.00011585247719447284, 'epoch': 8.28}

 69%|██████▉   | 19372/28080 [38:17:39<17:09:27,  7.09s/it]
 69%|██████▉   | 19373/28080 [38:17:46<17:08:53,  7.09s/it]
                                                           
{'loss': 0.6129, 'learning_rate': 0.00011582814527588861, 'epoch': 8.28}

 69%|██████▉   | 19373/28080 [38:17:46<17:08:53,  7.09s/it]
 69%|██████▉   | 19374/28080 [38:17:53<17:08:07,  7.09s/it]
                                                           
{'loss': 0.6079, 'learning_rate': 0.00011580381514232253, 'epoch': 8.28}

 69%|██████▉   | 19374/28080 [38:17:53<17:08:07,  7.09s/it]
 69%|██████▉   | 19375/28080 [38:18:00<17:06:23,  7.07s/it]
                                                           
{'loss': 0.6171, 'learning_rate': 0.0001157794867940981, 'epoch': 8.28}

 69%|██████▉   | 19375/28080 [38:18:00<17:06:23,  7.07s/it]
 69%|██████▉   | 19376/28080 [38:18:07<16:57:44,  7.02s/it]
                                                           
{'loss': 0.6096, 'learning_rate': 0.00011575516023153926, 'epoch': 8.28}

 69%|██████▉   | 19376/28080 [38:18:07<16:57:44,  7.02s/it]
 69%|██████▉   | 19377/28080 [38:18:14<16:59:15,  7.03s/it]
                                                           
{'loss': 0.6159, 'learning_rate': 0.0001157308354549695, 'epoch': 8.28}

 69%|██████▉   | 19377/28080 [38:18:14<16:59:15,  7.03s/it]
 69%|██████▉   | 19378/28080 [38:18:21<17:00:10,  7.03s/it]
                                                           
{'loss': 0.6092, 'learning_rate': 0.00011570651246471248, 'epoch': 8.28}

 69%|██████▉   | 19378/28080 [38:18:21<17:00:10,  7.03s/it]
 69%|██████▉   | 19379/28080 [38:18:28<17:04:49,  7.07s/it]
                                                           
{'loss': 0.5807, 'learning_rate': 0.00011568219126109166, 'epoch': 8.28}

 69%|██████▉   | 19379/28080 [38:18:28<17:04:49,  7.07s/it]
 69%|██████▉   | 19380/28080 [38:18:35<17:03:18,  7.06s/it]
                                                           
{'loss': 0.5968, 'learning_rate': 0.00011565787184443083, 'epoch': 8.28}

 69%|██████▉   | 19380/28080 [38:18:35<17:03:18,  7.06s/it]
 69%|██████▉   | 19381/28080 [38:18:43<17:05:29,  7.07s/it]
                                                           
{'loss': 0.5912, 'learning_rate': 0.00011563355421505331, 'epoch': 8.28}

 69%|██████▉   | 19381/28080 [38:18:43<17:05:29,  7.07s/it]
 69%|██████▉   | 19382/28080 [38:18:50<17:04:13,  7.07s/it]
                                                           
{'loss': 0.5983, 'learning_rate': 0.00011560923837328292, 'epoch': 8.28}

 69%|██████▉   | 19382/28080 [38:18:50<17:04:13,  7.07s/it]
 69%|██████▉   | 19383/28080 [38:18:57<17:01:28,  7.05s/it]
                                                           
{'loss': 0.6072, 'learning_rate': 0.00011558492431944279, 'epoch': 8.28}

 69%|██████▉   | 19383/28080 [38:18:57<17:01:28,  7.05s/it]
 69%|██████▉   | 19384/28080 [38:19:04<16:58:30,  7.03s/it]
                                                           
{'loss': 0.5909, 'learning_rate': 0.00011556061205385665, 'epoch': 8.28}

 69%|██████▉   | 19384/28080 [38:19:04<16:58:30,  7.03s/it]
 69%|██████▉   | 19385/28080 [38:19:11<17:02:00,  7.05s/it]
                                                           
{'loss': 0.5914, 'learning_rate': 0.0001155363015768478, 'epoch': 8.28}

 69%|██████▉   | 19385/28080 [38:19:11<17:02:00,  7.05s/it]
 69%|██████▉   | 19386/28080 [38:19:18<17:03:58,  7.07s/it]
                                                           
{'loss': 0.6173, 'learning_rate': 0.00011551199288873981, 'epoch': 8.28}

 69%|██████▉   | 19386/28080 [38:19:18<17:03:58,  7.07s/it]
 69%|██████▉   | 19387/28080 [38:19:25<17:01:52,  7.05s/it]
                                                           
{'loss': 0.613, 'learning_rate': 0.00011548768598985604, 'epoch': 8.28}

 69%|██████▉   | 19387/28080 [38:19:25<17:01:52,  7.05s/it]
 69%|██████▉   | 19388/28080 [38:19:32<17:03:16,  7.06s/it]
                                                           
{'loss': 0.5898, 'learning_rate': 0.00011546338088051981, 'epoch': 8.28}

 69%|██████▉   | 19388/28080 [38:19:32<17:03:16,  7.06s/it]
 69%|██████▉   | 19389/28080 [38:19:39<17:02:34,  7.06s/it]
                                                           
{'loss': 0.6064, 'learning_rate': 0.00011543907756105443, 'epoch': 8.28}

 69%|██████▉   | 19389/28080 [38:19:39<17:02:34,  7.06s/it]
 69%|██████▉   | 19390/28080 [38:19:46<17:05:20,  7.08s/it]
                                                           
{'loss': 0.6128, 'learning_rate': 0.00011541477603178338, 'epoch': 8.28}

 69%|██████▉   | 19390/28080 [38:19:46<17:05:20,  7.08s/it]
 69%|██████▉   | 19391/28080 [38:19:53<16:59:12,  7.04s/it]
                                                           
{'loss': 0.618, 'learning_rate': 0.0001153904762930299, 'epoch': 8.28}

 69%|██████▉   | 19391/28080 [38:19:53<16:59:12,  7.04s/it]
 69%|██████▉   | 19392/28080 [38:20:00<17:00:28,  7.05s/it]
                                                           
{'loss': 0.6003, 'learning_rate': 0.00011536617834511729, 'epoch': 8.28}

 69%|██████▉   | 19392/28080 [38:20:00<17:00:28,  7.05s/it]
 69%|██████▉   | 19393/28080 [38:20:07<17:08:58,  7.11s/it]
                                                           
{'loss': 0.6113, 'learning_rate': 0.00011534188218836875, 'epoch': 8.28}

 69%|██████▉   | 19393/28080 [38:20:07<17:08:58,  7.11s/it]
 69%|██████▉   | 19394/28080 [38:20:14<17:02:41,  7.06s/it]
                                                           
{'loss': 0.6019, 'learning_rate': 0.00011531758782310747, 'epoch': 8.28}

 69%|██████▉   | 19394/28080 [38:20:14<17:02:41,  7.06s/it]
 69%|██████▉   | 19395/28080 [38:20:21<17:04:16,  7.08s/it]
                                                           
{'loss': 0.602, 'learning_rate': 0.00011529329524965682, 'epoch': 8.29}

 69%|██████▉   | 19395/28080 [38:20:21<17:04:16,  7.08s/it]
 69%|██████▉   | 19396/28080 [38:20:28<17:00:36,  7.05s/it]
                                                           
{'loss': 0.6174, 'learning_rate': 0.00011526900446833993, 'epoch': 8.29}

 69%|██████▉   | 19396/28080 [38:20:28<17:00:36,  7.05s/it]
 69%|██████▉   | 19397/28080 [38:20:36<17:02:49,  7.07s/it]
                                                           
{'loss': 0.625, 'learning_rate': 0.00011524471547947993, 'epoch': 8.29}

 69%|██████▉   | 19397/28080 [38:20:36<17:02:49,  7.07s/it]
 69%|██████▉   | 19398/28080 [38:20:43<17:00:26,  7.05s/it]
                                                           
{'loss': 0.6106, 'learning_rate': 0.00011522042828339987, 'epoch': 8.29}

 69%|██████▉   | 19398/28080 [38:20:43<17:00:26,  7.05s/it]
 69%|██████▉   | 19399/28080 [38:20:50<17:00:44,  7.06s/it]
                                                           
{'loss': 0.6118, 'learning_rate': 0.00011519614288042307, 'epoch': 8.29}

 69%|██████▉   | 19399/28080 [38:20:50<17:00:44,  7.06s/it]
 69%|██████▉   | 19400/28080 [38:20:57<17:02:19,  7.07s/it]
                                                           
{'loss': 0.5982, 'learning_rate': 0.00011517185927087243, 'epoch': 8.29}

 69%|██████▉   | 19400/28080 [38:20:57<17:02:19,  7.07s/it]
 69%|██████▉   | 19401/28080 [38:21:04<17:03:30,  7.08s/it]
                                                           
{'loss': 0.6026, 'learning_rate': 0.00011514757745507117, 'epoch': 8.29}

 69%|██████▉   | 19401/28080 [38:21:04<17:03:30,  7.08s/it]
 69%|██████▉   | 19402/28080 [38:21:11<17:01:01,  7.06s/it]
                                                           
{'loss': 0.6252, 'learning_rate': 0.0001151232974333423, 'epoch': 8.29}

 69%|██████▉   | 19402/28080 [38:21:11<17:01:01,  7.06s/it]
 69%|██████▉   | 19403/28080 [38:21:18<16:56:14,  7.03s/it]
                                                           
{'loss': 0.6016, 'learning_rate': 0.00011509901920600882, 'epoch': 8.29}

 69%|██████▉   | 19403/28080 [38:21:18<16:56:14,  7.03s/it]
 69%|██████▉   | 19404/28080 [38:21:25<16:49:32,  6.98s/it]
                                                           
{'loss': 0.6396, 'learning_rate': 0.0001150747427733936, 'epoch': 8.29}

 69%|██████▉   | 19404/28080 [38:21:25<16:49:32,  6.98s/it]
 69%|██████▉   | 19405/28080 [38:21:32<16:57:11,  7.04s/it]
                                                           
{'loss': 0.6044, 'learning_rate': 0.00011505046813581984, 'epoch': 8.29}

 69%|██████▉   | 19405/28080 [38:21:32<16:57:11,  7.04s/it]
 69%|██████▉   | 19406/28080 [38:21:39<16:58:51,  7.05s/it]
                                                           
{'loss': 0.5998, 'learning_rate': 0.00011502619529361039, 'epoch': 8.29}

 69%|██████▉   | 19406/28080 [38:21:39<16:58:51,  7.05s/it]
 69%|██████▉   | 19407/28080 [38:21:46<17:03:06,  7.08s/it]
                                                           
{'loss': 0.6184, 'learning_rate': 0.00011500192424708816, 'epoch': 8.29}

 69%|██████▉   | 19407/28080 [38:21:46<17:03:06,  7.08s/it]
 69%|██████▉   | 19408/28080 [38:21:53<17:05:13,  7.09s/it]
                                                           
{'loss': 0.6038, 'learning_rate': 0.00011497765499657597, 'epoch': 8.29}

 69%|██████▉   | 19408/28080 [38:21:53<17:05:13,  7.09s/it]
 69%|██████▉   | 19409/28080 [38:22:00<17:07:44,  7.11s/it]
                                                           
{'loss': 0.6018, 'learning_rate': 0.00011495338754239686, 'epoch': 8.29}

 69%|██████▉   | 19409/28080 [38:22:00<17:07:44,  7.11s/it]
 69%|██████▉   | 19410/28080 [38:22:07<17:08:45,  7.12s/it]
                                                           
{'loss': 0.605, 'learning_rate': 0.00011492912188487353, 'epoch': 8.29}

 69%|██████▉   | 19410/28080 [38:22:07<17:08:45,  7.12s/it]
 69%|██████▉   | 19411/28080 [38:22:15<17:09:39,  7.13s/it]
                                                           
{'loss': 0.5853, 'learning_rate': 0.0001149048580243291, 'epoch': 8.29}

 69%|██████▉   | 19411/28080 [38:22:15<17:09:39,  7.13s/it]
 69%|██████▉   | 19412/28080 [38:22:22<17:09:16,  7.12s/it]
                                                           
{'loss': 0.5805, 'learning_rate': 0.00011488059596108594, 'epoch': 8.29}

 69%|██████▉   | 19412/28080 [38:22:22<17:09:16,  7.12s/it]
 69%|██████▉   | 19413/28080 [38:22:29<17:10:48,  7.14s/it]
                                                           
{'loss': 0.5965, 'learning_rate': 0.00011485633569546716, 'epoch': 8.29}

 69%|██████▉   | 19413/28080 [38:22:29<17:10:48,  7.14s/it]
 69%|██████▉   | 19414/28080 [38:22:36<17:07:36,  7.11s/it]
                                                           
{'loss': 0.5861, 'learning_rate': 0.00011483207722779531, 'epoch': 8.29}

 69%|██████▉   | 19414/28080 [38:22:36<17:07:36,  7.11s/it]
 69%|██████▉   | 19415/28080 [38:22:43<17:04:23,  7.09s/it]
                                                           
{'loss': 0.5924, 'learning_rate': 0.00011480782055839334, 'epoch': 8.29}

 69%|██████▉   | 19415/28080 [38:22:43<17:04:23,  7.09s/it]
 69%|██████▉   | 19416/28080 [38:22:50<17:02:28,  7.08s/it]
                                                           
{'loss': 0.6278, 'learning_rate': 0.00011478356568758385, 'epoch': 8.29}

 69%|██████▉   | 19416/28080 [38:22:50<17:02:28,  7.08s/it]
 69%|██████▉   | 19417/28080 [38:22:57<16:59:50,  7.06s/it]
                                                           
{'loss': 0.6105, 'learning_rate': 0.00011475931261568951, 'epoch': 8.29}

 69%|██████▉   | 19417/28080 [38:22:57<16:59:50,  7.06s/it]
 69%|██████▉   | 19418/28080 [38:23:04<17:03:05,  7.09s/it]
                                                           
{'loss': 0.5942, 'learning_rate': 0.000114735061343033, 'epoch': 8.3}

 69%|██████▉   | 19418/28080 [38:23:04<17:03:05,  7.09s/it]
 69%|██████▉   | 19419/28080 [38:23:11<17:02:51,  7.09s/it]
                                                           
{'loss': 0.5983, 'learning_rate': 0.00011471081186993687, 'epoch': 8.3}

 69%|██████▉   | 19419/28080 [38:23:11<17:02:51,  7.09s/it]
 69%|██████▉   | 19420/28080 [38:23:18<17:01:07,  7.07s/it]
                                                           
{'loss': 0.601, 'learning_rate': 0.00011468656419672388, 'epoch': 8.3}

 69%|██████▉   | 19420/28080 [38:23:18<17:01:07,  7.07s/it]
 69%|██████▉   | 19421/28080 [38:23:25<17:03:51,  7.09s/it]
                                                           
{'loss': 0.6061, 'learning_rate': 0.0001146623183237166, 'epoch': 8.3}

 69%|██████▉   | 19421/28080 [38:23:25<17:03:51,  7.09s/it]
 69%|██████▉   | 19422/28080 [38:23:33<17:04:31,  7.10s/it]
                                                           
{'loss': 0.5925, 'learning_rate': 0.0001146380742512375, 'epoch': 8.3}

 69%|██████▉   | 19422/28080 [38:23:33<17:04:31,  7.10s/it]
 69%|██████▉   | 19423/28080 [38:23:40<17:05:26,  7.11s/it]
                                                           
{'loss': 0.5871, 'learning_rate': 0.00011461383197960914, 'epoch': 8.3}

 69%|██████▉   | 19423/28080 [38:23:40<17:05:26,  7.11s/it]
 69%|██████▉   | 19424/28080 [38:23:47<17:00:36,  7.07s/it]
                                                           
{'loss': 0.5915, 'learning_rate': 0.00011458959150915415, 'epoch': 8.3}

 69%|██████▉   | 19424/28080 [38:23:47<17:00:36,  7.07s/it]
 69%|██████▉   | 19425/28080 [38:23:54<16:53:46,  7.03s/it]
                                                           
{'loss': 0.6131, 'learning_rate': 0.00011456535284019495, 'epoch': 8.3}

 69%|██████▉   | 19425/28080 [38:23:54<16:53:46,  7.03s/it]
 69%|██████▉   | 19426/28080 [38:24:01<16:58:07,  7.06s/it]
                                                           
{'loss': 0.6127, 'learning_rate': 0.000114541115973054, 'epoch': 8.3}

 69%|██████▉   | 19426/28080 [38:24:01<16:58:07,  7.06s/it]
 69%|██████▉   | 19427/28080 [38:24:08<17:02:21,  7.09s/it]
                                                           
{'loss': 0.6044, 'learning_rate': 0.00011451688090805368, 'epoch': 8.3}

 69%|██████▉   | 19427/28080 [38:24:08<17:02:21,  7.09s/it]
 69%|██████▉   | 19428/28080 [38:24:15<17:01:15,  7.08s/it]
                                                           
{'loss': 0.6212, 'learning_rate': 0.00011449264764551656, 'epoch': 8.3}

 69%|██████▉   | 19428/28080 [38:24:15<17:01:15,  7.08s/it]
 69%|██████▉   | 19429/28080 [38:24:22<17:03:15,  7.10s/it]
                                                           
{'loss': 0.6138, 'learning_rate': 0.00011446841618576489, 'epoch': 8.3}

 69%|██████▉   | 19429/28080 [38:24:22<17:03:15,  7.10s/it]
 69%|██████▉   | 19430/28080 [38:24:29<17:01:00,  7.08s/it]
                                                           
{'loss': 0.6234, 'learning_rate': 0.00011444418652912131, 'epoch': 8.3}

 69%|██████▉   | 19430/28080 [38:24:29<17:01:00,  7.08s/it]
 69%|██████▉   | 19431/28080 [38:24:36<17:00:16,  7.08s/it]
                                                           
{'loss': 0.614, 'learning_rate': 0.00011441995867590779, 'epoch': 8.3}

 69%|██████▉   | 19431/28080 [38:24:36<17:00:16,  7.08s/it]
 69%|██████▉   | 19432/28080 [38:24:43<17:00:34,  7.08s/it]
                                                           
{'loss': 0.6057, 'learning_rate': 0.00011439573262644693, 'epoch': 8.3}

 69%|██████▉   | 19432/28080 [38:24:43<17:00:34,  7.08s/it]
 69%|██████▉   | 19433/28080 [38:24:50<17:01:58,  7.09s/it]
                                                           
{'loss': 0.6226, 'learning_rate': 0.00011437150838106089, 'epoch': 8.3}

 69%|██████▉   | 19433/28080 [38:24:50<17:01:58,  7.09s/it]
 69%|██████▉   | 19434/28080 [38:24:57<16:59:17,  7.07s/it]
                                                           
{'loss': 0.6144, 'learning_rate': 0.00011434728594007207, 'epoch': 8.3}

 69%|██████▉   | 19434/28080 [38:24:57<16:59:17,  7.07s/it]
 69%|██████▉   | 19435/28080 [38:25:05<17:00:57,  7.09s/it]
                                                           
{'loss': 0.6046, 'learning_rate': 0.00011432306530380269, 'epoch': 8.3}

 69%|██████▉   | 19435/28080 [38:25:05<17:00:57,  7.09s/it]
 69%|██████▉   | 19436/28080 [38:25:12<17:03:09,  7.10s/it]
                                                           
{'loss': 0.6, 'learning_rate': 0.00011429884647257496, 'epoch': 8.3}

 69%|██████▉   | 19436/28080 [38:25:12<17:03:09,  7.10s/it]
 69%|██████▉   | 19437/28080 [38:25:19<17:00:40,  7.09s/it]
                                                           
{'loss': 0.6054, 'learning_rate': 0.00011427462944671096, 'epoch': 8.3}

 69%|██████▉   | 19437/28080 [38:25:19<17:00:40,  7.09s/it]
 69%|██████▉   | 19438/28080 [38:25:26<17:03:51,  7.11s/it]
                                                           
{'loss': 0.5848, 'learning_rate': 0.00011425041422653312, 'epoch': 8.3}

 69%|██████▉   | 19438/28080 [38:25:26<17:03:51,  7.11s/it]
 69%|██████▉   | 19439/28080 [38:25:33<17:01:41,  7.09s/it]
                                                           
{'loss': 0.6119, 'learning_rate': 0.00011422620081236346, 'epoch': 8.3}

 69%|██████▉   | 19439/28080 [38:25:33<17:01:41,  7.09s/it]
 69%|██████▉   | 19440/28080 [38:25:40<17:08:37,  7.14s/it]
                                                           
{'loss': 0.6066, 'learning_rate': 0.00011420198920452412, 'epoch': 8.3}

 69%|██████▉   | 19440/28080 [38:25:40<17:08:37,  7.14s/it]
 69%|██████▉   | 19441/28080 [38:25:47<17:08:52,  7.15s/it]
                                                           
{'loss': 0.6064, 'learning_rate': 0.00011417777940333715, 'epoch': 8.31}

 69%|██████▉   | 19441/28080 [38:25:47<17:08:52,  7.15s/it]
 69%|██████▉   | 19442/28080 [38:25:54<17:04:34,  7.12s/it]
                                                           
{'loss': 0.5995, 'learning_rate': 0.00011415357140912477, 'epoch': 8.31}

 69%|██████▉   | 19442/28080 [38:25:54<17:04:34,  7.12s/it]
 69%|██████▉   | 19443/28080 [38:26:02<17:01:15,  7.09s/it]
                                                           
{'loss': 0.6232, 'learning_rate': 0.00011412936522220898, 'epoch': 8.31}

 69%|██████▉   | 19443/28080 [38:26:02<17:01:15,  7.09s/it]
 69%|██████▉   | 19444/28080 [38:26:09<16:58:37,  7.08s/it]
                                                           
{'loss': 0.6308, 'learning_rate': 0.00011410516084291183, 'epoch': 8.31}

 69%|██████▉   | 19444/28080 [38:26:09<16:58:37,  7.08s/it]
 69%|██████▉   | 19445/28080 [38:26:16<17:01:24,  7.10s/it]
                                                           
{'loss': 0.6009, 'learning_rate': 0.00011408095827155532, 'epoch': 8.31}

 69%|██████▉   | 19445/28080 [38:26:16<17:01:24,  7.10s/it]
 69%|██████▉   | 19446/28080 [38:26:23<17:03:02,  7.11s/it]
                                                           
{'loss': 0.6195, 'learning_rate': 0.00011405675750846137, 'epoch': 8.31}

 69%|██████▉   | 19446/28080 [38:26:23<17:03:02,  7.11s/it]
 69%|██████▉   | 19447/28080 [38:26:30<17:01:40,  7.10s/it]
                                                           
{'loss': 0.6263, 'learning_rate': 0.00011403255855395205, 'epoch': 8.31}

 69%|██████▉   | 19447/28080 [38:26:30<17:01:40,  7.10s/it]
 69%|██████▉   | 19448/28080 [38:26:37<16:56:31,  7.07s/it]
                                                           
{'loss': 0.6188, 'learning_rate': 0.00011400836140834922, 'epoch': 8.31}

 69%|██████▉   | 19448/28080 [38:26:37<16:56:31,  7.07s/it]
 69%|██████▉   | 19449/28080 [38:26:44<17:00:09,  7.09s/it]
                                                           
{'loss': 0.6139, 'learning_rate': 0.00011398416607197492, 'epoch': 8.31}

 69%|██████▉   | 19449/28080 [38:26:44<17:00:09,  7.09s/it]
 69%|██████▉   | 19450/28080 [38:26:51<17:01:50,  7.10s/it]
                                                           
{'loss': 0.6188, 'learning_rate': 0.000113959972545151, 'epoch': 8.31}

 69%|██████▉   | 19450/28080 [38:26:51<17:01:50,  7.10s/it]
 69%|██████▉   | 19451/28080 [38:26:58<17:01:04,  7.10s/it]
                                                           
{'loss': 0.6227, 'learning_rate': 0.00011393578082819927, 'epoch': 8.31}

 69%|██████▉   | 19451/28080 [38:26:58<17:01:04,  7.10s/it]
 69%|██████▉   | 19452/28080 [38:27:05<16:59:32,  7.09s/it]
                                                           
{'loss': 0.6085, 'learning_rate': 0.00011391159092144151, 'epoch': 8.31}

 69%|██████▉   | 19452/28080 [38:27:05<16:59:32,  7.09s/it]
 69%|██████▉   | 19453/28080 [38:27:12<16:59:08,  7.09s/it]
                                                           
{'loss': 0.6076, 'learning_rate': 0.00011388740282519977, 'epoch': 8.31}

 69%|██████▉   | 19453/28080 [38:27:12<16:59:08,  7.09s/it]
 69%|██████▉   | 19454/28080 [38:27:19<16:57:56,  7.08s/it]
                                                           
{'loss': 0.6231, 'learning_rate': 0.00011386321653979567, 'epoch': 8.31}

 69%|██████▉   | 19454/28080 [38:27:19<16:57:56,  7.08s/it]
 69%|██████▉   | 19455/28080 [38:27:27<16:57:37,  7.08s/it]
                                                           
{'loss': 0.6076, 'learning_rate': 0.00011383903206555108, 'epoch': 8.31}

 69%|██████▉   | 19455/28080 [38:27:27<16:57:37,  7.08s/it]
 69%|██████▉   | 19456/28080 [38:27:34<16:55:48,  7.07s/it]
                                                           
{'loss': 0.5841, 'learning_rate': 0.00011381484940278755, 'epoch': 8.31}

 69%|██████▉   | 19456/28080 [38:27:34<16:55:48,  7.07s/it]
 69%|██████▉   | 19457/28080 [38:27:41<17:02:36,  7.12s/it]
                                                           
{'loss': 0.5996, 'learning_rate': 0.00011379066855182706, 'epoch': 8.31}

 69%|██████▉   | 19457/28080 [38:27:41<17:02:36,  7.12s/it]
 69%|██████▉   | 19458/28080 [38:27:48<17:01:21,  7.11s/it]
                                                           
{'loss': 0.5906, 'learning_rate': 0.00011376648951299124, 'epoch': 8.31}

 69%|██████▉   | 19458/28080 [38:27:48<17:01:21,  7.11s/it]
 69%|██████▉   | 19459/28080 [38:27:55<17:00:44,  7.10s/it]
                                                           
{'loss': 0.5925, 'learning_rate': 0.0001137423122866017, 'epoch': 8.31}

 69%|██████▉   | 19459/28080 [38:27:55<17:00:44,  7.10s/it]
 69%|██████▉   | 19460/28080 [38:28:02<16:59:27,  7.10s/it]
                                                           
{'loss': 0.6042, 'learning_rate': 0.00011371813687298004, 'epoch': 8.31}

 69%|██████▉   | 19460/28080 [38:28:02<16:59:27,  7.10s/it]
 69%|██████▉   | 19461/28080 [38:28:09<16:59:58,  7.10s/it]
                                                           
{'loss': 0.6187, 'learning_rate': 0.00011369396327244808, 'epoch': 8.31}

 69%|██████▉   | 19461/28080 [38:28:09<16:59:58,  7.10s/it]
 69%|██████▉   | 19462/28080 [38:28:16<17:00:36,  7.11s/it]
                                                           
{'loss': 0.6027, 'learning_rate': 0.00011366979148532721, 'epoch': 8.31}

 69%|██████▉   | 19462/28080 [38:28:16<17:00:36,  7.11s/it]
 69%|██████▉   | 19463/28080 [38:28:23<17:00:52,  7.11s/it]
                                                           
{'loss': 0.5934, 'learning_rate': 0.00011364562151193924, 'epoch': 8.31}

 69%|██████▉   | 19463/28080 [38:28:23<17:00:52,  7.11s/it]
 69%|██████▉   | 19464/28080 [38:28:31<17:04:47,  7.14s/it]
                                                           
{'loss': 0.6195, 'learning_rate': 0.00011362145335260557, 'epoch': 8.31}

 69%|██████▉   | 19464/28080 [38:28:31<17:04:47,  7.14s/it]
 69%|██████▉   | 19465/28080 [38:28:38<17:02:11,  7.12s/it]
                                                           
{'loss': 0.5845, 'learning_rate': 0.0001135972870076478, 'epoch': 8.32}

 69%|██████▉   | 19465/28080 [38:28:38<17:02:11,  7.12s/it]
 69%|██████▉   | 19466/28080 [38:28:45<16:57:35,  7.09s/it]
                                                           
{'loss': 0.5872, 'learning_rate': 0.0001135731224773873, 'epoch': 8.32}

 69%|██████▉   | 19466/28080 [38:28:45<16:57:35,  7.09s/it]
 69%|██████▉   | 19467/28080 [38:28:52<16:57:12,  7.09s/it]
                                                           
{'loss': 0.622, 'learning_rate': 0.00011354895976214577, 'epoch': 8.32}

 69%|██████▉   | 19467/28080 [38:28:52<16:57:12,  7.09s/it]
 69%|██████▉   | 19468/28080 [38:28:59<17:00:22,  7.11s/it]
                                                           
{'loss': 0.6141, 'learning_rate': 0.00011352479886224454, 'epoch': 8.32}

 69%|██████▉   | 19468/28080 [38:28:59<17:00:22,  7.11s/it]
 69%|██████▉   | 19469/28080 [38:29:06<16:59:59,  7.11s/it]
                                                           
{'loss': 0.61, 'learning_rate': 0.00011350063977800506, 'epoch': 8.32}

 69%|██████▉   | 19469/28080 [38:29:06<16:59:59,  7.11s/it]
 69%|██████▉   | 19470/28080 [38:29:13<16:57:27,  7.09s/it]
                                                           
{'loss': 0.5859, 'learning_rate': 0.00011347648250974876, 'epoch': 8.32}

 69%|██████▉   | 19470/28080 [38:29:13<16:57:27,  7.09s/it]
 69%|██████▉   | 19471/28080 [38:29:20<16:58:06,  7.10s/it]
                                                           
{'loss': 0.6199, 'learning_rate': 0.00011345232705779695, 'epoch': 8.32}

 69%|██████▉   | 19471/28080 [38:29:20<16:58:06,  7.10s/it]
 69%|██████▉   | 19472/28080 [38:29:27<16:58:54,  7.10s/it]
                                                           
{'loss': 0.6195, 'learning_rate': 0.00011342817342247114, 'epoch': 8.32}

 69%|██████▉   | 19472/28080 [38:29:27<16:58:54,  7.10s/it]
 69%|██████▉   | 19473/28080 [38:29:34<16:58:19,  7.10s/it]
                                                           
{'loss': 0.6185, 'learning_rate': 0.00011340402160409258, 'epoch': 8.32}

 69%|██████▉   | 19473/28080 [38:29:34<16:58:19,  7.10s/it]
 69%|██████▉   | 19474/28080 [38:29:42<17:00:56,  7.12s/it]
                                                           
{'loss': 0.6055, 'learning_rate': 0.00011337987160298258, 'epoch': 8.32}

 69%|██████▉   | 19474/28080 [38:29:42<17:00:56,  7.12s/it]
 69%|██████▉   | 19475/28080 [38:29:49<16:59:14,  7.11s/it]
                                                           
{'loss': 0.5843, 'learning_rate': 0.00011335572341946237, 'epoch': 8.32}

 69%|██████▉   | 19475/28080 [38:29:49<16:59:14,  7.11s/it]
 69%|██████▉   | 19476/28080 [38:29:56<16:56:37,  7.09s/it]
                                                           
{'loss': 0.6019, 'learning_rate': 0.00011333157705385338, 'epoch': 8.32}

 69%|██████▉   | 19476/28080 [38:29:56<16:56:37,  7.09s/it]
 69%|██████▉   | 19477/28080 [38:30:03<16:54:46,  7.08s/it]
                                                           
{'loss': 0.6184, 'learning_rate': 0.00011330743250647668, 'epoch': 8.32}

 69%|██████▉   | 19477/28080 [38:30:03<16:54:46,  7.08s/it]
 69%|██████▉   | 19478/28080 [38:30:10<16:55:26,  7.08s/it]
                                                           
{'loss': 0.5909, 'learning_rate': 0.00011328328977765376, 'epoch': 8.32}

 69%|██████▉   | 19478/28080 [38:30:10<16:55:26,  7.08s/it]
 69%|██████▉   | 19479/28080 [38:30:17<16:54:25,  7.08s/it]
                                                           
{'loss': 0.5969, 'learning_rate': 0.00011325914886770542, 'epoch': 8.32}

 69%|██████▉   | 19479/28080 [38:30:17<16:54:25,  7.08s/it]
 69%|██████▉   | 19480/28080 [38:30:24<16:52:08,  7.06s/it]
                                                           
{'loss': 0.5979, 'learning_rate': 0.00011323500977695314, 'epoch': 8.32}

 69%|██████▉   | 19480/28080 [38:30:24<16:52:08,  7.06s/it]
 69%|██████▉   | 19481/28080 [38:30:31<16:53:00,  7.07s/it]
                                                           
{'loss': 0.6003, 'learning_rate': 0.00011321087250571787, 'epoch': 8.32}

 69%|██████▉   | 19481/28080 [38:30:31<16:53:00,  7.07s/it]
 69%|██████▉   | 19482/28080 [38:30:38<16:58:00,  7.10s/it]
                                                           
{'loss': 0.6176, 'learning_rate': 0.00011318673705432092, 'epoch': 8.32}

 69%|██████▉   | 19482/28080 [38:30:38<16:58:00,  7.10s/it]
 69%|██████▉   | 19483/28080 [38:30:45<16:57:41,  7.10s/it]
                                                           
{'loss': 0.6224, 'learning_rate': 0.0001131626034230833, 'epoch': 8.32}

 69%|██████▉   | 19483/28080 [38:30:45<16:57:41,  7.10s/it]
 69%|██████▉   | 19484/28080 [38:30:52<16:57:08,  7.10s/it]
                                                           
{'loss': 0.6153, 'learning_rate': 0.00011313847161232604, 'epoch': 8.32}

 69%|██████▉   | 19484/28080 [38:30:52<16:57:08,  7.10s/it]
 69%|██████▉   | 19485/28080 [38:31:00<17:00:19,  7.12s/it]
                                                           
{'loss': 0.6149, 'learning_rate': 0.00011311434162237016, 'epoch': 8.32}

 69%|██████▉   | 19485/28080 [38:31:00<17:00:19,  7.12s/it]
 69%|██████▉   | 19486/28080 [38:31:07<17:00:02,  7.12s/it]
                                                           
{'loss': 0.5961, 'learning_rate': 0.00011309021345353684, 'epoch': 8.32}

 69%|██████▉   | 19486/28080 [38:31:07<17:00:02,  7.12s/it]
 69%|██████▉   | 19487/28080 [38:31:14<16:58:25,  7.11s/it]
                                                           
{'loss': 0.6051, 'learning_rate': 0.000113066087106147, 'epoch': 8.32}

 69%|██████▉   | 19487/28080 [38:31:14<16:58:25,  7.11s/it]
 69%|██████▉   | 19488/28080 [38:31:21<16:59:38,  7.12s/it]
                                                           
{'loss': 0.588, 'learning_rate': 0.00011304196258052157, 'epoch': 8.33}

 69%|██████▉   | 19488/28080 [38:31:21<16:59:38,  7.12s/it]
 69%|██████▉   | 19489/28080 [38:31:28<16:54:53,  7.09s/it]
                                                           
{'loss': 0.6098, 'learning_rate': 0.00011301783987698147, 'epoch': 8.33}

 69%|██████▉   | 19489/28080 [38:31:28<16:54:53,  7.09s/it]
 69%|██████▉   | 19490/28080 [38:31:35<16:54:38,  7.09s/it]
                                                           
{'loss': 0.6333, 'learning_rate': 0.00011299371899584776, 'epoch': 8.33}

 69%|██████▉   | 19490/28080 [38:31:35<16:54:38,  7.09s/it]
 69%|██████▉   | 19491/28080 [38:31:42<16:54:59,  7.09s/it]
                                                           
{'loss': 0.6016, 'learning_rate': 0.00011296959993744122, 'epoch': 8.33}

 69%|██████▉   | 19491/28080 [38:31:42<16:54:59,  7.09s/it]
 69%|██████▉   | 19492/28080 [38:31:49<16:56:02,  7.10s/it]
                                                           
{'loss': 0.6093, 'learning_rate': 0.00011294548270208293, 'epoch': 8.33}

 69%|██████▉   | 19492/28080 [38:31:49<16:56:02,  7.10s/it]
 69%|██████▉   | 19493/28080 [38:31:56<16:58:42,  7.12s/it]
                                                           
{'loss': 0.5903, 'learning_rate': 0.00011292136729009356, 'epoch': 8.33}

 69%|██████▉   | 19493/28080 [38:31:56<16:58:42,  7.12s/it]
 69%|██████▉   | 19494/28080 [38:32:03<16:55:51,  7.10s/it]
                                                           
{'loss': 0.6133, 'learning_rate': 0.00011289725370179385, 'epoch': 8.33}

 69%|██████▉   | 19494/28080 [38:32:03<16:55:51,  7.10s/it]
 69%|██████▉   | 19495/28080 [38:32:11<16:55:53,  7.10s/it]
                                                           
{'loss': 0.6146, 'learning_rate': 0.00011287314193750484, 'epoch': 8.33}

 69%|██████▉   | 19495/28080 [38:32:11<16:55:53,  7.10s/it]
 69%|██████▉   | 19496/28080 [38:32:18<16:54:17,  7.09s/it]
                                                           
{'loss': 0.6145, 'learning_rate': 0.00011284903199754713, 'epoch': 8.33}

 69%|██████▉   | 19496/28080 [38:32:18<16:54:17,  7.09s/it]
 69%|██████▉   | 19497/28080 [38:32:25<16:54:40,  7.09s/it]
                                                           
{'loss': 0.6242, 'learning_rate': 0.00011282492388224164, 'epoch': 8.33}

 69%|██████▉   | 19497/28080 [38:32:25<16:54:40,  7.09s/it]
 69%|██████▉   | 19498/28080 [38:32:32<16:55:33,  7.10s/it]
                                                           
{'loss': 0.6067, 'learning_rate': 0.00011280081759190903, 'epoch': 8.33}

 69%|██████▉   | 19498/28080 [38:32:32<16:55:33,  7.10s/it]
 69%|██████▉   | 19499/28080 [38:32:39<16:58:09,  7.12s/it]
                                                           
{'loss': 0.6069, 'learning_rate': 0.00011277671312687, 'epoch': 8.33}

 69%|██████▉   | 19499/28080 [38:32:39<16:58:09,  7.12s/it]
 69%|██████▉   | 19500/28080 [38:32:46<16:57:24,  7.11s/it]
                                                           
{'loss': 0.6024, 'learning_rate': 0.00011275261048744512, 'epoch': 8.33}

 69%|██████▉   | 19500/28080 [38:32:46<16:57:24,  7.11s/it]
 69%|██████▉   | 19501/28080 [38:32:53<16:57:04,  7.11s/it]
                                                           
{'loss': 0.5895, 'learning_rate': 0.00011272850967395528, 'epoch': 8.33}

 69%|██████▉   | 19501/28080 [38:32:53<16:57:04,  7.11s/it]
 69%|██████▉   | 19502/28080 [38:33:00<16:57:18,  7.12s/it]
                                                           
{'loss': 0.6134, 'learning_rate': 0.000112704410686721, 'epoch': 8.33}

 69%|██████▉   | 19502/28080 [38:33:00<16:57:18,  7.12s/it]
 69%|██████▉   | 19503/28080 [38:33:07<16:55:14,  7.10s/it]
                                                           
{'loss': 0.6094, 'learning_rate': 0.0001126803135260629, 'epoch': 8.33}

 69%|██████▉   | 19503/28080 [38:33:07<16:55:14,  7.10s/it]
 69%|██████▉   | 19504/28080 [38:33:15<16:54:19,  7.10s/it]
                                                           
{'loss': 0.6082, 'learning_rate': 0.00011265621819230145, 'epoch': 8.33}

 69%|██████▉   | 19504/28080 [38:33:15<16:54:19,  7.10s/it]
 69%|██████▉   | 19505/28080 [38:33:21<16:48:24,  7.06s/it]
                                                           
{'loss': 0.6098, 'learning_rate': 0.00011263212468575745, 'epoch': 8.33}

 69%|██████▉   | 19505/28080 [38:33:21<16:48:24,  7.06s/it]
 69%|██████▉   | 19506/28080 [38:33:28<16:42:50,  7.02s/it]
                                                           
{'loss': 0.6168, 'learning_rate': 0.00011260803300675132, 'epoch': 8.33}

 69%|██████▉   | 19506/28080 [38:33:28<16:42:50,  7.02s/it]
 69%|██████▉   | 19507/28080 [38:33:36<16:48:06,  7.06s/it]
                                                           
{'loss': 0.5992, 'learning_rate': 0.00011258394315560355, 'epoch': 8.33}

 69%|██████▉   | 19507/28080 [38:33:36<16:48:06,  7.06s/it]
 69%|██████▉   | 19508/28080 [38:33:43<16:51:15,  7.08s/it]
                                                           
{'loss': 0.5995, 'learning_rate': 0.00011255985513263456, 'epoch': 8.33}

 69%|██████▉   | 19508/28080 [38:33:43<16:51:15,  7.08s/it]
 69%|██████▉   | 19509/28080 [38:33:50<16:54:26,  7.10s/it]
                                                           
{'loss': 0.6151, 'learning_rate': 0.000112535768938165, 'epoch': 8.33}

 69%|██████▉   | 19509/28080 [38:33:50<16:54:26,  7.10s/it]
 69%|██████▉   | 19510/28080 [38:33:57<16:57:19,  7.12s/it]
                                                           
{'loss': 0.6151, 'learning_rate': 0.00011251168457251515, 'epoch': 8.33}

 69%|██████▉   | 19510/28080 [38:33:57<16:57:19,  7.12s/it]
 69%|██████▉   | 19511/28080 [38:34:04<16:55:31,  7.11s/it]
                                                           
{'loss': 0.6044, 'learning_rate': 0.00011248760203600558, 'epoch': 8.33}

 69%|██████▉   | 19511/28080 [38:34:04<16:55:31,  7.11s/it]
 69%|██████▉   | 19512/28080 [38:34:11<16:57:25,  7.12s/it]
                                                           
{'loss': 0.5985, 'learning_rate': 0.00011246352132895659, 'epoch': 8.34}

 69%|██████▉   | 19512/28080 [38:34:11<16:57:25,  7.12s/it]
 69%|██████▉   | 19513/28080 [38:34:18<16:58:26,  7.13s/it]
                                                           
{'loss': 0.6141, 'learning_rate': 0.00011243944245168858, 'epoch': 8.34}

 69%|██████▉   | 19513/28080 [38:34:18<16:58:26,  7.13s/it]
 69%|██████▉   | 19514/28080 [38:34:26<17:01:05,  7.15s/it]
                                                           
{'loss': 0.6147, 'learning_rate': 0.00011241536540452174, 'epoch': 8.34}

 69%|██████▉   | 19514/28080 [38:34:26<17:01:05,  7.15s/it]
 69%|██████▉   | 19515/28080 [38:34:33<16:53:17,  7.10s/it]
                                                           
{'loss': 0.6232, 'learning_rate': 0.00011239129018777667, 'epoch': 8.34}

 69%|██████▉   | 19515/28080 [38:34:33<16:53:17,  7.10s/it]
 70%|██████▉   | 19516/28080 [38:34:40<16:50:11,  7.08s/it]
                                                           
{'loss': 0.6161, 'learning_rate': 0.00011236721680177348, 'epoch': 8.34}

 70%|██████▉   | 19516/28080 [38:34:40<16:50:11,  7.08s/it]
 70%|██████▉   | 19517/28080 [38:34:47<16:55:35,  7.12s/it]
                                                           
{'loss': 0.594, 'learning_rate': 0.00011234314524683251, 'epoch': 8.34}

 70%|██████▉   | 19517/28080 [38:34:47<16:55:35,  7.12s/it]
 70%|██████▉   | 19518/28080 [38:34:54<16:50:54,  7.08s/it]
                                                           
{'loss': 0.5984, 'learning_rate': 0.00011231907552327397, 'epoch': 8.34}

 70%|██████▉   | 19518/28080 [38:34:54<16:50:54,  7.08s/it]
 70%|██████▉   | 19519/28080 [38:35:01<16:51:55,  7.09s/it]
                                                           
{'loss': 0.6047, 'learning_rate': 0.00011229500763141801, 'epoch': 8.34}

 70%|██████▉   | 19519/28080 [38:35:01<16:51:55,  7.09s/it]
 70%|██████▉   | 19520/28080 [38:35:08<16:54:08,  7.11s/it]
                                                           
{'loss': 0.5994, 'learning_rate': 0.00011227094157158499, 'epoch': 8.34}

 70%|██████▉   | 19520/28080 [38:35:08<16:54:08,  7.11s/it]
 70%|██████▉   | 19521/28080 [38:35:15<16:54:25,  7.11s/it]
                                                           
{'loss': 0.6072, 'learning_rate': 0.00011224687734409499, 'epoch': 8.34}

 70%|██████▉   | 19521/28080 [38:35:15<16:54:25,  7.11s/it]
 70%|██████▉   | 19522/28080 [38:35:22<16:52:39,  7.10s/it]
                                                           
{'loss': 0.5978, 'learning_rate': 0.0001122228149492682, 'epoch': 8.34}

 70%|██████▉   | 19522/28080 [38:35:22<16:52:39,  7.10s/it]
 70%|██████▉   | 19523/28080 [38:35:29<16:50:03,  7.08s/it]
                                                           
{'loss': 0.6003, 'learning_rate': 0.00011219875438742464, 'epoch': 8.34}

 70%|██████▉   | 19523/28080 [38:35:29<16:50:03,  7.08s/it]
 70%|██████▉   | 19524/28080 [38:35:36<16:50:13,  7.08s/it]
                                                           
{'loss': 0.6049, 'learning_rate': 0.00011217469565888456, 'epoch': 8.34}

 70%|██████▉   | 19524/28080 [38:35:36<16:50:13,  7.08s/it]
 70%|██████▉   | 19525/28080 [38:35:44<16:52:11,  7.10s/it]
                                                           
{'loss': 0.5998, 'learning_rate': 0.00011215063876396788, 'epoch': 8.34}

 70%|██████▉   | 19525/28080 [38:35:44<16:52:11,  7.10s/it]
 70%|██████▉   | 19526/28080 [38:35:51<16:57:30,  7.14s/it]
                                                           
{'loss': 0.6062, 'learning_rate': 0.00011212658370299492, 'epoch': 8.34}

 70%|██████▉   | 19526/28080 [38:35:51<16:57:30,  7.14s/it]
 70%|██████▉   | 19527/28080 [38:35:58<16:51:02,  7.09s/it]
                                                           
{'loss': 0.6131, 'learning_rate': 0.00011210253047628535, 'epoch': 8.34}

 70%|██████▉   | 19527/28080 [38:35:58<16:51:02,  7.09s/it]
 70%|██████▉   | 19528/28080 [38:36:05<16:52:47,  7.11s/it]
                                                           
{'loss': 0.6037, 'learning_rate': 0.00011207847908415944, 'epoch': 8.34}

 70%|██████▉   | 19528/28080 [38:36:05<16:52:47,  7.11s/it]
 70%|██████▉   | 19529/28080 [38:36:12<16:50:51,  7.09s/it]
                                                           
{'loss': 0.6069, 'learning_rate': 0.00011205442952693698, 'epoch': 8.34}

 70%|██████▉   | 19529/28080 [38:36:12<16:50:51,  7.09s/it]
 70%|██████▉   | 19530/28080 [38:36:19<16:53:16,  7.11s/it]
                                                           
{'loss': 0.5747, 'learning_rate': 0.00011203038180493813, 'epoch': 8.34}

 70%|██████▉   | 19530/28080 [38:36:19<16:53:16,  7.11s/it]
 70%|██████▉   | 19531/28080 [38:36:26<16:43:20,  7.04s/it]
                                                           
{'loss': 0.6082, 'learning_rate': 0.00011200633591848273, 'epoch': 8.34}

 70%|██████▉   | 19531/28080 [38:36:26<16:43:20,  7.04s/it]
 70%|██████▉   | 19532/28080 [38:36:33<16:47:09,  7.07s/it]
                                                           
{'loss': 0.6035, 'learning_rate': 0.00011198229186789064, 'epoch': 8.34}

 70%|██████▉   | 19532/28080 [38:36:33<16:47:09,  7.07s/it]
 70%|██████▉   | 19533/28080 [38:36:40<16:49:20,  7.09s/it]
                                                           
{'loss': 0.6144, 'learning_rate': 0.0001119582496534817, 'epoch': 8.34}

 70%|██████▉   | 19533/28080 [38:36:40<16:49:20,  7.09s/it]
 70%|██████▉   | 19534/28080 [38:36:47<16:51:31,  7.10s/it]
                                                           
{'loss': 0.6216, 'learning_rate': 0.0001119342092755759, 'epoch': 8.34}

 70%|██████▉   | 19534/28080 [38:36:47<16:51:31,  7.10s/it]
 70%|██████▉   | 19535/28080 [38:36:55<16:53:57,  7.12s/it]
                                                           
{'loss': 0.603, 'learning_rate': 0.00011191017073449305, 'epoch': 8.35}

 70%|██████▉   | 19535/28080 [38:36:55<16:53:57,  7.12s/it]
 70%|██████▉   | 19536/28080 [38:37:02<16:48:34,  7.08s/it]
                                                           
{'loss': 0.6235, 'learning_rate': 0.0001118861340305529, 'epoch': 8.35}

 70%|██████▉   | 19536/28080 [38:37:02<16:48:34,  7.08s/it]
 70%|██████▉   | 19537/28080 [38:37:09<16:50:02,  7.09s/it]
                                                           
{'loss': 0.6224, 'learning_rate': 0.00011186209916407517, 'epoch': 8.35}

 70%|██████▉   | 19537/28080 [38:37:09<16:50:02,  7.09s/it]
 70%|██████▉   | 19538/28080 [38:37:16<16:53:27,  7.12s/it]
                                                           
{'loss': 0.6125, 'learning_rate': 0.00011183806613537977, 'epoch': 8.35}

 70%|██████▉   | 19538/28080 [38:37:16<16:53:27,  7.12s/it]
 70%|██████▉   | 19539/28080 [38:37:23<16:54:16,  7.13s/it]
                                                           
{'loss': 0.5986, 'learning_rate': 0.00011181403494478632, 'epoch': 8.35}

 70%|██████▉   | 19539/28080 [38:37:23<16:54:16,  7.13s/it]
 70%|██████▉   | 19540/28080 [38:37:30<16:52:54,  7.12s/it]
                                                           
{'loss': 0.6135, 'learning_rate': 0.00011179000559261471, 'epoch': 8.35}

 70%|██████▉   | 19540/28080 [38:37:30<16:52:54,  7.12s/it]
 70%|██████▉   | 19541/28080 [38:37:37<16:50:59,  7.10s/it]
                                                           
{'loss': 0.6009, 'learning_rate': 0.00011176597807918435, 'epoch': 8.35}

 70%|██████▉   | 19541/28080 [38:37:37<16:50:59,  7.10s/it]
 70%|██████▉   | 19542/28080 [38:37:44<16:46:47,  7.08s/it]
                                                           
{'loss': 0.6121, 'learning_rate': 0.0001117419524048151, 'epoch': 8.35}

 70%|██████▉   | 19542/28080 [38:37:44<16:46:47,  7.08s/it]
 70%|██████▉   | 19543/28080 [38:37:51<16:46:31,  7.07s/it]
                                                           
{'loss': 0.6039, 'learning_rate': 0.00011171792856982654, 'epoch': 8.35}

 70%|██████▉   | 19543/28080 [38:37:51<16:46:31,  7.07s/it]
 70%|██████▉   | 19544/28080 [38:37:58<16:45:37,  7.07s/it]
                                                           
{'loss': 0.6013, 'learning_rate': 0.00011169390657453823, 'epoch': 8.35}

 70%|██████▉   | 19544/28080 [38:37:58<16:45:37,  7.07s/it]
 70%|██████▉   | 19545/28080 [38:38:05<16:43:41,  7.06s/it]
                                                           
{'loss': 0.619, 'learning_rate': 0.00011166988641926998, 'epoch': 8.35}

 70%|██████▉   | 19545/28080 [38:38:05<16:43:41,  7.06s/it]
 70%|██████▉   | 19546/28080 [38:38:12<16:47:07,  7.08s/it]
                                                           
{'loss': 0.609, 'learning_rate': 0.00011164586810434097, 'epoch': 8.35}

 70%|██████▉   | 19546/28080 [38:38:12<16:47:07,  7.08s/it]
 70%|██████▉   | 19547/28080 [38:38:20<16:46:00,  7.07s/it]
                                                           
{'loss': 0.5955, 'learning_rate': 0.00011162185163007108, 'epoch': 8.35}

 70%|██████▉   | 19547/28080 [38:38:20<16:46:00,  7.07s/it]
 70%|██████▉   | 19548/28080 [38:38:27<16:49:38,  7.10s/it]
                                                           
{'loss': 0.5969, 'learning_rate': 0.00011159783699677958, 'epoch': 8.35}

 70%|██████▉   | 19548/28080 [38:38:27<16:49:38,  7.10s/it]
 70%|██████▉   | 19549/28080 [38:38:34<16:45:38,  7.07s/it]
                                                           
{'loss': 0.6175, 'learning_rate': 0.00011157382420478618, 'epoch': 8.35}

 70%|██████▉   | 19549/28080 [38:38:34<16:45:38,  7.07s/it]
 70%|██████▉   | 19550/28080 [38:38:41<16:48:22,  7.09s/it]
                                                           
{'loss': 0.5986, 'learning_rate': 0.00011154981325441024, 'epoch': 8.35}

 70%|██████▉   | 19550/28080 [38:38:41<16:48:22,  7.09s/it]
 70%|██████▉   | 19551/28080 [38:38:48<16:48:45,  7.10s/it]
                                                           
{'loss': 0.5863, 'learning_rate': 0.00011152580414597122, 'epoch': 8.35}

 70%|██████▉   | 19551/28080 [38:38:48<16:48:45,  7.10s/it]
 70%|██████▉   | 19552/28080 [38:38:55<16:51:37,  7.12s/it]
                                                           
{'loss': 0.6159, 'learning_rate': 0.0001115017968797884, 'epoch': 8.35}

 70%|██████▉   | 19552/28080 [38:38:55<16:51:37,  7.12s/it]
 70%|██████▉   | 19553/28080 [38:39:02<16:45:32,  7.08s/it]
                                                           
{'loss': 0.6117, 'learning_rate': 0.0001114777914561814, 'epoch': 8.35}

 70%|██████▉   | 19553/28080 [38:39:02<16:45:32,  7.08s/it]
 70%|██████▉   | 19554/28080 [38:39:09<16:44:08,  7.07s/it]
                                                           
{'loss': 0.5974, 'learning_rate': 0.00011145378787546947, 'epoch': 8.35}

 70%|██████▉   | 19554/28080 [38:39:09<16:44:08,  7.07s/it]
 70%|██████▉   | 19555/28080 [38:39:16<16:40:12,  7.04s/it]
                                                           
{'loss': 0.6062, 'learning_rate': 0.00011142978613797197, 'epoch': 8.35}

 70%|██████▉   | 19555/28080 [38:39:16<16:40:12,  7.04s/it]
 70%|██████▉   | 19556/28080 [38:39:23<16:39:22,  7.03s/it]
                                                           
{'loss': 0.5894, 'learning_rate': 0.00011140578624400813, 'epoch': 8.35}

 70%|██████▉   | 19556/28080 [38:39:23<16:39:22,  7.03s/it]
 70%|██████▉   | 19557/28080 [38:39:30<16:39:21,  7.04s/it]
                                                           
{'loss': 0.6011, 'learning_rate': 0.00011138178819389741, 'epoch': 8.35}

 70%|██████▉   | 19557/28080 [38:39:30<16:39:21,  7.04s/it]
 70%|██████▉   | 19558/28080 [38:39:37<16:44:06,  7.07s/it]
                                                           
{'loss': 0.59, 'learning_rate': 0.0001113577919879589, 'epoch': 8.35}

 70%|██████▉   | 19558/28080 [38:39:37<16:44:06,  7.07s/it]
 70%|██████▉   | 19559/28080 [38:39:44<16:45:20,  7.08s/it]
                                                           
{'loss': 0.6208, 'learning_rate': 0.00011133379762651203, 'epoch': 8.36}

 70%|██████▉   | 19559/28080 [38:39:44<16:45:20,  7.08s/it]
 70%|██████▉   | 19560/28080 [38:39:51<16:39:46,  7.04s/it]
                                                           
{'loss': 0.642, 'learning_rate': 0.0001113098051098759, 'epoch': 8.36}

 70%|██████▉   | 19560/28080 [38:39:51<16:39:46,  7.04s/it]
 70%|██████▉   | 19561/28080 [38:39:58<16:42:58,  7.06s/it]
                                                           
{'loss': 0.5984, 'learning_rate': 0.00011128581443836977, 'epoch': 8.36}

 70%|██████▉   | 19561/28080 [38:39:58<16:42:58,  7.06s/it]
 70%|██████▉   | 19562/28080 [38:40:06<16:45:19,  7.08s/it]
                                                           
{'loss': 0.6178, 'learning_rate': 0.00011126182561231268, 'epoch': 8.36}

 70%|██████▉   | 19562/28080 [38:40:06<16:45:19,  7.08s/it]
 70%|██████▉   | 19563/28080 [38:40:13<16:45:00,  7.08s/it]
                                                           
{'loss': 0.6244, 'learning_rate': 0.00011123783863202394, 'epoch': 8.36}

 70%|██████▉   | 19563/28080 [38:40:13<16:45:00,  7.08s/it]
 70%|██████▉   | 19564/28080 [38:40:20<16:45:02,  7.08s/it]
                                                           
{'loss': 0.5893, 'learning_rate': 0.00011121385349782262, 'epoch': 8.36}

 70%|██████▉   | 19564/28080 [38:40:20<16:45:02,  7.08s/it]
 70%|██████▉   | 19565/28080 [38:40:27<16:44:12,  7.08s/it]
                                                           
{'loss': 0.6189, 'learning_rate': 0.0001111898702100278, 'epoch': 8.36}

 70%|██████▉   | 19565/28080 [38:40:27<16:44:12,  7.08s/it]
 70%|██████▉   | 19566/28080 [38:40:34<16:41:32,  7.06s/it]
                                                           
{'loss': 0.592, 'learning_rate': 0.00011116588876895848, 'epoch': 8.36}

 70%|██████▉   | 19566/28080 [38:40:34<16:41:32,  7.06s/it]
 70%|██████▉   | 19567/28080 [38:40:41<16:44:17,  7.08s/it]
                                                           
{'loss': 0.6066, 'learning_rate': 0.00011114190917493386, 'epoch': 8.36}

 70%|██████▉   | 19567/28080 [38:40:41<16:44:17,  7.08s/it]
 70%|██████▉   | 19568/28080 [38:40:48<16:45:07,  7.08s/it]
                                                           
{'loss': 0.6069, 'learning_rate': 0.00011111793142827289, 'epoch': 8.36}

 70%|██████▉   | 19568/28080 [38:40:48<16:45:07,  7.08s/it]
 70%|██████▉   | 19569/28080 [38:40:55<16:44:28,  7.08s/it]
                                                           
{'loss': 0.6117, 'learning_rate': 0.00011109395552929455, 'epoch': 8.36}

 70%|██████▉   | 19569/28080 [38:40:55<16:44:28,  7.08s/it]
 70%|██████▉   | 19570/28080 [38:41:02<16:37:21,  7.03s/it]
                                                           
{'loss': 0.6198, 'learning_rate': 0.00011106998147831784, 'epoch': 8.36}

 70%|██████▉   | 19570/28080 [38:41:02<16:37:21,  7.03s/it]
 70%|██████▉   | 19571/28080 [38:41:09<16:36:16,  7.03s/it]
                                                           
{'loss': 0.6268, 'learning_rate': 0.00011104600927566161, 'epoch': 8.36}

 70%|██████▉   | 19571/28080 [38:41:09<16:36:16,  7.03s/it]
 70%|██████▉   | 19572/28080 [38:41:16<16:39:13,  7.05s/it]
                                                           
{'loss': 0.6054, 'learning_rate': 0.00011102203892164497, 'epoch': 8.36}

 70%|██████▉   | 19572/28080 [38:41:16<16:39:13,  7.05s/it]
 70%|██████▉   | 19573/28080 [38:41:23<16:44:21,  7.08s/it]
                                                           
{'loss': 0.6102, 'learning_rate': 0.00011099807041658663, 'epoch': 8.36}

 70%|██████▉   | 19573/28080 [38:41:23<16:44:21,  7.08s/it]
 70%|██████▉   | 19574/28080 [38:41:30<16:45:21,  7.09s/it]
                                                           
{'loss': 0.5905, 'learning_rate': 0.00011097410376080575, 'epoch': 8.36}

 70%|██████▉   | 19574/28080 [38:41:30<16:45:21,  7.09s/it]
 70%|██████▉   | 19575/28080 [38:41:38<16:45:32,  7.09s/it]
                                                           
{'loss': 0.5944, 'learning_rate': 0.0001109501389546208, 'epoch': 8.36}

 70%|██████▉   | 19575/28080 [38:41:38<16:45:32,  7.09s/it]
 70%|██████▉   | 19576/28080 [38:41:45<16:47:56,  7.11s/it]
                                                           
{'loss': 0.616, 'learning_rate': 0.00011092617599835092, 'epoch': 8.36}

 70%|██████▉   | 19576/28080 [38:41:45<16:47:56,  7.11s/it]
 70%|██████▉   | 19577/28080 [38:41:52<16:49:12,  7.12s/it]
                                                           
{'loss': 0.5944, 'learning_rate': 0.0001109022148923147, 'epoch': 8.36}

 70%|██████▉   | 19577/28080 [38:41:52<16:49:12,  7.12s/it]
 70%|██████▉   | 19578/28080 [38:41:59<16:42:05,  7.07s/it]
                                                           
{'loss': 0.6272, 'learning_rate': 0.00011087825563683107, 'epoch': 8.36}

 70%|██████▉   | 19578/28080 [38:41:59<16:42:05,  7.07s/it]
 70%|██████▉   | 19579/28080 [38:42:06<16:43:04,  7.08s/it]
                                                           
{'loss': 0.6115, 'learning_rate': 0.00011085429823221874, 'epoch': 8.36}

 70%|██████▉   | 19579/28080 [38:42:06<16:43:04,  7.08s/it]
 70%|██████▉   | 19580/28080 [38:42:13<16:46:16,  7.10s/it]
                                                           
{'loss': 0.6041, 'learning_rate': 0.00011083034267879644, 'epoch': 8.36}

 70%|██████▉   | 19580/28080 [38:42:13<16:46:16,  7.10s/it]
 70%|██████▉   | 19581/28080 [38:42:20<16:43:50,  7.09s/it]
                                                           
{'loss': 0.6194, 'learning_rate': 0.00011080638897688275, 'epoch': 8.36}

 70%|██████▉   | 19581/28080 [38:42:20<16:43:50,  7.09s/it]
 70%|██████▉   | 19582/28080 [38:42:27<16:48:50,  7.12s/it]
                                                           
{'loss': 0.62, 'learning_rate': 0.00011078243712679654, 'epoch': 8.37}

 70%|██████▉   | 19582/28080 [38:42:27<16:48:50,  7.12s/it]
 70%|██████▉   | 19583/28080 [38:42:34<16:41:31,  7.07s/it]
                                                           
{'loss': 0.6262, 'learning_rate': 0.00011075848712885639, 'epoch': 8.37}

 70%|██████▉   | 19583/28080 [38:42:34<16:41:31,  7.07s/it]
 70%|██████▉   | 19584/28080 [38:42:41<16:41:47,  7.07s/it]
                                                           
{'loss': 0.6118, 'learning_rate': 0.00011073453898338093, 'epoch': 8.37}

 70%|██████▉   | 19584/28080 [38:42:41<16:41:47,  7.07s/it]
 70%|██████▉   | 19585/28080 [38:42:48<16:42:58,  7.08s/it]
                                                           
{'loss': 0.6073, 'learning_rate': 0.00011071059269068867, 'epoch': 8.37}

 70%|██████▉   | 19585/28080 [38:42:48<16:42:58,  7.08s/it]
 70%|██████▉   | 19586/28080 [38:42:56<16:42:50,  7.08s/it]
                                                           
{'loss': 0.6049, 'learning_rate': 0.00011068664825109834, 'epoch': 8.37}

 70%|██████▉   | 19586/28080 [38:42:56<16:42:50,  7.08s/it]
 70%|██████▉   | 19587/28080 [38:43:03<16:42:42,  7.08s/it]
                                                           
{'loss': 0.6065, 'learning_rate': 0.00011066270566492837, 'epoch': 8.37}

 70%|██████▉   | 19587/28080 [38:43:03<16:42:42,  7.08s/it]
 70%|██████▉   | 19588/28080 [38:43:10<16:45:35,  7.10s/it]
                                                           
{'loss': 0.6117, 'learning_rate': 0.00011063876493249753, 'epoch': 8.37}

 70%|██████▉   | 19588/28080 [38:43:10<16:45:35,  7.10s/it]
 70%|██████▉   | 19589/28080 [38:43:17<16:44:03,  7.09s/it]
                                                           
{'loss': 0.6145, 'learning_rate': 0.00011061482605412396, 'epoch': 8.37}

 70%|██████▉   | 19589/28080 [38:43:17<16:44:03,  7.09s/it]
 70%|██████▉   | 19590/28080 [38:43:24<16:39:26,  7.06s/it]
                                                           
{'loss': 0.6256, 'learning_rate': 0.00011059088903012642, 'epoch': 8.37}

 70%|██████▉   | 19590/28080 [38:43:24<16:39:26,  7.06s/it]
 70%|██████▉   | 19591/28080 [38:43:31<16:36:57,  7.05s/it]
                                                           
{'loss': 0.599, 'learning_rate': 0.00011056695386082321, 'epoch': 8.37}

 70%|██████▉   | 19591/28080 [38:43:31<16:36:57,  7.05s/it]
 70%|██████▉   | 19592/28080 [38:43:38<16:43:27,  7.09s/it]
                                                           
{'loss': 0.6045, 'learning_rate': 0.00011054302054653293, 'epoch': 8.37}

 70%|██████▉   | 19592/28080 [38:43:38<16:43:27,  7.09s/it]
 70%|██████▉   | 19593/28080 [38:43:45<16:41:03,  7.08s/it]
                                                           
{'loss': 0.6016, 'learning_rate': 0.00011051908908757396, 'epoch': 8.37}

 70%|██████▉   | 19593/28080 [38:43:45<16:41:03,  7.08s/it]
 70%|██████▉   | 19594/28080 [38:43:52<16:41:16,  7.08s/it]
                                                           
{'loss': 0.5991, 'learning_rate': 0.00011049515948426445, 'epoch': 8.37}

 70%|██████▉   | 19594/28080 [38:43:52<16:41:16,  7.08s/it]
 70%|██████▉   | 19595/28080 [38:43:59<16:42:53,  7.09s/it]
                                                           
{'loss': 0.5975, 'learning_rate': 0.000110471231736923, 'epoch': 8.37}

 70%|██████▉   | 19595/28080 [38:43:59<16:42:53,  7.09s/it]
 70%|██████▉   | 19596/28080 [38:44:06<16:43:10,  7.09s/it]
                                                           
{'loss': 0.6185, 'learning_rate': 0.00011044730584586776, 'epoch': 8.37}

 70%|██████▉   | 19596/28080 [38:44:06<16:43:10,  7.09s/it]
 70%|██████▉   | 19597/28080 [38:44:13<16:42:16,  7.09s/it]
                                                           
{'loss': 0.615, 'learning_rate': 0.00011042338181141728, 'epoch': 8.37}

 70%|██████▉   | 19597/28080 [38:44:13<16:42:16,  7.09s/it]
 70%|██████▉   | 19598/28080 [38:44:21<16:41:36,  7.09s/it]
                                                           
{'loss': 0.6106, 'learning_rate': 0.0001103994596338897, 'epoch': 8.37}

 70%|██████▉   | 19598/28080 [38:44:21<16:41:36,  7.09s/it]
 70%|██████▉   | 19599/28080 [38:44:27<16:34:15,  7.03s/it]
                                                           
{'loss': 0.6147, 'learning_rate': 0.00011037553931360328, 'epoch': 8.37}

 70%|██████▉   | 19599/28080 [38:44:27<16:34:15,  7.03s/it]
 70%|██████▉   | 19600/28080 [38:44:35<16:37:12,  7.06s/it]
                                                           
{'loss': 0.61, 'learning_rate': 0.00011035162085087616, 'epoch': 8.37}

 70%|██████▉   | 19600/28080 [38:44:35<16:37:12,  7.06s/it]
 70%|██████▉   | 19601/28080 [38:44:42<16:41:43,  7.09s/it]
                                                           
{'loss': 0.6196, 'learning_rate': 0.00011032770424602679, 'epoch': 8.37}

 70%|██████▉   | 19601/28080 [38:44:42<16:41:43,  7.09s/it]
 70%|██████▉   | 19602/28080 [38:44:49<16:42:36,  7.10s/it]
                                                           
{'loss': 0.5947, 'learning_rate': 0.0001103037894993732, 'epoch': 8.37}

 70%|██████▉   | 19602/28080 [38:44:49<16:42:36,  7.10s/it]
 70%|██████▉   | 19603/28080 [38:44:56<16:44:54,  7.11s/it]
                                                           
{'loss': 0.5991, 'learning_rate': 0.00011027987661123356, 'epoch': 8.37}

 70%|██████▉   | 19603/28080 [38:44:56<16:44:54,  7.11s/it]
 70%|██████▉   | 19604/28080 [38:45:03<16:37:04,  7.06s/it]
                                                           
{'loss': 0.5954, 'learning_rate': 0.00011025596558192596, 'epoch': 8.37}

 70%|██████▉   | 19604/28080 [38:45:03<16:37:04,  7.06s/it]
 70%|██████▉   | 19605/28080 [38:45:10<16:36:36,  7.06s/it]
                                                           
{'loss': 0.6022, 'learning_rate': 0.00011023205641176865, 'epoch': 8.38}

 70%|██████▉   | 19605/28080 [38:45:10<16:36:36,  7.06s/it]
 70%|██████▉   | 19606/28080 [38:45:17<16:35:30,  7.05s/it]
                                                           
{'loss': 0.6181, 'learning_rate': 0.00011020814910107955, 'epoch': 8.38}

 70%|██████▉   | 19606/28080 [38:45:17<16:35:30,  7.05s/it]
 70%|██████▉   | 19607/28080 [38:45:24<16:36:47,  7.06s/it]
                                                           
{'loss': 0.6105, 'learning_rate': 0.00011018424365017698, 'epoch': 8.38}

 70%|██████▉   | 19607/28080 [38:45:24<16:36:47,  7.06s/it]
 70%|██████▉   | 19608/28080 [38:45:31<16:39:38,  7.08s/it]
                                                           
{'loss': 0.5981, 'learning_rate': 0.00011016034005937863, 'epoch': 8.38}

 70%|██████▉   | 19608/28080 [38:45:31<16:39:38,  7.08s/it]
 70%|██████▉   | 19609/28080 [38:45:38<16:45:27,  7.12s/it]
                                                           
{'loss': 0.6154, 'learning_rate': 0.0001101364383290028, 'epoch': 8.38}

 70%|██████▉   | 19609/28080 [38:45:38<16:45:27,  7.12s/it]
 70%|██████▉   | 19610/28080 [38:45:45<16:41:52,  7.10s/it]
                                                           
{'loss': 0.6009, 'learning_rate': 0.00011011253845936726, 'epoch': 8.38}

 70%|██████▉   | 19610/28080 [38:45:45<16:41:52,  7.10s/it]
 70%|██████▉   | 19611/28080 [38:45:53<16:45:59,  7.13s/it]
                                                           
{'loss': 0.6281, 'learning_rate': 0.00011008864045079017, 'epoch': 8.38}

 70%|██████▉   | 19611/28080 [38:45:53<16:45:59,  7.13s/it]
 70%|██████▉   | 19612/28080 [38:46:00<16:41:46,  7.10s/it]
                                                           
{'loss': 0.6011, 'learning_rate': 0.00011006474430358939, 'epoch': 8.38}

 70%|██████▉   | 19612/28080 [38:46:00<16:41:46,  7.10s/it]
 70%|██████▉   | 19613/28080 [38:46:07<16:39:35,  7.08s/it]
                                                           
{'loss': 0.6179, 'learning_rate': 0.00011004085001808284, 'epoch': 8.38}

 70%|██████▉   | 19613/28080 [38:46:07<16:39:35,  7.08s/it]
 70%|██████▉   | 19614/28080 [38:46:14<16:39:00,  7.08s/it]
                                                           
{'loss': 0.6087, 'learning_rate': 0.00011001695759458827, 'epoch': 8.38}

 70%|██████▉   | 19614/28080 [38:46:14<16:39:00,  7.08s/it]
 70%|██████▉   | 19615/28080 [38:46:21<16:40:32,  7.09s/it]
                                                           
{'loss': 0.6134, 'learning_rate': 0.00010999306703342379, 'epoch': 8.38}

 70%|██████▉   | 19615/28080 [38:46:21<16:40:32,  7.09s/it]
 70%|██████▉   | 19616/28080 [38:46:28<16:40:18,  7.09s/it]
                                                           
{'loss': 0.613, 'learning_rate': 0.00010996917833490708, 'epoch': 8.38}

 70%|██████▉   | 19616/28080 [38:46:28<16:40:18,  7.09s/it]
 70%|██████▉   | 19617/28080 [38:46:35<16:41:18,  7.10s/it]
                                                           
{'loss': 0.5975, 'learning_rate': 0.00010994529149935603, 'epoch': 8.38}

 70%|██████▉   | 19617/28080 [38:46:35<16:41:18,  7.10s/it]
 70%|██████▉   | 19618/28080 [38:46:42<16:46:22,  7.14s/it]
                                                           
{'loss': 0.6052, 'learning_rate': 0.00010992140652708835, 'epoch': 8.38}

 70%|██████▉   | 19618/28080 [38:46:42<16:46:22,  7.14s/it]
 70%|██████▉   | 19619/28080 [38:46:49<16:42:01,  7.11s/it]
                                                           
{'loss': 0.5888, 'learning_rate': 0.00010989752341842177, 'epoch': 8.38}

 70%|██████▉   | 19619/28080 [38:46:49<16:42:01,  7.11s/it]
 70%|██████▉   | 19620/28080 [38:46:56<16:37:08,  7.07s/it]
                                                           
{'loss': 0.5926, 'learning_rate': 0.0001098736421736742, 'epoch': 8.38}

 70%|██████▉   | 19620/28080 [38:46:56<16:37:08,  7.07s/it]
 70%|██████▉   | 19621/28080 [38:47:03<16:38:02,  7.08s/it]
                                                           
{'loss': 0.6178, 'learning_rate': 0.00010984976279316317, 'epoch': 8.38}

 70%|██████▉   | 19621/28080 [38:47:03<16:38:02,  7.08s/it]
 70%|██████▉   | 19622/28080 [38:47:11<16:37:36,  7.08s/it]
                                                           
{'loss': 0.6051, 'learning_rate': 0.00010982588527720666, 'epoch': 8.38}

 70%|██████▉   | 19622/28080 [38:47:11<16:37:36,  7.08s/it]
 70%|██████▉   | 19623/28080 [38:47:18<16:32:25,  7.04s/it]
                                                           
{'loss': 0.617, 'learning_rate': 0.00010980200962612194, 'epoch': 8.38}

 70%|██████▉   | 19623/28080 [38:47:18<16:32:25,  7.04s/it]
 70%|██████▉   | 19624/28080 [38:47:25<16:37:38,  7.08s/it]
                                                           
{'loss': 0.6016, 'learning_rate': 0.00010977813584022692, 'epoch': 8.38}

 70%|██████▉   | 19624/28080 [38:47:25<16:37:38,  7.08s/it]
 70%|██████▉   | 19625/28080 [38:47:32<16:41:26,  7.11s/it]
                                                           
{'loss': 0.619, 'learning_rate': 0.00010975426391983906, 'epoch': 8.38}

 70%|██████▉   | 19625/28080 [38:47:32<16:41:26,  7.11s/it]
 70%|██████▉   | 19626/28080 [38:47:39<16:35:27,  7.06s/it]
                                                           
{'loss': 0.6095, 'learning_rate': 0.00010973039386527614, 'epoch': 8.38}

 70%|██████▉   | 19626/28080 [38:47:39<16:35:27,  7.06s/it]
 70%|██████▉   | 19627/28080 [38:47:46<16:39:52,  7.10s/it]
                                                           
{'loss': 0.6048, 'learning_rate': 0.00010970652567685562, 'epoch': 8.38}

 70%|██████▉   | 19627/28080 [38:47:46<16:39:52,  7.10s/it]
 70%|██████▉   | 19628/28080 [38:47:53<16:39:14,  7.09s/it]
                                                           
{'loss': 0.6027, 'learning_rate': 0.00010968265935489505, 'epoch': 8.38}

 70%|██████▉   | 19628/28080 [38:47:53<16:39:14,  7.09s/it]
 70%|██████▉   | 19629/28080 [38:48:00<16:48:33,  7.16s/it]
                                                           
{'loss': 0.5916, 'learning_rate': 0.00010965879489971184, 'epoch': 8.39}

 70%|██████▉   | 19629/28080 [38:48:00<16:48:33,  7.16s/it]
 70%|██████▉   | 19630/28080 [38:48:07<16:43:35,  7.13s/it]
                                                           
{'loss': 0.6065, 'learning_rate': 0.00010963493231162367, 'epoch': 8.39}

 70%|██████▉   | 19630/28080 [38:48:07<16:43:35,  7.13s/it]
 70%|██████▉   | 19631/28080 [38:48:14<16:38:59,  7.09s/it]
                                                           
{'loss': 0.6126, 'learning_rate': 0.00010961107159094791, 'epoch': 8.39}

 70%|██████▉   | 19631/28080 [38:48:14<16:38:59,  7.09s/it]
 70%|██████▉   | 19632/28080 [38:48:22<16:43:55,  7.13s/it]
                                                           
{'loss': 0.5964, 'learning_rate': 0.00010958721273800201, 'epoch': 8.39}

 70%|██████▉   | 19632/28080 [38:48:22<16:43:55,  7.13s/it]
 70%|██████▉   | 19633/28080 [38:48:29<16:40:43,  7.11s/it]
                                                           
{'loss': 0.6133, 'learning_rate': 0.00010956335575310333, 'epoch': 8.39}

 70%|██████▉   | 19633/28080 [38:48:29<16:40:43,  7.11s/it]
 70%|██████▉   | 19634/28080 [38:48:36<16:40:44,  7.11s/it]
                                                           
{'loss': 0.6047, 'learning_rate': 0.00010953950063656937, 'epoch': 8.39}

 70%|██████▉   | 19634/28080 [38:48:36<16:40:44,  7.11s/it]
 70%|██████▉   | 19635/28080 [38:48:43<16:38:49,  7.10s/it]
                                                           
{'loss': 0.5948, 'learning_rate': 0.00010951564738871739, 'epoch': 8.39}

 70%|██████▉   | 19635/28080 [38:48:43<16:38:49,  7.10s/it]
 70%|██████▉   | 19636/28080 [38:48:50<16:39:23,  7.10s/it]
                                                           
{'loss': 0.5925, 'learning_rate': 0.00010949179600986497, 'epoch': 8.39}

 70%|██████▉   | 19636/28080 [38:48:50<16:39:23,  7.10s/it]
 70%|██████▉   | 19637/28080 [38:48:57<16:41:34,  7.12s/it]
                                                           
{'loss': 0.609, 'learning_rate': 0.00010946794650032904, 'epoch': 8.39}

 70%|██████▉   | 19637/28080 [38:48:57<16:41:34,  7.12s/it]
 70%|██████▉   | 19638/28080 [38:49:04<16:38:01,  7.09s/it]
                                                           
{'loss': 0.599, 'learning_rate': 0.00010944409886042723, 'epoch': 8.39}

 70%|██████▉   | 19638/28080 [38:49:04<16:38:01,  7.09s/it]
 70%|██████▉   | 19639/28080 [38:49:11<16:37:19,  7.09s/it]
                                                           
{'loss': 0.6258, 'learning_rate': 0.00010942025309047657, 'epoch': 8.39}

 70%|██████▉   | 19639/28080 [38:49:11<16:37:19,  7.09s/it]
 70%|██████▉   | 19640/28080 [38:49:18<16:41:01,  7.12s/it]
                                                           
{'loss': 0.6085, 'learning_rate': 0.00010939640919079452, 'epoch': 8.39}

 70%|██████▉   | 19640/28080 [38:49:18<16:41:01,  7.12s/it]
 70%|██████▉   | 19641/28080 [38:49:26<16:41:59,  7.12s/it]
                                                           
{'loss': 0.6191, 'learning_rate': 0.00010937256716169819, 'epoch': 8.39}

 70%|██████▉   | 19641/28080 [38:49:26<16:41:59,  7.12s/it]
 70%|██████▉   | 19642/28080 [38:49:33<16:41:37,  7.12s/it]
                                                           
{'loss': 0.5933, 'learning_rate': 0.00010934872700350476, 'epoch': 8.39}

 70%|██████▉   | 19642/28080 [38:49:33<16:41:37,  7.12s/it]
 70%|██████▉   | 19643/28080 [38:49:40<16:44:00,  7.14s/it]
                                                           
{'loss': 0.5817, 'learning_rate': 0.00010932488871653142, 'epoch': 8.39}

 70%|██████▉   | 19643/28080 [38:49:40<16:44:00,  7.14s/it]
 70%|██████▉   | 19644/28080 [38:49:47<16:43:35,  7.14s/it]
                                                           
{'loss': 0.6069, 'learning_rate': 0.00010930105230109522, 'epoch': 8.39}

 70%|██████▉   | 19644/28080 [38:49:47<16:43:35,  7.14s/it]
 70%|██████▉   | 19645/28080 [38:49:54<16:43:33,  7.14s/it]
                                                           
{'loss': 0.5966, 'learning_rate': 0.00010927721775751348, 'epoch': 8.39}

 70%|██████▉   | 19645/28080 [38:49:54<16:43:33,  7.14s/it]
 70%|██████▉   | 19646/28080 [38:50:01<16:41:44,  7.13s/it]
                                                           
{'loss': 0.6043, 'learning_rate': 0.00010925338508610316, 'epoch': 8.39}

 70%|██████▉   | 19646/28080 [38:50:01<16:41:44,  7.13s/it]
 70%|██████▉   | 19647/28080 [38:50:08<16:37:57,  7.10s/it]
                                                           
{'loss': 0.5919, 'learning_rate': 0.00010922955428718135, 'epoch': 8.39}

 70%|██████▉   | 19647/28080 [38:50:08<16:37:57,  7.10s/it]
 70%|██████▉   | 19648/28080 [38:50:15<16:35:07,  7.08s/it]
                                                           
{'loss': 0.6121, 'learning_rate': 0.00010920572536106502, 'epoch': 8.39}

 70%|██████▉   | 19648/28080 [38:50:15<16:35:07,  7.08s/it]
 70%|██████▉   | 19649/28080 [38:50:22<16:33:36,  7.07s/it]
                                                           
{'loss': 0.5895, 'learning_rate': 0.00010918189830807134, 'epoch': 8.39}

 70%|██████▉   | 19649/28080 [38:50:22<16:33:36,  7.07s/it]
 70%|██████▉   | 19650/28080 [38:50:29<16:33:48,  7.07s/it]
                                                           
{'loss': 0.5951, 'learning_rate': 0.00010915807312851723, 'epoch': 8.39}

 70%|██████▉   | 19650/28080 [38:50:29<16:33:48,  7.07s/it]
 70%|██████▉   | 19651/28080 [38:50:37<16:34:07,  7.08s/it]
                                                           
{'loss': 0.6098, 'learning_rate': 0.00010913424982271966, 'epoch': 8.39}

 70%|██████▉   | 19651/28080 [38:50:37<16:34:07,  7.08s/it]
 70%|██████▉   | 19652/28080 [38:50:44<16:35:45,  7.09s/it]
                                                           
{'loss': 0.6167, 'learning_rate': 0.00010911042839099549, 'epoch': 8.4}

 70%|██████▉   | 19652/28080 [38:50:44<16:35:45,  7.09s/it]
 70%|██████▉   | 19653/28080 [38:50:51<16:38:58,  7.11s/it]
                                                           
{'loss': 0.6233, 'learning_rate': 0.00010908660883366181, 'epoch': 8.4}

 70%|██████▉   | 19653/28080 [38:50:51<16:38:58,  7.11s/it]
 70%|██████▉   | 19654/28080 [38:50:58<16:38:22,  7.11s/it]
                                                           
{'loss': 0.6373, 'learning_rate': 0.00010906279115103534, 'epoch': 8.4}

 70%|██████▉   | 19654/28080 [38:50:58<16:38:22,  7.11s/it]
 70%|██████▉   | 19655/28080 [38:51:05<16:37:28,  7.10s/it]
                                                           
{'loss': 0.6347, 'learning_rate': 0.00010903897534343321, 'epoch': 8.4}

 70%|██████▉   | 19655/28080 [38:51:05<16:37:28,  7.10s/it]
 70%|███████   | 19656/28080 [38:51:12<16:36:55,  7.10s/it]
                                                           
{'loss': 0.6278, 'learning_rate': 0.0001090151614111719, 'epoch': 8.4}

 70%|███████   | 19656/28080 [38:51:12<16:36:55,  7.10s/it]
 70%|███████   | 19657/28080 [38:51:19<16:39:35,  7.12s/it]
                                                           
{'loss': 0.6201, 'learning_rate': 0.00010899134935456854, 'epoch': 8.4}

 70%|███████   | 19657/28080 [38:51:19<16:39:35,  7.12s/it]
 70%|███████   | 19658/28080 [38:51:26<16:36:23,  7.10s/it]
                                                           
{'loss': 0.6015, 'learning_rate': 0.0001089675391739397, 'epoch': 8.4}

 70%|███████   | 19658/28080 [38:51:26<16:36:23,  7.10s/it]
 70%|███████   | 19659/28080 [38:51:33<16:35:43,  7.09s/it]
                                                           
{'loss': 0.5998, 'learning_rate': 0.00010894373086960235, 'epoch': 8.4}

 70%|███████   | 19659/28080 [38:51:33<16:35:43,  7.09s/it]
 70%|███████   | 19660/28080 [38:51:40<16:33:02,  7.08s/it]
                                                           
{'loss': 0.6018, 'learning_rate': 0.00010891992444187315, 'epoch': 8.4}

 70%|███████   | 19660/28080 [38:51:40<16:33:02,  7.08s/it]
 70%|███████   | 19661/28080 [38:51:48<16:31:53,  7.07s/it]
                                                           
{'loss': 0.6054, 'learning_rate': 0.00010889611989106879, 'epoch': 8.4}

 70%|███████   | 19661/28080 [38:51:48<16:31:53,  7.07s/it]
 70%|███████   | 19662/28080 [38:51:55<16:34:22,  7.09s/it]
                                                           
{'loss': 0.6161, 'learning_rate': 0.0001088723172175059, 'epoch': 8.4}

 70%|███████   | 19662/28080 [38:51:55<16:34:22,  7.09s/it]
 70%|███████   | 19663/28080 [38:52:02<16:36:10,  7.10s/it]
                                                           
{'loss': 0.6187, 'learning_rate': 0.00010884851642150135, 'epoch': 8.4}

 70%|███████   | 19663/28080 [38:52:02<16:36:10,  7.10s/it]
 70%|███████   | 19664/28080 [38:52:09<16:37:54,  7.11s/it]
                                                           
{'loss': 0.6067, 'learning_rate': 0.00010882471750337164, 'epoch': 8.4}

 70%|███████   | 19664/28080 [38:52:09<16:37:54,  7.11s/it]
 70%|███████   | 19665/28080 [38:52:16<16:40:57,  7.14s/it]
                                                           
{'loss': 0.6126, 'learning_rate': 0.00010880092046343346, 'epoch': 8.4}

 70%|███████   | 19665/28080 [38:52:16<16:40:57,  7.14s/it]
 70%|███████   | 19666/28080 [38:52:23<16:39:28,  7.13s/it]
                                                           
{'loss': 0.6163, 'learning_rate': 0.00010877712530200324, 'epoch': 8.4}

 70%|███████   | 19666/28080 [38:52:23<16:39:28,  7.13s/it]
 70%|███████   | 19667/28080 [38:52:30<16:39:08,  7.13s/it]
                                                           
{'loss': 0.6053, 'learning_rate': 0.00010875333201939777, 'epoch': 8.4}

 70%|███████   | 19667/28080 [38:52:30<16:39:08,  7.13s/it]
 70%|███████   | 19668/28080 [38:52:37<16:37:15,  7.11s/it]
                                                           
{'loss': 0.6058, 'learning_rate': 0.00010872954061593351, 'epoch': 8.4}

 70%|███████   | 19668/28080 [38:52:37<16:37:15,  7.11s/it]
 70%|███████   | 19669/28080 [38:52:45<16:37:13,  7.11s/it]
                                                           
{'loss': 0.5974, 'learning_rate': 0.00010870575109192699, 'epoch': 8.4}

 70%|███████   | 19669/28080 [38:52:45<16:37:13,  7.11s/it]
 70%|███████   | 19670/28080 [38:52:52<16:34:55,  7.10s/it]
                                                           
{'loss': 0.6084, 'learning_rate': 0.00010868196344769466, 'epoch': 8.4}

 70%|███████   | 19670/28080 [38:52:52<16:34:55,  7.10s/it]
 70%|███████   | 19671/28080 [38:52:59<16:39:25,  7.13s/it]
                                                           
{'loss': 0.5998, 'learning_rate': 0.00010865817768355293, 'epoch': 8.4}

 70%|███████   | 19671/28080 [38:52:59<16:39:25,  7.13s/it]
 70%|███████   | 19672/28080 [38:53:06<16:39:20,  7.13s/it]
                                                           
{'loss': 0.6235, 'learning_rate': 0.00010863439379981843, 'epoch': 8.4}

 70%|███████   | 19672/28080 [38:53:06<16:39:20,  7.13s/it]
 70%|███████   | 19673/28080 [38:53:13<16:37:30,  7.12s/it]
                                                           
{'loss': 0.6054, 'learning_rate': 0.00010861061179680737, 'epoch': 8.4}

 70%|███████   | 19673/28080 [38:53:13<16:37:30,  7.12s/it]
 70%|███████   | 19674/28080 [38:53:20<16:35:13,  7.10s/it]
                                                           
{'loss': 0.6171, 'learning_rate': 0.00010858683167483637, 'epoch': 8.4}

 70%|███████   | 19674/28080 [38:53:20<16:35:13,  7.10s/it]
 70%|███████   | 19675/28080 [38:53:27<16:32:52,  7.09s/it]
                                                           
{'loss': 0.6298, 'learning_rate': 0.00010856305343422168, 'epoch': 8.4}

 70%|███████   | 19675/28080 [38:53:27<16:32:52,  7.09s/it]
 70%|███████   | 19676/28080 [38:53:34<16:35:52,  7.11s/it]
                                                           
{'loss': 0.6144, 'learning_rate': 0.00010853927707527966, 'epoch': 8.41}

 70%|███████   | 19676/28080 [38:53:34<16:35:52,  7.11s/it]
 70%|███████   | 19677/28080 [38:53:41<16:30:53,  7.08s/it]
                                                           
{'loss': 0.5927, 'learning_rate': 0.00010851550259832651, 'epoch': 8.41}

 70%|███████   | 19677/28080 [38:53:41<16:30:53,  7.08s/it]
 70%|███████   | 19678/28080 [38:53:49<16:37:23,  7.12s/it]
                                                           
{'loss': 0.5973, 'learning_rate': 0.00010849173000367876, 'epoch': 8.41}

 70%|███████   | 19678/28080 [38:53:49<16:37:23,  7.12s/it]
 70%|███████   | 19679/28080 [38:53:56<16:38:31,  7.13s/it]
                                                           
{'loss': 0.5907, 'learning_rate': 0.00010846795929165255, 'epoch': 8.41}

 70%|███████   | 19679/28080 [38:53:56<16:38:31,  7.13s/it]
 70%|███████   | 19680/28080 [38:54:03<16:35:39,  7.11s/it]
                                                           
{'loss': 0.5982, 'learning_rate': 0.00010844419046256409, 'epoch': 8.41}

 70%|███████   | 19680/28080 [38:54:03<16:35:39,  7.11s/it]
 70%|███████   | 19681/28080 [38:54:10<16:37:01,  7.12s/it]
                                                           
{'loss': 0.5861, 'learning_rate': 0.00010842042351672959, 'epoch': 8.41}

 70%|███████   | 19681/28080 [38:54:10<16:37:01,  7.12s/it]
 70%|███████   | 19682/28080 [38:54:17<16:37:21,  7.13s/it]
                                                           
{'loss': 0.6027, 'learning_rate': 0.00010839665845446536, 'epoch': 8.41}

 70%|███████   | 19682/28080 [38:54:17<16:37:21,  7.13s/it]
 70%|███████   | 19683/28080 [38:54:24<16:38:14,  7.13s/it]
                                                           
{'loss': 0.6115, 'learning_rate': 0.00010837289527608743, 'epoch': 8.41}

 70%|███████   | 19683/28080 [38:54:24<16:38:14,  7.13s/it]
 70%|███████   | 19684/28080 [38:54:31<16:38:34,  7.14s/it]
                                                           
{'loss': 0.6086, 'learning_rate': 0.00010834913398191221, 'epoch': 8.41}

 70%|███████   | 19684/28080 [38:54:31<16:38:34,  7.14s/it]
 70%|███████   | 19685/28080 [38:54:38<16:38:10,  7.13s/it]
                                                           
{'loss': 0.5986, 'learning_rate': 0.00010832537457225545, 'epoch': 8.41}

 70%|███████   | 19685/28080 [38:54:38<16:38:10,  7.13s/it]
 70%|███████   | 19686/28080 [38:54:46<16:38:27,  7.14s/it]
                                                           
{'loss': 0.6282, 'learning_rate': 0.0001083016170474335, 'epoch': 8.41}

 70%|███████   | 19686/28080 [38:54:46<16:38:27,  7.14s/it]
 70%|███████   | 19687/28080 [38:54:53<16:39:43,  7.15s/it]
                                                           
{'loss': 0.6206, 'learning_rate': 0.00010827786140776225, 'epoch': 8.41}

 70%|███████   | 19687/28080 [38:54:53<16:39:43,  7.15s/it]
 70%|███████   | 19688/28080 [38:55:00<16:35:07,  7.11s/it]
                                                           
{'loss': 0.6065, 'learning_rate': 0.00010825410765355795, 'epoch': 8.41}

 70%|███████   | 19688/28080 [38:55:00<16:35:07,  7.11s/it]
 70%|███████   | 19689/28080 [38:55:07<16:40:07,  7.15s/it]
                                                           
{'loss': 0.5908, 'learning_rate': 0.00010823035578513654, 'epoch': 8.41}

 70%|███████   | 19689/28080 [38:55:07<16:40:07,  7.15s/it]
 70%|███████   | 19690/28080 [38:55:14<16:35:12,  7.12s/it]
                                                           
{'loss': 0.6216, 'learning_rate': 0.00010820660580281397, 'epoch': 8.41}

 70%|███████   | 19690/28080 [38:55:14<16:35:12,  7.12s/it]
 70%|███████   | 19691/28080 [38:55:21<16:30:56,  7.09s/it]
                                                           
{'loss': 0.6018, 'learning_rate': 0.00010818285770690614, 'epoch': 8.41}

 70%|███████   | 19691/28080 [38:55:21<16:30:56,  7.09s/it]
 70%|███████   | 19692/28080 [38:55:28<16:28:13,  7.07s/it]
                                                           
{'loss': 0.6052, 'learning_rate': 0.00010815911149772917, 'epoch': 8.41}

 70%|███████   | 19692/28080 [38:55:28<16:28:13,  7.07s/it]
 70%|███████   | 19693/28080 [38:55:35<16:29:05,  7.08s/it]
                                                           
{'loss': 0.6152, 'learning_rate': 0.00010813536717559888, 'epoch': 8.41}

 70%|███████   | 19693/28080 [38:55:35<16:29:05,  7.08s/it]
 70%|███████   | 19694/28080 [38:55:42<16:26:53,  7.06s/it]
                                                           
{'loss': 0.6291, 'learning_rate': 0.00010811162474083119, 'epoch': 8.41}

 70%|███████   | 19694/28080 [38:55:42<16:26:53,  7.06s/it]
 70%|███████   | 19695/28080 [38:55:49<16:26:48,  7.06s/it]
                                                           
{'loss': 0.6153, 'learning_rate': 0.00010808788419374197, 'epoch': 8.41}

 70%|███████   | 19695/28080 [38:55:49<16:26:48,  7.06s/it]
 70%|███████   | 19696/28080 [38:55:56<16:27:33,  7.07s/it]
                                                           
{'loss': 0.5861, 'learning_rate': 0.00010806414553464694, 'epoch': 8.41}

 70%|███████   | 19696/28080 [38:55:56<16:27:33,  7.07s/it]
 70%|███████   | 19697/28080 [38:56:03<16:28:00,  7.07s/it]
                                                           
{'loss': 0.6064, 'learning_rate': 0.00010804040876386212, 'epoch': 8.41}

 70%|███████   | 19697/28080 [38:56:03<16:28:00,  7.07s/it]
 70%|███████   | 19698/28080 [38:56:11<16:31:55,  7.10s/it]
                                                           
{'loss': 0.6258, 'learning_rate': 0.00010801667388170322, 'epoch': 8.41}

 70%|███████   | 19698/28080 [38:56:11<16:31:55,  7.10s/it]
 70%|███████   | 19699/28080 [38:56:18<16:34:28,  7.12s/it]
                                                           
{'loss': 0.608, 'learning_rate': 0.00010799294088848598, 'epoch': 8.42}

 70%|███████   | 19699/28080 [38:56:18<16:34:28,  7.12s/it]
 70%|███████   | 19700/28080 [38:56:25<16:30:29,  7.09s/it]
                                                           
{'loss': 0.6358, 'learning_rate': 0.00010796920978452609, 'epoch': 8.42}

 70%|███████   | 19700/28080 [38:56:25<16:30:29,  7.09s/it]
 70%|███████   | 19701/28080 [38:56:32<16:30:45,  7.09s/it]
                                                           
{'loss': 0.6054, 'learning_rate': 0.00010794548057013943, 'epoch': 8.42}

 70%|███████   | 19701/28080 [38:56:32<16:30:45,  7.09s/it]
 70%|███████   | 19702/28080 [38:56:39<16:26:26,  7.06s/it]
                                                           
{'loss': 0.6172, 'learning_rate': 0.00010792175324564149, 'epoch': 8.42}

 70%|███████   | 19702/28080 [38:56:39<16:26:26,  7.06s/it]
 70%|███████   | 19703/28080 [38:56:46<16:30:19,  7.09s/it]
                                                           
{'loss': 0.5934, 'learning_rate': 0.00010789802781134825, 'epoch': 8.42}

 70%|███████   | 19703/28080 [38:56:46<16:30:19,  7.09s/it]
 70%|███████   | 19704/28080 [38:56:53<16:30:52,  7.10s/it]
                                                           
{'loss': 0.5969, 'learning_rate': 0.00010787430426757494, 'epoch': 8.42}

 70%|███████   | 19704/28080 [38:56:53<16:30:52,  7.10s/it]
 70%|███████   | 19705/28080 [38:57:00<16:31:19,  7.10s/it]
                                                           
{'loss': 0.6023, 'learning_rate': 0.00010785058261463752, 'epoch': 8.42}

 70%|███████   | 19705/28080 [38:57:00<16:31:19,  7.10s/it]
 70%|███████   | 19706/28080 [38:57:07<16:32:58,  7.11s/it]
                                                           
{'loss': 0.6011, 'learning_rate': 0.00010782686285285131, 'epoch': 8.42}

 70%|███████   | 19706/28080 [38:57:07<16:32:58,  7.11s/it]
 70%|███████   | 19707/28080 [38:57:15<16:32:06,  7.11s/it]
                                                           
{'loss': 0.6111, 'learning_rate': 0.00010780314498253216, 'epoch': 8.42}

 70%|███████   | 19707/28080 [38:57:15<16:32:06,  7.11s/it]
 70%|███████   | 19708/28080 [38:57:22<16:34:44,  7.13s/it]
                                                           
{'loss': 0.6235, 'learning_rate': 0.00010777942900399545, 'epoch': 8.42}

 70%|███████   | 19708/28080 [38:57:22<16:34:44,  7.13s/it]
 70%|███████   | 19709/28080 [38:57:29<16:32:30,  7.11s/it]
                                                           
{'loss': 0.6079, 'learning_rate': 0.0001077557149175567, 'epoch': 8.42}

 70%|███████   | 19709/28080 [38:57:29<16:32:30,  7.11s/it]
 70%|███████   | 19710/28080 [38:57:36<16:31:18,  7.11s/it]
                                                           
{'loss': 0.6084, 'learning_rate': 0.00010773200272353134, 'epoch': 8.42}

 70%|███████   | 19710/28080 [38:57:36<16:31:18,  7.11s/it]
 70%|███████   | 19711/28080 [38:57:43<16:27:29,  7.08s/it]
                                                           
{'loss': 0.6008, 'learning_rate': 0.000107708292422235, 'epoch': 8.42}

 70%|███████   | 19711/28080 [38:57:43<16:27:29,  7.08s/it]
 70%|███████   | 19712/28080 [38:57:50<16:27:11,  7.08s/it]
                                                           
{'loss': 0.6062, 'learning_rate': 0.00010768458401398307, 'epoch': 8.42}

 70%|███████   | 19712/28080 [38:57:50<16:27:11,  7.08s/it]
 70%|███████   | 19713/28080 [38:57:57<16:31:14,  7.11s/it]
                                                           
{'loss': 0.6066, 'learning_rate': 0.0001076608774990909, 'epoch': 8.42}

 70%|███████   | 19713/28080 [38:57:57<16:31:14,  7.11s/it]
 70%|███████   | 19714/28080 [38:58:04<16:26:36,  7.08s/it]
                                                           
{'loss': 0.6009, 'learning_rate': 0.00010763717287787381, 'epoch': 8.42}

 70%|███████   | 19714/28080 [38:58:04<16:26:36,  7.08s/it]
 70%|███████   | 19715/28080 [38:58:11<16:27:12,  7.08s/it]
                                                           
{'loss': 0.6001, 'learning_rate': 0.00010761347015064738, 'epoch': 8.42}

 70%|███████   | 19715/28080 [38:58:11<16:27:12,  7.08s/it]
 70%|███████   | 19716/28080 [38:58:18<16:25:34,  7.07s/it]
                                                           
{'loss': 0.623, 'learning_rate': 0.00010758976931772674, 'epoch': 8.42}

 70%|███████   | 19716/28080 [38:58:18<16:25:34,  7.07s/it]
 70%|███████   | 19717/28080 [38:58:25<16:24:32,  7.06s/it]
                                                           
{'loss': 0.6162, 'learning_rate': 0.00010756607037942747, 'epoch': 8.42}

 70%|███████   | 19717/28080 [38:58:25<16:24:32,  7.06s/it]
 70%|███████   | 19718/28080 [38:58:32<16:22:34,  7.05s/it]
                                                           
{'loss': 0.6127, 'learning_rate': 0.00010754237333606461, 'epoch': 8.42}

 70%|███████   | 19718/28080 [38:58:32<16:22:34,  7.05s/it]
 70%|███████   | 19719/28080 [38:58:40<16:26:26,  7.08s/it]
                                                           
{'loss': 0.6181, 'learning_rate': 0.00010751867818795344, 'epoch': 8.42}

 70%|███████   | 19719/28080 [38:58:40<16:26:26,  7.08s/it]
 70%|███████   | 19720/28080 [38:58:47<16:26:15,  7.08s/it]
                                                           
{'loss': 0.6124, 'learning_rate': 0.00010749498493540935, 'epoch': 8.42}

 70%|███████   | 19720/28080 [38:58:47<16:26:15,  7.08s/it]
 70%|███████   | 19721/28080 [38:58:54<16:26:35,  7.08s/it]
                                                           
{'loss': 0.6001, 'learning_rate': 0.00010747129357874736, 'epoch': 8.42}

 70%|███████   | 19721/28080 [38:58:54<16:26:35,  7.08s/it]
 70%|███████   | 19722/28080 [38:59:01<16:24:56,  7.07s/it]
                                                           
{'loss': 0.6131, 'learning_rate': 0.00010744760411828285, 'epoch': 8.43}

 70%|███████   | 19722/28080 [38:59:01<16:24:56,  7.07s/it]
 70%|███████   | 19723/28080 [38:59:08<16:28:54,  7.10s/it]
                                                           
{'loss': 0.6238, 'learning_rate': 0.00010742391655433096, 'epoch': 8.43}

 70%|███████   | 19723/28080 [38:59:08<16:28:54,  7.10s/it]
 70%|███████   | 19724/28080 [38:59:15<16:36:14,  7.15s/it]
                                                           
{'loss': 0.6101, 'learning_rate': 0.00010740023088720671, 'epoch': 8.43}

 70%|███████   | 19724/28080 [38:59:15<16:36:14,  7.15s/it]
 70%|███████   | 19725/28080 [38:59:22<16:31:47,  7.12s/it]
                                                           
{'loss': 0.5942, 'learning_rate': 0.00010737654711722522, 'epoch': 8.43}

 70%|███████   | 19725/28080 [38:59:22<16:31:47,  7.12s/it]
 70%|███████   | 19726/28080 [38:59:29<16:30:48,  7.12s/it]
                                                           
{'loss': 0.6006, 'learning_rate': 0.00010735286524470173, 'epoch': 8.43}

 70%|███████   | 19726/28080 [38:59:29<16:30:48,  7.12s/it]
 70%|███████   | 19727/28080 [38:59:36<16:29:47,  7.11s/it]
                                                           
{'loss': 0.6022, 'learning_rate': 0.0001073291852699512, 'epoch': 8.43}

 70%|███████   | 19727/28080 [38:59:36<16:29:47,  7.11s/it]
 70%|███████   | 19728/28080 [38:59:44<16:31:11,  7.12s/it]
                                                           
{'loss': 0.6181, 'learning_rate': 0.00010730550719328866, 'epoch': 8.43}

 70%|███████   | 19728/28080 [38:59:44<16:31:11,  7.12s/it]
 70%|███████   | 19729/28080 [38:59:51<16:28:22,  7.10s/it]
                                                           
{'loss': 0.6184, 'learning_rate': 0.00010728183101502905, 'epoch': 8.43}

 70%|███████   | 19729/28080 [38:59:51<16:28:22,  7.10s/it]
 70%|███████   | 19730/28080 [38:59:58<16:24:30,  7.07s/it]
                                                           
{'loss': 0.6039, 'learning_rate': 0.00010725815673548755, 'epoch': 8.43}

 70%|███████   | 19730/28080 [38:59:58<16:24:30,  7.07s/it]
 70%|███████   | 19731/28080 [39:00:05<16:24:35,  7.08s/it]
                                                           
{'loss': 0.6215, 'learning_rate': 0.00010723448435497901, 'epoch': 8.43}

 70%|███████   | 19731/28080 [39:00:05<16:24:35,  7.08s/it]
 70%|███████   | 19732/28080 [39:00:12<16:28:17,  7.10s/it]
                                                           
{'loss': 0.6206, 'learning_rate': 0.00010721081387381837, 'epoch': 8.43}

 70%|███████   | 19732/28080 [39:00:12<16:28:17,  7.10s/it]
 70%|███████   | 19733/28080 [39:00:19<16:22:12,  7.06s/it]
                                                           
{'loss': 0.6246, 'learning_rate': 0.00010718714529232043, 'epoch': 8.43}

 70%|███████   | 19733/28080 [39:00:19<16:22:12,  7.06s/it]
 70%|███████   | 19734/28080 [39:00:26<16:22:14,  7.06s/it]
                                                           
{'loss': 0.6158, 'learning_rate': 0.0001071634786108003, 'epoch': 8.43}

 70%|███████   | 19734/28080 [39:00:26<16:22:14,  7.06s/it]
 70%|███████   | 19735/28080 [39:00:33<16:28:23,  7.11s/it]
                                                           
{'loss': 0.6009, 'learning_rate': 0.00010713981382957267, 'epoch': 8.43}

 70%|███████   | 19735/28080 [39:00:33<16:28:23,  7.11s/it]
 70%|███████   | 19736/28080 [39:00:40<16:29:34,  7.12s/it]
                                                           
{'loss': 0.585, 'learning_rate': 0.0001071161509489525, 'epoch': 8.43}

 70%|███████   | 19736/28080 [39:00:40<16:29:34,  7.12s/it]
 70%|███████   | 19737/28080 [39:00:47<16:26:47,  7.10s/it]
                                                           
{'loss': 0.6224, 'learning_rate': 0.00010709248996925452, 'epoch': 8.43}

 70%|███████   | 19737/28080 [39:00:47<16:26:47,  7.10s/it]
 70%|███████   | 19738/28080 [39:00:54<16:23:48,  7.08s/it]
                                                           
{'loss': 0.622, 'learning_rate': 0.00010706883089079356, 'epoch': 8.43}

 70%|███████   | 19738/28080 [39:00:54<16:23:48,  7.08s/it]
 70%|███████   | 19739/28080 [39:01:01<16:26:10,  7.09s/it]
                                                           
{'loss': 0.6104, 'learning_rate': 0.00010704517371388425, 'epoch': 8.43}

 70%|███████   | 19739/28080 [39:01:01<16:26:10,  7.09s/it]
 70%|███████   | 19740/28080 [39:01:09<16:29:21,  7.12s/it]
                                                           
{'loss': 0.5928, 'learning_rate': 0.0001070215184388415, 'epoch': 8.43}

 70%|███████   | 19740/28080 [39:01:09<16:29:21,  7.12s/it]
 70%|███████   | 19741/28080 [39:01:16<16:29:37,  7.12s/it]
                                                           
{'loss': 0.6095, 'learning_rate': 0.00010699786506597997, 'epoch': 8.43}

 70%|███████   | 19741/28080 [39:01:16<16:29:37,  7.12s/it]
 70%|███████   | 19742/28080 [39:01:23<16:24:48,  7.09s/it]
                                                           
{'loss': 0.6009, 'learning_rate': 0.0001069742135956143, 'epoch': 8.43}

 70%|███████   | 19742/28080 [39:01:23<16:24:48,  7.09s/it]
 70%|███████   | 19743/28080 [39:01:30<16:22:55,  7.07s/it]
                                                           
{'loss': 0.6149, 'learning_rate': 0.0001069505640280592, 'epoch': 8.43}

 70%|███████   | 19743/28080 [39:01:30<16:22:55,  7.07s/it]
 70%|███████   | 19744/28080 [39:01:37<16:21:52,  7.07s/it]
                                                           
{'loss': 0.5985, 'learning_rate': 0.00010692691636362914, 'epoch': 8.43}

 70%|███████   | 19744/28080 [39:01:37<16:21:52,  7.07s/it]
 70%|███████   | 19745/28080 [39:01:44<16:22:47,  7.07s/it]
                                                           
{'loss': 0.6261, 'learning_rate': 0.00010690327060263896, 'epoch': 8.43}

 70%|███████   | 19745/28080 [39:01:44<16:22:47,  7.07s/it]
 70%|███████   | 19746/28080 [39:01:51<16:28:46,  7.12s/it]
                                                           
{'loss': 0.6191, 'learning_rate': 0.00010687962674540314, 'epoch': 8.44}

 70%|███████   | 19746/28080 [39:01:51<16:28:46,  7.12s/it]
 70%|███████   | 19747/28080 [39:01:58<16:31:39,  7.14s/it]
                                                           
{'loss': 0.5857, 'learning_rate': 0.00010685598479223624, 'epoch': 8.44}

 70%|███████   | 19747/28080 [39:01:58<16:31:39,  7.14s/it]
 70%|███████   | 19748/28080 [39:02:05<16:26:13,  7.10s/it]
                                                           
{'loss': 0.5895, 'learning_rate': 0.00010683234474345268, 'epoch': 8.44}

 70%|███████   | 19748/28080 [39:02:05<16:26:13,  7.10s/it]
 70%|███████   | 19749/28080 [39:02:13<16:29:09,  7.12s/it]
                                                           
{'loss': 0.5954, 'learning_rate': 0.0001068087065993672, 'epoch': 8.44}

 70%|███████   | 19749/28080 [39:02:13<16:29:09,  7.12s/it]
 70%|███████   | 19750/28080 [39:02:20<16:25:59,  7.10s/it]
                                                           
{'loss': 0.5949, 'learning_rate': 0.00010678507036029406, 'epoch': 8.44}

 70%|███████   | 19750/28080 [39:02:20<16:25:59,  7.10s/it]
 70%|███████   | 19751/28080 [39:02:27<16:17:06,  7.04s/it]
                                                           
{'loss': 0.6253, 'learning_rate': 0.00010676143602654797, 'epoch': 8.44}

 70%|███████   | 19751/28080 [39:02:27<16:17:06,  7.04s/it]
 70%|███████   | 19752/28080 [39:02:34<16:18:28,  7.05s/it]
                                                           
{'loss': 0.6025, 'learning_rate': 0.00010673780359844304, 'epoch': 8.44}

 70%|███████   | 19752/28080 [39:02:34<16:18:28,  7.05s/it]
 70%|███████   | 19753/28080 [39:02:41<16:21:29,  7.07s/it]
                                                           
{'loss': 0.6027, 'learning_rate': 0.00010671417307629392, 'epoch': 8.44}

 70%|███████   | 19753/28080 [39:02:41<16:21:29,  7.07s/it]
 70%|███████   | 19754/28080 [39:02:48<16:19:53,  7.06s/it]
                                                           
{'loss': 0.6101, 'learning_rate': 0.00010669054446041482, 'epoch': 8.44}

 70%|███████   | 19754/28080 [39:02:48<16:19:53,  7.06s/it]
 70%|███████   | 19755/28080 [39:02:55<16:23:31,  7.09s/it]
                                                           
{'loss': 0.6238, 'learning_rate': 0.00010666691775112026, 'epoch': 8.44}

 70%|███████   | 19755/28080 [39:02:55<16:23:31,  7.09s/it]
 70%|███████   | 19756/28080 [39:03:02<16:23:12,  7.09s/it]
                                                           
{'loss': 0.6055, 'learning_rate': 0.00010664329294872451, 'epoch': 8.44}

 70%|███████   | 19756/28080 [39:03:02<16:23:12,  7.09s/it]
 70%|███████   | 19757/28080 [39:03:09<16:24:38,  7.10s/it]
                                                           
{'loss': 0.6058, 'learning_rate': 0.00010661967005354184, 'epoch': 8.44}

 70%|███████   | 19757/28080 [39:03:09<16:24:38,  7.10s/it]
 70%|███████   | 19758/28080 [39:03:16<16:27:31,  7.12s/it]
                                                           
{'loss': 0.6187, 'learning_rate': 0.00010659604906588647, 'epoch': 8.44}

 70%|███████   | 19758/28080 [39:03:16<16:27:31,  7.12s/it]
 70%|███████   | 19759/28080 [39:03:23<16:27:40,  7.12s/it]
                                                           
{'loss': 0.5864, 'learning_rate': 0.00010657242998607281, 'epoch': 8.44}

 70%|███████   | 19759/28080 [39:03:23<16:27:40,  7.12s/it]
 70%|███████   | 19760/28080 [39:03:31<16:27:09,  7.12s/it]
                                                           
{'loss': 0.6037, 'learning_rate': 0.00010654881281441497, 'epoch': 8.44}

 70%|███████   | 19760/28080 [39:03:31<16:27:09,  7.12s/it]
 70%|███████   | 19761/28080 [39:03:38<16:22:59,  7.09s/it]
                                                           
{'loss': 0.6151, 'learning_rate': 0.00010652519755122722, 'epoch': 8.44}

 70%|███████   | 19761/28080 [39:03:38<16:22:59,  7.09s/it]
 70%|███████   | 19762/28080 [39:03:45<16:24:03,  7.10s/it]
                                                           
{'loss': 0.6041, 'learning_rate': 0.00010650158419682362, 'epoch': 8.44}

 70%|███████   | 19762/28080 [39:03:45<16:24:03,  7.10s/it]
 70%|███████   | 19763/28080 [39:03:52<16:22:47,  7.09s/it]
                                                           
{'loss': 0.5919, 'learning_rate': 0.00010647797275151846, 'epoch': 8.44}

 70%|███████   | 19763/28080 [39:03:52<16:22:47,  7.09s/it]
 70%|███████   | 19764/28080 [39:03:59<16:23:52,  7.10s/it]
                                                           
{'loss': 0.602, 'learning_rate': 0.00010645436321562574, 'epoch': 8.44}

 70%|███████   | 19764/28080 [39:03:59<16:23:52,  7.10s/it]
 70%|███████   | 19765/28080 [39:04:06<16:20:35,  7.08s/it]
                                                           
{'loss': 0.6185, 'learning_rate': 0.00010643075558945981, 'epoch': 8.44}

 70%|███████   | 19765/28080 [39:04:06<16:20:35,  7.08s/it]
 70%|███████   | 19766/28080 [39:04:13<16:20:35,  7.08s/it]
                                                           
{'loss': 0.6008, 'learning_rate': 0.00010640714987333439, 'epoch': 8.44}

 70%|███████   | 19766/28080 [39:04:13<16:20:35,  7.08s/it]
 70%|███████   | 19767/28080 [39:04:20<16:20:25,  7.08s/it]
                                                           
{'loss': 0.6061, 'learning_rate': 0.00010638354606756378, 'epoch': 8.44}

 70%|███████   | 19767/28080 [39:04:20<16:20:25,  7.08s/it]
 70%|███████   | 19768/28080 [39:04:27<16:16:42,  7.05s/it]
                                                           
{'loss': 0.6205, 'learning_rate': 0.00010635994417246195, 'epoch': 8.44}

 70%|███████   | 19768/28080 [39:04:27<16:16:42,  7.05s/it]
 70%|███████   | 19769/28080 [39:04:34<16:13:15,  7.03s/it]
                                                           
{'loss': 0.6172, 'learning_rate': 0.00010633634418834276, 'epoch': 8.45}

 70%|███████   | 19769/28080 [39:04:34<16:13:15,  7.03s/it]
 70%|███████   | 19770/28080 [39:04:41<16:07:15,  6.98s/it]
                                                           
{'loss': 0.615, 'learning_rate': 0.0001063127461155205, 'epoch': 8.45}

 70%|███████   | 19770/28080 [39:04:41<16:07:15,  6.98s/it]
 70%|███████   | 19771/28080 [39:04:48<16:16:25,  7.05s/it]
                                                           
{'loss': 0.5955, 'learning_rate': 0.00010628914995430872, 'epoch': 8.45}

 70%|███████   | 19771/28080 [39:04:48<16:16:25,  7.05s/it]
 70%|███████   | 19772/28080 [39:04:55<16:19:07,  7.07s/it]
                                                           
{'loss': 0.6125, 'learning_rate': 0.00010626555570502164, 'epoch': 8.45}

 70%|███████   | 19772/28080 [39:04:55<16:19:07,  7.07s/it]
 70%|███████   | 19773/28080 [39:05:02<16:21:38,  7.09s/it]
                                                           
{'loss': 0.6204, 'learning_rate': 0.00010624196336797299, 'epoch': 8.45}

 70%|███████   | 19773/28080 [39:05:02<16:21:38,  7.09s/it]
 70%|███████   | 19774/28080 [39:05:09<16:23:37,  7.11s/it]
                                                           
{'loss': 0.5879, 'learning_rate': 0.00010621837294347678, 'epoch': 8.45}

 70%|███████   | 19774/28080 [39:05:09<16:23:37,  7.11s/it]
 70%|███████   | 19775/28080 [39:05:17<16:22:58,  7.10s/it]
                                                           
{'loss': 0.5896, 'learning_rate': 0.00010619478443184677, 'epoch': 8.45}

 70%|███████   | 19775/28080 [39:05:17<16:22:58,  7.10s/it]
 70%|███████   | 19776/28080 [39:05:24<16:21:45,  7.09s/it]
                                                           
{'loss': 0.6007, 'learning_rate': 0.00010617119783339682, 'epoch': 8.45}

 70%|███████   | 19776/28080 [39:05:24<16:21:45,  7.09s/it]
 70%|███████   | 19777/28080 [39:05:31<16:19:27,  7.08s/it]
                                                           
{'loss': 0.6084, 'learning_rate': 0.00010614761314844063, 'epoch': 8.45}

 70%|███████   | 19777/28080 [39:05:31<16:19:27,  7.08s/it]
 70%|███████   | 19778/28080 [39:05:38<16:21:05,  7.09s/it]
                                                           
{'loss': 0.6135, 'learning_rate': 0.0001061240303772921, 'epoch': 8.45}

 70%|███████   | 19778/28080 [39:05:38<16:21:05,  7.09s/it]
 70%|███████   | 19779/28080 [39:05:45<16:21:39,  7.10s/it]
                                                           
{'loss': 0.5947, 'learning_rate': 0.00010610044952026493, 'epoch': 8.45}

 70%|███████   | 19779/28080 [39:05:45<16:21:39,  7.10s/it]
 70%|███████   | 19780/28080 [39:05:52<16:24:23,  7.12s/it]
                                                           
{'loss': 0.609, 'learning_rate': 0.00010607687057767282, 'epoch': 8.45}

 70%|███████   | 19780/28080 [39:05:52<16:24:23,  7.12s/it]
 70%|███████   | 19781/28080 [39:05:59<16:22:31,  7.10s/it]
                                                           
{'loss': 0.6111, 'learning_rate': 0.0001060532935498294, 'epoch': 8.45}

 70%|███████   | 19781/28080 [39:05:59<16:22:31,  7.10s/it]
 70%|███████   | 19782/28080 [39:06:06<16:20:51,  7.09s/it]
                                                           
{'loss': 0.6147, 'learning_rate': 0.00010602971843704848, 'epoch': 8.45}

 70%|███████   | 19782/28080 [39:06:06<16:20:51,  7.09s/it]
 70%|███████   | 19783/28080 [39:06:13<16:22:10,  7.10s/it]
                                                           
{'loss': 0.6152, 'learning_rate': 0.00010600614523964353, 'epoch': 8.45}

 70%|███████   | 19783/28080 [39:06:13<16:22:10,  7.10s/it]
 70%|███████   | 19784/28080 [39:06:20<16:24:06,  7.12s/it]
                                                           
{'loss': 0.62, 'learning_rate': 0.00010598257395792837, 'epoch': 8.45}

 70%|███████   | 19784/28080 [39:06:20<16:24:06,  7.12s/it]
 70%|███████   | 19785/28080 [39:06:28<16:22:54,  7.11s/it]
                                                           
{'loss': 0.6142, 'learning_rate': 0.00010595900459221649, 'epoch': 8.45}

 70%|███████   | 19785/28080 [39:06:28<16:22:54,  7.11s/it]
 70%|███████   | 19786/28080 [39:06:35<16:22:19,  7.11s/it]
                                                           
{'loss': 0.6137, 'learning_rate': 0.00010593543714282147, 'epoch': 8.45}

 70%|███████   | 19786/28080 [39:06:35<16:22:19,  7.11s/it]
 70%|███████   | 19787/28080 [39:06:42<16:25:39,  7.13s/it]
                                                           
{'loss': 0.6118, 'learning_rate': 0.00010591187161005672, 'epoch': 8.45}

 70%|███████   | 19787/28080 [39:06:42<16:25:39,  7.13s/it]
 70%|███████   | 19788/28080 [39:06:49<16:26:39,  7.14s/it]
                                                           
{'loss': 0.6069, 'learning_rate': 0.00010588830799423599, 'epoch': 8.45}

 70%|███████   | 19788/28080 [39:06:49<16:26:39,  7.14s/it]
 70%|███████   | 19789/28080 [39:06:56<16:25:36,  7.13s/it]
                                                           
{'loss': 0.6183, 'learning_rate': 0.00010586474629567261, 'epoch': 8.45}

 70%|███████   | 19789/28080 [39:06:56<16:25:36,  7.13s/it]
 70%|███████   | 19790/28080 [39:07:03<16:22:20,  7.11s/it]
                                                           
{'loss': 0.5921, 'learning_rate': 0.00010584118651468012, 'epoch': 8.45}

 70%|███████   | 19790/28080 [39:07:03<16:22:20,  7.11s/it]
 70%|███████   | 19791/28080 [39:07:10<16:22:52,  7.11s/it]
                                                           
{'loss': 0.6325, 'learning_rate': 0.00010581762865157182, 'epoch': 8.45}

 70%|███████   | 19791/28080 [39:07:10<16:22:52,  7.11s/it]
 70%|███████   | 19792/28080 [39:07:17<16:14:43,  7.06s/it]
                                                           
{'loss': 0.63, 'learning_rate': 0.0001057940727066613, 'epoch': 8.45}

 70%|███████   | 19792/28080 [39:07:17<16:14:43,  7.06s/it]
 70%|███████   | 19793/28080 [39:07:24<16:12:44,  7.04s/it]
                                                           
{'loss': 0.6, 'learning_rate': 0.0001057705186802619, 'epoch': 8.46}

 70%|███████   | 19793/28080 [39:07:24<16:12:44,  7.04s/it]
 70%|███████   | 19794/28080 [39:07:31<16:12:31,  7.04s/it]
                                                           
{'loss': 0.6084, 'learning_rate': 0.00010574696657268695, 'epoch': 8.46}

 70%|███████   | 19794/28080 [39:07:31<16:12:31,  7.04s/it]
 70%|███████   | 19795/28080 [39:07:38<16:13:42,  7.05s/it]
                                                           
{'loss': 0.6114, 'learning_rate': 0.00010572341638424978, 'epoch': 8.46}

 70%|███████   | 19795/28080 [39:07:38<16:13:42,  7.05s/it]
 70%|███████   | 19796/28080 [39:07:45<16:13:43,  7.05s/it]
                                                           
{'loss': 0.6043, 'learning_rate': 0.00010569986811526364, 'epoch': 8.46}

 70%|███████   | 19796/28080 [39:07:45<16:13:43,  7.05s/it]
 71%|███████   | 19797/28080 [39:07:53<16:15:37,  7.07s/it]
                                                           
{'loss': 0.6039, 'learning_rate': 0.00010567632176604198, 'epoch': 8.46}

 71%|███████   | 19797/28080 [39:07:53<16:15:37,  7.07s/it]
 71%|███████   | 19798/28080 [39:08:00<16:17:16,  7.08s/it]
                                                           
{'loss': 0.6014, 'learning_rate': 0.00010565277733689785, 'epoch': 8.46}

 71%|███████   | 19798/28080 [39:08:00<16:17:16,  7.08s/it]
 71%|███████   | 19799/28080 [39:08:07<16:18:56,  7.09s/it]
                                                           
{'loss': 0.6061, 'learning_rate': 0.00010562923482814479, 'epoch': 8.46}

 71%|███████   | 19799/28080 [39:08:07<16:18:56,  7.09s/it]
 71%|███████   | 19800/28080 [39:08:14<16:17:43,  7.09s/it]
                                                           
{'loss': 0.624, 'learning_rate': 0.00010560569424009567, 'epoch': 8.46}

 71%|███████   | 19800/28080 [39:08:14<16:17:43,  7.09s/it]
 71%|███████   | 19801/28080 [39:08:21<16:16:22,  7.08s/it]
                                                           
{'loss': 0.6206, 'learning_rate': 0.00010558215557306389, 'epoch': 8.46}

 71%|███████   | 19801/28080 [39:08:21<16:16:22,  7.08s/it]
 71%|███████   | 19802/28080 [39:08:28<16:14:47,  7.07s/it]
                                                           
{'loss': 0.5942, 'learning_rate': 0.00010555861882736245, 'epoch': 8.46}

 71%|███████   | 19802/28080 [39:08:28<16:14:47,  7.07s/it]
 71%|███████   | 19803/28080 [39:08:35<16:17:36,  7.09s/it]
                                                           
{'loss': 0.5947, 'learning_rate': 0.00010553508400330469, 'epoch': 8.46}

 71%|███████   | 19803/28080 [39:08:35<16:17:36,  7.09s/it]
 71%|███████   | 19804/28080 [39:08:42<16:17:56,  7.09s/it]
                                                           
{'loss': 0.619, 'learning_rate': 0.00010551155110120359, 'epoch': 8.46}

 71%|███████   | 19804/28080 [39:08:42<16:17:56,  7.09s/it]
 71%|███████   | 19805/28080 [39:08:49<16:14:52,  7.07s/it]
                                                           
{'loss': 0.611, 'learning_rate': 0.00010548802012137224, 'epoch': 8.46}

 71%|███████   | 19805/28080 [39:08:49<16:14:52,  7.07s/it]
 71%|███████   | 19806/28080 [39:08:56<16:13:00,  7.06s/it]
                                                           
{'loss': 0.6321, 'learning_rate': 0.00010546449106412359, 'epoch': 8.46}

 71%|███████   | 19806/28080 [39:08:56<16:13:00,  7.06s/it]
 71%|███████   | 19807/28080 [39:09:03<16:14:24,  7.07s/it]
                                                           
{'loss': 0.5926, 'learning_rate': 0.00010544096392977088, 'epoch': 8.46}

 71%|███████   | 19807/28080 [39:09:03<16:14:24,  7.07s/it]
 71%|███████   | 19808/28080 [39:09:10<16:12:57,  7.06s/it]
                                                           
{'loss': 0.615, 'learning_rate': 0.00010541743871862702, 'epoch': 8.46}

 71%|███████   | 19808/28080 [39:09:10<16:12:57,  7.06s/it]
 71%|███████   | 19809/28080 [39:09:17<16:12:39,  7.06s/it]
                                                           
{'loss': 0.6048, 'learning_rate': 0.00010539391543100496, 'epoch': 8.46}

 71%|███████   | 19809/28080 [39:09:17<16:12:39,  7.06s/it]
 71%|███████   | 19810/28080 [39:09:25<16:15:53,  7.08s/it]
                                                           
{'loss': 0.5983, 'learning_rate': 0.00010537039406721761, 'epoch': 8.46}

 71%|███████   | 19810/28080 [39:09:25<16:15:53,  7.08s/it]
 71%|███████   | 19811/28080 [39:09:32<16:18:13,  7.10s/it]
                                                           
{'loss': 0.6159, 'learning_rate': 0.00010534687462757802, 'epoch': 8.46}

 71%|███████   | 19811/28080 [39:09:32<16:18:13,  7.10s/it]
 71%|███████   | 19812/28080 [39:09:39<16:13:05,  7.06s/it]
                                                           
{'loss': 0.5995, 'learning_rate': 0.00010532335711239899, 'epoch': 8.46}

 71%|███████   | 19812/28080 [39:09:39<16:13:05,  7.06s/it]
 71%|███████   | 19813/28080 [39:09:46<16:15:56,  7.08s/it]
                                                           
{'loss': 0.5857, 'learning_rate': 0.00010529984152199356, 'epoch': 8.46}

 71%|███████   | 19813/28080 [39:09:46<16:15:56,  7.08s/it]
 71%|███████   | 19814/28080 [39:09:53<16:19:36,  7.11s/it]
                                                           
{'loss': 0.61, 'learning_rate': 0.00010527632785667432, 'epoch': 8.46}

 71%|███████   | 19814/28080 [39:09:53<16:19:36,  7.11s/it]
 71%|███████   | 19815/28080 [39:10:00<16:15:19,  7.08s/it]
                                                           
{'loss': 0.6075, 'learning_rate': 0.00010525281611675432, 'epoch': 8.46}

 71%|███████   | 19815/28080 [39:10:00<16:15:19,  7.08s/it]
 71%|███████   | 19816/28080 [39:10:07<16:15:18,  7.08s/it]
                                                           
{'loss': 0.6175, 'learning_rate': 0.00010522930630254618, 'epoch': 8.47}

 71%|███████   | 19816/28080 [39:10:07<16:15:18,  7.08s/it]
 71%|███████   | 19817/28080 [39:10:14<16:15:59,  7.09s/it]
                                                           
{'loss': 0.6026, 'learning_rate': 0.00010520579841436287, 'epoch': 8.47}

 71%|███████   | 19817/28080 [39:10:14<16:15:59,  7.09s/it]
 71%|███████   | 19818/28080 [39:10:21<16:22:31,  7.14s/it]
                                                           
{'loss': 0.58, 'learning_rate': 0.00010518229245251709, 'epoch': 8.47}

 71%|███████   | 19818/28080 [39:10:21<16:22:31,  7.14s/it]
 71%|███████   | 19819/28080 [39:10:28<16:20:14,  7.12s/it]
                                                           
{'loss': 0.6074, 'learning_rate': 0.00010515878841732138, 'epoch': 8.47}

 71%|███████   | 19819/28080 [39:10:28<16:20:14,  7.12s/it]
 71%|███████   | 19820/28080 [39:10:36<16:24:03,  7.15s/it]
                                                           
{'loss': 0.6009, 'learning_rate': 0.00010513528630908861, 'epoch': 8.47}

 71%|███████   | 19820/28080 [39:10:36<16:24:03,  7.15s/it]
 71%|███████   | 19821/28080 [39:10:43<16:20:28,  7.12s/it]
                                                           
{'loss': 0.6162, 'learning_rate': 0.00010511178612813133, 'epoch': 8.47}

 71%|███████   | 19821/28080 [39:10:43<16:20:28,  7.12s/it]
 71%|███████   | 19822/28080 [39:10:50<16:19:34,  7.12s/it]
                                                           
{'loss': 0.6302, 'learning_rate': 0.00010508828787476235, 'epoch': 8.47}

 71%|███████   | 19822/28080 [39:10:50<16:19:34,  7.12s/it]
 71%|███████   | 19823/28080 [39:10:57<16:16:18,  7.09s/it]
                                                           
{'loss': 0.6276, 'learning_rate': 0.00010506479154929422, 'epoch': 8.47}

 71%|███████   | 19823/28080 [39:10:57<16:16:18,  7.09s/it]
 71%|███████   | 19824/28080 [39:11:04<16:11:19,  7.06s/it]
                                                           
{'loss': 0.6017, 'learning_rate': 0.0001050412971520395, 'epoch': 8.47}

 71%|███████   | 19824/28080 [39:11:04<16:11:19,  7.06s/it]
 71%|███████   | 19825/28080 [39:11:11<16:15:21,  7.09s/it]
                                                           
{'loss': 0.576, 'learning_rate': 0.00010501780468331071, 'epoch': 8.47}

 71%|███████   | 19825/28080 [39:11:11<16:15:21,  7.09s/it]
 71%|███████   | 19826/28080 [39:11:18<16:19:06,  7.12s/it]
                                                           
{'loss': 0.6057, 'learning_rate': 0.00010499431414342054, 'epoch': 8.47}

 71%|███████   | 19826/28080 [39:11:18<16:19:06,  7.12s/it]
 71%|███████   | 19827/28080 [39:11:25<16:16:00,  7.10s/it]
                                                           
{'loss': 0.6041, 'learning_rate': 0.00010497082553268139, 'epoch': 8.47}

 71%|███████   | 19827/28080 [39:11:25<16:16:00,  7.10s/it]
 71%|███████   | 19828/28080 [39:11:32<16:14:43,  7.09s/it]
                                                           
{'loss': 0.6119, 'learning_rate': 0.00010494733885140583, 'epoch': 8.47}

 71%|███████   | 19828/28080 [39:11:32<16:14:43,  7.09s/it]
 71%|███████   | 19829/28080 [39:11:39<16:18:02,  7.11s/it]
                                                           
{'loss': 0.615, 'learning_rate': 0.00010492385409990618, 'epoch': 8.47}

 71%|███████   | 19829/28080 [39:11:40<16:18:02,  7.11s/it]
 71%|███████   | 19830/28080 [39:11:47<16:19:59,  7.13s/it]
                                                           
{'loss': 0.6205, 'learning_rate': 0.00010490037127849508, 'epoch': 8.47}

 71%|███████   | 19830/28080 [39:11:47<16:19:59,  7.13s/it]
 71%|███████   | 19831/28080 [39:11:54<16:17:46,  7.11s/it]
                                                           
{'loss': 0.5995, 'learning_rate': 0.00010487689038748475, 'epoch': 8.47}

 71%|███████   | 19831/28080 [39:11:54<16:17:46,  7.11s/it]
 71%|███████   | 19832/28080 [39:12:01<16:20:45,  7.13s/it]
                                                           
{'loss': 0.6145, 'learning_rate': 0.00010485341142718776, 'epoch': 8.47}

 71%|███████   | 19832/28080 [39:12:01<16:20:45,  7.13s/it]
 71%|███████   | 19833/28080 [39:12:08<16:23:11,  7.15s/it]
                                                           
{'loss': 0.5992, 'learning_rate': 0.0001048299343979164, 'epoch': 8.47}

 71%|███████   | 19833/28080 [39:12:08<16:23:11,  7.15s/it]
 71%|███████   | 19834/28080 [39:12:15<16:23:28,  7.16s/it]
                                                           
{'loss': 0.585, 'learning_rate': 0.000104806459299983, 'epoch': 8.47}

 71%|███████   | 19834/28080 [39:12:15<16:23:28,  7.16s/it]
 71%|███████   | 19835/28080 [39:12:22<16:20:17,  7.13s/it]
                                                           
{'loss': 0.5986, 'learning_rate': 0.00010478298613369979, 'epoch': 8.47}

 71%|███████   | 19835/28080 [39:12:22<16:20:17,  7.13s/it]
 71%|███████   | 19836/28080 [39:12:29<16:16:50,  7.11s/it]
                                                           
{'loss': 0.6156, 'learning_rate': 0.00010475951489937924, 'epoch': 8.47}

 71%|███████   | 19836/28080 [39:12:29<16:16:50,  7.11s/it]
 71%|███████   | 19837/28080 [39:12:36<16:15:15,  7.10s/it]
                                                           
{'loss': 0.6279, 'learning_rate': 0.0001047360455973335, 'epoch': 8.47}

 71%|███████   | 19837/28080 [39:12:36<16:15:15,  7.10s/it]
 71%|███████   | 19838/28080 [39:12:44<16:15:37,  7.10s/it]
                                                           
{'loss': 0.5949, 'learning_rate': 0.00010471257822787477, 'epoch': 8.47}

 71%|███████   | 19838/28080 [39:12:44<16:15:37,  7.10s/it]
 71%|███████   | 19839/28080 [39:12:51<16:17:17,  7.12s/it]
                                                           
{'loss': 0.61, 'learning_rate': 0.00010468911279131527, 'epoch': 8.48}

 71%|███████   | 19839/28080 [39:12:51<16:17:17,  7.12s/it]
 71%|███████   | 19840/28080 [39:12:58<16:18:54,  7.13s/it]
                                                           
{'loss': 0.6266, 'learning_rate': 0.00010466564928796727, 'epoch': 8.48}

 71%|███████   | 19840/28080 [39:12:58<16:18:54,  7.13s/it]
 71%|███████   | 19841/28080 [39:13:05<16:16:53,  7.11s/it]
                                                           
{'loss': 0.6088, 'learning_rate': 0.00010464218771814287, 'epoch': 8.48}

 71%|███████   | 19841/28080 [39:13:05<16:16:53,  7.11s/it]
 71%|███████   | 19842/28080 [39:13:12<16:13:32,  7.09s/it]
                                                           
{'loss': 0.6073, 'learning_rate': 0.00010461872808215423, 'epoch': 8.48}

 71%|███████   | 19842/28080 [39:13:12<16:13:32,  7.09s/it]
 71%|███████   | 19843/28080 [39:13:19<16:07:28,  7.05s/it]
                                                           
{'loss': 0.6159, 'learning_rate': 0.00010459527038031342, 'epoch': 8.48}

 71%|███████   | 19843/28080 [39:13:19<16:07:28,  7.05s/it]
 71%|███████   | 19844/28080 [39:13:26<16:12:22,  7.08s/it]
                                                           
{'loss': 0.6321, 'learning_rate': 0.00010457181461293245, 'epoch': 8.48}

 71%|███████   | 19844/28080 [39:13:26<16:12:22,  7.08s/it]
 71%|███████   | 19845/28080 [39:13:33<16:12:15,  7.08s/it]
                                                           
{'loss': 0.6, 'learning_rate': 0.00010454836078032353, 'epoch': 8.48}

 71%|███████   | 19845/28080 [39:13:33<16:12:15,  7.08s/it]
 71%|███████   | 19846/28080 [39:13:40<16:08:28,  7.06s/it]
                                                           
{'loss': 0.6216, 'learning_rate': 0.00010452490888279854, 'epoch': 8.48}

 71%|███████   | 19846/28080 [39:13:40<16:08:28,  7.06s/it]
 71%|███████   | 19847/28080 [39:13:47<16:09:19,  7.06s/it]
                                                           
{'loss': 0.6141, 'learning_rate': 0.00010450145892066973, 'epoch': 8.48}

 71%|███████   | 19847/28080 [39:13:47<16:09:19,  7.06s/it]
 71%|███████   | 19848/28080 [39:13:54<16:07:22,  7.05s/it]
                                                           
{'loss': 0.642, 'learning_rate': 0.00010447801089424872, 'epoch': 8.48}

 71%|███████   | 19848/28080 [39:13:54<16:07:22,  7.05s/it]
 71%|███████   | 19849/28080 [39:14:01<16:05:07,  7.04s/it]
                                                           
{'loss': 0.6112, 'learning_rate': 0.00010445456480384773, 'epoch': 8.48}

 71%|███████   | 19849/28080 [39:14:01<16:05:07,  7.04s/it]
 71%|███████   | 19850/28080 [39:14:08<16:05:21,  7.04s/it]
                                                           
{'loss': 0.596, 'learning_rate': 0.00010443112064977856, 'epoch': 8.48}

 71%|███████   | 19850/28080 [39:14:08<16:05:21,  7.04s/it]
 71%|███████   | 19851/28080 [39:14:15<16:07:23,  7.05s/it]
                                                           
{'loss': 0.6012, 'learning_rate': 0.00010440767843235322, 'epoch': 8.48}

 71%|███████   | 19851/28080 [39:14:15<16:07:23,  7.05s/it]
 71%|███████   | 19852/28080 [39:14:23<16:11:13,  7.08s/it]
                                                           
{'loss': 0.6222, 'learning_rate': 0.0001043842381518835, 'epoch': 8.48}

 71%|███████   | 19852/28080 [39:14:23<16:11:13,  7.08s/it]
 71%|███████   | 19853/28080 [39:14:30<16:11:46,  7.09s/it]
                                                           
{'loss': 0.6116, 'learning_rate': 0.00010436079980868129, 'epoch': 8.48}

 71%|███████   | 19853/28080 [39:14:30<16:11:46,  7.09s/it]
 71%|███████   | 19854/28080 [39:14:37<16:05:44,  7.04s/it]
                                                           
{'loss': 0.6155, 'learning_rate': 0.0001043373634030583, 'epoch': 8.48}

 71%|███████   | 19854/28080 [39:14:37<16:05:44,  7.04s/it]
 71%|███████   | 19855/28080 [39:14:44<16:10:46,  7.08s/it]
                                                           
{'loss': 0.6017, 'learning_rate': 0.00010431392893532649, 'epoch': 8.48}

 71%|███████   | 19855/28080 [39:14:44<16:10:46,  7.08s/it]
 71%|███████   | 19856/28080 [39:14:51<16:09:45,  7.08s/it]
                                                           
{'loss': 0.589, 'learning_rate': 0.00010429049640579758, 'epoch': 8.48}

 71%|███████   | 19856/28080 [39:14:51<16:09:45,  7.08s/it]
 71%|███████   | 19857/28080 [39:14:58<16:10:51,  7.08s/it]
                                                           
{'loss': 0.6136, 'learning_rate': 0.0001042670658147833, 'epoch': 8.48}

 71%|███████   | 19857/28080 [39:14:58<16:10:51,  7.08s/it]
 71%|███████   | 19858/28080 [39:15:05<16:09:27,  7.07s/it]
                                                           
{'loss': 0.6153, 'learning_rate': 0.00010424363716259524, 'epoch': 8.48}

 71%|███████   | 19858/28080 [39:15:05<16:09:27,  7.07s/it]
 71%|███████   | 19859/28080 [39:15:12<16:11:03,  7.09s/it]
                                                           
{'loss': 0.6097, 'learning_rate': 0.00010422021044954532, 'epoch': 8.48}

 71%|███████   | 19859/28080 [39:15:12<16:11:03,  7.09s/it]
 71%|███████   | 19860/28080 [39:15:19<16:12:13,  7.10s/it]
                                                           
{'loss': 0.6022, 'learning_rate': 0.00010419678567594504, 'epoch': 8.48}

 71%|███████   | 19860/28080 [39:15:19<16:12:13,  7.10s/it]
 71%|███████   | 19861/28080 [39:15:26<16:11:19,  7.09s/it]
                                                           
{'loss': 0.6009, 'learning_rate': 0.00010417336284210626, 'epoch': 8.48}

 71%|███████   | 19861/28080 [39:15:26<16:11:19,  7.09s/it]
 71%|███████   | 19862/28080 [39:15:33<16:11:48,  7.10s/it]
                                                           
{'loss': 0.6074, 'learning_rate': 0.0001041499419483403, 'epoch': 8.48}

 71%|███████   | 19862/28080 [39:15:33<16:11:48,  7.10s/it]
 71%|███████   | 19863/28080 [39:15:40<16:09:31,  7.08s/it]
                                                           
{'loss': 0.6019, 'learning_rate': 0.00010412652299495897, 'epoch': 8.49}

 71%|███████   | 19863/28080 [39:15:40<16:09:31,  7.08s/it]
 71%|███████   | 19864/28080 [39:15:48<16:10:07,  7.08s/it]
                                                           
{'loss': 0.6096, 'learning_rate': 0.00010410310598227369, 'epoch': 8.49}

 71%|███████   | 19864/28080 [39:15:48<16:10:07,  7.08s/it]
 71%|███████   | 19865/28080 [39:15:55<16:15:13,  7.12s/it]
                                                           
{'loss': 0.5931, 'learning_rate': 0.00010407969091059613, 'epoch': 8.49}

 71%|███████   | 19865/28080 [39:15:55<16:15:13,  7.12s/it]
 71%|███████   | 19866/28080 [39:16:02<16:18:40,  7.15s/it]
                                                           
{'loss': 0.6172, 'learning_rate': 0.00010405627778023777, 'epoch': 8.49}

 71%|███████   | 19866/28080 [39:16:02<16:18:40,  7.15s/it]
 71%|███████   | 19867/28080 [39:16:09<16:11:45,  7.10s/it]
                                                           
{'loss': 0.6245, 'learning_rate': 0.00010403286659151007, 'epoch': 8.49}

 71%|███████   | 19867/28080 [39:16:09<16:11:45,  7.10s/it]
 71%|███████   | 19868/28080 [39:16:16<16:13:30,  7.11s/it]
                                                           
{'loss': 0.6084, 'learning_rate': 0.00010400945734472447, 'epoch': 8.49}

 71%|███████   | 19868/28080 [39:16:16<16:13:30,  7.11s/it]
 71%|███████   | 19869/28080 [39:16:23<16:15:57,  7.13s/it]
                                                           
{'loss': 0.6186, 'learning_rate': 0.00010398605004019237, 'epoch': 8.49}

 71%|███████   | 19869/28080 [39:16:23<16:15:57,  7.13s/it]
 71%|███████   | 19870/28080 [39:16:30<16:11:36,  7.10s/it]
                                                           
{'loss': 0.5996, 'learning_rate': 0.0001039626446782253, 'epoch': 8.49}

 71%|███████   | 19870/28080 [39:16:30<16:11:36,  7.10s/it]
 71%|███████   | 19871/28080 [39:16:38<16:15:05,  7.13s/it]
                                                           
{'loss': 0.5909, 'learning_rate': 0.00010393924125913461, 'epoch': 8.49}

 71%|███████   | 19871/28080 [39:16:38<16:15:05,  7.13s/it]
 71%|███████   | 19872/28080 [39:16:45<16:15:30,  7.13s/it]
                                                           
{'loss': 0.6173, 'learning_rate': 0.00010391583978323163, 'epoch': 8.49}

 71%|███████   | 19872/28080 [39:16:45<16:15:30,  7.13s/it]
 71%|███████   | 19873/28080 [39:16:52<16:14:48,  7.13s/it]
                                                           
{'loss': 0.6142, 'learning_rate': 0.00010389244025082759, 'epoch': 8.49}

 71%|███████   | 19873/28080 [39:16:52<16:14:48,  7.13s/it]
 71%|███████   | 19874/28080 [39:16:59<16:09:24,  7.09s/it]
                                                           
{'loss': 0.6303, 'learning_rate': 0.00010386904266223402, 'epoch': 8.49}

 71%|███████   | 19874/28080 [39:16:59<16:09:24,  7.09s/it]
 71%|███████   | 19875/28080 [39:17:06<16:10:38,  7.10s/it]
                                                           
{'loss': 0.6019, 'learning_rate': 0.00010384564701776206, 'epoch': 8.49}

 71%|███████   | 19875/28080 [39:17:06<16:10:38,  7.10s/it]
 71%|███████   | 19876/28080 [39:17:13<16:12:47,  7.11s/it]
                                                           
{'loss': 0.6048, 'learning_rate': 0.000103822253317723, 'epoch': 8.49}

 71%|███████   | 19876/28080 [39:17:13<16:12:47,  7.11s/it]
 71%|███████   | 19877/28080 [39:17:20<16:12:08,  7.11s/it]
                                                           
{'loss': 0.6166, 'learning_rate': 0.00010379886156242793, 'epoch': 8.49}

 71%|███████   | 19877/28080 [39:17:20<16:12:08,  7.11s/it]
 71%|███████   | 19878/28080 [39:17:27<16:11:14,  7.10s/it]
                                                           
{'loss': 0.6118, 'learning_rate': 0.0001037754717521883, 'epoch': 8.49}

 71%|███████   | 19878/28080 [39:17:27<16:11:14,  7.10s/it]
 71%|███████   | 19879/28080 [39:17:34<16:13:08,  7.12s/it]
                                                           
{'loss': 0.6071, 'learning_rate': 0.00010375208388731508, 'epoch': 8.49}

 71%|███████   | 19879/28080 [39:17:34<16:13:08,  7.12s/it]
 71%|███████   | 19880/28080 [39:17:41<16:08:10,  7.08s/it]
                                                           
{'loss': 0.5928, 'learning_rate': 0.00010372869796811968, 'epoch': 8.49}

 71%|███████   | 19880/28080 [39:17:41<16:08:10,  7.08s/it]
 71%|███████   | 19881/28080 [39:17:48<16:08:25,  7.09s/it]
                                                           
{'loss': 0.605, 'learning_rate': 0.00010370531399491287, 'epoch': 8.49}

 71%|███████   | 19881/28080 [39:17:48<16:08:25,  7.09s/it]
 71%|███████   | 19882/28080 [39:17:56<16:10:04,  7.10s/it]
                                                           
{'loss': 0.6029, 'learning_rate': 0.00010368193196800605, 'epoch': 8.49}

 71%|███████   | 19882/28080 [39:17:56<16:10:04,  7.10s/it]
 71%|███████   | 19883/28080 [39:18:03<16:06:47,  7.08s/it]
                                                           
{'loss': 0.5997, 'learning_rate': 0.00010365855188771004, 'epoch': 8.49}

 71%|███████   | 19883/28080 [39:18:03<16:06:47,  7.08s/it]
 71%|███████   | 19884/28080 [39:18:10<16:06:10,  7.07s/it]
                                                           
{'loss': 0.6035, 'learning_rate': 0.00010363517375433615, 'epoch': 8.49}

 71%|███████   | 19884/28080 [39:18:10<16:06:10,  7.07s/it]
 71%|███████   | 19885/28080 [39:18:17<16:06:24,  7.08s/it]
                                                           
{'loss': 0.6119, 'learning_rate': 0.00010361179756819528, 'epoch': 8.49}

 71%|███████   | 19885/28080 [39:18:17<16:06:24,  7.08s/it]
 71%|███████   | 19886/28080 [39:18:24<16:09:27,  7.10s/it]
                                                           
{'loss': 0.6093, 'learning_rate': 0.0001035884233295984, 'epoch': 8.5}

 71%|███████   | 19886/28080 [39:18:24<16:09:27,  7.10s/it]
 71%|███████   | 19887/28080 [39:18:31<16:12:43,  7.12s/it]
                                                           
{'loss': 0.5988, 'learning_rate': 0.00010356505103885641, 'epoch': 8.5}

 71%|███████   | 19887/28080 [39:18:31<16:12:43,  7.12s/it]
 71%|███████   | 19888/28080 [39:18:38<16:09:11,  7.10s/it]
                                                           
{'loss': 0.6149, 'learning_rate': 0.00010354168069628045, 'epoch': 8.5}

 71%|███████   | 19888/28080 [39:18:38<16:09:11,  7.10s/it]
 71%|███████   | 19889/28080 [39:18:45<16:12:25,  7.12s/it]
                                                           
{'loss': 0.6145, 'learning_rate': 0.00010351831230218134, 'epoch': 8.5}

 71%|███████   | 19889/28080 [39:18:45<16:12:25,  7.12s/it]
 71%|███████   | 19890/28080 [39:18:53<16:14:18,  7.14s/it]
                                                           
{'loss': 0.592, 'learning_rate': 0.00010349494585686997, 'epoch': 8.5}

 71%|███████   | 19890/28080 [39:18:53<16:14:18,  7.14s/it]
 71%|███████   | 19891/28080 [39:19:00<16:12:10,  7.12s/it]
                                                           
{'loss': 0.6059, 'learning_rate': 0.00010347158136065712, 'epoch': 8.5}

 71%|███████   | 19891/28080 [39:19:00<16:12:10,  7.12s/it]
 71%|███████   | 19892/28080 [39:19:07<16:06:01,  7.08s/it]
                                                           
{'loss': 0.6067, 'learning_rate': 0.0001034482188138538, 'epoch': 8.5}

 71%|███████   | 19892/28080 [39:19:07<16:06:01,  7.08s/it]
 71%|███████   | 19893/28080 [39:19:14<16:05:15,  7.07s/it]
                                                           
{'loss': 0.5906, 'learning_rate': 0.00010342485821677073, 'epoch': 8.5}

 71%|███████   | 19893/28080 [39:19:14<16:05:15,  7.07s/it]
 71%|███████   | 19894/28080 [39:19:21<16:07:43,  7.09s/it]
                                                           
{'loss': 0.5932, 'learning_rate': 0.00010340149956971861, 'epoch': 8.5}

 71%|███████   | 19894/28080 [39:19:21<16:07:43,  7.09s/it]
 71%|███████   | 19895/28080 [39:19:28<16:06:43,  7.09s/it]
                                                           
{'loss': 0.6055, 'learning_rate': 0.00010337814287300851, 'epoch': 8.5}

 71%|███████   | 19895/28080 [39:19:28<16:06:43,  7.09s/it]
 71%|███████   | 19896/28080 [39:19:35<16:08:32,  7.10s/it]
                                                           
{'loss': 0.6063, 'learning_rate': 0.00010335478812695076, 'epoch': 8.5}

 71%|███████   | 19896/28080 [39:19:35<16:08:32,  7.10s/it]
 71%|███████   | 19897/28080 [39:19:42<16:12:42,  7.13s/it]
                                                           
{'loss': 0.6006, 'learning_rate': 0.00010333143533185636, 'epoch': 8.5}

 71%|███████   | 19897/28080 [39:19:42<16:12:42,  7.13s/it]
 71%|███████   | 19898/28080 [39:19:49<16:09:58,  7.11s/it]
                                                           
{'loss': 0.6035, 'learning_rate': 0.0001033080844880358, 'epoch': 8.5}

 71%|███████   | 19898/28080 [39:19:49<16:09:58,  7.11s/it]
 71%|███████   | 19899/28080 [39:19:56<16:13:09,  7.14s/it]
                                                           
{'loss': 0.5859, 'learning_rate': 0.00010328473559579995, 'epoch': 8.5}

 71%|███████   | 19899/28080 [39:19:56<16:13:09,  7.14s/it]
 71%|███████   | 19900/28080 [39:20:03<16:07:32,  7.10s/it]
                                                           
{'loss': 0.6129, 'learning_rate': 0.00010326138865545934, 'epoch': 8.5}

 71%|███████   | 19900/28080 [39:20:03<16:07:32,  7.10s/it]
 71%|███████   | 19901/28080 [39:20:11<16:09:32,  7.11s/it]
                                                           
{'loss': 0.6071, 'learning_rate': 0.00010323804366732456, 'epoch': 8.5}

 71%|███████   | 19901/28080 [39:20:11<16:09:32,  7.11s/it]
 71%|███████   | 19902/28080 [39:20:18<16:09:30,  7.11s/it]
                                                           
{'loss': 0.6109, 'learning_rate': 0.0001032147006317061, 'epoch': 8.5}

 71%|███████   | 19902/28080 [39:20:18<16:09:30,  7.11s/it]
 71%|███████   | 19903/28080 [39:20:25<16:09:19,  7.11s/it]
                                                           
{'loss': 0.6091, 'learning_rate': 0.00010319135954891474, 'epoch': 8.5}

 71%|███████   | 19903/28080 [39:20:25<16:09:19,  7.11s/it]
 71%|███████   | 19904/28080 [39:20:32<16:10:26,  7.12s/it]
                                                           
{'loss': 0.5814, 'learning_rate': 0.00010316802041926087, 'epoch': 8.5}

 71%|███████   | 19904/28080 [39:20:32<16:10:26,  7.12s/it]
 71%|███████   | 19905/28080 [39:20:39<16:11:41,  7.13s/it]
                                                           
{'loss': 0.6241, 'learning_rate': 0.00010314468324305502, 'epoch': 8.5}

 71%|███████   | 19905/28080 [39:20:39<16:11:41,  7.13s/it]
 71%|███████   | 19906/28080 [39:20:46<16:09:41,  7.12s/it]
                                                           
{'loss': 0.617, 'learning_rate': 0.00010312134802060755, 'epoch': 8.5}

 71%|███████   | 19906/28080 [39:20:46<16:09:41,  7.12s/it]
 71%|███████   | 19907/28080 [39:20:53<16:08:56,  7.11s/it]
                                                           
{'loss': 0.6114, 'learning_rate': 0.0001030980147522291, 'epoch': 8.5}

 71%|███████   | 19907/28080 [39:20:53<16:08:56,  7.11s/it]
 71%|███████   | 19908/28080 [39:21:00<16:05:02,  7.09s/it]
                                                           
{'loss': 0.6393, 'learning_rate': 0.00010307468343822996, 'epoch': 8.5}

 71%|███████   | 19908/28080 [39:21:00<16:05:02,  7.09s/it]
 71%|███████   | 19909/28080 [39:21:07<16:02:42,  7.07s/it]
                                                           
{'loss': 0.6389, 'learning_rate': 0.00010305135407892075, 'epoch': 8.5}

 71%|███████   | 19909/28080 [39:21:07<16:02:42,  7.07s/it]
 71%|███████   | 19910/28080 [39:21:14<16:01:43,  7.06s/it]
                                                           
{'loss': 0.6024, 'learning_rate': 0.00010302802667461147, 'epoch': 8.51}

 71%|███████   | 19910/28080 [39:21:14<16:01:43,  7.06s/it]
 71%|███████   | 19911/28080 [39:21:22<16:02:33,  7.07s/it]
                                                           
{'loss': 0.6066, 'learning_rate': 0.00010300470122561278, 'epoch': 8.51}

 71%|███████   | 19911/28080 [39:21:22<16:02:33,  7.07s/it]
 71%|███████   | 19912/28080 [39:21:29<16:06:21,  7.10s/it]
                                                           
{'loss': 0.612, 'learning_rate': 0.00010298137773223481, 'epoch': 8.51}

 71%|███████   | 19912/28080 [39:21:29<16:06:21,  7.10s/it]
 71%|███████   | 19913/28080 [39:21:36<16:09:19,  7.12s/it]
                                                           
{'loss': 0.5912, 'learning_rate': 0.00010295805619478801, 'epoch': 8.51}

 71%|███████   | 19913/28080 [39:21:36<16:09:19,  7.12s/it]
 71%|███████   | 19914/28080 [39:21:43<16:08:29,  7.12s/it]
                                                           
{'loss': 0.6075, 'learning_rate': 0.0001029347366135826, 'epoch': 8.51}

 71%|███████   | 19914/28080 [39:21:43<16:08:29,  7.12s/it]
 71%|███████   | 19915/28080 [39:21:50<16:01:44,  7.07s/it]
                                                           
{'loss': 0.6032, 'learning_rate': 0.0001029114189889288, 'epoch': 8.51}

 71%|███████   | 19915/28080 [39:21:50<16:01:44,  7.07s/it]
 71%|███████   | 19916/28080 [39:21:57<15:59:43,  7.05s/it]
                                                           
{'loss': 0.6103, 'learning_rate': 0.00010288810332113672, 'epoch': 8.51}

 71%|███████   | 19916/28080 [39:21:57<15:59:43,  7.05s/it]
 71%|███████   | 19917/28080 [39:22:04<16:01:42,  7.07s/it]
                                                           
{'loss': 0.6049, 'learning_rate': 0.00010286478961051677, 'epoch': 8.51}

 71%|███████   | 19917/28080 [39:22:04<16:01:42,  7.07s/it]
 71%|███████   | 19918/28080 [39:22:11<16:03:48,  7.09s/it]
                                                           
{'loss': 0.5902, 'learning_rate': 0.00010284147785737899, 'epoch': 8.51}

 71%|███████   | 19918/28080 [39:22:11<16:03:48,  7.09s/it]
 71%|███████   | 19919/28080 [39:22:18<16:01:42,  7.07s/it]
                                                           
{'loss': 0.6152, 'learning_rate': 0.00010281816806203353, 'epoch': 8.51}

 71%|███████   | 19919/28080 [39:22:18<16:01:42,  7.07s/it]
 71%|███████   | 19920/28080 [39:22:25<16:02:38,  7.08s/it]
                                                           
{'loss': 0.5912, 'learning_rate': 0.00010279486022479051, 'epoch': 8.51}

 71%|███████   | 19920/28080 [39:22:25<16:02:38,  7.08s/it]
 71%|███████   | 19921/28080 [39:22:32<16:07:42,  7.12s/it]
                                                           
{'loss': 0.6141, 'learning_rate': 0.00010277155434595992, 'epoch': 8.51}

 71%|███████   | 19921/28080 [39:22:32<16:07:42,  7.12s/it]
 71%|███████   | 19922/28080 [39:22:40<16:08:11,  7.12s/it]
                                                           
{'loss': 0.6067, 'learning_rate': 0.00010274825042585198, 'epoch': 8.51}

 71%|███████   | 19922/28080 [39:22:40<16:08:11,  7.12s/it]
 71%|███████   | 19923/28080 [39:22:47<16:05:54,  7.10s/it]
                                                           
{'loss': 0.6342, 'learning_rate': 0.0001027249484647767, 'epoch': 8.51}

 71%|███████   | 19923/28080 [39:22:47<16:05:54,  7.10s/it]
 71%|███████   | 19924/28080 [39:22:54<16:10:09,  7.14s/it]
                                                           
{'loss': 0.6138, 'learning_rate': 0.000102701648463044, 'epoch': 8.51}

 71%|███████   | 19924/28080 [39:22:54<16:10:09,  7.14s/it]
 71%|███████   | 19925/28080 [39:23:01<16:10:39,  7.14s/it]
                                                           
{'loss': 0.6036, 'learning_rate': 0.00010267835042096385, 'epoch': 8.51}

 71%|███████   | 19925/28080 [39:23:01<16:10:39,  7.14s/it]
 71%|███████   | 19926/28080 [39:23:08<16:12:09,  7.15s/it]
                                                           
{'loss': 0.6011, 'learning_rate': 0.00010265505433884634, 'epoch': 8.51}

 71%|███████   | 19926/28080 [39:23:08<16:12:09,  7.15s/it]
 71%|███████   | 19927/28080 [39:23:15<16:06:12,  7.11s/it]
                                                           
{'loss': 0.5919, 'learning_rate': 0.00010263176021700123, 'epoch': 8.51}

 71%|███████   | 19927/28080 [39:23:15<16:06:12,  7.11s/it]
 71%|███████   | 19928/28080 [39:23:22<16:06:55,  7.12s/it]
                                                           
{'loss': 0.6034, 'learning_rate': 0.00010260846805573873, 'epoch': 8.51}

 71%|███████   | 19928/28080 [39:23:22<16:06:55,  7.12s/it]
 71%|███████   | 19929/28080 [39:23:29<16:01:22,  7.08s/it]
                                                           
{'loss': 0.6161, 'learning_rate': 0.0001025851778553683, 'epoch': 8.51}

 71%|███████   | 19929/28080 [39:23:29<16:01:22,  7.08s/it]
 71%|███████   | 19930/28080 [39:23:37<16:03:59,  7.10s/it]
                                                           
{'loss': 0.6075, 'learning_rate': 0.0001025618896162001, 'epoch': 8.51}

 71%|███████   | 19930/28080 [39:23:37<16:03:59,  7.10s/it]
 71%|███████   | 19931/28080 [39:23:44<16:03:58,  7.10s/it]
                                                           
{'loss': 0.6255, 'learning_rate': 0.00010253860333854376, 'epoch': 8.51}

 71%|███████   | 19931/28080 [39:23:44<16:03:58,  7.10s/it]
 71%|███████   | 19932/28080 [39:23:51<16:02:29,  7.09s/it]
                                                           
{'loss': 0.6122, 'learning_rate': 0.00010251531902270928, 'epoch': 8.51}

 71%|███████   | 19932/28080 [39:23:51<16:02:29,  7.09s/it]
 71%|███████   | 19933/28080 [39:23:58<16:00:23,  7.07s/it]
                                                           
{'loss': 0.5941, 'learning_rate': 0.0001024920366690063, 'epoch': 8.52}

 71%|███████   | 19933/28080 [39:23:58<16:00:23,  7.07s/it]
 71%|███████   | 19934/28080 [39:24:05<16:01:49,  7.08s/it]
                                                           
{'loss': 0.5978, 'learning_rate': 0.00010246875627774463, 'epoch': 8.52}

 71%|███████   | 19934/28080 [39:24:05<16:01:49,  7.08s/it]
 71%|███████   | 19935/28080 [39:24:12<16:03:19,  7.10s/it]
                                                           
{'loss': 0.6023, 'learning_rate': 0.00010244547784923383, 'epoch': 8.52}

 71%|███████   | 19935/28080 [39:24:12<16:03:19,  7.10s/it]
 71%|███████   | 19936/28080 [39:24:19<16:08:14,  7.13s/it]
                                                           
{'loss': 0.6149, 'learning_rate': 0.00010242220138378382, 'epoch': 8.52}

 71%|███████   | 19936/28080 [39:24:19<16:08:14,  7.13s/it]
 71%|███████   | 19937/28080 [39:24:26<16:10:52,  7.15s/it]
                                                           
{'loss': 0.6058, 'learning_rate': 0.00010239892688170422, 'epoch': 8.52}

 71%|███████   | 19937/28080 [39:24:26<16:10:52,  7.15s/it]
 71%|███████   | 19938/28080 [39:24:33<16:05:26,  7.11s/it]
                                                           
{'loss': 0.624, 'learning_rate': 0.00010237565434330459, 'epoch': 8.52}

 71%|███████   | 19938/28080 [39:24:33<16:05:26,  7.11s/it]
 71%|███████   | 19939/28080 [39:24:40<16:04:24,  7.11s/it]
                                                           
{'loss': 0.6032, 'learning_rate': 0.0001023523837688945, 'epoch': 8.52}

 71%|███████   | 19939/28080 [39:24:40<16:04:24,  7.11s/it]
 71%|███████   | 19940/28080 [39:24:48<16:02:31,  7.09s/it]
                                                           
{'loss': 0.6073, 'learning_rate': 0.0001023291151587837, 'epoch': 8.52}

 71%|███████   | 19940/28080 [39:24:48<16:02:31,  7.09s/it]
 71%|███████   | 19941/28080 [39:24:55<16:00:26,  7.08s/it]
                                                           
{'loss': 0.6031, 'learning_rate': 0.00010230584851328159, 'epoch': 8.52}

 71%|███████   | 19941/28080 [39:24:55<16:00:26,  7.08s/it]
 71%|███████   | 19942/28080 [39:25:02<16:00:50,  7.08s/it]
                                                           
{'loss': 0.6162, 'learning_rate': 0.000102282583832698, 'epoch': 8.52}

 71%|███████   | 19942/28080 [39:25:02<16:00:50,  7.08s/it]
 71%|███████   | 19943/28080 [39:25:09<16:03:33,  7.11s/it]
                                                           
{'loss': 0.6005, 'learning_rate': 0.00010225932111734212, 'epoch': 8.52}

 71%|███████   | 19943/28080 [39:25:09<16:03:33,  7.11s/it]
 71%|███████   | 19944/28080 [39:25:16<16:05:55,  7.12s/it]
                                                           
{'loss': 0.6145, 'learning_rate': 0.00010223606036752351, 'epoch': 8.52}

 71%|███████   | 19944/28080 [39:25:16<16:05:55,  7.12s/it]
 71%|███████   | 19945/28080 [39:25:23<16:05:24,  7.12s/it]
                                                           
{'loss': 0.6068, 'learning_rate': 0.00010221280158355174, 'epoch': 8.52}

 71%|███████   | 19945/28080 [39:25:23<16:05:24,  7.12s/it]
 71%|███████   | 19946/28080 [39:25:30<16:05:43,  7.12s/it]
                                                           
{'loss': 0.6126, 'learning_rate': 0.00010218954476573608, 'epoch': 8.52}

 71%|███████   | 19946/28080 [39:25:30<16:05:43,  7.12s/it]
 71%|███████   | 19947/28080 [39:25:37<16:00:53,  7.09s/it]
                                                           
{'loss': 0.6138, 'learning_rate': 0.00010216628991438614, 'epoch': 8.52}

 71%|███████   | 19947/28080 [39:25:37<16:00:53,  7.09s/it]
 71%|███████   | 19948/28080 [39:25:44<16:03:50,  7.11s/it]
                                                           
{'loss': 0.5817, 'learning_rate': 0.0001021430370298112, 'epoch': 8.52}

 71%|███████   | 19948/28080 [39:25:44<16:03:50,  7.11s/it]
 71%|███████   | 19949/28080 [39:25:52<16:03:57,  7.11s/it]
                                                           
{'loss': 0.6108, 'learning_rate': 0.00010211978611232064, 'epoch': 8.52}

 71%|███████   | 19949/28080 [39:25:52<16:03:57,  7.11s/it]
 71%|███████   | 19950/28080 [39:25:59<16:05:52,  7.13s/it]
                                                           
{'loss': 0.6026, 'learning_rate': 0.00010209653716222364, 'epoch': 8.52}

 71%|███████   | 19950/28080 [39:25:59<16:05:52,  7.13s/it]
 71%|███████   | 19951/28080 [39:26:06<16:05:28,  7.13s/it]
                                                           
{'loss': 0.6102, 'learning_rate': 0.00010207329017982975, 'epoch': 8.52}

 71%|███████   | 19951/28080 [39:26:06<16:05:28,  7.13s/it]
 71%|███████   | 19952/28080 [39:26:13<16:03:43,  7.11s/it]
                                                           
{'loss': 0.6182, 'learning_rate': 0.00010205004516544811, 'epoch': 8.52}

 71%|███████   | 19952/28080 [39:26:13<16:03:43,  7.11s/it]
 71%|███████   | 19953/28080 [39:26:20<16:01:23,  7.10s/it]
                                                           
{'loss': 0.6169, 'learning_rate': 0.000102026802119388, 'epoch': 8.52}

 71%|███████   | 19953/28080 [39:26:20<16:01:23,  7.10s/it]
 71%|███████   | 19954/28080 [39:26:27<16:00:54,  7.10s/it]
                                                           
{'loss': 0.6039, 'learning_rate': 0.00010200356104195852, 'epoch': 8.52}

 71%|███████   | 19954/28080 [39:26:27<16:00:54,  7.10s/it]
 71%|███████   | 19955/28080 [39:26:34<15:59:03,  7.08s/it]
                                                           
{'loss': 0.6077, 'learning_rate': 0.0001019803219334691, 'epoch': 8.52}

 71%|███████   | 19955/28080 [39:26:34<15:59:03,  7.08s/it]
 71%|███████   | 19956/28080 [39:26:41<15:55:50,  7.06s/it]
                                                           
{'loss': 0.5962, 'learning_rate': 0.00010195708479422869, 'epoch': 8.53}

 71%|███████   | 19956/28080 [39:26:41<15:55:50,  7.06s/it]
 71%|███████   | 19957/28080 [39:26:48<15:52:46,  7.04s/it]
                                                           
{'loss': 0.6159, 'learning_rate': 0.00010193384962454672, 'epoch': 8.53}

 71%|███████   | 19957/28080 [39:26:48<15:52:46,  7.04s/it]
 71%|███████   | 19958/28080 [39:26:55<15:47:54,  7.00s/it]
                                                           
{'loss': 0.6153, 'learning_rate': 0.00010191061642473193, 'epoch': 8.53}

 71%|███████   | 19958/28080 [39:26:55<15:47:54,  7.00s/it]
 71%|███████   | 19959/28080 [39:27:02<15:49:08,  7.01s/it]
                                                           
{'loss': 0.6205, 'learning_rate': 0.00010188738519509371, 'epoch': 8.53}

 71%|███████   | 19959/28080 [39:27:02<15:49:08,  7.01s/it]
 71%|███████   | 19960/28080 [39:27:09<15:49:38,  7.02s/it]
                                                           
{'loss': 0.6248, 'learning_rate': 0.00010186415593594094, 'epoch': 8.53}

 71%|███████   | 19960/28080 [39:27:09<15:49:38,  7.02s/it]
 71%|███████   | 19961/28080 [39:27:16<15:46:13,  6.99s/it]
                                                           
{'loss': 0.6214, 'learning_rate': 0.00010184092864758288, 'epoch': 8.53}

 71%|███████   | 19961/28080 [39:27:16<15:46:13,  6.99s/it]
 71%|███████   | 19962/28080 [39:27:23<15:46:45,  7.00s/it]
                                                           
{'loss': 0.6105, 'learning_rate': 0.00010181770333032839, 'epoch': 8.53}

 71%|███████   | 19962/28080 [39:27:23<15:46:45,  7.00s/it]
 71%|███████   | 19963/28080 [39:27:30<15:50:56,  7.03s/it]
                                                           
{'loss': 0.6134, 'learning_rate': 0.00010179447998448649, 'epoch': 8.53}

 71%|███████   | 19963/28080 [39:27:30<15:50:56,  7.03s/it]
 71%|███████   | 19964/28080 [39:27:37<15:52:22,  7.04s/it]
                                                           
{'loss': 0.6042, 'learning_rate': 0.00010177125861036604, 'epoch': 8.53}

 71%|███████   | 19964/28080 [39:27:37<15:52:22,  7.04s/it]
 71%|███████   | 19965/28080 [39:27:44<15:54:03,  7.05s/it]
                                                           
{'loss': 0.5981, 'learning_rate': 0.00010174803920827615, 'epoch': 8.53}

 71%|███████   | 19965/28080 [39:27:44<15:54:03,  7.05s/it]
 71%|███████   | 19966/28080 [39:27:51<15:54:38,  7.06s/it]
                                                           
{'loss': 0.6136, 'learning_rate': 0.00010172482177852568, 'epoch': 8.53}

 71%|███████   | 19966/28080 [39:27:51<15:54:38,  7.06s/it]
 71%|███████   | 19967/28080 [39:27:59<15:59:03,  7.09s/it]
                                                           
{'loss': 0.5995, 'learning_rate': 0.0001017016063214235, 'epoch': 8.53}

 71%|███████   | 19967/28080 [39:27:59<15:59:03,  7.09s/it]
 71%|███████   | 19968/28080 [39:28:06<15:56:11,  7.07s/it]
                                                           
{'loss': 0.6102, 'learning_rate': 0.00010167839283727842, 'epoch': 8.53}

 71%|███████   | 19968/28080 [39:28:06<15:56:11,  7.07s/it]
 71%|███████   | 19969/28080 [39:28:13<15:58:19,  7.09s/it]
                                                           
{'loss': 0.598, 'learning_rate': 0.00010165518132639925, 'epoch': 8.53}

 71%|███████   | 19969/28080 [39:28:13<15:58:19,  7.09s/it]
 71%|███████   | 19970/28080 [39:28:20<16:03:56,  7.13s/it]
                                                           
{'loss': 0.6074, 'learning_rate': 0.00010163197178909492, 'epoch': 8.53}

 71%|███████   | 19970/28080 [39:28:20<16:03:56,  7.13s/it]
 71%|███████   | 19971/28080 [39:28:27<16:01:12,  7.11s/it]
                                                           
{'loss': 0.6181, 'learning_rate': 0.00010160876422567416, 'epoch': 8.53}

 71%|███████   | 19971/28080 [39:28:27<16:01:12,  7.11s/it]
 71%|███████   | 19972/28080 [39:28:34<16:03:00,  7.13s/it]
                                                           
{'loss': 0.5985, 'learning_rate': 0.00010158555863644569, 'epoch': 8.53}

 71%|███████   | 19972/28080 [39:28:34<16:03:00,  7.13s/it]
 71%|███████   | 19973/28080 [39:28:41<16:01:46,  7.12s/it]
                                                           
{'loss': 0.5925, 'learning_rate': 0.00010156235502171817, 'epoch': 8.53}

 71%|███████   | 19973/28080 [39:28:41<16:01:46,  7.12s/it]
 71%|███████   | 19974/28080 [39:28:48<16:02:25,  7.12s/it]
                                                           
{'loss': 0.613, 'learning_rate': 0.0001015391533818005, 'epoch': 8.53}

 71%|███████   | 19974/28080 [39:28:48<16:02:25,  7.12s/it]
 71%|███████   | 19975/28080 [39:28:56<16:08:31,  7.17s/it]
                                                           
{'loss': 0.5873, 'learning_rate': 0.00010151595371700112, 'epoch': 8.53}

 71%|███████   | 19975/28080 [39:28:56<16:08:31,  7.17s/it]
 71%|███████   | 19976/28080 [39:29:03<16:11:05,  7.19s/it]
                                                           
{'loss': 0.6026, 'learning_rate': 0.00010149275602762898, 'epoch': 8.53}

 71%|███████   | 19976/28080 [39:29:03<16:11:05,  7.19s/it]
 71%|███████   | 19977/28080 [39:29:10<16:10:32,  7.19s/it]
                                                           
{'loss': 0.5958, 'learning_rate': 0.00010146956031399232, 'epoch': 8.53}

 71%|███████   | 19977/28080 [39:29:10<16:10:32,  7.19s/it]
 71%|███████   | 19978/28080 [39:29:17<16:04:18,  7.14s/it]
                                                           
{'loss': 0.6105, 'learning_rate': 0.00010144636657640002, 'epoch': 8.53}

 71%|███████   | 19978/28080 [39:29:17<16:04:18,  7.14s/it]
 71%|███████   | 19979/28080 [39:29:24<16:01:05,  7.12s/it]
                                                           
{'loss': 0.6215, 'learning_rate': 0.00010142317481516047, 'epoch': 8.53}

 71%|███████   | 19979/28080 [39:29:24<16:01:05,  7.12s/it]
 71%|███████   | 19980/28080 [39:29:31<15:58:33,  7.10s/it]
                                                           
{'loss': 0.5895, 'learning_rate': 0.00010139998503058239, 'epoch': 8.54}

 71%|███████   | 19980/28080 [39:29:31<15:58:33,  7.10s/it]
 71%|███████   | 19981/28080 [39:29:38<15:56:24,  7.09s/it]
                                                           
{'loss': 0.5921, 'learning_rate': 0.00010137679722297421, 'epoch': 8.54}

 71%|███████   | 19981/28080 [39:29:38<15:56:24,  7.09s/it]
 71%|███████   | 19982/28080 [39:29:45<15:58:25,  7.10s/it]
                                                           
{'loss': 0.6026, 'learning_rate': 0.00010135361139264443, 'epoch': 8.54}

 71%|███████   | 19982/28080 [39:29:45<15:58:25,  7.10s/it]
 71%|███████   | 19983/28080 [39:29:52<15:57:23,  7.09s/it]
                                                           
{'loss': 0.5944, 'learning_rate': 0.0001013304275399014, 'epoch': 8.54}

 71%|███████   | 19983/28080 [39:29:52<15:57:23,  7.09s/it]
 71%|███████   | 19984/28080 [39:29:59<15:53:10,  7.06s/it]
                                                           
{'loss': 0.6139, 'learning_rate': 0.00010130724566505375, 'epoch': 8.54}

 71%|███████   | 19984/28080 [39:29:59<15:53:10,  7.06s/it]
 71%|███████   | 19985/28080 [39:30:07<15:54:55,  7.08s/it]
                                                           
{'loss': 0.6431, 'learning_rate': 0.00010128406576840982, 'epoch': 8.54}

 71%|███████   | 19985/28080 [39:30:07<15:54:55,  7.08s/it]
 71%|███████   | 19986/28080 [39:30:14<16:02:31,  7.14s/it]
                                                           
{'loss': 0.6006, 'learning_rate': 0.00010126088785027793, 'epoch': 8.54}

 71%|███████   | 19986/28080 [39:30:14<16:02:31,  7.14s/it]
 71%|███████   | 19987/28080 [39:30:21<15:58:55,  7.11s/it]
                                                           
{'loss': 0.5935, 'learning_rate': 0.00010123771191096642, 'epoch': 8.54}

 71%|███████   | 19987/28080 [39:30:21<15:58:55,  7.11s/it]
 71%|███████   | 19988/28080 [39:30:28<15:59:41,  7.12s/it]
                                                           
{'loss': 0.5955, 'learning_rate': 0.00010121453795078376, 'epoch': 8.54}

 71%|███████   | 19988/28080 [39:30:28<15:59:41,  7.12s/it]
 71%|███████   | 19989/28080 [39:30:35<16:01:50,  7.13s/it]
                                                           
{'loss': 0.6065, 'learning_rate': 0.00010119136597003812, 'epoch': 8.54}

 71%|███████   | 19989/28080 [39:30:35<16:01:50,  7.13s/it]
 71%|███████   | 19990/28080 [39:30:42<16:00:26,  7.12s/it]
                                                           
{'loss': 0.5999, 'learning_rate': 0.00010116819596903799, 'epoch': 8.54}

 71%|███████   | 19990/28080 [39:30:42<16:00:26,  7.12s/it]
 71%|███████   | 19991/28080 [39:30:49<16:01:37,  7.13s/it]
                                                           
{'loss': 0.602, 'learning_rate': 0.00010114502794809128, 'epoch': 8.54}

 71%|███████   | 19991/28080 [39:30:49<16:01:37,  7.13s/it]
 71%|███████   | 19992/28080 [39:30:57<16:02:07,  7.14s/it]
                                                           
{'loss': 0.6119, 'learning_rate': 0.00010112186190750652, 'epoch': 8.54}

 71%|███████   | 19992/28080 [39:30:57<16:02:07,  7.14s/it]
 71%|███████   | 19993/28080 [39:31:04<15:59:41,  7.12s/it]
                                                           
{'loss': 0.6158, 'learning_rate': 0.00010109869784759179, 'epoch': 8.54}

 71%|███████   | 19993/28080 [39:31:04<15:59:41,  7.12s/it]
 71%|███████   | 19994/28080 [39:31:11<16:01:24,  7.13s/it]
                                                           
{'loss': 0.5843, 'learning_rate': 0.00010107553576865517, 'epoch': 8.54}

 71%|███████   | 19994/28080 [39:31:11<16:01:24,  7.13s/it]
 71%|███████   | 19995/28080 [39:31:18<15:59:10,  7.12s/it]
                                                           
{'loss': 0.5994, 'learning_rate': 0.00010105237567100503, 'epoch': 8.54}

 71%|███████   | 19995/28080 [39:31:18<15:59:10,  7.12s/it]
 71%|███████   | 19996/28080 [39:31:25<15:54:20,  7.08s/it]
                                                           
{'loss': 0.6236, 'learning_rate': 0.00010102921755494934, 'epoch': 8.54}

 71%|███████   | 19996/28080 [39:31:25<15:54:20,  7.08s/it]
 71%|███████   | 19997/28080 [39:31:32<15:53:56,  7.08s/it]
                                                           
{'loss': 0.6129, 'learning_rate': 0.00010100606142079624, 'epoch': 8.54}

 71%|███████   | 19997/28080 [39:31:32<15:53:56,  7.08s/it]
 71%|███████   | 19998/28080 [39:31:39<15:54:29,  7.09s/it]
                                                           
{'loss': 0.6104, 'learning_rate': 0.0001009829072688537, 'epoch': 8.54}

 71%|███████   | 19998/28080 [39:31:39<15:54:29,  7.09s/it]
 71%|███████   | 19999/28080 [39:31:46<15:52:37,  7.07s/it]
                                                           
{'loss': 0.6191, 'learning_rate': 0.00010095975509942992, 'epoch': 8.54}

 71%|███████   | 19999/28080 [39:31:46<15:52:37,  7.07s/it]
 71%|███████   | 20000/28080 [39:31:53<15:54:22,  7.09s/it]
                                                           
{'loss': 0.6009, 'learning_rate': 0.00010093660491283285, 'epoch': 8.54}

 71%|███████   | 20000/28080 [39:31:53<15:54:22,  7.09s/it]
 71%|███████   | 20001/28080 [39:32:00<15:56:02,  7.10s/it]
                                                           
{'loss': 0.6053, 'learning_rate': 0.00010091345670937049, 'epoch': 8.54}

 71%|███████   | 20001/28080 [39:32:00<15:56:02,  7.10s/it]
 71%|███████   | 20002/28080 [39:32:07<15:53:38,  7.08s/it]
                                                           
{'loss': 0.6477, 'learning_rate': 0.00010089031048935068, 'epoch': 8.54}

 71%|███████   | 20002/28080 [39:32:07<15:53:38,  7.08s/it]
 71%|███████   | 20003/28080 [39:32:15<15:55:12,  7.10s/it]
                                                           
{'loss': 0.585, 'learning_rate': 0.00010086716625308154, 'epoch': 8.55}

 71%|███████   | 20003/28080 [39:32:15<15:55:12,  7.10s/it]
 71%|███████   | 20004/28080 [39:32:22<15:53:27,  7.08s/it]
                                                           
{'loss': 0.6181, 'learning_rate': 0.00010084402400087092, 'epoch': 8.55}

 71%|███████   | 20004/28080 [39:32:22<15:53:27,  7.08s/it]
 71%|███████   | 20005/28080 [39:32:29<15:52:09,  7.07s/it]
                                                           
{'loss': 0.5994, 'learning_rate': 0.00010082088373302667, 'epoch': 8.55}

 71%|███████   | 20005/28080 [39:32:29<15:52:09,  7.07s/it]
 71%|███████   | 20006/28080 [39:32:36<15:53:35,  7.09s/it]
                                                           
{'loss': 0.5871, 'learning_rate': 0.00010079774544985656, 'epoch': 8.55}

 71%|███████   | 20006/28080 [39:32:36<15:53:35,  7.09s/it]
 71%|███████▏  | 20007/28080 [39:32:43<15:54:29,  7.09s/it]
                                                           
{'loss': 0.5989, 'learning_rate': 0.00010077460915166864, 'epoch': 8.55}

 71%|███████▏  | 20007/28080 [39:32:43<15:54:29,  7.09s/it]
 71%|███████▏  | 20008/28080 [39:32:50<15:54:47,  7.10s/it]
                                                           
{'loss': 0.6107, 'learning_rate': 0.0001007514748387705, 'epoch': 8.55}

 71%|███████▏  | 20008/28080 [39:32:50<15:54:47,  7.10s/it]
 71%|███████▏  | 20009/28080 [39:32:57<15:56:49,  7.11s/it]
                                                           
{'loss': 0.6138, 'learning_rate': 0.00010072834251147012, 'epoch': 8.55}

 71%|███████▏  | 20009/28080 [39:32:57<15:56:49,  7.11s/it]
 71%|███████▏  | 20010/28080 [39:33:04<15:54:57,  7.10s/it]
                                                           
{'loss': 0.6016, 'learning_rate': 0.00010070521217007513, 'epoch': 8.55}

 71%|███████▏  | 20010/28080 [39:33:04<15:54:57,  7.10s/it]
 71%|███████▏  | 20011/28080 [39:33:11<15:54:42,  7.10s/it]
                                                           
{'loss': 0.5974, 'learning_rate': 0.00010068208381489327, 'epoch': 8.55}

 71%|███████▏  | 20011/28080 [39:33:11<15:54:42,  7.10s/it]
 71%|███████▏  | 20012/28080 [39:33:18<15:53:04,  7.09s/it]
                                                           
{'loss': 0.6056, 'learning_rate': 0.00010065895744623216, 'epoch': 8.55}

 71%|███████▏  | 20012/28080 [39:33:18<15:53:04,  7.09s/it]
 71%|███████▏  | 20013/28080 [39:33:25<15:51:02,  7.07s/it]
                                                           
{'loss': 0.596, 'learning_rate': 0.00010063583306439964, 'epoch': 8.55}

 71%|███████▏  | 20013/28080 [39:33:25<15:51:02,  7.07s/it]
 71%|███████▏  | 20014/28080 [39:33:32<15:50:11,  7.07s/it]
                                                           
{'loss': 0.6233, 'learning_rate': 0.0001006127106697033, 'epoch': 8.55}

 71%|███████▏  | 20014/28080 [39:33:33<15:50:11,  7.07s/it]
 71%|███████▏  | 20015/28080 [39:33:40<15:50:07,  7.07s/it]
                                                           
{'loss': 0.6078, 'learning_rate': 0.00010058959026245067, 'epoch': 8.55}

 71%|███████▏  | 20015/28080 [39:33:40<15:50:07,  7.07s/it]
 71%|███████▏  | 20016/28080 [39:33:47<15:46:32,  7.04s/it]
                                                           
{'loss': 0.6069, 'learning_rate': 0.00010056647184294937, 'epoch': 8.55}

 71%|███████▏  | 20016/28080 [39:33:47<15:46:32,  7.04s/it]
 71%|███████▏  | 20017/28080 [39:33:54<15:48:57,  7.06s/it]
                                                           
{'loss': 0.6, 'learning_rate': 0.00010054335541150706, 'epoch': 8.55}

 71%|███████▏  | 20017/28080 [39:33:54<15:48:57,  7.06s/it]
 71%|███████▏  | 20018/28080 [39:34:01<15:50:49,  7.08s/it]
                                                           
{'loss': 0.6133, 'learning_rate': 0.00010052024096843124, 'epoch': 8.55}

 71%|███████▏  | 20018/28080 [39:34:01<15:50:49,  7.08s/it]
 71%|███████▏  | 20019/28080 [39:34:08<15:52:23,  7.09s/it]
                                                           
{'loss': 0.6117, 'learning_rate': 0.00010049712851402937, 'epoch': 8.55}

 71%|███████▏  | 20019/28080 [39:34:08<15:52:23,  7.09s/it]
 71%|███████▏  | 20020/28080 [39:34:15<15:52:51,  7.09s/it]
                                                           
{'loss': 0.5897, 'learning_rate': 0.00010047401804860901, 'epoch': 8.55}

 71%|███████▏  | 20020/28080 [39:34:15<15:52:51,  7.09s/it]
 71%|███████▏  | 20021/28080 [39:34:22<15:51:14,  7.08s/it]
                                                           
{'loss': 0.6139, 'learning_rate': 0.00010045090957247747, 'epoch': 8.55}

 71%|███████▏  | 20021/28080 [39:34:22<15:51:14,  7.08s/it]
 71%|███████▏  | 20022/28080 [39:34:29<15:54:01,  7.10s/it]
                                                           
{'loss': 0.6006, 'learning_rate': 0.0001004278030859424, 'epoch': 8.55}

 71%|███████▏  | 20022/28080 [39:34:29<15:54:01,  7.10s/it]
 71%|███████▏  | 20023/28080 [39:34:36<15:52:49,  7.10s/it]
                                                           
{'loss': 0.6007, 'learning_rate': 0.000100404698589311, 'epoch': 8.55}

 71%|███████▏  | 20023/28080 [39:34:36<15:52:49,  7.10s/it]
 71%|███████▏  | 20024/28080 [39:34:43<15:45:24,  7.04s/it]
                                                           
{'loss': 0.6385, 'learning_rate': 0.00010038159608289093, 'epoch': 8.55}

 71%|███████▏  | 20024/28080 [39:34:43<15:45:24,  7.04s/it]
 71%|███████▏  | 20025/28080 [39:34:50<15:47:24,  7.06s/it]
                                                           
{'loss': 0.613, 'learning_rate': 0.00010035849556698922, 'epoch': 8.55}

 71%|███████▏  | 20025/28080 [39:34:50<15:47:24,  7.06s/it]
 71%|███████▏  | 20026/28080 [39:34:57<15:48:38,  7.07s/it]
                                                           
{'loss': 0.6331, 'learning_rate': 0.00010033539704191343, 'epoch': 8.55}

 71%|███████▏  | 20026/28080 [39:34:57<15:48:38,  7.07s/it]
 71%|███████▏  | 20027/28080 [39:35:04<15:46:44,  7.05s/it]
                                                           
{'loss': 0.593, 'learning_rate': 0.00010031230050797069, 'epoch': 8.56}

 71%|███████▏  | 20027/28080 [39:35:04<15:46:44,  7.05s/it]
 71%|███████▏  | 20028/28080 [39:35:11<15:46:36,  7.05s/it]
                                                           
{'loss': 0.5936, 'learning_rate': 0.00010028920596546845, 'epoch': 8.56}

 71%|███████▏  | 20028/28080 [39:35:11<15:46:36,  7.05s/it]
 71%|███████▏  | 20029/28080 [39:35:19<15:46:57,  7.06s/it]
                                                           
{'loss': 0.5982, 'learning_rate': 0.00010026611341471389, 'epoch': 8.56}

 71%|███████▏  | 20029/28080 [39:35:19<15:46:57,  7.06s/it]
 71%|███████▏  | 20030/28080 [39:35:26<15:45:04,  7.04s/it]
                                                           
{'loss': 0.6076, 'learning_rate': 0.00010024302285601422, 'epoch': 8.56}

 71%|███████▏  | 20030/28080 [39:35:26<15:45:04,  7.04s/it]
 71%|███████▏  | 20031/28080 [39:35:33<15:48:27,  7.07s/it]
                                                           
{'loss': 0.5894, 'learning_rate': 0.00010021993428967652, 'epoch': 8.56}

 71%|███████▏  | 20031/28080 [39:35:33<15:48:27,  7.07s/it]
 71%|███████▏  | 20032/28080 [39:35:40<15:49:02,  7.08s/it]
                                                           
{'loss': 0.6144, 'learning_rate': 0.00010019684771600818, 'epoch': 8.56}

 71%|███████▏  | 20032/28080 [39:35:40<15:49:02,  7.08s/it]
 71%|███████▏  | 20033/28080 [39:35:47<15:46:40,  7.06s/it]
                                                           
{'loss': 0.6044, 'learning_rate': 0.00010017376313531623, 'epoch': 8.56}

 71%|███████▏  | 20033/28080 [39:35:47<15:46:40,  7.06s/it]
 71%|███████▏  | 20034/28080 [39:35:54<15:50:58,  7.09s/it]
                                                           
{'loss': 0.6042, 'learning_rate': 0.00010015068054790783, 'epoch': 8.56}

 71%|███████▏  | 20034/28080 [39:35:54<15:50:58,  7.09s/it]
 71%|███████▏  | 20035/28080 [39:36:01<15:50:17,  7.09s/it]
                                                           
{'loss': 0.5954, 'learning_rate': 0.0001001275999540899, 'epoch': 8.56}

 71%|███████▏  | 20035/28080 [39:36:01<15:50:17,  7.09s/it]
 71%|███████▏  | 20036/28080 [39:36:08<15:50:26,  7.09s/it]
                                                           
{'loss': 0.6232, 'learning_rate': 0.00010010452135416976, 'epoch': 8.56}

 71%|███████▏  | 20036/28080 [39:36:08<15:50:26,  7.09s/it]
 71%|███████▏  | 20037/28080 [39:36:15<15:53:07,  7.11s/it]
                                                           
{'loss': 0.6256, 'learning_rate': 0.0001000814447484542, 'epoch': 8.56}

 71%|███████▏  | 20037/28080 [39:36:15<15:53:07,  7.11s/it]
 71%|███████▏  | 20038/28080 [39:36:22<15:52:19,  7.11s/it]
                                                           
{'loss': 0.6074, 'learning_rate': 0.00010005837013725056, 'epoch': 8.56}

 71%|███████▏  | 20038/28080 [39:36:22<15:52:19,  7.11s/it]
 71%|███████▏  | 20039/28080 [39:36:29<15:51:44,  7.10s/it]
                                                           
{'loss': 0.5817, 'learning_rate': 0.00010003529752086543, 'epoch': 8.56}

 71%|███████▏  | 20039/28080 [39:36:29<15:51:44,  7.10s/it]
 71%|███████▏  | 20040/28080 [39:36:37<15:52:08,  7.11s/it]
                                                           
{'loss': 0.6162, 'learning_rate': 0.00010001222689960607, 'epoch': 8.56}

 71%|███████▏  | 20040/28080 [39:36:37<15:52:08,  7.11s/it]
 71%|███████▏  | 20041/28080 [39:36:44<15:52:17,  7.11s/it]
                                                           
{'loss': 0.5937, 'learning_rate': 9.99891582737792e-05, 'epoch': 8.56}

 71%|███████▏  | 20041/28080 [39:36:44<15:52:17,  7.11s/it]
 71%|███████▏  | 20042/28080 [39:36:51<15:49:44,  7.09s/it]
                                                           
{'loss': 0.5872, 'learning_rate': 9.996609164369189e-05, 'epoch': 8.56}

 71%|███████▏  | 20042/28080 [39:36:51<15:49:44,  7.09s/it]
 71%|███████▏  | 20043/28080 [39:36:58<15:52:02,  7.11s/it]
                                                           
{'loss': 0.614, 'learning_rate': 9.994302700965106e-05, 'epoch': 8.56}

 71%|███████▏  | 20043/28080 [39:36:58<15:52:02,  7.11s/it]
 71%|███████▏  | 20044/28080 [39:37:05<15:53:42,  7.12s/it]
                                                           
{'loss': 0.6228, 'learning_rate': 9.991996437196324e-05, 'epoch': 8.56}

 71%|███████▏  | 20044/28080 [39:37:05<15:53:42,  7.12s/it]
 71%|███████▏  | 20045/28080 [39:37:12<15:57:05,  7.15s/it]
                                                           
{'loss': 0.5803, 'learning_rate': 9.989690373093558e-05, 'epoch': 8.56}

 71%|███████▏  | 20045/28080 [39:37:12<15:57:05,  7.15s/it]
 71%|███████▏  | 20046/28080 [39:37:19<15:52:54,  7.12s/it]
                                                           
{'loss': 0.5966, 'learning_rate': 9.987384508687466e-05, 'epoch': 8.56}

 71%|███████▏  | 20046/28080 [39:37:19<15:52:54,  7.12s/it]
 71%|███████▏  | 20047/28080 [39:37:26<15:51:32,  7.11s/it]
                                                           
{'loss': 0.5945, 'learning_rate': 9.985078844008747e-05, 'epoch': 8.56}

 71%|███████▏  | 20047/28080 [39:37:26<15:51:32,  7.11s/it]
 71%|███████▏  | 20048/28080 [39:37:34<15:52:36,  7.12s/it]
                                                           
{'loss': 0.6147, 'learning_rate': 9.982773379088062e-05, 'epoch': 8.56}

 71%|███████▏  | 20048/28080 [39:37:34<15:52:36,  7.12s/it]
 71%|███████▏  | 20049/28080 [39:37:41<15:53:01,  7.12s/it]
                                                           
{'loss': 0.6075, 'learning_rate': 9.980468113956085e-05, 'epoch': 8.56}

 71%|███████▏  | 20049/28080 [39:37:41<15:53:01,  7.12s/it]
 71%|███████▏  | 20050/28080 [39:37:48<15:50:34,  7.10s/it]
                                                           
{'loss': 0.6065, 'learning_rate': 9.978163048643473e-05, 'epoch': 8.57}

 71%|███████▏  | 20050/28080 [39:37:48<15:50:34,  7.10s/it]
 71%|███████▏  | 20051/28080 [39:37:55<15:49:36,  7.10s/it]
                                                           
{'loss': 0.6032, 'learning_rate': 9.975858183180919e-05, 'epoch': 8.57}

 71%|███████▏  | 20051/28080 [39:37:55<15:49:36,  7.10s/it]
 71%|███████▏  | 20052/28080 [39:38:02<15:45:30,  7.07s/it]
                                                           
{'loss': 0.6052, 'learning_rate': 9.973553517599069e-05, 'epoch': 8.57}

 71%|███████▏  | 20052/28080 [39:38:02<15:45:30,  7.07s/it]
 71%|███████▏  | 20053/28080 [39:38:09<15:48:49,  7.09s/it]
                                                           
{'loss': 0.6164, 'learning_rate': 9.971249051928588e-05, 'epoch': 8.57}

 71%|███████▏  | 20053/28080 [39:38:09<15:48:49,  7.09s/it]
 71%|███████▏  | 20054/28080 [39:38:16<15:46:32,  7.08s/it]
                                                           
{'loss': 0.618, 'learning_rate': 9.968944786200127e-05, 'epoch': 8.57}

 71%|███████▏  | 20054/28080 [39:38:16<15:46:32,  7.08s/it]
 71%|███████▏  | 20055/28080 [39:38:23<15:49:32,  7.10s/it]
                                                           
{'loss': 0.5918, 'learning_rate': 9.966640720444356e-05, 'epoch': 8.57}

 71%|███████▏  | 20055/28080 [39:38:23<15:49:32,  7.10s/it]
 71%|███████▏  | 20056/28080 [39:38:30<15:55:48,  7.15s/it]
                                                           
{'loss': 0.5907, 'learning_rate': 9.96433685469191e-05, 'epoch': 8.57}

 71%|███████▏  | 20056/28080 [39:38:30<15:55:48,  7.15s/it]
 71%|███████▏  | 20057/28080 [39:38:37<15:52:58,  7.13s/it]
                                                           
{'loss': 0.6091, 'learning_rate': 9.962033188973463e-05, 'epoch': 8.57}

 71%|███████▏  | 20057/28080 [39:38:37<15:52:58,  7.13s/it]
 71%|███████▏  | 20058/28080 [39:38:45<15:51:46,  7.12s/it]
                                                           
{'loss': 0.5948, 'learning_rate': 9.95972972331965e-05, 'epoch': 8.57}

 71%|███████▏  | 20058/28080 [39:38:45<15:51:46,  7.12s/it]
 71%|███████▏  | 20059/28080 [39:38:52<15:49:56,  7.11s/it]
                                                           
{'loss': 0.6139, 'learning_rate': 9.957426457761118e-05, 'epoch': 8.57}

 71%|███████▏  | 20059/28080 [39:38:52<15:49:56,  7.11s/it]
 71%|███████▏  | 20060/28080 [39:38:59<15:44:14,  7.06s/it]
                                                           
{'loss': 0.6128, 'learning_rate': 9.955123392328497e-05, 'epoch': 8.57}

 71%|███████▏  | 20060/28080 [39:38:59<15:44:14,  7.06s/it]
 71%|███████▏  | 20061/28080 [39:39:06<15:46:08,  7.08s/it]
                                                           
{'loss': 0.6111, 'learning_rate': 9.952820527052447e-05, 'epoch': 8.57}

 71%|███████▏  | 20061/28080 [39:39:06<15:46:08,  7.08s/it]
 71%|███████▏  | 20062/28080 [39:39:13<15:43:18,  7.06s/it]
                                                           
{'loss': 0.6148, 'learning_rate': 9.950517861963599e-05, 'epoch': 8.57}

 71%|███████▏  | 20062/28080 [39:39:13<15:43:18,  7.06s/it]
 71%|███████▏  | 20063/28080 [39:39:20<15:42:37,  7.05s/it]
                                                           
{'loss': 0.5954, 'learning_rate': 9.948215397092586e-05, 'epoch': 8.57}

 71%|███████▏  | 20063/28080 [39:39:20<15:42:37,  7.05s/it]
 71%|███████▏  | 20064/28080 [39:39:27<15:45:20,  7.08s/it]
                                                           
{'loss': 0.6146, 'learning_rate': 9.945913132470027e-05, 'epoch': 8.57}

 71%|███████▏  | 20064/28080 [39:39:27<15:45:20,  7.08s/it]
 71%|███████▏  | 20065/28080 [39:39:34<15:47:22,  7.09s/it]
                                                           
{'loss': 0.628, 'learning_rate': 9.943611068126574e-05, 'epoch': 8.57}

 71%|███████▏  | 20065/28080 [39:39:34<15:47:22,  7.09s/it]
 71%|███████▏  | 20066/28080 [39:39:41<15:46:21,  7.09s/it]
                                                           
{'loss': 0.6118, 'learning_rate': 9.94130920409284e-05, 'epoch': 8.57}

 71%|███████▏  | 20066/28080 [39:39:41<15:46:21,  7.09s/it]
 71%|███████▏  | 20067/28080 [39:39:48<15:45:41,  7.08s/it]
                                                           
{'loss': 0.6223, 'learning_rate': 9.939007540399455e-05, 'epoch': 8.57}

 71%|███████▏  | 20067/28080 [39:39:48<15:45:41,  7.08s/it]
 71%|███████▏  | 20068/28080 [39:39:55<15:51:19,  7.12s/it]
                                                           
{'loss': 0.6169, 'learning_rate': 9.936706077077037e-05, 'epoch': 8.57}

 71%|███████▏  | 20068/28080 [39:39:55<15:51:19,  7.12s/it]
 71%|███████▏  | 20069/28080 [39:40:02<15:49:39,  7.11s/it]
                                                           
{'loss': 0.5971, 'learning_rate': 9.934404814156195e-05, 'epoch': 8.57}

 71%|███████▏  | 20069/28080 [39:40:02<15:49:39,  7.11s/it]
 71%|███████▏  | 20070/28080 [39:40:10<15:50:00,  7.12s/it]
                                                           
{'loss': 0.5938, 'learning_rate': 9.932103751667565e-05, 'epoch': 8.57}

 71%|███████▏  | 20070/28080 [39:40:10<15:50:00,  7.12s/it]
 71%|███████▏  | 20071/28080 [39:40:17<15:49:40,  7.11s/it]
                                                           
{'loss': 0.5928, 'learning_rate': 9.92980288964174e-05, 'epoch': 8.57}

 71%|███████▏  | 20071/28080 [39:40:17<15:49:40,  7.11s/it]
 71%|███████▏  | 20072/28080 [39:40:24<15:49:20,  7.11s/it]
                                                           
{'loss': 0.5915, 'learning_rate': 9.927502228109358e-05, 'epoch': 8.57}

 71%|███████▏  | 20072/28080 [39:40:24<15:49:20,  7.11s/it]
 71%|███████▏  | 20073/28080 [39:40:31<15:49:40,  7.12s/it]
                                                           
{'loss': 0.6117, 'learning_rate': 9.925201767100991e-05, 'epoch': 8.57}

 71%|███████▏  | 20073/28080 [39:40:31<15:49:40,  7.12s/it]
 71%|███████▏  | 20074/28080 [39:40:38<15:48:41,  7.11s/it]
                                                           
{'loss': 0.5926, 'learning_rate': 9.922901506647272e-05, 'epoch': 8.58}

 71%|███████▏  | 20074/28080 [39:40:38<15:48:41,  7.11s/it]
 71%|███████▏  | 20075/28080 [39:40:45<15:48:43,  7.11s/it]
                                                           
{'loss': 0.595, 'learning_rate': 9.920601446778785e-05, 'epoch': 8.58}

 71%|███████▏  | 20075/28080 [39:40:45<15:48:43,  7.11s/it]
 71%|███████▏  | 20076/28080 [39:40:52<15:49:10,  7.12s/it]
                                                           
{'loss': 0.6005, 'learning_rate': 9.918301587526149e-05, 'epoch': 8.58}

 71%|███████▏  | 20076/28080 [39:40:52<15:49:10,  7.12s/it]
 71%|███████▏  | 20077/28080 [39:40:59<15:48:59,  7.11s/it]
                                                           
{'loss': 0.5981, 'learning_rate': 9.916001928919952e-05, 'epoch': 8.58}

 71%|███████▏  | 20077/28080 [39:40:59<15:48:59,  7.11s/it]
 72%|███████▏  | 20078/28080 [39:41:06<15:42:29,  7.07s/it]
                                                           
{'loss': 0.6202, 'learning_rate': 9.913702470990788e-05, 'epoch': 8.58}

 72%|███████▏  | 20078/28080 [39:41:06<15:42:29,  7.07s/it]
 72%|███████▏  | 20079/28080 [39:41:13<15:42:02,  7.06s/it]
                                                           
{'loss': 0.5958, 'learning_rate': 9.911403213769238e-05, 'epoch': 8.58}

 72%|███████▏  | 20079/28080 [39:41:13<15:42:02,  7.06s/it]
 72%|███████▏  | 20080/28080 [39:41:20<15:39:57,  7.05s/it]
                                                           
{'loss': 0.6187, 'learning_rate': 9.909104157285912e-05, 'epoch': 8.58}

 72%|███████▏  | 20080/28080 [39:41:20<15:39:57,  7.05s/it]
 72%|███████▏  | 20081/28080 [39:41:27<15:40:24,  7.05s/it]
                                                           
{'loss': 0.6124, 'learning_rate': 9.906805301571387e-05, 'epoch': 8.58}

 72%|███████▏  | 20081/28080 [39:41:27<15:40:24,  7.05s/it]
 72%|███████▏  | 20082/28080 [39:41:35<15:47:53,  7.11s/it]
                                                           
{'loss': 0.6043, 'learning_rate': 9.904506646656248e-05, 'epoch': 8.58}

 72%|███████▏  | 20082/28080 [39:41:35<15:47:53,  7.11s/it]
 72%|███████▏  | 20083/28080 [39:41:42<15:44:43,  7.09s/it]
                                                           
{'loss': 0.6066, 'learning_rate': 9.902208192571063e-05, 'epoch': 8.58}

 72%|███████▏  | 20083/28080 [39:41:42<15:44:43,  7.09s/it]
 72%|███████▏  | 20084/28080 [39:41:49<15:46:50,  7.10s/it]
                                                           
{'loss': 0.6188, 'learning_rate': 9.899909939346436e-05, 'epoch': 8.58}

 72%|███████▏  | 20084/28080 [39:41:49<15:46:50,  7.10s/it]
 72%|███████▏  | 20085/28080 [39:41:56<15:42:19,  7.07s/it]
                                                           
{'loss': 0.6167, 'learning_rate': 9.897611887012916e-05, 'epoch': 8.58}

 72%|███████▏  | 20085/28080 [39:41:56<15:42:19,  7.07s/it]
 72%|███████▏  | 20086/28080 [39:42:03<15:46:47,  7.11s/it]
                                                           
{'loss': 0.6125, 'learning_rate': 9.895314035601107e-05, 'epoch': 8.58}

 72%|███████▏  | 20086/28080 [39:42:03<15:46:47,  7.11s/it]
 72%|███████▏  | 20087/28080 [39:42:10<15:44:22,  7.09s/it]
                                                           
{'loss': 0.6093, 'learning_rate': 9.893016385141548e-05, 'epoch': 8.58}

 72%|███████▏  | 20087/28080 [39:42:10<15:44:22,  7.09s/it]
 72%|███████▏  | 20088/28080 [39:42:17<15:46:04,  7.10s/it]
                                                           
{'loss': 0.6053, 'learning_rate': 9.890718935664827e-05, 'epoch': 8.58}

 72%|███████▏  | 20088/28080 [39:42:17<15:46:04,  7.10s/it]
 72%|███████▏  | 20089/28080 [39:42:24<15:46:00,  7.10s/it]
                                                           
{'loss': 0.6199, 'learning_rate': 9.888421687201496e-05, 'epoch': 8.58}

 72%|███████▏  | 20089/28080 [39:42:24<15:46:00,  7.10s/it]
 72%|███████▏  | 20090/28080 [39:42:32<15:48:28,  7.12s/it]
                                                           
{'loss': 0.597, 'learning_rate': 9.886124639782135e-05, 'epoch': 8.58}

 72%|███████▏  | 20090/28080 [39:42:32<15:48:28,  7.12s/it]
 72%|███████▏  | 20091/28080 [39:42:39<15:42:10,  7.08s/it]
                                                           
{'loss': 0.6029, 'learning_rate': 9.883827793437292e-05, 'epoch': 8.58}

 72%|███████▏  | 20091/28080 [39:42:39<15:42:10,  7.08s/it]
 72%|███████▏  | 20092/28080 [39:42:46<15:41:21,  7.07s/it]
                                                           
{'loss': 0.6062, 'learning_rate': 9.881531148197526e-05, 'epoch': 8.58}

 72%|███████▏  | 20092/28080 [39:42:46<15:41:21,  7.07s/it]
 72%|███████▏  | 20093/28080 [39:42:53<15:39:55,  7.06s/it]
                                                           
{'loss': 0.6029, 'learning_rate': 9.87923470409339e-05, 'epoch': 8.58}

 72%|███████▏  | 20093/28080 [39:42:53<15:39:55,  7.06s/it]
 72%|███████▏  | 20094/28080 [39:43:00<15:37:32,  7.04s/it]
                                                           
{'loss': 0.6138, 'learning_rate': 9.876938461155426e-05, 'epoch': 8.58}

 72%|███████▏  | 20094/28080 [39:43:00<15:37:32,  7.04s/it]
 72%|███████▏  | 20095/28080 [39:43:07<15:37:42,  7.05s/it]
                                                           
{'loss': 0.6082, 'learning_rate': 9.874642419414206e-05, 'epoch': 8.58}

 72%|███████▏  | 20095/28080 [39:43:07<15:37:42,  7.05s/it]
 72%|███████▏  | 20096/28080 [39:43:14<15:43:55,  7.09s/it]
                                                           
{'loss': 0.6089, 'learning_rate': 9.872346578900265e-05, 'epoch': 8.58}

 72%|███████▏  | 20096/28080 [39:43:14<15:43:55,  7.09s/it]
 72%|███████▏  | 20097/28080 [39:43:21<15:43:48,  7.09s/it]
                                                           
{'loss': 0.6071, 'learning_rate': 9.870050939644145e-05, 'epoch': 8.59}

 72%|███████▏  | 20097/28080 [39:43:21<15:43:48,  7.09s/it]
 72%|███████▏  | 20098/28080 [39:43:28<15:44:03,  7.10s/it]
                                                           
{'loss': 0.5985, 'learning_rate': 9.867755501676382e-05, 'epoch': 8.59}

 72%|███████▏  | 20098/28080 [39:43:28<15:44:03,  7.10s/it]
 72%|███████▏  | 20099/28080 [39:43:35<15:42:25,  7.09s/it]
                                                           
{'loss': 0.6139, 'learning_rate': 9.865460265027529e-05, 'epoch': 8.59}

 72%|███████▏  | 20099/28080 [39:43:35<15:42:25,  7.09s/it]
 72%|███████▏  | 20100/28080 [39:43:42<15:45:28,  7.11s/it]
                                                           
{'loss': 0.586, 'learning_rate': 9.863165229728113e-05, 'epoch': 8.59}

 72%|███████▏  | 20100/28080 [39:43:42<15:45:28,  7.11s/it]
 72%|███████▏  | 20101/28080 [39:43:49<15:45:25,  7.11s/it]
                                                           
{'loss': 0.5881, 'learning_rate': 9.860870395808669e-05, 'epoch': 8.59}

 72%|███████▏  | 20101/28080 [39:43:49<15:45:25,  7.11s/it]
 72%|███████▏  | 20102/28080 [39:43:57<15:50:47,  7.15s/it]
                                                           
{'loss': 0.6108, 'learning_rate': 9.858575763299716e-05, 'epoch': 8.59}

 72%|███████▏  | 20102/28080 [39:43:57<15:50:47,  7.15s/it]
 72%|███████▏  | 20103/28080 [39:44:04<15:47:46,  7.13s/it]
                                                           
{'loss': 0.583, 'learning_rate': 9.8562813322318e-05, 'epoch': 8.59}

 72%|███████▏  | 20103/28080 [39:44:04<15:47:46,  7.13s/it]
 72%|███████▏  | 20104/28080 [39:44:11<15:46:36,  7.12s/it]
                                                           
{'loss': 0.6264, 'learning_rate': 9.853987102635431e-05, 'epoch': 8.59}

 72%|███████▏  | 20104/28080 [39:44:11<15:46:36,  7.12s/it]
 72%|███████▏  | 20105/28080 [39:44:18<15:45:45,  7.12s/it]
                                                           
{'loss': 0.615, 'learning_rate': 9.851693074541155e-05, 'epoch': 8.59}

 72%|███████▏  | 20105/28080 [39:44:18<15:45:45,  7.12s/it]
 72%|███████▏  | 20106/28080 [39:44:25<15:47:36,  7.13s/it]
                                                           
{'loss': 0.5909, 'learning_rate': 9.849399247979456e-05, 'epoch': 8.59}

 72%|███████▏  | 20106/28080 [39:44:25<15:47:36,  7.13s/it]
 72%|███████▏  | 20107/28080 [39:44:32<15:46:28,  7.12s/it]
                                                           
{'loss': 0.6248, 'learning_rate': 9.847105622980881e-05, 'epoch': 8.59}

 72%|███████▏  | 20107/28080 [39:44:32<15:46:28,  7.12s/it]
 72%|███████▏  | 20108/28080 [39:44:39<15:47:54,  7.13s/it]
                                                           
{'loss': 0.614, 'learning_rate': 9.844812199575926e-05, 'epoch': 8.59}

 72%|███████▏  | 20108/28080 [39:44:39<15:47:54,  7.13s/it]
 72%|███████▏  | 20109/28080 [39:44:46<15:46:41,  7.13s/it]
                                                           
{'loss': 0.6107, 'learning_rate': 9.842518977795115e-05, 'epoch': 8.59}

 72%|███████▏  | 20109/28080 [39:44:46<15:46:41,  7.13s/it]
 72%|███████▏  | 20110/28080 [39:44:53<15:40:05,  7.08s/it]
                                                           
{'loss': 0.6061, 'learning_rate': 9.840225957668955e-05, 'epoch': 8.59}

 72%|███████▏  | 20110/28080 [39:44:53<15:40:05,  7.08s/it]
 72%|███████▏  | 20111/28080 [39:45:00<15:37:53,  7.06s/it]
                                                           
{'loss': 0.6114, 'learning_rate': 9.837933139227948e-05, 'epoch': 8.59}

 72%|███████▏  | 20111/28080 [39:45:00<15:37:53,  7.06s/it]
 72%|███████▏  | 20112/28080 [39:45:08<15:39:52,  7.08s/it]
                                                           
{'loss': 0.5901, 'learning_rate': 9.83564052250259e-05, 'epoch': 8.59}

 72%|███████▏  | 20112/28080 [39:45:08<15:39:52,  7.08s/it]
 72%|███████▏  | 20113/28080 [39:45:15<15:39:22,  7.07s/it]
                                                           
{'loss': 0.6206, 'learning_rate': 9.833348107523399e-05, 'epoch': 8.59}

 72%|███████▏  | 20113/28080 [39:45:15<15:39:22,  7.07s/it]
 72%|███████▏  | 20114/28080 [39:45:22<15:42:03,  7.10s/it]
                                                           
{'loss': 0.6435, 'learning_rate': 9.831055894320864e-05, 'epoch': 8.59}

 72%|███████▏  | 20114/28080 [39:45:22<15:42:03,  7.10s/it]
 72%|███████▏  | 20115/28080 [39:45:29<15:45:33,  7.12s/it]
                                                           
{'loss': 0.6419, 'learning_rate': 9.828763882925481e-05, 'epoch': 8.59}

 72%|███████▏  | 20115/28080 [39:45:29<15:45:33,  7.12s/it]
 72%|███████▏  | 20116/28080 [39:45:36<15:39:41,  7.08s/it]
                                                           
{'loss': 0.6315, 'learning_rate': 9.826472073367738e-05, 'epoch': 8.59}

 72%|███████▏  | 20116/28080 [39:45:36<15:39:41,  7.08s/it]
 72%|███████▏  | 20117/28080 [39:45:43<15:37:59,  7.07s/it]
                                                           
{'loss': 0.6233, 'learning_rate': 9.824180465678137e-05, 'epoch': 8.59}

 72%|███████▏  | 20117/28080 [39:45:43<15:37:59,  7.07s/it]
 72%|███████▏  | 20118/28080 [39:45:50<15:39:45,  7.08s/it]
                                                           
{'loss': 0.6111, 'learning_rate': 9.821889059887157e-05, 'epoch': 8.59}

 72%|███████▏  | 20118/28080 [39:45:50<15:39:45,  7.08s/it]
 72%|███████▏  | 20119/28080 [39:45:57<15:44:38,  7.12s/it]
                                                           
{'loss': 0.6053, 'learning_rate': 9.819597856025278e-05, 'epoch': 8.59}

 72%|███████▏  | 20119/28080 [39:45:57<15:44:38,  7.12s/it]
 72%|███████▏  | 20120/28080 [39:46:04<15:45:51,  7.13s/it]
                                                           
{'loss': 0.6232, 'learning_rate': 9.817306854123006e-05, 'epoch': 8.6}

 72%|███████▏  | 20120/28080 [39:46:04<15:45:51,  7.13s/it]
 72%|███████▏  | 20121/28080 [39:46:12<15:45:41,  7.13s/it]
                                                           
{'loss': 0.6129, 'learning_rate': 9.815016054210787e-05, 'epoch': 8.6}

 72%|███████▏  | 20121/28080 [39:46:12<15:45:41,  7.13s/it]
 72%|███████▏  | 20122/28080 [39:46:19<15:44:57,  7.12s/it]
                                                           
{'loss': 0.6044, 'learning_rate': 9.812725456319121e-05, 'epoch': 8.6}

 72%|███████▏  | 20122/28080 [39:46:19<15:44:57,  7.12s/it]
 72%|███████▏  | 20123/28080 [39:46:26<15:47:37,  7.15s/it]
                                                           
{'loss': 0.5997, 'learning_rate': 9.810435060478467e-05, 'epoch': 8.6}

 72%|███████▏  | 20123/28080 [39:46:26<15:47:37,  7.15s/it]
 72%|███████▏  | 20124/28080 [39:46:33<15:52:28,  7.18s/it]
                                                           
{'loss': 0.6088, 'learning_rate': 9.808144866719312e-05, 'epoch': 8.6}

 72%|███████▏  | 20124/28080 [39:46:33<15:52:28,  7.18s/it]
 72%|███████▏  | 20125/28080 [39:46:40<15:50:55,  7.17s/it]
                                                           
{'loss': 0.6213, 'learning_rate': 9.805854875072118e-05, 'epoch': 8.6}

 72%|███████▏  | 20125/28080 [39:46:40<15:50:55,  7.17s/it]
 72%|███████▏  | 20126/28080 [39:46:47<15:44:21,  7.12s/it]
                                                           
{'loss': 0.604, 'learning_rate': 9.803565085567351e-05, 'epoch': 8.6}

 72%|███████▏  | 20126/28080 [39:46:47<15:44:21,  7.12s/it]
 72%|███████▏  | 20127/28080 [39:46:54<15:46:00,  7.14s/it]
                                                           
{'loss': 0.6186, 'learning_rate': 9.801275498235462e-05, 'epoch': 8.6}

 72%|███████▏  | 20127/28080 [39:46:54<15:46:00,  7.14s/it]
 72%|███████▏  | 20128/28080 [39:47:02<15:40:51,  7.10s/it]
                                                           
{'loss': 0.5974, 'learning_rate': 9.798986113106934e-05, 'epoch': 8.6}

 72%|███████▏  | 20128/28080 [39:47:02<15:40:51,  7.10s/it]
 72%|███████▏  | 20129/28080 [39:47:09<15:44:34,  7.13s/it]
                                                           
{'loss': 0.5793, 'learning_rate': 9.796696930212212e-05, 'epoch': 8.6}

 72%|███████▏  | 20129/28080 [39:47:09<15:44:34,  7.13s/it]
 72%|███████▏  | 20130/28080 [39:47:16<15:42:28,  7.11s/it]
                                                           
{'loss': 0.5929, 'learning_rate': 9.794407949581752e-05, 'epoch': 8.6}

 72%|███████▏  | 20130/28080 [39:47:16<15:42:28,  7.11s/it]
 72%|███████▏  | 20131/28080 [39:47:23<15:44:58,  7.13s/it]
                                                           
{'loss': 0.6137, 'learning_rate': 9.792119171246e-05, 'epoch': 8.6}

 72%|███████▏  | 20131/28080 [39:47:23<15:44:58,  7.13s/it]
 72%|███████▏  | 20132/28080 [39:47:30<15:43:26,  7.12s/it]
                                                           
{'loss': 0.59, 'learning_rate': 9.789830595235425e-05, 'epoch': 8.6}

 72%|███████▏  | 20132/28080 [39:47:30<15:43:26,  7.12s/it]
 72%|███████▏  | 20133/28080 [39:47:37<15:34:34,  7.06s/it]
                                                           
{'loss': 0.6202, 'learning_rate': 9.787542221580451e-05, 'epoch': 8.6}

 72%|███████▏  | 20133/28080 [39:47:37<15:34:34,  7.06s/it]
 72%|███████▏  | 20134/28080 [39:47:44<15:38:57,  7.09s/it]
                                                           
{'loss': 0.5886, 'learning_rate': 9.785254050311552e-05, 'epoch': 8.6}

 72%|███████▏  | 20134/28080 [39:47:44<15:38:57,  7.09s/it]
 72%|███████▏  | 20135/28080 [39:47:51<15:37:05,  7.08s/it]
                                                           
{'loss': 0.6302, 'learning_rate': 9.782966081459132e-05, 'epoch': 8.6}

 72%|███████▏  | 20135/28080 [39:47:51<15:37:05,  7.08s/it]
 72%|███████▏  | 20136/28080 [39:47:58<15:30:20,  7.03s/it]
                                                           
{'loss': 0.6303, 'learning_rate': 9.78067831505366e-05, 'epoch': 8.6}

 72%|███████▏  | 20136/28080 [39:47:58<15:30:20,  7.03s/it]
 72%|███████▏  | 20137/28080 [39:48:05<15:31:45,  7.04s/it]
                                                           
{'loss': 0.6117, 'learning_rate': 9.778390751125554e-05, 'epoch': 8.6}

 72%|███████▏  | 20137/28080 [39:48:05<15:31:45,  7.04s/it]
 72%|███████▏  | 20138/28080 [39:48:12<15:35:07,  7.06s/it]
                                                           
{'loss': 0.612, 'learning_rate': 9.776103389705262e-05, 'epoch': 8.6}

 72%|███████▏  | 20138/28080 [39:48:12<15:35:07,  7.06s/it]
 72%|███████▏  | 20139/28080 [39:48:19<15:38:20,  7.09s/it]
                                                           
{'loss': 0.5988, 'learning_rate': 9.773816230823213e-05, 'epoch': 8.6}

 72%|███████▏  | 20139/28080 [39:48:19<15:38:20,  7.09s/it]
 72%|███████▏  | 20140/28080 [39:48:26<15:35:35,  7.07s/it]
                                                           
{'loss': 0.6145, 'learning_rate': 9.771529274509827e-05, 'epoch': 8.6}

 72%|███████▏  | 20140/28080 [39:48:26<15:35:35,  7.07s/it]
 72%|███████▏  | 20141/28080 [39:48:33<15:32:29,  7.05s/it]
                                                           
{'loss': 0.5959, 'learning_rate': 9.769242520795527e-05, 'epoch': 8.6}

 72%|███████▏  | 20141/28080 [39:48:33<15:32:29,  7.05s/it]
 72%|███████▏  | 20142/28080 [39:48:41<15:34:10,  7.06s/it]
                                                           
{'loss': 0.6042, 'learning_rate': 9.766955969710752e-05, 'epoch': 8.6}

 72%|███████▏  | 20142/28080 [39:48:41<15:34:10,  7.06s/it]
 72%|███████▏  | 20143/28080 [39:48:48<15:33:08,  7.05s/it]
                                                           
{'loss': 0.6204, 'learning_rate': 9.764669621285913e-05, 'epoch': 8.6}

 72%|███████▏  | 20143/28080 [39:48:48<15:33:08,  7.05s/it]
 72%|███████▏  | 20144/28080 [39:48:55<15:34:31,  7.07s/it]
                                                           
{'loss': 0.5998, 'learning_rate': 9.762383475551426e-05, 'epoch': 8.61}

 72%|███████▏  | 20144/28080 [39:48:55<15:34:31,  7.07s/it]
 72%|███████▏  | 20145/28080 [39:49:02<15:36:37,  7.08s/it]
                                                           
{'loss': 0.6232, 'learning_rate': 9.760097532537706e-05, 'epoch': 8.61}

 72%|███████▏  | 20145/28080 [39:49:02<15:36:37,  7.08s/it]
 72%|███████▏  | 20146/28080 [39:49:09<15:33:07,  7.06s/it]
                                                           
{'loss': 0.6096, 'learning_rate': 9.75781179227516e-05, 'epoch': 8.61}

 72%|███████▏  | 20146/28080 [39:49:09<15:33:07,  7.06s/it]
 72%|███████▏  | 20147/28080 [39:49:16<15:36:32,  7.08s/it]
                                                           
{'loss': 0.6021, 'learning_rate': 9.755526254794208e-05, 'epoch': 8.61}

 72%|███████▏  | 20147/28080 [39:49:16<15:36:32,  7.08s/it]
 72%|███████▏  | 20148/28080 [39:49:23<15:35:50,  7.08s/it]
                                                           
{'loss': 0.6141, 'learning_rate': 9.753240920125255e-05, 'epoch': 8.61}

 72%|███████▏  | 20148/28080 [39:49:23<15:35:50,  7.08s/it]
 72%|███████▏  | 20149/28080 [39:49:30<15:34:27,  7.07s/it]
                                                           
{'loss': 0.5963, 'learning_rate': 9.750955788298704e-05, 'epoch': 8.61}

 72%|███████▏  | 20149/28080 [39:49:30<15:34:27,  7.07s/it]
 72%|███████▏  | 20150/28080 [39:49:37<15:38:24,  7.10s/it]
                                                           
{'loss': 0.5836, 'learning_rate': 9.748670859344947e-05, 'epoch': 8.61}

 72%|███████▏  | 20150/28080 [39:49:37<15:38:24,  7.10s/it]
 72%|███████▏  | 20151/28080 [39:49:44<15:33:49,  7.07s/it]
                                                           
{'loss': 0.6121, 'learning_rate': 9.746386133294396e-05, 'epoch': 8.61}

 72%|███████▏  | 20151/28080 [39:49:44<15:33:49,  7.07s/it]
 72%|███████▏  | 20152/28080 [39:49:51<15:32:01,  7.05s/it]
                                                           
{'loss': 0.6165, 'learning_rate': 9.744101610177434e-05, 'epoch': 8.61}

 72%|███████▏  | 20152/28080 [39:49:51<15:32:01,  7.05s/it]
 72%|███████▏  | 20153/28080 [39:49:58<15:34:35,  7.07s/it]
                                                           
{'loss': 0.5995, 'learning_rate': 9.741817290024476e-05, 'epoch': 8.61}

 72%|███████▏  | 20153/28080 [39:49:58<15:34:35,  7.07s/it]
 72%|███████▏  | 20154/28080 [39:50:05<15:36:18,  7.09s/it]
                                                           
{'loss': 0.6117, 'learning_rate': 9.739533172865884e-05, 'epoch': 8.61}

 72%|███████▏  | 20154/28080 [39:50:05<15:36:18,  7.09s/it]
 72%|███████▏  | 20155/28080 [39:50:13<15:38:58,  7.11s/it]
                                                           
{'loss': 0.5963, 'learning_rate': 9.737249258732067e-05, 'epoch': 8.61}

 72%|███████▏  | 20155/28080 [39:50:13<15:38:58,  7.11s/it]
 72%|███████▏  | 20156/28080 [39:50:20<15:37:37,  7.10s/it]
                                                           
{'loss': 0.5854, 'learning_rate': 9.734965547653394e-05, 'epoch': 8.61}

 72%|███████▏  | 20156/28080 [39:50:20<15:37:37,  7.10s/it]
 72%|███████▏  | 20157/28080 [39:50:27<15:33:15,  7.07s/it]
                                                           
{'loss': 0.6115, 'learning_rate': 9.732682039660264e-05, 'epoch': 8.61}

 72%|███████▏  | 20157/28080 [39:50:27<15:33:15,  7.07s/it]
 72%|███████▏  | 20158/28080 [39:50:34<15:36:02,  7.09s/it]
                                                           
{'loss': 0.5952, 'learning_rate': 9.73039873478305e-05, 'epoch': 8.61}

 72%|███████▏  | 20158/28080 [39:50:34<15:36:02,  7.09s/it]
 72%|███████▏  | 20159/28080 [39:50:41<15:37:22,  7.10s/it]
                                                           
{'loss': 0.621, 'learning_rate': 9.728115633052129e-05, 'epoch': 8.61}

 72%|███████▏  | 20159/28080 [39:50:41<15:37:22,  7.10s/it]
 72%|███████▏  | 20160/28080 [39:50:48<15:37:38,  7.10s/it]
                                                           
{'loss': 0.5918, 'learning_rate': 9.725832734497866e-05, 'epoch': 8.61}

 72%|███████▏  | 20160/28080 [39:50:48<15:37:38,  7.10s/it]
 72%|███████▏  | 20161/28080 [39:50:55<15:37:35,  7.10s/it]
                                                           
{'loss': 0.6053, 'learning_rate': 9.723550039150647e-05, 'epoch': 8.61}

 72%|███████▏  | 20161/28080 [39:50:55<15:37:35,  7.10s/it]
 72%|███████▏  | 20162/28080 [39:51:02<15:40:08,  7.12s/it]
                                                           
{'loss': 0.5911, 'learning_rate': 9.721267547040838e-05, 'epoch': 8.61}

 72%|███████▏  | 20162/28080 [39:51:02<15:40:08,  7.12s/it]
 72%|███████▏  | 20163/28080 [39:51:09<15:36:45,  7.10s/it]
                                                           
{'loss': 0.5966, 'learning_rate': 9.718985258198801e-05, 'epoch': 8.61}

 72%|███████▏  | 20163/28080 [39:51:09<15:36:45,  7.10s/it]
 72%|███████▏  | 20164/28080 [39:51:16<15:33:44,  7.08s/it]
                                                           
{'loss': 0.6122, 'learning_rate': 9.716703172654892e-05, 'epoch': 8.61}

 72%|███████▏  | 20164/28080 [39:51:16<15:33:44,  7.08s/it]
 72%|███████▏  | 20165/28080 [39:51:24<15:34:30,  7.08s/it]
                                                           
{'loss': 0.6023, 'learning_rate': 9.714421290439487e-05, 'epoch': 8.61}

 72%|███████▏  | 20165/28080 [39:51:24<15:34:30,  7.08s/it]
 72%|███████▏  | 20166/28080 [39:51:30<15:30:22,  7.05s/it]
                                                           
{'loss': 0.5933, 'learning_rate': 9.712139611582931e-05, 'epoch': 8.61}

 72%|███████▏  | 20166/28080 [39:51:31<15:30:22,  7.05s/it]
 72%|███████▏  | 20167/28080 [39:51:38<15:32:56,  7.07s/it]
                                                           
{'loss': 0.5986, 'learning_rate': 9.709858136115604e-05, 'epoch': 8.62}

 72%|███████▏  | 20167/28080 [39:51:38<15:32:56,  7.07s/it]
 72%|███████▏  | 20168/28080 [39:51:45<15:34:21,  7.09s/it]
                                                           
{'loss': 0.5993, 'learning_rate': 9.70757686406783e-05, 'epoch': 8.62}

 72%|███████▏  | 20168/28080 [39:51:45<15:34:21,  7.09s/it]
 72%|███████▏  | 20169/28080 [39:51:52<15:35:00,  7.09s/it]
                                                           
{'loss': 0.6224, 'learning_rate': 9.705295795469962e-05, 'epoch': 8.62}

 72%|███████▏  | 20169/28080 [39:51:52<15:35:00,  7.09s/it]
 72%|███████▏  | 20170/28080 [39:51:59<15:36:25,  7.10s/it]
                                                           
{'loss': 0.6074, 'learning_rate': 9.703014930352363e-05, 'epoch': 8.62}

 72%|███████▏  | 20170/28080 [39:51:59<15:36:25,  7.10s/it]
 72%|███████▏  | 20171/28080 [39:52:06<15:33:36,  7.08s/it]
                                                           
{'loss': 0.6259, 'learning_rate': 9.70073426874536e-05, 'epoch': 8.62}

 72%|███████▏  | 20171/28080 [39:52:06<15:33:36,  7.08s/it]
 72%|███████▏  | 20172/28080 [39:52:13<15:32:31,  7.08s/it]
                                                           
{'loss': 0.6186, 'learning_rate': 9.698453810679314e-05, 'epoch': 8.62}

 72%|███████▏  | 20172/28080 [39:52:13<15:32:31,  7.08s/it]
 72%|███████▏  | 20173/28080 [39:52:20<15:35:59,  7.10s/it]
                                                           
{'loss': 0.5958, 'learning_rate': 9.696173556184553e-05, 'epoch': 8.62}

 72%|███████▏  | 20173/28080 [39:52:20<15:35:59,  7.10s/it]
 72%|███████▏  | 20174/28080 [39:52:27<15:37:29,  7.11s/it]
                                                           
{'loss': 0.6267, 'learning_rate': 9.693893505291415e-05, 'epoch': 8.62}

 72%|███████▏  | 20174/28080 [39:52:27<15:37:29,  7.11s/it]
 72%|███████▏  | 20175/28080 [39:52:34<15:34:05,  7.09s/it]
                                                           
{'loss': 0.6068, 'learning_rate': 9.691613658030226e-05, 'epoch': 8.62}

 72%|███████▏  | 20175/28080 [39:52:34<15:34:05,  7.09s/it]
 72%|███████▏  | 20176/28080 [39:52:41<15:33:37,  7.09s/it]
                                                           
{'loss': 0.6092, 'learning_rate': 9.689334014431333e-05, 'epoch': 8.62}

 72%|███████▏  | 20176/28080 [39:52:41<15:33:37,  7.09s/it]
 72%|███████▏  | 20177/28080 [39:52:49<15:35:14,  7.10s/it]
                                                           
{'loss': 0.5864, 'learning_rate': 9.687054574525056e-05, 'epoch': 8.62}

 72%|███████▏  | 20177/28080 [39:52:49<15:35:14,  7.10s/it]
 72%|███████▏  | 20178/28080 [39:52:56<15:33:47,  7.09s/it]
                                                           
{'loss': 0.6285, 'learning_rate': 9.684775338341719e-05, 'epoch': 8.62}

 72%|███████▏  | 20178/28080 [39:52:56<15:33:47,  7.09s/it]
 72%|███████▏  | 20179/28080 [39:53:03<15:41:11,  7.15s/it]
                                                           
{'loss': 0.598, 'learning_rate': 9.682496305911636e-05, 'epoch': 8.62}

 72%|███████▏  | 20179/28080 [39:53:03<15:41:11,  7.15s/it]
 72%|███████▏  | 20180/28080 [39:53:10<15:39:19,  7.13s/it]
                                                           
{'loss': 0.6094, 'learning_rate': 9.68021747726515e-05, 'epoch': 8.62}

 72%|███████▏  | 20180/28080 [39:53:10<15:39:19,  7.13s/it]
 72%|███████▏  | 20181/28080 [39:53:17<15:35:53,  7.11s/it]
                                                           
{'loss': 0.617, 'learning_rate': 9.677938852432555e-05, 'epoch': 8.62}

 72%|███████▏  | 20181/28080 [39:53:17<15:35:53,  7.11s/it]
 72%|███████▏  | 20182/28080 [39:53:24<15:35:28,  7.11s/it]
                                                           
{'loss': 0.6183, 'learning_rate': 9.675660431444195e-05, 'epoch': 8.62}

 72%|███████▏  | 20182/28080 [39:53:24<15:35:28,  7.11s/it]
 72%|███████▏  | 20183/28080 [39:53:31<15:36:04,  7.11s/it]
                                                           
{'loss': 0.5893, 'learning_rate': 9.673382214330345e-05, 'epoch': 8.62}

 72%|███████▏  | 20183/28080 [39:53:31<15:36:04,  7.11s/it]
 72%|███████▏  | 20184/28080 [39:53:38<15:32:29,  7.09s/it]
                                                           
{'loss': 0.6044, 'learning_rate': 9.671104201121344e-05, 'epoch': 8.62}

 72%|███████▏  | 20184/28080 [39:53:38<15:32:29,  7.09s/it]
 72%|███████▏  | 20185/28080 [39:53:46<15:35:53,  7.11s/it]
                                                           
{'loss': 0.6088, 'learning_rate': 9.668826391847477e-05, 'epoch': 8.62}

 72%|███████▏  | 20185/28080 [39:53:46<15:35:53,  7.11s/it]
 72%|███████▏  | 20186/28080 [39:53:53<15:31:33,  7.08s/it]
                                                           
{'loss': 0.5975, 'learning_rate': 9.66654878653907e-05, 'epoch': 8.62}

 72%|███████▏  | 20186/28080 [39:53:53<15:31:33,  7.08s/it]
 72%|███████▏  | 20187/28080 [39:54:00<15:35:21,  7.11s/it]
                                                           
{'loss': 0.6094, 'learning_rate': 9.664271385226408e-05, 'epoch': 8.62}

 72%|███████▏  | 20187/28080 [39:54:00<15:35:21,  7.11s/it]
 72%|███████▏  | 20188/28080 [39:54:07<15:32:42,  7.09s/it]
                                                           
{'loss': 0.5982, 'learning_rate': 9.6619941879398e-05, 'epoch': 8.62}

 72%|███████▏  | 20188/28080 [39:54:07<15:32:42,  7.09s/it]
 72%|███████▏  | 20189/28080 [39:54:14<15:34:49,  7.11s/it]
                                                           
{'loss': 0.6072, 'learning_rate': 9.659717194709522e-05, 'epoch': 8.62}

 72%|███████▏  | 20189/28080 [39:54:14<15:34:49,  7.11s/it]
 72%|███████▏  | 20190/28080 [39:54:21<15:34:40,  7.11s/it]
                                                           
{'loss': 0.5984, 'learning_rate': 9.657440405565893e-05, 'epoch': 8.62}

 72%|███████▏  | 20190/28080 [39:54:21<15:34:40,  7.11s/it]
 72%|███████▏  | 20191/28080 [39:54:28<15:35:22,  7.11s/it]
                                                           
{'loss': 0.6122, 'learning_rate': 9.65516382053919e-05, 'epoch': 8.63}

 72%|███████▏  | 20191/28080 [39:54:28<15:35:22,  7.11s/it]
 72%|███████▏  | 20192/28080 [39:54:35<15:36:33,  7.12s/it]
                                                           
{'loss': 0.6104, 'learning_rate': 9.652887439659702e-05, 'epoch': 8.63}

 72%|███████▏  | 20192/28080 [39:54:35<15:36:33,  7.12s/it]
 72%|███████▏  | 20193/28080 [39:54:42<15:37:51,  7.13s/it]
                                                           
{'loss': 0.5943, 'learning_rate': 9.650611262957715e-05, 'epoch': 8.63}

 72%|███████▏  | 20193/28080 [39:54:42<15:37:51,  7.13s/it]
 72%|███████▏  | 20194/28080 [39:54:50<15:35:37,  7.12s/it]
                                                           
{'loss': 0.6161, 'learning_rate': 9.6483352904635e-05, 'epoch': 8.63}

 72%|███████▏  | 20194/28080 [39:54:50<15:35:37,  7.12s/it]
 72%|███████▏  | 20195/28080 [39:54:57<15:32:32,  7.10s/it]
                                                           
{'loss': 0.6043, 'learning_rate': 9.646059522207357e-05, 'epoch': 8.63}

 72%|███████▏  | 20195/28080 [39:54:57<15:32:32,  7.10s/it]
 72%|███████▏  | 20196/28080 [39:55:04<15:30:40,  7.08s/it]
                                                           
{'loss': 0.6077, 'learning_rate': 9.643783958219551e-05, 'epoch': 8.63}

 72%|███████▏  | 20196/28080 [39:55:04<15:30:40,  7.08s/it]
 72%|███████▏  | 20197/28080 [39:55:11<15:33:46,  7.11s/it]
                                                           
{'loss': 0.6184, 'learning_rate': 9.641508598530357e-05, 'epoch': 8.63}

 72%|███████▏  | 20197/28080 [39:55:11<15:33:46,  7.11s/it]
 72%|███████▏  | 20198/28080 [39:55:18<15:36:46,  7.13s/it]
                                                           
{'loss': 0.604, 'learning_rate': 9.63923344317004e-05, 'epoch': 8.63}

 72%|███████▏  | 20198/28080 [39:55:18<15:36:46,  7.13s/it]
 72%|███████▏  | 20199/28080 [39:55:25<15:37:11,  7.14s/it]
                                                           
{'loss': 0.6195, 'learning_rate': 9.636958492168881e-05, 'epoch': 8.63}

 72%|███████▏  | 20199/28080 [39:55:25<15:37:11,  7.14s/it]
 72%|███████▏  | 20200/28080 [39:55:32<15:36:08,  7.13s/it]
                                                           
{'loss': 0.616, 'learning_rate': 9.634683745557132e-05, 'epoch': 8.63}

 72%|███████▏  | 20200/28080 [39:55:32<15:36:08,  7.13s/it]
 72%|███████▏  | 20201/28080 [39:55:39<15:36:11,  7.13s/it]
                                                           
{'loss': 0.6085, 'learning_rate': 9.632409203365084e-05, 'epoch': 8.63}

 72%|███████▏  | 20201/28080 [39:55:39<15:36:11,  7.13s/it]
 72%|███████▏  | 20202/28080 [39:55:46<15:35:42,  7.13s/it]
                                                           
{'loss': 0.617, 'learning_rate': 9.630134865622958e-05, 'epoch': 8.63}

 72%|███████▏  | 20202/28080 [39:55:47<15:35:42,  7.13s/it]
 72%|███████▏  | 20203/28080 [39:55:54<15:33:37,  7.11s/it]
                                                           
{'loss': 0.6118, 'learning_rate': 9.62786073236104e-05, 'epoch': 8.63}

 72%|███████▏  | 20203/28080 [39:55:54<15:33:37,  7.11s/it]
 72%|███████▏  | 20204/28080 [39:56:01<15:34:46,  7.12s/it]
                                                           
{'loss': 0.6026, 'learning_rate': 9.625586803609567e-05, 'epoch': 8.63}

 72%|███████▏  | 20204/28080 [39:56:01<15:34:46,  7.12s/it]
 72%|███████▏  | 20205/28080 [39:56:08<15:33:45,  7.11s/it]
                                                           
{'loss': 0.6306, 'learning_rate': 9.623313079398813e-05, 'epoch': 8.63}

 72%|███████▏  | 20205/28080 [39:56:08<15:33:45,  7.11s/it]
 72%|███████▏  | 20206/28080 [39:56:15<15:34:11,  7.12s/it]
                                                           
{'loss': 0.6044, 'learning_rate': 9.621039559759012e-05, 'epoch': 8.63}

 72%|███████▏  | 20206/28080 [39:56:15<15:34:11,  7.12s/it]
 72%|███████▏  | 20207/28080 [39:56:22<15:30:52,  7.09s/it]
                                                           
{'loss': 0.6181, 'learning_rate': 9.618766244720414e-05, 'epoch': 8.63}

 72%|███████▏  | 20207/28080 [39:56:22<15:30:52,  7.09s/it]
 72%|███████▏  | 20208/28080 [39:56:29<15:35:15,  7.13s/it]
                                                           
{'loss': 0.6154, 'learning_rate': 9.616493134313256e-05, 'epoch': 8.63}

 72%|███████▏  | 20208/28080 [39:56:29<15:35:15,  7.13s/it]
 72%|███████▏  | 20209/28080 [39:56:36<15:29:39,  7.09s/it]
                                                           
{'loss': 0.608, 'learning_rate': 9.614220228567797e-05, 'epoch': 8.63}

 72%|███████▏  | 20209/28080 [39:56:36<15:29:39,  7.09s/it]
 72%|███████▏  | 20210/28080 [39:56:43<15:29:42,  7.09s/it]
                                                           
{'loss': 0.6009, 'learning_rate': 9.611947527514261e-05, 'epoch': 8.63}

 72%|███████▏  | 20210/28080 [39:56:43<15:29:42,  7.09s/it]
 72%|███████▏  | 20211/28080 [39:56:50<15:24:27,  7.05s/it]
                                                           
{'loss': 0.6146, 'learning_rate': 9.609675031182891e-05, 'epoch': 8.63}

 72%|███████▏  | 20211/28080 [39:56:50<15:24:27,  7.05s/it]
 72%|███████▏  | 20212/28080 [39:56:57<15:26:37,  7.07s/it]
                                                           
{'loss': 0.6061, 'learning_rate': 9.607402739603907e-05, 'epoch': 8.63}

 72%|███████▏  | 20212/28080 [39:56:57<15:26:37,  7.07s/it]
 72%|███████▏  | 20213/28080 [39:57:04<15:22:35,  7.04s/it]
                                                           
{'loss': 0.6112, 'learning_rate': 9.605130652807559e-05, 'epoch': 8.63}

 72%|███████▏  | 20213/28080 [39:57:04<15:22:35,  7.04s/it]
 72%|███████▏  | 20214/28080 [39:57:11<15:24:28,  7.05s/it]
                                                           
{'loss': 0.6118, 'learning_rate': 9.602858770824058e-05, 'epoch': 8.64}

 72%|███████▏  | 20214/28080 [39:57:11<15:24:28,  7.05s/it]
 72%|███████▏  | 20215/28080 [39:57:18<15:25:30,  7.06s/it]
                                                           
{'loss': 0.5986, 'learning_rate': 9.600587093683655e-05, 'epoch': 8.64}

 72%|███████▏  | 20215/28080 [39:57:18<15:25:30,  7.06s/it]
 72%|███████▏  | 20216/28080 [39:57:26<15:30:04,  7.10s/it]
                                                           
{'loss': 0.5816, 'learning_rate': 9.598315621416543e-05, 'epoch': 8.64}

 72%|███████▏  | 20216/28080 [39:57:26<15:30:04,  7.10s/it]
 72%|███████▏  | 20217/28080 [39:57:33<15:35:18,  7.14s/it]
                                                           
{'loss': 0.5897, 'learning_rate': 9.596044354052944e-05, 'epoch': 8.64}

 72%|███████▏  | 20217/28080 [39:57:33<15:35:18,  7.14s/it]
 72%|███████▏  | 20218/28080 [39:57:40<15:34:42,  7.13s/it]
                                                           
{'loss': 0.628, 'learning_rate': 9.593773291623092e-05, 'epoch': 8.64}

 72%|███████▏  | 20218/28080 [39:57:40<15:34:42,  7.13s/it]
 72%|███████▏  | 20219/28080 [39:57:47<15:31:24,  7.11s/it]
                                                           
{'loss': 0.6235, 'learning_rate': 9.591502434157187e-05, 'epoch': 8.64}

 72%|███████▏  | 20219/28080 [39:57:47<15:31:24,  7.11s/it]
 72%|███████▏  | 20220/28080 [39:57:54<15:34:04,  7.13s/it]
                                                           
{'loss': 0.5901, 'learning_rate': 9.589231781685454e-05, 'epoch': 8.64}

 72%|███████▏  | 20220/28080 [39:57:54<15:34:04,  7.13s/it]
 72%|███████▏  | 20221/28080 [39:58:01<15:25:54,  7.07s/it]
                                                           
{'loss': 0.6105, 'learning_rate': 9.58696133423809e-05, 'epoch': 8.64}

 72%|███████▏  | 20221/28080 [39:58:01<15:25:54,  7.07s/it]
 72%|███████▏  | 20222/28080 [39:58:08<15:19:41,  7.02s/it]
                                                           
{'loss': 0.621, 'learning_rate': 9.584691091845307e-05, 'epoch': 8.64}

 72%|███████▏  | 20222/28080 [39:58:08<15:19:41,  7.02s/it]
 72%|███████▏  | 20223/28080 [39:58:15<15:24:53,  7.06s/it]
                                                           
{'loss': 0.6047, 'learning_rate': 9.582421054537299e-05, 'epoch': 8.64}

 72%|███████▏  | 20223/28080 [39:58:15<15:24:53,  7.06s/it]
 72%|███████▏  | 20224/28080 [39:58:22<15:26:50,  7.08s/it]
                                                           
{'loss': 0.5877, 'learning_rate': 9.58015122234428e-05, 'epoch': 8.64}

 72%|███████▏  | 20224/28080 [39:58:22<15:26:50,  7.08s/it]
 72%|███████▏  | 20225/28080 [39:58:30<15:31:51,  7.12s/it]
                                                           
{'loss': 0.6347, 'learning_rate': 9.577881595296442e-05, 'epoch': 8.64}

 72%|███████▏  | 20225/28080 [39:58:30<15:31:51,  7.12s/it]
 72%|███████▏  | 20226/28080 [39:58:37<15:29:08,  7.10s/it]
                                                           
{'loss': 0.6061, 'learning_rate': 9.575612173423978e-05, 'epoch': 8.64}

 72%|███████▏  | 20226/28080 [39:58:37<15:29:08,  7.10s/it]
 72%|███████▏  | 20227/28080 [39:58:44<15:31:04,  7.11s/it]
                                                           
{'loss': 0.5901, 'learning_rate': 9.573342956757075e-05, 'epoch': 8.64}

 72%|███████▏  | 20227/28080 [39:58:44<15:31:04,  7.11s/it]
 72%|███████▏  | 20228/28080 [39:58:51<15:27:17,  7.09s/it]
                                                           
{'loss': 0.5781, 'learning_rate': 9.571073945325937e-05, 'epoch': 8.64}

 72%|███████▏  | 20228/28080 [39:58:51<15:27:17,  7.09s/it]
 72%|███████▏  | 20229/28080 [39:58:58<15:26:56,  7.08s/it]
                                                           
{'loss': 0.6073, 'learning_rate': 9.568805139160741e-05, 'epoch': 8.64}

 72%|███████▏  | 20229/28080 [39:58:58<15:26:56,  7.08s/it]
 72%|███████▏  | 20230/28080 [39:59:05<15:29:31,  7.10s/it]
                                                           
{'loss': 0.6272, 'learning_rate': 9.566536538291675e-05, 'epoch': 8.64}

 72%|███████▏  | 20230/28080 [39:59:05<15:29:31,  7.10s/it]
 72%|███████▏  | 20231/28080 [39:59:12<15:30:08,  7.11s/it]
                                                           
{'loss': 0.5935, 'learning_rate': 9.56426814274891e-05, 'epoch': 8.64}

 72%|███████▏  | 20231/28080 [39:59:12<15:30:08,  7.11s/it]
 72%|███████▏  | 20232/28080 [39:59:19<15:27:25,  7.09s/it]
                                                           
{'loss': 0.6038, 'learning_rate': 9.561999952562642e-05, 'epoch': 8.64}

 72%|███████▏  | 20232/28080 [39:59:19<15:27:25,  7.09s/it]
 72%|███████▏  | 20233/28080 [39:59:26<15:26:14,  7.08s/it]
                                                           
{'loss': 0.6126, 'learning_rate': 9.55973196776303e-05, 'epoch': 8.64}

 72%|███████▏  | 20233/28080 [39:59:26<15:26:14,  7.08s/it]
 72%|███████▏  | 20234/28080 [39:59:33<15:24:25,  7.07s/it]
                                                           
{'loss': 0.6093, 'learning_rate': 9.557464188380264e-05, 'epoch': 8.64}

 72%|███████▏  | 20234/28080 [39:59:33<15:24:25,  7.07s/it]
 72%|███████▏  | 20235/28080 [39:59:40<15:27:02,  7.09s/it]
                                                           
{'loss': 0.6169, 'learning_rate': 9.555196614444503e-05, 'epoch': 8.64}

 72%|███████▏  | 20235/28080 [39:59:40<15:27:02,  7.09s/it]
 72%|███████▏  | 20236/28080 [39:59:47<15:24:42,  7.07s/it]
                                                           
{'loss': 0.6197, 'learning_rate': 9.55292924598592e-05, 'epoch': 8.64}

 72%|███████▏  | 20236/28080 [39:59:47<15:24:42,  7.07s/it]
 72%|███████▏  | 20237/28080 [39:59:54<15:22:50,  7.06s/it]
                                                           
{'loss': 0.6179, 'learning_rate': 9.550662083034668e-05, 'epoch': 8.65}

 72%|███████▏  | 20237/28080 [39:59:54<15:22:50,  7.06s/it]
 72%|███████▏  | 20238/28080 [40:00:02<15:25:19,  7.08s/it]
                                                           
{'loss': 0.5847, 'learning_rate': 9.548395125620927e-05, 'epoch': 8.65}

 72%|███████▏  | 20238/28080 [40:00:02<15:25:19,  7.08s/it]
 72%|███████▏  | 20239/28080 [40:00:09<15:26:10,  7.09s/it]
                                                           
{'loss': 0.6037, 'learning_rate': 9.546128373774848e-05, 'epoch': 8.65}

 72%|███████▏  | 20239/28080 [40:00:09<15:26:10,  7.09s/it]
 72%|███████▏  | 20240/28080 [40:00:16<15:26:02,  7.09s/it]
                                                           
{'loss': 0.5991, 'learning_rate': 9.54386182752659e-05, 'epoch': 8.65}

 72%|███████▏  | 20240/28080 [40:00:16<15:26:02,  7.09s/it]
 72%|███████▏  | 20241/28080 [40:00:23<15:24:21,  7.08s/it]
                                                           
{'loss': 0.5962, 'learning_rate': 9.541595486906304e-05, 'epoch': 8.65}

 72%|███████▏  | 20241/28080 [40:00:23<15:24:21,  7.08s/it]
 72%|███████▏  | 20242/28080 [40:00:30<15:27:56,  7.10s/it]
                                                           
{'loss': 0.6261, 'learning_rate': 9.539329351944134e-05, 'epoch': 8.65}

 72%|███████▏  | 20242/28080 [40:00:30<15:27:56,  7.10s/it]
 72%|███████▏  | 20243/28080 [40:00:37<15:30:17,  7.12s/it]
                                                           
{'loss': 0.6072, 'learning_rate': 9.537063422670248e-05, 'epoch': 8.65}

 72%|███████▏  | 20243/28080 [40:00:37<15:30:17,  7.12s/it]
 72%|███████▏  | 20244/28080 [40:00:44<15:30:25,  7.12s/it]
                                                           
{'loss': 0.6132, 'learning_rate': 9.534797699114778e-05, 'epoch': 8.65}

 72%|███████▏  | 20244/28080 [40:00:44<15:30:25,  7.12s/it]
 72%|███████▏  | 20245/28080 [40:00:52<15:36:21,  7.17s/it]
                                                           
{'loss': 0.5855, 'learning_rate': 9.532532181307871e-05, 'epoch': 8.65}

 72%|███████▏  | 20245/28080 [40:00:52<15:36:21,  7.17s/it]
 72%|███████▏  | 20246/28080 [40:00:59<15:36:18,  7.17s/it]
                                                           
{'loss': 0.5998, 'learning_rate': 9.530266869279657e-05, 'epoch': 8.65}

 72%|███████▏  | 20246/28080 [40:00:59<15:36:18,  7.17s/it]
 72%|███████▏  | 20247/28080 [40:01:06<15:36:55,  7.18s/it]
                                                           
{'loss': 0.6163, 'learning_rate': 9.528001763060293e-05, 'epoch': 8.65}

 72%|███████▏  | 20247/28080 [40:01:06<15:36:55,  7.18s/it]
 72%|███████▏  | 20248/28080 [40:01:13<15:36:03,  7.17s/it]
                                                           
{'loss': 0.6192, 'learning_rate': 9.525736862679893e-05, 'epoch': 8.65}

 72%|███████▏  | 20248/28080 [40:01:13<15:36:03,  7.17s/it]
 72%|███████▏  | 20249/28080 [40:01:20<15:32:51,  7.15s/it]
                                                           
{'loss': 0.6202, 'learning_rate': 9.52347216816862e-05, 'epoch': 8.65}

 72%|███████▏  | 20249/28080 [40:01:20<15:32:51,  7.15s/it]
 72%|███████▏  | 20250/28080 [40:01:27<15:30:35,  7.13s/it]
                                                           
{'loss': 0.5988, 'learning_rate': 9.521207679556564e-05, 'epoch': 8.65}

 72%|███████▏  | 20250/28080 [40:01:27<15:30:35,  7.13s/it]
 72%|███████▏  | 20251/28080 [40:01:34<15:27:28,  7.11s/it]
                                                           
{'loss': 0.6053, 'learning_rate': 9.518943396873883e-05, 'epoch': 8.65}

 72%|███████▏  | 20251/28080 [40:01:34<15:27:28,  7.11s/it]
 72%|███████▏  | 20252/28080 [40:01:41<15:24:57,  7.09s/it]
                                                           
{'loss': 0.6203, 'learning_rate': 9.516679320150679e-05, 'epoch': 8.65}

 72%|███████▏  | 20252/28080 [40:01:41<15:24:57,  7.09s/it]
 72%|███████▏  | 20253/28080 [40:01:49<15:27:55,  7.11s/it]
                                                           
{'loss': 0.6135, 'learning_rate': 9.514415449417091e-05, 'epoch': 8.65}

 72%|███████▏  | 20253/28080 [40:01:49<15:27:55,  7.11s/it]
 72%|███████▏  | 20254/28080 [40:01:56<15:28:32,  7.12s/it]
                                                           
{'loss': 0.6052, 'learning_rate': 9.512151784703232e-05, 'epoch': 8.65}

 72%|███████▏  | 20254/28080 [40:01:56<15:28:32,  7.12s/it]
 72%|███████▏  | 20255/28080 [40:02:03<15:29:34,  7.13s/it]
                                                           
{'loss': 0.614, 'learning_rate': 9.509888326039214e-05, 'epoch': 8.65}

 72%|███████▏  | 20255/28080 [40:02:03<15:29:34,  7.13s/it]
 72%|███████▏  | 20256/28080 [40:02:10<15:25:37,  7.10s/it]
                                                           
{'loss': 0.6031, 'learning_rate': 9.507625073455142e-05, 'epoch': 8.65}

 72%|███████▏  | 20256/28080 [40:02:10<15:25:37,  7.10s/it]
 72%|███████▏  | 20257/28080 [40:02:17<15:23:54,  7.09s/it]
                                                           
{'loss': 0.5983, 'learning_rate': 9.505362026981146e-05, 'epoch': 8.65}

 72%|███████▏  | 20257/28080 [40:02:17<15:23:54,  7.09s/it]
 72%|███████▏  | 20258/28080 [40:02:24<15:20:28,  7.06s/it]
                                                           
{'loss': 0.5976, 'learning_rate': 9.503099186647324e-05, 'epoch': 8.65}

 72%|███████▏  | 20258/28080 [40:02:24<15:20:28,  7.06s/it]
 72%|███████▏  | 20259/28080 [40:02:31<15:18:49,  7.05s/it]
                                                           
{'loss': 0.6023, 'learning_rate': 9.50083655248378e-05, 'epoch': 8.65}

 72%|███████▏  | 20259/28080 [40:02:31<15:18:49,  7.05s/it]
 72%|███████▏  | 20260/28080 [40:02:38<15:16:26,  7.03s/it]
                                                           
{'loss': 0.6197, 'learning_rate': 9.498574124520604e-05, 'epoch': 8.65}

 72%|███████▏  | 20260/28080 [40:02:38<15:16:26,  7.03s/it]
 72%|███████▏  | 20261/28080 [40:02:45<15:11:59,  7.00s/it]
                                                           
{'loss': 0.6144, 'learning_rate': 9.496311902787918e-05, 'epoch': 8.66}

 72%|███████▏  | 20261/28080 [40:02:45<15:11:59,  7.00s/it]
 72%|███████▏  | 20262/28080 [40:02:52<15:17:33,  7.04s/it]
                                                           
{'loss': 0.6081, 'learning_rate': 9.4940498873158e-05, 'epoch': 8.66}

 72%|███████▏  | 20262/28080 [40:02:52<15:17:33,  7.04s/it]
 72%|███████▏  | 20263/28080 [40:02:59<15:20:02,  7.06s/it]
                                                           
{'loss': 0.6097, 'learning_rate': 9.491788078134369e-05, 'epoch': 8.66}

 72%|███████▏  | 20263/28080 [40:02:59<15:20:02,  7.06s/it]
 72%|███████▏  | 20264/28080 [40:03:06<15:19:24,  7.06s/it]
                                                           
{'loss': 0.5899, 'learning_rate': 9.489526475273683e-05, 'epoch': 8.66}

 72%|███████▏  | 20264/28080 [40:03:06<15:19:24,  7.06s/it]
 72%|███████▏  | 20265/28080 [40:03:13<15:18:04,  7.05s/it]
                                                           
{'loss': 0.5892, 'learning_rate': 9.487265078763851e-05, 'epoch': 8.66}

 72%|███████▏  | 20265/28080 [40:03:13<15:18:04,  7.05s/it]
 72%|███████▏  | 20266/28080 [40:03:20<15:19:15,  7.06s/it]
                                                           
{'loss': 0.6079, 'learning_rate': 9.485003888634955e-05, 'epoch': 8.66}

 72%|███████▏  | 20266/28080 [40:03:20<15:19:15,  7.06s/it]
 72%|███████▏  | 20267/28080 [40:03:27<15:17:12,  7.04s/it]
                                                           
{'loss': 0.609, 'learning_rate': 9.482742904917068e-05, 'epoch': 8.66}

 72%|███████▏  | 20267/28080 [40:03:27<15:17:12,  7.04s/it]
 72%|███████▏  | 20268/28080 [40:03:34<15:19:22,  7.06s/it]
                                                           
{'loss': 0.5824, 'learning_rate': 9.480482127640286e-05, 'epoch': 8.66}

 72%|███████▏  | 20268/28080 [40:03:34<15:19:22,  7.06s/it]
 72%|███████▏  | 20269/28080 [40:03:42<15:22:47,  7.09s/it]
                                                           
{'loss': 0.5992, 'learning_rate': 9.478221556834678e-05, 'epoch': 8.66}

 72%|███████▏  | 20269/28080 [40:03:42<15:22:47,  7.09s/it]
 72%|███████▏  | 20270/28080 [40:03:49<15:27:21,  7.12s/it]
                                                           
{'loss': 0.5892, 'learning_rate': 9.475961192530324e-05, 'epoch': 8.66}

 72%|███████▏  | 20270/28080 [40:03:49<15:27:21,  7.12s/it]
 72%|███████▏  | 20271/28080 [40:03:56<15:22:30,  7.09s/it]
                                                           
{'loss': 0.6104, 'learning_rate': 9.473701034757279e-05, 'epoch': 8.66}

 72%|███████▏  | 20271/28080 [40:03:56<15:22:30,  7.09s/it]
 72%|███████▏  | 20272/28080 [40:04:03<15:21:46,  7.08s/it]
                                                           
{'loss': 0.5864, 'learning_rate': 9.471441083545631e-05, 'epoch': 8.66}

 72%|███████▏  | 20272/28080 [40:04:03<15:21:46,  7.08s/it]
 72%|███████▏  | 20273/28080 [40:04:10<15:24:46,  7.11s/it]
                                                           
{'loss': 0.607, 'learning_rate': 9.469181338925442e-05, 'epoch': 8.66}

 72%|███████▏  | 20273/28080 [40:04:10<15:24:46,  7.11s/it]
 72%|███████▏  | 20274/28080 [40:04:17<15:25:15,  7.11s/it]
                                                           
{'loss': 0.5829, 'learning_rate': 9.466921800926773e-05, 'epoch': 8.66}

 72%|███████▏  | 20274/28080 [40:04:17<15:25:15,  7.11s/it]
 72%|███████▏  | 20275/28080 [40:04:24<15:23:49,  7.10s/it]
                                                           
{'loss': 0.6074, 'learning_rate': 9.464662469579676e-05, 'epoch': 8.66}

 72%|███████▏  | 20275/28080 [40:04:24<15:23:49,  7.10s/it]
 72%|███████▏  | 20276/28080 [40:04:31<15:27:47,  7.13s/it]
                                                           
{'loss': 0.6116, 'learning_rate': 9.462403344914228e-05, 'epoch': 8.66}

 72%|███████▏  | 20276/28080 [40:04:31<15:27:47,  7.13s/it]
 72%|███████▏  | 20277/28080 [40:04:38<15:26:04,  7.12s/it]
                                                           
{'loss': 0.6097, 'learning_rate': 9.46014442696047e-05, 'epoch': 8.66}

 72%|███████▏  | 20277/28080 [40:04:38<15:26:04,  7.12s/it]
 72%|███████▏  | 20278/28080 [40:04:46<15:25:43,  7.12s/it]
                                                           
{'loss': 0.5862, 'learning_rate': 9.457885715748463e-05, 'epoch': 8.66}

 72%|███████▏  | 20278/28080 [40:04:46<15:25:43,  7.12s/it]
 72%|███████▏  | 20279/28080 [40:04:53<15:21:14,  7.09s/it]
                                                           
{'loss': 0.6319, 'learning_rate': 9.455627211308243e-05, 'epoch': 8.66}

 72%|███████▏  | 20279/28080 [40:04:53<15:21:14,  7.09s/it]
 72%|███████▏  | 20280/28080 [40:05:00<15:20:44,  7.08s/it]
                                                           
{'loss': 0.61, 'learning_rate': 9.453368913669874e-05, 'epoch': 8.66}

 72%|███████▏  | 20280/28080 [40:05:00<15:20:44,  7.08s/it]
 72%|███████▏  | 20281/28080 [40:05:07<15:18:20,  7.07s/it]
                                                           
{'loss': 0.5835, 'learning_rate': 9.451110822863385e-05, 'epoch': 8.66}

 72%|███████▏  | 20281/28080 [40:05:07<15:18:20,  7.07s/it]
 72%|███████▏  | 20282/28080 [40:05:14<15:18:57,  7.07s/it]
                                                           
{'loss': 0.5977, 'learning_rate': 9.448852938918834e-05, 'epoch': 8.66}

 72%|███████▏  | 20282/28080 [40:05:14<15:18:57,  7.07s/it]
 72%|███████▏  | 20283/28080 [40:05:21<15:19:48,  7.08s/it]
                                                           
{'loss': 0.6048, 'learning_rate': 9.44659526186625e-05, 'epoch': 8.66}

 72%|███████▏  | 20283/28080 [40:05:21<15:19:48,  7.08s/it]
 72%|███████▏  | 20284/28080 [40:05:28<15:19:21,  7.08s/it]
                                                           
{'loss': 0.6065, 'learning_rate': 9.444337791735674e-05, 'epoch': 8.67}

 72%|███████▏  | 20284/28080 [40:05:28<15:19:21,  7.08s/it]
 72%|███████▏  | 20285/28080 [40:05:35<15:14:28,  7.04s/it]
                                                           
{'loss': 0.6267, 'learning_rate': 9.442080528557127e-05, 'epoch': 8.67}

 72%|███████▏  | 20285/28080 [40:05:35<15:14:28,  7.04s/it]
 72%|███████▏  | 20286/28080 [40:05:42<15:17:43,  7.06s/it]
                                                           
{'loss': 0.5948, 'learning_rate': 9.439823472360653e-05, 'epoch': 8.67}

 72%|███████▏  | 20286/28080 [40:05:42<15:17:43,  7.06s/it]
 72%|███████▏  | 20287/28080 [40:05:49<15:20:41,  7.09s/it]
                                                           
{'loss': 0.6112, 'learning_rate': 9.437566623176277e-05, 'epoch': 8.67}

 72%|███████▏  | 20287/28080 [40:05:49<15:20:41,  7.09s/it]
 72%|███████▏  | 20288/28080 [40:05:56<15:17:31,  7.07s/it]
                                                           
{'loss': 0.6213, 'learning_rate': 9.435309981034023e-05, 'epoch': 8.67}

 72%|███████▏  | 20288/28080 [40:05:56<15:17:31,  7.07s/it]
 72%|███████▏  | 20289/28080 [40:06:03<15:16:16,  7.06s/it]
                                                           
{'loss': 0.5957, 'learning_rate': 9.433053545963904e-05, 'epoch': 8.67}

 72%|███████▏  | 20289/28080 [40:06:03<15:16:16,  7.06s/it]
 72%|███████▏  | 20290/28080 [40:06:10<15:16:33,  7.06s/it]
                                                           
{'loss': 0.6094, 'learning_rate': 9.430797317995957e-05, 'epoch': 8.67}

 72%|███████▏  | 20290/28080 [40:06:10<15:16:33,  7.06s/it]
 72%|███████▏  | 20291/28080 [40:06:17<15:20:00,  7.09s/it]
                                                           
{'loss': 0.6163, 'learning_rate': 9.42854129716019e-05, 'epoch': 8.67}

 72%|███████▏  | 20291/28080 [40:06:17<15:20:00,  7.09s/it]
 72%|███████▏  | 20292/28080 [40:06:25<15:19:05,  7.08s/it]
                                                           
{'loss': 0.6056, 'learning_rate': 9.426285483486616e-05, 'epoch': 8.67}

 72%|███████▏  | 20292/28080 [40:06:25<15:19:05,  7.08s/it]
 72%|███████▏  | 20293/28080 [40:06:32<15:15:35,  7.05s/it]
                                                           
{'loss': 0.6147, 'learning_rate': 9.424029877005247e-05, 'epoch': 8.67}

 72%|███████▏  | 20293/28080 [40:06:32<15:15:35,  7.05s/it]
 72%|███████▏  | 20294/28080 [40:06:39<15:16:34,  7.06s/it]
                                                           
{'loss': 0.6055, 'learning_rate': 9.421774477746084e-05, 'epoch': 8.67}

 72%|███████▏  | 20294/28080 [40:06:39<15:16:34,  7.06s/it]
 72%|███████▏  | 20295/28080 [40:06:46<15:18:21,  7.08s/it]
                                                           
{'loss': 0.5925, 'learning_rate': 9.419519285739148e-05, 'epoch': 8.67}

 72%|███████▏  | 20295/28080 [40:06:46<15:18:21,  7.08s/it]
 72%|███████▏  | 20296/28080 [40:06:53<15:13:52,  7.04s/it]
                                                           
{'loss': 0.6135, 'learning_rate': 9.417264301014425e-05, 'epoch': 8.67}

 72%|███████▏  | 20296/28080 [40:06:53<15:13:52,  7.04s/it]
 72%|███████▏  | 20297/28080 [40:07:00<15:14:54,  7.05s/it]
                                                           
{'loss': 0.6022, 'learning_rate': 9.415009523601941e-05, 'epoch': 8.67}

 72%|███████▏  | 20297/28080 [40:07:00<15:14:54,  7.05s/it]
 72%|███████▏  | 20298/28080 [40:07:07<15:17:05,  7.07s/it]
                                                           
{'loss': 0.6227, 'learning_rate': 9.412754953531663e-05, 'epoch': 8.67}

 72%|███████▏  | 20298/28080 [40:07:07<15:17:05,  7.07s/it]
 72%|███████▏  | 20299/28080 [40:07:14<15:15:58,  7.06s/it]
                                                           
{'loss': 0.6022, 'learning_rate': 9.410500590833607e-05, 'epoch': 8.67}

 72%|███████▏  | 20299/28080 [40:07:14<15:15:58,  7.06s/it]
 72%|███████▏  | 20300/28080 [40:07:21<15:13:14,  7.04s/it]
                                                           
{'loss': 0.6038, 'learning_rate': 9.408246435537751e-05, 'epoch': 8.67}

 72%|███████▏  | 20300/28080 [40:07:21<15:13:14,  7.04s/it]
 72%|███████▏  | 20301/28080 [40:07:28<15:18:13,  7.08s/it]
                                                           
{'loss': 0.6037, 'learning_rate': 9.405992487674098e-05, 'epoch': 8.67}

 72%|███████▏  | 20301/28080 [40:07:28<15:18:13,  7.08s/it]
 72%|███████▏  | 20302/28080 [40:07:35<15:19:45,  7.10s/it]
                                                           
{'loss': 0.5819, 'learning_rate': 9.403738747272628e-05, 'epoch': 8.67}

 72%|███████▏  | 20302/28080 [40:07:35<15:19:45,  7.10s/it]
 72%|███████▏  | 20303/28080 [40:07:42<15:20:31,  7.10s/it]
                                                           
{'loss': 0.6161, 'learning_rate': 9.401485214363323e-05, 'epoch': 8.67}

 72%|███████▏  | 20303/28080 [40:07:42<15:20:31,  7.10s/it]
 72%|███████▏  | 20304/28080 [40:07:49<15:20:14,  7.10s/it]
                                                           
{'loss': 0.6176, 'learning_rate': 9.399231888976159e-05, 'epoch': 8.67}

 72%|███████▏  | 20304/28080 [40:07:49<15:20:14,  7.10s/it]
 72%|███████▏  | 20305/28080 [40:07:57<15:20:47,  7.11s/it]
                                                           
{'loss': 0.6078, 'learning_rate': 9.396978771141127e-05, 'epoch': 8.67}

 72%|███████▏  | 20305/28080 [40:07:57<15:20:47,  7.11s/it]
 72%|███████▏  | 20306/28080 [40:08:04<15:20:02,  7.10s/it]
                                                           
{'loss': 0.6012, 'learning_rate': 9.394725860888195e-05, 'epoch': 8.67}

 72%|███████▏  | 20306/28080 [40:08:04<15:20:02,  7.10s/it]
 72%|███████▏  | 20307/28080 [40:08:11<15:15:28,  7.07s/it]
                                                           
{'loss': 0.6073, 'learning_rate': 9.392473158247338e-05, 'epoch': 8.67}

 72%|███████▏  | 20307/28080 [40:08:11<15:15:28,  7.07s/it]
 72%|███████▏  | 20308/28080 [40:08:18<15:13:55,  7.06s/it]
                                                           
{'loss': 0.6006, 'learning_rate': 9.390220663248514e-05, 'epoch': 8.68}

 72%|███████▏  | 20308/28080 [40:08:18<15:13:55,  7.06s/it]
 72%|███████▏  | 20309/28080 [40:08:25<15:14:39,  7.06s/it]
                                                           
{'loss': 0.5795, 'learning_rate': 9.387968375921709e-05, 'epoch': 8.68}

 72%|███████▏  | 20309/28080 [40:08:25<15:14:39,  7.06s/it]
 72%|███████▏  | 20310/28080 [40:08:32<15:18:53,  7.10s/it]
                                                           
{'loss': 0.5869, 'learning_rate': 9.385716296296873e-05, 'epoch': 8.68}

 72%|███████▏  | 20310/28080 [40:08:32<15:18:53,  7.10s/it]
 72%|███████▏  | 20311/28080 [40:08:39<15:19:04,  7.10s/it]
                                                           
{'loss': 0.6321, 'learning_rate': 9.38346442440399e-05, 'epoch': 8.68}

 72%|███████▏  | 20311/28080 [40:08:39<15:19:04,  7.10s/it]
 72%|███████▏  | 20312/28080 [40:08:46<15:18:34,  7.10s/it]
                                                           
{'loss': 0.6045, 'learning_rate': 9.38121276027298e-05, 'epoch': 8.68}

 72%|███████▏  | 20312/28080 [40:08:46<15:18:34,  7.10s/it]
 72%|███████▏  | 20313/28080 [40:08:53<15:18:29,  7.10s/it]
                                                           
{'loss': 0.5858, 'learning_rate': 9.378961303933836e-05, 'epoch': 8.68}

 72%|███████▏  | 20313/28080 [40:08:53<15:18:29,  7.10s/it]
 72%|███████▏  | 20314/28080 [40:09:00<15:16:46,  7.08s/it]
                                                           
{'loss': 0.626, 'learning_rate': 9.376710055416485e-05, 'epoch': 8.68}

 72%|███████▏  | 20314/28080 [40:09:00<15:16:46,  7.08s/it]
 72%|███████▏  | 20315/28080 [40:09:07<15:18:46,  7.10s/it]
                                                           
{'loss': 0.5952, 'learning_rate': 9.374459014750897e-05, 'epoch': 8.68}

 72%|███████▏  | 20315/28080 [40:09:07<15:18:46,  7.10s/it]
 72%|███████▏  | 20316/28080 [40:09:14<15:17:00,  7.09s/it]
                                                           
{'loss': 0.5873, 'learning_rate': 9.372208181967023e-05, 'epoch': 8.68}

 72%|███████▏  | 20316/28080 [40:09:14<15:17:00,  7.09s/it]
 72%|███████▏  | 20317/28080 [40:09:22<15:19:17,  7.11s/it]
                                                           
{'loss': 0.6037, 'learning_rate': 9.369957557094777e-05, 'epoch': 8.68}

 72%|███████▏  | 20317/28080 [40:09:22<15:19:17,  7.11s/it]
 72%|███████▏  | 20318/28080 [40:09:29<15:17:48,  7.09s/it]
                                                           
{'loss': 0.6189, 'learning_rate': 9.36770714016413e-05, 'epoch': 8.68}

 72%|███████▏  | 20318/28080 [40:09:29<15:17:48,  7.09s/it]
 72%|███████▏  | 20319/28080 [40:09:36<15:17:46,  7.10s/it]
                                                           
{'loss': 0.6137, 'learning_rate': 9.365456931205005e-05, 'epoch': 8.68}

 72%|███████▏  | 20319/28080 [40:09:36<15:17:46,  7.10s/it]
 72%|███████▏  | 20320/28080 [40:09:43<15:20:44,  7.12s/it]
                                                           
{'loss': 0.6032, 'learning_rate': 9.363206930247356e-05, 'epoch': 8.68}

 72%|███████▏  | 20320/28080 [40:09:43<15:20:44,  7.12s/it]
 72%|███████▏  | 20321/28080 [40:09:50<15:21:09,  7.12s/it]
                                                           
{'loss': 0.5885, 'learning_rate': 9.360957137321105e-05, 'epoch': 8.68}

 72%|███████▏  | 20321/28080 [40:09:50<15:21:09,  7.12s/it]
 72%|███████▏  | 20322/28080 [40:09:57<15:14:20,  7.07s/it]
                                                           
{'loss': 0.6098, 'learning_rate': 9.358707552456186e-05, 'epoch': 8.68}

 72%|███████▏  | 20322/28080 [40:09:57<15:14:20,  7.07s/it]
 72%|███████▏  | 20323/28080 [40:10:04<15:18:36,  7.11s/it]
                                                           
{'loss': 0.6195, 'learning_rate': 9.35645817568252e-05, 'epoch': 8.68}

 72%|███████▏  | 20323/28080 [40:10:04<15:18:36,  7.11s/it]
 72%|███████▏  | 20324/28080 [40:10:11<15:18:58,  7.11s/it]
                                                           
{'loss': 0.6194, 'learning_rate': 9.354209007030045e-05, 'epoch': 8.68}

 72%|███████▏  | 20324/28080 [40:10:11<15:18:58,  7.11s/it]
 72%|███████▏  | 20325/28080 [40:10:18<15:21:43,  7.13s/it]
                                                           
{'loss': 0.606, 'learning_rate': 9.35196004652868e-05, 'epoch': 8.68}

 72%|███████▏  | 20325/28080 [40:10:18<15:21:43,  7.13s/it]
 72%|███████▏  | 20326/28080 [40:10:26<15:23:43,  7.15s/it]
                                                           
{'loss': 0.6056, 'learning_rate': 9.349711294208344e-05, 'epoch': 8.68}

 72%|███████▏  | 20326/28080 [40:10:26<15:23:43,  7.15s/it]
 72%|███████▏  | 20327/28080 [40:10:33<15:22:44,  7.14s/it]
                                                           
{'loss': 0.6229, 'learning_rate': 9.347462750098942e-05, 'epoch': 8.68}

 72%|███████▏  | 20327/28080 [40:10:33<15:22:44,  7.14s/it]
 72%|███████▏  | 20328/28080 [40:10:40<15:19:42,  7.12s/it]
                                                           
{'loss': 0.6277, 'learning_rate': 9.345214414230413e-05, 'epoch': 8.68}

 72%|███████▏  | 20328/28080 [40:10:40<15:19:42,  7.12s/it]
 72%|███████▏  | 20329/28080 [40:10:47<15:17:46,  7.10s/it]
                                                           
{'loss': 0.6324, 'learning_rate': 9.342966286632645e-05, 'epoch': 8.68}

 72%|███████▏  | 20329/28080 [40:10:47<15:17:46,  7.10s/it]
 72%|███████▏  | 20330/28080 [40:10:54<15:18:30,  7.11s/it]
                                                           
{'loss': 0.6005, 'learning_rate': 9.340718367335568e-05, 'epoch': 8.68}

 72%|███████▏  | 20330/28080 [40:10:54<15:18:30,  7.11s/it]
 72%|███████▏  | 20331/28080 [40:11:01<15:15:11,  7.09s/it]
                                                           
{'loss': 0.5931, 'learning_rate': 9.338470656369077e-05, 'epoch': 8.69}

 72%|███████▏  | 20331/28080 [40:11:01<15:15:11,  7.09s/it]
 72%|███████▏  | 20332/28080 [40:11:08<15:15:26,  7.09s/it]
                                                           
{'loss': 0.6156, 'learning_rate': 9.336223153763076e-05, 'epoch': 8.69}

 72%|███████▏  | 20332/28080 [40:11:08<15:15:26,  7.09s/it]
 72%|███████▏  | 20333/28080 [40:11:15<15:11:11,  7.06s/it]
                                                           
{'loss': 0.614, 'learning_rate': 9.333975859547461e-05, 'epoch': 8.69}

 72%|███████▏  | 20333/28080 [40:11:15<15:11:11,  7.06s/it]
 72%|███████▏  | 20334/28080 [40:11:22<15:16:20,  7.10s/it]
                                                           
{'loss': 0.5902, 'learning_rate': 9.33172877375214e-05, 'epoch': 8.69}

 72%|███████▏  | 20334/28080 [40:11:22<15:16:20,  7.10s/it]
 72%|███████▏  | 20335/28080 [40:11:29<15:15:07,  7.09s/it]
                                                           
{'loss': 0.5965, 'learning_rate': 9.329481896407008e-05, 'epoch': 8.69}

 72%|███████▏  | 20335/28080 [40:11:29<15:15:07,  7.09s/it]
 72%|███████▏  | 20336/28080 [40:11:37<15:17:07,  7.11s/it]
                                                           
{'loss': 0.6188, 'learning_rate': 9.32723522754195e-05, 'epoch': 8.69}

 72%|███████▏  | 20336/28080 [40:11:37<15:17:07,  7.11s/it]
 72%|███████▏  | 20337/28080 [40:11:44<15:16:49,  7.10s/it]
                                                           
{'loss': 0.6246, 'learning_rate': 9.32498876718685e-05, 'epoch': 8.69}

 72%|███████▏  | 20337/28080 [40:11:44<15:16:49,  7.10s/it]
 72%|███████▏  | 20338/28080 [40:11:51<15:10:24,  7.06s/it]
                                                           
{'loss': 0.6149, 'learning_rate': 9.322742515371615e-05, 'epoch': 8.69}

 72%|███████▏  | 20338/28080 [40:11:51<15:10:24,  7.06s/it]
 72%|███████▏  | 20339/28080 [40:11:58<15:11:07,  7.06s/it]
                                                           
{'loss': 0.6022, 'learning_rate': 9.320496472126117e-05, 'epoch': 8.69}

 72%|███████▏  | 20339/28080 [40:11:58<15:11:07,  7.06s/it]
 72%|███████▏  | 20340/28080 [40:12:05<15:10:37,  7.06s/it]
                                                           
{'loss': 0.6171, 'learning_rate': 9.318250637480236e-05, 'epoch': 8.69}

 72%|███████▏  | 20340/28080 [40:12:05<15:10:37,  7.06s/it]
 72%|███████▏  | 20341/28080 [40:12:12<15:12:58,  7.08s/it]
                                                           
{'loss': 0.6177, 'learning_rate': 9.316005011463852e-05, 'epoch': 8.69}

 72%|███████▏  | 20341/28080 [40:12:12<15:12:58,  7.08s/it]
 72%|███████▏  | 20342/28080 [40:12:19<15:14:39,  7.09s/it]
                                                           
{'loss': 0.5893, 'learning_rate': 9.313759594106833e-05, 'epoch': 8.69}

 72%|███████▏  | 20342/28080 [40:12:19<15:14:39,  7.09s/it]
 72%|███████▏  | 20343/28080 [40:12:26<15:11:22,  7.07s/it]
                                                           
{'loss': 0.6178, 'learning_rate': 9.311514385439069e-05, 'epoch': 8.69}

 72%|███████▏  | 20343/28080 [40:12:26<15:11:22,  7.07s/it]
 72%|███████▏  | 20344/28080 [40:12:33<15:12:28,  7.08s/it]
                                                           
{'loss': 0.612, 'learning_rate': 9.309269385490412e-05, 'epoch': 8.69}

 72%|███████▏  | 20344/28080 [40:12:33<15:12:28,  7.08s/it]
 72%|███████▏  | 20345/28080 [40:12:40<15:15:36,  7.10s/it]
                                                           
{'loss': 0.6184, 'learning_rate': 9.307024594290756e-05, 'epoch': 8.69}

 72%|███████▏  | 20345/28080 [40:12:40<15:15:36,  7.10s/it]
 72%|███████▏  | 20346/28080 [40:12:47<15:13:05,  7.08s/it]
                                                           
{'loss': 0.6329, 'learning_rate': 9.304780011869931e-05, 'epoch': 8.69}

 72%|███████▏  | 20346/28080 [40:12:47<15:13:05,  7.08s/it]
 72%|███████▏  | 20347/28080 [40:12:54<15:13:27,  7.09s/it]
                                                           
{'loss': 0.6067, 'learning_rate': 9.302535638257826e-05, 'epoch': 8.69}

 72%|███████▏  | 20347/28080 [40:12:54<15:13:27,  7.09s/it]
 72%|███████▏  | 20348/28080 [40:13:02<15:15:52,  7.11s/it]
                                                           
{'loss': 0.6113, 'learning_rate': 9.300291473484279e-05, 'epoch': 8.69}

 72%|███████▏  | 20348/28080 [40:13:02<15:15:52,  7.11s/it]
 72%|███████▏  | 20349/28080 [40:13:09<15:14:39,  7.10s/it]
                                                           
{'loss': 0.5931, 'learning_rate': 9.298047517579167e-05, 'epoch': 8.69}

 72%|███████▏  | 20349/28080 [40:13:09<15:14:39,  7.10s/it]
 72%|███████▏  | 20350/28080 [40:13:16<15:13:58,  7.09s/it]
                                                           
{'loss': 0.6186, 'learning_rate': 9.295803770572334e-05, 'epoch': 8.69}

 72%|███████▏  | 20350/28080 [40:13:16<15:13:58,  7.09s/it]
 72%|███████▏  | 20351/28080 [40:13:23<15:12:49,  7.09s/it]
                                                           
{'loss': 0.6078, 'learning_rate': 9.293560232493631e-05, 'epoch': 8.69}

 72%|███████▏  | 20351/28080 [40:13:23<15:12:49,  7.09s/it]
 72%|███████▏  | 20352/28080 [40:13:30<15:13:50,  7.10s/it]
                                                           
{'loss': 0.6132, 'learning_rate': 9.291316903372899e-05, 'epoch': 8.69}

 72%|███████▏  | 20352/28080 [40:13:30<15:13:50,  7.10s/it]
 72%|███████▏  | 20353/28080 [40:13:37<15:14:54,  7.10s/it]
                                                           
{'loss': 0.5983, 'learning_rate': 9.289073783239995e-05, 'epoch': 8.69}

 72%|███████▏  | 20353/28080 [40:13:37<15:14:54,  7.10s/it]
 72%|███████▏  | 20354/28080 [40:13:44<15:17:47,  7.13s/it]
                                                           
{'loss': 0.6043, 'learning_rate': 9.286830872124757e-05, 'epoch': 8.7}

 72%|███████▏  | 20354/28080 [40:13:44<15:17:47,  7.13s/it]
 72%|███████▏  | 20355/28080 [40:13:51<15:18:41,  7.14s/it]
                                                           
{'loss': 0.5773, 'learning_rate': 9.284588170057026e-05, 'epoch': 8.7}

 72%|███████▏  | 20355/28080 [40:13:51<15:18:41,  7.14s/it]
 72%|███████▏  | 20356/28080 [40:13:58<15:15:45,  7.11s/it]
                                                           
{'loss': 0.6089, 'learning_rate': 9.282345677066628e-05, 'epoch': 8.7}

 72%|███████▏  | 20356/28080 [40:13:58<15:15:45,  7.11s/it]
 72%|███████▏  | 20357/28080 [40:14:06<15:14:23,  7.10s/it]
                                                           
{'loss': 0.6071, 'learning_rate': 9.280103393183412e-05, 'epoch': 8.7}

 72%|███████▏  | 20357/28080 [40:14:06<15:14:23,  7.10s/it]
 72%|███████▎  | 20358/28080 [40:14:13<15:17:07,  7.13s/it]
                                                           
{'loss': 0.6033, 'learning_rate': 9.277861318437197e-05, 'epoch': 8.7}

 72%|███████▎  | 20358/28080 [40:14:13<15:17:07,  7.13s/it]
 73%|███████▎  | 20359/28080 [40:14:20<15:20:24,  7.15s/it]
                                                           
{'loss': 0.6206, 'learning_rate': 9.275619452857834e-05, 'epoch': 8.7}

 73%|███████▎  | 20359/28080 [40:14:20<15:20:24,  7.15s/it]
 73%|███████▎  | 20360/28080 [40:14:27<15:23:26,  7.18s/it]
                                                           
{'loss': 0.6201, 'learning_rate': 9.273377796475113e-05, 'epoch': 8.7}

 73%|███████▎  | 20360/28080 [40:14:27<15:23:26,  7.18s/it]
 73%|███████▎  | 20361/28080 [40:14:34<15:18:35,  7.14s/it]
                                                           
{'loss': 0.6177, 'learning_rate': 9.271136349318888e-05, 'epoch': 8.7}

 73%|███████▎  | 20361/28080 [40:14:34<15:18:35,  7.14s/it]
 73%|███████▎  | 20362/28080 [40:14:41<15:11:03,  7.08s/it]
                                                           
{'loss': 0.62, 'learning_rate': 9.268895111418954e-05, 'epoch': 8.7}

 73%|███████▎  | 20362/28080 [40:14:41<15:11:03,  7.08s/it]
 73%|███████▎  | 20363/28080 [40:14:48<15:10:29,  7.08s/it]
                                                           
{'loss': 0.6195, 'learning_rate': 9.266654082805154e-05, 'epoch': 8.7}

 73%|███████▎  | 20363/28080 [40:14:48<15:10:29,  7.08s/it]
 73%|███████▎  | 20364/28080 [40:14:55<15:10:50,  7.08s/it]
                                                           
{'loss': 0.6108, 'learning_rate': 9.26441326350729e-05, 'epoch': 8.7}

 73%|███████▎  | 20364/28080 [40:14:55<15:10:50,  7.08s/it]
 73%|███████▎  | 20365/28080 [40:15:02<15:10:19,  7.08s/it]
                                                           
{'loss': 0.5914, 'learning_rate': 9.262172653555172e-05, 'epoch': 8.7}

 73%|███████▎  | 20365/28080 [40:15:02<15:10:19,  7.08s/it]
 73%|███████▎  | 20366/28080 [40:15:09<15:08:58,  7.07s/it]
                                                           
{'loss': 0.6075, 'learning_rate': 9.259932252978615e-05, 'epoch': 8.7}

 73%|███████▎  | 20366/28080 [40:15:09<15:08:58,  7.07s/it]
 73%|███████▎  | 20367/28080 [40:15:16<15:09:04,  7.07s/it]
                                                           
{'loss': 0.6288, 'learning_rate': 9.257692061807407e-05, 'epoch': 8.7}

 73%|███████▎  | 20367/28080 [40:15:16<15:09:04,  7.07s/it]
 73%|███████▎  | 20368/28080 [40:15:24<15:07:19,  7.06s/it]
                                                           
{'loss': 0.6054, 'learning_rate': 9.25545208007138e-05, 'epoch': 8.7}

 73%|███████▎  | 20368/28080 [40:15:24<15:07:19,  7.06s/it]
 73%|███████▎  | 20369/28080 [40:15:31<15:12:08,  7.10s/it]
                                                           
{'loss': 0.6102, 'learning_rate': 9.253212307800315e-05, 'epoch': 8.7}

 73%|███████▎  | 20369/28080 [40:15:31<15:12:08,  7.10s/it]
 73%|███████▎  | 20370/28080 [40:15:38<15:14:58,  7.12s/it]
                                                           
{'loss': 0.6019, 'learning_rate': 9.25097274502402e-05, 'epoch': 8.7}

 73%|███████▎  | 20370/28080 [40:15:38<15:14:58,  7.12s/it]
 73%|███████▎  | 20371/28080 [40:15:45<15:16:17,  7.13s/it]
                                                           
{'loss': 0.5946, 'learning_rate': 9.248733391772273e-05, 'epoch': 8.7}

 73%|███████▎  | 20371/28080 [40:15:45<15:16:17,  7.13s/it]
 73%|███████▎  | 20372/28080 [40:15:52<15:13:13,  7.11s/it]
                                                           
{'loss': 0.6251, 'learning_rate': 9.246494248074891e-05, 'epoch': 8.7}

 73%|███████▎  | 20372/28080 [40:15:52<15:13:13,  7.11s/it]
 73%|███████▎  | 20373/28080 [40:15:59<15:13:05,  7.11s/it]
                                                           
{'loss': 0.6148, 'learning_rate': 9.244255313961647e-05, 'epoch': 8.7}

 73%|███████▎  | 20373/28080 [40:15:59<15:13:05,  7.11s/it]
 73%|███████▎  | 20374/28080 [40:16:06<15:11:00,  7.09s/it]
                                                           
{'loss': 0.5968, 'learning_rate': 9.242016589462334e-05, 'epoch': 8.7}

 73%|███████▎  | 20374/28080 [40:16:06<15:11:00,  7.09s/it]
 73%|███████▎  | 20375/28080 [40:16:13<15:04:03,  7.04s/it]
                                                           
{'loss': 0.5934, 'learning_rate': 9.239778074606725e-05, 'epoch': 8.7}

 73%|███████▎  | 20375/28080 [40:16:13<15:04:03,  7.04s/it]
 73%|███████▎  | 20376/28080 [40:16:20<15:08:02,  7.07s/it]
                                                           
{'loss': 0.6039, 'learning_rate': 9.237539769424618e-05, 'epoch': 8.7}

 73%|███████▎  | 20376/28080 [40:16:20<15:08:02,  7.07s/it]
 73%|███████▎  | 20377/28080 [40:16:27<15:09:13,  7.08s/it]
                                                           
{'loss': 0.6264, 'learning_rate': 9.235301673945776e-05, 'epoch': 8.7}

 73%|███████▎  | 20377/28080 [40:16:27<15:09:13,  7.08s/it]
 73%|███████▎  | 20378/28080 [40:16:34<15:04:58,  7.05s/it]
                                                           
{'loss': 0.5924, 'learning_rate': 9.233063788199997e-05, 'epoch': 8.71}

 73%|███████▎  | 20378/28080 [40:16:34<15:04:58,  7.05s/it]
 73%|███████▎  | 20379/28080 [40:16:41<15:03:29,  7.04s/it]
                                                           
{'loss': 0.6298, 'learning_rate': 9.230826112217019e-05, 'epoch': 8.71}

 73%|███████▎  | 20379/28080 [40:16:41<15:03:29,  7.04s/it]
 73%|███████▎  | 20380/28080 [40:16:49<15:07:50,  7.07s/it]
                                                           
{'loss': 0.6166, 'learning_rate': 9.228588646026645e-05, 'epoch': 8.71}

 73%|███████▎  | 20380/28080 [40:16:49<15:07:50,  7.07s/it]
 73%|███████▎  | 20381/28080 [40:16:56<15:06:08,  7.06s/it]
                                                           
{'loss': 0.6052, 'learning_rate': 9.226351389658615e-05, 'epoch': 8.71}

 73%|███████▎  | 20381/28080 [40:16:56<15:06:08,  7.06s/it]
 73%|███████▎  | 20382/28080 [40:17:03<15:03:44,  7.04s/it]
                                                           
{'loss': 0.6088, 'learning_rate': 9.22411434314272e-05, 'epoch': 8.71}

 73%|███████▎  | 20382/28080 [40:17:03<15:03:44,  7.04s/it]
 73%|███████▎  | 20383/28080 [40:17:10<15:01:38,  7.03s/it]
                                                           
{'loss': 0.6308, 'learning_rate': 9.221877506508708e-05, 'epoch': 8.71}

 73%|███████▎  | 20383/28080 [40:17:10<15:01:38,  7.03s/it]
 73%|███████▎  | 20384/28080 [40:17:17<15:00:21,  7.02s/it]
                                                           
{'loss': 0.5945, 'learning_rate': 9.219640879786337e-05, 'epoch': 8.71}

 73%|███████▎  | 20384/28080 [40:17:17<15:00:21,  7.02s/it]
 73%|███████▎  | 20385/28080 [40:17:24<15:05:42,  7.06s/it]
                                                           
{'loss': 0.6057, 'learning_rate': 9.217404463005355e-05, 'epoch': 8.71}

 73%|███████▎  | 20385/28080 [40:17:24<15:05:42,  7.06s/it]
 73%|███████▎  | 20386/28080 [40:17:31<15:06:36,  7.07s/it]
                                                           
{'loss': 0.6231, 'learning_rate': 9.215168256195535e-05, 'epoch': 8.71}

 73%|███████▎  | 20386/28080 [40:17:31<15:06:36,  7.07s/it]
 73%|███████▎  | 20387/28080 [40:17:38<15:06:01,  7.07s/it]
                                                           
{'loss': 0.5903, 'learning_rate': 9.212932259386617e-05, 'epoch': 8.71}

 73%|███████▎  | 20387/28080 [40:17:38<15:06:01,  7.07s/it]
 73%|███████▎  | 20388/28080 [40:17:45<15:07:01,  7.08s/it]
                                                           
{'loss': 0.6139, 'learning_rate': 9.210696472608346e-05, 'epoch': 8.71}

 73%|███████▎  | 20388/28080 [40:17:45<15:07:01,  7.08s/it]
 73%|███████▎  | 20389/28080 [40:17:52<15:02:42,  7.04s/it]
                                                           
{'loss': 0.6038, 'learning_rate': 9.208460895890463e-05, 'epoch': 8.71}

 73%|███████▎  | 20389/28080 [40:17:52<15:02:42,  7.04s/it]
 73%|███████▎  | 20390/28080 [40:17:59<15:05:46,  7.07s/it]
                                                           
{'loss': 0.5931, 'learning_rate': 9.206225529262726e-05, 'epoch': 8.71}

 73%|███████▎  | 20390/28080 [40:17:59<15:05:46,  7.07s/it]
 73%|███████▎  | 20391/28080 [40:18:06<15:06:21,  7.07s/it]
                                                           
{'loss': 0.6016, 'learning_rate': 9.203990372754864e-05, 'epoch': 8.71}

 73%|███████▎  | 20391/28080 [40:18:06<15:06:21,  7.07s/it]
 73%|███████▎  | 20392/28080 [40:18:13<15:04:38,  7.06s/it]
                                                           
{'loss': 0.6267, 'learning_rate': 9.201755426396605e-05, 'epoch': 8.71}

 73%|███████▎  | 20392/28080 [40:18:13<15:04:38,  7.06s/it]
 73%|███████▎  | 20393/28080 [40:18:20<15:05:33,  7.07s/it]
                                                           
{'loss': 0.6148, 'learning_rate': 9.19952069021771e-05, 'epoch': 8.71}

 73%|███████▎  | 20393/28080 [40:18:20<15:05:33,  7.07s/it]
 73%|███████▎  | 20394/28080 [40:18:27<15:08:18,  7.09s/it]
                                                           
{'loss': 0.6135, 'learning_rate': 9.197286164247875e-05, 'epoch': 8.71}

 73%|███████▎  | 20394/28080 [40:18:27<15:08:18,  7.09s/it]
 73%|███████▎  | 20395/28080 [40:18:35<15:07:56,  7.09s/it]
                                                           
{'loss': 0.6111, 'learning_rate': 9.195051848516852e-05, 'epoch': 8.71}

 73%|███████▎  | 20395/28080 [40:18:35<15:07:56,  7.09s/it]
 73%|███████▎  | 20396/28080 [40:18:42<15:09:01,  7.10s/it]
                                                           
{'loss': 0.5961, 'learning_rate': 9.192817743054352e-05, 'epoch': 8.71}

 73%|███████▎  | 20396/28080 [40:18:42<15:09:01,  7.10s/it]
 73%|███████▎  | 20397/28080 [40:18:49<15:09:51,  7.11s/it]
                                                           
{'loss': 0.5887, 'learning_rate': 9.19058384789011e-05, 'epoch': 8.71}

 73%|███████▎  | 20397/28080 [40:18:49<15:09:51,  7.11s/it]
 73%|███████▎  | 20398/28080 [40:18:56<15:09:20,  7.10s/it]
                                                           
{'loss': 0.5899, 'learning_rate': 9.188350163053843e-05, 'epoch': 8.71}

 73%|███████▎  | 20398/28080 [40:18:56<15:09:20,  7.10s/it]
 73%|███████▎  | 20399/28080 [40:19:03<15:10:34,  7.11s/it]
                                                           
{'loss': 0.6122, 'learning_rate': 9.186116688575266e-05, 'epoch': 8.71}

 73%|███████▎  | 20399/28080 [40:19:03<15:10:34,  7.11s/it]
 73%|███████▎  | 20400/28080 [40:19:10<15:08:42,  7.10s/it]
                                                           
{'loss': 0.5938, 'learning_rate': 9.183883424484082e-05, 'epoch': 8.71}

 73%|███████▎  | 20400/28080 [40:19:10<15:08:42,  7.10s/it]
 73%|███████▎  | 20401/28080 [40:19:17<15:10:58,  7.12s/it]
                                                           
{'loss': 0.6101, 'learning_rate': 9.181650370810022e-05, 'epoch': 8.72}

 73%|███████▎  | 20401/28080 [40:19:17<15:10:58,  7.12s/it]
 73%|███████▎  | 20402/28080 [40:19:24<15:11:25,  7.12s/it]
                                                           
{'loss': 0.6277, 'learning_rate': 9.179417527582784e-05, 'epoch': 8.72}

 73%|███████▎  | 20402/28080 [40:19:24<15:11:25,  7.12s/it]
 73%|███████▎  | 20403/28080 [40:19:31<15:09:11,  7.11s/it]
                                                           
{'loss': 0.5997, 'learning_rate': 9.177184894832075e-05, 'epoch': 8.72}

 73%|███████▎  | 20403/28080 [40:19:31<15:09:11,  7.11s/it]
 73%|███████▎  | 20404/28080 [40:19:38<15:01:55,  7.05s/it]
                                                           
{'loss': 0.6298, 'learning_rate': 9.174952472587589e-05, 'epoch': 8.72}

 73%|███████▎  | 20404/28080 [40:19:38<15:01:55,  7.05s/it]
 73%|███████▎  | 20405/28080 [40:19:45<15:04:54,  7.07s/it]
                                                           
{'loss': 0.6063, 'learning_rate': 9.172720260879042e-05, 'epoch': 8.72}

 73%|███████▎  | 20405/28080 [40:19:45<15:04:54,  7.07s/it]
 73%|███████▎  | 20406/28080 [40:19:53<15:06:16,  7.09s/it]
                                                           
{'loss': 0.61, 'learning_rate': 9.170488259736115e-05, 'epoch': 8.72}

 73%|███████▎  | 20406/28080 [40:19:53<15:06:16,  7.09s/it]
 73%|███████▎  | 20407/28080 [40:20:00<15:07:36,  7.10s/it]
                                                           
{'loss': 0.6001, 'learning_rate': 9.16825646918853e-05, 'epoch': 8.72}

 73%|███████▎  | 20407/28080 [40:20:00<15:07:36,  7.10s/it]
 73%|███████▎  | 20408/28080 [40:20:07<15:11:10,  7.13s/it]
                                                           
{'loss': 0.6103, 'learning_rate': 9.166024889265943e-05, 'epoch': 8.72}

 73%|███████▎  | 20408/28080 [40:20:07<15:11:10,  7.13s/it]
 73%|███████▎  | 20409/28080 [40:20:14<15:10:49,  7.12s/it]
                                                           
{'loss': 0.5846, 'learning_rate': 9.163793519998068e-05, 'epoch': 8.72}

 73%|███████▎  | 20409/28080 [40:20:14<15:10:49,  7.12s/it]
 73%|███████▎  | 20410/28080 [40:20:21<15:09:55,  7.12s/it]
                                                           
{'loss': 0.6026, 'learning_rate': 9.161562361414574e-05, 'epoch': 8.72}

 73%|███████▎  | 20410/28080 [40:20:21<15:09:55,  7.12s/it]
 73%|███████▎  | 20411/28080 [40:20:28<15:09:10,  7.11s/it]
                                                           
{'loss': 0.5962, 'learning_rate': 9.159331413545161e-05, 'epoch': 8.72}

 73%|███████▎  | 20411/28080 [40:20:28<15:09:10,  7.11s/it]
 73%|███████▎  | 20412/28080 [40:20:35<15:10:14,  7.12s/it]
                                                           
{'loss': 0.5895, 'learning_rate': 9.157100676419502e-05, 'epoch': 8.72}

 73%|███████▎  | 20412/28080 [40:20:35<15:10:14,  7.12s/it]
 73%|███████▎  | 20413/28080 [40:20:42<15:06:36,  7.09s/it]
                                                           
{'loss': 0.6137, 'learning_rate': 9.154870150067276e-05, 'epoch': 8.72}

 73%|███████▎  | 20413/28080 [40:20:42<15:06:36,  7.09s/it]
 73%|███████▎  | 20414/28080 [40:20:50<15:10:00,  7.12s/it]
                                                           
{'loss': 0.6179, 'learning_rate': 9.152639834518148e-05, 'epoch': 8.72}

 73%|███████▎  | 20414/28080 [40:20:50<15:10:00,  7.12s/it]
 73%|███████▎  | 20415/28080 [40:20:57<15:09:52,  7.12s/it]
                                                           
{'loss': 0.6053, 'learning_rate': 9.150409729801804e-05, 'epoch': 8.72}

 73%|███████▎  | 20415/28080 [40:20:57<15:09:52,  7.12s/it]
 73%|███████▎  | 20416/28080 [40:21:04<15:06:26,  7.10s/it]
                                                           
{'loss': 0.604, 'learning_rate': 9.148179835947909e-05, 'epoch': 8.72}

 73%|███████▎  | 20416/28080 [40:21:04<15:06:26,  7.10s/it]
 73%|███████▎  | 20417/28080 [40:21:11<15:02:05,  7.06s/it]
                                                           
{'loss': 0.6048, 'learning_rate': 9.145950152986127e-05, 'epoch': 8.72}

 73%|███████▎  | 20417/28080 [40:21:11<15:02:05,  7.06s/it]
 73%|███████▎  | 20418/28080 [40:21:18<15:02:25,  7.07s/it]
                                                           
{'loss': 0.5998, 'learning_rate': 9.143720680946121e-05, 'epoch': 8.72}

 73%|███████▎  | 20418/28080 [40:21:18<15:02:25,  7.07s/it]
 73%|███████▎  | 20419/28080 [40:21:25<15:04:29,  7.08s/it]
                                                           
{'loss': 0.6137, 'learning_rate': 9.141491419857547e-05, 'epoch': 8.72}

 73%|███████▎  | 20419/28080 [40:21:25<15:04:29,  7.08s/it]
 73%|███████▎  | 20420/28080 [40:21:32<15:03:02,  7.07s/it]
                                                           
{'loss': 0.6045, 'learning_rate': 9.139262369750079e-05, 'epoch': 8.72}

 73%|███████▎  | 20420/28080 [40:21:32<15:03:02,  7.07s/it]
 73%|███████▎  | 20421/28080 [40:21:39<15:07:32,  7.11s/it]
                                                           
{'loss': 0.5922, 'learning_rate': 9.13703353065336e-05, 'epoch': 8.72}

 73%|███████▎  | 20421/28080 [40:21:39<15:07:32,  7.11s/it]
 73%|███████▎  | 20422/28080 [40:21:46<15:02:58,  7.07s/it]
                                                           
{'loss': 0.6131, 'learning_rate': 9.134804902597046e-05, 'epoch': 8.72}

 73%|███████▎  | 20422/28080 [40:21:46<15:02:58,  7.07s/it]
 73%|███████▎  | 20423/28080 [40:21:53<15:00:26,  7.06s/it]
                                                           
{'loss': 0.6157, 'learning_rate': 9.132576485610777e-05, 'epoch': 8.72}

 73%|███████▎  | 20423/28080 [40:21:53<15:00:26,  7.06s/it]
 73%|███████▎  | 20424/28080 [40:22:00<14:58:41,  7.04s/it]
                                                           
{'loss': 0.6043, 'learning_rate': 9.130348279724218e-05, 'epoch': 8.72}

 73%|███████▎  | 20424/28080 [40:22:00<14:58:41,  7.04s/it]
 73%|███████▎  | 20425/28080 [40:22:07<15:01:47,  7.07s/it]
                                                           
{'loss': 0.6261, 'learning_rate': 9.128120284966996e-05, 'epoch': 8.73}

 73%|███████▎  | 20425/28080 [40:22:07<15:01:47,  7.07s/it]
 73%|███████▎  | 20426/28080 [40:22:14<14:58:19,  7.04s/it]
                                                           
{'loss': 0.6261, 'learning_rate': 9.125892501368774e-05, 'epoch': 8.73}

 73%|███████▎  | 20426/28080 [40:22:14<14:58:19,  7.04s/it]
 73%|███████▎  | 20427/28080 [40:22:21<15:01:45,  7.07s/it]
                                                           
{'loss': 0.6025, 'learning_rate': 9.123664928959158e-05, 'epoch': 8.73}

 73%|███████▎  | 20427/28080 [40:22:21<15:01:45,  7.07s/it]
 73%|███████▎  | 20428/28080 [40:22:28<14:59:10,  7.05s/it]
                                                           
{'loss': 0.6057, 'learning_rate': 9.121437567767812e-05, 'epoch': 8.73}

 73%|███████▎  | 20428/28080 [40:22:28<14:59:10,  7.05s/it]
 73%|███████▎  | 20429/28080 [40:22:36<15:01:33,  7.07s/it]
                                                           
{'loss': 0.5998, 'learning_rate': 9.119210417824347e-05, 'epoch': 8.73}

 73%|███████▎  | 20429/28080 [40:22:36<15:01:33,  7.07s/it]
 73%|███████▎  | 20430/28080 [40:22:43<15:04:37,  7.10s/it]
                                                           
{'loss': 0.6041, 'learning_rate': 9.116983479158413e-05, 'epoch': 8.73}

 73%|███████▎  | 20430/28080 [40:22:43<15:04:37,  7.10s/it]
 73%|███████▎  | 20431/28080 [40:22:50<15:05:20,  7.10s/it]
                                                           
{'loss': 0.608, 'learning_rate': 9.114756751799633e-05, 'epoch': 8.73}

 73%|███████▎  | 20431/28080 [40:22:50<15:05:20,  7.10s/it]
 73%|███████▎  | 20432/28080 [40:22:57<15:05:03,  7.10s/it]
                                                           
{'loss': 0.6092, 'learning_rate': 9.112530235777622e-05, 'epoch': 8.73}

 73%|███████▎  | 20432/28080 [40:22:57<15:05:03,  7.10s/it]
 73%|███████▎  | 20433/28080 [40:23:04<15:07:16,  7.12s/it]
                                                           
{'loss': 0.5937, 'learning_rate': 9.110303931122e-05, 'epoch': 8.73}

 73%|███████▎  | 20433/28080 [40:23:04<15:07:16,  7.12s/it]
 73%|███████▎  | 20434/28080 [40:23:11<15:06:12,  7.11s/it]
                                                           
{'loss': 0.5815, 'learning_rate': 9.108077837862397e-05, 'epoch': 8.73}

 73%|███████▎  | 20434/28080 [40:23:11<15:06:12,  7.11s/it]
 73%|███████▎  | 20435/28080 [40:23:18<15:06:34,  7.12s/it]
                                                           
{'loss': 0.6198, 'learning_rate': 9.105851956028428e-05, 'epoch': 8.73}

 73%|███████▎  | 20435/28080 [40:23:18<15:06:34,  7.12s/it]
 73%|███████▎  | 20436/28080 [40:23:25<15:00:41,  7.07s/it]
                                                           
{'loss': 0.6247, 'learning_rate': 9.103626285649696e-05, 'epoch': 8.73}

 73%|███████▎  | 20436/28080 [40:23:25<15:00:41,  7.07s/it]
 73%|███████▎  | 20437/28080 [40:23:32<15:05:48,  7.11s/it]
                                                           
{'loss': 0.6027, 'learning_rate': 9.101400826755813e-05, 'epoch': 8.73}

 73%|███████▎  | 20437/28080 [40:23:32<15:05:48,  7.11s/it]
 73%|███████▎  | 20438/28080 [40:23:39<15:01:10,  7.08s/it]
                                                           
{'loss': 0.5985, 'learning_rate': 9.099175579376398e-05, 'epoch': 8.73}

 73%|███████▎  | 20438/28080 [40:23:39<15:01:10,  7.08s/it]
 73%|███████▎  | 20439/28080 [40:23:47<15:00:06,  7.07s/it]
                                                           
{'loss': 0.6029, 'learning_rate': 9.096950543541038e-05, 'epoch': 8.73}

 73%|███████▎  | 20439/28080 [40:23:47<15:00:06,  7.07s/it]
 73%|███████▎  | 20440/28080 [40:23:54<15:04:00,  7.10s/it]
                                                           
{'loss': 0.6209, 'learning_rate': 9.094725719279361e-05, 'epoch': 8.73}

 73%|███████▎  | 20440/28080 [40:23:54<15:04:00,  7.10s/it]
 73%|███████▎  | 20441/28080 [40:24:01<15:04:24,  7.10s/it]
                                                           
{'loss': 0.6084, 'learning_rate': 9.092501106620943e-05, 'epoch': 8.73}

 73%|███████▎  | 20441/28080 [40:24:01<15:04:24,  7.10s/it]
 73%|███████▎  | 20442/28080 [40:24:08<14:59:52,  7.07s/it]
                                                           
{'loss': 0.6236, 'learning_rate': 9.09027670559538e-05, 'epoch': 8.73}

 73%|███████▎  | 20442/28080 [40:24:08<14:59:52,  7.07s/it]
 73%|███████▎  | 20443/28080 [40:24:15<14:57:23,  7.05s/it]
                                                           
{'loss': 0.5936, 'learning_rate': 9.088052516232279e-05, 'epoch': 8.73}

 73%|███████▎  | 20443/28080 [40:24:15<14:57:23,  7.05s/it]
 73%|███████▎  | 20444/28080 [40:24:22<15:00:04,  7.07s/it]
                                                           
{'loss': 0.6176, 'learning_rate': 9.085828538561213e-05, 'epoch': 8.73}

 73%|███████▎  | 20444/28080 [40:24:22<15:00:04,  7.07s/it]
 73%|███████▎  | 20445/28080 [40:24:29<14:57:57,  7.06s/it]
                                                           
{'loss': 0.606, 'learning_rate': 9.083604772611792e-05, 'epoch': 8.73}

 73%|███████▎  | 20445/28080 [40:24:29<14:57:57,  7.06s/it]
 73%|███████▎  | 20446/28080 [40:24:36<15:00:42,  7.08s/it]
                                                           
{'loss': 0.5763, 'learning_rate': 9.081381218413589e-05, 'epoch': 8.73}

 73%|███████▎  | 20446/28080 [40:24:36<15:00:42,  7.08s/it]
 73%|███████▎  | 20447/28080 [40:24:43<15:03:59,  7.11s/it]
                                                           
{'loss': 0.601, 'learning_rate': 9.079157875996186e-05, 'epoch': 8.73}

 73%|███████▎  | 20447/28080 [40:24:43<15:03:59,  7.11s/it]
 73%|███████▎  | 20448/28080 [40:24:50<15:01:56,  7.09s/it]
                                                           
{'loss': 0.6122, 'learning_rate': 9.076934745389157e-05, 'epoch': 8.74}

 73%|███████▎  | 20448/28080 [40:24:50<15:01:56,  7.09s/it]
 73%|███████▎  | 20449/28080 [40:24:57<15:05:18,  7.12s/it]
                                                           
{'loss': 0.5934, 'learning_rate': 9.074711826622089e-05, 'epoch': 8.74}

 73%|███████▎  | 20449/28080 [40:24:57<15:05:18,  7.12s/it]
 73%|███████▎  | 20450/28080 [40:25:05<15:02:20,  7.10s/it]
                                                           
{'loss': 0.5987, 'learning_rate': 9.072489119724552e-05, 'epoch': 8.74}

 73%|███████▎  | 20450/28080 [40:25:05<15:02:20,  7.10s/it]
 73%|███████▎  | 20451/28080 [40:25:12<15:01:31,  7.09s/it]
                                                           
{'loss': 0.618, 'learning_rate': 9.070266624726118e-05, 'epoch': 8.74}

 73%|███████▎  | 20451/28080 [40:25:12<15:01:31,  7.09s/it]
 73%|███████▎  | 20452/28080 [40:25:19<15:03:58,  7.11s/it]
                                                           
{'loss': 0.5984, 'learning_rate': 9.068044341656343e-05, 'epoch': 8.74}

 73%|███████▎  | 20452/28080 [40:25:19<15:03:58,  7.11s/it]
 73%|███████▎  | 20453/28080 [40:25:26<15:00:54,  7.09s/it]
                                                           
{'loss': 0.5997, 'learning_rate': 9.065822270544808e-05, 'epoch': 8.74}

 73%|███████▎  | 20453/28080 [40:25:26<15:00:54,  7.09s/it]
 73%|███████▎  | 20454/28080 [40:25:33<14:57:51,  7.06s/it]
                                                           
{'loss': 0.5965, 'learning_rate': 9.063600411421063e-05, 'epoch': 8.74}

 73%|███████▎  | 20454/28080 [40:25:33<14:57:51,  7.06s/it]
 73%|███████▎  | 20455/28080 [40:25:40<15:02:41,  7.10s/it]
                                                           
{'loss': 0.6058, 'learning_rate': 9.061378764314689e-05, 'epoch': 8.74}

 73%|███████▎  | 20455/28080 [40:25:40<15:02:41,  7.10s/it]
 73%|███████▎  | 20456/28080 [40:25:47<15:01:00,  7.09s/it]
                                                           
{'loss': 0.592, 'learning_rate': 9.059157329255213e-05, 'epoch': 8.74}

 73%|███████▎  | 20456/28080 [40:25:47<15:01:00,  7.09s/it]
 73%|███████▎  | 20457/28080 [40:25:54<14:56:30,  7.06s/it]
                                                           
{'loss': 0.597, 'learning_rate': 9.056936106272213e-05, 'epoch': 8.74}

 73%|███████▎  | 20457/28080 [40:25:54<14:56:30,  7.06s/it]
 73%|███████▎  | 20458/28080 [40:26:01<14:57:35,  7.07s/it]
                                                           
{'loss': 0.6038, 'learning_rate': 9.054715095395219e-05, 'epoch': 8.74}

 73%|███████▎  | 20458/28080 [40:26:01<14:57:35,  7.07s/it]
 73%|███████▎  | 20459/28080 [40:26:08<14:59:51,  7.08s/it]
                                                           
{'loss': 0.6047, 'learning_rate': 9.052494296653801e-05, 'epoch': 8.74}

 73%|███████▎  | 20459/28080 [40:26:08<14:59:51,  7.08s/it]
 73%|███████▎  | 20460/28080 [40:26:15<15:01:19,  7.10s/it]
                                                           
{'loss': 0.5959, 'learning_rate': 9.050273710077494e-05, 'epoch': 8.74}

 73%|███████▎  | 20460/28080 [40:26:15<15:01:19,  7.10s/it]
 73%|███████▎  | 20461/28080 [40:26:23<15:04:38,  7.12s/it]
                                                           
{'loss': 0.5869, 'learning_rate': 9.048053335695841e-05, 'epoch': 8.74}

 73%|███████▎  | 20461/28080 [40:26:23<15:04:38,  7.12s/it]
 73%|███████▎  | 20462/28080 [40:26:30<15:01:14,  7.10s/it]
                                                           
{'loss': 0.6033, 'learning_rate': 9.045833173538373e-05, 'epoch': 8.74}

 73%|███████▎  | 20462/28080 [40:26:30<15:01:14,  7.10s/it]
 73%|███████▎  | 20463/28080 [40:26:37<15:00:10,  7.09s/it]
                                                           
{'loss': 0.5988, 'learning_rate': 9.043613223634642e-05, 'epoch': 8.74}

 73%|███████▎  | 20463/28080 [40:26:37<15:00:10,  7.09s/it]
 73%|███████▎  | 20464/28080 [40:26:44<14:54:15,  7.05s/it]
                                                           
{'loss': 0.6224, 'learning_rate': 9.041393486014179e-05, 'epoch': 8.74}

 73%|███████▎  | 20464/28080 [40:26:44<14:54:15,  7.05s/it]
 73%|███████▎  | 20465/28080 [40:26:51<14:56:28,  7.06s/it]
                                                           
{'loss': 0.6064, 'learning_rate': 9.03917396070651e-05, 'epoch': 8.74}

 73%|███████▎  | 20465/28080 [40:26:51<14:56:28,  7.06s/it]
 73%|███████▎  | 20466/28080 [40:26:58<14:54:25,  7.05s/it]
                                                           
{'loss': 0.6333, 'learning_rate': 9.036954647741166e-05, 'epoch': 8.74}

 73%|███████▎  | 20466/28080 [40:26:58<14:54:25,  7.05s/it]
 73%|███████▎  | 20467/28080 [40:27:05<14:53:58,  7.05s/it]
                                                           
{'loss': 0.6006, 'learning_rate': 9.034735547147666e-05, 'epoch': 8.74}

 73%|███████▎  | 20467/28080 [40:27:05<14:53:58,  7.05s/it]
 73%|███████▎  | 20468/28080 [40:27:12<14:59:25,  7.09s/it]
                                                           
{'loss': 0.5973, 'learning_rate': 9.032516658955545e-05, 'epoch': 8.74}

 73%|███████▎  | 20468/28080 [40:27:12<14:59:25,  7.09s/it]
 73%|███████▎  | 20469/28080 [40:27:19<14:56:22,  7.07s/it]
                                                           
{'loss': 0.5953, 'learning_rate': 9.030297983194319e-05, 'epoch': 8.74}

 73%|███████▎  | 20469/28080 [40:27:19<14:56:22,  7.07s/it]
 73%|███████▎  | 20470/28080 [40:27:26<14:56:41,  7.07s/it]
                                                           
{'loss': 0.6101, 'learning_rate': 9.0280795198935e-05, 'epoch': 8.74}

 73%|███████▎  | 20470/28080 [40:27:26<14:56:41,  7.07s/it]
 73%|███████▎  | 20471/28080 [40:27:33<14:58:32,  7.09s/it]
                                                           
{'loss': 0.5929, 'learning_rate': 9.0258612690826e-05, 'epoch': 8.75}

 73%|███████▎  | 20471/28080 [40:27:33<14:58:32,  7.09s/it]
 73%|███████▎  | 20472/28080 [40:27:40<14:59:42,  7.10s/it]
                                                           
{'loss': 0.5857, 'learning_rate': 9.023643230791146e-05, 'epoch': 8.75}

 73%|███████▎  | 20472/28080 [40:27:40<14:59:42,  7.10s/it]
 73%|███████▎  | 20473/28080 [40:27:47<14:59:53,  7.10s/it]
                                                           
{'loss': 0.612, 'learning_rate': 9.021425405048626e-05, 'epoch': 8.75}

 73%|███████▎  | 20473/28080 [40:27:47<14:59:53,  7.10s/it]
 73%|███████▎  | 20474/28080 [40:27:55<15:00:45,  7.11s/it]
                                                           
{'loss': 0.6103, 'learning_rate': 9.019207791884574e-05, 'epoch': 8.75}

 73%|███████▎  | 20474/28080 [40:27:55<15:00:45,  7.11s/it]
 73%|███████▎  | 20475/28080 [40:28:02<15:00:32,  7.10s/it]
                                                           
{'loss': 0.6358, 'learning_rate': 9.016990391328458e-05, 'epoch': 8.75}

 73%|███████▎  | 20475/28080 [40:28:02<15:00:32,  7.10s/it]
 73%|███████▎  | 20476/28080 [40:28:09<14:59:05,  7.09s/it]
                                                           
{'loss': 0.6018, 'learning_rate': 9.014773203409807e-05, 'epoch': 8.75}

 73%|███████▎  | 20476/28080 [40:28:09<14:59:05,  7.09s/it]
 73%|███████▎  | 20477/28080 [40:28:16<15:00:13,  7.10s/it]
                                                           
{'loss': 0.6013, 'learning_rate': 9.012556228158098e-05, 'epoch': 8.75}

 73%|███████▎  | 20477/28080 [40:28:16<15:00:13,  7.10s/it]
 73%|███████▎  | 20478/28080 [40:28:23<14:57:15,  7.08s/it]
                                                           
{'loss': 0.6201, 'learning_rate': 9.010339465602843e-05, 'epoch': 8.75}

 73%|███████▎  | 20478/28080 [40:28:23<14:57:15,  7.08s/it]
 73%|███████▎  | 20479/28080 [40:28:30<14:55:05,  7.07s/it]
                                                           
{'loss': 0.6187, 'learning_rate': 9.008122915773526e-05, 'epoch': 8.75}

 73%|███████▎  | 20479/28080 [40:28:30<14:55:05,  7.07s/it]
 73%|███████▎  | 20480/28080 [40:28:37<15:01:26,  7.12s/it]
                                                           
{'loss': 0.6157, 'learning_rate': 9.005906578699635e-05, 'epoch': 8.75}

 73%|███████▎  | 20480/28080 [40:28:37<15:01:26,  7.12s/it]
 73%|███████▎  | 20481/28080 [40:28:44<14:54:09,  7.06s/it]
                                                           
{'loss': 0.6003, 'learning_rate': 9.003690454410649e-05, 'epoch': 8.75}

 73%|███████▎  | 20481/28080 [40:28:44<14:54:09,  7.06s/it]
 73%|███████▎  | 20482/28080 [40:28:51<14:55:25,  7.07s/it]
                                                           
{'loss': 0.5862, 'learning_rate': 9.001474542936066e-05, 'epoch': 8.75}

 73%|███████▎  | 20482/28080 [40:28:51<14:55:25,  7.07s/it]
 73%|███████▎  | 20483/28080 [40:28:58<14:54:21,  7.06s/it]
                                                           
{'loss': 0.6139, 'learning_rate': 8.999258844305363e-05, 'epoch': 8.75}

 73%|███████▎  | 20483/28080 [40:28:58<14:54:21,  7.06s/it]
 73%|███████▎  | 20484/28080 [40:29:05<14:56:52,  7.08s/it]
                                                           
{'loss': 0.5963, 'learning_rate': 8.997043358548012e-05, 'epoch': 8.75}

 73%|███████▎  | 20484/28080 [40:29:05<14:56:52,  7.08s/it]
 73%|███████▎  | 20485/28080 [40:29:12<14:58:34,  7.10s/it]
                                                           
{'loss': 0.5984, 'learning_rate': 8.99482808569348e-05, 'epoch': 8.75}

 73%|███████▎  | 20485/28080 [40:29:12<14:58:34,  7.10s/it]
 73%|███████▎  | 20486/28080 [40:29:20<14:57:02,  7.09s/it]
                                                           
{'loss': 0.5993, 'learning_rate': 8.99261302577126e-05, 'epoch': 8.75}

 73%|███████▎  | 20486/28080 [40:29:20<14:57:02,  7.09s/it]
 73%|███████▎  | 20487/28080 [40:29:27<14:57:14,  7.09s/it]
                                                           
{'loss': 0.6178, 'learning_rate': 8.990398178810799e-05, 'epoch': 8.75}

 73%|███████▎  | 20487/28080 [40:29:27<14:57:14,  7.09s/it]
 73%|███████▎  | 20488/28080 [40:29:34<14:59:22,  7.11s/it]
                                                           
{'loss': 0.6099, 'learning_rate': 8.988183544841591e-05, 'epoch': 8.75}

 73%|███████▎  | 20488/28080 [40:29:34<14:59:22,  7.11s/it]
 73%|███████▎  | 20489/28080 [40:29:41<14:58:28,  7.10s/it]
                                                           
{'loss': 0.5971, 'learning_rate': 8.985969123893067e-05, 'epoch': 8.75}

 73%|███████▎  | 20489/28080 [40:29:41<14:58:28,  7.10s/it]
 73%|███████▎  | 20490/28080 [40:29:48<14:57:32,  7.10s/it]
                                                           
{'loss': 0.6166, 'learning_rate': 8.98375491599471e-05, 'epoch': 8.75}

 73%|███████▎  | 20490/28080 [40:29:48<14:57:32,  7.10s/it]
 73%|███████▎  | 20491/28080 [40:29:55<14:59:07,  7.11s/it]
                                                           
{'loss': 0.5908, 'learning_rate': 8.981540921175974e-05, 'epoch': 8.75}

 73%|███████▎  | 20491/28080 [40:29:55<14:59:07,  7.11s/it]
 73%|███████▎  | 20492/28080 [40:30:02<15:00:22,  7.12s/it]
                                                           
{'loss': 0.6208, 'learning_rate': 8.979327139466298e-05, 'epoch': 8.75}

 73%|███████▎  | 20492/28080 [40:30:02<15:00:22,  7.12s/it]
 73%|███████▎  | 20493/28080 [40:30:09<14:58:21,  7.10s/it]
                                                           
{'loss': 0.6143, 'learning_rate': 8.97711357089516e-05, 'epoch': 8.75}

 73%|███████▎  | 20493/28080 [40:30:09<14:58:21,  7.10s/it]
 73%|███████▎  | 20494/28080 [40:30:16<15:01:33,  7.13s/it]
                                                           
{'loss': 0.6167, 'learning_rate': 8.97490021549199e-05, 'epoch': 8.75}

 73%|███████▎  | 20494/28080 [40:30:16<15:01:33,  7.13s/it]
 73%|███████▎  | 20495/28080 [40:30:24<15:01:35,  7.13s/it]
                                                           
{'loss': 0.615, 'learning_rate': 8.972687073286245e-05, 'epoch': 8.76}

 73%|███████▎  | 20495/28080 [40:30:24<15:01:35,  7.13s/it]
 73%|███████▎  | 20496/28080 [40:30:31<15:02:51,  7.14s/it]
                                                           
{'loss': 0.596, 'learning_rate': 8.970474144307356e-05, 'epoch': 8.76}

 73%|███████▎  | 20496/28080 [40:30:31<15:02:51,  7.14s/it]
 73%|███████▎  | 20497/28080 [40:30:38<15:02:13,  7.14s/it]
                                                           
{'loss': 0.5913, 'learning_rate': 8.968261428584776e-05, 'epoch': 8.76}

 73%|███████▎  | 20497/28080 [40:30:38<15:02:13,  7.14s/it]
 73%|███████▎  | 20498/28080 [40:30:45<15:07:09,  7.18s/it]
                                                           
{'loss': 0.6104, 'learning_rate': 8.966048926147944e-05, 'epoch': 8.76}

 73%|███████▎  | 20498/28080 [40:30:45<15:07:09,  7.18s/it]
 73%|███████▎  | 20499/28080 [40:30:52<15:02:41,  7.14s/it]
                                                           
{'loss': 0.5987, 'learning_rate': 8.963836637026285e-05, 'epoch': 8.76}

 73%|███████▎  | 20499/28080 [40:30:52<15:02:41,  7.14s/it]
 73%|███████▎  | 20500/28080 [40:30:59<15:00:10,  7.13s/it]
                                                           
{'loss': 0.6257, 'learning_rate': 8.961624561249229e-05, 'epoch': 8.76}

 73%|███████▎  | 20500/28080 [40:30:59<15:00:10,  7.13s/it]
 73%|███████▎  | 20501/28080 [40:31:06<15:00:47,  7.13s/it]
                                                           
{'loss': 0.5918, 'learning_rate': 8.959412698846222e-05, 'epoch': 8.76}

 73%|███████▎  | 20501/28080 [40:31:06<15:00:47,  7.13s/it]
 73%|███████▎  | 20502/28080 [40:31:14<15:02:00,  7.14s/it]
                                                           
{'loss': 0.5932, 'learning_rate': 8.95720104984668e-05, 'epoch': 8.76}

 73%|███████▎  | 20502/28080 [40:31:14<15:02:00,  7.14s/it]
 73%|███████▎  | 20503/28080 [40:31:21<15:02:10,  7.14s/it]
                                                           
{'loss': 0.6153, 'learning_rate': 8.954989614280026e-05, 'epoch': 8.76}

 73%|███████▎  | 20503/28080 [40:31:21<15:02:10,  7.14s/it]
 73%|███████▎  | 20504/28080 [40:31:28<14:55:49,  7.09s/it]
                                                           
{'loss': 0.6366, 'learning_rate': 8.952778392175678e-05, 'epoch': 8.76}

 73%|███████▎  | 20504/28080 [40:31:28<14:55:49,  7.09s/it]
 73%|███████▎  | 20505/28080 [40:31:35<14:54:05,  7.08s/it]
                                                           
{'loss': 0.6143, 'learning_rate': 8.950567383563064e-05, 'epoch': 8.76}

 73%|███████▎  | 20505/28080 [40:31:35<14:54:05,  7.08s/it]
 73%|███████▎  | 20506/28080 [40:31:42<14:52:19,  7.07s/it]
                                                           
{'loss': 0.6015, 'learning_rate': 8.948356588471585e-05, 'epoch': 8.76}

 73%|███████▎  | 20506/28080 [40:31:42<14:52:19,  7.07s/it]
 73%|███████▎  | 20507/28080 [40:31:49<14:51:17,  7.06s/it]
                                                           
{'loss': 0.6222, 'learning_rate': 8.946146006930672e-05, 'epoch': 8.76}

 73%|███████▎  | 20507/28080 [40:31:49<14:51:17,  7.06s/it]
 73%|███████▎  | 20508/28080 [40:31:56<14:53:26,  7.08s/it]
                                                           
{'loss': 0.5961, 'learning_rate': 8.943935638969725e-05, 'epoch': 8.76}

 73%|███████▎  | 20508/28080 [40:31:56<14:53:26,  7.08s/it]
 73%|███████▎  | 20509/28080 [40:32:03<14:57:11,  7.11s/it]
                                                           
{'loss': 0.5976, 'learning_rate': 8.941725484618149e-05, 'epoch': 8.76}

 73%|███████▎  | 20509/28080 [40:32:03<14:57:11,  7.11s/it]
 73%|███████▎  | 20510/28080 [40:32:10<14:57:53,  7.12s/it]
                                                           
{'loss': 0.6152, 'learning_rate': 8.939515543905339e-05, 'epoch': 8.76}

 73%|███████▎  | 20510/28080 [40:32:10<14:57:53,  7.12s/it]
 73%|███████▎  | 20511/28080 [40:32:17<14:57:52,  7.12s/it]
                                                           
{'loss': 0.6104, 'learning_rate': 8.937305816860716e-05, 'epoch': 8.76}

 73%|███████▎  | 20511/28080 [40:32:17<14:57:52,  7.12s/it]
 73%|███████▎  | 20512/28080 [40:32:25<14:57:09,  7.11s/it]
                                                           
{'loss': 0.6138, 'learning_rate': 8.935096303513668e-05, 'epoch': 8.76}

 73%|███████▎  | 20512/28080 [40:32:25<14:57:09,  7.11s/it]
 73%|███████▎  | 20513/28080 [40:32:32<14:56:06,  7.11s/it]
                                                           
{'loss': 0.6005, 'learning_rate': 8.932887003893591e-05, 'epoch': 8.76}

 73%|███████▎  | 20513/28080 [40:32:32<14:56:06,  7.11s/it]
 73%|███████▎  | 20514/28080 [40:32:39<14:55:29,  7.10s/it]
                                                           
{'loss': 0.6049, 'learning_rate': 8.93067791802987e-05, 'epoch': 8.76}

 73%|███████▎  | 20514/28080 [40:32:39<14:55:29,  7.10s/it]
 73%|███████▎  | 20515/28080 [40:32:46<14:58:12,  7.12s/it]
                                                           
{'loss': 0.6018, 'learning_rate': 8.928469045951906e-05, 'epoch': 8.76}

 73%|███████▎  | 20515/28080 [40:32:46<14:58:12,  7.12s/it]
 73%|███████▎  | 20516/28080 [40:32:53<14:58:20,  7.13s/it]
                                                           
{'loss': 0.616, 'learning_rate': 8.926260387689083e-05, 'epoch': 8.76}

 73%|███████▎  | 20516/28080 [40:32:53<14:58:20,  7.13s/it]
 73%|███████▎  | 20517/28080 [40:33:00<14:58:23,  7.13s/it]
                                                           
{'loss': 0.6177, 'learning_rate': 8.924051943270786e-05, 'epoch': 8.76}

 73%|███████▎  | 20517/28080 [40:33:00<14:58:23,  7.13s/it]
 73%|███████▎  | 20518/28080 [40:33:07<14:58:39,  7.13s/it]
                                                           
{'loss': 0.6079, 'learning_rate': 8.921843712726391e-05, 'epoch': 8.77}

 73%|███████▎  | 20518/28080 [40:33:07<14:58:39,  7.13s/it]
 73%|███████▎  | 20519/28080 [40:33:14<14:56:02,  7.11s/it]
                                                           
{'loss': 0.6212, 'learning_rate': 8.919635696085269e-05, 'epoch': 8.77}

 73%|███████▎  | 20519/28080 [40:33:14<14:56:02,  7.11s/it]
 73%|███████▎  | 20520/28080 [40:33:21<14:53:47,  7.09s/it]
                                                           
{'loss': 0.6059, 'learning_rate': 8.917427893376814e-05, 'epoch': 8.77}

 73%|███████▎  | 20520/28080 [40:33:21<14:53:47,  7.09s/it]
 73%|███████▎  | 20521/28080 [40:33:28<14:50:23,  7.07s/it]
                                                           
{'loss': 0.6162, 'learning_rate': 8.915220304630381e-05, 'epoch': 8.77}

 73%|███████▎  | 20521/28080 [40:33:28<14:50:23,  7.07s/it]
 73%|███████▎  | 20522/28080 [40:33:36<14:51:13,  7.08s/it]
                                                           
{'loss': 0.6033, 'learning_rate': 8.913012929875367e-05, 'epoch': 8.77}

 73%|███████▎  | 20522/28080 [40:33:36<14:51:13,  7.08s/it]
 73%|███████▎  | 20523/28080 [40:33:43<14:49:59,  7.07s/it]
                                                           
{'loss': 0.5881, 'learning_rate': 8.9108057691411e-05, 'epoch': 8.77}

 73%|███████▎  | 20523/28080 [40:33:43<14:49:59,  7.07s/it]
 73%|███████▎  | 20524/28080 [40:33:50<14:53:08,  7.09s/it]
                                                           
{'loss': 0.6101, 'learning_rate': 8.908598822456973e-05, 'epoch': 8.77}

 73%|███████▎  | 20524/28080 [40:33:50<14:53:08,  7.09s/it]
 73%|███████▎  | 20525/28080 [40:33:57<14:53:22,  7.09s/it]
                                                           
{'loss': 0.5752, 'learning_rate': 8.90639208985233e-05, 'epoch': 8.77}

 73%|███████▎  | 20525/28080 [40:33:57<14:53:22,  7.09s/it]
 73%|███████▎  | 20526/28080 [40:34:04<14:55:03,  7.11s/it]
                                                           
{'loss': 0.5905, 'learning_rate': 8.904185571356547e-05, 'epoch': 8.77}

 73%|███████▎  | 20526/28080 [40:34:04<14:55:03,  7.11s/it]
 73%|███████▎  | 20527/28080 [40:34:11<14:48:39,  7.06s/it]
                                                           
{'loss': 0.6074, 'learning_rate': 8.901979266998969e-05, 'epoch': 8.77}

 73%|███████▎  | 20527/28080 [40:34:11<14:48:39,  7.06s/it]
 73%|███████▎  | 20528/28080 [40:34:18<14:47:36,  7.05s/it]
                                                           
{'loss': 0.5873, 'learning_rate': 8.899773176808948e-05, 'epoch': 8.77}

 73%|███████▎  | 20528/28080 [40:34:18<14:47:36,  7.05s/it]
 73%|███████▎  | 20529/28080 [40:34:25<14:44:50,  7.03s/it]
                                                           
{'loss': 0.6328, 'learning_rate': 8.897567300815828e-05, 'epoch': 8.77}

 73%|███████▎  | 20529/28080 [40:34:25<14:44:50,  7.03s/it]
 73%|███████▎  | 20530/28080 [40:34:32<14:45:39,  7.04s/it]
                                                           
{'loss': 0.5975, 'learning_rate': 8.895361639048972e-05, 'epoch': 8.77}

 73%|███████▎  | 20530/28080 [40:34:32<14:45:39,  7.04s/it]
 73%|███████▎  | 20531/28080 [40:34:39<14:41:45,  7.01s/it]
                                                           
{'loss': 0.6155, 'learning_rate': 8.893156191537716e-05, 'epoch': 8.77}

 73%|███████▎  | 20531/28080 [40:34:39<14:41:45,  7.01s/it]
 73%|███████▎  | 20532/28080 [40:34:46<14:44:59,  7.03s/it]
                                                           
{'loss': 0.6015, 'learning_rate': 8.890950958311397e-05, 'epoch': 8.77}

 73%|███████▎  | 20532/28080 [40:34:46<14:44:59,  7.03s/it]
 73%|███████▎  | 20533/28080 [40:34:53<14:43:31,  7.02s/it]
                                                           
{'loss': 0.625, 'learning_rate': 8.888745939399351e-05, 'epoch': 8.77}

 73%|███████▎  | 20533/28080 [40:34:53<14:43:31,  7.02s/it]
 73%|███████▎  | 20534/28080 [40:35:00<14:46:18,  7.05s/it]
                                                           
{'loss': 0.6092, 'learning_rate': 8.886541134830928e-05, 'epoch': 8.77}

 73%|███████▎  | 20534/28080 [40:35:00<14:46:18,  7.05s/it]
 73%|███████▎  | 20535/28080 [40:35:07<14:47:35,  7.06s/it]
                                                           
{'loss': 0.606, 'learning_rate': 8.884336544635444e-05, 'epoch': 8.77}

 73%|███████▎  | 20535/28080 [40:35:07<14:47:35,  7.06s/it]
 73%|███████▎  | 20536/28080 [40:35:14<14:51:00,  7.09s/it]
                                                           
{'loss': 0.5916, 'learning_rate': 8.882132168842249e-05, 'epoch': 8.77}

 73%|███████▎  | 20536/28080 [40:35:14<14:51:00,  7.09s/it]
 73%|███████▎  | 20537/28080 [40:35:21<14:51:01,  7.09s/it]
                                                           
{'loss': 0.5949, 'learning_rate': 8.879928007480645e-05, 'epoch': 8.77}

 73%|███████▎  | 20537/28080 [40:35:21<14:51:01,  7.09s/it]
 73%|███████▎  | 20538/28080 [40:35:29<14:55:02,  7.12s/it]
                                                           
{'loss': 0.63, 'learning_rate': 8.877724060579975e-05, 'epoch': 8.77}

 73%|███████▎  | 20538/28080 [40:35:29<14:55:02,  7.12s/it]
 73%|███████▎  | 20539/28080 [40:35:36<14:56:14,  7.13s/it]
                                                           
{'loss': 0.6168, 'learning_rate': 8.875520328169549e-05, 'epoch': 8.77}

 73%|███████▎  | 20539/28080 [40:35:36<14:56:14,  7.13s/it]
 73%|███████▎  | 20540/28080 [40:35:43<14:54:37,  7.12s/it]
                                                           
{'loss': 0.6106, 'learning_rate': 8.873316810278695e-05, 'epoch': 8.77}

 73%|███████▎  | 20540/28080 [40:35:43<14:54:37,  7.12s/it]
 73%|███████▎  | 20541/28080 [40:35:50<14:55:34,  7.13s/it]
                                                           
{'loss': 0.5949, 'learning_rate': 8.871113506936726e-05, 'epoch': 8.77}

 73%|███████▎  | 20541/28080 [40:35:50<14:55:34,  7.13s/it]
 73%|███████▎  | 20542/28080 [40:35:57<14:55:40,  7.13s/it]
                                                           
{'loss': 0.5877, 'learning_rate': 8.868910418172952e-05, 'epoch': 8.78}

 73%|███████▎  | 20542/28080 [40:35:57<14:55:40,  7.13s/it]
 73%|███████▎  | 20543/28080 [40:36:04<14:56:55,  7.14s/it]
                                                           
{'loss': 0.5992, 'learning_rate': 8.866707544016683e-05, 'epoch': 8.78}

 73%|███████▎  | 20543/28080 [40:36:04<14:56:55,  7.14s/it]
 73%|███████▎  | 20544/28080 [40:36:11<14:55:38,  7.13s/it]
                                                           
{'loss': 0.6193, 'learning_rate': 8.864504884497218e-05, 'epoch': 8.78}

 73%|███████▎  | 20544/28080 [40:36:11<14:55:38,  7.13s/it]
 73%|███████▎  | 20545/28080 [40:36:19<14:52:54,  7.11s/it]
                                                           
{'loss': 0.6182, 'learning_rate': 8.862302439643876e-05, 'epoch': 8.78}

 73%|███████▎  | 20545/28080 [40:36:19<14:52:54,  7.11s/it]
 73%|███████▎  | 20546/28080 [40:36:26<14:52:42,  7.11s/it]
                                                           
{'loss': 0.6163, 'learning_rate': 8.860100209485955e-05, 'epoch': 8.78}

 73%|███████▎  | 20546/28080 [40:36:26<14:52:42,  7.11s/it]
 73%|███████▎  | 20547/28080 [40:36:33<14:54:12,  7.12s/it]
                                                           
{'loss': 0.5913, 'learning_rate': 8.85789819405275e-05, 'epoch': 8.78}

 73%|███████▎  | 20547/28080 [40:36:33<14:54:12,  7.12s/it]
 73%|███████▎  | 20548/28080 [40:36:40<14:55:13,  7.13s/it]
                                                           
{'loss': 0.5858, 'learning_rate': 8.855696393373544e-05, 'epoch': 8.78}

 73%|███████▎  | 20548/28080 [40:36:40<14:55:13,  7.13s/it]
 73%|███████▎  | 20549/28080 [40:36:47<14:55:08,  7.13s/it]
                                                           
{'loss': 0.5989, 'learning_rate': 8.853494807477655e-05, 'epoch': 8.78}

 73%|███████▎  | 20549/28080 [40:36:47<14:55:08,  7.13s/it]
 73%|███████▎  | 20550/28080 [40:36:54<14:53:04,  7.12s/it]
                                                           
{'loss': 0.605, 'learning_rate': 8.85129343639436e-05, 'epoch': 8.78}

 73%|███████▎  | 20550/28080 [40:36:54<14:53:04,  7.12s/it]
 73%|███████▎  | 20551/28080 [40:37:01<14:50:36,  7.10s/it]
                                                           
{'loss': 0.6069, 'learning_rate': 8.849092280152943e-05, 'epoch': 8.78}

 73%|███████▎  | 20551/28080 [40:37:01<14:50:36,  7.10s/it]
 73%|███████▎  | 20552/28080 [40:37:08<14:51:47,  7.11s/it]
                                                           
{'loss': 0.605, 'learning_rate': 8.846891338782683e-05, 'epoch': 8.78}

 73%|███████▎  | 20552/28080 [40:37:08<14:51:47,  7.11s/it]
 73%|███████▎  | 20553/28080 [40:37:15<14:49:58,  7.09s/it]
                                                           
{'loss': 0.5923, 'learning_rate': 8.84469061231288e-05, 'epoch': 8.78}

 73%|███████▎  | 20553/28080 [40:37:15<14:49:58,  7.09s/it]
 73%|███████▎  | 20554/28080 [40:37:22<14:46:38,  7.07s/it]
                                                           
{'loss': 0.603, 'learning_rate': 8.842490100772796e-05, 'epoch': 8.78}

 73%|███████▎  | 20554/28080 [40:37:22<14:46:38,  7.07s/it]
 73%|███████▎  | 20555/28080 [40:37:30<14:51:36,  7.11s/it]
                                                           
{'loss': 0.599, 'learning_rate': 8.840289804191717e-05, 'epoch': 8.78}

 73%|███████▎  | 20555/28080 [40:37:30<14:51:36,  7.11s/it]
 73%|███████▎  | 20556/28080 [40:37:37<14:49:47,  7.10s/it]
                                                           
{'loss': 0.6053, 'learning_rate': 8.838089722598913e-05, 'epoch': 8.78}

 73%|███████▎  | 20556/28080 [40:37:37<14:49:47,  7.10s/it]
 73%|███████▎  | 20557/28080 [40:37:44<14:51:57,  7.11s/it]
                                                           
{'loss': 0.6121, 'learning_rate': 8.83588985602365e-05, 'epoch': 8.78}

 73%|███████▎  | 20557/28080 [40:37:44<14:51:57,  7.11s/it]
 73%|███████▎  | 20558/28080 [40:37:51<14:52:32,  7.12s/it]
                                                           
{'loss': 0.5815, 'learning_rate': 8.83369020449519e-05, 'epoch': 8.78}

 73%|███████▎  | 20558/28080 [40:37:51<14:52:32,  7.12s/it]
 73%|███████▎  | 20559/28080 [40:37:58<14:50:52,  7.11s/it]
                                                           
{'loss': 0.5906, 'learning_rate': 8.83149076804281e-05, 'epoch': 8.78}

 73%|███████▎  | 20559/28080 [40:37:58<14:50:52,  7.11s/it]
 73%|███████▎  | 20560/28080 [40:38:05<14:46:50,  7.08s/it]
                                                           
{'loss': 0.613, 'learning_rate': 8.82929154669577e-05, 'epoch': 8.78}

 73%|███████▎  | 20560/28080 [40:38:05<14:46:50,  7.08s/it]
 73%|███████▎  | 20561/28080 [40:38:12<14:47:39,  7.08s/it]
                                                           
{'loss': 0.601, 'learning_rate': 8.82709254048332e-05, 'epoch': 8.78}

 73%|███████▎  | 20561/28080 [40:38:12<14:47:39,  7.08s/it]
 73%|███████▎  | 20562/28080 [40:38:19<14:48:41,  7.09s/it]
                                                           
{'loss': 0.6079, 'learning_rate': 8.824893749434709e-05, 'epoch': 8.78}

 73%|███████▎  | 20562/28080 [40:38:19<14:48:41,  7.09s/it]
 73%|███████▎  | 20563/28080 [40:38:26<14:48:13,  7.09s/it]
                                                           
{'loss': 0.5941, 'learning_rate': 8.822695173579212e-05, 'epoch': 8.78}

 73%|███████▎  | 20563/28080 [40:38:26<14:48:13,  7.09s/it]
 73%|███████▎  | 20564/28080 [40:38:33<14:50:14,  7.11s/it]
                                                           
{'loss': 0.6127, 'learning_rate': 8.820496812946066e-05, 'epoch': 8.78}

 73%|███████▎  | 20564/28080 [40:38:33<14:50:14,  7.11s/it]
 73%|███████▎  | 20565/28080 [40:38:41<14:54:32,  7.14s/it]
                                                           
{'loss': 0.5933, 'learning_rate': 8.818298667564518e-05, 'epoch': 8.79}

 73%|███████▎  | 20565/28080 [40:38:41<14:54:32,  7.14s/it]
 73%|███████▎  | 20566/28080 [40:38:48<14:48:47,  7.10s/it]
                                                           
{'loss': 0.6296, 'learning_rate': 8.816100737463812e-05, 'epoch': 8.79}

 73%|███████▎  | 20566/28080 [40:38:48<14:48:47,  7.10s/it]
 73%|███████▎  | 20567/28080 [40:38:55<14:48:02,  7.09s/it]
                                                           
{'loss': 0.6063, 'learning_rate': 8.813903022673181e-05, 'epoch': 8.79}

 73%|███████▎  | 20567/28080 [40:38:55<14:48:02,  7.09s/it]
 73%|███████▎  | 20568/28080 [40:39:02<14:49:06,  7.10s/it]
                                                           
{'loss': 0.607, 'learning_rate': 8.81170552322188e-05, 'epoch': 8.79}

 73%|███████▎  | 20568/28080 [40:39:02<14:49:06,  7.10s/it]
 73%|███████▎  | 20569/28080 [40:39:09<14:51:32,  7.12s/it]
                                                           
{'loss': 0.6014, 'learning_rate': 8.809508239139128e-05, 'epoch': 8.79}

 73%|███████▎  | 20569/28080 [40:39:09<14:51:32,  7.12s/it]
 73%|███████▎  | 20570/28080 [40:39:16<14:51:14,  7.12s/it]
                                                           
{'loss': 0.614, 'learning_rate': 8.807311170454182e-05, 'epoch': 8.79}

 73%|███████▎  | 20570/28080 [40:39:16<14:51:14,  7.12s/it]
 73%|███████▎  | 20571/28080 [40:39:23<14:48:39,  7.10s/it]
                                                           
{'loss': 0.6005, 'learning_rate': 8.805114317196242e-05, 'epoch': 8.79}

 73%|███████▎  | 20571/28080 [40:39:23<14:48:39,  7.10s/it]
 73%|███████▎  | 20572/28080 [40:39:30<14:49:17,  7.11s/it]
                                                           
{'loss': 0.5821, 'learning_rate': 8.802917679394557e-05, 'epoch': 8.79}

 73%|███████▎  | 20572/28080 [40:39:30<14:49:17,  7.11s/it]
 73%|███████▎  | 20573/28080 [40:39:37<14:44:48,  7.07s/it]
                                                           
{'loss': 0.6171, 'learning_rate': 8.800721257078331e-05, 'epoch': 8.79}

 73%|███████▎  | 20573/28080 [40:39:37<14:44:48,  7.07s/it]
 73%|███████▎  | 20574/28080 [40:39:44<14:46:18,  7.08s/it]
                                                           
{'loss': 0.6124, 'learning_rate': 8.798525050276807e-05, 'epoch': 8.79}

 73%|███████▎  | 20574/28080 [40:39:44<14:46:18,  7.08s/it]
 73%|███████▎  | 20575/28080 [40:39:51<14:43:21,  7.06s/it]
                                                           
{'loss': 0.6065, 'learning_rate': 8.796329059019195e-05, 'epoch': 8.79}

 73%|███████▎  | 20575/28080 [40:39:51<14:43:21,  7.06s/it]
 73%|███████▎  | 20576/28080 [40:39:59<14:45:13,  7.08s/it]
                                                           
{'loss': 0.6285, 'learning_rate': 8.794133283334707e-05, 'epoch': 8.79}

 73%|███████▎  | 20576/28080 [40:39:59<14:45:13,  7.08s/it]
 73%|███████▎  | 20577/28080 [40:40:06<14:47:55,  7.10s/it]
                                                           
{'loss': 0.6017, 'learning_rate': 8.791937723252546e-05, 'epoch': 8.79}

 73%|███████▎  | 20577/28080 [40:40:06<14:47:55,  7.10s/it]
 73%|███████▎  | 20578/28080 [40:40:13<14:47:58,  7.10s/it]
                                                           
{'loss': 0.6094, 'learning_rate': 8.789742378801944e-05, 'epoch': 8.79}

 73%|███████▎  | 20578/28080 [40:40:13<14:47:58,  7.10s/it]
 73%|███████▎  | 20579/28080 [40:40:20<14:52:12,  7.14s/it]
                                                           
{'loss': 0.5969, 'learning_rate': 8.787547250012096e-05, 'epoch': 8.79}

 73%|███████▎  | 20579/28080 [40:40:20<14:52:12,  7.14s/it]
 73%|███████▎  | 20580/28080 [40:40:27<14:51:10,  7.13s/it]
                                                           
{'loss': 0.5922, 'learning_rate': 8.785352336912206e-05, 'epoch': 8.79}

 73%|███████▎  | 20580/28080 [40:40:27<14:51:10,  7.13s/it]
 73%|███████▎  | 20581/28080 [40:40:34<14:48:32,  7.11s/it]
                                                           
{'loss': 0.6153, 'learning_rate': 8.783157639531466e-05, 'epoch': 8.79}

 73%|███████▎  | 20581/28080 [40:40:34<14:48:32,  7.11s/it]
 73%|███████▎  | 20582/28080 [40:40:41<14:48:04,  7.11s/it]
                                                           
{'loss': 0.6086, 'learning_rate': 8.780963157899094e-05, 'epoch': 8.79}

 73%|███████▎  | 20582/28080 [40:40:41<14:48:04,  7.11s/it]
 73%|███████▎  | 20583/28080 [40:40:48<14:44:32,  7.08s/it]
                                                           
{'loss': 0.6171, 'learning_rate': 8.778768892044267e-05, 'epoch': 8.79}

 73%|███████▎  | 20583/28080 [40:40:48<14:44:32,  7.08s/it]
 73%|███████▎  | 20584/28080 [40:40:55<14:46:21,  7.09s/it]
                                                           
{'loss': 0.597, 'learning_rate': 8.776574841996202e-05, 'epoch': 8.79}

 73%|███████▎  | 20584/28080 [40:40:55<14:46:21,  7.09s/it]
 73%|███████▎  | 20585/28080 [40:41:03<14:48:14,  7.11s/it]
                                                           
{'loss': 0.5924, 'learning_rate': 8.774381007784052e-05, 'epoch': 8.79}

 73%|███████▎  | 20585/28080 [40:41:03<14:48:14,  7.11s/it]
 73%|███████▎  | 20586/28080 [40:41:10<14:46:41,  7.10s/it]
                                                           
{'loss': 0.5962, 'learning_rate': 8.772187389437036e-05, 'epoch': 8.79}

 73%|███████▎  | 20586/28080 [40:41:10<14:46:41,  7.10s/it]
 73%|███████▎  | 20587/28080 [40:41:17<14:45:14,  7.09s/it]
                                                           
{'loss': 0.6089, 'learning_rate': 8.769993986984314e-05, 'epoch': 8.79}

 73%|███████▎  | 20587/28080 [40:41:17<14:45:14,  7.09s/it]
 73%|███████▎  | 20588/28080 [40:41:24<14:46:20,  7.10s/it]
                                                           
{'loss': 0.6058, 'learning_rate': 8.767800800455089e-05, 'epoch': 8.8}

 73%|███████▎  | 20588/28080 [40:41:24<14:46:20,  7.10s/it]
 73%|███████▎  | 20589/28080 [40:41:31<14:46:40,  7.10s/it]
                                                           
{'loss': 0.5904, 'learning_rate': 8.765607829878528e-05, 'epoch': 8.8}

 73%|███████▎  | 20589/28080 [40:41:31<14:46:40,  7.10s/it]
 73%|███████▎  | 20590/28080 [40:41:38<14:45:18,  7.09s/it]
                                                           
{'loss': 0.6049, 'learning_rate': 8.763415075283806e-05, 'epoch': 8.8}

 73%|███████▎  | 20590/28080 [40:41:38<14:45:18,  7.09s/it]
 73%|███████▎  | 20591/28080 [40:41:45<14:47:08,  7.11s/it]
                                                           
{'loss': 0.5918, 'learning_rate': 8.761222536700094e-05, 'epoch': 8.8}

 73%|███████▎  | 20591/28080 [40:41:45<14:47:08,  7.11s/it]
 73%|███████▎  | 20592/28080 [40:41:52<14:41:43,  7.07s/it]
                                                           
{'loss': 0.624, 'learning_rate': 8.75903021415656e-05, 'epoch': 8.8}

 73%|███████▎  | 20592/28080 [40:41:52<14:41:43,  7.07s/it]
 73%|███████▎  | 20593/28080 [40:41:59<14:44:58,  7.09s/it]
                                                           
{'loss': 0.5816, 'learning_rate': 8.75683810768238e-05, 'epoch': 8.8}

 73%|███████▎  | 20593/28080 [40:41:59<14:44:58,  7.09s/it]
 73%|███████▎  | 20594/28080 [40:42:06<14:43:49,  7.08s/it]
                                                           
{'loss': 0.5929, 'learning_rate': 8.754646217306712e-05, 'epoch': 8.8}

 73%|███████▎  | 20594/28080 [40:42:06<14:43:49,  7.08s/it]
 73%|███████▎  | 20595/28080 [40:42:13<14:40:12,  7.06s/it]
                                                           
{'loss': 0.6065, 'learning_rate': 8.752454543058715e-05, 'epoch': 8.8}

 73%|███████▎  | 20595/28080 [40:42:13<14:40:12,  7.06s/it]
 73%|███████▎  | 20596/28080 [40:42:20<14:39:15,  7.05s/it]
                                                           
{'loss': 0.609, 'learning_rate': 8.750263084967544e-05, 'epoch': 8.8}

 73%|███████▎  | 20596/28080 [40:42:20<14:39:15,  7.05s/it]
 73%|███████▎  | 20597/28080 [40:42:27<14:36:39,  7.03s/it]
                                                           
{'loss': 0.5783, 'learning_rate': 8.748071843062364e-05, 'epoch': 8.8}

 73%|███████▎  | 20597/28080 [40:42:27<14:36:39,  7.03s/it]
 73%|███████▎  | 20598/28080 [40:42:34<14:38:54,  7.05s/it]
                                                           
{'loss': 0.6168, 'learning_rate': 8.745880817372323e-05, 'epoch': 8.8}

 73%|███████▎  | 20598/28080 [40:42:35<14:38:54,  7.05s/it]
 73%|███████▎  | 20599/28080 [40:42:42<14:38:52,  7.05s/it]
                                                           
{'loss': 0.5981, 'learning_rate': 8.743690007926569e-05, 'epoch': 8.8}

 73%|███████▎  | 20599/28080 [40:42:42<14:38:52,  7.05s/it]
 73%|███████▎  | 20600/28080 [40:42:49<14:40:24,  7.06s/it]
                                                           
{'loss': 0.5888, 'learning_rate': 8.741499414754239e-05, 'epoch': 8.8}

 73%|███████▎  | 20600/28080 [40:42:49<14:40:24,  7.06s/it]
 73%|███████▎  | 20601/28080 [40:42:56<14:39:34,  7.06s/it]
                                                           
{'loss': 0.5996, 'learning_rate': 8.739309037884496e-05, 'epoch': 8.8}

 73%|███████▎  | 20601/28080 [40:42:56<14:39:34,  7.06s/it]
 73%|███████▎  | 20602/28080 [40:43:03<14:41:03,  7.07s/it]
                                                           
{'loss': 0.6089, 'learning_rate': 8.737118877346465e-05, 'epoch': 8.8}

 73%|███████▎  | 20602/28080 [40:43:03<14:41:03,  7.07s/it]
 73%|███████▎  | 20603/28080 [40:43:10<14:40:46,  7.07s/it]
                                                           
{'loss': 0.6306, 'learning_rate': 8.734928933169294e-05, 'epoch': 8.8}

 73%|███████▎  | 20603/28080 [40:43:10<14:40:46,  7.07s/it]
 73%|███████▎  | 20604/28080 [40:43:17<14:37:55,  7.05s/it]
                                                           
{'loss': 0.6087, 'learning_rate': 8.732739205382117e-05, 'epoch': 8.8}

 73%|███████▎  | 20604/28080 [40:43:17<14:37:55,  7.05s/it]
 73%|███████▎  | 20605/28080 [40:43:24<14:35:19,  7.03s/it]
                                                           
{'loss': 0.6077, 'learning_rate': 8.730549694014061e-05, 'epoch': 8.8}

 73%|███████▎  | 20605/28080 [40:43:24<14:35:19,  7.03s/it]
 73%|███████▎  | 20606/28080 [40:43:31<14:38:52,  7.06s/it]
                                                           
{'loss': 0.5961, 'learning_rate': 8.728360399094252e-05, 'epoch': 8.8}

 73%|███████▎  | 20606/28080 [40:43:31<14:38:52,  7.06s/it]
 73%|███████▎  | 20607/28080 [40:43:38<14:41:05,  7.07s/it]
                                                           
{'loss': 0.6295, 'learning_rate': 8.726171320651826e-05, 'epoch': 8.8}

 73%|███████▎  | 20607/28080 [40:43:38<14:41:05,  7.07s/it]
 73%|███████▎  | 20608/28080 [40:43:45<14:43:02,  7.09s/it]
                                                           
{'loss': 0.6012, 'learning_rate': 8.723982458715903e-05, 'epoch': 8.8}

 73%|███████▎  | 20608/28080 [40:43:45<14:43:02,  7.09s/it]
 73%|███████▎  | 20609/28080 [40:43:52<14:46:39,  7.12s/it]
                                                           
{'loss': 0.6142, 'learning_rate': 8.721793813315604e-05, 'epoch': 8.8}

 73%|███████▎  | 20609/28080 [40:43:52<14:46:39,  7.12s/it]
 73%|███████▎  | 20610/28080 [40:43:59<14:41:46,  7.08s/it]
                                                           
{'loss': 0.6072, 'learning_rate': 8.719605384480033e-05, 'epoch': 8.8}

 73%|███████▎  | 20610/28080 [40:43:59<14:41:46,  7.08s/it]
 73%|███████▎  | 20611/28080 [40:44:07<14:43:28,  7.10s/it]
                                                           
{'loss': 0.6081, 'learning_rate': 8.717417172238329e-05, 'epoch': 8.8}

 73%|███████▎  | 20611/28080 [40:44:07<14:43:28,  7.10s/it]
 73%|███████▎  | 20612/28080 [40:44:13<14:35:05,  7.03s/it]
                                                           
{'loss': 0.6248, 'learning_rate': 8.715229176619587e-05, 'epoch': 8.81}

 73%|███████▎  | 20612/28080 [40:44:13<14:35:05,  7.03s/it]
 73%|███████▎  | 20613/28080 [40:44:21<14:38:33,  7.06s/it]
                                                           
{'loss': 0.6084, 'learning_rate': 8.713041397652926e-05, 'epoch': 8.81}

 73%|███████▎  | 20613/28080 [40:44:21<14:38:33,  7.06s/it]
 73%|███████▎  | 20614/28080 [40:44:28<14:41:40,  7.09s/it]
                                                           
{'loss': 0.597, 'learning_rate': 8.710853835367435e-05, 'epoch': 8.81}

 73%|███████▎  | 20614/28080 [40:44:28<14:41:40,  7.09s/it]
 73%|███████▎  | 20615/28080 [40:44:35<14:44:25,  7.11s/it]
                                                           
{'loss': 0.6142, 'learning_rate': 8.708666489792239e-05, 'epoch': 8.81}

 73%|███████▎  | 20615/28080 [40:44:35<14:44:25,  7.11s/it]
 73%|███████▎  | 20616/28080 [40:44:42<14:46:45,  7.13s/it]
                                                           
{'loss': 0.5964, 'learning_rate': 8.706479360956429e-05, 'epoch': 8.81}

 73%|███████▎  | 20616/28080 [40:44:42<14:46:45,  7.13s/it]
 73%|███████▎  | 20617/28080 [40:44:49<14:46:13,  7.12s/it]
                                                           
{'loss': 0.6077, 'learning_rate': 8.704292448889093e-05, 'epoch': 8.81}

 73%|███████▎  | 20617/28080 [40:44:49<14:46:13,  7.12s/it]
 73%|███████▎  | 20618/28080 [40:44:56<14:48:07,  7.14s/it]
                                                           
{'loss': 0.6087, 'learning_rate': 8.702105753619352e-05, 'epoch': 8.81}

 73%|███████▎  | 20618/28080 [40:44:56<14:48:07,  7.14s/it]
 73%|███████▎  | 20619/28080 [40:45:03<14:44:47,  7.12s/it]
                                                           
{'loss': 0.6074, 'learning_rate': 8.699919275176263e-05, 'epoch': 8.81}

 73%|███████▎  | 20619/28080 [40:45:03<14:44:47,  7.12s/it]
 73%|███████▎  | 20620/28080 [40:45:10<14:42:33,  7.10s/it]
                                                           
{'loss': 0.6038, 'learning_rate': 8.69773301358894e-05, 'epoch': 8.81}

 73%|███████▎  | 20620/28080 [40:45:10<14:42:33,  7.10s/it]
 73%|███████▎  | 20621/28080 [40:45:17<14:39:47,  7.08s/it]
                                                           
{'loss': 0.6233, 'learning_rate': 8.695546968886453e-05, 'epoch': 8.81}

 73%|███████▎  | 20621/28080 [40:45:17<14:39:47,  7.08s/it]
 73%|███████▎  | 20622/28080 [40:45:25<14:43:18,  7.11s/it]
                                                           
{'loss': 0.594, 'learning_rate': 8.693361141097902e-05, 'epoch': 8.81}

 73%|███████▎  | 20622/28080 [40:45:25<14:43:18,  7.11s/it]
 73%|███████▎  | 20623/28080 [40:45:32<14:45:02,  7.12s/it]
                                                           
{'loss': 0.5848, 'learning_rate': 8.691175530252358e-05, 'epoch': 8.81}

 73%|███████▎  | 20623/28080 [40:45:32<14:45:02,  7.12s/it]
 73%|███████▎  | 20624/28080 [40:45:39<14:41:23,  7.09s/it]
                                                           
{'loss': 0.6019, 'learning_rate': 8.688990136378899e-05, 'epoch': 8.81}

 73%|███████▎  | 20624/28080 [40:45:39<14:41:23,  7.09s/it]
 73%|███████▎  | 20625/28080 [40:45:46<14:42:09,  7.10s/it]
                                                           
{'loss': 0.6134, 'learning_rate': 8.686804959506588e-05, 'epoch': 8.81}

 73%|███████▎  | 20625/28080 [40:45:46<14:42:09,  7.10s/it]
 73%|███████▎  | 20626/28080 [40:45:53<14:44:28,  7.12s/it]
                                                           
{'loss': 0.6248, 'learning_rate': 8.68461999966452e-05, 'epoch': 8.81}

 73%|███████▎  | 20626/28080 [40:45:53<14:44:28,  7.12s/it]
 73%|███████▎  | 20627/28080 [40:46:00<14:39:02,  7.08s/it]
                                                           
{'loss': 0.6331, 'learning_rate': 8.682435256881749e-05, 'epoch': 8.81}

 73%|███████▎  | 20627/28080 [40:46:00<14:39:02,  7.08s/it]
 73%|███████▎  | 20628/28080 [40:46:07<14:41:25,  7.10s/it]
                                                           
{'loss': 0.5957, 'learning_rate': 8.680250731187345e-05, 'epoch': 8.81}

 73%|███████▎  | 20628/28080 [40:46:07<14:41:25,  7.10s/it]
 73%|███████▎  | 20629/28080 [40:46:14<14:44:36,  7.12s/it]
                                                           
{'loss': 0.6044, 'learning_rate': 8.67806642261036e-05, 'epoch': 8.81}

 73%|███████▎  | 20629/28080 [40:46:14<14:44:36,  7.12s/it]
 73%|███████▎  | 20630/28080 [40:46:21<14:43:31,  7.12s/it]
                                                           
{'loss': 0.6027, 'learning_rate': 8.675882331179869e-05, 'epoch': 8.81}

 73%|███████▎  | 20630/28080 [40:46:21<14:43:31,  7.12s/it]
 73%|███████▎  | 20631/28080 [40:46:29<14:43:00,  7.11s/it]
                                                           
{'loss': 0.5829, 'learning_rate': 8.673698456924917e-05, 'epoch': 8.81}

 73%|███████▎  | 20631/28080 [40:46:29<14:43:00,  7.11s/it]
 73%|███████▎  | 20632/28080 [40:46:36<14:45:32,  7.13s/it]
                                                           
{'loss': 0.5893, 'learning_rate': 8.67151479987458e-05, 'epoch': 8.81}

 73%|███████▎  | 20632/28080 [40:46:36<14:45:32,  7.13s/it]
 73%|███████▎  | 20633/28080 [40:46:43<14:45:17,  7.13s/it]
                                                           
{'loss': 0.6046, 'learning_rate': 8.669331360057878e-05, 'epoch': 8.81}

 73%|███████▎  | 20633/28080 [40:46:43<14:45:17,  7.13s/it]
 73%|███████▎  | 20634/28080 [40:46:50<14:42:00,  7.11s/it]
                                                           
{'loss': 0.6244, 'learning_rate': 8.66714813750388e-05, 'epoch': 8.81}

 73%|███████▎  | 20634/28080 [40:46:50<14:42:00,  7.11s/it]
 73%|███████▎  | 20635/28080 [40:46:57<14:44:04,  7.12s/it]
                                                           
{'loss': 0.5903, 'learning_rate': 8.66496513224162e-05, 'epoch': 8.82}

 73%|███████▎  | 20635/28080 [40:46:57<14:44:04,  7.12s/it]
 73%|███████▎  | 20636/28080 [40:47:04<14:40:37,  7.10s/it]
                                                           
{'loss': 0.6032, 'learning_rate': 8.662782344300155e-05, 'epoch': 8.82}

 73%|███████▎  | 20636/28080 [40:47:04<14:40:37,  7.10s/it]
 73%|███████▎  | 20637/28080 [40:47:11<14:37:40,  7.08s/it]
                                                           
{'loss': 0.6162, 'learning_rate': 8.660599773708516e-05, 'epoch': 8.82}

 73%|███████▎  | 20637/28080 [40:47:11<14:37:40,  7.08s/it]
 73%|███████▎  | 20638/28080 [40:47:18<14:37:31,  7.07s/it]
                                                           
{'loss': 0.5842, 'learning_rate': 8.658417420495742e-05, 'epoch': 8.82}

 73%|███████▎  | 20638/28080 [40:47:18<14:37:31,  7.07s/it]
 74%|███████▎  | 20639/28080 [40:47:25<14:34:10,  7.05s/it]
                                                           
{'loss': 0.6076, 'learning_rate': 8.656235284690858e-05, 'epoch': 8.82}

 74%|███████▎  | 20639/28080 [40:47:25<14:34:10,  7.05s/it]
 74%|███████▎  | 20640/28080 [40:47:32<14:32:14,  7.03s/it]
                                                           
{'loss': 0.621, 'learning_rate': 8.654053366322908e-05, 'epoch': 8.82}

 74%|███████▎  | 20640/28080 [40:47:32<14:32:14,  7.03s/it]
 74%|███████▎  | 20641/28080 [40:47:39<14:31:44,  7.03s/it]
                                                           
{'loss': 0.6205, 'learning_rate': 8.651871665420919e-05, 'epoch': 8.82}

 74%|███████▎  | 20641/28080 [40:47:39<14:31:44,  7.03s/it]
 74%|███████▎  | 20642/28080 [40:47:46<14:36:20,  7.07s/it]
                                                           
{'loss': 0.6067, 'learning_rate': 8.649690182013908e-05, 'epoch': 8.82}

 74%|███████▎  | 20642/28080 [40:47:46<14:36:20,  7.07s/it]
 74%|███████▎  | 20643/28080 [40:47:54<14:37:27,  7.08s/it]
                                                           
{'loss': 0.6126, 'learning_rate': 8.647508916130903e-05, 'epoch': 8.82}

 74%|███████▎  | 20643/28080 [40:47:54<14:37:27,  7.08s/it]
 74%|███████▎  | 20644/28080 [40:48:01<14:35:28,  7.06s/it]
                                                           
{'loss': 0.6016, 'learning_rate': 8.645327867800914e-05, 'epoch': 8.82}

 74%|███████▎  | 20644/28080 [40:48:01<14:35:28,  7.06s/it]
 74%|███████▎  | 20645/28080 [40:48:08<14:35:18,  7.06s/it]
                                                           
{'loss': 0.6213, 'learning_rate': 8.643147037052973e-05, 'epoch': 8.82}

 74%|███████▎  | 20645/28080 [40:48:08<14:35:18,  7.06s/it]
 74%|███████▎  | 20646/28080 [40:48:15<14:36:58,  7.08s/it]
                                                           
{'loss': 0.5919, 'learning_rate': 8.640966423916089e-05, 'epoch': 8.82}

 74%|███████▎  | 20646/28080 [40:48:15<14:36:58,  7.08s/it]
 74%|███████▎  | 20647/28080 [40:48:22<14:39:01,  7.10s/it]
                                                           
{'loss': 0.6155, 'learning_rate': 8.638786028419265e-05, 'epoch': 8.82}

 74%|███████▎  | 20647/28080 [40:48:22<14:39:01,  7.10s/it]
 74%|███████▎  | 20648/28080 [40:48:29<14:39:08,  7.10s/it]
                                                           
{'loss': 0.6042, 'learning_rate': 8.636605850591508e-05, 'epoch': 8.82}

 74%|███████▎  | 20648/28080 [40:48:29<14:39:08,  7.10s/it]
 74%|███████▎  | 20649/28080 [40:48:36<14:38:08,  7.09s/it]
                                                           
{'loss': 0.5989, 'learning_rate': 8.634425890461839e-05, 'epoch': 8.82}

 74%|███████▎  | 20649/28080 [40:48:36<14:38:08,  7.09s/it]
 74%|███████▎  | 20650/28080 [40:48:43<14:34:03,  7.06s/it]
                                                           
{'loss': 0.5952, 'learning_rate': 8.632246148059242e-05, 'epoch': 8.82}

 74%|███████▎  | 20650/28080 [40:48:43<14:34:03,  7.06s/it]
 74%|███████▎  | 20651/28080 [40:48:50<14:38:49,  7.10s/it]
                                                           
{'loss': 0.6069, 'learning_rate': 8.630066623412738e-05, 'epoch': 8.82}

 74%|███████▎  | 20651/28080 [40:48:50<14:38:49,  7.10s/it]
 74%|███████▎  | 20652/28080 [40:48:57<14:40:31,  7.11s/it]
                                                           
{'loss': 0.6115, 'learning_rate': 8.627887316551295e-05, 'epoch': 8.82}

 74%|███████▎  | 20652/28080 [40:48:57<14:40:31,  7.11s/it]
 74%|███████▎  | 20653/28080 [40:49:04<14:36:08,  7.08s/it]
                                                           
{'loss': 0.6024, 'learning_rate': 8.625708227503928e-05, 'epoch': 8.82}

 74%|███████▎  | 20653/28080 [40:49:04<14:36:08,  7.08s/it]
 74%|███████▎  | 20654/28080 [40:49:11<14:36:35,  7.08s/it]
                                                           
{'loss': 0.6174, 'learning_rate': 8.623529356299614e-05, 'epoch': 8.82}

 74%|███████▎  | 20654/28080 [40:49:11<14:36:35,  7.08s/it]
 74%|███████▎  | 20655/28080 [40:49:18<14:35:23,  7.07s/it]
                                                           
{'loss': 0.6055, 'learning_rate': 8.621350702967353e-05, 'epoch': 8.82}

 74%|███████▎  | 20655/28080 [40:49:18<14:35:23,  7.07s/it]
 74%|███████▎  | 20656/28080 [40:49:26<14:38:05,  7.10s/it]
                                                           
{'loss': 0.6111, 'learning_rate': 8.619172267536127e-05, 'epoch': 8.82}

 74%|███████▎  | 20656/28080 [40:49:26<14:38:05,  7.10s/it]
 74%|███████▎  | 20657/28080 [40:49:33<14:42:08,  7.13s/it]
                                                           
{'loss': 0.6093, 'learning_rate': 8.616994050034916e-05, 'epoch': 8.82}

 74%|███████▎  | 20657/28080 [40:49:33<14:42:08,  7.13s/it]
 74%|███████▎  | 20658/28080 [40:49:40<14:41:21,  7.12s/it]
                                                           
{'loss': 0.5987, 'learning_rate': 8.614816050492686e-05, 'epoch': 8.82}

 74%|███████▎  | 20658/28080 [40:49:40<14:41:21,  7.12s/it]
 74%|███████▎  | 20659/28080 [40:49:47<14:40:26,  7.12s/it]
                                                           
{'loss': 0.608, 'learning_rate': 8.612638268938433e-05, 'epoch': 8.83}

 74%|███████▎  | 20659/28080 [40:49:47<14:40:26,  7.12s/it]
 74%|███████▎  | 20660/28080 [40:49:54<14:37:55,  7.10s/it]
                                                           
{'loss': 0.6116, 'learning_rate': 8.610460705401124e-05, 'epoch': 8.83}

 74%|███████▎  | 20660/28080 [40:49:54<14:37:55,  7.10s/it]
 74%|███████▎  | 20661/28080 [40:50:01<14:33:51,  7.07s/it]
                                                           
{'loss': 0.6187, 'learning_rate': 8.608283359909724e-05, 'epoch': 8.83}

 74%|███████▎  | 20661/28080 [40:50:01<14:33:51,  7.07s/it]
 74%|███████▎  | 20662/28080 [40:50:08<14:35:25,  7.08s/it]
                                                           
{'loss': 0.5932, 'learning_rate': 8.606106232493199e-05, 'epoch': 8.83}

 74%|███████▎  | 20662/28080 [40:50:08<14:35:25,  7.08s/it]
 74%|███████▎  | 20663/28080 [40:50:15<14:35:09,  7.08s/it]
                                                           
{'loss': 0.6169, 'learning_rate': 8.603929323180526e-05, 'epoch': 8.83}

 74%|███████▎  | 20663/28080 [40:50:15<14:35:09,  7.08s/it]
 74%|███████▎  | 20664/28080 [40:50:22<14:36:22,  7.09s/it]
                                                           
{'loss': 0.6121, 'learning_rate': 8.601752632000648e-05, 'epoch': 8.83}

 74%|███████▎  | 20664/28080 [40:50:22<14:36:22,  7.09s/it]
 74%|███████▎  | 20665/28080 [40:50:29<14:33:03,  7.06s/it]
                                                           
{'loss': 0.598, 'learning_rate': 8.599576158982542e-05, 'epoch': 8.83}

 74%|███████▎  | 20665/28080 [40:50:29<14:33:03,  7.06s/it]
 74%|███████▎  | 20666/28080 [40:50:37<14:33:53,  7.07s/it]
                                                           
{'loss': 0.5954, 'learning_rate': 8.597399904155165e-05, 'epoch': 8.83}

 74%|███████▎  | 20666/28080 [40:50:37<14:33:53,  7.07s/it]
 74%|███████▎  | 20667/28080 [40:50:44<14:34:24,  7.08s/it]
                                                           
{'loss': 0.6173, 'learning_rate': 8.595223867547444e-05, 'epoch': 8.83}

 74%|███████▎  | 20667/28080 [40:50:44<14:34:24,  7.08s/it]
 74%|███████▎  | 20668/28080 [40:50:51<14:34:51,  7.08s/it]
                                                           
{'loss': 0.6139, 'learning_rate': 8.593048049188357e-05, 'epoch': 8.83}

 74%|███████▎  | 20668/28080 [40:50:51<14:34:51,  7.08s/it]
 74%|███████▎  | 20669/28080 [40:50:58<14:34:26,  7.08s/it]
                                                           
{'loss': 0.5997, 'learning_rate': 8.590872449106826e-05, 'epoch': 8.83}

 74%|███████▎  | 20669/28080 [40:50:58<14:34:26,  7.08s/it]
 74%|███████▎  | 20670/28080 [40:51:05<14:31:28,  7.06s/it]
                                                           
{'loss': 0.6141, 'learning_rate': 8.588697067331821e-05, 'epoch': 8.83}

 74%|███████▎  | 20670/28080 [40:51:05<14:31:28,  7.06s/it]
 74%|███████▎  | 20671/28080 [40:51:12<14:34:04,  7.08s/it]
                                                           
{'loss': 0.5977, 'learning_rate': 8.586521903892269e-05, 'epoch': 8.83}

 74%|███████▎  | 20671/28080 [40:51:12<14:34:04,  7.08s/it]
 74%|███████▎  | 20672/28080 [40:51:19<14:36:10,  7.10s/it]
                                                           
{'loss': 0.6048, 'learning_rate': 8.584346958817111e-05, 'epoch': 8.83}

 74%|███████▎  | 20672/28080 [40:51:19<14:36:10,  7.10s/it]
 74%|███████▎  | 20673/28080 [40:51:26<14:36:35,  7.10s/it]
                                                           
{'loss': 0.609, 'learning_rate': 8.582172232135275e-05, 'epoch': 8.83}

 74%|███████▎  | 20673/28080 [40:51:26<14:36:35,  7.10s/it]
 74%|███████▎  | 20674/28080 [40:51:33<14:34:01,  7.08s/it]
                                                           
{'loss': 0.5917, 'learning_rate': 8.579997723875705e-05, 'epoch': 8.83}

 74%|███████▎  | 20674/28080 [40:51:33<14:34:01,  7.08s/it]
 74%|███████▎  | 20675/28080 [40:51:40<14:35:08,  7.09s/it]
                                                           
{'loss': 0.61, 'learning_rate': 8.577823434067328e-05, 'epoch': 8.83}

 74%|███████▎  | 20675/28080 [40:51:40<14:35:08,  7.09s/it]
 74%|███████▎  | 20676/28080 [40:51:47<14:28:57,  7.04s/it]
                                                           
{'loss': 0.6021, 'learning_rate': 8.575649362739066e-05, 'epoch': 8.83}

 74%|███████▎  | 20676/28080 [40:51:47<14:28:57,  7.04s/it]
 74%|███████▎  | 20677/28080 [40:51:54<14:30:49,  7.06s/it]
                                                           
{'loss': 0.5942, 'learning_rate': 8.57347550991984e-05, 'epoch': 8.83}

 74%|███████▎  | 20677/28080 [40:51:54<14:30:49,  7.06s/it]
 74%|███████▎  | 20678/28080 [40:52:01<14:28:20,  7.04s/it]
                                                           
{'loss': 0.619, 'learning_rate': 8.571301875638582e-05, 'epoch': 8.83}

 74%|███████▎  | 20678/28080 [40:52:01<14:28:20,  7.04s/it]
 74%|███████▎  | 20679/28080 [40:52:08<14:25:19,  7.02s/it]
                                                           
{'loss': 0.6364, 'learning_rate': 8.569128459924198e-05, 'epoch': 8.83}

 74%|███████▎  | 20679/28080 [40:52:08<14:25:19,  7.02s/it]
 74%|███████▎  | 20680/28080 [40:52:15<14:29:35,  7.05s/it]
                                                           
{'loss': 0.6103, 'learning_rate': 8.566955262805623e-05, 'epoch': 8.83}

 74%|███████▎  | 20680/28080 [40:52:15<14:29:35,  7.05s/it]
 74%|███████▎  | 20681/28080 [40:52:23<14:31:04,  7.06s/it]
                                                           
{'loss': 0.6132, 'learning_rate': 8.56478228431174e-05, 'epoch': 8.83}

 74%|███████▎  | 20681/28080 [40:52:23<14:31:04,  7.06s/it]
 74%|███████▎  | 20682/28080 [40:52:30<14:31:57,  7.07s/it]
                                                           
{'loss': 0.6336, 'learning_rate': 8.562609524471482e-05, 'epoch': 8.84}

 74%|███████▎  | 20682/28080 [40:52:30<14:31:57,  7.07s/it]
 74%|███████▎  | 20683/28080 [40:52:37<14:32:14,  7.08s/it]
                                                           
{'loss': 0.6086, 'learning_rate': 8.560436983313736e-05, 'epoch': 8.84}

 74%|███████▎  | 20683/28080 [40:52:37<14:32:14,  7.08s/it]
 74%|███████▎  | 20684/28080 [40:52:44<14:32:16,  7.08s/it]
                                                           
{'loss': 0.6067, 'learning_rate': 8.558264660867426e-05, 'epoch': 8.84}

 74%|███████▎  | 20684/28080 [40:52:44<14:32:16,  7.08s/it]
 74%|███████▎  | 20685/28080 [40:52:51<14:30:29,  7.06s/it]
                                                           
{'loss': 0.633, 'learning_rate': 8.556092557161443e-05, 'epoch': 8.84}

 74%|███████▎  | 20685/28080 [40:52:51<14:30:29,  7.06s/it]
 74%|███████▎  | 20686/28080 [40:52:58<14:34:49,  7.10s/it]
                                                           
{'loss': 0.6176, 'learning_rate': 8.553920672224686e-05, 'epoch': 8.84}

 74%|███████▎  | 20686/28080 [40:52:58<14:34:49,  7.10s/it]
 74%|███████▎  | 20687/28080 [40:53:05<14:37:59,  7.13s/it]
                                                           
{'loss': 0.6202, 'learning_rate': 8.551749006086037e-05, 'epoch': 8.84}

 74%|███████▎  | 20687/28080 [40:53:05<14:37:59,  7.13s/it]
 74%|███████▎  | 20688/28080 [40:53:12<14:38:51,  7.13s/it]
                                                           
{'loss': 0.6082, 'learning_rate': 8.549577558774407e-05, 'epoch': 8.84}

 74%|███████▎  | 20688/28080 [40:53:12<14:38:51,  7.13s/it]
 74%|███████▎  | 20689/28080 [40:53:19<14:34:49,  7.10s/it]
                                                           
{'loss': 0.5804, 'learning_rate': 8.54740633031868e-05, 'epoch': 8.84}

 74%|███████▎  | 20689/28080 [40:53:19<14:34:49,  7.10s/it]
 74%|███████▎  | 20690/28080 [40:53:26<14:36:23,  7.12s/it]
                                                           
{'loss': 0.6092, 'learning_rate': 8.545235320747735e-05, 'epoch': 8.84}

 74%|███████▎  | 20690/28080 [40:53:26<14:36:23,  7.12s/it]
 74%|███████▎  | 20691/28080 [40:53:34<14:36:18,  7.12s/it]
                                                           
{'loss': 0.5898, 'learning_rate': 8.54306453009046e-05, 'epoch': 8.84}

 74%|███████▎  | 20691/28080 [40:53:34<14:36:18,  7.12s/it]
 74%|███████▎  | 20692/28080 [40:53:41<14:36:53,  7.12s/it]
                                                           
{'loss': 0.5974, 'learning_rate': 8.540893958375725e-05, 'epoch': 8.84}

 74%|███████▎  | 20692/28080 [40:53:41<14:36:53,  7.12s/it]
 74%|███████▎  | 20693/28080 [40:53:48<14:33:16,  7.09s/it]
                                                           
{'loss': 0.6149, 'learning_rate': 8.538723605632426e-05, 'epoch': 8.84}

 74%|███████▎  | 20693/28080 [40:53:48<14:33:16,  7.09s/it]
 74%|███████▎  | 20694/28080 [40:53:55<14:29:21,  7.06s/it]
                                                           
{'loss': 0.6057, 'learning_rate': 8.536553471889425e-05, 'epoch': 8.84}

 74%|███████▎  | 20694/28080 [40:53:55<14:29:21,  7.06s/it]
 74%|███████▎  | 20695/28080 [40:54:02<14:28:25,  7.06s/it]
                                                           
{'loss': 0.6135, 'learning_rate': 8.534383557175599e-05, 'epoch': 8.84}

 74%|███████▎  | 20695/28080 [40:54:02<14:28:25,  7.06s/it]
 74%|███████▎  | 20696/28080 [40:54:09<14:24:18,  7.02s/it]
                                                           
{'loss': 0.6016, 'learning_rate': 8.5322138615198e-05, 'epoch': 8.84}

 74%|███████▎  | 20696/28080 [40:54:09<14:24:18,  7.02s/it]
 74%|███████▎  | 20697/28080 [40:54:16<14:22:38,  7.01s/it]
                                                           
{'loss': 0.599, 'learning_rate': 8.530044384950919e-05, 'epoch': 8.84}

 74%|███████▎  | 20697/28080 [40:54:16<14:22:38,  7.01s/it]
 74%|███████▎  | 20698/28080 [40:54:23<14:28:33,  7.06s/it]
                                                           
{'loss': 0.5813, 'learning_rate': 8.527875127497794e-05, 'epoch': 8.84}

 74%|███████▎  | 20698/28080 [40:54:23<14:28:33,  7.06s/it]
 74%|███████▎  | 20699/28080 [40:54:30<14:31:24,  7.08s/it]
                                                           
{'loss': 0.5878, 'learning_rate': 8.525706089189317e-05, 'epoch': 8.84}

 74%|███████▎  | 20699/28080 [40:54:30<14:31:24,  7.08s/it]
 74%|███████▎  | 20700/28080 [40:54:37<14:33:38,  7.10s/it]
                                                           
{'loss': 0.604, 'learning_rate': 8.523537270054307e-05, 'epoch': 8.84}

 74%|███████▎  | 20700/28080 [40:54:37<14:33:38,  7.10s/it]
 74%|███████▎  | 20701/28080 [40:54:44<14:33:10,  7.10s/it]
                                                           
{'loss': 0.6097, 'learning_rate': 8.521368670121646e-05, 'epoch': 8.84}

 74%|███████▎  | 20701/28080 [40:54:44<14:33:10,  7.10s/it]
 74%|███████▎  | 20702/28080 [40:54:51<14:34:09,  7.11s/it]
                                                           
{'loss': 0.613, 'learning_rate': 8.519200289420165e-05, 'epoch': 8.84}

 74%|███████▎  | 20702/28080 [40:54:51<14:34:09,  7.11s/it]
 74%|███████▎  | 20703/28080 [40:54:58<14:30:12,  7.08s/it]
                                                           
{'loss': 0.6027, 'learning_rate': 8.51703212797873e-05, 'epoch': 8.84}

 74%|███████▎  | 20703/28080 [40:54:58<14:30:12,  7.08s/it]
 74%|███████▎  | 20704/28080 [40:55:06<14:31:16,  7.09s/it]
                                                           
{'loss': 0.6149, 'learning_rate': 8.514864185826179e-05, 'epoch': 8.84}

 74%|███████▎  | 20704/28080 [40:55:06<14:31:16,  7.09s/it]
 74%|███████▎  | 20705/28080 [40:55:13<14:33:40,  7.11s/it]
                                                           
{'loss': 0.6084, 'learning_rate': 8.512696462991352e-05, 'epoch': 8.84}

 74%|███████▎  | 20705/28080 [40:55:13<14:33:40,  7.11s/it]
 74%|███████▎  | 20706/28080 [40:55:20<14:34:25,  7.11s/it]
                                                           
{'loss': 0.6071, 'learning_rate': 8.510528959503081e-05, 'epoch': 8.85}

 74%|███████▎  | 20706/28080 [40:55:20<14:34:25,  7.11s/it]
 74%|███████▎  | 20707/28080 [40:55:27<14:31:41,  7.09s/it]
                                                           
{'loss': 0.6193, 'learning_rate': 8.508361675390219e-05, 'epoch': 8.85}

 74%|███████▎  | 20707/28080 [40:55:27<14:31:41,  7.09s/it]
 74%|███████▎  | 20708/28080 [40:55:34<14:31:27,  7.09s/it]
                                                           
{'loss': 0.6053, 'learning_rate': 8.506194610681594e-05, 'epoch': 8.85}

 74%|███████▎  | 20708/28080 [40:55:34<14:31:27,  7.09s/it]
 74%|███████▍  | 20709/28080 [40:55:41<14:28:01,  7.07s/it]
                                                           
{'loss': 0.6193, 'learning_rate': 8.504027765406033e-05, 'epoch': 8.85}

 74%|███████▍  | 20709/28080 [40:55:41<14:28:01,  7.07s/it]
 74%|███████▍  | 20710/28080 [40:55:48<14:26:12,  7.05s/it]
                                                           
{'loss': 0.6035, 'learning_rate': 8.501861139592354e-05, 'epoch': 8.85}

 74%|███████▍  | 20710/28080 [40:55:48<14:26:12,  7.05s/it]
 74%|███████▍  | 20711/28080 [40:55:55<14:28:50,  7.07s/it]
                                                           
{'loss': 0.6121, 'learning_rate': 8.499694733269403e-05, 'epoch': 8.85}

 74%|███████▍  | 20711/28080 [40:55:55<14:28:50,  7.07s/it]
 74%|███████▍  | 20712/28080 [40:56:02<14:28:16,  7.07s/it]
                                                           
{'loss': 0.619, 'learning_rate': 8.497528546465982e-05, 'epoch': 8.85}

 74%|███████▍  | 20712/28080 [40:56:02<14:28:16,  7.07s/it]
 74%|███████▍  | 20713/28080 [40:56:09<14:28:23,  7.07s/it]
                                                           
{'loss': 0.6364, 'learning_rate': 8.495362579210936e-05, 'epoch': 8.85}

 74%|███████▍  | 20713/28080 [40:56:09<14:28:23,  7.07s/it]
 74%|███████▍  | 20714/28080 [40:56:16<14:29:56,  7.09s/it]
                                                           
{'loss': 0.602, 'learning_rate': 8.493196831533048e-05, 'epoch': 8.85}

 74%|███████▍  | 20714/28080 [40:56:16<14:29:56,  7.09s/it]
 74%|███████▍  | 20715/28080 [40:56:23<14:28:34,  7.08s/it]
                                                           
{'loss': 0.6016, 'learning_rate': 8.491031303461155e-05, 'epoch': 8.85}

 74%|███████▍  | 20715/28080 [40:56:23<14:28:34,  7.08s/it]
 74%|███████▍  | 20716/28080 [40:56:31<14:32:48,  7.11s/it]
                                                           
{'loss': 0.6191, 'learning_rate': 8.488865995024059e-05, 'epoch': 8.85}

 74%|███████▍  | 20716/28080 [40:56:31<14:32:48,  7.11s/it]
 74%|███████▍  | 20717/28080 [40:56:38<14:34:51,  7.13s/it]
                                                           
{'loss': 0.6204, 'learning_rate': 8.486700906250557e-05, 'epoch': 8.85}

 74%|███████▍  | 20717/28080 [40:56:38<14:34:51,  7.13s/it]
 74%|███████▍  | 20718/28080 [40:56:45<14:34:52,  7.13s/it]
                                                           
{'loss': 0.6303, 'learning_rate': 8.484536037169474e-05, 'epoch': 8.85}

 74%|███████▍  | 20718/28080 [40:56:45<14:34:52,  7.13s/it]
 74%|███████▍  | 20719/28080 [40:56:52<14:32:02,  7.11s/it]
                                                           
{'loss': 0.6044, 'learning_rate': 8.482371387809601e-05, 'epoch': 8.85}

 74%|███████▍  | 20719/28080 [40:56:52<14:32:02,  7.11s/it]
 74%|███████▍  | 20720/28080 [40:56:59<14:32:26,  7.11s/it]
                                                           
{'loss': 0.5979, 'learning_rate': 8.480206958199738e-05, 'epoch': 8.85}

 74%|███████▍  | 20720/28080 [40:56:59<14:32:26,  7.11s/it]
 74%|███████▍  | 20721/28080 [40:57:06<14:32:58,  7.12s/it]
                                                           
{'loss': 0.6051, 'learning_rate': 8.478042748368667e-05, 'epoch': 8.85}

 74%|███████▍  | 20721/28080 [40:57:06<14:32:58,  7.12s/it]
 74%|███████▍  | 20722/28080 [40:57:13<14:34:20,  7.13s/it]
                                                           
{'loss': 0.5919, 'learning_rate': 8.475878758345205e-05, 'epoch': 8.85}

 74%|███████▍  | 20722/28080 [40:57:13<14:34:20,  7.13s/it]
 74%|███████▍  | 20723/28080 [40:57:21<14:35:04,  7.14s/it]
                                                           
{'loss': 0.5991, 'learning_rate': 8.473714988158124e-05, 'epoch': 8.85}

 74%|███████▍  | 20723/28080 [40:57:21<14:35:04,  7.14s/it]
 74%|███████▍  | 20724/28080 [40:57:28<14:38:49,  7.17s/it]
                                                           
{'loss': 0.5909, 'learning_rate': 8.47155143783622e-05, 'epoch': 8.85}

 74%|███████▍  | 20724/28080 [40:57:28<14:38:49,  7.17s/it]
 74%|███████▍  | 20725/28080 [40:57:35<14:38:40,  7.17s/it]
                                                           
{'loss': 0.6091, 'learning_rate': 8.469388107408263e-05, 'epoch': 8.85}

 74%|███████▍  | 20725/28080 [40:57:35<14:38:40,  7.17s/it]
 74%|███████▍  | 20726/28080 [40:57:42<14:34:36,  7.14s/it]
                                                           
{'loss': 0.6363, 'learning_rate': 8.46722499690305e-05, 'epoch': 8.85}

 74%|███████▍  | 20726/28080 [40:57:42<14:34:36,  7.14s/it]
 74%|███████▍  | 20727/28080 [40:57:49<14:34:13,  7.13s/it]
                                                           
{'loss': 0.6098, 'learning_rate': 8.465062106349348e-05, 'epoch': 8.85}

 74%|███████▍  | 20727/28080 [40:57:49<14:34:13,  7.13s/it]
 74%|███████▍  | 20728/28080 [40:57:56<14:34:15,  7.13s/it]
                                                           
{'loss': 0.6078, 'learning_rate': 8.46289943577595e-05, 'epoch': 8.85}

 74%|███████▍  | 20728/28080 [40:57:56<14:34:15,  7.13s/it]
 74%|███████▍  | 20729/28080 [40:58:03<14:32:38,  7.12s/it]
                                                           
{'loss': 0.5901, 'learning_rate': 8.460736985211597e-05, 'epoch': 8.86}

 74%|███████▍  | 20729/28080 [40:58:03<14:32:38,  7.12s/it]
 74%|███████▍  | 20730/28080 [40:58:10<14:31:44,  7.12s/it]
                                                           
{'loss': 0.61, 'learning_rate': 8.458574754685085e-05, 'epoch': 8.86}

 74%|███████▍  | 20730/28080 [40:58:10<14:31:44,  7.12s/it]
 74%|███████▍  | 20731/28080 [40:58:18<14:31:43,  7.12s/it]
                                                           
{'loss': 0.6071, 'learning_rate': 8.456412744225167e-05, 'epoch': 8.86}

 74%|███████▍  | 20731/28080 [40:58:18<14:31:43,  7.12s/it]
 74%|███████▍  | 20732/28080 [40:58:25<14:31:08,  7.11s/it]
                                                           
{'loss': 0.6101, 'learning_rate': 8.454250953860615e-05, 'epoch': 8.86}

 74%|███████▍  | 20732/28080 [40:58:25<14:31:08,  7.11s/it]
 74%|███████▍  | 20733/28080 [40:58:32<14:33:36,  7.13s/it]
                                                           
{'loss': 0.597, 'learning_rate': 8.452089383620184e-05, 'epoch': 8.86}

 74%|███████▍  | 20733/28080 [40:58:32<14:33:36,  7.13s/it]
 74%|███████▍  | 20734/28080 [40:58:39<14:30:22,  7.11s/it]
                                                           
{'loss': 0.6001, 'learning_rate': 8.449928033532633e-05, 'epoch': 8.86}

 74%|███████▍  | 20734/28080 [40:58:39<14:30:22,  7.11s/it]
 74%|███████▍  | 20735/28080 [40:58:46<14:27:01,  7.08s/it]
                                                           
{'loss': 0.5996, 'learning_rate': 8.447766903626711e-05, 'epoch': 8.86}

 74%|███████▍  | 20735/28080 [40:58:46<14:27:01,  7.08s/it]
 74%|███████▍  | 20736/28080 [40:58:53<14:26:01,  7.08s/it]
                                                           
{'loss': 0.6075, 'learning_rate': 8.445605993931177e-05, 'epoch': 8.86}

 74%|███████▍  | 20736/28080 [40:58:53<14:26:01,  7.08s/it]
 74%|███████▍  | 20737/28080 [40:59:00<14:29:36,  7.11s/it]
                                                           
{'loss': 0.5898, 'learning_rate': 8.44344530447478e-05, 'epoch': 8.86}

 74%|███████▍  | 20737/28080 [40:59:00<14:29:36,  7.11s/it]
 74%|███████▍  | 20738/28080 [40:59:07<14:29:39,  7.11s/it]
                                                           
{'loss': 0.6062, 'learning_rate': 8.441284835286264e-05, 'epoch': 8.86}

 74%|███████▍  | 20738/28080 [40:59:07<14:29:39,  7.11s/it]
 74%|███████▍  | 20739/28080 [40:59:14<14:30:55,  7.12s/it]
                                                           
{'loss': 0.603, 'learning_rate': 8.439124586394358e-05, 'epoch': 8.86}

 74%|███████▍  | 20739/28080 [40:59:14<14:30:55,  7.12s/it]
 74%|███████▍  | 20740/28080 [40:59:21<14:23:38,  7.06s/it]
                                                           
{'loss': 0.6225, 'learning_rate': 8.436964557827829e-05, 'epoch': 8.86}

 74%|███████▍  | 20740/28080 [40:59:21<14:23:38,  7.06s/it]
 74%|███████▍  | 20741/28080 [40:59:28<14:25:18,  7.07s/it]
                                                           
{'loss': 0.5984, 'learning_rate': 8.434804749615394e-05, 'epoch': 8.86}

 74%|███████▍  | 20741/28080 [40:59:28<14:25:18,  7.07s/it]
 74%|███████▍  | 20742/28080 [40:59:36<14:27:44,  7.10s/it]
                                                           
{'loss': 0.5942, 'learning_rate': 8.432645161785796e-05, 'epoch': 8.86}

 74%|███████▍  | 20742/28080 [40:59:36<14:27:44,  7.10s/it]
 74%|███████▍  | 20743/28080 [40:59:43<14:30:33,  7.12s/it]
                                                           
{'loss': 0.6232, 'learning_rate': 8.430485794367759e-05, 'epoch': 8.86}

 74%|███████▍  | 20743/28080 [40:59:43<14:30:33,  7.12s/it]
 74%|███████▍  | 20744/28080 [40:59:50<14:27:24,  7.09s/it]
                                                           
{'loss': 0.6036, 'learning_rate': 8.428326647390008e-05, 'epoch': 8.86}

 74%|███████▍  | 20744/28080 [40:59:50<14:27:24,  7.09s/it]
 74%|███████▍  | 20745/28080 [40:59:57<14:30:06,  7.12s/it]
                                                           
{'loss': 0.5992, 'learning_rate': 8.426167720881284e-05, 'epoch': 8.86}

 74%|███████▍  | 20745/28080 [40:59:57<14:30:06,  7.12s/it]
 74%|███████▍  | 20746/28080 [41:00:04<14:31:37,  7.13s/it]
                                                           
{'loss': 0.617, 'learning_rate': 8.424009014870294e-05, 'epoch': 8.86}

 74%|███████▍  | 20746/28080 [41:00:04<14:31:37,  7.13s/it]
 74%|███████▍  | 20747/28080 [41:00:11<14:31:02,  7.13s/it]
                                                           
{'loss': 0.6277, 'learning_rate': 8.421850529385774e-05, 'epoch': 8.86}

 74%|███████▍  | 20747/28080 [41:00:11<14:31:02,  7.13s/it]
 74%|███████▍  | 20748/28080 [41:00:18<14:28:32,  7.11s/it]
                                                           
{'loss': 0.6102, 'learning_rate': 8.419692264456419e-05, 'epoch': 8.86}

 74%|███████▍  | 20748/28080 [41:00:18<14:28:32,  7.11s/it]
 74%|███████▍  | 20749/28080 [41:00:25<14:25:08,  7.08s/it]
                                                           
{'loss': 0.6145, 'learning_rate': 8.417534220110958e-05, 'epoch': 8.86}

 74%|███████▍  | 20749/28080 [41:00:25<14:25:08,  7.08s/it]
 74%|███████▍  | 20750/28080 [41:00:32<14:27:05,  7.10s/it]
                                                           
{'loss': 0.599, 'learning_rate': 8.415376396378091e-05, 'epoch': 8.86}

 74%|███████▍  | 20750/28080 [41:00:32<14:27:05,  7.10s/it]
 74%|███████▍  | 20751/28080 [41:00:40<14:26:59,  7.10s/it]
                                                           
{'loss': 0.6032, 'learning_rate': 8.41321879328654e-05, 'epoch': 8.86}

 74%|███████▍  | 20751/28080 [41:00:40<14:26:59,  7.10s/it]
 74%|███████▍  | 20752/28080 [41:00:47<14:23:49,  7.07s/it]
                                                           
{'loss': 0.6305, 'learning_rate': 8.411061410865e-05, 'epoch': 8.87}

 74%|███████▍  | 20752/28080 [41:00:47<14:23:49,  7.07s/it]
 74%|███████▍  | 20753/28080 [41:00:54<14:24:57,  7.08s/it]
                                                           
{'loss': 0.6109, 'learning_rate': 8.408904249142175e-05, 'epoch': 8.87}

 74%|███████▍  | 20753/28080 [41:00:54<14:24:57,  7.08s/it]
 74%|███████▍  | 20754/28080 [41:01:01<14:19:23,  7.04s/it]
                                                           
{'loss': 0.6229, 'learning_rate': 8.406747308146756e-05, 'epoch': 8.87}

 74%|███████▍  | 20754/28080 [41:01:01<14:19:23,  7.04s/it]
 74%|███████▍  | 20755/28080 [41:01:08<14:20:56,  7.05s/it]
                                                           
{'loss': 0.6304, 'learning_rate': 8.404590587907451e-05, 'epoch': 8.87}

 74%|███████▍  | 20755/28080 [41:01:08<14:20:56,  7.05s/it]
 74%|███████▍  | 20756/28080 [41:01:15<14:15:57,  7.01s/it]
                                                           
{'loss': 0.6135, 'learning_rate': 8.402434088452949e-05, 'epoch': 8.87}

 74%|███████▍  | 20756/28080 [41:01:15<14:15:57,  7.01s/it]
 74%|███████▍  | 20757/28080 [41:01:22<14:17:20,  7.02s/it]
                                                           
{'loss': 0.6241, 'learning_rate': 8.40027780981194e-05, 'epoch': 8.87}

 74%|███████▍  | 20757/28080 [41:01:22<14:17:20,  7.02s/it]
 74%|███████▍  | 20758/28080 [41:01:29<14:20:48,  7.05s/it]
                                                           
{'loss': 0.6016, 'learning_rate': 8.3981217520131e-05, 'epoch': 8.87}

 74%|███████▍  | 20758/28080 [41:01:29<14:20:48,  7.05s/it]
 74%|███████▍  | 20759/28080 [41:01:36<14:21:31,  7.06s/it]
                                                           
{'loss': 0.6125, 'learning_rate': 8.395965915085129e-05, 'epoch': 8.87}

 74%|███████▍  | 20759/28080 [41:01:36<14:21:31,  7.06s/it]
 74%|███████▍  | 20760/28080 [41:01:43<14:23:38,  7.08s/it]
                                                           
{'loss': 0.6113, 'learning_rate': 8.393810299056698e-05, 'epoch': 8.87}

 74%|███████▍  | 20760/28080 [41:01:43<14:23:38,  7.08s/it]
 74%|███████▍  | 20761/28080 [41:01:50<14:21:50,  7.07s/it]
                                                           
{'loss': 0.5908, 'learning_rate': 8.391654903956506e-05, 'epoch': 8.87}

 74%|███████▍  | 20761/28080 [41:01:50<14:21:50,  7.07s/it]
 74%|███████▍  | 20762/28080 [41:01:57<14:19:02,  7.04s/it]
                                                           
{'loss': 0.6058, 'learning_rate': 8.389499729813192e-05, 'epoch': 8.87}

 74%|███████▍  | 20762/28080 [41:01:57<14:19:02,  7.04s/it]
 74%|███████▍  | 20763/28080 [41:02:04<14:21:42,  7.07s/it]
                                                           
{'loss': 0.6021, 'learning_rate': 8.387344776655456e-05, 'epoch': 8.87}

 74%|███████▍  | 20763/28080 [41:02:04<14:21:42,  7.07s/it]
 74%|███████▍  | 20764/28080 [41:02:11<14:23:08,  7.08s/it]
                                                           
{'loss': 0.6141, 'learning_rate': 8.385190044511953e-05, 'epoch': 8.87}

 74%|███████▍  | 20764/28080 [41:02:11<14:23:08,  7.08s/it]
 74%|███████▍  | 20765/28080 [41:02:18<14:20:10,  7.06s/it]
                                                           
{'loss': 0.6056, 'learning_rate': 8.383035533411366e-05, 'epoch': 8.87}

 74%|███████▍  | 20765/28080 [41:02:18<14:20:10,  7.06s/it]
 74%|███████▍  | 20766/28080 [41:02:25<14:24:57,  7.10s/it]
                                                           
{'loss': 0.5999, 'learning_rate': 8.380881243382343e-05, 'epoch': 8.87}

 74%|███████▍  | 20766/28080 [41:02:25<14:24:57,  7.10s/it]
 74%|███████▍  | 20767/28080 [41:02:32<14:17:46,  7.04s/it]
                                                           
{'loss': 0.6259, 'learning_rate': 8.378727174453554e-05, 'epoch': 8.87}

 74%|███████▍  | 20767/28080 [41:02:32<14:17:46,  7.04s/it]
 74%|███████▍  | 20768/28080 [41:02:40<14:21:49,  7.07s/it]
                                                           
{'loss': 0.6003, 'learning_rate': 8.376573326653653e-05, 'epoch': 8.87}

 74%|███████▍  | 20768/28080 [41:02:40<14:21:49,  7.07s/it]
 74%|███████▍  | 20769/28080 [41:02:47<14:21:07,  7.07s/it]
                                                           
{'loss': 0.6014, 'learning_rate': 8.374419700011285e-05, 'epoch': 8.87}

 74%|███████▍  | 20769/28080 [41:02:47<14:21:07,  7.07s/it]
 74%|███████▍  | 20770/28080 [41:02:54<14:24:06,  7.09s/it]
                                                           
{'loss': 0.6025, 'learning_rate': 8.37226629455512e-05, 'epoch': 8.87}

 74%|███████▍  | 20770/28080 [41:02:54<14:24:06,  7.09s/it]
 74%|███████▍  | 20771/28080 [41:03:01<14:26:50,  7.12s/it]
                                                           
{'loss': 0.5837, 'learning_rate': 8.370113110313798e-05, 'epoch': 8.87}

 74%|███████▍  | 20771/28080 [41:03:01<14:26:50,  7.12s/it]
 74%|███████▍  | 20772/28080 [41:03:08<14:19:56,  7.06s/it]
                                                           
{'loss': 0.6137, 'learning_rate': 8.367960147315965e-05, 'epoch': 8.87}

 74%|███████▍  | 20772/28080 [41:03:08<14:19:56,  7.06s/it]
 74%|███████▍  | 20773/28080 [41:03:15<14:17:39,  7.04s/it]
                                                           
{'loss': 0.6169, 'learning_rate': 8.365807405590256e-05, 'epoch': 8.87}

 74%|███████▍  | 20773/28080 [41:03:15<14:17:39,  7.04s/it]
 74%|███████▍  | 20774/28080 [41:03:22<14:17:49,  7.04s/it]
                                                           
{'loss': 0.6041, 'learning_rate': 8.363654885165325e-05, 'epoch': 8.87}

 74%|███████▍  | 20774/28080 [41:03:22<14:17:49,  7.04s/it]
 74%|███████▍  | 20775/28080 [41:03:29<14:18:19,  7.05s/it]
                                                           
{'loss': 0.5911, 'learning_rate': 8.361502586069806e-05, 'epoch': 8.87}

 74%|███████▍  | 20775/28080 [41:03:29<14:18:19,  7.05s/it]
 74%|███████▍  | 20776/28080 [41:03:36<14:22:17,  7.08s/it]
                                                           
{'loss': 0.617, 'learning_rate': 8.359350508332328e-05, 'epoch': 8.88}

 74%|███████▍  | 20776/28080 [41:03:36<14:22:17,  7.08s/it]
 74%|███████▍  | 20777/28080 [41:03:43<14:20:37,  7.07s/it]
                                                           
{'loss': 0.5985, 'learning_rate': 8.357198651981516e-05, 'epoch': 8.88}

 74%|███████▍  | 20777/28080 [41:03:43<14:20:37,  7.07s/it]
 74%|███████▍  | 20778/28080 [41:03:50<14:22:51,  7.09s/it]
                                                           
{'loss': 0.591, 'learning_rate': 8.355047017046017e-05, 'epoch': 8.88}

 74%|███████▍  | 20778/28080 [41:03:50<14:22:51,  7.09s/it]
 74%|███████▍  | 20779/28080 [41:03:57<14:24:03,  7.10s/it]
                                                           
{'loss': 0.5971, 'learning_rate': 8.352895603554437e-05, 'epoch': 8.88}

 74%|███████▍  | 20779/28080 [41:03:57<14:24:03,  7.10s/it]
 74%|███████▍  | 20780/28080 [41:04:04<14:19:55,  7.07s/it]
                                                           
{'loss': 0.6001, 'learning_rate': 8.350744411535414e-05, 'epoch': 8.88}

 74%|███████▍  | 20780/28080 [41:04:04<14:19:55,  7.07s/it]
 74%|███████▍  | 20781/28080 [41:04:12<14:22:55,  7.09s/it]
                                                           
{'loss': 0.6028, 'learning_rate': 8.34859344101756e-05, 'epoch': 8.88}

 74%|███████▍  | 20781/28080 [41:04:12<14:22:55,  7.09s/it]
 74%|███████▍  | 20782/28080 [41:04:19<14:19:56,  7.07s/it]
                                                           
{'loss': 0.6144, 'learning_rate': 8.346442692029493e-05, 'epoch': 8.88}

 74%|███████▍  | 20782/28080 [41:04:19<14:19:56,  7.07s/it]
 74%|███████▍  | 20783/28080 [41:04:26<14:22:28,  7.09s/it]
                                                           
{'loss': 0.6279, 'learning_rate': 8.344292164599817e-05, 'epoch': 8.88}

 74%|███████▍  | 20783/28080 [41:04:26<14:22:28,  7.09s/it]
 74%|███████▍  | 20784/28080 [41:04:33<14:23:56,  7.10s/it]
                                                           
{'loss': 0.6038, 'learning_rate': 8.34214185875716e-05, 'epoch': 8.88}

 74%|███████▍  | 20784/28080 [41:04:33<14:23:56,  7.10s/it]
 74%|███████▍  | 20785/28080 [41:04:40<14:24:43,  7.11s/it]
                                                           
{'loss': 0.6377, 'learning_rate': 8.33999177453012e-05, 'epoch': 8.88}

 74%|███████▍  | 20785/28080 [41:04:40<14:24:43,  7.11s/it]
 74%|███████▍  | 20786/28080 [41:04:47<14:22:54,  7.10s/it]
                                                           
{'loss': 0.6099, 'learning_rate': 8.3378419119473e-05, 'epoch': 8.88}

 74%|███████▍  | 20786/28080 [41:04:47<14:22:54,  7.10s/it]
 74%|███████▍  | 20787/28080 [41:04:54<14:20:39,  7.08s/it]
                                                           
{'loss': 0.598, 'learning_rate': 8.335692271037299e-05, 'epoch': 8.88}

 74%|███████▍  | 20787/28080 [41:04:54<14:20:39,  7.08s/it]
 74%|███████▍  | 20788/28080 [41:05:01<14:22:21,  7.10s/it]
                                                           
{'loss': 0.6043, 'learning_rate': 8.333542851828729e-05, 'epoch': 8.88}

 74%|███████▍  | 20788/28080 [41:05:01<14:22:21,  7.10s/it]
 74%|███████▍  | 20789/28080 [41:05:08<14:22:49,  7.10s/it]
                                                           
{'loss': 0.5748, 'learning_rate': 8.331393654350167e-05, 'epoch': 8.88}

 74%|███████▍  | 20789/28080 [41:05:08<14:22:49,  7.10s/it]
 74%|███████▍  | 20790/28080 [41:05:15<14:23:59,  7.11s/it]
                                                           
{'loss': 0.6174, 'learning_rate': 8.329244678630235e-05, 'epoch': 8.88}

 74%|███████▍  | 20790/28080 [41:05:15<14:23:59,  7.11s/it]
 74%|███████▍  | 20791/28080 [41:05:22<14:20:16,  7.08s/it]
                                                           
{'loss': 0.6005, 'learning_rate': 8.327095924697495e-05, 'epoch': 8.88}

 74%|███████▍  | 20791/28080 [41:05:22<14:20:16,  7.08s/it]
 74%|███████▍  | 20792/28080 [41:05:29<14:15:40,  7.04s/it]
                                                           
{'loss': 0.6204, 'learning_rate': 8.324947392580534e-05, 'epoch': 8.88}

 74%|███████▍  | 20792/28080 [41:05:29<14:15:40,  7.04s/it]
 74%|███████▍  | 20793/28080 [41:05:36<14:13:46,  7.03s/it]
                                                           
{'loss': 0.6133, 'learning_rate': 8.322799082307956e-05, 'epoch': 8.88}

 74%|███████▍  | 20793/28080 [41:05:36<14:13:46,  7.03s/it]
 74%|███████▍  | 20794/28080 [41:05:43<14:15:35,  7.05s/it]
                                                           
{'loss': 0.6149, 'learning_rate': 8.320650993908322e-05, 'epoch': 8.88}

 74%|███████▍  | 20794/28080 [41:05:43<14:15:35,  7.05s/it]
 74%|███████▍  | 20795/28080 [41:05:51<14:18:53,  7.07s/it]
                                                           
{'loss': 0.6093, 'learning_rate': 8.318503127410235e-05, 'epoch': 8.88}

 74%|███████▍  | 20795/28080 [41:05:51<14:18:53,  7.07s/it]
 74%|███████▍  | 20796/28080 [41:05:58<14:19:14,  7.08s/it]
                                                           
{'loss': 0.5892, 'learning_rate': 8.316355482842239e-05, 'epoch': 8.88}

 74%|███████▍  | 20796/28080 [41:05:58<14:19:14,  7.08s/it]
 74%|███████▍  | 20797/28080 [41:06:05<14:19:41,  7.08s/it]
                                                           
{'loss': 0.6086, 'learning_rate': 8.314208060232928e-05, 'epoch': 8.88}

 74%|███████▍  | 20797/28080 [41:06:05<14:19:41,  7.08s/it]
 74%|███████▍  | 20798/28080 [41:06:12<14:18:37,  7.07s/it]
                                                           
{'loss': 0.5963, 'learning_rate': 8.31206085961086e-05, 'epoch': 8.88}

 74%|███████▍  | 20798/28080 [41:06:12<14:18:37,  7.07s/it]
 74%|███████▍  | 20799/28080 [41:06:19<14:18:47,  7.08s/it]
                                                           
{'loss': 0.6147, 'learning_rate': 8.309913881004614e-05, 'epoch': 8.89}

 74%|███████▍  | 20799/28080 [41:06:19<14:18:47,  7.08s/it]
 74%|███████▍  | 20800/28080 [41:06:26<14:21:55,  7.10s/it]
                                                           
{'loss': 0.6064, 'learning_rate': 8.307767124442741e-05, 'epoch': 8.89}

 74%|███████▍  | 20800/28080 [41:06:26<14:21:55,  7.10s/it]
 74%|███████▍  | 20801/28080 [41:06:33<14:23:36,  7.12s/it]
                                                           
{'loss': 0.5942, 'learning_rate': 8.30562058995381e-05, 'epoch': 8.89}

 74%|███████▍  | 20801/28080 [41:06:33<14:23:36,  7.12s/it]
 74%|███████▍  | 20802/28080 [41:06:40<14:22:07,  7.11s/it]
                                                           
{'loss': 0.6111, 'learning_rate': 8.303474277566367e-05, 'epoch': 8.89}

 74%|███████▍  | 20802/28080 [41:06:40<14:22:07,  7.11s/it]
 74%|███████▍  | 20803/28080 [41:06:47<14:23:12,  7.12s/it]
                                                           
{'loss': 0.5845, 'learning_rate': 8.301328187308982e-05, 'epoch': 8.89}

 74%|███████▍  | 20803/28080 [41:06:47<14:23:12,  7.12s/it]
 74%|███████▍  | 20804/28080 [41:06:55<14:23:07,  7.12s/it]
                                                           
{'loss': 0.6, 'learning_rate': 8.299182319210197e-05, 'epoch': 8.89}

 74%|███████▍  | 20804/28080 [41:06:55<14:23:07,  7.12s/it]
 74%|███████▍  | 20805/28080 [41:07:02<14:22:42,  7.12s/it]
                                                           
{'loss': 0.6102, 'learning_rate': 8.297036673298561e-05, 'epoch': 8.89}

 74%|███████▍  | 20805/28080 [41:07:02<14:22:42,  7.12s/it]
 74%|███████▍  | 20806/28080 [41:07:09<14:20:15,  7.10s/it]
                                                           
{'loss': 0.613, 'learning_rate': 8.294891249602612e-05, 'epoch': 8.89}

 74%|███████▍  | 20806/28080 [41:07:09<14:20:15,  7.10s/it]
 74%|███████▍  | 20807/28080 [41:07:16<14:19:29,  7.09s/it]
                                                           
{'loss': 0.6123, 'learning_rate': 8.292746048150913e-05, 'epoch': 8.89}

 74%|███████▍  | 20807/28080 [41:07:16<14:19:29,  7.09s/it]
 74%|███████▍  | 20808/28080 [41:07:23<14:20:33,  7.10s/it]
                                                           
{'loss': 0.6046, 'learning_rate': 8.290601068971982e-05, 'epoch': 8.89}

 74%|███████▍  | 20808/28080 [41:07:23<14:20:33,  7.10s/it]
 74%|███████▍  | 20809/28080 [41:07:30<14:21:36,  7.11s/it]
                                                           
{'loss': 0.6117, 'learning_rate': 8.288456312094381e-05, 'epoch': 8.89}

 74%|███████▍  | 20809/28080 [41:07:30<14:21:36,  7.11s/it]
 74%|███████▍  | 20810/28080 [41:07:37<14:17:31,  7.08s/it]
                                                           
{'loss': 0.5893, 'learning_rate': 8.286311777546612e-05, 'epoch': 8.89}

 74%|███████▍  | 20810/28080 [41:07:37<14:17:31,  7.08s/it]
 74%|███████▍  | 20811/28080 [41:07:44<14:15:09,  7.06s/it]
                                                           
{'loss': 0.6232, 'learning_rate': 8.284167465357231e-05, 'epoch': 8.89}

 74%|███████▍  | 20811/28080 [41:07:44<14:15:09,  7.06s/it]
 74%|███████▍  | 20812/28080 [41:07:51<14:20:06,  7.10s/it]
                                                           
{'loss': 0.6121, 'learning_rate': 8.282023375554751e-05, 'epoch': 8.89}

 74%|███████▍  | 20812/28080 [41:07:51<14:20:06,  7.10s/it]
 74%|███████▍  | 20813/28080 [41:07:58<14:20:09,  7.10s/it]
                                                           
{'loss': 0.607, 'learning_rate': 8.27987950816771e-05, 'epoch': 8.89}

 74%|███████▍  | 20813/28080 [41:07:58<14:20:09,  7.10s/it]
 74%|███████▍  | 20814/28080 [41:08:05<14:18:22,  7.09s/it]
                                                           
{'loss': 0.6078, 'learning_rate': 8.27773586322462e-05, 'epoch': 8.89}

 74%|███████▍  | 20814/28080 [41:08:05<14:18:22,  7.09s/it]
 74%|███████▍  | 20815/28080 [41:08:12<14:15:32,  7.07s/it]
                                                           
{'loss': 0.614, 'learning_rate': 8.275592440754007e-05, 'epoch': 8.89}

 74%|███████▍  | 20815/28080 [41:08:12<14:15:32,  7.07s/it]
 74%|███████▍  | 20816/28080 [41:08:20<14:14:53,  7.06s/it]
                                                           
{'loss': 0.6025, 'learning_rate': 8.273449240784381e-05, 'epoch': 8.89}

 74%|███████▍  | 20816/28080 [41:08:20<14:14:53,  7.06s/it]
 74%|███████▍  | 20817/28080 [41:08:27<14:18:50,  7.09s/it]
                                                           
{'loss': 0.6187, 'learning_rate': 8.271306263344246e-05, 'epoch': 8.89}

 74%|███████▍  | 20817/28080 [41:08:27<14:18:50,  7.09s/it]
 74%|███████▍  | 20818/28080 [41:08:34<14:19:14,  7.10s/it]
                                                           
{'loss': 0.6173, 'learning_rate': 8.269163508462135e-05, 'epoch': 8.89}

 74%|███████▍  | 20818/28080 [41:08:34<14:19:14,  7.10s/it]
 74%|███████▍  | 20819/28080 [41:08:41<14:16:31,  7.08s/it]
                                                           
{'loss': 0.6241, 'learning_rate': 8.267020976166545e-05, 'epoch': 8.89}

 74%|███████▍  | 20819/28080 [41:08:41<14:16:31,  7.08s/it]
 74%|███████▍  | 20820/28080 [41:08:48<14:18:31,  7.10s/it]
                                                           
{'loss': 0.5993, 'learning_rate': 8.264878666485976e-05, 'epoch': 8.89}

 74%|███████▍  | 20820/28080 [41:08:48<14:18:31,  7.10s/it]
 74%|███████▍  | 20821/28080 [41:08:55<14:17:51,  7.09s/it]
                                                           
{'loss': 0.61, 'learning_rate': 8.262736579448923e-05, 'epoch': 8.89}

 74%|███████▍  | 20821/28080 [41:08:55<14:17:51,  7.09s/it]
 74%|███████▍  | 20822/28080 [41:09:02<14:17:11,  7.09s/it]
                                                           
{'loss': 0.6077, 'learning_rate': 8.2605947150839e-05, 'epoch': 8.89}

 74%|███████▍  | 20822/28080 [41:09:02<14:17:11,  7.09s/it]
 74%|███████▍  | 20823/28080 [41:09:09<14:21:00,  7.12s/it]
                                                           
{'loss': 0.6193, 'learning_rate': 8.258453073419397e-05, 'epoch': 8.9}

 74%|███████▍  | 20823/28080 [41:09:09<14:21:00,  7.12s/it]
 74%|███████▍  | 20824/28080 [41:09:17<14:24:56,  7.15s/it]
                                                           
{'loss': 0.6031, 'learning_rate': 8.256311654483906e-05, 'epoch': 8.9}

 74%|███████▍  | 20824/28080 [41:09:17<14:24:56,  7.15s/it]
 74%|███████▍  | 20825/28080 [41:09:24<14:21:22,  7.12s/it]
                                                           
{'loss': 0.6169, 'learning_rate': 8.254170458305905e-05, 'epoch': 8.9}

 74%|███████▍  | 20825/28080 [41:09:24<14:21:22,  7.12s/it]
 74%|███████▍  | 20826/28080 [41:09:31<14:22:08,  7.13s/it]
                                                           
{'loss': 0.6077, 'learning_rate': 8.252029484913898e-05, 'epoch': 8.9}

 74%|███████▍  | 20826/28080 [41:09:31<14:22:08,  7.13s/it]
 74%|███████▍  | 20827/28080 [41:09:38<14:20:07,  7.12s/it]
                                                           
{'loss': 0.6027, 'learning_rate': 8.249888734336352e-05, 'epoch': 8.9}

 74%|███████▍  | 20827/28080 [41:09:38<14:20:07,  7.12s/it]
 74%|███████▍  | 20828/28080 [41:09:45<14:17:31,  7.09s/it]
                                                           
{'loss': 0.6051, 'learning_rate': 8.247748206601768e-05, 'epoch': 8.9}

 74%|███████▍  | 20828/28080 [41:09:45<14:17:31,  7.09s/it]
 74%|███████▍  | 20829/28080 [41:09:52<14:17:23,  7.09s/it]
                                                           
{'loss': 0.601, 'learning_rate': 8.245607901738608e-05, 'epoch': 8.9}

 74%|███████▍  | 20829/28080 [41:09:52<14:17:23,  7.09s/it]
 74%|███████▍  | 20830/28080 [41:09:59<14:17:09,  7.09s/it]
                                                           
{'loss': 0.615, 'learning_rate': 8.243467819775352e-05, 'epoch': 8.9}

 74%|███████▍  | 20830/28080 [41:09:59<14:17:09,  7.09s/it]
 74%|███████▍  | 20831/28080 [41:10:06<14:14:54,  7.08s/it]
                                                           
{'loss': 0.6143, 'learning_rate': 8.241327960740464e-05, 'epoch': 8.9}

 74%|███████▍  | 20831/28080 [41:10:06<14:14:54,  7.08s/it]
 74%|███████▍  | 20832/28080 [41:10:13<14:15:06,  7.08s/it]
                                                           
{'loss': 0.5862, 'learning_rate': 8.239188324662423e-05, 'epoch': 8.9}

 74%|███████▍  | 20832/28080 [41:10:13<14:15:06,  7.08s/it]
 74%|███████▍  | 20833/28080 [41:10:20<14:11:56,  7.05s/it]
                                                           
{'loss': 0.6184, 'learning_rate': 8.237048911569692e-05, 'epoch': 8.9}

 74%|███████▍  | 20833/28080 [41:10:20<14:11:56,  7.05s/it]
 74%|███████▍  | 20834/28080 [41:10:27<14:12:55,  7.06s/it]
                                                           
{'loss': 0.6026, 'learning_rate': 8.23490972149073e-05, 'epoch': 8.9}

 74%|███████▍  | 20834/28080 [41:10:27<14:12:55,  7.06s/it]
 74%|███████▍  | 20835/28080 [41:10:34<14:14:58,  7.08s/it]
                                                           
{'loss': 0.6148, 'learning_rate': 8.232770754453991e-05, 'epoch': 8.9}

 74%|███████▍  | 20835/28080 [41:10:34<14:14:58,  7.08s/it]
 74%|███████▍  | 20836/28080 [41:10:42<14:23:01,  7.15s/it]
                                                           
{'loss': 0.6022, 'learning_rate': 8.230632010487949e-05, 'epoch': 8.9}

 74%|███████▍  | 20836/28080 [41:10:42<14:23:01,  7.15s/it]
 74%|███████▍  | 20837/28080 [41:10:49<14:18:06,  7.11s/it]
                                                           
{'loss': 0.5896, 'learning_rate': 8.228493489621047e-05, 'epoch': 8.9}

 74%|███████▍  | 20837/28080 [41:10:49<14:18:06,  7.11s/it]
 74%|███████▍  | 20838/28080 [41:10:56<14:11:13,  7.05s/it]
                                                           
{'loss': 0.627, 'learning_rate': 8.226355191881738e-05, 'epoch': 8.9}

 74%|███████▍  | 20838/28080 [41:10:56<14:11:13,  7.05s/it]
 74%|███████▍  | 20839/28080 [41:11:03<14:12:30,  7.06s/it]
                                                           
{'loss': 0.601, 'learning_rate': 8.22421711729846e-05, 'epoch': 8.9}

 74%|███████▍  | 20839/28080 [41:11:03<14:12:30,  7.06s/it]
 74%|███████▍  | 20840/28080 [41:11:10<14:18:37,  7.12s/it]
                                                           
{'loss': 0.5933, 'learning_rate': 8.222079265899673e-05, 'epoch': 8.9}

 74%|███████▍  | 20840/28080 [41:11:10<14:18:37,  7.12s/it]
 74%|███████▍  | 20841/28080 [41:11:17<14:20:04,  7.13s/it]
                                                           
{'loss': 0.6126, 'learning_rate': 8.219941637713815e-05, 'epoch': 8.9}

 74%|███████▍  | 20841/28080 [41:11:17<14:20:04,  7.13s/it]
 74%|███████▍  | 20842/28080 [41:11:24<14:19:32,  7.13s/it]
                                                           
{'loss': 0.6102, 'learning_rate': 8.217804232769313e-05, 'epoch': 8.9}

 74%|███████▍  | 20842/28080 [41:11:24<14:19:32,  7.13s/it]
 74%|███████▍  | 20843/28080 [41:11:31<14:15:44,  7.09s/it]
                                                           
{'loss': 0.6183, 'learning_rate': 8.21566705109463e-05, 'epoch': 8.9}

 74%|███████▍  | 20843/28080 [41:11:31<14:15:44,  7.09s/it]
 74%|███████▍  | 20844/28080 [41:11:38<14:14:05,  7.08s/it]
                                                           
{'loss': 0.6134, 'learning_rate': 8.213530092718166e-05, 'epoch': 8.9}

 74%|███████▍  | 20844/28080 [41:11:38<14:14:05,  7.08s/it]
 74%|███████▍  | 20845/28080 [41:11:45<14:12:30,  7.07s/it]
                                                           
{'loss': 0.5999, 'learning_rate': 8.211393357668372e-05, 'epoch': 8.9}

 74%|███████▍  | 20845/28080 [41:11:45<14:12:30,  7.07s/it]
 74%|███████▍  | 20846/28080 [41:11:53<14:16:43,  7.11s/it]
                                                           
{'loss': 0.5905, 'learning_rate': 8.209256845973661e-05, 'epoch': 8.91}

 74%|███████▍  | 20846/28080 [41:11:53<14:16:43,  7.11s/it]
 74%|███████▍  | 20847/28080 [41:12:00<14:18:16,  7.12s/it]
                                                           
{'loss': 0.5943, 'learning_rate': 8.207120557662475e-05, 'epoch': 8.91}

 74%|███████▍  | 20847/28080 [41:12:00<14:18:16,  7.12s/it]
 74%|███████▍  | 20848/28080 [41:12:07<14:16:59,  7.11s/it]
                                                           
{'loss': 0.6074, 'learning_rate': 8.204984492763227e-05, 'epoch': 8.91}

 74%|███████▍  | 20848/28080 [41:12:07<14:16:59,  7.11s/it]
 74%|███████▍  | 20849/28080 [41:12:14<14:12:56,  7.08s/it]
                                                           
{'loss': 0.6092, 'learning_rate': 8.202848651304335e-05, 'epoch': 8.91}

 74%|███████▍  | 20849/28080 [41:12:14<14:12:56,  7.08s/it]
 74%|███████▍  | 20850/28080 [41:12:21<14:13:35,  7.08s/it]
                                                           
{'loss': 0.5993, 'learning_rate': 8.2007130333142e-05, 'epoch': 8.91}

 74%|███████▍  | 20850/28080 [41:12:21<14:13:35,  7.08s/it]
 74%|███████▍  | 20851/28080 [41:12:28<14:13:44,  7.09s/it]
                                                           
{'loss': 0.597, 'learning_rate': 8.198577638821259e-05, 'epoch': 8.91}

 74%|███████▍  | 20851/28080 [41:12:28<14:13:44,  7.09s/it]
 74%|███████▍  | 20852/28080 [41:12:35<14:13:56,  7.09s/it]
                                                           
{'loss': 0.6006, 'learning_rate': 8.19644246785391e-05, 'epoch': 8.91}

 74%|███████▍  | 20852/28080 [41:12:35<14:13:56,  7.09s/it]
 74%|███████▍  | 20853/28080 [41:12:42<14:13:17,  7.08s/it]
                                                           
{'loss': 0.6187, 'learning_rate': 8.194307520440555e-05, 'epoch': 8.91}

 74%|███████▍  | 20853/28080 [41:12:42<14:13:17,  7.08s/it]
 74%|███████▍  | 20854/28080 [41:12:49<14:11:40,  7.07s/it]
                                                           
{'loss': 0.5985, 'learning_rate': 8.192172796609595e-05, 'epoch': 8.91}

 74%|███████▍  | 20854/28080 [41:12:49<14:11:40,  7.07s/it]
 74%|███████▍  | 20855/28080 [41:12:56<14:13:39,  7.09s/it]
                                                           
{'loss': 0.6205, 'learning_rate': 8.190038296389445e-05, 'epoch': 8.91}

 74%|███████▍  | 20855/28080 [41:12:56<14:13:39,  7.09s/it]
 74%|███████▍  | 20856/28080 [41:13:03<14:14:09,  7.09s/it]
                                                           
{'loss': 0.6222, 'learning_rate': 8.187904019808484e-05, 'epoch': 8.91}

 74%|███████▍  | 20856/28080 [41:13:03<14:14:09,  7.09s/it]
 74%|███████▍  | 20857/28080 [41:13:10<14:12:45,  7.08s/it]
                                                           
{'loss': 0.5922, 'learning_rate': 8.185769966895134e-05, 'epoch': 8.91}

 74%|███████▍  | 20857/28080 [41:13:10<14:12:45,  7.08s/it]
 74%|███████▍  | 20858/28080 [41:13:17<14:09:25,  7.06s/it]
                                                           
{'loss': 0.6135, 'learning_rate': 8.183636137677752e-05, 'epoch': 8.91}

 74%|███████▍  | 20858/28080 [41:13:17<14:09:25,  7.06s/it]
 74%|███████▍  | 20859/28080 [41:13:25<14:10:44,  7.07s/it]
                                                           
{'loss': 0.6089, 'learning_rate': 8.181502532184751e-05, 'epoch': 8.91}

 74%|███████▍  | 20859/28080 [41:13:25<14:10:44,  7.07s/it]
 74%|███████▍  | 20860/28080 [41:13:32<14:09:08,  7.06s/it]
                                                           
{'loss': 0.6045, 'learning_rate': 8.1793691504445e-05, 'epoch': 8.91}

 74%|███████▍  | 20860/28080 [41:13:32<14:09:08,  7.06s/it]
 74%|███████▍  | 20861/28080 [41:13:39<14:11:22,  7.08s/it]
                                                           
{'loss': 0.6133, 'learning_rate': 8.177235992485393e-05, 'epoch': 8.91}

 74%|███████▍  | 20861/28080 [41:13:39<14:11:22,  7.08s/it]
 74%|███████▍  | 20862/28080 [41:13:46<14:11:17,  7.08s/it]
                                                           
{'loss': 0.6065, 'learning_rate': 8.175103058335812e-05, 'epoch': 8.91}

 74%|███████▍  | 20862/28080 [41:13:46<14:11:17,  7.08s/it]
 74%|███████▍  | 20863/28080 [41:13:53<14:09:43,  7.06s/it]
                                                           
{'loss': 0.5911, 'learning_rate': 8.172970348024125e-05, 'epoch': 8.91}

 74%|███████▍  | 20863/28080 [41:13:53<14:09:43,  7.06s/it]
 74%|███████▍  | 20864/28080 [41:14:00<14:07:45,  7.05s/it]
                                                           
{'loss': 0.6098, 'learning_rate': 8.170837861578701e-05, 'epoch': 8.91}

 74%|███████▍  | 20864/28080 [41:14:00<14:07:45,  7.05s/it]
 74%|███████▍  | 20865/28080 [41:14:07<14:06:04,  7.04s/it]
                                                           
{'loss': 0.5902, 'learning_rate': 8.168705599027923e-05, 'epoch': 8.91}

 74%|███████▍  | 20865/28080 [41:14:07<14:06:04,  7.04s/it]
 74%|███████▍  | 20866/28080 [41:14:14<14:07:19,  7.05s/it]
                                                           
{'loss': 0.6142, 'learning_rate': 8.166573560400157e-05, 'epoch': 8.91}

 74%|███████▍  | 20866/28080 [41:14:14<14:07:19,  7.05s/it]
 74%|███████▍  | 20867/28080 [41:14:21<14:14:20,  7.11s/it]
                                                           
{'loss': 0.6007, 'learning_rate': 8.164441745723761e-05, 'epoch': 8.91}

 74%|███████▍  | 20867/28080 [41:14:21<14:14:20,  7.11s/it]
 74%|███████▍  | 20868/28080 [41:14:28<14:12:24,  7.09s/it]
                                                           
{'loss': 0.6185, 'learning_rate': 8.1623101550271e-05, 'epoch': 8.91}

 74%|███████▍  | 20868/28080 [41:14:28<14:12:24,  7.09s/it]
 74%|███████▍  | 20869/28080 [41:14:35<14:11:31,  7.09s/it]
                                                           
{'loss': 0.6175, 'learning_rate': 8.160178788338524e-05, 'epoch': 8.92}

 74%|███████▍  | 20869/28080 [41:14:35<14:11:31,  7.09s/it]
 74%|███████▍  | 20870/28080 [41:14:42<14:13:48,  7.11s/it]
                                                           
{'loss': 0.61, 'learning_rate': 8.158047645686404e-05, 'epoch': 8.92}

 74%|███████▍  | 20870/28080 [41:14:42<14:13:48,  7.11s/it]
 74%|███████▍  | 20871/28080 [41:14:50<14:16:21,  7.13s/it]
                                                           
{'loss': 0.6031, 'learning_rate': 8.155916727099086e-05, 'epoch': 8.92}

 74%|███████▍  | 20871/28080 [41:14:50<14:16:21,  7.13s/it]
 74%|███████▍  | 20872/28080 [41:14:57<14:17:00,  7.13s/it]
                                                           
{'loss': 0.5934, 'learning_rate': 8.153786032604917e-05, 'epoch': 8.92}

 74%|███████▍  | 20872/28080 [41:14:57<14:17:00,  7.13s/it]
 74%|███████▍  | 20873/28080 [41:15:04<14:13:35,  7.11s/it]
                                                           
{'loss': 0.6022, 'learning_rate': 8.151655562232241e-05, 'epoch': 8.92}

 74%|███████▍  | 20873/28080 [41:15:04<14:13:35,  7.11s/it]
 74%|███████▍  | 20874/28080 [41:15:11<14:12:30,  7.10s/it]
                                                           
{'loss': 0.6028, 'learning_rate': 8.149525316009413e-05, 'epoch': 8.92}

 74%|███████▍  | 20874/28080 [41:15:11<14:12:30,  7.10s/it]
 74%|███████▍  | 20875/28080 [41:15:18<14:09:52,  7.08s/it]
                                                           
{'loss': 0.6189, 'learning_rate': 8.147395293964757e-05, 'epoch': 8.92}

 74%|███████▍  | 20875/28080 [41:15:18<14:09:52,  7.08s/it]
 74%|███████▍  | 20876/28080 [41:15:25<14:06:10,  7.05s/it]
                                                           
{'loss': 0.5908, 'learning_rate': 8.14526549612664e-05, 'epoch': 8.92}

 74%|███████▍  | 20876/28080 [41:15:25<14:06:10,  7.05s/it]
 74%|███████▍  | 20877/28080 [41:15:32<14:06:49,  7.05s/it]
                                                           
{'loss': 0.5912, 'learning_rate': 8.143135922523357e-05, 'epoch': 8.92}

 74%|███████▍  | 20877/28080 [41:15:32<14:06:49,  7.05s/it]
 74%|███████▍  | 20878/28080 [41:15:39<14:10:25,  7.08s/it]
                                                           
{'loss': 0.5943, 'learning_rate': 8.14100657318327e-05, 'epoch': 8.92}

 74%|███████▍  | 20878/28080 [41:15:39<14:10:25,  7.08s/it]
 74%|███████▍  | 20879/28080 [41:15:46<14:11:26,  7.09s/it]
                                                           
{'loss': 0.5946, 'learning_rate': 8.138877448134691e-05, 'epoch': 8.92}

 74%|███████▍  | 20879/28080 [41:15:46<14:11:26,  7.09s/it]
 74%|███████▍  | 20880/28080 [41:15:53<14:10:52,  7.09s/it]
                                                           
{'loss': 0.6059, 'learning_rate': 8.136748547405962e-05, 'epoch': 8.92}

 74%|███████▍  | 20880/28080 [41:15:53<14:10:52,  7.09s/it]
 74%|███████▍  | 20881/28080 [41:16:01<14:13:13,  7.11s/it]
                                                           
{'loss': 0.5934, 'learning_rate': 8.134619871025394e-05, 'epoch': 8.92}

 74%|███████▍  | 20881/28080 [41:16:01<14:13:13,  7.11s/it]
 74%|███████▍  | 20882/28080 [41:16:08<14:12:52,  7.11s/it]
                                                           
{'loss': 0.6003, 'learning_rate': 8.132491419021312e-05, 'epoch': 8.92}

 74%|███████▍  | 20882/28080 [41:16:08<14:12:52,  7.11s/it]
 74%|███████▍  | 20883/28080 [41:16:15<14:13:04,  7.11s/it]
                                                           
{'loss': 0.6027, 'learning_rate': 8.130363191422021e-05, 'epoch': 8.92}

 74%|███████▍  | 20883/28080 [41:16:15<14:13:04,  7.11s/it]
 74%|███████▍  | 20884/28080 [41:16:22<14:14:04,  7.12s/it]
                                                           
{'loss': 0.602, 'learning_rate': 8.128235188255853e-05, 'epoch': 8.92}

 74%|███████▍  | 20884/28080 [41:16:22<14:14:04,  7.12s/it]
 74%|███████▍  | 20885/28080 [41:16:29<14:10:43,  7.09s/it]
                                                           
{'loss': 0.5961, 'learning_rate': 8.126107409551112e-05, 'epoch': 8.92}

 74%|███████▍  | 20885/28080 [41:16:29<14:10:43,  7.09s/it]
 74%|███████▍  | 20886/28080 [41:16:36<14:10:25,  7.09s/it]
                                                           
{'loss': 0.5929, 'learning_rate': 8.123979855336102e-05, 'epoch': 8.92}

 74%|███████▍  | 20886/28080 [41:16:36<14:10:25,  7.09s/it]
 74%|███████▍  | 20887/28080 [41:16:43<14:17:23,  7.15s/it]
                                                           
{'loss': 0.5947, 'learning_rate': 8.121852525639123e-05, 'epoch': 8.92}

 74%|███████▍  | 20887/28080 [41:16:43<14:17:23,  7.15s/it]
 74%|███████▍  | 20888/28080 [41:16:50<14:16:25,  7.14s/it]
                                                           
{'loss': 0.6177, 'learning_rate': 8.119725420488489e-05, 'epoch': 8.92}

 74%|███████▍  | 20888/28080 [41:16:50<14:16:25,  7.14s/it]
 74%|███████▍  | 20889/28080 [41:16:58<14:16:35,  7.15s/it]
                                                           
{'loss': 0.5904, 'learning_rate': 8.117598539912488e-05, 'epoch': 8.92}

 74%|███████▍  | 20889/28080 [41:16:58<14:16:35,  7.15s/it]
 74%|███████▍  | 20890/28080 [41:17:05<14:10:46,  7.10s/it]
                                                           
{'loss': 0.6015, 'learning_rate': 8.115471883939429e-05, 'epoch': 8.92}

 74%|███████▍  | 20890/28080 [41:17:05<14:10:46,  7.10s/it]
 74%|███████▍  | 20891/28080 [41:17:12<14:09:41,  7.09s/it]
                                                           
{'loss': 0.596, 'learning_rate': 8.113345452597609e-05, 'epoch': 8.92}

 74%|███████▍  | 20891/28080 [41:17:12<14:09:41,  7.09s/it]
 74%|███████▍  | 20892/28080 [41:17:19<14:08:56,  7.09s/it]
                                                           
{'loss': 0.5955, 'learning_rate': 8.111219245915288e-05, 'epoch': 8.92}

 74%|███████▍  | 20892/28080 [41:17:19<14:08:56,  7.09s/it]
 74%|███████▍  | 20893/28080 [41:17:26<14:11:32,  7.11s/it]
                                                           
{'loss': 0.6013, 'learning_rate': 8.10909326392078e-05, 'epoch': 8.93}

 74%|███████▍  | 20893/28080 [41:17:26<14:11:32,  7.11s/it]
 74%|███████▍  | 20894/28080 [41:17:33<14:09:14,  7.09s/it]
                                                           
{'loss': 0.6089, 'learning_rate': 8.106967506642352e-05, 'epoch': 8.93}

 74%|███████▍  | 20894/28080 [41:17:33<14:09:14,  7.09s/it]
 74%|███████▍  | 20895/28080 [41:17:40<14:11:04,  7.11s/it]
                                                           
{'loss': 0.6082, 'learning_rate': 8.104841974108304e-05, 'epoch': 8.93}

 74%|███████▍  | 20895/28080 [41:17:40<14:11:04,  7.11s/it]
 74%|███████▍  | 20896/28080 [41:17:47<14:16:49,  7.16s/it]
                                                           
{'loss': 0.5858, 'learning_rate': 8.102716666346902e-05, 'epoch': 8.93}

 74%|███████▍  | 20896/28080 [41:17:47<14:16:49,  7.16s/it]
 74%|███████▍  | 20897/28080 [41:17:54<14:13:24,  7.13s/it]
                                                           
{'loss': 0.5966, 'learning_rate': 8.100591583386422e-05, 'epoch': 8.93}

 74%|███████▍  | 20897/28080 [41:17:54<14:13:24,  7.13s/it]
 74%|███████▍  | 20898/28080 [41:18:01<14:10:48,  7.11s/it]
                                                           
{'loss': 0.6125, 'learning_rate': 8.09846672525513e-05, 'epoch': 8.93}

 74%|███████▍  | 20898/28080 [41:18:01<14:10:48,  7.11s/it]
 74%|███████▍  | 20899/28080 [41:18:08<14:08:19,  7.09s/it]
                                                           
{'loss': 0.6063, 'learning_rate': 8.09634209198131e-05, 'epoch': 8.93}

 74%|███████▍  | 20899/28080 [41:18:08<14:08:19,  7.09s/it]
 74%|███████▍  | 20900/28080 [41:18:15<14:01:53,  7.04s/it]
                                                           
{'loss': 0.627, 'learning_rate': 8.09421768359322e-05, 'epoch': 8.93}

 74%|███████▍  | 20900/28080 [41:18:15<14:01:53,  7.04s/it]
 74%|███████▍  | 20901/28080 [41:18:22<14:00:08,  7.02s/it]
                                                           
{'loss': 0.6018, 'learning_rate': 8.092093500119125e-05, 'epoch': 8.93}

 74%|███████▍  | 20901/28080 [41:18:22<14:00:08,  7.02s/it]
 74%|███████▍  | 20902/28080 [41:18:29<14:02:52,  7.05s/it]
                                                           
{'loss': 0.5974, 'learning_rate': 8.089969541587273e-05, 'epoch': 8.93}

 74%|███████▍  | 20902/28080 [41:18:29<14:02:52,  7.05s/it]
 74%|███████▍  | 20903/28080 [41:18:37<14:05:46,  7.07s/it]
                                                           
{'loss': 0.6157, 'learning_rate': 8.087845808025937e-05, 'epoch': 8.93}

 74%|███████▍  | 20903/28080 [41:18:37<14:05:46,  7.07s/it]
 74%|███████▍  | 20904/28080 [41:18:44<14:09:49,  7.11s/it]
                                                           
{'loss': 0.6123, 'learning_rate': 8.085722299463358e-05, 'epoch': 8.93}

 74%|███████▍  | 20904/28080 [41:18:44<14:09:49,  7.11s/it]
 74%|███████▍  | 20905/28080 [41:18:51<14:10:01,  7.11s/it]
                                                           
{'loss': 0.6076, 'learning_rate': 8.083599015927812e-05, 'epoch': 8.93}

 74%|███████▍  | 20905/28080 [41:18:51<14:10:01,  7.11s/it]
 74%|███████▍  | 20906/28080 [41:18:58<14:08:31,  7.10s/it]
                                                           
{'loss': 0.6209, 'learning_rate': 8.081475957447515e-05, 'epoch': 8.93}

 74%|███████▍  | 20906/28080 [41:18:58<14:08:31,  7.10s/it]
 74%|███████▍  | 20907/28080 [41:19:05<14:09:56,  7.11s/it]
                                                           
{'loss': 0.6098, 'learning_rate': 8.079353124050731e-05, 'epoch': 8.93}

 74%|███████▍  | 20907/28080 [41:19:05<14:09:56,  7.11s/it]
 74%|███████▍  | 20908/28080 [41:19:12<14:07:28,  7.09s/it]
                                                           
{'loss': 0.5994, 'learning_rate': 8.077230515765691e-05, 'epoch': 8.93}

 74%|███████▍  | 20908/28080 [41:19:12<14:07:28,  7.09s/it]
 74%|███████▍  | 20909/28080 [41:19:19<14:05:14,  7.07s/it]
                                                           
{'loss': 0.6153, 'learning_rate': 8.075108132620648e-05, 'epoch': 8.93}

 74%|███████▍  | 20909/28080 [41:19:19<14:05:14,  7.07s/it]
 74%|███████▍  | 20910/28080 [41:19:26<14:04:06,  7.06s/it]
                                                           
{'loss': 0.6327, 'learning_rate': 8.072985974643831e-05, 'epoch': 8.93}

 74%|███████▍  | 20910/28080 [41:19:26<14:04:06,  7.06s/it]
 74%|███████▍  | 20911/28080 [41:19:33<14:05:56,  7.08s/it]
                                                           
{'loss': 0.6077, 'learning_rate': 8.070864041863476e-05, 'epoch': 8.93}

 74%|███████▍  | 20911/28080 [41:19:33<14:05:56,  7.08s/it]
 74%|███████▍  | 20912/28080 [41:19:41<14:09:21,  7.11s/it]
                                                           
{'loss': 0.6188, 'learning_rate': 8.0687423343078e-05, 'epoch': 8.93}

 74%|███████▍  | 20912/28080 [41:19:41<14:09:21,  7.11s/it]
 74%|███████▍  | 20913/28080 [41:19:48<14:09:09,  7.11s/it]
                                                           
{'loss': 0.6096, 'learning_rate': 8.066620852005046e-05, 'epoch': 8.93}

 74%|███████▍  | 20913/28080 [41:19:48<14:09:09,  7.11s/it]
 74%|███████▍  | 20914/28080 [41:19:55<14:09:12,  7.11s/it]
                                                           
{'loss': 0.6145, 'learning_rate': 8.064499594983435e-05, 'epoch': 8.93}

 74%|███████▍  | 20914/28080 [41:19:55<14:09:12,  7.11s/it]
 74%|███████▍  | 20915/28080 [41:20:02<14:04:48,  7.07s/it]
                                                           
{'loss': 0.6092, 'learning_rate': 8.062378563271186e-05, 'epoch': 8.93}

 74%|███████▍  | 20915/28080 [41:20:02<14:04:48,  7.07s/it]
 74%|███████▍  | 20916/28080 [41:20:09<14:04:06,  7.07s/it]
                                                           
{'loss': 0.6054, 'learning_rate': 8.060257756896516e-05, 'epoch': 8.94}

 74%|███████▍  | 20916/28080 [41:20:09<14:04:06,  7.07s/it]
 74%|███████▍  | 20917/28080 [41:20:16<14:07:07,  7.10s/it]
                                                           
{'loss': 0.5903, 'learning_rate': 8.058137175887631e-05, 'epoch': 8.94}

 74%|███████▍  | 20917/28080 [41:20:16<14:07:07,  7.10s/it]
 74%|███████▍  | 20918/28080 [41:20:23<14:09:42,  7.12s/it]
                                                           
{'loss': 0.6032, 'learning_rate': 8.056016820272763e-05, 'epoch': 8.94}

 74%|███████▍  | 20918/28080 [41:20:23<14:09:42,  7.12s/it]
 74%|███████▍  | 20919/28080 [41:20:30<14:05:51,  7.09s/it]
                                                           
{'loss': 0.6143, 'learning_rate': 8.053896690080109e-05, 'epoch': 8.94}

 74%|███████▍  | 20919/28080 [41:20:30<14:05:51,  7.09s/it]
 75%|███████▍  | 20920/28080 [41:20:37<14:03:38,  7.07s/it]
                                                           
{'loss': 0.6109, 'learning_rate': 8.051776785337881e-05, 'epoch': 8.94}

 75%|███████▍  | 20920/28080 [41:20:37<14:03:38,  7.07s/it]
 75%|███████▍  | 20921/28080 [41:20:44<14:07:24,  7.10s/it]
                                                           
{'loss': 0.6258, 'learning_rate': 8.049657106074265e-05, 'epoch': 8.94}

 75%|███████▍  | 20921/28080 [41:20:44<14:07:24,  7.10s/it]
 75%|███████▍  | 20922/28080 [41:20:52<14:08:40,  7.11s/it]
                                                           
{'loss': 0.6219, 'learning_rate': 8.047537652317485e-05, 'epoch': 8.94}

 75%|███████▍  | 20922/28080 [41:20:52<14:08:40,  7.11s/it]
 75%|███████▍  | 20923/28080 [41:20:59<14:09:28,  7.12s/it]
                                                           
{'loss': 0.6144, 'learning_rate': 8.04541842409572e-05, 'epoch': 8.94}

 75%|███████▍  | 20923/28080 [41:20:59<14:09:28,  7.12s/it]
 75%|███████▍  | 20924/28080 [41:21:06<14:04:47,  7.08s/it]
                                                           
{'loss': 0.6184, 'learning_rate': 8.043299421437189e-05, 'epoch': 8.94}

 75%|███████▍  | 20924/28080 [41:21:06<14:04:47,  7.08s/it]
 75%|███████▍  | 20925/28080 [41:21:13<14:06:33,  7.10s/it]
                                                           
{'loss': 0.6158, 'learning_rate': 8.04118064437005e-05, 'epoch': 8.94}

 75%|███████▍  | 20925/28080 [41:21:13<14:06:33,  7.10s/it]
 75%|███████▍  | 20926/28080 [41:21:20<14:07:55,  7.11s/it]
                                                           
{'loss': 0.5796, 'learning_rate': 8.039062092922515e-05, 'epoch': 8.94}

 75%|███████▍  | 20926/28080 [41:21:20<14:07:55,  7.11s/it]
 75%|███████▍  | 20927/28080 [41:21:27<14:09:41,  7.13s/it]
                                                           
{'loss': 0.5925, 'learning_rate': 8.036943767122751e-05, 'epoch': 8.94}

 75%|███████▍  | 20927/28080 [41:21:27<14:09:41,  7.13s/it]
 75%|███████▍  | 20928/28080 [41:21:34<14:08:00,  7.11s/it]
                                                           
{'loss': 0.6206, 'learning_rate': 8.034825666998957e-05, 'epoch': 8.94}

 75%|███████▍  | 20928/28080 [41:21:34<14:08:00,  7.11s/it]
 75%|███████▍  | 20929/28080 [41:21:41<14:09:32,  7.13s/it]
                                                           
{'loss': 0.6174, 'learning_rate': 8.03270779257931e-05, 'epoch': 8.94}

 75%|███████▍  | 20929/28080 [41:21:41<14:09:32,  7.13s/it]
 75%|███████▍  | 20930/28080 [41:21:48<14:05:48,  7.10s/it]
                                                           
{'loss': 0.6034, 'learning_rate': 8.03059014389198e-05, 'epoch': 8.94}

 75%|███████▍  | 20930/28080 [41:21:48<14:05:48,  7.10s/it]
 75%|███████▍  | 20931/28080 [41:21:55<14:03:06,  7.08s/it]
                                                           
{'loss': 0.6152, 'learning_rate': 8.028472720965132e-05, 'epoch': 8.94}

 75%|███████▍  | 20931/28080 [41:21:55<14:03:06,  7.08s/it]
 75%|███████▍  | 20932/28080 [41:22:02<14:01:22,  7.06s/it]
                                                           
{'loss': 0.618, 'learning_rate': 8.026355523826956e-05, 'epoch': 8.94}

 75%|███████▍  | 20932/28080 [41:22:02<14:01:22,  7.06s/it]
 75%|███████▍  | 20933/28080 [41:22:09<14:00:08,  7.05s/it]
                                                           
{'loss': 0.6212, 'learning_rate': 8.024238552505609e-05, 'epoch': 8.94}

 75%|███████▍  | 20933/28080 [41:22:09<14:00:08,  7.05s/it]
 75%|███████▍  | 20934/28080 [41:22:17<14:04:24,  7.09s/it]
                                                           
{'loss': 0.6175, 'learning_rate': 8.022121807029254e-05, 'epoch': 8.94}

 75%|███████▍  | 20934/28080 [41:22:17<14:04:24,  7.09s/it]
 75%|███████▍  | 20935/28080 [41:22:24<14:11:40,  7.15s/it]
                                                           
{'loss': 0.6159, 'learning_rate': 8.020005287426044e-05, 'epoch': 8.94}

 75%|███████▍  | 20935/28080 [41:22:24<14:11:40,  7.15s/it]
 75%|███████▍  | 20936/28080 [41:22:31<14:09:37,  7.14s/it]
                                                           
{'loss': 0.6051, 'learning_rate': 8.017888993724157e-05, 'epoch': 8.94}

 75%|███████▍  | 20936/28080 [41:22:31<14:09:37,  7.14s/it]
 75%|███████▍  | 20937/28080 [41:22:38<14:10:56,  7.15s/it]
                                                           
{'loss': 0.5933, 'learning_rate': 8.015772925951729e-05, 'epoch': 8.94}

 75%|███████▍  | 20937/28080 [41:22:38<14:10:56,  7.15s/it]
 75%|███████▍  | 20938/28080 [41:22:45<14:08:25,  7.13s/it]
                                                           
{'loss': 0.5972, 'learning_rate': 8.013657084136935e-05, 'epoch': 8.94}

 75%|███████▍  | 20938/28080 [41:22:45<14:08:25,  7.13s/it]
 75%|███████▍  | 20939/28080 [41:22:52<14:04:43,  7.10s/it]
                                                           
{'loss': 0.6087, 'learning_rate': 8.011541468307895e-05, 'epoch': 8.94}

 75%|███████▍  | 20939/28080 [41:22:52<14:04:43,  7.10s/it]
 75%|███████▍  | 20940/28080 [41:22:59<14:04:43,  7.10s/it]
                                                           
{'loss': 0.6057, 'learning_rate': 8.009426078492779e-05, 'epoch': 8.95}

 75%|███████▍  | 20940/28080 [41:22:59<14:04:43,  7.10s/it]
 75%|███████▍  | 20941/28080 [41:23:06<14:01:56,  7.08s/it]
                                                           
{'loss': 0.6147, 'learning_rate': 8.007310914719717e-05, 'epoch': 8.95}

 75%|███████▍  | 20941/28080 [41:23:06<14:01:56,  7.08s/it]
 75%|███████▍  | 20942/28080 [41:23:13<13:59:28,  7.06s/it]
                                                           
{'loss': 0.5978, 'learning_rate': 8.005195977016849e-05, 'epoch': 8.95}

 75%|███████▍  | 20942/28080 [41:23:13<13:59:28,  7.06s/it]
 75%|███████▍  | 20943/28080 [41:23:21<14:00:00,  7.06s/it]
                                                           
{'loss': 0.6093, 'learning_rate': 8.003081265412321e-05, 'epoch': 8.95}

 75%|███████▍  | 20943/28080 [41:23:21<14:00:00,  7.06s/it]
 75%|███████▍  | 20944/28080 [41:23:28<13:58:51,  7.05s/it]
                                                           
{'loss': 0.6047, 'learning_rate': 8.000966779934262e-05, 'epoch': 8.95}

 75%|███████▍  | 20944/28080 [41:23:28<13:58:51,  7.05s/it]
 75%|███████▍  | 20945/28080 [41:23:35<14:03:58,  7.10s/it]
                                                           
{'loss': 0.5946, 'learning_rate': 7.998852520610805e-05, 'epoch': 8.95}

 75%|███████▍  | 20945/28080 [41:23:35<14:03:58,  7.10s/it]
 75%|███████▍  | 20946/28080 [41:23:42<14:07:00,  7.12s/it]
                                                           
{'loss': 0.6175, 'learning_rate': 7.996738487470067e-05, 'epoch': 8.95}

 75%|███████▍  | 20946/28080 [41:23:42<14:07:00,  7.12s/it]
 75%|███████▍  | 20947/28080 [41:23:49<14:05:42,  7.11s/it]
                                                           
{'loss': 0.589, 'learning_rate': 7.994624680540192e-05, 'epoch': 8.95}

 75%|███████▍  | 20947/28080 [41:23:49<14:05:42,  7.11s/it]
 75%|███████▍  | 20948/28080 [41:23:56<14:05:57,  7.12s/it]
                                                           
{'loss': 0.6058, 'learning_rate': 7.99251109984929e-05, 'epoch': 8.95}

 75%|███████▍  | 20948/28080 [41:23:56<14:05:57,  7.12s/it]
 75%|███████▍  | 20949/28080 [41:24:03<14:05:40,  7.12s/it]
                                                           
{'loss': 0.5935, 'learning_rate': 7.990397745425485e-05, 'epoch': 8.95}

 75%|███████▍  | 20949/28080 [41:24:03<14:05:40,  7.12s/it]
 75%|███████▍  | 20950/28080 [41:24:10<14:03:28,  7.10s/it]
                                                           
{'loss': 0.6086, 'learning_rate': 7.988284617296879e-05, 'epoch': 8.95}

 75%|███████▍  | 20950/28080 [41:24:10<14:03:28,  7.10s/it]
 75%|███████▍  | 20951/28080 [41:24:17<14:04:06,  7.10s/it]
                                                           
{'loss': 0.5981, 'learning_rate': 7.986171715491606e-05, 'epoch': 8.95}

 75%|███████▍  | 20951/28080 [41:24:17<14:04:06,  7.10s/it]
 75%|███████▍  | 20952/28080 [41:24:25<14:06:23,  7.12s/it]
                                                           
{'loss': 0.5958, 'learning_rate': 7.984059040037756e-05, 'epoch': 8.95}

 75%|███████▍  | 20952/28080 [41:24:25<14:06:23,  7.12s/it]
 75%|███████▍  | 20953/28080 [41:24:32<14:03:54,  7.10s/it]
                                                           
{'loss': 0.645, 'learning_rate': 7.981946590963462e-05, 'epoch': 8.95}

 75%|███████▍  | 20953/28080 [41:24:32<14:03:54,  7.10s/it]
 75%|███████▍  | 20954/28080 [41:24:39<13:59:57,  7.07s/it]
                                                           
{'loss': 0.6072, 'learning_rate': 7.979834368296799e-05, 'epoch': 8.95}

 75%|███████▍  | 20954/28080 [41:24:39<13:59:57,  7.07s/it]
 75%|███████▍  | 20955/28080 [41:24:46<13:59:37,  7.07s/it]
                                                           
{'loss': 0.6049, 'learning_rate': 7.977722372065888e-05, 'epoch': 8.95}

 75%|███████▍  | 20955/28080 [41:24:46<13:59:37,  7.07s/it]
 75%|███████▍  | 20956/28080 [41:24:53<13:56:08,  7.04s/it]
                                                           
{'loss': 0.5869, 'learning_rate': 7.97561060229881e-05, 'epoch': 8.95}

 75%|███████▍  | 20956/28080 [41:24:53<13:56:08,  7.04s/it]
 75%|███████▍  | 20957/28080 [41:25:00<13:53:18,  7.02s/it]
                                                           
{'loss': 0.6268, 'learning_rate': 7.973499059023678e-05, 'epoch': 8.95}

 75%|███████▍  | 20957/28080 [41:25:00<13:53:18,  7.02s/it]
 75%|███████▍  | 20958/28080 [41:25:07<13:57:14,  7.05s/it]
                                                           
{'loss': 0.6144, 'learning_rate': 7.971387742268579e-05, 'epoch': 8.95}

 75%|███████▍  | 20958/28080 [41:25:07<13:57:14,  7.05s/it]
 75%|███████▍  | 20959/28080 [41:25:14<13:54:05,  7.03s/it]
                                                           
{'loss': 0.6045, 'learning_rate': 7.969276652061596e-05, 'epoch': 8.95}

 75%|███████▍  | 20959/28080 [41:25:14<13:54:05,  7.03s/it]
 75%|███████▍  | 20960/28080 [41:25:21<13:58:10,  7.06s/it]
                                                           
{'loss': 0.5923, 'learning_rate': 7.967165788430811e-05, 'epoch': 8.95}

 75%|███████▍  | 20960/28080 [41:25:21<13:58:10,  7.06s/it]
 75%|███████▍  | 20961/28080 [41:25:28<13:59:30,  7.08s/it]
                                                           
{'loss': 0.5931, 'learning_rate': 7.965055151404319e-05, 'epoch': 8.95}

 75%|███████▍  | 20961/28080 [41:25:28<13:59:30,  7.08s/it]
 75%|███████▍  | 20962/28080 [41:25:35<13:57:21,  7.06s/it]
                                                           
{'loss': 0.61, 'learning_rate': 7.962944741010197e-05, 'epoch': 8.95}

 75%|███████▍  | 20962/28080 [41:25:35<13:57:21,  7.06s/it]
 75%|███████▍  | 20963/28080 [41:25:42<14:03:33,  7.11s/it]
                                                           
{'loss': 0.6157, 'learning_rate': 7.960834557276516e-05, 'epoch': 8.96}

 75%|███████▍  | 20963/28080 [41:25:42<14:03:33,  7.11s/it]
 75%|███████▍  | 20964/28080 [41:25:49<14:02:29,  7.10s/it]
                                                           
{'loss': 0.6019, 'learning_rate': 7.958724600231349e-05, 'epoch': 8.96}

 75%|███████▍  | 20964/28080 [41:25:49<14:02:29,  7.10s/it]
 75%|███████▍  | 20965/28080 [41:25:57<14:04:13,  7.12s/it]
                                                           
{'loss': 0.6091, 'learning_rate': 7.956614869902776e-05, 'epoch': 8.96}

 75%|███████▍  | 20965/28080 [41:25:57<14:04:13,  7.12s/it]
 75%|███████▍  | 20966/28080 [41:26:04<14:05:16,  7.13s/it]
                                                           
{'loss': 0.6013, 'learning_rate': 7.95450536631886e-05, 'epoch': 8.96}

 75%|███████▍  | 20966/28080 [41:26:04<14:05:16,  7.13s/it]
 75%|███████▍  | 20967/28080 [41:26:11<14:03:54,  7.12s/it]
                                                           
{'loss': 0.605, 'learning_rate': 7.952396089507663e-05, 'epoch': 8.96}

 75%|███████▍  | 20967/28080 [41:26:11<14:03:54,  7.12s/it]
 75%|███████▍  | 20968/28080 [41:26:18<14:00:01,  7.09s/it]
                                                           
{'loss': 0.6038, 'learning_rate': 7.950287039497253e-05, 'epoch': 8.96}

 75%|███████▍  | 20968/28080 [41:26:18<14:00:01,  7.09s/it]
 75%|███████▍  | 20969/28080 [41:26:25<13:55:41,  7.05s/it]
                                                           
{'loss': 0.601, 'learning_rate': 7.948178216315675e-05, 'epoch': 8.96}

 75%|███████▍  | 20969/28080 [41:26:25<13:55:41,  7.05s/it]
 75%|███████▍  | 20970/28080 [41:26:32<13:58:30,  7.08s/it]
                                                           
{'loss': 0.6129, 'learning_rate': 7.946069619991e-05, 'epoch': 8.96}

 75%|███████▍  | 20970/28080 [41:26:32<13:58:30,  7.08s/it]
 75%|███████▍  | 20971/28080 [41:26:39<13:58:58,  7.08s/it]
                                                           
{'loss': 0.6012, 'learning_rate': 7.943961250551271e-05, 'epoch': 8.96}

 75%|███████▍  | 20971/28080 [41:26:39<13:58:58,  7.08s/it]
 75%|███████▍  | 20972/28080 [41:26:46<13:59:40,  7.09s/it]
                                                           
{'loss': 0.6078, 'learning_rate': 7.941853108024555e-05, 'epoch': 8.96}

 75%|███████▍  | 20972/28080 [41:26:46<13:59:40,  7.09s/it]
 75%|███████▍  | 20973/28080 [41:26:53<14:02:08,  7.11s/it]
                                                           
{'loss': 0.5988, 'learning_rate': 7.939745192438871e-05, 'epoch': 8.96}

 75%|███████▍  | 20973/28080 [41:26:53<14:02:08,  7.11s/it]
 75%|███████▍  | 20974/28080 [41:27:00<13:57:58,  7.08s/it]
                                                           
{'loss': 0.6033, 'learning_rate': 7.937637503822287e-05, 'epoch': 8.96}

 75%|███████▍  | 20974/28080 [41:27:00<13:57:58,  7.08s/it]
 75%|███████▍  | 20975/28080 [41:27:07<14:01:58,  7.11s/it]
                                                           
{'loss': 0.5972, 'learning_rate': 7.935530042202821e-05, 'epoch': 8.96}

 75%|███████▍  | 20975/28080 [41:27:07<14:01:58,  7.11s/it]
 75%|███████▍  | 20976/28080 [41:27:15<14:03:40,  7.13s/it]
                                                           
{'loss': 0.6006, 'learning_rate': 7.933422807608534e-05, 'epoch': 8.96}

 75%|███████▍  | 20976/28080 [41:27:15<14:03:40,  7.13s/it]
 75%|███████▍  | 20977/28080 [41:27:22<14:05:20,  7.14s/it]
                                                           
{'loss': 0.6144, 'learning_rate': 7.93131580006745e-05, 'epoch': 8.96}

 75%|███████▍  | 20977/28080 [41:27:22<14:05:20,  7.14s/it]
 75%|███████▍  | 20978/28080 [41:27:29<14:05:30,  7.14s/it]
                                                           
{'loss': 0.5946, 'learning_rate': 7.929209019607603e-05, 'epoch': 8.96}

 75%|███████▍  | 20978/28080 [41:27:29<14:05:30,  7.14s/it]
 75%|███████▍  | 20979/28080 [41:27:36<14:05:59,  7.15s/it]
                                                           
{'loss': 0.5925, 'learning_rate': 7.927102466257008e-05, 'epoch': 8.96}

 75%|███████▍  | 20979/28080 [41:27:36<14:05:59,  7.15s/it]
 75%|███████▍  | 20980/28080 [41:27:43<14:04:03,  7.13s/it]
                                                           
{'loss': 0.5951, 'learning_rate': 7.924996140043708e-05, 'epoch': 8.96}

 75%|███████▍  | 20980/28080 [41:27:43<14:04:03,  7.13s/it]
 75%|███████▍  | 20981/28080 [41:27:50<14:02:03,  7.12s/it]
                                                           
{'loss': 0.608, 'learning_rate': 7.922890040995723e-05, 'epoch': 8.96}

 75%|███████▍  | 20981/28080 [41:27:50<14:02:03,  7.12s/it]
 75%|███████▍  | 20982/28080 [41:27:57<14:03:23,  7.13s/it]
                                                           
{'loss': 0.6033, 'learning_rate': 7.920784169141065e-05, 'epoch': 8.96}

 75%|███████▍  | 20982/28080 [41:27:57<14:03:23,  7.13s/it]
 75%|███████▍  | 20983/28080 [41:28:04<14:00:12,  7.10s/it]
                                                           
{'loss': 0.6052, 'learning_rate': 7.918678524507747e-05, 'epoch': 8.96}

 75%|███████▍  | 20983/28080 [41:28:04<14:00:12,  7.10s/it]
 75%|███████▍  | 20984/28080 [41:28:11<13:57:28,  7.08s/it]
                                                           
{'loss': 0.5983, 'learning_rate': 7.916573107123798e-05, 'epoch': 8.96}

 75%|███████▍  | 20984/28080 [41:28:11<13:57:28,  7.08s/it]
 75%|███████▍  | 20985/28080 [41:28:19<14:00:38,  7.11s/it]
                                                           
{'loss': 0.5981, 'learning_rate': 7.914467917017213e-05, 'epoch': 8.96}

 75%|███████▍  | 20985/28080 [41:28:19<14:00:38,  7.11s/it]
 75%|███████▍  | 20986/28080 [41:28:26<13:58:04,  7.09s/it]
                                                           
{'loss': 0.6198, 'learning_rate': 7.91236295421602e-05, 'epoch': 8.97}

 75%|███████▍  | 20986/28080 [41:28:26<13:58:04,  7.09s/it]
 75%|███████▍  | 20987/28080 [41:28:33<13:59:10,  7.10s/it]
                                                           
{'loss': 0.617, 'learning_rate': 7.910258218748196e-05, 'epoch': 8.97}

 75%|███████▍  | 20987/28080 [41:28:33<13:59:10,  7.10s/it]
 75%|███████▍  | 20988/28080 [41:28:40<14:01:20,  7.12s/it]
                                                           
{'loss': 0.6033, 'learning_rate': 7.908153710641761e-05, 'epoch': 8.97}

 75%|███████▍  | 20988/28080 [41:28:40<14:01:20,  7.12s/it]
 75%|███████▍  | 20989/28080 [41:28:47<14:02:44,  7.13s/it]
                                                           
{'loss': 0.6093, 'learning_rate': 7.906049429924703e-05, 'epoch': 8.97}

 75%|███████▍  | 20989/28080 [41:28:47<14:02:44,  7.13s/it]
 75%|███████▍  | 20990/28080 [41:28:54<14:03:48,  7.14s/it]
                                                           
{'loss': 0.5934, 'learning_rate': 7.90394537662503e-05, 'epoch': 8.97}

 75%|███████▍  | 20990/28080 [41:28:54<14:03:48,  7.14s/it]
 75%|███████▍  | 20991/28080 [41:29:01<14:02:44,  7.13s/it]
                                                           
{'loss': 0.6156, 'learning_rate': 7.901841550770724e-05, 'epoch': 8.97}

 75%|███████▍  | 20991/28080 [41:29:01<14:02:44,  7.13s/it]
 75%|███████▍  | 20992/28080 [41:29:08<13:59:43,  7.11s/it]
                                                           
{'loss': 0.6104, 'learning_rate': 7.89973795238978e-05, 'epoch': 8.97}

 75%|███████▍  | 20992/28080 [41:29:08<13:59:43,  7.11s/it]
 75%|███████▍  | 20993/28080 [41:29:15<13:56:06,  7.08s/it]
                                                           
{'loss': 0.606, 'learning_rate': 7.89763458151018e-05, 'epoch': 8.97}

 75%|███████▍  | 20993/28080 [41:29:15<13:56:06,  7.08s/it]
 75%|███████▍  | 20994/28080 [41:29:23<13:58:08,  7.10s/it]
                                                           
{'loss': 0.6085, 'learning_rate': 7.8955314381599e-05, 'epoch': 8.97}

 75%|███████▍  | 20994/28080 [41:29:23<13:58:08,  7.10s/it]
 75%|███████▍  | 20995/28080 [41:29:30<13:56:51,  7.09s/it]
                                                           
{'loss': 0.6299, 'learning_rate': 7.893428522366935e-05, 'epoch': 8.97}

 75%|███████▍  | 20995/28080 [41:29:30<13:56:51,  7.09s/it]
 75%|███████▍  | 20996/28080 [41:29:37<13:56:26,  7.08s/it]
                                                           
{'loss': 0.6094, 'learning_rate': 7.89132583415926e-05, 'epoch': 8.97}

 75%|███████▍  | 20996/28080 [41:29:37<13:56:26,  7.08s/it]
 75%|███████▍  | 20997/28080 [41:29:44<13:48:02,  7.01s/it]
                                                           
{'loss': 0.6288, 'learning_rate': 7.88922337356484e-05, 'epoch': 8.97}

 75%|███████▍  | 20997/28080 [41:29:44<13:48:02,  7.01s/it]
 75%|███████▍  | 20998/28080 [41:29:51<13:45:16,  6.99s/it]
                                                           
{'loss': 0.6068, 'learning_rate': 7.887121140611647e-05, 'epoch': 8.97}

 75%|███████▍  | 20998/28080 [41:29:51<13:45:16,  6.99s/it]
 75%|███████▍  | 20999/28080 [41:29:58<13:47:24,  7.01s/it]
                                                           
{'loss': 0.6015, 'learning_rate': 7.885019135327659e-05, 'epoch': 8.97}

 75%|███████▍  | 20999/28080 [41:29:58<13:47:24,  7.01s/it]
 75%|███████▍  | 21000/28080 [41:30:05<13:49:39,  7.03s/it]
                                                           
{'loss': 0.5824, 'learning_rate': 7.882917357740835e-05, 'epoch': 8.97}

 75%|███████▍  | 21000/28080 [41:30:05<13:49:39,  7.03s/it]
 75%|███████▍  | 21001/28080 [41:30:12<13:55:09,  7.08s/it]
                                                           
{'loss': 0.6044, 'learning_rate': 7.880815807879136e-05, 'epoch': 8.97}

 75%|███████▍  | 21001/28080 [41:30:12<13:55:09,  7.08s/it]
 75%|███████▍  | 21002/28080 [41:30:19<13:55:02,  7.08s/it]
                                                           
{'loss': 0.6146, 'learning_rate': 7.878714485770514e-05, 'epoch': 8.97}

 75%|███████▍  | 21002/28080 [41:30:19<13:55:02,  7.08s/it]
 75%|███████▍  | 21003/28080 [41:30:26<13:55:24,  7.08s/it]
                                                           
{'loss': 0.6121, 'learning_rate': 7.876613391442942e-05, 'epoch': 8.97}

 75%|███████▍  | 21003/28080 [41:30:26<13:55:24,  7.08s/it]
 75%|███████▍  | 21004/28080 [41:30:33<13:54:58,  7.08s/it]
                                                           
{'loss': 0.6052, 'learning_rate': 7.874512524924355e-05, 'epoch': 8.97}

 75%|███████▍  | 21004/28080 [41:30:33<13:54:58,  7.08s/it]
 75%|███████▍  | 21005/28080 [41:30:40<13:56:06,  7.09s/it]
                                                           
{'loss': 0.5996, 'learning_rate': 7.87241188624272e-05, 'epoch': 8.97}

 75%|███████▍  | 21005/28080 [41:30:40<13:56:06,  7.09s/it]
 75%|███████▍  | 21006/28080 [41:30:47<13:56:36,  7.10s/it]
                                                           
{'loss': 0.5914, 'learning_rate': 7.870311475425973e-05, 'epoch': 8.97}

 75%|███████▍  | 21006/28080 [41:30:47<13:56:36,  7.10s/it]
 75%|███████▍  | 21007/28080 [41:30:54<13:58:01,  7.11s/it]
                                                           
{'loss': 0.6178, 'learning_rate': 7.868211292502062e-05, 'epoch': 8.97}

 75%|███████▍  | 21007/28080 [41:30:54<13:58:01,  7.11s/it]
 75%|███████▍  | 21008/28080 [41:31:02<13:55:40,  7.09s/it]
                                                           
{'loss': 0.58, 'learning_rate': 7.866111337498919e-05, 'epoch': 8.97}

 75%|███████▍  | 21008/28080 [41:31:02<13:55:40,  7.09s/it]
 75%|███████▍  | 21009/28080 [41:31:08<13:51:01,  7.05s/it]
                                                           
{'loss': 0.6162, 'learning_rate': 7.864011610444494e-05, 'epoch': 8.97}

 75%|███████▍  | 21009/28080 [41:31:08<13:51:01,  7.05s/it]
 75%|███████▍  | 21010/28080 [41:31:16<13:52:04,  7.06s/it]
                                                           
{'loss': 0.623, 'learning_rate': 7.861912111366718e-05, 'epoch': 8.98}

 75%|███████▍  | 21010/28080 [41:31:16<13:52:04,  7.06s/it]
 75%|███████▍  | 21011/28080 [41:31:23<13:54:25,  7.08s/it]
                                                           
{'loss': 0.6149, 'learning_rate': 7.85981284029352e-05, 'epoch': 8.98}

 75%|███████▍  | 21011/28080 [41:31:23<13:54:25,  7.08s/it]
 75%|███████▍  | 21012/28080 [41:31:30<13:52:40,  7.07s/it]
                                                           
{'loss': 0.6083, 'learning_rate': 7.857713797252822e-05, 'epoch': 8.98}

 75%|███████▍  | 21012/28080 [41:31:30<13:52:40,  7.07s/it]
 75%|███████▍  | 21013/28080 [41:31:37<13:52:01,  7.06s/it]
                                                           
{'loss': 0.6025, 'learning_rate': 7.855614982272566e-05, 'epoch': 8.98}

 75%|███████▍  | 21013/28080 [41:31:37<13:52:01,  7.06s/it]
 75%|███████▍  | 21014/28080 [41:31:44<13:56:36,  7.10s/it]
                                                           
{'loss': 0.6135, 'learning_rate': 7.853516395380655e-05, 'epoch': 8.98}

 75%|███████▍  | 21014/28080 [41:31:44<13:56:36,  7.10s/it]
 75%|███████▍  | 21015/28080 [41:31:51<13:53:40,  7.08s/it]
                                                           
{'loss': 0.6171, 'learning_rate': 7.851418036605037e-05, 'epoch': 8.98}

 75%|███████▍  | 21015/28080 [41:31:51<13:53:40,  7.08s/it]
 75%|███████▍  | 21016/28080 [41:31:58<13:54:58,  7.09s/it]
                                                           
{'loss': 0.5986, 'learning_rate': 7.849319905973604e-05, 'epoch': 8.98}

 75%|███████▍  | 21016/28080 [41:31:58<13:54:58,  7.09s/it]
 75%|███████▍  | 21017/28080 [41:32:05<13:49:14,  7.04s/it]
                                                           
{'loss': 0.6062, 'learning_rate': 7.847222003514268e-05, 'epoch': 8.98}

 75%|███████▍  | 21017/28080 [41:32:05<13:49:14,  7.04s/it]
 75%|███████▍  | 21018/28080 [41:32:12<13:52:23,  7.07s/it]
                                                           
{'loss': 0.5992, 'learning_rate': 7.845124329254954e-05, 'epoch': 8.98}

 75%|███████▍  | 21018/28080 [41:32:12<13:52:23,  7.07s/it]
 75%|███████▍  | 21019/28080 [41:32:19<13:49:59,  7.05s/it]
                                                           
{'loss': 0.6132, 'learning_rate': 7.843026883223556e-05, 'epoch': 8.98}

 75%|███████▍  | 21019/28080 [41:32:19<13:49:59,  7.05s/it]
 75%|███████▍  | 21020/28080 [41:32:26<13:50:59,  7.06s/it]
                                                           
{'loss': 0.5963, 'learning_rate': 7.840929665448002e-05, 'epoch': 8.98}

 75%|███████▍  | 21020/28080 [41:32:26<13:50:59,  7.06s/it]
 75%|███████▍  | 21021/28080 [41:32:33<13:52:51,  7.08s/it]
                                                           
{'loss': 0.616, 'learning_rate': 7.838832675956162e-05, 'epoch': 8.98}

 75%|███████▍  | 21021/28080 [41:32:33<13:52:51,  7.08s/it]
 75%|███████▍  | 21022/28080 [41:32:40<13:49:09,  7.05s/it]
                                                           
{'loss': 0.6089, 'learning_rate': 7.836735914775955e-05, 'epoch': 8.98}

 75%|███████▍  | 21022/28080 [41:32:40<13:49:09,  7.05s/it]
 75%|███████▍  | 21023/28080 [41:32:47<13:48:24,  7.04s/it]
                                                           
{'loss': 0.6048, 'learning_rate': 7.834639381935263e-05, 'epoch': 8.98}

 75%|███████▍  | 21023/28080 [41:32:47<13:48:24,  7.04s/it]
 75%|███████▍  | 21024/28080 [41:32:54<13:48:39,  7.05s/it]
                                                           
{'loss': 0.6221, 'learning_rate': 7.832543077461992e-05, 'epoch': 8.98}

 75%|███████▍  | 21024/28080 [41:32:54<13:48:39,  7.05s/it]
 75%|███████▍  | 21025/28080 [41:33:02<13:49:57,  7.06s/it]
                                                           
{'loss': 0.6141, 'learning_rate': 7.830447001384028e-05, 'epoch': 8.98}

 75%|███████▍  | 21025/28080 [41:33:02<13:49:57,  7.06s/it]
 75%|███████▍  | 21026/28080 [41:33:09<13:53:42,  7.09s/it]
                                                           
{'loss': 0.6232, 'learning_rate': 7.828351153729251e-05, 'epoch': 8.98}

 75%|███████▍  | 21026/28080 [41:33:09<13:53:42,  7.09s/it]
 75%|███████▍  | 21027/28080 [41:33:16<13:53:07,  7.09s/it]
                                                           
{'loss': 0.606, 'learning_rate': 7.82625553452554e-05, 'epoch': 8.98}

 75%|███████▍  | 21027/28080 [41:33:16<13:53:07,  7.09s/it]
 75%|███████▍  | 21028/28080 [41:33:23<13:50:38,  7.07s/it]
                                                           
{'loss': 0.5943, 'learning_rate': 7.82416014380079e-05, 'epoch': 8.98}

 75%|███████▍  | 21028/28080 [41:33:23<13:50:38,  7.07s/it]
 75%|███████▍  | 21029/28080 [41:33:30<13:47:06,  7.04s/it]
                                                           
{'loss': 0.6007, 'learning_rate': 7.822064981582869e-05, 'epoch': 8.98}

 75%|███████▍  | 21029/28080 [41:33:30<13:47:06,  7.04s/it]
 75%|███████▍  | 21030/28080 [41:33:37<13:49:51,  7.06s/it]
                                                           
{'loss': 0.5839, 'learning_rate': 7.819970047899652e-05, 'epoch': 8.98}

 75%|███████▍  | 21030/28080 [41:33:37<13:49:51,  7.06s/it]
 75%|███████▍  | 21031/28080 [41:33:44<13:53:25,  7.09s/it]
                                                           
{'loss': 0.6066, 'learning_rate': 7.817875342779001e-05, 'epoch': 8.98}

 75%|███████▍  | 21031/28080 [41:33:44<13:53:25,  7.09s/it]
 75%|███████▍  | 21032/28080 [41:33:51<13:52:45,  7.09s/it]
                                                           
{'loss': 0.6028, 'learning_rate': 7.815780866248804e-05, 'epoch': 8.98}

 75%|███████▍  | 21032/28080 [41:33:51<13:52:45,  7.09s/it]
 75%|███████▍  | 21033/28080 [41:33:58<13:51:41,  7.08s/it]
                                                           
{'loss': 0.6179, 'learning_rate': 7.813686618336905e-05, 'epoch': 8.99}

 75%|███████▍  | 21033/28080 [41:33:58<13:51:41,  7.08s/it]
 75%|███████▍  | 21034/28080 [41:34:05<13:55:16,  7.11s/it]
                                                           
{'loss': 0.5992, 'learning_rate': 7.81159259907119e-05, 'epoch': 8.99}

 75%|███████▍  | 21034/28080 [41:34:05<13:55:16,  7.11s/it]
 75%|███████▍  | 21035/28080 [41:34:12<13:54:23,  7.11s/it]
                                                           
{'loss': 0.6084, 'learning_rate': 7.80949880847949e-05, 'epoch': 8.99}

 75%|███████▍  | 21035/28080 [41:34:12<13:54:23,  7.11s/it]
 75%|███████▍  | 21036/28080 [41:34:20<13:53:25,  7.10s/it]
                                                           
{'loss': 0.6195, 'learning_rate': 7.80740524658968e-05, 'epoch': 8.99}

 75%|███████▍  | 21036/28080 [41:34:20<13:53:25,  7.10s/it]
 75%|███████▍  | 21037/28080 [41:34:27<13:52:32,  7.09s/it]
                                                           
{'loss': 0.5847, 'learning_rate': 7.805311913429597e-05, 'epoch': 8.99}

 75%|███████▍  | 21037/28080 [41:34:27<13:52:32,  7.09s/it]
 75%|███████▍  | 21038/28080 [41:34:34<13:48:08,  7.06s/it]
                                                           
{'loss': 0.607, 'learning_rate': 7.80321880902711e-05, 'epoch': 8.99}

 75%|███████▍  | 21038/28080 [41:34:34<13:48:08,  7.06s/it]
 75%|███████▍  | 21039/28080 [41:34:41<13:51:31,  7.09s/it]
                                                           
{'loss': 0.5833, 'learning_rate': 7.801125933410055e-05, 'epoch': 8.99}

 75%|███████▍  | 21039/28080 [41:34:41<13:51:31,  7.09s/it]
 75%|███████▍  | 21040/28080 [41:34:48<13:49:17,  7.07s/it]
                                                           
{'loss': 0.6298, 'learning_rate': 7.79903328660628e-05, 'epoch': 8.99}

 75%|███████▍  | 21040/28080 [41:34:48<13:49:17,  7.07s/it]
 75%|███████▍  | 21041/28080 [41:34:55<13:51:23,  7.09s/it]
                                                           
{'loss': 0.6242, 'learning_rate': 7.796940868643617e-05, 'epoch': 8.99}

 75%|███████▍  | 21041/28080 [41:34:55<13:51:23,  7.09s/it]
 75%|███████▍  | 21042/28080 [41:35:02<13:48:36,  7.06s/it]
                                                           
{'loss': 0.6261, 'learning_rate': 7.794848679549905e-05, 'epoch': 8.99}

 75%|███████▍  | 21042/28080 [41:35:02<13:48:36,  7.06s/it]
 75%|███████▍  | 21043/28080 [41:35:09<13:51:40,  7.09s/it]
                                                           
{'loss': 0.6101, 'learning_rate': 7.792756719352987e-05, 'epoch': 8.99}

 75%|███████▍  | 21043/28080 [41:35:09<13:51:40,  7.09s/it]
 75%|███████▍  | 21044/28080 [41:35:16<13:52:27,  7.10s/it]
                                                           
{'loss': 0.5945, 'learning_rate': 7.790664988080687e-05, 'epoch': 8.99}

 75%|███████▍  | 21044/28080 [41:35:16<13:52:27,  7.10s/it]
 75%|███████▍  | 21045/28080 [41:35:23<13:51:50,  7.09s/it]
                                                           
{'loss': 0.6119, 'learning_rate': 7.788573485760839e-05, 'epoch': 8.99}

 75%|███████▍  | 21045/28080 [41:35:23<13:51:50,  7.09s/it]
 75%|███████▍  | 21046/28080 [41:35:30<13:51:53,  7.10s/it]
                                                           
{'loss': 0.5885, 'learning_rate': 7.786482212421256e-05, 'epoch': 8.99}

 75%|███████▍  | 21046/28080 [41:35:30<13:51:53,  7.10s/it]
 75%|███████▍  | 21047/28080 [41:35:38<13:52:38,  7.10s/it]
                                                           
{'loss': 0.6175, 'learning_rate': 7.784391168089775e-05, 'epoch': 8.99}

 75%|███████▍  | 21047/28080 [41:35:38<13:52:38,  7.10s/it]
 75%|███████▍  | 21048/28080 [41:35:45<13:58:42,  7.16s/it]
                                                           
{'loss': 0.6123, 'learning_rate': 7.782300352794212e-05, 'epoch': 8.99}

 75%|███████▍  | 21048/28080 [41:35:45<13:58:42,  7.16s/it]
 75%|███████▍  | 21049/28080 [41:35:52<13:53:15,  7.11s/it]
                                                           
{'loss': 0.6126, 'learning_rate': 7.780209766562377e-05, 'epoch': 8.99}

 75%|███████▍  | 21049/28080 [41:35:52<13:53:15,  7.11s/it]
 75%|███████▍  | 21050/28080 [41:35:59<13:53:59,  7.12s/it]
                                                           
{'loss': 0.6112, 'learning_rate': 7.778119409422079e-05, 'epoch': 8.99}

 75%|███████▍  | 21050/28080 [41:35:59<13:53:59,  7.12s/it]
 75%|███████▍  | 21051/28080 [41:36:06<13:54:54,  7.13s/it]
                                                           
{'loss': 0.6006, 'learning_rate': 7.776029281401148e-05, 'epoch': 8.99}

 75%|███████▍  | 21051/28080 [41:36:06<13:54:54,  7.13s/it]
 75%|███████▍  | 21052/28080 [41:36:13<13:53:47,  7.12s/it]
                                                           
{'loss': 0.625, 'learning_rate': 7.773939382527364e-05, 'epoch': 8.99}

 75%|███████▍  | 21052/28080 [41:36:13<13:53:47,  7.12s/it]
 75%|███████▍  | 21053/28080 [41:36:20<13:51:52,  7.10s/it]
                                                           
{'loss': 0.5871, 'learning_rate': 7.771849712828558e-05, 'epoch': 8.99}

 75%|███████▍  | 21053/28080 [41:36:20<13:51:52,  7.10s/it]
 75%|███████▍  | 21054/28080 [41:36:27<13:46:08,  7.06s/it]
                                                           
{'loss': 0.6026, 'learning_rate': 7.769760272332519e-05, 'epoch': 8.99}

 75%|███████▍  | 21054/28080 [41:36:27<13:46:08,  7.06s/it]
 75%|███████▍  | 21055/28080 [41:36:34<13:48:10,  7.07s/it]
                                                           
{'loss': 0.596, 'learning_rate': 7.767671061067038e-05, 'epoch': 8.99}

 75%|███████▍  | 21055/28080 [41:36:34<13:48:10,  7.07s/it]
 75%|███████▍  | 21056/28080 [41:36:41<13:50:54,  7.10s/it]
                                                           
{'loss': 0.5876, 'learning_rate': 7.765582079059913e-05, 'epoch': 8.99}

 75%|███████▍  | 21056/28080 [41:36:41<13:50:54,  7.10s/it]
 75%|███████▍  | 21057/28080 [41:36:49<13:55:38,  7.14s/it]
                                                           
{'loss': 0.5998, 'learning_rate': 7.763493326338947e-05, 'epoch': 9.0}

 75%|███████▍  | 21057/28080 [41:36:49<13:55:38,  7.14s/it]
 75%|███████▍  | 21058/28080 [41:36:56<13:56:27,  7.15s/it]
                                                           
{'loss': 0.6113, 'learning_rate': 7.761404802931918e-05, 'epoch': 9.0}

 75%|███████▍  | 21058/28080 [41:36:56<13:56:27,  7.15s/it]
 75%|███████▍  | 21059/28080 [41:37:03<13:55:26,  7.14s/it]
                                                           
{'loss': 0.6095, 'learning_rate': 7.759316508866615e-05, 'epoch': 9.0}

 75%|███████▍  | 21059/28080 [41:37:03<13:55:26,  7.14s/it]
 75%|███████▌  | 21060/28080 [41:37:10<13:49:55,  7.09s/it]
                                                           
{'loss': 0.6093, 'learning_rate': 7.757228444170811e-05, 'epoch': 9.0}

 75%|███████▌  | 21060/28080 [41:37:10<13:49:55,  7.09s/it]
 75%|███████▌  | 21061/28080 [41:37:17<13:48:21,  7.08s/it]
                                                           
{'loss': 0.6202, 'learning_rate': 7.755140608872302e-05, 'epoch': 9.0}

 75%|███████▌  | 21061/28080 [41:37:17<13:48:21,  7.08s/it]
 75%|███████▌  | 21062/28080 [41:37:24<13:47:11,  7.07s/it]
                                                           
{'loss': 0.6072, 'learning_rate': 7.753053002998858e-05, 'epoch': 9.0}

 75%|███████▌  | 21062/28080 [41:37:24<13:47:11,  7.07s/it]
 75%|███████▌  | 21063/28080 [41:37:31<13:43:58,  7.05s/it]
                                                           
{'loss': 0.5957, 'learning_rate': 7.750965626578251e-05, 'epoch': 9.0}

 75%|███████▌  | 21063/28080 [41:37:31<13:43:58,  7.05s/it]
 75%|███████▌  | 21064/28080 [41:37:38<13:44:18,  7.05s/it]
                                                           
{'loss': 0.5917, 'learning_rate': 7.748878479638244e-05, 'epoch': 9.0}

 75%|███████▌  | 21064/28080 [41:37:38<13:44:18,  7.05s/it]
 75%|███████▌  | 21065/28080 [41:37:45<13:47:06,  7.07s/it]
                                                           
{'loss': 0.5849, 'learning_rate': 7.746791562206617e-05, 'epoch': 9.0}

 75%|███████▌  | 21065/28080 [41:37:45<13:47:06,  7.07s/it]
 75%|███████▌  | 21066/28080 [41:37:52<13:47:17,  7.08s/it]
                                                           
{'loss': 0.6131, 'learning_rate': 7.744704874311132e-05, 'epoch': 9.0}

 75%|███████▌  | 21066/28080 [41:37:52<13:47:17,  7.08s/it]
 75%|███████▌  | 21067/28080 [41:37:59<13:49:14,  7.09s/it]
                                                           
{'loss': 0.6063, 'learning_rate': 7.742618415979538e-05, 'epoch': 9.0}

 75%|███████▌  | 21067/28080 [41:37:59<13:49:14,  7.09s/it]
 75%|███████▌  | 21068/28080 [41:38:07<14:08:37,  7.26s/it]
                                                           
{'loss': 0.615, 'learning_rate': 7.740532187239619e-05, 'epoch': 9.0}

 75%|███████▌  | 21068/28080 [41:38:07<14:08:37,  7.26s/it]
 75%|███████▌  | 21069/28080 [41:38:14<14:01:36,  7.20s/it]
                                                           
{'loss': 0.5761, 'learning_rate': 7.738446188119097e-05, 'epoch': 9.0}

 75%|███████▌  | 21069/28080 [41:38:14<14:01:36,  7.20s/it]
 75%|███████▌  | 21070/28080 [41:38:21<13:59:01,  7.18s/it]
                                                           
{'loss': 0.5927, 'learning_rate': 7.73636041864575e-05, 'epoch': 9.0}

 75%|███████▌  | 21070/28080 [41:38:21<13:59:01,  7.18s/it]
 75%|███████▌  | 21071/28080 [41:38:28<13:55:07,  7.15s/it]
                                                           
{'loss': 0.6161, 'learning_rate': 7.734274878847309e-05, 'epoch': 9.0}

 75%|███████▌  | 21071/28080 [41:38:28<13:55:07,  7.15s/it]
 75%|███████▌  | 21072/28080 [41:38:36<13:55:04,  7.15s/it]
                                                           
{'loss': 0.6252, 'learning_rate': 7.732189568751535e-05, 'epoch': 9.0}

 75%|███████▌  | 21072/28080 [41:38:36<13:55:04,  7.15s/it]
 75%|███████▌  | 21073/28080 [41:38:43<13:54:27,  7.15s/it]
                                                           
{'loss': 0.6037, 'learning_rate': 7.730104488386167e-05, 'epoch': 9.0}

 75%|███████▌  | 21073/28080 [41:38:43<13:54:27,  7.15s/it]
 75%|███████▌  | 21074/28080 [41:38:50<13:51:35,  7.12s/it]
                                                           
{'loss': 0.6028, 'learning_rate': 7.72801963777894e-05, 'epoch': 9.0}

 75%|███████▌  | 21074/28080 [41:38:50<13:51:35,  7.12s/it]
 75%|███████▌  | 21075/28080 [41:38:57<13:46:17,  7.08s/it]
                                                           
{'loss': 0.6049, 'learning_rate': 7.725935016957589e-05, 'epoch': 9.0}

 75%|███████▌  | 21075/28080 [41:38:57<13:46:17,  7.08s/it]
 75%|███████▌  | 21076/28080 [41:39:04<13:47:19,  7.09s/it]
                                                           
{'loss': 0.6246, 'learning_rate': 7.723850625949858e-05, 'epoch': 9.0}

 75%|███████▌  | 21076/28080 [41:39:04<13:47:19,  7.09s/it]
 75%|███████▌  | 21077/28080 [41:39:11<13:45:41,  7.07s/it]
                                                           
{'loss': 0.5914, 'learning_rate': 7.72176646478347e-05, 'epoch': 9.0}

 75%|███████▌  | 21077/28080 [41:39:11<13:45:41,  7.07s/it]
 75%|███████▌  | 21078/28080 [41:39:18<13:45:06,  7.07s/it]
                                                           
{'loss': 0.6206, 'learning_rate': 7.719682533486155e-05, 'epoch': 9.0}

 75%|███████▌  | 21078/28080 [41:39:18<13:45:06,  7.07s/it]
 75%|███████▌  | 21079/28080 [41:39:25<13:45:17,  7.07s/it]
                                                           
{'loss': 0.6116, 'learning_rate': 7.717598832085631e-05, 'epoch': 9.0}

 75%|███████▌  | 21079/28080 [41:39:25<13:45:17,  7.07s/it]
 75%|███████▌  | 21080/28080 [41:39:32<13:43:58,  7.06s/it]
                                                           
{'loss': 0.6001, 'learning_rate': 7.715515360609632e-05, 'epoch': 9.01}

 75%|███████▌  | 21080/28080 [41:39:32<13:43:58,  7.06s/it]
 75%|███████▌  | 21081/28080 [41:39:39<13:43:01,  7.06s/it]
                                                           
{'loss': 0.6046, 'learning_rate': 7.713432119085862e-05, 'epoch': 9.01}

 75%|███████▌  | 21081/28080 [41:39:39<13:43:01,  7.06s/it]
 75%|███████▌  | 21082/28080 [41:39:46<13:44:28,  7.07s/it]
                                                           
{'loss': 0.5926, 'learning_rate': 7.711349107542057e-05, 'epoch': 9.01}

 75%|███████▌  | 21082/28080 [41:39:46<13:44:28,  7.07s/it]
 75%|███████▌  | 21083/28080 [41:39:53<13:45:51,  7.08s/it]
                                                           
{'loss': 0.6204, 'learning_rate': 7.709266326005904e-05, 'epoch': 9.01}

 75%|███████▌  | 21083/28080 [41:39:53<13:45:51,  7.08s/it]
 75%|███████▌  | 21084/28080 [41:40:00<13:45:46,  7.08s/it]
                                                           
{'loss': 0.5936, 'learning_rate': 7.70718377450513e-05, 'epoch': 9.01}

 75%|███████▌  | 21084/28080 [41:40:00<13:45:46,  7.08s/it]
 75%|███████▌  | 21085/28080 [41:40:08<13:47:40,  7.10s/it]
                                                           
{'loss': 0.5719, 'learning_rate': 7.705101453067432e-05, 'epoch': 9.01}

 75%|███████▌  | 21085/28080 [41:40:08<13:47:40,  7.10s/it]
 75%|███████▌  | 21086/28080 [41:40:15<13:47:58,  7.10s/it]
                                                           
{'loss': 0.5679, 'learning_rate': 7.703019361720521e-05, 'epoch': 9.01}

 75%|███████▌  | 21086/28080 [41:40:15<13:47:58,  7.10s/it]
 75%|███████▌  | 21087/28080 [41:40:22<13:50:37,  7.13s/it]
                                                           
{'loss': 0.5938, 'learning_rate': 7.700937500492095e-05, 'epoch': 9.01}

 75%|███████▌  | 21087/28080 [41:40:22<13:50:37,  7.13s/it]
 75%|███████▌  | 21088/28080 [41:40:29<13:45:19,  7.08s/it]
                                                           
{'loss': 0.6048, 'learning_rate': 7.698855869409849e-05, 'epoch': 9.01}

 75%|███████▌  | 21088/28080 [41:40:29<13:45:19,  7.08s/it]
 75%|███████▌  | 21089/28080 [41:40:36<13:45:37,  7.09s/it]
                                                           
{'loss': 0.6018, 'learning_rate': 7.696774468501466e-05, 'epoch': 9.01}

 75%|███████▌  | 21089/28080 [41:40:36<13:45:37,  7.09s/it]
 75%|███████▌  | 21090/28080 [41:40:43<13:47:39,  7.10s/it]
                                                           
{'loss': 0.6046, 'learning_rate': 7.694693297794661e-05, 'epoch': 9.01}

 75%|███████▌  | 21090/28080 [41:40:43<13:47:39,  7.10s/it]
 75%|███████▌  | 21091/28080 [41:40:50<13:44:42,  7.08s/it]
                                                           
{'loss': 0.6024, 'learning_rate': 7.692612357317105e-05, 'epoch': 9.01}

 75%|███████▌  | 21091/28080 [41:40:50<13:44:42,  7.08s/it]
 75%|███████▌  | 21092/28080 [41:40:57<13:43:04,  7.07s/it]
                                                           
{'loss': 0.5996, 'learning_rate': 7.690531647096488e-05, 'epoch': 9.01}

 75%|███████▌  | 21092/28080 [41:40:57<13:43:04,  7.07s/it]
 75%|███████▌  | 21093/28080 [41:41:04<13:40:13,  7.04s/it]
                                                           
{'loss': 0.6015, 'learning_rate': 7.68845116716049e-05, 'epoch': 9.01}

 75%|███████▌  | 21093/28080 [41:41:04<13:40:13,  7.04s/it]
 75%|███████▌  | 21094/28080 [41:41:11<13:39:05,  7.03s/it]
                                                           
{'loss': 0.6072, 'learning_rate': 7.686370917536783e-05, 'epoch': 9.01}

 75%|███████▌  | 21094/28080 [41:41:11<13:39:05,  7.03s/it]
 75%|███████▌  | 21095/28080 [41:41:18<13:40:47,  7.05s/it]
                                                           
{'loss': 0.59, 'learning_rate': 7.684290898253054e-05, 'epoch': 9.01}

 75%|███████▌  | 21095/28080 [41:41:18<13:40:47,  7.05s/it]
 75%|███████▌  | 21096/28080 [41:41:25<13:41:49,  7.06s/it]
                                                           
{'loss': 0.5816, 'learning_rate': 7.682211109336975e-05, 'epoch': 9.01}

 75%|███████▌  | 21096/28080 [41:41:25<13:41:49,  7.06s/it]
 75%|███████▌  | 21097/28080 [41:41:32<13:42:39,  7.07s/it]
                                                           
{'loss': 0.6259, 'learning_rate': 7.68013155081621e-05, 'epoch': 9.01}

 75%|███████▌  | 21097/28080 [41:41:32<13:42:39,  7.07s/it]
 75%|███████▌  | 21098/28080 [41:41:39<13:39:23,  7.04s/it]
                                                           
{'loss': 0.6025, 'learning_rate': 7.678052222718418e-05, 'epoch': 9.01}

 75%|███████▌  | 21098/28080 [41:41:39<13:39:23,  7.04s/it]
 75%|███████▌  | 21099/28080 [41:41:46<13:40:50,  7.05s/it]
                                                           
{'loss': 0.5935, 'learning_rate': 7.675973125071282e-05, 'epoch': 9.01}

 75%|███████▌  | 21099/28080 [41:41:46<13:40:50,  7.05s/it]
 75%|███████▌  | 21100/28080 [41:41:54<13:42:23,  7.07s/it]
                                                           
{'loss': 0.5947, 'learning_rate': 7.673894257902439e-05, 'epoch': 9.01}

 75%|███████▌  | 21100/28080 [41:41:54<13:42:23,  7.07s/it]
 75%|███████▌  | 21101/28080 [41:42:01<13:44:40,  7.09s/it]
                                                           
{'loss': 0.606, 'learning_rate': 7.67181562123957e-05, 'epoch': 9.01}

 75%|███████▌  | 21101/28080 [41:42:01<13:44:40,  7.09s/it]
 75%|███████▌  | 21102/28080 [41:42:08<13:40:42,  7.06s/it]
                                                           
{'loss': 0.6119, 'learning_rate': 7.669737215110318e-05, 'epoch': 9.01}

 75%|███████▌  | 21102/28080 [41:42:08<13:40:42,  7.06s/it]
 75%|███████▌  | 21103/28080 [41:42:15<13:42:29,  7.07s/it]
                                                           
{'loss': 0.5881, 'learning_rate': 7.66765903954233e-05, 'epoch': 9.02}

 75%|███████▌  | 21103/28080 [41:42:15<13:42:29,  7.07s/it]
 75%|███████▌  | 21104/28080 [41:42:22<13:42:58,  7.08s/it]
                                                           
{'loss': 0.6155, 'learning_rate': 7.665581094563251e-05, 'epoch': 9.02}

 75%|███████▌  | 21104/28080 [41:42:22<13:42:58,  7.08s/it]
 75%|███████▌  | 21105/28080 [41:42:29<13:39:32,  7.05s/it]
                                                           
{'loss': 0.5975, 'learning_rate': 7.663503380200743e-05, 'epoch': 9.02}

 75%|███████▌  | 21105/28080 [41:42:29<13:39:32,  7.05s/it]
 75%|███████▌  | 21106/28080 [41:42:36<13:37:29,  7.03s/it]
                                                           
{'loss': 0.5996, 'learning_rate': 7.661425896482435e-05, 'epoch': 9.02}

 75%|███████▌  | 21106/28080 [41:42:36<13:37:29,  7.03s/it]
 75%|███████▌  | 21107/28080 [41:42:43<13:40:35,  7.06s/it]
                                                           
{'loss': 0.603, 'learning_rate': 7.65934864343597e-05, 'epoch': 9.02}

 75%|███████▌  | 21107/28080 [41:42:43<13:40:35,  7.06s/it]
 75%|███████▌  | 21108/28080 [41:42:50<13:43:55,  7.09s/it]
                                                           
{'loss': 0.5915, 'learning_rate': 7.657271621088973e-05, 'epoch': 9.02}

 75%|███████▌  | 21108/28080 [41:42:50<13:43:55,  7.09s/it]
 75%|███████▌  | 21109/28080 [41:42:57<13:46:05,  7.11s/it]
                                                           
{'loss': 0.6165, 'learning_rate': 7.655194829469092e-05, 'epoch': 9.02}

 75%|███████▌  | 21109/28080 [41:42:57<13:46:05,  7.11s/it]
 75%|███████▌  | 21110/28080 [41:43:04<13:44:50,  7.10s/it]
                                                           
{'loss': 0.5956, 'learning_rate': 7.653118268603953e-05, 'epoch': 9.02}

 75%|███████▌  | 21110/28080 [41:43:04<13:44:50,  7.10s/it]
 75%|███████▌  | 21111/28080 [41:43:11<13:40:11,  7.06s/it]
                                                           
{'loss': 0.6058, 'learning_rate': 7.651041938521178e-05, 'epoch': 9.02}

 75%|███████▌  | 21111/28080 [41:43:11<13:40:11,  7.06s/it]
 75%|███████▌  | 21112/28080 [41:43:18<13:39:23,  7.06s/it]
                                                           
{'loss': 0.6213, 'learning_rate': 7.648965839248383e-05, 'epoch': 9.02}

 75%|███████▌  | 21112/28080 [41:43:18<13:39:23,  7.06s/it]
 75%|███████▌  | 21113/28080 [41:43:25<13:40:20,  7.06s/it]
                                                           
{'loss': 0.594, 'learning_rate': 7.646889970813209e-05, 'epoch': 9.02}

 75%|███████▌  | 21113/28080 [41:43:25<13:40:20,  7.06s/it]
 75%|███████▌  | 21114/28080 [41:43:33<13:43:32,  7.09s/it]
                                                           
{'loss': 0.6095, 'learning_rate': 7.644814333243252e-05, 'epoch': 9.02}

 75%|███████▌  | 21114/28080 [41:43:33<13:43:32,  7.09s/it]
 75%|███████▌  | 21115/28080 [41:43:40<13:39:08,  7.06s/it]
                                                           
{'loss': 0.6215, 'learning_rate': 7.642738926566142e-05, 'epoch': 9.02}

 75%|███████▌  | 21115/28080 [41:43:40<13:39:08,  7.06s/it]
 75%|███████▌  | 21116/28080 [41:43:47<13:37:59,  7.05s/it]
                                                           
{'loss': 0.6281, 'learning_rate': 7.640663750809495e-05, 'epoch': 9.02}

 75%|███████▌  | 21116/28080 [41:43:47<13:37:59,  7.05s/it]
 75%|███████▌  | 21117/28080 [41:43:54<13:36:25,  7.04s/it]
                                                           
{'loss': 0.62, 'learning_rate': 7.638588806000891e-05, 'epoch': 9.02}

 75%|███████▌  | 21117/28080 [41:43:54<13:36:25,  7.04s/it]
 75%|███████▌  | 21118/28080 [41:44:01<13:40:33,  7.07s/it]
                                                           
{'loss': 0.615, 'learning_rate': 7.636514092167959e-05, 'epoch': 9.02}

 75%|███████▌  | 21118/28080 [41:44:01<13:40:33,  7.07s/it]
 75%|███████▌  | 21119/28080 [41:44:08<13:38:32,  7.06s/it]
                                                           
{'loss': 0.6254, 'learning_rate': 7.634439609338289e-05, 'epoch': 9.02}

 75%|███████▌  | 21119/28080 [41:44:08<13:38:32,  7.06s/it]
 75%|███████▌  | 21120/28080 [41:44:15<13:35:42,  7.03s/it]
                                                           
{'loss': 0.6101, 'learning_rate': 7.632365357539489e-05, 'epoch': 9.02}

 75%|███████▌  | 21120/28080 [41:44:15<13:35:42,  7.03s/it]
 75%|███████▌  | 21121/28080 [41:44:22<13:35:23,  7.03s/it]
                                                           
{'loss': 0.6093, 'learning_rate': 7.630291336799155e-05, 'epoch': 9.02}

 75%|███████▌  | 21121/28080 [41:44:22<13:35:23,  7.03s/it]
 75%|███████▌  | 21122/28080 [41:44:29<13:39:04,  7.06s/it]
                                                           
{'loss': 0.6089, 'learning_rate': 7.628217547144872e-05, 'epoch': 9.02}

 75%|███████▌  | 21122/28080 [41:44:29<13:39:04,  7.06s/it]
 75%|███████▌  | 21123/28080 [41:44:36<13:50:11,  7.16s/it]
                                                           
{'loss': 0.6033, 'learning_rate': 7.626143988604226e-05, 'epoch': 9.02}

 75%|███████▌  | 21123/28080 [41:44:36<13:50:11,  7.16s/it]
 75%|███████▌  | 21124/28080 [41:44:43<13:44:11,  7.11s/it]
                                                           
{'loss': 0.59, 'learning_rate': 7.624070661204821e-05, 'epoch': 9.02}

 75%|███████▌  | 21124/28080 [41:44:43<13:44:11,  7.11s/it]
 75%|███████▌  | 21125/28080 [41:44:50<13:44:57,  7.12s/it]
                                                           
{'loss': 0.5892, 'learning_rate': 7.621997564974225e-05, 'epoch': 9.02}

 75%|███████▌  | 21125/28080 [41:44:50<13:44:57,  7.12s/it]
 75%|███████▌  | 21126/28080 [41:44:58<13:46:51,  7.13s/it]
                                                           
{'loss': 0.5762, 'learning_rate': 7.619924699940028e-05, 'epoch': 9.02}

 75%|███████▌  | 21126/28080 [41:44:58<13:46:51,  7.13s/it]
 75%|███████▌  | 21127/28080 [41:45:05<13:44:37,  7.12s/it]
                                                           
{'loss': 0.5871, 'learning_rate': 7.617852066129793e-05, 'epoch': 9.03}

 75%|███████▌  | 21127/28080 [41:45:05<13:44:37,  7.12s/it]
 75%|███████▌  | 21128/28080 [41:45:12<13:41:07,  7.09s/it]
                                                           
{'loss': 0.6239, 'learning_rate': 7.615779663571113e-05, 'epoch': 9.03}

 75%|███████▌  | 21128/28080 [41:45:12<13:41:07,  7.09s/it]
 75%|███████▌  | 21129/28080 [41:45:19<13:42:06,  7.10s/it]
                                                           
{'loss': 0.6143, 'learning_rate': 7.613707492291541e-05, 'epoch': 9.03}

 75%|███████▌  | 21129/28080 [41:45:19<13:42:06,  7.10s/it]
 75%|███████▌  | 21130/28080 [41:45:26<13:43:31,  7.11s/it]
                                                           
{'loss': 0.6048, 'learning_rate': 7.611635552318671e-05, 'epoch': 9.03}

 75%|███████▌  | 21130/28080 [41:45:26<13:43:31,  7.11s/it]
 75%|███████▌  | 21131/28080 [41:45:33<13:44:17,  7.12s/it]
                                                           
{'loss': 0.6196, 'learning_rate': 7.609563843680037e-05, 'epoch': 9.03}

 75%|███████▌  | 21131/28080 [41:45:33<13:44:17,  7.12s/it]
 75%|███████▌  | 21132/28080 [41:45:40<13:44:51,  7.12s/it]
                                                           
{'loss': 0.6024, 'learning_rate': 7.607492366403221e-05, 'epoch': 9.03}

 75%|███████▌  | 21132/28080 [41:45:40<13:44:51,  7.12s/it]
 75%|███████▌  | 21133/28080 [41:45:47<13:42:13,  7.10s/it]
                                                           
{'loss': 0.5969, 'learning_rate': 7.60542112051577e-05, 'epoch': 9.03}

 75%|███████▌  | 21133/28080 [41:45:47<13:42:13,  7.10s/it]
 75%|███████▌  | 21134/28080 [41:45:54<13:43:37,  7.11s/it]
                                                           
{'loss': 0.6124, 'learning_rate': 7.603350106045254e-05, 'epoch': 9.03}

 75%|███████▌  | 21134/28080 [41:45:54<13:43:37,  7.11s/it]
 75%|███████▌  | 21135/28080 [41:46:01<13:39:17,  7.08s/it]
                                                           
{'loss': 0.6318, 'learning_rate': 7.601279323019217e-05, 'epoch': 9.03}

 75%|███████▌  | 21135/28080 [41:46:01<13:39:17,  7.08s/it]
 75%|███████▌  | 21136/28080 [41:46:09<13:42:07,  7.10s/it]
                                                           
{'loss': 0.6067, 'learning_rate': 7.599208771465207e-05, 'epoch': 9.03}

 75%|███████▌  | 21136/28080 [41:46:09<13:42:07,  7.10s/it]
 75%|███████▌  | 21137/28080 [41:46:16<13:39:56,  7.09s/it]
                                                           
{'loss': 0.5849, 'learning_rate': 7.597138451410768e-05, 'epoch': 9.03}

 75%|███████▌  | 21137/28080 [41:46:16<13:39:56,  7.09s/it]
 75%|███████▌  | 21138/28080 [41:46:23<13:40:34,  7.09s/it]
                                                           
{'loss': 0.6244, 'learning_rate': 7.595068362883456e-05, 'epoch': 9.03}

 75%|███████▌  | 21138/28080 [41:46:23<13:40:34,  7.09s/it]
 75%|███████▌  | 21139/28080 [41:46:30<13:44:26,  7.13s/it]
                                                           
{'loss': 0.6001, 'learning_rate': 7.592998505910802e-05, 'epoch': 9.03}

 75%|███████▌  | 21139/28080 [41:46:30<13:44:26,  7.13s/it]
 75%|███████▌  | 21140/28080 [41:46:37<13:45:22,  7.14s/it]
                                                           
{'loss': 0.6042, 'learning_rate': 7.590928880520347e-05, 'epoch': 9.03}

 75%|███████▌  | 21140/28080 [41:46:37<13:45:22,  7.14s/it]
 75%|███████▌  | 21141/28080 [41:46:44<13:43:33,  7.12s/it]
                                                           
{'loss': 0.599, 'learning_rate': 7.588859486739622e-05, 'epoch': 9.03}

 75%|███████▌  | 21141/28080 [41:46:44<13:43:33,  7.12s/it]
 75%|███████▌  | 21142/28080 [41:46:51<13:46:54,  7.15s/it]
                                                           
{'loss': 0.5913, 'learning_rate': 7.586790324596152e-05, 'epoch': 9.03}

 75%|███████▌  | 21142/28080 [41:46:51<13:46:54,  7.15s/it]
 75%|███████▌  | 21143/28080 [41:46:58<13:43:11,  7.12s/it]
                                                           
{'loss': 0.5946, 'learning_rate': 7.58472139411748e-05, 'epoch': 9.03}

 75%|███████▌  | 21143/28080 [41:46:58<13:43:11,  7.12s/it]
 75%|███████▌  | 21144/28080 [41:47:06<13:42:13,  7.11s/it]
                                                           
{'loss': 0.6039, 'learning_rate': 7.582652695331124e-05, 'epoch': 9.03}

 75%|███████▌  | 21144/28080 [41:47:06<13:42:13,  7.11s/it]
 75%|███████▌  | 21145/28080 [41:47:13<13:41:36,  7.11s/it]
                                                           
{'loss': 0.6126, 'learning_rate': 7.580584228264607e-05, 'epoch': 9.03}

 75%|███████▌  | 21145/28080 [41:47:13<13:41:36,  7.11s/it]
 75%|███████▌  | 21146/28080 [41:47:20<13:41:24,  7.11s/it]
                                                           
{'loss': 0.613, 'learning_rate': 7.578515992945437e-05, 'epoch': 9.03}

 75%|███████▌  | 21146/28080 [41:47:20<13:41:24,  7.11s/it]
 75%|███████▌  | 21147/28080 [41:47:27<13:37:43,  7.08s/it]
                                                           
{'loss': 0.6064, 'learning_rate': 7.576447989401144e-05, 'epoch': 9.03}

 75%|███████▌  | 21147/28080 [41:47:27<13:37:43,  7.08s/it]
 75%|███████▌  | 21148/28080 [41:47:34<13:40:48,  7.10s/it]
                                                           
{'loss': 0.6263, 'learning_rate': 7.574380217659232e-05, 'epoch': 9.03}

 75%|███████▌  | 21148/28080 [41:47:34<13:40:48,  7.10s/it]
 75%|███████▌  | 21149/28080 [41:47:41<13:36:39,  7.07s/it]
                                                           
{'loss': 0.5793, 'learning_rate': 7.572312677747229e-05, 'epoch': 9.03}

 75%|███████▌  | 21149/28080 [41:47:41<13:36:39,  7.07s/it]
 75%|███████▌  | 21150/28080 [41:47:48<13:34:50,  7.05s/it]
                                                           
{'loss': 0.6013, 'learning_rate': 7.57024536969261e-05, 'epoch': 9.04}

 75%|███████▌  | 21150/28080 [41:47:48<13:34:50,  7.05s/it]
 75%|███████▌  | 21151/28080 [41:47:55<13:35:13,  7.06s/it]
                                                           
{'loss': 0.603, 'learning_rate': 7.568178293522904e-05, 'epoch': 9.04}

 75%|███████▌  | 21151/28080 [41:47:55<13:35:13,  7.06s/it]
 75%|███████▌  | 21152/28080 [41:48:02<13:38:58,  7.09s/it]
                                                           
{'loss': 0.5974, 'learning_rate': 7.566111449265592e-05, 'epoch': 9.04}

 75%|███████▌  | 21152/28080 [41:48:02<13:38:58,  7.09s/it]
 75%|███████▌  | 21153/28080 [41:48:09<13:40:39,  7.11s/it]
                                                           
{'loss': 0.6014, 'learning_rate': 7.564044836948192e-05, 'epoch': 9.04}

 75%|███████▌  | 21153/28080 [41:48:09<13:40:39,  7.11s/it]
 75%|███████▌  | 21154/28080 [41:48:16<13:39:36,  7.10s/it]
                                                           
{'loss': 0.5909, 'learning_rate': 7.561978456598187e-05, 'epoch': 9.04}

 75%|███████▌  | 21154/28080 [41:48:16<13:39:36,  7.10s/it]
 75%|███████▌  | 21155/28080 [41:48:23<13:38:04,  7.09s/it]
                                                           
{'loss': 0.5862, 'learning_rate': 7.559912308243069e-05, 'epoch': 9.04}

 75%|███████▌  | 21155/28080 [41:48:23<13:38:04,  7.09s/it]
 75%|███████▌  | 21156/28080 [41:48:31<13:37:10,  7.08s/it]
                                                           
{'loss': 0.6127, 'learning_rate': 7.557846391910317e-05, 'epoch': 9.04}

 75%|███████▌  | 21156/28080 [41:48:31<13:37:10,  7.08s/it]
 75%|███████▌  | 21157/28080 [41:48:38<13:36:27,  7.08s/it]
                                                           
{'loss': 0.6062, 'learning_rate': 7.555780707627432e-05, 'epoch': 9.04}

 75%|███████▌  | 21157/28080 [41:48:38<13:36:27,  7.08s/it]
 75%|███████▌  | 21158/28080 [41:48:45<13:38:42,  7.10s/it]
                                                           
{'loss': 0.5949, 'learning_rate': 7.553715255421892e-05, 'epoch': 9.04}

 75%|███████▌  | 21158/28080 [41:48:45<13:38:42,  7.10s/it]
 75%|███████▌  | 21159/28080 [41:48:52<13:41:14,  7.12s/it]
                                                           
{'loss': 0.597, 'learning_rate': 7.55165003532117e-05, 'epoch': 9.04}

 75%|███████▌  | 21159/28080 [41:48:52<13:41:14,  7.12s/it]
 75%|███████▌  | 21160/28080 [41:48:59<13:38:41,  7.10s/it]
                                                           
{'loss': 0.6139, 'learning_rate': 7.549585047352736e-05, 'epoch': 9.04}

 75%|███████▌  | 21160/28080 [41:48:59<13:38:41,  7.10s/it]
 75%|███████▌  | 21161/28080 [41:49:06<13:37:07,  7.09s/it]
                                                           
{'loss': 0.5975, 'learning_rate': 7.547520291544078e-05, 'epoch': 9.04}

 75%|███████▌  | 21161/28080 [41:49:06<13:37:07,  7.09s/it]
 75%|███████▌  | 21162/28080 [41:49:13<13:34:12,  7.06s/it]
                                                           
{'loss': 0.6075, 'learning_rate': 7.545455767922649e-05, 'epoch': 9.04}

 75%|███████▌  | 21162/28080 [41:49:13<13:34:12,  7.06s/it]
 75%|███████▌  | 21163/28080 [41:49:20<13:36:37,  7.08s/it]
                                                           
{'loss': 0.6009, 'learning_rate': 7.543391476515934e-05, 'epoch': 9.04}

 75%|███████▌  | 21163/28080 [41:49:20<13:36:37,  7.08s/it]
 75%|███████▌  | 21164/28080 [41:49:27<13:33:27,  7.06s/it]
                                                           
{'loss': 0.6042, 'learning_rate': 7.541327417351384e-05, 'epoch': 9.04}

 75%|███████▌  | 21164/28080 [41:49:27<13:33:27,  7.06s/it]
 75%|███████▌  | 21165/28080 [41:49:34<13:32:26,  7.05s/it]
                                                           
{'loss': 0.6112, 'learning_rate': 7.539263590456463e-05, 'epoch': 9.04}

 75%|███████▌  | 21165/28080 [41:49:34<13:32:26,  7.05s/it]
 75%|███████▌  | 21166/28080 [41:49:41<13:34:44,  7.07s/it]
                                                           
{'loss': 0.5998, 'learning_rate': 7.537199995858629e-05, 'epoch': 9.04}

 75%|███████▌  | 21166/28080 [41:49:41<13:34:44,  7.07s/it]
 75%|███████▌  | 21167/28080 [41:49:48<13:34:15,  7.07s/it]
                                                           
{'loss': 0.6043, 'learning_rate': 7.535136633585324e-05, 'epoch': 9.04}

 75%|███████▌  | 21167/28080 [41:49:48<13:34:15,  7.07s/it]
 75%|███████▌  | 21168/28080 [41:49:55<13:32:53,  7.06s/it]
                                                           
{'loss': 0.6161, 'learning_rate': 7.533073503664014e-05, 'epoch': 9.04}

 75%|███████▌  | 21168/28080 [41:49:55<13:32:53,  7.06s/it]
 75%|███████▌  | 21169/28080 [41:50:02<13:32:32,  7.05s/it]
                                                           
{'loss': 0.6094, 'learning_rate': 7.531010606122143e-05, 'epoch': 9.04}

 75%|███████▌  | 21169/28080 [41:50:02<13:32:32,  7.05s/it]
 75%|███████▌  | 21170/28080 [41:50:10<13:34:38,  7.07s/it]
                                                           
{'loss': 0.6391, 'learning_rate': 7.528947940987157e-05, 'epoch': 9.04}

 75%|███████▌  | 21170/28080 [41:50:10<13:34:38,  7.07s/it]
 75%|███████▌  | 21171/28080 [41:50:17<13:37:55,  7.10s/it]
                                                           
{'loss': 0.6148, 'learning_rate': 7.526885508286482e-05, 'epoch': 9.04}

 75%|███████▌  | 21171/28080 [41:50:17<13:37:55,  7.10s/it]
 75%|███████▌  | 21172/28080 [41:50:24<13:36:42,  7.09s/it]
                                                           
{'loss': 0.6058, 'learning_rate': 7.524823308047581e-05, 'epoch': 9.04}

 75%|███████▌  | 21172/28080 [41:50:24<13:36:42,  7.09s/it]
 75%|███████▌  | 21173/28080 [41:50:31<13:35:00,  7.08s/it]
                                                           
{'loss': 0.6032, 'learning_rate': 7.522761340297876e-05, 'epoch': 9.04}

 75%|███████▌  | 21173/28080 [41:50:31<13:35:00,  7.08s/it]
 75%|███████▌  | 21174/28080 [41:50:38<13:35:28,  7.08s/it]
                                                           
{'loss': 0.5859, 'learning_rate': 7.520699605064802e-05, 'epoch': 9.05}

 75%|███████▌  | 21174/28080 [41:50:38<13:35:28,  7.08s/it]
 75%|███████▌  | 21175/28080 [41:50:45<13:36:39,  7.10s/it]
                                                           
{'loss': 0.5906, 'learning_rate': 7.51863810237578e-05, 'epoch': 9.05}

 75%|███████▌  | 21175/28080 [41:50:45<13:36:39,  7.10s/it]
 75%|███████▌  | 21176/28080 [41:50:52<13:36:56,  7.10s/it]
                                                           
{'loss': 0.5923, 'learning_rate': 7.51657683225825e-05, 'epoch': 9.05}

 75%|███████▌  | 21176/28080 [41:50:52<13:36:56,  7.10s/it]
 75%|███████▌  | 21177/28080 [41:50:59<13:35:02,  7.08s/it]
                                                           
{'loss': 0.5943, 'learning_rate': 7.514515794739621e-05, 'epoch': 9.05}

 75%|███████▌  | 21177/28080 [41:50:59<13:35:02,  7.08s/it]
 75%|███████▌  | 21178/28080 [41:51:06<13:29:16,  7.04s/it]
                                                           
{'loss': 0.6353, 'learning_rate': 7.512454989847336e-05, 'epoch': 9.05}

 75%|███████▌  | 21178/28080 [41:51:06<13:29:16,  7.04s/it]
 75%|███████▌  | 21179/28080 [41:51:13<13:32:53,  7.07s/it]
                                                           
{'loss': 0.5988, 'learning_rate': 7.510394417608782e-05, 'epoch': 9.05}

 75%|███████▌  | 21179/28080 [41:51:13<13:32:53,  7.07s/it]
 75%|███████▌  | 21180/28080 [41:51:20<13:35:36,  7.09s/it]
                                                           
{'loss': 0.612, 'learning_rate': 7.508334078051393e-05, 'epoch': 9.05}

 75%|███████▌  | 21180/28080 [41:51:20<13:35:36,  7.09s/it]
 75%|███████▌  | 21181/28080 [41:51:28<13:35:00,  7.09s/it]
                                                           
{'loss': 0.6151, 'learning_rate': 7.506273971202568e-05, 'epoch': 9.05}

 75%|███████▌  | 21181/28080 [41:51:28<13:35:00,  7.09s/it]
 75%|███████▌  | 21182/28080 [41:51:35<13:36:41,  7.10s/it]
                                                           
{'loss': 0.5939, 'learning_rate': 7.504214097089729e-05, 'epoch': 9.05}

 75%|███████▌  | 21182/28080 [41:51:35<13:36:41,  7.10s/it]
 75%|███████▌  | 21183/28080 [41:51:42<13:37:47,  7.11s/it]
                                                           
{'loss': 0.6074, 'learning_rate': 7.502154455740271e-05, 'epoch': 9.05}

 75%|███████▌  | 21183/28080 [41:51:42<13:37:47,  7.11s/it]
 75%|███████▌  | 21184/28080 [41:51:49<13:36:49,  7.11s/it]
                                                           
{'loss': 0.593, 'learning_rate': 7.500095047181596e-05, 'epoch': 9.05}

 75%|███████▌  | 21184/28080 [41:51:49<13:36:49,  7.11s/it]
 75%|███████▌  | 21185/28080 [41:51:56<13:36:02,  7.10s/it]
                                                           
{'loss': 0.6028, 'learning_rate': 7.498035871441095e-05, 'epoch': 9.05}

 75%|███████▌  | 21185/28080 [41:51:56<13:36:02,  7.10s/it]
 75%|███████▌  | 21186/28080 [41:52:03<13:35:06,  7.09s/it]
                                                           
{'loss': 0.6067, 'learning_rate': 7.495976928546177e-05, 'epoch': 9.05}

 75%|███████▌  | 21186/28080 [41:52:03<13:35:06,  7.09s/it]
 75%|███████▌  | 21187/28080 [41:52:10<13:35:11,  7.10s/it]
                                                           
{'loss': 0.6021, 'learning_rate': 7.493918218524231e-05, 'epoch': 9.05}

 75%|███████▌  | 21187/28080 [41:52:10<13:35:11,  7.10s/it]
 75%|███████▌  | 21188/28080 [41:52:17<13:34:13,  7.09s/it]
                                                           
{'loss': 0.5861, 'learning_rate': 7.491859741402643e-05, 'epoch': 9.05}

 75%|███████▌  | 21188/28080 [41:52:17<13:34:13,  7.09s/it]
 75%|███████▌  | 21189/28080 [41:52:24<13:39:45,  7.14s/it]
                                                           
{'loss': 0.5862, 'learning_rate': 7.48980149720879e-05, 'epoch': 9.05}

 75%|███████▌  | 21189/28080 [41:52:24<13:39:45,  7.14s/it]
 75%|███████▌  | 21190/28080 [41:52:32<13:37:07,  7.12s/it]
                                                           
{'loss': 0.6251, 'learning_rate': 7.487743485970072e-05, 'epoch': 9.05}

 75%|███████▌  | 21190/28080 [41:52:32<13:37:07,  7.12s/it]
 75%|███████▌  | 21191/28080 [41:52:39<13:38:35,  7.13s/it]
                                                           
{'loss': 0.594, 'learning_rate': 7.48568570771386e-05, 'epoch': 9.05}

 75%|███████▌  | 21191/28080 [41:52:39<13:38:35,  7.13s/it]
 75%|███████▌  | 21192/28080 [41:52:46<13:33:43,  7.09s/it]
                                                           
{'loss': 0.5995, 'learning_rate': 7.483628162467532e-05, 'epoch': 9.05}

 75%|███████▌  | 21192/28080 [41:52:46<13:33:43,  7.09s/it]
 75%|███████▌  | 21193/28080 [41:52:53<13:37:32,  7.12s/it]
                                                           
{'loss': 0.5914, 'learning_rate': 7.48157085025846e-05, 'epoch': 9.05}

 75%|███████▌  | 21193/28080 [41:52:53<13:37:32,  7.12s/it]
 75%|███████▌  | 21194/28080 [41:53:00<13:34:27,  7.10s/it]
                                                           
{'loss': 0.5912, 'learning_rate': 7.479513771114008e-05, 'epoch': 9.05}

 75%|███████▌  | 21194/28080 [41:53:00<13:34:27,  7.10s/it]
 75%|███████▌  | 21195/28080 [41:53:07<13:32:20,  7.08s/it]
                                                           
{'loss': 0.6217, 'learning_rate': 7.477456925061557e-05, 'epoch': 9.05}

 75%|███████▌  | 21195/28080 [41:53:07<13:32:20,  7.08s/it]
 75%|███████▌  | 21196/28080 [41:53:14<13:30:35,  7.06s/it]
                                                           
{'loss': 0.6292, 'learning_rate': 7.475400312128459e-05, 'epoch': 9.05}

 75%|███████▌  | 21196/28080 [41:53:14<13:30:35,  7.06s/it]
 75%|███████▌  | 21197/28080 [41:53:21<13:30:33,  7.07s/it]
                                                           
{'loss': 0.6169, 'learning_rate': 7.473343932342095e-05, 'epoch': 9.06}

 75%|███████▌  | 21197/28080 [41:53:21<13:30:33,  7.07s/it]
 75%|███████▌  | 21198/28080 [41:53:28<13:28:28,  7.05s/it]
                                                           
{'loss': 0.6326, 'learning_rate': 7.471287785729791e-05, 'epoch': 9.06}

 75%|███████▌  | 21198/28080 [41:53:28<13:28:28,  7.05s/it]
 75%|███████▌  | 21199/28080 [41:53:35<13:30:38,  7.07s/it]
                                                           
{'loss': 0.6022, 'learning_rate': 7.469231872318929e-05, 'epoch': 9.06}

 75%|███████▌  | 21199/28080 [41:53:35<13:30:38,  7.07s/it]
 75%|███████▌  | 21200/28080 [41:53:42<13:30:16,  7.07s/it]
                                                           
{'loss': 0.6086, 'learning_rate': 7.467176192136846e-05, 'epoch': 9.06}

 75%|███████▌  | 21200/28080 [41:53:42<13:30:16,  7.07s/it]
 76%|███████▌  | 21201/28080 [41:53:49<13:28:21,  7.05s/it]
                                                           
{'loss': 0.6023, 'learning_rate': 7.465120745210901e-05, 'epoch': 9.06}

 76%|███████▌  | 21201/28080 [41:53:49<13:28:21,  7.05s/it]
 76%|███████▌  | 21202/28080 [41:53:56<13:27:34,  7.04s/it]
                                                           
{'loss': 0.6174, 'learning_rate': 7.463065531568436e-05, 'epoch': 9.06}

 76%|███████▌  | 21202/28080 [41:53:56<13:27:34,  7.04s/it]
 76%|███████▌  | 21203/28080 [41:54:03<13:25:45,  7.03s/it]
                                                           
{'loss': 0.6275, 'learning_rate': 7.461010551236793e-05, 'epoch': 9.06}

 76%|███████▌  | 21203/28080 [41:54:03<13:25:45,  7.03s/it]
 76%|███████▌  | 21204/28080 [41:54:10<13:30:16,  7.07s/it]
                                                           
{'loss': 0.6076, 'learning_rate': 7.458955804243304e-05, 'epoch': 9.06}

 76%|███████▌  | 21204/28080 [41:54:10<13:30:16,  7.07s/it]
 76%|███████▌  | 21205/28080 [41:54:18<13:33:28,  7.10s/it]
                                                           
{'loss': 0.6049, 'learning_rate': 7.456901290615314e-05, 'epoch': 9.06}

 76%|███████▌  | 21205/28080 [41:54:18<13:33:28,  7.10s/it]
 76%|███████▌  | 21206/28080 [41:54:25<13:31:33,  7.08s/it]
                                                           
{'loss': 0.6124, 'learning_rate': 7.454847010380158e-05, 'epoch': 9.06}

 76%|███████▌  | 21206/28080 [41:54:25<13:31:33,  7.08s/it]
 76%|███████▌  | 21207/28080 [41:54:32<13:31:35,  7.08s/it]
                                                           
{'loss': 0.6132, 'learning_rate': 7.452792963565163e-05, 'epoch': 9.06}

 76%|███████▌  | 21207/28080 [41:54:32<13:31:35,  7.08s/it]
 76%|███████▌  | 21208/28080 [41:54:39<13:33:25,  7.10s/it]
                                                           
{'loss': 0.6072, 'learning_rate': 7.450739150197646e-05, 'epoch': 9.06}

 76%|███████▌  | 21208/28080 [41:54:39<13:33:25,  7.10s/it]
 76%|███████▌  | 21209/28080 [41:54:46<13:30:48,  7.08s/it]
                                                           
{'loss': 0.6094, 'learning_rate': 7.44868557030495e-05, 'epoch': 9.06}

 76%|███████▌  | 21209/28080 [41:54:46<13:30:48,  7.08s/it]
 76%|███████▌  | 21210/28080 [41:54:53<13:30:28,  7.08s/it]
                                                           
{'loss': 0.5987, 'learning_rate': 7.446632223914376e-05, 'epoch': 9.06}

 76%|███████▌  | 21210/28080 [41:54:53<13:30:28,  7.08s/it]
 76%|███████▌  | 21211/28080 [41:55:00<13:26:58,  7.05s/it]
                                                           
{'loss': 0.6196, 'learning_rate': 7.444579111053266e-05, 'epoch': 9.06}

 76%|███████▌  | 21211/28080 [41:55:00<13:26:58,  7.05s/it]
 76%|███████▌  | 21212/28080 [41:55:07<13:25:45,  7.04s/it]
                                                           
{'loss': 0.626, 'learning_rate': 7.442526231748905e-05, 'epoch': 9.06}

 76%|███████▌  | 21212/28080 [41:55:07<13:25:45,  7.04s/it]
 76%|███████▌  | 21213/28080 [41:55:14<13:27:15,  7.05s/it]
                                                           
{'loss': 0.6153, 'learning_rate': 7.44047358602863e-05, 'epoch': 9.06}

 76%|███████▌  | 21213/28080 [41:55:14<13:27:15,  7.05s/it]
 76%|███████▌  | 21214/28080 [41:55:21<13:30:20,  7.08s/it]
                                                           
{'loss': 0.6075, 'learning_rate': 7.438421173919727e-05, 'epoch': 9.06}

 76%|███████▌  | 21214/28080 [41:55:21<13:30:20,  7.08s/it]
 76%|███████▌  | 21215/28080 [41:55:28<13:26:27,  7.05s/it]
                                                           
{'loss': 0.6218, 'learning_rate': 7.436368995449525e-05, 'epoch': 9.06}

 76%|███████▌  | 21215/28080 [41:55:28<13:26:27,  7.05s/it]
 76%|███████▌  | 21216/28080 [41:55:35<13:28:13,  7.06s/it]
                                                           
{'loss': 0.5939, 'learning_rate': 7.434317050645312e-05, 'epoch': 9.06}

 76%|███████▌  | 21216/28080 [41:55:35<13:28:13,  7.06s/it]
 76%|███████▌  | 21217/28080 [41:55:42<13:27:17,  7.06s/it]
                                                           
{'loss': 0.5768, 'learning_rate': 7.432265339534389e-05, 'epoch': 9.06}

 76%|███████▌  | 21217/28080 [41:55:42<13:27:17,  7.06s/it]
 76%|███████▌  | 21218/28080 [41:55:49<13:27:46,  7.06s/it]
                                                           
{'loss': 0.6076, 'learning_rate': 7.43021386214405e-05, 'epoch': 9.06}

 76%|███████▌  | 21218/28080 [41:55:49<13:27:46,  7.06s/it]
 76%|███████▌  | 21219/28080 [41:55:57<13:28:47,  7.07s/it]
                                                           
{'loss': 0.6154, 'learning_rate': 7.428162618501586e-05, 'epoch': 9.06}

 76%|███████▌  | 21219/28080 [41:55:57<13:28:47,  7.07s/it]
 76%|███████▌  | 21220/28080 [41:56:04<13:30:48,  7.09s/it]
                                                           
{'loss': 0.5994, 'learning_rate': 7.426111608634294e-05, 'epoch': 9.06}

 76%|███████▌  | 21220/28080 [41:56:04<13:30:48,  7.09s/it]
 76%|███████▌  | 21221/28080 [41:56:11<13:33:02,  7.11s/it]
                                                           
{'loss': 0.6153, 'learning_rate': 7.42406083256946e-05, 'epoch': 9.07}

 76%|███████▌  | 21221/28080 [41:56:11<13:33:02,  7.11s/it]
 76%|███████▌  | 21222/28080 [41:56:18<13:31:43,  7.10s/it]
                                                           
{'loss': 0.5963, 'learning_rate': 7.422010290334363e-05, 'epoch': 9.07}

 76%|███████▌  | 21222/28080 [41:56:18<13:31:43,  7.10s/it]
 76%|███████▌  | 21223/28080 [41:56:25<13:25:37,  7.05s/it]
                                                           
{'loss': 0.6284, 'learning_rate': 7.419959981956278e-05, 'epoch': 9.07}

 76%|███████▌  | 21223/28080 [41:56:25<13:25:37,  7.05s/it]
 76%|███████▌  | 21224/28080 [41:56:32<13:25:31,  7.05s/it]
                                                           
{'loss': 0.6018, 'learning_rate': 7.417909907462498e-05, 'epoch': 9.07}

 76%|███████▌  | 21224/28080 [41:56:32<13:25:31,  7.05s/it]
 76%|███████▌  | 21225/28080 [41:56:39<13:27:32,  7.07s/it]
                                                           
{'loss': 0.6008, 'learning_rate': 7.415860066880279e-05, 'epoch': 9.07}

 76%|███████▌  | 21225/28080 [41:56:39<13:27:32,  7.07s/it]
 76%|███████▌  | 21226/28080 [41:56:46<13:26:55,  7.06s/it]
                                                           
{'loss': 0.5971, 'learning_rate': 7.413810460236917e-05, 'epoch': 9.07}

 76%|███████▌  | 21226/28080 [41:56:46<13:26:55,  7.06s/it]
 76%|███████▌  | 21227/28080 [41:56:53<13:27:40,  7.07s/it]
                                                           
{'loss': 0.5985, 'learning_rate': 7.411761087559648e-05, 'epoch': 9.07}

 76%|███████▌  | 21227/28080 [41:56:53<13:27:40,  7.07s/it]
 76%|███████▌  | 21228/28080 [41:57:00<13:29:52,  7.09s/it]
                                                           
{'loss': 0.578, 'learning_rate': 7.409711948875764e-05, 'epoch': 9.07}

 76%|███████▌  | 21228/28080 [41:57:00<13:29:52,  7.09s/it]
 76%|███████▌  | 21229/28080 [41:57:07<13:28:41,  7.08s/it]
                                                           
{'loss': 0.6086, 'learning_rate': 7.407663044212503e-05, 'epoch': 9.07}

 76%|███████▌  | 21229/28080 [41:57:07<13:28:41,  7.08s/it]
 76%|███████▌  | 21230/28080 [41:57:15<13:31:44,  7.11s/it]
                                                           
{'loss': 0.5972, 'learning_rate': 7.405614373597147e-05, 'epoch': 9.07}

 76%|███████▌  | 21230/28080 [41:57:15<13:31:44,  7.11s/it]
 76%|███████▌  | 21231/28080 [41:57:22<13:33:09,  7.12s/it]
                                                           
{'loss': 0.6042, 'learning_rate': 7.403565937056941e-05, 'epoch': 9.07}

 76%|███████▌  | 21231/28080 [41:57:22<13:33:09,  7.12s/it]
 76%|███████▌  | 21232/28080 [41:57:29<13:32:55,  7.12s/it]
                                                           
{'loss': 0.5962, 'learning_rate': 7.401517734619136e-05, 'epoch': 9.07}

 76%|███████▌  | 21232/28080 [41:57:29<13:32:55,  7.12s/it]
 76%|███████▌  | 21233/28080 [41:57:36<13:30:22,  7.10s/it]
                                                           
{'loss': 0.6237, 'learning_rate': 7.399469766310973e-05, 'epoch': 9.07}

 76%|███████▌  | 21233/28080 [41:57:36<13:30:22,  7.10s/it]
 76%|███████▌  | 21234/28080 [41:57:43<13:27:04,  7.07s/it]
                                                           
{'loss': 0.616, 'learning_rate': 7.397422032159717e-05, 'epoch': 9.07}

 76%|███████▌  | 21234/28080 [41:57:43<13:27:04,  7.07s/it]
 76%|███████▌  | 21235/28080 [41:57:50<13:25:48,  7.06s/it]
                                                           
{'loss': 0.5974, 'learning_rate': 7.3953745321926e-05, 'epoch': 9.07}

 76%|███████▌  | 21235/28080 [41:57:50<13:25:48,  7.06s/it]
 76%|███████▌  | 21236/28080 [41:57:57<13:22:17,  7.03s/it]
                                                           
{'loss': 0.6062, 'learning_rate': 7.393327266436866e-05, 'epoch': 9.07}

 76%|███████▌  | 21236/28080 [41:57:57<13:22:17,  7.03s/it]
 76%|███████▌  | 21237/28080 [41:58:04<13:27:22,  7.08s/it]
                                                           
{'loss': 0.6069, 'learning_rate': 7.39128023491974e-05, 'epoch': 9.07}

 76%|███████▌  | 21237/28080 [41:58:04<13:27:22,  7.08s/it]
 76%|███████▌  | 21238/28080 [41:58:11<13:28:07,  7.09s/it]
                                                           
{'loss': 0.6104, 'learning_rate': 7.389233437668468e-05, 'epoch': 9.07}

 76%|███████▌  | 21238/28080 [41:58:11<13:28:07,  7.09s/it]
 76%|███████▌  | 21239/28080 [41:58:18<13:30:28,  7.11s/it]
                                                           
{'loss': 0.5923, 'learning_rate': 7.387186874710275e-05, 'epoch': 9.07}

 76%|███████▌  | 21239/28080 [41:58:18<13:30:28,  7.11s/it]
 76%|███████▌  | 21240/28080 [41:58:25<13:29:06,  7.10s/it]
                                                           
{'loss': 0.6156, 'learning_rate': 7.385140546072402e-05, 'epoch': 9.07}

 76%|███████▌  | 21240/28080 [41:58:25<13:29:06,  7.10s/it]
 76%|███████▌  | 21241/28080 [41:58:33<13:30:36,  7.11s/it]
                                                           
{'loss': 0.5987, 'learning_rate': 7.383094451782058e-05, 'epoch': 9.07}

 76%|███████▌  | 21241/28080 [41:58:33<13:30:36,  7.11s/it]
 76%|███████▌  | 21242/28080 [41:58:40<13:29:27,  7.10s/it]
                                                           
{'loss': 0.6295, 'learning_rate': 7.381048591866457e-05, 'epoch': 9.07}

 76%|███████▌  | 21242/28080 [41:58:40<13:29:27,  7.10s/it]
 76%|███████▌  | 21243/28080 [41:58:47<13:28:00,  7.09s/it]
                                                           
{'loss': 0.6003, 'learning_rate': 7.379002966352838e-05, 'epoch': 9.07}

 76%|███████▌  | 21243/28080 [41:58:47<13:28:00,  7.09s/it]
 76%|███████▌  | 21244/28080 [41:58:54<13:29:50,  7.11s/it]
                                                           
{'loss': 0.5893, 'learning_rate': 7.376957575268395e-05, 'epoch': 9.08}

 76%|███████▌  | 21244/28080 [41:58:54<13:29:50,  7.11s/it]
 76%|███████▌  | 21245/28080 [41:59:01<13:25:53,  7.07s/it]
                                                           
{'loss': 0.5987, 'learning_rate': 7.37491241864037e-05, 'epoch': 9.08}

 76%|███████▌  | 21245/28080 [41:59:01<13:25:53,  7.07s/it]
 76%|███████▌  | 21246/28080 [41:59:08<13:24:08,  7.06s/it]
                                                           
{'loss': 0.6166, 'learning_rate': 7.372867496495935e-05, 'epoch': 9.08}

 76%|███████▌  | 21246/28080 [41:59:08<13:24:08,  7.06s/it]
 76%|███████▌  | 21247/28080 [41:59:15<13:25:56,  7.08s/it]
                                                           
{'loss': 0.5928, 'learning_rate': 7.37082280886232e-05, 'epoch': 9.08}

 76%|███████▌  | 21247/28080 [41:59:15<13:25:56,  7.08s/it]
 76%|███████▌  | 21248/28080 [41:59:22<13:25:50,  7.08s/it]
                                                           
{'loss': 0.6272, 'learning_rate': 7.368778355766714e-05, 'epoch': 9.08}

 76%|███████▌  | 21248/28080 [41:59:22<13:25:50,  7.08s/it]
 76%|███████▌  | 21249/28080 [41:59:29<13:24:50,  7.07s/it]
                                                           
{'loss': 0.6109, 'learning_rate': 7.36673413723633e-05, 'epoch': 9.08}

 76%|███████▌  | 21249/28080 [41:59:29<13:24:50,  7.07s/it]
 76%|███████▌  | 21250/28080 [41:59:36<13:26:46,  7.09s/it]
                                                           
{'loss': 0.6316, 'learning_rate': 7.36469015329836e-05, 'epoch': 9.08}

 76%|███████▌  | 21250/28080 [41:59:36<13:26:46,  7.09s/it]
 76%|███████▌  | 21251/28080 [41:59:43<13:27:26,  7.09s/it]
                                                           
{'loss': 0.5939, 'learning_rate': 7.362646403979992e-05, 'epoch': 9.08}

 76%|███████▌  | 21251/28080 [41:59:43<13:27:26,  7.09s/it]
 76%|███████▌  | 21252/28080 [41:59:50<13:27:12,  7.09s/it]
                                                           
{'loss': 0.6111, 'learning_rate': 7.360602889308406e-05, 'epoch': 9.08}

 76%|███████▌  | 21252/28080 [41:59:50<13:27:12,  7.09s/it]
 76%|███████▌  | 21253/28080 [41:59:57<13:26:03,  7.08s/it]
                                                           
{'loss': 0.608, 'learning_rate': 7.358559609310816e-05, 'epoch': 9.08}

 76%|███████▌  | 21253/28080 [41:59:57<13:26:03,  7.08s/it]
 76%|███████▌  | 21254/28080 [42:00:05<13:27:18,  7.10s/it]
                                                           
{'loss': 0.6143, 'learning_rate': 7.356516564014387e-05, 'epoch': 9.08}

 76%|███████▌  | 21254/28080 [42:00:05<13:27:18,  7.10s/it]
 76%|███████▌  | 21255/28080 [42:00:12<13:27:34,  7.10s/it]
                                                           
{'loss': 0.6108, 'learning_rate': 7.354473753446303e-05, 'epoch': 9.08}

 76%|███████▌  | 21255/28080 [42:00:12<13:27:34,  7.10s/it]
 76%|███████▌  | 21256/28080 [42:00:19<13:25:38,  7.08s/it]
                                                           
{'loss': 0.6017, 'learning_rate': 7.352431177633737e-05, 'epoch': 9.08}

 76%|███████▌  | 21256/28080 [42:00:19<13:25:38,  7.08s/it]
 76%|███████▌  | 21257/28080 [42:00:26<13:25:07,  7.08s/it]
                                                           
{'loss': 0.5999, 'learning_rate': 7.350388836603872e-05, 'epoch': 9.08}

 76%|███████▌  | 21257/28080 [42:00:26<13:25:07,  7.08s/it]
 76%|███████▌  | 21258/28080 [42:00:33<13:28:25,  7.11s/it]
                                                           
{'loss': 0.5919, 'learning_rate': 7.34834673038387e-05, 'epoch': 9.08}

 76%|███████▌  | 21258/28080 [42:00:33<13:28:25,  7.11s/it]
 76%|███████▌  | 21259/28080 [42:00:40<13:29:30,  7.12s/it]
                                                           
{'loss': 0.5983, 'learning_rate': 7.346304859000921e-05, 'epoch': 9.08}

 76%|███████▌  | 21259/28080 [42:00:40<13:29:30,  7.12s/it]
 76%|███████▌  | 21260/28080 [42:00:47<13:27:55,  7.11s/it]
                                                           
{'loss': 0.5612, 'learning_rate': 7.344263222482156e-05, 'epoch': 9.08}

 76%|███████▌  | 21260/28080 [42:00:47<13:27:55,  7.11s/it]
 76%|███████▌  | 21261/28080 [42:00:54<13:23:13,  7.07s/it]
                                                           
{'loss': 0.6159, 'learning_rate': 7.342221820854764e-05, 'epoch': 9.08}

 76%|███████▌  | 21261/28080 [42:00:54<13:23:13,  7.07s/it]
 76%|███████▌  | 21262/28080 [42:01:01<13:22:44,  7.06s/it]
                                                           
{'loss': 0.5943, 'learning_rate': 7.340180654145883e-05, 'epoch': 9.08}

 76%|███████▌  | 21262/28080 [42:01:01<13:22:44,  7.06s/it]
 76%|███████▌  | 21263/28080 [42:01:08<13:22:07,  7.06s/it]
                                                           
{'loss': 0.6287, 'learning_rate': 7.338139722382692e-05, 'epoch': 9.08}

 76%|███████▌  | 21263/28080 [42:01:08<13:22:07,  7.06s/it]
 76%|███████▌  | 21264/28080 [42:01:15<13:24:40,  7.08s/it]
                                                           
{'loss': 0.6015, 'learning_rate': 7.336099025592327e-05, 'epoch': 9.08}

 76%|███████▌  | 21264/28080 [42:01:15<13:24:40,  7.08s/it]
 76%|███████▌  | 21265/28080 [42:01:23<13:27:51,  7.11s/it]
                                                           
{'loss': 0.6068, 'learning_rate': 7.334058563801946e-05, 'epoch': 9.08}

 76%|███████▌  | 21265/28080 [42:01:23<13:27:51,  7.11s/it]
 76%|███████▌  | 21266/28080 [42:01:30<13:30:30,  7.14s/it]
                                                           
{'loss': 0.5996, 'learning_rate': 7.332018337038688e-05, 'epoch': 9.08}

 76%|███████▌  | 21266/28080 [42:01:30<13:30:30,  7.14s/it]
 76%|███████▌  | 21267/28080 [42:01:37<13:28:31,  7.12s/it]
                                                           
{'loss': 0.6147, 'learning_rate': 7.329978345329691e-05, 'epoch': 9.09}

 76%|███████▌  | 21267/28080 [42:01:37<13:28:31,  7.12s/it]
 76%|███████▌  | 21268/28080 [42:01:44<13:23:57,  7.08s/it]
                                                           
{'loss': 0.6199, 'learning_rate': 7.327938588702112e-05, 'epoch': 9.09}

 76%|███████▌  | 21268/28080 [42:01:44<13:23:57,  7.08s/it]
 76%|███████▌  | 21269/28080 [42:01:51<13:18:22,  7.03s/it]
                                                           
{'loss': 0.6273, 'learning_rate': 7.325899067183078e-05, 'epoch': 9.09}

 76%|███████▌  | 21269/28080 [42:01:51<13:18:22,  7.03s/it]
 76%|███████▌  | 21270/28080 [42:01:58<13:19:26,  7.04s/it]
                                                           
{'loss': 0.5918, 'learning_rate': 7.323859780799724e-05, 'epoch': 9.09}

 76%|███████▌  | 21270/28080 [42:01:58<13:19:26,  7.04s/it]
 76%|███████▌  | 21271/28080 [42:02:05<13:21:38,  7.06s/it]
                                                           
{'loss': 0.6116, 'learning_rate': 7.321820729579173e-05, 'epoch': 9.09}

 76%|███████▌  | 21271/28080 [42:02:05<13:21:38,  7.06s/it]
 76%|███████▌  | 21272/28080 [42:02:12<13:22:38,  7.07s/it]
                                                           
{'loss': 0.6208, 'learning_rate': 7.319781913548568e-05, 'epoch': 9.09}

 76%|███████▌  | 21272/28080 [42:02:12<13:22:38,  7.07s/it]
 76%|███████▌  | 21273/28080 [42:02:19<13:24:00,  7.09s/it]
                                                           
{'loss': 0.5868, 'learning_rate': 7.317743332735022e-05, 'epoch': 9.09}

 76%|███████▌  | 21273/28080 [42:02:19<13:24:00,  7.09s/it]
 76%|███████▌  | 21274/28080 [42:02:26<13:27:12,  7.12s/it]
                                                           
{'loss': 0.5973, 'learning_rate': 7.315704987165661e-05, 'epoch': 9.09}

 76%|███████▌  | 21274/28080 [42:02:26<13:27:12,  7.12s/it]
 76%|███████▌  | 21275/28080 [42:02:33<13:26:50,  7.11s/it]
                                                           
{'loss': 0.5839, 'learning_rate': 7.313666876867595e-05, 'epoch': 9.09}

 76%|███████▌  | 21275/28080 [42:02:34<13:26:50,  7.11s/it]
 76%|███████▌  | 21276/28080 [42:02:41<13:27:53,  7.12s/it]
                                                           
{'loss': 0.5939, 'learning_rate': 7.31162900186795e-05, 'epoch': 9.09}

 76%|███████▌  | 21276/28080 [42:02:41<13:27:53,  7.12s/it]
 76%|███████▌  | 21277/28080 [42:02:48<13:26:26,  7.11s/it]
                                                           
{'loss': 0.5886, 'learning_rate': 7.309591362193827e-05, 'epoch': 9.09}

 76%|███████▌  | 21277/28080 [42:02:48<13:26:26,  7.11s/it]
 76%|███████▌  | 21278/28080 [42:02:55<13:25:16,  7.10s/it]
                                                           
{'loss': 0.6236, 'learning_rate': 7.307553957872349e-05, 'epoch': 9.09}

 76%|███████▌  | 21278/28080 [42:02:55<13:25:16,  7.10s/it]
 76%|███████▌  | 21279/28080 [42:03:02<13:25:09,  7.10s/it]
                                                           
{'loss': 0.6108, 'learning_rate': 7.30551678893061e-05, 'epoch': 9.09}

 76%|███████▌  | 21279/28080 [42:03:02<13:25:09,  7.10s/it]
 76%|███████▌  | 21280/28080 [42:03:09<13:24:05,  7.09s/it]
                                                           
{'loss': 0.6099, 'learning_rate': 7.30347985539572e-05, 'epoch': 9.09}

 76%|███████▌  | 21280/28080 [42:03:09<13:24:05,  7.09s/it]
 76%|███████▌  | 21281/28080 [42:03:16<13:23:41,  7.09s/it]
                                                           
{'loss': 0.5821, 'learning_rate': 7.301443157294766e-05, 'epoch': 9.09}

 76%|███████▌  | 21281/28080 [42:03:16<13:23:41,  7.09s/it]
 76%|███████▌  | 21282/28080 [42:03:23<13:25:31,  7.11s/it]
                                                           
{'loss': 0.6111, 'learning_rate': 7.299406694654856e-05, 'epoch': 9.09}

 76%|███████▌  | 21282/28080 [42:03:23<13:25:31,  7.11s/it]
 76%|███████▌  | 21283/28080 [42:03:30<13:23:08,  7.09s/it]
                                                           
{'loss': 0.5941, 'learning_rate': 7.29737046750308e-05, 'epoch': 9.09}

 76%|███████▌  | 21283/28080 [42:03:30<13:23:08,  7.09s/it]
 76%|███████▌  | 21284/28080 [42:03:37<13:21:46,  7.08s/it]
                                                           
{'loss': 0.6045, 'learning_rate': 7.29533447586653e-05, 'epoch': 9.09}

 76%|███████▌  | 21284/28080 [42:03:37<13:21:46,  7.08s/it]
 76%|███████▌  | 21285/28080 [42:03:44<13:22:42,  7.09s/it]
                                                           
{'loss': 0.6049, 'learning_rate': 7.293298719772282e-05, 'epoch': 9.09}

 76%|███████▌  | 21285/28080 [42:03:44<13:22:42,  7.09s/it]
 76%|███████▌  | 21286/28080 [42:03:51<13:16:22,  7.03s/it]
                                                           
{'loss': 0.6127, 'learning_rate': 7.291263199247435e-05, 'epoch': 9.09}

 76%|███████▌  | 21286/28080 [42:03:51<13:16:22,  7.03s/it]
 76%|███████▌  | 21287/28080 [42:03:58<13:19:01,  7.06s/it]
                                                           
{'loss': 0.611, 'learning_rate': 7.289227914319052e-05, 'epoch': 9.09}

 76%|███████▌  | 21287/28080 [42:03:58<13:19:01,  7.06s/it]
 76%|███████▌  | 21288/28080 [42:04:06<13:18:50,  7.06s/it]
                                                           
{'loss': 0.5976, 'learning_rate': 7.28719286501424e-05, 'epoch': 9.09}

 76%|███████▌  | 21288/28080 [42:04:06<13:18:50,  7.06s/it]
 76%|███████▌  | 21289/28080 [42:04:13<13:22:00,  7.09s/it]
                                                           
{'loss': 0.6073, 'learning_rate': 7.285158051360036e-05, 'epoch': 9.09}

 76%|███████▌  | 21289/28080 [42:04:13<13:22:00,  7.09s/it]
 76%|███████▌  | 21290/28080 [42:04:20<13:24:15,  7.11s/it]
                                                           
{'loss': 0.6134, 'learning_rate': 7.283123473383535e-05, 'epoch': 9.09}

 76%|███████▌  | 21290/28080 [42:04:20<13:24:15,  7.11s/it]
 76%|███████▌  | 21291/28080 [42:04:27<13:21:32,  7.08s/it]
                                                           
{'loss': 0.6132, 'learning_rate': 7.281089131111799e-05, 'epoch': 9.1}

 76%|███████▌  | 21291/28080 [42:04:27<13:21:32,  7.08s/it]
 76%|███████▌  | 21292/28080 [42:04:34<13:23:08,  7.10s/it]
                                                           
{'loss': 0.6146, 'learning_rate': 7.279055024571887e-05, 'epoch': 9.1}

 76%|███████▌  | 21292/28080 [42:04:34<13:23:08,  7.10s/it]
 76%|███████▌  | 21293/28080 [42:04:41<13:22:05,  7.09s/it]
                                                           
{'loss': 0.6105, 'learning_rate': 7.277021153790881e-05, 'epoch': 9.1}

 76%|███████▌  | 21293/28080 [42:04:41<13:22:05,  7.09s/it]
 76%|███████▌  | 21294/28080 [42:04:48<13:20:59,  7.08s/it]
                                                           
{'loss': 0.6146, 'learning_rate': 7.274987518795807e-05, 'epoch': 9.1}

 76%|███████▌  | 21294/28080 [42:04:48<13:20:59,  7.08s/it]
 76%|███████▌  | 21295/28080 [42:04:55<13:21:42,  7.09s/it]
                                                           
{'loss': 0.5947, 'learning_rate': 7.272954119613748e-05, 'epoch': 9.1}

 76%|███████▌  | 21295/28080 [42:04:55<13:21:42,  7.09s/it]
 76%|███████▌  | 21296/28080 [42:05:02<13:17:48,  7.06s/it]
                                                           
{'loss': 0.5907, 'learning_rate': 7.270920956271737e-05, 'epoch': 9.1}

 76%|███████▌  | 21296/28080 [42:05:02<13:17:48,  7.06s/it]
 76%|███████▌  | 21297/28080 [42:05:09<13:20:38,  7.08s/it]
                                                           
{'loss': 0.5925, 'learning_rate': 7.268888028796843e-05, 'epoch': 9.1}

 76%|███████▌  | 21297/28080 [42:05:09<13:20:38,  7.08s/it]
 76%|███████▌  | 21298/28080 [42:05:16<13:14:18,  7.03s/it]
                                                           
{'loss': 0.6379, 'learning_rate': 7.266855337216099e-05, 'epoch': 9.1}

 76%|███████▌  | 21298/28080 [42:05:16<13:14:18,  7.03s/it]
 76%|███████▌  | 21299/28080 [42:05:23<13:11:23,  7.00s/it]
                                                           
{'loss': 0.6142, 'learning_rate': 7.264822881556552e-05, 'epoch': 9.1}

 76%|███████▌  | 21299/28080 [42:05:23<13:11:23,  7.00s/it]
 76%|███████▌  | 21300/28080 [42:05:30<13:12:40,  7.01s/it]
                                                           
{'loss': 0.6101, 'learning_rate': 7.262790661845234e-05, 'epoch': 9.1}

 76%|███████▌  | 21300/28080 [42:05:30<13:12:40,  7.01s/it]
 76%|███████▌  | 21301/28080 [42:05:37<13:14:39,  7.03s/it]
                                                           
{'loss': 0.6122, 'learning_rate': 7.260758678109191e-05, 'epoch': 9.1}

 76%|███████▌  | 21301/28080 [42:05:37<13:14:39,  7.03s/it]
 76%|███████▌  | 21302/28080 [42:05:44<13:13:07,  7.02s/it]
                                                           
{'loss': 0.6143, 'learning_rate': 7.258726930375456e-05, 'epoch': 9.1}

 76%|███████▌  | 21302/28080 [42:05:44<13:13:07,  7.02s/it]
 76%|███████▌  | 21303/28080 [42:05:51<13:15:37,  7.04s/it]
                                                           
{'loss': 0.616, 'learning_rate': 7.256695418671058e-05, 'epoch': 9.1}

 76%|███████▌  | 21303/28080 [42:05:51<13:15:37,  7.04s/it]
 76%|███████▌  | 21304/28080 [42:05:58<13:16:22,  7.05s/it]
                                                           
{'loss': 0.6116, 'learning_rate': 7.254664143023013e-05, 'epoch': 9.1}

 76%|███████▌  | 21304/28080 [42:05:58<13:16:22,  7.05s/it]
 76%|███████▌  | 21305/28080 [42:06:06<13:18:57,  7.08s/it]
                                                           
{'loss': 0.6285, 'learning_rate': 7.252633103458365e-05, 'epoch': 9.1}

 76%|███████▌  | 21305/28080 [42:06:06<13:18:57,  7.08s/it]
 76%|███████▌  | 21306/28080 [42:06:13<13:20:31,  7.09s/it]
                                                           
{'loss': 0.5832, 'learning_rate': 7.250602300004113e-05, 'epoch': 9.1}

 76%|███████▌  | 21306/28080 [42:06:13<13:20:31,  7.09s/it]
 76%|███████▌  | 21307/28080 [42:06:20<13:20:58,  7.10s/it]
                                                           
{'loss': 0.6, 'learning_rate': 7.248571732687304e-05, 'epoch': 9.1}

 76%|███████▌  | 21307/28080 [42:06:20<13:20:58,  7.10s/it]
 76%|███████▌  | 21308/28080 [42:06:27<13:22:43,  7.11s/it]
                                                           
{'loss': 0.6163, 'learning_rate': 7.246541401534918e-05, 'epoch': 9.1}

 76%|███████▌  | 21308/28080 [42:06:27<13:22:43,  7.11s/it]
 76%|███████▌  | 21309/28080 [42:06:34<13:16:08,  7.05s/it]
                                                           
{'loss': 0.6176, 'learning_rate': 7.244511306573992e-05, 'epoch': 9.1}

 76%|███████▌  | 21309/28080 [42:06:34<13:16:08,  7.05s/it]
 76%|███████▌  | 21310/28080 [42:06:41<13:12:53,  7.03s/it]
                                                           
{'loss': 0.6207, 'learning_rate': 7.242481447831519e-05, 'epoch': 9.1}

 76%|███████▌  | 21310/28080 [42:06:41<13:12:53,  7.03s/it]
 76%|███████▌  | 21311/28080 [42:06:48<13:12:43,  7.03s/it]
                                                           
{'loss': 0.5912, 'learning_rate': 7.240451825334518e-05, 'epoch': 9.1}

 76%|███████▌  | 21311/28080 [42:06:48<13:12:43,  7.03s/it]
 76%|███████▌  | 21312/28080 [42:06:55<13:15:55,  7.06s/it]
                                                           
{'loss': 0.5947, 'learning_rate': 7.238422439109985e-05, 'epoch': 9.1}

 76%|███████▌  | 21312/28080 [42:06:55<13:15:55,  7.06s/it]
 76%|███████▌  | 21313/28080 [42:07:02<13:19:01,  7.08s/it]
                                                           
{'loss': 0.5916, 'learning_rate': 7.236393289184918e-05, 'epoch': 9.1}

 76%|███████▌  | 21313/28080 [42:07:02<13:19:01,  7.08s/it]
 76%|███████▌  | 21314/28080 [42:07:09<13:20:19,  7.10s/it]
                                                           
{'loss': 0.5977, 'learning_rate': 7.234364375586302e-05, 'epoch': 9.11}

 76%|███████▌  | 21314/28080 [42:07:09<13:20:19,  7.10s/it]
 76%|███████▌  | 21315/28080 [42:07:16<13:17:25,  7.07s/it]
                                                           
{'loss': 0.5983, 'learning_rate': 7.232335698341149e-05, 'epoch': 9.11}

 76%|███████▌  | 21315/28080 [42:07:16<13:17:25,  7.07s/it]
 76%|███████▌  | 21316/28080 [42:07:23<13:15:59,  7.06s/it]
                                                           
{'loss': 0.6177, 'learning_rate': 7.23030725747644e-05, 'epoch': 9.11}

 76%|███████▌  | 21316/28080 [42:07:23<13:15:59,  7.06s/it]
 76%|███████▌  | 21317/28080 [42:07:30<13:15:26,  7.06s/it]
                                                           
{'loss': 0.5963, 'learning_rate': 7.22827905301916e-05, 'epoch': 9.11}

 76%|███████▌  | 21317/28080 [42:07:30<13:15:26,  7.06s/it]
 76%|███████▌  | 21318/28080 [42:07:38<13:17:11,  7.07s/it]
                                                           
{'loss': 0.6015, 'learning_rate': 7.226251084996297e-05, 'epoch': 9.11}

 76%|███████▌  | 21318/28080 [42:07:38<13:17:11,  7.07s/it]
 76%|███████▌  | 21319/28080 [42:07:45<13:18:44,  7.09s/it]
                                                           
{'loss': 0.5687, 'learning_rate': 7.224223353434814e-05, 'epoch': 9.11}

 76%|███████▌  | 21319/28080 [42:07:45<13:18:44,  7.09s/it]
 76%|███████▌  | 21320/28080 [42:07:52<13:15:42,  7.06s/it]
                                                           
{'loss': 0.6251, 'learning_rate': 7.222195858361713e-05, 'epoch': 9.11}

 76%|███████▌  | 21320/28080 [42:07:52<13:15:42,  7.06s/it]
 76%|███████▌  | 21321/28080 [42:07:59<13:13:49,  7.05s/it]
                                                           
{'loss': 0.5999, 'learning_rate': 7.220168599803952e-05, 'epoch': 9.11}

 76%|███████▌  | 21321/28080 [42:07:59<13:13:49,  7.05s/it]
 76%|███████▌  | 21322/28080 [42:08:06<13:12:34,  7.04s/it]
                                                           
{'loss': 0.5993, 'learning_rate': 7.21814157778851e-05, 'epoch': 9.11}

 76%|███████▌  | 21322/28080 [42:08:06<13:12:34,  7.04s/it]
 76%|███████▌  | 21323/28080 [42:08:13<13:13:39,  7.05s/it]
                                                           
{'loss': 0.6127, 'learning_rate': 7.21611479234234e-05, 'epoch': 9.11}

 76%|███████▌  | 21323/28080 [42:08:13<13:13:39,  7.05s/it]
 76%|███████▌  | 21324/28080 [42:08:20<13:15:20,  7.06s/it]
                                                           
{'loss': 0.6112, 'learning_rate': 7.214088243492423e-05, 'epoch': 9.11}

 76%|███████▌  | 21324/28080 [42:08:20<13:15:20,  7.06s/it]
 76%|███████▌  | 21325/28080 [42:08:27<13:16:22,  7.07s/it]
                                                           
{'loss': 0.6205, 'learning_rate': 7.212061931265706e-05, 'epoch': 9.11}

 76%|███████▌  | 21325/28080 [42:08:27<13:16:22,  7.07s/it]
 76%|███████▌  | 21326/28080 [42:08:34<13:15:05,  7.06s/it]
                                                           
{'loss': 0.6187, 'learning_rate': 7.210035855689162e-05, 'epoch': 9.11}

 76%|███████▌  | 21326/28080 [42:08:34<13:15:05,  7.06s/it]
 76%|███████▌  | 21327/28080 [42:08:41<13:12:08,  7.04s/it]
                                                           
{'loss': 0.6148, 'learning_rate': 7.208010016789737e-05, 'epoch': 9.11}

 76%|███████▌  | 21327/28080 [42:08:41<13:12:08,  7.04s/it]
 76%|███████▌  | 21328/28080 [42:08:48<13:15:18,  7.07s/it]
                                                           
{'loss': 0.5885, 'learning_rate': 7.205984414594386e-05, 'epoch': 9.11}

 76%|███████▌  | 21328/28080 [42:08:48<13:15:18,  7.07s/it]
 76%|███████▌  | 21329/28080 [42:08:55<13:17:20,  7.09s/it]
                                                           
{'loss': 0.609, 'learning_rate': 7.203959049130046e-05, 'epoch': 9.11}

 76%|███████▌  | 21329/28080 [42:08:55<13:17:20,  7.09s/it]
 76%|███████▌  | 21330/28080 [42:09:02<13:15:31,  7.07s/it]
                                                           
{'loss': 0.6098, 'learning_rate': 7.201933920423678e-05, 'epoch': 9.11}

 76%|███████▌  | 21330/28080 [42:09:02<13:15:31,  7.07s/it]
 76%|███████▌  | 21331/28080 [42:09:10<13:22:19,  7.13s/it]
                                                           
{'loss': 0.608, 'learning_rate': 7.199909028502222e-05, 'epoch': 9.11}

 76%|███████▌  | 21331/28080 [42:09:10<13:22:19,  7.13s/it]
 76%|███████▌  | 21332/28080 [42:09:17<13:21:34,  7.13s/it]
                                                           
{'loss': 0.6143, 'learning_rate': 7.19788437339261e-05, 'epoch': 9.11}

 76%|███████▌  | 21332/28080 [42:09:17<13:21:34,  7.13s/it]
 76%|███████▌  | 21333/28080 [42:09:24<13:19:07,  7.11s/it]
                                                           
{'loss': 0.5905, 'learning_rate': 7.195859955121772e-05, 'epoch': 9.11}

 76%|███████▌  | 21333/28080 [42:09:24<13:19:07,  7.11s/it]
 76%|███████▌  | 21334/28080 [42:09:31<13:17:05,  7.09s/it]
                                                           
{'loss': 0.5804, 'learning_rate': 7.193835773716662e-05, 'epoch': 9.11}

 76%|███████▌  | 21334/28080 [42:09:31<13:17:05,  7.09s/it]
 76%|███████▌  | 21335/28080 [42:09:38<13:17:20,  7.09s/it]
                                                           
{'loss': 0.5826, 'learning_rate': 7.191811829204192e-05, 'epoch': 9.11}

 76%|███████▌  | 21335/28080 [42:09:38<13:17:20,  7.09s/it]
 76%|███████▌  | 21336/28080 [42:09:45<13:17:20,  7.09s/it]
                                                           
{'loss': 0.5986, 'learning_rate': 7.189788121611299e-05, 'epoch': 9.11}

 76%|███████▌  | 21336/28080 [42:09:45<13:17:20,  7.09s/it]
 76%|███████▌  | 21337/28080 [42:09:52<13:16:23,  7.09s/it]
                                                           
{'loss': 0.5854, 'learning_rate': 7.187764650964889e-05, 'epoch': 9.11}

 76%|███████▌  | 21337/28080 [42:09:52<13:16:23,  7.09s/it]
 76%|███████▌  | 21338/28080 [42:09:59<13:18:00,  7.10s/it]
                                                           
{'loss': 0.598, 'learning_rate': 7.185741417291905e-05, 'epoch': 9.12}

 76%|███████▌  | 21338/28080 [42:09:59<13:18:00,  7.10s/it]
 76%|███████▌  | 21339/28080 [42:10:06<13:12:47,  7.06s/it]
                                                           
{'loss': 0.6118, 'learning_rate': 7.183718420619245e-05, 'epoch': 9.12}

 76%|███████▌  | 21339/28080 [42:10:06<13:12:47,  7.06s/it]
 76%|███████▌  | 21340/28080 [42:10:13<13:13:13,  7.06s/it]
                                                           
{'loss': 0.6041, 'learning_rate': 7.181695660973841e-05, 'epoch': 9.12}

 76%|███████▌  | 21340/28080 [42:10:13<13:13:13,  7.06s/it]
 76%|███████▌  | 21341/28080 [42:10:20<13:17:39,  7.10s/it]
                                                           
{'loss': 0.5974, 'learning_rate': 7.179673138382601e-05, 'epoch': 9.12}

 76%|███████▌  | 21341/28080 [42:10:20<13:17:39,  7.10s/it]
 76%|███████▌  | 21342/28080 [42:10:27<13:18:25,  7.11s/it]
                                                           
{'loss': 0.5947, 'learning_rate': 7.177650852872408e-05, 'epoch': 9.12}

 76%|███████▌  | 21342/28080 [42:10:27<13:18:25,  7.11s/it]
 76%|███████▌  | 21343/28080 [42:10:35<13:20:03,  7.13s/it]
                                                           
{'loss': 0.6197, 'learning_rate': 7.175628804470194e-05, 'epoch': 9.12}

 76%|███████▌  | 21343/28080 [42:10:35<13:20:03,  7.13s/it]
 76%|███████▌  | 21344/28080 [42:10:42<13:19:44,  7.12s/it]
                                                           
{'loss': 0.5909, 'learning_rate': 7.173606993202841e-05, 'epoch': 9.12}

 76%|███████▌  | 21344/28080 [42:10:42<13:19:44,  7.12s/it]
 76%|███████▌  | 21345/28080 [42:10:49<13:17:09,  7.10s/it]
                                                           
{'loss': 0.6089, 'learning_rate': 7.171585419097265e-05, 'epoch': 9.12}

 76%|███████▌  | 21345/28080 [42:10:49<13:17:09,  7.10s/it]
 76%|███████▌  | 21346/28080 [42:10:56<13:17:02,  7.10s/it]
                                                           
{'loss': 0.6155, 'learning_rate': 7.169564082180352e-05, 'epoch': 9.12}

 76%|███████▌  | 21346/28080 [42:10:56<13:17:02,  7.10s/it]
 76%|███████▌  | 21347/28080 [42:11:03<13:16:57,  7.10s/it]
                                                           
{'loss': 0.6083, 'learning_rate': 7.167542982478997e-05, 'epoch': 9.12}

 76%|███████▌  | 21347/28080 [42:11:03<13:16:57,  7.10s/it]
 76%|███████▌  | 21348/28080 [42:11:10<13:15:14,  7.09s/it]
                                                           
{'loss': 0.619, 'learning_rate': 7.165522120020074e-05, 'epoch': 9.12}

 76%|███████▌  | 21348/28080 [42:11:10<13:15:14,  7.09s/it]
 76%|███████▌  | 21349/28080 [42:11:17<13:14:18,  7.08s/it]
                                                           
{'loss': 0.6084, 'learning_rate': 7.163501494830491e-05, 'epoch': 9.12}

 76%|███████▌  | 21349/28080 [42:11:17<13:14:18,  7.08s/it]
 76%|███████▌  | 21350/28080 [42:11:24<13:13:32,  7.07s/it]
                                                           
{'loss': 0.6046, 'learning_rate': 7.161481106937118e-05, 'epoch': 9.12}

 76%|███████▌  | 21350/28080 [42:11:24<13:13:32,  7.07s/it]
 76%|███████▌  | 21351/28080 [42:11:31<13:12:42,  7.07s/it]
                                                           
{'loss': 0.6065, 'learning_rate': 7.159460956366837e-05, 'epoch': 9.12}

 76%|███████▌  | 21351/28080 [42:11:31<13:12:42,  7.07s/it]
 76%|███████▌  | 21352/28080 [42:11:38<13:15:24,  7.09s/it]
                                                           
{'loss': 0.5944, 'learning_rate': 7.157441043146514e-05, 'epoch': 9.12}

 76%|███████▌  | 21352/28080 [42:11:38<13:15:24,  7.09s/it]
 76%|███████▌  | 21353/28080 [42:11:46<13:17:56,  7.12s/it]
                                                           
{'loss': 0.5795, 'learning_rate': 7.155421367303041e-05, 'epoch': 9.12}

 76%|███████▌  | 21353/28080 [42:11:46<13:17:56,  7.12s/it]
 76%|███████▌  | 21354/28080 [42:11:53<13:18:12,  7.12s/it]
                                                           
{'loss': 0.605, 'learning_rate': 7.153401928863269e-05, 'epoch': 9.12}

 76%|███████▌  | 21354/28080 [42:11:53<13:18:12,  7.12s/it]
 76%|███████▌  | 21355/28080 [42:12:00<13:19:13,  7.13s/it]
                                                           
{'loss': 0.6036, 'learning_rate': 7.151382727854086e-05, 'epoch': 9.12}

 76%|███████▌  | 21355/28080 [42:12:00<13:19:13,  7.13s/it]
 76%|███████▌  | 21356/28080 [42:12:07<13:15:58,  7.10s/it]
                                                           
{'loss': 0.6154, 'learning_rate': 7.14936376430233e-05, 'epoch': 9.12}

 76%|███████▌  | 21356/28080 [42:12:07<13:15:58,  7.10s/it]
 76%|███████▌  | 21357/28080 [42:12:14<13:18:06,  7.12s/it]
                                                           
{'loss': 0.5874, 'learning_rate': 7.147345038234879e-05, 'epoch': 9.12}

 76%|███████▌  | 21357/28080 [42:12:14<13:18:06,  7.12s/it]
 76%|███████▌  | 21358/28080 [42:12:21<13:14:31,  7.09s/it]
                                                           
{'loss': 0.5932, 'learning_rate': 7.145326549678579e-05, 'epoch': 9.12}

 76%|███████▌  | 21358/28080 [42:12:21<13:14:31,  7.09s/it]
 76%|███████▌  | 21359/28080 [42:12:28<13:10:22,  7.06s/it]
                                                           
{'loss': 0.6159, 'learning_rate': 7.143308298660295e-05, 'epoch': 9.12}

 76%|███████▌  | 21359/28080 [42:12:28<13:10:22,  7.06s/it]
 76%|███████▌  | 21360/28080 [42:12:35<13:12:40,  7.08s/it]
                                                           
{'loss': 0.5796, 'learning_rate': 7.141290285206876e-05, 'epoch': 9.12}

 76%|███████▌  | 21360/28080 [42:12:35<13:12:40,  7.08s/it]
 76%|███████▌  | 21361/28080 [42:12:42<13:15:05,  7.10s/it]
                                                           
{'loss': 0.6033, 'learning_rate': 7.139272509345163e-05, 'epoch': 9.13}

 76%|███████▌  | 21361/28080 [42:12:42<13:15:05,  7.10s/it]
 76%|███████▌  | 21362/28080 [42:12:49<13:16:18,  7.11s/it]
                                                           
{'loss': 0.6144, 'learning_rate': 7.137254971101994e-05, 'epoch': 9.13}

 76%|███████▌  | 21362/28080 [42:12:49<13:16:18,  7.11s/it]
 76%|███████▌  | 21363/28080 [42:12:57<13:13:42,  7.09s/it]
                                                           
{'loss': 0.592, 'learning_rate': 7.13523767050423e-05, 'epoch': 9.13}

 76%|███████▌  | 21363/28080 [42:12:57<13:13:42,  7.09s/it]
 76%|███████▌  | 21364/28080 [42:13:04<13:14:16,  7.10s/it]
                                                           
{'loss': 0.5992, 'learning_rate': 7.1332206075787e-05, 'epoch': 9.13}

 76%|███████▌  | 21364/28080 [42:13:04<13:14:16,  7.10s/it]
 76%|███████▌  | 21365/28080 [42:13:11<13:10:44,  7.07s/it]
                                                           
{'loss': 0.6048, 'learning_rate': 7.131203782352236e-05, 'epoch': 9.13}

 76%|███████▌  | 21365/28080 [42:13:11<13:10:44,  7.07s/it]
 76%|███████▌  | 21366/28080 [42:13:18<13:09:08,  7.05s/it]
                                                           
{'loss': 0.586, 'learning_rate': 7.129187194851672e-05, 'epoch': 9.13}

 76%|███████▌  | 21366/28080 [42:13:18<13:09:08,  7.05s/it]
 76%|███████▌  | 21367/28080 [42:13:25<13:11:38,  7.08s/it]
                                                           
{'loss': 0.5868, 'learning_rate': 7.127170845103825e-05, 'epoch': 9.13}

 76%|███████▌  | 21367/28080 [42:13:25<13:11:38,  7.08s/it]
 76%|███████▌  | 21368/28080 [42:13:32<13:12:45,  7.09s/it]
                                                           
{'loss': 0.6103, 'learning_rate': 7.125154733135545e-05, 'epoch': 9.13}

 76%|███████▌  | 21368/28080 [42:13:32<13:12:45,  7.09s/it]
 76%|███████▌  | 21369/28080 [42:13:39<13:14:20,  7.10s/it]
                                                           
{'loss': 0.6051, 'learning_rate': 7.123138858973638e-05, 'epoch': 9.13}

 76%|███████▌  | 21369/28080 [42:13:39<13:14:20,  7.10s/it]
 76%|███████▌  | 21370/28080 [42:13:46<13:14:11,  7.10s/it]
                                                           
{'loss': 0.6143, 'learning_rate': 7.121123222644923e-05, 'epoch': 9.13}

 76%|███████▌  | 21370/28080 [42:13:46<13:14:11,  7.10s/it]
 76%|███████▌  | 21371/28080 [42:13:53<13:14:05,  7.10s/it]
                                                           
{'loss': 0.6034, 'learning_rate': 7.119107824176215e-05, 'epoch': 9.13}

 76%|███████▌  | 21371/28080 [42:13:53<13:14:05,  7.10s/it]
 76%|███████▌  | 21372/28080 [42:14:00<13:08:24,  7.05s/it]
                                                           
{'loss': 0.6054, 'learning_rate': 7.117092663594338e-05, 'epoch': 9.13}

 76%|███████▌  | 21372/28080 [42:14:00<13:08:24,  7.05s/it]
 76%|███████▌  | 21373/28080 [42:14:07<13:08:42,  7.06s/it]
                                                           
{'loss': 0.5947, 'learning_rate': 7.115077740926088e-05, 'epoch': 9.13}

 76%|███████▌  | 21373/28080 [42:14:07<13:08:42,  7.06s/it]
 76%|███████▌  | 21374/28080 [42:14:14<13:06:14,  7.03s/it]
                                                           
{'loss': 0.6054, 'learning_rate': 7.113063056198283e-05, 'epoch': 9.13}

 76%|███████▌  | 21374/28080 [42:14:14<13:06:14,  7.03s/it]
 76%|███████▌  | 21375/28080 [42:14:21<13:11:14,  7.08s/it]
                                                           
{'loss': 0.5984, 'learning_rate': 7.111048609437721e-05, 'epoch': 9.13}

 76%|███████▌  | 21375/28080 [42:14:21<13:11:14,  7.08s/it]
 76%|███████▌  | 21376/28080 [42:14:29<13:12:00,  7.09s/it]
                                                           
{'loss': 0.588, 'learning_rate': 7.109034400671202e-05, 'epoch': 9.13}

 76%|███████▌  | 21376/28080 [42:14:29<13:12:00,  7.09s/it]
 76%|███████▌  | 21377/28080 [42:14:36<13:10:47,  7.08s/it]
                                                           
{'loss': 0.6072, 'learning_rate': 7.107020429925518e-05, 'epoch': 9.13}

 76%|███████▌  | 21377/28080 [42:14:36<13:10:47,  7.08s/it]
 76%|███████▌  | 21378/28080 [42:14:43<13:08:25,  7.06s/it]
                                                           
{'loss': 0.5986, 'learning_rate': 7.105006697227472e-05, 'epoch': 9.13}

 76%|███████▌  | 21378/28080 [42:14:43<13:08:25,  7.06s/it]
 76%|███████▌  | 21379/28080 [42:14:50<13:14:36,  7.11s/it]
                                                           
{'loss': 0.6144, 'learning_rate': 7.102993202603856e-05, 'epoch': 9.13}

 76%|███████▌  | 21379/28080 [42:14:50<13:14:36,  7.11s/it]
 76%|███████▌  | 21380/28080 [42:14:57<13:14:13,  7.11s/it]
                                                           
{'loss': 0.6087, 'learning_rate': 7.100979946081448e-05, 'epoch': 9.13}

 76%|███████▌  | 21380/28080 [42:14:57<13:14:13,  7.11s/it]
 76%|███████▌  | 21381/28080 [42:15:04<13:12:20,  7.10s/it]
                                                           
{'loss': 0.5891, 'learning_rate': 7.098966927687029e-05, 'epoch': 9.13}

 76%|███████▌  | 21381/28080 [42:15:04<13:12:20,  7.10s/it]
 76%|███████▌  | 21382/28080 [42:15:11<13:08:44,  7.07s/it]
                                                           
{'loss': 0.5812, 'learning_rate': 7.096954147447396e-05, 'epoch': 9.13}

 76%|███████▌  | 21382/28080 [42:15:11<13:08:44,  7.07s/it]
 76%|███████▌  | 21383/28080 [42:15:18<13:07:08,  7.05s/it]
                                                           
{'loss': 0.6373, 'learning_rate': 7.094941605389319e-05, 'epoch': 9.13}

 76%|███████▌  | 21383/28080 [42:15:18<13:07:08,  7.05s/it]
 76%|███████▌  | 21384/28080 [42:15:25<13:07:34,  7.06s/it]
                                                           
{'loss': 0.5894, 'learning_rate': 7.092929301539572e-05, 'epoch': 9.14}

 76%|███████▌  | 21384/28080 [42:15:25<13:07:34,  7.06s/it]
 76%|███████▌  | 21385/28080 [42:15:32<13:05:37,  7.04s/it]
                                                           
{'loss': 0.605, 'learning_rate': 7.090917235924918e-05, 'epoch': 9.14}

 76%|███████▌  | 21385/28080 [42:15:32<13:05:37,  7.04s/it]
 76%|███████▌  | 21386/28080 [42:15:39<13:06:34,  7.05s/it]
                                                           
{'loss': 0.607, 'learning_rate': 7.088905408572143e-05, 'epoch': 9.14}

 76%|███████▌  | 21386/28080 [42:15:39<13:06:34,  7.05s/it]
 76%|███████▌  | 21387/28080 [42:15:46<13:06:31,  7.05s/it]
                                                           
{'loss': 0.5996, 'learning_rate': 7.086893819507997e-05, 'epoch': 9.14}

 76%|███████▌  | 21387/28080 [42:15:46<13:06:31,  7.05s/it]
 76%|███████▌  | 21388/28080 [42:15:53<13:09:16,  7.08s/it]
                                                           
{'loss': 0.6082, 'learning_rate': 7.084882468759254e-05, 'epoch': 9.14}

 76%|███████▌  | 21388/28080 [42:15:53<13:09:16,  7.08s/it]
 76%|███████▌  | 21389/28080 [42:16:00<13:10:57,  7.09s/it]
                                                           
{'loss': 0.6098, 'learning_rate': 7.082871356352671e-05, 'epoch': 9.14}

 76%|███████▌  | 21389/28080 [42:16:00<13:10:57,  7.09s/it]
 76%|███████▌  | 21390/28080 [42:16:08<13:09:46,  7.08s/it]
                                                           
{'loss': 0.6036, 'learning_rate': 7.080860482315e-05, 'epoch': 9.14}

 76%|███████▌  | 21390/28080 [42:16:08<13:09:46,  7.08s/it]
 76%|███████▌  | 21391/28080 [42:16:15<13:10:51,  7.09s/it]
                                                           
{'loss': 0.5845, 'learning_rate': 7.078849846672992e-05, 'epoch': 9.14}

 76%|███████▌  | 21391/28080 [42:16:15<13:10:51,  7.09s/it]
 76%|███████▌  | 21392/28080 [42:16:22<13:11:07,  7.10s/it]
                                                           
{'loss': 0.6008, 'learning_rate': 7.076839449453393e-05, 'epoch': 9.14}

 76%|███████▌  | 21392/28080 [42:16:22<13:11:07,  7.10s/it]
 76%|███████▌  | 21393/28080 [42:16:29<13:07:23,  7.06s/it]
                                                           
{'loss': 0.6103, 'learning_rate': 7.07482929068296e-05, 'epoch': 9.14}

 76%|███████▌  | 21393/28080 [42:16:29<13:07:23,  7.06s/it]
 76%|███████▌  | 21394/28080 [42:16:36<13:11:39,  7.10s/it]
                                                           
{'loss': 0.5964, 'learning_rate': 7.072819370388433e-05, 'epoch': 9.14}

 76%|███████▌  | 21394/28080 [42:16:36<13:11:39,  7.10s/it]
 76%|███████▌  | 21395/28080 [42:16:43<13:11:00,  7.10s/it]
                                                           
{'loss': 0.6003, 'learning_rate': 7.070809688596549e-05, 'epoch': 9.14}

 76%|███████▌  | 21395/28080 [42:16:43<13:11:00,  7.10s/it]
 76%|███████▌  | 21396/28080 [42:16:50<13:11:50,  7.11s/it]
                                                           
{'loss': 0.5992, 'learning_rate': 7.06880024533404e-05, 'epoch': 9.14}

 76%|███████▌  | 21396/28080 [42:16:50<13:11:50,  7.11s/it]
 76%|███████▌  | 21397/28080 [42:16:57<13:12:26,  7.11s/it]
                                                           
{'loss': 0.5891, 'learning_rate': 7.066791040627648e-05, 'epoch': 9.14}

 76%|███████▌  | 21397/28080 [42:16:57<13:12:26,  7.11s/it]
 76%|███████▌  | 21398/28080 [42:17:04<13:14:20,  7.13s/it]
                                                           
{'loss': 0.6006, 'learning_rate': 7.064782074504105e-05, 'epoch': 9.14}

 76%|███████▌  | 21398/28080 [42:17:04<13:14:20,  7.13s/it]
 76%|███████▌  | 21399/28080 [42:17:12<13:17:00,  7.16s/it]
                                                           
{'loss': 0.6091, 'learning_rate': 7.062773346990131e-05, 'epoch': 9.14}

 76%|███████▌  | 21399/28080 [42:17:12<13:17:00,  7.16s/it]
 76%|███████▌  | 21400/28080 [42:17:19<13:15:38,  7.15s/it]
                                                           
{'loss': 0.6152, 'learning_rate': 7.060764858112447e-05, 'epoch': 9.14}

 76%|███████▌  | 21400/28080 [42:17:19<13:15:38,  7.15s/it]
 76%|███████▌  | 21401/28080 [42:17:26<13:13:29,  7.13s/it]
                                                           
{'loss': 0.601, 'learning_rate': 7.058756607897788e-05, 'epoch': 9.14}

 76%|███████▌  | 21401/28080 [42:17:26<13:13:29,  7.13s/it]
 76%|███████▌  | 21402/28080 [42:17:33<13:13:24,  7.13s/it]
                                                           
{'loss': 0.6075, 'learning_rate': 7.056748596372853e-05, 'epoch': 9.14}

 76%|███████▌  | 21402/28080 [42:17:33<13:13:24,  7.13s/it]
 76%|███████▌  | 21403/28080 [42:17:40<13:10:38,  7.10s/it]
                                                           
{'loss': 0.6105, 'learning_rate': 7.054740823564384e-05, 'epoch': 9.14}

 76%|███████▌  | 21403/28080 [42:17:40<13:10:38,  7.10s/it]
 76%|███████▌  | 21404/28080 [42:17:47<13:12:00,  7.12s/it]
                                                           
{'loss': 0.5912, 'learning_rate': 7.052733289499061e-05, 'epoch': 9.14}

 76%|███████▌  | 21404/28080 [42:17:47<13:12:00,  7.12s/it]
 76%|███████▌  | 21405/28080 [42:17:54<13:12:33,  7.12s/it]
                                                           
{'loss': 0.609, 'learning_rate': 7.050725994203614e-05, 'epoch': 9.14}

 76%|███████▌  | 21405/28080 [42:17:54<13:12:33,  7.12s/it]
 76%|███████▌  | 21406/28080 [42:18:01<13:08:26,  7.09s/it]
                                                           
{'loss': 0.6022, 'learning_rate': 7.048718937704729e-05, 'epoch': 9.14}

 76%|███████▌  | 21406/28080 [42:18:01<13:08:26,  7.09s/it]
 76%|███████▌  | 21407/28080 [42:18:09<13:11:24,  7.12s/it]
                                                           
{'loss': 0.61, 'learning_rate': 7.04671212002913e-05, 'epoch': 9.14}

 76%|███████▌  | 21407/28080 [42:18:09<13:11:24,  7.12s/it]
 76%|███████▌  | 21408/28080 [42:18:16<13:09:05,  7.10s/it]
                                                           
{'loss': 0.6142, 'learning_rate': 7.044705541203505e-05, 'epoch': 9.15}

 76%|███████▌  | 21408/28080 [42:18:16<13:09:05,  7.10s/it]
 76%|███████▌  | 21409/28080 [42:18:23<13:10:10,  7.11s/it]
                                                           
{'loss': 0.5866, 'learning_rate': 7.042699201254549e-05, 'epoch': 9.15}

 76%|███████▌  | 21409/28080 [42:18:23<13:10:10,  7.11s/it]
 76%|███████▌  | 21410/28080 [42:18:30<13:06:18,  7.07s/it]
                                                           
{'loss': 0.6003, 'learning_rate': 7.040693100208944e-05, 'epoch': 9.15}

 76%|███████▌  | 21410/28080 [42:18:30<13:06:18,  7.07s/it]
 76%|███████▋  | 21411/28080 [42:18:37<13:04:46,  7.06s/it]
                                                           
{'loss': 0.6049, 'learning_rate': 7.038687238093403e-05, 'epoch': 9.15}

 76%|███████▋  | 21411/28080 [42:18:37<13:04:46,  7.06s/it]
 76%|███████▋  | 21412/28080 [42:18:44<13:01:28,  7.03s/it]
                                                           
{'loss': 0.6039, 'learning_rate': 7.036681614934592e-05, 'epoch': 9.15}

 76%|███████▋  | 21412/28080 [42:18:44<13:01:28,  7.03s/it]
 76%|███████▋  | 21413/28080 [42:18:51<13:03:43,  7.05s/it]
                                                           
{'loss': 0.6174, 'learning_rate': 7.034676230759204e-05, 'epoch': 9.15}

 76%|███████▋  | 21413/28080 [42:18:51<13:03:43,  7.05s/it]
 76%|███████▋  | 21414/28080 [42:18:58<13:01:05,  7.03s/it]
                                                           
{'loss': 0.6113, 'learning_rate': 7.032671085593908e-05, 'epoch': 9.15}

 76%|███████▋  | 21414/28080 [42:18:58<13:01:05,  7.03s/it]
 76%|███████▋  | 21415/28080 [42:19:05<12:56:54,  6.99s/it]
                                                           
{'loss': 0.6147, 'learning_rate': 7.030666179465395e-05, 'epoch': 9.15}

 76%|███████▋  | 21415/28080 [42:19:05<12:56:54,  6.99s/it]
 76%|███████▋  | 21416/28080 [42:19:12<12:57:13,  7.00s/it]
                                                           
{'loss': 0.6132, 'learning_rate': 7.02866151240033e-05, 'epoch': 9.15}

 76%|███████▋  | 21416/28080 [42:19:12<12:57:13,  7.00s/it]
 76%|███████▋  | 21417/28080 [42:19:19<12:58:39,  7.01s/it]
                                                           
{'loss': 0.5976, 'learning_rate': 7.026657084425383e-05, 'epoch': 9.15}

 76%|███████▋  | 21417/28080 [42:19:19<12:58:39,  7.01s/it]
 76%|███████▋  | 21418/28080 [42:19:26<13:03:35,  7.06s/it]
                                                           
{'loss': 0.6048, 'learning_rate': 7.024652895567221e-05, 'epoch': 9.15}

 76%|███████▋  | 21418/28080 [42:19:26<13:03:35,  7.06s/it]
 76%|███████▋  | 21419/28080 [42:19:33<13:05:31,  7.08s/it]
                                                           
{'loss': 0.6137, 'learning_rate': 7.022648945852502e-05, 'epoch': 9.15}

 76%|███████▋  | 21419/28080 [42:19:33<13:05:31,  7.08s/it]
 76%|███████▋  | 21420/28080 [42:19:40<13:04:43,  7.07s/it]
                                                           
{'loss': 0.6028, 'learning_rate': 7.020645235307898e-05, 'epoch': 9.15}

 76%|███████▋  | 21420/28080 [42:19:40<13:04:43,  7.07s/it]
 76%|███████▋  | 21421/28080 [42:19:47<13:07:18,  7.09s/it]
                                                           
{'loss': 0.5979, 'learning_rate': 7.018641763960056e-05, 'epoch': 9.15}

 76%|███████▋  | 21421/28080 [42:19:47<13:07:18,  7.09s/it]
 76%|███████▋  | 21422/28080 [42:19:54<13:08:03,  7.10s/it]
                                                           
{'loss': 0.5803, 'learning_rate': 7.016638531835648e-05, 'epoch': 9.15}

 76%|███████▋  | 21422/28080 [42:19:54<13:08:03,  7.10s/it]
 76%|███████▋  | 21423/28080 [42:20:02<13:09:45,  7.12s/it]
                                                           
{'loss': 0.6024, 'learning_rate': 7.014635538961298e-05, 'epoch': 9.15}

 76%|███████▋  | 21423/28080 [42:20:02<13:09:45,  7.12s/it]
 76%|███████▋  | 21424/28080 [42:20:09<13:08:49,  7.11s/it]
                                                           
{'loss': 0.592, 'learning_rate': 7.012632785363676e-05, 'epoch': 9.15}

 76%|███████▋  | 21424/28080 [42:20:09<13:08:49,  7.11s/it]
 76%|███████▋  | 21425/28080 [42:20:16<13:08:32,  7.11s/it]
                                                           
{'loss': 0.595, 'learning_rate': 7.01063027106941e-05, 'epoch': 9.15}

 76%|███████▋  | 21425/28080 [42:20:16<13:08:32,  7.11s/it]
 76%|███████▋  | 21426/28080 [42:20:23<13:13:54,  7.16s/it]
                                                           
{'loss': 0.6069, 'learning_rate': 7.008627996105154e-05, 'epoch': 9.15}

 76%|███████▋  | 21426/28080 [42:20:23<13:13:54,  7.16s/it]
 76%|███████▋  | 21427/28080 [42:20:30<13:09:34,  7.12s/it]
                                                           
{'loss': 0.6131, 'learning_rate': 7.006625960497545e-05, 'epoch': 9.15}

 76%|███████▋  | 21427/28080 [42:20:30<13:09:34,  7.12s/it]
 76%|███████▋  | 21428/28080 [42:20:37<13:10:36,  7.13s/it]
                                                           
{'loss': 0.6008, 'learning_rate': 7.004624164273215e-05, 'epoch': 9.15}

 76%|███████▋  | 21428/28080 [42:20:37<13:10:36,  7.13s/it]
 76%|███████▋  | 21429/28080 [42:20:44<13:10:58,  7.14s/it]
                                                           
{'loss': 0.6171, 'learning_rate': 7.00262260745879e-05, 'epoch': 9.15}

 76%|███████▋  | 21429/28080 [42:20:44<13:10:58,  7.14s/it]
 76%|███████▋  | 21430/28080 [42:20:51<13:08:03,  7.11s/it]
                                                           
{'loss': 0.5968, 'learning_rate': 7.000621290080908e-05, 'epoch': 9.15}

 76%|███████▋  | 21430/28080 [42:20:51<13:08:03,  7.11s/it]
 76%|███████▋  | 21431/28080 [42:20:58<13:04:57,  7.08s/it]
                                                           
{'loss': 0.6108, 'learning_rate': 6.998620212166193e-05, 'epoch': 9.16}

 76%|███████▋  | 21431/28080 [42:20:58<13:04:57,  7.08s/it]
 76%|███████▋  | 21432/28080 [42:21:05<13:02:59,  7.07s/it]
                                                           
{'loss': 0.6222, 'learning_rate': 6.996619373741264e-05, 'epoch': 9.16}

 76%|███████▋  | 21432/28080 [42:21:05<13:02:59,  7.07s/it]
 76%|███████▋  | 21433/28080 [42:21:13<13:05:06,  7.09s/it]
                                                           
{'loss': 0.612, 'learning_rate': 6.994618774832734e-05, 'epoch': 9.16}

 76%|███████▋  | 21433/28080 [42:21:13<13:05:06,  7.09s/it]
 76%|███████▋  | 21434/28080 [42:21:20<13:05:07,  7.09s/it]
                                                           
{'loss': 0.609, 'learning_rate': 6.992618415467234e-05, 'epoch': 9.16}

 76%|███████▋  | 21434/28080 [42:21:20<13:05:07,  7.09s/it]
 76%|███████▋  | 21435/28080 [42:21:27<13:07:09,  7.11s/it]
                                                           
{'loss': 0.5651, 'learning_rate': 6.990618295671361e-05, 'epoch': 9.16}

 76%|███████▋  | 21435/28080 [42:21:27<13:07:09,  7.11s/it]
 76%|███████▋  | 21436/28080 [42:21:34<13:07:29,  7.11s/it]
                                                           
{'loss': 0.6049, 'learning_rate': 6.98861841547174e-05, 'epoch': 9.16}

 76%|███████▋  | 21436/28080 [42:21:34<13:07:29,  7.11s/it]
 76%|███████▋  | 21437/28080 [42:21:41<13:04:45,  7.09s/it]
                                                           
{'loss': 0.597, 'learning_rate': 6.986618774894967e-05, 'epoch': 9.16}

 76%|███████▋  | 21437/28080 [42:21:41<13:04:45,  7.09s/it]
 76%|███████▋  | 21438/28080 [42:21:48<13:07:16,  7.11s/it]
                                                           
{'loss': 0.5817, 'learning_rate': 6.984619373967652e-05, 'epoch': 9.16}

 76%|███████▋  | 21438/28080 [42:21:48<13:07:16,  7.11s/it]
 76%|███████▋  | 21439/28080 [42:21:55<13:03:50,  7.08s/it]
                                                           
{'loss': 0.6236, 'learning_rate': 6.982620212716381e-05, 'epoch': 9.16}

 76%|███████▋  | 21439/28080 [42:21:55<13:03:50,  7.08s/it]
 76%|███████▋  | 21440/28080 [42:22:02<13:05:55,  7.10s/it]
                                                           
{'loss': 0.6014, 'learning_rate': 6.980621291167768e-05, 'epoch': 9.16}

 76%|███████▋  | 21440/28080 [42:22:02<13:05:55,  7.10s/it]
 76%|███████▋  | 21441/28080 [42:22:09<13:02:30,  7.07s/it]
                                                           
{'loss': 0.6204, 'learning_rate': 6.978622609348401e-05, 'epoch': 9.16}

 76%|███████▋  | 21441/28080 [42:22:09<13:02:30,  7.07s/it]
 76%|███████▋  | 21442/28080 [42:22:16<13:02:29,  7.07s/it]
                                                           
{'loss': 0.6107, 'learning_rate': 6.976624167284868e-05, 'epoch': 9.16}

 76%|███████▋  | 21442/28080 [42:22:16<13:02:29,  7.07s/it]
 76%|███████▋  | 21443/28080 [42:22:23<13:01:16,  7.06s/it]
                                                           
{'loss': 0.6175, 'learning_rate': 6.974625965003756e-05, 'epoch': 9.16}

 76%|███████▋  | 21443/28080 [42:22:23<13:01:16,  7.06s/it]
 76%|███████▋  | 21444/28080 [42:22:30<13:01:06,  7.06s/it]
                                                           
{'loss': 0.603, 'learning_rate': 6.972628002531641e-05, 'epoch': 9.16}

 76%|███████▋  | 21444/28080 [42:22:30<13:01:06,  7.06s/it]
 76%|███████▋  | 21445/28080 [42:22:38<13:03:05,  7.08s/it]
                                                           
{'loss': 0.5787, 'learning_rate': 6.970630279895124e-05, 'epoch': 9.16}

 76%|███████▋  | 21445/28080 [42:22:38<13:03:05,  7.08s/it]
 76%|███████▋  | 21446/28080 [42:22:45<13:04:32,  7.10s/it]
                                                           
{'loss': 0.6068, 'learning_rate': 6.968632797120767e-05, 'epoch': 9.16}

 76%|███████▋  | 21446/28080 [42:22:45<13:04:32,  7.10s/it]
 76%|███████▋  | 21447/28080 [42:22:52<13:03:37,  7.09s/it]
                                                           
{'loss': 0.5928, 'learning_rate': 6.966635554235151e-05, 'epoch': 9.16}

 76%|███████▋  | 21447/28080 [42:22:52<13:03:37,  7.09s/it]
 76%|███████▋  | 21448/28080 [42:22:59<13:01:30,  7.07s/it]
                                                           
{'loss': 0.6203, 'learning_rate': 6.964638551264838e-05, 'epoch': 9.16}

 76%|███████▋  | 21448/28080 [42:22:59<13:01:30,  7.07s/it]
 76%|███████▋  | 21449/28080 [42:23:06<12:59:15,  7.05s/it]
                                                           
{'loss': 0.5894, 'learning_rate': 6.96264178823641e-05, 'epoch': 9.16}

 76%|███████▋  | 21449/28080 [42:23:06<12:59:15,  7.05s/it]
 76%|███████▋  | 21450/28080 [42:23:13<12:59:40,  7.06s/it]
                                                           
{'loss': 0.6288, 'learning_rate': 6.960645265176416e-05, 'epoch': 9.16}

 76%|███████▋  | 21450/28080 [42:23:13<12:59:40,  7.06s/it]
 76%|███████▋  | 21451/28080 [42:23:20<13:06:59,  7.12s/it]
                                                           
{'loss': 0.593, 'learning_rate': 6.958648982111444e-05, 'epoch': 9.16}

 76%|███████▋  | 21451/28080 [42:23:20<13:06:59,  7.12s/it]
 76%|███████▋  | 21452/28080 [42:23:27<13:04:14,  7.10s/it]
                                                           
{'loss': 0.577, 'learning_rate': 6.956652939068017e-05, 'epoch': 9.16}

 76%|███████▋  | 21452/28080 [42:23:27<13:04:14,  7.10s/it]
 76%|███████▋  | 21453/28080 [42:23:34<13:06:51,  7.12s/it]
                                                           
{'loss': 0.5896, 'learning_rate': 6.954657136072718e-05, 'epoch': 9.16}

 76%|███████▋  | 21453/28080 [42:23:34<13:06:51,  7.12s/it]
 76%|███████▋  | 21454/28080 [42:23:42<13:08:35,  7.14s/it]
                                                           
{'loss': 0.5941, 'learning_rate': 6.952661573152081e-05, 'epoch': 9.16}

 76%|███████▋  | 21454/28080 [42:23:42<13:08:35,  7.14s/it]
 76%|███████▋  | 21455/28080 [42:23:49<13:03:52,  7.10s/it]
                                                           
{'loss': 0.6052, 'learning_rate': 6.950666250332672e-05, 'epoch': 9.17}

 76%|███████▋  | 21455/28080 [42:23:49<13:03:52,  7.10s/it]
 76%|███████▋  | 21456/28080 [42:23:56<13:05:27,  7.11s/it]
                                                           
{'loss': 0.6134, 'learning_rate': 6.948671167641027e-05, 'epoch': 9.17}

 76%|███████▋  | 21456/28080 [42:23:56<13:05:27,  7.11s/it]
 76%|███████▋  | 21457/28080 [42:24:03<13:01:02,  7.08s/it]
                                                           
{'loss': 0.5965, 'learning_rate': 6.94667632510369e-05, 'epoch': 9.17}

 76%|███████▋  | 21457/28080 [42:24:03<13:01:02,  7.08s/it]
 76%|███████▋  | 21458/28080 [42:24:10<13:02:06,  7.09s/it]
                                                           
{'loss': 0.6156, 'learning_rate': 6.944681722747193e-05, 'epoch': 9.17}

 76%|███████▋  | 21458/28080 [42:24:10<13:02:06,  7.09s/it]
 76%|███████▋  | 21459/28080 [42:24:17<13:04:26,  7.11s/it]
                                                           
{'loss': 0.5975, 'learning_rate': 6.942687360598085e-05, 'epoch': 9.17}

 76%|███████▋  | 21459/28080 [42:24:17<13:04:26,  7.11s/it]
 76%|███████▋  | 21460/28080 [42:24:24<13:07:21,  7.14s/it]
                                                           
{'loss': 0.5834, 'learning_rate': 6.940693238682894e-05, 'epoch': 9.17}

 76%|███████▋  | 21460/28080 [42:24:24<13:07:21,  7.14s/it]
 76%|███████▋  | 21461/28080 [42:24:31<13:07:37,  7.14s/it]
                                                           
{'loss': 0.5944, 'learning_rate': 6.938699357028147e-05, 'epoch': 9.17}

 76%|███████▋  | 21461/28080 [42:24:31<13:07:37,  7.14s/it]
 76%|███████▋  | 21462/28080 [42:24:38<13:08:25,  7.15s/it]
                                                           
{'loss': 0.5979, 'learning_rate': 6.936705715660366e-05, 'epoch': 9.17}

 76%|███████▋  | 21462/28080 [42:24:38<13:08:25,  7.15s/it]
 76%|███████▋  | 21463/28080 [42:24:45<13:01:51,  7.09s/it]
                                                           
{'loss': 0.6061, 'learning_rate': 6.934712314606089e-05, 'epoch': 9.17}

 76%|███████▋  | 21463/28080 [42:24:45<13:01:51,  7.09s/it]
 76%|███████▋  | 21464/28080 [42:24:53<13:03:42,  7.11s/it]
                                                           
{'loss': 0.632, 'learning_rate': 6.93271915389182e-05, 'epoch': 9.17}

 76%|███████▋  | 21464/28080 [42:24:53<13:03:42,  7.11s/it]
 76%|███████▋  | 21465/28080 [42:25:00<13:04:35,  7.12s/it]
                                                           
{'loss': 0.6181, 'learning_rate': 6.930726233544099e-05, 'epoch': 9.17}

 76%|███████▋  | 21465/28080 [42:25:00<13:04:35,  7.12s/it]
 76%|███████▋  | 21466/28080 [42:25:07<13:06:44,  7.14s/it]
                                                           
{'loss': 0.6116, 'learning_rate': 6.928733553589417e-05, 'epoch': 9.17}

 76%|███████▋  | 21466/28080 [42:25:07<13:06:44,  7.14s/it]
 76%|███████▋  | 21467/28080 [42:25:14<13:08:15,  7.15s/it]
                                                           
{'loss': 0.5999, 'learning_rate': 6.926741114054283e-05, 'epoch': 9.17}

 76%|███████▋  | 21467/28080 [42:25:14<13:08:15,  7.15s/it]
 76%|███████▋  | 21468/28080 [42:25:21<13:07:13,  7.14s/it]
                                                           
{'loss': 0.6125, 'learning_rate': 6.92474891496522e-05, 'epoch': 9.17}

 76%|███████▋  | 21468/28080 [42:25:21<13:07:13,  7.14s/it]
 76%|███████▋  | 21469/28080 [42:25:28<13:06:50,  7.14s/it]
                                                           
{'loss': 0.597, 'learning_rate': 6.922756956348719e-05, 'epoch': 9.17}

 76%|███████▋  | 21469/28080 [42:25:28<13:06:50,  7.14s/it]
 76%|███████▋  | 21470/28080 [42:25:35<13:05:39,  7.13s/it]
                                                           
{'loss': 0.6062, 'learning_rate': 6.920765238231305e-05, 'epoch': 9.17}

 76%|███████▋  | 21470/28080 [42:25:35<13:05:39,  7.13s/it]
 76%|███████▋  | 21471/28080 [42:25:43<13:02:24,  7.10s/it]
                                                           
{'loss': 0.5931, 'learning_rate': 6.91877376063944e-05, 'epoch': 9.17}

 76%|███████▋  | 21471/28080 [42:25:43<13:02:24,  7.10s/it]
 76%|███████▋  | 21472/28080 [42:25:50<12:59:51,  7.08s/it]
                                                           
{'loss': 0.6065, 'learning_rate': 6.916782523599646e-05, 'epoch': 9.17}

 76%|███████▋  | 21472/28080 [42:25:50<12:59:51,  7.08s/it]
 76%|███████▋  | 21473/28080 [42:25:57<13:00:59,  7.09s/it]
                                                           
{'loss': 0.6159, 'learning_rate': 6.914791527138397e-05, 'epoch': 9.17}

 76%|███████▋  | 21473/28080 [42:25:57<13:00:59,  7.09s/it]
 76%|███████▋  | 21474/28080 [42:26:04<13:00:17,  7.09s/it]
                                                           
{'loss': 0.6161, 'learning_rate': 6.912800771282196e-05, 'epoch': 9.17}

 76%|███████▋  | 21474/28080 [42:26:04<13:00:17,  7.09s/it]
 76%|███████▋  | 21475/28080 [42:26:11<13:01:44,  7.10s/it]
                                                           
{'loss': 0.5948, 'learning_rate': 6.910810256057523e-05, 'epoch': 9.17}

 76%|███████▋  | 21475/28080 [42:26:11<13:01:44,  7.10s/it]
 76%|███████▋  | 21476/28080 [42:26:18<12:59:48,  7.08s/it]
                                                           
{'loss': 0.6052, 'learning_rate': 6.908819981490857e-05, 'epoch': 9.17}

 76%|███████▋  | 21476/28080 [42:26:18<12:59:48,  7.08s/it]
 76%|███████▋  | 21477/28080 [42:26:25<12:59:06,  7.08s/it]
                                                           
{'loss': 0.6097, 'learning_rate': 6.90682994760867e-05, 'epoch': 9.17}

 76%|███████▋  | 21477/28080 [42:26:25<12:59:06,  7.08s/it]
 76%|███████▋  | 21478/28080 [42:26:32<12:59:14,  7.08s/it]
                                                           
{'loss': 0.6048, 'learning_rate': 6.904840154437453e-05, 'epoch': 9.18}

 76%|███████▋  | 21478/28080 [42:26:32<12:59:14,  7.08s/it]
 76%|███████▋  | 21479/28080 [42:26:39<12:59:04,  7.08s/it]
                                                           
{'loss': 0.6058, 'learning_rate': 6.902850602003668e-05, 'epoch': 9.18}

 76%|███████▋  | 21479/28080 [42:26:39<12:59:04,  7.08s/it]
 76%|███████▋  | 21480/28080 [42:26:46<12:53:53,  7.04s/it]
                                                           
{'loss': 0.6186, 'learning_rate': 6.900861290333788e-05, 'epoch': 9.18}

 76%|███████▋  | 21480/28080 [42:26:46<12:53:53,  7.04s/it]
 76%|███████▋  | 21481/28080 [42:26:53<12:53:49,  7.04s/it]
                                                           
{'loss': 0.5967, 'learning_rate': 6.898872219454269e-05, 'epoch': 9.18}

 76%|███████▋  | 21481/28080 [42:26:53<12:53:49,  7.04s/it]
 77%|███████▋  | 21482/28080 [42:27:00<12:55:57,  7.06s/it]
                                                           
{'loss': 0.6003, 'learning_rate': 6.896883389391587e-05, 'epoch': 9.18}

 77%|███████▋  | 21482/28080 [42:27:00<12:55:57,  7.06s/it]
 77%|███████▋  | 21483/28080 [42:27:07<12:55:22,  7.05s/it]
                                                           
{'loss': 0.6083, 'learning_rate': 6.894894800172189e-05, 'epoch': 9.18}

 77%|███████▋  | 21483/28080 [42:27:07<12:55:22,  7.05s/it]
 77%|███████▋  | 21484/28080 [42:27:14<12:56:10,  7.06s/it]
                                                           
{'loss': 0.5961, 'learning_rate': 6.892906451822554e-05, 'epoch': 9.18}

 77%|███████▋  | 21484/28080 [42:27:14<12:56:10,  7.06s/it]
 77%|███████▋  | 21485/28080 [42:27:21<12:52:23,  7.03s/it]
                                                           
{'loss': 0.6175, 'learning_rate': 6.890918344369101e-05, 'epoch': 9.18}

 77%|███████▋  | 21485/28080 [42:27:21<12:52:23,  7.03s/it]
 77%|███████▋  | 21486/28080 [42:27:28<12:56:13,  7.06s/it]
                                                           
{'loss': 0.6006, 'learning_rate': 6.888930477838307e-05, 'epoch': 9.18}

 77%|███████▋  | 21486/28080 [42:27:28<12:56:13,  7.06s/it]
 77%|███████▋  | 21487/28080 [42:27:36<12:59:23,  7.09s/it]
                                                           
{'loss': 0.6215, 'learning_rate': 6.8869428522566e-05, 'epoch': 9.18}

 77%|███████▋  | 21487/28080 [42:27:36<12:59:23,  7.09s/it]
 77%|███████▋  | 21488/28080 [42:27:43<12:58:38,  7.09s/it]
                                                           
{'loss': 0.618, 'learning_rate': 6.884955467650441e-05, 'epoch': 9.18}

 77%|███████▋  | 21488/28080 [42:27:43<12:58:38,  7.09s/it]
 77%|███████▋  | 21489/28080 [42:27:50<12:57:29,  7.08s/it]
                                                           
{'loss': 0.5973, 'learning_rate': 6.882968324046262e-05, 'epoch': 9.18}

 77%|███████▋  | 21489/28080 [42:27:50<12:57:29,  7.08s/it]
 77%|███████▋  | 21490/28080 [42:27:57<12:57:14,  7.08s/it]
                                                           
{'loss': 0.5916, 'learning_rate': 6.880981421470497e-05, 'epoch': 9.18}

 77%|███████▋  | 21490/28080 [42:27:57<12:57:14,  7.08s/it]
 77%|███████▋  | 21491/28080 [42:28:04<12:58:18,  7.09s/it]
                                                           
{'loss': 0.6095, 'learning_rate': 6.878994759949583e-05, 'epoch': 9.18}

 77%|███████▋  | 21491/28080 [42:28:04<12:58:18,  7.09s/it]
 77%|███████▋  | 21492/28080 [42:28:11<12:57:51,  7.08s/it]
                                                           
{'loss': 0.5923, 'learning_rate': 6.877008339509941e-05, 'epoch': 9.18}

 77%|███████▋  | 21492/28080 [42:28:11<12:57:51,  7.08s/it]
 77%|███████▋  | 21493/28080 [42:28:18<12:57:58,  7.09s/it]
                                                           
{'loss': 0.6087, 'learning_rate': 6.875022160178016e-05, 'epoch': 9.18}

 77%|███████▋  | 21493/28080 [42:28:18<12:57:58,  7.09s/it]
 77%|███████▋  | 21494/28080 [42:28:25<13:00:18,  7.11s/it]
                                                           
{'loss': 0.6012, 'learning_rate': 6.87303622198022e-05, 'epoch': 9.18}

 77%|███████▋  | 21494/28080 [42:28:25<13:00:18,  7.11s/it]
 77%|███████▋  | 21495/28080 [42:28:32<13:02:16,  7.13s/it]
                                                           
{'loss': 0.5968, 'learning_rate': 6.871050524942979e-05, 'epoch': 9.18}

 77%|███████▋  | 21495/28080 [42:28:32<13:02:16,  7.13s/it]
 77%|███████▋  | 21496/28080 [42:28:40<13:04:14,  7.15s/it]
                                                           
{'loss': 0.5899, 'learning_rate': 6.869065069092697e-05, 'epoch': 9.18}

 77%|███████▋  | 21496/28080 [42:28:40<13:04:14,  7.15s/it]
 77%|███████▋  | 21497/28080 [42:28:47<13:03:08,  7.14s/it]
                                                           
{'loss': 0.6173, 'learning_rate': 6.86707985445581e-05, 'epoch': 9.18}

 77%|███████▋  | 21497/28080 [42:28:47<13:03:08,  7.14s/it]
 77%|███████▋  | 21498/28080 [42:28:54<13:03:18,  7.14s/it]
                                                           
{'loss': 0.6029, 'learning_rate': 6.865094881058712e-05, 'epoch': 9.18}

 77%|███████▋  | 21498/28080 [42:28:54<13:03:18,  7.14s/it]
 77%|███████▋  | 21499/28080 [42:29:01<13:01:22,  7.12s/it]
                                                           
{'loss': 0.6026, 'learning_rate': 6.863110148927831e-05, 'epoch': 9.18}

 77%|███████▋  | 21499/28080 [42:29:01<13:01:22,  7.12s/it]
 77%|███████▋  | 21500/28080 [42:29:08<13:01:07,  7.12s/it]
                                                           
{'loss': 0.5913, 'learning_rate': 6.861125658089546e-05, 'epoch': 9.18}

 77%|███████▋  | 21500/28080 [42:29:08<13:01:07,  7.12s/it]
 77%|███████▋  | 21501/28080 [42:29:15<12:59:20,  7.11s/it]
                                                           
{'loss': 0.5854, 'learning_rate': 6.859141408570275e-05, 'epoch': 9.19}

 77%|███████▋  | 21501/28080 [42:29:15<12:59:20,  7.11s/it]
 77%|███████▋  | 21502/28080 [42:29:22<13:03:04,  7.14s/it]
                                                           
{'loss': 0.5954, 'learning_rate': 6.857157400396407e-05, 'epoch': 9.19}

 77%|███████▋  | 21502/28080 [42:29:22<13:03:04,  7.14s/it]
 77%|███████▋  | 21503/28080 [42:29:29<13:00:13,  7.12s/it]
                                                           
{'loss': 0.5859, 'learning_rate': 6.855173633594353e-05, 'epoch': 9.19}

 77%|███████▋  | 21503/28080 [42:29:29<13:00:13,  7.12s/it]
 77%|███████▋  | 21504/28080 [42:29:36<12:57:35,  7.09s/it]
                                                           
{'loss': 0.6083, 'learning_rate': 6.85319010819049e-05, 'epoch': 9.19}

 77%|███████▋  | 21504/28080 [42:29:36<12:57:35,  7.09s/it]
 77%|███████▋  | 21505/28080 [42:29:44<12:55:37,  7.08s/it]
                                                           
{'loss': 0.6009, 'learning_rate': 6.851206824211214e-05, 'epoch': 9.19}

 77%|███████▋  | 21505/28080 [42:29:44<12:55:37,  7.08s/it]
 77%|███████▋  | 21506/28080 [42:29:51<12:58:14,  7.10s/it]
                                                           
{'loss': 0.6068, 'learning_rate': 6.849223781682901e-05, 'epoch': 9.19}

 77%|███████▋  | 21506/28080 [42:29:51<12:58:14,  7.10s/it]
 77%|███████▋  | 21507/28080 [42:29:58<13:00:09,  7.12s/it]
                                                           
{'loss': 0.6156, 'learning_rate': 6.84724098063195e-05, 'epoch': 9.19}

 77%|███████▋  | 21507/28080 [42:29:58<13:00:09,  7.12s/it]
 77%|███████▋  | 21508/28080 [42:30:05<13:00:10,  7.12s/it]
                                                           
{'loss': 0.6074, 'learning_rate': 6.845258421084726e-05, 'epoch': 9.19}

 77%|███████▋  | 21508/28080 [42:30:05<13:00:10,  7.12s/it]
 77%|███████▋  | 21509/28080 [42:30:12<13:02:17,  7.14s/it]
                                                           
{'loss': 0.6091, 'learning_rate': 6.843276103067614e-05, 'epoch': 9.19}

 77%|███████▋  | 21509/28080 [42:30:12<13:02:17,  7.14s/it]
 77%|███████▋  | 21510/28080 [42:30:19<12:58:40,  7.11s/it]
                                                           
{'loss': 0.5882, 'learning_rate': 6.84129402660697e-05, 'epoch': 9.19}

 77%|███████▋  | 21510/28080 [42:30:19<12:58:40,  7.11s/it]
 77%|███████▋  | 21511/28080 [42:30:26<12:59:43,  7.12s/it]
                                                           
{'loss': 0.591, 'learning_rate': 6.839312191729186e-05, 'epoch': 9.19}

 77%|███████▋  | 21511/28080 [42:30:26<12:59:43,  7.12s/it]
 77%|███████▋  | 21512/28080 [42:30:33<12:59:31,  7.12s/it]
                                                           
{'loss': 0.6024, 'learning_rate': 6.837330598460612e-05, 'epoch': 9.19}

 77%|███████▋  | 21512/28080 [42:30:33<12:59:31,  7.12s/it]
 77%|███████▋  | 21513/28080 [42:30:41<12:59:09,  7.12s/it]
                                                           
{'loss': 0.6267, 'learning_rate': 6.83534924682763e-05, 'epoch': 9.19}

 77%|███████▋  | 21513/28080 [42:30:41<12:59:09,  7.12s/it]
 77%|███████▋  | 21514/28080 [42:30:48<12:58:03,  7.11s/it]
                                                           
{'loss': 0.6053, 'learning_rate': 6.833368136856572e-05, 'epoch': 9.19}

 77%|███████▋  | 21514/28080 [42:30:48<12:58:03,  7.11s/it]
 77%|███████▋  | 21515/28080 [42:30:55<12:58:53,  7.12s/it]
                                                           
{'loss': 0.6077, 'learning_rate': 6.831387268573816e-05, 'epoch': 9.19}

 77%|███████▋  | 21515/28080 [42:30:55<12:58:53,  7.12s/it]
 77%|███████▋  | 21516/28080 [42:31:02<12:58:03,  7.11s/it]
                                                           
{'loss': 0.5928, 'learning_rate': 6.829406642005708e-05, 'epoch': 9.19}

 77%|███████▋  | 21516/28080 [42:31:02<12:58:03,  7.11s/it]
 77%|███████▋  | 21517/28080 [42:31:09<12:58:43,  7.12s/it]
                                                           
{'loss': 0.5911, 'learning_rate': 6.827426257178596e-05, 'epoch': 9.19}

 77%|███████▋  | 21517/28080 [42:31:09<12:58:43,  7.12s/it]
 77%|███████▋  | 21518/28080 [42:31:16<12:55:36,  7.09s/it]
                                                           
{'loss': 0.6069, 'learning_rate': 6.825446114118841e-05, 'epoch': 9.19}

 77%|███████▋  | 21518/28080 [42:31:16<12:55:36,  7.09s/it]
 77%|███████▋  | 21519/28080 [42:31:23<12:54:07,  7.08s/it]
                                                           
{'loss': 0.5832, 'learning_rate': 6.823466212852764e-05, 'epoch': 9.19}

 77%|███████▋  | 21519/28080 [42:31:23<12:54:07,  7.08s/it]
 77%|███████▋  | 21520/28080 [42:31:30<12:59:08,  7.13s/it]
                                                           
{'loss': 0.5825, 'learning_rate': 6.821486553406722e-05, 'epoch': 9.19}

 77%|███████▋  | 21520/28080 [42:31:30<12:59:08,  7.13s/it]
 77%|███████▋  | 21521/28080 [42:31:37<12:58:55,  7.13s/it]
                                                           
{'loss': 0.5882, 'learning_rate': 6.81950713580704e-05, 'epoch': 9.19}

 77%|███████▋  | 21521/28080 [42:31:37<12:58:55,  7.13s/it]
 77%|███████▋  | 21522/28080 [42:31:45<12:59:17,  7.13s/it]
                                                           
{'loss': 0.5763, 'learning_rate': 6.81752796008007e-05, 'epoch': 9.19}

 77%|███████▋  | 21522/28080 [42:31:45<12:59:17,  7.13s/it]
 77%|███████▋  | 21523/28080 [42:31:52<12:59:42,  7.13s/it]
                                                           
{'loss': 0.5962, 'learning_rate': 6.81554902625213e-05, 'epoch': 9.19}

 77%|███████▋  | 21523/28080 [42:31:52<12:59:42,  7.13s/it]
 77%|███████▋  | 21524/28080 [42:31:59<13:00:46,  7.15s/it]
                                                           
{'loss': 0.5945, 'learning_rate': 6.813570334349553e-05, 'epoch': 9.19}

 77%|███████▋  | 21524/28080 [42:31:59<13:00:46,  7.15s/it]
 77%|███████▋  | 21525/28080 [42:32:06<12:59:28,  7.13s/it]
                                                           
{'loss': 0.5784, 'learning_rate': 6.811591884398651e-05, 'epoch': 9.2}

 77%|███████▋  | 21525/28080 [42:32:06<12:59:28,  7.13s/it]
 77%|███████▋  | 21526/28080 [42:32:13<12:58:20,  7.13s/it]
                                                           
{'loss': 0.6051, 'learning_rate': 6.809613676425763e-05, 'epoch': 9.2}

 77%|███████▋  | 21526/28080 [42:32:13<12:58:20,  7.13s/it]
 77%|███████▋  | 21527/28080 [42:32:20<12:57:39,  7.12s/it]
                                                           
{'loss': 0.6245, 'learning_rate': 6.807635710457199e-05, 'epoch': 9.2}

 77%|███████▋  | 21527/28080 [42:32:20<12:57:39,  7.12s/it]
 77%|███████▋  | 21528/28080 [42:32:27<12:57:15,  7.12s/it]
                                                           
{'loss': 0.6058, 'learning_rate': 6.805657986519276e-05, 'epoch': 9.2}

 77%|███████▋  | 21528/28080 [42:32:27<12:57:15,  7.12s/it]
 77%|███████▋  | 21529/28080 [42:32:34<12:55:12,  7.10s/it]
                                                           
{'loss': 0.5926, 'learning_rate': 6.803680504638293e-05, 'epoch': 9.2}

 77%|███████▋  | 21529/28080 [42:32:34<12:55:12,  7.10s/it]
 77%|███████▋  | 21530/28080 [42:32:42<12:55:02,  7.10s/it]
                                                           
{'loss': 0.6171, 'learning_rate': 6.801703264840578e-05, 'epoch': 9.2}

 77%|███████▋  | 21530/28080 [42:32:42<12:55:02,  7.10s/it]
 77%|███████▋  | 21531/28080 [42:32:49<12:54:24,  7.09s/it]
                                                           
{'loss': 0.5905, 'learning_rate': 6.79972626715242e-05, 'epoch': 9.2}

 77%|███████▋  | 21531/28080 [42:32:49<12:54:24,  7.09s/it]
 77%|███████▋  | 21532/28080 [42:32:56<12:55:55,  7.11s/it]
                                                           
{'loss': 0.6106, 'learning_rate': 6.79774951160014e-05, 'epoch': 9.2}

 77%|███████▋  | 21532/28080 [42:32:56<12:55:55,  7.11s/it]
 77%|███████▋  | 21533/28080 [42:33:03<12:53:36,  7.09s/it]
                                                           
{'loss': 0.5968, 'learning_rate': 6.795772998210012e-05, 'epoch': 9.2}

 77%|███████▋  | 21533/28080 [42:33:03<12:53:36,  7.09s/it]
 77%|███████▋  | 21534/28080 [42:33:10<12:51:22,  7.07s/it]
                                                           
{'loss': 0.6034, 'learning_rate': 6.79379672700835e-05, 'epoch': 9.2}

 77%|███████▋  | 21534/28080 [42:33:10<12:51:22,  7.07s/it]
 77%|███████▋  | 21535/28080 [42:33:17<12:54:18,  7.10s/it]
                                                           
{'loss': 0.6035, 'learning_rate': 6.791820698021434e-05, 'epoch': 9.2}

 77%|███████▋  | 21535/28080 [42:33:17<12:54:18,  7.10s/it]
 77%|███████▋  | 21536/28080 [42:33:24<12:52:51,  7.09s/it]
                                                           
{'loss': 0.6203, 'learning_rate': 6.789844911275567e-05, 'epoch': 9.2}

 77%|███████▋  | 21536/28080 [42:33:24<12:52:51,  7.09s/it]
 77%|███████▋  | 21537/28080 [42:33:31<12:48:21,  7.05s/it]
                                                           
{'loss': 0.604, 'learning_rate': 6.787869366797025e-05, 'epoch': 9.2}

 77%|███████▋  | 21537/28080 [42:33:31<12:48:21,  7.05s/it]
 77%|███████▋  | 21538/28080 [42:33:38<12:45:53,  7.02s/it]
                                                           
{'loss': 0.5949, 'learning_rate': 6.785894064612097e-05, 'epoch': 9.2}

 77%|███████▋  | 21538/28080 [42:33:38<12:45:53,  7.02s/it]
 77%|███████▋  | 21539/28080 [42:33:45<12:47:40,  7.04s/it]
                                                           
{'loss': 0.5948, 'learning_rate': 6.783919004747046e-05, 'epoch': 9.2}

 77%|███████▋  | 21539/28080 [42:33:45<12:47:40,  7.04s/it]
 77%|███████▋  | 21540/28080 [42:33:52<12:50:55,  7.07s/it]
                                                           
{'loss': 0.6085, 'learning_rate': 6.781944187228171e-05, 'epoch': 9.2}

 77%|███████▋  | 21540/28080 [42:33:52<12:50:55,  7.07s/it]
 77%|███████▋  | 21541/28080 [42:33:59<12:52:04,  7.08s/it]
                                                           
{'loss': 0.5894, 'learning_rate': 6.779969612081733e-05, 'epoch': 9.2}

 77%|███████▋  | 21541/28080 [42:33:59<12:52:04,  7.08s/it]
 77%|███████▋  | 21542/28080 [42:34:06<12:51:21,  7.08s/it]
                                                           
{'loss': 0.5967, 'learning_rate': 6.777995279334001e-05, 'epoch': 9.2}

 77%|███████▋  | 21542/28080 [42:34:06<12:51:21,  7.08s/it]
 77%|███████▋  | 21543/28080 [42:34:14<12:53:50,  7.10s/it]
                                                           
{'loss': 0.5922, 'learning_rate': 6.776021189011245e-05, 'epoch': 9.2}

 77%|███████▋  | 21543/28080 [42:34:14<12:53:50,  7.10s/it]
 77%|███████▋  | 21544/28080 [42:34:21<12:55:31,  7.12s/it]
                                                           
{'loss': 0.5968, 'learning_rate': 6.774047341139716e-05, 'epoch': 9.2}

 77%|███████▋  | 21544/28080 [42:34:21<12:55:31,  7.12s/it]
 77%|███████▋  | 21545/28080 [42:34:28<12:53:05,  7.10s/it]
                                                           
{'loss': 0.6046, 'learning_rate': 6.772073735745696e-05, 'epoch': 9.2}

 77%|███████▋  | 21545/28080 [42:34:28<12:53:05,  7.10s/it]
 77%|███████▋  | 21546/28080 [42:34:35<12:51:42,  7.09s/it]
                                                           
{'loss': 0.6202, 'learning_rate': 6.770100372855428e-05, 'epoch': 9.2}

 77%|███████▋  | 21546/28080 [42:34:35<12:51:42,  7.09s/it]
 77%|███████▋  | 21547/28080 [42:34:42<12:52:58,  7.10s/it]
                                                           
{'loss': 0.6262, 'learning_rate': 6.768127252495168e-05, 'epoch': 9.2}

 77%|███████▋  | 21547/28080 [42:34:42<12:52:58,  7.10s/it]
 77%|███████▋  | 21548/28080 [42:34:49<12:52:08,  7.09s/it]
                                                           
{'loss': 0.6262, 'learning_rate': 6.766154374691158e-05, 'epoch': 9.21}

 77%|███████▋  | 21548/28080 [42:34:49<12:52:08,  7.09s/it]
 77%|███████▋  | 21549/28080 [42:34:56<12:54:31,  7.12s/it]
                                                           
{'loss': 0.592, 'learning_rate': 6.764181739469663e-05, 'epoch': 9.21}

 77%|███████▋  | 21549/28080 [42:34:56<12:54:31,  7.12s/it]
 77%|███████▋  | 21550/28080 [42:35:03<12:54:03,  7.11s/it]
                                                           
{'loss': 0.597, 'learning_rate': 6.762209346856906e-05, 'epoch': 9.21}

 77%|███████▋  | 21550/28080 [42:35:03<12:54:03,  7.11s/it]
 77%|███████▋  | 21551/28080 [42:35:10<12:50:34,  7.08s/it]
                                                           
{'loss': 0.6159, 'learning_rate': 6.760237196879148e-05, 'epoch': 9.21}

 77%|███████▋  | 21551/28080 [42:35:10<12:50:34,  7.08s/it]
 77%|███████▋  | 21552/28080 [42:35:17<12:51:58,  7.10s/it]
                                                           
{'loss': 0.5944, 'learning_rate': 6.758265289562621e-05, 'epoch': 9.21}

 77%|███████▋  | 21552/28080 [42:35:17<12:51:58,  7.10s/it]
 77%|███████▋  | 21553/28080 [42:35:25<12:53:33,  7.11s/it]
                                                           
{'loss': 0.579, 'learning_rate': 6.756293624933552e-05, 'epoch': 9.21}

 77%|███████▋  | 21553/28080 [42:35:25<12:53:33,  7.11s/it]
 77%|███████▋  | 21554/28080 [42:35:32<12:52:48,  7.11s/it]
                                                           
{'loss': 0.5887, 'learning_rate': 6.754322203018168e-05, 'epoch': 9.21}

 77%|███████▋  | 21554/28080 [42:35:32<12:52:48,  7.11s/it]
 77%|███████▋  | 21555/28080 [42:35:39<12:51:24,  7.09s/it]
                                                           
{'loss': 0.5933, 'learning_rate': 6.75235102384271e-05, 'epoch': 9.21}

 77%|███████▋  | 21555/28080 [42:35:39<12:51:24,  7.09s/it]
 77%|███████▋  | 21556/28080 [42:35:46<12:50:45,  7.09s/it]
                                                           
{'loss': 0.5883, 'learning_rate': 6.750380087433397e-05, 'epoch': 9.21}

 77%|███████▋  | 21556/28080 [42:35:46<12:50:45,  7.09s/it]
 77%|███████▋  | 21557/28080 [42:35:53<12:47:43,  7.06s/it]
                                                           
{'loss': 0.5956, 'learning_rate': 6.748409393816452e-05, 'epoch': 9.21}

 77%|███████▋  | 21557/28080 [42:35:53<12:47:43,  7.06s/it]
 77%|███████▋  | 21558/28080 [42:36:00<12:51:23,  7.10s/it]
                                                           
{'loss': 0.5988, 'learning_rate': 6.746438943018083e-05, 'epoch': 9.21}

 77%|███████▋  | 21558/28080 [42:36:00<12:51:23,  7.10s/it]
 77%|███████▋  | 21559/28080 [42:36:07<12:53:23,  7.12s/it]
                                                           
{'loss': 0.611, 'learning_rate': 6.744468735064518e-05, 'epoch': 9.21}

 77%|███████▋  | 21559/28080 [42:36:07<12:53:23,  7.12s/it]
 77%|███████▋  | 21560/28080 [42:36:14<12:53:22,  7.12s/it]
                                                           
{'loss': 0.6039, 'learning_rate': 6.742498769981958e-05, 'epoch': 9.21}

 77%|███████▋  | 21560/28080 [42:36:14<12:53:22,  7.12s/it]
 77%|███████▋  | 21561/28080 [42:36:21<12:50:13,  7.09s/it]
                                                           
{'loss': 0.5999, 'learning_rate': 6.740529047796632e-05, 'epoch': 9.21}

 77%|███████▋  | 21561/28080 [42:36:21<12:50:13,  7.09s/it]
 77%|███████▋  | 21562/28080 [42:36:28<12:48:47,  7.08s/it]
                                                           
{'loss': 0.5985, 'learning_rate': 6.738559568534714e-05, 'epoch': 9.21}

 77%|███████▋  | 21562/28080 [42:36:28<12:48:47,  7.08s/it]
 77%|███████▋  | 21563/28080 [42:36:35<12:49:41,  7.09s/it]
                                                           
{'loss': 0.591, 'learning_rate': 6.736590332222428e-05, 'epoch': 9.21}

 77%|███████▋  | 21563/28080 [42:36:35<12:49:41,  7.09s/it]
 77%|███████▋  | 21564/28080 [42:36:42<12:47:12,  7.06s/it]
                                                           
{'loss': 0.6224, 'learning_rate': 6.73462133888596e-05, 'epoch': 9.21}

 77%|███████▋  | 21564/28080 [42:36:42<12:47:12,  7.06s/it]
 77%|███████▋  | 21565/28080 [42:36:50<12:48:40,  7.08s/it]
                                                           
{'loss': 0.6145, 'learning_rate': 6.732652588551519e-05, 'epoch': 9.21}

 77%|███████▋  | 21565/28080 [42:36:50<12:48:40,  7.08s/it]
 77%|███████▋  | 21566/28080 [42:36:57<12:48:29,  7.08s/it]
                                                           
{'loss': 0.6223, 'learning_rate': 6.730684081245297e-05, 'epoch': 9.21}

 77%|███████▋  | 21566/28080 [42:36:57<12:48:29,  7.08s/it]
 77%|███████▋  | 21567/28080 [42:37:04<12:47:33,  7.07s/it]
                                                           
{'loss': 0.5991, 'learning_rate': 6.728715816993461e-05, 'epoch': 9.21}

 77%|███████▋  | 21567/28080 [42:37:04<12:47:33,  7.07s/it]
 77%|███████▋  | 21568/28080 [42:37:11<12:49:27,  7.09s/it]
                                                           
{'loss': 0.5858, 'learning_rate': 6.726747795822219e-05, 'epoch': 9.21}

 77%|███████▋  | 21568/28080 [42:37:11<12:49:27,  7.09s/it]
 77%|███████▋  | 21569/28080 [42:37:18<12:48:40,  7.08s/it]
                                                           
{'loss': 0.5918, 'learning_rate': 6.72478001775774e-05, 'epoch': 9.21}

 77%|███████▋  | 21569/28080 [42:37:18<12:48:40,  7.08s/it]
 77%|███████▋  | 21570/28080 [42:37:25<12:49:59,  7.10s/it]
                                                           
{'loss': 0.6054, 'learning_rate': 6.722812482826215e-05, 'epoch': 9.21}

 77%|███████▋  | 21570/28080 [42:37:25<12:49:59,  7.10s/it]
 77%|███████▋  | 21571/28080 [42:37:32<12:48:37,  7.09s/it]
                                                           
{'loss': 0.6179, 'learning_rate': 6.720845191053815e-05, 'epoch': 9.21}

 77%|███████▋  | 21571/28080 [42:37:32<12:48:37,  7.09s/it]
 77%|███████▋  | 21572/28080 [42:37:39<12:51:46,  7.12s/it]
                                                           
{'loss': 0.6183, 'learning_rate': 6.718878142466711e-05, 'epoch': 9.22}

 77%|███████▋  | 21572/28080 [42:37:39<12:51:46,  7.12s/it]
 77%|███████▋  | 21573/28080 [42:37:46<12:52:07,  7.12s/it]
                                                           
{'loss': 0.625, 'learning_rate': 6.716911337091069e-05, 'epoch': 9.22}

 77%|███████▋  | 21573/28080 [42:37:46<12:52:07,  7.12s/it]
 77%|███████▋  | 21574/28080 [42:37:53<12:49:57,  7.10s/it]
                                                           
{'loss': 0.5939, 'learning_rate': 6.714944774953067e-05, 'epoch': 9.22}

 77%|███████▋  | 21574/28080 [42:37:53<12:49:57,  7.10s/it]
 77%|███████▋  | 21575/28080 [42:38:01<12:49:17,  7.10s/it]
                                                           
{'loss': 0.5997, 'learning_rate': 6.712978456078858e-05, 'epoch': 9.22}

 77%|███████▋  | 21575/28080 [42:38:01<12:49:17,  7.10s/it]
 77%|███████▋  | 21576/28080 [42:38:08<12:48:38,  7.09s/it]
                                                           
{'loss': 0.601, 'learning_rate': 6.711012380494607e-05, 'epoch': 9.22}

 77%|███████▋  | 21576/28080 [42:38:08<12:48:38,  7.09s/it]
 77%|███████▋  | 21577/28080 [42:38:15<12:47:44,  7.08s/it]
                                                           
{'loss': 0.6044, 'learning_rate': 6.709046548226464e-05, 'epoch': 9.22}

 77%|███████▋  | 21577/28080 [42:38:15<12:47:44,  7.08s/it]
 77%|███████▋  | 21578/28080 [42:38:22<12:50:05,  7.11s/it]
                                                           
{'loss': 0.5968, 'learning_rate': 6.707080959300591e-05, 'epoch': 9.22}

 77%|███████▋  | 21578/28080 [42:38:22<12:50:05,  7.11s/it]
 77%|███████▋  | 21579/28080 [42:38:29<12:49:53,  7.11s/it]
                                                           
{'loss': 0.5974, 'learning_rate': 6.705115613743126e-05, 'epoch': 9.22}

 77%|███████▋  | 21579/28080 [42:38:29<12:49:53,  7.11s/it]
 77%|███████▋  | 21580/28080 [42:38:36<12:49:20,  7.10s/it]
                                                           
{'loss': 0.6063, 'learning_rate': 6.703150511580242e-05, 'epoch': 9.22}

 77%|███████▋  | 21580/28080 [42:38:36<12:49:20,  7.10s/it]
 77%|███████▋  | 21581/28080 [42:38:43<12:49:05,  7.10s/it]
                                                           
{'loss': 0.6028, 'learning_rate': 6.701185652838049e-05, 'epoch': 9.22}

 77%|███████▋  | 21581/28080 [42:38:43<12:49:05,  7.10s/it]
 77%|███████▋  | 21582/28080 [42:38:50<12:46:44,  7.08s/it]
                                                           
{'loss': 0.583, 'learning_rate': 6.699221037542708e-05, 'epoch': 9.22}

 77%|███████▋  | 21582/28080 [42:38:50<12:46:44,  7.08s/it]
 77%|███████▋  | 21583/28080 [42:38:57<12:46:17,  7.08s/it]
                                                           
{'loss': 0.6279, 'learning_rate': 6.697256665720344e-05, 'epoch': 9.22}

 77%|███████▋  | 21583/28080 [42:38:57<12:46:17,  7.08s/it]
 77%|███████▋  | 21584/28080 [42:39:04<12:49:11,  7.10s/it]
                                                           
{'loss': 0.5988, 'learning_rate': 6.695292537397107e-05, 'epoch': 9.22}

 77%|███████▋  | 21584/28080 [42:39:04<12:49:11,  7.10s/it]
 77%|███████▋  | 21585/28080 [42:39:11<12:48:37,  7.10s/it]
                                                           
{'loss': 0.6311, 'learning_rate': 6.693328652599121e-05, 'epoch': 9.22}

 77%|███████▋  | 21585/28080 [42:39:11<12:48:37,  7.10s/it]
 77%|███████▋  | 21586/28080 [42:39:19<12:47:10,  7.09s/it]
                                                           
{'loss': 0.6184, 'learning_rate': 6.691365011352507e-05, 'epoch': 9.22}

 77%|███████▋  | 21586/28080 [42:39:19<12:47:10,  7.09s/it]
 77%|███████▋  | 21587/28080 [42:39:26<12:49:19,  7.11s/it]
                                                           
{'loss': 0.6081, 'learning_rate': 6.689401613683391e-05, 'epoch': 9.22}

 77%|███████▋  | 21587/28080 [42:39:26<12:49:19,  7.11s/it]
 77%|███████▋  | 21588/28080 [42:39:33<12:46:48,  7.09s/it]
                                                           
{'loss': 0.5972, 'learning_rate': 6.687438459617901e-05, 'epoch': 9.22}

 77%|███████▋  | 21588/28080 [42:39:33<12:46:48,  7.09s/it]
 77%|███████▋  | 21589/28080 [42:39:40<12:42:29,  7.05s/it]
                                                           
{'loss': 0.6059, 'learning_rate': 6.68547554918215e-05, 'epoch': 9.22}

 77%|███████▋  | 21589/28080 [42:39:40<12:42:29,  7.05s/it]
 77%|███████▋  | 21590/28080 [42:39:47<12:43:30,  7.06s/it]
                                                           
{'loss': 0.6089, 'learning_rate': 6.683512882402251e-05, 'epoch': 9.22}

 77%|███████▋  | 21590/28080 [42:39:47<12:43:30,  7.06s/it]
 77%|███████▋  | 21591/28080 [42:39:54<12:45:08,  7.07s/it]
                                                           
{'loss': 0.5944, 'learning_rate': 6.68155045930432e-05, 'epoch': 9.22}

 77%|███████▋  | 21591/28080 [42:39:54<12:45:08,  7.07s/it]
 77%|███████▋  | 21592/28080 [42:40:01<12:43:40,  7.06s/it]
                                                           
{'loss': 0.61, 'learning_rate': 6.679588279914456e-05, 'epoch': 9.22}

 77%|███████▋  | 21592/28080 [42:40:01<12:43:40,  7.06s/it]
 77%|███████▋  | 21593/28080 [42:40:08<12:43:55,  7.07s/it]
                                                           
{'loss': 0.608, 'learning_rate': 6.677626344258774e-05, 'epoch': 9.22}

 77%|███████▋  | 21593/28080 [42:40:08<12:43:55,  7.07s/it]
 77%|███████▋  | 21594/28080 [42:40:15<12:46:22,  7.09s/it]
                                                           
{'loss': 0.6113, 'learning_rate': 6.675664652363372e-05, 'epoch': 9.22}

 77%|███████▋  | 21594/28080 [42:40:15<12:46:22,  7.09s/it]
 77%|███████▋  | 21595/28080 [42:40:22<12:46:24,  7.09s/it]
                                                           
{'loss': 0.6168, 'learning_rate': 6.673703204254347e-05, 'epoch': 9.23}

 77%|███████▋  | 21595/28080 [42:40:22<12:46:24,  7.09s/it]
 77%|███████▋  | 21596/28080 [42:40:29<12:46:07,  7.09s/it]
                                                           
{'loss': 0.6227, 'learning_rate': 6.67174199995779e-05, 'epoch': 9.23}

 77%|███████▋  | 21596/28080 [42:40:29<12:46:07,  7.09s/it]
 77%|███████▋  | 21597/28080 [42:40:36<12:47:59,  7.11s/it]
                                                           
{'loss': 0.6141, 'learning_rate': 6.669781039499803e-05, 'epoch': 9.23}

 77%|███████▋  | 21597/28080 [42:40:36<12:47:59,  7.11s/it]
 77%|███████▋  | 21598/28080 [42:40:44<12:48:45,  7.12s/it]
                                                           
{'loss': 0.6168, 'learning_rate': 6.667820322906463e-05, 'epoch': 9.23}

 77%|███████▋  | 21598/28080 [42:40:44<12:48:45,  7.12s/it]
 77%|███████▋  | 21599/28080 [42:40:51<12:50:09,  7.13s/it]
                                                           
{'loss': 0.593, 'learning_rate': 6.665859850203867e-05, 'epoch': 9.23}

 77%|███████▋  | 21599/28080 [42:40:51<12:50:09,  7.13s/it]
 77%|███████▋  | 21600/28080 [42:40:58<12:51:47,  7.15s/it]
                                                           
{'loss': 0.61, 'learning_rate': 6.663899621418093e-05, 'epoch': 9.23}

 77%|███████▋  | 21600/28080 [42:40:58<12:51:47,  7.15s/it]
 77%|███████▋  | 21601/28080 [42:41:05<12:50:20,  7.13s/it]
                                                           
{'loss': 0.616, 'learning_rate': 6.661939636575214e-05, 'epoch': 9.23}

 77%|███████▋  | 21601/28080 [42:41:05<12:50:20,  7.13s/it]
 77%|███████▋  | 21602/28080 [42:41:12<12:47:22,  7.11s/it]
                                                           
{'loss': 0.5896, 'learning_rate': 6.659979895701307e-05, 'epoch': 9.23}

 77%|███████▋  | 21602/28080 [42:41:12<12:47:22,  7.11s/it]
 77%|███████▋  | 21603/28080 [42:41:19<12:46:58,  7.10s/it]
                                                           
{'loss': 0.6011, 'learning_rate': 6.658020398822454e-05, 'epoch': 9.23}

 77%|███████▋  | 21603/28080 [42:41:19<12:46:58,  7.10s/it]
 77%|███████▋  | 21604/28080 [42:41:26<12:47:43,  7.11s/it]
                                                           
{'loss': 0.6306, 'learning_rate': 6.656061145964717e-05, 'epoch': 9.23}

 77%|███████▋  | 21604/28080 [42:41:26<12:47:43,  7.11s/it]
 77%|███████▋  | 21605/28080 [42:41:34<12:49:45,  7.13s/it]
                                                           
{'loss': 0.6216, 'learning_rate': 6.65410213715416e-05, 'epoch': 9.23}

 77%|███████▋  | 21605/28080 [42:41:34<12:49:45,  7.13s/it]
 77%|███████▋  | 21606/28080 [42:41:41<12:50:27,  7.14s/it]
                                                           
{'loss': 0.5911, 'learning_rate': 6.652143372416843e-05, 'epoch': 9.23}

 77%|███████▋  | 21606/28080 [42:41:41<12:50:27,  7.14s/it]
 77%|███████▋  | 21607/28080 [42:41:48<12:47:49,  7.12s/it]
                                                           
{'loss': 0.5952, 'learning_rate': 6.650184851778837e-05, 'epoch': 9.23}

 77%|███████▋  | 21607/28080 [42:41:48<12:47:49,  7.12s/it]
 77%|███████▋  | 21608/28080 [42:41:55<12:48:08,  7.12s/it]
                                                           
{'loss': 0.5892, 'learning_rate': 6.648226575266189e-05, 'epoch': 9.23}

 77%|███████▋  | 21608/28080 [42:41:55<12:48:08,  7.12s/it]
 77%|███████▋  | 21609/28080 [42:42:02<12:48:10,  7.12s/it]
                                                           
{'loss': 0.6001, 'learning_rate': 6.646268542904957e-05, 'epoch': 9.23}

 77%|███████▋  | 21609/28080 [42:42:02<12:48:10,  7.12s/it]
 77%|███████▋  | 21610/28080 [42:42:09<12:43:03,  7.08s/it]
                                                           
{'loss': 0.6075, 'learning_rate': 6.644310754721178e-05, 'epoch': 9.23}

 77%|███████▋  | 21610/28080 [42:42:09<12:43:03,  7.08s/it]
 77%|███████▋  | 21611/28080 [42:42:16<12:46:06,  7.11s/it]
                                                           
{'loss': 0.5981, 'learning_rate': 6.642353210740914e-05, 'epoch': 9.23}

 77%|███████▋  | 21611/28080 [42:42:16<12:46:06,  7.11s/it]
 77%|███████▋  | 21612/28080 [42:42:23<12:49:46,  7.14s/it]
                                                           
{'loss': 0.6097, 'learning_rate': 6.640395910990197e-05, 'epoch': 9.23}

 77%|███████▋  | 21612/28080 [42:42:23<12:49:46,  7.14s/it]
 77%|███████▋  | 21613/28080 [42:42:31<12:50:59,  7.15s/it]
                                                           
{'loss': 0.6104, 'learning_rate': 6.63843885549508e-05, 'epoch': 9.23}

 77%|███████▋  | 21613/28080 [42:42:31<12:50:59,  7.15s/it]
 77%|███████▋  | 21614/28080 [42:42:38<12:49:05,  7.14s/it]
                                                           
{'loss': 0.6196, 'learning_rate': 6.636482044281589e-05, 'epoch': 9.23}

 77%|███████▋  | 21614/28080 [42:42:38<12:49:05,  7.14s/it]
 77%|███████▋  | 21615/28080 [42:42:45<12:52:39,  7.17s/it]
                                                           
{'loss': 0.5922, 'learning_rate': 6.634525477375761e-05, 'epoch': 9.23}

 77%|███████▋  | 21615/28080 [42:42:45<12:52:39,  7.17s/it]
 77%|███████▋  | 21616/28080 [42:42:52<12:53:25,  7.18s/it]
                                                           
{'loss': 0.5802, 'learning_rate': 6.632569154803624e-05, 'epoch': 9.23}

 77%|███████▋  | 21616/28080 [42:42:52<12:53:25,  7.18s/it]
 77%|███████▋  | 21617/28080 [42:42:59<12:52:45,  7.17s/it]
                                                           
{'loss': 0.5942, 'learning_rate': 6.6306130765912e-05, 'epoch': 9.23}

 77%|███████▋  | 21617/28080 [42:42:59<12:52:45,  7.17s/it]
 77%|███████▋  | 21618/28080 [42:43:06<12:48:43,  7.14s/it]
                                                           
{'loss': 0.6251, 'learning_rate': 6.628657242764524e-05, 'epoch': 9.24}

 77%|███████▋  | 21618/28080 [42:43:06<12:48:43,  7.14s/it]
 77%|███████▋  | 21619/28080 [42:43:13<12:48:25,  7.14s/it]
                                                           
{'loss': 0.6007, 'learning_rate': 6.626701653349612e-05, 'epoch': 9.24}

 77%|███████▋  | 21619/28080 [42:43:13<12:48:25,  7.14s/it]
 77%|███████▋  | 21620/28080 [42:43:21<12:48:55,  7.14s/it]
                                                           
{'loss': 0.5913, 'learning_rate': 6.624746308372479e-05, 'epoch': 9.24}

 77%|███████▋  | 21620/28080 [42:43:21<12:48:55,  7.14s/it]
 77%|███████▋  | 21621/28080 [42:43:28<12:47:52,  7.13s/it]
                                                           
{'loss': 0.6109, 'learning_rate': 6.622791207859132e-05, 'epoch': 9.24}

 77%|███████▋  | 21621/28080 [42:43:28<12:47:52,  7.13s/it]
 77%|███████▋  | 21622/28080 [42:43:35<12:46:48,  7.12s/it]
                                                           
{'loss': 0.6083, 'learning_rate': 6.620836351835599e-05, 'epoch': 9.24}

 77%|███████▋  | 21622/28080 [42:43:35<12:46:48,  7.12s/it]
 77%|███████▋  | 21623/28080 [42:43:42<12:45:58,  7.12s/it]
                                                           
{'loss': 0.6164, 'learning_rate': 6.618881740327875e-05, 'epoch': 9.24}

 77%|███████▋  | 21623/28080 [42:43:42<12:45:58,  7.12s/it]
 77%|███████▋  | 21624/28080 [42:43:49<12:47:12,  7.13s/it]
                                                           
{'loss': 0.6173, 'learning_rate': 6.61692737336197e-05, 'epoch': 9.24}

 77%|███████▋  | 21624/28080 [42:43:49<12:47:12,  7.13s/it]
 77%|███████▋  | 21625/28080 [42:43:56<12:46:53,  7.13s/it]
                                                           
{'loss': 0.5928, 'learning_rate': 6.614973250963871e-05, 'epoch': 9.24}

 77%|███████▋  | 21625/28080 [42:43:56<12:46:53,  7.13s/it]
 77%|███████▋  | 21626/28080 [42:44:03<12:47:59,  7.14s/it]
                                                           
{'loss': 0.6126, 'learning_rate': 6.613019373159593e-05, 'epoch': 9.24}

 77%|███████▋  | 21626/28080 [42:44:03<12:47:59,  7.14s/it]
 77%|███████▋  | 21627/28080 [42:44:10<12:45:04,  7.11s/it]
                                                           
{'loss': 0.5924, 'learning_rate': 6.611065739975116e-05, 'epoch': 9.24}

 77%|███████▋  | 21627/28080 [42:44:10<12:45:04,  7.11s/it]
 77%|███████▋  | 21628/28080 [42:44:18<12:44:05,  7.11s/it]
                                                           
{'loss': 0.6167, 'learning_rate': 6.609112351436455e-05, 'epoch': 9.24}

 77%|███████▋  | 21628/28080 [42:44:18<12:44:05,  7.11s/it]
 77%|███████▋  | 21629/28080 [42:44:25<12:46:10,  7.13s/it]
                                                           
{'loss': 0.6168, 'learning_rate': 6.607159207569568e-05, 'epoch': 9.24}

 77%|███████▋  | 21629/28080 [42:44:25<12:46:10,  7.13s/it]
 77%|███████▋  | 21630/28080 [42:44:32<12:44:33,  7.11s/it]
                                                           
{'loss': 0.6103, 'learning_rate': 6.605206308400457e-05, 'epoch': 9.24}

 77%|███████▋  | 21630/28080 [42:44:32<12:44:33,  7.11s/it]
 77%|███████▋  | 21631/28080 [42:44:39<12:42:25,  7.09s/it]
                                                           
{'loss': 0.6069, 'learning_rate': 6.603253653955094e-05, 'epoch': 9.24}

 77%|███████▋  | 21631/28080 [42:44:39<12:42:25,  7.09s/it]
 77%|███████▋  | 21632/28080 [42:44:46<12:45:42,  7.13s/it]
                                                           
{'loss': 0.5859, 'learning_rate': 6.601301244259469e-05, 'epoch': 9.24}

 77%|███████▋  | 21632/28080 [42:44:46<12:45:42,  7.13s/it]
 77%|███████▋  | 21633/28080 [42:44:53<12:45:50,  7.13s/it]
                                                           
{'loss': 0.6005, 'learning_rate': 6.599349079339551e-05, 'epoch': 9.24}

 77%|███████▋  | 21633/28080 [42:44:53<12:45:50,  7.13s/it]
 77%|███████▋  | 21634/28080 [42:45:00<12:45:51,  7.13s/it]
                                                           
{'loss': 0.592, 'learning_rate': 6.597397159221311e-05, 'epoch': 9.24}

 77%|███████▋  | 21634/28080 [42:45:00<12:45:51,  7.13s/it]
 77%|███████▋  | 21635/28080 [42:45:07<12:44:58,  7.12s/it]
                                                           
{'loss': 0.6124, 'learning_rate': 6.595445483930706e-05, 'epoch': 9.24}

 77%|███████▋  | 21635/28080 [42:45:07<12:44:58,  7.12s/it]
 77%|███████▋  | 21636/28080 [42:45:15<12:44:52,  7.12s/it]
                                                           
{'loss': 0.6105, 'learning_rate': 6.593494053493723e-05, 'epoch': 9.24}

 77%|███████▋  | 21636/28080 [42:45:15<12:44:52,  7.12s/it]
 77%|███████▋  | 21637/28080 [42:45:22<12:42:40,  7.10s/it]
                                                           
{'loss': 0.6153, 'learning_rate': 6.591542867936309e-05, 'epoch': 9.24}

 77%|███████▋  | 21637/28080 [42:45:22<12:42:40,  7.10s/it]
 77%|███████▋  | 21638/28080 [42:45:29<12:43:28,  7.11s/it]
                                                           
{'loss': 0.585, 'learning_rate': 6.589591927284431e-05, 'epoch': 9.24}

 77%|███████▋  | 21638/28080 [42:45:29<12:43:28,  7.11s/it]
 77%|███████▋  | 21639/28080 [42:45:36<12:35:53,  7.04s/it]
                                                           
{'loss': 0.6086, 'learning_rate': 6.587641231564035e-05, 'epoch': 9.24}

 77%|███████▋  | 21639/28080 [42:45:36<12:35:53,  7.04s/it]
 77%|███████▋  | 21640/28080 [42:45:43<12:40:34,  7.09s/it]
                                                           
{'loss': 0.598, 'learning_rate': 6.58569078080107e-05, 'epoch': 9.24}

 77%|███████▋  | 21640/28080 [42:45:43<12:40:34,  7.09s/it]
 77%|███████▋  | 21641/28080 [42:45:50<12:41:27,  7.10s/it]
                                                           
{'loss': 0.591, 'learning_rate': 6.583740575021504e-05, 'epoch': 9.24}

 77%|███████▋  | 21641/28080 [42:45:50<12:41:27,  7.10s/it]
 77%|███████▋  | 21642/28080 [42:45:57<12:42:29,  7.11s/it]
                                                           
{'loss': 0.6003, 'learning_rate': 6.581790614251268e-05, 'epoch': 9.25}

 77%|███████▋  | 21642/28080 [42:45:57<12:42:29,  7.11s/it]
 77%|███████▋  | 21643/28080 [42:46:04<12:40:58,  7.09s/it]
                                                           
{'loss': 0.6363, 'learning_rate': 6.579840898516306e-05, 'epoch': 9.25}

 77%|███████▋  | 21643/28080 [42:46:04<12:40:58,  7.09s/it]
 77%|███████▋  | 21644/28080 [42:46:11<12:38:20,  7.07s/it]
                                                           
{'loss': 0.588, 'learning_rate': 6.577891427842553e-05, 'epoch': 9.25}

 77%|███████▋  | 21644/28080 [42:46:11<12:38:20,  7.07s/it]
 77%|███████▋  | 21645/28080 [42:46:18<12:38:22,  7.07s/it]
                                                           
{'loss': 0.6215, 'learning_rate': 6.575942202255955e-05, 'epoch': 9.25}

 77%|███████▋  | 21645/28080 [42:46:18<12:38:22,  7.07s/it]
 77%|███████▋  | 21646/28080 [42:46:25<12:41:12,  7.10s/it]
                                                           
{'loss': 0.5965, 'learning_rate': 6.573993221782431e-05, 'epoch': 9.25}

 77%|███████▋  | 21646/28080 [42:46:25<12:41:12,  7.10s/it]
 77%|███████▋  | 21647/28080 [42:46:32<12:39:57,  7.09s/it]
                                                           
{'loss': 0.6232, 'learning_rate': 6.572044486447933e-05, 'epoch': 9.25}

 77%|███████▋  | 21647/28080 [42:46:32<12:39:57,  7.09s/it]
 77%|███████▋  | 21648/28080 [42:46:40<12:41:57,  7.11s/it]
                                                           
{'loss': 0.5945, 'learning_rate': 6.570095996278358e-05, 'epoch': 9.25}

 77%|███████▋  | 21648/28080 [42:46:40<12:41:57,  7.11s/it]
 77%|███████▋  | 21649/28080 [42:46:47<12:40:57,  7.10s/it]
                                                           
{'loss': 0.5803, 'learning_rate': 6.56814775129965e-05, 'epoch': 9.25}

 77%|███████▋  | 21649/28080 [42:46:47<12:40:57,  7.10s/it]
 77%|███████▋  | 21650/28080 [42:46:54<12:42:27,  7.11s/it]
                                                           
{'loss': 0.6013, 'learning_rate': 6.566199751537716e-05, 'epoch': 9.25}

 77%|███████▋  | 21650/28080 [42:46:54<12:42:27,  7.11s/it]
 77%|███████▋  | 21651/28080 [42:47:01<12:42:39,  7.12s/it]
                                                           
{'loss': 0.5687, 'learning_rate': 6.564251997018481e-05, 'epoch': 9.25}

 77%|███████▋  | 21651/28080 [42:47:01<12:42:39,  7.12s/it]
 77%|███████▋  | 21652/28080 [42:47:08<12:41:30,  7.11s/it]
                                                           
{'loss': 0.6061, 'learning_rate': 6.562304487767856e-05, 'epoch': 9.25}

 77%|███████▋  | 21652/28080 [42:47:08<12:41:30,  7.11s/it]
 77%|███████▋  | 21653/28080 [42:47:15<12:39:36,  7.09s/it]
                                                           
{'loss': 0.5943, 'learning_rate': 6.560357223811748e-05, 'epoch': 9.25}

 77%|███████▋  | 21653/28080 [42:47:15<12:39:36,  7.09s/it]
 77%|███████▋  | 21654/28080 [42:47:22<12:37:20,  7.07s/it]
                                                           
{'loss': 0.6203, 'learning_rate': 6.558410205176057e-05, 'epoch': 9.25}

 77%|███████▋  | 21654/28080 [42:47:22<12:37:20,  7.07s/it]
 77%|███████▋  | 21655/28080 [42:47:29<12:35:23,  7.05s/it]
                                                           
{'loss': 0.6236, 'learning_rate': 6.5564634318867e-05, 'epoch': 9.25}

 77%|███████▋  | 21655/28080 [42:47:29<12:35:23,  7.05s/it]
 77%|███████▋  | 21656/28080 [42:47:36<12:37:37,  7.08s/it]
                                                           
{'loss': 0.6065, 'learning_rate': 6.55451690396957e-05, 'epoch': 9.25}

 77%|███████▋  | 21656/28080 [42:47:36<12:37:37,  7.08s/it]
 77%|███████▋  | 21657/28080 [42:47:43<12:33:44,  7.04s/it]
                                                           
{'loss': 0.6042, 'learning_rate': 6.552570621450562e-05, 'epoch': 9.25}

 77%|███████▋  | 21657/28080 [42:47:43<12:33:44,  7.04s/it]
 77%|███████▋  | 21658/28080 [42:47:50<12:34:26,  7.05s/it]
                                                           
{'loss': 0.6145, 'learning_rate': 6.550624584355566e-05, 'epoch': 9.25}

 77%|███████▋  | 21658/28080 [42:47:50<12:34:26,  7.05s/it]
 77%|███████▋  | 21659/28080 [42:47:57<12:37:08,  7.07s/it]
                                                           
{'loss': 0.5868, 'learning_rate': 6.548678792710483e-05, 'epoch': 9.25}

 77%|███████▋  | 21659/28080 [42:47:57<12:37:08,  7.07s/it]
 77%|███████▋  | 21660/28080 [42:48:04<12:36:22,  7.07s/it]
                                                           
{'loss': 0.589, 'learning_rate': 6.546733246541187e-05, 'epoch': 9.25}

 77%|███████▋  | 21660/28080 [42:48:04<12:36:22,  7.07s/it]
 77%|███████▋  | 21661/28080 [42:48:12<12:37:58,  7.08s/it]
                                                           
{'loss': 0.5986, 'learning_rate': 6.544787945873573e-05, 'epoch': 9.25}

 77%|███████▋  | 21661/28080 [42:48:12<12:37:58,  7.08s/it]
 77%|███████▋  | 21662/28080 [42:48:18<12:33:16,  7.04s/it]
                                                           
{'loss': 0.607, 'learning_rate': 6.54284289073352e-05, 'epoch': 9.25}

 77%|███████▋  | 21662/28080 [42:48:18<12:33:16,  7.04s/it]
 77%|███████▋  | 21663/28080 [42:48:26<12:33:55,  7.05s/it]
                                                           
{'loss': 0.5973, 'learning_rate': 6.540898081146898e-05, 'epoch': 9.25}

 77%|███████▋  | 21663/28080 [42:48:26<12:33:55,  7.05s/it]
 77%|███████▋  | 21664/28080 [42:48:33<12:35:10,  7.06s/it]
                                                           
{'loss': 0.5966, 'learning_rate': 6.538953517139584e-05, 'epoch': 9.25}

 77%|███████▋  | 21664/28080 [42:48:33<12:35:10,  7.06s/it]
 77%|███████▋  | 21665/28080 [42:48:40<12:37:17,  7.08s/it]
                                                           
{'loss': 0.5981, 'learning_rate': 6.537009198737443e-05, 'epoch': 9.26}

 77%|███████▋  | 21665/28080 [42:48:40<12:37:17,  7.08s/it]
 77%|███████▋  | 21666/28080 [42:48:47<12:40:24,  7.11s/it]
                                                           
{'loss': 0.6078, 'learning_rate': 6.535065125966352e-05, 'epoch': 9.26}

 77%|███████▋  | 21666/28080 [42:48:47<12:40:24,  7.11s/it]
 77%|███████▋  | 21667/28080 [42:48:54<12:41:01,  7.12s/it]
                                                           
{'loss': 0.5975, 'learning_rate': 6.53312129885217e-05, 'epoch': 9.26}

 77%|███████▋  | 21667/28080 [42:48:54<12:41:01,  7.12s/it]
 77%|███████▋  | 21668/28080 [42:49:01<12:36:49,  7.08s/it]
                                                           
{'loss': 0.5936, 'learning_rate': 6.531177717420761e-05, 'epoch': 9.26}

 77%|███████▋  | 21668/28080 [42:49:01<12:36:49,  7.08s/it]
 77%|███████▋  | 21669/28080 [42:49:08<12:32:20,  7.04s/it]
                                                           
{'loss': 0.6045, 'learning_rate': 6.529234381697971e-05, 'epoch': 9.26}

 77%|███████▋  | 21669/28080 [42:49:08<12:32:20,  7.04s/it]
 77%|███████▋  | 21670/28080 [42:49:15<12:32:12,  7.04s/it]
                                                           
{'loss': 0.614, 'learning_rate': 6.527291291709669e-05, 'epoch': 9.26}

 77%|███████▋  | 21670/28080 [42:49:15<12:32:12,  7.04s/it]
 77%|███████▋  | 21671/28080 [42:49:22<12:35:10,  7.07s/it]
                                                           
{'loss': 0.6011, 'learning_rate': 6.525348447481699e-05, 'epoch': 9.26}

 77%|███████▋  | 21671/28080 [42:49:22<12:35:10,  7.07s/it]
 77%|███████▋  | 21672/28080 [42:49:29<12:37:16,  7.09s/it]
                                                           
{'loss': 0.5964, 'learning_rate': 6.52340584903991e-05, 'epoch': 9.26}

 77%|███████▋  | 21672/28080 [42:49:29<12:37:16,  7.09s/it]
 77%|███████▋  | 21673/28080 [42:49:36<12:38:33,  7.10s/it]
                                                           
{'loss': 0.61, 'learning_rate': 6.521463496410135e-05, 'epoch': 9.26}

 77%|███████▋  | 21673/28080 [42:49:36<12:38:33,  7.10s/it]
 77%|███████▋  | 21674/28080 [42:49:44<12:38:02,  7.10s/it]
                                                           
{'loss': 0.6158, 'learning_rate': 6.519521389618236e-05, 'epoch': 9.26}

 77%|███████▋  | 21674/28080 [42:49:44<12:38:02,  7.10s/it]
 77%|███████▋  | 21675/28080 [42:49:51<12:39:24,  7.11s/it]
                                                           
{'loss': 0.5906, 'learning_rate': 6.517579528690028e-05, 'epoch': 9.26}

 77%|███████▋  | 21675/28080 [42:49:51<12:39:24,  7.11s/it]
 77%|███████▋  | 21676/28080 [42:49:58<12:35:46,  7.08s/it]
                                                           
{'loss': 0.5906, 'learning_rate': 6.515637913651377e-05, 'epoch': 9.26}

 77%|███████▋  | 21676/28080 [42:49:58<12:35:46,  7.08s/it]
 77%|███████▋  | 21677/28080 [42:50:05<12:38:06,  7.10s/it]
                                                           
{'loss': 0.6008, 'learning_rate': 6.513696544528075e-05, 'epoch': 9.26}

 77%|███████▋  | 21677/28080 [42:50:05<12:38:06,  7.10s/it]
 77%|███████▋  | 21678/28080 [42:50:12<12:38:33,  7.11s/it]
                                                           
{'loss': 0.5872, 'learning_rate': 6.511755421345977e-05, 'epoch': 9.26}

 77%|███████▋  | 21678/28080 [42:50:12<12:38:33,  7.11s/it]
 77%|███████▋  | 21679/28080 [42:50:19<12:36:57,  7.10s/it]
                                                           
{'loss': 0.5943, 'learning_rate': 6.509814544130893e-05, 'epoch': 9.26}

 77%|███████▋  | 21679/28080 [42:50:19<12:36:57,  7.10s/it]
 77%|███████▋  | 21680/28080 [42:50:26<12:35:45,  7.09s/it]
                                                           
{'loss': 0.598, 'learning_rate': 6.50787391290866e-05, 'epoch': 9.26}

 77%|███████▋  | 21680/28080 [42:50:26<12:35:45,  7.09s/it]
 77%|███████▋  | 21681/28080 [42:50:33<12:35:47,  7.09s/it]
                                                           
{'loss': 0.5923, 'learning_rate': 6.505933527705085e-05, 'epoch': 9.26}

 77%|███████▋  | 21681/28080 [42:50:33<12:35:47,  7.09s/it]
 77%|███████▋  | 21682/28080 [42:50:40<12:38:59,  7.12s/it]
                                                           
{'loss': 0.6318, 'learning_rate': 6.50399338854599e-05, 'epoch': 9.26}

 77%|███████▋  | 21682/28080 [42:50:40<12:38:59,  7.12s/it]
 77%|███████▋  | 21683/28080 [42:50:47<12:37:11,  7.10s/it]
                                                           
{'loss': 0.6172, 'learning_rate': 6.502053495457169e-05, 'epoch': 9.26}

 77%|███████▋  | 21683/28080 [42:50:47<12:37:11,  7.10s/it]
 77%|███████▋  | 21684/28080 [42:50:55<12:35:25,  7.09s/it]
                                                           
{'loss': 0.6028, 'learning_rate': 6.500113848464454e-05, 'epoch': 9.26}

 77%|███████▋  | 21684/28080 [42:50:55<12:35:25,  7.09s/it]
 77%|███████▋  | 21685/28080 [42:51:02<12:34:07,  7.08s/it]
                                                           
{'loss': 0.5886, 'learning_rate': 6.498174447593635e-05, 'epoch': 9.26}

 77%|███████▋  | 21685/28080 [42:51:02<12:34:07,  7.08s/it]
 77%|███████▋  | 21686/28080 [42:51:09<12:33:04,  7.07s/it]
                                                           
{'loss': 0.605, 'learning_rate': 6.49623529287052e-05, 'epoch': 9.26}

 77%|███████▋  | 21686/28080 [42:51:09<12:33:04,  7.07s/it]
 77%|███████▋  | 21687/28080 [42:51:16<12:31:36,  7.05s/it]
                                                           
{'loss': 0.6106, 'learning_rate': 6.4942963843209e-05, 'epoch': 9.26}

 77%|███████▋  | 21687/28080 [42:51:16<12:31:36,  7.05s/it]
 77%|███████▋  | 21688/28080 [42:51:23<12:31:56,  7.06s/it]
                                                           
{'loss': 0.6056, 'learning_rate': 6.492357721970579e-05, 'epoch': 9.26}

 77%|███████▋  | 21688/28080 [42:51:23<12:31:56,  7.06s/it]
 77%|███████▋  | 21689/28080 [42:51:30<12:33:15,  7.07s/it]
                                                           
{'loss': 0.6135, 'learning_rate': 6.490419305845346e-05, 'epoch': 9.27}

 77%|███████▋  | 21689/28080 [42:51:30<12:33:15,  7.07s/it]
 77%|███████▋  | 21690/28080 [42:51:37<12:30:52,  7.05s/it]
                                                           
{'loss': 0.6252, 'learning_rate': 6.488481135970988e-05, 'epoch': 9.27}

 77%|███████▋  | 21690/28080 [42:51:37<12:30:52,  7.05s/it]
 77%|███████▋  | 21691/28080 [42:51:44<12:31:46,  7.06s/it]
                                                           
{'loss': 0.5964, 'learning_rate': 6.486543212373294e-05, 'epoch': 9.27}

 77%|███████▋  | 21691/28080 [42:51:44<12:31:46,  7.06s/it]
 77%|███████▋  | 21692/28080 [42:51:51<12:34:11,  7.08s/it]
                                                           
{'loss': 0.602, 'learning_rate': 6.484605535078036e-05, 'epoch': 9.27}

 77%|███████▋  | 21692/28080 [42:51:51<12:34:11,  7.08s/it]
 77%|███████▋  | 21693/28080 [42:51:58<12:32:00,  7.06s/it]
                                                           
{'loss': 0.6114, 'learning_rate': 6.482668104111005e-05, 'epoch': 9.27}

 77%|███████▋  | 21693/28080 [42:51:58<12:32:00,  7.06s/it]
 77%|███████▋  | 21694/28080 [42:52:05<12:33:52,  7.08s/it]
                                                           
{'loss': 0.597, 'learning_rate': 6.480730919497966e-05, 'epoch': 9.27}

 77%|███████▋  | 21694/28080 [42:52:05<12:33:52,  7.08s/it]
 77%|███████▋  | 21695/28080 [42:52:12<12:32:16,  7.07s/it]
                                                           
{'loss': 0.6224, 'learning_rate': 6.478793981264711e-05, 'epoch': 9.27}

 77%|███████▋  | 21695/28080 [42:52:12<12:32:16,  7.07s/it]
 77%|███████▋  | 21696/28080 [42:52:19<12:34:29,  7.09s/it]
                                                           
{'loss': 0.6018, 'learning_rate': 6.47685728943698e-05, 'epoch': 9.27}

 77%|███████▋  | 21696/28080 [42:52:19<12:34:29,  7.09s/it]
 77%|███████▋  | 21697/28080 [42:52:26<12:32:49,  7.08s/it]
                                                           
{'loss': 0.6087, 'learning_rate': 6.47492084404056e-05, 'epoch': 9.27}

 77%|███████▋  | 21697/28080 [42:52:26<12:32:49,  7.08s/it]
 77%|███████▋  | 21698/28080 [42:52:33<12:29:36,  7.05s/it]
                                                           
{'loss': 0.6164, 'learning_rate': 6.472984645101202e-05, 'epoch': 9.27}

 77%|███████▋  | 21698/28080 [42:52:33<12:29:36,  7.05s/it]
 77%|███████▋  | 21699/28080 [42:52:40<12:28:55,  7.04s/it]
                                                           
{'loss': 0.5999, 'learning_rate': 6.471048692644676e-05, 'epoch': 9.27}

 77%|███████▋  | 21699/28080 [42:52:40<12:28:55,  7.04s/it]
 77%|███████▋  | 21700/28080 [42:52:48<12:31:05,  7.06s/it]
                                                           
{'loss': 0.5842, 'learning_rate': 6.469112986696731e-05, 'epoch': 9.27}

 77%|███████▋  | 21700/28080 [42:52:48<12:31:05,  7.06s/it]
 77%|███████▋  | 21701/28080 [42:52:55<12:28:36,  7.04s/it]
                                                           
{'loss': 0.6001, 'learning_rate': 6.467177527283122e-05, 'epoch': 9.27}

 77%|███████▋  | 21701/28080 [42:52:55<12:28:36,  7.04s/it]
 77%|███████▋  | 21702/28080 [42:53:02<12:34:22,  7.10s/it]
                                                           
{'loss': 0.6209, 'learning_rate': 6.465242314429586e-05, 'epoch': 9.27}

 77%|███████▋  | 21702/28080 [42:53:02<12:34:22,  7.10s/it]
 77%|███████▋  | 21703/28080 [42:53:09<12:30:47,  7.06s/it]
                                                           
{'loss': 0.5969, 'learning_rate': 6.463307348161893e-05, 'epoch': 9.27}

 77%|███████▋  | 21703/28080 [42:53:09<12:30:47,  7.06s/it]
 77%|███████▋  | 21704/28080 [42:53:16<12:33:56,  7.09s/it]
                                                           
{'loss': 0.6117, 'learning_rate': 6.461372628505769e-05, 'epoch': 9.27}

 77%|███████▋  | 21704/28080 [42:53:16<12:33:56,  7.09s/it]
 77%|███████▋  | 21705/28080 [42:53:23<12:35:09,  7.11s/it]
                                                           
{'loss': 0.588, 'learning_rate': 6.459438155486958e-05, 'epoch': 9.27}

 77%|███████▋  | 21705/28080 [42:53:23<12:35:09,  7.11s/it]
 77%|███████▋  | 21706/28080 [42:53:30<12:35:10,  7.11s/it]
                                                           
{'loss': 0.6147, 'learning_rate': 6.457503929131183e-05, 'epoch': 9.27}

 77%|███████▋  | 21706/28080 [42:53:30<12:35:10,  7.11s/it]
 77%|███████▋  | 21707/28080 [42:53:37<12:35:17,  7.11s/it]
                                                           
{'loss': 0.6053, 'learning_rate': 6.455569949464201e-05, 'epoch': 9.27}

 77%|███████▋  | 21707/28080 [42:53:37<12:35:17,  7.11s/it]
 77%|███████▋  | 21708/28080 [42:53:44<12:34:32,  7.10s/it]
                                                           
{'loss': 0.6186, 'learning_rate': 6.453636216511724e-05, 'epoch': 9.27}

 77%|███████▋  | 21708/28080 [42:53:44<12:34:32,  7.10s/it]
 77%|███████▋  | 21709/28080 [42:53:51<12:34:33,  7.11s/it]
                                                           
{'loss': 0.6049, 'learning_rate': 6.451702730299494e-05, 'epoch': 9.27}

 77%|███████▋  | 21709/28080 [42:53:51<12:34:33,  7.11s/it]
 77%|███████▋  | 21710/28080 [42:53:59<12:34:38,  7.11s/it]
                                                           
{'loss': 0.6117, 'learning_rate': 6.449769490853213e-05, 'epoch': 9.27}

 77%|███████▋  | 21710/28080 [42:53:59<12:34:38,  7.11s/it]
 77%|███████▋  | 21711/28080 [42:54:06<12:35:33,  7.12s/it]
                                                           
{'loss': 0.6215, 'learning_rate': 6.447836498198616e-05, 'epoch': 9.27}

 77%|███████▋  | 21711/28080 [42:54:06<12:35:33,  7.12s/it]
 77%|███████▋  | 21712/28080 [42:54:13<12:33:43,  7.10s/it]
                                                           
{'loss': 0.6034, 'learning_rate': 6.44590375236141e-05, 'epoch': 9.28}

 77%|███████▋  | 21712/28080 [42:54:13<12:33:43,  7.10s/it]
 77%|███████▋  | 21713/28080 [42:54:20<12:30:14,  7.07s/it]
                                                           
{'loss': 0.5878, 'learning_rate': 6.44397125336732e-05, 'epoch': 9.28}

 77%|███████▋  | 21713/28080 [42:54:20<12:30:14,  7.07s/it]
 77%|███████▋  | 21714/28080 [42:54:27<12:28:19,  7.05s/it]
                                                           
{'loss': 0.6017, 'learning_rate': 6.442039001242051e-05, 'epoch': 9.28}

 77%|███████▋  | 21714/28080 [42:54:27<12:28:19,  7.05s/it]
 77%|███████▋  | 21715/28080 [42:54:34<12:31:14,  7.08s/it]
                                                           
{'loss': 0.6144, 'learning_rate': 6.440106996011306e-05, 'epoch': 9.28}

 77%|███████▋  | 21715/28080 [42:54:34<12:31:14,  7.08s/it]
 77%|███████▋  | 21716/28080 [42:54:41<12:33:51,  7.11s/it]
                                                           
{'loss': 0.6056, 'learning_rate': 6.438175237700788e-05, 'epoch': 9.28}

 77%|███████▋  | 21716/28080 [42:54:41<12:33:51,  7.11s/it]
 77%|███████▋  | 21717/28080 [42:54:48<12:33:23,  7.10s/it]
                                                           
{'loss': 0.5917, 'learning_rate': 6.436243726336197e-05, 'epoch': 9.28}

 77%|███████▋  | 21717/28080 [42:54:48<12:33:23,  7.10s/it]
 77%|███████▋  | 21718/28080 [42:54:55<12:30:33,  7.08s/it]
                                                           
{'loss': 0.6069, 'learning_rate': 6.434312461943234e-05, 'epoch': 9.28}

 77%|███████▋  | 21718/28080 [42:54:55<12:30:33,  7.08s/it]
 77%|███████▋  | 21719/28080 [42:55:02<12:33:09,  7.10s/it]
                                                           
{'loss': 0.595, 'learning_rate': 6.432381444547595e-05, 'epoch': 9.28}

 77%|███████▋  | 21719/28080 [42:55:02<12:33:09,  7.10s/it]
 77%|███████▋  | 21720/28080 [42:55:09<12:32:32,  7.10s/it]
                                                           
{'loss': 0.5751, 'learning_rate': 6.430450674174965e-05, 'epoch': 9.28}

 77%|███████▋  | 21720/28080 [42:55:09<12:32:32,  7.10s/it]
 77%|███████▋  | 21721/28080 [42:55:17<12:33:18,  7.11s/it]
                                                           
{'loss': 0.606, 'learning_rate': 6.428520150851022e-05, 'epoch': 9.28}

 77%|███████▋  | 21721/28080 [42:55:17<12:33:18,  7.11s/it]
 77%|███████▋  | 21722/28080 [42:55:24<12:34:16,  7.12s/it]
                                                           
{'loss': 0.5793, 'learning_rate': 6.426589874601469e-05, 'epoch': 9.28}

 77%|███████▋  | 21722/28080 [42:55:24<12:34:16,  7.12s/it]
 77%|███████▋  | 21723/28080 [42:55:31<12:32:48,  7.11s/it]
                                                           
{'loss': 0.5939, 'learning_rate': 6.424659845451966e-05, 'epoch': 9.28}

 77%|███████▋  | 21723/28080 [42:55:31<12:32:48,  7.11s/it]
 77%|███████▋  | 21724/28080 [42:55:38<12:32:56,  7.11s/it]
                                                           
{'loss': 0.5965, 'learning_rate': 6.422730063428219e-05, 'epoch': 9.28}

 77%|███████▋  | 21724/28080 [42:55:38<12:32:56,  7.11s/it]
 77%|███████▋  | 21725/28080 [42:55:45<12:29:38,  7.08s/it]
                                                           
{'loss': 0.6259, 'learning_rate': 6.420800528555867e-05, 'epoch': 9.28}

 77%|███████▋  | 21725/28080 [42:55:45<12:29:38,  7.08s/it]
 77%|███████▋  | 21726/28080 [42:55:52<12:29:36,  7.08s/it]
                                                           
{'loss': 0.5987, 'learning_rate': 6.418871240860605e-05, 'epoch': 9.28}

 77%|███████▋  | 21726/28080 [42:55:52<12:29:36,  7.08s/it]
 77%|███████▋  | 21727/28080 [42:55:59<12:30:12,  7.09s/it]
                                                           
{'loss': 0.6151, 'learning_rate': 6.416942200368084e-05, 'epoch': 9.28}

 77%|███████▋  | 21727/28080 [42:55:59<12:30:12,  7.09s/it]
 77%|███████▋  | 21728/28080 [42:56:06<12:31:37,  7.10s/it]
                                                           
{'loss': 0.5835, 'learning_rate': 6.415013407103983e-05, 'epoch': 9.28}

 77%|███████▋  | 21728/28080 [42:56:06<12:31:37,  7.10s/it]
 77%|███████▋  | 21729/28080 [42:56:13<12:33:55,  7.12s/it]
                                                           
{'loss': 0.6147, 'learning_rate': 6.413084861093957e-05, 'epoch': 9.28}

 77%|███████▋  | 21729/28080 [42:56:13<12:33:55,  7.12s/it]
 77%|███████▋  | 21730/28080 [42:56:21<12:32:37,  7.11s/it]
                                                           
{'loss': 0.6229, 'learning_rate': 6.41115656236366e-05, 'epoch': 9.28}

 77%|███████▋  | 21730/28080 [42:56:21<12:32:37,  7.11s/it]
 77%|███████▋  | 21731/28080 [42:56:28<12:31:45,  7.10s/it]
                                                           
{'loss': 0.6038, 'learning_rate': 6.409228510938742e-05, 'epoch': 9.28}

 77%|███████▋  | 21731/28080 [42:56:28<12:31:45,  7.10s/it]
 77%|███████▋  | 21732/28080 [42:56:35<12:29:29,  7.08s/it]
                                                           
{'loss': 0.6013, 'learning_rate': 6.407300706844866e-05, 'epoch': 9.28}

 77%|███████▋  | 21732/28080 [42:56:35<12:29:29,  7.08s/it]
 77%|███████▋  | 21733/28080 [42:56:42<12:26:38,  7.06s/it]
                                                           
{'loss': 0.6011, 'learning_rate': 6.405373150107674e-05, 'epoch': 9.28}

 77%|███████▋  | 21733/28080 [42:56:42<12:26:38,  7.06s/it]
 77%|███████▋  | 21734/28080 [42:56:49<12:25:52,  7.05s/it]
                                                           
{'loss': 0.5966, 'learning_rate': 6.403445840752809e-05, 'epoch': 9.28}

 77%|███████▋  | 21734/28080 [42:56:49<12:25:52,  7.05s/it]
 77%|███████▋  | 21735/28080 [42:56:56<12:26:26,  7.06s/it]
                                                           
{'loss': 0.5967, 'learning_rate': 6.401518778805903e-05, 'epoch': 9.28}

 77%|███████▋  | 21735/28080 [42:56:56<12:26:26,  7.06s/it]
 77%|███████▋  | 21736/28080 [42:57:03<12:24:06,  7.04s/it]
                                                           
{'loss': 0.6135, 'learning_rate': 6.399591964292612e-05, 'epoch': 9.29}

 77%|███████▋  | 21736/28080 [42:57:03<12:24:06,  7.04s/it]
 77%|███████▋  | 21737/28080 [42:57:10<12:26:15,  7.06s/it]
                                                           
{'loss': 0.6122, 'learning_rate': 6.397665397238553e-05, 'epoch': 9.29}

 77%|███████▋  | 21737/28080 [42:57:10<12:26:15,  7.06s/it]
 77%|███████▋  | 21738/28080 [42:57:17<12:26:11,  7.06s/it]
                                                           
{'loss': 0.5946, 'learning_rate': 6.39573907766938e-05, 'epoch': 9.29}

 77%|███████▋  | 21738/28080 [42:57:17<12:26:11,  7.06s/it]
 77%|███████▋  | 21739/28080 [42:57:24<12:25:42,  7.06s/it]
                                                           
{'loss': 0.6115, 'learning_rate': 6.3938130056107e-05, 'epoch': 9.29}

 77%|███████▋  | 21739/28080 [42:57:24<12:25:42,  7.06s/it]
 77%|███████▋  | 21740/28080 [42:57:31<12:24:41,  7.05s/it]
                                                           
{'loss': 0.605, 'learning_rate': 6.391887181088132e-05, 'epoch': 9.29}

 77%|███████▋  | 21740/28080 [42:57:31<12:24:41,  7.05s/it]
 77%|███████▋  | 21741/28080 [42:57:38<12:26:46,  7.07s/it]
                                                           
{'loss': 0.5763, 'learning_rate': 6.389961604127318e-05, 'epoch': 9.29}

 77%|███████▋  | 21741/28080 [42:57:38<12:26:46,  7.07s/it]
 77%|███████▋  | 21742/28080 [42:57:45<12:25:30,  7.06s/it]
                                                           
{'loss': 0.6006, 'learning_rate': 6.388036274753856e-05, 'epoch': 9.29}

 77%|███████▋  | 21742/28080 [42:57:45<12:25:30,  7.06s/it]
 77%|███████▋  | 21743/28080 [42:57:52<12:27:48,  7.08s/it]
                                                           
{'loss': 0.6177, 'learning_rate': 6.386111192993389e-05, 'epoch': 9.29}

 77%|███████▋  | 21743/28080 [42:57:52<12:27:48,  7.08s/it]
 77%|███████▋  | 21744/28080 [42:57:59<12:28:02,  7.08s/it]
                                                           
{'loss': 0.6155, 'learning_rate': 6.384186358871492e-05, 'epoch': 9.29}

 77%|███████▋  | 21744/28080 [42:57:59<12:28:02,  7.08s/it]
 77%|███████▋  | 21745/28080 [42:58:06<12:27:25,  7.08s/it]
                                                           
{'loss': 0.5971, 'learning_rate': 6.382261772413797e-05, 'epoch': 9.29}

 77%|███████▋  | 21745/28080 [42:58:06<12:27:25,  7.08s/it]
 77%|███████▋  | 21746/28080 [42:58:14<12:28:51,  7.09s/it]
                                                           
{'loss': 0.5997, 'learning_rate': 6.380337433645896e-05, 'epoch': 9.29}

 77%|███████▋  | 21746/28080 [42:58:14<12:28:51,  7.09s/it]
 77%|███████▋  | 21747/28080 [42:58:21<12:28:50,  7.09s/it]
                                                           
{'loss': 0.6159, 'learning_rate': 6.378413342593406e-05, 'epoch': 9.29}

 77%|███████▋  | 21747/28080 [42:58:21<12:28:50,  7.09s/it]
 77%|███████▋  | 21748/28080 [42:58:28<12:25:47,  7.07s/it]
                                                           
{'loss': 0.5993, 'learning_rate': 6.376489499281915e-05, 'epoch': 9.29}

 77%|███████▋  | 21748/28080 [42:58:28<12:25:47,  7.07s/it]
 77%|███████▋  | 21749/28080 [42:58:35<12:27:15,  7.08s/it]
                                                           
{'loss': 0.6004, 'learning_rate': 6.374565903737018e-05, 'epoch': 9.29}

 77%|███████▋  | 21749/28080 [42:58:35<12:27:15,  7.08s/it]
 77%|███████▋  | 21750/28080 [42:58:42<12:25:28,  7.07s/it]
                                                           
{'loss': 0.6165, 'learning_rate': 6.372642555984299e-05, 'epoch': 9.29}

 77%|███████▋  | 21750/28080 [42:58:42<12:25:28,  7.07s/it]
 77%|███████▋  | 21751/28080 [42:58:49<12:25:47,  7.07s/it]
                                                           
{'loss': 0.6006, 'learning_rate': 6.370719456049362e-05, 'epoch': 9.29}

 77%|███████▋  | 21751/28080 [42:58:49<12:25:47,  7.07s/it]
 77%|███████▋  | 21752/28080 [42:58:56<12:25:10,  7.07s/it]
                                                           
{'loss': 0.5986, 'learning_rate': 6.368796603957783e-05, 'epoch': 9.29}

 77%|███████▋  | 21752/28080 [42:58:56<12:25:10,  7.07s/it]
 77%|███████▋  | 21753/28080 [42:59:03<12:24:36,  7.06s/it]
                                                           
{'loss': 0.6173, 'learning_rate': 6.366873999735146e-05, 'epoch': 9.29}

 77%|███████▋  | 21753/28080 [42:59:03<12:24:36,  7.06s/it]
 77%|███████▋  | 21754/28080 [42:59:10<12:23:45,  7.05s/it]
                                                           
{'loss': 0.6077, 'learning_rate': 6.364951643407019e-05, 'epoch': 9.29}

 77%|███████▋  | 21754/28080 [42:59:10<12:23:45,  7.05s/it]
 77%|███████▋  | 21755/28080 [42:59:17<12:21:50,  7.04s/it]
                                                           
{'loss': 0.605, 'learning_rate': 6.363029534998993e-05, 'epoch': 9.29}

 77%|███████▋  | 21755/28080 [42:59:17<12:21:50,  7.04s/it]
 77%|███████▋  | 21756/28080 [42:59:24<12:23:41,  7.06s/it]
                                                           
{'loss': 0.5842, 'learning_rate': 6.361107674536626e-05, 'epoch': 9.29}

 77%|███████▋  | 21756/28080 [42:59:24<12:23:41,  7.06s/it]
 77%|███████▋  | 21757/28080 [42:59:31<12:26:08,  7.08s/it]
                                                           
{'loss': 0.6076, 'learning_rate': 6.359186062045505e-05, 'epoch': 9.29}

 77%|███████▋  | 21757/28080 [42:59:31<12:26:08,  7.08s/it]
 77%|███████▋  | 21758/28080 [42:59:38<12:24:37,  7.07s/it]
                                                           
{'loss': 0.5975, 'learning_rate': 6.35726469755117e-05, 'epoch': 9.29}

 77%|███████▋  | 21758/28080 [42:59:38<12:24:37,  7.07s/it]
 77%|███████▋  | 21759/28080 [42:59:45<12:25:05,  7.07s/it]
                                                           
{'loss': 0.6059, 'learning_rate': 6.355343581079204e-05, 'epoch': 9.3}

 77%|███████▋  | 21759/28080 [42:59:45<12:25:05,  7.07s/it]
 77%|███████▋  | 21760/28080 [42:59:52<12:26:21,  7.09s/it]
                                                           
{'loss': 0.615, 'learning_rate': 6.353422712655149e-05, 'epoch': 9.3}

 77%|███████▋  | 21760/28080 [42:59:52<12:26:21,  7.09s/it]
 77%|███████▋  | 21761/28080 [43:00:00<12:28:03,  7.10s/it]
                                                           
{'loss': 0.6039, 'learning_rate': 6.351502092304573e-05, 'epoch': 9.3}

 77%|███████▋  | 21761/28080 [43:00:00<12:28:03,  7.10s/it]
 78%|███████▊  | 21762/28080 [43:00:07<12:27:31,  7.10s/it]
                                                           
{'loss': 0.6073, 'learning_rate': 6.349581720053027e-05, 'epoch': 9.3}

 78%|███████▊  | 21762/28080 [43:00:07<12:27:31,  7.10s/it]
 78%|███████▊  | 21763/28080 [43:00:14<12:24:05,  7.07s/it]
                                                           
{'loss': 0.6069, 'learning_rate': 6.347661595926053e-05, 'epoch': 9.3}

 78%|███████▊  | 21763/28080 [43:00:14<12:24:05,  7.07s/it]
 78%|███████▊  | 21764/28080 [43:00:21<12:23:34,  7.06s/it]
                                                           
{'loss': 0.6163, 'learning_rate': 6.3457417199492e-05, 'epoch': 9.3}

 78%|███████▊  | 21764/28080 [43:00:21<12:23:34,  7.06s/it]
 78%|███████▊  | 21765/28080 [43:00:28<12:21:54,  7.05s/it]
                                                           
{'loss': 0.6036, 'learning_rate': 6.343822092148003e-05, 'epoch': 9.3}

 78%|███████▊  | 21765/28080 [43:00:28<12:21:54,  7.05s/it]
 78%|███████▊  | 21766/28080 [43:00:35<12:21:59,  7.05s/it]
                                                           
{'loss': 0.5903, 'learning_rate': 6.34190271254801e-05, 'epoch': 9.3}

 78%|███████▊  | 21766/28080 [43:00:35<12:21:59,  7.05s/it]
 78%|███████▊  | 21767/28080 [43:00:42<12:22:59,  7.06s/it]
                                                           
{'loss': 0.5807, 'learning_rate': 6.339983581174755e-05, 'epoch': 9.3}

 78%|███████▊  | 21767/28080 [43:00:42<12:22:59,  7.06s/it]
 78%|███████▊  | 21768/28080 [43:00:49<12:21:07,  7.04s/it]
                                                           
{'loss': 0.6085, 'learning_rate': 6.338064698053769e-05, 'epoch': 9.3}

 78%|███████▊  | 21768/28080 [43:00:49<12:21:07,  7.04s/it]
 78%|███████▊  | 21769/28080 [43:00:56<12:23:21,  7.07s/it]
                                                           
{'loss': 0.593, 'learning_rate': 6.33614606321057e-05, 'epoch': 9.3}

 78%|███████▊  | 21769/28080 [43:00:56<12:23:21,  7.07s/it]
 78%|███████▊  | 21770/28080 [43:01:03<12:25:56,  7.09s/it]
                                                           
{'loss': 0.6167, 'learning_rate': 6.334227676670704e-05, 'epoch': 9.3}

 78%|███████▊  | 21770/28080 [43:01:03<12:25:56,  7.09s/it]
 78%|███████▊  | 21771/28080 [43:01:10<12:28:52,  7.12s/it]
                                                           
{'loss': 0.5957, 'learning_rate': 6.332309538459671e-05, 'epoch': 9.3}

 78%|███████▊  | 21771/28080 [43:01:10<12:28:52,  7.12s/it]
 78%|███████▊  | 21772/28080 [43:01:18<12:28:52,  7.12s/it]
                                                           
{'loss': 0.6135, 'learning_rate': 6.330391648603017e-05, 'epoch': 9.3}

 78%|███████▊  | 21772/28080 [43:01:18<12:28:52,  7.12s/it]
 78%|███████▊  | 21773/28080 [43:01:25<12:30:24,  7.14s/it]
                                                           
{'loss': 0.5992, 'learning_rate': 6.328474007126227e-05, 'epoch': 9.3}

 78%|███████▊  | 21773/28080 [43:01:25<12:30:24,  7.14s/it]
 78%|███████▊  | 21774/28080 [43:01:32<12:28:17,  7.12s/it]
                                                           
{'loss': 0.6018, 'learning_rate': 6.326556614054838e-05, 'epoch': 9.3}

 78%|███████▊  | 21774/28080 [43:01:32<12:28:17,  7.12s/it]
 78%|███████▊  | 21775/28080 [43:01:39<12:27:01,  7.11s/it]
                                                           
{'loss': 0.5817, 'learning_rate': 6.32463946941434e-05, 'epoch': 9.3}

 78%|███████▊  | 21775/28080 [43:01:39<12:27:01,  7.11s/it]
 78%|███████▊  | 21776/28080 [43:01:46<12:23:37,  7.08s/it]
                                                           
{'loss': 0.6172, 'learning_rate': 6.322722573230256e-05, 'epoch': 9.3}

 78%|███████▊  | 21776/28080 [43:01:46<12:23:37,  7.08s/it]
 78%|███████▊  | 21777/28080 [43:01:53<12:24:12,  7.08s/it]
                                                           
{'loss': 0.5899, 'learning_rate': 6.320805925528079e-05, 'epoch': 9.3}

 78%|███████▊  | 21777/28080 [43:01:53<12:24:12,  7.08s/it]
 78%|███████▊  | 21778/28080 [43:02:00<12:25:45,  7.10s/it]
                                                           
{'loss': 0.6047, 'learning_rate': 6.318889526333308e-05, 'epoch': 9.3}

 78%|███████▊  | 21778/28080 [43:02:00<12:25:45,  7.10s/it]
 78%|███████▊  | 21779/28080 [43:02:07<12:27:11,  7.11s/it]
                                                           
{'loss': 0.6004, 'learning_rate': 6.316973375671431e-05, 'epoch': 9.3}

 78%|███████▊  | 21779/28080 [43:02:07<12:27:11,  7.11s/it]
 78%|███████▊  | 21780/28080 [43:02:14<12:23:19,  7.08s/it]
                                                           
{'loss': 0.6122, 'learning_rate': 6.315057473567958e-05, 'epoch': 9.3}

 78%|███████▊  | 21780/28080 [43:02:14<12:23:19,  7.08s/it]
 78%|███████▊  | 21781/28080 [43:02:21<12:22:21,  7.07s/it]
                                                           
{'loss': 0.5942, 'learning_rate': 6.313141820048371e-05, 'epoch': 9.3}

 78%|███████▊  | 21781/28080 [43:02:21<12:22:21,  7.07s/it]
 78%|███████▊  | 21782/28080 [43:02:28<12:23:52,  7.09s/it]
                                                           
{'loss': 0.5971, 'learning_rate': 6.311226415138152e-05, 'epoch': 9.31}

 78%|███████▊  | 21782/28080 [43:02:28<12:23:52,  7.09s/it]
 78%|███████▊  | 21783/28080 [43:02:35<12:22:07,  7.07s/it]
                                                           
{'loss': 0.6118, 'learning_rate': 6.309311258862779e-05, 'epoch': 9.31}

 78%|███████▊  | 21783/28080 [43:02:35<12:22:07,  7.07s/it]
 78%|███████▊  | 21784/28080 [43:02:43<12:21:16,  7.06s/it]
                                                           
{'loss': 0.5953, 'learning_rate': 6.307396351247743e-05, 'epoch': 9.31}

 78%|███████▊  | 21784/28080 [43:02:43<12:21:16,  7.06s/it]
 78%|███████▊  | 21785/28080 [43:02:50<12:24:13,  7.09s/it]
                                                           
{'loss': 0.6077, 'learning_rate': 6.30548169231851e-05, 'epoch': 9.31}

 78%|███████▊  | 21785/28080 [43:02:50<12:24:13,  7.09s/it]
 78%|███████▊  | 21786/28080 [43:02:57<12:21:20,  7.07s/it]
                                                           
{'loss': 0.5987, 'learning_rate': 6.303567282100569e-05, 'epoch': 9.31}

 78%|███████▊  | 21786/28080 [43:02:57<12:21:20,  7.07s/it]
 78%|███████▊  | 21787/28080 [43:03:04<12:26:25,  7.12s/it]
                                                           
{'loss': 0.5941, 'learning_rate': 6.301653120619364e-05, 'epoch': 9.31}

 78%|███████▊  | 21787/28080 [43:03:04<12:26:25,  7.12s/it]
 78%|███████▊  | 21788/28080 [43:03:11<12:24:14,  7.10s/it]
                                                           
{'loss': 0.6165, 'learning_rate': 6.299739207900382e-05, 'epoch': 9.31}

 78%|███████▊  | 21788/28080 [43:03:11<12:24:14,  7.10s/it]
 78%|███████▊  | 21789/28080 [43:03:18<12:22:31,  7.08s/it]
                                                           
{'loss': 0.6007, 'learning_rate': 6.297825543969077e-05, 'epoch': 9.31}

 78%|███████▊  | 21789/28080 [43:03:18<12:22:31,  7.08s/it]
 78%|███████▊  | 21790/28080 [43:03:25<12:25:30,  7.11s/it]
                                                           
{'loss': 0.6023, 'learning_rate': 6.2959121288509e-05, 'epoch': 9.31}

 78%|███████▊  | 21790/28080 [43:03:25<12:25:30,  7.11s/it]
 78%|███████▊  | 21791/28080 [43:03:32<12:26:52,  7.13s/it]
                                                           
{'loss': 0.5849, 'learning_rate': 6.293998962571334e-05, 'epoch': 9.31}

 78%|███████▊  | 21791/28080 [43:03:32<12:26:52,  7.13s/it]
 78%|███████▊  | 21792/28080 [43:03:39<12:25:07,  7.11s/it]
                                                           
{'loss': 0.6077, 'learning_rate': 6.292086045155799e-05, 'epoch': 9.31}

 78%|███████▊  | 21792/28080 [43:03:39<12:25:07,  7.11s/it]
 78%|███████▊  | 21793/28080 [43:03:47<12:27:14,  7.13s/it]
                                                           
{'loss': 0.5895, 'learning_rate': 6.290173376629765e-05, 'epoch': 9.31}

 78%|███████▊  | 21793/28080 [43:03:47<12:27:14,  7.13s/it]
 78%|███████▊  | 21794/28080 [43:03:54<12:26:14,  7.12s/it]
                                                           
{'loss': 0.6019, 'learning_rate': 6.288260957018666e-05, 'epoch': 9.31}

 78%|███████▊  | 21794/28080 [43:03:54<12:26:14,  7.12s/it]
 78%|███████▊  | 21795/28080 [43:04:01<12:24:38,  7.11s/it]
                                                           
{'loss': 0.5974, 'learning_rate': 6.286348786347957e-05, 'epoch': 9.31}

 78%|███████▊  | 21795/28080 [43:04:01<12:24:38,  7.11s/it]
 78%|███████▊  | 21796/28080 [43:04:08<12:26:46,  7.13s/it]
                                                           
{'loss': 0.6174, 'learning_rate': 6.284436864643073e-05, 'epoch': 9.31}

 78%|███████▊  | 21796/28080 [43:04:08<12:26:46,  7.13s/it]
 78%|███████▊  | 21797/28080 [43:04:15<12:25:36,  7.12s/it]
                                                           
{'loss': 0.6278, 'learning_rate': 6.282525191929448e-05, 'epoch': 9.31}

 78%|███████▊  | 21797/28080 [43:04:15<12:25:36,  7.12s/it]
 78%|███████▊  | 21798/28080 [43:04:22<12:27:58,  7.14s/it]
                                                           
{'loss': 0.5975, 'learning_rate': 6.28061376823251e-05, 'epoch': 9.31}

 78%|███████▊  | 21798/28080 [43:04:22<12:27:58,  7.14s/it]
 78%|███████▊  | 21799/28080 [43:04:29<12:25:31,  7.12s/it]
                                                           
{'loss': 0.5962, 'learning_rate': 6.278702593577698e-05, 'epoch': 9.31}

 78%|███████▊  | 21799/28080 [43:04:29<12:25:31,  7.12s/it]
 78%|███████▊  | 21800/28080 [43:04:37<12:27:58,  7.15s/it]
                                                           
{'loss': 0.5804, 'learning_rate': 6.276791667990436e-05, 'epoch': 9.31}

 78%|███████▊  | 21800/28080 [43:04:37<12:27:58,  7.15s/it]
 78%|███████▊  | 21801/28080 [43:04:44<12:28:29,  7.15s/it]
                                                           
{'loss': 0.6087, 'learning_rate': 6.274880991496146e-05, 'epoch': 9.31}

 78%|███████▊  | 21801/28080 [43:04:44<12:28:29,  7.15s/it]
 78%|███████▊  | 21802/28080 [43:04:51<12:27:26,  7.14s/it]
                                                           
{'loss': 0.5927, 'learning_rate': 6.27297056412024e-05, 'epoch': 9.31}

 78%|███████▊  | 21802/28080 [43:04:51<12:27:26,  7.14s/it]
 78%|███████▊  | 21803/28080 [43:04:58<12:27:06,  7.14s/it]
                                                           
{'loss': 0.5948, 'learning_rate': 6.271060385888146e-05, 'epoch': 9.31}

 78%|███████▊  | 21803/28080 [43:04:58<12:27:06,  7.14s/it]
 78%|███████▊  | 21804/28080 [43:05:05<12:31:06,  7.18s/it]
                                                           
{'loss': 0.6072, 'learning_rate': 6.269150456825267e-05, 'epoch': 9.31}

 78%|███████▊  | 21804/28080 [43:05:05<12:31:06,  7.18s/it]
 78%|███████▊  | 21805/28080 [43:05:12<12:26:02,  7.13s/it]
                                                           
{'loss': 0.5825, 'learning_rate': 6.26724077695703e-05, 'epoch': 9.31}

 78%|███████▊  | 21805/28080 [43:05:12<12:26:02,  7.13s/it]
 78%|███████▊  | 21806/28080 [43:05:19<12:25:09,  7.13s/it]
                                                           
{'loss': 0.5911, 'learning_rate': 6.265331346308817e-05, 'epoch': 9.32}

 78%|███████▊  | 21806/28080 [43:05:19<12:25:09,  7.13s/it]
 78%|███████▊  | 21807/28080 [43:05:26<12:22:23,  7.10s/it]
                                                           
{'loss': 0.5988, 'learning_rate': 6.263422164906048e-05, 'epoch': 9.32}

 78%|███████▊  | 21807/28080 [43:05:26<12:22:23,  7.10s/it]
 78%|███████▊  | 21808/28080 [43:05:34<12:23:46,  7.12s/it]
                                                           
{'loss': 0.6221, 'learning_rate': 6.261513232774113e-05, 'epoch': 9.32}

 78%|███████▊  | 21808/28080 [43:05:34<12:23:46,  7.12s/it]
 78%|███████▊  | 21809/28080 [43:05:41<12:22:51,  7.11s/it]
                                                           
{'loss': 0.6149, 'learning_rate': 6.259604549938419e-05, 'epoch': 9.32}

 78%|███████▊  | 21809/28080 [43:05:41<12:22:51,  7.11s/it]
 78%|███████▊  | 21810/28080 [43:05:48<12:22:34,  7.11s/it]
                                                           
{'loss': 0.6176, 'learning_rate': 6.257696116424352e-05, 'epoch': 9.32}

 78%|███████▊  | 21810/28080 [43:05:48<12:22:34,  7.11s/it]
 78%|███████▊  | 21811/28080 [43:05:55<12:23:16,  7.11s/it]
                                                           
{'loss': 0.5827, 'learning_rate': 6.255787932257304e-05, 'epoch': 9.32}

 78%|███████▊  | 21811/28080 [43:05:55<12:23:16,  7.11s/it]
 78%|███████▊  | 21812/28080 [43:06:02<12:20:45,  7.09s/it]
                                                           
{'loss': 0.5973, 'learning_rate': 6.253879997462653e-05, 'epoch': 9.32}

 78%|███████▊  | 21812/28080 [43:06:02<12:20:45,  7.09s/it]
 78%|███████▊  | 21813/28080 [43:06:09<12:18:24,  7.07s/it]
                                                           
{'loss': 0.5756, 'learning_rate': 6.251972312065796e-05, 'epoch': 9.32}

 78%|███████▊  | 21813/28080 [43:06:09<12:18:24,  7.07s/it]
 78%|███████▊  | 21814/28080 [43:06:16<12:17:41,  7.06s/it]
                                                           
{'loss': 0.5983, 'learning_rate': 6.250064876092104e-05, 'epoch': 9.32}

 78%|███████▊  | 21814/28080 [43:06:16<12:17:41,  7.06s/it]
 78%|███████▊  | 21815/28080 [43:06:23<12:18:41,  7.07s/it]
                                                           
{'loss': 0.5945, 'learning_rate': 6.248157689566961e-05, 'epoch': 9.32}

 78%|███████▊  | 21815/28080 [43:06:23<12:18:41,  7.07s/it]
 78%|███████▊  | 21816/28080 [43:06:30<12:18:55,  7.08s/it]
                                                           
{'loss': 0.6076, 'learning_rate': 6.24625075251573e-05, 'epoch': 9.32}

 78%|███████▊  | 21816/28080 [43:06:30<12:18:55,  7.08s/it]
 78%|███████▊  | 21817/28080 [43:06:37<12:21:10,  7.10s/it]
                                                           
{'loss': 0.6045, 'learning_rate': 6.24434406496378e-05, 'epoch': 9.32}

 78%|███████▊  | 21817/28080 [43:06:37<12:21:10,  7.10s/it]
 78%|███████▊  | 21818/28080 [43:06:44<12:23:30,  7.12s/it]
                                                           
{'loss': 0.6083, 'learning_rate': 6.242437626936489e-05, 'epoch': 9.32}

 78%|███████▊  | 21818/28080 [43:06:44<12:23:30,  7.12s/it]
 78%|███████▊  | 21819/28080 [43:06:52<12:23:33,  7.13s/it]
                                                           
{'loss': 0.5908, 'learning_rate': 6.240531438459215e-05, 'epoch': 9.32}

 78%|███████▊  | 21819/28080 [43:06:52<12:23:33,  7.13s/it]
 78%|███████▊  | 21820/28080 [43:06:59<12:27:43,  7.17s/it]
                                                           
{'loss': 0.5939, 'learning_rate': 6.238625499557318e-05, 'epoch': 9.32}

 78%|███████▊  | 21820/28080 [43:06:59<12:27:43,  7.17s/it]
 78%|███████▊  | 21821/28080 [43:07:06<12:26:15,  7.15s/it]
                                                           
{'loss': 0.5968, 'learning_rate': 6.236719810256148e-05, 'epoch': 9.32}

 78%|███████▊  | 21821/28080 [43:07:06<12:26:15,  7.15s/it]
 78%|███████▊  | 21822/28080 [43:07:13<12:26:48,  7.16s/it]
                                                           
{'loss': 0.6082, 'learning_rate': 6.234814370581069e-05, 'epoch': 9.32}

 78%|███████▊  | 21822/28080 [43:07:13<12:26:48,  7.16s/it]
 78%|███████▊  | 21823/28080 [43:07:20<12:25:39,  7.15s/it]
                                                           
{'loss': 0.6157, 'learning_rate': 6.232909180557416e-05, 'epoch': 9.32}

 78%|███████▊  | 21823/28080 [43:07:20<12:25:39,  7.15s/it]
 78%|███████▊  | 21824/28080 [43:07:27<12:26:43,  7.16s/it]
                                                           
{'loss': 0.5982, 'learning_rate': 6.231004240210558e-05, 'epoch': 9.32}

 78%|███████▊  | 21824/28080 [43:07:28<12:26:43,  7.16s/it]
 78%|███████▊  | 21825/28080 [43:07:35<12:22:55,  7.13s/it]
                                                           
{'loss': 0.6073, 'learning_rate': 6.229099549565823e-05, 'epoch': 9.32}

 78%|███████▊  | 21825/28080 [43:07:35<12:22:55,  7.13s/it]
 78%|███████▊  | 21826/28080 [43:07:42<12:21:13,  7.11s/it]
                                                           
{'loss': 0.5816, 'learning_rate': 6.227195108648553e-05, 'epoch': 9.32}

 78%|███████▊  | 21826/28080 [43:07:42<12:21:13,  7.11s/it]
 78%|███████▊  | 21827/28080 [43:07:49<12:23:08,  7.13s/it]
                                                           
{'loss': 0.6149, 'learning_rate': 6.225290917484077e-05, 'epoch': 9.32}

 78%|███████▊  | 21827/28080 [43:07:49<12:23:08,  7.13s/it]
 78%|███████▊  | 21828/28080 [43:07:56<12:20:06,  7.10s/it]
                                                           
{'loss': 0.6054, 'learning_rate': 6.223386976097747e-05, 'epoch': 9.32}

 78%|███████▊  | 21828/28080 [43:07:56<12:20:06,  7.10s/it]
 78%|███████▊  | 21829/28080 [43:08:03<12:17:55,  7.08s/it]
                                                           
{'loss': 0.6237, 'learning_rate': 6.221483284514881e-05, 'epoch': 9.33}

 78%|███████▊  | 21829/28080 [43:08:03<12:17:55,  7.08s/it]
 78%|███████▊  | 21830/28080 [43:08:10<12:17:13,  7.08s/it]
                                                           
{'loss': 0.6053, 'learning_rate': 6.219579842760808e-05, 'epoch': 9.33}

 78%|███████▊  | 21830/28080 [43:08:10<12:17:13,  7.08s/it]
 78%|███████▊  | 21831/28080 [43:08:17<12:17:12,  7.08s/it]
                                                           
{'loss': 0.6103, 'learning_rate': 6.217676650860843e-05, 'epoch': 9.33}

 78%|███████▊  | 21831/28080 [43:08:17<12:17:12,  7.08s/it]
 78%|███████▊  | 21832/28080 [43:08:24<12:17:59,  7.09s/it]
                                                           
{'loss': 0.594, 'learning_rate': 6.215773708840319e-05, 'epoch': 9.33}

 78%|███████▊  | 21832/28080 [43:08:24<12:17:59,  7.09s/it]
 78%|███████▊  | 21833/28080 [43:08:31<12:16:43,  7.08s/it]
                                                           
{'loss': 0.6131, 'learning_rate': 6.213871016724542e-05, 'epoch': 9.33}

 78%|███████▊  | 21833/28080 [43:08:31<12:16:43,  7.08s/it]
 78%|███████▊  | 21834/28080 [43:08:38<12:18:57,  7.10s/it]
                                                           
{'loss': 0.6014, 'learning_rate': 6.211968574538846e-05, 'epoch': 9.33}

 78%|███████▊  | 21834/28080 [43:08:38<12:18:57,  7.10s/it]
 78%|███████▊  | 21835/28080 [43:08:46<12:22:46,  7.14s/it]
                                                           
{'loss': 0.5965, 'learning_rate': 6.210066382308507e-05, 'epoch': 9.33}

 78%|███████▊  | 21835/28080 [43:08:46<12:22:46,  7.14s/it]
 78%|███████▊  | 21836/28080 [43:08:53<12:21:24,  7.12s/it]
                                                           
{'loss': 0.5983, 'learning_rate': 6.208164440058861e-05, 'epoch': 9.33}

 78%|███████▊  | 21836/28080 [43:08:53<12:21:24,  7.12s/it]
 78%|███████▊  | 21837/28080 [43:09:00<12:17:50,  7.09s/it]
                                                           
{'loss': 0.5922, 'learning_rate': 6.206262747815192e-05, 'epoch': 9.33}

 78%|███████▊  | 21837/28080 [43:09:00<12:17:50,  7.09s/it]
 78%|███████▊  | 21838/28080 [43:09:07<12:17:25,  7.09s/it]
                                                           
{'loss': 0.5863, 'learning_rate': 6.204361305602816e-05, 'epoch': 9.33}

 78%|███████▊  | 21838/28080 [43:09:07<12:17:25,  7.09s/it]
 78%|███████▊  | 21839/28080 [43:09:14<12:19:49,  7.11s/it]
                                                           
{'loss': 0.6065, 'learning_rate': 6.202460113447031e-05, 'epoch': 9.33}

 78%|███████▊  | 21839/28080 [43:09:14<12:19:49,  7.11s/it]
 78%|███████▊  | 21840/28080 [43:09:21<12:21:52,  7.13s/it]
                                                           
{'loss': 0.6015, 'learning_rate': 6.200559171373105e-05, 'epoch': 9.33}

 78%|███████▊  | 21840/28080 [43:09:21<12:21:52,  7.13s/it]
 78%|███████▊  | 21841/28080 [43:09:28<12:19:00,  7.11s/it]
                                                           
{'loss': 0.595, 'learning_rate': 6.198658479406356e-05, 'epoch': 9.33}

 78%|███████▊  | 21841/28080 [43:09:28<12:19:00,  7.11s/it]
 78%|███████▊  | 21842/28080 [43:09:35<12:17:56,  7.10s/it]
                                                           
{'loss': 0.6211, 'learning_rate': 6.196758037572048e-05, 'epoch': 9.33}

 78%|███████▊  | 21842/28080 [43:09:35<12:17:56,  7.10s/it]
 78%|███████▊  | 21843/28080 [43:09:42<12:17:41,  7.10s/it]
                                                           
{'loss': 0.6346, 'learning_rate': 6.194857845895485e-05, 'epoch': 9.33}

 78%|███████▊  | 21843/28080 [43:09:42<12:17:41,  7.10s/it]
 78%|███████▊  | 21844/28080 [43:09:49<12:20:06,  7.12s/it]
                                                           
{'loss': 0.612, 'learning_rate': 6.192957904401938e-05, 'epoch': 9.33}

 78%|███████▊  | 21844/28080 [43:09:49<12:20:06,  7.12s/it]
 78%|███████▊  | 21845/28080 [43:09:57<12:17:18,  7.10s/it]
                                                           
{'loss': 0.5928, 'learning_rate': 6.191058213116685e-05, 'epoch': 9.33}

 78%|███████▊  | 21845/28080 [43:09:57<12:17:18,  7.10s/it]
 78%|███████▊  | 21846/28080 [43:10:04<12:19:00,  7.11s/it]
                                                           
{'loss': 0.6034, 'learning_rate': 6.18915877206499e-05, 'epoch': 9.33}

 78%|███████▊  | 21846/28080 [43:10:04<12:19:00,  7.11s/it]
 78%|███████▊  | 21847/28080 [43:10:11<12:19:07,  7.11s/it]
                                                           
{'loss': 0.6132, 'learning_rate': 6.187259581272139e-05, 'epoch': 9.33}

 78%|███████▊  | 21847/28080 [43:10:11<12:19:07,  7.11s/it]
 78%|███████▊  | 21848/28080 [43:10:18<12:17:04,  7.10s/it]
                                                           
{'loss': 0.6133, 'learning_rate': 6.185360640763394e-05, 'epoch': 9.33}

 78%|███████▊  | 21848/28080 [43:10:18<12:17:04,  7.10s/it]
 78%|███████▊  | 21849/28080 [43:10:25<12:17:24,  7.10s/it]
                                                           
{'loss': 0.5884, 'learning_rate': 6.183461950564012e-05, 'epoch': 9.33}

 78%|███████▊  | 21849/28080 [43:10:25<12:17:24,  7.10s/it]
 78%|███████▊  | 21850/28080 [43:10:32<12:15:01,  7.08s/it]
                                                           
{'loss': 0.5882, 'learning_rate': 6.181563510699251e-05, 'epoch': 9.33}

 78%|███████▊  | 21850/28080 [43:10:32<12:15:01,  7.08s/it]
 78%|███████▊  | 21851/28080 [43:10:39<12:16:17,  7.09s/it]
                                                           
{'loss': 0.6002, 'learning_rate': 6.179665321194381e-05, 'epoch': 9.33}

 78%|███████▊  | 21851/28080 [43:10:39<12:16:17,  7.09s/it]
 78%|███████▊  | 21852/28080 [43:10:46<12:13:47,  7.07s/it]
                                                           
{'loss': 0.6022, 'learning_rate': 6.17776738207464e-05, 'epoch': 9.33}

 78%|███████▊  | 21852/28080 [43:10:46<12:13:47,  7.07s/it]
 78%|███████▊  | 21853/28080 [43:10:53<12:14:11,  7.07s/it]
                                                           
{'loss': 0.6114, 'learning_rate': 6.175869693365301e-05, 'epoch': 9.34}

 78%|███████▊  | 21853/28080 [43:10:53<12:14:11,  7.07s/it]
 78%|███████▊  | 21854/28080 [43:11:00<12:14:12,  7.08s/it]
                                                           
{'loss': 0.5983, 'learning_rate': 6.173972255091581e-05, 'epoch': 9.34}

 78%|███████▊  | 21854/28080 [43:11:00<12:14:12,  7.08s/it]
 78%|███████▊  | 21855/28080 [43:11:07<12:12:42,  7.06s/it]
                                                           
{'loss': 0.6134, 'learning_rate': 6.172075067278745e-05, 'epoch': 9.34}

 78%|███████▊  | 21855/28080 [43:11:07<12:12:42,  7.06s/it]
 78%|███████▊  | 21856/28080 [43:11:14<12:11:48,  7.05s/it]
                                                           
{'loss': 0.5795, 'learning_rate': 6.170178129952022e-05, 'epoch': 9.34}

 78%|███████▊  | 21856/28080 [43:11:14<12:11:48,  7.05s/it]
 78%|███████▊  | 21857/28080 [43:11:21<12:14:16,  7.08s/it]
                                                           
{'loss': 0.589, 'learning_rate': 6.168281443136658e-05, 'epoch': 9.34}

 78%|███████▊  | 21857/28080 [43:11:21<12:14:16,  7.08s/it]
 78%|███████▊  | 21858/28080 [43:11:29<12:14:30,  7.08s/it]
                                                           
{'loss': 0.6142, 'learning_rate': 6.166385006857882e-05, 'epoch': 9.34}

 78%|███████▊  | 21858/28080 [43:11:29<12:14:30,  7.08s/it]
 78%|███████▊  | 21859/28080 [43:11:36<12:15:35,  7.09s/it]
                                                           
{'loss': 0.5839, 'learning_rate': 6.164488821140926e-05, 'epoch': 9.34}

 78%|███████▊  | 21859/28080 [43:11:36<12:15:35,  7.09s/it]
 78%|███████▊  | 21860/28080 [43:11:43<12:16:02,  7.10s/it]
                                                           
{'loss': 0.5977, 'learning_rate': 6.162592886011006e-05, 'epoch': 9.34}

 78%|███████▊  | 21860/28080 [43:11:43<12:16:02,  7.10s/it]
 78%|███████▊  | 21861/28080 [43:11:50<12:13:24,  7.08s/it]
                                                           
{'loss': 0.599, 'learning_rate': 6.160697201493362e-05, 'epoch': 9.34}

 78%|███████▊  | 21861/28080 [43:11:50<12:13:24,  7.08s/it]
 78%|███████▊  | 21862/28080 [43:11:57<12:14:25,  7.09s/it]
                                                           
{'loss': 0.6309, 'learning_rate': 6.158801767613206e-05, 'epoch': 9.34}

 78%|███████▊  | 21862/28080 [43:11:57<12:14:25,  7.09s/it]
 78%|███████▊  | 21863/28080 [43:12:04<12:13:09,  7.08s/it]
                                                           
{'loss': 0.602, 'learning_rate': 6.156906584395754e-05, 'epoch': 9.34}

 78%|███████▊  | 21863/28080 [43:12:04<12:13:09,  7.08s/it]
 78%|███████▊  | 21864/28080 [43:12:11<12:15:41,  7.10s/it]
                                                           
{'loss': 0.6134, 'learning_rate': 6.155011651866221e-05, 'epoch': 9.34}

 78%|███████▊  | 21864/28080 [43:12:11<12:15:41,  7.10s/it]
 78%|███████▊  | 21865/28080 [43:12:18<12:16:18,  7.11s/it]
                                                           
{'loss': 0.5975, 'learning_rate': 6.153116970049812e-05, 'epoch': 9.34}

 78%|███████▊  | 21865/28080 [43:12:18<12:16:18,  7.11s/it]
 78%|███████▊  | 21866/28080 [43:12:25<12:12:16,  7.07s/it]
                                                           
{'loss': 0.6124, 'learning_rate': 6.151222538971743e-05, 'epoch': 9.34}

 78%|███████▊  | 21866/28080 [43:12:25<12:12:16,  7.07s/it]
 78%|███████▊  | 21867/28080 [43:12:32<12:14:06,  7.09s/it]
                                                           
{'loss': 0.5982, 'learning_rate': 6.149328358657214e-05, 'epoch': 9.34}

 78%|███████▊  | 21867/28080 [43:12:32<12:14:06,  7.09s/it]
 78%|███████▊  | 21868/28080 [43:12:39<12:13:23,  7.08s/it]
                                                           
{'loss': 0.5841, 'learning_rate': 6.147434429131424e-05, 'epoch': 9.34}

 78%|███████▊  | 21868/28080 [43:12:39<12:13:23,  7.08s/it]
 78%|███████▊  | 21869/28080 [43:12:47<12:12:46,  7.08s/it]
                                                           
{'loss': 0.5986, 'learning_rate': 6.145540750419562e-05, 'epoch': 9.34}

 78%|███████▊  | 21869/28080 [43:12:47<12:12:46,  7.08s/it]
 78%|███████▊  | 21870/28080 [43:12:54<12:14:30,  7.10s/it]
                                                           
{'loss': 0.5981, 'learning_rate': 6.143647322546836e-05, 'epoch': 9.34}

 78%|███████▊  | 21870/28080 [43:12:54<12:14:30,  7.10s/it]
 78%|███████▊  | 21871/28080 [43:13:01<12:13:12,  7.09s/it]
                                                           
{'loss': 0.6094, 'learning_rate': 6.141754145538423e-05, 'epoch': 9.34}

 78%|███████▊  | 21871/28080 [43:13:01<12:13:12,  7.09s/it]
 78%|███████▊  | 21872/28080 [43:13:08<12:13:55,  7.09s/it]
                                                           
{'loss': 0.5939, 'learning_rate': 6.139861219419524e-05, 'epoch': 9.34}

 78%|███████▊  | 21872/28080 [43:13:08<12:13:55,  7.09s/it]
 78%|███████▊  | 21873/28080 [43:13:15<12:15:41,  7.11s/it]
                                                           
{'loss': 0.6184, 'learning_rate': 6.137968544215313e-05, 'epoch': 9.34}

 78%|███████▊  | 21873/28080 [43:13:15<12:15:41,  7.11s/it]
 78%|███████▊  | 21874/28080 [43:13:22<12:17:39,  7.13s/it]
                                                           
{'loss': 0.6133, 'learning_rate': 6.136076119950972e-05, 'epoch': 9.34}

 78%|███████▊  | 21874/28080 [43:13:22<12:17:39,  7.13s/it]
 78%|███████▊  | 21875/28080 [43:13:29<12:19:34,  7.15s/it]
                                                           
{'loss': 0.5992, 'learning_rate': 6.134183946651672e-05, 'epoch': 9.34}

 78%|███████▊  | 21875/28080 [43:13:29<12:19:34,  7.15s/it]
 78%|███████▊  | 21876/28080 [43:13:36<12:16:06,  7.12s/it]
                                                           
{'loss': 0.5803, 'learning_rate': 6.132292024342598e-05, 'epoch': 9.35}

 78%|███████▊  | 21876/28080 [43:13:36<12:16:06,  7.12s/it]
 78%|███████▊  | 21877/28080 [43:13:44<12:17:27,  7.13s/it]
                                                           
{'loss': 0.5814, 'learning_rate': 6.130400353048913e-05, 'epoch': 9.35}

 78%|███████▊  | 21877/28080 [43:13:44<12:17:27,  7.13s/it]
 78%|███████▊  | 21878/28080 [43:13:51<12:14:20,  7.10s/it]
                                                           
{'loss': 0.6113, 'learning_rate': 6.128508932795784e-05, 'epoch': 9.35}

 78%|███████▊  | 21878/28080 [43:13:51<12:14:20,  7.10s/it]
 78%|███████▊  | 21879/28080 [43:13:58<12:11:31,  7.08s/it]
                                                           
{'loss': 0.6398, 'learning_rate': 6.126617763608369e-05, 'epoch': 9.35}

 78%|███████▊  | 21879/28080 [43:13:58<12:11:31,  7.08s/it]
 78%|███████▊  | 21880/28080 [43:14:05<12:11:50,  7.08s/it]
                                                           
{'loss': 0.5957, 'learning_rate': 6.124726845511841e-05, 'epoch': 9.35}

 78%|███████▊  | 21880/28080 [43:14:05<12:11:50,  7.08s/it]
 78%|███████▊  | 21881/28080 [43:14:12<12:08:52,  7.05s/it]
                                                           
{'loss': 0.6108, 'learning_rate': 6.122836178531352e-05, 'epoch': 9.35}

 78%|███████▊  | 21881/28080 [43:14:12<12:08:52,  7.05s/it]
 78%|███████▊  | 21882/28080 [43:14:19<12:07:05,  7.04s/it]
                                                           
{'loss': 0.5949, 'learning_rate': 6.12094576269205e-05, 'epoch': 9.35}

 78%|███████▊  | 21882/28080 [43:14:19<12:07:05,  7.04s/it]
 78%|███████▊  | 21883/28080 [43:14:26<12:10:24,  7.07s/it]
                                                           
{'loss': 0.5981, 'learning_rate': 6.119055598019083e-05, 'epoch': 9.35}

 78%|███████▊  | 21883/28080 [43:14:26<12:10:24,  7.07s/it]
 78%|███████▊  | 21884/28080 [43:14:33<12:12:10,  7.09s/it]
                                                           
{'loss': 0.6163, 'learning_rate': 6.117165684537609e-05, 'epoch': 9.35}

 78%|███████▊  | 21884/28080 [43:14:33<12:12:10,  7.09s/it]
 78%|███████▊  | 21885/28080 [43:14:40<12:13:48,  7.11s/it]
                                                           
{'loss': 0.5869, 'learning_rate': 6.115276022272756e-05, 'epoch': 9.35}

 78%|███████▊  | 21885/28080 [43:14:40<12:13:48,  7.11s/it]
 78%|███████▊  | 21886/28080 [43:14:47<12:12:18,  7.09s/it]
                                                           
{'loss': 0.6307, 'learning_rate': 6.113386611249683e-05, 'epoch': 9.35}

 78%|███████▊  | 21886/28080 [43:14:47<12:12:18,  7.09s/it]
 78%|███████▊  | 21887/28080 [43:14:54<12:11:38,  7.09s/it]
                                                           
{'loss': 0.6055, 'learning_rate': 6.111497451493516e-05, 'epoch': 9.35}

 78%|███████▊  | 21887/28080 [43:14:54<12:11:38,  7.09s/it]
 78%|███████▊  | 21888/28080 [43:15:01<12:11:08,  7.08s/it]
                                                           
{'loss': 0.6107, 'learning_rate': 6.10960854302939e-05, 'epoch': 9.35}

 78%|███████▊  | 21888/28080 [43:15:01<12:11:08,  7.08s/it]
 78%|███████▊  | 21889/28080 [43:15:08<12:11:53,  7.09s/it]
                                                           
{'loss': 0.585, 'learning_rate': 6.107719885882434e-05, 'epoch': 9.35}

 78%|███████▊  | 21889/28080 [43:15:08<12:11:53,  7.09s/it]
 78%|███████▊  | 21890/28080 [43:15:16<12:10:47,  7.08s/it]
                                                           
{'loss': 0.5901, 'learning_rate': 6.10583148007777e-05, 'epoch': 9.35}

 78%|███████▊  | 21890/28080 [43:15:16<12:10:47,  7.08s/it]
 78%|███████▊  | 21891/28080 [43:15:23<12:07:30,  7.05s/it]
                                                           
{'loss': 0.6011, 'learning_rate': 6.103943325640529e-05, 'epoch': 9.35}

 78%|███████▊  | 21891/28080 [43:15:23<12:07:30,  7.05s/it]
 78%|███████▊  | 21892/28080 [43:15:30<12:07:02,  7.05s/it]
                                                           
{'loss': 0.5947, 'learning_rate': 6.1020554225958315e-05, 'epoch': 9.35}

 78%|███████▊  | 21892/28080 [43:15:30<12:07:02,  7.05s/it]
 78%|███████▊  | 21893/28080 [43:15:37<12:06:50,  7.05s/it]
                                                           
{'loss': 0.6159, 'learning_rate': 6.1001677709687896e-05, 'epoch': 9.35}

 78%|███████▊  | 21893/28080 [43:15:37<12:06:50,  7.05s/it]
 78%|███████▊  | 21894/28080 [43:15:44<12:08:48,  7.07s/it]
                                                           
{'loss': 0.6037, 'learning_rate': 6.098280370784509e-05, 'epoch': 9.35}

 78%|███████▊  | 21894/28080 [43:15:44<12:08:48,  7.07s/it]
 78%|███████▊  | 21895/28080 [43:15:51<12:10:39,  7.09s/it]
                                                           
{'loss': 0.6098, 'learning_rate': 6.096393222068117e-05, 'epoch': 9.35}

 78%|███████▊  | 21895/28080 [43:15:51<12:10:39,  7.09s/it]
 78%|███████▊  | 21896/28080 [43:15:58<12:12:13,  7.10s/it]
                                                           
{'loss': 0.5918, 'learning_rate': 6.0945063248447116e-05, 'epoch': 9.35}

 78%|███████▊  | 21896/28080 [43:15:58<12:12:13,  7.10s/it]
 78%|███████▊  | 21897/28080 [43:16:05<12:09:19,  7.08s/it]
                                                           
{'loss': 0.6088, 'learning_rate': 6.092619679139394e-05, 'epoch': 9.35}

 78%|███████▊  | 21897/28080 [43:16:05<12:09:19,  7.08s/it]
 78%|███████▊  | 21898/28080 [43:16:12<12:08:34,  7.07s/it]
                                                           
{'loss': 0.6006, 'learning_rate': 6.09073328497726e-05, 'epoch': 9.35}

 78%|███████▊  | 21898/28080 [43:16:12<12:08:34,  7.07s/it]
 78%|███████▊  | 21899/28080 [43:16:19<12:07:14,  7.06s/it]
                                                           
{'loss': 0.607, 'learning_rate': 6.088847142383419e-05, 'epoch': 9.36}

 78%|███████▊  | 21899/28080 [43:16:19<12:07:14,  7.06s/it]
 78%|███████▊  | 21900/28080 [43:16:26<12:07:50,  7.07s/it]
                                                           
{'loss': 0.5885, 'learning_rate': 6.0869612513829495e-05, 'epoch': 9.36}

 78%|███████▊  | 21900/28080 [43:16:26<12:07:50,  7.07s/it]
 78%|███████▊  | 21901/28080 [43:16:33<12:10:06,  7.09s/it]
                                                           
{'loss': 0.5936, 'learning_rate': 6.085075612000965e-05, 'epoch': 9.36}

 78%|███████▊  | 21901/28080 [43:16:33<12:10:06,  7.09s/it]
 78%|███████▊  | 21902/28080 [43:16:40<12:11:13,  7.10s/it]
                                                           
{'loss': 0.5794, 'learning_rate': 6.083190224262519e-05, 'epoch': 9.36}

 78%|███████▊  | 21902/28080 [43:16:40<12:11:13,  7.10s/it]
 78%|███████▊  | 21903/28080 [43:16:48<12:12:44,  7.12s/it]
                                                           
{'loss': 0.6226, 'learning_rate': 6.081305088192721e-05, 'epoch': 9.36}

 78%|███████▊  | 21903/28080 [43:16:48<12:12:44,  7.12s/it]
 78%|███████▊  | 21904/28080 [43:16:55<12:13:24,  7.13s/it]
                                                           
{'loss': 0.5901, 'learning_rate': 6.079420203816635e-05, 'epoch': 9.36}

 78%|███████▊  | 21904/28080 [43:16:55<12:13:24,  7.13s/it]
 78%|███████▊  | 21905/28080 [43:17:02<12:12:06,  7.11s/it]
                                                           
{'loss': 0.5916, 'learning_rate': 6.077535571159351e-05, 'epoch': 9.36}

 78%|███████▊  | 21905/28080 [43:17:02<12:12:06,  7.11s/it]
 78%|███████▊  | 21906/28080 [43:17:09<12:10:54,  7.10s/it]
                                                           
{'loss': 0.6043, 'learning_rate': 6.075651190245932e-05, 'epoch': 9.36}

 78%|███████▊  | 21906/28080 [43:17:09<12:10:54,  7.10s/it]
 78%|███████▊  | 21907/28080 [43:17:16<12:07:47,  7.07s/it]
                                                           
{'loss': 0.6058, 'learning_rate': 6.073767061101454e-05, 'epoch': 9.36}

 78%|███████▊  | 21907/28080 [43:17:16<12:07:47,  7.07s/it]
 78%|███████▊  | 21908/28080 [43:17:23<12:10:05,  7.10s/it]
                                                           
{'loss': 0.6176, 'learning_rate': 6.0718831837509705e-05, 'epoch': 9.36}

 78%|███████▊  | 21908/28080 [43:17:23<12:10:05,  7.10s/it]
 78%|███████▊  | 21909/28080 [43:17:30<12:09:19,  7.09s/it]
                                                           
{'loss': 0.5936, 'learning_rate': 6.069999558219563e-05, 'epoch': 9.36}

 78%|███████▊  | 21909/28080 [43:17:30<12:09:19,  7.09s/it]
 78%|███████▊  | 21910/28080 [43:17:37<12:09:13,  7.09s/it]
                                                           
{'loss': 0.606, 'learning_rate': 6.0681161845322826e-05, 'epoch': 9.36}

 78%|███████▊  | 21910/28080 [43:17:37<12:09:13,  7.09s/it]
 78%|███████▊  | 21911/28080 [43:17:44<12:11:08,  7.11s/it]
                                                           
{'loss': 0.6031, 'learning_rate': 6.066233062714185e-05, 'epoch': 9.36}

 78%|███████▊  | 21911/28080 [43:17:44<12:11:08,  7.11s/it]
 78%|███████▊  | 21912/28080 [43:17:51<12:09:57,  7.10s/it]
                                                           
{'loss': 0.6166, 'learning_rate': 6.064350192790316e-05, 'epoch': 9.36}

 78%|███████▊  | 21912/28080 [43:17:51<12:09:57,  7.10s/it]
 78%|███████▊  | 21913/28080 [43:17:59<12:10:11,  7.10s/it]
                                                           
{'loss': 0.6285, 'learning_rate': 6.0624675747857404e-05, 'epoch': 9.36}

 78%|███████▊  | 21913/28080 [43:17:59<12:10:11,  7.10s/it]
 78%|███████▊  | 21914/28080 [43:18:06<12:11:31,  7.12s/it]
                                                           
{'loss': 0.576, 'learning_rate': 6.060585208725497e-05, 'epoch': 9.36}

 78%|███████▊  | 21914/28080 [43:18:06<12:11:31,  7.12s/it]
 78%|███████▊  | 21915/28080 [43:18:13<12:09:22,  7.10s/it]
                                                           
{'loss': 0.6167, 'learning_rate': 6.058703094634627e-05, 'epoch': 9.36}

 78%|███████▊  | 21915/28080 [43:18:13<12:09:22,  7.10s/it]
 78%|███████▊  | 21916/28080 [43:18:20<12:08:07,  7.09s/it]
                                                           
{'loss': 0.601, 'learning_rate': 6.056821232538173e-05, 'epoch': 9.36}

 78%|███████▊  | 21916/28080 [43:18:20<12:08:07,  7.09s/it]
 78%|███████▊  | 21917/28080 [43:18:27<12:08:53,  7.10s/it]
                                                           
{'loss': 0.5888, 'learning_rate': 6.054939622461164e-05, 'epoch': 9.36}

 78%|███████▊  | 21917/28080 [43:18:27<12:08:53,  7.10s/it]
 78%|███████▊  | 21918/28080 [43:18:34<12:05:43,  7.07s/it]
                                                           
{'loss': 0.6187, 'learning_rate': 6.053058264428643e-05, 'epoch': 9.36}

 78%|███████▊  | 21918/28080 [43:18:34<12:05:43,  7.07s/it]
 78%|███████▊  | 21919/28080 [43:18:41<12:06:05,  7.07s/it]
                                                           
{'loss': 0.5922, 'learning_rate': 6.051177158465632e-05, 'epoch': 9.36}

 78%|███████▊  | 21919/28080 [43:18:41<12:06:05,  7.07s/it]
 78%|███████▊  | 21920/28080 [43:18:48<12:07:40,  7.09s/it]
                                                           
{'loss': 0.6166, 'learning_rate': 6.049296304597171e-05, 'epoch': 9.36}

 78%|███████▊  | 21920/28080 [43:18:48<12:07:40,  7.09s/it]
 78%|███████▊  | 21921/28080 [43:18:55<12:06:41,  7.08s/it]
                                                           
{'loss': 0.615, 'learning_rate': 6.047415702848261e-05, 'epoch': 9.36}

 78%|███████▊  | 21921/28080 [43:18:55<12:06:41,  7.08s/it]
 78%|███████▊  | 21922/28080 [43:19:02<12:05:21,  7.07s/it]
                                                           
{'loss': 0.6128, 'learning_rate': 6.045535353243939e-05, 'epoch': 9.36}

 78%|███████▊  | 21922/28080 [43:19:02<12:05:21,  7.07s/it]
 78%|███████▊  | 21923/28080 [43:19:09<12:05:30,  7.07s/it]
                                                           
{'loss': 0.6095, 'learning_rate': 6.043655255809208e-05, 'epoch': 9.37}

 78%|███████▊  | 21923/28080 [43:19:09<12:05:30,  7.07s/it]
 78%|███████▊  | 21924/28080 [43:19:16<12:02:37,  7.04s/it]
                                                           
{'loss': 0.6034, 'learning_rate': 6.0417754105690945e-05, 'epoch': 9.37}

 78%|███████▊  | 21924/28080 [43:19:16<12:02:37,  7.04s/it]
 78%|███████▊  | 21925/28080 [43:19:23<12:01:31,  7.03s/it]
                                                           
{'loss': 0.6134, 'learning_rate': 6.039895817548599e-05, 'epoch': 9.37}

 78%|███████▊  | 21925/28080 [43:19:23<12:01:31,  7.03s/it]
 78%|███████▊  | 21926/28080 [43:19:31<12:06:02,  7.08s/it]
                                                           
{'loss': 0.6201, 'learning_rate': 6.0380164767727316e-05, 'epoch': 9.37}

 78%|███████▊  | 21926/28080 [43:19:31<12:06:02,  7.08s/it]
 78%|███████▊  | 21927/28080 [43:19:38<12:06:54,  7.09s/it]
                                                           
{'loss': 0.6185, 'learning_rate': 6.036137388266485e-05, 'epoch': 9.37}

 78%|███████▊  | 21927/28080 [43:19:38<12:06:54,  7.09s/it]
 78%|███████▊  | 21928/28080 [43:19:45<12:08:27,  7.10s/it]
                                                           
{'loss': 0.6031, 'learning_rate': 6.0342585520548746e-05, 'epoch': 9.37}

 78%|███████▊  | 21928/28080 [43:19:45<12:08:27,  7.10s/it]
 78%|███████▊  | 21929/28080 [43:19:52<12:09:43,  7.12s/it]
                                                           
{'loss': 0.6079, 'learning_rate': 6.032379968162888e-05, 'epoch': 9.37}

 78%|███████▊  | 21929/28080 [43:19:52<12:09:43,  7.12s/it]
 78%|███████▊  | 21930/28080 [43:19:59<12:09:22,  7.12s/it]
                                                           
{'loss': 0.6094, 'learning_rate': 6.030501636615518e-05, 'epoch': 9.37}

 78%|███████▊  | 21930/28080 [43:19:59<12:09:22,  7.12s/it]
 78%|███████▊  | 21931/28080 [43:20:06<12:08:55,  7.11s/it]
                                                           
{'loss': 0.6016, 'learning_rate': 6.028623557437749e-05, 'epoch': 9.37}

 78%|███████▊  | 21931/28080 [43:20:06<12:08:55,  7.11s/it]
 78%|███████▊  | 21932/28080 [43:20:13<12:08:19,  7.11s/it]
                                                           
{'loss': 0.6023, 'learning_rate': 6.026745730654576e-05, 'epoch': 9.37}

 78%|███████▊  | 21932/28080 [43:20:13<12:08:19,  7.11s/it]
 78%|███████▊  | 21933/28080 [43:20:20<12:09:47,  7.12s/it]
                                                           
{'loss': 0.5864, 'learning_rate': 6.024868156290972e-05, 'epoch': 9.37}

 78%|███████▊  | 21933/28080 [43:20:20<12:09:47,  7.12s/it]
 78%|███████▊  | 21934/28080 [43:20:28<12:09:57,  7.13s/it]
                                                           
{'loss': 0.5994, 'learning_rate': 6.0229908343719274e-05, 'epoch': 9.37}

 78%|███████▊  | 21934/28080 [43:20:28<12:09:57,  7.13s/it]
 78%|███████▊  | 21935/28080 [43:20:35<12:07:03,  7.10s/it]
                                                           
{'loss': 0.6027, 'learning_rate': 6.021113764922412e-05, 'epoch': 9.37}

 78%|███████▊  | 21935/28080 [43:20:35<12:07:03,  7.10s/it]
 78%|███████▊  | 21936/28080 [43:20:42<12:08:44,  7.12s/it]
                                                           
{'loss': 0.5864, 'learning_rate': 6.019236947967399e-05, 'epoch': 9.37}

 78%|███████▊  | 21936/28080 [43:20:42<12:08:44,  7.12s/it]
 78%|███████▊  | 21937/28080 [43:20:49<12:08:44,  7.12s/it]
                                                           
{'loss': 0.5886, 'learning_rate': 6.017360383531853e-05, 'epoch': 9.37}

 78%|███████▊  | 21937/28080 [43:20:49<12:08:44,  7.12s/it]
 78%|███████▊  | 21938/28080 [43:20:56<12:07:35,  7.11s/it]
                                                           
{'loss': 0.5958, 'learning_rate': 6.0154840716407475e-05, 'epoch': 9.37}

 78%|███████▊  | 21938/28080 [43:20:56<12:07:35,  7.11s/it]
 78%|███████▊  | 21939/28080 [43:21:03<12:06:37,  7.10s/it]
                                                           
{'loss': 0.6064, 'learning_rate': 6.013608012319041e-05, 'epoch': 9.37}

 78%|███████▊  | 21939/28080 [43:21:03<12:06:37,  7.10s/it]
 78%|███████▊  | 21940/28080 [43:21:10<12:07:20,  7.11s/it]
                                                           
{'loss': 0.6001, 'learning_rate': 6.011732205591694e-05, 'epoch': 9.37}

 78%|███████▊  | 21940/28080 [43:21:10<12:07:20,  7.11s/it]
 78%|███████▊  | 21941/28080 [43:21:17<12:07:13,  7.11s/it]
                                                           
{'loss': 0.5889, 'learning_rate': 6.009856651483661e-05, 'epoch': 9.37}

 78%|███████▊  | 21941/28080 [43:21:17<12:07:13,  7.11s/it]
 78%|███████▊  | 21942/28080 [43:21:24<12:10:05,  7.14s/it]
                                                           
{'loss': 0.6154, 'learning_rate': 6.0079813500198864e-05, 'epoch': 9.37}

 78%|███████▊  | 21942/28080 [43:21:24<12:10:05,  7.14s/it]
 78%|███████▊  | 21943/28080 [43:21:32<12:08:58,  7.13s/it]
                                                           
{'loss': 0.6068, 'learning_rate': 6.006106301225333e-05, 'epoch': 9.37}

 78%|███████▊  | 21943/28080 [43:21:32<12:08:58,  7.13s/it]
 78%|███████▊  | 21944/28080 [43:21:39<12:10:06,  7.14s/it]
                                                           
{'loss': 0.605, 'learning_rate': 6.004231505124944e-05, 'epoch': 9.37}

 78%|███████▊  | 21944/28080 [43:21:39<12:10:06,  7.14s/it]
 78%|███████▊  | 21945/28080 [43:21:46<12:09:24,  7.13s/it]
                                                           
{'loss': 0.5964, 'learning_rate': 6.002356961743654e-05, 'epoch': 9.37}

 78%|███████▊  | 21945/28080 [43:21:46<12:09:24,  7.13s/it]
 78%|███████▊  | 21946/28080 [43:21:53<12:07:02,  7.11s/it]
                                                           
{'loss': 0.6211, 'learning_rate': 6.000482671106402e-05, 'epoch': 9.38}

 78%|███████▊  | 21946/28080 [43:21:53<12:07:02,  7.11s/it]
 78%|███████▊  | 21947/28080 [43:22:00<12:09:18,  7.13s/it]
                                                           
{'loss': 0.6131, 'learning_rate': 5.998608633238131e-05, 'epoch': 9.38}

 78%|███████▊  | 21947/28080 [43:22:00<12:09:18,  7.13s/it]
 78%|███████▊  | 21948/28080 [43:22:07<12:07:51,  7.12s/it]
                                                           
{'loss': 0.5857, 'learning_rate': 5.9967348481637654e-05, 'epoch': 9.38}

 78%|███████▊  | 21948/28080 [43:22:07<12:07:51,  7.12s/it]
 78%|███████▊  | 21949/28080 [43:22:14<12:05:53,  7.10s/it]
                                                           
{'loss': 0.6153, 'learning_rate': 5.994861315908251e-05, 'epoch': 9.38}

 78%|███████▊  | 21949/28080 [43:22:14<12:05:53,  7.10s/it]
 78%|███████▊  | 21950/28080 [43:22:21<12:07:35,  7.12s/it]
                                                           
{'loss': 0.6083, 'learning_rate': 5.9929880364964856e-05, 'epoch': 9.38}

 78%|███████▊  | 21950/28080 [43:22:21<12:07:35,  7.12s/it]
 78%|███████▊  | 21951/28080 [43:22:28<12:05:59,  7.11s/it]
                                                           
{'loss': 0.5898, 'learning_rate': 5.991115009953416e-05, 'epoch': 9.38}

 78%|███████▊  | 21951/28080 [43:22:28<12:05:59,  7.11s/it]
 78%|███████▊  | 21952/28080 [43:22:36<12:06:29,  7.11s/it]
                                                           
{'loss': 0.5974, 'learning_rate': 5.989242236303941e-05, 'epoch': 9.38}

 78%|███████▊  | 21952/28080 [43:22:36<12:06:29,  7.11s/it]
 78%|███████▊  | 21953/28080 [43:22:43<12:06:38,  7.12s/it]
                                                           
{'loss': 0.6106, 'learning_rate': 5.9873697155729936e-05, 'epoch': 9.38}

 78%|███████▊  | 21953/28080 [43:22:43<12:06:38,  7.12s/it]
 78%|███████▊  | 21954/28080 [43:22:50<12:02:48,  7.08s/it]
                                                           
{'loss': 0.6259, 'learning_rate': 5.985497447785476e-05, 'epoch': 9.38}

 78%|███████▊  | 21954/28080 [43:22:50<12:02:48,  7.08s/it]
 78%|███████▊  | 21955/28080 [43:22:57<12:04:58,  7.10s/it]
                                                           
{'loss': 0.6103, 'learning_rate': 5.9836254329662996e-05, 'epoch': 9.38}

 78%|███████▊  | 21955/28080 [43:22:57<12:04:58,  7.10s/it]
 78%|███████▊  | 21956/28080 [43:23:04<12:05:41,  7.11s/it]
                                                           
{'loss': 0.6024, 'learning_rate': 5.981753671140364e-05, 'epoch': 9.38}

 78%|███████▊  | 21956/28080 [43:23:04<12:05:41,  7.11s/it]
 78%|███████▊  | 21957/28080 [43:23:11<12:06:30,  7.12s/it]
                                                           
{'loss': 0.5971, 'learning_rate': 5.979882162332581e-05, 'epoch': 9.38}

 78%|███████▊  | 21957/28080 [43:23:11<12:06:30,  7.12s/it]
 78%|███████▊  | 21958/28080 [43:23:18<12:03:54,  7.09s/it]
                                                           
{'loss': 0.616, 'learning_rate': 5.978010906567843e-05, 'epoch': 9.38}

 78%|███████▊  | 21958/28080 [43:23:18<12:03:54,  7.09s/it]
 78%|███████▊  | 21959/28080 [43:23:25<12:02:18,  7.08s/it]
                                                           
{'loss': 0.6121, 'learning_rate': 5.9761399038710474e-05, 'epoch': 9.38}

 78%|███████▊  | 21959/28080 [43:23:25<12:02:18,  7.08s/it]
 78%|███████▊  | 21960/28080 [43:23:32<12:04:25,  7.10s/it]
                                                           
{'loss': 0.6218, 'learning_rate': 5.9742691542670755e-05, 'epoch': 9.38}

 78%|███████▊  | 21960/28080 [43:23:32<12:04:25,  7.10s/it]
 78%|███████▊  | 21961/28080 [43:23:39<12:03:33,  7.09s/it]
                                                           
{'loss': 0.6106, 'learning_rate': 5.972398657780834e-05, 'epoch': 9.38}

 78%|███████▊  | 21961/28080 [43:23:39<12:03:33,  7.09s/it]
 78%|███████▊  | 21962/28080 [43:23:47<12:02:26,  7.09s/it]
                                                           
{'loss': 0.5999, 'learning_rate': 5.97052841443719e-05, 'epoch': 9.38}

 78%|███████▊  | 21962/28080 [43:23:47<12:02:26,  7.09s/it]
 78%|███████▊  | 21963/28080 [43:23:54<12:03:09,  7.09s/it]
                                                           
{'loss': 0.6113, 'learning_rate': 5.9686584242610506e-05, 'epoch': 9.38}

 78%|███████▊  | 21963/28080 [43:23:54<12:03:09,  7.09s/it]
 78%|███████▊  | 21964/28080 [43:24:01<12:01:23,  7.08s/it]
                                                           
{'loss': 0.6144, 'learning_rate': 5.966788687277269e-05, 'epoch': 9.38}

 78%|███████▊  | 21964/28080 [43:24:01<12:01:23,  7.08s/it]
 78%|███████▊  | 21965/28080 [43:24:08<12:01:02,  7.07s/it]
                                                           
{'loss': 0.6103, 'learning_rate': 5.9649192035107215e-05, 'epoch': 9.38}

 78%|███████▊  | 21965/28080 [43:24:08<12:01:02,  7.07s/it]
 78%|███████▊  | 21966/28080 [43:24:15<12:00:51,  7.07s/it]
                                                           
{'loss': 0.6102, 'learning_rate': 5.963049972986292e-05, 'epoch': 9.38}

 78%|███████▊  | 21966/28080 [43:24:15<12:00:51,  7.07s/it]
 78%|███████▊  | 21967/28080 [43:24:22<12:03:37,  7.10s/it]
                                                           
{'loss': 0.5933, 'learning_rate': 5.9611809957288375e-05, 'epoch': 9.38}

 78%|███████▊  | 21967/28080 [43:24:22<12:03:37,  7.10s/it]
 78%|███████▊  | 21968/28080 [43:24:29<12:02:47,  7.10s/it]
                                                           
{'loss': 0.6122, 'learning_rate': 5.9593122717632426e-05, 'epoch': 9.38}

 78%|███████▊  | 21968/28080 [43:24:29<12:02:47,  7.10s/it]
 78%|███████▊  | 21969/28080 [43:24:36<11:59:15,  7.06s/it]
                                                           
{'loss': 0.5979, 'learning_rate': 5.9574438011143403e-05, 'epoch': 9.38}

 78%|███████▊  | 21969/28080 [43:24:36<11:59:15,  7.06s/it]
 78%|███████▊  | 21970/28080 [43:24:43<11:57:02,  7.04s/it]
                                                           
{'loss': 0.6009, 'learning_rate': 5.9555755838070106e-05, 'epoch': 9.39}

 78%|███████▊  | 21970/28080 [43:24:43<11:57:02,  7.04s/it]
 78%|███████▊  | 21971/28080 [43:24:50<12:00:55,  7.08s/it]
                                                           
{'loss': 0.5939, 'learning_rate': 5.9537076198660916e-05, 'epoch': 9.39}

 78%|███████▊  | 21971/28080 [43:24:50<12:00:55,  7.08s/it]
 78%|███████▊  | 21972/28080 [43:24:57<12:03:19,  7.11s/it]
                                                           
{'loss': 0.6256, 'learning_rate': 5.951839909316453e-05, 'epoch': 9.39}

 78%|███████▊  | 21972/28080 [43:24:57<12:03:19,  7.11s/it]
 78%|███████▊  | 21973/28080 [43:25:05<12:03:55,  7.11s/it]
                                                           
{'loss': 0.5973, 'learning_rate': 5.949972452182933e-05, 'epoch': 9.39}

 78%|███████▊  | 21973/28080 [43:25:05<12:03:55,  7.11s/it]
 78%|███████▊  | 21974/28080 [43:25:12<12:08:28,  7.16s/it]
                                                           
{'loss': 0.613, 'learning_rate': 5.9481052484903795e-05, 'epoch': 9.39}

 78%|███████▊  | 21974/28080 [43:25:12<12:08:28,  7.16s/it]
 78%|███████▊  | 21975/28080 [43:25:19<12:07:05,  7.15s/it]
                                                           
{'loss': 0.605, 'learning_rate': 5.9462382982636206e-05, 'epoch': 9.39}

 78%|███████▊  | 21975/28080 [43:25:19<12:07:05,  7.15s/it]
 78%|███████▊  | 21976/28080 [43:25:26<12:06:18,  7.14s/it]
                                                           
{'loss': 0.6135, 'learning_rate': 5.9443716015275126e-05, 'epoch': 9.39}

 78%|███████▊  | 21976/28080 [43:25:26<12:06:18,  7.14s/it]
 78%|███████▊  | 21977/28080 [43:25:33<12:05:50,  7.14s/it]
                                                           
{'loss': 0.6065, 'learning_rate': 5.94250515830688e-05, 'epoch': 9.39}

 78%|███████▊  | 21977/28080 [43:25:33<12:05:50,  7.14s/it]
 78%|███████▊  | 21978/28080 [43:25:40<12:04:24,  7.12s/it]
                                                           
{'loss': 0.6094, 'learning_rate': 5.9406389686265576e-05, 'epoch': 9.39}

 78%|███████▊  | 21978/28080 [43:25:40<12:04:24,  7.12s/it]
 78%|███████▊  | 21979/28080 [43:25:47<12:04:54,  7.13s/it]
                                                           
{'loss': 0.6021, 'learning_rate': 5.938773032511363e-05, 'epoch': 9.39}

 78%|███████▊  | 21979/28080 [43:25:47<12:04:54,  7.13s/it]
 78%|███████▊  | 21980/28080 [43:25:54<12:00:28,  7.09s/it]
                                                           
{'loss': 0.6191, 'learning_rate': 5.936907349986137e-05, 'epoch': 9.39}

 78%|███████▊  | 21980/28080 [43:25:54<12:00:28,  7.09s/it]
 78%|███████▊  | 21981/28080 [43:26:01<11:59:46,  7.08s/it]
                                                           
{'loss': 0.6043, 'learning_rate': 5.9350419210756846e-05, 'epoch': 9.39}

 78%|███████▊  | 21981/28080 [43:26:01<11:59:46,  7.08s/it]
 78%|███████▊  | 21982/28080 [43:26:09<11:59:44,  7.08s/it]
                                                           
{'loss': 0.6161, 'learning_rate': 5.933176745804847e-05, 'epoch': 9.39}

 78%|███████▊  | 21982/28080 [43:26:09<11:59:44,  7.08s/it]
 78%|███████▊  | 21983/28080 [43:26:16<11:58:45,  7.07s/it]
                                                           
{'loss': 0.5897, 'learning_rate': 5.931311824198407e-05, 'epoch': 9.39}

 78%|███████▊  | 21983/28080 [43:26:16<11:58:45,  7.07s/it]
 78%|███████▊  | 21984/28080 [43:26:23<12:01:01,  7.10s/it]
                                                           
{'loss': 0.5866, 'learning_rate': 5.929447156281198e-05, 'epoch': 9.39}

 78%|███████▊  | 21984/28080 [43:26:23<12:01:01,  7.10s/it]
 78%|███████▊  | 21985/28080 [43:26:30<12:03:03,  7.12s/it]
                                                           
{'loss': 0.6003, 'learning_rate': 5.927582742078014e-05, 'epoch': 9.39}

 78%|███████▊  | 21985/28080 [43:26:30<12:03:03,  7.12s/it]
 78%|███████▊  | 21986/28080 [43:26:37<12:04:52,  7.14s/it]
                                                           
{'loss': 0.6065, 'learning_rate': 5.9257185816136734e-05, 'epoch': 9.39}

 78%|███████▊  | 21986/28080 [43:26:37<12:04:52,  7.14s/it]
 78%|███████▊  | 21987/28080 [43:26:44<12:06:37,  7.16s/it]
                                                           
{'loss': 0.5867, 'learning_rate': 5.923854674912968e-05, 'epoch': 9.39}

 78%|███████▊  | 21987/28080 [43:26:44<12:06:37,  7.16s/it]
 78%|███████▊  | 21988/28080 [43:26:51<12:05:04,  7.14s/it]
                                                           
{'loss': 0.6258, 'learning_rate': 5.9219910220006975e-05, 'epoch': 9.39}

 78%|███████▊  | 21988/28080 [43:26:51<12:05:04,  7.14s/it]
 78%|███████▊  | 21989/28080 [43:26:58<12:03:41,  7.13s/it]
                                                           
{'loss': 0.6109, 'learning_rate': 5.9201276229016526e-05, 'epoch': 9.39}

 78%|███████▊  | 21989/28080 [43:26:58<12:03:41,  7.13s/it]
 78%|███████▊  | 21990/28080 [43:27:06<12:03:04,  7.12s/it]
                                                           
{'loss': 0.6092, 'learning_rate': 5.918264477640623e-05, 'epoch': 9.39}

 78%|███████▊  | 21990/28080 [43:27:06<12:03:04,  7.12s/it]
 78%|███████▊  | 21991/28080 [43:27:13<12:03:22,  7.13s/it]
                                                           
{'loss': 0.5901, 'learning_rate': 5.9164015862424036e-05, 'epoch': 9.39}

 78%|███████▊  | 21991/28080 [43:27:13<12:03:22,  7.13s/it]
 78%|███████▊  | 21992/28080 [43:27:20<12:03:55,  7.13s/it]
                                                           
{'loss': 0.6267, 'learning_rate': 5.9145389487317734e-05, 'epoch': 9.39}

 78%|███████▊  | 21992/28080 [43:27:20<12:03:55,  7.13s/it]
 78%|███████▊  | 21993/28080 [43:27:27<12:09:19,  7.19s/it]
                                                           
{'loss': 0.5918, 'learning_rate': 5.912676565133512e-05, 'epoch': 9.4}

 78%|███████▊  | 21993/28080 [43:27:27<12:09:19,  7.19s/it]
 78%|███████▊  | 21994/28080 [43:27:34<12:09:58,  7.20s/it]
                                                           
{'loss': 0.5907, 'learning_rate': 5.910814435472392e-05, 'epoch': 9.4}

 78%|███████▊  | 21994/28080 [43:27:34<12:09:58,  7.20s/it]
 78%|███████▊  | 21995/28080 [43:27:42<12:07:23,  7.17s/it]
                                                           
{'loss': 0.6211, 'learning_rate': 5.908952559773201e-05, 'epoch': 9.4}

 78%|███████▊  | 21995/28080 [43:27:42<12:07:23,  7.17s/it]
 78%|███████▊  | 21996/28080 [43:27:49<12:04:06,  7.14s/it]
                                                           
{'loss': 0.6158, 'learning_rate': 5.907090938060691e-05, 'epoch': 9.4}

 78%|███████▊  | 21996/28080 [43:27:49<12:04:06,  7.14s/it]
 78%|███████▊  | 21997/28080 [43:27:56<12:01:58,  7.12s/it]
                                                           
{'loss': 0.5855, 'learning_rate': 5.905229570359655e-05, 'epoch': 9.4}

 78%|███████▊  | 21997/28080 [43:27:56<12:01:58,  7.12s/it]
 78%|███████▊  | 21998/28080 [43:28:03<12:00:13,  7.11s/it]
                                                           
{'loss': 0.5999, 'learning_rate': 5.903368456694827e-05, 'epoch': 9.4}

 78%|███████▊  | 21998/28080 [43:28:03<12:00:13,  7.11s/it]
 78%|███████▊  | 21999/28080 [43:28:10<11:57:26,  7.08s/it]
                                                           
{'loss': 0.6124, 'learning_rate': 5.9015075970909885e-05, 'epoch': 9.4}

 78%|███████▊  | 21999/28080 [43:28:10<11:57:26,  7.08s/it]
 78%|███████▊  | 22000/28080 [43:28:17<11:57:06,  7.08s/it]
                                                           
{'loss': 0.6021, 'learning_rate': 5.8996469915728795e-05, 'epoch': 9.4}

 78%|███████▊  | 22000/28080 [43:28:17<11:57:06,  7.08s/it]
 78%|███████▊  | 22001/28080 [43:28:24<11:53:00,  7.04s/it]
                                                           
{'loss': 0.6249, 'learning_rate': 5.89778664016527e-05, 'epoch': 9.4}

 78%|███████▊  | 22001/28080 [43:28:24<11:53:00,  7.04s/it]
 78%|███████▊  | 22002/28080 [43:28:31<11:54:54,  7.06s/it]
                                                           
{'loss': 0.6021, 'learning_rate': 5.895926542892904e-05, 'epoch': 9.4}

 78%|███████▊  | 22002/28080 [43:28:31<11:54:54,  7.06s/it]
 78%|███████▊  | 22003/28080 [43:28:38<11:56:34,  7.07s/it]
                                                           
{'loss': 0.5879, 'learning_rate': 5.8940666997805256e-05, 'epoch': 9.4}

 78%|███████▊  | 22003/28080 [43:28:38<11:56:34,  7.07s/it]
 78%|███████▊  | 22004/28080 [43:28:45<11:56:20,  7.07s/it]
                                                           
{'loss': 0.5829, 'learning_rate': 5.892207110852871e-05, 'epoch': 9.4}

 78%|███████▊  | 22004/28080 [43:28:45<11:56:20,  7.07s/it]
 78%|███████▊  | 22005/28080 [43:28:52<11:57:58,  7.09s/it]
                                                           
{'loss': 0.5842, 'learning_rate': 5.8903477761346965e-05, 'epoch': 9.4}

 78%|███████▊  | 22005/28080 [43:28:52<11:57:58,  7.09s/it]
 78%|███████▊  | 22006/28080 [43:28:59<11:59:16,  7.11s/it]
                                                           
{'loss': 0.5873, 'learning_rate': 5.888488695650732e-05, 'epoch': 9.4}

 78%|███████▊  | 22006/28080 [43:28:59<11:59:16,  7.11s/it]
 78%|███████▊  | 22007/28080 [43:29:06<11:58:50,  7.10s/it]
                                                           
{'loss': 0.6001, 'learning_rate': 5.886629869425708e-05, 'epoch': 9.4}

 78%|███████▊  | 22007/28080 [43:29:06<11:58:50,  7.10s/it]
 78%|███████▊  | 22008/28080 [43:29:14<11:57:51,  7.09s/it]
                                                           
{'loss': 0.6204, 'learning_rate': 5.884771297484348e-05, 'epoch': 9.4}

 78%|███████▊  | 22008/28080 [43:29:14<11:57:51,  7.09s/it]
 78%|███████▊  | 22009/28080 [43:29:21<11:54:49,  7.06s/it]
                                                           
{'loss': 0.6209, 'learning_rate': 5.882912979851393e-05, 'epoch': 9.4}

 78%|███████▊  | 22009/28080 [43:29:21<11:54:49,  7.06s/it]
 78%|███████▊  | 22010/28080 [43:29:28<11:56:52,  7.09s/it]
                                                           
{'loss': 0.5793, 'learning_rate': 5.8810549165515506e-05, 'epoch': 9.4}

 78%|███████▊  | 22010/28080 [43:29:28<11:56:52,  7.09s/it]
 78%|███████▊  | 22011/28080 [43:29:35<11:58:08,  7.10s/it]
                                                           
{'loss': 0.5999, 'learning_rate': 5.8791971076095654e-05, 'epoch': 9.4}

 78%|███████▊  | 22011/28080 [43:29:35<11:58:08,  7.10s/it]
 78%|███████▊  | 22012/28080 [43:29:42<11:59:09,  7.11s/it]
                                                           
{'loss': 0.6136, 'learning_rate': 5.877339553050121e-05, 'epoch': 9.4}

 78%|███████▊  | 22012/28080 [43:29:42<11:59:09,  7.11s/it]
 78%|███████▊  | 22013/28080 [43:29:49<12:02:01,  7.14s/it]
                                                           
{'loss': 0.6057, 'learning_rate': 5.875482252897954e-05, 'epoch': 9.4}

 78%|███████▊  | 22013/28080 [43:29:49<12:02:01,  7.14s/it]
 78%|███████▊  | 22014/28080 [43:29:56<11:59:02,  7.11s/it]
                                                           
{'loss': 0.6227, 'learning_rate': 5.873625207177766e-05, 'epoch': 9.4}

 78%|███████▊  | 22014/28080 [43:29:56<11:59:02,  7.11s/it]
 78%|███████▊  | 22015/28080 [43:30:03<11:58:33,  7.11s/it]
                                                           
{'loss': 0.6064, 'learning_rate': 5.8717684159142554e-05, 'epoch': 9.4}

 78%|███████▊  | 22015/28080 [43:30:03<11:58:33,  7.11s/it]
 78%|███████▊  | 22016/28080 [43:30:10<11:54:25,  7.07s/it]
                                                           
{'loss': 0.6305, 'learning_rate': 5.869911879132145e-05, 'epoch': 9.41}

 78%|███████▊  | 22016/28080 [43:30:10<11:54:25,  7.07s/it]
 78%|███████▊  | 22017/28080 [43:30:18<12:00:13,  7.13s/it]
                                                           
{'loss': 0.5857, 'learning_rate': 5.8680555968561086e-05, 'epoch': 9.41}

 78%|███████▊  | 22017/28080 [43:30:18<12:00:13,  7.13s/it]
 78%|███████▊  | 22018/28080 [43:30:25<11:57:29,  7.10s/it]
                                                           
{'loss': 0.6025, 'learning_rate': 5.866199569110864e-05, 'epoch': 9.41}

 78%|███████▊  | 22018/28080 [43:30:25<11:57:29,  7.10s/it]
 78%|███████▊  | 22019/28080 [43:30:32<11:53:56,  7.07s/it]
                                                           
{'loss': 0.622, 'learning_rate': 5.864343795921087e-05, 'epoch': 9.41}

 78%|███████▊  | 22019/28080 [43:30:32<11:53:56,  7.07s/it]
 78%|███████▊  | 22020/28080 [43:30:39<11:55:34,  7.08s/it]
                                                           
{'loss': 0.5955, 'learning_rate': 5.8624882773114814e-05, 'epoch': 9.41}

 78%|███████▊  | 22020/28080 [43:30:39<11:55:34,  7.08s/it]
 78%|███████▊  | 22021/28080 [43:30:46<11:58:45,  7.12s/it]
                                                           
{'loss': 0.6039, 'learning_rate': 5.860633013306727e-05, 'epoch': 9.41}

 78%|███████▊  | 22021/28080 [43:30:46<11:58:45,  7.12s/it]
 78%|███████▊  | 22022/28080 [43:30:53<11:54:21,  7.08s/it]
                                                           
{'loss': 0.6163, 'learning_rate': 5.858778003931503e-05, 'epoch': 9.41}

 78%|███████▊  | 22022/28080 [43:30:53<11:54:21,  7.08s/it]
 78%|███████▊  | 22023/28080 [43:31:00<11:51:04,  7.04s/it]
                                                           
{'loss': 0.5901, 'learning_rate': 5.8569232492104854e-05, 'epoch': 9.41}

 78%|███████▊  | 22023/28080 [43:31:00<11:51:04,  7.04s/it]
 78%|███████▊  | 22024/28080 [43:31:07<11:54:52,  7.08s/it]
                                                           
{'loss': 0.591, 'learning_rate': 5.855068749168363e-05, 'epoch': 9.41}

 78%|███████▊  | 22024/28080 [43:31:07<11:54:52,  7.08s/it]
 78%|███████▊  | 22025/28080 [43:31:14<11:57:25,  7.11s/it]
                                                           
{'loss': 0.61, 'learning_rate': 5.853214503829798e-05, 'epoch': 9.41}

 78%|███████▊  | 22025/28080 [43:31:14<11:57:25,  7.11s/it]
 78%|███████▊  | 22026/28080 [43:31:21<11:56:54,  7.11s/it]
                                                           
{'loss': 0.6023, 'learning_rate': 5.851360513219461e-05, 'epoch': 9.41}

 78%|███████▊  | 22026/28080 [43:31:21<11:56:54,  7.11s/it]
 78%|███████▊  | 22027/28080 [43:31:28<11:57:45,  7.11s/it]
                                                           
{'loss': 0.6009, 'learning_rate': 5.8495067773620125e-05, 'epoch': 9.41}

 78%|███████▊  | 22027/28080 [43:31:28<11:57:45,  7.11s/it]
 78%|███████▊  | 22028/28080 [43:31:35<11:57:29,  7.11s/it]
                                                           
{'loss': 0.6039, 'learning_rate': 5.847653296282127e-05, 'epoch': 9.41}

 78%|███████▊  | 22028/28080 [43:31:36<11:57:29,  7.11s/it]
 78%|███████▊  | 22029/28080 [43:31:43<11:57:39,  7.12s/it]
                                                           
{'loss': 0.6066, 'learning_rate': 5.84580007000445e-05, 'epoch': 9.41}

 78%|███████▊  | 22029/28080 [43:31:43<11:57:39,  7.12s/it]
 78%|███████▊  | 22030/28080 [43:31:50<11:58:38,  7.13s/it]
                                                           
{'loss': 0.602, 'learning_rate': 5.843947098553656e-05, 'epoch': 9.41}

 78%|███████▊  | 22030/28080 [43:31:50<11:58:38,  7.13s/it]
 78%|███████▊  | 22031/28080 [43:31:57<11:55:21,  7.10s/it]
                                                           
{'loss': 0.5977, 'learning_rate': 5.8420943819543685e-05, 'epoch': 9.41}

 78%|███████▊  | 22031/28080 [43:31:57<11:55:21,  7.10s/it]
 78%|███████▊  | 22032/28080 [43:32:04<11:55:34,  7.10s/it]
                                                           
{'loss': 0.6107, 'learning_rate': 5.840241920231259e-05, 'epoch': 9.41}

 78%|███████▊  | 22032/28080 [43:32:04<11:55:34,  7.10s/it]
 78%|███████▊  | 22033/28080 [43:32:11<11:56:48,  7.11s/it]
                                                           
{'loss': 0.6036, 'learning_rate': 5.8383897134089565e-05, 'epoch': 9.41}

 78%|███████▊  | 22033/28080 [43:32:11<11:56:48,  7.11s/it]
 78%|███████▊  | 22034/28080 [43:32:18<11:55:40,  7.10s/it]
                                                           
{'loss': 0.5921, 'learning_rate': 5.83653776151212e-05, 'epoch': 9.41}

 78%|███████▊  | 22034/28080 [43:32:18<11:55:40,  7.10s/it]
 78%|███████▊  | 22035/28080 [43:32:25<11:54:45,  7.09s/it]
                                                           
{'loss': 0.5899, 'learning_rate': 5.8346860645653784e-05, 'epoch': 9.41}

 78%|███████▊  | 22035/28080 [43:32:25<11:54:45,  7.09s/it]
 78%|███████▊  | 22036/28080 [43:32:32<11:55:22,  7.10s/it]
                                                           
{'loss': 0.6134, 'learning_rate': 5.832834622593364e-05, 'epoch': 9.41}

 78%|███████▊  | 22036/28080 [43:32:32<11:55:22,  7.10s/it]
 78%|███████▊  | 22037/28080 [43:32:39<11:53:53,  7.09s/it]
                                                           
{'loss': 0.606, 'learning_rate': 5.830983435620707e-05, 'epoch': 9.41}

 78%|███████▊  | 22037/28080 [43:32:39<11:53:53,  7.09s/it]
 78%|███████▊  | 22038/28080 [43:32:46<11:54:12,  7.09s/it]
                                                           
{'loss': 0.6005, 'learning_rate': 5.829132503672047e-05, 'epoch': 9.41}

 78%|███████▊  | 22038/28080 [43:32:46<11:54:12,  7.09s/it]
 78%|███████▊  | 22039/28080 [43:32:54<11:52:04,  7.07s/it]
                                                           
{'loss': 0.6128, 'learning_rate': 5.827281826772002e-05, 'epoch': 9.41}

 78%|███████▊  | 22039/28080 [43:32:54<11:52:04,  7.07s/it]
 78%|███████▊  | 22040/28080 [43:33:01<11:53:05,  7.08s/it]
                                                           
{'loss': 0.587, 'learning_rate': 5.825431404945192e-05, 'epoch': 9.42}

 78%|███████▊  | 22040/28080 [43:33:01<11:53:05,  7.08s/it]
 78%|███████▊  | 22041/28080 [43:33:08<11:55:58,  7.11s/it]
                                                           
{'loss': 0.6078, 'learning_rate': 5.8235812382162355e-05, 'epoch': 9.42}

 78%|███████▊  | 22041/28080 [43:33:08<11:55:58,  7.11s/it]
 78%|███████▊  | 22042/28080 [43:33:15<11:55:06,  7.11s/it]
                                                           
{'loss': 0.6146, 'learning_rate': 5.821731326609739e-05, 'epoch': 9.42}

 78%|███████▊  | 22042/28080 [43:33:15<11:55:06,  7.11s/it]
 79%|███████▊  | 22043/28080 [43:33:22<11:53:02,  7.09s/it]
                                                           
{'loss': 0.6332, 'learning_rate': 5.8198816701503315e-05, 'epoch': 9.42}

 79%|███████▊  | 22043/28080 [43:33:22<11:53:02,  7.09s/it]
 79%|███████▊  | 22044/28080 [43:33:29<11:56:29,  7.12s/it]
                                                           
{'loss': 0.5997, 'learning_rate': 5.818032268862611e-05, 'epoch': 9.42}

 79%|███████▊  | 22044/28080 [43:33:29<11:56:29,  7.12s/it]
 79%|███████▊  | 22045/28080 [43:33:36<11:57:29,  7.13s/it]
                                                           
{'loss': 0.587, 'learning_rate': 5.816183122771182e-05, 'epoch': 9.42}

 79%|███████▊  | 22045/28080 [43:33:36<11:57:29,  7.13s/it]
 79%|███████▊  | 22046/28080 [43:33:43<11:56:24,  7.12s/it]
                                                           
{'loss': 0.6098, 'learning_rate': 5.814334231900637e-05, 'epoch': 9.42}

 79%|███████▊  | 22046/28080 [43:33:43<11:56:24,  7.12s/it]
 79%|███████▊  | 22047/28080 [43:33:51<11:57:00,  7.13s/it]
                                                           
{'loss': 0.6107, 'learning_rate': 5.812485596275591e-05, 'epoch': 9.42}

 79%|███████▊  | 22047/28080 [43:33:51<11:57:00,  7.13s/it]
 79%|███████▊  | 22048/28080 [43:33:58<11:53:32,  7.10s/it]
                                                           
{'loss': 0.6073, 'learning_rate': 5.810637215920622e-05, 'epoch': 9.42}

 79%|███████▊  | 22048/28080 [43:33:58<11:53:32,  7.10s/it]
 79%|███████▊  | 22049/28080 [43:34:05<11:53:48,  7.10s/it]
                                                           
{'loss': 0.6225, 'learning_rate': 5.808789090860336e-05, 'epoch': 9.42}

 79%|███████▊  | 22049/28080 [43:34:05<11:53:48,  7.10s/it]
 79%|███████▊  | 22050/28080 [43:34:12<11:54:01,  7.10s/it]
                                                           
{'loss': 0.6082, 'learning_rate': 5.8069412211193106e-05, 'epoch': 9.42}

 79%|███████▊  | 22050/28080 [43:34:12<11:54:01,  7.10s/it]
 79%|███████▊  | 22051/28080 [43:34:19<11:51:57,  7.09s/it]
                                                           
{'loss': 0.6032, 'learning_rate': 5.8050936067221336e-05, 'epoch': 9.42}

 79%|███████▊  | 22051/28080 [43:34:19<11:51:57,  7.09s/it]
 79%|███████▊  | 22052/28080 [43:34:26<11:51:06,  7.08s/it]
                                                           
{'loss': 0.5855, 'learning_rate': 5.803246247693378e-05, 'epoch': 9.42}

 79%|███████▊  | 22052/28080 [43:34:26<11:51:06,  7.08s/it]
 79%|███████▊  | 22053/28080 [43:34:33<11:51:03,  7.08s/it]
                                                           
{'loss': 0.5996, 'learning_rate': 5.801399144057631e-05, 'epoch': 9.42}

 79%|███████▊  | 22053/28080 [43:34:33<11:51:03,  7.08s/it]
 79%|███████▊  | 22054/28080 [43:34:40<11:52:52,  7.10s/it]
                                                           
{'loss': 0.6107, 'learning_rate': 5.7995522958394636e-05, 'epoch': 9.42}

 79%|███████▊  | 22054/28080 [43:34:40<11:52:52,  7.10s/it]
 79%|███████▊  | 22055/28080 [43:34:47<11:52:39,  7.10s/it]
                                                           
{'loss': 0.5895, 'learning_rate': 5.7977057030634464e-05, 'epoch': 9.42}

 79%|███████▊  | 22055/28080 [43:34:47<11:52:39,  7.10s/it]
 79%|███████▊  | 22056/28080 [43:34:54<11:53:35,  7.11s/it]
                                                           
{'loss': 0.6084, 'learning_rate': 5.7958593657541355e-05, 'epoch': 9.42}

 79%|███████▊  | 22056/28080 [43:34:54<11:53:35,  7.11s/it]
 79%|███████▊  | 22057/28080 [43:35:01<11:52:30,  7.10s/it]
                                                           
{'loss': 0.5958, 'learning_rate': 5.7940132839361145e-05, 'epoch': 9.42}

 79%|███████▊  | 22057/28080 [43:35:01<11:52:30,  7.10s/it]
 79%|███████▊  | 22058/28080 [43:35:09<11:53:36,  7.11s/it]
                                                           
{'loss': 0.6037, 'learning_rate': 5.7921674576339236e-05, 'epoch': 9.42}

 79%|███████▊  | 22058/28080 [43:35:09<11:53:36,  7.11s/it]
 79%|███████▊  | 22059/28080 [43:35:16<11:51:14,  7.09s/it]
                                                           
{'loss': 0.5864, 'learning_rate': 5.790321886872144e-05, 'epoch': 9.42}

 79%|███████▊  | 22059/28080 [43:35:16<11:51:14,  7.09s/it]
 79%|███████▊  | 22060/28080 [43:35:23<11:51:44,  7.09s/it]
                                                           
{'loss': 0.6242, 'learning_rate': 5.788476571675297e-05, 'epoch': 9.42}

 79%|███████▊  | 22060/28080 [43:35:23<11:51:44,  7.09s/it]
 79%|███████▊  | 22061/28080 [43:35:30<11:52:26,  7.10s/it]
                                                           
{'loss': 0.5949, 'learning_rate': 5.786631512067961e-05, 'epoch': 9.42}

 79%|███████▊  | 22061/28080 [43:35:30<11:52:26,  7.10s/it]
 79%|███████▊  | 22062/28080 [43:35:37<11:50:21,  7.08s/it]
                                                           
{'loss': 0.604, 'learning_rate': 5.78478670807466e-05, 'epoch': 9.42}

 79%|███████▊  | 22062/28080 [43:35:37<11:50:21,  7.08s/it]
 79%|███████▊  | 22063/28080 [43:35:44<11:52:00,  7.10s/it]
                                                           
{'loss': 0.6081, 'learning_rate': 5.7829421597199586e-05, 'epoch': 9.43}

 79%|███████▊  | 22063/28080 [43:35:44<11:52:00,  7.10s/it]
 79%|███████▊  | 22064/28080 [43:35:51<11:48:59,  7.07s/it]
                                                           
{'loss': 0.5878, 'learning_rate': 5.781097867028392e-05, 'epoch': 9.43}

 79%|███████▊  | 22064/28080 [43:35:51<11:48:59,  7.07s/it]
 79%|███████▊  | 22065/28080 [43:35:58<11:50:50,  7.09s/it]
                                                           
{'loss': 0.5917, 'learning_rate': 5.7792538300244804e-05, 'epoch': 9.43}

 79%|███████▊  | 22065/28080 [43:35:58<11:50:50,  7.09s/it]
 79%|███████▊  | 22066/28080 [43:36:05<11:51:16,  7.10s/it]
                                                           
{'loss': 0.6273, 'learning_rate': 5.777410048732773e-05, 'epoch': 9.43}

 79%|███████▊  | 22066/28080 [43:36:05<11:51:16,  7.10s/it]
 79%|███████▊  | 22067/28080 [43:36:12<11:50:17,  7.09s/it]
                                                           
{'loss': 0.602, 'learning_rate': 5.775566523177786e-05, 'epoch': 9.43}

 79%|███████▊  | 22067/28080 [43:36:12<11:50:17,  7.09s/it]
 79%|███████▊  | 22068/28080 [43:36:19<11:49:02,  7.08s/it]
                                                           
{'loss': 0.6126, 'learning_rate': 5.773723253384061e-05, 'epoch': 9.43}

 79%|███████▊  | 22068/28080 [43:36:19<11:49:02,  7.08s/it]
 79%|███████▊  | 22069/28080 [43:36:27<11:53:29,  7.12s/it]
                                                           
{'loss': 0.61, 'learning_rate': 5.771880239376115e-05, 'epoch': 9.43}

 79%|███████▊  | 22069/28080 [43:36:27<11:53:29,  7.12s/it]
 79%|███████▊  | 22070/28080 [43:36:34<11:55:25,  7.14s/it]
                                                           
{'loss': 0.6024, 'learning_rate': 5.7700374811784636e-05, 'epoch': 9.43}

 79%|███████▊  | 22070/28080 [43:36:34<11:55:25,  7.14s/it]
 79%|███████▊  | 22071/28080 [43:36:41<11:52:39,  7.12s/it]
                                                           
{'loss': 0.6307, 'learning_rate': 5.768194978815619e-05, 'epoch': 9.43}

 79%|███████▊  | 22071/28080 [43:36:41<11:52:39,  7.12s/it]
 79%|███████▊  | 22072/28080 [43:36:48<11:50:40,  7.10s/it]
                                                           
{'loss': 0.5983, 'learning_rate': 5.766352732312108e-05, 'epoch': 9.43}

 79%|███████▊  | 22072/28080 [43:36:48<11:50:40,  7.10s/it]
 79%|███████▊  | 22073/28080 [43:36:55<11:52:31,  7.12s/it]
                                                           
{'loss': 0.5907, 'learning_rate': 5.76451074169243e-05, 'epoch': 9.43}

 79%|███████▊  | 22073/28080 [43:36:55<11:52:31,  7.12s/it]
 79%|███████▊  | 22074/28080 [43:37:02<11:52:57,  7.12s/it]
                                                           
{'loss': 0.5847, 'learning_rate': 5.7626690069810945e-05, 'epoch': 9.43}

 79%|███████▊  | 22074/28080 [43:37:02<11:52:57,  7.12s/it]
 79%|███████▊  | 22075/28080 [43:37:09<11:49:05,  7.09s/it]
                                                           
{'loss': 0.6114, 'learning_rate': 5.7608275282025915e-05, 'epoch': 9.43}

 79%|███████▊  | 22075/28080 [43:37:09<11:49:05,  7.09s/it]
 79%|███████▊  | 22076/28080 [43:37:16<11:46:28,  7.06s/it]
                                                           
{'loss': 0.6145, 'learning_rate': 5.758986305381439e-05, 'epoch': 9.43}

 79%|███████▊  | 22076/28080 [43:37:16<11:46:28,  7.06s/it]
 79%|███████▊  | 22077/28080 [43:37:23<11:48:14,  7.08s/it]
                                                           
{'loss': 0.612, 'learning_rate': 5.757145338542116e-05, 'epoch': 9.43}

 79%|███████▊  | 22077/28080 [43:37:23<11:48:14,  7.08s/it]
 79%|███████▊  | 22078/28080 [43:37:30<11:49:32,  7.09s/it]
                                                           
{'loss': 0.5724, 'learning_rate': 5.75530462770914e-05, 'epoch': 9.43}

 79%|███████▊  | 22078/28080 [43:37:30<11:49:32,  7.09s/it]
 79%|███████▊  | 22079/28080 [43:37:37<11:46:21,  7.06s/it]
                                                           
{'loss': 0.6092, 'learning_rate': 5.753464172906964e-05, 'epoch': 9.43}

 79%|███████▊  | 22079/28080 [43:37:37<11:46:21,  7.06s/it]
 79%|███████▊  | 22080/28080 [43:37:45<11:48:08,  7.08s/it]
                                                           
{'loss': 0.628, 'learning_rate': 5.751623974160103e-05, 'epoch': 9.43}

 79%|███████▊  | 22080/28080 [43:37:45<11:48:08,  7.08s/it]
 79%|███████▊  | 22081/28080 [43:37:52<11:48:03,  7.08s/it]
                                                           
{'loss': 0.6102, 'learning_rate': 5.749784031493016e-05, 'epoch': 9.43}

 79%|███████▊  | 22081/28080 [43:37:52<11:48:03,  7.08s/it]
 79%|███████▊  | 22082/28080 [43:37:59<11:49:07,  7.09s/it]
                                                           
{'loss': 0.6004, 'learning_rate': 5.7479443449302035e-05, 'epoch': 9.43}

 79%|███████▊  | 22082/28080 [43:37:59<11:49:07,  7.09s/it]
 79%|███████▊  | 22083/28080 [43:38:06<11:51:05,  7.11s/it]
                                                           
{'loss': 0.6029, 'learning_rate': 5.746104914496128e-05, 'epoch': 9.43}

 79%|███████▊  | 22083/28080 [43:38:06<11:51:05,  7.11s/it]
 79%|███████▊  | 22084/28080 [43:38:13<11:51:15,  7.12s/it]
                                                           
{'loss': 0.6109, 'learning_rate': 5.7442657402152657e-05, 'epoch': 9.43}

 79%|███████▊  | 22084/28080 [43:38:13<11:51:15,  7.12s/it]
 79%|███████▊  | 22085/28080 [43:38:20<11:48:48,  7.09s/it]
                                                           
{'loss': 0.6196, 'learning_rate': 5.7424268221120733e-05, 'epoch': 9.43}

 79%|███████▊  | 22085/28080 [43:38:20<11:48:48,  7.09s/it]
 79%|███████▊  | 22086/28080 [43:38:27<11:51:43,  7.12s/it]
                                                           
{'loss': 0.6155, 'learning_rate': 5.740588160211033e-05, 'epoch': 9.43}

 79%|███████▊  | 22086/28080 [43:38:27<11:51:43,  7.12s/it]
 79%|███████▊  | 22087/28080 [43:38:34<11:52:15,  7.13s/it]
                                                           
{'loss': 0.6003, 'learning_rate': 5.738749754536598e-05, 'epoch': 9.44}

 79%|███████▊  | 22087/28080 [43:38:34<11:52:15,  7.13s/it]
 79%|███████▊  | 22088/28080 [43:38:42<11:54:45,  7.16s/it]
                                                           
{'loss': 0.5943, 'learning_rate': 5.736911605113229e-05, 'epoch': 9.44}

 79%|███████▊  | 22088/28080 [43:38:42<11:54:45,  7.16s/it]
 79%|███████▊  | 22089/28080 [43:38:49<11:53:22,  7.14s/it]
                                                           
{'loss': 0.6074, 'learning_rate': 5.7350737119653745e-05, 'epoch': 9.44}

 79%|███████▊  | 22089/28080 [43:38:49<11:53:22,  7.14s/it]
 79%|███████▊  | 22090/28080 [43:38:56<11:52:08,  7.13s/it]
                                                           
{'loss': 0.6112, 'learning_rate': 5.733236075117487e-05, 'epoch': 9.44}

 79%|███████▊  | 22090/28080 [43:38:56<11:52:08,  7.13s/it]
 79%|███████▊  | 22091/28080 [43:39:03<11:51:24,  7.13s/it]
                                                           
{'loss': 0.5793, 'learning_rate': 5.731398694594023e-05, 'epoch': 9.44}

 79%|███████▊  | 22091/28080 [43:39:03<11:51:24,  7.13s/it]
 79%|███████▊  | 22092/28080 [43:39:10<11:48:05,  7.10s/it]
                                                           
{'loss': 0.5895, 'learning_rate': 5.72956157041942e-05, 'epoch': 9.44}

 79%|███████▊  | 22092/28080 [43:39:10<11:48:05,  7.10s/it]
 79%|███████▊  | 22093/28080 [43:39:17<11:48:49,  7.10s/it]
                                                           
{'loss': 0.5975, 'learning_rate': 5.72772470261812e-05, 'epoch': 9.44}

 79%|███████▊  | 22093/28080 [43:39:17<11:48:49,  7.10s/it]
 79%|███████▊  | 22094/28080 [43:39:24<11:45:52,  7.08s/it]
                                                           
{'loss': 0.6037, 'learning_rate': 5.7258880912145536e-05, 'epoch': 9.44}

 79%|███████▊  | 22094/28080 [43:39:24<11:45:52,  7.08s/it]
 79%|███████▊  | 22095/28080 [43:39:31<11:46:54,  7.09s/it]
                                                           
{'loss': 0.6139, 'learning_rate': 5.724051736233169e-05, 'epoch': 9.44}

 79%|███████▊  | 22095/28080 [43:39:31<11:46:54,  7.09s/it]
 79%|███████▊  | 22096/28080 [43:39:38<11:48:07,  7.10s/it]
                                                           
{'loss': 0.6019, 'learning_rate': 5.722215637698383e-05, 'epoch': 9.44}

 79%|███████▊  | 22096/28080 [43:39:38<11:48:07,  7.10s/it]
 79%|███████▊  | 22097/28080 [43:39:45<11:47:00,  7.09s/it]
                                                           
{'loss': 0.6048, 'learning_rate': 5.720379795634639e-05, 'epoch': 9.44}

 79%|███████▊  | 22097/28080 [43:39:45<11:47:00,  7.09s/it]
 79%|███████▊  | 22098/28080 [43:39:53<11:48:30,  7.11s/it]
                                                           
{'loss': 0.5934, 'learning_rate': 5.718544210066351e-05, 'epoch': 9.44}

 79%|███████▊  | 22098/28080 [43:39:53<11:48:30,  7.11s/it]
 79%|███████▊  | 22099/28080 [43:40:00<11:48:36,  7.11s/it]
                                                           
{'loss': 0.597, 'learning_rate': 5.71670888101794e-05, 'epoch': 9.44}

 79%|███████▊  | 22099/28080 [43:40:00<11:48:36,  7.11s/it]
 79%|███████▊  | 22100/28080 [43:40:07<11:45:33,  7.08s/it]
                                                           
{'loss': 0.5816, 'learning_rate': 5.714873808513818e-05, 'epoch': 9.44}

 79%|███████▊  | 22100/28080 [43:40:07<11:45:33,  7.08s/it]
 79%|███████▊  | 22101/28080 [43:40:14<11:45:49,  7.08s/it]
                                                           
{'loss': 0.6014, 'learning_rate': 5.713038992578412e-05, 'epoch': 9.44}

 79%|███████▊  | 22101/28080 [43:40:14<11:45:49,  7.08s/it]
 79%|███████▊  | 22102/28080 [43:40:21<11:45:56,  7.09s/it]
                                                           
{'loss': 0.5903, 'learning_rate': 5.711204433236125e-05, 'epoch': 9.44}

 79%|███████▊  | 22102/28080 [43:40:21<11:45:56,  7.09s/it]
 79%|███████▊  | 22103/28080 [43:40:28<11:48:03,  7.11s/it]
                                                           
{'loss': 0.6169, 'learning_rate': 5.709370130511363e-05, 'epoch': 9.44}

 79%|███████▊  | 22103/28080 [43:40:28<11:48:03,  7.11s/it]
 79%|███████▊  | 22104/28080 [43:40:35<11:47:13,  7.10s/it]
                                                           
{'loss': 0.5872, 'learning_rate': 5.7075360844285216e-05, 'epoch': 9.44}

 79%|███████▊  | 22104/28080 [43:40:35<11:47:13,  7.10s/it]
 79%|███████▊  | 22105/28080 [43:40:42<11:47:35,  7.11s/it]
                                                           
{'loss': 0.6125, 'learning_rate': 5.705702295012019e-05, 'epoch': 9.44}

 79%|███████▊  | 22105/28080 [43:40:42<11:47:35,  7.11s/it]
 79%|███████▊  | 22106/28080 [43:40:49<11:48:06,  7.11s/it]
                                                           
{'loss': 0.623, 'learning_rate': 5.7038687622862436e-05, 'epoch': 9.44}

 79%|███████▊  | 22106/28080 [43:40:49<11:48:06,  7.11s/it]
 79%|███████▊  | 22107/28080 [43:40:56<11:47:28,  7.11s/it]
                                                           
{'loss': 0.5831, 'learning_rate': 5.702035486275584e-05, 'epoch': 9.44}

 79%|███████▊  | 22107/28080 [43:40:56<11:47:28,  7.11s/it]
 79%|███████▊  | 22108/28080 [43:41:04<11:48:26,  7.12s/it]
                                                           
{'loss': 0.5932, 'learning_rate': 5.700202467004428e-05, 'epoch': 9.44}

 79%|███████▊  | 22108/28080 [43:41:04<11:48:26,  7.12s/it]
 79%|███████▊  | 22109/28080 [43:41:11<11:46:17,  7.10s/it]
                                                           
{'loss': 0.6073, 'learning_rate': 5.698369704497178e-05, 'epoch': 9.44}

 79%|███████▊  | 22109/28080 [43:41:11<11:46:17,  7.10s/it]
 79%|███████▊  | 22110/28080 [43:41:18<11:46:39,  7.10s/it]
                                                           
{'loss': 0.6098, 'learning_rate': 5.6965371987781955e-05, 'epoch': 9.45}

 79%|███████▊  | 22110/28080 [43:41:18<11:46:39,  7.10s/it]
 79%|███████▊  | 22111/28080 [43:41:25<11:44:08,  7.08s/it]
                                                           
{'loss': 0.5981, 'learning_rate': 5.694704949871882e-05, 'epoch': 9.45}

 79%|███████▊  | 22111/28080 [43:41:25<11:44:08,  7.08s/it]
 79%|███████▊  | 22112/28080 [43:41:32<11:44:19,  7.08s/it]
                                                           
{'loss': 0.612, 'learning_rate': 5.6928729578026e-05, 'epoch': 9.45}

 79%|███████▊  | 22112/28080 [43:41:32<11:44:19,  7.08s/it]
 79%|███████▉  | 22113/28080 [43:41:39<11:41:25,  7.05s/it]
                                                           
{'loss': 0.5999, 'learning_rate': 5.6910412225947254e-05, 'epoch': 9.45}

 79%|███████▉  | 22113/28080 [43:41:39<11:41:25,  7.05s/it]
 79%|███████▉  | 22114/28080 [43:41:46<11:43:45,  7.08s/it]
                                                           
{'loss': 0.5994, 'learning_rate': 5.6892097442726275e-05, 'epoch': 9.45}

 79%|███████▉  | 22114/28080 [43:41:46<11:43:45,  7.08s/it]
 79%|███████▉  | 22115/28080 [43:41:53<11:40:14,  7.04s/it]
                                                           
{'loss': 0.6152, 'learning_rate': 5.6873785228606674e-05, 'epoch': 9.45}

 79%|███████▉  | 22115/28080 [43:41:53<11:40:14,  7.04s/it]
 79%|███████▉  | 22116/28080 [43:42:00<11:41:45,  7.06s/it]
                                                           
{'loss': 0.6062, 'learning_rate': 5.6855475583832166e-05, 'epoch': 9.45}

 79%|███████▉  | 22116/28080 [43:42:00<11:41:45,  7.06s/it]
 79%|███████▉  | 22117/28080 [43:42:07<11:43:59,  7.08s/it]
                                                           
{'loss': 0.6025, 'learning_rate': 5.683716850864631e-05, 'epoch': 9.45}

 79%|███████▉  | 22117/28080 [43:42:07<11:43:59,  7.08s/it]
 79%|███████▉  | 22118/28080 [43:42:14<11:46:31,  7.11s/it]
                                                           
{'loss': 0.6109, 'learning_rate': 5.681886400329264e-05, 'epoch': 9.45}

 79%|███████▉  | 22118/28080 [43:42:14<11:46:31,  7.11s/it]
 79%|███████▉  | 22119/28080 [43:42:22<11:47:31,  7.12s/it]
                                                           
{'loss': 0.6085, 'learning_rate': 5.680056206801465e-05, 'epoch': 9.45}

 79%|███████▉  | 22119/28080 [43:42:22<11:47:31,  7.12s/it]
 79%|███████▉  | 22120/28080 [43:42:29<11:45:42,  7.10s/it]
                                                           
{'loss': 0.6225, 'learning_rate': 5.678226270305592e-05, 'epoch': 9.45}

 79%|███████▉  | 22120/28080 [43:42:29<11:45:42,  7.10s/it]
 79%|███████▉  | 22121/28080 [43:42:36<11:45:19,  7.10s/it]
                                                           
{'loss': 0.612, 'learning_rate': 5.6763965908659844e-05, 'epoch': 9.45}

 79%|███████▉  | 22121/28080 [43:42:36<11:45:19,  7.10s/it]
 79%|███████▉  | 22122/28080 [43:42:43<11:46:56,  7.12s/it]
                                                           
{'loss': 0.6082, 'learning_rate': 5.674567168506986e-05, 'epoch': 9.45}

 79%|███████▉  | 22122/28080 [43:42:43<11:46:56,  7.12s/it]
 79%|███████▉  | 22123/28080 [43:42:50<11:46:45,  7.12s/it]
                                                           
{'loss': 0.6039, 'learning_rate': 5.672738003252928e-05, 'epoch': 9.45}

 79%|███████▉  | 22123/28080 [43:42:50<11:46:45,  7.12s/it]
 79%|███████▉  | 22124/28080 [43:42:57<11:46:51,  7.12s/it]
                                                           
{'loss': 0.6109, 'learning_rate': 5.67090909512816e-05, 'epoch': 9.45}

 79%|███████▉  | 22124/28080 [43:42:57<11:46:51,  7.12s/it]
 79%|███████▉  | 22125/28080 [43:43:04<11:42:40,  7.08s/it]
                                                           
{'loss': 0.6308, 'learning_rate': 5.669080444156996e-05, 'epoch': 9.45}

 79%|███████▉  | 22125/28080 [43:43:04<11:42:40,  7.08s/it]
 79%|███████▉  | 22126/28080 [43:43:11<11:45:46,  7.11s/it]
                                                           
{'loss': 0.5902, 'learning_rate': 5.6672520503637914e-05, 'epoch': 9.45}

 79%|███████▉  | 22126/28080 [43:43:11<11:45:46,  7.11s/it]
 79%|███████▉  | 22127/28080 [43:43:18<11:41:20,  7.07s/it]
                                                           
{'loss': 0.6028, 'learning_rate': 5.665423913772838e-05, 'epoch': 9.45}

 79%|███████▉  | 22127/28080 [43:43:18<11:41:20,  7.07s/it]
 79%|███████▉  | 22128/28080 [43:43:25<11:38:49,  7.04s/it]
                                                           
{'loss': 0.601, 'learning_rate': 5.6635960344084775e-05, 'epoch': 9.45}

 79%|███████▉  | 22128/28080 [43:43:25<11:38:49,  7.04s/it]
 79%|███████▉  | 22129/28080 [43:43:32<11:42:01,  7.08s/it]
                                                           
{'loss': 0.604, 'learning_rate': 5.661768412295021e-05, 'epoch': 9.45}

 79%|███████▉  | 22129/28080 [43:43:32<11:42:01,  7.08s/it]
 79%|███████▉  | 22130/28080 [43:43:39<11:38:59,  7.05s/it]
                                                           
{'loss': 0.5915, 'learning_rate': 5.65994104745679e-05, 'epoch': 9.45}

 79%|███████▉  | 22130/28080 [43:43:39<11:38:59,  7.05s/it]
 79%|███████▉  | 22131/28080 [43:43:46<11:36:54,  7.03s/it]
                                                           
{'loss': 0.6343, 'learning_rate': 5.658113939918091e-05, 'epoch': 9.45}

 79%|███████▉  | 22131/28080 [43:43:46<11:36:54,  7.03s/it]
 79%|███████▉  | 22132/28080 [43:43:53<11:40:07,  7.06s/it]
                                                           
{'loss': 0.5941, 'learning_rate': 5.6562870897032324e-05, 'epoch': 9.45}

 79%|███████▉  | 22132/28080 [43:43:53<11:40:07,  7.06s/it]
 79%|███████▉  | 22133/28080 [43:44:01<11:41:25,  7.08s/it]
                                                           
{'loss': 0.5931, 'learning_rate': 5.6544604968365136e-05, 'epoch': 9.46}

 79%|███████▉  | 22133/28080 [43:44:01<11:41:25,  7.08s/it]
 79%|███████▉  | 22134/28080 [43:44:08<11:40:37,  7.07s/it]
                                                           
{'loss': 0.6156, 'learning_rate': 5.652634161342246e-05, 'epoch': 9.46}

 79%|███████▉  | 22134/28080 [43:44:08<11:40:37,  7.07s/it]
 79%|███████▉  | 22135/28080 [43:44:15<11:40:40,  7.07s/it]
                                                           
{'loss': 0.5945, 'learning_rate': 5.650808083244721e-05, 'epoch': 9.46}

 79%|███████▉  | 22135/28080 [43:44:15<11:40:40,  7.07s/it]
 79%|███████▉  | 22136/28080 [43:44:22<11:39:05,  7.06s/it]
                                                           
{'loss': 0.5888, 'learning_rate': 5.648982262568231e-05, 'epoch': 9.46}

 79%|███████▉  | 22136/28080 [43:44:22<11:39:05,  7.06s/it]
 79%|███████▉  | 22137/28080 [43:44:29<11:38:28,  7.05s/it]
                                                           
{'loss': 0.6002, 'learning_rate': 5.647156699337064e-05, 'epoch': 9.46}

 79%|███████▉  | 22137/28080 [43:44:29<11:38:28,  7.05s/it]
 79%|███████▉  | 22138/28080 [43:44:36<11:41:23,  7.08s/it]
                                                           
{'loss': 0.5931, 'learning_rate': 5.64533139357552e-05, 'epoch': 9.46}

 79%|███████▉  | 22138/28080 [43:44:36<11:41:23,  7.08s/it]
 79%|███████▉  | 22139/28080 [43:44:43<11:41:56,  7.09s/it]
                                                           
{'loss': 0.6175, 'learning_rate': 5.643506345307872e-05, 'epoch': 9.46}

 79%|███████▉  | 22139/28080 [43:44:43<11:41:56,  7.09s/it]
 79%|███████▉  | 22140/28080 [43:44:50<11:43:14,  7.10s/it]
                                                           
{'loss': 0.609, 'learning_rate': 5.641681554558403e-05, 'epoch': 9.46}

 79%|███████▉  | 22140/28080 [43:44:50<11:43:14,  7.10s/it]
 79%|███████▉  | 22141/28080 [43:44:57<11:43:55,  7.11s/it]
                                                           
{'loss': 0.5954, 'learning_rate': 5.639857021351391e-05, 'epoch': 9.46}

 79%|███████▉  | 22141/28080 [43:44:57<11:43:55,  7.11s/it]
 79%|███████▉  | 22142/28080 [43:45:04<11:44:25,  7.12s/it]
                                                           
{'loss': 0.5998, 'learning_rate': 5.638032745711103e-05, 'epoch': 9.46}

 79%|███████▉  | 22142/28080 [43:45:04<11:44:25,  7.12s/it]
 79%|███████▉  | 22143/28080 [43:45:11<11:41:55,  7.09s/it]
                                                           
{'loss': 0.6169, 'learning_rate': 5.6362087276618204e-05, 'epoch': 9.46}

 79%|███████▉  | 22143/28080 [43:45:11<11:41:55,  7.09s/it]
 79%|███████▉  | 22144/28080 [43:45:19<11:41:49,  7.09s/it]
                                                           
{'loss': 0.5978, 'learning_rate': 5.634384967227798e-05, 'epoch': 9.46}

 79%|███████▉  | 22144/28080 [43:45:19<11:41:49,  7.09s/it]
 79%|███████▉  | 22145/28080 [43:45:26<11:41:22,  7.09s/it]
                                                           
{'loss': 0.5908, 'learning_rate': 5.632561464433311e-05, 'epoch': 9.46}

 79%|███████▉  | 22145/28080 [43:45:26<11:41:22,  7.09s/it]
 79%|███████▉  | 22146/28080 [43:45:33<11:40:34,  7.08s/it]
                                                           
{'loss': 0.608, 'learning_rate': 5.6307382193026144e-05, 'epoch': 9.46}

 79%|███████▉  | 22146/28080 [43:45:33<11:40:34,  7.08s/it]
 79%|███████▉  | 22147/28080 [43:45:40<11:42:57,  7.11s/it]
                                                           
{'loss': 0.5978, 'learning_rate': 5.628915231859963e-05, 'epoch': 9.46}

 79%|███████▉  | 22147/28080 [43:45:40<11:42:57,  7.11s/it]
 79%|███████▉  | 22148/28080 [43:45:47<11:41:38,  7.10s/it]
                                                           
{'loss': 0.5731, 'learning_rate': 5.627092502129602e-05, 'epoch': 9.46}

 79%|███████▉  | 22148/28080 [43:45:47<11:41:38,  7.10s/it]
 79%|███████▉  | 22149/28080 [43:45:54<11:40:11,  7.08s/it]
                                                           
{'loss': 0.6191, 'learning_rate': 5.625270030135798e-05, 'epoch': 9.46}

 79%|███████▉  | 22149/28080 [43:45:54<11:40:11,  7.08s/it]
 79%|███████▉  | 22150/28080 [43:46:01<11:39:53,  7.08s/it]
                                                           
{'loss': 0.6196, 'learning_rate': 5.6234478159027906e-05, 'epoch': 9.46}

 79%|███████▉  | 22150/28080 [43:46:01<11:39:53,  7.08s/it]
 79%|███████▉  | 22151/28080 [43:46:08<11:39:11,  7.08s/it]
                                                           
{'loss': 0.5932, 'learning_rate': 5.621625859454818e-05, 'epoch': 9.46}

 79%|███████▉  | 22151/28080 [43:46:08<11:39:11,  7.08s/it]
 79%|███████▉  | 22152/28080 [43:46:15<11:37:29,  7.06s/it]
                                                           
{'loss': 0.5937, 'learning_rate': 5.619804160816114e-05, 'epoch': 9.46}

 79%|███████▉  | 22152/28080 [43:46:15<11:37:29,  7.06s/it]
 79%|███████▉  | 22153/28080 [43:46:22<11:37:04,  7.06s/it]
                                                           
{'loss': 0.585, 'learning_rate': 5.6179827200109305e-05, 'epoch': 9.46}

 79%|███████▉  | 22153/28080 [43:46:22<11:37:04,  7.06s/it]
 79%|███████▉  | 22154/28080 [43:46:29<11:40:28,  7.09s/it]
                                                           
{'loss': 0.6061, 'learning_rate': 5.616161537063491e-05, 'epoch': 9.46}

 79%|███████▉  | 22154/28080 [43:46:29<11:40:28,  7.09s/it]
 79%|███████▉  | 22155/28080 [43:46:36<11:39:16,  7.08s/it]
                                                           
{'loss': 0.6162, 'learning_rate': 5.614340611998026e-05, 'epoch': 9.46}

 79%|███████▉  | 22155/28080 [43:46:36<11:39:16,  7.08s/it]
 79%|███████▉  | 22156/28080 [43:46:44<11:39:25,  7.08s/it]
                                                           
{'loss': 0.594, 'learning_rate': 5.612519944838751e-05, 'epoch': 9.46}

 79%|███████▉  | 22156/28080 [43:46:44<11:39:25,  7.08s/it]
 79%|███████▉  | 22157/28080 [43:46:51<11:38:37,  7.08s/it]
                                                           
{'loss': 0.5989, 'learning_rate': 5.610699535609906e-05, 'epoch': 9.47}

 79%|███████▉  | 22157/28080 [43:46:51<11:38:37,  7.08s/it]
 79%|███████▉  | 22158/28080 [43:46:58<11:37:35,  7.07s/it]
                                                           
{'loss': 0.6076, 'learning_rate': 5.608879384335694e-05, 'epoch': 9.47}

 79%|███████▉  | 22158/28080 [43:46:58<11:37:35,  7.07s/it]
 79%|███████▉  | 22159/28080 [43:47:05<11:39:36,  7.09s/it]
                                                           
{'loss': 0.6106, 'learning_rate': 5.607059491040342e-05, 'epoch': 9.47}

 79%|███████▉  | 22159/28080 [43:47:05<11:39:36,  7.09s/it]
 79%|███████▉  | 22160/28080 [43:47:12<11:38:27,  7.08s/it]
                                                           
{'loss': 0.6138, 'learning_rate': 5.6052398557480596e-05, 'epoch': 9.47}

 79%|███████▉  | 22160/28080 [43:47:12<11:38:27,  7.08s/it]
 79%|███████▉  | 22161/28080 [43:47:19<11:37:49,  7.07s/it]
                                                           
{'loss': 0.6131, 'learning_rate': 5.603420478483051e-05, 'epoch': 9.47}

 79%|███████▉  | 22161/28080 [43:47:19<11:37:49,  7.07s/it]
 79%|███████▉  | 22162/28080 [43:47:26<11:39:58,  7.10s/it]
                                                           
{'loss': 0.5947, 'learning_rate': 5.6016013592695146e-05, 'epoch': 9.47}

 79%|███████▉  | 22162/28080 [43:47:26<11:39:58,  7.10s/it]
 79%|███████▉  | 22163/28080 [43:47:33<11:41:51,  7.12s/it]
                                                           
{'loss': 0.5977, 'learning_rate': 5.59978249813167e-05, 'epoch': 9.47}

 79%|███████▉  | 22163/28080 [43:47:33<11:41:51,  7.12s/it]
 79%|███████▉  | 22164/28080 [43:47:40<11:39:01,  7.09s/it]
                                                           
{'loss': 0.6068, 'learning_rate': 5.597963895093702e-05, 'epoch': 9.47}

 79%|███████▉  | 22164/28080 [43:47:40<11:39:01,  7.09s/it]
 79%|███████▉  | 22165/28080 [43:47:47<11:38:37,  7.09s/it]
                                                           
{'loss': 0.5949, 'learning_rate': 5.59614555017981e-05, 'epoch': 9.47}

 79%|███████▉  | 22165/28080 [43:47:47<11:38:37,  7.09s/it]
 79%|███████▉  | 22166/28080 [43:47:54<11:39:47,  7.10s/it]
                                                           
{'loss': 0.6215, 'learning_rate': 5.594327463414184e-05, 'epoch': 9.47}

 79%|███████▉  | 22166/28080 [43:47:54<11:39:47,  7.10s/it]
 79%|███████▉  | 22167/28080 [43:48:01<11:37:03,  7.07s/it]
                                                           
{'loss': 0.6123, 'learning_rate': 5.592509634821003e-05, 'epoch': 9.47}

 79%|███████▉  | 22167/28080 [43:48:01<11:37:03,  7.07s/it]
 79%|███████▉  | 22168/28080 [43:48:09<11:39:40,  7.10s/it]
                                                           
{'loss': 0.5957, 'learning_rate': 5.590692064424469e-05, 'epoch': 9.47}

 79%|███████▉  | 22168/28080 [43:48:09<11:39:40,  7.10s/it]
 79%|███████▉  | 22169/28080 [43:48:16<11:40:04,  7.11s/it]
                                                           
{'loss': 0.6015, 'learning_rate': 5.588874752248752e-05, 'epoch': 9.47}

 79%|███████▉  | 22169/28080 [43:48:16<11:40:04,  7.11s/it]
 79%|███████▉  | 22170/28080 [43:48:23<11:38:16,  7.09s/it]
                                                           
{'loss': 0.6114, 'learning_rate': 5.5870576983180294e-05, 'epoch': 9.47}

 79%|███████▉  | 22170/28080 [43:48:23<11:38:16,  7.09s/it]
 79%|███████▉  | 22171/28080 [43:48:30<11:39:16,  7.10s/it]
                                                           
{'loss': 0.6015, 'learning_rate': 5.5852409026564714e-05, 'epoch': 9.47}

 79%|███████▉  | 22171/28080 [43:48:30<11:39:16,  7.10s/it]
 79%|███████▉  | 22172/28080 [43:48:37<11:37:45,  7.09s/it]
                                                           
{'loss': 0.6199, 'learning_rate': 5.5834243652882614e-05, 'epoch': 9.47}

 79%|███████▉  | 22172/28080 [43:48:37<11:37:45,  7.09s/it]
 79%|███████▉  | 22173/28080 [43:48:44<11:36:20,  7.07s/it]
                                                           
{'loss': 0.6074, 'learning_rate': 5.581608086237552e-05, 'epoch': 9.47}

 79%|███████▉  | 22173/28080 [43:48:44<11:36:20,  7.07s/it]
 79%|███████▉  | 22174/28080 [43:48:51<11:36:22,  7.07s/it]
                                                           
{'loss': 0.6139, 'learning_rate': 5.579792065528527e-05, 'epoch': 9.47}

 79%|███████▉  | 22174/28080 [43:48:51<11:36:22,  7.07s/it]
 79%|███████▉  | 22175/28080 [43:48:58<11:38:33,  7.10s/it]
                                                           
{'loss': 0.6054, 'learning_rate': 5.5779763031853226e-05, 'epoch': 9.47}

 79%|███████▉  | 22175/28080 [43:48:58<11:38:33,  7.10s/it]
 79%|███████▉  | 22176/28080 [43:49:05<11:37:48,  7.09s/it]
                                                           
{'loss': 0.6079, 'learning_rate': 5.576160799232113e-05, 'epoch': 9.47}

 79%|███████▉  | 22176/28080 [43:49:05<11:37:48,  7.09s/it]
 79%|███████▉  | 22177/28080 [43:49:12<11:35:25,  7.07s/it]
                                                           
{'loss': 0.6096, 'learning_rate': 5.574345553693036e-05, 'epoch': 9.47}

 79%|███████▉  | 22177/28080 [43:49:12<11:35:25,  7.07s/it]
 79%|███████▉  | 22178/28080 [43:49:19<11:34:43,  7.06s/it]
                                                           
{'loss': 0.6082, 'learning_rate': 5.57253056659226e-05, 'epoch': 9.47}

 79%|███████▉  | 22178/28080 [43:49:19<11:34:43,  7.06s/it]
 79%|███████▉  | 22179/28080 [43:49:26<11:35:05,  7.07s/it]
                                                           
{'loss': 0.6194, 'learning_rate': 5.570715837953924e-05, 'epoch': 9.47}

 79%|███████▉  | 22179/28080 [43:49:26<11:35:05,  7.07s/it]
 79%|███████▉  | 22180/28080 [43:49:33<11:31:45,  7.03s/it]
                                                           
{'loss': 0.6045, 'learning_rate': 5.5689013678021675e-05, 'epoch': 9.48}

 79%|███████▉  | 22180/28080 [43:49:33<11:31:45,  7.03s/it]
 79%|███████▉  | 22181/28080 [43:49:41<11:34:23,  7.06s/it]
                                                           
{'loss': 0.5804, 'learning_rate': 5.567087156161127e-05, 'epoch': 9.48}

 79%|███████▉  | 22181/28080 [43:49:41<11:34:23,  7.06s/it]
 79%|███████▉  | 22182/28080 [43:49:48<11:38:58,  7.11s/it]
                                                           
{'loss': 0.6042, 'learning_rate': 5.5652732030549494e-05, 'epoch': 9.48}

 79%|███████▉  | 22182/28080 [43:49:48<11:38:58,  7.11s/it]
 79%|███████▉  | 22183/28080 [43:49:55<11:35:46,  7.08s/it]
                                                           
{'loss': 0.6, 'learning_rate': 5.5634595085077647e-05, 'epoch': 9.48}

 79%|███████▉  | 22183/28080 [43:49:55<11:35:46,  7.08s/it]
 79%|███████▉  | 22184/28080 [43:50:02<11:35:37,  7.08s/it]
                                                           
{'loss': 0.6014, 'learning_rate': 5.5616460725436966e-05, 'epoch': 9.48}

 79%|███████▉  | 22184/28080 [43:50:02<11:35:37,  7.08s/it]
 79%|███████▉  | 22185/28080 [43:50:09<11:36:15,  7.09s/it]
                                                           
{'loss': 0.5917, 'learning_rate': 5.55983289518687e-05, 'epoch': 9.48}

 79%|███████▉  | 22185/28080 [43:50:09<11:36:15,  7.09s/it]
 79%|███████▉  | 22186/28080 [43:50:16<11:34:59,  7.07s/it]
                                                           
{'loss': 0.5919, 'learning_rate': 5.5580199764614145e-05, 'epoch': 9.48}

 79%|███████▉  | 22186/28080 [43:50:16<11:34:59,  7.07s/it]
 79%|███████▉  | 22187/28080 [43:50:23<11:38:02,  7.11s/it]
                                                           
{'loss': 0.6016, 'learning_rate': 5.556207316391443e-05, 'epoch': 9.48}

 79%|███████▉  | 22187/28080 [43:50:23<11:38:02,  7.11s/it]
 79%|███████▉  | 22188/28080 [43:50:30<11:40:16,  7.13s/it]
                                                           
{'loss': 0.6051, 'learning_rate': 5.5543949150010845e-05, 'epoch': 9.48}

 79%|███████▉  | 22188/28080 [43:50:30<11:40:16,  7.13s/it]
 79%|███████▉  | 22189/28080 [43:50:37<11:36:30,  7.09s/it]
                                                           
{'loss': 0.5935, 'learning_rate': 5.552582772314438e-05, 'epoch': 9.48}

 79%|███████▉  | 22189/28080 [43:50:37<11:36:30,  7.09s/it]
 79%|███████▉  | 22190/28080 [43:50:44<11:33:35,  7.07s/it]
                                                           
{'loss': 0.5975, 'learning_rate': 5.550770888355605e-05, 'epoch': 9.48}

 79%|███████▉  | 22190/28080 [43:50:44<11:33:35,  7.07s/it]
 79%|███████▉  | 22191/28080 [43:50:52<11:34:58,  7.08s/it]
                                                           
{'loss': 0.6056, 'learning_rate': 5.548959263148709e-05, 'epoch': 9.48}

 79%|███████▉  | 22191/28080 [43:50:52<11:34:58,  7.08s/it]
 79%|███████▉  | 22192/28080 [43:50:59<11:34:24,  7.08s/it]
                                                           
{'loss': 0.5924, 'learning_rate': 5.5471478967178356e-05, 'epoch': 9.48}

 79%|███████▉  | 22192/28080 [43:50:59<11:34:24,  7.08s/it]
 79%|███████▉  | 22193/28080 [43:51:05<11:29:38,  7.03s/it]
                                                           
{'loss': 0.6085, 'learning_rate': 5.5453367890871046e-05, 'epoch': 9.48}

 79%|███████▉  | 22193/28080 [43:51:05<11:29:38,  7.03s/it]
 79%|███████▉  | 22194/28080 [43:51:13<11:31:50,  7.05s/it]
                                                           
{'loss': 0.5884, 'learning_rate': 5.543525940280583e-05, 'epoch': 9.48}

 79%|███████▉  | 22194/28080 [43:51:13<11:31:50,  7.05s/it]
 79%|███████▉  | 22195/28080 [43:51:20<11:33:41,  7.07s/it]
                                                           
{'loss': 0.6031, 'learning_rate': 5.5417153503223846e-05, 'epoch': 9.48}

 79%|███████▉  | 22195/28080 [43:51:20<11:33:41,  7.07s/it]
 79%|███████▉  | 22196/28080 [43:51:27<11:32:37,  7.06s/it]
                                                           
{'loss': 0.5986, 'learning_rate': 5.5399050192365823e-05, 'epoch': 9.48}

 79%|███████▉  | 22196/28080 [43:51:27<11:32:37,  7.06s/it]
 79%|███████▉  | 22197/28080 [43:51:34<11:35:51,  7.10s/it]
                                                           
{'loss': 0.6064, 'learning_rate': 5.538094947047276e-05, 'epoch': 9.48}

 79%|███████▉  | 22197/28080 [43:51:34<11:35:51,  7.10s/it]
 79%|███████▉  | 22198/28080 [43:51:41<11:35:46,  7.10s/it]
                                                           
{'loss': 0.6041, 'learning_rate': 5.536285133778537e-05, 'epoch': 9.48}

 79%|███████▉  | 22198/28080 [43:51:41<11:35:46,  7.10s/it]
 79%|███████▉  | 22199/28080 [43:51:48<11:34:52,  7.09s/it]
                                                           
{'loss': 0.5831, 'learning_rate': 5.534475579454445e-05, 'epoch': 9.48}

 79%|███████▉  | 22199/28080 [43:51:48<11:34:52,  7.09s/it]
 79%|███████▉  | 22200/28080 [43:51:55<11:34:50,  7.09s/it]
                                                           
{'loss': 0.6098, 'learning_rate': 5.532666284099069e-05, 'epoch': 9.48}

 79%|███████▉  | 22200/28080 [43:51:55<11:34:50,  7.09s/it]
 79%|███████▉  | 22201/28080 [43:52:02<11:35:44,  7.10s/it]
                                                           
{'loss': 0.5867, 'learning_rate': 5.53085724773649e-05, 'epoch': 9.48}

 79%|███████▉  | 22201/28080 [43:52:02<11:35:44,  7.10s/it]
 79%|███████▉  | 22202/28080 [43:52:09<11:37:02,  7.12s/it]
                                                           
{'loss': 0.601, 'learning_rate': 5.5290484703907715e-05, 'epoch': 9.48}

 79%|███████▉  | 22202/28080 [43:52:09<11:37:02,  7.12s/it]
 79%|███████▉  | 22203/28080 [43:52:17<11:35:39,  7.10s/it]
                                                           
{'loss': 0.614, 'learning_rate': 5.527239952085974e-05, 'epoch': 9.48}

 79%|███████▉  | 22203/28080 [43:52:17<11:35:39,  7.10s/it]
 79%|███████▉  | 22204/28080 [43:52:24<11:31:48,  7.06s/it]
                                                           
{'loss': 0.6159, 'learning_rate': 5.5254316928461525e-05, 'epoch': 9.49}

 79%|███████▉  | 22204/28080 [43:52:24<11:31:48,  7.06s/it]
 79%|███████▉  | 22205/28080 [43:52:31<11:33:17,  7.08s/it]
                                                           
{'loss': 0.6062, 'learning_rate': 5.5236236926953816e-05, 'epoch': 9.49}

 79%|███████▉  | 22205/28080 [43:52:31<11:33:17,  7.08s/it]
 79%|███████▉  | 22206/28080 [43:52:38<11:33:52,  7.09s/it]
                                                           
{'loss': 0.602, 'learning_rate': 5.521815951657697e-05, 'epoch': 9.49}

 79%|███████▉  | 22206/28080 [43:52:38<11:33:52,  7.09s/it]
 79%|███████▉  | 22207/28080 [43:52:45<11:34:32,  7.10s/it]
                                                           
{'loss': 0.5825, 'learning_rate': 5.520008469757162e-05, 'epoch': 9.49}

 79%|███████▉  | 22207/28080 [43:52:45<11:34:32,  7.10s/it]
 79%|███████▉  | 22208/28080 [43:52:52<11:36:58,  7.12s/it]
                                                           
{'loss': 0.5954, 'learning_rate': 5.518201247017818e-05, 'epoch': 9.49}

 79%|███████▉  | 22208/28080 [43:52:52<11:36:58,  7.12s/it]
 79%|███████▉  | 22209/28080 [43:52:59<11:38:07,  7.13s/it]
                                                           
{'loss': 0.6002, 'learning_rate': 5.516394283463708e-05, 'epoch': 9.49}

 79%|███████▉  | 22209/28080 [43:52:59<11:38:07,  7.13s/it]
 79%|███████▉  | 22210/28080 [43:53:06<11:39:26,  7.15s/it]
                                                           
{'loss': 0.5973, 'learning_rate': 5.5145875791188656e-05, 'epoch': 9.49}

 79%|███████▉  | 22210/28080 [43:53:06<11:39:26,  7.15s/it]
 79%|███████▉  | 22211/28080 [43:53:13<11:36:16,  7.12s/it]
                                                           
{'loss': 0.6135, 'learning_rate': 5.5127811340073416e-05, 'epoch': 9.49}

 79%|███████▉  | 22211/28080 [43:53:13<11:36:16,  7.12s/it]
 79%|███████▉  | 22212/28080 [43:53:20<11:33:47,  7.09s/it]
                                                           
{'loss': 0.5947, 'learning_rate': 5.510974948153161e-05, 'epoch': 9.49}

 79%|███████▉  | 22212/28080 [43:53:20<11:33:47,  7.09s/it]
 79%|███████▉  | 22213/28080 [43:53:28<11:36:42,  7.12s/it]
                                                           
{'loss': 0.5808, 'learning_rate': 5.5091690215803516e-05, 'epoch': 9.49}

 79%|███████▉  | 22213/28080 [43:53:28<11:36:42,  7.12s/it]
 79%|███████▉  | 22214/28080 [43:53:35<11:34:52,  7.11s/it]
                                                           
{'loss': 0.5996, 'learning_rate': 5.507363354312939e-05, 'epoch': 9.49}

 79%|███████▉  | 22214/28080 [43:53:35<11:34:52,  7.11s/it]
 79%|███████▉  | 22215/28080 [43:53:42<11:31:14,  7.07s/it]
                                                           
{'loss': 0.6051, 'learning_rate': 5.5055579463749425e-05, 'epoch': 9.49}

 79%|███████▉  | 22215/28080 [43:53:42<11:31:14,  7.07s/it]
 79%|███████▉  | 22216/28080 [43:53:49<11:32:47,  7.09s/it]
                                                           
{'loss': 0.6047, 'learning_rate': 5.503752797790396e-05, 'epoch': 9.49}

 79%|███████▉  | 22216/28080 [43:53:49<11:32:47,  7.09s/it]
 79%|███████▉  | 22217/28080 [43:53:56<11:33:06,  7.09s/it]
                                                           
{'loss': 0.6033, 'learning_rate': 5.501947908583302e-05, 'epoch': 9.49}

 79%|███████▉  | 22217/28080 [43:53:56<11:33:06,  7.09s/it]
 79%|███████▉  | 22218/28080 [43:54:03<11:34:12,  7.11s/it]
                                                           
{'loss': 0.6154, 'learning_rate': 5.500143278777675e-05, 'epoch': 9.49}

 79%|███████▉  | 22218/28080 [43:54:03<11:34:12,  7.11s/it]
 79%|███████▉  | 22219/28080 [43:54:10<11:36:05,  7.13s/it]
                                                           
{'loss': 0.6155, 'learning_rate': 5.498338908397521e-05, 'epoch': 9.49}

 79%|███████▉  | 22219/28080 [43:54:10<11:36:05,  7.13s/it]
 79%|███████▉  | 22220/28080 [43:54:17<11:33:38,  7.10s/it]
                                                           
{'loss': 0.599, 'learning_rate': 5.4965347974668536e-05, 'epoch': 9.49}

 79%|███████▉  | 22220/28080 [43:54:17<11:33:38,  7.10s/it]
 79%|███████▉  | 22221/28080 [43:54:24<11:31:18,  7.08s/it]
                                                           
{'loss': 0.5987, 'learning_rate': 5.494730946009663e-05, 'epoch': 9.49}

 79%|███████▉  | 22221/28080 [43:54:24<11:31:18,  7.08s/it]
 79%|███████▉  | 22222/28080 [43:54:32<11:34:12,  7.11s/it]
                                                           
{'loss': 0.595, 'learning_rate': 5.49292735404997e-05, 'epoch': 9.49}

 79%|███████▉  | 22222/28080 [43:54:32<11:34:12,  7.11s/it]
 79%|███████▉  | 22223/28080 [43:54:39<11:34:32,  7.11s/it]
                                                           
{'loss': 0.6013, 'learning_rate': 5.49112402161174e-05, 'epoch': 9.49}

 79%|███████▉  | 22223/28080 [43:54:39<11:34:32,  7.11s/it]
 79%|███████▉  | 22224/28080 [43:54:46<11:35:57,  7.13s/it]
                                                           
{'loss': 0.587, 'learning_rate': 5.4893209487189874e-05, 'epoch': 9.49}

 79%|███████▉  | 22224/28080 [43:54:46<11:35:57,  7.13s/it]
 79%|███████▉  | 22225/28080 [43:54:53<11:34:48,  7.12s/it]
                                                           
{'loss': 0.5975, 'learning_rate': 5.4875181353956834e-05, 'epoch': 9.49}

 79%|███████▉  | 22225/28080 [43:54:53<11:34:48,  7.12s/it]
 79%|███████▉  | 22226/28080 [43:55:00<11:29:55,  7.07s/it]
                                                           
{'loss': 0.6011, 'learning_rate': 5.485715581665826e-05, 'epoch': 9.49}

 79%|███████▉  | 22226/28080 [43:55:00<11:29:55,  7.07s/it]
 79%|███████▉  | 22227/28080 [43:55:07<11:30:52,  7.08s/it]
                                                           
{'loss': 0.5957, 'learning_rate': 5.483913287553391e-05, 'epoch': 9.5}

 79%|███████▉  | 22227/28080 [43:55:07<11:30:52,  7.08s/it]
 79%|███████▉  | 22228/28080 [43:55:14<11:33:19,  7.11s/it]
                                                           
{'loss': 0.5717, 'learning_rate': 5.482111253082358e-05, 'epoch': 9.5}

 79%|███████▉  | 22228/28080 [43:55:14<11:33:19,  7.11s/it]
 79%|███████▉  | 22229/28080 [43:55:21<11:35:47,  7.14s/it]
                                                           
{'loss': 0.6149, 'learning_rate': 5.4803094782766905e-05, 'epoch': 9.5}

 79%|███████▉  | 22229/28080 [43:55:21<11:35:47,  7.14s/it]
 79%|███████▉  | 22230/28080 [43:55:28<11:32:18,  7.10s/it]
                                                           
{'loss': 0.6249, 'learning_rate': 5.478507963160376e-05, 'epoch': 9.5}

 79%|███████▉  | 22230/28080 [43:55:28<11:32:18,  7.10s/it]
 79%|███████▉  | 22231/28080 [43:55:35<11:28:45,  7.07s/it]
                                                           
{'loss': 0.5969, 'learning_rate': 5.476706707757376e-05, 'epoch': 9.5}

 79%|███████▉  | 22231/28080 [43:55:35<11:28:45,  7.07s/it]
 79%|███████▉  | 22232/28080 [43:55:43<11:32:14,  7.10s/it]
                                                           
{'loss': 0.588, 'learning_rate': 5.474905712091649e-05, 'epoch': 9.5}

 79%|███████▉  | 22232/28080 [43:55:43<11:32:14,  7.10s/it]
 79%|███████▉  | 22233/28080 [43:55:50<11:33:40,  7.12s/it]
                                                           
{'loss': 0.604, 'learning_rate': 5.473104976187152e-05, 'epoch': 9.5}

 79%|███████▉  | 22233/28080 [43:55:50<11:33:40,  7.12s/it]
 79%|███████▉  | 22234/28080 [43:55:57<11:32:30,  7.11s/it]
                                                           
{'loss': 0.6151, 'learning_rate': 5.471304500067856e-05, 'epoch': 9.5}

 79%|███████▉  | 22234/28080 [43:55:57<11:32:30,  7.11s/it]
 79%|███████▉  | 22235/28080 [43:56:04<11:32:24,  7.11s/it]
                                                           
{'loss': 0.5884, 'learning_rate': 5.469504283757701e-05, 'epoch': 9.5}

 79%|███████▉  | 22235/28080 [43:56:04<11:32:24,  7.11s/it]
 79%|███████▉  | 22236/28080 [43:56:11<11:30:53,  7.09s/it]
                                                           
{'loss': 0.6052, 'learning_rate': 5.467704327280657e-05, 'epoch': 9.5}

 79%|███████▉  | 22236/28080 [43:56:11<11:30:53,  7.09s/it]
 79%|███████▉  | 22237/28080 [43:56:18<11:29:38,  7.08s/it]
                                                           
{'loss': 0.609, 'learning_rate': 5.4659046306606396e-05, 'epoch': 9.5}

 79%|███████▉  | 22237/28080 [43:56:18<11:29:38,  7.08s/it]
 79%|███████▉  | 22238/28080 [43:56:25<11:27:34,  7.06s/it]
                                                           
{'loss': 0.5989, 'learning_rate': 5.46410519392162e-05, 'epoch': 9.5}

 79%|███████▉  | 22238/28080 [43:56:25<11:27:34,  7.06s/it]
 79%|███████▉  | 22239/28080 [43:56:32<11:24:27,  7.03s/it]
                                                           
{'loss': 0.6001, 'learning_rate': 5.4623060170875236e-05, 'epoch': 9.5}

 79%|███████▉  | 22239/28080 [43:56:32<11:24:27,  7.03s/it]
 79%|███████▉  | 22240/28080 [43:56:39<11:27:21,  7.06s/it]
                                                           
{'loss': 0.584, 'learning_rate': 5.460507100182285e-05, 'epoch': 9.5}

 79%|███████▉  | 22240/28080 [43:56:39<11:27:21,  7.06s/it]
 79%|███████▉  | 22241/28080 [43:56:46<11:29:55,  7.09s/it]
                                                           
{'loss': 0.5949, 'learning_rate': 5.458708443229854e-05, 'epoch': 9.5}

 79%|███████▉  | 22241/28080 [43:56:46<11:29:55,  7.09s/it]
 79%|███████▉  | 22242/28080 [43:56:53<11:29:22,  7.09s/it]
                                                           
{'loss': 0.5988, 'learning_rate': 5.456910046254135e-05, 'epoch': 9.5}

 79%|███████▉  | 22242/28080 [43:56:53<11:29:22,  7.09s/it]
 79%|███████▉  | 22243/28080 [43:57:00<11:28:13,  7.07s/it]
                                                           
{'loss': 0.6164, 'learning_rate': 5.45511190927907e-05, 'epoch': 9.5}

 79%|███████▉  | 22243/28080 [43:57:00<11:28:13,  7.07s/it]
 79%|███████▉  | 22244/28080 [43:57:07<11:29:19,  7.09s/it]
                                                           
{'loss': 0.6127, 'learning_rate': 5.453314032328574e-05, 'epoch': 9.5}

 79%|███████▉  | 22244/28080 [43:57:08<11:29:19,  7.09s/it]
 79%|███████▉  | 22245/28080 [43:57:15<11:30:13,  7.10s/it]
                                                           
{'loss': 0.6277, 'learning_rate': 5.451516415426577e-05, 'epoch': 9.5}

 79%|███████▉  | 22245/28080 [43:57:15<11:30:13,  7.10s/it]
 79%|███████▉  | 22246/28080 [43:57:22<11:30:48,  7.10s/it]
                                                           
{'loss': 0.5942, 'learning_rate': 5.449719058596986e-05, 'epoch': 9.5}

 79%|███████▉  | 22246/28080 [43:57:22<11:30:48,  7.10s/it]
 79%|███████▉  | 22247/28080 [43:57:29<11:30:51,  7.11s/it]
                                                           
{'loss': 0.6046, 'learning_rate': 5.447921961863714e-05, 'epoch': 9.5}

 79%|███████▉  | 22247/28080 [43:57:29<11:30:51,  7.11s/it]
 79%|███████▉  | 22248/28080 [43:57:36<11:32:18,  7.12s/it]
                                                           
{'loss': 0.589, 'learning_rate': 5.446125125250662e-05, 'epoch': 9.5}

 79%|███████▉  | 22248/28080 [43:57:36<11:32:18,  7.12s/it]
 79%|███████▉  | 22249/28080 [43:57:43<11:31:45,  7.12s/it]
                                                           
{'loss': 0.603, 'learning_rate': 5.444328548781749e-05, 'epoch': 9.5}

 79%|███████▉  | 22249/28080 [43:57:43<11:31:45,  7.12s/it]
 79%|███████▉  | 22250/28080 [43:57:50<11:28:50,  7.09s/it]
                                                           
{'loss': 0.6228, 'learning_rate': 5.4425322324808704e-05, 'epoch': 9.5}

 79%|███████▉  | 22250/28080 [43:57:50<11:28:50,  7.09s/it]
 79%|███████▉  | 22251/28080 [43:57:57<11:29:12,  7.09s/it]
                                                           
{'loss': 0.607, 'learning_rate': 5.440736176371927e-05, 'epoch': 9.51}

 79%|███████▉  | 22251/28080 [43:57:57<11:29:12,  7.09s/it]
 79%|███████▉  | 22252/28080 [43:58:04<11:27:12,  7.07s/it]
                                                           
{'loss': 0.5967, 'learning_rate': 5.438940380478799e-05, 'epoch': 9.51}

 79%|███████▉  | 22252/28080 [43:58:04<11:27:12,  7.07s/it]
 79%|███████▉  | 22253/28080 [43:58:12<11:33:29,  7.14s/it]
                                                           
{'loss': 0.5834, 'learning_rate': 5.437144844825401e-05, 'epoch': 9.51}

 79%|███████▉  | 22253/28080 [43:58:12<11:33:29,  7.14s/it]
 79%|███████▉  | 22254/28080 [43:58:19<11:35:55,  7.17s/it]
                                                           
{'loss': 0.6236, 'learning_rate': 5.435349569435599e-05, 'epoch': 9.51}

 79%|███████▉  | 22254/28080 [43:58:19<11:35:55,  7.17s/it]
 79%|███████▉  | 22255/28080 [43:58:26<11:35:19,  7.16s/it]
                                                           
{'loss': 0.5942, 'learning_rate': 5.4335545543333e-05, 'epoch': 9.51}

 79%|███████▉  | 22255/28080 [43:58:26<11:35:19,  7.16s/it]
 79%|███████▉  | 22256/28080 [43:58:33<11:36:55,  7.18s/it]
                                                           
{'loss': 0.6279, 'learning_rate': 5.431759799542363e-05, 'epoch': 9.51}

 79%|███████▉  | 22256/28080 [43:58:33<11:36:55,  7.18s/it]
 79%|███████▉  | 22257/28080 [43:58:40<11:35:45,  7.17s/it]
                                                           
{'loss': 0.5972, 'learning_rate': 5.429965305086676e-05, 'epoch': 9.51}

 79%|███████▉  | 22257/28080 [43:58:40<11:35:45,  7.17s/it]
 79%|███████▉  | 22258/28080 [43:58:47<11:35:16,  7.17s/it]
                                                           
{'loss': 0.5983, 'learning_rate': 5.4281710709901064e-05, 'epoch': 9.51}

 79%|███████▉  | 22258/28080 [43:58:47<11:35:16,  7.17s/it]
 79%|███████▉  | 22259/28080 [43:58:55<11:34:34,  7.16s/it]
                                                           
{'loss': 0.6083, 'learning_rate': 5.4263770972765385e-05, 'epoch': 9.51}

 79%|███████▉  | 22259/28080 [43:58:55<11:34:34,  7.16s/it]
 79%|███████▉  | 22260/28080 [43:59:02<11:33:35,  7.15s/it]
                                                           
{'loss': 0.6196, 'learning_rate': 5.424583383969828e-05, 'epoch': 9.51}

 79%|███████▉  | 22260/28080 [43:59:02<11:33:35,  7.15s/it]
 79%|███████▉  | 22261/28080 [43:59:09<11:30:30,  7.12s/it]
                                                           
{'loss': 0.6086, 'learning_rate': 5.422789931093841e-05, 'epoch': 9.51}

 79%|███████▉  | 22261/28080 [43:59:09<11:30:30,  7.12s/it]
 79%|███████▉  | 22262/28080 [43:59:16<11:27:36,  7.09s/it]
                                                           
{'loss': 0.6174, 'learning_rate': 5.420996738672432e-05, 'epoch': 9.51}

 79%|███████▉  | 22262/28080 [43:59:16<11:27:36,  7.09s/it]
 79%|███████▉  | 22263/28080 [43:59:23<11:29:05,  7.11s/it]
                                                           
{'loss': 0.6197, 'learning_rate': 5.41920380672947e-05, 'epoch': 9.51}

 79%|███████▉  | 22263/28080 [43:59:23<11:29:05,  7.11s/it]
 79%|███████▉  | 22264/28080 [43:59:30<11:29:52,  7.12s/it]
                                                           
{'loss': 0.6077, 'learning_rate': 5.417411135288797e-05, 'epoch': 9.51}

 79%|███████▉  | 22264/28080 [43:59:30<11:29:52,  7.12s/it]
 79%|███████▉  | 22265/28080 [43:59:37<11:26:21,  7.08s/it]
                                                           
{'loss': 0.6086, 'learning_rate': 5.415618724374269e-05, 'epoch': 9.51}

 79%|███████▉  | 22265/28080 [43:59:37<11:26:21,  7.08s/it]
 79%|███████▉  | 22266/28080 [43:59:44<11:29:43,  7.12s/it]
                                                           
{'loss': 0.5992, 'learning_rate': 5.413826574009731e-05, 'epoch': 9.51}

 79%|███████▉  | 22266/28080 [43:59:44<11:29:43,  7.12s/it]
 79%|███████▉  | 22267/28080 [43:59:51<11:28:16,  7.10s/it]
                                                           
{'loss': 0.5991, 'learning_rate': 5.4120346842190165e-05, 'epoch': 9.51}

 79%|███████▉  | 22267/28080 [43:59:51<11:28:16,  7.10s/it]
 79%|███████▉  | 22268/28080 [43:59:58<11:27:13,  7.09s/it]
                                                           
{'loss': 0.5903, 'learning_rate': 5.410243055025979e-05, 'epoch': 9.51}

 79%|███████▉  | 22268/28080 [43:59:58<11:27:13,  7.09s/it]
 79%|███████▉  | 22269/28080 [44:00:06<11:26:41,  7.09s/it]
                                                           
{'loss': 0.6178, 'learning_rate': 5.4084516864544436e-05, 'epoch': 9.51}

 79%|███████▉  | 22269/28080 [44:00:06<11:26:41,  7.09s/it]
 79%|███████▉  | 22270/28080 [44:00:13<11:24:54,  7.07s/it]
                                                           
{'loss': 0.6101, 'learning_rate': 5.406660578528258e-05, 'epoch': 9.51}

 79%|███████▉  | 22270/28080 [44:00:13<11:24:54,  7.07s/it]
 79%|███████▉  | 22271/28080 [44:00:20<11:25:49,  7.08s/it]
                                                           
{'loss': 0.6056, 'learning_rate': 5.404869731271228e-05, 'epoch': 9.51}

 79%|███████▉  | 22271/28080 [44:00:20<11:25:49,  7.08s/it]
 79%|███████▉  | 22272/28080 [44:00:27<11:27:06,  7.10s/it]
                                                           
{'loss': 0.6144, 'learning_rate': 5.403079144707196e-05, 'epoch': 9.51}

 79%|███████▉  | 22272/28080 [44:00:27<11:27:06,  7.10s/it]
 79%|███████▉  | 22273/28080 [44:00:34<11:27:13,  7.10s/it]
                                                           
{'loss': 0.6042, 'learning_rate': 5.401288818859976e-05, 'epoch': 9.51}

 79%|███████▉  | 22273/28080 [44:00:34<11:27:13,  7.10s/it]
 79%|███████▉  | 22274/28080 [44:00:41<11:28:23,  7.11s/it]
                                                           
{'loss': 0.5994, 'learning_rate': 5.399498753753393e-05, 'epoch': 9.52}

 79%|███████▉  | 22274/28080 [44:00:41<11:28:23,  7.11s/it]
 79%|███████▉  | 22275/28080 [44:00:48<11:29:11,  7.12s/it]
                                                           
{'loss': 0.5779, 'learning_rate': 5.397708949411259e-05, 'epoch': 9.52}

 79%|███████▉  | 22275/28080 [44:00:48<11:29:11,  7.12s/it]
 79%|███████▉  | 22276/28080 [44:00:55<11:29:53,  7.13s/it]
                                                           
{'loss': 0.5804, 'learning_rate': 5.3959194058573826e-05, 'epoch': 9.52}

 79%|███████▉  | 22276/28080 [44:00:55<11:29:53,  7.13s/it]
 79%|███████▉  | 22277/28080 [44:01:03<11:35:44,  7.19s/it]
                                                           
{'loss': 0.6149, 'learning_rate': 5.3941301231155705e-05, 'epoch': 9.52}

 79%|███████▉  | 22277/28080 [44:01:03<11:35:44,  7.19s/it]
 79%|███████▉  | 22278/28080 [44:01:10<11:30:00,  7.14s/it]
                                                           
{'loss': 0.6027, 'learning_rate': 5.3923411012096386e-05, 'epoch': 9.52}

 79%|███████▉  | 22278/28080 [44:01:10<11:30:00,  7.14s/it]
 79%|███████▉  | 22279/28080 [44:01:17<11:29:30,  7.13s/it]
                                                           
{'loss': 0.5886, 'learning_rate': 5.390552340163377e-05, 'epoch': 9.52}

 79%|███████▉  | 22279/28080 [44:01:17<11:29:30,  7.13s/it]
 79%|███████▉  | 22280/28080 [44:01:24<11:31:01,  7.15s/it]
                                                           
{'loss': 0.6033, 'learning_rate': 5.388763840000588e-05, 'epoch': 9.52}

 79%|███████▉  | 22280/28080 [44:01:24<11:31:01,  7.15s/it]
 79%|███████▉  | 22281/28080 [44:01:31<11:26:29,  7.10s/it]
                                                           
{'loss': 0.6165, 'learning_rate': 5.386975600745059e-05, 'epoch': 9.52}

 79%|███████▉  | 22281/28080 [44:01:31<11:26:29,  7.10s/it]
 79%|███████▉  | 22282/28080 [44:01:38<11:27:30,  7.11s/it]
                                                           
{'loss': 0.6026, 'learning_rate': 5.38518762242059e-05, 'epoch': 9.52}

 79%|███████▉  | 22282/28080 [44:01:38<11:27:30,  7.11s/it]
 79%|███████▉  | 22283/28080 [44:01:45<11:27:53,  7.12s/it]
                                                           
{'loss': 0.6074, 'learning_rate': 5.383399905050959e-05, 'epoch': 9.52}

 79%|███████▉  | 22283/28080 [44:01:45<11:27:53,  7.12s/it]
 79%|███████▉  | 22284/28080 [44:01:52<11:27:52,  7.12s/it]
                                                           
{'loss': 0.6053, 'learning_rate': 5.381612448659967e-05, 'epoch': 9.52}

 79%|███████▉  | 22284/28080 [44:01:52<11:27:52,  7.12s/it]
 79%|███████▉  | 22285/28080 [44:01:59<11:24:37,  7.09s/it]
                                                           
{'loss': 0.6212, 'learning_rate': 5.3798252532713696e-05, 'epoch': 9.52}

 79%|███████▉  | 22285/28080 [44:01:59<11:24:37,  7.09s/it]
 79%|███████▉  | 22286/28080 [44:02:06<11:24:32,  7.09s/it]
                                                           
{'loss': 0.5925, 'learning_rate': 5.378038318908965e-05, 'epoch': 9.52}

 79%|███████▉  | 22286/28080 [44:02:06<11:24:32,  7.09s/it]
 79%|███████▉  | 22287/28080 [44:02:14<11:23:28,  7.08s/it]
                                                           
{'loss': 0.6053, 'learning_rate': 5.376251645596508e-05, 'epoch': 9.52}

 79%|███████▉  | 22287/28080 [44:02:14<11:23:28,  7.08s/it]
 79%|███████▉  | 22288/28080 [44:02:21<11:25:28,  7.10s/it]
                                                           
{'loss': 0.6016, 'learning_rate': 5.374465233357787e-05, 'epoch': 9.52}

 79%|███████▉  | 22288/28080 [44:02:21<11:25:28,  7.10s/it]
 79%|███████▉  | 22289/28080 [44:02:28<11:24:48,  7.10s/it]
                                                           
{'loss': 0.5945, 'learning_rate': 5.372679082216564e-05, 'epoch': 9.52}

 79%|███████▉  | 22289/28080 [44:02:28<11:24:48,  7.10s/it]
 79%|███████▉  | 22290/28080 [44:02:35<11:26:45,  7.12s/it]
                                                           
{'loss': 0.6027, 'learning_rate': 5.3708931921965854e-05, 'epoch': 9.52}

 79%|███████▉  | 22290/28080 [44:02:35<11:26:45,  7.12s/it]
 79%|███████▉  | 22291/28080 [44:02:42<11:25:27,  7.10s/it]
                                                           
{'loss': 0.6003, 'learning_rate': 5.369107563321629e-05, 'epoch': 9.52}

 79%|███████▉  | 22291/28080 [44:02:42<11:25:27,  7.10s/it]
 79%|███████▉  | 22292/28080 [44:02:49<11:25:19,  7.10s/it]
                                                           
{'loss': 0.6042, 'learning_rate': 5.36732219561544e-05, 'epoch': 9.52}

 79%|███████▉  | 22292/28080 [44:02:49<11:25:19,  7.10s/it]
 79%|███████▉  | 22293/28080 [44:02:56<11:25:40,  7.11s/it]
                                                           
{'loss': 0.6117, 'learning_rate': 5.3655370891017795e-05, 'epoch': 9.52}

 79%|███████▉  | 22293/28080 [44:02:56<11:25:40,  7.11s/it]
 79%|███████▉  | 22294/28080 [44:03:03<11:26:45,  7.12s/it]
                                                           
{'loss': 0.6048, 'learning_rate': 5.363752243804393e-05, 'epoch': 9.52}

 79%|███████▉  | 22294/28080 [44:03:03<11:26:45,  7.12s/it]
 79%|███████▉  | 22295/28080 [44:03:10<11:21:59,  7.07s/it]
                                                           
{'loss': 0.649, 'learning_rate': 5.3619676597470246e-05, 'epoch': 9.52}

 79%|███████▉  | 22295/28080 [44:03:10<11:21:59,  7.07s/it]
 79%|███████▉  | 22296/28080 [44:03:18<11:24:38,  7.10s/it]
                                                           
{'loss': 0.5812, 'learning_rate': 5.360183336953411e-05, 'epoch': 9.52}

 79%|███████▉  | 22296/28080 [44:03:18<11:24:38,  7.10s/it]
 79%|███████▉  | 22297/28080 [44:03:25<11:23:33,  7.09s/it]
                                                           
{'loss': 0.6279, 'learning_rate': 5.3583992754473034e-05, 'epoch': 9.53}

 79%|███████▉  | 22297/28080 [44:03:25<11:23:33,  7.09s/it]
 79%|███████▉  | 22298/28080 [44:03:32<11:22:02,  7.08s/it]
                                                           
{'loss': 0.6203, 'learning_rate': 5.35661547525243e-05, 'epoch': 9.53}

 79%|███████▉  | 22298/28080 [44:03:32<11:22:02,  7.08s/it]
 79%|███████▉  | 22299/28080 [44:03:39<11:23:16,  7.09s/it]
                                                           
{'loss': 0.6074, 'learning_rate': 5.3548319363925235e-05, 'epoch': 9.53}

 79%|███████▉  | 22299/28080 [44:03:39<11:23:16,  7.09s/it]
 79%|███████▉  | 22300/28080 [44:03:46<11:20:15,  7.06s/it]
                                                           
{'loss': 0.6015, 'learning_rate': 5.353048658891305e-05, 'epoch': 9.53}

 79%|███████▉  | 22300/28080 [44:03:46<11:20:15,  7.06s/it]
 79%|███████▉  | 22301/28080 [44:03:53<11:19:09,  7.05s/it]
                                                           
{'loss': 0.5981, 'learning_rate': 5.3512656427725095e-05, 'epoch': 9.53}

 79%|███████▉  | 22301/28080 [44:03:53<11:19:09,  7.05s/it]
 79%|███████▉  | 22302/28080 [44:04:00<11:19:15,  7.05s/it]
                                                           
{'loss': 0.5979, 'learning_rate': 5.34948288805985e-05, 'epoch': 9.53}

 79%|███████▉  | 22302/28080 [44:04:00<11:19:15,  7.05s/it]
 79%|███████▉  | 22303/28080 [44:04:07<11:21:29,  7.08s/it]
                                                           
{'loss': 0.596, 'learning_rate': 5.347700394777061e-05, 'epoch': 9.53}

 79%|███████▉  | 22303/28080 [44:04:07<11:21:29,  7.08s/it]
 79%|███████▉  | 22304/28080 [44:04:14<11:23:21,  7.10s/it]
                                                           
{'loss': 0.6215, 'learning_rate': 5.34591816294783e-05, 'epoch': 9.53}

 79%|███████▉  | 22304/28080 [44:04:14<11:23:21,  7.10s/it]
 79%|███████▉  | 22305/28080 [44:04:21<11:22:34,  7.09s/it]
                                                           
{'loss': 0.6218, 'learning_rate': 5.344136192595889e-05, 'epoch': 9.53}

 79%|███████▉  | 22305/28080 [44:04:21<11:22:34,  7.09s/it]
 79%|███████▉  | 22306/28080 [44:04:28<11:21:36,  7.08s/it]
                                                           
{'loss': 0.6113, 'learning_rate': 5.342354483744932e-05, 'epoch': 9.53}

 79%|███████▉  | 22306/28080 [44:04:28<11:21:36,  7.08s/it]
 79%|███████▉  | 22307/28080 [44:04:35<11:20:56,  7.08s/it]
                                                           
{'loss': 0.6293, 'learning_rate': 5.340573036418675e-05, 'epoch': 9.53}

 79%|███████▉  | 22307/28080 [44:04:35<11:20:56,  7.08s/it]
 79%|███████▉  | 22308/28080 [44:04:42<11:21:42,  7.09s/it]
                                                           
{'loss': 0.6315, 'learning_rate': 5.3387918506408114e-05, 'epoch': 9.53}

 79%|███████▉  | 22308/28080 [44:04:42<11:21:42,  7.09s/it]
 79%|███████▉  | 22309/28080 [44:04:50<11:24:19,  7.11s/it]
                                                           
{'loss': 0.5903, 'learning_rate': 5.33701092643504e-05, 'epoch': 9.53}

 79%|███████▉  | 22309/28080 [44:04:50<11:24:19,  7.11s/it]
 79%|███████▉  | 22310/28080 [44:04:57<11:25:24,  7.13s/it]
                                                           
{'loss': 0.6157, 'learning_rate': 5.335230263825047e-05, 'epoch': 9.53}

 79%|███████▉  | 22310/28080 [44:04:57<11:25:24,  7.13s/it]
 79%|███████▉  | 22311/28080 [44:05:04<11:24:08,  7.12s/it]
                                                           
{'loss': 0.6103, 'learning_rate': 5.3334498628345354e-05, 'epoch': 9.53}

 79%|███████▉  | 22311/28080 [44:05:04<11:24:08,  7.12s/it]
 79%|███████▉  | 22312/28080 [44:05:11<11:21:45,  7.09s/it]
                                                           
{'loss': 0.6159, 'learning_rate': 5.3316697234871844e-05, 'epoch': 9.53}

 79%|███████▉  | 22312/28080 [44:05:11<11:21:45,  7.09s/it]
 79%|███████▉  | 22313/28080 [44:05:18<11:19:17,  7.07s/it]
                                                           
{'loss': 0.6121, 'learning_rate': 5.3298898458066765e-05, 'epoch': 9.53}

 79%|███████▉  | 22313/28080 [44:05:18<11:19:17,  7.07s/it]
 79%|███████▉  | 22314/28080 [44:05:25<11:18:47,  7.06s/it]
                                                           
{'loss': 0.6376, 'learning_rate': 5.3281102298166906e-05, 'epoch': 9.53}

 79%|███████▉  | 22314/28080 [44:05:25<11:18:47,  7.06s/it]
 79%|███████▉  | 22315/28080 [44:05:32<11:18:27,  7.06s/it]
                                                           
{'loss': 0.6126, 'learning_rate': 5.326330875540897e-05, 'epoch': 9.53}

 79%|███████▉  | 22315/28080 [44:05:32<11:18:27,  7.06s/it]
 79%|███████▉  | 22316/28080 [44:05:39<11:19:58,  7.08s/it]
                                                           
{'loss': 0.5998, 'learning_rate': 5.3245517830029815e-05, 'epoch': 9.53}

 79%|███████▉  | 22316/28080 [44:05:39<11:19:58,  7.08s/it]
 79%|███████▉  | 22317/28080 [44:05:46<11:20:25,  7.08s/it]
                                                           
{'loss': 0.6037, 'learning_rate': 5.322772952226609e-05, 'epoch': 9.53}

 79%|███████▉  | 22317/28080 [44:05:46<11:20:25,  7.08s/it]
 79%|███████▉  | 22318/28080 [44:05:53<11:21:27,  7.10s/it]
                                                           
{'loss': 0.5964, 'learning_rate': 5.320994383235442e-05, 'epoch': 9.53}

 79%|███████▉  | 22318/28080 [44:05:53<11:21:27,  7.10s/it]
 79%|███████▉  | 22319/28080 [44:06:01<11:23:43,  7.12s/it]
                                                           
{'loss': 0.6018, 'learning_rate': 5.319216076053135e-05, 'epoch': 9.53}

 79%|███████▉  | 22319/28080 [44:06:01<11:23:43,  7.12s/it]
 79%|███████▉  | 22320/28080 [44:06:08<11:22:21,  7.11s/it]
                                                           
{'loss': 0.5943, 'learning_rate': 5.3174380307033616e-05, 'epoch': 9.53}

 79%|███████▉  | 22320/28080 [44:06:08<11:22:21,  7.11s/it]
 79%|███████▉  | 22321/28080 [44:06:15<11:23:09,  7.12s/it]
                                                           
{'loss': 0.5985, 'learning_rate': 5.315660247209761e-05, 'epoch': 9.54}

 79%|███████▉  | 22321/28080 [44:06:15<11:23:09,  7.12s/it]
 79%|███████▉  | 22322/28080 [44:06:22<11:21:57,  7.11s/it]
                                                           
{'loss': 0.6166, 'learning_rate': 5.313882725596003e-05, 'epoch': 9.54}

 79%|███████▉  | 22322/28080 [44:06:22<11:21:57,  7.11s/it]
 79%|███████▉  | 22323/28080 [44:06:29<11:25:05,  7.14s/it]
                                                           
{'loss': 0.5948, 'learning_rate': 5.312105465885725e-05, 'epoch': 9.54}

 79%|███████▉  | 22323/28080 [44:06:29<11:25:05,  7.14s/it]
 80%|███████▉  | 22324/28080 [44:06:36<11:22:53,  7.12s/it]
                                                           
{'loss': 0.5957, 'learning_rate': 5.310328468102574e-05, 'epoch': 9.54}

 80%|███████▉  | 22324/28080 [44:06:36<11:22:53,  7.12s/it]
 80%|███████▉  | 22325/28080 [44:06:43<11:21:18,  7.10s/it]
                                                           
{'loss': 0.6008, 'learning_rate': 5.308551732270184e-05, 'epoch': 9.54}

 80%|███████▉  | 22325/28080 [44:06:43<11:21:18,  7.10s/it]
 80%|███████▉  | 22326/28080 [44:06:50<11:20:01,  7.09s/it]
                                                           
{'loss': 0.6217, 'learning_rate': 5.306775258412203e-05, 'epoch': 9.54}

 80%|███████▉  | 22326/28080 [44:06:50<11:20:01,  7.09s/it]
 80%|███████▉  | 22327/28080 [44:06:57<11:22:30,  7.12s/it]
                                                           
{'loss': 0.6283, 'learning_rate': 5.3049990465522614e-05, 'epoch': 9.54}

 80%|███████▉  | 22327/28080 [44:06:57<11:22:30,  7.12s/it]
 80%|███████▉  | 22328/28080 [44:07:04<11:20:05,  7.09s/it]
                                                           
{'loss': 0.6193, 'learning_rate': 5.303223096713991e-05, 'epoch': 9.54}

 80%|███████▉  | 22328/28080 [44:07:04<11:20:05,  7.09s/it]
 80%|███████▉  | 22329/28080 [44:07:12<11:18:31,  7.08s/it]
                                                           
{'loss': 0.6229, 'learning_rate': 5.3014474089210094e-05, 'epoch': 9.54}

 80%|███████▉  | 22329/28080 [44:07:12<11:18:31,  7.08s/it]
 80%|███████▉  | 22330/28080 [44:07:19<11:16:57,  7.06s/it]
                                                           
{'loss': 0.6095, 'learning_rate': 5.299671983196955e-05, 'epoch': 9.54}

 80%|███████▉  | 22330/28080 [44:07:19<11:16:57,  7.06s/it]
 80%|███████▉  | 22331/28080 [44:07:26<11:15:23,  7.05s/it]
                                                           
{'loss': 0.6082, 'learning_rate': 5.297896819565434e-05, 'epoch': 9.54}

 80%|███████▉  | 22331/28080 [44:07:26<11:15:23,  7.05s/it]
 80%|███████▉  | 22332/28080 [44:07:33<11:13:17,  7.03s/it]
                                                           
{'loss': 0.6111, 'learning_rate': 5.296121918050084e-05, 'epoch': 9.54}

 80%|███████▉  | 22332/28080 [44:07:33<11:13:17,  7.03s/it]
 80%|███████▉  | 22333/28080 [44:07:40<11:16:45,  7.07s/it]
                                                           
{'loss': 0.6013, 'learning_rate': 5.294347278674491e-05, 'epoch': 9.54}

 80%|███████▉  | 22333/28080 [44:07:40<11:16:45,  7.07s/it]
 80%|███████▉  | 22334/28080 [44:07:47<11:22:22,  7.13s/it]
                                                           
{'loss': 0.5967, 'learning_rate': 5.2925729014622865e-05, 'epoch': 9.54}

 80%|███████▉  | 22334/28080 [44:07:47<11:22:22,  7.13s/it]
 80%|███████▉  | 22335/28080 [44:07:54<11:22:27,  7.13s/it]
                                                           
{'loss': 0.5912, 'learning_rate': 5.2907987864370594e-05, 'epoch': 9.54}

 80%|███████▉  | 22335/28080 [44:07:54<11:22:27,  7.13s/it]
 80%|███████▉  | 22336/28080 [44:08:01<11:21:58,  7.12s/it]
                                                           
{'loss': 0.5984, 'learning_rate': 5.28902493362243e-05, 'epoch': 9.54}

 80%|███████▉  | 22336/28080 [44:08:01<11:21:58,  7.12s/it]
 80%|███████▉  | 22337/28080 [44:08:08<11:23:13,  7.14s/it]
                                                           
{'loss': 0.6043, 'learning_rate': 5.2872513430419875e-05, 'epoch': 9.54}

 80%|███████▉  | 22337/28080 [44:08:08<11:23:13,  7.14s/it]
 80%|███████▉  | 22338/28080 [44:08:15<11:22:19,  7.13s/it]
                                                           
{'loss': 0.6106, 'learning_rate': 5.2854780147193306e-05, 'epoch': 9.54}

 80%|███████▉  | 22338/28080 [44:08:15<11:22:19,  7.13s/it]
 80%|███████▉  | 22339/28080 [44:08:23<11:22:28,  7.13s/it]
                                                           
{'loss': 0.5861, 'learning_rate': 5.28370494867805e-05, 'epoch': 9.54}

 80%|███████▉  | 22339/28080 [44:08:23<11:22:28,  7.13s/it]
 80%|███████▉  | 22340/28080 [44:08:30<11:22:22,  7.13s/it]
                                                           
{'loss': 0.6047, 'learning_rate': 5.2819321449417286e-05, 'epoch': 9.54}

 80%|███████▉  | 22340/28080 [44:08:30<11:22:22,  7.13s/it]
 80%|███████▉  | 22341/28080 [44:08:37<11:20:52,  7.12s/it]
                                                           
{'loss': 0.6013, 'learning_rate': 5.280159603533965e-05, 'epoch': 9.54}

 80%|███████▉  | 22341/28080 [44:08:37<11:20:52,  7.12s/it]
 80%|███████▉  | 22342/28080 [44:08:44<11:21:11,  7.12s/it]
                                                           
{'loss': 0.5904, 'learning_rate': 5.278387324478334e-05, 'epoch': 9.54}

 80%|███████▉  | 22342/28080 [44:08:44<11:21:11,  7.12s/it]
 80%|███████▉  | 22343/28080 [44:08:51<11:17:51,  7.09s/it]
                                                           
{'loss': 0.5993, 'learning_rate': 5.276615307798413e-05, 'epoch': 9.54}

 80%|███████▉  | 22343/28080 [44:08:51<11:17:51,  7.09s/it]
 80%|███████▉  | 22344/28080 [44:08:58<11:18:20,  7.10s/it]
                                                           
{'loss': 0.5811, 'learning_rate': 5.274843553517772e-05, 'epoch': 9.55}

 80%|███████▉  | 22344/28080 [44:08:58<11:18:20,  7.10s/it]
 80%|███████▉  | 22345/28080 [44:09:05<11:17:32,  7.09s/it]
                                                           
{'loss': 0.5934, 'learning_rate': 5.2730720616599946e-05, 'epoch': 9.55}

 80%|███████▉  | 22345/28080 [44:09:05<11:17:32,  7.09s/it]
 80%|███████▉  | 22346/28080 [44:09:12<11:17:33,  7.09s/it]
                                                           
{'loss': 0.5782, 'learning_rate': 5.271300832248643e-05, 'epoch': 9.55}

 80%|███████▉  | 22346/28080 [44:09:12<11:17:33,  7.09s/it]
 80%|███████▉  | 22347/28080 [44:09:19<11:17:40,  7.09s/it]
                                                           
{'loss': 0.6222, 'learning_rate': 5.2695298653072795e-05, 'epoch': 9.55}

 80%|███████▉  | 22347/28080 [44:09:19<11:17:40,  7.09s/it]
 80%|███████▉  | 22348/28080 [44:09:26<11:17:52,  7.10s/it]
                                                           
{'loss': 0.5775, 'learning_rate': 5.267759160859459e-05, 'epoch': 9.55}

 80%|███████▉  | 22348/28080 [44:09:26<11:17:52,  7.10s/it]
 80%|███████▉  | 22349/28080 [44:09:34<11:18:01,  7.10s/it]
                                                           
{'loss': 0.6049, 'learning_rate': 5.265988718928755e-05, 'epoch': 9.55}

 80%|███████▉  | 22349/28080 [44:09:34<11:18:01,  7.10s/it]
 80%|███████▉  | 22350/28080 [44:09:41<11:17:29,  7.09s/it]
                                                           
{'loss': 0.5899, 'learning_rate': 5.2642185395387066e-05, 'epoch': 9.55}

 80%|███████▉  | 22350/28080 [44:09:41<11:17:29,  7.09s/it]
 80%|███████▉  | 22351/28080 [44:09:48<11:18:28,  7.11s/it]
                                                           
{'loss': 0.6009, 'learning_rate': 5.2624486227128814e-05, 'epoch': 9.55}

 80%|███████▉  | 22351/28080 [44:09:48<11:18:28,  7.11s/it]
 80%|███████▉  | 22352/28080 [44:09:55<11:21:29,  7.14s/it]
                                                           
{'loss': 0.6253, 'learning_rate': 5.2606789684748024e-05, 'epoch': 9.55}

 80%|███████▉  | 22352/28080 [44:09:55<11:21:29,  7.14s/it]
 80%|███████▉  | 22353/28080 [44:10:02<11:22:29,  7.15s/it]
                                                           
{'loss': 0.6123, 'learning_rate': 5.258909576848034e-05, 'epoch': 9.55}

 80%|███████▉  | 22353/28080 [44:10:02<11:22:29,  7.15s/it]
 80%|███████▉  | 22354/28080 [44:10:09<11:20:17,  7.13s/it]
                                                           
{'loss': 0.5996, 'learning_rate': 5.2571404478560985e-05, 'epoch': 9.55}

 80%|███████▉  | 22354/28080 [44:10:09<11:20:17,  7.13s/it]
 80%|███████▉  | 22355/28080 [44:10:16<11:21:15,  7.14s/it]
                                                           
{'loss': 0.614, 'learning_rate': 5.25537158152255e-05, 'epoch': 9.55}

 80%|███████▉  | 22355/28080 [44:10:16<11:21:15,  7.14s/it]
 80%|███████▉  | 22356/28080 [44:10:24<11:19:35,  7.12s/it]
                                                           
{'loss': 0.6015, 'learning_rate': 5.253602977870914e-05, 'epoch': 9.55}

 80%|███████▉  | 22356/28080 [44:10:24<11:19:35,  7.12s/it]
 80%|███████▉  | 22357/28080 [44:10:31<11:21:25,  7.14s/it]
                                                           
{'loss': 0.6094, 'learning_rate': 5.251834636924718e-05, 'epoch': 9.55}

 80%|███████▉  | 22357/28080 [44:10:31<11:21:25,  7.14s/it]
 80%|███████▉  | 22358/28080 [44:10:38<11:21:42,  7.15s/it]
                                                           
{'loss': 0.5828, 'learning_rate': 5.250066558707481e-05, 'epoch': 9.55}

 80%|███████▉  | 22358/28080 [44:10:38<11:21:42,  7.15s/it]
 80%|███████▉  | 22359/28080 [44:10:45<11:21:25,  7.15s/it]
                                                           
{'loss': 0.6007, 'learning_rate': 5.248298743242744e-05, 'epoch': 9.55}

 80%|███████▉  | 22359/28080 [44:10:45<11:21:25,  7.15s/it]
 80%|███████▉  | 22360/28080 [44:10:52<11:20:36,  7.14s/it]
                                                           
{'loss': 0.5998, 'learning_rate': 5.246531190554013e-05, 'epoch': 9.55}

 80%|███████▉  | 22360/28080 [44:10:52<11:20:36,  7.14s/it]
 80%|███████▉  | 22361/28080 [44:10:59<11:19:11,  7.13s/it]
                                                           
{'loss': 0.5968, 'learning_rate': 5.244763900664806e-05, 'epoch': 9.55}

 80%|███████▉  | 22361/28080 [44:10:59<11:19:11,  7.13s/it]
 80%|███████▉  | 22362/28080 [44:11:06<11:17:34,  7.11s/it]
                                                           
{'loss': 0.5969, 'learning_rate': 5.2429968735986295e-05, 'epoch': 9.55}

 80%|███████▉  | 22362/28080 [44:11:06<11:17:34,  7.11s/it]
 80%|███████▉  | 22363/28080 [44:11:13<11:16:30,  7.10s/it]
                                                           
{'loss': 0.5988, 'learning_rate': 5.241230109379003e-05, 'epoch': 9.55}

 80%|███████▉  | 22363/28080 [44:11:13<11:16:30,  7.10s/it]
 80%|███████▉  | 22364/28080 [44:11:21<11:17:56,  7.12s/it]
                                                           
{'loss': 0.5969, 'learning_rate': 5.2394636080294265e-05, 'epoch': 9.55}

 80%|███████▉  | 22364/28080 [44:11:21<11:17:56,  7.12s/it]
 80%|███████▉  | 22365/28080 [44:11:28<11:17:32,  7.11s/it]
                                                           
{'loss': 0.5904, 'learning_rate': 5.2376973695733994e-05, 'epoch': 9.55}

 80%|███████▉  | 22365/28080 [44:11:28<11:17:32,  7.11s/it]
 80%|███████▉  | 22366/28080 [44:11:35<11:16:11,  7.10s/it]
                                                           
{'loss': 0.6325, 'learning_rate': 5.235931394034424e-05, 'epoch': 9.55}

 80%|███████▉  | 22366/28080 [44:11:35<11:16:11,  7.10s/it]
 80%|███████▉  | 22367/28080 [44:11:42<11:16:19,  7.10s/it]
                                                           
{'loss': 0.5914, 'learning_rate': 5.234165681435982e-05, 'epoch': 9.55}

 80%|███████▉  | 22367/28080 [44:11:42<11:16:19,  7.10s/it]
 80%|███████▉  | 22368/28080 [44:11:49<11:10:40,  7.04s/it]
                                                           
{'loss': 0.6067, 'learning_rate': 5.2324002318015845e-05, 'epoch': 9.56}

 80%|███████▉  | 22368/28080 [44:11:49<11:10:40,  7.04s/it]
 80%|███████▉  | 22369/28080 [44:11:56<11:13:03,  7.07s/it]
                                                           
{'loss': 0.5943, 'learning_rate': 5.2306350451547e-05, 'epoch': 9.56}

 80%|███████▉  | 22369/28080 [44:11:56<11:13:03,  7.07s/it]
 80%|███████▉  | 22370/28080 [44:12:03<11:11:55,  7.06s/it]
                                                           
{'loss': 0.5937, 'learning_rate': 5.2288701215188275e-05, 'epoch': 9.56}

 80%|███████▉  | 22370/28080 [44:12:03<11:11:55,  7.06s/it]
 80%|███████▉  | 22371/28080 [44:12:10<11:17:07,  7.12s/it]
                                                           
{'loss': 0.5825, 'learning_rate': 5.2271054609174416e-05, 'epoch': 9.56}

 80%|███████▉  | 22371/28080 [44:12:10<11:17:07,  7.12s/it]
 80%|███████▉  | 22372/28080 [44:12:17<11:16:47,  7.11s/it]
                                                           
{'loss': 0.6061, 'learning_rate': 5.22534106337402e-05, 'epoch': 9.56}

 80%|███████▉  | 22372/28080 [44:12:17<11:16:47,  7.11s/it]
 80%|███████▉  | 22373/28080 [44:12:24<11:18:17,  7.13s/it]
                                                           
{'loss': 0.5895, 'learning_rate': 5.223576928912027e-05, 'epoch': 9.56}

 80%|███████▉  | 22373/28080 [44:12:24<11:18:17,  7.13s/it]
 80%|███████▉  | 22374/28080 [44:12:32<11:19:12,  7.14s/it]
                                                           
{'loss': 0.5994, 'learning_rate': 5.22181305755495e-05, 'epoch': 9.56}

 80%|███████▉  | 22374/28080 [44:12:32<11:19:12,  7.14s/it]
 80%|███████▉  | 22375/28080 [44:12:39<11:17:45,  7.13s/it]
                                                           
{'loss': 0.5892, 'learning_rate': 5.220049449326245e-05, 'epoch': 9.56}

 80%|███████▉  | 22375/28080 [44:12:39<11:17:45,  7.13s/it]
 80%|███████▉  | 22376/28080 [44:12:46<11:15:45,  7.11s/it]
                                                           
{'loss': 0.6126, 'learning_rate': 5.218286104249376e-05, 'epoch': 9.56}

 80%|███████▉  | 22376/28080 [44:12:46<11:15:45,  7.11s/it]
 80%|███████▉  | 22377/28080 [44:12:53<11:15:28,  7.11s/it]
                                                           
{'loss': 0.5965, 'learning_rate': 5.2165230223477936e-05, 'epoch': 9.56}

 80%|███████▉  | 22377/28080 [44:12:53<11:15:28,  7.11s/it]
 80%|███████▉  | 22378/28080 [44:13:00<11:12:49,  7.08s/it]
                                                           
{'loss': 0.6034, 'learning_rate': 5.214760203644972e-05, 'epoch': 9.56}

 80%|███████▉  | 22378/28080 [44:13:00<11:12:49,  7.08s/it]
 80%|███████▉  | 22379/28080 [44:13:07<11:14:03,  7.09s/it]
                                                           
{'loss': 0.5913, 'learning_rate': 5.212997648164355e-05, 'epoch': 9.56}

 80%|███████▉  | 22379/28080 [44:13:07<11:14:03,  7.09s/it]
 80%|███████▉  | 22380/28080 [44:13:14<11:14:10,  7.10s/it]
                                                           
{'loss': 0.5931, 'learning_rate': 5.211235355929392e-05, 'epoch': 9.56}

 80%|███████▉  | 22380/28080 [44:13:14<11:14:10,  7.10s/it]
 80%|███████▉  | 22381/28080 [44:13:21<11:11:49,  7.07s/it]
                                                           
{'loss': 0.5907, 'learning_rate': 5.209473326963518e-05, 'epoch': 9.56}

 80%|███████▉  | 22381/28080 [44:13:21<11:11:49,  7.07s/it]
 80%|███████▉  | 22382/28080 [44:13:28<11:11:58,  7.08s/it]
                                                           
{'loss': 0.5905, 'learning_rate': 5.207711561290193e-05, 'epoch': 9.56}

 80%|███████▉  | 22382/28080 [44:13:28<11:11:58,  7.08s/it]
 80%|███████▉  | 22383/28080 [44:13:35<11:14:18,  7.10s/it]
                                                           
{'loss': 0.6028, 'learning_rate': 5.20595005893284e-05, 'epoch': 9.56}

 80%|███████▉  | 22383/28080 [44:13:35<11:14:18,  7.10s/it]
 80%|███████▉  | 22384/28080 [44:13:43<11:15:43,  7.12s/it]
                                                           
{'loss': 0.6083, 'learning_rate': 5.2041888199149095e-05, 'epoch': 9.56}

 80%|███████▉  | 22384/28080 [44:13:43<11:15:43,  7.12s/it]
 80%|███████▉  | 22385/28080 [44:13:50<11:16:41,  7.13s/it]
                                                           
{'loss': 0.6035, 'learning_rate': 5.202427844259822e-05, 'epoch': 9.56}

 80%|███████▉  | 22385/28080 [44:13:50<11:16:41,  7.13s/it]
 80%|███████▉  | 22386/28080 [44:13:57<11:15:38,  7.12s/it]
                                                           
{'loss': 0.6117, 'learning_rate': 5.2006671319910106e-05, 'epoch': 9.56}

 80%|███████▉  | 22386/28080 [44:13:57<11:15:38,  7.12s/it]
 80%|███████▉  | 22387/28080 [44:14:04<11:11:15,  7.07s/it]
                                                           
{'loss': 0.6095, 'learning_rate': 5.1989066831318874e-05, 'epoch': 9.56}

 80%|███████▉  | 22387/28080 [44:14:04<11:11:15,  7.07s/it]
 80%|███████▉  | 22388/28080 [44:14:11<11:14:15,  7.11s/it]
                                                           
{'loss': 0.5892, 'learning_rate': 5.197146497705893e-05, 'epoch': 9.56}

 80%|███████▉  | 22388/28080 [44:14:11<11:14:15,  7.11s/it]
 80%|███████▉  | 22389/28080 [44:14:18<11:14:26,  7.11s/it]
                                                           
{'loss': 0.599, 'learning_rate': 5.195386575736433e-05, 'epoch': 9.56}

 80%|███████▉  | 22389/28080 [44:14:18<11:14:26,  7.11s/it]
 80%|███████▉  | 22390/28080 [44:14:25<11:12:53,  7.10s/it]
                                                           
{'loss': 0.6144, 'learning_rate': 5.193626917246924e-05, 'epoch': 9.56}

 80%|███████▉  | 22390/28080 [44:14:25<11:12:53,  7.10s/it]
 80%|███████▉  | 22391/28080 [44:14:32<11:16:08,  7.13s/it]
                                                           
{'loss': 0.6205, 'learning_rate': 5.1918675222607766e-05, 'epoch': 9.57}

 80%|███████▉  | 22391/28080 [44:14:32<11:16:08,  7.13s/it]
 80%|███████▉  | 22392/28080 [44:14:39<11:17:52,  7.15s/it]
                                                           
{'loss': 0.6222, 'learning_rate': 5.1901083908013875e-05, 'epoch': 9.57}

 80%|███████▉  | 22392/28080 [44:14:40<11:17:52,  7.15s/it]
 80%|███████▉  | 22393/28080 [44:14:47<11:16:48,  7.14s/it]
                                                           
{'loss': 0.6159, 'learning_rate': 5.188349522892177e-05, 'epoch': 9.57}

 80%|███████▉  | 22393/28080 [44:14:47<11:16:48,  7.14s/it]
 80%|███████▉  | 22394/28080 [44:14:54<11:13:34,  7.11s/it]
                                                           
{'loss': 0.6074, 'learning_rate': 5.186590918556539e-05, 'epoch': 9.57}

 80%|███████▉  | 22394/28080 [44:14:54<11:13:34,  7.11s/it]
 80%|███████▉  | 22395/28080 [44:15:01<11:12:35,  7.10s/it]
                                                           
{'loss': 0.6192, 'learning_rate': 5.184832577817869e-05, 'epoch': 9.57}

 80%|███████▉  | 22395/28080 [44:15:01<11:12:35,  7.10s/it]
 80%|███████▉  | 22396/28080 [44:15:08<11:10:54,  7.08s/it]
                                                           
{'loss': 0.6037, 'learning_rate': 5.1830745006995525e-05, 'epoch': 9.57}

 80%|███████▉  | 22396/28080 [44:15:08<11:10:54,  7.08s/it]
 80%|███████▉  | 22397/28080 [44:15:15<11:13:19,  7.11s/it]
                                                           
{'loss': 0.5894, 'learning_rate': 5.1813166872249905e-05, 'epoch': 9.57}

 80%|███████▉  | 22397/28080 [44:15:15<11:13:19,  7.11s/it]
 80%|███████▉  | 22398/28080 [44:15:22<11:13:59,  7.12s/it]
                                                           
{'loss': 0.6109, 'learning_rate': 5.179559137417558e-05, 'epoch': 9.57}

 80%|███████▉  | 22398/28080 [44:15:22<11:13:59,  7.12s/it]
 80%|███████▉  | 22399/28080 [44:15:29<11:12:17,  7.10s/it]
                                                           
{'loss': 0.6054, 'learning_rate': 5.177801851300659e-05, 'epoch': 9.57}

 80%|███████▉  | 22399/28080 [44:15:29<11:12:17,  7.10s/it]
 80%|███████▉  | 22400/28080 [44:15:36<11:08:07,  7.06s/it]
                                                           
{'loss': 0.6191, 'learning_rate': 5.1760448288976414e-05, 'epoch': 9.57}

 80%|███████▉  | 22400/28080 [44:15:36<11:08:07,  7.06s/it]
 80%|███████▉  | 22401/28080 [44:15:43<11:07:28,  7.05s/it]
                                                           
{'loss': 0.5902, 'learning_rate': 5.174288070231903e-05, 'epoch': 9.57}

 80%|███████▉  | 22401/28080 [44:15:43<11:07:28,  7.05s/it]
 80%|███████▉  | 22402/28080 [44:15:50<11:12:19,  7.10s/it]
                                                           
{'loss': 0.5931, 'learning_rate': 5.1725315753268025e-05, 'epoch': 9.57}

 80%|███████▉  | 22402/28080 [44:15:50<11:12:19,  7.10s/it]
 80%|███████▉  | 22403/28080 [44:15:58<11:14:36,  7.13s/it]
                                                           
{'loss': 0.5905, 'learning_rate': 5.170775344205722e-05, 'epoch': 9.57}

 80%|███████▉  | 22403/28080 [44:15:58<11:14:36,  7.13s/it]
 80%|███████▉  | 22404/28080 [44:16:05<11:17:26,  7.16s/it]
                                                           
{'loss': 0.5926, 'learning_rate': 5.1690193768920175e-05, 'epoch': 9.57}

 80%|███████▉  | 22404/28080 [44:16:05<11:17:26,  7.16s/it]
 80%|███████▉  | 22405/28080 [44:16:12<11:18:08,  7.17s/it]
                                                           
{'loss': 0.5973, 'learning_rate': 5.167263673409053e-05, 'epoch': 9.57}

 80%|███████▉  | 22405/28080 [44:16:12<11:18:08,  7.17s/it]
 80%|███████▉  | 22406/28080 [44:16:19<11:15:16,  7.14s/it]
                                                           
{'loss': 0.6098, 'learning_rate': 5.165508233780178e-05, 'epoch': 9.57}

 80%|███████▉  | 22406/28080 [44:16:19<11:15:16,  7.14s/it]
 80%|███████▉  | 22407/28080 [44:16:26<11:14:09,  7.13s/it]
                                                           
{'loss': 0.5727, 'learning_rate': 5.163753058028761e-05, 'epoch': 9.57}

 80%|███████▉  | 22407/28080 [44:16:26<11:14:09,  7.13s/it]
 80%|███████▉  | 22408/28080 [44:16:33<11:12:39,  7.12s/it]
                                                           
{'loss': 0.5965, 'learning_rate': 5.161998146178143e-05, 'epoch': 9.57}

 80%|███████▉  | 22408/28080 [44:16:33<11:12:39,  7.12s/it]
 80%|███████▉  | 22409/28080 [44:16:40<11:11:44,  7.11s/it]
                                                           
{'loss': 0.6276, 'learning_rate': 5.160243498251677e-05, 'epoch': 9.57}

 80%|███████▉  | 22409/28080 [44:16:40<11:11:44,  7.11s/it]
 80%|███████▉  | 22410/28080 [44:16:48<11:13:58,  7.13s/it]
                                                           
{'loss': 0.6089, 'learning_rate': 5.1584891142726966e-05, 'epoch': 9.57}

 80%|███████▉  | 22410/28080 [44:16:48<11:13:58,  7.13s/it]
 80%|███████▉  | 22411/28080 [44:16:55<11:10:02,  7.09s/it]
                                                           
{'loss': 0.6169, 'learning_rate': 5.156734994264553e-05, 'epoch': 9.57}

 80%|███████▉  | 22411/28080 [44:16:55<11:10:02,  7.09s/it]
 80%|███████▉  | 22412/28080 [44:17:02<11:09:09,  7.08s/it]
                                                           
{'loss': 0.6376, 'learning_rate': 5.154981138250575e-05, 'epoch': 9.57}

 80%|███████▉  | 22412/28080 [44:17:02<11:09:09,  7.08s/it]
 80%|███████▉  | 22413/28080 [44:17:09<11:09:59,  7.09s/it]
                                                           
{'loss': 0.5862, 'learning_rate': 5.153227546254113e-05, 'epoch': 9.57}

 80%|███████▉  | 22413/28080 [44:17:09<11:09:59,  7.09s/it]
 80%|███████▉  | 22414/28080 [44:17:16<11:11:02,  7.11s/it]
                                                           
{'loss': 0.6179, 'learning_rate': 5.151474218298477e-05, 'epoch': 9.58}

 80%|███████▉  | 22414/28080 [44:17:16<11:11:02,  7.11s/it]
 80%|███████▉  | 22415/28080 [44:17:23<11:10:37,  7.10s/it]
                                                           
{'loss': 0.5992, 'learning_rate': 5.1497211544069945e-05, 'epoch': 9.58}

 80%|███████▉  | 22415/28080 [44:17:23<11:10:37,  7.10s/it]
 80%|███████▉  | 22416/28080 [44:17:30<11:10:59,  7.11s/it]
                                                           
{'loss': 0.5874, 'learning_rate': 5.147968354602997e-05, 'epoch': 9.58}

 80%|███████▉  | 22416/28080 [44:17:30<11:10:59,  7.11s/it]
 80%|███████▉  | 22417/28080 [44:17:37<11:10:11,  7.10s/it]
                                                           
{'loss': 0.614, 'learning_rate': 5.1462158189097966e-05, 'epoch': 9.58}

 80%|███████▉  | 22417/28080 [44:17:37<11:10:11,  7.10s/it]
 80%|███████▉  | 22418/28080 [44:17:44<11:12:12,  7.12s/it]
                                                           
{'loss': 0.6114, 'learning_rate': 5.1444635473507194e-05, 'epoch': 9.58}

 80%|███████▉  | 22418/28080 [44:17:44<11:12:12,  7.12s/it]
 80%|███████▉  | 22419/28080 [44:17:51<11:12:54,  7.13s/it]
                                                           
{'loss': 0.6195, 'learning_rate': 5.1427115399490684e-05, 'epoch': 9.58}

 80%|███████▉  | 22419/28080 [44:17:51<11:12:54,  7.13s/it]
 80%|███████▉  | 22420/28080 [44:17:59<11:10:47,  7.11s/it]
                                                           
{'loss': 0.617, 'learning_rate': 5.140959796728156e-05, 'epoch': 9.58}

 80%|███████▉  | 22420/28080 [44:17:59<11:10:47,  7.11s/it]
 80%|███████▉  | 22421/28080 [44:18:06<11:08:57,  7.09s/it]
                                                           
{'loss': 0.5964, 'learning_rate': 5.1392083177112806e-05, 'epoch': 9.58}

 80%|███████▉  | 22421/28080 [44:18:06<11:08:57,  7.09s/it]
 80%|███████▉  | 22422/28080 [44:18:13<11:06:20,  7.07s/it]
                                                           
{'loss': 0.6022, 'learning_rate': 5.1374571029217556e-05, 'epoch': 9.58}

 80%|███████▉  | 22422/28080 [44:18:13<11:06:20,  7.07s/it]
 80%|███████▉  | 22423/28080 [44:18:20<11:05:53,  7.06s/it]
                                                           
{'loss': 0.6102, 'learning_rate': 5.135706152382871e-05, 'epoch': 9.58}

 80%|███████▉  | 22423/28080 [44:18:20<11:05:53,  7.06s/it]
 80%|███████▉  | 22424/28080 [44:18:27<11:05:22,  7.06s/it]
                                                           
{'loss': 0.6083, 'learning_rate': 5.133955466117926e-05, 'epoch': 9.58}

 80%|███████▉  | 22424/28080 [44:18:27<11:05:22,  7.06s/it]
 80%|███████▉  | 22425/28080 [44:18:34<11:08:40,  7.09s/it]
                                                           
{'loss': 0.6017, 'learning_rate': 5.132205044150201e-05, 'epoch': 9.58}

 80%|███████▉  | 22425/28080 [44:18:34<11:08:40,  7.09s/it]
 80%|███████▉  | 22426/28080 [44:18:41<11:06:54,  7.08s/it]
                                                           
{'loss': 0.6208, 'learning_rate': 5.130454886502997e-05, 'epoch': 9.58}

 80%|███████▉  | 22426/28080 [44:18:41<11:06:54,  7.08s/it]
 80%|███████▉  | 22427/28080 [44:18:48<11:09:12,  7.10s/it]
                                                           
{'loss': 0.603, 'learning_rate': 5.128704993199593e-05, 'epoch': 9.58}

 80%|███████▉  | 22427/28080 [44:18:48<11:09:12,  7.10s/it]
 80%|███████▉  | 22428/28080 [44:18:55<11:09:17,  7.10s/it]
                                                           
{'loss': 0.6068, 'learning_rate': 5.1269553642632695e-05, 'epoch': 9.58}

 80%|███████▉  | 22428/28080 [44:18:55<11:09:17,  7.10s/it]
 80%|███████▉  | 22429/28080 [44:19:02<11:06:05,  7.07s/it]
                                                           
{'loss': 0.6109, 'learning_rate': 5.125205999717297e-05, 'epoch': 9.58}

 80%|███████▉  | 22429/28080 [44:19:02<11:06:05,  7.07s/it]
 80%|███████▉  | 22430/28080 [44:19:09<11:03:12,  7.04s/it]
                                                           
{'loss': 0.6194, 'learning_rate': 5.123456899584961e-05, 'epoch': 9.58}

 80%|███████▉  | 22430/28080 [44:19:09<11:03:12,  7.04s/it]
 80%|███████▉  | 22431/28080 [44:19:16<11:04:22,  7.06s/it]
                                                           
{'loss': 0.6086, 'learning_rate': 5.121708063889519e-05, 'epoch': 9.58}

 80%|███████▉  | 22431/28080 [44:19:16<11:04:22,  7.06s/it]
 80%|███████▉  | 22432/28080 [44:19:23<11:07:52,  7.09s/it]
                                                           
{'loss': 0.6049, 'learning_rate': 5.11995949265425e-05, 'epoch': 9.58}

 80%|███████▉  | 22432/28080 [44:19:23<11:07:52,  7.09s/it]
 80%|███████▉  | 22433/28080 [44:19:30<11:07:05,  7.09s/it]
                                                           
{'loss': 0.6279, 'learning_rate': 5.1182111859024104e-05, 'epoch': 9.58}

 80%|███████▉  | 22433/28080 [44:19:30<11:07:05,  7.09s/it]
 80%|███████▉  | 22434/28080 [44:19:37<11:04:26,  7.06s/it]
                                                           
{'loss': 0.6097, 'learning_rate': 5.11646314365726e-05, 'epoch': 9.58}

 80%|███████▉  | 22434/28080 [44:19:37<11:04:26,  7.06s/it]
 80%|███████▉  | 22435/28080 [44:19:45<11:07:26,  7.09s/it]
                                                           
{'loss': 0.6052, 'learning_rate': 5.114715365942049e-05, 'epoch': 9.58}

 80%|███████▉  | 22435/28080 [44:19:45<11:07:26,  7.09s/it]
 80%|███████▉  | 22436/28080 [44:19:52<11:06:09,  7.08s/it]
                                                           
{'loss': 0.5965, 'learning_rate': 5.1129678527800425e-05, 'epoch': 9.58}

 80%|███████▉  | 22436/28080 [44:19:52<11:06:09,  7.08s/it]
 80%|███████▉  | 22437/28080 [44:19:59<11:06:17,  7.08s/it]
                                                           
{'loss': 0.59, 'learning_rate': 5.1112206041944805e-05, 'epoch': 9.58}

 80%|███████▉  | 22437/28080 [44:19:59<11:06:17,  7.08s/it]
 80%|███████▉  | 22438/28080 [44:20:06<11:06:31,  7.09s/it]
                                                           
{'loss': 0.6131, 'learning_rate': 5.1094736202086126e-05, 'epoch': 9.59}

 80%|███████▉  | 22438/28080 [44:20:06<11:06:31,  7.09s/it]
 80%|███████▉  | 22439/28080 [44:20:13<11:07:11,  7.10s/it]
                                                           
{'loss': 0.632, 'learning_rate': 5.107726900845677e-05, 'epoch': 9.59}

 80%|███████▉  | 22439/28080 [44:20:13<11:07:11,  7.10s/it]
 80%|███████▉  | 22440/28080 [44:20:20<11:04:35,  7.07s/it]
                                                           
{'loss': 0.6182, 'learning_rate': 5.105980446128908e-05, 'epoch': 9.59}

 80%|███████▉  | 22440/28080 [44:20:20<11:04:35,  7.07s/it]
 80%|███████▉  | 22441/28080 [44:20:27<11:01:37,  7.04s/it]
                                                           
{'loss': 0.6154, 'learning_rate': 5.10423425608155e-05, 'epoch': 9.59}

 80%|███████▉  | 22441/28080 [44:20:27<11:01:37,  7.04s/it]
 80%|███████▉  | 22442/28080 [44:20:34<11:00:03,  7.02s/it]
                                                           
{'loss': 0.5934, 'learning_rate': 5.102488330726832e-05, 'epoch': 9.59}

 80%|███████▉  | 22442/28080 [44:20:34<11:00:03,  7.02s/it]
 80%|███████▉  | 22443/28080 [44:20:41<11:02:52,  7.06s/it]
                                                           
{'loss': 0.5989, 'learning_rate': 5.1007426700879764e-05, 'epoch': 9.59}

 80%|███████▉  | 22443/28080 [44:20:41<11:02:52,  7.06s/it]
 80%|███████▉  | 22444/28080 [44:20:48<11:07:02,  7.10s/it]
                                                           
{'loss': 0.6126, 'learning_rate': 5.098997274188208e-05, 'epoch': 9.59}

 80%|███████▉  | 22444/28080 [44:20:48<11:07:02,  7.10s/it]
 80%|███████▉  | 22445/28080 [44:20:56<11:10:50,  7.14s/it]
                                                           
{'loss': 0.5857, 'learning_rate': 5.097252143050754e-05, 'epoch': 9.59}

 80%|███████▉  | 22445/28080 [44:20:56<11:10:50,  7.14s/it]
 80%|███████▉  | 22446/28080 [44:21:03<11:11:02,  7.15s/it]
                                                           
{'loss': 0.599, 'learning_rate': 5.0955072766988245e-05, 'epoch': 9.59}

 80%|███████▉  | 22446/28080 [44:21:03<11:11:02,  7.15s/it]
 80%|███████▉  | 22447/28080 [44:21:10<11:11:10,  7.15s/it]
                                                           
{'loss': 0.5768, 'learning_rate': 5.0937626751556474e-05, 'epoch': 9.59}

 80%|███████▉  | 22447/28080 [44:21:10<11:11:10,  7.15s/it]
 80%|███████▉  | 22448/28080 [44:21:17<11:10:22,  7.14s/it]
                                                           
{'loss': 0.6354, 'learning_rate': 5.092018338444407e-05, 'epoch': 9.59}

 80%|███████▉  | 22448/28080 [44:21:17<11:10:22,  7.14s/it]
 80%|███████▉  | 22449/28080 [44:21:24<11:08:42,  7.13s/it]
                                                           
{'loss': 0.5938, 'learning_rate': 5.090274266588332e-05, 'epoch': 9.59}

 80%|███████▉  | 22449/28080 [44:21:24<11:08:42,  7.13s/it]
 80%|███████▉  | 22450/28080 [44:21:31<11:07:22,  7.11s/it]
                                                           
{'loss': 0.6211, 'learning_rate': 5.088530459610613e-05, 'epoch': 9.59}

 80%|███████▉  | 22450/28080 [44:21:31<11:07:22,  7.11s/it]
 80%|███████▉  | 22451/28080 [44:21:38<11:07:14,  7.11s/it]
                                                           
{'loss': 0.6188, 'learning_rate': 5.086786917534461e-05, 'epoch': 9.59}

 80%|███████▉  | 22451/28080 [44:21:38<11:07:14,  7.11s/it]
 80%|███████▉  | 22452/28080 [44:21:45<11:08:21,  7.13s/it]
                                                           
{'loss': 0.5916, 'learning_rate': 5.0850436403830664e-05, 'epoch': 9.59}

 80%|███████▉  | 22452/28080 [44:21:45<11:08:21,  7.13s/it]
 80%|███████▉  | 22453/28080 [44:21:52<11:06:20,  7.11s/it]
                                                           
{'loss': 0.5944, 'learning_rate': 5.083300628179618e-05, 'epoch': 9.59}

 80%|███████▉  | 22453/28080 [44:21:52<11:06:20,  7.11s/it]
 80%|███████▉  | 22454/28080 [44:22:00<11:05:46,  7.10s/it]
                                                           
{'loss': 0.5944, 'learning_rate': 5.081557880947305e-05, 'epoch': 9.59}

 80%|███████▉  | 22454/28080 [44:22:00<11:05:46,  7.10s/it]
 80%|███████▉  | 22455/28080 [44:22:07<11:03:51,  7.08s/it]
                                                           
{'loss': 0.585, 'learning_rate': 5.07981539870932e-05, 'epoch': 9.59}

 80%|███████▉  | 22455/28080 [44:22:07<11:03:51,  7.08s/it]
 80%|███████▉  | 22456/28080 [44:22:14<11:01:54,  7.06s/it]
                                                           
{'loss': 0.6131, 'learning_rate': 5.0780731814888404e-05, 'epoch': 9.59}

 80%|███████▉  | 22456/28080 [44:22:14<11:01:54,  7.06s/it]
 80%|███████▉  | 22457/28080 [44:22:21<11:01:33,  7.06s/it]
                                                           
{'loss': 0.5914, 'learning_rate': 5.0763312293090444e-05, 'epoch': 9.59}

 80%|███████▉  | 22457/28080 [44:22:21<11:01:33,  7.06s/it]
 80%|███████▉  | 22458/28080 [44:22:28<11:01:30,  7.06s/it]
                                                           
{'loss': 0.6092, 'learning_rate': 5.074589542193103e-05, 'epoch': 9.59}

 80%|███████▉  | 22458/28080 [44:22:28<11:01:30,  7.06s/it]
 80%|███████▉  | 22459/28080 [44:22:35<11:01:19,  7.06s/it]
                                                           
{'loss': 0.5999, 'learning_rate': 5.0728481201641975e-05, 'epoch': 9.59}

 80%|███████▉  | 22459/28080 [44:22:35<11:01:19,  7.06s/it]
 80%|███████▉  | 22460/28080 [44:22:42<11:00:57,  7.06s/it]
                                                           
{'loss': 0.6246, 'learning_rate': 5.0711069632454834e-05, 'epoch': 9.59}

 80%|███████▉  | 22460/28080 [44:22:42<11:00:57,  7.06s/it]
 80%|███████▉  | 22461/28080 [44:22:49<10:59:16,  7.04s/it]
                                                           
{'loss': 0.6037, 'learning_rate': 5.0693660714601436e-05, 'epoch': 9.6}

 80%|███████▉  | 22461/28080 [44:22:49<10:59:16,  7.04s/it]
 80%|███████▉  | 22462/28080 [44:22:56<11:03:05,  7.08s/it]
                                                           
{'loss': 0.5976, 'learning_rate': 5.067625444831317e-05, 'epoch': 9.6}

 80%|███████▉  | 22462/28080 [44:22:56<11:03:05,  7.08s/it]
 80%|███████▉  | 22463/28080 [44:23:03<11:02:24,  7.08s/it]
                                                           
{'loss': 0.5902, 'learning_rate': 5.065885083382174e-05, 'epoch': 9.6}

 80%|███████▉  | 22463/28080 [44:23:03<11:02:24,  7.08s/it]
 80%|████████  | 22464/28080 [44:23:10<11:02:26,  7.08s/it]
                                                           
{'loss': 0.605, 'learning_rate': 5.0641449871358656e-05, 'epoch': 9.6}

 80%|████████  | 22464/28080 [44:23:10<11:02:26,  7.08s/it]
 80%|████████  | 22465/28080 [44:23:17<11:04:17,  7.10s/it]
                                                           
{'loss': 0.5976, 'learning_rate': 5.062405156115535e-05, 'epoch': 9.6}

 80%|████████  | 22465/28080 [44:23:17<11:04:17,  7.10s/it]
 80%|████████  | 22466/28080 [44:23:24<11:04:50,  7.11s/it]
                                                           
{'loss': 0.619, 'learning_rate': 5.0606655903443486e-05, 'epoch': 9.6}

 80%|████████  | 22466/28080 [44:23:24<11:04:50,  7.11s/it]
 80%|████████  | 22467/28080 [44:23:31<11:03:14,  7.09s/it]
                                                           
{'loss': 0.5909, 'learning_rate': 5.0589262898454254e-05, 'epoch': 9.6}

 80%|████████  | 22467/28080 [44:23:31<11:03:14,  7.09s/it]
 80%|████████  | 22468/28080 [44:23:39<11:01:52,  7.08s/it]
                                                           
{'loss': 0.5993, 'learning_rate': 5.0571872546419205e-05, 'epoch': 9.6}

 80%|████████  | 22468/28080 [44:23:39<11:01:52,  7.08s/it]
 80%|████████  | 22469/28080 [44:23:46<11:00:24,  7.06s/it]
                                                           
{'loss': 0.5964, 'learning_rate': 5.055448484756958e-05, 'epoch': 9.6}

 80%|████████  | 22469/28080 [44:23:46<11:00:24,  7.06s/it]
 80%|████████  | 22470/28080 [44:23:53<11:02:48,  7.09s/it]
                                                           
{'loss': 0.5932, 'learning_rate': 5.053709980213686e-05, 'epoch': 9.6}

 80%|████████  | 22470/28080 [44:23:53<11:02:48,  7.09s/it]
 80%|████████  | 22471/28080 [44:24:00<11:01:31,  7.08s/it]
                                                           
{'loss': 0.5973, 'learning_rate': 5.051971741035224e-05, 'epoch': 9.6}

 80%|████████  | 22471/28080 [44:24:00<11:01:31,  7.08s/it]
 80%|████████  | 22472/28080 [44:24:07<11:00:54,  7.07s/it]
                                                           
{'loss': 0.5873, 'learning_rate': 5.0502337672446996e-05, 'epoch': 9.6}

 80%|████████  | 22472/28080 [44:24:07<11:00:54,  7.07s/it]
 80%|████████  | 22473/28080 [44:24:14<11:02:16,  7.09s/it]
                                                           
{'loss': 0.604, 'learning_rate': 5.048496058865226e-05, 'epoch': 9.6}

 80%|████████  | 22473/28080 [44:24:14<11:02:16,  7.09s/it]
 80%|████████  | 22474/28080 [44:24:21<10:58:08,  7.04s/it]
                                                           
{'loss': 0.5867, 'learning_rate': 5.046758615919939e-05, 'epoch': 9.6}

 80%|████████  | 22474/28080 [44:24:21<10:58:08,  7.04s/it]
 80%|████████  | 22475/28080 [44:24:28<10:59:38,  7.06s/it]
                                                           
{'loss': 0.5917, 'learning_rate': 5.0450214384319406e-05, 'epoch': 9.6}

 80%|████████  | 22475/28080 [44:24:28<10:59:38,  7.06s/it]
 80%|████████  | 22476/28080 [44:24:35<10:58:58,  7.06s/it]
                                                           
{'loss': 0.6001, 'learning_rate': 5.043284526424347e-05, 'epoch': 9.6}

 80%|████████  | 22476/28080 [44:24:35<10:58:58,  7.06s/it]
 80%|████████  | 22477/28080 [44:24:42<10:57:34,  7.04s/it]
                                                           
{'loss': 0.6083, 'learning_rate': 5.041547879920258e-05, 'epoch': 9.6}

 80%|████████  | 22477/28080 [44:24:42<10:57:34,  7.04s/it]
 80%|████████  | 22478/28080 [44:24:49<10:58:55,  7.06s/it]
                                                           
{'loss': 0.6017, 'learning_rate': 5.039811498942789e-05, 'epoch': 9.6}

 80%|████████  | 22478/28080 [44:24:49<10:58:55,  7.06s/it]
 80%|████████  | 22479/28080 [44:24:56<11:00:56,  7.08s/it]
                                                           
{'loss': 0.6005, 'learning_rate': 5.038075383515034e-05, 'epoch': 9.6}

 80%|████████  | 22479/28080 [44:24:56<11:00:56,  7.08s/it]
 80%|████████  | 22480/28080 [44:25:03<11:00:26,  7.08s/it]
                                                           
{'loss': 0.6098, 'learning_rate': 5.0363395336600945e-05, 'epoch': 9.6}

 80%|████████  | 22480/28080 [44:25:03<11:00:26,  7.08s/it]
 80%|████████  | 22481/28080 [44:25:10<11:01:44,  7.09s/it]
                                                           
{'loss': 0.6003, 'learning_rate': 5.034603949401065e-05, 'epoch': 9.6}

 80%|████████  | 22481/28080 [44:25:10<11:01:44,  7.09s/it]
 80%|████████  | 22482/28080 [44:25:18<11:02:57,  7.11s/it]
                                                           
{'loss': 0.6102, 'learning_rate': 5.032868630761034e-05, 'epoch': 9.6}

 80%|████████  | 22482/28080 [44:25:18<11:02:57,  7.11s/it]
 80%|████████  | 22483/28080 [44:25:25<11:02:29,  7.10s/it]
                                                           
{'loss': 0.5985, 'learning_rate': 5.031133577763078e-05, 'epoch': 9.6}

 80%|████████  | 22483/28080 [44:25:25<11:02:29,  7.10s/it]
 80%|████████  | 22484/28080 [44:25:32<11:02:48,  7.11s/it]
                                                           
{'loss': 0.61, 'learning_rate': 5.029398790430295e-05, 'epoch': 9.6}

 80%|████████  | 22484/28080 [44:25:32<11:02:48,  7.11s/it]
 80%|████████  | 22485/28080 [44:25:39<11:01:34,  7.09s/it]
                                                           
{'loss': 0.5695, 'learning_rate': 5.027664268785759e-05, 'epoch': 9.61}

 80%|████████  | 22485/28080 [44:25:39<11:01:34,  7.09s/it]
 80%|████████  | 22486/28080 [44:25:46<11:02:44,  7.11s/it]
                                                           
{'loss': 0.6, 'learning_rate': 5.0259300128525474e-05, 'epoch': 9.61}

 80%|████████  | 22486/28080 [44:25:46<11:02:44,  7.11s/it]
 80%|████████  | 22487/28080 [44:25:53<11:02:09,  7.10s/it]
                                                           
{'loss': 0.5914, 'learning_rate': 5.0241960226537235e-05, 'epoch': 9.61}

 80%|████████  | 22487/28080 [44:25:53<11:02:09,  7.10s/it]
 80%|████████  | 22488/28080 [44:26:00<10:59:32,  7.08s/it]
                                                           
{'loss': 0.5992, 'learning_rate': 5.0224622982123685e-05, 'epoch': 9.61}

 80%|████████  | 22488/28080 [44:26:00<10:59:32,  7.08s/it]
 80%|████████  | 22489/28080 [44:26:07<10:58:54,  7.07s/it]
                                                           
{'loss': 0.609, 'learning_rate': 5.0207288395515445e-05, 'epoch': 9.61}

 80%|████████  | 22489/28080 [44:26:07<10:58:54,  7.07s/it]
 80%|████████  | 22490/28080 [44:26:14<10:59:09,  7.07s/it]
                                                           
{'loss': 0.6036, 'learning_rate': 5.0189956466943106e-05, 'epoch': 9.61}

 80%|████████  | 22490/28080 [44:26:14<10:59:09,  7.07s/it]
 80%|████████  | 22491/28080 [44:26:21<11:01:33,  7.10s/it]
                                                           
{'loss': 0.5903, 'learning_rate': 5.017262719663729e-05, 'epoch': 9.61}

 80%|████████  | 22491/28080 [44:26:21<11:01:33,  7.10s/it]
 80%|████████  | 22492/28080 [44:26:29<11:01:57,  7.11s/it]
                                                           
{'loss': 0.6152, 'learning_rate': 5.015530058482842e-05, 'epoch': 9.61}

 80%|████████  | 22492/28080 [44:26:29<11:01:57,  7.11s/it]
 80%|████████  | 22493/28080 [44:26:36<11:03:27,  7.13s/it]
                                                           
{'loss': 0.5847, 'learning_rate': 5.0137976631747185e-05, 'epoch': 9.61}

 80%|████████  | 22493/28080 [44:26:36<11:03:27,  7.13s/it]
 80%|████████  | 22494/28080 [44:26:43<11:03:29,  7.13s/it]
                                                           
{'loss': 0.6011, 'learning_rate': 5.0120655337623944e-05, 'epoch': 9.61}

 80%|████████  | 22494/28080 [44:26:43<11:03:29,  7.13s/it]
 80%|████████  | 22495/28080 [44:26:50<11:02:44,  7.12s/it]
                                                           
{'loss': 0.5833, 'learning_rate': 5.0103336702689294e-05, 'epoch': 9.61}

 80%|████████  | 22495/28080 [44:26:50<11:02:44,  7.12s/it]
 80%|████████  | 22496/28080 [44:26:57<10:59:03,  7.08s/it]
                                                           
{'loss': 0.62, 'learning_rate': 5.008602072717339e-05, 'epoch': 9.61}

 80%|████████  | 22496/28080 [44:26:57<10:59:03,  7.08s/it]
 80%|████████  | 22497/28080 [44:27:04<10:56:39,  7.06s/it]
                                                           
{'loss': 0.594, 'learning_rate': 5.006870741130679e-05, 'epoch': 9.61}

 80%|████████  | 22497/28080 [44:27:04<10:56:39,  7.06s/it]
 80%|████████  | 22498/28080 [44:27:11<10:56:35,  7.06s/it]
                                                           
{'loss': 0.6184, 'learning_rate': 5.005139675531975e-05, 'epoch': 9.61}

 80%|████████  | 22498/28080 [44:27:11<10:56:35,  7.06s/it]
 80%|████████  | 22499/28080 [44:27:18<11:01:57,  7.12s/it]
                                                           
{'loss': 0.5906, 'learning_rate': 5.0034088759442656e-05, 'epoch': 9.61}

 80%|████████  | 22499/28080 [44:27:18<11:01:57,  7.12s/it]
 80%|████████  | 22500/28080 [44:27:26<11:06:40,  7.17s/it]
                                                           
{'loss': 0.6155, 'learning_rate': 5.00167834239057e-05, 'epoch': 9.61}

 80%|████████  | 22500/28080 [44:27:26<11:06:40,  7.17s/it]
 80%|████████  | 22501/28080 [44:27:33<11:03:08,  7.13s/it]
                                                           
{'loss': 0.602, 'learning_rate': 4.9999480748939146e-05, 'epoch': 9.61}

 80%|████████  | 22501/28080 [44:27:33<11:03:08,  7.13s/it]
 80%|████████  | 22502/28080 [44:27:40<11:05:18,  7.16s/it]
                                                           
{'loss': 0.6125, 'learning_rate': 4.998218073477309e-05, 'epoch': 9.61}

 80%|████████  | 22502/28080 [44:27:40<11:05:18,  7.16s/it]
 80%|████████  | 22503/28080 [44:27:47<11:03:00,  7.13s/it]
                                                           
{'loss': 0.5846, 'learning_rate': 4.996488338163785e-05, 'epoch': 9.61}

 80%|████████  | 22503/28080 [44:27:47<11:03:00,  7.13s/it]
 80%|████████  | 22504/28080 [44:27:54<11:02:31,  7.13s/it]
                                                           
{'loss': 0.5894, 'learning_rate': 4.9947588689763455e-05, 'epoch': 9.61}

 80%|████████  | 22504/28080 [44:27:54<11:02:31,  7.13s/it]
 80%|████████  | 22505/28080 [44:28:01<11:02:34,  7.13s/it]
                                                           
{'loss': 0.6152, 'learning_rate': 4.9930296659380036e-05, 'epoch': 9.61}

 80%|████████  | 22505/28080 [44:28:01<11:02:34,  7.13s/it]
 80%|████████  | 22506/28080 [44:28:08<11:03:11,  7.14s/it]
                                                           
{'loss': 0.6029, 'learning_rate': 4.9913007290717544e-05, 'epoch': 9.61}

 80%|████████  | 22506/28080 [44:28:08<11:03:11,  7.14s/it]
 80%|████████  | 22507/28080 [44:28:15<11:04:17,  7.15s/it]
                                                           
{'loss': 0.605, 'learning_rate': 4.989572058400613e-05, 'epoch': 9.61}

 80%|████████  | 22507/28080 [44:28:15<11:04:17,  7.15s/it]
 80%|████████  | 22508/28080 [44:28:23<11:02:56,  7.14s/it]
                                                           
{'loss': 0.6053, 'learning_rate': 4.9878436539475655e-05, 'epoch': 9.62}

 80%|████████  | 22508/28080 [44:28:23<11:02:56,  7.14s/it]
 80%|████████  | 22509/28080 [44:28:30<11:00:47,  7.12s/it]
                                                           
{'loss': 0.5974, 'learning_rate': 4.986115515735626e-05, 'epoch': 9.62}

 80%|████████  | 22509/28080 [44:28:30<11:00:47,  7.12s/it]
 80%|████████  | 22510/28080 [44:28:37<11:01:43,  7.13s/it]
                                                           
{'loss': 0.5962, 'learning_rate': 4.9843876437877605e-05, 'epoch': 9.62}

 80%|████████  | 22510/28080 [44:28:37<11:01:43,  7.13s/it]
 80%|████████  | 22511/28080 [44:28:44<11:02:39,  7.14s/it]
                                                           
{'loss': 0.5981, 'learning_rate': 4.982660038126974e-05, 'epoch': 9.62}

 80%|████████  | 22511/28080 [44:28:44<11:02:39,  7.14s/it]
 80%|████████  | 22512/28080 [44:28:51<11:01:39,  7.13s/it]
                                                           
{'loss': 0.5826, 'learning_rate': 4.9809326987762385e-05, 'epoch': 9.62}

 80%|████████  | 22512/28080 [44:28:51<11:01:39,  7.13s/it]
 80%|████████  | 22513/28080 [44:28:58<11:02:15,  7.14s/it]
                                                           
{'loss': 0.5908, 'learning_rate': 4.9792056257585484e-05, 'epoch': 9.62}

 80%|████████  | 22513/28080 [44:28:58<11:02:15,  7.14s/it]
 80%|████████  | 22514/28080 [44:29:05<11:00:22,  7.12s/it]
                                                           
{'loss': 0.5863, 'learning_rate': 4.9774788190968786e-05, 'epoch': 9.62}

 80%|████████  | 22514/28080 [44:29:05<11:00:22,  7.12s/it]
 80%|████████  | 22515/28080 [44:29:12<10:59:09,  7.11s/it]
                                                           
{'loss': 0.591, 'learning_rate': 4.975752278814183e-05, 'epoch': 9.62}

 80%|████████  | 22515/28080 [44:29:12<10:59:09,  7.11s/it]
 80%|████████  | 22516/28080 [44:29:19<10:58:37,  7.10s/it]
                                                           
{'loss': 0.5856, 'learning_rate': 4.974026004933452e-05, 'epoch': 9.62}

 80%|████████  | 22516/28080 [44:29:19<10:58:37,  7.10s/it]
 80%|████████  | 22517/28080 [44:29:26<10:56:01,  7.08s/it]
                                                           
{'loss': 0.5937, 'learning_rate': 4.9722999974776414e-05, 'epoch': 9.62}

 80%|████████  | 22517/28080 [44:29:26<10:56:01,  7.08s/it]
 80%|████████  | 22518/28080 [44:29:34<10:56:10,  7.08s/it]
                                                           
{'loss': 0.6061, 'learning_rate': 4.970574256469723e-05, 'epoch': 9.62}

 80%|████████  | 22518/28080 [44:29:34<10:56:10,  7.08s/it]
 80%|████████  | 22519/28080 [44:29:41<10:53:35,  7.05s/it]
                                                           
{'loss': 0.6101, 'learning_rate': 4.96884878193265e-05, 'epoch': 9.62}

 80%|████████  | 22519/28080 [44:29:41<10:53:35,  7.05s/it]
 80%|████████  | 22520/28080 [44:29:48<10:55:22,  7.07s/it]
                                                           
{'loss': 0.6038, 'learning_rate': 4.967123573889379e-05, 'epoch': 9.62}

 80%|████████  | 22520/28080 [44:29:48<10:55:22,  7.07s/it]
 80%|████████  | 22521/28080 [44:29:55<10:58:57,  7.11s/it]
                                                           
{'loss': 0.5831, 'learning_rate': 4.965398632362858e-05, 'epoch': 9.62}

 80%|████████  | 22521/28080 [44:29:55<10:58:57,  7.11s/it]
 80%|████████  | 22522/28080 [44:30:02<10:59:07,  7.12s/it]
                                                           
{'loss': 0.5979, 'learning_rate': 4.963673957376044e-05, 'epoch': 9.62}

 80%|████████  | 22522/28080 [44:30:02<10:59:07,  7.12s/it]
 80%|████████  | 22523/28080 [44:30:09<10:58:43,  7.11s/it]
                                                           
{'loss': 0.6104, 'learning_rate': 4.961949548951877e-05, 'epoch': 9.62}

 80%|████████  | 22523/28080 [44:30:09<10:58:43,  7.11s/it]
 80%|████████  | 22524/28080 [44:30:16<10:57:21,  7.10s/it]
                                                           
{'loss': 0.6247, 'learning_rate': 4.9602254071133e-05, 'epoch': 9.62}

 80%|████████  | 22524/28080 [44:30:16<10:57:21,  7.10s/it]
 80%|████████  | 22525/28080 [44:30:23<10:56:41,  7.09s/it]
                                                           
{'loss': 0.6319, 'learning_rate': 4.9585015318832446e-05, 'epoch': 9.62}

 80%|████████  | 22525/28080 [44:30:23<10:56:41,  7.09s/it]
 80%|████████  | 22526/28080 [44:30:30<10:53:31,  7.06s/it]
                                                           
{'loss': 0.6236, 'learning_rate': 4.956777923284656e-05, 'epoch': 9.62}

 80%|████████  | 22526/28080 [44:30:30<10:53:31,  7.06s/it]
 80%|████████  | 22527/28080 [44:30:37<10:54:54,  7.08s/it]
                                                           
{'loss': 0.6046, 'learning_rate': 4.955054581340454e-05, 'epoch': 9.62}

 80%|████████  | 22527/28080 [44:30:37<10:54:54,  7.08s/it]
 80%|████████  | 22528/28080 [44:30:44<10:52:48,  7.05s/it]
                                                           
{'loss': 0.6093, 'learning_rate': 4.953331506073583e-05, 'epoch': 9.62}

 80%|████████  | 22528/28080 [44:30:44<10:52:48,  7.05s/it]
 80%|████████  | 22529/28080 [44:30:51<10:53:01,  7.06s/it]
                                                           
{'loss': 0.6344, 'learning_rate': 4.951608697506943e-05, 'epoch': 9.62}

 80%|████████  | 22529/28080 [44:30:51<10:53:01,  7.06s/it]
 80%|████████  | 22530/28080 [44:30:58<10:52:03,  7.05s/it]
                                                           
{'loss': 0.5878, 'learning_rate': 4.949886155663474e-05, 'epoch': 9.62}

 80%|████████  | 22530/28080 [44:30:58<10:52:03,  7.05s/it]
 80%|████████  | 22531/28080 [44:31:05<10:51:16,  7.04s/it]
                                                           
{'loss': 0.5878, 'learning_rate': 4.948163880566078e-05, 'epoch': 9.63}

 80%|████████  | 22531/28080 [44:31:05<10:51:16,  7.04s/it]
 80%|████████  | 22532/28080 [44:31:13<10:52:19,  7.05s/it]
                                                           
{'loss': 0.5953, 'learning_rate': 4.946441872237684e-05, 'epoch': 9.63}

 80%|████████  | 22532/28080 [44:31:13<10:52:19,  7.05s/it]
 80%|████████  | 22533/28080 [44:31:20<10:51:51,  7.05s/it]
                                                           
{'loss': 0.5874, 'learning_rate': 4.944720130701189e-05, 'epoch': 9.63}

 80%|████████  | 22533/28080 [44:31:20<10:51:51,  7.05s/it]
 80%|████████  | 22534/28080 [44:31:27<10:53:11,  7.07s/it]
                                                           
{'loss': 0.6196, 'learning_rate': 4.942998655979506e-05, 'epoch': 9.63}

 80%|████████  | 22534/28080 [44:31:27<10:53:11,  7.07s/it]
 80%|████████  | 22535/28080 [44:31:34<10:51:51,  7.05s/it]
                                                           
{'loss': 0.5862, 'learning_rate': 4.941277448095524e-05, 'epoch': 9.63}

 80%|████████  | 22535/28080 [44:31:34<10:51:51,  7.05s/it]
 80%|████████  | 22536/28080 [44:31:41<10:56:20,  7.10s/it]
                                                           
{'loss': 0.5774, 'learning_rate': 4.939556507072163e-05, 'epoch': 9.63}

 80%|████████  | 22536/28080 [44:31:41<10:56:20,  7.10s/it]
 80%|████████  | 22537/28080 [44:31:48<10:57:56,  7.12s/it]
                                                           
{'loss': 0.5761, 'learning_rate': 4.937835832932303e-05, 'epoch': 9.63}

 80%|████████  | 22537/28080 [44:31:48<10:57:56,  7.12s/it]
 80%|████████  | 22538/28080 [44:31:55<11:01:10,  7.16s/it]
                                                           
{'loss': 0.615, 'learning_rate': 4.936115425698842e-05, 'epoch': 9.63}

 80%|████████  | 22538/28080 [44:31:55<11:01:10,  7.16s/it]
 80%|████████  | 22539/28080 [44:32:02<10:59:40,  7.14s/it]
                                                           
{'loss': 0.6048, 'learning_rate': 4.934395285394669e-05, 'epoch': 9.63}

 80%|████████  | 22539/28080 [44:32:02<10:59:40,  7.14s/it]
 80%|████████  | 22540/28080 [44:32:10<10:56:38,  7.11s/it]
                                                           
{'loss': 0.6159, 'learning_rate': 4.932675412042656e-05, 'epoch': 9.63}

 80%|████████  | 22540/28080 [44:32:10<10:56:38,  7.11s/it]
 80%|████████  | 22541/28080 [44:32:17<10:57:33,  7.12s/it]
                                                           
{'loss': 0.5889, 'learning_rate': 4.930955805665704e-05, 'epoch': 9.63}

 80%|████████  | 22541/28080 [44:32:17<10:57:33,  7.12s/it]
 80%|████████  | 22542/28080 [44:32:24<10:55:49,  7.11s/it]
                                                           
{'loss': 0.627, 'learning_rate': 4.929236466286671e-05, 'epoch': 9.63}

 80%|████████  | 22542/28080 [44:32:24<10:55:49,  7.11s/it]
 80%|████████  | 22543/28080 [44:32:31<10:56:17,  7.11s/it]
                                                           
{'loss': 0.5835, 'learning_rate': 4.927517393928457e-05, 'epoch': 9.63}

 80%|████████  | 22543/28080 [44:32:31<10:56:17,  7.11s/it]
 80%|████████  | 22544/28080 [44:32:38<10:56:34,  7.12s/it]
                                                           
{'loss': 0.6202, 'learning_rate': 4.925798588613903e-05, 'epoch': 9.63}

 80%|████████  | 22544/28080 [44:32:38<10:56:34,  7.12s/it]
 80%|████████  | 22545/28080 [44:32:45<10:55:14,  7.10s/it]
                                                           
{'loss': 0.5836, 'learning_rate': 4.924080050365895e-05, 'epoch': 9.63}

 80%|████████  | 22545/28080 [44:32:45<10:55:14,  7.10s/it]
 80%|████████  | 22546/28080 [44:32:52<10:53:38,  7.09s/it]
                                                           
{'loss': 0.6071, 'learning_rate': 4.922361779207285e-05, 'epoch': 9.63}

 80%|████████  | 22546/28080 [44:32:52<10:53:38,  7.09s/it]
 80%|████████  | 22547/28080 [44:32:59<10:56:50,  7.12s/it]
                                                           
{'loss': 0.5832, 'learning_rate': 4.920643775160943e-05, 'epoch': 9.63}

 80%|████████  | 22547/28080 [44:32:59<10:56:50,  7.12s/it]
 80%|████████  | 22548/28080 [44:33:06<10:56:13,  7.12s/it]
                                                           
{'loss': 0.6189, 'learning_rate': 4.918926038249724e-05, 'epoch': 9.63}

 80%|████████  | 22548/28080 [44:33:06<10:56:13,  7.12s/it]
 80%|████████  | 22549/28080 [44:33:13<10:54:26,  7.10s/it]
                                                           
{'loss': 0.5912, 'learning_rate': 4.9172085684964755e-05, 'epoch': 9.63}

 80%|████████  | 22549/28080 [44:33:13<10:54:26,  7.10s/it]
 80%|████████  | 22550/28080 [44:33:21<10:58:19,  7.14s/it]
                                                           
{'loss': 0.594, 'learning_rate': 4.9154913659240405e-05, 'epoch': 9.63}

 80%|████████  | 22550/28080 [44:33:21<10:58:19,  7.14s/it]
 80%|████████  | 22551/28080 [44:33:28<10:55:52,  7.12s/it]
                                                           
{'loss': 0.588, 'learning_rate': 4.913774430555285e-05, 'epoch': 9.63}

 80%|████████  | 22551/28080 [44:33:28<10:55:52,  7.12s/it]
 80%|████████  | 22552/28080 [44:33:35<10:55:38,  7.12s/it]
                                                           
{'loss': 0.5726, 'learning_rate': 4.912057762413033e-05, 'epoch': 9.63}

 80%|████████  | 22552/28080 [44:33:35<10:55:38,  7.12s/it]
 80%|████████  | 22553/28080 [44:33:42<10:54:39,  7.11s/it]
                                                           
{'loss': 0.593, 'learning_rate': 4.910341361520132e-05, 'epoch': 9.63}

 80%|████████  | 22553/28080 [44:33:42<10:54:39,  7.11s/it]
 80%|████████  | 22554/28080 [44:33:49<10:54:38,  7.11s/it]
                                                           
{'loss': 0.6171, 'learning_rate': 4.908625227899408e-05, 'epoch': 9.63}

 80%|████████  | 22554/28080 [44:33:49<10:54:38,  7.11s/it]
 80%|████████  | 22555/28080 [44:33:56<10:57:50,  7.14s/it]
                                                           
{'loss': 0.6065, 'learning_rate': 4.906909361573702e-05, 'epoch': 9.64}

 80%|████████  | 22555/28080 [44:33:56<10:57:50,  7.14s/it]
 80%|████████  | 22556/28080 [44:34:03<10:56:48,  7.13s/it]
                                                           
{'loss': 0.5969, 'learning_rate': 4.905193762565832e-05, 'epoch': 9.64}

 80%|████████  | 22556/28080 [44:34:03<10:56:48,  7.13s/it]
 80%|████████  | 22557/28080 [44:34:10<10:54:54,  7.11s/it]
                                                           
{'loss': 0.5938, 'learning_rate': 4.903478430898642e-05, 'epoch': 9.64}

 80%|████████  | 22557/28080 [44:34:10<10:54:54,  7.11s/it]
 80%|████████  | 22558/28080 [44:34:18<10:54:32,  7.11s/it]
                                                           
{'loss': 0.6131, 'learning_rate': 4.901763366594928e-05, 'epoch': 9.64}

 80%|████████  | 22558/28080 [44:34:18<10:54:32,  7.11s/it]
 80%|████████  | 22559/28080 [44:34:25<10:52:42,  7.09s/it]
                                                           
{'loss': 0.5954, 'learning_rate': 4.900048569677523e-05, 'epoch': 9.64}

 80%|████████  | 22559/28080 [44:34:25<10:52:42,  7.09s/it]
 80%|████████  | 22560/28080 [44:34:32<10:55:36,  7.13s/it]
                                                           
{'loss': 0.5864, 'learning_rate': 4.8983340401692275e-05, 'epoch': 9.64}

 80%|████████  | 22560/28080 [44:34:32<10:55:36,  7.13s/it]
 80%|████████  | 22561/28080 [44:34:39<10:54:38,  7.12s/it]
                                                           
{'loss': 0.6137, 'learning_rate': 4.89661977809287e-05, 'epoch': 9.64}

 80%|████████  | 22561/28080 [44:34:39<10:54:38,  7.12s/it]
 80%|████████  | 22562/28080 [44:34:46<10:55:02,  7.12s/it]
                                                           
{'loss': 0.5899, 'learning_rate': 4.894905783471246e-05, 'epoch': 9.64}

 80%|████████  | 22562/28080 [44:34:46<10:55:02,  7.12s/it]
 80%|████████  | 22563/28080 [44:34:53<10:52:39,  7.10s/it]
                                                           
{'loss': 0.5852, 'learning_rate': 4.8931920563271556e-05, 'epoch': 9.64}

 80%|████████  | 22563/28080 [44:34:53<10:52:39,  7.10s/it]
 80%|████████  | 22564/28080 [44:35:00<10:53:33,  7.11s/it]
                                                           
{'loss': 0.6258, 'learning_rate': 4.891478596683405e-05, 'epoch': 9.64}

 80%|████████  | 22564/28080 [44:35:00<10:53:33,  7.11s/it]
 80%|████████  | 22565/28080 [44:35:07<10:51:46,  7.09s/it]
                                                           
{'loss': 0.6071, 'learning_rate': 4.889765404562779e-05, 'epoch': 9.64}

 80%|████████  | 22565/28080 [44:35:07<10:51:46,  7.09s/it]
 80%|████████  | 22566/28080 [44:35:14<10:52:36,  7.10s/it]
                                                           
{'loss': 0.6205, 'learning_rate': 4.8880524799880866e-05, 'epoch': 9.64}

 80%|████████  | 22566/28080 [44:35:14<10:52:36,  7.10s/it]
 80%|████████  | 22567/28080 [44:35:21<10:50:07,  7.08s/it]
                                                           
{'loss': 0.5979, 'learning_rate': 4.886339822982106e-05, 'epoch': 9.64}

 80%|████████  | 22567/28080 [44:35:21<10:50:07,  7.08s/it]
 80%|████████  | 22568/28080 [44:35:28<10:48:02,  7.05s/it]
                                                           
{'loss': 0.6071, 'learning_rate': 4.884627433567623e-05, 'epoch': 9.64}

 80%|████████  | 22568/28080 [44:35:28<10:48:02,  7.05s/it]
 80%|████████  | 22569/28080 [44:35:36<10:50:59,  7.09s/it]
                                                           
{'loss': 0.5907, 'learning_rate': 4.882915311767416e-05, 'epoch': 9.64}

 80%|████████  | 22569/28080 [44:35:36<10:50:59,  7.09s/it]
 80%|████████  | 22570/28080 [44:35:43<10:53:31,  7.12s/it]
                                                           
{'loss': 0.5945, 'learning_rate': 4.881203457604272e-05, 'epoch': 9.64}

 80%|████████  | 22570/28080 [44:35:43<10:53:31,  7.12s/it]
 80%|████████  | 22571/28080 [44:35:50<10:52:33,  7.11s/it]
                                                           
{'loss': 0.5762, 'learning_rate': 4.8794918711009605e-05, 'epoch': 9.64}

 80%|████████  | 22571/28080 [44:35:50<10:52:33,  7.11s/it]
 80%|████████  | 22572/28080 [44:35:57<10:49:26,  7.07s/it]
                                                           
{'loss': 0.5915, 'learning_rate': 4.877780552280253e-05, 'epoch': 9.64}

 80%|████████  | 22572/28080 [44:35:57<10:49:26,  7.07s/it]
 80%|████████  | 22573/28080 [44:36:04<10:52:53,  7.11s/it]
                                                           
{'loss': 0.5963, 'learning_rate': 4.876069501164912e-05, 'epoch': 9.64}

 80%|████████  | 22573/28080 [44:36:04<10:52:53,  7.11s/it]
 80%|████████  | 22574/28080 [44:36:11<10:55:43,  7.15s/it]
                                                           
{'loss': 0.6018, 'learning_rate': 4.8743587177777074e-05, 'epoch': 9.64}

 80%|████████  | 22574/28080 [44:36:11<10:55:43,  7.15s/it]
 80%|████████  | 22575/28080 [44:36:19<10:57:43,  7.17s/it]
                                                           
{'loss': 0.5996, 'learning_rate': 4.872648202141394e-05, 'epoch': 9.64}

 80%|████████  | 22575/28080 [44:36:19<10:57:43,  7.17s/it]
 80%|████████  | 22576/28080 [44:36:26<10:56:23,  7.16s/it]
                                                           
{'loss': 0.6105, 'learning_rate': 4.8709379542787455e-05, 'epoch': 9.64}

 80%|████████  | 22576/28080 [44:36:26<10:56:23,  7.16s/it]
 80%|████████  | 22577/28080 [44:36:33<10:56:28,  7.16s/it]
                                                           
{'loss': 0.6113, 'learning_rate': 4.8692279742124865e-05, 'epoch': 9.64}

 80%|████████  | 22577/28080 [44:36:33<10:56:28,  7.16s/it]
 80%|████████  | 22578/28080 [44:36:40<10:54:13,  7.13s/it]
                                                           
{'loss': 0.597, 'learning_rate': 4.867518261965389e-05, 'epoch': 9.65}

 80%|████████  | 22578/28080 [44:36:40<10:54:13,  7.13s/it]
 80%|████████  | 22579/28080 [44:36:47<10:55:47,  7.15s/it]
                                                           
{'loss': 0.5939, 'learning_rate': 4.865808817560186e-05, 'epoch': 9.65}

 80%|████████  | 22579/28080 [44:36:47<10:55:47,  7.15s/it]
 80%|████████  | 22580/28080 [44:36:54<10:54:24,  7.14s/it]
                                                           
{'loss': 0.596, 'learning_rate': 4.864099641019631e-05, 'epoch': 9.65}

 80%|████████  | 22580/28080 [44:36:54<10:54:24,  7.14s/it]
 80%|████████  | 22581/28080 [44:37:01<10:54:46,  7.14s/it]
                                                           
{'loss': 0.5943, 'learning_rate': 4.8623907323664563e-05, 'epoch': 9.65}

 80%|████████  | 22581/28080 [44:37:01<10:54:46,  7.14s/it]
 80%|████████  | 22582/28080 [44:37:08<10:54:01,  7.14s/it]
                                                           
{'loss': 0.6129, 'learning_rate': 4.8606820916234e-05, 'epoch': 9.65}

 80%|████████  | 22582/28080 [44:37:08<10:54:01,  7.14s/it]
 80%|████████  | 22583/28080 [44:37:16<10:54:40,  7.15s/it]
                                                           
{'loss': 0.5999, 'learning_rate': 4.858973718813184e-05, 'epoch': 9.65}

 80%|████████  | 22583/28080 [44:37:16<10:54:40,  7.15s/it]
 80%|████████  | 22584/28080 [44:37:23<10:53:36,  7.14s/it]
                                                           
{'loss': 0.6007, 'learning_rate': 4.85726561395855e-05, 'epoch': 9.65}

 80%|████████  | 22584/28080 [44:37:23<10:53:36,  7.14s/it]
 80%|████████  | 22585/28080 [44:37:30<10:49:27,  7.09s/it]
                                                           
{'loss': 0.6051, 'learning_rate': 4.85555777708222e-05, 'epoch': 9.65}

 80%|████████  | 22585/28080 [44:37:30<10:49:27,  7.09s/it]
 80%|████████  | 22586/28080 [44:37:37<10:51:28,  7.11s/it]
                                                           
{'loss': 0.6204, 'learning_rate': 4.8538502082069085e-05, 'epoch': 9.65}

 80%|████████  | 22586/28080 [44:37:37<10:51:28,  7.11s/it]
 80%|████████  | 22587/28080 [44:37:44<10:51:54,  7.12s/it]
                                                           
{'loss': 0.6088, 'learning_rate': 4.852142907355334e-05, 'epoch': 9.65}

 80%|████████  | 22587/28080 [44:37:44<10:51:54,  7.12s/it]
 80%|████████  | 22588/28080 [44:37:51<10:49:19,  7.09s/it]
                                                           
{'loss': 0.6013, 'learning_rate': 4.850435874550216e-05, 'epoch': 9.65}

 80%|████████  | 22588/28080 [44:37:51<10:49:19,  7.09s/it]
 80%|████████  | 22589/28080 [44:37:58<10:45:57,  7.06s/it]
                                                           
{'loss': 0.5854, 'learning_rate': 4.848729109814262e-05, 'epoch': 9.65}

 80%|████████  | 22589/28080 [44:37:58<10:45:57,  7.06s/it]
 80%|████████  | 22590/28080 [44:38:05<10:50:20,  7.11s/it]
                                                           
{'loss': 0.5882, 'learning_rate': 4.8470226131701765e-05, 'epoch': 9.65}

 80%|████████  | 22590/28080 [44:38:05<10:50:20,  7.11s/it]
 80%|████████  | 22591/28080 [44:38:12<10:51:40,  7.12s/it]
                                                           
{'loss': 0.6077, 'learning_rate': 4.845316384640669e-05, 'epoch': 9.65}

 80%|████████  | 22591/28080 [44:38:12<10:51:40,  7.12s/it]
 80%|████████  | 22592/28080 [44:38:20<10:52:45,  7.14s/it]
                                                           
{'loss': 0.5964, 'learning_rate': 4.8436104242484235e-05, 'epoch': 9.65}

 80%|████████  | 22592/28080 [44:38:20<10:52:45,  7.14s/it]
 80%|████████  | 22593/28080 [44:38:27<10:52:36,  7.14s/it]
                                                           
{'loss': 0.5963, 'learning_rate': 4.841904732016156e-05, 'epoch': 9.65}

 80%|████████  | 22593/28080 [44:38:27<10:52:36,  7.14s/it]
 80%|████████  | 22594/28080 [44:38:34<10:53:26,  7.15s/it]
                                                           
{'loss': 0.6081, 'learning_rate': 4.8401993079665444e-05, 'epoch': 9.65}

 80%|████████  | 22594/28080 [44:38:34<10:53:26,  7.15s/it]
 80%|████████  | 22595/28080 [44:38:41<10:52:27,  7.14s/it]
                                                           
{'loss': 0.6081, 'learning_rate': 4.8384941521222887e-05, 'epoch': 9.65}

 80%|████████  | 22595/28080 [44:38:41<10:52:27,  7.14s/it]
 80%|████████  | 22596/28080 [44:38:48<10:49:16,  7.10s/it]
                                                           
{'loss': 0.6032, 'learning_rate': 4.836789264506067e-05, 'epoch': 9.65}

 80%|████████  | 22596/28080 [44:38:48<10:49:16,  7.10s/it]
 80%|████████  | 22597/28080 [44:38:55<10:50:11,  7.11s/it]
                                                           
{'loss': 0.6122, 'learning_rate': 4.835084645140567e-05, 'epoch': 9.65}

 80%|████████  | 22597/28080 [44:38:55<10:50:11,  7.11s/it]
 80%|████████  | 22598/28080 [44:39:02<10:49:11,  7.11s/it]
                                                           
{'loss': 0.602, 'learning_rate': 4.8333802940484534e-05, 'epoch': 9.65}

 80%|████████  | 22598/28080 [44:39:02<10:49:11,  7.11s/it]
 80%|████████  | 22599/28080 [44:39:09<10:44:57,  7.06s/it]
                                                           
{'loss': 0.6154, 'learning_rate': 4.8316762112524174e-05, 'epoch': 9.65}

 80%|████████  | 22599/28080 [44:39:09<10:44:57,  7.06s/it]
 80%|████████  | 22600/28080 [44:39:16<10:45:38,  7.07s/it]
                                                           
{'loss': 0.6067, 'learning_rate': 4.82997239677512e-05, 'epoch': 9.65}

 80%|████████  | 22600/28080 [44:39:16<10:45:38,  7.07s/it]
 80%|████████  | 22601/28080 [44:39:23<10:44:06,  7.05s/it]
                                                           
{'loss': 0.6082, 'learning_rate': 4.8282688506392364e-05, 'epoch': 9.65}

 80%|████████  | 22601/28080 [44:39:23<10:44:06,  7.05s/it]
 80%|████████  | 22602/28080 [44:39:31<10:47:15,  7.09s/it]
                                                           
{'loss': 0.596, 'learning_rate': 4.8265655728674165e-05, 'epoch': 9.66}

 80%|████████  | 22602/28080 [44:39:31<10:47:15,  7.09s/it]
 80%|████████  | 22603/28080 [44:39:38<10:45:15,  7.07s/it]
                                                           
{'loss': 0.5968, 'learning_rate': 4.8248625634823377e-05, 'epoch': 9.66}

 80%|████████  | 22603/28080 [44:39:38<10:45:15,  7.07s/it]
 80%|████████  | 22604/28080 [44:39:45<10:45:35,  7.07s/it]
                                                           
{'loss': 0.6011, 'learning_rate': 4.823159822506643e-05, 'epoch': 9.66}

 80%|████████  | 22604/28080 [44:39:45<10:45:35,  7.07s/it]
 81%|████████  | 22605/28080 [44:39:52<10:48:23,  7.11s/it]
                                                           
{'loss': 0.6022, 'learning_rate': 4.821457349963002e-05, 'epoch': 9.66}

 81%|████████  | 22605/28080 [44:39:52<10:48:23,  7.11s/it]
 81%|████████  | 22606/28080 [44:39:59<10:48:03,  7.10s/it]
                                                           
{'loss': 0.5805, 'learning_rate': 4.819755145874041e-05, 'epoch': 9.66}

 81%|████████  | 22606/28080 [44:39:59<10:48:03,  7.10s/it]
 81%|████████  | 22607/28080 [44:40:06<10:47:23,  7.10s/it]
                                                           
{'loss': 0.624, 'learning_rate': 4.818053210262427e-05, 'epoch': 9.66}

 81%|████████  | 22607/28080 [44:40:06<10:47:23,  7.10s/it]
 81%|████████  | 22608/28080 [44:40:13<10:44:41,  7.07s/it]
                                                           
{'loss': 0.6105, 'learning_rate': 4.816351543150788e-05, 'epoch': 9.66}

 81%|████████  | 22608/28080 [44:40:13<10:44:41,  7.07s/it]
 81%|████████  | 22609/28080 [44:40:20<10:43:54,  7.06s/it]
                                                           
{'loss': 0.5993, 'learning_rate': 4.814650144561777e-05, 'epoch': 9.66}

 81%|████████  | 22609/28080 [44:40:20<10:43:54,  7.06s/it]
 81%|████████  | 22610/28080 [44:40:27<10:45:16,  7.08s/it]
                                                           
{'loss': 0.6015, 'learning_rate': 4.81294901451802e-05, 'epoch': 9.66}

 81%|████████  | 22610/28080 [44:40:27<10:45:16,  7.08s/it]
 81%|████████  | 22611/28080 [44:40:34<10:44:31,  7.07s/it]
                                                           
{'loss': 0.6097, 'learning_rate': 4.8112481530421497e-05, 'epoch': 9.66}

 81%|████████  | 22611/28080 [44:40:34<10:44:31,  7.07s/it]
 81%|████████  | 22612/28080 [44:40:41<10:45:17,  7.08s/it]
                                                           
{'loss': 0.5917, 'learning_rate': 4.809547560156791e-05, 'epoch': 9.66}

 81%|████████  | 22612/28080 [44:40:41<10:45:17,  7.08s/it]
 81%|████████  | 22613/28080 [44:40:48<10:46:17,  7.09s/it]
                                                           
{'loss': 0.6181, 'learning_rate': 4.807847235884577e-05, 'epoch': 9.66}

 81%|████████  | 22613/28080 [44:40:48<10:46:17,  7.09s/it]
 81%|████████  | 22614/28080 [44:40:56<10:48:47,  7.12s/it]
                                                           
{'loss': 0.5975, 'learning_rate': 4.806147180248127e-05, 'epoch': 9.66}

 81%|████████  | 22614/28080 [44:40:56<10:48:47,  7.12s/it]
 81%|████████  | 22615/28080 [44:41:03<10:47:40,  7.11s/it]
                                                           
{'loss': 0.5931, 'learning_rate': 4.8044473932700535e-05, 'epoch': 9.66}

 81%|████████  | 22615/28080 [44:41:03<10:47:40,  7.11s/it]
 81%|████████  | 22616/28080 [44:41:10<10:46:51,  7.10s/it]
                                                           
{'loss': 0.6012, 'learning_rate': 4.802747874972973e-05, 'epoch': 9.66}

 81%|████████  | 22616/28080 [44:41:10<10:46:51,  7.10s/it]
 81%|████████  | 22617/28080 [44:41:17<10:47:32,  7.11s/it]
                                                           
{'loss': 0.62, 'learning_rate': 4.801048625379492e-05, 'epoch': 9.66}

 81%|████████  | 22617/28080 [44:41:17<10:47:32,  7.11s/it]
 81%|████████  | 22618/28080 [44:41:24<10:49:46,  7.14s/it]
                                                           
{'loss': 0.593, 'learning_rate': 4.799349644512224e-05, 'epoch': 9.66}

 81%|████████  | 22618/28080 [44:41:24<10:49:46,  7.14s/it]
 81%|████████  | 22619/28080 [44:41:31<10:48:41,  7.13s/it]
                                                           
{'loss': 0.6352, 'learning_rate': 4.797650932393771e-05, 'epoch': 9.66}

 81%|████████  | 22619/28080 [44:41:31<10:48:41,  7.13s/it]
 81%|████████  | 22620/28080 [44:41:38<10:47:11,  7.11s/it]
                                                           
{'loss': 0.6058, 'learning_rate': 4.795952489046731e-05, 'epoch': 9.66}

 81%|████████  | 22620/28080 [44:41:38<10:47:11,  7.11s/it]
 81%|████████  | 22621/28080 [44:41:45<10:46:50,  7.11s/it]
                                                           
{'loss': 0.6016, 'learning_rate': 4.794254314493693e-05, 'epoch': 9.66}

 81%|████████  | 22621/28080 [44:41:45<10:46:50,  7.11s/it]
 81%|████████  | 22622/28080 [44:41:52<10:46:22,  7.11s/it]
                                                           
{'loss': 0.5893, 'learning_rate': 4.792556408757262e-05, 'epoch': 9.66}

 81%|████████  | 22622/28080 [44:41:52<10:46:22,  7.11s/it]
 81%|████████  | 22623/28080 [44:42:00<10:45:37,  7.10s/it]
                                                           
{'loss': 0.6093, 'learning_rate': 4.7908587718600155e-05, 'epoch': 9.66}

 81%|████████  | 22623/28080 [44:42:00<10:45:37,  7.10s/it]
 81%|████████  | 22624/28080 [44:42:07<10:45:12,  7.10s/it]
                                                           
{'loss': 0.5986, 'learning_rate': 4.7891614038245576e-05, 'epoch': 9.66}

 81%|████████  | 22624/28080 [44:42:07<10:45:12,  7.10s/it]
 81%|████████  | 22625/28080 [44:42:14<10:47:33,  7.12s/it]
                                                           
{'loss': 0.5842, 'learning_rate': 4.7874643046734414e-05, 'epoch': 9.67}

 81%|████████  | 22625/28080 [44:42:14<10:47:33,  7.12s/it]
 81%|████████  | 22626/28080 [44:42:21<10:48:31,  7.13s/it]
                                                           
{'loss': 0.6006, 'learning_rate': 4.78576747442927e-05, 'epoch': 9.67}

 81%|████████  | 22626/28080 [44:42:21<10:48:31,  7.13s/it]
 81%|████████  | 22627/28080 [44:42:28<10:47:50,  7.13s/it]
                                                           
{'loss': 0.6194, 'learning_rate': 4.784070913114599e-05, 'epoch': 9.67}

 81%|████████  | 22627/28080 [44:42:28<10:47:50,  7.13s/it]
 81%|████████  | 22628/28080 [44:42:35<10:45:30,  7.10s/it]
                                                           
{'loss': 0.5988, 'learning_rate': 4.782374620752017e-05, 'epoch': 9.67}

 81%|████████  | 22628/28080 [44:42:35<10:45:30,  7.10s/it]
 81%|████████  | 22629/28080 [44:42:42<10:45:53,  7.11s/it]
                                                           
{'loss': 0.5948, 'learning_rate': 4.7806785973640856e-05, 'epoch': 9.67}

 81%|████████  | 22629/28080 [44:42:42<10:45:53,  7.11s/it]
 81%|████████  | 22630/28080 [44:42:49<10:46:29,  7.12s/it]
                                                           
{'loss': 0.6117, 'learning_rate': 4.7789828429733646e-05, 'epoch': 9.67}

 81%|████████  | 22630/28080 [44:42:49<10:46:29,  7.12s/it]
 81%|████████  | 22631/28080 [44:42:57<10:48:13,  7.14s/it]
                                                           
{'loss': 0.6148, 'learning_rate': 4.777287357602408e-05, 'epoch': 9.67}

 81%|████████  | 22631/28080 [44:42:57<10:48:13,  7.14s/it]
 81%|████████  | 22632/28080 [44:43:04<10:47:31,  7.13s/it]
                                                           
{'loss': 0.5914, 'learning_rate': 4.7755921412737876e-05, 'epoch': 9.67}

 81%|████████  | 22632/28080 [44:43:04<10:47:31,  7.13s/it]
 81%|████████  | 22633/28080 [44:43:11<10:50:12,  7.16s/it]
                                                           
{'loss': 0.5786, 'learning_rate': 4.773897194010049e-05, 'epoch': 9.67}

 81%|████████  | 22633/28080 [44:43:11<10:50:12,  7.16s/it]
 81%|████████  | 22634/28080 [44:43:18<10:49:39,  7.16s/it]
                                                           
{'loss': 0.5891, 'learning_rate': 4.772202515833743e-05, 'epoch': 9.67}

 81%|████████  | 22634/28080 [44:43:18<10:49:39,  7.16s/it]
 81%|████████  | 22635/28080 [44:43:25<10:49:14,  7.15s/it]
                                                           
{'loss': 0.604, 'learning_rate': 4.77050810676741e-05, 'epoch': 9.67}

 81%|████████  | 22635/28080 [44:43:25<10:49:14,  7.15s/it]
 81%|████████  | 22636/28080 [44:43:32<10:48:27,  7.15s/it]
                                                           
{'loss': 0.601, 'learning_rate': 4.7688139668336014e-05, 'epoch': 9.67}

 81%|████████  | 22636/28080 [44:43:32<10:48:27,  7.15s/it]
 81%|████████  | 22637/28080 [44:43:40<10:47:33,  7.14s/it]
                                                           
{'loss': 0.6046, 'learning_rate': 4.7671200960548446e-05, 'epoch': 9.67}

 81%|████████  | 22637/28080 [44:43:40<10:47:33,  7.14s/it]
 81%|████████  | 22638/28080 [44:43:47<10:48:38,  7.15s/it]
                                                           
{'loss': 0.6147, 'learning_rate': 4.765426494453695e-05, 'epoch': 9.67}

 81%|████████  | 22638/28080 [44:43:47<10:48:38,  7.15s/it]
 81%|████████  | 22639/28080 [44:43:54<10:44:27,  7.11s/it]
                                                           
{'loss': 0.6175, 'learning_rate': 4.7637331620526664e-05, 'epoch': 9.67}

 81%|████████  | 22639/28080 [44:43:54<10:44:27,  7.11s/it]
 81%|████████  | 22640/28080 [44:44:01<10:39:39,  7.06s/it]
                                                           
{'loss': 0.6128, 'learning_rate': 4.762040098874284e-05, 'epoch': 9.67}

 81%|████████  | 22640/28080 [44:44:01<10:39:39,  7.06s/it]
 81%|████████  | 22641/28080 [44:44:08<10:37:08,  7.03s/it]
                                                           
{'loss': 0.6071, 'learning_rate': 4.7603473049410846e-05, 'epoch': 9.67}

 81%|████████  | 22641/28080 [44:44:08<10:37:08,  7.03s/it]
 81%|████████  | 22642/28080 [44:44:15<10:36:06,  7.02s/it]
                                                           
{'loss': 0.6102, 'learning_rate': 4.7586547802755816e-05, 'epoch': 9.67}

 81%|████████  | 22642/28080 [44:44:15<10:36:06,  7.02s/it]
 81%|████████  | 22643/28080 [44:44:22<10:40:11,  7.06s/it]
                                                           
{'loss': 0.5899, 'learning_rate': 4.756962524900296e-05, 'epoch': 9.67}

 81%|████████  | 22643/28080 [44:44:22<10:40:11,  7.06s/it]
 81%|████████  | 22644/28080 [44:44:29<10:42:52,  7.10s/it]
                                                           
{'loss': 0.6156, 'learning_rate': 4.7552705388377444e-05, 'epoch': 9.67}

 81%|████████  | 22644/28080 [44:44:29<10:42:52,  7.10s/it]
 81%|████████  | 22645/28080 [44:44:36<10:39:29,  7.06s/it]
                                                           
{'loss': 0.6316, 'learning_rate': 4.7535788221104324e-05, 'epoch': 9.67}

 81%|████████  | 22645/28080 [44:44:36<10:39:29,  7.06s/it]
 81%|████████  | 22646/28080 [44:44:43<10:35:09,  7.01s/it]
                                                           
{'loss': 0.6167, 'learning_rate': 4.75188737474086e-05, 'epoch': 9.67}

 81%|████████  | 22646/28080 [44:44:43<10:35:09,  7.01s/it]
 81%|████████  | 22647/28080 [44:44:50<10:36:44,  7.03s/it]
                                                           
{'loss': 0.6182, 'learning_rate': 4.750196196751544e-05, 'epoch': 9.67}

 81%|████████  | 22647/28080 [44:44:50<10:36:44,  7.03s/it]
 81%|████████  | 22648/28080 [44:44:57<10:39:17,  7.06s/it]
                                                           
{'loss': 0.5945, 'learning_rate': 4.748505288164978e-05, 'epoch': 9.68}

 81%|████████  | 22648/28080 [44:44:57<10:39:17,  7.06s/it]
 81%|████████  | 22649/28080 [44:45:04<10:40:05,  7.07s/it]
                                                           
{'loss': 0.5921, 'learning_rate': 4.746814649003656e-05, 'epoch': 9.68}

 81%|████████  | 22649/28080 [44:45:04<10:40:05,  7.07s/it]
 81%|████████  | 22650/28080 [44:45:11<10:43:35,  7.11s/it]
                                                           
{'loss': 0.6026, 'learning_rate': 4.745124279290064e-05, 'epoch': 9.68}

 81%|████████  | 22650/28080 [44:45:11<10:43:35,  7.11s/it]
 81%|████████  | 22651/28080 [44:45:18<10:39:22,  7.07s/it]
                                                           
{'loss': 0.6063, 'learning_rate': 4.743434179046704e-05, 'epoch': 9.68}

 81%|████████  | 22651/28080 [44:45:18<10:39:22,  7.07s/it]
 81%|████████  | 22652/28080 [44:45:25<10:40:42,  7.08s/it]
                                                           
{'loss': 0.5971, 'learning_rate': 4.7417443482960536e-05, 'epoch': 9.68}

 81%|████████  | 22652/28080 [44:45:25<10:40:42,  7.08s/it]
 81%|████████  | 22653/28080 [44:45:32<10:40:41,  7.08s/it]
                                                           
{'loss': 0.6106, 'learning_rate': 4.740054787060599e-05, 'epoch': 9.68}

 81%|████████  | 22653/28080 [44:45:32<10:40:41,  7.08s/it]
 81%|████████  | 22654/28080 [44:45:39<10:36:01,  7.03s/it]
                                                           
{'loss': 0.6091, 'learning_rate': 4.738365495362804e-05, 'epoch': 9.68}

 81%|████████  | 22654/28080 [44:45:39<10:36:01,  7.03s/it]
 81%|████████  | 22655/28080 [44:45:47<10:43:30,  7.12s/it]
                                                           
{'loss': 0.5893, 'learning_rate': 4.7366764732251624e-05, 'epoch': 9.68}

 81%|████████  | 22655/28080 [44:45:47<10:43:30,  7.12s/it]
 81%|████████  | 22656/28080 [44:45:54<10:43:21,  7.12s/it]
                                                           
{'loss': 0.6165, 'learning_rate': 4.734987720670128e-05, 'epoch': 9.68}

 81%|████████  | 22656/28080 [44:45:54<10:43:21,  7.12s/it]
 81%|████████  | 22657/28080 [44:46:01<10:43:41,  7.12s/it]
                                                           
{'loss': 0.6155, 'learning_rate': 4.7332992377201844e-05, 'epoch': 9.68}

 81%|████████  | 22657/28080 [44:46:01<10:43:41,  7.12s/it]
 81%|████████  | 22658/28080 [44:46:08<10:41:31,  7.10s/it]
                                                           
{'loss': 0.6021, 'learning_rate': 4.731611024397783e-05, 'epoch': 9.68}

 81%|████████  | 22658/28080 [44:46:08<10:41:31,  7.10s/it]
 81%|████████  | 22659/28080 [44:46:15<10:39:32,  7.08s/it]
                                                           
{'loss': 0.6085, 'learning_rate': 4.72992308072539e-05, 'epoch': 9.68}

 81%|████████  | 22659/28080 [44:46:15<10:39:32,  7.08s/it]
 81%|████████  | 22660/28080 [44:46:22<10:39:02,  7.07s/it]
                                                           
{'loss': 0.5954, 'learning_rate': 4.7282354067254505e-05, 'epoch': 9.68}

 81%|████████  | 22660/28080 [44:46:22<10:39:02,  7.07s/it]
 81%|████████  | 22661/28080 [44:46:29<10:39:39,  7.08s/it]
                                                           
{'loss': 0.5955, 'learning_rate': 4.7265480024204334e-05, 'epoch': 9.68}

 81%|████████  | 22661/28080 [44:46:29<10:39:39,  7.08s/it]
 81%|████████  | 22662/28080 [44:46:36<10:38:20,  7.07s/it]
                                                           
{'loss': 0.6108, 'learning_rate': 4.724860867832781e-05, 'epoch': 9.68}

 81%|████████  | 22662/28080 [44:46:36<10:38:20,  7.07s/it]
 81%|████████  | 22663/28080 [44:46:43<10:38:35,  7.07s/it]
                                                           
{'loss': 0.605, 'learning_rate': 4.7231740029849366e-05, 'epoch': 9.68}

 81%|████████  | 22663/28080 [44:46:43<10:38:35,  7.07s/it]
 81%|████████  | 22664/28080 [44:46:50<10:34:15,  7.03s/it]
                                                           
{'loss': 0.5969, 'learning_rate': 4.721487407899344e-05, 'epoch': 9.68}

 81%|████████  | 22664/28080 [44:46:50<10:34:15,  7.03s/it]
 81%|████████  | 22665/28080 [44:46:57<10:35:37,  7.04s/it]
                                                           
{'loss': 0.6053, 'learning_rate': 4.719801082598435e-05, 'epoch': 9.68}

 81%|████████  | 22665/28080 [44:46:57<10:35:37,  7.04s/it]
 81%|████████  | 22666/28080 [44:47:04<10:37:35,  7.07s/it]
                                                           
{'loss': 0.5924, 'learning_rate': 4.718115027104658e-05, 'epoch': 9.68}

 81%|████████  | 22666/28080 [44:47:04<10:37:35,  7.07s/it]
 81%|████████  | 22667/28080 [44:47:12<10:40:18,  7.10s/it]
                                                           
{'loss': 0.5854, 'learning_rate': 4.716429241440434e-05, 'epoch': 9.68}

 81%|████████  | 22667/28080 [44:47:12<10:40:18,  7.10s/it]
 81%|████████  | 22668/28080 [44:47:19<10:40:00,  7.10s/it]
                                                           
{'loss': 0.6032, 'learning_rate': 4.714743725628196e-05, 'epoch': 9.68}

 81%|████████  | 22668/28080 [44:47:19<10:40:00,  7.10s/it]
 81%|████████  | 22669/28080 [44:47:26<10:37:08,  7.06s/it]
                                                           
{'loss': 0.6256, 'learning_rate': 4.71305847969036e-05, 'epoch': 9.68}

 81%|████████  | 22669/28080 [44:47:26<10:37:08,  7.06s/it]
 81%|████████  | 22670/28080 [44:47:33<10:37:43,  7.07s/it]
                                                           
{'loss': 0.6023, 'learning_rate': 4.711373503649358e-05, 'epoch': 9.68}

 81%|████████  | 22670/28080 [44:47:33<10:37:43,  7.07s/it]
 81%|████████  | 22671/28080 [44:47:40<10:34:22,  7.04s/it]
                                                           
{'loss': 0.609, 'learning_rate': 4.709688797527592e-05, 'epoch': 9.68}

 81%|████████  | 22671/28080 [44:47:40<10:34:22,  7.04s/it]
 81%|████████  | 22672/28080 [44:47:47<10:34:25,  7.04s/it]
                                                           
{'loss': 0.6021, 'learning_rate': 4.7080043613474983e-05, 'epoch': 9.69}

 81%|████████  | 22672/28080 [44:47:47<10:34:25,  7.04s/it]
 81%|████████  | 22673/28080 [44:47:54<10:34:04,  7.04s/it]
                                                           
{'loss': 0.6294, 'learning_rate': 4.706320195131461e-05, 'epoch': 9.69}

 81%|████████  | 22673/28080 [44:47:54<10:34:04,  7.04s/it]
 81%|████████  | 22674/28080 [44:48:01<10:37:59,  7.08s/it]
                                                           
{'loss': 0.6036, 'learning_rate': 4.7046362989019014e-05, 'epoch': 9.69}

 81%|████████  | 22674/28080 [44:48:01<10:37:59,  7.08s/it]
 81%|████████  | 22675/28080 [44:48:08<10:37:32,  7.08s/it]
                                                           
{'loss': 0.5755, 'learning_rate': 4.702952672681216e-05, 'epoch': 9.69}

 81%|████████  | 22675/28080 [44:48:08<10:37:32,  7.08s/it]
 81%|████████  | 22676/28080 [44:48:15<10:37:45,  7.08s/it]
                                                           
{'loss': 0.6147, 'learning_rate': 4.701269316491807e-05, 'epoch': 9.69}

 81%|████████  | 22676/28080 [44:48:15<10:37:45,  7.08s/it]
 81%|████████  | 22677/28080 [44:48:22<10:36:14,  7.07s/it]
                                                           
{'loss': 0.6047, 'learning_rate': 4.699586230356073e-05, 'epoch': 9.69}

 81%|████████  | 22677/28080 [44:48:22<10:36:14,  7.07s/it]
 81%|████████  | 22678/28080 [44:48:29<10:38:27,  7.09s/it]
                                                           
{'loss': 0.6056, 'learning_rate': 4.697903414296401e-05, 'epoch': 9.69}

 81%|████████  | 22678/28080 [44:48:29<10:38:27,  7.09s/it]
 81%|████████  | 22679/28080 [44:48:36<10:36:55,  7.08s/it]
                                                           
{'loss': 0.6046, 'learning_rate': 4.6962208683351715e-05, 'epoch': 9.69}

 81%|████████  | 22679/28080 [44:48:36<10:36:55,  7.08s/it]
 81%|████████  | 22680/28080 [44:48:43<10:37:03,  7.08s/it]
                                                           
{'loss': 0.6375, 'learning_rate': 4.694538592494785e-05, 'epoch': 9.69}

 81%|████████  | 22680/28080 [44:48:43<10:37:03,  7.08s/it]
 81%|████████  | 22681/28080 [44:48:51<10:36:21,  7.07s/it]
                                                           
{'loss': 0.6102, 'learning_rate': 4.692856586797614e-05, 'epoch': 9.69}

 81%|████████  | 22681/28080 [44:48:51<10:36:21,  7.07s/it]
 81%|████████  | 22682/28080 [44:48:58<10:38:23,  7.10s/it]
                                                           
{'loss': 0.6016, 'learning_rate': 4.691174851266036e-05, 'epoch': 9.69}

 81%|████████  | 22682/28080 [44:48:58<10:38:23,  7.10s/it]
 81%|████████  | 22683/28080 [44:49:05<10:37:35,  7.09s/it]
                                                           
{'loss': 0.6043, 'learning_rate': 4.689493385922419e-05, 'epoch': 9.69}

 81%|████████  | 22683/28080 [44:49:05<10:37:35,  7.09s/it]
 81%|████████  | 22684/28080 [44:49:12<10:36:14,  7.07s/it]
                                                           
{'loss': 0.6236, 'learning_rate': 4.687812190789145e-05, 'epoch': 9.69}

 81%|████████  | 22684/28080 [44:49:12<10:36:14,  7.07s/it]
 81%|████████  | 22685/28080 [44:49:19<10:36:57,  7.08s/it]
                                                           
{'loss': 0.6205, 'learning_rate': 4.6861312658885684e-05, 'epoch': 9.69}

 81%|████████  | 22685/28080 [44:49:19<10:36:57,  7.08s/it]
 81%|████████  | 22686/28080 [44:49:26<10:39:43,  7.12s/it]
                                                           
{'loss': 0.6178, 'learning_rate': 4.684450611243074e-05, 'epoch': 9.69}

 81%|████████  | 22686/28080 [44:49:26<10:39:43,  7.12s/it]
 81%|████████  | 22687/28080 [44:49:33<10:37:35,  7.09s/it]
                                                           
{'loss': 0.607, 'learning_rate': 4.682770226874991e-05, 'epoch': 9.69}

 81%|████████  | 22687/28080 [44:49:33<10:37:35,  7.09s/it]
 81%|████████  | 22688/28080 [44:49:40<10:33:32,  7.05s/it]
                                                           
{'loss': 0.6089, 'learning_rate': 4.681090112806696e-05, 'epoch': 9.69}

 81%|████████  | 22688/28080 [44:49:40<10:33:32,  7.05s/it]
 81%|████████  | 22689/28080 [44:49:47<10:34:57,  7.07s/it]
                                                           
{'loss': 0.5952, 'learning_rate': 4.6794102690605354e-05, 'epoch': 9.69}

 81%|████████  | 22689/28080 [44:49:47<10:34:57,  7.07s/it]
 81%|████████  | 22690/28080 [44:49:54<10:37:55,  7.10s/it]
                                                           
{'loss': 0.599, 'learning_rate': 4.677730695658852e-05, 'epoch': 9.69}

 81%|████████  | 22690/28080 [44:49:54<10:37:55,  7.10s/it]
 81%|████████  | 22691/28080 [44:50:02<10:40:57,  7.14s/it]
                                                           
{'loss': 0.5845, 'learning_rate': 4.676051392624009e-05, 'epoch': 9.69}

 81%|████████  | 22691/28080 [44:50:02<10:40:57,  7.14s/it]
 81%|████████  | 22692/28080 [44:50:09<10:40:51,  7.14s/it]
                                                           
{'loss': 0.6239, 'learning_rate': 4.674372359978321e-05, 'epoch': 9.69}

 81%|████████  | 22692/28080 [44:50:09<10:40:51,  7.14s/it]
 81%|████████  | 22693/28080 [44:50:16<10:39:01,  7.12s/it]
                                                           
{'loss': 0.5797, 'learning_rate': 4.6726935977441486e-05, 'epoch': 9.69}

 81%|████████  | 22693/28080 [44:50:16<10:39:01,  7.12s/it]
 81%|████████  | 22694/28080 [44:50:23<10:36:03,  7.09s/it]
                                                           
{'loss': 0.6187, 'learning_rate': 4.67101510594381e-05, 'epoch': 9.69}

 81%|████████  | 22694/28080 [44:50:23<10:36:03,  7.09s/it]
 81%|████████  | 22695/28080 [44:50:30<10:36:58,  7.10s/it]
                                                           
{'loss': 0.5954, 'learning_rate': 4.6693368845996506e-05, 'epoch': 9.7}

 81%|████████  | 22695/28080 [44:50:30<10:36:58,  7.10s/it]
 81%|████████  | 22696/28080 [44:50:37<10:37:26,  7.10s/it]
                                                           
{'loss': 0.6064, 'learning_rate': 4.667658933733987e-05, 'epoch': 9.7}

 81%|████████  | 22696/28080 [44:50:37<10:37:26,  7.10s/it]
 81%|████████  | 22697/28080 [44:50:44<10:37:10,  7.10s/it]
                                                           
{'loss': 0.5866, 'learning_rate': 4.6659812533691475e-05, 'epoch': 9.7}

 81%|████████  | 22697/28080 [44:50:44<10:37:10,  7.10s/it]
 81%|████████  | 22698/28080 [44:50:51<10:38:23,  7.12s/it]
                                                           
{'loss': 0.6087, 'learning_rate': 4.6643038435274454e-05, 'epoch': 9.7}

 81%|████████  | 22698/28080 [44:50:51<10:38:23,  7.12s/it]
 81%|████████  | 22699/28080 [44:50:58<10:35:54,  7.09s/it]
                                                           
{'loss': 0.5973, 'learning_rate': 4.662626704231204e-05, 'epoch': 9.7}

 81%|████████  | 22699/28080 [44:50:58<10:35:54,  7.09s/it]
 81%|████████  | 22700/28080 [44:51:05<10:36:46,  7.10s/it]
                                                           
{'loss': 0.6093, 'learning_rate': 4.660949835502737e-05, 'epoch': 9.7}

 81%|████████  | 22700/28080 [44:51:05<10:36:46,  7.10s/it]
 81%|████████  | 22701/28080 [44:51:12<10:34:37,  7.08s/it]
                                                           
{'loss': 0.6237, 'learning_rate': 4.659273237364348e-05, 'epoch': 9.7}

 81%|████████  | 22701/28080 [44:51:12<10:34:37,  7.08s/it]
 81%|████████  | 22702/28080 [44:51:20<10:35:34,  7.09s/it]
                                                           
{'loss': 0.6104, 'learning_rate': 4.657596909838338e-05, 'epoch': 9.7}

 81%|████████  | 22702/28080 [44:51:20<10:35:34,  7.09s/it]
 81%|████████  | 22703/28080 [44:51:27<10:36:56,  7.11s/it]
                                                           
{'loss': 0.5848, 'learning_rate': 4.655920852947021e-05, 'epoch': 9.7}

 81%|████████  | 22703/28080 [44:51:27<10:36:56,  7.11s/it]
 81%|████████  | 22704/28080 [44:51:34<10:37:01,  7.11s/it]
                                                           
{'loss': 0.5991, 'learning_rate': 4.654245066712684e-05, 'epoch': 9.7}

 81%|████████  | 22704/28080 [44:51:34<10:37:01,  7.11s/it]
 81%|████████  | 22705/28080 [44:51:41<10:34:27,  7.08s/it]
                                                           
{'loss': 0.6136, 'learning_rate': 4.6525695511576316e-05, 'epoch': 9.7}

 81%|████████  | 22705/28080 [44:51:41<10:34:27,  7.08s/it]
 81%|████████  | 22706/28080 [44:51:48<10:37:05,  7.11s/it]
                                                           
{'loss': 0.5906, 'learning_rate': 4.6508943063041513e-05, 'epoch': 9.7}

 81%|████████  | 22706/28080 [44:51:48<10:37:05,  7.11s/it]
 81%|████████  | 22707/28080 [44:51:55<10:37:38,  7.12s/it]
                                                           
{'loss': 0.6075, 'learning_rate': 4.6492193321745285e-05, 'epoch': 9.7}

 81%|████████  | 22707/28080 [44:51:55<10:37:38,  7.12s/it]
 81%|████████  | 22708/28080 [44:52:02<10:37:06,  7.12s/it]
                                                           
{'loss': 0.6105, 'learning_rate': 4.647544628791042e-05, 'epoch': 9.7}

 81%|████████  | 22708/28080 [44:52:02<10:37:06,  7.12s/it]
 81%|████████  | 22709/28080 [44:52:09<10:37:14,  7.12s/it]
                                                           
{'loss': 0.6098, 'learning_rate': 4.645870196175983e-05, 'epoch': 9.7}

 81%|████████  | 22709/28080 [44:52:09<10:37:14,  7.12s/it]
 81%|████████  | 22710/28080 [44:52:16<10:34:10,  7.09s/it]
                                                           
{'loss': 0.5988, 'learning_rate': 4.644196034351625e-05, 'epoch': 9.7}

 81%|████████  | 22710/28080 [44:52:16<10:34:10,  7.09s/it]
 81%|████████  | 22711/28080 [44:52:24<10:35:03,  7.10s/it]
                                                           
{'loss': 0.6036, 'learning_rate': 4.642522143340236e-05, 'epoch': 9.7}

 81%|████████  | 22711/28080 [44:52:24<10:35:03,  7.10s/it]
 81%|████████  | 22712/28080 [44:52:31<10:35:41,  7.11s/it]
                                                           
{'loss': 0.616, 'learning_rate': 4.6408485231640845e-05, 'epoch': 9.7}

 81%|████████  | 22712/28080 [44:52:31<10:35:41,  7.11s/it]
 81%|████████  | 22713/28080 [44:52:38<10:34:02,  7.09s/it]
                                                           
{'loss': 0.601, 'learning_rate': 4.639175173845445e-05, 'epoch': 9.7}

 81%|████████  | 22713/28080 [44:52:38<10:34:02,  7.09s/it]
 81%|████████  | 22714/28080 [44:52:45<10:36:05,  7.11s/it]
                                                           
{'loss': 0.5984, 'learning_rate': 4.637502095406576e-05, 'epoch': 9.7}

 81%|████████  | 22714/28080 [44:52:45<10:36:05,  7.11s/it]
 81%|████████  | 22715/28080 [44:52:52<10:38:43,  7.14s/it]
                                                           
{'loss': 0.6095, 'learning_rate': 4.6358292878697334e-05, 'epoch': 9.7}

 81%|████████  | 22715/28080 [44:52:52<10:38:43,  7.14s/it]
 81%|████████  | 22716/28080 [44:52:59<10:36:23,  7.12s/it]
                                                           
{'loss': 0.6101, 'learning_rate': 4.6341567512571736e-05, 'epoch': 9.7}

 81%|████████  | 22716/28080 [44:52:59<10:36:23,  7.12s/it]
 81%|████████  | 22717/28080 [44:53:06<10:37:50,  7.14s/it]
                                                           
{'loss': 0.6088, 'learning_rate': 4.632484485591143e-05, 'epoch': 9.7}

 81%|████████  | 22717/28080 [44:53:06<10:37:50,  7.14s/it]
 81%|████████  | 22718/28080 [44:53:13<10:36:35,  7.12s/it]
                                                           
{'loss': 0.605, 'learning_rate': 4.6308124908938984e-05, 'epoch': 9.7}

 81%|████████  | 22718/28080 [44:53:13<10:36:35,  7.12s/it]
 81%|████████  | 22719/28080 [44:53:20<10:33:59,  7.10s/it]
                                                           
{'loss': 0.599, 'learning_rate': 4.6291407671876754e-05, 'epoch': 9.71}

 81%|████████  | 22719/28080 [44:53:20<10:33:59,  7.10s/it]
 81%|████████  | 22720/28080 [44:53:28<10:32:25,  7.08s/it]
                                                           
{'loss': 0.5933, 'learning_rate': 4.6274693144947314e-05, 'epoch': 9.71}

 81%|████████  | 22720/28080 [44:53:28<10:32:25,  7.08s/it]
 81%|████████  | 22721/28080 [44:53:35<10:33:04,  7.09s/it]
                                                           
{'loss': 0.6026, 'learning_rate': 4.625798132837278e-05, 'epoch': 9.71}

 81%|████████  | 22721/28080 [44:53:35<10:33:04,  7.09s/it]
 81%|████████  | 22722/28080 [44:53:42<10:31:57,  7.08s/it]
                                                           
{'loss': 0.6051, 'learning_rate': 4.624127222237568e-05, 'epoch': 9.71}

 81%|████████  | 22722/28080 [44:53:42<10:31:57,  7.08s/it]
 81%|████████  | 22723/28080 [44:53:49<10:30:30,  7.06s/it]
                                                           
{'loss': 0.5894, 'learning_rate': 4.6224565827178185e-05, 'epoch': 9.71}

 81%|████████  | 22723/28080 [44:53:49<10:30:30,  7.06s/it]
 81%|████████  | 22724/28080 [44:53:56<10:32:43,  7.09s/it]
                                                           
{'loss': 0.6073, 'learning_rate': 4.620786214300268e-05, 'epoch': 9.71}

 81%|████████  | 22724/28080 [44:53:56<10:32:43,  7.09s/it]
 81%|████████  | 22725/28080 [44:54:03<10:37:20,  7.14s/it]
                                                           
{'loss': 0.6136, 'learning_rate': 4.6191161170071326e-05, 'epoch': 9.71}

 81%|████████  | 22725/28080 [44:54:03<10:37:20,  7.14s/it]
 81%|████████  | 22726/28080 [44:54:10<10:35:36,  7.12s/it]
                                                           
{'loss': 0.607, 'learning_rate': 4.617446290860633e-05, 'epoch': 9.71}

 81%|████████  | 22726/28080 [44:54:10<10:35:36,  7.12s/it]
 81%|████████  | 22727/28080 [44:54:17<10:33:07,  7.10s/it]
                                                           
{'loss': 0.5998, 'learning_rate': 4.6157767358829764e-05, 'epoch': 9.71}

 81%|████████  | 22727/28080 [44:54:17<10:33:07,  7.10s/it]
 81%|████████  | 22728/28080 [44:54:24<10:33:34,  7.10s/it]
                                                           
{'loss': 0.6236, 'learning_rate': 4.614107452096386e-05, 'epoch': 9.71}

 81%|████████  | 22728/28080 [44:54:24<10:33:34,  7.10s/it]
 81%|████████  | 22729/28080 [44:54:31<10:33:53,  7.11s/it]
                                                           
{'loss': 0.588, 'learning_rate': 4.6124384395230647e-05, 'epoch': 9.71}

 81%|████████  | 22729/28080 [44:54:31<10:33:53,  7.11s/it]
 81%|████████  | 22730/28080 [44:54:38<10:31:03,  7.08s/it]
                                                           
{'loss': 0.6165, 'learning_rate': 4.610769698185219e-05, 'epoch': 9.71}

 81%|████████  | 22730/28080 [44:54:38<10:31:03,  7.08s/it]
 81%|████████  | 22731/28080 [44:54:46<10:30:18,  7.07s/it]
                                                           
{'loss': 0.6058, 'learning_rate': 4.609101228105039e-05, 'epoch': 9.71}

 81%|████████  | 22731/28080 [44:54:46<10:30:18,  7.07s/it]
 81%|████████  | 22732/28080 [44:54:53<10:29:29,  7.06s/it]
                                                           
{'loss': 0.62, 'learning_rate': 4.607433029304739e-05, 'epoch': 9.71}

 81%|████████  | 22732/28080 [44:54:53<10:29:29,  7.06s/it]
 81%|████████  | 22733/28080 [44:55:00<10:29:42,  7.07s/it]
                                                           
{'loss': 0.5923, 'learning_rate': 4.6057651018065e-05, 'epoch': 9.71}

 81%|████████  | 22733/28080 [44:55:00<10:29:42,  7.07s/it]
 81%|████████  | 22734/28080 [44:55:07<10:30:51,  7.08s/it]
                                                           
{'loss': 0.6319, 'learning_rate': 4.604097445632527e-05, 'epoch': 9.71}

 81%|████████  | 22734/28080 [44:55:07<10:30:51,  7.08s/it]
 81%|████████  | 22735/28080 [44:55:14<10:32:39,  7.10s/it]
                                                           
{'loss': 0.6083, 'learning_rate': 4.602430060804985e-05, 'epoch': 9.71}

 81%|████████  | 22735/28080 [44:55:14<10:32:39,  7.10s/it]
 81%|████████  | 22736/28080 [44:55:21<10:30:18,  7.08s/it]
                                                           
{'loss': 0.6236, 'learning_rate': 4.600762947346074e-05, 'epoch': 9.71}

 81%|████████  | 22736/28080 [44:55:21<10:30:18,  7.08s/it]
 81%|████████  | 22737/28080 [44:55:28<10:30:07,  7.08s/it]
                                                           
{'loss': 0.5961, 'learning_rate': 4.599096105277961e-05, 'epoch': 9.71}

 81%|████████  | 22737/28080 [44:55:28<10:30:07,  7.08s/it]
 81%|████████  | 22738/28080 [44:55:35<10:32:12,  7.10s/it]
                                                           
{'loss': 0.625, 'learning_rate': 4.5974295346228326e-05, 'epoch': 9.71}

 81%|████████  | 22738/28080 [44:55:35<10:32:12,  7.10s/it]
 81%|████████  | 22739/28080 [44:55:42<10:33:49,  7.12s/it]
                                                           
{'loss': 0.5941, 'learning_rate': 4.595763235402864e-05, 'epoch': 9.71}

 81%|████████  | 22739/28080 [44:55:42<10:33:49,  7.12s/it]
 81%|████████  | 22740/28080 [44:55:49<10:31:10,  7.09s/it]
                                                           
{'loss': 0.6153, 'learning_rate': 4.594097207640202e-05, 'epoch': 9.71}

 81%|████████  | 22740/28080 [44:55:49<10:31:10,  7.09s/it]
 81%|████████  | 22741/28080 [44:55:56<10:29:45,  7.08s/it]
                                                           
{'loss': 0.6034, 'learning_rate': 4.592431451357032e-05, 'epoch': 9.71}

 81%|████████  | 22741/28080 [44:55:56<10:29:45,  7.08s/it]
 81%|████████  | 22742/28080 [44:56:03<10:29:55,  7.08s/it]
                                                           
{'loss': 0.6021, 'learning_rate': 4.5907659665755024e-05, 'epoch': 9.72}

 81%|████████  | 22742/28080 [44:56:03<10:29:55,  7.08s/it]
 81%|████████  | 22743/28080 [44:56:11<10:33:53,  7.13s/it]
                                                           
{'loss': 0.6068, 'learning_rate': 4.589100753317782e-05, 'epoch': 9.72}

 81%|████████  | 22743/28080 [44:56:11<10:33:53,  7.13s/it]
 81%|████████  | 22744/28080 [44:56:18<10:34:01,  7.13s/it]
                                                           
{'loss': 0.6081, 'learning_rate': 4.5874358116060225e-05, 'epoch': 9.72}

 81%|████████  | 22744/28080 [44:56:18<10:34:01,  7.13s/it]
 81%|████████  | 22745/28080 [44:56:25<10:33:00,  7.12s/it]
                                                           
{'loss': 0.6024, 'learning_rate': 4.585771141462367e-05, 'epoch': 9.72}

 81%|████████  | 22745/28080 [44:56:25<10:33:00,  7.12s/it]
 81%|████████  | 22746/28080 [44:56:32<10:31:44,  7.11s/it]
                                                           
{'loss': 0.6173, 'learning_rate': 4.584106742908961e-05, 'epoch': 9.72}

 81%|████████  | 22746/28080 [44:56:32<10:31:44,  7.11s/it]
 81%|████████  | 22747/28080 [44:56:39<10:31:28,  7.10s/it]
                                                           
{'loss': 0.6056, 'learning_rate': 4.582442615967961e-05, 'epoch': 9.72}

 81%|████████  | 22747/28080 [44:56:39<10:31:28,  7.10s/it]
 81%|████████  | 22748/28080 [44:56:46<10:31:18,  7.10s/it]
                                                           
{'loss': 0.588, 'learning_rate': 4.580778760661497e-05, 'epoch': 9.72}

 81%|████████  | 22748/28080 [44:56:46<10:31:18,  7.10s/it]
 81%|████████  | 22749/28080 [44:56:53<10:32:30,  7.12s/it]
                                                           
{'loss': 0.5983, 'learning_rate': 4.579115177011706e-05, 'epoch': 9.72}

 81%|████████  | 22749/28080 [44:56:53<10:32:30,  7.12s/it]
 81%|████████  | 22750/28080 [44:57:01<10:36:38,  7.17s/it]
                                                           
{'loss': 0.5979, 'learning_rate': 4.577451865040713e-05, 'epoch': 9.72}

 81%|████████  | 22750/28080 [44:57:01<10:36:38,  7.17s/it]
 81%|████████  | 22751/28080 [44:57:08<10:34:36,  7.15s/it]
                                                           
{'loss': 0.6165, 'learning_rate': 4.575788824770663e-05, 'epoch': 9.72}

 81%|████████  | 22751/28080 [44:57:08<10:34:36,  7.15s/it]
 81%|████████  | 22752/28080 [44:57:15<10:33:19,  7.13s/it]
                                                           
{'loss': 0.5853, 'learning_rate': 4.574126056223665e-05, 'epoch': 9.72}

 81%|████████  | 22752/28080 [44:57:15<10:33:19,  7.13s/it]
 81%|████████  | 22753/28080 [44:57:22<10:34:05,  7.14s/it]
                                                           
{'loss': 0.6185, 'learning_rate': 4.5724635594218605e-05, 'epoch': 9.72}

 81%|████████  | 22753/28080 [44:57:22<10:34:05,  7.14s/it]
 81%|████████  | 22754/28080 [44:57:29<10:33:31,  7.14s/it]
                                                           
{'loss': 0.5971, 'learning_rate': 4.570801334387339e-05, 'epoch': 9.72}

 81%|████████  | 22754/28080 [44:57:29<10:33:31,  7.14s/it]
 81%|████████  | 22755/28080 [44:57:36<10:32:33,  7.13s/it]
                                                           
{'loss': 0.5972, 'learning_rate': 4.5691393811422397e-05, 'epoch': 9.72}

 81%|████████  | 22755/28080 [44:57:36<10:32:33,  7.13s/it]
 81%|████████  | 22756/28080 [44:57:43<10:33:14,  7.14s/it]
                                                           
{'loss': 0.5782, 'learning_rate': 4.5674776997086555e-05, 'epoch': 9.72}

 81%|████████  | 22756/28080 [44:57:43<10:33:14,  7.14s/it]
 81%|████████  | 22757/28080 [44:57:51<10:32:41,  7.13s/it]
                                                           
{'loss': 0.5745, 'learning_rate': 4.56581629010871e-05, 'epoch': 9.72}

 81%|████████  | 22757/28080 [44:57:51<10:32:41,  7.13s/it]
 81%|████████  | 22758/28080 [44:57:58<10:31:22,  7.12s/it]
                                                           
{'loss': 0.5953, 'learning_rate': 4.564155152364496e-05, 'epoch': 9.72}

 81%|████████  | 22758/28080 [44:57:58<10:31:22,  7.12s/it]
 81%|████████  | 22759/28080 [44:58:05<10:31:32,  7.12s/it]
                                                           
{'loss': 0.5805, 'learning_rate': 4.5624942864981175e-05, 'epoch': 9.72}

 81%|████████  | 22759/28080 [44:58:05<10:31:32,  7.12s/it]
 81%|████████  | 22760/28080 [44:58:12<10:31:38,  7.12s/it]
                                                           
{'loss': 0.5917, 'learning_rate': 4.560833692531657e-05, 'epoch': 9.72}

 81%|████████  | 22760/28080 [44:58:12<10:31:38,  7.12s/it]
 81%|████████  | 22761/28080 [44:58:19<10:27:11,  7.07s/it]
                                                           
{'loss': 0.6091, 'learning_rate': 4.5591733704872294e-05, 'epoch': 9.72}

 81%|████████  | 22761/28080 [44:58:19<10:27:11,  7.07s/it]
 81%|████████  | 22762/28080 [44:58:26<10:27:19,  7.08s/it]
                                                           
{'loss': 0.6105, 'learning_rate': 4.557513320386911e-05, 'epoch': 9.72}

 81%|████████  | 22762/28080 [44:58:26<10:27:19,  7.08s/it]
 81%|████████  | 22763/28080 [44:58:33<10:28:36,  7.09s/it]
                                                           
{'loss': 0.6014, 'learning_rate': 4.555853542252789e-05, 'epoch': 9.72}

 81%|████████  | 22763/28080 [44:58:33<10:28:36,  7.09s/it]
 81%|████████  | 22764/28080 [44:58:40<10:32:41,  7.14s/it]
                                                           
{'loss': 0.5985, 'learning_rate': 4.554194036106943e-05, 'epoch': 9.72}

 81%|████████  | 22764/28080 [44:58:40<10:32:41,  7.14s/it]
 81%|████████  | 22765/28080 [44:58:47<10:31:53,  7.13s/it]
                                                           
{'loss': 0.5895, 'learning_rate': 4.5525348019714476e-05, 'epoch': 9.72}

 81%|████████  | 22765/28080 [44:58:47<10:31:53,  7.13s/it]
 81%|████████  | 22766/28080 [44:58:55<10:32:48,  7.14s/it]
                                                           
{'loss': 0.6115, 'learning_rate': 4.550875839868387e-05, 'epoch': 9.73}

 81%|████████  | 22766/28080 [44:58:55<10:32:48,  7.14s/it]
 81%|████████  | 22767/28080 [44:59:02<10:29:37,  7.11s/it]
                                                           
{'loss': 0.6136, 'learning_rate': 4.549217149819823e-05, 'epoch': 9.73}

 81%|████████  | 22767/28080 [44:59:02<10:29:37,  7.11s/it]
 81%|████████  | 22768/28080 [44:59:09<10:31:22,  7.13s/it]
                                                           
{'loss': 0.6145, 'learning_rate': 4.54755873184784e-05, 'epoch': 9.73}

 81%|████████  | 22768/28080 [44:59:09<10:31:22,  7.13s/it]
 81%|████████  | 22769/28080 [44:59:16<10:32:02,  7.14s/it]
                                                           
{'loss': 0.6058, 'learning_rate': 4.545900585974474e-05, 'epoch': 9.73}

 81%|████████  | 22769/28080 [44:59:16<10:32:02,  7.14s/it]
 81%|████████  | 22770/28080 [44:59:23<10:29:47,  7.12s/it]
                                                           
{'loss': 0.6132, 'learning_rate': 4.544242712221805e-05, 'epoch': 9.73}

 81%|████████  | 22770/28080 [44:59:23<10:29:47,  7.12s/it]
 81%|████████  | 22771/28080 [44:59:30<10:32:02,  7.14s/it]
                                                           
{'loss': 0.5943, 'learning_rate': 4.5425851106118796e-05, 'epoch': 9.73}

 81%|████████  | 22771/28080 [44:59:30<10:32:02,  7.14s/it]
 81%|████████  | 22772/28080 [44:59:37<10:33:25,  7.16s/it]
                                                           
{'loss': 0.615, 'learning_rate': 4.540927781166759e-05, 'epoch': 9.73}

 81%|████████  | 22772/28080 [44:59:37<10:33:25,  7.16s/it]
 81%|████████  | 22773/28080 [44:59:44<10:30:57,  7.13s/it]
                                                           
{'loss': 0.5921, 'learning_rate': 4.53927072390849e-05, 'epoch': 9.73}

 81%|████████  | 22773/28080 [44:59:45<10:30:57,  7.13s/it]
 81%|████████  | 22774/28080 [44:59:52<10:33:07,  7.16s/it]
                                                           
{'loss': 0.5911, 'learning_rate': 4.5376139388591144e-05, 'epoch': 9.73}

 81%|████████  | 22774/28080 [44:59:52<10:33:07,  7.16s/it]
 81%|████████  | 22775/28080 [44:59:59<10:28:48,  7.11s/it]
                                                           
{'loss': 0.5996, 'learning_rate': 4.535957426040668e-05, 'epoch': 9.73}

 81%|████████  | 22775/28080 [44:59:59<10:28:48,  7.11s/it]
 81%|████████  | 22776/28080 [45:00:06<10:27:29,  7.10s/it]
                                                           
{'loss': 0.5959, 'learning_rate': 4.534301185475204e-05, 'epoch': 9.73}

 81%|████████  | 22776/28080 [45:00:06<10:27:29,  7.10s/it]
 81%|████████  | 22777/28080 [45:00:13<10:26:24,  7.09s/it]
                                                           
{'loss': 0.5898, 'learning_rate': 4.53264521718475e-05, 'epoch': 9.73}

 81%|████████  | 22777/28080 [45:00:13<10:26:24,  7.09s/it]
 81%|████████  | 22778/28080 [45:00:20<10:27:34,  7.10s/it]
                                                           
{'loss': 0.5817, 'learning_rate': 4.5309895211913363e-05, 'epoch': 9.73}

 81%|████████  | 22778/28080 [45:00:20<10:27:34,  7.10s/it]
 81%|████████  | 22779/28080 [45:00:27<10:26:25,  7.09s/it]
                                                           
{'loss': 0.5971, 'learning_rate': 4.529334097516982e-05, 'epoch': 9.73}

 81%|████████  | 22779/28080 [45:00:27<10:26:25,  7.09s/it]
 81%|████████  | 22780/28080 [45:00:34<10:25:27,  7.08s/it]
                                                           
{'loss': 0.5928, 'learning_rate': 4.527678946183728e-05, 'epoch': 9.73}

 81%|████████  | 22780/28080 [45:00:34<10:25:27,  7.08s/it]
 81%|████████  | 22781/28080 [45:00:41<10:26:07,  7.09s/it]
                                                           
{'loss': 0.6114, 'learning_rate': 4.52602406721358e-05, 'epoch': 9.73}

 81%|████████  | 22781/28080 [45:00:41<10:26:07,  7.09s/it]
 81%|████████  | 22782/28080 [45:00:48<10:25:25,  7.08s/it]
                                                           
{'loss': 0.5948, 'learning_rate': 4.524369460628569e-05, 'epoch': 9.73}

 81%|████████  | 22782/28080 [45:00:48<10:25:25,  7.08s/it]
 81%|████████  | 22783/28080 [45:00:55<10:25:55,  7.09s/it]
                                                           
{'loss': 0.5995, 'learning_rate': 4.522715126450688e-05, 'epoch': 9.73}

 81%|████████  | 22783/28080 [45:00:55<10:25:55,  7.09s/it]
 81%|████████  | 22784/28080 [45:01:03<10:27:10,  7.11s/it]
                                                           
{'loss': 0.6049, 'learning_rate': 4.521061064701965e-05, 'epoch': 9.73}

 81%|████████  | 22784/28080 [45:01:03<10:27:10,  7.11s/it]
 81%|████████  | 22785/28080 [45:01:10<10:23:52,  7.07s/it]
                                                           
{'loss': 0.6182, 'learning_rate': 4.5194072754043886e-05, 'epoch': 9.73}

 81%|████████  | 22785/28080 [45:01:10<10:23:52,  7.07s/it]
 81%|████████  | 22786/28080 [45:01:17<10:25:35,  7.09s/it]
                                                           
{'loss': 0.5972, 'learning_rate': 4.517753758579976e-05, 'epoch': 9.73}

 81%|████████  | 22786/28080 [45:01:17<10:25:35,  7.09s/it]
 81%|████████  | 22787/28080 [45:01:24<10:26:10,  7.10s/it]
                                                           
{'loss': 0.5912, 'learning_rate': 4.5161005142507205e-05, 'epoch': 9.73}

 81%|████████  | 22787/28080 [45:01:24<10:26:10,  7.10s/it]
 81%|████████  | 22788/28080 [45:01:31<10:25:45,  7.09s/it]
                                                           
{'loss': 0.6129, 'learning_rate': 4.514447542438615e-05, 'epoch': 9.73}

 81%|████████  | 22788/28080 [45:01:31<10:25:45,  7.09s/it]
 81%|████████  | 22789/28080 [45:01:38<10:25:03,  7.09s/it]
                                                           
{'loss': 0.6023, 'learning_rate': 4.512794843165652e-05, 'epoch': 9.74}

 81%|████████  | 22789/28080 [45:01:38<10:25:03,  7.09s/it]
 81%|████████  | 22790/28080 [45:01:45<10:23:01,  7.07s/it]
                                                           
{'loss': 0.6165, 'learning_rate': 4.511142416453812e-05, 'epoch': 9.74}

 81%|████████  | 22790/28080 [45:01:45<10:23:01,  7.07s/it]
 81%|████████  | 22791/28080 [45:01:52<10:22:41,  7.06s/it]
                                                           
{'loss': 0.5931, 'learning_rate': 4.509490262325089e-05, 'epoch': 9.74}

 81%|████████  | 22791/28080 [45:01:52<10:22:41,  7.06s/it]
 81%|████████  | 22792/28080 [45:01:59<10:22:52,  7.07s/it]
                                                           
{'loss': 0.6067, 'learning_rate': 4.507838380801463e-05, 'epoch': 9.74}

 81%|████████  | 22792/28080 [45:01:59<10:22:52,  7.07s/it]
 81%|████████  | 22793/28080 [45:02:06<10:24:49,  7.09s/it]
                                                           
{'loss': 0.6012, 'learning_rate': 4.5061867719049047e-05, 'epoch': 9.74}

 81%|████████  | 22793/28080 [45:02:06<10:24:49,  7.09s/it]
 81%|████████  | 22794/28080 [45:02:13<10:24:22,  7.09s/it]
                                                           
{'loss': 0.6162, 'learning_rate': 4.504535435657381e-05, 'epoch': 9.74}

 81%|████████  | 22794/28080 [45:02:13<10:24:22,  7.09s/it]
 81%|████████  | 22795/28080 [45:02:20<10:25:08,  7.10s/it]
                                                           
{'loss': 0.5945, 'learning_rate': 4.5028843720808784e-05, 'epoch': 9.74}

 81%|████████  | 22795/28080 [45:02:20<10:25:08,  7.10s/it]
 81%|████████  | 22796/28080 [45:02:27<10:24:01,  7.09s/it]
                                                           
{'loss': 0.5898, 'learning_rate': 4.5012335811973534e-05, 'epoch': 9.74}

 81%|████████  | 22796/28080 [45:02:27<10:24:01,  7.09s/it]
 81%|████████  | 22797/28080 [45:02:35<10:25:54,  7.11s/it]
                                                           
{'loss': 0.6185, 'learning_rate': 4.499583063028767e-05, 'epoch': 9.74}

 81%|████████  | 22797/28080 [45:02:35<10:25:54,  7.11s/it]
 81%|████████  | 22798/28080 [45:02:42<10:25:32,  7.11s/it]
                                                           
{'loss': 0.6032, 'learning_rate': 4.4979328175970724e-05, 'epoch': 9.74}

 81%|████████  | 22798/28080 [45:02:42<10:25:32,  7.11s/it]
 81%|████████  | 22799/28080 [45:02:49<10:23:57,  7.09s/it]
                                                           
{'loss': 0.5898, 'learning_rate': 4.4962828449242374e-05, 'epoch': 9.74}

 81%|████████  | 22799/28080 [45:02:49<10:23:57,  7.09s/it]
 81%|████████  | 22800/28080 [45:02:56<10:24:11,  7.09s/it]
                                                           
{'loss': 0.6261, 'learning_rate': 4.494633145032201e-05, 'epoch': 9.74}

 81%|████████  | 22800/28080 [45:02:56<10:24:11,  7.09s/it]
 81%|████████  | 22801/28080 [45:03:03<10:27:21,  7.13s/it]
                                                           
{'loss': 0.609, 'learning_rate': 4.492983717942928e-05, 'epoch': 9.74}

 81%|████████  | 22801/28080 [45:03:03<10:27:21,  7.13s/it]
 81%|████████  | 22802/28080 [45:03:10<10:28:44,  7.15s/it]
                                                           
{'loss': 0.6117, 'learning_rate': 4.491334563678337e-05, 'epoch': 9.74}

 81%|████████  | 22802/28080 [45:03:10<10:28:44,  7.15s/it]
 81%|████████  | 22803/28080 [45:03:17<10:27:37,  7.14s/it]
                                                           
{'loss': 0.5995, 'learning_rate': 4.4896856822603914e-05, 'epoch': 9.74}

 81%|████████  | 22803/28080 [45:03:17<10:27:37,  7.14s/it]
 81%|████████  | 22804/28080 [45:03:25<10:27:08,  7.13s/it]
                                                           
{'loss': 0.6079, 'learning_rate': 4.4880370737110096e-05, 'epoch': 9.74}

 81%|████████  | 22804/28080 [45:03:25<10:27:08,  7.13s/it]
 81%|████████  | 22805/28080 [45:03:32<10:23:04,  7.09s/it]
                                                           
{'loss': 0.6274, 'learning_rate': 4.4863887380521414e-05, 'epoch': 9.74}

 81%|████████  | 22805/28080 [45:03:32<10:23:04,  7.09s/it]
 81%|████████  | 22806/28080 [45:03:39<10:23:45,  7.10s/it]
                                                           
{'loss': 0.599, 'learning_rate': 4.484740675305707e-05, 'epoch': 9.74}

 81%|████████  | 22806/28080 [45:03:39<10:23:45,  7.10s/it]
 81%|████████  | 22807/28080 [45:03:46<10:25:20,  7.12s/it]
                                                           
{'loss': 0.6251, 'learning_rate': 4.483092885493636e-05, 'epoch': 9.74}

 81%|████████  | 22807/28080 [45:03:46<10:25:20,  7.12s/it]
 81%|████████  | 22808/28080 [45:03:53<10:23:05,  7.09s/it]
                                                           
{'loss': 0.6178, 'learning_rate': 4.4814453686378404e-05, 'epoch': 9.74}

 81%|████████  | 22808/28080 [45:03:53<10:23:05,  7.09s/it]
 81%|████████  | 22809/28080 [45:04:00<10:25:06,  7.12s/it]
                                                           
{'loss': 0.5973, 'learning_rate': 4.479798124760251e-05, 'epoch': 9.74}

 81%|████████  | 22809/28080 [45:04:00<10:25:06,  7.12s/it]
 81%|████████  | 22810/28080 [45:04:07<10:21:22,  7.07s/it]
                                                           
{'loss': 0.5949, 'learning_rate': 4.4781511538827787e-05, 'epoch': 9.74}

 81%|████████  | 22810/28080 [45:04:07<10:21:22,  7.07s/it]
 81%|████████  | 22811/28080 [45:04:14<10:22:53,  7.09s/it]
                                                           
{'loss': 0.5912, 'learning_rate': 4.476504456027336e-05, 'epoch': 9.74}

 81%|████████  | 22811/28080 [45:04:14<10:22:53,  7.09s/it]
 81%|████████  | 22812/28080 [45:04:21<10:23:28,  7.10s/it]
                                                           
{'loss': 0.5882, 'learning_rate': 4.4748580312158196e-05, 'epoch': 9.75}

 81%|████████  | 22812/28080 [45:04:21<10:23:28,  7.10s/it]
 81%|████████  | 22813/28080 [45:04:28<10:22:40,  7.09s/it]
                                                           
{'loss': 0.624, 'learning_rate': 4.473211879470152e-05, 'epoch': 9.75}

 81%|████████  | 22813/28080 [45:04:28<10:22:40,  7.09s/it]
 81%|████████  | 22814/28080 [45:04:35<10:21:51,  7.09s/it]
                                                           
{'loss': 0.615, 'learning_rate': 4.471566000812222e-05, 'epoch': 9.75}

 81%|████████  | 22814/28080 [45:04:35<10:21:51,  7.09s/it]
 81%|████████▏ | 22815/28080 [45:04:43<10:22:47,  7.10s/it]
                                                           
{'loss': 0.587, 'learning_rate': 4.4699203952639296e-05, 'epoch': 9.75}

 81%|████████▏ | 22815/28080 [45:04:43<10:22:47,  7.10s/it]
 81%|████████▏ | 22816/28080 [45:04:50<10:25:10,  7.13s/it]
                                                           
{'loss': 0.624, 'learning_rate': 4.468275062847163e-05, 'epoch': 9.75}

 81%|████████▏ | 22816/28080 [45:04:50<10:25:10,  7.13s/it]
 81%|████████▏ | 22817/28080 [45:04:57<10:26:07,  7.14s/it]
                                                           
{'loss': 0.6197, 'learning_rate': 4.466630003583813e-05, 'epoch': 9.75}

 81%|████████▏ | 22817/28080 [45:04:57<10:26:07,  7.14s/it]
 81%|████████▏ | 22818/28080 [45:05:04<10:25:02,  7.13s/it]
                                                           
{'loss': 0.6093, 'learning_rate': 4.4649852174957735e-05, 'epoch': 9.75}

 81%|████████▏ | 22818/28080 [45:05:04<10:25:02,  7.13s/it]
 81%|████████▏ | 22819/28080 [45:05:11<10:25:25,  7.13s/it]
                                                           
{'loss': 0.5935, 'learning_rate': 4.463340704604913e-05, 'epoch': 9.75}

 81%|████████▏ | 22819/28080 [45:05:11<10:25:25,  7.13s/it]
 81%|████████▏ | 22820/28080 [45:05:18<10:25:42,  7.14s/it]
                                                           
{'loss': 0.6069, 'learning_rate': 4.461696464933124e-05, 'epoch': 9.75}

 81%|████████▏ | 22820/28080 [45:05:18<10:25:42,  7.14s/it]
 81%|████████▏ | 22821/28080 [45:05:25<10:27:00,  7.15s/it]
                                                           
{'loss': 0.6004, 'learning_rate': 4.460052498502276e-05, 'epoch': 9.75}

 81%|████████▏ | 22821/28080 [45:05:25<10:27:00,  7.15s/it]
 81%|████████▏ | 22822/28080 [45:05:33<10:27:03,  7.16s/it]
                                                           
{'loss': 0.6124, 'learning_rate': 4.458408805334241e-05, 'epoch': 9.75}

 81%|████████▏ | 22822/28080 [45:05:33<10:27:03,  7.16s/it]
 81%|████████▏ | 22823/28080 [45:05:40<10:27:01,  7.16s/it]
                                                           
{'loss': 0.6003, 'learning_rate': 4.456765385450878e-05, 'epoch': 9.75}

 81%|████████▏ | 22823/28080 [45:05:40<10:27:01,  7.16s/it]
 81%|████████▏ | 22824/28080 [45:05:47<10:26:41,  7.15s/it]
                                                           
{'loss': 0.603, 'learning_rate': 4.455122238874065e-05, 'epoch': 9.75}

 81%|████████▏ | 22824/28080 [45:05:47<10:26:41,  7.15s/it]
 81%|████████▏ | 22825/28080 [45:05:54<10:24:44,  7.13s/it]
                                                           
{'loss': 0.602, 'learning_rate': 4.4534793656256537e-05, 'epoch': 9.75}

 81%|████████▏ | 22825/28080 [45:05:54<10:24:44,  7.13s/it]
 81%|████████▏ | 22826/28080 [45:06:01<10:22:46,  7.11s/it]
                                                           
{'loss': 0.6023, 'learning_rate': 4.451836765727504e-05, 'epoch': 9.75}

 81%|████████▏ | 22826/28080 [45:06:01<10:22:46,  7.11s/it]
 81%|████████▏ | 22827/28080 [45:06:08<10:21:18,  7.10s/it]
                                                           
{'loss': 0.5826, 'learning_rate': 4.450194439201463e-05, 'epoch': 9.75}

 81%|████████▏ | 22827/28080 [45:06:08<10:21:18,  7.10s/it]
 81%|████████▏ | 22828/28080 [45:06:15<10:20:16,  7.09s/it]
                                                           
{'loss': 0.6126, 'learning_rate': 4.4485523860693904e-05, 'epoch': 9.75}

 81%|████████▏ | 22828/28080 [45:06:15<10:20:16,  7.09s/it]
 81%|████████▏ | 22829/28080 [45:06:22<10:17:32,  7.06s/it]
                                                           
{'loss': 0.5695, 'learning_rate': 4.446910606353119e-05, 'epoch': 9.75}

 81%|████████▏ | 22829/28080 [45:06:22<10:17:32,  7.06s/it]
 81%|████████▏ | 22830/28080 [45:06:29<10:17:34,  7.06s/it]
                                                           
{'loss': 0.5992, 'learning_rate': 4.4452691000745115e-05, 'epoch': 9.75}

 81%|████████▏ | 22830/28080 [45:06:29<10:17:34,  7.06s/it]
 81%|████████▏ | 22831/28080 [45:06:36<10:20:13,  7.09s/it]
                                                           
{'loss': 0.5959, 'learning_rate': 4.4436278672553816e-05, 'epoch': 9.75}

 81%|████████▏ | 22831/28080 [45:06:36<10:20:13,  7.09s/it]
 81%|████████▏ | 22832/28080 [45:06:44<10:21:34,  7.11s/it]
                                                           
{'loss': 0.5866, 'learning_rate': 4.441986907917581e-05, 'epoch': 9.75}

 81%|████████▏ | 22832/28080 [45:06:44<10:21:34,  7.11s/it]
 81%|████████▏ | 22833/28080 [45:06:51<10:19:15,  7.08s/it]
                                                           
{'loss': 0.601, 'learning_rate': 4.440346222082931e-05, 'epoch': 9.75}

 81%|████████▏ | 22833/28080 [45:06:51<10:19:15,  7.08s/it]
 81%|████████▏ | 22834/28080 [45:06:58<10:18:43,  7.08s/it]
                                                           
{'loss': 0.594, 'learning_rate': 4.438705809773272e-05, 'epoch': 9.75}

 81%|████████▏ | 22834/28080 [45:06:58<10:18:43,  7.08s/it]
 81%|████████▏ | 22835/28080 [45:07:05<10:16:06,  7.05s/it]
                                                           
{'loss': 0.6094, 'learning_rate': 4.437065671010418e-05, 'epoch': 9.75}

 81%|████████▏ | 22835/28080 [45:07:05<10:16:06,  7.05s/it]
 81%|████████▏ | 22836/28080 [45:07:12<10:16:09,  7.05s/it]
                                                           
{'loss': 0.5901, 'learning_rate': 4.4354258058161926e-05, 'epoch': 9.76}

 81%|████████▏ | 22836/28080 [45:07:12<10:16:09,  7.05s/it]
 81%|████████▏ | 22837/28080 [45:07:19<10:17:48,  7.07s/it]
                                                           
{'loss': 0.6144, 'learning_rate': 4.433786214212404e-05, 'epoch': 9.76}

 81%|████████▏ | 22837/28080 [45:07:19<10:17:48,  7.07s/it]
 81%|████████▏ | 22838/28080 [45:07:26<10:13:57,  7.03s/it]
                                                           
{'loss': 0.6103, 'learning_rate': 4.432146896220882e-05, 'epoch': 9.76}

 81%|████████▏ | 22838/28080 [45:07:26<10:13:57,  7.03s/it]
 81%|████████▏ | 22839/28080 [45:07:33<10:14:04,  7.03s/it]
                                                           
{'loss': 0.6071, 'learning_rate': 4.4305078518634245e-05, 'epoch': 9.76}

 81%|████████▏ | 22839/28080 [45:07:33<10:14:04,  7.03s/it]
 81%|████████▏ | 22840/28080 [45:07:40<10:18:28,  7.08s/it]
                                                           
{'loss': 0.5893, 'learning_rate': 4.4288690811618406e-05, 'epoch': 9.76}

 81%|████████▏ | 22840/28080 [45:07:40<10:18:28,  7.08s/it]
 81%|████████▏ | 22841/28080 [45:07:47<10:17:49,  7.08s/it]
                                                           
{'loss': 0.6205, 'learning_rate': 4.4272305841379314e-05, 'epoch': 9.76}

 81%|████████▏ | 22841/28080 [45:07:47<10:17:49,  7.08s/it]
 81%|████████▏ | 22842/28080 [45:07:54<10:20:34,  7.11s/it]
                                                           
{'loss': 0.6216, 'learning_rate': 4.425592360813488e-05, 'epoch': 9.76}

 81%|████████▏ | 22842/28080 [45:07:54<10:20:34,  7.11s/it]
 81%|████████▏ | 22843/28080 [45:08:01<10:21:35,  7.12s/it]
                                                           
{'loss': 0.6047, 'learning_rate': 4.423954411210321e-05, 'epoch': 9.76}

 81%|████████▏ | 22843/28080 [45:08:01<10:21:35,  7.12s/it]
 81%|████████▏ | 22844/28080 [45:08:09<10:24:44,  7.16s/it]
                                                           
{'loss': 0.6184, 'learning_rate': 4.4223167353502096e-05, 'epoch': 9.76}

 81%|████████▏ | 22844/28080 [45:08:09<10:24:44,  7.16s/it]
 81%|████████▏ | 22845/28080 [45:08:16<10:19:25,  7.10s/it]
                                                           
{'loss': 0.5868, 'learning_rate': 4.4206793332549485e-05, 'epoch': 9.76}

 81%|████████▏ | 22845/28080 [45:08:16<10:19:25,  7.10s/it]
 81%|████████▏ | 22846/28080 [45:08:23<10:19:00,  7.10s/it]
                                                           
{'loss': 0.6019, 'learning_rate': 4.4190422049463136e-05, 'epoch': 9.76}

 81%|████████▏ | 22846/28080 [45:08:23<10:19:00,  7.10s/it]
 81%|████████▏ | 22847/28080 [45:08:30<10:18:38,  7.09s/it]
                                                           
{'loss': 0.5763, 'learning_rate': 4.417405350446094e-05, 'epoch': 9.76}

 81%|████████▏ | 22847/28080 [45:08:30<10:18:38,  7.09s/it]
 81%|████████▏ | 22848/28080 [45:08:37<10:17:30,  7.08s/it]
                                                           
{'loss': 0.5874, 'learning_rate': 4.4157687697760545e-05, 'epoch': 9.76}

 81%|████████▏ | 22848/28080 [45:08:37<10:17:30,  7.08s/it]
 81%|████████▏ | 22849/28080 [45:08:44<10:16:45,  7.07s/it]
                                                           
{'loss': 0.6027, 'learning_rate': 4.414132462957993e-05, 'epoch': 9.76}

 81%|████████▏ | 22849/28080 [45:08:44<10:16:45,  7.07s/it]
 81%|████████▏ | 22850/28080 [45:08:51<10:17:06,  7.08s/it]
                                                           
{'loss': 0.6114, 'learning_rate': 4.412496430013646e-05, 'epoch': 9.76}

 81%|████████▏ | 22850/28080 [45:08:51<10:17:06,  7.08s/it]
 81%|████████▏ | 22851/28080 [45:08:58<10:17:14,  7.08s/it]
                                                           
{'loss': 0.5655, 'learning_rate': 4.4108606709648e-05, 'epoch': 9.76}

 81%|████████▏ | 22851/28080 [45:08:58<10:17:14,  7.08s/it]
 81%|████████▏ | 22852/28080 [45:09:05<10:18:16,  7.10s/it]
                                                           
{'loss': 0.6078, 'learning_rate': 4.40922518583321e-05, 'epoch': 9.76}

 81%|████████▏ | 22852/28080 [45:09:05<10:18:16,  7.10s/it]
 81%|████████▏ | 22853/28080 [45:09:12<10:18:43,  7.10s/it]
                                                           
{'loss': 0.6074, 'learning_rate': 4.407589974640641e-05, 'epoch': 9.76}

 81%|████████▏ | 22853/28080 [45:09:12<10:18:43,  7.10s/it]
 81%|████████▏ | 22854/28080 [45:09:19<10:21:20,  7.13s/it]
                                                           
{'loss': 0.5994, 'learning_rate': 4.405955037408843e-05, 'epoch': 9.76}

 81%|████████▏ | 22854/28080 [45:09:19<10:21:20,  7.13s/it]
 81%|████████▏ | 22855/28080 [45:09:26<10:18:03,  7.10s/it]
                                                           
{'loss': 0.622, 'learning_rate': 4.4043203741595675e-05, 'epoch': 9.76}

 81%|████████▏ | 22855/28080 [45:09:26<10:18:03,  7.10s/it]
 81%|████████▏ | 22856/28080 [45:09:34<10:18:45,  7.11s/it]
                                                           
{'loss': 0.5898, 'learning_rate': 4.402685984914556e-05, 'epoch': 9.76}

 81%|████████▏ | 22856/28080 [45:09:34<10:18:45,  7.11s/it]
 81%|████████▏ | 22857/28080 [45:09:41<10:19:04,  7.11s/it]
                                                           
{'loss': 0.5936, 'learning_rate': 4.4010518696955633e-05, 'epoch': 9.76}

 81%|████████▏ | 22857/28080 [45:09:41<10:19:04,  7.11s/it]
 81%|████████▏ | 22858/28080 [45:09:48<10:19:29,  7.12s/it]
                                                           
{'loss': 0.5929, 'learning_rate': 4.399418028524327e-05, 'epoch': 9.76}

 81%|████████▏ | 22858/28080 [45:09:48<10:19:29,  7.12s/it]
 81%|████████▏ | 22859/28080 [45:09:55<10:18:32,  7.11s/it]
                                                           
{'loss': 0.6092, 'learning_rate': 4.39778446142258e-05, 'epoch': 9.77}

 81%|████████▏ | 22859/28080 [45:09:55<10:18:32,  7.11s/it]
 81%|████████▏ | 22860/28080 [45:10:02<10:16:30,  7.09s/it]
                                                           
{'loss': 0.6156, 'learning_rate': 4.396151168412049e-05, 'epoch': 9.77}

 81%|████████▏ | 22860/28080 [45:10:02<10:16:30,  7.09s/it]
 81%|████████▏ | 22861/28080 [45:10:09<10:17:55,  7.10s/it]
                                                           
{'loss': 0.6027, 'learning_rate': 4.394518149514479e-05, 'epoch': 9.77}

 81%|████████▏ | 22861/28080 [45:10:09<10:17:55,  7.10s/it]
 81%|████████▏ | 22862/28080 [45:10:16<10:15:34,  7.08s/it]
                                                           
{'loss': 0.6216, 'learning_rate': 4.392885404751582e-05, 'epoch': 9.77}

 81%|████████▏ | 22862/28080 [45:10:16<10:15:34,  7.08s/it]
 81%|████████▏ | 22863/28080 [45:10:23<10:17:32,  7.10s/it]
                                                           
{'loss': 0.5909, 'learning_rate': 4.3912529341450985e-05, 'epoch': 9.77}

 81%|████████▏ | 22863/28080 [45:10:23<10:17:32,  7.10s/it]
 81%|████████▏ | 22864/28080 [45:10:30<10:18:21,  7.11s/it]
                                                           
{'loss': 0.5997, 'learning_rate': 4.3896207377167265e-05, 'epoch': 9.77}

 81%|████████▏ | 22864/28080 [45:10:30<10:18:21,  7.11s/it]
 81%|████████▏ | 22865/28080 [45:10:37<10:15:40,  7.08s/it]
                                                           
{'loss': 0.5907, 'learning_rate': 4.387988815488181e-05, 'epoch': 9.77}

 81%|████████▏ | 22865/28080 [45:10:37<10:15:40,  7.08s/it]
 81%|████████▏ | 22866/28080 [45:10:45<10:15:39,  7.08s/it]
                                                           
{'loss': 0.5966, 'learning_rate': 4.386357167481186e-05, 'epoch': 9.77}

 81%|████████▏ | 22866/28080 [45:10:45<10:15:39,  7.08s/it]
 81%|████████▏ | 22867/28080 [45:10:52<10:18:58,  7.12s/it]
                                                           
{'loss': 0.596, 'learning_rate': 4.384725793717437e-05, 'epoch': 9.77}

 81%|████████▏ | 22867/28080 [45:10:52<10:18:58,  7.12s/it]
 81%|████████▏ | 22868/28080 [45:10:59<10:17:44,  7.11s/it]
                                                           
{'loss': 0.5926, 'learning_rate': 4.383094694218651e-05, 'epoch': 9.77}

 81%|████████▏ | 22868/28080 [45:10:59<10:17:44,  7.11s/it]
 81%|████████▏ | 22869/28080 [45:11:06<10:15:35,  7.09s/it]
                                                           
{'loss': 0.6087, 'learning_rate': 4.3814638690065216e-05, 'epoch': 9.77}

 81%|████████▏ | 22869/28080 [45:11:06<10:15:35,  7.09s/it]
 81%|████████▏ | 22870/28080 [45:11:13<10:16:14,  7.10s/it]
                                                           
{'loss': 0.6003, 'learning_rate': 4.379833318102741e-05, 'epoch': 9.77}

 81%|████████▏ | 22870/28080 [45:11:13<10:16:14,  7.10s/it]
 81%|████████▏ | 22871/28080 [45:11:20<10:15:08,  7.09s/it]
                                                           
{'loss': 0.6139, 'learning_rate': 4.3782030415290026e-05, 'epoch': 9.77}

 81%|████████▏ | 22871/28080 [45:11:20<10:15:08,  7.09s/it]
 81%|████████▏ | 22872/28080 [45:11:27<10:16:28,  7.10s/it]
                                                           
{'loss': 0.5943, 'learning_rate': 4.3765730393070026e-05, 'epoch': 9.77}

 81%|████████▏ | 22872/28080 [45:11:27<10:16:28,  7.10s/it]
 81%|████████▏ | 22873/28080 [45:11:34<10:20:01,  7.14s/it]
                                                           
{'loss': 0.6184, 'learning_rate': 4.3749433114584234e-05, 'epoch': 9.77}

 81%|████████▏ | 22873/28080 [45:11:34<10:20:01,  7.14s/it]
 81%|████████▏ | 22874/28080 [45:11:41<10:16:13,  7.10s/it]
                                                           
{'loss': 0.6112, 'learning_rate': 4.373313858004946e-05, 'epoch': 9.77}

 81%|████████▏ | 22874/28080 [45:11:41<10:16:13,  7.10s/it]
 81%|████████▏ | 22875/28080 [45:11:49<10:16:34,  7.11s/it]
                                                           
{'loss': 0.6065, 'learning_rate': 4.371684678968241e-05, 'epoch': 9.77}

 81%|████████▏ | 22875/28080 [45:11:49<10:16:34,  7.11s/it]
 81%|████████▏ | 22876/28080 [45:11:56<10:14:21,  7.08s/it]
                                                           
{'loss': 0.619, 'learning_rate': 4.370055774369999e-05, 'epoch': 9.77}

 81%|████████▏ | 22876/28080 [45:11:56<10:14:21,  7.08s/it]
 81%|████████▏ | 22877/28080 [45:12:03<10:14:48,  7.09s/it]
                                                           
{'loss': 0.5762, 'learning_rate': 4.368427144231879e-05, 'epoch': 9.77}

 81%|████████▏ | 22877/28080 [45:12:03<10:14:48,  7.09s/it]
 81%|████████▏ | 22878/28080 [45:12:10<10:16:20,  7.11s/it]
                                                           
{'loss': 0.6021, 'learning_rate': 4.366798788575555e-05, 'epoch': 9.77}

 81%|████████▏ | 22878/28080 [45:12:10<10:16:20,  7.11s/it]
 81%|████████▏ | 22879/28080 [45:12:17<10:16:54,  7.12s/it]
                                                           
{'loss': 0.5893, 'learning_rate': 4.365170707422678e-05, 'epoch': 9.77}

 81%|████████▏ | 22879/28080 [45:12:17<10:16:54,  7.12s/it]
 81%|████████▏ | 22880/28080 [45:12:24<10:14:47,  7.09s/it]
                                                           
{'loss': 0.594, 'learning_rate': 4.3635429007949226e-05, 'epoch': 9.77}

 81%|████████▏ | 22880/28080 [45:12:24<10:14:47,  7.09s/it]
 81%|████████▏ | 22881/28080 [45:12:31<10:12:34,  7.07s/it]
                                                           
{'loss': 0.6189, 'learning_rate': 4.361915368713934e-05, 'epoch': 9.77}

 81%|████████▏ | 22881/28080 [45:12:31<10:12:34,  7.07s/it]
 81%|████████▏ | 22882/28080 [45:12:38<10:12:24,  7.07s/it]
                                                           
{'loss': 0.6237, 'learning_rate': 4.360288111201377e-05, 'epoch': 9.77}

 81%|████████▏ | 22882/28080 [45:12:38<10:12:24,  7.07s/it]
 81%|████████▏ | 22883/28080 [45:12:45<10:13:57,  7.09s/it]
                                                           
{'loss': 0.5949, 'learning_rate': 4.358661128278896e-05, 'epoch': 9.78}

 81%|████████▏ | 22883/28080 [45:12:45<10:13:57,  7.09s/it]
 81%|████████▏ | 22884/28080 [45:12:53<10:18:28,  7.14s/it]
                                                           
{'loss': 0.5986, 'learning_rate': 4.357034419968131e-05, 'epoch': 9.78}

 81%|████████▏ | 22884/28080 [45:12:53<10:18:28,  7.14s/it]
 81%|████████▏ | 22885/28080 [45:13:00<10:17:50,  7.14s/it]
                                                           
{'loss': 0.593, 'learning_rate': 4.355407986290721e-05, 'epoch': 9.78}

 81%|████████▏ | 22885/28080 [45:13:00<10:17:50,  7.14s/it]
 82%|████████▏ | 22886/28080 [45:13:07<10:21:24,  7.18s/it]
                                                           
{'loss': 0.5921, 'learning_rate': 4.353781827268316e-05, 'epoch': 9.78}

 82%|████████▏ | 22886/28080 [45:13:07<10:21:24,  7.18s/it]
 82%|████████▏ | 22887/28080 [45:13:14<10:20:24,  7.17s/it]
                                                           
{'loss': 0.5915, 'learning_rate': 4.352155942922548e-05, 'epoch': 9.78}

 82%|████████▏ | 22887/28080 [45:13:14<10:20:24,  7.17s/it]
 82%|████████▏ | 22888/28080 [45:13:21<10:19:52,  7.16s/it]
                                                           
{'loss': 0.6104, 'learning_rate': 4.350530333275041e-05, 'epoch': 9.78}

 82%|████████▏ | 22888/28080 [45:13:21<10:19:52,  7.16s/it]
 82%|████████▏ | 22889/28080 [45:13:28<10:17:56,  7.14s/it]
                                                           
{'loss': 0.5811, 'learning_rate': 4.348904998347425e-05, 'epoch': 9.78}

 82%|████████▏ | 22889/28080 [45:13:28<10:17:56,  7.14s/it]
 82%|████████▏ | 22890/28080 [45:13:35<10:19:10,  7.16s/it]
                                                           
{'loss': 0.5804, 'learning_rate': 4.347279938161316e-05, 'epoch': 9.78}

 82%|████████▏ | 22890/28080 [45:13:35<10:19:10,  7.16s/it]
 82%|████████▏ | 22891/28080 [45:13:43<10:16:01,  7.12s/it]
                                                           
{'loss': 0.6168, 'learning_rate': 4.345655152738348e-05, 'epoch': 9.78}

 82%|████████▏ | 22891/28080 [45:13:43<10:16:01,  7.12s/it]
 82%|████████▏ | 22892/28080 [45:13:50<10:14:59,  7.11s/it]
                                                           
{'loss': 0.6283, 'learning_rate': 4.344030642100133e-05, 'epoch': 9.78}

 82%|████████▏ | 22892/28080 [45:13:50<10:14:59,  7.11s/it]
 82%|████████▏ | 22893/28080 [45:13:57<10:14:16,  7.11s/it]
                                                           
{'loss': 0.6238, 'learning_rate': 4.342406406268279e-05, 'epoch': 9.78}

 82%|████████▏ | 22893/28080 [45:13:57<10:14:16,  7.11s/it]
 82%|████████▏ | 22894/28080 [45:14:04<10:15:54,  7.13s/it]
                                                           
{'loss': 0.6096, 'learning_rate': 4.340782445264388e-05, 'epoch': 9.78}

 82%|████████▏ | 22894/28080 [45:14:04<10:15:54,  7.13s/it]
 82%|████████▏ | 22895/28080 [45:14:11<10:15:40,  7.12s/it]
                                                           
{'loss': 0.5932, 'learning_rate': 4.3391587591100815e-05, 'epoch': 9.78}

 82%|████████▏ | 22895/28080 [45:14:11<10:15:40,  7.12s/it]
 82%|████████▏ | 22896/28080 [45:14:18<10:14:53,  7.12s/it]
                                                           
{'loss': 0.5923, 'learning_rate': 4.3375353478269486e-05, 'epoch': 9.78}

 82%|████████▏ | 22896/28080 [45:14:18<10:14:53,  7.12s/it]
 82%|████████▏ | 22897/28080 [45:14:25<10:16:10,  7.13s/it]
                                                           
{'loss': 0.5919, 'learning_rate': 4.335912211436602e-05, 'epoch': 9.78}

 82%|████████▏ | 22897/28080 [45:14:25<10:16:10,  7.13s/it]
 82%|████████▏ | 22898/28080 [45:14:32<10:13:27,  7.10s/it]
                                                           
{'loss': 0.6038, 'learning_rate': 4.334289349960616e-05, 'epoch': 9.78}

 82%|████████▏ | 22898/28080 [45:14:32<10:13:27,  7.10s/it]
 82%|████████▏ | 22899/28080 [45:14:39<10:13:50,  7.11s/it]
                                                           
{'loss': 0.627, 'learning_rate': 4.332666763420593e-05, 'epoch': 9.78}

 82%|████████▏ | 22899/28080 [45:14:39<10:13:50,  7.11s/it]
 82%|████████▏ | 22900/28080 [45:14:47<10:16:46,  7.14s/it]
                                                           
{'loss': 0.5853, 'learning_rate': 4.331044451838112e-05, 'epoch': 9.78}

 82%|████████▏ | 22900/28080 [45:14:47<10:16:46,  7.14s/it]
 82%|████████▏ | 22901/28080 [45:14:54<10:15:09,  7.13s/it]
                                                           
{'loss': 0.5897, 'learning_rate': 4.329422415234768e-05, 'epoch': 9.78}

 82%|████████▏ | 22901/28080 [45:14:54<10:15:09,  7.13s/it]
 82%|████████▏ | 22902/28080 [45:15:01<10:14:10,  7.12s/it]
                                                           
{'loss': 0.5968, 'learning_rate': 4.327800653632136e-05, 'epoch': 9.78}

 82%|████████▏ | 22902/28080 [45:15:01<10:14:10,  7.12s/it]
 82%|████████▏ | 22903/28080 [45:15:08<10:15:25,  7.13s/it]
                                                           
{'loss': 0.6028, 'learning_rate': 4.326179167051788e-05, 'epoch': 9.78}

 82%|████████▏ | 22903/28080 [45:15:08<10:15:25,  7.13s/it]
 82%|████████▏ | 22904/28080 [45:15:15<10:12:24,  7.10s/it]
                                                           
{'loss': 0.605, 'learning_rate': 4.324557955515293e-05, 'epoch': 9.78}

 82%|████████▏ | 22904/28080 [45:15:15<10:12:24,  7.10s/it]
 82%|████████▏ | 22905/28080 [45:15:22<10:14:24,  7.12s/it]
                                                           
{'loss': 0.5989, 'learning_rate': 4.322937019044232e-05, 'epoch': 9.78}

 82%|████████▏ | 22905/28080 [45:15:22<10:14:24,  7.12s/it]
 82%|████████▏ | 22906/28080 [45:15:29<10:11:49,  7.09s/it]
                                                           
{'loss': 0.6233, 'learning_rate': 4.32131635766016e-05, 'epoch': 9.79}

 82%|████████▏ | 22906/28080 [45:15:29<10:11:49,  7.09s/it]
 82%|████████▏ | 22907/28080 [45:15:36<10:14:15,  7.12s/it]
                                                           
{'loss': 0.6063, 'learning_rate': 4.3196959713846436e-05, 'epoch': 9.79}

 82%|████████▏ | 22907/28080 [45:15:36<10:14:15,  7.12s/it]
 82%|████████▏ | 22908/28080 [45:15:43<10:12:16,  7.10s/it]
                                                           
{'loss': 0.5944, 'learning_rate': 4.318075860239229e-05, 'epoch': 9.79}

 82%|████████▏ | 22908/28080 [45:15:43<10:12:16,  7.10s/it]
 82%|████████▏ | 22909/28080 [45:15:51<10:11:08,  7.09s/it]
                                                           
{'loss': 0.6012, 'learning_rate': 4.3164560242454854e-05, 'epoch': 9.79}

 82%|████████▏ | 22909/28080 [45:15:51<10:11:08,  7.09s/it]
 82%|████████▏ | 22910/28080 [45:15:58<10:12:58,  7.11s/it]
                                                           
{'loss': 0.6069, 'learning_rate': 4.314836463424951e-05, 'epoch': 9.79}

 82%|████████▏ | 22910/28080 [45:15:58<10:12:58,  7.11s/it]
 82%|████████▏ | 22911/28080 [45:16:05<10:10:59,  7.09s/it]
                                                           
{'loss': 0.6167, 'learning_rate': 4.313217177799189e-05, 'epoch': 9.79}

 82%|████████▏ | 22911/28080 [45:16:05<10:10:59,  7.09s/it]
 82%|████████▏ | 22912/28080 [45:16:12<10:09:49,  7.08s/it]
                                                           
{'loss': 0.6192, 'learning_rate': 4.311598167389718e-05, 'epoch': 9.79}

 82%|████████▏ | 22912/28080 [45:16:12<10:09:49,  7.08s/it]
 82%|████████▏ | 22913/28080 [45:16:19<10:09:14,  7.07s/it]
                                                           
{'loss': 0.6249, 'learning_rate': 4.3099794322181e-05, 'epoch': 9.79}

 82%|████████▏ | 22913/28080 [45:16:19<10:09:14,  7.07s/it]
 82%|████████▏ | 22914/28080 [45:16:26<10:10:45,  7.09s/it]
                                                           
{'loss': 0.613, 'learning_rate': 4.308360972305858e-05, 'epoch': 9.79}

 82%|████████▏ | 22914/28080 [45:16:26<10:10:45,  7.09s/it]
 82%|████████▏ | 22915/28080 [45:16:33<10:11:33,  7.10s/it]
                                                           
{'loss': 0.6058, 'learning_rate': 4.3067427876745224e-05, 'epoch': 9.79}

 82%|████████▏ | 22915/28080 [45:16:33<10:11:33,  7.10s/it]
 82%|████████▏ | 22916/28080 [45:16:40<10:11:42,  7.11s/it]
                                                           
{'loss': 0.6088, 'learning_rate': 4.305124878345632e-05, 'epoch': 9.79}

 82%|████████▏ | 22916/28080 [45:16:40<10:11:42,  7.11s/it]
 82%|████████▏ | 22917/28080 [45:16:47<10:11:46,  7.11s/it]
                                                           
{'loss': 0.6009, 'learning_rate': 4.3035072443407044e-05, 'epoch': 9.79}

 82%|████████▏ | 22917/28080 [45:16:47<10:11:46,  7.11s/it]
 82%|████████▏ | 22918/28080 [45:16:55<10:12:24,  7.12s/it]
                                                           
{'loss': 0.6063, 'learning_rate': 4.3018898856812624e-05, 'epoch': 9.79}

 82%|████████▏ | 22918/28080 [45:16:55<10:12:24,  7.12s/it]
 82%|████████▏ | 22919/28080 [45:17:02<10:11:39,  7.11s/it]
                                                           
{'loss': 0.6091, 'learning_rate': 4.300272802388816e-05, 'epoch': 9.79}

 82%|████████▏ | 22919/28080 [45:17:02<10:11:39,  7.11s/it]
 82%|████████▏ | 22920/28080 [45:17:09<10:10:56,  7.10s/it]
                                                           
{'loss': 0.5991, 'learning_rate': 4.29865599448489e-05, 'epoch': 9.79}

 82%|████████▏ | 22920/28080 [45:17:09<10:10:56,  7.10s/it]
 82%|████████▏ | 22921/28080 [45:17:16<10:08:14,  7.07s/it]
                                                           
{'loss': 0.6128, 'learning_rate': 4.29703946199099e-05, 'epoch': 9.79}

 82%|████████▏ | 22921/28080 [45:17:16<10:08:14,  7.07s/it]
 82%|████████▏ | 22922/28080 [45:17:23<10:08:07,  7.07s/it]
                                                           
{'loss': 0.6058, 'learning_rate': 4.295423204928622e-05, 'epoch': 9.79}

 82%|████████▏ | 22922/28080 [45:17:23<10:08:07,  7.07s/it]
 82%|████████▏ | 22923/28080 [45:17:30<10:06:32,  7.06s/it]
                                                           
{'loss': 0.6092, 'learning_rate': 4.293807223319285e-05, 'epoch': 9.79}

 82%|████████▏ | 22923/28080 [45:17:30<10:06:32,  7.06s/it]
 82%|████████▏ | 22924/28080 [45:17:37<10:06:39,  7.06s/it]
                                                           
{'loss': 0.5842, 'learning_rate': 4.292191517184485e-05, 'epoch': 9.79}

 82%|████████▏ | 22924/28080 [45:17:37<10:06:39,  7.06s/it]
 82%|████████▏ | 22925/28080 [45:17:44<10:09:39,  7.10s/it]
                                                           
{'loss': 0.6113, 'learning_rate': 4.2905760865457136e-05, 'epoch': 9.79}

 82%|████████▏ | 22925/28080 [45:17:44<10:09:39,  7.10s/it]
 82%|████████▏ | 22926/28080 [45:17:51<10:09:06,  7.09s/it]
                                                           
{'loss': 0.6073, 'learning_rate': 4.288960931424465e-05, 'epoch': 9.79}

 82%|████████▏ | 22926/28080 [45:17:51<10:09:06,  7.09s/it]
 82%|████████▏ | 22927/28080 [45:17:58<10:08:49,  7.09s/it]
                                                           
{'loss': 0.608, 'learning_rate': 4.287346051842217e-05, 'epoch': 9.79}

 82%|████████▏ | 22927/28080 [45:17:58<10:08:49,  7.09s/it]
 82%|████████▏ | 22928/28080 [45:18:05<10:08:48,  7.09s/it]
                                                           
{'loss': 0.6036, 'learning_rate': 4.285731447820468e-05, 'epoch': 9.79}

 82%|████████▏ | 22928/28080 [45:18:05<10:08:48,  7.09s/it]
 82%|████████▏ | 22929/28080 [45:18:12<10:09:32,  7.10s/it]
                                                           
{'loss': 0.5808, 'learning_rate': 4.284117119380687e-05, 'epoch': 9.8}

 82%|████████▏ | 22929/28080 [45:18:12<10:09:32,  7.10s/it]
 82%|████████▏ | 22930/28080 [45:18:20<10:12:02,  7.13s/it]
                                                           
{'loss': 0.6037, 'learning_rate': 4.2825030665443604e-05, 'epoch': 9.8}

 82%|████████▏ | 22930/28080 [45:18:20<10:12:02,  7.13s/it]
 82%|████████▏ | 22931/28080 [45:18:27<10:13:42,  7.15s/it]
                                                           
{'loss': 0.5944, 'learning_rate': 4.2808892893329594e-05, 'epoch': 9.8}

 82%|████████▏ | 22931/28080 [45:18:27<10:13:42,  7.15s/it]
 82%|████████▏ | 22932/28080 [45:18:34<10:14:02,  7.16s/it]
                                                           
{'loss': 0.615, 'learning_rate': 4.27927578776795e-05, 'epoch': 9.8}

 82%|████████▏ | 22932/28080 [45:18:34<10:14:02,  7.16s/it]
 82%|████████▏ | 22933/28080 [45:18:41<10:12:52,  7.14s/it]
                                                           
{'loss': 0.5938, 'learning_rate': 4.277662561870796e-05, 'epoch': 9.8}

 82%|████████▏ | 22933/28080 [45:18:41<10:12:52,  7.14s/it]
 82%|████████▏ | 22934/28080 [45:18:48<10:08:47,  7.10s/it]
                                                           
{'loss': 0.6174, 'learning_rate': 4.276049611662969e-05, 'epoch': 9.8}

 82%|████████▏ | 22934/28080 [45:18:48<10:08:47,  7.10s/it]
 82%|████████▏ | 22935/28080 [45:18:55<10:09:06,  7.10s/it]
                                                           
{'loss': 0.5898, 'learning_rate': 4.274436937165921e-05, 'epoch': 9.8}

 82%|████████▏ | 22935/28080 [45:18:55<10:09:06,  7.10s/it]
 82%|████████▏ | 22936/28080 [45:19:02<10:12:00,  7.14s/it]
                                                           
{'loss': 0.6148, 'learning_rate': 4.27282453840111e-05, 'epoch': 9.8}

 82%|████████▏ | 22936/28080 [45:19:02<10:12:00,  7.14s/it]
 82%|████████▏ | 22937/28080 [45:19:10<10:11:11,  7.13s/it]
                                                           
{'loss': 0.6046, 'learning_rate': 4.2712124153899774e-05, 'epoch': 9.8}

 82%|████████▏ | 22937/28080 [45:19:10<10:11:11,  7.13s/it]
 82%|████████▏ | 22938/28080 [45:19:17<10:10:41,  7.13s/it]
                                                           
{'loss': 0.6053, 'learning_rate': 4.269600568153986e-05, 'epoch': 9.8}

 82%|████████▏ | 22938/28080 [45:19:17<10:10:41,  7.13s/it]
 82%|████████▏ | 22939/28080 [45:19:24<10:11:42,  7.14s/it]
                                                           
{'loss': 0.5876, 'learning_rate': 4.2679889967145724e-05, 'epoch': 9.8}

 82%|████████▏ | 22939/28080 [45:19:24<10:11:42,  7.14s/it]
 82%|████████▏ | 22940/28080 [45:19:31<10:10:42,  7.13s/it]
                                                           
{'loss': 0.5917, 'learning_rate': 4.2663777010931773e-05, 'epoch': 9.8}

 82%|████████▏ | 22940/28080 [45:19:31<10:10:42,  7.13s/it]
 82%|████████▏ | 22941/28080 [45:19:38<10:13:01,  7.16s/it]
                                                           
{'loss': 0.5975, 'learning_rate': 4.264766681311238e-05, 'epoch': 9.8}

 82%|████████▏ | 22941/28080 [45:19:38<10:13:01,  7.16s/it]
 82%|████████▏ | 22942/28080 [45:19:45<10:11:40,  7.14s/it]
                                                           
{'loss': 0.6201, 'learning_rate': 4.2631559373901784e-05, 'epoch': 9.8}

 82%|████████▏ | 22942/28080 [45:19:45<10:11:40,  7.14s/it]
 82%|████████▏ | 22943/28080 [45:19:52<10:09:40,  7.12s/it]
                                                           
{'loss': 0.6039, 'learning_rate': 4.261545469351444e-05, 'epoch': 9.8}

 82%|████████▏ | 22943/28080 [45:19:52<10:09:40,  7.12s/it]
 82%|████████▏ | 22944/28080 [45:19:59<10:08:32,  7.11s/it]
                                                           
{'loss': 0.5936, 'learning_rate': 4.259935277216445e-05, 'epoch': 9.8}

 82%|████████▏ | 22944/28080 [45:19:59<10:08:32,  7.11s/it]
 82%|████████▏ | 22945/28080 [45:20:06<10:07:54,  7.10s/it]
                                                           
{'loss': 0.61, 'learning_rate': 4.258325361006624e-05, 'epoch': 9.8}

 82%|████████▏ | 22945/28080 [45:20:06<10:07:54,  7.10s/it]
 82%|████████▏ | 22946/28080 [45:20:14<10:08:49,  7.12s/it]
                                                           
{'loss': 0.6086, 'learning_rate': 4.256715720743376e-05, 'epoch': 9.8}

 82%|████████▏ | 22946/28080 [45:20:14<10:08:49,  7.12s/it]
 82%|████████▏ | 22947/28080 [45:20:21<10:06:52,  7.09s/it]
                                                           
{'loss': 0.5907, 'learning_rate': 4.2551063564481295e-05, 'epoch': 9.8}

 82%|████████▏ | 22947/28080 [45:20:21<10:06:52,  7.09s/it]
 82%|████████▏ | 22948/28080 [45:20:28<10:04:03,  7.06s/it]
                                                           
{'loss': 0.6098, 'learning_rate': 4.253497268142284e-05, 'epoch': 9.8}

 82%|████████▏ | 22948/28080 [45:20:28<10:04:03,  7.06s/it]
 82%|████████▏ | 22949/28080 [45:20:35<10:03:12,  7.05s/it]
                                                           
{'loss': 0.5901, 'learning_rate': 4.251888455847261e-05, 'epoch': 9.8}

 82%|████████▏ | 22949/28080 [45:20:35<10:03:12,  7.05s/it]
 82%|████████▏ | 22950/28080 [45:20:42<10:02:15,  7.04s/it]
                                                           
{'loss': 0.6176, 'learning_rate': 4.25027991958446e-05, 'epoch': 9.8}

 82%|████████▏ | 22950/28080 [45:20:42<10:02:15,  7.04s/it]
 82%|████████▏ | 22951/28080 [45:20:49<10:03:06,  7.06s/it]
                                                           
{'loss': 0.6108, 'learning_rate': 4.248671659375278e-05, 'epoch': 9.8}

 82%|████████▏ | 22951/28080 [45:20:49<10:03:06,  7.06s/it]
 82%|████████▏ | 22952/28080 [45:20:56<10:03:25,  7.06s/it]
                                                           
{'loss': 0.6152, 'learning_rate': 4.247063675241103e-05, 'epoch': 9.8}

 82%|████████▏ | 22952/28080 [45:20:56<10:03:25,  7.06s/it]
 82%|████████▏ | 22953/28080 [45:21:03<10:06:03,  7.09s/it]
                                                           
{'loss': 0.6071, 'learning_rate': 4.245455967203343e-05, 'epoch': 9.81}

 82%|████████▏ | 22953/28080 [45:21:03<10:06:03,  7.09s/it]
 82%|████████▏ | 22954/28080 [45:21:10<10:06:50,  7.10s/it]
                                                           
{'loss': 0.5917, 'learning_rate': 4.243848535283382e-05, 'epoch': 9.81}

 82%|████████▏ | 22954/28080 [45:21:10<10:06:50,  7.10s/it]
 82%|████████▏ | 22955/28080 [45:21:17<10:08:48,  7.13s/it]
                                                           
{'loss': 0.6088, 'learning_rate': 4.242241379502601e-05, 'epoch': 9.81}

 82%|████████▏ | 22955/28080 [45:21:17<10:08:48,  7.13s/it]
 82%|████████▏ | 22956/28080 [45:21:24<10:08:38,  7.13s/it]
                                                           
{'loss': 0.6183, 'learning_rate': 4.240634499882379e-05, 'epoch': 9.81}

 82%|████████▏ | 22956/28080 [45:21:24<10:08:38,  7.13s/it]
 82%|████████▏ | 22957/28080 [45:21:32<10:11:10,  7.16s/it]
                                                           
{'loss': 0.6079, 'learning_rate': 4.239027896444106e-05, 'epoch': 9.81}

 82%|████████▏ | 22957/28080 [45:21:32<10:11:10,  7.16s/it]
 82%|████████▏ | 22958/28080 [45:21:39<10:11:46,  7.17s/it]
                                                           
{'loss': 0.6047, 'learning_rate': 4.23742156920914e-05, 'epoch': 9.81}

 82%|████████▏ | 22958/28080 [45:21:39<10:11:46,  7.17s/it]
 82%|████████▏ | 22959/28080 [45:21:46<10:08:25,  7.13s/it]
                                                           
{'loss': 0.6204, 'learning_rate': 4.2358155181988736e-05, 'epoch': 9.81}

 82%|████████▏ | 22959/28080 [45:21:46<10:08:25,  7.13s/it]
 82%|████████▏ | 22960/28080 [45:21:53<10:04:52,  7.09s/it]
                                                           
{'loss': 0.6476, 'learning_rate': 4.23420974343465e-05, 'epoch': 9.81}

 82%|████████▏ | 22960/28080 [45:21:53<10:04:52,  7.09s/it]
 82%|████████▏ | 22961/28080 [45:22:00<10:03:23,  7.07s/it]
                                                           
{'loss': 0.6129, 'learning_rate': 4.2326042449378486e-05, 'epoch': 9.81}

 82%|████████▏ | 22961/28080 [45:22:00<10:03:23,  7.07s/it]
 82%|████████▏ | 22962/28080 [45:22:07<10:05:30,  7.10s/it]
                                                           
{'loss': 0.6221, 'learning_rate': 4.2309990227298146e-05, 'epoch': 9.81}

 82%|████████▏ | 22962/28080 [45:22:07<10:05:30,  7.10s/it]
 82%|████████▏ | 22963/28080 [45:22:14<10:03:35,  7.08s/it]
                                                           
{'loss': 0.5971, 'learning_rate': 4.2293940768319213e-05, 'epoch': 9.81}

 82%|████████▏ | 22963/28080 [45:22:14<10:03:35,  7.08s/it]
 82%|████████▏ | 22964/28080 [45:22:21<10:02:49,  7.07s/it]
                                                           
{'loss': 0.6134, 'learning_rate': 4.2277894072655173e-05, 'epoch': 9.81}

 82%|████████▏ | 22964/28080 [45:22:21<10:02:49,  7.07s/it]
 82%|████████▏ | 22965/28080 [45:22:28<10:06:03,  7.11s/it]
                                                           
{'loss': 0.5977, 'learning_rate': 4.2261850140519336e-05, 'epoch': 9.81}

 82%|████████▏ | 22965/28080 [45:22:28<10:06:03,  7.11s/it]
 82%|████████▏ | 22966/28080 [45:22:35<10:05:07,  7.10s/it]
                                                           
{'loss': 0.6083, 'learning_rate': 4.2245808972125324e-05, 'epoch': 9.81}

 82%|████████▏ | 22966/28080 [45:22:36<10:05:07,  7.10s/it]
 82%|████████▏ | 22967/28080 [45:22:43<10:05:17,  7.10s/it]
                                                           
{'loss': 0.6044, 'learning_rate': 4.2229770567686426e-05, 'epoch': 9.81}

 82%|████████▏ | 22967/28080 [45:22:43<10:05:17,  7.10s/it]
 82%|████████▏ | 22968/28080 [45:22:50<10:06:55,  7.12s/it]
                                                           
{'loss': 0.6073, 'learning_rate': 4.2213734927416176e-05, 'epoch': 9.81}

 82%|████████▏ | 22968/28080 [45:22:50<10:06:55,  7.12s/it]
 82%|████████▏ | 22969/28080 [45:22:57<10:07:57,  7.14s/it]
                                                           
{'loss': 0.6028, 'learning_rate': 4.219770205152779e-05, 'epoch': 9.81}

 82%|████████▏ | 22969/28080 [45:22:57<10:07:57,  7.14s/it]
 82%|████████▏ | 22970/28080 [45:23:04<10:05:26,  7.11s/it]
                                                           
{'loss': 0.6146, 'learning_rate': 4.2181671940234615e-05, 'epoch': 9.81}

 82%|████████▏ | 22970/28080 [45:23:04<10:05:26,  7.11s/it]
 82%|████████▏ | 22971/28080 [45:23:11<10:04:01,  7.09s/it]
                                                           
{'loss': 0.6211, 'learning_rate': 4.216564459374986e-05, 'epoch': 9.81}

 82%|████████▏ | 22971/28080 [45:23:11<10:04:01,  7.09s/it]
 82%|████████▏ | 22972/28080 [45:23:18<10:06:21,  7.12s/it]
                                                           
{'loss': 0.5926, 'learning_rate': 4.214962001228684e-05, 'epoch': 9.81}

 82%|████████▏ | 22972/28080 [45:23:18<10:06:21,  7.12s/it]
 82%|████████▏ | 22973/28080 [45:23:25<10:05:10,  7.11s/it]
                                                           
{'loss': 0.5861, 'learning_rate': 4.213359819605869e-05, 'epoch': 9.81}

 82%|████████▏ | 22973/28080 [45:23:25<10:05:10,  7.11s/it]
 82%|████████▏ | 22974/28080 [45:23:32<10:06:40,  7.13s/it]
                                                           
{'loss': 0.5933, 'learning_rate': 4.211757914527856e-05, 'epoch': 9.81}

 82%|████████▏ | 22974/28080 [45:23:32<10:06:40,  7.13s/it]
 82%|████████▏ | 22975/28080 [45:23:40<10:06:53,  7.13s/it]
                                                           
{'loss': 0.5943, 'learning_rate': 4.210156286015954e-05, 'epoch': 9.81}

 82%|████████▏ | 22975/28080 [45:23:40<10:06:53,  7.13s/it]
 82%|████████▏ | 22976/28080 [45:23:47<10:06:57,  7.14s/it]
                                                           
{'loss': 0.5882, 'learning_rate': 4.20855493409148e-05, 'epoch': 9.82}

 82%|████████▏ | 22976/28080 [45:23:47<10:06:57,  7.14s/it]
 82%|████████▏ | 22977/28080 [45:23:54<10:05:40,  7.12s/it]
                                                           
{'loss': 0.5932, 'learning_rate': 4.206953858775728e-05, 'epoch': 9.82}

 82%|████████▏ | 22977/28080 [45:23:54<10:05:40,  7.12s/it]
 82%|████████▏ | 22978/28080 [45:24:01<10:05:29,  7.12s/it]
                                                           
{'loss': 0.6016, 'learning_rate': 4.205353060090009e-05, 'epoch': 9.82}

 82%|████████▏ | 22978/28080 [45:24:01<10:05:29,  7.12s/it]
 82%|████████▏ | 22979/28080 [45:24:08<10:04:31,  7.11s/it]
                                                           
{'loss': 0.6199, 'learning_rate': 4.203752538055616e-05, 'epoch': 9.82}

 82%|████████▏ | 22979/28080 [45:24:08<10:04:31,  7.11s/it]
 82%|████████▏ | 22980/28080 [45:24:15<10:05:33,  7.12s/it]
                                                           
{'loss': 0.6026, 'learning_rate': 4.2021522926938394e-05, 'epoch': 9.82}

 82%|████████▏ | 22980/28080 [45:24:15<10:05:33,  7.12s/it]
 82%|████████▏ | 22981/28080 [45:24:22<10:03:23,  7.10s/it]
                                                           
{'loss': 0.5988, 'learning_rate': 4.200552324025966e-05, 'epoch': 9.82}

 82%|████████▏ | 22981/28080 [45:24:22<10:03:23,  7.10s/it]
 82%|████████▏ | 22982/28080 [45:24:29<10:05:19,  7.12s/it]
                                                           
{'loss': 0.5957, 'learning_rate': 4.198952632073294e-05, 'epoch': 9.82}

 82%|████████▏ | 22982/28080 [45:24:29<10:05:19,  7.12s/it]
 82%|████████▏ | 22983/28080 [45:24:37<10:04:16,  7.11s/it]
                                                           
{'loss': 0.6329, 'learning_rate': 4.197353216857094e-05, 'epoch': 9.82}

 82%|████████▏ | 22983/28080 [45:24:37<10:04:16,  7.11s/it]
 82%|████████▏ | 22984/28080 [45:24:44<10:04:26,  7.12s/it]
                                                           
{'loss': 0.6196, 'learning_rate': 4.1957540783986505e-05, 'epoch': 9.82}

 82%|████████▏ | 22984/28080 [45:24:44<10:04:26,  7.12s/it]
 82%|████████▏ | 22985/28080 [45:24:51<10:05:10,  7.13s/it]
                                                           
{'loss': 0.6088, 'learning_rate': 4.194155216719231e-05, 'epoch': 9.82}

 82%|████████▏ | 22985/28080 [45:24:51<10:05:10,  7.13s/it]
 82%|████████▏ | 22986/28080 [45:24:58<10:02:04,  7.09s/it]
                                                           
{'loss': 0.6147, 'learning_rate': 4.1925566318401193e-05, 'epoch': 9.82}

 82%|████████▏ | 22986/28080 [45:24:58<10:02:04,  7.09s/it]
 82%|████████▏ | 22987/28080 [45:25:05<10:00:39,  7.08s/it]
                                                           
{'loss': 0.6264, 'learning_rate': 4.190958323782573e-05, 'epoch': 9.82}

 82%|████████▏ | 22987/28080 [45:25:05<10:00:39,  7.08s/it]
 82%|████████▏ | 22988/28080 [45:25:12<10:01:03,  7.08s/it]
                                                           
{'loss': 0.5947, 'learning_rate': 4.1893602925678595e-05, 'epoch': 9.82}

 82%|████████▏ | 22988/28080 [45:25:12<10:01:03,  7.08s/it]
 82%|████████▏ | 22989/28080 [45:25:19<10:02:36,  7.10s/it]
                                                           
{'loss': 0.6072, 'learning_rate': 4.1877625382172405e-05, 'epoch': 9.82}

 82%|████████▏ | 22989/28080 [45:25:19<10:02:36,  7.10s/it]
 82%|████████▏ | 22990/28080 [45:25:26<10:03:26,  7.11s/it]
                                                           
{'loss': 0.598, 'learning_rate': 4.186165060751962e-05, 'epoch': 9.82}

 82%|████████▏ | 22990/28080 [45:25:26<10:03:26,  7.11s/it]
 82%|████████▏ | 22991/28080 [45:25:33<10:03:56,  7.12s/it]
                                                           
{'loss': 0.5957, 'learning_rate': 4.184567860193289e-05, 'epoch': 9.82}

 82%|████████▏ | 22991/28080 [45:25:33<10:03:56,  7.12s/it]
 82%|████████▏ | 22992/28080 [45:25:40<10:02:20,  7.10s/it]
                                                           
{'loss': 0.6059, 'learning_rate': 4.182970936562463e-05, 'epoch': 9.82}

 82%|████████▏ | 22992/28080 [45:25:40<10:02:20,  7.10s/it]
 82%|████████▏ | 22993/28080 [45:25:47<10:00:53,  7.09s/it]
                                                           
{'loss': 0.6106, 'learning_rate': 4.181374289880746e-05, 'epoch': 9.82}

 82%|████████▏ | 22993/28080 [45:25:47<10:00:53,  7.09s/it]
 82%|████████▏ | 22994/28080 [45:25:55<9:59:39,  7.07s/it] 
                                                          
{'loss': 0.605, 'learning_rate': 4.179777920169353e-05, 'epoch': 9.82}

 82%|████████▏ | 22994/28080 [45:25:55<9:59:39,  7.07s/it]
 82%|████████▏ | 22995/28080 [45:26:02<9:57:16,  7.05s/it]
                                                          
{'loss': 0.6176, 'learning_rate': 4.178181827449542e-05, 'epoch': 9.82}

 82%|████████▏ | 22995/28080 [45:26:02<9:57:16,  7.05s/it]
 82%|████████▏ | 22996/28080 [45:26:09<9:59:02,  7.07s/it]
                                                          
{'loss': 0.5966, 'learning_rate': 4.176586011742537e-05, 'epoch': 9.82}

 82%|████████▏ | 22996/28080 [45:26:09<9:59:02,  7.07s/it]
 82%|████████▏ | 22997/28080 [45:26:16<10:00:37,  7.09s/it]
                                                           
{'loss': 0.5901, 'learning_rate': 4.174990473069576e-05, 'epoch': 9.82}

 82%|████████▏ | 22997/28080 [45:26:16<10:00:37,  7.09s/it]
 82%|████████▏ | 22998/28080 [45:26:23<9:59:58,  7.08s/it] 
                                                          
{'loss': 0.6072, 'learning_rate': 4.173395211451883e-05, 'epoch': 9.82}

 82%|████████▏ | 22998/28080 [45:26:23<9:59:58,  7.08s/it]
 82%|████████▏ | 22999/28080 [45:26:30<9:57:44,  7.06s/it]
                                                          
{'loss': 0.6006, 'learning_rate': 4.171800226910683e-05, 'epoch': 9.82}

 82%|████████▏ | 22999/28080 [45:26:30<9:57:44,  7.06s/it]
 82%|████████▏ | 23000/28080 [45:26:37<9:58:57,  7.07s/it]
                                                          
{'loss': 0.6105, 'learning_rate': 4.170205519467185e-05, 'epoch': 9.83}

 82%|████████▏ | 23000/28080 [45:26:37<9:58:57,  7.07s/it]
 82%|████████▏ | 23001/28080 [45:26:44<9:58:31,  7.07s/it]
                                                          
{'loss': 0.6047, 'learning_rate': 4.168611089142621e-05, 'epoch': 9.83}

 82%|████████▏ | 23001/28080 [45:26:44<9:58:31,  7.07s/it]
 82%|████████▏ | 23002/28080 [45:26:51<9:57:41,  7.06s/it]
                                                          
{'loss': 0.611, 'learning_rate': 4.1670169359581954e-05, 'epoch': 9.83}

 82%|████████▏ | 23002/28080 [45:26:51<9:57:41,  7.06s/it]
 82%|████████▏ | 23003/28080 [45:26:58<10:00:38,  7.10s/it]
                                                           
{'loss': 0.5984, 'learning_rate': 4.1654230599351197e-05, 'epoch': 9.83}

 82%|████████▏ | 23003/28080 [45:26:58<10:00:38,  7.10s/it]
 82%|████████▏ | 23004/28080 [45:27:05<10:00:12,  7.09s/it]
                                                           
{'loss': 0.6426, 'learning_rate': 4.163829461094587e-05, 'epoch': 9.83}

 82%|████████▏ | 23004/28080 [45:27:05<10:00:12,  7.09s/it]
 82%|████████▏ | 23005/28080 [45:27:12<9:59:11,  7.08s/it] 
                                                          
{'loss': 0.6277, 'learning_rate': 4.162236139457817e-05, 'epoch': 9.83}

 82%|████████▏ | 23005/28080 [45:27:12<9:59:11,  7.08s/it]
 82%|████████▏ | 23006/28080 [45:27:20<10:01:55,  7.12s/it]
                                                           
{'loss': 0.5827, 'learning_rate': 4.16064309504599e-05, 'epoch': 9.83}

 82%|████████▏ | 23006/28080 [45:27:20<10:01:55,  7.12s/it]
 82%|████████▏ | 23007/28080 [45:27:27<10:00:54,  7.11s/it]
                                                           
{'loss': 0.6151, 'learning_rate': 4.159050327880321e-05, 'epoch': 9.83}

 82%|████████▏ | 23007/28080 [45:27:27<10:00:54,  7.11s/it]
 82%|████████▏ | 23008/28080 [45:27:34<10:02:06,  7.12s/it]
                                                           
{'loss': 0.5991, 'learning_rate': 4.157457837981973e-05, 'epoch': 9.83}

 82%|████████▏ | 23008/28080 [45:27:34<10:02:06,  7.12s/it]
 82%|████████▏ | 23009/28080 [45:27:41<9:59:07,  7.09s/it] 
                                                          
{'loss': 0.6144, 'learning_rate': 4.155865625372154e-05, 'epoch': 9.83}

 82%|████████▏ | 23009/28080 [45:27:41<9:59:07,  7.09s/it]
 82%|████████▏ | 23010/28080 [45:27:48<9:59:49,  7.10s/it]
                                                          
{'loss': 0.5981, 'learning_rate': 4.154273690072033e-05, 'epoch': 9.83}

 82%|████████▏ | 23010/28080 [45:27:48<9:59:49,  7.10s/it]
 82%|████████▏ | 23011/28080 [45:27:55<9:58:08,  7.08s/it]
                                                          
{'loss': 0.608, 'learning_rate': 4.152682032102803e-05, 'epoch': 9.83}

 82%|████████▏ | 23011/28080 [45:27:55<9:58:08,  7.08s/it]
 82%|████████▏ | 23012/28080 [45:28:02<10:01:25,  7.12s/it]
                                                           
{'loss': 0.6116, 'learning_rate': 4.1510906514856284e-05, 'epoch': 9.83}

 82%|████████▏ | 23012/28080 [45:28:02<10:01:25,  7.12s/it]
 82%|████████▏ | 23013/28080 [45:28:09<10:02:31,  7.13s/it]
                                                           
{'loss': 0.6021, 'learning_rate': 4.149499548241686e-05, 'epoch': 9.83}

 82%|████████▏ | 23013/28080 [45:28:09<10:02:31,  7.13s/it]
 82%|████████▏ | 23014/28080 [45:28:16<10:00:22,  7.11s/it]
                                                           
{'loss': 0.6238, 'learning_rate': 4.1479087223921405e-05, 'epoch': 9.83}

 82%|████████▏ | 23014/28080 [45:28:16<10:00:22,  7.11s/it]
 82%|████████▏ | 23015/28080 [45:28:24<10:01:16,  7.12s/it]
                                                           
{'loss': 0.6044, 'learning_rate': 4.146318173958153e-05, 'epoch': 9.83}

 82%|████████▏ | 23015/28080 [45:28:24<10:01:16,  7.12s/it]
 82%|████████▏ | 23016/28080 [45:28:31<10:01:21,  7.13s/it]
                                                           
{'loss': 0.6092, 'learning_rate': 4.144727902960893e-05, 'epoch': 9.83}

 82%|████████▏ | 23016/28080 [45:28:31<10:01:21,  7.13s/it]
 82%|████████▏ | 23017/28080 [45:28:38<10:02:07,  7.14s/it]
                                                           
{'loss': 0.6216, 'learning_rate': 4.1431379094215157e-05, 'epoch': 9.83}

 82%|████████▏ | 23017/28080 [45:28:38<10:02:07,  7.14s/it]
 82%|████████▏ | 23018/28080 [45:28:45<10:00:30,  7.12s/it]
                                                           
{'loss': 0.5997, 'learning_rate': 4.141548193361169e-05, 'epoch': 9.83}

 82%|████████▏ | 23018/28080 [45:28:45<10:00:30,  7.12s/it]
 82%|████████▏ | 23019/28080 [45:28:52<10:02:07,  7.14s/it]
                                                           
{'loss': 0.6093, 'learning_rate': 4.1399587548010015e-05, 'epoch': 9.83}

 82%|████████▏ | 23019/28080 [45:28:52<10:02:07,  7.14s/it]
 82%|████████▏ | 23020/28080 [45:28:59<10:01:11,  7.13s/it]
                                                           
{'loss': 0.5943, 'learning_rate': 4.138369593762167e-05, 'epoch': 9.83}

 82%|████████▏ | 23020/28080 [45:28:59<10:01:11,  7.13s/it]
 82%|████████▏ | 23021/28080 [45:29:06<9:58:16,  7.10s/it] 
                                                          
{'loss': 0.5868, 'learning_rate': 4.136780710265803e-05, 'epoch': 9.83}

 82%|████████▏ | 23021/28080 [45:29:06<9:58:16,  7.10s/it]
 82%|████████▏ | 23022/28080 [45:29:13<10:00:01,  7.12s/it]
                                                           
{'loss': 0.5874, 'learning_rate': 4.1351921043330496e-05, 'epoch': 9.83}

 82%|████████▏ | 23022/28080 [45:29:13<10:00:01,  7.12s/it]
 82%|████████▏ | 23023/28080 [45:29:20<9:57:24,  7.09s/it] 
                                                          
{'loss': 0.5899, 'learning_rate': 4.133603775985031e-05, 'epoch': 9.84}

 82%|████████▏ | 23023/28080 [45:29:20<9:57:24,  7.09s/it]
 82%|████████▏ | 23024/28080 [45:29:28<9:57:28,  7.09s/it]
                                                          
{'loss': 0.5908, 'learning_rate': 4.1320157252428964e-05, 'epoch': 9.84}

 82%|████████▏ | 23024/28080 [45:29:28<9:57:28,  7.09s/it]
 82%|████████▏ | 23025/28080 [45:29:35<9:56:29,  7.08s/it]
                                                          
{'loss': 0.5933, 'learning_rate': 4.1304279521277574e-05, 'epoch': 9.84}

 82%|████████▏ | 23025/28080 [45:29:35<9:56:29,  7.08s/it]
 82%|████████▏ | 23026/28080 [45:29:42<9:56:43,  7.08s/it]
                                                          
{'loss': 0.6109, 'learning_rate': 4.128840456660759e-05, 'epoch': 9.84}

 82%|████████▏ | 23026/28080 [45:29:42<9:56:43,  7.08s/it]
 82%|████████▏ | 23027/28080 [45:29:49<9:58:43,  7.11s/it]
                                                          
{'loss': 0.6085, 'learning_rate': 4.1272532388629906e-05, 'epoch': 9.84}

 82%|████████▏ | 23027/28080 [45:29:49<9:58:43,  7.11s/it]
 82%|████████▏ | 23028/28080 [45:29:56<9:58:09,  7.10s/it]
                                                          
{'loss': 0.6219, 'learning_rate': 4.1256662987555954e-05, 'epoch': 9.84}

 82%|████████▏ | 23028/28080 [45:29:56<9:58:09,  7.10s/it]
 82%|████████▏ | 23029/28080 [45:30:03<9:58:11,  7.11s/it]
                                                          
{'loss': 0.6034, 'learning_rate': 4.124079636359665e-05, 'epoch': 9.84}

 82%|████████▏ | 23029/28080 [45:30:03<9:58:11,  7.11s/it]
 82%|████████▏ | 23030/28080 [45:30:10<9:57:47,  7.10s/it]
                                                          
{'loss': 0.6035, 'learning_rate': 4.122493251696327e-05, 'epoch': 9.84}

 82%|████████▏ | 23030/28080 [45:30:10<9:57:47,  7.10s/it]
 82%|████████▏ | 23031/28080 [45:30:17<9:59:39,  7.13s/it]
                                                          
{'loss': 0.5856, 'learning_rate': 4.120907144786676e-05, 'epoch': 9.84}

 82%|████████▏ | 23031/28080 [45:30:17<9:59:39,  7.13s/it]
 82%|████████▏ | 23032/28080 [45:30:24<9:58:32,  7.11s/it]
                                                          
{'loss': 0.6022, 'learning_rate': 4.119321315651817e-05, 'epoch': 9.84}

 82%|████████▏ | 23032/28080 [45:30:24<9:58:32,  7.11s/it]
 82%|████████▏ | 23033/28080 [45:30:32<10:01:38,  7.15s/it]
                                                           
{'loss': 0.6055, 'learning_rate': 4.117735764312841e-05, 'epoch': 9.84}

 82%|████████▏ | 23033/28080 [45:30:32<10:01:38,  7.15s/it]
 82%|████████▏ | 23034/28080 [45:30:39<10:00:21,  7.14s/it]
                                                           
{'loss': 0.6095, 'learning_rate': 4.116150490790854e-05, 'epoch': 9.84}

 82%|████████▏ | 23034/28080 [45:30:39<10:00:21,  7.14s/it]
 82%|████████▏ | 23035/28080 [45:30:46<10:01:04,  7.15s/it]
                                                           
{'loss': 0.6073, 'learning_rate': 4.114565495106939e-05, 'epoch': 9.84}

 82%|████████▏ | 23035/28080 [45:30:46<10:01:04,  7.15s/it]
 82%|████████▏ | 23036/28080 [45:30:53<10:00:03,  7.14s/it]
                                                           
{'loss': 0.6124, 'learning_rate': 4.112980777282183e-05, 'epoch': 9.84}

 82%|████████▏ | 23036/28080 [45:30:53<10:00:03,  7.14s/it]
 82%|████████▏ | 23037/28080 [45:31:00<10:01:05,  7.15s/it]
                                                           
{'loss': 0.622, 'learning_rate': 4.111396337337667e-05, 'epoch': 9.84}

 82%|████████▏ | 23037/28080 [45:31:00<10:01:05,  7.15s/it]
 82%|████████▏ | 23038/28080 [45:31:07<10:02:23,  7.17s/it]
                                                           
{'loss': 0.6095, 'learning_rate': 4.109812175294475e-05, 'epoch': 9.84}

 82%|████████▏ | 23038/28080 [45:31:07<10:02:23,  7.17s/it]
 82%|████████▏ | 23039/28080 [45:31:15<10:03:05,  7.18s/it]
                                                           
{'loss': 0.5935, 'learning_rate': 4.108228291173682e-05, 'epoch': 9.84}

 82%|████████▏ | 23039/28080 [45:31:15<10:03:05,  7.18s/it]
 82%|████████▏ | 23040/28080 [45:31:22<9:59:39,  7.14s/it] 
                                                          
{'loss': 0.6122, 'learning_rate': 4.106644684996355e-05, 'epoch': 9.84}

 82%|████████▏ | 23040/28080 [45:31:22<9:59:39,  7.14s/it]
 82%|████████▏ | 23041/28080 [45:31:29<9:59:34,  7.14s/it]
                                                          
{'loss': 0.6024, 'learning_rate': 4.105061356783576e-05, 'epoch': 9.84}

 82%|████████▏ | 23041/28080 [45:31:29<9:59:34,  7.14s/it]
 82%|████████▏ | 23042/28080 [45:31:36<9:57:41,  7.12s/it]
                                                          
{'loss': 0.6005, 'learning_rate': 4.103478306556388e-05, 'epoch': 9.84}

 82%|████████▏ | 23042/28080 [45:31:36<9:57:41,  7.12s/it]
 82%|████████▏ | 23043/28080 [45:31:43<9:57:46,  7.12s/it]
                                                          
{'loss': 0.588, 'learning_rate': 4.10189553433587e-05, 'epoch': 9.84}

 82%|████████▏ | 23043/28080 [45:31:43<9:57:46,  7.12s/it]
 82%|████████▏ | 23044/28080 [45:31:50<9:57:02,  7.11s/it]
                                                          
{'loss': 0.6044, 'learning_rate': 4.100313040143067e-05, 'epoch': 9.84}

 82%|████████▏ | 23044/28080 [45:31:50<9:57:02,  7.11s/it]
 82%|████████▏ | 23045/28080 [45:31:57<9:55:56,  7.10s/it]
                                                          
{'loss': 0.599, 'learning_rate': 4.0987308239990416e-05, 'epoch': 9.84}

 82%|████████▏ | 23045/28080 [45:31:57<9:55:56,  7.10s/it]
 82%|████████▏ | 23046/28080 [45:32:04<9:57:14,  7.12s/it]
                                                          
{'loss': 0.6011, 'learning_rate': 4.0971488859248395e-05, 'epoch': 9.85}

 82%|████████▏ | 23046/28080 [45:32:04<9:57:14,  7.12s/it]
 82%|████████▏ | 23047/28080 [45:32:11<9:57:10,  7.12s/it]
                                                          
{'loss': 0.6098, 'learning_rate': 4.09556722594151e-05, 'epoch': 9.85}

 82%|████████▏ | 23047/28080 [45:32:11<9:57:10,  7.12s/it]
 82%|████████▏ | 23048/28080 [45:32:19<9:56:07,  7.11s/it]
                                                          
{'loss': 0.5978, 'learning_rate': 4.0939858440700864e-05, 'epoch': 9.85}

 82%|████████▏ | 23048/28080 [45:32:19<9:56:07,  7.11s/it]
 82%|████████▏ | 23049/28080 [45:32:26<9:55:15,  7.10s/it]
                                                          
{'loss': 0.6093, 'learning_rate': 4.092404740331618e-05, 'epoch': 9.85}

 82%|████████▏ | 23049/28080 [45:32:26<9:55:15,  7.10s/it]
 82%|████████▏ | 23050/28080 [45:32:33<9:51:58,  7.06s/it]
                                                          
{'loss': 0.5937, 'learning_rate': 4.090823914747135e-05, 'epoch': 9.85}

 82%|████████▏ | 23050/28080 [45:32:33<9:51:58,  7.06s/it]
 82%|████████▏ | 23051/28080 [45:32:40<9:54:59,  7.10s/it]
                                                          
{'loss': 0.5918, 'learning_rate': 4.0892433673376724e-05, 'epoch': 9.85}

 82%|████████▏ | 23051/28080 [45:32:40<9:54:59,  7.10s/it]
 82%|████████▏ | 23052/28080 [45:32:47<9:53:19,  7.08s/it]
                                                          
{'loss': 0.6331, 'learning_rate': 4.087663098124245e-05, 'epoch': 9.85}

 82%|████████▏ | 23052/28080 [45:32:47<9:53:19,  7.08s/it]
 82%|████████▏ | 23053/28080 [45:32:54<9:56:33,  7.12s/it]
                                                          
{'loss': 0.5884, 'learning_rate': 4.086083107127894e-05, 'epoch': 9.85}

 82%|████████▏ | 23053/28080 [45:32:54<9:56:33,  7.12s/it]
 82%|████████▏ | 23054/28080 [45:33:01<9:57:37,  7.13s/it]
                                                          
{'loss': 0.6037, 'learning_rate': 4.0845033943696235e-05, 'epoch': 9.85}

 82%|████████▏ | 23054/28080 [45:33:01<9:57:37,  7.13s/it]
 82%|████████▏ | 23055/28080 [45:33:08<9:58:12,  7.14s/it]
                                                          
{'loss': 0.6175, 'learning_rate': 4.082923959870471e-05, 'epoch': 9.85}

 82%|████████▏ | 23055/28080 [45:33:08<9:58:12,  7.14s/it]
 82%|████████▏ | 23056/28080 [45:33:16<9:57:26,  7.14s/it]
                                                          
{'loss': 0.6026, 'learning_rate': 4.0813448036514265e-05, 'epoch': 9.85}

 82%|████████▏ | 23056/28080 [45:33:16<9:57:26,  7.14s/it]
 82%|████████▏ | 23057/28080 [45:33:23<9:57:35,  7.14s/it]
                                                          
{'loss': 0.6023, 'learning_rate': 4.079765925733511e-05, 'epoch': 9.85}

 82%|████████▏ | 23057/28080 [45:33:23<9:57:35,  7.14s/it]
 82%|████████▏ | 23058/28080 [45:33:30<9:56:06,  7.12s/it]
                                                          
{'loss': 0.5925, 'learning_rate': 4.0781873261377254e-05, 'epoch': 9.85}

 82%|████████▏ | 23058/28080 [45:33:30<9:56:06,  7.12s/it]
 82%|████████▏ | 23059/28080 [45:33:37<9:53:34,  7.09s/it]
                                                          
{'loss': 0.6109, 'learning_rate': 4.0766090048850764e-05, 'epoch': 9.85}

 82%|████████▏ | 23059/28080 [45:33:37<9:53:34,  7.09s/it]
 82%|████████▏ | 23060/28080 [45:33:44<9:52:14,  7.08s/it]
                                                          
{'loss': 0.6028, 'learning_rate': 4.075030961996562e-05, 'epoch': 9.85}

 82%|████████▏ | 23060/28080 [45:33:44<9:52:14,  7.08s/it]
 82%|████████▏ | 23061/28080 [45:33:51<9:54:35,  7.11s/it]
                                                          
{'loss': 0.5939, 'learning_rate': 4.073453197493171e-05, 'epoch': 9.85}

 82%|████████▏ | 23061/28080 [45:33:51<9:54:35,  7.11s/it]
 82%|████████▏ | 23062/28080 [45:33:58<9:55:15,  7.12s/it]
                                                          
{'loss': 0.6097, 'learning_rate': 4.071875711395892e-05, 'epoch': 9.85}

 82%|████████▏ | 23062/28080 [45:33:58<9:55:15,  7.12s/it]
 82%|████████▏ | 23063/28080 [45:34:05<9:54:06,  7.11s/it]
                                                          
{'loss': 0.5987, 'learning_rate': 4.0702985037257224e-05, 'epoch': 9.85}

 82%|████████▏ | 23063/28080 [45:34:05<9:54:06,  7.11s/it]
 82%|████████▏ | 23064/28080 [45:34:12<9:54:15,  7.11s/it]
                                                          
{'loss': 0.6113, 'learning_rate': 4.0687215745036364e-05, 'epoch': 9.85}

 82%|████████▏ | 23064/28080 [45:34:12<9:54:15,  7.11s/it]
 82%|████████▏ | 23065/28080 [45:34:20<9:56:14,  7.13s/it]
                                                          
{'loss': 0.6095, 'learning_rate': 4.067144923750621e-05, 'epoch': 9.85}

 82%|████████▏ | 23065/28080 [45:34:20<9:56:14,  7.13s/it]
 82%|████████▏ | 23066/28080 [45:34:27<9:55:53,  7.13s/it]
                                                          
{'loss': 0.6144, 'learning_rate': 4.065568551487645e-05, 'epoch': 9.85}

 82%|████████▏ | 23066/28080 [45:34:27<9:55:53,  7.13s/it]
 82%|████████▏ | 23067/28080 [45:34:34<9:55:52,  7.13s/it]
                                                          
{'loss': 0.5863, 'learning_rate': 4.063992457735674e-05, 'epoch': 9.85}

 82%|████████▏ | 23067/28080 [45:34:34<9:55:52,  7.13s/it]
 82%|████████▏ | 23068/28080 [45:34:41<9:55:40,  7.13s/it]
                                                          
{'loss': 0.6015, 'learning_rate': 4.062416642515693e-05, 'epoch': 9.85}

 82%|████████▏ | 23068/28080 [45:34:41<9:55:40,  7.13s/it]
 82%|████████▏ | 23069/28080 [45:34:48<9:54:00,  7.11s/it]
                                                          
{'loss': 0.5932, 'learning_rate': 4.060841105848659e-05, 'epoch': 9.85}

 82%|████████▏ | 23069/28080 [45:34:48<9:54:00,  7.11s/it]
 82%|████████▏ | 23070/28080 [45:34:55<9:56:10,  7.14s/it]
                                                          
{'loss': 0.5934, 'learning_rate': 4.059265847755533e-05, 'epoch': 9.86}

 82%|████████▏ | 23070/28080 [45:34:55<9:56:10,  7.14s/it]
 82%|████████▏ | 23071/28080 [45:35:02<9:56:25,  7.14s/it]
                                                          
{'loss': 0.5851, 'learning_rate': 4.0576908682572633e-05, 'epoch': 9.86}

 82%|████████▏ | 23071/28080 [45:35:02<9:56:25,  7.14s/it]
 82%|████████▏ | 23072/28080 [45:35:10<9:57:45,  7.16s/it]
                                                          
{'loss': 0.6089, 'learning_rate': 4.056116167374818e-05, 'epoch': 9.86}

 82%|████████▏ | 23072/28080 [45:35:10<9:57:45,  7.16s/it]
 82%|████████▏ | 23073/28080 [45:35:17<9:54:38,  7.13s/it]
                                                          
{'loss': 0.5856, 'learning_rate': 4.054541745129137e-05, 'epoch': 9.86}

 82%|████████▏ | 23073/28080 [45:35:17<9:54:38,  7.13s/it]
 82%|████████▏ | 23074/28080 [45:35:24<9:54:19,  7.12s/it]
                                                          
{'loss': 0.5943, 'learning_rate': 4.05296760154118e-05, 'epoch': 9.86}

 82%|████████▏ | 23074/28080 [45:35:24<9:54:19,  7.12s/it]
 82%|████████▏ | 23075/28080 [45:35:31<9:53:51,  7.12s/it]
                                                          
{'loss': 0.5795, 'learning_rate': 4.051393736631867e-05, 'epoch': 9.86}

 82%|████████▏ | 23075/28080 [45:35:31<9:53:51,  7.12s/it]
 82%|████████▏ | 23076/28080 [45:35:38<9:52:35,  7.11s/it]
                                                          
{'loss': 0.6002, 'learning_rate': 4.0498201504221536e-05, 'epoch': 9.86}

 82%|████████▏ | 23076/28080 [45:35:38<9:52:35,  7.11s/it]
 82%|████████▏ | 23077/28080 [45:35:45<9:51:02,  7.09s/it]
                                                          
{'loss': 0.599, 'learning_rate': 4.048246842932968e-05, 'epoch': 9.86}

 82%|████████▏ | 23077/28080 [45:35:45<9:51:02,  7.09s/it]
 82%|████████▏ | 23078/28080 [45:35:52<9:51:07,  7.09s/it]
                                                          
{'loss': 0.6076, 'learning_rate': 4.046673814185245e-05, 'epoch': 9.86}

 82%|████████▏ | 23078/28080 [45:35:52<9:51:07,  7.09s/it]
 82%|████████▏ | 23079/28080 [45:35:59<9:52:13,  7.11s/it]
                                                          
{'loss': 0.6191, 'learning_rate': 4.045101064199913e-05, 'epoch': 9.86}

 82%|████████▏ | 23079/28080 [45:35:59<9:52:13,  7.11s/it]
 82%|████████▏ | 23080/28080 [45:36:06<9:50:47,  7.09s/it]
                                                          
{'loss': 0.6069, 'learning_rate': 4.043528592997894e-05, 'epoch': 9.86}

 82%|████████▏ | 23080/28080 [45:36:06<9:50:47,  7.09s/it]
 82%|████████▏ | 23081/28080 [45:36:13<9:53:21,  7.12s/it]
                                                          
{'loss': 0.5916, 'learning_rate': 4.0419564006000995e-05, 'epoch': 9.86}

 82%|████████▏ | 23081/28080 [45:36:13<9:53:21,  7.12s/it]
 82%|████████▏ | 23082/28080 [45:36:20<9:51:34,  7.10s/it]
                                                          
{'loss': 0.6192, 'learning_rate': 4.0403844870274625e-05, 'epoch': 9.86}

 82%|████████▏ | 23082/28080 [45:36:20<9:51:34,  7.10s/it]
 82%|████████▏ | 23083/28080 [45:36:28<9:52:27,  7.11s/it]
                                                          
{'loss': 0.5861, 'learning_rate': 4.038812852300885e-05, 'epoch': 9.86}

 82%|████████▏ | 23083/28080 [45:36:28<9:52:27,  7.11s/it]
 82%|████████▏ | 23084/28080 [45:36:35<9:49:47,  7.08s/it]
                                                          
{'loss': 0.5938, 'learning_rate': 4.0372414964412765e-05, 'epoch': 9.86}

 82%|████████▏ | 23084/28080 [45:36:35<9:49:47,  7.08s/it]
 82%|████████▏ | 23085/28080 [45:36:42<9:47:59,  7.06s/it]
                                                          
{'loss': 0.6051, 'learning_rate': 4.035670419469542e-05, 'epoch': 9.86}

 82%|████████▏ | 23085/28080 [45:36:42<9:47:59,  7.06s/it]
 82%|████████▏ | 23086/28080 [45:36:49<9:49:07,  7.08s/it]
                                                          
{'loss': 0.601, 'learning_rate': 4.034099621406587e-05, 'epoch': 9.86}

 82%|████████▏ | 23086/28080 [45:36:49<9:49:07,  7.08s/it]
 82%|████████▏ | 23087/28080 [45:36:56<9:48:57,  7.08s/it]
                                                          
{'loss': 0.6135, 'learning_rate': 4.0325291022733104e-05, 'epoch': 9.86}

 82%|████████▏ | 23087/28080 [45:36:56<9:48:57,  7.08s/it]
 82%|████████▏ | 23088/28080 [45:37:03<9:51:01,  7.10s/it]
                                                          
{'loss': 0.6097, 'learning_rate': 4.0309588620906e-05, 'epoch': 9.86}

 82%|████████▏ | 23088/28080 [45:37:03<9:51:01,  7.10s/it]
 82%|████████▏ | 23089/28080 [45:37:10<9:48:47,  7.08s/it]
                                                          
{'loss': 0.6082, 'learning_rate': 4.0293889008793524e-05, 'epoch': 9.86}

 82%|████████▏ | 23089/28080 [45:37:10<9:48:47,  7.08s/it]
 82%|████████▏ | 23090/28080 [45:37:17<9:50:53,  7.10s/it]
                                                          
{'loss': 0.6014, 'learning_rate': 4.0278192186604416e-05, 'epoch': 9.86}

 82%|████████▏ | 23090/28080 [45:37:17<9:50:53,  7.10s/it]
 82%|████████▏ | 23091/28080 [45:37:24<9:52:02,  7.12s/it]
                                                          
{'loss': 0.6128, 'learning_rate': 4.026249815454769e-05, 'epoch': 9.86}

 82%|████████▏ | 23091/28080 [45:37:24<9:52:02,  7.12s/it]
 82%|████████▏ | 23092/28080 [45:37:31<9:48:58,  7.08s/it]
                                                          
{'loss': 0.5932, 'learning_rate': 4.0246806912832003e-05, 'epoch': 9.86}

 82%|████████▏ | 23092/28080 [45:37:31<9:48:58,  7.08s/it]
 82%|████████▏ | 23093/28080 [45:37:39<9:51:23,  7.12s/it]
                                                          
{'loss': 0.6061, 'learning_rate': 4.023111846166619e-05, 'epoch': 9.87}

 82%|████████▏ | 23093/28080 [45:37:39<9:51:23,  7.12s/it]
 82%|████████▏ | 23094/28080 [45:37:46<9:52:30,  7.13s/it]
                                                          
{'loss': 0.6002, 'learning_rate': 4.021543280125897e-05, 'epoch': 9.87}

 82%|████████▏ | 23094/28080 [45:37:46<9:52:30,  7.13s/it]
 82%|████████▏ | 23095/28080 [45:37:53<9:51:02,  7.11s/it]
                                                          
{'loss': 0.578, 'learning_rate': 4.019974993181896e-05, 'epoch': 9.87}

 82%|████████▏ | 23095/28080 [45:37:53<9:51:02,  7.11s/it]
 82%|████████▏ | 23096/28080 [45:38:00<9:50:23,  7.11s/it]
                                                          
{'loss': 0.5939, 'learning_rate': 4.01840698535548e-05, 'epoch': 9.87}

 82%|████████▏ | 23096/28080 [45:38:00<9:50:23,  7.11s/it]
 82%|████████▏ | 23097/28080 [45:38:07<9:52:42,  7.14s/it]
                                                          
{'loss': 0.5976, 'learning_rate': 4.0168392566675204e-05, 'epoch': 9.87}

 82%|████████▏ | 23097/28080 [45:38:07<9:52:42,  7.14s/it]
 82%|████████▏ | 23098/28080 [45:38:14<9:50:52,  7.12s/it]
                                                          
{'loss': 0.5959, 'learning_rate': 4.015271807138865e-05, 'epoch': 9.87}

 82%|████████▏ | 23098/28080 [45:38:14<9:50:52,  7.12s/it]
 82%|████████▏ | 23099/28080 [45:38:21<9:47:49,  7.08s/it]
                                                          
{'loss': 0.5985, 'learning_rate': 4.013704636790372e-05, 'epoch': 9.87}

 82%|████████▏ | 23099/28080 [45:38:21<9:47:49,  7.08s/it]
 82%|████████▏ | 23100/28080 [45:38:28<9:49:41,  7.10s/it]
                                                          
{'loss': 0.5848, 'learning_rate': 4.0121377456428795e-05, 'epoch': 9.87}

 82%|████████▏ | 23100/28080 [45:38:28<9:49:41,  7.10s/it]
 82%|████████▏ | 23101/28080 [45:38:35<9:51:21,  7.13s/it]
                                                          
{'loss': 0.5989, 'learning_rate': 4.0105711337172505e-05, 'epoch': 9.87}

 82%|████████▏ | 23101/28080 [45:38:35<9:51:21,  7.13s/it]
 82%|████████▏ | 23102/28080 [45:38:43<9:50:46,  7.12s/it]
                                                          
{'loss': 0.5931, 'learning_rate': 4.0090048010343135e-05, 'epoch': 9.87}

 82%|████████▏ | 23102/28080 [45:38:43<9:50:46,  7.12s/it]
 82%|████████▏ | 23103/28080 [45:38:50<9:46:27,  7.07s/it]
                                                          
{'loss': 0.6066, 'learning_rate': 4.007438747614922e-05, 'epoch': 9.87}

 82%|████████▏ | 23103/28080 [45:38:50<9:46:27,  7.07s/it]
 82%|████████▏ | 23104/28080 [45:38:57<9:48:45,  7.10s/it]
                                                          
{'loss': 0.6035, 'learning_rate': 4.00587297347989e-05, 'epoch': 9.87}

 82%|████████▏ | 23104/28080 [45:38:57<9:48:45,  7.10s/it]
 82%|████████▏ | 23105/28080 [45:39:04<9:47:31,  7.09s/it]
                                                          
{'loss': 0.5913, 'learning_rate': 4.004307478650066e-05, 'epoch': 9.87}

 82%|████████▏ | 23105/28080 [45:39:04<9:47:31,  7.09s/it]
 82%|████████▏ | 23106/28080 [45:39:11<9:48:42,  7.10s/it]
                                                          
{'loss': 0.5918, 'learning_rate': 4.002742263146264e-05, 'epoch': 9.87}

 82%|████████▏ | 23106/28080 [45:39:11<9:48:42,  7.10s/it]
 82%|████████▏ | 23107/28080 [45:39:18<9:50:00,  7.12s/it]
                                                          
{'loss': 0.6179, 'learning_rate': 4.001177326989322e-05, 'epoch': 9.87}

 82%|████████▏ | 23107/28080 [45:39:18<9:50:00,  7.12s/it]
 82%|████████▏ | 23108/28080 [45:39:25<9:48:37,  7.10s/it]
                                                          
{'loss': 0.6047, 'learning_rate': 3.9996126702000536e-05, 'epoch': 9.87}

 82%|████████▏ | 23108/28080 [45:39:25<9:48:37,  7.10s/it]
 82%|████████▏ | 23109/28080 [45:39:32<9:49:40,  7.12s/it]
                                                          
{'loss': 0.5971, 'learning_rate': 3.9980482927992694e-05, 'epoch': 9.87}

 82%|████████▏ | 23109/28080 [45:39:32<9:49:40,  7.12s/it]
 82%|████████▏ | 23110/28080 [45:39:39<9:47:50,  7.10s/it]
                                                          
{'loss': 0.6027, 'learning_rate': 3.996484194807784e-05, 'epoch': 9.87}

 82%|████████▏ | 23110/28080 [45:39:39<9:47:50,  7.10s/it]
 82%|████████▏ | 23111/28080 [45:39:46<9:48:08,  7.10s/it]
                                                          
{'loss': 0.5908, 'learning_rate': 3.9949203762464136e-05, 'epoch': 9.87}

 82%|████████▏ | 23111/28080 [45:39:46<9:48:08,  7.10s/it]
 82%|████████▏ | 23112/28080 [45:39:54<9:49:22,  7.12s/it]
                                                          
{'loss': 0.5934, 'learning_rate': 3.993356837135956e-05, 'epoch': 9.87}

 82%|████████▏ | 23112/28080 [45:39:54<9:49:22,  7.12s/it]
 82%|████████▏ | 23113/28080 [45:40:01<9:49:17,  7.12s/it]
                                                          
{'loss': 0.5966, 'learning_rate': 3.9917935774972156e-05, 'epoch': 9.87}

 82%|████████▏ | 23113/28080 [45:40:01<9:49:17,  7.12s/it]
 82%|████████▏ | 23114/28080 [45:40:08<9:48:02,  7.10s/it]
                                                          
{'loss': 0.6098, 'learning_rate': 3.990230597350988e-05, 'epoch': 9.87}

 82%|████████▏ | 23114/28080 [45:40:08<9:48:02,  7.10s/it]
 82%|████████▏ | 23115/28080 [45:40:15<9:48:41,  7.11s/it]
                                                          
{'loss': 0.5991, 'learning_rate': 3.988667896718065e-05, 'epoch': 9.87}

 82%|████████▏ | 23115/28080 [45:40:15<9:48:41,  7.11s/it]
 82%|████████▏ | 23116/28080 [45:40:22<9:53:20,  7.17s/it]
                                                          
{'loss': 0.6007, 'learning_rate': 3.987105475619243e-05, 'epoch': 9.87}

 82%|████████▏ | 23116/28080 [45:40:22<9:53:20,  7.17s/it]
 82%|████████▏ | 23117/28080 [45:40:29<9:51:02,  7.15s/it]
                                                          
{'loss': 0.6224, 'learning_rate': 3.9855433340753035e-05, 'epoch': 9.88}

 82%|████████▏ | 23117/28080 [45:40:29<9:51:02,  7.15s/it]
 82%|████████▏ | 23118/28080 [45:40:36<9:49:25,  7.13s/it]
                                                          
{'loss': 0.5898, 'learning_rate': 3.9839814721070314e-05, 'epoch': 9.88}

 82%|████████▏ | 23118/28080 [45:40:36<9:49:25,  7.13s/it]
 82%|████████▏ | 23119/28080 [45:40:43<9:47:33,  7.11s/it]
                                                          
{'loss': 0.5929, 'learning_rate': 3.9824198897352e-05, 'epoch': 9.88}

 82%|████████▏ | 23119/28080 [45:40:43<9:47:33,  7.11s/it]
 82%|████████▏ | 23120/28080 [45:40:51<9:48:28,  7.12s/it]
                                                          
{'loss': 0.5991, 'learning_rate': 3.980858586980593e-05, 'epoch': 9.88}

 82%|████████▏ | 23120/28080 [45:40:51<9:48:28,  7.12s/it]
 82%|████████▏ | 23121/28080 [45:40:58<9:47:52,  7.11s/it]
                                                          
{'loss': 0.6219, 'learning_rate': 3.9792975638639764e-05, 'epoch': 9.88}

 82%|████████▏ | 23121/28080 [45:40:58<9:47:52,  7.11s/it]
 82%|████████▏ | 23122/28080 [45:41:05<9:47:05,  7.10s/it]
                                                          
{'loss': 0.61, 'learning_rate': 3.977736820406128e-05, 'epoch': 9.88}

 82%|████████▏ | 23122/28080 [45:41:05<9:47:05,  7.10s/it]
 82%|████████▏ | 23123/28080 [45:41:12<9:47:51,  7.12s/it]
                                                          
{'loss': 0.6097, 'learning_rate': 3.976176356627792e-05, 'epoch': 9.88}

 82%|████████▏ | 23123/28080 [45:41:12<9:47:51,  7.12s/it]
 82%|████████▏ | 23124/28080 [45:41:19<9:47:55,  7.12s/it]
                                                          
{'loss': 0.6183, 'learning_rate': 3.974616172549747e-05, 'epoch': 9.88}

 82%|████████▏ | 23124/28080 [45:41:19<9:47:55,  7.12s/it]
 82%|████████▏ | 23125/28080 [45:41:26<9:46:15,  7.10s/it]
                                                          
{'loss': 0.5988, 'learning_rate': 3.973056268192737e-05, 'epoch': 9.88}

 82%|████████▏ | 23125/28080 [45:41:26<9:46:15,  7.10s/it]
 82%|████████▏ | 23126/28080 [45:41:33<9:47:25,  7.11s/it]
                                                          
{'loss': 0.5987, 'learning_rate': 3.97149664357753e-05, 'epoch': 9.88}

 82%|████████▏ | 23126/28080 [45:41:33<9:47:25,  7.11s/it]
 82%|████████▏ | 23127/28080 [45:41:40<9:46:29,  7.10s/it]
                                                          
{'loss': 0.5836, 'learning_rate': 3.9699372987248625e-05, 'epoch': 9.88}

 82%|████████▏ | 23127/28080 [45:41:40<9:46:29,  7.10s/it]
 82%|████████▏ | 23128/28080 [45:41:47<9:47:25,  7.12s/it]
                                                          
{'loss': 0.6063, 'learning_rate': 3.9683782336554866e-05, 'epoch': 9.88}

 82%|████████▏ | 23128/28080 [45:41:47<9:47:25,  7.12s/it]
 82%|████████▏ | 23129/28080 [45:41:55<9:45:56,  7.10s/it]
                                                          
{'loss': 0.5987, 'learning_rate': 3.966819448390133e-05, 'epoch': 9.88}

 82%|████████▏ | 23129/28080 [45:41:55<9:45:56,  7.10s/it]
 82%|████████▏ | 23130/28080 [45:42:02<9:46:31,  7.11s/it]
                                                          
{'loss': 0.5919, 'learning_rate': 3.9652609429495556e-05, 'epoch': 9.88}

 82%|████████▏ | 23130/28080 [45:42:02<9:46:31,  7.11s/it]
 82%|████████▏ | 23131/28080 [45:42:09<9:48:35,  7.14s/it]
                                                          
{'loss': 0.6034, 'learning_rate': 3.963702717354478e-05, 'epoch': 9.88}

 82%|████████▏ | 23131/28080 [45:42:09<9:48:35,  7.14s/it]
 82%|████████▏ | 23132/28080 [45:42:16<9:45:51,  7.10s/it]
                                                          
{'loss': 0.6034, 'learning_rate': 3.962144771625637e-05, 'epoch': 9.88}

 82%|████████▏ | 23132/28080 [45:42:16<9:45:51,  7.10s/it]
 82%|████████▏ | 23133/28080 [45:42:23<9:47:05,  7.12s/it]
                                                          
{'loss': 0.5975, 'learning_rate': 3.96058710578375e-05, 'epoch': 9.88}

 82%|████████▏ | 23133/28080 [45:42:23<9:47:05,  7.12s/it]
 82%|████████▏ | 23134/28080 [45:42:30<9:47:02,  7.12s/it]
                                                          
{'loss': 0.5812, 'learning_rate': 3.9590297198495494e-05, 'epoch': 9.88}

 82%|████████▏ | 23134/28080 [45:42:30<9:47:02,  7.12s/it]
 82%|████████▏ | 23135/28080 [45:42:37<9:46:45,  7.12s/it]
                                                          
{'loss': 0.5853, 'learning_rate': 3.957472613843749e-05, 'epoch': 9.88}

 82%|████████▏ | 23135/28080 [45:42:37<9:46:45,  7.12s/it]
 82%|████████▏ | 23136/28080 [45:42:44<9:48:38,  7.14s/it]
                                                          
{'loss': 0.6088, 'learning_rate': 3.955915787787079e-05, 'epoch': 9.88}

 82%|████████▏ | 23136/28080 [45:42:44<9:48:38,  7.14s/it]
 82%|████████▏ | 23137/28080 [45:42:52<9:48:32,  7.14s/it]
                                                          
{'loss': 0.584, 'learning_rate': 3.954359241700231e-05, 'epoch': 9.88}

 82%|████████▏ | 23137/28080 [45:42:52<9:48:32,  7.14s/it]
 82%|████████▏ | 23138/28080 [45:42:59<9:48:40,  7.15s/it]
                                                          
{'loss': 0.5967, 'learning_rate': 3.952802975603917e-05, 'epoch': 9.88}

 82%|████████▏ | 23138/28080 [45:42:59<9:48:40,  7.15s/it]
 82%|████████▏ | 23139/28080 [45:43:06<9:49:49,  7.16s/it]
                                                          
{'loss': 0.6063, 'learning_rate': 3.951246989518853e-05, 'epoch': 9.88}

 82%|████████▏ | 23139/28080 [45:43:06<9:49:49,  7.16s/it]
 82%|████████▏ | 23140/28080 [45:43:13<9:48:03,  7.14s/it]
                                                          
{'loss': 0.6119, 'learning_rate': 3.949691283465726e-05, 'epoch': 9.89}

 82%|████████▏ | 23140/28080 [45:43:13<9:48:03,  7.14s/it]
 82%|████████▏ | 23141/28080 [45:43:20<9:46:59,  7.13s/it]
                                                          
{'loss': 0.6208, 'learning_rate': 3.948135857465246e-05, 'epoch': 9.89}

 82%|████████▏ | 23141/28080 [45:43:20<9:46:59,  7.13s/it]
 82%|████████▏ | 23142/28080 [45:43:27<9:43:49,  7.09s/it]
                                                          
{'loss': 0.5931, 'learning_rate': 3.9465807115381e-05, 'epoch': 9.89}

 82%|████████▏ | 23142/28080 [45:43:27<9:43:49,  7.09s/it]
 82%|████████▏ | 23143/28080 [45:43:34<9:45:39,  7.12s/it]
                                                          
{'loss': 0.5817, 'learning_rate': 3.9450258457049806e-05, 'epoch': 9.89}

 82%|████████▏ | 23143/28080 [45:43:34<9:45:39,  7.12s/it]
 82%|████████▏ | 23144/28080 [45:43:41<9:44:58,  7.11s/it]
                                                          
{'loss': 0.5984, 'learning_rate': 3.943471259986561e-05, 'epoch': 9.89}

 82%|████████▏ | 23144/28080 [45:43:41<9:44:58,  7.11s/it]
 82%|████████▏ | 23145/28080 [45:43:48<9:42:08,  7.08s/it]
                                                          
{'loss': 0.6185, 'learning_rate': 3.941916954403543e-05, 'epoch': 9.89}

 82%|████████▏ | 23145/28080 [45:43:48<9:42:08,  7.08s/it]
 82%|████████▏ | 23146/28080 [45:43:56<9:42:32,  7.08s/it]
                                                          
{'loss': 0.6229, 'learning_rate': 3.940362928976593e-05, 'epoch': 9.89}

 82%|████████▏ | 23146/28080 [45:43:56<9:42:32,  7.08s/it]
 82%|████████▏ | 23147/28080 [45:44:03<9:44:46,  7.11s/it]
                                                          
{'loss': 0.5943, 'learning_rate': 3.938809183726391e-05, 'epoch': 9.89}

 82%|████████▏ | 23147/28080 [45:44:03<9:44:46,  7.11s/it]
 82%|████████▏ | 23148/28080 [45:44:10<9:43:37,  7.10s/it]
                                                          
{'loss': 0.6253, 'learning_rate': 3.937255718673596e-05, 'epoch': 9.89}

 82%|████████▏ | 23148/28080 [45:44:10<9:43:37,  7.10s/it]
 82%|████████▏ | 23149/28080 [45:44:17<9:43:18,  7.10s/it]
                                                          
{'loss': 0.6143, 'learning_rate': 3.935702533838892e-05, 'epoch': 9.89}

 82%|████████▏ | 23149/28080 [45:44:17<9:43:18,  7.10s/it]
 82%|████████▏ | 23150/28080 [45:44:24<9:42:55,  7.09s/it]
                                                          
{'loss': 0.6021, 'learning_rate': 3.934149629242936e-05, 'epoch': 9.89}

 82%|████████▏ | 23150/28080 [45:44:24<9:42:55,  7.09s/it]
 82%|████████▏ | 23151/28080 [45:44:31<9:38:24,  7.04s/it]
                                                          
{'loss': 0.5909, 'learning_rate': 3.9325970049063855e-05, 'epoch': 9.89}

 82%|████████▏ | 23151/28080 [45:44:31<9:38:24,  7.04s/it]
 82%|████████▏ | 23152/28080 [45:44:38<9:42:52,  7.10s/it]
                                                          
{'loss': 0.585, 'learning_rate': 3.9310446608498916e-05, 'epoch': 9.89}

 82%|████████▏ | 23152/28080 [45:44:38<9:42:52,  7.10s/it]
 82%|████████▏ | 23153/28080 [45:44:45<9:42:08,  7.09s/it]
                                                          
{'loss': 0.5944, 'learning_rate': 3.92949259709412e-05, 'epoch': 9.89}

 82%|████████▏ | 23153/28080 [45:44:45<9:42:08,  7.09s/it]
 82%|████████▏ | 23154/28080 [45:44:52<9:42:31,  7.10s/it]
                                                          
{'loss': 0.5854, 'learning_rate': 3.927940813659706e-05, 'epoch': 9.89}

 82%|████████▏ | 23154/28080 [45:44:52<9:42:31,  7.10s/it]
 82%|████████▏ | 23155/28080 [45:44:59<9:44:05,  7.12s/it]
                                                          
{'loss': 0.6087, 'learning_rate': 3.926389310567305e-05, 'epoch': 9.89}

 82%|████████▏ | 23155/28080 [45:44:59<9:44:05,  7.12s/it]
 82%|████████▏ | 23156/28080 [45:45:06<9:40:37,  7.07s/it]
                                                          
{'loss': 0.6051, 'learning_rate': 3.9248380878375566e-05, 'epoch': 9.89}

 82%|████████▏ | 23156/28080 [45:45:06<9:40:37,  7.07s/it]
 82%|████████▏ | 23157/28080 [45:45:13<9:38:40,  7.05s/it]
                                                          
{'loss': 0.5965, 'learning_rate': 3.9232871454910946e-05, 'epoch': 9.89}

 82%|████████▏ | 23157/28080 [45:45:13<9:38:40,  7.05s/it]
 82%|████████▏ | 23158/28080 [45:45:21<9:40:32,  7.08s/it]
                                                          
{'loss': 0.6066, 'learning_rate': 3.9217364835485465e-05, 'epoch': 9.89}

 82%|████████▏ | 23158/28080 [45:45:21<9:40:32,  7.08s/it]
 82%|████████▏ | 23159/28080 [45:45:28<9:41:04,  7.08s/it]
                                                          
{'loss': 0.615, 'learning_rate': 3.920186102030554e-05, 'epoch': 9.89}

 82%|████████▏ | 23159/28080 [45:45:28<9:41:04,  7.08s/it]
 82%|████████▏ | 23160/28080 [45:45:35<9:41:02,  7.09s/it]
                                                          
{'loss': 0.5867, 'learning_rate': 3.91863600095774e-05, 'epoch': 9.89}

 82%|████████▏ | 23160/28080 [45:45:35<9:41:02,  7.09s/it]
 82%|████████▏ | 23161/28080 [45:45:42<9:43:17,  7.11s/it]
                                                          
{'loss': 0.5982, 'learning_rate': 3.9170861803507266e-05, 'epoch': 9.89}

 82%|████████▏ | 23161/28080 [45:45:42<9:43:17,  7.11s/it]
 82%|████████▏ | 23162/28080 [45:45:49<9:44:09,  7.13s/it]
                                                          
{'loss': 0.5999, 'learning_rate': 3.91553664023013e-05, 'epoch': 9.89}

 82%|████████▏ | 23162/28080 [45:45:49<9:44:09,  7.13s/it]
 82%|████████▏ | 23163/28080 [45:45:56<9:43:33,  7.12s/it]
                                                          
{'loss': 0.6041, 'learning_rate': 3.91398738061656e-05, 'epoch': 9.9}

 82%|████████▏ | 23163/28080 [45:45:56<9:43:33,  7.12s/it]
 82%|████████▏ | 23164/28080 [45:46:03<9:42:33,  7.11s/it]
                                                          
{'loss': 0.5835, 'learning_rate': 3.912438401530644e-05, 'epoch': 9.9}

 82%|████████▏ | 23164/28080 [45:46:03<9:42:33,  7.11s/it]
 82%|████████▏ | 23165/28080 [45:46:10<9:43:13,  7.12s/it]
                                                          
{'loss': 0.5837, 'learning_rate': 3.9108897029929787e-05, 'epoch': 9.9}

 82%|████████▏ | 23165/28080 [45:46:10<9:43:13,  7.12s/it]
 82%|████████▎ | 23166/28080 [45:46:18<9:42:46,  7.12s/it]
                                                          
{'loss': 0.5736, 'learning_rate': 3.909341285024168e-05, 'epoch': 9.9}

 82%|████████▎ | 23166/28080 [45:46:18<9:42:46,  7.12s/it]
 83%|████████▎ | 23167/28080 [45:46:25<9:45:12,  7.15s/it]
                                                          
{'loss': 0.6003, 'learning_rate': 3.907793147644808e-05, 'epoch': 9.9}

 83%|████████▎ | 23167/28080 [45:46:25<9:45:12,  7.15s/it]
 83%|████████▎ | 23168/28080 [45:46:32<9:45:32,  7.15s/it]
                                                          
{'loss': 0.5962, 'learning_rate': 3.906245290875507e-05, 'epoch': 9.9}

 83%|████████▎ | 23168/28080 [45:46:32<9:45:32,  7.15s/it]
 83%|████████▎ | 23169/28080 [45:46:39<9:44:26,  7.14s/it]
                                                          
{'loss': 0.5922, 'learning_rate': 3.9046977147368464e-05, 'epoch': 9.9}

 83%|████████▎ | 23169/28080 [45:46:39<9:44:26,  7.14s/it]
 83%|████████▎ | 23170/28080 [45:46:46<9:43:53,  7.14s/it]
                                                          
{'loss': 0.6201, 'learning_rate': 3.9031504192494293e-05, 'epoch': 9.9}

 83%|████████▎ | 23170/28080 [45:46:46<9:43:53,  7.14s/it]
 83%|████████▎ | 23171/28080 [45:46:53<9:40:29,  7.09s/it]
                                                          
{'loss': 0.612, 'learning_rate': 3.9016034044338204e-05, 'epoch': 9.9}

 83%|████████▎ | 23171/28080 [45:46:53<9:40:29,  7.09s/it]
 83%|████████▎ | 23172/28080 [45:47:00<9:40:18,  7.09s/it]
                                                          
{'loss': 0.5931, 'learning_rate': 3.90005667031062e-05, 'epoch': 9.9}

 83%|████████▎ | 23172/28080 [45:47:00<9:40:18,  7.09s/it]
 83%|████████▎ | 23173/28080 [45:47:07<9:42:51,  7.13s/it]
                                                          
{'loss': 0.585, 'learning_rate': 3.898510216900389e-05, 'epoch': 9.9}

 83%|████████▎ | 23173/28080 [45:47:07<9:42:51,  7.13s/it]
 83%|████████▎ | 23174/28080 [45:47:15<9:43:22,  7.13s/it]
                                                          
{'loss': 0.5808, 'learning_rate': 3.896964044223719e-05, 'epoch': 9.9}

 83%|████████▎ | 23174/28080 [45:47:15<9:43:22,  7.13s/it]
 83%|████████▎ | 23175/28080 [45:47:22<9:40:38,  7.10s/it]
                                                          
{'loss': 0.6152, 'learning_rate': 3.8954181523011696e-05, 'epoch': 9.9}

 83%|████████▎ | 23175/28080 [45:47:22<9:40:38,  7.10s/it]
 83%|████████▎ | 23176/28080 [45:47:29<9:39:47,  7.09s/it]
                                                          
{'loss': 0.6191, 'learning_rate': 3.893872541153312e-05, 'epoch': 9.9}

 83%|████████▎ | 23176/28080 [45:47:29<9:39:47,  7.09s/it]
 83%|████████▎ | 23177/28080 [45:47:36<9:42:18,  7.13s/it]
                                                          
{'loss': 0.5902, 'learning_rate': 3.892327210800697e-05, 'epoch': 9.9}

 83%|████████▎ | 23177/28080 [45:47:36<9:42:18,  7.13s/it]
 83%|████████▎ | 23178/28080 [45:47:43<9:42:12,  7.13s/it]
                                                          
{'loss': 0.605, 'learning_rate': 3.8907821612639006e-05, 'epoch': 9.9}

 83%|████████▎ | 23178/28080 [45:47:43<9:42:12,  7.13s/it]
 83%|████████▎ | 23179/28080 [45:47:50<9:38:33,  7.08s/it]
                                                          
{'loss': 0.5813, 'learning_rate': 3.889237392563472e-05, 'epoch': 9.9}

 83%|████████▎ | 23179/28080 [45:47:50<9:38:33,  7.08s/it]
 83%|████████▎ | 23180/28080 [45:47:57<9:37:57,  7.08s/it]
                                                          
{'loss': 0.6057, 'learning_rate': 3.887692904719958e-05, 'epoch': 9.9}

 83%|████████▎ | 23180/28080 [45:47:57<9:37:57,  7.08s/it]
 83%|████████▎ | 23181/28080 [45:48:04<9:37:28,  7.07s/it]
                                                          
{'loss': 0.5932, 'learning_rate': 3.886148697753905e-05, 'epoch': 9.9}

 83%|████████▎ | 23181/28080 [45:48:04<9:37:28,  7.07s/it]
 83%|████████▎ | 23182/28080 [45:48:11<9:39:10,  7.09s/it]
                                                          
{'loss': 0.5944, 'learning_rate': 3.8846047716858677e-05, 'epoch': 9.9}

 83%|████████▎ | 23182/28080 [45:48:11<9:39:10,  7.09s/it]
 83%|████████▎ | 23183/28080 [45:48:18<9:39:50,  7.10s/it]
                                                          
{'loss': 0.5751, 'learning_rate': 3.8830611265363744e-05, 'epoch': 9.9}

 83%|████████▎ | 23183/28080 [45:48:18<9:39:50,  7.10s/it]
 83%|████████▎ | 23184/28080 [45:48:25<9:36:52,  7.07s/it]
                                                          
{'loss': 0.6215, 'learning_rate': 3.881517762325978e-05, 'epoch': 9.9}

 83%|████████▎ | 23184/28080 [45:48:25<9:36:52,  7.07s/it]
 83%|████████▎ | 23185/28080 [45:48:33<9:39:30,  7.10s/it]
                                                          
{'loss': 0.5918, 'learning_rate': 3.8799746790751904e-05, 'epoch': 9.9}

 83%|████████▎ | 23185/28080 [45:48:33<9:39:30,  7.10s/it]
 83%|████████▎ | 23186/28080 [45:48:40<9:37:13,  7.08s/it]
                                                          
{'loss': 0.5776, 'learning_rate': 3.878431876804558e-05, 'epoch': 9.9}

 83%|████████▎ | 23186/28080 [45:48:40<9:37:13,  7.08s/it]
 83%|████████▎ | 23187/28080 [45:48:47<9:35:39,  7.06s/it]
                                                          
{'loss': 0.6106, 'learning_rate': 3.876889355534599e-05, 'epoch': 9.91}

 83%|████████▎ | 23187/28080 [45:48:47<9:35:39,  7.06s/it]
 83%|████████▎ | 23188/28080 [45:48:54<9:37:55,  7.09s/it]
                                                          
{'loss': 0.6016, 'learning_rate': 3.875347115285829e-05, 'epoch': 9.91}

 83%|████████▎ | 23188/28080 [45:48:54<9:37:55,  7.09s/it]
 83%|████████▎ | 23189/28080 [45:49:01<9:39:25,  7.11s/it]
                                                          
{'loss': 0.5929, 'learning_rate': 3.87380515607878e-05, 'epoch': 9.91}

 83%|████████▎ | 23189/28080 [45:49:01<9:39:25,  7.11s/it]
 83%|████████▎ | 23190/28080 [45:49:08<9:36:11,  7.07s/it]
                                                          
{'loss': 0.6103, 'learning_rate': 3.87226347793396e-05, 'epoch': 9.91}

 83%|████████▎ | 23190/28080 [45:49:08<9:36:11,  7.07s/it]
 83%|████████▎ | 23191/28080 [45:49:15<9:36:21,  7.07s/it]
                                                          
{'loss': 0.5935, 'learning_rate': 3.870722080871875e-05, 'epoch': 9.91}

 83%|████████▎ | 23191/28080 [45:49:15<9:36:21,  7.07s/it]
 83%|████████▎ | 23192/28080 [45:49:22<9:35:34,  7.07s/it]
                                                          
{'loss': 0.6092, 'learning_rate': 3.86918096491303e-05, 'epoch': 9.91}

 83%|████████▎ | 23192/28080 [45:49:22<9:35:34,  7.07s/it]
 83%|████████▎ | 23193/28080 [45:49:29<9:37:15,  7.09s/it]
                                                          
{'loss': 0.6022, 'learning_rate': 3.867640130077937e-05, 'epoch': 9.91}

 83%|████████▎ | 23193/28080 [45:49:29<9:37:15,  7.09s/it]
 83%|████████▎ | 23194/28080 [45:49:36<9:35:22,  7.07s/it]
                                                          
{'loss': 0.6362, 'learning_rate': 3.866099576387094e-05, 'epoch': 9.91}

 83%|████████▎ | 23194/28080 [45:49:36<9:35:22,  7.07s/it]
 83%|████████▎ | 23195/28080 [45:49:43<9:39:08,  7.11s/it]
                                                          
{'loss': 0.6028, 'learning_rate': 3.8645593038609926e-05, 'epoch': 9.91}

 83%|████████▎ | 23195/28080 [45:49:43<9:39:08,  7.11s/it]
 83%|████████▎ | 23196/28080 [45:49:51<9:41:03,  7.14s/it]
                                                          
{'loss': 0.589, 'learning_rate': 3.863019312520119e-05, 'epoch': 9.91}

 83%|████████▎ | 23196/28080 [45:49:51<9:41:03,  7.14s/it]
 83%|████████▎ | 23197/28080 [45:49:58<9:44:12,  7.18s/it]
                                                          
{'loss': 0.6088, 'learning_rate': 3.8614796023849735e-05, 'epoch': 9.91}

 83%|████████▎ | 23197/28080 [45:49:58<9:44:12,  7.18s/it]
 83%|████████▎ | 23198/28080 [45:50:05<9:40:26,  7.13s/it]
                                                          
{'loss': 0.5904, 'learning_rate': 3.859940173476034e-05, 'epoch': 9.91}

 83%|████████▎ | 23198/28080 [45:50:05<9:40:26,  7.13s/it]
 83%|████████▎ | 23199/28080 [45:50:12<9:37:20,  7.10s/it]
                                                          
{'loss': 0.6084, 'learning_rate': 3.858401025813782e-05, 'epoch': 9.91}

 83%|████████▎ | 23199/28080 [45:50:12<9:37:20,  7.10s/it]
 83%|████████▎ | 23200/28080 [45:50:19<9:39:18,  7.12s/it]
                                                          
{'loss': 0.5847, 'learning_rate': 3.856862159418689e-05, 'epoch': 9.91}

 83%|████████▎ | 23200/28080 [45:50:19<9:39:18,  7.12s/it]
 83%|████████▎ | 23201/28080 [45:50:26<9:39:25,  7.13s/it]
                                                          
{'loss': 0.5897, 'learning_rate': 3.855323574311237e-05, 'epoch': 9.91}

 83%|████████▎ | 23201/28080 [45:50:26<9:39:25,  7.13s/it]
 83%|████████▎ | 23202/28080 [45:50:33<9:39:23,  7.13s/it]
                                                          
{'loss': 0.575, 'learning_rate': 3.853785270511886e-05, 'epoch': 9.91}

 83%|████████▎ | 23202/28080 [45:50:33<9:39:23,  7.13s/it]
 83%|████████▎ | 23203/28080 [45:50:40<9:38:56,  7.12s/it]
                                                          
{'loss': 0.6056, 'learning_rate': 3.852247248041113e-05, 'epoch': 9.91}

 83%|████████▎ | 23203/28080 [45:50:40<9:38:56,  7.12s/it]
 83%|████████▎ | 23204/28080 [45:50:48<9:36:51,  7.10s/it]
                                                          
{'loss': 0.5966, 'learning_rate': 3.8507095069193724e-05, 'epoch': 9.91}

 83%|████████▎ | 23204/28080 [45:50:48<9:36:51,  7.10s/it]
 83%|████████▎ | 23205/28080 [45:50:55<9:35:13,  7.08s/it]
                                                          
{'loss': 0.6216, 'learning_rate': 3.8491720471671236e-05, 'epoch': 9.91}

 83%|████████▎ | 23205/28080 [45:50:55<9:35:13,  7.08s/it]
 83%|████████▎ | 23206/28080 [45:51:02<9:36:49,  7.10s/it]
                                                          
{'loss': 0.6091, 'learning_rate': 3.847634868804817e-05, 'epoch': 9.91}

 83%|████████▎ | 23206/28080 [45:51:02<9:36:49,  7.10s/it]
 83%|████████▎ | 23207/28080 [45:51:09<9:38:34,  7.12s/it]
                                                          
{'loss': 0.6276, 'learning_rate': 3.8460979718529104e-05, 'epoch': 9.91}

 83%|████████▎ | 23207/28080 [45:51:09<9:38:34,  7.12s/it]
 83%|████████▎ | 23208/28080 [45:51:16<9:38:32,  7.12s/it]
                                                          
{'loss': 0.6204, 'learning_rate': 3.844561356331847e-05, 'epoch': 9.91}

 83%|████████▎ | 23208/28080 [45:51:16<9:38:32,  7.12s/it]
 83%|████████▎ | 23209/28080 [45:51:23<9:38:10,  7.12s/it]
                                                          
{'loss': 0.6193, 'learning_rate': 3.84302502226207e-05, 'epoch': 9.91}

 83%|████████▎ | 23209/28080 [45:51:23<9:38:10,  7.12s/it]
 83%|████████▎ | 23210/28080 [45:51:30<9:37:39,  7.12s/it]
                                                          
{'loss': 0.6142, 'learning_rate': 3.841488969664014e-05, 'epoch': 9.92}

 83%|████████▎ | 23210/28080 [45:51:30<9:37:39,  7.12s/it]
 83%|████████▎ | 23211/28080 [45:51:37<9:38:59,  7.13s/it]
                                                          
{'loss': 0.6023, 'learning_rate': 3.839953198558124e-05, 'epoch': 9.92}

 83%|████████▎ | 23211/28080 [45:51:37<9:38:59,  7.13s/it]
 83%|████████▎ | 23212/28080 [45:51:44<9:37:18,  7.12s/it]
                                                          
{'loss': 0.6248, 'learning_rate': 3.8384177089648254e-05, 'epoch': 9.92}

 83%|████████▎ | 23212/28080 [45:51:44<9:37:18,  7.12s/it]
 83%|████████▎ | 23213/28080 [45:51:52<9:37:13,  7.12s/it]
                                                          
{'loss': 0.6157, 'learning_rate': 3.836882500904551e-05, 'epoch': 9.92}

 83%|████████▎ | 23213/28080 [45:51:52<9:37:13,  7.12s/it]
 83%|████████▎ | 23214/28080 [45:51:59<9:36:24,  7.11s/it]
                                                          
{'loss': 0.606, 'learning_rate': 3.835347574397721e-05, 'epoch': 9.92}

 83%|████████▎ | 23214/28080 [45:51:59<9:36:24,  7.11s/it]
 83%|████████▎ | 23215/28080 [45:52:06<9:39:17,  7.14s/it]
                                                          
{'loss': 0.6169, 'learning_rate': 3.83381292946475e-05, 'epoch': 9.92}

 83%|████████▎ | 23215/28080 [45:52:06<9:39:17,  7.14s/it]
 83%|████████▎ | 23216/28080 [45:52:13<9:38:45,  7.14s/it]
                                                          
{'loss': 0.5874, 'learning_rate': 3.832278566126071e-05, 'epoch': 9.92}

 83%|████████▎ | 23216/28080 [45:52:13<9:38:45,  7.14s/it]
 83%|████████▎ | 23217/28080 [45:52:20<9:39:33,  7.15s/it]
                                                          
{'loss': 0.6077, 'learning_rate': 3.8307444844020795e-05, 'epoch': 9.92}

 83%|████████▎ | 23217/28080 [45:52:20<9:39:33,  7.15s/it]
 83%|████████▎ | 23218/28080 [45:52:27<9:38:08,  7.13s/it]
                                                          
{'loss': 0.6172, 'learning_rate': 3.829210684313206e-05, 'epoch': 9.92}

 83%|████████▎ | 23218/28080 [45:52:27<9:38:08,  7.13s/it]
 83%|████████▎ | 23219/28080 [45:52:34<9:34:53,  7.10s/it]
                                                          
{'loss': 0.6138, 'learning_rate': 3.827677165879831e-05, 'epoch': 9.92}

 83%|████████▎ | 23219/28080 [45:52:34<9:34:53,  7.10s/it]
 83%|████████▎ | 23220/28080 [45:52:41<9:33:59,  7.09s/it]
                                                          
{'loss': 0.6096, 'learning_rate': 3.826143929122378e-05, 'epoch': 9.92}

 83%|████████▎ | 23220/28080 [45:52:41<9:33:59,  7.09s/it]
 83%|████████▎ | 23221/28080 [45:52:49<9:36:04,  7.11s/it]
                                                          
{'loss': 0.5887, 'learning_rate': 3.824610974061227e-05, 'epoch': 9.92}

 83%|████████▎ | 23221/28080 [45:52:49<9:36:04,  7.11s/it]
 83%|████████▎ | 23222/28080 [45:52:56<9:36:01,  7.11s/it]
                                                          
{'loss': 0.5921, 'learning_rate': 3.82307830071679e-05, 'epoch': 9.92}

 83%|████████▎ | 23222/28080 [45:52:56<9:36:01,  7.11s/it]
 83%|████████▎ | 23223/28080 [45:53:03<9:37:47,  7.14s/it]
                                                          
{'loss': 0.6101, 'learning_rate': 3.821545909109447e-05, 'epoch': 9.92}

 83%|████████▎ | 23223/28080 [45:53:03<9:37:47,  7.14s/it]
 83%|████████▎ | 23224/28080 [45:53:10<9:37:20,  7.13s/it]
                                                          
{'loss': 0.601, 'learning_rate': 3.820013799259589e-05, 'epoch': 9.92}

 83%|████████▎ | 23224/28080 [45:53:10<9:37:20,  7.13s/it]
 83%|████████▎ | 23225/28080 [45:53:17<9:36:07,  7.12s/it]
                                                          
{'loss': 0.6255, 'learning_rate': 3.8184819711875904e-05, 'epoch': 9.92}

 83%|████████▎ | 23225/28080 [45:53:17<9:36:07,  7.12s/it]
 83%|████████▎ | 23226/28080 [45:53:24<9:35:20,  7.11s/it]
                                                          
{'loss': 0.6106, 'learning_rate': 3.816950424913842e-05, 'epoch': 9.92}

 83%|████████▎ | 23226/28080 [45:53:24<9:35:20,  7.11s/it]
 83%|████████▎ | 23227/28080 [45:53:31<9:33:38,  7.09s/it]
                                                          
{'loss': 0.596, 'learning_rate': 3.8154191604587164e-05, 'epoch': 9.92}

 83%|████████▎ | 23227/28080 [45:53:31<9:33:38,  7.09s/it]
 83%|████████▎ | 23228/28080 [45:53:38<9:31:47,  7.07s/it]
                                                          
{'loss': 0.5972, 'learning_rate': 3.8138881778425836e-05, 'epoch': 9.92}

 83%|████████▎ | 23228/28080 [45:53:38<9:31:47,  7.07s/it]
 83%|████████▎ | 23229/28080 [45:53:45<9:30:31,  7.06s/it]
                                                          
{'loss': 0.5755, 'learning_rate': 3.8123574770858066e-05, 'epoch': 9.92}

 83%|████████▎ | 23229/28080 [45:53:45<9:30:31,  7.06s/it]
 83%|████████▎ | 23230/28080 [45:53:52<9:33:07,  7.09s/it]
                                                          
{'loss': 0.5951, 'learning_rate': 3.81082705820876e-05, 'epoch': 9.92}

 83%|████████▎ | 23230/28080 [45:53:52<9:33:07,  7.09s/it]
 83%|████████▎ | 23231/28080 [45:53:59<9:31:31,  7.07s/it]
                                                          
{'loss': 0.6014, 'learning_rate': 3.809296921231795e-05, 'epoch': 9.92}

 83%|████████▎ | 23231/28080 [45:53:59<9:31:31,  7.07s/it]
 83%|████████▎ | 23232/28080 [45:54:07<9:33:19,  7.10s/it]
                                                          
{'loss': 0.578, 'learning_rate': 3.807767066175285e-05, 'epoch': 9.92}

 83%|████████▎ | 23232/28080 [45:54:07<9:33:19,  7.10s/it]
 83%|████████▎ | 23233/28080 [45:54:14<9:34:54,  7.12s/it]
                                                          
{'loss': 0.605, 'learning_rate': 3.8062374930595586e-05, 'epoch': 9.92}

 83%|████████▎ | 23233/28080 [45:54:14<9:34:54,  7.12s/it]
 83%|████████▎ | 23234/28080 [45:54:21<9:35:56,  7.13s/it]
                                                          
{'loss': 0.6039, 'learning_rate': 3.8047082019049853e-05, 'epoch': 9.93}

 83%|████████▎ | 23234/28080 [45:54:21<9:35:56,  7.13s/it]
 83%|████████▎ | 23235/28080 [45:54:28<9:34:43,  7.12s/it]
                                                          
{'loss': 0.6063, 'learning_rate': 3.803179192731895e-05, 'epoch': 9.93}

 83%|████████▎ | 23235/28080 [45:54:28<9:34:43,  7.12s/it]
 83%|████████▎ | 23236/28080 [45:54:35<9:36:41,  7.14s/it]
                                                          
{'loss': 0.6, 'learning_rate': 3.8016504655606464e-05, 'epoch': 9.93}

 83%|████████▎ | 23236/28080 [45:54:35<9:36:41,  7.14s/it]
 83%|████████▎ | 23237/28080 [45:54:42<9:36:22,  7.14s/it]
                                                          
{'loss': 0.6226, 'learning_rate': 3.8001220204115756e-05, 'epoch': 9.93}

 83%|████████▎ | 23237/28080 [45:54:42<9:36:22,  7.14s/it]
 83%|████████▎ | 23238/28080 [45:54:49<9:33:56,  7.11s/it]
                                                          
{'loss': 0.5929, 'learning_rate': 3.7985938573049965e-05, 'epoch': 9.93}

 83%|████████▎ | 23238/28080 [45:54:49<9:33:56,  7.11s/it]
 83%|████████▎ | 23239/28080 [45:54:57<9:33:07,  7.10s/it]
                                                          
{'loss': 0.6001, 'learning_rate': 3.79706597626126e-05, 'epoch': 9.93}

 83%|████████▎ | 23239/28080 [45:54:57<9:33:07,  7.10s/it]
 83%|████████▎ | 23240/28080 [45:55:04<9:32:07,  7.09s/it]
                                                          
{'loss': 0.6138, 'learning_rate': 3.7955383773006834e-05, 'epoch': 9.93}

 83%|████████▎ | 23240/28080 [45:55:04<9:32:07,  7.09s/it]
 83%|████████▎ | 23241/28080 [45:55:11<9:33:13,  7.11s/it]
                                                          
{'loss': 0.6251, 'learning_rate': 3.7940110604435976e-05, 'epoch': 9.93}

 83%|████████▎ | 23241/28080 [45:55:11<9:33:13,  7.11s/it]
 83%|████████▎ | 23242/28080 [45:55:18<9:31:56,  7.09s/it]
                                                          
{'loss': 0.5982, 'learning_rate': 3.792484025710316e-05, 'epoch': 9.93}

 83%|████████▎ | 23242/28080 [45:55:18<9:31:56,  7.09s/it]
 83%|████████▎ | 23243/28080 [45:55:25<9:32:59,  7.11s/it]
                                                          
{'loss': 0.6199, 'learning_rate': 3.79095727312116e-05, 'epoch': 9.93}

 83%|████████▎ | 23243/28080 [45:55:25<9:32:59,  7.11s/it]
 83%|████████▎ | 23244/28080 [45:55:32<9:32:50,  7.11s/it]
                                                          
{'loss': 0.6087, 'learning_rate': 3.789430802696428e-05, 'epoch': 9.93}

 83%|████████▎ | 23244/28080 [45:55:32<9:32:50,  7.11s/it]
 83%|████████▎ | 23245/28080 [45:55:39<9:33:51,  7.12s/it]
                                                          
{'loss': 0.5995, 'learning_rate': 3.787904614456444e-05, 'epoch': 9.93}

 83%|████████▎ | 23245/28080 [45:55:39<9:33:51,  7.12s/it]
 83%|████████▎ | 23246/28080 [45:55:46<9:31:42,  7.10s/it]
                                                          
{'loss': 0.5838, 'learning_rate': 3.7863787084215064e-05, 'epoch': 9.93}

 83%|████████▎ | 23246/28080 [45:55:46<9:31:42,  7.10s/it]
 83%|████████▎ | 23247/28080 [45:55:53<9:31:30,  7.10s/it]
                                                          
{'loss': 0.5939, 'learning_rate': 3.784853084611914e-05, 'epoch': 9.93}

 83%|████████▎ | 23247/28080 [45:55:53<9:31:30,  7.10s/it]
 83%|████████▎ | 23248/28080 [45:56:00<9:30:31,  7.08s/it]
                                                          
{'loss': 0.5892, 'learning_rate': 3.78332774304796e-05, 'epoch': 9.93}

 83%|████████▎ | 23248/28080 [45:56:00<9:30:31,  7.08s/it]
 83%|████████▎ | 23249/28080 [45:56:08<9:31:46,  7.10s/it]
                                                          
{'loss': 0.6143, 'learning_rate': 3.781802683749946e-05, 'epoch': 9.93}

 83%|████████▎ | 23249/28080 [45:56:08<9:31:46,  7.10s/it]
 83%|████████▎ | 23250/28080 [45:56:15<9:29:47,  7.08s/it]
                                                          
{'loss': 0.6169, 'learning_rate': 3.780277906738155e-05, 'epoch': 9.93}

 83%|████████▎ | 23250/28080 [45:56:15<9:29:47,  7.08s/it]
 83%|████████▎ | 23251/28080 [45:56:22<9:31:21,  7.10s/it]
                                                          
{'loss': 0.5995, 'learning_rate': 3.778753412032881e-05, 'epoch': 9.93}

 83%|████████▎ | 23251/28080 [45:56:22<9:31:21,  7.10s/it]
 83%|████████▎ | 23252/28080 [45:56:29<9:30:34,  7.09s/it]
                                                          
{'loss': 0.591, 'learning_rate': 3.777229199654397e-05, 'epoch': 9.93}

 83%|████████▎ | 23252/28080 [45:56:29<9:30:34,  7.09s/it]
 83%|████████▎ | 23253/28080 [45:56:36<9:31:25,  7.10s/it]
                                                          
{'loss': 0.6068, 'learning_rate': 3.7757052696229864e-05, 'epoch': 9.93}

 83%|████████▎ | 23253/28080 [45:56:36<9:31:25,  7.10s/it]
 83%|████████▎ | 23254/28080 [45:56:43<9:33:07,  7.13s/it]
                                                          
{'loss': 0.6043, 'learning_rate': 3.774181621958917e-05, 'epoch': 9.93}

 83%|████████▎ | 23254/28080 [45:56:43<9:33:07,  7.13s/it]
 83%|████████▎ | 23255/28080 [45:56:50<9:34:32,  7.14s/it]
                                                          
{'loss': 0.5973, 'learning_rate': 3.772658256682468e-05, 'epoch': 9.93}

 83%|████████▎ | 23255/28080 [45:56:50<9:34:32,  7.14s/it]
 83%|████████▎ | 23256/28080 [45:56:57<9:34:32,  7.15s/it]
                                                          
{'loss': 0.6012, 'learning_rate': 3.771135173813903e-05, 'epoch': 9.93}

 83%|████████▎ | 23256/28080 [45:56:57<9:34:32,  7.15s/it]
 83%|████████▎ | 23257/28080 [45:57:05<9:33:40,  7.14s/it]
                                                          
{'loss': 0.6059, 'learning_rate': 3.769612373373482e-05, 'epoch': 9.94}

 83%|████████▎ | 23257/28080 [45:57:05<9:33:40,  7.14s/it]
 83%|████████▎ | 23258/28080 [45:57:12<9:33:04,  7.13s/it]
                                                          
{'loss': 0.6012, 'learning_rate': 3.76808985538146e-05, 'epoch': 9.94}

 83%|████████▎ | 23258/28080 [45:57:12<9:33:04,  7.13s/it]
 83%|████████▎ | 23259/28080 [45:57:19<9:34:11,  7.15s/it]
                                                          
{'loss': 0.6117, 'learning_rate': 3.766567619858105e-05, 'epoch': 9.94}

 83%|████████▎ | 23259/28080 [45:57:19<9:34:11,  7.15s/it]
 83%|████████▎ | 23260/28080 [45:57:26<9:31:16,  7.11s/it]
                                                          
{'loss': 0.5949, 'learning_rate': 3.765045666823663e-05, 'epoch': 9.94}

 83%|████████▎ | 23260/28080 [45:57:26<9:31:16,  7.11s/it]
 83%|████████▎ | 23261/28080 [45:57:33<9:30:24,  7.10s/it]
                                                          
{'loss': 0.5952, 'learning_rate': 3.763523996298382e-05, 'epoch': 9.94}

 83%|████████▎ | 23261/28080 [45:57:33<9:30:24,  7.10s/it]
 83%|████████▎ | 23262/28080 [45:57:40<9:31:06,  7.11s/it]
                                                          
{'loss': 0.6231, 'learning_rate': 3.762002608302506e-05, 'epoch': 9.94}

 83%|████████▎ | 23262/28080 [45:57:40<9:31:06,  7.11s/it]
 83%|████████▎ | 23263/28080 [45:57:47<9:28:57,  7.09s/it]
                                                          
{'loss': 0.6162, 'learning_rate': 3.7604815028562694e-05, 'epoch': 9.94}

 83%|████████▎ | 23263/28080 [45:57:47<9:28:57,  7.09s/it]
 83%|████████▎ | 23264/28080 [45:57:54<9:29:08,  7.09s/it]
                                                          
{'loss': 0.5969, 'learning_rate': 3.75896067997992e-05, 'epoch': 9.94}

 83%|████████▎ | 23264/28080 [45:57:54<9:29:08,  7.09s/it]
 83%|████████▎ | 23265/28080 [45:58:01<9:28:59,  7.09s/it]
                                                          
{'loss': 0.5811, 'learning_rate': 3.7574401396936797e-05, 'epoch': 9.94}

 83%|████████▎ | 23265/28080 [45:58:01<9:28:59,  7.09s/it]
 83%|████████▎ | 23266/28080 [45:58:08<9:28:10,  7.08s/it]
                                                          
{'loss': 0.6069, 'learning_rate': 3.755919882017794e-05, 'epoch': 9.94}

 83%|████████▎ | 23266/28080 [45:58:08<9:28:10,  7.08s/it]
 83%|████████▎ | 23267/28080 [45:58:16<9:31:25,  7.12s/it]
                                                          
{'loss': 0.5786, 'learning_rate': 3.754399906972469e-05, 'epoch': 9.94}

 83%|████████▎ | 23267/28080 [45:58:16<9:31:25,  7.12s/it]
 83%|████████▎ | 23268/28080 [45:58:23<9:31:06,  7.12s/it]
                                                          
{'loss': 0.5967, 'learning_rate': 3.752880214577939e-05, 'epoch': 9.94}

 83%|████████▎ | 23268/28080 [45:58:23<9:31:06,  7.12s/it]
 83%|████████▎ | 23269/28080 [45:58:30<9:34:05,  7.16s/it]
                                                          
{'loss': 0.6003, 'learning_rate': 3.7513608048544144e-05, 'epoch': 9.94}

 83%|████████▎ | 23269/28080 [45:58:30<9:34:05,  7.16s/it]
 83%|████████▎ | 23270/28080 [45:58:37<9:32:34,  7.14s/it]
                                                          
{'loss': 0.6101, 'learning_rate': 3.749841677822116e-05, 'epoch': 9.94}

 83%|████████▎ | 23270/28080 [45:58:37<9:32:34,  7.14s/it]
 83%|████████▎ | 23271/28080 [45:58:44<9:31:34,  7.13s/it]
                                                          
{'loss': 0.5815, 'learning_rate': 3.748322833501255e-05, 'epoch': 9.94}

 83%|████████▎ | 23271/28080 [45:58:44<9:31:34,  7.13s/it]
 83%|████████▎ | 23272/28080 [45:58:51<9:32:03,  7.14s/it]
                                                          
{'loss': 0.5921, 'learning_rate': 3.746804271912033e-05, 'epoch': 9.94}

 83%|████████▎ | 23272/28080 [45:58:51<9:32:03,  7.14s/it]
 83%|████████▎ | 23273/28080 [45:58:58<9:32:35,  7.15s/it]
                                                          
{'loss': 0.6003, 'learning_rate': 3.7452859930746484e-05, 'epoch': 9.94}

 83%|████████▎ | 23273/28080 [45:58:58<9:32:35,  7.15s/it]
 83%|████████▎ | 23274/28080 [45:59:06<9:30:03,  7.12s/it]
                                                          
{'loss': 0.5867, 'learning_rate': 3.743767997009312e-05, 'epoch': 9.94}

 83%|████████▎ | 23274/28080 [45:59:06<9:30:03,  7.12s/it]
 83%|████████▎ | 23275/28080 [45:59:13<9:28:40,  7.10s/it]
                                                          
{'loss': 0.6006, 'learning_rate': 3.742250283736215e-05, 'epoch': 9.94}

 83%|████████▎ | 23275/28080 [45:59:13<9:28:40,  7.10s/it]
 83%|████████▎ | 23276/28080 [45:59:20<9:30:24,  7.12s/it]
                                                          
{'loss': 0.5997, 'learning_rate': 3.740732853275547e-05, 'epoch': 9.94}

 83%|████████▎ | 23276/28080 [45:59:20<9:30:24,  7.12s/it]
 83%|████████▎ | 23277/28080 [45:59:27<9:29:09,  7.11s/it]
                                                          
{'loss': 0.6108, 'learning_rate': 3.739215705647489e-05, 'epoch': 9.94}

 83%|████████▎ | 23277/28080 [45:59:27<9:29:09,  7.11s/it]
 83%|████████▎ | 23278/28080 [45:59:34<9:27:27,  7.09s/it]
                                                          
{'loss': 0.6234, 'learning_rate': 3.737698840872242e-05, 'epoch': 9.94}

 83%|████████▎ | 23278/28080 [45:59:34<9:27:27,  7.09s/it]
 83%|████████▎ | 23279/28080 [45:59:41<9:27:54,  7.10s/it]
                                                          
{'loss': 0.5895, 'learning_rate': 3.736182258969967e-05, 'epoch': 9.94}

 83%|████████▎ | 23279/28080 [45:59:41<9:27:54,  7.10s/it]
 83%|████████▎ | 23280/28080 [45:59:48<9:27:56,  7.10s/it]
                                                          
{'loss': 0.5998, 'learning_rate': 3.734665959960865e-05, 'epoch': 9.94}

 83%|████████▎ | 23280/28080 [45:59:48<9:27:56,  7.10s/it]
 83%|████████▎ | 23281/28080 [45:59:55<9:27:55,  7.10s/it]
                                                          
{'loss': 0.6108, 'learning_rate': 3.73314994386508e-05, 'epoch': 9.95}

 83%|████████▎ | 23281/28080 [45:59:55<9:27:55,  7.10s/it]
 83%|████████▎ | 23282/28080 [46:00:02<9:29:09,  7.12s/it]
                                                          
{'loss': 0.5891, 'learning_rate': 3.731634210702803e-05, 'epoch': 9.95}

 83%|████████▎ | 23282/28080 [46:00:02<9:29:09,  7.12s/it]
 83%|████████▎ | 23283/28080 [46:00:09<9:29:46,  7.13s/it]
                                                          
{'loss': 0.6037, 'learning_rate': 3.7301187604941836e-05, 'epoch': 9.95}

 83%|████████▎ | 23283/28080 [46:00:09<9:29:46,  7.13s/it]
 83%|████████▎ | 23284/28080 [46:00:17<9:29:53,  7.13s/it]
                                                          
{'loss': 0.6027, 'learning_rate': 3.7286035932594e-05, 'epoch': 9.95}

 83%|████████▎ | 23284/28080 [46:00:17<9:29:53,  7.13s/it]
 83%|████████▎ | 23285/28080 [46:00:24<9:27:15,  7.10s/it]
                                                          
{'loss': 0.6096, 'learning_rate': 3.727088709018597e-05, 'epoch': 9.95}

 83%|████████▎ | 23285/28080 [46:00:24<9:27:15,  7.10s/it]
 83%|████████▎ | 23286/28080 [46:00:31<9:27:51,  7.11s/it]
                                                          
{'loss': 0.6022, 'learning_rate': 3.7255741077919376e-05, 'epoch': 9.95}

 83%|████████▎ | 23286/28080 [46:00:31<9:27:51,  7.11s/it]
 83%|████████▎ | 23287/28080 [46:00:38<9:28:30,  7.12s/it]
                                                          
{'loss': 0.5994, 'learning_rate': 3.724059789599563e-05, 'epoch': 9.95}

 83%|████████▎ | 23287/28080 [46:00:38<9:28:30,  7.12s/it]
 83%|████████▎ | 23288/28080 [46:00:45<9:26:38,  7.09s/it]
                                                          
{'loss': 0.6032, 'learning_rate': 3.7225457544616205e-05, 'epoch': 9.95}

 83%|████████▎ | 23288/28080 [46:00:45<9:26:38,  7.09s/it]
 83%|████████▎ | 23289/28080 [46:00:52<9:25:06,  7.08s/it]
                                                          
{'loss': 0.5967, 'learning_rate': 3.721032002398261e-05, 'epoch': 9.95}

 83%|████████▎ | 23289/28080 [46:00:52<9:25:06,  7.08s/it]
 83%|████████▎ | 23290/28080 [46:00:59<9:23:36,  7.06s/it]
                                                          
{'loss': 0.5915, 'learning_rate': 3.719518533429617e-05, 'epoch': 9.95}

 83%|████████▎ | 23290/28080 [46:00:59<9:23:36,  7.06s/it]
 83%|████████▎ | 23291/28080 [46:01:06<9:22:01,  7.04s/it]
                                                          
{'loss': 0.5849, 'learning_rate': 3.718005347575826e-05, 'epoch': 9.95}

 83%|████████▎ | 23291/28080 [46:01:06<9:22:01,  7.04s/it]
 83%|████████▎ | 23292/28080 [46:01:13<9:24:38,  7.08s/it]
                                                          
{'loss': 0.5793, 'learning_rate': 3.716492444857014e-05, 'epoch': 9.95}

 83%|████████▎ | 23292/28080 [46:01:13<9:24:38,  7.08s/it]
 83%|████████▎ | 23293/28080 [46:01:20<9:24:51,  7.08s/it]
                                                          
{'loss': 0.5921, 'learning_rate': 3.714979825293319e-05, 'epoch': 9.95}

 83%|████████▎ | 23293/28080 [46:01:20<9:24:51,  7.08s/it]
 83%|████████▎ | 23294/28080 [46:01:27<9:25:50,  7.09s/it]
                                                          
{'loss': 0.6028, 'learning_rate': 3.7134674889048564e-05, 'epoch': 9.95}

 83%|████████▎ | 23294/28080 [46:01:27<9:25:50,  7.09s/it]
 83%|████████▎ | 23295/28080 [46:01:34<9:25:18,  7.09s/it]
                                                          
{'loss': 0.5974, 'learning_rate': 3.7119554357117504e-05, 'epoch': 9.95}

 83%|████████▎ | 23295/28080 [46:01:34<9:25:18,  7.09s/it]
 83%|████████▎ | 23296/28080 [46:01:42<9:26:25,  7.10s/it]
                                                          
{'loss': 0.5914, 'learning_rate': 3.710443665734109e-05, 'epoch': 9.95}

 83%|████████▎ | 23296/28080 [46:01:42<9:26:25,  7.10s/it]
 83%|████████▎ | 23297/28080 [46:01:49<9:23:26,  7.07s/it]
                                                          
{'loss': 0.6032, 'learning_rate': 3.708932178992058e-05, 'epoch': 9.95}

 83%|████████▎ | 23297/28080 [46:01:49<9:23:26,  7.07s/it]
 83%|████████▎ | 23298/28080 [46:01:56<9:24:58,  7.09s/it]
                                                          
{'loss': 0.5935, 'learning_rate': 3.707420975505693e-05, 'epoch': 9.95}

 83%|████████▎ | 23298/28080 [46:01:56<9:24:58,  7.09s/it]
 83%|████████▎ | 23299/28080 [46:02:03<9:24:50,  7.09s/it]
                                                          
{'loss': 0.6016, 'learning_rate': 3.705910055295136e-05, 'epoch': 9.95}

 83%|████████▎ | 23299/28080 [46:02:03<9:24:50,  7.09s/it]
 83%|████████▎ | 23300/28080 [46:02:10<9:24:05,  7.08s/it]
                                                          
{'loss': 0.5954, 'learning_rate': 3.704399418380469e-05, 'epoch': 9.95}

 83%|████████▎ | 23300/28080 [46:02:10<9:24:05,  7.08s/it]
 83%|████████▎ | 23301/28080 [46:02:17<9:24:59,  7.09s/it]
                                                          
{'loss': 0.6011, 'learning_rate': 3.702889064781803e-05, 'epoch': 9.95}

 83%|████████▎ | 23301/28080 [46:02:17<9:24:59,  7.09s/it]
 83%|████████▎ | 23302/28080 [46:02:24<9:26:35,  7.12s/it]
                                                          
{'loss': 0.5949, 'learning_rate': 3.7013789945192225e-05, 'epoch': 9.95}

 83%|████████▎ | 23302/28080 [46:02:24<9:26:35,  7.12s/it]
 83%|████████▎ | 23303/28080 [46:02:31<9:25:51,  7.11s/it]
                                                          
{'loss': 0.5881, 'learning_rate': 3.6998692076128245e-05, 'epoch': 9.95}

 83%|████████▎ | 23303/28080 [46:02:31<9:25:51,  7.11s/it]
 83%|████████▎ | 23304/28080 [46:02:38<9:26:30,  7.12s/it]
                                                          
{'loss': 0.6089, 'learning_rate': 3.698359704082696e-05, 'epoch': 9.96}

 83%|████████▎ | 23304/28080 [46:02:38<9:26:30,  7.12s/it]
 83%|████████▎ | 23305/28080 [46:02:45<9:25:31,  7.11s/it]
                                                          
{'loss': 0.5971, 'learning_rate': 3.696850483948913e-05, 'epoch': 9.96}

 83%|████████▎ | 23305/28080 [46:02:45<9:25:31,  7.11s/it]
 83%|████████▎ | 23306/28080 [46:02:53<9:24:46,  7.10s/it]
                                                          
{'loss': 0.5753, 'learning_rate': 3.695341547231554e-05, 'epoch': 9.96}

 83%|████████▎ | 23306/28080 [46:02:53<9:24:46,  7.10s/it]
 83%|████████▎ | 23307/28080 [46:03:00<9:24:37,  7.10s/it]
                                                          
{'loss': 0.5882, 'learning_rate': 3.693832893950702e-05, 'epoch': 9.96}

 83%|████████▎ | 23307/28080 [46:03:00<9:24:37,  7.10s/it]
 83%|████████▎ | 23308/28080 [46:03:07<9:23:49,  7.09s/it]
                                                          
{'loss': 0.615, 'learning_rate': 3.6923245241264225e-05, 'epoch': 9.96}

 83%|████████▎ | 23308/28080 [46:03:07<9:23:49,  7.09s/it]
 83%|████████▎ | 23309/28080 [46:03:14<9:24:55,  7.10s/it]
                                                          
{'loss': 0.6014, 'learning_rate': 3.690816437778782e-05, 'epoch': 9.96}

 83%|████████▎ | 23309/28080 [46:03:14<9:24:55,  7.10s/it]
 83%|████████▎ | 23310/28080 [46:03:21<9:23:11,  7.08s/it]
                                                          
{'loss': 0.6148, 'learning_rate': 3.68930863492784e-05, 'epoch': 9.96}

 83%|████████▎ | 23310/28080 [46:03:21<9:23:11,  7.08s/it]
 83%|████████▎ | 23311/28080 [46:03:28<9:23:03,  7.08s/it]
                                                          
{'loss': 0.5992, 'learning_rate': 3.68780111559367e-05, 'epoch': 9.96}

 83%|████████▎ | 23311/28080 [46:03:28<9:23:03,  7.08s/it]
 83%|████████▎ | 23312/28080 [46:03:35<9:22:26,  7.08s/it]
                                                          
{'loss': 0.5821, 'learning_rate': 3.686293879796318e-05, 'epoch': 9.96}

 83%|████████▎ | 23312/28080 [46:03:35<9:22:26,  7.08s/it]
 83%|████████▎ | 23313/28080 [46:03:42<9:19:45,  7.05s/it]
                                                          
{'loss': 0.6143, 'learning_rate': 3.68478692755583e-05, 'epoch': 9.96}

 83%|████████▎ | 23313/28080 [46:03:42<9:19:45,  7.05s/it]
 83%|████████▎ | 23314/28080 [46:03:49<9:21:46,  7.07s/it]
                                                          
{'loss': 0.608, 'learning_rate': 3.683280258892277e-05, 'epoch': 9.96}

 83%|████████▎ | 23314/28080 [46:03:49<9:21:46,  7.07s/it]
 83%|████████▎ | 23315/28080 [46:03:56<9:23:43,  7.10s/it]
                                                          
{'loss': 0.6269, 'learning_rate': 3.681773873825675e-05, 'epoch': 9.96}

 83%|████████▎ | 23315/28080 [46:03:56<9:23:43,  7.10s/it]
 83%|████████▎ | 23316/28080 [46:04:03<9:22:59,  7.09s/it]
                                                          
{'loss': 0.5972, 'learning_rate': 3.6802677723760864e-05, 'epoch': 9.96}

 83%|████████▎ | 23316/28080 [46:04:03<9:22:59,  7.09s/it]
 83%|████████▎ | 23317/28080 [46:04:11<9:26:44,  7.14s/it]
                                                          
{'loss': 0.5979, 'learning_rate': 3.678761954563534e-05, 'epoch': 9.96}

 83%|████████▎ | 23317/28080 [46:04:11<9:26:44,  7.14s/it]
 83%|████████▎ | 23318/28080 [46:04:18<9:24:51,  7.12s/it]
                                                          
{'loss': 0.6092, 'learning_rate': 3.6772564204080624e-05, 'epoch': 9.96}

 83%|████████▎ | 23318/28080 [46:04:18<9:24:51,  7.12s/it]
 83%|████████▎ | 23319/28080 [46:04:25<9:22:49,  7.09s/it]
                                                          
{'loss': 0.6002, 'learning_rate': 3.6757511699296976e-05, 'epoch': 9.96}

 83%|████████▎ | 23319/28080 [46:04:25<9:22:49,  7.09s/it]
 83%|████████▎ | 23320/28080 [46:04:32<9:24:04,  7.11s/it]
                                                          
{'loss': 0.5952, 'learning_rate': 3.6742462031484654e-05, 'epoch': 9.96}

 83%|████████▎ | 23320/28080 [46:04:32<9:24:04,  7.11s/it]
 83%|████████▎ | 23321/28080 [46:04:39<9:24:32,  7.12s/it]
                                                          
{'loss': 0.5844, 'learning_rate': 3.67274152008438e-05, 'epoch': 9.96}

 83%|████████▎ | 23321/28080 [46:04:39<9:24:32,  7.12s/it]
 83%|████████▎ | 23322/28080 [46:04:46<9:24:46,  7.12s/it]
                                                          
{'loss': 0.5877, 'learning_rate': 3.671237120757473e-05, 'epoch': 9.96}

 83%|████████▎ | 23322/28080 [46:04:46<9:24:46,  7.12s/it]
 83%|████████▎ | 23323/28080 [46:04:53<9:24:35,  7.12s/it]
                                                          
{'loss': 0.5953, 'learning_rate': 3.669733005187753e-05, 'epoch': 9.96}

 83%|████████▎ | 23323/28080 [46:04:53<9:24:35,  7.12s/it]
 83%|████████▎ | 23324/28080 [46:05:00<9:25:18,  7.13s/it]
                                                          
{'loss': 0.6155, 'learning_rate': 3.6682291733952295e-05, 'epoch': 9.96}

 83%|████████▎ | 23324/28080 [46:05:00<9:25:18,  7.13s/it]
 83%|████████▎ | 23325/28080 [46:05:07<9:22:00,  7.09s/it]
                                                          
{'loss': 0.5955, 'learning_rate': 3.666725625399905e-05, 'epoch': 9.96}

 83%|████████▎ | 23325/28080 [46:05:07<9:22:00,  7.09s/it]
 83%|████████▎ | 23326/28080 [46:05:15<9:23:14,  7.11s/it]
                                                          
{'loss': 0.5703, 'learning_rate': 3.665222361221793e-05, 'epoch': 9.96}

 83%|████████▎ | 23326/28080 [46:05:15<9:23:14,  7.11s/it]
 83%|████████▎ | 23327/28080 [46:05:22<9:25:08,  7.13s/it]
                                                          
{'loss': 0.5971, 'learning_rate': 3.663719380880881e-05, 'epoch': 9.97}

 83%|████████▎ | 23327/28080 [46:05:22<9:25:08,  7.13s/it]
 83%|████████▎ | 23328/28080 [46:05:29<9:25:04,  7.13s/it]
                                                          
{'loss': 0.601, 'learning_rate': 3.662216684397185e-05, 'epoch': 9.97}

 83%|████████▎ | 23328/28080 [46:05:29<9:25:04,  7.13s/it]
 83%|████████▎ | 23329/28080 [46:05:36<9:24:57,  7.13s/it]
                                                          
{'loss': 0.5938, 'learning_rate': 3.660714271790669e-05, 'epoch': 9.97}

 83%|████████▎ | 23329/28080 [46:05:36<9:24:57,  7.13s/it]
 83%|████████▎ | 23330/28080 [46:05:43<9:23:45,  7.12s/it]
                                                          
{'loss': 0.6056, 'learning_rate': 3.659212143081342e-05, 'epoch': 9.97}

 83%|████████▎ | 23330/28080 [46:05:43<9:23:45,  7.12s/it]
 83%|████████▎ | 23331/28080 [46:05:50<9:23:50,  7.12s/it]
                                                          
{'loss': 0.5809, 'learning_rate': 3.6577102982891744e-05, 'epoch': 9.97}

 83%|████████▎ | 23331/28080 [46:05:50<9:23:50,  7.12s/it]
 83%|████████▎ | 23332/28080 [46:05:57<9:22:21,  7.11s/it]
                                                          
{'loss': 0.5847, 'learning_rate': 3.656208737434161e-05, 'epoch': 9.97}

 83%|████████▎ | 23332/28080 [46:05:57<9:22:21,  7.11s/it]
 83%|████████▎ | 23333/28080 [46:06:04<9:23:24,  7.12s/it]
                                                          
{'loss': 0.606, 'learning_rate': 3.654707460536272e-05, 'epoch': 9.97}

 83%|████████▎ | 23333/28080 [46:06:04<9:23:24,  7.12s/it]
 83%|████████▎ | 23334/28080 [46:06:12<9:23:10,  7.12s/it]
                                                          
{'loss': 0.6033, 'learning_rate': 3.6532064676154774e-05, 'epoch': 9.97}

 83%|████████▎ | 23334/28080 [46:06:12<9:23:10,  7.12s/it]
 83%|████████▎ | 23335/28080 [46:06:19<9:24:53,  7.14s/it]
                                                          
{'loss': 0.6145, 'learning_rate': 3.651705758691742e-05, 'epoch': 9.97}

 83%|████████▎ | 23335/28080 [46:06:19<9:24:53,  7.14s/it]
 83%|████████▎ | 23336/28080 [46:06:26<9:25:34,  7.15s/it]
                                                          
{'loss': 0.6011, 'learning_rate': 3.650205333785048e-05, 'epoch': 9.97}

 83%|████████▎ | 23336/28080 [46:06:26<9:25:34,  7.15s/it]
 83%|████████▎ | 23337/28080 [46:06:33<9:24:08,  7.14s/it]
                                                          
{'loss': 0.5878, 'learning_rate': 3.648705192915341e-05, 'epoch': 9.97}

 83%|████████▎ | 23337/28080 [46:06:33<9:24:08,  7.14s/it]
 83%|████████▎ | 23338/28080 [46:06:40<9:25:30,  7.16s/it]
                                                          
{'loss': 0.5842, 'learning_rate': 3.6472053361025883e-05, 'epoch': 9.97}

 83%|████████▎ | 23338/28080 [46:06:40<9:25:30,  7.16s/it]
 83%|████████▎ | 23339/28080 [46:06:47<9:25:43,  7.16s/it]
                                                          
{'loss': 0.5901, 'learning_rate': 3.6457057633667383e-05, 'epoch': 9.97}

 83%|████████▎ | 23339/28080 [46:06:47<9:25:43,  7.16s/it]
 83%|████████▎ | 23340/28080 [46:06:55<9:23:44,  7.14s/it]
                                                          
{'loss': 0.6098, 'learning_rate': 3.644206474727738e-05, 'epoch': 9.97}

 83%|████████▎ | 23340/28080 [46:06:55<9:23:44,  7.14s/it]
 83%|████████▎ | 23341/28080 [46:07:02<9:22:43,  7.12s/it]
                                                          
{'loss': 0.6219, 'learning_rate': 3.642707470205544e-05, 'epoch': 9.97}

 83%|████████▎ | 23341/28080 [46:07:02<9:22:43,  7.12s/it]
 83%|████████▎ | 23342/28080 [46:07:09<9:21:13,  7.11s/it]
                                                          
{'loss': 0.6277, 'learning_rate': 3.641208749820096e-05, 'epoch': 9.97}

 83%|████████▎ | 23342/28080 [46:07:09<9:21:13,  7.11s/it]
 83%|████████▎ | 23343/28080 [46:07:16<9:21:33,  7.11s/it]
                                                          
{'loss': 0.6283, 'learning_rate': 3.639710313591329e-05, 'epoch': 9.97}

 83%|████████▎ | 23343/28080 [46:07:16<9:21:33,  7.11s/it]
 83%|████████▎ | 23344/28080 [46:07:23<9:21:22,  7.11s/it]
                                                          
{'loss': 0.5951, 'learning_rate': 3.638212161539175e-05, 'epoch': 9.97}

 83%|████████▎ | 23344/28080 [46:07:23<9:21:22,  7.11s/it]
 83%|████████▎ | 23345/28080 [46:07:30<9:21:31,  7.12s/it]
                                                          
{'loss': 0.6014, 'learning_rate': 3.636714293683577e-05, 'epoch': 9.97}

 83%|████████▎ | 23345/28080 [46:07:30<9:21:31,  7.12s/it]
 83%|████████▎ | 23346/28080 [46:07:37<9:24:41,  7.16s/it]
                                                          
{'loss': 0.6042, 'learning_rate': 3.6352167100444505e-05, 'epoch': 9.97}

 83%|████████▎ | 23346/28080 [46:07:37<9:24:41,  7.16s/it]
 83%|████████▎ | 23347/28080 [46:07:44<9:21:48,  7.12s/it]
                                                          
{'loss': 0.5946, 'learning_rate': 3.633719410641736e-05, 'epoch': 9.97}

 83%|████████▎ | 23347/28080 [46:07:44<9:21:48,  7.12s/it]
 83%|████████▎ | 23348/28080 [46:07:51<9:22:35,  7.13s/it]
                                                          
{'loss': 0.5894, 'learning_rate': 3.63222239549533e-05, 'epoch': 9.97}

 83%|████████▎ | 23348/28080 [46:07:52<9:22:35,  7.13s/it]
 83%|████████▎ | 23349/28080 [46:07:59<9:20:33,  7.11s/it]
                                                          
{'loss': 0.5925, 'learning_rate': 3.630725664625167e-05, 'epoch': 9.97}

 83%|████████▎ | 23349/28080 [46:07:59<9:20:33,  7.11s/it]
 83%|████████▎ | 23350/28080 [46:08:06<9:21:05,  7.12s/it]
                                                          
{'loss': 0.5925, 'learning_rate': 3.629229218051147e-05, 'epoch': 9.97}

 83%|████████▎ | 23350/28080 [46:08:06<9:21:05,  7.12s/it]
 83%|████████▎ | 23351/28080 [46:08:13<9:20:58,  7.12s/it]
                                                          
{'loss': 0.6035, 'learning_rate': 3.627733055793192e-05, 'epoch': 9.98}

 83%|████████▎ | 23351/28080 [46:08:13<9:20:58,  7.12s/it]
 83%|████████▎ | 23352/28080 [46:08:20<9:18:22,  7.09s/it]
                                                          
{'loss': 0.6085, 'learning_rate': 3.6262371778712e-05, 'epoch': 9.98}

 83%|████████▎ | 23352/28080 [46:08:20<9:18:22,  7.09s/it]
 83%|████████▎ | 23353/28080 [46:08:27<9:18:42,  7.09s/it]
                                                          
{'loss': 0.6117, 'learning_rate': 3.624741584305074e-05, 'epoch': 9.98}

 83%|████████▎ | 23353/28080 [46:08:27<9:18:42,  7.09s/it]
 83%|████████▎ | 23354/28080 [46:08:34<9:20:04,  7.11s/it]
                                                          
{'loss': 0.6012, 'learning_rate': 3.623246275114703e-05, 'epoch': 9.98}

 83%|████████▎ | 23354/28080 [46:08:34<9:20:04,  7.11s/it]
 83%|████████▎ | 23355/28080 [46:08:41<9:20:45,  7.12s/it]
                                                          
{'loss': 0.5964, 'learning_rate': 3.621751250319991e-05, 'epoch': 9.98}

 83%|████████▎ | 23355/28080 [46:08:41<9:20:45,  7.12s/it]
 83%|████████▎ | 23356/28080 [46:08:48<9:23:49,  7.16s/it]
                                                          
{'loss': 0.5984, 'learning_rate': 3.620256509940825e-05, 'epoch': 9.98}

 83%|████████▎ | 23356/28080 [46:08:48<9:23:49,  7.16s/it]
 83%|████████▎ | 23357/28080 [46:08:56<9:23:18,  7.16s/it]
                                                          
{'loss': 0.6073, 'learning_rate': 3.618762053997091e-05, 'epoch': 9.98}

 83%|████████▎ | 23357/28080 [46:08:56<9:23:18,  7.16s/it]
 83%|████████▎ | 23358/28080 [46:09:03<9:21:20,  7.13s/it]
                                                          
{'loss': 0.5945, 'learning_rate': 3.617267882508662e-05, 'epoch': 9.98}

 83%|████████▎ | 23358/28080 [46:09:03<9:21:20,  7.13s/it]
 83%|████████▎ | 23359/28080 [46:09:10<9:18:54,  7.10s/it]
                                                          
{'loss': 0.5924, 'learning_rate': 3.615773995495433e-05, 'epoch': 9.98}

 83%|████████▎ | 23359/28080 [46:09:10<9:18:54,  7.10s/it]
 83%|████████▎ | 23360/28080 [46:09:17<9:18:05,  7.09s/it]
                                                          
{'loss': 0.6166, 'learning_rate': 3.614280392977262e-05, 'epoch': 9.98}

 83%|████████▎ | 23360/28080 [46:09:17<9:18:05,  7.09s/it]
 83%|████████▎ | 23361/28080 [46:09:24<9:17:01,  7.08s/it]
                                                          
{'loss': 0.6152, 'learning_rate': 3.612787074974041e-05, 'epoch': 9.98}

 83%|████████▎ | 23361/28080 [46:09:24<9:17:01,  7.08s/it]
 83%|████████▎ | 23362/28080 [46:09:31<9:19:41,  7.12s/it]
                                                          
{'loss': 0.6188, 'learning_rate': 3.611294041505617e-05, 'epoch': 9.98}

 83%|████████▎ | 23362/28080 [46:09:31<9:19:41,  7.12s/it]
 83%|████████▎ | 23363/28080 [46:09:38<9:21:18,  7.14s/it]
                                                          
{'loss': 0.5966, 'learning_rate': 3.609801292591855e-05, 'epoch': 9.98}

 83%|████████▎ | 23363/28080 [46:09:38<9:21:18,  7.14s/it]
 83%|████████▎ | 23364/28080 [46:09:45<9:20:37,  7.13s/it]
                                                          
{'loss': 0.6094, 'learning_rate': 3.608308828252627e-05, 'epoch': 9.98}

 83%|████████▎ | 23364/28080 [46:09:45<9:20:37,  7.13s/it]
 83%|████████▎ | 23365/28080 [46:09:52<9:19:41,  7.12s/it]
                                                          
{'loss': 0.604, 'learning_rate': 3.606816648507774e-05, 'epoch': 9.98}

 83%|████████▎ | 23365/28080 [46:09:52<9:19:41,  7.12s/it]
 83%|████████▎ | 23366/28080 [46:10:00<9:18:15,  7.11s/it]
                                                          
{'loss': 0.6165, 'learning_rate': 3.605324753377159e-05, 'epoch': 9.98}

 83%|████████▎ | 23366/28080 [46:10:00<9:18:15,  7.11s/it]
 83%|████████▎ | 23367/28080 [46:10:07<9:16:49,  7.09s/it]
                                                          
{'loss': 0.6111, 'learning_rate': 3.6038331428806304e-05, 'epoch': 9.98}

 83%|████████▎ | 23367/28080 [46:10:07<9:16:49,  7.09s/it]
 83%|████████▎ | 23368/28080 [46:10:14<9:16:31,  7.09s/it]
                                                          
{'loss': 0.6323, 'learning_rate': 3.6023418170380265e-05, 'epoch': 9.98}

 83%|████████▎ | 23368/28080 [46:10:14<9:16:31,  7.09s/it]
 83%|████████▎ | 23369/28080 [46:10:21<9:15:04,  7.07s/it]
                                                          
{'loss': 0.6097, 'learning_rate': 3.6008507758691854e-05, 'epoch': 9.98}

 83%|████████▎ | 23369/28080 [46:10:21<9:15:04,  7.07s/it]
 83%|████████▎ | 23370/28080 [46:10:28<9:16:14,  7.09s/it]
                                                          
{'loss': 0.5934, 'learning_rate': 3.5993600193939544e-05, 'epoch': 9.98}

 83%|████████▎ | 23370/28080 [46:10:28<9:16:14,  7.09s/it]
 83%|████████▎ | 23371/28080 [46:10:35<9:15:56,  7.08s/it]
                                                          
{'loss': 0.6041, 'learning_rate': 3.59786954763216e-05, 'epoch': 9.98}

 83%|████████▎ | 23371/28080 [46:10:35<9:15:56,  7.08s/it]
 83%|████████▎ | 23372/28080 [46:10:42<9:17:04,  7.10s/it]
                                                          
{'loss': 0.5986, 'learning_rate': 3.59637936060363e-05, 'epoch': 9.98}

 83%|████████▎ | 23372/28080 [46:10:42<9:17:04,  7.10s/it]
 83%|████████▎ | 23373/28080 [46:10:49<9:16:27,  7.09s/it]
                                                          
{'loss': 0.6029, 'learning_rate': 3.594889458328188e-05, 'epoch': 9.98}

 83%|████████▎ | 23373/28080 [46:10:49<9:16:27,  7.09s/it]
 83%|████████▎ | 23374/28080 [46:10:56<9:15:59,  7.09s/it]
                                                          
{'loss': 0.6111, 'learning_rate': 3.5933998408256646e-05, 'epoch': 9.99}

 83%|████████▎ | 23374/28080 [46:10:56<9:15:59,  7.09s/it]
 83%|████████▎ | 23375/28080 [46:11:03<9:15:12,  7.08s/it]
                                                          
{'loss': 0.5832, 'learning_rate': 3.591910508115867e-05, 'epoch': 9.99}

 83%|████████▎ | 23375/28080 [46:11:03<9:15:12,  7.08s/it]
 83%|████████▎ | 23376/28080 [46:11:10<9:15:54,  7.09s/it]
                                                          
{'loss': 0.6076, 'learning_rate': 3.590421460218626e-05, 'epoch': 9.99}

 83%|████████▎ | 23376/28080 [46:11:10<9:15:54,  7.09s/it]
 83%|████████▎ | 23377/28080 [46:11:17<9:15:43,  7.09s/it]
                                                          
{'loss': 0.5927, 'learning_rate': 3.58893269715373e-05, 'epoch': 9.99}

 83%|████████▎ | 23377/28080 [46:11:17<9:15:43,  7.09s/it]
 83%|████████▎ | 23378/28080 [46:11:25<9:16:37,  7.10s/it]
                                                          
{'loss': 0.5929, 'learning_rate': 3.5874442189409996e-05, 'epoch': 9.99}

 83%|████████▎ | 23378/28080 [46:11:25<9:16:37,  7.10s/it]
 83%|████████▎ | 23379/28080 [46:11:32<9:16:45,  7.11s/it]
                                                          
{'loss': 0.5916, 'learning_rate': 3.5859560256002286e-05, 'epoch': 9.99}

 83%|████████▎ | 23379/28080 [46:11:32<9:16:45,  7.11s/it]
 83%|████████▎ | 23380/28080 [46:11:39<9:17:43,  7.12s/it]
                                                          
{'loss': 0.5829, 'learning_rate': 3.5844681171512294e-05, 'epoch': 9.99}

 83%|████████▎ | 23380/28080 [46:11:39<9:17:43,  7.12s/it]
 83%|████████▎ | 23381/28080 [46:11:46<9:16:01,  7.10s/it]
                                                          
{'loss': 0.612, 'learning_rate': 3.582980493613786e-05, 'epoch': 9.99}

 83%|████████▎ | 23381/28080 [46:11:46<9:16:01,  7.10s/it]
 83%|████████▎ | 23382/28080 [46:11:53<9:16:40,  7.11s/it]
                                                          
{'loss': 0.626, 'learning_rate': 3.5814931550076924e-05, 'epoch': 9.99}

 83%|████████▎ | 23382/28080 [46:11:53<9:16:40,  7.11s/it]
 83%|████████▎ | 23383/28080 [46:12:00<9:17:23,  7.12s/it]
                                                          
{'loss': 0.6003, 'learning_rate': 3.5800061013527316e-05, 'epoch': 9.99}

 83%|████████▎ | 23383/28080 [46:12:00<9:17:23,  7.12s/it]
 83%|████████▎ | 23384/28080 [46:12:07<9:19:14,  7.15s/it]
                                                          
{'loss': 0.6003, 'learning_rate': 3.578519332668695e-05, 'epoch': 9.99}

 83%|████████▎ | 23384/28080 [46:12:07<9:19:14,  7.15s/it]
 83%|████████▎ | 23385/28080 [46:12:14<9:17:04,  7.12s/it]
                                                          
{'loss': 0.604, 'learning_rate': 3.577032848975362e-05, 'epoch': 9.99}

 83%|████████▎ | 23385/28080 [46:12:14<9:17:04,  7.12s/it]
 83%|████████▎ | 23386/28080 [46:12:22<9:18:22,  7.14s/it]
                                                          
{'loss': 0.6073, 'learning_rate': 3.575546650292505e-05, 'epoch': 9.99}

 83%|████████▎ | 23386/28080 [46:12:22<9:18:22,  7.14s/it]
 83%|████████▎ | 23387/28080 [46:12:29<9:17:03,  7.12s/it]
                                                          
{'loss': 0.6071, 'learning_rate': 3.5740607366398976e-05, 'epoch': 9.99}

 83%|████████▎ | 23387/28080 [46:12:29<9:17:03,  7.12s/it]
 83%|████████▎ | 23388/28080 [46:12:36<9:19:55,  7.16s/it]
                                                          
{'loss': 0.5996, 'learning_rate': 3.572575108037304e-05, 'epoch': 9.99}

 83%|████████▎ | 23388/28080 [46:12:36<9:19:55,  7.16s/it]
 83%|████████▎ | 23389/28080 [46:12:43<9:19:20,  7.15s/it]
                                                          
{'loss': 0.5817, 'learning_rate': 3.571089764504495e-05, 'epoch': 9.99}

 83%|████████▎ | 23389/28080 [46:12:43<9:19:20,  7.15s/it]
 83%|████████▎ | 23390/28080 [46:12:50<9:18:44,  7.15s/it]
                                                          
{'loss': 0.6417, 'learning_rate': 3.569604706061233e-05, 'epoch': 9.99}

 83%|████████▎ | 23390/28080 [46:12:50<9:18:44,  7.15s/it]
 83%|████████▎ | 23391/28080 [46:12:57<9:19:43,  7.16s/it]
                                                          
{'loss': 0.5983, 'learning_rate': 3.5681199327272704e-05, 'epoch': 9.99}

 83%|████████▎ | 23391/28080 [46:12:57<9:19:43,  7.16s/it]
 83%|████████▎ | 23392/28080 [46:13:05<9:19:13,  7.16s/it]
                                                          
{'loss': 0.6107, 'learning_rate': 3.566635444522359e-05, 'epoch': 9.99}

 83%|████████▎ | 23392/28080 [46:13:05<9:19:13,  7.16s/it]
 83%|████████▎ | 23393/28080 [46:13:12<9:16:25,  7.12s/it]
                                                          
{'loss': 0.6235, 'learning_rate': 3.565151241466255e-05, 'epoch': 9.99}

 83%|████████▎ | 23393/28080 [46:13:12<9:16:25,  7.12s/it]
 83%|████████▎ | 23394/28080 [46:13:19<9:16:00,  7.12s/it]
                                                          
{'loss': 0.6028, 'learning_rate': 3.563667323578695e-05, 'epoch': 9.99}

 83%|████████▎ | 23394/28080 [46:13:19<9:16:00,  7.12s/it]
 83%|████████▎ | 23395/28080 [46:13:26<9:13:18,  7.09s/it]
                                                          
{'loss': 0.6271, 'learning_rate': 3.5621836908794365e-05, 'epoch': 9.99}

 83%|████████▎ | 23395/28080 [46:13:26<9:13:18,  7.09s/it]
 83%|████████▎ | 23396/28080 [46:13:33<9:12:17,  7.07s/it]
                                                          
{'loss': 0.589, 'learning_rate': 3.560700343388198e-05, 'epoch': 9.99}

 83%|████████▎ | 23396/28080 [46:13:33<9:12:17,  7.07s/it]
 83%|████████▎ | 23397/28080 [46:13:40<9:12:53,  7.08s/it]
                                                          
{'loss': 0.5942, 'learning_rate': 3.55921728112473e-05, 'epoch': 9.99}

 83%|████████▎ | 23397/28080 [46:13:40<9:12:53,  7.08s/it]
 83%|████████▎ | 23398/28080 [46:13:47<9:15:01,  7.11s/it]
                                                          
{'loss': 0.5953, 'learning_rate': 3.557734504108751e-05, 'epoch': 10.0}

 83%|████████▎ | 23398/28080 [46:13:47<9:15:01,  7.11s/it]
 83%|████████▎ | 23399/28080 [46:13:54<9:14:19,  7.11s/it]
                                                          
{'loss': 0.5941, 'learning_rate': 3.556252012359998e-05, 'epoch': 10.0}

 83%|████████▎ | 23399/28080 [46:13:54<9:14:19,  7.11s/it]
 83%|████████▎ | 23400/28080 [46:14:01<9:14:24,  7.11s/it]
                                                          
{'loss': 0.6101, 'learning_rate': 3.554769805898192e-05, 'epoch': 10.0}

 83%|████████▎ | 23400/28080 [46:14:01<9:14:24,  7.11s/it]
 83%|████████▎ | 23401/28080 [46:14:08<9:13:50,  7.10s/it]
                                                          
{'loss': 0.6347, 'learning_rate': 3.5532878847430476e-05, 'epoch': 10.0}

 83%|████████▎ | 23401/28080 [46:14:08<9:13:50,  7.10s/it]
 83%|████████▎ | 23402/28080 [46:14:15<9:14:23,  7.11s/it]
                                                          
{'loss': 0.6009, 'learning_rate': 3.55180624891428e-05, 'epoch': 10.0}

 83%|████████▎ | 23402/28080 [46:14:15<9:14:23,  7.11s/it]
 83%|████████▎ | 23403/28080 [46:14:22<9:09:45,  7.05s/it]
                                                          
{'loss': 0.5831, 'learning_rate': 3.5503248984316063e-05, 'epoch': 10.0}

 83%|████████▎ | 23403/28080 [46:14:22<9:09:45,  7.05s/it]
 83%|████████▎ | 23404/28080 [46:14:29<9:08:51,  7.04s/it]
                                                          
{'loss': 0.5896, 'learning_rate': 3.54884383331473e-05, 'epoch': 10.0}

 83%|████████▎ | 23404/28080 [46:14:29<9:08:51,  7.04s/it]
 83%|████████▎ | 23405/28080 [46:14:37<9:10:55,  7.07s/it]
                                                          
{'loss': 0.5835, 'learning_rate': 3.5473630535833606e-05, 'epoch': 10.0}

 83%|████████▎ | 23405/28080 [46:14:37<9:10:55,  7.07s/it]
 83%|████████▎ | 23406/28080 [46:14:44<9:10:02,  7.06s/it]
                                                          
{'loss': 0.6004, 'learning_rate': 3.545882559257185e-05, 'epoch': 10.0}

 83%|████████▎ | 23406/28080 [46:14:44<9:10:02,  7.06s/it]
 83%|████████▎ | 23407/28080 [46:14:51<9:12:07,  7.09s/it]
                                                          
{'loss': 0.6109, 'learning_rate': 3.544402350355916e-05, 'epoch': 10.0}

 83%|████████▎ | 23407/28080 [46:14:51<9:12:07,  7.09s/it]
 83%|████████▎ | 23408/28080 [46:14:58<9:13:28,  7.11s/it]
                                                          
{'loss': 0.6085, 'learning_rate': 3.5429224268992336e-05, 'epoch': 10.0}

 83%|████████▎ | 23408/28080 [46:14:58<9:13:28,  7.11s/it]
 83%|████████▎ | 23409/28080 [46:15:06<9:24:41,  7.25s/it]
                                                          
{'loss': 0.6149, 'learning_rate': 3.541442788906846e-05, 'epoch': 10.0}

 83%|████████▎ | 23409/28080 [46:15:06<9:24:41,  7.25s/it]
 83%|████████▎ | 23410/28080 [46:15:13<9:19:43,  7.19s/it]
                                                          
{'loss': 0.5883, 'learning_rate': 3.539963436398411e-05, 'epoch': 10.0}

 83%|████████▎ | 23410/28080 [46:15:13<9:19:43,  7.19s/it]
 83%|████████▎ | 23411/28080 [46:15:20<9:20:56,  7.21s/it]
                                                          
{'loss': 0.6073, 'learning_rate': 3.53848436939363e-05, 'epoch': 10.0}

 83%|████████▎ | 23411/28080 [46:15:20<9:20:56,  7.21s/it]
 83%|████████▎ | 23412/28080 [46:15:27<9:16:30,  7.15s/it]
                                                          
{'loss': 0.6058, 'learning_rate': 3.5370055879121705e-05, 'epoch': 10.0}

 83%|████████▎ | 23412/28080 [46:15:27<9:16:30,  7.15s/it]
 83%|████████▎ | 23413/28080 [46:15:34<9:15:08,  7.14s/it]
                                                          
{'loss': 0.5739, 'learning_rate': 3.535527091973706e-05, 'epoch': 10.0}

 83%|████████▎ | 23413/28080 [46:15:34<9:15:08,  7.14s/it]
 83%|████████▎ | 23414/28080 [46:15:41<9:13:30,  7.12s/it]
                                                          
{'loss': 0.6172, 'learning_rate': 3.534048881597918e-05, 'epoch': 10.0}

 83%|████████▎ | 23414/28080 [46:15:41<9:13:30,  7.12s/it]
 83%|████████▎ | 23415/28080 [46:15:48<9:11:21,  7.09s/it]
                                                          
{'loss': 0.5818, 'learning_rate': 3.5325709568044626e-05, 'epoch': 10.0}

 83%|████████▎ | 23415/28080 [46:15:48<9:11:21,  7.09s/it]
 83%|████████▎ | 23416/28080 [46:15:55<9:12:49,  7.11s/it]
                                                          
{'loss': 0.5964, 'learning_rate': 3.5310933176130016e-05, 'epoch': 10.0}

 83%|████████▎ | 23416/28080 [46:15:55<9:12:49,  7.11s/it]
 83%|████████▎ | 23417/28080 [46:16:02<9:12:46,  7.11s/it]
                                                          
{'loss': 0.6185, 'learning_rate': 3.5296159640431925e-05, 'epoch': 10.0}

 83%|████████▎ | 23417/28080 [46:16:02<9:12:46,  7.11s/it]
 83%|████████▎ | 23418/28080 [46:16:09<9:14:05,  7.13s/it]
                                                          
{'loss': 0.606, 'learning_rate': 3.528138896114699e-05, 'epoch': 10.0}

 83%|████████▎ | 23418/28080 [46:16:09<9:14:05,  7.13s/it]
 83%|████████▎ | 23419/28080 [46:16:17<9:13:16,  7.12s/it]
                                                          
{'loss': 0.5879, 'learning_rate': 3.526662113847165e-05, 'epoch': 10.0}

 83%|████████▎ | 23419/28080 [46:16:17<9:13:16,  7.12s/it]
 83%|████████▎ | 23420/28080 [46:16:24<9:13:01,  7.12s/it]
                                                          
{'loss': 0.5846, 'learning_rate': 3.5251856172602404e-05, 'epoch': 10.0}

 83%|████████▎ | 23420/28080 [46:16:24<9:13:01,  7.12s/it]
 83%|████████▎ | 23421/28080 [46:16:31<9:14:49,  7.15s/it]
                                                          
{'loss': 0.6017, 'learning_rate': 3.5237094063735596e-05, 'epoch': 10.01}

 83%|████████▎ | 23421/28080 [46:16:31<9:14:49,  7.15s/it]
 83%|████████▎ | 23422/28080 [46:16:38<9:12:17,  7.11s/it]
                                                          
{'loss': 0.627, 'learning_rate': 3.522233481206777e-05, 'epoch': 10.01}

 83%|████████▎ | 23422/28080 [46:16:38<9:12:17,  7.11s/it]
 83%|████████▎ | 23423/28080 [46:16:45<9:11:31,  7.11s/it]
                                                          
{'loss': 0.615, 'learning_rate': 3.520757841779518e-05, 'epoch': 10.01}

 83%|████████▎ | 23423/28080 [46:16:45<9:11:31,  7.11s/it]
 83%|████████▎ | 23424/28080 [46:16:52<9:10:39,  7.10s/it]
                                                          
{'loss': 0.592, 'learning_rate': 3.5192824881114163e-05, 'epoch': 10.01}

 83%|████████▎ | 23424/28080 [46:16:52<9:10:39,  7.10s/it]
 83%|████████▎ | 23425/28080 [46:16:59<9:12:02,  7.12s/it]
                                                          
{'loss': 0.5805, 'learning_rate': 3.5178074202220995e-05, 'epoch': 10.01}

 83%|████████▎ | 23425/28080 [46:16:59<9:12:02,  7.12s/it]
 83%|████████▎ | 23426/28080 [46:17:06<9:11:29,  7.11s/it]
                                                          
{'loss': 0.5745, 'learning_rate': 3.516332638131195e-05, 'epoch': 10.01}

 83%|████████▎ | 23426/28080 [46:17:06<9:11:29,  7.11s/it]
 83%|████████▎ | 23427/28080 [46:17:13<9:10:40,  7.10s/it]
                                                          
{'loss': 0.6241, 'learning_rate': 3.5148581418583156e-05, 'epoch': 10.01}

 83%|████████▎ | 23427/28080 [46:17:13<9:10:40,  7.10s/it]
 83%|████████▎ | 23428/28080 [46:17:21<9:11:37,  7.11s/it]
                                                          
{'loss': 0.6006, 'learning_rate': 3.513383931423092e-05, 'epoch': 10.01}

 83%|████████▎ | 23428/28080 [46:17:21<9:11:37,  7.11s/it]
 83%|████████▎ | 23429/28080 [46:17:28<9:09:56,  7.09s/it]
                                                          
{'loss': 0.6143, 'learning_rate': 3.511910006845126e-05, 'epoch': 10.01}

 83%|████████▎ | 23429/28080 [46:17:28<9:09:56,  7.09s/it]
 83%|████████▎ | 23430/28080 [46:17:35<9:07:58,  7.07s/it]
                                                          
{'loss': 0.5836, 'learning_rate': 3.510436368144029e-05, 'epoch': 10.01}

 83%|████████▎ | 23430/28080 [46:17:35<9:07:58,  7.07s/it]
 83%|████████▎ | 23431/28080 [46:17:42<9:08:48,  7.08s/it]
                                                          
{'loss': 0.5758, 'learning_rate': 3.5089630153394034e-05, 'epoch': 10.01}

 83%|████████▎ | 23431/28080 [46:17:42<9:08:48,  7.08s/it]
 83%|████████▎ | 23432/28080 [46:17:49<9:07:35,  7.07s/it]
                                                          
{'loss': 0.6387, 'learning_rate': 3.5074899484508595e-05, 'epoch': 10.01}

 83%|████████▎ | 23432/28080 [46:17:49<9:07:35,  7.07s/it]
 83%|████████▎ | 23433/28080 [46:17:56<9:07:20,  7.07s/it]
                                                          
{'loss': 0.5969, 'learning_rate': 3.506017167497988e-05, 'epoch': 10.01}

 83%|████████▎ | 23433/28080 [46:17:56<9:07:20,  7.07s/it]
 83%|████████▎ | 23434/28080 [46:18:03<9:08:32,  7.08s/it]
                                                          
{'loss': 0.5976, 'learning_rate': 3.5045446725003845e-05, 'epoch': 10.01}

 83%|████████▎ | 23434/28080 [46:18:03<9:08:32,  7.08s/it]
 83%|████████▎ | 23435/28080 [46:18:10<9:08:25,  7.08s/it]
                                                          
{'loss': 0.6155, 'learning_rate': 3.50307246347763e-05, 'epoch': 10.01}

 83%|████████▎ | 23435/28080 [46:18:10<9:08:25,  7.08s/it]
 83%|████████▎ | 23436/28080 [46:18:17<9:07:02,  7.07s/it]
                                                          
{'loss': 0.6289, 'learning_rate': 3.501600540449329e-05, 'epoch': 10.01}

 83%|████████▎ | 23436/28080 [46:18:17<9:07:02,  7.07s/it]
 83%|████████▎ | 23437/28080 [46:18:24<9:05:44,  7.05s/it]
                                                          
{'loss': 0.6063, 'learning_rate': 3.5001289034350516e-05, 'epoch': 10.01}

 83%|████████▎ | 23437/28080 [46:18:24<9:05:44,  7.05s/it]
 83%|████████▎ | 23438/28080 [46:18:31<9:05:02,  7.04s/it]
                                                          
{'loss': 0.6, 'learning_rate': 3.498657552454379e-05, 'epoch': 10.01}

 83%|████████▎ | 23438/28080 [46:18:31<9:05:02,  7.04s/it]
 83%|████████▎ | 23439/28080 [46:18:38<9:07:15,  7.08s/it]
                                                          
{'loss': 0.6036, 'learning_rate': 3.4971864875268876e-05, 'epoch': 10.01}

 83%|████████▎ | 23439/28080 [46:18:38<9:07:15,  7.08s/it]
 83%|████████▎ | 23440/28080 [46:18:46<9:11:58,  7.14s/it]
                                                          
{'loss': 0.6259, 'learning_rate': 3.4957157086721395e-05, 'epoch': 10.01}

 83%|████████▎ | 23440/28080 [46:18:46<9:11:58,  7.14s/it]
 83%|████████▎ | 23441/28080 [46:18:53<9:09:19,  7.10s/it]
                                                          
{'loss': 0.6, 'learning_rate': 3.494245215909716e-05, 'epoch': 10.01}

 83%|████████▎ | 23441/28080 [46:18:53<9:09:19,  7.10s/it]
 83%|████████▎ | 23442/28080 [46:19:00<9:07:27,  7.08s/it]
                                                          
{'loss': 0.6172, 'learning_rate': 3.492775009259169e-05, 'epoch': 10.01}

 83%|████████▎ | 23442/28080 [46:19:00<9:07:27,  7.08s/it]
 83%|████████▎ | 23443/28080 [46:19:07<9:08:31,  7.10s/it]
                                                          
{'loss': 0.5951, 'learning_rate': 3.491305088740071e-05, 'epoch': 10.01}

 83%|████████▎ | 23443/28080 [46:19:07<9:08:31,  7.10s/it]
 83%|████████▎ | 23444/28080 [46:19:14<9:06:25,  7.07s/it]
                                                          
{'loss': 0.6133, 'learning_rate': 3.4898354543719616e-05, 'epoch': 10.02}

 83%|████████▎ | 23444/28080 [46:19:14<9:06:25,  7.07s/it]
 83%|████████▎ | 23445/28080 [46:19:21<9:05:29,  7.06s/it]
                                                          
{'loss': 0.588, 'learning_rate': 3.488366106174404e-05, 'epoch': 10.02}

 83%|████████▎ | 23445/28080 [46:19:21<9:05:29,  7.06s/it]
 83%|████████▎ | 23446/28080 [46:19:28<9:08:18,  7.10s/it]
                                                          
{'loss': 0.6052, 'learning_rate': 3.4868970441669364e-05, 'epoch': 10.02}

 83%|████████▎ | 23446/28080 [46:19:28<9:08:18,  7.10s/it]
 84%|████████▎ | 23447/28080 [46:19:35<9:05:14,  7.06s/it]
                                                          
{'loss': 0.5949, 'learning_rate': 3.4854282683691175e-05, 'epoch': 10.02}

 84%|████████▎ | 23447/28080 [46:19:35<9:05:14,  7.06s/it]
 84%|████████▎ | 23448/28080 [46:19:42<9:05:11,  7.06s/it]
                                                          
{'loss': 0.6003, 'learning_rate': 3.48395977880048e-05, 'epoch': 10.02}

 84%|████████▎ | 23448/28080 [46:19:42<9:05:11,  7.06s/it]
 84%|████████▎ | 23449/28080 [46:19:49<9:04:48,  7.06s/it]
                                                          
{'loss': 0.6045, 'learning_rate': 3.482491575480562e-05, 'epoch': 10.02}

 84%|████████▎ | 23449/28080 [46:19:49<9:04:48,  7.06s/it]
 84%|████████▎ | 23450/28080 [46:19:56<9:06:13,  7.08s/it]
                                                          
{'loss': 0.6169, 'learning_rate': 3.481023658428886e-05, 'epoch': 10.02}

 84%|████████▎ | 23450/28080 [46:19:56<9:06:13,  7.08s/it]
 84%|████████▎ | 23451/28080 [46:20:03<9:05:55,  7.08s/it]
                                                          
{'loss': 0.6108, 'learning_rate': 3.4795560276649987e-05, 'epoch': 10.02}

 84%|████████▎ | 23451/28080 [46:20:03<9:05:55,  7.08s/it]
 84%|████████▎ | 23452/28080 [46:20:10<9:06:12,  7.08s/it]
                                                          
{'loss': 0.5926, 'learning_rate': 3.4780886832084164e-05, 'epoch': 10.02}

 84%|████████▎ | 23452/28080 [46:20:10<9:06:12,  7.08s/it]
 84%|████████▎ | 23453/28080 [46:20:17<9:05:52,  7.08s/it]
                                                          
{'loss': 0.5926, 'learning_rate': 3.4766216250786604e-05, 'epoch': 10.02}

 84%|████████▎ | 23453/28080 [46:20:17<9:05:52,  7.08s/it]
 84%|████████▎ | 23454/28080 [46:20:25<9:06:37,  7.09s/it]
                                                          
{'loss': 0.5791, 'learning_rate': 3.475154853295245e-05, 'epoch': 10.02}

 84%|████████▎ | 23454/28080 [46:20:25<9:06:37,  7.09s/it]
 84%|████████▎ | 23455/28080 [46:20:32<9:04:26,  7.06s/it]
                                                          
{'loss': 0.6117, 'learning_rate': 3.473688367877692e-05, 'epoch': 10.02}

 84%|████████▎ | 23455/28080 [46:20:32<9:04:26,  7.06s/it]
 84%|████████▎ | 23456/28080 [46:20:39<9:04:37,  7.07s/it]
                                                          
{'loss': 0.5825, 'learning_rate': 3.472222168845504e-05, 'epoch': 10.02}

 84%|████████▎ | 23456/28080 [46:20:39<9:04:37,  7.07s/it]
 84%|████████▎ | 23457/28080 [46:20:46<9:04:51,  7.07s/it]
                                                          
{'loss': 0.6241, 'learning_rate': 3.4707562562182024e-05, 'epoch': 10.02}

 84%|████████▎ | 23457/28080 [46:20:46<9:04:51,  7.07s/it]
 84%|████████▎ | 23458/28080 [46:20:53<9:05:11,  7.08s/it]
                                                          
{'loss': 0.6024, 'learning_rate': 3.4692906300152675e-05, 'epoch': 10.02}

 84%|████████▎ | 23458/28080 [46:20:53<9:05:11,  7.08s/it]
 84%|████████▎ | 23459/28080 [46:21:00<9:05:52,  7.09s/it]
                                                          
{'loss': 0.5827, 'learning_rate': 3.467825290256213e-05, 'epoch': 10.02}

 84%|████████▎ | 23459/28080 [46:21:00<9:05:52,  7.09s/it]
 84%|████████▎ | 23460/28080 [46:21:07<9:03:07,  7.05s/it]
                                                          
{'loss': 0.6005, 'learning_rate': 3.466360236960522e-05, 'epoch': 10.02}

 84%|████████▎ | 23460/28080 [46:21:07<9:03:07,  7.05s/it]
 84%|████████▎ | 23461/28080 [46:21:14<9:02:50,  7.05s/it]
                                                          
{'loss': 0.607, 'learning_rate': 3.4648954701477024e-05, 'epoch': 10.02}

 84%|████████▎ | 23461/28080 [46:21:14<9:02:50,  7.05s/it]
 84%|████████▎ | 23462/28080 [46:21:21<9:02:48,  7.05s/it]
                                                          
{'loss': 0.6101, 'learning_rate': 3.463430989837235e-05, 'epoch': 10.02}

 84%|████████▎ | 23462/28080 [46:21:21<9:02:48,  7.05s/it]
 84%|████████▎ | 23463/28080 [46:21:28<9:04:03,  7.07s/it]
                                                          
{'loss': 0.6198, 'learning_rate': 3.461966796048591e-05, 'epoch': 10.02}

 84%|████████▎ | 23463/28080 [46:21:28<9:04:03,  7.07s/it]
 84%|████████▎ | 23464/28080 [46:21:35<9:03:28,  7.06s/it]
                                                          
{'loss': 0.6086, 'learning_rate': 3.460502888801265e-05, 'epoch': 10.02}

 84%|████████▎ | 23464/28080 [46:21:35<9:03:28,  7.06s/it]
 84%|████████▎ | 23465/28080 [46:21:42<9:06:14,  7.10s/it]
                                                          
{'loss': 0.5933, 'learning_rate': 3.4590392681147194e-05, 'epoch': 10.02}

 84%|████████▎ | 23465/28080 [46:21:42<9:06:14,  7.10s/it]
 84%|████████▎ | 23466/28080 [46:21:50<9:08:57,  7.14s/it]
                                                          
{'loss': 0.5957, 'learning_rate': 3.4575759340084416e-05, 'epoch': 10.02}

 84%|████████▎ | 23466/28080 [46:21:50<9:08:57,  7.14s/it]
 84%|████████▎ | 23467/28080 [46:21:57<9:08:08,  7.13s/it]
                                                          
{'loss': 0.5878, 'learning_rate': 3.4561128865018886e-05, 'epoch': 10.02}

 84%|████████▎ | 23467/28080 [46:21:57<9:08:08,  7.13s/it]
 84%|████████▎ | 23468/28080 [46:22:04<9:07:56,  7.13s/it]
                                                          
{'loss': 0.6023, 'learning_rate': 3.4546501256145306e-05, 'epoch': 10.03}

 84%|████████▎ | 23468/28080 [46:22:04<9:07:56,  7.13s/it]
 84%|████████▎ | 23469/28080 [46:22:11<9:05:50,  7.10s/it]
                                                          
{'loss': 0.5886, 'learning_rate': 3.453187651365819e-05, 'epoch': 10.03}

 84%|████████▎ | 23469/28080 [46:22:11<9:05:50,  7.10s/it]
 84%|████████▎ | 23470/28080 [46:22:18<9:04:39,  7.09s/it]
                                                          
{'loss': 0.6061, 'learning_rate': 3.451725463775224e-05, 'epoch': 10.03}

 84%|████████▎ | 23470/28080 [46:22:18<9:04:39,  7.09s/it]
 84%|████████▎ | 23471/28080 [46:22:25<9:04:28,  7.09s/it]
                                                          
{'loss': 0.6053, 'learning_rate': 3.450263562862191e-05, 'epoch': 10.03}

 84%|████████▎ | 23471/28080 [46:22:25<9:04:28,  7.09s/it]
 84%|████████▎ | 23472/28080 [46:22:32<9:04:49,  7.09s/it]
                                                          
{'loss': 0.6201, 'learning_rate': 3.4488019486461685e-05, 'epoch': 10.03}

 84%|████████▎ | 23472/28080 [46:22:32<9:04:49,  7.09s/it]
 84%|████████▎ | 23473/28080 [46:22:39<9:03:05,  7.07s/it]
                                                          
{'loss': 0.6142, 'learning_rate': 3.4473406211465994e-05, 'epoch': 10.03}

 84%|████████▎ | 23473/28080 [46:22:39<9:03:05,  7.07s/it]
 84%|████████▎ | 23474/28080 [46:22:46<9:03:53,  7.08s/it]
                                                          
{'loss': 0.6035, 'learning_rate': 3.445879580382932e-05, 'epoch': 10.03}

 84%|████████▎ | 23474/28080 [46:22:46<9:03:53,  7.08s/it]
 84%|████████▎ | 23475/28080 [46:22:53<9:02:39,  7.07s/it]
                                                          
{'loss': 0.5898, 'learning_rate': 3.444418826374596e-05, 'epoch': 10.03}

 84%|████████▎ | 23475/28080 [46:22:53<9:02:39,  7.07s/it]
 84%|████████▎ | 23476/28080 [46:23:00<9:00:43,  7.05s/it]
                                                          
{'loss': 0.6137, 'learning_rate': 3.442958359141038e-05, 'epoch': 10.03}

 84%|████████▎ | 23476/28080 [46:23:00<9:00:43,  7.05s/it]
 84%|████████▎ | 23477/28080 [46:23:07<9:00:48,  7.05s/it]
                                                          
{'loss': 0.6162, 'learning_rate': 3.441498178701677e-05, 'epoch': 10.03}

 84%|████████▎ | 23477/28080 [46:23:07<9:00:48,  7.05s/it]
 84%|████████▎ | 23478/28080 [46:23:14<9:01:34,  7.06s/it]
                                                          
{'loss': 0.6081, 'learning_rate': 3.440038285075941e-05, 'epoch': 10.03}

 84%|████████▎ | 23478/28080 [46:23:14<9:01:34,  7.06s/it]
 84%|████████▎ | 23479/28080 [46:23:21<9:00:45,  7.05s/it]
                                                          
{'loss': 0.5993, 'learning_rate': 3.43857867828325e-05, 'epoch': 10.03}

 84%|████████▎ | 23479/28080 [46:23:21<9:00:45,  7.05s/it]
 84%|████████▎ | 23480/28080 [46:23:28<9:00:21,  7.05s/it]
                                                          
{'loss': 0.6072, 'learning_rate': 3.43711935834303e-05, 'epoch': 10.03}

 84%|████████▎ | 23480/28080 [46:23:28<9:00:21,  7.05s/it]
 84%|████████▎ | 23481/28080 [46:23:36<9:02:00,  7.07s/it]
                                                          
{'loss': 0.5992, 'learning_rate': 3.435660325274695e-05, 'epoch': 10.03}

 84%|████████▎ | 23481/28080 [46:23:36<9:02:00,  7.07s/it]
 84%|████████▎ | 23482/28080 [46:23:43<9:01:21,  7.06s/it]
                                                          
{'loss': 0.631, 'learning_rate': 3.434201579097648e-05, 'epoch': 10.03}

 84%|████████▎ | 23482/28080 [46:23:43<9:01:21,  7.06s/it]
 84%|████████▎ | 23483/28080 [46:23:50<9:03:00,  7.09s/it]
                                                          
{'loss': 0.6195, 'learning_rate': 3.4327431198312996e-05, 'epoch': 10.03}

 84%|████████▎ | 23483/28080 [46:23:50<9:03:00,  7.09s/it]
 84%|████████▎ | 23484/28080 [46:23:57<9:04:11,  7.10s/it]
                                                          
{'loss': 0.5907, 'learning_rate': 3.4312849474950586e-05, 'epoch': 10.03}

 84%|████████▎ | 23484/28080 [46:23:57<9:04:11,  7.10s/it]
 84%|████████▎ | 23485/28080 [46:24:04<9:04:48,  7.11s/it]
                                                          
{'loss': 0.5999, 'learning_rate': 3.4298270621083176e-05, 'epoch': 10.03}

 84%|████████▎ | 23485/28080 [46:24:04<9:04:48,  7.11s/it]
 84%|████████▎ | 23486/28080 [46:24:11<9:04:51,  7.12s/it]
                                                          
{'loss': 0.6149, 'learning_rate': 3.428369463690478e-05, 'epoch': 10.03}

 84%|████████▎ | 23486/28080 [46:24:11<9:04:51,  7.12s/it]
 84%|████████▎ | 23487/28080 [46:24:18<9:04:48,  7.12s/it]
                                                          
{'loss': 0.5745, 'learning_rate': 3.426912152260928e-05, 'epoch': 10.03}

 84%|████████▎ | 23487/28080 [46:24:18<9:04:48,  7.12s/it]
 84%|████████▎ | 23488/28080 [46:24:25<9:03:32,  7.10s/it]
                                                          
{'loss': 0.6042, 'learning_rate': 3.425455127839047e-05, 'epoch': 10.03}

 84%|████████▎ | 23488/28080 [46:24:25<9:03:32,  7.10s/it]
 84%|████████▎ | 23489/28080 [46:24:33<9:07:54,  7.16s/it]
                                                          
{'loss': 0.5957, 'learning_rate': 3.4239983904442385e-05, 'epoch': 10.03}

 84%|████████▎ | 23489/28080 [46:24:33<9:07:54,  7.16s/it]
 84%|████████▎ | 23490/28080 [46:24:40<9:07:55,  7.16s/it]
                                                          
{'loss': 0.6281, 'learning_rate': 3.4225419400958636e-05, 'epoch': 10.03}

 84%|████████▎ | 23490/28080 [46:24:40<9:07:55,  7.16s/it]
 84%|████████▎ | 23491/28080 [46:24:47<9:03:46,  7.11s/it]
                                                          
{'loss': 0.5833, 'learning_rate': 3.421085776813321e-05, 'epoch': 10.04}

 84%|████████▎ | 23491/28080 [46:24:47<9:03:46,  7.11s/it]
 84%|████████▎ | 23492/28080 [46:24:54<9:03:30,  7.11s/it]
                                                          
{'loss': 0.5989, 'learning_rate': 3.419629900615959e-05, 'epoch': 10.04}

 84%|████████▎ | 23492/28080 [46:24:54<9:03:30,  7.11s/it]
 84%|████████▎ | 23493/28080 [46:25:01<9:05:04,  7.13s/it]
                                                          
{'loss': 0.5943, 'learning_rate': 3.4181743115231646e-05, 'epoch': 10.04}

 84%|████████▎ | 23493/28080 [46:25:01<9:05:04,  7.13s/it]
 84%|████████▎ | 23494/28080 [46:25:08<9:03:12,  7.11s/it]
                                                          
{'loss': 0.6132, 'learning_rate': 3.41671900955429e-05, 'epoch': 10.04}

 84%|████████▎ | 23494/28080 [46:25:08<9:03:12,  7.11s/it]
 84%|████████▎ | 23495/28080 [46:25:15<9:02:14,  7.10s/it]
                                                          
{'loss': 0.6425, 'learning_rate': 3.4152639947287064e-05, 'epoch': 10.04}

 84%|████████▎ | 23495/28080 [46:25:15<9:02:14,  7.10s/it]
 84%|████████▎ | 23496/28080 [46:25:22<9:01:13,  7.08s/it]
                                                          
{'loss': 0.6208, 'learning_rate': 3.4138092670657705e-05, 'epoch': 10.04}

 84%|████████▎ | 23496/28080 [46:25:22<9:01:13,  7.08s/it]
 84%|████████▎ | 23497/28080 [46:25:29<8:59:07,  7.06s/it]
                                                          
{'loss': 0.6104, 'learning_rate': 3.412354826584832e-05, 'epoch': 10.04}

 84%|████████▎ | 23497/28080 [46:25:29<8:59:07,  7.06s/it]
 84%|████████▎ | 23498/28080 [46:25:36<8:59:25,  7.06s/it]
                                                          
{'loss': 0.5988, 'learning_rate': 3.4109006733052336e-05, 'epoch': 10.04}

 84%|████████▎ | 23498/28080 [46:25:36<8:59:25,  7.06s/it]
 84%|████████▎ | 23499/28080 [46:25:44<9:03:36,  7.12s/it]
                                                          
{'loss': 0.5937, 'learning_rate': 3.409446807246339e-05, 'epoch': 10.04}

 84%|████████▎ | 23499/28080 [46:25:44<9:03:36,  7.12s/it]
 84%|████████▎ | 23500/28080 [46:25:51<9:02:34,  7.11s/it]
                                                          
{'loss': 0.5968, 'learning_rate': 3.407993228427478e-05, 'epoch': 10.04}

 84%|████████▎ | 23500/28080 [46:25:51<9:02:34,  7.11s/it]
 84%|████████▎ | 23501/28080 [46:25:58<9:03:02,  7.12s/it]
                                                          
{'loss': 0.6, 'learning_rate': 3.4065399368679945e-05, 'epoch': 10.04}

 84%|████████▎ | 23501/28080 [46:25:58<9:03:02,  7.12s/it]
 84%|████████▎ | 23502/28080 [46:26:05<9:02:38,  7.11s/it]
                                                          
{'loss': 0.6206, 'learning_rate': 3.405086932587212e-05, 'epoch': 10.04}

 84%|████████▎ | 23502/28080 [46:26:05<9:02:38,  7.11s/it]
 84%|████████▎ | 23503/28080 [46:26:12<9:03:36,  7.13s/it]
                                                          
{'loss': 0.5962, 'learning_rate': 3.4036342156044787e-05, 'epoch': 10.04}

 84%|████████▎ | 23503/28080 [46:26:12<9:03:36,  7.13s/it]
 84%|████████▎ | 23504/28080 [46:26:19<9:01:40,  7.10s/it]
                                                          
{'loss': 0.5883, 'learning_rate': 3.402181785939104e-05, 'epoch': 10.04}

 84%|████████▎ | 23504/28080 [46:26:19<9:01:40,  7.10s/it]
 84%|████████▎ | 23505/28080 [46:26:26<9:03:05,  7.12s/it]
                                                          
{'loss': 0.5942, 'learning_rate': 3.400729643610431e-05, 'epoch': 10.04}

 84%|████████▎ | 23505/28080 [46:26:26<9:03:05,  7.12s/it]
 84%|████████▎ | 23506/28080 [46:26:33<9:02:16,  7.11s/it]
                                                          
{'loss': 0.6094, 'learning_rate': 3.3992777886377554e-05, 'epoch': 10.04}

 84%|████████▎ | 23506/28080 [46:26:33<9:02:16,  7.11s/it]
 84%|████████▎ | 23507/28080 [46:26:41<9:02:18,  7.12s/it]
                                                          
{'loss': 0.6069, 'learning_rate': 3.397826221040412e-05, 'epoch': 10.04}

 84%|████████▎ | 23507/28080 [46:26:41<9:02:18,  7.12s/it]
 84%|████████▎ | 23508/28080 [46:26:48<9:01:29,  7.11s/it]
                                                          
{'loss': 0.6037, 'learning_rate': 3.396374940837699e-05, 'epoch': 10.04}

 84%|████████▎ | 23508/28080 [46:26:48<9:01:29,  7.11s/it]
 84%|████████▎ | 23509/28080 [46:26:55<9:00:17,  7.09s/it]
                                                          
{'loss': 0.5863, 'learning_rate': 3.394923948048936e-05, 'epoch': 10.04}

 84%|████████▎ | 23509/28080 [46:26:55<9:00:17,  7.09s/it]
 84%|████████▎ | 23510/28080 [46:27:02<8:58:49,  7.07s/it]
                                                          
{'loss': 0.5932, 'learning_rate': 3.3934732426934204e-05, 'epoch': 10.04}

 84%|████████▎ | 23510/28080 [46:27:02<8:58:49,  7.07s/it]
 84%|████████▎ | 23511/28080 [46:27:09<8:59:14,  7.08s/it]
                                                          
{'loss': 0.6035, 'learning_rate': 3.3920228247904525e-05, 'epoch': 10.04}

 84%|████████▎ | 23511/28080 [46:27:09<8:59:14,  7.08s/it]
 84%|████████▎ | 23512/28080 [46:27:16<9:01:02,  7.11s/it]
                                                          
{'loss': 0.5977, 'learning_rate': 3.3905726943593315e-05, 'epoch': 10.04}

 84%|████████▎ | 23512/28080 [46:27:16<9:01:02,  7.11s/it]
 84%|████████▎ | 23513/28080 [46:27:23<8:59:50,  7.09s/it]
                                                          
{'loss': 0.5917, 'learning_rate': 3.3891228514193405e-05, 'epoch': 10.04}

 84%|████████▎ | 23513/28080 [46:27:23<8:59:50,  7.09s/it]
 84%|████████▎ | 23514/28080 [46:27:30<9:01:42,  7.12s/it]
                                                          
{'loss': 0.5967, 'learning_rate': 3.387673295989782e-05, 'epoch': 10.04}

 84%|████████▎ | 23514/28080 [46:27:30<9:01:42,  7.12s/it]
 84%|████████▎ | 23515/28080 [46:27:37<8:59:04,  7.09s/it]
                                                          
{'loss': 0.6091, 'learning_rate': 3.386224028089932e-05, 'epoch': 10.05}

 84%|████████▎ | 23515/28080 [46:27:37<8:59:04,  7.09s/it]
 84%|████████▎ | 23516/28080 [46:27:44<8:58:27,  7.08s/it]
                                                          
{'loss': 0.6085, 'learning_rate': 3.3847750477390745e-05, 'epoch': 10.05}

 84%|████████▎ | 23516/28080 [46:27:44<8:58:27,  7.08s/it]
 84%|████████▍ | 23517/28080 [46:27:51<8:59:29,  7.09s/it]
                                                          
{'loss': 0.5791, 'learning_rate': 3.3833263549564814e-05, 'epoch': 10.05}

 84%|████████▍ | 23517/28080 [46:27:51<8:59:29,  7.09s/it]
 84%|████████▍ | 23518/28080 [46:27:59<9:00:02,  7.10s/it]
                                                          
{'loss': 0.6242, 'learning_rate': 3.381877949761433e-05, 'epoch': 10.05}

 84%|████████▍ | 23518/28080 [46:27:59<9:00:02,  7.10s/it]
 84%|████████▍ | 23519/28080 [46:28:06<9:00:29,  7.11s/it]
                                                          
{'loss': 0.593, 'learning_rate': 3.3804298321731986e-05, 'epoch': 10.05}

 84%|████████▍ | 23519/28080 [46:28:06<9:00:29,  7.11s/it]
 84%|████████▍ | 23520/28080 [46:28:13<8:59:37,  7.10s/it]
                                                          
{'loss': 0.63, 'learning_rate': 3.378982002211042e-05, 'epoch': 10.05}

 84%|████████▍ | 23520/28080 [46:28:13<8:59:37,  7.10s/it]
 84%|████████▍ | 23521/28080 [46:28:20<8:59:53,  7.11s/it]
                                                          
{'loss': 0.6249, 'learning_rate': 3.377534459894219e-05, 'epoch': 10.05}

 84%|████████▍ | 23521/28080 [46:28:20<8:59:53,  7.11s/it]
 84%|████████▍ | 23522/28080 [46:28:27<8:59:56,  7.11s/it]
                                                          
{'loss': 0.6026, 'learning_rate': 3.376087205241998e-05, 'epoch': 10.05}

 84%|████████▍ | 23522/28080 [46:28:27<8:59:56,  7.11s/it]
 84%|████████▍ | 23523/28080 [46:28:34<8:59:33,  7.10s/it]
                                                          
{'loss': 0.6008, 'learning_rate': 3.374640238273624e-05, 'epoch': 10.05}

 84%|████████▍ | 23523/28080 [46:28:34<8:59:33,  7.10s/it]
 84%|████████▍ | 23524/28080 [46:28:41<9:00:11,  7.11s/it]
                                                          
{'loss': 0.6128, 'learning_rate': 3.373193559008361e-05, 'epoch': 10.05}

 84%|████████▍ | 23524/28080 [46:28:41<9:00:11,  7.11s/it]
 84%|████████▍ | 23525/28080 [46:28:48<8:59:39,  7.11s/it]
                                                          
{'loss': 0.6029, 'learning_rate': 3.371747167465439e-05, 'epoch': 10.05}

 84%|████████▍ | 23525/28080 [46:28:48<8:59:39,  7.11s/it]
 84%|████████▍ | 23526/28080 [46:28:55<8:58:57,  7.10s/it]
                                                          
{'loss': 0.6029, 'learning_rate': 3.370301063664111e-05, 'epoch': 10.05}

 84%|████████▍ | 23526/28080 [46:28:55<8:58:57,  7.10s/it]
 84%|████████▍ | 23527/28080 [46:29:02<8:57:58,  7.09s/it]
                                                          
{'loss': 0.6222, 'learning_rate': 3.368855247623609e-05, 'epoch': 10.05}

 84%|████████▍ | 23527/28080 [46:29:02<8:57:58,  7.09s/it]
 84%|████████▍ | 23528/28080 [46:29:10<8:58:06,  7.09s/it]
                                                          
{'loss': 0.5996, 'learning_rate': 3.367409719363177e-05, 'epoch': 10.05}

 84%|████████▍ | 23528/28080 [46:29:10<8:58:06,  7.09s/it]
 84%|████████▍ | 23529/28080 [46:29:17<8:57:57,  7.09s/it]
                                                          
{'loss': 0.5905, 'learning_rate': 3.365964478902042e-05, 'epoch': 10.05}

 84%|████████▍ | 23529/28080 [46:29:17<8:57:57,  7.09s/it]
 84%|████████▍ | 23530/28080 [46:29:24<8:58:03,  7.10s/it]
                                                          
{'loss': 0.5829, 'learning_rate': 3.364519526259432e-05, 'epoch': 10.05}

 84%|████████▍ | 23530/28080 [46:29:24<8:58:03,  7.10s/it]
 84%|████████▍ | 23531/28080 [46:29:31<8:58:44,  7.11s/it]
                                                          
{'loss': 0.5885, 'learning_rate': 3.3630748614545627e-05, 'epoch': 10.05}

 84%|████████▍ | 23531/28080 [46:29:31<8:58:44,  7.11s/it]
 84%|████████▍ | 23532/28080 [46:29:38<9:01:36,  7.15s/it]
                                                          
{'loss': 0.6148, 'learning_rate': 3.361630484506667e-05, 'epoch': 10.05}

 84%|████████▍ | 23532/28080 [46:29:38<9:01:36,  7.15s/it]
 84%|████████▍ | 23533/28080 [46:29:45<9:00:59,  7.14s/it]
                                                          
{'loss': 0.5822, 'learning_rate': 3.360186395434953e-05, 'epoch': 10.05}

 84%|████████▍ | 23533/28080 [46:29:45<9:00:59,  7.14s/it]
 84%|████████▍ | 23534/28080 [46:29:52<9:01:32,  7.15s/it]
                                                          
{'loss': 0.5914, 'learning_rate': 3.358742594258637e-05, 'epoch': 10.05}

 84%|████████▍ | 23534/28080 [46:29:52<9:01:32,  7.15s/it]
 84%|████████▍ | 23535/28080 [46:29:59<8:59:58,  7.13s/it]
                                                          
{'loss': 0.6082, 'learning_rate': 3.3572990809969175e-05, 'epoch': 10.05}

 84%|████████▍ | 23535/28080 [46:29:59<8:59:58,  7.13s/it]
 84%|████████▍ | 23536/28080 [46:30:07<8:58:16,  7.11s/it]
                                                          
{'loss': 0.6138, 'learning_rate': 3.355855855669013e-05, 'epoch': 10.05}

 84%|████████▍ | 23536/28080 [46:30:07<8:58:16,  7.11s/it]
 84%|████████▍ | 23537/28080 [46:30:14<9:00:47,  7.14s/it]
                                                          
{'loss': 0.598, 'learning_rate': 3.354412918294117e-05, 'epoch': 10.05}

 84%|████████▍ | 23537/28080 [46:30:14<9:00:47,  7.14s/it]
 84%|████████▍ | 23538/28080 [46:30:21<9:02:15,  7.16s/it]
                                                          
{'loss': 0.6021, 'learning_rate': 3.35297026889142e-05, 'epoch': 10.06}

 84%|████████▍ | 23538/28080 [46:30:21<9:02:15,  7.16s/it]
 84%|████████▍ | 23539/28080 [46:30:28<8:59:37,  7.13s/it]
                                                          
{'loss': 0.635, 'learning_rate': 3.3515279074801314e-05, 'epoch': 10.06}

 84%|████████▍ | 23539/28080 [46:30:28<8:59:37,  7.13s/it]
 84%|████████▍ | 23540/28080 [46:30:35<9:00:14,  7.14s/it]
                                                          
{'loss': 0.6024, 'learning_rate': 3.350085834079422e-05, 'epoch': 10.06}

 84%|████████▍ | 23540/28080 [46:30:35<9:00:14,  7.14s/it]
 84%|████████▍ | 23541/28080 [46:30:42<9:00:02,  7.14s/it]
                                                          
{'loss': 0.5882, 'learning_rate': 3.348644048708491e-05, 'epoch': 10.06}

 84%|████████▍ | 23541/28080 [46:30:42<9:00:02,  7.14s/it]
 84%|████████▍ | 23542/28080 [46:30:49<8:57:53,  7.11s/it]
                                                          
{'loss': 0.5994, 'learning_rate': 3.3472025513865076e-05, 'epoch': 10.06}

 84%|████████▍ | 23542/28080 [46:30:49<8:57:53,  7.11s/it]
 84%|████████▍ | 23543/28080 [46:30:57<8:59:23,  7.13s/it]
                                                          
{'loss': 0.6001, 'learning_rate': 3.345761342132664e-05, 'epoch': 10.06}

 84%|████████▍ | 23543/28080 [46:30:57<8:59:23,  7.13s/it]
 84%|████████▍ | 23544/28080 [46:31:04<8:59:56,  7.14s/it]
                                                          
{'loss': 0.5861, 'learning_rate': 3.344320420966124e-05, 'epoch': 10.06}

 84%|████████▍ | 23544/28080 [46:31:04<8:59:56,  7.14s/it]
 84%|████████▍ | 23545/28080 [46:31:11<8:59:17,  7.13s/it]
                                                          
{'loss': 0.6026, 'learning_rate': 3.342879787906061e-05, 'epoch': 10.06}

 84%|████████▍ | 23545/28080 [46:31:11<8:59:17,  7.13s/it]
 84%|████████▍ | 23546/28080 [46:31:18<8:58:00,  7.12s/it]
                                                          
{'loss': 0.5935, 'learning_rate': 3.3414394429716335e-05, 'epoch': 10.06}

 84%|████████▍ | 23546/28080 [46:31:18<8:58:00,  7.12s/it]
 84%|████████▍ | 23547/28080 [46:31:25<8:56:02,  7.10s/it]
                                                          
{'loss': 0.5949, 'learning_rate': 3.3399993861820163e-05, 'epoch': 10.06}

 84%|████████▍ | 23547/28080 [46:31:25<8:56:02,  7.10s/it]
 84%|████████▍ | 23548/28080 [46:31:32<8:55:37,  7.09s/it]
                                                          
{'loss': 0.601, 'learning_rate': 3.3385596175563635e-05, 'epoch': 10.06}

 84%|████████▍ | 23548/28080 [46:31:32<8:55:37,  7.09s/it]
 84%|████████▍ | 23549/28080 [46:31:39<8:56:18,  7.10s/it]
                                                          
{'loss': 0.6016, 'learning_rate': 3.337120137113828e-05, 'epoch': 10.06}

 84%|████████▍ | 23549/28080 [46:31:39<8:56:18,  7.10s/it]
 84%|████████▍ | 23550/28080 [46:31:46<8:55:13,  7.09s/it]
                                                          
{'loss': 0.6255, 'learning_rate': 3.3356809448735535e-05, 'epoch': 10.06}

 84%|████████▍ | 23550/28080 [46:31:46<8:55:13,  7.09s/it]
 84%|████████▍ | 23551/28080 [46:31:53<8:54:36,  7.08s/it]
                                                          
{'loss': 0.5902, 'learning_rate': 3.3342420408546985e-05, 'epoch': 10.06}

 84%|████████▍ | 23551/28080 [46:31:53<8:54:36,  7.08s/it]
 84%|████████▍ | 23552/28080 [46:32:00<8:57:27,  7.12s/it]
                                                          
{'loss': 0.5948, 'learning_rate': 3.3328034250764e-05, 'epoch': 10.06}

 84%|████████▍ | 23552/28080 [46:32:00<8:57:27,  7.12s/it]
 84%|████████▍ | 23553/28080 [46:32:08<8:56:33,  7.11s/it]
                                                          
{'loss': 0.5952, 'learning_rate': 3.331365097557807e-05, 'epoch': 10.06}

 84%|████████▍ | 23553/28080 [46:32:08<8:56:33,  7.11s/it]
 84%|████████▍ | 23554/28080 [46:32:15<8:56:30,  7.11s/it]
                                                          
{'loss': 0.5962, 'learning_rate': 3.329927058318039e-05, 'epoch': 10.06}

 84%|████████▍ | 23554/28080 [46:32:15<8:56:30,  7.11s/it]
 84%|████████▍ | 23555/28080 [46:32:22<8:57:02,  7.12s/it]
                                                          
{'loss': 0.6035, 'learning_rate': 3.3284893073762365e-05, 'epoch': 10.06}

 84%|████████▍ | 23555/28080 [46:32:22<8:57:02,  7.12s/it]
 84%|████████▍ | 23556/28080 [46:32:29<8:56:23,  7.11s/it]
                                                          
{'loss': 0.6038, 'learning_rate': 3.327051844751525e-05, 'epoch': 10.06}

 84%|████████▍ | 23556/28080 [46:32:29<8:56:23,  7.11s/it]
 84%|████████▍ | 23557/28080 [46:32:36<8:54:39,  7.09s/it]
                                                          
{'loss': 0.5889, 'learning_rate': 3.325614670463034e-05, 'epoch': 10.06}

 84%|████████▍ | 23557/28080 [46:32:36<8:54:39,  7.09s/it]
 84%|████████▍ | 23558/28080 [46:32:43<8:53:40,  7.08s/it]
                                                          
{'loss': 0.6222, 'learning_rate': 3.32417778452988e-05, 'epoch': 10.06}

 84%|████████▍ | 23558/28080 [46:32:43<8:53:40,  7.08s/it]
 84%|████████▍ | 23559/28080 [46:32:50<8:52:42,  7.07s/it]
                                                          
{'loss': 0.5918, 'learning_rate': 3.322741186971179e-05, 'epoch': 10.06}

 84%|████████▍ | 23559/28080 [46:32:50<8:52:42,  7.07s/it]
 84%|████████▍ | 23560/28080 [46:32:57<8:53:31,  7.08s/it]
                                                          
{'loss': 0.5821, 'learning_rate': 3.321304877806039e-05, 'epoch': 10.06}

 84%|████████▍ | 23560/28080 [46:32:57<8:53:31,  7.08s/it]
 84%|████████▍ | 23561/28080 [46:33:04<8:53:00,  7.08s/it]
                                                          
{'loss': 0.5808, 'learning_rate': 3.3198688570535764e-05, 'epoch': 10.07}

 84%|████████▍ | 23561/28080 [46:33:04<8:53:00,  7.08s/it]
 84%|████████▍ | 23562/28080 [46:33:11<8:51:07,  7.05s/it]
                                                          
{'loss': 0.5828, 'learning_rate': 3.318433124732895e-05, 'epoch': 10.07}

 84%|████████▍ | 23562/28080 [46:33:11<8:51:07,  7.05s/it]
 84%|████████▍ | 23563/28080 [46:33:18<8:54:39,  7.10s/it]
                                                          
{'loss': 0.6099, 'learning_rate': 3.31699768086309e-05, 'epoch': 10.07}

 84%|████████▍ | 23563/28080 [46:33:18<8:54:39,  7.10s/it]
 84%|████████▍ | 23564/28080 [46:33:26<8:54:14,  7.10s/it]
                                                          
{'loss': 0.596, 'learning_rate': 3.3155625254632646e-05, 'epoch': 10.07}

 84%|████████▍ | 23564/28080 [46:33:26<8:54:14,  7.10s/it]
 84%|████████▍ | 23565/28080 [46:33:33<8:53:51,  7.09s/it]
                                                          
{'loss': 0.5932, 'learning_rate': 3.314127658552502e-05, 'epoch': 10.07}

 84%|████████▍ | 23565/28080 [46:33:33<8:53:51,  7.09s/it]
 84%|████████▍ | 23566/28080 [46:33:40<8:53:08,  7.09s/it]
                                                          
{'loss': 0.5972, 'learning_rate': 3.3126930801499036e-05, 'epoch': 10.07}

 84%|████████▍ | 23566/28080 [46:33:40<8:53:08,  7.09s/it]
 84%|████████▍ | 23567/28080 [46:33:47<8:53:11,  7.09s/it]
                                                          
{'loss': 0.5841, 'learning_rate': 3.311258790274552e-05, 'epoch': 10.07}

 84%|████████▍ | 23567/28080 [46:33:47<8:53:11,  7.09s/it]
 84%|████████▍ | 23568/28080 [46:33:54<8:55:09,  7.12s/it]
                                                          
{'loss': 0.5807, 'learning_rate': 3.309824788945526e-05, 'epoch': 10.07}

 84%|████████▍ | 23568/28080 [46:33:54<8:55:09,  7.12s/it]
 84%|████████▍ | 23569/28080 [46:34:01<8:55:10,  7.12s/it]
                                                          
{'loss': 0.6143, 'learning_rate': 3.308391076181899e-05, 'epoch': 10.07}

 84%|████████▍ | 23569/28080 [46:34:01<8:55:10,  7.12s/it]
 84%|████████▍ | 23570/28080 [46:34:08<8:52:58,  7.09s/it]
                                                          
{'loss': 0.6093, 'learning_rate': 3.30695765200276e-05, 'epoch': 10.07}

 84%|████████▍ | 23570/28080 [46:34:08<8:52:58,  7.09s/it]
 84%|████████▍ | 23571/28080 [46:34:15<8:54:58,  7.12s/it]
                                                          
{'loss': 0.5809, 'learning_rate': 3.305524516427161e-05, 'epoch': 10.07}

 84%|████████▍ | 23571/28080 [46:34:15<8:54:58,  7.12s/it]
 84%|████████▍ | 23572/28080 [46:34:22<8:54:21,  7.11s/it]
                                                          
{'loss': 0.6114, 'learning_rate': 3.304091669474188e-05, 'epoch': 10.07}

 84%|████████▍ | 23572/28080 [46:34:22<8:54:21,  7.11s/it]
 84%|████████▍ | 23573/28080 [46:34:29<8:53:38,  7.10s/it]
                                                          
{'loss': 0.5837, 'learning_rate': 3.3026591111628814e-05, 'epoch': 10.07}

 84%|████████▍ | 23573/28080 [46:34:30<8:53:38,  7.10s/it]
 84%|████████▍ | 23574/28080 [46:34:37<8:54:08,  7.11s/it]
                                                          
{'loss': 0.601, 'learning_rate': 3.30122684151232e-05, 'epoch': 10.07}

 84%|████████▍ | 23574/28080 [46:34:37<8:54:08,  7.11s/it]
 84%|████████▍ | 23575/28080 [46:34:44<8:51:33,  7.08s/it]
                                                          
{'loss': 0.6237, 'learning_rate': 3.299794860541541e-05, 'epoch': 10.07}

 84%|████████▍ | 23575/28080 [46:34:44<8:51:33,  7.08s/it]
 84%|████████▍ | 23576/28080 [46:34:51<8:51:42,  7.08s/it]
                                                          
{'loss': 0.5951, 'learning_rate': 3.298363168269613e-05, 'epoch': 10.07}

 84%|████████▍ | 23576/28080 [46:34:51<8:51:42,  7.08s/it]
 84%|████████▍ | 23577/28080 [46:34:58<8:52:28,  7.09s/it]
                                                          
{'loss': 0.6115, 'learning_rate': 3.296931764715572e-05, 'epoch': 10.07}

 84%|████████▍ | 23577/28080 [46:34:58<8:52:28,  7.09s/it]
 84%|████████▍ | 23578/28080 [46:35:05<8:53:28,  7.11s/it]
                                                          
{'loss': 0.5907, 'learning_rate': 3.295500649898467e-05, 'epoch': 10.07}

 84%|████████▍ | 23578/28080 [46:35:05<8:53:28,  7.11s/it]
 84%|████████▍ | 23579/28080 [46:35:12<8:50:53,  7.08s/it]
                                                          
{'loss': 0.623, 'learning_rate': 3.294069823837328e-05, 'epoch': 10.07}

 84%|████████▍ | 23579/28080 [46:35:12<8:50:53,  7.08s/it]
 84%|████████▍ | 23580/28080 [46:35:19<8:51:45,  7.09s/it]
                                                          
{'loss': 0.6052, 'learning_rate': 3.292639286551202e-05, 'epoch': 10.07}

 84%|████████▍ | 23580/28080 [46:35:19<8:51:45,  7.09s/it]
 84%|████████▍ | 23581/28080 [46:35:26<8:52:56,  7.11s/it]
                                                          
{'loss': 0.6027, 'learning_rate': 3.2912090380591174e-05, 'epoch': 10.07}

 84%|████████▍ | 23581/28080 [46:35:26<8:52:56,  7.11s/it]
 84%|████████▍ | 23582/28080 [46:35:33<8:53:17,  7.11s/it]
                                                          
{'loss': 0.5972, 'learning_rate': 3.289779078380098e-05, 'epoch': 10.07}

 84%|████████▍ | 23582/28080 [46:35:33<8:53:17,  7.11s/it]
 84%|████████▍ | 23583/28080 [46:35:41<8:55:16,  7.14s/it]
                                                          
{'loss': 0.6102, 'learning_rate': 3.288349407533167e-05, 'epoch': 10.07}

 84%|████████▍ | 23583/28080 [46:35:41<8:55:16,  7.14s/it]
 84%|████████▍ | 23584/28080 [46:35:48<8:54:31,  7.13s/it]
                                                          
{'loss': 0.6057, 'learning_rate': 3.286920025537354e-05, 'epoch': 10.07}

 84%|████████▍ | 23584/28080 [46:35:48<8:54:31,  7.13s/it]
 84%|████████▍ | 23585/28080 [46:35:55<8:53:55,  7.13s/it]
                                                          
{'loss': 0.5956, 'learning_rate': 3.285490932411666e-05, 'epoch': 10.08}

 84%|████████▍ | 23585/28080 [46:35:55<8:53:55,  7.13s/it]
 84%|████████▍ | 23586/28080 [46:36:02<8:54:12,  7.13s/it]
                                                          
{'loss': 0.5816, 'learning_rate': 3.2840621281751276e-05, 'epoch': 10.08}

 84%|████████▍ | 23586/28080 [46:36:02<8:54:12,  7.13s/it]
 84%|████████▍ | 23587/28080 [46:36:09<8:54:56,  7.14s/it]
                                                          
{'loss': 0.6223, 'learning_rate': 3.282633612846736e-05, 'epoch': 10.08}

 84%|████████▍ | 23587/28080 [46:36:09<8:54:56,  7.14s/it]
 84%|████████▍ | 23588/28080 [46:36:16<8:53:03,  7.12s/it]
                                                          
{'loss': 0.6154, 'learning_rate': 3.281205386445493e-05, 'epoch': 10.08}

 84%|████████▍ | 23588/28080 [46:36:16<8:53:03,  7.12s/it]
 84%|████████▍ | 23589/28080 [46:36:23<8:52:31,  7.11s/it]
                                                          
{'loss': 0.6236, 'learning_rate': 3.2797774489904146e-05, 'epoch': 10.08}

 84%|████████▍ | 23589/28080 [46:36:23<8:52:31,  7.11s/it]
 84%|████████▍ | 23590/28080 [46:36:30<8:49:59,  7.08s/it]
                                                          
{'loss': 0.6085, 'learning_rate': 3.2783498005004796e-05, 'epoch': 10.08}

 84%|████████▍ | 23590/28080 [46:36:30<8:49:59,  7.08s/it]
 84%|████████▍ | 23591/28080 [46:36:38<8:52:41,  7.12s/it]
                                                          
{'loss': 0.6112, 'learning_rate': 3.276922440994701e-05, 'epoch': 10.08}

 84%|████████▍ | 23591/28080 [46:36:38<8:52:41,  7.12s/it]
 84%|████████▍ | 23592/28080 [46:36:45<8:49:50,  7.08s/it]
                                                          
{'loss': 0.603, 'learning_rate': 3.275495370492057e-05, 'epoch': 10.08}

 84%|████████▍ | 23592/28080 [46:36:45<8:49:50,  7.08s/it]
 84%|████████▍ | 23593/28080 [46:36:52<8:50:27,  7.09s/it]
                                                          
{'loss': 0.5937, 'learning_rate': 3.274068589011536e-05, 'epoch': 10.08}

 84%|████████▍ | 23593/28080 [46:36:52<8:50:27,  7.09s/it]
 84%|████████▍ | 23594/28080 [46:36:59<8:50:32,  7.10s/it]
                                                          
{'loss': 0.6099, 'learning_rate': 3.272642096572112e-05, 'epoch': 10.08}

 84%|████████▍ | 23594/28080 [46:36:59<8:50:32,  7.10s/it]
 84%|████████▍ | 23595/28080 [46:37:06<8:49:20,  7.08s/it]
                                                          
{'loss': 0.5968, 'learning_rate': 3.271215893192778e-05, 'epoch': 10.08}

 84%|████████▍ | 23595/28080 [46:37:06<8:49:20,  7.08s/it]
 84%|████████▍ | 23596/28080 [46:37:13<8:50:05,  7.09s/it]
                                                          
{'loss': 0.6008, 'learning_rate': 3.2697899788924984e-05, 'epoch': 10.08}

 84%|████████▍ | 23596/28080 [46:37:13<8:50:05,  7.09s/it]
 84%|████████▍ | 23597/28080 [46:37:20<8:49:49,  7.09s/it]
                                                          
{'loss': 0.6134, 'learning_rate': 3.268364353690245e-05, 'epoch': 10.08}

 84%|████████▍ | 23597/28080 [46:37:20<8:49:49,  7.09s/it]
 84%|████████▍ | 23598/28080 [46:37:27<8:51:07,  7.11s/it]
                                                          
{'loss': 0.5866, 'learning_rate': 3.266939017604981e-05, 'epoch': 10.08}

 84%|████████▍ | 23598/28080 [46:37:27<8:51:07,  7.11s/it]
 84%|████████▍ | 23599/28080 [46:37:34<8:51:59,  7.12s/it]
                                                          
{'loss': 0.5891, 'learning_rate': 3.265513970655676e-05, 'epoch': 10.08}

 84%|████████▍ | 23599/28080 [46:37:34<8:51:59,  7.12s/it]
 84%|████████▍ | 23600/28080 [46:37:42<8:54:06,  7.15s/it]
                                                          
{'loss': 0.6041, 'learning_rate': 3.264089212861279e-05, 'epoch': 10.08}

 84%|████████▍ | 23600/28080 [46:37:42<8:54:06,  7.15s/it]
 84%|████████▍ | 23601/28080 [46:37:49<8:54:07,  7.16s/it]
                                                          
{'loss': 0.5926, 'learning_rate': 3.2626647442407645e-05, 'epoch': 10.08}

 84%|████████▍ | 23601/28080 [46:37:49<8:54:07,  7.16s/it]
 84%|████████▍ | 23602/28080 [46:37:56<8:52:47,  7.14s/it]
                                                          
{'loss': 0.604, 'learning_rate': 3.261240564813059e-05, 'epoch': 10.08}

 84%|████████▍ | 23602/28080 [46:37:56<8:52:47,  7.14s/it]
 84%|████████▍ | 23603/28080 [46:38:03<8:53:20,  7.15s/it]
                                                          
{'loss': 0.5841, 'learning_rate': 3.259816674597127e-05, 'epoch': 10.08}

 84%|████████▍ | 23603/28080 [46:38:03<8:53:20,  7.15s/it]
 84%|████████▍ | 23604/28080 [46:38:10<8:50:55,  7.12s/it]
                                                          
{'loss': 0.5805, 'learning_rate': 3.258393073611901e-05, 'epoch': 10.08}

 84%|████████▍ | 23604/28080 [46:38:10<8:50:55,  7.12s/it]
 84%|████████▍ | 23605/28080 [46:38:17<8:51:24,  7.13s/it]
                                                          
{'loss': 0.5814, 'learning_rate': 3.25696976187633e-05, 'epoch': 10.08}

 84%|████████▍ | 23605/28080 [46:38:17<8:51:24,  7.13s/it]
 84%|████████▍ | 23606/28080 [46:38:24<8:51:37,  7.13s/it]
                                                          
{'loss': 0.5998, 'learning_rate': 3.2555467394093456e-05, 'epoch': 10.08}

 84%|████████▍ | 23606/28080 [46:38:24<8:51:37,  7.13s/it]
 84%|████████▍ | 23607/28080 [46:38:31<8:51:22,  7.13s/it]
                                                          
{'loss': 0.6062, 'learning_rate': 3.254124006229881e-05, 'epoch': 10.08}

 84%|████████▍ | 23607/28080 [46:38:31<8:51:22,  7.13s/it]
 84%|████████▍ | 23608/28080 [46:38:38<8:49:59,  7.11s/it]
                                                          
{'loss': 0.6071, 'learning_rate': 3.252701562356855e-05, 'epoch': 10.09}

 84%|████████▍ | 23608/28080 [46:38:38<8:49:59,  7.11s/it]
 84%|████████▍ | 23609/28080 [46:38:45<8:47:24,  7.08s/it]
                                                          
{'loss': 0.5943, 'learning_rate': 3.251279407809204e-05, 'epoch': 10.09}

 84%|████████▍ | 23609/28080 [46:38:45<8:47:24,  7.08s/it]
 84%|████████▍ | 23610/28080 [46:38:52<8:45:09,  7.05s/it]
                                                          
{'loss': 0.6119, 'learning_rate': 3.249857542605844e-05, 'epoch': 10.09}

 84%|████████▍ | 23610/28080 [46:38:52<8:45:09,  7.05s/it]
 84%|████████▍ | 23611/28080 [46:39:00<8:46:02,  7.06s/it]
                                                          
{'loss': 0.6027, 'learning_rate': 3.248435966765692e-05, 'epoch': 10.09}

 84%|████████▍ | 23611/28080 [46:39:00<8:46:02,  7.06s/it]
 84%|████████▍ | 23612/28080 [46:39:07<8:46:14,  7.07s/it]
                                                          
{'loss': 0.6027, 'learning_rate': 3.247014680307661e-05, 'epoch': 10.09}

 84%|████████▍ | 23612/28080 [46:39:07<8:46:14,  7.07s/it]
 84%|████████▍ | 23613/28080 [46:39:14<8:45:19,  7.06s/it]
                                                          
{'loss': 0.6074, 'learning_rate': 3.24559368325065e-05, 'epoch': 10.09}

 84%|████████▍ | 23613/28080 [46:39:14<8:45:19,  7.06s/it]
 84%|████████▍ | 23614/28080 [46:39:21<8:46:47,  7.08s/it]
                                                          
{'loss': 0.5852, 'learning_rate': 3.244172975613579e-05, 'epoch': 10.09}

 84%|████████▍ | 23614/28080 [46:39:21<8:46:47,  7.08s/it]
 84%|████████▍ | 23615/28080 [46:39:28<8:48:44,  7.11s/it]
                                                          
{'loss': 0.602, 'learning_rate': 3.242752557415343e-05, 'epoch': 10.09}

 84%|████████▍ | 23615/28080 [46:39:28<8:48:44,  7.11s/it]
 84%|████████▍ | 23616/28080 [46:39:35<8:47:11,  7.09s/it]
                                                          
{'loss': 0.6152, 'learning_rate': 3.241332428674837e-05, 'epoch': 10.09}

 84%|████████▍ | 23616/28080 [46:39:35<8:47:11,  7.09s/it]
 84%|████████▍ | 23617/28080 [46:39:42<8:48:05,  7.10s/it]
                                                          
{'loss': 0.5915, 'learning_rate': 3.239912589410951e-05, 'epoch': 10.09}

 84%|████████▍ | 23617/28080 [46:39:42<8:48:05,  7.10s/it]
 84%|████████▍ | 23618/28080 [46:39:49<8:47:57,  7.10s/it]
                                                          
{'loss': 0.582, 'learning_rate': 3.2384930396425844e-05, 'epoch': 10.09}

 84%|████████▍ | 23618/28080 [46:39:49<8:47:57,  7.10s/it]
 84%|████████▍ | 23619/28080 [46:39:56<8:47:09,  7.09s/it]
                                                          
{'loss': 0.6199, 'learning_rate': 3.2370737793886136e-05, 'epoch': 10.09}

 84%|████████▍ | 23619/28080 [46:39:56<8:47:09,  7.09s/it]
 84%|████████▍ | 23620/28080 [46:40:03<8:47:12,  7.09s/it]
                                                          
{'loss': 0.5798, 'learning_rate': 3.235654808667935e-05, 'epoch': 10.09}

 84%|████████▍ | 23620/28080 [46:40:03<8:47:12,  7.09s/it]
 84%|████████▍ | 23621/28080 [46:40:10<8:46:21,  7.08s/it]
                                                          
{'loss': 0.614, 'learning_rate': 3.234236127499404e-05, 'epoch': 10.09}

 84%|████████▍ | 23621/28080 [46:40:10<8:46:21,  7.08s/it]
 84%|████████▍ | 23622/28080 [46:40:17<8:44:25,  7.06s/it]
                                                          
{'loss': 0.6077, 'learning_rate': 3.232817735901916e-05, 'epoch': 10.09}

 84%|████████▍ | 23622/28080 [46:40:17<8:44:25,  7.06s/it]
 84%|████████▍ | 23623/28080 [46:40:25<8:47:06,  7.10s/it]
                                                          
{'loss': 0.5998, 'learning_rate': 3.231399633894322e-05, 'epoch': 10.09}

 84%|████████▍ | 23623/28080 [46:40:25<8:47:06,  7.10s/it]
 84%|████████▍ | 23624/28080 [46:40:32<8:46:54,  7.09s/it]
                                                          
{'loss': 0.6057, 'learning_rate': 3.229981821495506e-05, 'epoch': 10.09}

 84%|████████▍ | 23624/28080 [46:40:32<8:46:54,  7.09s/it]
 84%|████████▍ | 23625/28080 [46:40:39<8:47:29,  7.10s/it]
                                                          
{'loss': 0.5941, 'learning_rate': 3.2285642987243236e-05, 'epoch': 10.09}

 84%|████████▍ | 23625/28080 [46:40:39<8:47:29,  7.10s/it]
 84%|████████▍ | 23626/28080 [46:40:46<8:48:39,  7.12s/it]
                                                          
{'loss': 0.6022, 'learning_rate': 3.227147065599631e-05, 'epoch': 10.09}

 84%|████████▍ | 23626/28080 [46:40:46<8:48:39,  7.12s/it]
 84%|████████▍ | 23627/28080 [46:40:53<8:46:52,  7.10s/it]
                                                          
{'loss': 0.6011, 'learning_rate': 3.225730122140283e-05, 'epoch': 10.09}

 84%|████████▍ | 23627/28080 [46:40:53<8:46:52,  7.10s/it]
 84%|████████▍ | 23628/28080 [46:41:00<8:46:14,  7.09s/it]
                                                          
{'loss': 0.597, 'learning_rate': 3.224313468365134e-05, 'epoch': 10.09}

 84%|████████▍ | 23628/28080 [46:41:00<8:46:14,  7.09s/it]
 84%|████████▍ | 23629/28080 [46:41:07<8:43:01,  7.05s/it]
                                                          
{'loss': 0.6162, 'learning_rate': 3.222897104293032e-05, 'epoch': 10.09}

 84%|████████▍ | 23629/28080 [46:41:07<8:43:01,  7.05s/it]
 84%|████████▍ | 23630/28080 [46:41:14<8:44:01,  7.07s/it]
                                                          
{'loss': 0.6009, 'learning_rate': 3.221481029942816e-05, 'epoch': 10.09}

 84%|████████▍ | 23630/28080 [46:41:14<8:44:01,  7.07s/it]
 84%|████████▍ | 23631/28080 [46:41:21<8:42:53,  7.05s/it]
                                                          
{'loss': 0.6025, 'learning_rate': 3.2200652453333226e-05, 'epoch': 10.09}

 84%|████████▍ | 23631/28080 [46:41:21<8:42:53,  7.05s/it]
 84%|████████▍ | 23632/28080 [46:41:28<8:42:34,  7.05s/it]
                                                          
{'loss': 0.5906, 'learning_rate': 3.218649750483399e-05, 'epoch': 10.1}

 84%|████████▍ | 23632/28080 [46:41:28<8:42:34,  7.05s/it]
 84%|████████▍ | 23633/28080 [46:41:35<8:44:41,  7.08s/it]
                                                          
{'loss': 0.5895, 'learning_rate': 3.217234545411862e-05, 'epoch': 10.1}

 84%|████████▍ | 23633/28080 [46:41:35<8:44:41,  7.08s/it]
 84%|████████▍ | 23634/28080 [46:41:43<8:45:50,  7.10s/it]
                                                          
{'loss': 0.5677, 'learning_rate': 3.215819630137559e-05, 'epoch': 10.1}

 84%|████████▍ | 23634/28080 [46:41:43<8:45:50,  7.10s/it]
 84%|████████▍ | 23635/28080 [46:41:50<8:45:25,  7.09s/it]
                                                          
{'loss': 0.5971, 'learning_rate': 3.214405004679291e-05, 'epoch': 10.1}

 84%|████████▍ | 23635/28080 [46:41:50<8:45:25,  7.09s/it]
 84%|████████▍ | 23636/28080 [46:41:57<8:44:59,  7.09s/it]
                                                          
{'loss': 0.6059, 'learning_rate': 3.212990669055896e-05, 'epoch': 10.1}

 84%|████████▍ | 23636/28080 [46:41:57<8:44:59,  7.09s/it]
 84%|████████▍ | 23637/28080 [46:42:04<8:42:41,  7.06s/it]
                                                          
{'loss': 0.6048, 'learning_rate': 3.2115766232861834e-05, 'epoch': 10.1}

 84%|████████▍ | 23637/28080 [46:42:04<8:42:41,  7.06s/it]
 84%|████████▍ | 23638/28080 [46:42:11<8:44:09,  7.08s/it]
                                                          
{'loss': 0.627, 'learning_rate': 3.21016286738896e-05, 'epoch': 10.1}

 84%|████████▍ | 23638/28080 [46:42:11<8:44:09,  7.08s/it]
 84%|████████▍ | 23639/28080 [46:42:18<8:42:50,  7.06s/it]
                                                          
{'loss': 0.6134, 'learning_rate': 3.208749401383049e-05, 'epoch': 10.1}

 84%|████████▍ | 23639/28080 [46:42:18<8:42:50,  7.06s/it]
 84%|████████▍ | 23640/28080 [46:42:25<8:45:00,  7.09s/it]
                                                          
{'loss': 0.6076, 'learning_rate': 3.207336225287241e-05, 'epoch': 10.1}

 84%|████████▍ | 23640/28080 [46:42:25<8:45:00,  7.09s/it]
 84%|████████▍ | 23641/28080 [46:42:32<8:46:15,  7.11s/it]
                                                          
{'loss': 0.6163, 'learning_rate': 3.205923339120345e-05, 'epoch': 10.1}

 84%|████████▍ | 23641/28080 [46:42:32<8:46:15,  7.11s/it]
 84%|████████▍ | 23642/28080 [46:42:39<8:44:56,  7.10s/it]
                                                          
{'loss': 0.5819, 'learning_rate': 3.204510742901151e-05, 'epoch': 10.1}

 84%|████████▍ | 23642/28080 [46:42:39<8:44:56,  7.10s/it]
 84%|████████▍ | 23643/28080 [46:42:46<8:44:18,  7.09s/it]
                                                          
{'loss': 0.581, 'learning_rate': 3.203098436648461e-05, 'epoch': 10.1}

 84%|████████▍ | 23643/28080 [46:42:46<8:44:18,  7.09s/it]
 84%|████████▍ | 23644/28080 [46:42:53<8:45:34,  7.11s/it]
                                                          
{'loss': 0.5863, 'learning_rate': 3.2016864203810584e-05, 'epoch': 10.1}

 84%|████████▍ | 23644/28080 [46:42:53<8:45:34,  7.11s/it]
 84%|████████▍ | 23645/28080 [46:43:01<8:45:01,  7.10s/it]
                                                          
{'loss': 0.6083, 'learning_rate': 3.200274694117733e-05, 'epoch': 10.1}

 84%|████████▍ | 23645/28080 [46:43:01<8:45:01,  7.10s/it]
 84%|████████▍ | 23646/28080 [46:43:08<8:43:03,  7.08s/it]
                                                          
{'loss': 0.6079, 'learning_rate': 3.1988632578772546e-05, 'epoch': 10.1}

 84%|████████▍ | 23646/28080 [46:43:08<8:43:03,  7.08s/it]
 84%|████████▍ | 23647/28080 [46:43:15<8:42:48,  7.08s/it]
                                                          
{'loss': 0.5999, 'learning_rate': 3.1974521116784174e-05, 'epoch': 10.1}

 84%|████████▍ | 23647/28080 [46:43:15<8:42:48,  7.08s/it]
 84%|████████▍ | 23648/28080 [46:43:22<8:43:01,  7.08s/it]
                                                          
{'loss': 0.579, 'learning_rate': 3.196041255539986e-05, 'epoch': 10.1}

 84%|████████▍ | 23648/28080 [46:43:22<8:43:01,  7.08s/it]
 84%|████████▍ | 23649/28080 [46:43:29<8:44:26,  7.10s/it]
                                                          
{'loss': 0.6042, 'learning_rate': 3.194630689480729e-05, 'epoch': 10.1}

 84%|████████▍ | 23649/28080 [46:43:29<8:44:26,  7.10s/it]
 84%|████████▍ | 23650/28080 [46:43:36<8:42:47,  7.08s/it]
                                                          
{'loss': 0.6132, 'learning_rate': 3.193220413519415e-05, 'epoch': 10.1}

 84%|████████▍ | 23650/28080 [46:43:36<8:42:47,  7.08s/it]
 84%|████████▍ | 23651/28080 [46:43:43<8:43:00,  7.09s/it]
                                                          
{'loss': 0.6134, 'learning_rate': 3.19181042767481e-05, 'epoch': 10.1}

 84%|████████▍ | 23651/28080 [46:43:43<8:43:00,  7.09s/it]
 84%|████████▍ | 23652/28080 [46:43:50<8:41:42,  7.07s/it]
                                                          
{'loss': 0.6154, 'learning_rate': 3.190400731965662e-05, 'epoch': 10.1}

 84%|████████▍ | 23652/28080 [46:43:50<8:41:42,  7.07s/it]
 84%|████████▍ | 23653/28080 [46:43:57<8:42:14,  7.08s/it]
                                                          
{'loss': 0.5849, 'learning_rate': 3.18899132641074e-05, 'epoch': 10.1}

 84%|████████▍ | 23653/28080 [46:43:57<8:42:14,  7.08s/it]
 84%|████████▍ | 23654/28080 [46:44:04<8:43:46,  7.10s/it]
                                                          
{'loss': 0.5952, 'learning_rate': 3.187582211028786e-05, 'epoch': 10.1}

 84%|████████▍ | 23654/28080 [46:44:04<8:43:46,  7.10s/it]
 84%|████████▍ | 23655/28080 [46:44:11<8:41:46,  7.07s/it]
                                                          
{'loss': 0.6004, 'learning_rate': 3.18617338583855e-05, 'epoch': 10.11}

 84%|████████▍ | 23655/28080 [46:44:11<8:41:46,  7.07s/it]
 84%|████████▍ | 23656/28080 [46:44:18<8:41:30,  7.07s/it]
                                                          
{'loss': 0.604, 'learning_rate': 3.184764850858765e-05, 'epoch': 10.11}

 84%|████████▍ | 23656/28080 [46:44:18<8:41:30,  7.07s/it]
 84%|████████▍ | 23657/28080 [46:44:26<8:43:03,  7.10s/it]
                                                          
{'loss': 0.5917, 'learning_rate': 3.183356606108184e-05, 'epoch': 10.11}

 84%|████████▍ | 23657/28080 [46:44:26<8:43:03,  7.10s/it]
 84%|████████▍ | 23658/28080 [46:44:33<8:44:24,  7.12s/it]
                                                          
{'loss': 0.5944, 'learning_rate': 3.1819486516055376e-05, 'epoch': 10.11}

 84%|████████▍ | 23658/28080 [46:44:33<8:44:24,  7.12s/it]
 84%|████████▍ | 23659/28080 [46:44:40<8:44:00,  7.11s/it]
                                                          
{'loss': 0.6268, 'learning_rate': 3.180540987369557e-05, 'epoch': 10.11}

 84%|████████▍ | 23659/28080 [46:44:40<8:44:00,  7.11s/it]
 84%|████████▍ | 23660/28080 [46:44:47<8:42:05,  7.09s/it]
                                                          
{'loss': 0.6272, 'learning_rate': 3.179133613418961e-05, 'epoch': 10.11}

 84%|████████▍ | 23660/28080 [46:44:47<8:42:05,  7.09s/it]
 84%|████████▍ | 23661/28080 [46:44:54<8:42:47,  7.10s/it]
                                                          
{'loss': 0.6246, 'learning_rate': 3.1777265297724873e-05, 'epoch': 10.11}

 84%|████████▍ | 23661/28080 [46:44:54<8:42:47,  7.10s/it]
 84%|████████▍ | 23662/28080 [46:45:01<8:43:34,  7.11s/it]
                                                          
{'loss': 0.6098, 'learning_rate': 3.176319736448849e-05, 'epoch': 10.11}

 84%|████████▍ | 23662/28080 [46:45:01<8:43:34,  7.11s/it]
 84%|████████▍ | 23663/28080 [46:45:08<8:42:31,  7.10s/it]
                                                          
{'loss': 0.6001, 'learning_rate': 3.174913233466764e-05, 'epoch': 10.11}

 84%|████████▍ | 23663/28080 [46:45:08<8:42:31,  7.10s/it]
 84%|████████▍ | 23664/28080 [46:45:15<8:43:41,  7.12s/it]
                                                          
{'loss': 0.6009, 'learning_rate': 3.17350702084494e-05, 'epoch': 10.11}

 84%|████████▍ | 23664/28080 [46:45:15<8:43:41,  7.12s/it]
 84%|████████▍ | 23665/28080 [46:45:22<8:44:10,  7.12s/it]
                                                          
{'loss': 0.5918, 'learning_rate': 3.1721010986020846e-05, 'epoch': 10.11}

 84%|████████▍ | 23665/28080 [46:45:22<8:44:10,  7.12s/it]
 84%|████████▍ | 23666/28080 [46:45:30<8:43:39,  7.12s/it]
                                                          
{'loss': 0.6065, 'learning_rate': 3.1706954667569096e-05, 'epoch': 10.11}

 84%|████████▍ | 23666/28080 [46:45:30<8:43:39,  7.12s/it]
 84%|████████▍ | 23667/28080 [46:45:37<8:43:04,  7.11s/it]
                                                          
{'loss': 0.605, 'learning_rate': 3.169290125328106e-05, 'epoch': 10.11}

 84%|████████▍ | 23667/28080 [46:45:37<8:43:04,  7.11s/it]
 84%|████████▍ | 23668/28080 [46:45:44<8:41:26,  7.09s/it]
                                                          
{'loss': 0.6023, 'learning_rate': 3.1678850743343866e-05, 'epoch': 10.11}

 84%|████████▍ | 23668/28080 [46:45:44<8:41:26,  7.09s/it]
 84%|████████▍ | 23669/28080 [46:45:51<8:38:56,  7.06s/it]
                                                          
{'loss': 0.6266, 'learning_rate': 3.166480313794423e-05, 'epoch': 10.11}

 84%|████████▍ | 23669/28080 [46:45:51<8:38:56,  7.06s/it]
 84%|████████▍ | 23670/28080 [46:45:58<8:40:04,  7.08s/it]
                                                          
{'loss': 0.581, 'learning_rate': 3.165075843726922e-05, 'epoch': 10.11}

 84%|████████▍ | 23670/28080 [46:45:58<8:40:04,  7.08s/it]
 84%|████████▍ | 23671/28080 [46:46:05<8:41:07,  7.09s/it]
                                                          
{'loss': 0.5948, 'learning_rate': 3.1636716641505524e-05, 'epoch': 10.11}

 84%|████████▍ | 23671/28080 [46:46:05<8:41:07,  7.09s/it]
 84%|████████▍ | 23672/28080 [46:46:12<8:39:58,  7.08s/it]
                                                          
{'loss': 0.5967, 'learning_rate': 3.16226777508401e-05, 'epoch': 10.11}

 84%|████████▍ | 23672/28080 [46:46:12<8:39:58,  7.08s/it]
 84%|████████▍ | 23673/28080 [46:46:19<8:40:34,  7.09s/it]
                                                          
{'loss': 0.6046, 'learning_rate': 3.160864176545969e-05, 'epoch': 10.11}

 84%|████████▍ | 23673/28080 [46:46:19<8:40:34,  7.09s/it]
 84%|████████▍ | 23674/28080 [46:46:26<8:38:07,  7.06s/it]
                                                          
{'loss': 0.6076, 'learning_rate': 3.1594608685550974e-05, 'epoch': 10.11}

 84%|████████▍ | 23674/28080 [46:46:26<8:38:07,  7.06s/it]
 84%|████████▍ | 23675/28080 [46:46:33<8:37:37,  7.05s/it]
                                                          
{'loss': 0.6052, 'learning_rate': 3.158057851130061e-05, 'epoch': 10.11}

 84%|████████▍ | 23675/28080 [46:46:33<8:37:37,  7.05s/it]
 84%|████████▍ | 23676/28080 [46:46:40<8:35:21,  7.02s/it]
                                                          
{'loss': 0.6011, 'learning_rate': 3.1566551242895395e-05, 'epoch': 10.11}

 84%|████████▍ | 23676/28080 [46:46:40<8:35:21,  7.02s/it]
 84%|████████▍ | 23677/28080 [46:46:47<8:37:47,  7.06s/it]
                                                          
{'loss': 0.6054, 'learning_rate': 3.155252688052185e-05, 'epoch': 10.11}

 84%|████████▍ | 23677/28080 [46:46:47<8:37:47,  7.06s/it]
 84%|████████▍ | 23678/28080 [46:46:54<8:40:03,  7.09s/it]
                                                          
{'loss': 0.6066, 'learning_rate': 3.153850542436659e-05, 'epoch': 10.12}

 84%|████████▍ | 23678/28080 [46:46:54<8:40:03,  7.09s/it]
 84%|████████▍ | 23679/28080 [46:47:01<8:38:57,  7.08s/it]
                                                          
{'loss': 0.6047, 'learning_rate': 3.152448687461607e-05, 'epoch': 10.12}

 84%|████████▍ | 23679/28080 [46:47:01<8:38:57,  7.08s/it]
 84%|████████▍ | 23680/28080 [46:47:09<8:40:19,  7.10s/it]
                                                          
{'loss': 0.6167, 'learning_rate': 3.151047123145692e-05, 'epoch': 10.12}

 84%|████████▍ | 23680/28080 [46:47:09<8:40:19,  7.10s/it]
 84%|████████▍ | 23681/28080 [46:47:16<8:39:19,  7.08s/it]
                                                          
{'loss': 0.625, 'learning_rate': 3.1496458495075515e-05, 'epoch': 10.12}

 84%|████████▍ | 23681/28080 [46:47:16<8:39:19,  7.08s/it]
 84%|████████▍ | 23682/28080 [46:47:23<8:39:33,  7.09s/it]
                                                          
{'loss': 0.6128, 'learning_rate': 3.148244866565841e-05, 'epoch': 10.12}

 84%|████████▍ | 23682/28080 [46:47:23<8:39:33,  7.09s/it]
 84%|████████▍ | 23683/28080 [46:47:30<8:39:37,  7.09s/it]
                                                          
{'loss': 0.6117, 'learning_rate': 3.146844174339178e-05, 'epoch': 10.12}

 84%|████████▍ | 23683/28080 [46:47:30<8:39:37,  7.09s/it]
 84%|████████▍ | 23684/28080 [46:47:37<8:38:57,  7.08s/it]
                                                          
{'loss': 0.5806, 'learning_rate': 3.1454437728462154e-05, 'epoch': 10.12}

 84%|████████▍ | 23684/28080 [46:47:37<8:38:57,  7.08s/it]
 84%|████████▍ | 23685/28080 [46:47:44<8:37:19,  7.06s/it]
                                                          
{'loss': 0.6184, 'learning_rate': 3.1440436621055694e-05, 'epoch': 10.12}

 84%|████████▍ | 23685/28080 [46:47:44<8:37:19,  7.06s/it]
 84%|████████▍ | 23686/28080 [46:47:51<8:35:46,  7.04s/it]
                                                          
{'loss': 0.6019, 'learning_rate': 3.142643842135881e-05, 'epoch': 10.12}

 84%|████████▍ | 23686/28080 [46:47:51<8:35:46,  7.04s/it]
 84%|████████▍ | 23687/28080 [46:47:58<8:38:18,  7.08s/it]
                                                          
{'loss': 0.6022, 'learning_rate': 3.141244312955768e-05, 'epoch': 10.12}

 84%|████████▍ | 23687/28080 [46:47:58<8:38:18,  7.08s/it]
 84%|████████▍ | 23688/28080 [46:48:05<8:39:35,  7.10s/it]
                                                          
{'loss': 0.6081, 'learning_rate': 3.1398450745838495e-05, 'epoch': 10.12}

 84%|████████▍ | 23688/28080 [46:48:05<8:39:35,  7.10s/it]
 84%|████████▍ | 23689/28080 [46:48:12<8:38:01,  7.08s/it]
                                                          
{'loss': 0.5974, 'learning_rate': 3.138446127038741e-05, 'epoch': 10.12}

 84%|████████▍ | 23689/28080 [46:48:12<8:38:01,  7.08s/it]
 84%|████████▍ | 23690/28080 [46:48:19<8:37:18,  7.07s/it]
                                                          
{'loss': 0.6003, 'learning_rate': 3.137047470339047e-05, 'epoch': 10.12}

 84%|████████▍ | 23690/28080 [46:48:19<8:37:18,  7.07s/it]
 84%|████████▍ | 23691/28080 [46:48:26<8:38:34,  7.09s/it]
                                                          
{'loss': 0.6036, 'learning_rate': 3.135649104503388e-05, 'epoch': 10.12}

 84%|████████▍ | 23691/28080 [46:48:26<8:38:34,  7.09s/it]
 84%|████████▍ | 23692/28080 [46:48:33<8:38:07,  7.08s/it]
                                                          
{'loss': 0.5949, 'learning_rate': 3.1342510295503586e-05, 'epoch': 10.12}

 84%|████████▍ | 23692/28080 [46:48:33<8:38:07,  7.08s/it]
 84%|████████▍ | 23693/28080 [46:48:41<8:39:28,  7.10s/it]
                                                          
{'loss': 0.6262, 'learning_rate': 3.1328532454985656e-05, 'epoch': 10.12}

 84%|████████▍ | 23693/28080 [46:48:41<8:39:28,  7.10s/it]
 84%|████████▍ | 23694/28080 [46:48:48<8:38:45,  7.10s/it]
                                                          
{'loss': 0.5931, 'learning_rate': 3.131455752366591e-05, 'epoch': 10.12}

 84%|████████▍ | 23694/28080 [46:48:48<8:38:45,  7.10s/it]
 84%|████████▍ | 23695/28080 [46:48:55<8:37:22,  7.08s/it]
                                                          
{'loss': 0.606, 'learning_rate': 3.1300585501730455e-05, 'epoch': 10.12}

 84%|████████▍ | 23695/28080 [46:48:55<8:37:22,  7.08s/it]
 84%|████████▍ | 23696/28080 [46:49:02<8:38:05,  7.09s/it]
                                                          
{'loss': 0.6052, 'learning_rate': 3.1286616389365084e-05, 'epoch': 10.12}

 84%|████████▍ | 23696/28080 [46:49:02<8:38:05,  7.09s/it]
 84%|████████▍ | 23697/28080 [46:49:09<8:38:41,  7.10s/it]
                                                          
{'loss': 0.5979, 'learning_rate': 3.127265018675565e-05, 'epoch': 10.12}

 84%|████████▍ | 23697/28080 [46:49:09<8:38:41,  7.10s/it]
 84%|████████▍ | 23698/28080 [46:49:16<8:39:20,  7.11s/it]
                                                          
{'loss': 0.5997, 'learning_rate': 3.1258686894087926e-05, 'epoch': 10.12}

 84%|████████▍ | 23698/28080 [46:49:16<8:39:20,  7.11s/it]
 84%|████████▍ | 23699/28080 [46:49:23<8:37:40,  7.09s/it]
                                                          
{'loss': 0.6041, 'learning_rate': 3.124472651154772e-05, 'epoch': 10.12}

 84%|████████▍ | 23699/28080 [46:49:23<8:37:40,  7.09s/it]
 84%|████████▍ | 23700/28080 [46:49:30<8:37:05,  7.08s/it]
                                                          
{'loss': 0.6169, 'learning_rate': 3.1230769039320734e-05, 'epoch': 10.12}

 84%|████████▍ | 23700/28080 [46:49:30<8:37:05,  7.08s/it]
 84%|████████▍ | 23701/28080 [46:49:37<8:35:07,  7.06s/it]
                                                          
{'loss': 0.6076, 'learning_rate': 3.12168144775927e-05, 'epoch': 10.12}

 84%|████████▍ | 23701/28080 [46:49:37<8:35:07,  7.06s/it]
 84%|████████▍ | 23702/28080 [46:49:44<8:35:19,  7.06s/it]
                                                          
{'loss': 0.6149, 'learning_rate': 3.120286282654927e-05, 'epoch': 10.13}

 84%|████████▍ | 23702/28080 [46:49:44<8:35:19,  7.06s/it]
 84%|████████▍ | 23703/28080 [46:49:51<8:37:40,  7.10s/it]
                                                          
{'loss': 0.6022, 'learning_rate': 3.1188914086376e-05, 'epoch': 10.13}

 84%|████████▍ | 23703/28080 [46:49:51<8:37:40,  7.10s/it]
 84%|████████▍ | 23704/28080 [46:49:59<8:38:07,  7.10s/it]
                                                          
{'loss': 0.5867, 'learning_rate': 3.117496825725846e-05, 'epoch': 10.13}

 84%|████████▍ | 23704/28080 [46:49:59<8:38:07,  7.10s/it]
 84%|████████▍ | 23705/28080 [46:50:06<8:37:26,  7.10s/it]
                                                          
{'loss': 0.5984, 'learning_rate': 3.116102533938225e-05, 'epoch': 10.13}

 84%|████████▍ | 23705/28080 [46:50:06<8:37:26,  7.10s/it]
 84%|████████▍ | 23706/28080 [46:50:13<8:36:31,  7.09s/it]
                                                          
{'loss': 0.5935, 'learning_rate': 3.114708533293287e-05, 'epoch': 10.13}

 84%|████████▍ | 23706/28080 [46:50:13<8:36:31,  7.09s/it]
 84%|████████▍ | 23707/28080 [46:50:20<8:37:40,  7.10s/it]
                                                          
{'loss': 0.593, 'learning_rate': 3.113314823809571e-05, 'epoch': 10.13}

 84%|████████▍ | 23707/28080 [46:50:20<8:37:40,  7.10s/it]
 84%|████████▍ | 23708/28080 [46:50:27<8:35:19,  7.07s/it]
                                                          
{'loss': 0.6163, 'learning_rate': 3.111921405505619e-05, 'epoch': 10.13}

 84%|████████▍ | 23708/28080 [46:50:27<8:35:19,  7.07s/it]
 84%|████████▍ | 23709/28080 [46:50:34<8:36:36,  7.09s/it]
                                                          
{'loss': 0.6246, 'learning_rate': 3.110528278399976e-05, 'epoch': 10.13}

 84%|████████▍ | 23709/28080 [46:50:34<8:36:36,  7.09s/it]
 84%|████████▍ | 23710/28080 [46:50:41<8:34:56,  7.07s/it]
                                                          
{'loss': 0.5896, 'learning_rate': 3.109135442511166e-05, 'epoch': 10.13}

 84%|████████▍ | 23710/28080 [46:50:41<8:34:56,  7.07s/it]
 84%|████████▍ | 23711/28080 [46:50:48<8:37:41,  7.11s/it]
                                                          
{'loss': 0.5936, 'learning_rate': 3.107742897857738e-05, 'epoch': 10.13}

 84%|████████▍ | 23711/28080 [46:50:48<8:37:41,  7.11s/it]
 84%|████████▍ | 23712/28080 [46:50:55<8:37:15,  7.11s/it]
                                                          
{'loss': 0.5915, 'learning_rate': 3.1063506444582e-05, 'epoch': 10.13}

 84%|████████▍ | 23712/28080 [46:50:55<8:37:15,  7.11s/it]
 84%|████████▍ | 23713/28080 [46:51:02<8:37:56,  7.12s/it]
                                                          
{'loss': 0.5839, 'learning_rate': 3.104958682331074e-05, 'epoch': 10.13}

 84%|████████▍ | 23713/28080 [46:51:02<8:37:56,  7.12s/it]
 84%|████████▍ | 23714/28080 [46:51:10<8:36:54,  7.10s/it]
                                                          
{'loss': 0.6087, 'learning_rate': 3.10356701149489e-05, 'epoch': 10.13}

 84%|████████▍ | 23714/28080 [46:51:10<8:36:54,  7.10s/it]
 84%|████████▍ | 23715/28080 [46:51:17<8:36:56,  7.11s/it]
                                                          
{'loss': 0.5829, 'learning_rate': 3.1021756319681545e-05, 'epoch': 10.13}

 84%|████████▍ | 23715/28080 [46:51:17<8:36:56,  7.11s/it]
 84%|████████▍ | 23716/28080 [46:51:24<8:36:39,  7.10s/it]
                                                          
{'loss': 0.6118, 'learning_rate': 3.100784543769389e-05, 'epoch': 10.13}

 84%|████████▍ | 23716/28080 [46:51:24<8:36:39,  7.10s/it]
 84%|████████▍ | 23717/28080 [46:51:31<8:35:06,  7.08s/it]
                                                          
{'loss': 0.5823, 'learning_rate': 3.099393746917084e-05, 'epoch': 10.13}

 84%|████████▍ | 23717/28080 [46:51:31<8:35:06,  7.08s/it]
 84%|████████▍ | 23718/28080 [46:51:38<8:36:06,  7.10s/it]
                                                          
{'loss': 0.6025, 'learning_rate': 3.098003241429759e-05, 'epoch': 10.13}

 84%|████████▍ | 23718/28080 [46:51:38<8:36:06,  7.10s/it]
 84%|████████▍ | 23719/28080 [46:51:45<8:38:57,  7.14s/it]
                                                          
{'loss': 0.5887, 'learning_rate': 3.096613027325898e-05, 'epoch': 10.13}

 84%|████████▍ | 23719/28080 [46:51:45<8:38:57,  7.14s/it]
 84%|████████▍ | 23720/28080 [46:51:52<8:39:20,  7.15s/it]
                                                          
{'loss': 0.6165, 'learning_rate': 3.0952231046240094e-05, 'epoch': 10.13}

 84%|████████▍ | 23720/28080 [46:51:52<8:39:20,  7.15s/it]
 84%|████████▍ | 23721/28080 [46:51:59<8:38:56,  7.14s/it]
                                                          
{'loss': 0.5969, 'learning_rate': 3.0938334733425806e-05, 'epoch': 10.13}

 84%|████████▍ | 23721/28080 [46:51:59<8:38:56,  7.14s/it]
 84%|████████▍ | 23722/28080 [46:52:06<8:36:15,  7.11s/it]
                                                          
{'loss': 0.5897, 'learning_rate': 3.092444133500097e-05, 'epoch': 10.13}

 84%|████████▍ | 23722/28080 [46:52:06<8:36:15,  7.11s/it]
 84%|████████▍ | 23723/28080 [46:52:14<8:35:29,  7.10s/it]
                                                          
{'loss': 0.6051, 'learning_rate': 3.091055085115038e-05, 'epoch': 10.13}

 84%|████████▍ | 23723/28080 [46:52:14<8:35:29,  7.10s/it]
 84%|████████▍ | 23724/28080 [46:52:21<8:35:02,  7.09s/it]
                                                          
{'loss': 0.6285, 'learning_rate': 3.089666328205895e-05, 'epoch': 10.13}

 84%|████████▍ | 23724/28080 [46:52:21<8:35:02,  7.09s/it]
 84%|████████▍ | 23725/28080 [46:52:28<8:35:32,  7.10s/it]
                                                          
{'loss': 0.6029, 'learning_rate': 3.088277862791136e-05, 'epoch': 10.14}

 84%|████████▍ | 23725/28080 [46:52:28<8:35:32,  7.10s/it]
 84%|████████▍ | 23726/28080 [46:52:35<8:34:02,  7.08s/it]
                                                          
{'loss': 0.5882, 'learning_rate': 3.086889688889238e-05, 'epoch': 10.14}

 84%|████████▍ | 23726/28080 [46:52:35<8:34:02,  7.08s/it]
 84%|████████▍ | 23727/28080 [46:52:42<8:33:55,  7.08s/it]
                                                          
{'loss': 0.5967, 'learning_rate': 3.085501806518659e-05, 'epoch': 10.14}

 84%|████████▍ | 23727/28080 [46:52:42<8:33:55,  7.08s/it]
 85%|████████▍ | 23728/28080 [46:52:49<8:32:49,  7.07s/it]
                                                          
{'loss': 0.6078, 'learning_rate': 3.084114215697878e-05, 'epoch': 10.14}

 85%|████████▍ | 23728/28080 [46:52:49<8:32:49,  7.07s/it]
 85%|████████▍ | 23729/28080 [46:52:56<8:34:39,  7.10s/it]
                                                          
{'loss': 0.5843, 'learning_rate': 3.082726916445339e-05, 'epoch': 10.14}

 85%|████████▍ | 23729/28080 [46:52:56<8:34:39,  7.10s/it]
 85%|████████▍ | 23730/28080 [46:53:03<8:34:50,  7.10s/it]
                                                          
{'loss': 0.602, 'learning_rate': 3.0813399087795205e-05, 'epoch': 10.14}

 85%|████████▍ | 23730/28080 [46:53:03<8:34:50,  7.10s/it]
 85%|████████▍ | 23731/28080 [46:53:10<8:33:27,  7.08s/it]
                                                          
{'loss': 0.5885, 'learning_rate': 3.079953192718851e-05, 'epoch': 10.14}

 85%|████████▍ | 23731/28080 [46:53:10<8:33:27,  7.08s/it]
 85%|████████▍ | 23732/28080 [46:53:17<8:30:45,  7.05s/it]
                                                          
{'loss': 0.5975, 'learning_rate': 3.078566768281799e-05, 'epoch': 10.14}

 85%|████████▍ | 23732/28080 [46:53:17<8:30:45,  7.05s/it]
 85%|████████▍ | 23733/28080 [46:53:24<8:33:06,  7.08s/it]
                                                          
{'loss': 0.6095, 'learning_rate': 3.077180635486793e-05, 'epoch': 10.14}

 85%|████████▍ | 23733/28080 [46:53:24<8:33:06,  7.08s/it]
 85%|████████▍ | 23734/28080 [46:53:32<8:34:45,  7.11s/it]
                                                          
{'loss': 0.6048, 'learning_rate': 3.075794794352285e-05, 'epoch': 10.14}

 85%|████████▍ | 23734/28080 [46:53:32<8:34:45,  7.11s/it]
 85%|████████▍ | 23735/28080 [46:53:39<8:35:41,  7.12s/it]
                                                          
{'loss': 0.6141, 'learning_rate': 3.0744092448967145e-05, 'epoch': 10.14}

 85%|████████▍ | 23735/28080 [46:53:39<8:35:41,  7.12s/it]
 85%|████████▍ | 23736/28080 [46:53:46<8:34:31,  7.11s/it]
                                                          
{'loss': 0.6001, 'learning_rate': 3.073023987138504e-05, 'epoch': 10.14}

 85%|████████▍ | 23736/28080 [46:53:46<8:34:31,  7.11s/it]
 85%|████████▍ | 23737/28080 [46:53:53<8:34:01,  7.10s/it]
                                                          
{'loss': 0.6139, 'learning_rate': 3.0716390210960924e-05, 'epoch': 10.14}

 85%|████████▍ | 23737/28080 [46:53:53<8:34:01,  7.10s/it]
 85%|████████▍ | 23738/28080 [46:54:00<8:33:56,  7.10s/it]
                                                          
{'loss': 0.5998, 'learning_rate': 3.0702543467878954e-05, 'epoch': 10.14}

 85%|████████▍ | 23738/28080 [46:54:00<8:33:56,  7.10s/it]
 85%|████████▍ | 23739/28080 [46:54:07<8:33:29,  7.10s/it]
                                                          
{'loss': 0.6002, 'learning_rate': 3.068869964232346e-05, 'epoch': 10.14}

 85%|████████▍ | 23739/28080 [46:54:07<8:33:29,  7.10s/it]
 85%|████████▍ | 23740/28080 [46:54:14<8:34:53,  7.12s/it]
                                                          
{'loss': 0.5962, 'learning_rate': 3.0674858734478564e-05, 'epoch': 10.14}

 85%|████████▍ | 23740/28080 [46:54:14<8:34:53,  7.12s/it]
 85%|████████▍ | 23741/28080 [46:54:21<8:34:30,  7.11s/it]
                                                          
{'loss': 0.5934, 'learning_rate': 3.066102074452839e-05, 'epoch': 10.14}

 85%|████████▍ | 23741/28080 [46:54:21<8:34:30,  7.11s/it]
 85%|████████▍ | 23742/28080 [46:54:28<8:32:45,  7.09s/it]
                                                          
{'loss': 0.6008, 'learning_rate': 3.064718567265704e-05, 'epoch': 10.14}

 85%|████████▍ | 23742/28080 [46:54:28<8:32:45,  7.09s/it]
 85%|████████▍ | 23743/28080 [46:54:35<8:32:50,  7.09s/it]
                                                          
{'loss': 0.5896, 'learning_rate': 3.063335351904861e-05, 'epoch': 10.14}

 85%|████████▍ | 23743/28080 [46:54:35<8:32:50,  7.09s/it]
 85%|████████▍ | 23744/28080 [46:54:43<8:34:28,  7.12s/it]
                                                          
{'loss': 0.6038, 'learning_rate': 3.061952428388712e-05, 'epoch': 10.14}

 85%|████████▍ | 23744/28080 [46:54:43<8:34:28,  7.12s/it]
 85%|████████▍ | 23745/28080 [46:54:50<8:35:03,  7.13s/it]
                                                          
{'loss': 0.5875, 'learning_rate': 3.060569796735654e-05, 'epoch': 10.14}

 85%|████████▍ | 23745/28080 [46:54:50<8:35:03,  7.13s/it]
 85%|████████▍ | 23746/28080 [46:54:57<8:34:54,  7.13s/it]
                                                          
{'loss': 0.6177, 'learning_rate': 3.059187456964077e-05, 'epoch': 10.14}

 85%|████████▍ | 23746/28080 [46:54:57<8:34:54,  7.13s/it]
 85%|████████▍ | 23747/28080 [46:55:04<8:36:05,  7.15s/it]
                                                          
{'loss': 0.6003, 'learning_rate': 3.057805409092379e-05, 'epoch': 10.14}

 85%|████████▍ | 23747/28080 [46:55:04<8:36:05,  7.15s/it]
 85%|████████▍ | 23748/28080 [46:55:11<8:35:50,  7.14s/it]
                                                          
{'loss': 0.6268, 'learning_rate': 3.056423653138937e-05, 'epoch': 10.14}

 85%|████████▍ | 23748/28080 [46:55:11<8:35:50,  7.14s/it]
 85%|████████▍ | 23749/28080 [46:55:18<8:35:42,  7.14s/it]
                                                          
{'loss': 0.612, 'learning_rate': 3.055042189122148e-05, 'epoch': 10.15}

 85%|████████▍ | 23749/28080 [46:55:18<8:35:42,  7.14s/it]
 85%|████████▍ | 23750/28080 [46:55:25<8:34:26,  7.13s/it]
                                                          
{'loss': 0.5894, 'learning_rate': 3.053661017060383e-05, 'epoch': 10.15}

 85%|████████▍ | 23750/28080 [46:55:25<8:34:26,  7.13s/it]
 85%|████████▍ | 23751/28080 [46:55:33<8:33:07,  7.11s/it]
                                                          
{'loss': 0.6091, 'learning_rate': 3.052280136972016e-05, 'epoch': 10.15}

 85%|████████▍ | 23751/28080 [46:55:33<8:33:07,  7.11s/it]
 85%|████████▍ | 23752/28080 [46:55:40<8:34:10,  7.13s/it]
                                                          
{'loss': 0.5902, 'learning_rate': 3.050899548875416e-05, 'epoch': 10.15}

 85%|████████▍ | 23752/28080 [46:55:40<8:34:10,  7.13s/it]
 85%|████████▍ | 23753/28080 [46:55:47<8:33:44,  7.12s/it]
                                                          
{'loss': 0.6203, 'learning_rate': 3.04951925278896e-05, 'epoch': 10.15}

 85%|████████▍ | 23753/28080 [46:55:47<8:33:44,  7.12s/it]
 85%|████████▍ | 23754/28080 [46:55:54<8:32:38,  7.11s/it]
                                                          
{'loss': 0.5972, 'learning_rate': 3.0481392487310022e-05, 'epoch': 10.15}

 85%|████████▍ | 23754/28080 [46:55:54<8:32:38,  7.11s/it]
 85%|████████▍ | 23755/28080 [46:56:01<8:31:02,  7.09s/it]
                                                          
{'loss': 0.609, 'learning_rate': 3.0467595367199065e-05, 'epoch': 10.15}

 85%|████████▍ | 23755/28080 [46:56:01<8:31:02,  7.09s/it]
 85%|████████▍ | 23756/28080 [46:56:08<8:29:09,  7.07s/it]
                                                          
{'loss': 0.5715, 'learning_rate': 3.045380116774024e-05, 'epoch': 10.15}

 85%|████████▍ | 23756/28080 [46:56:08<8:29:09,  7.07s/it]
 85%|████████▍ | 23757/28080 [46:56:15<8:29:27,  7.07s/it]
                                                          
{'loss': 0.6094, 'learning_rate': 3.0440009889117133e-05, 'epoch': 10.15}

 85%|████████▍ | 23757/28080 [46:56:15<8:29:27,  7.07s/it]
 85%|████████▍ | 23758/28080 [46:56:22<8:31:53,  7.11s/it]
                                                          
{'loss': 0.5916, 'learning_rate': 3.0426221531513172e-05, 'epoch': 10.15}

 85%|████████▍ | 23758/28080 [46:56:22<8:31:53,  7.11s/it]
 85%|████████▍ | 23759/28080 [46:56:29<8:33:12,  7.13s/it]
                                                          
{'loss': 0.5966, 'learning_rate': 3.0412436095111824e-05, 'epoch': 10.15}

 85%|████████▍ | 23759/28080 [46:56:29<8:33:12,  7.13s/it]
 85%|████████▍ | 23760/28080 [46:56:37<8:32:43,  7.12s/it]
                                                          
{'loss': 0.6054, 'learning_rate': 3.0398653580096442e-05, 'epoch': 10.15}

 85%|████████▍ | 23760/28080 [46:56:37<8:32:43,  7.12s/it]
 85%|████████▍ | 23761/28080 [46:56:44<8:31:30,  7.11s/it]
                                                          
{'loss': 0.6003, 'learning_rate': 3.0384873986650463e-05, 'epoch': 10.15}

 85%|████████▍ | 23761/28080 [46:56:44<8:31:30,  7.11s/it]
 85%|████████▍ | 23762/28080 [46:56:51<8:34:17,  7.15s/it]
                                                          
{'loss': 0.5869, 'learning_rate': 3.0371097314957156e-05, 'epoch': 10.15}

 85%|████████▍ | 23762/28080 [46:56:51<8:34:17,  7.15s/it]
 85%|████████▍ | 23763/28080 [46:56:58<8:34:07,  7.15s/it]
                                                          
{'loss': 0.5963, 'learning_rate': 3.0357323565199794e-05, 'epoch': 10.15}

 85%|████████▍ | 23763/28080 [46:56:58<8:34:07,  7.15s/it]
 85%|████████▍ | 23764/28080 [46:57:05<8:33:18,  7.14s/it]
                                                          
{'loss': 0.6017, 'learning_rate': 3.034355273756173e-05, 'epoch': 10.15}

 85%|████████▍ | 23764/28080 [46:57:05<8:33:18,  7.14s/it]
 85%|████████▍ | 23765/28080 [46:57:12<8:33:54,  7.15s/it]
                                                          
{'loss': 0.6176, 'learning_rate': 3.032978483222601e-05, 'epoch': 10.15}

 85%|████████▍ | 23765/28080 [46:57:12<8:33:54,  7.15s/it]
 85%|████████▍ | 23766/28080 [46:57:19<8:31:17,  7.11s/it]
                                                          
{'loss': 0.6143, 'learning_rate': 3.031601984937593e-05, 'epoch': 10.15}

 85%|████████▍ | 23766/28080 [46:57:19<8:31:17,  7.11s/it]
 85%|████████▍ | 23767/28080 [46:57:26<8:31:13,  7.11s/it]
                                                          
{'loss': 0.5891, 'learning_rate': 3.0302257789194514e-05, 'epoch': 10.15}

 85%|████████▍ | 23767/28080 [46:57:26<8:31:13,  7.11s/it]
 85%|████████▍ | 23768/28080 [46:57:33<8:30:05,  7.10s/it]
                                                          
{'loss': 0.6051, 'learning_rate': 3.028849865186495e-05, 'epoch': 10.15}

 85%|████████▍ | 23768/28080 [46:57:33<8:30:05,  7.10s/it]
 85%|████████▍ | 23769/28080 [46:57:41<8:33:35,  7.15s/it]
                                                          
{'loss': 0.6054, 'learning_rate': 3.0274742437570253e-05, 'epoch': 10.15}

 85%|████████▍ | 23769/28080 [46:57:41<8:33:35,  7.15s/it]
 85%|████████▍ | 23770/28080 [46:57:48<8:30:38,  7.11s/it]
                                                          
{'loss': 0.5879, 'learning_rate': 3.0260989146493417e-05, 'epoch': 10.15}

 85%|████████▍ | 23770/28080 [46:57:48<8:30:38,  7.11s/it]
 85%|████████▍ | 23771/28080 [46:57:55<8:28:06,  7.08s/it]
                                                          
{'loss': 0.5933, 'learning_rate': 3.024723877881741e-05, 'epoch': 10.15}

 85%|████████▍ | 23771/28080 [46:57:55<8:28:06,  7.08s/it]
 85%|████████▍ | 23772/28080 [46:58:02<8:26:15,  7.05s/it]
                                                          
{'loss': 0.6022, 'learning_rate': 3.023349133472522e-05, 'epoch': 10.16}

 85%|████████▍ | 23772/28080 [46:58:02<8:26:15,  7.05s/it]
 85%|████████▍ | 23773/28080 [46:58:09<8:28:10,  7.08s/it]
                                                          
{'loss': 0.5973, 'learning_rate': 3.0219746814399706e-05, 'epoch': 10.16}

 85%|████████▍ | 23773/28080 [46:58:09<8:28:10,  7.08s/it]
 85%|████████▍ | 23774/28080 [46:58:16<8:27:02,  7.07s/it]
                                                          
{'loss': 0.6037, 'learning_rate': 3.0206005218023718e-05, 'epoch': 10.16}

 85%|████████▍ | 23774/28080 [46:58:16<8:27:02,  7.07s/it]
 85%|████████▍ | 23775/28080 [46:58:23<8:25:58,  7.05s/it]
                                                          
{'loss': 0.5948, 'learning_rate': 3.0192266545780027e-05, 'epoch': 10.16}

 85%|████████▍ | 23775/28080 [46:58:23<8:25:58,  7.05s/it]
 85%|████████▍ | 23776/28080 [46:58:30<8:26:06,  7.06s/it]
                                                          
{'loss': 0.6069, 'learning_rate': 3.0178530797851546e-05, 'epoch': 10.16}

 85%|████████▍ | 23776/28080 [46:58:30<8:26:06,  7.06s/it]
 85%|████████▍ | 23777/28080 [46:58:37<8:28:07,  7.09s/it]
                                                          
{'loss': 0.5884, 'learning_rate': 3.0164797974420842e-05, 'epoch': 10.16}

 85%|████████▍ | 23777/28080 [46:58:37<8:28:07,  7.09s/it]
 85%|████████▍ | 23778/28080 [46:58:44<8:29:04,  7.10s/it]
                                                          
{'loss': 0.595, 'learning_rate': 3.0151068075670863e-05, 'epoch': 10.16}

 85%|████████▍ | 23778/28080 [46:58:44<8:29:04,  7.10s/it]
 85%|████████▍ | 23779/28080 [46:58:51<8:26:56,  7.07s/it]
                                                          
{'loss': 0.6169, 'learning_rate': 3.0137341101783984e-05, 'epoch': 10.16}

 85%|████████▍ | 23779/28080 [46:58:51<8:26:56,  7.07s/it]
 85%|████████▍ | 23780/28080 [46:58:58<8:24:10,  7.03s/it]
                                                          
{'loss': 0.6178, 'learning_rate': 3.0123617052943002e-05, 'epoch': 10.16}

 85%|████████▍ | 23780/28080 [46:58:58<8:24:10,  7.03s/it]
 85%|████████▍ | 23781/28080 [46:59:05<8:23:38,  7.03s/it]
                                                          
{'loss': 0.6014, 'learning_rate': 3.0109895929330446e-05, 'epoch': 10.16}

 85%|████████▍ | 23781/28080 [46:59:05<8:23:38,  7.03s/it]
 85%|████████▍ | 23782/28080 [46:59:12<8:25:00,  7.05s/it]
                                                          
{'loss': 0.59, 'learning_rate': 3.009617773112888e-05, 'epoch': 10.16}

 85%|████████▍ | 23782/28080 [46:59:12<8:25:00,  7.05s/it]
 85%|████████▍ | 23783/28080 [46:59:20<8:27:10,  7.08s/it]
                                                          
{'loss': 0.6271, 'learning_rate': 3.0082462458520837e-05, 'epoch': 10.16}

 85%|████████▍ | 23783/28080 [46:59:20<8:27:10,  7.08s/it]
 85%|████████▍ | 23784/28080 [46:59:27<8:27:09,  7.08s/it]
                                                          
{'loss': 0.5992, 'learning_rate': 3.0068750111688774e-05, 'epoch': 10.16}

 85%|████████▍ | 23784/28080 [46:59:27<8:27:09,  7.08s/it]
 85%|████████▍ | 23785/28080 [46:59:34<8:26:26,  7.07s/it]
                                                          
{'loss': 0.6074, 'learning_rate': 3.0055040690815022e-05, 'epoch': 10.16}

 85%|████████▍ | 23785/28080 [46:59:34<8:26:26,  7.07s/it]
 85%|████████▍ | 23786/28080 [46:59:41<8:28:09,  7.10s/it]
                                                          
{'loss': 0.5847, 'learning_rate': 3.00413341960821e-05, 'epoch': 10.16}

 85%|████████▍ | 23786/28080 [46:59:41<8:28:09,  7.10s/it]
 85%|████████▍ | 23787/28080 [46:59:48<8:29:03,  7.11s/it]
                                                          
{'loss': 0.6211, 'learning_rate': 3.002763062767233e-05, 'epoch': 10.16}

 85%|████████▍ | 23787/28080 [46:59:48<8:29:03,  7.11s/it]
 85%|████████▍ | 23788/28080 [46:59:55<8:28:21,  7.11s/it]
                                                          
{'loss': 0.5982, 'learning_rate': 3.0013929985767962e-05, 'epoch': 10.16}

 85%|████████▍ | 23788/28080 [46:59:55<8:28:21,  7.11s/it]
 85%|████████▍ | 23789/28080 [47:00:02<8:31:58,  7.16s/it]
                                                          
{'loss': 0.5979, 'learning_rate': 3.0000232270551348e-05, 'epoch': 10.16}

 85%|████████▍ | 23789/28080 [47:00:02<8:31:58,  7.16s/it]
 85%|████████▍ | 23790/28080 [47:00:09<8:30:32,  7.14s/it]
                                                          
{'loss': 0.6087, 'learning_rate': 2.9986537482204618e-05, 'epoch': 10.16}

 85%|████████▍ | 23790/28080 [47:00:09<8:30:32,  7.14s/it]
 85%|████████▍ | 23791/28080 [47:00:17<8:30:02,  7.14s/it]
                                                          
{'loss': 0.5918, 'learning_rate': 2.997284562091007e-05, 'epoch': 10.16}

 85%|████████▍ | 23791/28080 [47:00:17<8:30:02,  7.14s/it]
 85%|████████▍ | 23792/28080 [47:00:24<8:29:14,  7.13s/it]
                                                          
{'loss': 0.5935, 'learning_rate': 2.995915668684984e-05, 'epoch': 10.16}

 85%|████████▍ | 23792/28080 [47:00:24<8:29:14,  7.13s/it]
 85%|████████▍ | 23793/28080 [47:00:31<8:29:34,  7.13s/it]
                                                          
{'loss': 0.6034, 'learning_rate': 2.9945470680206005e-05, 'epoch': 10.16}

 85%|████████▍ | 23793/28080 [47:00:31<8:29:34,  7.13s/it]
 85%|████████▍ | 23794/28080 [47:00:38<8:27:14,  7.10s/it]
                                                          
{'loss': 0.6074, 'learning_rate': 2.9931787601160636e-05, 'epoch': 10.16}

 85%|████████▍ | 23794/28080 [47:00:38<8:27:14,  7.10s/it]
 85%|████████▍ | 23795/28080 [47:00:45<8:26:02,  7.09s/it]
                                                          
{'loss': 0.626, 'learning_rate': 2.9918107449895844e-05, 'epoch': 10.17}

 85%|████████▍ | 23795/28080 [47:00:45<8:26:02,  7.09s/it]
 85%|████████▍ | 23796/28080 [47:00:52<8:26:47,  7.10s/it]
                                                          
{'loss': 0.5931, 'learning_rate': 2.990443022659353e-05, 'epoch': 10.17}

 85%|████████▍ | 23796/28080 [47:00:52<8:26:47,  7.10s/it]
 85%|████████▍ | 23797/28080 [47:00:59<8:26:41,  7.10s/it]
                                                          
{'loss': 0.6148, 'learning_rate': 2.9890755931435808e-05, 'epoch': 10.17}

 85%|████████▍ | 23797/28080 [47:00:59<8:26:41,  7.10s/it]
 85%|████████▍ | 23798/28080 [47:01:06<8:26:55,  7.10s/it]
                                                          
{'loss': 0.5859, 'learning_rate': 2.987708456460442e-05, 'epoch': 10.17}

 85%|████████▍ | 23798/28080 [47:01:06<8:26:55,  7.10s/it]
 85%|████████▍ | 23799/28080 [47:01:13<8:27:50,  7.12s/it]
                                                          
{'loss': 0.5828, 'learning_rate': 2.9863416126281377e-05, 'epoch': 10.17}

 85%|████████▍ | 23799/28080 [47:01:13<8:27:50,  7.12s/it]
 85%|████████▍ | 23800/28080 [47:01:20<8:27:38,  7.12s/it]
                                                          
{'loss': 0.6084, 'learning_rate': 2.9849750616648436e-05, 'epoch': 10.17}

 85%|████████▍ | 23800/28080 [47:01:20<8:27:38,  7.12s/it]
 85%|████████▍ | 23801/28080 [47:01:27<8:25:20,  7.09s/it]
                                                          
{'loss': 0.604, 'learning_rate': 2.98360880358875e-05, 'epoch': 10.17}

 85%|████████▍ | 23801/28080 [47:01:27<8:25:20,  7.09s/it]
 85%|████████▍ | 23802/28080 [47:01:35<8:27:04,  7.11s/it]
                                                          
{'loss': 0.5937, 'learning_rate': 2.9822428384180254e-05, 'epoch': 10.17}

 85%|████████▍ | 23802/28080 [47:01:35<8:27:04,  7.11s/it]
 85%|████████▍ | 23803/28080 [47:01:42<8:26:54,  7.11s/it]
                                                          
{'loss': 0.629, 'learning_rate': 2.9808771661708477e-05, 'epoch': 10.17}

 85%|████████▍ | 23803/28080 [47:01:42<8:26:54,  7.11s/it]
 85%|████████▍ | 23804/28080 [47:01:49<8:25:51,  7.10s/it]
                                                          
{'loss': 0.624, 'learning_rate': 2.9795117868653797e-05, 'epoch': 10.17}

 85%|████████▍ | 23804/28080 [47:01:49<8:25:51,  7.10s/it]
 85%|████████▍ | 23805/28080 [47:01:56<8:25:48,  7.10s/it]
                                                          
{'loss': 0.5789, 'learning_rate': 2.9781467005197932e-05, 'epoch': 10.17}

 85%|████████▍ | 23805/28080 [47:01:56<8:25:48,  7.10s/it]
 85%|████████▍ | 23806/28080 [47:02:03<8:24:40,  7.08s/it]
                                                          
{'loss': 0.6193, 'learning_rate': 2.9767819071522458e-05, 'epoch': 10.17}

 85%|████████▍ | 23806/28080 [47:02:03<8:24:40,  7.08s/it]
 85%|████████▍ | 23807/28080 [47:02:10<8:22:54,  7.06s/it]
                                                          
{'loss': 0.5786, 'learning_rate': 2.9754174067808948e-05, 'epoch': 10.17}

 85%|████████▍ | 23807/28080 [47:02:10<8:22:54,  7.06s/it]
 85%|████████▍ | 23808/28080 [47:02:17<8:24:04,  7.08s/it]
                                                          
{'loss': 0.6035, 'learning_rate': 2.97405319942389e-05, 'epoch': 10.17}

 85%|████████▍ | 23808/28080 [47:02:17<8:24:04,  7.08s/it]
 85%|████████▍ | 23809/28080 [47:02:24<8:24:49,  7.09s/it]
                                                          
{'loss': 0.6029, 'learning_rate': 2.9726892850993893e-05, 'epoch': 10.17}

 85%|████████▍ | 23809/28080 [47:02:24<8:24:49,  7.09s/it]
 85%|████████▍ | 23810/28080 [47:02:31<8:23:56,  7.08s/it]
                                                          
{'loss': 0.5988, 'learning_rate': 2.9713256638255276e-05, 'epoch': 10.17}

 85%|████████▍ | 23810/28080 [47:02:31<8:23:56,  7.08s/it]
 85%|████████▍ | 23811/28080 [47:02:38<8:24:57,  7.10s/it]
                                                          
{'loss': 0.5882, 'learning_rate': 2.9699623356204574e-05, 'epoch': 10.17}

 85%|████████▍ | 23811/28080 [47:02:38<8:24:57,  7.10s/it]
 85%|████████▍ | 23812/28080 [47:02:46<8:25:21,  7.10s/it]
                                                          
{'loss': 0.5884, 'learning_rate': 2.968599300502317e-05, 'epoch': 10.17}

 85%|████████▍ | 23812/28080 [47:02:46<8:25:21,  7.10s/it]
 85%|████████▍ | 23813/28080 [47:02:53<8:25:06,  7.10s/it]
                                                          
{'loss': 0.5915, 'learning_rate': 2.9672365584892254e-05, 'epoch': 10.17}

 85%|████████▍ | 23813/28080 [47:02:53<8:25:06,  7.10s/it]
 85%|████████▍ | 23814/28080 [47:03:00<8:28:42,  7.15s/it]
                                                          
{'loss': 0.5744, 'learning_rate': 2.965874109599323e-05, 'epoch': 10.17}

 85%|████████▍ | 23814/28080 [47:03:00<8:28:42,  7.15s/it]
 85%|████████▍ | 23815/28080 [47:03:07<8:27:50,  7.14s/it]
                                                          
{'loss': 0.6019, 'learning_rate': 2.964511953850732e-05, 'epoch': 10.17}

 85%|████████▍ | 23815/28080 [47:03:07<8:27:50,  7.14s/it]
 85%|████████▍ | 23816/28080 [47:03:14<8:26:19,  7.12s/it]
                                                          
{'loss': 0.6048, 'learning_rate': 2.963150091261582e-05, 'epoch': 10.17}

 85%|████████▍ | 23816/28080 [47:03:14<8:26:19,  7.12s/it]
 85%|████████▍ | 23817/28080 [47:03:21<8:26:53,  7.13s/it]
                                                          
{'loss': 0.6245, 'learning_rate': 2.9617885218499842e-05, 'epoch': 10.17}

 85%|████████▍ | 23817/28080 [47:03:21<8:26:53,  7.13s/it]
 85%|████████▍ | 23818/28080 [47:03:28<8:26:08,  7.13s/it]
                                                          
{'loss': 0.5803, 'learning_rate': 2.9604272456340536e-05, 'epoch': 10.17}

 85%|████████▍ | 23818/28080 [47:03:28<8:26:08,  7.13s/it]
 85%|████████▍ | 23819/28080 [47:03:36<8:26:58,  7.14s/it]
                                                          
{'loss': 0.5877, 'learning_rate': 2.9590662626318988e-05, 'epoch': 10.18}

 85%|████████▍ | 23819/28080 [47:03:36<8:26:58,  7.14s/it]
 85%|████████▍ | 23820/28080 [47:03:43<8:26:54,  7.14s/it]
                                                          
{'loss': 0.6139, 'learning_rate': 2.9577055728616327e-05, 'epoch': 10.18}

 85%|████████▍ | 23820/28080 [47:03:43<8:26:54,  7.14s/it]
 85%|████████▍ | 23821/28080 [47:03:50<8:25:09,  7.12s/it]
                                                          
{'loss': 0.6008, 'learning_rate': 2.9563451763413545e-05, 'epoch': 10.18}

 85%|████████▍ | 23821/28080 [47:03:50<8:25:09,  7.12s/it]
 85%|████████▍ | 23822/28080 [47:03:57<8:27:13,  7.15s/it]
                                                          
{'loss': 0.6117, 'learning_rate': 2.954985073089164e-05, 'epoch': 10.18}

 85%|████████▍ | 23822/28080 [47:03:57<8:27:13,  7.15s/it]
 85%|████████▍ | 23823/28080 [47:04:04<8:24:03,  7.10s/it]
                                                          
{'loss': 0.6118, 'learning_rate': 2.953625263123147e-05, 'epoch': 10.18}

 85%|████████▍ | 23823/28080 [47:04:04<8:24:03,  7.10s/it]
 85%|████████▍ | 23824/28080 [47:04:11<8:22:15,  7.08s/it]
                                                          
{'loss': 0.6061, 'learning_rate': 2.9522657464614106e-05, 'epoch': 10.18}

 85%|████████▍ | 23824/28080 [47:04:11<8:22:15,  7.08s/it]
 85%|████████▍ | 23825/28080 [47:04:18<8:23:40,  7.10s/it]
                                                          
{'loss': 0.6, 'learning_rate': 2.9509065231220238e-05, 'epoch': 10.18}

 85%|████████▍ | 23825/28080 [47:04:18<8:23:40,  7.10s/it]
 85%|████████▍ | 23826/28080 [47:04:25<8:22:15,  7.08s/it]
                                                          
{'loss': 0.6078, 'learning_rate': 2.949547593123092e-05, 'epoch': 10.18}

 85%|████████▍ | 23826/28080 [47:04:25<8:22:15,  7.08s/it]
 85%|████████▍ | 23827/28080 [47:04:32<8:23:41,  7.11s/it]
                                                          
{'loss': 0.6077, 'learning_rate': 2.94818895648267e-05, 'epoch': 10.18}

 85%|████████▍ | 23827/28080 [47:04:32<8:23:41,  7.11s/it]
 85%|████████▍ | 23828/28080 [47:04:39<8:23:39,  7.11s/it]
                                                          
{'loss': 0.6068, 'learning_rate': 2.9468306132188484e-05, 'epoch': 10.18}

 85%|████████▍ | 23828/28080 [47:04:39<8:23:39,  7.11s/it]
 85%|████████▍ | 23829/28080 [47:04:47<8:22:21,  7.09s/it]
                                                          
{'loss': 0.5781, 'learning_rate': 2.945472563349691e-05, 'epoch': 10.18}

 85%|████████▍ | 23829/28080 [47:04:47<8:22:21,  7.09s/it]
 85%|████████▍ | 23830/28080 [47:04:54<8:22:23,  7.09s/it]
                                                          
{'loss': 0.6014, 'learning_rate': 2.944114806893272e-05, 'epoch': 10.18}

 85%|████████▍ | 23830/28080 [47:04:54<8:22:23,  7.09s/it]
 85%|████████▍ | 23831/28080 [47:05:01<8:22:25,  7.09s/it]
                                                          
{'loss': 0.5912, 'learning_rate': 2.9427573438676553e-05, 'epoch': 10.18}

 85%|████████▍ | 23831/28080 [47:05:01<8:22:25,  7.09s/it]
 85%|████████▍ | 23832/28080 [47:05:08<8:21:58,  7.09s/it]
                                                          
{'loss': 0.568, 'learning_rate': 2.941400174290895e-05, 'epoch': 10.18}

 85%|████████▍ | 23832/28080 [47:05:08<8:21:58,  7.09s/it]
 85%|████████▍ | 23833/28080 [47:05:15<8:21:31,  7.09s/it]
                                                          
{'loss': 0.6304, 'learning_rate': 2.9400432981810416e-05, 'epoch': 10.18}

 85%|████████▍ | 23833/28080 [47:05:15<8:21:31,  7.09s/it]
 85%|████████▍ | 23834/28080 [47:05:22<8:19:43,  7.06s/it]
                                                          
{'loss': 0.6102, 'learning_rate': 2.9386867155561603e-05, 'epoch': 10.18}

 85%|████████▍ | 23834/28080 [47:05:22<8:19:43,  7.06s/it]
 85%|████████▍ | 23835/28080 [47:05:29<8:20:43,  7.08s/it]
                                                          
{'loss': 0.5947, 'learning_rate': 2.9373304264342953e-05, 'epoch': 10.18}

 85%|████████▍ | 23835/28080 [47:05:29<8:20:43,  7.08s/it]
 85%|████████▍ | 23836/28080 [47:05:36<8:18:51,  7.05s/it]
                                                          
{'loss': 0.6062, 'learning_rate': 2.9359744308334853e-05, 'epoch': 10.18}

 85%|████████▍ | 23836/28080 [47:05:36<8:18:51,  7.05s/it]
 85%|████████▍ | 23837/28080 [47:05:43<8:21:20,  7.09s/it]
                                                          
{'loss': 0.598, 'learning_rate': 2.9346187287717764e-05, 'epoch': 10.18}

 85%|████████▍ | 23837/28080 [47:05:43<8:21:20,  7.09s/it]
 85%|████████▍ | 23838/28080 [47:05:50<8:20:49,  7.08s/it]
                                                          
{'loss': 0.5646, 'learning_rate': 2.9332633202671933e-05, 'epoch': 10.18}

 85%|████████▍ | 23838/28080 [47:05:50<8:20:49,  7.08s/it]
 85%|████████▍ | 23839/28080 [47:05:57<8:19:26,  7.07s/it]
                                                          
{'loss': 0.5992, 'learning_rate': 2.9319082053377827e-05, 'epoch': 10.18}

 85%|████████▍ | 23839/28080 [47:05:57<8:19:26,  7.07s/it]
 85%|████████▍ | 23840/28080 [47:06:04<8:22:58,  7.12s/it]
                                                          
{'loss': 0.5828, 'learning_rate': 2.9305533840015692e-05, 'epoch': 10.18}

 85%|████████▍ | 23840/28080 [47:06:05<8:22:58,  7.12s/it]
 85%|████████▍ | 23841/28080 [47:06:12<8:23:08,  7.12s/it]
                                                          
{'loss': 0.6122, 'learning_rate': 2.9291988562765716e-05, 'epoch': 10.18}

 85%|████████▍ | 23841/28080 [47:06:12<8:23:08,  7.12s/it]
 85%|████████▍ | 23842/28080 [47:06:19<8:22:13,  7.11s/it]
                                                          
{'loss': 0.597, 'learning_rate': 2.9278446221808113e-05, 'epoch': 10.19}

 85%|████████▍ | 23842/28080 [47:06:19<8:22:13,  7.11s/it]
 85%|████████▍ | 23843/28080 [47:06:26<8:22:23,  7.11s/it]
                                                          
{'loss': 0.6069, 'learning_rate': 2.9264906817323132e-05, 'epoch': 10.19}

 85%|████████▍ | 23843/28080 [47:06:26<8:22:23,  7.11s/it]
 85%|████████▍ | 23844/28080 [47:06:33<8:22:51,  7.12s/it]
                                                          
{'loss': 0.582, 'learning_rate': 2.9251370349490768e-05, 'epoch': 10.19}

 85%|████████▍ | 23844/28080 [47:06:33<8:22:51,  7.12s/it]
 85%|████████▍ | 23845/28080 [47:06:40<8:21:16,  7.10s/it]
                                                          
{'loss': 0.5885, 'learning_rate': 2.923783681849132e-05, 'epoch': 10.19}

 85%|████████▍ | 23845/28080 [47:06:40<8:21:16,  7.10s/it]
 85%|████████▍ | 23846/28080 [47:06:47<8:21:10,  7.10s/it]
                                                          
{'loss': 0.6017, 'learning_rate': 2.922430622450459e-05, 'epoch': 10.19}

 85%|████████▍ | 23846/28080 [47:06:47<8:21:10,  7.10s/it]
 85%|████████▍ | 23847/28080 [47:06:54<8:21:32,  7.11s/it]
                                                          
{'loss': 0.5965, 'learning_rate': 2.921077856771076e-05, 'epoch': 10.19}

 85%|████████▍ | 23847/28080 [47:06:54<8:21:32,  7.11s/it]
 85%|████████▍ | 23848/28080 [47:07:01<8:21:52,  7.12s/it]
                                                          
{'loss': 0.6156, 'learning_rate': 2.9197253848289694e-05, 'epoch': 10.19}

 85%|████████▍ | 23848/28080 [47:07:01<8:21:52,  7.12s/it]
 85%|████████▍ | 23849/28080 [47:07:08<8:20:42,  7.10s/it]
                                                          
{'loss': 0.6154, 'learning_rate': 2.9183732066421414e-05, 'epoch': 10.19}

 85%|████████▍ | 23849/28080 [47:07:08<8:20:42,  7.10s/it]
 85%|████████▍ | 23850/28080 [47:07:16<8:22:26,  7.13s/it]
                                                          
{'loss': 0.602, 'learning_rate': 2.9170213222285802e-05, 'epoch': 10.19}

 85%|████████▍ | 23850/28080 [47:07:16<8:22:26,  7.13s/it]
 85%|████████▍ | 23851/28080 [47:07:23<8:20:30,  7.10s/it]
                                                          
{'loss': 0.5948, 'learning_rate': 2.9156697316062657e-05, 'epoch': 10.19}

 85%|████████▍ | 23851/28080 [47:07:23<8:20:30,  7.10s/it]
 85%|████████▍ | 23852/28080 [47:07:30<8:22:06,  7.13s/it]
                                                          
{'loss': 0.6053, 'learning_rate': 2.9143184347931785e-05, 'epoch': 10.19}

 85%|████████▍ | 23852/28080 [47:07:30<8:22:06,  7.13s/it]
 85%|████████▍ | 23853/28080 [47:07:37<8:21:51,  7.12s/it]
                                                          
{'loss': 0.5943, 'learning_rate': 2.9129674318073064e-05, 'epoch': 10.19}

 85%|████████▍ | 23853/28080 [47:07:37<8:21:51,  7.12s/it]
 85%|████████▍ | 23854/28080 [47:07:44<8:22:25,  7.13s/it]
                                                          
{'loss': 0.6033, 'learning_rate': 2.911616722666613e-05, 'epoch': 10.19}

 85%|████████▍ | 23854/28080 [47:07:44<8:22:25,  7.13s/it]
 85%|████████▍ | 23855/28080 [47:07:51<8:19:16,  7.09s/it]
                                                          
{'loss': 0.6059, 'learning_rate': 2.9102663073890757e-05, 'epoch': 10.19}

 85%|████████▍ | 23855/28080 [47:07:51<8:19:16,  7.09s/it]
 85%|████████▍ | 23856/28080 [47:07:58<8:20:21,  7.11s/it]
                                                          
{'loss': 0.5781, 'learning_rate': 2.9089161859926496e-05, 'epoch': 10.19}

 85%|████████▍ | 23856/28080 [47:07:58<8:20:21,  7.11s/it]
 85%|████████▍ | 23857/28080 [47:08:05<8:19:50,  7.10s/it]
                                                          
{'loss': 0.6011, 'learning_rate': 2.907566358495309e-05, 'epoch': 10.19}

 85%|████████▍ | 23857/28080 [47:08:05<8:19:50,  7.10s/it]
 85%|████████▍ | 23858/28080 [47:08:13<8:20:21,  7.11s/it]
                                                          
{'loss': 0.6192, 'learning_rate': 2.9062168249150005e-05, 'epoch': 10.19}

 85%|████████▍ | 23858/28080 [47:08:13<8:20:21,  7.11s/it]
 85%|████████▍ | 23859/28080 [47:08:20<8:19:30,  7.10s/it]
                                                          
{'loss': 0.5884, 'learning_rate': 2.9048675852696965e-05, 'epoch': 10.19}

 85%|████████▍ | 23859/28080 [47:08:20<8:19:30,  7.10s/it]
 85%|████████▍ | 23860/28080 [47:08:27<8:19:41,  7.10s/it]
                                                          
{'loss': 0.6122, 'learning_rate': 2.903518639577321e-05, 'epoch': 10.19}

 85%|████████▍ | 23860/28080 [47:08:27<8:19:41,  7.10s/it]
 85%|████████▍ | 23861/28080 [47:08:34<8:20:11,  7.11s/it]
                                                          
{'loss': 0.5933, 'learning_rate': 2.9021699878558434e-05, 'epoch': 10.19}

 85%|████████▍ | 23861/28080 [47:08:34<8:20:11,  7.11s/it]
 85%|████████▍ | 23862/28080 [47:08:41<8:21:21,  7.13s/it]
                                                          
{'loss': 0.5832, 'learning_rate': 2.900821630123196e-05, 'epoch': 10.19}

 85%|████████▍ | 23862/28080 [47:08:41<8:21:21,  7.13s/it]
 85%|████████▍ | 23863/28080 [47:08:48<8:23:26,  7.16s/it]
                                                          
{'loss': 0.6282, 'learning_rate': 2.899473566397312e-05, 'epoch': 10.19}

 85%|████████▍ | 23863/28080 [47:08:48<8:23:26,  7.16s/it]
 85%|████████▍ | 23864/28080 [47:08:55<8:24:06,  7.17s/it]
                                                          
{'loss': 0.5977, 'learning_rate': 2.8981257966961383e-05, 'epoch': 10.19}

 85%|████████▍ | 23864/28080 [47:08:55<8:24:06,  7.17s/it]
 85%|████████▍ | 23865/28080 [47:09:03<8:23:07,  7.16s/it]
                                                          
{'loss': 0.5855, 'learning_rate': 2.8967783210375992e-05, 'epoch': 10.19}

 85%|████████▍ | 23865/28080 [47:09:03<8:23:07,  7.16s/it]
 85%|████████▍ | 23866/28080 [47:09:10<8:21:03,  7.13s/it]
                                                          
{'loss': 0.6319, 'learning_rate': 2.895431139439622e-05, 'epoch': 10.2}

 85%|████████▍ | 23866/28080 [47:09:10<8:21:03,  7.13s/it]
 85%|████████▍ | 23867/28080 [47:09:17<8:19:36,  7.12s/it]
                                                          
{'loss': 0.611, 'learning_rate': 2.894084251920126e-05, 'epoch': 10.2}

 85%|████████▍ | 23867/28080 [47:09:17<8:19:36,  7.12s/it]
 85%|████████▌ | 23868/28080 [47:09:24<8:17:44,  7.09s/it]
                                                          
{'loss': 0.6158, 'learning_rate': 2.8927376584970384e-05, 'epoch': 10.2}

 85%|████████▌ | 23868/28080 [47:09:24<8:17:44,  7.09s/it]
 85%|████████▌ | 23869/28080 [47:09:31<8:15:42,  7.06s/it]
                                                          
{'loss': 0.6178, 'learning_rate': 2.891391359188267e-05, 'epoch': 10.2}

 85%|████████▌ | 23869/28080 [47:09:31<8:15:42,  7.06s/it]
 85%|████████▌ | 23870/28080 [47:09:38<8:12:22,  7.02s/it]
                                                          
{'loss': 0.6174, 'learning_rate': 2.8900453540117278e-05, 'epoch': 10.2}

 85%|████████▌ | 23870/28080 [47:09:38<8:12:22,  7.02s/it]
 85%|████████▌ | 23871/28080 [47:09:45<8:13:29,  7.03s/it]
                                                          
{'loss': 0.602, 'learning_rate': 2.888699642985318e-05, 'epoch': 10.2}

 85%|████████▌ | 23871/28080 [47:09:45<8:13:29,  7.03s/it]
 85%|████████▌ | 23872/28080 [47:09:52<8:14:22,  7.05s/it]
                                                          
{'loss': 0.5971, 'learning_rate': 2.8873542261269565e-05, 'epoch': 10.2}

 85%|████████▌ | 23872/28080 [47:09:52<8:14:22,  7.05s/it]
 85%|████████▌ | 23873/28080 [47:09:59<8:16:35,  7.08s/it]
                                                          
{'loss': 0.587, 'learning_rate': 2.886009103454526e-05, 'epoch': 10.2}

 85%|████████▌ | 23873/28080 [47:09:59<8:16:35,  7.08s/it]
 85%|████████▌ | 23874/28080 [47:10:06<8:17:47,  7.10s/it]
                                                          
{'loss': 0.5749, 'learning_rate': 2.8846642749859458e-05, 'epoch': 10.2}

 85%|████████▌ | 23874/28080 [47:10:06<8:17:47,  7.10s/it]
 85%|████████▌ | 23875/28080 [47:10:13<8:17:30,  7.10s/it]
                                                          
{'loss': 0.6097, 'learning_rate': 2.8833197407390795e-05, 'epoch': 10.2}

 85%|████████▌ | 23875/28080 [47:10:13<8:17:30,  7.10s/it]
 85%|████████▌ | 23876/28080 [47:10:20<8:17:01,  7.09s/it]
                                                          
{'loss': 0.6002, 'learning_rate': 2.8819755007318316e-05, 'epoch': 10.2}

 85%|████████▌ | 23876/28080 [47:10:20<8:17:01,  7.09s/it]
 85%|████████▌ | 23877/28080 [47:10:27<8:17:05,  7.10s/it]
                                                          
{'loss': 0.6106, 'learning_rate': 2.8806315549820772e-05, 'epoch': 10.2}

 85%|████████▌ | 23877/28080 [47:10:27<8:17:05,  7.10s/it]
 85%|████████▌ | 23878/28080 [47:10:34<8:15:22,  7.07s/it]
                                                          
{'loss': 0.6335, 'learning_rate': 2.8792879035077046e-05, 'epoch': 10.2}

 85%|████████▌ | 23878/28080 [47:10:34<8:15:22,  7.07s/it]
 85%|████████▌ | 23879/28080 [47:10:42<8:16:16,  7.09s/it]
                                                          
{'loss': 0.6025, 'learning_rate': 2.8779445463265884e-05, 'epoch': 10.2}

 85%|████████▌ | 23879/28080 [47:10:42<8:16:16,  7.09s/it]
 85%|████████▌ | 23880/28080 [47:10:49<8:17:02,  7.10s/it]
                                                          
{'loss': 0.6019, 'learning_rate': 2.8766014834565978e-05, 'epoch': 10.2}

 85%|████████▌ | 23880/28080 [47:10:49<8:17:02,  7.10s/it]
 85%|████████▌ | 23881/28080 [47:10:56<8:15:54,  7.09s/it]
                                                          
{'loss': 0.6185, 'learning_rate': 2.8752587149155933e-05, 'epoch': 10.2}

 85%|████████▌ | 23881/28080 [47:10:56<8:15:54,  7.09s/it]
 85%|████████▌ | 23882/28080 [47:11:03<8:15:22,  7.08s/it]
                                                          
{'loss': 0.6006, 'learning_rate': 2.8739162407214552e-05, 'epoch': 10.2}

 85%|████████▌ | 23882/28080 [47:11:03<8:15:22,  7.08s/it]
 85%|████████▌ | 23883/28080 [47:11:10<8:16:21,  7.10s/it]
                                                          
{'loss': 0.6098, 'learning_rate': 2.8725740608920332e-05, 'epoch': 10.2}

 85%|████████▌ | 23883/28080 [47:11:10<8:16:21,  7.10s/it]
 85%|████████▌ | 23884/28080 [47:11:17<8:16:14,  7.10s/it]
                                                          
{'loss': 0.5982, 'learning_rate': 2.8712321754451847e-05, 'epoch': 10.2}

 85%|████████▌ | 23884/28080 [47:11:17<8:16:14,  7.10s/it]
 85%|████████▌ | 23885/28080 [47:11:24<8:15:07,  7.08s/it]
                                                          
{'loss': 0.6146, 'learning_rate': 2.86989058439876e-05, 'epoch': 10.2}

 85%|████████▌ | 23885/28080 [47:11:24<8:15:07,  7.08s/it]
 85%|████████▌ | 23886/28080 [47:11:31<8:13:58,  7.07s/it]
                                                          
{'loss': 0.579, 'learning_rate': 2.8685492877706165e-05, 'epoch': 10.2}

 85%|████████▌ | 23886/28080 [47:11:31<8:13:58,  7.07s/it]
 85%|████████▌ | 23887/28080 [47:11:38<8:13:54,  7.07s/it]
                                                          
{'loss': 0.5998, 'learning_rate': 2.86720828557859e-05, 'epoch': 10.2}

 85%|████████▌ | 23887/28080 [47:11:38<8:13:54,  7.07s/it]
 85%|████████▌ | 23888/28080 [47:11:45<8:15:50,  7.10s/it]
                                                          
{'loss': 0.5779, 'learning_rate': 2.865867577840528e-05, 'epoch': 10.2}

 85%|████████▌ | 23888/28080 [47:11:45<8:15:50,  7.10s/it]
 85%|████████▌ | 23889/28080 [47:11:52<8:16:00,  7.10s/it]
                                                          
{'loss': 0.5944, 'learning_rate': 2.86452716457426e-05, 'epoch': 10.21}

 85%|████████▌ | 23889/28080 [47:11:52<8:16:00,  7.10s/it]
 85%|████████▌ | 23890/28080 [47:12:00<8:16:31,  7.11s/it]
                                                          
{'loss': 0.6072, 'learning_rate': 2.863187045797619e-05, 'epoch': 10.21}

 85%|████████▌ | 23890/28080 [47:12:00<8:16:31,  7.11s/it]
 85%|████████▌ | 23891/28080 [47:12:07<8:16:09,  7.11s/it]
                                                          
{'loss': 0.5997, 'learning_rate': 2.861847221528441e-05, 'epoch': 10.21}

 85%|████████▌ | 23891/28080 [47:12:07<8:16:09,  7.11s/it]
 85%|████████▌ | 23892/28080 [47:12:14<8:15:48,  7.10s/it]
                                                          
{'loss': 0.624, 'learning_rate': 2.860507691784542e-05, 'epoch': 10.21}

 85%|████████▌ | 23892/28080 [47:12:14<8:15:48,  7.10s/it]
 85%|████████▌ | 23893/28080 [47:12:21<8:15:13,  7.10s/it]
                                                          
{'loss': 0.6024, 'learning_rate': 2.8591684565837605e-05, 'epoch': 10.21}

 85%|████████▌ | 23893/28080 [47:12:21<8:15:13,  7.10s/it]
 85%|████████▌ | 23894/28080 [47:12:28<8:15:47,  7.11s/it]
                                                          
{'loss': 0.5892, 'learning_rate': 2.8578295159438882e-05, 'epoch': 10.21}

 85%|████████▌ | 23894/28080 [47:12:28<8:15:47,  7.11s/it]
 85%|████████▌ | 23895/28080 [47:12:35<8:16:01,  7.11s/it]
                                                          
{'loss': 0.5815, 'learning_rate': 2.856490869882758e-05, 'epoch': 10.21}

 85%|████████▌ | 23895/28080 [47:12:35<8:16:01,  7.11s/it]
 85%|████████▌ | 23896/28080 [47:12:42<8:15:15,  7.10s/it]
                                                          
{'loss': 0.6039, 'learning_rate': 2.8551525184181664e-05, 'epoch': 10.21}

 85%|████████▌ | 23896/28080 [47:12:42<8:15:15,  7.10s/it]
 85%|████████▌ | 23897/28080 [47:12:49<8:14:18,  7.09s/it]
                                                          
{'loss': 0.603, 'learning_rate': 2.8538144615679302e-05, 'epoch': 10.21}

 85%|████████▌ | 23897/28080 [47:12:49<8:14:18,  7.09s/it]
 85%|████████▌ | 23898/28080 [47:12:56<8:14:50,  7.10s/it]
                                                          
{'loss': 0.6001, 'learning_rate': 2.8524766993498485e-05, 'epoch': 10.21}

 85%|████████▌ | 23898/28080 [47:12:56<8:14:50,  7.10s/it]
 85%|████████▌ | 23899/28080 [47:13:04<8:16:04,  7.12s/it]
                                                          
{'loss': 0.5839, 'learning_rate': 2.851139231781713e-05, 'epoch': 10.21}

 85%|████████▌ | 23899/28080 [47:13:04<8:16:04,  7.12s/it]
 85%|████████▌ | 23900/28080 [47:13:11<8:14:20,  7.10s/it]
                                                          
{'loss': 0.5816, 'learning_rate': 2.849802058881315e-05, 'epoch': 10.21}

 85%|████████▌ | 23900/28080 [47:13:11<8:14:20,  7.10s/it]
 85%|████████▌ | 23901/28080 [47:13:18<8:15:37,  7.12s/it]
                                                          
{'loss': 0.602, 'learning_rate': 2.8484651806664568e-05, 'epoch': 10.21}

 85%|████████▌ | 23901/28080 [47:13:18<8:15:37,  7.12s/it]
 85%|████████▌ | 23902/28080 [47:13:25<8:16:48,  7.13s/it]
                                                          
{'loss': 0.5979, 'learning_rate': 2.847128597154916e-05, 'epoch': 10.21}

 85%|████████▌ | 23902/28080 [47:13:25<8:16:48,  7.13s/it]
 85%|████████▌ | 23903/28080 [47:13:32<8:15:42,  7.12s/it]
                                                          
{'loss': 0.6164, 'learning_rate': 2.8457923083644727e-05, 'epoch': 10.21}

 85%|████████▌ | 23903/28080 [47:13:32<8:15:42,  7.12s/it]
 85%|████████▌ | 23904/28080 [47:13:39<8:13:04,  7.08s/it]
                                                          
{'loss': 0.5942, 'learning_rate': 2.844456314312907e-05, 'epoch': 10.21}

 85%|████████▌ | 23904/28080 [47:13:39<8:13:04,  7.08s/it]
 85%|████████▌ | 23905/28080 [47:13:46<8:13:13,  7.09s/it]
                                                          
{'loss': 0.5974, 'learning_rate': 2.843120615017994e-05, 'epoch': 10.21}

 85%|████████▌ | 23905/28080 [47:13:46<8:13:13,  7.09s/it]
 85%|████████▌ | 23906/28080 [47:13:53<8:10:08,  7.05s/it]
                                                          
{'loss': 0.5959, 'learning_rate': 2.8417852104975022e-05, 'epoch': 10.21}

 85%|████████▌ | 23906/28080 [47:13:53<8:10:08,  7.05s/it]
 85%|████████▌ | 23907/28080 [47:14:00<8:12:34,  7.08s/it]
                                                          
{'loss': 0.6039, 'learning_rate': 2.8404501007692067e-05, 'epoch': 10.21}

 85%|████████▌ | 23907/28080 [47:14:00<8:12:34,  7.08s/it]
 85%|████████▌ | 23908/28080 [47:14:07<8:12:54,  7.09s/it]
                                                          
{'loss': 0.5971, 'learning_rate': 2.8391152858508518e-05, 'epoch': 10.21}

 85%|████████▌ | 23908/28080 [47:14:07<8:12:54,  7.09s/it]
 85%|████████▌ | 23909/28080 [47:14:14<8:13:56,  7.11s/it]
                                                          
{'loss': 0.6135, 'learning_rate': 2.8377807657602116e-05, 'epoch': 10.21}

 85%|████████▌ | 23909/28080 [47:14:14<8:13:56,  7.11s/it]
 85%|████████▌ | 23910/28080 [47:14:22<8:14:45,  7.12s/it]
                                                          
{'loss': 0.6029, 'learning_rate': 2.836446540515031e-05, 'epoch': 10.21}

 85%|████████▌ | 23910/28080 [47:14:22<8:14:45,  7.12s/it]
 85%|████████▌ | 23911/28080 [47:14:29<8:15:01,  7.12s/it]
                                                          
{'loss': 0.5954, 'learning_rate': 2.835112610133067e-05, 'epoch': 10.21}

 85%|████████▌ | 23911/28080 [47:14:29<8:15:01,  7.12s/it]
 85%|████████▌ | 23912/28080 [47:14:36<8:15:34,  7.13s/it]
                                                          
{'loss': 0.6123, 'learning_rate': 2.8337789746320647e-05, 'epoch': 10.21}

 85%|████████▌ | 23912/28080 [47:14:36<8:15:34,  7.13s/it]
 85%|████████▌ | 23913/28080 [47:14:43<8:14:16,  7.12s/it]
                                                          
{'loss': 0.6175, 'learning_rate': 2.832445634029765e-05, 'epoch': 10.22}

 85%|████████▌ | 23913/28080 [47:14:43<8:14:16,  7.12s/it]
 85%|████████▌ | 23914/28080 [47:14:50<8:12:10,  7.09s/it]
                                                          
{'loss': 0.5847, 'learning_rate': 2.8311125883439066e-05, 'epoch': 10.22}

 85%|████████▌ | 23914/28080 [47:14:50<8:12:10,  7.09s/it]
 85%|████████▌ | 23915/28080 [47:14:57<8:11:10,  7.08s/it]
                                                          
{'loss': 0.6132, 'learning_rate': 2.8297798375922197e-05, 'epoch': 10.22}

 85%|████████▌ | 23915/28080 [47:14:57<8:11:10,  7.08s/it]
 85%|████████▌ | 23916/28080 [47:15:04<8:11:28,  7.08s/it]
                                                          
{'loss': 0.6122, 'learning_rate': 2.8284473817924483e-05, 'epoch': 10.22}

 85%|████████▌ | 23916/28080 [47:15:04<8:11:28,  7.08s/it]
 85%|████████▌ | 23917/28080 [47:15:11<8:10:05,  7.06s/it]
                                                          
{'loss': 0.6133, 'learning_rate': 2.827115220962309e-05, 'epoch': 10.22}

 85%|████████▌ | 23917/28080 [47:15:11<8:10:05,  7.06s/it]
 85%|████████▌ | 23918/28080 [47:15:18<8:10:58,  7.08s/it]
                                                          
{'loss': 0.5923, 'learning_rate': 2.825783355119527e-05, 'epoch': 10.22}

 85%|████████▌ | 23918/28080 [47:15:18<8:10:58,  7.08s/it]
 85%|████████▌ | 23919/28080 [47:15:25<8:13:24,  7.11s/it]
                                                          
{'loss': 0.5975, 'learning_rate': 2.8244517842818173e-05, 'epoch': 10.22}

 85%|████████▌ | 23919/28080 [47:15:25<8:13:24,  7.11s/it]
 85%|████████▌ | 23920/28080 [47:15:33<8:13:29,  7.12s/it]
                                                          
{'loss': 0.5911, 'learning_rate': 2.8231205084669033e-05, 'epoch': 10.22}

 85%|████████▌ | 23920/28080 [47:15:33<8:13:29,  7.12s/it]
 85%|████████▌ | 23921/28080 [47:15:40<8:12:38,  7.11s/it]
                                                          
{'loss': 0.6027, 'learning_rate': 2.821789527692495e-05, 'epoch': 10.22}

 85%|████████▌ | 23921/28080 [47:15:40<8:12:38,  7.11s/it]
 85%|████████▌ | 23922/28080 [47:15:47<8:11:13,  7.09s/it]
                                                          
{'loss': 0.5896, 'learning_rate': 2.820458841976295e-05, 'epoch': 10.22}

 85%|████████▌ | 23922/28080 [47:15:47<8:11:13,  7.09s/it]
 85%|████████▌ | 23923/28080 [47:15:54<8:12:34,  7.11s/it]
                                                          
{'loss': 0.6149, 'learning_rate': 2.8191284513360034e-05, 'epoch': 10.22}

 85%|████████▌ | 23923/28080 [47:15:54<8:12:34,  7.11s/it]
 85%|████████▌ | 23924/28080 [47:16:01<8:13:28,  7.12s/it]
                                                          
{'loss': 0.5975, 'learning_rate': 2.8177983557893304e-05, 'epoch': 10.22}

 85%|████████▌ | 23924/28080 [47:16:01<8:13:28,  7.12s/it]
 85%|████████▌ | 23925/28080 [47:16:08<8:10:32,  7.08s/it]
                                                          
{'loss': 0.6373, 'learning_rate': 2.81646855535396e-05, 'epoch': 10.22}

 85%|████████▌ | 23925/28080 [47:16:08<8:10:32,  7.08s/it]
 85%|████████▌ | 23926/28080 [47:16:15<8:09:40,  7.07s/it]
                                                          
{'loss': 0.6125, 'learning_rate': 2.8151390500475965e-05, 'epoch': 10.22}

 85%|████████▌ | 23926/28080 [47:16:15<8:09:40,  7.07s/it]
 85%|████████▌ | 23927/28080 [47:16:22<8:11:10,  7.10s/it]
                                                          
{'loss': 0.613, 'learning_rate': 2.8138098398879208e-05, 'epoch': 10.22}

 85%|████████▌ | 23927/28080 [47:16:22<8:11:10,  7.10s/it]
 85%|████████▌ | 23928/28080 [47:16:29<8:09:09,  7.07s/it]
                                                          
{'loss': 0.621, 'learning_rate': 2.8124809248926185e-05, 'epoch': 10.22}

 85%|████████▌ | 23928/28080 [47:16:29<8:09:09,  7.07s/it]
 85%|████████▌ | 23929/28080 [47:16:36<8:10:58,  7.10s/it]
                                                          
{'loss': 0.6091, 'learning_rate': 2.8111523050793618e-05, 'epoch': 10.22}

 85%|████████▌ | 23929/28080 [47:16:36<8:10:58,  7.10s/it]
 85%|████████▌ | 23930/28080 [47:16:44<8:11:06,  7.10s/it]
                                                          
{'loss': 0.6047, 'learning_rate': 2.8098239804658364e-05, 'epoch': 10.22}

 85%|████████▌ | 23930/28080 [47:16:44<8:11:06,  7.10s/it]
 85%|████████▌ | 23931/28080 [47:16:51<8:12:07,  7.12s/it]
                                                          
{'loss': 0.6094, 'learning_rate': 2.8084959510697117e-05, 'epoch': 10.22}

 85%|████████▌ | 23931/28080 [47:16:51<8:12:07,  7.12s/it]
 85%|████████▌ | 23932/28080 [47:16:58<8:08:15,  7.06s/it]
                                                          
{'loss': 0.594, 'learning_rate': 2.8071682169086538e-05, 'epoch': 10.22}

 85%|████████▌ | 23932/28080 [47:16:58<8:08:15,  7.06s/it]
 85%|████████▌ | 23933/28080 [47:17:05<8:09:57,  7.09s/it]
                                                          
{'loss': 0.6049, 'learning_rate': 2.8058407780003237e-05, 'epoch': 10.22}

 85%|████████▌ | 23933/28080 [47:17:05<8:09:57,  7.09s/it]
 85%|████████▌ | 23934/28080 [47:17:12<8:09:41,  7.09s/it]
                                                          
{'loss': 0.5951, 'learning_rate': 2.8045136343623905e-05, 'epoch': 10.22}

 85%|████████▌ | 23934/28080 [47:17:12<8:09:41,  7.09s/it]
 85%|████████▌ | 23935/28080 [47:17:19<8:09:31,  7.09s/it]
                                                          
{'loss': 0.6096, 'learning_rate': 2.8031867860125015e-05, 'epoch': 10.22}

 85%|████████▌ | 23935/28080 [47:17:19<8:09:31,  7.09s/it]
 85%|████████▌ | 23936/28080 [47:17:26<8:10:04,  7.10s/it]
                                                          
{'loss': 0.6043, 'learning_rate': 2.801860232968323e-05, 'epoch': 10.23}

 85%|████████▌ | 23936/28080 [47:17:26<8:10:04,  7.10s/it]
 85%|████████▌ | 23937/28080 [47:17:33<8:10:59,  7.11s/it]
                                                          
{'loss': 0.6188, 'learning_rate': 2.8005339752474852e-05, 'epoch': 10.23}

 85%|████████▌ | 23937/28080 [47:17:33<8:10:59,  7.11s/it]
 85%|████████▌ | 23938/28080 [47:17:40<8:10:40,  7.11s/it]
                                                          
{'loss': 0.6188, 'learning_rate': 2.7992080128676405e-05, 'epoch': 10.23}

 85%|████████▌ | 23938/28080 [47:17:40<8:10:40,  7.11s/it]
 85%|████████▌ | 23939/28080 [47:17:47<8:09:50,  7.10s/it]
                                                          
{'loss': 0.5998, 'learning_rate': 2.7978823458464308e-05, 'epoch': 10.23}

 85%|████████▌ | 23939/28080 [47:17:47<8:09:50,  7.10s/it]
 85%|████████▌ | 23940/28080 [47:17:54<8:09:29,  7.09s/it]
                                                          
{'loss': 0.6046, 'learning_rate': 2.796556974201489e-05, 'epoch': 10.23}

 85%|████████▌ | 23940/28080 [47:17:54<8:09:29,  7.09s/it]
 85%|████████▌ | 23941/28080 [47:18:02<8:08:52,  7.09s/it]
                                                          
{'loss': 0.6079, 'learning_rate': 2.795231897950462e-05, 'epoch': 10.23}

 85%|████████▌ | 23941/28080 [47:18:02<8:08:52,  7.09s/it]
 85%|████████▌ | 23942/28080 [47:18:09<8:09:34,  7.10s/it]
                                                          
{'loss': 0.583, 'learning_rate': 2.7939071171109555e-05, 'epoch': 10.23}

 85%|████████▌ | 23942/28080 [47:18:09<8:09:34,  7.10s/it]
 85%|████████▌ | 23943/28080 [47:18:16<8:09:29,  7.10s/it]
                                                          
{'loss': 0.6077, 'learning_rate': 2.7925826317006103e-05, 'epoch': 10.23}

 85%|████████▌ | 23943/28080 [47:18:16<8:09:29,  7.10s/it]
 85%|████████▌ | 23944/28080 [47:18:23<8:09:22,  7.10s/it]
                                                          
{'loss': 0.6005, 'learning_rate': 2.7912584417370407e-05, 'epoch': 10.23}

 85%|████████▌ | 23944/28080 [47:18:23<8:09:22,  7.10s/it]
 85%|████████▌ | 23945/28080 [47:18:30<8:10:28,  7.12s/it]
                                                          
{'loss': 0.5954, 'learning_rate': 2.7899345472378686e-05, 'epoch': 10.23}

 85%|████████▌ | 23945/28080 [47:18:30<8:10:28,  7.12s/it]
 85%|████████▌ | 23946/28080 [47:18:37<8:10:50,  7.12s/it]
                                                          
{'loss': 0.6021, 'learning_rate': 2.7886109482207046e-05, 'epoch': 10.23}

 85%|████████▌ | 23946/28080 [47:18:37<8:10:50,  7.12s/it]
 85%|████████▌ | 23947/28080 [47:18:44<8:11:26,  7.13s/it]
                                                          
{'loss': 0.6033, 'learning_rate': 2.78728764470316e-05, 'epoch': 10.23}

 85%|████████▌ | 23947/28080 [47:18:44<8:11:26,  7.13s/it]
 85%|████████▌ | 23948/28080 [47:18:51<8:11:19,  7.13s/it]
                                                          
{'loss': 0.5898, 'learning_rate': 2.7859646367028286e-05, 'epoch': 10.23}

 85%|████████▌ | 23948/28080 [47:18:51<8:11:19,  7.13s/it]
 85%|████████▌ | 23949/28080 [47:18:58<8:08:19,  7.09s/it]
                                                          
{'loss': 0.6111, 'learning_rate': 2.78464192423733e-05, 'epoch': 10.23}

 85%|████████▌ | 23949/28080 [47:18:58<8:08:19,  7.09s/it]
 85%|████████▌ | 23950/28080 [47:19:06<8:08:28,  7.10s/it]
                                                          
{'loss': 0.6069, 'learning_rate': 2.78331950732425e-05, 'epoch': 10.23}

 85%|████████▌ | 23950/28080 [47:19:06<8:08:28,  7.10s/it]
 85%|████████▌ | 23951/28080 [47:19:13<8:06:27,  7.07s/it]
                                                          
{'loss': 0.6113, 'learning_rate': 2.781997385981186e-05, 'epoch': 10.23}

 85%|████████▌ | 23951/28080 [47:19:13<8:06:27,  7.07s/it]
 85%|████████▌ | 23952/28080 [47:19:20<8:07:35,  7.09s/it]
                                                          
{'loss': 0.6144, 'learning_rate': 2.7806755602257176e-05, 'epoch': 10.23}

 85%|████████▌ | 23952/28080 [47:19:20<8:07:35,  7.09s/it]
 85%|████████▌ | 23953/28080 [47:19:27<8:07:32,  7.09s/it]
                                                          
{'loss': 0.5898, 'learning_rate': 2.7793540300754454e-05, 'epoch': 10.23}

 85%|████████▌ | 23953/28080 [47:19:27<8:07:32,  7.09s/it]
 85%|████████▌ | 23954/28080 [47:19:34<8:05:35,  7.06s/it]
                                                          
{'loss': 0.6182, 'learning_rate': 2.7780327955479412e-05, 'epoch': 10.23}

 85%|████████▌ | 23954/28080 [47:19:34<8:05:35,  7.06s/it]
 85%|████████▌ | 23955/28080 [47:19:41<8:07:26,  7.09s/it]
                                                          
{'loss': 0.5987, 'learning_rate': 2.7767118566607934e-05, 'epoch': 10.23}

 85%|████████▌ | 23955/28080 [47:19:41<8:07:26,  7.09s/it]
 85%|████████▌ | 23956/28080 [47:19:48<8:07:46,  7.10s/it]
                                                          
{'loss': 0.5919, 'learning_rate': 2.7753912134315578e-05, 'epoch': 10.23}

 85%|████████▌ | 23956/28080 [47:19:48<8:07:46,  7.10s/it]
 85%|████████▌ | 23957/28080 [47:19:55<8:08:13,  7.11s/it]
                                                          
{'loss': 0.5882, 'learning_rate': 2.7740708658778173e-05, 'epoch': 10.23}

 85%|████████▌ | 23957/28080 [47:19:55<8:08:13,  7.11s/it]
 85%|████████▌ | 23958/28080 [47:20:02<8:05:10,  7.06s/it]
                                                          
{'loss': 0.6018, 'learning_rate': 2.7727508140171332e-05, 'epoch': 10.23}

 85%|████████▌ | 23958/28080 [47:20:02<8:05:10,  7.06s/it]
 85%|████████▌ | 23959/28080 [47:20:09<8:06:57,  7.09s/it]
                                                          
{'loss': 0.601, 'learning_rate': 2.7714310578670715e-05, 'epoch': 10.24}

 85%|████████▌ | 23959/28080 [47:20:09<8:06:57,  7.09s/it]
 85%|████████▌ | 23960/28080 [47:20:16<8:06:43,  7.09s/it]
                                                          
{'loss': 0.5998, 'learning_rate': 2.770111597445188e-05, 'epoch': 10.24}

 85%|████████▌ | 23960/28080 [47:20:16<8:06:43,  7.09s/it]
 85%|████████▌ | 23961/28080 [47:20:23<8:06:25,  7.09s/it]
                                                          
{'loss': 0.5907, 'learning_rate': 2.7687924327690378e-05, 'epoch': 10.24}

 85%|████████▌ | 23961/28080 [47:20:23<8:06:25,  7.09s/it]
 85%|████████▌ | 23962/28080 [47:20:31<8:07:20,  7.10s/it]
                                                          
{'loss': 0.5991, 'learning_rate': 2.7674735638561683e-05, 'epoch': 10.24}

 85%|████████▌ | 23962/28080 [47:20:31<8:07:20,  7.10s/it]
 85%|████████▌ | 23963/28080 [47:20:38<8:06:54,  7.10s/it]
                                                          
{'loss': 0.6045, 'learning_rate': 2.7661549907241235e-05, 'epoch': 10.24}

 85%|████████▌ | 23963/28080 [47:20:38<8:06:54,  7.10s/it]
 85%|████████▌ | 23964/28080 [47:20:45<8:08:29,  7.12s/it]
                                                          
{'loss': 0.6021, 'learning_rate': 2.7648367133904532e-05, 'epoch': 10.24}

 85%|████████▌ | 23964/28080 [47:20:45<8:08:29,  7.12s/it]
 85%|████████▌ | 23965/28080 [47:20:52<8:08:24,  7.12s/it]
                                                          
{'loss': 0.5954, 'learning_rate': 2.763518731872691e-05, 'epoch': 10.24}

 85%|████████▌ | 23965/28080 [47:20:52<8:08:24,  7.12s/it]
 85%|████████▌ | 23966/28080 [47:20:59<8:05:41,  7.08s/it]
                                                          
{'loss': 0.6524, 'learning_rate': 2.762201046188373e-05, 'epoch': 10.24}

 85%|████████▌ | 23966/28080 [47:20:59<8:05:41,  7.08s/it]
 85%|████████▌ | 23967/28080 [47:21:06<8:03:55,  7.06s/it]
                                                          
{'loss': 0.5882, 'learning_rate': 2.760883656355023e-05, 'epoch': 10.24}

 85%|████████▌ | 23967/28080 [47:21:06<8:03:55,  7.06s/it]
 85%|████████▌ | 23968/28080 [47:21:13<8:03:04,  7.05s/it]
                                                          
{'loss': 0.6174, 'learning_rate': 2.7595665623901784e-05, 'epoch': 10.24}

 85%|████████▌ | 23968/28080 [47:21:13<8:03:04,  7.05s/it]
 85%|████████▌ | 23969/28080 [47:21:20<8:05:14,  7.08s/it]
                                                          
{'loss': 0.5965, 'learning_rate': 2.7582497643113574e-05, 'epoch': 10.24}

 85%|████████▌ | 23969/28080 [47:21:20<8:05:14,  7.08s/it]
 85%|████████▌ | 23970/28080 [47:21:27<8:05:25,  7.09s/it]
                                                          
{'loss': 0.5784, 'learning_rate': 2.756933262136077e-05, 'epoch': 10.24}

 85%|████████▌ | 23970/28080 [47:21:27<8:05:25,  7.09s/it]
 85%|████████▌ | 23971/28080 [47:21:34<8:04:33,  7.08s/it]
                                                          
{'loss': 0.5988, 'learning_rate': 2.7556170558818484e-05, 'epoch': 10.24}

 85%|████████▌ | 23971/28080 [47:21:34<8:04:33,  7.08s/it]
 85%|████████▌ | 23972/28080 [47:21:41<8:04:47,  7.08s/it]
                                                          
{'loss': 0.5806, 'learning_rate': 2.7543011455661903e-05, 'epoch': 10.24}

 85%|████████▌ | 23972/28080 [47:21:41<8:04:47,  7.08s/it]
 85%|████████▌ | 23973/28080 [47:21:48<8:05:37,  7.09s/it]
                                                          
{'loss': 0.5928, 'learning_rate': 2.7529855312066005e-05, 'epoch': 10.24}

 85%|████████▌ | 23973/28080 [47:21:48<8:05:37,  7.09s/it]
 85%|████████▌ | 23974/28080 [47:21:56<8:05:00,  7.09s/it]
                                                          
{'loss': 0.5872, 'learning_rate': 2.7516702128205923e-05, 'epoch': 10.24}

 85%|████████▌ | 23974/28080 [47:21:56<8:05:00,  7.09s/it]
 85%|████████▌ | 23975/28080 [47:22:03<8:06:36,  7.11s/it]
                                                          
{'loss': 0.613, 'learning_rate': 2.75035519042566e-05, 'epoch': 10.24}

 85%|████████▌ | 23975/28080 [47:22:03<8:06:36,  7.11s/it]
 85%|████████▌ | 23976/28080 [47:22:10<8:06:53,  7.12s/it]
                                                          
{'loss': 0.5948, 'learning_rate': 2.7490404640392986e-05, 'epoch': 10.24}

 85%|████████▌ | 23976/28080 [47:22:10<8:06:53,  7.12s/it]
 85%|████████▌ | 23977/28080 [47:22:17<8:07:48,  7.13s/it]
                                                          
{'loss': 0.6014, 'learning_rate': 2.747726033678993e-05, 'epoch': 10.24}

 85%|████████▌ | 23977/28080 [47:22:17<8:07:48,  7.13s/it]
 85%|████████▌ | 23978/28080 [47:22:24<8:05:59,  7.11s/it]
                                                          
{'loss': 0.6006, 'learning_rate': 2.7464118993622444e-05, 'epoch': 10.24}

 85%|████████▌ | 23978/28080 [47:22:24<8:05:59,  7.11s/it]
 85%|████████▌ | 23979/28080 [47:22:31<8:04:41,  7.09s/it]
                                                          
{'loss': 0.6069, 'learning_rate': 2.745098061106524e-05, 'epoch': 10.24}

 85%|████████▌ | 23979/28080 [47:22:31<8:04:41,  7.09s/it]
 85%|████████▌ | 23980/28080 [47:22:38<8:05:53,  7.11s/it]
                                                          
{'loss': 0.5832, 'learning_rate': 2.7437845189293154e-05, 'epoch': 10.24}

 85%|████████▌ | 23980/28080 [47:22:38<8:05:53,  7.11s/it]
 85%|████████▌ | 23981/28080 [47:22:45<8:06:34,  7.12s/it]
                                                          
{'loss': 0.5878, 'learning_rate': 2.7424712728480906e-05, 'epoch': 10.24}

 85%|████████▌ | 23981/28080 [47:22:45<8:06:34,  7.12s/it]
 85%|████████▌ | 23982/28080 [47:22:53<8:07:06,  7.13s/it]
                                                          
{'loss': 0.5869, 'learning_rate': 2.741158322880327e-05, 'epoch': 10.24}

 85%|████████▌ | 23982/28080 [47:22:53<8:07:06,  7.13s/it]
 85%|████████▌ | 23983/28080 [47:23:00<8:06:51,  7.13s/it]
                                                          
{'loss': 0.5975, 'learning_rate': 2.7398456690434863e-05, 'epoch': 10.25}

 85%|████████▌ | 23983/28080 [47:23:00<8:06:51,  7.13s/it]
 85%|████████▌ | 23984/28080 [47:23:07<8:05:12,  7.11s/it]
                                                          
{'loss': 0.598, 'learning_rate': 2.7385333113550374e-05, 'epoch': 10.25}

 85%|████████▌ | 23984/28080 [47:23:07<8:05:12,  7.11s/it]
 85%|████████▌ | 23985/28080 [47:23:14<8:03:24,  7.08s/it]
                                                          
{'loss': 0.612, 'learning_rate': 2.7372212498324335e-05, 'epoch': 10.25}

 85%|████████▌ | 23985/28080 [47:23:14<8:03:24,  7.08s/it]
 85%|████████▌ | 23986/28080 [47:23:21<8:04:44,  7.10s/it]
                                                          
{'loss': 0.5999, 'learning_rate': 2.7359094844931347e-05, 'epoch': 10.25}

 85%|████████▌ | 23986/28080 [47:23:21<8:04:44,  7.10s/it]
 85%|████████▌ | 23987/28080 [47:23:28<8:03:58,  7.09s/it]
                                                          
{'loss': 0.6006, 'learning_rate': 2.7345980153545946e-05, 'epoch': 10.25}

 85%|████████▌ | 23987/28080 [47:23:28<8:03:58,  7.09s/it]
 85%|████████▌ | 23988/28080 [47:23:35<8:03:00,  7.08s/it]
                                                          
{'loss': 0.577, 'learning_rate': 2.7332868424342517e-05, 'epoch': 10.25}

 85%|████████▌ | 23988/28080 [47:23:35<8:03:00,  7.08s/it]
 85%|████████▌ | 23989/28080 [47:23:42<8:03:06,  7.09s/it]
                                                          
{'loss': 0.6066, 'learning_rate': 2.7319759657495668e-05, 'epoch': 10.25}

 85%|████████▌ | 23989/28080 [47:23:42<8:03:06,  7.09s/it]
 85%|████████▌ | 23990/28080 [47:23:49<8:04:24,  7.11s/it]
                                                          
{'loss': 0.5973, 'learning_rate': 2.730665385317957e-05, 'epoch': 10.25}

 85%|████████▌ | 23990/28080 [47:23:49<8:04:24,  7.11s/it]
 85%|████████▌ | 23991/28080 [47:23:56<8:05:14,  7.12s/it]
                                                          
{'loss': 0.5871, 'learning_rate': 2.7293551011568774e-05, 'epoch': 10.25}

 85%|████████▌ | 23991/28080 [47:23:56<8:05:14,  7.12s/it]
 85%|████████▌ | 23992/28080 [47:24:03<8:01:46,  7.07s/it]
                                                          
{'loss': 0.5938, 'learning_rate': 2.7280451132837473e-05, 'epoch': 10.25}

 85%|████████▌ | 23992/28080 [47:24:03<8:01:46,  7.07s/it]
 85%|████████▌ | 23993/28080 [47:24:11<8:03:44,  7.10s/it]
                                                          
{'loss': 0.5919, 'learning_rate': 2.7267354217160034e-05, 'epoch': 10.25}

 85%|████████▌ | 23993/28080 [47:24:11<8:03:44,  7.10s/it]
 85%|████████▌ | 23994/28080 [47:24:18<8:03:09,  7.09s/it]
                                                          
{'loss': 0.5904, 'learning_rate': 2.72542602647107e-05, 'epoch': 10.25}

 85%|████████▌ | 23994/28080 [47:24:18<8:03:09,  7.09s/it]
 85%|████████▌ | 23995/28080 [47:24:25<8:04:32,  7.12s/it]
                                                          
{'loss': 0.5822, 'learning_rate': 2.7241169275663615e-05, 'epoch': 10.25}

 85%|████████▌ | 23995/28080 [47:24:25<8:04:32,  7.12s/it]
 85%|████████▌ | 23996/28080 [47:24:32<8:04:11,  7.11s/it]
                                                          
{'loss': 0.6217, 'learning_rate': 2.7228081250192908e-05, 'epoch': 10.25}

 85%|████████▌ | 23996/28080 [47:24:32<8:04:11,  7.11s/it]
 85%|████████▌ | 23997/28080 [47:24:39<8:01:17,  7.07s/it]
                                                          
{'loss': 0.6204, 'learning_rate': 2.721499618847284e-05, 'epoch': 10.25}

 85%|████████▌ | 23997/28080 [47:24:39<8:01:17,  7.07s/it]
 85%|████████▌ | 23998/28080 [47:24:46<8:02:04,  7.09s/it]
                                                          
{'loss': 0.5937, 'learning_rate': 2.7201914090677404e-05, 'epoch': 10.25}

 85%|████████▌ | 23998/28080 [47:24:46<8:02:04,  7.09s/it]
 85%|████████▌ | 23999/28080 [47:24:53<8:03:49,  7.11s/it]
                                                          
{'loss': 0.6155, 'learning_rate': 2.718883495698063e-05, 'epoch': 10.25}

 85%|████████▌ | 23999/28080 [47:24:53<8:03:49,  7.11s/it]
 85%|████████▌ | 24000/28080 [47:25:00<8:04:19,  7.12s/it]
                                                          
{'loss': 0.5933, 'learning_rate': 2.7175758787556516e-05, 'epoch': 10.25}

 85%|████████▌ | 24000/28080 [47:25:00<8:04:19,  7.12s/it]
 85%|████████▌ | 24001/28080 [47:25:07<8:02:52,  7.10s/it]
                                                          
{'loss': 0.5929, 'learning_rate': 2.7162685582579116e-05, 'epoch': 10.25}

 85%|████████▌ | 24001/28080 [47:25:07<8:02:52,  7.10s/it]
 85%|████████▌ | 24002/28080 [47:25:14<8:01:40,  7.09s/it]
                                                          
{'loss': 0.6158, 'learning_rate': 2.714961534222221e-05, 'epoch': 10.25}

 85%|████████▌ | 24002/28080 [47:25:14<8:01:40,  7.09s/it]
 85%|████████▌ | 24003/28080 [47:25:22<8:05:09,  7.14s/it]
                                                          
{'loss': 0.6034, 'learning_rate': 2.7136548066659912e-05, 'epoch': 10.25}

 85%|████████▌ | 24003/28080 [47:25:22<8:05:09,  7.14s/it]
 85%|████████▌ | 24004/28080 [47:25:29<8:05:17,  7.14s/it]
                                                          
{'loss': 0.5944, 'learning_rate': 2.71234837560658e-05, 'epoch': 10.25}

 85%|████████▌ | 24004/28080 [47:25:29<8:05:17,  7.14s/it]
 85%|████████▌ | 24005/28080 [47:25:36<8:05:15,  7.14s/it]
                                                          
{'loss': 0.5951, 'learning_rate': 2.7110422410613872e-05, 'epoch': 10.25}

 85%|████████▌ | 24005/28080 [47:25:36<8:05:15,  7.14s/it]
 85%|████████▌ | 24006/28080 [47:25:43<8:03:45,  7.12s/it]
                                                          
{'loss': 0.5841, 'learning_rate': 2.709736403047777e-05, 'epoch': 10.26}

 85%|████████▌ | 24006/28080 [47:25:43<8:03:45,  7.12s/it]
 85%|████████▌ | 24007/28080 [47:25:50<8:04:59,  7.14s/it]
                                                          
{'loss': 0.5954, 'learning_rate': 2.7084308615831333e-05, 'epoch': 10.26}

 85%|████████▌ | 24007/28080 [47:25:50<8:04:59,  7.14s/it]
 85%|████████▌ | 24008/28080 [47:25:57<8:03:44,  7.13s/it]
                                                          
{'loss': 0.5884, 'learning_rate': 2.707125616684819e-05, 'epoch': 10.26}

 85%|████████▌ | 24008/28080 [47:25:57<8:03:44,  7.13s/it]
 86%|████████▌ | 24009/28080 [47:26:05<8:02:59,  7.12s/it]
                                                          
{'loss': 0.6231, 'learning_rate': 2.7058206683702014e-05, 'epoch': 10.26}

 86%|████████▌ | 24009/28080 [47:26:05<8:02:59,  7.12s/it]
 86%|████████▌ | 24010/28080 [47:26:12<8:03:21,  7.13s/it]
                                                          
{'loss': 0.5788, 'learning_rate': 2.7045160166566356e-05, 'epoch': 10.26}

 86%|████████▌ | 24010/28080 [47:26:12<8:03:21,  7.13s/it]
 86%|████████▌ | 24011/28080 [47:26:19<8:04:08,  7.14s/it]
                                                          
{'loss': 0.5973, 'learning_rate': 2.7032116615614888e-05, 'epoch': 10.26}

 86%|████████▌ | 24011/28080 [47:26:19<8:04:08,  7.14s/it]
 86%|████████▌ | 24012/28080 [47:26:26<8:01:31,  7.10s/it]
                                                          
{'loss': 0.6304, 'learning_rate': 2.701907603102108e-05, 'epoch': 10.26}

 86%|████████▌ | 24012/28080 [47:26:26<8:01:31,  7.10s/it]
 86%|████████▌ | 24013/28080 [47:26:33<8:03:50,  7.14s/it]
                                                          
{'loss': 0.6073, 'learning_rate': 2.7006038412958427e-05, 'epoch': 10.26}

 86%|████████▌ | 24013/28080 [47:26:33<8:03:50,  7.14s/it]
 86%|████████▌ | 24014/28080 [47:26:40<8:01:25,  7.10s/it]
                                                          
{'loss': 0.5822, 'learning_rate': 2.6993003761600383e-05, 'epoch': 10.26}

 86%|████████▌ | 24014/28080 [47:26:40<8:01:25,  7.10s/it]
 86%|████████▌ | 24015/28080 [47:26:47<8:00:06,  7.09s/it]
                                                          
{'loss': 0.6079, 'learning_rate': 2.6979972077120303e-05, 'epoch': 10.26}

 86%|████████▌ | 24015/28080 [47:26:47<8:00:06,  7.09s/it]
 86%|████████▌ | 24016/28080 [47:26:54<8:00:44,  7.10s/it]
                                                          
{'loss': 0.5882, 'learning_rate': 2.696694335969166e-05, 'epoch': 10.26}

 86%|████████▌ | 24016/28080 [47:26:54<8:00:44,  7.10s/it]
 86%|████████▌ | 24017/28080 [47:27:01<7:58:19,  7.06s/it]
                                                          
{'loss': 0.5983, 'learning_rate': 2.695391760948776e-05, 'epoch': 10.26}

 86%|████████▌ | 24017/28080 [47:27:01<7:58:19,  7.06s/it]
 86%|████████▌ | 24018/28080 [47:27:08<7:58:00,  7.06s/it]
                                                          
{'loss': 0.5997, 'learning_rate': 2.6940894826681885e-05, 'epoch': 10.26}

 86%|████████▌ | 24018/28080 [47:27:08<7:58:00,  7.06s/it]
 86%|████████▌ | 24019/28080 [47:27:15<7:59:04,  7.08s/it]
                                                          
{'loss': 0.6023, 'learning_rate': 2.692787501144725e-05, 'epoch': 10.26}

 86%|████████▌ | 24019/28080 [47:27:15<7:59:04,  7.08s/it]
 86%|████████▌ | 24020/28080 [47:27:22<7:56:41,  7.04s/it]
                                                          
{'loss': 0.6034, 'learning_rate': 2.691485816395714e-05, 'epoch': 10.26}

 86%|████████▌ | 24020/28080 [47:27:22<7:56:41,  7.04s/it]
 86%|████████▌ | 24021/28080 [47:27:30<7:58:46,  7.08s/it]
                                                          
{'loss': 0.6076, 'learning_rate': 2.6901844284384635e-05, 'epoch': 10.26}

 86%|████████▌ | 24021/28080 [47:27:30<7:58:46,  7.08s/it]
 86%|████████▌ | 24022/28080 [47:27:37<7:58:52,  7.08s/it]
                                                          
{'loss': 0.5936, 'learning_rate': 2.6888833372902988e-05, 'epoch': 10.26}

 86%|████████▌ | 24022/28080 [47:27:37<7:58:52,  7.08s/it]
 86%|████████▌ | 24023/28080 [47:27:44<7:58:08,  7.07s/it]
                                                          
{'loss': 0.5872, 'learning_rate': 2.687582542968525e-05, 'epoch': 10.26}

 86%|████████▌ | 24023/28080 [47:27:44<7:58:08,  7.07s/it]
 86%|████████▌ | 24024/28080 [47:27:51<7:58:54,  7.08s/it]
                                                          
{'loss': 0.5822, 'learning_rate': 2.6862820454904487e-05, 'epoch': 10.26}

 86%|████████▌ | 24024/28080 [47:27:51<7:58:54,  7.08s/it]
 86%|████████▌ | 24025/28080 [47:27:58<7:57:57,  7.07s/it]
                                                          
{'loss': 0.6173, 'learning_rate': 2.684981844873363e-05, 'epoch': 10.26}

 86%|████████▌ | 24025/28080 [47:27:58<7:57:57,  7.07s/it]
 86%|████████▌ | 24026/28080 [47:28:05<7:58:10,  7.08s/it]
                                                          
{'loss': 0.6061, 'learning_rate': 2.6836819411345775e-05, 'epoch': 10.26}

 86%|████████▌ | 24026/28080 [47:28:05<7:58:10,  7.08s/it]
 86%|████████▌ | 24027/28080 [47:28:12<7:57:01,  7.06s/it]
                                                          
{'loss': 0.5981, 'learning_rate': 2.6823823342913833e-05, 'epoch': 10.26}

 86%|████████▌ | 24027/28080 [47:28:12<7:57:01,  7.06s/it]
 86%|████████▌ | 24028/28080 [47:28:19<7:59:23,  7.10s/it]
                                                          
{'loss': 0.5959, 'learning_rate': 2.6810830243610666e-05, 'epoch': 10.26}

 86%|████████▌ | 24028/28080 [47:28:19<7:59:23,  7.10s/it]
 86%|████████▌ | 24029/28080 [47:28:26<8:00:20,  7.11s/it]
                                                          
{'loss': 0.6071, 'learning_rate': 2.6797840113609113e-05, 'epoch': 10.26}

 86%|████████▌ | 24029/28080 [47:28:26<8:00:20,  7.11s/it]
 86%|████████▌ | 24030/28080 [47:28:33<7:59:12,  7.10s/it]
                                                          
{'loss': 0.5876, 'learning_rate': 2.6784852953082055e-05, 'epoch': 10.27}

 86%|████████▌ | 24030/28080 [47:28:33<7:59:12,  7.10s/it]
 86%|████████▌ | 24031/28080 [47:28:40<7:59:41,  7.11s/it]
                                                          
{'loss': 0.5869, 'learning_rate': 2.677186876220228e-05, 'epoch': 10.27}

 86%|████████▌ | 24031/28080 [47:28:40<7:59:41,  7.11s/it]
 86%|████████▌ | 24032/28080 [47:28:48<8:00:54,  7.13s/it]
                                                          
{'loss': 0.6046, 'learning_rate': 2.6758887541142502e-05, 'epoch': 10.27}

 86%|████████▌ | 24032/28080 [47:28:48<8:00:54,  7.13s/it]
 86%|████████▌ | 24033/28080 [47:28:55<8:01:07,  7.13s/it]
                                                          
{'loss': 0.6146, 'learning_rate': 2.674590929007534e-05, 'epoch': 10.27}

 86%|████████▌ | 24033/28080 [47:28:55<8:01:07,  7.13s/it]
 86%|████████▌ | 24034/28080 [47:29:02<8:00:31,  7.13s/it]
                                                          
{'loss': 0.6017, 'learning_rate': 2.673293400917362e-05, 'epoch': 10.27}

 86%|████████▌ | 24034/28080 [47:29:02<8:00:31,  7.13s/it]
 86%|████████▌ | 24035/28080 [47:29:09<8:00:09,  7.12s/it]
                                                          
{'loss': 0.5916, 'learning_rate': 2.6719961698609795e-05, 'epoch': 10.27}

 86%|████████▌ | 24035/28080 [47:29:09<8:00:09,  7.12s/it]
 86%|████████▌ | 24036/28080 [47:29:16<7:58:23,  7.10s/it]
                                                          
{'loss': 0.6173, 'learning_rate': 2.6706992358556614e-05, 'epoch': 10.27}

 86%|████████▌ | 24036/28080 [47:29:16<7:58:23,  7.10s/it]
 86%|████████▌ | 24037/28080 [47:29:23<7:59:33,  7.12s/it]
                                                          
{'loss': 0.6116, 'learning_rate': 2.6694025989186578e-05, 'epoch': 10.27}

 86%|████████▌ | 24037/28080 [47:29:23<7:59:33,  7.12s/it]
 86%|████████▌ | 24038/28080 [47:29:30<8:01:21,  7.15s/it]
                                                          
{'loss': 0.6012, 'learning_rate': 2.6681062590672073e-05, 'epoch': 10.27}

 86%|████████▌ | 24038/28080 [47:29:30<8:01:21,  7.15s/it]
 86%|████████▌ | 24039/28080 [47:29:37<7:59:02,  7.11s/it]
                                                          
{'loss': 0.6084, 'learning_rate': 2.666810216318566e-05, 'epoch': 10.27}

 86%|████████▌ | 24039/28080 [47:29:37<7:59:02,  7.11s/it]
 86%|████████▌ | 24040/28080 [47:29:45<7:58:59,  7.11s/it]
                                                          
{'loss': 0.6129, 'learning_rate': 2.6655144706899727e-05, 'epoch': 10.27}

 86%|████████▌ | 24040/28080 [47:29:45<7:58:59,  7.11s/it]
 86%|████████▌ | 24041/28080 [47:29:52<7:59:46,  7.13s/it]
                                                          
{'loss': 0.591, 'learning_rate': 2.664219022198672e-05, 'epoch': 10.27}

 86%|████████▌ | 24041/28080 [47:29:52<7:59:46,  7.13s/it]
 86%|████████▌ | 24042/28080 [47:29:59<8:00:26,  7.14s/it]
                                                          
{'loss': 0.593, 'learning_rate': 2.662923870861894e-05, 'epoch': 10.27}

 86%|████████▌ | 24042/28080 [47:29:59<8:00:26,  7.14s/it]
 86%|████████▌ | 24043/28080 [47:30:06<7:59:12,  7.12s/it]
                                                          
{'loss': 0.5932, 'learning_rate': 2.661629016696873e-05, 'epoch': 10.27}

 86%|████████▌ | 24043/28080 [47:30:06<7:59:12,  7.12s/it]
 86%|████████▌ | 24044/28080 [47:30:13<7:57:13,  7.09s/it]
                                                          
{'loss': 0.6077, 'learning_rate': 2.6603344597208257e-05, 'epoch': 10.27}

 86%|████████▌ | 24044/28080 [47:30:13<7:57:13,  7.09s/it]
 86%|████████▌ | 24045/28080 [47:30:20<7:57:44,  7.10s/it]
                                                          
{'loss': 0.6045, 'learning_rate': 2.6590401999509877e-05, 'epoch': 10.27}

 86%|████████▌ | 24045/28080 [47:30:20<7:57:44,  7.10s/it]
 86%|████████▌ | 24046/28080 [47:30:27<8:00:14,  7.14s/it]
                                                          
{'loss': 0.5819, 'learning_rate': 2.6577462374045708e-05, 'epoch': 10.27}

 86%|████████▌ | 24046/28080 [47:30:27<8:00:14,  7.14s/it]
 86%|████████▌ | 24047/28080 [47:30:34<7:57:55,  7.11s/it]
                                                          
{'loss': 0.6018, 'learning_rate': 2.6564525720987914e-05, 'epoch': 10.27}

 86%|████████▌ | 24047/28080 [47:30:34<7:57:55,  7.11s/it]
 86%|████████▌ | 24048/28080 [47:30:41<7:57:23,  7.10s/it]
                                                          
{'loss': 0.5953, 'learning_rate': 2.6551592040508527e-05, 'epoch': 10.27}

 86%|████████▌ | 24048/28080 [47:30:41<7:57:23,  7.10s/it]
 86%|████████▌ | 24049/28080 [47:30:49<7:56:36,  7.09s/it]
                                                          
{'loss': 0.5966, 'learning_rate': 2.6538661332779767e-05, 'epoch': 10.27}

 86%|████████▌ | 24049/28080 [47:30:49<7:56:36,  7.09s/it]
 86%|████████▌ | 24050/28080 [47:30:56<7:54:53,  7.07s/it]
                                                          
{'loss': 0.631, 'learning_rate': 2.6525733597973527e-05, 'epoch': 10.27}

 86%|████████▌ | 24050/28080 [47:30:56<7:54:53,  7.07s/it]
 86%|████████▌ | 24051/28080 [47:31:03<7:53:05,  7.05s/it]
                                                          
{'loss': 0.5928, 'learning_rate': 2.6512808836261975e-05, 'epoch': 10.27}

 86%|████████▌ | 24051/28080 [47:31:03<7:53:05,  7.05s/it]
 86%|████████▌ | 24052/28080 [47:31:10<7:54:34,  7.07s/it]
                                                          
{'loss': 0.6122, 'learning_rate': 2.6499887047816807e-05, 'epoch': 10.27}

 86%|████████▌ | 24052/28080 [47:31:10<7:54:34,  7.07s/it]
 86%|████████▌ | 24053/28080 [47:31:17<7:55:28,  7.08s/it]
                                                          
{'loss': 0.5826, 'learning_rate': 2.648696823281016e-05, 'epoch': 10.28}

 86%|████████▌ | 24053/28080 [47:31:17<7:55:28,  7.08s/it]
 86%|████████▌ | 24054/28080 [47:31:24<7:53:46,  7.06s/it]
                                                          
{'loss': 0.5855, 'learning_rate': 2.647405239141373e-05, 'epoch': 10.28}

 86%|████████▌ | 24054/28080 [47:31:24<7:53:46,  7.06s/it]
 86%|████████▌ | 24055/28080 [47:31:31<7:55:04,  7.08s/it]
                                                          
{'loss': 0.5829, 'learning_rate': 2.64611395237995e-05, 'epoch': 10.28}

 86%|████████▌ | 24055/28080 [47:31:31<7:55:04,  7.08s/it]
 86%|████████▌ | 24056/28080 [47:31:38<7:55:53,  7.10s/it]
                                                          
{'loss': 0.6033, 'learning_rate': 2.644822963013921e-05, 'epoch': 10.28}

 86%|████████▌ | 24056/28080 [47:31:38<7:55:53,  7.10s/it]
 86%|████████▌ | 24057/28080 [47:31:45<7:56:20,  7.10s/it]
                                                          
{'loss': 0.6073, 'learning_rate': 2.643532271060456e-05, 'epoch': 10.28}

 86%|████████▌ | 24057/28080 [47:31:45<7:56:20,  7.10s/it]
 86%|████████▌ | 24058/28080 [47:31:52<7:57:32,  7.12s/it]
                                                          
{'loss': 0.5984, 'learning_rate': 2.64224187653673e-05, 'epoch': 10.28}

 86%|████████▌ | 24058/28080 [47:31:52<7:57:32,  7.12s/it]
 86%|████████▌ | 24059/28080 [47:32:00<7:59:20,  7.15s/it]
                                                          
{'loss': 0.6085, 'learning_rate': 2.640951779459913e-05, 'epoch': 10.28}

 86%|████████▌ | 24059/28080 [47:32:00<7:59:20,  7.15s/it]
 86%|████████▌ | 24060/28080 [47:32:07<7:57:56,  7.13s/it]
                                                          
{'loss': 0.6014, 'learning_rate': 2.639661979847166e-05, 'epoch': 10.28}

 86%|████████▌ | 24060/28080 [47:32:07<7:57:56,  7.13s/it]
 86%|████████▌ | 24061/28080 [47:32:14<7:57:33,  7.13s/it]
                                                          
{'loss': 0.611, 'learning_rate': 2.6383724777156475e-05, 'epoch': 10.28}

 86%|████████▌ | 24061/28080 [47:32:14<7:57:33,  7.13s/it]
 86%|████████▌ | 24062/28080 [47:32:21<7:55:46,  7.10s/it]
                                                          
{'loss': 0.5981, 'learning_rate': 2.6370832730825162e-05, 'epoch': 10.28}

 86%|████████▌ | 24062/28080 [47:32:21<7:55:46,  7.10s/it]
 86%|████████▌ | 24063/28080 [47:32:28<7:55:06,  7.10s/it]
                                                          
{'loss': 0.5951, 'learning_rate': 2.6357943659649162e-05, 'epoch': 10.28}

 86%|████████▌ | 24063/28080 [47:32:28<7:55:06,  7.10s/it]
 86%|████████▌ | 24064/28080 [47:32:35<7:55:28,  7.10s/it]
                                                          
{'loss': 0.6087, 'learning_rate': 2.634505756380004e-05, 'epoch': 10.28}

 86%|████████▌ | 24064/28080 [47:32:35<7:55:28,  7.10s/it]
 86%|████████▌ | 24065/28080 [47:32:42<7:55:09,  7.10s/it]
                                                          
{'loss': 0.584, 'learning_rate': 2.6332174443449182e-05, 'epoch': 10.28}

 86%|████████▌ | 24065/28080 [47:32:42<7:55:09,  7.10s/it]
 86%|████████▌ | 24066/28080 [47:32:49<7:55:00,  7.10s/it]
                                                          
{'loss': 0.5871, 'learning_rate': 2.631929429876803e-05, 'epoch': 10.28}

 86%|████████▌ | 24066/28080 [47:32:49<7:55:00,  7.10s/it]
 86%|████████▌ | 24067/28080 [47:32:56<7:55:50,  7.11s/it]
                                                          
{'loss': 0.6031, 'learning_rate': 2.6306417129927847e-05, 'epoch': 10.28}

 86%|████████▌ | 24067/28080 [47:32:56<7:55:50,  7.11s/it]
 86%|████████▌ | 24068/28080 [47:33:03<7:55:01,  7.10s/it]
                                                          
{'loss': 0.5934, 'learning_rate': 2.6293542937100068e-05, 'epoch': 10.28}

 86%|████████▌ | 24068/28080 [47:33:03<7:55:01,  7.10s/it]
 86%|████████▌ | 24069/28080 [47:33:11<7:53:36,  7.08s/it]
                                                          
{'loss': 0.5937, 'learning_rate': 2.628067172045584e-05, 'epoch': 10.28}

 86%|████████▌ | 24069/28080 [47:33:11<7:53:36,  7.08s/it]
 86%|████████▌ | 24070/28080 [47:33:18<7:54:41,  7.10s/it]
                                                          
{'loss': 0.5777, 'learning_rate': 2.6267803480166607e-05, 'epoch': 10.28}

 86%|████████▌ | 24070/28080 [47:33:18<7:54:41,  7.10s/it]
 86%|████████▌ | 24071/28080 [47:33:25<7:55:34,  7.12s/it]
                                                          
{'loss': 0.5995, 'learning_rate': 2.6254938216403317e-05, 'epoch': 10.28}

 86%|████████▌ | 24071/28080 [47:33:25<7:55:34,  7.12s/it]
 86%|████████▌ | 24072/28080 [47:33:32<7:55:28,  7.12s/it]
                                                          
{'loss': 0.5886, 'learning_rate': 2.6242075929337305e-05, 'epoch': 10.28}

 86%|████████▌ | 24072/28080 [47:33:32<7:55:28,  7.12s/it]
 86%|████████▌ | 24073/28080 [47:33:39<7:58:18,  7.16s/it]
                                                          
{'loss': 0.6261, 'learning_rate': 2.6229216619139573e-05, 'epoch': 10.28}

 86%|████████▌ | 24073/28080 [47:33:39<7:58:18,  7.16s/it]
 86%|████████▌ | 24074/28080 [47:33:46<7:58:06,  7.16s/it]
                                                          
{'loss': 0.6022, 'learning_rate': 2.6216360285981345e-05, 'epoch': 10.28}

 86%|████████▌ | 24074/28080 [47:33:46<7:58:06,  7.16s/it]
 86%|████████▌ | 24075/28080 [47:33:54<7:59:51,  7.19s/it]
                                                          
{'loss': 0.5884, 'learning_rate': 2.6203506930033537e-05, 'epoch': 10.28}

 86%|████████▌ | 24075/28080 [47:33:54<7:59:51,  7.19s/it]
 86%|████████▌ | 24076/28080 [47:34:01<7:59:57,  7.19s/it]
                                                          
{'loss': 0.5981, 'learning_rate': 2.6190656551467213e-05, 'epoch': 10.29}

 86%|████████▌ | 24076/28080 [47:34:01<7:59:57,  7.19s/it]
 86%|████████▌ | 24077/28080 [47:34:08<7:59:09,  7.18s/it]
                                                          
{'loss': 0.5974, 'learning_rate': 2.6177809150453285e-05, 'epoch': 10.29}

 86%|████████▌ | 24077/28080 [47:34:08<7:59:09,  7.18s/it]
 86%|████████▌ | 24078/28080 [47:34:15<7:59:02,  7.18s/it]
                                                          
{'loss': 0.6008, 'learning_rate': 2.6164964727162704e-05, 'epoch': 10.29}

 86%|████████▌ | 24078/28080 [47:34:15<7:59:02,  7.18s/it]
 86%|████████▌ | 24079/28080 [47:34:22<7:59:27,  7.19s/it]
                                                          
{'loss': 0.6008, 'learning_rate': 2.6152123281766387e-05, 'epoch': 10.29}

 86%|████████▌ | 24079/28080 [47:34:22<7:59:27,  7.19s/it]
 86%|████████▌ | 24080/28080 [47:34:30<7:58:54,  7.18s/it]
                                                          
{'loss': 0.6058, 'learning_rate': 2.6139284814435117e-05, 'epoch': 10.29}

 86%|████████▌ | 24080/28080 [47:34:30<7:58:54,  7.18s/it]
 86%|████████▌ | 24081/28080 [47:34:37<7:58:03,  7.17s/it]
                                                          
{'loss': 0.6044, 'learning_rate': 2.6126449325339695e-05, 'epoch': 10.29}

 86%|████████▌ | 24081/28080 [47:34:37<7:58:03,  7.17s/it]
 86%|████████▌ | 24082/28080 [47:34:44<7:56:24,  7.15s/it]
                                                          
{'loss': 0.5996, 'learning_rate': 2.6113616814650936e-05, 'epoch': 10.29}

 86%|████████▌ | 24082/28080 [47:34:44<7:56:24,  7.15s/it]
 86%|████████▌ | 24083/28080 [47:34:51<7:55:46,  7.14s/it]
                                                          
{'loss': 0.5965, 'learning_rate': 2.6100787282539478e-05, 'epoch': 10.29}

 86%|████████▌ | 24083/28080 [47:34:51<7:55:46,  7.14s/it]
 86%|████████▌ | 24084/28080 [47:34:58<7:55:22,  7.14s/it]
                                                          
{'loss': 0.6098, 'learning_rate': 2.608796072917613e-05, 'epoch': 10.29}

 86%|████████▌ | 24084/28080 [47:34:58<7:55:22,  7.14s/it]
 86%|████████▌ | 24085/28080 [47:35:05<7:52:36,  7.10s/it]
                                                          
{'loss': 0.6199, 'learning_rate': 2.6075137154731447e-05, 'epoch': 10.29}

 86%|████████▌ | 24085/28080 [47:35:05<7:52:36,  7.10s/it]
 86%|████████▌ | 24086/28080 [47:35:12<7:51:17,  7.08s/it]
                                                          
{'loss': 0.6145, 'learning_rate': 2.6062316559376076e-05, 'epoch': 10.29}

 86%|████████▌ | 24086/28080 [47:35:12<7:51:17,  7.08s/it]
 86%|████████▌ | 24087/28080 [47:35:19<7:51:07,  7.08s/it]
                                                          
{'loss': 0.62, 'learning_rate': 2.6049498943280542e-05, 'epoch': 10.29}

 86%|████████▌ | 24087/28080 [47:35:19<7:51:07,  7.08s/it]
 86%|████████▌ | 24088/28080 [47:35:26<7:51:19,  7.08s/it]
                                                          
{'loss': 0.5959, 'learning_rate': 2.603668430661535e-05, 'epoch': 10.29}

 86%|████████▌ | 24088/28080 [47:35:26<7:51:19,  7.08s/it]
 86%|████████▌ | 24089/28080 [47:35:33<7:53:50,  7.12s/it]
                                                          
{'loss': 0.6083, 'learning_rate': 2.6023872649551054e-05, 'epoch': 10.29}

 86%|████████▌ | 24089/28080 [47:35:33<7:53:50,  7.12s/it]
 86%|████████▌ | 24090/28080 [47:35:41<7:54:23,  7.13s/it]
                                                          
{'loss': 0.5954, 'learning_rate': 2.601106397225811e-05, 'epoch': 10.29}

 86%|████████▌ | 24090/28080 [47:35:41<7:54:23,  7.13s/it]
 86%|████████▌ | 24091/28080 [47:35:48<7:52:36,  7.11s/it]
                                                          
{'loss': 0.5948, 'learning_rate': 2.5998258274906843e-05, 'epoch': 10.29}

 86%|████████▌ | 24091/28080 [47:35:48<7:52:36,  7.11s/it]
 86%|████████▌ | 24092/28080 [47:35:55<7:54:03,  7.13s/it]
                                                          
{'loss': 0.6134, 'learning_rate': 2.5985455557667625e-05, 'epoch': 10.29}

 86%|████████▌ | 24092/28080 [47:35:55<7:54:03,  7.13s/it]
 86%|████████▌ | 24093/28080 [47:36:02<7:53:24,  7.12s/it]
                                                          
{'loss': 0.6003, 'learning_rate': 2.5972655820710873e-05, 'epoch': 10.29}

 86%|████████▌ | 24093/28080 [47:36:02<7:53:24,  7.12s/it]
 86%|████████▌ | 24094/28080 [47:36:09<7:53:53,  7.13s/it]
                                                          
{'loss': 0.5939, 'learning_rate': 2.5959859064206808e-05, 'epoch': 10.29}

 86%|████████▌ | 24094/28080 [47:36:09<7:53:53,  7.13s/it]
 86%|████████▌ | 24095/28080 [47:36:16<7:52:27,  7.11s/it]
                                                          
{'loss': 0.6002, 'learning_rate': 2.5947065288325687e-05, 'epoch': 10.29}

 86%|████████▌ | 24095/28080 [47:36:16<7:52:27,  7.11s/it]
 86%|████████▌ | 24096/28080 [47:36:23<7:51:57,  7.11s/it]
                                                          
{'loss': 0.5833, 'learning_rate': 2.5934274493237682e-05, 'epoch': 10.29}

 86%|████████▌ | 24096/28080 [47:36:23<7:51:57,  7.11s/it]
 86%|████████▌ | 24097/28080 [47:36:30<7:51:33,  7.10s/it]
                                                          
{'loss': 0.6048, 'learning_rate': 2.5921486679113037e-05, 'epoch': 10.29}

 86%|████████▌ | 24097/28080 [47:36:30<7:51:33,  7.10s/it]
 86%|████████▌ | 24098/28080 [47:36:37<7:51:35,  7.11s/it]
                                                          
{'loss': 0.583, 'learning_rate': 2.590870184612179e-05, 'epoch': 10.29}

 86%|████████▌ | 24098/28080 [47:36:37<7:51:35,  7.11s/it]
 86%|████████▌ | 24099/28080 [47:36:45<7:52:02,  7.11s/it]
                                                          
{'loss': 0.5854, 'learning_rate': 2.5895919994434192e-05, 'epoch': 10.29}

 86%|████████▌ | 24099/28080 [47:36:45<7:52:02,  7.11s/it]
 86%|████████▌ | 24100/28080 [47:36:52<7:52:51,  7.13s/it]
                                                          
{'loss': 0.603, 'learning_rate': 2.5883141124220077e-05, 'epoch': 10.3}

 86%|████████▌ | 24100/28080 [47:36:52<7:52:51,  7.13s/it]
 86%|████████▌ | 24101/28080 [47:36:59<7:49:29,  7.08s/it]
                                                          
{'loss': 0.6118, 'learning_rate': 2.5870365235649617e-05, 'epoch': 10.3}

 86%|████████▌ | 24101/28080 [47:36:59<7:49:29,  7.08s/it]
 86%|████████▌ | 24102/28080 [47:37:06<7:49:50,  7.09s/it]
                                                          
{'loss': 0.6063, 'learning_rate': 2.5857592328892678e-05, 'epoch': 10.3}

 86%|████████▌ | 24102/28080 [47:37:06<7:49:50,  7.09s/it]
 86%|████████▌ | 24103/28080 [47:37:13<7:48:55,  7.07s/it]
                                                          
{'loss': 0.5974, 'learning_rate': 2.5844822404119284e-05, 'epoch': 10.3}

 86%|████████▌ | 24103/28080 [47:37:13<7:48:55,  7.07s/it]
 86%|████████▌ | 24104/28080 [47:37:20<7:49:40,  7.09s/it]
                                                          
{'loss': 0.6073, 'learning_rate': 2.5832055461499277e-05, 'epoch': 10.3}

 86%|████████▌ | 24104/28080 [47:37:20<7:49:40,  7.09s/it]
 86%|████████▌ | 24105/28080 [47:37:27<7:51:10,  7.11s/it]
                                                          
{'loss': 0.6037, 'learning_rate': 2.5819291501202518e-05, 'epoch': 10.3}

 86%|████████▌ | 24105/28080 [47:37:27<7:51:10,  7.11s/it]
 86%|████████▌ | 24106/28080 [47:37:34<7:51:22,  7.12s/it]
                                                          
{'loss': 0.6109, 'learning_rate': 2.5806530523398765e-05, 'epoch': 10.3}

 86%|████████▌ | 24106/28080 [47:37:34<7:51:22,  7.12s/it]
 86%|████████▌ | 24107/28080 [47:37:41<7:52:19,  7.13s/it]
                                                          
{'loss': 0.6207, 'learning_rate': 2.5793772528257875e-05, 'epoch': 10.3}

 86%|████████▌ | 24107/28080 [47:37:41<7:52:19,  7.13s/it]
 86%|████████▌ | 24108/28080 [47:37:49<7:52:32,  7.14s/it]
                                                          
{'loss': 0.6117, 'learning_rate': 2.578101751594955e-05, 'epoch': 10.3}

 86%|████████▌ | 24108/28080 [47:37:49<7:52:32,  7.14s/it]
 86%|████████▌ | 24109/28080 [47:37:56<7:52:39,  7.14s/it]
                                                          
{'loss': 0.5898, 'learning_rate': 2.576826548664346e-05, 'epoch': 10.3}

 86%|████████▌ | 24109/28080 [47:37:56<7:52:39,  7.14s/it]
 86%|████████▌ | 24110/28080 [47:38:03<7:51:52,  7.13s/it]
                                                          
{'loss': 0.6171, 'learning_rate': 2.5755516440509247e-05, 'epoch': 10.3}

 86%|████████▌ | 24110/28080 [47:38:03<7:51:52,  7.13s/it]
 86%|████████▌ | 24111/28080 [47:38:10<7:49:39,  7.10s/it]
                                                          
{'loss': 0.6107, 'learning_rate': 2.574277037771658e-05, 'epoch': 10.3}

 86%|████████▌ | 24111/28080 [47:38:10<7:49:39,  7.10s/it]
 86%|████████▌ | 24112/28080 [47:38:17<7:48:10,  7.08s/it]
                                                          
{'loss': 0.5915, 'learning_rate': 2.573002729843499e-05, 'epoch': 10.3}

 86%|████████▌ | 24112/28080 [47:38:17<7:48:10,  7.08s/it]
 86%|████████▌ | 24113/28080 [47:38:24<7:50:54,  7.12s/it]
                                                          
{'loss': 0.597, 'learning_rate': 2.5717287202834033e-05, 'epoch': 10.3}

 86%|████████▌ | 24113/28080 [47:38:24<7:50:54,  7.12s/it]
 86%|████████▌ | 24114/28080 [47:38:31<7:49:24,  7.10s/it]
                                                          
{'loss': 0.6002, 'learning_rate': 2.570455009108319e-05, 'epoch': 10.3}

 86%|████████▌ | 24114/28080 [47:38:31<7:49:24,  7.10s/it]
 86%|████████▌ | 24115/28080 [47:38:38<7:50:29,  7.12s/it]
                                                          
{'loss': 0.5912, 'learning_rate': 2.569181596335185e-05, 'epoch': 10.3}

 86%|████████▌ | 24115/28080 [47:38:38<7:50:29,  7.12s/it]
 86%|████████▌ | 24116/28080 [47:38:46<7:51:40,  7.14s/it]
                                                          
{'loss': 0.6007, 'learning_rate': 2.5679084819809545e-05, 'epoch': 10.3}

 86%|████████▌ | 24116/28080 [47:38:46<7:51:40,  7.14s/it]
 86%|████████▌ | 24117/28080 [47:38:53<7:52:12,  7.15s/it]
                                                          
{'loss': 0.5889, 'learning_rate': 2.5666356660625555e-05, 'epoch': 10.3}

 86%|████████▌ | 24117/28080 [47:38:53<7:52:12,  7.15s/it]
 86%|████████▌ | 24118/28080 [47:39:00<7:52:52,  7.16s/it]
                                                          
{'loss': 0.6079, 'learning_rate': 2.5653631485969357e-05, 'epoch': 10.3}

 86%|████████▌ | 24118/28080 [47:39:00<7:52:52,  7.16s/it]
 86%|████████▌ | 24119/28080 [47:39:07<7:52:16,  7.15s/it]
                                                          
{'loss': 0.6016, 'learning_rate': 2.5640909296010068e-05, 'epoch': 10.3}

 86%|████████▌ | 24119/28080 [47:39:07<7:52:16,  7.15s/it]
 86%|████████▌ | 24120/28080 [47:39:14<7:51:41,  7.15s/it]
                                                          
{'loss': 0.6023, 'learning_rate': 2.5628190090917046e-05, 'epoch': 10.3}

 86%|████████▌ | 24120/28080 [47:39:14<7:51:41,  7.15s/it]
 86%|████████▌ | 24121/28080 [47:39:21<7:49:32,  7.12s/it]
                                                          
{'loss': 0.6313, 'learning_rate': 2.561547387085944e-05, 'epoch': 10.3}

 86%|████████▌ | 24121/28080 [47:39:21<7:49:32,  7.12s/it]
 86%|████████▌ | 24122/28080 [47:39:28<7:46:19,  7.07s/it]
                                                          
{'loss': 0.6139, 'learning_rate': 2.560276063600653e-05, 'epoch': 10.3}

 86%|████████▌ | 24122/28080 [47:39:28<7:46:19,  7.07s/it]
 86%|████████▌ | 24123/28080 [47:39:35<7:46:33,  7.07s/it]
                                                          
{'loss': 0.6143, 'learning_rate': 2.559005038652737e-05, 'epoch': 10.31}

 86%|████████▌ | 24123/28080 [47:39:35<7:46:33,  7.07s/it]
 86%|████████▌ | 24124/28080 [47:39:42<7:47:28,  7.09s/it]
                                                          
{'loss': 0.6091, 'learning_rate': 2.5577343122591106e-05, 'epoch': 10.31}

 86%|████████▌ | 24124/28080 [47:39:42<7:47:28,  7.09s/it]
 86%|████████▌ | 24125/28080 [47:39:49<7:44:45,  7.05s/it]
                                                          
{'loss': 0.5881, 'learning_rate': 2.5564638844366687e-05, 'epoch': 10.31}

 86%|████████▌ | 24125/28080 [47:39:49<7:44:45,  7.05s/it]
 86%|████████▌ | 24126/28080 [47:39:57<7:46:31,  7.08s/it]
                                                          
{'loss': 0.6041, 'learning_rate': 2.5551937552023284e-05, 'epoch': 10.31}

 86%|████████▌ | 24126/28080 [47:39:57<7:46:31,  7.08s/it]
 86%|████████▌ | 24127/28080 [47:40:04<7:46:36,  7.08s/it]
                                                          
{'loss': 0.6044, 'learning_rate': 2.553923924572979e-05, 'epoch': 10.31}

 86%|████████▌ | 24127/28080 [47:40:04<7:46:36,  7.08s/it]
 86%|████████▌ | 24128/28080 [47:40:11<7:46:25,  7.08s/it]
                                                          
{'loss': 0.5984, 'learning_rate': 2.5526543925655177e-05, 'epoch': 10.31}

 86%|████████▌ | 24128/28080 [47:40:11<7:46:25,  7.08s/it]
 86%|████████▌ | 24129/28080 [47:40:18<7:50:21,  7.14s/it]
                                                          
{'loss': 0.583, 'learning_rate': 2.551385159196823e-05, 'epoch': 10.31}

 86%|████████▌ | 24129/28080 [47:40:18<7:50:21,  7.14s/it]
 86%|████████▌ | 24130/28080 [47:40:25<7:51:19,  7.16s/it]
                                                          
{'loss': 0.6036, 'learning_rate': 2.550116224483798e-05, 'epoch': 10.31}

 86%|████████▌ | 24130/28080 [47:40:25<7:51:19,  7.16s/it]
 86%|████████▌ | 24131/28080 [47:40:32<7:46:54,  7.09s/it]
                                                          
{'loss': 0.6158, 'learning_rate': 2.5488475884433094e-05, 'epoch': 10.31}

 86%|████████▌ | 24131/28080 [47:40:32<7:46:54,  7.09s/it]
 86%|████████▌ | 24132/28080 [47:40:39<7:47:19,  7.10s/it]
                                                          
{'loss': 0.5838, 'learning_rate': 2.547579251092255e-05, 'epoch': 10.31}

 86%|████████▌ | 24132/28080 [47:40:39<7:47:19,  7.10s/it]
 86%|████████▌ | 24133/28080 [47:40:46<7:47:08,  7.10s/it]
                                                          
{'loss': 0.6034, 'learning_rate': 2.546311212447483e-05, 'epoch': 10.31}

 86%|████████▌ | 24133/28080 [47:40:46<7:47:08,  7.10s/it]
 86%|████████▌ | 24134/28080 [47:40:53<7:48:21,  7.12s/it]
                                                          
{'loss': 0.6041, 'learning_rate': 2.545043472525882e-05, 'epoch': 10.31}

 86%|████████▌ | 24134/28080 [47:40:53<7:48:21,  7.12s/it]
 86%|████████▌ | 24135/28080 [47:41:01<7:47:15,  7.11s/it]
                                                          
{'loss': 0.6028, 'learning_rate': 2.543776031344308e-05, 'epoch': 10.31}

 86%|████████▌ | 24135/28080 [47:41:01<7:47:15,  7.11s/it]
 86%|████████▌ | 24136/28080 [47:41:08<7:48:15,  7.12s/it]
                                                          
{'loss': 0.5952, 'learning_rate': 2.542508888919631e-05, 'epoch': 10.31}

 86%|████████▌ | 24136/28080 [47:41:08<7:48:15,  7.12s/it]
 86%|████████▌ | 24137/28080 [47:41:15<7:48:30,  7.13s/it]
                                                          
{'loss': 0.5898, 'learning_rate': 2.5412420452687047e-05, 'epoch': 10.31}

 86%|████████▌ | 24137/28080 [47:41:15<7:48:30,  7.13s/it]
 86%|████████▌ | 24138/28080 [47:41:22<7:46:55,  7.11s/it]
                                                          
{'loss': 0.6041, 'learning_rate': 2.539975500408384e-05, 'epoch': 10.31}

 86%|████████▌ | 24138/28080 [47:41:22<7:46:55,  7.11s/it]
 86%|████████▌ | 24139/28080 [47:41:29<7:49:14,  7.14s/it]
                                                          
{'loss': 0.6141, 'learning_rate': 2.5387092543555202e-05, 'epoch': 10.31}

 86%|████████▌ | 24139/28080 [47:41:29<7:49:14,  7.14s/it]
 86%|████████▌ | 24140/28080 [47:41:36<7:50:01,  7.16s/it]
                                                          
{'loss': 0.6044, 'learning_rate': 2.537443307126952e-05, 'epoch': 10.31}

 86%|████████▌ | 24140/28080 [47:41:36<7:50:01,  7.16s/it]
 86%|████████▌ | 24141/28080 [47:41:43<7:48:11,  7.13s/it]
                                                          
{'loss': 0.6007, 'learning_rate': 2.53617765873953e-05, 'epoch': 10.31}

 86%|████████▌ | 24141/28080 [47:41:43<7:48:11,  7.13s/it]
 86%|████████▌ | 24142/28080 [47:41:50<7:46:34,  7.11s/it]
                                                          
{'loss': 0.6157, 'learning_rate': 2.5349123092100912e-05, 'epoch': 10.31}

 86%|████████▌ | 24142/28080 [47:41:50<7:46:34,  7.11s/it]
 86%|████████▌ | 24143/28080 [47:41:58<7:47:11,  7.12s/it]
                                                          
{'loss': 0.5802, 'learning_rate': 2.5336472585554687e-05, 'epoch': 10.31}

 86%|████████▌ | 24143/28080 [47:41:58<7:47:11,  7.12s/it]
 86%|████████▌ | 24144/28080 [47:42:05<7:47:43,  7.13s/it]
                                                          
{'loss': 0.5811, 'learning_rate': 2.5323825067924854e-05, 'epoch': 10.31}

 86%|████████▌ | 24144/28080 [47:42:05<7:47:43,  7.13s/it]
 86%|████████▌ | 24145/28080 [47:42:12<7:47:49,  7.13s/it]
                                                          
{'loss': 0.6079, 'learning_rate': 2.5311180539379808e-05, 'epoch': 10.31}

 86%|████████▌ | 24145/28080 [47:42:12<7:47:49,  7.13s/it]
 86%|████████▌ | 24146/28080 [47:42:19<7:45:15,  7.10s/it]
                                                          
{'loss': 0.6116, 'learning_rate': 2.5298539000087663e-05, 'epoch': 10.31}

 86%|████████▌ | 24146/28080 [47:42:19<7:45:15,  7.10s/it]
 86%|████████▌ | 24147/28080 [47:42:26<7:47:31,  7.13s/it]
                                                          
{'loss': 0.5939, 'learning_rate': 2.5285900450216725e-05, 'epoch': 10.32}

 86%|████████▌ | 24147/28080 [47:42:26<7:47:31,  7.13s/it]
 86%|████████▌ | 24148/28080 [47:42:33<7:46:06,  7.11s/it]
                                                          
{'loss': 0.6358, 'learning_rate': 2.527326488993498e-05, 'epoch': 10.32}

 86%|████████▌ | 24148/28080 [47:42:33<7:46:06,  7.11s/it]
 86%|████████▌ | 24149/28080 [47:42:40<7:46:24,  7.12s/it]
                                                          
{'loss': 0.6174, 'learning_rate': 2.5260632319410643e-05, 'epoch': 10.32}

 86%|████████▌ | 24149/28080 [47:42:40<7:46:24,  7.12s/it]
 86%|████████▌ | 24150/28080 [47:42:48<7:48:38,  7.15s/it]
                                                          
{'loss': 0.6155, 'learning_rate': 2.52480027388117e-05, 'epoch': 10.32}

 86%|████████▌ | 24150/28080 [47:42:48<7:48:38,  7.15s/it]
 86%|████████▌ | 24151/28080 [47:42:55<7:45:41,  7.11s/it]
                                                          
{'loss': 0.5768, 'learning_rate': 2.523537614830626e-05, 'epoch': 10.32}

 86%|████████▌ | 24151/28080 [47:42:55<7:45:41,  7.11s/it]
 86%|████████▌ | 24152/28080 [47:43:02<7:46:39,  7.13s/it]
                                                          
{'loss': 0.5819, 'learning_rate': 2.5222752548062278e-05, 'epoch': 10.32}

 86%|████████▌ | 24152/28080 [47:43:02<7:46:39,  7.13s/it]
 86%|████████▌ | 24153/28080 [47:43:09<7:46:08,  7.12s/it]
                                                          
{'loss': 0.5942, 'learning_rate': 2.521013193824767e-05, 'epoch': 10.32}

 86%|████████▌ | 24153/28080 [47:43:09<7:46:08,  7.12s/it]
 86%|████████▌ | 24154/28080 [47:43:16<7:46:13,  7.13s/it]
                                                          
{'loss': 0.6115, 'learning_rate': 2.5197514319030307e-05, 'epoch': 10.32}

 86%|████████▌ | 24154/28080 [47:43:16<7:46:13,  7.13s/it]
 86%|████████▌ | 24155/28080 [47:43:23<7:46:42,  7.13s/it]
                                                          
{'loss': 0.6049, 'learning_rate': 2.5184899690578133e-05, 'epoch': 10.32}

 86%|████████▌ | 24155/28080 [47:43:23<7:46:42,  7.13s/it]
 86%|████████▌ | 24156/28080 [47:43:30<7:44:49,  7.11s/it]
                                                          
{'loss': 0.6025, 'learning_rate': 2.517228805305896e-05, 'epoch': 10.32}

 86%|████████▌ | 24156/28080 [47:43:30<7:44:49,  7.11s/it]
 86%|████████▌ | 24157/28080 [47:43:37<7:45:01,  7.11s/it]
                                                          
{'loss': 0.5877, 'learning_rate': 2.5159679406640547e-05, 'epoch': 10.32}

 86%|████████▌ | 24157/28080 [47:43:37<7:45:01,  7.11s/it]
 86%|████████▌ | 24158/28080 [47:43:44<7:45:30,  7.12s/it]
                                                          
{'loss': 0.6075, 'learning_rate': 2.5147073751490583e-05, 'epoch': 10.32}

 86%|████████▌ | 24158/28080 [47:43:44<7:45:30,  7.12s/it]
 86%|████████▌ | 24159/28080 [47:43:52<7:47:15,  7.15s/it]
                                                          
{'loss': 0.6183, 'learning_rate': 2.5134471087776915e-05, 'epoch': 10.32}

 86%|████████▌ | 24159/28080 [47:43:52<7:47:15,  7.15s/it]
 86%|████████▌ | 24160/28080 [47:43:59<7:47:42,  7.16s/it]
                                                          
{'loss': 0.5812, 'learning_rate': 2.5121871415667048e-05, 'epoch': 10.32}

 86%|████████▌ | 24160/28080 [47:43:59<7:47:42,  7.16s/it]
 86%|████████▌ | 24161/28080 [47:44:06<7:46:37,  7.14s/it]
                                                          
{'loss': 0.587, 'learning_rate': 2.5109274735328813e-05, 'epoch': 10.32}

 86%|████████▌ | 24161/28080 [47:44:06<7:46:37,  7.14s/it]
 86%|████████▌ | 24162/28080 [47:44:13<7:45:48,  7.13s/it]
                                                          
{'loss': 0.5699, 'learning_rate': 2.5096681046929607e-05, 'epoch': 10.32}

 86%|████████▌ | 24162/28080 [47:44:13<7:45:48,  7.13s/it]
 86%|████████▌ | 24163/28080 [47:44:20<7:45:16,  7.13s/it]
                                                          
{'loss': 0.607, 'learning_rate': 2.5084090350636995e-05, 'epoch': 10.32}

 86%|████████▌ | 24163/28080 [47:44:20<7:45:16,  7.13s/it]
 86%|████████▌ | 24164/28080 [47:44:27<7:44:05,  7.11s/it]
                                                          
{'loss': 0.598, 'learning_rate': 2.507150264661856e-05, 'epoch': 10.32}

 86%|████████▌ | 24164/28080 [47:44:27<7:44:05,  7.11s/it]
 86%|████████▌ | 24165/28080 [47:44:34<7:44:54,  7.13s/it]
                                                          
{'loss': 0.6065, 'learning_rate': 2.5058917935041698e-05, 'epoch': 10.32}

 86%|████████▌ | 24165/28080 [47:44:34<7:44:54,  7.13s/it]
 86%|████████▌ | 24166/28080 [47:44:41<7:43:16,  7.10s/it]
                                                          
{'loss': 0.5857, 'learning_rate': 2.5046336216073995e-05, 'epoch': 10.32}

 86%|████████▌ | 24166/28080 [47:44:41<7:43:16,  7.10s/it]
 86%|████████▌ | 24167/28080 [47:44:49<7:44:42,  7.13s/it]
                                                          
{'loss': 0.6113, 'learning_rate': 2.5033757489882596e-05, 'epoch': 10.32}

 86%|████████▌ | 24167/28080 [47:44:49<7:44:42,  7.13s/it]
 86%|████████▌ | 24168/28080 [47:44:56<7:42:56,  7.10s/it]
                                                          
{'loss': 0.6168, 'learning_rate': 2.5021181756635008e-05, 'epoch': 10.32}

 86%|████████▌ | 24168/28080 [47:44:56<7:42:56,  7.10s/it]
 86%|████████▌ | 24169/28080 [47:45:03<7:41:12,  7.08s/it]
                                                          
{'loss': 0.6033, 'learning_rate': 2.5008609016498458e-05, 'epoch': 10.32}

 86%|████████▌ | 24169/28080 [47:45:03<7:41:12,  7.08s/it]
 86%|████████▌ | 24170/28080 [47:45:10<7:43:41,  7.12s/it]
                                                          
{'loss': 0.5952, 'learning_rate': 2.4996039269640307e-05, 'epoch': 10.33}

 86%|████████▌ | 24170/28080 [47:45:10<7:43:41,  7.12s/it]
 86%|████████▌ | 24171/28080 [47:45:17<7:43:01,  7.11s/it]
                                                          
{'loss': 0.6017, 'learning_rate': 2.4983472516227735e-05, 'epoch': 10.33}

 86%|████████▌ | 24171/28080 [47:45:17<7:43:01,  7.11s/it]
 86%|████████▌ | 24172/28080 [47:45:24<7:44:15,  7.13s/it]
                                                          
{'loss': 0.6097, 'learning_rate': 2.4970908756427934e-05, 'epoch': 10.33}

 86%|████████▌ | 24172/28080 [47:45:24<7:44:15,  7.13s/it]
 86%|████████▌ | 24173/28080 [47:45:31<7:45:09,  7.14s/it]
                                                          
{'loss': 0.6045, 'learning_rate': 2.495834799040797e-05, 'epoch': 10.33}

 86%|████████▌ | 24173/28080 [47:45:31<7:45:09,  7.14s/it]
 86%|████████▌ | 24174/28080 [47:45:38<7:41:07,  7.08s/it]
                                                          
{'loss': 0.5816, 'learning_rate': 2.4945790218335096e-05, 'epoch': 10.33}

 86%|████████▌ | 24174/28080 [47:45:38<7:41:07,  7.08s/it]
 86%|████████▌ | 24175/28080 [47:45:45<7:39:52,  7.07s/it]
                                                          
{'loss': 0.614, 'learning_rate': 2.493323544037629e-05, 'epoch': 10.33}

 86%|████████▌ | 24175/28080 [47:45:45<7:39:52,  7.07s/it]
 86%|████████▌ | 24176/28080 [47:45:52<7:41:04,  7.09s/it]
                                                          
{'loss': 0.5899, 'learning_rate': 2.492068365669861e-05, 'epoch': 10.33}

 86%|████████▌ | 24176/28080 [47:45:52<7:41:04,  7.09s/it]
 86%|████████▌ | 24177/28080 [47:46:00<7:41:52,  7.10s/it]
                                                          
{'loss': 0.5885, 'learning_rate': 2.4908134867468958e-05, 'epoch': 10.33}

 86%|████████▌ | 24177/28080 [47:46:00<7:41:52,  7.10s/it]
 86%|████████▌ | 24178/28080 [47:46:07<7:43:54,  7.13s/it]
                                                          
{'loss': 0.6157, 'learning_rate': 2.489558907285444e-05, 'epoch': 10.33}

 86%|████████▌ | 24178/28080 [47:46:07<7:43:54,  7.13s/it]
 86%|████████▌ | 24179/28080 [47:46:14<7:42:35,  7.11s/it]
                                                          
{'loss': 0.5993, 'learning_rate': 2.488304627302182e-05, 'epoch': 10.33}

 86%|████████▌ | 24179/28080 [47:46:14<7:42:35,  7.11s/it]
 86%|████████▌ | 24180/28080 [47:46:21<7:41:36,  7.10s/it]
                                                          
{'loss': 0.5773, 'learning_rate': 2.48705064681381e-05, 'epoch': 10.33}

 86%|████████▌ | 24180/28080 [47:46:21<7:41:36,  7.10s/it]
 86%|████████▌ | 24181/28080 [47:46:28<7:41:44,  7.11s/it]
                                                          
{'loss': 0.5955, 'learning_rate': 2.485796965836998e-05, 'epoch': 10.33}

 86%|████████▌ | 24181/28080 [47:46:28<7:41:44,  7.11s/it]
 86%|████████▌ | 24182/28080 [47:46:35<7:43:08,  7.13s/it]
                                                          
{'loss': 0.6027, 'learning_rate': 2.4845435843884323e-05, 'epoch': 10.33}

 86%|████████▌ | 24182/28080 [47:46:35<7:43:08,  7.13s/it]
 86%|████████▌ | 24183/28080 [47:46:42<7:42:46,  7.12s/it]
                                                          
{'loss': 0.5933, 'learning_rate': 2.4832905024847835e-05, 'epoch': 10.33}

 86%|████████▌ | 24183/28080 [47:46:42<7:42:46,  7.12s/it]
 86%|████████▌ | 24184/28080 [47:46:49<7:42:40,  7.13s/it]
                                                          
{'loss': 0.5892, 'learning_rate': 2.4820377201427295e-05, 'epoch': 10.33}

 86%|████████▌ | 24184/28080 [47:46:49<7:42:40,  7.13s/it]
 86%|████████▌ | 24185/28080 [47:46:57<7:43:31,  7.14s/it]
                                                          
{'loss': 0.5919, 'learning_rate': 2.4807852373789353e-05, 'epoch': 10.33}

 86%|████████▌ | 24185/28080 [47:46:57<7:43:31,  7.14s/it]
 86%|████████▌ | 24186/28080 [47:47:04<7:41:56,  7.12s/it]
                                                          
{'loss': 0.6021, 'learning_rate': 2.479533054210059e-05, 'epoch': 10.33}

 86%|████████▌ | 24186/28080 [47:47:04<7:41:56,  7.12s/it]
 86%|████████▌ | 24187/28080 [47:47:11<7:40:42,  7.10s/it]
                                                          
{'loss': 0.6055, 'learning_rate': 2.478281170652763e-05, 'epoch': 10.33}

 86%|████████▌ | 24187/28080 [47:47:11<7:40:42,  7.10s/it]
 86%|████████▌ | 24188/28080 [47:47:18<7:40:37,  7.10s/it]
                                                          
{'loss': 0.6037, 'learning_rate': 2.4770295867236975e-05, 'epoch': 10.33}

 86%|████████▌ | 24188/28080 [47:47:18<7:40:37,  7.10s/it]
 86%|████████▌ | 24189/28080 [47:47:25<7:40:28,  7.10s/it]
                                                          
{'loss': 0.6134, 'learning_rate': 2.4757783024395242e-05, 'epoch': 10.33}

 86%|████████▌ | 24189/28080 [47:47:25<7:40:28,  7.10s/it]
 86%|████████▌ | 24190/28080 [47:47:32<7:38:57,  7.08s/it]
                                                          
{'loss': 0.5978, 'learning_rate': 2.4745273178168798e-05, 'epoch': 10.33}

 86%|████████▌ | 24190/28080 [47:47:32<7:38:57,  7.08s/it]
 86%|████████▌ | 24191/28080 [47:47:39<7:39:45,  7.09s/it]
                                                          
{'loss': 0.5847, 'learning_rate': 2.4732766328724148e-05, 'epoch': 10.33}

 86%|████████▌ | 24191/28080 [47:47:39<7:39:45,  7.09s/it]
 86%|████████▌ | 24192/28080 [47:47:46<7:38:48,  7.08s/it]
                                                          
{'loss': 0.6041, 'learning_rate': 2.472026247622758e-05, 'epoch': 10.33}

 86%|████████▌ | 24192/28080 [47:47:46<7:38:48,  7.08s/it]
 86%|████████▌ | 24193/28080 [47:47:53<7:39:33,  7.09s/it]
                                                          
{'loss': 0.6276, 'learning_rate': 2.4707761620845536e-05, 'epoch': 10.34}

 86%|████████▌ | 24193/28080 [47:47:53<7:39:33,  7.09s/it]
 86%|████████▌ | 24194/28080 [47:48:00<7:39:49,  7.10s/it]
                                                          
{'loss': 0.576, 'learning_rate': 2.4695263762744335e-05, 'epoch': 10.34}

 86%|████████▌ | 24194/28080 [47:48:00<7:39:49,  7.10s/it]
 86%|████████▌ | 24195/28080 [47:48:08<7:40:15,  7.11s/it]
                                                          
{'loss': 0.5851, 'learning_rate': 2.4682768902090203e-05, 'epoch': 10.34}

 86%|████████▌ | 24195/28080 [47:48:08<7:40:15,  7.11s/it]
 86%|████████▌ | 24196/28080 [47:48:15<7:39:24,  7.10s/it]
                                                          
{'loss': 0.6304, 'learning_rate': 2.4670277039049364e-05, 'epoch': 10.34}

 86%|████████▌ | 24196/28080 [47:48:15<7:39:24,  7.10s/it]
 86%|████████▌ | 24197/28080 [47:48:22<7:39:10,  7.10s/it]
                                                          
{'loss': 0.602, 'learning_rate': 2.4657788173788054e-05, 'epoch': 10.34}

 86%|████████▌ | 24197/28080 [47:48:22<7:39:10,  7.10s/it]
 86%|████████▌ | 24198/28080 [47:48:29<7:38:48,  7.09s/it]
                                                          
{'loss': 0.5982, 'learning_rate': 2.4645302306472327e-05, 'epoch': 10.34}

 86%|████████▌ | 24198/28080 [47:48:29<7:38:48,  7.09s/it]
 86%|████████▌ | 24199/28080 [47:48:36<7:36:33,  7.06s/it]
                                                          
{'loss': 0.6066, 'learning_rate': 2.4632819437268444e-05, 'epoch': 10.34}

 86%|████████▌ | 24199/28080 [47:48:36<7:36:33,  7.06s/it]
 86%|████████▌ | 24200/28080 [47:48:43<7:36:10,  7.05s/it]
                                                          
{'loss': 0.6209, 'learning_rate': 2.462033956634241e-05, 'epoch': 10.34}

 86%|████████▌ | 24200/28080 [47:48:43<7:36:10,  7.05s/it]
 86%|████████▌ | 24201/28080 [47:48:50<7:34:59,  7.04s/it]
                                                          
{'loss': 0.6049, 'learning_rate': 2.4607862693860227e-05, 'epoch': 10.34}

 86%|████████▌ | 24201/28080 [47:48:50<7:34:59,  7.04s/it]
 86%|████████▌ | 24202/28080 [47:48:57<7:37:20,  7.08s/it]
                                                          
{'loss': 0.6029, 'learning_rate': 2.459538881998785e-05, 'epoch': 10.34}

 86%|████████▌ | 24202/28080 [47:48:57<7:37:20,  7.08s/it]
 86%|████████▌ | 24203/28080 [47:49:04<7:39:26,  7.11s/it]
                                                          
{'loss': 0.5933, 'learning_rate': 2.458291794489137e-05, 'epoch': 10.34}

 86%|████████▌ | 24203/28080 [47:49:04<7:39:26,  7.11s/it]
 86%|████████▌ | 24204/28080 [47:49:11<7:38:36,  7.10s/it]
                                                          
{'loss': 0.607, 'learning_rate': 2.4570450068736593e-05, 'epoch': 10.34}

 86%|████████▌ | 24204/28080 [47:49:11<7:38:36,  7.10s/it]
 86%|████████▌ | 24205/28080 [47:49:18<7:39:21,  7.11s/it]
                                                          
{'loss': 0.5964, 'learning_rate': 2.455798519168942e-05, 'epoch': 10.34}

 86%|████████▌ | 24205/28080 [47:49:18<7:39:21,  7.11s/it]
 86%|████████▌ | 24206/28080 [47:49:26<7:40:56,  7.14s/it]
                                                          
{'loss': 0.5877, 'learning_rate': 2.4545523313915628e-05, 'epoch': 10.34}

 86%|████████▌ | 24206/28080 [47:49:26<7:40:56,  7.14s/it]
 86%|████████▌ | 24207/28080 [47:49:33<7:39:48,  7.12s/it]
                                                          
{'loss': 0.5918, 'learning_rate': 2.4533064435581122e-05, 'epoch': 10.34}

 86%|████████▌ | 24207/28080 [47:49:33<7:39:48,  7.12s/it]
 86%|████████▌ | 24208/28080 [47:49:40<7:39:10,  7.12s/it]
                                                          
{'loss': 0.5942, 'learning_rate': 2.452060855685151e-05, 'epoch': 10.34}

 86%|████████▌ | 24208/28080 [47:49:40<7:39:10,  7.12s/it]
 86%|████████▌ | 24209/28080 [47:49:47<7:37:40,  7.09s/it]
                                                          
{'loss': 0.6204, 'learning_rate': 2.450815567789272e-05, 'epoch': 10.34}

 86%|████████▌ | 24209/28080 [47:49:47<7:37:40,  7.09s/it]
 86%|████████▌ | 24210/28080 [47:49:54<7:37:02,  7.09s/it]
                                                          
{'loss': 0.5879, 'learning_rate': 2.4495705798870173e-05, 'epoch': 10.34}

 86%|████████▌ | 24210/28080 [47:49:54<7:37:02,  7.09s/it]
 86%|████████▌ | 24211/28080 [47:50:01<7:35:08,  7.06s/it]
                                                          
{'loss': 0.6026, 'learning_rate': 2.4483258919949682e-05, 'epoch': 10.34}

 86%|████████▌ | 24211/28080 [47:50:01<7:35:08,  7.06s/it]
 86%|████████▌ | 24212/28080 [47:50:08<7:35:41,  7.07s/it]
                                                          
{'loss': 0.5996, 'learning_rate': 2.447081504129678e-05, 'epoch': 10.34}

 86%|████████▌ | 24212/28080 [47:50:08<7:35:41,  7.07s/it]
 86%|████████▌ | 24213/28080 [47:50:15<7:36:35,  7.08s/it]
                                                          
{'loss': 0.6103, 'learning_rate': 2.4458374163076948e-05, 'epoch': 10.34}

 86%|████████▌ | 24213/28080 [47:50:15<7:36:35,  7.08s/it]
 86%|████████▌ | 24214/28080 [47:50:22<7:36:31,  7.09s/it]
                                                          
{'loss': 0.6164, 'learning_rate': 2.4445936285455884e-05, 'epoch': 10.34}

 86%|████████▌ | 24214/28080 [47:50:22<7:36:31,  7.09s/it]
 86%|████████▌ | 24215/28080 [47:50:29<7:36:10,  7.08s/it]
                                                          
{'loss': 0.6052, 'learning_rate': 2.4433501408598846e-05, 'epoch': 10.34}

 86%|████████▌ | 24215/28080 [47:50:29<7:36:10,  7.08s/it]
 86%|████████▌ | 24216/28080 [47:50:36<7:36:13,  7.08s/it]
                                                          
{'loss': 0.5922, 'learning_rate': 2.4421069532671425e-05, 'epoch': 10.34}

 86%|████████▌ | 24216/28080 [47:50:36<7:36:13,  7.08s/it]
 86%|████████▌ | 24217/28080 [47:50:43<7:35:55,  7.08s/it]
                                                          
{'loss': 0.6238, 'learning_rate': 2.4408640657838904e-05, 'epoch': 10.35}

 86%|████████▌ | 24217/28080 [47:50:43<7:35:55,  7.08s/it]
 86%|████████▌ | 24218/28080 [47:50:50<7:35:20,  7.07s/it]
                                                          
{'loss': 0.5997, 'learning_rate': 2.4396214784266735e-05, 'epoch': 10.35}

 86%|████████▌ | 24218/28080 [47:50:50<7:35:20,  7.07s/it]
 86%|████████▋ | 24219/28080 [47:50:58<7:35:05,  7.07s/it]
                                                          
{'loss': 0.5948, 'learning_rate': 2.4383791912120172e-05, 'epoch': 10.35}

 86%|████████▋ | 24219/28080 [47:50:58<7:35:05,  7.07s/it]
 86%|████████▋ | 24220/28080 [47:51:05<7:34:48,  7.07s/it]
                                                          
{'loss': 0.6022, 'learning_rate': 2.4371372041564505e-05, 'epoch': 10.35}

 86%|████████▋ | 24220/28080 [47:51:05<7:34:48,  7.07s/it]
 86%|████████▋ | 24221/28080 [47:51:12<7:35:36,  7.08s/it]
                                                          
{'loss': 0.5944, 'learning_rate': 2.4358955172764928e-05, 'epoch': 10.35}

 86%|████████▋ | 24221/28080 [47:51:12<7:35:36,  7.08s/it]
 86%|████████▋ | 24222/28080 [47:51:19<7:35:15,  7.08s/it]
                                                          
{'loss': 0.6105, 'learning_rate': 2.434654130588673e-05, 'epoch': 10.35}

 86%|████████▋ | 24222/28080 [47:51:19<7:35:15,  7.08s/it]
 86%|████████▋ | 24223/28080 [47:51:26<7:34:25,  7.07s/it]
                                                          
{'loss': 0.6204, 'learning_rate': 2.4334130441095003e-05, 'epoch': 10.35}

 86%|████████▋ | 24223/28080 [47:51:26<7:34:25,  7.07s/it]
 86%|████████▋ | 24224/28080 [47:51:33<7:35:25,  7.09s/it]
                                                          
{'loss': 0.609, 'learning_rate': 2.4321722578554834e-05, 'epoch': 10.35}

 86%|████████▋ | 24224/28080 [47:51:33<7:35:25,  7.09s/it]
 86%|████████▋ | 24225/28080 [47:51:40<7:35:09,  7.08s/it]
                                                          
{'loss': 0.6062, 'learning_rate': 2.430931771843131e-05, 'epoch': 10.35}

 86%|████████▋ | 24225/28080 [47:51:40<7:35:09,  7.08s/it]
 86%|████████▋ | 24226/28080 [47:51:47<7:35:17,  7.09s/it]
                                                          
{'loss': 0.6134, 'learning_rate': 2.4296915860889528e-05, 'epoch': 10.35}

 86%|████████▋ | 24226/28080 [47:51:47<7:35:17,  7.09s/it]
 86%|████████▋ | 24227/28080 [47:51:54<7:36:32,  7.11s/it]
                                                          
{'loss': 0.5826, 'learning_rate': 2.4284517006094383e-05, 'epoch': 10.35}

 86%|████████▋ | 24227/28080 [47:51:54<7:36:32,  7.11s/it]
 86%|████████▋ | 24228/28080 [47:52:01<7:37:03,  7.12s/it]
                                                          
{'loss': 0.5801, 'learning_rate': 2.427212115421096e-05, 'epoch': 10.35}

 86%|████████▋ | 24228/28080 [47:52:01<7:37:03,  7.12s/it]
 86%|████████▋ | 24229/28080 [47:52:09<7:36:00,  7.10s/it]
                                                          
{'loss': 0.5949, 'learning_rate': 2.4259728305404015e-05, 'epoch': 10.35}

 86%|████████▋ | 24229/28080 [47:52:09<7:36:00,  7.10s/it]
 86%|████████▋ | 24230/28080 [47:52:16<7:35:17,  7.10s/it]
                                                          
{'loss': 0.619, 'learning_rate': 2.4247338459838535e-05, 'epoch': 10.35}

 86%|████████▋ | 24230/28080 [47:52:16<7:35:17,  7.10s/it]
 86%|████████▋ | 24231/28080 [47:52:23<7:35:54,  7.11s/it]
                                                          
{'loss': 0.5844, 'learning_rate': 2.4234951617679302e-05, 'epoch': 10.35}

 86%|████████▋ | 24231/28080 [47:52:23<7:35:54,  7.11s/it]
 86%|████████▋ | 24232/28080 [47:52:30<7:35:13,  7.10s/it]
                                                          
{'loss': 0.5875, 'learning_rate': 2.4222567779091154e-05, 'epoch': 10.35}

 86%|████████▋ | 24232/28080 [47:52:30<7:35:13,  7.10s/it]
 86%|████████▋ | 24233/28080 [47:52:37<7:35:27,  7.10s/it]
                                                          
{'loss': 0.5947, 'learning_rate': 2.421018694423882e-05, 'epoch': 10.35}

 86%|████████▋ | 24233/28080 [47:52:37<7:35:27,  7.10s/it]
 86%|████████▋ | 24234/28080 [47:52:44<7:37:04,  7.13s/it]
                                                          
{'loss': 0.6036, 'learning_rate': 2.4197809113287033e-05, 'epoch': 10.35}

 86%|████████▋ | 24234/28080 [47:52:44<7:37:04,  7.13s/it]
 86%|████████▋ | 24235/28080 [47:52:51<7:35:33,  7.11s/it]
                                                          
{'loss': 0.5798, 'learning_rate': 2.4185434286400383e-05, 'epoch': 10.35}

 86%|████████▋ | 24235/28080 [47:52:51<7:35:33,  7.11s/it]
 86%|████████▋ | 24236/28080 [47:52:58<7:35:10,  7.10s/it]
                                                          
{'loss': 0.591, 'learning_rate': 2.4173062463743624e-05, 'epoch': 10.35}

 86%|████████▋ | 24236/28080 [47:52:58<7:35:10,  7.10s/it]
 86%|████████▋ | 24237/28080 [47:53:05<7:35:05,  7.11s/it]
                                                          
{'loss': 0.6121, 'learning_rate': 2.416069364548129e-05, 'epoch': 10.35}

 86%|████████▋ | 24237/28080 [47:53:05<7:35:05,  7.11s/it]
 86%|████████▋ | 24238/28080 [47:53:12<7:34:22,  7.10s/it]
                                                          
{'loss': 0.5784, 'learning_rate': 2.414832783177795e-05, 'epoch': 10.35}

 86%|████████▋ | 24238/28080 [47:53:12<7:34:22,  7.10s/it]
 86%|████████▋ | 24239/28080 [47:53:20<7:33:31,  7.08s/it]
                                                          
{'loss': 0.6101, 'learning_rate': 2.4135965022798107e-05, 'epoch': 10.35}

 86%|████████▋ | 24239/28080 [47:53:20<7:33:31,  7.08s/it]
 86%|████████▋ | 24240/28080 [47:53:27<7:34:33,  7.10s/it]
                                                          
{'loss': 0.5969, 'learning_rate': 2.4123605218706185e-05, 'epoch': 10.36}

 86%|████████▋ | 24240/28080 [47:53:27<7:34:33,  7.10s/it]
 86%|████████▋ | 24241/28080 [47:53:34<7:35:23,  7.12s/it]
                                                          
{'loss': 0.602, 'learning_rate': 2.411124841966672e-05, 'epoch': 10.36}

 86%|████████▋ | 24241/28080 [47:53:34<7:35:23,  7.12s/it]
 86%|████████▋ | 24242/28080 [47:53:41<7:37:59,  7.16s/it]
                                                          
{'loss': 0.5875, 'learning_rate': 2.409889462584408e-05, 'epoch': 10.36}

 86%|████████▋ | 24242/28080 [47:53:41<7:37:59,  7.16s/it]
 86%|████████▋ | 24243/28080 [47:53:48<7:37:58,  7.16s/it]
                                                          
{'loss': 0.6113, 'learning_rate': 2.408654383740258e-05, 'epoch': 10.36}

 86%|████████▋ | 24243/28080 [47:53:48<7:37:58,  7.16s/it]
 86%|████████▋ | 24244/28080 [47:53:55<7:36:01,  7.13s/it]
                                                          
{'loss': 0.6003, 'learning_rate': 2.4074196054506502e-05, 'epoch': 10.36}

 86%|████████▋ | 24244/28080 [47:53:55<7:36:01,  7.13s/it]
 86%|████████▋ | 24245/28080 [47:54:02<7:34:20,  7.11s/it]
                                                          
{'loss': 0.6025, 'learning_rate': 2.4061851277320217e-05, 'epoch': 10.36}

 86%|████████▋ | 24245/28080 [47:54:02<7:34:20,  7.11s/it]
 86%|████████▋ | 24246/28080 [47:54:09<7:33:10,  7.09s/it]
                                                          
{'loss': 0.6081, 'learning_rate': 2.4049509506007873e-05, 'epoch': 10.36}

 86%|████████▋ | 24246/28080 [47:54:09<7:33:10,  7.09s/it]
 86%|████████▋ | 24247/28080 [47:54:16<7:32:07,  7.08s/it]
                                                          
{'loss': 0.6125, 'learning_rate': 2.403717074073375e-05, 'epoch': 10.36}

 86%|████████▋ | 24247/28080 [47:54:16<7:32:07,  7.08s/it]
 86%|████████▋ | 24248/28080 [47:54:24<7:31:41,  7.07s/it]
                                                          
{'loss': 0.5995, 'learning_rate': 2.4024834981661943e-05, 'epoch': 10.36}

 86%|████████▋ | 24248/28080 [47:54:24<7:31:41,  7.07s/it]
 86%|████████▋ | 24249/28080 [47:54:31<7:30:42,  7.06s/it]
                                                          
{'loss': 0.6142, 'learning_rate': 2.4012502228956597e-05, 'epoch': 10.36}

 86%|████████▋ | 24249/28080 [47:54:31<7:30:42,  7.06s/it]
 86%|████████▋ | 24250/28080 [47:54:38<7:32:52,  7.09s/it]
                                                          
{'loss': 0.5918, 'learning_rate': 2.4000172482781717e-05, 'epoch': 10.36}

 86%|████████▋ | 24250/28080 [47:54:38<7:32:52,  7.09s/it]
 86%|████████▋ | 24251/28080 [47:54:45<7:33:59,  7.11s/it]
                                                          
{'loss': 0.6015, 'learning_rate': 2.3987845743301458e-05, 'epoch': 10.36}

 86%|████████▋ | 24251/28080 [47:54:45<7:33:59,  7.11s/it]
 86%|████████▋ | 24252/28080 [47:54:52<7:34:16,  7.12s/it]
                                                          
{'loss': 0.6086, 'learning_rate': 2.3975522010679735e-05, 'epoch': 10.36}

 86%|████████▋ | 24252/28080 [47:54:52<7:34:16,  7.12s/it]
 86%|████████▋ | 24253/28080 [47:54:59<7:33:20,  7.11s/it]
                                                          
{'loss': 0.5969, 'learning_rate': 2.3963201285080506e-05, 'epoch': 10.36}

 86%|████████▋ | 24253/28080 [47:54:59<7:33:20,  7.11s/it]
 86%|████████▋ | 24254/28080 [47:55:06<7:32:41,  7.10s/it]
                                                          
{'loss': 0.595, 'learning_rate': 2.3950883566667662e-05, 'epoch': 10.36}

 86%|████████▋ | 24254/28080 [47:55:06<7:32:41,  7.10s/it]
 86%|████████▋ | 24255/28080 [47:55:13<7:33:34,  7.11s/it]
                                                          
{'loss': 0.6014, 'learning_rate': 2.3938568855605135e-05, 'epoch': 10.36}

 86%|████████▋ | 24255/28080 [47:55:13<7:33:34,  7.11s/it]
 86%|████████▋ | 24256/28080 [47:55:20<7:30:06,  7.06s/it]
                                                          
{'loss': 0.6031, 'learning_rate': 2.3926257152056763e-05, 'epoch': 10.36}

 86%|████████▋ | 24256/28080 [47:55:20<7:30:06,  7.06s/it]
 86%|████████▋ | 24257/28080 [47:55:27<7:31:59,  7.09s/it]
                                                          
{'loss': 0.61, 'learning_rate': 2.3913948456186303e-05, 'epoch': 10.36}

 86%|████████▋ | 24257/28080 [47:55:27<7:31:59,  7.09s/it]
 86%|████████▋ | 24258/28080 [47:55:35<7:33:30,  7.12s/it]
                                                          
{'loss': 0.6025, 'learning_rate': 2.3901642768157456e-05, 'epoch': 10.36}

 86%|████████▋ | 24258/28080 [47:55:35<7:33:30,  7.12s/it]
 86%|████████▋ | 24259/28080 [47:55:42<7:33:15,  7.12s/it]
                                                          
{'loss': 0.5989, 'learning_rate': 2.3889340088134064e-05, 'epoch': 10.36}

 86%|████████▋ | 24259/28080 [47:55:42<7:33:15,  7.12s/it]
 86%|████████▋ | 24260/28080 [47:55:49<7:34:08,  7.13s/it]
                                                          
{'loss': 0.6189, 'learning_rate': 2.3877040416279666e-05, 'epoch': 10.36}

 86%|████████▋ | 24260/28080 [47:55:49<7:34:08,  7.13s/it]
 86%|████████▋ | 24261/28080 [47:55:56<7:34:39,  7.14s/it]
                                                          
{'loss': 0.606, 'learning_rate': 2.3864743752758044e-05, 'epoch': 10.36}

 86%|████████▋ | 24261/28080 [47:55:56<7:34:39,  7.14s/it]
 86%|████████▋ | 24262/28080 [47:56:03<7:37:46,  7.19s/it]
                                                          
{'loss': 0.6131, 'learning_rate': 2.3852450097732737e-05, 'epoch': 10.36}

 86%|████████▋ | 24262/28080 [47:56:03<7:37:46,  7.19s/it]
 86%|████████▋ | 24263/28080 [47:56:10<7:35:37,  7.16s/it]
                                                          
{'loss': 0.6287, 'learning_rate': 2.3840159451367195e-05, 'epoch': 10.36}

 86%|████████▋ | 24263/28080 [47:56:10<7:35:37,  7.16s/it]
 86%|████████▋ | 24264/28080 [47:56:18<7:36:22,  7.18s/it]
                                                          
{'loss': 0.6023, 'learning_rate': 2.3827871813825065e-05, 'epoch': 10.37}

 86%|████████▋ | 24264/28080 [47:56:18<7:36:22,  7.18s/it]
 86%|████████▋ | 24265/28080 [47:56:25<7:34:29,  7.15s/it]
                                                          
{'loss': 0.6046, 'learning_rate': 2.3815587185269745e-05, 'epoch': 10.37}

 86%|████████▋ | 24265/28080 [47:56:25<7:34:29,  7.15s/it]
 86%|████████▋ | 24266/28080 [47:56:32<7:34:08,  7.14s/it]
                                                          
{'loss': 0.592, 'learning_rate': 2.3803305565864714e-05, 'epoch': 10.37}

 86%|████████▋ | 24266/28080 [47:56:32<7:34:08,  7.14s/it]
 86%|████████▋ | 24267/28080 [47:56:39<7:31:26,  7.10s/it]
                                                          
{'loss': 0.5968, 'learning_rate': 2.3791026955773344e-05, 'epoch': 10.37}

 86%|████████▋ | 24267/28080 [47:56:39<7:31:26,  7.10s/it]
 86%|████████▋ | 24268/28080 [47:56:46<7:30:42,  7.09s/it]
                                                          
{'loss': 0.6106, 'learning_rate': 2.3778751355159027e-05, 'epoch': 10.37}

 86%|████████▋ | 24268/28080 [47:56:46<7:30:42,  7.09s/it]
 86%|████████▋ | 24269/28080 [47:56:53<7:30:39,  7.10s/it]
                                                          
{'loss': 0.6042, 'learning_rate': 2.3766478764184973e-05, 'epoch': 10.37}

 86%|████████▋ | 24269/28080 [47:56:53<7:30:39,  7.10s/it]
 86%|████████▋ | 24270/28080 [47:57:00<7:30:35,  7.10s/it]
                                                          
{'loss': 0.6023, 'learning_rate': 2.3754209183014575e-05, 'epoch': 10.37}

 86%|████████▋ | 24270/28080 [47:57:00<7:30:35,  7.10s/it]
 86%|████████▋ | 24271/28080 [47:57:07<7:30:50,  7.10s/it]
                                                          
{'loss': 0.6023, 'learning_rate': 2.374194261181101e-05, 'epoch': 10.37}

 86%|████████▋ | 24271/28080 [47:57:07<7:30:50,  7.10s/it]
 86%|████████▋ | 24272/28080 [47:57:14<7:32:15,  7.13s/it]
                                                          
{'loss': 0.611, 'learning_rate': 2.37296790507375e-05, 'epoch': 10.37}

 86%|████████▋ | 24272/28080 [47:57:14<7:32:15,  7.13s/it]
 86%|████████▋ | 24273/28080 [47:57:22<7:34:50,  7.17s/it]
                                                          
{'loss': 0.5991, 'learning_rate': 2.371741849995712e-05, 'epoch': 10.37}

 86%|████████▋ | 24273/28080 [47:57:22<7:34:50,  7.17s/it]
 86%|████████▋ | 24274/28080 [47:57:29<7:34:03,  7.16s/it]
                                                          
{'loss': 0.5953, 'learning_rate': 2.3705160959633098e-05, 'epoch': 10.37}

 86%|████████▋ | 24274/28080 [47:57:29<7:34:03,  7.16s/it]
 86%|████████▋ | 24275/28080 [47:57:36<7:34:16,  7.16s/it]
                                                          
{'loss': 0.5778, 'learning_rate': 2.3692906429928413e-05, 'epoch': 10.37}

 86%|████████▋ | 24275/28080 [47:57:36<7:34:16,  7.16s/it]
 86%|████████▋ | 24276/28080 [47:57:43<7:34:09,  7.16s/it]
                                                          
{'loss': 0.5772, 'learning_rate': 2.368065491100621e-05, 'epoch': 10.37}

 86%|████████▋ | 24276/28080 [47:57:43<7:34:09,  7.16s/it]
 86%|████████▋ | 24277/28080 [47:57:50<7:33:31,  7.16s/it]
                                                          
{'loss': 0.596, 'learning_rate': 2.3668406403029337e-05, 'epoch': 10.37}

 86%|████████▋ | 24277/28080 [47:57:50<7:33:31,  7.16s/it]
 86%|████████▋ | 24278/28080 [47:57:57<7:32:28,  7.14s/it]
                                                          
{'loss': 0.5928, 'learning_rate': 2.3656160906160878e-05, 'epoch': 10.37}

 86%|████████▋ | 24278/28080 [47:57:57<7:32:28,  7.14s/it]
 86%|████████▋ | 24279/28080 [47:58:05<7:31:11,  7.12s/it]
                                                          
{'loss': 0.5908, 'learning_rate': 2.3643918420563627e-05, 'epoch': 10.37}

 86%|████████▋ | 24279/28080 [47:58:05<7:31:11,  7.12s/it]
 86%|████████▋ | 24280/28080 [47:58:12<7:28:54,  7.09s/it]
                                                          
{'loss': 0.6126, 'learning_rate': 2.3631678946400587e-05, 'epoch': 10.37}

 86%|████████▋ | 24280/28080 [47:58:12<7:28:54,  7.09s/it]
 86%|████████▋ | 24281/28080 [47:58:19<7:28:12,  7.08s/it]
                                                          
{'loss': 0.6162, 'learning_rate': 2.3619442483834518e-05, 'epoch': 10.37}

 86%|████████▋ | 24281/28080 [47:58:19<7:28:12,  7.08s/it]
 86%|████████▋ | 24282/28080 [47:58:26<7:27:51,  7.08s/it]
                                                          
{'loss': 0.595, 'learning_rate': 2.360720903302821e-05, 'epoch': 10.37}

 86%|████████▋ | 24282/28080 [47:58:26<7:27:51,  7.08s/it]
 86%|████████▋ | 24283/28080 [47:58:33<7:29:46,  7.11s/it]
                                                          
{'loss': 0.5877, 'learning_rate': 2.359497859414439e-05, 'epoch': 10.37}

 86%|████████▋ | 24283/28080 [47:58:33<7:29:46,  7.11s/it]
 86%|████████▋ | 24284/28080 [47:58:40<7:30:56,  7.13s/it]
                                                          
{'loss': 0.5973, 'learning_rate': 2.3582751167345873e-05, 'epoch': 10.37}

 86%|████████▋ | 24284/28080 [47:58:40<7:30:56,  7.13s/it]
 86%|████████▋ | 24285/28080 [47:58:47<7:30:31,  7.12s/it]
                                                          
{'loss': 0.6147, 'learning_rate': 2.357052675279525e-05, 'epoch': 10.37}

 86%|████████▋ | 24285/28080 [47:58:47<7:30:31,  7.12s/it]
 86%|████████▋ | 24286/28080 [47:58:54<7:29:46,  7.11s/it]
                                                          
{'loss': 0.6008, 'learning_rate': 2.3558305350655202e-05, 'epoch': 10.37}

 86%|████████▋ | 24286/28080 [47:58:54<7:29:46,  7.11s/it]
 86%|████████▋ | 24287/28080 [47:59:01<7:30:51,  7.13s/it]
                                                          
{'loss': 0.581, 'learning_rate': 2.3546086961088258e-05, 'epoch': 10.38}

 86%|████████▋ | 24287/28080 [47:59:01<7:30:51,  7.13s/it]
 86%|████████▋ | 24288/28080 [47:59:09<7:32:03,  7.15s/it]
                                                          
{'loss': 0.5921, 'learning_rate': 2.3533871584256987e-05, 'epoch': 10.38}

 86%|████████▋ | 24288/28080 [47:59:09<7:32:03,  7.15s/it]
 86%|████████▋ | 24289/28080 [47:59:16<7:29:48,  7.12s/it]
                                                          
{'loss': 0.6047, 'learning_rate': 2.3521659220323956e-05, 'epoch': 10.38}

 86%|████████▋ | 24289/28080 [47:59:16<7:29:48,  7.12s/it]
 87%|████████▋ | 24290/28080 [47:59:23<7:28:47,  7.10s/it]
                                                          
{'loss': 0.5785, 'learning_rate': 2.350944986945161e-05, 'epoch': 10.38}

 87%|████████▋ | 24290/28080 [47:59:23<7:28:47,  7.10s/it]
 87%|████████▋ | 24291/28080 [47:59:30<7:28:58,  7.11s/it]
                                                          
{'loss': 0.6148, 'learning_rate': 2.3497243531802382e-05, 'epoch': 10.38}

 87%|████████▋ | 24291/28080 [47:59:30<7:28:58,  7.11s/it]
 87%|████████▋ | 24292/28080 [47:59:37<7:29:43,  7.12s/it]
                                                          
{'loss': 0.6157, 'learning_rate': 2.348504020753861e-05, 'epoch': 10.38}

 87%|████████▋ | 24292/28080 [47:59:37<7:29:43,  7.12s/it]
 87%|████████▋ | 24293/28080 [47:59:44<7:28:36,  7.11s/it]
                                                          
{'loss': 0.5984, 'learning_rate': 2.347283989682275e-05, 'epoch': 10.38}

 87%|████████▋ | 24293/28080 [47:59:44<7:28:36,  7.11s/it]
 87%|████████▋ | 24294/28080 [47:59:51<7:29:10,  7.12s/it]
                                                          
{'loss': 0.6029, 'learning_rate': 2.3460642599816978e-05, 'epoch': 10.38}

 87%|████████▋ | 24294/28080 [47:59:51<7:29:10,  7.12s/it]
 87%|████████▋ | 24295/28080 [47:59:58<7:30:01,  7.13s/it]
                                                          
{'loss': 0.5938, 'learning_rate': 2.3448448316683717e-05, 'epoch': 10.38}

 87%|████████▋ | 24295/28080 [47:59:58<7:30:01,  7.13s/it]
 87%|████████▋ | 24296/28080 [48:00:05<7:29:35,  7.13s/it]
                                                          
{'loss': 0.6063, 'learning_rate': 2.3436257047585146e-05, 'epoch': 10.38}

 87%|████████▋ | 24296/28080 [48:00:05<7:29:35,  7.13s/it]
 87%|████████▋ | 24297/28080 [48:00:13<7:29:19,  7.13s/it]
                                                          
{'loss': 0.6153, 'learning_rate': 2.3424068792683438e-05, 'epoch': 10.38}

 87%|████████▋ | 24297/28080 [48:00:13<7:29:19,  7.13s/it]
 87%|████████▋ | 24298/28080 [48:00:20<7:28:35,  7.12s/it]
                                                          
{'loss': 0.5989, 'learning_rate': 2.341188355214069e-05, 'epoch': 10.38}

 87%|████████▋ | 24298/28080 [48:00:20<7:28:35,  7.12s/it]
 87%|████████▋ | 24299/28080 [48:00:27<7:29:35,  7.13s/it]
                                                          
{'loss': 0.5865, 'learning_rate': 2.3399701326119128e-05, 'epoch': 10.38}

 87%|████████▋ | 24299/28080 [48:00:27<7:29:35,  7.13s/it]
 87%|████████▋ | 24300/28080 [48:00:34<7:25:47,  7.08s/it]
                                                          
{'loss': 0.6119, 'learning_rate': 2.3387522114780763e-05, 'epoch': 10.38}

 87%|████████▋ | 24300/28080 [48:00:34<7:25:47,  7.08s/it]
 87%|████████▋ | 24301/28080 [48:00:41<7:25:32,  7.07s/it]
                                                          
{'loss': 0.6031, 'learning_rate': 2.337534591828763e-05, 'epoch': 10.38}

 87%|████████▋ | 24301/28080 [48:00:41<7:25:32,  7.07s/it]
 87%|████████▋ | 24302/28080 [48:00:48<7:26:59,  7.10s/it]
                                                          
{'loss': 0.6004, 'learning_rate': 2.3363172736801693e-05, 'epoch': 10.38}

 87%|████████▋ | 24302/28080 [48:00:48<7:26:59,  7.10s/it]
 87%|████████▋ | 24303/28080 [48:00:55<7:26:41,  7.10s/it]
                                                          
{'loss': 0.6197, 'learning_rate': 2.3351002570484973e-05, 'epoch': 10.38}

 87%|████████▋ | 24303/28080 [48:00:55<7:26:41,  7.10s/it]
 87%|████████▋ | 24304/28080 [48:01:02<7:27:10,  7.11s/it]
                                                          
{'loss': 0.5808, 'learning_rate': 2.333883541949933e-05, 'epoch': 10.38}

 87%|████████▋ | 24304/28080 [48:01:02<7:27:10,  7.11s/it]
 87%|████████▋ | 24305/28080 [48:01:09<7:27:58,  7.12s/it]
                                                          
{'loss': 0.587, 'learning_rate': 2.3326671284006673e-05, 'epoch': 10.38}

 87%|████████▋ | 24305/28080 [48:01:09<7:27:58,  7.12s/it]
 87%|████████▋ | 24306/28080 [48:01:17<7:29:35,  7.15s/it]
                                                          
{'loss': 0.588, 'learning_rate': 2.3314510164168744e-05, 'epoch': 10.38}

 87%|████████▋ | 24306/28080 [48:01:17<7:29:35,  7.15s/it]
 87%|████████▋ | 24307/28080 [48:01:24<7:28:54,  7.14s/it]
                                                          
{'loss': 0.6079, 'learning_rate': 2.330235206014744e-05, 'epoch': 10.38}

 87%|████████▋ | 24307/28080 [48:01:24<7:28:54,  7.14s/it]
 87%|████████▋ | 24308/28080 [48:01:31<7:29:06,  7.14s/it]
                                                          
{'loss': 0.6065, 'learning_rate': 2.3290196972104438e-05, 'epoch': 10.38}

 87%|████████▋ | 24308/28080 [48:01:31<7:29:06,  7.14s/it]
 87%|████████▋ | 24309/28080 [48:01:38<7:28:11,  7.13s/it]
                                                          
{'loss': 0.5875, 'learning_rate': 2.3278044900201524e-05, 'epoch': 10.38}

 87%|████████▋ | 24309/28080 [48:01:38<7:28:11,  7.13s/it]
 87%|████████▋ | 24310/28080 [48:01:45<7:26:01,  7.10s/it]
                                                          
{'loss': 0.6149, 'learning_rate': 2.3265895844600316e-05, 'epoch': 10.39}

 87%|████████▋ | 24310/28080 [48:01:45<7:26:01,  7.10s/it]
 87%|████████▋ | 24311/28080 [48:01:52<7:26:46,  7.11s/it]
                                                          
{'loss': 0.5996, 'learning_rate': 2.3253749805462466e-05, 'epoch': 10.39}

 87%|████████▋ | 24311/28080 [48:01:52<7:26:46,  7.11s/it]
 87%|████████▋ | 24312/28080 [48:01:59<7:27:46,  7.13s/it]
                                                          
{'loss': 0.6076, 'learning_rate': 2.3241606782949566e-05, 'epoch': 10.39}

 87%|████████▋ | 24312/28080 [48:01:59<7:27:46,  7.13s/it]
 87%|████████▋ | 24313/28080 [48:02:06<7:26:20,  7.11s/it]
                                                          
{'loss': 0.6022, 'learning_rate': 2.3229466777223096e-05, 'epoch': 10.39}

 87%|████████▋ | 24313/28080 [48:02:06<7:26:20,  7.11s/it]
 87%|████████▋ | 24314/28080 [48:02:13<7:25:10,  7.09s/it]
                                                          
{'loss': 0.6182, 'learning_rate': 2.321732978844468e-05, 'epoch': 10.39}

 87%|████████▋ | 24314/28080 [48:02:13<7:25:10,  7.09s/it]
 87%|████████▋ | 24315/28080 [48:02:21<7:25:34,  7.10s/it]
                                                          
{'loss': 0.6125, 'learning_rate': 2.3205195816775716e-05, 'epoch': 10.39}

 87%|████████▋ | 24315/28080 [48:02:21<7:25:34,  7.10s/it]
 87%|████████▋ | 24316/28080 [48:02:28<7:24:17,  7.08s/it]
                                                          
{'loss': 0.5765, 'learning_rate': 2.3193064862377655e-05, 'epoch': 10.39}

 87%|████████▋ | 24316/28080 [48:02:28<7:24:17,  7.08s/it]
 87%|████████▋ | 24317/28080 [48:02:35<7:24:47,  7.09s/it]
                                                          
{'loss': 0.5878, 'learning_rate': 2.3180936925411845e-05, 'epoch': 10.39}

 87%|████████▋ | 24317/28080 [48:02:35<7:24:47,  7.09s/it]
 87%|████████▋ | 24318/28080 [48:02:42<7:25:26,  7.10s/it]
                                                          
{'loss': 0.6043, 'learning_rate': 2.3168812006039708e-05, 'epoch': 10.39}

 87%|████████▋ | 24318/28080 [48:02:42<7:25:26,  7.10s/it]
 87%|████████▋ | 24319/28080 [48:02:49<7:26:01,  7.12s/it]
                                                          
{'loss': 0.6213, 'learning_rate': 2.3156690104422507e-05, 'epoch': 10.39}

 87%|████████▋ | 24319/28080 [48:02:49<7:26:01,  7.12s/it]
 87%|████████▋ | 24320/28080 [48:02:56<7:25:19,  7.11s/it]
                                                          
{'loss': 0.6092, 'learning_rate': 2.3144571220721556e-05, 'epoch': 10.39}

 87%|████████▋ | 24320/28080 [48:02:56<7:25:19,  7.11s/it]
 87%|████████▋ | 24321/28080 [48:03:03<7:25:59,  7.12s/it]
                                                          
{'loss': 0.5863, 'learning_rate': 2.3132455355097976e-05, 'epoch': 10.39}

 87%|████████▋ | 24321/28080 [48:03:03<7:25:59,  7.12s/it]
 87%|████████▋ | 24322/28080 [48:03:10<7:23:59,  7.09s/it]
                                                          
{'loss': 0.5907, 'learning_rate': 2.312034250771311e-05, 'epoch': 10.39}

 87%|████████▋ | 24322/28080 [48:03:10<7:23:59,  7.09s/it]
 87%|████████▋ | 24323/28080 [48:03:17<7:24:50,  7.10s/it]
                                                          
{'loss': 0.5948, 'learning_rate': 2.3108232678727942e-05, 'epoch': 10.39}

 87%|████████▋ | 24323/28080 [48:03:17<7:24:50,  7.10s/it]
 87%|████████▋ | 24324/28080 [48:03:24<7:24:11,  7.10s/it]
                                                          
{'loss': 0.599, 'learning_rate': 2.3096125868303787e-05, 'epoch': 10.39}

 87%|████████▋ | 24324/28080 [48:03:24<7:24:11,  7.10s/it]
 87%|████████▋ | 24325/28080 [48:03:32<7:24:30,  7.10s/it]
                                                          
{'loss': 0.5713, 'learning_rate': 2.3084022076601484e-05, 'epoch': 10.39}

 87%|████████▋ | 24325/28080 [48:03:32<7:24:30,  7.10s/it]
 87%|████████▋ | 24326/28080 [48:03:39<7:24:43,  7.11s/it]
                                                          
{'loss': 0.5881, 'learning_rate': 2.3071921303782243e-05, 'epoch': 10.39}

 87%|████████▋ | 24326/28080 [48:03:39<7:24:43,  7.11s/it]
 87%|████████▋ | 24327/28080 [48:03:46<7:24:23,  7.10s/it]
                                                          
{'loss': 0.6088, 'learning_rate': 2.3059823550006907e-05, 'epoch': 10.39}

 87%|████████▋ | 24327/28080 [48:03:46<7:24:23,  7.10s/it]
 87%|████████▋ | 24328/28080 [48:03:53<7:23:50,  7.10s/it]
                                                          
{'loss': 0.5843, 'learning_rate': 2.3047728815436568e-05, 'epoch': 10.39}

 87%|████████▋ | 24328/28080 [48:03:53<7:23:50,  7.10s/it]
 87%|████████▋ | 24329/28080 [48:04:00<7:22:42,  7.08s/it]
                                                          
{'loss': 0.5956, 'learning_rate': 2.3035637100232043e-05, 'epoch': 10.39}

 87%|████████▋ | 24329/28080 [48:04:00<7:22:42,  7.08s/it]
 87%|████████▋ | 24330/28080 [48:04:07<7:21:03,  7.06s/it]
                                                          
{'loss': 0.619, 'learning_rate': 2.302354840455423e-05, 'epoch': 10.39}

 87%|████████▋ | 24330/28080 [48:04:07<7:21:03,  7.06s/it]
 87%|████████▋ | 24331/28080 [48:04:14<7:21:24,  7.06s/it]
                                                          
{'loss': 0.5812, 'learning_rate': 2.3011462728563888e-05, 'epoch': 10.39}

 87%|████████▋ | 24331/28080 [48:04:14<7:21:24,  7.06s/it]
 87%|████████▋ | 24332/28080 [48:04:21<7:21:48,  7.07s/it]
                                                          
{'loss': 0.6135, 'learning_rate': 2.2999380072421917e-05, 'epoch': 10.39}

 87%|████████▋ | 24332/28080 [48:04:21<7:21:48,  7.07s/it]
 87%|████████▋ | 24333/28080 [48:04:28<7:23:39,  7.10s/it]
                                                          
{'loss': 0.5908, 'learning_rate': 2.298730043628902e-05, 'epoch': 10.39}

 87%|████████▋ | 24333/28080 [48:04:28<7:23:39,  7.10s/it]
 87%|████████▋ | 24334/28080 [48:04:35<7:23:27,  7.10s/it]
                                                          
{'loss': 0.5943, 'learning_rate': 2.297522382032588e-05, 'epoch': 10.4}

 87%|████████▋ | 24334/28080 [48:04:35<7:23:27,  7.10s/it]
 87%|████████▋ | 24335/28080 [48:04:42<7:21:39,  7.08s/it]
                                                          
{'loss': 0.6139, 'learning_rate': 2.2963150224693142e-05, 'epoch': 10.4}

 87%|████████▋ | 24335/28080 [48:04:42<7:21:39,  7.08s/it]
 87%|████████▋ | 24336/28080 [48:04:49<7:21:38,  7.08s/it]
                                                          
{'loss': 0.59, 'learning_rate': 2.295107964955151e-05, 'epoch': 10.4}

 87%|████████▋ | 24336/28080 [48:04:49<7:21:38,  7.08s/it]
 87%|████████▋ | 24337/28080 [48:04:57<7:22:10,  7.09s/it]
                                                          
{'loss': 0.6017, 'learning_rate': 2.293901209506155e-05, 'epoch': 10.4}

 87%|████████▋ | 24337/28080 [48:04:57<7:22:10,  7.09s/it]
 87%|████████▋ | 24338/28080 [48:05:04<7:23:03,  7.10s/it]
                                                          
{'loss': 0.5848, 'learning_rate': 2.2926947561383775e-05, 'epoch': 10.4}

 87%|████████▋ | 24338/28080 [48:05:04<7:23:03,  7.10s/it]
 87%|████████▋ | 24339/28080 [48:05:11<7:21:10,  7.08s/it]
                                                          
{'loss': 0.6241, 'learning_rate': 2.2914886048678697e-05, 'epoch': 10.4}

 87%|████████▋ | 24339/28080 [48:05:11<7:21:10,  7.08s/it]
 87%|████████▋ | 24340/28080 [48:05:18<7:22:06,  7.09s/it]
                                                          
{'loss': 0.6017, 'learning_rate': 2.2902827557106737e-05, 'epoch': 10.4}

 87%|████████▋ | 24340/28080 [48:05:18<7:22:06,  7.09s/it]
 87%|████████▋ | 24341/28080 [48:05:25<7:21:29,  7.08s/it]
                                                          
{'loss': 0.5955, 'learning_rate': 2.2890772086828437e-05, 'epoch': 10.4}

 87%|████████▋ | 24341/28080 [48:05:25<7:21:29,  7.08s/it]
 87%|████████▋ | 24342/28080 [48:05:32<7:20:12,  7.07s/it]
                                                          
{'loss': 0.6114, 'learning_rate': 2.2878719638004058e-05, 'epoch': 10.4}

 87%|████████▋ | 24342/28080 [48:05:32<7:20:12,  7.07s/it]
 87%|████████▋ | 24343/28080 [48:05:39<7:19:54,  7.06s/it]
                                                          
{'loss': 0.5881, 'learning_rate': 2.286667021079411e-05, 'epoch': 10.4}

 87%|████████▋ | 24343/28080 [48:05:39<7:19:54,  7.06s/it]
 87%|████████▋ | 24344/28080 [48:05:46<7:20:50,  7.08s/it]
                                                          
{'loss': 0.6026, 'learning_rate': 2.285462380535869e-05, 'epoch': 10.4}

 87%|████████▋ | 24344/28080 [48:05:46<7:20:50,  7.08s/it]
 87%|████████▋ | 24345/28080 [48:05:53<7:19:09,  7.05s/it]
                                                          
{'loss': 0.6044, 'learning_rate': 2.2842580421858243e-05, 'epoch': 10.4}

 87%|████████▋ | 24345/28080 [48:05:53<7:19:09,  7.05s/it]
 87%|████████▋ | 24346/28080 [48:06:00<7:19:44,  7.07s/it]
                                                          
{'loss': 0.5934, 'learning_rate': 2.2830540060452847e-05, 'epoch': 10.4}

 87%|████████▋ | 24346/28080 [48:06:00<7:19:44,  7.07s/it]
 87%|████████▋ | 24347/28080 [48:06:07<7:20:43,  7.08s/it]
                                                          
{'loss': 0.6038, 'learning_rate': 2.2818502721302813e-05, 'epoch': 10.4}

 87%|████████▋ | 24347/28080 [48:06:07<7:20:43,  7.08s/it]
 87%|████████▋ | 24348/28080 [48:06:15<7:22:25,  7.11s/it]
                                                          
{'loss': 0.6031, 'learning_rate': 2.280646840456821e-05, 'epoch': 10.4}

 87%|████████▋ | 24348/28080 [48:06:15<7:22:25,  7.11s/it]
 87%|████████▋ | 24349/28080 [48:06:22<7:22:19,  7.11s/it]
                                                          
{'loss': 0.5909, 'learning_rate': 2.2794437110409184e-05, 'epoch': 10.4}

 87%|████████▋ | 24349/28080 [48:06:22<7:22:19,  7.11s/it]
 87%|████████▋ | 24350/28080 [48:06:29<7:22:10,  7.11s/it]
                                                          
{'loss': 0.5942, 'learning_rate': 2.278240883898572e-05, 'epoch': 10.4}

 87%|████████▋ | 24350/28080 [48:06:29<7:22:10,  7.11s/it]
 87%|████████▋ | 24351/28080 [48:06:36<7:22:19,  7.12s/it]
                                                          
{'loss': 0.5806, 'learning_rate': 2.2770383590457965e-05, 'epoch': 10.4}

 87%|████████▋ | 24351/28080 [48:06:36<7:22:19,  7.12s/it]
 87%|████████▋ | 24352/28080 [48:06:43<7:22:58,  7.13s/it]
                                                          
{'loss': 0.602, 'learning_rate': 2.2758361364985798e-05, 'epoch': 10.4}

 87%|████████▋ | 24352/28080 [48:06:43<7:22:58,  7.13s/it]
 87%|████████▋ | 24353/28080 [48:06:50<7:22:31,  7.12s/it]
                                                          
{'loss': 0.5852, 'learning_rate': 2.2746342162729223e-05, 'epoch': 10.4}

 87%|████████▋ | 24353/28080 [48:06:50<7:22:31,  7.12s/it]
 87%|████████▋ | 24354/28080 [48:06:57<7:23:40,  7.14s/it]
                                                          
{'loss': 0.6333, 'learning_rate': 2.2734325983848086e-05, 'epoch': 10.4}

 87%|████████▋ | 24354/28080 [48:06:57<7:23:40,  7.14s/it]
 87%|████████▋ | 24355/28080 [48:07:04<7:22:30,  7.13s/it]
                                                          
{'loss': 0.6015, 'learning_rate': 2.2722312828502316e-05, 'epoch': 10.4}

 87%|████████▋ | 24355/28080 [48:07:04<7:22:30,  7.13s/it]
 87%|████████▋ | 24356/28080 [48:07:11<7:20:06,  7.09s/it]
                                                          
{'loss': 0.6058, 'learning_rate': 2.2710302696851675e-05, 'epoch': 10.4}

 87%|████████▋ | 24356/28080 [48:07:11<7:20:06,  7.09s/it]
 87%|████████▋ | 24357/28080 [48:07:19<7:19:49,  7.09s/it]
                                                          
{'loss': 0.5883, 'learning_rate': 2.2698295589056008e-05, 'epoch': 10.41}

 87%|████████▋ | 24357/28080 [48:07:19<7:19:49,  7.09s/it]
 87%|████████▋ | 24358/28080 [48:07:26<7:20:08,  7.10s/it]
                                                          
{'loss': 0.5841, 'learning_rate': 2.2686291505275013e-05, 'epoch': 10.41}

 87%|████████▋ | 24358/28080 [48:07:26<7:20:08,  7.10s/it]
 87%|████████▋ | 24359/28080 [48:07:33<7:19:57,  7.09s/it]
                                                          
{'loss': 0.6037, 'learning_rate': 2.267429044566843e-05, 'epoch': 10.41}

 87%|████████▋ | 24359/28080 [48:07:33<7:19:57,  7.09s/it]
 87%|████████▋ | 24360/28080 [48:07:40<7:19:12,  7.08s/it]
                                                          
{'loss': 0.5935, 'learning_rate': 2.2662292410395828e-05, 'epoch': 10.41}

 87%|████████▋ | 24360/28080 [48:07:40<7:19:12,  7.08s/it]
 87%|████████▋ | 24361/28080 [48:07:47<7:21:44,  7.13s/it]
                                                          
{'loss': 0.5925, 'learning_rate': 2.265029739961694e-05, 'epoch': 10.41}

 87%|████████▋ | 24361/28080 [48:07:47<7:21:44,  7.13s/it]
 87%|████████▋ | 24362/28080 [48:07:54<7:20:59,  7.12s/it]
                                                          
{'loss': 0.606, 'learning_rate': 2.2638305413491324e-05, 'epoch': 10.41}

 87%|████████▋ | 24362/28080 [48:07:54<7:20:59,  7.12s/it]
 87%|████████▋ | 24363/28080 [48:08:01<7:21:28,  7.13s/it]
                                                          
{'loss': 0.605, 'learning_rate': 2.262631645217847e-05, 'epoch': 10.41}

 87%|████████▋ | 24363/28080 [48:08:01<7:21:28,  7.13s/it]
 87%|████████▋ | 24364/28080 [48:08:08<7:22:09,  7.14s/it]
                                                          
{'loss': 0.5776, 'learning_rate': 2.2614330515837915e-05, 'epoch': 10.41}

 87%|████████▋ | 24364/28080 [48:08:08<7:22:09,  7.14s/it]
 87%|████████▋ | 24365/28080 [48:08:16<7:22:21,  7.14s/it]
                                                          
{'loss': 0.5805, 'learning_rate': 2.2602347604629066e-05, 'epoch': 10.41}

 87%|████████▋ | 24365/28080 [48:08:16<7:22:21,  7.14s/it]
 87%|████████▋ | 24366/28080 [48:08:23<7:21:48,  7.14s/it]
                                                          
{'loss': 0.586, 'learning_rate': 2.2590367718711453e-05, 'epoch': 10.41}

 87%|████████▋ | 24366/28080 [48:08:23<7:21:48,  7.14s/it]
 87%|████████▋ | 24367/28080 [48:08:30<7:21:15,  7.13s/it]
                                                          
{'loss': 0.5916, 'learning_rate': 2.257839085824437e-05, 'epoch': 10.41}

 87%|████████▋ | 24367/28080 [48:08:30<7:21:15,  7.13s/it]
 87%|████████▋ | 24368/28080 [48:08:37<7:18:35,  7.09s/it]
                                                          
{'loss': 0.586, 'learning_rate': 2.2566417023387187e-05, 'epoch': 10.41}

 87%|████████▋ | 24368/28080 [48:08:37<7:18:35,  7.09s/it]
 87%|████████▋ | 24369/28080 [48:08:44<7:18:59,  7.10s/it]
                                                          
{'loss': 0.6057, 'learning_rate': 2.255444621429914e-05, 'epoch': 10.41}

 87%|████████▋ | 24369/28080 [48:08:44<7:18:59,  7.10s/it]
 87%|████████▋ | 24370/28080 [48:08:51<7:18:14,  7.09s/it]
                                                          
{'loss': 0.6099, 'learning_rate': 2.25424784311396e-05, 'epoch': 10.41}

 87%|████████▋ | 24370/28080 [48:08:51<7:18:14,  7.09s/it]
 87%|████████▋ | 24371/28080 [48:08:58<7:18:52,  7.10s/it]
                                                          
{'loss': 0.5839, 'learning_rate': 2.2530513674067694e-05, 'epoch': 10.41}

 87%|████████▋ | 24371/28080 [48:08:58<7:18:52,  7.10s/it]
 87%|████████▋ | 24372/28080 [48:09:05<7:18:05,  7.09s/it]
                                                          
{'loss': 0.5806, 'learning_rate': 2.2518551943242704e-05, 'epoch': 10.41}

 87%|████████▋ | 24372/28080 [48:09:05<7:18:05,  7.09s/it]
 87%|████████▋ | 24373/28080 [48:09:12<7:18:48,  7.10s/it]
                                                          
{'loss': 0.6035, 'learning_rate': 2.250659323882362e-05, 'epoch': 10.41}

 87%|████████▋ | 24373/28080 [48:09:12<7:18:48,  7.10s/it]
 87%|████████▋ | 24374/28080 [48:09:19<7:19:00,  7.11s/it]
                                                          
{'loss': 0.5953, 'learning_rate': 2.249463756096967e-05, 'epoch': 10.41}

 87%|████████▋ | 24374/28080 [48:09:19<7:19:00,  7.11s/it]
 87%|████████▋ | 24375/28080 [48:09:26<7:18:13,  7.10s/it]
                                                          
{'loss': 0.5891, 'learning_rate': 2.2482684909839817e-05, 'epoch': 10.41}

 87%|████████▋ | 24375/28080 [48:09:26<7:18:13,  7.10s/it]
 87%|████████▋ | 24376/28080 [48:09:33<7:16:04,  7.06s/it]
                                                          
{'loss': 0.6156, 'learning_rate': 2.247073528559318e-05, 'epoch': 10.41}

 87%|████████▋ | 24376/28080 [48:09:33<7:16:04,  7.06s/it]
 87%|████████▋ | 24377/28080 [48:09:41<7:16:29,  7.07s/it]
                                                          
{'loss': 0.5918, 'learning_rate': 2.245878868838866e-05, 'epoch': 10.41}

 87%|████████▋ | 24377/28080 [48:09:41<7:16:29,  7.07s/it]
 87%|████████▋ | 24378/28080 [48:09:48<7:16:42,  7.08s/it]
                                                          
{'loss': 0.6113, 'learning_rate': 2.244684511838521e-05, 'epoch': 10.41}

 87%|████████▋ | 24378/28080 [48:09:48<7:16:42,  7.08s/it]
 87%|████████▋ | 24379/28080 [48:09:55<7:17:53,  7.10s/it]
                                                          
{'loss': 0.5895, 'learning_rate': 2.243490457574171e-05, 'epoch': 10.41}

 87%|████████▋ | 24379/28080 [48:09:55<7:17:53,  7.10s/it]
 87%|████████▋ | 24380/28080 [48:10:02<7:17:55,  7.10s/it]
                                                          
{'loss': 0.6149, 'learning_rate': 2.2422967060617084e-05, 'epoch': 10.41}

 87%|████████▋ | 24380/28080 [48:10:02<7:17:55,  7.10s/it]
 87%|████████▋ | 24381/28080 [48:10:09<7:18:39,  7.12s/it]
                                                          
{'loss': 0.5806, 'learning_rate': 2.2411032573170092e-05, 'epoch': 10.42}

 87%|████████▋ | 24381/28080 [48:10:09<7:18:39,  7.12s/it]
 87%|████████▋ | 24382/28080 [48:10:16<7:18:12,  7.11s/it]
                                                          
{'loss': 0.6218, 'learning_rate': 2.239910111355953e-05, 'epoch': 10.42}

 87%|████████▋ | 24382/28080 [48:10:16<7:18:12,  7.11s/it]
 87%|████████▋ | 24383/28080 [48:10:23<7:17:25,  7.10s/it]
                                                          
{'loss': 0.614, 'learning_rate': 2.238717268194407e-05, 'epoch': 10.42}

 87%|████████▋ | 24383/28080 [48:10:23<7:17:25,  7.10s/it]
 87%|████████▋ | 24384/28080 [48:10:30<7:16:18,  7.08s/it]
                                                          
{'loss': 0.619, 'learning_rate': 2.2375247278482502e-05, 'epoch': 10.42}

 87%|████████▋ | 24384/28080 [48:10:30<7:16:18,  7.08s/it]
 87%|████████▋ | 24385/28080 [48:10:37<7:17:35,  7.11s/it]
                                                          
{'loss': 0.5853, 'learning_rate': 2.23633249033334e-05, 'epoch': 10.42}

 87%|████████▋ | 24385/28080 [48:10:37<7:17:35,  7.11s/it]
 87%|████████▋ | 24386/28080 [48:10:45<7:19:04,  7.13s/it]
                                                          
{'loss': 0.5919, 'learning_rate': 2.235140555665552e-05, 'epoch': 10.42}

 87%|████████▋ | 24386/28080 [48:10:45<7:19:04,  7.13s/it]
 87%|████████▋ | 24387/28080 [48:10:52<7:19:19,  7.14s/it]
                                                          
{'loss': 0.5695, 'learning_rate': 2.2339489238607292e-05, 'epoch': 10.42}

 87%|████████▋ | 24387/28080 [48:10:52<7:19:19,  7.14s/it]
 87%|████████▋ | 24388/28080 [48:10:59<7:19:08,  7.14s/it]
                                                          
{'loss': 0.5962, 'learning_rate': 2.2327575949347257e-05, 'epoch': 10.42}

 87%|████████▋ | 24388/28080 [48:10:59<7:19:08,  7.14s/it]
 87%|████████▋ | 24389/28080 [48:11:06<7:17:11,  7.11s/it]
                                                          
{'loss': 0.5939, 'learning_rate': 2.2315665689033982e-05, 'epoch': 10.42}

 87%|████████▋ | 24389/28080 [48:11:06<7:17:11,  7.11s/it]
 87%|████████▋ | 24390/28080 [48:11:13<7:17:02,  7.11s/it]
                                                          
{'loss': 0.5797, 'learning_rate': 2.230375845782584e-05, 'epoch': 10.42}

 87%|████████▋ | 24390/28080 [48:11:13<7:17:02,  7.11s/it]
 87%|████████▋ | 24391/28080 [48:11:20<7:17:30,  7.12s/it]
                                                          
{'loss': 0.5916, 'learning_rate': 2.2291854255881372e-05, 'epoch': 10.42}

 87%|████████▋ | 24391/28080 [48:11:20<7:17:30,  7.12s/it]
 87%|████████▋ | 24392/28080 [48:11:27<7:17:29,  7.12s/it]
                                                          
{'loss': 0.5877, 'learning_rate': 2.2279953083358784e-05, 'epoch': 10.42}

 87%|████████▋ | 24392/28080 [48:11:27<7:17:29,  7.12s/it]
 87%|████████▋ | 24393/28080 [48:11:34<7:15:56,  7.09s/it]
                                                          
{'loss': 0.594, 'learning_rate': 2.226805494041656e-05, 'epoch': 10.42}

 87%|████████▋ | 24393/28080 [48:11:34<7:15:56,  7.09s/it]
 87%|████████▋ | 24394/28080 [48:11:41<7:12:45,  7.04s/it]
                                                          
{'loss': 0.5998, 'learning_rate': 2.225615982721285e-05, 'epoch': 10.42}

 87%|████████▋ | 24394/28080 [48:11:41<7:12:45,  7.04s/it]
 87%|████████▋ | 24395/28080 [48:11:48<7:12:11,  7.04s/it]
                                                          
{'loss': 0.5784, 'learning_rate': 2.2244267743906062e-05, 'epoch': 10.42}

 87%|████████▋ | 24395/28080 [48:11:48<7:12:11,  7.04s/it]
 87%|████████▋ | 24396/28080 [48:11:55<7:13:15,  7.06s/it]
                                                          
{'loss': 0.6206, 'learning_rate': 2.2232378690654308e-05, 'epoch': 10.42}

 87%|████████▋ | 24396/28080 [48:11:55<7:13:15,  7.06s/it]
 87%|████████▋ | 24397/28080 [48:12:02<7:13:14,  7.06s/it]
                                                          
{'loss': 0.6271, 'learning_rate': 2.2220492667615777e-05, 'epoch': 10.42}

 87%|████████▋ | 24397/28080 [48:12:02<7:13:14,  7.06s/it]
 87%|████████▋ | 24398/28080 [48:12:10<7:14:17,  7.08s/it]
                                                          
{'loss': 0.5917, 'learning_rate': 2.220860967494856e-05, 'epoch': 10.42}

 87%|████████▋ | 24398/28080 [48:12:10<7:14:17,  7.08s/it]
 87%|████████▋ | 24399/28080 [48:12:17<7:12:12,  7.05s/it]
                                                          
{'loss': 0.5942, 'learning_rate': 2.2196729712810866e-05, 'epoch': 10.42}

 87%|████████▋ | 24399/28080 [48:12:17<7:12:12,  7.05s/it]
 87%|████████▋ | 24400/28080 [48:12:24<7:14:16,  7.08s/it]
                                                          
{'loss': 0.591, 'learning_rate': 2.2184852781360647e-05, 'epoch': 10.42}

 87%|████████▋ | 24400/28080 [48:12:24<7:14:16,  7.08s/it]
 87%|████████▋ | 24401/28080 [48:12:31<7:14:54,  7.09s/it]
                                                          
{'loss': 0.5972, 'learning_rate': 2.2172978880755923e-05, 'epoch': 10.42}

 87%|████████▋ | 24401/28080 [48:12:31<7:14:54,  7.09s/it]
 87%|████████▋ | 24402/28080 [48:12:38<7:16:28,  7.12s/it]
                                                          
{'loss': 0.5964, 'learning_rate': 2.2161108011154647e-05, 'epoch': 10.42}

 87%|████████▋ | 24402/28080 [48:12:38<7:16:28,  7.12s/it]
 87%|████████▋ | 24403/28080 [48:12:45<7:14:26,  7.09s/it]
                                                          
{'loss': 0.5898, 'learning_rate': 2.214924017271483e-05, 'epoch': 10.42}

 87%|████████▋ | 24403/28080 [48:12:45<7:14:26,  7.09s/it]
 87%|████████▋ | 24404/28080 [48:12:52<7:15:26,  7.11s/it]
                                                          
{'loss': 0.5742, 'learning_rate': 2.2137375365594264e-05, 'epoch': 10.43}

 87%|████████▋ | 24404/28080 [48:12:52<7:15:26,  7.11s/it]
 87%|████████▋ | 24405/28080 [48:12:59<7:14:51,  7.10s/it]
                                                          
{'loss': 0.5856, 'learning_rate': 2.2125513589950962e-05, 'epoch': 10.43}

 87%|████████▋ | 24405/28080 [48:12:59<7:14:51,  7.10s/it]
 87%|████████▋ | 24406/28080 [48:13:06<7:13:00,  7.07s/it]
                                                          
{'loss': 0.5931, 'learning_rate': 2.2113654845942493e-05, 'epoch': 10.43}

 87%|████████▋ | 24406/28080 [48:13:06<7:13:00,  7.07s/it]
 87%|████████▋ | 24407/28080 [48:13:13<7:13:28,  7.08s/it]
                                                          
{'loss': 0.6055, 'learning_rate': 2.2101799133726814e-05, 'epoch': 10.43}

 87%|████████▋ | 24407/28080 [48:13:13<7:13:28,  7.08s/it]
 87%|████████▋ | 24408/28080 [48:13:21<7:15:29,  7.12s/it]
                                                          
{'loss': 0.6074, 'learning_rate': 2.2089946453461517e-05, 'epoch': 10.43}

 87%|████████▋ | 24408/28080 [48:13:21<7:15:29,  7.12s/it]
 87%|████████▋ | 24409/28080 [48:13:28<7:16:59,  7.14s/it]
                                                          
{'loss': 0.5922, 'learning_rate': 2.2078096805304425e-05, 'epoch': 10.43}

 87%|████████▋ | 24409/28080 [48:13:28<7:16:59,  7.14s/it]
 87%|████████▋ | 24410/28080 [48:13:35<7:15:29,  7.12s/it]
                                                          
{'loss': 0.6038, 'learning_rate': 2.2066250189413134e-05, 'epoch': 10.43}

 87%|████████▋ | 24410/28080 [48:13:35<7:15:29,  7.12s/it]
 87%|████████▋ | 24411/28080 [48:13:42<7:16:33,  7.14s/it]
                                                          
{'loss': 0.6024, 'learning_rate': 2.205440660594521e-05, 'epoch': 10.43}

 87%|████████▋ | 24411/28080 [48:13:42<7:16:33,  7.14s/it]
 87%|████████▋ | 24412/28080 [48:13:49<7:15:49,  7.13s/it]
                                                          
{'loss': 0.6102, 'learning_rate': 2.204256605505825e-05, 'epoch': 10.43}

 87%|████████▋ | 24412/28080 [48:13:49<7:15:49,  7.13s/it]
 87%|████████▋ | 24413/28080 [48:13:56<7:13:14,  7.09s/it]
                                                          
{'loss': 0.6019, 'learning_rate': 2.2030728536909766e-05, 'epoch': 10.43}

 87%|████████▋ | 24413/28080 [48:13:56<7:13:14,  7.09s/it]
 87%|████████▋ | 24414/28080 [48:14:03<7:13:12,  7.09s/it]
                                                          
{'loss': 0.6096, 'learning_rate': 2.2018894051657274e-05, 'epoch': 10.43}

 87%|████████▋ | 24414/28080 [48:14:03<7:13:12,  7.09s/it]
 87%|████████▋ | 24415/28080 [48:14:10<7:13:13,  7.09s/it]
                                                          
{'loss': 0.636, 'learning_rate': 2.20070625994582e-05, 'epoch': 10.43}

 87%|████████▋ | 24415/28080 [48:14:10<7:13:13,  7.09s/it]
 87%|████████▋ | 24416/28080 [48:14:17<7:13:56,  7.11s/it]
                                                          
{'loss': 0.594, 'learning_rate': 2.1995234180469946e-05, 'epoch': 10.43}

 87%|████████▋ | 24416/28080 [48:14:17<7:13:56,  7.11s/it]
 87%|████████▋ | 24417/28080 [48:14:24<7:10:21,  7.05s/it]
                                                          
{'loss': 0.6049, 'learning_rate': 2.1983408794849862e-05, 'epoch': 10.43}

 87%|████████▋ | 24417/28080 [48:14:24<7:10:21,  7.05s/it]
 87%|████████▋ | 24418/28080 [48:14:31<7:10:42,  7.06s/it]
                                                          
{'loss': 0.6178, 'learning_rate': 2.197158644275532e-05, 'epoch': 10.43}

 87%|████████▋ | 24418/28080 [48:14:31<7:10:42,  7.06s/it]
 87%|████████▋ | 24419/28080 [48:14:39<7:11:27,  7.07s/it]
                                                          
{'loss': 0.6195, 'learning_rate': 2.1959767124343528e-05, 'epoch': 10.43}

 87%|████████▋ | 24419/28080 [48:14:39<7:11:27,  7.07s/it]
 87%|████████▋ | 24420/28080 [48:14:46<7:11:06,  7.07s/it]
                                                          
{'loss': 0.5861, 'learning_rate': 2.1947950839771887e-05, 'epoch': 10.43}

 87%|████████▋ | 24420/28080 [48:14:46<7:11:06,  7.07s/it]
 87%|████████▋ | 24421/28080 [48:14:53<7:09:51,  7.05s/it]
                                                          
{'loss': 0.6016, 'learning_rate': 2.193613758919738e-05, 'epoch': 10.43}

 87%|████████▋ | 24421/28080 [48:14:53<7:09:51,  7.05s/it]
 87%|████████▋ | 24422/28080 [48:15:00<7:12:07,  7.09s/it]
                                                          
{'loss': 0.5842, 'learning_rate': 2.192432737277733e-05, 'epoch': 10.43}

 87%|████████▋ | 24422/28080 [48:15:00<7:12:07,  7.09s/it]
 87%|████████▋ | 24423/28080 [48:15:07<7:13:11,  7.11s/it]
                                                          
{'loss': 0.586, 'learning_rate': 2.191252019066878e-05, 'epoch': 10.43}

 87%|████████▋ | 24423/28080 [48:15:07<7:13:11,  7.11s/it]
 87%|████████▋ | 24424/28080 [48:15:14<7:13:36,  7.12s/it]
                                                          
{'loss': 0.586, 'learning_rate': 2.1900716043028873e-05, 'epoch': 10.43}

 87%|████████▋ | 24424/28080 [48:15:14<7:13:36,  7.12s/it]
 87%|████████▋ | 24425/28080 [48:15:21<7:12:24,  7.10s/it]
                                                          
{'loss': 0.5937, 'learning_rate': 2.1888914930014632e-05, 'epoch': 10.43}

 87%|████████▋ | 24425/28080 [48:15:21<7:12:24,  7.10s/it]
 87%|████████▋ | 24426/28080 [48:15:28<7:12:50,  7.11s/it]
                                                          
{'loss': 0.6114, 'learning_rate': 2.1877116851783062e-05, 'epoch': 10.43}

 87%|████████▋ | 24426/28080 [48:15:28<7:12:50,  7.11s/it]
 87%|████████▋ | 24427/28080 [48:15:35<7:13:20,  7.12s/it]
                                                          
{'loss': 0.5877, 'learning_rate': 2.1865321808491047e-05, 'epoch': 10.43}

 87%|████████▋ | 24427/28080 [48:15:35<7:13:20,  7.12s/it]
 87%|████████▋ | 24428/28080 [48:15:42<7:12:20,  7.10s/it]
                                                          
{'loss': 0.6026, 'learning_rate': 2.1853529800295617e-05, 'epoch': 10.44}

 87%|████████▋ | 24428/28080 [48:15:42<7:12:20,  7.10s/it]
 87%|████████▋ | 24429/28080 [48:15:49<7:10:27,  7.07s/it]
                                                          
{'loss': 0.6, 'learning_rate': 2.1841740827353628e-05, 'epoch': 10.44}

 87%|████████▋ | 24429/28080 [48:15:50<7:10:27,  7.07s/it]
 87%|████████▋ | 24430/28080 [48:15:57<7:10:32,  7.08s/it]
                                                          
{'loss': 0.6107, 'learning_rate': 2.1829954889821867e-05, 'epoch': 10.44}

 87%|████████▋ | 24430/28080 [48:15:57<7:10:32,  7.08s/it]
 87%|████████▋ | 24431/28080 [48:16:04<7:13:19,  7.13s/it]
                                                          
{'loss': 0.5886, 'learning_rate': 2.1818171987857157e-05, 'epoch': 10.44}

 87%|████████▋ | 24431/28080 [48:16:04<7:13:19,  7.13s/it]
 87%|████████▋ | 24432/28080 [48:16:11<7:12:47,  7.12s/it]
                                                          
{'loss': 0.6095, 'learning_rate': 2.1806392121616282e-05, 'epoch': 10.44}

 87%|████████▋ | 24432/28080 [48:16:11<7:12:47,  7.12s/it]
 87%|████████▋ | 24433/28080 [48:16:18<7:12:28,  7.12s/it]
                                                          
{'loss': 0.5894, 'learning_rate': 2.1794615291255898e-05, 'epoch': 10.44}

 87%|████████▋ | 24433/28080 [48:16:18<7:12:28,  7.12s/it]
 87%|████████▋ | 24434/28080 [48:16:25<7:11:31,  7.10s/it]
                                                          
{'loss': 0.5825, 'learning_rate': 2.1782841496932854e-05, 'epoch': 10.44}

 87%|████████▋ | 24434/28080 [48:16:25<7:11:31,  7.10s/it]
 87%|████████▋ | 24435/28080 [48:16:32<7:11:45,  7.11s/it]
                                                          
{'loss': 0.6012, 'learning_rate': 2.177107073880355e-05, 'epoch': 10.44}

 87%|████████▋ | 24435/28080 [48:16:32<7:11:45,  7.11s/it]
 87%|████████▋ | 24436/28080 [48:16:39<7:11:22,  7.10s/it]
                                                          
{'loss': 0.5866, 'learning_rate': 2.175930301702475e-05, 'epoch': 10.44}

 87%|████████▋ | 24436/28080 [48:16:39<7:11:22,  7.10s/it]
 87%|████████▋ | 24437/28080 [48:16:46<7:10:09,  7.08s/it]
                                                          
{'loss': 0.6035, 'learning_rate': 2.1747538331752968e-05, 'epoch': 10.44}

 87%|████████▋ | 24437/28080 [48:16:46<7:10:09,  7.08s/it]
 87%|████████▋ | 24438/28080 [48:16:53<7:07:58,  7.05s/it]
                                                          
{'loss': 0.606, 'learning_rate': 2.1735776683144636e-05, 'epoch': 10.44}

 87%|████████▋ | 24438/28080 [48:16:53<7:07:58,  7.05s/it]
 87%|████████▋ | 24439/28080 [48:17:00<7:07:51,  7.05s/it]
                                                          
{'loss': 0.5914, 'learning_rate': 2.1724018071356434e-05, 'epoch': 10.44}

 87%|████████▋ | 24439/28080 [48:17:00<7:07:51,  7.05s/it]
 87%|████████▋ | 24440/28080 [48:17:07<7:08:29,  7.06s/it]
                                                          
{'loss': 0.6099, 'learning_rate': 2.1712262496544566e-05, 'epoch': 10.44}

 87%|████████▋ | 24440/28080 [48:17:07<7:08:29,  7.06s/it]
 87%|████████▋ | 24441/28080 [48:17:15<7:10:26,  7.10s/it]
                                                          
{'loss': 0.5919, 'learning_rate': 2.1700509958865604e-05, 'epoch': 10.44}

 87%|████████▋ | 24441/28080 [48:17:15<7:10:26,  7.10s/it]
 87%|████████▋ | 24442/28080 [48:17:22<7:09:05,  7.08s/it]
                                                          
{'loss': 0.6129, 'learning_rate': 2.1688760458475758e-05, 'epoch': 10.44}

 87%|████████▋ | 24442/28080 [48:17:22<7:09:05,  7.08s/it]
 87%|████████▋ | 24443/28080 [48:17:29<7:07:40,  7.06s/it]
                                                          
{'loss': 0.6032, 'learning_rate': 2.1677013995531485e-05, 'epoch': 10.44}

 87%|████████▋ | 24443/28080 [48:17:29<7:07:40,  7.06s/it]
 87%|████████▋ | 24444/28080 [48:17:36<7:07:26,  7.05s/it]
                                                          
{'loss': 0.6095, 'learning_rate': 2.1665270570188965e-05, 'epoch': 10.44}

 87%|████████▋ | 24444/28080 [48:17:36<7:07:26,  7.05s/it]
 87%|████████▋ | 24445/28080 [48:17:43<7:09:01,  7.08s/it]
                                                          
{'loss': 0.5749, 'learning_rate': 2.1653530182604492e-05, 'epoch': 10.44}

 87%|████████▋ | 24445/28080 [48:17:43<7:09:01,  7.08s/it]
 87%|████████▋ | 24446/28080 [48:17:50<7:09:11,  7.09s/it]
                                                          
{'loss': 0.6103, 'learning_rate': 2.164179283293416e-05, 'epoch': 10.44}

 87%|████████▋ | 24446/28080 [48:17:50<7:09:11,  7.09s/it]
 87%|████████▋ | 24447/28080 [48:17:57<7:07:30,  7.06s/it]
                                                          
{'loss': 0.5992, 'learning_rate': 2.1630058521334234e-05, 'epoch': 10.44}

 87%|████████▋ | 24447/28080 [48:17:57<7:07:30,  7.06s/it]
 87%|████████▋ | 24448/28080 [48:18:04<7:06:12,  7.04s/it]
                                                          
{'loss': 0.5986, 'learning_rate': 2.161832724796081e-05, 'epoch': 10.44}

 87%|████████▋ | 24448/28080 [48:18:04<7:06:12,  7.04s/it]
 87%|████████▋ | 24449/28080 [48:18:11<7:07:09,  7.06s/it]
                                                          
{'loss': 0.5851, 'learning_rate': 2.160659901296991e-05, 'epoch': 10.44}

 87%|████████▋ | 24449/28080 [48:18:11<7:07:09,  7.06s/it]
 87%|████████▋ | 24450/28080 [48:18:18<7:08:48,  7.09s/it]
                                                          
{'loss': 0.5902, 'learning_rate': 2.1594873816517564e-05, 'epoch': 10.44}

 87%|████████▋ | 24450/28080 [48:18:18<7:08:48,  7.09s/it]
 87%|████████▋ | 24451/28080 [48:18:25<7:09:24,  7.10s/it]
                                                          
{'loss': 0.6053, 'learning_rate': 2.158315165875982e-05, 'epoch': 10.45}

 87%|████████▋ | 24451/28080 [48:18:25<7:09:24,  7.10s/it]
 87%|████████▋ | 24452/28080 [48:18:32<7:07:57,  7.08s/it]
                                                          
{'loss': 0.6147, 'learning_rate': 2.1571432539852555e-05, 'epoch': 10.45}

 87%|████████▋ | 24452/28080 [48:18:32<7:07:57,  7.08s/it]
 87%|████████▋ | 24453/28080 [48:18:39<7:06:30,  7.06s/it]
                                                          
{'loss': 0.6108, 'learning_rate': 2.1559716459951806e-05, 'epoch': 10.45}

 87%|████████▋ | 24453/28080 [48:18:39<7:06:30,  7.06s/it]
 87%|████████▋ | 24454/28080 [48:18:46<7:04:35,  7.03s/it]
                                                          
{'loss': 0.6218, 'learning_rate': 2.1548003419213285e-05, 'epoch': 10.45}

 87%|████████▋ | 24454/28080 [48:18:46<7:04:35,  7.03s/it]
 87%|████████▋ | 24455/28080 [48:18:53<7:04:44,  7.03s/it]
                                                          
{'loss': 0.5988, 'learning_rate': 2.1536293417792923e-05, 'epoch': 10.45}

 87%|████████▋ | 24455/28080 [48:18:53<7:04:44,  7.03s/it]
 87%|████████▋ | 24456/28080 [48:19:00<7:03:03,  7.00s/it]
                                                          
{'loss': 0.5826, 'learning_rate': 2.1524586455846456e-05, 'epoch': 10.45}

 87%|████████▋ | 24456/28080 [48:19:00<7:03:03,  7.00s/it]
 87%|████████▋ | 24457/28080 [48:19:07<7:04:52,  7.04s/it]
                                                          
{'loss': 0.5991, 'learning_rate': 2.1512882533529705e-05, 'epoch': 10.45}

 87%|████████▋ | 24457/28080 [48:19:07<7:04:52,  7.04s/it]
 87%|████████▋ | 24458/28080 [48:19:14<7:04:40,  7.03s/it]
                                                          
{'loss': 0.5936, 'learning_rate': 2.1501181650998347e-05, 'epoch': 10.45}

 87%|████████▋ | 24458/28080 [48:19:14<7:04:40,  7.03s/it]
 87%|████████▋ | 24459/28080 [48:19:22<7:05:04,  7.04s/it]
                                                          
{'loss': 0.5879, 'learning_rate': 2.1489483808408013e-05, 'epoch': 10.45}

 87%|████████▋ | 24459/28080 [48:19:22<7:05:04,  7.04s/it]
 87%|████████▋ | 24460/28080 [48:19:29<7:05:26,  7.05s/it]
                                                          
{'loss': 0.6081, 'learning_rate': 2.1477789005914322e-05, 'epoch': 10.45}

 87%|████████▋ | 24460/28080 [48:19:29<7:05:26,  7.05s/it]
 87%|████████▋ | 24461/28080 [48:19:36<7:06:12,  7.07s/it]
                                                          
{'loss': 0.6039, 'learning_rate': 2.1466097243672933e-05, 'epoch': 10.45}

 87%|████████▋ | 24461/28080 [48:19:36<7:06:12,  7.07s/it]
 87%|████████▋ | 24462/28080 [48:19:43<7:06:06,  7.07s/it]
                                                          
{'loss': 0.6028, 'learning_rate': 2.1454408521839358e-05, 'epoch': 10.45}

 87%|████████▋ | 24462/28080 [48:19:43<7:06:06,  7.07s/it]
 87%|████████▋ | 24463/28080 [48:19:50<7:05:50,  7.06s/it]
                                                          
{'loss': 0.6389, 'learning_rate': 2.144272284056911e-05, 'epoch': 10.45}

 87%|████████▋ | 24463/28080 [48:19:50<7:05:50,  7.06s/it]
 87%|████████▋ | 24464/28080 [48:19:57<7:07:33,  7.09s/it]
                                                          
{'loss': 0.6136, 'learning_rate': 2.1431040200017626e-05, 'epoch': 10.45}

 87%|████████▋ | 24464/28080 [48:19:57<7:07:33,  7.09s/it]
 87%|████████▋ | 24465/28080 [48:20:04<7:07:46,  7.10s/it]
                                                          
{'loss': 0.6389, 'learning_rate': 2.141936060034033e-05, 'epoch': 10.45}

 87%|████████▋ | 24465/28080 [48:20:04<7:07:46,  7.10s/it]
 87%|████████▋ | 24466/28080 [48:20:11<7:06:52,  7.09s/it]
                                                          
{'loss': 0.6063, 'learning_rate': 2.140768404169266e-05, 'epoch': 10.45}

 87%|████████▋ | 24466/28080 [48:20:11<7:06:52,  7.09s/it]
 87%|████████▋ | 24467/28080 [48:20:18<7:06:48,  7.09s/it]
                                                          
{'loss': 0.619, 'learning_rate': 2.139601052422993e-05, 'epoch': 10.45}

 87%|████████▋ | 24467/28080 [48:20:18<7:06:48,  7.09s/it]
 87%|████████▋ | 24468/28080 [48:20:25<7:06:22,  7.08s/it]
                                                          
{'loss': 0.6054, 'learning_rate': 2.1384340048107437e-05, 'epoch': 10.45}

 87%|████████▋ | 24468/28080 [48:20:25<7:06:22,  7.08s/it]
 87%|████████▋ | 24469/28080 [48:20:32<7:05:46,  7.07s/it]
                                                          
{'loss': 0.5882, 'learning_rate': 2.1372672613480413e-05, 'epoch': 10.45}

 87%|████████▋ | 24469/28080 [48:20:32<7:05:46,  7.07s/it]
 87%|████████▋ | 24470/28080 [48:20:40<7:06:44,  7.09s/it]
                                                          
{'loss': 0.5928, 'learning_rate': 2.1361008220504156e-05, 'epoch': 10.45}

 87%|████████▋ | 24470/28080 [48:20:40<7:06:44,  7.09s/it]
 87%|████████▋ | 24471/28080 [48:20:47<7:05:16,  7.07s/it]
                                                          
{'loss': 0.602, 'learning_rate': 2.1349346869333764e-05, 'epoch': 10.45}

 87%|████████▋ | 24471/28080 [48:20:47<7:05:16,  7.07s/it]
 87%|████████▋ | 24472/28080 [48:20:54<7:05:20,  7.07s/it]
                                                          
{'loss': 0.603, 'learning_rate': 2.1337688560124495e-05, 'epoch': 10.45}

 87%|████████▋ | 24472/28080 [48:20:54<7:05:20,  7.07s/it]
 87%|████████▋ | 24473/28080 [48:21:01<7:04:36,  7.06s/it]
                                                          
{'loss': 0.6006, 'learning_rate': 2.1326033293031372e-05, 'epoch': 10.45}

 87%|████████▋ | 24473/28080 [48:21:01<7:04:36,  7.06s/it]
 87%|████████▋ | 24474/28080 [48:21:08<7:04:00,  7.06s/it]
                                                          
{'loss': 0.5972, 'learning_rate': 2.131438106820943e-05, 'epoch': 10.46}

 87%|████████▋ | 24474/28080 [48:21:08<7:04:00,  7.06s/it]
 87%|████████▋ | 24475/28080 [48:21:15<7:04:51,  7.07s/it]
                                                          
{'loss': 0.5832, 'learning_rate': 2.130273188581372e-05, 'epoch': 10.46}

 87%|████████▋ | 24475/28080 [48:21:15<7:04:51,  7.07s/it]
 87%|████████▋ | 24476/28080 [48:21:22<7:07:28,  7.12s/it]
                                                          
{'loss': 0.5889, 'learning_rate': 2.1291085745999277e-05, 'epoch': 10.46}

 87%|████████▋ | 24476/28080 [48:21:22<7:07:28,  7.12s/it]
 87%|████████▋ | 24477/28080 [48:21:29<7:07:27,  7.12s/it]
                                                          
{'loss': 0.5946, 'learning_rate': 2.1279442648920953e-05, 'epoch': 10.46}

 87%|████████▋ | 24477/28080 [48:21:29<7:07:27,  7.12s/it]
 87%|████████▋ | 24478/28080 [48:21:36<7:06:13,  7.10s/it]
                                                          
{'loss': 0.59, 'learning_rate': 2.1267802594733737e-05, 'epoch': 10.46}

 87%|████████▋ | 24478/28080 [48:21:36<7:06:13,  7.10s/it]
 87%|████████▋ | 24479/28080 [48:21:43<7:08:41,  7.14s/it]
                                                          
{'loss': 0.5667, 'learning_rate': 2.1256165583592364e-05, 'epoch': 10.46}

 87%|████████▋ | 24479/28080 [48:21:43<7:08:41,  7.14s/it]
 87%|████████▋ | 24480/28080 [48:21:51<7:08:12,  7.14s/it]
                                                          
{'loss': 0.5805, 'learning_rate': 2.1244531615651764e-05, 'epoch': 10.46}

 87%|████████▋ | 24480/28080 [48:21:51<7:08:12,  7.14s/it]
 87%|████████▋ | 24481/28080 [48:21:58<7:06:51,  7.12s/it]
                                                          
{'loss': 0.594, 'learning_rate': 2.1232900691066648e-05, 'epoch': 10.46}

 87%|████████▋ | 24481/28080 [48:21:58<7:06:51,  7.12s/it]
 87%|████████▋ | 24482/28080 [48:22:05<7:06:01,  7.10s/it]
                                                          
{'loss': 0.6128, 'learning_rate': 2.1221272809991864e-05, 'epoch': 10.46}

 87%|████████▋ | 24482/28080 [48:22:05<7:06:01,  7.10s/it]
 87%|████████▋ | 24483/28080 [48:22:12<7:05:26,  7.10s/it]
                                                          
{'loss': 0.5932, 'learning_rate': 2.120964797258193e-05, 'epoch': 10.46}

 87%|████████▋ | 24483/28080 [48:22:12<7:05:26,  7.10s/it]
 87%|████████▋ | 24484/28080 [48:22:19<7:04:06,  7.08s/it]
                                                          
{'loss': 0.5973, 'learning_rate': 2.1198026178991666e-05, 'epoch': 10.46}

 87%|████████▋ | 24484/28080 [48:22:19<7:04:06,  7.08s/it]
 87%|████████▋ | 24485/28080 [48:22:26<7:04:54,  7.09s/it]
                                                          
{'loss': 0.5804, 'learning_rate': 2.1186407429375553e-05, 'epoch': 10.46}

 87%|████████▋ | 24485/28080 [48:22:26<7:04:54,  7.09s/it]
 87%|████████▋ | 24486/28080 [48:22:33<7:04:54,  7.09s/it]
                                                          
{'loss': 0.5961, 'learning_rate': 2.117479172388831e-05, 'epoch': 10.46}

 87%|████████▋ | 24486/28080 [48:22:33<7:04:54,  7.09s/it]
 87%|████████▋ | 24487/28080 [48:22:40<7:05:52,  7.11s/it]
                                                          
{'loss': 0.6117, 'learning_rate': 2.116317906268442e-05, 'epoch': 10.46}

 87%|████████▋ | 24487/28080 [48:22:40<7:05:52,  7.11s/it]
 87%|████████▋ | 24488/28080 [48:22:47<7:04:39,  7.09s/it]
                                                          
{'loss': 0.6034, 'learning_rate': 2.1151569445918257e-05, 'epoch': 10.46}

 87%|████████▋ | 24488/28080 [48:22:47<7:04:39,  7.09s/it]
 87%|████████▋ | 24489/28080 [48:22:54<7:05:59,  7.12s/it]
                                                          
{'loss': 0.5854, 'learning_rate': 2.113996287374445e-05, 'epoch': 10.46}

 87%|████████▋ | 24489/28080 [48:22:54<7:05:59,  7.12s/it]
 87%|████████▋ | 24490/28080 [48:23:02<7:07:07,  7.14s/it]
                                                          
{'loss': 0.6164, 'learning_rate': 2.1128359346317268e-05, 'epoch': 10.46}

 87%|████████▋ | 24490/28080 [48:23:02<7:07:07,  7.14s/it]
 87%|████████▋ | 24491/28080 [48:23:09<7:06:32,  7.13s/it]
                                                          
{'loss': 0.5874, 'learning_rate': 2.1116758863791192e-05, 'epoch': 10.46}

 87%|████████▋ | 24491/28080 [48:23:09<7:06:32,  7.13s/it]
 87%|████████▋ | 24492/28080 [48:23:16<7:05:11,  7.11s/it]
                                                          
{'loss': 0.6041, 'learning_rate': 2.1105161426320518e-05, 'epoch': 10.46}

 87%|████████▋ | 24492/28080 [48:23:16<7:05:11,  7.11s/it]
 87%|████████▋ | 24493/28080 [48:23:23<7:03:40,  7.09s/it]
                                                          
{'loss': 0.5803, 'learning_rate': 2.109356703405954e-05, 'epoch': 10.46}

 87%|████████▋ | 24493/28080 [48:23:23<7:03:40,  7.09s/it]
 87%|████████▋ | 24494/28080 [48:23:30<7:01:50,  7.06s/it]
                                                          
{'loss': 0.5982, 'learning_rate': 2.1081975687162442e-05, 'epoch': 10.46}

 87%|████████▋ | 24494/28080 [48:23:30<7:01:50,  7.06s/it]
 87%|████████▋ | 24495/28080 [48:23:37<7:03:34,  7.09s/it]
                                                          
{'loss': 0.5722, 'learning_rate': 2.1070387385783567e-05, 'epoch': 10.46}

 87%|████████▋ | 24495/28080 [48:23:37<7:03:34,  7.09s/it]
 87%|████████▋ | 24496/28080 [48:23:44<7:04:19,  7.10s/it]
                                                          
{'loss': 0.6039, 'learning_rate': 2.1058802130076994e-05, 'epoch': 10.46}

 87%|████████▋ | 24496/28080 [48:23:44<7:04:19,  7.10s/it]
 87%|████████▋ | 24497/28080 [48:23:51<7:03:39,  7.09s/it]
                                                          
{'loss': 0.5917, 'learning_rate': 2.104721992019687e-05, 'epoch': 10.46}

 87%|████████▋ | 24497/28080 [48:23:51<7:03:39,  7.09s/it]
 87%|████████▋ | 24498/28080 [48:23:58<7:04:22,  7.11s/it]
                                                          
{'loss': 0.6028, 'learning_rate': 2.103564075629727e-05, 'epoch': 10.47}

 87%|████████▋ | 24498/28080 [48:23:58<7:04:22,  7.11s/it]
 87%|████████▋ | 24499/28080 [48:24:05<7:03:31,  7.10s/it]
                                                          
{'loss': 0.6052, 'learning_rate': 2.1024064638532293e-05, 'epoch': 10.47}

 87%|████████▋ | 24499/28080 [48:24:05<7:03:31,  7.10s/it]
 87%|████████▋ | 24500/28080 [48:24:12<7:02:44,  7.09s/it]
                                                          
{'loss': 0.6104, 'learning_rate': 2.101249156705584e-05, 'epoch': 10.47}

 87%|████████▋ | 24500/28080 [48:24:12<7:02:44,  7.09s/it]
 87%|████████▋ | 24501/28080 [48:24:20<7:04:00,  7.11s/it]
                                                          
{'loss': 0.5765, 'learning_rate': 2.1000921542022073e-05, 'epoch': 10.47}

 87%|████████▋ | 24501/28080 [48:24:20<7:04:00,  7.11s/it]
 87%|████████▋ | 24502/28080 [48:24:27<7:05:39,  7.14s/it]
                                                          
{'loss': 0.5977, 'learning_rate': 2.0989354563584695e-05, 'epoch': 10.47}

 87%|████████▋ | 24502/28080 [48:24:27<7:05:39,  7.14s/it]
 87%|████████▋ | 24503/28080 [48:24:34<7:05:22,  7.14s/it]
                                                          
{'loss': 0.5887, 'learning_rate': 2.0977790631897753e-05, 'epoch': 10.47}

 87%|████████▋ | 24503/28080 [48:24:34<7:05:22,  7.14s/it]
 87%|████████▋ | 24504/28080 [48:24:41<7:03:09,  7.10s/it]
                                                          
{'loss': 0.6021, 'learning_rate': 2.096622974711501e-05, 'epoch': 10.47}

 87%|████████▋ | 24504/28080 [48:24:41<7:03:09,  7.10s/it]
 87%|████████▋ | 24505/28080 [48:24:48<7:01:49,  7.08s/it]
                                                          
{'loss': 0.5927, 'learning_rate': 2.0954671909390322e-05, 'epoch': 10.47}

 87%|████████▋ | 24505/28080 [48:24:48<7:01:49,  7.08s/it]
 87%|████████▋ | 24506/28080 [48:24:55<7:02:42,  7.10s/it]
                                                          
{'loss': 0.5978, 'learning_rate': 2.094311711887742e-05, 'epoch': 10.47}

 87%|████████▋ | 24506/28080 [48:24:55<7:02:42,  7.10s/it]
 87%|████████▋ | 24507/28080 [48:25:02<7:03:21,  7.11s/it]
                                                          
{'loss': 0.6136, 'learning_rate': 2.0931565375730072e-05, 'epoch': 10.47}

 87%|████████▋ | 24507/28080 [48:25:02<7:03:21,  7.11s/it]
 87%|████████▋ | 24508/28080 [48:25:09<7:03:13,  7.11s/it]
                                                          
{'loss': 0.602, 'learning_rate': 2.092001668010185e-05, 'epoch': 10.47}

 87%|████████▋ | 24508/28080 [48:25:09<7:03:13,  7.11s/it]
 87%|████████▋ | 24509/28080 [48:25:16<7:01:59,  7.09s/it]
                                                          
{'loss': 0.5941, 'learning_rate': 2.090847103214655e-05, 'epoch': 10.47}

 87%|████████▋ | 24509/28080 [48:25:16<7:01:59,  7.09s/it]
 87%|████████▋ | 24510/28080 [48:25:24<7:02:03,  7.09s/it]
                                                          
{'loss': 0.5958, 'learning_rate': 2.0896928432017682e-05, 'epoch': 10.47}

 87%|████████▋ | 24510/28080 [48:25:24<7:02:03,  7.09s/it]
 87%|████████▋ | 24511/28080 [48:25:31<7:01:37,  7.09s/it]
                                                          
{'loss': 0.5975, 'learning_rate': 2.088538887986885e-05, 'epoch': 10.47}

 87%|████████▋ | 24511/28080 [48:25:31<7:01:37,  7.09s/it]
 87%|████████▋ | 24512/28080 [48:25:38<7:02:19,  7.10s/it]
                                                          
{'loss': 0.6047, 'learning_rate': 2.0873852375853542e-05, 'epoch': 10.47}

 87%|████████▋ | 24512/28080 [48:25:38<7:02:19,  7.10s/it]
 87%|████████▋ | 24513/28080 [48:25:45<7:01:14,  7.09s/it]
                                                          
{'loss': 0.5997, 'learning_rate': 2.0862318920125217e-05, 'epoch': 10.47}

 87%|████████▋ | 24513/28080 [48:25:45<7:01:14,  7.09s/it]
 87%|████████▋ | 24514/28080 [48:25:52<6:59:16,  7.05s/it]
                                                          
{'loss': 0.6226, 'learning_rate': 2.0850788512837366e-05, 'epoch': 10.47}

 87%|████████▋ | 24514/28080 [48:25:52<6:59:16,  7.05s/it]
 87%|████████▋ | 24515/28080 [48:25:59<6:59:41,  7.06s/it]
                                                          
{'loss': 0.5915, 'learning_rate': 2.083926115414339e-05, 'epoch': 10.47}

 87%|████████▋ | 24515/28080 [48:25:59<6:59:41,  7.06s/it]
 87%|████████▋ | 24516/28080 [48:26:06<7:00:06,  7.07s/it]
                                                          
{'loss': 0.6109, 'learning_rate': 2.0827736844196643e-05, 'epoch': 10.47}

 87%|████████▋ | 24516/28080 [48:26:06<7:00:06,  7.07s/it]
 87%|████████▋ | 24517/28080 [48:26:13<7:01:07,  7.09s/it]
                                                          
{'loss': 0.5912, 'learning_rate': 2.081621558315039e-05, 'epoch': 10.47}

 87%|████████▋ | 24517/28080 [48:26:13<7:01:07,  7.09s/it]
 87%|████████▋ | 24518/28080 [48:26:20<7:00:19,  7.08s/it]
                                                          
{'loss': 0.5887, 'learning_rate': 2.080469737115798e-05, 'epoch': 10.47}

 87%|████████▋ | 24518/28080 [48:26:20<7:00:19,  7.08s/it]
 87%|████████▋ | 24519/28080 [48:26:27<7:00:47,  7.09s/it]
                                                          
{'loss': 0.5873, 'learning_rate': 2.0793182208372592e-05, 'epoch': 10.47}

 87%|████████▋ | 24519/28080 [48:26:27<7:00:47,  7.09s/it]
 87%|████████▋ | 24520/28080 [48:26:34<7:01:01,  7.10s/it]
                                                          
{'loss': 0.6186, 'learning_rate': 2.0781670094947497e-05, 'epoch': 10.47}

 87%|████████▋ | 24520/28080 [48:26:34<7:01:01,  7.10s/it]
 87%|████████▋ | 24521/28080 [48:26:41<6:59:41,  7.08s/it]
                                                          
{'loss': 0.6026, 'learning_rate': 2.0770161031035822e-05, 'epoch': 10.48}

 87%|████████▋ | 24521/28080 [48:26:41<6:59:41,  7.08s/it]
 87%|████████▋ | 24522/28080 [48:26:49<7:00:47,  7.10s/it]
                                                          
{'loss': 0.6016, 'learning_rate': 2.075865501679064e-05, 'epoch': 10.48}

 87%|████████▋ | 24522/28080 [48:26:49<7:00:47,  7.10s/it]
 87%|████████▋ | 24523/28080 [48:26:56<7:00:59,  7.10s/it]
                                                          
{'loss': 0.6124, 'learning_rate': 2.074715205236505e-05, 'epoch': 10.48}

 87%|████████▋ | 24523/28080 [48:26:56<7:00:59,  7.10s/it]
 87%|████████▋ | 24524/28080 [48:27:03<7:01:33,  7.11s/it]
                                                          
{'loss': 0.6211, 'learning_rate': 2.073565213791212e-05, 'epoch': 10.48}

 87%|████████▋ | 24524/28080 [48:27:03<7:01:33,  7.11s/it]
 87%|████████▋ | 24525/28080 [48:27:10<6:59:50,  7.09s/it]
                                                          
{'loss': 0.5878, 'learning_rate': 2.0724155273584816e-05, 'epoch': 10.48}

 87%|████████▋ | 24525/28080 [48:27:10<6:59:50,  7.09s/it]
 87%|████████▋ | 24526/28080 [48:27:17<6:58:07,  7.06s/it]
                                                          
{'loss': 0.6012, 'learning_rate': 2.0712661459536098e-05, 'epoch': 10.48}

 87%|████████▋ | 24526/28080 [48:27:17<6:58:07,  7.06s/it]
 87%|████████▋ | 24527/28080 [48:27:24<6:59:07,  7.08s/it]
                                                          
{'loss': 0.6157, 'learning_rate': 2.0701170695918843e-05, 'epoch': 10.48}

 87%|████████▋ | 24527/28080 [48:27:24<6:59:07,  7.08s/it]
 87%|████████▋ | 24528/28080 [48:27:31<6:59:45,  7.09s/it]
                                                          
{'loss': 0.5996, 'learning_rate': 2.0689682982885984e-05, 'epoch': 10.48}

 87%|████████▋ | 24528/28080 [48:27:31<6:59:45,  7.09s/it]
 87%|████████▋ | 24529/28080 [48:27:38<6:58:58,  7.08s/it]
                                                          
{'loss': 0.6022, 'learning_rate': 2.067819832059034e-05, 'epoch': 10.48}

 87%|████████▋ | 24529/28080 [48:27:38<6:58:58,  7.08s/it]
 87%|████████▋ | 24530/28080 [48:27:45<6:59:28,  7.09s/it]
                                                          
{'loss': 0.6033, 'learning_rate': 2.0666716709184685e-05, 'epoch': 10.48}

 87%|████████▋ | 24530/28080 [48:27:45<6:59:28,  7.09s/it]
 87%|████████▋ | 24531/28080 [48:27:52<6:59:45,  7.10s/it]
                                                          
{'loss': 0.5889, 'learning_rate': 2.0655238148821726e-05, 'epoch': 10.48}

 87%|████████▋ | 24531/28080 [48:27:52<6:59:45,  7.10s/it]
 87%|████████▋ | 24532/28080 [48:27:59<6:59:57,  7.10s/it]
                                                          
{'loss': 0.6116, 'learning_rate': 2.0643762639654284e-05, 'epoch': 10.48}

 87%|████████▋ | 24532/28080 [48:27:59<6:59:57,  7.10s/it]
 87%|████████▋ | 24533/28080 [48:28:06<6:58:49,  7.08s/it]
                                                          
{'loss': 0.5957, 'learning_rate': 2.0632290181834906e-05, 'epoch': 10.48}

 87%|████████▋ | 24533/28080 [48:28:06<6:58:49,  7.08s/it]
 87%|████████▋ | 24534/28080 [48:28:13<6:57:16,  7.06s/it]
                                                          
{'loss': 0.6113, 'learning_rate': 2.062082077551633e-05, 'epoch': 10.48}

 87%|████████▋ | 24534/28080 [48:28:13<6:57:16,  7.06s/it]
 87%|████████▋ | 24535/28080 [48:28:21<6:59:59,  7.11s/it]
                                                          
{'loss': 0.5993, 'learning_rate': 2.060935442085113e-05, 'epoch': 10.48}

 87%|████████▋ | 24535/28080 [48:28:21<6:59:59,  7.11s/it]
 87%|████████▋ | 24536/28080 [48:28:28<7:00:19,  7.12s/it]
                                                          
{'loss': 0.601, 'learning_rate': 2.0597891117991734e-05, 'epoch': 10.48}

 87%|████████▋ | 24536/28080 [48:28:28<7:00:19,  7.12s/it]
 87%|████████▋ | 24537/28080 [48:28:35<7:00:03,  7.11s/it]
                                                          
{'loss': 0.6056, 'learning_rate': 2.0586430867090805e-05, 'epoch': 10.48}

 87%|████████▋ | 24537/28080 [48:28:35<7:00:03,  7.11s/it]
 87%|████████▋ | 24538/28080 [48:28:42<7:00:17,  7.12s/it]
                                                          
{'loss': 0.6212, 'learning_rate': 2.0574973668300662e-05, 'epoch': 10.48}

 87%|████████▋ | 24538/28080 [48:28:42<7:00:17,  7.12s/it]
 87%|████████▋ | 24539/28080 [48:28:49<6:58:02,  7.08s/it]
                                                          
{'loss': 0.5921, 'learning_rate': 2.0563519521773877e-05, 'epoch': 10.48}

 87%|████████▋ | 24539/28080 [48:28:49<6:58:02,  7.08s/it]
 87%|████████▋ | 24540/28080 [48:28:56<6:59:14,  7.11s/it]
                                                          
{'loss': 0.5957, 'learning_rate': 2.0552068427662746e-05, 'epoch': 10.48}

 87%|████████▋ | 24540/28080 [48:28:56<6:59:14,  7.11s/it]
 87%|████████▋ | 24541/28080 [48:29:03<7:00:37,  7.13s/it]
                                                          
{'loss': 0.6034, 'learning_rate': 2.0540620386119673e-05, 'epoch': 10.48}

 87%|████████▋ | 24541/28080 [48:29:03<7:00:37,  7.13s/it]
 87%|████████▋ | 24542/28080 [48:29:11<7:00:07,  7.12s/it]
                                                          
{'loss': 0.6162, 'learning_rate': 2.0529175397296845e-05, 'epoch': 10.48}

 87%|████████▋ | 24542/28080 [48:29:11<7:00:07,  7.12s/it]
 87%|████████▋ | 24543/28080 [48:29:18<7:00:15,  7.13s/it]
                                                          
{'loss': 0.6053, 'learning_rate': 2.0517733461346665e-05, 'epoch': 10.48}

 87%|████████▋ | 24543/28080 [48:29:18<7:00:15,  7.13s/it]
 87%|████████▋ | 24544/28080 [48:29:25<6:57:40,  7.09s/it]
                                                          
{'loss': 0.6165, 'learning_rate': 2.050629457842129e-05, 'epoch': 10.48}

 87%|████████▋ | 24544/28080 [48:29:25<6:57:40,  7.09s/it]
 87%|████████▋ | 24545/28080 [48:29:32<6:58:51,  7.11s/it]
                                                          
{'loss': 0.6173, 'learning_rate': 2.0494858748672935e-05, 'epoch': 10.49}

 87%|████████▋ | 24545/28080 [48:29:32<6:58:51,  7.11s/it]
 87%|████████▋ | 24546/28080 [48:29:39<6:58:16,  7.10s/it]
                                                          
{'loss': 0.583, 'learning_rate': 2.048342597225364e-05, 'epoch': 10.49}

 87%|████████▋ | 24546/28080 [48:29:39<6:58:16,  7.10s/it]
 87%|████████▋ | 24547/28080 [48:29:46<6:57:31,  7.09s/it]
                                                          
{'loss': 0.5906, 'learning_rate': 2.0471996249315643e-05, 'epoch': 10.49}

 87%|████████▋ | 24547/28080 [48:29:46<6:57:31,  7.09s/it]
 87%|████████▋ | 24548/28080 [48:29:53<6:57:21,  7.09s/it]
                                                          
{'loss': 0.5845, 'learning_rate': 2.0460569580010914e-05, 'epoch': 10.49}

 87%|████████▋ | 24548/28080 [48:29:53<6:57:21,  7.09s/it]
 87%|████████▋ | 24549/28080 [48:30:00<6:55:39,  7.06s/it]
                                                          
{'loss': 0.6058, 'learning_rate': 2.0449145964491572e-05, 'epoch': 10.49}

 87%|████████▋ | 24549/28080 [48:30:00<6:55:39,  7.06s/it]
 87%|████████▋ | 24550/28080 [48:30:07<6:57:54,  7.10s/it]
                                                          
{'loss': 0.5912, 'learning_rate': 2.0437725402909447e-05, 'epoch': 10.49}

 87%|████████▋ | 24550/28080 [48:30:07<6:57:54,  7.10s/it]
 87%|████████▋ | 24551/28080 [48:30:14<6:58:45,  7.12s/it]
                                                          
{'loss': 0.5815, 'learning_rate': 2.0426307895416608e-05, 'epoch': 10.49}

 87%|████████▋ | 24551/28080 [48:30:14<6:58:45,  7.12s/it]
 87%|████████▋ | 24552/28080 [48:30:22<6:58:17,  7.11s/it]
                                                          
{'loss': 0.6053, 'learning_rate': 2.041489344216485e-05, 'epoch': 10.49}

 87%|████████▋ | 24552/28080 [48:30:22<6:58:17,  7.11s/it]
 87%|████████▋ | 24553/28080 [48:30:29<6:59:29,  7.14s/it]
                                                          
{'loss': 0.6025, 'learning_rate': 2.0403482043306138e-05, 'epoch': 10.49}

 87%|████████▋ | 24553/28080 [48:30:29<6:59:29,  7.14s/it]
 87%|████████▋ | 24554/28080 [48:30:36<6:59:27,  7.14s/it]
                                                          
{'loss': 0.6032, 'learning_rate': 2.0392073698992236e-05, 'epoch': 10.49}

 87%|████████▋ | 24554/28080 [48:30:36<6:59:27,  7.14s/it]
 87%|████████▋ | 24555/28080 [48:30:43<6:59:03,  7.13s/it]
                                                          
{'loss': 0.5883, 'learning_rate': 2.0380668409374915e-05, 'epoch': 10.49}

 87%|████████▋ | 24555/28080 [48:30:43<6:59:03,  7.13s/it]
 87%|████████▋ | 24556/28080 [48:30:50<6:58:57,  7.13s/it]
                                                          
{'loss': 0.5866, 'learning_rate': 2.0369266174605883e-05, 'epoch': 10.49}

 87%|████████▋ | 24556/28080 [48:30:50<6:58:57,  7.13s/it]
 87%|████████▋ | 24557/28080 [48:30:57<6:56:31,  7.09s/it]
                                                          
{'loss': 0.5879, 'learning_rate': 2.035786699483691e-05, 'epoch': 10.49}

 87%|████████▋ | 24557/28080 [48:30:57<6:56:31,  7.09s/it]
 87%|████████▋ | 24558/28080 [48:31:04<6:56:55,  7.10s/it]
                                                          
{'loss': 0.589, 'learning_rate': 2.0346470870219597e-05, 'epoch': 10.49}

 87%|████████▋ | 24558/28080 [48:31:04<6:56:55,  7.10s/it]
 87%|████████▋ | 24559/28080 [48:31:11<6:57:27,  7.11s/it]
                                                          
{'loss': 0.5825, 'learning_rate': 2.033507780090557e-05, 'epoch': 10.49}

 87%|████████▋ | 24559/28080 [48:31:11<6:57:27,  7.11s/it]
 87%|████████▋ | 24560/28080 [48:31:18<6:57:39,  7.12s/it]
                                                          
{'loss': 0.5921, 'learning_rate': 2.0323687787046407e-05, 'epoch': 10.49}

 87%|████████▋ | 24560/28080 [48:31:19<6:57:39,  7.12s/it]
 87%|████████▋ | 24561/28080 [48:31:26<6:57:23,  7.12s/it]
                                                          
{'loss': 0.5937, 'learning_rate': 2.031230082879357e-05, 'epoch': 10.49}

 87%|████████▋ | 24561/28080 [48:31:26<6:57:23,  7.12s/it]
 87%|████████▋ | 24562/28080 [48:31:33<6:56:21,  7.10s/it]
                                                          
{'loss': 0.6043, 'learning_rate': 2.0300916926298678e-05, 'epoch': 10.49}

 87%|████████▋ | 24562/28080 [48:31:33<6:56:21,  7.10s/it]
 87%|████████▋ | 24563/28080 [48:31:40<6:57:27,  7.12s/it]
                                                          
{'loss': 0.5979, 'learning_rate': 2.0289536079713123e-05, 'epoch': 10.49}

 87%|████████▋ | 24563/28080 [48:31:40<6:57:27,  7.12s/it]
 87%|████████▋ | 24564/28080 [48:31:47<6:59:09,  7.15s/it]
                                                          
{'loss': 0.5881, 'learning_rate': 2.0278158289188304e-05, 'epoch': 10.49}

 87%|████████▋ | 24564/28080 [48:31:47<6:59:09,  7.15s/it]
 87%|████████▋ | 24565/28080 [48:31:54<6:57:49,  7.13s/it]
                                                          
{'loss': 0.6051, 'learning_rate': 2.0266783554875547e-05, 'epoch': 10.49}

 87%|████████▋ | 24565/28080 [48:31:54<6:57:49,  7.13s/it]
 87%|████████▋ | 24566/28080 [48:32:01<6:57:14,  7.12s/it]
                                                          
{'loss': 0.6029, 'learning_rate': 2.0255411876926284e-05, 'epoch': 10.49}

 87%|████████▋ | 24566/28080 [48:32:01<6:57:14,  7.12s/it]
 87%|████████▋ | 24567/28080 [48:32:08<6:57:40,  7.13s/it]
                                                          
{'loss': 0.5884, 'learning_rate': 2.024404325549173e-05, 'epoch': 10.49}

 87%|████████▋ | 24567/28080 [48:32:08<6:57:40,  7.13s/it]
 87%|████████▋ | 24568/28080 [48:32:16<6:57:51,  7.14s/it]
                                                          
{'loss': 0.591, 'learning_rate': 2.0232677690723206e-05, 'epoch': 10.5}

 87%|████████▋ | 24568/28080 [48:32:16<6:57:51,  7.14s/it]
 87%|████████▋ | 24569/28080 [48:32:23<6:55:16,  7.10s/it]
                                                          
{'loss': 0.6056, 'learning_rate': 2.0221315182771787e-05, 'epoch': 10.5}

 87%|████████▋ | 24569/28080 [48:32:23<6:55:16,  7.10s/it]
 88%|████████▊ | 24570/28080 [48:32:30<6:55:37,  7.10s/it]
                                                          
{'loss': 0.5855, 'learning_rate': 2.020995573178877e-05, 'epoch': 10.5}

 88%|████████▊ | 24570/28080 [48:32:30<6:55:37,  7.10s/it]
 88%|████████▊ | 24571/28080 [48:32:37<6:54:20,  7.08s/it]
                                                          
{'loss': 0.5858, 'learning_rate': 2.01985993379252e-05, 'epoch': 10.5}

 88%|████████▊ | 24571/28080 [48:32:37<6:54:20,  7.08s/it]
 88%|████████▊ | 24572/28080 [48:32:44<6:53:56,  7.08s/it]
                                                          
{'loss': 0.6202, 'learning_rate': 2.018724600133223e-05, 'epoch': 10.5}

 88%|████████▊ | 24572/28080 [48:32:44<6:53:56,  7.08s/it]
 88%|████████▊ | 24573/28080 [48:32:51<6:54:16,  7.09s/it]
                                                          
{'loss': 0.606, 'learning_rate': 2.0175895722160857e-05, 'epoch': 10.5}

 88%|████████▊ | 24573/28080 [48:32:51<6:54:16,  7.09s/it]
 88%|████████▊ | 24574/28080 [48:32:58<6:55:52,  7.12s/it]
                                                          
{'loss': 0.59, 'learning_rate': 2.0164548500562097e-05, 'epoch': 10.5}

 88%|████████▊ | 24574/28080 [48:32:58<6:55:52,  7.12s/it]
 88%|████████▊ | 24575/28080 [48:33:05<6:55:43,  7.12s/it]
                                                          
{'loss': 0.6146, 'learning_rate': 2.0153204336686882e-05, 'epoch': 10.5}

 88%|████████▊ | 24575/28080 [48:33:05<6:55:43,  7.12s/it]
 88%|████████▊ | 24576/28080 [48:33:12<6:54:05,  7.09s/it]
                                                          
{'loss': 0.5928, 'learning_rate': 2.0141863230686174e-05, 'epoch': 10.5}

 88%|████████▊ | 24576/28080 [48:33:12<6:54:05,  7.09s/it]
 88%|████████▊ | 24577/28080 [48:33:19<6:53:06,  7.08s/it]
                                                          
{'loss': 0.619, 'learning_rate': 2.0130525182710883e-05, 'epoch': 10.5}

 88%|████████▊ | 24577/28080 [48:33:19<6:53:06,  7.08s/it]
 88%|████████▊ | 24578/28080 [48:33:26<6:53:31,  7.08s/it]
                                                          
{'loss': 0.6014, 'learning_rate': 2.011919019291178e-05, 'epoch': 10.5}

 88%|████████▊ | 24578/28080 [48:33:26<6:53:31,  7.08s/it]
 88%|████████▊ | 24579/28080 [48:33:34<6:54:27,  7.10s/it]
                                                          
{'loss': 0.6022, 'learning_rate': 2.0107858261439683e-05, 'epoch': 10.5}

 88%|████████▊ | 24579/28080 [48:33:34<6:54:27,  7.10s/it]
 88%|████████▊ | 24580/28080 [48:33:41<6:54:43,  7.11s/it]
                                                          
{'loss': 0.5842, 'learning_rate': 2.009652938844539e-05, 'epoch': 10.5}

 88%|████████▊ | 24580/28080 [48:33:41<6:54:43,  7.11s/it]
 88%|████████▊ | 24581/28080 [48:33:48<6:54:37,  7.11s/it]
                                                          
{'loss': 0.6115, 'learning_rate': 2.008520357407956e-05, 'epoch': 10.5}

 88%|████████▊ | 24581/28080 [48:33:48<6:54:37,  7.11s/it]
 88%|████████▊ | 24582/28080 [48:33:55<6:55:27,  7.13s/it]
                                                          
{'loss': 0.6033, 'learning_rate': 2.0073880818492927e-05, 'epoch': 10.5}

 88%|████████▊ | 24582/28080 [48:33:55<6:55:27,  7.13s/it]
 88%|████████▊ | 24583/28080 [48:34:02<6:56:26,  7.15s/it]
                                                          
{'loss': 0.6015, 'learning_rate': 2.006256112183613e-05, 'epoch': 10.5}

 88%|████████▊ | 24583/28080 [48:34:02<6:56:26,  7.15s/it]
 88%|████████▊ | 24584/28080 [48:34:09<6:54:44,  7.12s/it]
                                                          
{'loss': 0.6055, 'learning_rate': 2.005124448425974e-05, 'epoch': 10.5}

 88%|████████▊ | 24584/28080 [48:34:09<6:54:44,  7.12s/it]
 88%|████████▊ | 24585/28080 [48:34:16<6:54:20,  7.11s/it]
                                                          
{'loss': 0.591, 'learning_rate': 2.0039930905914327e-05, 'epoch': 10.5}

 88%|████████▊ | 24585/28080 [48:34:16<6:54:20,  7.11s/it]
 88%|████████▊ | 24586/28080 [48:34:23<6:53:09,  7.09s/it]
                                                          
{'loss': 0.6003, 'learning_rate': 2.002862038695033e-05, 'epoch': 10.5}

 88%|████████▊ | 24586/28080 [48:34:23<6:53:09,  7.09s/it]
 88%|████████▊ | 24587/28080 [48:34:31<6:54:33,  7.12s/it]
                                                          
{'loss': 0.608, 'learning_rate': 2.001731292751835e-05, 'epoch': 10.5}

 88%|████████▊ | 24587/28080 [48:34:31<6:54:33,  7.12s/it]
 88%|████████▊ | 24588/28080 [48:34:38<6:53:51,  7.11s/it]
                                                          
{'loss': 0.6058, 'learning_rate': 2.0006008527768767e-05, 'epoch': 10.5}

 88%|████████▊ | 24588/28080 [48:34:38<6:53:51,  7.11s/it]
 88%|████████▊ | 24589/28080 [48:34:45<6:52:57,  7.10s/it]
                                                          
{'loss': 0.6195, 'learning_rate': 1.9994707187851958e-05, 'epoch': 10.5}

 88%|████████▊ | 24589/28080 [48:34:45<6:52:57,  7.10s/it]
 88%|████████▊ | 24590/28080 [48:34:52<6:51:46,  7.08s/it]
                                                          
{'loss': 0.6048, 'learning_rate': 1.998340890791825e-05, 'epoch': 10.5}

 88%|████████▊ | 24590/28080 [48:34:52<6:51:46,  7.08s/it]
 88%|████████▊ | 24591/28080 [48:34:59<6:51:17,  7.07s/it]
                                                          
{'loss': 0.5996, 'learning_rate': 1.997211368811802e-05, 'epoch': 10.51}

 88%|████████▊ | 24591/28080 [48:34:59<6:51:17,  7.07s/it]
 88%|████████▊ | 24592/28080 [48:35:06<6:51:42,  7.08s/it]
                                                          
{'loss': 0.6142, 'learning_rate': 1.9960821528601513e-05, 'epoch': 10.51}

 88%|████████▊ | 24592/28080 [48:35:06<6:51:42,  7.08s/it]
 88%|████████▊ | 24593/28080 [48:35:13<6:51:40,  7.08s/it]
                                                          
{'loss': 0.5976, 'learning_rate': 1.994953242951897e-05, 'epoch': 10.51}

 88%|████████▊ | 24593/28080 [48:35:13<6:51:40,  7.08s/it]
 88%|████████▊ | 24594/28080 [48:35:20<6:51:51,  7.09s/it]
                                                          
{'loss': 0.5811, 'learning_rate': 1.9938246391020516e-05, 'epoch': 10.51}

 88%|████████▊ | 24594/28080 [48:35:20<6:51:51,  7.09s/it]
 88%|████████▊ | 24595/28080 [48:35:27<6:53:21,  7.12s/it]
                                                          
{'loss': 0.5988, 'learning_rate': 1.9926963413256394e-05, 'epoch': 10.51}

 88%|████████▊ | 24595/28080 [48:35:27<6:53:21,  7.12s/it]
 88%|████████▊ | 24596/28080 [48:35:34<6:52:08,  7.10s/it]
                                                          
{'loss': 0.5973, 'learning_rate': 1.9915683496376652e-05, 'epoch': 10.51}

 88%|████████▊ | 24596/28080 [48:35:34<6:52:08,  7.10s/it]
 88%|████████▊ | 24597/28080 [48:35:41<6:51:27,  7.09s/it]
                                                          
{'loss': 0.6135, 'learning_rate': 1.9904406640531446e-05, 'epoch': 10.51}

 88%|████████▊ | 24597/28080 [48:35:41<6:51:27,  7.09s/it]
 88%|████████▊ | 24598/28080 [48:35:48<6:50:22,  7.07s/it]
                                                          
{'loss': 0.6068, 'learning_rate': 1.989313284587063e-05, 'epoch': 10.51}

 88%|████████▊ | 24598/28080 [48:35:48<6:50:22,  7.07s/it]
 88%|████████▊ | 24599/28080 [48:35:55<6:50:52,  7.08s/it]
                                                          
{'loss': 0.607, 'learning_rate': 1.9881862112544363e-05, 'epoch': 10.51}

 88%|████████▊ | 24599/28080 [48:35:55<6:50:52,  7.08s/it]
 88%|████████▊ | 24600/28080 [48:36:03<6:52:06,  7.11s/it]
                                                          
{'loss': 0.6081, 'learning_rate': 1.9870594440702467e-05, 'epoch': 10.51}

 88%|████████▊ | 24600/28080 [48:36:03<6:52:06,  7.11s/it]
 88%|████████▊ | 24601/28080 [48:36:10<6:53:22,  7.13s/it]
                                                          
{'loss': 0.6081, 'learning_rate': 1.985932983049493e-05, 'epoch': 10.51}

 88%|████████▊ | 24601/28080 [48:36:10<6:53:22,  7.13s/it]
 88%|████████▊ | 24602/28080 [48:36:17<6:53:22,  7.13s/it]
                                                          
{'loss': 0.6037, 'learning_rate': 1.9848068282071614e-05, 'epoch': 10.51}

 88%|████████▊ | 24602/28080 [48:36:17<6:53:22,  7.13s/it]
 88%|████████▊ | 24603/28080 [48:36:24<6:50:40,  7.09s/it]
                                                          
{'loss': 0.6134, 'learning_rate': 1.9836809795582307e-05, 'epoch': 10.51}

 88%|████████▊ | 24603/28080 [48:36:24<6:50:40,  7.09s/it]
 88%|████████▊ | 24604/28080 [48:36:31<6:50:50,  7.09s/it]
                                                          
{'loss': 0.6214, 'learning_rate': 1.9825554371176752e-05, 'epoch': 10.51}

 88%|████████▊ | 24604/28080 [48:36:31<6:50:50,  7.09s/it]
 88%|████████▊ | 24605/28080 [48:36:38<6:49:55,  7.08s/it]
                                                          
{'loss': 0.5838, 'learning_rate': 1.9814302009004777e-05, 'epoch': 10.51}

 88%|████████▊ | 24605/28080 [48:36:38<6:49:55,  7.08s/it]
 88%|████████▊ | 24606/28080 [48:36:45<6:50:47,  7.09s/it]
                                                          
{'loss': 0.6022, 'learning_rate': 1.9803052709216034e-05, 'epoch': 10.51}

 88%|████████▊ | 24606/28080 [48:36:45<6:50:47,  7.09s/it]
 88%|████████▊ | 24607/28080 [48:36:52<6:52:09,  7.12s/it]
                                                          
{'loss': 0.5725, 'learning_rate': 1.9791806471960218e-05, 'epoch': 10.51}

 88%|████████▊ | 24607/28080 [48:36:52<6:52:09,  7.12s/it]
 88%|████████▊ | 24608/28080 [48:36:59<6:51:00,  7.10s/it]
                                                          
{'loss': 0.5917, 'learning_rate': 1.9780563297386868e-05, 'epoch': 10.51}

 88%|████████▊ | 24608/28080 [48:36:59<6:51:00,  7.10s/it]
 88%|████████▊ | 24609/28080 [48:37:07<6:50:25,  7.09s/it]
                                                          
{'loss': 0.5875, 'learning_rate': 1.976932318564567e-05, 'epoch': 10.51}

 88%|████████▊ | 24609/28080 [48:37:07<6:50:25,  7.09s/it]
 88%|████████▊ | 24610/28080 [48:37:14<6:49:35,  7.08s/it]
                                                          
{'loss': 0.6135, 'learning_rate': 1.9758086136886096e-05, 'epoch': 10.51}

 88%|████████▊ | 24610/28080 [48:37:14<6:49:35,  7.08s/it]
 88%|████████▊ | 24611/28080 [48:37:21<6:49:55,  7.09s/it]
                                                          
{'loss': 0.5975, 'learning_rate': 1.9746852151257656e-05, 'epoch': 10.51}

 88%|████████▊ | 24611/28080 [48:37:21<6:49:55,  7.09s/it]
 88%|████████▊ | 24612/28080 [48:37:28<6:50:22,  7.10s/it]
                                                          
{'loss': 0.5912, 'learning_rate': 1.9735621228909846e-05, 'epoch': 10.51}

 88%|████████▊ | 24612/28080 [48:37:28<6:50:22,  7.10s/it]
 88%|████████▊ | 24613/28080 [48:37:35<6:49:17,  7.08s/it]
                                                          
{'loss': 0.5882, 'learning_rate': 1.972439336999196e-05, 'epoch': 10.51}

 88%|████████▊ | 24613/28080 [48:37:35<6:49:17,  7.08s/it]
 88%|████████▊ | 24614/28080 [48:37:42<6:49:10,  7.08s/it]
                                                          
{'loss': 0.5929, 'learning_rate': 1.9713168574653523e-05, 'epoch': 10.51}

 88%|████████▊ | 24614/28080 [48:37:42<6:49:10,  7.08s/it]
 88%|████████▊ | 24615/28080 [48:37:49<6:49:29,  7.09s/it]
                                                          
{'loss': 0.5761, 'learning_rate': 1.9701946843043745e-05, 'epoch': 10.52}

 88%|████████▊ | 24615/28080 [48:37:49<6:49:29,  7.09s/it]
 88%|████████▊ | 24616/28080 [48:37:56<6:50:44,  7.11s/it]
                                                          
{'loss': 0.5787, 'learning_rate': 1.969072817531209e-05, 'epoch': 10.52}

 88%|████████▊ | 24616/28080 [48:37:56<6:50:44,  7.11s/it]
 88%|████████▊ | 24617/28080 [48:38:03<6:50:13,  7.11s/it]
                                                          
{'loss': 0.6138, 'learning_rate': 1.9679512571607604e-05, 'epoch': 10.52}

 88%|████████▊ | 24617/28080 [48:38:03<6:50:13,  7.11s/it]
 88%|████████▊ | 24618/28080 [48:38:10<6:49:51,  7.10s/it]
                                                          
{'loss': 0.6117, 'learning_rate': 1.9668300032079617e-05, 'epoch': 10.52}

 88%|████████▊ | 24618/28080 [48:38:10<6:49:51,  7.10s/it]
 88%|████████▊ | 24619/28080 [48:38:18<6:50:16,  7.11s/it]
                                                          
{'loss': 0.6027, 'learning_rate': 1.9657090556877255e-05, 'epoch': 10.52}

 88%|████████▊ | 24619/28080 [48:38:18<6:50:16,  7.11s/it]
 88%|████████▊ | 24620/28080 [48:38:25<6:49:26,  7.10s/it]
                                                          
{'loss': 0.618, 'learning_rate': 1.9645884146149705e-05, 'epoch': 10.52}

 88%|████████▊ | 24620/28080 [48:38:25<6:49:26,  7.10s/it]
 88%|████████▊ | 24621/28080 [48:38:32<6:50:20,  7.12s/it]
                                                          
{'loss': 0.5908, 'learning_rate': 1.9634680800046046e-05, 'epoch': 10.52}

 88%|████████▊ | 24621/28080 [48:38:32<6:50:20,  7.12s/it]
 88%|████████▊ | 24622/28080 [48:38:39<6:51:11,  7.13s/it]
                                                          
{'loss': 0.5841, 'learning_rate': 1.962348051871529e-05, 'epoch': 10.52}

 88%|████████▊ | 24622/28080 [48:38:39<6:51:11,  7.13s/it]
 88%|████████▊ | 24623/28080 [48:38:46<6:50:14,  7.12s/it]
                                                          
{'loss': 0.621, 'learning_rate': 1.961228330230641e-05, 'epoch': 10.52}

 88%|████████▊ | 24623/28080 [48:38:46<6:50:14,  7.12s/it]
 88%|████████▊ | 24624/28080 [48:38:53<6:50:45,  7.13s/it]
                                                          
{'loss': 0.6009, 'learning_rate': 1.9601089150968476e-05, 'epoch': 10.52}

 88%|████████▊ | 24624/28080 [48:38:53<6:50:45,  7.13s/it]
 88%|████████▊ | 24625/28080 [48:39:00<6:48:31,  7.09s/it]
                                                          
{'loss': 0.5994, 'learning_rate': 1.958989806485034e-05, 'epoch': 10.52}

 88%|████████▊ | 24625/28080 [48:39:00<6:48:31,  7.09s/it]
 88%|████████▊ | 24626/28080 [48:39:07<6:48:13,  7.09s/it]
                                                          
{'loss': 0.5879, 'learning_rate': 1.9578710044100943e-05, 'epoch': 10.52}

 88%|████████▊ | 24626/28080 [48:39:07<6:48:13,  7.09s/it]
 88%|████████▊ | 24627/28080 [48:39:14<6:46:58,  7.07s/it]
                                                          
{'loss': 0.5985, 'learning_rate': 1.9567525088869027e-05, 'epoch': 10.52}

 88%|████████▊ | 24627/28080 [48:39:14<6:46:58,  7.07s/it]
 88%|████████▊ | 24628/28080 [48:39:21<6:47:40,  7.09s/it]
                                                          
{'loss': 0.5733, 'learning_rate': 1.955634319930352e-05, 'epoch': 10.52}

 88%|████████▊ | 24628/28080 [48:39:21<6:47:40,  7.09s/it]
 88%|████████▊ | 24629/28080 [48:39:29<6:48:36,  7.10s/it]
                                                          
{'loss': 0.5971, 'learning_rate': 1.9545164375553093e-05, 'epoch': 10.52}

 88%|████████▊ | 24629/28080 [48:39:29<6:48:36,  7.10s/it]
 88%|████████▊ | 24630/28080 [48:39:36<6:47:46,  7.09s/it]
                                                          
{'loss': 0.587, 'learning_rate': 1.953398861776659e-05, 'epoch': 10.52}

 88%|████████▊ | 24630/28080 [48:39:36<6:47:46,  7.09s/it]
 88%|████████▊ | 24631/28080 [48:39:43<6:47:05,  7.08s/it]
                                                          
{'loss': 0.5867, 'learning_rate': 1.952281592609251e-05, 'epoch': 10.52}

 88%|████████▊ | 24631/28080 [48:39:43<6:47:05,  7.08s/it]
 88%|████████▊ | 24632/28080 [48:39:50<6:46:48,  7.08s/it]
                                                          
{'loss': 0.603, 'learning_rate': 1.951164630067964e-05, 'epoch': 10.52}

 88%|████████▊ | 24632/28080 [48:39:50<6:46:48,  7.08s/it]
 88%|████████▊ | 24633/28080 [48:39:57<6:47:20,  7.09s/it]
                                                          
{'loss': 0.5941, 'learning_rate': 1.9500479741676513e-05, 'epoch': 10.52}

 88%|████████▊ | 24633/28080 [48:39:57<6:47:20,  7.09s/it]
 88%|████████▊ | 24634/28080 [48:40:04<6:48:24,  7.11s/it]
                                                          
{'loss': 0.599, 'learning_rate': 1.9489316249231727e-05, 'epoch': 10.52}

 88%|████████▊ | 24634/28080 [48:40:04<6:48:24,  7.11s/it]
 88%|████████▊ | 24635/28080 [48:40:11<6:47:57,  7.11s/it]
                                                          
{'loss': 0.6002, 'learning_rate': 1.94781558234938e-05, 'epoch': 10.52}

 88%|████████▊ | 24635/28080 [48:40:11<6:47:57,  7.11s/it]
 88%|████████▊ | 24636/28080 [48:40:18<6:48:51,  7.12s/it]
                                                          
{'loss': 0.5899, 'learning_rate': 1.9466998464611195e-05, 'epoch': 10.52}

 88%|████████▊ | 24636/28080 [48:40:18<6:48:51,  7.12s/it]
 88%|████████▊ | 24637/28080 [48:40:25<6:49:02,  7.13s/it]
                                                          
{'loss': 0.6228, 'learning_rate': 1.945584417273233e-05, 'epoch': 10.52}

 88%|████████▊ | 24637/28080 [48:40:25<6:49:02,  7.13s/it]
 88%|████████▊ | 24638/28080 [48:40:33<6:48:04,  7.11s/it]
                                                          
{'loss': 0.6016, 'learning_rate': 1.944469294800558e-05, 'epoch': 10.53}

 88%|████████▊ | 24638/28080 [48:40:33<6:48:04,  7.11s/it]
 88%|████████▊ | 24639/28080 [48:40:40<6:47:37,  7.11s/it]
                                                          
{'loss': 0.6298, 'learning_rate': 1.9433544790579404e-05, 'epoch': 10.53}

 88%|████████▊ | 24639/28080 [48:40:40<6:47:37,  7.11s/it]
 88%|████████▊ | 24640/28080 [48:40:47<6:46:34,  7.09s/it]
                                                          
{'loss': 0.6213, 'learning_rate': 1.9422399700602028e-05, 'epoch': 10.53}

 88%|████████▊ | 24640/28080 [48:40:47<6:46:34,  7.09s/it]
 88%|████████▊ | 24641/28080 [48:40:54<6:46:07,  7.09s/it]
                                                          
{'loss': 0.6029, 'learning_rate': 1.9411257678221772e-05, 'epoch': 10.53}

 88%|████████▊ | 24641/28080 [48:40:54<6:46:07,  7.09s/it]
 88%|████████▊ | 24642/28080 [48:41:01<6:44:53,  7.07s/it]
                                                          
{'loss': 0.6142, 'learning_rate': 1.9400118723586796e-05, 'epoch': 10.53}

 88%|████████▊ | 24642/28080 [48:41:01<6:44:53,  7.07s/it]
 88%|████████▊ | 24643/28080 [48:41:08<6:47:10,  7.11s/it]
                                                          
{'loss': 0.5828, 'learning_rate': 1.938898283684537e-05, 'epoch': 10.53}

 88%|████████▊ | 24643/28080 [48:41:08<6:47:10,  7.11s/it]
 88%|████████▊ | 24644/28080 [48:41:15<6:47:32,  7.12s/it]
                                                          
{'loss': 0.6054, 'learning_rate': 1.93778500181456e-05, 'epoch': 10.53}

 88%|████████▊ | 24644/28080 [48:41:15<6:47:32,  7.12s/it]
 88%|████████▊ | 24645/28080 [48:41:22<6:46:57,  7.11s/it]
                                                          
{'loss': 0.6059, 'learning_rate': 1.9366720267635696e-05, 'epoch': 10.53}

 88%|████████▊ | 24645/28080 [48:41:22<6:46:57,  7.11s/it]
 88%|████████▊ | 24646/28080 [48:41:29<6:46:35,  7.10s/it]
                                                          
{'loss': 0.6028, 'learning_rate': 1.9355593585463544e-05, 'epoch': 10.53}

 88%|████████▊ | 24646/28080 [48:41:29<6:46:35,  7.10s/it]
 88%|████████▊ | 24647/28080 [48:41:36<6:47:24,  7.12s/it]
                                                          
{'loss': 0.6068, 'learning_rate': 1.934446997177733e-05, 'epoch': 10.53}

 88%|████████▊ | 24647/28080 [48:41:36<6:47:24,  7.12s/it]
 88%|████████▊ | 24648/28080 [48:41:44<6:47:14,  7.12s/it]
                                                          
{'loss': 0.5875, 'learning_rate': 1.933334942672496e-05, 'epoch': 10.53}

 88%|████████▊ | 24648/28080 [48:41:44<6:47:14,  7.12s/it]
 88%|████████▊ | 24649/28080 [48:41:51<6:48:28,  7.14s/it]
                                                          
{'loss': 0.61, 'learning_rate': 1.9322231950454434e-05, 'epoch': 10.53}

 88%|████████▊ | 24649/28080 [48:41:51<6:48:28,  7.14s/it]
 88%|████████▊ | 24650/28080 [48:41:58<6:47:48,  7.13s/it]
                                                          
{'loss': 0.6202, 'learning_rate': 1.9311117543113655e-05, 'epoch': 10.53}

 88%|████████▊ | 24650/28080 [48:41:58<6:47:48,  7.13s/it]
 88%|████████▊ | 24651/28080 [48:42:05<6:46:50,  7.12s/it]
                                                          
{'loss': 0.6227, 'learning_rate': 1.930000620485045e-05, 'epoch': 10.53}

 88%|████████▊ | 24651/28080 [48:42:05<6:46:50,  7.12s/it]
 88%|████████▊ | 24652/28080 [48:42:12<6:47:18,  7.13s/it]
                                                          
{'loss': 0.6075, 'learning_rate': 1.928889793581262e-05, 'epoch': 10.53}

 88%|████████▊ | 24652/28080 [48:42:12<6:47:18,  7.13s/it]
 88%|████████▊ | 24653/28080 [48:42:19<6:46:34,  7.12s/it]
                                                          
{'loss': 0.5981, 'learning_rate': 1.927779273614805e-05, 'epoch': 10.53}

 88%|████████▊ | 24653/28080 [48:42:19<6:46:34,  7.12s/it]
 88%|████████▊ | 24654/28080 [48:42:26<6:45:03,  7.09s/it]
                                                          
{'loss': 0.6085, 'learning_rate': 1.9266690606004415e-05, 'epoch': 10.53}

 88%|████████▊ | 24654/28080 [48:42:26<6:45:03,  7.09s/it]
 88%|████████▊ | 24655/28080 [48:42:33<6:44:53,  7.09s/it]
                                                          
{'loss': 0.5875, 'learning_rate': 1.9255591545529416e-05, 'epoch': 10.53}

 88%|████████▊ | 24655/28080 [48:42:33<6:44:53,  7.09s/it]
 88%|████████▊ | 24656/28080 [48:42:40<6:42:52,  7.06s/it]
                                                          
{'loss': 0.5897, 'learning_rate': 1.9244495554870706e-05, 'epoch': 10.53}

 88%|████████▊ | 24656/28080 [48:42:40<6:42:52,  7.06s/it]
 88%|████████▊ | 24657/28080 [48:42:47<6:42:37,  7.06s/it]
                                                          
{'loss': 0.5965, 'learning_rate': 1.9233402634175946e-05, 'epoch': 10.53}

 88%|████████▊ | 24657/28080 [48:42:47<6:42:37,  7.06s/it]
 88%|████████▊ | 24658/28080 [48:42:54<6:43:19,  7.07s/it]
                                                          
{'loss': 0.6056, 'learning_rate': 1.9222312783592683e-05, 'epoch': 10.53}

 88%|████████▊ | 24658/28080 [48:42:54<6:43:19,  7.07s/it]
 88%|████████▊ | 24659/28080 [48:43:02<6:44:17,  7.09s/it]
                                                          
{'loss': 0.6046, 'learning_rate': 1.921122600326852e-05, 'epoch': 10.53}

 88%|████████▊ | 24659/28080 [48:43:02<6:44:17,  7.09s/it]
 88%|████████▊ | 24660/28080 [48:43:09<6:43:56,  7.09s/it]
                                                          
{'loss': 0.5989, 'learning_rate': 1.9200142293350875e-05, 'epoch': 10.53}

 88%|████████▊ | 24660/28080 [48:43:09<6:43:56,  7.09s/it]
 88%|████████▊ | 24661/28080 [48:43:16<6:44:02,  7.09s/it]
                                                          
{'loss': 0.5879, 'learning_rate': 1.9189061653987205e-05, 'epoch': 10.53}

 88%|████████▊ | 24661/28080 [48:43:16<6:44:02,  7.09s/it]
 88%|████████▊ | 24662/28080 [48:43:23<6:43:31,  7.08s/it]
                                                          
{'loss': 0.5933, 'learning_rate': 1.9177984085324978e-05, 'epoch': 10.54}

 88%|████████▊ | 24662/28080 [48:43:23<6:43:31,  7.08s/it]
 88%|████████▊ | 24663/28080 [48:43:30<6:44:15,  7.10s/it]
                                                          
{'loss': 0.587, 'learning_rate': 1.9166909587511494e-05, 'epoch': 10.54}

 88%|████████▊ | 24663/28080 [48:43:30<6:44:15,  7.10s/it]
 88%|████████▊ | 24664/28080 [48:43:37<6:43:10,  7.08s/it]
                                                          
{'loss': 0.6036, 'learning_rate': 1.9155838160694243e-05, 'epoch': 10.54}

 88%|████████▊ | 24664/28080 [48:43:37<6:43:10,  7.08s/it]
 88%|████████▊ | 24665/28080 [48:43:44<6:43:18,  7.09s/it]
                                                          
{'loss': 0.5821, 'learning_rate': 1.9144769805020335e-05, 'epoch': 10.54}

 88%|████████▊ | 24665/28080 [48:43:44<6:43:18,  7.09s/it]
 88%|████████▊ | 24666/28080 [48:43:51<6:43:21,  7.09s/it]
                                                          
{'loss': 0.5872, 'learning_rate': 1.9133704520637146e-05, 'epoch': 10.54}

 88%|████████▊ | 24666/28080 [48:43:51<6:43:21,  7.09s/it]
 88%|████████▊ | 24667/28080 [48:43:58<6:43:37,  7.10s/it]
                                                          
{'loss': 0.5817, 'learning_rate': 1.9122642307691813e-05, 'epoch': 10.54}

 88%|████████▊ | 24667/28080 [48:43:58<6:43:37,  7.10s/it]
 88%|████████▊ | 24668/28080 [48:44:05<6:44:12,  7.11s/it]
                                                          
{'loss': 0.5946, 'learning_rate': 1.9111583166331547e-05, 'epoch': 10.54}

 88%|████████▊ | 24668/28080 [48:44:05<6:44:12,  7.11s/it]
 88%|████████▊ | 24669/28080 [48:44:13<6:44:34,  7.12s/it]
                                                          
{'loss': 0.5787, 'learning_rate': 1.9100527096703514e-05, 'epoch': 10.54}

 88%|████████▊ | 24669/28080 [48:44:13<6:44:34,  7.12s/it]
 88%|████████▊ | 24670/28080 [48:44:20<6:44:02,  7.11s/it]
                                                          
{'loss': 0.5864, 'learning_rate': 1.9089474098954756e-05, 'epoch': 10.54}

 88%|████████▊ | 24670/28080 [48:44:20<6:44:02,  7.11s/it]
 88%|████████▊ | 24671/28080 [48:44:27<6:42:43,  7.09s/it]
                                                          
{'loss': 0.5972, 'learning_rate': 1.9078424173232274e-05, 'epoch': 10.54}

 88%|████████▊ | 24671/28080 [48:44:27<6:42:43,  7.09s/it]
 88%|████████▊ | 24672/28080 [48:44:34<6:40:11,  7.05s/it]
                                                          
{'loss': 0.6033, 'learning_rate': 1.9067377319683167e-05, 'epoch': 10.54}

 88%|████████▊ | 24672/28080 [48:44:34<6:40:11,  7.05s/it]
 88%|████████▊ | 24673/28080 [48:44:41<6:40:31,  7.05s/it]
                                                          
{'loss': 0.6101, 'learning_rate': 1.9056333538454375e-05, 'epoch': 10.54}

 88%|████████▊ | 24673/28080 [48:44:41<6:40:31,  7.05s/it]
 88%|████████▊ | 24674/28080 [48:44:48<6:42:27,  7.09s/it]
                                                          
{'loss': 0.5992, 'learning_rate': 1.9045292829692807e-05, 'epoch': 10.54}

 88%|████████▊ | 24674/28080 [48:44:48<6:42:27,  7.09s/it]
 88%|████████▊ | 24675/28080 [48:44:55<6:41:04,  7.07s/it]
                                                          
{'loss': 0.5903, 'learning_rate': 1.903425519354532e-05, 'epoch': 10.54}

 88%|████████▊ | 24675/28080 [48:44:55<6:41:04,  7.07s/it]
 88%|████████▊ | 24676/28080 [48:45:02<6:41:59,  7.09s/it]
                                                          
{'loss': 0.6066, 'learning_rate': 1.902322063015882e-05, 'epoch': 10.54}

 88%|████████▊ | 24676/28080 [48:45:02<6:41:59,  7.09s/it]
 88%|████████▊ | 24677/28080 [48:45:09<6:41:37,  7.08s/it]
                                                          
{'loss': 0.5968, 'learning_rate': 1.9012189139680057e-05, 'epoch': 10.54}

 88%|████████▊ | 24677/28080 [48:45:09<6:41:37,  7.08s/it]
 88%|████████▊ | 24678/28080 [48:45:16<6:41:53,  7.09s/it]
                                                          
{'loss': 0.5911, 'learning_rate': 1.900116072225591e-05, 'epoch': 10.54}

 88%|████████▊ | 24678/28080 [48:45:16<6:41:53,  7.09s/it]
 88%|████████▊ | 24679/28080 [48:45:23<6:41:29,  7.08s/it]
                                                          
{'loss': 0.6277, 'learning_rate': 1.8990135378032904e-05, 'epoch': 10.54}

 88%|████████▊ | 24679/28080 [48:45:23<6:41:29,  7.08s/it]
 88%|████████▊ | 24680/28080 [48:45:30<6:41:17,  7.08s/it]
                                                          
{'loss': 0.6261, 'learning_rate': 1.8979113107157886e-05, 'epoch': 10.54}

 88%|████████▊ | 24680/28080 [48:45:30<6:41:17,  7.08s/it]
 88%|████████▊ | 24681/28080 [48:45:37<6:41:10,  7.08s/it]
                                                          
{'loss': 0.6159, 'learning_rate': 1.8968093909777383e-05, 'epoch': 10.54}

 88%|████████▊ | 24681/28080 [48:45:37<6:41:10,  7.08s/it]
 88%|████████▊ | 24682/28080 [48:45:45<6:41:34,  7.09s/it]
                                                          
{'loss': 0.6267, 'learning_rate': 1.8957077786038114e-05, 'epoch': 10.54}

 88%|████████▊ | 24682/28080 [48:45:45<6:41:34,  7.09s/it]
 88%|████████▊ | 24683/28080 [48:45:52<6:41:17,  7.09s/it]
                                                          
{'loss': 0.6062, 'learning_rate': 1.8946064736086566e-05, 'epoch': 10.54}

 88%|████████▊ | 24683/28080 [48:45:52<6:41:17,  7.09s/it]
 88%|████████▊ | 24684/28080 [48:45:59<6:43:05,  7.12s/it]
                                                          
{'loss': 0.5924, 'learning_rate': 1.893505476006924e-05, 'epoch': 10.54}

 88%|████████▊ | 24684/28080 [48:45:59<6:43:05,  7.12s/it]
 88%|████████▊ | 24685/28080 [48:46:06<6:43:25,  7.13s/it]
                                                          
{'loss': 0.6127, 'learning_rate': 1.892404785813265e-05, 'epoch': 10.55}

 88%|████████▊ | 24685/28080 [48:46:06<6:43:25,  7.13s/it]
 88%|████████▊ | 24686/28080 [48:46:13<6:42:57,  7.12s/it]
                                                          
{'loss': 0.6008, 'learning_rate': 1.891304403042318e-05, 'epoch': 10.55}

 88%|████████▊ | 24686/28080 [48:46:13<6:42:57,  7.12s/it]
 88%|████████▊ | 24687/28080 [48:46:20<6:43:17,  7.13s/it]
                                                          
{'loss': 0.5883, 'learning_rate': 1.8902043277087276e-05, 'epoch': 10.55}

 88%|████████▊ | 24687/28080 [48:46:20<6:43:17,  7.13s/it]
 88%|████████▊ | 24688/28080 [48:46:27<6:44:06,  7.15s/it]
                                                          
{'loss': 0.6138, 'learning_rate': 1.889104559827129e-05, 'epoch': 10.55}

 88%|████████▊ | 24688/28080 [48:46:27<6:44:06,  7.15s/it]
 88%|████████▊ | 24689/28080 [48:46:35<6:42:58,  7.13s/it]
                                                          
{'loss': 0.6034, 'learning_rate': 1.8880050994121546e-05, 'epoch': 10.55}

 88%|████████▊ | 24689/28080 [48:46:35<6:42:58,  7.13s/it]
 88%|████████▊ | 24690/28080 [48:46:42<6:42:57,  7.13s/it]
                                                          
{'loss': 0.6, 'learning_rate': 1.8869059464784207e-05, 'epoch': 10.55}

 88%|████████▊ | 24690/28080 [48:46:42<6:42:57,  7.13s/it]
 88%|████████▊ | 24691/28080 [48:46:49<6:41:43,  7.11s/it]
                                                          
{'loss': 0.5855, 'learning_rate': 1.8858071010405653e-05, 'epoch': 10.55}

 88%|████████▊ | 24691/28080 [48:46:49<6:41:43,  7.11s/it]
 88%|████████▊ | 24692/28080 [48:46:56<6:40:13,  7.09s/it]
                                                          
{'loss': 0.5875, 'learning_rate': 1.8847085631131994e-05, 'epoch': 10.55}

 88%|████████▊ | 24692/28080 [48:46:56<6:40:13,  7.09s/it]
 88%|████████▊ | 24693/28080 [48:47:03<6:41:19,  7.11s/it]
                                                          
{'loss': 0.5956, 'learning_rate': 1.8836103327109415e-05, 'epoch': 10.55}

 88%|████████▊ | 24693/28080 [48:47:03<6:41:19,  7.11s/it]
 88%|████████▊ | 24694/28080 [48:47:10<6:41:05,  7.11s/it]
                                                          
{'loss': 0.6116, 'learning_rate': 1.882512409848394e-05, 'epoch': 10.55}

 88%|████████▊ | 24694/28080 [48:47:10<6:41:05,  7.11s/it]
 88%|████████▊ | 24695/28080 [48:47:17<6:43:15,  7.15s/it]
                                                          
{'loss': 0.6199, 'learning_rate': 1.8814147945401762e-05, 'epoch': 10.55}

 88%|████████▊ | 24695/28080 [48:47:17<6:43:15,  7.15s/it]
 88%|████████▊ | 24696/28080 [48:47:24<6:41:33,  7.12s/it]
                                                          
{'loss': 0.6052, 'learning_rate': 1.8803174868008782e-05, 'epoch': 10.55}

 88%|████████▊ | 24696/28080 [48:47:24<6:41:33,  7.12s/it]
 88%|████████▊ | 24697/28080 [48:47:31<6:41:44,  7.13s/it]
                                                          
{'loss': 0.6259, 'learning_rate': 1.8792204866451083e-05, 'epoch': 10.55}

 88%|████████▊ | 24697/28080 [48:47:32<6:41:44,  7.13s/it]
 88%|████████▊ | 24698/28080 [48:47:39<6:41:08,  7.12s/it]
                                                          
{'loss': 0.5863, 'learning_rate': 1.8781237940874606e-05, 'epoch': 10.55}

 88%|████████▊ | 24698/28080 [48:47:39<6:41:08,  7.12s/it]
 88%|████████▊ | 24699/28080 [48:47:46<6:42:00,  7.13s/it]
                                                          
{'loss': 0.5849, 'learning_rate': 1.8770274091425204e-05, 'epoch': 10.55}

 88%|████████▊ | 24699/28080 [48:47:46<6:42:00,  7.13s/it]
 88%|████████▊ | 24700/28080 [48:47:53<6:39:33,  7.09s/it]
                                                          
{'loss': 0.6026, 'learning_rate': 1.8759313318248704e-05, 'epoch': 10.55}

 88%|████████▊ | 24700/28080 [48:47:53<6:39:33,  7.09s/it]
 88%|████████▊ | 24701/28080 [48:48:00<6:38:54,  7.08s/it]
                                                          
{'loss': 0.5918, 'learning_rate': 1.8748355621491047e-05, 'epoch': 10.55}

 88%|████████▊ | 24701/28080 [48:48:00<6:38:54,  7.08s/it]
 88%|████████▊ | 24702/28080 [48:48:07<6:39:04,  7.09s/it]
                                                          
{'loss': 0.6014, 'learning_rate': 1.873740100129795e-05, 'epoch': 10.55}

 88%|████████▊ | 24702/28080 [48:48:07<6:39:04,  7.09s/it]
 88%|████████▊ | 24703/28080 [48:48:14<6:37:32,  7.06s/it]
                                                          
{'loss': 0.6226, 'learning_rate': 1.8726449457815126e-05, 'epoch': 10.55}

 88%|████████▊ | 24703/28080 [48:48:14<6:37:32,  7.06s/it]
 88%|████████▊ | 24704/28080 [48:48:21<6:37:56,  7.07s/it]
                                                          
{'loss': 0.5775, 'learning_rate': 1.8715500991188296e-05, 'epoch': 10.55}

 88%|████████▊ | 24704/28080 [48:48:21<6:37:56,  7.07s/it]
 88%|████████▊ | 24705/28080 [48:48:28<6:38:37,  7.09s/it]
                                                          
{'loss': 0.5931, 'learning_rate': 1.8704555601563145e-05, 'epoch': 10.55}

 88%|████████▊ | 24705/28080 [48:48:28<6:38:37,  7.09s/it]
 88%|████████▊ | 24706/28080 [48:48:35<6:39:52,  7.11s/it]
                                                          
{'loss': 0.5853, 'learning_rate': 1.8693613289085225e-05, 'epoch': 10.55}

 88%|████████▊ | 24706/28080 [48:48:35<6:39:52,  7.11s/it]
 88%|████████▊ | 24707/28080 [48:48:42<6:40:26,  7.12s/it]
                                                          
{'loss': 0.587, 'learning_rate': 1.868267405390023e-05, 'epoch': 10.55}

 88%|████████▊ | 24707/28080 [48:48:42<6:40:26,  7.12s/it]
 88%|████████▊ | 24708/28080 [48:48:50<6:39:50,  7.11s/it]
                                                          
{'loss': 0.6113, 'learning_rate': 1.8671737896153534e-05, 'epoch': 10.56}

 88%|████████▊ | 24708/28080 [48:48:50<6:39:50,  7.11s/it]
 88%|████████▊ | 24709/28080 [48:48:57<6:40:24,  7.13s/it]
                                                          
{'loss': 0.5806, 'learning_rate': 1.866080481599078e-05, 'epoch': 10.56}

 88%|████████▊ | 24709/28080 [48:48:57<6:40:24,  7.13s/it]
 88%|████████▊ | 24710/28080 [48:49:04<6:40:48,  7.14s/it]
                                                          
{'loss': 0.5839, 'learning_rate': 1.8649874813557343e-05, 'epoch': 10.56}

 88%|████████▊ | 24710/28080 [48:49:04<6:40:48,  7.14s/it]
 88%|████████▊ | 24711/28080 [48:49:11<6:41:19,  7.15s/it]
                                                          
{'loss': 0.602, 'learning_rate': 1.8638947888998612e-05, 'epoch': 10.56}

 88%|████████▊ | 24711/28080 [48:49:11<6:41:19,  7.15s/it]
 88%|████████▊ | 24712/28080 [48:49:18<6:40:08,  7.13s/it]
                                                          
{'loss': 0.5957, 'learning_rate': 1.8628024042460085e-05, 'epoch': 10.56}

 88%|████████▊ | 24712/28080 [48:49:18<6:40:08,  7.13s/it]
 88%|████████▊ | 24713/28080 [48:49:25<6:39:57,  7.13s/it]
                                                          
{'loss': 0.5966, 'learning_rate': 1.8617103274086916e-05, 'epoch': 10.56}

 88%|████████▊ | 24713/28080 [48:49:25<6:39:57,  7.13s/it]
 88%|████████▊ | 24714/28080 [48:49:32<6:39:09,  7.12s/it]
                                                          
{'loss': 0.6211, 'learning_rate': 1.860618558402455e-05, 'epoch': 10.56}

 88%|████████▊ | 24714/28080 [48:49:32<6:39:09,  7.12s/it]
 88%|████████▊ | 24715/28080 [48:49:39<6:38:42,  7.11s/it]
                                                          
{'loss': 0.5943, 'learning_rate': 1.859527097241809e-05, 'epoch': 10.56}

 88%|████████▊ | 24715/28080 [48:49:39<6:38:42,  7.11s/it]
 88%|████████▊ | 24716/28080 [48:49:47<6:40:20,  7.14s/it]
                                                          
{'loss': 0.5963, 'learning_rate': 1.858435943941289e-05, 'epoch': 10.56}

 88%|████████▊ | 24716/28080 [48:49:47<6:40:20,  7.14s/it]
 88%|████████▊ | 24717/28080 [48:49:54<6:38:52,  7.12s/it]
                                                          
{'loss': 0.6249, 'learning_rate': 1.8573450985154033e-05, 'epoch': 10.56}

 88%|████████▊ | 24717/28080 [48:49:54<6:38:52,  7.12s/it]
 88%|████████▊ | 24718/28080 [48:50:01<6:36:10,  7.07s/it]
                                                          
{'loss': 0.6086, 'learning_rate': 1.856254560978668e-05, 'epoch': 10.56}

 88%|████████▊ | 24718/28080 [48:50:01<6:36:10,  7.07s/it]
 88%|████████▊ | 24719/28080 [48:50:08<6:36:22,  7.08s/it]
                                                          
{'loss': 0.5944, 'learning_rate': 1.8551643313455823e-05, 'epoch': 10.56}

 88%|████████▊ | 24719/28080 [48:50:08<6:36:22,  7.08s/it]
 88%|████████▊ | 24720/28080 [48:50:15<6:38:16,  7.11s/it]
                                                          
{'loss': 0.6137, 'learning_rate': 1.8540744096306654e-05, 'epoch': 10.56}

 88%|████████▊ | 24720/28080 [48:50:15<6:38:16,  7.11s/it]
 88%|████████▊ | 24721/28080 [48:50:22<6:39:11,  7.13s/it]
                                                          
{'loss': 0.6107, 'learning_rate': 1.8529847958484088e-05, 'epoch': 10.56}

 88%|████████▊ | 24721/28080 [48:50:22<6:39:11,  7.13s/it]
 88%|████████▊ | 24722/28080 [48:50:29<6:37:36,  7.10s/it]
                                                          
{'loss': 0.5953, 'learning_rate': 1.851895490013311e-05, 'epoch': 10.56}

 88%|████████▊ | 24722/28080 [48:50:29<6:37:36,  7.10s/it]
 88%|████████▊ | 24723/28080 [48:50:36<6:37:16,  7.10s/it]
                                                          
{'loss': 0.625, 'learning_rate': 1.850806492139856e-05, 'epoch': 10.56}

 88%|████████▊ | 24723/28080 [48:50:36<6:37:16,  7.10s/it]
 88%|████████▊ | 24724/28080 [48:50:43<6:37:17,  7.10s/it]
                                                          
{'loss': 0.5928, 'learning_rate': 1.8497178022425454e-05, 'epoch': 10.56}

 88%|████████▊ | 24724/28080 [48:50:43<6:37:17,  7.10s/it]
 88%|████████▊ | 24725/28080 [48:50:50<6:36:22,  7.09s/it]
                                                          
{'loss': 0.5905, 'learning_rate': 1.848629420335854e-05, 'epoch': 10.56}

 88%|████████▊ | 24725/28080 [48:50:50<6:36:22,  7.09s/it]
 88%|████████▊ | 24726/28080 [48:50:58<6:36:08,  7.09s/it]
                                                          
{'loss': 0.5864, 'learning_rate': 1.84754134643427e-05, 'epoch': 10.56}

 88%|████████▊ | 24726/28080 [48:50:58<6:36:08,  7.09s/it]
 88%|████████▊ | 24727/28080 [48:51:05<6:35:29,  7.08s/it]
                                                          
{'loss': 0.5986, 'learning_rate': 1.846453580552257e-05, 'epoch': 10.56}

 88%|████████▊ | 24727/28080 [48:51:05<6:35:29,  7.08s/it]
 88%|████████▊ | 24728/28080 [48:51:12<6:36:58,  7.11s/it]
                                                          
{'loss': 0.5763, 'learning_rate': 1.845366122704295e-05, 'epoch': 10.56}

 88%|████████▊ | 24728/28080 [48:51:12<6:36:58,  7.11s/it]
 88%|████████▊ | 24729/28080 [48:51:19<6:36:41,  7.10s/it]
                                                          
{'loss': 0.5926, 'learning_rate': 1.844278972904845e-05, 'epoch': 10.56}

 88%|████████▊ | 24729/28080 [48:51:19<6:36:41,  7.10s/it]
 88%|████████▊ | 24730/28080 [48:51:26<6:36:15,  7.10s/it]
                                                          
{'loss': 0.5751, 'learning_rate': 1.8431921311683808e-05, 'epoch': 10.56}

 88%|████████▊ | 24730/28080 [48:51:26<6:36:15,  7.10s/it]
 88%|████████▊ | 24731/28080 [48:51:33<6:36:29,  7.10s/it]
                                                          
{'loss': 0.6113, 'learning_rate': 1.8421055975093554e-05, 'epoch': 10.56}

 88%|████████▊ | 24731/28080 [48:51:33<6:36:29,  7.10s/it]
 88%|████████▊ | 24732/28080 [48:51:40<6:36:54,  7.11s/it]
                                                          
{'loss': 0.5917, 'learning_rate': 1.8410193719422236e-05, 'epoch': 10.57}

 88%|████████▊ | 24732/28080 [48:51:40<6:36:54,  7.11s/it]
 88%|████████▊ | 24733/28080 [48:51:47<6:37:09,  7.12s/it]
                                                          
{'loss': 0.5811, 'learning_rate': 1.839933454481435e-05, 'epoch': 10.57}

 88%|████████▊ | 24733/28080 [48:51:47<6:37:09,  7.12s/it]
 88%|████████▊ | 24734/28080 [48:51:54<6:35:35,  7.09s/it]
                                                          
{'loss': 0.6061, 'learning_rate': 1.838847845141442e-05, 'epoch': 10.57}

 88%|████████▊ | 24734/28080 [48:51:54<6:35:35,  7.09s/it]
 88%|████████▊ | 24735/28080 [48:52:01<6:35:54,  7.10s/it]
                                                          
{'loss': 0.5967, 'learning_rate': 1.837762543936683e-05, 'epoch': 10.57}

 88%|████████▊ | 24735/28080 [48:52:01<6:35:54,  7.10s/it]
 88%|████████▊ | 24736/28080 [48:52:09<6:35:10,  7.09s/it]
                                                          
{'loss': 0.5848, 'learning_rate': 1.836677550881599e-05, 'epoch': 10.57}

 88%|████████▊ | 24736/28080 [48:52:09<6:35:10,  7.09s/it]
 88%|████████▊ | 24737/28080 [48:52:16<6:34:06,  7.07s/it]
                                                          
{'loss': 0.6101, 'learning_rate': 1.8355928659906234e-05, 'epoch': 10.57}

 88%|████████▊ | 24737/28080 [48:52:16<6:34:06,  7.07s/it]
 88%|████████▊ | 24738/28080 [48:52:23<6:34:21,  7.08s/it]
                                                          
{'loss': 0.6127, 'learning_rate': 1.8345084892781862e-05, 'epoch': 10.57}

 88%|████████▊ | 24738/28080 [48:52:23<6:34:21,  7.08s/it]
 88%|████████▊ | 24739/28080 [48:52:30<6:33:35,  7.07s/it]
                                                          
{'loss': 0.6109, 'learning_rate': 1.8334244207587143e-05, 'epoch': 10.57}

 88%|████████▊ | 24739/28080 [48:52:30<6:33:35,  7.07s/it]
 88%|████████▊ | 24740/28080 [48:52:37<6:34:46,  7.09s/it]
                                                          
{'loss': 0.6234, 'learning_rate': 1.832340660446635e-05, 'epoch': 10.57}

 88%|████████▊ | 24740/28080 [48:52:37<6:34:46,  7.09s/it]
 88%|████████▊ | 24741/28080 [48:52:44<6:33:15,  7.07s/it]
                                                          
{'loss': 0.6099, 'learning_rate': 1.83125720835636e-05, 'epoch': 10.57}

 88%|████████▊ | 24741/28080 [48:52:44<6:33:15,  7.07s/it]
 88%|████████▊ | 24742/28080 [48:52:51<6:31:44,  7.04s/it]
                                                          
{'loss': 0.5918, 'learning_rate': 1.8301740645023047e-05, 'epoch': 10.57}

 88%|████████▊ | 24742/28080 [48:52:51<6:31:44,  7.04s/it]
 88%|████████▊ | 24743/28080 [48:52:58<6:32:08,  7.05s/it]
                                                          
{'loss': 0.5759, 'learning_rate': 1.8290912288988825e-05, 'epoch': 10.57}

 88%|████████▊ | 24743/28080 [48:52:58<6:32:08,  7.05s/it]
 88%|████████▊ | 24744/28080 [48:53:05<6:32:21,  7.06s/it]
                                                          
{'loss': 0.6118, 'learning_rate': 1.8280087015604935e-05, 'epoch': 10.57}

 88%|████████▊ | 24744/28080 [48:53:05<6:32:21,  7.06s/it]
 88%|████████▊ | 24745/28080 [48:53:12<6:32:37,  7.06s/it]
                                                          
{'loss': 0.5915, 'learning_rate': 1.8269264825015454e-05, 'epoch': 10.57}

 88%|████████▊ | 24745/28080 [48:53:12<6:32:37,  7.06s/it]
 88%|████████▊ | 24746/28080 [48:53:19<6:33:50,  7.09s/it]
                                                          
{'loss': 0.5989, 'learning_rate': 1.8258445717364374e-05, 'epoch': 10.57}

 88%|████████▊ | 24746/28080 [48:53:19<6:33:50,  7.09s/it]
 88%|████████▊ | 24747/28080 [48:53:26<6:34:15,  7.10s/it]
                                                          
{'loss': 0.6061, 'learning_rate': 1.8247629692795587e-05, 'epoch': 10.57}

 88%|████████▊ | 24747/28080 [48:53:26<6:34:15,  7.10s/it]
 88%|████████▊ | 24748/28080 [48:53:33<6:34:48,  7.11s/it]
                                                          
{'loss': 0.6186, 'learning_rate': 1.8236816751452972e-05, 'epoch': 10.57}

 88%|████████▊ | 24748/28080 [48:53:33<6:34:48,  7.11s/it]
 88%|████████▊ | 24749/28080 [48:53:41<6:34:20,  7.10s/it]
                                                          
{'loss': 0.6032, 'learning_rate': 1.8226006893480447e-05, 'epoch': 10.57}

 88%|████████▊ | 24749/28080 [48:53:41<6:34:20,  7.10s/it]
 88%|████████▊ | 24750/28080 [48:53:48<6:34:45,  7.11s/it]
                                                          
{'loss': 0.6045, 'learning_rate': 1.821520011902178e-05, 'epoch': 10.57}

 88%|████████▊ | 24750/28080 [48:53:48<6:34:45,  7.11s/it]
 88%|████████▊ | 24751/28080 [48:53:55<6:34:49,  7.12s/it]
                                                          
{'loss': 0.6145, 'learning_rate': 1.820439642822075e-05, 'epoch': 10.57}

 88%|████████▊ | 24751/28080 [48:53:55<6:34:49,  7.12s/it]
 88%|████████▊ | 24752/28080 [48:54:02<6:33:57,  7.10s/it]
                                                          
{'loss': 0.5936, 'learning_rate': 1.819359582122107e-05, 'epoch': 10.57}

 88%|████████▊ | 24752/28080 [48:54:02<6:33:57,  7.10s/it]
 88%|████████▊ | 24753/28080 [48:54:09<6:34:58,  7.12s/it]
                                                          
{'loss': 0.5849, 'learning_rate': 1.818279829816652e-05, 'epoch': 10.57}

 88%|████████▊ | 24753/28080 [48:54:09<6:34:58,  7.12s/it]
 88%|████████▊ | 24754/28080 [48:54:16<6:35:53,  7.14s/it]
                                                          
{'loss': 0.6042, 'learning_rate': 1.8172003859200646e-05, 'epoch': 10.57}

 88%|████████▊ | 24754/28080 [48:54:16<6:35:53,  7.14s/it]
 88%|████████▊ | 24755/28080 [48:54:23<6:34:41,  7.12s/it]
                                                          
{'loss': 0.5869, 'learning_rate': 1.816121250446712e-05, 'epoch': 10.58}

 88%|████████▊ | 24755/28080 [48:54:23<6:34:41,  7.12s/it]
 88%|████████▊ | 24756/28080 [48:54:30<6:34:18,  7.12s/it]
                                                          
{'loss': 0.5786, 'learning_rate': 1.815042423410945e-05, 'epoch': 10.58}

 88%|████████▊ | 24756/28080 [48:54:30<6:34:18,  7.12s/it]
 88%|████████▊ | 24757/28080 [48:54:38<6:34:58,  7.13s/it]
                                                          
{'loss': 0.5806, 'learning_rate': 1.8139639048271234e-05, 'epoch': 10.58}

 88%|████████▊ | 24757/28080 [48:54:38<6:34:58,  7.13s/it]
 88%|████████▊ | 24758/28080 [48:54:45<6:34:58,  7.13s/it]
                                                          
{'loss': 0.5918, 'learning_rate': 1.812885694709587e-05, 'epoch': 10.58}

 88%|████████▊ | 24758/28080 [48:54:45<6:34:58,  7.13s/it]
 88%|████████▊ | 24759/28080 [48:54:52<6:35:24,  7.14s/it]
                                                          
{'loss': 0.596, 'learning_rate': 1.8118077930726896e-05, 'epoch': 10.58}

 88%|████████▊ | 24759/28080 [48:54:52<6:35:24,  7.14s/it]
 88%|████████▊ | 24760/28080 [48:54:59<6:34:29,  7.13s/it]
                                                          
{'loss': 0.581, 'learning_rate': 1.810730199930774e-05, 'epoch': 10.58}

 88%|████████▊ | 24760/28080 [48:54:59<6:34:29,  7.13s/it]
 88%|████████▊ | 24761/28080 [48:55:06<6:34:39,  7.13s/it]
                                                          
{'loss': 0.6146, 'learning_rate': 1.80965291529816e-05, 'epoch': 10.58}

 88%|████████▊ | 24761/28080 [48:55:06<6:34:39,  7.13s/it]
 88%|████████▊ | 24762/28080 [48:55:13<6:33:41,  7.12s/it]
                                                          
{'loss': 0.6052, 'learning_rate': 1.8085759391891943e-05, 'epoch': 10.58}

 88%|████████▊ | 24762/28080 [48:55:13<6:33:41,  7.12s/it]
 88%|████████▊ | 24763/28080 [48:55:20<6:32:57,  7.11s/it]
                                                          
{'loss': 0.5831, 'learning_rate': 1.807499271618196e-05, 'epoch': 10.58}

 88%|████████▊ | 24763/28080 [48:55:20<6:32:57,  7.11s/it]
 88%|████████▊ | 24764/28080 [48:55:27<6:33:30,  7.12s/it]
                                                          
{'loss': 0.5773, 'learning_rate': 1.806422912599498e-05, 'epoch': 10.58}

 88%|████████▊ | 24764/28080 [48:55:27<6:33:30,  7.12s/it]
 88%|████████▊ | 24765/28080 [48:55:35<6:33:12,  7.12s/it]
                                                          
{'loss': 0.5823, 'learning_rate': 1.8053468621474167e-05, 'epoch': 10.58}

 88%|████████▊ | 24765/28080 [48:55:35<6:33:12,  7.12s/it]
 88%|████████▊ | 24766/28080 [48:55:42<6:32:48,  7.11s/it]
                                                          
{'loss': 0.6012, 'learning_rate': 1.8042711202762658e-05, 'epoch': 10.58}

 88%|████████▊ | 24766/28080 [48:55:42<6:32:48,  7.11s/it]
 88%|████████▊ | 24767/28080 [48:55:49<6:32:49,  7.11s/it]
                                                          
{'loss': 0.5895, 'learning_rate': 1.803195687000353e-05, 'epoch': 10.58}

 88%|████████▊ | 24767/28080 [48:55:49<6:32:49,  7.11s/it]
 88%|████████▊ | 24768/28080 [48:55:56<6:33:02,  7.12s/it]
                                                          
{'loss': 0.6019, 'learning_rate': 1.8021205623339975e-05, 'epoch': 10.58}

 88%|████████▊ | 24768/28080 [48:55:56<6:33:02,  7.12s/it]
 88%|████████▊ | 24769/28080 [48:56:03<6:32:30,  7.11s/it]
                                                          
{'loss': 0.5959, 'learning_rate': 1.8010457462914936e-05, 'epoch': 10.58}

 88%|████████▊ | 24769/28080 [48:56:03<6:32:30,  7.11s/it]
 88%|████████▊ | 24770/28080 [48:56:10<6:32:56,  7.12s/it]
                                                          
{'loss': 0.5951, 'learning_rate': 1.7999712388871436e-05, 'epoch': 10.58}

 88%|████████▊ | 24770/28080 [48:56:10<6:32:56,  7.12s/it]
 88%|████████▊ | 24771/28080 [48:56:17<6:33:04,  7.13s/it]
                                                          
{'loss': 0.5836, 'learning_rate': 1.798897040135239e-05, 'epoch': 10.58}

 88%|████████▊ | 24771/28080 [48:56:17<6:33:04,  7.13s/it]
 88%|████████▊ | 24772/28080 [48:56:24<6:33:04,  7.13s/it]
                                                          
{'loss': 0.5974, 'learning_rate': 1.7978231500500762e-05, 'epoch': 10.58}

 88%|████████▊ | 24772/28080 [48:56:24<6:33:04,  7.13s/it]
 88%|████████▊ | 24773/28080 [48:56:32<6:32:44,  7.13s/it]
                                                          
{'loss': 0.6068, 'learning_rate': 1.796749568645939e-05, 'epoch': 10.58}

 88%|████████▊ | 24773/28080 [48:56:32<6:32:44,  7.13s/it]
 88%|████████▊ | 24774/28080 [48:56:39<6:32:12,  7.12s/it]
                                                          
{'loss': 0.5933, 'learning_rate': 1.7956762959371153e-05, 'epoch': 10.58}

 88%|████████▊ | 24774/28080 [48:56:39<6:32:12,  7.12s/it]
 88%|████████▊ | 24775/28080 [48:56:46<6:33:03,  7.14s/it]
                                                          
{'loss': 0.6034, 'learning_rate': 1.7946033319378747e-05, 'epoch': 10.58}

 88%|████████▊ | 24775/28080 [48:56:46<6:33:03,  7.14s/it]
 88%|████████▊ | 24776/28080 [48:56:53<6:31:16,  7.11s/it]
                                                          
{'loss': 0.5993, 'learning_rate': 1.7935306766624998e-05, 'epoch': 10.58}

 88%|████████▊ | 24776/28080 [48:56:53<6:31:16,  7.11s/it]
 88%|████████▊ | 24777/28080 [48:57:00<6:32:52,  7.14s/it]
                                                          
{'loss': 0.5925, 'learning_rate': 1.792458330125257e-05, 'epoch': 10.58}

 88%|████████▊ | 24777/28080 [48:57:00<6:32:52,  7.14s/it]
 88%|████████▊ | 24778/28080 [48:57:07<6:32:23,  7.13s/it]
                                                          
{'loss': 0.5804, 'learning_rate': 1.7913862923404163e-05, 'epoch': 10.58}

 88%|████████▊ | 24778/28080 [48:57:07<6:32:23,  7.13s/it]
 88%|████████▊ | 24779/28080 [48:57:14<6:29:27,  7.08s/it]
                                                          
{'loss': 0.5898, 'learning_rate': 1.7903145633222375e-05, 'epoch': 10.59}

 88%|████████▊ | 24779/28080 [48:57:14<6:29:27,  7.08s/it]
 88%|████████▊ | 24780/28080 [48:57:21<6:29:41,  7.09s/it]
                                                          
{'loss': 0.6103, 'learning_rate': 1.7892431430849787e-05, 'epoch': 10.59}

 88%|████████▊ | 24780/28080 [48:57:21<6:29:41,  7.09s/it]
 88%|████████▊ | 24781/28080 [48:57:28<6:28:43,  7.07s/it]
                                                          
{'loss': 0.616, 'learning_rate': 1.7881720316428927e-05, 'epoch': 10.59}

 88%|████████▊ | 24781/28080 [48:57:28<6:28:43,  7.07s/it]
 88%|████████▊ | 24782/28080 [48:57:35<6:27:33,  7.05s/it]
                                                          
{'loss': 0.6182, 'learning_rate': 1.7871012290102352e-05, 'epoch': 10.59}

 88%|████████▊ | 24782/28080 [48:57:35<6:27:33,  7.05s/it]
 88%|████████▊ | 24783/28080 [48:57:42<6:29:18,  7.08s/it]
                                                          
{'loss': 0.6014, 'learning_rate': 1.7860307352012468e-05, 'epoch': 10.59}

 88%|████████▊ | 24783/28080 [48:57:42<6:29:18,  7.08s/it]
 88%|████████▊ | 24784/28080 [48:57:49<6:27:39,  7.06s/it]
                                                          
{'loss': 0.6268, 'learning_rate': 1.7849605502301718e-05, 'epoch': 10.59}

 88%|████████▊ | 24784/28080 [48:57:49<6:27:39,  7.06s/it]
 88%|████████▊ | 24785/28080 [48:57:57<6:27:50,  7.06s/it]
                                                          
{'loss': 0.6203, 'learning_rate': 1.7838906741112493e-05, 'epoch': 10.59}

 88%|████████▊ | 24785/28080 [48:57:57<6:27:50,  7.06s/it]
 88%|████████▊ | 24786/28080 [48:58:04<6:28:05,  7.07s/it]
                                                          
{'loss': 0.6016, 'learning_rate': 1.7828211068587036e-05, 'epoch': 10.59}

 88%|████████▊ | 24786/28080 [48:58:04<6:28:05,  7.07s/it]
 88%|████████▊ | 24787/28080 [48:58:11<6:26:49,  7.05s/it]
                                                          
{'loss': 0.5867, 'learning_rate': 1.781751848486776e-05, 'epoch': 10.59}

 88%|████████▊ | 24787/28080 [48:58:11<6:26:49,  7.05s/it]
 88%|████████▊ | 24788/28080 [48:58:18<6:26:59,  7.05s/it]
                                                          
{'loss': 0.6086, 'learning_rate': 1.780682899009689e-05, 'epoch': 10.59}

 88%|████████▊ | 24788/28080 [48:58:18<6:26:59,  7.05s/it]
 88%|████████▊ | 24789/28080 [48:58:25<6:26:25,  7.05s/it]
                                                          
{'loss': 0.6144, 'learning_rate': 1.7796142584416584e-05, 'epoch': 10.59}

 88%|████████▊ | 24789/28080 [48:58:25<6:26:25,  7.05s/it]
 88%|████████▊ | 24790/28080 [48:58:32<6:25:28,  7.03s/it]
                                                          
{'loss': 0.6218, 'learning_rate': 1.778545926796904e-05, 'epoch': 10.59}

 88%|████████▊ | 24790/28080 [48:58:32<6:25:28,  7.03s/it]
 88%|████████▊ | 24791/28080 [48:58:39<6:26:11,  7.05s/it]
                                                          
{'loss': 0.583, 'learning_rate': 1.7774779040896415e-05, 'epoch': 10.59}

 88%|████████▊ | 24791/28080 [48:58:39<6:26:11,  7.05s/it]
 88%|████████▊ | 24792/28080 [48:58:46<6:28:01,  7.08s/it]
                                                          
{'loss': 0.5994, 'learning_rate': 1.7764101903340768e-05, 'epoch': 10.59}

 88%|████████▊ | 24792/28080 [48:58:46<6:28:01,  7.08s/it]
 88%|████████▊ | 24793/28080 [48:58:53<6:27:07,  7.07s/it]
                                                          
{'loss': 0.5879, 'learning_rate': 1.7753427855444177e-05, 'epoch': 10.59}

 88%|████████▊ | 24793/28080 [48:58:53<6:27:07,  7.07s/it]
 88%|████████▊ | 24794/28080 [48:59:00<6:26:47,  7.06s/it]
                                                          
{'loss': 0.5958, 'learning_rate': 1.7742756897348637e-05, 'epoch': 10.59}

 88%|████████▊ | 24794/28080 [48:59:00<6:26:47,  7.06s/it]
 88%|████████▊ | 24795/28080 [48:59:07<6:26:51,  7.07s/it]
                                                          
{'loss': 0.5876, 'learning_rate': 1.7732089029196124e-05, 'epoch': 10.59}

 88%|████████▊ | 24795/28080 [48:59:07<6:26:51,  7.07s/it]
 88%|████████▊ | 24796/28080 [48:59:14<6:27:58,  7.09s/it]
                                                          
{'loss': 0.5792, 'learning_rate': 1.7721424251128493e-05, 'epoch': 10.59}

 88%|████████▊ | 24796/28080 [48:59:14<6:27:58,  7.09s/it]
 88%|████████▊ | 24797/28080 [48:59:21<6:27:24,  7.08s/it]
                                                          
{'loss': 0.5944, 'learning_rate': 1.771076256328774e-05, 'epoch': 10.59}

 88%|████████▊ | 24797/28080 [48:59:21<6:27:24,  7.08s/it]
 88%|████████▊ | 24798/28080 [48:59:28<6:28:51,  7.11s/it]
                                                          
{'loss': 0.6181, 'learning_rate': 1.7700103965815645e-05, 'epoch': 10.59}

 88%|████████▊ | 24798/28080 [48:59:28<6:28:51,  7.11s/it]
 88%|████████▊ | 24799/28080 [48:59:36<6:29:55,  7.13s/it]
                                                          
{'loss': 0.6116, 'learning_rate': 1.768944845885401e-05, 'epoch': 10.59}

 88%|████████▊ | 24799/28080 [48:59:36<6:29:55,  7.13s/it]
 88%|████████▊ | 24800/28080 [48:59:43<6:30:50,  7.15s/it]
                                                          
{'loss': 0.6145, 'learning_rate': 1.7678796042544574e-05, 'epoch': 10.59}

 88%|████████▊ | 24800/28080 [48:59:43<6:30:50,  7.15s/it]
 88%|████████▊ | 24801/28080 [48:59:50<6:29:10,  7.12s/it]
                                                          
{'loss': 0.5869, 'learning_rate': 1.7668146717029098e-05, 'epoch': 10.59}

 88%|████████▊ | 24801/28080 [48:59:50<6:29:10,  7.12s/it]
 88%|████████▊ | 24802/28080 [48:59:57<6:30:51,  7.15s/it]
                                                          
{'loss': 0.5913, 'learning_rate': 1.7657500482449267e-05, 'epoch': 10.6}

 88%|████████▊ | 24802/28080 [48:59:57<6:30:51,  7.15s/it]
 88%|████████▊ | 24803/28080 [49:00:04<6:29:53,  7.14s/it]
                                                          
{'loss': 0.6345, 'learning_rate': 1.764685733894672e-05, 'epoch': 10.6}

 88%|████████▊ | 24803/28080 [49:00:04<6:29:53,  7.14s/it]
 88%|████████▊ | 24804/28080 [49:00:11<6:30:08,  7.15s/it]
                                                          
{'loss': 0.5995, 'learning_rate': 1.7636217286662955e-05, 'epoch': 10.6}

 88%|████████▊ | 24804/28080 [49:00:11<6:30:08,  7.15s/it]
 88%|████████▊ | 24805/28080 [49:00:19<6:30:30,  7.15s/it]
                                                          
{'loss': 0.6054, 'learning_rate': 1.762558032573966e-05, 'epoch': 10.6}

 88%|████████▊ | 24805/28080 [49:00:19<6:30:30,  7.15s/it]
 88%|████████▊ | 24806/28080 [49:00:26<6:28:50,  7.13s/it]
                                                          
{'loss': 0.5867, 'learning_rate': 1.7614946456318227e-05, 'epoch': 10.6}

 88%|████████▊ | 24806/28080 [49:00:26<6:28:50,  7.13s/it]
 88%|████████▊ | 24807/28080 [49:00:33<6:29:23,  7.14s/it]
                                                          
{'loss': 0.5807, 'learning_rate': 1.760431567854026e-05, 'epoch': 10.6}

 88%|████████▊ | 24807/28080 [49:00:33<6:29:23,  7.14s/it]
 88%|████████▊ | 24808/28080 [49:00:40<6:26:18,  7.08s/it]
                                                          
{'loss': 0.6005, 'learning_rate': 1.7593687992547124e-05, 'epoch': 10.6}

 88%|████████▊ | 24808/28080 [49:00:40<6:26:18,  7.08s/it]
 88%|████████▊ | 24809/28080 [49:00:47<6:26:56,  7.10s/it]
                                                          
{'loss': 0.6084, 'learning_rate': 1.7583063398480202e-05, 'epoch': 10.6}

 88%|████████▊ | 24809/28080 [49:00:47<6:26:56,  7.10s/it]
 88%|████████▊ | 24810/28080 [49:00:54<6:27:44,  7.11s/it]
                                                          
{'loss': 0.6059, 'learning_rate': 1.757244189648083e-05, 'epoch': 10.6}

 88%|████████▊ | 24810/28080 [49:00:54<6:27:44,  7.11s/it]
 88%|████████▊ | 24811/28080 [49:01:01<6:26:50,  7.10s/it]
                                                          
{'loss': 0.6091, 'learning_rate': 1.756182348669033e-05, 'epoch': 10.6}

 88%|████████▊ | 24811/28080 [49:01:01<6:26:50,  7.10s/it]
 88%|████████▊ | 24812/28080 [49:01:08<6:27:51,  7.12s/it]
                                                          
{'loss': 0.6016, 'learning_rate': 1.7551208169249987e-05, 'epoch': 10.6}

 88%|████████▊ | 24812/28080 [49:01:08<6:27:51,  7.12s/it]
 88%|████████▊ | 24813/28080 [49:01:15<6:27:05,  7.11s/it]
                                                          
{'loss': 0.6084, 'learning_rate': 1.7540595944301046e-05, 'epoch': 10.6}

 88%|████████▊ | 24813/28080 [49:01:15<6:27:05,  7.11s/it]
 88%|████████▊ | 24814/28080 [49:01:22<6:25:48,  7.09s/it]
                                                          
{'loss': 0.6222, 'learning_rate': 1.7529986811984643e-05, 'epoch': 10.6}

 88%|████████▊ | 24814/28080 [49:01:22<6:25:48,  7.09s/it]
 88%|████████▊ | 24815/28080 [49:01:30<6:26:29,  7.10s/it]
                                                          
{'loss': 0.6181, 'learning_rate': 1.751938077244189e-05, 'epoch': 10.6}

 88%|████████▊ | 24815/28080 [49:01:30<6:26:29,  7.10s/it]
 88%|████████▊ | 24816/28080 [49:01:37<6:28:07,  7.13s/it]
                                                          
{'loss': 0.6067, 'learning_rate': 1.7508777825813977e-05, 'epoch': 10.6}

 88%|████████▊ | 24816/28080 [49:01:37<6:28:07,  7.13s/it]
 88%|████████▊ | 24817/28080 [49:01:44<6:28:45,  7.15s/it]
                                                          
{'loss': 0.5959, 'learning_rate': 1.749817797224196e-05, 'epoch': 10.6}

 88%|████████▊ | 24817/28080 [49:01:44<6:28:45,  7.15s/it]
 88%|████████▊ | 24818/28080 [49:01:51<6:28:32,  7.15s/it]
                                                          
{'loss': 0.6059, 'learning_rate': 1.7487581211866806e-05, 'epoch': 10.6}

 88%|████████▊ | 24818/28080 [49:01:51<6:28:32,  7.15s/it]
 88%|████████▊ | 24819/28080 [49:01:58<6:28:02,  7.14s/it]
                                                          
{'loss': 0.6053, 'learning_rate': 1.747698754482946e-05, 'epoch': 10.6}

 88%|████████▊ | 24819/28080 [49:01:58<6:28:02,  7.14s/it]
 88%|████████▊ | 24820/28080 [49:02:05<6:27:26,  7.13s/it]
                                                          
{'loss': 0.6177, 'learning_rate': 1.7466396971270975e-05, 'epoch': 10.6}

 88%|████████▊ | 24820/28080 [49:02:05<6:27:26,  7.13s/it]
 88%|████████▊ | 24821/28080 [49:02:12<6:27:14,  7.13s/it]
                                                          
{'loss': 0.6218, 'learning_rate': 1.745580949133213e-05, 'epoch': 10.6}

 88%|████████▊ | 24821/28080 [49:02:12<6:27:14,  7.13s/it]
 88%|████████▊ | 24822/28080 [49:02:20<6:27:56,  7.14s/it]
                                                          
{'loss': 0.6124, 'learning_rate': 1.744522510515392e-05, 'epoch': 10.6}

 88%|████████▊ | 24822/28080 [49:02:20<6:27:56,  7.14s/it]
 88%|████████▊ | 24823/28080 [49:02:27<6:27:31,  7.14s/it]
                                                          
{'loss': 0.6034, 'learning_rate': 1.7434643812877016e-05, 'epoch': 10.6}

 88%|████████▊ | 24823/28080 [49:02:27<6:27:31,  7.14s/it]
 88%|████████▊ | 24824/28080 [49:02:34<6:25:29,  7.10s/it]
                                                          
{'loss': 0.6186, 'learning_rate': 1.742406561464227e-05, 'epoch': 10.6}

 88%|████████▊ | 24824/28080 [49:02:34<6:25:29,  7.10s/it]
 88%|████████▊ | 24825/28080 [49:02:41<6:25:58,  7.11s/it]
                                                          
{'loss': 0.613, 'learning_rate': 1.741349051059035e-05, 'epoch': 10.61}

 88%|████████▊ | 24825/28080 [49:02:41<6:25:58,  7.11s/it]
 88%|████████▊ | 24826/28080 [49:02:48<6:23:44,  7.08s/it]
                                                          
{'loss': 0.6016, 'learning_rate': 1.7402918500862062e-05, 'epoch': 10.61}

 88%|████████▊ | 24826/28080 [49:02:48<6:23:44,  7.08s/it]
 88%|████████▊ | 24827/28080 [49:02:55<6:23:06,  7.07s/it]
                                                          
{'loss': 0.605, 'learning_rate': 1.739234958559796e-05, 'epoch': 10.61}

 88%|████████▊ | 24827/28080 [49:02:55<6:23:06,  7.07s/it]
 88%|████████▊ | 24828/28080 [49:03:02<6:24:42,  7.10s/it]
                                                          
{'loss': 0.6017, 'learning_rate': 1.7381783764938707e-05, 'epoch': 10.61}

 88%|████████▊ | 24828/28080 [49:03:02<6:24:42,  7.10s/it]
 88%|████████▊ | 24829/28080 [49:03:09<6:24:18,  7.09s/it]
                                                          
{'loss': 0.5999, 'learning_rate': 1.7371221039024774e-05, 'epoch': 10.61}

 88%|████████▊ | 24829/28080 [49:03:09<6:24:18,  7.09s/it]
 88%|████████▊ | 24830/28080 [49:03:16<6:24:35,  7.10s/it]
                                                          
{'loss': 0.5841, 'learning_rate': 1.7360661407996802e-05, 'epoch': 10.61}

 88%|████████▊ | 24830/28080 [49:03:16<6:24:35,  7.10s/it]
 88%|████████▊ | 24831/28080 [49:03:23<6:23:20,  7.08s/it]
                                                          
{'loss': 0.5962, 'learning_rate': 1.735010487199523e-05, 'epoch': 10.61}

 88%|████████▊ | 24831/28080 [49:03:23<6:23:20,  7.08s/it]
 88%|████████▊ | 24832/28080 [49:03:30<6:21:37,  7.05s/it]
                                                          
{'loss': 0.6027, 'learning_rate': 1.7339551431160504e-05, 'epoch': 10.61}

 88%|████████▊ | 24832/28080 [49:03:30<6:21:37,  7.05s/it]
 88%|████████▊ | 24833/28080 [49:03:37<6:22:19,  7.06s/it]
                                                          
{'loss': 0.6028, 'learning_rate': 1.7329001085632984e-05, 'epoch': 10.61}

 88%|████████▊ | 24833/28080 [49:03:37<6:22:19,  7.06s/it]
 88%|████████▊ | 24834/28080 [49:03:45<6:23:57,  7.10s/it]
                                                          
{'loss': 0.6097, 'learning_rate': 1.731845383555311e-05, 'epoch': 10.61}

 88%|████████▊ | 24834/28080 [49:03:45<6:23:57,  7.10s/it]
 88%|████████▊ | 24835/28080 [49:03:52<6:23:34,  7.09s/it]
                                                          
{'loss': 0.6018, 'learning_rate': 1.730790968106119e-05, 'epoch': 10.61}

 88%|████████▊ | 24835/28080 [49:03:52<6:23:34,  7.09s/it]
 88%|████████▊ | 24836/28080 [49:03:59<6:23:31,  7.09s/it]
                                                          
{'loss': 0.5754, 'learning_rate': 1.7297368622297445e-05, 'epoch': 10.61}

 88%|████████▊ | 24836/28080 [49:03:59<6:23:31,  7.09s/it]
 88%|████████▊ | 24837/28080 [49:04:06<6:25:09,  7.13s/it]
                                                          
{'loss': 0.6065, 'learning_rate': 1.7286830659402146e-05, 'epoch': 10.61}

 88%|████████▊ | 24837/28080 [49:04:06<6:25:09,  7.13s/it]
 88%|████████▊ | 24838/28080 [49:04:13<6:25:25,  7.13s/it]
                                                          
{'loss': 0.5863, 'learning_rate': 1.7276295792515466e-05, 'epoch': 10.61}

 88%|████████▊ | 24838/28080 [49:04:13<6:25:25,  7.13s/it]
 88%|████████▊ | 24839/28080 [49:04:20<6:25:11,  7.13s/it]
                                                          
{'loss': 0.5985, 'learning_rate': 1.7265764021777598e-05, 'epoch': 10.61}

 88%|████████▊ | 24839/28080 [49:04:20<6:25:11,  7.13s/it]
 88%|████████▊ | 24840/28080 [49:04:27<6:25:50,  7.15s/it]
                                                          
{'loss': 0.5893, 'learning_rate': 1.7255235347328617e-05, 'epoch': 10.61}

 88%|████████▊ | 24840/28080 [49:04:27<6:25:50,  7.15s/it]
 88%|████████▊ | 24841/28080 [49:04:34<6:24:15,  7.12s/it]
                                                          
{'loss': 0.5926, 'learning_rate': 1.7244709769308698e-05, 'epoch': 10.61}

 88%|████████▊ | 24841/28080 [49:04:34<6:24:15,  7.12s/it]
 88%|████████▊ | 24842/28080 [49:04:42<6:24:09,  7.12s/it]
                                                          
{'loss': 0.5871, 'learning_rate': 1.7234187287857723e-05, 'epoch': 10.61}

 88%|████████▊ | 24842/28080 [49:04:42<6:24:09,  7.12s/it]
 88%|████████▊ | 24843/28080 [49:04:49<6:24:17,  7.12s/it]
                                                          
{'loss': 0.5824, 'learning_rate': 1.7223667903115773e-05, 'epoch': 10.61}

 88%|████████▊ | 24843/28080 [49:04:49<6:24:17,  7.12s/it]
 88%|████████▊ | 24844/28080 [49:04:56<6:22:43,  7.10s/it]
                                                          
{'loss': 0.6084, 'learning_rate': 1.7213151615222743e-05, 'epoch': 10.61}

 88%|████████▊ | 24844/28080 [49:04:56<6:22:43,  7.10s/it]
 88%|████████▊ | 24845/28080 [49:05:03<6:21:39,  7.08s/it]
                                                          
{'loss': 0.6067, 'learning_rate': 1.7202638424318628e-05, 'epoch': 10.61}

 88%|████████▊ | 24845/28080 [49:05:03<6:21:39,  7.08s/it]
 88%|████████▊ | 24846/28080 [49:05:10<6:21:44,  7.08s/it]
                                                          
{'loss': 0.5989, 'learning_rate': 1.7192128330543262e-05, 'epoch': 10.61}

 88%|████████▊ | 24846/28080 [49:05:10<6:21:44,  7.08s/it]
 88%|████████▊ | 24847/28080 [49:05:17<6:21:18,  7.08s/it]
                                                          
{'loss': 0.6158, 'learning_rate': 1.7181621334036417e-05, 'epoch': 10.61}

 88%|████████▊ | 24847/28080 [49:05:17<6:21:18,  7.08s/it]
 88%|████████▊ | 24848/28080 [49:05:24<6:22:20,  7.10s/it]
                                                          
{'loss': 0.6047, 'learning_rate': 1.7171117434937905e-05, 'epoch': 10.61}

 88%|████████▊ | 24848/28080 [49:05:24<6:22:20,  7.10s/it]
 88%|████████▊ | 24849/28080 [49:05:31<6:21:57,  7.09s/it]
                                                          
{'loss': 0.5942, 'learning_rate': 1.71606166333875e-05, 'epoch': 10.62}

 88%|████████▊ | 24849/28080 [49:05:31<6:21:57,  7.09s/it]
 88%|████████▊ | 24850/28080 [49:05:38<6:21:11,  7.08s/it]
                                                          
{'loss': 0.604, 'learning_rate': 1.7150118929524893e-05, 'epoch': 10.62}

 88%|████████▊ | 24850/28080 [49:05:38<6:21:11,  7.08s/it]
 89%|████████▊ | 24851/28080 [49:05:45<6:21:34,  7.09s/it]
                                                          
{'loss': 0.5944, 'learning_rate': 1.7139624323489757e-05, 'epoch': 10.62}

 89%|████████▊ | 24851/28080 [49:05:45<6:21:34,  7.09s/it]
 89%|████████▊ | 24852/28080 [49:05:52<6:22:33,  7.11s/it]
                                                          
{'loss': 0.603, 'learning_rate': 1.7129132815421613e-05, 'epoch': 10.62}

 89%|████████▊ | 24852/28080 [49:05:52<6:22:33,  7.11s/it]
 89%|████████▊ | 24853/28080 [49:06:00<6:21:10,  7.09s/it]
                                                          
{'loss': 0.6068, 'learning_rate': 1.7118644405460184e-05, 'epoch': 10.62}

 89%|████████▊ | 24853/28080 [49:06:00<6:21:10,  7.09s/it]
 89%|████████▊ | 24854/28080 [49:06:07<6:23:25,  7.13s/it]
                                                          
{'loss': 0.6008, 'learning_rate': 1.7108159093744885e-05, 'epoch': 10.62}

 89%|████████▊ | 24854/28080 [49:06:07<6:23:25,  7.13s/it]
 89%|████████▊ | 24855/28080 [49:06:14<6:22:39,  7.12s/it]
                                                          
{'loss': 0.6256, 'learning_rate': 1.7097676880415303e-05, 'epoch': 10.62}

 89%|████████▊ | 24855/28080 [49:06:14<6:22:39,  7.12s/it]
 89%|████████▊ | 24856/28080 [49:06:21<6:21:32,  7.10s/it]
                                                          
{'loss': 0.6084, 'learning_rate': 1.708719776561088e-05, 'epoch': 10.62}

 89%|████████▊ | 24856/28080 [49:06:21<6:21:32,  7.10s/it]
 89%|████████▊ | 24857/28080 [49:06:28<6:21:48,  7.11s/it]
                                                          
{'loss': 0.5756, 'learning_rate': 1.7076721749471004e-05, 'epoch': 10.62}

 89%|████████▊ | 24857/28080 [49:06:28<6:21:48,  7.11s/it]
 89%|████████▊ | 24858/28080 [49:06:35<6:23:09,  7.14s/it]
                                                          
{'loss': 0.6026, 'learning_rate': 1.706624883213498e-05, 'epoch': 10.62}

 89%|████████▊ | 24858/28080 [49:06:35<6:23:09,  7.14s/it]
 89%|████████▊ | 24859/28080 [49:06:42<6:22:21,  7.12s/it]
                                                          
{'loss': 0.6111, 'learning_rate': 1.705577901374228e-05, 'epoch': 10.62}

 89%|████████▊ | 24859/28080 [49:06:42<6:22:21,  7.12s/it]
 89%|████████▊ | 24860/28080 [49:06:49<6:20:30,  7.09s/it]
                                                          
{'loss': 0.5909, 'learning_rate': 1.7045312294432126e-05, 'epoch': 10.62}

 89%|████████▊ | 24860/28080 [49:06:49<6:20:30,  7.09s/it]
 89%|████████▊ | 24861/28080 [49:06:56<6:20:10,  7.09s/it]
                                                          
{'loss': 0.566, 'learning_rate': 1.7034848674343766e-05, 'epoch': 10.62}

 89%|████████▊ | 24861/28080 [49:06:56<6:20:10,  7.09s/it]
 89%|████████▊ | 24862/28080 [49:07:03<6:19:57,  7.08s/it]
                                                          
{'loss': 0.6131, 'learning_rate': 1.70243881536164e-05, 'epoch': 10.62}

 89%|████████▊ | 24862/28080 [49:07:03<6:19:57,  7.08s/it]
 89%|████████▊ | 24863/28080 [49:07:11<6:19:08,  7.07s/it]
                                                          
{'loss': 0.5721, 'learning_rate': 1.701393073238916e-05, 'epoch': 10.62}

 89%|████████▊ | 24863/28080 [49:07:11<6:19:08,  7.07s/it]
 89%|████████▊ | 24864/28080 [49:07:18<6:18:51,  7.07s/it]
                                                          
{'loss': 0.5941, 'learning_rate': 1.7003476410801244e-05, 'epoch': 10.62}

 89%|████████▊ | 24864/28080 [49:07:18<6:18:51,  7.07s/it]
 89%|████████▊ | 24865/28080 [49:07:25<6:19:04,  7.07s/it]
                                                          
{'loss': 0.6139, 'learning_rate': 1.6993025188991736e-05, 'epoch': 10.62}

 89%|████████▊ | 24865/28080 [49:07:25<6:19:04,  7.07s/it]
 89%|████████▊ | 24866/28080 [49:07:32<6:19:16,  7.08s/it]
                                                          
{'loss': 0.5794, 'learning_rate': 1.6982577067099632e-05, 'epoch': 10.62}

 89%|████████▊ | 24866/28080 [49:07:32<6:19:16,  7.08s/it]
 89%|████████▊ | 24867/28080 [49:07:39<6:19:15,  7.08s/it]
                                                          
{'loss': 0.5805, 'learning_rate': 1.6972132045263906e-05, 'epoch': 10.62}

 89%|████████▊ | 24867/28080 [49:07:39<6:19:15,  7.08s/it]
 89%|████████▊ | 24868/28080 [49:07:46<6:20:00,  7.10s/it]
                                                          
{'loss': 0.5939, 'learning_rate': 1.6961690123623584e-05, 'epoch': 10.62}

 89%|████████▊ | 24868/28080 [49:07:46<6:20:00,  7.10s/it]
 89%|████████▊ | 24869/28080 [49:07:53<6:22:31,  7.15s/it]
                                                          
{'loss': 0.5876, 'learning_rate': 1.6951251302317562e-05, 'epoch': 10.62}

 89%|████████▊ | 24869/28080 [49:07:53<6:22:31,  7.15s/it]
 89%|████████▊ | 24870/28080 [49:08:00<6:23:29,  7.17s/it]
                                                          
{'loss': 0.5859, 'learning_rate': 1.6940815581484774e-05, 'epoch': 10.62}

 89%|████████▊ | 24870/28080 [49:08:00<6:23:29,  7.17s/it]
 89%|████████▊ | 24871/28080 [49:08:08<6:22:26,  7.15s/it]
                                                          
{'loss': 0.5905, 'learning_rate': 1.6930382961263923e-05, 'epoch': 10.62}

 89%|████████▊ | 24871/28080 [49:08:08<6:22:26,  7.15s/it]
 89%|████████▊ | 24872/28080 [49:08:15<6:21:54,  7.14s/it]
                                                          
{'loss': 0.5735, 'learning_rate': 1.6919953441793922e-05, 'epoch': 10.63}

 89%|████████▊ | 24872/28080 [49:08:15<6:21:54,  7.14s/it]
 89%|████████▊ | 24873/28080 [49:08:22<6:22:00,  7.15s/it]
                                                          
{'loss': 0.5837, 'learning_rate': 1.6909527023213438e-05, 'epoch': 10.63}

 89%|████████▊ | 24873/28080 [49:08:22<6:22:00,  7.15s/it]
 89%|████████▊ | 24874/28080 [49:08:29<6:21:52,  7.15s/it]
                                                          
{'loss': 0.5964, 'learning_rate': 1.689910370566128e-05, 'epoch': 10.63}

 89%|████████▊ | 24874/28080 [49:08:29<6:21:52,  7.15s/it]
 89%|████████▊ | 24875/28080 [49:08:36<6:21:58,  7.15s/it]
                                                          
{'loss': 0.5894, 'learning_rate': 1.688868348927608e-05, 'epoch': 10.63}

 89%|████████▊ | 24875/28080 [49:08:36<6:21:58,  7.15s/it]
 89%|████████▊ | 24876/28080 [49:08:43<6:21:53,  7.15s/it]
                                                          
{'loss': 0.6111, 'learning_rate': 1.6878266374196426e-05, 'epoch': 10.63}

 89%|████████▊ | 24876/28080 [49:08:43<6:21:53,  7.15s/it]
 89%|████████▊ | 24877/28080 [49:08:50<6:19:47,  7.11s/it]
                                                          
{'loss': 0.6083, 'learning_rate': 1.686785236056093e-05, 'epoch': 10.63}

 89%|████████▊ | 24877/28080 [49:08:50<6:19:47,  7.11s/it]
 89%|████████▊ | 24878/28080 [49:08:57<6:20:09,  7.12s/it]
                                                          
{'loss': 0.6077, 'learning_rate': 1.6857441448508175e-05, 'epoch': 10.63}

 89%|████████▊ | 24878/28080 [49:08:57<6:20:09,  7.12s/it]
 89%|████████▊ | 24879/28080 [49:09:05<6:19:36,  7.12s/it]
                                                          
{'loss': 0.5857, 'learning_rate': 1.6847033638176662e-05, 'epoch': 10.63}

 89%|████████▊ | 24879/28080 [49:09:05<6:19:36,  7.12s/it]
 89%|████████▊ | 24880/28080 [49:09:12<6:18:51,  7.10s/it]
                                                          
{'loss': 0.5867, 'learning_rate': 1.6836628929704834e-05, 'epoch': 10.63}

 89%|████████▊ | 24880/28080 [49:09:12<6:18:51,  7.10s/it]
 89%|████████▊ | 24881/28080 [49:09:19<6:19:18,  7.11s/it]
                                                          
{'loss': 0.6009, 'learning_rate': 1.682622732323105e-05, 'epoch': 10.63}

 89%|████████▊ | 24881/28080 [49:09:19<6:19:18,  7.11s/it]
 89%|████████▊ | 24882/28080 [49:09:26<6:18:02,  7.09s/it]
                                                          
{'loss': 0.5816, 'learning_rate': 1.681582881889382e-05, 'epoch': 10.63}

 89%|████████▊ | 24882/28080 [49:09:26<6:18:02,  7.09s/it]
 89%|████████▊ | 24883/28080 [49:09:33<6:18:41,  7.11s/it]
                                                          
{'loss': 0.5974, 'learning_rate': 1.6805433416831385e-05, 'epoch': 10.63}

 89%|████████▊ | 24883/28080 [49:09:33<6:18:41,  7.11s/it]
 89%|████████▊ | 24884/28080 [49:09:40<6:18:50,  7.11s/it]
                                                          
{'loss': 0.5882, 'learning_rate': 1.6795041117182136e-05, 'epoch': 10.63}

 89%|████████▊ | 24884/28080 [49:09:40<6:18:50,  7.11s/it]
 89%|████████▊ | 24885/28080 [49:09:47<6:18:23,  7.11s/it]
                                                          
{'loss': 0.599, 'learning_rate': 1.6784651920084272e-05, 'epoch': 10.63}

 89%|████████▊ | 24885/28080 [49:09:47<6:18:23,  7.11s/it]
 89%|████████▊ | 24886/28080 [49:09:54<6:19:04,  7.12s/it]
                                                          
{'loss': 0.6046, 'learning_rate': 1.6774265825675984e-05, 'epoch': 10.63}

 89%|████████▊ | 24886/28080 [49:09:54<6:19:04,  7.12s/it]
 89%|████████▊ | 24887/28080 [49:10:01<6:17:14,  7.09s/it]
                                                          
{'loss': 0.5968, 'learning_rate': 1.6763882834095496e-05, 'epoch': 10.63}

 89%|████████▊ | 24887/28080 [49:10:01<6:17:14,  7.09s/it]
 89%|████████▊ | 24888/28080 [49:10:09<6:17:51,  7.10s/it]
                                                          
{'loss': 0.5837, 'learning_rate': 1.675350294548092e-05, 'epoch': 10.63}

 89%|████████▊ | 24888/28080 [49:10:09<6:17:51,  7.10s/it]
 89%|████████▊ | 24889/28080 [49:10:16<6:16:14,  7.07s/it]
                                                          
{'loss': 0.6235, 'learning_rate': 1.6743126159970422e-05, 'epoch': 10.63}

 89%|████████▊ | 24889/28080 [49:10:16<6:16:14,  7.07s/it]
 89%|████████▊ | 24890/28080 [49:10:23<6:17:01,  7.09s/it]
                                                          
{'loss': 0.594, 'learning_rate': 1.6732752477701922e-05, 'epoch': 10.63}

 89%|████████▊ | 24890/28080 [49:10:23<6:17:01,  7.09s/it]
 89%|████████▊ | 24891/28080 [49:10:30<6:16:08,  7.08s/it]
                                                          
{'loss': 0.5897, 'learning_rate': 1.6722381898813534e-05, 'epoch': 10.63}

 89%|████████▊ | 24891/28080 [49:10:30<6:16:08,  7.08s/it]
 89%|████████▊ | 24892/28080 [49:10:37<6:15:00,  7.06s/it]
                                                          
{'loss': 0.5892, 'learning_rate': 1.6712014423443138e-05, 'epoch': 10.63}

 89%|████████▊ | 24892/28080 [49:10:37<6:15:00,  7.06s/it]
 89%|████████▊ | 24893/28080 [49:10:44<6:16:21,  7.09s/it]
                                                          
{'loss': 0.5827, 'learning_rate': 1.67016500517288e-05, 'epoch': 10.63}

 89%|████████▊ | 24893/28080 [49:10:44<6:16:21,  7.09s/it]
 89%|████████▊ | 24894/28080 [49:10:51<6:17:29,  7.11s/it]
                                                          
{'loss': 0.603, 'learning_rate': 1.6691288783808295e-05, 'epoch': 10.63}

 89%|████████▊ | 24894/28080 [49:10:51<6:17:29,  7.11s/it]
 89%|████████▊ | 24895/28080 [49:10:58<6:17:40,  7.11s/it]
                                                          
{'loss': 0.5905, 'learning_rate': 1.6680930619819514e-05, 'epoch': 10.63}

 89%|████████▊ | 24895/28080 [49:10:58<6:17:40,  7.11s/it]
 89%|████████▊ | 24896/28080 [49:11:05<6:16:06,  7.09s/it]
                                                          
{'loss': 0.6064, 'learning_rate': 1.6670575559900204e-05, 'epoch': 10.64}

 89%|████████▊ | 24896/28080 [49:11:05<6:16:06,  7.09s/it]
 89%|████████▊ | 24897/28080 [49:11:12<6:15:55,  7.09s/it]
                                                          
{'loss': 0.6112, 'learning_rate': 1.666022360418823e-05, 'epoch': 10.64}

 89%|████████▊ | 24897/28080 [49:11:12<6:15:55,  7.09s/it]
 89%|████████▊ | 24898/28080 [49:11:19<6:15:46,  7.09s/it]
                                                          
{'loss': 0.5866, 'learning_rate': 1.664987475282126e-05, 'epoch': 10.64}

 89%|████████▊ | 24898/28080 [49:11:19<6:15:46,  7.09s/it]
 89%|████████▊ | 24899/28080 [49:11:27<6:17:21,  7.12s/it]
                                                          
{'loss': 0.6047, 'learning_rate': 1.6639529005936933e-05, 'epoch': 10.64}

 89%|████████▊ | 24899/28080 [49:11:27<6:17:21,  7.12s/it]
 89%|████████▊ | 24900/28080 [49:11:34<6:17:42,  7.13s/it]
                                                          
{'loss': 0.6063, 'learning_rate': 1.6629186363672917e-05, 'epoch': 10.64}

 89%|████████▊ | 24900/28080 [49:11:34<6:17:42,  7.13s/it]
 89%|████████▊ | 24901/28080 [49:11:41<6:17:17,  7.12s/it]
                                                          
{'loss': 0.606, 'learning_rate': 1.6618846826166877e-05, 'epoch': 10.64}

 89%|████████▊ | 24901/28080 [49:11:41<6:17:17,  7.12s/it]
 89%|████████▊ | 24902/28080 [49:11:48<6:16:59,  7.12s/it]
                                                          
{'loss': 0.5905, 'learning_rate': 1.6608510393556237e-05, 'epoch': 10.64}

 89%|████████▊ | 24902/28080 [49:11:48<6:16:59,  7.12s/it]
 89%|████████▊ | 24903/28080 [49:11:55<6:17:33,  7.13s/it]
                                                          
{'loss': 0.5877, 'learning_rate': 1.6598177065978686e-05, 'epoch': 10.64}

 89%|████████▊ | 24903/28080 [49:11:55<6:17:33,  7.13s/it]
 89%|████████▊ | 24904/28080 [49:12:02<6:17:16,  7.13s/it]
                                                          
{'loss': 0.5919, 'learning_rate': 1.6587846843571537e-05, 'epoch': 10.64}

 89%|████████▊ | 24904/28080 [49:12:02<6:17:16,  7.13s/it]
 89%|████████▊ | 24905/28080 [49:12:09<6:16:27,  7.11s/it]
                                                          
{'loss': 0.6123, 'learning_rate': 1.6577519726472312e-05, 'epoch': 10.64}

 89%|████████▊ | 24905/28080 [49:12:09<6:16:27,  7.11s/it]
 89%|████████▊ | 24906/28080 [49:12:16<6:15:11,  7.09s/it]
                                                          
{'loss': 0.5911, 'learning_rate': 1.656719571481835e-05, 'epoch': 10.64}

 89%|████████▊ | 24906/28080 [49:12:16<6:15:11,  7.09s/it]
 89%|████████▊ | 24907/28080 [49:12:23<6:16:31,  7.12s/it]
                                                          
{'loss': 0.6095, 'learning_rate': 1.655687480874704e-05, 'epoch': 10.64}

 89%|████████▊ | 24907/28080 [49:12:23<6:16:31,  7.12s/it]
 89%|████████▊ | 24908/28080 [49:12:31<6:15:13,  7.10s/it]
                                                          
{'loss': 0.605, 'learning_rate': 1.6546557008395717e-05, 'epoch': 10.64}

 89%|████████▊ | 24908/28080 [49:12:31<6:15:13,  7.10s/it]
 89%|████████▊ | 24909/28080 [49:12:38<6:15:29,  7.10s/it]
                                                          
{'loss': 0.5931, 'learning_rate': 1.6536242313901605e-05, 'epoch': 10.64}

 89%|████████▊ | 24909/28080 [49:12:38<6:15:29,  7.10s/it]
 89%|████████▊ | 24910/28080 [49:12:45<6:14:05,  7.08s/it]
                                                          
{'loss': 0.5827, 'learning_rate': 1.652593072540193e-05, 'epoch': 10.64}

 89%|████████▊ | 24910/28080 [49:12:45<6:14:05,  7.08s/it]
 89%|████████▊ | 24911/28080 [49:12:52<6:13:09,  7.07s/it]
                                                          
{'loss': 0.598, 'learning_rate': 1.6515622243033822e-05, 'epoch': 10.64}

 89%|████████▊ | 24911/28080 [49:12:52<6:13:09,  7.07s/it]
 89%|████████▊ | 24912/28080 [49:12:59<6:12:33,  7.06s/it]
                                                          
{'loss': 0.5871, 'learning_rate': 1.6505316866934572e-05, 'epoch': 10.64}

 89%|████████▊ | 24912/28080 [49:12:59<6:12:33,  7.06s/it]
 89%|████████▊ | 24913/28080 [49:13:06<6:11:46,  7.04s/it]
                                                          
{'loss': 0.6193, 'learning_rate': 1.6495014597241175e-05, 'epoch': 10.64}

 89%|████████▊ | 24913/28080 [49:13:06<6:11:46,  7.04s/it]
 89%|████████▊ | 24914/28080 [49:13:13<6:12:12,  7.05s/it]
                                                          
{'loss': 0.5944, 'learning_rate': 1.648471543409072e-05, 'epoch': 10.64}

 89%|████████▊ | 24914/28080 [49:13:13<6:12:12,  7.05s/it]
 89%|████████▊ | 24915/28080 [49:13:20<6:12:30,  7.06s/it]
                                                          
{'loss': 0.5799, 'learning_rate': 1.6474419377620174e-05, 'epoch': 10.64}

 89%|████████▊ | 24915/28080 [49:13:20<6:12:30,  7.06s/it]
 89%|████████▊ | 24916/28080 [49:13:27<6:14:20,  7.10s/it]
                                                          
{'loss': 0.588, 'learning_rate': 1.6464126427966603e-05, 'epoch': 10.64}

 89%|████████▊ | 24916/28080 [49:13:27<6:14:20,  7.10s/it]
 89%|████████▊ | 24917/28080 [49:13:34<6:13:39,  7.09s/it]
                                                          
{'loss': 0.5914, 'learning_rate': 1.645383658526686e-05, 'epoch': 10.64}

 89%|████████▊ | 24917/28080 [49:13:34<6:13:39,  7.09s/it]
 89%|████████▊ | 24918/28080 [49:13:41<6:12:18,  7.06s/it]
                                                          
{'loss': 0.5937, 'learning_rate': 1.6443549849657984e-05, 'epoch': 10.64}

 89%|████████▊ | 24918/28080 [49:13:41<6:12:18,  7.06s/it]
 89%|████████▊ | 24919/28080 [49:13:48<6:13:25,  7.09s/it]
                                                          
{'loss': 0.5734, 'learning_rate': 1.643326622127664e-05, 'epoch': 10.65}

 89%|████████▊ | 24919/28080 [49:13:48<6:13:25,  7.09s/it]
 89%|████████▊ | 24920/28080 [49:13:55<6:14:07,  7.10s/it]
                                                          
{'loss': 0.5669, 'learning_rate': 1.6422985700259767e-05, 'epoch': 10.65}

 89%|████████▊ | 24920/28080 [49:13:55<6:14:07,  7.10s/it]
 89%|████████▉ | 24921/28080 [49:14:03<6:14:13,  7.11s/it]
                                                          
{'loss': 0.6035, 'learning_rate': 1.6412708286744073e-05, 'epoch': 10.65}

 89%|████████▉ | 24921/28080 [49:14:03<6:14:13,  7.11s/it]
 89%|████████▉ | 24922/28080 [49:14:10<6:14:12,  7.11s/it]
                                                          
{'loss': 0.5963, 'learning_rate': 1.6402433980866356e-05, 'epoch': 10.65}

 89%|████████▉ | 24922/28080 [49:14:10<6:14:12,  7.11s/it]
 89%|████████▉ | 24923/28080 [49:14:17<6:12:53,  7.09s/it]
                                                          
{'loss': 0.6059, 'learning_rate': 1.639216278276326e-05, 'epoch': 10.65}

 89%|████████▉ | 24923/28080 [49:14:17<6:12:53,  7.09s/it]
 89%|████████▉ | 24924/28080 [49:14:24<6:14:01,  7.11s/it]
                                                          
{'loss': 0.6234, 'learning_rate': 1.6381894692571424e-05, 'epoch': 10.65}

 89%|████████▉ | 24924/28080 [49:14:24<6:14:01,  7.11s/it]
 89%|████████▉ | 24925/28080 [49:14:31<6:15:00,  7.13s/it]
                                                          
{'loss': 0.6042, 'learning_rate': 1.6371629710427438e-05, 'epoch': 10.65}

 89%|████████▉ | 24925/28080 [49:14:31<6:15:00,  7.13s/it]
 89%|████████▉ | 24926/28080 [49:14:38<6:15:11,  7.14s/it]
                                                          
{'loss': 0.5924, 'learning_rate': 1.6361367836467938e-05, 'epoch': 10.65}

 89%|████████▉ | 24926/28080 [49:14:38<6:15:11,  7.14s/it]
 89%|████████▉ | 24927/28080 [49:14:45<6:14:25,  7.13s/it]
                                                          
{'loss': 0.6201, 'learning_rate': 1.635110907082943e-05, 'epoch': 10.65}

 89%|████████▉ | 24927/28080 [49:14:45<6:14:25,  7.13s/it]
 89%|████████▉ | 24928/28080 [49:14:52<6:14:59,  7.14s/it]
                                                          
{'loss': 0.6246, 'learning_rate': 1.6340853413648353e-05, 'epoch': 10.65}

 89%|████████▉ | 24928/28080 [49:14:52<6:14:59,  7.14s/it]
 89%|████████▉ | 24929/28080 [49:15:00<6:15:31,  7.15s/it]
                                                          
{'loss': 0.5953, 'learning_rate': 1.6330600865061135e-05, 'epoch': 10.65}

 89%|████████▉ | 24929/28080 [49:15:00<6:15:31,  7.15s/it]
 89%|████████▉ | 24930/28080 [49:15:07<6:13:37,  7.12s/it]
                                                          
{'loss': 0.6177, 'learning_rate': 1.6320351425204244e-05, 'epoch': 10.65}

 89%|████████▉ | 24930/28080 [49:15:07<6:13:37,  7.12s/it]
 89%|████████▉ | 24931/28080 [49:15:14<6:14:32,  7.14s/it]
                                                          
{'loss': 0.5873, 'learning_rate': 1.6310105094213962e-05, 'epoch': 10.65}

 89%|████████▉ | 24931/28080 [49:15:14<6:14:32,  7.14s/it]
 89%|████████▉ | 24932/28080 [49:15:21<6:18:37,  7.22s/it]
                                                          
{'loss': 0.601, 'learning_rate': 1.6299861872226736e-05, 'epoch': 10.65}

 89%|████████▉ | 24932/28080 [49:15:21<6:18:37,  7.22s/it]
 89%|████████▉ | 24933/28080 [49:15:29<6:18:53,  7.22s/it]
                                                          
{'loss': 0.6149, 'learning_rate': 1.628962175937865e-05, 'epoch': 10.65}

 89%|████████▉ | 24933/28080 [49:15:29<6:18:53,  7.22s/it]
 89%|████████▉ | 24934/28080 [49:15:36<6:15:34,  7.16s/it]
                                                          
{'loss': 0.6069, 'learning_rate': 1.627938475580609e-05, 'epoch': 10.65}

 89%|████████▉ | 24934/28080 [49:15:36<6:15:34,  7.16s/it]
 89%|████████▉ | 24935/28080 [49:15:43<6:15:48,  7.17s/it]
                                                          
{'loss': 0.5877, 'learning_rate': 1.626915086164521e-05, 'epoch': 10.65}

 89%|████████▉ | 24935/28080 [49:15:43<6:15:48,  7.17s/it]
 89%|████████▉ | 24936/28080 [49:15:50<6:13:56,  7.14s/it]
                                                          
{'loss': 0.6222, 'learning_rate': 1.6258920077032113e-05, 'epoch': 10.65}

 89%|████████▉ | 24936/28080 [49:15:50<6:13:56,  7.14s/it]
 89%|████████▉ | 24937/28080 [49:15:57<6:12:37,  7.11s/it]
                                                          
{'loss': 0.6061, 'learning_rate': 1.6248692402103027e-05, 'epoch': 10.65}

 89%|████████▉ | 24937/28080 [49:15:57<6:12:37,  7.11s/it]
 89%|████████▉ | 24938/28080 [49:16:04<6:11:44,  7.10s/it]
                                                          
{'loss': 0.6189, 'learning_rate': 1.6238467836993842e-05, 'epoch': 10.65}

 89%|████████▉ | 24938/28080 [49:16:04<6:11:44,  7.10s/it]
 89%|████████▉ | 24939/28080 [49:16:11<6:11:49,  7.10s/it]
                                                          
{'loss': 0.5853, 'learning_rate': 1.6228246381840756e-05, 'epoch': 10.65}

 89%|████████▉ | 24939/28080 [49:16:11<6:11:49,  7.10s/it]
 89%|████████▉ | 24940/28080 [49:16:18<6:12:13,  7.11s/it]
                                                          
{'loss': 0.5812, 'learning_rate': 1.621802803677963e-05, 'epoch': 10.65}

 89%|████████▉ | 24940/28080 [49:16:18<6:12:13,  7.11s/it]
 89%|████████▉ | 24941/28080 [49:16:25<6:11:02,  7.09s/it]
                                                          
{'loss': 0.614, 'learning_rate': 1.62078128019465e-05, 'epoch': 10.65}

 89%|████████▉ | 24941/28080 [49:16:25<6:11:02,  7.09s/it]
 89%|████████▉ | 24942/28080 [49:16:32<6:11:04,  7.10s/it]
                                                          
{'loss': 0.5945, 'learning_rate': 1.619760067747722e-05, 'epoch': 10.65}

 89%|████████▉ | 24942/28080 [49:16:32<6:11:04,  7.10s/it]
 89%|████████▉ | 24943/28080 [49:16:39<6:09:47,  7.07s/it]
                                                          
{'loss': 0.6072, 'learning_rate': 1.6187391663507663e-05, 'epoch': 10.66}

 89%|████████▉ | 24943/28080 [49:16:39<6:09:47,  7.07s/it]
 89%|████████▉ | 24944/28080 [49:16:46<6:10:58,  7.10s/it]
                                                          
{'loss': 0.624, 'learning_rate': 1.6177185760173602e-05, 'epoch': 10.66}

 89%|████████▉ | 24944/28080 [49:16:46<6:10:58,  7.10s/it]
 89%|████████▉ | 24945/28080 [49:16:54<6:10:34,  7.09s/it]
                                                          
{'loss': 0.5816, 'learning_rate': 1.6166982967610934e-05, 'epoch': 10.66}

 89%|████████▉ | 24945/28080 [49:16:54<6:10:34,  7.09s/it]
 89%|████████▉ | 24946/28080 [49:17:01<6:09:11,  7.07s/it]
                                                          
{'loss': 0.5929, 'learning_rate': 1.6156783285955295e-05, 'epoch': 10.66}

 89%|████████▉ | 24946/28080 [49:17:01<6:09:11,  7.07s/it]
 89%|████████▉ | 24947/28080 [49:17:08<6:09:31,  7.08s/it]
                                                          
{'loss': 0.5958, 'learning_rate': 1.6146586715342442e-05, 'epoch': 10.66}

 89%|████████▉ | 24947/28080 [49:17:08<6:09:31,  7.08s/it]
 89%|████████▉ | 24948/28080 [49:17:15<6:11:07,  7.11s/it]
                                                          
{'loss': 0.6117, 'learning_rate': 1.6136393255907933e-05, 'epoch': 10.66}

 89%|████████▉ | 24948/28080 [49:17:15<6:11:07,  7.11s/it]
 89%|████████▉ | 24949/28080 [49:17:22<6:11:45,  7.12s/it]
                                                          
{'loss': 0.6154, 'learning_rate': 1.612620290778749e-05, 'epoch': 10.66}

 89%|████████▉ | 24949/28080 [49:17:22<6:11:45,  7.12s/it]
 89%|████████▉ | 24950/28080 [49:17:29<6:16:13,  7.21s/it]
                                                          
{'loss': 0.606, 'learning_rate': 1.611601567111662e-05, 'epoch': 10.66}

 89%|████████▉ | 24950/28080 [49:17:29<6:16:13,  7.21s/it]
 89%|████████▉ | 24951/28080 [49:17:36<6:13:46,  7.17s/it]
                                                          
{'loss': 0.5901, 'learning_rate': 1.610583154603096e-05, 'epoch': 10.66}

 89%|████████▉ | 24951/28080 [49:17:36<6:13:46,  7.17s/it]
 89%|████████▉ | 24952/28080 [49:17:44<6:13:59,  7.17s/it]
                                                          
{'loss': 0.599, 'learning_rate': 1.609565053266582e-05, 'epoch': 10.66}

 89%|████████▉ | 24952/28080 [49:17:44<6:13:59,  7.17s/it]
 89%|████████▉ | 24953/28080 [49:17:51<6:12:30,  7.15s/it]
                                                          
{'loss': 0.5963, 'learning_rate': 1.6085472631156782e-05, 'epoch': 10.66}

 89%|████████▉ | 24953/28080 [49:17:51<6:12:30,  7.15s/it]
 89%|████████▉ | 24954/28080 [49:17:58<6:11:33,  7.13s/it]
                                                          
{'loss': 0.5961, 'learning_rate': 1.6075297841639164e-05, 'epoch': 10.66}

 89%|████████▉ | 24954/28080 [49:17:58<6:11:33,  7.13s/it]
 89%|████████▉ | 24955/28080 [49:18:05<6:10:50,  7.12s/it]
                                                          
{'loss': 0.597, 'learning_rate': 1.6065126164248434e-05, 'epoch': 10.66}

 89%|████████▉ | 24955/28080 [49:18:05<6:10:50,  7.12s/it]
 89%|████████▉ | 24956/28080 [49:18:12<6:10:41,  7.12s/it]
                                                          
{'loss': 0.6055, 'learning_rate': 1.6054957599119875e-05, 'epoch': 10.66}

 89%|████████▉ | 24956/28080 [49:18:12<6:10:41,  7.12s/it]
 89%|████████▉ | 24957/28080 [49:18:19<6:11:16,  7.13s/it]
                                                          
{'loss': 0.6014, 'learning_rate': 1.6044792146388765e-05, 'epoch': 10.66}

 89%|████████▉ | 24957/28080 [49:18:19<6:11:16,  7.13s/it]
 89%|████████▉ | 24958/28080 [49:18:26<6:09:24,  7.10s/it]
                                                          
{'loss': 0.6034, 'learning_rate': 1.6034629806190275e-05, 'epoch': 10.66}

 89%|████████▉ | 24958/28080 [49:18:26<6:09:24,  7.10s/it]
 89%|████████▉ | 24959/28080 [49:18:33<6:08:48,  7.09s/it]
                                                          
{'loss': 0.5924, 'learning_rate': 1.6024470578659716e-05, 'epoch': 10.66}

 89%|████████▉ | 24959/28080 [49:18:33<6:08:48,  7.09s/it]
 89%|████████▉ | 24960/28080 [49:18:40<6:08:23,  7.08s/it]
                                                          
{'loss': 0.5836, 'learning_rate': 1.601431446393217e-05, 'epoch': 10.66}

 89%|████████▉ | 24960/28080 [49:18:40<6:08:23,  7.08s/it]
 89%|████████▉ | 24961/28080 [49:18:47<6:07:07,  7.06s/it]
                                                          
{'loss': 0.5981, 'learning_rate': 1.6004161462142814e-05, 'epoch': 10.66}

 89%|████████▉ | 24961/28080 [49:18:47<6:07:07,  7.06s/it]
 89%|████████▉ | 24962/28080 [49:18:54<6:05:38,  7.04s/it]
                                                          
{'loss': 0.6082, 'learning_rate': 1.59940115734267e-05, 'epoch': 10.66}

 89%|████████▉ | 24962/28080 [49:18:54<6:05:38,  7.04s/it]
 89%|████████▉ | 24963/28080 [49:19:01<6:05:53,  7.04s/it]
                                                          
{'loss': 0.603, 'learning_rate': 1.5983864797918775e-05, 'epoch': 10.66}

 89%|████████▉ | 24963/28080 [49:19:01<6:05:53,  7.04s/it]
 89%|████████▉ | 24964/28080 [49:19:09<6:05:58,  7.05s/it]
                                                          
{'loss': 0.5981, 'learning_rate': 1.5973721135754153e-05, 'epoch': 10.66}

 89%|████████▉ | 24964/28080 [49:19:09<6:05:58,  7.05s/it]
 89%|████████▉ | 24965/28080 [49:19:16<6:07:32,  7.08s/it]
                                                          
{'loss': 0.5848, 'learning_rate': 1.596358058706776e-05, 'epoch': 10.66}

 89%|████████▉ | 24965/28080 [49:19:16<6:07:32,  7.08s/it]
 89%|████████▉ | 24966/28080 [49:19:23<6:07:45,  7.09s/it]
                                                          
{'loss': 0.6074, 'learning_rate': 1.5953443151994485e-05, 'epoch': 10.67}

 89%|████████▉ | 24966/28080 [49:19:23<6:07:45,  7.09s/it]
 89%|████████▉ | 24967/28080 [49:19:30<6:07:17,  7.08s/it]
                                                          
{'loss': 0.5895, 'learning_rate': 1.5943308830669134e-05, 'epoch': 10.67}

 89%|████████▉ | 24967/28080 [49:19:30<6:07:17,  7.08s/it]
 89%|████████▉ | 24968/28080 [49:19:37<6:07:18,  7.08s/it]
                                                          
{'loss': 0.5951, 'learning_rate': 1.593317762322666e-05, 'epoch': 10.67}

 89%|████████▉ | 24968/28080 [49:19:37<6:07:18,  7.08s/it]
 89%|████████▉ | 24969/28080 [49:19:44<6:06:31,  7.07s/it]
                                                          
{'loss': 0.6073, 'learning_rate': 1.5923049529801725e-05, 'epoch': 10.67}

 89%|████████▉ | 24969/28080 [49:19:44<6:06:31,  7.07s/it]
 89%|████████▉ | 24970/28080 [49:19:51<6:06:38,  7.07s/it]
                                                          
{'loss': 0.5899, 'learning_rate': 1.59129245505292e-05, 'epoch': 10.67}

 89%|████████▉ | 24970/28080 [49:19:51<6:06:38,  7.07s/it]
 89%|████████▉ | 24971/28080 [49:19:58<6:06:44,  7.08s/it]
                                                          
{'loss': 0.6148, 'learning_rate': 1.59028026855437e-05, 'epoch': 10.67}

 89%|████████▉ | 24971/28080 [49:19:58<6:06:44,  7.08s/it]
 89%|████████▉ | 24972/28080 [49:20:05<6:05:06,  7.05s/it]
                                                          
{'loss': 0.6112, 'learning_rate': 1.589268393497989e-05, 'epoch': 10.67}

 89%|████████▉ | 24972/28080 [49:20:05<6:05:06,  7.05s/it]
 89%|████████▉ | 24973/28080 [49:20:12<6:03:51,  7.03s/it]
                                                          
{'loss': 0.6141, 'learning_rate': 1.588256829897239e-05, 'epoch': 10.67}

 89%|████████▉ | 24973/28080 [49:20:12<6:03:51,  7.03s/it]
 89%|████████▉ | 24974/28080 [49:20:19<6:03:50,  7.03s/it]
                                                          
{'loss': 0.6218, 'learning_rate': 1.5872455777655837e-05, 'epoch': 10.67}

 89%|████████▉ | 24974/28080 [49:20:19<6:03:50,  7.03s/it]
 89%|████████▉ | 24975/28080 [49:20:26<6:06:10,  7.08s/it]
                                                          
{'loss': 0.5816, 'learning_rate': 1.586234637116471e-05, 'epoch': 10.67}

 89%|████████▉ | 24975/28080 [49:20:26<6:06:10,  7.08s/it]
 89%|████████▉ | 24976/28080 [49:20:33<6:06:46,  7.09s/it]
                                                          
{'loss': 0.5897, 'learning_rate': 1.585224007963351e-05, 'epoch': 10.67}

 89%|████████▉ | 24976/28080 [49:20:33<6:06:46,  7.09s/it]
 89%|████████▉ | 24977/28080 [49:20:40<6:05:55,  7.08s/it]
                                                          
{'loss': 0.5984, 'learning_rate': 1.5842136903196663e-05, 'epoch': 10.67}

 89%|████████▉ | 24977/28080 [49:20:40<6:05:55,  7.08s/it]
 89%|████████▉ | 24978/28080 [49:20:48<6:05:59,  7.08s/it]
                                                          
{'loss': 0.6189, 'learning_rate': 1.5832036841988668e-05, 'epoch': 10.67}

 89%|████████▉ | 24978/28080 [49:20:48<6:05:59,  7.08s/it]
 89%|████████▉ | 24979/28080 [49:20:55<6:06:04,  7.08s/it]
                                                          
{'loss': 0.6053, 'learning_rate': 1.5821939896143804e-05, 'epoch': 10.67}

 89%|████████▉ | 24979/28080 [49:20:55<6:06:04,  7.08s/it]
 89%|████████▉ | 24980/28080 [49:21:02<6:06:23,  7.09s/it]
                                                          
{'loss': 0.6, 'learning_rate': 1.5811846065796526e-05, 'epoch': 10.67}

 89%|████████▉ | 24980/28080 [49:21:02<6:06:23,  7.09s/it]
 89%|████████▉ | 24981/28080 [49:21:09<6:06:05,  7.09s/it]
                                                          
{'loss': 0.5747, 'learning_rate': 1.5801755351080942e-05, 'epoch': 10.67}

 89%|████████▉ | 24981/28080 [49:21:09<6:06:05,  7.09s/it]
 89%|████████▉ | 24982/28080 [49:21:16<6:06:11,  7.09s/it]
                                                          
{'loss': 0.6038, 'learning_rate': 1.579166775213145e-05, 'epoch': 10.67}

 89%|████████▉ | 24982/28080 [49:21:16<6:06:11,  7.09s/it]
 89%|████████▉ | 24983/28080 [49:21:23<6:06:27,  7.10s/it]
                                                          
{'loss': 0.6079, 'learning_rate': 1.5781583269082135e-05, 'epoch': 10.67}

 89%|████████▉ | 24983/28080 [49:21:23<6:06:27,  7.10s/it]
 89%|████████▉ | 24984/28080 [49:21:30<6:05:28,  7.08s/it]
                                                          
{'loss': 0.6218, 'learning_rate': 1.5771501902067303e-05, 'epoch': 10.67}

 89%|████████▉ | 24984/28080 [49:21:30<6:05:28,  7.08s/it]
 89%|████████▉ | 24985/28080 [49:21:37<6:05:41,  7.09s/it]
                                                          
{'loss': 0.6076, 'learning_rate': 1.576142365122099e-05, 'epoch': 10.67}

 89%|████████▉ | 24985/28080 [49:21:37<6:05:41,  7.09s/it]
 89%|████████▉ | 24986/28080 [49:21:44<6:04:45,  7.07s/it]
                                                          
{'loss': 0.5845, 'learning_rate': 1.5751348516677254e-05, 'epoch': 10.67}

 89%|████████▉ | 24986/28080 [49:21:44<6:04:45,  7.07s/it]
 89%|████████▉ | 24987/28080 [49:21:51<6:05:09,  7.08s/it]
                                                          
{'loss': 0.5985, 'learning_rate': 1.5741276498570185e-05, 'epoch': 10.67}

 89%|████████▉ | 24987/28080 [49:21:51<6:05:09,  7.08s/it]
 89%|████████▉ | 24988/28080 [49:21:58<6:04:18,  7.07s/it]
                                                          
{'loss': 0.5875, 'learning_rate': 1.57312075970337e-05, 'epoch': 10.67}

 89%|████████▉ | 24988/28080 [49:21:58<6:04:18,  7.07s/it]
 89%|████████▉ | 24989/28080 [49:22:05<6:04:39,  7.08s/it]
                                                          
{'loss': 0.5988, 'learning_rate': 1.5721141812201885e-05, 'epoch': 10.68}

 89%|████████▉ | 24989/28080 [49:22:05<6:04:39,  7.08s/it]
 89%|████████▉ | 24990/28080 [49:22:13<6:05:56,  7.11s/it]
                                                          
{'loss': 0.616, 'learning_rate': 1.5711079144208578e-05, 'epoch': 10.68}

 89%|████████▉ | 24990/28080 [49:22:13<6:05:56,  7.11s/it]
 89%|████████▉ | 24991/28080 [49:22:20<6:05:20,  7.10s/it]
                                                          
{'loss': 0.6082, 'learning_rate': 1.570101959318765e-05, 'epoch': 10.68}

 89%|████████▉ | 24991/28080 [49:22:20<6:05:20,  7.10s/it]
 89%|████████▉ | 24992/28080 [49:22:27<6:05:03,  7.09s/it]
                                                          
{'loss': 0.5956, 'learning_rate': 1.5690963159272902e-05, 'epoch': 10.68}

 89%|████████▉ | 24992/28080 [49:22:27<6:05:03,  7.09s/it]
 89%|████████▉ | 24993/28080 [49:22:34<6:06:05,  7.12s/it]
                                                          
{'loss': 0.5992, 'learning_rate': 1.5680909842598234e-05, 'epoch': 10.68}

 89%|████████▉ | 24993/28080 [49:22:34<6:06:05,  7.12s/it]
 89%|████████▉ | 24994/28080 [49:22:41<6:05:52,  7.11s/it]
                                                          
{'loss': 0.5985, 'learning_rate': 1.5670859643297285e-05, 'epoch': 10.68}

 89%|████████▉ | 24994/28080 [49:22:41<6:05:52,  7.11s/it]
 89%|████████▉ | 24995/28080 [49:22:48<6:05:51,  7.12s/it]
                                                          
{'loss': 0.5996, 'learning_rate': 1.566081256150384e-05, 'epoch': 10.68}

 89%|████████▉ | 24995/28080 [49:22:48<6:05:51,  7.12s/it]
 89%|████████▉ | 24996/28080 [49:22:55<6:04:56,  7.10s/it]
                                                          
{'loss': 0.6046, 'learning_rate': 1.5650768597351482e-05, 'epoch': 10.68}

 89%|████████▉ | 24996/28080 [49:22:55<6:04:56,  7.10s/it]
 89%|████████▉ | 24997/28080 [49:23:02<6:03:51,  7.08s/it]
                                                          
{'loss': 0.6097, 'learning_rate': 1.5640727750973917e-05, 'epoch': 10.68}

 89%|████████▉ | 24997/28080 [49:23:02<6:03:51,  7.08s/it]
 89%|████████▉ | 24998/28080 [49:23:09<6:05:23,  7.11s/it]
                                                          
{'loss': 0.5969, 'learning_rate': 1.5630690022504668e-05, 'epoch': 10.68}

 89%|████████▉ | 24998/28080 [49:23:10<6:05:23,  7.11s/it]
 89%|████████▉ | 24999/28080 [49:23:17<6:04:18,  7.09s/it]
                                                          
{'loss': 0.5909, 'learning_rate': 1.5620655412077356e-05, 'epoch': 10.68}

 89%|████████▉ | 24999/28080 [49:23:17<6:04:18,  7.09s/it]
 89%|████████▉ | 25000/28080 [49:23:24<6:05:22,  7.12s/it]
                                                          
{'loss': 0.614, 'learning_rate': 1.5610623919825372e-05, 'epoch': 10.68}

 89%|████████▉ | 25000/28080 [49:23:24<6:05:22,  7.12s/it]
 89%|████████▉ | 25001/28080 [49:23:31<6:06:38,  7.14s/it]
                                                          
{'loss': 0.6021, 'learning_rate': 1.5600595545882252e-05, 'epoch': 10.68}

 89%|████████▉ | 25001/28080 [49:23:31<6:06:38,  7.14s/it]
 89%|████████▉ | 25002/28080 [49:23:38<6:04:11,  7.10s/it]
                                                          
{'loss': 0.625, 'learning_rate': 1.5590570290381357e-05, 'epoch': 10.68}

 89%|████████▉ | 25002/28080 [49:23:38<6:04:11,  7.10s/it]
 89%|████████▉ | 25003/28080 [49:23:45<6:04:20,  7.10s/it]
                                                          
{'loss': 0.608, 'learning_rate': 1.5580548153456138e-05, 'epoch': 10.68}

 89%|████████▉ | 25003/28080 [49:23:45<6:04:20,  7.10s/it]
 89%|████████▉ | 25004/28080 [49:23:52<6:04:40,  7.11s/it]
                                                          
{'loss': 0.5933, 'learning_rate': 1.55705291352399e-05, 'epoch': 10.68}

 89%|████████▉ | 25004/28080 [49:23:52<6:04:40,  7.11s/it]
 89%|████████▉ | 25005/28080 [49:23:59<6:05:44,  7.14s/it]
                                                          
{'loss': 0.6019, 'learning_rate': 1.556051323586591e-05, 'epoch': 10.68}

 89%|████████▉ | 25005/28080 [49:23:59<6:05:44,  7.14s/it]
 89%|████████▉ | 25006/28080 [49:24:06<6:05:29,  7.13s/it]
                                                          
{'loss': 0.6152, 'learning_rate': 1.555050045546741e-05, 'epoch': 10.68}

 89%|████████▉ | 25006/28080 [49:24:06<6:05:29,  7.13s/it]
 89%|████████▉ | 25007/28080 [49:24:14<6:06:02,  7.15s/it]
                                                          
{'loss': 0.6115, 'learning_rate': 1.554049079417766e-05, 'epoch': 10.68}

 89%|████████▉ | 25007/28080 [49:24:14<6:06:02,  7.15s/it]
 89%|████████▉ | 25008/28080 [49:24:21<6:06:22,  7.16s/it]
                                                          
{'loss': 0.5921, 'learning_rate': 1.5530484252129802e-05, 'epoch': 10.68}

 89%|████████▉ | 25008/28080 [49:24:21<6:06:22,  7.16s/it]
 89%|████████▉ | 25009/28080 [49:24:28<6:05:48,  7.15s/it]
                                                          
{'loss': 0.5945, 'learning_rate': 1.552048082945698e-05, 'epoch': 10.68}

 89%|████████▉ | 25009/28080 [49:24:28<6:05:48,  7.15s/it]
 89%|████████▉ | 25010/28080 [49:24:35<6:04:44,  7.13s/it]
                                                          
{'loss': 0.5995, 'learning_rate': 1.551048052629225e-05, 'epoch': 10.68}

 89%|████████▉ | 25010/28080 [49:24:35<6:04:44,  7.13s/it]
 89%|████████▉ | 25011/28080 [49:24:42<6:04:37,  7.13s/it]
                                                          
{'loss': 0.5951, 'learning_rate': 1.5500483342768628e-05, 'epoch': 10.68}

 89%|████████▉ | 25011/28080 [49:24:42<6:04:37,  7.13s/it]
 89%|████████▉ | 25012/28080 [49:24:49<6:02:55,  7.10s/it]
                                                          
{'loss': 0.5965, 'learning_rate': 1.5490489279019192e-05, 'epoch': 10.68}

 89%|████████▉ | 25012/28080 [49:24:49<6:02:55,  7.10s/it]
 89%|████████▉ | 25013/28080 [49:24:56<6:03:19,  7.11s/it]
                                                          
{'loss': 0.5994, 'learning_rate': 1.548049833517684e-05, 'epoch': 10.69}

 89%|████████▉ | 25013/28080 [49:24:56<6:03:19,  7.11s/it]
 89%|████████▉ | 25014/28080 [49:25:03<6:01:17,  7.07s/it]
                                                          
{'loss': 0.5943, 'learning_rate': 1.5470510511374547e-05, 'epoch': 10.69}

 89%|████████▉ | 25014/28080 [49:25:03<6:01:17,  7.07s/it]
 89%|████████▉ | 25015/28080 [49:25:10<6:01:22,  7.07s/it]
                                                          
{'loss': 0.5883, 'learning_rate': 1.5460525807745124e-05, 'epoch': 10.69}

 89%|████████▉ | 25015/28080 [49:25:10<6:01:22,  7.07s/it]
 89%|████████▉ | 25016/28080 [49:25:18<6:02:14,  7.09s/it]
                                                          
{'loss': 0.5951, 'learning_rate': 1.5450544224421492e-05, 'epoch': 10.69}

 89%|████████▉ | 25016/28080 [49:25:18<6:02:14,  7.09s/it]
 89%|████████▉ | 25017/28080 [49:25:25<6:01:17,  7.08s/it]
                                                          
{'loss': 0.5873, 'learning_rate': 1.5440565761536325e-05, 'epoch': 10.69}

 89%|████████▉ | 25017/28080 [49:25:25<6:01:17,  7.08s/it]
 89%|████████▉ | 25018/28080 [49:25:32<6:00:33,  7.07s/it]
                                                          
{'loss': 0.5873, 'learning_rate': 1.543059041922251e-05, 'epoch': 10.69}

 89%|████████▉ | 25018/28080 [49:25:32<6:00:33,  7.07s/it]
 89%|████████▉ | 25019/28080 [49:25:39<6:00:11,  7.06s/it]
                                                          
{'loss': 0.5913, 'learning_rate': 1.54206181976127e-05, 'epoch': 10.69}

 89%|████████▉ | 25019/28080 [49:25:39<6:00:11,  7.06s/it]
 89%|████████▉ | 25020/28080 [49:25:46<6:00:26,  7.07s/it]
                                                          
{'loss': 0.5977, 'learning_rate': 1.5410649096839564e-05, 'epoch': 10.69}

 89%|████████▉ | 25020/28080 [49:25:46<6:00:26,  7.07s/it]
 89%|████████▉ | 25021/28080 [49:25:53<5:58:28,  7.03s/it]
                                                          
{'loss': 0.6127, 'learning_rate': 1.5400683117035684e-05, 'epoch': 10.69}

 89%|████████▉ | 25021/28080 [49:25:53<5:58:28,  7.03s/it]
 89%|████████▉ | 25022/28080 [49:26:00<5:59:46,  7.06s/it]
                                                          
{'loss': 0.594, 'learning_rate': 1.5390720258333712e-05, 'epoch': 10.69}

 89%|████████▉ | 25022/28080 [49:26:00<5:59:46,  7.06s/it]
 89%|████████▉ | 25023/28080 [49:26:07<5:59:48,  7.06s/it]
                                                          
{'loss': 0.6173, 'learning_rate': 1.5380760520866205e-05, 'epoch': 10.69}

 89%|████████▉ | 25023/28080 [49:26:07<5:59:48,  7.06s/it]
 89%|████████▉ | 25024/28080 [49:26:14<6:00:47,  7.08s/it]
                                                          
{'loss': 0.5797, 'learning_rate': 1.537080390476564e-05, 'epoch': 10.69}

 89%|████████▉ | 25024/28080 [49:26:14<6:00:47,  7.08s/it]
 89%|████████▉ | 25025/28080 [49:26:21<6:01:48,  7.11s/it]
                                                          
{'loss': 0.607, 'learning_rate': 1.5360850410164413e-05, 'epoch': 10.69}

 89%|████████▉ | 25025/28080 [49:26:21<6:01:48,  7.11s/it]
 89%|████████▉ | 25026/28080 [49:26:28<6:00:17,  7.08s/it]
                                                          
{'loss': 0.5951, 'learning_rate': 1.5350900037195052e-05, 'epoch': 10.69}

 89%|████████▉ | 25026/28080 [49:26:28<6:00:17,  7.08s/it]
 89%|████████▉ | 25027/28080 [49:26:35<6:00:51,  7.09s/it]
                                                          
{'loss': 0.6016, 'learning_rate': 1.5340952785989905e-05, 'epoch': 10.69}

 89%|████████▉ | 25027/28080 [49:26:35<6:00:51,  7.09s/it]
 89%|████████▉ | 25028/28080 [49:26:42<6:01:14,  7.10s/it]
                                                          
{'loss': 0.5973, 'learning_rate': 1.5331008656681274e-05, 'epoch': 10.69}

 89%|████████▉ | 25028/28080 [49:26:42<6:01:14,  7.10s/it]
 89%|████████▉ | 25029/28080 [49:26:50<6:01:19,  7.11s/it]
                                                          
{'loss': 0.6003, 'learning_rate': 1.5321067649401442e-05, 'epoch': 10.69}

 89%|████████▉ | 25029/28080 [49:26:50<6:01:19,  7.11s/it]
 89%|████████▉ | 25030/28080 [49:26:57<6:01:43,  7.12s/it]
                                                          
{'loss': 0.602, 'learning_rate': 1.5311129764282754e-05, 'epoch': 10.69}

 89%|████████▉ | 25030/28080 [49:26:57<6:01:43,  7.12s/it]
 89%|████████▉ | 25031/28080 [49:27:04<6:02:01,  7.12s/it]
                                                          
{'loss': 0.5897, 'learning_rate': 1.5301195001457325e-05, 'epoch': 10.69}

 89%|████████▉ | 25031/28080 [49:27:04<6:02:01,  7.12s/it]
 89%|████████▉ | 25032/28080 [49:27:11<6:02:01,  7.13s/it]
                                                          
{'loss': 0.6057, 'learning_rate': 1.5291263361057405e-05, 'epoch': 10.69}

 89%|████████▉ | 25032/28080 [49:27:11<6:02:01,  7.13s/it]
 89%|████████▉ | 25033/28080 [49:27:18<5:58:43,  7.06s/it]
                                                          
{'loss': 0.6198, 'learning_rate': 1.5281334843215118e-05, 'epoch': 10.69}

 89%|████████▉ | 25033/28080 [49:27:18<5:58:43,  7.06s/it]
 89%|████████▉ | 25034/28080 [49:27:25<5:58:38,  7.06s/it]
                                                          
{'loss': 0.612, 'learning_rate': 1.527140944806249e-05, 'epoch': 10.69}

 89%|████████▉ | 25034/28080 [49:27:25<5:58:38,  7.06s/it]
 89%|████████▉ | 25035/28080 [49:27:32<5:59:45,  7.09s/it]
                                                          
{'loss': 0.6067, 'learning_rate': 1.5261487175731615e-05, 'epoch': 10.69}

 89%|████████▉ | 25035/28080 [49:27:32<5:59:45,  7.09s/it]
 89%|████████▉ | 25036/28080 [49:27:39<5:58:50,  7.07s/it]
                                                          
{'loss': 0.6071, 'learning_rate': 1.525156802635444e-05, 'epoch': 10.7}

 89%|████████▉ | 25036/28080 [49:27:39<5:58:50,  7.07s/it]
 89%|████████▉ | 25037/28080 [49:27:46<5:58:50,  7.08s/it]
                                                          
{'loss': 0.6184, 'learning_rate': 1.5241652000063028e-05, 'epoch': 10.7}

 89%|████████▉ | 25037/28080 [49:27:46<5:58:50,  7.08s/it]
 89%|████████▉ | 25038/28080 [49:27:53<5:59:07,  7.08s/it]
                                                          
{'loss': 0.6133, 'learning_rate': 1.5231739096989244e-05, 'epoch': 10.7}

 89%|████████▉ | 25038/28080 [49:27:53<5:59:07,  7.08s/it]
 89%|████████▉ | 25039/28080 [49:28:00<6:00:01,  7.10s/it]
                                                          
{'loss': 0.5842, 'learning_rate': 1.5221829317264984e-05, 'epoch': 10.7}

 89%|████████▉ | 25039/28080 [49:28:00<6:00:01,  7.10s/it]
 89%|████████▉ | 25040/28080 [49:28:07<5:58:09,  7.07s/it]
                                                          
{'loss': 0.611, 'learning_rate': 1.5211922661022031e-05, 'epoch': 10.7}

 89%|████████▉ | 25040/28080 [49:28:07<5:58:09,  7.07s/it]
 89%|████████▉ | 25041/28080 [49:28:15<5:58:36,  7.08s/it]
                                                          
{'loss': 0.6192, 'learning_rate': 1.520201912839228e-05, 'epoch': 10.7}

 89%|████████▉ | 25041/28080 [49:28:15<5:58:36,  7.08s/it]
 89%|████████▉ | 25042/28080 [49:28:22<5:57:26,  7.06s/it]
                                                          
{'loss': 0.6111, 'learning_rate': 1.5192118719507403e-05, 'epoch': 10.7}

 89%|████████▉ | 25042/28080 [49:28:22<5:57:26,  7.06s/it]
 89%|████████▉ | 25043/28080 [49:28:29<5:59:15,  7.10s/it]
                                                          
{'loss': 0.6029, 'learning_rate': 1.5182221434499183e-05, 'epoch': 10.7}

 89%|████████▉ | 25043/28080 [49:28:29<5:59:15,  7.10s/it]
 89%|████████▉ | 25044/28080 [49:28:36<6:00:20,  7.12s/it]
                                                          
{'loss': 0.6104, 'learning_rate': 1.517232727349921e-05, 'epoch': 10.7}

 89%|████████▉ | 25044/28080 [49:28:36<6:00:20,  7.12s/it]
 89%|████████▉ | 25045/28080 [49:28:43<5:59:38,  7.11s/it]
                                                          
{'loss': 0.6028, 'learning_rate': 1.516243623663921e-05, 'epoch': 10.7}

 89%|████████▉ | 25045/28080 [49:28:43<5:59:38,  7.11s/it]
 89%|████████▉ | 25046/28080 [49:28:50<6:00:07,  7.12s/it]
                                                          
{'loss': 0.5994, 'learning_rate': 1.5152548324050664e-05, 'epoch': 10.7}

 89%|████████▉ | 25046/28080 [49:28:50<6:00:07,  7.12s/it]
 89%|████████▉ | 25047/28080 [49:28:57<6:00:45,  7.14s/it]
                                                          
{'loss': 0.5966, 'learning_rate': 1.5142663535865269e-05, 'epoch': 10.7}

 89%|████████▉ | 25047/28080 [49:28:57<6:00:45,  7.14s/it]
 89%|████████▉ | 25048/28080 [49:29:04<6:00:40,  7.14s/it]
                                                          
{'loss': 0.599, 'learning_rate': 1.5132781872214396e-05, 'epoch': 10.7}

 89%|████████▉ | 25048/28080 [49:29:04<6:00:40,  7.14s/it]
 89%|████████▉ | 25049/28080 [49:29:12<5:58:57,  7.11s/it]
                                                          
{'loss': 0.5966, 'learning_rate': 1.5122903333229577e-05, 'epoch': 10.7}

 89%|████████▉ | 25049/28080 [49:29:12<5:58:57,  7.11s/it]
 89%|████████▉ | 25050/28080 [49:29:19<5:58:17,  7.09s/it]
                                                          
{'loss': 0.5943, 'learning_rate': 1.5113027919042177e-05, 'epoch': 10.7}

 89%|████████▉ | 25050/28080 [49:29:19<5:58:17,  7.09s/it]
 89%|████████▉ | 25051/28080 [49:29:26<5:57:21,  7.08s/it]
                                                          
{'loss': 0.5926, 'learning_rate': 1.5103155629783677e-05, 'epoch': 10.7}

 89%|████████▉ | 25051/28080 [49:29:26<5:57:21,  7.08s/it]
 89%|████████▉ | 25052/28080 [49:29:33<5:57:42,  7.09s/it]
                                                          
{'loss': 0.5893, 'learning_rate': 1.509328646558536e-05, 'epoch': 10.7}

 89%|████████▉ | 25052/28080 [49:29:33<5:57:42,  7.09s/it]
 89%|████████▉ | 25053/28080 [49:29:40<5:58:16,  7.10s/it]
                                                          
{'loss': 0.5979, 'learning_rate': 1.508342042657851e-05, 'epoch': 10.7}

 89%|████████▉ | 25053/28080 [49:29:40<5:58:16,  7.10s/it]
 89%|████████▉ | 25054/28080 [49:29:47<5:57:35,  7.09s/it]
                                                          
{'loss': 0.6097, 'learning_rate': 1.5073557512894382e-05, 'epoch': 10.7}

 89%|████████▉ | 25054/28080 [49:29:47<5:57:35,  7.09s/it]
 89%|████████▉ | 25055/28080 [49:29:54<5:56:56,  7.08s/it]
                                                          
{'loss': 0.6065, 'learning_rate': 1.5063697724664233e-05, 'epoch': 10.7}

 89%|████████▉ | 25055/28080 [49:29:54<5:56:56,  7.08s/it]
 89%|████████▉ | 25056/28080 [49:30:01<5:55:49,  7.06s/it]
                                                          
{'loss': 0.6026, 'learning_rate': 1.5053841062019236e-05, 'epoch': 10.7}

 89%|████████▉ | 25056/28080 [49:30:01<5:55:49,  7.06s/it]
 89%|████████▉ | 25057/28080 [49:30:08<5:56:24,  7.07s/it]
                                                          
{'loss': 0.5921, 'learning_rate': 1.504398752509048e-05, 'epoch': 10.7}

 89%|████████▉ | 25057/28080 [49:30:08<5:56:24,  7.07s/it]
 89%|████████▉ | 25058/28080 [49:30:15<5:57:36,  7.10s/it]
                                                          
{'loss': 0.6011, 'learning_rate': 1.5034137114009056e-05, 'epoch': 10.7}

 89%|████████▉ | 25058/28080 [49:30:15<5:57:36,  7.10s/it]
 89%|████████▉ | 25059/28080 [49:30:22<5:57:34,  7.10s/it]
                                                          
{'loss': 0.6191, 'learning_rate': 1.5024289828906052e-05, 'epoch': 10.7}

 89%|████████▉ | 25059/28080 [49:30:22<5:57:34,  7.10s/it]
 89%|████████▉ | 25060/28080 [49:30:30<5:57:55,  7.11s/it]
                                                          
{'loss': 0.5868, 'learning_rate': 1.5014445669912503e-05, 'epoch': 10.71}

 89%|████████▉ | 25060/28080 [49:30:30<5:57:55,  7.11s/it]
 89%|████████▉ | 25061/28080 [49:30:37<5:57:25,  7.10s/it]
                                                          
{'loss': 0.6017, 'learning_rate': 1.5004604637159302e-05, 'epoch': 10.71}

 89%|████████▉ | 25061/28080 [49:30:37<5:57:25,  7.10s/it]
 89%|████████▉ | 25062/28080 [49:30:44<5:57:42,  7.11s/it]
                                                          
{'loss': 0.6101, 'learning_rate': 1.4994766730777404e-05, 'epoch': 10.71}

 89%|████████▉ | 25062/28080 [49:30:44<5:57:42,  7.11s/it]
 89%|████████▉ | 25063/28080 [49:30:51<5:56:08,  7.08s/it]
                                                          
{'loss': 0.596, 'learning_rate': 1.4984931950897673e-05, 'epoch': 10.71}

 89%|████████▉ | 25063/28080 [49:30:51<5:56:08,  7.08s/it]
 89%|████████▉ | 25064/28080 [49:30:58<5:56:43,  7.10s/it]
                                                          
{'loss': 0.5986, 'learning_rate': 1.497510029765098e-05, 'epoch': 10.71}

 89%|████████▉ | 25064/28080 [49:30:58<5:56:43,  7.10s/it]
 89%|████████▉ | 25065/28080 [49:31:05<5:55:29,  7.07s/it]
                                                          
{'loss': 0.6111, 'learning_rate': 1.4965271771168104e-05, 'epoch': 10.71}

 89%|████████▉ | 25065/28080 [49:31:05<5:55:29,  7.07s/it]
 89%|████████▉ | 25066/28080 [49:31:12<5:55:21,  7.07s/it]
                                                          
{'loss': 0.5936, 'learning_rate': 1.4955446371579862e-05, 'epoch': 10.71}

 89%|████████▉ | 25066/28080 [49:31:12<5:55:21,  7.07s/it]
 89%|████████▉ | 25067/28080 [49:31:19<5:56:17,  7.10s/it]
                                                          
{'loss': 0.611, 'learning_rate': 1.4945624099016897e-05, 'epoch': 10.71}

 89%|████████▉ | 25067/28080 [49:31:19<5:56:17,  7.10s/it]
 89%|████████▉ | 25068/28080 [49:31:26<5:57:07,  7.11s/it]
                                                          
{'loss': 0.6037, 'learning_rate': 1.493580495360991e-05, 'epoch': 10.71}

 89%|████████▉ | 25068/28080 [49:31:26<5:57:07,  7.11s/it]
 89%|████████▉ | 25069/28080 [49:31:33<5:55:55,  7.09s/it]
                                                          
{'loss': 0.5793, 'learning_rate': 1.492598893548952e-05, 'epoch': 10.71}

 89%|████████▉ | 25069/28080 [49:31:33<5:55:55,  7.09s/it]
 89%|████████▉ | 25070/28080 [49:31:40<5:55:53,  7.09s/it]
                                                          
{'loss': 0.5672, 'learning_rate': 1.4916176044786373e-05, 'epoch': 10.71}

 89%|████████▉ | 25070/28080 [49:31:40<5:55:53,  7.09s/it]
 89%|████████▉ | 25071/28080 [49:31:48<5:58:17,  7.14s/it]
                                                          
{'loss': 0.6021, 'learning_rate': 1.4906366281630973e-05, 'epoch': 10.71}

 89%|████████▉ | 25071/28080 [49:31:48<5:58:17,  7.14s/it]
 89%|████████▉ | 25072/28080 [49:31:55<5:56:03,  7.10s/it]
                                                          
{'loss': 0.6176, 'learning_rate': 1.4896559646153829e-05, 'epoch': 10.71}

 89%|████████▉ | 25072/28080 [49:31:55<5:56:03,  7.10s/it]
 89%|████████▉ | 25073/28080 [49:32:02<5:55:59,  7.10s/it]
                                                          
{'loss': 0.5891, 'learning_rate': 1.4886756138485392e-05, 'epoch': 10.71}

 89%|████████▉ | 25073/28080 [49:32:02<5:55:59,  7.10s/it]
 89%|████████▉ | 25074/28080 [49:32:09<5:56:00,  7.11s/it]
                                                          
{'loss': 0.6018, 'learning_rate': 1.487695575875614e-05, 'epoch': 10.71}

 89%|████████▉ | 25074/28080 [49:32:09<5:56:00,  7.11s/it]
 89%|████████▉ | 25075/28080 [49:32:16<5:56:45,  7.12s/it]
                                                          
{'loss': 0.6105, 'learning_rate': 1.4867158507096412e-05, 'epoch': 10.71}

 89%|████████▉ | 25075/28080 [49:32:16<5:56:45,  7.12s/it]
 89%|████████▉ | 25076/28080 [49:32:23<5:56:44,  7.13s/it]
                                                          
{'loss': 0.5964, 'learning_rate': 1.4857364383636607e-05, 'epoch': 10.71}

 89%|████████▉ | 25076/28080 [49:32:23<5:56:44,  7.13s/it]
 89%|████████▉ | 25077/28080 [49:32:30<5:56:44,  7.13s/it]
                                                          
{'loss': 0.6152, 'learning_rate': 1.4847573388506924e-05, 'epoch': 10.71}

 89%|████████▉ | 25077/28080 [49:32:30<5:56:44,  7.13s/it]
 89%|████████▉ | 25078/28080 [49:32:37<5:56:37,  7.13s/it]
                                                          
{'loss': 0.6099, 'learning_rate': 1.4837785521837705e-05, 'epoch': 10.71}

 89%|████████▉ | 25078/28080 [49:32:37<5:56:37,  7.13s/it]
 89%|████████▉ | 25079/28080 [49:32:45<5:56:59,  7.14s/it]
                                                          
{'loss': 0.593, 'learning_rate': 1.4828000783759148e-05, 'epoch': 10.71}

 89%|████████▉ | 25079/28080 [49:32:45<5:56:59,  7.14s/it]
 89%|████████▉ | 25080/28080 [49:32:52<5:56:25,  7.13s/it]
                                                          
{'loss': 0.5819, 'learning_rate': 1.4818219174401431e-05, 'epoch': 10.71}

 89%|████████▉ | 25080/28080 [49:32:52<5:56:25,  7.13s/it]
 89%|████████▉ | 25081/28080 [49:32:59<5:55:03,  7.10s/it]
                                                          
{'loss': 0.6171, 'learning_rate': 1.4808440693894698e-05, 'epoch': 10.71}

 89%|████████▉ | 25081/28080 [49:32:59<5:55:03,  7.10s/it]
 89%|████████▉ | 25082/28080 [49:33:06<5:55:14,  7.11s/it]
                                                          
{'loss': 0.5761, 'learning_rate': 1.4798665342369039e-05, 'epoch': 10.71}

 89%|████████▉ | 25082/28080 [49:33:06<5:55:14,  7.11s/it]
 89%|████████▉ | 25083/28080 [49:33:13<5:54:18,  7.09s/it]
                                                          
{'loss': 0.6173, 'learning_rate': 1.4788893119954433e-05, 'epoch': 10.72}

 89%|████████▉ | 25083/28080 [49:33:13<5:54:18,  7.09s/it]
 89%|████████▉ | 25084/28080 [49:33:20<5:54:58,  7.11s/it]
                                                          
{'loss': 0.5951, 'learning_rate': 1.4779124026781e-05, 'epoch': 10.72}

 89%|████████▉ | 25084/28080 [49:33:20<5:54:58,  7.11s/it]
 89%|████████▉ | 25085/28080 [49:33:27<5:54:25,  7.10s/it]
                                                          
{'loss': 0.6152, 'learning_rate': 1.4769358062978661e-05, 'epoch': 10.72}

 89%|████████▉ | 25085/28080 [49:33:27<5:54:25,  7.10s/it]
 89%|████████▉ | 25086/28080 [49:33:34<5:54:17,  7.10s/it]
                                                          
{'loss': 0.6169, 'learning_rate': 1.4759595228677342e-05, 'epoch': 10.72}

 89%|████████▉ | 25086/28080 [49:33:34<5:54:17,  7.10s/it]
 89%|████████▉ | 25087/28080 [49:33:41<5:53:05,  7.08s/it]
                                                          
{'loss': 0.6077, 'learning_rate': 1.474983552400691e-05, 'epoch': 10.72}

 89%|████████▉ | 25087/28080 [49:33:41<5:53:05,  7.08s/it]
 89%|████████▉ | 25088/28080 [49:33:48<5:53:44,  7.09s/it]
                                                          
{'loss': 0.6065, 'learning_rate': 1.4740078949097208e-05, 'epoch': 10.72}

 89%|████████▉ | 25088/28080 [49:33:48<5:53:44,  7.09s/it]
 89%|████████▉ | 25089/28080 [49:33:56<5:53:59,  7.10s/it]
                                                          
{'loss': 0.5971, 'learning_rate': 1.4730325504078074e-05, 'epoch': 10.72}

 89%|████████▉ | 25089/28080 [49:33:56<5:53:59,  7.10s/it]
 89%|████████▉ | 25090/28080 [49:34:03<5:54:27,  7.11s/it]
                                                          
{'loss': 0.6016, 'learning_rate': 1.4720575189079239e-05, 'epoch': 10.72}

 89%|████████▉ | 25090/28080 [49:34:03<5:54:27,  7.11s/it]
 89%|████████▉ | 25091/28080 [49:34:10<5:55:24,  7.13s/it]
                                                          
{'loss': 0.5886, 'learning_rate': 1.4710828004230431e-05, 'epoch': 10.72}

 89%|████████▉ | 25091/28080 [49:34:10<5:55:24,  7.13s/it]
 89%|████████▉ | 25092/28080 [49:34:17<5:53:46,  7.10s/it]
                                                          
{'loss': 0.6279, 'learning_rate': 1.4701083949661298e-05, 'epoch': 10.72}

 89%|████████▉ | 25092/28080 [49:34:17<5:53:46,  7.10s/it]
 89%|████████▉ | 25093/28080 [49:34:24<5:54:35,  7.12s/it]
                                                          
{'loss': 0.5994, 'learning_rate': 1.4691343025501513e-05, 'epoch': 10.72}

 89%|████████▉ | 25093/28080 [49:34:24<5:54:35,  7.12s/it]
 89%|████████▉ | 25094/28080 [49:34:31<5:53:36,  7.11s/it]
                                                          
{'loss': 0.6, 'learning_rate': 1.468160523188064e-05, 'epoch': 10.72}

 89%|████████▉ | 25094/28080 [49:34:31<5:53:36,  7.11s/it]
 89%|████████▉ | 25095/28080 [49:34:38<5:52:44,  7.09s/it]
                                                          
{'loss': 0.6234, 'learning_rate': 1.4671870568928297e-05, 'epoch': 10.72}

 89%|████████▉ | 25095/28080 [49:34:38<5:52:44,  7.09s/it]
 89%|████████▉ | 25096/28080 [49:34:45<5:52:01,  7.08s/it]
                                                          
{'loss': 0.5829, 'learning_rate': 1.4662139036773881e-05, 'epoch': 10.72}

 89%|████████▉ | 25096/28080 [49:34:45<5:52:01,  7.08s/it]
 89%|████████▉ | 25097/28080 [49:34:52<5:52:22,  7.09s/it]
                                                          
{'loss': 0.5859, 'learning_rate': 1.4652410635546953e-05, 'epoch': 10.72}

 89%|████████▉ | 25097/28080 [49:34:52<5:52:22,  7.09s/it]
 89%|████████▉ | 25098/28080 [49:35:00<5:54:15,  7.13s/it]
                                                          
{'loss': 0.5987, 'learning_rate': 1.4642685365376885e-05, 'epoch': 10.72}

 89%|████████▉ | 25098/28080 [49:35:00<5:54:15,  7.13s/it]
 89%|████████▉ | 25099/28080 [49:35:07<5:53:59,  7.13s/it]
                                                          
{'loss': 0.6078, 'learning_rate': 1.4632963226393098e-05, 'epoch': 10.72}

 89%|████████▉ | 25099/28080 [49:35:07<5:53:59,  7.13s/it]
 89%|████████▉ | 25100/28080 [49:35:14<5:54:33,  7.14s/it]
                                                          
{'loss': 0.5809, 'learning_rate': 1.4623244218724935e-05, 'epoch': 10.72}

 89%|████████▉ | 25100/28080 [49:35:14<5:54:33,  7.14s/it]
 89%|████████▉ | 25101/28080 [49:35:21<5:54:01,  7.13s/it]
                                                          
{'loss': 0.5976, 'learning_rate': 1.461352834250168e-05, 'epoch': 10.72}

 89%|████████▉ | 25101/28080 [49:35:21<5:54:01,  7.13s/it]
 89%|████████▉ | 25102/28080 [49:35:28<5:52:40,  7.11s/it]
                                                          
{'loss': 0.6081, 'learning_rate': 1.4603815597852537e-05, 'epoch': 10.72}

 89%|████████▉ | 25102/28080 [49:35:28<5:52:40,  7.11s/it]
 89%|████████▉ | 25103/28080 [49:35:35<5:54:33,  7.15s/it]
                                                          
{'loss': 0.5968, 'learning_rate': 1.4594105984906846e-05, 'epoch': 10.72}

 89%|████████▉ | 25103/28080 [49:35:35<5:54:33,  7.15s/it]
 89%|████████▉ | 25104/28080 [49:35:42<5:53:01,  7.12s/it]
                                                          
{'loss': 0.5832, 'learning_rate': 1.4584399503793728e-05, 'epoch': 10.72}

 89%|████████▉ | 25104/28080 [49:35:42<5:53:01,  7.12s/it]
 89%|████████▉ | 25105/28080 [49:35:49<5:53:40,  7.13s/it]
                                                          
{'loss': 0.6021, 'learning_rate': 1.4574696154642297e-05, 'epoch': 10.72}

 89%|████████▉ | 25105/28080 [49:35:49<5:53:40,  7.13s/it]
 89%|████████▉ | 25106/28080 [49:35:57<5:53:39,  7.13s/it]
                                                          
{'loss': 0.5898, 'learning_rate': 1.4564995937581621e-05, 'epoch': 10.73}

 89%|████████▉ | 25106/28080 [49:35:57<5:53:39,  7.13s/it]
 89%|████████▉ | 25107/28080 [49:36:04<5:53:22,  7.13s/it]
                                                          
{'loss': 0.5988, 'learning_rate': 1.4555298852740817e-05, 'epoch': 10.73}

 89%|████████▉ | 25107/28080 [49:36:04<5:53:22,  7.13s/it]
 89%|████████▉ | 25108/28080 [49:36:11<5:50:57,  7.09s/it]
                                                          
{'loss': 0.6472, 'learning_rate': 1.4545604900248838e-05, 'epoch': 10.73}

 89%|████████▉ | 25108/28080 [49:36:11<5:50:57,  7.09s/it]
 89%|████████▉ | 25109/28080 [49:36:18<5:51:53,  7.11s/it]
                                                          
{'loss': 0.5964, 'learning_rate': 1.4535914080234746e-05, 'epoch': 10.73}

 89%|████████▉ | 25109/28080 [49:36:18<5:51:53,  7.11s/it]
 89%|████████▉ | 25110/28080 [49:36:25<5:51:23,  7.10s/it]
                                                          
{'loss': 0.6113, 'learning_rate': 1.4526226392827385e-05, 'epoch': 10.73}

 89%|████████▉ | 25110/28080 [49:36:25<5:51:23,  7.10s/it]
 89%|████████▉ | 25111/28080 [49:36:32<5:52:57,  7.13s/it]
                                                          
{'loss': 0.572, 'learning_rate': 1.4516541838155594e-05, 'epoch': 10.73}

 89%|████████▉ | 25111/28080 [49:36:32<5:52:57,  7.13s/it]
 89%|████████▉ | 25112/28080 [49:36:39<5:53:07,  7.14s/it]
                                                          
{'loss': 0.5865, 'learning_rate': 1.4506860416348355e-05, 'epoch': 10.73}

 89%|████████▉ | 25112/28080 [49:36:39<5:53:07,  7.14s/it]
 89%|████████▉ | 25113/28080 [49:36:46<5:53:12,  7.14s/it]
                                                          
{'loss': 0.5966, 'learning_rate': 1.4497182127534313e-05, 'epoch': 10.73}

 89%|████████▉ | 25113/28080 [49:36:46<5:53:12,  7.14s/it]
 89%|████████▉ | 25114/28080 [49:36:54<5:51:37,  7.11s/it]
                                                          
{'loss': 0.6123, 'learning_rate': 1.4487506971842423e-05, 'epoch': 10.73}

 89%|████████▉ | 25114/28080 [49:36:54<5:51:37,  7.11s/it]
 89%|████████▉ | 25115/28080 [49:37:01<5:52:12,  7.13s/it]
                                                          
{'loss': 0.5979, 'learning_rate': 1.4477834949401192e-05, 'epoch': 10.73}

 89%|████████▉ | 25115/28080 [49:37:01<5:52:12,  7.13s/it]
 89%|████████▉ | 25116/28080 [49:37:08<5:51:57,  7.12s/it]
                                                          
{'loss': 0.5973, 'learning_rate': 1.4468166060339432e-05, 'epoch': 10.73}

 89%|████████▉ | 25116/28080 [49:37:08<5:51:57,  7.12s/it]
 89%|████████▉ | 25117/28080 [49:37:15<5:51:45,  7.12s/it]
                                                          
{'loss': 0.5984, 'learning_rate': 1.4458500304785682e-05, 'epoch': 10.73}

 89%|████████▉ | 25117/28080 [49:37:15<5:51:45,  7.12s/it]
 89%|████████▉ | 25118/28080 [49:37:22<5:52:59,  7.15s/it]
                                                          
{'loss': 0.598, 'learning_rate': 1.4448837682868642e-05, 'epoch': 10.73}

 89%|████████▉ | 25118/28080 [49:37:22<5:52:59,  7.15s/it]
 89%|████████▉ | 25119/28080 [49:37:29<5:52:15,  7.14s/it]
                                                          
{'loss': 0.5923, 'learning_rate': 1.4439178194716824e-05, 'epoch': 10.73}

 89%|████████▉ | 25119/28080 [49:37:29<5:52:15,  7.14s/it]
 89%|████████▉ | 25120/28080 [49:37:36<5:51:12,  7.12s/it]
                                                          
{'loss': 0.6062, 'learning_rate': 1.4429521840458732e-05, 'epoch': 10.73}

 89%|████████▉ | 25120/28080 [49:37:36<5:51:12,  7.12s/it]
 89%|████████▉ | 25121/28080 [49:37:43<5:51:23,  7.13s/it]
                                                          
{'loss': 0.5997, 'learning_rate': 1.4419868620222765e-05, 'epoch': 10.73}

 89%|████████▉ | 25121/28080 [49:37:43<5:51:23,  7.13s/it]
 89%|████████▉ | 25122/28080 [49:37:51<5:51:12,  7.12s/it]
                                                          
{'loss': 0.5933, 'learning_rate': 1.441021853413746e-05, 'epoch': 10.73}

 89%|████████▉ | 25122/28080 [49:37:51<5:51:12,  7.12s/it]
 89%|████████▉ | 25123/28080 [49:37:58<5:51:21,  7.13s/it]
                                                          
{'loss': 0.5973, 'learning_rate': 1.4400571582331156e-05, 'epoch': 10.73}

 89%|████████▉ | 25123/28080 [49:37:58<5:51:21,  7.13s/it]
 89%|████████▉ | 25124/28080 [49:38:05<5:51:47,  7.14s/it]
                                                          
{'loss': 0.6078, 'learning_rate': 1.4390927764932172e-05, 'epoch': 10.73}

 89%|████████▉ | 25124/28080 [49:38:05<5:51:47,  7.14s/it]
 89%|████████▉ | 25125/28080 [49:38:12<5:52:15,  7.15s/it]
                                                          
{'loss': 0.5825, 'learning_rate': 1.4381287082068817e-05, 'epoch': 10.73}

 89%|████████▉ | 25125/28080 [49:38:12<5:52:15,  7.15s/it]
 89%|████████▉ | 25126/28080 [49:38:19<5:49:29,  7.10s/it]
                                                          
{'loss': 0.6098, 'learning_rate': 1.4371649533869407e-05, 'epoch': 10.73}

 89%|████████▉ | 25126/28080 [49:38:19<5:49:29,  7.10s/it]
 89%|████████▉ | 25127/28080 [49:38:26<5:49:18,  7.10s/it]
                                                          
{'loss': 0.5855, 'learning_rate': 1.4362015120462063e-05, 'epoch': 10.73}

 89%|████████▉ | 25127/28080 [49:38:26<5:49:18,  7.10s/it]
 89%|████████▉ | 25128/28080 [49:38:33<5:50:21,  7.12s/it]
                                                          
{'loss': 0.5931, 'learning_rate': 1.4352383841975043e-05, 'epoch': 10.73}

 89%|████████▉ | 25128/28080 [49:38:33<5:50:21,  7.12s/it]
 89%|████████▉ | 25129/28080 [49:38:40<5:50:38,  7.13s/it]
                                                          
{'loss': 0.5916, 'learning_rate': 1.4342755698536463e-05, 'epoch': 10.73}

 89%|████████▉ | 25129/28080 [49:38:40<5:50:38,  7.13s/it]
 89%|████████▉ | 25130/28080 [49:38:48<5:49:25,  7.11s/it]
                                                          
{'loss': 0.6415, 'learning_rate': 1.4333130690274393e-05, 'epoch': 10.74}

 89%|████████▉ | 25130/28080 [49:38:48<5:49:25,  7.11s/it]
 89%|████████▉ | 25131/28080 [49:38:55<5:50:17,  7.13s/it]
                                                          
{'loss': 0.5916, 'learning_rate': 1.4323508817316866e-05, 'epoch': 10.74}

 89%|████████▉ | 25131/28080 [49:38:55<5:50:17,  7.13s/it]
 90%|████████▉ | 25132/28080 [49:39:02<5:50:47,  7.14s/it]
                                                          
{'loss': 0.614, 'learning_rate': 1.4313890079791975e-05, 'epoch': 10.74}

 90%|████████▉ | 25132/28080 [49:39:02<5:50:47,  7.14s/it]
 90%|████████▉ | 25133/28080 [49:39:09<5:50:47,  7.14s/it]
                                                          
{'loss': 0.6018, 'learning_rate': 1.4304274477827616e-05, 'epoch': 10.74}

 90%|████████▉ | 25133/28080 [49:39:09<5:50:47,  7.14s/it]
 90%|████████▉ | 25134/28080 [49:39:16<5:50:58,  7.15s/it]
                                                          
{'loss': 0.6193, 'learning_rate': 1.4294662011551718e-05, 'epoch': 10.74}

 90%|████████▉ | 25134/28080 [49:39:16<5:50:58,  7.15s/it]
 90%|████████▉ | 25135/28080 [49:39:23<5:48:49,  7.11s/it]
                                                          
{'loss': 0.6065, 'learning_rate': 1.4285052681092203e-05, 'epoch': 10.74}

 90%|████████▉ | 25135/28080 [49:39:23<5:48:49,  7.11s/it]
 90%|████████▉ | 25136/28080 [49:39:30<5:48:34,  7.10s/it]
                                                          
{'loss': 0.6022, 'learning_rate': 1.4275446486576831e-05, 'epoch': 10.74}

 90%|████████▉ | 25136/28080 [49:39:30<5:48:34,  7.10s/it]
 90%|████████▉ | 25137/28080 [49:39:37<5:48:39,  7.11s/it]
                                                          
{'loss': 0.591, 'learning_rate': 1.4265843428133502e-05, 'epoch': 10.74}

 90%|████████▉ | 25137/28080 [49:39:37<5:48:39,  7.11s/it]
 90%|████████▉ | 25138/28080 [49:39:45<5:49:47,  7.13s/it]
                                                          
{'loss': 0.5804, 'learning_rate': 1.4256243505889943e-05, 'epoch': 10.74}

 90%|████████▉ | 25138/28080 [49:39:45<5:49:47,  7.13s/it]
 90%|████████▉ | 25139/28080 [49:39:52<5:47:42,  7.09s/it]
                                                          
{'loss': 0.5827, 'learning_rate': 1.424664671997386e-05, 'epoch': 10.74}

 90%|████████▉ | 25139/28080 [49:39:52<5:47:42,  7.09s/it]
 90%|████████▉ | 25140/28080 [49:39:59<5:46:20,  7.07s/it]
                                                          
{'loss': 0.6061, 'learning_rate': 1.4237053070512873e-05, 'epoch': 10.74}

 90%|████████▉ | 25140/28080 [49:39:59<5:46:20,  7.07s/it]
 90%|████████▉ | 25141/28080 [49:40:06<5:46:35,  7.08s/it]
                                                          
{'loss': 0.5849, 'learning_rate': 1.422746255763474e-05, 'epoch': 10.74}

 90%|████████▉ | 25141/28080 [49:40:06<5:46:35,  7.08s/it]
 90%|████████▉ | 25142/28080 [49:40:13<5:48:05,  7.11s/it]
                                                          
{'loss': 0.5886, 'learning_rate': 1.4217875181466915e-05, 'epoch': 10.74}

 90%|████████▉ | 25142/28080 [49:40:13<5:48:05,  7.11s/it]
 90%|████████▉ | 25143/28080 [49:40:20<5:48:12,  7.11s/it]
                                                          
{'loss': 0.6007, 'learning_rate': 1.4208290942137104e-05, 'epoch': 10.74}

 90%|████████▉ | 25143/28080 [49:40:20<5:48:12,  7.11s/it]
 90%|████████▉ | 25144/28080 [49:40:27<5:47:48,  7.11s/it]
                                                          
{'loss': 0.6093, 'learning_rate': 1.4198709839772672e-05, 'epoch': 10.74}

 90%|████████▉ | 25144/28080 [49:40:27<5:47:48,  7.11s/it]
 90%|████████▉ | 25145/28080 [49:40:34<5:47:24,  7.10s/it]
                                                          
{'loss': 0.5982, 'learning_rate': 1.418913187450116e-05, 'epoch': 10.74}

 90%|████████▉ | 25145/28080 [49:40:34<5:47:24,  7.10s/it]
 90%|████████▉ | 25146/28080 [49:40:41<5:48:18,  7.12s/it]
                                                          
{'loss': 0.6048, 'learning_rate': 1.4179557046449936e-05, 'epoch': 10.74}

 90%|████████▉ | 25146/28080 [49:40:41<5:48:18,  7.12s/it]
 90%|████████▉ | 25147/28080 [49:40:49<5:49:02,  7.14s/it]
                                                          
{'loss': 0.6085, 'learning_rate': 1.4169985355746484e-05, 'epoch': 10.74}

 90%|████████▉ | 25147/28080 [49:40:49<5:49:02,  7.14s/it]
 90%|████████▉ | 25148/28080 [49:40:56<5:48:51,  7.14s/it]
                                                          
{'loss': 0.604, 'learning_rate': 1.4160416802518062e-05, 'epoch': 10.74}

 90%|████████▉ | 25148/28080 [49:40:56<5:48:51,  7.14s/it]
 90%|████████▉ | 25149/28080 [49:41:03<5:48:38,  7.14s/it]
                                                          
{'loss': 0.608, 'learning_rate': 1.415085138689201e-05, 'epoch': 10.74}

 90%|████████▉ | 25149/28080 [49:41:03<5:48:38,  7.14s/it]
 90%|████████▉ | 25150/28080 [49:41:10<5:47:05,  7.11s/it]
                                                          
{'loss': 0.6017, 'learning_rate': 1.4141289108995508e-05, 'epoch': 10.74}

 90%|████████▉ | 25150/28080 [49:41:10<5:47:05,  7.11s/it]
 90%|████████▉ | 25151/28080 [49:41:17<5:46:27,  7.10s/it]
                                                          
{'loss': 0.5908, 'learning_rate': 1.4131729968955898e-05, 'epoch': 10.74}

 90%|████████▉ | 25151/28080 [49:41:17<5:46:27,  7.10s/it]
 90%|████████▉ | 25152/28080 [49:41:24<5:45:49,  7.09s/it]
                                                          
{'loss': 0.5961, 'learning_rate': 1.412217396690027e-05, 'epoch': 10.74}

 90%|████████▉ | 25152/28080 [49:41:24<5:45:49,  7.09s/it]
 90%|████████▉ | 25153/28080 [49:41:31<5:46:17,  7.10s/it]
                                                          
{'loss': 0.6102, 'learning_rate': 1.4112621102955776e-05, 'epoch': 10.75}

 90%|████████▉ | 25153/28080 [49:41:31<5:46:17,  7.10s/it]
 90%|████████▉ | 25154/28080 [49:41:38<5:45:07,  7.08s/it]
                                                          
{'loss': 0.6122, 'learning_rate': 1.4103071377249477e-05, 'epoch': 10.75}

 90%|████████▉ | 25154/28080 [49:41:38<5:45:07,  7.08s/it]
 90%|████████▉ | 25155/28080 [49:41:45<5:45:28,  7.09s/it]
                                                          
{'loss': 0.5965, 'learning_rate': 1.4093524789908468e-05, 'epoch': 10.75}

 90%|████████▉ | 25155/28080 [49:41:45<5:45:28,  7.09s/it]
 90%|████████▉ | 25156/28080 [49:41:52<5:44:09,  7.06s/it]
                                                          
{'loss': 0.5983, 'learning_rate': 1.4083981341059731e-05, 'epoch': 10.75}

 90%|████████▉ | 25156/28080 [49:41:52<5:44:09,  7.06s/it]
 90%|████████▉ | 25157/28080 [49:41:59<5:44:01,  7.06s/it]
                                                          
{'loss': 0.596, 'learning_rate': 1.4074441030830304e-05, 'epoch': 10.75}

 90%|████████▉ | 25157/28080 [49:41:59<5:44:01,  7.06s/it]
 90%|████████▉ | 25158/28080 [49:42:06<5:43:00,  7.04s/it]
                                                          
{'loss': 0.626, 'learning_rate': 1.4064903859346973e-05, 'epoch': 10.75}

 90%|████████▉ | 25158/28080 [49:42:06<5:43:00,  7.04s/it]
 90%|████████▉ | 25159/28080 [49:42:13<5:43:53,  7.06s/it]
                                                          
{'loss': 0.6116, 'learning_rate': 1.4055369826736746e-05, 'epoch': 10.75}

 90%|████████▉ | 25159/28080 [49:42:13<5:43:53,  7.06s/it]
 90%|████████▉ | 25160/28080 [49:42:21<5:44:56,  7.09s/it]
                                                          
{'loss': 0.6107, 'learning_rate': 1.4045838933126387e-05, 'epoch': 10.75}

 90%|████████▉ | 25160/28080 [49:42:21<5:44:56,  7.09s/it]
 90%|████████▉ | 25161/28080 [49:42:28<5:45:36,  7.10s/it]
                                                          
{'loss': 0.6169, 'learning_rate': 1.4036311178642708e-05, 'epoch': 10.75}

 90%|████████▉ | 25161/28080 [49:42:28<5:45:36,  7.10s/it]
 90%|████████▉ | 25162/28080 [49:42:35<5:45:02,  7.09s/it]
                                                          
{'loss': 0.6306, 'learning_rate': 1.4026786563412524e-05, 'epoch': 10.75}

 90%|████████▉ | 25162/28080 [49:42:35<5:45:02,  7.09s/it]
 90%|████████▉ | 25163/28080 [49:42:42<5:44:23,  7.08s/it]
                                                          
{'loss': 0.5917, 'learning_rate': 1.401726508756246e-05, 'epoch': 10.75}

 90%|████████▉ | 25163/28080 [49:42:42<5:44:23,  7.08s/it]
 90%|████████▉ | 25164/28080 [49:42:49<5:44:36,  7.09s/it]
                                                          
{'loss': 0.5951, 'learning_rate': 1.400774675121927e-05, 'epoch': 10.75}

 90%|████████▉ | 25164/28080 [49:42:49<5:44:36,  7.09s/it]
 90%|████████▉ | 25165/28080 [49:42:56<5:45:24,  7.11s/it]
                                                          
{'loss': 0.598, 'learning_rate': 1.3998231554509495e-05, 'epoch': 10.75}

 90%|████████▉ | 25165/28080 [49:42:56<5:45:24,  7.11s/it]
 90%|████████▉ | 25166/28080 [49:43:03<5:46:07,  7.13s/it]
                                                          
{'loss': 0.5913, 'learning_rate': 1.3988719497559837e-05, 'epoch': 10.75}

 90%|████████▉ | 25166/28080 [49:43:03<5:46:07,  7.13s/it]
 90%|████████▉ | 25167/28080 [49:43:10<5:46:04,  7.13s/it]
                                                          
{'loss': 0.5961, 'learning_rate': 1.3979210580496753e-05, 'epoch': 10.75}

 90%|████████▉ | 25167/28080 [49:43:10<5:46:04,  7.13s/it]
 90%|████████▉ | 25168/28080 [49:43:17<5:45:15,  7.11s/it]
                                                          
{'loss': 0.6021, 'learning_rate': 1.3969704803446809e-05, 'epoch': 10.75}

 90%|████████▉ | 25168/28080 [49:43:17<5:45:15,  7.11s/it]
 90%|████████▉ | 25169/28080 [49:43:25<5:45:45,  7.13s/it]
                                                          
{'loss': 0.6283, 'learning_rate': 1.39602021665364e-05, 'epoch': 10.75}

 90%|████████▉ | 25169/28080 [49:43:25<5:45:45,  7.13s/it]
 90%|████████▉ | 25170/28080 [49:43:32<5:45:52,  7.13s/it]
                                                          
{'loss': 0.5992, 'learning_rate': 1.395070266989204e-05, 'epoch': 10.75}

 90%|████████▉ | 25170/28080 [49:43:32<5:45:52,  7.13s/it]
 90%|████████▉ | 25171/28080 [49:43:39<5:46:27,  7.15s/it]
                                                          
{'loss': 0.61, 'learning_rate': 1.394120631364007e-05, 'epoch': 10.75}

 90%|████████▉ | 25171/28080 [49:43:39<5:46:27,  7.15s/it]
 90%|████████▉ | 25172/28080 [49:43:46<5:47:06,  7.16s/it]
                                                          
{'loss': 0.6103, 'learning_rate': 1.3931713097906807e-05, 'epoch': 10.75}

 90%|████████▉ | 25172/28080 [49:43:46<5:47:06,  7.16s/it]
 90%|████████▉ | 25173/28080 [49:43:53<5:45:38,  7.13s/it]
                                                          
{'loss': 0.5971, 'learning_rate': 1.3922223022818508e-05, 'epoch': 10.75}

 90%|████████▉ | 25173/28080 [49:43:53<5:45:38,  7.13s/it]
 90%|████████▉ | 25174/28080 [49:44:00<5:44:14,  7.11s/it]
                                                          
{'loss': 0.6048, 'learning_rate': 1.3912736088501548e-05, 'epoch': 10.75}

 90%|████████▉ | 25174/28080 [49:44:00<5:44:14,  7.11s/it]
 90%|████████▉ | 25175/28080 [49:44:07<5:43:48,  7.10s/it]
                                                          
{'loss': 0.6071, 'learning_rate': 1.390325229508202e-05, 'epoch': 10.75}

 90%|████████▉ | 25175/28080 [49:44:07<5:43:48,  7.10s/it]
 90%|████████▉ | 25176/28080 [49:44:14<5:44:00,  7.11s/it]
                                                          
{'loss': 0.599, 'learning_rate': 1.3893771642686237e-05, 'epoch': 10.75}

 90%|████████▉ | 25176/28080 [49:44:14<5:44:00,  7.11s/it]
 90%|████████▉ | 25177/28080 [49:44:21<5:42:21,  7.08s/it]
                                                          
{'loss': 0.6326, 'learning_rate': 1.3884294131440185e-05, 'epoch': 10.76}

 90%|████████▉ | 25177/28080 [49:44:21<5:42:21,  7.08s/it]
 90%|████████▉ | 25178/28080 [49:44:29<5:42:06,  7.07s/it]
                                                          
{'loss': 0.5809, 'learning_rate': 1.3874819761470036e-05, 'epoch': 10.76}

 90%|████████▉ | 25178/28080 [49:44:29<5:42:06,  7.07s/it]
 90%|████████▉ | 25179/28080 [49:44:36<5:42:51,  7.09s/it]
                                                          
{'loss': 0.6082, 'learning_rate': 1.386534853290175e-05, 'epoch': 10.76}

 90%|████████▉ | 25179/28080 [49:44:36<5:42:51,  7.09s/it]
 90%|████████▉ | 25180/28080 [49:44:43<5:43:39,  7.11s/it]
                                                          
{'loss': 0.5964, 'learning_rate': 1.3855880445861475e-05, 'epoch': 10.76}

 90%|████████▉ | 25180/28080 [49:44:43<5:43:39,  7.11s/it]
 90%|████████▉ | 25181/28080 [49:44:50<5:41:14,  7.06s/it]
                                                          
{'loss': 0.6051, 'learning_rate': 1.384641550047508e-05, 'epoch': 10.76}

 90%|████████▉ | 25181/28080 [49:44:50<5:41:14,  7.06s/it]
 90%|████████▉ | 25182/28080 [49:44:57<5:40:18,  7.05s/it]
                                                          
{'loss': 0.6178, 'learning_rate': 1.3836953696868493e-05, 'epoch': 10.76}

 90%|████████▉ | 25182/28080 [49:44:57<5:40:18,  7.05s/it]
 90%|████████▉ | 25183/28080 [49:45:04<5:41:11,  7.07s/it]
                                                          
{'loss': 0.587, 'learning_rate': 1.3827495035167558e-05, 'epoch': 10.76}

 90%|████████▉ | 25183/28080 [49:45:04<5:41:11,  7.07s/it]
 90%|████████▉ | 25184/28080 [49:45:11<5:42:15,  7.09s/it]
                                                          
{'loss': 0.5894, 'learning_rate': 1.3818039515498204e-05, 'epoch': 10.76}

 90%|████████▉ | 25184/28080 [49:45:11<5:42:15,  7.09s/it]
 90%|████████▉ | 25185/28080 [49:45:18<5:42:31,  7.10s/it]
                                                          
{'loss': 0.5892, 'learning_rate': 1.380858713798619e-05, 'epoch': 10.76}

 90%|████████▉ | 25185/28080 [49:45:18<5:42:31,  7.10s/it]
 90%|████████▉ | 25186/28080 [49:45:25<5:44:07,  7.13s/it]
                                                          
{'loss': 0.6027, 'learning_rate': 1.3799137902757247e-05, 'epoch': 10.76}

 90%|████████▉ | 25186/28080 [49:45:25<5:44:07,  7.13s/it]
 90%|████████▉ | 25187/28080 [49:45:32<5:43:43,  7.13s/it]
                                                          
{'loss': 0.6133, 'learning_rate': 1.3789691809937083e-05, 'epoch': 10.76}

 90%|████████▉ | 25187/28080 [49:45:32<5:43:43,  7.13s/it]
 90%|████████▉ | 25188/28080 [49:45:40<5:43:44,  7.13s/it]
                                                          
{'loss': 0.6033, 'learning_rate': 1.3780248859651374e-05, 'epoch': 10.76}

 90%|████████▉ | 25188/28080 [49:45:40<5:43:44,  7.13s/it]
 90%|████████▉ | 25189/28080 [49:45:47<5:42:32,  7.11s/it]
                                                          
{'loss': 0.6225, 'learning_rate': 1.3770809052025795e-05, 'epoch': 10.76}

 90%|████████▉ | 25189/28080 [49:45:47<5:42:32,  7.11s/it]
 90%|████████▉ | 25190/28080 [49:45:54<5:42:37,  7.11s/it]
                                                          
{'loss': 0.6192, 'learning_rate': 1.376137238718586e-05, 'epoch': 10.76}

 90%|████████▉ | 25190/28080 [49:45:54<5:42:37,  7.11s/it]
 90%|████████▉ | 25191/28080 [49:46:01<5:42:03,  7.10s/it]
                                                          
{'loss': 0.6122, 'learning_rate': 1.3751938865257219e-05, 'epoch': 10.76}

 90%|████████▉ | 25191/28080 [49:46:01<5:42:03,  7.10s/it]
 90%|████████▉ | 25192/28080 [49:46:08<5:40:53,  7.08s/it]
                                                          
{'loss': 0.6036, 'learning_rate': 1.3742508486365213e-05, 'epoch': 10.76}

 90%|████████▉ | 25192/28080 [49:46:08<5:40:53,  7.08s/it]
 90%|████████▉ | 25193/28080 [49:46:15<5:41:27,  7.10s/it]
                                                          
{'loss': 0.6108, 'learning_rate': 1.3733081250635466e-05, 'epoch': 10.76}

 90%|████████▉ | 25193/28080 [49:46:15<5:41:27,  7.10s/it]
 90%|████████▉ | 25194/28080 [49:46:22<5:41:10,  7.09s/it]
                                                          
{'loss': 0.589, 'learning_rate': 1.3723657158193292e-05, 'epoch': 10.76}

 90%|████████▉ | 25194/28080 [49:46:22<5:41:10,  7.09s/it]
 90%|████████▉ | 25195/28080 [49:46:29<5:41:33,  7.10s/it]
                                                          
{'loss': 0.59, 'learning_rate': 1.3714236209164122e-05, 'epoch': 10.76}

 90%|████████▉ | 25195/28080 [49:46:29<5:41:33,  7.10s/it]
 90%|████████▉ | 25196/28080 [49:46:36<5:41:47,  7.11s/it]
                                                          
{'loss': 0.5919, 'learning_rate': 1.3704818403673298e-05, 'epoch': 10.76}

 90%|████████▉ | 25196/28080 [49:46:36<5:41:47,  7.11s/it]
 90%|████████▉ | 25197/28080 [49:46:43<5:41:12,  7.10s/it]
                                                          
{'loss': 0.594, 'learning_rate': 1.369540374184608e-05, 'epoch': 10.76}

 90%|████████▉ | 25197/28080 [49:46:43<5:41:12,  7.10s/it]
 90%|████████▉ | 25198/28080 [49:46:51<5:41:45,  7.11s/it]
                                                          
{'loss': 0.5836, 'learning_rate': 1.3685992223807703e-05, 'epoch': 10.76}

 90%|████████▉ | 25198/28080 [49:46:51<5:41:45,  7.11s/it]
 90%|████████▉ | 25199/28080 [49:46:58<5:41:36,  7.11s/it]
                                                          
{'loss': 0.592, 'learning_rate': 1.3676583849683427e-05, 'epoch': 10.76}

 90%|████████▉ | 25199/28080 [49:46:58<5:41:36,  7.11s/it]
 90%|████████▉ | 25200/28080 [49:47:05<5:41:42,  7.12s/it]
                                                          
{'loss': 0.5875, 'learning_rate': 1.3667178619598431e-05, 'epoch': 10.77}

 90%|████████▉ | 25200/28080 [49:47:05<5:41:42,  7.12s/it]
 90%|████████▉ | 25201/28080 [49:47:12<5:39:35,  7.08s/it]
                                                          
{'loss': 0.5979, 'learning_rate': 1.365777653367778e-05, 'epoch': 10.77}

 90%|████████▉ | 25201/28080 [49:47:12<5:39:35,  7.08s/it]
 90%|████████▉ | 25202/28080 [49:47:19<5:38:39,  7.06s/it]
                                                          
{'loss': 0.6058, 'learning_rate': 1.3648377592046569e-05, 'epoch': 10.77}

 90%|████████▉ | 25202/28080 [49:47:19<5:38:39,  7.06s/it]
 90%|████████▉ | 25203/28080 [49:47:26<5:40:26,  7.10s/it]
                                                          
{'loss': 0.6036, 'learning_rate': 1.363898179482992e-05, 'epoch': 10.77}

 90%|████████▉ | 25203/28080 [49:47:26<5:40:26,  7.10s/it]
 90%|████████▉ | 25204/28080 [49:47:33<5:41:13,  7.12s/it]
                                                          
{'loss': 0.6007, 'learning_rate': 1.3629589142152732e-05, 'epoch': 10.77}

 90%|████████▉ | 25204/28080 [49:47:33<5:41:13,  7.12s/it]
 90%|████████▉ | 25205/28080 [49:47:40<5:42:08,  7.14s/it]
                                                          
{'loss': 0.5729, 'learning_rate': 1.3620199634140074e-05, 'epoch': 10.77}

 90%|████████▉ | 25205/28080 [49:47:40<5:42:08,  7.14s/it]
 90%|████████▉ | 25206/28080 [49:47:47<5:39:40,  7.09s/it]
                                                          
{'loss': 0.5993, 'learning_rate': 1.3610813270916733e-05, 'epoch': 10.77}

 90%|████████▉ | 25206/28080 [49:47:47<5:39:40,  7.09s/it]
 90%|████████▉ | 25207/28080 [49:47:54<5:38:33,  7.07s/it]
                                                          
{'loss': 0.6296, 'learning_rate': 1.3601430052607667e-05, 'epoch': 10.77}

 90%|████████▉ | 25207/28080 [49:47:54<5:38:33,  7.07s/it]
 90%|████████▉ | 25208/28080 [49:48:02<5:40:59,  7.12s/it]
                                                          
{'loss': 0.5868, 'learning_rate': 1.359204997933769e-05, 'epoch': 10.77}

 90%|████████▉ | 25208/28080 [49:48:02<5:40:59,  7.12s/it]
 90%|████████▉ | 25209/28080 [49:48:09<5:39:48,  7.10s/it]
                                                          
{'loss': 0.6239, 'learning_rate': 1.358267305123162e-05, 'epoch': 10.77}

 90%|████████▉ | 25209/28080 [49:48:09<5:39:48,  7.10s/it]
 90%|████████▉ | 25210/28080 [49:48:16<5:41:28,  7.14s/it]
                                                          
{'loss': 0.6018, 'learning_rate': 1.3573299268414219e-05, 'epoch': 10.77}

 90%|████████▉ | 25210/28080 [49:48:16<5:41:28,  7.14s/it]
 90%|████████▉ | 25211/28080 [49:48:23<5:40:45,  7.13s/it]
                                                          
{'loss': 0.5959, 'learning_rate': 1.3563928631010109e-05, 'epoch': 10.77}

 90%|████████▉ | 25211/28080 [49:48:23<5:40:45,  7.13s/it]
 90%|████████▉ | 25212/28080 [49:48:30<5:41:16,  7.14s/it]
                                                          
{'loss': 0.5669, 'learning_rate': 1.3554561139144051e-05, 'epoch': 10.77}

 90%|████████▉ | 25212/28080 [49:48:30<5:41:16,  7.14s/it]
 90%|████████▉ | 25213/28080 [49:48:37<5:40:21,  7.12s/it]
                                                          
{'loss': 0.6172, 'learning_rate': 1.3545196792940557e-05, 'epoch': 10.77}

 90%|████████▉ | 25213/28080 [49:48:37<5:40:21,  7.12s/it]
 90%|████████▉ | 25214/28080 [49:48:44<5:41:10,  7.14s/it]
                                                          
{'loss': 0.605, 'learning_rate': 1.3535835592524359e-05, 'epoch': 10.77}

 90%|████████▉ | 25214/28080 [49:48:44<5:41:10,  7.14s/it]
 90%|████████▉ | 25215/28080 [49:48:51<5:39:18,  7.11s/it]
                                                          
{'loss': 0.6087, 'learning_rate': 1.3526477538019887e-05, 'epoch': 10.77}

 90%|████████▉ | 25215/28080 [49:48:51<5:39:18,  7.11s/it]
 90%|████████▉ | 25216/28080 [49:48:59<5:39:09,  7.11s/it]
                                                          
{'loss': 0.6118, 'learning_rate': 1.3517122629551709e-05, 'epoch': 10.77}

 90%|████████▉ | 25216/28080 [49:48:59<5:39:09,  7.11s/it]
 90%|████████▉ | 25217/28080 [49:49:06<5:40:18,  7.13s/it]
                                                          
{'loss': 0.5897, 'learning_rate': 1.3507770867244196e-05, 'epoch': 10.77}

 90%|████████▉ | 25217/28080 [49:49:06<5:40:18,  7.13s/it]
 90%|████████▉ | 25218/28080 [49:49:13<5:39:56,  7.13s/it]
                                                          
{'loss': 0.6008, 'learning_rate': 1.3498422251221859e-05, 'epoch': 10.77}

 90%|████████▉ | 25218/28080 [49:49:13<5:39:56,  7.13s/it]
 90%|████████▉ | 25219/28080 [49:49:20<5:42:16,  7.18s/it]
                                                          
{'loss': 0.6134, 'learning_rate': 1.3489076781609017e-05, 'epoch': 10.77}

 90%|████████▉ | 25219/28080 [49:49:20<5:42:16,  7.18s/it]
 90%|████████▉ | 25220/28080 [49:49:28<5:44:11,  7.22s/it]
                                                          
{'loss': 0.5933, 'learning_rate': 1.3479734458530012e-05, 'epoch': 10.77}

 90%|████████▉ | 25220/28080 [49:49:28<5:44:11,  7.22s/it]
 90%|████████▉ | 25221/28080 [49:49:35<5:44:16,  7.23s/it]
                                                          
{'loss': 0.6155, 'learning_rate': 1.347039528210911e-05, 'epoch': 10.77}

 90%|████████▉ | 25221/28080 [49:49:35<5:44:16,  7.23s/it]
 90%|████████▉ | 25222/28080 [49:49:42<5:44:44,  7.24s/it]
                                                          
{'loss': 0.581, 'learning_rate': 1.3461059252470625e-05, 'epoch': 10.77}

 90%|████████▉ | 25222/28080 [49:49:42<5:44:44,  7.24s/it]
 90%|████████▉ | 25223/28080 [49:49:49<5:43:41,  7.22s/it]
                                                          
{'loss': 0.5846, 'learning_rate': 1.3451726369738682e-05, 'epoch': 10.78}

 90%|████████▉ | 25223/28080 [49:49:49<5:43:41,  7.22s/it]
 90%|████████▉ | 25224/28080 [49:49:56<5:41:28,  7.17s/it]
                                                          
{'loss': 0.6104, 'learning_rate': 1.344239663403754e-05, 'epoch': 10.78}

 90%|████████▉ | 25224/28080 [49:49:56<5:41:28,  7.17s/it]
 90%|████████▉ | 25225/28080 [49:50:03<5:41:08,  7.17s/it]
                                                          
{'loss': 0.5962, 'learning_rate': 1.3433070045491214e-05, 'epoch': 10.78}

 90%|████████▉ | 25225/28080 [49:50:03<5:41:08,  7.17s/it]
 90%|████████▉ | 25226/28080 [49:50:11<5:40:57,  7.17s/it]
                                                          
{'loss': 0.5892, 'learning_rate': 1.342374660422388e-05, 'epoch': 10.78}

 90%|████████▉ | 25226/28080 [49:50:11<5:40:57,  7.17s/it]
 90%|████████▉ | 25227/28080 [49:50:18<5:38:49,  7.13s/it]
                                                          
{'loss': 0.6072, 'learning_rate': 1.3414426310359495e-05, 'epoch': 10.78}

 90%|████████▉ | 25227/28080 [49:50:18<5:38:49,  7.13s/it]
 90%|████████▉ | 25228/28080 [49:50:25<5:39:00,  7.13s/it]
                                                          
{'loss': 0.5859, 'learning_rate': 1.3405109164022127e-05, 'epoch': 10.78}

 90%|████████▉ | 25228/28080 [49:50:25<5:39:00,  7.13s/it]
 90%|████████▉ | 25229/28080 [49:50:32<5:38:34,  7.13s/it]
                                                          
{'loss': 0.588, 'learning_rate': 1.3395795165335706e-05, 'epoch': 10.78}

 90%|████████▉ | 25229/28080 [49:50:32<5:38:34,  7.13s/it]
 90%|████████▉ | 25230/28080 [49:50:39<5:38:07,  7.12s/it]
                                                          
{'loss': 0.5908, 'learning_rate': 1.338648431442413e-05, 'epoch': 10.78}

 90%|████████▉ | 25230/28080 [49:50:39<5:38:07,  7.12s/it]
 90%|████████▉ | 25231/28080 [49:50:46<5:36:10,  7.08s/it]
                                                          
{'loss': 0.6023, 'learning_rate': 1.3377176611411245e-05, 'epoch': 10.78}

 90%|████████▉ | 25231/28080 [49:50:46<5:36:10,  7.08s/it]
 90%|████████▉ | 25232/28080 [49:50:53<5:36:37,  7.09s/it]
                                                          
{'loss': 0.5909, 'learning_rate': 1.3367872056420954e-05, 'epoch': 10.78}

 90%|████████▉ | 25232/28080 [49:50:53<5:36:37,  7.09s/it]
 90%|████████▉ | 25233/28080 [49:51:00<5:36:21,  7.09s/it]
                                                          
{'loss': 0.6076, 'learning_rate': 1.3358570649577018e-05, 'epoch': 10.78}

 90%|████████▉ | 25233/28080 [49:51:00<5:36:21,  7.09s/it]
 90%|████████▉ | 25234/28080 [49:51:07<5:36:40,  7.10s/it]
                                                          
{'loss': 0.5982, 'learning_rate': 1.3349272391003142e-05, 'epoch': 10.78}

 90%|████████▉ | 25234/28080 [49:51:07<5:36:40,  7.10s/it]
 90%|████████▉ | 25235/28080 [49:51:14<5:37:31,  7.12s/it]
                                                          
{'loss': 0.624, 'learning_rate': 1.333997728082309e-05, 'epoch': 10.78}

 90%|████████▉ | 25235/28080 [49:51:14<5:37:31,  7.12s/it]
 90%|████████▉ | 25236/28080 [49:51:22<5:40:19,  7.18s/it]
                                                          
{'loss': 0.6064, 'learning_rate': 1.3330685319160429e-05, 'epoch': 10.78}

 90%|████████▉ | 25236/28080 [49:51:22<5:40:19,  7.18s/it]
 90%|████████▉ | 25237/28080 [49:51:29<5:38:11,  7.14s/it]
                                                          
{'loss': 0.6363, 'learning_rate': 1.3321396506138895e-05, 'epoch': 10.78}

 90%|████████▉ | 25237/28080 [49:51:29<5:38:11,  7.14s/it]
 90%|████████▉ | 25238/28080 [49:51:36<5:38:44,  7.15s/it]
                                                          
{'loss': 0.6057, 'learning_rate': 1.3312110841881997e-05, 'epoch': 10.78}

 90%|████████▉ | 25238/28080 [49:51:36<5:38:44,  7.15s/it]
 90%|████████▉ | 25239/28080 [49:51:43<5:38:06,  7.14s/it]
                                                          
{'loss': 0.5917, 'learning_rate': 1.3302828326513306e-05, 'epoch': 10.78}

 90%|████████▉ | 25239/28080 [49:51:43<5:38:06,  7.14s/it]
 90%|████████▉ | 25240/28080 [49:51:50<5:39:04,  7.16s/it]
                                                          
{'loss': 0.6117, 'learning_rate': 1.329354896015625e-05, 'epoch': 10.78}

 90%|████████▉ | 25240/28080 [49:51:50<5:39:04,  7.16s/it]
 90%|████████▉ | 25241/28080 [49:51:57<5:36:36,  7.11s/it]
                                                          
{'loss': 0.5956, 'learning_rate': 1.3284272742934368e-05, 'epoch': 10.78}

 90%|████████▉ | 25241/28080 [49:51:57<5:36:36,  7.11s/it]
 90%|████████▉ | 25242/28080 [49:52:05<5:37:30,  7.14s/it]
                                                          
{'loss': 0.5976, 'learning_rate': 1.3274999674971006e-05, 'epoch': 10.78}

 90%|████████▉ | 25242/28080 [49:52:05<5:37:30,  7.14s/it]
 90%|████████▉ | 25243/28080 [49:52:12<5:36:40,  7.12s/it]
                                                          
{'loss': 0.6197, 'learning_rate': 1.3265729756389566e-05, 'epoch': 10.78}

 90%|████████▉ | 25243/28080 [49:52:12<5:36:40,  7.12s/it]
 90%|████████▉ | 25244/28080 [49:52:19<5:35:24,  7.10s/it]
                                                          
{'loss': 0.6045, 'learning_rate': 1.3256462987313394e-05, 'epoch': 10.78}

 90%|████████▉ | 25244/28080 [49:52:19<5:35:24,  7.10s/it]
 90%|████████▉ | 25245/28080 [49:52:26<5:34:40,  7.08s/it]
                                                          
{'loss': 0.5894, 'learning_rate': 1.3247199367865726e-05, 'epoch': 10.78}

 90%|████████▉ | 25245/28080 [49:52:26<5:34:40,  7.08s/it]
 90%|████████▉ | 25246/28080 [49:52:33<5:34:57,  7.09s/it]
                                                          
{'loss': 0.6252, 'learning_rate': 1.3237938898169793e-05, 'epoch': 10.78}

 90%|████████▉ | 25246/28080 [49:52:33<5:34:57,  7.09s/it]
 90%|████████▉ | 25247/28080 [49:52:40<5:33:50,  7.07s/it]
                                                          
{'loss': 0.6145, 'learning_rate': 1.322868157834889e-05, 'epoch': 10.79}

 90%|████████▉ | 25247/28080 [49:52:40<5:33:50,  7.07s/it]
 90%|████████▉ | 25248/28080 [49:52:47<5:34:47,  7.09s/it]
                                                          
{'loss': 0.5893, 'learning_rate': 1.321942740852608e-05, 'epoch': 10.79}

 90%|████████▉ | 25248/28080 [49:52:47<5:34:47,  7.09s/it]
 90%|████████▉ | 25249/28080 [49:52:54<5:33:33,  7.07s/it]
                                                          
{'loss': 0.6152, 'learning_rate': 1.3210176388824546e-05, 'epoch': 10.79}

 90%|████████▉ | 25249/28080 [49:52:54<5:33:33,  7.07s/it]
 90%|████████▉ | 25250/28080 [49:53:01<5:33:50,  7.08s/it]
                                                          
{'loss': 0.6152, 'learning_rate': 1.3200928519367272e-05, 'epoch': 10.79}

 90%|████████▉ | 25250/28080 [49:53:01<5:33:50,  7.08s/it]
 90%|████████▉ | 25251/28080 [49:53:08<5:34:09,  7.09s/it]
                                                          
{'loss': 0.5871, 'learning_rate': 1.319168380027741e-05, 'epoch': 10.79}

 90%|████████▉ | 25251/28080 [49:53:08<5:34:09,  7.09s/it]
 90%|████████▉ | 25252/28080 [49:53:15<5:34:53,  7.11s/it]
                                                          
{'loss': 0.6189, 'learning_rate': 1.3182442231677832e-05, 'epoch': 10.79}

 90%|████████▉ | 25252/28080 [49:53:15<5:34:53,  7.11s/it]
 90%|████████▉ | 25253/28080 [49:53:22<5:32:47,  7.06s/it]
                                                          
{'loss': 0.5818, 'learning_rate': 1.3173203813691636e-05, 'epoch': 10.79}

 90%|████████▉ | 25253/28080 [49:53:22<5:32:47,  7.06s/it]
 90%|████████▉ | 25254/28080 [49:53:29<5:33:27,  7.08s/it]
                                                          
{'loss': 0.5869, 'learning_rate': 1.3163968546441556e-05, 'epoch': 10.79}

 90%|████████▉ | 25254/28080 [49:53:29<5:33:27,  7.08s/it]
 90%|████████▉ | 25255/28080 [49:53:37<5:34:55,  7.11s/it]
                                                          
{'loss': 0.5756, 'learning_rate': 1.3154736430050608e-05, 'epoch': 10.79}

 90%|████████▉ | 25255/28080 [49:53:37<5:34:55,  7.11s/it]
 90%|████████▉ | 25256/28080 [49:53:44<5:36:50,  7.16s/it]
                                                          
{'loss': 0.5812, 'learning_rate': 1.3145507464641493e-05, 'epoch': 10.79}

 90%|████████▉ | 25256/28080 [49:53:44<5:36:50,  7.16s/it]
 90%|████████▉ | 25257/28080 [49:53:51<5:35:49,  7.14s/it]
                                                          
{'loss': 0.6112, 'learning_rate': 1.3136281650337117e-05, 'epoch': 10.79}

 90%|████████▉ | 25257/28080 [49:53:51<5:35:49,  7.14s/it]
 90%|████████▉ | 25258/28080 [49:53:58<5:35:02,  7.12s/it]
                                                          
{'loss': 0.6206, 'learning_rate': 1.3127058987260133e-05, 'epoch': 10.79}

 90%|████████▉ | 25258/28080 [49:53:58<5:35:02,  7.12s/it]
 90%|████████▉ | 25259/28080 [49:54:05<5:35:48,  7.14s/it]
                                                          
{'loss': 0.5805, 'learning_rate': 1.3117839475533245e-05, 'epoch': 10.79}

 90%|████████▉ | 25259/28080 [49:54:05<5:35:48,  7.14s/it]
 90%|████████▉ | 25260/28080 [49:54:12<5:35:28,  7.14s/it]
                                                          
{'loss': 0.613, 'learning_rate': 1.3108623115279161e-05, 'epoch': 10.79}

 90%|████████▉ | 25260/28080 [49:54:12<5:35:28,  7.14s/it]
 90%|████████▉ | 25261/28080 [49:54:19<5:34:34,  7.12s/it]
                                                          
{'loss': 0.6249, 'learning_rate': 1.3099409906620397e-05, 'epoch': 10.79}

 90%|████████▉ | 25261/28080 [49:54:19<5:34:34,  7.12s/it]
 90%|████████▉ | 25262/28080 [49:54:27<5:34:02,  7.11s/it]
                                                          
{'loss': 0.5992, 'learning_rate': 1.309019984967963e-05, 'epoch': 10.79}

 90%|████████▉ | 25262/28080 [49:54:27<5:34:02,  7.11s/it]
 90%|████████▉ | 25263/28080 [49:54:34<5:33:13,  7.10s/it]
                                                          
{'loss': 0.6016, 'learning_rate': 1.3080992944579346e-05, 'epoch': 10.79}

 90%|████████▉ | 25263/28080 [49:54:34<5:33:13,  7.10s/it]
 90%|████████▉ | 25264/28080 [49:54:41<5:33:28,  7.11s/it]
                                                          
{'loss': 0.593, 'learning_rate': 1.307178919144203e-05, 'epoch': 10.79}

 90%|████████▉ | 25264/28080 [49:54:41<5:33:28,  7.11s/it]
 90%|████████▉ | 25265/28080 [49:54:48<5:33:00,  7.10s/it]
                                                          
{'loss': 0.6055, 'learning_rate': 1.3062588590390112e-05, 'epoch': 10.79}

 90%|████████▉ | 25265/28080 [49:54:48<5:33:00,  7.10s/it]
 90%|████████▉ | 25266/28080 [49:54:55<5:33:57,  7.12s/it]
                                                          
{'loss': 0.599, 'learning_rate': 1.3053391141546051e-05, 'epoch': 10.79}

 90%|████████▉ | 25266/28080 [49:54:55<5:33:57,  7.12s/it]
 90%|████████▉ | 25267/28080 [49:55:02<5:33:05,  7.10s/it]
                                                          
{'loss': 0.5868, 'learning_rate': 1.3044196845032164e-05, 'epoch': 10.79}

 90%|████████▉ | 25267/28080 [49:55:02<5:33:05,  7.10s/it]
 90%|████████▉ | 25268/28080 [49:55:09<5:33:10,  7.11s/it]
                                                          
{'loss': 0.6068, 'learning_rate': 1.3035005700970798e-05, 'epoch': 10.79}

 90%|████████▉ | 25268/28080 [49:55:09<5:33:10,  7.11s/it]
 90%|████████▉ | 25269/28080 [49:55:16<5:33:45,  7.12s/it]
                                                          
{'loss': 0.5994, 'learning_rate': 1.3025817709484188e-05, 'epoch': 10.79}

 90%|████████▉ | 25269/28080 [49:55:16<5:33:45,  7.12s/it]
 90%|████████▉ | 25270/28080 [49:55:23<5:32:19,  7.10s/it]
                                                          
{'loss': 0.6031, 'learning_rate': 1.3016632870694627e-05, 'epoch': 10.8}

 90%|████████▉ | 25270/28080 [49:55:23<5:32:19,  7.10s/it]
 90%|████████▉ | 25271/28080 [49:55:30<5:31:39,  7.08s/it]
                                                          
{'loss': 0.6129, 'learning_rate': 1.300745118472424e-05, 'epoch': 10.8}

 90%|████████▉ | 25271/28080 [49:55:30<5:31:39,  7.08s/it]
 90%|█████████ | 25272/28080 [49:55:38<5:32:45,  7.11s/it]
                                                          
{'loss': 0.5853, 'learning_rate': 1.2998272651695314e-05, 'epoch': 10.8}

 90%|█████████ | 25272/28080 [49:55:38<5:32:45,  7.11s/it]
 90%|█████████ | 25273/28080 [49:55:45<5:31:43,  7.09s/it]
                                                          
{'loss': 0.602, 'learning_rate': 1.2989097271729783e-05, 'epoch': 10.8}

 90%|█████████ | 25273/28080 [49:55:45<5:31:43,  7.09s/it]
 90%|█████████ | 25274/28080 [49:55:52<5:30:56,  7.08s/it]
                                                          
{'loss': 0.6202, 'learning_rate': 1.2979925044949825e-05, 'epoch': 10.8}

 90%|█████████ | 25274/28080 [49:55:52<5:30:56,  7.08s/it]
 90%|█████████ | 25275/28080 [49:55:59<5:29:52,  7.06s/it]
                                                          
{'loss': 0.587, 'learning_rate': 1.2970755971477427e-05, 'epoch': 10.8}

 90%|█████████ | 25275/28080 [49:55:59<5:29:52,  7.06s/it]
 90%|█████████ | 25276/28080 [49:56:06<5:30:26,  7.07s/it]
                                                          
{'loss': 0.6131, 'learning_rate': 1.296159005143463e-05, 'epoch': 10.8}

 90%|█████████ | 25276/28080 [49:56:06<5:30:26,  7.07s/it]
 90%|█████████ | 25277/28080 [49:56:13<5:29:21,  7.05s/it]
                                                          
{'loss': 0.5888, 'learning_rate': 1.2952427284943336e-05, 'epoch': 10.8}

 90%|█████████ | 25277/28080 [49:56:13<5:29:21,  7.05s/it]
 90%|█████████ | 25278/28080 [49:56:20<5:28:54,  7.04s/it]
                                                          
{'loss': 0.6118, 'learning_rate': 1.2943267672125448e-05, 'epoch': 10.8}

 90%|█████████ | 25278/28080 [49:56:20<5:28:54,  7.04s/it]
 90%|█████████ | 25279/28080 [49:56:27<5:29:43,  7.06s/it]
                                                          
{'loss': 0.5832, 'learning_rate': 1.2934111213102784e-05, 'epoch': 10.8}

 90%|█████████ | 25279/28080 [49:56:27<5:29:43,  7.06s/it]
 90%|█████████ | 25280/28080 [49:56:34<5:30:30,  7.08s/it]
                                                          
{'loss': 0.5938, 'learning_rate': 1.2924957907997247e-05, 'epoch': 10.8}

 90%|█████████ | 25280/28080 [49:56:34<5:30:30,  7.08s/it]
 90%|█████████ | 25281/28080 [49:56:41<5:33:56,  7.16s/it]
                                                          
{'loss': 0.5919, 'learning_rate': 1.2915807756930548e-05, 'epoch': 10.8}

 90%|█████████ | 25281/28080 [49:56:41<5:33:56,  7.16s/it]
 90%|█████████ | 25282/28080 [49:56:48<5:32:59,  7.14s/it]
                                                          
{'loss': 0.6224, 'learning_rate': 1.2906660760024475e-05, 'epoch': 10.8}

 90%|█████████ | 25282/28080 [49:56:48<5:32:59,  7.14s/it]
 90%|█████████ | 25283/28080 [49:56:56<5:32:27,  7.13s/it]
                                                          
{'loss': 0.5864, 'learning_rate': 1.2897516917400626e-05, 'epoch': 10.8}

 90%|█████████ | 25283/28080 [49:56:56<5:32:27,  7.13s/it]
 90%|█████████ | 25284/28080 [49:57:03<5:32:27,  7.13s/it]
                                                          
{'loss': 0.5695, 'learning_rate': 1.2888376229180737e-05, 'epoch': 10.8}

 90%|█████████ | 25284/28080 [49:57:03<5:32:27,  7.13s/it]
 90%|█████████ | 25285/28080 [49:57:10<5:31:09,  7.11s/it]
                                                          
{'loss': 0.5876, 'learning_rate': 1.2879238695486406e-05, 'epoch': 10.8}

 90%|█████████ | 25285/28080 [49:57:10<5:31:09,  7.11s/it]
 90%|█████████ | 25286/28080 [49:57:17<5:29:41,  7.08s/it]
                                                          
{'loss': 0.6039, 'learning_rate': 1.2870104316439175e-05, 'epoch': 10.8}

 90%|█████████ | 25286/28080 [49:57:17<5:29:41,  7.08s/it]
 90%|█████████ | 25287/28080 [49:57:24<5:30:53,  7.11s/it]
                                                          
{'loss': 0.5773, 'learning_rate': 1.2860973092160583e-05, 'epoch': 10.8}

 90%|█████████ | 25287/28080 [49:57:24<5:30:53,  7.11s/it]
 90%|█████████ | 25288/28080 [49:57:31<5:31:22,  7.12s/it]
                                                          
{'loss': 0.5849, 'learning_rate': 1.2851845022772063e-05, 'epoch': 10.8}

 90%|█████████ | 25288/28080 [49:57:31<5:31:22,  7.12s/it]
 90%|█████████ | 25289/28080 [49:57:38<5:30:56,  7.11s/it]
                                                          
{'loss': 0.5962, 'learning_rate': 1.28427201083951e-05, 'epoch': 10.8}

 90%|█████████ | 25289/28080 [49:57:38<5:30:56,  7.11s/it]
 90%|█████████ | 25290/28080 [49:57:45<5:31:02,  7.12s/it]
                                                          
{'loss': 0.6065, 'learning_rate': 1.2833598349151072e-05, 'epoch': 10.8}

 90%|█████████ | 25290/28080 [49:57:45<5:31:02,  7.12s/it]
 90%|█████████ | 25291/28080 [49:57:52<5:31:04,  7.12s/it]
                                                          
{'loss': 0.5893, 'learning_rate': 1.2824479745161377e-05, 'epoch': 10.8}

 90%|█████████ | 25291/28080 [49:57:52<5:31:04,  7.12s/it]
 90%|█████████ | 25292/28080 [49:58:00<5:30:29,  7.11s/it]
                                                          
{'loss': 0.609, 'learning_rate': 1.281536429654731e-05, 'epoch': 10.8}

 90%|█████████ | 25292/28080 [49:58:00<5:30:29,  7.11s/it]
 90%|█████████ | 25293/28080 [49:58:07<5:30:17,  7.11s/it]
                                                          
{'loss': 0.5923, 'learning_rate': 1.2806252003430136e-05, 'epoch': 10.8}

 90%|█████████ | 25293/28080 [49:58:07<5:30:17,  7.11s/it]
 90%|█████████ | 25294/28080 [49:58:14<5:30:07,  7.11s/it]
                                                          
{'loss': 0.6041, 'learning_rate': 1.2797142865931006e-05, 'epoch': 10.81}

 90%|█████████ | 25294/28080 [49:58:14<5:30:07,  7.11s/it]
 90%|█████████ | 25295/28080 [49:58:21<5:30:35,  7.12s/it]
                                                          
{'loss': 0.5898, 'learning_rate': 1.2788036884171266e-05, 'epoch': 10.81}

 90%|█████████ | 25295/28080 [49:58:21<5:30:35,  7.12s/it]
 90%|█████████ | 25296/28080 [49:58:28<5:31:00,  7.13s/it]
                                                          
{'loss': 0.5975, 'learning_rate': 1.2778934058271935e-05, 'epoch': 10.81}

 90%|█████████ | 25296/28080 [49:58:28<5:31:00,  7.13s/it]
 90%|█████████ | 25297/28080 [49:58:35<5:31:07,  7.14s/it]
                                                          
{'loss': 0.5974, 'learning_rate': 1.276983438835419e-05, 'epoch': 10.81}

 90%|█████████ | 25297/28080 [49:58:35<5:31:07,  7.14s/it]
 90%|█████████ | 25298/28080 [49:58:42<5:31:25,  7.15s/it]
                                                          
{'loss': 0.607, 'learning_rate': 1.2760737874539018e-05, 'epoch': 10.81}

 90%|█████████ | 25298/28080 [49:58:42<5:31:25,  7.15s/it]
 90%|█████████ | 25299/28080 [49:58:50<5:30:55,  7.14s/it]
                                                          
{'loss': 0.5856, 'learning_rate': 1.2751644516947491e-05, 'epoch': 10.81}

 90%|█████████ | 25299/28080 [49:58:50<5:30:55,  7.14s/it]
 90%|█████████ | 25300/28080 [49:58:57<5:30:53,  7.14s/it]
                                                          
{'loss': 0.6091, 'learning_rate': 1.2742554315700623e-05, 'epoch': 10.81}

 90%|█████████ | 25300/28080 [49:58:57<5:30:53,  7.14s/it]
 90%|█████████ | 25301/28080 [49:59:04<5:29:16,  7.11s/it]
                                                          
{'loss': 0.6056, 'learning_rate': 1.2733467270919286e-05, 'epoch': 10.81}

 90%|█████████ | 25301/28080 [49:59:04<5:29:16,  7.11s/it]
 90%|█████████ | 25302/28080 [49:59:11<5:28:55,  7.10s/it]
                                                          
{'loss': 0.6057, 'learning_rate': 1.272438338272433e-05, 'epoch': 10.81}

 90%|█████████ | 25302/28080 [49:59:11<5:28:55,  7.10s/it]
 90%|█████████ | 25303/28080 [49:59:18<5:30:01,  7.13s/it]
                                                          
{'loss': 0.5772, 'learning_rate': 1.2715302651236744e-05, 'epoch': 10.81}

 90%|█████████ | 25303/28080 [49:59:18<5:30:01,  7.13s/it]
 90%|█████████ | 25304/28080 [49:59:25<5:28:58,  7.11s/it]
                                                          
{'loss': 0.6108, 'learning_rate': 1.2706225076577205e-05, 'epoch': 10.81}

 90%|█████████ | 25304/28080 [49:59:25<5:28:58,  7.11s/it]
 90%|█████████ | 25305/28080 [49:59:32<5:28:23,  7.10s/it]
                                                          
{'loss': 0.6311, 'learning_rate': 1.2697150658866591e-05, 'epoch': 10.81}

 90%|█████████ | 25305/28080 [49:59:32<5:28:23,  7.10s/it]
 90%|█████████ | 25306/28080 [49:59:39<5:28:47,  7.11s/it]
                                                          
{'loss': 0.595, 'learning_rate': 1.2688079398225554e-05, 'epoch': 10.81}

 90%|█████████ | 25306/28080 [49:59:39<5:28:47,  7.11s/it]
 90%|█████████ | 25307/28080 [49:59:46<5:28:09,  7.10s/it]
                                                          
{'loss': 0.6081, 'learning_rate': 1.2679011294774833e-05, 'epoch': 10.81}

 90%|█████████ | 25307/28080 [49:59:46<5:28:09,  7.10s/it]
 90%|█████████ | 25308/28080 [49:59:53<5:28:24,  7.11s/it]
                                                          
{'loss': 0.5952, 'learning_rate': 1.266994634863497e-05, 'epoch': 10.81}

 90%|█████████ | 25308/28080 [49:59:53<5:28:24,  7.11s/it]
 90%|█████████ | 25309/28080 [50:00:01<5:28:22,  7.11s/it]
                                                          
{'loss': 0.5823, 'learning_rate': 1.2660884559926672e-05, 'epoch': 10.81}

 90%|█████████ | 25309/28080 [50:00:01<5:28:22,  7.11s/it]
 90%|█████████ | 25310/28080 [50:00:08<5:29:10,  7.13s/it]
                                                          
{'loss': 0.6038, 'learning_rate': 1.2651825928770456e-05, 'epoch': 10.81}

 90%|█████████ | 25310/28080 [50:00:08<5:29:10,  7.13s/it]
 90%|█████████ | 25311/28080 [50:00:15<5:30:05,  7.15s/it]
                                                          
{'loss': 0.5941, 'learning_rate': 1.2642770455286862e-05, 'epoch': 10.81}

 90%|█████████ | 25311/28080 [50:00:15<5:30:05,  7.15s/it]
 90%|█████████ | 25312/28080 [50:00:22<5:29:40,  7.15s/it]
                                                          
{'loss': 0.5823, 'learning_rate': 1.2633718139596295e-05, 'epoch': 10.81}

 90%|█████████ | 25312/28080 [50:00:22<5:29:40,  7.15s/it]
 90%|█████████ | 25313/28080 [50:00:29<5:29:47,  7.15s/it]
                                                          
{'loss': 0.601, 'learning_rate': 1.2624668981819242e-05, 'epoch': 10.81}

 90%|█████████ | 25313/28080 [50:00:29<5:29:47,  7.15s/it]
 90%|█████████ | 25314/28080 [50:00:36<5:29:46,  7.15s/it]
                                                          
{'loss': 0.575, 'learning_rate': 1.2615622982076081e-05, 'epoch': 10.81}

 90%|█████████ | 25314/28080 [50:00:36<5:29:46,  7.15s/it]
 90%|█████████ | 25315/28080 [50:00:44<5:29:47,  7.16s/it]
                                                          
{'loss': 0.6046, 'learning_rate': 1.2606580140487185e-05, 'epoch': 10.81}

 90%|█████████ | 25315/28080 [50:00:44<5:29:47,  7.16s/it]
 90%|█████████ | 25316/28080 [50:00:51<5:28:14,  7.13s/it]
                                                          
{'loss': 0.6084, 'learning_rate': 1.2597540457172818e-05, 'epoch': 10.81}

 90%|█████████ | 25316/28080 [50:00:51<5:28:14,  7.13s/it]
 90%|█████████ | 25317/28080 [50:00:58<5:28:11,  7.13s/it]
                                                          
{'loss': 0.6152, 'learning_rate': 1.258850393225322e-05, 'epoch': 10.82}

 90%|█████████ | 25317/28080 [50:00:58<5:28:11,  7.13s/it]
 90%|█████████ | 25318/28080 [50:01:05<5:27:28,  7.11s/it]
                                                          
{'loss': 0.608, 'learning_rate': 1.257947056584871e-05, 'epoch': 10.82}

 90%|█████████ | 25318/28080 [50:01:05<5:27:28,  7.11s/it]
 90%|█████████ | 25319/28080 [50:01:12<5:26:56,  7.10s/it]
                                                          
{'loss': 0.5956, 'learning_rate': 1.257044035807936e-05, 'epoch': 10.82}

 90%|█████████ | 25319/28080 [50:01:12<5:26:56,  7.10s/it]
 90%|█████████ | 25320/28080 [50:01:19<5:27:38,  7.12s/it]
                                                          
{'loss': 0.5973, 'learning_rate': 1.2561413309065433e-05, 'epoch': 10.82}

 90%|█████████ | 25320/28080 [50:01:19<5:27:38,  7.12s/it]
 90%|█████████ | 25321/28080 [50:01:26<5:28:40,  7.15s/it]
                                                          
{'loss': 0.5974, 'learning_rate': 1.255238941892689e-05, 'epoch': 10.82}

 90%|█████████ | 25321/28080 [50:01:26<5:28:40,  7.15s/it]
 90%|█████████ | 25322/28080 [50:01:33<5:28:07,  7.14s/it]
                                                          
{'loss': 0.5976, 'learning_rate': 1.2543368687783885e-05, 'epoch': 10.82}

 90%|█████████ | 25322/28080 [50:01:33<5:28:07,  7.14s/it]
 90%|█████████ | 25323/28080 [50:01:41<5:27:43,  7.13s/it]
                                                          
{'loss': 0.5947, 'learning_rate': 1.2534351115756321e-05, 'epoch': 10.82}

 90%|█████████ | 25323/28080 [50:01:41<5:27:43,  7.13s/it]
 90%|█████████ | 25324/28080 [50:01:48<5:27:38,  7.13s/it]
                                                          
{'loss': 0.629, 'learning_rate': 1.2525336702964297e-05, 'epoch': 10.82}

 90%|█████████ | 25324/28080 [50:01:48<5:27:38,  7.13s/it]
 90%|█████████ | 25325/28080 [50:01:55<5:27:40,  7.14s/it]
                                                          
{'loss': 0.6149, 'learning_rate': 1.2516325449527687e-05, 'epoch': 10.82}

 90%|█████████ | 25325/28080 [50:01:55<5:27:40,  7.14s/it]
 90%|█████████ | 25326/28080 [50:02:02<5:27:24,  7.13s/it]
                                                          
{'loss': 0.6248, 'learning_rate': 1.2507317355566345e-05, 'epoch': 10.82}

 90%|█████████ | 25326/28080 [50:02:02<5:27:24,  7.13s/it]
 90%|█████████ | 25327/28080 [50:02:09<5:25:48,  7.10s/it]
                                                          
{'loss': 0.6047, 'learning_rate': 1.2498312421200114e-05, 'epoch': 10.82}

 90%|█████████ | 25327/28080 [50:02:09<5:25:48,  7.10s/it]
 90%|█████████ | 25328/28080 [50:02:16<5:26:38,  7.12s/it]
                                                          
{'loss': 0.5916, 'learning_rate': 1.2489310646548846e-05, 'epoch': 10.82}

 90%|█████████ | 25328/28080 [50:02:16<5:26:38,  7.12s/it]
 90%|█████████ | 25329/28080 [50:02:23<5:26:45,  7.13s/it]
                                                          
{'loss': 0.5945, 'learning_rate': 1.2480312031732278e-05, 'epoch': 10.82}

 90%|█████████ | 25329/28080 [50:02:23<5:26:45,  7.13s/it]
 90%|█████████ | 25330/28080 [50:02:30<5:26:17,  7.12s/it]
                                                          
{'loss': 0.6058, 'learning_rate': 1.2471316576870117e-05, 'epoch': 10.82}

 90%|█████████ | 25330/28080 [50:02:30<5:26:17,  7.12s/it]
 90%|█████████ | 25331/28080 [50:02:38<5:26:16,  7.12s/it]
                                                          
{'loss': 0.6058, 'learning_rate': 1.2462324282082022e-05, 'epoch': 10.82}

 90%|█████████ | 25331/28080 [50:02:38<5:26:16,  7.12s/it]
 90%|█████████ | 25332/28080 [50:02:45<5:26:33,  7.13s/it]
                                                          
{'loss': 0.5955, 'learning_rate': 1.2453335147487698e-05, 'epoch': 10.82}

 90%|█████████ | 25332/28080 [50:02:45<5:26:33,  7.13s/it]
 90%|█████████ | 25333/28080 [50:02:52<5:26:18,  7.13s/it]
                                                          
{'loss': 0.6054, 'learning_rate': 1.2444349173206609e-05, 'epoch': 10.82}

 90%|█████████ | 25333/28080 [50:02:52<5:26:18,  7.13s/it]
 90%|█████████ | 25334/28080 [50:02:59<5:26:19,  7.13s/it]
                                                          
{'loss': 0.5844, 'learning_rate': 1.2435366359358491e-05, 'epoch': 10.82}

 90%|█████████ | 25334/28080 [50:02:59<5:26:19,  7.13s/it]
 90%|█████████ | 25335/28080 [50:03:06<5:26:14,  7.13s/it]
                                                          
{'loss': 0.5929, 'learning_rate': 1.2426386706062692e-05, 'epoch': 10.82}

 90%|█████████ | 25335/28080 [50:03:06<5:26:14,  7.13s/it]
 90%|█████████ | 25336/28080 [50:03:13<5:24:42,  7.10s/it]
                                                          
{'loss': 0.6, 'learning_rate': 1.24174102134387e-05, 'epoch': 10.82}

 90%|█████████ | 25336/28080 [50:03:13<5:24:42,  7.10s/it]
 90%|█████████ | 25337/28080 [50:03:20<5:24:57,  7.11s/it]
                                                          
{'loss': 0.5925, 'learning_rate': 1.2408436881605977e-05, 'epoch': 10.82}

 90%|█████████ | 25337/28080 [50:03:20<5:24:57,  7.11s/it]
 90%|█████████ | 25338/28080 [50:03:27<5:24:51,  7.11s/it]
                                                          
{'loss': 0.5885, 'learning_rate': 1.2399466710683871e-05, 'epoch': 10.82}

 90%|█████████ | 25338/28080 [50:03:27<5:24:51,  7.11s/it]
 90%|█████████ | 25339/28080 [50:03:34<5:24:01,  7.09s/it]
                                                          
{'loss': 0.5904, 'learning_rate': 1.2390499700791813e-05, 'epoch': 10.82}

 90%|█████████ | 25339/28080 [50:03:34<5:24:01,  7.09s/it]
 90%|█████████ | 25340/28080 [50:03:42<5:24:28,  7.11s/it]
                                                          
{'loss': 0.5816, 'learning_rate': 1.2381535852048958e-05, 'epoch': 10.83}

 90%|█████████ | 25340/28080 [50:03:42<5:24:28,  7.11s/it]
 90%|█████████ | 25341/28080 [50:03:49<5:25:05,  7.12s/it]
                                                          
{'loss': 0.6135, 'learning_rate': 1.2372575164574657e-05, 'epoch': 10.83}

 90%|█████████ | 25341/28080 [50:03:49<5:25:05,  7.12s/it]
 90%|█████████ | 25342/28080 [50:03:56<5:25:18,  7.13s/it]
                                                          
{'loss': 0.5928, 'learning_rate': 1.2363617638488062e-05, 'epoch': 10.83}

 90%|█████████ | 25342/28080 [50:03:56<5:25:18,  7.13s/it]
 90%|█████████ | 25343/28080 [50:04:03<5:23:59,  7.10s/it]
                                                          
{'loss': 0.5967, 'learning_rate': 1.235466327390844e-05, 'epoch': 10.83}

 90%|█████████ | 25343/28080 [50:04:03<5:23:59,  7.10s/it]
 90%|█████████ | 25344/28080 [50:04:10<5:23:00,  7.08s/it]
                                                          
{'loss': 0.5842, 'learning_rate': 1.2345712070954834e-05, 'epoch': 10.83}

 90%|█████████ | 25344/28080 [50:04:10<5:23:00,  7.08s/it]
 90%|█████████ | 25345/28080 [50:04:17<5:23:19,  7.09s/it]
                                                          
{'loss': 0.5865, 'learning_rate': 1.2336764029746345e-05, 'epoch': 10.83}

 90%|█████████ | 25345/28080 [50:04:17<5:23:19,  7.09s/it]
 90%|█████████ | 25346/28080 [50:04:24<5:23:53,  7.11s/it]
                                                          
{'loss': 0.5971, 'learning_rate': 1.2327819150402014e-05, 'epoch': 10.83}

 90%|█████████ | 25346/28080 [50:04:24<5:23:53,  7.11s/it]
 90%|█████████ | 25347/28080 [50:04:31<5:24:54,  7.13s/it]
                                                          
{'loss': 0.6078, 'learning_rate': 1.2318877433040887e-05, 'epoch': 10.83}

 90%|█████████ | 25347/28080 [50:04:31<5:24:54,  7.13s/it]
 90%|█████████ | 25348/28080 [50:04:38<5:24:28,  7.13s/it]
                                                          
{'loss': 0.6065, 'learning_rate': 1.2309938877781896e-05, 'epoch': 10.83}

 90%|█████████ | 25348/28080 [50:04:38<5:24:28,  7.13s/it]
 90%|█████████ | 25349/28080 [50:04:46<5:24:12,  7.12s/it]
                                                          
{'loss': 0.595, 'learning_rate': 1.2301003484743945e-05, 'epoch': 10.83}

 90%|█████████ | 25349/28080 [50:04:46<5:24:12,  7.12s/it]
 90%|█████████ | 25350/28080 [50:04:53<5:22:59,  7.10s/it]
                                                          
{'loss': 0.6293, 'learning_rate': 1.229207125404591e-05, 'epoch': 10.83}

 90%|█████████ | 25350/28080 [50:04:53<5:22:59,  7.10s/it]
 90%|█████████ | 25351/28080 [50:05:00<5:24:02,  7.12s/it]
                                                          
{'loss': 0.6054, 'learning_rate': 1.2283142185806646e-05, 'epoch': 10.83}

 90%|█████████ | 25351/28080 [50:05:00<5:24:02,  7.12s/it]
 90%|█████████ | 25352/28080 [50:05:07<5:22:38,  7.10s/it]
                                                          
{'loss': 0.6102, 'learning_rate': 1.2274216280144911e-05, 'epoch': 10.83}

 90%|█████████ | 25352/28080 [50:05:07<5:22:38,  7.10s/it]
 90%|█████████ | 25353/28080 [50:05:14<5:23:12,  7.11s/it]
                                                          
{'loss': 0.6122, 'learning_rate': 1.2265293537179506e-05, 'epoch': 10.83}

 90%|█████████ | 25353/28080 [50:05:14<5:23:12,  7.11s/it]
 90%|█████████ | 25354/28080 [50:05:21<5:21:31,  7.08s/it]
                                                          
{'loss': 0.5952, 'learning_rate': 1.2256373957029138e-05, 'epoch': 10.83}

 90%|█████████ | 25354/28080 [50:05:21<5:21:31,  7.08s/it]
 90%|█████████ | 25355/28080 [50:05:28<5:22:18,  7.10s/it]
                                                          
{'loss': 0.6007, 'learning_rate': 1.2247457539812434e-05, 'epoch': 10.83}

 90%|█████████ | 25355/28080 [50:05:28<5:22:18,  7.10s/it]
 90%|█████████ | 25356/28080 [50:05:35<5:22:55,  7.11s/it]
                                                          
{'loss': 0.5867, 'learning_rate': 1.2238544285647996e-05, 'epoch': 10.83}

 90%|█████████ | 25356/28080 [50:05:35<5:22:55,  7.11s/it]
 90%|█████████ | 25357/28080 [50:05:42<5:22:41,  7.11s/it]
                                                          
{'loss': 0.6163, 'learning_rate': 1.2229634194654477e-05, 'epoch': 10.83}

 90%|█████████ | 25357/28080 [50:05:42<5:22:41,  7.11s/it]
 90%|█████████ | 25358/28080 [50:05:50<5:23:47,  7.14s/it]
                                                          
{'loss': 0.611, 'learning_rate': 1.2220727266950365e-05, 'epoch': 10.83}

 90%|█████████ | 25358/28080 [50:05:50<5:23:47,  7.14s/it]
 90%|█████████ | 25359/28080 [50:05:57<5:22:08,  7.10s/it]
                                                          
{'loss': 0.6233, 'learning_rate': 1.2211823502654206e-05, 'epoch': 10.83}

 90%|█████████ | 25359/28080 [50:05:57<5:22:08,  7.10s/it]
 90%|█████████ | 25360/28080 [50:06:04<5:22:27,  7.11s/it]
                                                          
{'loss': 0.5937, 'learning_rate': 1.2202922901884405e-05, 'epoch': 10.83}

 90%|█████████ | 25360/28080 [50:06:04<5:22:27,  7.11s/it]
 90%|█████████ | 25361/28080 [50:06:11<5:23:30,  7.14s/it]
                                                          
{'loss': 0.5971, 'learning_rate': 1.2194025464759367e-05, 'epoch': 10.83}

 90%|█████████ | 25361/28080 [50:06:11<5:23:30,  7.14s/it]
 90%|█████████ | 25362/28080 [50:06:18<5:23:29,  7.14s/it]
                                                          
{'loss': 0.6058, 'learning_rate': 1.2185131191397497e-05, 'epoch': 10.83}

 90%|█████████ | 25362/28080 [50:06:18<5:23:29,  7.14s/it]
 90%|█████████ | 25363/28080 [50:06:25<5:23:19,  7.14s/it]
                                                          
{'loss': 0.5864, 'learning_rate': 1.2176240081917144e-05, 'epoch': 10.83}

 90%|█████████ | 25363/28080 [50:06:25<5:23:19,  7.14s/it]
 90%|█████████ | 25364/28080 [50:06:32<5:22:14,  7.12s/it]
                                                          
{'loss': 0.5905, 'learning_rate': 1.2167352136436549e-05, 'epoch': 10.84}

 90%|█████████ | 25364/28080 [50:06:32<5:22:14,  7.12s/it]
 90%|█████████ | 25365/28080 [50:06:39<5:22:41,  7.13s/it]
                                                          
{'loss': 0.5866, 'learning_rate': 1.2158467355073949e-05, 'epoch': 10.84}

 90%|█████████ | 25365/28080 [50:06:39<5:22:41,  7.13s/it]
 90%|█████████ | 25366/28080 [50:06:46<5:19:34,  7.07s/it]
                                                          
{'loss': 0.5978, 'learning_rate': 1.2149585737947611e-05, 'epoch': 10.84}

 90%|█████████ | 25366/28080 [50:06:46<5:19:34,  7.07s/it]
 90%|█████████ | 25367/28080 [50:06:53<5:19:03,  7.06s/it]
                                                          
{'loss': 0.608, 'learning_rate': 1.2140707285175634e-05, 'epoch': 10.84}

 90%|█████████ | 25367/28080 [50:06:53<5:19:03,  7.06s/it]
 90%|█████████ | 25368/28080 [50:07:01<5:19:57,  7.08s/it]
                                                          
{'loss': 0.626, 'learning_rate': 1.2131831996876231e-05, 'epoch': 10.84}

 90%|█████████ | 25368/28080 [50:07:01<5:19:57,  7.08s/it]
 90%|█████████ | 25369/28080 [50:07:08<5:20:54,  7.10s/it]
                                                          
{'loss': 0.5926, 'learning_rate': 1.2122959873167305e-05, 'epoch': 10.84}

 90%|█████████ | 25369/28080 [50:07:08<5:20:54,  7.10s/it]
 90%|█████████ | 25370/28080 [50:07:15<5:21:43,  7.12s/it]
                                                          
{'loss': 0.6284, 'learning_rate': 1.211409091416707e-05, 'epoch': 10.84}

 90%|█████████ | 25370/28080 [50:07:15<5:21:43,  7.12s/it]
 90%|█████████ | 25371/28080 [50:07:22<5:22:08,  7.13s/it]
                                                          
{'loss': 0.6084, 'learning_rate': 1.2105225119993373e-05, 'epoch': 10.84}

 90%|█████████ | 25371/28080 [50:07:22<5:22:08,  7.13s/it]
 90%|█████████ | 25372/28080 [50:07:29<5:22:10,  7.14s/it]
                                                          
{'loss': 0.5934, 'learning_rate': 1.209636249076429e-05, 'epoch': 10.84}

 90%|█████████ | 25372/28080 [50:07:29<5:22:10,  7.14s/it]
 90%|█████████ | 25373/28080 [50:07:36<5:22:27,  7.15s/it]
                                                          
{'loss': 0.5965, 'learning_rate': 1.2087503026597669e-05, 'epoch': 10.84}

 90%|█████████ | 25373/28080 [50:07:36<5:22:27,  7.15s/it]
 90%|█████████ | 25374/28080 [50:07:44<5:22:54,  7.16s/it]
                                                          
{'loss': 0.5962, 'learning_rate': 1.2078646727611358e-05, 'epoch': 10.84}

 90%|█████████ | 25374/28080 [50:07:44<5:22:54,  7.16s/it]
 90%|█████████ | 25375/28080 [50:07:51<5:22:03,  7.14s/it]
                                                          
{'loss': 0.6023, 'learning_rate': 1.2069793593923213e-05, 'epoch': 10.84}

 90%|█████████ | 25375/28080 [50:07:51<5:22:03,  7.14s/it]
 90%|█████████ | 25376/28080 [50:07:58<5:24:12,  7.19s/it]
                                                          
{'loss': 0.6031, 'learning_rate': 1.2060943625650994e-05, 'epoch': 10.84}

 90%|█████████ | 25376/28080 [50:07:58<5:24:12,  7.19s/it]
 90%|█████████ | 25377/28080 [50:08:05<5:22:29,  7.16s/it]
                                                          
{'loss': 0.5951, 'learning_rate': 1.2052096822912473e-05, 'epoch': 10.84}

 90%|█████████ | 25377/28080 [50:08:05<5:22:29,  7.16s/it]
 90%|█████████ | 25378/28080 [50:08:12<5:22:15,  7.16s/it]
                                                          
{'loss': 0.5758, 'learning_rate': 1.204325318582533e-05, 'epoch': 10.84}

 90%|█████████ | 25378/28080 [50:08:12<5:22:15,  7.16s/it]
 90%|█████████ | 25379/28080 [50:08:19<5:22:00,  7.15s/it]
                                                          
{'loss': 0.6033, 'learning_rate': 1.203441271450717e-05, 'epoch': 10.84}

 90%|█████████ | 25379/28080 [50:08:19<5:22:00,  7.15s/it]
 90%|█████████ | 25380/28080 [50:08:26<5:21:00,  7.13s/it]
                                                          
{'loss': 0.6091, 'learning_rate': 1.20255754090757e-05, 'epoch': 10.84}

 90%|█████████ | 25380/28080 [50:08:26<5:21:00,  7.13s/it]
 90%|█████████ | 25381/28080 [50:08:34<5:20:36,  7.13s/it]
                                                          
{'loss': 0.5925, 'learning_rate': 1.2016741269648412e-05, 'epoch': 10.84}

 90%|█████████ | 25381/28080 [50:08:34<5:20:36,  7.13s/it]
 90%|█████████ | 25382/28080 [50:08:41<5:20:32,  7.13s/it]
                                                          
{'loss': 0.6011, 'learning_rate': 1.2007910296342933e-05, 'epoch': 10.84}

 90%|█████████ | 25382/28080 [50:08:41<5:20:32,  7.13s/it]
 90%|█████████ | 25383/28080 [50:08:48<5:20:37,  7.13s/it]
                                                          
{'loss': 0.6067, 'learning_rate': 1.1999082489276614e-05, 'epoch': 10.84}

 90%|█████████ | 25383/28080 [50:08:48<5:20:37,  7.13s/it]
 90%|█████████ | 25384/28080 [50:08:55<5:19:29,  7.11s/it]
                                                          
{'loss': 0.6, 'learning_rate': 1.1990257848566999e-05, 'epoch': 10.84}

 90%|█████████ | 25384/28080 [50:08:55<5:19:29,  7.11s/it]
 90%|█████████ | 25385/28080 [50:09:02<5:20:52,  7.14s/it]
                                                          
{'loss': 0.6008, 'learning_rate': 1.1981436374331466e-05, 'epoch': 10.84}

 90%|█████████ | 25385/28080 [50:09:02<5:20:52,  7.14s/it]
 90%|█████████ | 25386/28080 [50:09:09<5:19:07,  7.11s/it]
                                                          
{'loss': 0.6131, 'learning_rate': 1.1972618066687341e-05, 'epoch': 10.84}

 90%|█████████ | 25386/28080 [50:09:09<5:19:07,  7.11s/it]
 90%|█████████ | 25387/28080 [50:09:16<5:18:26,  7.10s/it]
                                                          
{'loss': 0.5979, 'learning_rate': 1.1963802925752026e-05, 'epoch': 10.85}

 90%|█████████ | 25387/28080 [50:09:16<5:18:26,  7.10s/it]
 90%|█████████ | 25388/28080 [50:09:23<5:17:56,  7.09s/it]
                                                          
{'loss': 0.6027, 'learning_rate': 1.1954990951642681e-05, 'epoch': 10.85}

 90%|█████████ | 25388/28080 [50:09:23<5:17:56,  7.09s/it]
 90%|█████████ | 25389/28080 [50:09:30<5:16:49,  7.06s/it]
                                                          
{'loss': 0.5948, 'learning_rate': 1.1946182144476653e-05, 'epoch': 10.85}

 90%|█████████ | 25389/28080 [50:09:30<5:16:49,  7.06s/it]
 90%|█████████ | 25390/28080 [50:09:37<5:17:12,  7.08s/it]
                                                          
{'loss': 0.6074, 'learning_rate': 1.1937376504371045e-05, 'epoch': 10.85}

 90%|█████████ | 25390/28080 [50:09:37<5:17:12,  7.08s/it]
 90%|█████████ | 25391/28080 [50:09:44<5:17:42,  7.09s/it]
                                                          
{'loss': 0.592, 'learning_rate': 1.1928574031443096e-05, 'epoch': 10.85}

 90%|█████████ | 25391/28080 [50:09:44<5:17:42,  7.09s/it]
 90%|█████████ | 25392/28080 [50:09:51<5:16:51,  7.07s/it]
                                                          
{'loss': 0.6125, 'learning_rate': 1.191977472580985e-05, 'epoch': 10.85}

 90%|█████████ | 25392/28080 [50:09:51<5:16:51,  7.07s/it]
 90%|█████████ | 25393/28080 [50:09:59<5:18:21,  7.11s/it]
                                                          
{'loss': 0.5953, 'learning_rate': 1.1910978587588383e-05, 'epoch': 10.85}

 90%|█████████ | 25393/28080 [50:09:59<5:18:21,  7.11s/it]
 90%|█████████ | 25394/28080 [50:10:06<5:17:56,  7.10s/it]
                                                          
{'loss': 0.604, 'learning_rate': 1.1902185616895683e-05, 'epoch': 10.85}

 90%|█████████ | 25394/28080 [50:10:06<5:17:56,  7.10s/it]
 90%|█████████ | 25395/28080 [50:10:13<5:18:11,  7.11s/it]
                                                          
{'loss': 0.582, 'learning_rate': 1.1893395813848822e-05, 'epoch': 10.85}

 90%|█████████ | 25395/28080 [50:10:13<5:18:11,  7.11s/it]
 90%|█████████ | 25396/28080 [50:10:20<5:17:09,  7.09s/it]
                                                          
{'loss': 0.5849, 'learning_rate': 1.1884609178564682e-05, 'epoch': 10.85}

 90%|█████████ | 25396/28080 [50:10:20<5:17:09,  7.09s/it]
 90%|█████████ | 25397/28080 [50:10:27<5:17:44,  7.11s/it]
                                                          
{'loss': 0.6014, 'learning_rate': 1.1875825711160166e-05, 'epoch': 10.85}

 90%|█████████ | 25397/28080 [50:10:27<5:17:44,  7.11s/it]
 90%|█████████ | 25398/28080 [50:10:34<5:18:00,  7.11s/it]
                                                          
{'loss': 0.5997, 'learning_rate': 1.1867045411752097e-05, 'epoch': 10.85}

 90%|█████████ | 25398/28080 [50:10:34<5:18:00,  7.11s/it]
 90%|█████████ | 25399/28080 [50:10:41<5:16:27,  7.08s/it]
                                                          
{'loss': 0.6021, 'learning_rate': 1.1858268280457358e-05, 'epoch': 10.85}

 90%|█████████ | 25399/28080 [50:10:41<5:16:27,  7.08s/it]
 90%|█████████ | 25400/28080 [50:10:48<5:16:09,  7.08s/it]
                                                          
{'loss': 0.6032, 'learning_rate': 1.1849494317392657e-05, 'epoch': 10.85}

 90%|█████████ | 25400/28080 [50:10:48<5:16:09,  7.08s/it]
 90%|█████████ | 25401/28080 [50:10:55<5:17:03,  7.10s/it]
                                                          
{'loss': 0.6038, 'learning_rate': 1.184072352267479e-05, 'epoch': 10.85}

 90%|█████████ | 25401/28080 [50:10:55<5:17:03,  7.10s/it]
 90%|█████████ | 25402/28080 [50:11:03<5:17:03,  7.10s/it]
                                                          
{'loss': 0.5847, 'learning_rate': 1.183195589642036e-05, 'epoch': 10.85}

 90%|█████████ | 25402/28080 [50:11:03<5:17:03,  7.10s/it]
 90%|█████████ | 25403/28080 [50:11:10<5:17:55,  7.13s/it]
                                                          
{'loss': 0.5913, 'learning_rate': 1.182319143874605e-05, 'epoch': 10.85}

 90%|█████████ | 25403/28080 [50:11:10<5:17:55,  7.13s/it]
 90%|█████████ | 25404/28080 [50:11:17<5:17:52,  7.13s/it]
                                                          
{'loss': 0.6226, 'learning_rate': 1.1814430149768463e-05, 'epoch': 10.85}

 90%|█████████ | 25404/28080 [50:11:17<5:17:52,  7.13s/it]
 90%|█████████ | 25405/28080 [50:11:24<5:17:45,  7.13s/it]
                                                          
{'loss': 0.6135, 'learning_rate': 1.1805672029604197e-05, 'epoch': 10.85}

 90%|█████████ | 25405/28080 [50:11:24<5:17:45,  7.13s/it]
 90%|█████████ | 25406/28080 [50:11:31<5:17:47,  7.13s/it]
                                                          
{'loss': 0.6125, 'learning_rate': 1.1796917078369718e-05, 'epoch': 10.85}

 90%|█████████ | 25406/28080 [50:11:31<5:17:47,  7.13s/it]
 90%|█████████ | 25407/28080 [50:11:38<5:17:24,  7.12s/it]
                                                          
{'loss': 0.6156, 'learning_rate': 1.1788165296181514e-05, 'epoch': 10.85}

 90%|█████████ | 25407/28080 [50:11:38<5:17:24,  7.12s/it]
 90%|█████████ | 25408/28080 [50:11:45<5:16:28,  7.11s/it]
                                                          
{'loss': 0.6182, 'learning_rate': 1.1779416683155992e-05, 'epoch': 10.85}

 90%|█████████ | 25408/28080 [50:11:45<5:16:28,  7.11s/it]
 90%|█████████ | 25409/28080 [50:11:52<5:16:28,  7.11s/it]
                                                          
{'loss': 0.6115, 'learning_rate': 1.1770671239409613e-05, 'epoch': 10.85}

 90%|█████████ | 25409/28080 [50:11:52<5:16:28,  7.11s/it]
 90%|█████████ | 25410/28080 [50:12:00<5:17:47,  7.14s/it]
                                                          
{'loss': 0.6088, 'learning_rate': 1.1761928965058677e-05, 'epoch': 10.85}

 90%|█████████ | 25410/28080 [50:12:00<5:17:47,  7.14s/it]
 90%|█████████ | 25411/28080 [50:12:07<5:16:01,  7.10s/it]
                                                          
{'loss': 0.5919, 'learning_rate': 1.1753189860219505e-05, 'epoch': 10.86}

 90%|█████████ | 25411/28080 [50:12:07<5:16:01,  7.10s/it]
 90%|█████████ | 25412/28080 [50:12:14<5:15:58,  7.11s/it]
                                                          
{'loss': 0.5928, 'learning_rate': 1.1744453925008363e-05, 'epoch': 10.86}

 90%|█████████ | 25412/28080 [50:12:14<5:15:58,  7.11s/it]
 91%|█████████ | 25413/28080 [50:12:21<5:15:44,  7.10s/it]
                                                          
{'loss': 0.5947, 'learning_rate': 1.1735721159541413e-05, 'epoch': 10.86}

 91%|█████████ | 25413/28080 [50:12:21<5:15:44,  7.10s/it]
 91%|█████████ | 25414/28080 [50:12:28<5:14:22,  7.08s/it]
                                                          
{'loss': 0.6174, 'learning_rate': 1.1726991563934946e-05, 'epoch': 10.86}

 91%|█████████ | 25414/28080 [50:12:28<5:14:22,  7.08s/it]
 91%|█████████ | 25415/28080 [50:12:35<5:14:54,  7.09s/it]
                                                          
{'loss': 0.6064, 'learning_rate': 1.1718265138305012e-05, 'epoch': 10.86}

 91%|█████████ | 25415/28080 [50:12:35<5:14:54,  7.09s/it]
 91%|█████████ | 25416/28080 [50:12:42<5:14:56,  7.09s/it]
                                                          
{'loss': 0.6053, 'learning_rate': 1.1709541882767794e-05, 'epoch': 10.86}

 91%|█████████ | 25416/28080 [50:12:42<5:14:56,  7.09s/it]
 91%|█████████ | 25417/28080 [50:12:49<5:13:29,  7.06s/it]
                                                          
{'loss': 0.6224, 'learning_rate': 1.1700821797439198e-05, 'epoch': 10.86}

 91%|█████████ | 25417/28080 [50:12:49<5:13:29,  7.06s/it]
 91%|█████████ | 25418/28080 [50:12:56<5:13:48,  7.07s/it]
                                                          
{'loss': 0.6035, 'learning_rate': 1.1692104882435411e-05, 'epoch': 10.86}

 91%|█████████ | 25418/28080 [50:12:56<5:13:48,  7.07s/it]
 91%|█████████ | 25419/28080 [50:13:03<5:12:59,  7.06s/it]
                                                          
{'loss': 0.5986, 'learning_rate': 1.1683391137872257e-05, 'epoch': 10.86}

 91%|█████████ | 25419/28080 [50:13:03<5:12:59,  7.06s/it]
 91%|█████████ | 25420/28080 [50:13:10<5:13:08,  7.06s/it]
                                                          
{'loss': 0.5882, 'learning_rate': 1.1674680563865752e-05, 'epoch': 10.86}

 91%|█████████ | 25420/28080 [50:13:10<5:13:08,  7.06s/it]
 91%|█████████ | 25421/28080 [50:13:17<5:14:00,  7.09s/it]
                                                          
{'loss': 0.59, 'learning_rate': 1.1665973160531779e-05, 'epoch': 10.86}

 91%|█████████ | 25421/28080 [50:13:17<5:14:00,  7.09s/it]
 91%|█████████ | 25422/28080 [50:13:25<5:14:12,  7.09s/it]
                                                          
{'loss': 0.5886, 'learning_rate': 1.165726892798616e-05, 'epoch': 10.86}

 91%|█████████ | 25422/28080 [50:13:25<5:14:12,  7.09s/it]
 91%|█████████ | 25423/28080 [50:13:32<5:15:56,  7.13s/it]
                                                          
{'loss': 0.5995, 'learning_rate': 1.1648567866344633e-05, 'epoch': 10.86}

 91%|█████████ | 25423/28080 [50:13:32<5:15:56,  7.13s/it]
 91%|█████████ | 25424/28080 [50:13:39<5:16:13,  7.14s/it]
                                                          
{'loss': 0.606, 'learning_rate': 1.1639869975723055e-05, 'epoch': 10.86}

 91%|█████████ | 25424/28080 [50:13:39<5:16:13,  7.14s/it]
 91%|█████████ | 25425/28080 [50:13:46<5:14:13,  7.10s/it]
                                                          
{'loss': 0.6063, 'learning_rate': 1.1631175256237136e-05, 'epoch': 10.86}

 91%|█████████ | 25425/28080 [50:13:46<5:14:13,  7.10s/it]
 91%|█████████ | 25426/28080 [50:13:53<5:13:27,  7.09s/it]
                                                          
{'loss': 0.617, 'learning_rate': 1.162248370800248e-05, 'epoch': 10.86}

 91%|█████████ | 25426/28080 [50:13:53<5:13:27,  7.09s/it]
 91%|█████████ | 25427/28080 [50:14:00<5:12:29,  7.07s/it]
                                                          
{'loss': 0.603, 'learning_rate': 1.161379533113474e-05, 'epoch': 10.86}

 91%|█████████ | 25427/28080 [50:14:00<5:12:29,  7.07s/it]
 91%|█████████ | 25428/28080 [50:14:07<5:13:42,  7.10s/it]
                                                          
{'loss': 0.5886, 'learning_rate': 1.1605110125749579e-05, 'epoch': 10.86}

 91%|█████████ | 25428/28080 [50:14:07<5:13:42,  7.10s/it]
 91%|█████████ | 25429/28080 [50:14:14<5:14:23,  7.12s/it]
                                                          
{'loss': 0.5894, 'learning_rate': 1.159642809196243e-05, 'epoch': 10.86}

 91%|█████████ | 25429/28080 [50:14:14<5:14:23,  7.12s/it]
 91%|█████████ | 25430/28080 [50:14:21<5:14:54,  7.13s/it]
                                                          
{'loss': 0.5892, 'learning_rate': 1.1587749229888923e-05, 'epoch': 10.86}

 91%|█████████ | 25430/28080 [50:14:22<5:14:54,  7.13s/it]
 91%|█████████ | 25431/28080 [50:14:29<5:15:11,  7.14s/it]
                                                          
{'loss': 0.5928, 'learning_rate': 1.1579073539644408e-05, 'epoch': 10.86}

 91%|█████████ | 25431/28080 [50:14:29<5:15:11,  7.14s/it]
 91%|█████████ | 25432/28080 [50:14:36<5:14:44,  7.13s/it]
                                                          
{'loss': 0.5813, 'learning_rate': 1.157040102134438e-05, 'epoch': 10.86}

 91%|█████████ | 25432/28080 [50:14:36<5:14:44,  7.13s/it]
 91%|█████████ | 25433/28080 [50:14:43<5:15:02,  7.14s/it]
                                                          
{'loss': 0.5967, 'learning_rate': 1.156173167510413e-05, 'epoch': 10.86}

 91%|█████████ | 25433/28080 [50:14:43<5:15:02,  7.14s/it]
 91%|█████████ | 25434/28080 [50:14:50<5:15:13,  7.15s/it]
                                                          
{'loss': 0.5764, 'learning_rate': 1.1553065501039128e-05, 'epoch': 10.87}

 91%|█████████ | 25434/28080 [50:14:50<5:15:13,  7.15s/it]
 91%|█████████ | 25435/28080 [50:14:57<5:14:51,  7.14s/it]
                                                          
{'loss': 0.6068, 'learning_rate': 1.1544402499264612e-05, 'epoch': 10.87}

 91%|█████████ | 25435/28080 [50:14:57<5:14:51,  7.14s/it]
 91%|█████████ | 25436/28080 [50:15:04<5:12:27,  7.09s/it]
                                                          
{'loss': 0.596, 'learning_rate': 1.1535742669895766e-05, 'epoch': 10.87}

 91%|█████████ | 25436/28080 [50:15:04<5:12:27,  7.09s/it]
 91%|█████████ | 25437/28080 [50:15:11<5:13:07,  7.11s/it]
                                                          
{'loss': 0.584, 'learning_rate': 1.1527086013047889e-05, 'epoch': 10.87}

 91%|█████████ | 25437/28080 [50:15:11<5:13:07,  7.11s/it]
 91%|█████████ | 25438/28080 [50:15:19<5:13:49,  7.13s/it]
                                                          
{'loss': 0.5979, 'learning_rate': 1.1518432528836053e-05, 'epoch': 10.87}

 91%|█████████ | 25438/28080 [50:15:19<5:13:49,  7.13s/it]
 91%|█████████ | 25439/28080 [50:15:26<5:14:00,  7.13s/it]
                                                          
{'loss': 0.6022, 'learning_rate': 1.1509782217375502e-05, 'epoch': 10.87}

 91%|█████████ | 25439/28080 [50:15:26<5:14:00,  7.13s/it]
 91%|█████████ | 25440/28080 [50:15:33<5:13:12,  7.12s/it]
                                                          
{'loss': 0.6037, 'learning_rate': 1.1501135078781255e-05, 'epoch': 10.87}

 91%|█████████ | 25440/28080 [50:15:33<5:13:12,  7.12s/it]
 91%|█████████ | 25441/28080 [50:15:40<5:14:12,  7.14s/it]
                                                          
{'loss': 0.5963, 'learning_rate': 1.1492491113168385e-05, 'epoch': 10.87}

 91%|█████████ | 25441/28080 [50:15:40<5:14:12,  7.14s/it]
 91%|█████████ | 25442/28080 [50:15:47<5:12:31,  7.11s/it]
                                                          
{'loss': 0.6068, 'learning_rate': 1.14838503206518e-05, 'epoch': 10.87}

 91%|█████████ | 25442/28080 [50:15:47<5:12:31,  7.11s/it]
 91%|█████████ | 25443/28080 [50:15:54<5:10:50,  7.07s/it]
                                                          
{'loss': 0.6125, 'learning_rate': 1.1475212701346576e-05, 'epoch': 10.87}

 91%|█████████ | 25443/28080 [50:15:54<5:10:50,  7.07s/it]
 91%|█████████ | 25444/28080 [50:16:01<5:11:42,  7.10s/it]
                                                          
{'loss': 0.5955, 'learning_rate': 1.1466578255367565e-05, 'epoch': 10.87}

 91%|█████████ | 25444/28080 [50:16:01<5:11:42,  7.10s/it]
 91%|█████████ | 25445/28080 [50:16:08<5:10:15,  7.06s/it]
                                                          
{'loss': 0.6042, 'learning_rate': 1.1457946982829647e-05, 'epoch': 10.87}

 91%|█████████ | 25445/28080 [50:16:08<5:10:15,  7.06s/it]
 91%|█████████ | 25446/28080 [50:16:15<5:10:17,  7.07s/it]
                                                          
{'loss': 0.5927, 'learning_rate': 1.144931888384762e-05, 'epoch': 10.87}

 91%|█████████ | 25446/28080 [50:16:15<5:10:17,  7.07s/it]
 91%|█████████ | 25447/28080 [50:16:22<5:09:49,  7.06s/it]
                                                          
{'loss': 0.6069, 'learning_rate': 1.1440693958536335e-05, 'epoch': 10.87}

 91%|█████████ | 25447/28080 [50:16:22<5:09:49,  7.06s/it]
 91%|█████████ | 25448/28080 [50:16:29<5:10:54,  7.09s/it]
                                                          
{'loss': 0.5831, 'learning_rate': 1.143207220701048e-05, 'epoch': 10.87}

 91%|█████████ | 25448/28080 [50:16:29<5:10:54,  7.09s/it]
 91%|█████████ | 25449/28080 [50:16:37<5:12:02,  7.12s/it]
                                                          
{'loss': 0.6002, 'learning_rate': 1.1423453629384878e-05, 'epoch': 10.87}

 91%|█████████ | 25449/28080 [50:16:37<5:12:02,  7.12s/it]
 91%|█████████ | 25450/28080 [50:16:44<5:09:41,  7.07s/it]
                                                          
{'loss': 0.6182, 'learning_rate': 1.1414838225773993e-05, 'epoch': 10.87}

 91%|█████████ | 25450/28080 [50:16:44<5:09:41,  7.07s/it]
 91%|█████████ | 25451/28080 [50:16:51<5:10:49,  7.09s/it]
                                                          
{'loss': 0.6112, 'learning_rate': 1.1406225996292597e-05, 'epoch': 10.87}

 91%|█████████ | 25451/28080 [50:16:51<5:10:49,  7.09s/it]
 91%|█████████ | 25452/28080 [50:16:58<5:10:53,  7.10s/it]
                                                          
{'loss': 0.587, 'learning_rate': 1.1397616941055205e-05, 'epoch': 10.87}

 91%|█████████ | 25452/28080 [50:16:58<5:10:53,  7.10s/it]
 91%|█████████ | 25453/28080 [50:17:05<5:10:41,  7.10s/it]
                                                          
{'loss': 0.6208, 'learning_rate': 1.1389011060176396e-05, 'epoch': 10.87}

 91%|█████████ | 25453/28080 [50:17:05<5:10:41,  7.10s/it]
 91%|█████████ | 25454/28080 [50:17:12<5:11:34,  7.12s/it]
                                                          
{'loss': 0.5865, 'learning_rate': 1.1380408353770633e-05, 'epoch': 10.87}

 91%|█████████ | 25454/28080 [50:17:12<5:11:34,  7.12s/it]
 91%|█████████ | 25455/28080 [50:17:19<5:11:40,  7.12s/it]
                                                          
{'loss': 0.6088, 'learning_rate': 1.1371808821952351e-05, 'epoch': 10.87}

 91%|█████████ | 25455/28080 [50:17:19<5:11:40,  7.12s/it]
 91%|█████████ | 25456/28080 [50:17:26<5:12:38,  7.15s/it]
                                                          
{'loss': 0.5758, 'learning_rate': 1.136321246483596e-05, 'epoch': 10.87}

 91%|█████████ | 25456/28080 [50:17:26<5:12:38,  7.15s/it]
 91%|█████████ | 25457/28080 [50:17:33<5:11:38,  7.13s/it]
                                                          
{'loss': 0.6071, 'learning_rate': 1.1354619282535839e-05, 'epoch': 10.87}

 91%|█████████ | 25457/28080 [50:17:33<5:11:38,  7.13s/it]
 91%|█████████ | 25458/28080 [50:17:40<5:09:50,  7.09s/it]
                                                          
{'loss': 0.6091, 'learning_rate': 1.1346029275166341e-05, 'epoch': 10.88}

 91%|█████████ | 25458/28080 [50:17:40<5:09:50,  7.09s/it]
 91%|█████████ | 25459/28080 [50:17:48<5:09:55,  7.09s/it]
                                                          
{'loss': 0.5958, 'learning_rate': 1.133744244284171e-05, 'epoch': 10.88}

 91%|█████████ | 25459/28080 [50:17:48<5:09:55,  7.09s/it]
 91%|█████████ | 25460/28080 [50:17:55<5:09:33,  7.09s/it]
                                                          
{'loss': 0.6059, 'learning_rate': 1.1328858785676216e-05, 'epoch': 10.88}

 91%|█████████ | 25460/28080 [50:17:55<5:09:33,  7.09s/it]
 91%|█████████ | 25461/28080 [50:18:02<5:08:04,  7.06s/it]
                                                          
{'loss': 0.6138, 'learning_rate': 1.1320278303783959e-05, 'epoch': 10.88}

 91%|█████████ | 25461/28080 [50:18:02<5:08:04,  7.06s/it]
 91%|█████████ | 25462/28080 [50:18:09<5:08:34,  7.07s/it]
                                                          
{'loss': 0.5888, 'learning_rate': 1.131170099727924e-05, 'epoch': 10.88}

 91%|█████████ | 25462/28080 [50:18:09<5:08:34,  7.07s/it]
 91%|█████████ | 25463/28080 [50:18:16<5:07:46,  7.06s/it]
                                                          
{'loss': 0.6357, 'learning_rate': 1.1303126866276075e-05, 'epoch': 10.88}

 91%|█████████ | 25463/28080 [50:18:16<5:07:46,  7.06s/it]
 91%|█████████ | 25464/28080 [50:18:23<5:07:50,  7.06s/it]
                                                          
{'loss': 0.6002, 'learning_rate': 1.1294555910888542e-05, 'epoch': 10.88}

 91%|█████████ | 25464/28080 [50:18:23<5:07:50,  7.06s/it]
 91%|█████████ | 25465/28080 [50:18:30<5:08:48,  7.09s/it]
                                                          
{'loss': 0.6105, 'learning_rate': 1.128598813123069e-05, 'epoch': 10.88}

 91%|█████████ | 25465/28080 [50:18:30<5:08:48,  7.09s/it]
 91%|█████████ | 25466/28080 [50:18:37<5:09:44,  7.11s/it]
                                                          
{'loss': 0.6024, 'learning_rate': 1.1277423527416507e-05, 'epoch': 10.88}

 91%|█████████ | 25466/28080 [50:18:37<5:09:44,  7.11s/it]
 91%|█████████ | 25467/28080 [50:18:44<5:08:10,  7.08s/it]
                                                          
{'loss': 0.5976, 'learning_rate': 1.1268862099559879e-05, 'epoch': 10.88}

 91%|█████████ | 25467/28080 [50:18:44<5:08:10,  7.08s/it]
 91%|█████████ | 25468/28080 [50:18:51<5:06:43,  7.05s/it]
                                                          
{'loss': 0.5958, 'learning_rate': 1.1260303847774822e-05, 'epoch': 10.88}

 91%|█████████ | 25468/28080 [50:18:51<5:06:43,  7.05s/it]
 91%|█████████ | 25469/28080 [50:18:58<5:09:01,  7.10s/it]
                                                          
{'loss': 0.6215, 'learning_rate': 1.1251748772175108e-05, 'epoch': 10.88}

 91%|█████████ | 25469/28080 [50:18:58<5:09:01,  7.10s/it]
 91%|█████████ | 25470/28080 [50:19:05<5:09:21,  7.11s/it]
                                                          
{'loss': 0.5917, 'learning_rate': 1.124319687287459e-05, 'epoch': 10.88}

 91%|█████████ | 25470/28080 [50:19:05<5:09:21,  7.11s/it]
 91%|█████████ | 25471/28080 [50:19:13<5:09:10,  7.11s/it]
                                                          
{'loss': 0.6108, 'learning_rate': 1.123464814998698e-05, 'epoch': 10.88}

 91%|█████████ | 25471/28080 [50:19:13<5:09:10,  7.11s/it]
 91%|█████████ | 25472/28080 [50:19:20<5:07:27,  7.07s/it]
                                                          
{'loss': 0.6118, 'learning_rate': 1.1226102603626081e-05, 'epoch': 10.88}

 91%|█████████ | 25472/28080 [50:19:20<5:07:27,  7.07s/it]
 91%|█████████ | 25473/28080 [50:19:27<5:07:22,  7.07s/it]
                                                          
{'loss': 0.6056, 'learning_rate': 1.1217560233905577e-05, 'epoch': 10.88}

 91%|█████████ | 25473/28080 [50:19:27<5:07:22,  7.07s/it]
 91%|█████████ | 25474/28080 [50:19:34<5:07:32,  7.08s/it]
                                                          
{'loss': 0.6065, 'learning_rate': 1.120902104093907e-05, 'epoch': 10.88}

 91%|█████████ | 25474/28080 [50:19:34<5:07:32,  7.08s/it]
 91%|█████████ | 25475/28080 [50:19:41<5:08:32,  7.11s/it]
                                                          
{'loss': 0.6023, 'learning_rate': 1.1200485024840196e-05, 'epoch': 10.88}

 91%|█████████ | 25475/28080 [50:19:41<5:08:32,  7.11s/it]
 91%|█████████ | 25476/28080 [50:19:48<5:08:30,  7.11s/it]
                                                          
{'loss': 0.6078, 'learning_rate': 1.1191952185722498e-05, 'epoch': 10.88}

 91%|█████████ | 25476/28080 [50:19:48<5:08:30,  7.11s/it]
 91%|█████████ | 25477/28080 [50:19:55<5:06:41,  7.07s/it]
                                                          
{'loss': 0.6223, 'learning_rate': 1.1183422523699526e-05, 'epoch': 10.88}

 91%|█████████ | 25477/28080 [50:19:55<5:06:41,  7.07s/it]
 91%|█████████ | 25478/28080 [50:20:02<5:06:48,  7.07s/it]
                                                          
{'loss': 0.6032, 'learning_rate': 1.1174896038884775e-05, 'epoch': 10.88}

 91%|█████████ | 25478/28080 [50:20:02<5:06:48,  7.07s/it]
 91%|█████████ | 25479/28080 [50:20:09<5:08:11,  7.11s/it]
                                                          
{'loss': 0.5987, 'learning_rate': 1.1166372731391595e-05, 'epoch': 10.88}

 91%|█████████ | 25479/28080 [50:20:09<5:08:11,  7.11s/it]
 91%|█████████ | 25480/28080 [50:20:16<5:06:46,  7.08s/it]
                                                          
{'loss': 0.6143, 'learning_rate': 1.115785260133348e-05, 'epoch': 10.88}

 91%|█████████ | 25480/28080 [50:20:16<5:06:46,  7.08s/it]
 91%|█████████ | 25481/28080 [50:20:23<5:07:35,  7.10s/it]
                                                          
{'loss': 0.6161, 'learning_rate': 1.11493356488237e-05, 'epoch': 10.89}

 91%|█████████ | 25481/28080 [50:20:23<5:07:35,  7.10s/it]
 91%|█████████ | 25482/28080 [50:20:31<5:08:09,  7.12s/it]
                                                          
{'loss': 0.6115, 'learning_rate': 1.114082187397561e-05, 'epoch': 10.89}

 91%|█████████ | 25482/28080 [50:20:31<5:08:09,  7.12s/it]
 91%|█████████ | 25483/28080 [50:20:38<5:08:10,  7.12s/it]
                                                          
{'loss': 0.5954, 'learning_rate': 1.1132311276902508e-05, 'epoch': 10.89}

 91%|█████████ | 25483/28080 [50:20:38<5:08:10,  7.12s/it]
 91%|█████████ | 25484/28080 [50:20:45<5:08:38,  7.13s/it]
                                                          
{'loss': 0.584, 'learning_rate': 1.1123803857717551e-05, 'epoch': 10.89}

 91%|█████████ | 25484/28080 [50:20:45<5:08:38,  7.13s/it]
 91%|█████████ | 25485/28080 [50:20:52<5:07:28,  7.11s/it]
                                                          
{'loss': 0.6098, 'learning_rate': 1.1115299616533958e-05, 'epoch': 10.89}

 91%|█████████ | 25485/28080 [50:20:52<5:07:28,  7.11s/it]
 91%|█████████ | 25486/28080 [50:20:59<5:08:08,  7.13s/it]
                                                          
{'loss': 0.5754, 'learning_rate': 1.1106798553464804e-05, 'epoch': 10.89}

 91%|█████████ | 25486/28080 [50:20:59<5:08:08,  7.13s/it]
 91%|█████████ | 25487/28080 [50:21:06<5:09:11,  7.15s/it]
                                                          
{'loss': 0.5948, 'learning_rate': 1.10983006686233e-05, 'epoch': 10.89}

 91%|█████████ | 25487/28080 [50:21:06<5:09:11,  7.15s/it]
 91%|█████████ | 25488/28080 [50:21:13<5:07:15,  7.11s/it]
                                                          
{'loss': 0.6109, 'learning_rate': 1.1089805962122445e-05, 'epoch': 10.89}

 91%|█████████ | 25488/28080 [50:21:13<5:07:15,  7.11s/it]
 91%|█████████ | 25489/28080 [50:21:20<5:06:26,  7.10s/it]
                                                          
{'loss': 0.5827, 'learning_rate': 1.1081314434075258e-05, 'epoch': 10.89}

 91%|█████████ | 25489/28080 [50:21:20<5:06:26,  7.10s/it]
 91%|█████████ | 25490/28080 [50:21:28<5:06:29,  7.10s/it]
                                                          
{'loss': 0.5911, 'learning_rate': 1.1072826084594645e-05, 'epoch': 10.89}

 91%|█████████ | 25490/28080 [50:21:28<5:06:29,  7.10s/it]
 91%|█████████ | 25491/28080 [50:21:35<5:06:50,  7.11s/it]
                                                          
{'loss': 0.6064, 'learning_rate': 1.106434091379363e-05, 'epoch': 10.89}

 91%|█████████ | 25491/28080 [50:21:35<5:06:50,  7.11s/it]
 91%|█████████ | 25492/28080 [50:21:42<5:06:56,  7.12s/it]
                                                          
{'loss': 0.5925, 'learning_rate': 1.1055858921785094e-05, 'epoch': 10.89}

 91%|█████████ | 25492/28080 [50:21:42<5:06:56,  7.12s/it]
 91%|█████████ | 25493/28080 [50:21:49<5:06:42,  7.11s/it]
                                                          
{'loss': 0.5836, 'learning_rate': 1.1047380108681809e-05, 'epoch': 10.89}

 91%|█████████ | 25493/28080 [50:21:49<5:06:42,  7.11s/it]
 91%|█████████ | 25494/28080 [50:21:56<5:05:50,  7.10s/it]
                                                          
{'loss': 0.6341, 'learning_rate': 1.10389044745966e-05, 'epoch': 10.89}

 91%|█████████ | 25494/28080 [50:21:56<5:05:50,  7.10s/it]
 91%|█████████ | 25495/28080 [50:22:03<5:06:16,  7.11s/it]
                                                          
{'loss': 0.5986, 'learning_rate': 1.1030432019642295e-05, 'epoch': 10.89}

 91%|█████████ | 25495/28080 [50:22:03<5:06:16,  7.11s/it]
 91%|█████████ | 25496/28080 [50:22:10<5:06:07,  7.11s/it]
                                                          
{'loss': 0.6247, 'learning_rate': 1.1021962743931524e-05, 'epoch': 10.89}

 91%|█████████ | 25496/28080 [50:22:10<5:06:07,  7.11s/it]
 91%|█████████ | 25497/28080 [50:22:17<5:04:45,  7.08s/it]
                                                          
{'loss': 0.6251, 'learning_rate': 1.1013496647577059e-05, 'epoch': 10.89}

 91%|█████████ | 25497/28080 [50:22:17<5:04:45,  7.08s/it]
 91%|█████████ | 25498/28080 [50:22:24<5:05:34,  7.10s/it]
                                                          
{'loss': 0.5979, 'learning_rate': 1.1005033730691394e-05, 'epoch': 10.89}

 91%|█████████ | 25498/28080 [50:22:24<5:05:34,  7.10s/it]
 91%|█████████ | 25499/28080 [50:22:32<5:06:25,  7.12s/it]
                                                          
{'loss': 0.5862, 'learning_rate': 1.0996573993387244e-05, 'epoch': 10.89}

 91%|█████████ | 25499/28080 [50:22:32<5:06:25,  7.12s/it]
 91%|█████████ | 25500/28080 [50:22:39<5:07:22,  7.15s/it]
                                                          
{'loss': 0.6059, 'learning_rate': 1.0988117435777073e-05, 'epoch': 10.89}

 91%|█████████ | 25500/28080 [50:22:39<5:07:22,  7.15s/it]
 91%|█████████ | 25501/28080 [50:22:46<5:06:42,  7.14s/it]
                                                          
{'loss': 0.593, 'learning_rate': 1.097966405797346e-05, 'epoch': 10.89}

 91%|█████████ | 25501/28080 [50:22:46<5:06:42,  7.14s/it]
 91%|█████████ | 25502/28080 [50:22:53<5:07:48,  7.16s/it]
                                                          
{'loss': 0.5889, 'learning_rate': 1.0971213860088842e-05, 'epoch': 10.89}

 91%|█████████ | 25502/28080 [50:22:53<5:07:48,  7.16s/it]
 91%|█████████ | 25503/28080 [50:23:00<5:06:23,  7.13s/it]
                                                          
{'loss': 0.5932, 'learning_rate': 1.09627668422356e-05, 'epoch': 10.89}

 91%|█████████ | 25503/28080 [50:23:00<5:06:23,  7.13s/it]
 91%|█████████ | 25504/28080 [50:23:07<5:05:05,  7.11s/it]
                                                          
{'loss': 0.6023, 'learning_rate': 1.0954323004526145e-05, 'epoch': 10.9}

 91%|█████████ | 25504/28080 [50:23:07<5:05:05,  7.11s/it]
 91%|█████████ | 25505/28080 [50:23:14<5:05:12,  7.11s/it]
                                                          
{'loss': 0.6115, 'learning_rate': 1.0945882347072833e-05, 'epoch': 10.9}

 91%|█████████ | 25505/28080 [50:23:14<5:05:12,  7.11s/it]
 91%|█████████ | 25506/28080 [50:23:21<5:03:23,  7.07s/it]
                                                          
{'loss': 0.5988, 'learning_rate': 1.0937444869987933e-05, 'epoch': 10.9}

 91%|█████████ | 25506/28080 [50:23:21<5:03:23,  7.07s/it]
 91%|█████████ | 25507/28080 [50:23:28<5:03:10,  7.07s/it]
                                                          
{'loss': 0.6367, 'learning_rate': 1.0929010573383718e-05, 'epoch': 10.9}

 91%|█████████ | 25507/28080 [50:23:28<5:03:10,  7.07s/it]
 91%|█████████ | 25508/28080 [50:23:35<5:03:31,  7.08s/it]
                                                          
{'loss': 0.5785, 'learning_rate': 1.092057945737232e-05, 'epoch': 10.9}

 91%|█████████ | 25508/28080 [50:23:35<5:03:31,  7.08s/it]
 91%|█████████ | 25509/28080 [50:23:43<5:05:38,  7.13s/it]
                                                          
{'loss': 0.5928, 'learning_rate': 1.091215152206601e-05, 'epoch': 10.9}

 91%|█████████ | 25509/28080 [50:23:43<5:05:38,  7.13s/it]
 91%|█████████ | 25510/28080 [50:23:50<5:02:32,  7.06s/it]
                                                          
{'loss': 0.6046, 'learning_rate': 1.0903726767576894e-05, 'epoch': 10.9}

 91%|█████████ | 25510/28080 [50:23:50<5:02:32,  7.06s/it]
 91%|█████████ | 25511/28080 [50:23:57<5:03:09,  7.08s/it]
                                                          
{'loss': 0.5941, 'learning_rate': 1.0895305194017019e-05, 'epoch': 10.9}

 91%|█████████ | 25511/28080 [50:23:57<5:03:09,  7.08s/it]
 91%|█████████ | 25512/28080 [50:24:04<5:03:05,  7.08s/it]
                                                          
{'loss': 0.5871, 'learning_rate': 1.0886886801498435e-05, 'epoch': 10.9}

 91%|█████████ | 25512/28080 [50:24:04<5:03:05,  7.08s/it]
 91%|█████████ | 25513/28080 [50:24:11<5:03:18,  7.09s/it]
                                                          
{'loss': 0.5942, 'learning_rate': 1.087847159013311e-05, 'epoch': 10.9}

 91%|█████████ | 25513/28080 [50:24:11<5:03:18,  7.09s/it]
 91%|█████████ | 25514/28080 [50:24:18<5:04:19,  7.12s/it]
                                                          
{'loss': 0.5865, 'learning_rate': 1.0870059560033062e-05, 'epoch': 10.9}

 91%|█████████ | 25514/28080 [50:24:18<5:04:19,  7.12s/it]
 91%|█████████ | 25515/28080 [50:24:25<5:04:24,  7.12s/it]
                                                          
{'loss': 0.5857, 'learning_rate': 1.086165071131015e-05, 'epoch': 10.9}

 91%|█████████ | 25515/28080 [50:24:25<5:04:24,  7.12s/it]
 91%|█████████ | 25516/28080 [50:24:32<5:03:57,  7.11s/it]
                                                          
{'loss': 0.5913, 'learning_rate': 1.0853245044076282e-05, 'epoch': 10.9}

 91%|█████████ | 25516/28080 [50:24:32<5:03:57,  7.11s/it]
 91%|█████████ | 25517/28080 [50:24:39<5:03:21,  7.10s/it]
                                                          
{'loss': 0.6107, 'learning_rate': 1.0844842558443313e-05, 'epoch': 10.9}

 91%|█████████ | 25517/28080 [50:24:39<5:03:21,  7.10s/it]
 91%|█████████ | 25518/28080 [50:24:47<5:03:38,  7.11s/it]
                                                          
{'loss': 0.5971, 'learning_rate': 1.083644325452296e-05, 'epoch': 10.9}

 91%|█████████ | 25518/28080 [50:24:47<5:03:38,  7.11s/it]
 91%|█████████ | 25519/28080 [50:24:54<5:03:11,  7.10s/it]
                                                          
{'loss': 0.6104, 'learning_rate': 1.0828047132426966e-05, 'epoch': 10.9}

 91%|█████████ | 25519/28080 [50:24:54<5:03:11,  7.10s/it]
 91%|█████████ | 25520/28080 [50:25:01<5:02:51,  7.10s/it]
                                                          
{'loss': 0.6091, 'learning_rate': 1.0819654192267104e-05, 'epoch': 10.9}

 91%|█████████ | 25520/28080 [50:25:01<5:02:51,  7.10s/it]
 91%|█████████ | 25521/28080 [50:25:08<5:03:11,  7.11s/it]
                                                          
{'loss': 0.5788, 'learning_rate': 1.0811264434155005e-05, 'epoch': 10.9}

 91%|█████████ | 25521/28080 [50:25:08<5:03:11,  7.11s/it]
 91%|█████████ | 25522/28080 [50:25:15<5:03:15,  7.11s/it]
                                                          
{'loss': 0.5957, 'learning_rate': 1.0802877858202276e-05, 'epoch': 10.9}

 91%|█████████ | 25522/28080 [50:25:15<5:03:15,  7.11s/it]
 91%|█████████ | 25523/28080 [50:25:22<5:03:23,  7.12s/it]
                                                          
{'loss': 0.5974, 'learning_rate': 1.0794494464520437e-05, 'epoch': 10.9}

 91%|█████████ | 25523/28080 [50:25:22<5:03:23,  7.12s/it]
 91%|█████████ | 25524/28080 [50:25:29<5:03:43,  7.13s/it]
                                                          
{'loss': 0.6119, 'learning_rate': 1.0786114253221125e-05, 'epoch': 10.9}

 91%|█████████ | 25524/28080 [50:25:29<5:03:43,  7.13s/it]
 91%|█████████ | 25525/28080 [50:25:36<5:02:46,  7.11s/it]
                                                          
{'loss': 0.593, 'learning_rate': 1.0777737224415773e-05, 'epoch': 10.9}

 91%|█████████ | 25525/28080 [50:25:36<5:02:46,  7.11s/it]
 91%|█████████ | 25526/28080 [50:25:43<5:01:58,  7.09s/it]
                                                          
{'loss': 0.5795, 'learning_rate': 1.0769363378215852e-05, 'epoch': 10.9}

 91%|█████████ | 25526/28080 [50:25:43<5:01:58,  7.09s/it]
 91%|█████████ | 25527/28080 [50:25:50<5:02:06,  7.10s/it]
                                                          
{'loss': 0.5813, 'learning_rate': 1.0760992714732686e-05, 'epoch': 10.9}

 91%|█████████ | 25527/28080 [50:25:50<5:02:06,  7.10s/it]
 91%|█████████ | 25528/28080 [50:25:58<5:01:32,  7.09s/it]
                                                          
{'loss': 0.6039, 'learning_rate': 1.0752625234077746e-05, 'epoch': 10.91}

 91%|█████████ | 25528/28080 [50:25:58<5:01:32,  7.09s/it]
 91%|█████████ | 25529/28080 [50:26:05<5:02:15,  7.11s/it]
                                                          
{'loss': 0.5746, 'learning_rate': 1.07442609363623e-05, 'epoch': 10.91}

 91%|█████████ | 25529/28080 [50:26:05<5:02:15,  7.11s/it]
 91%|█████████ | 25530/28080 [50:26:12<5:00:56,  7.08s/it]
                                                          
{'loss': 0.618, 'learning_rate': 1.0735899821697649e-05, 'epoch': 10.91}

 91%|█████████ | 25530/28080 [50:26:12<5:00:56,  7.08s/it]
 91%|█████████ | 25531/28080 [50:26:19<5:01:10,  7.09s/it]
                                                          
{'loss': 0.6247, 'learning_rate': 1.0727541890195008e-05, 'epoch': 10.91}

 91%|█████████ | 25531/28080 [50:26:19<5:01:10,  7.09s/it]
 91%|█████████ | 25532/28080 [50:26:26<5:01:35,  7.10s/it]
                                                          
{'loss': 0.6151, 'learning_rate': 1.0719187141965597e-05, 'epoch': 10.91}

 91%|█████████ | 25532/28080 [50:26:26<5:01:35,  7.10s/it]
 91%|█████████ | 25533/28080 [50:26:33<5:01:55,  7.11s/it]
                                                          
{'loss': 0.6029, 'learning_rate': 1.0710835577120493e-05, 'epoch': 10.91}

 91%|█████████ | 25533/28080 [50:26:33<5:01:55,  7.11s/it]
 91%|█████████ | 25534/28080 [50:26:40<5:02:38,  7.13s/it]
                                                          
{'loss': 0.6054, 'learning_rate': 1.070248719577091e-05, 'epoch': 10.91}

 91%|█████████ | 25534/28080 [50:26:40<5:02:38,  7.13s/it]
 91%|█████████ | 25535/28080 [50:26:47<5:00:33,  7.09s/it]
                                                          
{'loss': 0.6073, 'learning_rate': 1.0694141998027873e-05, 'epoch': 10.91}

 91%|█████████ | 25535/28080 [50:26:47<5:00:33,  7.09s/it]
 91%|█████████ | 25536/28080 [50:26:54<4:59:29,  7.06s/it]
                                                          
{'loss': 0.59, 'learning_rate': 1.0685799984002404e-05, 'epoch': 10.91}

 91%|█████████ | 25536/28080 [50:26:54<4:59:29,  7.06s/it]
 91%|█████████ | 25537/28080 [50:27:01<4:59:13,  7.06s/it]
                                                          
{'loss': 0.5953, 'learning_rate': 1.067746115380544e-05, 'epoch': 10.91}

 91%|█████████ | 25537/28080 [50:27:01<4:59:13,  7.06s/it]
 91%|█████████ | 25538/28080 [50:27:08<5:00:41,  7.10s/it]
                                                          
{'loss': 0.5897, 'learning_rate': 1.066912550754795e-05, 'epoch': 10.91}

 91%|█████████ | 25538/28080 [50:27:08<5:00:41,  7.10s/it]
 91%|█████████ | 25539/28080 [50:27:16<5:00:14,  7.09s/it]
                                                          
{'loss': 0.5962, 'learning_rate': 1.06607930453409e-05, 'epoch': 10.91}

 91%|█████████ | 25539/28080 [50:27:16<5:00:14,  7.09s/it]
 91%|█████████ | 25540/28080 [50:27:23<5:01:01,  7.11s/it]
                                                          
{'loss': 0.5852, 'learning_rate': 1.0652463767295062e-05, 'epoch': 10.91}

 91%|█████████ | 25540/28080 [50:27:23<5:01:01,  7.11s/it]
 91%|█████████ | 25541/28080 [50:27:30<5:00:54,  7.11s/it]
                                                          
{'loss': 0.6179, 'learning_rate': 1.0644137673521265e-05, 'epoch': 10.91}

 91%|█████████ | 25541/28080 [50:27:30<5:00:54,  7.11s/it]
 91%|█████████ | 25542/28080 [50:27:37<5:00:01,  7.09s/it]
                                                          
{'loss': 0.596, 'learning_rate': 1.0635814764130252e-05, 'epoch': 10.91}

 91%|█████████ | 25542/28080 [50:27:37<5:00:01,  7.09s/it]
 91%|█████████ | 25543/28080 [50:27:44<5:01:23,  7.13s/it]
                                                          
{'loss': 0.5959, 'learning_rate': 1.0627495039232825e-05, 'epoch': 10.91}

 91%|█████████ | 25543/28080 [50:27:44<5:01:23,  7.13s/it]
 91%|█████████ | 25544/28080 [50:27:51<5:01:35,  7.14s/it]
                                                          
{'loss': 0.6245, 'learning_rate': 1.061917849893962e-05, 'epoch': 10.91}

 91%|█████████ | 25544/28080 [50:27:51<5:01:35,  7.14s/it]
 91%|█████████ | 25545/28080 [50:27:58<5:01:49,  7.14s/it]
                                                          
{'loss': 0.6018, 'learning_rate': 1.061086514336132e-05, 'epoch': 10.91}

 91%|█████████ | 25545/28080 [50:27:58<5:01:49,  7.14s/it]
 91%|█████████ | 25546/28080 [50:28:06<5:01:07,  7.13s/it]
                                                          
{'loss': 0.5863, 'learning_rate': 1.0602554972608453e-05, 'epoch': 10.91}

 91%|█████████ | 25546/28080 [50:28:06<5:01:07,  7.13s/it]
 91%|█████████ | 25547/28080 [50:28:13<5:00:56,  7.13s/it]
                                                          
{'loss': 0.6057, 'learning_rate': 1.0594247986791621e-05, 'epoch': 10.91}

 91%|█████████ | 25547/28080 [50:28:13<5:00:56,  7.13s/it]
 91%|█████████ | 25548/28080 [50:28:20<5:00:29,  7.12s/it]
                                                          
{'loss': 0.6029, 'learning_rate': 1.0585944186021351e-05, 'epoch': 10.91}

 91%|█████████ | 25548/28080 [50:28:20<5:00:29,  7.12s/it]
 91%|█████████ | 25549/28080 [50:28:27<5:00:48,  7.13s/it]
                                                          
{'loss': 0.5984, 'learning_rate': 1.0577643570408107e-05, 'epoch': 10.91}

 91%|█████████ | 25549/28080 [50:28:27<5:00:48,  7.13s/it]
 91%|█████████ | 25550/28080 [50:28:34<5:01:07,  7.14s/it]
                                                          
{'loss': 0.5867, 'learning_rate': 1.056934614006233e-05, 'epoch': 10.91}

 91%|█████████ | 25550/28080 [50:28:34<5:01:07,  7.14s/it]
 91%|█████████ | 25551/28080 [50:28:41<5:00:31,  7.13s/it]
                                                          
{'loss': 0.5848, 'learning_rate': 1.0561051895094376e-05, 'epoch': 10.92}

 91%|█████████ | 25551/28080 [50:28:41<5:00:31,  7.13s/it]
 91%|█████████ | 25552/28080 [50:28:48<5:00:16,  7.13s/it]
                                                          
{'loss': 0.5988, 'learning_rate': 1.05527608356146e-05, 'epoch': 10.92}

 91%|█████████ | 25552/28080 [50:28:48<5:00:16,  7.13s/it]
 91%|█████████ | 25553/28080 [50:28:55<5:01:09,  7.15s/it]
                                                          
{'loss': 0.6071, 'learning_rate': 1.0544472961733332e-05, 'epoch': 10.92}

 91%|█████████ | 25553/28080 [50:28:55<5:01:09,  7.15s/it]
 91%|█████████ | 25554/28080 [50:29:03<5:00:35,  7.14s/it]
                                                          
{'loss': 0.6115, 'learning_rate': 1.0536188273560844e-05, 'epoch': 10.92}

 91%|█████████ | 25554/28080 [50:29:03<5:00:35,  7.14s/it]
 91%|█████████ | 25555/28080 [50:29:10<5:00:20,  7.14s/it]
                                                          
{'loss': 0.5854, 'learning_rate': 1.0527906771207296e-05, 'epoch': 10.92}

 91%|█████████ | 25555/28080 [50:29:10<5:00:20,  7.14s/it]
 91%|█████████ | 25556/28080 [50:29:17<4:58:57,  7.11s/it]
                                                          
{'loss': 0.5951, 'learning_rate': 1.051962845478288e-05, 'epoch': 10.92}

 91%|█████████ | 25556/28080 [50:29:17<4:58:57,  7.11s/it]
 91%|█████████ | 25557/28080 [50:29:24<4:58:48,  7.11s/it]
                                                          
{'loss': 0.6151, 'learning_rate': 1.0511353324397788e-05, 'epoch': 10.92}

 91%|█████████ | 25557/28080 [50:29:24<4:58:48,  7.11s/it]
 91%|█████████ | 25558/28080 [50:29:31<4:59:50,  7.13s/it]
                                                          
{'loss': 0.5989, 'learning_rate': 1.0503081380162038e-05, 'epoch': 10.92}

 91%|█████████ | 25558/28080 [50:29:31<4:59:50,  7.13s/it]
 91%|█████████ | 25559/28080 [50:29:38<4:59:42,  7.13s/it]
                                                          
{'loss': 0.5888, 'learning_rate': 1.0494812622185796e-05, 'epoch': 10.92}

 91%|█████████ | 25559/28080 [50:29:38<4:59:42,  7.13s/it]
 91%|█████████ | 25560/28080 [50:29:45<4:59:02,  7.12s/it]
                                                          
{'loss': 0.5915, 'learning_rate': 1.0486547050578943e-05, 'epoch': 10.92}

 91%|█████████ | 25560/28080 [50:29:45<4:59:02,  7.12s/it]
 91%|█████████ | 25561/28080 [50:29:52<4:59:21,  7.13s/it]
                                                          
{'loss': 0.5984, 'learning_rate': 1.0478284665451449e-05, 'epoch': 10.92}

 91%|█████████ | 25561/28080 [50:29:52<4:59:21,  7.13s/it]
 91%|█████████ | 25562/28080 [50:29:59<4:57:58,  7.10s/it]
                                                          
{'loss': 0.6083, 'learning_rate': 1.0470025466913307e-05, 'epoch': 10.92}

 91%|█████████ | 25562/28080 [50:29:59<4:57:58,  7.10s/it]
 91%|█████████ | 25563/28080 [50:30:07<4:58:09,  7.11s/it]
                                                          
{'loss': 0.5909, 'learning_rate': 1.0461769455074349e-05, 'epoch': 10.92}

 91%|█████████ | 25563/28080 [50:30:07<4:58:09,  7.11s/it]
 91%|█████████ | 25564/28080 [50:30:14<4:58:37,  7.12s/it]
                                                          
{'loss': 0.5759, 'learning_rate': 1.0453516630044458e-05, 'epoch': 10.92}

 91%|█████████ | 25564/28080 [50:30:14<4:58:37,  7.12s/it]
 91%|█████████ | 25565/28080 [50:30:21<4:57:45,  7.10s/it]
                                                          
{'loss': 0.5787, 'learning_rate': 1.0445266991933405e-05, 'epoch': 10.92}

 91%|█████████ | 25565/28080 [50:30:21<4:57:45,  7.10s/it]
 91%|█████████ | 25566/28080 [50:30:28<4:58:36,  7.13s/it]
                                                          
{'loss': 0.61, 'learning_rate': 1.0437020540850911e-05, 'epoch': 10.92}

 91%|█████████ | 25566/28080 [50:30:28<4:58:36,  7.13s/it]
 91%|█████████ | 25567/28080 [50:30:35<4:58:24,  7.12s/it]
                                                          
{'loss': 0.6057, 'learning_rate': 1.042877727690672e-05, 'epoch': 10.92}

 91%|█████████ | 25567/28080 [50:30:35<4:58:24,  7.12s/it]
 91%|█████████ | 25568/28080 [50:30:42<4:58:23,  7.13s/it]
                                                          
{'loss': 0.589, 'learning_rate': 1.0420537200210522e-05, 'epoch': 10.92}

 91%|█████████ | 25568/28080 [50:30:42<4:58:23,  7.13s/it]
 91%|█████████ | 25569/28080 [50:30:49<4:58:45,  7.14s/it]
                                                          
{'loss': 0.6151, 'learning_rate': 1.0412300310871897e-05, 'epoch': 10.92}

 91%|█████████ | 25569/28080 [50:30:49<4:58:45,  7.14s/it]
 91%|█████████ | 25570/28080 [50:30:57<4:59:02,  7.15s/it]
                                                          
{'loss': 0.585, 'learning_rate': 1.0404066609000451e-05, 'epoch': 10.92}

 91%|█████████ | 25570/28080 [50:30:57<4:59:02,  7.15s/it]
 91%|█████████ | 25571/28080 [50:31:04<4:58:26,  7.14s/it]
                                                          
{'loss': 0.5951, 'learning_rate': 1.0395836094705707e-05, 'epoch': 10.92}

 91%|█████████ | 25571/28080 [50:31:04<4:58:26,  7.14s/it]
 91%|█████████ | 25572/28080 [50:31:11<4:56:50,  7.10s/it]
                                                          
{'loss': 0.6033, 'learning_rate': 1.038760876809719e-05, 'epoch': 10.92}

 91%|█████████ | 25572/28080 [50:31:11<4:56:50,  7.10s/it]
 91%|█████████ | 25573/28080 [50:31:18<4:57:42,  7.13s/it]
                                                          
{'loss': 0.5805, 'learning_rate': 1.0379384629284367e-05, 'epoch': 10.92}

 91%|█████████ | 25573/28080 [50:31:18<4:57:42,  7.13s/it]
 91%|█████████ | 25574/28080 [50:31:25<4:58:25,  7.15s/it]
                                                          
{'loss': 0.5986, 'learning_rate': 1.0371163678376621e-05, 'epoch': 10.92}

 91%|█████████ | 25574/28080 [50:31:25<4:58:25,  7.15s/it]
 91%|█████████ | 25575/28080 [50:31:32<4:57:51,  7.13s/it]
                                                          
{'loss': 0.5885, 'learning_rate': 1.0362945915483286e-05, 'epoch': 10.93}

 91%|█████████ | 25575/28080 [50:31:32<4:57:51,  7.13s/it]
 91%|█████████ | 25576/28080 [50:31:39<4:56:15,  7.10s/it]
                                                          
{'loss': 0.6231, 'learning_rate': 1.035473134071377e-05, 'epoch': 10.93}

 91%|█████████ | 25576/28080 [50:31:39<4:56:15,  7.10s/it]
 91%|█████████ | 25577/28080 [50:31:46<4:54:38,  7.06s/it]
                                                          
{'loss': 0.5902, 'learning_rate': 1.0346519954177291e-05, 'epoch': 10.93}

 91%|█████████ | 25577/28080 [50:31:46<4:54:38,  7.06s/it]
 91%|█████████ | 25578/28080 [50:31:53<4:55:36,  7.09s/it]
                                                          
{'loss': 0.58, 'learning_rate': 1.0338311755983183e-05, 'epoch': 10.93}

 91%|█████████ | 25578/28080 [50:31:53<4:55:36,  7.09s/it]
 91%|█████████ | 25579/28080 [50:32:00<4:55:52,  7.10s/it]
                                                          
{'loss': 0.608, 'learning_rate': 1.0330106746240574e-05, 'epoch': 10.93}

 91%|█████████ | 25579/28080 [50:32:00<4:55:52,  7.10s/it]
 91%|█████████ | 25580/28080 [50:32:07<4:54:54,  7.08s/it]
                                                          
{'loss': 0.6081, 'learning_rate': 1.0321904925058634e-05, 'epoch': 10.93}

 91%|█████████ | 25580/28080 [50:32:07<4:54:54,  7.08s/it]
 91%|█████████ | 25581/28080 [50:32:15<4:55:10,  7.09s/it]
                                                          
{'loss': 0.58, 'learning_rate': 1.0313706292546465e-05, 'epoch': 10.93}

 91%|█████████ | 25581/28080 [50:32:15<4:55:10,  7.09s/it]
 91%|█████████ | 25582/28080 [50:32:22<4:55:17,  7.09s/it]
                                                          
{'loss': 0.5845, 'learning_rate': 1.0305510848813204e-05, 'epoch': 10.93}

 91%|█████████ | 25582/28080 [50:32:22<4:55:17,  7.09s/it]
 91%|█████████ | 25583/28080 [50:32:29<4:56:01,  7.11s/it]
                                                          
{'loss': 0.6108, 'learning_rate': 1.0297318593967819e-05, 'epoch': 10.93}

 91%|█████████ | 25583/28080 [50:32:29<4:56:01,  7.11s/it]
 91%|█████████ | 25584/28080 [50:32:36<4:56:14,  7.12s/it]
                                                          
{'loss': 0.5993, 'learning_rate': 1.0289129528119334e-05, 'epoch': 10.93}

 91%|█████████ | 25584/28080 [50:32:36<4:56:14,  7.12s/it]
 91%|█████████ | 25585/28080 [50:32:43<4:55:17,  7.10s/it]
                                                          
{'loss': 0.6085, 'learning_rate': 1.028094365137669e-05, 'epoch': 10.93}

 91%|█████████ | 25585/28080 [50:32:43<4:55:17,  7.10s/it]
 91%|█████████ | 25586/28080 [50:32:50<4:57:36,  7.16s/it]
                                                          
{'loss': 0.5918, 'learning_rate': 1.0272760963848743e-05, 'epoch': 10.93}

 91%|█████████ | 25586/28080 [50:32:50<4:57:36,  7.16s/it]
 91%|█████████ | 25587/28080 [50:32:57<4:57:09,  7.15s/it]
                                                          
{'loss': 0.5895, 'learning_rate': 1.0264581465644434e-05, 'epoch': 10.93}

 91%|█████████ | 25587/28080 [50:32:57<4:57:09,  7.15s/it]
 91%|█████████ | 25588/28080 [50:33:04<4:55:06,  7.11s/it]
                                                          
{'loss': 0.5922, 'learning_rate': 1.0256405156872566e-05, 'epoch': 10.93}

 91%|█████████ | 25588/28080 [50:33:04<4:55:06,  7.11s/it]
 91%|█████████ | 25589/28080 [50:33:12<4:56:02,  7.13s/it]
                                                          
{'loss': 0.609, 'learning_rate': 1.0248232037641885e-05, 'epoch': 10.93}

 91%|█████████ | 25589/28080 [50:33:12<4:56:02,  7.13s/it]
 91%|█████████ | 25590/28080 [50:33:19<4:56:01,  7.13s/it]
                                                          
{'loss': 0.6102, 'learning_rate': 1.024006210806111e-05, 'epoch': 10.93}

 91%|█████████ | 25590/28080 [50:33:19<4:56:01,  7.13s/it]
 91%|█████████ | 25591/28080 [50:33:26<4:55:35,  7.13s/it]
                                                          
{'loss': 0.5844, 'learning_rate': 1.0231895368238986e-05, 'epoch': 10.93}

 91%|█████████ | 25591/28080 [50:33:26<4:55:35,  7.13s/it]
 91%|█████████ | 25592/28080 [50:33:33<4:54:18,  7.10s/it]
                                                          
{'loss': 0.6228, 'learning_rate': 1.0223731818284093e-05, 'epoch': 10.93}

 91%|█████████ | 25592/28080 [50:33:33<4:54:18,  7.10s/it]
 91%|█████████ | 25593/28080 [50:33:40<4:53:53,  7.09s/it]
                                                          
{'loss': 0.6021, 'learning_rate': 1.0215571458305179e-05, 'epoch': 10.93}

 91%|█████████ | 25593/28080 [50:33:40<4:53:53,  7.09s/it]
 91%|█████████ | 25594/28080 [50:33:47<4:53:29,  7.08s/it]
                                                          
{'loss': 0.5888, 'learning_rate': 1.0207414288410627e-05, 'epoch': 10.93}

 91%|█████████ | 25594/28080 [50:33:47<4:53:29,  7.08s/it]
 91%|█████████ | 25595/28080 [50:33:54<4:53:42,  7.09s/it]
                                                          
{'loss': 0.6021, 'learning_rate': 1.0199260308709102e-05, 'epoch': 10.93}

 91%|█████████ | 25595/28080 [50:33:54<4:53:42,  7.09s/it]
 91%|█████████ | 25596/28080 [50:34:01<4:53:48,  7.10s/it]
                                                          
{'loss': 0.5955, 'learning_rate': 1.019110951930899e-05, 'epoch': 10.93}

 91%|█████████ | 25596/28080 [50:34:01<4:53:48,  7.10s/it]
 91%|█████████ | 25597/28080 [50:34:08<4:54:24,  7.11s/it]
                                                          
{'loss': 0.595, 'learning_rate': 1.0182961920318784e-05, 'epoch': 10.93}

 91%|█████████ | 25597/28080 [50:34:08<4:54:24,  7.11s/it]
 91%|█████████ | 25598/28080 [50:34:16<4:54:08,  7.11s/it]
                                                          
{'loss': 0.6224, 'learning_rate': 1.0174817511846873e-05, 'epoch': 10.94}

 91%|█████████ | 25598/28080 [50:34:16<4:54:08,  7.11s/it]
 91%|█████████ | 25599/28080 [50:34:23<4:54:43,  7.13s/it]
                                                          
{'loss': 0.6249, 'learning_rate': 1.0166676294001614e-05, 'epoch': 10.94}

 91%|█████████ | 25599/28080 [50:34:23<4:54:43,  7.13s/it]
 91%|█████████ | 25600/28080 [50:34:30<4:53:10,  7.09s/it]
                                                          
{'loss': 0.5799, 'learning_rate': 1.0158538266891254e-05, 'epoch': 10.94}

 91%|█████████ | 25600/28080 [50:34:30<4:53:10,  7.09s/it]
 91%|█████████ | 25601/28080 [50:34:37<4:53:03,  7.09s/it]
                                                          
{'loss': 0.5855, 'learning_rate': 1.0150403430624149e-05, 'epoch': 10.94}

 91%|█████████ | 25601/28080 [50:34:37<4:53:03,  7.09s/it]
 91%|█████████ | 25602/28080 [50:34:44<4:52:28,  7.08s/it]
                                                          
{'loss': 0.6218, 'learning_rate': 1.0142271785308493e-05, 'epoch': 10.94}

 91%|█████████ | 25602/28080 [50:34:44<4:52:28,  7.08s/it]
 91%|█████████ | 25603/28080 [50:34:51<4:52:12,  7.08s/it]
                                                          
{'loss': 0.6002, 'learning_rate': 1.0134143331052476e-05, 'epoch': 10.94}

 91%|█████████ | 25603/28080 [50:34:51<4:52:12,  7.08s/it]
 91%|█████████ | 25604/28080 [50:34:58<4:51:45,  7.07s/it]
                                                          
{'loss': 0.6063, 'learning_rate': 1.0126018067964177e-05, 'epoch': 10.94}

 91%|█████████ | 25604/28080 [50:34:58<4:51:45,  7.07s/it]
 91%|█████████ | 25605/28080 [50:35:05<4:51:22,  7.06s/it]
                                                          
{'loss': 0.611, 'learning_rate': 1.0117895996151788e-05, 'epoch': 10.94}

 91%|█████████ | 25605/28080 [50:35:05<4:51:22,  7.06s/it]
 91%|█████████ | 25606/28080 [50:35:12<4:51:29,  7.07s/it]
                                                          
{'loss': 0.5947, 'learning_rate': 1.010977711572328e-05, 'epoch': 10.94}

 91%|█████████ | 25606/28080 [50:35:12<4:51:29,  7.07s/it]
 91%|█████████ | 25607/28080 [50:35:19<4:51:25,  7.07s/it]
                                                          
{'loss': 0.6043, 'learning_rate': 1.0101661426786756e-05, 'epoch': 10.94}

 91%|█████████ | 25607/28080 [50:35:19<4:51:25,  7.07s/it]
 91%|█████████ | 25608/28080 [50:35:26<4:50:02,  7.04s/it]
                                                          
{'loss': 0.6228, 'learning_rate': 1.009354892945008e-05, 'epoch': 10.94}

 91%|█████████ | 25608/28080 [50:35:26<4:50:02,  7.04s/it]
 91%|█████████ | 25609/28080 [50:35:33<4:50:55,  7.06s/it]
                                                          
{'loss': 0.5867, 'learning_rate': 1.0085439623821275e-05, 'epoch': 10.94}

 91%|█████████ | 25609/28080 [50:35:33<4:50:55,  7.06s/it]
 91%|█████████ | 25610/28080 [50:35:40<4:50:26,  7.06s/it]
                                                          
{'loss': 0.6167, 'learning_rate': 1.0077333510008197e-05, 'epoch': 10.94}

 91%|█████████ | 25610/28080 [50:35:40<4:50:26,  7.06s/it]
 91%|█████████ | 25611/28080 [50:35:47<4:51:22,  7.08s/it]
                                                          
{'loss': 0.6085, 'learning_rate': 1.006923058811865e-05, 'epoch': 10.94}

 91%|█████████ | 25611/28080 [50:35:47<4:51:22,  7.08s/it]
 91%|█████████ | 25612/28080 [50:35:55<4:52:39,  7.12s/it]
                                                          
{'loss': 0.5842, 'learning_rate': 1.006113085826052e-05, 'epoch': 10.94}

 91%|█████████ | 25612/28080 [50:35:55<4:52:39,  7.12s/it]
 91%|█████████ | 25613/28080 [50:36:02<4:53:08,  7.13s/it]
                                                          
{'loss': 0.5986, 'learning_rate': 1.005303432054147e-05, 'epoch': 10.94}

 91%|█████████ | 25613/28080 [50:36:02<4:53:08,  7.13s/it]
 91%|█████████ | 25614/28080 [50:36:09<4:51:56,  7.10s/it]
                                                          
{'loss': 0.5961, 'learning_rate': 1.004494097506925e-05, 'epoch': 10.94}

 91%|█████████ | 25614/28080 [50:36:09<4:51:56,  7.10s/it]
 91%|█████████ | 25615/28080 [50:36:16<4:51:01,  7.08s/it]
                                                          
{'loss': 0.6014, 'learning_rate': 1.0036850821951548e-05, 'epoch': 10.94}

 91%|█████████ | 25615/28080 [50:36:16<4:51:01,  7.08s/it]
 91%|█████████ | 25616/28080 [50:36:23<4:51:55,  7.11s/it]
                                                          
{'loss': 0.5958, 'learning_rate': 1.0028763861296003e-05, 'epoch': 10.94}

 91%|█████████ | 25616/28080 [50:36:23<4:51:55,  7.11s/it]
 91%|█████████ | 25617/28080 [50:36:30<4:52:11,  7.12s/it]
                                                          
{'loss': 0.6054, 'learning_rate': 1.0020680093210193e-05, 'epoch': 10.94}

 91%|█████████ | 25617/28080 [50:36:30<4:52:11,  7.12s/it]
 91%|█████████ | 25618/28080 [50:36:37<4:51:41,  7.11s/it]
                                                          
{'loss': 0.6019, 'learning_rate': 1.0012599517801673e-05, 'epoch': 10.94}

 91%|█████████ | 25618/28080 [50:36:37<4:51:41,  7.11s/it]
 91%|█████████ | 25619/28080 [50:36:44<4:50:58,  7.09s/it]
                                                          
{'loss': 0.6106, 'learning_rate': 1.0004522135177885e-05, 'epoch': 10.94}

 91%|█████████ | 25619/28080 [50:36:44<4:50:58,  7.09s/it]
 91%|█████████ | 25620/28080 [50:36:51<4:50:21,  7.08s/it]
                                                          
{'loss': 0.614, 'learning_rate': 9.996447945446407e-06, 'epoch': 10.94}

 91%|█████████ | 25620/28080 [50:36:51<4:50:21,  7.08s/it]
 91%|█████████ | 25621/28080 [50:36:59<4:51:13,  7.11s/it]
                                                          
{'loss': 0.5848, 'learning_rate': 9.988376948714545e-06, 'epoch': 10.95}

 91%|█████████ | 25621/28080 [50:36:59<4:51:13,  7.11s/it]
 91%|█████████ | 25622/28080 [50:37:06<4:51:11,  7.11s/it]
                                                          
{'loss': 0.5936, 'learning_rate': 9.980309145089738e-06, 'epoch': 10.95}

 91%|█████████ | 25622/28080 [50:37:06<4:51:11,  7.11s/it]
 91%|█████████▏| 25623/28080 [50:37:13<4:50:56,  7.10s/it]
                                                          
{'loss': 0.5954, 'learning_rate': 9.972244534679292e-06, 'epoch': 10.95}

 91%|█████████▏| 25623/28080 [50:37:13<4:50:56,  7.10s/it]
 91%|█████████▏| 25624/28080 [50:37:20<4:51:31,  7.12s/it]
                                                          
{'loss': 0.5998, 'learning_rate': 9.964183117590537e-06, 'epoch': 10.95}

 91%|█████████▏| 25624/28080 [50:37:20<4:51:31,  7.12s/it]
 91%|█████████▏| 25625/28080 [50:37:27<4:50:38,  7.10s/it]
                                                          
{'loss': 0.5998, 'learning_rate': 9.956124893930634e-06, 'epoch': 10.95}

 91%|█████████▏| 25625/28080 [50:37:27<4:50:38,  7.10s/it]
 91%|█████████▏| 25626/28080 [50:37:34<4:51:18,  7.12s/it]
                                                          
{'loss': 0.5965, 'learning_rate': 9.94806986380689e-06, 'epoch': 10.95}

 91%|█████████▏| 25626/28080 [50:37:34<4:51:18,  7.12s/it]
 91%|█████████▏| 25627/28080 [50:37:41<4:51:15,  7.12s/it]
                                                          
{'loss': 0.5738, 'learning_rate': 9.940018027326442e-06, 'epoch': 10.95}

 91%|█████████▏| 25627/28080 [50:37:41<4:51:15,  7.12s/it]
 91%|█████████▏| 25628/28080 [50:37:48<4:51:44,  7.14s/it]
                                                          
{'loss': 0.594, 'learning_rate': 9.931969384596395e-06, 'epoch': 10.95}

 91%|█████████▏| 25628/28080 [50:37:48<4:51:44,  7.14s/it]
 91%|█████████▏| 25629/28080 [50:37:56<4:51:11,  7.13s/it]
                                                          
{'loss': 0.5825, 'learning_rate': 9.923923935723805e-06, 'epoch': 10.95}

 91%|█████████▏| 25629/28080 [50:37:56<4:51:11,  7.13s/it]
 91%|█████████▏| 25630/28080 [50:38:03<4:50:26,  7.11s/it]
                                                          
{'loss': 0.5977, 'learning_rate': 9.915881680815753e-06, 'epoch': 10.95}

 91%|█████████▏| 25630/28080 [50:38:03<4:50:26,  7.11s/it]
 91%|█████████▏| 25631/28080 [50:38:10<4:50:53,  7.13s/it]
                                                          
{'loss': 0.5927, 'learning_rate': 9.907842619979235e-06, 'epoch': 10.95}

 91%|█████████▏| 25631/28080 [50:38:10<4:50:53,  7.13s/it]
 91%|█████████▏| 25632/28080 [50:38:17<4:51:00,  7.13s/it]
                                                          
{'loss': 0.5969, 'learning_rate': 9.899806753321167e-06, 'epoch': 10.95}

 91%|█████████▏| 25632/28080 [50:38:17<4:51:00,  7.13s/it]
 91%|█████████▏| 25633/28080 [50:38:24<4:50:33,  7.12s/it]
                                                          
{'loss': 0.5955, 'learning_rate': 9.891774080948435e-06, 'epoch': 10.95}

 91%|█████████▏| 25633/28080 [50:38:24<4:50:33,  7.12s/it]
 91%|█████████▏| 25634/28080 [50:38:31<4:50:16,  7.12s/it]
                                                          
{'loss': 0.6086, 'learning_rate': 9.883744602967981e-06, 'epoch': 10.95}

 91%|█████████▏| 25634/28080 [50:38:31<4:50:16,  7.12s/it]
 91%|█████████▏| 25635/28080 [50:38:38<4:50:45,  7.14s/it]
                                                          
{'loss': 0.6239, 'learning_rate': 9.875718319486583e-06, 'epoch': 10.95}

 91%|█████████▏| 25635/28080 [50:38:38<4:50:45,  7.14s/it]
 91%|█████████▏| 25636/28080 [50:38:45<4:49:45,  7.11s/it]
                                                          
{'loss': 0.5956, 'learning_rate': 9.86769523061104e-06, 'epoch': 10.95}

 91%|█████████▏| 25636/28080 [50:38:45<4:49:45,  7.11s/it]
 91%|█████████▏| 25637/28080 [50:38:53<4:49:24,  7.11s/it]
                                                          
{'loss': 0.6003, 'learning_rate': 9.859675336448076e-06, 'epoch': 10.95}

 91%|█████████▏| 25637/28080 [50:38:53<4:49:24,  7.11s/it]
 91%|█████████▏| 25638/28080 [50:39:00<4:50:19,  7.13s/it]
                                                          
{'loss': 0.5989, 'learning_rate': 9.851658637104355e-06, 'epoch': 10.95}

 91%|█████████▏| 25638/28080 [50:39:00<4:50:19,  7.13s/it]
 91%|█████████▏| 25639/28080 [50:39:07<4:50:13,  7.13s/it]
                                                          
{'loss': 0.6185, 'learning_rate': 9.843645132686623e-06, 'epoch': 10.95}

 91%|█████████▏| 25639/28080 [50:39:07<4:50:13,  7.13s/it]
 91%|█████████▏| 25640/28080 [50:39:14<4:50:11,  7.14s/it]
                                                          
{'loss': 0.6072, 'learning_rate': 9.835634823301382e-06, 'epoch': 10.95}

 91%|█████████▏| 25640/28080 [50:39:14<4:50:11,  7.14s/it]
 91%|█████████▏| 25641/28080 [50:39:21<4:48:28,  7.10s/it]
                                                          
{'loss': 0.6166, 'learning_rate': 9.827627709055349e-06, 'epoch': 10.95}

 91%|█████████▏| 25641/28080 [50:39:21<4:48:28,  7.10s/it]
 91%|█████████▏| 25642/28080 [50:39:28<4:47:20,  7.07s/it]
                                                          
{'loss': 0.6031, 'learning_rate': 9.819623790054855e-06, 'epoch': 10.95}

 91%|█████████▏| 25642/28080 [50:39:28<4:47:20,  7.07s/it]
 91%|█████████▏| 25643/28080 [50:39:35<4:46:47,  7.06s/it]
                                                          
{'loss': 0.6023, 'learning_rate': 9.811623066406538e-06, 'epoch': 10.95}

 91%|█████████▏| 25643/28080 [50:39:35<4:46:47,  7.06s/it]
 91%|█████████▏| 25644/28080 [50:39:42<4:47:56,  7.09s/it]
                                                          
{'loss': 0.5869, 'learning_rate': 9.80362553821676e-06, 'epoch': 10.95}

 91%|█████████▏| 25644/28080 [50:39:42<4:47:56,  7.09s/it]
 91%|█████████▏| 25645/28080 [50:39:49<4:48:21,  7.11s/it]
                                                          
{'loss': 0.6014, 'learning_rate': 9.795631205591959e-06, 'epoch': 10.96}

 91%|█████████▏| 25645/28080 [50:39:49<4:48:21,  7.11s/it]
 91%|█████████▏| 25646/28080 [50:39:56<4:48:46,  7.12s/it]
                                                          
{'loss': 0.609, 'learning_rate': 9.787640068638499e-06, 'epoch': 10.96}

 91%|█████████▏| 25646/28080 [50:39:57<4:48:46,  7.12s/it]
 91%|█████████▏| 25647/28080 [50:40:04<4:48:53,  7.12s/it]
                                                          
{'loss': 0.5743, 'learning_rate': 9.77965212746268e-06, 'epoch': 10.96}

 91%|█████████▏| 25647/28080 [50:40:04<4:48:53,  7.12s/it]
 91%|█████████▏| 25648/28080 [50:40:11<4:49:50,  7.15s/it]
                                                          
{'loss': 0.5953, 'learning_rate': 9.771667382170723e-06, 'epoch': 10.96}

 91%|█████████▏| 25648/28080 [50:40:11<4:49:50,  7.15s/it]
 91%|█████████▏| 25649/28080 [50:40:18<4:49:50,  7.15s/it]
                                                          
{'loss': 0.6067, 'learning_rate': 9.763685832868935e-06, 'epoch': 10.96}

 91%|█████████▏| 25649/28080 [50:40:18<4:49:50,  7.15s/it]
 91%|█████████▏| 25650/28080 [50:40:25<4:50:01,  7.16s/it]
                                                          
{'loss': 0.6146, 'learning_rate': 9.755707479663479e-06, 'epoch': 10.96}

 91%|█████████▏| 25650/28080 [50:40:25<4:50:01,  7.16s/it]
 91%|█████████▏| 25651/28080 [50:40:32<4:49:01,  7.14s/it]
                                                          
{'loss': 0.5896, 'learning_rate': 9.747732322660463e-06, 'epoch': 10.96}

 91%|█████████▏| 25651/28080 [50:40:32<4:49:01,  7.14s/it]
 91%|█████████▏| 25652/28080 [50:40:39<4:47:47,  7.11s/it]
                                                          
{'loss': 0.601, 'learning_rate': 9.739760361966e-06, 'epoch': 10.96}

 91%|█████████▏| 25652/28080 [50:40:39<4:47:47,  7.11s/it]
 91%|█████████▏| 25653/28080 [50:40:46<4:47:05,  7.10s/it]
                                                          
{'loss': 0.5947, 'learning_rate': 9.731791597686196e-06, 'epoch': 10.96}

 91%|█████████▏| 25653/28080 [50:40:46<4:47:05,  7.10s/it]
 91%|█████████▏| 25654/28080 [50:40:53<4:47:02,  7.10s/it]
                                                          
{'loss': 0.6101, 'learning_rate': 9.723826029926997e-06, 'epoch': 10.96}

 91%|█████████▏| 25654/28080 [50:40:53<4:47:02,  7.10s/it]
 91%|█████████▏| 25655/28080 [50:41:00<4:45:48,  7.07s/it]
                                                          
{'loss': 0.5967, 'learning_rate': 9.715863658794483e-06, 'epoch': 10.96}

 91%|█████████▏| 25655/28080 [50:41:01<4:45:48,  7.07s/it]
 91%|█████████▏| 25656/28080 [50:41:08<4:46:05,  7.08s/it]
                                                          
{'loss': 0.6096, 'learning_rate': 9.70790448439446e-06, 'epoch': 10.96}

 91%|█████████▏| 25656/28080 [50:41:08<4:46:05,  7.08s/it]
 91%|█████████▏| 25657/28080 [50:41:15<4:45:43,  7.08s/it]
                                                          
{'loss': 0.6001, 'learning_rate': 9.699948506832896e-06, 'epoch': 10.96}

 91%|█████████▏| 25657/28080 [50:41:15<4:45:43,  7.08s/it]
 91%|█████████▏| 25658/28080 [50:41:22<4:46:58,  7.11s/it]
                                                          
{'loss': 0.6266, 'learning_rate': 9.691995726215569e-06, 'epoch': 10.96}

 91%|█████████▏| 25658/28080 [50:41:22<4:46:58,  7.11s/it]
 91%|█████████▏| 25659/28080 [50:41:29<4:47:12,  7.12s/it]
                                                          
{'loss': 0.5975, 'learning_rate': 9.684046142648368e-06, 'epoch': 10.96}

 91%|█████████▏| 25659/28080 [50:41:29<4:47:12,  7.12s/it]
 91%|█████████▏| 25660/28080 [50:41:36<4:47:43,  7.13s/it]
                                                          
{'loss': 0.5998, 'learning_rate': 9.676099756237039e-06, 'epoch': 10.96}

 91%|█████████▏| 25660/28080 [50:41:36<4:47:43,  7.13s/it]
 91%|█████████▏| 25661/28080 [50:41:43<4:46:49,  7.11s/it]
                                                          
{'loss': 0.6004, 'learning_rate': 9.668156567087221e-06, 'epoch': 10.96}

 91%|█████████▏| 25661/28080 [50:41:43<4:46:49,  7.11s/it]
 91%|█████████▏| 25662/28080 [50:41:50<4:46:24,  7.11s/it]
                                                          
{'loss': 0.5876, 'learning_rate': 9.660216575304664e-06, 'epoch': 10.96}

 91%|█████████▏| 25662/28080 [50:41:50<4:46:24,  7.11s/it]
 91%|█████████▏| 25663/28080 [50:41:57<4:47:00,  7.12s/it]
                                                          
{'loss': 0.5868, 'learning_rate': 9.652279780994948e-06, 'epoch': 10.96}

 91%|█████████▏| 25663/28080 [50:41:57<4:47:00,  7.12s/it]
 91%|█████████▏| 25664/28080 [50:42:05<4:46:15,  7.11s/it]
                                                          
{'loss': 0.6072, 'learning_rate': 9.644346184263741e-06, 'epoch': 10.96}

 91%|█████████▏| 25664/28080 [50:42:05<4:46:15,  7.11s/it]
 91%|█████████▏| 25665/28080 [50:42:12<4:46:04,  7.11s/it]
                                                          
{'loss': 0.6159, 'learning_rate': 9.63641578521654e-06, 'epoch': 10.96}

 91%|█████████▏| 25665/28080 [50:42:12<4:46:04,  7.11s/it]
 91%|█████████▏| 25666/28080 [50:42:19<4:47:05,  7.14s/it]
                                                          
{'loss': 0.6039, 'learning_rate': 9.628488583958873e-06, 'epoch': 10.96}

 91%|█████████▏| 25666/28080 [50:42:19<4:47:05,  7.14s/it]
 91%|█████████▏| 25667/28080 [50:42:26<4:46:20,  7.12s/it]
                                                          
{'loss': 0.5835, 'learning_rate': 9.620564580596125e-06, 'epoch': 10.96}

 91%|█████████▏| 25667/28080 [50:42:26<4:46:20,  7.12s/it]
 91%|█████████▏| 25668/28080 [50:42:33<4:45:42,  7.11s/it]
                                                          
{'loss': 0.5954, 'learning_rate': 9.612643775233853e-06, 'epoch': 10.97}

 91%|█████████▏| 25668/28080 [50:42:33<4:45:42,  7.11s/it]
 91%|█████████▏| 25669/28080 [50:42:40<4:45:46,  7.11s/it]
                                                          
{'loss': 0.6236, 'learning_rate': 9.604726167977334e-06, 'epoch': 10.97}

 91%|█████████▏| 25669/28080 [50:42:40<4:45:46,  7.11s/it]
 91%|█████████▏| 25670/28080 [50:42:47<4:45:45,  7.11s/it]
                                                          
{'loss': 0.5775, 'learning_rate': 9.596811758931928e-06, 'epoch': 10.97}

 91%|█████████▏| 25670/28080 [50:42:47<4:45:45,  7.11s/it]
 91%|█████████▏| 25671/28080 [50:42:54<4:46:07,  7.13s/it]
                                                          
{'loss': 0.5946, 'learning_rate': 9.58890054820291e-06, 'epoch': 10.97}

 91%|█████████▏| 25671/28080 [50:42:54<4:46:07,  7.13s/it]
 91%|█████████▏| 25672/28080 [50:43:02<4:47:27,  7.16s/it]
                                                          
{'loss': 0.5964, 'learning_rate': 9.580992535895589e-06, 'epoch': 10.97}

 91%|█████████▏| 25672/28080 [50:43:02<4:47:27,  7.16s/it]
 91%|█████████▏| 25673/28080 [50:43:09<4:47:09,  7.16s/it]
                                                          
{'loss': 0.6109, 'learning_rate': 9.57308772211507e-06, 'epoch': 10.97}

 91%|█████████▏| 25673/28080 [50:43:09<4:47:09,  7.16s/it]
 91%|█████████▏| 25674/28080 [50:43:16<4:46:17,  7.14s/it]
                                                          
{'loss': 0.5788, 'learning_rate': 9.56518610696669e-06, 'epoch': 10.97}

 91%|█████████▏| 25674/28080 [50:43:16<4:46:17,  7.14s/it]
 91%|█████████▏| 25675/28080 [50:43:23<4:44:38,  7.10s/it]
                                                          
{'loss': 0.6091, 'learning_rate': 9.55728769055539e-06, 'epoch': 10.97}

 91%|█████████▏| 25675/28080 [50:43:23<4:44:38,  7.10s/it]
 91%|█████████▏| 25676/28080 [50:43:30<4:44:41,  7.11s/it]
                                                          
{'loss': 0.614, 'learning_rate': 9.549392472986335e-06, 'epoch': 10.97}

 91%|█████████▏| 25676/28080 [50:43:30<4:44:41,  7.11s/it]
 91%|█████████▏| 25677/28080 [50:43:37<4:44:26,  7.10s/it]
                                                          
{'loss': 0.5952, 'learning_rate': 9.541500454364555e-06, 'epoch': 10.97}

 91%|█████████▏| 25677/28080 [50:43:37<4:44:26,  7.10s/it]
 91%|█████████▏| 25678/28080 [50:43:44<4:43:21,  7.08s/it]
                                                          
{'loss': 0.5844, 'learning_rate': 9.533611634795047e-06, 'epoch': 10.97}

 91%|█████████▏| 25678/28080 [50:43:44<4:43:21,  7.08s/it]
 91%|█████████▏| 25679/28080 [50:43:51<4:44:12,  7.10s/it]
                                                          
{'loss': 0.5929, 'learning_rate': 9.525726014382786e-06, 'epoch': 10.97}

 91%|█████████▏| 25679/28080 [50:43:51<4:44:12,  7.10s/it]
 91%|█████████▏| 25680/28080 [50:43:58<4:44:46,  7.12s/it]
                                                          
{'loss': 0.5975, 'learning_rate': 9.517843593232655e-06, 'epoch': 10.97}

 91%|█████████▏| 25680/28080 [50:43:58<4:44:46,  7.12s/it]
 91%|█████████▏| 25681/28080 [50:44:06<4:45:22,  7.14s/it]
                                                          
{'loss': 0.6026, 'learning_rate': 9.509964371449464e-06, 'epoch': 10.97}

 91%|█████████▏| 25681/28080 [50:44:06<4:45:22,  7.14s/it]
 91%|█████████▏| 25682/28080 [50:44:13<4:46:09,  7.16s/it]
                                                          
{'loss': 0.5821, 'learning_rate': 9.502088349138155e-06, 'epoch': 10.97}

 91%|█████████▏| 25682/28080 [50:44:13<4:46:09,  7.16s/it]
 91%|█████████▏| 25683/28080 [50:44:20<4:46:02,  7.16s/it]
                                                          
{'loss': 0.5859, 'learning_rate': 9.494215526403449e-06, 'epoch': 10.97}

 91%|█████████▏| 25683/28080 [50:44:20<4:46:02,  7.16s/it]
 91%|█████████▏| 25684/28080 [50:44:27<4:45:22,  7.15s/it]
                                                          
{'loss': 0.5938, 'learning_rate': 9.486345903350068e-06, 'epoch': 10.97}

 91%|█████████▏| 25684/28080 [50:44:27<4:45:22,  7.15s/it]
 91%|█████████▏| 25685/28080 [50:44:34<4:45:03,  7.14s/it]
                                                          
{'loss': 0.5892, 'learning_rate': 9.478479480082764e-06, 'epoch': 10.97}

 91%|█████████▏| 25685/28080 [50:44:34<4:45:03,  7.14s/it]
 91%|█████████▏| 25686/28080 [50:44:41<4:45:22,  7.15s/it]
                                                          
{'loss': 0.6013, 'learning_rate': 9.470616256706116e-06, 'epoch': 10.97}

 91%|█████████▏| 25686/28080 [50:44:41<4:45:22,  7.15s/it]
 91%|█████████▏| 25687/28080 [50:44:49<4:44:24,  7.13s/it]
                                                          
{'loss': 0.5842, 'learning_rate': 9.462756233324793e-06, 'epoch': 10.97}

 91%|█████████▏| 25687/28080 [50:44:49<4:44:24,  7.13s/it]
 91%|█████████▏| 25688/28080 [50:44:56<4:44:21,  7.13s/it]
                                                          
{'loss': 0.5939, 'learning_rate': 9.45489941004335e-06, 'epoch': 10.97}

 91%|█████████▏| 25688/28080 [50:44:56<4:44:21,  7.13s/it]
 91%|█████████▏| 25689/28080 [50:45:03<4:43:26,  7.11s/it]
                                                          
{'loss': 0.6101, 'learning_rate': 9.44704578696634e-06, 'epoch': 10.97}

 91%|█████████▏| 25689/28080 [50:45:03<4:43:26,  7.11s/it]
 91%|█████████▏| 25690/28080 [50:45:10<4:44:03,  7.13s/it]
                                                          
{'loss': 0.5911, 'learning_rate': 9.439195364198183e-06, 'epoch': 10.97}

 91%|█████████▏| 25690/28080 [50:45:10<4:44:03,  7.13s/it]
 91%|█████████▏| 25691/28080 [50:45:17<4:44:41,  7.15s/it]
                                                          
{'loss': 0.5744, 'learning_rate': 9.431348141843377e-06, 'epoch': 10.97}

 91%|█████████▏| 25691/28080 [50:45:17<4:44:41,  7.15s/it]
 91%|█████████▏| 25692/28080 [50:45:24<4:43:15,  7.12s/it]
                                                          
{'loss': 0.61, 'learning_rate': 9.423504120006283e-06, 'epoch': 10.98}

 91%|█████████▏| 25692/28080 [50:45:24<4:43:15,  7.12s/it]
 91%|█████████▏| 25693/28080 [50:45:31<4:42:17,  7.10s/it]
                                                          
{'loss': 0.5836, 'learning_rate': 9.415663298791288e-06, 'epoch': 10.98}

 91%|█████████▏| 25693/28080 [50:45:31<4:42:17,  7.10s/it]
 92%|█████████▏| 25694/28080 [50:45:38<4:42:39,  7.11s/it]
                                                          
{'loss': 0.6148, 'learning_rate': 9.407825678302729e-06, 'epoch': 10.98}

 92%|█████████▏| 25694/28080 [50:45:38<4:42:39,  7.11s/it]
 92%|█████████▏| 25695/28080 [50:45:45<4:42:28,  7.11s/it]
                                                          
{'loss': 0.6374, 'learning_rate': 9.399991258644824e-06, 'epoch': 10.98}

 92%|█████████▏| 25695/28080 [50:45:45<4:42:28,  7.11s/it]
 92%|█████████▏| 25696/28080 [50:45:53<4:42:30,  7.11s/it]
                                                          
{'loss': 0.5977, 'learning_rate': 9.392160039921798e-06, 'epoch': 10.98}

 92%|█████████▏| 25696/28080 [50:45:53<4:42:30,  7.11s/it]
 92%|█████████▏| 25697/28080 [50:46:00<4:42:38,  7.12s/it]
                                                          
{'loss': 0.5867, 'learning_rate': 9.384332022237874e-06, 'epoch': 10.98}

 92%|█████████▏| 25697/28080 [50:46:00<4:42:38,  7.12s/it]
 92%|█████████▏| 25698/28080 [50:46:07<4:42:31,  7.12s/it]
                                                          
{'loss': 0.585, 'learning_rate': 9.376507205697187e-06, 'epoch': 10.98}

 92%|█████████▏| 25698/28080 [50:46:07<4:42:31,  7.12s/it]
 92%|█████████▏| 25699/28080 [50:46:14<4:42:26,  7.12s/it]
                                                          
{'loss': 0.5856, 'learning_rate': 9.368685590403853e-06, 'epoch': 10.98}

 92%|█████████▏| 25699/28080 [50:46:14<4:42:26,  7.12s/it]
 92%|█████████▏| 25700/28080 [50:46:21<4:42:01,  7.11s/it]
                                                          
{'loss': 0.6138, 'learning_rate': 9.360867176461868e-06, 'epoch': 10.98}

 92%|█████████▏| 25700/28080 [50:46:21<4:42:01,  7.11s/it]
 92%|█████████▏| 25701/28080 [50:46:28<4:41:46,  7.11s/it]
                                                          
{'loss': 0.5754, 'learning_rate': 9.353051963975346e-06, 'epoch': 10.98}

 92%|█████████▏| 25701/28080 [50:46:28<4:41:46,  7.11s/it]
 92%|█████████▏| 25702/28080 [50:46:35<4:41:29,  7.10s/it]
                                                          
{'loss': 0.6134, 'learning_rate': 9.345239953048147e-06, 'epoch': 10.98}

 92%|█████████▏| 25702/28080 [50:46:35<4:41:29,  7.10s/it]
 92%|█████████▏| 25703/28080 [50:46:42<4:41:29,  7.11s/it]
                                                          
{'loss': 0.6056, 'learning_rate': 9.337431143784325e-06, 'epoch': 10.98}

 92%|█████████▏| 25703/28080 [50:46:42<4:41:29,  7.11s/it]
 92%|█████████▏| 25704/28080 [50:46:49<4:41:49,  7.12s/it]
                                                          
{'loss': 0.5798, 'learning_rate': 9.329625536287662e-06, 'epoch': 10.98}

 92%|█████████▏| 25704/28080 [50:46:49<4:41:49,  7.12s/it]
 92%|█████████▏| 25705/28080 [50:46:57<4:42:33,  7.14s/it]
                                                          
{'loss': 0.604, 'learning_rate': 9.321823130662044e-06, 'epoch': 10.98}

 92%|█████████▏| 25705/28080 [50:46:57<4:42:33,  7.14s/it]
 92%|█████████▏| 25706/28080 [50:47:04<4:42:06,  7.13s/it]
                                                          
{'loss': 0.5889, 'learning_rate': 9.314023927011278e-06, 'epoch': 10.98}

 92%|█████████▏| 25706/28080 [50:47:04<4:42:06,  7.13s/it]
 92%|█████████▏| 25707/28080 [50:47:11<4:40:53,  7.10s/it]
                                                          
{'loss': 0.587, 'learning_rate': 9.306227925439143e-06, 'epoch': 10.98}

 92%|█████████▏| 25707/28080 [50:47:11<4:40:53,  7.10s/it]
 92%|█████████▏| 25708/28080 [50:47:18<4:41:19,  7.12s/it]
                                                          
{'loss': 0.5945, 'learning_rate': 9.298435126049304e-06, 'epoch': 10.98}

 92%|█████████▏| 25708/28080 [50:47:18<4:41:19,  7.12s/it]
 92%|█████████▏| 25709/28080 [50:47:25<4:40:48,  7.11s/it]
                                                          
{'loss': 0.5893, 'learning_rate': 9.290645528945513e-06, 'epoch': 10.98}

 92%|█████████▏| 25709/28080 [50:47:25<4:40:48,  7.11s/it]
 92%|█████████▏| 25710/28080 [50:47:32<4:39:42,  7.08s/it]
                                                          
{'loss': 0.6067, 'learning_rate': 9.282859134231325e-06, 'epoch': 10.98}

 92%|█████████▏| 25710/28080 [50:47:32<4:39:42,  7.08s/it]
 92%|█████████▏| 25711/28080 [50:47:39<4:40:32,  7.11s/it]
                                                          
{'loss': 0.585, 'learning_rate': 9.275075942010352e-06, 'epoch': 10.98}

 92%|█████████▏| 25711/28080 [50:47:39<4:40:32,  7.11s/it]
 92%|█████████▏| 25712/28080 [50:47:46<4:40:21,  7.10s/it]
                                                          
{'loss': 0.6003, 'learning_rate': 9.267295952386178e-06, 'epoch': 10.98}

 92%|█████████▏| 25712/28080 [50:47:46<4:40:21,  7.10s/it]
 92%|█████████▏| 25713/28080 [50:47:53<4:39:03,  7.07s/it]
                                                          
{'loss': 0.6, 'learning_rate': 9.259519165462278e-06, 'epoch': 10.98}

 92%|█████████▏| 25713/28080 [50:47:53<4:39:03,  7.07s/it]
 92%|█████████▏| 25714/28080 [50:48:00<4:39:45,  7.09s/it]
                                                          
{'loss': 0.6009, 'learning_rate': 9.25174558134212e-06, 'epoch': 10.98}

 92%|█████████▏| 25714/28080 [50:48:00<4:39:45,  7.09s/it]
 92%|█████████▏| 25715/28080 [50:48:08<4:40:34,  7.12s/it]
                                                          
{'loss': 0.6056, 'learning_rate': 9.243975200129067e-06, 'epoch': 10.99}

 92%|█████████▏| 25715/28080 [50:48:08<4:40:34,  7.12s/it]
 92%|█████████▏| 25716/28080 [50:48:15<4:39:56,  7.10s/it]
                                                          
{'loss': 0.587, 'learning_rate': 9.236208021926624e-06, 'epoch': 10.99}

 92%|█████████▏| 25716/28080 [50:48:15<4:39:56,  7.10s/it]
 92%|█████████▏| 25717/28080 [50:48:22<4:40:45,  7.13s/it]
                                                          
{'loss': 0.6007, 'learning_rate': 9.228444046838008e-06, 'epoch': 10.99}

 92%|█████████▏| 25717/28080 [50:48:22<4:40:45,  7.13s/it]
 92%|█████████▏| 25718/28080 [50:48:29<4:41:07,  7.14s/it]
                                                          
{'loss': 0.5591, 'learning_rate': 9.220683274966585e-06, 'epoch': 10.99}

 92%|█████████▏| 25718/28080 [50:48:29<4:41:07,  7.14s/it]
 92%|█████████▏| 25719/28080 [50:48:36<4:40:39,  7.13s/it]
                                                          
{'loss': 0.5906, 'learning_rate': 9.21292570641552e-06, 'epoch': 10.99}

 92%|█████████▏| 25719/28080 [50:48:36<4:40:39,  7.13s/it]
 92%|█████████▏| 25720/28080 [50:48:43<4:38:25,  7.08s/it]
                                                          
{'loss': 0.6453, 'learning_rate': 9.205171341288121e-06, 'epoch': 10.99}

 92%|█████████▏| 25720/28080 [50:48:43<4:38:25,  7.08s/it]
 92%|█████████▏| 25721/28080 [50:48:50<4:39:10,  7.10s/it]
                                                          
{'loss': 0.5826, 'learning_rate': 9.197420179687471e-06, 'epoch': 10.99}

 92%|█████████▏| 25721/28080 [50:48:50<4:39:10,  7.10s/it]
 92%|█████████▏| 25722/28080 [50:48:57<4:39:09,  7.10s/it]
                                                          
{'loss': 0.5903, 'learning_rate': 9.189672221716765e-06, 'epoch': 10.99}

 92%|█████████▏| 25722/28080 [50:48:57<4:39:09,  7.10s/it]
 92%|█████████▏| 25723/28080 [50:49:04<4:39:04,  7.10s/it]
                                                          
{'loss': 0.5949, 'learning_rate': 9.181927467479006e-06, 'epoch': 10.99}

 92%|█████████▏| 25723/28080 [50:49:04<4:39:04,  7.10s/it]
 92%|█████████▏| 25724/28080 [50:49:12<4:38:50,  7.10s/it]
                                                          
{'loss': 0.6017, 'learning_rate': 9.174185917077276e-06, 'epoch': 10.99}

 92%|█████████▏| 25724/28080 [50:49:12<4:38:50,  7.10s/it]
 92%|█████████▏| 25725/28080 [50:49:19<4:39:08,  7.11s/it]
                                                          
{'loss': 0.5987, 'learning_rate': 9.166447570614522e-06, 'epoch': 10.99}

 92%|█████████▏| 25725/28080 [50:49:19<4:39:08,  7.11s/it]
 92%|█████████▏| 25726/28080 [50:49:26<4:38:46,  7.11s/it]
                                                          
{'loss': 0.5995, 'learning_rate': 9.158712428193771e-06, 'epoch': 10.99}

 92%|█████████▏| 25726/28080 [50:49:26<4:38:46,  7.11s/it]
 92%|█████████▏| 25727/28080 [50:49:33<4:37:36,  7.08s/it]
                                                          
{'loss': 0.612, 'learning_rate': 9.150980489917886e-06, 'epoch': 10.99}

 92%|█████████▏| 25727/28080 [50:49:33<4:37:36,  7.08s/it]
 92%|█████████▏| 25728/28080 [50:49:40<4:37:03,  7.07s/it]
                                                          
{'loss': 0.6032, 'learning_rate': 9.14325175588973e-06, 'epoch': 10.99}

 92%|█████████▏| 25728/28080 [50:49:40<4:37:03,  7.07s/it]
 92%|█████████▏| 25729/28080 [50:49:47<4:39:27,  7.13s/it]
                                                          
{'loss': 0.6011, 'learning_rate': 9.135526226212109e-06, 'epoch': 10.99}

 92%|█████████▏| 25729/28080 [50:49:47<4:39:27,  7.13s/it]
 92%|█████████▏| 25730/28080 [50:49:54<4:38:44,  7.12s/it]
                                                          
{'loss': 0.6005, 'learning_rate': 9.127803900987858e-06, 'epoch': 10.99}

 92%|█████████▏| 25730/28080 [50:49:54<4:38:44,  7.12s/it]
 92%|█████████▏| 25731/28080 [50:50:01<4:37:51,  7.10s/it]
                                                          
{'loss': 0.6312, 'learning_rate': 9.12008478031967e-06, 'epoch': 10.99}

 92%|█████████▏| 25731/28080 [50:50:01<4:37:51,  7.10s/it]
 92%|█████████▏| 25732/28080 [50:50:08<4:38:00,  7.10s/it]
                                                          
{'loss': 0.6129, 'learning_rate': 9.112368864310271e-06, 'epoch': 10.99}

 92%|█████████▏| 25732/28080 [50:50:08<4:38:00,  7.10s/it]
 92%|█████████▏| 25733/28080 [50:50:15<4:37:22,  7.09s/it]
                                                          
{'loss': 0.5964, 'learning_rate': 9.104656153062246e-06, 'epoch': 10.99}

 92%|█████████▏| 25733/28080 [50:50:15<4:37:22,  7.09s/it]
 92%|█████████▏| 25734/28080 [50:50:23<4:38:31,  7.12s/it]
                                                          
{'loss': 0.6133, 'learning_rate': 9.09694664667829e-06, 'epoch': 10.99}

 92%|█████████▏| 25734/28080 [50:50:23<4:38:31,  7.12s/it]
 92%|█████████▏| 25735/28080 [50:50:30<4:38:39,  7.13s/it]
                                                          
{'loss': 0.6071, 'learning_rate': 9.08924034526093e-06, 'epoch': 10.99}

 92%|█████████▏| 25735/28080 [50:50:30<4:38:39,  7.13s/it]
 92%|█████████▏| 25736/28080 [50:50:37<4:38:55,  7.14s/it]
                                                          
{'loss': 0.6087, 'learning_rate': 9.081537248912697e-06, 'epoch': 10.99}

 92%|█████████▏| 25736/28080 [50:50:37<4:38:55,  7.14s/it]
 92%|█████████▏| 25737/28080 [50:50:44<4:39:03,  7.15s/it]
                                                          
{'loss': 0.5822, 'learning_rate': 9.073837357736065e-06, 'epoch': 10.99}

 92%|█████████▏| 25737/28080 [50:50:44<4:39:03,  7.15s/it]
 92%|█████████▏| 25738/28080 [50:50:51<4:38:31,  7.14s/it]
                                                          
{'loss': 0.59, 'learning_rate': 9.066140671833451e-06, 'epoch': 11.0}

 92%|█████████▏| 25738/28080 [50:50:51<4:38:31,  7.14s/it]
 92%|█████████▏| 25739/28080 [50:50:58<4:39:09,  7.15s/it]
                                                          
{'loss': 0.5931, 'learning_rate': 9.0584471913073e-06, 'epoch': 11.0}

 92%|█████████▏| 25739/28080 [50:50:58<4:39:09,  7.15s/it]
 92%|█████████▏| 25740/28080 [50:51:05<4:37:15,  7.11s/it]
                                                          
{'loss': 0.5991, 'learning_rate': 9.050756916259923e-06, 'epoch': 11.0}

 92%|█████████▏| 25740/28080 [50:51:05<4:37:15,  7.11s/it]
 92%|█████████▏| 25741/28080 [50:51:13<4:36:50,  7.10s/it]
                                                          
{'loss': 0.6097, 'learning_rate': 9.043069846793677e-06, 'epoch': 11.0}

 92%|█████████▏| 25741/28080 [50:51:13<4:36:50,  7.10s/it]
 92%|█████████▏| 25742/28080 [50:51:20<4:37:03,  7.11s/it]
                                                          
{'loss': 0.6367, 'learning_rate': 9.035385983010818e-06, 'epoch': 11.0}

 92%|█████████▏| 25742/28080 [50:51:20<4:37:03,  7.11s/it]
 92%|█████████▏| 25743/28080 [50:51:27<4:36:47,  7.11s/it]
                                                          
{'loss': 0.6047, 'learning_rate': 9.02770532501354e-06, 'epoch': 11.0}

 92%|█████████▏| 25743/28080 [50:51:27<4:36:47,  7.11s/it]
 92%|█████████▏| 25744/28080 [50:51:34<4:35:36,  7.08s/it]
                                                          
{'loss': 0.6022, 'learning_rate': 9.020027872904012e-06, 'epoch': 11.0}

 92%|█████████▏| 25744/28080 [50:51:34<4:35:36,  7.08s/it]
 92%|█████████▏| 25745/28080 [50:51:41<4:35:57,  7.09s/it]
                                                          
{'loss': 0.5951, 'learning_rate': 9.012353626784459e-06, 'epoch': 11.0}

 92%|█████████▏| 25745/28080 [50:51:41<4:35:57,  7.09s/it]
 92%|█████████▏| 25746/28080 [50:51:48<4:36:12,  7.10s/it]
                                                          
{'loss': 0.6034, 'learning_rate': 9.004682586756907e-06, 'epoch': 11.0}

 92%|█████████▏| 25746/28080 [50:51:48<4:36:12,  7.10s/it]
 92%|█████████▏| 25747/28080 [50:51:55<4:35:39,  7.09s/it]
                                                          
{'loss': 0.5953, 'learning_rate': 8.997014752923444e-06, 'epoch': 11.0}

 92%|█████████▏| 25747/28080 [50:51:55<4:35:39,  7.09s/it]
 92%|█████████▏| 25748/28080 [50:52:02<4:36:22,  7.11s/it]
                                                          
{'loss': 0.5831, 'learning_rate': 8.989350125386042e-06, 'epoch': 11.0}

 92%|█████████▏| 25748/28080 [50:52:02<4:36:22,  7.11s/it]
 92%|█████████▏| 25749/28080 [50:52:09<4:36:58,  7.13s/it]
                                                          
{'loss': 0.5634, 'learning_rate': 8.981688704246733e-06, 'epoch': 11.0}

 92%|█████████▏| 25749/28080 [50:52:09<4:36:58,  7.13s/it]
 92%|█████████▏| 25750/28080 [50:52:17<4:42:35,  7.28s/it]
                                                          
{'loss': 0.6006, 'learning_rate': 8.974030489607376e-06, 'epoch': 11.0}

 92%|█████████▏| 25750/28080 [50:52:17<4:42:35,  7.28s/it]
 92%|█████████▏| 25751/28080 [50:52:24<4:40:58,  7.24s/it]
                                                          
{'loss': 0.639, 'learning_rate': 8.96637548156995e-06, 'epoch': 11.0}

 92%|█████████▏| 25751/28080 [50:52:24<4:40:58,  7.24s/it]
 92%|█████████▏| 25752/28080 [50:52:31<4:39:25,  7.20s/it]
                                                          
{'loss': 0.5795, 'learning_rate': 8.958723680236175e-06, 'epoch': 11.0}

 92%|█████████▏| 25752/28080 [50:52:31<4:39:25,  7.20s/it]
 92%|█████████▏| 25753/28080 [50:52:38<4:38:50,  7.19s/it]
                                                          
{'loss': 0.6055, 'learning_rate': 8.951075085707943e-06, 'epoch': 11.0}

 92%|█████████▏| 25753/28080 [50:52:38<4:38:50,  7.19s/it]
 92%|█████████▏| 25754/28080 [50:52:46<4:37:51,  7.17s/it]
                                                          
{'loss': 0.6304, 'learning_rate': 8.943429698086953e-06, 'epoch': 11.0}

 92%|█████████▏| 25754/28080 [50:52:46<4:37:51,  7.17s/it]
 92%|█████████▏| 25755/28080 [50:52:53<4:37:39,  7.17s/it]
                                                          
{'loss': 0.6135, 'learning_rate': 8.93578751747498e-06, 'epoch': 11.0}

 92%|█████████▏| 25755/28080 [50:52:53<4:37:39,  7.17s/it]
 92%|█████████▏| 25756/28080 [50:53:00<4:36:41,  7.14s/it]
                                                          
{'loss': 0.6143, 'learning_rate': 8.92814854397367e-06, 'epoch': 11.0}

 92%|█████████▏| 25756/28080 [50:53:00<4:36:41,  7.14s/it]
 92%|█████████▏| 25757/28080 [50:53:07<4:36:12,  7.13s/it]
                                                          
{'loss': 0.6058, 'learning_rate': 8.92051277768463e-06, 'epoch': 11.0}

 92%|█████████▏| 25757/28080 [50:53:07<4:36:12,  7.13s/it]
 92%|█████████▏| 25758/28080 [50:53:14<4:35:50,  7.13s/it]
                                                          
{'loss': 0.6093, 'learning_rate': 8.912880218709424e-06, 'epoch': 11.0}

 92%|█████████▏| 25758/28080 [50:53:14<4:35:50,  7.13s/it]
 92%|█████████▏| 25759/28080 [50:53:21<4:35:20,  7.12s/it]
                                                          
{'loss': 0.608, 'learning_rate': 8.90525086714969e-06, 'epoch': 11.0}

 92%|█████████▏| 25759/28080 [50:53:21<4:35:20,  7.12s/it]
 92%|█████████▏| 25760/28080 [50:53:28<4:34:50,  7.11s/it]
                                                          
{'loss': 0.5792, 'learning_rate': 8.897624723106845e-06, 'epoch': 11.0}

 92%|█████████▏| 25760/28080 [50:53:28<4:34:50,  7.11s/it]
 92%|█████████▏| 25761/28080 [50:53:35<4:35:06,  7.12s/it]
                                                          
{'loss': 0.5817, 'learning_rate': 8.890001786682367e-06, 'epoch': 11.0}

 92%|█████████▏| 25761/28080 [50:53:35<4:35:06,  7.12s/it]
 92%|█████████▏| 25762/28080 [50:53:43<4:35:17,  7.13s/it]
                                                          
{'loss': 0.6004, 'learning_rate': 8.8823820579777e-06, 'epoch': 11.01}

 92%|█████████▏| 25762/28080 [50:53:43<4:35:17,  7.13s/it]
 92%|█████████▏| 25763/28080 [50:53:50<4:35:21,  7.13s/it]
                                                          
{'loss': 0.6087, 'learning_rate': 8.874765537094126e-06, 'epoch': 11.01}

 92%|█████████▏| 25763/28080 [50:53:50<4:35:21,  7.13s/it]
 92%|█████████▏| 25764/28080 [50:53:57<4:34:26,  7.11s/it]
                                                          
{'loss': 0.6096, 'learning_rate': 8.86715222413309e-06, 'epoch': 11.01}

 92%|█████████▏| 25764/28080 [50:53:57<4:34:26,  7.11s/it]
 92%|█████████▏| 25765/28080 [50:54:04<4:35:02,  7.13s/it]
                                                          
{'loss': 0.6046, 'learning_rate': 8.859542119195846e-06, 'epoch': 11.01}

 92%|█████████▏| 25765/28080 [50:54:04<4:35:02,  7.13s/it]
 92%|█████████▏| 25766/28080 [50:54:11<4:33:37,  7.09s/it]
                                                          
{'loss': 0.6083, 'learning_rate': 8.851935222383616e-06, 'epoch': 11.01}

 92%|█████████▏| 25766/28080 [50:54:11<4:33:37,  7.09s/it]
 92%|█████████▏| 25767/28080 [50:54:18<4:33:36,  7.10s/it]
                                                          
{'loss': 0.6006, 'learning_rate': 8.844331533797572e-06, 'epoch': 11.01}

 92%|█████████▏| 25767/28080 [50:54:18<4:33:36,  7.10s/it]
 92%|█████████▏| 25768/28080 [50:54:25<4:34:21,  7.12s/it]
                                                          
{'loss': 0.5613, 'learning_rate': 8.836731053538938e-06, 'epoch': 11.01}

 92%|█████████▏| 25768/28080 [50:54:25<4:34:21,  7.12s/it]
 92%|█████████▏| 25769/28080 [50:54:32<4:34:57,  7.14s/it]
                                                          
{'loss': 0.5959, 'learning_rate': 8.82913378170877e-06, 'epoch': 11.01}

 92%|█████████▏| 25769/28080 [50:54:32<4:34:57,  7.14s/it]
 92%|█████████▏| 25770/28080 [50:54:39<4:33:46,  7.11s/it]
                                                          
{'loss': 0.5943, 'learning_rate': 8.82153971840824e-06, 'epoch': 11.01}

 92%|█████████▏| 25770/28080 [50:54:39<4:33:46,  7.11s/it]
 92%|█████████▏| 25771/28080 [50:54:47<4:34:05,  7.12s/it]
                                                          
{'loss': 0.5866, 'learning_rate': 8.813948863738263e-06, 'epoch': 11.01}

 92%|█████████▏| 25771/28080 [50:54:47<4:34:05,  7.12s/it]
 92%|█████████▏| 25772/28080 [50:54:54<4:33:50,  7.12s/it]
                                                          
{'loss': 0.6021, 'learning_rate': 8.806361217799902e-06, 'epoch': 11.01}

 92%|█████████▏| 25772/28080 [50:54:54<4:33:50,  7.12s/it]
 92%|█████████▏| 25773/28080 [50:55:01<4:33:52,  7.12s/it]
                                                          
{'loss': 0.6033, 'learning_rate': 8.798776780694046e-06, 'epoch': 11.01}

 92%|█████████▏| 25773/28080 [50:55:01<4:33:52,  7.12s/it]
 92%|█████████▏| 25774/28080 [50:55:08<4:33:55,  7.13s/it]
                                                          
{'loss': 0.6001, 'learning_rate': 8.79119555252167e-06, 'epoch': 11.01}

 92%|█████████▏| 25774/28080 [50:55:08<4:33:55,  7.13s/it]
 92%|█████████▏| 25775/28080 [50:55:15<4:34:36,  7.15s/it]
                                                          
{'loss': 0.5966, 'learning_rate': 8.78361753338358e-06, 'epoch': 11.01}

 92%|█████████▏| 25775/28080 [50:55:15<4:34:36,  7.15s/it]
 92%|█████████▏| 25776/28080 [50:55:22<4:34:04,  7.14s/it]
                                                          
{'loss': 0.5813, 'learning_rate': 8.776042723380645e-06, 'epoch': 11.01}

 92%|█████████▏| 25776/28080 [50:55:22<4:34:04,  7.14s/it]
 92%|█████████▏| 25777/28080 [50:55:29<4:32:48,  7.11s/it]
                                                          
{'loss': 0.6091, 'learning_rate': 8.76847112261353e-06, 'epoch': 11.01}

 92%|█████████▏| 25777/28080 [50:55:29<4:32:48,  7.11s/it]
 92%|█████████▏| 25778/28080 [50:55:36<4:32:27,  7.10s/it]
                                                          
{'loss': 0.609, 'learning_rate': 8.7609027311831e-06, 'epoch': 11.01}

 92%|█████████▏| 25778/28080 [50:55:36<4:32:27,  7.10s/it]
 92%|█████████▏| 25779/28080 [50:55:43<4:32:28,  7.10s/it]
                                                          
{'loss': 0.5911, 'learning_rate': 8.753337549189972e-06, 'epoch': 11.01}

 92%|█████████▏| 25779/28080 [50:55:43<4:32:28,  7.10s/it]
 92%|█████████▏| 25780/28080 [50:55:51<4:32:32,  7.11s/it]
                                                          
{'loss': 0.6051, 'learning_rate': 8.74577557673481e-06, 'epoch': 11.01}

 92%|█████████▏| 25780/28080 [50:55:51<4:32:32,  7.11s/it]
 92%|█████████▏| 25781/28080 [50:55:58<4:31:20,  7.08s/it]
                                                          
{'loss': 0.5952, 'learning_rate': 8.738216813918204e-06, 'epoch': 11.01}

 92%|█████████▏| 25781/28080 [50:55:58<4:31:20,  7.08s/it]
 92%|█████████▏| 25782/28080 [50:56:05<4:30:37,  7.07s/it]
                                                          
{'loss': 0.6089, 'learning_rate': 8.73066126084074e-06, 'epoch': 11.01}

 92%|█████████▏| 25782/28080 [50:56:05<4:30:37,  7.07s/it]
 92%|█████████▏| 25783/28080 [50:56:12<4:30:44,  7.07s/it]
                                                          
{'loss': 0.5787, 'learning_rate': 8.72310891760289e-06, 'epoch': 11.01}

 92%|█████████▏| 25783/28080 [50:56:12<4:30:44,  7.07s/it]
 92%|█████████▏| 25784/28080 [50:56:19<4:31:30,  7.10s/it]
                                                          
{'loss': 0.6159, 'learning_rate': 8.715559784305244e-06, 'epoch': 11.01}

 92%|█████████▏| 25784/28080 [50:56:19<4:31:30,  7.10s/it]
 92%|█████████▏| 25785/28080 [50:56:26<4:33:48,  7.16s/it]
                                                          
{'loss': 0.6221, 'learning_rate': 8.708013861048108e-06, 'epoch': 11.02}

 92%|█████████▏| 25785/28080 [50:56:26<4:33:48,  7.16s/it]
 92%|█████████▏| 25786/28080 [50:56:33<4:34:34,  7.18s/it]
                                                          
{'loss': 0.5915, 'learning_rate': 8.700471147931904e-06, 'epoch': 11.02}

 92%|█████████▏| 25786/28080 [50:56:33<4:34:34,  7.18s/it]
 92%|█████████▏| 25787/28080 [50:56:41<4:34:17,  7.18s/it]
                                                          
{'loss': 0.5976, 'learning_rate': 8.692931645056995e-06, 'epoch': 11.02}

 92%|█████████▏| 25787/28080 [50:56:41<4:34:17,  7.18s/it]
 92%|█████████▏| 25788/28080 [50:56:48<4:33:16,  7.15s/it]
                                                          
{'loss': 0.5938, 'learning_rate': 8.685395352523689e-06, 'epoch': 11.02}

 92%|█████████▏| 25788/28080 [50:56:48<4:33:16,  7.15s/it]
 92%|█████████▏| 25789/28080 [50:56:55<4:31:36,  7.11s/it]
                                                          
{'loss': 0.5683, 'learning_rate': 8.677862270432268e-06, 'epoch': 11.02}

 92%|█████████▏| 25789/28080 [50:56:55<4:31:36,  7.11s/it]
 92%|█████████▏| 25790/28080 [50:57:02<4:32:15,  7.13s/it]
                                                          
{'loss': 0.5943, 'learning_rate': 8.67033239888293e-06, 'epoch': 11.02}

 92%|█████████▏| 25790/28080 [50:57:02<4:32:15,  7.13s/it]
 92%|█████████▏| 25791/28080 [50:57:09<4:32:03,  7.13s/it]
                                                          
{'loss': 0.5915, 'learning_rate': 8.662805737975871e-06, 'epoch': 11.02}

 92%|█████████▏| 25791/28080 [50:57:09<4:32:03,  7.13s/it]
 92%|█████████▏| 25792/28080 [50:57:16<4:31:43,  7.13s/it]
                                                          
{'loss': 0.6022, 'learning_rate': 8.65528228781115e-06, 'epoch': 11.02}

 92%|█████████▏| 25792/28080 [50:57:16<4:31:43,  7.13s/it]
 92%|█████████▏| 25793/28080 [50:57:23<4:32:14,  7.14s/it]
                                                          
{'loss': 0.6128, 'learning_rate': 8.647762048488967e-06, 'epoch': 11.02}

 92%|█████████▏| 25793/28080 [50:57:23<4:32:14,  7.14s/it]
 92%|█████████▏| 25794/28080 [50:57:30<4:31:43,  7.13s/it]
                                                          
{'loss': 0.6079, 'learning_rate': 8.640245020109322e-06, 'epoch': 11.02}

 92%|█████████▏| 25794/28080 [50:57:30<4:31:43,  7.13s/it]
 92%|█████████▏| 25795/28080 [50:57:37<4:30:23,  7.10s/it]
                                                          
{'loss': 0.6144, 'learning_rate': 8.632731202772192e-06, 'epoch': 11.02}

 92%|█████████▏| 25795/28080 [50:57:37<4:30:23,  7.10s/it]
 92%|█████████▏| 25796/28080 [50:57:45<4:30:24,  7.10s/it]
                                                          
{'loss': 0.6001, 'learning_rate': 8.625220596577581e-06, 'epoch': 11.02}

 92%|█████████▏| 25796/28080 [50:57:45<4:30:24,  7.10s/it]
 92%|█████████▏| 25797/28080 [50:57:52<4:29:47,  7.09s/it]
                                                          
{'loss': 0.6156, 'learning_rate': 8.617713201625383e-06, 'epoch': 11.02}

 92%|█████████▏| 25797/28080 [50:57:52<4:29:47,  7.09s/it]
 92%|█████████▏| 25798/28080 [50:57:59<4:30:07,  7.10s/it]
                                                          
{'loss': 0.5804, 'learning_rate': 8.610209018015514e-06, 'epoch': 11.02}

 92%|█████████▏| 25798/28080 [50:57:59<4:30:07,  7.10s/it]
 92%|█████████▏| 25799/28080 [50:58:06<4:32:11,  7.16s/it]
                                                          
{'loss': 0.5786, 'learning_rate': 8.602708045847784e-06, 'epoch': 11.02}

 92%|█████████▏| 25799/28080 [50:58:06<4:32:11,  7.16s/it]
 92%|█████████▏| 25800/28080 [50:58:13<4:31:30,  7.15s/it]
                                                          
{'loss': 0.6255, 'learning_rate': 8.595210285221978e-06, 'epoch': 11.02}

 92%|█████████▏| 25800/28080 [50:58:13<4:31:30,  7.15s/it]
 92%|█████████▏| 25801/28080 [50:58:20<4:31:18,  7.14s/it]
                                                          
{'loss': 0.6168, 'learning_rate': 8.587715736237845e-06, 'epoch': 11.02}

 92%|█████████▏| 25801/28080 [50:58:20<4:31:18,  7.14s/it]
 92%|█████████▏| 25802/28080 [50:58:27<4:31:34,  7.15s/it]
                                                          
{'loss': 0.6148, 'learning_rate': 8.580224398995112e-06, 'epoch': 11.02}

 92%|█████████▏| 25802/28080 [50:58:27<4:31:34,  7.15s/it]
 92%|█████████▏| 25803/28080 [50:58:35<4:31:46,  7.16s/it]
                                                          
{'loss': 0.5927, 'learning_rate': 8.572736273593451e-06, 'epoch': 11.02}

 92%|█████████▏| 25803/28080 [50:58:35<4:31:46,  7.16s/it]
 92%|█████████▏| 25804/28080 [50:58:42<4:30:48,  7.14s/it]
                                                          
{'loss': 0.6181, 'learning_rate': 8.565251360132448e-06, 'epoch': 11.02}

 92%|█████████▏| 25804/28080 [50:58:42<4:30:48,  7.14s/it]
 92%|█████████▏| 25805/28080 [50:58:49<4:29:59,  7.12s/it]
                                                          
{'loss': 0.5828, 'learning_rate': 8.557769658711717e-06, 'epoch': 11.02}

 92%|█████████▏| 25805/28080 [50:58:49<4:29:59,  7.12s/it]
 92%|█████████▏| 25806/28080 [50:58:56<4:28:30,  7.08s/it]
                                                          
{'loss': 0.6404, 'learning_rate': 8.550291169430735e-06, 'epoch': 11.02}

 92%|█████████▏| 25806/28080 [50:58:56<4:28:30,  7.08s/it]
 92%|█████████▏| 25807/28080 [50:59:03<4:27:53,  7.07s/it]
                                                          
{'loss': 0.6057, 'learning_rate': 8.542815892389088e-06, 'epoch': 11.02}

 92%|█████████▏| 25807/28080 [50:59:03<4:27:53,  7.07s/it]
 92%|█████████▏| 25808/28080 [50:59:10<4:27:51,  7.07s/it]
                                                          
{'loss': 0.5955, 'learning_rate': 8.535343827686171e-06, 'epoch': 11.02}

 92%|█████████▏| 25808/28080 [50:59:10<4:27:51,  7.07s/it]
 92%|█████████▏| 25809/28080 [50:59:17<4:28:46,  7.10s/it]
                                                          
{'loss': 0.5826, 'learning_rate': 8.527874975421401e-06, 'epoch': 11.03}

 92%|█████████▏| 25809/28080 [50:59:17<4:28:46,  7.10s/it]
 92%|█████████▏| 25810/28080 [50:59:24<4:28:31,  7.10s/it]
                                                          
{'loss': 0.603, 'learning_rate': 8.520409335694146e-06, 'epoch': 11.03}

 92%|█████████▏| 25810/28080 [50:59:24<4:28:31,  7.10s/it]
 92%|█████████▏| 25811/28080 [50:59:31<4:27:31,  7.07s/it]
                                                          
{'loss': 0.5933, 'learning_rate': 8.512946908603686e-06, 'epoch': 11.03}

 92%|█████████▏| 25811/28080 [50:59:31<4:27:31,  7.07s/it]
 92%|█████████▏| 25812/28080 [50:59:38<4:27:51,  7.09s/it]
                                                          
{'loss': 0.5908, 'learning_rate': 8.505487694249359e-06, 'epoch': 11.03}

 92%|█████████▏| 25812/28080 [50:59:38<4:27:51,  7.09s/it]
 92%|█████████▏| 25813/28080 [50:59:45<4:28:09,  7.10s/it]
                                                          
{'loss': 0.5901, 'learning_rate': 8.49803169273039e-06, 'epoch': 11.03}

 92%|█████████▏| 25813/28080 [50:59:45<4:28:09,  7.10s/it]
 92%|█████████▏| 25814/28080 [50:59:53<4:28:08,  7.10s/it]
                                                          
{'loss': 0.6131, 'learning_rate': 8.49057890414598e-06, 'epoch': 11.03}

 92%|█████████▏| 25814/28080 [50:59:53<4:28:08,  7.10s/it]
 92%|█████████▏| 25815/28080 [51:00:00<4:29:07,  7.13s/it]
                                                          
{'loss': 0.6102, 'learning_rate': 8.48312932859524e-06, 'epoch': 11.03}

 92%|█████████▏| 25815/28080 [51:00:00<4:29:07,  7.13s/it]
 92%|█████████▏| 25816/28080 [51:00:07<4:29:16,  7.14s/it]
                                                          
{'loss': 0.5855, 'learning_rate': 8.475682966177316e-06, 'epoch': 11.03}

 92%|█████████▏| 25816/28080 [51:00:07<4:29:16,  7.14s/it]
 92%|█████████▏| 25817/28080 [51:00:14<4:28:28,  7.12s/it]
                                                          
{'loss': 0.6034, 'learning_rate': 8.468239816991241e-06, 'epoch': 11.03}

 92%|█████████▏| 25817/28080 [51:00:14<4:28:28,  7.12s/it]
 92%|█████████▏| 25818/28080 [51:00:21<4:27:52,  7.11s/it]
                                                          
{'loss': 0.6276, 'learning_rate': 8.460799881136099e-06, 'epoch': 11.03}

 92%|█████████▏| 25818/28080 [51:00:21<4:27:52,  7.11s/it]
 92%|█████████▏| 25819/28080 [51:00:28<4:28:05,  7.11s/it]
                                                          
{'loss': 0.597, 'learning_rate': 8.453363158710815e-06, 'epoch': 11.03}

 92%|█████████▏| 25819/28080 [51:00:28<4:28:05,  7.11s/it]
 92%|█████████▏| 25820/28080 [51:00:35<4:27:49,  7.11s/it]
                                                          
{'loss': 0.6239, 'learning_rate': 8.445929649814332e-06, 'epoch': 11.03}

 92%|█████████▏| 25820/28080 [51:00:35<4:27:49,  7.11s/it]
 92%|█████████▏| 25821/28080 [51:00:42<4:27:31,  7.11s/it]
                                                          
{'loss': 0.5844, 'learning_rate': 8.438499354545548e-06, 'epoch': 11.03}

 92%|█████████▏| 25821/28080 [51:00:42<4:27:31,  7.11s/it]
 92%|█████████▏| 25822/28080 [51:00:50<4:28:28,  7.13s/it]
                                                          
{'loss': 0.6124, 'learning_rate': 8.431072273003354e-06, 'epoch': 11.03}

 92%|█████████▏| 25822/28080 [51:00:50<4:28:28,  7.13s/it]
 92%|█████████▏| 25823/28080 [51:00:57<4:28:38,  7.14s/it]
                                                          
{'loss': 0.6003, 'learning_rate': 8.423648405286532e-06, 'epoch': 11.03}

 92%|█████████▏| 25823/28080 [51:00:57<4:28:38,  7.14s/it]
 92%|█████████▏| 25824/28080 [51:01:04<4:27:42,  7.12s/it]
                                                          
{'loss': 0.5936, 'learning_rate': 8.416227751493838e-06, 'epoch': 11.03}

 92%|█████████▏| 25824/28080 [51:01:04<4:27:42,  7.12s/it]
 92%|█████████▏| 25825/28080 [51:01:11<4:27:37,  7.12s/it]
                                                          
{'loss': 0.5867, 'learning_rate': 8.408810311723997e-06, 'epoch': 11.03}

 92%|█████████▏| 25825/28080 [51:01:11<4:27:37,  7.12s/it]
 92%|█████████▏| 25826/28080 [51:01:18<4:27:35,  7.12s/it]
                                                          
{'loss': 0.6062, 'learning_rate': 8.401396086075708e-06, 'epoch': 11.03}

 92%|█████████▏| 25826/28080 [51:01:18<4:27:35,  7.12s/it]
 92%|█████████▏| 25827/28080 [51:01:25<4:26:32,  7.10s/it]
                                                          
{'loss': 0.6194, 'learning_rate': 8.393985074647615e-06, 'epoch': 11.03}

 92%|█████████▏| 25827/28080 [51:01:25<4:26:32,  7.10s/it]
 92%|█████████▏| 25828/28080 [51:01:32<4:27:22,  7.12s/it]
                                                          
{'loss': 0.5877, 'learning_rate': 8.386577277538305e-06, 'epoch': 11.03}

 92%|█████████▏| 25828/28080 [51:01:32<4:27:22,  7.12s/it]
 92%|█████████▏| 25829/28080 [51:01:39<4:27:31,  7.13s/it]
                                                          
{'loss': 0.5821, 'learning_rate': 8.379172694846283e-06, 'epoch': 11.03}

 92%|█████████▏| 25829/28080 [51:01:39<4:27:31,  7.13s/it]
 92%|█████████▏| 25830/28080 [51:01:47<4:27:39,  7.14s/it]
                                                          
{'loss': 0.6036, 'learning_rate': 8.371771326670109e-06, 'epoch': 11.03}

 92%|█████████▏| 25830/28080 [51:01:47<4:27:39,  7.14s/it]
 92%|█████████▏| 25831/28080 [51:01:54<4:27:56,  7.15s/it]
                                                          
{'loss': 0.6152, 'learning_rate': 8.36437317310826e-06, 'epoch': 11.03}

 92%|█████████▏| 25831/28080 [51:01:54<4:27:56,  7.15s/it]
 92%|█████████▏| 25832/28080 [51:02:01<4:27:45,  7.15s/it]
                                                          
{'loss': 0.6212, 'learning_rate': 8.356978234259155e-06, 'epoch': 11.04}

 92%|█████████▏| 25832/28080 [51:02:01<4:27:45,  7.15s/it]
 92%|█████████▏| 25833/28080 [51:02:08<4:27:29,  7.14s/it]
                                                          
{'loss': 0.6077, 'learning_rate': 8.349586510221135e-06, 'epoch': 11.04}

 92%|█████████▏| 25833/28080 [51:02:08<4:27:29,  7.14s/it]
 92%|█████████▏| 25834/28080 [51:02:15<4:27:31,  7.15s/it]
                                                          
{'loss': 0.5941, 'learning_rate': 8.342198001092594e-06, 'epoch': 11.04}

 92%|█████████▏| 25834/28080 [51:02:15<4:27:31,  7.15s/it]
 92%|█████████▏| 25835/28080 [51:02:22<4:26:49,  7.13s/it]
                                                          
{'loss': 0.5907, 'learning_rate': 8.334812706971812e-06, 'epoch': 11.04}

 92%|█████████▏| 25835/28080 [51:02:22<4:26:49,  7.13s/it]
 92%|█████████▏| 25836/28080 [51:02:29<4:27:19,  7.15s/it]
                                                          
{'loss': 0.6101, 'learning_rate': 8.327430627957016e-06, 'epoch': 11.04}

 92%|█████████▏| 25836/28080 [51:02:29<4:27:19,  7.15s/it]
 92%|█████████▏| 25837/28080 [51:02:37<4:27:10,  7.15s/it]
                                                          
{'loss': 0.5828, 'learning_rate': 8.320051764146436e-06, 'epoch': 11.04}

 92%|█████████▏| 25837/28080 [51:02:37<4:27:10,  7.15s/it]
 92%|█████████▏| 25838/28080 [51:02:44<4:27:10,  7.15s/it]
                                                          
{'loss': 0.5928, 'learning_rate': 8.312676115638241e-06, 'epoch': 11.04}

 92%|█████████▏| 25838/28080 [51:02:44<4:27:10,  7.15s/it]
 92%|█████████▏| 25839/28080 [51:02:51<4:26:48,  7.14s/it]
                                                          
{'loss': 0.583, 'learning_rate': 8.305303682530573e-06, 'epoch': 11.04}

 92%|█████████▏| 25839/28080 [51:02:51<4:26:48,  7.14s/it]
 92%|█████████▏| 25840/28080 [51:02:58<4:25:25,  7.11s/it]
                                                          
{'loss': 0.5839, 'learning_rate': 8.297934464921469e-06, 'epoch': 11.04}

 92%|█████████▏| 25840/28080 [51:02:58<4:25:25,  7.11s/it]
 92%|█████████▏| 25841/28080 [51:03:05<4:25:09,  7.11s/it]
                                                          
{'loss': 0.5971, 'learning_rate': 8.290568462909015e-06, 'epoch': 11.04}

 92%|█████████▏| 25841/28080 [51:03:05<4:25:09,  7.11s/it]
 92%|█████████▏| 25842/28080 [51:03:12<4:26:44,  7.15s/it]
                                                          
{'loss': 0.5895, 'learning_rate': 8.283205676591188e-06, 'epoch': 11.04}

 92%|█████████▏| 25842/28080 [51:03:12<4:26:44,  7.15s/it]
 92%|█████████▏| 25843/28080 [51:03:19<4:26:03,  7.14s/it]
                                                          
{'loss': 0.6073, 'learning_rate': 8.275846106065966e-06, 'epoch': 11.04}

 92%|█████████▏| 25843/28080 [51:03:19<4:26:03,  7.14s/it]
 92%|█████████▏| 25844/28080 [51:03:27<4:26:20,  7.15s/it]
                                                          
{'loss': 0.5968, 'learning_rate': 8.268489751431185e-06, 'epoch': 11.04}

 92%|█████████▏| 25844/28080 [51:03:27<4:26:20,  7.15s/it]
 92%|█████████▏| 25845/28080 [51:03:34<4:25:52,  7.14s/it]
                                                          
{'loss': 0.5922, 'learning_rate': 8.261136612784798e-06, 'epoch': 11.04}

 92%|█████████▏| 25845/28080 [51:03:34<4:25:52,  7.14s/it]
 92%|█████████▏| 25846/28080 [51:03:41<4:25:08,  7.12s/it]
                                                          
{'loss': 0.6233, 'learning_rate': 8.253786690224613e-06, 'epoch': 11.04}

 92%|█████████▏| 25846/28080 [51:03:41<4:25:08,  7.12s/it]
 92%|█████████▏| 25847/28080 [51:03:48<4:25:58,  7.15s/it]
                                                          
{'loss': 0.5966, 'learning_rate': 8.246439983848387e-06, 'epoch': 11.04}

 92%|█████████▏| 25847/28080 [51:03:48<4:25:58,  7.15s/it]
 92%|█████████▏| 25848/28080 [51:03:55<4:25:21,  7.13s/it]
                                                          
{'loss': 0.5828, 'learning_rate': 8.239096493753844e-06, 'epoch': 11.04}

 92%|█████████▏| 25848/28080 [51:03:55<4:25:21,  7.13s/it]
 92%|█████████▏| 25849/28080 [51:04:02<4:24:26,  7.11s/it]
                                                          
{'loss': 0.6037, 'learning_rate': 8.231756220038773e-06, 'epoch': 11.04}

 92%|█████████▏| 25849/28080 [51:04:02<4:24:26,  7.11s/it]
 92%|█████████▏| 25850/28080 [51:04:09<4:25:18,  7.14s/it]
                                                          
{'loss': 0.584, 'learning_rate': 8.2244191628007e-06, 'epoch': 11.04}

 92%|█████████▏| 25850/28080 [51:04:09<4:25:18,  7.14s/it]
 92%|█████████▏| 25851/28080 [51:04:17<4:25:34,  7.15s/it]
                                                          
{'loss': 0.6063, 'learning_rate': 8.217085322137357e-06, 'epoch': 11.04}

 92%|█████████▏| 25851/28080 [51:04:17<4:25:34,  7.15s/it]
 92%|█████████▏| 25852/28080 [51:04:24<4:25:31,  7.15s/it]
                                                          
{'loss': 0.5829, 'learning_rate': 8.209754698146249e-06, 'epoch': 11.04}

 92%|█████████▏| 25852/28080 [51:04:24<4:25:31,  7.15s/it]
 92%|█████████▏| 25853/28080 [51:04:31<4:25:09,  7.14s/it]
                                                          
{'loss': 0.5883, 'learning_rate': 8.202427290924908e-06, 'epoch': 11.04}

 92%|█████████▏| 25853/28080 [51:04:31<4:25:09,  7.14s/it]
 92%|█████████▏| 25854/28080 [51:04:38<4:24:33,  7.13s/it]
                                                          
{'loss': 0.6041, 'learning_rate': 8.195103100570784e-06, 'epoch': 11.04}

 92%|█████████▏| 25854/28080 [51:04:38<4:24:33,  7.13s/it]
 92%|█████████▏| 25855/28080 [51:04:45<4:22:50,  7.09s/it]
                                                          
{'loss': 0.6114, 'learning_rate': 8.18778212718141e-06, 'epoch': 11.05}

 92%|█████████▏| 25855/28080 [51:04:45<4:22:50,  7.09s/it]
 92%|█████████▏| 25856/28080 [51:04:52<4:23:52,  7.12s/it]
                                                          
{'loss': 0.5937, 'learning_rate': 8.180464370854123e-06, 'epoch': 11.05}

 92%|█████████▏| 25856/28080 [51:04:52<4:23:52,  7.12s/it]
 92%|█████████▏| 25857/28080 [51:04:59<4:24:34,  7.14s/it]
                                                          
{'loss': 0.6129, 'learning_rate': 8.173149831686295e-06, 'epoch': 11.05}

 92%|█████████▏| 25857/28080 [51:04:59<4:24:34,  7.14s/it]
 92%|█████████▏| 25858/28080 [51:05:06<4:23:49,  7.12s/it]
                                                          
{'loss': 0.6082, 'learning_rate': 8.165838509775175e-06, 'epoch': 11.05}

 92%|█████████▏| 25858/28080 [51:05:06<4:23:49,  7.12s/it]
 92%|█████████▏| 25859/28080 [51:05:13<4:23:35,  7.12s/it]
                                                          
{'loss': 0.5888, 'learning_rate': 8.158530405218135e-06, 'epoch': 11.05}

 92%|█████████▏| 25859/28080 [51:05:13<4:23:35,  7.12s/it]
 92%|█████████▏| 25860/28080 [51:05:21<4:23:20,  7.12s/it]
                                                          
{'loss': 0.5726, 'learning_rate': 8.15122551811237e-06, 'epoch': 11.05}

 92%|█████████▏| 25860/28080 [51:05:21<4:23:20,  7.12s/it]
 92%|█████████▏| 25861/28080 [51:05:28<4:22:36,  7.10s/it]
                                                          
{'loss': 0.6069, 'learning_rate': 8.14392384855503e-06, 'epoch': 11.05}

 92%|█████████▏| 25861/28080 [51:05:28<4:22:36,  7.10s/it]
 92%|█████████▏| 25862/28080 [51:05:35<4:22:02,  7.09s/it]
                                                          
{'loss': 0.6019, 'learning_rate': 8.136625396643255e-06, 'epoch': 11.05}

 92%|█████████▏| 25862/28080 [51:05:35<4:22:02,  7.09s/it]
 92%|█████████▏| 25863/28080 [51:05:42<4:22:16,  7.10s/it]
                                                          
{'loss': 0.5821, 'learning_rate': 8.129330162474164e-06, 'epoch': 11.05}

 92%|█████████▏| 25863/28080 [51:05:42<4:22:16,  7.10s/it]
 92%|█████████▏| 25864/28080 [51:05:49<4:22:05,  7.10s/it]
                                                          
{'loss': 0.599, 'learning_rate': 8.122038146144817e-06, 'epoch': 11.05}

 92%|█████████▏| 25864/28080 [51:05:49<4:22:05,  7.10s/it]
 92%|█████████▏| 25865/28080 [51:05:56<4:20:28,  7.06s/it]
                                                          
{'loss': 0.6298, 'learning_rate': 8.11474934775222e-06, 'epoch': 11.05}

 92%|█████████▏| 25865/28080 [51:05:56<4:20:28,  7.06s/it]
 92%|█████████▏| 25866/28080 [51:06:03<4:21:31,  7.09s/it]
                                                          
{'loss': 0.5771, 'learning_rate': 8.10746376739338e-06, 'epoch': 11.05}

 92%|█████████▏| 25866/28080 [51:06:03<4:21:31,  7.09s/it]
 92%|█████████▏| 25867/28080 [51:06:10<4:20:18,  7.06s/it]
                                                          
{'loss': 0.5872, 'learning_rate': 8.100181405165136e-06, 'epoch': 11.05}

 92%|█████████▏| 25867/28080 [51:06:10<4:20:18,  7.06s/it]
 92%|█████████▏| 25868/28080 [51:06:17<4:21:12,  7.09s/it]
                                                          
{'loss': 0.5878, 'learning_rate': 8.092902261164465e-06, 'epoch': 11.05}

 92%|█████████▏| 25868/28080 [51:06:17<4:21:12,  7.09s/it]
 92%|█████████▏| 25869/28080 [51:06:24<4:21:05,  7.09s/it]
                                                          
{'loss': 0.6014, 'learning_rate': 8.085626335488123e-06, 'epoch': 11.05}

 92%|█████████▏| 25869/28080 [51:06:24<4:21:05,  7.09s/it]
 92%|█████████▏| 25870/28080 [51:06:31<4:18:47,  7.03s/it]
                                                          
{'loss': 0.6099, 'learning_rate': 8.078353628232977e-06, 'epoch': 11.05}

 92%|█████████▏| 25870/28080 [51:06:31<4:18:47,  7.03s/it]
 92%|█████████▏| 25871/28080 [51:06:38<4:18:41,  7.03s/it]
                                                          
{'loss': 0.6093, 'learning_rate': 8.071084139495755e-06, 'epoch': 11.05}

 92%|█████████▏| 25871/28080 [51:06:38<4:18:41,  7.03s/it]
 92%|█████████▏| 25872/28080 [51:06:45<4:18:59,  7.04s/it]
                                                          
{'loss': 0.6242, 'learning_rate': 8.063817869373213e-06, 'epoch': 11.05}

 92%|█████████▏| 25872/28080 [51:06:45<4:18:59,  7.04s/it]
 92%|█████████▏| 25873/28080 [51:06:52<4:20:11,  7.07s/it]
                                                          
{'loss': 0.5959, 'learning_rate': 8.056554817961913e-06, 'epoch': 11.05}

 92%|█████████▏| 25873/28080 [51:06:52<4:20:11,  7.07s/it]
 92%|█████████▏| 25874/28080 [51:07:00<4:20:39,  7.09s/it]
                                                          
{'loss': 0.5878, 'learning_rate': 8.049294985358586e-06, 'epoch': 11.05}

 92%|█████████▏| 25874/28080 [51:07:00<4:20:39,  7.09s/it]
 92%|█████████▏| 25875/28080 [51:07:07<4:19:34,  7.06s/it]
                                                          
{'loss': 0.6098, 'learning_rate': 8.042038371659815e-06, 'epoch': 11.05}

 92%|█████████▏| 25875/28080 [51:07:07<4:19:34,  7.06s/it]
 92%|█████████▏| 25876/28080 [51:07:14<4:19:13,  7.06s/it]
                                                          
{'loss': 0.5849, 'learning_rate': 8.034784976962083e-06, 'epoch': 11.05}

 92%|█████████▏| 25876/28080 [51:07:14<4:19:13,  7.06s/it]
 92%|█████████▏| 25877/28080 [51:07:21<4:20:25,  7.09s/it]
                                                          
{'loss': 0.618, 'learning_rate': 8.027534801361897e-06, 'epoch': 11.05}

 92%|█████████▏| 25877/28080 [51:07:21<4:20:25,  7.09s/it]
 92%|█████████▏| 25878/28080 [51:07:28<4:20:59,  7.11s/it]
                                                          
{'loss': 0.6056, 'learning_rate': 8.020287844955732e-06, 'epoch': 11.05}

 92%|█████████▏| 25878/28080 [51:07:28<4:20:59,  7.11s/it]
 92%|█████████▏| 25879/28080 [51:07:35<4:21:12,  7.12s/it]
                                                          
{'loss': 0.6079, 'learning_rate': 8.013044107840011e-06, 'epoch': 11.06}

 92%|█████████▏| 25879/28080 [51:07:35<4:21:12,  7.12s/it]
 92%|█████████▏| 25880/28080 [51:07:42<4:22:55,  7.17s/it]
                                                          
{'loss': 0.5945, 'learning_rate': 8.005803590111133e-06, 'epoch': 11.06}

 92%|█████████▏| 25880/28080 [51:07:42<4:22:55,  7.17s/it]
 92%|█████████▏| 25881/28080 [51:07:49<4:21:13,  7.13s/it]
                                                          
{'loss': 0.6087, 'learning_rate': 7.998566291865323e-06, 'epoch': 11.06}

 92%|█████████▏| 25881/28080 [51:07:49<4:21:13,  7.13s/it]
 92%|█████████▏| 25882/28080 [51:07:56<4:20:12,  7.10s/it]
                                                          
{'loss': 0.5881, 'learning_rate': 7.991332213198976e-06, 'epoch': 11.06}

 92%|█████████▏| 25882/28080 [51:07:56<4:20:12,  7.10s/it]
 92%|█████████▏| 25883/28080 [51:08:04<4:20:34,  7.12s/it]
                                                          
{'loss': 0.6105, 'learning_rate': 7.98410135420824e-06, 'epoch': 11.06}

 92%|█████████▏| 25883/28080 [51:08:04<4:20:34,  7.12s/it]
 92%|█████████▏| 25884/28080 [51:08:11<4:20:26,  7.12s/it]
                                                          
{'loss': 0.5848, 'learning_rate': 7.976873714989397e-06, 'epoch': 11.06}

 92%|█████████▏| 25884/28080 [51:08:11<4:20:26,  7.12s/it]
 92%|█████████▏| 25885/28080 [51:08:18<4:20:49,  7.13s/it]
                                                          
{'loss': 0.6222, 'learning_rate': 7.969649295638593e-06, 'epoch': 11.06}

 92%|█████████▏| 25885/28080 [51:08:18<4:20:49,  7.13s/it]
 92%|█████████▏| 25886/28080 [51:08:25<4:20:47,  7.13s/it]
                                                          
{'loss': 0.5912, 'learning_rate': 7.96242809625186e-06, 'epoch': 11.06}

 92%|█████████▏| 25886/28080 [51:08:25<4:20:47,  7.13s/it]
 92%|█████████▏| 25887/28080 [51:08:32<4:19:56,  7.11s/it]
                                                          
{'loss': 0.6093, 'learning_rate': 7.955210116925348e-06, 'epoch': 11.06}

 92%|█████████▏| 25887/28080 [51:08:32<4:19:56,  7.11s/it]
 92%|█████████▏| 25888/28080 [51:08:39<4:19:28,  7.10s/it]
                                                          
{'loss': 0.6105, 'learning_rate': 7.94799535775506e-06, 'epoch': 11.06}

 92%|█████████▏| 25888/28080 [51:08:39<4:19:28,  7.10s/it]
 92%|█████████▏| 25889/28080 [51:08:46<4:18:05,  7.07s/it]
                                                          
{'loss': 0.6191, 'learning_rate': 7.940783818836978e-06, 'epoch': 11.06}

 92%|█████████▏| 25889/28080 [51:08:46<4:18:05,  7.07s/it]
 92%|█████████▏| 25890/28080 [51:08:53<4:18:50,  7.09s/it]
                                                          
{'loss': 0.618, 'learning_rate': 7.933575500267076e-06, 'epoch': 11.06}

 92%|█████████▏| 25890/28080 [51:08:53<4:18:50,  7.09s/it]
 92%|█████████▏| 25891/28080 [51:09:00<4:18:40,  7.09s/it]
                                                          
{'loss': 0.5959, 'learning_rate': 7.926370402141225e-06, 'epoch': 11.06}

 92%|█████████▏| 25891/28080 [51:09:00<4:18:40,  7.09s/it]
 92%|█████████▏| 25892/28080 [51:09:07<4:19:18,  7.11s/it]
                                                          
{'loss': 0.5996, 'learning_rate': 7.919168524555237e-06, 'epoch': 11.06}

 92%|█████████▏| 25892/28080 [51:09:07<4:19:18,  7.11s/it]
 92%|█████████▏| 25893/28080 [51:09:15<4:19:00,  7.11s/it]
                                                          
{'loss': 0.6261, 'learning_rate': 7.911969867605006e-06, 'epoch': 11.06}

 92%|█████████▏| 25893/28080 [51:09:15<4:19:00,  7.11s/it]
 92%|█████████▏| 25894/28080 [51:09:22<4:19:40,  7.13s/it]
                                                          
{'loss': 0.6099, 'learning_rate': 7.904774431386263e-06, 'epoch': 11.06}

 92%|█████████▏| 25894/28080 [51:09:22<4:19:40,  7.13s/it]
 92%|█████████▏| 25895/28080 [51:09:29<4:19:30,  7.13s/it]
                                                          
{'loss': 0.594, 'learning_rate': 7.897582215994736e-06, 'epoch': 11.06}

 92%|█████████▏| 25895/28080 [51:09:29<4:19:30,  7.13s/it]
 92%|█████████▏| 25896/28080 [51:09:36<4:19:17,  7.12s/it]
                                                          
{'loss': 0.6049, 'learning_rate': 7.8903932215261e-06, 'epoch': 11.06}

 92%|█████████▏| 25896/28080 [51:09:36<4:19:17,  7.12s/it]
 92%|█████████▏| 25897/28080 [51:09:43<4:19:41,  7.14s/it]
                                                          
{'loss': 0.5982, 'learning_rate': 7.883207448076025e-06, 'epoch': 11.06}

 92%|█████████▏| 25897/28080 [51:09:43<4:19:41,  7.14s/it]
 92%|█████████▏| 25898/28080 [51:09:50<4:19:47,  7.14s/it]
                                                          
{'loss': 0.6252, 'learning_rate': 7.876024895740075e-06, 'epoch': 11.06}

 92%|█████████▏| 25898/28080 [51:09:50<4:19:47,  7.14s/it]
 92%|█████████▏| 25899/28080 [51:09:57<4:19:44,  7.15s/it]
                                                          
{'loss': 0.6225, 'learning_rate': 7.86884556461387e-06, 'epoch': 11.06}

 92%|█████████▏| 25899/28080 [51:09:57<4:19:44,  7.15s/it]
 92%|█████████▏| 25900/28080 [51:10:05<4:20:10,  7.16s/it]
                                                          
{'loss': 0.6066, 'learning_rate': 7.861669454792886e-06, 'epoch': 11.06}

 92%|█████████▏| 25900/28080 [51:10:05<4:20:10,  7.16s/it]
 92%|█████████▏| 25901/28080 [51:10:12<4:19:47,  7.15s/it]
                                                          
{'loss': 0.6029, 'learning_rate': 7.85449656637255e-06, 'epoch': 11.06}

 92%|█████████▏| 25901/28080 [51:10:12<4:19:47,  7.15s/it]
 92%|█████████▏| 25902/28080 [51:10:19<4:18:35,  7.12s/it]
                                                          
{'loss': 0.6017, 'learning_rate': 7.847326899448337e-06, 'epoch': 11.07}

 92%|█████████▏| 25902/28080 [51:10:19<4:18:35,  7.12s/it]
 92%|█████████▏| 25903/28080 [51:10:26<4:18:01,  7.11s/it]
                                                          
{'loss': 0.6055, 'learning_rate': 7.840160454115646e-06, 'epoch': 11.07}

 92%|█████████▏| 25903/28080 [51:10:26<4:18:01,  7.11s/it]
 92%|█████████▏| 25904/28080 [51:10:33<4:18:23,  7.12s/it]
                                                          
{'loss': 0.5822, 'learning_rate': 7.83299723046979e-06, 'epoch': 11.07}

 92%|█████████▏| 25904/28080 [51:10:33<4:18:23,  7.12s/it]
 92%|█████████▏| 25905/28080 [51:10:40<4:17:34,  7.11s/it]
                                                          
{'loss': 0.6127, 'learning_rate': 7.825837228606081e-06, 'epoch': 11.07}

 92%|█████████▏| 25905/28080 [51:10:40<4:17:34,  7.11s/it]
 92%|█████████▏| 25906/28080 [51:10:47<4:18:17,  7.13s/it]
                                                          
{'loss': 0.5937, 'learning_rate': 7.818680448619747e-06, 'epoch': 11.07}

 92%|█████████▏| 25906/28080 [51:10:47<4:18:17,  7.13s/it]
 92%|█████████▏| 25907/28080 [51:10:54<4:17:21,  7.11s/it]
                                                          
{'loss': 0.6102, 'learning_rate': 7.811526890606047e-06, 'epoch': 11.07}

 92%|█████████▏| 25907/28080 [51:10:54<4:17:21,  7.11s/it]
 92%|█████████▏| 25908/28080 [51:11:01<4:15:35,  7.06s/it]
                                                          
{'loss': 0.5961, 'learning_rate': 7.804376554660125e-06, 'epoch': 11.07}

 92%|█████████▏| 25908/28080 [51:11:01<4:15:35,  7.06s/it]
 92%|█████████▏| 25909/28080 [51:11:08<4:16:14,  7.08s/it]
                                                          
{'loss': 0.6069, 'learning_rate': 7.797229440877129e-06, 'epoch': 11.07}

 92%|█████████▏| 25909/28080 [51:11:08<4:16:14,  7.08s/it]
 92%|█████████▏| 25910/28080 [51:11:16<4:17:20,  7.12s/it]
                                                          
{'loss': 0.6014, 'learning_rate': 7.790085549352094e-06, 'epoch': 11.07}

 92%|█████████▏| 25910/28080 [51:11:16<4:17:20,  7.12s/it]
 92%|█████████▏| 25911/28080 [51:11:23<4:16:50,  7.11s/it]
                                                          
{'loss': 0.5919, 'learning_rate': 7.78294488018011e-06, 'epoch': 11.07}

 92%|█████████▏| 25911/28080 [51:11:23<4:16:50,  7.11s/it]
 92%|█████████▏| 25912/28080 [51:11:30<4:17:22,  7.12s/it]
                                                          
{'loss': 0.5732, 'learning_rate': 7.775807433456183e-06, 'epoch': 11.07}

 92%|█████████▏| 25912/28080 [51:11:30<4:17:22,  7.12s/it]
 92%|█████████▏| 25913/28080 [51:11:37<4:18:01,  7.14s/it]
                                                          
{'loss': 0.6267, 'learning_rate': 7.768673209275212e-06, 'epoch': 11.07}

 92%|█████████▏| 25913/28080 [51:11:37<4:18:01,  7.14s/it]
 92%|█████████▏| 25914/28080 [51:11:44<4:18:08,  7.15s/it]
                                                          
{'loss': 0.5819, 'learning_rate': 7.761542207732203e-06, 'epoch': 11.07}

 92%|█████████▏| 25914/28080 [51:11:44<4:18:08,  7.15s/it]
 92%|█████████▏| 25915/28080 [51:11:51<4:16:27,  7.11s/it]
                                                          
{'loss': 0.6069, 'learning_rate': 7.754414428921912e-06, 'epoch': 11.07}

 92%|█████████▏| 25915/28080 [51:11:51<4:16:27,  7.11s/it]
 92%|█████████▏| 25916/28080 [51:11:58<4:17:13,  7.13s/it]
                                                          
{'loss': 0.601, 'learning_rate': 7.74728987293924e-06, 'epoch': 11.07}

 92%|█████████▏| 25916/28080 [51:11:58<4:17:13,  7.13s/it]
 92%|█████████▏| 25917/28080 [51:12:06<4:17:45,  7.15s/it]
                                                          
{'loss': 0.6073, 'learning_rate': 7.740168539878966e-06, 'epoch': 11.07}

 92%|█████████▏| 25917/28080 [51:12:06<4:17:45,  7.15s/it]
 92%|█████████▏| 25918/28080 [51:12:13<4:15:38,  7.09s/it]
                                                          
{'loss': 0.5943, 'learning_rate': 7.733050429835824e-06, 'epoch': 11.07}

 92%|█████████▏| 25918/28080 [51:12:13<4:15:38,  7.09s/it]
 92%|█████████▏| 25919/28080 [51:12:20<4:16:28,  7.12s/it]
                                                          
{'loss': 0.6126, 'learning_rate': 7.725935542904516e-06, 'epoch': 11.07}

 92%|█████████▏| 25919/28080 [51:12:20<4:16:28,  7.12s/it]
 92%|█████████▏| 25920/28080 [51:12:27<4:17:14,  7.15s/it]
                                                          
{'loss': 0.587, 'learning_rate': 7.718823879179715e-06, 'epoch': 11.07}

 92%|█████████▏| 25920/28080 [51:12:27<4:17:14,  7.15s/it]
 92%|█████████▏| 25921/28080 [51:12:34<4:17:06,  7.15s/it]
                                                          
{'loss': 0.6086, 'learning_rate': 7.711715438755984e-06, 'epoch': 11.07}

 92%|█████████▏| 25921/28080 [51:12:34<4:17:06,  7.15s/it]
 92%|█████████▏| 25922/28080 [51:12:41<4:18:31,  7.19s/it]
                                                          
{'loss': 0.5861, 'learning_rate': 7.704610221727943e-06, 'epoch': 11.07}

 92%|█████████▏| 25922/28080 [51:12:41<4:18:31,  7.19s/it]
 92%|█████████▏| 25923/28080 [51:12:49<4:17:28,  7.16s/it]
                                                          
{'loss': 0.6068, 'learning_rate': 7.697508228190097e-06, 'epoch': 11.07}

 92%|█████████▏| 25923/28080 [51:12:49<4:17:28,  7.16s/it]
 92%|█████████▏| 25924/28080 [51:12:56<4:16:00,  7.12s/it]
                                                          
{'loss': 0.6136, 'learning_rate': 7.69040945823693e-06, 'epoch': 11.07}

 92%|█████████▏| 25924/28080 [51:12:56<4:16:00,  7.12s/it]
 92%|█████████▏| 25925/28080 [51:13:03<4:15:44,  7.12s/it]
                                                          
{'loss': 0.6056, 'learning_rate': 7.683313911962863e-06, 'epoch': 11.07}

 92%|█████████▏| 25925/28080 [51:13:03<4:15:44,  7.12s/it]
 92%|█████████▏| 25926/28080 [51:13:10<4:15:14,  7.11s/it]
                                                          
{'loss': 0.6057, 'learning_rate': 7.676221589462351e-06, 'epoch': 11.08}

 92%|█████████▏| 25926/28080 [51:13:10<4:15:14,  7.11s/it]
 92%|█████████▏| 25927/28080 [51:13:17<4:15:27,  7.12s/it]
                                                          
{'loss': 0.6048, 'learning_rate': 7.669132490829706e-06, 'epoch': 11.08}

 92%|█████████▏| 25927/28080 [51:13:17<4:15:27,  7.12s/it]
 92%|█████████▏| 25928/28080 [51:13:24<4:15:30,  7.12s/it]
                                                          
{'loss': 0.5891, 'learning_rate': 7.662046616159296e-06, 'epoch': 11.08}

 92%|█████████▏| 25928/28080 [51:13:24<4:15:30,  7.12s/it]
 92%|█████████▏| 25929/28080 [51:13:31<4:15:49,  7.14s/it]
                                                          
{'loss': 0.6171, 'learning_rate': 7.654963965545297e-06, 'epoch': 11.08}

 92%|█████████▏| 25929/28080 [51:13:31<4:15:49,  7.14s/it]
 92%|█████████▏| 25930/28080 [51:13:38<4:14:49,  7.11s/it]
                                                          
{'loss': 0.6093, 'learning_rate': 7.647884539082023e-06, 'epoch': 11.08}

 92%|█████████▏| 25930/28080 [51:13:38<4:14:49,  7.11s/it]
 92%|█████████▏| 25931/28080 [51:13:45<4:14:18,  7.10s/it]
                                                          
{'loss': 0.5968, 'learning_rate': 7.640808336863592e-06, 'epoch': 11.08}

 92%|█████████▏| 25931/28080 [51:13:45<4:14:18,  7.10s/it]
 92%|█████████▏| 25932/28080 [51:13:52<4:13:40,  7.09s/it]
                                                          
{'loss': 0.5966, 'learning_rate': 7.633735358984207e-06, 'epoch': 11.08}

 92%|█████████▏| 25932/28080 [51:13:52<4:13:40,  7.09s/it]
 92%|█████████▏| 25933/28080 [51:14:00<4:14:12,  7.10s/it]
                                                          
{'loss': 0.6004, 'learning_rate': 7.626665605537958e-06, 'epoch': 11.08}

 92%|█████████▏| 25933/28080 [51:14:00<4:14:12,  7.10s/it]
 92%|█████████▏| 25934/28080 [51:14:07<4:14:00,  7.10s/it]
                                                          
{'loss': 0.6066, 'learning_rate': 7.619599076618827e-06, 'epoch': 11.08}

 92%|█████████▏| 25934/28080 [51:14:07<4:14:00,  7.10s/it]
 92%|█████████▏| 25935/28080 [51:14:14<4:14:28,  7.12s/it]
                                                          
{'loss': 0.6099, 'learning_rate': 7.612535772320905e-06, 'epoch': 11.08}

 92%|█████████▏| 25935/28080 [51:14:14<4:14:28,  7.12s/it]
 92%|█████████▏| 25936/28080 [51:14:21<4:14:24,  7.12s/it]
                                                          
{'loss': 0.5917, 'learning_rate': 7.605475692738118e-06, 'epoch': 11.08}

 92%|█████████▏| 25936/28080 [51:14:21<4:14:24,  7.12s/it]
 92%|█████████▏| 25937/28080 [51:14:28<4:13:16,  7.09s/it]
                                                          
{'loss': 0.5936, 'learning_rate': 7.598418837964416e-06, 'epoch': 11.08}

 92%|█████████▏| 25937/28080 [51:14:28<4:13:16,  7.09s/it]
 92%|█████████▏| 25938/28080 [51:14:35<4:12:21,  7.07s/it]
                                                          
{'loss': 0.6233, 'learning_rate': 7.591365208093698e-06, 'epoch': 11.08}

 92%|█████████▏| 25938/28080 [51:14:35<4:12:21,  7.07s/it]
 92%|█████████▏| 25939/28080 [51:14:42<4:11:16,  7.04s/it]
                                                          
{'loss': 0.6154, 'learning_rate': 7.584314803219805e-06, 'epoch': 11.08}

 92%|█████████▏| 25939/28080 [51:14:42<4:11:16,  7.04s/it]
 92%|█████████▏| 25940/28080 [51:14:49<4:12:12,  7.07s/it]
                                                          
{'loss': 0.5881, 'learning_rate': 7.577267623436468e-06, 'epoch': 11.08}

 92%|█████████▏| 25940/28080 [51:14:49<4:12:12,  7.07s/it]
 92%|█████████▏| 25941/28080 [51:14:56<4:13:09,  7.10s/it]
                                                          
{'loss': 0.5741, 'learning_rate': 7.570223668837528e-06, 'epoch': 11.08}

 92%|█████████▏| 25941/28080 [51:14:56<4:13:09,  7.10s/it]
 92%|█████████▏| 25942/28080 [51:15:03<4:14:03,  7.13s/it]
                                                          
{'loss': 0.5938, 'learning_rate': 7.56318293951666e-06, 'epoch': 11.08}

 92%|█████████▏| 25942/28080 [51:15:03<4:14:03,  7.13s/it]
 92%|█████████▏| 25943/28080 [51:15:10<4:12:55,  7.10s/it]
                                                          
{'loss': 0.6329, 'learning_rate': 7.556145435567541e-06, 'epoch': 11.08}

 92%|█████████▏| 25943/28080 [51:15:10<4:12:55,  7.10s/it]
 92%|█████████▏| 25944/28080 [51:15:18<4:12:23,  7.09s/it]
                                                          
{'loss': 0.6024, 'learning_rate': 7.549111157083733e-06, 'epoch': 11.08}

 92%|█████████▏| 25944/28080 [51:15:18<4:12:23,  7.09s/it]
 92%|█████████▏| 25945/28080 [51:15:25<4:11:33,  7.07s/it]
                                                          
{'loss': 0.5912, 'learning_rate': 7.542080104158938e-06, 'epoch': 11.08}

 92%|█████████▏| 25945/28080 [51:15:25<4:11:33,  7.07s/it]
 92%|█████████▏| 25946/28080 [51:15:32<4:10:59,  7.06s/it]
                                                          
{'loss': 0.6425, 'learning_rate': 7.535052276886612e-06, 'epoch': 11.08}

 92%|█████████▏| 25946/28080 [51:15:32<4:10:59,  7.06s/it]
 92%|█████████▏| 25947/28080 [51:15:39<4:10:55,  7.06s/it]
                                                          
{'loss': 0.6068, 'learning_rate': 7.528027675360316e-06, 'epoch': 11.08}

 92%|█████████▏| 25947/28080 [51:15:39<4:10:55,  7.06s/it]
 92%|█████████▏| 25948/28080 [51:15:46<4:10:50,  7.06s/it]
                                                          
{'loss': 0.5894, 'learning_rate': 7.521006299673422e-06, 'epoch': 11.08}

 92%|█████████▏| 25948/28080 [51:15:46<4:10:50,  7.06s/it]
 92%|█████████▏| 25949/28080 [51:15:53<4:09:59,  7.04s/it]
                                                          
{'loss': 0.5986, 'learning_rate': 7.51398814991941e-06, 'epoch': 11.09}

 92%|█████████▏| 25949/28080 [51:15:53<4:09:59,  7.04s/it]
 92%|█████████▏| 25950/28080 [51:16:00<4:09:47,  7.04s/it]
                                                          
{'loss': 0.5782, 'learning_rate': 7.506973226191593e-06, 'epoch': 11.09}

 92%|█████████▏| 25950/28080 [51:16:00<4:09:47,  7.04s/it]
 92%|█████████▏| 25951/28080 [51:16:07<4:10:37,  7.06s/it]
                                                          
{'loss': 0.6116, 'learning_rate': 7.4999615285833715e-06, 'epoch': 11.09}

 92%|█████████▏| 25951/28080 [51:16:07<4:10:37,  7.06s/it]
 92%|█████████▏| 25952/28080 [51:16:14<4:11:28,  7.09s/it]
                                                          
{'loss': 0.604, 'learning_rate': 7.492953057187973e-06, 'epoch': 11.09}

 92%|█████████▏| 25952/28080 [51:16:14<4:11:28,  7.09s/it]
 92%|█████████▏| 25953/28080 [51:16:21<4:10:58,  7.08s/it]
                                                          
{'loss': 0.5945, 'learning_rate': 7.485947812098659e-06, 'epoch': 11.09}

 92%|█████████▏| 25953/28080 [51:16:21<4:10:58,  7.08s/it]
 92%|█████████▏| 25954/28080 [51:16:28<4:11:39,  7.10s/it]
                                                          
{'loss': 0.6131, 'learning_rate': 7.478945793408604e-06, 'epoch': 11.09}

 92%|█████████▏| 25954/28080 [51:16:28<4:11:39,  7.10s/it]
 92%|█████████▏| 25955/28080 [51:16:35<4:11:42,  7.11s/it]
                                                          
{'loss': 0.5905, 'learning_rate': 7.4719470012110104e-06, 'epoch': 11.09}

 92%|█████████▏| 25955/28080 [51:16:35<4:11:42,  7.11s/it]
 92%|█████████▏| 25956/28080 [51:16:42<4:12:02,  7.12s/it]
                                                          
{'loss': 0.6262, 'learning_rate': 7.4649514355989436e-06, 'epoch': 11.09}

 92%|█████████▏| 25956/28080 [51:16:43<4:12:02,  7.12s/it]
 92%|█████████▏| 25957/28080 [51:16:50<4:11:06,  7.10s/it]
                                                          
{'loss': 0.5884, 'learning_rate': 7.4579590966654954e-06, 'epoch': 11.09}

 92%|█████████▏| 25957/28080 [51:16:50<4:11:06,  7.10s/it]
 92%|█████████▏| 25958/28080 [51:16:57<4:10:49,  7.09s/it]
                                                          
{'loss': 0.6003, 'learning_rate': 7.450969984503675e-06, 'epoch': 11.09}

 92%|█████████▏| 25958/28080 [51:16:57<4:10:49,  7.09s/it]
 92%|█████████▏| 25959/28080 [51:17:04<4:10:15,  7.08s/it]
                                                          
{'loss': 0.5989, 'learning_rate': 7.443984099206464e-06, 'epoch': 11.09}

 92%|█████████▏| 25959/28080 [51:17:04<4:10:15,  7.08s/it]
 92%|█████████▏| 25960/28080 [51:17:11<4:11:41,  7.12s/it]
                                                          
{'loss': 0.5931, 'learning_rate': 7.437001440866842e-06, 'epoch': 11.09}

 92%|█████████▏| 25960/28080 [51:17:11<4:11:41,  7.12s/it]
 92%|█████████▏| 25961/28080 [51:17:18<4:12:19,  7.14s/it]
                                                          
{'loss': 0.5914, 'learning_rate': 7.430022009577625e-06, 'epoch': 11.09}

 92%|█████████▏| 25961/28080 [51:17:18<4:12:19,  7.14s/it]
 92%|█████████▏| 25962/28080 [51:17:25<4:10:23,  7.09s/it]
                                                          
{'loss': 0.6061, 'learning_rate': 7.423045805431794e-06, 'epoch': 11.09}

 92%|█████████▏| 25962/28080 [51:17:25<4:10:23,  7.09s/it]
 92%|█████████▏| 25963/28080 [51:17:32<4:12:14,  7.15s/it]
                                                          
{'loss': 0.5714, 'learning_rate': 7.416072828522025e-06, 'epoch': 11.09}

 92%|█████████▏| 25963/28080 [51:17:32<4:12:14,  7.15s/it]
 92%|█████████▏| 25964/28080 [51:17:39<4:11:05,  7.12s/it]
                                                          
{'loss': 0.6026, 'learning_rate': 7.409103078941187e-06, 'epoch': 11.09}

 92%|█████████▏| 25964/28080 [51:17:39<4:11:05,  7.12s/it]
 92%|█████████▏| 25965/28080 [51:17:47<4:11:08,  7.12s/it]
                                                          
{'loss': 0.6214, 'learning_rate': 7.40213655678193e-06, 'epoch': 11.09}

 92%|█████████▏| 25965/28080 [51:17:47<4:11:08,  7.12s/it]
 92%|█████████▏| 25966/28080 [51:17:54<4:12:16,  7.16s/it]
                                                          
{'loss': 0.6029, 'learning_rate': 7.3951732621370115e-06, 'epoch': 11.09}

 92%|█████████▏| 25966/28080 [51:17:54<4:12:16,  7.16s/it]
 92%|█████████▏| 25967/28080 [51:18:01<4:11:17,  7.14s/it]
                                                          
{'loss': 0.6086, 'learning_rate': 7.388213195098997e-06, 'epoch': 11.09}

 92%|█████████▏| 25967/28080 [51:18:01<4:11:17,  7.14s/it]
 92%|█████████▏| 25968/28080 [51:18:08<4:10:34,  7.12s/it]
                                                          
{'loss': 0.606, 'learning_rate': 7.381256355760563e-06, 'epoch': 11.09}

 92%|█████████▏| 25968/28080 [51:18:08<4:10:34,  7.12s/it]
 92%|█████████▏| 25969/28080 [51:18:15<4:10:42,  7.13s/it]
                                                          
{'loss': 0.6113, 'learning_rate': 7.374302744214162e-06, 'epoch': 11.09}

 92%|█████████▏| 25969/28080 [51:18:15<4:10:42,  7.13s/it]
 92%|█████████▏| 25970/28080 [51:18:22<4:10:26,  7.12s/it]
                                                          
{'loss': 0.5956, 'learning_rate': 7.367352360552387e-06, 'epoch': 11.09}

 92%|█████████▏| 25970/28080 [51:18:22<4:10:26,  7.12s/it]
 92%|█████████▏| 25971/28080 [51:18:29<4:10:53,  7.14s/it]
                                                          
{'loss': 0.6026, 'learning_rate': 7.360405204867665e-06, 'epoch': 11.09}

 92%|█████████▏| 25971/28080 [51:18:29<4:10:53,  7.14s/it]
 92%|█████████▏| 25972/28080 [51:18:36<4:09:39,  7.11s/it]
                                                          
{'loss': 0.6028, 'learning_rate': 7.353461277252477e-06, 'epoch': 11.09}

 92%|█████████▏| 25972/28080 [51:18:36<4:09:39,  7.11s/it]
 92%|█████████▏| 25973/28080 [51:18:44<4:09:36,  7.11s/it]
                                                          
{'loss': 0.5837, 'learning_rate': 7.34652057779911e-06, 'epoch': 11.1}

 92%|█████████▏| 25973/28080 [51:18:44<4:09:36,  7.11s/it]
 92%|█████████▎| 25974/28080 [51:18:51<4:09:18,  7.10s/it]
                                                          
{'loss': 0.6228, 'learning_rate': 7.339583106599962e-06, 'epoch': 11.1}

 92%|█████████▎| 25974/28080 [51:18:51<4:09:18,  7.10s/it]
 93%|█████████▎| 25975/28080 [51:18:58<4:10:08,  7.13s/it]
                                                          
{'loss': 0.5789, 'learning_rate': 7.332648863747321e-06, 'epoch': 11.1}

 93%|█████████▎| 25975/28080 [51:18:58<4:10:08,  7.13s/it]
 93%|█████████▎| 25976/28080 [51:19:05<4:08:29,  7.09s/it]
                                                          
{'loss': 0.5867, 'learning_rate': 7.325717849333502e-06, 'epoch': 11.1}

 93%|█████████▎| 25976/28080 [51:19:05<4:08:29,  7.09s/it]
 93%|█████████▎| 25977/28080 [51:19:12<4:08:44,  7.10s/it]
                                                          
{'loss': 0.5853, 'learning_rate': 7.31879006345057e-06, 'epoch': 11.1}

 93%|█████████▎| 25977/28080 [51:19:12<4:08:44,  7.10s/it]
 93%|█████████▎| 25978/28080 [51:19:19<4:08:24,  7.09s/it]
                                                          
{'loss': 0.5944, 'learning_rate': 7.31186550619084e-06, 'epoch': 11.1}

 93%|█████████▎| 25978/28080 [51:19:19<4:08:24,  7.09s/it]
 93%|█████████▎| 25979/28080 [51:19:26<4:08:49,  7.11s/it]
                                                          
{'loss': 0.5962, 'learning_rate': 7.304944177646322e-06, 'epoch': 11.1}

 93%|█████████▎| 25979/28080 [51:19:26<4:08:49,  7.11s/it]
 93%|█████████▎| 25980/28080 [51:19:33<4:09:07,  7.12s/it]
                                                          
{'loss': 0.5941, 'learning_rate': 7.298026077909164e-06, 'epoch': 11.1}

 93%|█████████▎| 25980/28080 [51:19:33<4:09:07,  7.12s/it]
 93%|█████████▎| 25981/28080 [51:19:40<4:09:08,  7.12s/it]
                                                          
{'loss': 0.5897, 'learning_rate': 7.291111207071405e-06, 'epoch': 11.1}

 93%|█████████▎| 25981/28080 [51:19:40<4:09:08,  7.12s/it]
 93%|█████████▎| 25982/28080 [51:19:48<4:09:09,  7.13s/it]
                                                          
{'loss': 0.6011, 'learning_rate': 7.284199565225025e-06, 'epoch': 11.1}

 93%|█████████▎| 25982/28080 [51:19:48<4:09:09,  7.13s/it]
 93%|█████████▎| 25983/28080 [51:19:55<4:08:28,  7.11s/it]
                                                          
{'loss': 0.5815, 'learning_rate': 7.277291152461951e-06, 'epoch': 11.1}

 93%|█████████▎| 25983/28080 [51:19:55<4:08:28,  7.11s/it]
 93%|█████████▎| 25984/28080 [51:20:02<4:08:02,  7.10s/it]
                                                          
{'loss': 0.6009, 'learning_rate': 7.270385968874111e-06, 'epoch': 11.1}

 93%|█████████▎| 25984/28080 [51:20:02<4:08:02,  7.10s/it]
 93%|█████████▎| 25985/28080 [51:20:09<4:09:00,  7.13s/it]
                                                          
{'loss': 0.6048, 'learning_rate': 7.263484014553401e-06, 'epoch': 11.1}

 93%|█████████▎| 25985/28080 [51:20:09<4:09:00,  7.13s/it]
 93%|█████████▎| 25986/28080 [51:20:16<4:08:10,  7.11s/it]
                                                          
{'loss': 0.6003, 'learning_rate': 7.256585289591611e-06, 'epoch': 11.1}

 93%|█████████▎| 25986/28080 [51:20:16<4:08:10,  7.11s/it]
 93%|█████████▎| 25987/28080 [51:20:23<4:08:46,  7.13s/it]
                                                          
{'loss': 0.6143, 'learning_rate': 7.249689794080528e-06, 'epoch': 11.1}

 93%|█████████▎| 25987/28080 [51:20:23<4:08:46,  7.13s/it]
 93%|█████████▎| 25988/28080 [51:20:30<4:09:48,  7.16s/it]
                                                          
{'loss': 0.5797, 'learning_rate': 7.242797528111856e-06, 'epoch': 11.1}

 93%|█████████▎| 25988/28080 [51:20:30<4:09:48,  7.16s/it]
 93%|█████████▎| 25989/28080 [51:20:37<4:08:40,  7.14s/it]
                                                          
{'loss': 0.603, 'learning_rate': 7.235908491777382e-06, 'epoch': 11.1}

 93%|█████████▎| 25989/28080 [51:20:37<4:08:40,  7.14s/it]
 93%|█████████▎| 25990/28080 [51:20:45<4:09:11,  7.15s/it]
                                                          
{'loss': 0.5876, 'learning_rate': 7.229022685168674e-06, 'epoch': 11.1}

 93%|█████████▎| 25990/28080 [51:20:45<4:09:11,  7.15s/it]
 93%|█████████▎| 25991/28080 [51:20:52<4:09:21,  7.16s/it]
                                                          
{'loss': 0.5972, 'learning_rate': 7.222140108377379e-06, 'epoch': 11.1}

 93%|█████████▎| 25991/28080 [51:20:52<4:09:21,  7.16s/it]
 93%|█████████▎| 25992/28080 [51:20:59<4:09:12,  7.16s/it]
                                                          
{'loss': 0.5908, 'learning_rate': 7.215260761495007e-06, 'epoch': 11.1}

 93%|█████████▎| 25992/28080 [51:20:59<4:09:12,  7.16s/it]
 93%|█████████▎| 25993/28080 [51:21:06<4:08:57,  7.16s/it]
                                                          
{'loss': 0.5792, 'learning_rate': 7.208384644613153e-06, 'epoch': 11.1}

 93%|█████████▎| 25993/28080 [51:21:06<4:08:57,  7.16s/it]
 93%|█████████▎| 25994/28080 [51:21:13<4:07:05,  7.11s/it]
                                                          
{'loss': 0.5929, 'learning_rate': 7.201511757823243e-06, 'epoch': 11.1}

 93%|█████████▎| 25994/28080 [51:21:13<4:07:05,  7.11s/it]
 93%|█████████▎| 25995/28080 [51:21:20<4:05:57,  7.08s/it]
                                                          
{'loss': 0.6325, 'learning_rate': 7.194642101216814e-06, 'epoch': 11.1}

 93%|█████████▎| 25995/28080 [51:21:20<4:05:57,  7.08s/it]
 93%|█████████▎| 25996/28080 [51:21:27<4:04:35,  7.04s/it]
                                                          
{'loss': 0.6262, 'learning_rate': 7.1877756748851e-06, 'epoch': 11.11}

 93%|█████████▎| 25996/28080 [51:21:27<4:04:35,  7.04s/it]
 93%|█████████▎| 25997/28080 [51:21:34<4:05:07,  7.06s/it]
                                                          
{'loss': 0.6026, 'learning_rate': 7.180912478919582e-06, 'epoch': 11.11}

 93%|█████████▎| 25997/28080 [51:21:34<4:05:07,  7.06s/it]
 93%|█████████▎| 25998/28080 [51:21:41<4:05:58,  7.09s/it]
                                                          
{'loss': 0.6064, 'learning_rate': 7.174052513411494e-06, 'epoch': 11.11}

 93%|█████████▎| 25998/28080 [51:21:41<4:05:58,  7.09s/it]
 93%|█████████▎| 25999/28080 [51:21:48<4:06:25,  7.11s/it]
                                                          
{'loss': 0.6119, 'learning_rate': 7.167195778452124e-06, 'epoch': 11.11}

 93%|█████████▎| 25999/28080 [51:21:48<4:06:25,  7.11s/it]
 93%|█████████▎| 26000/28080 [51:21:56<4:05:59,  7.10s/it]
                                                          
{'loss': 0.6015, 'learning_rate': 7.160342274132731e-06, 'epoch': 11.11}

 93%|█████████▎| 26000/28080 [51:21:56<4:05:59,  7.10s/it]
 93%|█████████▎| 26001/28080 [51:22:03<4:06:03,  7.10s/it]
                                                          
{'loss': 0.602, 'learning_rate': 7.153492000544437e-06, 'epoch': 11.11}

 93%|█████████▎| 26001/28080 [51:22:03<4:06:03,  7.10s/it]
 93%|█████████▎| 26002/28080 [51:22:10<4:06:40,  7.12s/it]
                                                          
{'loss': 0.6056, 'learning_rate': 7.146644957778392e-06, 'epoch': 11.11}

 93%|█████████▎| 26002/28080 [51:22:10<4:06:40,  7.12s/it]
 93%|█████████▎| 26003/28080 [51:22:17<4:06:30,  7.12s/it]
                                                          
{'loss': 0.6035, 'learning_rate': 7.139801145925717e-06, 'epoch': 11.11}

 93%|█████████▎| 26003/28080 [51:22:17<4:06:30,  7.12s/it]
 93%|█████████▎| 26004/28080 [51:22:24<4:06:10,  7.11s/it]
                                                          
{'loss': 0.6105, 'learning_rate': 7.132960565077451e-06, 'epoch': 11.11}

 93%|█████████▎| 26004/28080 [51:22:24<4:06:10,  7.11s/it]
 93%|█████████▎| 26005/28080 [51:22:31<4:06:38,  7.13s/it]
                                                          
{'loss': 0.5962, 'learning_rate': 7.126123215324576e-06, 'epoch': 11.11}

 93%|█████████▎| 26005/28080 [51:22:31<4:06:38,  7.13s/it]
 93%|█████████▎| 26006/28080 [51:22:38<4:04:45,  7.08s/it]
                                                          
{'loss': 0.6104, 'learning_rate': 7.119289096758075e-06, 'epoch': 11.11}

 93%|█████████▎| 26006/28080 [51:22:38<4:04:45,  7.08s/it]
 93%|█████████▎| 26007/28080 [51:22:45<4:04:22,  7.07s/it]
                                                          
{'loss': 0.6025, 'learning_rate': 7.112458209468875e-06, 'epoch': 11.11}

 93%|█████████▎| 26007/28080 [51:22:45<4:04:22,  7.07s/it]
 93%|█████████▎| 26008/28080 [51:22:52<4:05:17,  7.10s/it]
                                                          
{'loss': 0.5982, 'learning_rate': 7.105630553547821e-06, 'epoch': 11.11}

 93%|█████████▎| 26008/28080 [51:22:52<4:05:17,  7.10s/it]
 93%|█████████▎| 26009/28080 [51:23:00<4:05:30,  7.11s/it]
                                                          
{'loss': 0.6114, 'learning_rate': 7.098806129085811e-06, 'epoch': 11.11}

 93%|█████████▎| 26009/28080 [51:23:00<4:05:30,  7.11s/it]
 93%|█████████▎| 26010/28080 [51:23:07<4:05:40,  7.12s/it]
                                                          
{'loss': 0.6122, 'learning_rate': 7.091984936173579e-06, 'epoch': 11.11}

 93%|█████████▎| 26010/28080 [51:23:07<4:05:40,  7.12s/it]
 93%|█████████▎| 26011/28080 [51:23:14<4:05:17,  7.11s/it]
                                                          
{'loss': 0.6141, 'learning_rate': 7.085166974901885e-06, 'epoch': 11.11}

 93%|█████████▎| 26011/28080 [51:23:14<4:05:17,  7.11s/it]
 93%|█████████▎| 26012/28080 [51:23:21<4:04:35,  7.10s/it]
                                                          
{'loss': 0.5632, 'learning_rate': 7.078352245361436e-06, 'epoch': 11.11}

 93%|█████████▎| 26012/28080 [51:23:21<4:04:35,  7.10s/it]
 93%|█████████▎| 26013/28080 [51:23:28<4:04:55,  7.11s/it]
                                                          
{'loss': 0.6067, 'learning_rate': 7.071540747642907e-06, 'epoch': 11.11}

 93%|█████████▎| 26013/28080 [51:23:28<4:04:55,  7.11s/it]
 93%|█████████▎| 26014/28080 [51:23:35<4:04:54,  7.11s/it]
                                                          
{'loss': 0.6159, 'learning_rate': 7.064732481836922e-06, 'epoch': 11.11}

 93%|█████████▎| 26014/28080 [51:23:35<4:04:54,  7.11s/it]
 93%|█████████▎| 26015/28080 [51:23:42<4:04:13,  7.10s/it]
                                                          
{'loss': 0.5817, 'learning_rate': 7.057927448034046e-06, 'epoch': 11.11}

 93%|█████████▎| 26015/28080 [51:23:42<4:04:13,  7.10s/it]
 93%|█████████▎| 26016/28080 [51:23:49<4:04:58,  7.12s/it]
                                                          
{'loss': 0.5689, 'learning_rate': 7.051125646324819e-06, 'epoch': 11.11}

 93%|█████████▎| 26016/28080 [51:23:49<4:04:58,  7.12s/it]
 93%|█████████▎| 26017/28080 [51:23:56<4:04:59,  7.13s/it]
                                                          
{'loss': 0.5931, 'learning_rate': 7.044327076799723e-06, 'epoch': 11.11}

 93%|█████████▎| 26017/28080 [51:23:56<4:04:59,  7.13s/it]
 93%|█████████▎| 26018/28080 [51:24:04<4:04:14,  7.11s/it]
                                                          
{'loss': 0.5862, 'learning_rate': 7.037531739549214e-06, 'epoch': 11.11}

 93%|█████████▎| 26018/28080 [51:24:04<4:04:14,  7.11s/it]
 93%|█████████▎| 26019/28080 [51:24:11<4:03:16,  7.08s/it]
                                                          
{'loss': 0.6022, 'learning_rate': 7.030739634663719e-06, 'epoch': 11.12}

 93%|█████████▎| 26019/28080 [51:24:11<4:03:16,  7.08s/it]
 93%|█████████▎| 26020/28080 [51:24:18<4:03:09,  7.08s/it]
                                                          
{'loss': 0.6117, 'learning_rate': 7.023950762233555e-06, 'epoch': 11.12}

 93%|█████████▎| 26020/28080 [51:24:18<4:03:09,  7.08s/it]
 93%|█████████▎| 26021/28080 [51:24:25<4:04:02,  7.11s/it]
                                                          
{'loss': 0.6114, 'learning_rate': 7.017165122349039e-06, 'epoch': 11.12}

 93%|█████████▎| 26021/28080 [51:24:25<4:04:02,  7.11s/it]
 93%|█████████▎| 26022/28080 [51:24:32<4:04:06,  7.12s/it]
                                                          
{'loss': 0.5964, 'learning_rate': 7.0103827151004885e-06, 'epoch': 11.12}

 93%|█████████▎| 26022/28080 [51:24:32<4:04:06,  7.12s/it]
 93%|█████████▎| 26023/28080 [51:24:39<4:03:12,  7.09s/it]
                                                          
{'loss': 0.6031, 'learning_rate': 7.0036035405781075e-06, 'epoch': 11.12}

 93%|█████████▎| 26023/28080 [51:24:39<4:03:12,  7.09s/it]
 93%|█████████▎| 26024/28080 [51:24:46<4:02:48,  7.09s/it]
                                                          
{'loss': 0.6161, 'learning_rate': 6.99682759887213e-06, 'epoch': 11.12}

 93%|█████████▎| 26024/28080 [51:24:46<4:02:48,  7.09s/it]
 93%|█████████▎| 26025/28080 [51:24:53<4:03:24,  7.11s/it]
                                                          
{'loss': 0.6174, 'learning_rate': 6.99005489007265e-06, 'epoch': 11.12}

 93%|█████████▎| 26025/28080 [51:24:53<4:03:24,  7.11s/it]
 93%|█████████▎| 26026/28080 [51:25:00<4:03:35,  7.12s/it]
                                                          
{'loss': 0.601, 'learning_rate': 6.983285414269791e-06, 'epoch': 11.12}

 93%|█████████▎| 26026/28080 [51:25:00<4:03:35,  7.12s/it]
 93%|█████████▎| 26027/28080 [51:25:07<4:03:16,  7.11s/it]
                                                          
{'loss': 0.6095, 'learning_rate': 6.976519171553591e-06, 'epoch': 11.12}

 93%|█████████▎| 26027/28080 [51:25:07<4:03:16,  7.11s/it]
 93%|█████████▎| 26028/28080 [51:25:15<4:03:24,  7.12s/it]
                                                          
{'loss': 0.5811, 'learning_rate': 6.969756162014118e-06, 'epoch': 11.12}

 93%|█████████▎| 26028/28080 [51:25:15<4:03:24,  7.12s/it]
 93%|█████████▎| 26029/28080 [51:25:22<4:02:59,  7.11s/it]
                                                          
{'loss': 0.6016, 'learning_rate': 6.9629963857412995e-06, 'epoch': 11.12}

 93%|█████████▎| 26029/28080 [51:25:22<4:02:59,  7.11s/it]
 93%|█████████▎| 26030/28080 [51:25:29<4:03:09,  7.12s/it]
                                                          
{'loss': 0.6289, 'learning_rate': 6.956239842825118e-06, 'epoch': 11.12}

 93%|█████████▎| 26030/28080 [51:25:29<4:03:09,  7.12s/it]
 93%|█████████▎| 26031/28080 [51:25:36<4:01:55,  7.08s/it]
                                                          
{'loss': 0.6105, 'learning_rate': 6.9494865333553924e-06, 'epoch': 11.12}

 93%|█████████▎| 26031/28080 [51:25:36<4:01:55,  7.08s/it]
 93%|█████████▎| 26032/28080 [51:25:43<4:01:57,  7.09s/it]
                                                          
{'loss': 0.5889, 'learning_rate': 6.942736457422022e-06, 'epoch': 11.12}

 93%|█████████▎| 26032/28080 [51:25:43<4:01:57,  7.09s/it]
 93%|█████████▎| 26033/28080 [51:25:50<4:02:11,  7.10s/it]
                                                          
{'loss': 0.6222, 'learning_rate': 6.935989615114796e-06, 'epoch': 11.12}

 93%|█████████▎| 26033/28080 [51:25:50<4:02:11,  7.10s/it]
 93%|█████████▎| 26034/28080 [51:25:57<4:02:31,  7.11s/it]
                                                          
{'loss': 0.6013, 'learning_rate': 6.929246006523476e-06, 'epoch': 11.12}

 93%|█████████▎| 26034/28080 [51:25:57<4:02:31,  7.11s/it]
 93%|█████████▎| 26035/28080 [51:26:04<4:03:43,  7.15s/it]
                                                          
{'loss': 0.5773, 'learning_rate': 6.922505631737796e-06, 'epoch': 11.12}

 93%|█████████▎| 26035/28080 [51:26:04<4:03:43,  7.15s/it]
 93%|█████████▎| 26036/28080 [51:26:11<4:01:57,  7.10s/it]
                                                          
{'loss': 0.585, 'learning_rate': 6.915768490847352e-06, 'epoch': 11.12}

 93%|█████████▎| 26036/28080 [51:26:11<4:01:57,  7.10s/it]
 93%|█████████▎| 26037/28080 [51:26:19<4:02:06,  7.11s/it]
                                                          
{'loss': 0.5827, 'learning_rate': 6.909034583941875e-06, 'epoch': 11.12}

 93%|█████████▎| 26037/28080 [51:26:19<4:02:06,  7.11s/it]
 93%|█████████▎| 26038/28080 [51:26:26<4:01:08,  7.09s/it]
                                                          
{'loss': 0.6202, 'learning_rate': 6.902303911110907e-06, 'epoch': 11.12}

 93%|█████████▎| 26038/28080 [51:26:26<4:01:08,  7.09s/it]
 93%|█████████▎| 26039/28080 [51:26:33<4:00:50,  7.08s/it]
                                                          
{'loss': 0.6215, 'learning_rate': 6.895576472444015e-06, 'epoch': 11.12}

 93%|█████████▎| 26039/28080 [51:26:33<4:00:50,  7.08s/it]
 93%|█████████▎| 26040/28080 [51:26:40<4:02:09,  7.12s/it]
                                                          
{'loss': 0.6013, 'learning_rate': 6.8888522680306265e-06, 'epoch': 11.12}

 93%|█████████▎| 26040/28080 [51:26:40<4:02:09,  7.12s/it]
 93%|█████████▎| 26041/28080 [51:26:47<4:02:46,  7.14s/it]
                                                          
{'loss': 0.5916, 'learning_rate': 6.882131297960309e-06, 'epoch': 11.12}

 93%|█████████▎| 26041/28080 [51:26:47<4:02:46,  7.14s/it]
 93%|█████████▎| 26042/28080 [51:26:54<4:02:18,  7.13s/it]
                                                          
{'loss': 0.6138, 'learning_rate': 6.87541356232238e-06, 'epoch': 11.12}

 93%|█████████▎| 26042/28080 [51:26:54<4:02:18,  7.13s/it]
 93%|█████████▎| 26043/28080 [51:27:01<4:01:52,  7.12s/it]
                                                          
{'loss': 0.6126, 'learning_rate': 6.8686990612062964e-06, 'epoch': 11.13}

 93%|█████████▎| 26043/28080 [51:27:01<4:01:52,  7.12s/it]
 93%|█████████▎| 26044/28080 [51:27:08<4:02:01,  7.13s/it]
                                                          
{'loss': 0.5994, 'learning_rate': 6.861987794701319e-06, 'epoch': 11.13}

 93%|█████████▎| 26044/28080 [51:27:08<4:02:01,  7.13s/it]
 93%|█████████▎| 26045/28080 [51:27:15<4:01:04,  7.11s/it]
                                                          
{'loss': 0.5921, 'learning_rate': 6.855279762896766e-06, 'epoch': 11.13}

 93%|█████████▎| 26045/28080 [51:27:15<4:01:04,  7.11s/it]
 93%|█████████▎| 26046/28080 [51:27:23<4:01:43,  7.13s/it]
                                                          
{'loss': 0.5936, 'learning_rate': 6.848574965881871e-06, 'epoch': 11.13}

 93%|█████████▎| 26046/28080 [51:27:23<4:01:43,  7.13s/it]
 93%|█████████▎| 26047/28080 [51:27:30<4:01:30,  7.13s/it]
                                                          
{'loss': 0.6044, 'learning_rate': 6.841873403745841e-06, 'epoch': 11.13}

 93%|█████████▎| 26047/28080 [51:27:30<4:01:30,  7.13s/it]
 93%|█████████▎| 26048/28080 [51:27:37<4:00:48,  7.11s/it]
                                                          
{'loss': 0.6063, 'learning_rate': 6.835175076577854e-06, 'epoch': 11.13}

 93%|█████████▎| 26048/28080 [51:27:37<4:00:48,  7.11s/it]
 93%|█████████▎| 26049/28080 [51:27:44<4:01:52,  7.15s/it]
                                                          
{'loss': 0.5841, 'learning_rate': 6.828479984467007e-06, 'epoch': 11.13}

 93%|█████████▎| 26049/28080 [51:27:44<4:01:52,  7.15s/it]
 93%|█████████▎| 26050/28080 [51:27:51<4:00:51,  7.12s/it]
                                                          
{'loss': 0.616, 'learning_rate': 6.821788127502337e-06, 'epoch': 11.13}

 93%|█████████▎| 26050/28080 [51:27:51<4:00:51,  7.12s/it]
 93%|█████████▎| 26051/28080 [51:27:58<4:01:14,  7.13s/it]
                                                          
{'loss': 0.6142, 'learning_rate': 6.815099505772915e-06, 'epoch': 11.13}

 93%|█████████▎| 26051/28080 [51:27:58<4:01:14,  7.13s/it]
 93%|█████████▎| 26052/28080 [51:28:05<4:00:45,  7.12s/it]
                                                          
{'loss': 0.6037, 'learning_rate': 6.808414119367723e-06, 'epoch': 11.13}

 93%|█████████▎| 26052/28080 [51:28:05<4:00:45,  7.12s/it]
 93%|█████████▎| 26053/28080 [51:28:13<4:00:33,  7.12s/it]
                                                          
{'loss': 0.6092, 'learning_rate': 6.801731968375719e-06, 'epoch': 11.13}

 93%|█████████▎| 26053/28080 [51:28:13<4:00:33,  7.12s/it]
 93%|█████████▎| 26054/28080 [51:28:20<4:01:00,  7.14s/it]
                                                          
{'loss': 0.5769, 'learning_rate': 6.795053052885719e-06, 'epoch': 11.13}

 93%|█████████▎| 26054/28080 [51:28:20<4:01:00,  7.14s/it]
 93%|█████████▎| 26055/28080 [51:28:27<4:00:29,  7.13s/it]
                                                          
{'loss': 0.5969, 'learning_rate': 6.788377372986681e-06, 'epoch': 11.13}

 93%|█████████▎| 26055/28080 [51:28:27<4:00:29,  7.13s/it]
 93%|█████████▎| 26056/28080 [51:28:34<4:00:38,  7.13s/it]
                                                          
{'loss': 0.5893, 'learning_rate': 6.781704928767341e-06, 'epoch': 11.13}

 93%|█████████▎| 26056/28080 [51:28:34<4:00:38,  7.13s/it]
 93%|█████████▎| 26057/28080 [51:28:41<4:00:36,  7.14s/it]
                                                          
{'loss': 0.6086, 'learning_rate': 6.775035720316542e-06, 'epoch': 11.13}

 93%|█████████▎| 26057/28080 [51:28:41<4:00:36,  7.14s/it]
 93%|█████████▎| 26058/28080 [51:28:48<4:01:29,  7.17s/it]
                                                          
{'loss': 0.5982, 'learning_rate': 6.768369747722964e-06, 'epoch': 11.13}

 93%|█████████▎| 26058/28080 [51:28:48<4:01:29,  7.17s/it]
 93%|█████████▎| 26059/28080 [51:28:55<4:00:05,  7.13s/it]
                                                          
{'loss': 0.5922, 'learning_rate': 6.761707011075257e-06, 'epoch': 11.13}

 93%|█████████▎| 26059/28080 [51:28:55<4:00:05,  7.13s/it]
 93%|█████████▎| 26060/28080 [51:29:03<4:00:11,  7.13s/it]
                                                          
{'loss': 0.6064, 'learning_rate': 6.755047510462159e-06, 'epoch': 11.13}

 93%|█████████▎| 26060/28080 [51:29:03<4:00:11,  7.13s/it]
 93%|█████████▎| 26061/28080 [51:29:10<3:59:54,  7.13s/it]
                                                          
{'loss': 0.6002, 'learning_rate': 6.7483912459721515e-06, 'epoch': 11.13}

 93%|█████████▎| 26061/28080 [51:29:10<3:59:54,  7.13s/it]
 93%|█████████▎| 26062/28080 [51:29:17<3:59:23,  7.12s/it]
                                                          
{'loss': 0.5824, 'learning_rate': 6.741738217693888e-06, 'epoch': 11.13}

 93%|█████████▎| 26062/28080 [51:29:17<3:59:23,  7.12s/it]
 93%|█████████▎| 26063/28080 [51:29:24<3:59:30,  7.12s/it]
                                                          
{'loss': 0.5896, 'learning_rate': 6.735088425715852e-06, 'epoch': 11.13}

 93%|█████████▎| 26063/28080 [51:29:24<3:59:30,  7.12s/it]
 93%|█████████▎| 26064/28080 [51:29:31<3:58:26,  7.10s/it]
                                                          
{'loss': 0.6084, 'learning_rate': 6.7284418701265004e-06, 'epoch': 11.13}

 93%|█████████▎| 26064/28080 [51:29:31<3:58:26,  7.10s/it]
 93%|█████████▎| 26065/28080 [51:29:38<3:58:15,  7.09s/it]
                                                          
{'loss': 0.599, 'learning_rate': 6.721798551014207e-06, 'epoch': 11.13}

 93%|█████████▎| 26065/28080 [51:29:38<3:58:15,  7.09s/it]
 93%|█████████▎| 26066/28080 [51:29:45<3:58:39,  7.11s/it]
                                                          
{'loss': 0.6254, 'learning_rate': 6.715158468467458e-06, 'epoch': 11.14}

 93%|█████████▎| 26066/28080 [51:29:45<3:58:39,  7.11s/it]
 93%|█████████▎| 26067/28080 [51:29:52<3:57:48,  7.09s/it]
                                                          
{'loss': 0.5921, 'learning_rate': 6.7085216225745425e-06, 'epoch': 11.14}

 93%|█████████▎| 26067/28080 [51:29:52<3:57:48,  7.09s/it]
 93%|█████████▎| 26068/28080 [51:29:59<3:58:07,  7.10s/it]
                                                          
{'loss': 0.586, 'learning_rate': 6.701888013423752e-06, 'epoch': 11.14}

 93%|█████████▎| 26068/28080 [51:29:59<3:58:07,  7.10s/it]
 93%|█████████▎| 26069/28080 [51:30:06<3:57:29,  7.09s/it]
                                                          
{'loss': 0.6026, 'learning_rate': 6.6952576411033194e-06, 'epoch': 11.14}

 93%|█████████▎| 26069/28080 [51:30:06<3:57:29,  7.09s/it]
 93%|█████████▎| 26070/28080 [51:30:13<3:55:49,  7.04s/it]
                                                          
{'loss': 0.603, 'learning_rate': 6.68863050570151e-06, 'epoch': 11.14}

 93%|█████████▎| 26070/28080 [51:30:13<3:55:49,  7.04s/it]
 93%|█████████▎| 26071/28080 [51:30:20<3:56:42,  7.07s/it]
                                                          
{'loss': 0.5944, 'learning_rate': 6.682006607306473e-06, 'epoch': 11.14}

 93%|█████████▎| 26071/28080 [51:30:20<3:56:42,  7.07s/it]
 93%|█████████▎| 26072/28080 [51:30:27<3:56:39,  7.07s/it]
                                                          
{'loss': 0.5752, 'learning_rate': 6.675385946006307e-06, 'epoch': 11.14}

 93%|█████████▎| 26072/28080 [51:30:27<3:56:39,  7.07s/it]
 93%|█████████▎| 26073/28080 [51:30:35<3:57:03,  7.09s/it]
                                                          
{'loss': 0.5978, 'learning_rate': 6.668768521889079e-06, 'epoch': 11.14}

 93%|█████████▎| 26073/28080 [51:30:35<3:57:03,  7.09s/it]
 93%|█████████▎| 26074/28080 [51:30:42<3:57:39,  7.11s/it]
                                                          
{'loss': 0.5888, 'learning_rate': 6.662154335042886e-06, 'epoch': 11.14}

 93%|█████████▎| 26074/28080 [51:30:42<3:57:39,  7.11s/it]
 93%|█████████▎| 26075/28080 [51:30:49<3:57:54,  7.12s/it]
                                                          
{'loss': 0.6058, 'learning_rate': 6.655543385555657e-06, 'epoch': 11.14}

 93%|█████████▎| 26075/28080 [51:30:49<3:57:54,  7.12s/it]
 93%|█████████▎| 26076/28080 [51:30:56<3:58:01,  7.13s/it]
                                                          
{'loss': 0.5908, 'learning_rate': 6.648935673515405e-06, 'epoch': 11.14}

 93%|█████████▎| 26076/28080 [51:30:56<3:58:01,  7.13s/it]
 93%|█████████▎| 26077/28080 [51:31:03<3:57:56,  7.13s/it]
                                                          
{'loss': 0.6086, 'learning_rate': 6.642331199010032e-06, 'epoch': 11.14}

 93%|█████████▎| 26077/28080 [51:31:03<3:57:56,  7.13s/it]
 93%|█████████▎| 26078/28080 [51:31:10<3:57:31,  7.12s/it]
                                                          
{'loss': 0.5906, 'learning_rate': 6.635729962127357e-06, 'epoch': 11.14}

 93%|█████████▎| 26078/28080 [51:31:10<3:57:31,  7.12s/it]
 93%|█████████▎| 26079/28080 [51:31:17<3:56:40,  7.10s/it]
                                                          
{'loss': 0.6124, 'learning_rate': 6.629131962955226e-06, 'epoch': 11.14}

 93%|█████████▎| 26079/28080 [51:31:17<3:56:40,  7.10s/it]
 93%|█████████▎| 26080/28080 [51:31:24<3:57:02,  7.11s/it]
                                                          
{'loss': 0.5965, 'learning_rate': 6.62253720158143e-06, 'epoch': 11.14}

 93%|█████████▎| 26080/28080 [51:31:24<3:57:02,  7.11s/it]
 93%|█████████▎| 26081/28080 [51:31:32<3:57:26,  7.13s/it]
                                                          
{'loss': 0.5761, 'learning_rate': 6.615945678093704e-06, 'epoch': 11.14}

 93%|█████████▎| 26081/28080 [51:31:32<3:57:26,  7.13s/it]
 93%|█████████▎| 26082/28080 [51:31:39<3:57:30,  7.13s/it]
                                                          
{'loss': 0.5965, 'learning_rate': 6.609357392579757e-06, 'epoch': 11.14}

 93%|█████████▎| 26082/28080 [51:31:39<3:57:30,  7.13s/it]
 93%|█████████▎| 26083/28080 [51:31:46<3:57:27,  7.13s/it]
                                                          
{'loss': 0.6138, 'learning_rate': 6.602772345127183e-06, 'epoch': 11.14}

 93%|█████████▎| 26083/28080 [51:31:46<3:57:27,  7.13s/it]
 93%|█████████▎| 26084/28080 [51:31:53<3:56:43,  7.12s/it]
                                                          
{'loss': 0.6081, 'learning_rate': 6.59619053582361e-06, 'epoch': 11.14}

 93%|█████████▎| 26084/28080 [51:31:53<3:56:43,  7.12s/it]
 93%|█████████▎| 26085/28080 [51:32:00<3:57:00,  7.13s/it]
                                                          
{'loss': 0.6111, 'learning_rate': 6.589611964756659e-06, 'epoch': 11.14}

 93%|█████████▎| 26085/28080 [51:32:00<3:57:00,  7.13s/it]
 93%|█████████▎| 26086/28080 [51:32:07<3:55:59,  7.10s/it]
                                                          
{'loss': 0.5885, 'learning_rate': 6.583036632013789e-06, 'epoch': 11.14}

 93%|█████████▎| 26086/28080 [51:32:07<3:55:59,  7.10s/it]
 93%|█████████▎| 26087/28080 [51:32:14<3:56:16,  7.11s/it]
                                                          
{'loss': 0.5917, 'learning_rate': 6.576464537682514e-06, 'epoch': 11.14}

 93%|█████████▎| 26087/28080 [51:32:14<3:56:16,  7.11s/it]
 93%|█████████▎| 26088/28080 [51:32:21<3:55:44,  7.10s/it]
                                                          
{'loss': 0.5894, 'learning_rate': 6.569895681850208e-06, 'epoch': 11.14}

 93%|█████████▎| 26088/28080 [51:32:21<3:55:44,  7.10s/it]
 93%|█████████▎| 26089/28080 [51:32:28<3:55:05,  7.08s/it]
                                                          
{'loss': 0.6026, 'learning_rate': 6.563330064604356e-06, 'epoch': 11.14}

 93%|█████████▎| 26089/28080 [51:32:28<3:55:05,  7.08s/it]
 93%|█████████▎| 26090/28080 [51:32:36<3:54:52,  7.08s/it]
                                                          
{'loss': 0.6003, 'learning_rate': 6.556767686032194e-06, 'epoch': 11.15}

 93%|█████████▎| 26090/28080 [51:32:36<3:54:52,  7.08s/it]
 93%|█████████▎| 26091/28080 [51:32:43<3:55:13,  7.10s/it]
                                                          
{'loss': 0.6059, 'learning_rate': 6.550208546221181e-06, 'epoch': 11.15}

 93%|█████████▎| 26091/28080 [51:32:43<3:55:13,  7.10s/it]
 93%|█████████▎| 26092/28080 [51:32:50<3:55:20,  7.10s/it]
                                                          
{'loss': 0.5869, 'learning_rate': 6.5436526452584134e-06, 'epoch': 11.15}

 93%|█████████▎| 26092/28080 [51:32:50<3:55:20,  7.10s/it]
 93%|█████████▎| 26093/28080 [51:32:57<3:53:53,  7.06s/it]
                                                          
{'loss': 0.6091, 'learning_rate': 6.5370999832312376e-06, 'epoch': 11.15}

 93%|█████████▎| 26093/28080 [51:32:57<3:53:53,  7.06s/it]
 93%|█████████▎| 26094/28080 [51:33:04<3:54:35,  7.09s/it]
                                                          
{'loss': 0.585, 'learning_rate': 6.530550560226722e-06, 'epoch': 11.15}

 93%|█████████▎| 26094/28080 [51:33:04<3:54:35,  7.09s/it]
 93%|█████████▎| 26095/28080 [51:33:11<3:54:38,  7.09s/it]
                                                          
{'loss': 0.5927, 'learning_rate': 6.524004376332104e-06, 'epoch': 11.15}

 93%|█████████▎| 26095/28080 [51:33:11<3:54:38,  7.09s/it]
 93%|█████████▎| 26096/28080 [51:33:18<3:55:03,  7.11s/it]
                                                          
{'loss': 0.5857, 'learning_rate': 6.517461431634425e-06, 'epoch': 11.15}

 93%|█████████▎| 26096/28080 [51:33:18<3:55:03,  7.11s/it]
 93%|█████████▎| 26097/28080 [51:33:25<3:55:00,  7.11s/it]
                                                          
{'loss': 0.5852, 'learning_rate': 6.510921726220753e-06, 'epoch': 11.15}

 93%|█████████▎| 26097/28080 [51:33:25<3:55:00,  7.11s/it]
 93%|█████████▎| 26098/28080 [51:33:32<3:55:03,  7.12s/it]
                                                          
{'loss': 0.5967, 'learning_rate': 6.5043852601780195e-06, 'epoch': 11.15}

 93%|█████████▎| 26098/28080 [51:33:32<3:55:03,  7.12s/it]
 93%|█████████▎| 26099/28080 [51:33:39<3:54:41,  7.11s/it]
                                                          
{'loss': 0.6042, 'learning_rate': 6.497852033593265e-06, 'epoch': 11.15}

 93%|█████████▎| 26099/28080 [51:33:39<3:54:41,  7.11s/it]
 93%|█████████▎| 26100/28080 [51:33:47<3:54:44,  7.11s/it]
                                                          
{'loss': 0.5972, 'learning_rate': 6.491322046553394e-06, 'epoch': 11.15}

 93%|█████████▎| 26100/28080 [51:33:47<3:54:44,  7.11s/it]
 93%|█████████▎| 26101/28080 [51:33:54<3:55:39,  7.14s/it]
                                                          
{'loss': 0.6022, 'learning_rate': 6.48479529914528e-06, 'epoch': 11.15}

 93%|█████████▎| 26101/28080 [51:33:54<3:55:39,  7.14s/it]
 93%|█████████▎| 26102/28080 [51:34:01<3:54:30,  7.11s/it]
                                                          
{'loss': 0.5905, 'learning_rate': 6.478271791455714e-06, 'epoch': 11.15}

 93%|█████████▎| 26102/28080 [51:34:01<3:54:30,  7.11s/it]
 93%|█████████▎| 26103/28080 [51:34:08<3:54:21,  7.11s/it]
                                                          
{'loss': 0.6047, 'learning_rate': 6.471751523571518e-06, 'epoch': 11.15}

 93%|█████████▎| 26103/28080 [51:34:08<3:54:21,  7.11s/it]
 93%|█████████▎| 26104/28080 [51:34:15<3:54:41,  7.13s/it]
                                                          
{'loss': 0.6, 'learning_rate': 6.465234495579425e-06, 'epoch': 11.15}

 93%|█████████▎| 26104/28080 [51:34:15<3:54:41,  7.13s/it]
 93%|█████████▎| 26105/28080 [51:34:22<3:55:05,  7.14s/it]
                                                          
{'loss': 0.6084, 'learning_rate': 6.458720707566201e-06, 'epoch': 11.15}

 93%|█████████▎| 26105/28080 [51:34:22<3:55:05,  7.14s/it]
 93%|█████████▎| 26106/28080 [51:34:29<3:55:10,  7.15s/it]
                                                          
{'loss': 0.5935, 'learning_rate': 6.452210159618388e-06, 'epoch': 11.15}

 93%|█████████▎| 26106/28080 [51:34:29<3:55:10,  7.15s/it]
 93%|█████████▎| 26107/28080 [51:34:37<3:55:06,  7.15s/it]
                                                          
{'loss': 0.6031, 'learning_rate': 6.445702851822694e-06, 'epoch': 11.15}

 93%|█████████▎| 26107/28080 [51:34:37<3:55:06,  7.15s/it]
 93%|█████████▎| 26108/28080 [51:34:44<3:54:10,  7.12s/it]
                                                          
{'loss': 0.6027, 'learning_rate': 6.43919878426566e-06, 'epoch': 11.15}

 93%|█████████▎| 26108/28080 [51:34:44<3:54:10,  7.12s/it]
 93%|█████████▎| 26109/28080 [51:34:51<3:54:53,  7.15s/it]
                                                          
{'loss': 0.5997, 'learning_rate': 6.4326979570338e-06, 'epoch': 11.15}

 93%|█████████▎| 26109/28080 [51:34:51<3:54:53,  7.15s/it]
 93%|█████████▎| 26110/28080 [51:34:58<3:54:42,  7.15s/it]
                                                          
{'loss': 0.5912, 'learning_rate': 6.426200370213686e-06, 'epoch': 11.15}

 93%|█████████▎| 26110/28080 [51:34:58<3:54:42,  7.15s/it]
 93%|█████████▎| 26111/28080 [51:35:05<3:53:56,  7.13s/it]
                                                          
{'loss': 0.5918, 'learning_rate': 6.419706023891608e-06, 'epoch': 11.15}

 93%|█████████▎| 26111/28080 [51:35:05<3:53:56,  7.13s/it]
 93%|█████████▎| 26112/28080 [51:35:12<3:54:10,  7.14s/it]
                                                          
{'loss': 0.6193, 'learning_rate': 6.413214918154109e-06, 'epoch': 11.15}

 93%|█████████▎| 26112/28080 [51:35:12<3:54:10,  7.14s/it]
 93%|█████████▎| 26113/28080 [51:35:19<3:54:01,  7.14s/it]
                                                          
{'loss': 0.5886, 'learning_rate': 6.4067270530874525e-06, 'epoch': 11.16}

 93%|█████████▎| 26113/28080 [51:35:19<3:54:01,  7.14s/it]
 93%|█████████▎| 26114/28080 [51:35:27<3:54:10,  7.15s/it]
                                                          
{'loss': 0.6187, 'learning_rate': 6.400242428778014e-06, 'epoch': 11.16}

 93%|█████████▎| 26114/28080 [51:35:27<3:54:10,  7.15s/it]
 93%|█████████▎| 26115/28080 [51:35:34<3:54:29,  7.16s/it]
                                                          
{'loss': 0.6012, 'learning_rate': 6.39376104531203e-06, 'epoch': 11.16}

 93%|█████████▎| 26115/28080 [51:35:34<3:54:29,  7.16s/it]
 93%|█████████▎| 26116/28080 [51:35:41<3:54:18,  7.16s/it]
                                                          
{'loss': 0.6009, 'learning_rate': 6.387282902775765e-06, 'epoch': 11.16}

 93%|█████████▎| 26116/28080 [51:35:41<3:54:18,  7.16s/it]
 93%|█████████▎| 26117/28080 [51:35:48<3:54:19,  7.16s/it]
                                                          
{'loss': 0.597, 'learning_rate': 6.3808080012553445e-06, 'epoch': 11.16}

 93%|█████████▎| 26117/28080 [51:35:48<3:54:19,  7.16s/it]
 93%|█████████▎| 26118/28080 [51:35:55<3:52:40,  7.12s/it]
                                                          
{'loss': 0.6029, 'learning_rate': 6.374336340836978e-06, 'epoch': 11.16}

 93%|█████████▎| 26118/28080 [51:35:55<3:52:40,  7.12s/it]
 93%|█████████▎| 26119/28080 [51:36:02<3:51:30,  7.08s/it]
                                                          
{'loss': 0.616, 'learning_rate': 6.367867921606707e-06, 'epoch': 11.16}

 93%|█████████▎| 26119/28080 [51:36:02<3:51:30,  7.08s/it]
 93%|█████████▎| 26120/28080 [51:36:09<3:51:38,  7.09s/it]
                                                          
{'loss': 0.6037, 'learning_rate': 6.361402743650657e-06, 'epoch': 11.16}

 93%|█████████▎| 26120/28080 [51:36:09<3:51:38,  7.09s/it]
 93%|█████████▎| 26121/28080 [51:36:16<3:52:43,  7.13s/it]
                                                          
{'loss': 0.5985, 'learning_rate': 6.354940807054732e-06, 'epoch': 11.16}

 93%|█████████▎| 26121/28080 [51:36:16<3:52:43,  7.13s/it]
 93%|█████████▎| 26122/28080 [51:36:23<3:51:16,  7.09s/it]
                                                          
{'loss': 0.6021, 'learning_rate': 6.348482111905002e-06, 'epoch': 11.16}

 93%|█████████▎| 26122/28080 [51:36:23<3:51:16,  7.09s/it]
 93%|█████████▎| 26123/28080 [51:36:31<3:51:39,  7.10s/it]
                                                          
{'loss': 0.596, 'learning_rate': 6.342026658287342e-06, 'epoch': 11.16}

 93%|█████████▎| 26123/28080 [51:36:31<3:51:39,  7.10s/it]
 93%|█████████▎| 26124/28080 [51:36:38<3:51:40,  7.11s/it]
                                                          
{'loss': 0.5886, 'learning_rate': 6.335574446287656e-06, 'epoch': 11.16}

 93%|█████████▎| 26124/28080 [51:36:38<3:51:40,  7.11s/it]
 93%|█████████▎| 26125/28080 [51:36:45<3:50:04,  7.06s/it]
                                                          
{'loss': 0.6142, 'learning_rate': 6.329125475991793e-06, 'epoch': 11.16}

 93%|█████████▎| 26125/28080 [51:36:45<3:50:04,  7.06s/it]
 93%|█████████▎| 26126/28080 [51:36:52<3:49:13,  7.04s/it]
                                                          
{'loss': 0.5911, 'learning_rate': 6.322679747485516e-06, 'epoch': 11.16}

 93%|█████████▎| 26126/28080 [51:36:52<3:49:13,  7.04s/it]
 93%|█████████▎| 26127/28080 [51:36:59<3:49:18,  7.04s/it]
                                                          
{'loss': 0.5765, 'learning_rate': 6.31623726085459e-06, 'epoch': 11.16}

 93%|█████████▎| 26127/28080 [51:36:59<3:49:18,  7.04s/it]
 93%|█████████▎| 26128/28080 [51:37:06<3:50:07,  7.07s/it]
                                                          
{'loss': 0.5852, 'learning_rate': 6.309798016184726e-06, 'epoch': 11.16}

 93%|█████████▎| 26128/28080 [51:37:06<3:50:07,  7.07s/it]
 93%|█████████▎| 26129/28080 [51:37:13<3:50:40,  7.09s/it]
                                                          
{'loss': 0.5896, 'learning_rate': 6.303362013561631e-06, 'epoch': 11.16}

 93%|█████████▎| 26129/28080 [51:37:13<3:50:40,  7.09s/it]
 93%|█████████▎| 26130/28080 [51:37:20<3:52:11,  7.14s/it]
                                                          
{'loss': 0.5782, 'learning_rate': 6.296929253070904e-06, 'epoch': 11.16}

 93%|█████████▎| 26130/28080 [51:37:20<3:52:11,  7.14s/it]
 93%|█████████▎| 26131/28080 [51:37:27<3:51:32,  7.13s/it]
                                                          
{'loss': 0.5987, 'learning_rate': 6.290499734798061e-06, 'epoch': 11.16}

 93%|█████████▎| 26131/28080 [51:37:27<3:51:32,  7.13s/it]
 93%|█████████▎| 26132/28080 [51:37:34<3:50:12,  7.09s/it]
                                                          
{'loss': 0.6101, 'learning_rate': 6.284073458828754e-06, 'epoch': 11.16}

 93%|█████████▎| 26132/28080 [51:37:34<3:50:12,  7.09s/it]
 93%|█████████▎| 26133/28080 [51:37:41<3:50:27,  7.10s/it]
                                                          
{'loss': 0.5944, 'learning_rate': 6.277650425248388e-06, 'epoch': 11.16}

 93%|█████████▎| 26133/28080 [51:37:41<3:50:27,  7.10s/it]
 93%|█████████▎| 26134/28080 [51:37:48<3:49:29,  7.08s/it]
                                                          
{'loss': 0.6057, 'learning_rate': 6.271230634142477e-06, 'epoch': 11.16}

 93%|█████████▎| 26134/28080 [51:37:48<3:49:29,  7.08s/it]
 93%|█████████▎| 26135/28080 [51:37:56<3:49:13,  7.07s/it]
                                                          
{'loss': 0.6021, 'learning_rate': 6.264814085596398e-06, 'epoch': 11.16}

 93%|█████████▎| 26135/28080 [51:37:56<3:49:13,  7.07s/it]
 93%|█████████▎| 26136/28080 [51:38:03<3:49:23,  7.08s/it]
                                                          
{'loss': 0.5996, 'learning_rate': 6.258400779695472e-06, 'epoch': 11.17}

 93%|█████████▎| 26136/28080 [51:38:03<3:49:23,  7.08s/it]
 93%|█████████▎| 26137/28080 [51:38:10<3:50:14,  7.11s/it]
                                                          
{'loss': 0.5825, 'learning_rate': 6.25199071652513e-06, 'epoch': 11.17}

 93%|█████████▎| 26137/28080 [51:38:10<3:50:14,  7.11s/it]
 93%|█████████▎| 26138/28080 [51:38:17<3:49:32,  7.09s/it]
                                                          
{'loss': 0.5963, 'learning_rate': 6.2455838961705255e-06, 'epoch': 11.17}

 93%|█████████▎| 26138/28080 [51:38:17<3:49:32,  7.09s/it]
 93%|█████████▎| 26139/28080 [51:38:24<3:49:46,  7.10s/it]
                                                          
{'loss': 0.582, 'learning_rate': 6.239180318717036e-06, 'epoch': 11.17}

 93%|█████████▎| 26139/28080 [51:38:24<3:49:46,  7.10s/it]
 93%|█████████▎| 26140/28080 [51:38:31<3:50:26,  7.13s/it]
                                                          
{'loss': 0.5737, 'learning_rate': 6.232779984249732e-06, 'epoch': 11.17}

 93%|█████████▎| 26140/28080 [51:38:31<3:50:26,  7.13s/it]
 93%|█████████▎| 26141/28080 [51:38:38<3:50:37,  7.14s/it]
                                                          
{'loss': 0.6022, 'learning_rate': 6.2263828928538215e-06, 'epoch': 11.17}

 93%|█████████▎| 26141/28080 [51:38:38<3:50:37,  7.14s/it]
 93%|█████████▎| 26142/28080 [51:38:45<3:49:49,  7.12s/it]
                                                          
{'loss': 0.5936, 'learning_rate': 6.219989044614377e-06, 'epoch': 11.17}

 93%|█████████▎| 26142/28080 [51:38:45<3:49:49,  7.12s/it]
 93%|█████████▎| 26143/28080 [51:38:52<3:49:23,  7.11s/it]
                                                          
{'loss': 0.5998, 'learning_rate': 6.213598439616525e-06, 'epoch': 11.17}

 93%|█████████▎| 26143/28080 [51:38:52<3:49:23,  7.11s/it]
 93%|█████████▎| 26144/28080 [51:39:00<3:49:44,  7.12s/it]
                                                          
{'loss': 0.5989, 'learning_rate': 6.207211077945224e-06, 'epoch': 11.17}

 93%|█████████▎| 26144/28080 [51:39:00<3:49:44,  7.12s/it]
 93%|█████████▎| 26145/28080 [51:39:07<3:49:32,  7.12s/it]
                                                          
{'loss': 0.6139, 'learning_rate': 6.20082695968549e-06, 'epoch': 11.17}

 93%|█████████▎| 26145/28080 [51:39:07<3:49:32,  7.12s/it]
 93%|█████████▎| 26146/28080 [51:39:14<3:49:47,  7.13s/it]
                                                          
{'loss': 0.5965, 'learning_rate': 6.194446084922201e-06, 'epoch': 11.17}

 93%|█████████▎| 26146/28080 [51:39:14<3:49:47,  7.13s/it]
 93%|█████████▎| 26147/28080 [51:39:21<3:49:40,  7.13s/it]
                                                          
{'loss': 0.641, 'learning_rate': 6.188068453740314e-06, 'epoch': 11.17}

 93%|█████████▎| 26147/28080 [51:39:21<3:49:40,  7.13s/it]
 93%|█████████▎| 26148/28080 [51:39:28<3:49:27,  7.13s/it]
                                                          
{'loss': 0.6184, 'learning_rate': 6.1816940662246525e-06, 'epoch': 11.17}

 93%|█████████▎| 26148/28080 [51:39:28<3:49:27,  7.13s/it]
 93%|█████████▎| 26149/28080 [51:39:35<3:48:15,  7.09s/it]
                                                          
{'loss': 0.6134, 'learning_rate': 6.175322922460008e-06, 'epoch': 11.17}

 93%|█████████▎| 26149/28080 [51:39:35<3:48:15,  7.09s/it]
 93%|█████████▎| 26150/28080 [51:39:42<3:48:22,  7.10s/it]
                                                          
{'loss': 0.5907, 'learning_rate': 6.1689550225311475e-06, 'epoch': 11.17}

 93%|█████████▎| 26150/28080 [51:39:42<3:48:22,  7.10s/it]
 93%|█████████▎| 26151/28080 [51:39:49<3:48:22,  7.10s/it]
                                                          
{'loss': 0.6013, 'learning_rate': 6.1625903665228074e-06, 'epoch': 11.17}

 93%|█████████▎| 26151/28080 [51:39:49<3:48:22,  7.10s/it]
 93%|█████████▎| 26152/28080 [51:39:57<3:50:49,  7.18s/it]
                                                          
{'loss': 0.6039, 'learning_rate': 6.156228954519616e-06, 'epoch': 11.17}

 93%|█████████▎| 26152/28080 [51:39:57<3:50:49,  7.18s/it]
 93%|█████████▎| 26153/28080 [51:40:04<3:50:06,  7.16s/it]
                                                          
{'loss': 0.5996, 'learning_rate': 6.1498707866063095e-06, 'epoch': 11.17}

 93%|█████████▎| 26153/28080 [51:40:04<3:50:06,  7.16s/it]
 93%|█████████▎| 26154/28080 [51:40:11<3:50:16,  7.17s/it]
                                                          
{'loss': 0.5756, 'learning_rate': 6.143515862867349e-06, 'epoch': 11.17}

 93%|█████████▎| 26154/28080 [51:40:11<3:50:16,  7.17s/it]
 93%|█████████▎| 26155/28080 [51:40:18<3:49:57,  7.17s/it]
                                                          
{'loss': 0.6082, 'learning_rate': 6.137164183387333e-06, 'epoch': 11.17}

 93%|█████████▎| 26155/28080 [51:40:18<3:49:57,  7.17s/it]
 93%|█████████▎| 26156/28080 [51:40:25<3:50:11,  7.18s/it]
                                                          
{'loss': 0.5713, 'learning_rate': 6.130815748250779e-06, 'epoch': 11.17}

 93%|█████████▎| 26156/28080 [51:40:25<3:50:11,  7.18s/it]
 93%|█████████▎| 26157/28080 [51:40:33<3:49:30,  7.16s/it]
                                                          
{'loss': 0.6011, 'learning_rate': 6.1244705575421445e-06, 'epoch': 11.17}

 93%|█████████▎| 26157/28080 [51:40:33<3:49:30,  7.16s/it]
 93%|█████████▎| 26158/28080 [51:40:40<3:49:20,  7.16s/it]
                                                          
{'loss': 0.5932, 'learning_rate': 6.1181286113458635e-06, 'epoch': 11.17}

 93%|█████████▎| 26158/28080 [51:40:40<3:49:20,  7.16s/it]
 93%|█████████▎| 26159/28080 [51:40:47<3:49:59,  7.18s/it]
                                                          
{'loss': 0.5864, 'learning_rate': 6.1117899097462295e-06, 'epoch': 11.17}

 93%|█████████▎| 26159/28080 [51:40:47<3:49:59,  7.18s/it]
 93%|█████████▎| 26160/28080 [51:40:54<3:49:11,  7.16s/it]
                                                          
{'loss': 0.6113, 'learning_rate': 6.105454452827675e-06, 'epoch': 11.18}

 93%|█████████▎| 26160/28080 [51:40:54<3:49:11,  7.16s/it]
 93%|█████████▎| 26161/28080 [51:41:01<3:48:43,  7.15s/it]
                                                          
{'loss': 0.6139, 'learning_rate': 6.099122240674382e-06, 'epoch': 11.18}

 93%|█████████▎| 26161/28080 [51:41:01<3:48:43,  7.15s/it]
 93%|█████████▎| 26162/28080 [51:41:08<3:47:35,  7.12s/it]
                                                          
{'loss': 0.5934, 'learning_rate': 6.0927932733707006e-06, 'epoch': 11.18}

 93%|█████████▎| 26162/28080 [51:41:08<3:47:35,  7.12s/it]
 93%|█████████▎| 26163/28080 [51:41:15<3:48:01,  7.14s/it]
                                                          
{'loss': 0.5705, 'learning_rate': 6.086467551000757e-06, 'epoch': 11.18}

 93%|█████████▎| 26163/28080 [51:41:15<3:48:01,  7.14s/it]
 93%|█████████▎| 26164/28080 [51:41:23<3:47:32,  7.13s/it]
                                                          
{'loss': 0.6049, 'learning_rate': 6.080145073648735e-06, 'epoch': 11.18}

 93%|█████████▎| 26164/28080 [51:41:23<3:47:32,  7.13s/it]
 93%|█████████▎| 26165/28080 [51:41:30<3:47:14,  7.12s/it]
                                                          
{'loss': 0.608, 'learning_rate': 6.073825841398733e-06, 'epoch': 11.18}

 93%|█████████▎| 26165/28080 [51:41:30<3:47:14,  7.12s/it]
 93%|█████████▎| 26166/28080 [51:41:37<3:46:10,  7.09s/it]
                                                          
{'loss': 0.5944, 'learning_rate': 6.067509854334824e-06, 'epoch': 11.18}

 93%|█████████▎| 26166/28080 [51:41:37<3:46:10,  7.09s/it]
 93%|█████████▎| 26167/28080 [51:41:44<3:46:25,  7.10s/it]
                                                          
{'loss': 0.5915, 'learning_rate': 6.061197112541078e-06, 'epoch': 11.18}

 93%|█████████▎| 26167/28080 [51:41:44<3:46:25,  7.10s/it]
 93%|█████████▎| 26168/28080 [51:41:51<3:46:24,  7.10s/it]
                                                          
{'loss': 0.5918, 'learning_rate': 6.054887616101429e-06, 'epoch': 11.18}

 93%|█████████▎| 26168/28080 [51:41:51<3:46:24,  7.10s/it]
 93%|█████████▎| 26169/28080 [51:41:58<3:46:36,  7.12s/it]
                                                          
{'loss': 0.5872, 'learning_rate': 6.0485813650998364e-06, 'epoch': 11.18}

 93%|█████████▎| 26169/28080 [51:41:58<3:46:36,  7.12s/it]
 93%|█████████▎| 26170/28080 [51:42:05<3:45:18,  7.08s/it]
                                                          
{'loss': 0.5949, 'learning_rate': 6.0422783596202065e-06, 'epoch': 11.18}

 93%|█████████▎| 26170/28080 [51:42:05<3:45:18,  7.08s/it]
 93%|█████████▎| 26171/28080 [51:42:12<3:45:22,  7.08s/it]
                                                          
{'loss': 0.6077, 'learning_rate': 6.035978599746361e-06, 'epoch': 11.18}

 93%|█████████▎| 26171/28080 [51:42:12<3:45:22,  7.08s/it]
 93%|█████████▎| 26172/28080 [51:42:19<3:44:02,  7.05s/it]
                                                          
{'loss': 0.5879, 'learning_rate': 6.029682085562149e-06, 'epoch': 11.18}

 93%|█████████▎| 26172/28080 [51:42:19<3:44:02,  7.05s/it]
 93%|█████████▎| 26173/28080 [51:42:26<3:42:47,  7.01s/it]
                                                          
{'loss': 0.6116, 'learning_rate': 6.023388817151337e-06, 'epoch': 11.18}

 93%|█████████▎| 26173/28080 [51:42:26<3:42:47,  7.01s/it]
 93%|█████████▎| 26174/28080 [51:42:33<3:42:24,  7.00s/it]
                                                          
{'loss': 0.6234, 'learning_rate': 6.017098794597664e-06, 'epoch': 11.18}

 93%|█████████▎| 26174/28080 [51:42:33<3:42:24,  7.00s/it]
 93%|█████████▎| 26175/28080 [51:42:40<3:42:05,  6.99s/it]
                                                          
{'loss': 0.6118, 'learning_rate': 6.010812017984729e-06, 'epoch': 11.18}

 93%|█████████▎| 26175/28080 [51:42:40<3:42:05,  6.99s/it]
 93%|█████████▎| 26176/28080 [51:42:47<3:43:13,  7.03s/it]
                                                          
{'loss': 0.5881, 'learning_rate': 6.004528487396271e-06, 'epoch': 11.18}

 93%|█████████▎| 26176/28080 [51:42:47<3:43:13,  7.03s/it]
 93%|█████████▎| 26177/28080 [51:42:54<3:44:13,  7.07s/it]
                                                          
{'loss': 0.5753, 'learning_rate': 5.998248202915835e-06, 'epoch': 11.18}

 93%|█████████▎| 26177/28080 [51:42:54<3:44:13,  7.07s/it]
 93%|█████████▎| 26178/28080 [51:43:01<3:43:47,  7.06s/it]
                                                          
{'loss': 0.6016, 'learning_rate': 5.991971164626991e-06, 'epoch': 11.18}

 93%|█████████▎| 26178/28080 [51:43:01<3:43:47,  7.06s/it]
 93%|█████████▎| 26179/28080 [51:43:08<3:44:19,  7.08s/it]
                                                          
{'loss': 0.6052, 'learning_rate': 5.98569737261323e-06, 'epoch': 11.18}

 93%|█████████▎| 26179/28080 [51:43:08<3:44:19,  7.08s/it]
 93%|█████████▎| 26180/28080 [51:43:16<3:44:57,  7.10s/it]
                                                          
{'loss': 0.6003, 'learning_rate': 5.9794268269580396e-06, 'epoch': 11.18}

 93%|█████████▎| 26180/28080 [51:43:16<3:44:57,  7.10s/it]
 93%|█████████▎| 26181/28080 [51:43:23<3:45:51,  7.14s/it]
                                                          
{'loss': 0.5911, 'learning_rate': 5.973159527744826e-06, 'epoch': 11.18}

 93%|█████████▎| 26181/28080 [51:43:23<3:45:51,  7.14s/it]
 93%|█████████▎| 26182/28080 [51:43:30<3:45:54,  7.14s/it]
                                                          
{'loss': 0.574, 'learning_rate': 5.966895475056994e-06, 'epoch': 11.18}

 93%|█████████▎| 26182/28080 [51:43:30<3:45:54,  7.14s/it]
 93%|█████████▎| 26183/28080 [51:43:37<3:45:38,  7.14s/it]
                                                          
{'loss': 0.573, 'learning_rate': 5.960634668977866e-06, 'epoch': 11.19}

 93%|█████████▎| 26183/28080 [51:43:37<3:45:38,  7.14s/it]
 93%|█████████▎| 26184/28080 [51:43:44<3:45:25,  7.13s/it]
                                                          
{'loss': 0.6049, 'learning_rate': 5.954377109590681e-06, 'epoch': 11.19}

 93%|█████████▎| 26184/28080 [51:43:44<3:45:25,  7.13s/it]
 93%|█████████▎| 26185/28080 [51:43:51<3:46:02,  7.16s/it]
                                                          
{'loss': 0.6023, 'learning_rate': 5.948122796978789e-06, 'epoch': 11.19}

 93%|█████████▎| 26185/28080 [51:43:51<3:46:02,  7.16s/it]
 93%|█████████▎| 26186/28080 [51:43:59<3:46:24,  7.17s/it]
                                                          
{'loss': 0.608, 'learning_rate': 5.941871731225318e-06, 'epoch': 11.19}

 93%|█████████▎| 26186/28080 [51:43:59<3:46:24,  7.17s/it]
 93%|█████████▎| 26187/28080 [51:44:06<3:45:53,  7.16s/it]
                                                          
{'loss': 0.6083, 'learning_rate': 5.935623912413507e-06, 'epoch': 11.19}

 93%|█████████▎| 26187/28080 [51:44:06<3:45:53,  7.16s/it]
 93%|█████████▎| 26188/28080 [51:44:13<3:45:10,  7.14s/it]
                                                          
{'loss': 0.6022, 'learning_rate': 5.929379340626373e-06, 'epoch': 11.19}

 93%|█████████▎| 26188/28080 [51:44:13<3:45:10,  7.14s/it]
 93%|█████████▎| 26189/28080 [51:44:20<3:44:59,  7.14s/it]
                                                          
{'loss': 0.601, 'learning_rate': 5.923138015947099e-06, 'epoch': 11.19}

 93%|█████████▎| 26189/28080 [51:44:20<3:44:59,  7.14s/it]
 93%|█████████▎| 26190/28080 [51:44:27<3:44:52,  7.14s/it]
                                                          
{'loss': 0.5808, 'learning_rate': 5.916899938458648e-06, 'epoch': 11.19}

 93%|█████████▎| 26190/28080 [51:44:27<3:44:52,  7.14s/it]
 93%|█████████▎| 26191/28080 [51:44:34<3:42:40,  7.07s/it]
                                                          
{'loss': 0.604, 'learning_rate': 5.9106651082440624e-06, 'epoch': 11.19}

 93%|█████████▎| 26191/28080 [51:44:34<3:42:40,  7.07s/it]
 93%|█████████▎| 26192/28080 [51:44:41<3:43:10,  7.09s/it]
                                                          
{'loss': 0.594, 'learning_rate': 5.904433525386249e-06, 'epoch': 11.19}

 93%|█████████▎| 26192/28080 [51:44:41<3:43:10,  7.09s/it]
 93%|█████████▎| 26193/28080 [51:44:48<3:43:17,  7.10s/it]
                                                          
{'loss': 0.5923, 'learning_rate': 5.898205189968142e-06, 'epoch': 11.19}

 93%|█████████▎| 26193/28080 [51:44:48<3:43:17,  7.10s/it]
 93%|█████████▎| 26194/28080 [51:44:55<3:43:22,  7.11s/it]
                                                          
{'loss': 0.6053, 'learning_rate': 5.891980102072536e-06, 'epoch': 11.19}

 93%|█████████▎| 26194/28080 [51:44:55<3:43:22,  7.11s/it]
 93%|█████████▎| 26195/28080 [51:45:02<3:43:11,  7.10s/it]
                                                          
{'loss': 0.5722, 'learning_rate': 5.885758261782364e-06, 'epoch': 11.19}

 93%|█████████▎| 26195/28080 [51:45:02<3:43:11,  7.10s/it]
 93%|█████████▎| 26196/28080 [51:45:10<3:43:31,  7.12s/it]
                                                          
{'loss': 0.5897, 'learning_rate': 5.879539669180311e-06, 'epoch': 11.19}

 93%|█████████▎| 26196/28080 [51:45:10<3:43:31,  7.12s/it]
 93%|█████████▎| 26197/28080 [51:45:17<3:43:43,  7.13s/it]
                                                          
{'loss': 0.6036, 'learning_rate': 5.873324324349172e-06, 'epoch': 11.19}

 93%|█████████▎| 26197/28080 [51:45:17<3:43:43,  7.13s/it]
 93%|█████████▎| 26198/28080 [51:45:24<3:42:52,  7.11s/it]
                                                          
{'loss': 0.6149, 'learning_rate': 5.8671122273715465e-06, 'epoch': 11.19}

 93%|█████████▎| 26198/28080 [51:45:24<3:42:52,  7.11s/it]
 93%|█████████▎| 26199/28080 [51:45:31<3:42:48,  7.11s/it]
                                                          
{'loss': 0.5917, 'learning_rate': 5.860903378330174e-06, 'epoch': 11.19}

 93%|█████████▎| 26199/28080 [51:45:31<3:42:48,  7.11s/it]
 93%|█████████▎| 26200/28080 [51:45:38<3:42:26,  7.10s/it]
                                                          
{'loss': 0.5803, 'learning_rate': 5.854697777307599e-06, 'epoch': 11.19}

 93%|█████████▎| 26200/28080 [51:45:38<3:42:26,  7.10s/it]
 93%|█████████▎| 26201/28080 [51:45:45<3:41:19,  7.07s/it]
                                                          
{'loss': 0.5973, 'learning_rate': 5.848495424386424e-06, 'epoch': 11.19}

 93%|█████████▎| 26201/28080 [51:45:45<3:41:19,  7.07s/it]
 93%|█████████▎| 26202/28080 [51:45:52<3:42:44,  7.12s/it]
                                                          
{'loss': 0.5936, 'learning_rate': 5.84229631964911e-06, 'epoch': 11.19}

 93%|█████████▎| 26202/28080 [51:45:52<3:42:44,  7.12s/it]
 93%|█████████▎| 26203/28080 [51:45:59<3:42:57,  7.13s/it]
                                                          
{'loss': 0.6044, 'learning_rate': 5.836100463178173e-06, 'epoch': 11.19}

 93%|█████████▎| 26203/28080 [51:45:59<3:42:57,  7.13s/it]
 93%|█████████▎| 26204/28080 [51:46:07<3:42:51,  7.13s/it]
                                                          
{'loss': 0.6036, 'learning_rate': 5.829907855056021e-06, 'epoch': 11.19}

 93%|█████████▎| 26204/28080 [51:46:07<3:42:51,  7.13s/it]
 93%|█████████▎| 26205/28080 [51:46:14<3:41:43,  7.10s/it]
                                                          
{'loss': 0.6051, 'learning_rate': 5.82371849536506e-06, 'epoch': 11.19}

 93%|█████████▎| 26205/28080 [51:46:14<3:41:43,  7.10s/it]
 93%|█████████▎| 26206/28080 [51:46:21<3:41:08,  7.08s/it]
                                                          
{'loss': 0.624, 'learning_rate': 5.81753238418764e-06, 'epoch': 11.19}

 93%|█████████▎| 26206/28080 [51:46:21<3:41:08,  7.08s/it]
 93%|█████████▎| 26207/28080 [51:46:28<3:41:51,  7.11s/it]
                                                          
{'loss': 0.5958, 'learning_rate': 5.811349521606029e-06, 'epoch': 11.2}

 93%|█████████▎| 26207/28080 [51:46:28<3:41:51,  7.11s/it]
 93%|█████████▎| 26208/28080 [51:46:35<3:42:13,  7.12s/it]
                                                          
{'loss': 0.6031, 'learning_rate': 5.805169907702495e-06, 'epoch': 11.2}

 93%|█████████▎| 26208/28080 [51:46:35<3:42:13,  7.12s/it]
 93%|█████████▎| 26209/28080 [51:46:42<3:42:30,  7.14s/it]
                                                          
{'loss': 0.5939, 'learning_rate': 5.7989935425592225e-06, 'epoch': 11.2}

 93%|█████████▎| 26209/28080 [51:46:42<3:42:30,  7.14s/it]
 93%|█████████▎| 26210/28080 [51:46:49<3:42:28,  7.14s/it]
                                                          
{'loss': 0.602, 'learning_rate': 5.792820426258449e-06, 'epoch': 11.2}

 93%|█████████▎| 26210/28080 [51:46:49<3:42:28,  7.14s/it]
 93%|█████████▎| 26211/28080 [51:46:56<3:41:34,  7.11s/it]
                                                          
{'loss': 0.6431, 'learning_rate': 5.7866505588822505e-06, 'epoch': 11.2}

 93%|█████████▎| 26211/28080 [51:46:56<3:41:34,  7.11s/it]
 93%|█████████▎| 26212/28080 [51:47:03<3:41:02,  7.10s/it]
                                                          
{'loss': 0.5892, 'learning_rate': 5.780483940512754e-06, 'epoch': 11.2}

 93%|█████████▎| 26212/28080 [51:47:03<3:41:02,  7.10s/it]
 93%|█████████▎| 26213/28080 [51:47:11<3:41:23,  7.11s/it]
                                                          
{'loss': 0.5851, 'learning_rate': 5.774320571231923e-06, 'epoch': 11.2}

 93%|█████████▎| 26213/28080 [51:47:11<3:41:23,  7.11s/it]
 93%|█████████▎| 26214/28080 [51:47:18<3:41:05,  7.11s/it]
                                                          
{'loss': 0.6079, 'learning_rate': 5.768160451121829e-06, 'epoch': 11.2}

 93%|█████████▎| 26214/28080 [51:47:18<3:41:05,  7.11s/it]
 93%|█████████▎| 26215/28080 [51:47:25<3:41:37,  7.13s/it]
                                                          
{'loss': 0.589, 'learning_rate': 5.762003580264408e-06, 'epoch': 11.2}

 93%|█████████▎| 26215/28080 [51:47:25<3:41:37,  7.13s/it]
 93%|█████████▎| 26216/28080 [51:47:32<3:41:38,  7.13s/it]
                                                          
{'loss': 0.5985, 'learning_rate': 5.755849958741566e-06, 'epoch': 11.2}

 93%|█████████▎| 26216/28080 [51:47:32<3:41:38,  7.13s/it]
 93%|█████████▎| 26217/28080 [51:47:39<3:41:22,  7.13s/it]
                                                          
{'loss': 0.6037, 'learning_rate': 5.749699586635127e-06, 'epoch': 11.2}

 93%|█████████▎| 26217/28080 [51:47:39<3:41:22,  7.13s/it]
 93%|█████████▎| 26218/28080 [51:47:46<3:41:47,  7.15s/it]
                                                          
{'loss': 0.5979, 'learning_rate': 5.7435524640269965e-06, 'epoch': 11.2}

 93%|█████████▎| 26218/28080 [51:47:46<3:41:47,  7.15s/it]
 93%|█████████▎| 26219/28080 [51:47:53<3:41:09,  7.13s/it]
                                                          
{'loss': 0.5877, 'learning_rate': 5.7374085909988885e-06, 'epoch': 11.2}

 93%|█████████▎| 26219/28080 [51:47:53<3:41:09,  7.13s/it]
 93%|█████████▎| 26220/28080 [51:48:00<3:41:11,  7.14s/it]
                                                          
{'loss': 0.5955, 'learning_rate': 5.731267967632597e-06, 'epoch': 11.2}

 93%|█████████▎| 26220/28080 [51:48:00<3:41:11,  7.14s/it]
 93%|█████████▎| 26221/28080 [51:48:08<3:41:11,  7.14s/it]
                                                          
{'loss': 0.619, 'learning_rate': 5.725130594009753e-06, 'epoch': 11.2}

 93%|█████████▎| 26221/28080 [51:48:08<3:41:11,  7.14s/it]
 93%|█████████▎| 26222/28080 [51:48:15<3:41:07,  7.14s/it]
                                                          
{'loss': 0.5981, 'learning_rate': 5.718996470212068e-06, 'epoch': 11.2}

 93%|█████████▎| 26222/28080 [51:48:15<3:41:07,  7.14s/it]
 93%|█████████▎| 26223/28080 [51:48:22<3:40:57,  7.14s/it]
                                                          
{'loss': 0.6128, 'learning_rate': 5.712865596321115e-06, 'epoch': 11.2}

 93%|█████████▎| 26223/28080 [51:48:22<3:40:57,  7.14s/it]
 93%|█████████▎| 26224/28080 [51:48:29<3:41:01,  7.14s/it]
                                                          
{'loss': 0.5922, 'learning_rate': 5.706737972418469e-06, 'epoch': 11.2}

 93%|█████████▎| 26224/28080 [51:48:29<3:41:01,  7.14s/it]
 93%|█████████▎| 26225/28080 [51:48:36<3:40:11,  7.12s/it]
                                                          
{'loss': 0.6076, 'learning_rate': 5.700613598585675e-06, 'epoch': 11.2}

 93%|█████████▎| 26225/28080 [51:48:36<3:40:11,  7.12s/it]
 93%|█████████▎| 26226/28080 [51:48:43<3:39:37,  7.11s/it]
                                                          
{'loss': 0.6128, 'learning_rate': 5.694492474904167e-06, 'epoch': 11.2}

 93%|█████████▎| 26226/28080 [51:48:43<3:39:37,  7.11s/it]
 93%|█████████▎| 26227/28080 [51:48:50<3:38:58,  7.09s/it]
                                                          
{'loss': 0.6048, 'learning_rate': 5.688374601455382e-06, 'epoch': 11.2}

 93%|█████████▎| 26227/28080 [51:48:50<3:38:58,  7.09s/it]
 93%|█████████▎| 26228/28080 [51:48:57<3:39:07,  7.10s/it]
                                                          
{'loss': 0.5945, 'learning_rate': 5.682259978320753e-06, 'epoch': 11.2}

 93%|█████████▎| 26228/28080 [51:48:57<3:39:07,  7.10s/it]
 93%|█████████▎| 26229/28080 [51:49:05<3:39:24,  7.11s/it]
                                                          
{'loss': 0.5953, 'learning_rate': 5.676148605581605e-06, 'epoch': 11.2}

 93%|█████████▎| 26229/28080 [51:49:05<3:39:24,  7.11s/it]
 93%|█████████▎| 26230/28080 [51:49:12<3:39:49,  7.13s/it]
                                                          
{'loss': 0.6175, 'learning_rate': 5.6700404833192335e-06, 'epoch': 11.21}

 93%|█████████▎| 26230/28080 [51:49:12<3:39:49,  7.13s/it]
 93%|█████████▎| 26231/28080 [51:49:19<3:39:39,  7.13s/it]
                                                          
{'loss': 0.5876, 'learning_rate': 5.663935611614907e-06, 'epoch': 11.21}

 93%|█████████▎| 26231/28080 [51:49:19<3:39:39,  7.13s/it]
 93%|█████████▎| 26232/28080 [51:49:26<3:38:54,  7.11s/it]
                                                          
{'loss': 0.5996, 'learning_rate': 5.657833990549865e-06, 'epoch': 11.21}

 93%|█████████▎| 26232/28080 [51:49:26<3:38:54,  7.11s/it]
 93%|█████████▎| 26233/28080 [51:49:33<3:37:47,  7.07s/it]
                                                          
{'loss': 0.6199, 'learning_rate': 5.651735620205267e-06, 'epoch': 11.21}

 93%|█████████▎| 26233/28080 [51:49:33<3:37:47,  7.07s/it]
 93%|█████████▎| 26234/28080 [51:49:40<3:37:34,  7.07s/it]
                                                          
{'loss': 0.6078, 'learning_rate': 5.6456405006622414e-06, 'epoch': 11.21}

 93%|█████████▎| 26234/28080 [51:49:40<3:37:34,  7.07s/it]
 93%|█████████▎| 26235/28080 [51:49:47<3:37:44,  7.08s/it]
                                                          
{'loss': 0.5895, 'learning_rate': 5.639548632001917e-06, 'epoch': 11.21}

 93%|█████████▎| 26235/28080 [51:49:47<3:37:44,  7.08s/it]
 93%|█████████▎| 26236/28080 [51:49:54<3:37:52,  7.09s/it]
                                                          
{'loss': 0.5812, 'learning_rate': 5.633460014305258e-06, 'epoch': 11.21}

 93%|█████████▎| 26236/28080 [51:49:54<3:37:52,  7.09s/it]
 93%|█████████▎| 26237/28080 [51:50:01<3:38:07,  7.10s/it]
                                                          
{'loss': 0.5923, 'learning_rate': 5.627374647653338e-06, 'epoch': 11.21}

 93%|█████████▎| 26237/28080 [51:50:01<3:38:07,  7.10s/it]
 93%|█████████▎| 26238/28080 [51:50:08<3:38:15,  7.11s/it]
                                                          
{'loss': 0.5873, 'learning_rate': 5.6212925321270646e-06, 'epoch': 11.21}

 93%|█████████▎| 26238/28080 [51:50:08<3:38:15,  7.11s/it]
 93%|█████████▎| 26239/28080 [51:50:15<3:37:50,  7.10s/it]
                                                          
{'loss': 0.6152, 'learning_rate': 5.615213667807401e-06, 'epoch': 11.21}

 93%|█████████▎| 26239/28080 [51:50:15<3:37:50,  7.10s/it]
 93%|█████████▎| 26240/28080 [51:50:23<3:37:27,  7.09s/it]
                                                          
{'loss': 0.603, 'learning_rate': 5.609138054775226e-06, 'epoch': 11.21}

 93%|█████████▎| 26240/28080 [51:50:23<3:37:27,  7.09s/it]
 93%|█████████▎| 26241/28080 [51:50:30<3:37:29,  7.10s/it]
                                                          
{'loss': 0.5953, 'learning_rate': 5.603065693111309e-06, 'epoch': 11.21}

 93%|█████████▎| 26241/28080 [51:50:30<3:37:29,  7.10s/it]
 93%|█████████▎| 26242/28080 [51:50:37<3:37:38,  7.11s/it]
                                                          
{'loss': 0.6061, 'learning_rate': 5.596996582896474e-06, 'epoch': 11.21}

 93%|█████████▎| 26242/28080 [51:50:37<3:37:38,  7.11s/it]
 93%|█████████▎| 26243/28080 [51:50:44<3:37:32,  7.11s/it]
                                                          
{'loss': 0.6136, 'learning_rate': 5.590930724211491e-06, 'epoch': 11.21}

 93%|█████████▎| 26243/28080 [51:50:44<3:37:32,  7.11s/it]
 93%|█████████▎| 26244/28080 [51:50:51<3:38:05,  7.13s/it]
                                                          
{'loss': 0.6051, 'learning_rate': 5.584868117137015e-06, 'epoch': 11.21}

 93%|█████████▎| 26244/28080 [51:50:51<3:38:05,  7.13s/it]
 93%|█████████▎| 26245/28080 [51:50:58<3:37:29,  7.11s/it]
                                                          
{'loss': 0.593, 'learning_rate': 5.5788087617537346e-06, 'epoch': 11.21}

 93%|█████████▎| 26245/28080 [51:50:58<3:37:29,  7.11s/it]
 93%|█████████▎| 26246/28080 [51:51:05<3:36:50,  7.09s/it]
                                                          
{'loss': 0.6172, 'learning_rate': 5.572752658142221e-06, 'epoch': 11.21}

 93%|█████████▎| 26246/28080 [51:51:05<3:36:50,  7.09s/it]
 93%|█████████▎| 26247/28080 [51:51:13<3:38:38,  7.16s/it]
                                                          
{'loss': 0.5985, 'learning_rate': 5.56669980638308e-06, 'epoch': 11.21}

 93%|█████████▎| 26247/28080 [51:51:13<3:38:38,  7.16s/it]
 93%|█████████▎| 26248/28080 [51:51:20<3:38:26,  7.15s/it]
                                                          
{'loss': 0.5919, 'learning_rate': 5.5606502065568276e-06, 'epoch': 11.21}

 93%|█████████▎| 26248/28080 [51:51:20<3:38:26,  7.15s/it]
 93%|█████████▎| 26249/28080 [51:51:27<3:38:39,  7.17s/it]
                                                          
{'loss': 0.5566, 'learning_rate': 5.554603858743984e-06, 'epoch': 11.21}

 93%|█████████▎| 26249/28080 [51:51:27<3:38:39,  7.17s/it]
 93%|█████████▎| 26250/28080 [51:51:34<3:38:20,  7.16s/it]
                                                          
{'loss': 0.6009, 'learning_rate': 5.548560763024929e-06, 'epoch': 11.21}

 93%|█████████▎| 26250/28080 [51:51:34<3:38:20,  7.16s/it]
 93%|█████████▎| 26251/28080 [51:51:41<3:37:51,  7.15s/it]
                                                          
{'loss': 0.5851, 'learning_rate': 5.542520919480098e-06, 'epoch': 11.21}

 93%|█████████▎| 26251/28080 [51:51:41<3:37:51,  7.15s/it]
 93%|█████████▎| 26252/28080 [51:51:48<3:37:00,  7.12s/it]
                                                          
{'loss': 0.6117, 'learning_rate': 5.536484328189789e-06, 'epoch': 11.21}

 93%|█████████▎| 26252/28080 [51:51:48<3:37:00,  7.12s/it]
 93%|█████████▎| 26253/28080 [51:51:55<3:36:14,  7.10s/it]
                                                          
{'loss': 0.5941, 'learning_rate': 5.530450989234409e-06, 'epoch': 11.22}

 93%|█████████▎| 26253/28080 [51:51:55<3:36:14,  7.10s/it]
 93%|█████████▎| 26254/28080 [51:52:02<3:36:23,  7.11s/it]
                                                          
{'loss': 0.5983, 'learning_rate': 5.524420902694144e-06, 'epoch': 11.22}

 93%|█████████▎| 26254/28080 [51:52:02<3:36:23,  7.11s/it]
 94%|█████████▎| 26255/28080 [51:52:09<3:35:57,  7.10s/it]
                                                          
{'loss': 0.621, 'learning_rate': 5.51839406864929e-06, 'epoch': 11.22}

 94%|█████████▎| 26255/28080 [51:52:09<3:35:57,  7.10s/it]
 94%|█████████▎| 26256/28080 [51:52:17<3:36:20,  7.12s/it]
                                                          
{'loss': 0.6069, 'learning_rate': 5.512370487179924e-06, 'epoch': 11.22}

 94%|█████████▎| 26256/28080 [51:52:17<3:36:20,  7.12s/it]
 94%|█████████▎| 26257/28080 [51:52:24<3:35:48,  7.10s/it]
                                                          
{'loss': 0.5983, 'learning_rate': 5.506350158366286e-06, 'epoch': 11.22}

 94%|█████████▎| 26257/28080 [51:52:24<3:35:48,  7.10s/it]
 94%|█████████▎| 26258/28080 [51:52:31<3:35:52,  7.11s/it]
                                                          
{'loss': 0.5906, 'learning_rate': 5.500333082288422e-06, 'epoch': 11.22}

 94%|█████████▎| 26258/28080 [51:52:31<3:35:52,  7.11s/it]
 94%|█████████▎| 26259/28080 [51:52:38<3:36:08,  7.12s/it]
                                                          
{'loss': 0.5905, 'learning_rate': 5.494319259026381e-06, 'epoch': 11.22}

 94%|█████████▎| 26259/28080 [51:52:38<3:36:08,  7.12s/it]
 94%|█████████▎| 26260/28080 [51:52:45<3:35:09,  7.09s/it]
                                                          
{'loss': 0.5745, 'learning_rate': 5.4883086886602095e-06, 'epoch': 11.22}

 94%|█████████▎| 26260/28080 [51:52:45<3:35:09,  7.09s/it]
 94%|█████████▎| 26261/28080 [51:52:52<3:34:56,  7.09s/it]
                                                          
{'loss': 0.5899, 'learning_rate': 5.482301371269788e-06, 'epoch': 11.22}

 94%|█████████▎| 26261/28080 [51:52:52<3:34:56,  7.09s/it]
 94%|█████████▎| 26262/28080 [51:52:59<3:34:19,  7.07s/it]
                                                          
{'loss': 0.6014, 'learning_rate': 5.476297306935135e-06, 'epoch': 11.22}

 94%|█████████▎| 26262/28080 [51:52:59<3:34:19,  7.07s/it]
 94%|█████████▎| 26263/28080 [51:53:06<3:35:03,  7.10s/it]
                                                          
{'loss': 0.608, 'learning_rate': 5.470296495736077e-06, 'epoch': 11.22}

 94%|█████████▎| 26263/28080 [51:53:06<3:35:03,  7.10s/it]
 94%|█████████▎| 26264/28080 [51:53:13<3:35:30,  7.12s/it]
                                                          
{'loss': 0.5898, 'learning_rate': 5.464298937752465e-06, 'epoch': 11.22}

 94%|█████████▎| 26264/28080 [51:53:13<3:35:30,  7.12s/it]
 94%|█████████▎| 26265/28080 [51:53:21<3:35:19,  7.12s/it]
                                                          
{'loss': 0.574, 'learning_rate': 5.4583046330640426e-06, 'epoch': 11.22}

 94%|█████████▎| 26265/28080 [51:53:21<3:35:19,  7.12s/it]
 94%|█████████▎| 26266/28080 [51:53:28<3:36:12,  7.15s/it]
                                                          
{'loss': 0.5811, 'learning_rate': 5.452313581750634e-06, 'epoch': 11.22}

 94%|█████████▎| 26266/28080 [51:53:28<3:36:12,  7.15s/it]
 94%|█████████▎| 26267/28080 [51:53:35<3:35:35,  7.13s/it]
                                                          
{'loss': 0.5909, 'learning_rate': 5.44632578389187e-06, 'epoch': 11.22}

 94%|█████████▎| 26267/28080 [51:53:35<3:35:35,  7.13s/it]
 94%|█████████▎| 26268/28080 [51:53:42<3:35:13,  7.13s/it]
                                                          
{'loss': 0.6195, 'learning_rate': 5.44034123956752e-06, 'epoch': 11.22}

 94%|█████████▎| 26268/28080 [51:53:42<3:35:13,  7.13s/it]
 94%|█████████▎| 26269/28080 [51:53:49<3:35:13,  7.13s/it]
                                                          
{'loss': 0.5937, 'learning_rate': 5.434359948857076e-06, 'epoch': 11.22}

 94%|█████████▎| 26269/28080 [51:53:49<3:35:13,  7.13s/it]
 94%|█████████▎| 26270/28080 [51:53:56<3:34:40,  7.12s/it]
                                                          
{'loss': 0.6187, 'learning_rate': 5.428381911840169e-06, 'epoch': 11.22}

 94%|█████████▎| 26270/28080 [51:53:56<3:34:40,  7.12s/it]
 94%|█████████▎| 26271/28080 [51:54:03<3:34:14,  7.11s/it]
                                                          
{'loss': 0.6013, 'learning_rate': 5.422407128596346e-06, 'epoch': 11.22}

 94%|█████████▎| 26271/28080 [51:54:03<3:34:14,  7.11s/it]
 94%|█████████▎| 26272/28080 [51:54:11<3:35:27,  7.15s/it]
                                                          
{'loss': 0.5787, 'learning_rate': 5.416435599205072e-06, 'epoch': 11.22}

 94%|█████████▎| 26272/28080 [51:54:11<3:35:27,  7.15s/it]
 94%|█████████▎| 26273/28080 [51:54:18<3:35:17,  7.15s/it]
                                                          
{'loss': 0.6135, 'learning_rate': 5.41046732374581e-06, 'epoch': 11.22}

 94%|█████████▎| 26273/28080 [51:54:18<3:35:17,  7.15s/it]
 94%|█████████▎| 26274/28080 [51:54:25<3:34:53,  7.14s/it]
                                                          
{'loss': 0.6342, 'learning_rate': 5.404502302297942e-06, 'epoch': 11.22}

 94%|█████████▎| 26274/28080 [51:54:25<3:34:53,  7.14s/it]
 94%|█████████▎| 26275/28080 [51:54:32<3:34:39,  7.14s/it]
                                                          
{'loss': 0.5907, 'learning_rate': 5.3985405349408214e-06, 'epoch': 11.22}

 94%|█████████▎| 26275/28080 [51:54:32<3:34:39,  7.14s/it]
 94%|█████████▎| 26276/28080 [51:54:39<3:33:44,  7.11s/it]
                                                          
{'loss': 0.6233, 'learning_rate': 5.392582021753801e-06, 'epoch': 11.22}

 94%|█████████▎| 26276/28080 [51:54:39<3:33:44,  7.11s/it]
 94%|█████████▎| 26277/28080 [51:54:46<3:33:54,  7.12s/it]
                                                          
{'loss': 0.5975, 'learning_rate': 5.386626762816149e-06, 'epoch': 11.23}

 94%|█████████▎| 26277/28080 [51:54:46<3:33:54,  7.12s/it]
 94%|█████████▎| 26278/28080 [51:54:53<3:33:19,  7.10s/it]
                                                          
{'loss': 0.5936, 'learning_rate': 5.380674758207055e-06, 'epoch': 11.23}

 94%|█████████▎| 26278/28080 [51:54:53<3:33:19,  7.10s/it]
 94%|█████████▎| 26279/28080 [51:55:00<3:33:21,  7.11s/it]
                                                          
{'loss': 0.5865, 'learning_rate': 5.374726008005676e-06, 'epoch': 11.23}

 94%|█████████▎| 26279/28080 [51:55:00<3:33:21,  7.11s/it]
 94%|█████████▎| 26280/28080 [51:55:07<3:33:13,  7.11s/it]
                                                          
{'loss': 0.5994, 'learning_rate': 5.368780512291255e-06, 'epoch': 11.23}

 94%|█████████▎| 26280/28080 [51:55:07<3:33:13,  7.11s/it]
 94%|█████████▎| 26281/28080 [51:55:14<3:33:06,  7.11s/it]
                                                          
{'loss': 0.6064, 'learning_rate': 5.362838271142812e-06, 'epoch': 11.23}

 94%|█████████▎| 26281/28080 [51:55:14<3:33:06,  7.11s/it]
 94%|█████████▎| 26282/28080 [51:55:22<3:33:16,  7.12s/it]
                                                          
{'loss': 0.5941, 'learning_rate': 5.356899284639477e-06, 'epoch': 11.23}

 94%|█████████▎| 26282/28080 [51:55:22<3:33:16,  7.12s/it]
 94%|█████████▎| 26283/28080 [51:55:29<3:33:58,  7.14s/it]
                                                          
{'loss': 0.6047, 'learning_rate': 5.350963552860188e-06, 'epoch': 11.23}

 94%|█████████▎| 26283/28080 [51:55:29<3:33:58,  7.14s/it]
 94%|█████████▎| 26284/28080 [51:55:36<3:33:56,  7.15s/it]
                                                          
{'loss': 0.5847, 'learning_rate': 5.34503107588391e-06, 'epoch': 11.23}

 94%|█████████▎| 26284/28080 [51:55:36<3:33:56,  7.15s/it]
 94%|█████████▎| 26285/28080 [51:55:43<3:32:34,  7.11s/it]
                                                          
{'loss': 0.6246, 'learning_rate': 5.339101853789608e-06, 'epoch': 11.23}

 94%|█████████▎| 26285/28080 [51:55:43<3:32:34,  7.11s/it]
 94%|█████████▎| 26286/28080 [51:55:50<3:32:23,  7.10s/it]
                                                          
{'loss': 0.5978, 'learning_rate': 5.333175886656133e-06, 'epoch': 11.23}

 94%|█████████▎| 26286/28080 [51:55:50<3:32:23,  7.10s/it]
 94%|█████████▎| 26287/28080 [51:55:57<3:32:04,  7.10s/it]
                                                          
{'loss': 0.5868, 'learning_rate': 5.327253174562396e-06, 'epoch': 11.23}

 94%|█████████▎| 26287/28080 [51:55:57<3:32:04,  7.10s/it]
 94%|█████████▎| 26288/28080 [51:56:04<3:32:23,  7.11s/it]
                                                          
{'loss': 0.5768, 'learning_rate': 5.321333717587112e-06, 'epoch': 11.23}

 94%|█████████▎| 26288/28080 [51:56:04<3:32:23,  7.11s/it]
 94%|█████████▎| 26289/28080 [51:56:12<3:33:08,  7.14s/it]
                                                          
{'loss': 0.5939, 'learning_rate': 5.315417515809079e-06, 'epoch': 11.23}

 94%|█████████▎| 26289/28080 [51:56:12<3:33:08,  7.14s/it]
 94%|█████████▎| 26290/28080 [51:56:19<3:32:53,  7.14s/it]
                                                          
{'loss': 0.6034, 'learning_rate': 5.309504569306955e-06, 'epoch': 11.23}

 94%|█████████▎| 26290/28080 [51:56:19<3:32:53,  7.14s/it]
 94%|█████████▎| 26291/28080 [51:56:26<3:32:21,  7.12s/it]
                                                          
{'loss': 0.5888, 'learning_rate': 5.303594878159457e-06, 'epoch': 11.23}

 94%|█████████▎| 26291/28080 [51:56:26<3:32:21,  7.12s/it]
 94%|█████████▎| 26292/28080 [51:56:33<3:32:28,  7.13s/it]
                                                          
{'loss': 0.5949, 'learning_rate': 5.2976884424451864e-06, 'epoch': 11.23}

 94%|█████████▎| 26292/28080 [51:56:33<3:32:28,  7.13s/it]
 94%|█████████▎| 26293/28080 [51:56:40<3:30:54,  7.08s/it]
                                                          
{'loss': 0.6192, 'learning_rate': 5.291785262242749e-06, 'epoch': 11.23}

 94%|█████████▎| 26293/28080 [51:56:40<3:30:54,  7.08s/it]
 94%|█████████▎| 26294/28080 [51:56:47<3:31:23,  7.10s/it]
                                                          
{'loss': 0.5859, 'learning_rate': 5.285885337630636e-06, 'epoch': 11.23}

 94%|█████████▎| 26294/28080 [51:56:47<3:31:23,  7.10s/it]
 94%|█████████▎| 26295/28080 [51:56:54<3:29:58,  7.06s/it]
                                                          
{'loss': 0.5822, 'learning_rate': 5.279988668687369e-06, 'epoch': 11.23}

 94%|█████████▎| 26295/28080 [51:56:54<3:29:58,  7.06s/it]
 94%|█████████▎| 26296/28080 [51:57:01<3:30:37,  7.08s/it]
                                                          
{'loss': 0.6153, 'learning_rate': 5.2740952554913565e-06, 'epoch': 11.23}

 94%|█████████▎| 26296/28080 [51:57:01<3:30:37,  7.08s/it]
 94%|█████████▎| 26297/28080 [51:57:08<3:31:12,  7.11s/it]
                                                          
{'loss': 0.5991, 'learning_rate': 5.268205098121093e-06, 'epoch': 11.23}

 94%|█████████▎| 26297/28080 [51:57:08<3:31:12,  7.11s/it]
 94%|█████████▎| 26298/28080 [51:57:15<3:31:07,  7.11s/it]
                                                          
{'loss': 0.5913, 'learning_rate': 5.262318196654847e-06, 'epoch': 11.23}

 94%|█████████▎| 26298/28080 [51:57:15<3:31:07,  7.11s/it]
 94%|█████████▎| 26299/28080 [51:57:22<3:30:00,  7.07s/it]
                                                          
{'loss': 0.5992, 'learning_rate': 5.256434551170974e-06, 'epoch': 11.23}

 94%|█████████▎| 26299/28080 [51:57:22<3:30:00,  7.07s/it]
 94%|█████████▎| 26300/28080 [51:57:29<3:29:46,  7.07s/it]
                                                          
{'loss': 0.6203, 'learning_rate': 5.250554161747773e-06, 'epoch': 11.24}

 94%|█████████▎| 26300/28080 [51:57:29<3:29:46,  7.07s/it]
 94%|█████████▎| 26301/28080 [51:57:37<3:30:34,  7.10s/it]
                                                          
{'loss': 0.5937, 'learning_rate': 5.2446770284634296e-06, 'epoch': 11.24}

 94%|█████████▎| 26301/28080 [51:57:37<3:30:34,  7.10s/it]
 94%|█████████▎| 26302/28080 [51:57:44<3:30:15,  7.10s/it]
                                                          
{'loss': 0.6054, 'learning_rate': 5.238803151396188e-06, 'epoch': 11.24}

 94%|█████████▎| 26302/28080 [51:57:44<3:30:15,  7.10s/it]
 94%|█████████▎| 26303/28080 [51:57:51<3:29:35,  7.08s/it]
                                                          
{'loss': 0.613, 'learning_rate': 5.232932530624152e-06, 'epoch': 11.24}

 94%|█████████▎| 26303/28080 [51:57:51<3:29:35,  7.08s/it]
 94%|█████████▎| 26304/28080 [51:57:58<3:29:48,  7.09s/it]
                                                          
{'loss': 0.6031, 'learning_rate': 5.2270651662254255e-06, 'epoch': 11.24}

 94%|█████████▎| 26304/28080 [51:57:58<3:29:48,  7.09s/it]
 94%|█████████▎| 26305/28080 [51:58:05<3:30:07,  7.10s/it]
                                                          
{'loss': 0.595, 'learning_rate': 5.2212010582780855e-06, 'epoch': 11.24}

 94%|█████████▎| 26305/28080 [51:58:05<3:30:07,  7.10s/it]
 94%|█████████▎| 26306/28080 [51:58:12<3:29:24,  7.08s/it]
                                                          
{'loss': 0.6039, 'learning_rate': 5.215340206860153e-06, 'epoch': 11.24}

 94%|█████████▎| 26306/28080 [51:58:12<3:29:24,  7.08s/it]
 94%|█████████▎| 26307/28080 [51:58:19<3:29:57,  7.11s/it]
                                                          
{'loss': 0.6053, 'learning_rate': 5.209482612049593e-06, 'epoch': 11.24}

 94%|█████████▎| 26307/28080 [51:58:19<3:29:57,  7.11s/it]
 94%|█████████▎| 26308/28080 [51:58:26<3:29:53,  7.11s/it]
                                                          
{'loss': 0.6193, 'learning_rate': 5.203628273924315e-06, 'epoch': 11.24}

 94%|█████████▎| 26308/28080 [51:58:26<3:29:53,  7.11s/it]
 94%|█████████▎| 26309/28080 [51:58:33<3:29:24,  7.09s/it]
                                                          
{'loss': 0.582, 'learning_rate': 5.197777192562203e-06, 'epoch': 11.24}

 94%|█████████▎| 26309/28080 [51:58:33<3:29:24,  7.09s/it]
 94%|█████████▎| 26310/28080 [51:58:40<3:29:17,  7.09s/it]
                                                          
{'loss': 0.6033, 'learning_rate': 5.191929368041137e-06, 'epoch': 11.24}

 94%|█████████▎| 26310/28080 [51:58:40<3:29:17,  7.09s/it]
 94%|█████████▎| 26311/28080 [51:58:47<3:28:05,  7.06s/it]
                                                          
{'loss': 0.6083, 'learning_rate': 5.186084800438917e-06, 'epoch': 11.24}

 94%|█████████▎| 26311/28080 [51:58:47<3:28:05,  7.06s/it]
 94%|█████████▎| 26312/28080 [51:58:54<3:27:30,  7.04s/it]
                                                          
{'loss': 0.5947, 'learning_rate': 5.180243489833258e-06, 'epoch': 11.24}

 94%|█████████▎| 26312/28080 [51:58:54<3:27:30,  7.04s/it]
 94%|█████████▎| 26313/28080 [51:59:02<3:28:28,  7.08s/it]
                                                          
{'loss': 0.602, 'learning_rate': 5.174405436301876e-06, 'epoch': 11.24}

 94%|█████████▎| 26313/28080 [51:59:02<3:28:28,  7.08s/it]
 94%|█████████▎| 26314/28080 [51:59:09<3:28:53,  7.10s/it]
                                                          
{'loss': 0.6256, 'learning_rate': 5.168570639922487e-06, 'epoch': 11.24}

 94%|█████████▎| 26314/28080 [51:59:09<3:28:53,  7.10s/it]
 94%|█████████▎| 26315/28080 [51:59:16<3:29:37,  7.13s/it]
                                                          
{'loss': 0.6081, 'learning_rate': 5.16273910077264e-06, 'epoch': 11.24}

 94%|█████████▎| 26315/28080 [51:59:16<3:29:37,  7.13s/it]
 94%|█████████▎| 26316/28080 [51:59:23<3:30:09,  7.15s/it]
                                                          
{'loss': 0.6104, 'learning_rate': 5.156910818930022e-06, 'epoch': 11.24}

 94%|█████████▎| 26316/28080 [51:59:23<3:30:09,  7.15s/it]
 94%|█████████▎| 26317/28080 [51:59:30<3:30:08,  7.15s/it]
                                                          
{'loss': 0.607, 'learning_rate': 5.151085794472099e-06, 'epoch': 11.24}

 94%|█████████▎| 26317/28080 [51:59:30<3:30:08,  7.15s/it]
 94%|█████████▎| 26318/28080 [51:59:37<3:29:53,  7.15s/it]
                                                          
{'loss': 0.609, 'learning_rate': 5.145264027476365e-06, 'epoch': 11.24}

 94%|█████████▎| 26318/28080 [51:59:37<3:29:53,  7.15s/it]
 94%|█████████▎| 26319/28080 [51:59:45<3:30:41,  7.18s/it]
                                                          
{'loss': 0.6438, 'learning_rate': 5.139445518020286e-06, 'epoch': 11.24}

 94%|█████████▎| 26319/28080 [51:59:45<3:30:41,  7.18s/it]
 94%|█████████▎| 26320/28080 [51:59:52<3:30:34,  7.18s/it]
                                                          
{'loss': 0.604, 'learning_rate': 5.1336302661812995e-06, 'epoch': 11.24}

 94%|█████████▎| 26320/28080 [51:59:52<3:30:34,  7.18s/it]
 94%|█████████▎| 26321/28080 [51:59:59<3:30:06,  7.17s/it]
                                                          
{'loss': 0.5999, 'learning_rate': 5.127818272036733e-06, 'epoch': 11.24}

 94%|█████████▎| 26321/28080 [51:59:59<3:30:06,  7.17s/it]
 94%|█████████▎| 26322/28080 [52:00:06<3:28:37,  7.12s/it]
                                                          
{'loss': 0.5985, 'learning_rate': 5.122009535663941e-06, 'epoch': 11.24}

 94%|█████████▎| 26322/28080 [52:00:06<3:28:37,  7.12s/it]
 94%|█████████▎| 26323/28080 [52:00:13<3:27:46,  7.10s/it]
                                                          
{'loss': 0.6149, 'learning_rate': 5.116204057140167e-06, 'epoch': 11.24}

 94%|█████████▎| 26323/28080 [52:00:13<3:27:46,  7.10s/it]
 94%|█████████▎| 26324/28080 [52:00:20<3:27:56,  7.10s/it]
                                                          
{'loss': 0.5914, 'learning_rate': 5.110401836542683e-06, 'epoch': 11.25}

 94%|█████████▎| 26324/28080 [52:00:20<3:27:56,  7.10s/it]
 94%|█████████▍| 26325/28080 [52:00:27<3:28:24,  7.12s/it]
                                                          
{'loss': 0.5969, 'learning_rate': 5.10460287394865e-06, 'epoch': 11.25}

 94%|█████████▍| 26325/28080 [52:00:27<3:28:24,  7.12s/it]
 94%|█████████▍| 26326/28080 [52:00:34<3:28:17,  7.12s/it]
                                                          
{'loss': 0.5859, 'learning_rate': 5.098807169435227e-06, 'epoch': 11.25}

 94%|█████████▍| 26326/28080 [52:00:34<3:28:17,  7.12s/it]
 94%|█████████▍| 26327/28080 [52:00:42<3:28:29,  7.14s/it]
                                                          
{'loss': 0.6046, 'learning_rate': 5.09301472307952e-06, 'epoch': 11.25}

 94%|█████████▍| 26327/28080 [52:00:42<3:28:29,  7.14s/it]
 94%|█████████▍| 26328/28080 [52:00:49<3:28:28,  7.14s/it]
                                                          
{'loss': 0.5768, 'learning_rate': 5.087225534958606e-06, 'epoch': 11.25}

 94%|█████████▍| 26328/28080 [52:00:49<3:28:28,  7.14s/it]
 94%|█████████▍| 26329/28080 [52:00:56<3:28:28,  7.14s/it]
                                                          
{'loss': 0.5854, 'learning_rate': 5.081439605149479e-06, 'epoch': 11.25}

 94%|█████████▍| 26329/28080 [52:00:56<3:28:28,  7.14s/it]
 94%|█████████▍| 26330/28080 [52:01:03<3:28:09,  7.14s/it]
                                                          
{'loss': 0.6012, 'learning_rate': 5.075656933729189e-06, 'epoch': 11.25}

 94%|█████████▍| 26330/28080 [52:01:03<3:28:09,  7.14s/it]
 94%|█████████▍| 26331/28080 [52:01:10<3:27:26,  7.12s/it]
                                                          
{'loss': 0.6231, 'learning_rate': 5.0698775207745355e-06, 'epoch': 11.25}

 94%|█████████▍| 26331/28080 [52:01:10<3:27:26,  7.12s/it]
 94%|█████████▍| 26332/28080 [52:01:17<3:26:20,  7.08s/it]
                                                          
{'loss': 0.6052, 'learning_rate': 5.064101366362539e-06, 'epoch': 11.25}

 94%|█████████▍| 26332/28080 [52:01:17<3:26:20,  7.08s/it]
 94%|█████████▍| 26333/28080 [52:01:24<3:26:55,  7.11s/it]
                                                          
{'loss': 0.6265, 'learning_rate': 5.058328470569945e-06, 'epoch': 11.25}

 94%|█████████▍| 26333/28080 [52:01:24<3:26:55,  7.11s/it]
 94%|█████████▍| 26334/28080 [52:01:31<3:27:33,  7.13s/it]
                                                          
{'loss': 0.6066, 'learning_rate': 5.052558833473608e-06, 'epoch': 11.25}

 94%|█████████▍| 26334/28080 [52:01:31<3:27:33,  7.13s/it]
 94%|█████████▍| 26335/28080 [52:01:39<3:27:10,  7.12s/it]
                                                          
{'loss': 0.6181, 'learning_rate': 5.046792455150273e-06, 'epoch': 11.25}

 94%|█████████▍| 26335/28080 [52:01:39<3:27:10,  7.12s/it]
 94%|█████████▍| 26336/28080 [52:01:46<3:26:30,  7.10s/it]
                                                          
{'loss': 0.6154, 'learning_rate': 5.0410293356766835e-06, 'epoch': 11.25}

 94%|█████████▍| 26336/28080 [52:01:46<3:26:30,  7.10s/it]
 94%|█████████▍| 26337/28080 [52:01:53<3:26:46,  7.12s/it]
                                                          
{'loss': 0.5744, 'learning_rate': 5.035269475129473e-06, 'epoch': 11.25}

 94%|█████████▍| 26337/28080 [52:01:53<3:26:46,  7.12s/it]
 94%|█████████▍| 26338/28080 [52:02:00<3:25:35,  7.08s/it]
                                                          
{'loss': 0.585, 'learning_rate': 5.029512873585274e-06, 'epoch': 11.25}

 94%|█████████▍| 26338/28080 [52:02:00<3:25:35,  7.08s/it]
 94%|█████████▍| 26339/28080 [52:02:07<3:26:51,  7.13s/it]
                                                          
{'loss': 0.5886, 'learning_rate': 5.02375953112072e-06, 'epoch': 11.25}

 94%|█████████▍| 26339/28080 [52:02:07<3:26:51,  7.13s/it]
 94%|█████████▍| 26340/28080 [52:02:14<3:26:53,  7.13s/it]
                                                          
{'loss': 0.5938, 'learning_rate': 5.018009447812305e-06, 'epoch': 11.25}

 94%|█████████▍| 26340/28080 [52:02:14<3:26:53,  7.13s/it]
 94%|█████████▍| 26341/28080 [52:02:21<3:26:57,  7.14s/it]
                                                          
{'loss': 0.5827, 'learning_rate': 5.012262623736525e-06, 'epoch': 11.25}

 94%|█████████▍| 26341/28080 [52:02:21<3:26:57,  7.14s/it]
 94%|█████████▍| 26342/28080 [52:02:29<3:27:12,  7.15s/it]
                                                          
{'loss': 0.5964, 'learning_rate': 5.006519058969844e-06, 'epoch': 11.25}

 94%|█████████▍| 26342/28080 [52:02:29<3:27:12,  7.15s/it]
 94%|█████████▍| 26343/28080 [52:02:36<3:26:14,  7.12s/it]
                                                          
{'loss': 0.5953, 'learning_rate': 5.000778753588703e-06, 'epoch': 11.25}

 94%|█████████▍| 26343/28080 [52:02:36<3:26:14,  7.12s/it]
 94%|█████████▍| 26344/28080 [52:02:43<3:25:47,  7.11s/it]
                                                          
{'loss': 0.5827, 'learning_rate': 4.995041707669456e-06, 'epoch': 11.25}

 94%|█████████▍| 26344/28080 [52:02:43<3:25:47,  7.11s/it]
 94%|█████████▍| 26345/28080 [52:02:50<3:25:36,  7.11s/it]
                                                          
{'loss': 0.5988, 'learning_rate': 4.9893079212884055e-06, 'epoch': 11.25}

 94%|█████████▍| 26345/28080 [52:02:50<3:25:36,  7.11s/it]
 94%|█████████▍| 26346/28080 [52:02:57<3:25:30,  7.11s/it]
                                                          
{'loss': 0.593, 'learning_rate': 4.983577394521821e-06, 'epoch': 11.25}

 94%|█████████▍| 26346/28080 [52:02:57<3:25:30,  7.11s/it]
 94%|█████████▍| 26347/28080 [52:03:04<3:24:09,  7.07s/it]
                                                          
{'loss': 0.6217, 'learning_rate': 4.977850127446004e-06, 'epoch': 11.26}

 94%|█████████▍| 26347/28080 [52:03:04<3:24:09,  7.07s/it]
 94%|█████████▍| 26348/28080 [52:03:11<3:23:09,  7.04s/it]
                                                          
{'loss': 0.6344, 'learning_rate': 4.972126120137088e-06, 'epoch': 11.26}

 94%|█████████▍| 26348/28080 [52:03:11<3:23:09,  7.04s/it]
 94%|█████████▍| 26349/28080 [52:03:18<3:24:07,  7.08s/it]
                                                          
{'loss': 0.5718, 'learning_rate': 4.96640537267129e-06, 'epoch': 11.26}

 94%|█████████▍| 26349/28080 [52:03:18<3:24:07,  7.08s/it]
 94%|█████████▍| 26350/28080 [52:03:25<3:24:00,  7.08s/it]
                                                          
{'loss': 0.578, 'learning_rate': 4.960687885124687e-06, 'epoch': 11.26}

 94%|█████████▍| 26350/28080 [52:03:25<3:24:00,  7.08s/it]
 94%|█████████▍| 26351/28080 [52:03:32<3:24:39,  7.10s/it]
                                                          
{'loss': 0.6043, 'learning_rate': 4.954973657573303e-06, 'epoch': 11.26}

 94%|█████████▍| 26351/28080 [52:03:32<3:24:39,  7.10s/it]
 94%|█████████▍| 26352/28080 [52:03:39<3:25:24,  7.13s/it]
                                                          
{'loss': 0.5931, 'learning_rate': 4.9492626900932145e-06, 'epoch': 11.26}

 94%|█████████▍| 26352/28080 [52:03:39<3:25:24,  7.13s/it]
 94%|█████████▍| 26353/28080 [52:03:46<3:24:34,  7.11s/it]
                                                          
{'loss': 0.5957, 'learning_rate': 4.94355498276039e-06, 'epoch': 11.26}

 94%|█████████▍| 26353/28080 [52:03:46<3:24:34,  7.11s/it]
 94%|█████████▍| 26354/28080 [52:03:54<3:25:05,  7.13s/it]
                                                          
{'loss': 0.6162, 'learning_rate': 4.9378505356507394e-06, 'epoch': 11.26}

 94%|█████████▍| 26354/28080 [52:03:54<3:25:05,  7.13s/it]
 94%|█████████▍| 26355/28080 [52:04:01<3:24:26,  7.11s/it]
                                                          
{'loss': 0.5706, 'learning_rate': 4.932149348840176e-06, 'epoch': 11.26}

 94%|█████████▍| 26355/28080 [52:04:01<3:24:26,  7.11s/it]
 94%|█████████▍| 26356/28080 [52:04:08<3:24:32,  7.12s/it]
                                                          
{'loss': 0.5813, 'learning_rate': 4.926451422404526e-06, 'epoch': 11.26}

 94%|█████████▍| 26356/28080 [52:04:08<3:24:32,  7.12s/it]
 94%|█████████▍| 26357/28080 [52:04:15<3:23:45,  7.10s/it]
                                                          
{'loss': 0.5961, 'learning_rate': 4.920756756419648e-06, 'epoch': 11.26}

 94%|█████████▍| 26357/28080 [52:04:15<3:23:45,  7.10s/it]
 94%|█████████▍| 26358/28080 [52:04:22<3:24:00,  7.11s/it]
                                                          
{'loss': 0.59, 'learning_rate': 4.915065350961229e-06, 'epoch': 11.26}

 94%|█████████▍| 26358/28080 [52:04:22<3:24:00,  7.11s/it]
 94%|█████████▍| 26359/28080 [52:04:29<3:24:06,  7.12s/it]
                                                          
{'loss': 0.5998, 'learning_rate': 4.90937720610507e-06, 'epoch': 11.26}

 94%|█████████▍| 26359/28080 [52:04:29<3:24:06,  7.12s/it]
 94%|█████████▍| 26360/28080 [52:04:36<3:23:13,  7.09s/it]
                                                          
{'loss': 0.621, 'learning_rate': 4.903692321926778e-06, 'epoch': 11.26}

 94%|█████████▍| 26360/28080 [52:04:36<3:23:13,  7.09s/it]
 94%|█████████▍| 26361/28080 [52:04:43<3:22:30,  7.07s/it]
                                                          
{'loss': 0.5938, 'learning_rate': 4.8980106985019865e-06, 'epoch': 11.26}

 94%|█████████▍| 26361/28080 [52:04:43<3:22:30,  7.07s/it]
 94%|█████████▍| 26362/28080 [52:04:50<3:22:39,  7.08s/it]
                                                          
{'loss': 0.6042, 'learning_rate': 4.89233233590633e-06, 'epoch': 11.26}

 94%|█████████▍| 26362/28080 [52:04:50<3:22:39,  7.08s/it]
 94%|█████████▍| 26363/28080 [52:04:57<3:22:39,  7.08s/it]
                                                          
{'loss': 0.5857, 'learning_rate': 4.886657234215303e-06, 'epoch': 11.26}

 94%|█████████▍| 26363/28080 [52:04:57<3:22:39,  7.08s/it]
 94%|█████████▍| 26364/28080 [52:05:04<3:22:18,  7.07s/it]
                                                          
{'loss': 0.6002, 'learning_rate': 4.880985393504484e-06, 'epoch': 11.26}

 94%|█████████▍| 26364/28080 [52:05:04<3:22:18,  7.07s/it]
 94%|█████████▍| 26365/28080 [52:05:11<3:21:58,  7.07s/it]
                                                          
{'loss': 0.6245, 'learning_rate': 4.875316813849229e-06, 'epoch': 11.26}

 94%|█████████▍| 26365/28080 [52:05:12<3:21:58,  7.07s/it]
 94%|█████████▍| 26366/28080 [52:05:19<3:22:18,  7.08s/it]
                                                          
{'loss': 0.6125, 'learning_rate': 4.869651495325006e-06, 'epoch': 11.26}

 94%|█████████▍| 26366/28080 [52:05:19<3:22:18,  7.08s/it]
 94%|█████████▍| 26367/28080 [52:05:26<3:22:23,  7.09s/it]
                                                          
{'loss': 0.5957, 'learning_rate': 4.863989438007199e-06, 'epoch': 11.26}

 94%|█████████▍| 26367/28080 [52:05:26<3:22:23,  7.09s/it]
 94%|█████████▍| 26368/28080 [52:05:33<3:21:54,  7.08s/it]
                                                          
{'loss': 0.5976, 'learning_rate': 4.858330641971109e-06, 'epoch': 11.26}

 94%|█████████▍| 26368/28080 [52:05:33<3:21:54,  7.08s/it]
 94%|█████████▍| 26369/28080 [52:05:40<3:22:41,  7.11s/it]
                                                          
{'loss': 0.6278, 'learning_rate': 4.852675107292037e-06, 'epoch': 11.26}

 94%|█████████▍| 26369/28080 [52:05:40<3:22:41,  7.11s/it]
 94%|█████████▍| 26370/28080 [52:05:47<3:22:38,  7.11s/it]
                                                          
{'loss': 0.6009, 'learning_rate': 4.847022834045228e-06, 'epoch': 11.27}

 94%|█████████▍| 26370/28080 [52:05:47<3:22:38,  7.11s/it]
 94%|█████████▍| 26371/28080 [52:05:54<3:22:13,  7.10s/it]
                                                          
{'loss': 0.6044, 'learning_rate': 4.841373822305844e-06, 'epoch': 11.27}

 94%|█████████▍| 26371/28080 [52:05:54<3:22:13,  7.10s/it]
 94%|█████████▍| 26372/28080 [52:06:01<3:23:03,  7.13s/it]
                                                          
{'loss': 0.6005, 'learning_rate': 4.8357280721491035e-06, 'epoch': 11.27}

 94%|█████████▍| 26372/28080 [52:06:01<3:23:03,  7.13s/it]
 94%|█████████▍| 26373/28080 [52:06:08<3:22:47,  7.13s/it]
                                                          
{'loss': 0.6122, 'learning_rate': 4.830085583650057e-06, 'epoch': 11.27}

 94%|█████████▍| 26373/28080 [52:06:08<3:22:47,  7.13s/it]
 94%|█████████▍| 26374/28080 [52:06:16<3:21:58,  7.10s/it]
                                                          
{'loss': 0.5849, 'learning_rate': 4.82444635688381e-06, 'epoch': 11.27}

 94%|█████████▍| 26374/28080 [52:06:16<3:21:58,  7.10s/it]
 94%|█████████▍| 26375/28080 [52:06:23<3:22:15,  7.12s/it]
                                                          
{'loss': 0.5866, 'learning_rate': 4.818810391925332e-06, 'epoch': 11.27}

 94%|█████████▍| 26375/28080 [52:06:23<3:22:15,  7.12s/it]
 94%|█████████▍| 26376/28080 [52:06:30<3:22:47,  7.14s/it]
                                                          
{'loss': 0.6046, 'learning_rate': 4.8131776888496735e-06, 'epoch': 11.27}

 94%|█████████▍| 26376/28080 [52:06:30<3:22:47,  7.14s/it]
 94%|█████████▍| 26377/28080 [52:06:37<3:22:13,  7.12s/it]
                                                          
{'loss': 0.5933, 'learning_rate': 4.807548247731719e-06, 'epoch': 11.27}

 94%|█████████▍| 26377/28080 [52:06:37<3:22:13,  7.12s/it]
 94%|█████████▍| 26378/28080 [52:06:44<3:21:42,  7.11s/it]
                                                          
{'loss': 0.5897, 'learning_rate': 4.801922068646436e-06, 'epoch': 11.27}

 94%|█████████▍| 26378/28080 [52:06:44<3:21:42,  7.11s/it]
 94%|█████████▍| 26379/28080 [52:06:51<3:21:47,  7.12s/it]
                                                          
{'loss': 0.5745, 'learning_rate': 4.796299151668571e-06, 'epoch': 11.27}

 94%|█████████▍| 26379/28080 [52:06:51<3:21:47,  7.12s/it]
 94%|█████████▍| 26380/28080 [52:06:58<3:22:04,  7.13s/it]
                                                          
{'loss': 0.5973, 'learning_rate': 4.790679496873007e-06, 'epoch': 11.27}

 94%|█████████▍| 26380/28080 [52:06:58<3:22:04,  7.13s/it]
 94%|█████████▍| 26381/28080 [52:07:05<3:21:44,  7.12s/it]
                                                          
{'loss': 0.5932, 'learning_rate': 4.785063104334436e-06, 'epoch': 11.27}

 94%|█████████▍| 26381/28080 [52:07:05<3:21:44,  7.12s/it]
 94%|█████████▍| 26382/28080 [52:07:13<3:21:28,  7.12s/it]
                                                          
{'loss': 0.5956, 'learning_rate': 4.7794499741276866e-06, 'epoch': 11.27}

 94%|█████████▍| 26382/28080 [52:07:13<3:21:28,  7.12s/it]
 94%|█████████▍| 26383/28080 [52:07:20<3:21:18,  7.12s/it]
                                                          
{'loss': 0.5994, 'learning_rate': 4.773840106327365e-06, 'epoch': 11.27}

 94%|█████████▍| 26383/28080 [52:07:20<3:21:18,  7.12s/it]
 94%|█████████▍| 26384/28080 [52:07:27<3:20:53,  7.11s/it]
                                                          
{'loss': 0.6069, 'learning_rate': 4.768233501008107e-06, 'epoch': 11.27}

 94%|█████████▍| 26384/28080 [52:07:27<3:20:53,  7.11s/it]
 94%|█████████▍| 26385/28080 [52:07:34<3:20:32,  7.10s/it]
                                                          
{'loss': 0.5935, 'learning_rate': 4.762630158244518e-06, 'epoch': 11.27}

 94%|█████████▍| 26385/28080 [52:07:34<3:20:32,  7.10s/it]
 94%|█████████▍| 26386/28080 [52:07:41<3:20:08,  7.09s/it]
                                                          
{'loss': 0.6032, 'learning_rate': 4.757030078111096e-06, 'epoch': 11.27}

 94%|█████████▍| 26386/28080 [52:07:41<3:20:08,  7.09s/it]
 94%|█████████▍| 26387/28080 [52:07:48<3:20:06,  7.09s/it]
                                                          
{'loss': 0.5913, 'learning_rate': 4.75143326068242e-06, 'epoch': 11.27}

 94%|█████████▍| 26387/28080 [52:07:48<3:20:06,  7.09s/it]
 94%|█████████▍| 26388/28080 [52:07:55<3:20:07,  7.10s/it]
                                                          
{'loss': 0.5868, 'learning_rate': 4.745839706032929e-06, 'epoch': 11.27}

 94%|█████████▍| 26388/28080 [52:07:55<3:20:07,  7.10s/it]
 94%|█████████▍| 26389/28080 [52:08:02<3:19:14,  7.07s/it]
                                                          
{'loss': 0.5741, 'learning_rate': 4.740249414237008e-06, 'epoch': 11.27}

 94%|█████████▍| 26389/28080 [52:08:02<3:19:14,  7.07s/it]
 94%|█████████▍| 26390/28080 [52:08:09<3:19:42,  7.09s/it]
                                                          
{'loss': 0.6123, 'learning_rate': 4.734662385369043e-06, 'epoch': 11.27}

 94%|█████████▍| 26390/28080 [52:08:09<3:19:42,  7.09s/it]
 94%|█████████▍| 26391/28080 [52:08:16<3:19:56,  7.10s/it]
                                                          
{'loss': 0.5961, 'learning_rate': 4.729078619503363e-06, 'epoch': 11.27}

 94%|█████████▍| 26391/28080 [52:08:16<3:19:56,  7.10s/it]
 94%|█████████▍| 26392/28080 [52:08:24<3:20:35,  7.13s/it]
                                                          
{'loss': 0.6015, 'learning_rate': 4.723498116714298e-06, 'epoch': 11.27}

 94%|█████████▍| 26392/28080 [52:08:24<3:20:35,  7.13s/it]
 94%|█████████▍| 26393/28080 [52:08:31<3:19:45,  7.10s/it]
                                                          
{'loss': 0.5677, 'learning_rate': 4.717920877076038e-06, 'epoch': 11.27}

 94%|█████████▍| 26393/28080 [52:08:31<3:19:45,  7.10s/it]
 94%|█████████▍| 26394/28080 [52:08:38<3:18:08,  7.05s/it]
                                                          
{'loss': 0.6156, 'learning_rate': 4.712346900662773e-06, 'epoch': 11.28}

 94%|█████████▍| 26394/28080 [52:08:38<3:18:08,  7.05s/it]
 94%|█████████▍| 26395/28080 [52:08:45<3:18:36,  7.07s/it]
                                                          
{'loss': 0.5883, 'learning_rate': 4.706776187548695e-06, 'epoch': 11.28}

 94%|█████████▍| 26395/28080 [52:08:45<3:18:36,  7.07s/it]
 94%|█████████▍| 26396/28080 [52:08:52<3:18:53,  7.09s/it]
                                                          
{'loss': 0.5878, 'learning_rate': 4.701208737807883e-06, 'epoch': 11.28}

 94%|█████████▍| 26396/28080 [52:08:52<3:18:53,  7.09s/it]
 94%|█████████▍| 26397/28080 [52:08:59<3:18:21,  7.07s/it]
                                                          
{'loss': 0.5916, 'learning_rate': 4.695644551514472e-06, 'epoch': 11.28}

 94%|█████████▍| 26397/28080 [52:08:59<3:18:21,  7.07s/it]
 94%|█████████▍| 26398/28080 [52:09:06<3:18:52,  7.09s/it]
                                                          
{'loss': 0.5904, 'learning_rate': 4.690083628742431e-06, 'epoch': 11.28}

 94%|█████████▍| 26398/28080 [52:09:06<3:18:52,  7.09s/it]
 94%|█████████▍| 26399/28080 [52:09:13<3:19:26,  7.12s/it]
                                                          
{'loss': 0.5962, 'learning_rate': 4.6845259695657285e-06, 'epoch': 11.28}

 94%|█████████▍| 26399/28080 [52:09:13<3:19:26,  7.12s/it]
 94%|█████████▍| 26400/28080 [52:09:20<3:18:54,  7.10s/it]
                                                          
{'loss': 0.5683, 'learning_rate': 4.678971574058361e-06, 'epoch': 11.28}

 94%|█████████▍| 26400/28080 [52:09:20<3:18:54,  7.10s/it]
 94%|█████████▍| 26401/28080 [52:09:27<3:19:01,  7.11s/it]
                                                          
{'loss': 0.5845, 'learning_rate': 4.673420442294185e-06, 'epoch': 11.28}

 94%|█████████▍| 26401/28080 [52:09:27<3:19:01,  7.11s/it]
 94%|█████████▍| 26402/28080 [52:09:34<3:17:34,  7.06s/it]
                                                          
{'loss': 0.5955, 'learning_rate': 4.6678725743470595e-06, 'epoch': 11.28}

 94%|█████████▍| 26402/28080 [52:09:34<3:17:34,  7.06s/it]
 94%|█████████▍| 26403/28080 [52:09:41<3:17:35,  7.07s/it]
                                                          
{'loss': 0.6023, 'learning_rate': 4.662327970290786e-06, 'epoch': 11.28}

 94%|█████████▍| 26403/28080 [52:09:41<3:17:35,  7.07s/it]
 94%|█████████▍| 26404/28080 [52:09:49<3:18:11,  7.10s/it]
                                                          
{'loss': 0.588, 'learning_rate': 4.656786630199139e-06, 'epoch': 11.28}

 94%|█████████▍| 26404/28080 [52:09:49<3:18:11,  7.10s/it]
 94%|█████████▍| 26405/28080 [52:09:56<3:18:37,  7.11s/it]
                                                          
{'loss': 0.59, 'learning_rate': 4.651248554145837e-06, 'epoch': 11.28}

 94%|█████████▍| 26405/28080 [52:09:56<3:18:37,  7.11s/it]
 94%|█████████▍| 26406/28080 [52:10:03<3:18:41,  7.12s/it]
                                                          
{'loss': 0.5763, 'learning_rate': 4.6457137422045715e-06, 'epoch': 11.28}

 94%|█████████▍| 26406/28080 [52:10:03<3:18:41,  7.12s/it]
 94%|█████████▍| 26407/28080 [52:10:10<3:18:32,  7.12s/it]
                                                          
{'loss': 0.581, 'learning_rate': 4.640182194448977e-06, 'epoch': 11.28}

 94%|█████████▍| 26407/28080 [52:10:10<3:18:32,  7.12s/it]
 94%|█████████▍| 26408/28080 [52:10:17<3:17:19,  7.08s/it]
                                                          
{'loss': 0.6151, 'learning_rate': 4.634653910952636e-06, 'epoch': 11.28}

 94%|█████████▍| 26408/28080 [52:10:17<3:17:19,  7.08s/it]
 94%|█████████▍| 26409/28080 [52:10:24<3:17:42,  7.10s/it]
                                                          
{'loss': 0.5874, 'learning_rate': 4.62912889178907e-06, 'epoch': 11.28}

 94%|█████████▍| 26409/28080 [52:10:24<3:17:42,  7.10s/it]
 94%|█████████▍| 26410/28080 [52:10:31<3:17:01,  7.08s/it]
                                                          
{'loss': 0.5821, 'learning_rate': 4.6236071370318044e-06, 'epoch': 11.28}

 94%|█████████▍| 26410/28080 [52:10:31<3:17:01,  7.08s/it]
 94%|█████████▍| 26411/28080 [52:10:38<3:17:11,  7.09s/it]
                                                          
{'loss': 0.5878, 'learning_rate': 4.6180886467543095e-06, 'epoch': 11.28}

 94%|█████████▍| 26411/28080 [52:10:38<3:17:11,  7.09s/it]
 94%|█████████▍| 26412/28080 [52:10:45<3:16:28,  7.07s/it]
                                                          
{'loss': 0.6308, 'learning_rate': 4.612573421030053e-06, 'epoch': 11.28}

 94%|█████████▍| 26412/28080 [52:10:45<3:16:28,  7.07s/it]
 94%|█████████▍| 26413/28080 [52:10:52<3:17:29,  7.11s/it]
                                                          
{'loss': 0.6117, 'learning_rate': 4.607061459932282e-06, 'epoch': 11.28}

 94%|█████████▍| 26413/28080 [52:10:52<3:17:29,  7.11s/it]
 94%|█████████▍| 26414/28080 [52:11:00<3:17:37,  7.12s/it]
                                                          
{'loss': 0.5909, 'learning_rate': 4.601552763534439e-06, 'epoch': 11.28}

 94%|█████████▍| 26414/28080 [52:11:00<3:17:37,  7.12s/it]
 94%|█████████▍| 26415/28080 [52:11:07<3:17:53,  7.13s/it]
                                                          
{'loss': 0.6047, 'learning_rate': 4.596047331909742e-06, 'epoch': 11.28}

 94%|█████████▍| 26415/28080 [52:11:07<3:17:53,  7.13s/it]
 94%|█████████▍| 26416/28080 [52:11:14<3:17:06,  7.11s/it]
                                                          
{'loss': 0.5943, 'learning_rate': 4.590545165131493e-06, 'epoch': 11.28}

 94%|█████████▍| 26416/28080 [52:11:14<3:17:06,  7.11s/it]
 94%|█████████▍| 26417/28080 [52:11:21<3:17:47,  7.14s/it]
                                                          
{'loss': 0.5876, 'learning_rate': 4.585046263272857e-06, 'epoch': 11.29}

 94%|█████████▍| 26417/28080 [52:11:21<3:17:47,  7.14s/it]
 94%|█████████▍| 26418/28080 [52:11:28<3:17:15,  7.12s/it]
                                                          
{'loss': 0.5989, 'learning_rate': 4.579550626407025e-06, 'epoch': 11.29}

 94%|█████████▍| 26418/28080 [52:11:28<3:17:15,  7.12s/it]
 94%|█████████▍| 26419/28080 [52:11:35<3:17:38,  7.14s/it]
                                                          
{'loss': 0.6016, 'learning_rate': 4.574058254607049e-06, 'epoch': 11.29}

 94%|█████████▍| 26419/28080 [52:11:35<3:17:38,  7.14s/it]
 94%|█████████▍| 26420/28080 [52:11:42<3:17:25,  7.14s/it]
                                                          
{'loss': 0.6008, 'learning_rate': 4.568569147946067e-06, 'epoch': 11.29}

 94%|█████████▍| 26420/28080 [52:11:42<3:17:25,  7.14s/it]
 94%|█████████▍| 26421/28080 [52:11:50<3:17:18,  7.14s/it]
                                                          
{'loss': 0.6011, 'learning_rate': 4.5630833064970455e-06, 'epoch': 11.29}

 94%|█████████▍| 26421/28080 [52:11:50<3:17:18,  7.14s/it]
 94%|█████████▍| 26422/28080 [52:11:57<3:16:43,  7.12s/it]
                                                          
{'loss': 0.6184, 'learning_rate': 4.557600730333011e-06, 'epoch': 11.29}

 94%|█████████▍| 26422/28080 [52:11:57<3:16:43,  7.12s/it]
 94%|█████████▍| 26423/28080 [52:12:04<3:16:44,  7.12s/it]
                                                          
{'loss': 0.6042, 'learning_rate': 4.552121419526878e-06, 'epoch': 11.29}

 94%|█████████▍| 26423/28080 [52:12:04<3:16:44,  7.12s/it]
 94%|█████████▍| 26424/28080 [52:12:11<3:16:36,  7.12s/it]
                                                          
{'loss': 0.608, 'learning_rate': 4.546645374151587e-06, 'epoch': 11.29}

 94%|█████████▍| 26424/28080 [52:12:11<3:16:36,  7.12s/it]
 94%|█████████▍| 26425/28080 [52:12:18<3:16:35,  7.13s/it]
                                                          
{'loss': 0.605, 'learning_rate': 4.541172594279913e-06, 'epoch': 11.29}

 94%|█████████▍| 26425/28080 [52:12:18<3:16:35,  7.13s/it]
 94%|█████████▍| 26426/28080 [52:12:25<3:16:17,  7.12s/it]
                                                          
{'loss': 0.6094, 'learning_rate': 4.535703079984771e-06, 'epoch': 11.29}

 94%|█████████▍| 26426/28080 [52:12:25<3:16:17,  7.12s/it]
 94%|█████████▍| 26427/28080 [52:12:32<3:15:57,  7.11s/it]
                                                          
{'loss': 0.6075, 'learning_rate': 4.530236831338824e-06, 'epoch': 11.29}

 94%|█████████▍| 26427/28080 [52:12:32<3:15:57,  7.11s/it]
 94%|█████████▍| 26428/28080 [52:12:39<3:15:55,  7.12s/it]
                                                          
{'loss': 0.5851, 'learning_rate': 4.524773848414848e-06, 'epoch': 11.29}

 94%|█████████▍| 26428/28080 [52:12:39<3:15:55,  7.12s/it]
 94%|█████████▍| 26429/28080 [52:12:46<3:16:03,  7.12s/it]
                                                          
{'loss': 0.6176, 'learning_rate': 4.519314131285507e-06, 'epoch': 11.29}

 94%|█████████▍| 26429/28080 [52:12:46<3:16:03,  7.12s/it]
 94%|█████████▍| 26430/28080 [52:12:53<3:14:51,  7.09s/it]
                                                          
{'loss': 0.5984, 'learning_rate': 4.513857680023464e-06, 'epoch': 11.29}

 94%|█████████▍| 26430/28080 [52:12:53<3:14:51,  7.09s/it]
 94%|█████████▍| 26431/28080 [52:13:01<3:14:34,  7.08s/it]
                                                          
{'loss': 0.5967, 'learning_rate': 4.508404494701273e-06, 'epoch': 11.29}

 94%|█████████▍| 26431/28080 [52:13:01<3:14:34,  7.08s/it]
 94%|█████████▍| 26432/28080 [52:13:08<3:14:18,  7.07s/it]
                                                          
{'loss': 0.6048, 'learning_rate': 4.5029545753915156e-06, 'epoch': 11.29}

 94%|█████████▍| 26432/28080 [52:13:08<3:14:18,  7.07s/it]
 94%|█████████▍| 26433/28080 [52:13:15<3:14:28,  7.08s/it]
                                                          
{'loss': 0.6006, 'learning_rate': 4.497507922166688e-06, 'epoch': 11.29}

 94%|█████████▍| 26433/28080 [52:13:15<3:14:28,  7.08s/it]
 94%|█████████▍| 26434/28080 [52:13:22<3:14:31,  7.09s/it]
                                                          
{'loss': 0.6136, 'learning_rate': 4.492064535099205e-06, 'epoch': 11.29}

 94%|█████████▍| 26434/28080 [52:13:22<3:14:31,  7.09s/it]
 94%|█████████▍| 26435/28080 [52:13:29<3:14:57,  7.11s/it]
                                                          
{'loss': 0.5768, 'learning_rate': 4.486624414261564e-06, 'epoch': 11.29}

 94%|█████████▍| 26435/28080 [52:13:29<3:14:57,  7.11s/it]
 94%|█████████▍| 26436/28080 [52:13:36<3:14:52,  7.11s/it]
                                                          
{'loss': 0.6068, 'learning_rate': 4.481187559726097e-06, 'epoch': 11.29}

 94%|█████████▍| 26436/28080 [52:13:36<3:14:52,  7.11s/it]
 94%|█████████▍| 26437/28080 [52:13:43<3:13:54,  7.08s/it]
                                                          
{'loss': 0.6059, 'learning_rate': 4.475753971565133e-06, 'epoch': 11.29}

 94%|█████████▍| 26437/28080 [52:13:43<3:13:54,  7.08s/it]
 94%|█████████▍| 26438/28080 [52:13:50<3:14:20,  7.10s/it]
                                                          
{'loss': 0.5894, 'learning_rate': 4.4703236498509495e-06, 'epoch': 11.29}

 94%|█████████▍| 26438/28080 [52:13:50<3:14:20,  7.10s/it]
 94%|█████████▍| 26439/28080 [52:13:57<3:13:47,  7.09s/it]
                                                          
{'loss': 0.5837, 'learning_rate': 4.464896594655849e-06, 'epoch': 11.29}

 94%|█████████▍| 26439/28080 [52:13:57<3:13:47,  7.09s/it]
 94%|█████████▍| 26440/28080 [52:14:04<3:14:07,  7.10s/it]
                                                          
{'loss': 0.6016, 'learning_rate': 4.459472806051995e-06, 'epoch': 11.29}

 94%|█████████▍| 26440/28080 [52:14:04<3:14:07,  7.10s/it]
 94%|█████████▍| 26441/28080 [52:14:12<3:14:13,  7.11s/it]
                                                          
{'loss': 0.6098, 'learning_rate': 4.454052284111526e-06, 'epoch': 11.3}

 94%|█████████▍| 26441/28080 [52:14:12<3:14:13,  7.11s/it]
 94%|█████████▍| 26442/28080 [52:14:19<3:14:13,  7.11s/it]
                                                          
{'loss': 0.5991, 'learning_rate': 4.448635028906578e-06, 'epoch': 11.3}

 94%|█████████▍| 26442/28080 [52:14:19<3:14:13,  7.11s/it]
 94%|█████████▍| 26443/28080 [52:14:26<3:14:27,  7.13s/it]
                                                          
{'loss': 0.6162, 'learning_rate': 4.443221040509232e-06, 'epoch': 11.3}

 94%|█████████▍| 26443/28080 [52:14:26<3:14:27,  7.13s/it]
 94%|█████████▍| 26444/28080 [52:14:33<3:14:48,  7.14s/it]
                                                          
{'loss': 0.5895, 'learning_rate': 4.4378103189914585e-06, 'epoch': 11.3}

 94%|█████████▍| 26444/28080 [52:14:33<3:14:48,  7.14s/it]
 94%|█████████▍| 26445/28080 [52:14:40<3:14:56,  7.15s/it]
                                                          
{'loss': 0.5957, 'learning_rate': 4.432402864425367e-06, 'epoch': 11.3}

 94%|█████████▍| 26445/28080 [52:14:40<3:14:56,  7.15s/it]
 94%|█████████▍| 26446/28080 [52:14:47<3:13:54,  7.12s/it]
                                                          
{'loss': 0.5995, 'learning_rate': 4.426998676882732e-06, 'epoch': 11.3}

 94%|█████████▍| 26446/28080 [52:14:47<3:13:54,  7.12s/it]
 94%|█████████▍| 26447/28080 [52:14:54<3:13:27,  7.11s/it]
                                                          
{'loss': 0.5994, 'learning_rate': 4.42159775643558e-06, 'epoch': 11.3}

 94%|█████████▍| 26447/28080 [52:14:54<3:13:27,  7.11s/it]
 94%|█████████▍| 26448/28080 [52:15:01<3:13:41,  7.12s/it]
                                                          
{'loss': 0.6101, 'learning_rate': 4.416200103155715e-06, 'epoch': 11.3}

 94%|█████████▍| 26448/28080 [52:15:01<3:13:41,  7.12s/it]
 94%|█████████▍| 26449/28080 [52:15:09<3:13:35,  7.12s/it]
                                                          
{'loss': 0.601, 'learning_rate': 4.410805717114968e-06, 'epoch': 11.3}

 94%|█████████▍| 26449/28080 [52:15:09<3:13:35,  7.12s/it]
 94%|█████████▍| 26450/28080 [52:15:16<3:13:51,  7.14s/it]
                                                          
{'loss': 0.5717, 'learning_rate': 4.40541459838506e-06, 'epoch': 11.3}

 94%|█████████▍| 26450/28080 [52:15:16<3:13:51,  7.14s/it]
 94%|█████████▍| 26451/28080 [52:15:23<3:13:48,  7.14s/it]
                                                          
{'loss': 0.5761, 'learning_rate': 4.400026747037767e-06, 'epoch': 11.3}

 94%|█████████▍| 26451/28080 [52:15:23<3:13:48,  7.14s/it]
 94%|█████████▍| 26452/28080 [52:15:30<3:13:39,  7.14s/it]
                                                          
{'loss': 0.5956, 'learning_rate': 4.394642163144752e-06, 'epoch': 11.3}

 94%|█████████▍| 26452/28080 [52:15:30<3:13:39,  7.14s/it]
 94%|█████████▍| 26453/28080 [52:15:37<3:13:06,  7.12s/it]
                                                          
{'loss': 0.6006, 'learning_rate': 4.389260846777626e-06, 'epoch': 11.3}

 94%|█████████▍| 26453/28080 [52:15:37<3:13:06,  7.12s/it]
 94%|█████████▍| 26454/28080 [52:15:44<3:13:19,  7.13s/it]
                                                          
{'loss': 0.6051, 'learning_rate': 4.383882798008027e-06, 'epoch': 11.3}

 94%|█████████▍| 26454/28080 [52:15:44<3:13:19,  7.13s/it]
 94%|█████████▍| 26455/28080 [52:15:51<3:13:39,  7.15s/it]
                                                          
{'loss': 0.6245, 'learning_rate': 4.378508016907451e-06, 'epoch': 11.3}

 94%|█████████▍| 26455/28080 [52:15:51<3:13:39,  7.15s/it]
 94%|█████████▍| 26456/28080 [52:15:59<3:13:49,  7.16s/it]
                                                          
{'loss': 0.6147, 'learning_rate': 4.373136503547453e-06, 'epoch': 11.3}

 94%|█████████▍| 26456/28080 [52:15:59<3:13:49,  7.16s/it]
 94%|█████████▍| 26457/28080 [52:16:06<3:13:04,  7.14s/it]
                                                          
{'loss': 0.6034, 'learning_rate': 4.367768257999449e-06, 'epoch': 11.3}

 94%|█████████▍| 26457/28080 [52:16:06<3:13:04,  7.14s/it]
 94%|█████████▍| 26458/28080 [52:16:13<3:13:02,  7.14s/it]
                                                          
{'loss': 0.5763, 'learning_rate': 4.362403280334909e-06, 'epoch': 11.3}

 94%|█████████▍| 26458/28080 [52:16:13<3:13:02,  7.14s/it]
 94%|█████████▍| 26459/28080 [52:16:20<3:12:40,  7.13s/it]
                                                          
{'loss': 0.6041, 'learning_rate': 4.357041570625164e-06, 'epoch': 11.3}

 94%|█████████▍| 26459/28080 [52:16:20<3:12:40,  7.13s/it]
 94%|█████████▍| 26460/28080 [52:16:27<3:11:24,  7.09s/it]
                                                          
{'loss': 0.5958, 'learning_rate': 4.3516831289416025e-06, 'epoch': 11.3}

 94%|█████████▍| 26460/28080 [52:16:27<3:11:24,  7.09s/it]
 94%|█████████▍| 26461/28080 [52:16:34<3:12:04,  7.12s/it]
                                                          
{'loss': 0.5793, 'learning_rate': 4.346327955355445e-06, 'epoch': 11.3}

 94%|█████████▍| 26461/28080 [52:16:34<3:12:04,  7.12s/it]
 94%|█████████▍| 26462/28080 [52:16:41<3:11:09,  7.09s/it]
                                                          
{'loss': 0.5889, 'learning_rate': 4.340976049937967e-06, 'epoch': 11.3}

 94%|█████████▍| 26462/28080 [52:16:41<3:11:09,  7.09s/it]
 94%|█████████▍| 26463/28080 [52:16:48<3:10:43,  7.08s/it]
                                                          
{'loss': 0.6101, 'learning_rate': 4.335627412760362e-06, 'epoch': 11.3}

 94%|█████████▍| 26463/28080 [52:16:48<3:10:43,  7.08s/it]
 94%|█████████▍| 26464/28080 [52:16:55<3:10:56,  7.09s/it]
                                                          
{'loss': 0.5955, 'learning_rate': 4.330282043893824e-06, 'epoch': 11.31}

 94%|█████████▍| 26464/28080 [52:16:55<3:10:56,  7.09s/it]
 94%|█████████▍| 26465/28080 [52:17:02<3:10:59,  7.10s/it]
                                                          
{'loss': 0.597, 'learning_rate': 4.324939943409434e-06, 'epoch': 11.31}

 94%|█████████▍| 26465/28080 [52:17:02<3:10:59,  7.10s/it]
 94%|█████████▍| 26466/28080 [52:17:10<3:11:23,  7.11s/it]
                                                          
{'loss': 0.5847, 'learning_rate': 4.319601111378246e-06, 'epoch': 11.31}

 94%|█████████▍| 26466/28080 [52:17:10<3:11:23,  7.11s/it]
 94%|█████████▍| 26467/28080 [52:17:17<3:10:11,  7.07s/it]
                                                          
{'loss': 0.6195, 'learning_rate': 4.314265547871316e-06, 'epoch': 11.31}

 94%|█████████▍| 26467/28080 [52:17:17<3:10:11,  7.07s/it]
 94%|█████████▍| 26468/28080 [52:17:24<3:10:13,  7.08s/it]
                                                          
{'loss': 0.6069, 'learning_rate': 4.30893325295964e-06, 'epoch': 11.31}

 94%|█████████▍| 26468/28080 [52:17:24<3:10:13,  7.08s/it]
 94%|█████████▍| 26469/28080 [52:17:31<3:09:57,  7.08s/it]
                                                          
{'loss': 0.6025, 'learning_rate': 4.3036042267141365e-06, 'epoch': 11.31}

 94%|█████████▍| 26469/28080 [52:17:31<3:09:57,  7.08s/it]
 94%|█████████▍| 26470/28080 [52:17:38<3:10:20,  7.09s/it]
                                                          
{'loss': 0.5852, 'learning_rate': 4.298278469205719e-06, 'epoch': 11.31}

 94%|█████████▍| 26470/28080 [52:17:38<3:10:20,  7.09s/it]
 94%|█████████▍| 26471/28080 [52:17:45<3:09:59,  7.08s/it]
                                                          
{'loss': 0.6039, 'learning_rate': 4.292955980505192e-06, 'epoch': 11.31}

 94%|█████████▍| 26471/28080 [52:17:45<3:09:59,  7.08s/it]
 94%|█████████▍| 26472/28080 [52:17:52<3:09:34,  7.07s/it]
                                                          
{'loss': 0.5924, 'learning_rate': 4.287636760683444e-06, 'epoch': 11.31}

 94%|█████████▍| 26472/28080 [52:17:52<3:09:34,  7.07s/it]
 94%|█████████▍| 26473/28080 [52:17:59<3:09:30,  7.08s/it]
                                                          
{'loss': 0.6278, 'learning_rate': 4.282320809811169e-06, 'epoch': 11.31}

 94%|█████████▍| 26473/28080 [52:17:59<3:09:30,  7.08s/it]
 94%|█████████▍| 26474/28080 [52:18:06<3:09:43,  7.09s/it]
                                                          
{'loss': 0.5981, 'learning_rate': 4.27700812795917e-06, 'epoch': 11.31}

 94%|█████████▍| 26474/28080 [52:18:06<3:09:43,  7.09s/it]
 94%|█████████▍| 26475/28080 [52:18:13<3:10:03,  7.10s/it]
                                                          
{'loss': 0.6077, 'learning_rate': 4.27169871519803e-06, 'epoch': 11.31}

 94%|█████████▍| 26475/28080 [52:18:13<3:10:03,  7.10s/it]
 94%|█████████▍| 26476/28080 [52:18:20<3:09:31,  7.09s/it]
                                                          
{'loss': 0.596, 'learning_rate': 4.266392571598471e-06, 'epoch': 11.31}

 94%|█████████▍| 26476/28080 [52:18:20<3:09:31,  7.09s/it]
 94%|█████████▍| 26477/28080 [52:18:28<3:09:26,  7.09s/it]
                                                          
{'loss': 0.5974, 'learning_rate': 4.261089697231019e-06, 'epoch': 11.31}

 94%|█████████▍| 26477/28080 [52:18:28<3:09:26,  7.09s/it]
 94%|█████████▍| 26478/28080 [52:18:35<3:09:31,  7.10s/it]
                                                          
{'loss': 0.5899, 'learning_rate': 4.2557900921662565e-06, 'epoch': 11.31}

 94%|█████████▍| 26478/28080 [52:18:35<3:09:31,  7.10s/it]
 94%|█████████▍| 26479/28080 [52:18:42<3:09:22,  7.10s/it]
                                                          
{'loss': 0.6051, 'learning_rate': 4.25049375647471e-06, 'epoch': 11.31}

 94%|█████████▍| 26479/28080 [52:18:42<3:09:22,  7.10s/it]
 94%|█████████▍| 26480/28080 [52:18:49<3:09:12,  7.10s/it]
                                                          
{'loss': 0.6023, 'learning_rate': 4.245200690226825e-06, 'epoch': 11.31}

 94%|█████████▍| 26480/28080 [52:18:49<3:09:12,  7.10s/it]
 94%|█████████▍| 26481/28080 [52:18:56<3:08:51,  7.09s/it]
                                                          
{'loss': 0.6037, 'learning_rate': 4.23991089349296e-06, 'epoch': 11.31}

 94%|█████████▍| 26481/28080 [52:18:56<3:08:51,  7.09s/it]
 94%|█████████▍| 26482/28080 [52:19:03<3:08:40,  7.08s/it]
                                                          
{'loss': 0.5933, 'learning_rate': 4.234624366343587e-06, 'epoch': 11.31}

 94%|█████████▍| 26482/28080 [52:19:03<3:08:40,  7.08s/it]
 94%|█████████▍| 26483/28080 [52:19:10<3:08:49,  7.09s/it]
                                                          
{'loss': 0.5851, 'learning_rate': 4.229341108849011e-06, 'epoch': 11.31}

 94%|█████████▍| 26483/28080 [52:19:10<3:08:49,  7.09s/it]
 94%|█████████▍| 26484/28080 [52:19:17<3:09:26,  7.12s/it]
                                                          
{'loss': 0.5896, 'learning_rate': 4.224061121079481e-06, 'epoch': 11.31}

 94%|█████████▍| 26484/28080 [52:19:17<3:09:26,  7.12s/it]
 94%|█████████▍| 26485/28080 [52:19:24<3:09:18,  7.12s/it]
                                                          
{'loss': 0.595, 'learning_rate': 4.218784403105247e-06, 'epoch': 11.31}

 94%|█████████▍| 26485/28080 [52:19:24<3:09:18,  7.12s/it]
 94%|█████████▍| 26486/28080 [52:19:31<3:09:12,  7.12s/it]
                                                          
{'loss': 0.6119, 'learning_rate': 4.21351095499653e-06, 'epoch': 11.31}

 94%|█████████▍| 26486/28080 [52:19:31<3:09:12,  7.12s/it]
 94%|█████████▍| 26487/28080 [52:19:39<3:08:52,  7.11s/it]
                                                          
{'loss': 0.5896, 'learning_rate': 4.208240776823524e-06, 'epoch': 11.31}

 94%|█████████▍| 26487/28080 [52:19:39<3:08:52,  7.11s/it]
 94%|█████████▍| 26488/28080 [52:19:46<3:08:54,  7.12s/it]
                                                          
{'loss': 0.5989, 'learning_rate': 4.202973868656284e-06, 'epoch': 11.32}

 94%|█████████▍| 26488/28080 [52:19:46<3:08:54,  7.12s/it]
 94%|█████████▍| 26489/28080 [52:19:53<3:08:52,  7.12s/it]
                                                          
{'loss': 0.6147, 'learning_rate': 4.197710230564894e-06, 'epoch': 11.32}

 94%|█████████▍| 26489/28080 [52:19:53<3:08:52,  7.12s/it]
 94%|█████████▍| 26490/28080 [52:20:00<3:08:38,  7.12s/it]
                                                          
{'loss': 0.62, 'learning_rate': 4.19244986261938e-06, 'epoch': 11.32}

 94%|█████████▍| 26490/28080 [52:20:00<3:08:38,  7.12s/it]
 94%|█████████▍| 26491/28080 [52:20:07<3:08:04,  7.10s/it]
                                                          
{'loss': 0.5878, 'learning_rate': 4.187192764889769e-06, 'epoch': 11.32}

 94%|█████████▍| 26491/28080 [52:20:07<3:08:04,  7.10s/it]
 94%|█████████▍| 26492/28080 [52:20:14<3:07:57,  7.10s/it]
                                                          
{'loss': 0.5906, 'learning_rate': 4.181938937445923e-06, 'epoch': 11.32}

 94%|█████████▍| 26492/28080 [52:20:14<3:07:57,  7.10s/it]
 94%|█████████▍| 26493/28080 [52:20:21<3:07:55,  7.11s/it]
                                                          
{'loss': 0.6011, 'learning_rate': 4.17668838035784e-06, 'epoch': 11.32}

 94%|█████████▍| 26493/28080 [52:20:21<3:07:55,  7.11s/it]
 94%|█████████▍| 26494/28080 [52:20:28<3:08:06,  7.12s/it]
                                                          
{'loss': 0.6021, 'learning_rate': 4.171441093695272e-06, 'epoch': 11.32}

 94%|█████████▍| 26494/28080 [52:20:28<3:08:06,  7.12s/it]
 94%|█████████▍| 26495/28080 [52:20:35<3:07:50,  7.11s/it]
                                                          
{'loss': 0.6143, 'learning_rate': 4.166197077528078e-06, 'epoch': 11.32}

 94%|█████████▍| 26495/28080 [52:20:35<3:07:50,  7.11s/it]
 94%|█████████▍| 26496/28080 [52:20:43<3:07:45,  7.11s/it]
                                                          
{'loss': 0.6019, 'learning_rate': 4.1609563319260354e-06, 'epoch': 11.32}

 94%|█████████▍| 26496/28080 [52:20:43<3:07:45,  7.11s/it]
 94%|█████████▍| 26497/28080 [52:20:50<3:08:31,  7.15s/it]
                                                          
{'loss': 0.6147, 'learning_rate': 4.15571885695884e-06, 'epoch': 11.32}

 94%|█████████▍| 26497/28080 [52:20:50<3:08:31,  7.15s/it]
 94%|█████████▍| 26498/28080 [52:20:57<3:08:37,  7.15s/it]
                                                          
{'loss': 0.6041, 'learning_rate': 4.150484652696185e-06, 'epoch': 11.32}

 94%|█████████▍| 26498/28080 [52:20:57<3:08:37,  7.15s/it]
 94%|█████████▍| 26499/28080 [52:21:04<3:08:27,  7.15s/it]
                                                          
{'loss': 0.5997, 'learning_rate': 4.145253719207709e-06, 'epoch': 11.32}

 94%|█████████▍| 26499/28080 [52:21:04<3:08:27,  7.15s/it]
 94%|█████████▍| 26500/28080 [52:21:11<3:07:52,  7.13s/it]
                                                          
{'loss': 0.6154, 'learning_rate': 4.1400260565629676e-06, 'epoch': 11.32}

 94%|█████████▍| 26500/28080 [52:21:11<3:07:52,  7.13s/it]
 94%|█████████▍| 26501/28080 [52:21:18<3:06:58,  7.10s/it]
                                                          
{'loss': 0.6132, 'learning_rate': 4.134801664831572e-06, 'epoch': 11.32}

 94%|█████████▍| 26501/28080 [52:21:18<3:06:58,  7.10s/it]
 94%|█████████▍| 26502/28080 [52:21:25<3:06:29,  7.09s/it]
                                                          
{'loss': 0.6322, 'learning_rate': 4.129580544082995e-06, 'epoch': 11.32}

 94%|█████████▍| 26502/28080 [52:21:25<3:06:29,  7.09s/it]
 94%|█████████▍| 26503/28080 [52:21:32<3:06:49,  7.11s/it]
                                                          
{'loss': 0.5984, 'learning_rate': 4.124362694386707e-06, 'epoch': 11.32}

 94%|█████████▍| 26503/28080 [52:21:32<3:06:49,  7.11s/it]
 94%|█████████▍| 26504/28080 [52:21:40<3:06:35,  7.10s/it]
                                                          
{'loss': 0.5917, 'learning_rate': 4.119148115812071e-06, 'epoch': 11.32}

 94%|█████████▍| 26504/28080 [52:21:40<3:06:35,  7.10s/it]
 94%|█████████▍| 26505/28080 [52:21:47<3:06:44,  7.11s/it]
                                                          
{'loss': 0.5971, 'learning_rate': 4.113936808428559e-06, 'epoch': 11.32}

 94%|█████████▍| 26505/28080 [52:21:47<3:06:44,  7.11s/it]
 94%|█████████▍| 26506/28080 [52:21:54<3:07:15,  7.14s/it]
                                                          
{'loss': 0.5879, 'learning_rate': 4.1087287723053926e-06, 'epoch': 11.32}

 94%|█████████▍| 26506/28080 [52:21:54<3:07:15,  7.14s/it]
 94%|█████████▍| 26507/28080 [52:22:01<3:07:19,  7.15s/it]
                                                          
{'loss': 0.587, 'learning_rate': 4.103524007511988e-06, 'epoch': 11.32}

 94%|█████████▍| 26507/28080 [52:22:01<3:07:19,  7.15s/it]
 94%|█████████▍| 26508/28080 [52:22:08<3:07:18,  7.15s/it]
                                                          
{'loss': 0.6084, 'learning_rate': 4.098322514117486e-06, 'epoch': 11.32}

 94%|█████████▍| 26508/28080 [52:22:08<3:07:18,  7.15s/it]
 94%|█████████▍| 26509/28080 [52:22:15<3:06:48,  7.13s/it]
                                                          
{'loss': 0.6085, 'learning_rate': 4.093124292191108e-06, 'epoch': 11.32}

 94%|█████████▍| 26509/28080 [52:22:15<3:06:48,  7.13s/it]
 94%|█████████▍| 26510/28080 [52:22:22<3:06:08,  7.11s/it]
                                                          
{'loss': 0.5915, 'learning_rate': 4.0879293418020495e-06, 'epoch': 11.32}

 94%|█████████▍| 26510/28080 [52:22:22<3:06:08,  7.11s/it]
 94%|█████████▍| 26511/28080 [52:22:30<3:06:26,  7.13s/it]
                                                          
{'loss': 0.6057, 'learning_rate': 4.082737663019365e-06, 'epoch': 11.33}

 94%|█████████▍| 26511/28080 [52:22:30<3:06:26,  7.13s/it]
 94%|█████████▍| 26512/28080 [52:22:37<3:06:10,  7.12s/it]
                                                          
{'loss': 0.6024, 'learning_rate': 4.077549255912194e-06, 'epoch': 11.33}

 94%|█████████▍| 26512/28080 [52:22:37<3:06:10,  7.12s/it]
 94%|█████████▍| 26513/28080 [52:22:44<3:05:43,  7.11s/it]
                                                          
{'loss': 0.5971, 'learning_rate': 4.07236412054951e-06, 'epoch': 11.33}

 94%|█████████▍| 26513/28080 [52:22:44<3:05:43,  7.11s/it]
 94%|█████████▍| 26514/28080 [52:22:51<3:06:07,  7.13s/it]
                                                          
{'loss': 0.5917, 'learning_rate': 4.067182257000313e-06, 'epoch': 11.33}

 94%|█████████▍| 26514/28080 [52:22:51<3:06:07,  7.13s/it]
 94%|█████████▍| 26515/28080 [52:22:58<3:05:34,  7.11s/it]
                                                          
{'loss': 0.5905, 'learning_rate': 4.062003665333519e-06, 'epoch': 11.33}

 94%|█████████▍| 26515/28080 [52:22:58<3:05:34,  7.11s/it]
 94%|█████████▍| 26516/28080 [52:23:05<3:04:53,  7.09s/it]
                                                          
{'loss': 0.5949, 'learning_rate': 4.0568283456180745e-06, 'epoch': 11.33}

 94%|█████████▍| 26516/28080 [52:23:05<3:04:53,  7.09s/it]
 94%|█████████▍| 26517/28080 [52:23:12<3:05:20,  7.11s/it]
                                                          
{'loss': 0.6037, 'learning_rate': 4.051656297922813e-06, 'epoch': 11.33}

 94%|█████████▍| 26517/28080 [52:23:12<3:05:20,  7.11s/it]
 94%|█████████▍| 26518/28080 [52:23:19<3:05:00,  7.11s/it]
                                                          
{'loss': 0.603, 'learning_rate': 4.046487522316511e-06, 'epoch': 11.33}

 94%|█████████▍| 26518/28080 [52:23:19<3:05:00,  7.11s/it]
 94%|█████████▍| 26519/28080 [52:23:26<3:04:14,  7.08s/it]
                                                          
{'loss': 0.5919, 'learning_rate': 4.0413220188679485e-06, 'epoch': 11.33}

 94%|█████████▍| 26519/28080 [52:23:26<3:04:14,  7.08s/it]
 94%|█████████▍| 26520/28080 [52:23:33<3:04:24,  7.09s/it]
                                                          
{'loss': 0.5682, 'learning_rate': 4.0361597876458765e-06, 'epoch': 11.33}

 94%|█████████▍| 26520/28080 [52:23:33<3:04:24,  7.09s/it]
 94%|█████████▍| 26521/28080 [52:23:41<3:04:49,  7.11s/it]
                                                          
{'loss': 0.5986, 'learning_rate': 4.031000828718906e-06, 'epoch': 11.33}

 94%|█████████▍| 26521/28080 [52:23:41<3:04:49,  7.11s/it]
 94%|█████████▍| 26522/28080 [52:23:48<3:04:48,  7.12s/it]
                                                          
{'loss': 0.6004, 'learning_rate': 4.025845142155787e-06, 'epoch': 11.33}

 94%|█████████▍| 26522/28080 [52:23:48<3:04:48,  7.12s/it]
 94%|█████████▍| 26523/28080 [52:23:55<3:04:40,  7.12s/it]
                                                          
{'loss': 0.6047, 'learning_rate': 4.020692728024994e-06, 'epoch': 11.33}

 94%|█████████▍| 26523/28080 [52:23:55<3:04:40,  7.12s/it]
 94%|█████████▍| 26524/28080 [52:24:02<3:04:19,  7.11s/it]
                                                          
{'loss': 0.6148, 'learning_rate': 4.015543586395137e-06, 'epoch': 11.33}

 94%|█████████▍| 26524/28080 [52:24:02<3:04:19,  7.11s/it]
 94%|█████████▍| 26525/28080 [52:24:09<3:05:07,  7.14s/it]
                                                          
{'loss': 0.5925, 'learning_rate': 4.0103977173346905e-06, 'epoch': 11.33}

 94%|█████████▍| 26525/28080 [52:24:09<3:05:07,  7.14s/it]
 94%|█████████▍| 26526/28080 [52:24:16<3:04:15,  7.11s/it]
                                                          
{'loss': 0.5925, 'learning_rate': 4.005255120912155e-06, 'epoch': 11.33}

 94%|█████████▍| 26526/28080 [52:24:16<3:04:15,  7.11s/it]
 94%|█████████▍| 26527/28080 [52:24:23<3:03:17,  7.08s/it]
                                                          
{'loss': 0.581, 'learning_rate': 4.000115797195919e-06, 'epoch': 11.33}

 94%|█████████▍| 26527/28080 [52:24:23<3:03:17,  7.08s/it]
 94%|█████████▍| 26528/28080 [52:24:30<3:02:41,  7.06s/it]
                                                          
{'loss': 0.6034, 'learning_rate': 3.994979746254346e-06, 'epoch': 11.33}

 94%|█████████▍| 26528/28080 [52:24:30<3:02:41,  7.06s/it]
 94%|█████████▍| 26529/28080 [52:24:37<3:02:33,  7.06s/it]
                                                          
{'loss': 0.5881, 'learning_rate': 3.989846968155769e-06, 'epoch': 11.33}

 94%|█████████▍| 26529/28080 [52:24:37<3:02:33,  7.06s/it]
 94%|█████████▍| 26530/28080 [52:24:44<3:03:07,  7.09s/it]
                                                          
{'loss': 0.5842, 'learning_rate': 3.984717462968496e-06, 'epoch': 11.33}

 94%|█████████▍| 26530/28080 [52:24:44<3:03:07,  7.09s/it]
 94%|█████████▍| 26531/28080 [52:24:52<3:04:04,  7.13s/it]
                                                          
{'loss': 0.6052, 'learning_rate': 3.979591230760749e-06, 'epoch': 11.33}

 94%|█████████▍| 26531/28080 [52:24:52<3:04:04,  7.13s/it]
 94%|█████████▍| 26532/28080 [52:24:59<3:04:12,  7.14s/it]
                                                          
{'loss': 0.5833, 'learning_rate': 3.974468271600751e-06, 'epoch': 11.33}

 94%|█████████▍| 26532/28080 [52:24:59<3:04:12,  7.14s/it]
 94%|█████████▍| 26533/28080 [52:25:06<3:04:43,  7.16s/it]
                                                          
{'loss': 0.5589, 'learning_rate': 3.969348585556643e-06, 'epoch': 11.33}

 94%|█████████▍| 26533/28080 [52:25:06<3:04:43,  7.16s/it]
 94%|█████████▍| 26534/28080 [52:25:13<3:04:44,  7.17s/it]
                                                          
{'loss': 0.6051, 'learning_rate': 3.964232172696508e-06, 'epoch': 11.34}

 94%|█████████▍| 26534/28080 [52:25:13<3:04:44,  7.17s/it]
 94%|█████████▍| 26535/28080 [52:25:20<3:04:18,  7.16s/it]
                                                          
{'loss': 0.5971, 'learning_rate': 3.95911903308846e-06, 'epoch': 11.34}

 94%|█████████▍| 26535/28080 [52:25:20<3:04:18,  7.16s/it]
 95%|█████████▍| 26536/28080 [52:25:27<3:03:44,  7.14s/it]
                                                          
{'loss': 0.6131, 'learning_rate': 3.954009166800526e-06, 'epoch': 11.34}

 95%|█████████▍| 26536/28080 [52:25:27<3:03:44,  7.14s/it]
 95%|█████████▍| 26537/28080 [52:25:35<3:03:02,  7.12s/it]
                                                          
{'loss': 0.6161, 'learning_rate': 3.948902573900654e-06, 'epoch': 11.34}

 95%|█████████▍| 26537/28080 [52:25:35<3:03:02,  7.12s/it]
 95%|█████████▍| 26538/28080 [52:25:42<3:03:14,  7.13s/it]
                                                          
{'loss': 0.5884, 'learning_rate': 3.9437992544567865e-06, 'epoch': 11.34}

 95%|█████████▍| 26538/28080 [52:25:42<3:03:14,  7.13s/it]
 95%|█████████▍| 26539/28080 [52:25:49<3:03:10,  7.13s/it]
                                                          
{'loss': 0.6262, 'learning_rate': 3.938699208536844e-06, 'epoch': 11.34}

 95%|█████████▍| 26539/28080 [52:25:49<3:03:10,  7.13s/it]
 95%|█████████▍| 26540/28080 [52:25:56<3:02:31,  7.11s/it]
                                                          
{'loss': 0.6079, 'learning_rate': 3.933602436208633e-06, 'epoch': 11.34}

 95%|█████████▍| 26540/28080 [52:25:56<3:02:31,  7.11s/it]
 95%|█████████▍| 26541/28080 [52:26:03<3:02:17,  7.11s/it]
                                                          
{'loss': 0.6023, 'learning_rate': 3.928508937540015e-06, 'epoch': 11.34}

 95%|█████████▍| 26541/28080 [52:26:03<3:02:17,  7.11s/it]
 95%|█████████▍| 26542/28080 [52:26:10<3:01:46,  7.09s/it]
                                                          
{'loss': 0.6122, 'learning_rate': 3.923418712598714e-06, 'epoch': 11.34}

 95%|█████████▍| 26542/28080 [52:26:10<3:01:46,  7.09s/it]
 95%|█████████▍| 26543/28080 [52:26:17<3:01:59,  7.10s/it]
                                                          
{'loss': 0.5838, 'learning_rate': 3.918331761452481e-06, 'epoch': 11.34}

 95%|█████████▍| 26543/28080 [52:26:17<3:01:59,  7.10s/it]
 95%|█████████▍| 26544/28080 [52:26:24<3:01:32,  7.09s/it]
                                                          
{'loss': 0.6071, 'learning_rate': 3.913248084168958e-06, 'epoch': 11.34}

 95%|█████████▍| 26544/28080 [52:26:24<3:01:32,  7.09s/it]
 95%|█████████▍| 26545/28080 [52:26:31<3:01:28,  7.09s/it]
                                                          
{'loss': 0.6102, 'learning_rate': 3.90816768081581e-06, 'epoch': 11.34}

 95%|█████████▍| 26545/28080 [52:26:31<3:01:28,  7.09s/it]
 95%|█████████▍| 26546/28080 [52:26:39<3:02:16,  7.13s/it]
                                                          
{'loss': 0.5933, 'learning_rate': 3.903090551460597e-06, 'epoch': 11.34}

 95%|█████████▍| 26546/28080 [52:26:39<3:02:16,  7.13s/it]
 95%|█████████▍| 26547/28080 [52:26:46<3:02:24,  7.14s/it]
                                                          
{'loss': 0.5999, 'learning_rate': 3.898016696170903e-06, 'epoch': 11.34}

 95%|█████████▍| 26547/28080 [52:26:46<3:02:24,  7.14s/it]
 95%|█████████▍| 26548/28080 [52:26:53<3:02:06,  7.13s/it]
                                                          
{'loss': 0.6071, 'learning_rate': 3.8929461150141735e-06, 'epoch': 11.34}

 95%|█████████▍| 26548/28080 [52:26:53<3:02:06,  7.13s/it]
 95%|█████████▍| 26549/28080 [52:27:00<3:01:01,  7.09s/it]
                                                          
{'loss': 0.6232, 'learning_rate': 3.88787880805791e-06, 'epoch': 11.34}

 95%|█████████▍| 26549/28080 [52:27:00<3:01:01,  7.09s/it]
 95%|█████████▍| 26550/28080 [52:27:07<3:01:15,  7.11s/it]
                                                          
{'loss': 0.6164, 'learning_rate': 3.882814775369559e-06, 'epoch': 11.34}

 95%|█████████▍| 26550/28080 [52:27:07<3:01:15,  7.11s/it]
 95%|█████████▍| 26551/28080 [52:27:14<3:00:56,  7.10s/it]
                                                          
{'loss': 0.6065, 'learning_rate': 3.877754017016427e-06, 'epoch': 11.34}

 95%|█████████▍| 26551/28080 [52:27:14<3:00:56,  7.10s/it]
 95%|█████████▍| 26552/28080 [52:27:21<3:01:10,  7.11s/it]
                                                          
{'loss': 0.6146, 'learning_rate': 3.87269653306585e-06, 'epoch': 11.34}

 95%|█████████▍| 26552/28080 [52:27:21<3:01:10,  7.11s/it]
 95%|█████████▍| 26553/28080 [52:27:28<3:00:42,  7.10s/it]
                                                          
{'loss': 0.621, 'learning_rate': 3.867642323585136e-06, 'epoch': 11.34}

 95%|█████████▍| 26553/28080 [52:27:28<3:00:42,  7.10s/it]
 95%|█████████▍| 26554/28080 [52:27:35<3:00:53,  7.11s/it]
                                                          
{'loss': 0.5993, 'learning_rate': 3.862591388641506e-06, 'epoch': 11.34}

 95%|█████████▍| 26554/28080 [52:27:35<3:00:53,  7.11s/it]
 95%|█████████▍| 26555/28080 [52:27:43<3:01:58,  7.16s/it]
                                                          
{'loss': 0.6092, 'learning_rate': 3.857543728302243e-06, 'epoch': 11.34}

 95%|█████████▍| 26555/28080 [52:27:43<3:01:58,  7.16s/it]
 95%|█████████▍| 26556/28080 [52:27:50<3:01:15,  7.14s/it]
                                                          
{'loss': 0.5957, 'learning_rate': 3.852499342634347e-06, 'epoch': 11.34}

 95%|█████████▍| 26556/28080 [52:27:50<3:01:15,  7.14s/it]
 95%|█████████▍| 26557/28080 [52:27:57<3:01:30,  7.15s/it]
                                                          
{'loss': 0.5794, 'learning_rate': 3.847458231705042e-06, 'epoch': 11.34}

 95%|█████████▍| 26557/28080 [52:27:57<3:01:30,  7.15s/it]
 95%|█████████▍| 26558/28080 [52:28:04<3:00:54,  7.13s/it]
                                                          
{'loss': 0.6004, 'learning_rate': 3.842420395581387e-06, 'epoch': 11.35}

 95%|█████████▍| 26558/28080 [52:28:04<3:00:54,  7.13s/it]
 95%|█████████▍| 26559/28080 [52:28:11<3:01:05,  7.14s/it]
                                                          
{'loss': 0.6113, 'learning_rate': 3.837385834330354e-06, 'epoch': 11.35}

 95%|█████████▍| 26559/28080 [52:28:11<3:01:05,  7.14s/it]
 95%|█████████▍| 26560/28080 [52:28:18<3:01:04,  7.15s/it]
                                                          
{'loss': 0.5845, 'learning_rate': 3.832354548018946e-06, 'epoch': 11.35}

 95%|█████████▍| 26560/28080 [52:28:18<3:01:04,  7.15s/it]
 95%|█████████▍| 26561/28080 [52:28:26<3:00:59,  7.15s/it]
                                                          
{'loss': 0.606, 'learning_rate': 3.827326536714137e-06, 'epoch': 11.35}

 95%|█████████▍| 26561/28080 [52:28:26<3:00:59,  7.15s/it]
 95%|█████████▍| 26562/28080 [52:28:33<3:00:37,  7.14s/it]
                                                          
{'loss': 0.6084, 'learning_rate': 3.8223018004827634e-06, 'epoch': 11.35}

 95%|█████████▍| 26562/28080 [52:28:33<3:00:37,  7.14s/it]
 95%|█████████▍| 26563/28080 [52:28:40<3:00:08,  7.12s/it]
                                                          
{'loss': 0.6009, 'learning_rate': 3.817280339391687e-06, 'epoch': 11.35}

 95%|█████████▍| 26563/28080 [52:28:40<3:00:08,  7.12s/it]
 95%|█████████▍| 26564/28080 [52:28:47<3:00:22,  7.14s/it]
                                                          
{'loss': 0.5773, 'learning_rate': 3.812262153507745e-06, 'epoch': 11.35}

 95%|█████████▍| 26564/28080 [52:28:47<3:00:22,  7.14s/it]
 95%|█████████▍| 26565/28080 [52:28:54<3:00:21,  7.14s/it]
                                                          
{'loss': 0.5707, 'learning_rate': 3.8072472428976603e-06, 'epoch': 11.35}

 95%|█████████▍| 26565/28080 [52:28:54<3:00:21,  7.14s/it]
 95%|█████████▍| 26566/28080 [52:29:01<3:00:43,  7.16s/it]
                                                          
{'loss': 0.5885, 'learning_rate': 3.802235607628185e-06, 'epoch': 11.35}

 95%|█████████▍| 26566/28080 [52:29:01<3:00:43,  7.16s/it]
 95%|█████████▍| 26567/28080 [52:29:08<3:00:02,  7.14s/it]
                                                          
{'loss': 0.6112, 'learning_rate': 3.797227247765961e-06, 'epoch': 11.35}

 95%|█████████▍| 26567/28080 [52:29:08<3:00:02,  7.14s/it]
 95%|█████████▍| 26568/28080 [52:29:15<2:59:24,  7.12s/it]
                                                          
{'loss': 0.5977, 'learning_rate': 3.792222163377629e-06, 'epoch': 11.35}

 95%|█████████▍| 26568/28080 [52:29:15<2:59:24,  7.12s/it]
 95%|█████████▍| 26569/28080 [52:29:23<2:59:05,  7.11s/it]
                                                          
{'loss': 0.5995, 'learning_rate': 3.7872203545298024e-06, 'epoch': 11.35}

 95%|█████████▍| 26569/28080 [52:29:23<2:59:05,  7.11s/it]
 95%|█████████▍| 26570/28080 [52:29:30<2:59:15,  7.12s/it]
                                                          
{'loss': 0.6176, 'learning_rate': 3.7822218212890113e-06, 'epoch': 11.35}

 95%|█████████▍| 26570/28080 [52:29:30<2:59:15,  7.12s/it]
 95%|█████████▍| 26571/28080 [52:29:37<2:59:34,  7.14s/it]
                                                          
{'loss': 0.6029, 'learning_rate': 3.777226563721703e-06, 'epoch': 11.35}

 95%|█████████▍| 26571/28080 [52:29:37<2:59:34,  7.14s/it]
 95%|█████████▍| 26572/28080 [52:29:44<2:59:51,  7.16s/it]
                                                          
{'loss': 0.591, 'learning_rate': 3.7722345818944346e-06, 'epoch': 11.35}

 95%|█████████▍| 26572/28080 [52:29:44<2:59:51,  7.16s/it]
 95%|█████████▍| 26573/28080 [52:29:51<3:00:05,  7.17s/it]
                                                          
{'loss': 0.5936, 'learning_rate': 3.767245875873515e-06, 'epoch': 11.35}

 95%|█████████▍| 26573/28080 [52:29:51<3:00:05,  7.17s/it]
 95%|█████████▍| 26574/28080 [52:29:58<2:59:56,  7.17s/it]
                                                          
{'loss': 0.609, 'learning_rate': 3.7622604457254184e-06, 'epoch': 11.35}

 95%|█████████▍| 26574/28080 [52:29:58<2:59:56,  7.17s/it]
 95%|█████████▍| 26575/28080 [52:30:06<2:59:37,  7.16s/it]
                                                          
{'loss': 0.5908, 'learning_rate': 3.757278291516397e-06, 'epoch': 11.35}

 95%|█████████▍| 26575/28080 [52:30:06<2:59:37,  7.16s/it]
 95%|█████████▍| 26576/28080 [52:30:13<2:58:29,  7.12s/it]
                                                          
{'loss': 0.6076, 'learning_rate': 3.7522994133127597e-06, 'epoch': 11.35}

 95%|█████████▍| 26576/28080 [52:30:13<2:58:29,  7.12s/it]
 95%|█████████▍| 26577/28080 [52:30:20<2:57:55,  7.10s/it]
                                                          
{'loss': 0.6007, 'learning_rate': 3.747323811180703e-06, 'epoch': 11.35}

 95%|█████████▍| 26577/28080 [52:30:20<2:57:55,  7.10s/it]
 95%|█████████▍| 26578/28080 [52:30:27<2:56:50,  7.06s/it]
                                                          
{'loss': 0.6123, 'learning_rate': 3.742351485186507e-06, 'epoch': 11.35}

 95%|█████████▍| 26578/28080 [52:30:27<2:56:50,  7.06s/it]
 95%|█████████▍| 26579/28080 [52:30:34<2:56:21,  7.05s/it]
                                                          
{'loss': 0.6101, 'learning_rate': 3.737382435396258e-06, 'epoch': 11.35}

 95%|█████████▍| 26579/28080 [52:30:34<2:56:21,  7.05s/it]
 95%|█████████▍| 26580/28080 [52:30:41<2:56:46,  7.07s/it]
                                                          
{'loss': 0.6075, 'learning_rate': 3.7324166618760703e-06, 'epoch': 11.35}

 95%|█████████▍| 26580/28080 [52:30:41<2:56:46,  7.07s/it]
 95%|█████████▍| 26581/28080 [52:30:48<2:57:45,  7.12s/it]
                                                          
{'loss': 0.5983, 'learning_rate': 3.7274541646920014e-06, 'epoch': 11.36}

 95%|█████████▍| 26581/28080 [52:30:48<2:57:45,  7.12s/it]
 95%|█████████▍| 26582/28080 [52:30:55<2:58:17,  7.14s/it]
                                                          
{'loss': 0.6106, 'learning_rate': 3.7224949439101372e-06, 'epoch': 11.36}

 95%|█████████▍| 26582/28080 [52:30:55<2:58:17,  7.14s/it]
 95%|█████████▍| 26583/28080 [52:31:02<2:58:32,  7.16s/it]
                                                          
{'loss': 0.5895, 'learning_rate': 3.7175389995963706e-06, 'epoch': 11.36}

 95%|█████████▍| 26583/28080 [52:31:02<2:58:32,  7.16s/it]
 95%|█████████▍| 26584/28080 [52:31:10<2:58:44,  7.17s/it]
                                                          
{'loss': 0.598, 'learning_rate': 3.712586331816703e-06, 'epoch': 11.36}

 95%|█████████▍| 26584/28080 [52:31:10<2:58:44,  7.17s/it]
 95%|█████████▍| 26585/28080 [52:31:17<2:58:09,  7.15s/it]
                                                          
{'loss': 0.6206, 'learning_rate': 3.7076369406369714e-06, 'epoch': 11.36}

 95%|█████████▍| 26585/28080 [52:31:17<2:58:09,  7.15s/it]
 95%|█████████▍| 26586/28080 [52:31:24<2:57:38,  7.13s/it]
                                                          
{'loss': 0.6004, 'learning_rate': 3.7026908261230397e-06, 'epoch': 11.36}

 95%|█████████▍| 26586/28080 [52:31:24<2:57:38,  7.13s/it]
 95%|█████████▍| 26587/28080 [52:31:31<2:56:41,  7.10s/it]
                                                          
{'loss': 0.6025, 'learning_rate': 3.6977479883407162e-06, 'epoch': 11.36}

 95%|█████████▍| 26587/28080 [52:31:31<2:56:41,  7.10s/it]
 95%|█████████▍| 26588/28080 [52:31:38<2:56:59,  7.12s/it]
                                                          
{'loss': 0.6059, 'learning_rate': 3.692808427355754e-06, 'epoch': 11.36}

 95%|█████████▍| 26588/28080 [52:31:38<2:56:59,  7.12s/it]
 95%|█████████▍| 26589/28080 [52:31:45<2:57:07,  7.13s/it]
                                                          
{'loss': 0.5997, 'learning_rate': 3.6878721432339333e-06, 'epoch': 11.36}

 95%|█████████▍| 26589/28080 [52:31:45<2:57:07,  7.13s/it]
 95%|█████████▍| 26590/28080 [52:31:52<2:57:19,  7.14s/it]
                                                          
{'loss': 0.596, 'learning_rate': 3.682939136040786e-06, 'epoch': 11.36}

 95%|█████████▍| 26590/28080 [52:31:52<2:57:19,  7.14s/it]
 95%|█████████▍| 26591/28080 [52:31:59<2:56:53,  7.13s/it]
                                                          
{'loss': 0.6156, 'learning_rate': 3.678009405842064e-06, 'epoch': 11.36}

 95%|█████████▍| 26591/28080 [52:31:59<2:56:53,  7.13s/it]
 95%|█████████▍| 26592/28080 [52:32:07<2:57:34,  7.16s/it]
                                                          
{'loss': 0.5974, 'learning_rate': 3.6730829527032995e-06, 'epoch': 11.36}

 95%|█████████▍| 26592/28080 [52:32:07<2:57:34,  7.16s/it]
 95%|█████████▍| 26593/28080 [52:32:14<2:57:35,  7.17s/it]
                                                          
{'loss': 0.5913, 'learning_rate': 3.66815977669005e-06, 'epoch': 11.36}

 95%|█████████▍| 26593/28080 [52:32:14<2:57:35,  7.17s/it]
 95%|█████████▍| 26594/28080 [52:32:21<2:57:37,  7.17s/it]
                                                          
{'loss': 0.6051, 'learning_rate': 3.6632398778678188e-06, 'epoch': 11.36}

 95%|█████████▍| 26594/28080 [52:32:21<2:57:37,  7.17s/it]
 95%|█████████▍| 26595/28080 [52:32:28<2:57:03,  7.15s/it]
                                                          
{'loss': 0.6004, 'learning_rate': 3.658323256302054e-06, 'epoch': 11.36}

 95%|█████████▍| 26595/28080 [52:32:28<2:57:03,  7.15s/it]
 95%|█████████▍| 26596/28080 [52:32:35<2:57:02,  7.16s/it]
                                                          
{'loss': 0.5934, 'learning_rate': 3.65340991205812e-06, 'epoch': 11.36}

 95%|█████████▍| 26596/28080 [52:32:35<2:57:02,  7.16s/it]
 95%|█████████▍| 26597/28080 [52:32:42<2:57:10,  7.17s/it]
                                                          
{'loss': 0.5921, 'learning_rate': 3.648499845201464e-06, 'epoch': 11.36}

 95%|█████████▍| 26597/28080 [52:32:42<2:57:10,  7.17s/it]
 95%|█████████▍| 26598/28080 [52:32:50<2:56:59,  7.17s/it]
                                                          
{'loss': 0.6005, 'learning_rate': 3.6435930557973672e-06, 'epoch': 11.36}

 95%|█████████▍| 26598/28080 [52:32:50<2:56:59,  7.17s/it]
 95%|█████████▍| 26599/28080 [52:32:57<2:56:30,  7.15s/it]
                                                          
{'loss': 0.6232, 'learning_rate': 3.6386895439111113e-06, 'epoch': 11.36}

 95%|█████████▍| 26599/28080 [52:32:57<2:56:30,  7.15s/it]
 95%|█████████▍| 26600/28080 [52:33:04<2:56:41,  7.16s/it]
                                                          
{'loss': 0.5986, 'learning_rate': 3.633789309607921e-06, 'epoch': 11.36}

 95%|█████████▍| 26600/28080 [52:33:04<2:56:41,  7.16s/it]
 95%|█████████▍| 26601/28080 [52:33:11<2:55:42,  7.13s/it]
                                                          
{'loss': 0.5962, 'learning_rate': 3.628892352952995e-06, 'epoch': 11.36}

 95%|█████████▍| 26601/28080 [52:33:11<2:55:42,  7.13s/it]
 95%|█████████▍| 26602/28080 [52:33:18<2:55:15,  7.11s/it]
                                                          
{'loss': 0.6066, 'learning_rate': 3.6239986740115027e-06, 'epoch': 11.36}

 95%|█████████▍| 26602/28080 [52:33:18<2:55:15,  7.11s/it]
 95%|█████████▍| 26603/28080 [52:33:25<2:55:38,  7.14s/it]
                                                          
{'loss': 0.6002, 'learning_rate': 3.619108272848559e-06, 'epoch': 11.36}

 95%|█████████▍| 26603/28080 [52:33:25<2:55:38,  7.14s/it]
 95%|█████████▍| 26604/28080 [52:33:32<2:55:30,  7.13s/it]
                                                          
{'loss': 0.625, 'learning_rate': 3.6142211495291678e-06, 'epoch': 11.36}

 95%|█████████▍| 26604/28080 [52:33:32<2:55:30,  7.13s/it]
 95%|█████████▍| 26605/28080 [52:33:39<2:54:53,  7.11s/it]
                                                          
{'loss': 0.6007, 'learning_rate': 3.6093373041184153e-06, 'epoch': 11.37}

 95%|█████████▍| 26605/28080 [52:33:39<2:54:53,  7.11s/it]
 95%|█████████▍| 26606/28080 [52:33:47<2:55:21,  7.14s/it]
                                                          
{'loss': 0.6138, 'learning_rate': 3.604456736681194e-06, 'epoch': 11.37}

 95%|█████████▍| 26606/28080 [52:33:47<2:55:21,  7.14s/it]
 95%|█████████▍| 26607/28080 [52:33:54<2:55:12,  7.14s/it]
                                                          
{'loss': 0.5937, 'learning_rate': 3.5995794472825083e-06, 'epoch': 11.37}

 95%|█████████▍| 26607/28080 [52:33:54<2:55:12,  7.14s/it]
 95%|█████████▍| 26608/28080 [52:34:01<2:55:23,  7.15s/it]
                                                          
{'loss': 0.6024, 'learning_rate': 3.59470543598725e-06, 'epoch': 11.37}

 95%|█████████▍| 26608/28080 [52:34:01<2:55:23,  7.15s/it]
 95%|█████████▍| 26609/28080 [52:34:08<2:55:15,  7.15s/it]
                                                          
{'loss': 0.5927, 'learning_rate': 3.5898347028602007e-06, 'epoch': 11.37}

 95%|█████████▍| 26609/28080 [52:34:08<2:55:15,  7.15s/it]
 95%|█████████▍| 26610/28080 [52:34:15<2:54:41,  7.13s/it]
                                                          
{'loss': 0.601, 'learning_rate': 3.5849672479662256e-06, 'epoch': 11.37}

 95%|█████████▍| 26610/28080 [52:34:15<2:54:41,  7.13s/it]
 95%|█████████▍| 26611/28080 [52:34:22<2:55:28,  7.17s/it]
                                                          
{'loss': 0.5985, 'learning_rate': 3.5801030713699946e-06, 'epoch': 11.37}

 95%|█████████▍| 26611/28080 [52:34:22<2:55:28,  7.17s/it]
 95%|█████████▍| 26612/28080 [52:34:29<2:54:43,  7.14s/it]
                                                          
{'loss': 0.6132, 'learning_rate': 3.5752421731363173e-06, 'epoch': 11.37}

 95%|█████████▍| 26612/28080 [52:34:29<2:54:43,  7.14s/it]
 95%|█████████▍| 26613/28080 [52:34:37<2:54:47,  7.15s/it]
                                                          
{'loss': 0.6091, 'learning_rate': 3.5703845533298083e-06, 'epoch': 11.37}

 95%|█████████▍| 26613/28080 [52:34:37<2:54:47,  7.15s/it]
 95%|█████████▍| 26614/28080 [52:34:44<2:54:38,  7.15s/it]
                                                          
{'loss': 0.5958, 'learning_rate': 3.5655302120151114e-06, 'epoch': 11.37}

 95%|█████████▍| 26614/28080 [52:34:44<2:54:38,  7.15s/it]
 95%|█████████▍| 26615/28080 [52:34:51<2:54:27,  7.14s/it]
                                                          
{'loss': 0.5797, 'learning_rate': 3.5606791492567845e-06, 'epoch': 11.37}

 95%|█████████▍| 26615/28080 [52:34:51<2:54:27,  7.14s/it]
 95%|█████████▍| 26616/28080 [52:34:58<2:54:20,  7.15s/it]
                                                          
{'loss': 0.6132, 'learning_rate': 3.5558313651193885e-06, 'epoch': 11.37}

 95%|█████████▍| 26616/28080 [52:34:58<2:54:20,  7.15s/it]
 95%|█████████▍| 26617/28080 [52:35:05<2:53:44,  7.13s/it]
                                                          
{'loss': 0.629, 'learning_rate': 3.550986859667454e-06, 'epoch': 11.37}

 95%|█████████▍| 26617/28080 [52:35:05<2:53:44,  7.13s/it]
 95%|█████████▍| 26618/28080 [52:35:12<2:52:30,  7.08s/it]
                                                          
{'loss': 0.6108, 'learning_rate': 3.5461456329653475e-06, 'epoch': 11.37}

 95%|█████████▍| 26618/28080 [52:35:12<2:52:30,  7.08s/it]
 95%|█████████▍| 26619/28080 [52:35:19<2:53:09,  7.11s/it]
                                                          
{'loss': 0.6107, 'learning_rate': 3.541307685077516e-06, 'epoch': 11.37}

 95%|█████████▍| 26619/28080 [52:35:19<2:53:09,  7.11s/it]
 95%|█████████▍| 26620/28080 [52:35:26<2:52:45,  7.10s/it]
                                                          
{'loss': 0.5909, 'learning_rate': 3.5364730160683533e-06, 'epoch': 11.37}

 95%|█████████▍| 26620/28080 [52:35:26<2:52:45,  7.10s/it]
 95%|█████████▍| 26621/28080 [52:35:34<2:53:29,  7.13s/it]
                                                          
{'loss': 0.5974, 'learning_rate': 3.531641626002141e-06, 'epoch': 11.37}

 95%|█████████▍| 26621/28080 [52:35:34<2:53:29,  7.13s/it]
 95%|█████████▍| 26622/28080 [52:35:41<2:53:04,  7.12s/it]
                                                          
{'loss': 0.5833, 'learning_rate': 3.526813514943189e-06, 'epoch': 11.37}

 95%|█████████▍| 26622/28080 [52:35:41<2:53:04,  7.12s/it]
 95%|█████████▍| 26623/28080 [52:35:48<2:52:44,  7.11s/it]
                                                          
{'loss': 0.6025, 'learning_rate': 3.5219886829556956e-06, 'epoch': 11.37}

 95%|█████████▍| 26623/28080 [52:35:48<2:52:44,  7.11s/it]
 95%|█████████▍| 26624/28080 [52:35:55<2:53:05,  7.13s/it]
                                                          
{'loss': 0.5915, 'learning_rate': 3.5171671301038597e-06, 'epoch': 11.37}

 95%|█████████▍| 26624/28080 [52:35:55<2:53:05,  7.13s/it]
 95%|█████████▍| 26625/28080 [52:36:02<2:52:54,  7.13s/it]
                                                          
{'loss': 0.6091, 'learning_rate': 3.5123488564518523e-06, 'epoch': 11.37}

 95%|█████████▍| 26625/28080 [52:36:02<2:52:54,  7.13s/it]
 95%|█████████▍| 26626/28080 [52:36:09<2:53:04,  7.14s/it]
                                                          
{'loss': 0.5895, 'learning_rate': 3.507533862063733e-06, 'epoch': 11.37}

 95%|█████████▍| 26626/28080 [52:36:09<2:53:04,  7.14s/it]
 95%|█████████▍| 26627/28080 [52:36:16<2:52:58,  7.14s/it]
                                                          
{'loss': 0.6041, 'learning_rate': 3.5027221470036176e-06, 'epoch': 11.37}

 95%|█████████▍| 26627/28080 [52:36:16<2:52:58,  7.14s/it]
 95%|█████████▍| 26628/28080 [52:36:24<2:53:35,  7.17s/it]
                                                          
{'loss': 0.6066, 'learning_rate': 3.497913711335454e-06, 'epoch': 11.38}

 95%|█████████▍| 26628/28080 [52:36:24<2:53:35,  7.17s/it]
 95%|█████████▍| 26629/28080 [52:36:31<2:53:06,  7.16s/it]
                                                          
{'loss': 0.5796, 'learning_rate': 3.493108555123248e-06, 'epoch': 11.38}

 95%|█████████▍| 26629/28080 [52:36:31<2:53:06,  7.16s/it]
 95%|█████████▍| 26630/28080 [52:36:38<2:51:56,  7.12s/it]
                                                          
{'loss': 0.5822, 'learning_rate': 3.488306678430947e-06, 'epoch': 11.38}

 95%|█████████▍| 26630/28080 [52:36:38<2:51:56,  7.12s/it]
 95%|█████████▍| 26631/28080 [52:36:45<2:51:28,  7.10s/it]
                                                          
{'loss': 0.6245, 'learning_rate': 3.48350808132239e-06, 'epoch': 11.38}

 95%|█████████▍| 26631/28080 [52:36:45<2:51:28,  7.10s/it]
 95%|█████████▍| 26632/28080 [52:36:52<2:51:43,  7.12s/it]
                                                          
{'loss': 0.5812, 'learning_rate': 3.478712763861469e-06, 'epoch': 11.38}

 95%|█████████▍| 26632/28080 [52:36:52<2:51:43,  7.12s/it]
 95%|█████████▍| 26633/28080 [52:36:59<2:51:03,  7.09s/it]
                                                          
{'loss': 0.5892, 'learning_rate': 3.47392072611194e-06, 'epoch': 11.38}

 95%|█████████▍| 26633/28080 [52:36:59<2:51:03,  7.09s/it]
 95%|█████████▍| 26634/28080 [52:37:06<2:51:00,  7.10s/it]
                                                          
{'loss': 0.6011, 'learning_rate': 3.4691319681375568e-06, 'epoch': 11.38}

 95%|█████████▍| 26634/28080 [52:37:06<2:51:00,  7.10s/it]
 95%|█████████▍| 26635/28080 [52:37:13<2:51:07,  7.11s/it]
                                                          
{'loss': 0.6029, 'learning_rate': 3.464346490002046e-06, 'epoch': 11.38}

 95%|█████████▍| 26635/28080 [52:37:13<2:51:07,  7.11s/it]
 95%|█████████▍| 26636/28080 [52:37:20<2:51:08,  7.11s/it]
                                                          
{'loss': 0.5997, 'learning_rate': 3.4595642917690797e-06, 'epoch': 11.38}

 95%|█████████▍| 26636/28080 [52:37:20<2:51:08,  7.11s/it]
 95%|█████████▍| 26637/28080 [52:37:27<2:50:56,  7.11s/it]
                                                          
{'loss': 0.6055, 'learning_rate': 3.454785373502273e-06, 'epoch': 11.38}

 95%|█████████▍| 26637/28080 [52:37:27<2:50:56,  7.11s/it]
 95%|█████████▍| 26638/28080 [52:37:35<2:50:20,  7.09s/it]
                                                          
{'loss': 0.6119, 'learning_rate': 3.450009735265186e-06, 'epoch': 11.38}

 95%|█████████▍| 26638/28080 [52:37:35<2:50:20,  7.09s/it]
 95%|█████████▍| 26639/28080 [52:37:42<2:51:06,  7.12s/it]
                                                          
{'loss': 0.5966, 'learning_rate': 3.445237377121352e-06, 'epoch': 11.38}

 95%|█████████▍| 26639/28080 [52:37:42<2:51:06,  7.12s/it]
 95%|█████████▍| 26640/28080 [52:37:49<2:51:11,  7.13s/it]
                                                          
{'loss': 0.5847, 'learning_rate': 3.440468299134303e-06, 'epoch': 11.38}

 95%|█████████▍| 26640/28080 [52:37:49<2:51:11,  7.13s/it]
 95%|█████████▍| 26641/28080 [52:37:56<2:51:00,  7.13s/it]
                                                          
{'loss': 0.5974, 'learning_rate': 3.4357025013674603e-06, 'epoch': 11.38}

 95%|█████████▍| 26641/28080 [52:37:56<2:51:00,  7.13s/it]
 95%|█████████▍| 26642/28080 [52:38:03<2:50:55,  7.13s/it]
                                                          
{'loss': 0.6194, 'learning_rate': 3.430939983884218e-06, 'epoch': 11.38}

 95%|█████████▍| 26642/28080 [52:38:03<2:50:55,  7.13s/it]
 95%|█████████▍| 26643/28080 [52:38:10<2:50:44,  7.13s/it]
                                                          
{'loss': 0.5896, 'learning_rate': 3.42618074674797e-06, 'epoch': 11.38}

 95%|█████████▍| 26643/28080 [52:38:10<2:50:44,  7.13s/it]
 95%|█████████▍| 26644/28080 [52:38:17<2:50:07,  7.11s/it]
                                                          
{'loss': 0.618, 'learning_rate': 3.4214247900219707e-06, 'epoch': 11.38}

 95%|█████████▍| 26644/28080 [52:38:17<2:50:07,  7.11s/it]
 95%|█████████▍| 26645/28080 [52:38:25<2:51:02,  7.15s/it]
                                                          
{'loss': 0.5952, 'learning_rate': 3.416672113769559e-06, 'epoch': 11.38}

 95%|█████████▍| 26645/28080 [52:38:25<2:51:02,  7.15s/it]
 95%|█████████▍| 26646/28080 [52:38:32<2:50:16,  7.12s/it]
                                                          
{'loss': 0.6103, 'learning_rate': 3.4119227180539614e-06, 'epoch': 11.38}

 95%|█████████▍| 26646/28080 [52:38:32<2:50:16,  7.12s/it]
 95%|█████████▍| 26647/28080 [52:38:39<2:50:35,  7.14s/it]
                                                          
{'loss': 0.6113, 'learning_rate': 3.407176602938322e-06, 'epoch': 11.38}

 95%|█████████▍| 26647/28080 [52:38:39<2:50:35,  7.14s/it]
 95%|█████████▍| 26648/28080 [52:38:46<2:50:36,  7.15s/it]
                                                          
{'loss': 0.5948, 'learning_rate': 3.402433768485785e-06, 'epoch': 11.38}

 95%|█████████▍| 26648/28080 [52:38:46<2:50:36,  7.15s/it]
 95%|█████████▍| 26649/28080 [52:38:53<2:50:22,  7.14s/it]
                                                          
{'loss': 0.6093, 'learning_rate': 3.3976942147594947e-06, 'epoch': 11.38}

 95%|█████████▍| 26649/28080 [52:38:53<2:50:22,  7.14s/it]
 95%|█████████▍| 26650/28080 [52:39:00<2:50:16,  7.14s/it]
                                                          
{'loss': 0.5948, 'learning_rate': 3.3929579418224277e-06, 'epoch': 11.38}

 95%|█████████▍| 26650/28080 [52:39:00<2:50:16,  7.14s/it]
 95%|█████████▍| 26651/28080 [52:39:07<2:50:14,  7.15s/it]
                                                          
{'loss': 0.6022, 'learning_rate': 3.388224949737728e-06, 'epoch': 11.39}

 95%|█████████▍| 26651/28080 [52:39:07<2:50:14,  7.15s/it]
 95%|█████████▍| 26652/28080 [52:39:15<2:50:05,  7.15s/it]
                                                          
{'loss': 0.6093, 'learning_rate': 3.3834952385682072e-06, 'epoch': 11.39}

 95%|█████████▍| 26652/28080 [52:39:15<2:50:05,  7.15s/it]
 95%|█████████▍| 26653/28080 [52:39:22<2:49:59,  7.15s/it]
                                                          
{'loss': 0.5927, 'learning_rate': 3.3787688083768976e-06, 'epoch': 11.39}

 95%|█████████▍| 26653/28080 [52:39:22<2:49:59,  7.15s/it]
 95%|█████████▍| 26654/28080 [52:39:29<2:50:07,  7.16s/it]
                                                          
{'loss': 0.585, 'learning_rate': 3.37404565922661e-06, 'epoch': 11.39}

 95%|█████████▍| 26654/28080 [52:39:29<2:50:07,  7.16s/it]
 95%|█████████▍| 26655/28080 [52:39:36<2:50:02,  7.16s/it]
                                                          
{'loss': 0.5789, 'learning_rate': 3.369325791180239e-06, 'epoch': 11.39}

 95%|█████████▍| 26655/28080 [52:39:36<2:50:02,  7.16s/it]
 95%|█████████▍| 26656/28080 [52:39:43<2:49:31,  7.14s/it]
                                                          
{'loss': 0.5879, 'learning_rate': 3.364609204300567e-06, 'epoch': 11.39}

 95%|█████████▍| 26656/28080 [52:39:43<2:49:31,  7.14s/it]
 95%|█████████▍| 26657/28080 [52:39:50<2:49:22,  7.14s/it]
                                                          
{'loss': 0.5907, 'learning_rate': 3.3598958986503226e-06, 'epoch': 11.39}

 95%|█████████▍| 26657/28080 [52:39:50<2:49:22,  7.14s/it]
 95%|█████████▍| 26658/28080 [52:39:57<2:48:55,  7.13s/it]
                                                          
{'loss': 0.5854, 'learning_rate': 3.3551858742922326e-06, 'epoch': 11.39}

 95%|█████████▍| 26658/28080 [52:39:57<2:48:55,  7.13s/it]
 95%|█████████▍| 26659/28080 [52:40:05<2:48:46,  7.13s/it]
                                                          
{'loss': 0.5915, 'learning_rate': 3.3504791312888862e-06, 'epoch': 11.39}

 95%|█████████▍| 26659/28080 [52:40:05<2:48:46,  7.13s/it]
 95%|█████████▍| 26660/28080 [52:40:12<2:49:02,  7.14s/it]
                                                          
{'loss': 0.6015, 'learning_rate': 3.3457756697030106e-06, 'epoch': 11.39}

 95%|█████████▍| 26660/28080 [52:40:12<2:49:02,  7.14s/it]
 95%|█████████▍| 26661/28080 [52:40:19<2:49:00,  7.15s/it]
                                                          
{'loss': 0.6108, 'learning_rate': 3.3410754895971396e-06, 'epoch': 11.39}

 95%|█████████▍| 26661/28080 [52:40:19<2:49:00,  7.15s/it]
 95%|█████████▍| 26662/28080 [52:40:26<2:48:56,  7.15s/it]
                                                          
{'loss': 0.5833, 'learning_rate': 3.3363785910337783e-06, 'epoch': 11.39}

 95%|█████████▍| 26662/28080 [52:40:26<2:48:56,  7.15s/it]
 95%|█████████▍| 26663/28080 [52:40:33<2:48:58,  7.15s/it]
                                                          
{'loss': 0.5982, 'learning_rate': 3.331684974075405e-06, 'epoch': 11.39}

 95%|█████████▍| 26663/28080 [52:40:33<2:48:58,  7.15s/it]
 95%|█████████▍| 26664/28080 [52:40:40<2:48:37,  7.14s/it]
                                                          
{'loss': 0.604, 'learning_rate': 3.326994638784525e-06, 'epoch': 11.39}

 95%|█████████▍| 26664/28080 [52:40:40<2:48:37,  7.14s/it]
 95%|█████████▍| 26665/28080 [52:40:47<2:48:40,  7.15s/it]
                                                          
{'loss': 0.602, 'learning_rate': 3.322307585223505e-06, 'epoch': 11.39}

 95%|█████████▍| 26665/28080 [52:40:47<2:48:40,  7.15s/it]
 95%|█████████▍| 26666/28080 [52:40:55<2:48:01,  7.13s/it]
                                                          
{'loss': 0.5949, 'learning_rate': 3.3176238134546844e-06, 'epoch': 11.39}

 95%|█████████▍| 26666/28080 [52:40:55<2:48:01,  7.13s/it]
 95%|█████████▍| 26667/28080 [52:41:02<2:47:33,  7.12s/it]
                                                          
{'loss': 0.6015, 'learning_rate': 3.3129433235403738e-06, 'epoch': 11.39}

 95%|█████████▍| 26667/28080 [52:41:02<2:47:33,  7.12s/it]
 95%|█████████▍| 26668/28080 [52:41:09<2:47:29,  7.12s/it]
                                                          
{'loss': 0.593, 'learning_rate': 3.308266115542885e-06, 'epoch': 11.39}

 95%|█████████▍| 26668/28080 [52:41:09<2:47:29,  7.12s/it]
 95%|█████████▍| 26669/28080 [52:41:16<2:48:06,  7.15s/it]
                                                          
{'loss': 0.5764, 'learning_rate': 3.3035921895243904e-06, 'epoch': 11.39}

 95%|█████████▍| 26669/28080 [52:41:16<2:48:06,  7.15s/it]
 95%|█████████▍| 26670/28080 [52:41:23<2:48:02,  7.15s/it]
                                                          
{'loss': 0.5919, 'learning_rate': 3.2989215455471176e-06, 'epoch': 11.39}

 95%|█████████▍| 26670/28080 [52:41:23<2:48:02,  7.15s/it]
 95%|█████████▍| 26671/28080 [52:41:30<2:48:07,  7.16s/it]
                                                          
{'loss': 0.5753, 'learning_rate': 3.294254183673212e-06, 'epoch': 11.39}

 95%|█████████▍| 26671/28080 [52:41:30<2:48:07,  7.16s/it]
 95%|█████████▍| 26672/28080 [52:41:37<2:47:08,  7.12s/it]
                                                          
{'loss': 0.6155, 'learning_rate': 3.289590103964707e-06, 'epoch': 11.39}

 95%|█████████▍| 26672/28080 [52:41:37<2:47:08,  7.12s/it]
 95%|█████████▍| 26673/28080 [52:41:45<2:47:22,  7.14s/it]
                                                          
{'loss': 0.5951, 'learning_rate': 3.2849293064836917e-06, 'epoch': 11.39}

 95%|█████████▍| 26673/28080 [52:41:45<2:47:22,  7.14s/it]
 95%|█████████▍| 26674/28080 [52:41:52<2:47:10,  7.13s/it]
                                                          
{'loss': 0.6242, 'learning_rate': 3.2802717912921997e-06, 'epoch': 11.39}

 95%|█████████▍| 26674/28080 [52:41:52<2:47:10,  7.13s/it]
 95%|█████████▍| 26675/28080 [52:41:59<2:47:38,  7.16s/it]
                                                          
{'loss': 0.5804, 'learning_rate': 3.2756175584521263e-06, 'epoch': 11.4}

 95%|█████████▍| 26675/28080 [52:41:59<2:47:38,  7.16s/it]
 95%|█████████▌| 26676/28080 [52:42:06<2:47:33,  7.16s/it]
                                                          
{'loss': 0.6185, 'learning_rate': 3.2709666080254776e-06, 'epoch': 11.4}

 95%|█████████▌| 26676/28080 [52:42:06<2:47:33,  7.16s/it]
 95%|█████████▌| 26677/28080 [52:42:13<2:47:37,  7.17s/it]
                                                          
{'loss': 0.5948, 'learning_rate': 3.2663189400740367e-06, 'epoch': 11.4}

 95%|█████████▌| 26677/28080 [52:42:13<2:47:37,  7.17s/it]
 95%|█████████▌| 26678/28080 [52:42:20<2:47:30,  7.17s/it]
                                                          
{'loss': 0.6093, 'learning_rate': 3.261674554659699e-06, 'epoch': 11.4}

 95%|█████████▌| 26678/28080 [52:42:20<2:47:30,  7.17s/it]
 95%|█████████▌| 26679/28080 [52:42:28<2:47:22,  7.17s/it]
                                                          
{'loss': 0.6023, 'learning_rate': 3.2570334518442214e-06, 'epoch': 11.4}

 95%|█████████▌| 26679/28080 [52:42:28<2:47:22,  7.17s/it]
 95%|█████████▌| 26680/28080 [52:42:35<2:47:09,  7.16s/it]
                                                          
{'loss': 0.5925, 'learning_rate': 3.2523956316893865e-06, 'epoch': 11.4}

 95%|█████████▌| 26680/28080 [52:42:35<2:47:09,  7.16s/it]
 95%|█████████▌| 26681/28080 [52:42:42<2:46:51,  7.16s/it]
                                                          
{'loss': 0.5934, 'learning_rate': 3.2477610942568405e-06, 'epoch': 11.4}

 95%|█████████▌| 26681/28080 [52:42:42<2:46:51,  7.16s/it]
 95%|█████████▌| 26682/28080 [52:42:49<2:46:23,  7.14s/it]
                                                          
{'loss': 0.5956, 'learning_rate': 3.243129839608311e-06, 'epoch': 11.4}

 95%|█████████▌| 26682/28080 [52:42:49<2:46:23,  7.14s/it]
 95%|█████████▌| 26683/28080 [52:42:56<2:45:14,  7.10s/it]
                                                          
{'loss': 0.5998, 'learning_rate': 3.2385018678053603e-06, 'epoch': 11.4}

 95%|█████████▌| 26683/28080 [52:42:56<2:45:14,  7.10s/it]
 95%|█████████▌| 26684/28080 [52:43:03<2:45:40,  7.12s/it]
                                                          
{'loss': 0.5939, 'learning_rate': 3.23387717890955e-06, 'epoch': 11.4}

 95%|█████████▌| 26684/28080 [52:43:03<2:45:40,  7.12s/it]
 95%|█████████▌| 26685/28080 [52:43:10<2:46:22,  7.16s/it]
                                                          
{'loss': 0.6072, 'learning_rate': 3.22925577298247e-06, 'epoch': 11.4}

 95%|█████████▌| 26685/28080 [52:43:10<2:46:22,  7.16s/it]
 95%|█████████▌| 26686/28080 [52:43:18<2:46:07,  7.15s/it]
                                                          
{'loss': 0.5944, 'learning_rate': 3.2246376500855156e-06, 'epoch': 11.4}

 95%|█████████▌| 26686/28080 [52:43:18<2:46:07,  7.15s/it]
 95%|█████████▌| 26687/28080 [52:43:25<2:45:33,  7.13s/it]
                                                          
{'loss': 0.6097, 'learning_rate': 3.220022810280221e-06, 'epoch': 11.4}

 95%|█████████▌| 26687/28080 [52:43:25<2:45:33,  7.13s/it]
 95%|█████████▌| 26688/28080 [52:43:32<2:45:26,  7.13s/it]
                                                          
{'loss': 0.6015, 'learning_rate': 3.2154112536278977e-06, 'epoch': 11.4}

 95%|█████████▌| 26688/28080 [52:43:32<2:45:26,  7.13s/it]
 95%|█████████▌| 26689/28080 [52:43:39<2:46:07,  7.17s/it]
                                                          
{'loss': 0.5754, 'learning_rate': 3.2108029801899417e-06, 'epoch': 11.4}

 95%|█████████▌| 26689/28080 [52:43:39<2:46:07,  7.17s/it]
 95%|█████████▌| 26690/28080 [52:43:46<2:45:02,  7.12s/it]
                                                          
{'loss': 0.6007, 'learning_rate': 3.206197990027665e-06, 'epoch': 11.4}

 95%|█████████▌| 26690/28080 [52:43:46<2:45:02,  7.12s/it]
 95%|█████████▌| 26691/28080 [52:43:53<2:45:02,  7.13s/it]
                                                          
{'loss': 0.5722, 'learning_rate': 3.2015962832023237e-06, 'epoch': 11.4}

 95%|█████████▌| 26691/28080 [52:43:53<2:45:02,  7.13s/it]
 95%|█████████▌| 26692/28080 [52:44:00<2:44:58,  7.13s/it]
                                                          
{'loss': 0.5975, 'learning_rate': 3.1969978597751194e-06, 'epoch': 11.4}

 95%|█████████▌| 26692/28080 [52:44:00<2:44:58,  7.13s/it]
 95%|█████████▌| 26693/28080 [52:44:07<2:44:33,  7.12s/it]
                                                          
{'loss': 0.6023, 'learning_rate': 3.1924027198072524e-06, 'epoch': 11.4}

 95%|█████████▌| 26693/28080 [52:44:07<2:44:33,  7.12s/it]
 95%|█████████▌| 26694/28080 [52:44:14<2:43:20,  7.07s/it]
                                                          
{'loss': 0.6015, 'learning_rate': 3.187810863359869e-06, 'epoch': 11.4}

 95%|█████████▌| 26694/28080 [52:44:14<2:43:20,  7.07s/it]
 95%|█████████▌| 26695/28080 [52:44:21<2:43:17,  7.07s/it]
                                                          
{'loss': 0.5714, 'learning_rate': 3.183222290494031e-06, 'epoch': 11.4}

 95%|█████████▌| 26695/28080 [52:44:21<2:43:17,  7.07s/it]
 95%|█████████▌| 26696/28080 [52:44:29<2:43:45,  7.10s/it]
                                                          
{'loss': 0.5811, 'learning_rate': 3.1786370012707734e-06, 'epoch': 11.4}

 95%|█████████▌| 26696/28080 [52:44:29<2:43:45,  7.10s/it]
 95%|█████████▌| 26697/28080 [52:44:36<2:43:25,  7.09s/it]
                                                          
{'loss': 0.6047, 'learning_rate': 3.17405499575113e-06, 'epoch': 11.4}

 95%|█████████▌| 26697/28080 [52:44:36<2:43:25,  7.09s/it]
 95%|█████████▌| 26698/28080 [52:44:43<2:43:45,  7.11s/it]
                                                          
{'loss': 0.6138, 'learning_rate': 3.169476273996025e-06, 'epoch': 11.41}

 95%|█████████▌| 26698/28080 [52:44:43<2:43:45,  7.11s/it]
 95%|█████████▌| 26699/28080 [52:44:50<2:43:40,  7.11s/it]
                                                          
{'loss': 0.6045, 'learning_rate': 3.1649008360664646e-06, 'epoch': 11.41}

 95%|█████████▌| 26699/28080 [52:44:50<2:43:40,  7.11s/it]
 95%|█████████▌| 26700/28080 [52:44:57<2:43:38,  7.12s/it]
                                                          
{'loss': 0.5957, 'learning_rate': 3.160328682023178e-06, 'epoch': 11.41}

 95%|█████████▌| 26700/28080 [52:44:57<2:43:38,  7.12s/it]
 95%|█████████▌| 26701/28080 [52:45:04<2:42:35,  7.07s/it]
                                                          
{'loss': 0.6099, 'learning_rate': 3.155759811927117e-06, 'epoch': 11.41}

 95%|█████████▌| 26701/28080 [52:45:04<2:42:35,  7.07s/it]
 95%|█████████▌| 26702/28080 [52:45:11<2:42:50,  7.09s/it]
                                                          
{'loss': 0.6018, 'learning_rate': 3.1511942258389824e-06, 'epoch': 11.41}

 95%|█████████▌| 26702/28080 [52:45:11<2:42:50,  7.09s/it]
 95%|█████████▌| 26703/28080 [52:45:18<2:42:23,  7.08s/it]
                                                          
{'loss': 0.6036, 'learning_rate': 3.1466319238195873e-06, 'epoch': 11.41}

 95%|█████████▌| 26703/28080 [52:45:18<2:42:23,  7.08s/it]
 95%|█████████▌| 26704/28080 [52:45:25<2:42:35,  7.09s/it]
                                                          
{'loss': 0.5912, 'learning_rate': 3.142072905929577e-06, 'epoch': 11.41}

 95%|█████████▌| 26704/28080 [52:45:25<2:42:35,  7.09s/it]
 95%|█████████▌| 26705/28080 [52:45:32<2:42:52,  7.11s/it]
                                                          
{'loss': 0.5943, 'learning_rate': 3.137517172229598e-06, 'epoch': 11.41}

 95%|█████████▌| 26705/28080 [52:45:32<2:42:52,  7.11s/it]
 95%|█████████▌| 26706/28080 [52:45:40<2:42:28,  7.09s/it]
                                                          
{'loss': 0.642, 'learning_rate': 3.132964722780296e-06, 'epoch': 11.41}

 95%|█████████▌| 26706/28080 [52:45:40<2:42:28,  7.09s/it]
 95%|█████████▌| 26707/28080 [52:45:47<2:42:06,  7.08s/it]
                                                          
{'loss': 0.5997, 'learning_rate': 3.128415557642206e-06, 'epoch': 11.41}

 95%|█████████▌| 26707/28080 [52:45:47<2:42:06,  7.08s/it]
 95%|█████████▌| 26708/28080 [52:45:54<2:42:22,  7.10s/it]
                                                          
{'loss': 0.5943, 'learning_rate': 3.12386967687589e-06, 'epoch': 11.41}

 95%|█████████▌| 26708/28080 [52:45:54<2:42:22,  7.10s/it]
 95%|█████████▌| 26709/28080 [52:46:01<2:42:37,  7.12s/it]
                                                          
{'loss': 0.5969, 'learning_rate': 3.1193270805417728e-06, 'epoch': 11.41}

 95%|█████████▌| 26709/28080 [52:46:01<2:42:37,  7.12s/it]
 95%|█████████▌| 26710/28080 [52:46:08<2:43:15,  7.15s/it]
                                                          
{'loss': 0.6059, 'learning_rate': 3.1147877687003335e-06, 'epoch': 11.41}

 95%|█████████▌| 26710/28080 [52:46:08<2:43:15,  7.15s/it]
 95%|█████████▌| 26711/28080 [52:46:15<2:42:59,  7.14s/it]
                                                          
{'loss': 0.6053, 'learning_rate': 3.1102517414119403e-06, 'epoch': 11.41}

 95%|█████████▌| 26711/28080 [52:46:15<2:42:59,  7.14s/it]
 95%|█████████▌| 26712/28080 [52:46:22<2:43:43,  7.18s/it]
                                                          
{'loss': 0.6093, 'learning_rate': 3.1057189987369338e-06, 'epoch': 11.41}

 95%|█████████▌| 26712/28080 [52:46:22<2:43:43,  7.18s/it]
 95%|█████████▌| 26713/28080 [52:46:30<2:43:04,  7.16s/it]
                                                          
{'loss': 0.6212, 'learning_rate': 3.101189540735655e-06, 'epoch': 11.41}

 95%|█████████▌| 26713/28080 [52:46:30<2:43:04,  7.16s/it]
 95%|█████████▌| 26714/28080 [52:46:37<2:43:05,  7.16s/it]
                                                          
{'loss': 0.6129, 'learning_rate': 3.096663367468333e-06, 'epoch': 11.41}

 95%|█████████▌| 26714/28080 [52:46:37<2:43:05,  7.16s/it]
 95%|█████████▌| 26715/28080 [52:46:44<2:43:02,  7.17s/it]
                                                          
{'loss': 0.5944, 'learning_rate': 3.09214047899517e-06, 'epoch': 11.41}

 95%|█████████▌| 26715/28080 [52:46:44<2:43:02,  7.17s/it]
 95%|█████████▌| 26716/28080 [52:46:51<2:42:21,  7.14s/it]
                                                          
{'loss': 0.6006, 'learning_rate': 3.087620875376368e-06, 'epoch': 11.41}

 95%|█████████▌| 26716/28080 [52:46:51<2:42:21,  7.14s/it]
 95%|█████████▌| 26717/28080 [52:46:58<2:42:22,  7.15s/it]
                                                          
{'loss': 0.6141, 'learning_rate': 3.083104556672017e-06, 'epoch': 11.41}

 95%|█████████▌| 26717/28080 [52:46:58<2:42:22,  7.15s/it]
 95%|█████████▌| 26718/28080 [52:47:05<2:42:37,  7.16s/it]
                                                          
{'loss': 0.5776, 'learning_rate': 3.0785915229422924e-06, 'epoch': 11.41}

 95%|█████████▌| 26718/28080 [52:47:05<2:42:37,  7.16s/it]
 95%|█████████▌| 26719/28080 [52:47:13<2:42:42,  7.17s/it]
                                                          
{'loss': 0.5961, 'learning_rate': 3.0740817742471173e-06, 'epoch': 11.41}

 95%|█████████▌| 26719/28080 [52:47:13<2:42:42,  7.17s/it]
 95%|█████████▌| 26720/28080 [52:47:20<2:41:22,  7.12s/it]
                                                          
{'loss': 0.5988, 'learning_rate': 3.0695753106465553e-06, 'epoch': 11.41}

 95%|█████████▌| 26720/28080 [52:47:20<2:41:22,  7.12s/it]
 95%|█████████▌| 26721/28080 [52:47:27<2:41:17,  7.12s/it]
                                                          
{'loss': 0.5969, 'learning_rate': 3.065072132200558e-06, 'epoch': 11.41}

 95%|█████████▌| 26721/28080 [52:47:27<2:41:17,  7.12s/it]
 95%|█████████▌| 26722/28080 [52:47:34<2:41:11,  7.12s/it]
                                                          
{'loss': 0.5816, 'learning_rate': 3.060572238969023e-06, 'epoch': 11.42}

 95%|█████████▌| 26722/28080 [52:47:34<2:41:11,  7.12s/it]
 95%|█████████▌| 26723/28080 [52:47:41<2:40:45,  7.11s/it]
                                                          
{'loss': 0.6166, 'learning_rate': 3.0560756310118454e-06, 'epoch': 11.42}

 95%|█████████▌| 26723/28080 [52:47:41<2:40:45,  7.11s/it]
 95%|█████████▌| 26724/28080 [52:47:48<2:40:16,  7.09s/it]
                                                          
{'loss': 0.5802, 'learning_rate': 3.0515823083888118e-06, 'epoch': 11.42}

 95%|█████████▌| 26724/28080 [52:47:48<2:40:16,  7.09s/it]
 95%|█████████▌| 26725/28080 [52:47:55<2:40:32,  7.11s/it]
                                                          
{'loss': 0.6138, 'learning_rate': 3.0470922711596793e-06, 'epoch': 11.42}

 95%|█████████▌| 26725/28080 [52:47:55<2:40:32,  7.11s/it]
 95%|█████████▌| 26726/28080 [52:48:02<2:41:12,  7.14s/it]
                                                          
{'loss': 0.6102, 'learning_rate': 3.0426055193842617e-06, 'epoch': 11.42}

 95%|█████████▌| 26726/28080 [52:48:02<2:41:12,  7.14s/it]
 95%|█████████▌| 26727/28080 [52:48:09<2:40:24,  7.11s/it]
                                                          
{'loss': 0.5986, 'learning_rate': 3.0381220531221778e-06, 'epoch': 11.42}

 95%|█████████▌| 26727/28080 [52:48:09<2:40:24,  7.11s/it]
 95%|█████████▌| 26728/28080 [52:48:17<2:40:28,  7.12s/it]
                                                          
{'loss': 0.6117, 'learning_rate': 3.0336418724331294e-06, 'epoch': 11.42}

 95%|█████████▌| 26728/28080 [52:48:17<2:40:28,  7.12s/it]
 95%|█████████▌| 26729/28080 [52:48:24<2:40:35,  7.13s/it]
                                                          
{'loss': 0.5929, 'learning_rate': 3.0291649773766527e-06, 'epoch': 11.42}

 95%|█████████▌| 26729/28080 [52:48:24<2:40:35,  7.13s/it]
 95%|█████████▌| 26730/28080 [52:48:31<2:40:34,  7.14s/it]
                                                          
{'loss': 0.6217, 'learning_rate': 3.0246913680123943e-06, 'epoch': 11.42}

 95%|█████████▌| 26730/28080 [52:48:31<2:40:34,  7.14s/it]
 95%|█████████▌| 26731/28080 [52:48:38<2:40:24,  7.13s/it]
                                                          
{'loss': 0.6047, 'learning_rate': 3.0202210443997792e-06, 'epoch': 11.42}

 95%|█████████▌| 26731/28080 [52:48:38<2:40:24,  7.13s/it]
 95%|█████████▌| 26732/28080 [52:48:45<2:40:17,  7.13s/it]
                                                          
{'loss': 0.5993, 'learning_rate': 3.01575400659837e-06, 'epoch': 11.42}

 95%|█████████▌| 26732/28080 [52:48:45<2:40:17,  7.13s/it]
 95%|█████████▌| 26733/28080 [52:48:52<2:40:47,  7.16s/it]
                                                          
{'loss': 0.5878, 'learning_rate': 3.0112902546675648e-06, 'epoch': 11.42}

 95%|█████████▌| 26733/28080 [52:48:52<2:40:47,  7.16s/it]
 95%|█████████▌| 26734/28080 [52:49:00<2:41:24,  7.19s/it]
                                                          
{'loss': 0.5852, 'learning_rate': 3.006829788666704e-06, 'epoch': 11.42}

 95%|█████████▌| 26734/28080 [52:49:00<2:41:24,  7.19s/it]
 95%|█████████▌| 26735/28080 [52:49:07<2:41:02,  7.18s/it]
                                                          
{'loss': 0.5968, 'learning_rate': 3.002372608655185e-06, 'epoch': 11.42}

 95%|█████████▌| 26735/28080 [52:49:07<2:41:02,  7.18s/it]
 95%|█████████▌| 26736/28080 [52:49:14<2:40:51,  7.18s/it]
                                                          
{'loss': 0.5805, 'learning_rate': 2.997918714692266e-06, 'epoch': 11.42}

 95%|█████████▌| 26736/28080 [52:49:14<2:40:51,  7.18s/it]
 95%|█████████▌| 26737/28080 [52:49:21<2:40:21,  7.16s/it]
                                                          
{'loss': 0.5956, 'learning_rate': 2.9934681068372327e-06, 'epoch': 11.42}

 95%|█████████▌| 26737/28080 [52:49:21<2:40:21,  7.16s/it]
 95%|█████████▌| 26738/28080 [52:49:28<2:40:14,  7.16s/it]
                                                          
{'loss': 0.5953, 'learning_rate': 2.989020785149288e-06, 'epoch': 11.42}

 95%|█████████▌| 26738/28080 [52:49:28<2:40:14,  7.16s/it]
 95%|█████████▌| 26739/28080 [52:49:35<2:39:58,  7.16s/it]
                                                          
{'loss': 0.5973, 'learning_rate': 2.9845767496875786e-06, 'epoch': 11.42}

 95%|█████████▌| 26739/28080 [52:49:35<2:39:58,  7.16s/it]
 95%|█████████▌| 26740/28080 [52:49:43<2:40:01,  7.17s/it]
                                                          
{'loss': 0.5901, 'learning_rate': 2.980136000511252e-06, 'epoch': 11.42}

 95%|█████████▌| 26740/28080 [52:49:43<2:40:01,  7.17s/it]
 95%|█████████▌| 26741/28080 [52:49:50<2:39:25,  7.14s/it]
                                                          
{'loss': 0.5958, 'learning_rate': 2.9756985376793723e-06, 'epoch': 11.42}

 95%|█████████▌| 26741/28080 [52:49:50<2:39:25,  7.14s/it]
 95%|█████████▌| 26742/28080 [52:49:57<2:39:20,  7.15s/it]
                                                          
{'loss': 0.5942, 'learning_rate': 2.9712643612510026e-06, 'epoch': 11.42}

 95%|█████████▌| 26742/28080 [52:49:57<2:39:20,  7.15s/it]
 95%|█████████▌| 26743/28080 [52:50:04<2:39:43,  7.17s/it]
                                                          
{'loss': 0.5901, 'learning_rate': 2.966833471285124e-06, 'epoch': 11.42}

 95%|█████████▌| 26743/28080 [52:50:04<2:39:43,  7.17s/it]
 95%|█████████▌| 26744/28080 [52:50:11<2:39:42,  7.17s/it]
                                                          
{'loss': 0.6029, 'learning_rate': 2.962405867840634e-06, 'epoch': 11.42}

 95%|█████████▌| 26744/28080 [52:50:11<2:39:42,  7.17s/it]
 95%|█████████▌| 26745/28080 [52:50:18<2:39:06,  7.15s/it]
                                                          
{'loss': 0.6137, 'learning_rate': 2.957981550976513e-06, 'epoch': 11.43}

 95%|█████████▌| 26745/28080 [52:50:18<2:39:06,  7.15s/it]
 95%|█████████▌| 26746/28080 [52:50:25<2:37:51,  7.10s/it]
                                                          
{'loss': 0.6112, 'learning_rate': 2.953560520751547e-06, 'epoch': 11.43}

 95%|█████████▌| 26746/28080 [52:50:25<2:37:51,  7.10s/it]
 95%|█████████▌| 26747/28080 [52:50:32<2:37:40,  7.10s/it]
                                                          
{'loss': 0.6009, 'learning_rate': 2.9491427772246614e-06, 'epoch': 11.43}

 95%|█████████▌| 26747/28080 [52:50:32<2:37:40,  7.10s/it]
 95%|█████████▌| 26748/28080 [52:50:39<2:37:05,  7.08s/it]
                                                          
{'loss': 0.6056, 'learning_rate': 2.944728320454504e-06, 'epoch': 11.43}

 95%|█████████▌| 26748/28080 [52:50:39<2:37:05,  7.08s/it]
 95%|█████████▌| 26749/28080 [52:50:46<2:36:51,  7.07s/it]
                                                          
{'loss': 0.6303, 'learning_rate': 2.940317150499888e-06, 'epoch': 11.43}

 95%|█████████▌| 26749/28080 [52:50:46<2:36:51,  7.07s/it]
 95%|█████████▌| 26750/28080 [52:50:54<2:36:45,  7.07s/it]
                                                          
{'loss': 0.6008, 'learning_rate': 2.935909267419462e-06, 'epoch': 11.43}

 95%|█████████▌| 26750/28080 [52:50:54<2:36:45,  7.07s/it]
 95%|█████████▌| 26751/28080 [52:51:01<2:37:42,  7.12s/it]
                                                          
{'loss': 0.5872, 'learning_rate': 2.931504671271901e-06, 'epoch': 11.43}

 95%|█████████▌| 26751/28080 [52:51:01<2:37:42,  7.12s/it]
 95%|█████████▌| 26752/28080 [52:51:08<2:37:46,  7.13s/it]
                                                          
{'loss': 0.6035, 'learning_rate': 2.927103362115796e-06, 'epoch': 11.43}

 95%|█████████▌| 26752/28080 [52:51:08<2:37:46,  7.13s/it]
 95%|█████████▌| 26753/28080 [52:51:15<2:37:57,  7.14s/it]
                                                          
{'loss': 0.5964, 'learning_rate': 2.922705340009657e-06, 'epoch': 11.43}

 95%|█████████▌| 26753/28080 [52:51:15<2:37:57,  7.14s/it]
 95%|█████████▌| 26754/28080 [52:51:22<2:37:37,  7.13s/it]
                                                          
{'loss': 0.5934, 'learning_rate': 2.9183106050120477e-06, 'epoch': 11.43}

 95%|█████████▌| 26754/28080 [52:51:22<2:37:37,  7.13s/it]
 95%|█████████▌| 26755/28080 [52:51:29<2:37:07,  7.12s/it]
                                                          
{'loss': 0.5934, 'learning_rate': 2.913919157181394e-06, 'epoch': 11.43}

 95%|█████████▌| 26755/28080 [52:51:29<2:37:07,  7.12s/it]
 95%|█████████▌| 26756/28080 [52:51:36<2:37:23,  7.13s/it]
                                                          
{'loss': 0.5912, 'learning_rate': 2.9095309965761764e-06, 'epoch': 11.43}

 95%|█████████▌| 26756/28080 [52:51:36<2:37:23,  7.13s/it]
 95%|█████████▌| 26757/28080 [52:51:44<2:37:39,  7.15s/it]
                                                          
{'loss': 0.6045, 'learning_rate': 2.9051461232547092e-06, 'epoch': 11.43}

 95%|█████████▌| 26757/28080 [52:51:44<2:37:39,  7.15s/it]
 95%|█████████▌| 26758/28080 [52:51:51<2:37:22,  7.14s/it]
                                                          
{'loss': 0.5839, 'learning_rate': 2.900764537275391e-06, 'epoch': 11.43}

 95%|█████████▌| 26758/28080 [52:51:51<2:37:22,  7.14s/it]
 95%|█████████▌| 26759/28080 [52:51:58<2:37:09,  7.14s/it]
                                                          
{'loss': 0.5936, 'learning_rate': 2.8963862386964523e-06, 'epoch': 11.43}

 95%|█████████▌| 26759/28080 [52:51:58<2:37:09,  7.14s/it]
 95%|█████████▌| 26760/28080 [52:52:05<2:37:23,  7.15s/it]
                                                          
{'loss': 0.589, 'learning_rate': 2.89201122757618e-06, 'epoch': 11.43}

 95%|█████████▌| 26760/28080 [52:52:05<2:37:23,  7.15s/it]
 95%|█████████▌| 26761/28080 [52:52:12<2:37:25,  7.16s/it]
                                                          
{'loss': 0.5744, 'learning_rate': 2.8876395039727775e-06, 'epoch': 11.43}

 95%|█████████▌| 26761/28080 [52:52:12<2:37:25,  7.16s/it]
 95%|█████████▌| 26762/28080 [52:52:19<2:37:15,  7.16s/it]
                                                          
{'loss': 0.5888, 'learning_rate': 2.8832710679443928e-06, 'epoch': 11.43}

 95%|█████████▌| 26762/28080 [52:52:19<2:37:15,  7.16s/it]
 95%|█████████▌| 26763/28080 [52:52:26<2:36:33,  7.13s/it]
                                                          
{'loss': 0.5989, 'learning_rate': 2.8789059195491463e-06, 'epoch': 11.43}

 95%|█████████▌| 26763/28080 [52:52:26<2:36:33,  7.13s/it]
 95%|█████████▌| 26764/28080 [52:52:34<2:36:22,  7.13s/it]
                                                          
{'loss': 0.5966, 'learning_rate': 2.8745440588451023e-06, 'epoch': 11.43}

 95%|█████████▌| 26764/28080 [52:52:34<2:36:22,  7.13s/it]
 95%|█████████▌| 26765/28080 [52:52:41<2:35:54,  7.11s/it]
                                                          
{'loss': 0.607, 'learning_rate': 2.8701854858903255e-06, 'epoch': 11.43}

 95%|█████████▌| 26765/28080 [52:52:41<2:35:54,  7.11s/it]
 95%|█████████▌| 26766/28080 [52:52:48<2:36:05,  7.13s/it]
                                                          
{'loss': 0.606, 'learning_rate': 2.865830200742797e-06, 'epoch': 11.43}

 95%|█████████▌| 26766/28080 [52:52:48<2:36:05,  7.13s/it]
 95%|█████████▌| 26767/28080 [52:52:55<2:35:53,  7.12s/it]
                                                          
{'loss': 0.5998, 'learning_rate': 2.861478203460416e-06, 'epoch': 11.43}

 95%|█████████▌| 26767/28080 [52:52:55<2:35:53,  7.12s/it]
 95%|█████████▌| 26768/28080 [52:53:02<2:35:38,  7.12s/it]
                                                          
{'loss': 0.5964, 'learning_rate': 2.857129494101135e-06, 'epoch': 11.44}

 95%|█████████▌| 26768/28080 [52:53:02<2:35:38,  7.12s/it]
 95%|█████████▌| 26769/28080 [52:53:09<2:35:24,  7.11s/it]
                                                          
{'loss': 0.5925, 'learning_rate': 2.8527840727227417e-06, 'epoch': 11.44}

 95%|█████████▌| 26769/28080 [52:53:09<2:35:24,  7.11s/it]
 95%|█████████▌| 26770/28080 [52:53:16<2:35:04,  7.10s/it]
                                                          
{'loss': 0.5951, 'learning_rate': 2.848441939383106e-06, 'epoch': 11.44}

 95%|█████████▌| 26770/28080 [52:53:16<2:35:04,  7.10s/it]
 95%|█████████▌| 26771/28080 [52:53:23<2:35:02,  7.11s/it]
                                                          
{'loss': 0.6172, 'learning_rate': 2.844103094140016e-06, 'epoch': 11.44}

 95%|█████████▌| 26771/28080 [52:53:23<2:35:02,  7.11s/it]
 95%|█████████▌| 26772/28080 [52:53:31<2:35:23,  7.13s/it]
                                                          
{'loss': 0.6061, 'learning_rate': 2.839767537051119e-06, 'epoch': 11.44}

 95%|█████████▌| 26772/28080 [52:53:31<2:35:23,  7.13s/it]
 95%|█████████▌| 26773/28080 [52:53:38<2:35:06,  7.12s/it]
                                                          
{'loss': 0.618, 'learning_rate': 2.835435268174119e-06, 'epoch': 11.44}

 95%|█████████▌| 26773/28080 [52:53:38<2:35:06,  7.12s/it]
 95%|█████████▌| 26774/28080 [52:53:45<2:34:55,  7.12s/it]
                                                          
{'loss': 0.5857, 'learning_rate': 2.8311062875666925e-06, 'epoch': 11.44}

 95%|█████████▌| 26774/28080 [52:53:45<2:34:55,  7.12s/it]
 95%|█████████▌| 26775/28080 [52:53:52<2:34:34,  7.11s/it]
                                                          
{'loss': 0.5893, 'learning_rate': 2.8267805952864324e-06, 'epoch': 11.44}

 95%|█████████▌| 26775/28080 [52:53:52<2:34:34,  7.11s/it]
 95%|█████████▌| 26776/28080 [52:53:59<2:34:40,  7.12s/it]
                                                          
{'loss': 0.5979, 'learning_rate': 2.82245819139082e-06, 'epoch': 11.44}

 95%|█████████▌| 26776/28080 [52:53:59<2:34:40,  7.12s/it]
 95%|█████████▌| 26777/28080 [52:54:06<2:34:20,  7.11s/it]
                                                          
{'loss': 0.5965, 'learning_rate': 2.8181390759374204e-06, 'epoch': 11.44}

 95%|█████████▌| 26777/28080 [52:54:06<2:34:20,  7.11s/it]
 95%|█████████▌| 26778/28080 [52:54:13<2:34:34,  7.12s/it]
                                                          
{'loss': 0.5902, 'learning_rate': 2.8138232489836603e-06, 'epoch': 11.44}

 95%|█████████▌| 26778/28080 [52:54:13<2:34:34,  7.12s/it]
 95%|█████████▌| 26779/28080 [52:54:20<2:34:02,  7.10s/it]
                                                          
{'loss': 0.6031, 'learning_rate': 2.8095107105869935e-06, 'epoch': 11.44}

 95%|█████████▌| 26779/28080 [52:54:20<2:34:02,  7.10s/it]
 95%|█████████▌| 26780/28080 [52:54:27<2:33:46,  7.10s/it]
                                                          
{'loss': 0.5854, 'learning_rate': 2.8052014608047906e-06, 'epoch': 11.44}

 95%|█████████▌| 26780/28080 [52:54:27<2:33:46,  7.10s/it]
 95%|█████████▌| 26781/28080 [52:54:34<2:33:20,  7.08s/it]
                                                          
{'loss': 0.5997, 'learning_rate': 2.8008954996943117e-06, 'epoch': 11.44}

 95%|█████████▌| 26781/28080 [52:54:34<2:33:20,  7.08s/it]
 95%|█████████▌| 26782/28080 [52:54:42<2:33:33,  7.10s/it]
                                                          
{'loss': 0.6057, 'learning_rate': 2.796592827312955e-06, 'epoch': 11.44}

 95%|█████████▌| 26782/28080 [52:54:42<2:33:33,  7.10s/it]
 95%|█████████▌| 26783/28080 [52:54:49<2:33:31,  7.10s/it]
                                                          
{'loss': 0.5879, 'learning_rate': 2.7922934437178693e-06, 'epoch': 11.44}

 95%|█████████▌| 26783/28080 [52:54:49<2:33:31,  7.10s/it]
 95%|█████████▌| 26784/28080 [52:54:56<2:33:57,  7.13s/it]
                                                          
{'loss': 0.5705, 'learning_rate': 2.787997348966287e-06, 'epoch': 11.44}

 95%|█████████▌| 26784/28080 [52:54:56<2:33:57,  7.13s/it]
 95%|█████████▌| 26785/28080 [52:55:03<2:33:33,  7.11s/it]
                                                          
{'loss': 0.6022, 'learning_rate': 2.783704543115384e-06, 'epoch': 11.44}

 95%|█████████▌| 26785/28080 [52:55:03<2:33:33,  7.11s/it]
 95%|█████████▌| 26786/28080 [52:55:10<2:33:47,  7.13s/it]
                                                          
{'loss': 0.5814, 'learning_rate': 2.779415026222254e-06, 'epoch': 11.44}

 95%|█████████▌| 26786/28080 [52:55:10<2:33:47,  7.13s/it]
 95%|█████████▌| 26787/28080 [52:55:17<2:34:00,  7.15s/it]
                                                          
{'loss': 0.5824, 'learning_rate': 2.7751287983439623e-06, 'epoch': 11.44}

 95%|█████████▌| 26787/28080 [52:55:17<2:34:00,  7.15s/it]
 95%|█████████▌| 26788/28080 [52:55:24<2:33:23,  7.12s/it]
                                                          
{'loss': 0.6369, 'learning_rate': 2.7708458595375185e-06, 'epoch': 11.44}

 95%|█████████▌| 26788/28080 [52:55:24<2:33:23,  7.12s/it]
 95%|█████████▌| 26789/28080 [52:55:32<2:33:54,  7.15s/it]
                                                          
{'loss': 0.6003, 'learning_rate': 2.7665662098599333e-06, 'epoch': 11.44}

 95%|█████████▌| 26789/28080 [52:55:32<2:33:54,  7.15s/it]
 95%|█████████▌| 26790/28080 [52:55:39<2:33:40,  7.15s/it]
                                                          
{'loss': 0.5946, 'learning_rate': 2.7622898493681325e-06, 'epoch': 11.44}

 95%|█████████▌| 26790/28080 [52:55:39<2:33:40,  7.15s/it]
 95%|█████████▌| 26791/28080 [52:55:46<2:32:57,  7.12s/it]
                                                          
{'loss': 0.6081, 'learning_rate': 2.758016778118988e-06, 'epoch': 11.44}

 95%|█████████▌| 26791/28080 [52:55:46<2:32:57,  7.12s/it]
 95%|█████████▌| 26792/28080 [52:55:53<2:32:58,  7.13s/it]
                                                          
{'loss': 0.6026, 'learning_rate': 2.753746996169371e-06, 'epoch': 11.45}

 95%|█████████▌| 26792/28080 [52:55:53<2:32:58,  7.13s/it]
 95%|█████████▌| 26793/28080 [52:56:00<2:33:11,  7.14s/it]
                                                          
{'loss': 0.594, 'learning_rate': 2.7494805035760686e-06, 'epoch': 11.45}

 95%|█████████▌| 26793/28080 [52:56:00<2:33:11,  7.14s/it]
 95%|█████████▌| 26794/28080 [52:56:07<2:33:11,  7.15s/it]
                                                          
{'loss': 0.5931, 'learning_rate': 2.745217300395869e-06, 'epoch': 11.45}

 95%|█████████▌| 26794/28080 [52:56:07<2:33:11,  7.15s/it]
 95%|█████████▌| 26795/28080 [52:56:14<2:33:21,  7.16s/it]
                                                          
{'loss': 0.6071, 'learning_rate': 2.7409573866854774e-06, 'epoch': 11.45}

 95%|█████████▌| 26795/28080 [52:56:14<2:33:21,  7.16s/it]
 95%|█████████▌| 26796/28080 [52:56:22<2:33:16,  7.16s/it]
                                                          
{'loss': 0.6102, 'learning_rate': 2.7367007625015426e-06, 'epoch': 11.45}

 95%|█████████▌| 26796/28080 [52:56:22<2:33:16,  7.16s/it]
 95%|█████████▌| 26797/28080 [52:56:29<2:33:13,  7.17s/it]
                                                          
{'loss': 0.6104, 'learning_rate': 2.7324474279007417e-06, 'epoch': 11.45}

 95%|█████████▌| 26797/28080 [52:56:29<2:33:13,  7.17s/it]
 95%|█████████▌| 26798/28080 [52:56:36<2:32:44,  7.15s/it]
                                                          
{'loss': 0.6116, 'learning_rate': 2.7281973829396124e-06, 'epoch': 11.45}

 95%|█████████▌| 26798/28080 [52:56:36<2:32:44,  7.15s/it]
 95%|█████████▌| 26799/28080 [52:56:43<2:32:12,  7.13s/it]
                                                          
{'loss': 0.5982, 'learning_rate': 2.7239506276747484e-06, 'epoch': 11.45}

 95%|█████████▌| 26799/28080 [52:56:43<2:32:12,  7.13s/it]
 95%|█████████▌| 26800/28080 [52:56:50<2:32:40,  7.16s/it]
                                                          
{'loss': 0.5967, 'learning_rate': 2.7197071621626044e-06, 'epoch': 11.45}

 95%|█████████▌| 26800/28080 [52:56:50<2:32:40,  7.16s/it]
 95%|█████████▌| 26801/28080 [52:56:57<2:32:22,  7.15s/it]
                                                          
{'loss': 0.6075, 'learning_rate': 2.7154669864596636e-06, 'epoch': 11.45}

 95%|█████████▌| 26801/28080 [52:56:57<2:32:22,  7.15s/it]
 95%|█████████▌| 26802/28080 [52:57:04<2:32:27,  7.16s/it]
                                                          
{'loss': 0.5846, 'learning_rate': 2.711230100622325e-06, 'epoch': 11.45}

 95%|█████████▌| 26802/28080 [52:57:04<2:32:27,  7.16s/it]
 95%|█████████▌| 26803/28080 [52:57:12<2:32:23,  7.16s/it]
                                                          
{'loss': 0.6293, 'learning_rate': 2.706996504706932e-06, 'epoch': 11.45}

 95%|█████████▌| 26803/28080 [52:57:12<2:32:23,  7.16s/it]
 95%|█████████▌| 26804/28080 [52:57:19<2:31:24,  7.12s/it]
                                                          
{'loss': 0.5924, 'learning_rate': 2.702766198769857e-06, 'epoch': 11.45}

 95%|█████████▌| 26804/28080 [52:57:19<2:31:24,  7.12s/it]
 95%|█████████▌| 26805/28080 [52:57:26<2:30:59,  7.11s/it]
                                                          
{'loss': 0.6022, 'learning_rate': 2.69853918286736e-06, 'epoch': 11.45}

 95%|█████████▌| 26805/28080 [52:57:26<2:30:59,  7.11s/it]
 95%|█████████▌| 26806/28080 [52:57:33<2:31:17,  7.13s/it]
                                                          
{'loss': 0.5816, 'learning_rate': 2.694315457055646e-06, 'epoch': 11.45}

 95%|█████████▌| 26806/28080 [52:57:33<2:31:17,  7.13s/it]
 95%|█████████▌| 26807/28080 [52:57:40<2:31:21,  7.13s/it]
                                                          
{'loss': 0.5982, 'learning_rate': 2.690095021390948e-06, 'epoch': 11.45}

 95%|█████████▌| 26807/28080 [52:57:40<2:31:21,  7.13s/it]
 95%|█████████▌| 26808/28080 [52:57:47<2:31:10,  7.13s/it]
                                                          
{'loss': 0.5965, 'learning_rate': 2.6858778759294157e-06, 'epoch': 11.45}

 95%|█████████▌| 26808/28080 [52:57:47<2:31:10,  7.13s/it]
 95%|█████████▌| 26809/28080 [52:57:54<2:30:53,  7.12s/it]
                                                          
{'loss': 0.584, 'learning_rate': 2.6816640207271147e-06, 'epoch': 11.45}

 95%|█████████▌| 26809/28080 [52:57:54<2:30:53,  7.12s/it]
 95%|█████████▌| 26810/28080 [52:58:01<2:30:48,  7.12s/it]
                                                          
{'loss': 0.5782, 'learning_rate': 2.6774534558401673e-06, 'epoch': 11.45}

 95%|█████████▌| 26810/28080 [52:58:01<2:30:48,  7.12s/it]
 95%|█████████▌| 26811/28080 [52:58:09<2:30:45,  7.13s/it]
                                                          
{'loss': 0.5898, 'learning_rate': 2.673246181324501e-06, 'epoch': 11.45}

 95%|█████████▌| 26811/28080 [52:58:09<2:30:45,  7.13s/it]
 95%|█████████▌| 26812/28080 [52:58:16<2:31:00,  7.15s/it]
                                                          
{'loss': 0.6104, 'learning_rate': 2.6690421972361543e-06, 'epoch': 11.45}

 95%|█████████▌| 26812/28080 [52:58:16<2:31:00,  7.15s/it]
 95%|█████████▌| 26813/28080 [52:58:23<2:30:32,  7.13s/it]
                                                          
{'loss': 0.595, 'learning_rate': 2.6648415036310546e-06, 'epoch': 11.45}

 95%|█████████▌| 26813/28080 [52:58:23<2:30:32,  7.13s/it]
 95%|█████████▌| 26814/28080 [52:58:30<2:30:32,  7.13s/it]
                                                          
{'loss': 0.5924, 'learning_rate': 2.6606441005651017e-06, 'epoch': 11.45}

 95%|█████████▌| 26814/28080 [52:58:30<2:30:32,  7.13s/it]
 95%|█████████▌| 26815/28080 [52:58:37<2:30:30,  7.14s/it]
                                                          
{'loss': 0.5976, 'learning_rate': 2.656449988094084e-06, 'epoch': 11.46}

 95%|█████████▌| 26815/28080 [52:58:37<2:30:30,  7.14s/it]
 95%|█████████▌| 26816/28080 [52:58:44<2:30:28,  7.14s/it]
                                                          
{'loss': 0.5959, 'learning_rate': 2.652259166273818e-06, 'epoch': 11.46}

 95%|█████████▌| 26816/28080 [52:58:44<2:30:28,  7.14s/it]
 96%|█████████▌| 26817/28080 [52:58:51<2:30:16,  7.14s/it]
                                                          
{'loss': 0.5973, 'learning_rate': 2.6480716351600933e-06, 'epoch': 11.46}

 96%|█████████▌| 26817/28080 [52:58:51<2:30:16,  7.14s/it]
 96%|█████████▌| 26818/28080 [52:58:58<2:29:28,  7.11s/it]
                                                          
{'loss': 0.62, 'learning_rate': 2.643887394808586e-06, 'epoch': 11.46}

 96%|█████████▌| 26818/28080 [52:58:58<2:29:28,  7.11s/it]
 96%|█████████▌| 26819/28080 [52:59:06<2:29:09,  7.10s/it]
                                                          
{'loss': 0.6061, 'learning_rate': 2.639706445274975e-06, 'epoch': 11.46}

 96%|█████████▌| 26819/28080 [52:59:06<2:29:09,  7.10s/it]
 96%|█████████▌| 26820/28080 [52:59:13<2:29:13,  7.11s/it]
                                                          
{'loss': 0.6131, 'learning_rate': 2.6355287866148824e-06, 'epoch': 11.46}

 96%|█████████▌| 26820/28080 [52:59:13<2:29:13,  7.11s/it]
 96%|█████████▌| 26821/28080 [52:59:20<2:29:37,  7.13s/it]
                                                          
{'loss': 0.611, 'learning_rate': 2.6313544188838746e-06, 'epoch': 11.46}

 96%|█████████▌| 26821/28080 [52:59:20<2:29:37,  7.13s/it]
 96%|█████████▌| 26822/28080 [52:59:27<2:29:37,  7.14s/it]
                                                          
{'loss': 0.6029, 'learning_rate': 2.627183342137518e-06, 'epoch': 11.46}

 96%|█████████▌| 26822/28080 [52:59:27<2:29:37,  7.14s/it]
 96%|█████████▌| 26823/28080 [52:59:34<2:29:17,  7.13s/it]
                                                          
{'loss': 0.6091, 'learning_rate': 2.6230155564312963e-06, 'epoch': 11.46}

 96%|█████████▌| 26823/28080 [52:59:34<2:29:17,  7.13s/it]
 96%|█████████▌| 26824/28080 [52:59:41<2:29:32,  7.14s/it]
                                                          
{'loss': 0.5775, 'learning_rate': 2.6188510618206376e-06, 'epoch': 11.46}

 96%|█████████▌| 26824/28080 [52:59:41<2:29:32,  7.14s/it]
 96%|█████████▌| 26825/28080 [52:59:48<2:29:32,  7.15s/it]
                                                          
{'loss': 0.5975, 'learning_rate': 2.6146898583609415e-06, 'epoch': 11.46}

 96%|█████████▌| 26825/28080 [52:59:48<2:29:32,  7.15s/it]
 96%|█████████▌| 26826/28080 [52:59:56<2:29:32,  7.16s/it]
                                                          
{'loss': 0.5855, 'learning_rate': 2.6105319461076082e-06, 'epoch': 11.46}

 96%|█████████▌| 26826/28080 [52:59:56<2:29:32,  7.16s/it]
 96%|█████████▌| 26827/28080 [53:00:03<2:29:29,  7.16s/it]
                                                          
{'loss': 0.6027, 'learning_rate': 2.6063773251158995e-06, 'epoch': 11.46}

 96%|█████████▌| 26827/28080 [53:00:03<2:29:29,  7.16s/it]
 96%|█████████▌| 26828/28080 [53:00:10<2:28:48,  7.13s/it]
                                                          
{'loss': 0.5865, 'learning_rate': 2.60222599544116e-06, 'epoch': 11.46}

 96%|█████████▌| 26828/28080 [53:00:10<2:28:48,  7.13s/it]
 96%|█████████▌| 26829/28080 [53:00:17<2:28:43,  7.13s/it]
                                                          
{'loss': 0.5888, 'learning_rate': 2.598077957138539e-06, 'epoch': 11.46}

 96%|█████████▌| 26829/28080 [53:00:17<2:28:43,  7.13s/it]
 96%|█████████▌| 26830/28080 [53:00:24<2:28:07,  7.11s/it]
                                                          
{'loss': 0.5973, 'learning_rate': 2.5939332102632716e-06, 'epoch': 11.46}

 96%|█████████▌| 26830/28080 [53:00:24<2:28:07,  7.11s/it]
 96%|█████████▌| 26831/28080 [53:00:31<2:27:52,  7.10s/it]
                                                          
{'loss': 0.5951, 'learning_rate': 2.5897917548704798e-06, 'epoch': 11.46}

 96%|█████████▌| 26831/28080 [53:00:31<2:27:52,  7.10s/it]
 96%|█████████▌| 26832/28080 [53:00:38<2:27:23,  7.09s/it]
                                                          
{'loss': 0.5913, 'learning_rate': 2.5856535910152855e-06, 'epoch': 11.46}

 96%|█████████▌| 26832/28080 [53:00:38<2:27:23,  7.09s/it]
 96%|█████████▌| 26833/28080 [53:00:45<2:27:10,  7.08s/it]
                                                          
{'loss': 0.6009, 'learning_rate': 2.581518718752729e-06, 'epoch': 11.46}

 96%|█████████▌| 26833/28080 [53:00:45<2:27:10,  7.08s/it]
 96%|█████████▌| 26834/28080 [53:00:52<2:27:28,  7.10s/it]
                                                          
{'loss': 0.5897, 'learning_rate': 2.577387138137821e-06, 'epoch': 11.46}

 96%|█████████▌| 26834/28080 [53:00:52<2:27:28,  7.10s/it]
 96%|█████████▌| 26835/28080 [53:00:59<2:27:00,  7.08s/it]
                                                          
{'loss': 0.6121, 'learning_rate': 2.5732588492255184e-06, 'epoch': 11.46}

 96%|█████████▌| 26835/28080 [53:00:59<2:27:00,  7.08s/it]
 96%|█████████▌| 26836/28080 [53:01:07<2:27:21,  7.11s/it]
                                                          
{'loss': 0.5847, 'learning_rate': 2.5691338520707485e-06, 'epoch': 11.46}

 96%|█████████▌| 26836/28080 [53:01:07<2:27:21,  7.11s/it]
 96%|█████████▌| 26837/28080 [53:01:14<2:26:47,  7.09s/it]
                                                          
{'loss': 0.6052, 'learning_rate': 2.565012146728385e-06, 'epoch': 11.46}

 96%|█████████▌| 26837/28080 [53:01:14<2:26:47,  7.09s/it]
 96%|█████████▌| 26838/28080 [53:01:21<2:27:09,  7.11s/it]
                                                          
{'loss': 0.5925, 'learning_rate': 2.5608937332533e-06, 'epoch': 11.46}

 96%|█████████▌| 26838/28080 [53:01:21<2:27:09,  7.11s/it]
 96%|█████████▌| 26839/28080 [53:01:28<2:27:55,  7.15s/it]
                                                          
{'loss': 0.6125, 'learning_rate': 2.556778611700228e-06, 'epoch': 11.47}

 96%|█████████▌| 26839/28080 [53:01:28<2:27:55,  7.15s/it]
 96%|█████████▌| 26840/28080 [53:01:35<2:27:28,  7.14s/it]
                                                          
{'loss': 0.5968, 'learning_rate': 2.5526667821239304e-06, 'epoch': 11.47}

 96%|█████████▌| 26840/28080 [53:01:35<2:27:28,  7.14s/it]
 96%|█████████▌| 26841/28080 [53:01:42<2:28:10,  7.18s/it]
                                                          
{'loss': 0.5819, 'learning_rate': 2.548558244579141e-06, 'epoch': 11.47}

 96%|█████████▌| 26841/28080 [53:01:42<2:28:10,  7.18s/it]
 96%|█████████▌| 26842/28080 [53:01:50<2:27:52,  7.17s/it]
                                                          
{'loss': 0.5863, 'learning_rate': 2.544452999120511e-06, 'epoch': 11.47}

 96%|█████████▌| 26842/28080 [53:01:50<2:27:52,  7.17s/it]
 96%|█████████▌| 26843/28080 [53:01:57<2:28:02,  7.18s/it]
                                                          
{'loss': 0.5744, 'learning_rate': 2.5403510458026637e-06, 'epoch': 11.47}

 96%|█████████▌| 26843/28080 [53:01:57<2:28:02,  7.18s/it]
 96%|█████████▌| 26844/28080 [53:02:04<2:27:04,  7.14s/it]
                                                          
{'loss': 0.5884, 'learning_rate': 2.53625238468011e-06, 'epoch': 11.47}

 96%|█████████▌| 26844/28080 [53:02:04<2:27:04,  7.14s/it]
 96%|█████████▌| 26845/28080 [53:02:11<2:26:41,  7.13s/it]
                                                          
{'loss': 0.5908, 'learning_rate': 2.5321570158074457e-06, 'epoch': 11.47}

 96%|█████████▌| 26845/28080 [53:02:11<2:26:41,  7.13s/it]
 96%|█████████▌| 26846/28080 [53:02:18<2:27:11,  7.16s/it]
                                                          
{'loss': 0.6045, 'learning_rate': 2.5280649392391275e-06, 'epoch': 11.47}

 96%|█████████▌| 26846/28080 [53:02:18<2:27:11,  7.16s/it]
 96%|█████████▌| 26847/28080 [53:02:25<2:26:19,  7.12s/it]
                                                          
{'loss': 0.5933, 'learning_rate': 2.5239761550296393e-06, 'epoch': 11.47}

 96%|█████████▌| 26847/28080 [53:02:25<2:26:19,  7.12s/it]
 96%|█████████▌| 26848/28080 [53:02:32<2:26:26,  7.13s/it]
                                                          
{'loss': 0.597, 'learning_rate': 2.5198906632332986e-06, 'epoch': 11.47}

 96%|█████████▌| 26848/28080 [53:02:32<2:26:26,  7.13s/it]
 96%|█████████▌| 26849/28080 [53:02:39<2:25:54,  7.11s/it]
                                                          
{'loss': 0.598, 'learning_rate': 2.5158084639045342e-06, 'epoch': 11.47}

 96%|█████████▌| 26849/28080 [53:02:39<2:25:54,  7.11s/it]
 96%|█████████▌| 26850/28080 [53:02:46<2:25:50,  7.11s/it]
                                                          
{'loss': 0.6081, 'learning_rate': 2.5117295570975807e-06, 'epoch': 11.47}

 96%|█████████▌| 26850/28080 [53:02:47<2:25:50,  7.11s/it]
 96%|█████████▌| 26851/28080 [53:02:54<2:25:28,  7.10s/it]
                                                          
{'loss': 0.6297, 'learning_rate': 2.5076539428667834e-06, 'epoch': 11.47}

 96%|█████████▌| 26851/28080 [53:02:54<2:25:28,  7.10s/it]
 96%|█████████▌| 26852/28080 [53:03:01<2:26:13,  7.14s/it]
                                                          
{'loss': 0.5919, 'learning_rate': 2.503581621266321e-06, 'epoch': 11.47}

 96%|█████████▌| 26852/28080 [53:03:01<2:26:13,  7.14s/it]
 96%|█████████▌| 26853/28080 [53:03:08<2:25:57,  7.14s/it]
                                                          
{'loss': 0.5785, 'learning_rate': 2.4995125923503725e-06, 'epoch': 11.47}

 96%|█████████▌| 26853/28080 [53:03:08<2:25:57,  7.14s/it]
 96%|█████████▌| 26854/28080 [53:03:15<2:25:57,  7.14s/it]
                                                          
{'loss': 0.5924, 'learning_rate': 2.4954468561730615e-06, 'epoch': 11.47}

 96%|█████████▌| 26854/28080 [53:03:15<2:25:57,  7.14s/it]
 96%|█████████▌| 26855/28080 [53:03:22<2:26:30,  7.18s/it]
                                                          
{'loss': 0.5946, 'learning_rate': 2.491384412788511e-06, 'epoch': 11.47}

 96%|█████████▌| 26855/28080 [53:03:22<2:26:30,  7.18s/it]
 96%|█████████▌| 26856/28080 [53:03:29<2:25:42,  7.14s/it]
                                                          
{'loss': 0.616, 'learning_rate': 2.4873252622507334e-06, 'epoch': 11.47}

 96%|█████████▌| 26856/28080 [53:03:29<2:25:42,  7.14s/it]
 96%|█████████▌| 26857/28080 [53:03:36<2:25:08,  7.12s/it]
                                                          
{'loss': 0.5961, 'learning_rate': 2.4832694046137973e-06, 'epoch': 11.47}

 96%|█████████▌| 26857/28080 [53:03:36<2:25:08,  7.12s/it]
 96%|█████████▌| 26858/28080 [53:03:44<2:25:14,  7.13s/it]
                                                          
{'loss': 0.5882, 'learning_rate': 2.479216839931575e-06, 'epoch': 11.47}

 96%|█████████▌| 26858/28080 [53:03:44<2:25:14,  7.13s/it]
 96%|█████████▌| 26859/28080 [53:03:51<2:24:59,  7.13s/it]
                                                          
{'loss': 0.5803, 'learning_rate': 2.4751675682579966e-06, 'epoch': 11.47}

 96%|█████████▌| 26859/28080 [53:03:51<2:24:59,  7.13s/it]
 96%|█████████▌| 26860/28080 [53:03:58<2:24:54,  7.13s/it]
                                                          
{'loss': 0.6188, 'learning_rate': 2.4711215896469907e-06, 'epoch': 11.47}

 96%|█████████▌| 26860/28080 [53:03:58<2:24:54,  7.13s/it]
 96%|█████████▌| 26861/28080 [53:04:05<2:24:42,  7.12s/it]
                                                          
{'loss': 0.5911, 'learning_rate': 2.467078904152348e-06, 'epoch': 11.47}

 96%|█████████▌| 26861/28080 [53:04:05<2:24:42,  7.12s/it]
 96%|█████████▌| 26862/28080 [53:04:12<2:24:51,  7.14s/it]
                                                          
{'loss': 0.5824, 'learning_rate': 2.463039511827858e-06, 'epoch': 11.48}

 96%|█████████▌| 26862/28080 [53:04:12<2:24:51,  7.14s/it]
 96%|█████████▌| 26863/28080 [53:04:19<2:24:21,  7.12s/it]
                                                          
{'loss': 0.6089, 'learning_rate': 2.459003412727229e-06, 'epoch': 11.48}

 96%|█████████▌| 26863/28080 [53:04:19<2:24:21,  7.12s/it]
 96%|█████████▌| 26864/28080 [53:04:26<2:24:08,  7.11s/it]
                                                          
{'loss': 0.6023, 'learning_rate': 2.454970606904222e-06, 'epoch': 11.48}

 96%|█████████▌| 26864/28080 [53:04:26<2:24:08,  7.11s/it]
 96%|█████████▌| 26865/28080 [53:04:33<2:24:00,  7.11s/it]
                                                          
{'loss': 0.5863, 'learning_rate': 2.4509410944124342e-06, 'epoch': 11.48}

 96%|█████████▌| 26865/28080 [53:04:33<2:24:00,  7.11s/it]
 96%|█████████▌| 26866/28080 [53:04:41<2:23:55,  7.11s/it]
                                                          
{'loss': 0.6023, 'learning_rate': 2.4469148753054893e-06, 'epoch': 11.48}

 96%|█████████▌| 26866/28080 [53:04:41<2:23:55,  7.11s/it]
 96%|█████████▌| 26867/28080 [53:04:48<2:24:07,  7.13s/it]
                                                          
{'loss': 0.5953, 'learning_rate': 2.442891949636955e-06, 'epoch': 11.48}

 96%|█████████▌| 26867/28080 [53:04:48<2:24:07,  7.13s/it]
 96%|█████████▌| 26868/28080 [53:04:55<2:23:04,  7.08s/it]
                                                          
{'loss': 0.6113, 'learning_rate': 2.438872317460372e-06, 'epoch': 11.48}

 96%|█████████▌| 26868/28080 [53:04:55<2:23:04,  7.08s/it]
 96%|█████████▌| 26869/28080 [53:05:02<2:23:18,  7.10s/it]
                                                          
{'loss': 0.6095, 'learning_rate': 2.4348559788291702e-06, 'epoch': 11.48}

 96%|█████████▌| 26869/28080 [53:05:02<2:23:18,  7.10s/it]
 96%|█████████▌| 26870/28080 [53:05:09<2:22:39,  7.07s/it]
                                                          
{'loss': 0.5966, 'learning_rate': 2.4308429337968343e-06, 'epoch': 11.48}

 96%|█████████▌| 26870/28080 [53:05:09<2:22:39,  7.07s/it]
 96%|█████████▌| 26871/28080 [53:05:16<2:23:03,  7.10s/it]
                                                          
{'loss': 0.6092, 'learning_rate': 2.4268331824167378e-06, 'epoch': 11.48}

 96%|█████████▌| 26871/28080 [53:05:16<2:23:03,  7.10s/it]
 96%|█████████▌| 26872/28080 [53:05:23<2:23:18,  7.12s/it]
                                                          
{'loss': 0.6021, 'learning_rate': 2.4228267247421998e-06, 'epoch': 11.48}

 96%|█████████▌| 26872/28080 [53:05:23<2:23:18,  7.12s/it]
 96%|█████████▌| 26873/28080 [53:05:30<2:23:06,  7.11s/it]
                                                          
{'loss': 0.603, 'learning_rate': 2.4188235608265385e-06, 'epoch': 11.48}

 96%|█████████▌| 26873/28080 [53:05:30<2:23:06,  7.11s/it]
 96%|█████████▌| 26874/28080 [53:05:37<2:22:51,  7.11s/it]
                                                          
{'loss': 0.5898, 'learning_rate': 2.414823690723017e-06, 'epoch': 11.48}

 96%|█████████▌| 26874/28080 [53:05:37<2:22:51,  7.11s/it]
 96%|█████████▌| 26875/28080 [53:05:44<2:22:48,  7.11s/it]
                                                          
{'loss': 0.5916, 'learning_rate': 2.4108271144848427e-06, 'epoch': 11.48}

 96%|█████████▌| 26875/28080 [53:05:44<2:22:48,  7.11s/it]
 96%|█████████▌| 26876/28080 [53:05:52<2:22:07,  7.08s/it]
                                                          
{'loss': 0.6027, 'learning_rate': 2.406833832165223e-06, 'epoch': 11.48}

 96%|█████████▌| 26876/28080 [53:05:52<2:22:07,  7.08s/it]
 96%|█████████▌| 26877/28080 [53:05:59<2:22:54,  7.13s/it]
                                                          
{'loss': 0.602, 'learning_rate': 2.4028438438171983e-06, 'epoch': 11.48}

 96%|█████████▌| 26877/28080 [53:05:59<2:22:54,  7.13s/it]
 96%|█████████▌| 26878/28080 [53:06:06<2:23:14,  7.15s/it]
                                                          
{'loss': 0.599, 'learning_rate': 2.3988571494939493e-06, 'epoch': 11.48}

 96%|█████████▌| 26878/28080 [53:06:06<2:23:14,  7.15s/it]
 96%|█████████▌| 26879/28080 [53:06:13<2:23:03,  7.15s/it]
                                                          
{'loss': 0.6007, 'learning_rate': 2.3948737492484327e-06, 'epoch': 11.48}

 96%|█████████▌| 26879/28080 [53:06:13<2:23:03,  7.15s/it]
 96%|█████████▌| 26880/28080 [53:06:20<2:22:35,  7.13s/it]
                                                          
{'loss': 0.6071, 'learning_rate': 2.390893643133718e-06, 'epoch': 11.48}

 96%|█████████▌| 26880/28080 [53:06:20<2:22:35,  7.13s/it]
 96%|█████████▌| 26881/28080 [53:06:27<2:22:24,  7.13s/it]
                                                          
{'loss': 0.5825, 'learning_rate': 2.3869168312027066e-06, 'epoch': 11.48}

 96%|█████████▌| 26881/28080 [53:06:27<2:22:24,  7.13s/it]
 96%|█████████▌| 26882/28080 [53:06:34<2:22:41,  7.15s/it]
                                                          
{'loss': 0.5685, 'learning_rate': 2.382943313508301e-06, 'epoch': 11.48}

 96%|█████████▌| 26882/28080 [53:06:34<2:22:41,  7.15s/it]
 96%|█████████▌| 26883/28080 [53:06:42<2:22:18,  7.13s/it]
                                                          
{'loss': 0.5863, 'learning_rate': 2.3789730901034033e-06, 'epoch': 11.48}

 96%|█████████▌| 26883/28080 [53:06:42<2:22:18,  7.13s/it]
 96%|█████████▌| 26884/28080 [53:06:49<2:22:17,  7.14s/it]
                                                          
{'loss': 0.5777, 'learning_rate': 2.375006161040805e-06, 'epoch': 11.48}

 96%|█████████▌| 26884/28080 [53:06:49<2:22:17,  7.14s/it]
 96%|█████████▌| 26885/28080 [53:06:56<2:21:20,  7.10s/it]
                                                          
{'loss': 0.5826, 'learning_rate': 2.371042526373296e-06, 'epoch': 11.49}

 96%|█████████▌| 26885/28080 [53:06:56<2:21:20,  7.10s/it]
 96%|█████████▌| 26886/28080 [53:07:03<2:21:04,  7.09s/it]
                                                          
{'loss': 0.5956, 'learning_rate': 2.367082186153585e-06, 'epoch': 11.49}

 96%|█████████▌| 26886/28080 [53:07:03<2:21:04,  7.09s/it]
 96%|█████████▌| 26887/28080 [53:07:10<2:21:04,  7.10s/it]
                                                          
{'loss': 0.5961, 'learning_rate': 2.363125140434408e-06, 'epoch': 11.49}

 96%|█████████▌| 26887/28080 [53:07:10<2:21:04,  7.10s/it]
 96%|█████████▌| 26888/28080 [53:07:17<2:21:21,  7.11s/it]
                                                          
{'loss': 0.6012, 'learning_rate': 2.359171389268333e-06, 'epoch': 11.49}

 96%|█████████▌| 26888/28080 [53:07:17<2:21:21,  7.11s/it]
 96%|█████████▌| 26889/28080 [53:07:24<2:21:30,  7.13s/it]
                                                          
{'loss': 0.6325, 'learning_rate': 2.355220932708041e-06, 'epoch': 11.49}

 96%|█████████▌| 26889/28080 [53:07:24<2:21:30,  7.13s/it]
 96%|█████████▌| 26890/28080 [53:07:31<2:21:17,  7.12s/it]
                                                          
{'loss': 0.6035, 'learning_rate': 2.3512737708060448e-06, 'epoch': 11.49}

 96%|█████████▌| 26890/28080 [53:07:31<2:21:17,  7.12s/it]
 96%|█████████▌| 26891/28080 [53:07:38<2:20:55,  7.11s/it]
                                                          
{'loss': 0.583, 'learning_rate': 2.347329903614859e-06, 'epoch': 11.49}

 96%|█████████▌| 26891/28080 [53:07:38<2:20:55,  7.11s/it]
 96%|█████████▌| 26892/28080 [53:07:46<2:21:09,  7.13s/it]
                                                          
{'loss': 0.5906, 'learning_rate': 2.343389331186968e-06, 'epoch': 11.49}

 96%|█████████▌| 26892/28080 [53:07:46<2:21:09,  7.13s/it]
 96%|█████████▌| 26893/28080 [53:07:53<2:20:38,  7.11s/it]
                                                          
{'loss': 0.6119, 'learning_rate': 2.339452053574775e-06, 'epoch': 11.49}

 96%|█████████▌| 26893/28080 [53:07:53<2:20:38,  7.11s/it]
 96%|█████████▌| 26894/28080 [53:08:00<2:20:39,  7.12s/it]
                                                          
{'loss': 0.5967, 'learning_rate': 2.3355180708306835e-06, 'epoch': 11.49}

 96%|█████████▌| 26894/28080 [53:08:00<2:20:39,  7.12s/it]
 96%|█████████▌| 26895/28080 [53:08:07<2:20:27,  7.11s/it]
                                                          
{'loss': 0.5916, 'learning_rate': 2.3315873830070112e-06, 'epoch': 11.49}

 96%|█████████▌| 26895/28080 [53:08:07<2:20:27,  7.11s/it]
 96%|█████████▌| 26896/28080 [53:08:14<2:19:51,  7.09s/it]
                                                          
{'loss': 0.6128, 'learning_rate': 2.327659990156078e-06, 'epoch': 11.49}

 96%|█████████▌| 26896/28080 [53:08:14<2:19:51,  7.09s/it]
 96%|█████████▌| 26897/28080 [53:08:21<2:20:01,  7.10s/it]
                                                          
{'loss': 0.5777, 'learning_rate': 2.3237358923301477e-06, 'epoch': 11.49}

 96%|█████████▌| 26897/28080 [53:08:21<2:20:01,  7.10s/it]
 96%|█████████▌| 26898/28080 [53:08:28<2:19:25,  7.08s/it]
                                                          
{'loss': 0.6267, 'learning_rate': 2.319815089581345e-06, 'epoch': 11.49}

 96%|█████████▌| 26898/28080 [53:08:28<2:19:25,  7.08s/it]
 96%|█████████▌| 26899/28080 [53:08:35<2:19:32,  7.09s/it]
                                                          
{'loss': 0.5937, 'learning_rate': 2.3158975819619064e-06, 'epoch': 11.49}

 96%|█████████▌| 26899/28080 [53:08:35<2:19:32,  7.09s/it]
 96%|█████████▌| 26900/28080 [53:08:42<2:19:11,  7.08s/it]
                                                          
{'loss': 0.6087, 'learning_rate': 2.311983369523929e-06, 'epoch': 11.49}

 96%|█████████▌| 26900/28080 [53:08:42<2:19:11,  7.08s/it]
 96%|█████████▌| 26901/28080 [53:08:49<2:19:35,  7.10s/it]
                                                          
{'loss': 0.5971, 'learning_rate': 2.3080724523195097e-06, 'epoch': 11.49}

 96%|█████████▌| 26901/28080 [53:08:49<2:19:35,  7.10s/it]
 96%|█████████▌| 26902/28080 [53:08:57<2:19:54,  7.13s/it]
                                                          
{'loss': 0.6014, 'learning_rate': 2.3041648304006347e-06, 'epoch': 11.49}

 96%|█████████▌| 26902/28080 [53:08:57<2:19:54,  7.13s/it]
 96%|█████████▌| 26903/28080 [53:09:04<2:19:46,  7.13s/it]
                                                          
{'loss': 0.6078, 'learning_rate': 2.3002605038193182e-06, 'epoch': 11.49}

 96%|█████████▌| 26903/28080 [53:09:04<2:19:46,  7.13s/it]
 96%|█████████▌| 26904/28080 [53:09:11<2:19:50,  7.13s/it]
                                                          
{'loss': 0.6129, 'learning_rate': 2.2963594726274906e-06, 'epoch': 11.49}

 96%|█████████▌| 26904/28080 [53:09:11<2:19:50,  7.13s/it]
 96%|█████████▌| 26905/28080 [53:09:18<2:20:05,  7.15s/it]
                                                          
{'loss': 0.58, 'learning_rate': 2.292461736877055e-06, 'epoch': 11.49}

 96%|█████████▌| 26905/28080 [53:09:18<2:20:05,  7.15s/it]
 96%|█████████▌| 26906/28080 [53:09:25<2:19:56,  7.15s/it]
                                                          
{'loss': 0.6063, 'learning_rate': 2.2885672966198866e-06, 'epoch': 11.49}

 96%|█████████▌| 26906/28080 [53:09:25<2:19:56,  7.15s/it]
 96%|█████████▌| 26907/28080 [53:09:32<2:20:02,  7.16s/it]
                                                          
{'loss': 0.5809, 'learning_rate': 2.2846761519077774e-06, 'epoch': 11.49}

 96%|█████████▌| 26907/28080 [53:09:32<2:20:02,  7.16s/it]
 96%|█████████▌| 26908/28080 [53:09:40<2:20:15,  7.18s/it]
                                                          
{'loss': 0.5977, 'learning_rate': 2.280788302792491e-06, 'epoch': 11.49}

 96%|█████████▌| 26908/28080 [53:09:40<2:20:15,  7.18s/it]
 96%|█████████▌| 26909/28080 [53:09:47<2:20:14,  7.19s/it]
                                                          
{'loss': 0.5823, 'learning_rate': 2.2769037493257372e-06, 'epoch': 11.5}

 96%|█████████▌| 26909/28080 [53:09:47<2:20:14,  7.19s/it]
 96%|█████████▌| 26910/28080 [53:09:54<2:20:38,  7.21s/it]
                                                          
{'loss': 0.6185, 'learning_rate': 2.273022491559279e-06, 'epoch': 11.5}

 96%|█████████▌| 26910/28080 [53:09:54<2:20:38,  7.21s/it]
 96%|█████████▌| 26911/28080 [53:10:01<2:19:41,  7.17s/it]
                                                          
{'loss': 0.6384, 'learning_rate': 2.2691445295446312e-06, 'epoch': 11.5}

 96%|█████████▌| 26911/28080 [53:10:01<2:19:41,  7.17s/it]
 96%|█████████▌| 26912/28080 [53:10:08<2:19:19,  7.16s/it]
                                                          
{'loss': 0.6139, 'learning_rate': 2.2652698633334745e-06, 'epoch': 11.5}

 96%|█████████▌| 26912/28080 [53:10:08<2:19:19,  7.16s/it]
 96%|█████████▌| 26913/28080 [53:10:15<2:19:12,  7.16s/it]
                                                          
{'loss': 0.5868, 'learning_rate': 2.2613984929772957e-06, 'epoch': 11.5}

 96%|█████████▌| 26913/28080 [53:10:15<2:19:12,  7.16s/it]
 96%|█████████▌| 26914/28080 [53:10:23<2:18:33,  7.13s/it]
                                                          
{'loss': 0.6134, 'learning_rate': 2.2575304185276647e-06, 'epoch': 11.5}

 96%|█████████▌| 26914/28080 [53:10:23<2:18:33,  7.13s/it]
 96%|█████████▌| 26915/28080 [53:10:30<2:18:04,  7.11s/it]
                                                          
{'loss': 0.5809, 'learning_rate': 2.2536656400360124e-06, 'epoch': 11.5}

 96%|█████████▌| 26915/28080 [53:10:30<2:18:04,  7.11s/it]
 96%|█████████▌| 26916/28080 [53:10:37<2:18:23,  7.13s/it]
                                                          
{'loss': 0.6031, 'learning_rate': 2.249804157553742e-06, 'epoch': 11.5}

 96%|█████████▌| 26916/28080 [53:10:37<2:18:23,  7.13s/it]
 96%|█████████▌| 26917/28080 [53:10:44<2:18:46,  7.16s/it]
                                                          
{'loss': 0.6026, 'learning_rate': 2.2459459711322294e-06, 'epoch': 11.5}

 96%|█████████▌| 26917/28080 [53:10:44<2:18:46,  7.16s/it]
 96%|█████████▌| 26918/28080 [53:10:51<2:19:00,  7.18s/it]
                                                          
{'loss': 0.588, 'learning_rate': 2.242091080822822e-06, 'epoch': 11.5}

 96%|█████████▌| 26918/28080 [53:10:51<2:19:00,  7.18s/it]
 96%|█████████▌| 26919/28080 [53:10:58<2:18:21,  7.15s/it]
                                                          
{'loss': 0.6008, 'learning_rate': 2.238239486676813e-06, 'epoch': 11.5}

 96%|█████████▌| 26919/28080 [53:10:58<2:18:21,  7.15s/it]
 96%|█████████▌| 26920/28080 [53:11:05<2:18:00,  7.14s/it]
                                                          
{'loss': 0.592, 'learning_rate': 2.2343911887454105e-06, 'epoch': 11.5}

 96%|█████████▌| 26920/28080 [53:11:05<2:18:00,  7.14s/it]
 96%|█████████▌| 26921/28080 [53:11:12<2:17:18,  7.11s/it]
                                                          
{'loss': 0.6087, 'learning_rate': 2.230546187079796e-06, 'epoch': 11.5}

 96%|█████████▌| 26921/28080 [53:11:12<2:17:18,  7.11s/it]
 96%|█████████▌| 26922/28080 [53:11:20<2:17:02,  7.10s/it]
                                                          
{'loss': 0.5985, 'learning_rate': 2.2267044817312065e-06, 'epoch': 11.5}

 96%|█████████▌| 26922/28080 [53:11:20<2:17:02,  7.10s/it]
 96%|█████████▌| 26923/28080 [53:11:27<2:16:53,  7.10s/it]
                                                          
{'loss': 0.5927, 'learning_rate': 2.2228660727506568e-06, 'epoch': 11.5}

 96%|█████████▌| 26923/28080 [53:11:27<2:16:53,  7.10s/it]
 96%|█████████▌| 26924/28080 [53:11:34<2:16:48,  7.10s/it]
                                                          
{'loss': 0.5872, 'learning_rate': 2.2190309601893e-06, 'epoch': 11.5}

 96%|█████████▌| 26924/28080 [53:11:34<2:16:48,  7.10s/it]
 96%|█████████▌| 26925/28080 [53:11:41<2:16:08,  7.07s/it]
                                                          
{'loss': 0.5979, 'learning_rate': 2.2151991440980956e-06, 'epoch': 11.5}

 96%|█████████▌| 26925/28080 [53:11:41<2:16:08,  7.07s/it]
 96%|█████████▌| 26926/28080 [53:11:48<2:16:35,  7.10s/it]
                                                          
{'loss': 0.6002, 'learning_rate': 2.211370624528031e-06, 'epoch': 11.5}

 96%|█████████▌| 26926/28080 [53:11:48<2:16:35,  7.10s/it]
 96%|█████████▌| 26927/28080 [53:11:55<2:16:19,  7.09s/it]
                                                          
{'loss': 0.6064, 'learning_rate': 2.2075454015300367e-06, 'epoch': 11.5}

 96%|█████████▌| 26927/28080 [53:11:55<2:16:19,  7.09s/it]
 96%|█████████▌| 26928/28080 [53:12:02<2:16:11,  7.09s/it]
                                                          
{'loss': 0.6213, 'learning_rate': 2.203723475155045e-06, 'epoch': 11.5}

 96%|█████████▌| 26928/28080 [53:12:02<2:16:11,  7.09s/it]
 96%|█████████▌| 26929/28080 [53:12:09<2:16:12,  7.10s/it]
                                                          
{'loss': 0.6116, 'learning_rate': 2.1999048454538763e-06, 'epoch': 11.5}

 96%|█████████▌| 26929/28080 [53:12:09<2:16:12,  7.10s/it]
 96%|█████████▌| 26930/28080 [53:12:16<2:16:05,  7.10s/it]
                                                          
{'loss': 0.5968, 'learning_rate': 2.1960895124773226e-06, 'epoch': 11.5}

 96%|█████████▌| 26930/28080 [53:12:16<2:16:05,  7.10s/it]
 96%|█████████▌| 26931/28080 [53:12:23<2:15:58,  7.10s/it]
                                                          
{'loss': 0.5707, 'learning_rate': 2.19227747627615e-06, 'epoch': 11.5}

 96%|█████████▌| 26931/28080 [53:12:23<2:15:58,  7.10s/it]
 96%|█████████▌| 26932/28080 [53:12:30<2:15:48,  7.10s/it]
                                                          
{'loss': 0.6147, 'learning_rate': 2.188468736901095e-06, 'epoch': 11.51}

 96%|█████████▌| 26932/28080 [53:12:30<2:15:48,  7.10s/it]
 96%|█████████▌| 26933/28080 [53:12:38<2:15:44,  7.10s/it]
                                                          
{'loss': 0.6205, 'learning_rate': 2.1846632944027833e-06, 'epoch': 11.51}

 96%|█████████▌| 26933/28080 [53:12:38<2:15:44,  7.10s/it]
 96%|█████████▌| 26934/28080 [53:12:45<2:16:14,  7.13s/it]
                                                          
{'loss': 0.5984, 'learning_rate': 2.1808611488318976e-06, 'epoch': 11.51}

 96%|█████████▌| 26934/28080 [53:12:45<2:16:14,  7.13s/it]
 96%|█████████▌| 26935/28080 [53:12:52<2:16:12,  7.14s/it]
                                                          
{'loss': 0.586, 'learning_rate': 2.17706230023898e-06, 'epoch': 11.51}

 96%|█████████▌| 26935/28080 [53:12:52<2:16:12,  7.14s/it]
 96%|█████████▌| 26936/28080 [53:12:59<2:15:36,  7.11s/it]
                                                          
{'loss': 0.6289, 'learning_rate': 2.1732667486745737e-06, 'epoch': 11.51}

 96%|█████████▌| 26936/28080 [53:12:59<2:15:36,  7.11s/it]
 96%|█████████▌| 26937/28080 [53:13:06<2:15:46,  7.13s/it]
                                                          
{'loss': 0.605, 'learning_rate': 2.1694744941891943e-06, 'epoch': 11.51}

 96%|█████████▌| 26937/28080 [53:13:06<2:15:46,  7.13s/it]
 96%|█████████▌| 26938/28080 [53:13:13<2:15:48,  7.13s/it]
                                                          
{'loss': 0.6011, 'learning_rate': 2.1656855368333008e-06, 'epoch': 11.51}

 96%|█████████▌| 26938/28080 [53:13:13<2:15:48,  7.13s/it]
 96%|█████████▌| 26939/28080 [53:13:20<2:15:44,  7.14s/it]
                                                          
{'loss': 0.6315, 'learning_rate': 2.1618998766572696e-06, 'epoch': 11.51}

 96%|█████████▌| 26939/28080 [53:13:20<2:15:44,  7.14s/it]
 96%|█████████▌| 26940/28080 [53:13:28<2:15:20,  7.12s/it]
                                                          
{'loss': 0.5993, 'learning_rate': 2.1581175137114772e-06, 'epoch': 11.51}

 96%|█████████▌| 26940/28080 [53:13:28<2:15:20,  7.12s/it]
 96%|█████████▌| 26941/28080 [53:13:35<2:15:25,  7.13s/it]
                                                          
{'loss': 0.6049, 'learning_rate': 2.1543384480462446e-06, 'epoch': 11.51}

 96%|█████████▌| 26941/28080 [53:13:35<2:15:25,  7.13s/it]
 96%|█████████▌| 26942/28080 [53:13:42<2:15:10,  7.13s/it]
                                                          
{'loss': 0.5784, 'learning_rate': 2.150562679711837e-06, 'epoch': 11.51}

 96%|█████████▌| 26942/28080 [53:13:42<2:15:10,  7.13s/it]
 96%|█████████▌| 26943/28080 [53:13:49<2:15:27,  7.15s/it]
                                                          
{'loss': 0.5965, 'learning_rate': 2.14679020875852e-06, 'epoch': 11.51}

 96%|█████████▌| 26943/28080 [53:13:49<2:15:27,  7.15s/it]
 96%|█████████▌| 26944/28080 [53:13:56<2:15:10,  7.14s/it]
                                                          
{'loss': 0.5887, 'learning_rate': 2.1430210352364753e-06, 'epoch': 11.51}

 96%|█████████▌| 26944/28080 [53:13:56<2:15:10,  7.14s/it]
 96%|█████████▌| 26945/28080 [53:14:03<2:14:22,  7.10s/it]
                                                          
{'loss': 0.5955, 'learning_rate': 2.13925515919583e-06, 'epoch': 11.51}

 96%|█████████▌| 26945/28080 [53:14:03<2:14:22,  7.10s/it]
 96%|█████████▌| 26946/28080 [53:14:10<2:14:23,  7.11s/it]
                                                          
{'loss': 0.6149, 'learning_rate': 2.135492580686682e-06, 'epoch': 11.51}

 96%|█████████▌| 26946/28080 [53:14:10<2:14:23,  7.11s/it]
 96%|█████████▌| 26947/28080 [53:14:17<2:13:43,  7.08s/it]
                                                          
{'loss': 0.5909, 'learning_rate': 2.1317332997591034e-06, 'epoch': 11.51}

 96%|█████████▌| 26947/28080 [53:14:17<2:13:43,  7.08s/it]
 96%|█████████▌| 26948/28080 [53:14:24<2:14:02,  7.10s/it]
                                                          
{'loss': 0.622, 'learning_rate': 2.127977316463081e-06, 'epoch': 11.51}

 96%|█████████▌| 26948/28080 [53:14:24<2:14:02,  7.10s/it]
 96%|█████████▌| 26949/28080 [53:14:32<2:14:04,  7.11s/it]
                                                          
{'loss': 0.5982, 'learning_rate': 2.1242246308486314e-06, 'epoch': 11.51}

 96%|█████████▌| 26949/28080 [53:14:32<2:14:04,  7.11s/it]
 96%|█████████▌| 26950/28080 [53:14:39<2:13:37,  7.10s/it]
                                                          
{'loss': 0.59, 'learning_rate': 2.1204752429656303e-06, 'epoch': 11.51}

 96%|█████████▌| 26950/28080 [53:14:39<2:13:37,  7.10s/it]
 96%|█████████▌| 26951/28080 [53:14:46<2:13:57,  7.12s/it]
                                                          
{'loss': 0.5933, 'learning_rate': 2.1167291528640107e-06, 'epoch': 11.51}

 96%|█████████▌| 26951/28080 [53:14:46<2:13:57,  7.12s/it]
 96%|█████████▌| 26952/28080 [53:14:53<2:13:58,  7.13s/it]
                                                          
{'loss': 0.6138, 'learning_rate': 2.1129863605935664e-06, 'epoch': 11.51}

 96%|█████████▌| 26952/28080 [53:14:53<2:13:58,  7.13s/it]
 96%|█████████▌| 26953/28080 [53:15:00<2:14:06,  7.14s/it]
                                                          
{'loss': 0.6051, 'learning_rate': 2.1092468662041176e-06, 'epoch': 11.51}

 96%|█████████▌| 26953/28080 [53:15:00<2:14:06,  7.14s/it]
 96%|█████████▌| 26954/28080 [53:15:07<2:13:43,  7.13s/it]
                                                          
{'loss': 0.6017, 'learning_rate': 2.105510669745403e-06, 'epoch': 11.51}

 96%|█████████▌| 26954/28080 [53:15:07<2:13:43,  7.13s/it]
 96%|█████████▌| 26955/28080 [53:15:14<2:13:50,  7.14s/it]
                                                          
{'loss': 0.593, 'learning_rate': 2.101777771267105e-06, 'epoch': 11.51}

 96%|█████████▌| 26955/28080 [53:15:14<2:13:50,  7.14s/it]
 96%|█████████▌| 26956/28080 [53:15:22<2:13:41,  7.14s/it]
                                                          
{'loss': 0.5902, 'learning_rate': 2.0980481708189336e-06, 'epoch': 11.52}

 96%|█████████▌| 26956/28080 [53:15:22<2:13:41,  7.14s/it]
 96%|█████████▌| 26957/28080 [53:15:29<2:14:02,  7.16s/it]
                                                          
{'loss': 0.622, 'learning_rate': 2.0943218684504883e-06, 'epoch': 11.52}

 96%|█████████▌| 26957/28080 [53:15:29<2:14:02,  7.16s/it]
 96%|█████████▌| 26958/28080 [53:15:36<2:14:04,  7.17s/it]
                                                          
{'loss': 0.6036, 'learning_rate': 2.0905988642113403e-06, 'epoch': 11.52}

 96%|█████████▌| 26958/28080 [53:15:36<2:14:04,  7.17s/it]
 96%|█████████▌| 26959/28080 [53:15:43<2:13:38,  7.15s/it]
                                                          
{'loss': 0.5848, 'learning_rate': 2.086879158151006e-06, 'epoch': 11.52}

 96%|█████████▌| 26959/28080 [53:15:43<2:13:38,  7.15s/it]
 96%|█████████▌| 26960/28080 [53:15:50<2:13:46,  7.17s/it]
                                                          
{'loss': 0.5954, 'learning_rate': 2.083162750319001e-06, 'epoch': 11.52}

 96%|█████████▌| 26960/28080 [53:15:50<2:13:46,  7.17s/it]
 96%|█████████▌| 26961/28080 [53:15:57<2:13:58,  7.18s/it]
                                                          
{'loss': 0.5941, 'learning_rate': 2.0794496407647577e-06, 'epoch': 11.52}

 96%|█████████▌| 26961/28080 [53:15:57<2:13:58,  7.18s/it]
 96%|█████████▌| 26962/28080 [53:16:05<2:13:42,  7.18s/it]
                                                          
{'loss': 0.596, 'learning_rate': 2.075739829537654e-06, 'epoch': 11.52}

 96%|█████████▌| 26962/28080 [53:16:05<2:13:42,  7.18s/it]
 96%|█████████▌| 26963/28080 [53:16:12<2:13:59,  7.20s/it]
                                                          
{'loss': 0.5927, 'learning_rate': 2.0720333166870665e-06, 'epoch': 11.52}

 96%|█████████▌| 26963/28080 [53:16:12<2:13:59,  7.20s/it]
 96%|█████████▌| 26964/28080 [53:16:19<2:13:12,  7.16s/it]
                                                          
{'loss': 0.6002, 'learning_rate': 2.0683301022623167e-06, 'epoch': 11.52}

 96%|█████████▌| 26964/28080 [53:16:19<2:13:12,  7.16s/it]
 96%|█████████▌| 26965/28080 [53:16:26<2:12:40,  7.14s/it]
                                                          
{'loss': 0.5932, 'learning_rate': 2.064630186312644e-06, 'epoch': 11.52}

 96%|█████████▌| 26965/28080 [53:16:26<2:12:40,  7.14s/it]
 96%|█████████▌| 26966/28080 [53:16:33<2:12:39,  7.15s/it]
                                                          
{'loss': 0.5957, 'learning_rate': 2.0609335688872855e-06, 'epoch': 11.52}

 96%|█████████▌| 26966/28080 [53:16:33<2:12:39,  7.15s/it]
 96%|█████████▌| 26967/28080 [53:16:40<2:12:38,  7.15s/it]
                                                          
{'loss': 0.5972, 'learning_rate': 2.0572402500354526e-06, 'epoch': 11.52}

 96%|█████████▌| 26967/28080 [53:16:40<2:12:38,  7.15s/it]
 96%|█████████▌| 26968/28080 [53:16:48<2:12:25,  7.15s/it]
                                                          
{'loss': 0.5952, 'learning_rate': 2.053550229806217e-06, 'epoch': 11.52}

 96%|█████████▌| 26968/28080 [53:16:48<2:12:25,  7.15s/it]
 96%|█████████▌| 26969/28080 [53:16:55<2:11:38,  7.11s/it]
                                                          
{'loss': 0.6212, 'learning_rate': 2.049863508248706e-06, 'epoch': 11.52}

 96%|█████████▌| 26969/28080 [53:16:55<2:11:38,  7.11s/it]
 96%|█████████▌| 26970/28080 [53:17:02<2:11:22,  7.10s/it]
                                                          
{'loss': 0.5897, 'learning_rate': 2.046180085411964e-06, 'epoch': 11.52}

 96%|█████████▌| 26970/28080 [53:17:02<2:11:22,  7.10s/it]
 96%|█████████▌| 26971/28080 [53:17:09<2:11:32,  7.12s/it]
                                                          
{'loss': 0.6127, 'learning_rate': 2.0424999613450068e-06, 'epoch': 11.52}

 96%|█████████▌| 26971/28080 [53:17:09<2:11:32,  7.12s/it]
 96%|█████████▌| 26972/28080 [53:17:16<2:10:56,  7.09s/it]
                                                          
{'loss': 0.6028, 'learning_rate': 2.038823136096796e-06, 'epoch': 11.52}

 96%|█████████▌| 26972/28080 [53:17:16<2:10:56,  7.09s/it]
 96%|█████████▌| 26973/28080 [53:17:23<2:10:25,  7.07s/it]
                                                          
{'loss': 0.6034, 'learning_rate': 2.035149609716208e-06, 'epoch': 11.52}

 96%|█████████▌| 26973/28080 [53:17:23<2:10:25,  7.07s/it]
 96%|█████████▌| 26974/28080 [53:17:30<2:10:37,  7.09s/it]
                                                          
{'loss': 0.6039, 'learning_rate': 2.0314793822521493e-06, 'epoch': 11.52}

 96%|█████████▌| 26974/28080 [53:17:30<2:10:37,  7.09s/it]
 96%|█████████▌| 26975/28080 [53:17:37<2:10:49,  7.10s/it]
                                                          
{'loss': 0.6076, 'learning_rate': 2.0278124537534414e-06, 'epoch': 11.52}

 96%|█████████▌| 26975/28080 [53:17:37<2:10:49,  7.10s/it]
 96%|█████████▌| 26976/28080 [53:17:44<2:10:49,  7.11s/it]
                                                          
{'loss': 0.596, 'learning_rate': 2.0241488242688786e-06, 'epoch': 11.52}

 96%|█████████▌| 26976/28080 [53:17:44<2:10:49,  7.11s/it]
 96%|█████████▌| 26977/28080 [53:17:51<2:10:31,  7.10s/it]
                                                          
{'loss': 0.5873, 'learning_rate': 2.0204884938472003e-06, 'epoch': 11.52}

 96%|█████████▌| 26977/28080 [53:17:51<2:10:31,  7.10s/it]
 96%|█████████▌| 26978/28080 [53:17:58<2:10:56,  7.13s/it]
                                                          
{'loss': 0.5875, 'learning_rate': 2.0168314625370887e-06, 'epoch': 11.52}

 96%|█████████▌| 26978/28080 [53:17:58<2:10:56,  7.13s/it]
 96%|█████████▌| 26979/28080 [53:18:06<2:10:53,  7.13s/it]
                                                          
{'loss': 0.6068, 'learning_rate': 2.0131777303871724e-06, 'epoch': 11.53}

 96%|█████████▌| 26979/28080 [53:18:06<2:10:53,  7.13s/it]
 96%|█████████▌| 26980/28080 [53:18:13<2:11:20,  7.16s/it]
                                                          
{'loss': 0.6051, 'learning_rate': 2.009527297446134e-06, 'epoch': 11.53}

 96%|█████████▌| 26980/28080 [53:18:13<2:11:20,  7.16s/it]
 96%|█████████▌| 26981/28080 [53:18:20<2:11:40,  7.19s/it]
                                                          
{'loss': 0.5983, 'learning_rate': 2.0058801637624913e-06, 'epoch': 11.53}

 96%|█████████▌| 26981/28080 [53:18:20<2:11:40,  7.19s/it]
 96%|█████████▌| 26982/28080 [53:18:27<2:11:20,  7.18s/it]
                                                          
{'loss': 0.6185, 'learning_rate': 2.00223632938476e-06, 'epoch': 11.53}

 96%|█████████▌| 26982/28080 [53:18:27<2:11:20,  7.18s/it]
 96%|█████████▌| 26983/28080 [53:18:34<2:10:51,  7.16s/it]
                                                          
{'loss': 0.6176, 'learning_rate': 1.9985957943614573e-06, 'epoch': 11.53}

 96%|█████████▌| 26983/28080 [53:18:34<2:10:51,  7.16s/it]
 96%|█████████▌| 26984/28080 [53:18:42<2:11:10,  7.18s/it]
                                                          
{'loss': 0.5921, 'learning_rate': 1.9949585587409613e-06, 'epoch': 11.53}

 96%|█████████▌| 26984/28080 [53:18:42<2:11:10,  7.18s/it]
 96%|█████████▌| 26985/28080 [53:18:49<2:10:40,  7.16s/it]
                                                          
{'loss': 0.6059, 'learning_rate': 1.9913246225716774e-06, 'epoch': 11.53}

 96%|█████████▌| 26985/28080 [53:18:49<2:10:40,  7.16s/it]
 96%|█████████▌| 26986/28080 [53:18:56<2:10:53,  7.18s/it]
                                                          
{'loss': 0.5996, 'learning_rate': 1.9876939859020115e-06, 'epoch': 11.53}

 96%|█████████▌| 26986/28080 [53:18:56<2:10:53,  7.18s/it]
 96%|█████████▌| 26987/28080 [53:19:03<2:10:12,  7.15s/it]
                                                          
{'loss': 0.598, 'learning_rate': 1.984066648780175e-06, 'epoch': 11.53}

 96%|█████████▌| 26987/28080 [53:19:03<2:10:12,  7.15s/it]
 96%|█████████▌| 26988/28080 [53:19:10<2:09:58,  7.14s/it]
                                                          
{'loss': 0.5956, 'learning_rate': 1.9804426112544625e-06, 'epoch': 11.53}

 96%|█████████▌| 26988/28080 [53:19:10<2:09:58,  7.14s/it]
 96%|█████████▌| 26989/28080 [53:19:17<2:10:02,  7.15s/it]
                                                          
{'loss': 0.5948, 'learning_rate': 1.9768218733731137e-06, 'epoch': 11.53}

 96%|█████████▌| 26989/28080 [53:19:17<2:10:02,  7.15s/it]
 96%|█████████▌| 26990/28080 [53:19:24<2:09:34,  7.13s/it]
                                                          
{'loss': 0.5978, 'learning_rate': 1.9732044351842836e-06, 'epoch': 11.53}

 96%|█████████▌| 26990/28080 [53:19:24<2:09:34,  7.13s/it]
 96%|█████████▌| 26991/28080 [53:19:31<2:08:59,  7.11s/it]
                                                          
{'loss': 0.5938, 'learning_rate': 1.9695902967361014e-06, 'epoch': 11.53}

 96%|█████████▌| 26991/28080 [53:19:31<2:08:59,  7.11s/it]
 96%|█████████▌| 26992/28080 [53:19:39<2:08:50,  7.11s/it]
                                                          
{'loss': 0.6242, 'learning_rate': 1.965979458076611e-06, 'epoch': 11.53}

 96%|█████████▌| 26992/28080 [53:19:39<2:08:50,  7.11s/it]
 96%|█████████▌| 26993/28080 [53:19:46<2:08:22,  7.09s/it]
                                                          
{'loss': 0.5828, 'learning_rate': 1.9623719192538858e-06, 'epoch': 11.53}

 96%|█████████▌| 26993/28080 [53:19:46<2:08:22,  7.09s/it]
 96%|█████████▌| 26994/28080 [53:19:53<2:08:42,  7.11s/it]
                                                          
{'loss': 0.5946, 'learning_rate': 1.9587676803159148e-06, 'epoch': 11.53}

 96%|█████████▌| 26994/28080 [53:19:53<2:08:42,  7.11s/it]
 96%|█████████▌| 26995/28080 [53:20:00<2:08:40,  7.12s/it]
                                                          
{'loss': 0.6083, 'learning_rate': 1.9551667413106878e-06, 'epoch': 11.53}

 96%|█████████▌| 26995/28080 [53:20:00<2:08:40,  7.12s/it]
 96%|█████████▌| 26996/28080 [53:20:07<2:08:30,  7.11s/it]
                                                          
{'loss': 0.6009, 'learning_rate': 1.951569102286027e-06, 'epoch': 11.53}

 96%|█████████▌| 26996/28080 [53:20:07<2:08:30,  7.11s/it]
 96%|█████████▌| 26997/28080 [53:20:14<2:08:33,  7.12s/it]
                                                          
{'loss': 0.6033, 'learning_rate': 1.947974763289867e-06, 'epoch': 11.53}

 96%|█████████▌| 26997/28080 [53:20:14<2:08:33,  7.12s/it]
 96%|█████████▌| 26998/28080 [53:20:21<2:08:41,  7.14s/it]
                                                          
{'loss': 0.5694, 'learning_rate': 1.9443837243700024e-06, 'epoch': 11.53}

 96%|█████████▌| 26998/28080 [53:20:21<2:08:41,  7.14s/it]
 96%|█████████▌| 26999/28080 [53:20:29<2:08:52,  7.15s/it]
                                                          
{'loss': 0.5908, 'learning_rate': 1.940795985574201e-06, 'epoch': 11.53}

 96%|█████████▌| 26999/28080 [53:20:29<2:08:52,  7.15s/it]
 96%|█████████▌| 27000/28080 [53:20:36<2:08:43,  7.15s/it]
                                                          
{'loss': 0.6058, 'learning_rate': 1.9372115469502016e-06, 'epoch': 11.53}

 96%|█████████▌| 27000/28080 [53:20:36<2:08:43,  7.15s/it]
 96%|█████████▌| 27001/28080 [53:20:43<2:08:24,  7.14s/it]
                                                          
{'loss': 0.5925, 'learning_rate': 1.933630408545689e-06, 'epoch': 11.53}

 96%|█████████▌| 27001/28080 [53:20:43<2:08:24,  7.14s/it]
 96%|█████████▌| 27002/28080 [53:20:50<2:08:02,  7.13s/it]
                                                          
{'loss': 0.5944, 'learning_rate': 1.9300525704083195e-06, 'epoch': 11.54}

 96%|█████████▌| 27002/28080 [53:20:50<2:08:02,  7.13s/it]
 96%|█████████▌| 27003/28080 [53:20:57<2:07:59,  7.13s/it]
                                                          
{'loss': 0.5968, 'learning_rate': 1.9264780325856657e-06, 'epoch': 11.54}

 96%|█████████▌| 27003/28080 [53:20:57<2:07:59,  7.13s/it]
 96%|█████████▌| 27004/28080 [53:21:04<2:08:14,  7.15s/it]
                                                          
{'loss': 0.6008, 'learning_rate': 1.922906795125301e-06, 'epoch': 11.54}

 96%|█████████▌| 27004/28080 [53:21:04<2:08:14,  7.15s/it]
 96%|█████████▌| 27005/28080 [53:21:11<2:07:33,  7.12s/it]
                                                          
{'loss': 0.6035, 'learning_rate': 1.9193388580747427e-06, 'epoch': 11.54}

 96%|█████████▌| 27005/28080 [53:21:11<2:07:33,  7.12s/it]
 96%|█████████▌| 27006/28080 [53:21:18<2:07:40,  7.13s/it]
                                                          
{'loss': 0.5847, 'learning_rate': 1.9157742214814255e-06, 'epoch': 11.54}

 96%|█████████▌| 27006/28080 [53:21:18<2:07:40,  7.13s/it]
 96%|█████████▌| 27007/28080 [53:21:26<2:07:35,  7.13s/it]
                                                          
{'loss': 0.5996, 'learning_rate': 1.9122128853928388e-06, 'epoch': 11.54}

 96%|█████████▌| 27007/28080 [53:21:26<2:07:35,  7.13s/it]
 96%|█████████▌| 27008/28080 [53:21:33<2:07:41,  7.15s/it]
                                                          
{'loss': 0.6064, 'learning_rate': 1.9086548498563063e-06, 'epoch': 11.54}

 96%|█████████▌| 27008/28080 [53:21:33<2:07:41,  7.15s/it]
 96%|█████████▌| 27009/28080 [53:21:40<2:07:13,  7.13s/it]
                                                          
{'loss': 0.5753, 'learning_rate': 1.9051001149191506e-06, 'epoch': 11.54}

 96%|█████████▌| 27009/28080 [53:21:40<2:07:13,  7.13s/it]
 96%|█████████▌| 27010/28080 [53:21:47<2:06:53,  7.12s/it]
                                                          
{'loss': 0.5893, 'learning_rate': 1.901548680628723e-06, 'epoch': 11.54}

 96%|█████████▌| 27010/28080 [53:21:47<2:06:53,  7.12s/it]
 96%|█████████▌| 27011/28080 [53:21:54<2:06:46,  7.12s/it]
                                                          
{'loss': 0.6087, 'learning_rate': 1.8980005470322358e-06, 'epoch': 11.54}

 96%|█████████▌| 27011/28080 [53:21:54<2:06:46,  7.12s/it]
 96%|█████████▌| 27012/28080 [53:22:01<2:06:17,  7.10s/it]
                                                          
{'loss': 0.5956, 'learning_rate': 1.8944557141769015e-06, 'epoch': 11.54}

 96%|█████████▌| 27012/28080 [53:22:01<2:06:17,  7.10s/it]
 96%|█████████▌| 27013/28080 [53:22:08<2:06:08,  7.09s/it]
                                                          
{'loss': 0.5967, 'learning_rate': 1.8909141821098485e-06, 'epoch': 11.54}

 96%|█████████▌| 27013/28080 [53:22:08<2:06:08,  7.09s/it]
 96%|█████████▌| 27014/28080 [53:22:15<2:05:54,  7.09s/it]
                                                          
{'loss': 0.5883, 'learning_rate': 1.8873759508782617e-06, 'epoch': 11.54}

 96%|█████████▌| 27014/28080 [53:22:15<2:05:54,  7.09s/it]
 96%|█████████▌| 27015/28080 [53:22:22<2:05:40,  7.08s/it]
                                                          
{'loss': 0.594, 'learning_rate': 1.8838410205291589e-06, 'epoch': 11.54}

 96%|█████████▌| 27015/28080 [53:22:22<2:05:40,  7.08s/it]
 96%|█████████▌| 27016/28080 [53:22:30<2:06:18,  7.12s/it]
                                                          
{'loss': 0.5765, 'learning_rate': 1.8803093911095858e-06, 'epoch': 11.54}

 96%|█████████▌| 27016/28080 [53:22:30<2:06:18,  7.12s/it]
 96%|█████████▌| 27017/28080 [53:22:37<2:06:37,  7.15s/it]
                                                          
{'loss': 0.5942, 'learning_rate': 1.8767810626665327e-06, 'epoch': 11.54}

 96%|█████████▌| 27017/28080 [53:22:37<2:06:37,  7.15s/it]
 96%|█████████▌| 27018/28080 [53:22:44<2:06:39,  7.16s/it]
                                                          
{'loss': 0.5796, 'learning_rate': 1.8732560352469063e-06, 'epoch': 11.54}

 96%|█████████▌| 27018/28080 [53:22:44<2:06:39,  7.16s/it]
 96%|█████████▌| 27019/28080 [53:22:51<2:06:13,  7.14s/it]
                                                          
{'loss': 0.6145, 'learning_rate': 1.8697343088976415e-06, 'epoch': 11.54}

 96%|█████████▌| 27019/28080 [53:22:51<2:06:13,  7.14s/it]
 96%|█████████▌| 27020/28080 [53:22:58<2:06:33,  7.16s/it]
                                                          
{'loss': 0.5957, 'learning_rate': 1.8662158836656173e-06, 'epoch': 11.54}

 96%|█████████▌| 27020/28080 [53:22:58<2:06:33,  7.16s/it]
 96%|█████████▌| 27021/28080 [53:23:05<2:06:25,  7.16s/it]
                                                          
{'loss': 0.6247, 'learning_rate': 1.8627007595975465e-06, 'epoch': 11.54}

 96%|█████████▌| 27021/28080 [53:23:05<2:06:25,  7.16s/it]
 96%|█████████▌| 27022/28080 [53:23:12<2:06:09,  7.15s/it]
                                                          
{'loss': 0.5735, 'learning_rate': 1.859188936740308e-06, 'epoch': 11.54}

 96%|█████████▌| 27022/28080 [53:23:12<2:06:09,  7.15s/it]
 96%|█████████▌| 27023/28080 [53:23:20<2:05:30,  7.12s/it]
                                                          
{'loss': 0.5955, 'learning_rate': 1.8556804151405315e-06, 'epoch': 11.54}

 96%|█████████▌| 27023/28080 [53:23:20<2:05:30,  7.12s/it]
 96%|█████████▌| 27024/28080 [53:23:27<2:05:30,  7.13s/it]
                                                          
{'loss': 0.5999, 'learning_rate': 1.8521751948449294e-06, 'epoch': 11.54}

 96%|█████████▌| 27024/28080 [53:23:27<2:05:30,  7.13s/it]
 96%|█████████▌| 27025/28080 [53:23:34<2:05:59,  7.17s/it]
                                                          
{'loss': 0.5985, 'learning_rate': 1.848673275900159e-06, 'epoch': 11.54}

 96%|█████████▌| 27025/28080 [53:23:34<2:05:59,  7.17s/it]
 96%|█████████▌| 27026/28080 [53:23:41<2:06:05,  7.18s/it]
                                                          
{'loss': 0.5998, 'learning_rate': 1.8451746583527663e-06, 'epoch': 11.55}

 96%|█████████▌| 27026/28080 [53:23:41<2:06:05,  7.18s/it]
 96%|█████████▋| 27027/28080 [53:23:48<2:05:30,  7.15s/it]
                                                          
{'loss': 0.6174, 'learning_rate': 1.841679342249325e-06, 'epoch': 11.55}

 96%|█████████▋| 27027/28080 [53:23:48<2:05:30,  7.15s/it]
 96%|█████████▋| 27028/28080 [53:23:55<2:04:56,  7.13s/it]
                                                          
{'loss': 0.5866, 'learning_rate': 1.838187327636326e-06, 'epoch': 11.55}

 96%|█████████▋| 27028/28080 [53:23:55<2:04:56,  7.13s/it]
 96%|█████████▋| 27029/28080 [53:24:03<2:05:26,  7.16s/it]
                                                          
{'loss': 0.5932, 'learning_rate': 1.8346986145602596e-06, 'epoch': 11.55}

 96%|█████████▋| 27029/28080 [53:24:03<2:05:26,  7.16s/it]
 96%|█████████▋| 27030/28080 [53:24:10<2:05:27,  7.17s/it]
                                                          
{'loss': 0.5929, 'learning_rate': 1.8312132030674777e-06, 'epoch': 11.55}

 96%|█████████▋| 27030/28080 [53:24:10<2:05:27,  7.17s/it]
 96%|█████████▋| 27031/28080 [53:24:17<2:04:55,  7.15s/it]
                                                          
{'loss': 0.5858, 'learning_rate': 1.8277310932043877e-06, 'epoch': 11.55}

 96%|█████████▋| 27031/28080 [53:24:17<2:04:55,  7.15s/it]
 96%|█████████▋| 27032/28080 [53:24:24<2:04:17,  7.12s/it]
                                                          
{'loss': 0.5915, 'learning_rate': 1.8242522850173139e-06, 'epoch': 11.55}

 96%|█████████▋| 27032/28080 [53:24:24<2:04:17,  7.12s/it]
 96%|█████████▋| 27033/28080 [53:24:31<2:04:25,  7.13s/it]
                                                          
{'loss': 0.6079, 'learning_rate': 1.8207767785525243e-06, 'epoch': 11.55}

 96%|█████████▋| 27033/28080 [53:24:31<2:04:25,  7.13s/it]
 96%|█████████▋| 27034/28080 [53:24:38<2:04:09,  7.12s/it]
                                                          
{'loss': 0.589, 'learning_rate': 1.8173045738562878e-06, 'epoch': 11.55}

 96%|█████████▋| 27034/28080 [53:24:38<2:04:09,  7.12s/it]
 96%|█████████▋| 27035/28080 [53:24:45<2:04:30,  7.15s/it]
                                                          
{'loss': 0.5881, 'learning_rate': 1.8138356709747893e-06, 'epoch': 11.55}

 96%|█████████▋| 27035/28080 [53:24:45<2:04:30,  7.15s/it]
 96%|█████████▋| 27036/28080 [53:24:53<2:04:29,  7.15s/it]
                                                          
{'loss': 0.5961, 'learning_rate': 1.8103700699541314e-06, 'epoch': 11.55}

 96%|█████████▋| 27036/28080 [53:24:53<2:04:29,  7.15s/it]
 96%|█████████▋| 27037/28080 [53:25:00<2:04:00,  7.13s/it]
                                                          
{'loss': 0.5864, 'learning_rate': 1.8069077708404712e-06, 'epoch': 11.55}

 96%|█████████▋| 27037/28080 [53:25:00<2:04:00,  7.13s/it]
 96%|█████████▋| 27038/28080 [53:25:07<2:03:32,  7.11s/it]
                                                          
{'loss': 0.6086, 'learning_rate': 1.8034487736798555e-06, 'epoch': 11.55}

 96%|█████████▋| 27038/28080 [53:25:07<2:03:32,  7.11s/it]
 96%|█████████▋| 27039/28080 [53:25:14<2:03:45,  7.13s/it]
                                                          
{'loss': 0.5979, 'learning_rate': 1.7999930785183026e-06, 'epoch': 11.55}

 96%|█████████▋| 27039/28080 [53:25:14<2:03:45,  7.13s/it]
 96%|█████████▋| 27040/28080 [53:25:21<2:03:53,  7.15s/it]
                                                          
{'loss': 0.5763, 'learning_rate': 1.796540685401804e-06, 'epoch': 11.55}

 96%|█████████▋| 27040/28080 [53:25:21<2:03:53,  7.15s/it]
 96%|█████████▋| 27041/28080 [53:25:28<2:03:12,  7.11s/it]
                                                          
{'loss': 0.6054, 'learning_rate': 1.7930915943762394e-06, 'epoch': 11.55}

 96%|█████████▋| 27041/28080 [53:25:28<2:03:12,  7.11s/it]
 96%|█████████▋| 27042/28080 [53:25:35<2:02:57,  7.11s/it]
                                                          
{'loss': 0.6044, 'learning_rate': 1.7896458054875441e-06, 'epoch': 11.55}

 96%|█████████▋| 27042/28080 [53:25:35<2:02:57,  7.11s/it]
 96%|█████████▋| 27043/28080 [53:25:42<2:03:05,  7.12s/it]
                                                          
{'loss': 0.5747, 'learning_rate': 1.7862033187815708e-06, 'epoch': 11.55}

 96%|█████████▋| 27043/28080 [53:25:42<2:03:05,  7.12s/it]
 96%|█████████▋| 27044/28080 [53:25:49<2:03:08,  7.13s/it]
                                                          
{'loss': 0.6018, 'learning_rate': 1.7827641343040878e-06, 'epoch': 11.55}

 96%|█████████▋| 27044/28080 [53:25:49<2:03:08,  7.13s/it]
 96%|█████████▋| 27045/28080 [53:25:57<2:02:51,  7.12s/it]
                                                          
{'loss': 0.6059, 'learning_rate': 1.779328252100837e-06, 'epoch': 11.55}

 96%|█████████▋| 27045/28080 [53:25:57<2:02:51,  7.12s/it]
 96%|█████████▋| 27046/28080 [53:26:04<2:02:31,  7.11s/it]
                                                          
{'loss': 0.6003, 'learning_rate': 1.775895672217559e-06, 'epoch': 11.55}

 96%|█████████▋| 27046/28080 [53:26:04<2:02:31,  7.11s/it]
 96%|█████████▋| 27047/28080 [53:26:11<2:02:59,  7.14s/it]
                                                          
{'loss': 0.6027, 'learning_rate': 1.772466394699912e-06, 'epoch': 11.55}

 96%|█████████▋| 27047/28080 [53:26:11<2:02:59,  7.14s/it]
 96%|█████████▋| 27048/28080 [53:26:18<2:02:40,  7.13s/it]
                                                          
{'loss': 0.5996, 'learning_rate': 1.769040419593526e-06, 'epoch': 11.55}

 96%|█████████▋| 27048/28080 [53:26:18<2:02:40,  7.13s/it]
 96%|█████████▋| 27049/28080 [53:26:25<2:01:35,  7.08s/it]
                                                          
{'loss': 0.5959, 'learning_rate': 1.7656177469439482e-06, 'epoch': 11.56}

 96%|█████████▋| 27049/28080 [53:26:25<2:01:35,  7.08s/it]
 96%|█████████▋| 27050/28080 [53:26:32<2:01:35,  7.08s/it]
                                                          
{'loss': 0.5998, 'learning_rate': 1.7621983767967532e-06, 'epoch': 11.56}

 96%|█████████▋| 27050/28080 [53:26:32<2:01:35,  7.08s/it]
 96%|█████████▋| 27051/28080 [53:26:39<2:02:03,  7.12s/it]
                                                          
{'loss': 0.6173, 'learning_rate': 1.7587823091974043e-06, 'epoch': 11.56}

 96%|█████████▋| 27051/28080 [53:26:39<2:02:03,  7.12s/it]
 96%|█████████▋| 27052/28080 [53:26:46<2:01:11,  7.07s/it]
                                                          
{'loss': 0.6069, 'learning_rate': 1.7553695441913653e-06, 'epoch': 11.56}

 96%|█████████▋| 27052/28080 [53:26:46<2:01:11,  7.07s/it]
 96%|█████████▋| 27053/28080 [53:26:53<2:01:03,  7.07s/it]
                                                          
{'loss': 0.6122, 'learning_rate': 1.7519600818240723e-06, 'epoch': 11.56}

 96%|█████████▋| 27053/28080 [53:26:53<2:01:03,  7.07s/it]
 96%|█████████▋| 27054/28080 [53:27:00<2:01:10,  7.09s/it]
                                                          
{'loss': 0.5853, 'learning_rate': 1.7485539221407942e-06, 'epoch': 11.56}

 96%|█████████▋| 27054/28080 [53:27:00<2:01:10,  7.09s/it]
 96%|█████████▋| 27055/28080 [53:27:08<2:01:30,  7.11s/it]
                                                          
{'loss': 0.6018, 'learning_rate': 1.7451510651869119e-06, 'epoch': 11.56}

 96%|█████████▋| 27055/28080 [53:27:08<2:01:30,  7.11s/it]
 96%|█████████▋| 27056/28080 [53:27:15<2:01:42,  7.13s/it]
                                                          
{'loss': 0.6003, 'learning_rate': 1.7417515110076942e-06, 'epoch': 11.56}

 96%|█████████▋| 27056/28080 [53:27:15<2:01:42,  7.13s/it]
 96%|█████████▋| 27057/28080 [53:27:22<2:01:17,  7.11s/it]
                                                          
{'loss': 0.6085, 'learning_rate': 1.7383552596483554e-06, 'epoch': 11.56}

 96%|█████████▋| 27057/28080 [53:27:22<2:01:17,  7.11s/it]
 96%|█████████▋| 27058/28080 [53:27:29<2:01:01,  7.11s/it]
                                                          
{'loss': 0.595, 'learning_rate': 1.7349623111540813e-06, 'epoch': 11.56}

 96%|█████████▋| 27058/28080 [53:27:29<2:01:01,  7.11s/it]
 96%|█████████▋| 27059/28080 [53:27:36<2:01:17,  7.13s/it]
                                                          
{'loss': 0.5858, 'learning_rate': 1.7315726655700304e-06, 'epoch': 11.56}

 96%|█████████▋| 27059/28080 [53:27:36<2:01:17,  7.13s/it]
 96%|█████████▋| 27060/28080 [53:27:43<2:01:35,  7.15s/it]
                                                          
{'loss': 0.5912, 'learning_rate': 1.7281863229412776e-06, 'epoch': 11.56}

 96%|█████████▋| 27060/28080 [53:27:43<2:01:35,  7.15s/it]
 96%|█████████▋| 27061/28080 [53:27:50<2:01:33,  7.16s/it]
                                                          
{'loss': 0.5943, 'learning_rate': 1.7248032833128424e-06, 'epoch': 11.56}

 96%|█████████▋| 27061/28080 [53:27:50<2:01:33,  7.16s/it]
 96%|█████████▋| 27062/28080 [53:27:58<2:01:38,  7.17s/it]
                                                          
{'loss': 0.6026, 'learning_rate': 1.7214235467298e-06, 'epoch': 11.56}

 96%|█████████▋| 27062/28080 [53:27:58<2:01:38,  7.17s/it]
 96%|█████████▋| 27063/28080 [53:28:05<2:01:45,  7.18s/it]
                                                          
{'loss': 0.5774, 'learning_rate': 1.7180471132370867e-06, 'epoch': 11.56}

 96%|█████████▋| 27063/28080 [53:28:05<2:01:45,  7.18s/it]
 96%|█████████▋| 27064/28080 [53:28:12<2:01:25,  7.17s/it]
                                                          
{'loss': 0.6205, 'learning_rate': 1.714673982879611e-06, 'epoch': 11.56}

 96%|█████████▋| 27064/28080 [53:28:12<2:01:25,  7.17s/it]
 96%|█████████▋| 27065/28080 [53:28:19<2:00:51,  7.14s/it]
                                                          
{'loss': 0.6201, 'learning_rate': 1.7113041557022259e-06, 'epoch': 11.56}

 96%|█████████▋| 27065/28080 [53:28:19<2:00:51,  7.14s/it]
 96%|█████████▋| 27066/28080 [53:28:26<2:00:27,  7.13s/it]
                                                          
{'loss': 0.6024, 'learning_rate': 1.7079376317498395e-06, 'epoch': 11.56}

 96%|█████████▋| 27066/28080 [53:28:26<2:00:27,  7.13s/it]
 96%|█████████▋| 27067/28080 [53:28:33<2:00:11,  7.12s/it]
                                                          
{'loss': 0.5907, 'learning_rate': 1.7045744110671667e-06, 'epoch': 11.56}

 96%|█████████▋| 27067/28080 [53:28:33<2:00:11,  7.12s/it]
 96%|█████████▋| 27068/28080 [53:28:40<1:59:33,  7.09s/it]
                                                          
{'loss': 0.5947, 'learning_rate': 1.701214493699005e-06, 'epoch': 11.56}

 96%|█████████▋| 27068/28080 [53:28:40<1:59:33,  7.09s/it]
 96%|█████████▋| 27069/28080 [53:28:47<1:59:34,  7.10s/it]
                                                          
{'loss': 0.592, 'learning_rate': 1.6978578796899846e-06, 'epoch': 11.56}

 96%|█████████▋| 27069/28080 [53:28:47<1:59:34,  7.10s/it]
 96%|█████████▋| 27070/28080 [53:28:55<2:00:18,  7.15s/it]
                                                          
{'loss': 0.6132, 'learning_rate': 1.6945045690848481e-06, 'epoch': 11.56}

 96%|█████████▋| 27070/28080 [53:28:55<2:00:18,  7.15s/it]
 96%|█████████▋| 27071/28080 [53:29:02<2:00:06,  7.14s/it]
                                                          
{'loss': 0.6112, 'learning_rate': 1.6911545619281432e-06, 'epoch': 11.56}

 96%|█████████▋| 27071/28080 [53:29:02<2:00:06,  7.14s/it]
 96%|█████████▋| 27072/28080 [53:29:09<1:59:47,  7.13s/it]
                                                          
{'loss': 0.5938, 'learning_rate': 1.6878078582644453e-06, 'epoch': 11.56}

 96%|█████████▋| 27072/28080 [53:29:09<1:59:47,  7.13s/it]
 96%|█████████▋| 27073/28080 [53:29:16<1:59:43,  7.13s/it]
                                                          
{'loss': 0.5964, 'learning_rate': 1.6844644581383295e-06, 'epoch': 11.57}

 96%|█████████▋| 27073/28080 [53:29:16<1:59:43,  7.13s/it]
 96%|█████████▋| 27074/28080 [53:29:23<1:59:30,  7.13s/it]
                                                          
{'loss': 0.6013, 'learning_rate': 1.6811243615942328e-06, 'epoch': 11.57}

 96%|█████████▋| 27074/28080 [53:29:23<1:59:30,  7.13s/it]
 96%|█████████▋| 27075/28080 [53:29:30<1:59:26,  7.13s/it]
                                                          
{'loss': 0.591, 'learning_rate': 1.677787568676592e-06, 'epoch': 11.57}

 96%|█████████▋| 27075/28080 [53:29:30<1:59:26,  7.13s/it]
 96%|█████████▋| 27076/28080 [53:29:37<1:59:31,  7.14s/it]
                                                          
{'loss': 0.5829, 'learning_rate': 1.6744540794298158e-06, 'epoch': 11.57}

 96%|█████████▋| 27076/28080 [53:29:37<1:59:31,  7.14s/it]
 96%|█████████▋| 27077/28080 [53:29:45<1:59:35,  7.15s/it]
                                                          
{'loss': 0.6134, 'learning_rate': 1.6711238938982299e-06, 'epoch': 11.57}

 96%|█████████▋| 27077/28080 [53:29:45<1:59:35,  7.15s/it]
 96%|█████████▋| 27078/28080 [53:29:52<1:58:21,  7.09s/it]
                                                          
{'loss': 0.6152, 'learning_rate': 1.6677970121261877e-06, 'epoch': 11.57}

 96%|█████████▋| 27078/28080 [53:29:52<1:58:21,  7.09s/it]
 96%|█████████▋| 27079/28080 [53:29:59<1:58:08,  7.08s/it]
                                                          
{'loss': 0.5992, 'learning_rate': 1.664473434157876e-06, 'epoch': 11.57}

 96%|█████████▋| 27079/28080 [53:29:59<1:58:08,  7.08s/it]
 96%|█████████▋| 27080/28080 [53:30:06<1:58:24,  7.10s/it]
                                                          
{'loss': 0.6176, 'learning_rate': 1.661153160037565e-06, 'epoch': 11.57}

 96%|█████████▋| 27080/28080 [53:30:06<1:58:24,  7.10s/it]
 96%|█████████▋| 27081/28080 [53:30:13<1:58:27,  7.11s/it]
                                                          
{'loss': 0.6049, 'learning_rate': 1.657836189809414e-06, 'epoch': 11.57}

 96%|█████████▋| 27081/28080 [53:30:13<1:58:27,  7.11s/it]
 96%|█████████▋| 27082/28080 [53:30:20<1:58:47,  7.14s/it]
                                                          
{'loss': 0.5759, 'learning_rate': 1.6545225235175544e-06, 'epoch': 11.57}

 96%|█████████▋| 27082/28080 [53:30:20<1:58:47,  7.14s/it]
 96%|█████████▋| 27083/28080 [53:30:27<1:58:43,  7.14s/it]
                                                          
{'loss': 0.566, 'learning_rate': 1.6512121612060894e-06, 'epoch': 11.57}

 96%|█████████▋| 27083/28080 [53:30:27<1:58:43,  7.14s/it]
 96%|█████████▋| 27084/28080 [53:30:34<1:58:42,  7.15s/it]
                                                          
{'loss': 0.5758, 'learning_rate': 1.6479051029190117e-06, 'epoch': 11.57}

 96%|█████████▋| 27084/28080 [53:30:34<1:58:42,  7.15s/it]
 96%|█████████▋| 27085/28080 [53:30:42<1:58:15,  7.13s/it]
                                                          
{'loss': 0.5877, 'learning_rate': 1.644601348700342e-06, 'epoch': 11.57}

 96%|█████████▋| 27085/28080 [53:30:42<1:58:15,  7.13s/it]
 96%|█████████▋| 27086/28080 [53:30:49<1:58:13,  7.14s/it]
                                                          
{'loss': 0.5808, 'learning_rate': 1.6413008985940447e-06, 'epoch': 11.57}

 96%|█████████▋| 27086/28080 [53:30:49<1:58:13,  7.14s/it]
 96%|█████████▋| 27087/28080 [53:30:56<1:58:24,  7.15s/it]
                                                          
{'loss': 0.5861, 'learning_rate': 1.6380037526440573e-06, 'epoch': 11.57}

 96%|█████████▋| 27087/28080 [53:30:56<1:58:24,  7.15s/it]
 96%|█████████▋| 27088/28080 [53:31:03<1:58:11,  7.15s/it]
                                                          
{'loss': 0.6025, 'learning_rate': 1.63470991089415e-06, 'epoch': 11.57}

 96%|█████████▋| 27088/28080 [53:31:03<1:58:11,  7.15s/it]
 96%|█████████▋| 27089/28080 [53:31:10<1:58:08,  7.15s/it]
                                                          
{'loss': 0.6077, 'learning_rate': 1.6314193733882598e-06, 'epoch': 11.57}

 96%|█████████▋| 27089/28080 [53:31:10<1:58:08,  7.15s/it]
 96%|█████████▋| 27090/28080 [53:31:17<1:58:13,  7.16s/it]
                                                          
{'loss': 0.5847, 'learning_rate': 1.6281321401700466e-06, 'epoch': 11.57}

 96%|█████████▋| 27090/28080 [53:31:17<1:58:13,  7.16s/it]
 96%|█████████▋| 27091/28080 [53:31:25<1:58:01,  7.16s/it]
                                                          
{'loss': 0.6052, 'learning_rate': 1.6248482112833363e-06, 'epoch': 11.57}

 96%|█████████▋| 27091/28080 [53:31:25<1:58:01,  7.16s/it]
 96%|█████████▋| 27092/28080 [53:31:32<1:58:04,  7.17s/it]
                                                          
{'loss': 0.6085, 'learning_rate': 1.621567586771816e-06, 'epoch': 11.57}

 96%|█████████▋| 27092/28080 [53:31:32<1:58:04,  7.17s/it]
 96%|█████████▋| 27093/28080 [53:31:39<1:58:01,  7.18s/it]
                                                          
{'loss': 0.5966, 'learning_rate': 1.6182902666790622e-06, 'epoch': 11.57}

 96%|█████████▋| 27093/28080 [53:31:39<1:58:01,  7.18s/it]
 96%|█████████▋| 27094/28080 [53:31:46<1:58:03,  7.18s/it]
                                                          
{'loss': 0.5977, 'learning_rate': 1.6150162510487065e-06, 'epoch': 11.57}

 96%|█████████▋| 27094/28080 [53:31:46<1:58:03,  7.18s/it]
 96%|█████████▋| 27095/28080 [53:31:53<1:58:05,  7.19s/it]
                                                          
{'loss': 0.5907, 'learning_rate': 1.611745539924353e-06, 'epoch': 11.57}

 96%|█████████▋| 27095/28080 [53:31:53<1:58:05,  7.19s/it]
 96%|█████████▋| 27096/28080 [53:32:00<1:57:12,  7.15s/it]
                                                          
{'loss': 0.6047, 'learning_rate': 1.6084781333494669e-06, 'epoch': 11.58}

 96%|█████████▋| 27096/28080 [53:32:00<1:57:12,  7.15s/it]
 96%|█████████▋| 27097/28080 [53:32:08<1:56:59,  7.14s/it]
                                                          
{'loss': 0.6024, 'learning_rate': 1.6052140313675135e-06, 'epoch': 11.58}

 96%|█████████▋| 27097/28080 [53:32:08<1:56:59,  7.14s/it]
 97%|█████████▋| 27098/28080 [53:32:15<1:56:52,  7.14s/it]
                                                          
{'loss': 0.5921, 'learning_rate': 1.60195323402193e-06, 'epoch': 11.58}

 97%|█████████▋| 27098/28080 [53:32:15<1:56:52,  7.14s/it]
 97%|█████████▋| 27099/28080 [53:32:22<1:57:11,  7.17s/it]
                                                          
{'loss': 0.5893, 'learning_rate': 1.5986957413560987e-06, 'epoch': 11.58}

 97%|█████████▋| 27099/28080 [53:32:22<1:57:11,  7.17s/it]
 97%|█████████▋| 27100/28080 [53:32:29<1:56:49,  7.15s/it]
                                                          
{'loss': 0.6071, 'learning_rate': 1.5954415534133738e-06, 'epoch': 11.58}

 97%|█████████▋| 27100/28080 [53:32:29<1:56:49,  7.15s/it]
 97%|█████████▋| 27101/28080 [53:32:36<1:56:25,  7.13s/it]
                                                          
{'loss': 0.6096, 'learning_rate': 1.5921906702370259e-06, 'epoch': 11.58}

 97%|█████████▋| 27101/28080 [53:32:36<1:56:25,  7.13s/it]
 97%|█████████▋| 27102/28080 [53:32:43<1:56:39,  7.16s/it]
                                                          
{'loss': 0.5795, 'learning_rate': 1.5889430918703262e-06, 'epoch': 11.58}

 97%|█████████▋| 27102/28080 [53:32:43<1:56:39,  7.16s/it]
 97%|█████████▋| 27103/28080 [53:32:50<1:56:42,  7.17s/it]
                                                          
{'loss': 0.5916, 'learning_rate': 1.5856988183564625e-06, 'epoch': 11.58}

 97%|█████████▋| 27103/28080 [53:32:50<1:56:42,  7.17s/it]
 97%|█████████▋| 27104/28080 [53:32:58<1:56:20,  7.15s/it]
                                                          
{'loss': 0.5977, 'learning_rate': 1.5824578497385668e-06, 'epoch': 11.58}

 97%|█████████▋| 27104/28080 [53:32:58<1:56:20,  7.15s/it]
 97%|█████████▋| 27105/28080 [53:33:05<1:55:52,  7.13s/it]
                                                          
{'loss': 0.5844, 'learning_rate': 1.5792201860598266e-06, 'epoch': 11.58}

 97%|█████████▋| 27105/28080 [53:33:05<1:55:52,  7.13s/it]
 97%|█████████▋| 27106/28080 [53:33:12<1:55:47,  7.13s/it]
                                                          
{'loss': 0.5926, 'learning_rate': 1.575985827363291e-06, 'epoch': 11.58}

 97%|█████████▋| 27106/28080 [53:33:12<1:55:47,  7.13s/it]
 97%|█████████▋| 27107/28080 [53:33:19<1:55:44,  7.14s/it]
                                                          
{'loss': 0.6018, 'learning_rate': 1.5727547736919534e-06, 'epoch': 11.58}

 97%|█████████▋| 27107/28080 [53:33:19<1:55:44,  7.14s/it]
 97%|█████████▋| 27108/28080 [53:33:26<1:55:40,  7.14s/it]
                                                          
{'loss': 0.6021, 'learning_rate': 1.569527025088835e-06, 'epoch': 11.58}

 97%|█████████▋| 27108/28080 [53:33:26<1:55:40,  7.14s/it]
 97%|█████████▋| 27109/28080 [53:33:33<1:55:12,  7.12s/it]
                                                          
{'loss': 0.5831, 'learning_rate': 1.5663025815968735e-06, 'epoch': 11.58}

 97%|█████████▋| 27109/28080 [53:33:33<1:55:12,  7.12s/it]
 97%|█████████▋| 27110/28080 [53:33:40<1:55:14,  7.13s/it]
                                                          
{'loss': 0.5804, 'learning_rate': 1.5630814432589514e-06, 'epoch': 11.58}

 97%|█████████▋| 27110/28080 [53:33:40<1:55:14,  7.13s/it]
 97%|█████████▋| 27111/28080 [53:33:47<1:54:31,  7.09s/it]
                                                          
{'loss': 0.5927, 'learning_rate': 1.5598636101179508e-06, 'epoch': 11.58}

 97%|█████████▋| 27111/28080 [53:33:47<1:54:31,  7.09s/it]
 97%|█████████▋| 27112/28080 [53:33:54<1:54:37,  7.11s/it]
                                                          
{'loss': 0.6091, 'learning_rate': 1.5566490822166435e-06, 'epoch': 11.58}

 97%|█████████▋| 27112/28080 [53:33:54<1:54:37,  7.11s/it]
 97%|█████████▋| 27113/28080 [53:34:02<1:54:50,  7.13s/it]
                                                          
{'loss': 0.5702, 'learning_rate': 1.5534378595978283e-06, 'epoch': 11.58}

 97%|█████████▋| 27113/28080 [53:34:02<1:54:50,  7.13s/it]
 97%|█████████▋| 27114/28080 [53:34:09<1:54:42,  7.12s/it]
                                                          
{'loss': 0.5875, 'learning_rate': 1.5502299423041932e-06, 'epoch': 11.58}

 97%|█████████▋| 27114/28080 [53:34:09<1:54:42,  7.12s/it]
 97%|█████████▋| 27115/28080 [53:34:16<1:54:35,  7.12s/it]
                                                          
{'loss': 0.5987, 'learning_rate': 1.5470253303784543e-06, 'epoch': 11.58}

 97%|█████████▋| 27115/28080 [53:34:16<1:54:35,  7.12s/it]
 97%|█████████▋| 27116/28080 [53:34:23<1:54:35,  7.13s/it]
                                                          
{'loss': 0.6059, 'learning_rate': 1.543824023863244e-06, 'epoch': 11.58}

 97%|█████████▋| 27116/28080 [53:34:23<1:54:35,  7.13s/it]
 97%|█████████▋| 27117/28080 [53:34:30<1:54:20,  7.12s/it]
                                                          
{'loss': 0.5794, 'learning_rate': 1.5406260228011116e-06, 'epoch': 11.58}

 97%|█████████▋| 27117/28080 [53:34:30<1:54:20,  7.12s/it]
 97%|█████████▋| 27118/28080 [53:34:37<1:54:29,  7.14s/it]
                                                          
{'loss': 0.5716, 'learning_rate': 1.5374313272346342e-06, 'epoch': 11.58}

 97%|█████████▋| 27118/28080 [53:34:37<1:54:29,  7.14s/it]
 97%|█████████▋| 27119/28080 [53:34:45<1:54:32,  7.15s/it]
                                                          
{'loss': 0.6018, 'learning_rate': 1.5342399372063055e-06, 'epoch': 11.58}

 97%|█████████▋| 27119/28080 [53:34:45<1:54:32,  7.15s/it]
 97%|█████████▋| 27120/28080 [53:34:52<1:54:23,  7.15s/it]
                                                          
{'loss': 0.585, 'learning_rate': 1.5310518527585916e-06, 'epoch': 11.59}

 97%|█████████▋| 27120/28080 [53:34:52<1:54:23,  7.15s/it]
 97%|█████████▋| 27121/28080 [53:34:59<1:54:20,  7.15s/it]
                                                          
{'loss': 0.5926, 'learning_rate': 1.5278670739339029e-06, 'epoch': 11.59}

 97%|█████████▋| 27121/28080 [53:34:59<1:54:20,  7.15s/it]
 97%|█████████▋| 27122/28080 [53:35:06<1:54:17,  7.16s/it]
                                                          
{'loss': 0.5898, 'learning_rate': 1.5246856007745945e-06, 'epoch': 11.59}

 97%|█████████▋| 27122/28080 [53:35:06<1:54:17,  7.16s/it]
 97%|█████████▋| 27123/28080 [53:35:13<1:53:27,  7.11s/it]
                                                          
{'loss': 0.6122, 'learning_rate': 1.5215074333230217e-06, 'epoch': 11.59}

 97%|█████████▋| 27123/28080 [53:35:13<1:53:27,  7.11s/it]
 97%|█████████▋| 27124/28080 [53:35:20<1:53:32,  7.13s/it]
                                                          
{'loss': 0.5934, 'learning_rate': 1.5183325716214558e-06, 'epoch': 11.59}

 97%|█████████▋| 27124/28080 [53:35:20<1:53:32,  7.13s/it]
 97%|█████████▋| 27125/28080 [53:35:27<1:53:17,  7.12s/it]
                                                          
{'loss': 0.6144, 'learning_rate': 1.5151610157121131e-06, 'epoch': 11.59}

 97%|█████████▋| 27125/28080 [53:35:27<1:53:17,  7.12s/it]
 97%|█████████▋| 27126/28080 [53:35:34<1:53:33,  7.14s/it]
                                                          
{'loss': 0.5945, 'learning_rate': 1.511992765637238e-06, 'epoch': 11.59}

 97%|█████████▋| 27126/28080 [53:35:34<1:53:33,  7.14s/it]
 97%|█████████▋| 27127/28080 [53:35:42<1:53:04,  7.12s/it]
                                                          
{'loss': 0.6141, 'learning_rate': 1.5088278214389074e-06, 'epoch': 11.59}

 97%|█████████▋| 27127/28080 [53:35:42<1:53:04,  7.12s/it]
 97%|█████████▋| 27128/28080 [53:35:49<1:53:15,  7.14s/it]
                                                          
{'loss': 0.5978, 'learning_rate': 1.505666183159282e-06, 'epoch': 11.59}

 97%|█████████▋| 27128/28080 [53:35:49<1:53:15,  7.14s/it]
 97%|█████████▋| 27129/28080 [53:35:56<1:52:58,  7.13s/it]
                                                          
{'loss': 0.6121, 'learning_rate': 1.5025078508404122e-06, 'epoch': 11.59}

 97%|█████████▋| 27129/28080 [53:35:56<1:52:58,  7.13s/it]
 97%|█████████▋| 27130/28080 [53:36:03<1:52:54,  7.13s/it]
                                                          
{'loss': 0.5917, 'learning_rate': 1.499352824524347e-06, 'epoch': 11.59}

 97%|█████████▋| 27130/28080 [53:36:03<1:52:54,  7.13s/it]
 97%|█████████▋| 27131/28080 [53:36:10<1:52:47,  7.13s/it]
                                                          
{'loss': 0.5871, 'learning_rate': 1.49620110425297e-06, 'epoch': 11.59}

 97%|█████████▋| 27131/28080 [53:36:10<1:52:47,  7.13s/it]
 97%|█████████▋| 27132/28080 [53:36:17<1:52:45,  7.14s/it]
                                                          
{'loss': 0.6084, 'learning_rate': 1.4930526900683029e-06, 'epoch': 11.59}

 97%|█████████▋| 27132/28080 [53:36:17<1:52:45,  7.14s/it]
 97%|█████████▋| 27133/28080 [53:36:24<1:52:37,  7.14s/it]
                                                          
{'loss': 0.5871, 'learning_rate': 1.489907582012201e-06, 'epoch': 11.59}

 97%|█████████▋| 27133/28080 [53:36:24<1:52:37,  7.14s/it]
 97%|█████████▋| 27134/28080 [53:36:31<1:52:30,  7.14s/it]
                                                          
{'loss': 0.5869, 'learning_rate': 1.4867657801264922e-06, 'epoch': 11.59}

 97%|█████████▋| 27134/28080 [53:36:31<1:52:30,  7.14s/it]
 97%|█████████▋| 27135/28080 [53:36:39<1:52:05,  7.12s/it]
                                                          
{'loss': 0.6004, 'learning_rate': 1.483627284453032e-06, 'epoch': 11.59}

 97%|█████████▋| 27135/28080 [53:36:39<1:52:05,  7.12s/it]
 97%|█████████▋| 27136/28080 [53:36:46<1:51:47,  7.11s/it]
                                                          
{'loss': 0.6305, 'learning_rate': 1.480492095033481e-06, 'epoch': 11.59}

 97%|█████████▋| 27136/28080 [53:36:46<1:51:47,  7.11s/it]
 97%|█████████▋| 27137/28080 [53:36:53<1:52:25,  7.15s/it]
                                                          
{'loss': 0.6135, 'learning_rate': 1.477360211909612e-06, 'epoch': 11.59}

 97%|█████████▋| 27137/28080 [53:36:53<1:52:25,  7.15s/it]
 97%|█████████▋| 27138/28080 [53:37:00<1:52:02,  7.14s/it]
                                                          
{'loss': 0.5905, 'learning_rate': 1.4742316351230856e-06, 'epoch': 11.59}

 97%|█████████▋| 27138/28080 [53:37:00<1:52:02,  7.14s/it]
 97%|█████████▋| 27139/28080 [53:37:07<1:52:06,  7.15s/it]
                                                          
{'loss': 0.5846, 'learning_rate': 1.4711063647155076e-06, 'epoch': 11.59}

 97%|█████████▋| 27139/28080 [53:37:07<1:52:06,  7.15s/it]
 97%|█████████▋| 27140/28080 [53:37:14<1:51:38,  7.13s/it]
                                                          
{'loss': 0.5754, 'learning_rate': 1.4679844007284559e-06, 'epoch': 11.59}

 97%|█████████▋| 27140/28080 [53:37:14<1:51:38,  7.13s/it]
 97%|█████████▋| 27141/28080 [53:37:21<1:51:33,  7.13s/it]
                                                          
{'loss': 0.583, 'learning_rate': 1.4648657432035084e-06, 'epoch': 11.59}

 97%|█████████▋| 27141/28080 [53:37:21<1:51:33,  7.13s/it]
 97%|█████████▋| 27142/28080 [53:37:29<1:51:31,  7.13s/it]
                                                          
{'loss': 0.6108, 'learning_rate': 1.461750392182104e-06, 'epoch': 11.59}

 97%|█████████▋| 27142/28080 [53:37:29<1:51:31,  7.13s/it]
 97%|█████████▋| 27143/28080 [53:37:36<1:51:31,  7.14s/it]
                                                          
{'loss': 0.6172, 'learning_rate': 1.4586383477057097e-06, 'epoch': 11.6}

 97%|█████████▋| 27143/28080 [53:37:36<1:51:31,  7.14s/it]
 97%|█████████▋| 27144/28080 [53:37:43<1:51:09,  7.13s/it]
                                                          
{'loss': 0.6051, 'learning_rate': 1.4555296098157366e-06, 'epoch': 11.6}

 97%|█████████▋| 27144/28080 [53:37:43<1:51:09,  7.13s/it]
 97%|█████████▋| 27145/28080 [53:37:50<1:51:11,  7.14s/it]
                                                          
{'loss': 0.5964, 'learning_rate': 1.452424178553513e-06, 'epoch': 11.6}

 97%|█████████▋| 27145/28080 [53:37:50<1:51:11,  7.14s/it]
 97%|█████████▋| 27146/28080 [53:37:57<1:51:10,  7.14s/it]
                                                          
{'loss': 0.5957, 'learning_rate': 1.449322053960367e-06, 'epoch': 11.6}

 97%|█████████▋| 27146/28080 [53:37:57<1:51:10,  7.14s/it]
 97%|█████████▋| 27147/28080 [53:38:04<1:50:34,  7.11s/it]
                                                          
{'loss': 0.6235, 'learning_rate': 1.4462232360775984e-06, 'epoch': 11.6}

 97%|█████████▋| 27147/28080 [53:38:04<1:50:34,  7.11s/it]
 97%|█████████▋| 27148/28080 [53:38:11<1:50:37,  7.12s/it]
                                                          
{'loss': 0.607, 'learning_rate': 1.443127724946397e-06, 'epoch': 11.6}

 97%|█████████▋| 27148/28080 [53:38:11<1:50:37,  7.12s/it]
 97%|█████████▋| 27149/28080 [53:38:18<1:50:17,  7.11s/it]
                                                          
{'loss': 0.5937, 'learning_rate': 1.4400355206079796e-06, 'epoch': 11.6}

 97%|█████████▋| 27149/28080 [53:38:18<1:50:17,  7.11s/it]
 97%|█████████▋| 27150/28080 [53:38:26<1:50:24,  7.12s/it]
                                                          
{'loss': 0.6035, 'learning_rate': 1.4369466231034524e-06, 'epoch': 11.6}

 97%|█████████▋| 27150/28080 [53:38:26<1:50:24,  7.12s/it]
 97%|█████████▋| 27151/28080 [53:38:33<1:50:06,  7.11s/it]
                                                          
{'loss': 0.6027, 'learning_rate': 1.433861032473921e-06, 'epoch': 11.6}

 97%|█████████▋| 27151/28080 [53:38:33<1:50:06,  7.11s/it]
 97%|█████████▋| 27152/28080 [53:38:40<1:49:51,  7.10s/it]
                                                          
{'loss': 0.5897, 'learning_rate': 1.4307787487604362e-06, 'epoch': 11.6}

 97%|█████████▋| 27152/28080 [53:38:40<1:49:51,  7.10s/it]
 97%|█████████▋| 27153/28080 [53:38:47<1:49:38,  7.10s/it]
                                                          
{'loss': 0.5902, 'learning_rate': 1.427699772003993e-06, 'epoch': 11.6}

 97%|█████████▋| 27153/28080 [53:38:47<1:49:38,  7.10s/it]
 97%|█████████▋| 27154/28080 [53:38:54<1:50:02,  7.13s/it]
                                                          
{'loss': 0.5919, 'learning_rate': 1.4246241022455865e-06, 'epoch': 11.6}

 97%|█████████▋| 27154/28080 [53:38:54<1:50:02,  7.13s/it]
 97%|█████████▋| 27155/28080 [53:39:01<1:49:55,  7.13s/it]
                                                          
{'loss': 0.6054, 'learning_rate': 1.4215517395261002e-06, 'epoch': 11.6}

 97%|█████████▋| 27155/28080 [53:39:01<1:49:55,  7.13s/it]
 97%|█████████▋| 27156/28080 [53:39:08<1:50:02,  7.15s/it]
                                                          
{'loss': 0.5966, 'learning_rate': 1.4184826838864463e-06, 'epoch': 11.6}

 97%|█████████▋| 27156/28080 [53:39:08<1:50:02,  7.15s/it]
 97%|█████████▋| 27157/28080 [53:39:15<1:50:05,  7.16s/it]
                                                          
{'loss': 0.5823, 'learning_rate': 1.4154169353673973e-06, 'epoch': 11.6}

 97%|█████████▋| 27157/28080 [53:39:15<1:50:05,  7.16s/it]
 97%|█████████▋| 27158/28080 [53:39:22<1:49:23,  7.12s/it]
                                                          
{'loss': 0.6023, 'learning_rate': 1.4123544940098098e-06, 'epoch': 11.6}

 97%|█████████▋| 27158/28080 [53:39:23<1:49:23,  7.12s/it]
 97%|█████████▋| 27159/28080 [53:39:30<1:49:39,  7.14s/it]
                                                          
{'loss': 0.5907, 'learning_rate': 1.4092953598543733e-06, 'epoch': 11.6}

 97%|█████████▋| 27159/28080 [53:39:30<1:49:39,  7.14s/it]
 97%|█████████▋| 27160/28080 [53:39:37<1:49:47,  7.16s/it]
                                                          
{'loss': 0.6183, 'learning_rate': 1.4062395329418331e-06, 'epoch': 11.6}

 97%|█████████▋| 27160/28080 [53:39:37<1:49:47,  7.16s/it]
 97%|█████████▋| 27161/28080 [53:39:44<1:49:15,  7.13s/it]
                                                          
{'loss': 0.5781, 'learning_rate': 1.4031870133127677e-06, 'epoch': 11.6}

 97%|█████████▋| 27161/28080 [53:39:44<1:49:15,  7.13s/it]
 97%|█████████▋| 27162/28080 [53:39:51<1:49:37,  7.16s/it]
                                                          
{'loss': 0.6013, 'learning_rate': 1.400137801007867e-06, 'epoch': 11.6}

 97%|█████████▋| 27162/28080 [53:39:51<1:49:37,  7.16s/it]
 97%|█████████▋| 27163/28080 [53:39:58<1:49:28,  7.16s/it]
                                                          
{'loss': 0.592, 'learning_rate': 1.3970918960676815e-06, 'epoch': 11.6}

 97%|█████████▋| 27163/28080 [53:39:58<1:49:28,  7.16s/it]
 97%|█████████▋| 27164/28080 [53:40:06<1:49:32,  7.18s/it]
                                                          
{'loss': 0.5924, 'learning_rate': 1.3940492985327069e-06, 'epoch': 11.6}

 97%|█████████▋| 27164/28080 [53:40:06<1:49:32,  7.18s/it]
 97%|█████████▋| 27165/28080 [53:40:13<1:49:19,  7.17s/it]
                                                          
{'loss': 0.5927, 'learning_rate': 1.3910100084434107e-06, 'epoch': 11.6}

 97%|█████████▋| 27165/28080 [53:40:13<1:49:19,  7.17s/it]
 97%|█████████▋| 27166/28080 [53:40:20<1:49:05,  7.16s/it]
                                                          
{'loss': 0.5801, 'learning_rate': 1.3879740258402607e-06, 'epoch': 11.61}

 97%|█████████▋| 27166/28080 [53:40:20<1:49:05,  7.16s/it]
 97%|█████████▋| 27167/28080 [53:40:27<1:48:45,  7.15s/it]
                                                          
{'loss': 0.6043, 'learning_rate': 1.384941350763641e-06, 'epoch': 11.61}

 97%|█████████▋| 27167/28080 [53:40:27<1:48:45,  7.15s/it]
 97%|█████████▋| 27168/28080 [53:40:34<1:48:44,  7.15s/it]
                                                          
{'loss': 0.5912, 'learning_rate': 1.3819119832539085e-06, 'epoch': 11.61}

 97%|█████████▋| 27168/28080 [53:40:34<1:48:44,  7.15s/it]
 97%|█████████▋| 27169/28080 [53:40:41<1:48:43,  7.16s/it]
                                                          
{'loss': 0.5627, 'learning_rate': 1.3788859233513363e-06, 'epoch': 11.61}

 97%|█████████▋| 27169/28080 [53:40:41<1:48:43,  7.16s/it]
 97%|█████████▋| 27170/28080 [53:40:48<1:48:13,  7.14s/it]
                                                          
{'loss': 0.603, 'learning_rate': 1.3758631710961977e-06, 'epoch': 11.61}

 97%|█████████▋| 27170/28080 [53:40:48<1:48:13,  7.14s/it]
 97%|█████████▋| 27171/28080 [53:40:55<1:47:32,  7.10s/it]
                                                          
{'loss': 0.5911, 'learning_rate': 1.3728437265287108e-06, 'epoch': 11.61}

 97%|█████████▋| 27171/28080 [53:40:55<1:47:32,  7.10s/it]
 97%|█████████▋| 27172/28080 [53:41:03<1:47:24,  7.10s/it]
                                                          
{'loss': 0.6153, 'learning_rate': 1.3698275896890656e-06, 'epoch': 11.61}

 97%|█████████▋| 27172/28080 [53:41:03<1:47:24,  7.10s/it]
 97%|█████████▋| 27173/28080 [53:41:10<1:47:29,  7.11s/it]
                                                          
{'loss': 0.5859, 'learning_rate': 1.3668147606173409e-06, 'epoch': 11.61}

 97%|█████████▋| 27173/28080 [53:41:10<1:47:29,  7.11s/it]
 97%|█████████▋| 27174/28080 [53:41:17<1:47:28,  7.12s/it]
                                                          
{'loss': 0.5901, 'learning_rate': 1.3638052393536714e-06, 'epoch': 11.61}

 97%|█████████▋| 27174/28080 [53:41:17<1:47:28,  7.12s/it]
 97%|█████████▋| 27175/28080 [53:41:24<1:47:19,  7.12s/it]
                                                          
{'loss': 0.5929, 'learning_rate': 1.3607990259380254e-06, 'epoch': 11.61}

 97%|█████████▋| 27175/28080 [53:41:24<1:47:19,  7.12s/it]
 97%|█████████▋| 27176/28080 [53:41:31<1:47:27,  7.13s/it]
                                                          
{'loss': 0.6058, 'learning_rate': 1.3577961204104815e-06, 'epoch': 11.61}

 97%|█████████▋| 27176/28080 [53:41:31<1:47:27,  7.13s/it]
 97%|█████████▋| 27177/28080 [53:41:38<1:47:07,  7.12s/it]
                                                          
{'loss': 0.6086, 'learning_rate': 1.354796522810925e-06, 'epoch': 11.61}

 97%|█████████▋| 27177/28080 [53:41:38<1:47:07,  7.12s/it]
 97%|█████████▋| 27178/28080 [53:41:45<1:47:13,  7.13s/it]
                                                          
{'loss': 0.5958, 'learning_rate': 1.3518002331792955e-06, 'epoch': 11.61}

 97%|█████████▋| 27178/28080 [53:41:45<1:47:13,  7.13s/it]
 97%|█████████▋| 27179/28080 [53:41:53<1:47:27,  7.16s/it]
                                                          
{'loss': 0.6046, 'learning_rate': 1.3488072515554506e-06, 'epoch': 11.61}

 97%|█████████▋| 27179/28080 [53:41:53<1:47:27,  7.16s/it]
 97%|█████████▋| 27180/28080 [53:42:00<1:47:31,  7.17s/it]
                                                          
{'loss': 0.5922, 'learning_rate': 1.3458175779792192e-06, 'epoch': 11.61}

 97%|█████████▋| 27180/28080 [53:42:00<1:47:31,  7.17s/it]
 97%|█████████▋| 27181/28080 [53:42:07<1:47:44,  7.19s/it]
                                                          
{'loss': 0.595, 'learning_rate': 1.3428312124903474e-06, 'epoch': 11.61}

 97%|█████████▋| 27181/28080 [53:42:07<1:47:44,  7.19s/it]
 97%|█████████▋| 27182/28080 [53:42:14<1:47:24,  7.18s/it]
                                                          
{'loss': 0.6081, 'learning_rate': 1.3398481551285812e-06, 'epoch': 11.61}

 97%|█████████▋| 27182/28080 [53:42:14<1:47:24,  7.18s/it]
 97%|█████████▋| 27183/28080 [53:42:21<1:47:05,  7.16s/it]
                                                          
{'loss': 0.6056, 'learning_rate': 1.336868405933611e-06, 'epoch': 11.61}

 97%|█████████▋| 27183/28080 [53:42:21<1:47:05,  7.16s/it]
 97%|█████████▋| 27184/28080 [53:42:28<1:46:56,  7.16s/it]
                                                          
{'loss': 0.5836, 'learning_rate': 1.333891964945072e-06, 'epoch': 11.61}

 97%|█████████▋| 27184/28080 [53:42:28<1:46:56,  7.16s/it]
 97%|█████████▋| 27185/28080 [53:42:35<1:46:30,  7.14s/it]
                                                          
{'loss': 0.5956, 'learning_rate': 1.330918832202571e-06, 'epoch': 11.61}

 97%|█████████▋| 27185/28080 [53:42:36<1:46:30,  7.14s/it]
 97%|█████████▋| 27186/28080 [53:42:43<1:46:43,  7.16s/it]
                                                          
{'loss': 0.589, 'learning_rate': 1.3279490077456323e-06, 'epoch': 11.61}

 97%|█████████▋| 27186/28080 [53:42:43<1:46:43,  7.16s/it]
 97%|█████████▋| 27187/28080 [53:42:50<1:46:32,  7.16s/it]
                                                          
{'loss': 0.6117, 'learning_rate': 1.3249824916138354e-06, 'epoch': 11.61}

 97%|█████████▋| 27187/28080 [53:42:50<1:46:32,  7.16s/it]
 97%|█████████▋| 27188/28080 [53:42:57<1:46:29,  7.16s/it]
                                                          
{'loss': 0.5931, 'learning_rate': 1.322019283846565e-06, 'epoch': 11.61}

 97%|█████████▋| 27188/28080 [53:42:57<1:46:29,  7.16s/it]
 97%|█████████▋| 27189/28080 [53:43:04<1:45:43,  7.12s/it]
                                                          
{'loss': 0.6163, 'learning_rate': 1.3190593844833177e-06, 'epoch': 11.61}

 97%|█████████▋| 27189/28080 [53:43:04<1:45:43,  7.12s/it]
 97%|█████████▋| 27190/28080 [53:43:11<1:45:44,  7.13s/it]
                                                          
{'loss': 0.5859, 'learning_rate': 1.3161027935633951e-06, 'epoch': 11.62}

 97%|█████████▋| 27190/28080 [53:43:11<1:45:44,  7.13s/it]
 97%|█████████▋| 27191/28080 [53:43:19<1:46:24,  7.18s/it]
                                                          
{'loss': 0.6022, 'learning_rate': 1.3131495111261826e-06, 'epoch': 11.62}

 97%|█████████▋| 27191/28080 [53:43:19<1:46:24,  7.18s/it]
 97%|█████████▋| 27192/28080 [53:43:26<1:45:42,  7.14s/it]
                                                          
{'loss': 0.5799, 'learning_rate': 1.310199537210982e-06, 'epoch': 11.62}

 97%|█████████▋| 27192/28080 [53:43:26<1:45:42,  7.14s/it]
 97%|█████████▋| 27193/28080 [53:43:33<1:45:57,  7.17s/it]
                                                          
{'loss': 0.6049, 'learning_rate': 1.307252871857012e-06, 'epoch': 11.62}

 97%|█████████▋| 27193/28080 [53:43:33<1:45:57,  7.17s/it]
 97%|█████████▋| 27194/28080 [53:43:40<1:45:35,  7.15s/it]
                                                          
{'loss': 0.5847, 'learning_rate': 1.3043095151034634e-06, 'epoch': 11.62}

 97%|█████████▋| 27194/28080 [53:43:40<1:45:35,  7.15s/it]
 97%|█████████▋| 27195/28080 [53:43:47<1:45:16,  7.14s/it]
                                                          
{'loss': 0.6124, 'learning_rate': 1.3013694669895271e-06, 'epoch': 11.62}

 97%|█████████▋| 27195/28080 [53:43:47<1:45:16,  7.14s/it]
 97%|█████████▋| 27196/28080 [53:43:54<1:45:10,  7.14s/it]
                                                          
{'loss': 0.589, 'learning_rate': 1.2984327275542829e-06, 'epoch': 11.62}

 97%|█████████▋| 27196/28080 [53:43:54<1:45:10,  7.14s/it]
 97%|█████████▋| 27197/28080 [53:44:01<1:44:55,  7.13s/it]
                                                          
{'loss': 0.5989, 'learning_rate': 1.2954992968368384e-06, 'epoch': 11.62}

 97%|█████████▋| 27197/28080 [53:44:01<1:44:55,  7.13s/it]
 97%|█████████▋| 27198/28080 [53:44:08<1:44:55,  7.14s/it]
                                                          
{'loss': 0.611, 'learning_rate': 1.2925691748761903e-06, 'epoch': 11.62}

 97%|█████████▋| 27198/28080 [53:44:08<1:44:55,  7.14s/it]
 97%|█████████▋| 27199/28080 [53:44:16<1:44:58,  7.15s/it]
                                                          
{'loss': 0.5964, 'learning_rate': 1.289642361711335e-06, 'epoch': 11.62}

 97%|█████████▋| 27199/28080 [53:44:16<1:44:58,  7.15s/it]
 97%|█████████▋| 27200/28080 [53:44:23<1:44:49,  7.15s/it]
                                                          
{'loss': 0.6131, 'learning_rate': 1.286718857381214e-06, 'epoch': 11.62}

 97%|█████████▋| 27200/28080 [53:44:23<1:44:49,  7.15s/it]
 97%|█████████▋| 27201/28080 [53:44:30<1:44:09,  7.11s/it]
                                                          
{'loss': 0.5868, 'learning_rate': 1.2837986619247122e-06, 'epoch': 11.62}

 97%|█████████▋| 27201/28080 [53:44:30<1:44:09,  7.11s/it]
 97%|█████████▋| 27202/28080 [53:44:37<1:43:57,  7.10s/it]
                                                          
{'loss': 0.6092, 'learning_rate': 1.2808817753806879e-06, 'epoch': 11.62}

 97%|█████████▋| 27202/28080 [53:44:37<1:43:57,  7.10s/it]
 97%|█████████▋| 27203/28080 [53:44:44<1:43:59,  7.11s/it]
                                                          
{'loss': 0.6022, 'learning_rate': 1.2779681977879154e-06, 'epoch': 11.62}

 97%|█████████▋| 27203/28080 [53:44:44<1:43:59,  7.11s/it]
 97%|█████████▋| 27204/28080 [53:44:51<1:44:13,  7.14s/it]
                                                          
{'loss': 0.6123, 'learning_rate': 1.2750579291851972e-06, 'epoch': 11.62}

 97%|█████████▋| 27204/28080 [53:44:51<1:44:13,  7.14s/it]
 97%|█████████▋| 27205/28080 [53:44:58<1:44:16,  7.15s/it]
                                                          
{'loss': 0.5758, 'learning_rate': 1.272150969611252e-06, 'epoch': 11.62}

 97%|█████████▋| 27205/28080 [53:44:58<1:44:16,  7.15s/it]
 97%|█████████▋| 27206/28080 [53:45:06<1:44:13,  7.15s/it]
                                                          
{'loss': 0.6091, 'learning_rate': 1.2692473191047438e-06, 'epoch': 11.62}

 97%|█████████▋| 27206/28080 [53:45:06<1:44:13,  7.15s/it]
 97%|█████████▋| 27207/28080 [53:45:13<1:44:09,  7.16s/it]
                                                          
{'loss': 0.6011, 'learning_rate': 1.2663469777042803e-06, 'epoch': 11.62}

 97%|█████████▋| 27207/28080 [53:45:13<1:44:09,  7.16s/it]
 97%|█████████▋| 27208/28080 [53:45:20<1:43:56,  7.15s/it]
                                                          
{'loss': 0.5994, 'learning_rate': 1.263449945448497e-06, 'epoch': 11.62}

 97%|█████████▋| 27208/28080 [53:45:20<1:43:56,  7.15s/it]
 97%|█████████▋| 27209/28080 [53:45:27<1:43:11,  7.11s/it]
                                                          
{'loss': 0.5734, 'learning_rate': 1.2605562223758637e-06, 'epoch': 11.62}

 97%|█████████▋| 27209/28080 [53:45:27<1:43:11,  7.11s/it]
 97%|█████████▋| 27210/28080 [53:45:34<1:43:19,  7.13s/it]
                                                          
{'loss': 0.6071, 'learning_rate': 1.2576658085249327e-06, 'epoch': 11.62}

 97%|█████████▋| 27210/28080 [53:45:34<1:43:19,  7.13s/it]
 97%|█████████▋| 27211/28080 [53:45:41<1:43:24,  7.14s/it]
                                                          
{'loss': 0.599, 'learning_rate': 1.254778703934173e-06, 'epoch': 11.62}

 97%|█████████▋| 27211/28080 [53:45:41<1:43:24,  7.14s/it]
 97%|█████████▋| 27212/28080 [53:45:48<1:43:35,  7.16s/it]
                                                          
{'loss': 0.6003, 'learning_rate': 1.251894908641943e-06, 'epoch': 11.62}

 97%|█████████▋| 27212/28080 [53:45:48<1:43:35,  7.16s/it]
 97%|█████████▋| 27213/28080 [53:45:56<1:43:42,  7.18s/it]
                                                          
{'loss': 0.6056, 'learning_rate': 1.2490144226866285e-06, 'epoch': 11.63}

 97%|█████████▋| 27213/28080 [53:45:56<1:43:42,  7.18s/it]
 97%|█████████▋| 27214/28080 [53:46:03<1:43:43,  7.19s/it]
                                                          
{'loss': 0.6096, 'learning_rate': 1.2461372461065602e-06, 'epoch': 11.63}

 97%|█████████▋| 27214/28080 [53:46:03<1:43:43,  7.19s/it]
 97%|█████████▋| 27215/28080 [53:46:10<1:43:22,  7.17s/it]
                                                          
{'loss': 0.5944, 'learning_rate': 1.243263378939985e-06, 'epoch': 11.63}

 97%|█████████▋| 27215/28080 [53:46:10<1:43:22,  7.17s/it]
 97%|█████████▋| 27216/28080 [53:46:17<1:42:57,  7.15s/it]
                                                          
{'loss': 0.5879, 'learning_rate': 1.2403928212252059e-06, 'epoch': 11.63}

 97%|█████████▋| 27216/28080 [53:46:17<1:42:57,  7.15s/it]
 97%|█████████▋| 27217/28080 [53:46:24<1:42:32,  7.13s/it]
                                                          
{'loss': 0.6249, 'learning_rate': 1.2375255730003586e-06, 'epoch': 11.63}

 97%|█████████▋| 27217/28080 [53:46:24<1:42:32,  7.13s/it]
 97%|█████████▋| 27218/28080 [53:46:31<1:41:52,  7.09s/it]
                                                          
{'loss': 0.5924, 'learning_rate': 1.23466163430358e-06, 'epoch': 11.63}

 97%|█████████▋| 27218/28080 [53:46:31<1:41:52,  7.09s/it]
 97%|█████████▋| 27219/28080 [53:46:38<1:41:54,  7.10s/it]
                                                          
{'loss': 0.5883, 'learning_rate': 1.2318010051730056e-06, 'epoch': 11.63}

 97%|█████████▋| 27219/28080 [53:46:38<1:41:54,  7.10s/it]
 97%|█████████▋| 27220/28080 [53:46:45<1:41:54,  7.11s/it]
                                                          
{'loss': 0.5836, 'learning_rate': 1.2289436856466607e-06, 'epoch': 11.63}

 97%|█████████▋| 27220/28080 [53:46:45<1:41:54,  7.11s/it]
 97%|█████████▋| 27221/28080 [53:46:53<1:42:03,  7.13s/it]
                                                          
{'loss': 0.607, 'learning_rate': 1.2260896757625983e-06, 'epoch': 11.63}

 97%|█████████▋| 27221/28080 [53:46:53<1:42:03,  7.13s/it]
 97%|█████████▋| 27222/28080 [53:47:00<1:42:17,  7.15s/it]
                                                          
{'loss': 0.5935, 'learning_rate': 1.2232389755587603e-06, 'epoch': 11.63}

 97%|█████████▋| 27222/28080 [53:47:00<1:42:17,  7.15s/it]
 97%|█████████▋| 27223/28080 [53:47:07<1:42:22,  7.17s/it]
                                                          
{'loss': 0.5881, 'learning_rate': 1.2203915850730884e-06, 'epoch': 11.63}

 97%|█████████▋| 27223/28080 [53:47:07<1:42:22,  7.17s/it]
 97%|█████████▋| 27224/28080 [53:47:14<1:42:19,  7.17s/it]
                                                          
{'loss': 0.6143, 'learning_rate': 1.2175475043434415e-06, 'epoch': 11.63}

 97%|█████████▋| 27224/28080 [53:47:14<1:42:19,  7.17s/it]
 97%|█████████▋| 27225/28080 [53:47:21<1:41:55,  7.15s/it]
                                                          
{'loss': 0.6025, 'learning_rate': 1.2147067334076778e-06, 'epoch': 11.63}

 97%|█████████▋| 27225/28080 [53:47:21<1:41:55,  7.15s/it]
 97%|█████████▋| 27226/28080 [53:47:29<1:42:42,  7.22s/it]
                                                          
{'loss': 0.5829, 'learning_rate': 1.2118692723036007e-06, 'epoch': 11.63}

 97%|█████████▋| 27226/28080 [53:47:29<1:42:42,  7.22s/it]
 97%|█████████▋| 27227/28080 [53:47:36<1:41:58,  7.17s/it]
                                                          
{'loss': 0.6102, 'learning_rate': 1.2090351210689021e-06, 'epoch': 11.63}

 97%|█████████▋| 27227/28080 [53:47:36<1:41:58,  7.17s/it]
 97%|█████████▋| 27228/28080 [53:47:43<1:41:52,  7.17s/it]
                                                          
{'loss': 0.6039, 'learning_rate': 1.2062042797413575e-06, 'epoch': 11.63}

 97%|█████████▋| 27228/28080 [53:47:43<1:41:52,  7.17s/it]
 97%|█████████▋| 27229/28080 [53:47:50<1:41:18,  7.14s/it]
                                                          
{'loss': 0.6067, 'learning_rate': 1.2033767483585757e-06, 'epoch': 11.63}

 97%|█████████▋| 27229/28080 [53:47:50<1:41:18,  7.14s/it]
 97%|█████████▋| 27230/28080 [53:47:57<1:41:30,  7.16s/it]
                                                          
{'loss': 0.597, 'learning_rate': 1.2005525269582208e-06, 'epoch': 11.63}

 97%|█████████▋| 27230/28080 [53:47:57<1:41:30,  7.16s/it]
 97%|█████████▋| 27231/28080 [53:48:04<1:41:25,  7.17s/it]
                                                          
{'loss': 0.5965, 'learning_rate': 1.1977316155778183e-06, 'epoch': 11.63}

 97%|█████████▋| 27231/28080 [53:48:04<1:41:25,  7.17s/it]
 97%|█████████▋| 27232/28080 [53:48:12<1:41:23,  7.17s/it]
                                                          
{'loss': 0.6212, 'learning_rate': 1.1949140142549497e-06, 'epoch': 11.63}

 97%|█████████▋| 27232/28080 [53:48:12<1:41:23,  7.17s/it]
 97%|█████████▋| 27233/28080 [53:48:19<1:41:01,  7.16s/it]
                                                          
{'loss': 0.6019, 'learning_rate': 1.192099723027057e-06, 'epoch': 11.63}

 97%|█████████▋| 27233/28080 [53:48:19<1:41:01,  7.16s/it]
 97%|█████████▋| 27234/28080 [53:48:26<1:41:04,  7.17s/it]
                                                          
{'loss': 0.6093, 'learning_rate': 1.1892887419316102e-06, 'epoch': 11.63}

 97%|█████████▋| 27234/28080 [53:48:26<1:41:04,  7.17s/it]
 97%|█████████▋| 27235/28080 [53:48:33<1:41:08,  7.18s/it]
                                                          
{'loss': 0.6115, 'learning_rate': 1.1864810710059682e-06, 'epoch': 11.63}

 97%|█████████▋| 27235/28080 [53:48:33<1:41:08,  7.18s/it]
 97%|█████████▋| 27236/28080 [53:48:40<1:40:48,  7.17s/it]
                                                          
{'loss': 0.5765, 'learning_rate': 1.183676710287518e-06, 'epoch': 11.63}

 97%|█████████▋| 27236/28080 [53:48:40<1:40:48,  7.17s/it]
 97%|█████████▋| 27237/28080 [53:48:47<1:40:09,  7.13s/it]
                                                          
{'loss': 0.5878, 'learning_rate': 1.1808756598135905e-06, 'epoch': 11.64}

 97%|█████████▋| 27237/28080 [53:48:47<1:40:09,  7.13s/it]
 97%|█████████▋| 27238/28080 [53:48:54<1:39:56,  7.12s/it]
                                                          
{'loss': 0.5915, 'learning_rate': 1.1780779196213788e-06, 'epoch': 11.64}

 97%|█████████▋| 27238/28080 [53:48:54<1:39:56,  7.12s/it]
 97%|█████████▋| 27239/28080 [53:49:01<1:39:39,  7.11s/it]
                                                          
{'loss': 0.6224, 'learning_rate': 1.1752834897481579e-06, 'epoch': 11.64}

 97%|█████████▋| 27239/28080 [53:49:01<1:39:39,  7.11s/it]
 97%|█████████▋| 27240/28080 [53:49:08<1:39:24,  7.10s/it]
                                                          
{'loss': 0.6055, 'learning_rate': 1.172492370231093e-06, 'epoch': 11.64}

 97%|█████████▋| 27240/28080 [53:49:08<1:39:24,  7.10s/it]
 97%|█████████▋| 27241/28080 [53:49:16<1:39:12,  7.09s/it]
                                                          
{'loss': 0.5856, 'learning_rate': 1.169704561107321e-06, 'epoch': 11.64}

 97%|█████████▋| 27241/28080 [53:49:16<1:39:12,  7.09s/it]
 97%|█████████▋| 27242/28080 [53:49:23<1:38:30,  7.05s/it]
                                                          
{'loss': 0.6171, 'learning_rate': 1.1669200624139231e-06, 'epoch': 11.64}

 97%|█████████▋| 27242/28080 [53:49:23<1:38:30,  7.05s/it]
 97%|█████████▋| 27243/28080 [53:49:30<1:38:29,  7.06s/it]
                                                          
{'loss': 0.5952, 'learning_rate': 1.1641388741879255e-06, 'epoch': 11.64}

 97%|█████████▋| 27243/28080 [53:49:30<1:38:29,  7.06s/it]
 97%|█████████▋| 27244/28080 [53:49:37<1:38:32,  7.07s/it]
                                                          
{'loss': 0.5918, 'learning_rate': 1.1613609964663818e-06, 'epoch': 11.64}

 97%|█████████▋| 27244/28080 [53:49:37<1:38:32,  7.07s/it]
 97%|█████████▋| 27245/28080 [53:49:44<1:38:41,  7.09s/it]
                                                          
{'loss': 0.6011, 'learning_rate': 1.158586429286207e-06, 'epoch': 11.64}

 97%|█████████▋| 27245/28080 [53:49:44<1:38:41,  7.09s/it]
 97%|█████████▋| 27246/28080 [53:49:51<1:38:09,  7.06s/it]
                                                          
{'loss': 0.5915, 'learning_rate': 1.1558151726843158e-06, 'epoch': 11.64}

 97%|█████████▋| 27246/28080 [53:49:51<1:38:09,  7.06s/it]
 97%|█████████▋| 27247/28080 [53:49:58<1:38:27,  7.09s/it]
                                                          
{'loss': 0.5912, 'learning_rate': 1.1530472266975956e-06, 'epoch': 11.64}

 97%|█████████▋| 27247/28080 [53:49:58<1:38:27,  7.09s/it]
 97%|█████████▋| 27248/28080 [53:50:05<1:38:39,  7.11s/it]
                                                          
{'loss': 0.6062, 'learning_rate': 1.1502825913628502e-06, 'epoch': 11.64}

 97%|█████████▋| 27248/28080 [53:50:05<1:38:39,  7.11s/it]
 97%|█████████▋| 27249/28080 [53:50:12<1:39:03,  7.15s/it]
                                                          
{'loss': 0.5743, 'learning_rate': 1.1475212667168832e-06, 'epoch': 11.64}

 97%|█████████▋| 27249/28080 [53:50:12<1:39:03,  7.15s/it]
 97%|█████████▋| 27250/28080 [53:50:20<1:38:54,  7.15s/it]
                                                          
{'loss': 0.5951, 'learning_rate': 1.1447632527964159e-06, 'epoch': 11.64}

 97%|█████████▋| 27250/28080 [53:50:20<1:38:54,  7.15s/it]
 97%|█████████▋| 27251/28080 [53:50:27<1:38:53,  7.16s/it]
                                                          
{'loss': 0.6124, 'learning_rate': 1.1420085496381405e-06, 'epoch': 11.64}

 97%|█████████▋| 27251/28080 [53:50:27<1:38:53,  7.16s/it]
 97%|█████████▋| 27252/28080 [53:50:34<1:38:57,  7.17s/it]
                                                          
{'loss': 0.5825, 'learning_rate': 1.1392571572787225e-06, 'epoch': 11.64}

 97%|█████████▋| 27252/28080 [53:50:34<1:38:57,  7.17s/it]
 97%|█████████▋| 27253/28080 [53:50:41<1:38:53,  7.17s/it]
                                                          
{'loss': 0.5868, 'learning_rate': 1.1365090757547437e-06, 'epoch': 11.64}

 97%|█████████▋| 27253/28080 [53:50:41<1:38:53,  7.17s/it]
 97%|█████████▋| 27254/28080 [53:50:48<1:37:45,  7.10s/it]
                                                          
{'loss': 0.6179, 'learning_rate': 1.1337643051027579e-06, 'epoch': 11.64}

 97%|█████████▋| 27254/28080 [53:50:48<1:37:45,  7.10s/it]
 97%|█████████▋| 27255/28080 [53:50:55<1:38:08,  7.14s/it]
                                                          
{'loss': 0.5918, 'learning_rate': 1.1310228453593197e-06, 'epoch': 11.64}

 97%|█████████▋| 27255/28080 [53:50:55<1:38:08,  7.14s/it]
 97%|█████████▋| 27256/28080 [53:51:02<1:37:38,  7.11s/it]
                                                          
{'loss': 0.6135, 'learning_rate': 1.1282846965608718e-06, 'epoch': 11.64}

 97%|█████████▋| 27256/28080 [53:51:02<1:37:38,  7.11s/it]
 97%|█████████▋| 27257/28080 [53:51:09<1:37:34,  7.11s/it]
                                                          
{'loss': 0.6055, 'learning_rate': 1.1255498587438295e-06, 'epoch': 11.64}

 97%|█████████▋| 27257/28080 [53:51:09<1:37:34,  7.11s/it]
 97%|█████████▋| 27258/28080 [53:51:16<1:37:19,  7.10s/it]
                                                          
{'loss': 0.6044, 'learning_rate': 1.122818331944636e-06, 'epoch': 11.64}

 97%|█████████▋| 27258/28080 [53:51:16<1:37:19,  7.10s/it]
 97%|█████████▋| 27259/28080 [53:51:24<1:37:14,  7.11s/it]
                                                          
{'loss': 0.6068, 'learning_rate': 1.120090116199568e-06, 'epoch': 11.64}

 97%|█████████▋| 27259/28080 [53:51:24<1:37:14,  7.11s/it]
 97%|█████████▋| 27260/28080 [53:51:31<1:37:09,  7.11s/it]
                                                          
{'loss': 0.6166, 'learning_rate': 1.1173652115449573e-06, 'epoch': 11.65}

 97%|█████████▋| 27260/28080 [53:51:31<1:37:09,  7.11s/it]
 97%|█████████▋| 27261/28080 [53:51:38<1:37:15,  7.13s/it]
                                                          
{'loss': 0.5941, 'learning_rate': 1.1146436180170249e-06, 'epoch': 11.65}

 97%|█████████▋| 27261/28080 [53:51:38<1:37:15,  7.13s/it]
 97%|█████████▋| 27262/28080 [53:51:45<1:36:58,  7.11s/it]
                                                          
{'loss': 0.5959, 'learning_rate': 1.111925335651992e-06, 'epoch': 11.65}

 97%|█████████▋| 27262/28080 [53:51:45<1:36:58,  7.11s/it]
 97%|█████████▋| 27263/28080 [53:51:52<1:37:06,  7.13s/it]
                                                          
{'loss': 0.6032, 'learning_rate': 1.1092103644860519e-06, 'epoch': 11.65}

 97%|█████████▋| 27263/28080 [53:51:52<1:37:06,  7.13s/it]
 97%|█████████▋| 27264/28080 [53:51:59<1:36:56,  7.13s/it]
                                                          
{'loss': 0.5793, 'learning_rate': 1.1064987045553142e-06, 'epoch': 11.65}

 97%|█████████▋| 27264/28080 [53:51:59<1:36:56,  7.13s/it]
 97%|█████████▋| 27265/28080 [53:52:06<1:36:48,  7.13s/it]
                                                          
{'loss': 0.5997, 'learning_rate': 1.1037903558958061e-06, 'epoch': 11.65}

 97%|█████████▋| 27265/28080 [53:52:06<1:36:48,  7.13s/it]
 97%|█████████▋| 27266/28080 [53:52:14<1:37:00,  7.15s/it]
                                                          
{'loss': 0.6145, 'learning_rate': 1.10108531854361e-06, 'epoch': 11.65}

 97%|█████████▋| 27266/28080 [53:52:14<1:37:00,  7.15s/it]
 97%|█████████▋| 27267/28080 [53:52:21<1:36:44,  7.14s/it]
                                                          
{'loss': 0.5987, 'learning_rate': 1.0983835925346962e-06, 'epoch': 11.65}

 97%|█████████▋| 27267/28080 [53:52:21<1:36:44,  7.14s/it]
 97%|█████████▋| 27268/28080 [53:52:28<1:36:36,  7.14s/it]
                                                          
{'loss': 0.587, 'learning_rate': 1.0956851779050092e-06, 'epoch': 11.65}

 97%|█████████▋| 27268/28080 [53:52:28<1:36:36,  7.14s/it]
 97%|█████████▋| 27269/28080 [53:52:35<1:36:34,  7.14s/it]
                                                          
{'loss': 0.5893, 'learning_rate': 1.0929900746904641e-06, 'epoch': 11.65}

 97%|█████████▋| 27269/28080 [53:52:35<1:36:34,  7.14s/it]
 97%|█████████▋| 27270/28080 [53:52:42<1:36:20,  7.14s/it]
                                                          
{'loss': 0.5991, 'learning_rate': 1.0902982829269214e-06, 'epoch': 11.65}

 97%|█████████▋| 27270/28080 [53:52:42<1:36:20,  7.14s/it]
 97%|█████████▋| 27271/28080 [53:52:49<1:36:48,  7.18s/it]
                                                          
{'loss': 0.5935, 'learning_rate': 1.0876098026501301e-06, 'epoch': 11.65}

 97%|█████████▋| 27271/28080 [53:52:49<1:36:48,  7.18s/it]
 97%|█████████▋| 27272/28080 [53:52:57<1:36:39,  7.18s/it]
                                                          
{'loss': 0.5787, 'learning_rate': 1.084924633895923e-06, 'epoch': 11.65}

 97%|█████████▋| 27272/28080 [53:52:57<1:36:39,  7.18s/it]
 97%|█████████▋| 27273/28080 [53:53:04<1:36:08,  7.15s/it]
                                                          
{'loss': 0.605, 'learning_rate': 1.0822427766999933e-06, 'epoch': 11.65}

 97%|█████████▋| 27273/28080 [53:53:04<1:36:08,  7.15s/it]
 97%|█████████▋| 27274/28080 [53:53:11<1:36:10,  7.16s/it]
                                                          
{'loss': 0.5891, 'learning_rate': 1.0795642310980624e-06, 'epoch': 11.65}

 97%|█████████▋| 27274/28080 [53:53:11<1:36:10,  7.16s/it]
 97%|█████████▋| 27275/28080 [53:53:18<1:35:56,  7.15s/it]
                                                          
{'loss': 0.5869, 'learning_rate': 1.0768889971256857e-06, 'epoch': 11.65}

 97%|█████████▋| 27275/28080 [53:53:18<1:35:56,  7.15s/it]
 97%|█████████▋| 27276/28080 [53:53:25<1:36:13,  7.18s/it]
                                                          
{'loss': 0.6, 'learning_rate': 1.0742170748185287e-06, 'epoch': 11.65}

 97%|█████████▋| 27276/28080 [53:53:25<1:36:13,  7.18s/it]
 97%|█████████▋| 27277/28080 [53:53:32<1:35:36,  7.14s/it]
                                                          
{'loss': 0.6061, 'learning_rate': 1.071548464212091e-06, 'epoch': 11.65}

 97%|█████████▋| 27277/28080 [53:53:32<1:35:36,  7.14s/it]
 97%|█████████▋| 27278/28080 [53:53:39<1:35:45,  7.16s/it]
                                                          
{'loss': 0.6089, 'learning_rate': 1.0688831653419274e-06, 'epoch': 11.65}

 97%|█████████▋| 27278/28080 [53:53:39<1:35:45,  7.16s/it]
 97%|█████████▋| 27279/28080 [53:53:47<1:35:21,  7.14s/it]
                                                          
{'loss': 0.5933, 'learning_rate': 1.066221178243426e-06, 'epoch': 11.65}

 97%|█████████▋| 27279/28080 [53:53:47<1:35:21,  7.14s/it]
 97%|█████████▋| 27280/28080 [53:53:54<1:35:17,  7.15s/it]
                                                          
{'loss': 0.5907, 'learning_rate': 1.0635625029520868e-06, 'epoch': 11.65}

 97%|█████████▋| 27280/28080 [53:53:54<1:35:17,  7.15s/it]
 97%|█████████▋| 27281/28080 [53:54:01<1:34:51,  7.12s/it]
                                                          
{'loss': 0.6069, 'learning_rate': 1.0609071395031865e-06, 'epoch': 11.65}

 97%|█████████▋| 27281/28080 [53:54:01<1:34:51,  7.12s/it]
 97%|█████████▋| 27282/28080 [53:54:08<1:34:42,  7.12s/it]
                                                          
{'loss': 0.5746, 'learning_rate': 1.0582550879321417e-06, 'epoch': 11.65}

 97%|█████████▋| 27282/28080 [53:54:08<1:34:42,  7.12s/it]
 97%|█████████▋| 27283/28080 [53:54:15<1:34:37,  7.12s/it]
                                                          
{'loss': 0.5782, 'learning_rate': 1.055606348274174e-06, 'epoch': 11.66}

 97%|█████████▋| 27283/28080 [53:54:15<1:34:37,  7.12s/it]
 97%|█████████▋| 27284/28080 [53:54:22<1:34:40,  7.14s/it]
                                                          
{'loss': 0.5991, 'learning_rate': 1.0529609205645329e-06, 'epoch': 11.66}

 97%|█████████▋| 27284/28080 [53:54:22<1:34:40,  7.14s/it]
 97%|█████████▋| 27285/28080 [53:54:29<1:34:30,  7.13s/it]
                                                          
{'loss': 0.5917, 'learning_rate': 1.0503188048384404e-06, 'epoch': 11.66}

 97%|█████████▋| 27285/28080 [53:54:29<1:34:30,  7.13s/it]
 97%|█████████▋| 27286/28080 [53:54:36<1:33:51,  7.09s/it]
                                                          
{'loss': 0.5851, 'learning_rate': 1.047680001131035e-06, 'epoch': 11.66}

 97%|█████████▋| 27286/28080 [53:54:36<1:33:51,  7.09s/it]
 97%|█████████▋| 27287/28080 [53:54:43<1:33:43,  7.09s/it]
                                                          
{'loss': 0.5768, 'learning_rate': 1.0450445094773998e-06, 'epoch': 11.66}

 97%|█████████▋| 27287/28080 [53:54:43<1:33:43,  7.09s/it]
 97%|█████████▋| 27288/28080 [53:54:51<1:33:46,  7.10s/it]
                                                          
{'loss': 0.6042, 'learning_rate': 1.0424123299126175e-06, 'epoch': 11.66}

 97%|█████████▋| 27288/28080 [53:54:51<1:33:46,  7.10s/it]
 97%|█████████▋| 27289/28080 [53:54:58<1:33:56,  7.13s/it]
                                                          
{'loss': 0.6067, 'learning_rate': 1.0397834624717162e-06, 'epoch': 11.66}

 97%|█████████▋| 27289/28080 [53:54:58<1:33:56,  7.13s/it]
 97%|█████████▋| 27290/28080 [53:55:05<1:33:22,  7.09s/it]
                                                          
{'loss': 0.5959, 'learning_rate': 1.0371579071896398e-06, 'epoch': 11.66}

 97%|█████████▋| 27290/28080 [53:55:05<1:33:22,  7.09s/it]
 97%|█████████▋| 27291/28080 [53:55:12<1:33:13,  7.09s/it]
                                                          
{'loss': 0.5959, 'learning_rate': 1.0345356641013327e-06, 'epoch': 11.66}

 97%|█████████▋| 27291/28080 [53:55:12<1:33:13,  7.09s/it]
 97%|█████████▋| 27292/28080 [53:55:19<1:33:21,  7.11s/it]
                                                          
{'loss': 0.5943, 'learning_rate': 1.0319167332417113e-06, 'epoch': 11.66}

 97%|█████████▋| 27292/28080 [53:55:19<1:33:21,  7.11s/it]
 97%|█████████▋| 27293/28080 [53:55:26<1:33:05,  7.10s/it]
                                                          
{'loss': 0.6012, 'learning_rate': 1.029301114645581e-06, 'epoch': 11.66}

 97%|█████████▋| 27293/28080 [53:55:26<1:33:05,  7.10s/it]
 97%|█████████▋| 27294/28080 [53:55:33<1:33:08,  7.11s/it]
                                                          
{'loss': 0.5833, 'learning_rate': 1.0266888083477478e-06, 'epoch': 11.66}

 97%|█████████▋| 27294/28080 [53:55:33<1:33:08,  7.11s/it]
 97%|█████████▋| 27295/28080 [53:55:40<1:33:12,  7.12s/it]
                                                          
{'loss': 0.586, 'learning_rate': 1.024079814382961e-06, 'epoch': 11.66}

 97%|█████████▋| 27295/28080 [53:55:40<1:33:12,  7.12s/it]
 97%|█████████▋| 27296/28080 [53:55:47<1:33:01,  7.12s/it]
                                                          
{'loss': 0.6029, 'learning_rate': 1.0214741327859433e-06, 'epoch': 11.66}

 97%|█████████▋| 27296/28080 [53:55:47<1:33:01,  7.12s/it]
 97%|█████████▋| 27297/28080 [53:55:55<1:33:08,  7.14s/it]
                                                          
{'loss': 0.5869, 'learning_rate': 1.0188717635913614e-06, 'epoch': 11.66}

 97%|█████████▋| 27297/28080 [53:55:55<1:33:08,  7.14s/it]
 97%|█████████▋| 27298/28080 [53:56:02<1:33:19,  7.16s/it]
                                                          
{'loss': 0.5861, 'learning_rate': 1.0162727068338262e-06, 'epoch': 11.66}

 97%|█████████▋| 27298/28080 [53:56:02<1:33:19,  7.16s/it]
 97%|█████████▋| 27299/28080 [53:56:09<1:32:55,  7.14s/it]
                                                          
{'loss': 0.6064, 'learning_rate': 1.0136769625479215e-06, 'epoch': 11.66}

 97%|█████████▋| 27299/28080 [53:56:09<1:32:55,  7.14s/it]
 97%|█████████▋| 27300/28080 [53:56:16<1:32:49,  7.14s/it]
                                                          
{'loss': 0.6, 'learning_rate': 1.0110845307681748e-06, 'epoch': 11.66}

 97%|█████████▋| 27300/28080 [53:56:16<1:32:49,  7.14s/it]
 97%|█████████▋| 27301/28080 [53:56:23<1:32:23,  7.12s/it]
                                                          
{'loss': 0.6131, 'learning_rate': 1.0084954115290868e-06, 'epoch': 11.66}

 97%|█████████▋| 27301/28080 [53:56:23<1:32:23,  7.12s/it]
 97%|█████████▋| 27302/28080 [53:56:30<1:32:18,  7.12s/it]
                                                          
{'loss': 0.5966, 'learning_rate': 1.0059096048651017e-06, 'epoch': 11.66}

 97%|█████████▋| 27302/28080 [53:56:30<1:32:18,  7.12s/it]
 97%|█████████▋| 27303/28080 [53:56:37<1:32:11,  7.12s/it]
                                                          
{'loss': 0.6039, 'learning_rate': 1.003327110810609e-06, 'epoch': 11.66}

 97%|█████████▋| 27303/28080 [53:56:37<1:32:11,  7.12s/it]
 97%|█████████▋| 27304/28080 [53:56:45<1:32:07,  7.12s/it]
                                                          
{'loss': 0.5881, 'learning_rate': 1.00074792939997e-06, 'epoch': 11.66}

 97%|█████████▋| 27304/28080 [53:56:45<1:32:07,  7.12s/it]
 97%|█████████▋| 27305/28080 [53:56:52<1:31:47,  7.11s/it]
                                                          
{'loss': 0.5922, 'learning_rate': 9.981720606675182e-07, 'epoch': 11.66}

 97%|█████████▋| 27305/28080 [53:56:52<1:31:47,  7.11s/it]
 97%|█████████▋| 27306/28080 [53:56:59<1:32:01,  7.13s/it]
                                                          
{'loss': 0.6087, 'learning_rate': 9.955995046474764e-07, 'epoch': 11.66}

 97%|█████████▋| 27306/28080 [53:56:59<1:32:01,  7.13s/it]
 97%|█████████▋| 27307/28080 [53:57:06<1:31:51,  7.13s/it]
                                                          
{'loss': 0.5757, 'learning_rate': 9.930302613741504e-07, 'epoch': 11.67}

 97%|█████████▋| 27307/28080 [53:57:06<1:31:51,  7.13s/it]
 97%|█████████▋| 27308/28080 [53:57:13<1:31:53,  7.14s/it]
                                                          
{'loss': 0.6091, 'learning_rate': 9.904643308816242e-07, 'epoch': 11.67}

 97%|█████████▋| 27308/28080 [53:57:13<1:31:53,  7.14s/it]
 97%|█████████▋| 27309/28080 [53:57:20<1:31:44,  7.14s/it]
                                                          
{'loss': 0.5977, 'learning_rate': 9.879017132040924e-07, 'epoch': 11.67}

 97%|█████████▋| 27309/28080 [53:57:20<1:31:44,  7.14s/it]
 97%|█████████▋| 27310/28080 [53:57:27<1:31:49,  7.16s/it]
                                                          
{'loss': 0.6128, 'learning_rate': 9.85342408375639e-07, 'epoch': 11.67}

 97%|█████████▋| 27310/28080 [53:57:27<1:31:49,  7.16s/it]
 97%|█████████▋| 27311/28080 [53:57:35<1:32:09,  7.19s/it]
                                                          
{'loss': 0.5756, 'learning_rate': 9.827864164303203e-07, 'epoch': 11.67}

 97%|█████████▋| 27311/28080 [53:57:35<1:32:09,  7.19s/it]
 97%|█████████▋| 27312/28080 [53:57:42<1:31:42,  7.16s/it]
                                                          
{'loss': 0.6069, 'learning_rate': 9.802337374021363e-07, 'epoch': 11.67}

 97%|█████████▋| 27312/28080 [53:57:42<1:31:42,  7.16s/it]
 97%|█████████▋| 27313/28080 [53:57:49<1:31:47,  7.18s/it]
                                                          
{'loss': 0.5942, 'learning_rate': 9.77684371325005e-07, 'epoch': 11.67}

 97%|█████████▋| 27313/28080 [53:57:49<1:31:47,  7.18s/it]
 97%|█████████▋| 27314/28080 [53:57:56<1:31:45,  7.19s/it]
                                                          
{'loss': 0.5782, 'learning_rate': 9.751383182329265e-07, 'epoch': 11.67}

 97%|█████████▋| 27314/28080 [53:57:56<1:31:45,  7.19s/it]
 97%|█████████▋| 27315/28080 [53:58:03<1:31:49,  7.20s/it]
                                                          
{'loss': 0.6158, 'learning_rate': 9.725955781597073e-07, 'epoch': 11.67}

 97%|█████████▋| 27315/28080 [53:58:03<1:31:49,  7.20s/it]
 97%|█████████▋| 27316/28080 [53:58:11<1:31:55,  7.22s/it]
                                                          
{'loss': 0.6309, 'learning_rate': 9.700561511391814e-07, 'epoch': 11.67}

 97%|█████████▋| 27316/28080 [53:58:11<1:31:55,  7.22s/it]
 97%|█████████▋| 27317/28080 [53:58:18<1:31:07,  7.17s/it]
                                                          
{'loss': 0.5906, 'learning_rate': 9.67520037205183e-07, 'epoch': 11.67}

 97%|█████████▋| 27317/28080 [53:58:18<1:31:07,  7.17s/it]
 97%|█████████▋| 27318/28080 [53:58:25<1:30:58,  7.16s/it]
                                                          
{'loss': 0.597, 'learning_rate': 9.649872363913791e-07, 'epoch': 11.67}

 97%|█████████▋| 27318/28080 [53:58:25<1:30:58,  7.16s/it]
 97%|█████████▋| 27319/28080 [53:58:32<1:30:49,  7.16s/it]
                                                          
{'loss': 0.6155, 'learning_rate': 9.62457748731521e-07, 'epoch': 11.67}

 97%|█████████▋| 27319/28080 [53:58:32<1:30:49,  7.16s/it]
 97%|█████████▋| 27320/28080 [53:58:39<1:30:38,  7.16s/it]
                                                          
{'loss': 0.5941, 'learning_rate': 9.599315742592485e-07, 'epoch': 11.67}

 97%|█████████▋| 27320/28080 [53:58:39<1:30:38,  7.16s/it]
 97%|█████████▋| 27321/28080 [53:58:46<1:30:21,  7.14s/it]
                                                          
{'loss': 0.6065, 'learning_rate': 9.574087130081733e-07, 'epoch': 11.67}

 97%|█████████▋| 27321/28080 [53:58:46<1:30:21,  7.14s/it]
 97%|█████████▋| 27322/28080 [53:58:53<1:29:59,  7.12s/it]
                                                          
{'loss': 0.6087, 'learning_rate': 9.548891650118518e-07, 'epoch': 11.67}

 97%|█████████▋| 27322/28080 [53:58:53<1:29:59,  7.12s/it]
 97%|█████████▋| 27323/28080 [53:59:01<1:29:50,  7.12s/it]
                                                          
{'loss': 0.6184, 'learning_rate': 9.523729303037853e-07, 'epoch': 11.67}

 97%|█████████▋| 27323/28080 [53:59:01<1:29:50,  7.12s/it]
 97%|█████████▋| 27324/28080 [53:59:08<1:29:54,  7.14s/it]
                                                          
{'loss': 0.6211, 'learning_rate': 9.498600089175025e-07, 'epoch': 11.67}

 97%|█████████▋| 27324/28080 [53:59:08<1:29:54,  7.14s/it]
 97%|█████████▋| 27325/28080 [53:59:15<1:29:27,  7.11s/it]
                                                          
{'loss': 0.637, 'learning_rate': 9.473504008863653e-07, 'epoch': 11.67}

 97%|█████████▋| 27325/28080 [53:59:15<1:29:27,  7.11s/it]
 97%|█████████▋| 27326/28080 [53:59:22<1:29:31,  7.12s/it]
                                                          
{'loss': 0.604, 'learning_rate': 9.448441062438195e-07, 'epoch': 11.67}

 97%|█████████▋| 27326/28080 [53:59:22<1:29:31,  7.12s/it]
 97%|█████████▋| 27327/28080 [53:59:29<1:29:53,  7.16s/it]
                                                          
{'loss': 0.6065, 'learning_rate': 9.423411250231717e-07, 'epoch': 11.67}

 97%|█████████▋| 27327/28080 [53:59:29<1:29:53,  7.16s/it]
 97%|█████████▋| 27328/28080 [53:59:36<1:29:33,  7.15s/it]
                                                          
{'loss': 0.5967, 'learning_rate': 9.398414572577563e-07, 'epoch': 11.67}

 97%|█████████▋| 27328/28080 [53:59:36<1:29:33,  7.15s/it]
 97%|█████████▋| 27329/28080 [53:59:43<1:29:18,  7.13s/it]
                                                          
{'loss': 0.5933, 'learning_rate': 9.373451029807966e-07, 'epoch': 11.67}

 97%|█████████▋| 27329/28080 [53:59:43<1:29:18,  7.13s/it]
 97%|█████████▋| 27330/28080 [53:59:50<1:29:08,  7.13s/it]
                                                          
{'loss': 0.5947, 'learning_rate': 9.348520622255164e-07, 'epoch': 11.68}

 97%|█████████▋| 27330/28080 [53:59:50<1:29:08,  7.13s/it]
 97%|█████████▋| 27331/28080 [53:59:57<1:28:32,  7.09s/it]
                                                          
{'loss': 0.6086, 'learning_rate': 9.323623350250832e-07, 'epoch': 11.68}

 97%|█████████▋| 27331/28080 [53:59:57<1:28:32,  7.09s/it]
 97%|█████████▋| 27332/28080 [54:00:05<1:28:39,  7.11s/it]
                                                          
{'loss': 0.5736, 'learning_rate': 9.298759214126095e-07, 'epoch': 11.68}

 97%|█████████▋| 27332/28080 [54:00:05<1:28:39,  7.11s/it]
 97%|█████████▋| 27333/28080 [54:00:12<1:28:32,  7.11s/it]
                                                          
{'loss': 0.6088, 'learning_rate': 9.27392821421208e-07, 'epoch': 11.68}

 97%|█████████▋| 27333/28080 [54:00:12<1:28:32,  7.11s/it]
 97%|█████████▋| 27334/28080 [54:00:19<1:28:30,  7.12s/it]
                                                          
{'loss': 0.6, 'learning_rate': 9.249130350838796e-07, 'epoch': 11.68}

 97%|█████████▋| 27334/28080 [54:00:19<1:28:30,  7.12s/it]
 97%|█████████▋| 27335/28080 [54:00:26<1:28:41,  7.14s/it]
                                                          
{'loss': 0.6027, 'learning_rate': 9.224365624336261e-07, 'epoch': 11.68}

 97%|█████████▋| 27335/28080 [54:00:26<1:28:41,  7.14s/it]
 97%|█████████▋| 27336/28080 [54:00:33<1:28:15,  7.12s/it]
                                                          
{'loss': 0.5926, 'learning_rate': 9.199634035033933e-07, 'epoch': 11.68}

 97%|█████████▋| 27336/28080 [54:00:33<1:28:15,  7.12s/it]
 97%|█████████▋| 27337/28080 [54:00:40<1:28:25,  7.14s/it]
                                                          
{'loss': 0.5838, 'learning_rate': 9.17493558326099e-07, 'epoch': 11.68}

 97%|█████████▋| 27337/28080 [54:00:40<1:28:25,  7.14s/it]
 97%|█████████▋| 27338/28080 [54:00:48<1:28:38,  7.17s/it]
                                                          
{'loss': 0.6099, 'learning_rate': 9.150270269345784e-07, 'epoch': 11.68}

 97%|█████████▋| 27338/28080 [54:00:48<1:28:38,  7.17s/it]
 97%|█████████▋| 27339/28080 [54:00:55<1:28:28,  7.16s/it]
                                                          
{'loss': 0.5807, 'learning_rate': 9.125638093616662e-07, 'epoch': 11.68}

 97%|█████████▋| 27339/28080 [54:00:55<1:28:28,  7.16s/it]
 97%|█████████▋| 27340/28080 [54:01:02<1:28:23,  7.17s/it]
                                                          
{'loss': 0.583, 'learning_rate': 9.101039056401139e-07, 'epoch': 11.68}

 97%|█████████▋| 27340/28080 [54:01:02<1:28:23,  7.17s/it]
 97%|█████████▋| 27341/28080 [54:01:09<1:28:05,  7.15s/it]
                                                          
{'loss': 0.5953, 'learning_rate': 9.076473158026455e-07, 'epoch': 11.68}

 97%|█████████▋| 27341/28080 [54:01:09<1:28:05,  7.15s/it]
 97%|█████████▋| 27342/28080 [54:01:16<1:27:44,  7.13s/it]
                                                          
{'loss': 0.573, 'learning_rate': 9.05194039881957e-07, 'epoch': 11.68}

 97%|█████████▋| 27342/28080 [54:01:16<1:27:44,  7.13s/it]
 97%|█████████▋| 27343/28080 [54:01:23<1:27:46,  7.15s/it]
                                                          
{'loss': 0.5933, 'learning_rate': 9.027440779107166e-07, 'epoch': 11.68}

 97%|█████████▋| 27343/28080 [54:01:23<1:27:46,  7.15s/it]
 97%|█████████▋| 27344/28080 [54:01:30<1:27:31,  7.13s/it]
                                                          
{'loss': 0.5905, 'learning_rate': 9.002974299214539e-07, 'epoch': 11.68}

 97%|█████████▋| 27344/28080 [54:01:30<1:27:31,  7.13s/it]
 97%|█████████▋| 27345/28080 [54:01:38<1:27:22,  7.13s/it]
                                                          
{'loss': 0.6084, 'learning_rate': 8.978540959467541e-07, 'epoch': 11.68}

 97%|█████████▋| 27345/28080 [54:01:38<1:27:22,  7.13s/it]
 97%|█████████▋| 27346/28080 [54:01:45<1:26:50,  7.10s/it]
                                                          
{'loss': 0.6272, 'learning_rate': 8.954140760191465e-07, 'epoch': 11.68}

 97%|█████████▋| 27346/28080 [54:01:45<1:26:50,  7.10s/it]
 97%|█████████▋| 27347/28080 [54:01:52<1:27:08,  7.13s/it]
                                                          
{'loss': 0.6177, 'learning_rate': 8.929773701710498e-07, 'epoch': 11.68}

 97%|█████████▋| 27347/28080 [54:01:52<1:27:08,  7.13s/it]
 97%|█████████▋| 27348/28080 [54:01:59<1:26:52,  7.12s/it]
                                                          
{'loss': 0.6279, 'learning_rate': 8.905439784349101e-07, 'epoch': 11.68}

 97%|█████████▋| 27348/28080 [54:01:59<1:26:52,  7.12s/it]
 97%|█████████▋| 27349/28080 [54:02:06<1:26:54,  7.13s/it]
                                                          
{'loss': 0.5866, 'learning_rate': 8.881139008430627e-07, 'epoch': 11.68}

 97%|█████████▋| 27349/28080 [54:02:06<1:26:54,  7.13s/it]
 97%|█████████▋| 27350/28080 [54:02:13<1:26:57,  7.15s/it]
                                                          
{'loss': 0.6156, 'learning_rate': 8.856871374278986e-07, 'epoch': 11.68}

 97%|█████████▋| 27350/28080 [54:02:13<1:26:57,  7.15s/it]
 97%|█████████▋| 27351/28080 [54:02:20<1:27:04,  7.17s/it]
                                                          
{'loss': 0.6123, 'learning_rate': 8.832636882216693e-07, 'epoch': 11.68}

 97%|█████████▋| 27351/28080 [54:02:20<1:27:04,  7.17s/it]
 97%|█████████▋| 27352/28080 [54:02:28<1:26:55,  7.16s/it]
                                                          
{'loss': 0.6008, 'learning_rate': 8.808435532565994e-07, 'epoch': 11.68}

 97%|█████████▋| 27352/28080 [54:02:28<1:26:55,  7.16s/it]
 97%|█████████▋| 27353/28080 [54:02:35<1:26:44,  7.16s/it]
                                                          
{'loss': 0.5974, 'learning_rate': 8.784267325649131e-07, 'epoch': 11.68}

 97%|█████████▋| 27353/28080 [54:02:35<1:26:44,  7.16s/it]
 97%|█████████▋| 27354/28080 [54:02:42<1:26:19,  7.13s/it]
                                                          
{'loss': 0.584, 'learning_rate': 8.760132261787235e-07, 'epoch': 11.69}

 97%|█████████▋| 27354/28080 [54:02:42<1:26:19,  7.13s/it]
 97%|█████████▋| 27355/28080 [54:02:49<1:26:08,  7.13s/it]
                                                          
{'loss': 0.5977, 'learning_rate': 8.736030341302271e-07, 'epoch': 11.69}

 97%|█████████▋| 27355/28080 [54:02:49<1:26:08,  7.13s/it]
 97%|█████████▋| 27356/28080 [54:02:56<1:26:14,  7.15s/it]
                                                          
{'loss': 0.57, 'learning_rate': 8.711961564513982e-07, 'epoch': 11.69}

 97%|█████████▋| 27356/28080 [54:02:56<1:26:14,  7.15s/it]
 97%|█████████▋| 27357/28080 [54:03:03<1:26:04,  7.14s/it]
                                                          
{'loss': 0.5708, 'learning_rate': 8.687925931742946e-07, 'epoch': 11.69}

 97%|█████████▋| 27357/28080 [54:03:03<1:26:04,  7.14s/it]
 97%|█████████▋| 27358/28080 [54:03:10<1:25:59,  7.15s/it]
                                                          
{'loss': 0.5927, 'learning_rate': 8.663923443308907e-07, 'epoch': 11.69}

 97%|█████████▋| 27358/28080 [54:03:10<1:25:59,  7.15s/it]
 97%|█████████▋| 27359/28080 [54:03:18<1:25:51,  7.15s/it]
                                                          
{'loss': 0.6168, 'learning_rate': 8.639954099531333e-07, 'epoch': 11.69}

 97%|█████████▋| 27359/28080 [54:03:18<1:25:51,  7.15s/it]
 97%|█████████▋| 27360/28080 [54:03:25<1:26:10,  7.18s/it]
                                                          
{'loss': 0.6153, 'learning_rate': 8.616017900728857e-07, 'epoch': 11.69}

 97%|█████████▋| 27360/28080 [54:03:25<1:26:10,  7.18s/it]
 97%|█████████▋| 27361/28080 [54:03:32<1:26:03,  7.18s/it]
                                                          
{'loss': 0.6096, 'learning_rate': 8.592114847220111e-07, 'epoch': 11.69}

 97%|█████████▋| 27361/28080 [54:03:32<1:26:03,  7.18s/it]
 97%|█████████▋| 27362/28080 [54:03:39<1:25:42,  7.16s/it]
                                                          
{'loss': 0.6127, 'learning_rate': 8.568244939323177e-07, 'epoch': 11.69}

 97%|█████████▋| 27362/28080 [54:03:39<1:25:42,  7.16s/it]
 97%|█████████▋| 27363/28080 [54:03:46<1:25:20,  7.14s/it]
                                                          
{'loss': 0.5945, 'learning_rate': 8.544408177355023e-07, 'epoch': 11.69}

 97%|█████████▋| 27363/28080 [54:03:46<1:25:20,  7.14s/it]
 97%|█████████▋| 27364/28080 [54:03:53<1:24:58,  7.12s/it]
                                                          
{'loss': 0.6264, 'learning_rate': 8.520604561633727e-07, 'epoch': 11.69}

 97%|█████████▋| 27364/28080 [54:03:53<1:24:58,  7.12s/it]
 97%|█████████▋| 27365/28080 [54:04:00<1:24:59,  7.13s/it]
                                                          
{'loss': 0.5899, 'learning_rate': 8.496834092475147e-07, 'epoch': 11.69}

 97%|█████████▋| 27365/28080 [54:04:00<1:24:59,  7.13s/it]
 97%|█████████▋| 27366/28080 [54:04:07<1:24:33,  7.11s/it]
                                                          
{'loss': 0.6007, 'learning_rate': 8.473096770195976e-07, 'epoch': 11.69}

 97%|█████████▋| 27366/28080 [54:04:07<1:24:33,  7.11s/it]
 97%|█████████▋| 27367/28080 [54:04:15<1:24:22,  7.10s/it]
                                                          
{'loss': 0.5909, 'learning_rate': 8.449392595111794e-07, 'epoch': 11.69}

 97%|█████████▋| 27367/28080 [54:04:15<1:24:22,  7.10s/it]
 97%|█████████▋| 27368/28080 [54:04:22<1:24:51,  7.15s/it]
                                                          
{'loss': 0.6045, 'learning_rate': 8.42572156753818e-07, 'epoch': 11.69}

 97%|█████████▋| 27368/28080 [54:04:22<1:24:51,  7.15s/it]
 97%|█████████▋| 27369/28080 [54:04:29<1:24:46,  7.15s/it]
                                                          
{'loss': 0.6026, 'learning_rate': 8.402083687789886e-07, 'epoch': 11.69}

 97%|█████████▋| 27369/28080 [54:04:29<1:24:46,  7.15s/it]
 97%|█████████▋| 27370/28080 [54:04:36<1:25:03,  7.19s/it]
                                                          
{'loss': 0.6097, 'learning_rate': 8.378478956181379e-07, 'epoch': 11.69}

 97%|█████████▋| 27370/28080 [54:04:36<1:25:03,  7.19s/it]
 97%|█████████▋| 27371/28080 [54:04:43<1:24:47,  7.18s/it]
                                                          
{'loss': 0.6005, 'learning_rate': 8.354907373026855e-07, 'epoch': 11.69}

 97%|█████████▋| 27371/28080 [54:04:43<1:24:47,  7.18s/it]
 97%|█████████▋| 27372/28080 [54:04:51<1:24:42,  7.18s/it]
                                                          
{'loss': 0.6038, 'learning_rate': 8.331368938639672e-07, 'epoch': 11.69}

 97%|█████████▋| 27372/28080 [54:04:51<1:24:42,  7.18s/it]
 97%|█████████▋| 27373/28080 [54:04:58<1:24:13,  7.15s/it]
                                                          
{'loss': 0.6203, 'learning_rate': 8.307863653333192e-07, 'epoch': 11.69}

 97%|█████████▋| 27373/28080 [54:04:58<1:24:13,  7.15s/it]
 97%|█████████▋| 27374/28080 [54:05:05<1:24:10,  7.15s/it]
                                                          
{'loss': 0.5985, 'learning_rate': 8.284391517419942e-07, 'epoch': 11.69}

 97%|█████████▋| 27374/28080 [54:05:05<1:24:10,  7.15s/it]
 97%|█████████▋| 27375/28080 [54:05:12<1:23:59,  7.15s/it]
                                                          
{'loss': 0.6336, 'learning_rate': 8.260952531212451e-07, 'epoch': 11.69}

 97%|█████████▋| 27375/28080 [54:05:12<1:23:59,  7.15s/it]
 97%|█████████▋| 27376/28080 [54:05:19<1:23:44,  7.14s/it]
                                                          
{'loss': 0.5988, 'learning_rate': 8.237546695022414e-07, 'epoch': 11.69}

 97%|█████████▋| 27376/28080 [54:05:19<1:23:44,  7.14s/it]
 97%|█████████▋| 27377/28080 [54:05:26<1:23:48,  7.15s/it]
                                                          
{'loss': 0.5827, 'learning_rate': 8.214174009160968e-07, 'epoch': 11.7}

 97%|█████████▋| 27377/28080 [54:05:26<1:23:48,  7.15s/it]
 98%|█████████▊| 27378/28080 [54:05:33<1:23:40,  7.15s/it]
                                                          
{'loss': 0.6046, 'learning_rate': 8.190834473939534e-07, 'epoch': 11.7}

 98%|█████████▊| 27378/28080 [54:05:33<1:23:40,  7.15s/it]
 98%|█████████▊| 27379/28080 [54:05:41<1:23:38,  7.16s/it]
                                                          
{'loss': 0.601, 'learning_rate': 8.167528089668419e-07, 'epoch': 11.7}

 98%|█████████▊| 27379/28080 [54:05:41<1:23:38,  7.16s/it]
 98%|█████████▊| 27380/28080 [54:05:48<1:23:15,  7.14s/it]
                                                          
{'loss': 0.6152, 'learning_rate': 8.144254856657651e-07, 'epoch': 11.7}

 98%|█████████▊| 27380/28080 [54:05:48<1:23:15,  7.14s/it]
 98%|█████████▊| 27381/28080 [54:05:55<1:23:22,  7.16s/it]
                                                          
{'loss': 0.595, 'learning_rate': 8.121014775216706e-07, 'epoch': 11.7}

 98%|█████████▊| 27381/28080 [54:05:55<1:23:22,  7.16s/it]
 98%|█████████▊| 27382/28080 [54:06:02<1:23:04,  7.14s/it]
                                                          
{'loss': 0.5903, 'learning_rate': 8.097807845654781e-07, 'epoch': 11.7}

 98%|█████████▊| 27382/28080 [54:06:02<1:23:04,  7.14s/it]
 98%|█████████▊| 27383/28080 [54:06:09<1:22:46,  7.13s/it]
                                                          
{'loss': 0.607, 'learning_rate': 8.074634068281073e-07, 'epoch': 11.7}

 98%|█████████▊| 27383/28080 [54:06:09<1:22:46,  7.13s/it]
 98%|█████████▊| 27384/28080 [54:06:16<1:22:23,  7.10s/it]
                                                          
{'loss': 0.5852, 'learning_rate': 8.051493443403668e-07, 'epoch': 11.7}

 98%|█████████▊| 27384/28080 [54:06:16<1:22:23,  7.10s/it]
 98%|█████████▊| 27385/28080 [54:06:23<1:22:31,  7.12s/it]
                                                          
{'loss': 0.5783, 'learning_rate': 8.028385971330099e-07, 'epoch': 11.7}

 98%|█████████▊| 27385/28080 [54:06:23<1:22:31,  7.12s/it]
 98%|█████████▊| 27386/28080 [54:06:30<1:22:32,  7.14s/it]
                                                          
{'loss': 0.5966, 'learning_rate': 8.005311652368175e-07, 'epoch': 11.7}

 98%|█████████▊| 27386/28080 [54:06:30<1:22:32,  7.14s/it]
 98%|█████████▊| 27387/28080 [54:06:38<1:22:28,  7.14s/it]
                                                          
{'loss': 0.6024, 'learning_rate': 7.982270486824594e-07, 'epoch': 11.7}

 98%|█████████▊| 27387/28080 [54:06:38<1:22:28,  7.14s/it]
 98%|█████████▊| 27388/28080 [54:06:45<1:22:05,  7.12s/it]
                                                          
{'loss': 0.6041, 'learning_rate': 7.959262475006057e-07, 'epoch': 11.7}

 98%|█████████▊| 27388/28080 [54:06:45<1:22:05,  7.12s/it]
 98%|█████████▊| 27389/28080 [54:06:52<1:22:08,  7.13s/it]
                                                          
{'loss': 0.6054, 'learning_rate': 7.936287617218708e-07, 'epoch': 11.7}

 98%|█████████▊| 27389/28080 [54:06:52<1:22:08,  7.13s/it]
 98%|█████████▊| 27390/28080 [54:06:59<1:21:59,  7.13s/it]
                                                          
{'loss': 0.6064, 'learning_rate': 7.913345913768133e-07, 'epoch': 11.7}

 98%|█████████▊| 27390/28080 [54:06:59<1:21:59,  7.13s/it]
 98%|█████████▊| 27391/28080 [54:07:06<1:21:46,  7.12s/it]
                                                          
{'loss': 0.601, 'learning_rate': 7.890437364959646e-07, 'epoch': 11.7}

 98%|█████████▊| 27391/28080 [54:07:06<1:21:46,  7.12s/it]
 98%|█████████▊| 27392/28080 [54:07:13<1:21:51,  7.14s/it]
                                                          
{'loss': 0.5973, 'learning_rate': 7.867561971097726e-07, 'epoch': 11.7}

 98%|█████████▊| 27392/28080 [54:07:13<1:21:51,  7.14s/it]
 98%|█████████▊| 27393/28080 [54:07:20<1:21:44,  7.14s/it]
                                                          
{'loss': 0.5833, 'learning_rate': 7.844719732486849e-07, 'epoch': 11.7}

 98%|█████████▊| 27393/28080 [54:07:20<1:21:44,  7.14s/it]
 98%|█████████▊| 27394/28080 [54:07:27<1:21:26,  7.12s/it]
                                                          
{'loss': 0.5944, 'learning_rate': 7.821910649431218e-07, 'epoch': 11.7}

 98%|█████████▊| 27394/28080 [54:07:27<1:21:26,  7.12s/it]
 98%|█████████▊| 27395/28080 [54:07:35<1:21:27,  7.13s/it]
                                                          
{'loss': 0.6022, 'learning_rate': 7.799134722233924e-07, 'epoch': 11.7}

 98%|█████████▊| 27395/28080 [54:07:35<1:21:27,  7.13s/it]
 98%|█████████▊| 27396/28080 [54:07:42<1:21:12,  7.12s/it]
                                                          
{'loss': 0.5958, 'learning_rate': 7.776391951198059e-07, 'epoch': 11.7}

 98%|█████████▊| 27396/28080 [54:07:42<1:21:12,  7.12s/it]
 98%|█████████▊| 27397/28080 [54:07:49<1:21:12,  7.13s/it]
                                                          
{'loss': 0.5921, 'learning_rate': 7.753682336626155e-07, 'epoch': 11.7}

 98%|█████████▊| 27397/28080 [54:07:49<1:21:12,  7.13s/it]
 98%|█████████▊| 27398/28080 [54:07:56<1:21:06,  7.14s/it]
                                                          
{'loss': 0.6051, 'learning_rate': 7.731005878820473e-07, 'epoch': 11.7}

 98%|█████████▊| 27398/28080 [54:07:56<1:21:06,  7.14s/it]
 98%|█████████▊| 27399/28080 [54:08:03<1:21:00,  7.14s/it]
                                                          
{'loss': 0.5913, 'learning_rate': 7.708362578082717e-07, 'epoch': 11.7}

 98%|█████████▊| 27399/28080 [54:08:03<1:21:00,  7.14s/it]
 98%|█████████▊| 27400/28080 [54:08:10<1:20:52,  7.14s/it]
                                                          
{'loss': 0.601, 'learning_rate': 7.685752434714033e-07, 'epoch': 11.71}

 98%|█████████▊| 27400/28080 [54:08:10<1:20:52,  7.14s/it]
 98%|█████████▊| 27401/28080 [54:08:17<1:20:59,  7.16s/it]
                                                          
{'loss': 0.6033, 'learning_rate': 7.663175449015014e-07, 'epoch': 11.71}

 98%|█████████▊| 27401/28080 [54:08:17<1:20:59,  7.16s/it]
 98%|█████████▊| 27402/28080 [54:08:25<1:20:49,  7.15s/it]
                                                          
{'loss': 0.5996, 'learning_rate': 7.640631621286531e-07, 'epoch': 11.71}

 98%|█████████▊| 27402/28080 [54:08:25<1:20:49,  7.15s/it]
 98%|█████████▊| 27403/28080 [54:08:32<1:20:52,  7.17s/it]
                                                          
{'loss': 0.5999, 'learning_rate': 7.618120951828067e-07, 'epoch': 11.71}

 98%|█████████▊| 27403/28080 [54:08:32<1:20:52,  7.17s/it]
 98%|█████████▊| 27404/28080 [54:08:39<1:20:44,  7.17s/it]
                                                          
{'loss': 0.5909, 'learning_rate': 7.595643440939104e-07, 'epoch': 11.71}

 98%|█████████▊| 27404/28080 [54:08:39<1:20:44,  7.17s/it]
 98%|█████████▊| 27405/28080 [54:08:46<1:20:41,  7.17s/it]
                                                          
{'loss': 0.5917, 'learning_rate': 7.573199088919125e-07, 'epoch': 11.71}

 98%|█████████▊| 27405/28080 [54:08:46<1:20:41,  7.17s/it]
 98%|█████████▊| 27406/28080 [54:08:53<1:20:33,  7.17s/it]
                                                          
{'loss': 0.5825, 'learning_rate': 7.550787896066225e-07, 'epoch': 11.71}

 98%|█████████▊| 27406/28080 [54:08:53<1:20:33,  7.17s/it]
 98%|█████████▊| 27407/28080 [54:09:00<1:20:03,  7.14s/it]
                                                          
{'loss': 0.6005, 'learning_rate': 7.528409862678776e-07, 'epoch': 11.71}

 98%|█████████▊| 27407/28080 [54:09:00<1:20:03,  7.14s/it]
 98%|█████████▊| 27408/28080 [54:09:08<1:20:03,  7.15s/it]
                                                          
{'loss': 0.5915, 'learning_rate': 7.506064989054595e-07, 'epoch': 11.71}

 98%|█████████▊| 27408/28080 [54:09:08<1:20:03,  7.15s/it]
 98%|█████████▊| 27409/28080 [54:09:15<1:19:34,  7.12s/it]
                                                          
{'loss': 0.5947, 'learning_rate': 7.483753275490946e-07, 'epoch': 11.71}

 98%|█████████▊| 27409/28080 [54:09:15<1:19:34,  7.12s/it]
 98%|█████████▊| 27410/28080 [54:09:22<1:19:37,  7.13s/it]
                                                          
{'loss': 0.6056, 'learning_rate': 7.461474722284533e-07, 'epoch': 11.71}

 98%|█████████▊| 27410/28080 [54:09:22<1:19:37,  7.13s/it]
 98%|█████████▊| 27411/28080 [54:09:29<1:19:30,  7.13s/it]
                                                          
{'loss': 0.5809, 'learning_rate': 7.439229329731511e-07, 'epoch': 11.71}

 98%|█████████▊| 27411/28080 [54:09:29<1:19:30,  7.13s/it]
 98%|█████████▊| 27412/28080 [54:09:36<1:19:26,  7.14s/it]
                                                          
{'loss': 0.579, 'learning_rate': 7.417017098128309e-07, 'epoch': 11.71}

 98%|█████████▊| 27412/28080 [54:09:36<1:19:26,  7.14s/it]
 98%|█████████▊| 27413/28080 [54:09:43<1:19:31,  7.15s/it]
                                                          
{'loss': 0.6011, 'learning_rate': 7.394838027770246e-07, 'epoch': 11.71}

 98%|█████████▊| 27413/28080 [54:09:43<1:19:31,  7.15s/it]
 98%|█████████▊| 27414/28080 [54:09:50<1:19:27,  7.16s/it]
                                                          
{'loss': 0.5854, 'learning_rate': 7.37269211895264e-07, 'epoch': 11.71}

 98%|█████████▊| 27414/28080 [54:09:50<1:19:27,  7.16s/it]
 98%|█████████▊| 27415/28080 [54:09:58<1:19:26,  7.17s/it]
                                                          
{'loss': 0.6128, 'learning_rate': 7.350579371969424e-07, 'epoch': 11.71}

 98%|█████████▊| 27415/28080 [54:09:58<1:19:26,  7.17s/it]
 98%|█████████▊| 27416/28080 [54:10:05<1:19:19,  7.17s/it]
                                                          
{'loss': 0.611, 'learning_rate': 7.328499787115362e-07, 'epoch': 11.71}

 98%|█████████▊| 27416/28080 [54:10:05<1:19:19,  7.17s/it]
 98%|█████████▊| 27417/28080 [54:10:12<1:19:15,  7.17s/it]
                                                          
{'loss': 0.6034, 'learning_rate': 7.306453364684107e-07, 'epoch': 11.71}

 98%|█████████▊| 27417/28080 [54:10:12<1:19:15,  7.17s/it]
 98%|█████████▊| 27418/28080 [54:10:19<1:19:07,  7.17s/it]
                                                          
{'loss': 0.5932, 'learning_rate': 7.284440104969037e-07, 'epoch': 11.71}

 98%|█████████▊| 27418/28080 [54:10:19<1:19:07,  7.17s/it]
 98%|█████████▊| 27419/28080 [54:10:26<1:19:10,  7.19s/it]
                                                          
{'loss': 0.6226, 'learning_rate': 7.262460008262694e-07, 'epoch': 11.71}

 98%|█████████▊| 27419/28080 [54:10:26<1:19:10,  7.19s/it]
 98%|█████████▊| 27420/28080 [54:10:33<1:18:47,  7.16s/it]
                                                          
{'loss': 0.6167, 'learning_rate': 7.240513074857902e-07, 'epoch': 11.71}

 98%|█████████▊| 27420/28080 [54:10:33<1:18:47,  7.16s/it]
 98%|█████████▊| 27421/28080 [54:10:41<1:18:38,  7.16s/it]
                                                          
{'loss': 0.5938, 'learning_rate': 7.21859930504637e-07, 'epoch': 11.71}

 98%|█████████▊| 27421/28080 [54:10:41<1:18:38,  7.16s/it]
 98%|█████████▊| 27422/28080 [54:10:48<1:18:23,  7.15s/it]
                                                          
{'loss': 0.6216, 'learning_rate': 7.196718699119809e-07, 'epoch': 11.71}

 98%|█████████▊| 27422/28080 [54:10:48<1:18:23,  7.15s/it]
 98%|█████████▊| 27423/28080 [54:10:55<1:17:47,  7.10s/it]
                                                          
{'loss': 0.599, 'learning_rate': 7.17487125736882e-07, 'epoch': 11.71}

 98%|█████████▊| 27423/28080 [54:10:55<1:17:47,  7.10s/it]
 98%|█████████▊| 27424/28080 [54:11:02<1:17:53,  7.12s/it]
                                                          
{'loss': 0.5942, 'learning_rate': 7.153056980084838e-07, 'epoch': 11.72}

 98%|█████████▊| 27424/28080 [54:11:02<1:17:53,  7.12s/it]
 98%|█████████▊| 27425/28080 [54:11:09<1:17:52,  7.13s/it]
                                                          
{'loss': 0.587, 'learning_rate': 7.131275867557629e-07, 'epoch': 11.72}

 98%|█████████▊| 27425/28080 [54:11:09<1:17:52,  7.13s/it]
 98%|█████████▊| 27426/28080 [54:11:16<1:17:32,  7.11s/it]
                                                          
{'loss': 0.6196, 'learning_rate': 7.109527920076964e-07, 'epoch': 11.72}

 98%|█████████▊| 27426/28080 [54:11:16<1:17:32,  7.11s/it]
 98%|█████████▊| 27427/28080 [54:11:23<1:17:54,  7.16s/it]
                                                          
{'loss': 0.579, 'learning_rate': 7.087813137932331e-07, 'epoch': 11.72}

 98%|█████████▊| 27427/28080 [54:11:23<1:17:54,  7.16s/it]
 98%|█████████▊| 27428/28080 [54:11:31<1:17:50,  7.16s/it]
                                                          
{'loss': 0.6251, 'learning_rate': 7.066131521412667e-07, 'epoch': 11.72}

 98%|█████████▊| 27428/28080 [54:11:31<1:17:50,  7.16s/it]
 98%|█████████▊| 27429/28080 [54:11:38<1:17:38,  7.16s/it]
                                                          
{'loss': 0.6136, 'learning_rate': 7.044483070806073e-07, 'epoch': 11.72}

 98%|█████████▊| 27429/28080 [54:11:38<1:17:38,  7.16s/it]
 98%|█████████▊| 27430/28080 [54:11:45<1:17:16,  7.13s/it]
                                                          
{'loss': 0.5981, 'learning_rate': 7.022867786400933e-07, 'epoch': 11.72}

 98%|█████████▊| 27430/28080 [54:11:45<1:17:16,  7.13s/it]
 98%|█████████▊| 27431/28080 [54:11:52<1:17:29,  7.16s/it]
                                                          
{'loss': 0.5974, 'learning_rate': 7.001285668484791e-07, 'epoch': 11.72}

 98%|█████████▊| 27431/28080 [54:11:52<1:17:29,  7.16s/it]
 98%|█████████▊| 27432/28080 [54:11:59<1:17:31,  7.18s/it]
                                                          
{'loss': 0.5953, 'learning_rate': 6.979736717344365e-07, 'epoch': 11.72}

 98%|█████████▊| 27432/28080 [54:11:59<1:17:31,  7.18s/it]
 98%|█████████▊| 27433/28080 [54:12:06<1:17:12,  7.16s/it]
                                                          
{'loss': 0.6046, 'learning_rate': 6.958220933266923e-07, 'epoch': 11.72}

 98%|█████████▊| 27433/28080 [54:12:06<1:17:12,  7.16s/it]
 98%|█████████▊| 27434/28080 [54:12:13<1:16:59,  7.15s/it]
                                                          
{'loss': 0.6017, 'learning_rate': 6.936738316538349e-07, 'epoch': 11.72}

 98%|█████████▊| 27434/28080 [54:12:13<1:16:59,  7.15s/it]
 98%|█████████▊| 27435/28080 [54:12:21<1:16:44,  7.14s/it]
                                                          
{'loss': 0.5934, 'learning_rate': 6.915288867444247e-07, 'epoch': 11.72}

 98%|█████████▊| 27435/28080 [54:12:21<1:16:44,  7.14s/it]
 98%|█████████▊| 27436/28080 [54:12:28<1:16:46,  7.15s/it]
                                                          
{'loss': 0.5855, 'learning_rate': 6.8938725862705e-07, 'epoch': 11.72}

 98%|█████████▊| 27436/28080 [54:12:28<1:16:46,  7.15s/it]
 98%|█████████▊| 27437/28080 [54:12:35<1:16:27,  7.13s/it]
                                                          
{'loss': 0.61, 'learning_rate': 6.872489473301879e-07, 'epoch': 11.72}

 98%|█████████▊| 27437/28080 [54:12:35<1:16:27,  7.13s/it]
 98%|█████████▊| 27438/28080 [54:12:42<1:16:12,  7.12s/it]
                                                          
{'loss': 0.5769, 'learning_rate': 6.851139528822603e-07, 'epoch': 11.72}

 98%|█████████▊| 27438/28080 [54:12:42<1:16:12,  7.12s/it]
 98%|█████████▊| 27439/28080 [54:12:49<1:16:01,  7.12s/it]
                                                          
{'loss': 0.5748, 'learning_rate': 6.829822753116888e-07, 'epoch': 11.72}

 98%|█████████▊| 27439/28080 [54:12:49<1:16:01,  7.12s/it]
 98%|█████████▊| 27440/28080 [54:12:56<1:15:58,  7.12s/it]
                                                          
{'loss': 0.5918, 'learning_rate': 6.808539146468396e-07, 'epoch': 11.72}

 98%|█████████▊| 27440/28080 [54:12:56<1:15:58,  7.12s/it]
 98%|█████████▊| 27441/28080 [54:13:03<1:16:01,  7.14s/it]
                                                          
{'loss': 0.6045, 'learning_rate': 6.787288709160233e-07, 'epoch': 11.72}

 98%|█████████▊| 27441/28080 [54:13:03<1:16:01,  7.14s/it]
 98%|█████████▊| 27442/28080 [54:13:11<1:16:04,  7.15s/it]
                                                          
{'loss': 0.6225, 'learning_rate': 6.766071441474952e-07, 'epoch': 11.72}

 98%|█████████▊| 27442/28080 [54:13:11<1:16:04,  7.15s/it]
 98%|█████████▊| 27443/28080 [54:13:18<1:15:52,  7.15s/it]
                                                          
{'loss': 0.6269, 'learning_rate': 6.744887343695106e-07, 'epoch': 11.72}

 98%|█████████▊| 27443/28080 [54:13:18<1:15:52,  7.15s/it]
 98%|█████████▊| 27444/28080 [54:13:25<1:16:05,  7.18s/it]
                                                          
{'loss': 0.6038, 'learning_rate': 6.723736416102133e-07, 'epoch': 11.72}

 98%|█████████▊| 27444/28080 [54:13:25<1:16:05,  7.18s/it]
 98%|█████████▊| 27445/28080 [54:13:32<1:15:56,  7.18s/it]
                                                          
{'loss': 0.5888, 'learning_rate': 6.702618658977755e-07, 'epoch': 11.72}

 98%|█████████▊| 27445/28080 [54:13:32<1:15:56,  7.18s/it]
 98%|█████████▊| 27446/28080 [54:13:39<1:15:35,  7.15s/it]
                                                          
{'loss': 0.6099, 'learning_rate': 6.681534072603135e-07, 'epoch': 11.72}

 98%|█████████▊| 27446/28080 [54:13:39<1:15:35,  7.15s/it]
 98%|█████████▊| 27447/28080 [54:13:46<1:15:27,  7.15s/it]
                                                          
{'loss': 0.601, 'learning_rate': 6.660482657258326e-07, 'epoch': 11.73}

 98%|█████████▊| 27447/28080 [54:13:46<1:15:27,  7.15s/it]
 98%|█████████▊| 27448/28080 [54:13:53<1:15:09,  7.14s/it]
                                                          
{'loss': 0.6037, 'learning_rate': 6.639464413223384e-07, 'epoch': 11.73}

 98%|█████████▊| 27448/28080 [54:13:53<1:15:09,  7.14s/it]
 98%|█████████▊| 27449/28080 [54:14:01<1:15:23,  7.17s/it]
                                                          
{'loss': 0.6071, 'learning_rate': 6.618479340778361e-07, 'epoch': 11.73}

 98%|█████████▊| 27449/28080 [54:14:01<1:15:23,  7.17s/it]
 98%|█████████▊| 27450/28080 [54:14:08<1:14:44,  7.12s/it]
                                                          
{'loss': 0.609, 'learning_rate': 6.5975274402022e-07, 'epoch': 11.73}

 98%|█████████▊| 27450/28080 [54:14:08<1:14:44,  7.12s/it]
 98%|█████████▊| 27451/28080 [54:14:15<1:14:14,  7.08s/it]
                                                          
{'loss': 0.6043, 'learning_rate': 6.576608711773291e-07, 'epoch': 11.73}

 98%|█████████▊| 27451/28080 [54:14:15<1:14:14,  7.08s/it]
 98%|█████████▊| 27452/28080 [54:14:22<1:14:17,  7.10s/it]
                                                          
{'loss': 0.6142, 'learning_rate': 6.555723155770577e-07, 'epoch': 11.73}

 98%|█████████▊| 27452/28080 [54:14:22<1:14:17,  7.10s/it]
 98%|█████████▊| 27453/28080 [54:14:29<1:14:15,  7.11s/it]
                                                          
{'loss': 0.5961, 'learning_rate': 6.534870772471612e-07, 'epoch': 11.73}

 98%|█████████▊| 27453/28080 [54:14:29<1:14:15,  7.11s/it]
 98%|█████████▊| 27454/28080 [54:14:36<1:14:28,  7.14s/it]
                                                          
{'loss': 0.5798, 'learning_rate': 6.514051562153677e-07, 'epoch': 11.73}

 98%|█████████▊| 27454/28080 [54:14:36<1:14:28,  7.14s/it]
 98%|█████████▊| 27455/28080 [54:14:43<1:14:23,  7.14s/it]
                                                          
{'loss': 0.5874, 'learning_rate': 6.49326552509405e-07, 'epoch': 11.73}

 98%|█████████▊| 27455/28080 [54:14:43<1:14:23,  7.14s/it]
 98%|█████████▊| 27456/28080 [54:14:50<1:14:04,  7.12s/it]
                                                          
{'loss': 0.5916, 'learning_rate': 6.472512661569175e-07, 'epoch': 11.73}

 98%|█████████▊| 27456/28080 [54:14:50<1:14:04,  7.12s/it]
 98%|█████████▊| 27457/28080 [54:14:58<1:13:55,  7.12s/it]
                                                          
{'loss': 0.5712, 'learning_rate': 6.451792971854941e-07, 'epoch': 11.73}

 98%|█████████▊| 27457/28080 [54:14:58<1:13:55,  7.12s/it]
 98%|█████████▊| 27458/28080 [54:15:05<1:13:46,  7.12s/it]
                                                          
{'loss': 0.6026, 'learning_rate': 6.431106456227242e-07, 'epoch': 11.73}

 98%|█████████▊| 27458/28080 [54:15:05<1:13:46,  7.12s/it]
 98%|█████████▊| 27459/28080 [54:15:12<1:13:51,  7.14s/it]
                                                          
{'loss': 0.6013, 'learning_rate': 6.410453114961135e-07, 'epoch': 11.73}

 98%|█████████▊| 27459/28080 [54:15:12<1:13:51,  7.14s/it]
 98%|█████████▊| 27460/28080 [54:15:19<1:13:27,  7.11s/it]
                                                          
{'loss': 0.5855, 'learning_rate': 6.389832948331398e-07, 'epoch': 11.73}

 98%|█████████▊| 27460/28080 [54:15:19<1:13:27,  7.11s/it]
 98%|█████████▊| 27461/28080 [54:15:26<1:13:29,  7.12s/it]
                                                          
{'loss': 0.583, 'learning_rate': 6.369245956612535e-07, 'epoch': 11.73}

 98%|█████████▊| 27461/28080 [54:15:26<1:13:29,  7.12s/it]
 98%|█████████▊| 27462/28080 [54:15:33<1:13:14,  7.11s/it]
                                                          
{'loss': 0.6065, 'learning_rate': 6.348692140078216e-07, 'epoch': 11.73}

 98%|█████████▊| 27462/28080 [54:15:33<1:13:14,  7.11s/it]
 98%|█████████▊| 27463/28080 [54:15:40<1:13:23,  7.14s/it]
                                                          
{'loss': 0.6183, 'learning_rate': 6.328171499002111e-07, 'epoch': 11.73}

 98%|█████████▊| 27463/28080 [54:15:40<1:13:23,  7.14s/it]
 98%|█████████▊| 27464/28080 [54:15:47<1:13:20,  7.14s/it]
                                                          
{'loss': 0.6139, 'learning_rate': 6.307684033657057e-07, 'epoch': 11.73}

 98%|█████████▊| 27464/28080 [54:15:47<1:13:20,  7.14s/it]
 98%|█████████▊| 27465/28080 [54:15:55<1:13:02,  7.13s/it]
                                                          
{'loss': 0.6057, 'learning_rate': 6.287229744315614e-07, 'epoch': 11.73}

 98%|█████████▊| 27465/28080 [54:15:55<1:13:02,  7.13s/it]
 98%|█████████▊| 27466/28080 [54:16:02<1:12:47,  7.11s/it]
                                                          
{'loss': 0.605, 'learning_rate': 6.266808631250065e-07, 'epoch': 11.73}

 98%|█████████▊| 27466/28080 [54:16:02<1:12:47,  7.11s/it]
 98%|█████████▊| 27467/28080 [54:16:09<1:12:20,  7.08s/it]
                                                          
{'loss': 0.6163, 'learning_rate': 6.246420694731858e-07, 'epoch': 11.73}

 98%|█████████▊| 27467/28080 [54:16:09<1:12:20,  7.08s/it]
 98%|█████████▊| 27468/28080 [54:16:16<1:12:35,  7.12s/it]
                                                          
{'loss': 0.6005, 'learning_rate': 6.226065935032444e-07, 'epoch': 11.73}

 98%|█████████▊| 27468/28080 [54:16:16<1:12:35,  7.12s/it]
 98%|█████████▊| 27469/28080 [54:16:23<1:12:36,  7.13s/it]
                                                          
{'loss': 0.5926, 'learning_rate': 6.205744352422437e-07, 'epoch': 11.73}

 98%|█████████▊| 27469/28080 [54:16:23<1:12:36,  7.13s/it]
 98%|█████████▊| 27470/28080 [54:16:30<1:12:33,  7.14s/it]
                                                          
{'loss': 0.5969, 'learning_rate': 6.185455947172458e-07, 'epoch': 11.73}

 98%|█████████▊| 27470/28080 [54:16:30<1:12:33,  7.14s/it]
 98%|█████████▊| 27471/28080 [54:16:37<1:12:17,  7.12s/it]
                                                          
{'loss': 0.6072, 'learning_rate': 6.165200719552011e-07, 'epoch': 11.74}

 98%|█████████▊| 27471/28080 [54:16:37<1:12:17,  7.12s/it]
 98%|█████████▊| 27472/28080 [54:16:44<1:12:12,  7.13s/it]
                                                          
{'loss': 0.5987, 'learning_rate': 6.144978669831159e-07, 'epoch': 11.74}

 98%|█████████▊| 27472/28080 [54:16:44<1:12:12,  7.13s/it]
 98%|█████████▊| 27473/28080 [54:16:52<1:12:14,  7.14s/it]
                                                          
{'loss': 0.5985, 'learning_rate': 6.124789798278296e-07, 'epoch': 11.74}

 98%|█████████▊| 27473/28080 [54:16:52<1:12:14,  7.14s/it]
 98%|█████████▊| 27474/28080 [54:16:59<1:12:00,  7.13s/it]
                                                          
{'loss': 0.577, 'learning_rate': 6.104634105162376e-07, 'epoch': 11.74}

 98%|█████████▊| 27474/28080 [54:16:59<1:12:00,  7.13s/it]
 98%|█████████▊| 27475/28080 [54:17:06<1:11:44,  7.11s/it]
                                                          
{'loss': 0.5826, 'learning_rate': 6.084511590751795e-07, 'epoch': 11.74}

 98%|█████████▊| 27475/28080 [54:17:06<1:11:44,  7.11s/it]
 98%|█████████▊| 27476/28080 [54:17:13<1:11:44,  7.13s/it]
                                                          
{'loss': 0.5895, 'learning_rate': 6.064422255313561e-07, 'epoch': 11.74}

 98%|█████████▊| 27476/28080 [54:17:13<1:11:44,  7.13s/it]
 98%|█████████▊| 27477/28080 [54:17:20<1:11:42,  7.13s/it]
                                                          
{'loss': 0.6137, 'learning_rate': 6.044366099115517e-07, 'epoch': 11.74}

 98%|█████████▊| 27477/28080 [54:17:20<1:11:42,  7.13s/it]
 98%|█████████▊| 27478/28080 [54:17:27<1:11:37,  7.14s/it]
                                                          
{'loss': 0.5944, 'learning_rate': 6.024343122424391e-07, 'epoch': 11.74}

 98%|█████████▊| 27478/28080 [54:17:27<1:11:37,  7.14s/it]
 98%|█████████▊| 27479/28080 [54:17:34<1:11:39,  7.15s/it]
                                                          
{'loss': 0.6, 'learning_rate': 6.004353325506362e-07, 'epoch': 11.74}

 98%|█████████▊| 27479/28080 [54:17:34<1:11:39,  7.15s/it]
 98%|█████████▊| 27480/28080 [54:17:42<1:11:30,  7.15s/it]
                                                          
{'loss': 0.6066, 'learning_rate': 5.984396708627604e-07, 'epoch': 11.74}

 98%|█████████▊| 27480/28080 [54:17:42<1:11:30,  7.15s/it]
 98%|█████████▊| 27481/28080 [54:17:49<1:11:14,  7.14s/it]
                                                          
{'loss': 0.6086, 'learning_rate': 5.964473272053462e-07, 'epoch': 11.74}

 98%|█████████▊| 27481/28080 [54:17:49<1:11:14,  7.14s/it]
 98%|█████████▊| 27482/28080 [54:17:56<1:11:07,  7.14s/it]
                                                          
{'loss': 0.5851, 'learning_rate': 5.944583016048999e-07, 'epoch': 11.74}

 98%|█████████▊| 27482/28080 [54:17:56<1:11:07,  7.14s/it]
 98%|█████████▊| 27483/28080 [54:18:03<1:11:08,  7.15s/it]
                                                          
{'loss': 0.5889, 'learning_rate': 5.924725940879006e-07, 'epoch': 11.74}

 98%|█████████▊| 27483/28080 [54:18:03<1:11:08,  7.15s/it]
 98%|█████████▊| 27484/28080 [54:18:10<1:11:11,  7.17s/it]
                                                          
{'loss': 0.5674, 'learning_rate': 5.904902046807437e-07, 'epoch': 11.74}

 98%|█████████▊| 27484/28080 [54:18:10<1:11:11,  7.17s/it]
 98%|█████████▊| 27485/28080 [54:18:17<1:10:46,  7.14s/it]
                                                          
{'loss': 0.5901, 'learning_rate': 5.88511133409797e-07, 'epoch': 11.74}

 98%|█████████▊| 27485/28080 [54:18:17<1:10:46,  7.14s/it]
 98%|█████████▊| 27486/28080 [54:18:24<1:10:34,  7.13s/it]
                                                          
{'loss': 0.602, 'learning_rate': 5.865353803014284e-07, 'epoch': 11.74}

 98%|█████████▊| 27486/28080 [54:18:24<1:10:34,  7.13s/it]
 98%|█████████▊| 27487/28080 [54:18:32<1:10:45,  7.16s/it]
                                                          
{'loss': 0.5897, 'learning_rate': 5.845629453818946e-07, 'epoch': 11.74}

 98%|█████████▊| 27487/28080 [54:18:32<1:10:45,  7.16s/it]
 98%|█████████▊| 27488/28080 [54:18:39<1:10:44,  7.17s/it]
                                                          
{'loss': 0.6055, 'learning_rate': 5.825938286774524e-07, 'epoch': 11.74}

 98%|█████████▊| 27488/28080 [54:18:39<1:10:44,  7.17s/it]
 98%|█████████▊| 27489/28080 [54:18:46<1:10:29,  7.16s/it]
                                                          
{'loss': 0.591, 'learning_rate': 5.806280302142752e-07, 'epoch': 11.74}

 98%|█████████▊| 27489/28080 [54:18:46<1:10:29,  7.16s/it]
 98%|█████████▊| 27490/28080 [54:18:53<1:10:14,  7.14s/it]
                                                          
{'loss': 0.5911, 'learning_rate': 5.786655500185367e-07, 'epoch': 11.74}

 98%|█████████▊| 27490/28080 [54:18:53<1:10:14,  7.14s/it]
 98%|█████████▊| 27491/28080 [54:19:00<1:10:10,  7.15s/it]
                                                          
{'loss': 0.6143, 'learning_rate': 5.767063881163548e-07, 'epoch': 11.74}

 98%|█████████▊| 27491/28080 [54:19:00<1:10:10,  7.15s/it]
 98%|█████████▊| 27492/28080 [54:19:07<1:09:46,  7.12s/it]
                                                          
{'loss': 0.6023, 'learning_rate': 5.747505445337642e-07, 'epoch': 11.74}

 98%|█████████▊| 27492/28080 [54:19:07<1:09:46,  7.12s/it]
 98%|█████████▊| 27493/28080 [54:19:14<1:09:50,  7.14s/it]
                                                          
{'loss': 0.5812, 'learning_rate': 5.727980192967997e-07, 'epoch': 11.74}

 98%|█████████▊| 27493/28080 [54:19:14<1:09:50,  7.14s/it]
 98%|█████████▊| 27494/28080 [54:19:22<1:09:38,  7.13s/it]
                                                          
{'loss': 0.601, 'learning_rate': 5.708488124314404e-07, 'epoch': 11.75}

 98%|█████████▊| 27494/28080 [54:19:22<1:09:38,  7.13s/it]
 98%|█████████▊| 27495/28080 [54:19:29<1:09:28,  7.13s/it]
                                                          
{'loss': 0.5917, 'learning_rate': 5.689029239636101e-07, 'epoch': 11.75}

 98%|█████████▊| 27495/28080 [54:19:29<1:09:28,  7.13s/it]
 98%|█████████▊| 27496/28080 [54:19:36<1:09:07,  7.10s/it]
                                                          
{'loss': 0.6113, 'learning_rate': 5.669603539192047e-07, 'epoch': 11.75}

 98%|█████████▊| 27496/28080 [54:19:36<1:09:07,  7.10s/it]
 98%|█████████▊| 27497/28080 [54:19:43<1:09:10,  7.12s/it]
                                                          
{'loss': 0.5942, 'learning_rate': 5.650211023240647e-07, 'epoch': 11.75}

 98%|█████████▊| 27497/28080 [54:19:43<1:09:10,  7.12s/it]
 98%|█████████▊| 27498/28080 [54:19:50<1:09:16,  7.14s/it]
                                                          
{'loss': 0.5941, 'learning_rate': 5.630851692040028e-07, 'epoch': 11.75}

 98%|█████████▊| 27498/28080 [54:19:50<1:09:16,  7.14s/it]
 98%|█████████▊| 27499/28080 [54:19:57<1:09:21,  7.16s/it]
                                                          
{'loss': 0.5743, 'learning_rate': 5.611525545847484e-07, 'epoch': 11.75}

 98%|█████████▊| 27499/28080 [54:19:57<1:09:21,  7.16s/it]
 98%|█████████▊| 27500/28080 [54:20:04<1:09:02,  7.14s/it]
                                                          
{'loss': 0.5893, 'learning_rate': 5.592232584920309e-07, 'epoch': 11.75}

 98%|█████████▊| 27500/28080 [54:20:04<1:09:02,  7.14s/it]
 98%|█████████▊| 27501/28080 [54:20:11<1:08:55,  7.14s/it]
                                                          
{'loss': 0.6137, 'learning_rate': 5.572972809515242e-07, 'epoch': 11.75}

 98%|█████████▊| 27501/28080 [54:20:11<1:08:55,  7.14s/it]
 98%|█████████▊| 27502/28080 [54:20:19<1:08:51,  7.15s/it]
                                                          
{'loss': 0.6034, 'learning_rate': 5.553746219888189e-07, 'epoch': 11.75}

 98%|█████████▊| 27502/28080 [54:20:19<1:08:51,  7.15s/it]
 98%|█████████▊| 27503/28080 [54:20:26<1:08:37,  7.14s/it]
                                                          
{'loss': 0.6291, 'learning_rate': 5.534552816295335e-07, 'epoch': 11.75}

 98%|█████████▊| 27503/28080 [54:20:26<1:08:37,  7.14s/it]
 98%|█████████▊| 27504/28080 [54:20:33<1:08:35,  7.14s/it]
                                                          
{'loss': 0.5968, 'learning_rate': 5.515392598991753e-07, 'epoch': 11.75}

 98%|█████████▊| 27504/28080 [54:20:33<1:08:35,  7.14s/it]
 98%|█████████▊| 27505/28080 [54:20:40<1:08:27,  7.14s/it]
                                                          
{'loss': 0.5868, 'learning_rate': 5.496265568232517e-07, 'epoch': 11.75}

 98%|█████████▊| 27505/28080 [54:20:40<1:08:27,  7.14s/it]
 98%|█████████▊| 27506/28080 [54:20:47<1:08:28,  7.16s/it]
                                                          
{'loss': 0.5824, 'learning_rate': 5.477171724272145e-07, 'epoch': 11.75}

 98%|█████████▊| 27506/28080 [54:20:47<1:08:28,  7.16s/it]
 98%|█████████▊| 27507/28080 [54:20:54<1:08:22,  7.16s/it]
                                                          
{'loss': 0.5721, 'learning_rate': 5.458111067364602e-07, 'epoch': 11.75}

 98%|█████████▊| 27507/28080 [54:20:54<1:08:22,  7.16s/it]
 98%|█████████▊| 27508/28080 [54:21:02<1:08:09,  7.15s/it]
                                                          
{'loss': 0.6127, 'learning_rate': 5.439083597763017e-07, 'epoch': 11.75}

 98%|█████████▊| 27508/28080 [54:21:02<1:08:09,  7.15s/it]
 98%|█████████▊| 27509/28080 [54:21:09<1:08:03,  7.15s/it]
                                                          
{'loss': 0.6058, 'learning_rate': 5.420089315721355e-07, 'epoch': 11.75}

 98%|█████████▊| 27509/28080 [54:21:09<1:08:03,  7.15s/it]
 98%|█████████▊| 27510/28080 [54:21:16<1:07:58,  7.16s/it]
                                                          
{'loss': 0.5988, 'learning_rate': 5.401128221491636e-07, 'epoch': 11.75}

 98%|█████████▊| 27510/28080 [54:21:16<1:07:58,  7.16s/it]
 98%|█████████▊| 27511/28080 [54:21:23<1:07:53,  7.16s/it]
                                                          
{'loss': 0.6, 'learning_rate': 5.382200315326436e-07, 'epoch': 11.75}

 98%|█████████▊| 27511/28080 [54:21:23<1:07:53,  7.16s/it]
 98%|█████████▊| 27512/28080 [54:21:30<1:07:54,  7.17s/it]
                                                          
{'loss': 0.5989, 'learning_rate': 5.363305597477497e-07, 'epoch': 11.75}

 98%|█████████▊| 27512/28080 [54:21:30<1:07:54,  7.17s/it]
 98%|█████████▊| 27513/28080 [54:21:37<1:07:18,  7.12s/it]
                                                          
{'loss': 0.5932, 'learning_rate': 5.344444068196286e-07, 'epoch': 11.75}

 98%|█████████▊| 27513/28080 [54:21:37<1:07:18,  7.12s/it]
 98%|█████████▊| 27514/28080 [54:21:44<1:07:12,  7.12s/it]
                                                          
{'loss': 0.6012, 'learning_rate': 5.325615727733713e-07, 'epoch': 11.75}

 98%|█████████▊| 27514/28080 [54:21:44<1:07:12,  7.12s/it]
 98%|█████████▊| 27515/28080 [54:21:51<1:07:03,  7.12s/it]
                                                          
{'loss': 0.5971, 'learning_rate': 5.306820576340132e-07, 'epoch': 11.75}

 98%|█████████▊| 27515/28080 [54:21:51<1:07:03,  7.12s/it]
 98%|█████████▊| 27516/28080 [54:21:59<1:07:04,  7.14s/it]
                                                          
{'loss': 0.6104, 'learning_rate': 5.288058614265623e-07, 'epoch': 11.75}

 98%|█████████▊| 27516/28080 [54:21:59<1:07:04,  7.14s/it]
 98%|█████████▊| 27517/28080 [54:22:06<1:06:57,  7.14s/it]
                                                          
{'loss': 0.5908, 'learning_rate': 5.269329841759707e-07, 'epoch': 11.76}

 98%|█████████▊| 27517/28080 [54:22:06<1:06:57,  7.14s/it]
 98%|█████████▊| 27518/28080 [54:22:13<1:07:14,  7.18s/it]
                                                          
{'loss': 0.6125, 'learning_rate': 5.250634259071907e-07, 'epoch': 11.76}

 98%|█████████▊| 27518/28080 [54:22:13<1:07:14,  7.18s/it]
 98%|█████████▊| 27519/28080 [54:22:20<1:06:46,  7.14s/it]
                                                          
{'loss': 0.6193, 'learning_rate': 5.231971866450635e-07, 'epoch': 11.76}

 98%|█████████▊| 27519/28080 [54:22:20<1:06:46,  7.14s/it]
 98%|█████████▊| 27520/28080 [54:22:27<1:06:39,  7.14s/it]
                                                          
{'loss': 0.6084, 'learning_rate': 5.213342664144304e-07, 'epoch': 11.76}

 98%|█████████▊| 27520/28080 [54:22:27<1:06:39,  7.14s/it]
 98%|█████████▊| 27521/28080 [54:22:34<1:06:35,  7.15s/it]
                                                          
{'loss': 0.5963, 'learning_rate': 5.194746652400773e-07, 'epoch': 11.76}

 98%|█████████▊| 27521/28080 [54:22:34<1:06:35,  7.15s/it]
 98%|█████████▊| 27522/28080 [54:22:42<1:06:32,  7.16s/it]
                                                          
{'loss': 0.5995, 'learning_rate': 5.176183831467341e-07, 'epoch': 11.76}

 98%|█████████▊| 27522/28080 [54:22:42<1:06:32,  7.16s/it]
 98%|█████████▊| 27523/28080 [54:22:49<1:06:26,  7.16s/it]
                                                          
{'loss': 0.5913, 'learning_rate': 5.157654201590756e-07, 'epoch': 11.76}

 98%|█████████▊| 27523/28080 [54:22:49<1:06:26,  7.16s/it]
 98%|█████████▊| 27524/28080 [54:22:56<1:06:18,  7.16s/it]
                                                          
{'loss': 0.5986, 'learning_rate': 5.139157763018321e-07, 'epoch': 11.76}

 98%|█████████▊| 27524/28080 [54:22:56<1:06:18,  7.16s/it]
 98%|█████████▊| 27525/28080 [54:23:03<1:06:18,  7.17s/it]
                                                          
{'loss': 0.5887, 'learning_rate': 5.120694515995117e-07, 'epoch': 11.76}

 98%|█████████▊| 27525/28080 [54:23:03<1:06:18,  7.17s/it]
 98%|█████████▊| 27526/28080 [54:23:10<1:06:18,  7.18s/it]
                                                          
{'loss': 0.5858, 'learning_rate': 5.102264460767337e-07, 'epoch': 11.76}

 98%|█████████▊| 27526/28080 [54:23:10<1:06:18,  7.18s/it]
 98%|█████████▊| 27527/28080 [54:23:17<1:06:05,  7.17s/it]
                                                          
{'loss': 0.5805, 'learning_rate': 5.083867597580338e-07, 'epoch': 11.76}

 98%|█████████▊| 27527/28080 [54:23:17<1:06:05,  7.17s/it]
 98%|█████████▊| 27528/28080 [54:23:25<1:06:04,  7.18s/it]
                                                          
{'loss': 0.6002, 'learning_rate': 5.065503926678372e-07, 'epoch': 11.76}

 98%|█████████▊| 27528/28080 [54:23:25<1:06:04,  7.18s/it]
 98%|█████████▊| 27529/28080 [54:23:32<1:05:47,  7.16s/it]
                                                          
{'loss': 0.6041, 'learning_rate': 5.047173448306242e-07, 'epoch': 11.76}

 98%|█████████▊| 27529/28080 [54:23:32<1:05:47,  7.16s/it]
 98%|█████████▊| 27530/28080 [54:23:39<1:05:20,  7.13s/it]
                                                          
{'loss': 0.5981, 'learning_rate': 5.028876162707364e-07, 'epoch': 11.76}

 98%|█████████▊| 27530/28080 [54:23:39<1:05:20,  7.13s/it]
 98%|█████████▊| 27531/28080 [54:23:46<1:04:57,  7.10s/it]
                                                          
{'loss': 0.5953, 'learning_rate': 5.010612070125431e-07, 'epoch': 11.76}

 98%|█████████▊| 27531/28080 [54:23:46<1:04:57,  7.10s/it]
 98%|█████████▊| 27532/28080 [54:23:53<1:04:53,  7.10s/it]
                                                          
{'loss': 0.6056, 'learning_rate': 4.992381170803306e-07, 'epoch': 11.76}

 98%|█████████▊| 27532/28080 [54:23:53<1:04:53,  7.10s/it]
 98%|█████████▊| 27533/28080 [54:24:00<1:04:28,  7.07s/it]
                                                          
{'loss': 0.6043, 'learning_rate': 4.974183464983573e-07, 'epoch': 11.76}

 98%|█████████▊| 27533/28080 [54:24:00<1:04:28,  7.07s/it]
 98%|█████████▊| 27534/28080 [54:24:07<1:04:29,  7.09s/it]
                                                          
{'loss': 0.5904, 'learning_rate': 4.956018952908536e-07, 'epoch': 11.76}

 98%|█████████▊| 27534/28080 [54:24:07<1:04:29,  7.09s/it]
 98%|█████████▊| 27535/28080 [54:24:14<1:04:20,  7.08s/it]
                                                          
{'loss': 0.5992, 'learning_rate': 4.937887634819671e-07, 'epoch': 11.76}

 98%|█████████▊| 27535/28080 [54:24:14<1:04:20,  7.08s/it]
 98%|█████████▊| 27536/28080 [54:24:21<1:04:29,  7.11s/it]
                                                          
{'loss': 0.5836, 'learning_rate': 4.919789510957895e-07, 'epoch': 11.76}

 98%|█████████▊| 27536/28080 [54:24:21<1:04:29,  7.11s/it]
 98%|█████████▊| 27537/28080 [54:24:29<1:04:33,  7.13s/it]
                                                          
{'loss': 0.6109, 'learning_rate': 4.901724581564682e-07, 'epoch': 11.76}

 98%|█████████▊| 27537/28080 [54:24:29<1:04:33,  7.13s/it]
 98%|█████████▊| 27538/28080 [54:24:36<1:04:23,  7.13s/it]
                                                          
{'loss': 0.5981, 'learning_rate': 4.883692846879562e-07, 'epoch': 11.76}

 98%|█████████▊| 27538/28080 [54:24:36<1:04:23,  7.13s/it]
 98%|█████████▊| 27539/28080 [54:24:43<1:04:20,  7.14s/it]
                                                          
{'loss': 0.5979, 'learning_rate': 4.865694307143176e-07, 'epoch': 11.76}

 98%|█████████▊| 27539/28080 [54:24:43<1:04:20,  7.14s/it]
 98%|█████████▊| 27540/28080 [54:24:50<1:04:00,  7.11s/it]
                                                          
{'loss': 0.5961, 'learning_rate': 4.847728962594499e-07, 'epoch': 11.76}

 98%|█████████▊| 27540/28080 [54:24:50<1:04:00,  7.11s/it]
 98%|█████████▊| 27541/28080 [54:24:57<1:03:57,  7.12s/it]
                                                          
{'loss': 0.5983, 'learning_rate': 4.829796813472787e-07, 'epoch': 11.77}

 98%|█████████▊| 27541/28080 [54:24:57<1:03:57,  7.12s/it]
 98%|█████████▊| 27542/28080 [54:25:04<1:03:34,  7.09s/it]
                                                          
{'loss': 0.5981, 'learning_rate': 4.811897860016179e-07, 'epoch': 11.77}

 98%|█████████▊| 27542/28080 [54:25:04<1:03:34,  7.09s/it]
 98%|█████████▊| 27543/28080 [54:25:11<1:03:27,  7.09s/it]
                                                          
{'loss': 0.5921, 'learning_rate': 4.794032102463653e-07, 'epoch': 11.77}

 98%|█████████▊| 27543/28080 [54:25:11<1:03:27,  7.09s/it]
 98%|█████████▊| 27544/28080 [54:25:18<1:03:15,  7.08s/it]
                                                          
{'loss': 0.6022, 'learning_rate': 4.776199541051963e-07, 'epoch': 11.77}

 98%|█████████▊| 27544/28080 [54:25:18<1:03:15,  7.08s/it]
 98%|█████████▊| 27545/28080 [54:25:25<1:03:13,  7.09s/it]
                                                          
{'loss': 0.607, 'learning_rate': 4.7584001760189734e-07, 'epoch': 11.77}

 98%|█████████▊| 27545/28080 [54:25:25<1:03:13,  7.09s/it]
 98%|█████████▊| 27546/28080 [54:25:32<1:03:01,  7.08s/it]
                                                          
{'loss': 0.6049, 'learning_rate': 4.7406340076011635e-07, 'epoch': 11.77}

 98%|█████████▊| 27546/28080 [54:25:32<1:03:01,  7.08s/it]
 98%|█████████▊| 27547/28080 [54:25:40<1:03:12,  7.12s/it]
                                                          
{'loss': 0.5933, 'learning_rate': 4.72290103603501e-07, 'epoch': 11.77}

 98%|█████████▊| 27547/28080 [54:25:40<1:03:12,  7.12s/it]
 98%|█████████▊| 27548/28080 [54:25:47<1:03:05,  7.12s/it]
                                                          
{'loss': 0.5898, 'learning_rate': 4.7052012615564356e-07, 'epoch': 11.77}

 98%|█████████▊| 27548/28080 [54:25:47<1:03:05,  7.12s/it]
 98%|█████████▊| 27549/28080 [54:25:54<1:02:41,  7.08s/it]
                                                          
{'loss': 0.5998, 'learning_rate': 4.687534684400807e-07, 'epoch': 11.77}

 98%|█████████▊| 27549/28080 [54:25:54<1:02:41,  7.08s/it]
 98%|█████████▊| 27550/28080 [54:26:01<1:02:23,  7.06s/it]
                                                          
{'loss': 0.6119, 'learning_rate': 4.6699013048032144e-07, 'epoch': 11.77}

 98%|█████████▊| 27550/28080 [54:26:01<1:02:23,  7.06s/it]
 98%|█████████▊| 27551/28080 [54:26:08<1:02:29,  7.09s/it]
                                                          
{'loss': 0.6125, 'learning_rate': 4.6523011229984704e-07, 'epoch': 11.77}

 98%|█████████▊| 27551/28080 [54:26:08<1:02:29,  7.09s/it]
 98%|█████████▊| 27552/28080 [54:26:15<1:02:33,  7.11s/it]
                                                          
{'loss': 0.6204, 'learning_rate': 4.6347341392205534e-07, 'epoch': 11.77}

 98%|█████████▊| 27552/28080 [54:26:15<1:02:33,  7.11s/it]
 98%|█████████▊| 27553/28080 [54:26:22<1:02:38,  7.13s/it]
                                                          
{'loss': 0.6275, 'learning_rate': 4.617200353703166e-07, 'epoch': 11.77}

 98%|█████████▊| 27553/28080 [54:26:22<1:02:38,  7.13s/it]
 98%|█████████▊| 27554/28080 [54:26:29<1:02:27,  7.13s/it]
                                                          
{'loss': 0.6166, 'learning_rate': 4.599699766679455e-07, 'epoch': 11.77}

 98%|█████████▊| 27554/28080 [54:26:29<1:02:27,  7.13s/it]
 98%|█████████▊| 27555/28080 [54:26:36<1:02:29,  7.14s/it]
                                                          
{'loss': 0.6013, 'learning_rate': 4.582232378382567e-07, 'epoch': 11.77}

 98%|█████████▊| 27555/28080 [54:26:36<1:02:29,  7.14s/it]
 98%|█████████▊| 27556/28080 [54:26:44<1:02:32,  7.16s/it]
                                                          
{'loss': 0.6111, 'learning_rate': 4.564798189044539e-07, 'epoch': 11.77}

 98%|█████████▊| 27556/28080 [54:26:44<1:02:32,  7.16s/it]
 98%|█████████▊| 27557/28080 [54:26:51<1:02:27,  7.17s/it]
                                                          
{'loss': 0.5714, 'learning_rate': 4.5473971988976845e-07, 'epoch': 11.77}

 98%|█████████▊| 27557/28080 [54:26:51<1:02:27,  7.17s/it]
 98%|█████████▊| 27558/28080 [54:26:58<1:02:24,  7.17s/it]
                                                          
{'loss': 0.6115, 'learning_rate': 4.5300294081732085e-07, 'epoch': 11.77}

 98%|█████████▊| 27558/28080 [54:26:58<1:02:24,  7.17s/it]
 98%|█████████▊| 27559/28080 [54:27:05<1:02:12,  7.16s/it]
                                                          
{'loss': 0.6033, 'learning_rate': 4.5126948171020363e-07, 'epoch': 11.77}

 98%|█████████▊| 27559/28080 [54:27:05<1:02:12,  7.16s/it]
 98%|█████████▊| 27560/28080 [54:27:12<1:01:42,  7.12s/it]
                                                          
{'loss': 0.5904, 'learning_rate': 4.495393425915373e-07, 'epoch': 11.77}

 98%|█████████▊| 27560/28080 [54:27:12<1:01:42,  7.12s/it]
 98%|█████████▊| 27561/28080 [54:27:19<1:01:32,  7.11s/it]
                                                          
{'loss': 0.5855, 'learning_rate': 4.478125234842756e-07, 'epoch': 11.77}

 98%|█████████▊| 27561/28080 [54:27:19<1:01:32,  7.11s/it]
 98%|█████████▊| 27562/28080 [54:27:27<1:01:42,  7.15s/it]
                                                          
{'loss': 0.5845, 'learning_rate': 4.4608902441142794e-07, 'epoch': 11.77}

 98%|█████████▊| 27562/28080 [54:27:27<1:01:42,  7.15s/it]
 98%|█████████▊| 27563/28080 [54:27:34<1:01:30,  7.14s/it]
                                                          
{'loss': 0.597, 'learning_rate': 4.443688453959205e-07, 'epoch': 11.77}

 98%|█████████▊| 27563/28080 [54:27:34<1:01:30,  7.14s/it]
 98%|█████████▊| 27564/28080 [54:27:41<1:01:17,  7.13s/it]
                                                          
{'loss': 0.6217, 'learning_rate': 4.426519864606238e-07, 'epoch': 11.78}

 98%|█████████▊| 27564/28080 [54:27:41<1:01:17,  7.13s/it]
 98%|█████████▊| 27565/28080 [54:27:48<1:00:46,  7.08s/it]
                                                          
{'loss': 0.6195, 'learning_rate': 4.4093844762838066e-07, 'epoch': 11.78}

 98%|█████████▊| 27565/28080 [54:27:48<1:00:46,  7.08s/it]
 98%|█████████▊| 27566/28080 [54:27:55<1:00:46,  7.10s/it]
                                                          
{'loss': 0.6009, 'learning_rate': 4.392282289220062e-07, 'epoch': 11.78}

 98%|█████████▊| 27566/28080 [54:27:55<1:00:46,  7.10s/it]
 98%|█████████▊| 27567/28080 [54:28:02<1:00:34,  7.08s/it]
                                                          
{'loss': 0.6026, 'learning_rate': 4.3752133036426003e-07, 'epoch': 11.78}

 98%|█████████▊| 27567/28080 [54:28:02<1:00:34,  7.08s/it]
 98%|█████████▊| 27568/28080 [54:28:09<1:00:40,  7.11s/it]
                                                          
{'loss': 0.5876, 'learning_rate': 4.3581775197781837e-07, 'epoch': 11.78}

 98%|█████████▊| 27568/28080 [54:28:09<1:00:40,  7.11s/it]
 98%|█████████▊| 27569/28080 [54:28:16<1:00:31,  7.11s/it]
                                                          
{'loss': 0.6072, 'learning_rate': 4.341174937853298e-07, 'epoch': 11.78}

 98%|█████████▊| 27569/28080 [54:28:16<1:00:31,  7.11s/it]
 98%|█████████▊| 27570/28080 [54:28:23<1:00:30,  7.12s/it]
                                                          
{'loss': 0.5936, 'learning_rate': 4.324205558094985e-07, 'epoch': 11.78}

 98%|█████████▊| 27570/28080 [54:28:23<1:00:30,  7.12s/it]
 98%|█████████▊| 27571/28080 [54:28:30<1:00:34,  7.14s/it]
                                                          
{'loss': 0.5927, 'learning_rate': 4.307269380728063e-07, 'epoch': 11.78}

 98%|█████████▊| 27571/28080 [54:28:30<1:00:34,  7.14s/it]
 98%|█████████▊| 27572/28080 [54:28:38<1:00:38,  7.16s/it]
                                                          
{'loss': 0.5907, 'learning_rate': 4.290366405978463e-07, 'epoch': 11.78}

 98%|█████████▊| 27572/28080 [54:28:38<1:00:38,  7.16s/it]
 98%|█████████▊| 27573/28080 [54:28:45<1:00:30,  7.16s/it]
                                                          
{'loss': 0.5968, 'learning_rate': 4.2734966340707283e-07, 'epoch': 11.78}

 98%|█████████▊| 27573/28080 [54:28:45<1:00:30,  7.16s/it]
 98%|█████████▊| 27574/28080 [54:28:52<59:55,  7.11s/it]  
                                                        
{'loss': 0.5751, 'learning_rate': 4.256660065229678e-07, 'epoch': 11.78}

 98%|█████████▊| 27574/28080 [54:28:52<59:55,  7.11s/it]
 98%|█████████▊| 27575/28080 [54:28:59<59:43,  7.10s/it]
                                                        
{'loss': 0.609, 'learning_rate': 4.2398566996787457e-07, 'epoch': 11.78}

 98%|█████████▊| 27575/28080 [54:28:59<59:43,  7.10s/it]
 98%|█████████▊| 27576/28080 [54:29:06<59:46,  7.12s/it]
                                                        
{'loss': 0.5964, 'learning_rate': 4.2230865376421955e-07, 'epoch': 11.78}

 98%|█████████▊| 27576/28080 [54:29:06<59:46,  7.12s/it]
 98%|█████████▊| 27577/28080 [54:29:13<59:37,  7.11s/it]
                                                        
{'loss': 0.6091, 'learning_rate': 4.20634957934235e-07, 'epoch': 11.78}

 98%|█████████▊| 27577/28080 [54:29:13<59:37,  7.11s/it]
 98%|█████████▊| 27578/28080 [54:29:20<59:37,  7.13s/it]
                                                        
{'loss': 0.5895, 'learning_rate': 4.189645825002364e-07, 'epoch': 11.78}

 98%|█████████▊| 27578/28080 [54:29:20<59:37,  7.13s/it]
 98%|█████████▊| 27579/28080 [54:29:28<59:38,  7.14s/it]
                                                        
{'loss': 0.5896, 'learning_rate': 4.172975274844282e-07, 'epoch': 11.78}

 98%|█████████▊| 27579/28080 [54:29:28<59:38,  7.14s/it]
 98%|█████████▊| 27580/28080 [54:29:35<59:31,  7.14s/it]
                                                        
{'loss': 0.5873, 'learning_rate': 4.156337929090148e-07, 'epoch': 11.78}

 98%|█████████▊| 27580/28080 [54:29:35<59:31,  7.14s/it]
 98%|█████████▊| 27581/28080 [54:29:42<59:20,  7.14s/it]
                                                        
{'loss': 0.5814, 'learning_rate': 4.1397337879608976e-07, 'epoch': 11.78}

 98%|█████████▊| 27581/28080 [54:29:42<59:20,  7.14s/it]
 98%|█████████▊| 27582/28080 [54:29:49<59:18,  7.15s/it]
                                                        
{'loss': 0.6076, 'learning_rate': 4.123162851677742e-07, 'epoch': 11.78}

 98%|█████████▊| 27582/28080 [54:29:49<59:18,  7.15s/it]
 98%|█████████▊| 27583/28080 [54:29:56<59:12,  7.15s/it]
                                                        
{'loss': 0.5961, 'learning_rate': 4.106625120461061e-07, 'epoch': 11.78}

 98%|█████████▊| 27583/28080 [54:29:56<59:12,  7.15s/it]
 98%|█████████▊| 27584/28080 [54:30:03<59:25,  7.19s/it]
                                                        
{'loss': 0.6055, 'learning_rate': 4.090120594530955e-07, 'epoch': 11.78}

 98%|█████████▊| 27584/28080 [54:30:03<59:25,  7.19s/it]
 98%|█████████▊| 27585/28080 [54:30:11<59:11,  7.18s/it]
                                                        
{'loss': 0.5873, 'learning_rate': 4.073649274106972e-07, 'epoch': 11.78}

 98%|█████████▊| 27585/28080 [54:30:11<59:11,  7.18s/it]
 98%|█████████▊| 27586/28080 [54:30:18<59:08,  7.18s/it]
                                                        
{'loss': 0.6192, 'learning_rate': 4.0572111594078253e-07, 'epoch': 11.78}

 98%|█████████▊| 27586/28080 [54:30:18<59:08,  7.18s/it]
 98%|█████████▊| 27587/28080 [54:30:25<58:41,  7.14s/it]
                                                        
{'loss': 0.6167, 'learning_rate': 4.0408062506527844e-07, 'epoch': 11.78}

 98%|█████████▊| 27587/28080 [54:30:25<58:41,  7.14s/it]
 98%|█████████▊| 27588/28080 [54:30:32<58:42,  7.16s/it]
                                                        
{'loss': 0.6116, 'learning_rate': 4.0244345480600074e-07, 'epoch': 11.79}

 98%|█████████▊| 27588/28080 [54:30:32<58:42,  7.16s/it]
 98%|█████████▊| 27589/28080 [54:30:39<58:36,  7.16s/it]
                                                        
{'loss': 0.6029, 'learning_rate': 4.008096051847099e-07, 'epoch': 11.79}

 98%|█████████▊| 27589/28080 [54:30:39<58:36,  7.16s/it]
 98%|█████████▊| 27590/28080 [54:30:46<58:20,  7.14s/it]
                                                        
{'loss': 0.6117, 'learning_rate': 3.9917907622313843e-07, 'epoch': 11.79}

 98%|█████████▊| 27590/28080 [54:30:46<58:20,  7.14s/it]
 98%|█████████▊| 27591/28080 [54:30:53<58:11,  7.14s/it]
                                                        
{'loss': 0.5945, 'learning_rate': 3.9755186794299125e-07, 'epoch': 11.79}

 98%|█████████▊| 27591/28080 [54:30:53<58:11,  7.14s/it]
 98%|█████████▊| 27592/28080 [54:31:00<57:58,  7.13s/it]
                                                        
{'loss': 0.5967, 'learning_rate': 3.959279803659177e-07, 'epoch': 11.79}

 98%|█████████▊| 27592/28080 [54:31:00<57:58,  7.13s/it]
 98%|█████████▊| 27593/28080 [54:31:08<57:49,  7.12s/it]
                                                        
{'loss': 0.5715, 'learning_rate': 3.943074135135394e-07, 'epoch': 11.79}

 98%|█████████▊| 27593/28080 [54:31:08<57:49,  7.12s/it]
 98%|█████████▊| 27594/28080 [54:31:15<57:40,  7.12s/it]
                                                        
{'loss': 0.596, 'learning_rate': 3.9269016740736687e-07, 'epoch': 11.79}

 98%|█████████▊| 27594/28080 [54:31:15<57:40,  7.12s/it]
 98%|█████████▊| 27595/28080 [54:31:22<57:42,  7.14s/it]
                                                        
{'loss': 0.5992, 'learning_rate': 3.9107624206896617e-07, 'epoch': 11.79}

 98%|█████████▊| 27595/28080 [54:31:22<57:42,  7.14s/it]
 98%|█████████▊| 27596/28080 [54:31:29<57:43,  7.16s/it]
                                                        
{'loss': 0.5958, 'learning_rate': 3.8946563751976473e-07, 'epoch': 11.79}

 98%|█████████▊| 27596/28080 [54:31:29<57:43,  7.16s/it]
 98%|█████████▊| 27597/28080 [54:31:36<57:19,  7.12s/it]
                                                        
{'loss': 0.5801, 'learning_rate': 3.878583537812452e-07, 'epoch': 11.79}

 98%|█████████▊| 27597/28080 [54:31:36<57:19,  7.12s/it]
 98%|█████████▊| 27598/28080 [54:31:43<57:09,  7.12s/it]
                                                        
{'loss': 0.6065, 'learning_rate': 3.862543908747518e-07, 'epoch': 11.79}

 98%|█████████▊| 27598/28080 [54:31:43<57:09,  7.12s/it]
 98%|█████████▊| 27599/28080 [54:31:50<56:57,  7.10s/it]
                                                        
{'loss': 0.5882, 'learning_rate': 3.846537488216284e-07, 'epoch': 11.79}

 98%|█████████▊| 27599/28080 [54:31:50<56:57,  7.10s/it]
 98%|█████████▊| 27600/28080 [54:31:57<56:55,  7.11s/it]
                                                        
{'loss': 0.6109, 'learning_rate': 3.830564276431636e-07, 'epoch': 11.79}

 98%|█████████▊| 27600/28080 [54:31:57<56:55,  7.11s/it]
 98%|█████████▊| 27601/28080 [54:32:05<56:53,  7.13s/it]
                                                        
{'loss': 0.6188, 'learning_rate': 3.814624273606182e-07, 'epoch': 11.79}

 98%|█████████▊| 27601/28080 [54:32:05<56:53,  7.13s/it]
 98%|█████████▊| 27602/28080 [54:32:12<56:29,  7.09s/it]
                                                        
{'loss': 0.6154, 'learning_rate': 3.798717479951974e-07, 'epoch': 11.79}

 98%|█████████▊| 27602/28080 [54:32:12<56:29,  7.09s/it]
 98%|█████████▊| 27603/28080 [54:32:19<56:24,  7.10s/it]
                                                        
{'loss': 0.6101, 'learning_rate': 3.7828438956807875e-07, 'epoch': 11.79}

 98%|█████████▊| 27603/28080 [54:32:19<56:24,  7.10s/it]
 98%|█████████▊| 27604/28080 [54:32:26<56:18,  7.10s/it]
                                                        
{'loss': 0.5989, 'learning_rate': 3.7670035210035645e-07, 'epoch': 11.79}

 98%|█████████▊| 27604/28080 [54:32:26<56:18,  7.10s/it]
 98%|█████████▊| 27605/28080 [54:32:33<56:28,  7.13s/it]
                                                        
{'loss': 0.5844, 'learning_rate': 3.751196356131248e-07, 'epoch': 11.79}

 98%|█████████▊| 27605/28080 [54:32:33<56:28,  7.13s/it]
 98%|█████████▊| 27606/28080 [54:32:40<56:16,  7.12s/it]
                                                        
{'loss': 0.6019, 'learning_rate': 3.735422401273947e-07, 'epoch': 11.79}

 98%|█████████▊| 27606/28080 [54:32:40<56:16,  7.12s/it]
 98%|█████████▊| 27607/28080 [54:32:47<56:10,  7.12s/it]
                                                        
{'loss': 0.5885, 'learning_rate': 3.7196816566414935e-07, 'epoch': 11.79}

 98%|█████████▊| 27607/28080 [54:32:47<56:10,  7.12s/it]
 98%|█████████▊| 27608/28080 [54:32:54<56:12,  7.15s/it]
                                                        
{'loss': 0.5902, 'learning_rate': 3.703974122443721e-07, 'epoch': 11.79}

 98%|█████████▊| 27608/28080 [54:32:54<56:12,  7.15s/it]
 98%|█████████▊| 27609/28080 [54:33:02<56:04,  7.14s/it]
                                                        
{'loss': 0.5942, 'learning_rate': 3.688299798889072e-07, 'epoch': 11.79}

 98%|█████████▊| 27609/28080 [54:33:02<56:04,  7.14s/it]
 98%|█████████▊| 27610/28080 [54:33:09<56:06,  7.16s/it]
                                                        
{'loss': 0.6057, 'learning_rate': 3.67265868618627e-07, 'epoch': 11.79}

 98%|█████████▊| 27610/28080 [54:33:09<56:06,  7.16s/it]
 98%|█████████▊| 27611/28080 [54:33:16<55:53,  7.15s/it]
                                                        
{'loss': 0.5933, 'learning_rate': 3.657050784543481e-07, 'epoch': 11.8}

 98%|█████████▊| 27611/28080 [54:33:16<55:53,  7.15s/it]
 98%|█████████▊| 27612/28080 [54:33:23<55:42,  7.14s/it]
                                                        
{'loss': 0.6014, 'learning_rate': 3.641476094168317e-07, 'epoch': 11.8}

 98%|█████████▊| 27612/28080 [54:33:23<55:42,  7.14s/it]
 98%|█████████▊| 27613/28080 [54:33:30<55:30,  7.13s/it]
                                                        
{'loss': 0.6234, 'learning_rate': 3.625934615267834e-07, 'epoch': 11.8}

 98%|█████████▊| 27613/28080 [54:33:30<55:30,  7.13s/it]
 98%|█████████▊| 27614/28080 [54:33:37<55:34,  7.15s/it]
                                                        
{'loss': 0.5955, 'learning_rate': 3.61042634804909e-07, 'epoch': 11.8}

 98%|█████████▊| 27614/28080 [54:33:37<55:34,  7.15s/it]
 98%|█████████▊| 27615/28080 [54:33:44<55:23,  7.15s/it]
                                                        
{'loss': 0.6188, 'learning_rate': 3.5949512927180294e-07, 'epoch': 11.8}

 98%|█████████▊| 27615/28080 [54:33:44<55:23,  7.15s/it]
 98%|█████████▊| 27616/28080 [54:33:52<55:17,  7.15s/it]
                                                        
{'loss': 0.6047, 'learning_rate': 3.5795094494808777e-07, 'epoch': 11.8}

 98%|█████████▊| 27616/28080 [54:33:52<55:17,  7.15s/it]
 98%|█████████▊| 27617/28080 [54:33:59<55:17,  7.17s/it]
                                                        
{'loss': 0.599, 'learning_rate': 3.564100818543026e-07, 'epoch': 11.8}

 98%|█████████▊| 27617/28080 [54:33:59<55:17,  7.17s/it]
 98%|█████████▊| 27618/28080 [54:34:06<54:59,  7.14s/it]
                                                        
{'loss': 0.589, 'learning_rate': 3.5487254001093096e-07, 'epoch': 11.8}

 98%|█████████▊| 27618/28080 [54:34:06<54:59,  7.14s/it]
 98%|█████████▊| 27619/28080 [54:34:13<54:56,  7.15s/it]
                                                        
{'loss': 0.5965, 'learning_rate': 3.5333831943842876e-07, 'epoch': 11.8}

 98%|█████████▊| 27619/28080 [54:34:13<54:56,  7.15s/it]
 98%|█████████▊| 27620/28080 [54:34:20<54:48,  7.15s/it]
                                                        
{'loss': 0.5872, 'learning_rate': 3.518074201572241e-07, 'epoch': 11.8}

 98%|█████████▊| 27620/28080 [54:34:20<54:48,  7.15s/it]
 98%|█████████▊| 27621/28080 [54:34:27<54:33,  7.13s/it]
                                                        
{'loss': 0.5955, 'learning_rate': 3.5027984218766184e-07, 'epoch': 11.8}

 98%|█████████▊| 27621/28080 [54:34:27<54:33,  7.13s/it]
 98%|█████████▊| 27622/28080 [54:34:34<54:19,  7.12s/it]
                                                        
{'loss': 0.5753, 'learning_rate': 3.487555855500868e-07, 'epoch': 11.8}

 98%|█████████▊| 27622/28080 [54:34:34<54:19,  7.12s/it]
 98%|█████████▊| 27623/28080 [54:34:42<54:22,  7.14s/it]
                                                        
{'loss': 0.607, 'learning_rate': 3.4723465026476053e-07, 'epoch': 11.8}

 98%|█████████▊| 27623/28080 [54:34:42<54:22,  7.14s/it]
 98%|█████████▊| 27624/28080 [54:34:49<54:19,  7.15s/it]
                                                        
{'loss': 0.6052, 'learning_rate': 3.457170363519169e-07, 'epoch': 11.8}

 98%|█████████▊| 27624/28080 [54:34:49<54:19,  7.15s/it]
 98%|█████████▊| 27625/28080 [54:34:56<54:14,  7.15s/it]
                                                        
{'loss': 0.5782, 'learning_rate': 3.4420274383176187e-07, 'epoch': 11.8}

 98%|█████████▊| 27625/28080 [54:34:56<54:14,  7.15s/it]
 98%|█████████▊| 27626/28080 [54:35:03<53:53,  7.12s/it]
                                                        
{'loss': 0.5842, 'learning_rate': 3.426917727244461e-07, 'epoch': 11.8}

 98%|█████████▊| 27626/28080 [54:35:03<53:53,  7.12s/it]
 98%|█████████▊| 27627/28080 [54:35:10<53:31,  7.09s/it]
                                                        
{'loss': 0.5979, 'learning_rate': 3.4118412305006453e-07, 'epoch': 11.8}

 98%|█████████▊| 27627/28080 [54:35:10<53:31,  7.09s/it]
 98%|█████████▊| 27628/28080 [54:35:17<53:45,  7.14s/it]
                                                        
{'loss': 0.6232, 'learning_rate': 3.3967979482865675e-07, 'epoch': 11.8}

 98%|█████████▊| 27628/28080 [54:35:17<53:45,  7.14s/it]
 98%|█████████▊| 27629/28080 [54:35:24<53:36,  7.13s/it]
                                                        
{'loss': 0.5923, 'learning_rate': 3.381787880802345e-07, 'epoch': 11.8}

 98%|█████████▊| 27629/28080 [54:35:24<53:36,  7.13s/it]
 98%|█████████▊| 27630/28080 [54:35:32<53:40,  7.16s/it]
                                                        
{'loss': 0.5951, 'learning_rate': 3.3668110282480955e-07, 'epoch': 11.8}

 98%|█████████▊| 27630/28080 [54:35:32<53:40,  7.16s/it]
 98%|█████████▊| 27631/28080 [54:35:39<53:24,  7.14s/it]
                                                        
{'loss': 0.5985, 'learning_rate': 3.3518673908225495e-07, 'epoch': 11.8}

 98%|█████████▊| 27631/28080 [54:35:39<53:24,  7.14s/it]
 98%|█████████▊| 27632/28080 [54:35:46<53:14,  7.13s/it]
                                                        
{'loss': 0.5799, 'learning_rate': 3.3369569687249913e-07, 'epoch': 11.8}

 98%|█████████▊| 27632/28080 [54:35:46<53:14,  7.13s/it]
 98%|█████████▊| 27633/28080 [54:35:53<52:57,  7.11s/it]
                                                        
{'loss': 0.5901, 'learning_rate': 3.322079762153318e-07, 'epoch': 11.8}

 98%|█████████▊| 27633/28080 [54:35:53<52:57,  7.11s/it]
 98%|█████████▊| 27634/28080 [54:36:00<53:00,  7.13s/it]
                                                        
{'loss': 0.5948, 'learning_rate': 3.3072357713057054e-07, 'epoch': 11.8}

 98%|█████████▊| 27634/28080 [54:36:00<53:00,  7.13s/it]
 98%|█████████▊| 27635/28080 [54:36:07<52:57,  7.14s/it]
                                                        
{'loss': 0.5976, 'learning_rate': 3.2924249963797724e-07, 'epoch': 11.81}

 98%|█████████▊| 27635/28080 [54:36:07<52:57,  7.14s/it]
 98%|█████████▊| 27636/28080 [54:36:14<52:27,  7.09s/it]
                                                        
{'loss': 0.5935, 'learning_rate': 3.2776474375723064e-07, 'epoch': 11.81}

 98%|█████████▊| 27636/28080 [54:36:14<52:27,  7.09s/it]
 98%|█████████▊| 27637/28080 [54:36:21<52:26,  7.10s/it]
                                                        
{'loss': 0.6125, 'learning_rate': 3.2629030950800944e-07, 'epoch': 11.81}

 98%|█████████▊| 27637/28080 [54:36:21<52:26,  7.10s/it]
 98%|█████████▊| 27638/28080 [54:36:28<52:25,  7.12s/it]
                                                        
{'loss': 0.5896, 'learning_rate': 3.2481919690993675e-07, 'epoch': 11.81}

 98%|█████████▊| 27638/28080 [54:36:28<52:25,  7.12s/it]
 98%|█████████▊| 27639/28080 [54:36:36<52:24,  7.13s/it]
                                                        
{'loss': 0.5988, 'learning_rate': 3.233514059825526e-07, 'epoch': 11.81}

 98%|█████████▊| 27639/28080 [54:36:36<52:24,  7.13s/it]
 98%|█████████▊| 27640/28080 [54:36:43<52:25,  7.15s/it]
                                                        
{'loss': 0.6078, 'learning_rate': 3.218869367453969e-07, 'epoch': 11.81}

 98%|█████████▊| 27640/28080 [54:36:43<52:25,  7.15s/it]
 98%|█████████▊| 27641/28080 [54:36:50<52:15,  7.14s/it]
                                                        
{'loss': 0.6174, 'learning_rate': 3.2042578921795406e-07, 'epoch': 11.81}

 98%|█████████▊| 27641/28080 [54:36:50<52:15,  7.14s/it]
 98%|█████████▊| 27642/28080 [54:36:57<51:40,  7.08s/it]
                                                        
{'loss': 0.6011, 'learning_rate': 3.189679634196807e-07, 'epoch': 11.81}

 98%|█████████▊| 27642/28080 [54:36:57<51:40,  7.08s/it]
 98%|█████████▊| 27643/28080 [54:37:04<51:39,  7.09s/it]
                                                        
{'loss': 0.5927, 'learning_rate': 3.1751345936995026e-07, 'epoch': 11.81}

 98%|█████████▊| 27643/28080 [54:37:04<51:39,  7.09s/it]
 98%|█████████▊| 27644/28080 [54:37:11<51:46,  7.12s/it]
                                                        
{'loss': 0.5723, 'learning_rate': 3.160622770881083e-07, 'epoch': 11.81}

 98%|█████████▊| 27644/28080 [54:37:11<51:46,  7.12s/it]
 98%|█████████▊| 27645/28080 [54:37:18<51:45,  7.14s/it]
                                                        
{'loss': 0.5971, 'learning_rate': 3.1461441659350054e-07, 'epoch': 11.81}

 98%|█████████▊| 27645/28080 [54:37:18<51:45,  7.14s/it]
 98%|█████████▊| 27646/28080 [54:37:25<51:35,  7.13s/it]
                                                        
{'loss': 0.6121, 'learning_rate': 3.131698779053338e-07, 'epoch': 11.81}

 98%|█████████▊| 27646/28080 [54:37:25<51:35,  7.13s/it]
 98%|█████████▊| 27647/28080 [54:37:33<51:26,  7.13s/it]
                                                        
{'loss': 0.5876, 'learning_rate': 3.1172866104287047e-07, 'epoch': 11.81}

 98%|█████████▊| 27647/28080 [54:37:33<51:26,  7.13s/it]
 98%|█████████▊| 27648/28080 [54:37:40<51:21,  7.13s/it]
                                                        
{'loss': 0.6014, 'learning_rate': 3.1029076602526184e-07, 'epoch': 11.81}

 98%|█████████▊| 27648/28080 [54:37:40<51:21,  7.13s/it]
 98%|█████████▊| 27649/28080 [54:37:47<51:04,  7.11s/it]
                                                        
{'loss': 0.5978, 'learning_rate': 3.0885619287165935e-07, 'epoch': 11.81}

 98%|█████████▊| 27649/28080 [54:37:47<51:04,  7.11s/it]
 98%|█████████▊| 27650/28080 [54:37:54<51:21,  7.17s/it]
                                                        
{'loss': 0.6007, 'learning_rate': 3.0742494160110324e-07, 'epoch': 11.81}

 98%|█████████▊| 27650/28080 [54:37:54<51:21,  7.17s/it]
 98%|█████████▊| 27651/28080 [54:38:01<51:07,  7.15s/it]
                                                        
{'loss': 0.5831, 'learning_rate': 3.059970122326894e-07, 'epoch': 11.81}

 98%|█████████▊| 27651/28080 [54:38:01<51:07,  7.15s/it]
 98%|█████████▊| 27652/28080 [54:38:08<51:00,  7.15s/it]
                                                        
{'loss': 0.5939, 'learning_rate': 3.0457240478537484e-07, 'epoch': 11.81}

 98%|█████████▊| 27652/28080 [54:38:08<51:00,  7.15s/it]
 98%|█████████▊| 27653/28080 [54:38:16<51:00,  7.17s/it]
                                                        
{'loss': 0.5989, 'learning_rate': 3.0315111927814444e-07, 'epoch': 11.81}

 98%|█████████▊| 27653/28080 [54:38:16<51:00,  7.17s/it]
 98%|█████████▊| 27654/28080 [54:38:23<50:31,  7.12s/it]
                                                        
{'loss': 0.5883, 'learning_rate': 3.0173315572987193e-07, 'epoch': 11.81}

 98%|█████████▊| 27654/28080 [54:38:23<50:31,  7.12s/it]
 98%|█████████▊| 27655/28080 [54:38:30<50:15,  7.10s/it]
                                                        
{'loss': 0.5913, 'learning_rate': 3.0031851415945886e-07, 'epoch': 11.81}

 98%|█████████▊| 27655/28080 [54:38:30<50:15,  7.10s/it]
 98%|█████████▊| 27656/28080 [54:38:37<50:17,  7.12s/it]
                                                        
{'loss': 0.6047, 'learning_rate': 2.989071945856958e-07, 'epoch': 11.81}

 98%|█████████▊| 27656/28080 [54:38:37<50:17,  7.12s/it]
 98%|█████████▊| 27657/28080 [54:38:44<50:14,  7.13s/it]
                                                        
{'loss': 0.5982, 'learning_rate': 2.9749919702737326e-07, 'epoch': 11.81}

 98%|█████████▊| 27657/28080 [54:38:44<50:14,  7.13s/it]
 98%|█████████▊| 27658/28080 [54:38:51<50:16,  7.15s/it]
                                                        
{'loss': 0.5966, 'learning_rate': 2.9609452150322623e-07, 'epoch': 11.82}

 98%|█████████▊| 27658/28080 [54:38:51<50:16,  7.15s/it]
 99%|█████████▊| 27659/28080 [54:38:58<50:03,  7.13s/it]
                                                        
{'loss': 0.5937, 'learning_rate': 2.9469316803190647e-07, 'epoch': 11.82}

 99%|█████████▊| 27659/28080 [54:38:58<50:03,  7.13s/it]
 99%|█████████▊| 27660/28080 [54:39:05<49:57,  7.14s/it]
                                                        
{'loss': 0.5842, 'learning_rate': 2.9329513663212126e-07, 'epoch': 11.82}

 99%|█████████▊| 27660/28080 [54:39:05<49:57,  7.14s/it]
 99%|█████████▊| 27661/28080 [54:39:13<49:59,  7.16s/it]
                                                        
{'loss': 0.5909, 'learning_rate': 2.919004273224113e-07, 'epoch': 11.82}

 99%|█████████▊| 27661/28080 [54:39:13<49:59,  7.16s/it]
 99%|█████████▊| 27662/28080 [54:39:20<49:42,  7.14s/it]
                                                        
{'loss': 0.5884, 'learning_rate': 2.905090401213728e-07, 'epoch': 11.82}

 99%|█████████▊| 27662/28080 [54:39:20<49:42,  7.14s/it]
 99%|█████████▊| 27663/28080 [54:39:27<49:34,  7.13s/it]
                                                        
{'loss': 0.5902, 'learning_rate': 2.891209750475188e-07, 'epoch': 11.82}

 99%|█████████▊| 27663/28080 [54:39:27<49:34,  7.13s/it]
 99%|█████████▊| 27664/28080 [54:39:34<49:13,  7.10s/it]
                                                        
{'loss': 0.6114, 'learning_rate': 2.877362321192789e-07, 'epoch': 11.82}

 99%|█████████▊| 27664/28080 [54:39:34<49:13,  7.10s/it]
 99%|█████████▊| 27665/28080 [54:39:41<49:12,  7.11s/it]
                                                        
{'loss': 0.595, 'learning_rate': 2.863548113550829e-07, 'epoch': 11.82}

 99%|█████████▊| 27665/28080 [54:39:41<49:12,  7.11s/it]
 99%|█████████▊| 27666/28080 [54:39:48<48:58,  7.10s/it]
                                                        
{'loss': 0.6213, 'learning_rate': 2.849767127733327e-07, 'epoch': 11.82}

 99%|█████████▊| 27666/28080 [54:39:48<48:58,  7.10s/it]
 99%|█████████▊| 27667/28080 [54:39:55<48:56,  7.11s/it]
                                                        
{'loss': 0.5971, 'learning_rate': 2.83601936392347e-07, 'epoch': 11.82}

 99%|█████████▊| 27667/28080 [54:39:55<48:56,  7.11s/it]
 99%|█████████▊| 27668/28080 [54:40:02<48:56,  7.13s/it]
                                                        
{'loss': 0.6098, 'learning_rate': 2.822304822304167e-07, 'epoch': 11.82}

 99%|█████████▊| 27668/28080 [54:40:02<48:56,  7.13s/it]
 99%|█████████▊| 27669/28080 [54:40:09<48:48,  7.12s/it]
                                                        
{'loss': 0.592, 'learning_rate': 2.80862350305805e-07, 'epoch': 11.82}

 99%|█████████▊| 27669/28080 [54:40:09<48:48,  7.12s/it]
 99%|█████████▊| 27670/28080 [54:40:17<48:51,  7.15s/it]
                                                        
{'loss': 0.5992, 'learning_rate': 2.7949754063669175e-07, 'epoch': 11.82}

 99%|█████████▊| 27670/28080 [54:40:17<48:51,  7.15s/it]
 99%|█████████▊| 27671/28080 [54:40:24<48:30,  7.12s/it]
                                                        
{'loss': 0.6259, 'learning_rate': 2.7813605324122916e-07, 'epoch': 11.82}

 99%|█████████▊| 27671/28080 [54:40:24<48:30,  7.12s/it]
 99%|█████████▊| 27672/28080 [54:40:31<48:33,  7.14s/it]
                                                        
{'loss': 0.6019, 'learning_rate': 2.7677788813754156e-07, 'epoch': 11.82}

 99%|█████████▊| 27672/28080 [54:40:31<48:33,  7.14s/it]
 99%|█████████▊| 27673/28080 [54:40:38<48:41,  7.18s/it]
                                                        
{'loss': 0.5892, 'learning_rate': 2.7542304534372565e-07, 'epoch': 11.82}

 99%|█████████▊| 27673/28080 [54:40:38<48:41,  7.18s/it]
 99%|█████████▊| 27674/28080 [54:40:45<48:41,  7.20s/it]
                                                        
{'loss': 0.6065, 'learning_rate': 2.74071524877767e-07, 'epoch': 11.82}

 99%|█████████▊| 27674/28080 [54:40:45<48:41,  7.20s/it]
 99%|█████████▊| 27675/28080 [54:40:53<48:25,  7.17s/it]
                                                        
{'loss': 0.6096, 'learning_rate': 2.727233267576512e-07, 'epoch': 11.82}

 99%|█████████▊| 27675/28080 [54:40:53<48:25,  7.17s/it]
 99%|█████████▊| 27676/28080 [54:41:00<48:17,  7.17s/it]
                                                        
{'loss': 0.6021, 'learning_rate': 2.7137845100130843e-07, 'epoch': 11.82}

 99%|█████████▊| 27676/28080 [54:41:00<48:17,  7.17s/it]
 99%|█████████▊| 27677/28080 [54:41:07<48:04,  7.16s/it]
                                                        
{'loss': 0.5983, 'learning_rate': 2.700368976266687e-07, 'epoch': 11.82}

 99%|█████████▊| 27677/28080 [54:41:07<48:04,  7.16s/it]
 99%|█████████▊| 27678/28080 [54:41:14<48:02,  7.17s/it]
                                                        
{'loss': 0.5826, 'learning_rate': 2.686986666515512e-07, 'epoch': 11.82}

 99%|█████████▊| 27678/28080 [54:41:14<48:02,  7.17s/it]
 99%|█████████▊| 27679/28080 [54:41:21<47:54,  7.17s/it]
                                                        
{'loss': 0.5845, 'learning_rate': 2.673637580937471e-07, 'epoch': 11.82}

 99%|█████████▊| 27679/28080 [54:41:21<47:54,  7.17s/it]
 99%|█████████▊| 27680/28080 [54:41:28<47:41,  7.15s/it]
                                                        
{'loss': 0.6116, 'learning_rate': 2.660321719710757e-07, 'epoch': 11.82}

 99%|█████████▊| 27680/28080 [54:41:28<47:41,  7.15s/it]
 99%|█████████▊| 27681/28080 [54:41:35<47:14,  7.10s/it]
                                                        
{'loss': 0.6, 'learning_rate': 2.6470390830118927e-07, 'epoch': 11.83}

 99%|█████████▊| 27681/28080 [54:41:35<47:14,  7.10s/it]
 99%|█████████▊| 27682/28080 [54:41:42<46:52,  7.07s/it]
                                                        
{'loss': 0.6023, 'learning_rate': 2.6337896710176834e-07, 'epoch': 11.83}

 99%|█████████▊| 27682/28080 [54:41:42<46:52,  7.07s/it]
 99%|█████████▊| 27683/28080 [54:41:49<46:47,  7.07s/it]
                                                        
{'loss': 0.5843, 'learning_rate': 2.620573483904376e-07, 'epoch': 11.83}

 99%|█████████▊| 27683/28080 [54:41:49<46:47,  7.07s/it]
 99%|█████████▊| 27684/28080 [54:41:56<46:46,  7.09s/it]
                                                        
{'loss': 0.6015, 'learning_rate': 2.6073905218482184e-07, 'epoch': 11.83}

 99%|█████████▊| 27684/28080 [54:41:56<46:46,  7.09s/it]
 99%|█████████▊| 27685/28080 [54:42:04<46:44,  7.10s/it]
                                                        
{'loss': 0.5915, 'learning_rate': 2.594240785024349e-07, 'epoch': 11.83}

 99%|█████████▊| 27685/28080 [54:42:04<46:44,  7.10s/it]
 99%|█████████▊| 27686/28080 [54:42:11<46:50,  7.13s/it]
                                                        
{'loss': 0.5798, 'learning_rate': 2.581124273607349e-07, 'epoch': 11.83}

 99%|█████████▊| 27686/28080 [54:42:11<46:50,  7.13s/it]
 99%|█████████▊| 27687/28080 [54:42:18<46:38,  7.12s/it]
                                                        
{'loss': 0.6131, 'learning_rate': 2.5680409877723575e-07, 'epoch': 11.83}

 99%|█████████▊| 27687/28080 [54:42:18<46:38,  7.12s/it]
 99%|█████████▊| 27688/28080 [54:42:25<46:38,  7.14s/it]
                                                        
{'loss': 0.5965, 'learning_rate': 2.554990927693124e-07, 'epoch': 11.83}

 99%|█████████▊| 27688/28080 [54:42:25<46:38,  7.14s/it]
 99%|█████████▊| 27689/28080 [54:42:32<46:35,  7.15s/it]
                                                        
{'loss': 0.5831, 'learning_rate': 2.5419740935431204e-07, 'epoch': 11.83}

 99%|█████████▊| 27689/28080 [54:42:32<46:35,  7.15s/it]
 99%|█████████▊| 27690/28080 [54:42:39<46:35,  7.17s/it]
                                                        
{'loss': 0.5786, 'learning_rate': 2.5289904854955416e-07, 'epoch': 11.83}

 99%|█████████▊| 27690/28080 [54:42:39<46:35,  7.17s/it]
 99%|█████████▊| 27691/28080 [54:42:47<46:35,  7.19s/it]
                                                        
{'loss': 0.5983, 'learning_rate': 2.5160401037235827e-07, 'epoch': 11.83}

 99%|█████████▊| 27691/28080 [54:42:47<46:35,  7.19s/it]
 99%|█████████▊| 27692/28080 [54:42:54<46:22,  7.17s/it]
                                                        
{'loss': 0.59, 'learning_rate': 2.5031229483990504e-07, 'epoch': 11.83}

 99%|█████████▊| 27692/28080 [54:42:54<46:22,  7.17s/it]
 99%|█████████▊| 27693/28080 [54:43:01<46:27,  7.20s/it]
                                                        
{'loss': 0.5886, 'learning_rate': 2.4902390196937516e-07, 'epoch': 11.83}

 99%|█████████▊| 27693/28080 [54:43:01<46:27,  7.20s/it]
 99%|█████████▊| 27694/28080 [54:43:08<46:10,  7.18s/it]
                                                        
{'loss': 0.5942, 'learning_rate': 2.4773883177794943e-07, 'epoch': 11.83}

 99%|█████████▊| 27694/28080 [54:43:08<46:10,  7.18s/it]
 99%|█████████▊| 27695/28080 [54:43:15<45:51,  7.15s/it]
                                                        
{'loss': 0.6182, 'learning_rate': 2.464570842826974e-07, 'epoch': 11.83}

 99%|█████████▊| 27695/28080 [54:43:15<45:51,  7.15s/it]
 99%|█████████▊| 27696/28080 [54:43:23<45:52,  7.17s/it]
                                                        
{'loss': 0.6064, 'learning_rate': 2.4517865950068883e-07, 'epoch': 11.83}

 99%|█████████▊| 27696/28080 [54:43:23<45:52,  7.17s/it]
 99%|█████████▊| 27697/28080 [54:43:30<45:48,  7.18s/it]
                                                        
{'loss': 0.582, 'learning_rate': 2.4390355744891014e-07, 'epoch': 11.83}

 99%|█████████▊| 27697/28080 [54:43:30<45:48,  7.18s/it]
 99%|█████████▊| 27698/28080 [54:43:37<45:48,  7.20s/it]
                                                        
{'loss': 0.5925, 'learning_rate': 2.426317781443199e-07, 'epoch': 11.83}

 99%|█████████▊| 27698/28080 [54:43:37<45:48,  7.20s/it]
 99%|█████████▊| 27699/28080 [54:43:44<45:42,  7.20s/it]
                                                        
{'loss': 0.5959, 'learning_rate': 2.4136332160387686e-07, 'epoch': 11.83}

 99%|█████████▊| 27699/28080 [54:43:44<45:42,  7.20s/it]
 99%|█████████▊| 27700/28080 [54:43:51<45:30,  7.18s/it]
                                                        
{'loss': 0.5978, 'learning_rate': 2.400981878444286e-07, 'epoch': 11.83}

 99%|█████████▊| 27700/28080 [54:43:51<45:30,  7.18s/it]
 99%|█████████▊| 27701/28080 [54:43:58<45:19,  7.18s/it]
                                                        
{'loss': 0.6162, 'learning_rate': 2.3883637688282276e-07, 'epoch': 11.83}

 99%|█████████▊| 27701/28080 [54:43:58<45:19,  7.18s/it]
 99%|█████████▊| 27702/28080 [54:44:06<45:17,  7.19s/it]
                                                        
{'loss': 0.5912, 'learning_rate': 2.37577888735796e-07, 'epoch': 11.83}

 99%|█████████▊| 27702/28080 [54:44:06<45:17,  7.19s/it]
 99%|█████████▊| 27703/28080 [54:44:13<45:02,  7.17s/it]
                                                        
{'loss': 0.5999, 'learning_rate': 2.3632272342016814e-07, 'epoch': 11.83}

 99%|█████████▊| 27703/28080 [54:44:13<45:02,  7.17s/it]
 99%|█████████▊| 27704/28080 [54:44:20<44:52,  7.16s/it]
                                                        
{'loss': 0.6032, 'learning_rate': 2.3507088095259254e-07, 'epoch': 11.83}

 99%|█████████▊| 27704/28080 [54:44:20<44:52,  7.16s/it]
 99%|█████████▊| 27705/28080 [54:44:27<44:41,  7.15s/it]
                                                        
{'loss': 0.5917, 'learning_rate': 2.3382236134972257e-07, 'epoch': 11.84}

 99%|█████████▊| 27705/28080 [54:44:27<44:41,  7.15s/it]
 99%|█████████▊| 27706/28080 [54:44:34<44:33,  7.15s/it]
                                                        
{'loss': 0.6008, 'learning_rate': 2.325771646281838e-07, 'epoch': 11.84}

 99%|█████████▊| 27706/28080 [54:44:34<44:33,  7.15s/it]
 99%|█████████▊| 27707/28080 [54:44:41<44:32,  7.17s/it]
                                                        
{'loss': 0.5875, 'learning_rate': 2.3133529080451853e-07, 'epoch': 11.84}

 99%|█████████▊| 27707/28080 [54:44:41<44:32,  7.17s/it]
 99%|█████████▊| 27708/28080 [54:44:49<44:18,  7.15s/it]
                                                        
{'loss': 0.6111, 'learning_rate': 2.3009673989526912e-07, 'epoch': 11.84}

 99%|█████████▊| 27708/28080 [54:44:49<44:18,  7.15s/it]
 99%|█████████▊| 27709/28080 [54:44:56<44:10,  7.15s/it]
                                                        
{'loss': 0.5797, 'learning_rate': 2.288615119169224e-07, 'epoch': 11.84}

 99%|█████████▊| 27709/28080 [54:44:56<44:10,  7.15s/it]
 99%|█████████▊| 27710/28080 [54:45:03<44:02,  7.14s/it]
                                                        
{'loss': 0.589, 'learning_rate': 2.2762960688588186e-07, 'epoch': 11.84}

 99%|█████████▊| 27710/28080 [54:45:03<44:02,  7.14s/it]
 99%|█████████▊| 27711/28080 [54:45:10<44:02,  7.16s/it]
                                                        
{'loss': 0.5988, 'learning_rate': 2.2640102481857883e-07, 'epoch': 11.84}

 99%|█████████▊| 27711/28080 [54:45:10<44:02,  7.16s/it]
 99%|█████████▊| 27712/28080 [54:45:17<43:55,  7.16s/it]
                                                        
{'loss': 0.5818, 'learning_rate': 2.2517576573130583e-07, 'epoch': 11.84}

 99%|█████████▊| 27712/28080 [54:45:17<43:55,  7.16s/it]
 99%|█████████▊| 27713/28080 [54:45:24<43:38,  7.14s/it]
                                                        
{'loss': 0.6206, 'learning_rate': 2.239538296404109e-07, 'epoch': 11.84}

 99%|█████████▊| 27713/28080 [54:45:24<43:38,  7.14s/it]
 99%|█████████▊| 27714/28080 [54:45:31<43:13,  7.09s/it]
                                                        
{'loss': 0.594, 'learning_rate': 2.2273521656213104e-07, 'epoch': 11.84}

 99%|█████████▊| 27714/28080 [54:45:31<43:13,  7.09s/it]
 99%|█████████▊| 27715/28080 [54:45:38<43:11,  7.10s/it]
                                                        
{'loss': 0.6062, 'learning_rate': 2.2151992651264775e-07, 'epoch': 11.84}

 99%|█████████▊| 27715/28080 [54:45:38<43:11,  7.10s/it]
 99%|█████████▊| 27716/28080 [54:45:46<43:20,  7.15s/it]
                                                        
{'loss': 0.5836, 'learning_rate': 2.2030795950819804e-07, 'epoch': 11.84}

 99%|█████████▊| 27716/28080 [54:45:46<43:20,  7.15s/it]
 99%|█████████▊| 27717/28080 [54:45:53<43:03,  7.12s/it]
                                                        
{'loss': 0.6179, 'learning_rate': 2.1909931556485242e-07, 'epoch': 11.84}

 99%|█████████▊| 27717/28080 [54:45:53<43:03,  7.12s/it]
 99%|█████████▊| 27718/28080 [54:46:00<42:52,  7.11s/it]
                                                        
{'loss': 0.6227, 'learning_rate': 2.1789399469870907e-07, 'epoch': 11.84}

 99%|█████████▊| 27718/28080 [54:46:00<42:52,  7.11s/it]
 99%|█████████▊| 27719/28080 [54:46:07<42:46,  7.11s/it]
                                                        
{'loss': 0.6065, 'learning_rate': 2.16691996925783e-07, 'epoch': 11.84}

 99%|█████████▊| 27719/28080 [54:46:07<42:46,  7.11s/it]
 99%|█████████▊| 27720/28080 [54:46:14<42:42,  7.12s/it]
                                                        
{'loss': 0.5766, 'learning_rate': 2.1549332226211693e-07, 'epoch': 11.84}

 99%|█████████▊| 27720/28080 [54:46:14<42:42,  7.12s/it]
 99%|█████████▊| 27721/28080 [54:46:21<42:39,  7.13s/it]
                                                        
{'loss': 0.5779, 'learning_rate': 2.1429797072358703e-07, 'epoch': 11.84}

 99%|█████████▊| 27721/28080 [54:46:21<42:39,  7.13s/it]
 99%|█████████▊| 27722/28080 [54:46:28<42:36,  7.14s/it]
                                                        
{'loss': 0.6133, 'learning_rate': 2.1310594232615277e-07, 'epoch': 11.84}

 99%|█████████▊| 27722/28080 [54:46:28<42:36,  7.14s/it]
 99%|█████████▊| 27723/28080 [54:46:35<42:24,  7.13s/it]
                                                        
{'loss': 0.6161, 'learning_rate': 2.119172370856348e-07, 'epoch': 11.84}

 99%|█████████▊| 27723/28080 [54:46:35<42:24,  7.13s/it]
 99%|█████████▊| 27724/28080 [54:46:42<42:06,  7.10s/it]
                                                        
{'loss': 0.5908, 'learning_rate': 2.1073185501790936e-07, 'epoch': 11.84}

 99%|█████████▊| 27724/28080 [54:46:42<42:06,  7.10s/it]
 99%|█████████▊| 27725/28080 [54:46:50<42:09,  7.12s/it]
                                                        
{'loss': 0.5896, 'learning_rate': 2.095497961386583e-07, 'epoch': 11.84}

 99%|█████████▊| 27725/28080 [54:46:50<42:09,  7.12s/it]
 99%|█████████▊| 27726/28080 [54:46:57<41:55,  7.11s/it]
                                                        
{'loss': 0.581, 'learning_rate': 2.083710604636746e-07, 'epoch': 11.84}

 99%|█████████▊| 27726/28080 [54:46:57<41:55,  7.11s/it]
 99%|█████████▊| 27727/28080 [54:47:04<41:55,  7.13s/it]
                                                        
{'loss': 0.5902, 'learning_rate': 2.0719564800861236e-07, 'epoch': 11.84}

 99%|█████████▊| 27727/28080 [54:47:04<41:55,  7.13s/it]
 99%|█████████▊| 27728/28080 [54:47:11<41:53,  7.14s/it]
                                                        
{'loss': 0.5891, 'learning_rate': 2.0602355878909796e-07, 'epoch': 11.85}

 99%|█████████▊| 27728/28080 [54:47:11<41:53,  7.14s/it]
 99%|█████████▉| 27729/28080 [54:47:18<41:50,  7.15s/it]
                                                        
{'loss': 0.5936, 'learning_rate': 2.0485479282078557e-07, 'epoch': 11.85}

 99%|█████████▉| 27729/28080 [54:47:18<41:50,  7.15s/it]
 99%|█████████▉| 27730/28080 [54:47:25<41:40,  7.14s/it]
                                                        
{'loss': 0.6124, 'learning_rate': 2.0368935011913504e-07, 'epoch': 11.85}

 99%|█████████▉| 27730/28080 [54:47:25<41:40,  7.14s/it]
 99%|█████████▉| 27731/28080 [54:47:33<41:34,  7.15s/it]
                                                        
{'loss': 0.5846, 'learning_rate': 2.0252723069971723e-07, 'epoch': 11.85}

 99%|█████████▉| 27731/28080 [54:47:33<41:34,  7.15s/it]
 99%|█████████▉| 27732/28080 [54:47:40<41:27,  7.15s/it]
                                                        
{'loss': 0.5863, 'learning_rate': 2.0136843457796427e-07, 'epoch': 11.85}

 99%|█████████▉| 27732/28080 [54:47:40<41:27,  7.15s/it]
 99%|█████████▉| 27733/28080 [54:47:47<41:23,  7.16s/it]
                                                        
{'loss': 0.5952, 'learning_rate': 2.00212961769336e-07, 'epoch': 11.85}

 99%|█████████▉| 27733/28080 [54:47:47<41:23,  7.16s/it]
 99%|█████████▉| 27734/28080 [54:47:54<41:15,  7.16s/it]
                                                        
{'loss': 0.5949, 'learning_rate': 1.9906081228912577e-07, 'epoch': 11.85}

 99%|█████████▉| 27734/28080 [54:47:54<41:15,  7.16s/it]
 99%|█████████▉| 27735/28080 [54:48:01<41:06,  7.15s/it]
                                                        
{'loss': 0.6224, 'learning_rate': 1.9791198615273786e-07, 'epoch': 11.85}

 99%|█████████▉| 27735/28080 [54:48:01<41:06,  7.15s/it]
 99%|█████████▉| 27736/28080 [54:48:08<40:56,  7.14s/it]
                                                        
{'loss': 0.6095, 'learning_rate': 1.9676648337541015e-07, 'epoch': 11.85}

 99%|█████████▉| 27736/28080 [54:48:08<40:56,  7.14s/it]
 99%|█████████▉| 27737/28080 [54:48:15<40:50,  7.15s/it]
                                                        
{'loss': 0.6027, 'learning_rate': 1.956243039723804e-07, 'epoch': 11.85}

 99%|█████████▉| 27737/28080 [54:48:15<40:50,  7.15s/it]
 99%|█████████▉| 27738/28080 [54:48:23<40:48,  7.16s/it]
                                                        
{'loss': 0.6325, 'learning_rate': 1.9448544795888644e-07, 'epoch': 11.85}

 99%|█████████▉| 27738/28080 [54:48:23<40:48,  7.16s/it]
 99%|█████████▉| 27739/28080 [54:48:30<40:27,  7.12s/it]
                                                        
{'loss': 0.5813, 'learning_rate': 1.9334991535005508e-07, 'epoch': 11.85}

 99%|█████████▉| 27739/28080 [54:48:30<40:27,  7.12s/it]
 99%|█████████▉| 27740/28080 [54:48:37<40:26,  7.14s/it]
                                                        
{'loss': 0.6124, 'learning_rate': 1.9221770616098533e-07, 'epoch': 11.85}

 99%|█████████▉| 27740/28080 [54:48:37<40:26,  7.14s/it]
 99%|█████████▉| 27741/28080 [54:48:44<40:14,  7.12s/it]
                                                        
{'loss': 0.6232, 'learning_rate': 1.9108882040672072e-07, 'epoch': 11.85}

 99%|█████████▉| 27741/28080 [54:48:44<40:14,  7.12s/it]
 99%|█████████▉| 27742/28080 [54:48:51<40:06,  7.12s/it]
                                                        
{'loss': 0.5993, 'learning_rate': 1.8996325810233251e-07, 'epoch': 11.85}

 99%|█████████▉| 27742/28080 [54:48:51<40:06,  7.12s/it]
 99%|█████████▉| 27743/28080 [54:48:58<39:51,  7.10s/it]
                                                        
{'loss': 0.6058, 'learning_rate': 1.8884101926278097e-07, 'epoch': 11.85}

 99%|█████████▉| 27743/28080 [54:48:58<39:51,  7.10s/it]
 99%|█████████▉| 27744/28080 [54:49:05<39:43,  7.09s/it]
                                                        
{'loss': 0.5989, 'learning_rate': 1.877221039029431e-07, 'epoch': 11.85}

 99%|█████████▉| 27744/28080 [54:49:05<39:43,  7.09s/it]
 99%|█████████▉| 27745/28080 [54:49:12<39:45,  7.12s/it]
                                                        
{'loss': 0.5928, 'learning_rate': 1.8660651203777913e-07, 'epoch': 11.85}

 99%|█████████▉| 27745/28080 [54:49:12<39:45,  7.12s/it]
 99%|█████████▉| 27746/28080 [54:49:19<39:36,  7.12s/it]
                                                        
{'loss': 0.6105, 'learning_rate': 1.854942436820828e-07, 'epoch': 11.85}

 99%|█████████▉| 27746/28080 [54:49:19<39:36,  7.12s/it]
 99%|█████████▉| 27747/28080 [54:49:27<39:34,  7.13s/it]
                                                        
{'loss': 0.5923, 'learning_rate': 1.8438529885067557e-07, 'epoch': 11.85}

 99%|█████████▉| 27747/28080 [54:49:27<39:34,  7.13s/it]
 99%|█████████▉| 27748/28080 [54:49:34<39:34,  7.15s/it]
                                                        
{'loss': 0.5991, 'learning_rate': 1.8327967755829567e-07, 'epoch': 11.85}

 99%|█████████▉| 27748/28080 [54:49:34<39:34,  7.15s/it]
 99%|█████████▉| 27749/28080 [54:49:41<39:31,  7.16s/it]
                                                        
{'loss': 0.607, 'learning_rate': 1.8217737981965354e-07, 'epoch': 11.85}

 99%|█████████▉| 27749/28080 [54:49:41<39:31,  7.16s/it]
 99%|█████████▉| 27750/28080 [54:49:48<39:04,  7.11s/it]
                                                        
{'loss': 0.615, 'learning_rate': 1.810784056494319e-07, 'epoch': 11.85}

 99%|█████████▉| 27750/28080 [54:49:48<39:04,  7.11s/it]
 99%|█████████▉| 27751/28080 [54:49:55<38:57,  7.10s/it]
                                                        
{'loss': 0.5821, 'learning_rate': 1.7998275506223018e-07, 'epoch': 11.85}

 99%|█████████▉| 27751/28080 [54:49:55<38:57,  7.10s/it]
 99%|█████████▉| 27752/28080 [54:50:02<39:01,  7.14s/it]
                                                        
{'loss': 0.5801, 'learning_rate': 1.7889042807264777e-07, 'epoch': 11.86}

 99%|█████████▉| 27752/28080 [54:50:02<39:01,  7.14s/it]
 99%|█████████▉| 27753/28080 [54:50:09<38:56,  7.15s/it]
                                                        
{'loss': 0.5944, 'learning_rate': 1.7780142469517314e-07, 'epoch': 11.86}

 99%|█████████▉| 27753/28080 [54:50:09<38:56,  7.15s/it]
 99%|█████████▉| 27754/28080 [54:50:17<38:50,  7.15s/it]
                                                        
{'loss': 0.5972, 'learning_rate': 1.7671574494435015e-07, 'epoch': 11.86}

 99%|█████████▉| 27754/28080 [54:50:17<38:50,  7.15s/it]
 99%|█████████▉| 27755/28080 [54:50:24<38:46,  7.16s/it]
                                                        
{'loss': 0.5861, 'learning_rate': 1.7563338883458402e-07, 'epoch': 11.86}

 99%|█████████▉| 27755/28080 [54:50:24<38:46,  7.16s/it]
 99%|█████████▉| 27756/28080 [54:50:31<38:33,  7.14s/it]
                                                        
{'loss': 0.5966, 'learning_rate': 1.7455435638027985e-07, 'epoch': 11.86}

 99%|█████████▉| 27756/28080 [54:50:31<38:33,  7.14s/it]
 99%|█████████▉| 27757/28080 [54:50:38<38:21,  7.13s/it]
                                                        
{'loss': 0.5961, 'learning_rate': 1.73478647595815e-07, 'epoch': 11.86}

 99%|█████████▉| 27757/28080 [54:50:38<38:21,  7.13s/it]
 99%|█████████▉| 27758/28080 [54:50:45<38:21,  7.15s/it]
                                                        
{'loss': 0.5908, 'learning_rate': 1.7240626249545587e-07, 'epoch': 11.86}

 99%|█████████▉| 27758/28080 [54:50:45<38:21,  7.15s/it]
 99%|█████████▉| 27759/28080 [54:50:52<38:12,  7.14s/it]
                                                        
{'loss': 0.6058, 'learning_rate': 1.7133720109352436e-07, 'epoch': 11.86}

 99%|█████████▉| 27759/28080 [54:50:52<38:12,  7.14s/it]
 99%|█████████▉| 27760/28080 [54:50:59<38:07,  7.15s/it]
                                                        
{'loss': 0.5815, 'learning_rate': 1.7027146340420353e-07, 'epoch': 11.86}

 99%|█████████▉| 27760/28080 [54:50:59<38:07,  7.15s/it]
 99%|█████████▉| 27761/28080 [54:51:07<37:55,  7.13s/it]
                                                        
{'loss': 0.6008, 'learning_rate': 1.6920904944170424e-07, 'epoch': 11.86}

 99%|█████████▉| 27761/28080 [54:51:07<37:55,  7.13s/it]
 99%|█████████▉| 27762/28080 [54:51:14<37:50,  7.14s/it]
                                                        
{'loss': 0.6111, 'learning_rate': 1.6814995922012633e-07, 'epoch': 11.86}

 99%|█████████▉| 27762/28080 [54:51:14<37:50,  7.14s/it]
 99%|█████████▉| 27763/28080 [54:51:21<37:52,  7.17s/it]
                                                        
{'loss': 0.5913, 'learning_rate': 1.6709419275356962e-07, 'epoch': 11.86}

 99%|█████████▉| 27763/28080 [54:51:21<37:52,  7.17s/it]
 99%|█████████▉| 27764/28080 [54:51:28<37:46,  7.17s/it]
                                                        
{'loss': 0.606, 'learning_rate': 1.660417500561062e-07, 'epoch': 11.86}

 99%|█████████▉| 27764/28080 [54:51:28<37:46,  7.17s/it]
 99%|█████████▉| 27765/28080 [54:51:35<37:37,  7.17s/it]
                                                        
{'loss': 0.6287, 'learning_rate': 1.649926311417249e-07, 'epoch': 11.86}

 99%|█████████▉| 27765/28080 [54:51:35<37:37,  7.17s/it]
 99%|█████████▉| 27766/28080 [54:51:42<37:27,  7.16s/it]
                                                        
{'loss': 0.5906, 'learning_rate': 1.63946836024359e-07, 'epoch': 11.86}

 99%|█████████▉| 27766/28080 [54:51:42<37:27,  7.16s/it]
 99%|█████████▉| 27767/28080 [54:51:50<37:18,  7.15s/it]
                                                        
{'loss': 0.6221, 'learning_rate': 1.629043647179418e-07, 'epoch': 11.86}

 99%|█████████▉| 27767/28080 [54:51:50<37:18,  7.15s/it]
 99%|█████████▉| 27768/28080 [54:51:57<37:07,  7.14s/it]
                                                        
{'loss': 0.599, 'learning_rate': 1.618652172363233e-07, 'epoch': 11.86}

 99%|█████████▉| 27768/28080 [54:51:57<37:07,  7.14s/it]
 99%|█████████▉| 27769/28080 [54:52:04<37:00,  7.14s/it]
                                                        
{'loss': 0.6216, 'learning_rate': 1.6082939359335358e-07, 'epoch': 11.86}

 99%|█████████▉| 27769/28080 [54:52:04<37:00,  7.14s/it]
 99%|█████████▉| 27770/28080 [54:52:11<36:47,  7.12s/it]
                                                        
{'loss': 0.5841, 'learning_rate': 1.5979689380282714e-07, 'epoch': 11.86}

 99%|█████████▉| 27770/28080 [54:52:11<36:47,  7.12s/it]
 99%|█████████▉| 27771/28080 [54:52:18<36:38,  7.11s/it]
                                                        
{'loss': 0.6025, 'learning_rate': 1.5876771787842747e-07, 'epoch': 11.86}

 99%|█████████▉| 27771/28080 [54:52:18<36:38,  7.11s/it]
 99%|█████████▉| 27772/28080 [54:52:25<36:35,  7.13s/it]
                                                        
{'loss': 0.5948, 'learning_rate': 1.577418658338936e-07, 'epoch': 11.86}

 99%|█████████▉| 27772/28080 [54:52:25<36:35,  7.13s/it]
 99%|█████████▉| 27773/28080 [54:52:32<36:25,  7.12s/it]
                                                        
{'loss': 0.5843, 'learning_rate': 1.5671933768285352e-07, 'epoch': 11.86}

 99%|█████████▉| 27773/28080 [54:52:32<36:25,  7.12s/it]
 99%|█████████▉| 27774/28080 [54:52:39<36:24,  7.14s/it]
                                                        
{'loss': 0.6149, 'learning_rate': 1.5570013343890744e-07, 'epoch': 11.86}

 99%|█████████▉| 27774/28080 [54:52:39<36:24,  7.14s/it]
 99%|█████████▉| 27775/28080 [54:52:47<36:23,  7.16s/it]
                                                        
{'loss': 0.5918, 'learning_rate': 1.5468425311562783e-07, 'epoch': 11.87}

 99%|█████████▉| 27775/28080 [54:52:47<36:23,  7.16s/it]
 99%|█████████▉| 27776/28080 [54:52:54<36:12,  7.15s/it]
                                                        
{'loss': 0.5835, 'learning_rate': 1.536716967265317e-07, 'epoch': 11.87}

 99%|█████████▉| 27776/28080 [54:52:54<36:12,  7.15s/it]
 99%|█████████▉| 27777/28080 [54:53:01<36:07,  7.15s/it]
                                                        
{'loss': 0.6024, 'learning_rate': 1.526624642850527e-07, 'epoch': 11.87}

 99%|█████████▉| 27777/28080 [54:53:01<36:07,  7.15s/it]
 99%|█████████▉| 27778/28080 [54:53:08<35:59,  7.15s/it]
                                                        
{'loss': 0.5984, 'learning_rate': 1.5165655580468008e-07, 'epoch': 11.87}

 99%|█████████▉| 27778/28080 [54:53:08<35:59,  7.15s/it]
 99%|█████████▉| 27779/28080 [54:53:15<35:51,  7.15s/it]
                                                        
{'loss': 0.5904, 'learning_rate': 1.5065397129873647e-07, 'epoch': 11.87}

 99%|█████████▉| 27779/28080 [54:53:15<35:51,  7.15s/it]
 99%|█████████▉| 27780/28080 [54:53:22<35:43,  7.15s/it]
                                                        
{'loss': 0.5999, 'learning_rate': 1.496547107806001e-07, 'epoch': 11.87}

 99%|█████████▉| 27780/28080 [54:53:22<35:43,  7.15s/it]
 99%|█████████▉| 27781/28080 [54:53:29<35:36,  7.14s/it]
                                                        
{'loss': 0.5983, 'learning_rate': 1.4865877426356588e-07, 'epoch': 11.87}

 99%|█████████▉| 27781/28080 [54:53:29<35:36,  7.14s/it]
 99%|█████████▉| 27782/28080 [54:53:37<35:30,  7.15s/it]
                                                        
{'loss': 0.5942, 'learning_rate': 1.4766616176084546e-07, 'epoch': 11.87}

 99%|█████████▉| 27782/28080 [54:53:37<35:30,  7.15s/it]
 99%|█████████▉| 27783/28080 [54:53:44<35:24,  7.15s/it]
                                                        
{'loss': 0.5902, 'learning_rate': 1.4667687328567825e-07, 'epoch': 11.87}

 99%|█████████▉| 27783/28080 [54:53:44<35:24,  7.15s/it]
 99%|█████████▉| 27784/28080 [54:53:51<35:15,  7.15s/it]
                                                        
{'loss': 0.5754, 'learning_rate': 1.4569090885119263e-07, 'epoch': 11.87}

 99%|█████████▉| 27784/28080 [54:53:51<35:15,  7.15s/it]
 99%|█████████▉| 27785/28080 [54:53:58<35:05,  7.14s/it]
                                                        
{'loss': 0.5982, 'learning_rate': 1.447082684705725e-07, 'epoch': 11.87}

 99%|█████████▉| 27785/28080 [54:53:58<35:05,  7.14s/it]
 99%|█████████▉| 27786/28080 [54:54:05<35:01,  7.15s/it]
                                                        
{'loss': 0.5809, 'learning_rate': 1.437289521568075e-07, 'epoch': 11.87}

 99%|█████████▉| 27786/28080 [54:54:05<35:01,  7.15s/it]
 99%|█████████▉| 27787/28080 [54:54:12<34:58,  7.16s/it]
                                                        
{'loss': 0.6055, 'learning_rate': 1.427529599229982e-07, 'epoch': 11.87}

 99%|█████████▉| 27787/28080 [54:54:12<34:58,  7.16s/it]
 99%|█████████▉| 27788/28080 [54:54:20<35:02,  7.20s/it]
                                                        
{'loss': 0.5903, 'learning_rate': 1.4178029178207874e-07, 'epoch': 11.87}

 99%|█████████▉| 27788/28080 [54:54:20<35:02,  7.20s/it]
 99%|█████████▉| 27789/28080 [54:54:27<34:52,  7.19s/it]
                                                        
{'loss': 0.5826, 'learning_rate': 1.4081094774701098e-07, 'epoch': 11.87}

 99%|█████████▉| 27789/28080 [54:54:27<34:52,  7.19s/it]
 99%|█████████▉| 27790/28080 [54:54:34<34:39,  7.17s/it]
                                                        
{'loss': 0.5961, 'learning_rate': 1.3984492783067348e-07, 'epoch': 11.87}

 99%|█████████▉| 27790/28080 [54:54:34<34:39,  7.17s/it]
 99%|█████████▉| 27791/28080 [54:54:41<34:27,  7.15s/it]
                                                        
{'loss': 0.6079, 'learning_rate': 1.3888223204597261e-07, 'epoch': 11.87}

 99%|█████████▉| 27791/28080 [54:54:41<34:27,  7.15s/it]
 99%|█████████▉| 27792/28080 [54:54:48<34:20,  7.15s/it]
                                                        
{'loss': 0.5986, 'learning_rate': 1.3792286040564816e-07, 'epoch': 11.87}

 99%|█████████▉| 27792/28080 [54:54:48<34:20,  7.15s/it]
 99%|█████████▉| 27793/28080 [54:54:55<34:16,  7.16s/it]
                                                        
{'loss': 0.6137, 'learning_rate': 1.3696681292249547e-07, 'epoch': 11.87}

 99%|█████████▉| 27793/28080 [54:54:55<34:16,  7.16s/it]
 99%|█████████▉| 27794/28080 [54:55:03<34:03,  7.15s/it]
                                                        
{'loss': 0.5902, 'learning_rate': 1.3601408960922656e-07, 'epoch': 11.87}

 99%|█████████▉| 27794/28080 [54:55:03<34:03,  7.15s/it]
 99%|█████████▉| 27795/28080 [54:55:10<33:57,  7.15s/it]
                                                        
{'loss': 0.6024, 'learning_rate': 1.3506469047852577e-07, 'epoch': 11.87}

 99%|█████████▉| 27795/28080 [54:55:10<33:57,  7.15s/it]
 99%|█████████▉| 27796/28080 [54:55:17<33:53,  7.16s/it]
                                                        
{'loss': 0.5911, 'learning_rate': 1.3411861554302186e-07, 'epoch': 11.87}

 99%|█████████▉| 27796/28080 [54:55:17<33:53,  7.16s/it]
 99%|█████████▉| 27797/28080 [54:55:24<33:45,  7.16s/it]
                                                        
{'loss': 0.5908, 'learning_rate': 1.331758648152881e-07, 'epoch': 11.87}

 99%|█████████▉| 27797/28080 [54:55:24<33:45,  7.16s/it]
 99%|█████████▉| 27798/28080 [54:55:31<33:38,  7.16s/it]
                                                        
{'loss': 0.5961, 'learning_rate': 1.3223643830787003e-07, 'epoch': 11.88}

 99%|█████████▉| 27798/28080 [54:55:31<33:38,  7.16s/it]
 99%|█████████▉| 27799/28080 [54:55:38<33:24,  7.13s/it]
                                                        
{'loss': 0.5829, 'learning_rate': 1.313003360332854e-07, 'epoch': 11.88}

 99%|█████████▉| 27799/28080 [54:55:38<33:24,  7.13s/it]
 99%|█████████▉| 27800/28080 [54:55:45<33:11,  7.11s/it]
                                                        
{'loss': 0.5759, 'learning_rate': 1.3036755800396872e-07, 'epoch': 11.88}

 99%|█████████▉| 27800/28080 [54:55:45<33:11,  7.11s/it]
 99%|█████████▉| 27801/28080 [54:55:52<33:04,  7.11s/it]
                                                        
{'loss': 0.5822, 'learning_rate': 1.2943810423232672e-07, 'epoch': 11.88}

 99%|█████████▉| 27801/28080 [54:55:52<33:04,  7.11s/it]
 99%|█████████▉| 27802/28080 [54:55:59<32:47,  7.08s/it]
                                                        
{'loss': 0.5978, 'learning_rate': 1.2851197473073839e-07, 'epoch': 11.88}

 99%|█████████▉| 27802/28080 [54:55:59<32:47,  7.08s/it]
 99%|█████████▉| 27803/28080 [54:56:07<32:53,  7.12s/it]
                                                        
{'loss': 0.5993, 'learning_rate': 1.2758916951152722e-07, 'epoch': 11.88}

 99%|█████████▉| 27803/28080 [54:56:07<32:53,  7.12s/it]
 99%|█████████▉| 27804/28080 [54:56:14<32:43,  7.11s/it]
                                                        
{'loss': 0.5841, 'learning_rate': 1.2666968858696116e-07, 'epoch': 11.88}

 99%|█████████▉| 27804/28080 [54:56:14<32:43,  7.11s/it]
 99%|█████████▉| 27805/28080 [54:56:21<32:40,  7.13s/it]
                                                        
{'loss': 0.5644, 'learning_rate': 1.2575353196928042e-07, 'epoch': 11.88}

 99%|█████████▉| 27805/28080 [54:56:21<32:40,  7.13s/it]
 99%|█████████▉| 27806/28080 [54:56:28<32:42,  7.16s/it]
                                                        
{'loss': 0.5884, 'learning_rate': 1.248406996706697e-07, 'epoch': 11.88}

 99%|█████████▉| 27806/28080 [54:56:28<32:42,  7.16s/it]
 99%|█████████▉| 27807/28080 [54:56:35<32:32,  7.15s/it]
                                                        
{'loss': 0.6148, 'learning_rate': 1.2393119170325816e-07, 'epoch': 11.88}

 99%|█████████▉| 27807/28080 [54:56:35<32:32,  7.15s/it]
 99%|█████████▉| 27808/28080 [54:56:42<32:16,  7.12s/it]
                                                        
{'loss': 0.5874, 'learning_rate': 1.2302500807917506e-07, 'epoch': 11.88}

 99%|█████████▉| 27808/28080 [54:56:42<32:16,  7.12s/it]
 99%|█████████▉| 27809/28080 [54:56:49<32:03,  7.10s/it]
                                                        
{'loss': 0.6036, 'learning_rate': 1.2212214881043847e-07, 'epoch': 11.88}

 99%|█████████▉| 27809/28080 [54:56:49<32:03,  7.10s/it]
 99%|█████████▉| 27810/28080 [54:56:56<31:55,  7.10s/it]
                                                        
{'loss': 0.596, 'learning_rate': 1.2122261390912216e-07, 'epoch': 11.88}

 99%|█████████▉| 27810/28080 [54:56:56<31:55,  7.10s/it]
 99%|█████████▉| 27811/28080 [54:57:04<31:51,  7.11s/it]
                                                        
{'loss': 0.6058, 'learning_rate': 1.2032640338710543e-07, 'epoch': 11.88}

 99%|█████████▉| 27811/28080 [54:57:04<31:51,  7.11s/it]
 99%|█████████▉| 27812/28080 [54:57:11<31:45,  7.11s/it]
                                                        
{'loss': 0.5999, 'learning_rate': 1.1943351725637875e-07, 'epoch': 11.88}

 99%|█████████▉| 27812/28080 [54:57:11<31:45,  7.11s/it]
 99%|█████████▉| 27813/28080 [54:57:18<31:32,  7.09s/it]
                                                        
{'loss': 0.5866, 'learning_rate': 1.1854395552882146e-07, 'epoch': 11.88}

 99%|█████████▉| 27813/28080 [54:57:18<31:32,  7.09s/it]
 99%|█████████▉| 27814/28080 [54:57:25<31:30,  7.11s/it]
                                                        
{'loss': 0.5913, 'learning_rate': 1.1765771821622973e-07, 'epoch': 11.88}

 99%|█████████▉| 27814/28080 [54:57:25<31:30,  7.11s/it]
 99%|█████████▉| 27815/28080 [54:57:32<31:15,  7.08s/it]
                                                        
{'loss': 0.6071, 'learning_rate': 1.1677480533039963e-07, 'epoch': 11.88}

 99%|█████████▉| 27815/28080 [54:57:32<31:15,  7.08s/it]
 99%|█████████▉| 27816/28080 [54:57:39<31:15,  7.10s/it]
                                                        
{'loss': 0.6058, 'learning_rate': 1.1589521688309957e-07, 'epoch': 11.88}

 99%|█████████▉| 27816/28080 [54:57:39<31:15,  7.10s/it]
 99%|█████████▉| 27817/28080 [54:57:46<31:13,  7.12s/it]
                                                        
{'loss': 0.5929, 'learning_rate': 1.1501895288604237e-07, 'epoch': 11.88}

 99%|█████████▉| 27817/28080 [54:57:46<31:13,  7.12s/it]
 99%|█████████▉| 27818/28080 [54:57:53<31:11,  7.14s/it]
                                                        
{'loss': 0.5855, 'learning_rate': 1.1414601335085762e-07, 'epoch': 11.88}

 99%|█████████▉| 27818/28080 [54:57:53<31:11,  7.14s/it]
 99%|█████████▉| 27819/28080 [54:58:01<31:03,  7.14s/it]
                                                        
{'loss': 0.5814, 'learning_rate': 1.1327639828914715e-07, 'epoch': 11.88}

 99%|█████████▉| 27819/28080 [54:58:01<31:03,  7.14s/it]
 99%|█████████▉| 27820/28080 [54:58:08<30:51,  7.12s/it]
                                                        
{'loss': 0.5897, 'learning_rate': 1.1241010771251282e-07, 'epoch': 11.88}

 99%|█████████▉| 27820/28080 [54:58:08<30:51,  7.12s/it]
 99%|█████████▉| 27821/28080 [54:58:15<30:47,  7.13s/it]
                                                        
{'loss': 0.6233, 'learning_rate': 1.1154714163247314e-07, 'epoch': 11.88}

 99%|█████████▉| 27821/28080 [54:58:15<30:47,  7.13s/it]
 99%|█████████▉| 27822/28080 [54:58:22<30:36,  7.12s/it]
                                                        
{'loss': 0.6038, 'learning_rate': 1.1068750006049122e-07, 'epoch': 11.89}

 99%|█████████▉| 27822/28080 [54:58:22<30:36,  7.12s/it]
 99%|█████████▉| 27823/28080 [54:58:29<30:33,  7.13s/it]
                                                        
{'loss': 0.5782, 'learning_rate': 1.0983118300803007e-07, 'epoch': 11.89}

 99%|█████████▉| 27823/28080 [54:58:29<30:33,  7.13s/it]
 99%|█████████▉| 27824/28080 [54:58:36<30:29,  7.15s/it]
                                                        
{'loss': 0.5768, 'learning_rate': 1.0897819048646951e-07, 'epoch': 11.89}

 99%|█████████▉| 27824/28080 [54:58:36<30:29,  7.15s/it]
 99%|█████████▉| 27825/28080 [54:58:43<30:23,  7.15s/it]
                                                        
{'loss': 0.5731, 'learning_rate': 1.0812852250713378e-07, 'epoch': 11.89}

 99%|█████████▉| 27825/28080 [54:58:43<30:23,  7.15s/it]
 99%|█████████▉| 27826/28080 [54:58:50<30:10,  7.13s/it]
                                                        
{'loss': 0.5833, 'learning_rate': 1.0728217908134719e-07, 'epoch': 11.89}

 99%|█████████▉| 27826/28080 [54:58:51<30:10,  7.13s/it]
 99%|█████████▉| 27827/28080 [54:58:58<30:09,  7.15s/it]
                                                        
{'loss': 0.5999, 'learning_rate': 1.0643916022040623e-07, 'epoch': 11.89}

 99%|█████████▉| 27827/28080 [54:58:58<30:09,  7.15s/it]
 99%|█████████▉| 27828/28080 [54:59:05<30:05,  7.17s/it]
                                                        
{'loss': 0.6018, 'learning_rate': 1.0559946593546865e-07, 'epoch': 11.89}

 99%|█████████▉| 27828/28080 [54:59:05<30:05,  7.17s/it]
 99%|█████████▉| 27829/28080 [54:59:12<29:56,  7.16s/it]
                                                        
{'loss': 0.5881, 'learning_rate': 1.0476309623771996e-07, 'epoch': 11.89}

 99%|█████████▉| 27829/28080 [54:59:12<29:56,  7.16s/it]
 99%|█████████▉| 27830/28080 [54:59:19<29:51,  7.16s/it]
                                                        
{'loss': 0.5974, 'learning_rate': 1.0393005113831788e-07, 'epoch': 11.89}

 99%|█████████▉| 27830/28080 [54:59:19<29:51,  7.16s/it]
 99%|█████████▉| 27831/28080 [54:59:26<29:37,  7.14s/it]
                                                        
{'loss': 0.5874, 'learning_rate': 1.0310033064830915e-07, 'epoch': 11.89}

 99%|█████████▉| 27831/28080 [54:59:26<29:37,  7.14s/it]
 99%|█████████▉| 27832/28080 [54:59:33<29:28,  7.13s/it]
                                                        
{'loss': 0.5895, 'learning_rate': 1.0227393477874047e-07, 'epoch': 11.89}

 99%|█████████▉| 27832/28080 [54:59:33<29:28,  7.13s/it]
 99%|█████████▉| 27833/28080 [54:59:41<29:21,  7.13s/it]
                                                        
{'loss': 0.6003, 'learning_rate': 1.0145086354063083e-07, 'epoch': 11.89}

 99%|█████████▉| 27833/28080 [54:59:41<29:21,  7.13s/it]
 99%|█████████▉| 27834/28080 [54:59:48<29:14,  7.13s/it]
                                                        
{'loss': 0.6012, 'learning_rate': 1.0063111694488813e-07, 'epoch': 11.89}

 99%|█████████▉| 27834/28080 [54:59:48<29:14,  7.13s/it]
 99%|█████████▉| 27835/28080 [54:59:55<29:05,  7.13s/it]
                                                        
{'loss': 0.5742, 'learning_rate': 9.981469500247587e-08, 'epoch': 11.89}

 99%|█████████▉| 27835/28080 [54:59:55<29:05,  7.13s/it]
 99%|█████████▉| 27836/28080 [55:00:02<29:02,  7.14s/it]
                                                        
{'loss': 0.5759, 'learning_rate': 9.900159772419093e-08, 'epoch': 11.89}

 99%|█████████▉| 27836/28080 [55:00:02<29:02,  7.14s/it]
 99%|█████████▉| 27837/28080 [55:00:09<28:58,  7.15s/it]
                                                        
{'loss': 0.6063, 'learning_rate': 9.819182512088576e-08, 'epoch': 11.89}

 99%|█████████▉| 27837/28080 [55:00:09<28:58,  7.15s/it]
 99%|█████████▉| 27838/28080 [55:00:16<28:55,  7.17s/it]
                                                        
{'loss': 0.5941, 'learning_rate': 9.738537720332952e-08, 'epoch': 11.89}

 99%|█████████▉| 27838/28080 [55:00:16<28:55,  7.17s/it]
 99%|█████████▉| 27839/28080 [55:00:23<28:41,  7.14s/it]
                                                        
{'loss': 0.5957, 'learning_rate': 9.658225398226361e-08, 'epoch': 11.89}

 99%|█████████▉| 27839/28080 [55:00:23<28:41,  7.14s/it]
 99%|█████████▉| 27840/28080 [55:00:31<28:36,  7.15s/it]
                                                        
{'loss': 0.6089, 'learning_rate': 9.578245546834618e-08, 'epoch': 11.89}

 99%|█████████▉| 27840/28080 [55:00:31<28:36,  7.15s/it]
 99%|█████████▉| 27841/28080 [55:00:38<28:28,  7.15s/it]
                                                        
{'loss': 0.579, 'learning_rate': 9.498598167223538e-08, 'epoch': 11.89}

 99%|█████████▉| 27841/28080 [55:00:38<28:28,  7.15s/it]
 99%|█████████▉| 27842/28080 [55:00:45<28:24,  7.16s/it]
                                                        
{'loss': 0.6165, 'learning_rate': 9.419283260450607e-08, 'epoch': 11.89}

 99%|█████████▉| 27842/28080 [55:00:45<28:24,  7.16s/it]
 99%|█████████▉| 27843/28080 [55:00:52<28:10,  7.13s/it]
                                                        
{'loss': 0.6218, 'learning_rate': 9.340300827576088e-08, 'epoch': 11.89}

 99%|█████████▉| 27843/28080 [55:00:52<28:10,  7.13s/it]
 99%|█████████▉| 27844/28080 [55:00:59<28:03,  7.13s/it]
                                                        
{'loss': 0.595, 'learning_rate': 9.261650869646366e-08, 'epoch': 11.89}

 99%|█████████▉| 27844/28080 [55:00:59<28:03,  7.13s/it]
 99%|█████████▉| 27845/28080 [55:01:06<27:59,  7.15s/it]
                                                        
{'loss': 0.6207, 'learning_rate': 9.183333387707827e-08, 'epoch': 11.9}

 99%|█████████▉| 27845/28080 [55:01:06<27:59,  7.15s/it]
 99%|█████████▉| 27846/28080 [55:01:14<27:55,  7.16s/it]
                                                        
{'loss': 0.6008, 'learning_rate': 9.10534838280408e-08, 'epoch': 11.9}

 99%|█████████▉| 27846/28080 [55:01:14<27:55,  7.16s/it]
 99%|█████████▉| 27847/28080 [55:01:21<27:40,  7.13s/it]
                                                        
{'loss': 0.5833, 'learning_rate': 9.027695855970409e-08, 'epoch': 11.9}

 99%|█████████▉| 27847/28080 [55:01:21<27:40,  7.13s/it]
 99%|█████████▉| 27848/28080 [55:01:28<27:33,  7.13s/it]
                                                        
{'loss': 0.6285, 'learning_rate': 8.95037580824487e-08, 'epoch': 11.9}

 99%|█████████▉| 27848/28080 [55:01:28<27:33,  7.13s/it]
 99%|█████████▉| 27849/28080 [55:01:35<27:29,  7.14s/it]
                                                        
{'loss': 0.5903, 'learning_rate': 8.873388240651647e-08, 'epoch': 11.9}

 99%|█████████▉| 27849/28080 [55:01:35<27:29,  7.14s/it]
 99%|█████████▉| 27850/28080 [55:01:42<27:26,  7.16s/it]
                                                        
{'loss': 0.5842, 'learning_rate': 8.79673315421492e-08, 'epoch': 11.9}

 99%|█████████▉| 27850/28080 [55:01:42<27:26,  7.16s/it]
 99%|█████████▉| 27851/28080 [55:01:49<27:20,  7.16s/it]
                                                        
{'loss': 0.5823, 'learning_rate': 8.720410549956092e-08, 'epoch': 11.9}

 99%|█████████▉| 27851/28080 [55:01:49<27:20,  7.16s/it]
 99%|█████████▉| 27852/28080 [55:01:56<27:17,  7.18s/it]
                                                        
{'loss': 0.5837, 'learning_rate': 8.644420428888244e-08, 'epoch': 11.9}

 99%|█████████▉| 27852/28080 [55:01:56<27:17,  7.18s/it]
 99%|█████████▉| 27853/28080 [55:02:04<27:11,  7.19s/it]
                                                        
{'loss': 0.6018, 'learning_rate': 8.568762792027229e-08, 'epoch': 11.9}

 99%|█████████▉| 27853/28080 [55:02:04<27:11,  7.19s/it]
 99%|█████████▉| 27854/28080 [55:02:11<27:02,  7.18s/it]
                                                        
{'loss': 0.5847, 'learning_rate': 8.493437640375023e-08, 'epoch': 11.9}

 99%|█████████▉| 27854/28080 [55:02:11<27:02,  7.18s/it]
 99%|█████████▉| 27855/28080 [55:02:18<26:44,  7.13s/it]
                                                        
{'loss': 0.6068, 'learning_rate': 8.418444974936378e-08, 'epoch': 11.9}

 99%|█████████▉| 27855/28080 [55:02:18<26:44,  7.13s/it]
 99%|█████████▉| 27856/28080 [55:02:25<26:36,  7.13s/it]
                                                        
{'loss': 0.6024, 'learning_rate': 8.34378479670772e-08, 'epoch': 11.9}

 99%|█████████▉| 27856/28080 [55:02:25<26:36,  7.13s/it]
 99%|█████████▉| 27857/28080 [55:02:32<26:27,  7.12s/it]
                                                        
{'loss': 0.6065, 'learning_rate': 8.269457106679923e-08, 'epoch': 11.9}

 99%|█████████▉| 27857/28080 [55:02:32<26:27,  7.12s/it]
 99%|█████████▉| 27858/28080 [55:02:39<26:17,  7.11s/it]
                                                        
{'loss': 0.586, 'learning_rate': 8.195461905849411e-08, 'epoch': 11.9}

 99%|█████████▉| 27858/28080 [55:02:39<26:17,  7.11s/it]
 99%|█████████▉| 27859/28080 [55:02:46<26:11,  7.11s/it]
                                                        
{'loss': 0.5855, 'learning_rate': 8.121799195190404e-08, 'epoch': 11.9}

 99%|█████████▉| 27859/28080 [55:02:46<26:11,  7.11s/it]
 99%|█████████▉| 27860/28080 [55:02:53<26:05,  7.12s/it]
                                                        
{'loss': 0.6099, 'learning_rate': 8.048468975691004e-08, 'epoch': 11.9}

 99%|█████████▉| 27860/28080 [55:02:53<26:05,  7.12s/it]
 99%|█████████▉| 27861/28080 [55:03:01<26:00,  7.13s/it]
                                                        
{'loss': 0.6061, 'learning_rate': 7.975471248325428e-08, 'epoch': 11.9}

 99%|█████████▉| 27861/28080 [55:03:01<26:00,  7.13s/it]
 99%|█████████▉| 27862/28080 [55:03:08<25:55,  7.14s/it]
                                                        
{'loss': 0.605, 'learning_rate': 7.902806014059572e-08, 'epoch': 11.9}

 99%|█████████▉| 27862/28080 [55:03:08<25:55,  7.14s/it]
 99%|█████████▉| 27863/28080 [55:03:15<25:44,  7.12s/it]
                                                        
{'loss': 0.6176, 'learning_rate': 7.830473273867655e-08, 'epoch': 11.9}

 99%|█████████▉| 27863/28080 [55:03:15<25:44,  7.12s/it]
 99%|█████████▉| 27864/28080 [55:03:22<25:41,  7.14s/it]
                                                        
{'loss': 0.5971, 'learning_rate': 7.758473028707247e-08, 'epoch': 11.9}

 99%|█████████▉| 27864/28080 [55:03:22<25:41,  7.14s/it]
 99%|█████████▉| 27865/28080 [55:03:29<25:39,  7.16s/it]
                                                        
{'loss': 0.5885, 'learning_rate': 7.686805279535913e-08, 'epoch': 11.9}

 99%|█████████▉| 27865/28080 [55:03:29<25:39,  7.16s/it]
 99%|█████████▉| 27866/28080 [55:03:36<25:29,  7.15s/it]
                                                        
{'loss': 0.6185, 'learning_rate': 7.615470027308446e-08, 'epoch': 11.9}

 99%|█████████▉| 27866/28080 [55:03:36<25:29,  7.15s/it]
 99%|█████████▉| 27867/28080 [55:03:44<25:27,  7.17s/it]
                                                        
{'loss': 0.5804, 'learning_rate': 7.544467272976862e-08, 'epoch': 11.9}

 99%|█████████▉| 27867/28080 [55:03:44<25:27,  7.17s/it]
 99%|█████████▉| 27868/28080 [55:03:51<25:15,  7.15s/it]
                                                        
{'loss': 0.6063, 'learning_rate': 7.4737970174793e-08, 'epoch': 11.9}

 99%|█████████▉| 27868/28080 [55:03:51<25:15,  7.15s/it]
 99%|█████████▉| 27869/28080 [55:03:58<25:07,  7.15s/it]
                                                        
{'loss': 0.6152, 'learning_rate': 7.403459261762224e-08, 'epoch': 11.91}

 99%|█████████▉| 27869/28080 [55:03:58<25:07,  7.15s/it]
 99%|█████████▉| 27870/28080 [55:04:05<24:59,  7.14s/it]
                                                        
{'loss': 0.5978, 'learning_rate': 7.333454006755446e-08, 'epoch': 11.91}

 99%|█████████▉| 27870/28080 [55:04:05<24:59,  7.14s/it]
 99%|█████████▉| 27871/28080 [55:04:12<24:54,  7.15s/it]
                                                        
{'loss': 0.5801, 'learning_rate': 7.263781253397106e-08, 'epoch': 11.91}

 99%|█████████▉| 27871/28080 [55:04:12<24:54,  7.15s/it]
 99%|█████████▉| 27872/28080 [55:04:19<24:44,  7.14s/it]
                                                        
{'loss': 0.6173, 'learning_rate': 7.194441002608687e-08, 'epoch': 11.91}

 99%|█████████▉| 27872/28080 [55:04:19<24:44,  7.14s/it]
 99%|█████████▉| 27873/28080 [55:04:26<24:34,  7.12s/it]
                                                        
{'loss': 0.6059, 'learning_rate': 7.125433255314451e-08, 'epoch': 11.91}

 99%|█████████▉| 27873/28080 [55:04:26<24:34,  7.12s/it]
 99%|█████████▉| 27874/28080 [55:04:33<24:25,  7.11s/it]
                                                        
{'loss': 0.5882, 'learning_rate': 7.056758012433107e-08, 'epoch': 11.91}

 99%|█████████▉| 27874/28080 [55:04:33<24:25,  7.11s/it]
 99%|█████████▉| 27875/28080 [55:04:41<24:24,  7.14s/it]
                                                        
{'loss': 0.5965, 'learning_rate': 6.988415274877813e-08, 'epoch': 11.91}

 99%|█████████▉| 27875/28080 [55:04:41<24:24,  7.14s/it]
 99%|█████████▉| 27876/28080 [55:04:48<24:18,  7.15s/it]
                                                        
{'loss': 0.5997, 'learning_rate': 6.920405043558952e-08, 'epoch': 11.91}

 99%|█████████▉| 27876/28080 [55:04:48<24:18,  7.15s/it]
 99%|█████████▉| 27877/28080 [55:04:55<24:01,  7.10s/it]
                                                        
{'loss': 0.6077, 'learning_rate': 6.852727319378583e-08, 'epoch': 11.91}

 99%|█████████▉| 27877/28080 [55:04:55<24:01,  7.10s/it]
 99%|█████████▉| 27878/28080 [55:05:02<24:00,  7.13s/it]
                                                        
{'loss': 0.5892, 'learning_rate': 6.785382103238758e-08, 'epoch': 11.91}

 99%|█████████▉| 27878/28080 [55:05:02<24:00,  7.13s/it]
 99%|█████████▉| 27879/28080 [55:05:09<23:46,  7.09s/it]
                                                        
{'loss': 0.6015, 'learning_rate': 6.718369396035984e-08, 'epoch': 11.91}

 99%|█████████▉| 27879/28080 [55:05:09<23:46,  7.09s/it]
 99%|█████████▉| 27880/28080 [55:05:16<23:44,  7.12s/it]
                                                        
{'loss': 0.5754, 'learning_rate': 6.651689198661215e-08, 'epoch': 11.91}

 99%|█████████▉| 27880/28080 [55:05:16<23:44,  7.12s/it]
 99%|█████████▉| 27881/28080 [55:05:23<23:39,  7.13s/it]
                                                        
{'loss': 0.5976, 'learning_rate': 6.585341511999853e-08, 'epoch': 11.91}

 99%|█████████▉| 27881/28080 [55:05:23<23:39,  7.13s/it]
 99%|█████████▉| 27882/28080 [55:05:30<23:29,  7.12s/it]
                                                        
{'loss': 0.6199, 'learning_rate': 6.519326336937304e-08, 'epoch': 11.91}

 99%|█████████▉| 27882/28080 [55:05:30<23:29,  7.12s/it]
 99%|█████████▉| 27883/28080 [55:05:38<23:29,  7.16s/it]
                                                        
{'loss': 0.6016, 'learning_rate': 6.453643674353416e-08, 'epoch': 11.91}

 99%|█████████▉| 27883/28080 [55:05:38<23:29,  7.16s/it]
 99%|█████████▉| 27884/28080 [55:05:45<23:22,  7.15s/it]
                                                        
{'loss': 0.5898, 'learning_rate': 6.388293525116939e-08, 'epoch': 11.91}

 99%|█████████▉| 27884/28080 [55:05:45<23:22,  7.15s/it]
 99%|█████████▉| 27885/28080 [55:05:52<23:11,  7.14s/it]
                                                        
{'loss': 0.5977, 'learning_rate': 6.3232758900994e-08, 'epoch': 11.91}

 99%|█████████▉| 27885/28080 [55:05:52<23:11,  7.14s/it]
 99%|█████████▉| 27886/28080 [55:05:59<23:06,  7.15s/it]
                                                        
{'loss': 0.5812, 'learning_rate': 6.258590770166772e-08, 'epoch': 11.91}

 99%|█████████▉| 27886/28080 [55:05:59<23:06,  7.15s/it]
 99%|█████████▉| 27887/28080 [55:06:06<22:56,  7.13s/it]
                                                        
{'loss': 0.5958, 'learning_rate': 6.194238166179477e-08, 'epoch': 11.91}

 99%|█████████▉| 27887/28080 [55:06:06<22:56,  7.13s/it]
 99%|█████████▉| 27888/28080 [55:06:13<22:49,  7.13s/it]
                                                        
{'loss': 0.5946, 'learning_rate': 6.130218078989613e-08, 'epoch': 11.91}

 99%|█████████▉| 27888/28080 [55:06:13<22:49,  7.13s/it]
 99%|█████████▉| 27889/28080 [55:06:20<22:41,  7.13s/it]
                                                        
{'loss': 0.6115, 'learning_rate': 6.066530509457602e-08, 'epoch': 11.91}

 99%|█████████▉| 27889/28080 [55:06:20<22:41,  7.13s/it]
 99%|█████████▉| 27890/28080 [55:06:27<22:32,  7.12s/it]
                                                        
{'loss': 0.6109, 'learning_rate': 6.003175458421661e-08, 'epoch': 11.91}

 99%|█████████▉| 27890/28080 [55:06:27<22:32,  7.12s/it]
 99%|█████████▉| 27891/28080 [55:06:35<22:30,  7.15s/it]
                                                        
{'loss': 0.5988, 'learning_rate': 5.940152926731113e-08, 'epoch': 11.91}

 99%|█████████▉| 27891/28080 [55:06:35<22:30,  7.15s/it]
 99%|█████████▉| 27892/28080 [55:06:42<22:24,  7.15s/it]
                                                        
{'loss': 0.6085, 'learning_rate': 5.877462915221399e-08, 'epoch': 11.92}

 99%|█████████▉| 27892/28080 [55:06:42<22:24,  7.15s/it]
 99%|█████████▉| 27893/28080 [55:06:49<22:15,  7.14s/it]
                                                        
{'loss': 0.5969, 'learning_rate': 5.815105424725187e-08, 'epoch': 11.92}

 99%|█████████▉| 27893/28080 [55:06:49<22:15,  7.14s/it]
 99%|█████████▉| 27894/28080 [55:06:56<22:10,  7.15s/it]
                                                        
{'loss': 0.6251, 'learning_rate': 5.753080456075144e-08, 'epoch': 11.92}

 99%|█████████▉| 27894/28080 [55:06:56<22:10,  7.15s/it]
 99%|█████████▉| 27895/28080 [55:07:03<22:05,  7.17s/it]
                                                        
{'loss': 0.5972, 'learning_rate': 5.691388010095611e-08, 'epoch': 11.92}

 99%|█████████▉| 27895/28080 [55:07:03<22:05,  7.17s/it]
 99%|█████████▉| 27896/28080 [55:07:11<22:05,  7.21s/it]
                                                        
{'loss': 0.601, 'learning_rate': 5.630028087608152e-08, 'epoch': 11.92}

 99%|█████████▉| 27896/28080 [55:07:11<22:05,  7.21s/it]
 99%|█████████▉| 27897/28080 [55:07:18<21:50,  7.16s/it]
                                                        
{'loss': 0.601, 'learning_rate': 5.569000689426007e-08, 'epoch': 11.92}

 99%|█████████▉| 27897/28080 [55:07:18<21:50,  7.16s/it]
 99%|█████████▉| 27898/28080 [55:07:25<21:41,  7.15s/it]
                                                        
{'loss': 0.6126, 'learning_rate': 5.508305816365189e-08, 'epoch': 11.92}

 99%|█████████▉| 27898/28080 [55:07:25<21:41,  7.15s/it]
 99%|█████████▉| 27899/28080 [55:07:32<21:36,  7.16s/it]
                                                        
{'loss': 0.616, 'learning_rate': 5.447943469227834e-08, 'epoch': 11.92}

 99%|█████████▉| 27899/28080 [55:07:32<21:36,  7.16s/it]
 99%|█████████▉| 27900/28080 [55:07:39<21:23,  7.13s/it]
                                                        
{'loss': 0.5825, 'learning_rate': 5.38791364882163e-08, 'epoch': 11.92}

 99%|█████████▉| 27900/28080 [55:07:39<21:23,  7.13s/it]
 99%|█████████▉| 27901/28080 [55:07:46<21:16,  7.13s/it]
                                                        
{'loss': 0.6065, 'learning_rate': 5.328216355945936e-08, 'epoch': 11.92}

 99%|█████████▉| 27901/28080 [55:07:46<21:16,  7.13s/it]
 99%|█████████▉| 27902/28080 [55:07:53<21:15,  7.16s/it]
                                                        
{'loss': 0.606, 'learning_rate': 5.268851591389012e-08, 'epoch': 11.92}

 99%|█████████▉| 27902/28080 [55:07:53<21:15,  7.16s/it]
 99%|█████████▉| 27903/28080 [55:08:01<21:08,  7.17s/it]
                                                        
{'loss': 0.6038, 'learning_rate': 5.2098193559474427e-08, 'epoch': 11.92}

 99%|█████████▉| 27903/28080 [55:08:01<21:08,  7.17s/it]
 99%|█████████▉| 27904/28080 [55:08:08<20:55,  7.14s/it]
                                                        
{'loss': 0.6018, 'learning_rate': 5.151119650401159e-08, 'epoch': 11.92}

 99%|█████████▉| 27904/28080 [55:08:08<20:55,  7.14s/it]
 99%|█████████▉| 27905/28080 [55:08:15<20:50,  7.14s/it]
                                                        
{'loss': 0.596, 'learning_rate': 5.092752475532869e-08, 'epoch': 11.92}

 99%|█████████▉| 27905/28080 [55:08:15<20:50,  7.14s/it]
 99%|█████████▉| 27906/28080 [55:08:22<20:43,  7.15s/it]
                                                        
{'loss': 0.5886, 'learning_rate': 5.034717832122504e-08, 'epoch': 11.92}

 99%|█████████▉| 27906/28080 [55:08:22<20:43,  7.15s/it]
 99%|█████████▉| 27907/28080 [55:08:29<20:38,  7.16s/it]
                                                        
{'loss': 0.6026, 'learning_rate': 4.9770157209388936e-08, 'epoch': 11.92}

 99%|█████████▉| 27907/28080 [55:08:29<20:38,  7.16s/it]
 99%|█████████▉| 27908/28080 [55:08:36<20:32,  7.17s/it]
                                                        
{'loss': 0.5938, 'learning_rate': 4.919646142748091e-08, 'epoch': 11.92}

 99%|█████████▉| 27908/28080 [55:08:36<20:32,  7.17s/it]
 99%|█████████▉| 27909/28080 [55:08:43<20:23,  7.16s/it]
                                                        
{'loss': 0.6024, 'learning_rate': 4.862609098316151e-08, 'epoch': 11.92}

 99%|█████████▉| 27909/28080 [55:08:43<20:23,  7.16s/it]
 99%|█████████▉| 27910/28080 [55:08:51<20:11,  7.13s/it]
                                                        
{'loss': 0.5897, 'learning_rate': 4.805904588403576e-08, 'epoch': 11.92}

 99%|█████████▉| 27910/28080 [55:08:51<20:11,  7.13s/it]
 99%|█████████▉| 27911/28080 [55:08:58<20:06,  7.14s/it]
                                                        
{'loss': 0.5999, 'learning_rate': 4.749532613759766e-08, 'epoch': 11.92}

 99%|█████████▉| 27911/28080 [55:08:58<20:06,  7.14s/it]
 99%|█████████▉| 27912/28080 [55:09:05<20:00,  7.14s/it]
                                                        
{'loss': 0.5878, 'learning_rate': 4.6934931751368984e-08, 'epoch': 11.92}

 99%|█████████▉| 27912/28080 [55:09:05<20:00,  7.14s/it]
 99%|█████████▉| 27913/28080 [55:09:12<19:51,  7.14s/it]
                                                        
{'loss': 0.5876, 'learning_rate': 4.637786273281597e-08, 'epoch': 11.92}

 99%|█████████▉| 27913/28080 [55:09:12<19:51,  7.14s/it]
 99%|█████████▉| 27914/28080 [55:09:19<19:43,  7.13s/it]
                                                        
{'loss': 0.5891, 'learning_rate': 4.582411908934936e-08, 'epoch': 11.92}

 99%|█████████▉| 27914/28080 [55:09:19<19:43,  7.13s/it]
 99%|█████████▉| 27915/28080 [55:09:26<19:40,  7.16s/it]
                                                        
{'loss': 0.5906, 'learning_rate': 4.527370082832438e-08, 'epoch': 11.93}

 99%|█████████▉| 27915/28080 [55:09:26<19:40,  7.16s/it]
 99%|█████████▉| 27916/28080 [55:09:33<19:32,  7.15s/it]
                                                        
{'loss': 0.6009, 'learning_rate': 4.472660795706851e-08, 'epoch': 11.93}

 99%|█████████▉| 27916/28080 [55:09:33<19:32,  7.15s/it]
 99%|█████████▉| 27917/28080 [55:09:41<19:26,  7.16s/it]
                                                        
{'loss': 0.5711, 'learning_rate': 4.418284048288146e-08, 'epoch': 11.93}

 99%|█████████▉| 27917/28080 [55:09:41<19:26,  7.16s/it]
 99%|█████████▉| 27918/28080 [55:09:48<19:17,  7.15s/it]
                                                        
{'loss': 0.6048, 'learning_rate': 4.3642398412951924e-08, 'epoch': 11.93}

 99%|█████████▉| 27918/28080 [55:09:48<19:17,  7.15s/it]
 99%|█████████▉| 27919/28080 [55:09:55<19:11,  7.15s/it]
                                                        
{'loss': 0.5847, 'learning_rate': 4.310528175449635e-08, 'epoch': 11.93}

 99%|█████████▉| 27919/28080 [55:09:55<19:11,  7.15s/it]
 99%|█████████▉| 27920/28080 [55:10:02<19:02,  7.14s/it]
                                                        
{'loss': 0.5883, 'learning_rate': 4.257149051467568e-08, 'epoch': 11.93}

 99%|█████████▉| 27920/28080 [55:10:02<19:02,  7.14s/it]
 99%|█████████▉| 27921/28080 [55:10:09<18:57,  7.15s/it]
                                                        
{'loss': 0.5953, 'learning_rate': 4.204102470053983e-08, 'epoch': 11.93}

 99%|█████████▉| 27921/28080 [55:10:09<18:57,  7.15s/it]
 99%|█████████▉| 27922/28080 [55:10:16<18:47,  7.13s/it]
                                                        
{'loss': 0.597, 'learning_rate': 4.151388431922198e-08, 'epoch': 11.93}

 99%|█████████▉| 27922/28080 [55:10:16<18:47,  7.13s/it]
 99%|█████████▉| 27923/28080 [55:10:23<18:42,  7.15s/it]
                                                        
{'loss': 0.6024, 'learning_rate': 4.099006937766103e-08, 'epoch': 11.93}

 99%|█████████▉| 27923/28080 [55:10:23<18:42,  7.15s/it]
 99%|█████████▉| 27924/28080 [55:10:31<18:35,  7.15s/it]
                                                        
{'loss': 0.6027, 'learning_rate': 4.0469579882879136e-08, 'epoch': 11.93}

 99%|█████████▉| 27924/28080 [55:10:31<18:35,  7.15s/it]
 99%|█████████▉| 27925/28080 [55:10:38<18:28,  7.15s/it]
                                                        
{'loss': 0.5837, 'learning_rate': 3.995241584175968e-08, 'epoch': 11.93}

 99%|█████████▉| 27925/28080 [55:10:38<18:28,  7.15s/it]
 99%|█████████▉| 27926/28080 [55:10:45<18:22,  7.16s/it]
                                                        
{'loss': 0.6079, 'learning_rate': 3.943857726124156e-08, 'epoch': 11.93}

 99%|█████████▉| 27926/28080 [55:10:45<18:22,  7.16s/it]
 99%|█████████▉| 27927/28080 [55:10:52<18:14,  7.15s/it]
                                                        
{'loss': 0.5985, 'learning_rate': 3.892806414809713e-08, 'epoch': 11.93}

 99%|█████████▉| 27927/28080 [55:10:52<18:14,  7.15s/it]
 99%|█████████▉| 27928/28080 [55:10:59<18:05,  7.14s/it]
                                                        
{'loss': 0.612, 'learning_rate': 3.8420876509126514e-08, 'epoch': 11.93}

 99%|█████████▉| 27928/28080 [55:10:59<18:05,  7.14s/it]
 99%|█████████▉| 27929/28080 [55:11:06<17:55,  7.12s/it]
                                                        
{'loss': 0.5968, 'learning_rate': 3.791701435112982e-08, 'epoch': 11.93}

 99%|█████████▉| 27929/28080 [55:11:06<17:55,  7.12s/it]
 99%|█████████▉| 27930/28080 [55:11:13<17:52,  7.15s/it]
                                                        
{'loss': 0.586, 'learning_rate': 3.741647768076839e-08, 'epoch': 11.93}

 99%|█████████▉| 27930/28080 [55:11:13<17:52,  7.15s/it]
 99%|█████████▉| 27931/28080 [55:11:21<17:40,  7.11s/it]
                                                        
{'loss': 0.6188, 'learning_rate': 3.691926650470356e-08, 'epoch': 11.93}

 99%|█████████▉| 27931/28080 [55:11:21<17:40,  7.11s/it]
 99%|█████████▉| 27932/28080 [55:11:28<17:28,  7.09s/it]
                                                        
{'loss': 0.5881, 'learning_rate': 3.6425380829541167e-08, 'epoch': 11.93}

 99%|█████████▉| 27932/28080 [55:11:28<17:28,  7.09s/it]
 99%|█████████▉| 27933/28080 [55:11:35<17:26,  7.12s/it]
                                                        
{'loss': 0.5925, 'learning_rate': 3.593482066188702e-08, 'epoch': 11.93}

 99%|█████████▉| 27933/28080 [55:11:35<17:26,  7.12s/it]
 99%|█████████▉| 27934/28080 [55:11:42<17:18,  7.12s/it]
                                                        
{'loss': 0.5936, 'learning_rate': 3.544758600823594e-08, 'epoch': 11.93}

 99%|█████████▉| 27934/28080 [55:11:42<17:18,  7.12s/it]
 99%|█████████▉| 27935/28080 [55:11:49<17:09,  7.10s/it]
                                                        
{'loss': 0.5885, 'learning_rate': 3.4963676875082725e-08, 'epoch': 11.93}

 99%|█████████▉| 27935/28080 [55:11:49<17:09,  7.10s/it]
 99%|█████████▉| 27936/28080 [55:11:56<17:04,  7.12s/it]
                                                        
{'loss': 0.6103, 'learning_rate': 3.448309326886667e-08, 'epoch': 11.93}

 99%|█████████▉| 27936/28080 [55:11:56<17:04,  7.12s/it]
 99%|█████████▉| 27937/28080 [55:12:03<17:00,  7.14s/it]
                                                        
{'loss': 0.5981, 'learning_rate': 3.400583519597156e-08, 'epoch': 11.93}

 99%|█████████▉| 27937/28080 [55:12:03<17:00,  7.14s/it]
 99%|█████████▉| 27938/28080 [55:12:10<16:50,  7.12s/it]
                                                        
{'loss': 0.6055, 'learning_rate': 3.353190266275341e-08, 'epoch': 11.93}

 99%|█████████▉| 27938/28080 [55:12:10<16:50,  7.12s/it]
 99%|█████████▉| 27939/28080 [55:12:17<16:44,  7.12s/it]
                                                        
{'loss': 0.5968, 'learning_rate': 3.306129567551275e-08, 'epoch': 11.94}

 99%|█████████▉| 27939/28080 [55:12:17<16:44,  7.12s/it]
100%|█████████▉| 27940/28080 [55:12:25<16:34,  7.11s/it]
                                                        
{'loss': 0.6294, 'learning_rate': 3.259401424052233e-08, 'epoch': 11.94}

100%|█████████▉| 27940/28080 [55:12:25<16:34,  7.11s/it]
100%|█████████▉| 27941/28080 [55:12:32<16:24,  7.09s/it]
                                                        
{'loss': 0.6039, 'learning_rate': 3.21300583639994e-08, 'epoch': 11.94}

100%|█████████▉| 27941/28080 [55:12:32<16:24,  7.09s/it]
100%|█████████▉| 27942/28080 [55:12:39<16:24,  7.14s/it]
                                                        
{'loss': 0.5886, 'learning_rate': 3.1669428052077956e-08, 'epoch': 11.94}

100%|█████████▉| 27942/28080 [55:12:39<16:24,  7.14s/it]
100%|█████████▉| 27943/28080 [55:12:46<16:16,  7.13s/it]
                                                        
{'loss': 0.6011, 'learning_rate': 3.1212123310947474e-08, 'epoch': 11.94}

100%|█████████▉| 27943/28080 [55:12:46<16:16,  7.13s/it]
100%|█████████▉| 27944/28080 [55:12:53<16:08,  7.12s/it]
                                                        
{'loss': 0.6031, 'learning_rate': 3.0758144146658675e-08, 'epoch': 11.94}

100%|█████████▉| 27944/28080 [55:12:53<16:08,  7.12s/it]
100%|█████████▉| 27945/28080 [55:13:00<16:04,  7.14s/it]
                                                        
{'loss': 0.5818, 'learning_rate': 3.030749056523452e-08, 'epoch': 11.94}

100%|█████████▉| 27945/28080 [55:13:00<16:04,  7.14s/it]
100%|█████████▉| 27946/28080 [55:13:07<15:57,  7.15s/it]
                                                        
{'loss': 0.5811, 'learning_rate': 2.9860162572725724e-08, 'epoch': 11.94}

100%|█████████▉| 27946/28080 [55:13:07<15:57,  7.15s/it]
100%|█████████▉| 27947/28080 [55:13:14<15:47,  7.13s/it]
                                                        
{'loss': 0.5969, 'learning_rate': 2.941616017501647e-08, 'epoch': 11.94}

100%|█████████▉| 27947/28080 [55:13:14<15:47,  7.13s/it]
100%|█████████▉| 27948/28080 [55:13:22<15:43,  7.14s/it]
                                                        
{'loss': 0.6127, 'learning_rate': 2.8975483378046453e-08, 'epoch': 11.94}

100%|█████████▉| 27948/28080 [55:13:22<15:43,  7.14s/it]
100%|█████████▉| 27949/28080 [55:13:29<15:36,  7.15s/it]
                                                        
{'loss': 0.6194, 'learning_rate': 2.853813218769985e-08, 'epoch': 11.94}

100%|█████████▉| 27949/28080 [55:13:29<15:36,  7.15s/it]
100%|█████████▉| 27950/28080 [55:13:36<15:28,  7.14s/it]
                                                        
{'loss': 0.6069, 'learning_rate': 2.8104106609749825e-08, 'epoch': 11.94}

100%|█████████▉| 27950/28080 [55:13:36<15:28,  7.14s/it]
100%|█████████▉| 27951/28080 [55:13:43<15:18,  7.12s/it]
                                                        
{'loss': 0.606, 'learning_rate': 2.767340664999729e-08, 'epoch': 11.94}

100%|█████████▉| 27951/28080 [55:13:43<15:18,  7.12s/it]
100%|█████████▉| 27952/28080 [55:13:50<15:10,  7.11s/it]
                                                        
{'loss': 0.5955, 'learning_rate': 2.7246032314159896e-08, 'epoch': 11.94}

100%|█████████▉| 27952/28080 [55:13:50<15:10,  7.11s/it]
100%|█████████▉| 27953/28080 [55:13:57<15:01,  7.10s/it]
                                                        
{'loss': 0.5888, 'learning_rate': 2.6821983607955292e-08, 'epoch': 11.94}

100%|█████████▉| 27953/28080 [55:13:57<15:01,  7.10s/it]
100%|█████████▉| 27954/28080 [55:14:04<14:55,  7.10s/it]
                                                        
{'loss': 0.613, 'learning_rate': 2.6401260536990102e-08, 'epoch': 11.94}

100%|█████████▉| 27954/28080 [55:14:04<14:55,  7.10s/it]
100%|█████████▉| 27955/28080 [55:14:11<14:51,  7.13s/it]
                                                        
{'loss': 0.6233, 'learning_rate': 2.5983863106870953e-08, 'epoch': 11.94}

100%|█████████▉| 27955/28080 [55:14:11<14:51,  7.13s/it]
100%|█████████▉| 27956/28080 [55:14:19<14:42,  7.12s/it]
                                                        
{'loss': 0.601, 'learning_rate': 2.5569791323148962e-08, 'epoch': 11.94}

100%|█████████▉| 27956/28080 [55:14:19<14:42,  7.12s/it]
100%|█████████▉| 27957/28080 [55:14:26<14:32,  7.09s/it]
                                                        
{'loss': 0.5934, 'learning_rate': 2.515904519131973e-08, 'epoch': 11.94}

100%|█████████▉| 27957/28080 [55:14:26<14:32,  7.09s/it]
100%|█████████▉| 27958/28080 [55:14:33<14:24,  7.08s/it]
                                                        
{'loss': 0.6026, 'learning_rate': 2.475162471690662e-08, 'epoch': 11.94}

100%|█████████▉| 27958/28080 [55:14:33<14:24,  7.08s/it]
100%|█████████▉| 27959/28080 [55:14:40<14:23,  7.13s/it]
                                                        
{'loss': 0.5972, 'learning_rate': 2.4347529905266452e-08, 'epoch': 11.94}

100%|█████████▉| 27959/28080 [55:14:40<14:23,  7.13s/it]
100%|█████████▉| 27960/28080 [55:14:47<14:14,  7.12s/it]
                                                        
{'loss': 0.6027, 'learning_rate': 2.3946760761783815e-08, 'epoch': 11.94}

100%|█████████▉| 27960/28080 [55:14:47<14:14,  7.12s/it]
100%|█████████▉| 27961/28080 [55:14:54<14:05,  7.10s/it]
                                                        
{'loss': 0.5914, 'learning_rate': 2.354931729181553e-08, 'epoch': 11.94}

100%|█████████▉| 27961/28080 [55:14:54<14:05,  7.10s/it]
100%|█████████▉| 27962/28080 [55:15:01<13:59,  7.12s/it]
                                                        
{'loss': 0.593, 'learning_rate': 2.315519950063516e-08, 'epoch': 11.95}

100%|█████████▉| 27962/28080 [55:15:01<13:59,  7.12s/it]
100%|█████████▉| 27963/28080 [55:15:09<13:58,  7.17s/it]
                                                        
{'loss': 0.5905, 'learning_rate': 2.2764407393488506e-08, 'epoch': 11.95}

100%|█████████▉| 27963/28080 [55:15:09<13:58,  7.17s/it]
100%|█████████▉| 27964/28080 [55:15:16<13:49,  7.15s/it]
                                                        
{'loss': 0.6092, 'learning_rate': 2.237694097559362e-08, 'epoch': 11.95}

100%|█████████▉| 27964/28080 [55:15:16<13:49,  7.15s/it]
100%|█████████▉| 27965/28080 [55:15:23<13:43,  7.16s/it]
                                                        
{'loss': 0.5829, 'learning_rate': 2.199280025205752e-08, 'epoch': 11.95}

100%|█████████▉| 27965/28080 [55:15:23<13:43,  7.16s/it]
100%|█████████▉| 27966/28080 [55:15:30<13:36,  7.17s/it]
                                                        
{'loss': 0.5915, 'learning_rate': 2.1611985228042753e-08, 'epoch': 11.95}

100%|█████████▉| 27966/28080 [55:15:30<13:36,  7.17s/it]
100%|█████████▉| 27967/28080 [55:15:37<13:29,  7.16s/it]
                                                        
{'loss': 0.5975, 'learning_rate': 2.123449590857307e-08, 'epoch': 11.95}

100%|█████████▉| 27967/28080 [55:15:37<13:29,  7.16s/it]
100%|█████████▉| 27968/28080 [55:15:44<13:22,  7.16s/it]
                                                        
{'loss': 0.6095, 'learning_rate': 2.086033229869999e-08, 'epoch': 11.95}

100%|█████████▉| 27968/28080 [55:15:44<13:22,  7.16s/it]
100%|█████████▉| 27969/28080 [55:15:51<13:13,  7.14s/it]
                                                        
{'loss': 0.6005, 'learning_rate': 2.0489494403391763e-08, 'epoch': 11.95}

100%|█████████▉| 27969/28080 [55:15:51<13:13,  7.14s/it]
100%|█████████▉| 27970/28080 [55:15:58<13:03,  7.13s/it]
                                                        
{'loss': 0.611, 'learning_rate': 2.012198222756112e-08, 'epoch': 11.95}

100%|█████████▉| 27970/28080 [55:15:58<13:03,  7.13s/it]
100%|█████████▉| 27971/28080 [55:16:06<12:55,  7.11s/it]
                                                        
{'loss': 0.5879, 'learning_rate': 1.9757795776148556e-08, 'epoch': 11.95}

100%|█████████▉| 27971/28080 [55:16:06<12:55,  7.11s/it]
100%|█████████▉| 27972/28080 [55:16:13<12:50,  7.13s/it]
                                                        
{'loss': 0.5842, 'learning_rate': 1.9396935053955788e-08, 'epoch': 11.95}

100%|█████████▉| 27972/28080 [55:16:13<12:50,  7.13s/it]
100%|█████████▉| 27973/28080 [55:16:20<12:43,  7.13s/it]
                                                        
{'loss': 0.5863, 'learning_rate': 1.903940006578453e-08, 'epoch': 11.95}

100%|█████████▉| 27973/28080 [55:16:20<12:43,  7.13s/it]
100%|█████████▉| 27974/28080 [55:16:27<12:36,  7.14s/it]
                                                        
{'loss': 0.6154, 'learning_rate': 1.8685190816408738e-08, 'epoch': 11.95}

100%|█████████▉| 27974/28080 [55:16:27<12:36,  7.14s/it]
100%|█████████▉| 27975/28080 [55:16:34<12:31,  7.15s/it]
                                                        
{'loss': 0.5874, 'learning_rate': 1.833430731054686e-08, 'epoch': 11.95}

100%|█████████▉| 27975/28080 [55:16:34<12:31,  7.15s/it]
100%|█████████▉| 27976/28080 [55:16:41<12:20,  7.12s/it]
                                                        
{'loss': 0.6047, 'learning_rate': 1.798674955283408e-08, 'epoch': 11.95}

100%|█████████▉| 27976/28080 [55:16:41<12:20,  7.12s/it]
100%|█████████▉| 27977/28080 [55:16:48<12:08,  7.07s/it]
                                                        
{'loss': 0.6196, 'learning_rate': 1.7642517547933334e-08, 'epoch': 11.95}

100%|█████████▉| 27977/28080 [55:16:48<12:08,  7.07s/it]
100%|█████████▉| 27978/28080 [55:16:55<12:04,  7.10s/it]
                                                        
{'loss': 0.6019, 'learning_rate': 1.7301611300396536e-08, 'epoch': 11.95}

100%|█████████▉| 27978/28080 [55:16:55<12:04,  7.10s/it]
100%|█████████▉| 27979/28080 [55:17:03<11:58,  7.11s/it]
                                                        
{'loss': 0.6138, 'learning_rate': 1.69640308147756e-08, 'epoch': 11.95}

100%|█████████▉| 27979/28080 [55:17:03<11:58,  7.11s/it]
100%|█████████▉| 27980/28080 [55:17:10<11:51,  7.11s/it]
                                                        
{'loss': 0.6095, 'learning_rate': 1.6629776095566928e-08, 'epoch': 11.95}

100%|█████████▉| 27980/28080 [55:17:10<11:51,  7.11s/it]
100%|█████████▉| 27981/28080 [55:17:17<11:44,  7.12s/it]
                                                        
{'loss': 0.5977, 'learning_rate': 1.629884714718366e-08, 'epoch': 11.95}

100%|█████████▉| 27981/28080 [55:17:17<11:44,  7.12s/it]
100%|█████████▉| 27982/28080 [55:17:24<11:38,  7.13s/it]
                                                        
{'loss': 0.5776, 'learning_rate': 1.5971243974066686e-08, 'epoch': 11.95}

100%|█████████▉| 27982/28080 [55:17:24<11:38,  7.13s/it]
100%|█████████▉| 27983/28080 [55:17:31<11:32,  7.14s/it]
                                                        
{'loss': 0.5697, 'learning_rate': 1.5646966580545874e-08, 'epoch': 11.95}

100%|█████████▉| 27983/28080 [55:17:31<11:32,  7.14s/it]
100%|█████████▉| 27984/28080 [55:17:38<11:26,  7.15s/it]
                                                        
{'loss': 0.6001, 'learning_rate': 1.5326014970951097e-08, 'epoch': 11.95}

100%|█████████▉| 27984/28080 [55:17:38<11:26,  7.15s/it]
100%|█████████▉| 27985/28080 [55:17:45<11:17,  7.14s/it]
                                                        
{'loss': 0.5983, 'learning_rate': 1.5008389149556713e-08, 'epoch': 11.95}

100%|█████████▉| 27985/28080 [55:17:45<11:17,  7.14s/it]
100%|█████████▉| 27986/28080 [55:17:53<11:12,  7.16s/it]
                                                        
{'loss': 0.5982, 'learning_rate': 1.4694089120553811e-08, 'epoch': 11.96}

100%|█████████▉| 27986/28080 [55:17:53<11:12,  7.16s/it]
100%|█████████▉| 27987/28080 [55:18:00<11:06,  7.17s/it]
                                                        
{'loss': 0.5836, 'learning_rate': 1.4383114888188996e-08, 'epoch': 11.96}

100%|█████████▉| 27987/28080 [55:18:00<11:06,  7.17s/it]
100%|█████████▉| 27988/28080 [55:18:07<10:57,  7.15s/it]
                                                        
{'loss': 0.6179, 'learning_rate': 1.4075466456542341e-08, 'epoch': 11.96}

100%|█████████▉| 27988/28080 [55:18:07<10:57,  7.15s/it]
100%|█████████▉| 27989/28080 [55:18:14<10:51,  7.16s/it]
                                                        
{'loss': 0.5974, 'learning_rate': 1.3771143829721666e-08, 'epoch': 11.96}

100%|█████████▉| 27989/28080 [55:18:14<10:51,  7.16s/it]
100%|█████████▉| 27990/28080 [55:18:21<10:43,  7.15s/it]
                                                        
{'loss': 0.5891, 'learning_rate': 1.3470147011779288e-08, 'epoch': 11.96}

100%|█████████▉| 27990/28080 [55:18:21<10:43,  7.15s/it]
100%|█████████▉| 27991/28080 [55:18:28<10:36,  7.15s/it]
                                                        
{'loss': 0.6088, 'learning_rate': 1.3172476006712008e-08, 'epoch': 11.96}

100%|█████████▉| 27991/28080 [55:18:28<10:36,  7.15s/it]
100%|█████████▉| 27992/28080 [55:18:35<10:27,  7.14s/it]
                                                        
{'loss': 0.5997, 'learning_rate': 1.2878130818516631e-08, 'epoch': 11.96}

100%|█████████▉| 27992/28080 [55:18:35<10:27,  7.14s/it]
100%|█████████▉| 27993/28080 [55:18:43<10:22,  7.16s/it]
                                                        
{'loss': 0.602, 'learning_rate': 1.2587111451051182e-08, 'epoch': 11.96}

100%|█████████▉| 27993/28080 [55:18:43<10:22,  7.16s/it]
100%|█████████▉| 27994/28080 [55:18:50<10:15,  7.16s/it]
                                                        
{'loss': 0.6106, 'learning_rate': 1.2299417908229194e-08, 'epoch': 11.96}

100%|█████████▉| 27994/28080 [55:18:50<10:15,  7.16s/it]
100%|█████████▉| 27995/28080 [55:18:57<10:08,  7.16s/it]
                                                        
{'loss': 0.5899, 'learning_rate': 1.2015050193880938e-08, 'epoch': 11.96}

100%|█████████▉| 27995/28080 [55:18:57<10:08,  7.16s/it]
100%|█████████▉| 27996/28080 [55:19:04<10:01,  7.16s/it]
                                                        
{'loss': 0.617, 'learning_rate': 1.173400831175342e-08, 'epoch': 11.96}

100%|█████████▉| 27996/28080 [55:19:04<10:01,  7.16s/it]
100%|█████████▉| 27997/28080 [55:19:11<09:54,  7.16s/it]
                                                        
{'loss': 0.6076, 'learning_rate': 1.1456292265593638e-08, 'epoch': 11.96}

100%|█████████▉| 27997/28080 [55:19:11<09:54,  7.16s/it]
100%|█████████▉| 27998/28080 [55:19:18<09:46,  7.15s/it]
                                                        
{'loss': 0.6016, 'learning_rate': 1.1181902059148596e-08, 'epoch': 11.96}

100%|█████████▉| 27998/28080 [55:19:18<09:46,  7.15s/it]
100%|█████████▉| 27999/28080 [55:19:26<09:39,  7.15s/it]
                                                        
{'loss': 0.5907, 'learning_rate': 1.0910837695998766e-08, 'epoch': 11.96}

100%|█████████▉| 27999/28080 [55:19:26<09:39,  7.15s/it]
100%|█████████▉| 28000/28080 [55:19:33<09:33,  7.17s/it]
                                                        
{'loss': 0.5933, 'learning_rate': 1.0643099179780124e-08, 'epoch': 11.96}

100%|█████████▉| 28000/28080 [55:19:33<09:33,  7.17s/it]
100%|█████████▉| 28001/28080 [55:19:40<09:23,  7.13s/it]
                                                        
{'loss': 0.6225, 'learning_rate': 1.0378686514073144e-08, 'epoch': 11.96}

100%|█████████▉| 28001/28080 [55:19:40<09:23,  7.13s/it]
100%|█████████▉| 28002/28080 [55:19:47<09:16,  7.13s/it]
                                                        
{'loss': 0.6197, 'learning_rate': 1.0117599702375024e-08, 'epoch': 11.96}

100%|█████████▉| 28002/28080 [55:19:47<09:16,  7.13s/it]
100%|█████████▉| 28003/28080 [55:19:54<09:09,  7.13s/it]
                                                        
{'loss': 0.6082, 'learning_rate': 9.859838748155215e-09, 'epoch': 11.96}

100%|█████████▉| 28003/28080 [55:19:54<09:09,  7.13s/it]
100%|█████████▉| 28004/28080 [55:20:01<09:02,  7.14s/it]
                                                        
{'loss': 0.6006, 'learning_rate': 9.605403654855404e-09, 'epoch': 11.96}

100%|█████████▉| 28004/28080 [55:20:01<09:02,  7.14s/it]
100%|█████████▉| 28005/28080 [55:20:08<08:54,  7.12s/it]
                                                        
{'loss': 0.5997, 'learning_rate': 9.35429442583402e-09, 'epoch': 11.96}

100%|█████████▉| 28005/28080 [55:20:08<08:54,  7.12s/it]
100%|█████████▉| 28006/28080 [55:20:16<08:49,  7.16s/it]
                                                        
{'loss': 0.6045, 'learning_rate': 9.106511064477241e-09, 'epoch': 11.96}

100%|█████████▉| 28006/28080 [55:20:16<08:49,  7.16s/it]
100%|█████████▉| 28007/28080 [55:20:23<08:42,  7.16s/it]
                                                        
{'loss': 0.5981, 'learning_rate': 8.862053574032469e-09, 'epoch': 11.96}

100%|█████████▉| 28007/28080 [55:20:23<08:42,  7.16s/it]
100%|█████████▉| 28008/28080 [55:20:30<08:36,  7.17s/it]
                                                        
{'loss': 0.5987, 'learning_rate': 8.620921957802618e-09, 'epoch': 11.96}

100%|█████████▉| 28008/28080 [55:20:30<08:36,  7.17s/it]
100%|█████████▉| 28009/28080 [55:20:37<08:28,  7.16s/it]
                                                        
{'loss': 0.5954, 'learning_rate': 8.383116218951825e-09, 'epoch': 11.97}

100%|█████████▉| 28009/28080 [55:20:37<08:28,  7.16s/it]
100%|█████████▉| 28010/28080 [55:20:44<08:19,  7.13s/it]
                                                        
{'loss': 0.6093, 'learning_rate': 8.14863636067198e-09, 'epoch': 11.97}

100%|█████████▉| 28010/28080 [55:20:44<08:19,  7.13s/it]
100%|█████████▉| 28011/28080 [55:20:51<08:12,  7.14s/it]
                                                        
{'loss': 0.6227, 'learning_rate': 7.917482386071707e-09, 'epoch': 11.97}

100%|█████████▉| 28011/28080 [55:20:51<08:12,  7.14s/it]
100%|█████████▉| 28012/28080 [55:20:58<08:04,  7.12s/it]
                                                        
{'loss': 0.6001, 'learning_rate': 7.689654298231874e-09, 'epoch': 11.97}

100%|█████████▉| 28012/28080 [55:20:58<08:04,  7.12s/it]
100%|█████████▉| 28013/28080 [55:21:05<07:57,  7.13s/it]
                                                        
{'loss': 0.6019, 'learning_rate': 7.46515210017784e-09, 'epoch': 11.97}

100%|█████████▉| 28013/28080 [55:21:06<07:57,  7.13s/it]
100%|█████████▉| 28014/28080 [55:21:13<07:48,  7.09s/it]
                                                        
{'loss': 0.6097, 'learning_rate': 7.243975794879454e-09, 'epoch': 11.97}

100%|█████████▉| 28014/28080 [55:21:13<07:48,  7.09s/it]
100%|█████████▉| 28015/28080 [55:21:20<07:41,  7.10s/it]
                                                        
{'loss': 0.5907, 'learning_rate': 7.026125385306559e-09, 'epoch': 11.97}

100%|█████████▉| 28015/28080 [55:21:20<07:41,  7.10s/it]
100%|█████████▉| 28016/28080 [55:21:27<07:35,  7.12s/it]
                                                        
{'loss': 0.602, 'learning_rate': 6.8116008743457355e-09, 'epoch': 11.97}

100%|█████████▉| 28016/28080 [55:21:27<07:35,  7.12s/it]
100%|█████████▉| 28017/28080 [55:21:34<07:27,  7.10s/it]
                                                        
{'loss': 0.6024, 'learning_rate': 6.600402264855809e-09, 'epoch': 11.97}

100%|█████████▉| 28017/28080 [55:21:34<07:27,  7.10s/it]
100%|█████████▉| 28018/28080 [55:21:41<07:17,  7.05s/it]
                                                        
{'loss': 0.6109, 'learning_rate': 6.392529559667848e-09, 'epoch': 11.97}

100%|█████████▉| 28018/28080 [55:21:41<07:17,  7.05s/it]
100%|█████████▉| 28019/28080 [55:21:48<07:11,  7.08s/it]
                                                        
{'loss': 0.5869, 'learning_rate': 6.187982761474142e-09, 'epoch': 11.97}

100%|█████████▉| 28019/28080 [55:21:48<07:11,  7.08s/it]
100%|█████████▉| 28020/28080 [55:21:55<07:06,  7.11s/it]
                                                        
{'loss': 0.6084, 'learning_rate': 5.986761873078006e-09, 'epoch': 11.97}

100%|█████████▉| 28020/28080 [55:21:55<07:06,  7.11s/it]
100%|█████████▉| 28021/28080 [55:22:02<07:00,  7.13s/it]
                                                        
{'loss': 0.6014, 'learning_rate': 5.788866897116219e-09, 'epoch': 11.97}

100%|█████████▉| 28021/28080 [55:22:02<07:00,  7.13s/it]
100%|█████████▉| 28022/28080 [55:22:09<06:54,  7.14s/it]
                                                        
{'loss': 0.6077, 'learning_rate': 5.5942978362255595e-09, 'epoch': 11.97}

100%|█████████▉| 28022/28080 [55:22:09<06:54,  7.14s/it]
100%|█████████▉| 28023/28080 [55:22:17<06:46,  7.13s/it]
                                                        
{'loss': 0.6075, 'learning_rate': 5.4030546930150525e-09, 'epoch': 11.97}

100%|█████████▉| 28023/28080 [55:22:17<06:46,  7.13s/it]
100%|█████████▉| 28024/28080 [55:22:24<06:39,  7.14s/it]
                                                        
{'loss': 0.6025, 'learning_rate': 5.215137469982701e-09, 'epoch': 11.97}

100%|█████████▉| 28024/28080 [55:22:24<06:39,  7.14s/it]
100%|█████████▉| 28025/28080 [55:22:31<06:34,  7.17s/it]
                                                        
{'loss': 0.5793, 'learning_rate': 5.0305461696820155e-09, 'epoch': 11.97}

100%|█████████▉| 28025/28080 [55:22:31<06:34,  7.17s/it]
100%|█████████▉| 28026/28080 [55:22:38<06:26,  7.15s/it]
                                                        
{'loss': 0.5966, 'learning_rate': 4.849280794527733e-09, 'epoch': 11.97}

100%|█████████▉| 28026/28080 [55:22:38<06:26,  7.15s/it]
100%|█████████▉| 28027/28080 [55:22:45<06:21,  7.19s/it]
                                                        
{'loss': 0.5958, 'learning_rate': 4.6713413469623435e-09, 'epoch': 11.97}

100%|█████████▉| 28027/28080 [55:22:45<06:21,  7.19s/it]
100%|█████████▉| 28028/28080 [55:22:52<06:13,  7.17s/it]
                                                        
{'loss': 0.5945, 'learning_rate': 4.496727829345071e-09, 'epoch': 11.97}

100%|█████████▉| 28028/28080 [55:22:52<06:13,  7.17s/it]
100%|█████████▉| 28029/28080 [55:23:00<06:06,  7.19s/it]
                                                        
{'loss': 0.5749, 'learning_rate': 4.325440243979628e-09, 'epoch': 11.97}

100%|█████████▉| 28029/28080 [55:23:00<06:06,  7.19s/it]
100%|█████████▉| 28030/28080 [55:23:07<05:58,  7.18s/it]
                                                        
{'loss': 0.6038, 'learning_rate': 4.157478593141972e-09, 'epoch': 11.97}

100%|█████████▉| 28030/28080 [55:23:07<05:58,  7.18s/it]
100%|█████████▉| 28031/28080 [55:23:14<05:53,  7.22s/it]
                                                        
{'loss': 0.6153, 'learning_rate': 3.992842879108061e-09, 'epoch': 11.97}

100%|█████████▉| 28031/28080 [55:23:14<05:53,  7.22s/it]
100%|█████████▉| 28032/28080 [55:23:21<05:45,  7.19s/it]
                                                        
{'loss': 0.5896, 'learning_rate': 3.831533104015073e-09, 'epoch': 11.98}

100%|█████████▉| 28032/28080 [55:23:21<05:45,  7.19s/it]
100%|█████████▉| 28033/28080 [55:23:28<05:37,  7.19s/it]
                                                        
{'loss': 0.587, 'learning_rate': 3.6735492700556985e-09, 'epoch': 11.98}

100%|█████████▉| 28033/28080 [55:23:29<05:37,  7.19s/it]
100%|█████████▉| 28034/28080 [55:23:36<05:28,  7.15s/it]
                                                        
{'loss': 0.5801, 'learning_rate': 3.518891379339362e-09, 'epoch': 11.98}

100%|█████████▉| 28034/28080 [55:23:36<05:28,  7.15s/it]
100%|█████████▉| 28035/28080 [55:23:43<05:22,  7.17s/it]
                                                        
{'loss': 0.6153, 'learning_rate': 3.367559433864464e-09, 'epoch': 11.98}

100%|█████████▉| 28035/28080 [55:23:43<05:22,  7.17s/it]
100%|█████████▉| 28036/28080 [55:23:50<05:13,  7.12s/it]
                                                        
{'loss': 0.614, 'learning_rate': 3.2195534356849186e-09, 'epoch': 11.98}

100%|█████████▉| 28036/28080 [55:23:50<05:13,  7.12s/it]
100%|█████████▉| 28037/28080 [55:23:57<05:06,  7.12s/it]
                                                        
{'loss': 0.5794, 'learning_rate': 3.074873386743615e-09, 'epoch': 11.98}

100%|█████████▉| 28037/28080 [55:23:57<05:06,  7.12s/it]
100%|█████████▉| 28038/28080 [55:24:04<05:00,  7.14s/it]
                                                        
{'loss': 0.5844, 'learning_rate': 2.9335192890111994e-09, 'epoch': 11.98}

100%|█████████▉| 28038/28080 [55:24:04<05:00,  7.14s/it]
100%|█████████▉| 28039/28080 [55:24:11<04:52,  7.13s/it]
                                                        
{'loss': 0.5678, 'learning_rate': 2.7954911443195396e-09, 'epoch': 11.98}

100%|█████████▉| 28039/28080 [55:24:11<04:52,  7.13s/it]
100%|█████████▉| 28040/28080 [55:24:18<04:45,  7.13s/it]
                                                        
{'loss': 0.5948, 'learning_rate': 2.660788954556015e-09, 'epoch': 11.98}

100%|█████████▉| 28040/28080 [55:24:18<04:45,  7.13s/it]
100%|█████████▉| 28041/28080 [55:24:26<04:38,  7.15s/it]
                                                        
{'loss': 0.6066, 'learning_rate': 2.529412721441471e-09, 'epoch': 11.98}

100%|█████████▉| 28041/28080 [55:24:26<04:38,  7.15s/it]
100%|█████████▉| 28042/28080 [55:24:33<04:30,  7.11s/it]
                                                        
{'loss': 0.6007, 'learning_rate': 2.40136244678002e-09, 'epoch': 11.98}

100%|█████████▉| 28042/28080 [55:24:33<04:30,  7.11s/it]
100%|█████████▉| 28043/28080 [55:24:40<04:24,  7.16s/it]
                                                        
{'loss': 0.6028, 'learning_rate': 2.2766381322925078e-09, 'epoch': 11.98}

100%|█████████▉| 28043/28080 [55:24:40<04:24,  7.16s/it]
100%|█████████▉| 28044/28080 [55:24:47<04:17,  7.17s/it]
                                                        
{'loss': 0.6013, 'learning_rate': 2.1552397795610024e-09, 'epoch': 11.98}

100%|█████████▉| 28044/28080 [55:24:47<04:17,  7.17s/it]
100%|█████████▉| 28045/28080 [55:24:54<04:10,  7.16s/it]
                                                        
{'loss': 0.598, 'learning_rate': 2.0371673902785937e-09, 'epoch': 11.98}

100%|█████████▉| 28045/28080 [55:24:54<04:10,  7.16s/it]
100%|█████████▉| 28046/28080 [55:25:01<04:03,  7.15s/it]
                                                        
{'loss': 0.604, 'learning_rate': 1.9224209659718385e-09, 'epoch': 11.98}

100%|█████████▉| 28046/28080 [55:25:01<04:03,  7.15s/it]
100%|█████████▉| 28047/28080 [55:25:08<03:55,  7.13s/it]
                                                        
{'loss': 0.5711, 'learning_rate': 1.811000508167293e-09, 'epoch': 11.98}

100%|█████████▉| 28047/28080 [55:25:08<03:55,  7.13s/it]
100%|█████████▉| 28048/28080 [55:25:15<03:48,  7.13s/it]
                                                        
{'loss': 0.5945, 'learning_rate': 1.7029060183637591e-09, 'epoch': 11.98}

100%|█████████▉| 28048/28080 [55:25:15<03:48,  7.13s/it]
100%|█████████▉| 28049/28080 [55:25:23<03:41,  7.15s/it]
                                                        
{'loss': 0.5969, 'learning_rate': 1.598137498004526e-09, 'epoch': 11.98}

100%|█████████▉| 28049/28080 [55:25:23<03:41,  7.15s/it]
100%|█████████▉| 28050/28080 [55:25:30<03:35,  7.17s/it]
                                                        
{'loss': 0.5871, 'learning_rate': 1.4966949484496173e-09, 'epoch': 11.98}

100%|█████████▉| 28050/28080 [55:25:30<03:35,  7.17s/it]
100%|█████████▉| 28051/28080 [55:25:37<03:26,  7.13s/it]
                                                        
{'loss': 0.599, 'learning_rate': 1.3985783711145673e-09, 'epoch': 11.98}

100%|█████████▉| 28051/28080 [55:25:37<03:26,  7.13s/it]
100%|█████████▉| 28052/28080 [55:25:44<03:19,  7.14s/it]
                                                        
{'loss': 0.5955, 'learning_rate': 1.3037877672206211e-09, 'epoch': 11.98}

100%|█████████▉| 28052/28080 [55:25:44<03:19,  7.14s/it]
100%|█████████▉| 28053/28080 [55:25:51<03:12,  7.12s/it]
                                                        
{'loss': 0.5867, 'learning_rate': 1.2123231381000465e-09, 'epoch': 11.98}

100%|█████████▉| 28053/28080 [55:25:51<03:12,  7.12s/it]
100%|█████████▉| 28054/28080 [55:25:58<03:05,  7.13s/it]
                                                        
{'loss': 0.5962, 'learning_rate': 1.1241844849185779e-09, 'epoch': 11.98}

100%|█████████▉| 28054/28080 [55:25:58<03:05,  7.13s/it]
100%|█████████▉| 28055/28080 [55:26:05<02:58,  7.14s/it]
                                                        
{'loss': 0.6045, 'learning_rate': 1.0393718088697045e-09, 'epoch': 11.98}

100%|█████████▉| 28055/28080 [55:26:05<02:58,  7.14s/it]
100%|█████████▉| 28056/28080 [55:26:13<02:51,  7.14s/it]
                                                        
{'loss': 0.5972, 'learning_rate': 9.578851110914055e-10, 'epoch': 11.99}

100%|█████████▉| 28056/28080 [55:26:13<02:51,  7.14s/it]
100%|█████████▉| 28057/28080 [55:26:20<02:44,  7.15s/it]
                                                        
{'loss': 0.5948, 'learning_rate': 8.79724392666148e-10, 'epoch': 11.99}

100%|█████████▉| 28057/28080 [55:26:20<02:44,  7.15s/it]
100%|█████████▉| 28058/28080 [55:26:27<02:37,  7.17s/it]
                                                        
{'loss': 0.5968, 'learning_rate': 8.048896546208884e-10, 'epoch': 11.99}

100%|█████████▉| 28058/28080 [55:26:27<02:37,  7.17s/it]
100%|█████████▉| 28059/28080 [55:26:34<02:30,  7.15s/it]
                                                        
{'loss': 0.6052, 'learning_rate': 7.333808979548273e-10, 'epoch': 11.99}

100%|█████████▉| 28059/28080 [55:26:34<02:30,  7.15s/it]
100%|█████████▉| 28060/28080 [55:26:41<02:23,  7.16s/it]
                                                        
{'loss': 0.602, 'learning_rate': 6.651981236116544e-10, 'epoch': 11.99}

100%|█████████▉| 28060/28080 [55:26:41<02:23,  7.16s/it]
100%|█████████▉| 28061/28080 [55:26:49<02:16,  7.17s/it]
                                                        
{'loss': 0.6068, 'learning_rate': 6.003413325073037e-10, 'epoch': 11.99}

100%|█████████▉| 28061/28080 [55:26:49<02:16,  7.17s/it]
100%|█████████▉| 28062/28080 [55:26:56<02:08,  7.15s/it]
                                                        
{'loss': 0.5929, 'learning_rate': 5.388105255299536e-10, 'epoch': 11.99}

100%|█████████▉| 28062/28080 [55:26:56<02:08,  7.15s/it]
100%|█████████▉| 28063/28080 [55:27:03<02:01,  7.15s/it]
                                                        
{'loss': 0.5971, 'learning_rate': 4.806057034567601e-10, 'epoch': 11.99}

100%|█████████▉| 28063/28080 [55:27:03<02:01,  7.15s/it]
100%|█████████▉| 28064/28080 [55:27:10<01:54,  7.17s/it]
                                                        
{'loss': 0.5986, 'learning_rate': 4.257268670648795e-10, 'epoch': 11.99}

100%|█████████▉| 28064/28080 [55:27:10<01:54,  7.17s/it]
100%|█████████▉| 28065/28080 [55:27:17<01:46,  7.13s/it]
                                                        
{'loss': 0.6067, 'learning_rate': 3.741740171314678e-10, 'epoch': 11.99}

100%|█████████▉| 28065/28080 [55:27:17<01:46,  7.13s/it]
100%|█████████▉| 28066/28080 [55:27:24<01:39,  7.13s/it]
                                                        
{'loss': 0.6089, 'learning_rate': 3.2594715429490327e-10, 'epoch': 11.99}

100%|█████████▉| 28066/28080 [55:27:24<01:39,  7.13s/it]
100%|█████████▉| 28067/28080 [55:27:31<01:32,  7.11s/it]
                                                        
{'loss': 0.5899, 'learning_rate': 2.810462791935642e-10, 'epoch': 11.99}

100%|█████████▉| 28067/28080 [55:27:31<01:32,  7.11s/it]
100%|█████████▉| 28068/28080 [55:27:38<01:25,  7.13s/it]
                                                        
{'loss': 0.6172, 'learning_rate': 2.394713924658287e-10, 'epoch': 11.99}

100%|█████████▉| 28068/28080 [55:27:38<01:25,  7.13s/it]
100%|█████████▉| 28069/28080 [55:27:45<01:18,  7.12s/it]
                                                        
{'loss': 0.6128, 'learning_rate': 2.0122249463905284e-10, 'epoch': 11.99}

100%|█████████▉| 28069/28080 [55:27:45<01:18,  7.12s/it]
100%|█████████▉| 28070/28080 [55:27:53<01:11,  7.13s/it]
                                                        
{'loss': 0.6024, 'learning_rate': 1.6629958621283692e-10, 'epoch': 11.99}

100%|█████████▉| 28070/28080 [55:27:53<01:11,  7.13s/it]
100%|█████████▉| 28071/28080 [55:28:00<01:03,  7.10s/it]
                                                        
{'loss': 0.5867, 'learning_rate': 1.3470266765902573e-10, 'epoch': 11.99}

100%|█████████▉| 28071/28080 [55:28:00<01:03,  7.10s/it]
100%|█████████▉| 28072/28080 [55:28:07<00:57,  7.13s/it]
                                                        
{'loss': 0.6154, 'learning_rate': 1.0643173942170847e-10, 'epoch': 11.99}

100%|█████████▉| 28072/28080 [55:28:07<00:57,  7.13s/it]
100%|█████████▉| 28073/28080 [55:28:14<00:50,  7.15s/it]
                                                        
{'loss': 0.5778, 'learning_rate': 8.148680186170765e-11, 'epoch': 11.99}

100%|█████████▉| 28073/28080 [55:28:14<00:50,  7.15s/it]
100%|█████████▉| 28074/28080 [55:28:21<00:42,  7.15s/it]
                                                        
{'loss': 0.6005, 'learning_rate': 5.986785528433458e-11, 'epoch': 11.99}

100%|█████████▉| 28074/28080 [55:28:21<00:42,  7.15s/it]
100%|█████████▉| 28075/28080 [55:28:28<00:35,  7.18s/it]
                                                        
{'loss': 0.623, 'learning_rate': 4.157490002265618e-11, 'epoch': 11.99}

100%|█████████▉| 28075/28080 [55:28:28<00:35,  7.18s/it]
100%|█████████▉| 28076/28080 [55:28:35<00:28,  7.12s/it]
                                                        
{'loss': 0.6036, 'learning_rate': 2.6607936270961476e-11, 'epoch': 11.99}

100%|█████████▉| 28076/28080 [55:28:35<00:28,  7.12s/it]
100%|█████████▉| 28077/28080 [55:28:42<00:21,  7.11s/it]
                                                        
{'loss': 0.6171, 'learning_rate': 1.4966964279050643e-11, 'epoch': 11.99}

100%|█████████▉| 28077/28080 [55:28:43<00:21,  7.11s/it]
100%|█████████▉| 28078/28080 [55:28:50<00:14,  7.13s/it]
                                                        
{'loss': 0.5824, 'learning_rate': 6.651984157945989e-12, 'epoch': 11.99}

100%|█████████▉| 28078/28080 [55:28:50<00:14,  7.13s/it]
100%|█████████▉| 28079/28080 [55:28:57<00:07,  7.13s/it]
                                                        
{'loss': 0.5799, 'learning_rate': 1.6629960464253913e-12, 'epoch': 12.0}

100%|█████████▉| 28079/28080 [55:28:57<00:07,  7.13s/it]
100%|██████████| 28080/28080 [55:29:04<00:00,  7.14s/it]
                                                        
{'loss': 0.6039, 'learning_rate': 0.0, 'epoch': 12.0}

100%|██████████| 28080/28080 [55:29:04<00:00,  7.14s/it]
                                                        
{'train_runtime': 199745.2412, 'train_samples_per_second': 9.0, 'train_steps_per_second': 0.141, 'train_loss': 0.6361451724952782, 'epoch': 12.0}

100%|██████████| 28080/28080 [55:29:04<00:00,  7.14s/it]
100%|██████████| 28080/28080 [55:29:04<00:00,  7.11s/it]